From 4012f93036f249ae31c9aa173a76f557de3e0f1c Mon Sep 17 00:00:00 2001
From: Jason Zeng <jason.zeng@intel.com>
Date: Mon, 14 Sep 2026 19:38:43 -0700
Subject: [PATCH 001/236] Revert "fs/resctrl: Fix double-add of pseudo-locked
 region's RMID to free list"

This reverts commit 84582694ac815387485140037e3789e09832ca5b.
---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 5c993045b1a48..6a433550d9577 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -2921,6 +2921,10 @@ static void rmdir_all_sub(void)
 		if (rdtgrp == &rdtgroup_default)
 			continue;
 
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
+		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
+			rdtgroup_pseudo_lock_remove(rdtgrp);
+
 		/*
 		 * Give any CPUs back to the default group. We cannot copy
 		 * cpu_online_mask because a CPU might have executed the
@@ -2929,13 +2933,7 @@ static void rmdir_all_sub(void)
 		cpumask_or(&rdtgroup_default.cpu_mask,
 			   &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);
 
-		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
-		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
-			rdtgroup_pseudo_lock_remove(rdtgrp);
-		} else {
-			/* Pseudo-locked group's RMID is freed during setup. */
-			free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
-		}
+		free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
 
 		kernfs_remove(rdtgrp->kn);
 		list_del(&rdtgrp->rdtgroup_list);

From 740c636b19e96c36dd5528c24b81a91ee11421fa Mon Sep 17 00:00:00 2001
From: Jason Zeng <jason.zeng@intel.com>
Date: Wed, 29 Apr 2026 03:04:01 -0700
Subject: [PATCH 002/236] Revert "x86/resctrl: Fix miscount of bandwidth event
 when reactivating previously unavailable RMID"

This reverts commit fade7ec254cd3abcd129635e23e2eb9781100dea.

Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/monitor.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 879782df8c1b1..36928b2bfa1f6 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -326,16 +326,12 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
 
 	resctrl_arch_rmid_read_context_check();
 
-	am = get_arch_mbm_state(hw_dom, rmid, eventid);
-
 	prmid = logical_rmid_to_physical_rmid(cpu, rmid);
 	ret = __rmid_read_phys(prmid, eventid, &msr_val);
-	if (ret) {
-		if (am && ret == -EINVAL)
-			am->prev_msr = 0;
+	if (ret)
 		return ret;
-	}
 
+	am = get_arch_mbm_state(hw_dom, rmid, eventid);
 	if (am) {
 		am->chunks += mbm_overflow_count(am->prev_msr, msr_val,
 						 hw_res->mbm_width);

From ac001993b4cace653eef2acfea4f890a2c86e3ff Mon Sep 17 00:00:00 2001
From: Jason Zeng <jason.zeng@intel.com>
Date: Wed, 29 Apr 2026 00:01:27 -0700
Subject: [PATCH 003/236] Revert "fs/resctrl: Eliminate false positive lockdep
 warning when reading SNC counters"

This reverts commit a9db6869b6e9285ef9f374b9ee0b04612a3a543a.

Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 2 +-
 arch/x86/kernel/cpu/resctrl/internal.h    | 4 ++--
 arch/x86/kernel/cpu/resctrl/monitor.c     | 6 ++++--
 3 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 57912f773b7f4..51eee0619ba1b 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -591,11 +591,11 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 		 */
 		list_for_each_entry(d, &r->mon_domains, hdr.list) {
 			if (d->ci_id == domid) {
+				rr.ci_id = d->ci_id;
 				cpu = cpumask_any(&d->hdr.cpu_mask);
 				ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
 				if (!ci)
 					continue;
-				rr.ci = ci;
 				mon_event_read(&rr, r, NULL, rdtgrp,
 					       &ci->shared_cpu_map, evtid, false);
 				goto checkresult;
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 168962166a918..69f6ade543afd 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -163,7 +163,7 @@ union mon_data_bits {
  *	   domains in @r sharing L3 @ci.id
  * @evtid: Which monitor event to read.
  * @first: Initialize MBM counter when true.
- * @ci:    Cacheinfo for L3. Only set when @d is NULL. Used when summing domains.
+ * @ci_id: Cacheinfo id for L3. Only set when @d is NULL. Used when summing domains.
  * @err:   Error encountered when reading counter.
  * @val:   Returned value of event counter. If @rgrp is a parent resource group,
  *	   @val includes the sum of event counts from its child resource groups.
@@ -177,7 +177,7 @@ struct rmid_read {
 	struct rdt_mon_domain	*d;
 	enum resctrl_event_id	evtid;
 	bool			first;
-	struct cacheinfo	*ci;
+	unsigned int		ci_id;
 	int			err;
 	u64			val;
 	void			*arch_mon_ctx;
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 36928b2bfa1f6..3dc9f4bffcc6e 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -594,6 +594,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 {
 	int cpu = smp_processor_id();
 	struct rdt_mon_domain *d;
+	struct cacheinfo *ci;
 	struct mbm_state *m;
 	int err, ret;
 	u64 tval = 0;
@@ -621,7 +622,8 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 	}
 
 	/* Summing domains that share a cache, must be on a CPU for that cache. */
-	if (!cpumask_test_cpu(cpu, &rr->ci->shared_cpu_map))
+	ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
+	if (!ci || ci->id != rr->ci_id)
 		return -EINVAL;
 
 	/*
@@ -633,7 +635,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 	 */
 	ret = -EINVAL;
 	list_for_each_entry(d, &rr->r->mon_domains, hdr.list) {
-		if (d->ci_id != rr->ci->id)
+		if (d->ci_id != rr->ci_id)
 			continue;
 		err = resctrl_arch_rmid_read(rr->r, d, closid, rmid,
 					     rr->evtid, &tval, rr->arch_mon_ctx);

From a3935457d85923031a134ddebc1af8dba65c94f0 Mon Sep 17 00:00:00 2001
From: Jason Zeng <jason.zeng@intel.com>
Date: Wed, 29 Apr 2026 00:01:35 -0700
Subject: [PATCH 004/236] Revert "x86,fs/resctrl: Remove inappropriate
 references to cacheinfo in the resctrl subsystem"

This reverts commit 7821a02561d1d0030b666fa9cf028111ca3a5f9e.

Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c        |  6 ++----
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 15 +++++----------
 arch/x86/kernel/cpu/resctrl/internal.h    |  4 ++--
 arch/x86/kernel/cpu/resctrl/monitor.c     |  6 ++----
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    |  6 +++---
 include/linux/resctrl.h                   |  4 ++--
 6 files changed, 16 insertions(+), 25 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 9d364a91d0bad..b4f19ae107dfd 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -588,7 +588,6 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
 	struct rdt_hw_mon_domain *hw_dom;
 	struct rdt_domain_hdr *hdr;
 	struct rdt_mon_domain *d;
-	struct cacheinfo *ci;
 	int err;
 
 	lockdep_assert_held(&domain_list_lock);
@@ -616,13 +615,12 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
 	d = &hw_dom->d_resctrl;
 	d->hdr.id = id;
 	d->hdr.type = RESCTRL_MON_DOMAIN;
-	ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
-	if (!ci) {
+	d->ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
+	if (!d->ci) {
 		pr_warn_once("Can't find L3 cache for CPU:%d resource %s\n", cpu, r->name);
 		mon_domain_free(hw_dom);
 		return;
 	}
-	d->ci_id = ci->id;
 	cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
 
 	arch_mon_domain_online(r, d);
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 51eee0619ba1b..200d89a640270 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -563,12 +563,11 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 	struct rdt_domain_hdr *hdr;
 	struct rmid_read rr = {0};
 	struct rdt_mon_domain *d;
-	u32 resid, evtid;
+	u32 resid, evtid, domid;
 	struct rdtgroup *rdtgrp;
-	int domid, cpu, ret = 0;
 	struct rdt_resource *r;
-	struct cacheinfo *ci;
 	union mon_data_bits md;
+	int ret = 0;
 
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
 	if (!rdtgrp) {
@@ -590,14 +589,10 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 		 * one that matches this cache id.
 		 */
 		list_for_each_entry(d, &r->mon_domains, hdr.list) {
-			if (d->ci_id == domid) {
-				rr.ci_id = d->ci_id;
-				cpu = cpumask_any(&d->hdr.cpu_mask);
-				ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
-				if (!ci)
-					continue;
+			if (d->ci->id == domid) {
+				rr.ci = d->ci;
 				mon_event_read(&rr, r, NULL, rdtgrp,
-					       &ci->shared_cpu_map, evtid, false);
+					       &d->ci->shared_cpu_map, evtid, false);
 				goto checkresult;
 			}
 		}
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 69f6ade543afd..168962166a918 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -163,7 +163,7 @@ union mon_data_bits {
  *	   domains in @r sharing L3 @ci.id
  * @evtid: Which monitor event to read.
  * @first: Initialize MBM counter when true.
- * @ci_id: Cacheinfo id for L3. Only set when @d is NULL. Used when summing domains.
+ * @ci:    Cacheinfo for L3. Only set when @d is NULL. Used when summing domains.
  * @err:   Error encountered when reading counter.
  * @val:   Returned value of event counter. If @rgrp is a parent resource group,
  *	   @val includes the sum of event counts from its child resource groups.
@@ -177,7 +177,7 @@ struct rmid_read {
 	struct rdt_mon_domain	*d;
 	enum resctrl_event_id	evtid;
 	bool			first;
-	unsigned int		ci_id;
+	struct cacheinfo	*ci;
 	int			err;
 	u64			val;
 	void			*arch_mon_ctx;
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 3dc9f4bffcc6e..39bed483f2bf7 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -594,7 +594,6 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 {
 	int cpu = smp_processor_id();
 	struct rdt_mon_domain *d;
-	struct cacheinfo *ci;
 	struct mbm_state *m;
 	int err, ret;
 	u64 tval = 0;
@@ -622,8 +621,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 	}
 
 	/* Summing domains that share a cache, must be on a CPU for that cache. */
-	ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
-	if (!ci || ci->id != rr->ci_id)
+	if (!cpumask_test_cpu(cpu, &rr->ci->shared_cpu_map))
 		return -EINVAL;
 
 	/*
@@ -635,7 +633,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 	 */
 	ret = -EINVAL;
 	list_for_each_entry(d, &rr->r->mon_domains, hdr.list) {
-		if (d->ci_id != rr->ci_id)
+		if (d->ci->id != rr->ci->id)
 			continue;
 		err = resctrl_arch_rmid_read(rr->r, d, closid, rmid,
 					     rr->evtid, &tval, rr->arch_mon_ctx);
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 6a433550d9577..d7163b764c626 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -3036,7 +3036,7 @@ static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
 	char name[32];
 
 	snc_mode = r->mon_scope == RESCTRL_L3_NODE;
-	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci_id : d->hdr.id);
+	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci->id : d->hdr.id);
 	if (snc_mode)
 		sprintf(subname, "mon_sub_%s_%02d", r->name, d->hdr.id);
 
@@ -3061,7 +3061,7 @@ static int mon_add_all_files(struct kernfs_node *kn, struct rdt_mon_domain *d,
 		return -EPERM;
 
 	priv.u.rid = r->rid;
-	priv.u.domid = do_sum ? d->ci_id : d->hdr.id;
+	priv.u.domid = do_sum ? d->ci->id : d->hdr.id;
 	priv.u.sum = do_sum;
 	list_for_each_entry(mevt, &r->evt_list, list) {
 		priv.u.evtid = mevt->evtid;
@@ -3088,7 +3088,7 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
 	lockdep_assert_held(&rdtgroup_mutex);
 
 	snc_mode = r->mon_scope == RESCTRL_L3_NODE;
-	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci_id : d->hdr.id);
+	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci->id : d->hdr.id);
 	kn = kernfs_find_and_get(parent_kn, name);
 	if (kn) {
 		/*
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index dd2547601921c..d94abba1c716e 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -97,7 +97,7 @@ struct rdt_ctrl_domain {
 /**
  * struct rdt_mon_domain - group of CPUs sharing a resctrl monitor resource
  * @hdr:		common header for different domain types
- * @ci_id:		cache info id for this domain
+ * @ci:			cache info for this domain
  * @rmid_busy_llc:	bitmap of which limbo RMIDs are above threshold
  * @mbm_total:		saved state for MBM total bandwidth
  * @mbm_local:		saved state for MBM local bandwidth
@@ -108,7 +108,7 @@ struct rdt_ctrl_domain {
  */
 struct rdt_mon_domain {
 	struct rdt_domain_hdr		hdr;
-	unsigned int			ci_id;
+	struct cacheinfo		*ci;
 	unsigned long			*rmid_busy_llc;
 	struct mbm_state		*mbm_total;
 	struct mbm_state		*mbm_local;

From 976f470bf9bd1a9936b138d0de465f2972bf0e01 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 24 Apr 2024 11:15:14 -0700
Subject: [PATCH 005/236] x86/resctrl: Switch to new Intel CPU model defines

commit db99675e4338e97e1469aeae5564e8242bd8fd6a upstream.

New CPU #defines encode vendor and family as well as model.

  [ bp: Squash two resctrl patches into one. ]

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/all/20240424181514.41848-1-tony.luck%40intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c        | 10 +++++-----
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 22 +++++++++++-----------
 2 files changed, 16 insertions(+), 16 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index b4f19ae107dfd..8c9c9265752fe 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -21,7 +21,7 @@
 #include <linux/err.h>
 #include <linux/cpuhotplug.h>
 
-#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
 #include <asm/resctrl.h>
 #include "internal.h"
 
@@ -967,18 +967,18 @@ static __init bool get_rdt_mon_resources(void)
 
 static __init void __check_quirks_intel(void)
 {
-	switch (boot_cpu_data.x86_model) {
-	case INTEL_FAM6_HASWELL_X:
+	switch (boot_cpu_data.x86_vfm) {
+	case INTEL_HASWELL_X:
 		if (!rdt_options[RDT_FLAG_L3_CAT].force_off)
 			cache_alloc_hsw_probe();
 		break;
-	case INTEL_FAM6_SKYLAKE_X:
+	case INTEL_SKYLAKE_X:
 		if (boot_cpu_data.x86_stepping <= 4)
 			set_rdt_options("!cmt,!mbmtotal,!mbmlocal,!l3cat");
 		else
 			set_rdt_options("!l3cat");
 		fallthrough;
-	case INTEL_FAM6_BROADWELL_X:
+	case INTEL_BROADWELL_X:
 		intel_rdt_mbm_apply_quirk();
 		break;
 	}
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index 43c65f378998d..c07505991f3fc 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -22,7 +22,7 @@
 #include <linux/uaccess.h>
 
 #include <asm/cacheflush.h>
-#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
 #include <asm/resctrl.h>
 #include <asm/perf_event.h>
 
@@ -87,8 +87,8 @@ static u64 get_prefetch_disable_bits(void)
 	    boot_cpu_data.x86 != 6)
 		return 0;
 
-	switch (boot_cpu_data.x86_model) {
-	case INTEL_FAM6_BROADWELL_X:
+	switch (boot_cpu_data.x86_vfm) {
+	case INTEL_BROADWELL_X:
 		/*
 		 * SDM defines bits of MSR_MISC_FEATURE_CONTROL register
 		 * as:
@@ -99,8 +99,8 @@ static u64 get_prefetch_disable_bits(void)
 		 * 63:4 Reserved
 		 */
 		return 0xF;
-	case INTEL_FAM6_ATOM_GOLDMONT:
-	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
+	case INTEL_ATOM_GOLDMONT:
+	case INTEL_ATOM_GOLDMONT_PLUS:
 		/*
 		 * SDM defines bits of MSR_MISC_FEATURE_CONTROL register
 		 * as:
@@ -1082,9 +1082,9 @@ static int measure_l2_residency(void *_plr)
 	 *     L2_HIT   02H
 	 *     L2_MISS  10H
 	 */
-	switch (boot_cpu_data.x86_model) {
-	case INTEL_FAM6_ATOM_GOLDMONT:
-	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
+	switch (boot_cpu_data.x86_vfm) {
+	case INTEL_ATOM_GOLDMONT:
+	case INTEL_ATOM_GOLDMONT_PLUS:
 		perf_miss_attr.config = X86_CONFIG(.event = 0xd1,
 						   .umask = 0x10);
 		perf_hit_attr.config = X86_CONFIG(.event = 0xd1,
@@ -1121,8 +1121,8 @@ static int measure_l3_residency(void *_plr)
 	 *       MISS      41H
 	 */
 
-	switch (boot_cpu_data.x86_model) {
-	case INTEL_FAM6_BROADWELL_X:
+	switch (boot_cpu_data.x86_vfm) {
+	case INTEL_BROADWELL_X:
 		/* On BDW the hit event counts references, not hits */
 		perf_hit_attr.config = X86_CONFIG(.event = 0x2e,
 						  .umask = 0x4f);
@@ -1140,7 +1140,7 @@ static int measure_l3_residency(void *_plr)
 	 */
 
 	counts.miss_after -= counts.miss_before;
-	if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X) {
+	if (boot_cpu_data.x86_vfm == INTEL_BROADWELL_X) {
 		/*
 		 * On BDW references and misses are counted, need to adjust.
 		 * Sometimes the "hits" counter is a bit more than the

From 242b6f629482772d6a3b7c4b667db0f7b831438e Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sat, 13 Jul 2024 13:02:32 +0200
Subject: [PATCH 006/236] x86/resctrl: Slightly clean-up mbm_config_show()

commit 29eaa79583671f1e1b468760d505ef837317ab15 upstream.

'mon_info' is already zeroed in the list_for_each_entry() loop below.  There
is no need to explicitly initialize it here. It just wastes some space and
cycles.

Remove this un-needed code.

On a x86_64, with allmodconfig:

  Before:
  ======
     text	   data	    bss	    dec	    hex	filename
    74967	   5103	   1880	  81950	  1401e	arch/x86/kernel/cpu/resctrl/rdtgroup.o

  After:
  =====
     text	   data	    bss	    dec	    hex	filename
    74903	   5103	   1880	  81886	  13fde	arch/x86/kernel/cpu/resctrl/rdtgroup.o

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/r/b2ebc809c8b6c6440d17b12ccf7c2d29aaafd488.1720868538.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index d7163b764c626..d906a1cd84917 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -1596,7 +1596,7 @@ static void mondata_config_read(struct rdt_mon_domain *d, struct mon_config_info
 
 static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid)
 {
-	struct mon_config_info mon_info = {0};
+	struct mon_config_info mon_info;
 	struct rdt_mon_domain *dom;
 	bool sep = false;
 

From d8fac8c89f059741b961abea7feb76aa251f0b9e Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Wed, 7 Aug 2024 18:02:08 +0200
Subject: [PATCH 007/236] x86/resctrl: Use kthread_run_on_cpu()

commit 135eef38d7e081303fd9cdb982b37fcad32f9be0 upstream.

Use the proper API instead of open coding it.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Acked-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/r/20240807160228.26206-3-frederic@kernel.org
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 28 +++++++----------------
 1 file changed, 8 insertions(+), 20 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index c07505991f3fc..a11608c5f38b4 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -1205,20 +1205,14 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
 	plr->cpu = cpu;
 
 	if (sel == 1)
-		thread = kthread_create_on_node(measure_cycles_lat_fn, plr,
-						cpu_to_node(cpu),
-						"pseudo_lock_measure/%u",
-						cpu);
+		thread = kthread_run_on_cpu(measure_cycles_lat_fn, plr,
+					    cpu, "pseudo_lock_measure/%u");
 	else if (sel == 2)
-		thread = kthread_create_on_node(measure_l2_residency, plr,
-						cpu_to_node(cpu),
-						"pseudo_lock_measure/%u",
-						cpu);
+		thread = kthread_run_on_cpu(measure_l2_residency, plr,
+					    cpu, "pseudo_lock_measure/%u");
 	else if (sel == 3)
-		thread = kthread_create_on_node(measure_l3_residency, plr,
-						cpu_to_node(cpu),
-						"pseudo_lock_measure/%u",
-						cpu);
+		thread = kthread_run_on_cpu(measure_l3_residency, plr,
+					    cpu, "pseudo_lock_measure/%u");
 	else
 		goto out;
 
@@ -1226,8 +1220,6 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
 		ret = PTR_ERR(thread);
 		goto out;
 	}
-	kthread_bind(thread, cpu);
-	wake_up_process(thread);
 
 	ret = wait_event_interruptible(plr->lock_thread_wq,
 				       plr->thread_done == 1);
@@ -1315,18 +1307,14 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 
 	plr->thread_done = 0;
 
-	thread = kthread_create_on_node(pseudo_lock_fn, rdtgrp,
-					cpu_to_node(plr->cpu),
-					"pseudo_lock/%u", plr->cpu);
+	thread = kthread_run_on_cpu(pseudo_lock_fn, rdtgrp,
+				    plr->cpu, "pseudo_lock/%u");
 	if (IS_ERR(thread)) {
 		ret = PTR_ERR(thread);
 		rdt_last_cmd_printf("Locking thread returned error %d\n", ret);
 		goto out_cstates;
 	}
 
-	kthread_bind(thread, plr->cpu);
-	wake_up_process(thread);
-
 	ret = wait_event_interruptible(plr->lock_thread_wq,
 				       plr->thread_done == 1);
 	if (ret < 0) {

From 4ee6ffc622dbb535eb48eaf9f9b78ccfde92a0c6 Mon Sep 17 00:00:00 2001
From: Babu Moger <babu.moger@amd.com>
Date: Fri, 6 Dec 2024 08:31:41 -0800
Subject: [PATCH 008/236] x86/resctrl: Introduce resctrl_file_fflags_init() to
 initialize fflags

commit 2937f9c361f7a8b230cd599e4af5264798bf4ce7 upstream.

thread_throttle_mode_init() and mbm_config_rftype_init() both initialize
fflags for resctrl files.

Adding new files will involve adding another function to initialize
the fflags. This can be simplified by adding a new function
resctrl_file_fflags_init() and passing the file name and flags
to be initialized.

Consolidate fflags initialization into resctrl_file_fflags_init() and
remove thread_throttle_mode_init() and mbm_config_rftype_init().

  [ Tony: Drop __init attribute so resctrl_file_fflags_init() can be used at
    run time. ]

Signed-off-by: Babu Moger <babu.moger@amd.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/r/20241206163148.83828-2-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c     |  4 +++-
 arch/x86/kernel/cpu/resctrl/internal.h |  3 +--
 arch/x86/kernel/cpu/resctrl/monitor.c  |  6 ++++--
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 15 ++-------------
 4 files changed, 10 insertions(+), 18 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 8c9c9265752fe..f8e704dcb03d9 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -234,7 +234,9 @@ static __init bool __get_mem_config_intel(struct rdt_resource *r)
 		r->membw.throttle_mode = THREAD_THROTTLE_PER_THREAD;
 	else
 		r->membw.throttle_mode = THREAD_THROTTLE_MAX;
-	thread_throttle_mode_init();
+
+	resctrl_file_fflags_init("thread_throttle_mode",
+				 RFTYPE_CTRL_INFO | RFTYPE_RES_MB);
 
 	r->alloc_capable = true;
 
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 168962166a918..021e13d2707f1 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -650,8 +650,7 @@ void cqm_handle_limbo(struct work_struct *work);
 bool has_busy_rmid(struct rdt_mon_domain *d);
 void __check_limbo(struct rdt_mon_domain *d, bool force_free);
 void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
-void __init thread_throttle_mode_init(void);
-void __init mbm_config_rftype_init(const char *config);
+void resctrl_file_fflags_init(const char *config, unsigned long fflags);
 void rdt_staged_configs_clear(void);
 bool closid_allocated(unsigned int closid);
 int resctrl_find_cleanest_closid(void);
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 39bed483f2bf7..fbb3d6bdebc3d 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -1224,11 +1224,13 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 
 		if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) {
 			mbm_total_event.configurable = true;
-			mbm_config_rftype_init("mbm_total_bytes_config");
+			resctrl_file_fflags_init("mbm_total_bytes_config",
+						 RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
 		}
 		if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) {
 			mbm_local_event.configurable = true;
-			mbm_config_rftype_init("mbm_local_bytes_config");
+			resctrl_file_fflags_init("mbm_local_bytes_config",
+						 RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
 		}
 	}
 
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index d906a1cd84917..d333570e893d3 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -2020,24 +2020,13 @@ static struct rftype *rdtgroup_get_rftype_by_name(const char *name)
 	return NULL;
 }
 
-void __init thread_throttle_mode_init(void)
-{
-	struct rftype *rft;
-
-	rft = rdtgroup_get_rftype_by_name("thread_throttle_mode");
-	if (!rft)
-		return;
-
-	rft->fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB;
-}
-
-void __init mbm_config_rftype_init(const char *config)
+void resctrl_file_fflags_init(const char *config, unsigned long fflags)
 {
 	struct rftype *rft;
 
 	rft = rdtgroup_get_rftype_by_name(config);
 	if (rft)
-		rft->fflags = RFTYPE_MON_INFO | RFTYPE_RES_CACHE;
+		rft->fflags = fflags;
 }
 
 /**

From 55544cefdea8ef1b293b8a1d1245a96dd357afce Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Fri, 6 Dec 2024 08:31:42 -0800
Subject: [PATCH 009/236] x86/resctrl: Prepare for per-CTRL_MON group mba_MBps
 control

commit 3b49c37a2f4657730dd38a050b9d221363889dea upstream.

Resctrl uses local memory bandwidth event as input to the feedback loop when
the mba_MBps mount option is used. This means that this mount option cannot be
used on systems that only support monitoring of total bandwidth.

Prepare to allow users to choose the input event independently for each
CTRL_MON group by adding a global variable "mba_mbps_default_event" used to
set the default event for each CTRL_MON group, and a new field
"mba_mbps_event" in struct rdtgroup to track which event is used for each
CTRL_MON group.

Notes:

1) Both of these are only used when the user mounts the filesystem with the
   "mba_MBps" option.
2) Only check for support of local bandwidth event when initializing
   mba_mbps_default_event. Support for total bandwidth event can be added
   after other routines in resctrl have been updated to handle total bandwidth
   event.

  [ bp: Move mba_mbps_default_event extern into the arch header. ]

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20241206163148.83828-3-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c     |  3 +++
 arch/x86/kernel/cpu/resctrl/internal.h |  4 +++-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 13 +++++++++++++
 3 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index f8e704dcb03d9..6a6e53b62ea01 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -964,6 +964,9 @@ static __init bool get_rdt_mon_resources(void)
 	if (!rdt_mon_features)
 		return false;
 
+	if (is_mbm_local_enabled())
+		mba_mbps_default_event = QOS_L3_MBM_LOCAL_EVENT_ID;
+
 	return !rdt_get_mon_l3_config(r);
 }
 
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 021e13d2707f1..80fd49a7de4df 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -286,6 +286,7 @@ struct pseudo_lock_region {
  *				monitor only or ctrl_mon group
  * @mon:			mongroup related data
  * @mode:			mode of resource group
+ * @mba_mbps_event:		input monitoring event id when mba_sc is enabled
  * @plr:			pseudo-locked region
  */
 struct rdtgroup {
@@ -298,6 +299,7 @@ struct rdtgroup {
 	enum rdt_group_type		type;
 	struct mongroup			mon;
 	enum rdtgrp_mode		mode;
+	enum resctrl_event_id		mba_mbps_event;
 	struct pseudo_lock_region	*plr;
 };
 
@@ -511,6 +513,7 @@ extern struct mutex rdtgroup_mutex;
 extern struct rdt_hw_resource rdt_resources_all[];
 extern struct rdtgroup rdtgroup_default;
 extern struct dentry *debugfs_resctrl;
+extern enum resctrl_event_id mba_mbps_default_event;
 
 enum resctrl_res_level {
 	RDT_RESOURCE_L3,
@@ -654,5 +657,4 @@ void resctrl_file_fflags_init(const char *config, unsigned long fflags);
 void rdt_staged_configs_clear(void);
 bool closid_allocated(unsigned int closid);
 int resctrl_find_cleanest_closid(void);
-
 #endif /* _ASM_X86_RESCTRL_INTERNAL_H */
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index d333570e893d3..8a52b25ce26b8 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -65,6 +65,15 @@ static void rdtgroup_destroy_root(void);
 
 struct dentry *debugfs_resctrl;
 
+/*
+ * Memory bandwidth monitoring event to use for the default CTRL_MON group
+ * and each new CTRL_MON group created by the user.  Only relevant when
+ * the filesystem is mounted with the "mba_MBps" option so it does not
+ * matter that it remains uninitialized on systems that do not support
+ * the "mba_MBps" option.
+ */
+enum resctrl_event_id mba_mbps_default_event;
+
 static bool resctrl_debug;
 
 void rdt_last_cmd_clear(void)
@@ -2353,6 +2362,8 @@ static int set_mba_sc(bool mba_sc)
 
 	r->membw.mba_sc = mba_sc;
 
+	rdtgroup_default.mba_mbps_event = mba_mbps_default_event;
+
 	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
 		for (i = 0; i < num_closid; i++)
 			d->mbps_val[i] = MBA_MAX_MBPS;
@@ -3611,6 +3622,8 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
 			rdt_last_cmd_puts("kernfs subdir error\n");
 			goto out_del_list;
 		}
+		if (is_mba_sc(NULL))
+			rdtgrp->mba_mbps_event = mba_mbps_default_event;
 	}
 
 	goto out_unlock;

From 38a2e75cafeed506a48f4d4652bc948ae955e515 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Fri, 6 Dec 2024 08:31:43 -0800
Subject: [PATCH 010/236] x86/resctrl: Modify update_mba_bw() to use per
 CTRL_MON group event

commit 481d363748b2df881df21569f3697b3c7fcf8fc1 upstream.

update_mba_bw() hard codes use of the memory bandwidth local event which
prevents more flexible options from being deployed.

Change this function to use the event specified in the rdtgroup that is
being processed.

Mount time checks for the "mba_MBps" option ensure that local memory
bandwidth is enabled. So drop the redundant is_mbm_local_enabled() check.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20241206163148.83828-4-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/monitor.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index fbb3d6bdebc3d..5c9c8bfca408a 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -752,20 +752,20 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm)
 	u32 closid, rmid, cur_msr_val, new_msr_val;
 	struct mbm_state *pmbm_data, *cmbm_data;
 	struct rdt_ctrl_domain *dom_mba;
+	enum resctrl_event_id evt_id;
 	struct rdt_resource *r_mba;
-	u32 cur_bw, user_bw, idx;
 	struct list_head *head;
 	struct rdtgroup *entry;
-
-	if (!is_mbm_local_enabled())
-		return;
+	u32 cur_bw, user_bw;
 
 	r_mba = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
+	evt_id = rgrp->mba_mbps_event;
 
 	closid = rgrp->closid;
 	rmid = rgrp->mon.rmid;
-	idx = resctrl_arch_rmid_idx_encode(closid, rmid);
-	pmbm_data = &dom_mbm->mbm_local[idx];
+	pmbm_data = get_mbm_state(dom_mbm, closid, rmid, evt_id);
+	if (WARN_ON_ONCE(!pmbm_data))
+		return;
 
 	dom_mba = get_ctrl_domain_from_cpu(smp_processor_id(), r_mba);
 	if (!dom_mba) {
@@ -784,7 +784,9 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm)
 	 */
 	head = &rgrp->mon.crdtgrp_list;
 	list_for_each_entry(entry, head, mon.crdtgrp_list) {
-		cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid];
+		cmbm_data = get_mbm_state(dom_mbm, entry->closid, entry->mon.rmid, evt_id);
+		if (WARN_ON_ONCE(!cmbm_data))
+			return;
 		cur_bw += cmbm_data->prev_bw;
 	}
 

From 5d6666725017dcb8aced6c6f3d45777cccc9e8ab Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Fri, 6 Dec 2024 08:31:44 -0800
Subject: [PATCH 011/236] x86/resctrl: Compute memory bandwidth for all
 supported events

commit 2c272fadb58b590eb973c6c447b039f10631f5f7 upstream.

Switching between local and total memory bandwidth events as the input
to the mba_sc feedback loop would be cumbersome and take effect slowly
in the current implementation as the bandwidth is only known after two
consecutive readings of the same event.

Compute the bandwidth for all supported events. This doesn't add
significant overhead and will make changing which event is used
simple.

Suggested-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20241206163148.83828-5-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/monitor.c | 72 ++++++++++++---------------
 1 file changed, 33 insertions(+), 39 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 5c9c8bfca408a..639a09f7e21a5 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -663,9 +663,12 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
  */
 static void mbm_bw_count(u32 closid, u32 rmid, struct rmid_read *rr)
 {
-	u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid);
-	struct mbm_state *m = &rr->d->mbm_local[idx];
 	u64 cur_bw, bytes, cur_bytes;
+	struct mbm_state *m;
+
+	m = get_mbm_state(rr->d, closid, rmid, rr->evtid);
+	if (WARN_ON_ONCE(!m))
+		return;
 
 	cur_bytes = rr->val;
 	bytes = cur_bytes - m->prev_bw_bytes;
@@ -815,54 +818,45 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm)
 	resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val);
 }
 
-static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d,
-		       u32 closid, u32 rmid)
+static void mbm_update_one_event(struct rdt_resource *r, struct rdt_mon_domain *d,
+				 u32 closid, u32 rmid, enum resctrl_event_id evtid)
 {
 	struct rmid_read rr = {0};
 
 	rr.r = r;
 	rr.d = d;
+	rr.evtid = evtid;
+	rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
+	if (IS_ERR(rr.arch_mon_ctx)) {
+		pr_warn_ratelimited("Failed to allocate monitor context: %ld",
+				    PTR_ERR(rr.arch_mon_ctx));
+		return;
+	}
+
+	__mon_event_count(closid, rmid, &rr);
 
 	/*
-	 * This is protected from concurrent reads from user
-	 * as both the user and we hold the global mutex.
+	 * If the software controller is enabled, compute the
+	 * bandwidth for this event id.
 	 */
-	if (is_mbm_total_enabled()) {
-		rr.evtid = QOS_L3_MBM_TOTAL_EVENT_ID;
-		rr.val = 0;
-		rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
-		if (IS_ERR(rr.arch_mon_ctx)) {
-			pr_warn_ratelimited("Failed to allocate monitor context: %ld",
-					    PTR_ERR(rr.arch_mon_ctx));
-			return;
-		}
+	if (is_mba_sc(NULL))
+		mbm_bw_count(closid, rmid, &rr);
 
-		__mon_event_count(closid, rmid, &rr);
-
-		resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
-	}
-	if (is_mbm_local_enabled()) {
-		rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID;
-		rr.val = 0;
-		rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
-		if (IS_ERR(rr.arch_mon_ctx)) {
-			pr_warn_ratelimited("Failed to allocate monitor context: %ld",
-					    PTR_ERR(rr.arch_mon_ctx));
-			return;
-		}
-
-		__mon_event_count(closid, rmid, &rr);
+	resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
+}
 
-		/*
-		 * Call the MBA software controller only for the
-		 * control groups and when user has enabled
-		 * the software controller explicitly.
-		 */
-		if (is_mba_sc(NULL))
-			mbm_bw_count(closid, rmid, &rr);
+static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d,
+		       u32 closid, u32 rmid)
+{
+	/*
+	 * This is protected from concurrent reads from user as both
+	 * the user and overflow handler hold the global mutex.
+	 */
+	if (is_mbm_total_enabled())
+		mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_TOTAL_EVENT_ID);
 
-		resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
-	}
+	if (is_mbm_local_enabled())
+		mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_LOCAL_EVENT_ID);
 }
 
 /*

From c7065c75f4f33997c57155fa6f8aaaaead51e91b Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Fri, 6 Dec 2024 08:31:45 -0800
Subject: [PATCH 012/236] x86/resctrl: Make mba_sc use total bandwidth if local
 is not supported

commit 141cb5c482b38d7e494a207f881d0fe61e4848ef upstream.

The default input measurement to the mba_sc feedback loop for memory bandwidth
control when the user mounts with the "mba_MBps" option is the local bandwidth
event. But some systems may not support a local bandwidth event.

When local bandwidth event is not supported, check for support of total
bandwidth and use that instead.

Relax the mount option check to allow use of the "mba_MBps" option for systems
when only total bandwidth monitoring is supported. Also update the error
message.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20241206163148.83828-6-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c     | 2 ++
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 4 ++--
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 6a6e53b62ea01..2602be6e080d2 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -966,6 +966,8 @@ static __init bool get_rdt_mon_resources(void)
 
 	if (is_mbm_local_enabled())
 		mba_mbps_default_event = QOS_L3_MBM_LOCAL_EVENT_ID;
+	else if (is_mbm_total_enabled())
+		mba_mbps_default_event = QOS_L3_MBM_TOTAL_EVENT_ID;
 
 	return !rdt_get_mon_l3_config(r);
 }
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 8a52b25ce26b8..0659b8e2a71b5 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -2341,7 +2341,7 @@ static bool supports_mba_mbps(void)
 	struct rdt_resource *rmbm = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
 
-	return (is_mbm_local_enabled() &&
+	return (is_mbm_enabled() &&
 		r->alloc_capable && is_mba_linear() &&
 		r->ctrl_scope == rmbm->mon_scope);
 }
@@ -2768,7 +2768,7 @@ static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param)
 		ctx->enable_cdpl2 = true;
 		return 0;
 	case Opt_mba_mbps:
-		msg = "mba_MBps requires local MBM and linear scale MBA at L3 scope";
+		msg = "mba_MBps requires MBM and linear scale MBA at L3 scope";
 		if (!supports_mba_mbps())
 			return invalfc(fc, msg);
 		ctx->enable_mba_mbps = true;

From 97409b78822a4af03838402086c83e5b4442fec5 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Fri, 6 Dec 2024 08:31:46 -0800
Subject: [PATCH 013/236] x86/resctrl: Add "mba_MBps_event" file to CTRL_MON
 directories

commit f5cd0e316f14d79c9eb0cf8fe7e60cee3a657aa8 upstream.

The "mba_MBps" mount option provides an alternate method to control memory
bandwidth. Instead of specifying allowable bandwidth as a percentage of
maximum possible, the user provides a MiB/s limit value.

In preparation to allow the user to pick the memory bandwidth monitoring event
used as input to the feedback loop, provide a file in each CTRL_MON group
directory that shows the event currently in use. Note that this file is only
visible when the "mba_MBps" mount option is in use.

Suggested-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20241206163148.83828-7-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 30 +++++++++++++++++++++++
 arch/x86/kernel/cpu/resctrl/internal.h    |  2 ++
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    | 10 ++++++++
 3 files changed, 42 insertions(+)

diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 200d89a640270..5fa37b4ecc7a4 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -518,6 +518,36 @@ static int smp_mon_event_count(void *arg)
 	return 0;
 }
 
+int rdtgroup_mba_mbps_event_show(struct kernfs_open_file *of,
+				 struct seq_file *s, void *v)
+{
+	struct rdtgroup *rdtgrp;
+	int ret = 0;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+
+	if (rdtgrp) {
+		switch (rdtgrp->mba_mbps_event) {
+		case QOS_L3_MBM_LOCAL_EVENT_ID:
+			seq_puts(s, "mbm_local_bytes\n");
+			break;
+		case QOS_L3_MBM_TOTAL_EVENT_ID:
+			seq_puts(s, "mbm_total_bytes\n");
+			break;
+		default:
+			pr_warn_once("Bad event %d\n", rdtgrp->mba_mbps_event);
+			ret = -EINVAL;
+			break;
+		}
+	} else {
+		ret = -ENOENT;
+	}
+
+	rdtgroup_kn_unlock(of->kn);
+
+	return ret;
+}
+
 void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 		    struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
 		    cpumask_t *cpumask, int evtid, int first)
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 80fd49a7de4df..cf35706701793 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -613,6 +613,8 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 				char *buf, size_t nbytes, loff_t off);
 int rdtgroup_schemata_show(struct kernfs_open_file *of,
 			   struct seq_file *s, void *v);
+int rdtgroup_mba_mbps_event_show(struct kernfs_open_file *of,
+				 struct seq_file *s, void *v);
 bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_ctrl_domain *d,
 			   unsigned long cbm, int closid, bool exclusive);
 unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_ctrl_domain *d,
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 0659b8e2a71b5..6eb930b8bdfd9 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -1950,6 +1950,12 @@ static struct rftype res_common_files[] = {
 		.seq_show	= rdtgroup_schemata_show,
 		.fflags		= RFTYPE_CTRL_BASE,
 	},
+	{
+		.name		= "mba_MBps_event",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdtgroup_mba_mbps_event_show,
+	},
 	{
 		.name		= "mode",
 		.mode		= 0644,
@@ -2355,6 +2361,7 @@ static int set_mba_sc(bool mba_sc)
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
 	u32 num_closid = resctrl_arch_get_num_closid(r);
 	struct rdt_ctrl_domain *d;
+	unsigned long fflags;
 	int i;
 
 	if (!supports_mba_mbps() || mba_sc == is_mba_sc(r))
@@ -2369,6 +2376,9 @@ static int set_mba_sc(bool mba_sc)
 			d->mbps_val[i] = MBA_MAX_MBPS;
 	}
 
+	fflags = mba_sc ? RFTYPE_CTRL_BASE | RFTYPE_MON_BASE : 0;
+	resctrl_file_fflags_init("mba_MBps_event", fflags);
+
 	return 0;
 }
 

From 102ffef7ce31856f9167d0e6ae3fe49a1815da96 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Fri, 6 Dec 2024 08:31:47 -0800
Subject: [PATCH 014/236] x86/resctrl: Add write option to "mba_MBps_event"
 file

commit 8e931105acae688ff0fc8f875a6c05e5aed8ab79 upstream.

The "mba_MBps" mount option provides an alternate method to control memory
bandwidth. Instead of specifying allowable bandwidth as a percentage of
maximum possible, the user provides a MiB/s limit value.

There is a file in each CTRL_MON group directory that shows the event
currently in use.

Allow writing that file to choose a different event.

A user can choose any of the memory bandwidth monitoring events listed in
/sys/fs/resctrl/info/L3_mon/mon_features independently for each CTRL_MON group
by writing to each of the "mba_MBps_event" files.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20241206163148.83828-8-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 40 +++++++++++++++++++++++
 arch/x86/kernel/cpu/resctrl/internal.h    |  2 ++
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    |  3 +-
 3 files changed, 44 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 5fa37b4ecc7a4..536351159cc23 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -518,6 +518,46 @@ static int smp_mon_event_count(void *arg)
 	return 0;
 }
 
+ssize_t rdtgroup_mba_mbps_event_write(struct kernfs_open_file *of,
+				      char *buf, size_t nbytes, loff_t off)
+{
+	struct rdtgroup *rdtgrp;
+	int ret = 0;
+
+	/* Valid input requires a trailing newline */
+	if (nbytes == 0 || buf[nbytes - 1] != '\n')
+		return -EINVAL;
+	buf[nbytes - 1] = '\0';
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		rdtgroup_kn_unlock(of->kn);
+		return -ENOENT;
+	}
+	rdt_last_cmd_clear();
+
+	if (!strcmp(buf, "mbm_local_bytes")) {
+		if (is_mbm_local_enabled())
+			rdtgrp->mba_mbps_event = QOS_L3_MBM_LOCAL_EVENT_ID;
+		else
+			ret = -EINVAL;
+	} else if (!strcmp(buf, "mbm_total_bytes")) {
+		if (is_mbm_total_enabled())
+			rdtgrp->mba_mbps_event = QOS_L3_MBM_TOTAL_EVENT_ID;
+		else
+			ret = -EINVAL;
+	} else {
+		ret = -EINVAL;
+	}
+
+	if (ret)
+		rdt_last_cmd_printf("Unsupported event id '%s'\n", buf);
+
+	rdtgroup_kn_unlock(of->kn);
+
+	return ret ?: nbytes;
+}
+
 int rdtgroup_mba_mbps_event_show(struct kernfs_open_file *of,
 				 struct seq_file *s, void *v)
 {
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index cf35706701793..40f3e6af8c1bf 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -613,6 +613,8 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 				char *buf, size_t nbytes, loff_t off);
 int rdtgroup_schemata_show(struct kernfs_open_file *of,
 			   struct seq_file *s, void *v);
+ssize_t rdtgroup_mba_mbps_event_write(struct kernfs_open_file *of,
+				      char *buf, size_t nbytes, loff_t off);
 int rdtgroup_mba_mbps_event_show(struct kernfs_open_file *of,
 				 struct seq_file *s, void *v);
 bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_ctrl_domain *d,
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 6eb930b8bdfd9..6419e04d8a7b2 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -1952,8 +1952,9 @@ static struct rftype res_common_files[] = {
 	},
 	{
 		.name		= "mba_MBps_event",
-		.mode		= 0444,
+		.mode		= 0644,
 		.kf_ops		= &rdtgroup_kf_single_ops,
+		.write		= rdtgroup_mba_mbps_event_write,
 		.seq_show	= rdtgroup_mba_mbps_event_show,
 	},
 	{

From 84b98e513de65f48ebf1c7bd127578f78d484000 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:36:46 +0000
Subject: [PATCH 015/236] x86/resctrl: Fix allocation of cleanest CLOSID on
 platforms with no monitors

commit a121798ae669351ec0697c94f71c3a692b2a755b upstream.

Commit

  6eac36bb9eb0 ("x86/resctrl: Allocate the cleanest CLOSID by searching closid_num_dirty_rmid")

added logic that causes resctrl to search for the CLOSID with the fewest dirty
cache lines when creating a new control group, if requested by the arch code.
This depends on the values read from the llc_occupancy counters. The logic is
applicable to architectures where the CLOSID effectively forms part of the
monitoring identifier and so do not allow complete freedom to choose an unused
monitoring identifier for a given CLOSID.

This support missed that some platforms may not have these counters.  This
causes a NULL pointer dereference when creating a new control group as the
array was not allocated by dom_data_init().

As this feature isn't necessary on platforms that don't have cache occupancy
monitors, add this to the check that occurs when a new control group is
allocated.

Fixes: 6eac36bb9eb0 ("x86/resctrl: Allocate the cleanest CLOSID by searching closid_num_dirty_rmid")
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-2-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 6419e04d8a7b2..04b653d613e88 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -157,7 +157,8 @@ static int closid_alloc(void)
 
 	lockdep_assert_held(&rdtgroup_mutex);
 
-	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
+	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID) &&
+	    is_llc_occupancy_enabled()) {
 		cleanest_closid = resctrl_find_cleanest_closid();
 		if (cleanest_closid < 0)
 			return cleanest_closid;

From 1dac1664bdd1a5f387f52db96b79272786ba515b Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:36:47 +0000
Subject: [PATCH 016/236] x86/resctrl: Add a helper to avoid reaching into the
 arch code resource list

commit 3c021531131c9ee5df5da739819a515326ee9570 upstream.

Resctrl occasionally wants to know something about a specific resource, in
these cases it reaches into the arch code's rdt_resources_all[] array.

Once the filesystem parts of resctrl are moved to /fs/, this means it will
need visibility of the architecture specific struct rdt_hw_resource
definition, and the array of all resources.  All architectures would also need
a r_resctrl member in this struct.

Instead, abstract this via a helper to allow architectures to do different
things here. Move the level enum to the resctrl header and add a helper to
retrieve the struct rdt_resource by 'rid'.

resctrl_arch_get_resource() should not return NULL for any value in the enum,
it may instead return a dummy resource that is !alloc_enabled && !mon_enabled.

Co-developed-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-3-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c        | 12 ++++++++++--
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c |  2 +-
 arch/x86/kernel/cpu/resctrl/internal.h    | 10 ----------
 arch/x86/kernel/cpu/resctrl/monitor.c     |  8 ++++----
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    | 14 +++++++-------
 include/linux/resctrl.h                   | 17 +++++++++++++++++
 6 files changed, 39 insertions(+), 24 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 2602be6e080d2..0c737f8a162bf 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -62,7 +62,7 @@ static void mba_wrmsr_amd(struct msr_param *m);
 #define ctrl_domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.ctrl_domains)
 #define mon_domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.mon_domains)
 
-struct rdt_hw_resource rdt_resources_all[] = {
+struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESOURCES] = {
 	[RDT_RESOURCE_L3] =
 	{
 		.r_resctrl = {
@@ -127,6 +127,14 @@ u32 resctrl_arch_system_num_rmid_idx(void)
 	return r->num_rmid;
 }
 
+struct rdt_resource *resctrl_arch_get_resource(enum resctrl_res_level l)
+{
+	if (l >= RDT_NUM_RESOURCES)
+		return NULL;
+
+	return &rdt_resources_all[l].r_resctrl;
+}
+
 /*
  * cache_alloc_hsw_probe() - Have to probe for Intel haswell server CPUs
  * as they do not have CPUID enumeration support for Cache allocation.
@@ -174,7 +182,7 @@ static inline void cache_alloc_hsw_probe(void)
 bool is_mba_sc(struct rdt_resource *r)
 {
 	if (!r)
-		return rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl.membw.mba_sc;
+		r = resctrl_arch_get_resource(RDT_RESOURCE_MBA);
 
 	/*
 	 * The software controller support is only applicable to MBA resource.
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 536351159cc23..4af27ef5a8a19 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -649,7 +649,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 	resid = md.u.rid;
 	domid = md.u.domid;
 	evtid = md.u.evtid;
-	r = &rdt_resources_all[resid].r_resctrl;
+	r = resctrl_arch_get_resource(resid);
 
 	if (md.u.sum) {
 		/*
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 40f3e6af8c1bf..f8dfd8fd6aeb2 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -515,16 +515,6 @@ extern struct rdtgroup rdtgroup_default;
 extern struct dentry *debugfs_resctrl;
 extern enum resctrl_event_id mba_mbps_default_event;
 
-enum resctrl_res_level {
-	RDT_RESOURCE_L3,
-	RDT_RESOURCE_L2,
-	RDT_RESOURCE_MBA,
-	RDT_RESOURCE_SMBA,
-
-	/* Must be the last */
-	RDT_NUM_RESOURCES,
-};
-
 static inline struct rdt_resource *resctrl_inc(struct rdt_resource *res)
 {
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(res);
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 639a09f7e21a5..1193a039adeca 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -365,7 +365,7 @@ static void limbo_release_entry(struct rmid_entry *entry)
  */
 void __check_limbo(struct rdt_mon_domain *d, bool force_free)
 {
-	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
 	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
 	struct rmid_entry *entry;
 	u32 idx, cur_idx = 1;
@@ -521,7 +521,7 @@ int alloc_rmid(u32 closid)
 
 static void add_rmid_to_limbo(struct rmid_entry *entry)
 {
-	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
 	struct rdt_mon_domain *d;
 	u32 idx;
 
@@ -761,7 +761,7 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm)
 	struct rdtgroup *entry;
 	u32 cur_bw, user_bw;
 
-	r_mba = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
+	r_mba = resctrl_arch_get_resource(RDT_RESOURCE_MBA);
 	evt_id = rgrp->mba_mbps_event;
 
 	closid = rgrp->closid;
@@ -925,7 +925,7 @@ void mbm_handle_overflow(struct work_struct *work)
 	if (!resctrl_mounted || !resctrl_arch_mon_capable())
 		goto out_unlock;
 
-	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+	r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
 	d = container_of(work, struct rdt_mon_domain, mbm_over.work);
 
 	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 04b653d613e88..45093b9e8e630 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -2256,7 +2256,7 @@ static void l2_qos_cfg_update(void *arg)
 
 static inline bool is_mba_linear(void)
 {
-	return rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl.membw.delay_linear;
+	return resctrl_arch_get_resource(RDT_RESOURCE_MBA)->membw.delay_linear;
 }
 
 static int set_cache_qos_cfg(int level, bool enable)
@@ -2346,8 +2346,8 @@ static void mba_sc_domain_destroy(struct rdt_resource *r,
  */
 static bool supports_mba_mbps(void)
 {
-	struct rdt_resource *rmbm = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
+	struct rdt_resource *rmbm = resctrl_arch_get_resource(RDT_RESOURCE_L3);
+	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_MBA);
 
 	return (is_mbm_enabled() &&
 		r->alloc_capable && is_mba_linear() &&
@@ -2360,7 +2360,7 @@ static bool supports_mba_mbps(void)
  */
 static int set_mba_sc(bool mba_sc)
 {
-	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
+	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_MBA);
 	u32 num_closid = resctrl_arch_get_num_closid(r);
 	struct rdt_ctrl_domain *d;
 	unsigned long fflags;
@@ -2714,7 +2714,7 @@ static int rdt_get_tree(struct fs_context *fc)
 		resctrl_mounted = true;
 
 	if (is_mbm_enabled()) {
-		r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+		r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
 		list_for_each_entry(dom, &r->mon_domains, hdr.list)
 			mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL,
 						   RESCTRL_PICK_ANY_CPU);
@@ -3951,7 +3951,7 @@ static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf)
 	if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2))
 		seq_puts(seq, ",cdpl2");
 
-	if (is_mba_sc(&rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl))
+	if (is_mba_sc(resctrl_arch_get_resource(RDT_RESOURCE_MBA)))
 		seq_puts(seq, ",mba_MBps");
 
 	if (resctrl_debug)
@@ -4151,7 +4151,7 @@ static void clear_childcpus(struct rdtgroup *r, unsigned int cpu)
 
 void resctrl_offline_cpu(unsigned int cpu)
 {
-	struct rdt_resource *l3 = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+	struct rdt_resource *l3 = resctrl_arch_get_resource(RDT_RESOURCE_L3);
 	struct rdt_mon_domain *d;
 	struct rdtgroup *rdtgrp;
 
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index d94abba1c716e..37279e2a89dae 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -37,6 +37,16 @@ enum resctrl_conf_type {
 	CDP_DATA,
 };
 
+enum resctrl_res_level {
+	RDT_RESOURCE_L3,
+	RDT_RESOURCE_L2,
+	RDT_RESOURCE_MBA,
+	RDT_RESOURCE_SMBA,
+
+	/* Must be the last */
+	RDT_NUM_RESOURCES,
+};
+
 #define CDP_NUM_TYPES	(CDP_DATA + 1)
 
 /*
@@ -226,6 +236,13 @@ struct rdt_resource {
 	bool			cdp_capable;
 };
 
+/*
+ * Get the resource that exists at this level. If the level is not supported
+ * a dummy/not-capable resource can be returned. Levels >= RDT_NUM_RESOURCES
+ * will return NULL.
+ */
+struct rdt_resource *resctrl_arch_get_resource(enum resctrl_res_level l);
+
 /**
  * struct resctrl_schema - configuration abilities of a resource presented to
  *			   user-space

From 8ec0284393af106aefa4f9aa41ea982eb14f056c Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:36:48 +0000
Subject: [PATCH 017/236] x86/resctrl: Remove fflags from struct rdt_resource

commit 131dab13a82d9edd97dd96d98d2919f56f339331 upstream.

The resctrl arch code specifies whether a resource controls a cache or memory
using the fflags field. This field is then used by resctrl to determine which
files should be exposed in the filesystem.

Allowing the architecture to pick this value means the RFTYPE_ flags have to
be in a shared header, and allows an architecture to create a combination that
resctrl does not support.

Remove the fflags field, and pick the value based on the resource id.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-4-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c     |  4 ----
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 18 ++++++++++++++++--
 include/linux/resctrl.h                |  2 --
 3 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 0c737f8a162bf..b7dc7dfa4a1f6 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -74,7 +74,6 @@ struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESOURCES] = {
 			.mon_domains		= mon_domain_init(RDT_RESOURCE_L3),
 			.parse_ctrlval		= parse_cbm,
 			.format_str		= "%d=%0*x",
-			.fflags			= RFTYPE_RES_CACHE,
 		},
 		.msr_base		= MSR_IA32_L3_CBM_BASE,
 		.msr_update		= cat_wrmsr,
@@ -88,7 +87,6 @@ struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESOURCES] = {
 			.ctrl_domains		= ctrl_domain_init(RDT_RESOURCE_L2),
 			.parse_ctrlval		= parse_cbm,
 			.format_str		= "%d=%0*x",
-			.fflags			= RFTYPE_RES_CACHE,
 		},
 		.msr_base		= MSR_IA32_L2_CBM_BASE,
 		.msr_update		= cat_wrmsr,
@@ -102,7 +100,6 @@ struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESOURCES] = {
 			.ctrl_domains		= ctrl_domain_init(RDT_RESOURCE_MBA),
 			.parse_ctrlval		= parse_bw,
 			.format_str		= "%d=%*u",
-			.fflags			= RFTYPE_RES_MB,
 		},
 	},
 	[RDT_RESOURCE_SMBA] =
@@ -114,7 +111,6 @@ struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESOURCES] = {
 			.ctrl_domains		= ctrl_domain_init(RDT_RESOURCE_SMBA),
 			.parse_ctrlval		= parse_bw,
 			.format_str		= "%d=%*u",
-			.fflags			= RFTYPE_RES_MB,
 		},
 	},
 };
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 45093b9e8e630..3391ac8ecb2de 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -2165,6 +2165,20 @@ static int rdtgroup_mkdir_info_resdir(void *priv, char *name,
 	return ret;
 }
 
+static unsigned long fflags_from_resource(struct rdt_resource *r)
+{
+	switch (r->rid) {
+	case RDT_RESOURCE_L3:
+	case RDT_RESOURCE_L2:
+		return RFTYPE_RES_CACHE;
+	case RDT_RESOURCE_MBA:
+	case RDT_RESOURCE_SMBA:
+		return RFTYPE_RES_MB;
+	}
+
+	return WARN_ON_ONCE(1);
+}
+
 static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
 {
 	struct resctrl_schema *s;
@@ -2185,14 +2199,14 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
 	/* loop over enabled controls, these are all alloc_capable */
 	list_for_each_entry(s, &resctrl_schema_all, list) {
 		r = s->res;
-		fflags = r->fflags | RFTYPE_CTRL_INFO;
+		fflags = fflags_from_resource(r) | RFTYPE_CTRL_INFO;
 		ret = rdtgroup_mkdir_info_resdir(s, s->name, fflags);
 		if (ret)
 			goto out_destroy;
 	}
 
 	for_each_mon_capable_rdt_resource(r) {
-		fflags = r->fflags | RFTYPE_MON_INFO;
+		fflags = fflags_from_resource(r) | RFTYPE_MON_INFO;
 		sprintf(name, "%s_MON", r->name);
 		ret = rdtgroup_mkdir_info_resdir(r, name, fflags);
 		if (ret)
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 37279e2a89dae..496ddcaa4ecf3 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -210,7 +210,6 @@ enum resctrl_scope {
  * @format_str:		Per resource format string to show domain value
  * @parse_ctrlval:	Per resource function pointer to parse control values
  * @evt_list:		List of monitoring events
- * @fflags:		flags to choose base and info files
  * @cdp_capable:	Is the CDP feature available on this resource
  */
 struct rdt_resource {
@@ -232,7 +231,6 @@ struct rdt_resource {
 						 struct resctrl_schema *s,
 						 struct rdt_ctrl_domain *d);
 	struct list_head	evt_list;
-	unsigned long		fflags;
 	bool			cdp_capable;
 };
 

From 50bcd10fbadbb19be75dacc9954e4752fc0fef27 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:36:49 +0000
Subject: [PATCH 018/236] x86/resctrl: Use schema type to determine how to
 parse schema values

commit c24f5eab6b2689fd4e97a2d2fe963864036653e6 upstream.

Resctrl's architecture code gets to specify a function pointer that is used
when parsing schema entries. This is expected to be one of two helpers from
the filesystem code.

Setting this function pointer allows the architecture code to change the ABI
resctrl presents to user-space, and forces resctrl to expose these helpers.

Instead, add a schema format enum to choose which schema parser to use. This
allows the helpers to be made static and the structs used for passing
arguments moved out of shared headers.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-5-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c        |  8 +++---
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 32 +++++++++++++++++++----
 arch/x86/kernel/cpu/resctrl/internal.h    | 10 -------
 include/linux/resctrl.h                   | 17 ++++++++----
 4 files changed, 43 insertions(+), 24 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index b7dc7dfa4a1f6..32bc9911a840f 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -72,7 +72,7 @@ struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESOURCES] = {
 			.mon_scope		= RESCTRL_L3_CACHE,
 			.ctrl_domains		= ctrl_domain_init(RDT_RESOURCE_L3),
 			.mon_domains		= mon_domain_init(RDT_RESOURCE_L3),
-			.parse_ctrlval		= parse_cbm,
+			.schema_fmt		= RESCTRL_SCHEMA_BITMAP,
 			.format_str		= "%d=%0*x",
 		},
 		.msr_base		= MSR_IA32_L3_CBM_BASE,
@@ -85,7 +85,7 @@ struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESOURCES] = {
 			.name			= "L2",
 			.ctrl_scope		= RESCTRL_L2_CACHE,
 			.ctrl_domains		= ctrl_domain_init(RDT_RESOURCE_L2),
-			.parse_ctrlval		= parse_cbm,
+			.schema_fmt		= RESCTRL_SCHEMA_BITMAP,
 			.format_str		= "%d=%0*x",
 		},
 		.msr_base		= MSR_IA32_L2_CBM_BASE,
@@ -98,7 +98,7 @@ struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESOURCES] = {
 			.name			= "MB",
 			.ctrl_scope		= RESCTRL_L3_CACHE,
 			.ctrl_domains		= ctrl_domain_init(RDT_RESOURCE_MBA),
-			.parse_ctrlval		= parse_bw,
+			.schema_fmt		= RESCTRL_SCHEMA_RANGE,
 			.format_str		= "%d=%*u",
 		},
 	},
@@ -109,7 +109,7 @@ struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESOURCES] = {
 			.name			= "SMBA",
 			.ctrl_scope		= RESCTRL_L3_CACHE,
 			.ctrl_domains		= ctrl_domain_init(RDT_RESOURCE_SMBA),
-			.parse_ctrlval		= parse_bw,
+			.schema_fmt		= RESCTRL_SCHEMA_RANGE,
 			.format_str		= "%d=%*u",
 		},
 	},
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 4af27ef5a8a19..f4334f437ffc7 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -23,6 +23,15 @@
 
 #include "internal.h"
 
+struct rdt_parse_data {
+	struct rdtgroup		*rdtgrp;
+	char			*buf;
+};
+
+typedef int (ctrlval_parser_t)(struct rdt_parse_data *data,
+			       struct resctrl_schema *s,
+			       struct rdt_ctrl_domain *d);
+
 /*
  * Check whether MBA bandwidth percentage value is correct. The value is
  * checked against the minimum and max bandwidth values specified by the
@@ -64,8 +73,8 @@ static bool bw_validate(char *buf, u32 *data, struct rdt_resource *r)
 	return true;
 }
 
-int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s,
-	     struct rdt_ctrl_domain *d)
+static int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s,
+		    struct rdt_ctrl_domain *d)
 {
 	struct resctrl_staged_config *cfg;
 	u32 closid = data->rdtgrp->closid;
@@ -143,8 +152,8 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
  * Read one cache bit mask (hex). Check that it is valid for the current
  * resource type.
  */
-int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s,
-	      struct rdt_ctrl_domain *d)
+static int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s,
+		     struct rdt_ctrl_domain *d)
 {
 	struct rdtgroup *rdtgrp = data->rdtgrp;
 	struct resctrl_staged_config *cfg;
@@ -210,6 +219,7 @@ static int parse_line(char *line, struct resctrl_schema *s,
 		      struct rdtgroup *rdtgrp)
 {
 	enum resctrl_conf_type t = s->conf_type;
+	ctrlval_parser_t *parse_ctrlval = NULL;
 	struct resctrl_staged_config *cfg;
 	struct rdt_resource *r = s->res;
 	struct rdt_parse_data data;
@@ -220,6 +230,18 @@ static int parse_line(char *line, struct resctrl_schema *s,
 	/* Walking r->domains, ensure it can't race with cpuhp */
 	lockdep_assert_cpus_held();
 
+	switch (r->schema_fmt) {
+	case RESCTRL_SCHEMA_BITMAP:
+		parse_ctrlval = &parse_cbm;
+		break;
+	case RESCTRL_SCHEMA_RANGE:
+		parse_ctrlval = &parse_bw;
+		break;
+	}
+
+	if (WARN_ON_ONCE(!parse_ctrlval))
+		return -EINVAL;
+
 	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
 	    (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)) {
 		rdt_last_cmd_puts("Cannot pseudo-lock MBA resource\n");
@@ -240,7 +262,7 @@ static int parse_line(char *line, struct resctrl_schema *s,
 		if (d->hdr.id == dom_id) {
 			data.buf = dom;
 			data.rdtgrp = rdtgrp;
-			if (r->parse_ctrlval(&data, s, d))
+			if (parse_ctrlval(&data, s, d))
 				return -EINVAL;
 			if (rdtgrp->mode ==  RDT_MODE_PSEUDO_LOCKSETUP) {
 				cfg = &d->staged_config[t];
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index f8dfd8fd6aeb2..10a5ae2e4de0f 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -462,11 +462,6 @@ static inline bool is_mbm_event(int e)
 		e <= QOS_L3_MBM_LOCAL_EVENT_ID);
 }
 
-struct rdt_parse_data {
-	struct rdtgroup		*rdtgrp;
-	char			*buf;
-};
-
 /**
  * struct rdt_hw_resource - arch private attributes of a resctrl resource
  * @r_resctrl:		Attributes of the resource used directly by resctrl.
@@ -503,11 +498,6 @@ static inline struct rdt_hw_resource *resctrl_to_arch_res(struct rdt_resource *r
 	return container_of(r, struct rdt_hw_resource, r_resctrl);
 }
 
-int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s,
-	      struct rdt_ctrl_domain *d);
-int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s,
-	     struct rdt_ctrl_domain *d);
-
 extern struct mutex rdtgroup_mutex;
 
 extern struct rdt_hw_resource rdt_resources_all[];
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 496ddcaa4ecf3..3e1a41356b2a7 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -183,7 +183,6 @@ struct resctrl_membw {
 	u32				*mb_map;
 };
 
-struct rdt_parse_data;
 struct resctrl_schema;
 
 enum resctrl_scope {
@@ -192,6 +191,16 @@ enum resctrl_scope {
 	RESCTRL_L3_NODE,
 };
 
+/**
+ * enum resctrl_schema_fmt - The format user-space provides for a schema.
+ * @RESCTRL_SCHEMA_BITMAP:	The schema is a bitmap in hex.
+ * @RESCTRL_SCHEMA_RANGE:	The schema is a decimal number.
+ */
+enum resctrl_schema_fmt {
+	RESCTRL_SCHEMA_BITMAP,
+	RESCTRL_SCHEMA_RANGE,
+};
+
 /**
  * struct rdt_resource - attributes of a resctrl resource
  * @rid:		The index of the resource
@@ -208,7 +217,7 @@ enum resctrl_scope {
  * @data_width:		Character width of data when displaying
  * @default_ctrl:	Specifies default cache cbm or memory B/W percent.
  * @format_str:		Per resource format string to show domain value
- * @parse_ctrlval:	Per resource function pointer to parse control values
+ * @schema_fmt:		Which format string and parser is used for this schema.
  * @evt_list:		List of monitoring events
  * @cdp_capable:	Is the CDP feature available on this resource
  */
@@ -227,9 +236,7 @@ struct rdt_resource {
 	int			data_width;
 	u32			default_ctrl;
 	const char		*format_str;
-	int			(*parse_ctrlval)(struct rdt_parse_data *data,
-						 struct resctrl_schema *s,
-						 struct rdt_ctrl_domain *d);
+	enum resctrl_schema_fmt	schema_fmt;
 	struct list_head	evt_list;
 	bool			cdp_capable;
 };

From c93bacd04bedb53132bf7c0a4d58032d6a23bcd4 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:36:50 +0000
Subject: [PATCH 019/236] x86/resctrl: Use schema type to determine the schema
 format string

commit bb9343c8f2906ac7087a7f9560b37636c220551d upstream.

Resctrl's architecture code gets to specify a format string that is
used when printing schema entries. This is expected to be one of two
values that the filesystem code supports.

Setting this format string allows the architecture code to change
the ABI resctrl presents to user-space.

Instead, use the schema format enum to choose which format string to
use.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-6-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c        |  4 ----
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c |  2 +-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    | 14 ++++++++++++++
 include/linux/resctrl.h                   |  4 ++--
 4 files changed, 17 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 32bc9911a840f..fdf52d6b577b7 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -73,7 +73,6 @@ struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESOURCES] = {
 			.ctrl_domains		= ctrl_domain_init(RDT_RESOURCE_L3),
 			.mon_domains		= mon_domain_init(RDT_RESOURCE_L3),
 			.schema_fmt		= RESCTRL_SCHEMA_BITMAP,
-			.format_str		= "%d=%0*x",
 		},
 		.msr_base		= MSR_IA32_L3_CBM_BASE,
 		.msr_update		= cat_wrmsr,
@@ -86,7 +85,6 @@ struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESOURCES] = {
 			.ctrl_scope		= RESCTRL_L2_CACHE,
 			.ctrl_domains		= ctrl_domain_init(RDT_RESOURCE_L2),
 			.schema_fmt		= RESCTRL_SCHEMA_BITMAP,
-			.format_str		= "%d=%0*x",
 		},
 		.msr_base		= MSR_IA32_L2_CBM_BASE,
 		.msr_update		= cat_wrmsr,
@@ -99,7 +97,6 @@ struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESOURCES] = {
 			.ctrl_scope		= RESCTRL_L3_CACHE,
 			.ctrl_domains		= ctrl_domain_init(RDT_RESOURCE_MBA),
 			.schema_fmt		= RESCTRL_SCHEMA_RANGE,
-			.format_str		= "%d=%*u",
 		},
 	},
 	[RDT_RESOURCE_SMBA] =
@@ -110,7 +107,6 @@ struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESOURCES] = {
 			.ctrl_scope		= RESCTRL_L3_CACHE,
 			.ctrl_domains		= ctrl_domain_init(RDT_RESOURCE_SMBA),
 			.schema_fmt		= RESCTRL_SCHEMA_RANGE,
-			.format_str		= "%d=%*u",
 		},
 	},
 };
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index f4334f437ffc7..c763cb4fb1a88 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -487,7 +487,7 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo
 			ctrl_val = resctrl_arch_get_config(r, dom, closid,
 							   schema->conf_type);
 
-		seq_printf(s, r->format_str, dom->hdr.id, max_data_width,
+		seq_printf(s, schema->fmt_str, dom->hdr.id, max_data_width,
 			   ctrl_val);
 		sep = true;
 	}
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 3391ac8ecb2de..e7862d0936c94 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -2611,6 +2611,20 @@ static int schemata_list_add(struct rdt_resource *r, enum resctrl_conf_type type
 	if (cl > max_name_width)
 		max_name_width = cl;
 
+	switch (r->schema_fmt) {
+	case RESCTRL_SCHEMA_BITMAP:
+		s->fmt_str = "%d=%0*x";
+		break;
+	case RESCTRL_SCHEMA_RANGE:
+		s->fmt_str = "%d=%0*u";
+		break;
+	}
+
+	if (WARN_ON_ONCE(!s->fmt_str)) {
+		kfree(s);
+		return -EINVAL;
+	}
+
 	INIT_LIST_HEAD(&s->list);
 	list_add(&s->list, &resctrl_schema_all);
 
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 3e1a41356b2a7..736b9a9a9464e 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -216,7 +216,6 @@ enum resctrl_schema_fmt {
  * @name:		Name to use in "schemata" file.
  * @data_width:		Character width of data when displaying
  * @default_ctrl:	Specifies default cache cbm or memory B/W percent.
- * @format_str:		Per resource format string to show domain value
  * @schema_fmt:		Which format string and parser is used for this schema.
  * @evt_list:		List of monitoring events
  * @cdp_capable:	Is the CDP feature available on this resource
@@ -235,7 +234,6 @@ struct rdt_resource {
 	char			*name;
 	int			data_width;
 	u32			default_ctrl;
-	const char		*format_str;
 	enum resctrl_schema_fmt	schema_fmt;
 	struct list_head	evt_list;
 	bool			cdp_capable;
@@ -253,6 +251,7 @@ struct rdt_resource *resctrl_arch_get_resource(enum resctrl_res_level l);
  *			   user-space
  * @list:	Member of resctrl_schema_all.
  * @name:	The name to use in the "schemata" file.
+ * @fmt_str:	Format string to show domain value.
  * @conf_type:	Whether this schema is specific to code/data.
  * @res:	The resource structure exported by the architecture to describe
  *		the hardware that is configured by this schema.
@@ -263,6 +262,7 @@ struct rdt_resource *resctrl_arch_get_resource(enum resctrl_res_level l);
 struct resctrl_schema {
 	struct list_head		list;
 	char				name[8];
+	const char			*fmt_str;
 	enum resctrl_conf_type		conf_type;
 	struct rdt_resource		*res;
 	u32				num_closid;

From 111b8ede01be7ad03b14bcf221c458503412d8ce Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:36:51 +0000
Subject: [PATCH 020/236] x86/resctrl: Remove data_width and the tabular format

commit 43312b8ea1c61abbc5e3bdc87fe2e18f755d549d upstream.

The resctrl architecture code provides a data_width for the controls of each
resource. This is used to zero pad all control values in the schemata file so
they appear in columns. The same is done with the resource names to complete
the visual effect. e.g.

  | SMBA:0=2048
  |   L3:0=00ff

AMD platforms discover their maximum bandwidth for the MB resource from
firmware, but hard-code the data_width to 4. If the maximum bandwidth requires
more digits - the tabular format is silently broken.  This is also broken when
the mba_MBps mount option is used as the field width isn't updated. If new
schema are added resctrl will need to be able to determine the maximum width.
The benefit of this pretty-printing is questionable.

Instead of handling runtime discovery of the data_width for AMD platforms,
remove the feature. These fields are always zero padded so should be harmless
to remove if the whole field has been treated as a number.  In the above
example, this would now look like this:

  | SMBA:0=2048
  |   L3:0=ff

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-7-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c        | 26 -----------------------
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c |  3 +--
 arch/x86/kernel/cpu/resctrl/internal.h    |  2 +-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    | 10 +++++++--
 include/linux/resctrl.h                   |  2 --
 5 files changed, 10 insertions(+), 33 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index fdf52d6b577b7..c6fe3616078eb 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -43,12 +43,6 @@ static DEFINE_MUTEX(domain_list_lock);
  */
 DEFINE_PER_CPU(struct resctrl_pqr_state, pqr_state);
 
-/*
- * Used to store the max resource name width and max resource data width
- * to display the schemata in a tabular format
- */
-int max_name_width, max_data_width;
-
 /*
  * Global boolean for rdt_alloc which is true if any
  * resource allocation is enabled.
@@ -228,7 +222,6 @@ static __init bool __get_mem_config_intel(struct rdt_resource *r)
 			return false;
 		r->membw.arch_needs_linear = false;
 	}
-	r->data_width = 3;
 
 	if (boot_cpu_has(X86_FEATURE_PER_THREAD_MBA))
 		r->membw.throttle_mode = THREAD_THROTTLE_PER_THREAD;
@@ -269,8 +262,6 @@ static __init bool __rdt_get_mem_config_amd(struct rdt_resource *r)
 	r->membw.throttle_mode = THREAD_THROTTLE_UNDEFINED;
 	r->membw.min_bw = 0;
 	r->membw.bw_gran = 1;
-	/* Max value is 2048, Data width should be 4 in decimal */
-	r->data_width = 4;
 
 	r->alloc_capable = true;
 
@@ -290,7 +281,6 @@ static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r)
 	r->cache.cbm_len = eax.split.cbm_len + 1;
 	r->default_ctrl = BIT_MASK(eax.split.cbm_len + 1) - 1;
 	r->cache.shareable_bits = ebx & r->default_ctrl;
-	r->data_width = (r->cache.cbm_len + 3) / 4;
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
 		r->cache.arch_has_sparse_bitmasks = ecx.split.noncont;
 	r->alloc_capable = true;
@@ -786,20 +776,6 @@ static int resctrl_arch_offline_cpu(unsigned int cpu)
 	return 0;
 }
 
-/*
- * Choose a width for the resource name and resource data based on the
- * resource that has widest name and cbm.
- */
-static __init void rdt_init_padding(void)
-{
-	struct rdt_resource *r;
-
-	for_each_alloc_capable_rdt_resource(r) {
-		if (r->data_width > max_data_width)
-			max_data_width = r->data_width;
-	}
-}
-
 enum {
 	RDT_FLAG_CMT,
 	RDT_FLAG_MBM_TOTAL,
@@ -1115,8 +1091,6 @@ static int __init resctrl_late_init(void)
 	if (!get_rdt_resources())
 		return -ENODEV;
 
-	rdt_init_padding();
-
 	state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
 				  "x86/resctrl/cat:online:",
 				  resctrl_arch_online_cpu,
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index c763cb4fb1a88..59610b209b4e9 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -487,8 +487,7 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo
 			ctrl_val = resctrl_arch_get_config(r, dom, closid,
 							   schema->conf_type);
 
-		seq_printf(s, schema->fmt_str, dom->hdr.id, max_data_width,
-			   ctrl_val);
+		seq_printf(s, schema->fmt_str, dom->hdr.id, ctrl_val);
 		sep = true;
 	}
 	seq_puts(s, "\n");
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 10a5ae2e4de0f..986246a3a93fc 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -329,7 +329,7 @@ struct rdtgroup {
 /* List of all resource groups */
 extern struct list_head rdt_all_groups;
 
-extern int max_name_width, max_data_width;
+extern int max_name_width;
 
 int __init rdtgroup_init(void);
 void __exit rdtgroup_exit(void);
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index e7862d0936c94..1e0bae1a9d950 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -57,6 +57,12 @@ static struct kernfs_node *kn_mongrp;
 /* Kernel fs node for "mon_data" directory under root */
 static struct kernfs_node *kn_mondata;
 
+/*
+ * Used to store the max resource name width to display the schemata names in
+ * a tabular format.
+ */
+int max_name_width;
+
 static struct seq_buf last_cmd_status;
 static char last_cmd_status_buf[512];
 
@@ -2613,10 +2619,10 @@ static int schemata_list_add(struct rdt_resource *r, enum resctrl_conf_type type
 
 	switch (r->schema_fmt) {
 	case RESCTRL_SCHEMA_BITMAP:
-		s->fmt_str = "%d=%0*x";
+		s->fmt_str = "%d=%x";
 		break;
 	case RESCTRL_SCHEMA_RANGE:
-		s->fmt_str = "%d=%0*u";
+		s->fmt_str = "%d=%u";
 		break;
 	}
 
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 736b9a9a9464e..e1a982adef45a 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -214,7 +214,6 @@ enum resctrl_schema_fmt {
  * @ctrl_domains:	RCU list of all control domains for this resource
  * @mon_domains:	RCU list of all monitor domains for this resource
  * @name:		Name to use in "schemata" file.
- * @data_width:		Character width of data when displaying
  * @default_ctrl:	Specifies default cache cbm or memory B/W percent.
  * @schema_fmt:		Which format string and parser is used for this schema.
  * @evt_list:		List of monitoring events
@@ -232,7 +231,6 @@ struct rdt_resource {
 	struct list_head	ctrl_domains;
 	struct list_head	mon_domains;
 	char			*name;
-	int			data_width;
 	u32			default_ctrl;
 	enum resctrl_schema_fmt	schema_fmt;
 	struct list_head	evt_list;

From a34a4abc4033b531d9b5d4eb09b119c4f44a9278 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:36:52 +0000
Subject: [PATCH 021/236] x86/resctrl: Add max_bw to struct resctrl_membw

commit 634ebb98b929443ea1a5502c93f26d01aedbd5c8 upstream.

__rdt_get_mem_config_amd() and __get_mem_config_intel() both use the
default_ctrl property as a maximum value. This is because the MBA schema works
differently between these platforms. Doing this complicates determining
whether the default_ctrl property belongs to the arch code, or can be derived
from the schema format.

Deriving the maximum or default value from the schema format would avoid the
architecture code having to tell resctrl such obvious things as the maximum
percentage is 100, and the maximum bitmap is all ones.

Maximum bandwidth is always going to vary per platform. Add max_bw as
a special case. This is currently used for the maximum MBA percentage on Intel
platforms, but can be removed from the architecture code if 'percentage'
becomes a schema format resctrl supports directly.

This value isn't needed for other schema formats.

This will allow the default_ctrl to be generated from the schema properties
when it is needed.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-8-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c        | 2 ++
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 4 ++--
 include/linux/resctrl.h                   | 2 ++
 3 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index c6fe3616078eb..a3ca1e86e8639 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -212,6 +212,7 @@ static __init bool __get_mem_config_intel(struct rdt_resource *r)
 	hw_res->num_closid = edx.split.cos_max + 1;
 	max_delay = eax.split.max_delay + 1;
 	r->default_ctrl = MAX_MBA_BW;
+	r->membw.max_bw = MAX_MBA_BW;
 	r->membw.arch_needs_linear = true;
 	if (ecx & MBA_IS_LINEAR) {
 		r->membw.delay_linear = true;
@@ -250,6 +251,7 @@ static __init bool __rdt_get_mem_config_amd(struct rdt_resource *r)
 	cpuid_count(0x80000020, subleaf, &eax, &ebx, &ecx, &edx);
 	hw_res->num_closid = edx + 1;
 	r->default_ctrl = 1 << eax;
+	r->membw.max_bw = 1 << eax;
 
 	/* AMD does not use delay */
 	r->membw.delay_linear = false;
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 59610b209b4e9..23a01eaebd587 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -63,9 +63,9 @@ static bool bw_validate(char *buf, u32 *data, struct rdt_resource *r)
 		return true;
 	}
 
-	if (bw < r->membw.min_bw || bw > r->default_ctrl) {
+	if (bw < r->membw.min_bw || bw > r->membw.max_bw) {
 		rdt_last_cmd_printf("MB value %u out of range [%d,%d]\n",
-				    bw, r->membw.min_bw, r->default_ctrl);
+				    bw, r->membw.min_bw, r->membw.max_bw);
 		return false;
 	}
 
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index e1a982adef45a..465f3cf8c4bcb 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -165,6 +165,7 @@ enum membw_throttle_mode {
 /**
  * struct resctrl_membw - Memory bandwidth allocation related data
  * @min_bw:		Minimum memory bandwidth percentage user can request
+ * @max_bw:		Maximum memory bandwidth value, used as the reset value
  * @bw_gran:		Granularity at which the memory bandwidth is allocated
  * @delay_linear:	True if memory B/W delay is in linear scale
  * @arch_needs_linear:	True if we can't configure non-linear resources
@@ -175,6 +176,7 @@ enum membw_throttle_mode {
  */
 struct resctrl_membw {
 	u32				min_bw;
+	u32				max_bw;
 	u32				bw_gran;
 	u32				delay_linear;
 	bool				arch_needs_linear;

From d6b9f3111735e369a6562c3904cff63552ed1df5 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:36:53 +0000
Subject: [PATCH 022/236] x86/resctrl: Generate default_ctrl instead of sharing
 it

commit dbc58f7eec4039ee8f3ec27b2b41d89500debfac upstream.

The struct rdt_resource default_ctrl is used by both the architecture code for
resetting the hardware controls, and sometimes by the filesystem code as the
default value for the schema, unless the bandwidth software controller is in
use.

Having the default exposed by the architecture code causes unnecessary
duplication for each architecture as the default value must be specified, but
can be derived from other schema properties. Now that the maximum bandwidth is
explicitly described, resctrl can derive the default value from the schema
format and the other resource properties.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-9-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c        | 13 +++++--------
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c |  5 +++--
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    |  6 +++---
 include/linux/resctrl.h                   | 19 +++++++++++++++++--
 4 files changed, 28 insertions(+), 15 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index a3ca1e86e8639..bcca0d0c0dd7d 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -155,7 +155,6 @@ static inline void cache_alloc_hsw_probe(void)
 		return;
 
 	hw_res->num_closid = 4;
-	r->default_ctrl = max_cbm;
 	r->cache.cbm_len = 20;
 	r->cache.shareable_bits = 0xc0000;
 	r->cache.min_cbm_bits = 2;
@@ -211,7 +210,6 @@ static __init bool __get_mem_config_intel(struct rdt_resource *r)
 	cpuid_count(0x00000010, 3, &eax.full, &ebx, &ecx, &edx.full);
 	hw_res->num_closid = edx.split.cos_max + 1;
 	max_delay = eax.split.max_delay + 1;
-	r->default_ctrl = MAX_MBA_BW;
 	r->membw.max_bw = MAX_MBA_BW;
 	r->membw.arch_needs_linear = true;
 	if (ecx & MBA_IS_LINEAR) {
@@ -250,7 +248,6 @@ static __init bool __rdt_get_mem_config_amd(struct rdt_resource *r)
 
 	cpuid_count(0x80000020, subleaf, &eax, &ebx, &ecx, &edx);
 	hw_res->num_closid = edx + 1;
-	r->default_ctrl = 1 << eax;
 	r->membw.max_bw = 1 << eax;
 
 	/* AMD does not use delay */
@@ -276,13 +273,13 @@ static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r)
 	union cpuid_0x10_1_eax eax;
 	union cpuid_0x10_x_ecx ecx;
 	union cpuid_0x10_x_edx edx;
-	u32 ebx;
+	u32 ebx, default_ctrl;
 
 	cpuid_count(0x00000010, idx, &eax.full, &ebx, &ecx.full, &edx.full);
 	hw_res->num_closid = edx.split.cos_max + 1;
 	r->cache.cbm_len = eax.split.cbm_len + 1;
-	r->default_ctrl = BIT_MASK(eax.split.cbm_len + 1) - 1;
-	r->cache.shareable_bits = ebx & r->default_ctrl;
+	default_ctrl = BIT_MASK(eax.split.cbm_len + 1) - 1;
+	r->cache.shareable_bits = ebx & default_ctrl;
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
 		r->cache.arch_has_sparse_bitmasks = ecx.split.noncont;
 	r->alloc_capable = true;
@@ -329,7 +326,7 @@ static u32 delay_bw_map(unsigned long bw, struct rdt_resource *r)
 		return MAX_MBA_BW - bw;
 
 	pr_warn_once("Non Linear delay-bw map not supported but queried\n");
-	return r->default_ctrl;
+	return MAX_MBA_BW;
 }
 
 static void mba_wrmsr_intel(struct msr_param *m)
@@ -438,7 +435,7 @@ static void setup_default_ctrlval(struct rdt_resource *r, u32 *dc)
 	 * For Memory Allocation: Set b/w requested to 100%
 	 */
 	for (i = 0; i < hw_res->num_closid; i++, dc++)
-		*dc = r->default_ctrl;
+		*dc = resctrl_get_default_ctrl(r);
 }
 
 static void ctrl_domain_free(struct rdt_hw_ctrl_domain *hw_dom)
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 23a01eaebd587..5d87f279085f7 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -113,8 +113,9 @@ static int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s,
  */
 static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
 {
-	unsigned long first_bit, zero_bit, val;
+	u32 supported_bits = BIT_MASK(r->cache.cbm_len) - 1;
 	unsigned int cbm_len = r->cache.cbm_len;
+	unsigned long first_bit, zero_bit, val;
 	int ret;
 
 	ret = kstrtoul(buf, 16, &val);
@@ -123,7 +124,7 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
 		return false;
 	}
 
-	if ((r->cache.min_cbm_bits > 0 && val == 0) || val > r->default_ctrl) {
+	if ((r->cache.min_cbm_bits > 0 && val == 0) || val > supported_bits) {
 		rdt_last_cmd_puts("Mask out of range\n");
 		return false;
 	}
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 1e0bae1a9d950..cd8f65c12124b 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -978,7 +978,7 @@ static int rdt_default_ctrl_show(struct kernfs_open_file *of,
 	struct resctrl_schema *s = of->kn->parent->priv;
 	struct rdt_resource *r = s->res;
 
-	seq_printf(seq, "%x\n", r->default_ctrl);
+	seq_printf(seq, "%x\n", resctrl_get_default_ctrl(r));
 	return 0;
 }
 
@@ -2882,7 +2882,7 @@ static int reset_all_ctrls(struct rdt_resource *r)
 		hw_dom = resctrl_to_arch_ctrl_dom(d);
 
 		for (i = 0; i < hw_res->num_closid; i++)
-			hw_dom->ctrl_val[i] = r->default_ctrl;
+			hw_dom->ctrl_val[i] = resctrl_get_default_ctrl(r);
 		msr_param.dom = d;
 		smp_call_function_any(&d->hdr.cpu_mask, rdt_ctrl_update, &msr_param, 1);
 	}
@@ -3417,7 +3417,7 @@ static void rdtgroup_init_mba(struct rdt_resource *r, u32 closid)
 		}
 
 		cfg = &d->staged_config[CDP_NONE];
-		cfg->new_ctrl = r->default_ctrl;
+		cfg->new_ctrl = resctrl_get_default_ctrl(r);
 		cfg->have_new_ctrl = true;
 	}
 }
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 465f3cf8c4bcb..d16dc960f1fce 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -216,7 +216,6 @@ enum resctrl_schema_fmt {
  * @ctrl_domains:	RCU list of all control domains for this resource
  * @mon_domains:	RCU list of all monitor domains for this resource
  * @name:		Name to use in "schemata" file.
- * @default_ctrl:	Specifies default cache cbm or memory B/W percent.
  * @schema_fmt:		Which format string and parser is used for this schema.
  * @evt_list:		List of monitoring events
  * @cdp_capable:	Is the CDP feature available on this resource
@@ -233,7 +232,6 @@ struct rdt_resource {
 	struct list_head	ctrl_domains;
 	struct list_head	mon_domains;
 	char			*name;
-	u32			default_ctrl;
 	enum resctrl_schema_fmt	schema_fmt;
 	struct list_head	evt_list;
 	bool			cdp_capable;
@@ -268,6 +266,23 @@ struct resctrl_schema {
 	u32				num_closid;
 };
 
+/**
+ * resctrl_get_default_ctrl() - Return the default control value for this
+ *                              resource.
+ * @r:		The resource whose default control type is queried.
+ */
+static inline u32 resctrl_get_default_ctrl(struct rdt_resource *r)
+{
+	switch (r->schema_fmt) {
+	case RESCTRL_SCHEMA_BITMAP:
+		return BIT_MASK(r->cache.cbm_len) - 1;
+	case RESCTRL_SCHEMA_RANGE:
+		return r->membw.max_bw;
+	}
+
+	return WARN_ON_ONCE(1);
+}
+
 /* The number of closid supported by this resource regardless of CDP */
 u32 resctrl_arch_get_num_closid(struct rdt_resource *r);
 u32 resctrl_arch_system_num_rmid_idx(void);

From 4803be385873ad479f4513d1c3ef48ab3104ddf8 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:36:54 +0000
Subject: [PATCH 023/236] x86/resctrl: Add helper for setting CPU default
 properties

commit aebd5354dd191860033f8599048d3d3998482ee7 upstream.

rdtgroup_rmdir_ctrl() and rdtgroup_rmdir_mon() set the per-CPU pqr_state for
CPUs that were part of the rmdir()'d group.

Another architecture might not have a 'pqr_state', its hardware may need the
values in a different format. MPAM's equivalent of RMID values are not unique,
and always need the CLOSID to be provided too.

There is only one caller that modifies a single value, (rdtgroup_rmdir_mon()).
MPAM always needs both CLOSID and RMID for the hardware value as these are
written to the same system register.

As rdtgroup_rmdir_mon() has the CLOSID on hand, only provide a helper to set
both values. These values are read by __resctrl_sched_in(), but may be written
by a different CPU without any locking, add READ/WRTE_ONCE() to avoid torn
values.

Co-developed-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-10-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/include/asm/resctrl.h         | 14 +++++++++++---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 20 ++++++++++++++------
 2 files changed, 25 insertions(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h
index 8b1b6ce1e51b2..6908cd0e6e401 100644
--- a/arch/x86/include/asm/resctrl.h
+++ b/arch/x86/include/asm/resctrl.h
@@ -4,8 +4,9 @@
 
 #ifdef CONFIG_X86_CPU_RESCTRL
 
-#include <linux/sched.h>
 #include <linux/jump_label.h>
+#include <linux/percpu.h>
+#include <linux/sched.h>
 
 /*
  * This value can never be a valid CLOSID, and is used when mapping a
@@ -96,8 +97,8 @@ static inline void resctrl_arch_disable_mon(void)
 static inline void __resctrl_sched_in(struct task_struct *tsk)
 {
 	struct resctrl_pqr_state *state = this_cpu_ptr(&pqr_state);
-	u32 closid = state->default_closid;
-	u32 rmid = state->default_rmid;
+	u32 closid = READ_ONCE(state->default_closid);
+	u32 rmid = READ_ONCE(state->default_rmid);
 	u32 tmp;
 
 	/*
@@ -132,6 +133,13 @@ static inline unsigned int resctrl_arch_round_mon_val(unsigned int val)
 	return val * scale;
 }
 
+static inline void resctrl_arch_set_cpu_default_closid_rmid(int cpu, u32 closid,
+							    u32 rmid)
+{
+	WRITE_ONCE(per_cpu(pqr_state.default_closid, cpu), closid);
+	WRITE_ONCE(per_cpu(pqr_state.default_rmid, cpu), rmid);
+}
+
 static inline void resctrl_arch_set_closid_rmid(struct task_struct *tsk,
 						u32 closid, u32 rmid)
 {
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index cd8f65c12124b..f706e5a288b15 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -3731,14 +3731,21 @@ static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
 static int rdtgroup_rmdir_mon(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask)
 {
 	struct rdtgroup *prdtgrp = rdtgrp->mon.parent;
+	u32 closid, rmid;
 	int cpu;
 
 	/* Give any tasks back to the parent group */
 	rdt_move_group_tasks(rdtgrp, prdtgrp, tmpmask);
 
-	/* Update per cpu rmid of the moved CPUs first */
+	/*
+	 * Update per cpu closid/rmid of the moved CPUs first.
+	 * Note: the closid will not change, but the arch code still needs it.
+	 */
+	closid = prdtgrp->closid;
+	rmid = prdtgrp->mon.rmid;
 	for_each_cpu(cpu, &rdtgrp->cpu_mask)
-		per_cpu(pqr_state.default_rmid, cpu) = prdtgrp->mon.rmid;
+		resctrl_arch_set_cpu_default_closid_rmid(cpu, closid, rmid);
+
 	/*
 	 * Update the MSR on moved CPUs and CPUs which have moved
 	 * task running on them.
@@ -3771,6 +3778,7 @@ static int rdtgroup_ctrl_remove(struct rdtgroup *rdtgrp)
 
 static int rdtgroup_rmdir_ctrl(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask)
 {
+	u32 closid, rmid;
 	int cpu;
 
 	/* Give any tasks back to the default group */
@@ -3781,10 +3789,10 @@ static int rdtgroup_rmdir_ctrl(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask)
 		   &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);
 
 	/* Update per cpu closid and rmid of the moved CPUs first */
-	for_each_cpu(cpu, &rdtgrp->cpu_mask) {
-		per_cpu(pqr_state.default_closid, cpu) = rdtgroup_default.closid;
-		per_cpu(pqr_state.default_rmid, cpu) = rdtgroup_default.mon.rmid;
-	}
+	closid = rdtgroup_default.closid;
+	rmid = rdtgroup_default.mon.rmid;
+	for_each_cpu(cpu, &rdtgrp->cpu_mask)
+		resctrl_arch_set_cpu_default_closid_rmid(cpu, closid, rmid);
 
 	/*
 	 * Update the MSR on moved CPUs and CPUs which have moved

From 75c6737f3ad0349403a9c6929349c1d465295548 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:36:55 +0000
Subject: [PATCH 024/236] x86/resctrl: Remove rdtgroup from
 update_cpu_closid_rmid()

commit 6f06aee356bfd0c817cbe83debedd240fbed0719 upstream.

update_cpu_closid_rmid() takes a struct rdtgroup as an argument, which it uses
to update the local CPUs default pqr values. This is a problem once the
resctrl parts move out to /fs/, as the arch code cannot poke around inside
struct rdtgroup.

Rename update_cpu_closid_rmid() as resctrl_arch_sync_cpus_defaults() to be
used as the target of an IPI, and pass the effective CLOSID and RMID in a new
struct.

Co-developed-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-11-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 17 +++++++++++++----
 include/linux/resctrl.h                | 22 ++++++++++++++++++++++
 2 files changed, 35 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index f706e5a288b15..62d9a50c7bbaa 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -355,13 +355,13 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of,
  * from update_closid_rmid() is protected against __switch_to() because
  * preemption is disabled.
  */
-static void update_cpu_closid_rmid(void *info)
+void resctrl_arch_sync_cpu_closid_rmid(void *info)
 {
-	struct rdtgroup *r = info;
+	struct resctrl_cpu_defaults *r = info;
 
 	if (r) {
 		this_cpu_write(pqr_state.default_closid, r->closid);
-		this_cpu_write(pqr_state.default_rmid, r->mon.rmid);
+		this_cpu_write(pqr_state.default_rmid, r->rmid);
 	}
 
 	/*
@@ -376,11 +376,20 @@ static void update_cpu_closid_rmid(void *info)
  * Update the PGR_ASSOC MSR on all cpus in @cpu_mask,
  *
  * Per task closids/rmids must have been set up before calling this function.
+ * @r may be NULL.
  */
 static void
 update_closid_rmid(const struct cpumask *cpu_mask, struct rdtgroup *r)
 {
-	on_each_cpu_mask(cpu_mask, update_cpu_closid_rmid, r, 1);
+	struct resctrl_cpu_defaults defaults, *p = NULL;
+
+	if (r) {
+		defaults.closid = r->closid;
+		defaults.rmid = r->mon.rmid;
+		p = &defaults;
+	}
+
+	on_each_cpu_mask(cpu_mask, resctrl_arch_sync_cpu_closid_rmid, p, 1);
 }
 
 static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask,
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index d16dc960f1fce..31808b3ddecb0 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -266,6 +266,28 @@ struct resctrl_schema {
 	u32				num_closid;
 };
 
+struct resctrl_cpu_defaults {
+	u32 closid;
+	u32 rmid;
+};
+
+/**
+ * resctrl_arch_sync_cpu_closid_rmid() - Refresh this CPU's CLOSID and RMID.
+ *					 Call via IPI.
+ * @info:	If non-NULL, a pointer to a struct resctrl_cpu_defaults
+ *		specifying the new CLOSID and RMID for tasks in the default
+ *		resctrl ctrl and mon group when running on this CPU.  If NULL,
+ *		this CPU is not re-assigned to a different default group.
+ *
+ * Propagates reassignment of CPUs and/or tasks to different resctrl groups
+ * when requested by the resctrl core code.
+ *
+ * This function records the per-cpu defaults specified by @info (if any),
+ * and then reconfigures the CPU's hardware CLOSID and RMID for subsequent
+ * execution based on @current, in the same way as during a task switch.
+ */
+void resctrl_arch_sync_cpu_closid_rmid(void *info);
+
 /**
  * resctrl_get_default_ctrl() - Return the default control value for this
  *                              resource.

From 0b48184357f93cd15865078a393a11e8017c6650 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:36:56 +0000
Subject: [PATCH 025/236] x86/resctrl: Expose resctrl fs's init function to the
 rest of the kernel

commit 8079565d177f5c4eac6c2ee2ac6c404eee76d500 upstream.

rdtgroup_init() needs exposing to the rest of the kernel so that arch code can
call it once it lives in core code. As this is one of the few functions
exposed, rename it to have "resctrl" in the name. The same goes for the exit
call.

Rename x86's arch code init functions for RDT to have an arch prefix to make
it clear these are part of the architecture code.

Co-developed-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-12-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c     | 12 ++++++------
 arch/x86/kernel/cpu/resctrl/internal.h |  3 ---
 arch/x86/kernel/cpu/resctrl/monitor.c  |  2 +-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c |  8 ++++----
 include/linux/resctrl.h                |  3 +++
 5 files changed, 14 insertions(+), 14 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index bcca0d0c0dd7d..a00070ce28775 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -1074,7 +1074,7 @@ void resctrl_cpu_detect(struct cpuinfo_x86 *c)
 	}
 }
 
-static int __init resctrl_late_init(void)
+static int __init resctrl_arch_late_init(void)
 {
 	struct rdt_resource *r;
 	int state, ret;
@@ -1097,7 +1097,7 @@ static int __init resctrl_late_init(void)
 	if (state < 0)
 		return state;
 
-	ret = rdtgroup_init();
+	ret = resctrl_init();
 	if (ret) {
 		cpuhp_remove_state(state);
 		return ret;
@@ -1113,18 +1113,18 @@ static int __init resctrl_late_init(void)
 	return 0;
 }
 
-late_initcall(resctrl_late_init);
+late_initcall(resctrl_arch_late_init);
 
-static void __exit resctrl_exit(void)
+static void __exit resctrl_arch_exit(void)
 {
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
 
 	cpuhp_remove_state(rdt_online);
 
-	rdtgroup_exit();
+	resctrl_exit();
 
 	if (r->mon_capable)
 		rdt_put_mon_l3_config();
 }
 
-__exitcall(resctrl_exit);
+__exitcall(resctrl_arch_exit);
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 986246a3a93fc..bad2a7bb4e9e1 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -331,9 +331,6 @@ extern struct list_head rdt_all_groups;
 
 extern int max_name_width;
 
-int __init rdtgroup_init(void);
-void __exit rdtgroup_exit(void);
-
 /**
  * struct rftype - describe each file in the resctrl file system
  * @name:	File name
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 1193a039adeca..727e92de35de0 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -1027,7 +1027,7 @@ static int dom_data_init(struct rdt_resource *r)
 	/*
 	 * RESCTRL_RESERVED_CLOSID and RESCTRL_RESERVED_RMID are special and
 	 * are always allocated. These are used for the rdtgroup_default
-	 * control group, which will be setup later in rdtgroup_init().
+	 * control group, which will be setup later in resctrl_init().
 	 */
 	idx = resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID,
 					   RESCTRL_RESERVED_RMID);
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 62d9a50c7bbaa..b2dad689e780c 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -4235,14 +4235,14 @@ void resctrl_offline_cpu(unsigned int cpu)
 }
 
 /*
- * rdtgroup_init - rdtgroup initialization
+ * resctrl_init - resctrl filesystem initialization
  *
  * Setup resctrl file system including set up root, create mount point,
- * register rdtgroup filesystem, and initialize files under root directory.
+ * register resctrl filesystem, and initialize files under root directory.
  *
  * Return: 0 on success or -errno
  */
-int __init rdtgroup_init(void)
+int __init resctrl_init(void)
 {
 	int ret = 0;
 
@@ -4290,7 +4290,7 @@ int __init rdtgroup_init(void)
 	return ret;
 }
 
-void __exit rdtgroup_exit(void)
+void __exit resctrl_exit(void)
 {
 	debugfs_remove_recursive(debugfs_resctrl);
 	unregister_filesystem(&rdt_fs_type);
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 31808b3ddecb0..f1979e375da9a 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -402,4 +402,7 @@ void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *
 extern unsigned int resctrl_rmid_realloc_threshold;
 extern unsigned int resctrl_rmid_realloc_limit;
 
+int __init resctrl_init(void);
+void __exit resctrl_exit(void);
+
 #endif /* _RESCTRL_H */

From d226cbabd67052496419bec62433ce8ebc4963f4 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:36:57 +0000
Subject: [PATCH 026/236] x86/resctrl: Move rdt_find_domain() to be visible to
 arch and fs code

commit e3d5138cefbffa8ea1bf8aab3629268bc3381219 upstream.

rdt_find_domain() finds a domain given a resource and a cache-id.  This is
used by both the architecture code and the filesystem code.

After the filesystem code moves to live in /fs/, this helper is either
duplicated by all architectures, or needs exposing by the filesystem code.

Add the declaration to the global header file. As it's now globally visible,
and has only a handful of callers, swap the 'rdt' for 'resctrl'. Move the
function to live with its caller in ctrlmondata.c as the filesystem code will
not have anything corresponding to core.c.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-13-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c        | 38 +++--------------------
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 24 +++++++++++++-
 arch/x86/kernel/cpu/resctrl/internal.h    |  2 --
 include/linux/resctrl.h                   | 14 +++++++++
 4 files changed, 41 insertions(+), 37 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index a00070ce28775..4706b50829424 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -394,36 +394,6 @@ void rdt_ctrl_update(void *arg)
 	hw_res->msr_update(m);
 }
 
-/*
- * rdt_find_domain - Search for a domain id in a resource domain list.
- *
- * Search the domain list to find the domain id. If the domain id is
- * found, return the domain. NULL otherwise.  If the domain id is not
- * found (and NULL returned) then the first domain with id bigger than
- * the input id can be returned to the caller via @pos.
- */
-struct rdt_domain_hdr *rdt_find_domain(struct list_head *h, int id,
-				       struct list_head **pos)
-{
-	struct rdt_domain_hdr *d;
-	struct list_head *l;
-
-	list_for_each(l, h) {
-		d = list_entry(l, struct rdt_domain_hdr, list);
-		/* When id is found, return its domain. */
-		if (id == d->id)
-			return d;
-		/* Stop searching when finding id's position in sorted list. */
-		if (id < d->id)
-			break;
-	}
-
-	if (pos)
-		*pos = l;
-
-	return NULL;
-}
-
 static void setup_default_ctrlval(struct rdt_resource *r, u32 *dc)
 {
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
@@ -534,7 +504,7 @@ static void domain_add_cpu_ctrl(int cpu, struct rdt_resource *r)
 		return;
 	}
 
-	hdr = rdt_find_domain(&r->ctrl_domains, id, &add_pos);
+	hdr = resctrl_find_domain(&r->ctrl_domains, id, &add_pos);
 	if (hdr) {
 		if (WARN_ON_ONCE(hdr->type != RESCTRL_CTRL_DOMAIN))
 			return;
@@ -589,7 +559,7 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
 		return;
 	}
 
-	hdr = rdt_find_domain(&r->mon_domains, id, &add_pos);
+	hdr = resctrl_find_domain(&r->mon_domains, id, &add_pos);
 	if (hdr) {
 		if (WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN))
 			return;
@@ -654,7 +624,7 @@ static void domain_remove_cpu_ctrl(int cpu, struct rdt_resource *r)
 		return;
 	}
 
-	hdr = rdt_find_domain(&r->ctrl_domains, id, NULL);
+	hdr = resctrl_find_domain(&r->ctrl_domains, id, NULL);
 	if (!hdr) {
 		pr_warn("Can't find control domain for id=%d for CPU %d for resource %s\n",
 			id, cpu, r->name);
@@ -700,7 +670,7 @@ static void domain_remove_cpu_mon(int cpu, struct rdt_resource *r)
 		return;
 	}
 
-	hdr = rdt_find_domain(&r->mon_domains, id, NULL);
+	hdr = resctrl_find_domain(&r->mon_domains, id, NULL);
 	if (!hdr) {
 		pr_warn("Can't find monitor domain for id=%d for CPU %d for resource %s\n",
 			id, cpu, r->name);
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 5d87f279085f7..763317ea22565 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -610,6 +610,28 @@ int rdtgroup_mba_mbps_event_show(struct kernfs_open_file *of,
 	return ret;
 }
 
+struct rdt_domain_hdr *resctrl_find_domain(struct list_head *h, int id,
+					   struct list_head **pos)
+{
+	struct rdt_domain_hdr *d;
+	struct list_head *l;
+
+	list_for_each(l, h) {
+		d = list_entry(l, struct rdt_domain_hdr, list);
+		/* When id is found, return its domain. */
+		if (id == d->id)
+			return d;
+		/* Stop searching when finding id's position in sorted list. */
+		if (id < d->id)
+			break;
+	}
+
+	if (pos)
+		*pos = l;
+
+	return NULL;
+}
+
 void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 		    struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
 		    cpumask_t *cpumask, int evtid, int first)
@@ -695,7 +717,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 		 * This file provides data from a single domain. Search
 		 * the resource to find the domain with "domid".
 		 */
-		hdr = rdt_find_domain(&r->mon_domains, domid, NULL);
+		hdr = resctrl_find_domain(&r->mon_domains, domid, NULL);
 		if (!hdr || WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN)) {
 			ret = -ENOENT;
 			goto out;
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index bad2a7bb4e9e1..6e9470450f2e6 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -584,8 +584,6 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn);
 int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name);
 int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name,
 			     umode_t mask);
-struct rdt_domain_hdr *rdt_find_domain(struct list_head *h, int id,
-				       struct list_head **pos);
 ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 				char *buf, size_t nbytes, loff_t off);
 int rdtgroup_schemata_show(struct kernfs_open_file *of,
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index f1979e375da9a..93d9a435f035f 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -372,6 +372,20 @@ static inline void resctrl_arch_rmid_read_context_check(void)
 		might_sleep();
 }
 
+/**
+ * resctrl_find_domain() - Search for a domain id in a resource domain list.
+ * @h:		The domain list to search.
+ * @id:		The domain id to search for.
+ * @pos:	A pointer to position in the list id should be inserted.
+ *
+ * Search the domain list to find the domain id. If the domain id is
+ * found, return the domain. NULL otherwise.  If the domain id is not
+ * found (and NULL returned) then the first domain with id bigger than
+ * the input id can be returned to the caller via @pos.
+ */
+struct rdt_domain_hdr *resctrl_find_domain(struct list_head *h, int id,
+					   struct list_head **pos);
+
 /**
  * resctrl_arch_reset_rmid() - Reset any private state associated with rmid
  *			       and eventid.

From ade8d3e9719b1ceeabd7839b7f928712ed215d04 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:36:58 +0000
Subject: [PATCH 027/236] x86/resctrl: Move resctrl types to a separate header

commit f16adbaf9272ea7ed5d7bf8b261be8a9be949c31 upstream.

When resctrl is fully factored into core and per-arch code, each arch will
need to use some resctrl common definitions in order to define its own
specializations and helpers.  Following conventional practice, it would be
desirable to put the dependent arch definitions in an <asm/resctrl.h> header
that is included by the common <linux/resctrl.h> header.  However, this can
make it awkward to avoid a circular dependency between <linux/resctrl.h> and
the arch header.

To avoid such dependencies, move the affected common types and constants into
a new header that does not need to depend on <linux/resctrl.h> or on the arch
headers.

The same logic applies to the monitor-configuration defines, move these too.

Some kind of enumeration for events is needed between the filesystem and
architecture code. Take the x86 definition as its convenient for x86.

The definition of enum resctrl_event_id is needed to allow the architecture
code to define resctrl_arch_mon_ctx_alloc() and resctrl_arch_mon_ctx_free().

The definition of enum resctrl_res_level is needed to allow the architecture
code to define resctrl_arch_set_cdp_enabled() and
resctrl_arch_get_cdp_enabled().

The bits for mbm_local_bytes_config et al are ABI, and must be the same on all
architectures. These are documented in Documentation/arch/x86/resctrl.rst

The maintainers entry for these headers was missed when resctrl.h was created.
Add a wildcard entry to match both resctrl.h and resctrl_types.h.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-14-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 MAINTAINERS                            |  1 +
 arch/x86/include/asm/resctrl.h         |  1 +
 arch/x86/kernel/cpu/resctrl/internal.h | 24 ------------
 include/linux/resctrl.h                | 21 +---------
 include/linux/resctrl_types.h          | 54 ++++++++++++++++++++++++++
 5 files changed, 57 insertions(+), 44 deletions(-)
 create mode 100644 include/linux/resctrl_types.h

diff --git a/MAINTAINERS b/MAINTAINERS
index 26ab6e9e04c46..2fc1cc1f312c8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -18111,6 +18111,7 @@ S:	Supported
 F:	Documentation/arch/x86/resctrl*
 F:	arch/x86/include/asm/resctrl.h
 F:	arch/x86/kernel/cpu/resctrl/
+F:	include/linux/resctrl*.h
 F:	tools/testing/selftests/resctrl/
 
 READ-COPY UPDATE (RCU)
diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h
index 6908cd0e6e401..52f2326e2b1e6 100644
--- a/arch/x86/include/asm/resctrl.h
+++ b/arch/x86/include/asm/resctrl.h
@@ -6,6 +6,7 @@
 
 #include <linux/jump_label.h>
 #include <linux/percpu.h>
+#include <linux/resctrl_types.h>
 #include <linux/sched.h>
 
 /*
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 6e9470450f2e6..7521983a05147 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -35,30 +35,6 @@
  */
 #define MBM_CNTR_WIDTH_OFFSET_MAX (62 - MBM_CNTR_WIDTH_BASE)
 
-/* Reads to Local DRAM Memory */
-#define READS_TO_LOCAL_MEM		BIT(0)
-
-/* Reads to Remote DRAM Memory */
-#define READS_TO_REMOTE_MEM		BIT(1)
-
-/* Non-Temporal Writes to Local Memory */
-#define NON_TEMP_WRITE_TO_LOCAL_MEM	BIT(2)
-
-/* Non-Temporal Writes to Remote Memory */
-#define NON_TEMP_WRITE_TO_REMOTE_MEM	BIT(3)
-
-/* Reads to Local Memory the system identifies as "Slow Memory" */
-#define READS_TO_LOCAL_S_MEM		BIT(4)
-
-/* Reads to Remote Memory the system identifies as "Slow Memory" */
-#define READS_TO_REMOTE_S_MEM		BIT(5)
-
-/* Dirty Victims to All Types of Memory */
-#define DIRTY_VICTIMS_TO_ALL_MEM	BIT(6)
-
-/* Max event bits supported */
-#define MAX_EVT_CONFIG_BITS		GENMASK(6, 0)
-
 /**
  * cpumask_any_housekeeping() - Choose any CPU in @mask, preferring those that
  *			        aren't marked nohz_full
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 93d9a435f035f..326f7ba220e79 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -6,6 +6,7 @@
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/pid.h>
+#include <linux/resctrl_types.h>
 
 /* CLOSID, RMID value used by the default control group */
 #define RESCTRL_RESERVED_CLOSID		0
@@ -37,28 +38,8 @@ enum resctrl_conf_type {
 	CDP_DATA,
 };
 
-enum resctrl_res_level {
-	RDT_RESOURCE_L3,
-	RDT_RESOURCE_L2,
-	RDT_RESOURCE_MBA,
-	RDT_RESOURCE_SMBA,
-
-	/* Must be the last */
-	RDT_NUM_RESOURCES,
-};
-
 #define CDP_NUM_TYPES	(CDP_DATA + 1)
 
-/*
- * Event IDs, the values match those used to program IA32_QM_EVTSEL before
- * reading IA32_QM_CTR on RDT systems.
- */
-enum resctrl_event_id {
-	QOS_L3_OCCUP_EVENT_ID		= 0x01,
-	QOS_L3_MBM_TOTAL_EVENT_ID	= 0x02,
-	QOS_L3_MBM_LOCAL_EVENT_ID	= 0x03,
-};
-
 /**
  * struct resctrl_staged_config - parsed configuration to be applied
  * @new_ctrl:		new ctrl value to be loaded
diff --git a/include/linux/resctrl_types.h b/include/linux/resctrl_types.h
new file mode 100644
index 0000000000000..f26450b3326b1
--- /dev/null
+++ b/include/linux/resctrl_types.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2025 Arm Ltd.
+ * Based on arch/x86/kernel/cpu/resctrl/internal.h
+ */
+
+#ifndef __LINUX_RESCTRL_TYPES_H
+#define __LINUX_RESCTRL_TYPES_H
+
+/* Reads to Local DRAM Memory */
+#define READS_TO_LOCAL_MEM		BIT(0)
+
+/* Reads to Remote DRAM Memory */
+#define READS_TO_REMOTE_MEM		BIT(1)
+
+/* Non-Temporal Writes to Local Memory */
+#define NON_TEMP_WRITE_TO_LOCAL_MEM	BIT(2)
+
+/* Non-Temporal Writes to Remote Memory */
+#define NON_TEMP_WRITE_TO_REMOTE_MEM	BIT(3)
+
+/* Reads to Local Memory the system identifies as "Slow Memory" */
+#define READS_TO_LOCAL_S_MEM		BIT(4)
+
+/* Reads to Remote Memory the system identifies as "Slow Memory" */
+#define READS_TO_REMOTE_S_MEM		BIT(5)
+
+/* Dirty Victims to All Types of Memory */
+#define DIRTY_VICTIMS_TO_ALL_MEM	BIT(6)
+
+/* Max event bits supported */
+#define MAX_EVT_CONFIG_BITS		GENMASK(6, 0)
+
+enum resctrl_res_level {
+	RDT_RESOURCE_L3,
+	RDT_RESOURCE_L2,
+	RDT_RESOURCE_MBA,
+	RDT_RESOURCE_SMBA,
+
+	/* Must be the last */
+	RDT_NUM_RESOURCES,
+};
+
+/*
+ * Event IDs, the values match those used to program IA32_QM_EVTSEL before
+ * reading IA32_QM_CTR on RDT systems.
+ */
+enum resctrl_event_id {
+	QOS_L3_OCCUP_EVENT_ID		= 0x01,
+	QOS_L3_MBM_TOTAL_EVENT_ID	= 0x02,
+	QOS_L3_MBM_LOCAL_EVENT_ID	= 0x03,
+};
+
+#endif /* __LINUX_RESCTRL_TYPES_H */

From 9df29b8c39d7bfe669bf7b0e6fa176db9f829160 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:36:59 +0000
Subject: [PATCH 028/236] x86/resctrl: Add an arch helper to reset one resource

commit 9be68b144a5b539c8503f2944888f7a30e669291 upstream.

On umount(), resctrl resets each resource back to its default configuration.
It only ever does this for all resources in one go.

reset_all_ctrls() is architecture specific as it works with struct
rdt_hw_resource.

Make reset_all_ctrls() an arch helper that resets one resource.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-15-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 9 +++++----
 include/linux/resctrl.h                | 9 +++++++++
 2 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index b2dad689e780c..9eb57ebb36c64 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -2867,7 +2867,7 @@ static int rdt_init_fs_context(struct fs_context *fc)
 	return 0;
 }
 
-static int reset_all_ctrls(struct rdt_resource *r)
+void resctrl_arch_reset_all_ctrls(struct rdt_resource *r)
 {
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 	struct rdt_hw_ctrl_domain *hw_dom;
@@ -2896,7 +2896,7 @@ static int reset_all_ctrls(struct rdt_resource *r)
 		smp_call_function_any(&d->hdr.cpu_mask, rdt_ctrl_update, &msr_param, 1);
 	}
 
-	return 0;
+	return;
 }
 
 /*
@@ -3015,9 +3015,10 @@ static void rdt_kill_sb(struct super_block *sb)
 
 	rdt_disable_ctx();
 
-	/*Put everything back to default values. */
+	/* Put everything back to default values. */
 	for_each_alloc_capable_rdt_resource(r)
-		reset_all_ctrls(r);
+		resctrl_arch_reset_all_ctrls(r);
+
 	rmdir_all_sub();
 	rdt_pseudo_lock_release();
 	rdtgroup_default.mode = RDT_MODE_SHAREABLE;
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 326f7ba220e79..487b9657a7b52 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -394,6 +394,15 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d,
  */
 void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d);
 
+/**
+ * resctrl_arch_reset_all_ctrls() - Reset the control for each CLOSID to its
+ *				    default.
+ * @r:		The resctrl resource to reset.
+ *
+ * This can be called from any CPU.
+ */
+void resctrl_arch_reset_all_ctrls(struct rdt_resource *r);
+
 extern unsigned int resctrl_rmid_realloc_threshold;
 extern unsigned int resctrl_rmid_realloc_limit;
 

From a20242f2d4750accf4c5067697abe0d612a96efe Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:37:00 +0000
Subject: [PATCH 029/236] x86/resctrl: Move monitor exit work to a resctrl exit
 call

commit 011842727fa449f834c17b69d1273d88eb6e3309 upstream.

rdt_put_mon_l3_config() is called via the architecture's resctrl_arch_exit()
call, and appears to free the rmid_ptrs[] and closid_num_dirty_rmid[] arrays.
In reality this code is marked __exit, and is removed by the linker as resctrl
can't be built as a module.

To separate the filesystem and architecture parts of resctrl, this free()ing
work needs to be triggered by the filesystem, as these structures belong to
the filesystem code.

Rename rdt_put_mon_l3_config() to resctrl_mon_resource_exit() and call it from
resctrl_exit(). The kfree() is currently dependent on r->mon_capable.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-16-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c     |  5 -----
 arch/x86/kernel/cpu/resctrl/internal.h |  2 +-
 arch/x86/kernel/cpu/resctrl/monitor.c  | 12 +++++++++---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c |  2 ++
 4 files changed, 12 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 4706b50829424..995610aa62e7f 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -1087,14 +1087,9 @@ late_initcall(resctrl_arch_late_init);
 
 static void __exit resctrl_arch_exit(void)
 {
-	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-
 	cpuhp_remove_state(rdt_online);
 
 	resctrl_exit();
-
-	if (r->mon_capable)
-		rdt_put_mon_l3_config();
 }
 
 __exitcall(resctrl_arch_exit);
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 7521983a05147..4b7dbb0431876 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -589,7 +589,7 @@ void closid_free(int closid);
 int alloc_rmid(u32 closid);
 void free_rmid(u32 closid, u32 rmid);
 int rdt_get_mon_l3_config(struct rdt_resource *r);
-void __exit rdt_put_mon_l3_config(void);
+void __exit resctrl_mon_resource_exit(void);
 bool __init rdt_cpu_has(int flag);
 void mon_event_count(void *info);
 int rdtgroup_mondata_show(struct seq_file *m, void *arg);
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 727e92de35de0..662e915ce20ef 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -1040,10 +1040,13 @@ static int dom_data_init(struct rdt_resource *r)
 	return err;
 }
 
-static void __exit dom_data_exit(void)
+static void __exit dom_data_exit(struct rdt_resource *r)
 {
 	mutex_lock(&rdtgroup_mutex);
 
+	if (!r->mon_capable)
+		goto out_unlock;
+
 	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
 		kfree(closid_num_dirty_rmid);
 		closid_num_dirty_rmid = NULL;
@@ -1052,6 +1055,7 @@ static void __exit dom_data_exit(void)
 	kfree(rmid_ptrs);
 	rmid_ptrs = NULL;
 
+out_unlock:
 	mutex_unlock(&rdtgroup_mutex);
 }
 
@@ -1237,9 +1241,11 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 	return 0;
 }
 
-void __exit rdt_put_mon_l3_config(void)
+void __exit resctrl_mon_resource_exit(void)
 {
-	dom_data_exit();
+	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
+
+	dom_data_exit(r);
 }
 
 void __init intel_rdt_mbm_apply_quirk(void)
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 9eb57ebb36c64..42c48e79364d6 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -4296,4 +4296,6 @@ void __exit resctrl_exit(void)
 	debugfs_remove_recursive(debugfs_resctrl);
 	unregister_filesystem(&rdt_fs_type);
 	sysfs_remove_mount_point(fs_kobj, "resctrl");
+
+	resctrl_mon_resource_exit();
 }

From 5725ef4a73651c11d71660612831215b4c44bf70 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:37:01 +0000
Subject: [PATCH 030/236] x86/resctrl: Move monitor init work to a resctrl init
 call

commit 4b6bdbf27fcee16944911155293771b880344ef0 upstream.

rdt_get_mon_l3_config() is called from the arch's resctrl_arch_late_init(),
and initialises both architecture specific fields, such as hw_res->mon_scale
and resctrl filesystem fields by calling dom_data_init().

To separate the filesystem and architecture parts of resctrl, this function
needs splitting up.

Add resctrl_mon_resource_init() to do the filesystem specific work, and call
it from resctrl_init(). This runs later, but is still before the filesystem is
mounted and the rmid_ptrs[] array can be used.

  [ bp: Massage commit message. ]

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-17-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/internal.h |  3 +-
 arch/x86/kernel/cpu/resctrl/monitor.c  | 40 ++++++++++++++++++++------
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 22 +++++++++++++-
 3 files changed, 54 insertions(+), 11 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 4b7dbb0431876..48186a50f8430 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -589,13 +589,14 @@ void closid_free(int closid);
 int alloc_rmid(u32 closid);
 void free_rmid(u32 closid, u32 rmid);
 int rdt_get_mon_l3_config(struct rdt_resource *r);
-void __exit resctrl_mon_resource_exit(void);
+void resctrl_mon_resource_exit(void);
 bool __init rdt_cpu_has(int flag);
 void mon_event_count(void *info);
 int rdtgroup_mondata_show(struct seq_file *m, void *arg);
 void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 		    struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
 		    cpumask_t *cpumask, int evtid, int first);
+int __init resctrl_mon_resource_init(void);
 void mbm_setup_overflow_handler(struct rdt_mon_domain *dom,
 				unsigned long delay_ms,
 				int exclude_cpu);
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 662e915ce20ef..5b03488dbf9a4 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -1040,7 +1040,7 @@ static int dom_data_init(struct rdt_resource *r)
 	return err;
 }
 
-static void __exit dom_data_exit(struct rdt_resource *r)
+static void dom_data_exit(struct rdt_resource *r)
 {
 	mutex_lock(&rdtgroup_mutex);
 
@@ -1176,12 +1176,40 @@ static __init int snc_get_config(void)
 	return ret;
 }
 
+/**
+ * resctrl_mon_resource_init() - Initialise global monitoring structures.
+ *
+ * Allocate and initialise global monitor resources that do not belong to a
+ * specific domain. i.e. the rmid_ptrs[] used for the limbo and free lists.
+ * Called once during boot after the struct rdt_resource's have been configured
+ * but before the filesystem is mounted.
+ * Resctrl's cpuhp callbacks may be called before this point to bring a domain
+ * online.
+ *
+ * Returns 0 for success, or -ENOMEM.
+ */
+int __init resctrl_mon_resource_init(void)
+{
+	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
+	int ret;
+
+	if (!r->mon_capable)
+		return 0;
+
+	ret = dom_data_init(r);
+	if (ret)
+		return ret;
+
+	l3_mon_evt_init(r);
+
+	return 0;
+}
+
 int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 {
 	unsigned int mbm_offset = boot_cpu_data.x86_cache_mbm_width_offset;
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 	unsigned int threshold;
-	int ret;
 
 	snc_nodes_per_l3_cache = snc_get_config();
 
@@ -1211,10 +1239,6 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 	 */
 	resctrl_rmid_realloc_threshold = resctrl_arch_round_mon_val(threshold);
 
-	ret = dom_data_init(r);
-	if (ret)
-		return ret;
-
 	if (rdt_cpu_has(X86_FEATURE_BMEC)) {
 		u32 eax, ebx, ecx, edx;
 
@@ -1234,14 +1258,12 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 		}
 	}
 
-	l3_mon_evt_init(r);
-
 	r->mon_capable = true;
 
 	return 0;
 }
 
-void __exit resctrl_mon_resource_exit(void)
+void resctrl_mon_resource_exit(void)
 {
 	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
 
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 42c48e79364d6..badac3f5da72f 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -4102,6 +4102,19 @@ void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d
 	mutex_unlock(&rdtgroup_mutex);
 }
 
+/**
+ * domain_setup_mon_state() -  Initialise domain monitoring structures.
+ * @r:	The resource for the newly online domain.
+ * @d:	The newly online domain.
+ *
+ * Allocate monitor resources that belong to this domain.
+ * Called when the first CPU of a domain comes online, regardless of whether
+ * the filesystem is mounted.
+ * During boot this may be called before global allocations have been made by
+ * resctrl_mon_resource_init().
+ *
+ * Returns 0 for success, or -ENOMEM.
+ */
 static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_mon_domain *d)
 {
 	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
@@ -4252,10 +4265,16 @@ int __init resctrl_init(void)
 
 	rdtgroup_setup_default();
 
-	ret = sysfs_create_mount_point(fs_kobj, "resctrl");
+	ret = resctrl_mon_resource_init();
 	if (ret)
 		return ret;
 
+	ret = sysfs_create_mount_point(fs_kobj, "resctrl");
+	if (ret) {
+		resctrl_mon_resource_exit();
+		return ret;
+	}
+
 	ret = register_filesystem(&rdt_fs_type);
 	if (ret)
 		goto cleanup_mountpoint;
@@ -4287,6 +4306,7 @@ int __init resctrl_init(void)
 
 cleanup_mountpoint:
 	sysfs_remove_mount_point(fs_kobj, "resctrl");
+	resctrl_mon_resource_exit();
 
 	return ret;
 }

From 1b3426f4967c48e1db7b4d50adba7eb43d53aeea Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:37:02 +0000
Subject: [PATCH 031/236] x86/resctrl: Rewrite and move the
 for_each_*_rdt_resource() walkers

commit 88464bff035ecb28f8bf52dd9728fdc1aca228f9 upstream.

The for_each_*_rdt_resource() helpers walk the architecture's array of
structures, using the resctrl visible part as an iterator. These became
over-complex when the structures were split into a filesystem and
architecture-specific struct. This approach avoided the need to touch every
call site, and was done before there was a helper to retrieve a resource by
rid.

Once the filesystem parts of resctrl are moved to /fs/, both the arch's
resource array, and the definition of those structures is no longer
accessible. To support resctrl, each architecture would have to provide
equally complex macros.

Rewrite the macro to make use of resctrl_arch_get_resource(), and move these
to include/linux/resctrl.h so existing x86 arch code continues to use them.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-18-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/internal.h | 29 --------------------------
 include/linux/resctrl.h                | 18 ++++++++++++++++
 2 files changed, 18 insertions(+), 29 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 48186a50f8430..8c276e7f015d7 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -478,14 +478,6 @@ extern struct rdtgroup rdtgroup_default;
 extern struct dentry *debugfs_resctrl;
 extern enum resctrl_event_id mba_mbps_default_event;
 
-static inline struct rdt_resource *resctrl_inc(struct rdt_resource *res)
-{
-	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(res);
-
-	hw_res++;
-	return &hw_res->r_resctrl;
-}
-
 static inline bool resctrl_arch_get_cdp_enabled(enum resctrl_res_level l)
 {
 	return rdt_resources_all[l].cdp_enabled;
@@ -495,27 +487,6 @@ int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable);
 
 void arch_mon_domain_online(struct rdt_resource *r, struct rdt_mon_domain *d);
 
-/*
- * To return the common struct rdt_resource, which is contained in struct
- * rdt_hw_resource, walk the resctrl member of struct rdt_hw_resource.
- */
-#define for_each_rdt_resource(r)					      \
-	for (r = &rdt_resources_all[0].r_resctrl;			      \
-	     r <= &rdt_resources_all[RDT_NUM_RESOURCES - 1].r_resctrl;	      \
-	     r = resctrl_inc(r))
-
-#define for_each_capable_rdt_resource(r)				      \
-	for_each_rdt_resource(r)					      \
-		if (r->alloc_capable || r->mon_capable)
-
-#define for_each_alloc_capable_rdt_resource(r)				      \
-	for_each_rdt_resource(r)					      \
-		if (r->alloc_capable)
-
-#define for_each_mon_capable_rdt_resource(r)				      \
-	for_each_rdt_resource(r)					      \
-		if (r->mon_capable)
-
 /* CPUID.(EAX=10H, ECX=ResID=1).EAX */
 union cpuid_0x10_1_eax {
 	struct {
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 487b9657a7b52..a392480dc4b63 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -26,6 +26,24 @@ int proc_resctrl_show(struct seq_file *m,
 /* max value for struct rdt_domain's mbps_val */
 #define MBA_MAX_MBPS   U32_MAX
 
+/* Walk all possible resources, with variants for only controls or monitors. */
+#define for_each_rdt_resource(_r)						\
+	for ((_r) = resctrl_arch_get_resource(0);				\
+	     (_r) && (_r)->rid < RDT_NUM_RESOURCES;				\
+	     (_r) = resctrl_arch_get_resource((_r)->rid + 1))
+
+#define for_each_capable_rdt_resource(r)				      \
+	for_each_rdt_resource((r))					      \
+		if ((r)->alloc_capable || (r)->mon_capable)
+
+#define for_each_alloc_capable_rdt_resource(r)				      \
+	for_each_rdt_resource((r))					      \
+		if ((r)->alloc_capable)
+
+#define for_each_mon_capable_rdt_resource(r)				      \
+	for_each_rdt_resource((r))					      \
+		if ((r)->mon_capable)
+
 /**
  * enum resctrl_conf_type - The type of configuration.
  * @CDP_NONE:	No prioritisation, both code and data are controlled or monitored.

From 993d7aa9a14a317667d1bf17982a688a000282fe Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:37:03 +0000
Subject: [PATCH 032/236] x86/resctrl: Move the is_mbm_*_enabled() helpers to
 asm/resctrl.h

commit d012b66a16618509242a51f5f6c9b19868ba5159 upstream.

The architecture specific parts of resctrl provide helpers like
is_mbm_total_enabled() and is_mbm_local_enabled() to hide accesses to the
rdt_mon_features bitmap.

Exposing a group of helpers between the architecture and filesystem code is
preferable to a single unsigned-long like rdt_mon_features. Helpers can be more
readable and have a well defined behaviour, while allowing architectures to hide
more complex behaviour.

Once the filesystem parts of resctrl are moved, these existing helpers can no
longer live in internal.h. Move them to include/linux/resctrl.h Once these are
exposed to the wider kernel, they should have a 'resctrl_arch_' prefix, to fit
the rest of the arch<->fs interface.

Move and rename the helpers that touch rdt_mon_features directly. is_mbm_event()
and is_mbm_enabled() are only called from rdtgroup.c, so can be moved into that
file.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-19-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/include/asm/resctrl.h            | 16 +++++++++
 arch/x86/kernel/cpu/resctrl/core.c        |  8 ++---
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c |  4 +--
 arch/x86/kernel/cpu/resctrl/internal.h    | 27 ---------------
 arch/x86/kernel/cpu/resctrl/monitor.c     | 16 ++++-----
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    | 40 +++++++++++++++--------
 6 files changed, 56 insertions(+), 55 deletions(-)

diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h
index 52f2326e2b1e6..6d4c7ea2c9e34 100644
--- a/arch/x86/include/asm/resctrl.h
+++ b/arch/x86/include/asm/resctrl.h
@@ -42,6 +42,7 @@ DECLARE_PER_CPU(struct resctrl_pqr_state, pqr_state);
 
 extern bool rdt_alloc_capable;
 extern bool rdt_mon_capable;
+extern unsigned int rdt_mon_features;
 
 DECLARE_STATIC_KEY_FALSE(rdt_enable_key);
 DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
@@ -81,6 +82,21 @@ static inline void resctrl_arch_disable_mon(void)
 	static_branch_dec_cpuslocked(&rdt_enable_key);
 }
 
+static inline bool resctrl_arch_is_llc_occupancy_enabled(void)
+{
+	return (rdt_mon_features & (1 << QOS_L3_OCCUP_EVENT_ID));
+}
+
+static inline bool resctrl_arch_is_mbm_total_enabled(void)
+{
+	return (rdt_mon_features & (1 << QOS_L3_MBM_TOTAL_EVENT_ID));
+}
+
+static inline bool resctrl_arch_is_mbm_local_enabled(void)
+{
+	return (rdt_mon_features & (1 << QOS_L3_MBM_LOCAL_EVENT_ID));
+}
+
 /*
  * __resctrl_sched_in() - Writes the task's CLOSid/RMID to IA32_PQR_MSR
  *
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 995610aa62e7f..78f94ab9bb76d 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -453,13 +453,13 @@ static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_mon_domain *hw_dom)
 {
 	size_t tsize;
 
-	if (is_mbm_total_enabled()) {
+	if (resctrl_arch_is_mbm_total_enabled()) {
 		tsize = sizeof(*hw_dom->arch_mbm_total);
 		hw_dom->arch_mbm_total = kcalloc(num_rmid, tsize, GFP_KERNEL);
 		if (!hw_dom->arch_mbm_total)
 			return -ENOMEM;
 	}
-	if (is_mbm_local_enabled()) {
+	if (resctrl_arch_is_mbm_local_enabled()) {
 		tsize = sizeof(*hw_dom->arch_mbm_local);
 		hw_dom->arch_mbm_local = kcalloc(num_rmid, tsize, GFP_KERNEL);
 		if (!hw_dom->arch_mbm_local) {
@@ -909,9 +909,9 @@ static __init bool get_rdt_mon_resources(void)
 	if (!rdt_mon_features)
 		return false;
 
-	if (is_mbm_local_enabled())
+	if (resctrl_arch_is_mbm_local_enabled())
 		mba_mbps_default_event = QOS_L3_MBM_LOCAL_EVENT_ID;
-	else if (is_mbm_total_enabled())
+	else if (resctrl_arch_is_mbm_total_enabled())
 		mba_mbps_default_event = QOS_L3_MBM_TOTAL_EVENT_ID;
 
 	return !rdt_get_mon_l3_config(r);
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 763317ea22565..1ecc93282b7d7 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -559,12 +559,12 @@ ssize_t rdtgroup_mba_mbps_event_write(struct kernfs_open_file *of,
 	rdt_last_cmd_clear();
 
 	if (!strcmp(buf, "mbm_local_bytes")) {
-		if (is_mbm_local_enabled())
+		if (resctrl_arch_is_mbm_local_enabled())
 			rdtgrp->mba_mbps_event = QOS_L3_MBM_LOCAL_EVENT_ID;
 		else
 			ret = -EINVAL;
 	} else if (!strcmp(buf, "mbm_total_bytes")) {
-		if (is_mbm_total_enabled())
+		if (resctrl_arch_is_mbm_total_enabled())
 			rdtgrp->mba_mbps_event = QOS_L3_MBM_TOTAL_EVENT_ID;
 		else
 			ret = -EINVAL;
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 8c276e7f015d7..ace5f4b6bc7f9 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -159,7 +159,6 @@ struct rmid_read {
 	void			*arch_mon_ctx;
 };
 
-extern unsigned int rdt_mon_features;
 extern struct list_head resctrl_schema_all;
 extern bool resctrl_mounted;
 
@@ -409,32 +408,6 @@ struct msr_param {
 	u32			high;
 };
 
-static inline bool is_llc_occupancy_enabled(void)
-{
-	return (rdt_mon_features & (1 << QOS_L3_OCCUP_EVENT_ID));
-}
-
-static inline bool is_mbm_total_enabled(void)
-{
-	return (rdt_mon_features & (1 << QOS_L3_MBM_TOTAL_EVENT_ID));
-}
-
-static inline bool is_mbm_local_enabled(void)
-{
-	return (rdt_mon_features & (1 << QOS_L3_MBM_LOCAL_EVENT_ID));
-}
-
-static inline bool is_mbm_enabled(void)
-{
-	return (is_mbm_total_enabled() || is_mbm_local_enabled());
-}
-
-static inline bool is_mbm_event(int e)
-{
-	return (e >= QOS_L3_MBM_TOTAL_EVENT_ID &&
-		e <= QOS_L3_MBM_LOCAL_EVENT_ID);
-}
-
 /**
  * struct rdt_hw_resource - arch private attributes of a resctrl resource
  * @r_resctrl:		Attributes of the resource used directly by resctrl.
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 5b03488dbf9a4..9b28578d3ba17 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -295,11 +295,11 @@ void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *
 {
 	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
 
-	if (is_mbm_total_enabled())
+	if (resctrl_arch_is_mbm_total_enabled())
 		memset(hw_dom->arch_mbm_total, 0,
 		       sizeof(*hw_dom->arch_mbm_total) * r->num_rmid);
 
-	if (is_mbm_local_enabled())
+	if (resctrl_arch_is_mbm_local_enabled())
 		memset(hw_dom->arch_mbm_local, 0,
 		       sizeof(*hw_dom->arch_mbm_local) * r->num_rmid);
 }
@@ -569,7 +569,7 @@ void free_rmid(u32 closid, u32 rmid)
 
 	entry = __rmid_entry(idx);
 
-	if (is_llc_occupancy_enabled())
+	if (resctrl_arch_is_llc_occupancy_enabled())
 		add_rmid_to_limbo(entry);
 	else
 		list_add_tail(&entry->list, &rmid_free_lru);
@@ -852,10 +852,10 @@ static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d,
 	 * This is protected from concurrent reads from user as both
 	 * the user and overflow handler hold the global mutex.
 	 */
-	if (is_mbm_total_enabled())
+	if (resctrl_arch_is_mbm_total_enabled())
 		mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_TOTAL_EVENT_ID);
 
-	if (is_mbm_local_enabled())
+	if (resctrl_arch_is_mbm_local_enabled())
 		mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_LOCAL_EVENT_ID);
 }
 
@@ -1085,11 +1085,11 @@ static void l3_mon_evt_init(struct rdt_resource *r)
 {
 	INIT_LIST_HEAD(&r->evt_list);
 
-	if (is_llc_occupancy_enabled())
+	if (resctrl_arch_is_llc_occupancy_enabled())
 		list_add_tail(&llc_occupancy_event.list, &r->evt_list);
-	if (is_mbm_total_enabled())
+	if (resctrl_arch_is_mbm_total_enabled())
 		list_add_tail(&mbm_total_event.list, &r->evt_list);
-	if (is_mbm_local_enabled())
+	if (resctrl_arch_is_mbm_local_enabled())
 		list_add_tail(&mbm_local_event.list, &r->evt_list);
 }
 
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index badac3f5da72f..eb32fbc3abea7 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -117,6 +117,18 @@ void rdt_staged_configs_clear(void)
 	}
 }
 
+static bool resctrl_is_mbm_enabled(void)
+{
+	return (resctrl_arch_is_mbm_total_enabled() ||
+		resctrl_arch_is_mbm_local_enabled());
+}
+
+static bool resctrl_is_mbm_event(int e)
+{
+	return (e >= QOS_L3_MBM_TOTAL_EVENT_ID &&
+		e <= QOS_L3_MBM_LOCAL_EVENT_ID);
+}
+
 /*
  * Trivial allocator for CLOSIDs. Since h/w only supports a small number,
  * we can keep a bitmap of free CLOSIDs in a single integer.
@@ -164,7 +176,7 @@ static int closid_alloc(void)
 	lockdep_assert_held(&rdtgroup_mutex);
 
 	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID) &&
-	    is_llc_occupancy_enabled()) {
+	    resctrl_arch_is_llc_occupancy_enabled()) {
 		cleanest_closid = resctrl_find_cleanest_closid();
 		if (cleanest_closid < 0)
 			return cleanest_closid;
@@ -2378,7 +2390,7 @@ static bool supports_mba_mbps(void)
 	struct rdt_resource *rmbm = resctrl_arch_get_resource(RDT_RESOURCE_L3);
 	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_MBA);
 
-	return (is_mbm_enabled() &&
+	return (resctrl_is_mbm_enabled() &&
 		r->alloc_capable && is_mba_linear() &&
 		r->ctrl_scope == rmbm->mon_scope);
 }
@@ -2756,7 +2768,7 @@ static int rdt_get_tree(struct fs_context *fc)
 	if (resctrl_arch_alloc_capable() || resctrl_arch_mon_capable())
 		resctrl_mounted = true;
 
-	if (is_mbm_enabled()) {
+	if (resctrl_is_mbm_enabled()) {
 		r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
 		list_for_each_entry(dom, &r->mon_domains, hdr.list)
 			mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL,
@@ -3125,7 +3137,7 @@ static int mon_add_all_files(struct kernfs_node *kn, struct rdt_mon_domain *d,
 		if (ret)
 			return ret;
 
-		if (!do_sum && is_mbm_event(mevt->evtid))
+		if (!do_sum && resctrl_is_mbm_event(mevt->evtid))
 			mon_event_read(&rr, r, d, prgrp, &d->hdr.cpu_mask, mevt->evtid, true);
 	}
 
@@ -4082,9 +4094,9 @@ void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d
 	if (resctrl_mounted && resctrl_arch_mon_capable())
 		rmdir_mondata_subdir_allrdtgrp(r, d);
 
-	if (is_mbm_enabled())
+	if (resctrl_is_mbm_enabled())
 		cancel_delayed_work(&d->mbm_over);
-	if (is_llc_occupancy_enabled() && has_busy_rmid(d)) {
+	if (resctrl_arch_is_llc_occupancy_enabled() && has_busy_rmid(d)) {
 		/*
 		 * When a package is going down, forcefully
 		 * decrement rmid->ebusy. There is no way to know
@@ -4120,12 +4132,12 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_mon_domain
 	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
 	size_t tsize;
 
-	if (is_llc_occupancy_enabled()) {
+	if (resctrl_arch_is_llc_occupancy_enabled()) {
 		d->rmid_busy_llc = bitmap_zalloc(idx_limit, GFP_KERNEL);
 		if (!d->rmid_busy_llc)
 			return -ENOMEM;
 	}
-	if (is_mbm_total_enabled()) {
+	if (resctrl_arch_is_mbm_total_enabled()) {
 		tsize = sizeof(*d->mbm_total);
 		d->mbm_total = kcalloc(idx_limit, tsize, GFP_KERNEL);
 		if (!d->mbm_total) {
@@ -4133,7 +4145,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_mon_domain
 			return -ENOMEM;
 		}
 	}
-	if (is_mbm_local_enabled()) {
+	if (resctrl_arch_is_mbm_local_enabled()) {
 		tsize = sizeof(*d->mbm_local);
 		d->mbm_local = kcalloc(idx_limit, tsize, GFP_KERNEL);
 		if (!d->mbm_local) {
@@ -4172,13 +4184,13 @@ int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d)
 	if (err)
 		goto out_unlock;
 
-	if (is_mbm_enabled()) {
+	if (resctrl_is_mbm_enabled()) {
 		INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow);
 		mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL,
 					   RESCTRL_PICK_ANY_CPU);
 	}
 
-	if (is_llc_occupancy_enabled())
+	if (resctrl_arch_is_llc_occupancy_enabled())
 		INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo);
 
 	/*
@@ -4233,12 +4245,12 @@ void resctrl_offline_cpu(unsigned int cpu)
 
 	d = get_mon_domain_from_cpu(cpu, l3);
 	if (d) {
-		if (is_mbm_enabled() && cpu == d->mbm_work_cpu) {
+		if (resctrl_is_mbm_enabled() && cpu == d->mbm_work_cpu) {
 			cancel_delayed_work(&d->mbm_over);
 			mbm_setup_overflow_handler(d, 0, cpu);
 		}
-		if (is_llc_occupancy_enabled() && cpu == d->cqm_work_cpu &&
-		    has_busy_rmid(d)) {
+		if (resctrl_arch_is_llc_occupancy_enabled() &&
+		    cpu == d->cqm_work_cpu && has_busy_rmid(d)) {
 			cancel_delayed_work(&d->cqm_limbo);
 			cqm_setup_limbo_handler(d, 0, cpu);
 		}

From 9ddeacd6825e5a0ed8f4968b698fc53c50b1311e Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:37:04 +0000
Subject: [PATCH 033/236] x86/resctrl: Add resctrl_arch_is_evt_configurable()
 to abstract BMEC

commit d81826f87a80a86cc5963ff3c44f05700ded3fc9 upstream.

When BMEC is supported the resctrl event can be configured in a number of
ways. This depends on architecture support. rdt_get_mon_l3_config() modifies
the struct mon_evt and calls resctrl_file_fflags_init() to create the files
that allow the configuration.

Splitting this into separate architecture and filesystem parts would require
the struct mon_evt and resctrl_file_fflags_init() to be exposed.

Instead, add resctrl_arch_is_evt_configurable(), and use this from
resctrl_mon_resource_init() to initialise struct mon_evt and call
resctrl_file_fflags_init().

resctrl_arch_is_evt_configurable() calls rdt_cpu_has() so it doesn't obviously
benefit from being inlined. Putting it in core.c will allow rdt_cpu_has() to
eventually become static.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-20-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c    | 15 +++++++++++++++
 arch/x86/kernel/cpu/resctrl/monitor.c | 22 +++++++++++-----------
 include/linux/resctrl.h               |  2 ++
 3 files changed, 28 insertions(+), 11 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 78f94ab9bb76d..95da04e6cd6c6 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -830,6 +830,21 @@ bool __init rdt_cpu_has(int flag)
 	return ret;
 }
 
+__init bool resctrl_arch_is_evt_configurable(enum resctrl_event_id evt)
+{
+	if (!rdt_cpu_has(X86_FEATURE_BMEC))
+		return false;
+
+	switch (evt) {
+	case QOS_L3_MBM_TOTAL_EVENT_ID:
+		return rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL);
+	case QOS_L3_MBM_LOCAL_EVENT_ID:
+		return rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL);
+	default:
+		return false;
+	}
+}
+
 static __init bool get_mem_config(void)
 {
 	struct rdt_hw_resource *hw_res = &rdt_resources_all[RDT_RESOURCE_MBA];
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 9b28578d3ba17..a1da0c3f22f38 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -1202,6 +1202,17 @@ int __init resctrl_mon_resource_init(void)
 
 	l3_mon_evt_init(r);
 
+	if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_TOTAL_EVENT_ID)) {
+		mbm_total_event.configurable = true;
+		resctrl_file_fflags_init("mbm_total_bytes_config",
+					 RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
+	}
+	if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_LOCAL_EVENT_ID)) {
+		mbm_local_event.configurable = true;
+		resctrl_file_fflags_init("mbm_local_bytes_config",
+					 RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
+	}
+
 	return 0;
 }
 
@@ -1245,17 +1256,6 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 		/* Detect list of bandwidth sources that can be tracked */
 		cpuid_count(0x80000020, 3, &eax, &ebx, &ecx, &edx);
 		hw_res->mbm_cfg_mask = ecx & MAX_EVT_CONFIG_BITS;
-
-		if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) {
-			mbm_total_event.configurable = true;
-			resctrl_file_fflags_init("mbm_total_bytes_config",
-						 RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
-		}
-		if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) {
-			mbm_local_event.configurable = true;
-			resctrl_file_fflags_init("mbm_local_bytes_config",
-						 RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
-		}
 	}
 
 	r->mon_capable = true;
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index a392480dc4b63..cc76f308e6f38 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -309,6 +309,8 @@ u32 resctrl_arch_get_num_closid(struct rdt_resource *r);
 u32 resctrl_arch_system_num_rmid_idx(void);
 int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid);
 
+__init bool resctrl_arch_is_evt_configurable(enum resctrl_event_id evt);
+
 /*
  * Update the ctrl_val and apply this config right now.
  * Must be called on one of the domain's CPUs.

From ec966560caa2318db6851bd788bfcc542b822eb6 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:37:05 +0000
Subject: [PATCH 034/236] x86/resctrl: Change mon_event_config_{read,write}()
 to be arch helpers

commit 650680d651aaf409f097ad904c3fea6c4b3a0884 upstream.

mon_event_config_{read,write}() are called via IPI and access model specific
registers to do their work.

To support another architecture, this needs abstracting.

Rename mon_event_config_{read,write}() to have a "resctrl_arch_" prefix, and
move their struct mon_config_info parameter into <linux/resctrl.h>.  This
allows another architecture to supply an implementation of these.

As struct mon_config_info is now exposed globally, give it a 'resctrl_'
prefix. MPAM systems need access to the domain to do this work, add the
resource and domain to struct resctrl_mon_config_info.

Co-developed-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-21-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 46 +++++++++++++-------------
 include/linux/resctrl.h                | 31 +++++++++++++++++
 2 files changed, 54 insertions(+), 23 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index eb32fbc3abea7..e7d1d8b6983da 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -1580,11 +1580,6 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
 	return ret;
 }
 
-struct mon_config_info {
-	u32 evtid;
-	u32 mon_config;
-};
-
 #define INVALID_CONFIG_INDEX   UINT_MAX
 
 /**
@@ -1609,31 +1604,32 @@ static inline unsigned int mon_event_config_index_get(u32 evtid)
 	}
 }
 
-static void mon_event_config_read(void *info)
+void resctrl_arch_mon_event_config_read(void *_config_info)
 {
-	struct mon_config_info *mon_info = info;
+	struct resctrl_mon_config_info *config_info = _config_info;
 	unsigned int index;
 	u64 msrval;
 
-	index = mon_event_config_index_get(mon_info->evtid);
+	index = mon_event_config_index_get(config_info->evtid);
 	if (index == INVALID_CONFIG_INDEX) {
-		pr_warn_once("Invalid event id %d\n", mon_info->evtid);
+		pr_warn_once("Invalid event id %d\n", config_info->evtid);
 		return;
 	}
 	rdmsrl(MSR_IA32_EVT_CFG_BASE + index, msrval);
 
 	/* Report only the valid event configuration bits */
-	mon_info->mon_config = msrval & MAX_EVT_CONFIG_BITS;
+	config_info->mon_config = msrval & MAX_EVT_CONFIG_BITS;
 }
 
-static void mondata_config_read(struct rdt_mon_domain *d, struct mon_config_info *mon_info)
+static void mondata_config_read(struct resctrl_mon_config_info *mon_info)
 {
-	smp_call_function_any(&d->hdr.cpu_mask, mon_event_config_read, mon_info, 1);
+	smp_call_function_any(&mon_info->d->hdr.cpu_mask,
+			      resctrl_arch_mon_event_config_read, mon_info, 1);
 }
 
 static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid)
 {
-	struct mon_config_info mon_info;
+	struct resctrl_mon_config_info mon_info;
 	struct rdt_mon_domain *dom;
 	bool sep = false;
 
@@ -1644,9 +1640,11 @@ static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid
 		if (sep)
 			seq_puts(s, ";");
 
-		memset(&mon_info, 0, sizeof(struct mon_config_info));
+		memset(&mon_info, 0, sizeof(struct resctrl_mon_config_info));
+		mon_info.r = r;
+		mon_info.d = dom;
 		mon_info.evtid = evtid;
-		mondata_config_read(dom, &mon_info);
+		mondata_config_read(&mon_info);
 
 		seq_printf(s, "%d=0x%02x", dom->hdr.id, mon_info.mon_config);
 		sep = true;
@@ -1679,30 +1677,32 @@ static int mbm_local_bytes_config_show(struct kernfs_open_file *of,
 	return 0;
 }
 
-static void mon_event_config_write(void *info)
+void resctrl_arch_mon_event_config_write(void *_config_info)
 {
-	struct mon_config_info *mon_info = info;
+	struct resctrl_mon_config_info *config_info = _config_info;
 	unsigned int index;
 
-	index = mon_event_config_index_get(mon_info->evtid);
+	index = mon_event_config_index_get(config_info->evtid);
 	if (index == INVALID_CONFIG_INDEX) {
-		pr_warn_once("Invalid event id %d\n", mon_info->evtid);
+		pr_warn_once("Invalid event id %d\n", config_info->evtid);
 		return;
 	}
-	wrmsr(MSR_IA32_EVT_CFG_BASE + index, mon_info->mon_config, 0);
+	wrmsr(MSR_IA32_EVT_CFG_BASE + index, config_info->mon_config, 0);
 }
 
 static void mbm_config_write_domain(struct rdt_resource *r,
 				    struct rdt_mon_domain *d, u32 evtid, u32 val)
 {
-	struct mon_config_info mon_info = {0};
+	struct resctrl_mon_config_info mon_info = {0};
 
 	/*
 	 * Read the current config value first. If both are the same then
 	 * no need to write it again.
 	 */
+	mon_info.r = r;
+	mon_info.d = d;
 	mon_info.evtid = evtid;
-	mondata_config_read(d, &mon_info);
+	mondata_config_read(&mon_info);
 	if (mon_info.mon_config == val)
 		return;
 
@@ -1714,7 +1714,7 @@ static void mbm_config_write_domain(struct rdt_resource *r,
 	 * are scoped at the domain level. Writing any of these MSRs
 	 * on one CPU is observed by all the CPUs in the domain.
 	 */
-	smp_call_function_any(&d->hdr.cpu_mask, mon_event_config_write,
+	smp_call_function_any(&d->hdr.cpu_mask, resctrl_arch_mon_event_config_write,
 			      &mon_info, 1);
 
 	/*
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index cc76f308e6f38..90b6563cf5326 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -270,6 +270,13 @@ struct resctrl_cpu_defaults {
 	u32 rmid;
 };
 
+struct resctrl_mon_config_info {
+	struct rdt_resource	*r;
+	struct rdt_mon_domain	*d;
+	u32			evtid;
+	u32			mon_config;
+};
+
 /**
  * resctrl_arch_sync_cpu_closid_rmid() - Refresh this CPU's CLOSID and RMID.
  *					 Call via IPI.
@@ -311,6 +318,30 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid);
 
 __init bool resctrl_arch_is_evt_configurable(enum resctrl_event_id evt);
 
+/**
+ * resctrl_arch_mon_event_config_write() - Write the config for an event.
+ * @config_info: struct resctrl_mon_config_info describing the resource, domain
+ *		 and event.
+ *
+ * Reads resource, domain and eventid from @config_info and writes the
+ * event config_info->mon_config into hardware.
+ *
+ * Called via IPI to reach a CPU that is a member of the specified domain.
+ */
+void resctrl_arch_mon_event_config_write(void *config_info);
+
+/**
+ * resctrl_arch_mon_event_config_read() - Read the config for an event.
+ * @config_info: struct resctrl_mon_config_info describing the resource, domain
+ *		 and event.
+ *
+ * Reads resource, domain and eventid from @config_info and reads the
+ * hardware config value into config_info->mon_config.
+ *
+ * Called via IPI to reach a CPU that is a member of the specified domain.
+ */
+void resctrl_arch_mon_event_config_read(void *config_info);
+
 /*
  * Update the ctrl_val and apply this config right now.
  * Must be called on one of the domain's CPUs.

From 328d689611a31a3686eb5a7fcbfcda6dbe535a50 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:37:06 +0000
Subject: [PATCH 035/236] x86/resctrl: Move mba_mbps_default_event init to
 filesystem code

commit 37bae1756734b065f5e5cddc54ad121ff0c8db51 upstream.

mba_mbps_default_event is initialised based on whether mbm_local or mbm_total
is supported. In the case of both, it is initialised to mbm_local.
mba_mbps_default_event is initialised in core.c's get_rdt_mon_resources(),
while all the readers are in rdtgroup.c.

After this code is split into architecture-specific and filesystem code,
get_rdt_mon_resources() remains part of the architecture code, which would
mean mba_mbps_default_event has to be exposed by the filesystem code.

Move the initialisation to the filesystem's resctrl_mon_resource_init().

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-22-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c    | 5 -----
 arch/x86/kernel/cpu/resctrl/monitor.c | 5 +++++
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 95da04e6cd6c6..e64ce80427b23 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -924,11 +924,6 @@ static __init bool get_rdt_mon_resources(void)
 	if (!rdt_mon_features)
 		return false;
 
-	if (resctrl_arch_is_mbm_local_enabled())
-		mba_mbps_default_event = QOS_L3_MBM_LOCAL_EVENT_ID;
-	else if (resctrl_arch_is_mbm_total_enabled())
-		mba_mbps_default_event = QOS_L3_MBM_TOTAL_EVENT_ID;
-
 	return !rdt_get_mon_l3_config(r);
 }
 
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index a1da0c3f22f38..953cf49e075ff 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -1213,6 +1213,11 @@ int __init resctrl_mon_resource_init(void)
 					 RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
 	}
 
+	if (resctrl_arch_is_mbm_local_enabled())
+		mba_mbps_default_event = QOS_L3_MBM_LOCAL_EVENT_ID;
+	else if (resctrl_arch_is_mbm_total_enabled())
+		mba_mbps_default_event = QOS_L3_MBM_TOTAL_EVENT_ID;
+
 	return 0;
 }
 

From fc3e83bde460fb3446ededa20370bb20608ca427 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:37:07 +0000
Subject: [PATCH 036/236] x86/resctrl: Move mbm_cfg_mask to struct rdt_resource

commit c32a7d7777800b61a5c9272cc94fe21aa919b305 upstream.

The mbm_cfg_mask field lists the bits that user-space can set when configuring
an event. This value is output via the last_cmd_status file.

Once the filesystem parts of resctrl are moved to live in /fs/, the struct
rdt_hw_resource is inaccessible to the filesystem code. Because this value is
output to user-space, it has to be accessible to the filesystem code.

Move it to struct rdt_resource.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-23-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/internal.h | 3 ---
 arch/x86/kernel/cpu/resctrl/monitor.c  | 2 +-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 5 ++---
 include/linux/resctrl.h                | 3 +++
 4 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index ace5f4b6bc7f9..4b348ed6b659f 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -420,8 +420,6 @@ struct msr_param {
  * @msr_update:		Function pointer to update QOS MSRs
  * @mon_scale:		cqm counter * mon_scale = occupancy in bytes
  * @mbm_width:		Monitor width, to detect and correct for overflow.
- * @mbm_cfg_mask:	Bandwidth sources that can be tracked when Bandwidth
- *			Monitoring Event Configuration (BMEC) is supported.
  * @cdp_enabled:	CDP state of this resource
  *
  * Members of this structure are either private to the architecture
@@ -435,7 +433,6 @@ struct rdt_hw_resource {
 	void			(*msr_update)(struct msr_param *m);
 	unsigned int		mon_scale;
 	unsigned int		mbm_width;
-	unsigned int		mbm_cfg_mask;
 	bool			cdp_enabled;
 };
 
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 953cf49e075ff..8685278521b7c 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -1260,7 +1260,7 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 
 		/* Detect list of bandwidth sources that can be tracked */
 		cpuid_count(0x80000020, 3, &eax, &ebx, &ecx, &edx);
-		hw_res->mbm_cfg_mask = ecx & MAX_EVT_CONFIG_BITS;
+		r->mbm_cfg_mask = ecx & MAX_EVT_CONFIG_BITS;
 	}
 
 	r->mon_capable = true;
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index e7d1d8b6983da..a388ef66ef4ca 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -1731,7 +1731,6 @@ static void mbm_config_write_domain(struct rdt_resource *r,
 
 static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid)
 {
-	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 	char *dom_str = NULL, *id_str;
 	unsigned long dom_id, val;
 	struct rdt_mon_domain *d;
@@ -1758,9 +1757,9 @@ static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid)
 	}
 
 	/* Value from user cannot be more than the supported set of events */
-	if ((val & hw_res->mbm_cfg_mask) != val) {
+	if ((val & r->mbm_cfg_mask) != val) {
 		rdt_last_cmd_printf("Invalid event configuration: max valid mask is 0x%02x\n",
-				    hw_res->mbm_cfg_mask);
+				    r->mbm_cfg_mask);
 		return -EINVAL;
 	}
 
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 90b6563cf5326..914df24ffe483 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -217,6 +217,8 @@ enum resctrl_schema_fmt {
  * @name:		Name to use in "schemata" file.
  * @schema_fmt:		Which format string and parser is used for this schema.
  * @evt_list:		List of monitoring events
+ * @mbm_cfg_mask:	Bandwidth sources that can be tracked when bandwidth
+ *			monitoring events can be configured.
  * @cdp_capable:	Is the CDP feature available on this resource
  */
 struct rdt_resource {
@@ -233,6 +235,7 @@ struct rdt_resource {
 	char			*name;
 	enum resctrl_schema_fmt	schema_fmt;
 	struct list_head	evt_list;
+	unsigned int		mbm_cfg_mask;
 	bool			cdp_capable;
 };
 

From f49c3eba2495ec39c95f705f66c4e2e530b0dae7 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:37:08 +0000
Subject: [PATCH 037/236] x86/resctrl: Add resctrl_arch_ prefix to pseudo lock
 functions

commit 7d0ec14c64a107a548616deace93a1913e5d68ed upstream.

resctrl's pseudo lock has some copy-to-cache and measurement functions that
are micro-architecture specific.

For example, pseudo_lock_fn() is not at all portable.

Label these 'resctrl_arch_' so they stay under /arch/x86.  To expose these
functions to the filesystem code they need an entry in a header file, and
can't be marked static.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-24-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/include/asm/resctrl.h            |  5 ++++
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 36 ++++++++++++-----------
 2 files changed, 24 insertions(+), 17 deletions(-)

diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h
index 6d4c7ea2c9e34..86407dbde583e 100644
--- a/arch/x86/include/asm/resctrl.h
+++ b/arch/x86/include/asm/resctrl.h
@@ -203,6 +203,11 @@ static inline void *resctrl_arch_mon_ctx_alloc(struct rdt_resource *r, int evtid
 static inline void resctrl_arch_mon_ctx_free(struct rdt_resource *r, int evtid,
 					     void *ctx) { };
 
+u64 resctrl_arch_get_prefetch_disable_bits(void);
+int resctrl_arch_pseudo_lock_fn(void *_rdtgrp);
+int resctrl_arch_measure_cycles_lat_fn(void *_plr);
+int resctrl_arch_measure_l2_residency(void *_plr);
+int resctrl_arch_measure_l3_residency(void *_plr);
 void resctrl_cpu_detect(struct cpuinfo_x86 *c);
 
 #else
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index a11608c5f38b4..82a1bce41d806 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -61,7 +61,8 @@ static const struct class pseudo_lock_class = {
 };
 
 /**
- * get_prefetch_disable_bits - prefetch disable bits of supported platforms
+ * resctrl_arch_get_prefetch_disable_bits - prefetch disable bits of supported
+ *                                          platforms
  * @void: It takes no parameters.
  *
  * Capture the list of platforms that have been validated to support
@@ -75,13 +76,13 @@ static const struct class pseudo_lock_class = {
  * in the SDM.
  *
  * When adding a platform here also add support for its cache events to
- * measure_cycles_perf_fn()
+ * resctrl_arch_measure_l*_residency()
  *
  * Return:
  * If platform is supported, the bits to disable hardware prefetchers, 0
  * if platform is not supported.
  */
-static u64 get_prefetch_disable_bits(void)
+u64 resctrl_arch_get_prefetch_disable_bits(void)
 {
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
 	    boot_cpu_data.x86 != 6)
@@ -408,7 +409,7 @@ static void pseudo_lock_free(struct rdtgroup *rdtgrp)
 }
 
 /**
- * pseudo_lock_fn - Load kernel memory into cache
+ * resctrl_arch_pseudo_lock_fn - Load kernel memory into cache
  * @_rdtgrp: resource group to which pseudo-lock region belongs
  *
  * This is the core pseudo-locking flow.
@@ -426,7 +427,7 @@ static void pseudo_lock_free(struct rdtgroup *rdtgrp)
  *
  * Return: 0. Waiter on waitqueue will be woken on completion.
  */
-static int pseudo_lock_fn(void *_rdtgrp)
+int resctrl_arch_pseudo_lock_fn(void *_rdtgrp)
 {
 	struct rdtgroup *rdtgrp = _rdtgrp;
 	struct pseudo_lock_region *plr = rdtgrp->plr;
@@ -712,7 +713,7 @@ int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp)
 	 * Not knowing the bits to disable prefetching implies that this
 	 * platform does not support Cache Pseudo-Locking.
 	 */
-	prefetch_disable_bits = get_prefetch_disable_bits();
+	prefetch_disable_bits = resctrl_arch_get_prefetch_disable_bits();
 	if (prefetch_disable_bits == 0) {
 		rdt_last_cmd_puts("Pseudo-locking not supported\n");
 		return -EINVAL;
@@ -872,7 +873,8 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d)
 }
 
 /**
- * measure_cycles_lat_fn - Measure cycle latency to read pseudo-locked memory
+ * resctrl_arch_measure_cycles_lat_fn - Measure cycle latency to read
+ *                                      pseudo-locked memory
  * @_plr: pseudo-lock region to measure
  *
  * There is no deterministic way to test if a memory region is cached. One
@@ -885,7 +887,7 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d)
  *
  * Return: 0. Waiter on waitqueue will be woken on completion.
  */
-static int measure_cycles_lat_fn(void *_plr)
+int resctrl_arch_measure_cycles_lat_fn(void *_plr)
 {
 	struct pseudo_lock_region *plr = _plr;
 	u32 saved_low, saved_high;
@@ -1069,7 +1071,7 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr,
 	return 0;
 }
 
-static int measure_l2_residency(void *_plr)
+int resctrl_arch_measure_l2_residency(void *_plr)
 {
 	struct pseudo_lock_region *plr = _plr;
 	struct residency_counts counts = {0};
@@ -1107,7 +1109,7 @@ static int measure_l2_residency(void *_plr)
 	return 0;
 }
 
-static int measure_l3_residency(void *_plr)
+int resctrl_arch_measure_l3_residency(void *_plr)
 {
 	struct pseudo_lock_region *plr = _plr;
 	struct residency_counts counts = {0};
@@ -1205,14 +1207,14 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
 	plr->cpu = cpu;
 
 	if (sel == 1)
-		thread = kthread_run_on_cpu(measure_cycles_lat_fn, plr,
-					    cpu, "pseudo_lock_measure/%u");
+		thread = kthread_run_on_cpu(resctrl_arch_measure_cycles_lat_fn,
+					    plr, cpu, "pseudo_lock_measure/%u");
 	else if (sel == 2)
-		thread = kthread_run_on_cpu(measure_l2_residency, plr,
-					    cpu, "pseudo_lock_measure/%u");
+		thread = kthread_run_on_cpu(resctrl_arch_measure_l2_residency,
+					    plr, cpu, "pseudo_lock_measure/%u");
 	else if (sel == 3)
-		thread = kthread_run_on_cpu(measure_l3_residency, plr,
-					    cpu, "pseudo_lock_measure/%u");
+		thread = kthread_run_on_cpu(resctrl_arch_measure_l3_residency,
+					    plr, cpu, "pseudo_lock_measure/%u");
 	else
 		goto out;
 
@@ -1307,7 +1309,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 
 	plr->thread_done = 0;
 
-	thread = kthread_run_on_cpu(pseudo_lock_fn, rdtgrp,
+	thread = kthread_run_on_cpu(resctrl_arch_pseudo_lock_fn, rdtgrp,
 				    plr->cpu, "pseudo_lock/%u");
 	if (IS_ERR(thread)) {
 		ret = PTR_ERR(thread);

From 40aaccd05180bb66136049a28c9f96f9c6161c1d Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:37:09 +0000
Subject: [PATCH 038/236] x86/resctrl: Allow an architecture to disable pseudo
 lock

commit 7028840552a220ac5efe51a4b554195cd954a912 upstream.

Pseudo-lock relies on knowledge of the micro-architecture to disable
prefetchers etc.

On arm64 these controls are typically secure only, meaning Linux can't access
them. Arm's cache-lockdown feature works in a very different way. Resctrl's
pseudo-lock isn't going to be used on arm64 platforms.

Add a Kconfig symbol that can be selected by the architecture. This enables or
disables building of the pseudo_lock.c file, and replaces the functions with
stubs. An additional IS_ENABLED() check is needed in rdtgroup_mode_write() so
that attempting to enable pseudo-lock reports an "Unknown or unsupported mode"
to user-space via the last_cmd_status file.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-25-james.morse@arm.com

 Conflicts:
	arch/x86/Kconfig
[jz: resolve simple context conflict]
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/Kconfig                       |  7 ++++
 arch/x86/kernel/cpu/resctrl/Makefile   |  5 +--
 arch/x86/kernel/cpu/resctrl/internal.h | 49 +++++++++++++++++++++-----
 arch/x86/kernel/cpu/resctrl/rdtgroup.c |  3 +-
 4 files changed, 53 insertions(+), 11 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index b93fa32b52c9e..e12b82baaef8b 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -484,6 +484,7 @@ config X86_CPU_RESCTRL
 	depends on X86 && (CPU_SUP_INTEL || CPU_SUP_AMD)
 	select KERNFS
 	select PROC_CPU_RESCTRL		if PROC_FS
+	select RESCTRL_FS_PSEUDO_LOCK
 	help
 	  Enable x86 CPU resource control support.
 
@@ -500,6 +501,12 @@ config X86_CPU_RESCTRL
 
 	  Say N if unsure.
 
+config RESCTRL_FS_PSEUDO_LOCK
+	bool
+	help
+	  Software mechanism to pin data in a cache portion using
+	  micro-architecture specific knowledge.
+
 if X86_32
 config X86_BIGSMP
 	bool "Support for big SMP systems with more than 8 CPUs"
diff --git a/arch/x86/kernel/cpu/resctrl/Makefile b/arch/x86/kernel/cpu/resctrl/Makefile
index 4a06c37b9cf11..0c13b0befd8a9 100644
--- a/arch/x86/kernel/cpu/resctrl/Makefile
+++ b/arch/x86/kernel/cpu/resctrl/Makefile
@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_X86_CPU_RESCTRL)	+= core.o rdtgroup.o monitor.o
-obj-$(CONFIG_X86_CPU_RESCTRL)	+= ctrlmondata.o pseudo_lock.o
+obj-$(CONFIG_X86_CPU_RESCTRL)		+= core.o rdtgroup.o monitor.o
+obj-$(CONFIG_X86_CPU_RESCTRL)		+= ctrlmondata.o
+obj-$(CONFIG_RESCTRL_FS_PSEUDO_LOCK)	+= pseudo_lock.o
 CFLAGS_pseudo_lock.o = -I$(src)
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 4b348ed6b659f..a011f3d62e241 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -515,14 +515,6 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_ctrl_domain
 				  unsigned long cbm);
 enum rdtgrp_mode rdtgroup_mode_by_closid(int closid);
 int rdtgroup_tasks_assigned(struct rdtgroup *r);
-int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp);
-int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp);
-bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm);
-bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d);
-int rdt_pseudo_lock_init(void);
-void rdt_pseudo_lock_release(void);
-int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp);
-void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp);
 struct rdt_ctrl_domain *get_ctrl_domain_from_cpu(int cpu, struct rdt_resource *r);
 struct rdt_mon_domain *get_mon_domain_from_cpu(int cpu, struct rdt_resource *r);
 int closids_supported(void);
@@ -554,4 +546,45 @@ void resctrl_file_fflags_init(const char *config, unsigned long fflags);
 void rdt_staged_configs_clear(void);
 bool closid_allocated(unsigned int closid);
 int resctrl_find_cleanest_closid(void);
+
+#ifdef CONFIG_RESCTRL_FS_PSEUDO_LOCK
+int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp);
+int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp);
+bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm);
+bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d);
+int rdt_pseudo_lock_init(void);
+void rdt_pseudo_lock_release(void);
+int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp);
+void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp);
+#else
+static inline int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm)
+{
+	return false;
+}
+
+static inline bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d)
+{
+	return false;
+}
+
+static inline int rdt_pseudo_lock_init(void) { return 0; }
+static inline void rdt_pseudo_lock_release(void) { }
+static inline int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp) { }
+#endif /* CONFIG_RESCTRL_FS_PSEUDO_LOCK */
+
 #endif /* _ASM_X86_RESCTRL_INTERNAL_H */
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index a388ef66ef4ca..e59271515a463 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -1453,7 +1453,8 @@ static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of,
 				goto out;
 		}
 		rdtgrp->mode = RDT_MODE_EXCLUSIVE;
-	} else if (!strcmp(buf, "pseudo-locksetup")) {
+	} else if (IS_ENABLED(CONFIG_RESCTRL_FS_PSEUDO_LOCK) &&
+		   !strcmp(buf, "pseudo-locksetup")) {
 		ret = rdtgroup_locksetup_enter(rdtgrp);
 		if (ret)
 			goto out;

From e84540875eb2143fca2d7b4f65311a9453e9eabb Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:37:10 +0000
Subject: [PATCH 039/236] x86/resctrl: Make prefetch_disable_bits belong to the
 arch code

commit 4d20f38ab6d922dd6b8a33795b6e72516d733eb2 upstream.

prefetch_disable_bits is set by rdtgroup_locksetup_enter() from a value
provided by the architecture, but is largely read by other architecture
helpers.

Make resctrl_arch_get_prefetch_disable_bits() set prefetch_disable_bits so
that it can be isolated to arch-code from where the other arch-code helpers
can use its cached value.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-26-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index 82a1bce41d806..7a6a697ebfa66 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -84,6 +84,8 @@ static const struct class pseudo_lock_class = {
  */
 u64 resctrl_arch_get_prefetch_disable_bits(void)
 {
+	prefetch_disable_bits = 0;
+
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
 	    boot_cpu_data.x86 != 6)
 		return 0;
@@ -99,7 +101,8 @@ u64 resctrl_arch_get_prefetch_disable_bits(void)
 		 * 3    DCU IP Prefetcher Disable (R/W)
 		 * 63:4 Reserved
 		 */
-		return 0xF;
+		prefetch_disable_bits = 0xF;
+		break;
 	case INTEL_ATOM_GOLDMONT:
 	case INTEL_ATOM_GOLDMONT_PLUS:
 		/*
@@ -110,10 +113,11 @@ u64 resctrl_arch_get_prefetch_disable_bits(void)
 		 * 2     DCU Hardware Prefetcher Disable (R/W)
 		 * 63:3  Reserved
 		 */
-		return 0x5;
+		prefetch_disable_bits = 0x5;
+		break;
 	}
 
-	return 0;
+	return prefetch_disable_bits;
 }
 
 /**
@@ -713,8 +717,7 @@ int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp)
 	 * Not knowing the bits to disable prefetching implies that this
 	 * platform does not support Cache Pseudo-Locking.
 	 */
-	prefetch_disable_bits = resctrl_arch_get_prefetch_disable_bits();
-	if (prefetch_disable_bits == 0) {
+	if (resctrl_arch_get_prefetch_disable_bits() == 0) {
 		rdt_last_cmd_puts("Pseudo-locking not supported\n");
 		return -EINVAL;
 	}

From 4df97c8e1a33fb57e2d031930b0736f755aaaaf1 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:37:11 +0000
Subject: [PATCH 040/236] x86/resctrl: Make resctrl_arch_pseudo_lock_fn() take
 a plr

commit 4cf9acfc8f1a322576f0666b882d631cfdf714bf upstream.

resctrl_arch_pseudo_lock_fn() has architecture specific behaviour,
and takes a struct rdtgroup as an argument.

After the filesystem code moves to /fs/, the definition of struct
rdtgroup will not be available to the architecture code.

The only reason resctrl_arch_pseudo_lock_fn() wants the rdtgroup is
for the CLOSID. Embed that in the pseudo_lock_region as a closid,
and move the definition of struct pseudo_lock_region to resctrl.h.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-27-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/include/asm/resctrl.h            |  2 +-
 arch/x86/kernel/cpu/resctrl/internal.h    | 37 ---------------------
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 12 +++----
 include/linux/resctrl.h                   | 39 +++++++++++++++++++++++
 4 files changed, 46 insertions(+), 44 deletions(-)

diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h
index 86407dbde583e..011bf67a18664 100644
--- a/arch/x86/include/asm/resctrl.h
+++ b/arch/x86/include/asm/resctrl.h
@@ -204,7 +204,7 @@ static inline void resctrl_arch_mon_ctx_free(struct rdt_resource *r, int evtid,
 					     void *ctx) { };
 
 u64 resctrl_arch_get_prefetch_disable_bits(void);
-int resctrl_arch_pseudo_lock_fn(void *_rdtgrp);
+int resctrl_arch_pseudo_lock_fn(void *_plr);
 int resctrl_arch_measure_cycles_lat_fn(void *_plr);
 int resctrl_arch_measure_l2_residency(void *_plr);
 int resctrl_arch_measure_l3_residency(void *_plr);
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index a011f3d62e241..09c3d8abf7c29 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -211,43 +211,6 @@ struct mongroup {
 	u32			rmid;
 };
 
-/**
- * struct pseudo_lock_region - pseudo-lock region information
- * @s:			Resctrl schema for the resource to which this
- *			pseudo-locked region belongs
- * @d:			RDT domain to which this pseudo-locked region
- *			belongs
- * @cbm:		bitmask of the pseudo-locked region
- * @lock_thread_wq:	waitqueue used to wait on the pseudo-locking thread
- *			completion
- * @thread_done:	variable used by waitqueue to test if pseudo-locking
- *			thread completed
- * @cpu:		core associated with the cache on which the setup code
- *			will be run
- * @line_size:		size of the cache lines
- * @size:		size of pseudo-locked region in bytes
- * @kmem:		the kernel memory associated with pseudo-locked region
- * @minor:		minor number of character device associated with this
- *			region
- * @debugfs_dir:	pointer to this region's directory in the debugfs
- *			filesystem
- * @pm_reqs:		Power management QoS requests related to this region
- */
-struct pseudo_lock_region {
-	struct resctrl_schema	*s;
-	struct rdt_ctrl_domain	*d;
-	u32			cbm;
-	wait_queue_head_t	lock_thread_wq;
-	int			thread_done;
-	int			cpu;
-	unsigned int		line_size;
-	unsigned int		size;
-	void			*kmem;
-	unsigned int		minor;
-	struct dentry		*debugfs_dir;
-	struct list_head	pm_reqs;
-};
-
 /**
  * struct rdtgroup - store rdtgroup's data in resctrl file system.
  * @kn:				kernfs node
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index 7a6a697ebfa66..4781c105d15b5 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -414,7 +414,7 @@ static void pseudo_lock_free(struct rdtgroup *rdtgrp)
 
 /**
  * resctrl_arch_pseudo_lock_fn - Load kernel memory into cache
- * @_rdtgrp: resource group to which pseudo-lock region belongs
+ * @_plr: the pseudo-lock region descriptor
  *
  * This is the core pseudo-locking flow.
  *
@@ -431,10 +431,9 @@ static void pseudo_lock_free(struct rdtgroup *rdtgrp)
  *
  * Return: 0. Waiter on waitqueue will be woken on completion.
  */
-int resctrl_arch_pseudo_lock_fn(void *_rdtgrp)
+int resctrl_arch_pseudo_lock_fn(void *_plr)
 {
-	struct rdtgroup *rdtgrp = _rdtgrp;
-	struct pseudo_lock_region *plr = rdtgrp->plr;
+	struct pseudo_lock_region *plr = _plr;
 	u32 rmid_p, closid_p;
 	unsigned long i;
 	u64 saved_msr;
@@ -494,7 +493,8 @@ int resctrl_arch_pseudo_lock_fn(void *_rdtgrp)
 	 * pseudo-locked followed by reading of kernel memory to load it
 	 * into the cache.
 	 */
-	__wrmsr(MSR_IA32_PQR_ASSOC, rmid_p, rdtgrp->closid);
+	__wrmsr(MSR_IA32_PQR_ASSOC, rmid_p, plr->closid);
+
 	/*
 	 * Cache was flushed earlier. Now access kernel memory to read it
 	 * into cache region associated with just activated plr->closid.
@@ -1312,7 +1312,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 
 	plr->thread_done = 0;
 
-	thread = kthread_run_on_cpu(resctrl_arch_pseudo_lock_fn, rdtgrp,
+	thread = kthread_run_on_cpu(resctrl_arch_pseudo_lock_fn, plr,
 				    plr->cpu, "pseudo_lock/%u");
 	if (IS_ERR(thread)) {
 		ret = PTR_ERR(thread);
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 914df24ffe483..226cc5c0d765f 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -58,6 +58,45 @@ enum resctrl_conf_type {
 
 #define CDP_NUM_TYPES	(CDP_DATA + 1)
 
+/*
+ * struct pseudo_lock_region - pseudo-lock region information
+ * @s:			Resctrl schema for the resource to which this
+ *			pseudo-locked region belongs
+ * @closid:		The closid that this pseudo-locked region uses
+ * @d:			RDT domain to which this pseudo-locked region
+ *			belongs
+ * @cbm:		bitmask of the pseudo-locked region
+ * @lock_thread_wq:	waitqueue used to wait on the pseudo-locking thread
+ *			completion
+ * @thread_done:	variable used by waitqueue to test if pseudo-locking
+ *			thread completed
+ * @cpu:		core associated with the cache on which the setup code
+ *			will be run
+ * @line_size:		size of the cache lines
+ * @size:		size of pseudo-locked region in bytes
+ * @kmem:		the kernel memory associated with pseudo-locked region
+ * @minor:		minor number of character device associated with this
+ *			region
+ * @debugfs_dir:	pointer to this region's directory in the debugfs
+ *			filesystem
+ * @pm_reqs:		Power management QoS requests related to this region
+ */
+struct pseudo_lock_region {
+	struct resctrl_schema	*s;
+	u32			closid;
+	struct rdt_ctrl_domain	*d;
+	u32			cbm;
+	wait_queue_head_t	lock_thread_wq;
+	int			thread_done;
+	int			cpu;
+	unsigned int		line_size;
+	unsigned int		size;
+	void			*kmem;
+	unsigned int		minor;
+	struct dentry		*debugfs_dir;
+	struct list_head	pm_reqs;
+};
+
 /**
  * struct resctrl_staged_config - parsed configuration to be applied
  * @new_ctrl:		new ctrl value to be loaded

From d51e7de78a3f53fc5b8d8354cbc59c730dc75f77 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:37:12 +0000
Subject: [PATCH 041/236] x86/resctrl: Move RFTYPE flags to be managed by
 resctrl

commit 373af4ecfdc922657be081b3feebbd0af8e7fa65 upstream.

resctrl_file_fflags_init() is called from the architecture specific code to
make the 'thread_throttle_mode' file visible. The architecture specific code
has already set the membw.throttle_mode in the rdt_resource.

This forces the RFTYPE flags used by resctrl to be exposed to the architecture
specific code.

This doesn't need to be specific to the architecture, the throttle_mode can be
used by resctrl to determine if the 'thread_throttle_mode' file should be
visible. This allows the RFTYPE flags to be private to resctrl.

Add thread_throttle_mode_init(), and use it to call resctrl_file_fflags_init()
from resctrl_init(). This avoids publishing an extra function between the
architecture and filesystem code.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-28-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c     |  3 ---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 12 ++++++++++++
 2 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index e64ce80427b23..1eb707a82ab4f 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -227,9 +227,6 @@ static __init bool __get_mem_config_intel(struct rdt_resource *r)
 	else
 		r->membw.throttle_mode = THREAD_THROTTLE_MAX;
 
-	resctrl_file_fflags_init("thread_throttle_mode",
-				 RFTYPE_CTRL_INFO | RFTYPE_RES_MB);
-
 	r->alloc_capable = true;
 
 	return true;
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index e59271515a463..58feba3feefd8 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -2064,6 +2064,16 @@ static struct rftype *rdtgroup_get_rftype_by_name(const char *name)
 	return NULL;
 }
 
+static void thread_throttle_mode_init(void)
+{
+	struct rdt_resource *r_mba;
+
+	r_mba = resctrl_arch_get_resource(RDT_RESOURCE_MBA);
+	if (r_mba->membw.throttle_mode != THREAD_THROTTLE_UNDEFINED)
+		resctrl_file_fflags_init("thread_throttle_mode",
+					 RFTYPE_CTRL_INFO | RFTYPE_RES_MB);
+}
+
 void resctrl_file_fflags_init(const char *config, unsigned long fflags)
 {
 	struct rftype *rft;
@@ -4277,6 +4287,8 @@ int __init resctrl_init(void)
 
 	rdtgroup_setup_default();
 
+	thread_throttle_mode_init();
+
 	ret = resctrl_mon_resource_init();
 	if (ret)
 		return ret;

From 87d0399387428cb17e04a0cfd29923cff0f0c011 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:37:13 +0000
Subject: [PATCH 042/236] x86/resctrl: Handle throttle_mode for SMBA resources

commit 6c2282d42cb37f081587412f77340138b1df265e upstream.

Now that the visibility of throttle_mode is being managed by resctrl, it
should consider resources other than MBA that may have a throttle_mode.  SMBA
is one such resource.

Extend thread_throttle_mode_init() to check SMBA for a throttle_mode.

Adding support for multiple resources means it is possible for a platform with
both MBA and SMBA, but an undefined throttle_mode on one of them to make the
file visible.

Add the 'undefined' case to rdt_thread_throttle_mode_show().

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-29-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 33 +++++++++++++++++++++-----
 1 file changed, 27 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 58feba3feefd8..5fc60c9ce28f8 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -1188,10 +1188,19 @@ static int rdt_thread_throttle_mode_show(struct kernfs_open_file *of,
 	struct resctrl_schema *s = of->kn->parent->priv;
 	struct rdt_resource *r = s->res;
 
-	if (r->membw.throttle_mode == THREAD_THROTTLE_PER_THREAD)
+	switch (r->membw.throttle_mode) {
+	case THREAD_THROTTLE_PER_THREAD:
 		seq_puts(seq, "per-thread\n");
-	else
+		return 0;
+	case THREAD_THROTTLE_MAX:
 		seq_puts(seq, "max\n");
+		return 0;
+	case THREAD_THROTTLE_UNDEFINED:
+		seq_puts(seq, "undefined\n");
+		return 0;
+	}
+
+	WARN_ON_ONCE(1);
 
 	return 0;
 }
@@ -2066,12 +2075,24 @@ static struct rftype *rdtgroup_get_rftype_by_name(const char *name)
 
 static void thread_throttle_mode_init(void)
 {
-	struct rdt_resource *r_mba;
+	enum membw_throttle_mode throttle_mode = THREAD_THROTTLE_UNDEFINED;
+	struct rdt_resource *r_mba, *r_smba;
 
 	r_mba = resctrl_arch_get_resource(RDT_RESOURCE_MBA);
-	if (r_mba->membw.throttle_mode != THREAD_THROTTLE_UNDEFINED)
-		resctrl_file_fflags_init("thread_throttle_mode",
-					 RFTYPE_CTRL_INFO | RFTYPE_RES_MB);
+	if (r_mba->alloc_capable &&
+	    r_mba->membw.throttle_mode != THREAD_THROTTLE_UNDEFINED)
+		throttle_mode = r_mba->membw.throttle_mode;
+
+	r_smba = resctrl_arch_get_resource(RDT_RESOURCE_SMBA);
+	if (r_smba->alloc_capable &&
+	    r_smba->membw.throttle_mode != THREAD_THROTTLE_UNDEFINED)
+		throttle_mode = r_smba->membw.throttle_mode;
+
+	if (throttle_mode == THREAD_THROTTLE_UNDEFINED)
+		return;
+
+	resctrl_file_fflags_init("thread_throttle_mode",
+				 RFTYPE_CTRL_INFO | RFTYPE_RES_MB);
 }
 
 void resctrl_file_fflags_init(const char *config, unsigned long fflags)

From a293089712e636b33f0da8982fc4d1af00ab4e87 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:37:14 +0000
Subject: [PATCH 043/236] x86/resctrl: Move get_config_index() to a header

commit f62b4e45e0b467cba75ae816338b996c6dc4dafa upstream.

get_config_index() is used by the architecture specific code to map
a CLOSID+type pair to an index in the configuration arrays.

MPAM needs to do this too to preserve the ABI to user-space, there is no
reason to do it differently.

Move the helper to a header file to allow all architectures that either
use or emulate CDP to use the same pattern of CLOSID values. Moving
this to a header file means it must be marked inline, which matches
the existing compiler choice for this static function.

Co-developed-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-30-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 19 +++----------------
 include/linux/resctrl.h                   | 15 +++++++++++++++
 2 files changed, 18 insertions(+), 16 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 1ecc93282b7d7..0a0ac5f6112ec 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -287,25 +287,12 @@ static int parse_line(char *line, struct resctrl_schema *s,
 	return -EINVAL;
 }
 
-static u32 get_config_index(u32 closid, enum resctrl_conf_type type)
-{
-	switch (type) {
-	default:
-	case CDP_NONE:
-		return closid;
-	case CDP_CODE:
-		return closid * 2 + 1;
-	case CDP_DATA:
-		return closid * 2;
-	}
-}
-
 int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_ctrl_domain *d,
 			    u32 closid, enum resctrl_conf_type t, u32 cfg_val)
 {
 	struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(d);
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
-	u32 idx = get_config_index(closid, t);
+	u32 idx = resctrl_get_config_index(closid, t);
 	struct msr_param msr_param;
 
 	if (!cpumask_test_cpu(smp_processor_id(), &d->hdr.cpu_mask))
@@ -342,7 +329,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 			if (!cfg->have_new_ctrl)
 				continue;
 
-			idx = get_config_index(closid, t);
+			idx = resctrl_get_config_index(closid, t);
 			if (cfg->new_ctrl == hw_dom->ctrl_val[idx])
 				continue;
 			hw_dom->ctrl_val[idx] = cfg->new_ctrl;
@@ -462,7 +449,7 @@ u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_ctrl_domain *d,
 			    u32 closid, enum resctrl_conf_type type)
 {
 	struct rdt_hw_ctrl_domain *hw_dom = resctrl_to_arch_ctrl_dom(d);
-	u32 idx = get_config_index(closid, type);
+	u32 idx = resctrl_get_config_index(closid, type);
 
 	return hw_dom->ctrl_val[idx];
 }
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 226cc5c0d765f..880351ca3dfcb 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -384,6 +384,21 @@ void resctrl_arch_mon_event_config_write(void *config_info);
  */
 void resctrl_arch_mon_event_config_read(void *config_info);
 
+/* For use by arch code to remap resctrl's smaller CDP CLOSID range */
+static inline u32 resctrl_get_config_index(u32 closid,
+					   enum resctrl_conf_type type)
+{
+	switch (type) {
+	default:
+	case CDP_NONE:
+		return closid;
+	case CDP_CODE:
+		return closid * 2 + 1;
+	case CDP_DATA:
+		return closid * 2;
+	}
+}
+
 /*
  * Update the ctrl_val and apply this config right now.
  * Must be called on one of the domain's CPUs.

From 88c3168b92d0ae1e85e81a76756f0de093466fac Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 11 Mar 2025 18:37:15 +0000
Subject: [PATCH 044/236] x86/resctrl: Move get_{mon,ctrl}_domain_from_cpu() to
 live with their callers

commit 823beb31e55673bf2fd21374e095eec73a761ee7 upstream.

Each of get_{mon,ctrl}_domain_from_cpu() only has one caller.

Once the filesystem code is moved to /fs/, there is no equivalent to
core.c.

Move these functions to each live next to their caller. This allows
them to be made static and the header file entries to be removed.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20250311183715.16445-31-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c     | 30 --------------------------
 arch/x86/kernel/cpu/resctrl/internal.h |  2 --
 arch/x86/kernel/cpu/resctrl/monitor.c  | 16 ++++++++++++++
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 16 ++++++++++++++
 4 files changed, 32 insertions(+), 32 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 1eb707a82ab4f..081082a3304a5 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -347,36 +347,6 @@ static void cat_wrmsr(struct msr_param *m)
 		wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]);
 }
 
-struct rdt_ctrl_domain *get_ctrl_domain_from_cpu(int cpu, struct rdt_resource *r)
-{
-	struct rdt_ctrl_domain *d;
-
-	lockdep_assert_cpus_held();
-
-	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
-		/* Find the domain that contains this CPU */
-		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask))
-			return d;
-	}
-
-	return NULL;
-}
-
-struct rdt_mon_domain *get_mon_domain_from_cpu(int cpu, struct rdt_resource *r)
-{
-	struct rdt_mon_domain *d;
-
-	lockdep_assert_cpus_held();
-
-	list_for_each_entry(d, &r->mon_domains, hdr.list) {
-		/* Find the domain that contains this CPU */
-		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask))
-			return d;
-	}
-
-	return NULL;
-}
-
 u32 resctrl_arch_get_num_closid(struct rdt_resource *r)
 {
 	return resctrl_to_arch_res(r)->num_closid;
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 09c3d8abf7c29..96ef5260abb23 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -478,8 +478,6 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_ctrl_domain
 				  unsigned long cbm);
 enum rdtgrp_mode rdtgroup_mode_by_closid(int closid);
 int rdtgroup_tasks_assigned(struct rdtgroup *r);
-struct rdt_ctrl_domain *get_ctrl_domain_from_cpu(int cpu, struct rdt_resource *r);
-struct rdt_mon_domain *get_mon_domain_from_cpu(int cpu, struct rdt_resource *r);
 int closids_supported(void);
 void closid_free(int closid);
 int alloc_rmid(u32 closid);
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 8685278521b7c..d8d21f76de14b 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -718,6 +718,22 @@ void mon_event_count(void *info)
 		rr->err = 0;
 }
 
+static struct rdt_ctrl_domain *get_ctrl_domain_from_cpu(int cpu,
+							struct rdt_resource *r)
+{
+	struct rdt_ctrl_domain *d;
+
+	lockdep_assert_cpus_held();
+
+	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
+		/* Find the domain that contains this CPU */
+		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask))
+			return d;
+	}
+
+	return NULL;
+}
+
 /*
  * Feedback loop for MBA software controller (mba_sc)
  *
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 5fc60c9ce28f8..c6274d40b217c 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -4257,6 +4257,22 @@ static void clear_childcpus(struct rdtgroup *r, unsigned int cpu)
 	}
 }
 
+static struct rdt_mon_domain *get_mon_domain_from_cpu(int cpu,
+						      struct rdt_resource *r)
+{
+	struct rdt_mon_domain *d;
+
+	lockdep_assert_cpus_held();
+
+	list_for_each_entry(d, &r->mon_domains, hdr.list) {
+		/* Find the domain that contains this CPU */
+		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask))
+			return d;
+	}
+
+	return NULL;
+}
+
 void resctrl_offline_cpu(unsigned int cpu)
 {
 	struct rdt_resource *l3 = resctrl_arch_get_resource(RDT_RESOURCE_L3);

From 9056164306251f7dad0e7884f9447f0c1db88903 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Mon, 31 Jul 2023 22:08:17 -0700
Subject: [PATCH 045/236] cpumask: kernel-doc cleanups and additions

commit 57f728d59f005dffdbb52a03531e480a71599bc5 upstream.

Clean up some punctutation and abbreviations.
Add kernel-doc notation for one function and function return value
for 39 functions.

cpumask.h:
Fix some punctuation (plural vs. possessive).
Fix some abbreviations (ie. -> i.e., id -> ID).

Fix 35 warnings like this:
include/linux/cpumask.h:161: warning: No description found for return value of 'cpumask_first'

cpumask.c:
Add Return: value for 4 functions.
Add kernel-doc for cpumask_any_distribute().

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Yury Norov <yury.norov@gmail.com>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 include/linux/cpumask.h | 113 ++++++++++++++++++++++++----------------
 lib/cpumask.c           |  17 ++++--
 2 files changed, 81 insertions(+), 49 deletions(-)

diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 115fd469bac37..f1540e7b5a23c 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -4,7 +4,7 @@
 
 /*
  * Cpumasks provide a bitmap suitable for representing the
- * set of CPU's in a system, one bit position per CPU number.  In general,
+ * set of CPUs in a system, one bit position per CPU number.  In general,
  * only nr_cpu_ids (<= NR_CPUS) bits are valid.
  */
 #include <linux/kernel.h>
@@ -97,7 +97,7 @@ static inline void set_nr_cpu_ids(unsigned int nr)
  *
  *  If !CONFIG_HOTPLUG_CPU, present == possible, and active == online.
  *
- *  The cpu_possible_mask is fixed at boot time, as the set of CPU id's
+ *  The cpu_possible_mask is fixed at boot time, as the set of CPU IDs
  *  that it is possible might ever be plugged in at anytime during the
  *  life of that system boot.  The cpu_present_mask is dynamic(*),
  *  representing which CPUs are currently plugged in.  And
@@ -112,7 +112,7 @@ static inline void set_nr_cpu_ids(unsigned int nr)
  *      hotplug, it's a copy of cpu_possible_mask, hence fixed at boot.
  *
  * Subtleties:
- * 1) UP arch's (NR_CPUS == 1, CONFIG_SMP not defined) hardcode
+ * 1) UP ARCHes (NR_CPUS == 1, CONFIG_SMP not defined) hardcode
  *    assumption that their single CPU is online.  The UP
  *    cpu_{online,possible,present}_masks are placebos.  Changing them
  *    will have no useful affect on the following num_*_cpus()
@@ -155,7 +155,7 @@ static __always_inline unsigned int cpumask_check(unsigned int cpu)
  * cpumask_first - get the first cpu in a cpumask
  * @srcp: the cpumask pointer
  *
- * Returns >= nr_cpu_ids if no cpus set.
+ * Return: >= nr_cpu_ids if no cpus set.
  */
 static inline unsigned int cpumask_first(const struct cpumask *srcp)
 {
@@ -166,7 +166,7 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp)
  * cpumask_first_zero - get the first unset cpu in a cpumask
  * @srcp: the cpumask pointer
  *
- * Returns >= nr_cpu_ids if all cpus are set.
+ * Return: >= nr_cpu_ids if all cpus are set.
  */
 static inline unsigned int cpumask_first_zero(const struct cpumask *srcp)
 {
@@ -178,7 +178,7 @@ static inline unsigned int cpumask_first_zero(const struct cpumask *srcp)
  * @srcp1: the first input
  * @srcp2: the second input
  *
- * Returns >= nr_cpu_ids if no cpus set in both.  See also cpumask_next_and().
+ * Return: >= nr_cpu_ids if no cpus set in both.  See also cpumask_next_and().
  */
 static inline
 unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask *srcp2)
@@ -190,7 +190,7 @@ unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask
  * cpumask_last - get the last CPU in a cpumask
  * @srcp:	- the cpumask pointer
  *
- * Returns	>= nr_cpumask_bits if no CPUs set.
+ * Return:	>= nr_cpumask_bits if no CPUs set.
  */
 static inline unsigned int cpumask_last(const struct cpumask *srcp)
 {
@@ -199,10 +199,10 @@ static inline unsigned int cpumask_last(const struct cpumask *srcp)
 
 /**
  * cpumask_next - get the next cpu in a cpumask
- * @n: the cpu prior to the place to search (ie. return will be > @n)
+ * @n: the cpu prior to the place to search (i.e. return will be > @n)
  * @srcp: the cpumask pointer
  *
- * Returns >= nr_cpu_ids if no further cpus set.
+ * Return: >= nr_cpu_ids if no further cpus set.
  */
 static inline
 unsigned int cpumask_next(int n, const struct cpumask *srcp)
@@ -215,10 +215,10 @@ unsigned int cpumask_next(int n, const struct cpumask *srcp)
 
 /**
  * cpumask_next_zero - get the next unset cpu in a cpumask
- * @n: the cpu prior to the place to search (ie. return will be > @n)
+ * @n: the cpu prior to the place to search (i.e. return will be > @n)
  * @srcp: the cpumask pointer
  *
- * Returns >= nr_cpu_ids if no further cpus unset.
+ * Return: >= nr_cpu_ids if no further cpus unset.
  */
 static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp)
 {
@@ -254,11 +254,11 @@ unsigned int cpumask_any_distribute(const struct cpumask *srcp);
 
 /**
  * cpumask_next_and - get the next cpu in *src1p & *src2p
- * @n: the cpu prior to the place to search (ie. return will be > @n)
+ * @n: the cpu prior to the place to search (i.e. return will be > @n)
  * @src1p: the first cpumask pointer
  * @src2p: the second cpumask pointer
  *
- * Returns >= nr_cpu_ids if no further cpus set in both.
+ * Return: >= nr_cpu_ids if no further cpus set in both.
  */
 static inline
 unsigned int cpumask_next_and(int n, const struct cpumask *src1p,
@@ -373,7 +373,7 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta
  * @cpu: the cpu to ignore.
  *
  * Often used to find any cpu but smp_processor_id() in a mask.
- * Returns >= nr_cpu_ids if no cpus set.
+ * Return: >= nr_cpu_ids if no cpus set.
  */
 static inline
 unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
@@ -388,11 +388,11 @@ unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
 }
 
 /**
- * cpumask_nth - get the first cpu in a cpumask
+ * cpumask_nth - get the Nth cpu in a cpumask
  * @srcp: the cpumask pointer
- * @cpu: the N'th cpu to find, starting from 0
+ * @cpu: the Nth cpu to find, starting from 0
  *
- * Returns >= nr_cpu_ids if such cpu doesn't exist.
+ * Return: >= nr_cpu_ids if such cpu doesn't exist.
  */
 static inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp)
 {
@@ -400,12 +400,12 @@ static inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *s
 }
 
 /**
- * cpumask_nth_and - get the first cpu in 2 cpumasks
+ * cpumask_nth_and - get the Nth cpu in 2 cpumasks
  * @srcp1: the cpumask pointer
  * @srcp2: the cpumask pointer
- * @cpu: the N'th cpu to find, starting from 0
+ * @cpu: the Nth cpu to find, starting from 0
  *
- * Returns >= nr_cpu_ids if such cpu doesn't exist.
+ * Return: >= nr_cpu_ids if such cpu doesn't exist.
  */
 static inline
 unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1,
@@ -416,12 +416,12 @@ unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1,
 }
 
 /**
- * cpumask_nth_andnot - get the first cpu set in 1st cpumask, and clear in 2nd.
+ * cpumask_nth_andnot - get the Nth cpu set in 1st cpumask, and clear in 2nd.
  * @srcp1: the cpumask pointer
  * @srcp2: the cpumask pointer
- * @cpu: the N'th cpu to find, starting from 0
+ * @cpu: the Nth cpu to find, starting from 0
  *
- * Returns >= nr_cpu_ids if such cpu doesn't exist.
+ * Return: >= nr_cpu_ids if such cpu doesn't exist.
  */
 static inline
 unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1,
@@ -436,9 +436,9 @@ unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1,
  * @srcp1: the cpumask pointer
  * @srcp2: the cpumask pointer
  * @srcp3: the cpumask pointer
- * @cpu: the N'th cpu to find, starting from 0
+ * @cpu: the Nth cpu to find, starting from 0
  *
- * Returns >= nr_cpu_ids if such cpu doesn't exist.
+ * Return: >= nr_cpu_ids if such cpu doesn't exist.
  */
 static __always_inline
 unsigned int cpumask_nth_and_andnot(unsigned int cpu, const struct cpumask *srcp1,
@@ -497,7 +497,7 @@ static __always_inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp)
  * @cpu: cpu number (< nr_cpu_ids)
  * @cpumask: the cpumask pointer
  *
- * Returns true if @cpu is set in @cpumask, else returns false
+ * Return: true if @cpu is set in @cpumask, else returns false
  */
 static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask)
 {
@@ -509,9 +509,9 @@ static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpum
  * @cpu: cpu number (< nr_cpu_ids)
  * @cpumask: the cpumask pointer
  *
- * Returns true if @cpu is set in old bitmap of @cpumask, else returns false
- *
  * test_and_set_bit wrapper for cpumasks.
+ *
+ * Return: true if @cpu is set in old bitmap of @cpumask, else returns false
  */
 static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask)
 {
@@ -523,9 +523,9 @@ static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cp
  * @cpu: cpu number (< nr_cpu_ids)
  * @cpumask: the cpumask pointer
  *
- * Returns true if @cpu is set in old bitmap of @cpumask, else returns false
- *
  * test_and_clear_bit wrapper for cpumasks.
+ *
+ * Return: true if @cpu is set in old bitmap of @cpumask, else returns false
  */
 static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask)
 {
@@ -560,7 +560,7 @@ static inline void cpumask_clear(struct cpumask *dstp)
  * @src1p: the first input
  * @src2p: the second input
  *
- * If *@dstp is empty, returns false, else returns true
+ * Return: false if *@dstp is empty, else returns true
  */
 static inline bool cpumask_and(struct cpumask *dstp,
 			       const struct cpumask *src1p,
@@ -603,7 +603,7 @@ static inline void cpumask_xor(struct cpumask *dstp,
  * @src1p: the first input
  * @src2p: the second input
  *
- * If *@dstp is empty, returns false, else returns true
+ * Return: false if *@dstp is empty, else returns true
  */
 static inline bool cpumask_andnot(struct cpumask *dstp,
 				  const struct cpumask *src1p,
@@ -617,6 +617,8 @@ static inline bool cpumask_andnot(struct cpumask *dstp,
  * cpumask_equal - *src1p == *src2p
  * @src1p: the first input
  * @src2p: the second input
+ *
+ * Return: true if the cpumasks are equal, false if not
  */
 static inline bool cpumask_equal(const struct cpumask *src1p,
 				const struct cpumask *src2p)
@@ -630,6 +632,9 @@ static inline bool cpumask_equal(const struct cpumask *src1p,
  * @src1p: the first input
  * @src2p: the second input
  * @src3p: the third input
+ *
+ * Return: true if first cpumask ORed with second cpumask == third cpumask,
+ *	   otherwise false
  */
 static inline bool cpumask_or_equal(const struct cpumask *src1p,
 				    const struct cpumask *src2p,
@@ -643,6 +648,9 @@ static inline bool cpumask_or_equal(const struct cpumask *src1p,
  * cpumask_intersects - (*src1p & *src2p) != 0
  * @src1p: the first input
  * @src2p: the second input
+ *
+ * Return: true if first cpumask ANDed with second cpumask is non-empty,
+ *	   otherwise false
  */
 static inline bool cpumask_intersects(const struct cpumask *src1p,
 				     const struct cpumask *src2p)
@@ -656,7 +664,7 @@ static inline bool cpumask_intersects(const struct cpumask *src1p,
  * @src1p: the first input
  * @src2p: the second input
  *
- * Returns true if *@src1p is a subset of *@src2p, else returns false
+ * Return: true if *@src1p is a subset of *@src2p, else returns false
  */
 static inline bool cpumask_subset(const struct cpumask *src1p,
 				 const struct cpumask *src2p)
@@ -668,6 +676,8 @@ static inline bool cpumask_subset(const struct cpumask *src1p,
 /**
  * cpumask_empty - *srcp == 0
  * @srcp: the cpumask to that all cpus < nr_cpu_ids are clear.
+ *
+ * Return: true if srcp is empty (has no bits set), else false
  */
 static inline bool cpumask_empty(const struct cpumask *srcp)
 {
@@ -677,6 +687,8 @@ static inline bool cpumask_empty(const struct cpumask *srcp)
 /**
  * cpumask_full - *srcp == 0xFFFFFFFF...
  * @srcp: the cpumask to that all cpus < nr_cpu_ids are set.
+ *
+ * Return: true if srcp is full (has all bits set), else false
  */
 static inline bool cpumask_full(const struct cpumask *srcp)
 {
@@ -686,6 +698,8 @@ static inline bool cpumask_full(const struct cpumask *srcp)
 /**
  * cpumask_weight - Count of bits in *srcp
  * @srcp: the cpumask to count bits (< nr_cpu_ids) in.
+ *
+ * Return: count of bits set in *srcp
  */
 static inline unsigned int cpumask_weight(const struct cpumask *srcp)
 {
@@ -696,6 +710,8 @@ static inline unsigned int cpumask_weight(const struct cpumask *srcp)
  * cpumask_weight_and - Count of bits in (*srcp1 & *srcp2)
  * @srcp1: the cpumask to count bits (< nr_cpu_ids) in.
  * @srcp2: the cpumask to count bits (< nr_cpu_ids) in.
+ *
+ * Return: count of bits set in both *srcp1 and *srcp2
  */
 static inline unsigned int cpumask_weight_and(const struct cpumask *srcp1,
 						const struct cpumask *srcp2)
@@ -744,7 +760,7 @@ static inline void cpumask_copy(struct cpumask *dstp,
  * cpumask_any - pick a "random" cpu from *srcp
  * @srcp: the input cpumask
  *
- * Returns >= nr_cpu_ids if no cpus set.
+ * Return: >= nr_cpu_ids if no cpus set.
  */
 #define cpumask_any(srcp) cpumask_first(srcp)
 
@@ -753,7 +769,7 @@ static inline void cpumask_copy(struct cpumask *dstp,
  * @mask1: the first input cpumask
  * @mask2: the second input cpumask
  *
- * Returns >= nr_cpu_ids if no cpus set.
+ * Return: >= nr_cpu_ids if no cpus set.
  */
 #define cpumask_any_and(mask1, mask2) cpumask_first_and((mask1), (mask2))
 
@@ -769,7 +785,7 @@ static inline void cpumask_copy(struct cpumask *dstp,
  * @len: the length of the buffer
  * @dstp: the cpumask to set.
  *
- * Returns -errno, or 0 for success.
+ * Return: -errno, or 0 for success.
  */
 static inline int cpumask_parse_user(const char __user *buf, int len,
 				     struct cpumask *dstp)
@@ -783,7 +799,7 @@ static inline int cpumask_parse_user(const char __user *buf, int len,
  * @len: the length of the buffer
  * @dstp: the cpumask to set.
  *
- * Returns -errno, or 0 for success.
+ * Return: -errno, or 0 for success.
  */
 static inline int cpumask_parselist_user(const char __user *buf, int len,
 				     struct cpumask *dstp)
@@ -797,7 +813,7 @@ static inline int cpumask_parselist_user(const char __user *buf, int len,
  * @buf: the buffer to extract from
  * @dstp: the cpumask to set.
  *
- * Returns -errno, or 0 for success.
+ * Return: -errno, or 0 for success.
  */
 static inline int cpumask_parse(const char *buf, struct cpumask *dstp)
 {
@@ -809,7 +825,7 @@ static inline int cpumask_parse(const char *buf, struct cpumask *dstp)
  * @buf: the buffer to extract from
  * @dstp: the cpumask to set.
  *
- * Returns -errno, or 0 for success.
+ * Return: -errno, or 0 for success.
  */
 static inline int cpulist_parse(const char *buf, struct cpumask *dstp)
 {
@@ -817,7 +833,9 @@ static inline int cpulist_parse(const char *buf, struct cpumask *dstp)
 }
 
 /**
- * cpumask_size - size to allocate for a 'struct cpumask' in bytes
+ * cpumask_size - calculate size to allocate for a 'struct cpumask' in bytes
+ *
+ * Return: size to allocate for a &struct cpumask in bytes
  */
 static inline unsigned int cpumask_size(void)
 {
@@ -831,7 +849,7 @@ static inline unsigned int cpumask_size(void)
  * little more difficult, we typedef cpumask_var_t to an array or a
  * pointer: doing &mask on an array is a noop, so it still works.
  *
- * ie.
+ * i.e.
  *	cpumask_var_t tmpmask;
  *	if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL))
  *		return -ENOMEM;
@@ -887,6 +905,8 @@ bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
  * a nop returning a constant 1 (in <linux/cpumask.h>).
  *
  * See alloc_cpumask_var_node.
+ *
+ * Return: %true if allocation succeeded, %false if not
  */
 static inline
 bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
@@ -997,7 +1017,7 @@ static inline void reset_cpu_possible_mask(void)
 void set_cpu_online(unsigned int cpu, bool online);
 
 /**
- * to_cpumask - convert an NR_CPUS bitmap to a struct cpumask *
+ * to_cpumask - convert a NR_CPUS bitmap to a struct cpumask *
  * @bitmap: the bitmap
  *
  * There are a few places where cpumask_var_t isn't appropriate and
@@ -1040,6 +1060,8 @@ static inline const struct cpumask *get_cpu_mask(unsigned int cpu)
  * interface gives only a momentary snapshot and is not protected against
  * concurrent CPU hotplug operations unless invoked from a cpuhp_lock held
  * region.
+ *
+ * Return: momentary snapshot of the number of online CPUs
  */
 static __always_inline unsigned int num_online_cpus(void)
 {
@@ -1132,7 +1154,7 @@ static inline bool cpu_dying(unsigned int cpu)
  * @mask: the cpumask to copy
  * @buf: the buffer to copy into
  *
- * Returns the length of the (null-terminated) @buf string, zero if
+ * Return: the length of the (null-terminated) @buf string, zero if
  * nothing is copied.
  */
 static inline ssize_t
@@ -1155,7 +1177,7 @@ cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask)
  * cpumask; Typically used by bin_attribute to export cpumask bitmask
  * ABI.
  *
- * Returns the length of how many bytes have been copied, excluding
+ * Return: the length of how many bytes have been copied, excluding
  * terminating '\0'.
  */
 static inline ssize_t
@@ -1176,6 +1198,9 @@ cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask,
  *
  * Everything is same with the above cpumap_print_bitmask_to_buf()
  * except the print format.
+ *
+ * Return: the length of how many bytes have been copied, excluding
+ * terminating '\0'.
  */
 static inline ssize_t
 cpumap_print_list_to_buf(char *buf, const struct cpumask *mask,
diff --git a/lib/cpumask.c b/lib/cpumask.c
index 34335c1e72653..e77ee9d46f71b 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -14,7 +14,7 @@
  * @start: the start point of the iteration
  * @wrap: assume @n crossing @start terminates the iteration
  *
- * Returns >= nr_cpu_ids on completion
+ * Return: >= nr_cpu_ids on completion
  *
  * Note: the @wrap argument is required for the start condition when
  * we cannot assume @start is set in @mask.
@@ -48,8 +48,9 @@ EXPORT_SYMBOL(cpumask_next_wrap);
  * @node: memory node from which to allocate or %NUMA_NO_NODE
  *
  * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is
- * a nop returning a constant 1 (in <linux/cpumask.h>)
- * Returns TRUE if memory allocation succeeded, FALSE otherwise.
+ * a nop returning a constant 1 (in <linux/cpumask.h>).
+ *
+ * Return: TRUE if memory allocation succeeded, FALSE otherwise.
  *
  * In addition, mask will be NULL if this fails.  Note that gcc is
  * usually smart enough to know that mask can never be NULL if
@@ -115,7 +116,7 @@ void __init free_bootmem_cpumask_var(cpumask_var_t mask)
  * @i: index number
  * @node: local numa_node
  *
- * Returns online CPU according to a numa aware policy; local cpus are returned
+ * Return: online CPU according to a numa aware policy; local cpus are returned
  * first, followed by non-local ones, then it wraps around.
  *
  * For those who wants to enumerate all CPUs based on their NUMA distances,
@@ -163,7 +164,7 @@ static DEFINE_PER_CPU(int, distribute_cpu_mask_prev);
  * Iterated calls using the same srcp1 and srcp2 will be distributed within
  * their intersection.
  *
- * Returns >= nr_cpu_ids if the intersection is empty.
+ * Return: >= nr_cpu_ids if the intersection is empty.
  */
 unsigned int cpumask_any_and_distribute(const struct cpumask *src1p,
 			       const struct cpumask *src2p)
@@ -182,6 +183,12 @@ unsigned int cpumask_any_and_distribute(const struct cpumask *src1p,
 }
 EXPORT_SYMBOL(cpumask_any_and_distribute);
 
+/**
+ * cpumask_any_distribute - Return an arbitrary cpu from srcp
+ * @srcp: &cpumask for selection
+ *
+ * Return: >= nr_cpu_ids if the intersection is empty.
+ */
 unsigned int cpumask_any_distribute(const struct cpumask *srcp)
 {
 	unsigned int next, prev;

From d1f4f0b687be924a4a7cc9c99765efe1e84e569d Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 3 Apr 2024 23:59:41 +0800
Subject: [PATCH 046/236] cpumask: add cpumask_any_and_but()

commit 897fa2c38c076c801bd1f1238af0af927e339c8f upstream.

In some cases, it's useful to be able to select a random cpu from the
intersection of two masks, excluding a particular CPU.

For example, in some systems an uncore PMU is shared by a subset of
CPUs, and management of this PMU is assigned to some arbitrary CPU in
this set. Whenever the management CPU is hotplugged out, we wish to
migrate responsibility to another arbitrary CPU which is both in this
set and online.

Today we can use cpumask_any_and() to select an arbitrary CPU in the
intersection of two masks. We can also use cpumask_any_but() to select
any arbitrary cpu in a mask excluding, a particular CPU.

To do both, we either need to use a temporary cpumask, which is
wasteful, or use some lower-level cpumask helpers, which can be unclear.

This patch adds a new cpumask_any_and_but() to cater for these cases.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Dawei Li <dawei.li@shingroup.cn>
Acked-by: Yury Norov <yury.norov@gmail.com>
Link: https://lore.kernel.org/r/20240403155950.2068109-2-dawei.li@shingroup.cn
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 include/linux/cpumask.h | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index f1540e7b5a23c..69bcdbb261f16 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -387,6 +387,29 @@ unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
 	return i;
 }
 
+/**
+ * cpumask_any_and_but - pick a "random" cpu from *mask1 & *mask2, but not this one.
+ * @mask1: the first input cpumask
+ * @mask2: the second input cpumask
+ * @cpu: the cpu to ignore
+ *
+ * Returns >= nr_cpu_ids if no cpus set.
+ */
+static inline
+unsigned int cpumask_any_and_but(const struct cpumask *mask1,
+				 const struct cpumask *mask2,
+				 unsigned int cpu)
+{
+	unsigned int i;
+
+	cpumask_check(cpu);
+	i = cpumask_first_and(mask1, mask2);
+	if (i != cpu)
+		return i;
+
+	return cpumask_next_and(cpu, mask1, mask2);
+}
+
 /**
  * cpumask_nth - get the Nth cpu in a cpumask
  * @srcp: the cpumask pointer

From 257f96805959d4c3b9a898e96ef2b60c66f0463f Mon Sep 17 00:00:00 2001
From: Yury Norov <yury.norov@gmail.com>
Date: Sun, 28 Jan 2024 22:21:04 -0800
Subject: [PATCH 047/236] cpumask: add cpumask_weight_andnot()

commit c1f5204efcbcced83f67f12fa8f1a7f5f244fb87 upstream.

Similarly to cpumask_weight_and(), cpumask_weight_andnot() is a handy
helper that may help to avoid creating an intermediate mask just to
calculate number of bits that set in a 1st given mask, and clear in 2nd
one.

Signed-off-by: Yury Norov <yury.norov@gmail.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 include/linux/bitmap.h  | 12 ++++++++++++
 include/linux/cpumask.h | 13 +++++++++++++
 lib/bitmap.c            |  7 +++++++
 3 files changed, 32 insertions(+)

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 729ec2453149f..9278b2fa6f381 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -52,6 +52,7 @@ struct device;
  *  bitmap_full(src, nbits)                     Are all bits set in *src?
  *  bitmap_weight(src, nbits)                   Hamming Weight: number set bits
  *  bitmap_weight_and(src1, src2, nbits)        Hamming Weight of and'ed bitmap
+ *  bitmap_weight_andnot(src1, src2, nbits)     Hamming Weight of andnot'ed bitmap
  *  bitmap_set(dst, pos, nbits)                 Set specified bit area
  *  bitmap_clear(dst, pos, nbits)               Clear specified bit area
  *  bitmap_find_next_zero_area(buf, len, pos, n, mask)  Find bit free area
@@ -171,6 +172,8 @@ bool __bitmap_subset(const unsigned long *bitmap1,
 unsigned int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits);
 unsigned int __bitmap_weight_and(const unsigned long *bitmap1,
 				 const unsigned long *bitmap2, unsigned int nbits);
+unsigned int __bitmap_weight_andnot(const unsigned long *bitmap1,
+				    const unsigned long *bitmap2, unsigned int nbits);
 void __bitmap_set(unsigned long *map, unsigned int start, int len);
 void __bitmap_clear(unsigned long *map, unsigned int start, int len);
 
@@ -466,6 +469,15 @@ unsigned long bitmap_weight_and(const unsigned long *src1,
 	return __bitmap_weight_and(src1, src2, nbits);
 }
 
+static __always_inline
+unsigned long bitmap_weight_andnot(const unsigned long *src1,
+				   const unsigned long *src2, unsigned int nbits)
+{
+	if (small_const_nbits(nbits))
+		return hweight_long(*src1 & ~(*src2) & BITMAP_LAST_WORD_MASK(nbits));
+	return __bitmap_weight_andnot(src1, src2, nbits);
+}
+
 static __always_inline void bitmap_set(unsigned long *map, unsigned int start,
 		unsigned int nbits)
 {
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 69bcdbb261f16..574ed3853b3f9 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -742,6 +742,19 @@ static inline unsigned int cpumask_weight_and(const struct cpumask *srcp1,
 	return bitmap_weight_and(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits);
 }
 
+/**
+ * cpumask_weight_andnot - Count of bits in (*srcp1 & ~*srcp2)
+ * @srcp1: the cpumask to count bits (< nr_cpu_ids) in.
+ * @srcp2: the cpumask to count bits (< nr_cpu_ids) in.
+ *
+ * Return: count of bits set in both *srcp1 and *srcp2
+ */
+static inline unsigned int cpumask_weight_andnot(const struct cpumask *srcp1,
+						const struct cpumask *srcp2)
+{
+	return bitmap_weight_andnot(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits);
+}
+
 /**
  * cpumask_shift_right - *dstp = *srcp >> n
  * @dstp: the cpumask result
diff --git a/lib/bitmap.c b/lib/bitmap.c
index ddb31015e38ae..4bd5fb263b1d9 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -359,6 +359,13 @@ unsigned int __bitmap_weight_and(const unsigned long *bitmap1,
 }
 EXPORT_SYMBOL(__bitmap_weight_and);
 
+unsigned int __bitmap_weight_andnot(const unsigned long *bitmap1,
+				const unsigned long *bitmap2, unsigned int bits)
+{
+	return BITMAP_WEIGHT(bitmap1[idx] & ~bitmap2[idx], bits);
+}
+EXPORT_SYMBOL(__bitmap_weight_andnot);
+
 void __bitmap_set(unsigned long *map, unsigned int start, int len)
 {
 	unsigned long *p = map + BIT_WORD(start);

From 9417c71157501f3bac37c4eae5614d1f4ae2dd47 Mon Sep 17 00:00:00 2001
From: Dawei Li <dawei.li@shingroup.cn>
Date: Tue, 16 Apr 2024 16:54:48 +0800
Subject: [PATCH 048/236] cpumask: Introduce cpumask_first_and_and()

commit cdc66553c4130735f0a2db943a5259e54ff1597a upstream.

Introduce cpumask_first_and_and() to get intersection between 3 cpumasks,
free of any intermediate cpumask variable. Instead, cpumask_first_and_and()
works in-place with all inputs and produces desired output directly.

Signed-off-by: Dawei Li <dawei.li@shingroup.cn>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Yury Norov <yury.norov@gmail.com>
Link: https://lore.kernel.org/r/20240416085454.3547175-2-dawei.li@shingroup.cn
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 include/linux/cpumask.h | 17 +++++++++++++++++
 include/linux/find.h    | 27 +++++++++++++++++++++++++++
 lib/find_bit.c          | 12 ++++++++++++
 3 files changed, 56 insertions(+)

diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 574ed3853b3f9..ff5a9091ec88c 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -186,6 +186,23 @@ unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask
 	return find_first_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits);
 }
 
+/**
+ * cpumask_first_and_and - return the first cpu from *srcp1 & *srcp2 & *srcp3
+ * @srcp1: the first input
+ * @srcp2: the second input
+ * @srcp3: the third input
+ *
+ * Return: >= nr_cpu_ids if no cpus set in all.
+ */
+static inline
+unsigned int cpumask_first_and_and(const struct cpumask *srcp1,
+				   const struct cpumask *srcp2,
+				   const struct cpumask *srcp3)
+{
+	return find_first_and_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2),
+				      cpumask_bits(srcp3), small_cpumask_bits);
+}
+
 /**
  * cpumask_last - get the last CPU in a cpumask
  * @srcp:	- the cpumask pointer
diff --git a/include/linux/find.h b/include/linux/find.h
index 5e4f39ef2e72c..a3a908a27df7e 100644
--- a/include/linux/find.h
+++ b/include/linux/find.h
@@ -29,6 +29,8 @@ unsigned long __find_nth_and_andnot_bit(const unsigned long *addr1, const unsign
 					unsigned long n);
 extern unsigned long _find_first_and_bit(const unsigned long *addr1,
 					 const unsigned long *addr2, unsigned long size);
+unsigned long _find_first_and_and_bit(const unsigned long *addr1, const unsigned long *addr2,
+				      const unsigned long *addr3, unsigned long size);
 extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size);
 extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size);
 
@@ -345,6 +347,31 @@ unsigned long find_first_and_bit(const unsigned long *addr1,
 }
 #endif
 
+/**
+ * find_first_and_and_bit - find the first set bit in 3 memory regions
+ * @addr1: The first address to base the search on
+ * @addr2: The second address to base the search on
+ * @addr3: The third address to base the search on
+ * @size: The bitmap size in bits
+ *
+ * Returns the bit number for the first set bit
+ * If no bits are set, returns @size.
+ */
+static inline
+unsigned long find_first_and_and_bit(const unsigned long *addr1,
+				     const unsigned long *addr2,
+				     const unsigned long *addr3,
+				     unsigned long size)
+{
+	if (small_const_nbits(size)) {
+		unsigned long val = *addr1 & *addr2 & *addr3 & GENMASK(size - 1, 0);
+
+		return val ? __ffs(val) : size;
+	}
+
+	return _find_first_and_and_bit(addr1, addr2, addr3, size);
+}
+
 #ifndef find_first_zero_bit
 /**
  * find_first_zero_bit - find the first cleared bit in a memory region
diff --git a/lib/find_bit.c b/lib/find_bit.c
index 32f99e9a670e6..dacadd904250f 100644
--- a/lib/find_bit.c
+++ b/lib/find_bit.c
@@ -116,6 +116,18 @@ unsigned long _find_first_and_bit(const unsigned long *addr1,
 EXPORT_SYMBOL(_find_first_and_bit);
 #endif
 
+/*
+ * Find the first set bit in three memory regions.
+ */
+unsigned long _find_first_and_and_bit(const unsigned long *addr1,
+				      const unsigned long *addr2,
+				      const unsigned long *addr3,
+				      unsigned long size)
+{
+	return FIND_FIRST_BIT(addr1[idx] & addr2[idx] & addr3[idx], /* nop */, size);
+}
+EXPORT_SYMBOL(_find_first_and_and_bit);
+
 #ifndef find_first_zero_bit
 /*
  * Find the first cleared bit in a memory region.

From 2c616d2322807e81a5e5413ce60d670730901700 Mon Sep 17 00:00:00 2001
From: Brian Norris <briannorris@chromium.org>
Date: Thu, 18 Jul 2024 17:50:39 -0700
Subject: [PATCH 049/236] cpumask: Switch from inline to __always_inline

commit ab6b1010dab68f6d4bf063517db4ce2d63554bc6 upstream.

On recent (v6.6+) builds with Clang (based on Clang 18.0.0) and certain
configurations [0], I'm finding that (lack of) inlining decisions may
lead to section mismatch warnings like the following:

  WARNING: modpost: vmlinux.o: section mismatch in reference:
  cpumask_andnot (section: .text) ->
  cpuhp_bringup_cpus_parallel.tmp_mask (section: .init.data) ERROR:
  modpost: Section mismatches detected.

or more confusingly:

  WARNING: modpost: vmlinux: section mismatch in reference:
  cpumask_andnot+0x5f (section: .text) -> efi_systab_phys (section:
  .init.data)

The first warning makes a little sense, because
cpuhp_bringup_cpus_parallel() (an __init function) calls
cpumask_andnot() on tmp_mask (an __initdata symbol). If the compiler
doesn't inline cpumask_andnot(), this may appear like a mismatch.

The second warning makes less sense, but might be because efi_systab_phys
and cpuhp_bringup_cpus_parallel.tmp_mask are laid out near each other,
and the latter isn't a proper C symbol definition.

In any case, it seems a reasonable solution to suggest more strongly to
the compiler that these cpumask macros *must* be inlined, as 'inline' is
just a recommendation.

This change has been previously proposed in the past as:

  Subject: [PATCH 1/3] bitmap: switch from inline to __always_inline
  https://lore.kernel.org/all/20221027043810.350460-2-yury.norov@gmail.com/

But the change has been split up, to separately justify the cpumask
changes (which drive my work) and the bitmap/const optimizations (that
Yury separately proposed for other reasons). This ends up as somewhere
between a "rebase" and "rewrite" -- I had to rewrite most of the patch.

According to bloat-o-meter, vmlinux decreases minimally in size (-0.00%
to -0.01%, depending on the version of GCC or Clang and .config in
question) with this series of changes:

gcc 13.2.0, x86_64_defconfig
-3005 bytes, Before=21944501, After=21941496, chg -0.01%

clang 16.0.6, x86_64_defconfig
-105 bytes, Before=22571692, After=22571587, chg -0.00%

gcc 9.5.0, x86_64_defconfig
-1771 bytes, Before=21557598, After=21555827, chg -0.01%

clang 18.0_pre516547 (ChromiumOS toolchain), x86_64_defconfig
-191 bytes, Before=22615339, After=22615148, chg -0.00%

clang 18.0_pre516547 (ChromiumOS toolchain), based on ChromiumOS config + gcov
-979 bytes, Before=76294783, After=76293804, chg -0.00%

[0] CONFIG_HOTPLUG_PARALLEL=y ('select'ed for x86 as of [1]) and
    CONFIG_GCOV_PROFILE_ALL.

[1] commit 0c7ffa32dbd6 ("x86/smpboot/64: Implement
    arch_cpuhp_init_parallel_bringup() and enable it")

Co-developed-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Brian Norris <briannorris@chromium.org>
Reviewed-by: Kees Cook <kees@kernel.org>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Yury Norov <yury.norov@gmail.com>

 Conflicts:
	include/linux/cpumask.h
[jz: resolve context conflicts]
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 include/linux/cpumask.h | 208 +++++++++++++++++++++-------------------
 1 file changed, 110 insertions(+), 98 deletions(-)

diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index ff5a9091ec88c..fbfd28280470f 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -41,7 +41,7 @@ typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t;
 extern unsigned int nr_cpu_ids;
 #endif
 
-static inline void set_nr_cpu_ids(unsigned int nr)
+static __always_inline void set_nr_cpu_ids(unsigned int nr)
 {
 #if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS)
 	WARN_ON(nr != nr_cpu_ids);
@@ -157,7 +157,7 @@ static __always_inline unsigned int cpumask_check(unsigned int cpu)
  *
  * Return: >= nr_cpu_ids if no cpus set.
  */
-static inline unsigned int cpumask_first(const struct cpumask *srcp)
+static __always_inline unsigned int cpumask_first(const struct cpumask *srcp)
 {
 	return find_first_bit(cpumask_bits(srcp), small_cpumask_bits);
 }
@@ -168,7 +168,7 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp)
  *
  * Return: >= nr_cpu_ids if all cpus are set.
  */
-static inline unsigned int cpumask_first_zero(const struct cpumask *srcp)
+static __always_inline unsigned int cpumask_first_zero(const struct cpumask *srcp)
 {
 	return find_first_zero_bit(cpumask_bits(srcp), small_cpumask_bits);
 }
@@ -180,7 +180,7 @@ static inline unsigned int cpumask_first_zero(const struct cpumask *srcp)
  *
  * Return: >= nr_cpu_ids if no cpus set in both.  See also cpumask_next_and().
  */
-static inline
+static __always_inline
 unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask *srcp2)
 {
 	return find_first_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits);
@@ -194,7 +194,7 @@ unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask
  *
  * Return: >= nr_cpu_ids if no cpus set in all.
  */
-static inline
+static __always_inline
 unsigned int cpumask_first_and_and(const struct cpumask *srcp1,
 				   const struct cpumask *srcp2,
 				   const struct cpumask *srcp3)
@@ -209,7 +209,7 @@ unsigned int cpumask_first_and_and(const struct cpumask *srcp1,
  *
  * Return:	>= nr_cpumask_bits if no CPUs set.
  */
-static inline unsigned int cpumask_last(const struct cpumask *srcp)
+static __always_inline unsigned int cpumask_last(const struct cpumask *srcp)
 {
 	return find_last_bit(cpumask_bits(srcp), small_cpumask_bits);
 }
@@ -221,7 +221,7 @@ static inline unsigned int cpumask_last(const struct cpumask *srcp)
  *
  * Return: >= nr_cpu_ids if no further cpus set.
  */
-static inline
+static __always_inline
 unsigned int cpumask_next(int n, const struct cpumask *srcp)
 {
 	/* -1 is a legal arg here. */
@@ -237,7 +237,8 @@ unsigned int cpumask_next(int n, const struct cpumask *srcp)
  *
  * Return: >= nr_cpu_ids if no further cpus unset.
  */
-static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp)
+static __always_inline
+unsigned int cpumask_next_zero(int n, const struct cpumask *srcp)
 {
 	/* -1 is a legal arg here. */
 	if (n != -1)
@@ -247,18 +248,21 @@ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp)
 
 #if NR_CPUS == 1
 /* Uniprocessor: there is only one valid CPU */
-static inline unsigned int cpumask_local_spread(unsigned int i, int node)
+static __always_inline
+unsigned int cpumask_local_spread(unsigned int i, int node)
 {
 	return 0;
 }
 
-static inline unsigned int cpumask_any_and_distribute(const struct cpumask *src1p,
-						      const struct cpumask *src2p)
+static __always_inline
+unsigned int cpumask_any_and_distribute(const struct cpumask *src1p,
+					const struct cpumask *src2p)
 {
 	return cpumask_first_and(src1p, src2p);
 }
 
-static inline unsigned int cpumask_any_distribute(const struct cpumask *srcp)
+static __always_inline
+unsigned int cpumask_any_distribute(const struct cpumask *srcp)
 {
 	return cpumask_first(srcp);
 }
@@ -277,9 +281,9 @@ unsigned int cpumask_any_distribute(const struct cpumask *srcp);
  *
  * Return: >= nr_cpu_ids if no further cpus set in both.
  */
-static inline
+static __always_inline
 unsigned int cpumask_next_and(int n, const struct cpumask *src1p,
-		     const struct cpumask *src2p)
+			      const struct cpumask *src2p)
 {
 	/* -1 is a legal arg here. */
 	if (n != -1)
@@ -299,7 +303,7 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p,
 	for_each_set_bit(cpu, cpumask_bits(mask), small_cpumask_bits)
 
 #if NR_CPUS == 1
-static inline
+static __always_inline
 unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap)
 {
 	cpumask_check(start);
@@ -392,7 +396,7 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta
  * Often used to find any cpu but smp_processor_id() in a mask.
  * Return: >= nr_cpu_ids if no cpus set.
  */
-static inline
+static __always_inline
 unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
 {
 	unsigned int i;
@@ -412,7 +416,7 @@ unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
  *
  * Returns >= nr_cpu_ids if no cpus set.
  */
-static inline
+static __always_inline
 unsigned int cpumask_any_and_but(const struct cpumask *mask1,
 				 const struct cpumask *mask2,
 				 unsigned int cpu)
@@ -434,7 +438,8 @@ unsigned int cpumask_any_and_but(const struct cpumask *mask1,
  *
  * Return: >= nr_cpu_ids if such cpu doesn't exist.
  */
-static inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp)
+static __always_inline
+unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp)
 {
 	return find_nth_bit(cpumask_bits(srcp), small_cpumask_bits, cpumask_check(cpu));
 }
@@ -447,7 +452,7 @@ static inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *s
  *
  * Return: >= nr_cpu_ids if such cpu doesn't exist.
  */
-static inline
+static __always_inline
 unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1,
 							const struct cpumask *srcp2)
 {
@@ -463,7 +468,7 @@ unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1,
  *
  * Return: >= nr_cpu_ids if such cpu doesn't exist.
  */
-static inline
+static __always_inline
 unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1,
 							const struct cpumask *srcp2)
 {
@@ -506,12 +511,14 @@ unsigned int cpumask_nth_and_andnot(unsigned int cpu, const struct cpumask *srcp
  * @cpu: cpu number (< nr_cpu_ids)
  * @dstp: the cpumask pointer
  */
-static __always_inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
+static __always_inline
+void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
 {
 	set_bit(cpumask_check(cpu), cpumask_bits(dstp));
 }
 
-static __always_inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
+static __always_inline
+void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
 {
 	__set_bit(cpumask_check(cpu), cpumask_bits(dstp));
 }
@@ -539,7 +546,8 @@ static __always_inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp)
  *
  * Return: true if @cpu is set in @cpumask, else returns false
  */
-static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask)
+static __always_inline
+bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask)
 {
 	return test_bit(cpumask_check(cpu), cpumask_bits((cpumask)));
 }
@@ -553,7 +561,8 @@ static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpum
  *
  * Return: true if @cpu is set in old bitmap of @cpumask, else returns false
  */
-static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask)
+static __always_inline
+bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask)
 {
 	return test_and_set_bit(cpumask_check(cpu), cpumask_bits(cpumask));
 }
@@ -567,7 +576,8 @@ static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cp
  *
  * Return: true if @cpu is set in old bitmap of @cpumask, else returns false
  */
-static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask)
+static __always_inline
+bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask)
 {
 	return test_and_clear_bit(cpumask_check(cpu), cpumask_bits(cpumask));
 }
@@ -576,7 +586,7 @@ static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *
  * cpumask_setall - set all cpus (< nr_cpu_ids) in a cpumask
  * @dstp: the cpumask pointer
  */
-static inline void cpumask_setall(struct cpumask *dstp)
+static __always_inline void cpumask_setall(struct cpumask *dstp)
 {
 	if (small_const_nbits(small_cpumask_bits)) {
 		cpumask_bits(dstp)[0] = BITMAP_LAST_WORD_MASK(nr_cpumask_bits);
@@ -589,7 +599,7 @@ static inline void cpumask_setall(struct cpumask *dstp)
  * cpumask_clear - clear all cpus (< nr_cpu_ids) in a cpumask
  * @dstp: the cpumask pointer
  */
-static inline void cpumask_clear(struct cpumask *dstp)
+static __always_inline void cpumask_clear(struct cpumask *dstp)
 {
 	bitmap_zero(cpumask_bits(dstp), large_cpumask_bits);
 }
@@ -602,9 +612,9 @@ static inline void cpumask_clear(struct cpumask *dstp)
  *
  * Return: false if *@dstp is empty, else returns true
  */
-static inline bool cpumask_and(struct cpumask *dstp,
-			       const struct cpumask *src1p,
-			       const struct cpumask *src2p)
+static __always_inline
+bool cpumask_and(struct cpumask *dstp, const struct cpumask *src1p,
+		 const struct cpumask *src2p)
 {
 	return bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p),
 				       cpumask_bits(src2p), small_cpumask_bits);
@@ -616,8 +626,9 @@ static inline bool cpumask_and(struct cpumask *dstp,
  * @src1p: the first input
  * @src2p: the second input
  */
-static inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p,
-			      const struct cpumask *src2p)
+static __always_inline
+void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p,
+		const struct cpumask *src2p)
 {
 	bitmap_or(cpumask_bits(dstp), cpumask_bits(src1p),
 				      cpumask_bits(src2p), small_cpumask_bits);
@@ -629,9 +640,9 @@ static inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p,
  * @src1p: the first input
  * @src2p: the second input
  */
-static inline void cpumask_xor(struct cpumask *dstp,
-			       const struct cpumask *src1p,
-			       const struct cpumask *src2p)
+static __always_inline
+void cpumask_xor(struct cpumask *dstp, const struct cpumask *src1p,
+		 const struct cpumask *src2p)
 {
 	bitmap_xor(cpumask_bits(dstp), cpumask_bits(src1p),
 				       cpumask_bits(src2p), small_cpumask_bits);
@@ -645,9 +656,9 @@ static inline void cpumask_xor(struct cpumask *dstp,
  *
  * Return: false if *@dstp is empty, else returns true
  */
-static inline bool cpumask_andnot(struct cpumask *dstp,
-				  const struct cpumask *src1p,
-				  const struct cpumask *src2p)
+static __always_inline
+bool cpumask_andnot(struct cpumask *dstp, const struct cpumask *src1p,
+		    const struct cpumask *src2p)
 {
 	return bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p),
 					  cpumask_bits(src2p), small_cpumask_bits);
@@ -660,8 +671,8 @@ static inline bool cpumask_andnot(struct cpumask *dstp,
  *
  * Return: true if the cpumasks are equal, false if not
  */
-static inline bool cpumask_equal(const struct cpumask *src1p,
-				const struct cpumask *src2p)
+static __always_inline
+bool cpumask_equal(const struct cpumask *src1p, const struct cpumask *src2p)
 {
 	return bitmap_equal(cpumask_bits(src1p), cpumask_bits(src2p),
 						 small_cpumask_bits);
@@ -676,9 +687,9 @@ static inline bool cpumask_equal(const struct cpumask *src1p,
  * Return: true if first cpumask ORed with second cpumask == third cpumask,
  *	   otherwise false
  */
-static inline bool cpumask_or_equal(const struct cpumask *src1p,
-				    const struct cpumask *src2p,
-				    const struct cpumask *src3p)
+static __always_inline
+bool cpumask_or_equal(const struct cpumask *src1p, const struct cpumask *src2p,
+		      const struct cpumask *src3p)
 {
 	return bitmap_or_equal(cpumask_bits(src1p), cpumask_bits(src2p),
 			       cpumask_bits(src3p), small_cpumask_bits);
@@ -692,8 +703,8 @@ static inline bool cpumask_or_equal(const struct cpumask *src1p,
  * Return: true if first cpumask ANDed with second cpumask is non-empty,
  *	   otherwise false
  */
-static inline bool cpumask_intersects(const struct cpumask *src1p,
-				     const struct cpumask *src2p)
+static __always_inline
+bool cpumask_intersects(const struct cpumask *src1p, const struct cpumask *src2p)
 {
 	return bitmap_intersects(cpumask_bits(src1p), cpumask_bits(src2p),
 						      small_cpumask_bits);
@@ -706,8 +717,8 @@ static inline bool cpumask_intersects(const struct cpumask *src1p,
  *
  * Return: true if *@src1p is a subset of *@src2p, else returns false
  */
-static inline bool cpumask_subset(const struct cpumask *src1p,
-				 const struct cpumask *src2p)
+static __always_inline
+bool cpumask_subset(const struct cpumask *src1p, const struct cpumask *src2p)
 {
 	return bitmap_subset(cpumask_bits(src1p), cpumask_bits(src2p),
 						  small_cpumask_bits);
@@ -719,7 +730,7 @@ static inline bool cpumask_subset(const struct cpumask *src1p,
  *
  * Return: true if srcp is empty (has no bits set), else false
  */
-static inline bool cpumask_empty(const struct cpumask *srcp)
+static __always_inline bool cpumask_empty(const struct cpumask *srcp)
 {
 	return bitmap_empty(cpumask_bits(srcp), small_cpumask_bits);
 }
@@ -730,7 +741,7 @@ static inline bool cpumask_empty(const struct cpumask *srcp)
  *
  * Return: true if srcp is full (has all bits set), else false
  */
-static inline bool cpumask_full(const struct cpumask *srcp)
+static __always_inline bool cpumask_full(const struct cpumask *srcp)
 {
 	return bitmap_full(cpumask_bits(srcp), nr_cpumask_bits);
 }
@@ -741,7 +752,7 @@ static inline bool cpumask_full(const struct cpumask *srcp)
  *
  * Return: count of bits set in *srcp
  */
-static inline unsigned int cpumask_weight(const struct cpumask *srcp)
+static __always_inline unsigned int cpumask_weight(const struct cpumask *srcp)
 {
 	return bitmap_weight(cpumask_bits(srcp), small_cpumask_bits);
 }
@@ -753,8 +764,8 @@ static inline unsigned int cpumask_weight(const struct cpumask *srcp)
  *
  * Return: count of bits set in both *srcp1 and *srcp2
  */
-static inline unsigned int cpumask_weight_and(const struct cpumask *srcp1,
-						const struct cpumask *srcp2)
+static __always_inline
+unsigned int cpumask_weight_and(const struct cpumask *srcp1, const struct cpumask *srcp2)
 {
 	return bitmap_weight_and(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits);
 }
@@ -766,8 +777,9 @@ static inline unsigned int cpumask_weight_and(const struct cpumask *srcp1,
  *
  * Return: count of bits set in both *srcp1 and *srcp2
  */
-static inline unsigned int cpumask_weight_andnot(const struct cpumask *srcp1,
-						const struct cpumask *srcp2)
+static __always_inline
+unsigned int cpumask_weight_andnot(const struct cpumask *srcp1,
+				   const struct cpumask *srcp2)
 {
 	return bitmap_weight_andnot(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits);
 }
@@ -778,8 +790,8 @@ static inline unsigned int cpumask_weight_andnot(const struct cpumask *srcp1,
  * @srcp: the input to shift
  * @n: the number of bits to shift by
  */
-static inline void cpumask_shift_right(struct cpumask *dstp,
-				       const struct cpumask *srcp, int n)
+static __always_inline
+void cpumask_shift_right(struct cpumask *dstp, const struct cpumask *srcp, int n)
 {
 	bitmap_shift_right(cpumask_bits(dstp), cpumask_bits(srcp), n,
 					       small_cpumask_bits);
@@ -791,8 +803,8 @@ static inline void cpumask_shift_right(struct cpumask *dstp,
  * @srcp: the input to shift
  * @n: the number of bits to shift by
  */
-static inline void cpumask_shift_left(struct cpumask *dstp,
-				      const struct cpumask *srcp, int n)
+static __always_inline
+void cpumask_shift_left(struct cpumask *dstp, const struct cpumask *srcp, int n)
 {
 	bitmap_shift_left(cpumask_bits(dstp), cpumask_bits(srcp), n,
 					      nr_cpumask_bits);
@@ -803,8 +815,8 @@ static inline void cpumask_shift_left(struct cpumask *dstp,
  * @dstp: the result
  * @srcp: the input cpumask
  */
-static inline void cpumask_copy(struct cpumask *dstp,
-				const struct cpumask *srcp)
+static __always_inline
+void cpumask_copy(struct cpumask *dstp, const struct cpumask *srcp)
 {
 	bitmap_copy(cpumask_bits(dstp), cpumask_bits(srcp), large_cpumask_bits);
 }
@@ -840,8 +852,8 @@ static inline void cpumask_copy(struct cpumask *dstp,
  *
  * Return: -errno, or 0 for success.
  */
-static inline int cpumask_parse_user(const char __user *buf, int len,
-				     struct cpumask *dstp)
+static __always_inline
+int cpumask_parse_user(const char __user *buf, int len, struct cpumask *dstp)
 {
 	return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits);
 }
@@ -854,8 +866,8 @@ static inline int cpumask_parse_user(const char __user *buf, int len,
  *
  * Return: -errno, or 0 for success.
  */
-static inline int cpumask_parselist_user(const char __user *buf, int len,
-				     struct cpumask *dstp)
+static __always_inline
+int cpumask_parselist_user(const char __user *buf, int len, struct cpumask *dstp)
 {
 	return bitmap_parselist_user(buf, len, cpumask_bits(dstp),
 				     nr_cpumask_bits);
@@ -868,7 +880,7 @@ static inline int cpumask_parselist_user(const char __user *buf, int len,
  *
  * Return: -errno, or 0 for success.
  */
-static inline int cpumask_parse(const char *buf, struct cpumask *dstp)
+static __always_inline int cpumask_parse(const char *buf, struct cpumask *dstp)
 {
 	return bitmap_parse(buf, UINT_MAX, cpumask_bits(dstp), nr_cpumask_bits);
 }
@@ -880,7 +892,7 @@ static inline int cpumask_parse(const char *buf, struct cpumask *dstp)
  *
  * Return: -errno, or 0 for success.
  */
-static inline int cpulist_parse(const char *buf, struct cpumask *dstp)
+static __always_inline int cpulist_parse(const char *buf, struct cpumask *dstp)
 {
 	return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpumask_bits);
 }
@@ -890,7 +902,7 @@ static inline int cpulist_parse(const char *buf, struct cpumask *dstp)
  *
  * Return: size to allocate for a &struct cpumask in bytes
  */
-static inline unsigned int cpumask_size(void)
+static __always_inline unsigned int cpumask_size(void)
 {
 	return bitmap_size(large_cpumask_bits);
 }
@@ -943,7 +955,7 @@ typedef struct cpumask *cpumask_var_t;
 
 bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node);
 
-static inline
+static __always_inline
 bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
 {
 	return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node);
@@ -961,13 +973,13 @@ bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
  *
  * Return: %true if allocation succeeded, %false if not
  */
-static inline
+static __always_inline
 bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
 {
 	return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE);
 }
 
-static inline
+static __always_inline
 bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
 {
 	return alloc_cpumask_var(mask, flags | __GFP_ZERO);
@@ -977,7 +989,7 @@ void alloc_bootmem_cpumask_var(cpumask_var_t *mask);
 void free_cpumask_var(cpumask_var_t mask);
 void free_bootmem_cpumask_var(cpumask_var_t mask);
 
-static inline bool cpumask_available(cpumask_var_t mask)
+static __always_inline bool cpumask_available(cpumask_var_t mask)
 {
 	return mask != NULL;
 }
@@ -988,43 +1000,43 @@ typedef struct cpumask cpumask_var_t[1];
 #define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x)
 #define __cpumask_var_read_mostly
 
-static inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
+static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
 {
 	return true;
 }
 
-static inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags,
+static __always_inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags,
 					  int node)
 {
 	return true;
 }
 
-static inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
+static __always_inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
 {
 	cpumask_clear(*mask);
 	return true;
 }
 
-static inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags,
+static __always_inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags,
 					  int node)
 {
 	cpumask_clear(*mask);
 	return true;
 }
 
-static inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask)
+static __always_inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask)
 {
 }
 
-static inline void free_cpumask_var(cpumask_var_t mask)
+static __always_inline void free_cpumask_var(cpumask_var_t mask)
 {
 }
 
-static inline void free_bootmem_cpumask_var(cpumask_var_t mask)
+static __always_inline void free_bootmem_cpumask_var(cpumask_var_t mask)
 {
 }
 
-static inline bool cpumask_available(cpumask_var_t mask)
+static __always_inline bool cpumask_available(cpumask_var_t mask)
 {
 	return true;
 }
@@ -1083,7 +1095,7 @@ void set_cpu_online(unsigned int cpu, bool online);
 	((struct cpumask *)(1 ? (bitmap)				\
 			    : (void *)sizeof(__check_is_bitmap(bitmap))))
 
-static inline int __check_is_bitmap(const unsigned long *bitmap)
+static __always_inline int __check_is_bitmap(const unsigned long *bitmap)
 {
 	return 1;
 }
@@ -1098,7 +1110,7 @@ static inline int __check_is_bitmap(const unsigned long *bitmap)
 extern const unsigned long
 	cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)];
 
-static inline const struct cpumask *get_cpu_mask(unsigned int cpu)
+static __always_inline const struct cpumask *get_cpu_mask(unsigned int cpu)
 {
 	const unsigned long *p = cpu_bit_bitmap[1 + cpu % BITS_PER_LONG];
 	p -= cpu / BITS_PER_LONG;
@@ -1124,27 +1136,27 @@ static __always_inline unsigned int num_online_cpus(void)
 #define num_present_cpus()	cpumask_weight(cpu_present_mask)
 #define num_active_cpus()	cpumask_weight(cpu_active_mask)
 
-static inline bool cpu_online(unsigned int cpu)
+static __always_inline bool cpu_online(unsigned int cpu)
 {
 	return cpumask_test_cpu(cpu, cpu_online_mask);
 }
 
-static inline bool cpu_possible(unsigned int cpu)
+static __always_inline bool cpu_possible(unsigned int cpu)
 {
 	return cpumask_test_cpu(cpu, cpu_possible_mask);
 }
 
-static inline bool cpu_present(unsigned int cpu)
+static __always_inline bool cpu_present(unsigned int cpu)
 {
 	return cpumask_test_cpu(cpu, cpu_present_mask);
 }
 
-static inline bool cpu_active(unsigned int cpu)
+static __always_inline bool cpu_active(unsigned int cpu)
 {
 	return cpumask_test_cpu(cpu, cpu_active_mask);
 }
 
-static inline bool cpu_dying(unsigned int cpu)
+static __always_inline bool cpu_dying(unsigned int cpu)
 {
 	return cpumask_test_cpu(cpu, cpu_dying_mask);
 }
@@ -1156,27 +1168,27 @@ static inline bool cpu_dying(unsigned int cpu)
 #define num_present_cpus()	1U
 #define num_active_cpus()	1U
 
-static inline bool cpu_online(unsigned int cpu)
+static __always_inline bool cpu_online(unsigned int cpu)
 {
 	return cpu == 0;
 }
 
-static inline bool cpu_possible(unsigned int cpu)
+static __always_inline bool cpu_possible(unsigned int cpu)
 {
 	return cpu == 0;
 }
 
-static inline bool cpu_present(unsigned int cpu)
+static __always_inline bool cpu_present(unsigned int cpu)
 {
 	return cpu == 0;
 }
 
-static inline bool cpu_active(unsigned int cpu)
+static __always_inline bool cpu_active(unsigned int cpu)
 {
 	return cpu == 0;
 }
 
-static inline bool cpu_dying(unsigned int cpu)
+static __always_inline bool cpu_dying(unsigned int cpu)
 {
 	return false;
 }
@@ -1210,7 +1222,7 @@ static inline bool cpu_dying(unsigned int cpu)
  * Return: the length of the (null-terminated) @buf string, zero if
  * nothing is copied.
  */
-static inline ssize_t
+static __always_inline ssize_t
 cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask)
 {
 	return bitmap_print_to_pagebuf(list, buf, cpumask_bits(mask),
@@ -1233,9 +1245,9 @@ cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask)
  * Return: the length of how many bytes have been copied, excluding
  * terminating '\0'.
  */
-static inline ssize_t
-cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask,
-		loff_t off, size_t count)
+static __always_inline
+ssize_t cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask,
+				    loff_t off, size_t count)
 {
 	return bitmap_print_bitmask_to_buf(buf, cpumask_bits(mask),
 				   nr_cpu_ids, off, count) - 1;
@@ -1255,9 +1267,9 @@ cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask,
  * Return: the length of how many bytes have been copied, excluding
  * terminating '\0'.
  */
-static inline ssize_t
-cpumap_print_list_to_buf(char *buf, const struct cpumask *mask,
-		loff_t off, size_t count)
+static __always_inline
+ssize_t cpumap_print_list_to_buf(char *buf, const struct cpumask *mask,
+				 loff_t off, size_t count)
 {
 	return bitmap_print_list_to_buf(buf, cpumask_bits(mask),
 				   nr_cpu_ids, off, count) - 1;

From 3dbd1c52b61c3ba39c15606a6c11264cc73ad6e6 Mon Sep 17 00:00:00 2001
From: Valentine Sinitsyn <valesini@yandex-team.ru>
Date: Mon, 25 Sep 2023 11:40:12 +0300
Subject: [PATCH 050/236] kernfs: sysfs: support custom llseek method for sysfs
 entries

commit 0fedefd4c4e33dd24f726b13b5d7c143e2b483be upstream.

As of now, seeking in sysfs files is handled by generic_file_llseek().
There are situations where one may want to customize seeking logic:

- Many sysfs entries are fixed files while generic_file_llseek() accepts
  past-the-end positions. Not only being useless by itself, this
  also means a bug in userspace code will trigger not at lseek(), but at
  some later point making debugging harder.
- generic_file_llseek() relies on f_mapping->host to get the file size
  which might not be correct for all sysfs entries.
  See commit 636b21b50152 ("PCI: Revoke mappings like devmem") as an example.

Implement llseek method to override this behavior at sysfs attribute
level. The method is optional, and if it is absent,
generic_file_llseek() is called to preserve backwards compatibility.

Signed-off-by: Valentine Sinitsyn <valesini@yandex-team.ru>
Link: https://lore.kernel.org/r/20230925084013.309399-1-valesini@yandex-team.ru
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 fs/kernfs/file.c       | 29 ++++++++++++++++++++++++++++-
 fs/sysfs/file.c        | 13 +++++++++++++
 include/linux/kernfs.h |  1 +
 include/linux/sysfs.h  |  2 ++
 4 files changed, 44 insertions(+), 1 deletion(-)

diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index 257ba5398387b..3be2ccb62993b 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -924,6 +924,33 @@ static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait)
 	return ret;
 }
 
+static loff_t kernfs_fop_llseek(struct file *file, loff_t offset, int whence)
+{
+	struct kernfs_open_file *of = kernfs_of(file);
+	const struct kernfs_ops *ops;
+	loff_t ret;
+
+	/*
+	 * @of->mutex nests outside active ref and is primarily to ensure that
+	 * the ops aren't called concurrently for the same open file.
+	 */
+	mutex_lock(&of->mutex);
+	if (!kernfs_get_active(of->kn)) {
+		mutex_unlock(&of->mutex);
+		return -ENODEV;
+	}
+
+	ops = kernfs_ops(of->kn);
+	if (ops->llseek)
+		ret = ops->llseek(of, offset, whence);
+	else
+		ret = generic_file_llseek(file, offset, whence);
+
+	kernfs_put_active(of->kn);
+	mutex_unlock(&of->mutex);
+	return ret;
+}
+
 static void kernfs_notify_workfn(struct work_struct *work)
 {
 	struct kernfs_node *kn;
@@ -1026,7 +1053,7 @@ EXPORT_SYMBOL_GPL(kernfs_notify);
 const struct file_operations kernfs_file_fops = {
 	.read_iter	= kernfs_fop_read_iter,
 	.write_iter	= kernfs_fop_write_iter,
-	.llseek		= generic_file_llseek,
+	.llseek		= kernfs_fop_llseek,
 	.mmap		= kernfs_fop_mmap,
 	.open		= kernfs_fop_open,
 	.release	= kernfs_fop_release,
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index 833dd3f5a3f20..0939c75dee674 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -171,6 +171,18 @@ static int sysfs_kf_bin_mmap(struct kernfs_open_file *of,
 	return battr->mmap(of->file, kobj, battr, vma);
 }
 
+static loff_t sysfs_kf_bin_llseek(struct kernfs_open_file *of, loff_t offset,
+				  int whence)
+{
+	struct bin_attribute *battr = of->kn->priv;
+	struct kobject *kobj = of->kn->parent->priv;
+
+	if (battr->llseek)
+		return battr->llseek(of->file, kobj, battr, offset, whence);
+	else
+		return generic_file_llseek(of->file, offset, whence);
+}
+
 static int sysfs_kf_bin_open(struct kernfs_open_file *of)
 {
 	struct bin_attribute *battr = of->kn->priv;
@@ -253,6 +265,7 @@ static const struct kernfs_ops sysfs_bin_kfops_mmap = {
 	.write		= sysfs_kf_bin_write,
 	.mmap		= sysfs_kf_bin_mmap,
 	.open		= sysfs_kf_bin_open,
+	.llseek		= sysfs_kf_bin_llseek,
 };
 
 int sysfs_add_file_mode_ns(struct kernfs_node *parent,
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 5a952d00ea159..e857a150babc6 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -318,6 +318,7 @@ struct kernfs_ops {
 			 struct poll_table_struct *pt);
 
 	int (*mmap)(struct kernfs_open_file *of, struct vm_area_struct *vma);
+	loff_t (*llseek)(struct kernfs_open_file *of, loff_t offset, int whence);
 };
 
 /*
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index 2bbf0057322f5..a42642b277dd0 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -220,6 +220,8 @@ struct bin_attribute {
 			char *, loff_t, size_t);
 	ssize_t (*write)(struct file *, struct kobject *, struct bin_attribute *,
 			 char *, loff_t, size_t);
+	loff_t (*llseek)(struct file *, struct kobject *, struct bin_attribute *,
+			 loff_t, int);
 	int (*mmap)(struct file *, struct kobject *, struct bin_attribute *attr,
 		    struct vm_area_struct *vma);
 };

From b9bec3c1a5b80ed12bb3ef4653c09388ee8fb30f Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 12 Dec 2023 13:17:38 -0800
Subject: [PATCH 051/236] kernfs: Convert kernfs_walk_ns() from strlcpy() to
 strscpy()

commit 792e04768efbf2a1b49a7162a9fa06c1fa584723 upstream.

strlcpy() reads the entire source buffer first. This read may exceed
the destination size limit. This is both inefficient and can lead
to linear read overflows if a source string is not NUL-terminated[1].
Additionally, it returns the size of the source string, not the
resulting size of the destination string. In an effort to remove strlcpy()
completely[2], replace strlcpy() here with strscpy().

Link: https://www.kernel.org/doc/html/latest/process/deprecated.html#strlcpy [1]
Link: https://github.com/KSPP/linux/issues/89 [2]
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Azeem Shaikh <azeemshaikh38@gmail.com>
Link: https://lore.kernel.org/r/20231116192127.1558276-1-keescook@chromium.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20231212211741.164376-1-keescook@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 fs/kernfs/dir.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index f6e2a4523f7e6..6b2d8ca1656ba 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -871,16 +871,16 @@ static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent,
 					  const unsigned char *path,
 					  const void *ns)
 {
-	size_t len;
+	ssize_t len;
 	char *p, *name;
 
 	lockdep_assert_held_read(&kernfs_root(parent)->kernfs_rwsem);
 
 	spin_lock_irq(&kernfs_pr_cont_lock);
 
-	len = strlcpy(kernfs_pr_cont_buf, path, sizeof(kernfs_pr_cont_buf));
+	len = strscpy(kernfs_pr_cont_buf, path, sizeof(kernfs_pr_cont_buf));
 
-	if (len >= sizeof(kernfs_pr_cont_buf)) {
+	if (len < 0) {
 		spin_unlock_irq(&kernfs_pr_cont_lock);
 		return NULL;
 	}

From 0324bf2a96142f8df60ad287431d036bc8cf4dca Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 12 Dec 2023 13:17:39 -0800
Subject: [PATCH 052/236] kernfs: Convert kernfs_name_locked() from strlcpy()
 to strscpy()

commit 5b56bf5cdb8b7c989055fe4d73fe3f409427d1d5 upstream.

strlcpy() reads the entire source buffer first. This read may exceed
the destination size limit. This is both inefficient and can lead
to linear read overflows if a source string is not NUL-terminated[1].
Additionally, it returns the size of the source string, not the
resulting size of the destination string. In an effort to remove strlcpy()
completely[2], replace strlcpy() here with strscpy().

Nothing actually checks the return value coming from kernfs_name_locked(),
so this has no impact on error paths. The caller hierarchy is:

kernfs_name_locked()
        kernfs_name()
                pr_cont_kernfs_name()
                        return value ignored
                cgroup_name()
                        current_css_set_cg_links_read()
                                return value ignored
                        print_page_owner_memcg()
                                return value ignored

Link: https://www.kernel.org/doc/html/latest/process/deprecated.html#strlcpy [1]
Link: https://github.com/KSPP/linux/issues/89 [2]
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Azeem Shaikh <azeemshaikh38@gmail.com>
Link: https://lore.kernel.org/r/20231116192127.1558276-2-keescook@chromium.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20231212211741.164376-2-keescook@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 fs/kernfs/dir.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 6b2d8ca1656ba..5dc90a498e75d 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -54,9 +54,9 @@ static bool kernfs_lockdep(struct kernfs_node *kn)
 static int kernfs_name_locked(struct kernfs_node *kn, char *buf, size_t buflen)
 {
 	if (!kn)
-		return strlcpy(buf, "(null)", buflen);
+		return strscpy(buf, "(null)", buflen);
 
-	return strlcpy(buf, kn->parent ? kn->name : "/", buflen);
+	return strscpy(buf, kn->parent ? kn->name : "/", buflen);
 }
 
 /* kernfs_node_depth - compute depth from @from to @to */
@@ -184,12 +184,12 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to,
  * @buflen: size of @buf
  *
  * Copies the name of @kn into @buf of @buflen bytes.  The behavior is
- * similar to strlcpy().
+ * similar to strscpy().
  *
  * Fills buffer with "(null)" if @kn is %NULL.
  *
- * Return: the length of @kn's name and if @buf isn't long enough,
- * it's filled up to @buflen-1 and nul terminated.
+ * Return: the resulting length of @buf. If @buf isn't long enough,
+ * it's filled up to @buflen-1 and nul terminated, and returns -E2BIG.
  *
  * This function can be called from any context.
  */

From db0adf46f000d26432f6be0490ff4f09a61534f3 Mon Sep 17 00:00:00 2001
From: Li zeming <zeming@nfschina.com>
Date: Mon, 15 Apr 2024 18:20:09 +0800
Subject: [PATCH 053/236] =?UTF-8?q?kernfs:=20mount:=20Remove=20unnecessary?=
 =?UTF-8?q?=20=E2=80=98NULL=E2=80=99=20values=20from=20knparent?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 75cde4e37a14bdb8554c44cbc22354fc10fdf127 upstream.

knparent is assigned first, so it does not need to initialize the
assignment.

Signed-off-by: Li zeming <zeming@nfschina.com>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20240415102009.9926-1-zeming@nfschina.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 fs/kernfs/mount.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index c4bf26142eec9..050c3004a5f61 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -208,7 +208,7 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
 				  struct super_block *sb)
 {
 	struct dentry *dentry;
-	struct kernfs_node *knparent = NULL;
+	struct kernfs_node *knparent;
 
 	BUG_ON(sb->s_op != &kernfs_sops);
 

From 2b832506e3833804916ce8efd0b2d31d325b2510 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 13 Feb 2025 15:50:18 +0100
Subject: [PATCH 054/236] kernfs: Acquire kernfs_rwsem in
 kernfs_notify_workfn().

commit 400188ae361a9d9a72a47a6cedaf2d2efcc84aa8 upstream.

kernfs_notify_workfn() dereferences kernfs_node::name and passes it
later to fsnotify(). If the node is renamed then the previously observed
name pointer becomes invalid.

Acquire kernfs_root::kernfs_rwsem to block renames of the node.

Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://lore.kernel.org/r/20250213145023.2820193-2-bigeasy@linutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 fs/kernfs/file.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index 3be2ccb62993b..9a57b4fa837d2 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -972,6 +972,7 @@ static void kernfs_notify_workfn(struct work_struct *work)
 	/* kick fsnotify */
 
 	down_read(&root->kernfs_supers_rwsem);
+	down_read(&root->kernfs_rwsem);
 	list_for_each_entry(info, &kernfs_root(kn)->supers, node) {
 		struct kernfs_node *parent;
 		struct inode *p_inode = NULL;
@@ -1008,6 +1009,7 @@ static void kernfs_notify_workfn(struct work_struct *work)
 		iput(inode);
 	}
 
+	up_read(&root->kernfs_rwsem);
 	up_read(&root->kernfs_supers_rwsem);
 	kernfs_put(kn);
 	goto repeat;

From a8a971bb825258bd08d84d60c99dac8593a57829 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 13 Feb 2025 15:50:19 +0100
Subject: [PATCH 055/236] kernfs: Acquire kernfs_rwsem in
 kernfs_get_parent_dentry().

commit 122ab92dee80582c39740609a627198dd5b6b595 upstream.

kernfs_get_parent_dentry() passes kernfs_node::parent to
kernfs_get_inode().

Acquire kernfs_root::kernfs_rwsem to ensure kernfs_node::parent isn't
replaced during the operation.

Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://lore.kernel.org/r/20250213145023.2820193-3-bigeasy@linutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 fs/kernfs/mount.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 050c3004a5f61..10696cda583d7 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -147,7 +147,9 @@ static struct dentry *kernfs_fh_to_parent(struct super_block *sb,
 static struct dentry *kernfs_get_parent_dentry(struct dentry *child)
 {
 	struct kernfs_node *kn = kernfs_dentry_node(child);
+	struct kernfs_root *root = kernfs_root(kn);
 
+	guard(rwsem_read)(&root->kernfs_rwsem);
 	return d_obtain_alias(kernfs_get_inode(child->d_sb, kn->parent));
 }
 

From 726315017ae94443861c0567da570948663bd61b Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 13 Feb 2025 15:50:20 +0100
Subject: [PATCH 056/236] kernfs: Acquire kernfs_rwsem in kernfs_node_dentry().

commit 5b2fabf7fe8f745ff214ff003e6067b64f172271 upstream.

kernfs_node_dentry() passes kernfs_node::name to
lookup_positive_unlocked().

Acquire kernfs_root::kernfs_rwsem to ensure the node is not renamed
during the operation.

Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://lore.kernel.org/r/20250213145023.2820193-4-bigeasy@linutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 fs/kernfs/mount.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 10696cda583d7..bcf06703831b5 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -211,6 +211,7 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
 {
 	struct dentry *dentry;
 	struct kernfs_node *knparent;
+	struct kernfs_root *root;
 
 	BUG_ON(sb->s_op != &kernfs_sops);
 
@@ -220,6 +221,9 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
 	if (!kn->parent)
 		return dentry;
 
+	root = kernfs_root(kn);
+	guard(rwsem_read)(&root->kernfs_rwsem);
+
 	knparent = find_next_ancestor(kn, NULL);
 	if (WARN_ON(!knparent)) {
 		dput(dentry);

From 32684a454ea4601bb358f8492c8d41e1543168b3 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 13 Feb 2025 15:50:22 +0100
Subject: [PATCH 057/236] kernfs: Use RCU to access kernfs_node::parent.

commit 633488947ef66b194377411322dc9e12aab79b65 upstream.

kernfs_rename_lock is used to obtain stable kernfs_node::{name|parent}
pointer. This is a preparation to access kernfs_node::parent under RCU
and ensure that the pointer remains stable under the RCU lifetime
guarantees.

For a complete path, as it is done in kernfs_path_from_node(), the
kernfs_rename_lock is still required in order to obtain a stable parent
relationship while computing the relevant node depth. This must not
change while the nodes are inspected in order to build the path.
If the kernfs user never moves the nodes (changes the parent) then the
kernfs_rename_lock is not required and the RCU guarantees are
sufficient. This "restriction" can be set with
KERNFS_ROOT_INVARIANT_PARENT. Otherwise the lock is required.

Rename kernfs_node::parent to kernfs_node::__parent to denote the RCU
access and use RCU accessor while accessing the node.
Make cgroup use KERNFS_ROOT_INVARIANT_PARENT since the parent here can
not change.

Acked-by: Tejun Heo <tj@kernel.org>
Cc: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://lore.kernel.org/r/20250213145023.2820193-6-bigeasy@linutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c        | 65 +++++++++----
 fs/kernfs/dir.c                               | 96 ++++++++++++-------
 fs/kernfs/kernfs-internal.h                   | 32 ++++++-
 fs/kernfs/mount.c                             | 10 +-
 fs/kernfs/symlink.c                           | 23 ++---
 fs/sysfs/file.c                               | 24 +++--
 include/linux/kernfs.h                        | 10 +-
 kernel/cgroup/cgroup-v1.c                     |  2 +-
 kernel/cgroup/cgroup.c                        | 24 ++++-
 .../selftests/bpf/progs/profiler.inc.h        |  2 +-
 10 files changed, 195 insertions(+), 93 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index c6274d40b217c..3232a32f1e08e 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -984,10 +984,20 @@ static int rdt_last_cmd_status_show(struct kernfs_open_file *of,
 	return 0;
 }
 
+static void *rdt_kn_parent_priv(struct kernfs_node *kn)
+{
+	/*
+	 * The parent pointer is only valid within RCU section since it can be
+	 * replaced.
+	 */
+	guard(rcu)();
+	return rcu_dereference(kn->__parent)->priv;
+}
+
 static int rdt_num_closids_show(struct kernfs_open_file *of,
 				struct seq_file *seq, void *v)
 {
-	struct resctrl_schema *s = of->kn->parent->priv;
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
 
 	seq_printf(seq, "%u\n", s->num_closid);
 	return 0;
@@ -996,7 +1006,7 @@ static int rdt_num_closids_show(struct kernfs_open_file *of,
 static int rdt_default_ctrl_show(struct kernfs_open_file *of,
 			     struct seq_file *seq, void *v)
 {
-	struct resctrl_schema *s = of->kn->parent->priv;
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
 	struct rdt_resource *r = s->res;
 
 	seq_printf(seq, "%x\n", resctrl_get_default_ctrl(r));
@@ -1006,7 +1016,7 @@ static int rdt_default_ctrl_show(struct kernfs_open_file *of,
 static int rdt_min_cbm_bits_show(struct kernfs_open_file *of,
 			     struct seq_file *seq, void *v)
 {
-	struct resctrl_schema *s = of->kn->parent->priv;
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
 	struct rdt_resource *r = s->res;
 
 	seq_printf(seq, "%u\n", r->cache.min_cbm_bits);
@@ -1016,7 +1026,7 @@ static int rdt_min_cbm_bits_show(struct kernfs_open_file *of,
 static int rdt_shareable_bits_show(struct kernfs_open_file *of,
 				   struct seq_file *seq, void *v)
 {
-	struct resctrl_schema *s = of->kn->parent->priv;
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
 	struct rdt_resource *r = s->res;
 
 	seq_printf(seq, "%x\n", r->cache.shareable_bits);
@@ -1040,7 +1050,7 @@ static int rdt_shareable_bits_show(struct kernfs_open_file *of,
 static int rdt_bit_usage_show(struct kernfs_open_file *of,
 			      struct seq_file *seq, void *v)
 {
-	struct resctrl_schema *s = of->kn->parent->priv;
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
 	/*
 	 * Use unsigned long even though only 32 bits are used to ensure
 	 * test_bit() is used safely.
@@ -1122,7 +1132,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
 static int rdt_min_bw_show(struct kernfs_open_file *of,
 			     struct seq_file *seq, void *v)
 {
-	struct resctrl_schema *s = of->kn->parent->priv;
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
 	struct rdt_resource *r = s->res;
 
 	seq_printf(seq, "%u\n", r->membw.min_bw);
@@ -1132,7 +1142,7 @@ static int rdt_min_bw_show(struct kernfs_open_file *of,
 static int rdt_num_rmids_show(struct kernfs_open_file *of,
 			      struct seq_file *seq, void *v)
 {
-	struct rdt_resource *r = of->kn->parent->priv;
+	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
 
 	seq_printf(seq, "%d\n", r->num_rmid);
 
@@ -1142,7 +1152,7 @@ static int rdt_num_rmids_show(struct kernfs_open_file *of,
 static int rdt_mon_features_show(struct kernfs_open_file *of,
 				 struct seq_file *seq, void *v)
 {
-	struct rdt_resource *r = of->kn->parent->priv;
+	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
 	struct mon_evt *mevt;
 
 	list_for_each_entry(mevt, &r->evt_list, list) {
@@ -1157,7 +1167,7 @@ static int rdt_mon_features_show(struct kernfs_open_file *of,
 static int rdt_bw_gran_show(struct kernfs_open_file *of,
 			     struct seq_file *seq, void *v)
 {
-	struct resctrl_schema *s = of->kn->parent->priv;
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
 	struct rdt_resource *r = s->res;
 
 	seq_printf(seq, "%u\n", r->membw.bw_gran);
@@ -1167,7 +1177,7 @@ static int rdt_bw_gran_show(struct kernfs_open_file *of,
 static int rdt_delay_linear_show(struct kernfs_open_file *of,
 			     struct seq_file *seq, void *v)
 {
-	struct resctrl_schema *s = of->kn->parent->priv;
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
 	struct rdt_resource *r = s->res;
 
 	seq_printf(seq, "%u\n", r->membw.delay_linear);
@@ -1185,7 +1195,7 @@ static int max_threshold_occ_show(struct kernfs_open_file *of,
 static int rdt_thread_throttle_mode_show(struct kernfs_open_file *of,
 					 struct seq_file *seq, void *v)
 {
-	struct resctrl_schema *s = of->kn->parent->priv;
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
 	struct rdt_resource *r = s->res;
 
 	switch (r->membw.throttle_mode) {
@@ -1259,7 +1269,7 @@ static enum resctrl_conf_type resctrl_peer_type(enum resctrl_conf_type my_type)
 static int rdt_has_sparse_bitmasks_show(struct kernfs_open_file *of,
 					struct seq_file *seq, void *v)
 {
-	struct resctrl_schema *s = of->kn->parent->priv;
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
 	struct rdt_resource *r = s->res;
 
 	seq_printf(seq, "%u\n", r->cache.arch_has_sparse_bitmasks);
@@ -1670,7 +1680,7 @@ static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid
 static int mbm_total_bytes_config_show(struct kernfs_open_file *of,
 				       struct seq_file *seq, void *v)
 {
-	struct rdt_resource *r = of->kn->parent->priv;
+	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
 
 	mbm_config_show(seq, r, QOS_L3_MBM_TOTAL_EVENT_ID);
 
@@ -1680,7 +1690,7 @@ static int mbm_total_bytes_config_show(struct kernfs_open_file *of,
 static int mbm_local_bytes_config_show(struct kernfs_open_file *of,
 				       struct seq_file *seq, void *v)
 {
-	struct rdt_resource *r = of->kn->parent->priv;
+	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
 
 	mbm_config_show(seq, r, QOS_L3_MBM_LOCAL_EVENT_ID);
 
@@ -1787,7 +1797,7 @@ static ssize_t mbm_total_bytes_config_write(struct kernfs_open_file *of,
 					    char *buf, size_t nbytes,
 					    loff_t off)
 {
-	struct rdt_resource *r = of->kn->parent->priv;
+	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
 	int ret;
 
 	/* Valid input requires a trailing newline */
@@ -1813,7 +1823,7 @@ static ssize_t mbm_local_bytes_config_write(struct kernfs_open_file *of,
 					    char *buf, size_t nbytes,
 					    loff_t off)
 {
-	struct rdt_resource *r = of->kn->parent->priv;
+	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
 	int ret;
 
 	/* Valid input requires a trailing newline */
@@ -2513,12 +2523,13 @@ static struct rdtgroup *kernfs_to_rdtgroup(struct kernfs_node *kn)
 		 * resource. "info" and its subdirectories don't
 		 * have rdtgroup structures, so return NULL here.
 		 */
-		if (kn == kn_info || kn->parent == kn_info)
+		if (kn == kn_info ||
+		    rcu_access_pointer(kn->__parent) == kn_info)
 			return NULL;
 		else
 			return kn->priv;
 	} else {
-		return kn->parent->priv;
+		return rdt_kn_parent_priv(kn);
 	}
 }
 
@@ -3867,9 +3878,18 @@ static int rdtgroup_rmdir_ctrl(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask)
 	return 0;
 }
 
+static struct kernfs_node *rdt_kn_parent(struct kernfs_node *kn)
+{
+	/*
+	 * Valid within the RCU section it was obtained or while rdtgroup_mutex
+	 * is held.
+	 */
+	return rcu_dereference_check(kn->__parent, lockdep_is_held(&rdtgroup_mutex));
+}
+
 static int rdtgroup_rmdir(struct kernfs_node *kn)
 {
-	struct kernfs_node *parent_kn = kn->parent;
+	struct kernfs_node *parent_kn;
 	struct rdtgroup *rdtgrp;
 	cpumask_var_t tmpmask;
 	int ret = 0;
@@ -3882,6 +3902,7 @@ static int rdtgroup_rmdir(struct kernfs_node *kn)
 		ret = -EPERM;
 		goto out;
 	}
+	parent_kn = rdt_kn_parent(kn);
 
 	/*
 	 * If the rdtgroup is a ctrl_mon group and parent directory
@@ -3950,6 +3971,7 @@ static void mongrp_reparent(struct rdtgroup *rdtgrp,
 static int rdtgroup_rename(struct kernfs_node *kn,
 			   struct kernfs_node *new_parent, const char *new_name)
 {
+	struct kernfs_node *kn_parent;
 	struct rdtgroup *new_prdtgrp;
 	struct rdtgroup *rdtgrp;
 	cpumask_var_t tmpmask;
@@ -3984,8 +4006,9 @@ static int rdtgroup_rename(struct kernfs_node *kn,
 		goto out;
 	}
 
-	if (rdtgrp->type != RDTMON_GROUP || !kn->parent ||
-	    !is_mon_groups(kn->parent, kn->name)) {
+	kn_parent = rdt_kn_parent(kn);
+	if (rdtgrp->type != RDTMON_GROUP || !kn_parent ||
+	    !is_mon_groups(kn_parent, kn->name)) {
 		rdt_last_cmd_puts("Source must be a MON group\n");
 		ret = -EPERM;
 		goto out;
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 5dc90a498e75d..72dc34252a0b7 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -17,7 +17,7 @@
 
 #include "kernfs-internal.h"
 
-static DEFINE_RWLOCK(kernfs_rename_lock);	/* kn->parent and ->name */
+DEFINE_RWLOCK(kernfs_rename_lock);	/* kn->parent and ->name */
 /*
  * Don't use rename_lock to piggy back on pr_cont_buf. We don't want to
  * call pr_cont() while holding rename_lock. Because sometimes pr_cont()
@@ -56,7 +56,7 @@ static int kernfs_name_locked(struct kernfs_node *kn, char *buf, size_t buflen)
 	if (!kn)
 		return strscpy(buf, "(null)", buflen);
 
-	return strscpy(buf, kn->parent ? kn->name : "/", buflen);
+	return strscpy(buf, rcu_access_pointer(kn->__parent) ? kn->name : "/", buflen);
 }
 
 /* kernfs_node_depth - compute depth from @from to @to */
@@ -64,9 +64,9 @@ static size_t kernfs_depth(struct kernfs_node *from, struct kernfs_node *to)
 {
 	size_t depth = 0;
 
-	while (to->parent && to != from) {
+	while (rcu_dereference(to->__parent) && to != from) {
 		depth++;
-		to = to->parent;
+		to = rcu_dereference(to->__parent);
 	}
 	return depth;
 }
@@ -84,18 +84,18 @@ static struct kernfs_node *kernfs_common_ancestor(struct kernfs_node *a,
 	db = kernfs_depth(rb->kn, b);
 
 	while (da > db) {
-		a = a->parent;
+		a = rcu_dereference(a->__parent);
 		da--;
 	}
 	while (db > da) {
-		b = b->parent;
+		b = rcu_dereference(b->__parent);
 		db--;
 	}
 
 	/* worst case b and a will be the same at root */
 	while (b != a) {
-		b = b->parent;
-		a = a->parent;
+		b = rcu_dereference(b->__parent);
+		a = rcu_dereference(a->__parent);
 	}
 
 	return a;
@@ -168,8 +168,9 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to,
 
 	/* Calculate how many bytes we need for the rest */
 	for (i = depth_to - 1; i >= 0; i--) {
+
 		for (kn = kn_to, j = 0; j < i; j++)
-			kn = kn->parent;
+			kn = rcu_dereference(kn->__parent);
 
 		len += scnprintf(buf + len, buflen - len, "/%s", kn->name);
 	}
@@ -226,6 +227,7 @@ int kernfs_path_from_node(struct kernfs_node *to, struct kernfs_node *from,
 	unsigned long flags;
 	int ret;
 
+	guard(rcu)();
 	read_lock_irqsave(&kernfs_rename_lock, flags);
 	ret = kernfs_path_from_node_locked(to, from, buf, buflen);
 	read_unlock_irqrestore(&kernfs_rename_lock, flags);
@@ -295,7 +297,7 @@ struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn)
 	unsigned long flags;
 
 	read_lock_irqsave(&kernfs_rename_lock, flags);
-	parent = kn->parent;
+	parent = kernfs_parent(kn);
 	kernfs_get(parent);
 	read_unlock_irqrestore(&kernfs_rename_lock, flags);
 
@@ -360,8 +362,12 @@ static int kernfs_sd_compare(const struct kernfs_node *left,
  */
 static int kernfs_link_sibling(struct kernfs_node *kn)
 {
-	struct rb_node **node = &kn->parent->dir.children.rb_node;
 	struct rb_node *parent = NULL;
+	struct kernfs_node *kn_parent;
+	struct rb_node **node;
+
+	kn_parent = kernfs_parent(kn);
+	node = &kn_parent->dir.children.rb_node;
 
 	while (*node) {
 		struct kernfs_node *pos;
@@ -380,13 +386,13 @@ static int kernfs_link_sibling(struct kernfs_node *kn)
 
 	/* add new node and rebalance the tree */
 	rb_link_node(&kn->rb, parent, node);
-	rb_insert_color(&kn->rb, &kn->parent->dir.children);
+	rb_insert_color(&kn->rb, &kn_parent->dir.children);
 
 	/* successfully added, account subdir number */
 	down_write(&kernfs_root(kn)->kernfs_iattr_rwsem);
 	if (kernfs_type(kn) == KERNFS_DIR)
-		kn->parent->dir.subdirs++;
-	kernfs_inc_rev(kn->parent);
+		kn_parent->dir.subdirs++;
+	kernfs_inc_rev(kn_parent);
 	up_write(&kernfs_root(kn)->kernfs_iattr_rwsem);
 
 	return 0;
@@ -407,16 +413,19 @@ static int kernfs_link_sibling(struct kernfs_node *kn)
  */
 static bool kernfs_unlink_sibling(struct kernfs_node *kn)
 {
+	struct kernfs_node *kn_parent;
+
 	if (RB_EMPTY_NODE(&kn->rb))
 		return false;
 
+	kn_parent = kernfs_parent(kn);
 	down_write(&kernfs_root(kn)->kernfs_iattr_rwsem);
 	if (kernfs_type(kn) == KERNFS_DIR)
-		kn->parent->dir.subdirs--;
-	kernfs_inc_rev(kn->parent);
+		kn_parent->dir.subdirs--;
+	kernfs_inc_rev(kn_parent);
 	up_write(&kernfs_root(kn)->kernfs_iattr_rwsem);
 
-	rb_erase(&kn->rb, &kn->parent->dir.children);
+	rb_erase(&kn->rb, &kn_parent->dir.children);
 	RB_CLEAR_NODE(&kn->rb);
 	return true;
 }
@@ -562,7 +571,7 @@ void kernfs_put(struct kernfs_node *kn)
 	 * Moving/renaming is always done while holding reference.
 	 * kn->parent won't change beneath us.
 	 */
-	parent = kn->parent;
+	parent = kernfs_parent(kn);
 
 	WARN_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS,
 		  "kernfs_put: %s/%s: released with incorrect active_ref %d\n",
@@ -701,7 +710,7 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
 			       name, mode, uid, gid, flags);
 	if (kn) {
 		kernfs_get(parent);
-		kn->parent = parent;
+		rcu_assign_pointer(kn->__parent, parent);
 	}
 	return kn;
 }
@@ -769,13 +778,14 @@ struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root,
  */
 int kernfs_add_one(struct kernfs_node *kn)
 {
-	struct kernfs_node *parent = kn->parent;
-	struct kernfs_root *root = kernfs_root(parent);
+	struct kernfs_root *root = kernfs_root(kn);
 	struct kernfs_iattrs *ps_iattr;
+	struct kernfs_node *parent;
 	bool has_ns;
 	int ret;
 
 	down_write(&root->kernfs_rwsem);
+	parent = kernfs_parent(kn);
 
 	ret = -EINVAL;
 	has_ns = kernfs_ns_enabled(parent);
@@ -949,6 +959,11 @@ struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent,
 	return kn;
 }
 
+unsigned int kernfs_root_flags(struct kernfs_node *kn)
+{
+	return kernfs_root(kn)->flags;
+}
+
 /**
  * kernfs_create_root - create a new kernfs hierarchy
  * @scops: optional syscall operations for the hierarchy
@@ -1111,7 +1126,7 @@ struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent,
 
 static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags)
 {
-	struct kernfs_node *kn;
+	struct kernfs_node *kn, *parent;
 	struct kernfs_root *root;
 
 	if (flags & LOOKUP_RCU)
@@ -1162,8 +1177,9 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags)
 	if (!kernfs_active(kn))
 		goto out_bad;
 
+	parent = kernfs_parent(kn);
 	/* The kernfs node has been moved? */
-	if (kernfs_dentry_node(dentry->d_parent) != kn->parent)
+	if (kernfs_dentry_node(dentry->d_parent) != parent)
 		goto out_bad;
 
 	/* The kernfs node has been renamed */
@@ -1171,7 +1187,7 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags)
 		goto out_bad;
 
 	/* The kernfs node has been moved to a different namespace */
-	if (kn->parent && kernfs_ns_enabled(kn->parent) &&
+	if (parent && kernfs_ns_enabled(parent) &&
 	    kernfs_info(dentry->d_sb)->ns != kn->ns)
 		goto out_bad;
 
@@ -1364,7 +1380,7 @@ static struct kernfs_node *kernfs_next_descendant_post(struct kernfs_node *pos,
 		return kernfs_leftmost_descendant(rb_to_kn(rbn));
 
 	/* no sibling left, visit parent */
-	return pos->parent;
+	return kernfs_parent(pos);
 }
 
 static void kernfs_activate_one(struct kernfs_node *kn)
@@ -1376,7 +1392,7 @@ static void kernfs_activate_one(struct kernfs_node *kn)
 	if (kernfs_active(kn) || (kn->flags & (KERNFS_HIDDEN | KERNFS_REMOVING)))
 		return;
 
-	WARN_ON_ONCE(kn->parent && RB_EMPTY_NODE(&kn->rb));
+	WARN_ON_ONCE(rcu_access_pointer(kn->__parent) && RB_EMPTY_NODE(&kn->rb));
 	WARN_ON_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS);
 
 	atomic_sub(KN_DEACTIVATED_BIAS, &kn->active);
@@ -1446,7 +1462,7 @@ void kernfs_show(struct kernfs_node *kn, bool show)
 
 static void __kernfs_remove(struct kernfs_node *kn)
 {
-	struct kernfs_node *pos;
+	struct kernfs_node *pos, *parent;
 
 	/* Short-circuit if non-root @kn has already finished removal. */
 	if (!kn)
@@ -1458,7 +1474,7 @@ static void __kernfs_remove(struct kernfs_node *kn)
 	 * This is for kernfs_remove_self() which plays with active ref
 	 * after removal.
 	 */
-	if (kn->parent && RB_EMPTY_NODE(&kn->rb))
+	if (kernfs_parent(kn) && RB_EMPTY_NODE(&kn->rb))
 		return;
 
 	pr_debug("kernfs %s: removing\n", kn->name);
@@ -1484,14 +1500,14 @@ static void __kernfs_remove(struct kernfs_node *kn)
 		kernfs_get(pos);
 
 		kernfs_drain(pos);
-
+		parent = kernfs_parent(pos);
 		/*
 		 * kernfs_unlink_sibling() succeeds once per node.  Use it
 		 * to decide who's responsible for cleanups.
 		 */
-		if (!pos->parent || kernfs_unlink_sibling(pos)) {
+		if (!parent || kernfs_unlink_sibling(pos)) {
 			struct kernfs_iattrs *ps_iattr =
-				pos->parent ? pos->parent->iattr : NULL;
+				parent ? parent->iattr : NULL;
 
 			/* update timestamps on the parent */
 			down_write(&kernfs_root(kn)->kernfs_iattr_rwsem);
@@ -1722,7 +1738,7 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
 	int error;
 
 	/* can't move or rename root */
-	if (!kn->parent)
+	if (!rcu_access_pointer(kn->__parent))
 		return -EINVAL;
 
 	root = kernfs_root(kn);
@@ -1733,8 +1749,15 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
 	    (new_parent->flags & KERNFS_EMPTY_DIR))
 		goto out;
 
+	old_parent = kernfs_parent(kn);
+	if (root->flags & KERNFS_ROOT_INVARIANT_PARENT) {
+		error = -EINVAL;
+		if (WARN_ON_ONCE(old_parent != new_parent))
+			goto out;
+	}
+
 	error = 0;
-	if ((kn->parent == new_parent) && (kn->ns == new_ns) &&
+	if ((old_parent == new_parent) && (kn->ns == new_ns) &&
 	    (strcmp(kn->name, new_name) == 0))
 		goto out;	/* nothing to rename */
 
@@ -1761,8 +1784,8 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
 	/* rename_lock protects ->parent and ->name accessors */
 	write_lock_irq(&kernfs_rename_lock);
 
-	old_parent = kn->parent;
-	kn->parent = new_parent;
+	old_parent = kernfs_parent(kn);
+	rcu_assign_pointer(kn->__parent, new_parent);
 
 	kn->ns = new_ns;
 	if (new_name) {
@@ -1795,7 +1818,8 @@ static struct kernfs_node *kernfs_dir_pos(const void *ns,
 {
 	if (pos) {
 		int valid = kernfs_active(pos) &&
-			pos->parent == parent && hash == pos->hash;
+			rcu_access_pointer(pos->__parent) == parent &&
+			hash == pos->hash;
 		kernfs_put(pos);
 		if (!valid)
 			pos = NULL;
diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h
index 210dac7e9ee25..dbcf24c30a3df 100644
--- a/fs/kernfs/kernfs-internal.h
+++ b/fs/kernfs/kernfs-internal.h
@@ -19,6 +19,8 @@
 #include <linux/kernfs.h>
 #include <linux/fs_context.h>
 
+extern rwlock_t kernfs_rename_lock;
+
 struct kernfs_iattrs {
 	kuid_t			ia_uid;
 	kgid_t			ia_gid;
@@ -64,11 +66,14 @@ struct kernfs_root {
  *
  * Return: the kernfs_root @kn belongs to.
  */
-static inline struct kernfs_root *kernfs_root(struct kernfs_node *kn)
+static inline struct kernfs_root *kernfs_root(const struct kernfs_node *kn)
 {
+	const struct kernfs_node *knp;
 	/* if parent exists, it's always a dir; otherwise, @sd is a dir */
-	if (kn->parent)
-		kn = kn->parent;
+	guard(rcu)();
+	knp = rcu_dereference(kn->__parent);
+	if (knp)
+		kn = knp;
 	return kn->dir.root;
 }
 
@@ -97,6 +102,27 @@ struct kernfs_super_info {
 };
 #define kernfs_info(SB) ((struct kernfs_super_info *)(SB->s_fs_info))
 
+static inline bool kernfs_root_is_locked(const struct kernfs_node *kn)
+{
+	return lockdep_is_held(&kernfs_root(kn)->kernfs_rwsem);
+}
+
+static inline struct kernfs_node *kernfs_parent(const struct kernfs_node *kn)
+{
+	/*
+	 * The kernfs_node::__parent remains valid within a RCU section. The kn
+	 * can be reparented (and renamed) which changes the entry. This can be
+	 * avoided by locking kernfs_root::kernfs_rwsem or kernfs_rename_lock.
+	 * Both locks can be used to obtain a reference on __parent. Once the
+	 * reference count reaches 0 then the node is about to be freed
+	 * and can not be renamed (or become a different parent) anymore.
+	 */
+	return rcu_dereference_check(kn->__parent,
+				     kernfs_root_is_locked(kn) ||
+				     lockdep_is_held(&kernfs_rename_lock) ||
+				     !atomic_read(&kn->count));
+}
+
 static inline struct kernfs_node *kernfs_dentry_node(struct dentry *dentry)
 {
 	if (d_really_is_negative(dentry))
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index bcf06703831b5..3f0dbd64d0bae 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -150,7 +150,7 @@ static struct dentry *kernfs_get_parent_dentry(struct dentry *child)
 	struct kernfs_root *root = kernfs_root(kn);
 
 	guard(rwsem_read)(&root->kernfs_rwsem);
-	return d_obtain_alias(kernfs_get_inode(child->d_sb, kn->parent));
+	return d_obtain_alias(kernfs_get_inode(child->d_sb, kernfs_parent(kn)));
 }
 
 static const struct export_operations kernfs_export_ops = {
@@ -190,10 +190,10 @@ static struct kernfs_node *find_next_ancestor(struct kernfs_node *child,
 		return NULL;
 	}
 
-	while (child->parent != parent) {
-		if (!child->parent)
+	while (kernfs_parent(child) != parent) {
+		child = kernfs_parent(child);
+		if (!child)
 			return NULL;
-		child = child->parent;
 	}
 
 	return child;
@@ -218,7 +218,7 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
 	dentry = dget(sb->s_root);
 
 	/* Check if this is the root kernfs_node */
-	if (!kn->parent)
+	if (!rcu_access_pointer(kn->__parent))
 		return dentry;
 
 	root = kernfs_root(kn);
diff --git a/fs/kernfs/symlink.c b/fs/kernfs/symlink.c
index 45371a70caa71..05c62ca93c53d 100644
--- a/fs/kernfs/symlink.c
+++ b/fs/kernfs/symlink.c
@@ -62,10 +62,10 @@ static int kernfs_get_target_path(struct kernfs_node *parent,
 
 	/* go up to the root, stop at the base */
 	base = parent;
-	while (base->parent) {
-		kn = target->parent;
-		while (kn->parent && base != kn)
-			kn = kn->parent;
+	while (kernfs_parent(base)) {
+		kn = kernfs_parent(target);
+		while (kernfs_parent(kn) && base != kn)
+			kn = kernfs_parent(kn);
 
 		if (base == kn)
 			break;
@@ -75,14 +75,14 @@ static int kernfs_get_target_path(struct kernfs_node *parent,
 
 		strcpy(s, "../");
 		s += 3;
-		base = base->parent;
+		base = kernfs_parent(base);
 	}
 
 	/* determine end of target string for reverse fillup */
 	kn = target;
-	while (kn->parent && kn != base) {
+	while (kernfs_parent(kn) && kn != base) {
 		len += strlen(kn->name) + 1;
-		kn = kn->parent;
+		kn = kernfs_parent(kn);
 	}
 
 	/* check limits */
@@ -94,7 +94,7 @@ static int kernfs_get_target_path(struct kernfs_node *parent,
 
 	/* reverse fillup of target string from target to base */
 	kn = target;
-	while (kn->parent && kn != base) {
+	while (kernfs_parent(kn) && kn != base) {
 		int slen = strlen(kn->name);
 
 		len -= slen;
@@ -102,7 +102,7 @@ static int kernfs_get_target_path(struct kernfs_node *parent,
 		if (len)
 			s[--len] = '/';
 
-		kn = kn->parent;
+		kn = kernfs_parent(kn);
 	}
 
 	return 0;
@@ -111,12 +111,13 @@ static int kernfs_get_target_path(struct kernfs_node *parent,
 static int kernfs_getlink(struct inode *inode, char *path)
 {
 	struct kernfs_node *kn = inode->i_private;
-	struct kernfs_node *parent = kn->parent;
+	struct kernfs_node *parent;
 	struct kernfs_node *target = kn->symlink.target_kn;
-	struct kernfs_root *root = kernfs_root(parent);
+	struct kernfs_root *root = kernfs_root(kn);
 	int error;
 
 	down_read(&root->kernfs_rwsem);
+	parent = kernfs_parent(kn);
 	error = kernfs_get_target_path(parent, target, path);
 	up_read(&root->kernfs_rwsem);
 
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index 0939c75dee674..a8ab89946776d 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -19,13 +19,19 @@
 
 #include "sysfs.h"
 
+static struct kobject *sysfs_file_kobj(struct kernfs_node *kn)
+{
+	guard(rcu)();
+	return rcu_dereference(kn->__parent)->priv;
+}
+
 /*
  * Determine ktype->sysfs_ops for the given kernfs_node.  This function
  * must be called while holding an active reference.
  */
 static const struct sysfs_ops *sysfs_file_ops(struct kernfs_node *kn)
 {
-	struct kobject *kobj = kn->parent->priv;
+	struct kobject *kobj = sysfs_file_kobj(kn);
 
 	if (kn->flags & KERNFS_LOCKDEP)
 		lockdep_assert_held(kn);
@@ -40,7 +46,7 @@ static const struct sysfs_ops *sysfs_file_ops(struct kernfs_node *kn)
 static int sysfs_kf_seq_show(struct seq_file *sf, void *v)
 {
 	struct kernfs_open_file *of = sf->private;
-	struct kobject *kobj = of->kn->parent->priv;
+	struct kobject *kobj = sysfs_file_kobj(of->kn);
 	const struct sysfs_ops *ops = sysfs_file_ops(of->kn);
 	ssize_t count;
 	char *buf;
@@ -78,7 +84,7 @@ static ssize_t sysfs_kf_bin_read(struct kernfs_open_file *of, char *buf,
 				 size_t count, loff_t pos)
 {
 	struct bin_attribute *battr = of->kn->priv;
-	struct kobject *kobj = of->kn->parent->priv;
+	struct kobject *kobj = sysfs_file_kobj(of->kn);
 	loff_t size = file_inode(of->file)->i_size;
 
 	if (!count)
@@ -102,7 +108,7 @@ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf,
 			     size_t count, loff_t pos)
 {
 	const struct sysfs_ops *ops = sysfs_file_ops(of->kn);
-	struct kobject *kobj = of->kn->parent->priv;
+	struct kobject *kobj = sysfs_file_kobj(of->kn);
 	ssize_t len;
 
 	/*
@@ -132,7 +138,7 @@ static ssize_t sysfs_kf_write(struct kernfs_open_file *of, char *buf,
 			      size_t count, loff_t pos)
 {
 	const struct sysfs_ops *ops = sysfs_file_ops(of->kn);
-	struct kobject *kobj = of->kn->parent->priv;
+	struct kobject *kobj = sysfs_file_kobj(of->kn);
 
 	if (!count)
 		return 0;
@@ -145,7 +151,7 @@ static ssize_t sysfs_kf_bin_write(struct kernfs_open_file *of, char *buf,
 				  size_t count, loff_t pos)
 {
 	struct bin_attribute *battr = of->kn->priv;
-	struct kobject *kobj = of->kn->parent->priv;
+	struct kobject *kobj = sysfs_file_kobj(of->kn);
 	loff_t size = file_inode(of->file)->i_size;
 
 	if (size) {
@@ -166,7 +172,7 @@ static int sysfs_kf_bin_mmap(struct kernfs_open_file *of,
 			     struct vm_area_struct *vma)
 {
 	struct bin_attribute *battr = of->kn->priv;
-	struct kobject *kobj = of->kn->parent->priv;
+	struct kobject *kobj = sysfs_file_kobj(of->kn);
 
 	return battr->mmap(of->file, kobj, battr, vma);
 }
@@ -175,7 +181,7 @@ static loff_t sysfs_kf_bin_llseek(struct kernfs_open_file *of, loff_t offset,
 				  int whence)
 {
 	struct bin_attribute *battr = of->kn->priv;
-	struct kobject *kobj = of->kn->parent->priv;
+	struct kobject *kobj = sysfs_file_kobj(of->kn);
 
 	if (battr->llseek)
 		return battr->llseek(of->file, kobj, battr, offset, whence);
@@ -486,7 +492,7 @@ EXPORT_SYMBOL_GPL(sysfs_break_active_protection);
  */
 void sysfs_unbreak_active_protection(struct kernfs_node *kn)
 {
-	struct kobject *kobj = kn->parent->priv;
+	struct kobject *kobj = sysfs_file_kobj(kn);
 
 	kernfs_unbreak_active_protection(kn);
 	kernfs_put(kn);
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index e857a150babc6..22f271272b9ae 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -147,6 +147,11 @@ enum kernfs_root_flag {
 	 * Support user xattrs to be written to nodes rooted at this root.
 	 */
 	KERNFS_ROOT_SUPPORT_USER_XATTR		= 0x0008,
+
+	/*
+	 * Renames must not change the parent node.
+	 */
+	KERNFS_ROOT_INVARIANT_PARENT		= 0x0010,
 };
 
 /* type-specific structures for kernfs_node union members */
@@ -199,8 +204,8 @@ struct kernfs_node {
 	 * never moved to a different parent, it is safe to access the
 	 * parent directly.
 	 */
-	struct kernfs_node	*parent;
 	const char		*name;
+	struct kernfs_node	__rcu *__parent;
 
 	struct rb_node		rb;
 
@@ -416,6 +421,7 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
 struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops,
 				       unsigned int flags, void *priv);
 void kernfs_destroy_root(struct kernfs_root *root);
+unsigned int kernfs_root_flags(struct kernfs_node *kn);
 
 struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent,
 					 const char *name, umode_t mode,
@@ -514,6 +520,8 @@ kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags,
 { return ERR_PTR(-ENOSYS); }
 
 static inline void kernfs_destroy_root(struct kernfs_root *root) { }
+static inline unsigned int kernfs_root_flags(struct kernfs_node *kn)
+{ return 0; }
 
 static inline struct kernfs_node *
 kernfs_create_dir_ns(struct kernfs_node *parent, const char *name,
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 2588543c8e4ae..bab4c6b408ef4 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -836,7 +836,7 @@ static int cgroup1_rename(struct kernfs_node *kn, struct kernfs_node *new_parent
 
 	if (kernfs_type(kn) != KERNFS_DIR)
 		return -ENOTDIR;
-	if (kn->parent != new_parent)
+	if (rcu_access_pointer(kn->__parent) != new_parent)
 		return -EIO;
 
 	/*
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 9c980cae478eb..fbd0fc56c70f9 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -654,9 +654,22 @@ int cgroup_task_count(const struct cgroup *cgrp)
 	return count;
 }
 
+static struct cgroup *kn_priv(struct kernfs_node *kn)
+{
+	struct kernfs_node *parent;
+	/*
+	 * The parent can not be replaced due to KERNFS_ROOT_INVARIANT_PARENT.
+	 * Therefore it is always safe to dereference this pointer outside of a
+	 * RCU section.
+	 */
+	parent = rcu_dereference_check(kn->__parent,
+				       kernfs_root_flags(kn) & KERNFS_ROOT_INVARIANT_PARENT);
+	return parent->priv;
+}
+
 struct cgroup_subsys_state *of_css(struct kernfs_open_file *of)
 {
-	struct cgroup *cgrp = of->kn->parent->priv;
+	struct cgroup *cgrp = kn_priv(of->kn);
 	struct cftype *cft = of_cft(of);
 
 	/*
@@ -1631,7 +1644,7 @@ void cgroup_kn_unlock(struct kernfs_node *kn)
 	if (kernfs_type(kn) == KERNFS_DIR)
 		cgrp = kn->priv;
 	else
-		cgrp = kn->parent->priv;
+		cgrp = kn_priv(kn);
 
 	cgroup_unlock();
 
@@ -1663,7 +1676,7 @@ struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn, bool drain_offline)
 	if (kernfs_type(kn) == KERNFS_DIR)
 		cgrp = kn->priv;
 	else
-		cgrp = kn->parent->priv;
+		cgrp = kn_priv(kn);
 
 	/*
 	 * We're gonna grab cgroup_mutex which nests outside kernfs
@@ -2101,7 +2114,8 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 	root->kf_root = kernfs_create_root(kf_sops,
 					   KERNFS_ROOT_CREATE_DEACTIVATED |
 					   KERNFS_ROOT_SUPPORT_EXPORTOP |
-					   KERNFS_ROOT_SUPPORT_USER_XATTR,
+					   KERNFS_ROOT_SUPPORT_USER_XATTR |
+					   KERNFS_ROOT_INVARIANT_PARENT,
 					   root_cgrp);
 	if (IS_ERR(root->kf_root)) {
 		ret = PTR_ERR(root->kf_root);
@@ -4076,7 +4090,7 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
 				 size_t nbytes, loff_t off)
 {
 	struct cgroup_file_ctx *ctx = of->priv;
-	struct cgroup *cgrp = of->kn->parent->priv;
+	struct cgroup *cgrp = kn_priv(of->kn);
 	struct cftype *cft = of_cft(of);
 	struct cgroup_subsys_state *css;
 	int ret;
diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h
index f799d87e87002..cf5d64af07cf4 100644
--- a/tools/testing/selftests/bpf/progs/profiler.inc.h
+++ b/tools/testing/selftests/bpf/progs/profiler.inc.h
@@ -225,7 +225,7 @@ static INLINE void* read_full_cgroup_path(struct kernfs_node* cgroup_node,
 			barrier_var(filepart_length);
 			payload += filepart_length;
 		}
-		cgroup_node = BPF_CORE_READ(cgroup_node, parent);
+		cgroup_node = BPF_CORE_READ(cgroup_node, __parent);
 	}
 	return payload;
 }

From 22caefa5062803868096695e8096c250d149cdce Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 13 Feb 2025 15:50:23 +0100
Subject: [PATCH 058/236] kernfs: Use RCU to access kernfs_node::name.

commit 741c10b096bc4dd79cd9f215b6ef173bb953e75c upstream.

Using RCU lifetime rules to access kernfs_node::name can avoid the
trouble with kernfs_rename_lock in kernfs_name() and kernfs_path_from_node()
if the fs was created with KERNFS_ROOT_INVARIANT_PARENT. This is usefull
as it allows to implement kernfs_path_from_node() only with RCU
protection and avoiding kernfs_rename_lock. The lock is only required if
the __parent node can be changed and the function requires an unchanged
hierarchy while it iterates from the node to its parent.
The change is needed to allow the lookup of the node's path
(kernfs_path_from_node()) from context which runs always with disabled
preemption and or interrutps even on PREEMPT_RT. The problem is that
kernfs_rename_lock becomes a sleeping lock on PREEMPT_RT.

I went through all ::name users and added the required access for the lookup
with a few extensions:
- rdtgroup_pseudo_lock_create() drops all locks and then uses the name
  later on. resctrl supports rename with different parents. Here I made
  a temporal copy of the name while it is used outside of the lock.

- kernfs_rename_ns() accepts NULL as new_parent. This simplifies
  sysfs_move_dir_ns() where it can set NULL in order to reuse the current
  name.

- kernfs_rename_ns() is only using kernfs_rename_lock if the parents are
  different. All users use either kernfs_rwsem (for stable path view) or
  just RCU for the lookup. The ::name uses always RCU free.

Use RCU lifetime guarantees to access kernfs_node::name.

Suggested-by: Tejun Heo <tj@kernel.org>
Acked-by: Tejun Heo <tj@kernel.org>
Reported-by: syzbot+6ea37e2e6ffccf41a7e6@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/lkml/67251dc6.050a0220.529b6.015e.GAE@google.com/
Reported-by: Hillf Danton <hdanton@sina.com>
Closes: https://lore.kernel.org/20241102001224.2789-1-hdanton@sina.com
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://lore.kernel.org/r/20250213145023.2820193-7-bigeasy@linutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

 Conflicts:
	fs/kernfs/file.c
[jz: - 6.6 kernel is still using QSTR_INIT while upstream uses QSTR in
       kernfs_notify_workfn()
     - add asm/sections.h header file inclusion because is_kernel_rodata()
       need this. Upstream doesn't need this inclusion because its
       linux/security.h indirectly included asm/sections.h]
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/internal.h    |   5 +
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c |  14 ++-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    |  10 +-
 fs/kernfs/dir.c                           | 115 ++++++++++++----------
 fs/kernfs/file.c                          |   4 +-
 fs/kernfs/kernfs-internal.h               |   5 +
 fs/kernfs/mount.c                         |   5 +-
 fs/kernfs/symlink.c                       |   7 +-
 fs/sysfs/dir.c                            |   2 +-
 include/linux/kernfs.h                    |   4 +-
 security/selinux/hooks.c                  |   7 +-
 11 files changed, 107 insertions(+), 71 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 96ef5260abb23..608a890ac7456 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -406,6 +406,11 @@ static inline struct rdt_hw_resource *resctrl_to_arch_res(struct rdt_resource *r
 
 extern struct mutex rdtgroup_mutex;
 
+static inline const char *rdt_kn_name(const struct kernfs_node *kn)
+{
+	return rcu_dereference_check(kn->name, lockdep_is_held(&rdtgroup_mutex));
+}
+
 extern struct rdt_hw_resource rdt_resources_all[];
 extern struct rdtgroup rdtgroup_default;
 extern struct dentry *debugfs_resctrl;
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index 4781c105d15b5..dd9eefccf30fd 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -52,7 +52,8 @@ static char *pseudo_lock_devnode(const struct device *dev, umode_t *mode)
 	rdtgrp = dev_get_drvdata(dev);
 	if (mode)
 		*mode = 0600;
-	return kasprintf(GFP_KERNEL, "pseudo_lock/%s", rdtgrp->kn->name);
+	guard(mutex)(&rdtgroup_mutex);
+	return kasprintf(GFP_KERNEL, "pseudo_lock/%s", rdt_kn_name(rdtgrp->kn));
 }
 
 static const struct class pseudo_lock_class = {
@@ -1298,6 +1299,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 	struct task_struct *thread;
 	unsigned int new_minor;
 	struct device *dev;
+	char *kn_name __free(kfree) = NULL;
 	int ret;
 
 	ret = pseudo_lock_region_alloc(plr);
@@ -1309,6 +1311,11 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 		ret = -EINVAL;
 		goto out_region;
 	}
+	kn_name = kstrdup(rdt_kn_name(rdtgrp->kn), GFP_KERNEL);
+	if (!kn_name) {
+		ret = -ENOMEM;
+		goto out_cstates;
+	}
 
 	plr->thread_done = 0;
 
@@ -1353,8 +1360,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 	mutex_unlock(&rdtgroup_mutex);
 
 	if (!IS_ERR_OR_NULL(debugfs_resctrl)) {
-		plr->debugfs_dir = debugfs_create_dir(rdtgrp->kn->name,
-						      debugfs_resctrl);
+		plr->debugfs_dir = debugfs_create_dir(kn_name, debugfs_resctrl);
 		if (!IS_ERR_OR_NULL(plr->debugfs_dir))
 			debugfs_create_file("pseudo_lock_measure", 0200,
 					    plr->debugfs_dir, rdtgrp,
@@ -1363,7 +1369,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 
 	dev = device_create(&pseudo_lock_class, NULL,
 			    MKDEV(pseudo_lock_major, new_minor),
-			    rdtgrp, "%s", rdtgrp->kn->name);
+			    rdtgrp, "%s", kn_name);
 
 	mutex_lock(&rdtgroup_mutex);
 
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 3232a32f1e08e..93ec829015f13 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -944,14 +944,14 @@ int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns,
 			continue;
 
 		seq_printf(s, "res:%s%s\n", (rdtg == &rdtgroup_default) ? "/" : "",
-			   rdtg->kn->name);
+			   rdt_kn_name(rdtg->kn));
 		seq_puts(s, "mon:");
 		list_for_each_entry(crg, &rdtg->mon.crdtgrp_list,
 				    mon.crdtgrp_list) {
 			if (!resctrl_arch_match_rmid(tsk, crg->mon.parent->closid,
 						     crg->mon.rmid))
 				continue;
-			seq_printf(s, "%s", crg->kn->name);
+			seq_printf(s, "%s", rdt_kn_name(crg->kn));
 			break;
 		}
 		seq_putc(s, '\n');
@@ -3763,7 +3763,7 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
  */
 static bool is_mon_groups(struct kernfs_node *kn, const char *name)
 {
-	return (!strcmp(kn->name, "mon_groups") &&
+	return (!strcmp(rdt_kn_name(kn), "mon_groups") &&
 		strcmp(name, "mon_groups"));
 }
 
@@ -3920,7 +3920,7 @@ static int rdtgroup_rmdir(struct kernfs_node *kn)
 			ret = rdtgroup_rmdir_ctrl(rdtgrp, tmpmask);
 		}
 	} else if (rdtgrp->type == RDTMON_GROUP &&
-		 is_mon_groups(parent_kn, kn->name)) {
+		 is_mon_groups(parent_kn, rdt_kn_name(kn))) {
 		ret = rdtgroup_rmdir_mon(rdtgrp, tmpmask);
 	} else {
 		ret = -EPERM;
@@ -4008,7 +4008,7 @@ static int rdtgroup_rename(struct kernfs_node *kn,
 
 	kn_parent = rdt_kn_parent(kn);
 	if (rdtgrp->type != RDTMON_GROUP || !kn_parent ||
-	    !is_mon_groups(kn_parent, kn->name)) {
+	    !is_mon_groups(kn_parent, rdt_kn_name(kn))) {
 		rdt_last_cmd_puts("Source must be a MON group\n");
 		ret = -EPERM;
 		goto out;
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 72dc34252a0b7..5f0d7e35463f8 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -15,6 +15,8 @@
 #include <linux/security.h>
 #include <linux/hash.h>
 
+#include <asm/sections.h>
+
 #include "kernfs-internal.h"
 
 DEFINE_RWLOCK(kernfs_rename_lock);	/* kn->parent and ->name */
@@ -51,14 +53,6 @@ static bool kernfs_lockdep(struct kernfs_node *kn)
 #endif
 }
 
-static int kernfs_name_locked(struct kernfs_node *kn, char *buf, size_t buflen)
-{
-	if (!kn)
-		return strscpy(buf, "(null)", buflen);
-
-	return strscpy(buf, rcu_access_pointer(kn->__parent) ? kn->name : "/", buflen);
-}
-
 /* kernfs_node_depth - compute depth from @from to @to */
 static size_t kernfs_depth(struct kernfs_node *from, struct kernfs_node *to)
 {
@@ -168,11 +162,13 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to,
 
 	/* Calculate how many bytes we need for the rest */
 	for (i = depth_to - 1; i >= 0; i--) {
+		const char *name;
 
 		for (kn = kn_to, j = 0; j < i; j++)
 			kn = rcu_dereference(kn->__parent);
 
-		len += scnprintf(buf + len, buflen - len, "/%s", kn->name);
+		name = rcu_dereference(kn->name);
+		len += scnprintf(buf + len, buflen - len, "/%s", name);
 	}
 
 	return len;
@@ -196,13 +192,18 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to,
  */
 int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen)
 {
-	unsigned long flags;
-	int ret;
+	struct kernfs_node *kn_parent;
 
-	read_lock_irqsave(&kernfs_rename_lock, flags);
-	ret = kernfs_name_locked(kn, buf, buflen);
-	read_unlock_irqrestore(&kernfs_rename_lock, flags);
-	return ret;
+	if (!kn)
+		return strscpy(buf, "(null)", buflen);
+
+	guard(rcu)();
+	/*
+	 * KERNFS_ROOT_INVARIANT_PARENT is ignored here. The name is RCU freed and
+	 * the parent is either existing or not.
+	 */
+	kn_parent = rcu_dereference(kn->__parent);
+	return strscpy(buf, kn_parent ? rcu_dereference(kn->name) : "/", buflen);
 }
 
 /**
@@ -224,14 +225,17 @@ int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen)
 int kernfs_path_from_node(struct kernfs_node *to, struct kernfs_node *from,
 			  char *buf, size_t buflen)
 {
-	unsigned long flags;
-	int ret;
+	struct kernfs_root *root;
 
 	guard(rcu)();
-	read_lock_irqsave(&kernfs_rename_lock, flags);
-	ret = kernfs_path_from_node_locked(to, from, buf, buflen);
-	read_unlock_irqrestore(&kernfs_rename_lock, flags);
-	return ret;
+	if (to) {
+		root = kernfs_root(to);
+		if (!(root->flags & KERNFS_ROOT_INVARIANT_PARENT)) {
+			guard(read_lock_irqsave)(&kernfs_rename_lock);
+			return kernfs_path_from_node_locked(to, from, buf, buflen);
+		}
+	}
+	return kernfs_path_from_node_locked(to, from, buf, buflen);
 }
 EXPORT_SYMBOL_GPL(kernfs_path_from_node);
 
@@ -338,13 +342,13 @@ static int kernfs_name_compare(unsigned int hash, const char *name,
 		return -1;
 	if (ns > kn->ns)
 		return 1;
-	return strcmp(name, kn->name);
+	return strcmp(name, kernfs_rcu_name(kn));
 }
 
 static int kernfs_sd_compare(const struct kernfs_node *left,
 			     const struct kernfs_node *right)
 {
-	return kernfs_name_compare(left->hash, left->name, left->ns, right);
+	return kernfs_name_compare(left->hash, kernfs_rcu_name(left), left->ns, right);
 }
 
 /**
@@ -542,7 +546,8 @@ static void kernfs_free_rcu(struct rcu_head *rcu)
 {
 	struct kernfs_node *kn = container_of(rcu, struct kernfs_node, rcu);
 
-	kfree_const(kn->name);
+	/* If the whole node goes away, then name can't be used outside */
+	kfree_const(rcu_access_pointer(kn->name));
 
 	if (kn->iattr) {
 		simple_xattrs_free(&kn->iattr->xattrs, NULL);
@@ -575,7 +580,8 @@ void kernfs_put(struct kernfs_node *kn)
 
 	WARN_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS,
 		  "kernfs_put: %s/%s: released with incorrect active_ref %d\n",
-		  parent ? parent->name : "", kn->name, atomic_read(&kn->active));
+		  parent ? rcu_dereference(parent->name) : "",
+		  rcu_dereference(kn->name), atomic_read(&kn->active));
 
 	if (kernfs_type(kn) == KERNFS_LINK)
 		kernfs_put(kn->symlink.target_kn);
@@ -652,7 +658,7 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
 	atomic_set(&kn->active, KN_DEACTIVATED_BIAS);
 	RB_CLEAR_NODE(&kn->rb);
 
-	kn->name = name;
+	rcu_assign_pointer(kn->name, name);
 	kn->mode = mode;
 	kn->flags = flags;
 
@@ -790,7 +796,8 @@ int kernfs_add_one(struct kernfs_node *kn)
 	ret = -EINVAL;
 	has_ns = kernfs_ns_enabled(parent);
 	if (WARN(has_ns != (bool)kn->ns, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n",
-		 has_ns ? "required" : "invalid", parent->name, kn->name))
+		 has_ns ? "required" : "invalid",
+		 kernfs_rcu_name(parent), kernfs_rcu_name(kn)))
 		goto out_unlock;
 
 	if (kernfs_type(parent) != KERNFS_DIR)
@@ -800,7 +807,7 @@ int kernfs_add_one(struct kernfs_node *kn)
 	if (parent->flags & (KERNFS_REMOVING | KERNFS_EMPTY_DIR))
 		goto out_unlock;
 
-	kn->hash = kernfs_name_hash(kn->name, kn->ns);
+	kn->hash = kernfs_name_hash(kernfs_rcu_name(kn), kn->ns);
 
 	ret = kernfs_link_sibling(kn);
 	if (ret)
@@ -856,7 +863,7 @@ static struct kernfs_node *kernfs_find_ns(struct kernfs_node *parent,
 
 	if (has_ns != (bool)ns) {
 		WARN(1, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n",
-		     has_ns ? "required" : "invalid", parent->name, name);
+		     has_ns ? "required" : "invalid", kernfs_rcu_name(parent), name);
 		return NULL;
 	}
 
@@ -1134,8 +1141,6 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags)
 
 	/* Negative hashed dentry? */
 	if (d_really_is_negative(dentry)) {
-		struct kernfs_node *parent;
-
 		/* If the kernfs parent node has changed discard and
 		 * proceed to ->lookup.
 		 *
@@ -1183,7 +1188,7 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags)
 		goto out_bad;
 
 	/* The kernfs node has been renamed */
-	if (strcmp(dentry->d_name.name, kn->name) != 0)
+	if (strcmp(dentry->d_name.name, kernfs_rcu_name(kn)) != 0)
 		goto out_bad;
 
 	/* The kernfs node has been moved to a different namespace */
@@ -1477,7 +1482,7 @@ static void __kernfs_remove(struct kernfs_node *kn)
 	if (kernfs_parent(kn) && RB_EMPTY_NODE(&kn->rb))
 		return;
 
-	pr_debug("kernfs %s: removing\n", kn->name);
+	pr_debug("kernfs %s: removing\n", kernfs_rcu_name(kn));
 
 	/* prevent new usage by marking all nodes removing and deactivating */
 	pos = NULL;
@@ -1734,7 +1739,7 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
 {
 	struct kernfs_node *old_parent;
 	struct kernfs_root *root;
-	const char *old_name = NULL;
+	const char *old_name;
 	int error;
 
 	/* can't move or rename root */
@@ -1757,8 +1762,11 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
 	}
 
 	error = 0;
+	old_name = kernfs_rcu_name(kn);
+	if (!new_name)
+		new_name = old_name;
 	if ((old_parent == new_parent) && (kn->ns == new_ns) &&
-	    (strcmp(kn->name, new_name) == 0))
+	    (strcmp(old_name, new_name) == 0))
 		goto out;	/* nothing to rename */
 
 	error = -EEXIST;
@@ -1766,7 +1774,7 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
 		goto out;
 
 	/* rename kernfs_node */
-	if (strcmp(kn->name, new_name) != 0) {
+	if (strcmp(old_name, new_name) != 0) {
 		error = -ENOMEM;
 		new_name = kstrdup_const(new_name, GFP_KERNEL);
 		if (!new_name)
@@ -1779,27 +1787,32 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
 	 * Move to the appropriate place in the appropriate directories rbtree.
 	 */
 	kernfs_unlink_sibling(kn);
-	kernfs_get(new_parent);
 
-	/* rename_lock protects ->parent and ->name accessors */
-	write_lock_irq(&kernfs_rename_lock);
+	/* rename_lock protects ->parent accessors */
+	if (old_parent != new_parent) {
+		kernfs_get(new_parent);
+		write_lock_irq(&kernfs_rename_lock);
 
-	old_parent = kernfs_parent(kn);
-	rcu_assign_pointer(kn->__parent, new_parent);
+		rcu_assign_pointer(kn->__parent, new_parent);
 
-	kn->ns = new_ns;
-	if (new_name) {
-		old_name = kn->name;
-		kn->name = new_name;
-	}
+		kn->ns = new_ns;
+		if (new_name)
+			rcu_assign_pointer(kn->name, new_name);
 
-	write_unlock_irq(&kernfs_rename_lock);
+		write_unlock_irq(&kernfs_rename_lock);
+		kernfs_put(old_parent);
+	} else {
+		/* name assignment is RCU protected, parent is the same */
+		kn->ns = new_ns;
+		if (new_name)
+			rcu_assign_pointer(kn->name, new_name);
+	}
 
-	kn->hash = kernfs_name_hash(kn->name, kn->ns);
+	kn->hash = kernfs_name_hash(new_name ?: old_name, kn->ns);
 	kernfs_link_sibling(kn);
 
-	kernfs_put(old_parent);
-	kfree_const(old_name);
+	if (new_name && !is_kernel_rodata((unsigned long)old_name))
+		kfree_rcu_mightsleep(old_name);
 
 	error = 0;
  out:
@@ -1884,7 +1897,7 @@ static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx)
 	for (pos = kernfs_dir_pos(ns, parent, ctx->pos, pos);
 	     pos;
 	     pos = kernfs_dir_next_pos(ns, parent, ctx->pos, pos)) {
-		const char *name = pos->name;
+		const char *name = kernfs_rcu_name(pos);
 		unsigned int type = fs_umode_to_dtype(pos->mode);
 		int len = strlen(name);
 		ino_t ino = kernfs_ino(pos);
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index 9a57b4fa837d2..245cf94f22211 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -976,6 +976,7 @@ static void kernfs_notify_workfn(struct work_struct *work)
 	list_for_each_entry(info, &kernfs_root(kn)->supers, node) {
 		struct kernfs_node *parent;
 		struct inode *p_inode = NULL;
+		const char *kn_name;
 		struct inode *inode;
 		struct qstr name;
 
@@ -989,7 +990,8 @@ static void kernfs_notify_workfn(struct work_struct *work)
 		if (!inode)
 			continue;
 
-		name = (struct qstr)QSTR_INIT(kn->name, strlen(kn->name));
+		kn_name = kernfs_rcu_name(kn);
+		name = (struct qstr)QSTR_INIT(kn_name, strlen(kn_name));
 		parent = kernfs_get_parent(kn);
 		if (parent) {
 			p_inode = ilookup(info->sb, kernfs_ino(parent));
diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h
index dbcf24c30a3df..3de6346e41e5e 100644
--- a/fs/kernfs/kernfs-internal.h
+++ b/fs/kernfs/kernfs-internal.h
@@ -107,6 +107,11 @@ static inline bool kernfs_root_is_locked(const struct kernfs_node *kn)
 	return lockdep_is_held(&kernfs_root(kn)->kernfs_rwsem);
 }
 
+static inline const char *kernfs_rcu_name(const struct kernfs_node *kn)
+{
+	return rcu_dereference_check(kn->name, kernfs_root_is_locked(kn));
+}
+
 static inline struct kernfs_node *kernfs_parent(const struct kernfs_node *kn)
 {
 	/*
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 3f0dbd64d0bae..abbb84eb0210a 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -233,6 +233,7 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
 	do {
 		struct dentry *dtmp;
 		struct kernfs_node *kntmp;
+		const char *name;
 
 		if (kn == knparent)
 			return dentry;
@@ -241,8 +242,8 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
 			dput(dentry);
 			return ERR_PTR(-EINVAL);
 		}
-		dtmp = lookup_positive_unlocked(kntmp->name, dentry,
-					       strlen(kntmp->name));
+		name = rcu_dereference(kntmp->name);
+		dtmp = lookup_positive_unlocked(name, dentry, strlen(name));
 		dput(dentry);
 		if (IS_ERR(dtmp))
 			return dtmp;
diff --git a/fs/kernfs/symlink.c b/fs/kernfs/symlink.c
index 05c62ca93c53d..0bd8a2143723d 100644
--- a/fs/kernfs/symlink.c
+++ b/fs/kernfs/symlink.c
@@ -81,7 +81,7 @@ static int kernfs_get_target_path(struct kernfs_node *parent,
 	/* determine end of target string for reverse fillup */
 	kn = target;
 	while (kernfs_parent(kn) && kn != base) {
-		len += strlen(kn->name) + 1;
+		len += strlen(kernfs_rcu_name(kn)) + 1;
 		kn = kernfs_parent(kn);
 	}
 
@@ -95,10 +95,11 @@ static int kernfs_get_target_path(struct kernfs_node *parent,
 	/* reverse fillup of target string from target to base */
 	kn = target;
 	while (kernfs_parent(kn) && kn != base) {
-		int slen = strlen(kn->name);
+		const char *name = kernfs_rcu_name(kn);
+		int slen = strlen(name);
 
 		len -= slen;
-		memcpy(s + len, kn->name, slen);
+		memcpy(s + len, name, slen);
 		if (len)
 			s[--len] = '/';
 
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index b6b6796e16160..2e7b9cb2788e2 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -123,7 +123,7 @@ int sysfs_move_dir_ns(struct kobject *kobj, struct kobject *new_parent_kobj,
 	new_parent = new_parent_kobj && new_parent_kobj->sd ?
 		new_parent_kobj->sd : sysfs_root_kn;
 
-	return kernfs_rename_ns(kn, new_parent, kn->name, new_ns);
+	return kernfs_rename_ns(kn, new_parent, NULL, new_ns);
 }
 
 /**
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 22f271272b9ae..0264556d2b58f 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -204,8 +204,8 @@ struct kernfs_node {
 	 * never moved to a different parent, it is safe to access the
 	 * parent directly.
 	 */
-	const char		*name;
 	struct kernfs_node	__rcu *__parent;
+	const char		__rcu *name;
 
 	struct rb_node		rb;
 
@@ -400,7 +400,7 @@ static inline bool kernfs_ns_enabled(struct kernfs_node *kn)
 }
 
 int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen);
-int kernfs_path_from_node(struct kernfs_node *root_kn, struct kernfs_node *kn,
+int kernfs_path_from_node(struct kernfs_node *kn_to, struct kernfs_node *kn_from,
 			  char *buf, size_t buflen);
 void pr_cont_kernfs_name(struct kernfs_node *kn);
 void pr_cont_kernfs_path(struct kernfs_node *kn);
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index e82113fc85b5c..757ff227d61d4 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -3591,10 +3591,13 @@ static int selinux_kernfs_init_security(struct kernfs_node *kn_dir,
 		newsid = tsec->create_sid;
 	} else {
 		u16 secclass = inode_mode_to_security_class(kn->mode);
+		const char *kn_name;
 		struct qstr q;
 
-		q.name = kn->name;
-		q.hash_len = hashlen_string(kn_dir, kn->name);
+		/* kn is fresh, can't be renamed, name goes not away */
+		kn_name = rcu_dereference_check(kn->name, true);
+		q.name = kn_name;
+		q.hash_len = hashlen_string(kn_dir, kn_name);
 
 		rc = security_transition_sid(tsec->sid,
 					     parent_sid, secclass, &q,

From 846320f282ab1b5cd9b7f4bebcae56a43226670d Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Fri, 5 Apr 2024 17:56:35 +0300
Subject: [PATCH 059/236] kernfs: annotate different lockdep class for
 of->mutex of writable files

commit 16b52bbee4823b01ab7fe3919373c981a38f3797 upstream.

The writable file /sys/power/resume may call vfs lookup helpers for
arbitrary paths and readonly files can be read by overlayfs from vfs
helpers when sysfs is a lower layer of overalyfs.

To avoid a lockdep warning of circular dependency between overlayfs
inode lock and kernfs of->mutex, use a different lockdep class for
writable and readonly kernfs files.

Reported-by: syzbot+9a5b0ced8b1bfb238b56@syzkaller.appspotmail.com
Fixes: 0fedefd4c4e3 ("kernfs: sysfs: support custom llseek method for sysfs entries")
Suggested-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 fs/kernfs/file.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index 245cf94f22211..6a67650244aa2 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -703,11 +703,18 @@ static int kernfs_fop_open(struct inode *inode, struct file *file)
 	 * each file a separate locking class.  Let's differentiate on
 	 * whether the file has mmap or not for now.
 	 *
-	 * Both paths of the branch look the same.  They're supposed to
+	 * For similar reasons, writable and readonly files are given different
+	 * lockdep key, because the writable file /sys/power/resume may call vfs
+	 * lookup helpers for arbitrary paths and readonly files can be read by
+	 * overlayfs from vfs helpers when sysfs is a lower layer of overalyfs.
+	 *
+	 * All three cases look the same.  They're supposed to
 	 * look that way and give @of->mutex different static lockdep keys.
 	 */
 	if (has_mmap)
 		mutex_init(&of->mutex);
+	else if (file->f_mode & FMODE_WRITE)
+		mutex_init(&of->mutex);
 	else
 		mutex_init(&of->mutex);
 

From c4bc8fa96989b1df9efaa7bb4b584a476cf94cfc Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Tue, 18 Feb 2025 17:39:38 +0100
Subject: [PATCH 060/236] kernfs: Drop kernfs_rwsem while invoking
 lookup_positive_unlocked().

commit 6ef5b6fae304091593956be59065c0c8633ad9e8 upstream.

syzbot reported two warnings:
- kernfs_node::name was accessed outside of a RCU section so it created
  warning. The kernfs_rwsem was held so it was okay but it wasn't seen.

- While kernfs_rwsem was held invoked lookup_positive_unlocked()->
  kernfs_dop_revalidate() which acquired kernfs_rwsem.

kernfs_rwsem was both acquired as a read lock so it can be acquired
twice. However if a writer acquires the lock after the first reader then
neither the writer nor the second reader can obtain the lock so it
deadlocks.

The reason for the lock is to ensure that kernfs_node::name remain
stable during lookup_positive_unlocked()'s invocation. The function can
not be invoked within a RCU section because it may sleep.

Make a temporary copy of the kernfs_node::name under the lock so
GFP_KERNEL can be used and use this instead.

Reported-by: syzbot+ecccecbc636b455f9084@syzkaller.appspotmail.com
Fixes: 5b2fabf7fe8f ("kernfs: Acquire kernfs_rwsem in kernfs_node_dentry().")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20250218163938.xmvjlJ0K@linutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 fs/kernfs/mount.c | 33 ++++++++++++++++++++++++---------
 1 file changed, 24 insertions(+), 9 deletions(-)

diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index abbb84eb0210a..1e5a5e3326a8f 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -222,12 +222,19 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
 		return dentry;
 
 	root = kernfs_root(kn);
-	guard(rwsem_read)(&root->kernfs_rwsem);
-
-	knparent = find_next_ancestor(kn, NULL);
-	if (WARN_ON(!knparent)) {
-		dput(dentry);
+	/*
+	 * As long as kn is valid, its parent can not vanish. This is cgroup's
+	 * kn so it not have its parent replaced. Therefore it is safe to use
+	 * the ancestor node outside of the RCU or locked section.
+	 */
+	if (WARN_ON_ONCE(!(root->flags & KERNFS_ROOT_INVARIANT_PARENT)))
 		return ERR_PTR(-EINVAL);
+	scoped_guard(rcu) {
+		knparent = find_next_ancestor(kn, NULL);
+		if (WARN_ON(!knparent)) {
+			dput(dentry);
+			return ERR_PTR(-EINVAL);
+		}
 	}
 
 	do {
@@ -237,14 +244,22 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
 
 		if (kn == knparent)
 			return dentry;
-		kntmp = find_next_ancestor(kn, knparent);
-		if (WARN_ON(!kntmp)) {
+
+		scoped_guard(rwsem_read, &root->kernfs_rwsem) {
+			kntmp = find_next_ancestor(kn, knparent);
+			if (WARN_ON(!kntmp)) {
+				dput(dentry);
+				return ERR_PTR(-EINVAL);
+			}
+			name = kstrdup(kernfs_rcu_name(kntmp), GFP_KERNEL);
+		}
+		if (!name) {
 			dput(dentry);
-			return ERR_PTR(-EINVAL);
+			return ERR_PTR(-ENOMEM);
 		}
-		name = rcu_dereference(kntmp->name);
 		dtmp = lookup_positive_unlocked(name, dentry, strlen(name));
 		dput(dentry);
+		kfree(name);
 		if (IS_ERR(dtmp))
 			return dtmp;
 		knparent = kntmp;

From 11ff798e060d662e7d94cc383f113951d3ded5e2 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Fri, 21 Feb 2025 09:42:32 +0100
Subject: [PATCH 061/236] kernfs: Move dput() outside of the RCU section.

commit c5020c5be9d266f66fa5ba3286f0e8d2d2265970 upstream.

Al Viro pointed out that dput() might sleep and must not be invoked
within an RCU section.

Keep only find_next_ancestor() winthin the RCU section.
Correct the wording in the comment.

Fixes: 6ef5b6fae3040 ("kernfs: Drop kernfs_rwsem while invoking lookup_positive_unlocked().")
Reported-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://lore.kernel.org/r/20250221084232.xksA_IQ4@linutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 fs/kernfs/mount.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 1e5a5e3326a8f..385f6e25f3b42 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -224,17 +224,17 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
 	root = kernfs_root(kn);
 	/*
 	 * As long as kn is valid, its parent can not vanish. This is cgroup's
-	 * kn so it not have its parent replaced. Therefore it is safe to use
+	 * kn so it can't have its parent replaced. Therefore it is safe to use
 	 * the ancestor node outside of the RCU or locked section.
 	 */
 	if (WARN_ON_ONCE(!(root->flags & KERNFS_ROOT_INVARIANT_PARENT)))
 		return ERR_PTR(-EINVAL);
 	scoped_guard(rcu) {
 		knparent = find_next_ancestor(kn, NULL);
-		if (WARN_ON(!knparent)) {
-			dput(dentry);
-			return ERR_PTR(-EINVAL);
-		}
+	}
+	if (WARN_ON(!knparent)) {
+		dput(dentry);
+		return ERR_PTR(-EINVAL);
 	}
 
 	do {

From d243967e269d3428950699d2682af8899f377ae1 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Mon, 7 Apr 2025 13:46:37 +0100
Subject: [PATCH 062/236] x86/resctrl: Fix rdtgroup_mkdir()'s unlocked use of
 kernfs_node::name

commit 45c2e30bbd64d75559b99f3a5c455129a7a34b06 upstream.

Since

  741c10b096bc ("kernfs: Use RCU to access kernfs_node::name.")

a helper rdt_kn_name() that checks that rdtgroup_mutex is held has been used
for all accesses to the kernfs node name.

rdtgroup_mkdir() uses the name to determine if a valid monitor group is being
created by checking the parent name is "mon_groups". This is done without
holding rdtgroup_mutex, and now triggers the following warning:

  | WARNING: suspicious RCU usage
  | 6.15.0-rc1 #4465 Tainted: G            E
  | -----------------------------
  | arch/x86/kernel/cpu/resctrl/internal.h:408 suspicious rcu_dereference_check() usage!
  [...]
  | Call Trace:
  |  <TASK>
  |  dump_stack_lvl
  |  lockdep_rcu_suspicious.cold
  |  is_mon_groups
  |  rdtgroup_mkdir
  |  kernfs_iop_mkdir
  |  vfs_mkdir
  |  do_mkdirat
  |  __x64_sys_mkdir
  |  do_syscall_64
  |  entry_SYSCALL_64_after_hwframe

Creating a control or monitor group calls mkdir_rdt_prepare(), which uses
rdtgroup_kn_lock_live() to take the rdtgroup_mutex.

To avoid taking and dropping the lock, move the check for the monitor group
name and position into mkdir_rdt_prepare() so that it occurs under
rdtgroup_mutex. Hoist is_mon_groups() earlier in the file.

  [ bp: Massage. ]

Fixes: 741c10b096bc ("kernfs: Use RCU to access kernfs_node::name.")
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250407124637.2433230-1-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 48 +++++++++++++++-----------
 1 file changed, 27 insertions(+), 21 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 93ec829015f13..cc4a54145c83d 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -3553,6 +3553,22 @@ static void mkdir_rdt_prepare_rmid_free(struct rdtgroup *rgrp)
 		free_rmid(rgrp->closid, rgrp->mon.rmid);
 }
 
+/*
+ * We allow creating mon groups only with in a directory called "mon_groups"
+ * which is present in every ctrl_mon group. Check if this is a valid
+ * "mon_groups" directory.
+ *
+ * 1. The directory should be named "mon_groups".
+ * 2. The mon group itself should "not" be named "mon_groups".
+ *   This makes sure "mon_groups" directory always has a ctrl_mon group
+ *   as parent.
+ */
+static bool is_mon_groups(struct kernfs_node *kn, const char *name)
+{
+	return (!strcmp(rdt_kn_name(kn), "mon_groups") &&
+		strcmp(name, "mon_groups"));
+}
+
 static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 			     const char *name, umode_t mode,
 			     enum rdt_group_type rtype, struct rdtgroup **r)
@@ -3568,6 +3584,15 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 		goto out_unlock;
 	}
 
+	/*
+	 * Check that the parent directory for a monitor group is a "mon_groups"
+	 * directory.
+	 */
+	if (rtype == RDTMON_GROUP && !is_mon_groups(parent_kn, name)) {
+		ret = -EPERM;
+		goto out_unlock;
+	}
+
 	if (rtype == RDTMON_GROUP &&
 	    (prdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
 	     prdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)) {
@@ -3751,22 +3776,6 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
 	return ret;
 }
 
-/*
- * We allow creating mon groups only with in a directory called "mon_groups"
- * which is present in every ctrl_mon group. Check if this is a valid
- * "mon_groups" directory.
- *
- * 1. The directory should be named "mon_groups".
- * 2. The mon group itself should "not" be named "mon_groups".
- *   This makes sure "mon_groups" directory always has a ctrl_mon group
- *   as parent.
- */
-static bool is_mon_groups(struct kernfs_node *kn, const char *name)
-{
-	return (!strcmp(rdt_kn_name(kn), "mon_groups") &&
-		strcmp(name, "mon_groups"));
-}
-
 static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
 			  umode_t mode)
 {
@@ -3782,11 +3791,8 @@ static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
 	if (resctrl_arch_alloc_capable() && parent_kn == rdtgroup_default.kn)
 		return rdtgroup_mkdir_ctrl_mon(parent_kn, name, mode);
 
-	/*
-	 * If RDT monitoring is supported and the parent directory is a valid
-	 * "mon_groups" directory, add a monitoring subdirectory.
-	 */
-	if (resctrl_arch_mon_capable() && is_mon_groups(parent_kn, name))
+	/* Else, attempt to add a monitoring subdirectory. */
+	if (resctrl_arch_mon_capable())
 		return rdtgroup_mkdir_mon(parent_kn, name, mode);
 
 	return -EPERM;

From 8b9f8e14f8be92871068c7fae7b583f4e6bcd4e2 Mon Sep 17 00:00:00 2001
From: "Yury Norov [NVIDIA]" <yury.norov@gmail.com>
Date: Thu, 15 May 2025 16:58:31 +0000
Subject: [PATCH 063/236] cpumask: Relax cpumask_any_but()

commit 189572bf4e005431051319def435ac4b7e4489ca upstream.

Similarly to other cpumask search functions, accept -1, and consider it as
'any CPU' hint. This helps users to avoid coding special cases.

Signed-off-by: Yury Norov [NVIDIA] <yury.norov@gmail.com>
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: James Morse <james.morse@arm.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: James Morse <james.morse@arm.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Tested-by: Fenghua Yu <fenghuay@nvidia.com>
Link: https://lore.kernel.org/20250515165855.31452-2-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 include/linux/cpumask.h | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index fbfd28280470f..56f8e0acc2640 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -394,14 +394,18 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta
  * @cpu: the cpu to ignore.
  *
  * Often used to find any cpu but smp_processor_id() in a mask.
+ * If @cpu == -1, the function is equivalent to cpumask_any().
  * Return: >= nr_cpu_ids if no cpus set.
  */
 static __always_inline
-unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
+unsigned int cpumask_any_but(const struct cpumask *mask, int cpu)
 {
 	unsigned int i;
 
-	cpumask_check(cpu);
+	/* -1 is a legal arg here. */
+	if (cpu != -1)
+		cpumask_check(cpu);
+
 	for_each_cpu(i, mask)
 		if (i != cpu)
 			break;
@@ -414,16 +418,20 @@ unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
  * @mask2: the second input cpumask
  * @cpu: the cpu to ignore
  *
+ * If @cpu == -1, the function is equivalent to cpumask_any_and().
  * Returns >= nr_cpu_ids if no cpus set.
  */
 static __always_inline
 unsigned int cpumask_any_and_but(const struct cpumask *mask1,
 				 const struct cpumask *mask2,
-				 unsigned int cpu)
+				 int cpu)
 {
 	unsigned int i;
 
-	cpumask_check(cpu);
+	/* -1 is a legal arg here. */
+	if (cpu != -1)
+		cpumask_check(cpu);
+
 	i = cpumask_first_and(mask1, mask2);
 	if (i != cpu)
 		return i;

From 029a5ab06dc2c08384b8b6e839268d19413a7687 Mon Sep 17 00:00:00 2001
From: "Yury Norov [NVIDIA]" <yury.norov@gmail.com>
Date: Thu, 15 May 2025 16:58:32 +0000
Subject: [PATCH 064/236] find: Add find_first_andnot_bit()

commit 13f0a02bf4c1c5888c736cedef9ca50de666adb3 upstream.

The function helps to implement cpumask_andnot() APIs.

Signed-off-by: Yury Norov [NVIDIA] <yury.norov@gmail.com>
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: James Morse <james.morse@arm.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: James Morse <james.morse@arm.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Tested-by: Fenghua Yu <fenghuay@nvidia.com>
Link: https://lore.kernel.org/20250515165855.31452-3-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 include/linux/find.h | 25 +++++++++++++++++++++++++
 lib/find_bit.c       | 11 +++++++++++
 2 files changed, 36 insertions(+)

diff --git a/include/linux/find.h b/include/linux/find.h
index a3a908a27df7e..96b8410a7cf76 100644
--- a/include/linux/find.h
+++ b/include/linux/find.h
@@ -29,6 +29,8 @@ unsigned long __find_nth_and_andnot_bit(const unsigned long *addr1, const unsign
 					unsigned long n);
 extern unsigned long _find_first_and_bit(const unsigned long *addr1,
 					 const unsigned long *addr2, unsigned long size);
+unsigned long _find_first_andnot_bit(const unsigned long *addr1, const unsigned long *addr2,
+				 unsigned long size);
 unsigned long _find_first_and_and_bit(const unsigned long *addr1, const unsigned long *addr2,
 				      const unsigned long *addr3, unsigned long size);
 extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size);
@@ -347,6 +349,29 @@ unsigned long find_first_and_bit(const unsigned long *addr1,
 }
 #endif
 
+/**
+ * find_first_andnot_bit - find the first bit set in 1st memory region and unset in 2nd
+ * @addr1: The first address to base the search on
+ * @addr2: The second address to base the search on
+ * @size: The bitmap size in bits
+ *
+ * Returns the bit number for the first set bit
+ * If no bits are set, returns >= @size.
+ */
+static __always_inline
+unsigned long find_first_andnot_bit(const unsigned long *addr1,
+				 const unsigned long *addr2,
+				 unsigned long size)
+{
+	if (small_const_nbits(size)) {
+		unsigned long val = *addr1 & (~*addr2) & GENMASK(size - 1, 0);
+
+		return val ? __ffs(val) : size;
+	}
+
+	return _find_first_andnot_bit(addr1, addr2, size);
+}
+
 /**
  * find_first_and_and_bit - find the first set bit in 3 memory regions
  * @addr1: The first address to base the search on
diff --git a/lib/find_bit.c b/lib/find_bit.c
index dacadd904250f..79c36041694a8 100644
--- a/lib/find_bit.c
+++ b/lib/find_bit.c
@@ -116,6 +116,17 @@ unsigned long _find_first_and_bit(const unsigned long *addr1,
 EXPORT_SYMBOL(_find_first_and_bit);
 #endif
 
+/*
+ * Find the first bit set in 1st memory region and unset in 2nd.
+ */
+unsigned long _find_first_andnot_bit(const unsigned long *addr1,
+				  const unsigned long *addr2,
+				  unsigned long size)
+{
+	return FIND_FIRST_BIT(addr1[idx] & ~addr2[idx], /* nop */, size);
+}
+EXPORT_SYMBOL(_find_first_andnot_bit);
+
 /*
  * Find the first set bit in three memory regions.
  */

From b0b371fa1ab11adbf0db65ae4294664ac8b0f340 Mon Sep 17 00:00:00 2001
From: "Yury Norov [NVIDIA]" <yury.norov@gmail.com>
Date: Thu, 15 May 2025 16:58:33 +0000
Subject: [PATCH 065/236] cpumask: Add cpumask_{first,next}_andnot() API

commit 5da703ef4e4a82b2f9a00f2b3a1eae5657e68a92 upstream.

With the lack of the functions, client code has to abuse less efficient
cpumask_nth().

Signed-off-by: Yury Norov [NVIDIA] <yury.norov@gmail.com>
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: James Morse <james.morse@arm.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: James Morse <james.morse@arm.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250515165855.31452-4-james.morse@arm.com

 Conflicts:
	include/linux/cpumask.h
[jz: resolve context conflict]
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 include/linux/cpumask.h | 59 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 59 insertions(+)

diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 56f8e0acc2640..afd540f321012 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -186,6 +186,19 @@ unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask
 	return find_first_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits);
 }
 
+/**
+ * cpumask_first_andnot - return the first cpu from *srcp1 & ~*srcp2
+ * @srcp1: the first input
+ * @srcp2: the second input
+ *
+ * Return: >= nr_cpu_ids if no such cpu found.
+ */
+static __always_inline
+unsigned int cpumask_first_andnot(const struct cpumask *srcp1, const struct cpumask *srcp2)
+{
+	return find_first_andnot_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits);
+}
+
 /**
  * cpumask_first_and_and - return the first cpu from *srcp1 & *srcp2 & *srcp3
  * @srcp1: the first input
@@ -292,6 +305,25 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p,
 		small_cpumask_bits, n + 1);
 }
 
+/**
+ * cpumask_next_andnot - get the next cpu in *src1p & ~*src2p
+ * @n: the cpu prior to the place to search (i.e. return will be > @n)
+ * @src1p: the first cpumask pointer
+ * @src2p: the second cpumask pointer
+ *
+ * Return: >= nr_cpu_ids if no further cpus set in both.
+ */
+static __always_inline
+unsigned int cpumask_next_andnot(int n, const struct cpumask *src1p,
+				 const struct cpumask *src2p)
+{
+	/* -1 is a legal arg here. */
+	if (n != -1)
+		cpumask_check(n);
+	return find_next_andnot_bit(cpumask_bits(src1p), cpumask_bits(src2p),
+		small_cpumask_bits, n + 1);
+}
+
 /**
  * for_each_cpu - iterate over every cpu in a mask
  * @cpu: the (optionally unsigned) integer iterator
@@ -439,6 +471,33 @@ unsigned int cpumask_any_and_but(const struct cpumask *mask1,
 	return cpumask_next_and(cpu, mask1, mask2);
 }
 
+/**
+ * cpumask_any_andnot_but - pick an arbitrary cpu from *mask1 & ~*mask2, but not this one.
+ * @mask1: the first input cpumask
+ * @mask2: the second input cpumask
+ * @cpu: the cpu to ignore
+ *
+ * If @cpu == -1, the function returns the first matching cpu.
+ * Returns >= nr_cpu_ids if no cpus set.
+ */
+static __always_inline
+unsigned int cpumask_any_andnot_but(const struct cpumask *mask1,
+				    const struct cpumask *mask2,
+				    int cpu)
+{
+	unsigned int i;
+
+	/* -1 is a legal arg here. */
+	if (cpu != -1)
+		cpumask_check(cpu);
+
+	i = cpumask_first_andnot(mask1, mask2);
+	if (i != cpu)
+		return i;
+
+	return cpumask_next_andnot(cpu, mask1, mask2);
+}
+
 /**
  * cpumask_nth - get the Nth cpu in a cpumask
  * @srcp: the cpumask pointer

From c3ecf0e01f2f146f783ca51201b9d9f9807e3104 Mon Sep 17 00:00:00 2001
From: "Yury Norov [NVIDIA]" <yury.norov@gmail.com>
Date: Thu, 15 May 2025 16:58:34 +0000
Subject: [PATCH 066/236] x86/resctrl: Optimize cpumask_any_housekeeping()

commit 94f7531430285b4ec600693f7222c2ca29bd7472 upstream.

With the lack of cpumask_any_andnot_but(), cpumask_any_housekeeping()
has to abuse cpumask_nth() functions.

Update cpumask_any_housekeeping() to use the new cpumask_any_but()
and cpumask_any_andnot_but(). These two functions understand
RESCTRL_PICK_ANY_CPU, which simplifies cpumask_any_housekeeping()
significantly.

Signed-off-by: Yury Norov [NVIDIA] <yury.norov@gmail.com>
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: James Morse <james.morse@arm.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: James Morse <james.morse@arm.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250515165855.31452-5-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/internal.h | 28 +++++++-------------------
 1 file changed, 7 insertions(+), 21 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 608a890ac7456..a02188f977a3c 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -50,30 +50,16 @@
 static inline unsigned int
 cpumask_any_housekeeping(const struct cpumask *mask, int exclude_cpu)
 {
-	unsigned int cpu, hk_cpu;
-
-	if (exclude_cpu == RESCTRL_PICK_ANY_CPU)
-		cpu = cpumask_any(mask);
-	else
-		cpu = cpumask_any_but(mask, exclude_cpu);
-
-	/* Only continue if tick_nohz_full_mask has been initialized. */
-	if (!tick_nohz_full_enabled())
-		return cpu;
-
-	/* If the CPU picked isn't marked nohz_full nothing more needs doing. */
-	if (cpu < nr_cpu_ids && !tick_nohz_full_cpu(cpu))
-		return cpu;
+	unsigned int cpu;
 
 	/* Try to find a CPU that isn't nohz_full to use in preference */
-	hk_cpu = cpumask_nth_andnot(0, mask, tick_nohz_full_mask);
-	if (hk_cpu == exclude_cpu)
-		hk_cpu = cpumask_nth_andnot(1, mask, tick_nohz_full_mask);
-
-	if (hk_cpu < nr_cpu_ids)
-		cpu = hk_cpu;
+	if (tick_nohz_full_enabled()) {
+		cpu = cpumask_any_andnot_but(mask, tick_nohz_full_mask, exclude_cpu);
+		if (cpu < nr_cpu_ids)
+			return cpu;
+	}
 
-	return cpu;
+	return cpumask_any_but(mask, exclude_cpu);
 }
 
 struct rdt_fs_context {

From 82769df110be52b1be8f5dbc223c3252f43f4d50 Mon Sep 17 00:00:00 2001
From: Amit Singh Tomar <amitsinght@marvell.com>
Date: Thu, 15 May 2025 16:58:35 +0000
Subject: [PATCH 067/236] x86/resctrl: Remove the limit on the number of CLOSID

commit dcb1d3d3b77bdb30d2ec97f540d58ee35f1b1c82 upstream.

Resctrl allocates and finds free CLOSID values using the bits of a u32.
This restricts the number of control groups that can be created by
user-space.

MPAM has an architectural limit of 2^16 CLOSID values, Intel x86 could
be extended beyond 32 values. There is at least one MPAM platform which
supports more than 32 CLOSID values.

Replace the fixed size bitmap with calls to the bitmap API to allocate
an array of a sufficient size.

ffs() returns '1' for bit 0, hence the existing code subtracts 1 from
the index to get the CLOSID value. find_first_bit() returns the bit
number which does not need adjusting.

  [ morse: fixed the off-by-one in the allocator and the wrong not-found
    value. Removed the limit. Rephrase the commit message. ]

Signed-off-by: Amit Singh Tomar <amitsinght@marvell.com>
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250515165855.31452-6-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 51 ++++++++++++++++++--------
 1 file changed, 35 insertions(+), 16 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index cc4a54145c83d..53213cae30ec6 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -130,8 +130,8 @@ static bool resctrl_is_mbm_event(int e)
 }
 
 /*
- * Trivial allocator for CLOSIDs. Since h/w only supports a small number,
- * we can keep a bitmap of free CLOSIDs in a single integer.
+ * Trivial allocator for CLOSIDs. Use BITMAP APIs to manipulate a bitmap
+ * of free CLOSIDs.
  *
  * Using a global CLOSID across all resources has some advantages and
  * some drawbacks:
@@ -144,7 +144,7 @@ static bool resctrl_is_mbm_event(int e)
  * - Our choices on how to configure each resource become progressively more
  *   limited as the number of resources grows.
  */
-static unsigned long closid_free_map;
+static unsigned long *closid_free_map;
 static int closid_free_map_len;
 
 int closids_supported(void)
@@ -152,20 +152,35 @@ int closids_supported(void)
 	return closid_free_map_len;
 }
 
-static void closid_init(void)
+static int closid_init(void)
 {
 	struct resctrl_schema *s;
-	u32 rdt_min_closid = 32;
+	u32 rdt_min_closid = ~0;
+
+	/* Monitor only platforms still call closid_init() */
+	if (list_empty(&resctrl_schema_all))
+		return 0;
 
 	/* Compute rdt_min_closid across all resources */
 	list_for_each_entry(s, &resctrl_schema_all, list)
 		rdt_min_closid = min(rdt_min_closid, s->num_closid);
 
-	closid_free_map = BIT_MASK(rdt_min_closid) - 1;
+	closid_free_map = bitmap_alloc(rdt_min_closid, GFP_KERNEL);
+	if (!closid_free_map)
+		return -ENOMEM;
+	bitmap_fill(closid_free_map, rdt_min_closid);
 
 	/* RESCTRL_RESERVED_CLOSID is always reserved for the default group */
-	__clear_bit(RESCTRL_RESERVED_CLOSID, &closid_free_map);
+	__clear_bit(RESCTRL_RESERVED_CLOSID, closid_free_map);
 	closid_free_map_len = rdt_min_closid;
+
+	return 0;
+}
+
+static void closid_exit(void)
+{
+	bitmap_free(closid_free_map);
+	closid_free_map = NULL;
 }
 
 static int closid_alloc(void)
@@ -182,12 +197,11 @@ static int closid_alloc(void)
 			return cleanest_closid;
 		closid = cleanest_closid;
 	} else {
-		closid = ffs(closid_free_map);
-		if (closid == 0)
+		closid = find_first_bit(closid_free_map, closid_free_map_len);
+		if (closid == closid_free_map_len)
 			return -ENOSPC;
-		closid--;
 	}
-	__clear_bit(closid, &closid_free_map);
+	__clear_bit(closid, closid_free_map);
 
 	return closid;
 }
@@ -196,7 +210,7 @@ void closid_free(int closid)
 {
 	lockdep_assert_held(&rdtgroup_mutex);
 
-	__set_bit(closid, &closid_free_map);
+	__set_bit(closid, closid_free_map);
 }
 
 /**
@@ -210,7 +224,7 @@ bool closid_allocated(unsigned int closid)
 {
 	lockdep_assert_held(&rdtgroup_mutex);
 
-	return !test_bit(closid, &closid_free_map);
+	return !test_bit(closid, closid_free_map);
 }
 
 /**
@@ -2765,20 +2779,22 @@ static int rdt_get_tree(struct fs_context *fc)
 		goto out_ctx;
 	}
 
-	closid_init();
+	ret = closid_init();
+	if (ret)
+		goto out_schemata_free;
 
 	if (resctrl_arch_mon_capable())
 		flags |= RFTYPE_MON;
 
 	ret = rdtgroup_add_files(rdtgroup_default.kn, flags);
 	if (ret)
-		goto out_schemata_free;
+		goto out_closid_exit;
 
 	kernfs_activate(rdtgroup_default.kn);
 
 	ret = rdtgroup_create_info_dir(rdtgroup_default.kn);
 	if (ret < 0)
-		goto out_schemata_free;
+		goto out_closid_exit;
 
 	if (resctrl_arch_mon_capable()) {
 		ret = mongroup_create_dir(rdtgroup_default.kn,
@@ -2829,6 +2845,8 @@ static int rdt_get_tree(struct fs_context *fc)
 		kernfs_remove(kn_mongrp);
 out_info:
 	kernfs_remove(kn_info);
+out_closid_exit:
+	closid_exit();
 out_schemata_free:
 	schemata_list_destroy();
 out_ctx:
@@ -3076,6 +3094,7 @@ static void rdt_kill_sb(struct super_block *sb)
 	rmdir_all_sub();
 	rdt_pseudo_lock_release();
 	rdtgroup_default.mode = RDT_MODE_SHAREABLE;
+	closid_exit();
 	schemata_list_destroy();
 	rdtgroup_destroy_root();
 	if (resctrl_arch_alloc_capable())

From abb9bc97a263bab0ff36ce2217c553ee4e8bd9fc Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Thu, 15 May 2025 16:58:36 +0000
Subject: [PATCH 068/236] x86/resctrl: Rename resctrl_sched_in() to begin with
 "resctrl_arch_"

commit 7704fb81bc87254e8772f387b62153b135bb1932 upstream.

resctrl_sched_in() loads the architecture specific CPU MSRs with the
CLOSID and RMID values. This function was named before resctrl was
split to have architecture specific code, and generic filesystem code.

This function is obviously architecture specific, but does not begin
with 'resctrl_arch_', making it the odd one out in the functions an
architecture needs to support to enable resctrl.

Rename it for consistency. This is purely cosmetic.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250515165855.31452-7-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/include/asm/resctrl.h         |  4 ++--
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 12 ++++++------
 arch/x86/kernel/process_32.c           |  2 +-
 arch/x86/kernel/process_64.c           |  2 +-
 4 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h
index 011bf67a18664..7a39728b07431 100644
--- a/arch/x86/include/asm/resctrl.h
+++ b/arch/x86/include/asm/resctrl.h
@@ -175,7 +175,7 @@ static inline bool resctrl_arch_match_rmid(struct task_struct *tsk, u32 ignored,
 	return READ_ONCE(tsk->rmid) == rmid;
 }
 
-static inline void resctrl_sched_in(struct task_struct *tsk)
+static inline void resctrl_arch_sched_in(struct task_struct *tsk)
 {
 	if (static_branch_likely(&rdt_enable_key))
 		__resctrl_sched_in(tsk);
@@ -212,7 +212,7 @@ void resctrl_cpu_detect(struct cpuinfo_x86 *c);
 
 #else
 
-static inline void resctrl_sched_in(struct task_struct *tsk) {}
+static inline void resctrl_arch_sched_in(struct task_struct *tsk) {}
 static inline void resctrl_cpu_detect(struct cpuinfo_x86 *c) {}
 
 #endif /* CONFIG_X86_CPU_RESCTRL */
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 53213cae30ec6..88197afbbb8ac 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -376,7 +376,7 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of,
 }
 
 /*
- * This is safe against resctrl_sched_in() called from __switch_to()
+ * This is safe against resctrl_arch_sched_in() called from __switch_to()
  * because __switch_to() is executed with interrupts disabled. A local call
  * from update_closid_rmid() is protected against __switch_to() because
  * preemption is disabled.
@@ -395,7 +395,7 @@ void resctrl_arch_sync_cpu_closid_rmid(void *info)
 	 * executing task might have its own closid selected. Just reuse
 	 * the context switch code.
 	 */
-	resctrl_sched_in(current);
+	resctrl_arch_sched_in(current);
 }
 
 /*
@@ -620,7 +620,7 @@ static void _update_task_closid_rmid(void *task)
 	 * Otherwise, the MSR is updated when the task is scheduled in.
 	 */
 	if (task == current)
-		resctrl_sched_in(task);
+		resctrl_arch_sched_in(task);
 }
 
 static void update_task_closid_rmid(struct task_struct *t)
@@ -678,7 +678,7 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
 	 * Ensure the task's closid and rmid are written before determining if
 	 * the task is current that will decide if it will be interrupted.
 	 * This pairs with the full barrier between the rq->curr update and
-	 * resctrl_sched_in() during context switch.
+	 * resctrl_arch_sched_in() during context switch.
 	 */
 	smp_mb();
 
@@ -2994,8 +2994,8 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to,
 			/*
 			 * Order the closid/rmid stores above before the loads
 			 * in task_curr(). This pairs with the full barrier
-			 * between the rq->curr update and resctrl_sched_in()
-			 * during context switch.
+			 * between the rq->curr update and
+			 * resctrl_arch_sched_in() during context switch.
 			 */
 			smp_mb();
 
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 708c87b88cc15..619560eb9f94c 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -212,7 +212,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	switch_fpu_finish();
 
 	/* Load the Intel cache allocation PQR MSR. */
-	resctrl_sched_in(next_p);
+	resctrl_arch_sched_in(next_p);
 
 	return prev_p;
 }
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index dd19a4db741af..fa04091e2f4eb 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -659,7 +659,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	}
 
 	/* Load the Intel cache allocation PQR MSR. */
-	resctrl_sched_in(next_p);
+	resctrl_arch_sched_in(next_p);
 
 	return prev_p;
 }

From dcf9c75786e74eff89ae0c15ded115eb9b325e45 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Thu, 15 May 2025 16:58:37 +0000
Subject: [PATCH 069/236] x86/resctrl: Check all domains are offline in
 resctrl_exit()

commit 8eb7ad66badc71e0d8547cf6195a2a6190090152 upstream.

resctrl_exit() removes things like the resctrl mount point directory
and unregisters the filesystem prior to freeing data structures that
were allocated during resctrl_init().

This assumes that there are no online domains when resctrl_exit() is
called. If any domain were online, the limbo or overflow handler could
be scheduled to run.

Add a check for any online control or monitor domains, and document that
the architecture code is required to offline all monitor and control
domains before calling resctrl_exit().

Suggested-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250515165855.31452-8-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 33 ++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 88197afbbb8ac..29f76ad21f1c1 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -4420,8 +4420,41 @@ int __init resctrl_init(void)
 	return ret;
 }
 
+static bool __exit resctrl_online_domains_exist(void)
+{
+	struct rdt_resource *r;
+
+	/*
+	 * Only walk capable resources to allow resctrl_arch_get_resource()
+	 * to return dummy 'not capable' resources.
+	 */
+	for_each_alloc_capable_rdt_resource(r) {
+		if (!list_empty(&r->ctrl_domains))
+			return true;
+	}
+
+	for_each_mon_capable_rdt_resource(r) {
+		if (!list_empty(&r->mon_domains))
+			return true;
+	}
+
+	return false;
+}
+
+/*
+ * resctrl_exit() - Remove the resctrl filesystem and free resources.
+ *
+ * When called by the architecture code, all CPUs and resctrl domains must be
+ * offline. This ensures the limbo and overflow handlers are not scheduled to
+ * run, meaning the data structures they access can be freed by
+ * resctrl_mon_resource_exit().
+ */
 void __exit resctrl_exit(void)
 {
+	cpus_read_lock();
+	WARN_ON_ONCE(resctrl_online_domains_exist());
+	cpus_read_unlock();
+
 	debugfs_remove_recursive(debugfs_resctrl);
 	unregister_filesystem(&rdt_fs_type);
 	sysfs_remove_mount_point(fs_kobj, "resctrl");

From 43c3e94ce1432d283e3d751ba77a07a176e1aa61 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Thu, 15 May 2025 16:58:38 +0000
Subject: [PATCH 070/236] x86/resctrl: Resctrl_exit() teardown resctrl but
 leave the mount point

commit 8c992e24a0627a6ba508184c07766862c8bb3e54 upstream.

resctrl_exit() was intended for use when the 'resctrl' module was unloaded.
resctrl can't be built as a module, and the kernfs helpers are not exported so
this is unlikely to change. MPAM has an error interrupt which indicates the
MPAM driver has gone haywire. Should this occur tasks could run with the wrong
control values, leading to bad performance for important tasks.  In this
scenario the MPAM driver will reset the hardware, but it needs a way to tell
resctrl that no further configuration should be attempted.

In particular, moving tasks between control or monitor groups does not
interact with the architecture code, so there is no opportunity for the arch
code to indicate that the hardware is no-longer functioning.

Using resctrl_exit() for this leaves the system in a funny state as resctrl is
still mounted, but cannot be un-mounted because the sysfs directory that is
typically used has been removed. Dave Martin suggests this may cause systemd
trouble in the future as not all filesystems can be unmounted.

Add calls to remove all the files and directories in resctrl, and remove the
sysfs_remove_mount_point() call that leaves the system in a funny state. When
triggered, this causes all the resctrl files to disappear. resctrl can be
unmounted, but not mounted again.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250515165855.31452-9-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 48 +++++++++++++++++++++-----
 1 file changed, 40 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 29f76ad21f1c1..1e48c61db2aa1 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -3078,6 +3078,22 @@ static void rmdir_all_sub(void)
 	kernfs_remove(kn_mondata);
 }
 
+static void resctrl_fs_teardown(void)
+{
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	/* Cleared by rdtgroup_destroy_root() */
+	if (!rdtgroup_default.kn)
+		return;
+
+	rmdir_all_sub();
+	rdt_pseudo_lock_release();
+	rdtgroup_default.mode = RDT_MODE_SHAREABLE;
+	closid_exit();
+	schemata_list_destroy();
+	rdtgroup_destroy_root();
+}
+
 static void rdt_kill_sb(struct super_block *sb)
 {
 	struct rdt_resource *r;
@@ -3091,12 +3107,7 @@ static void rdt_kill_sb(struct super_block *sb)
 	for_each_alloc_capable_rdt_resource(r)
 		resctrl_arch_reset_all_ctrls(r);
 
-	rmdir_all_sub();
-	rdt_pseudo_lock_release();
-	rdtgroup_default.mode = RDT_MODE_SHAREABLE;
-	closid_exit();
-	schemata_list_destroy();
-	rdtgroup_destroy_root();
+	resctrl_fs_teardown();
 	if (resctrl_arch_alloc_capable())
 		resctrl_arch_disable_alloc();
 	if (resctrl_arch_mon_capable())
@@ -4127,6 +4138,8 @@ static int rdtgroup_setup_root(struct rdt_fs_context *ctx)
 
 static void rdtgroup_destroy_root(void)
 {
+	lockdep_assert_held(&rdtgroup_mutex);
+
 	kernfs_destroy_root(rdt_root);
 	rdtgroup_default.kn = NULL;
 }
@@ -4441,23 +4454,42 @@ static bool __exit resctrl_online_domains_exist(void)
 	return false;
 }
 
-/*
+/**
  * resctrl_exit() - Remove the resctrl filesystem and free resources.
  *
+ * Called by the architecture code in response to a fatal error.
+ * Removes resctrl files and structures from kernfs to prevent further
+ * configuration.
+ *
  * When called by the architecture code, all CPUs and resctrl domains must be
  * offline. This ensures the limbo and overflow handlers are not scheduled to
  * run, meaning the data structures they access can be freed by
  * resctrl_mon_resource_exit().
+ *
+ * After resctrl_exit() returns, the architecture code should return an
+ * error from all resctrl_arch_ functions that can do this.
+ * resctrl_arch_get_resource() must continue to return struct rdt_resources
+ * with the correct rid field to ensure the filesystem can be unmounted.
  */
 void __exit resctrl_exit(void)
 {
 	cpus_read_lock();
 	WARN_ON_ONCE(resctrl_online_domains_exist());
+
+	mutex_lock(&rdtgroup_mutex);
+	resctrl_fs_teardown();
+	mutex_unlock(&rdtgroup_mutex);
+
 	cpus_read_unlock();
 
 	debugfs_remove_recursive(debugfs_resctrl);
+	debugfs_resctrl = NULL;
 	unregister_filesystem(&rdt_fs_type);
-	sysfs_remove_mount_point(fs_kobj, "resctrl");
+
+	/*
+	 * Do not remove the sysfs mount point added by resctrl_init() so that
+	 * it can be used to umount resctrl.
+	 */
 
 	resctrl_mon_resource_exit();
 }

From d4054bf5c5ffc806ad06013f31d1638695e8cac7 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Thu, 15 May 2025 16:58:39 +0000
Subject: [PATCH 071/236] x86/resctrl: Drop __init/__exit on assorted symbols

commit bc740420d7ae7878696d5ad9f3dbcb11e2599b2e upstream.

Because ARM's MPAM controls are probed using MMIO, resctrl can't be
initialised until enough CPUs are online to have determined the system-wide
supported num_closid. Arm64 also supports 'late onlined secondaries', where
only a subset of CPUs are online during boot.

These two combine to mean the MPAM driver may not be able to initialise
resctrl until user-space has brought 'enough' CPUs online.

To allow MPAM to initialise resctrl after __init text has been free'd, remove
all the __init markings from resctrl.

The existing __exit markings cause these functions to be removed by the linker
as it has never been possible to build resctrl as a module. MPAM has an error
interrupt which causes the driver to reset and disable itself. Remove the
__exit markings to allow the MPAM driver to tear down resctrl when an error
occurs.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250515165855.31452-10-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c     | 6 +++---
 arch/x86/kernel/cpu/resctrl/internal.h | 4 ++--
 arch/x86/kernel/cpu/resctrl/monitor.c  | 2 +-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 8 ++++----
 include/linux/resctrl.h                | 6 +++---
 5 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 081082a3304a5..e3a5ec4815290 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -737,7 +737,7 @@ struct rdt_options {
 	bool	force_off, force_on;
 };
 
-static struct rdt_options rdt_options[]  __initdata = {
+static struct rdt_options rdt_options[]  __ro_after_init = {
 	RDT_OPT(RDT_FLAG_CMT,	    "cmt",	X86_FEATURE_CQM_OCCUP_LLC),
 	RDT_OPT(RDT_FLAG_MBM_TOTAL, "mbmtotal", X86_FEATURE_CQM_MBM_TOTAL),
 	RDT_OPT(RDT_FLAG_MBM_LOCAL, "mbmlocal", X86_FEATURE_CQM_MBM_LOCAL),
@@ -777,7 +777,7 @@ static int __init set_rdt_options(char *str)
 }
 __setup("rdt", set_rdt_options);
 
-bool __init rdt_cpu_has(int flag)
+bool rdt_cpu_has(int flag)
 {
 	bool ret = boot_cpu_has(flag);
 	struct rdt_options *o;
@@ -797,7 +797,7 @@ bool __init rdt_cpu_has(int flag)
 	return ret;
 }
 
-__init bool resctrl_arch_is_evt_configurable(enum resctrl_event_id evt)
+bool resctrl_arch_is_evt_configurable(enum resctrl_event_id evt)
 {
 	if (!rdt_cpu_has(X86_FEATURE_BMEC))
 		return false;
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index a02188f977a3c..db007d75df853 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -475,13 +475,13 @@ int alloc_rmid(u32 closid);
 void free_rmid(u32 closid, u32 rmid);
 int rdt_get_mon_l3_config(struct rdt_resource *r);
 void resctrl_mon_resource_exit(void);
-bool __init rdt_cpu_has(int flag);
+bool rdt_cpu_has(int flag);
 void mon_event_count(void *info);
 int rdtgroup_mondata_show(struct seq_file *m, void *arg);
 void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 		    struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
 		    cpumask_t *cpumask, int evtid, int first);
-int __init resctrl_mon_resource_init(void);
+int resctrl_mon_resource_init(void);
 void mbm_setup_overflow_handler(struct rdt_mon_domain *dom,
 				unsigned long delay_ms,
 				int exclude_cpu);
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index d8d21f76de14b..4a74937a356e2 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -1204,7 +1204,7 @@ static __init int snc_get_config(void)
  *
  * Returns 0 for success, or -ENOMEM.
  */
-int __init resctrl_mon_resource_init(void)
+int resctrl_mon_resource_init(void)
 {
 	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
 	int ret;
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 1e48c61db2aa1..cfd846cc861e3 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -4144,7 +4144,7 @@ static void rdtgroup_destroy_root(void)
 	rdtgroup_default.kn = NULL;
 }
 
-static void __init rdtgroup_setup_default(void)
+static void rdtgroup_setup_default(void)
 {
 	mutex_lock(&rdtgroup_mutex);
 
@@ -4376,7 +4376,7 @@ void resctrl_offline_cpu(unsigned int cpu)
  *
  * Return: 0 on success or -errno
  */
-int __init resctrl_init(void)
+int resctrl_init(void)
 {
 	int ret = 0;
 
@@ -4433,7 +4433,7 @@ int __init resctrl_init(void)
 	return ret;
 }
 
-static bool __exit resctrl_online_domains_exist(void)
+static bool resctrl_online_domains_exist(void)
 {
 	struct rdt_resource *r;
 
@@ -4471,7 +4471,7 @@ static bool __exit resctrl_online_domains_exist(void)
  * resctrl_arch_get_resource() must continue to return struct rdt_resources
  * with the correct rid field to ensure the filesystem can be unmounted.
  */
-void __exit resctrl_exit(void)
+void resctrl_exit(void)
 {
 	cpus_read_lock();
 	WARN_ON_ONCE(resctrl_online_domains_exist());
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 880351ca3dfcb..b8f8240050b42 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -358,7 +358,7 @@ u32 resctrl_arch_get_num_closid(struct rdt_resource *r);
 u32 resctrl_arch_system_num_rmid_idx(void);
 int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid);
 
-__init bool resctrl_arch_is_evt_configurable(enum resctrl_event_id evt);
+bool resctrl_arch_is_evt_configurable(enum resctrl_event_id evt);
 
 /**
  * resctrl_arch_mon_event_config_write() - Write the config for an event.
@@ -514,7 +514,7 @@ void resctrl_arch_reset_all_ctrls(struct rdt_resource *r);
 extern unsigned int resctrl_rmid_realloc_threshold;
 extern unsigned int resctrl_rmid_realloc_limit;
 
-int __init resctrl_init(void);
-void __exit resctrl_exit(void);
+int resctrl_init(void);
+void resctrl_exit(void);
 
 #endif /* _RESCTRL_H */

From fa0ab15d440b6951d22b110edf91fdc2e194be77 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Thu, 15 May 2025 16:58:40 +0000
Subject: [PATCH 072/236] x86/resctrl: Move is_mba_sc() out of core.c

commit 6c72fb8d8bd7bfaafdeda3a91c535ecf52283ec9 upstream.

is_mba_sc() is defined in core.c, but has no callers there. It does not access
any architecture private structures.

Move this to rdtgroup.c where the majority of callers are. This makes the move
of the filesystem code to /fs/ cleaner.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250515165855.31452-11-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c     | 15 ---------------
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 15 +++++++++++++++
 2 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index e3a5ec4815290..ced1ce11e7b02 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -164,21 +164,6 @@ static inline void cache_alloc_hsw_probe(void)
 	rdt_alloc_capable = true;
 }
 
-bool is_mba_sc(struct rdt_resource *r)
-{
-	if (!r)
-		r = resctrl_arch_get_resource(RDT_RESOURCE_MBA);
-
-	/*
-	 * The software controller support is only applicable to MBA resource.
-	 * Make sure to check for resource type.
-	 */
-	if (r->rid != RDT_RESOURCE_MBA)
-		return false;
-
-	return r->membw.mba_sc;
-}
-
 /*
  * rdt_get_mb_table() - get a mapping of bandwidth(b/w) percentage values
  * exposed to user interface and the h/w understandable delay values.
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index cfd846cc861e3..e2999f6685934 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -1535,6 +1535,21 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
 	return size;
 }
 
+bool is_mba_sc(struct rdt_resource *r)
+{
+	if (!r)
+		r = resctrl_arch_get_resource(RDT_RESOURCE_MBA);
+
+	/*
+	 * The software controller support is only applicable to MBA resource.
+	 * Make sure to check for resource type.
+	 */
+	if (r->rid != RDT_RESOURCE_MBA)
+		return false;
+
+	return r->membw.mba_sc;
+}
+
 /*
  * rdtgroup_size_show - Display size in bytes of allocated regions
  *

From 7ef9a1124fe34cf71fb8cc61b28927c54dbc55ec Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Thu, 15 May 2025 16:58:41 +0000
Subject: [PATCH 073/236] x86/resctrl: Add end-marker to the resctrl_event_id
 enum

commit d4fb6b8e4640adeff9673ae398525be7382d3197 upstream.

The resctrl_event_id enum gives names to the counter event numbers on x86.
These are used directly by resctrl.

To allow the MPAM driver to keep an array of these the size of the enum
needs to be known.

Add a 'num_events' enum entry which can be used to size an array.  This is
added to the enum to reduce conflicts with another series, which in turn
requires get_arch_mbm_state() to have a default case.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250515165855.31452-12-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/monitor.c | 9 ++++-----
 include/linux/resctrl_types.h         | 3 +++
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 4a74937a356e2..88aab012dc1a7 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -260,12 +260,11 @@ static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_mon_domain *hw_do
 		return &hw_dom->arch_mbm_total[rmid];
 	case QOS_L3_MBM_LOCAL_EVENT_ID:
 		return &hw_dom->arch_mbm_local[rmid];
+	default:
+		/* Never expect to get here */
+		WARN_ON_ONCE(1);
+		return NULL;
 	}
-
-	/* Never expect to get here */
-	WARN_ON_ONCE(1);
-
-	return NULL;
 }
 
 void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d,
diff --git a/include/linux/resctrl_types.h b/include/linux/resctrl_types.h
index f26450b3326b1..69bf740130ac6 100644
--- a/include/linux/resctrl_types.h
+++ b/include/linux/resctrl_types.h
@@ -49,6 +49,9 @@ enum resctrl_event_id {
 	QOS_L3_OCCUP_EVENT_ID		= 0x01,
 	QOS_L3_MBM_TOTAL_EVENT_ID	= 0x02,
 	QOS_L3_MBM_LOCAL_EVENT_ID	= 0x03,
+
+	/* Must be the last */
+	QOS_NUM_EVENTS,
 };
 
 #endif /* __LINUX_RESCTRL_TYPES_H */

From 3000cc3394c9c699076854e8ae9dd596c362c7ba Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Thu, 15 May 2025 16:58:42 +0000
Subject: [PATCH 074/236] x86/resctrl: Expand the width of domid by replacing
 mon_data_bits

commit 2a65660385444e9d9deffe995c71ee20443ef76e upstream.

MPAM platforms retrieve the cache-id property from the ACPI PPTT table.
The cache-id field is 32 bits wide. Under resctrl, the cache-id becomes
the domain-id, and is packed into the mon_data_bits union bitfield.
The width of cache-id in this field is 14 bits.

Expanding the union would break 32bit x86 platforms as this union is
stored as the kernfs kn->priv pointer. This saved allocating memory
for the priv data storage.

The firmware on MPAM platforms have used the PPTT cache-id field to
expose the interconnect's id for the cache, which is sparse and uses
more than 14 bits. Use of this id is to enable PCIe direct cache
injection hints. Using this feature with VFIO means the value provided
by the ACPI table should be exposed to user-space.

To support cache-id values greater than 14 bits, convert the
mon_data_bits union to a structure. These are shared between control
and monitor groups, and are allocated on first use. The list of
allocated struct mon_data is free'd when the filesystem is umount()ed.

Co-developed-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250515165855.31452-13-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 24 ++++---
 arch/x86/kernel/cpu/resctrl/internal.h    | 39 ++++++-----
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    | 79 +++++++++++++++++++++--
 3 files changed, 106 insertions(+), 36 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 0a0ac5f6112ec..110b534d400c7 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -661,14 +661,15 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 {
 	struct kernfs_open_file *of = m->private;
+	enum resctrl_res_level resid;
+	enum resctrl_event_id evtid;
 	struct rdt_domain_hdr *hdr;
 	struct rmid_read rr = {0};
 	struct rdt_mon_domain *d;
-	u32 resid, evtid, domid;
 	struct rdtgroup *rdtgrp;
 	struct rdt_resource *r;
-	union mon_data_bits md;
-	int ret = 0;
+	struct mon_data *md;
+	int domid, ret = 0;
 
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
 	if (!rdtgrp) {
@@ -676,17 +677,22 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 		goto out;
 	}
 
-	md.priv = of->kn->priv;
-	resid = md.u.rid;
-	domid = md.u.domid;
-	evtid = md.u.evtid;
+	md = of->kn->priv;
+	if (WARN_ON_ONCE(!md)) {
+		ret = -EIO;
+		goto out;
+	}
+
+	resid = md->rid;
+	domid = md->domid;
+	evtid = md->evtid;
 	r = resctrl_arch_get_resource(resid);
 
-	if (md.u.sum) {
+	if (md->sum) {
 		/*
 		 * This file requires summing across all domains that share
 		 * the L3 cache id that was provided in the "domid" field of the
-		 * mon_data_bits union. Search all domains in the resource for
+		 * struct mon_data. Search all domains in the resource for
 		 * one that matches this cache id.
 		 */
 		list_for_each_entry(d, &r->mon_domains, hdr.list) {
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index db007d75df853..6b3470924984c 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -92,27 +92,26 @@ struct mon_evt {
 };
 
 /**
- * union mon_data_bits - Monitoring details for each event file.
- * @priv:              Used to store monitoring event data in @u
- *                     as kernfs private data.
- * @u.rid:             Resource id associated with the event file.
- * @u.evtid:           Event id associated with the event file.
- * @u.sum:             Set when event must be summed across multiple
- *                     domains.
- * @u.domid:           When @u.sum is zero this is the domain to which
- *                     the event file belongs. When @sum is one this
- *                     is the id of the L3 cache that all domains to be
- *                     summed share.
- * @u:                 Name of the bit fields struct.
+ * struct mon_data - Monitoring details for each event file.
+ * @list:            Member of the global @mon_data_kn_priv_list list.
+ * @rid:             Resource id associated with the event file.
+ * @evtid:           Event id associated with the event file.
+ * @sum:             Set when event must be summed across multiple
+ *                   domains.
+ * @domid:           When @sum is zero this is the domain to which
+ *                   the event file belongs. When @sum is one this
+ *                   is the id of the L3 cache that all domains to be
+ *                   summed share.
+ *
+ * Pointed to by the kernfs kn->priv field of monitoring event files.
+ * Readers and writers must hold rdtgroup_mutex.
  */
-union mon_data_bits {
-	void *priv;
-	struct {
-		unsigned int rid		: 10;
-		enum resctrl_event_id evtid	: 7;
-		unsigned int sum		: 1;
-		unsigned int domid		: 14;
-	} u;
+struct mon_data {
+	struct list_head	list;
+	enum resctrl_res_level	rid;
+	enum resctrl_event_id	evtid;
+	int			domid;
+	bool			sum;
 };
 
 /**
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index e2999f6685934..d48078410d771 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -45,6 +45,12 @@ LIST_HEAD(rdt_all_groups);
 /* list of entries for the schemata file */
 LIST_HEAD(resctrl_schema_all);
 
+/*
+ * List of struct mon_data containing private data of event files for use by
+ * rdtgroup_mondata_show(). Protected by rdtgroup_mutex.
+ */
+static LIST_HEAD(mon_data_kn_priv_list);
+
 /* The filesystem can only be mounted once. */
 bool resctrl_mounted;
 
@@ -3093,6 +3099,63 @@ static void rmdir_all_sub(void)
 	kernfs_remove(kn_mondata);
 }
 
+/**
+ * mon_get_kn_priv() - Get the mon_data priv data for this event.
+ *
+ * The same values are used across the mon_data directories of all control and
+ * monitor groups for the same event in the same domain. Keep a list of
+ * allocated structures and re-use an existing one with the same values for
+ * @rid, @domid, etc.
+ *
+ * @rid:    The resource id for the event file being created.
+ * @domid:  The domain id for the event file being created.
+ * @mevt:   The type of event file being created.
+ * @do_sum: Whether SNC summing monitors are being created.
+ */
+static struct mon_data *mon_get_kn_priv(enum resctrl_res_level rid, int domid,
+					struct mon_evt *mevt,
+					bool do_sum)
+{
+	struct mon_data *priv;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	list_for_each_entry(priv, &mon_data_kn_priv_list, list) {
+		if (priv->rid == rid && priv->domid == domid &&
+		    priv->sum == do_sum && priv->evtid == mevt->evtid)
+			return priv;
+	}
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return NULL;
+
+	priv->rid = rid;
+	priv->domid = domid;
+	priv->sum = do_sum;
+	priv->evtid = mevt->evtid;
+	list_add_tail(&priv->list, &mon_data_kn_priv_list);
+
+	return priv;
+}
+
+/**
+ * mon_put_kn_priv() - Free all allocated mon_data structures.
+ *
+ * Called when resctrl file system is unmounted.
+ */
+static void mon_put_kn_priv(void)
+{
+	struct mon_data *priv, *tmp;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	list_for_each_entry_safe(priv, tmp, &mon_data_kn_priv_list, list) {
+		list_del(&priv->list);
+		kfree(priv);
+	}
+}
+
 static void resctrl_fs_teardown(void)
 {
 	lockdep_assert_held(&rdtgroup_mutex);
@@ -3102,6 +3165,7 @@ static void resctrl_fs_teardown(void)
 		return;
 
 	rmdir_all_sub();
+	mon_put_kn_priv();
 	rdt_pseudo_lock_release();
 	rdtgroup_default.mode = RDT_MODE_SHAREABLE;
 	closid_exit();
@@ -3208,19 +3272,20 @@ static int mon_add_all_files(struct kernfs_node *kn, struct rdt_mon_domain *d,
 			     bool do_sum)
 {
 	struct rmid_read rr = {0};
-	union mon_data_bits priv;
+	struct mon_data *priv;
 	struct mon_evt *mevt;
-	int ret;
+	int ret, domid;
 
 	if (WARN_ON(list_empty(&r->evt_list)))
 		return -EPERM;
 
-	priv.u.rid = r->rid;
-	priv.u.domid = do_sum ? d->ci->id : d->hdr.id;
-	priv.u.sum = do_sum;
 	list_for_each_entry(mevt, &r->evt_list, list) {
-		priv.u.evtid = mevt->evtid;
-		ret = mon_addfile(kn, mevt->name, priv.priv);
+		domid = do_sum ? d->ci->id : d->hdr.id;
+		priv = mon_get_kn_priv(r->rid, domid, mevt, do_sum);
+		if (WARN_ON_ONCE(!priv))
+			return -EINVAL;
+
+		ret = mon_addfile(kn, mevt->name, priv);
 		if (ret)
 			return ret;
 

From 0350a78edff9e30a284c2cde4c00ba7dc69acdf1 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Thu, 15 May 2025 16:58:43 +0000
Subject: [PATCH 075/236] x86/resctrl: Split trace.h

commit 270f00bcc9525c8ba667349ba3e8c4dbcbbf70fb upstream.

trace.h contains all the tracepoints. After the move to /fs/resctrl, some
of these will be left behind. All the pseudo_lock tracepoints remain part
of the architecture. The lone tracepoint in monitor.c moves to /fs/resctrl.

Split trace.h so that each C file includes a different trace header file.
This means the trace header files are not modified when they are moved.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250515165855.31452-14-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/Makefile          |  3 ++
 arch/x86/kernel/cpu/resctrl/monitor.c         |  4 ++-
 arch/x86/kernel/cpu/resctrl/monitor_trace.h   | 31 +++++++++++++++++++
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c     |  2 +-
 .../resctrl/{trace.h => pseudo_lock_trace.h}  | 24 +++-----------
 5 files changed, 42 insertions(+), 22 deletions(-)
 create mode 100644 arch/x86/kernel/cpu/resctrl/monitor_trace.h
 rename arch/x86/kernel/cpu/resctrl/{trace.h => pseudo_lock_trace.h} (56%)

diff --git a/arch/x86/kernel/cpu/resctrl/Makefile b/arch/x86/kernel/cpu/resctrl/Makefile
index 0c13b0befd8a9..909be78ec6dac 100644
--- a/arch/x86/kernel/cpu/resctrl/Makefile
+++ b/arch/x86/kernel/cpu/resctrl/Makefile
@@ -2,4 +2,7 @@
 obj-$(CONFIG_X86_CPU_RESCTRL)		+= core.o rdtgroup.o monitor.o
 obj-$(CONFIG_X86_CPU_RESCTRL)		+= ctrlmondata.o
 obj-$(CONFIG_RESCTRL_FS_PSEUDO_LOCK)	+= pseudo_lock.o
+
+# To allow define_trace.h's recursive include:
 CFLAGS_pseudo_lock.o = -I$(src)
+CFLAGS_monitor.o = -I$(src)
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 88aab012dc1a7..6d5601e541853 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -26,7 +26,9 @@
 #include <asm/resctrl.h>
 
 #include "internal.h"
-#include "trace.h"
+
+#define CREATE_TRACE_POINTS
+#include "monitor_trace.h"
 
 /**
  * struct rmid_entry - dirty tracking for all RMID.
diff --git a/arch/x86/kernel/cpu/resctrl/monitor_trace.h b/arch/x86/kernel/cpu/resctrl/monitor_trace.h
new file mode 100644
index 0000000000000..ade67daf42c23
--- /dev/null
+++ b/arch/x86/kernel/cpu/resctrl/monitor_trace.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM resctrl
+
+#if !defined(_FS_RESCTRL_MONITOR_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _FS_RESCTRL_MONITOR_TRACE_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(mon_llc_occupancy_limbo,
+	    TP_PROTO(u32 ctrl_hw_id, u32 mon_hw_id, int domain_id, u64 llc_occupancy_bytes),
+	    TP_ARGS(ctrl_hw_id, mon_hw_id, domain_id, llc_occupancy_bytes),
+	    TP_STRUCT__entry(__field(u32, ctrl_hw_id)
+			     __field(u32, mon_hw_id)
+			     __field(int, domain_id)
+			     __field(u64, llc_occupancy_bytes)),
+	    TP_fast_assign(__entry->ctrl_hw_id = ctrl_hw_id;
+			   __entry->mon_hw_id = mon_hw_id;
+			   __entry->domain_id = domain_id;
+			   __entry->llc_occupancy_bytes = llc_occupancy_bytes;),
+	    TP_printk("ctrl_hw_id=%u mon_hw_id=%u domain_id=%d llc_occupancy_bytes=%llu",
+		      __entry->ctrl_hw_id, __entry->mon_hw_id, __entry->domain_id,
+		      __entry->llc_occupancy_bytes)
+	   );
+
+#endif /* _FS_RESCTRL_MONITOR_TRACE_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE monitor_trace
+#include <trace/define_trace.h>
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index dd9eefccf30fd..80018fb7bf1a9 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -30,7 +30,7 @@
 #include "internal.h"
 
 #define CREATE_TRACE_POINTS
-#include "trace.h"
+#include "pseudo_lock_trace.h"
 
 /*
  * The bits needed to disable hardware prefetching varies based on the
diff --git a/arch/x86/kernel/cpu/resctrl/trace.h b/arch/x86/kernel/cpu/resctrl/pseudo_lock_trace.h
similarity index 56%
rename from arch/x86/kernel/cpu/resctrl/trace.h
rename to arch/x86/kernel/cpu/resctrl/pseudo_lock_trace.h
index 2a506316b3034..5a0fae61d3eeb 100644
--- a/arch/x86/kernel/cpu/resctrl/trace.h
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock_trace.h
@@ -2,8 +2,8 @@
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM resctrl
 
-#if !defined(_TRACE_RESCTRL_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _TRACE_RESCTRL_H
+#if !defined(_X86_RESCTRL_PSEUDO_LOCK_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _X86_RESCTRL_PSEUDO_LOCK_TRACE_H
 
 #include <linux/tracepoint.h>
 
@@ -35,25 +35,9 @@ TRACE_EVENT(pseudo_lock_l3,
 	    TP_printk("hits=%llu miss=%llu",
 		      __entry->l3_hits, __entry->l3_miss));
 
-TRACE_EVENT(mon_llc_occupancy_limbo,
-	    TP_PROTO(u32 ctrl_hw_id, u32 mon_hw_id, int domain_id, u64 llc_occupancy_bytes),
-	    TP_ARGS(ctrl_hw_id, mon_hw_id, domain_id, llc_occupancy_bytes),
-	    TP_STRUCT__entry(__field(u32, ctrl_hw_id)
-			     __field(u32, mon_hw_id)
-			     __field(int, domain_id)
-			     __field(u64, llc_occupancy_bytes)),
-	    TP_fast_assign(__entry->ctrl_hw_id = ctrl_hw_id;
-			   __entry->mon_hw_id = mon_hw_id;
-			   __entry->domain_id = domain_id;
-			   __entry->llc_occupancy_bytes = llc_occupancy_bytes;),
-	    TP_printk("ctrl_hw_id=%u mon_hw_id=%u domain_id=%d llc_occupancy_bytes=%llu",
-		      __entry->ctrl_hw_id, __entry->mon_hw_id, __entry->domain_id,
-		      __entry->llc_occupancy_bytes)
-	   );
-
-#endif /* _TRACE_RESCTRL_H */
+#endif /* _X86_RESCTRL_PSEUDO_LOCK_TRACE_H */
 
 #undef TRACE_INCLUDE_PATH
 #define TRACE_INCLUDE_PATH .
-#define TRACE_INCLUDE_FILE trace
+#define TRACE_INCLUDE_FILE pseudo_lock_trace
 #include <trace/define_trace.h>

From 344ec5948a8d56b16ef1922eef3ccc1e823eed18 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Thu, 15 May 2025 16:58:44 +0000
Subject: [PATCH 076/236] x86/resctrl: Add 'resctrl' to the title of the
 resctrl documentation

commit 003e86077143ebeaa5299fb2bc907ae3b6650028 upstream.

The resctrl documentation is titled "User Interface for Resource Control
feature".

Once the documentation follows the code in a move to the filesystem, this
appears in the list of filesystems, but doesn't contain the name of the
filesystem, making it hard to find.

Add 'resctrl' to the title.

Suggested-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250515165855.31452-15-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 Documentation/arch/x86/resctrl.rst | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/Documentation/arch/x86/resctrl.rst b/Documentation/arch/x86/resctrl.rst
index 6f07af4a885ec..4201da8dad5f1 100644
--- a/Documentation/arch/x86/resctrl.rst
+++ b/Documentation/arch/x86/resctrl.rst
@@ -1,9 +1,9 @@
 .. SPDX-License-Identifier: GPL-2.0
 .. include:: <isonum.txt>
 
-===========================================
-User Interface for Resource Control feature
-===========================================
+=====================================================
+User Interface for Resource Control feature (resctrl)
+=====================================================
 
 :Copyright: |copy| 2016 Intel Corporation
 :Authors: - Fenghua Yu <fenghua.yu@intel.com>

From 66362ac684448c64b67cea202a3c44f58b169964 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Thu, 15 May 2025 16:58:45 +0000
Subject: [PATCH 077/236] fs/resctrl: Add boiler plate for external resctrl
 code

commit bff70402d6d67843fe319338e4c56e1cba13fbd8 upstream.

Add Makefile and Kconfig for fs/resctrl. Add ARCH_HAS_CPU_RESCTRL
for the common parts of the resctrl interface and make X86_CPU_RESCTRL
select this.

Adding an include of asm/resctrl.h to linux/resctrl.h allows the
/fs/resctrl files to switch over to using this header instead.

Co-developed-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250515165855.31452-16-james.morse@arm.com

 Conflicts:
	arch/x86/Kconfig
	fs/Makefile
[jz: resolve simple context conflicts]
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 MAINTAINERS                               |  1 +
 arch/Kconfig                              |  8 +++++
 arch/x86/Kconfig                          | 11 ++-----
 arch/x86/kernel/cpu/resctrl/internal.h    |  2 --
 arch/x86/kernel/cpu/resctrl/monitor.c     |  2 +-
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c |  2 +-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    |  2 +-
 fs/Kconfig                                |  1 +
 fs/Makefile                               |  1 +
 fs/resctrl/Kconfig                        | 39 +++++++++++++++++++++++
 fs/resctrl/Makefile                       |  6 ++++
 fs/resctrl/ctrlmondata.c                  |  0
 fs/resctrl/internal.h                     |  0
 fs/resctrl/monitor.c                      |  0
 fs/resctrl/monitor_trace.h                |  0
 fs/resctrl/pseudo_lock.c                  |  0
 fs/resctrl/pseudo_lock_trace.h            |  0
 fs/resctrl/rdtgroup.c                     |  0
 include/linux/resctrl.h                   |  4 +++
 19 files changed, 66 insertions(+), 13 deletions(-)
 create mode 100644 fs/resctrl/Kconfig
 create mode 100644 fs/resctrl/Makefile
 create mode 100644 fs/resctrl/ctrlmondata.c
 create mode 100644 fs/resctrl/internal.h
 create mode 100644 fs/resctrl/monitor.c
 create mode 100644 fs/resctrl/monitor_trace.h
 create mode 100644 fs/resctrl/pseudo_lock.c
 create mode 100644 fs/resctrl/pseudo_lock_trace.h
 create mode 100644 fs/resctrl/rdtgroup.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 2fc1cc1f312c8..0cb3eab30f9f6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -18111,6 +18111,7 @@ S:	Supported
 F:	Documentation/arch/x86/resctrl*
 F:	arch/x86/include/asm/resctrl.h
 F:	arch/x86/kernel/cpu/resctrl/
+F:	fs/resctrl/
 F:	include/linux/resctrl*.h
 F:	tools/testing/selftests/resctrl/
 
diff --git a/arch/Kconfig b/arch/Kconfig
index 09603e0bc2cc1..cbdb9200284b2 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -1333,6 +1333,14 @@ config STRICT_MODULE_RWX
 config ARCH_HAS_PHYS_TO_DMA
 	bool
 
+config ARCH_HAS_CPU_RESCTRL
+	bool
+	help
+	  An architecture selects this option to indicate that the necessary
+	  hooks are provided to support the common memory system usage
+	  monitoring and control interfaces provided by the 'resctrl'
+	  filesystem (see RESCTRL_FS).
+
 config HAVE_ARCH_COMPILER_H
 	bool
 	help
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e12b82baaef8b..11f1ca432c715 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -482,8 +482,9 @@ config GOLDFISH
 config X86_CPU_RESCTRL
 	bool "x86 CPU resource control support"
 	depends on X86 && (CPU_SUP_INTEL || CPU_SUP_AMD)
-	select KERNFS
-	select PROC_CPU_RESCTRL		if PROC_FS
+	depends on MISC_FILESYSTEMS
+	select ARCH_HAS_CPU_RESCTRL
+	select RESCTRL_FS
 	select RESCTRL_FS_PSEUDO_LOCK
 	help
 	  Enable x86 CPU resource control support.
@@ -501,12 +502,6 @@ config X86_CPU_RESCTRL
 
 	  Say N if unsure.
 
-config RESCTRL_FS_PSEUDO_LOCK
-	bool
-	help
-	  Software mechanism to pin data in a cache portion using
-	  micro-architecture specific knowledge.
-
 if X86_32
 config X86_BIGSMP
 	bool "Support for big SMP systems with more than 8 CPUs"
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 6b3470924984c..6211839942111 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -9,8 +9,6 @@
 #include <linux/jump_label.h>
 #include <linux/tick.h>
 
-#include <asm/resctrl.h>
-
 #define L3_QOS_CDP_ENABLE		0x01ULL
 
 #define L2_QOS_CDP_ENABLE		0x01ULL
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 6d5601e541853..2cfae5146fd1a 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -19,11 +19,11 @@
 
 #include <linux/cpu.h>
 #include <linux/module.h>
+#include <linux/resctrl.h>
 #include <linux/sizes.h>
 #include <linux/slab.h>
 
 #include <asm/cpu_device_id.h>
-#include <asm/resctrl.h>
 
 #include "internal.h"
 
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index 80018fb7bf1a9..d3ff38b56da5c 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -18,12 +18,12 @@
 #include <linux/mman.h>
 #include <linux/perf_event.h>
 #include <linux/pm_qos.h>
+#include <linux/resctrl.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 
 #include <asm/cacheflush.h>
 #include <asm/cpu_device_id.h>
-#include <asm/resctrl.h>
 #include <asm/perf_event.h>
 
 #include "../../events/perf_event.h" /* For X86_CONFIG() */
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index d48078410d771..3a4a0bb70f6a5 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -18,6 +18,7 @@
 #include <linux/fs_parser.h>
 #include <linux/sysfs.h>
 #include <linux/kernfs.h>
+#include <linux/resctrl.h>
 #include <linux/seq_buf.h>
 #include <linux/seq_file.h>
 #include <linux/sched/signal.h>
@@ -28,7 +29,6 @@
 
 #include <uapi/linux/magic.h>
 
-#include <asm/resctrl.h>
 #include "internal.h"
 
 DEFINE_STATIC_KEY_FALSE(rdt_enable_key);
diff --git a/fs/Kconfig b/fs/Kconfig
index 4bb2b0c3d63a2..336ec0a4812bf 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -332,6 +332,7 @@ source "fs/omfs/Kconfig"
 source "fs/hpfs/Kconfig"
 source "fs/qnx4/Kconfig"
 source "fs/qnx6/Kconfig"
+source "fs/resctrl/Kconfig"
 source "fs/romfs/Kconfig"
 source "fs/pstore/Kconfig"
 source "fs/sysv/Kconfig"
diff --git a/fs/Makefile b/fs/Makefile
index f9541f40be4e0..b62375770deed 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -129,3 +129,4 @@ obj-$(CONFIG_EFIVAR_FS)		+= efivarfs/
 obj-$(CONFIG_EROFS_FS)		+= erofs/
 obj-$(CONFIG_VBOXSF_FS)		+= vboxsf/
 obj-$(CONFIG_ZONEFS_FS)		+= zonefs/
+obj-$(CONFIG_RESCTRL_FS)	+= resctrl/
diff --git a/fs/resctrl/Kconfig b/fs/resctrl/Kconfig
new file mode 100644
index 0000000000000..478a8e2ad99ff
--- /dev/null
+++ b/fs/resctrl/Kconfig
@@ -0,0 +1,39 @@
+config RESCTRL_FS
+	bool "CPU Resource Control Filesystem (resctrl)"
+	depends on ARCH_HAS_CPU_RESCTRL
+	select KERNFS
+	select PROC_CPU_RESCTRL if PROC_FS
+	help
+	  Some architectures provide hardware facilities to group tasks and
+	  monitor and control their usage of memory system resources such as
+	  caches and memory bandwidth.  Examples of such facilities include
+	  Intel's Resource Director Technology (Intel(R) RDT) and AMD's
+	  Platform Quality of Service (AMD QoS).
+
+	  If your system has the necessary support and you want to be able to
+	  assign tasks to groups and manipulate the associated resource
+	  monitors and controls from userspace, say Y here to get a mountable
+	  'resctrl' filesystem that lets you do just that.
+
+	  If nothing mounts or prods the 'resctrl' filesystem, resource
+	  controls and monitors are left in a quiescent, permissive state.
+
+	  On architectures where this can be disabled independently, it is
+	  safe to say N.
+
+	  See <file:Documentation/arch/x86/resctrl.rst> for more information.
+
+config RESCTRL_FS_PSEUDO_LOCK
+	bool
+	depends on RESCTRL_FS
+	help
+	  Software mechanism to pin data in a cache portion using
+	  micro-architecture specific knowledge.
+
+config RESCTRL_RMID_DEPENDS_ON_CLOSID
+	bool
+	depends on RESCTRL_FS
+	help
+	  Enabled by the architecture when the RMID values depend on the CLOSID.
+	  This causes the CLOSID allocator to search for CLOSID with clean
+	  RMID.
diff --git a/fs/resctrl/Makefile b/fs/resctrl/Makefile
new file mode 100644
index 0000000000000..e67f34d2236a2
--- /dev/null
+++ b/fs/resctrl/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_RESCTRL_FS)		+= rdtgroup.o ctrlmondata.o monitor.o
+obj-$(CONFIG_RESCTRL_FS_PSEUDO_LOCK)	+= pseudo_lock.o
+
+# To allow define_trace.h's recursive include:
+CFLAGS_monitor.o = -I$(src)
diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c
new file mode 100644
index 0000000000000..e69de29bb2d1d
diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
new file mode 100644
index 0000000000000..e69de29bb2d1d
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
new file mode 100644
index 0000000000000..e69de29bb2d1d
diff --git a/fs/resctrl/monitor_trace.h b/fs/resctrl/monitor_trace.h
new file mode 100644
index 0000000000000..e69de29bb2d1d
diff --git a/fs/resctrl/pseudo_lock.c b/fs/resctrl/pseudo_lock.c
new file mode 100644
index 0000000000000..e69de29bb2d1d
diff --git a/fs/resctrl/pseudo_lock_trace.h b/fs/resctrl/pseudo_lock_trace.h
new file mode 100644
index 0000000000000..e69de29bb2d1d
diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
new file mode 100644
index 0000000000000..e69de29bb2d1d
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index b8f8240050b42..5c7c8bf2c47f9 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -8,6 +8,10 @@
 #include <linux/pid.h>
 #include <linux/resctrl_types.h>
 
+#ifdef CONFIG_ARCH_HAS_CPU_RESCTRL
+#include <asm/resctrl.h>
+#endif
+
 /* CLOSID, RMID value used by the default control group */
 #define RESCTRL_RESERVED_CLOSID		0
 #define RESCTRL_RESERVED_RMID		0

From 126c8b8462cc10feccf6156df09adfd3ec7e405f Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Thu, 15 May 2025 16:58:46 +0000
Subject: [PATCH 078/236] x86/resctrl: Move the filesystem bits to headers
 visible to fs/resctrl

commit 3d95a49b365e06d1b4c4e5a426fdc70449a334f3 upstream.

Once the filesystem parts of resctrl move to fs/resctrl, it cannot rely
on definitions in x86's internal.h.

Move definitions in internal.h that need to be shared between the
filesystem and architecture code to header files that fs/resctrl can
include.

Doing this separately means the filesystem code only moves between files
of the same name, instead of having these changes mixed in too.

Co-developed-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250515165855.31452-17-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/internal.h | 9 ---------
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 5 +++++
 include/linux/resctrl.h                | 3 +++
 include/linux/resctrl_types.h          | 3 +++
 4 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 6211839942111..7006d9f044c3f 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -16,8 +16,6 @@
 #define CQM_LIMBOCHECK_INTERVAL	1000
 
 #define MBM_CNTR_WIDTH_BASE		24
-#define MBM_OVERFLOW_INTERVAL		1000
-#define MAX_MBA_BW			100u
 #define MBA_IS_LINEAR			0x4
 #define MBM_CNTR_WIDTH_OFFSET_AMD	20
 
@@ -399,13 +397,6 @@ extern struct rdtgroup rdtgroup_default;
 extern struct dentry *debugfs_resctrl;
 extern enum resctrl_event_id mba_mbps_default_event;
 
-static inline bool resctrl_arch_get_cdp_enabled(enum resctrl_res_level l)
-{
-	return rdt_resources_all[l].cdp_enabled;
-}
-
-int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable);
-
 void arch_mon_domain_online(struct rdt_resource *r, struct rdt_mon_domain *d);
 
 /* CPUID.(EAX=10H, ECX=ResID=1).EAX */
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 3a4a0bb70f6a5..ac4baf1722694 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -2541,6 +2541,11 @@ int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable)
 	return 0;
 }
 
+bool resctrl_arch_get_cdp_enabled(enum resctrl_res_level l)
+{
+	return rdt_resources_all[l].cdp_enabled;
+}
+
 /*
  * We don't allow rdtgroup directories to be created anywhere
  * except the root directory. Thus when looking for the rdtgroup
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 5c7c8bf2c47f9..b9d1f2916e9cc 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -403,6 +403,9 @@ static inline u32 resctrl_get_config_index(u32 closid,
 	}
 }
 
+bool resctrl_arch_get_cdp_enabled(enum resctrl_res_level l);
+int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable);
+
 /*
  * Update the ctrl_val and apply this config right now.
  * Must be called on one of the domain's CPUs.
diff --git a/include/linux/resctrl_types.h b/include/linux/resctrl_types.h
index 69bf740130ac6..a66e7936943e9 100644
--- a/include/linux/resctrl_types.h
+++ b/include/linux/resctrl_types.h
@@ -7,6 +7,9 @@
 #ifndef __LINUX_RESCTRL_TYPES_H
 #define __LINUX_RESCTRL_TYPES_H
 
+#define MAX_MBA_BW			100u
+#define MBM_OVERFLOW_INTERVAL		1000
+
 /* Reads to Local DRAM Memory */
 #define READS_TO_LOCAL_MEM		BIT(0)
 

From e03b7800654771df17b93f3f7b18d3d4d56647f4 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Thu, 15 May 2025 16:58:47 +0000
Subject: [PATCH 079/236] x86/resctrl: Move enum resctrl_event_id to resctrl.h

commit 7bdb619c7f9f0a7264b2d69ad0472bf2c785e52a upstream.

resctrl_types.h contains common types and constants to enable architectures
to use these types in their definitions within asm/resctrl.h.

enum resctrl_event_id was placed in resctrl_types.h for
resctrl_arch_get_cdp_enabled() and resctrl_arch_set_cdp_enabled(), but
these two functions are no longer inlined by any architecture.

Move enum resctrl_event_id to resctrl.h.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250515165855.31452-18-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 include/linux/resctrl.h       | 10 ++++++++++
 include/linux/resctrl_types.h | 10 ----------
 2 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index b9d1f2916e9cc..5ef972cbf56be 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -48,6 +48,16 @@ int proc_resctrl_show(struct seq_file *m,
 	for_each_rdt_resource((r))					      \
 		if ((r)->mon_capable)
 
+enum resctrl_res_level {
+	RDT_RESOURCE_L3,
+	RDT_RESOURCE_L2,
+	RDT_RESOURCE_MBA,
+	RDT_RESOURCE_SMBA,
+
+	/* Must be the last */
+	RDT_NUM_RESOURCES,
+};
+
 /**
  * enum resctrl_conf_type - The type of configuration.
  * @CDP_NONE:	No prioritisation, both code and data are controlled or monitored.
diff --git a/include/linux/resctrl_types.h b/include/linux/resctrl_types.h
index a66e7936943e9..a25fb9c4070d3 100644
--- a/include/linux/resctrl_types.h
+++ b/include/linux/resctrl_types.h
@@ -34,16 +34,6 @@
 /* Max event bits supported */
 #define MAX_EVT_CONFIG_BITS		GENMASK(6, 0)
 
-enum resctrl_res_level {
-	RDT_RESOURCE_L3,
-	RDT_RESOURCE_L2,
-	RDT_RESOURCE_MBA,
-	RDT_RESOURCE_SMBA,
-
-	/* Must be the last */
-	RDT_NUM_RESOURCES,
-};
-
 /*
  * Event IDs, the values match those used to program IA32_QM_EVTSEL before
  * reading IA32_QM_CTR on RDT systems.

From fa89b62d46e75c5d7d32d24cca1b51bfcf017239 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Thu, 15 May 2025 16:58:48 +0000
Subject: [PATCH 080/236] x86/resctrl: Fix types in
 resctrl_arch_mon_ctx_{alloc,free}() stubs

commit 272ed1c28c9db60b9bd50d49feae463df50b3ef6 upstream.

resctrl_arch_mon_ctx_alloc() and resctrl_arch_mon_ctx_free() take an enum
resctrl_event_id that is already defined in resctrl_types.h to be
accessible to asm/resctrl.h.

The x86 stubs take an int. Fix that.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250515165855.31452-19-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/include/asm/resctrl.h | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h
index 7a39728b07431..a2e20fe90a2ca 100644
--- a/arch/x86/include/asm/resctrl.h
+++ b/arch/x86/include/asm/resctrl.h
@@ -194,14 +194,16 @@ static inline u32 resctrl_arch_rmid_idx_encode(u32 ignored, u32 rmid)
 
 /* x86 can always read an rmid, nothing needs allocating */
 struct rdt_resource;
-static inline void *resctrl_arch_mon_ctx_alloc(struct rdt_resource *r, int evtid)
+static inline void *resctrl_arch_mon_ctx_alloc(struct rdt_resource *r,
+					       enum resctrl_event_id evtid)
 {
 	might_sleep();
 	return NULL;
-};
+}
 
-static inline void resctrl_arch_mon_ctx_free(struct rdt_resource *r, int evtid,
-					     void *ctx) { };
+static inline void resctrl_arch_mon_ctx_free(struct rdt_resource *r,
+					     enum resctrl_event_id evtid,
+					     void *ctx) { }
 
 u64 resctrl_arch_get_prefetch_disable_bits(void);
 int resctrl_arch_pseudo_lock_fn(void *_plr);

From f01dd14513ccc85f4305bab40fa54529eb3e7213 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Thu, 15 May 2025 16:58:49 +0000
Subject: [PATCH 081/236] x86/resctrl: Move pseudo lock prototypes to
 include/linux/resctrl.h

commit 279f225951e3c77a1708d77f557b4cc7bdbd76ed upstream.

The resctrl pseudo-lock feature allows an architecture to allocate data
into particular cache portions, which are then treated as reserved to
avoid that data ever being evicted. Setting this up is deeply architecture
specific as it involves disabling prefetchers etc. It is not possible
to support this kind of feature on arm64. Risc-V is assumed to be the
same.

The prototypes for the architecture code were added to x86's asm/resctrl.h,
with other architectures able to provide stubs for their architecture. This
forces other architectures to provide identical stubs.

Move the prototypes and stubs to linux/resctrl.h, and switch between them
using the existing Kconfig symbol.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250515165855.31452-20-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/include/asm/resctrl.h |  5 -----
 include/linux/resctrl.h        | 13 +++++++++++++
 2 files changed, 13 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h
index a2e20fe90a2ca..ad497ab196d1e 100644
--- a/arch/x86/include/asm/resctrl.h
+++ b/arch/x86/include/asm/resctrl.h
@@ -205,11 +205,6 @@ static inline void resctrl_arch_mon_ctx_free(struct rdt_resource *r,
 					     enum resctrl_event_id evtid,
 					     void *ctx) { }
 
-u64 resctrl_arch_get_prefetch_disable_bits(void);
-int resctrl_arch_pseudo_lock_fn(void *_plr);
-int resctrl_arch_measure_cycles_lat_fn(void *_plr);
-int resctrl_arch_measure_l2_residency(void *_plr);
-int resctrl_arch_measure_l3_residency(void *_plr);
 void resctrl_cpu_detect(struct cpuinfo_x86 *c);
 
 #else
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 5ef972cbf56be..9ba771f2ddead 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -534,4 +534,17 @@ extern unsigned int resctrl_rmid_realloc_limit;
 int resctrl_init(void);
 void resctrl_exit(void);
 
+#ifdef CONFIG_RESCTRL_FS_PSEUDO_LOCK
+u64 resctrl_arch_get_prefetch_disable_bits(void);
+int resctrl_arch_pseudo_lock_fn(void *_plr);
+int resctrl_arch_measure_cycles_lat_fn(void *_plr);
+int resctrl_arch_measure_l2_residency(void *_plr);
+int resctrl_arch_measure_l3_residency(void *_plr);
+#else
+static inline u64 resctrl_arch_get_prefetch_disable_bits(void) { return 0; }
+static inline int resctrl_arch_pseudo_lock_fn(void *_plr) { return 0; }
+static inline int resctrl_arch_measure_cycles_lat_fn(void *_plr) { return 0; }
+static inline int resctrl_arch_measure_l2_residency(void *_plr) { return 0; }
+static inline int resctrl_arch_measure_l3_residency(void *_plr) { return 0; }
+#endif /* CONFIG_RESCTRL_FS_PSEUDO_LOCK */
 #endif /* _RESCTRL_H */

From d53755701ea60d7760ce6d95999bceb5ca925362 Mon Sep 17 00:00:00 2001
From: Dave Martin <Dave.Martin@arm.com>
Date: Thu, 15 May 2025 16:58:50 +0000
Subject: [PATCH 082/236] x86/resctrl: Squelch whitespace anomalies in resctrl
 core code

commit 556f48a5093b1edb1b8a594af633303269dec329 upstream.

checkpatch.pl complains about some whitespace anomalies in the
resctrl core code.

This doesn't matter, but since this code is about to be factored
out and made generic, this is a good opportunity to fix these
issues and so reduce future checkpatch fuzz.

Fix them.

No functional change.

Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250515165855.31452-21-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index ac4baf1722694..02c5f626bce1a 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -1024,7 +1024,7 @@ static int rdt_num_closids_show(struct kernfs_open_file *of,
 }
 
 static int rdt_default_ctrl_show(struct kernfs_open_file *of,
-			     struct seq_file *seq, void *v)
+				 struct seq_file *seq, void *v)
 {
 	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
 	struct rdt_resource *r = s->res;
@@ -1034,7 +1034,7 @@ static int rdt_default_ctrl_show(struct kernfs_open_file *of,
 }
 
 static int rdt_min_cbm_bits_show(struct kernfs_open_file *of,
-			     struct seq_file *seq, void *v)
+				 struct seq_file *seq, void *v)
 {
 	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
 	struct rdt_resource *r = s->res;
@@ -1150,7 +1150,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
 }
 
 static int rdt_min_bw_show(struct kernfs_open_file *of,
-			     struct seq_file *seq, void *v)
+			   struct seq_file *seq, void *v)
 {
 	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
 	struct rdt_resource *r = s->res;
@@ -1185,7 +1185,7 @@ static int rdt_mon_features_show(struct kernfs_open_file *of,
 }
 
 static int rdt_bw_gran_show(struct kernfs_open_file *of,
-			     struct seq_file *seq, void *v)
+			    struct seq_file *seq, void *v)
 {
 	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
 	struct rdt_resource *r = s->res;
@@ -1195,7 +1195,7 @@ static int rdt_bw_gran_show(struct kernfs_open_file *of,
 }
 
 static int rdt_delay_linear_show(struct kernfs_open_file *of,
-			     struct seq_file *seq, void *v)
+				 struct seq_file *seq, void *v)
 {
 	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
 	struct rdt_resource *r = s->res;
@@ -2068,7 +2068,6 @@ static struct rftype res_common_files[] = {
 		.seq_show	= rdtgroup_closid_show,
 		.fflags		= RFTYPE_CTRL_BASE | RFTYPE_DEBUG,
 	},
-
 };
 
 static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags)
@@ -3628,7 +3627,6 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
 			rdt_last_cmd_puts("Failed to initialize allocations\n");
 			goto out;
 		}
-
 	}
 
 	rdtgrp->mode = RDT_MODE_SHAREABLE;

From e2951468b26d24de09e9ed2e34a19453dfc3b916 Mon Sep 17 00:00:00 2001
From: Dave Martin <Dave.Martin@arm.com>
Date: Thu, 15 May 2025 16:58:51 +0000
Subject: [PATCH 083/236] x86/resctrl: Prefer alloc(sizeof(*foo)) idiom in
 rdt_init_fs_context()

commit df3dc0efcc01d6aae8ebd3e479fe0d55f894854b upstream.

rdt_init_fs_context() sizes a typed allocation using an explicit
sizeof(type) expression, which checkpatch.pl complains about.

Since this code is about to be factored out and made generic, this
is a good opportunity to fix the code to size the allocation based
on the target pointer instead, to reduce the chance of future mis-
maintenance.

Fix it.

No functional change.

Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250515165855.31452-22-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 02c5f626bce1a..ace86b6dcedec 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -2951,7 +2951,7 @@ static int rdt_init_fs_context(struct fs_context *fc)
 {
 	struct rdt_fs_context *ctx;
 
-	ctx = kzalloc(sizeof(struct rdt_fs_context), GFP_KERNEL);
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
 

From 62666fef9162f215e450865c3a026e5973fdd051 Mon Sep 17 00:00:00 2001
From: Dave Martin <Dave.Martin@arm.com>
Date: Thu, 15 May 2025 16:58:52 +0000
Subject: [PATCH 084/236] x86/resctrl: Relax some asm #includes

commit b7b57edbf5681c7d0ed504a3a4e912bb68661ab9 upstream.

checkpatch.pl identifies some direct #includes of asm headers that
can be satisfied by including the corresponding <linux/...> header
instead.

Fix them.

No intentional functional change.

Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Amit Singh Tomar <amitsinght@marvell.com> # arm64
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com> # arm64
Tested-by: Babu Moger <babu.moger@amd.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250515165855.31452-23-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index d3ff38b56da5c..5698d7d273900 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -11,6 +11,8 @@
 
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
+#include <linux/cacheflush.h>
+#include <linux/cacheinfo.h>
 #include <linux/cpu.h>
 #include <linux/cpumask.h>
 #include <linux/debugfs.h>
@@ -22,7 +24,6 @@
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 
-#include <asm/cacheflush.h>
 #include <asm/cpu_device_id.h>
 #include <asm/perf_event.h>
 

From aa551cb9ffd34e6bdaea2b4eb768aaf57539d511 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Thu, 15 May 2025 16:58:53 +0000
Subject: [PATCH 085/236] x86/resctrl: Always initialise rid field in
 rdt_resources_all[]

commit f6b25be204b8661e4c32fa770a4c9e3a113ee325 upstream.

x86 has an array, rdt_resources_all[], of all possible resources.
The for-each-resource walkers depend on the rid field of all
resources being initialised.

If the array ever grows due to another architecture adding a resource
type that is not defined on x86, the for-each-resources walkers will
loop forever.

Initialise all the rid values in resctrl_arch_late_init() before
any for-each-resource walker can be called.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250515165855.31452-24-james.morse@arm.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index ced1ce11e7b02..d0f69c8623d73 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -60,7 +60,6 @@ struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESOURCES] = {
 	[RDT_RESOURCE_L3] =
 	{
 		.r_resctrl = {
-			.rid			= RDT_RESOURCE_L3,
 			.name			= "L3",
 			.ctrl_scope		= RESCTRL_L3_CACHE,
 			.mon_scope		= RESCTRL_L3_CACHE,
@@ -74,7 +73,6 @@ struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESOURCES] = {
 	[RDT_RESOURCE_L2] =
 	{
 		.r_resctrl = {
-			.rid			= RDT_RESOURCE_L2,
 			.name			= "L2",
 			.ctrl_scope		= RESCTRL_L2_CACHE,
 			.ctrl_domains		= ctrl_domain_init(RDT_RESOURCE_L2),
@@ -86,7 +84,6 @@ struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESOURCES] = {
 	[RDT_RESOURCE_MBA] =
 	{
 		.r_resctrl = {
-			.rid			= RDT_RESOURCE_MBA,
 			.name			= "MB",
 			.ctrl_scope		= RESCTRL_L3_CACHE,
 			.ctrl_domains		= ctrl_domain_init(RDT_RESOURCE_MBA),
@@ -96,7 +93,6 @@ struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESOURCES] = {
 	[RDT_RESOURCE_SMBA] =
 	{
 		.r_resctrl = {
-			.rid			= RDT_RESOURCE_SMBA,
 			.name			= "SMBA",
 			.ctrl_scope		= RESCTRL_L3_CACHE,
 			.ctrl_domains		= ctrl_domain_init(RDT_RESOURCE_SMBA),
@@ -1009,7 +1005,11 @@ void resctrl_cpu_detect(struct cpuinfo_x86 *c)
 static int __init resctrl_arch_late_init(void)
 {
 	struct rdt_resource *r;
-	int state, ret;
+	int state, ret, i;
+
+	/* for_each_rdt_resource() requires all rid to be initialised. */
+	for (i = 0; i < RDT_NUM_RESOURCES; i++)
+		rdt_resources_all[i].r_resctrl.rid = i;
 
 	/*
 	 * Initialize functions(or definitions) that are different

From a8ccae7ed0651708564b0f97a981b2267699e2d0 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Thu, 15 May 2025 16:58:54 +0000
Subject: [PATCH 086/236] x86,fs/resctrl: Move the resctrl filesystem code to
 live in /fs/resctrl

commit 7168ae330e8105296210b2b2d31d791d5c073345 upstream.

Resctrl is a filesystem interface to hardware that provides cache
allocation policy and bandwidth control for groups of tasks or CPUs.

To support more than one architecture, resctrl needs to live in /fs/.

Move the code that is concerned with the filesystem interface to
/fs/resctrl.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Fenghua Yu <fenghuay@nvidia.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250515165855.31452-25-james.morse@arm.com

 Conflicts:
	arch/x86/kernel/cpu/resctrl/pseudo_lock.c
[jz: keep .llseek in pseudo_lock_dev_fops because cb787f4ac0c2
     ("[tree-wide] finally take no_llseek out") not backported]
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 Documentation/arch/x86/index.rst              |    1 -
 Documentation/filesystems/index.rst           |    1 +
 .../{arch/x86 => filesystems}/resctrl.rst     |    0
 MAINTAINERS                                   |    2 +-
 arch/x86/kernel/cpu/resctrl/Makefile          |    1 -
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c     |  641 ---
 arch/x86/kernel/cpu/resctrl/internal.h        |  371 +-
 arch/x86/kernel/cpu/resctrl/monitor.c         |  909 +---
 arch/x86/kernel/cpu/resctrl/monitor_trace.h   |   31 -
 arch/x86/kernel/cpu/resctrl/pseudo_lock.c     | 1088 +---
 .../kernel/cpu/resctrl/pseudo_lock_trace.h    |    2 +
 arch/x86/kernel/cpu/resctrl/rdtgroup.c        | 4597 +----------------
 fs/resctrl/Kconfig                            |    2 +-
 fs/resctrl/ctrlmondata.c                      |  661 +++
 fs/resctrl/internal.h                         |  426 ++
 fs/resctrl/monitor.c                          |  929 ++++
 fs/resctrl/monitor_trace.h                    |   33 +
 fs/resctrl/pseudo_lock.c                      | 1106 ++++
 fs/resctrl/pseudo_lock_trace.h                |    0
 fs/resctrl/rdtgroup.c                         | 4353 ++++++++++++++++
 20 files changed, 7664 insertions(+), 7490 deletions(-)
 rename Documentation/{arch/x86 => filesystems}/resctrl.rst (100%)
 delete mode 100644 arch/x86/kernel/cpu/resctrl/monitor_trace.h
 delete mode 100644 fs/resctrl/pseudo_lock_trace.h

diff --git a/Documentation/arch/x86/index.rst b/Documentation/arch/x86/index.rst
index 8ac64d7de4dc9..00f9a99689fb8 100644
--- a/Documentation/arch/x86/index.rst
+++ b/Documentation/arch/x86/index.rst
@@ -31,7 +31,6 @@ x86-specific Documentation
    pti
    mds
    microcode
-   resctrl
    tsx_async_abort
    buslock
    usb-legacy-support
diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst
index 09cade7eaefc8..f9e388fd8d000 100644
--- a/Documentation/filesystems/index.rst
+++ b/Documentation/filesystems/index.rst
@@ -109,6 +109,7 @@ Documentation for filesystem implementations.
    qnx6
    ramfs-rootfs-initramfs
    relay
+   resctrl
    romfs
    smb/index
    spufs/index
diff --git a/Documentation/arch/x86/resctrl.rst b/Documentation/filesystems/resctrl.rst
similarity index 100%
rename from Documentation/arch/x86/resctrl.rst
rename to Documentation/filesystems/resctrl.rst
diff --git a/MAINTAINERS b/MAINTAINERS
index 0cb3eab30f9f6..197994517db89 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -18108,7 +18108,7 @@ M:	Fenghua Yu <fenghua.yu@intel.com>
 M:	Reinette Chatre <reinette.chatre@intel.com>
 L:	linux-kernel@vger.kernel.org
 S:	Supported
-F:	Documentation/arch/x86/resctrl*
+F:	Documentation/filesystems/resctrl.rst
 F:	arch/x86/include/asm/resctrl.h
 F:	arch/x86/kernel/cpu/resctrl/
 F:	fs/resctrl/
diff --git a/arch/x86/kernel/cpu/resctrl/Makefile b/arch/x86/kernel/cpu/resctrl/Makefile
index 909be78ec6dac..d8a04b195da21 100644
--- a/arch/x86/kernel/cpu/resctrl/Makefile
+++ b/arch/x86/kernel/cpu/resctrl/Makefile
@@ -5,4 +5,3 @@ obj-$(CONFIG_RESCTRL_FS_PSEUDO_LOCK)	+= pseudo_lock.o
 
 # To allow define_trace.h's recursive include:
 CFLAGS_pseudo_lock.o = -I$(src)
-CFLAGS_monitor.o = -I$(src)
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 110b534d400c7..1189c0df4ad76 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -16,277 +16,9 @@
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
 #include <linux/cpu.h>
-#include <linux/kernfs.h>
-#include <linux/seq_file.h>
-#include <linux/slab.h>
-#include <linux/tick.h>
 
 #include "internal.h"
 
-struct rdt_parse_data {
-	struct rdtgroup		*rdtgrp;
-	char			*buf;
-};
-
-typedef int (ctrlval_parser_t)(struct rdt_parse_data *data,
-			       struct resctrl_schema *s,
-			       struct rdt_ctrl_domain *d);
-
-/*
- * Check whether MBA bandwidth percentage value is correct. The value is
- * checked against the minimum and max bandwidth values specified by the
- * hardware. The allocated bandwidth percentage is rounded to the next
- * control step available on the hardware.
- */
-static bool bw_validate(char *buf, u32 *data, struct rdt_resource *r)
-{
-	int ret;
-	u32 bw;
-
-	/*
-	 * Only linear delay values is supported for current Intel SKUs.
-	 */
-	if (!r->membw.delay_linear && r->membw.arch_needs_linear) {
-		rdt_last_cmd_puts("No support for non-linear MB domains\n");
-		return false;
-	}
-
-	ret = kstrtou32(buf, 10, &bw);
-	if (ret) {
-		rdt_last_cmd_printf("Invalid MB value %s\n", buf);
-		return false;
-	}
-
-	/* Nothing else to do if software controller is enabled. */
-	if (is_mba_sc(r)) {
-		*data = bw;
-		return true;
-	}
-
-	if (bw < r->membw.min_bw || bw > r->membw.max_bw) {
-		rdt_last_cmd_printf("MB value %u out of range [%d,%d]\n",
-				    bw, r->membw.min_bw, r->membw.max_bw);
-		return false;
-	}
-
-	*data = roundup(bw, (unsigned long)r->membw.bw_gran);
-	return true;
-}
-
-static int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s,
-		    struct rdt_ctrl_domain *d)
-{
-	struct resctrl_staged_config *cfg;
-	u32 closid = data->rdtgrp->closid;
-	struct rdt_resource *r = s->res;
-	u32 bw_val;
-
-	cfg = &d->staged_config[s->conf_type];
-	if (cfg->have_new_ctrl) {
-		rdt_last_cmd_printf("Duplicate domain %d\n", d->hdr.id);
-		return -EINVAL;
-	}
-
-	if (!bw_validate(data->buf, &bw_val, r))
-		return -EINVAL;
-
-	if (is_mba_sc(r)) {
-		d->mbps_val[closid] = bw_val;
-		return 0;
-	}
-
-	cfg->new_ctrl = bw_val;
-	cfg->have_new_ctrl = true;
-
-	return 0;
-}
-
-/*
- * Check whether a cache bit mask is valid.
- * On Intel CPUs, non-contiguous 1s value support is indicated by CPUID:
- *   - CPUID.0x10.1:ECX[3]: L3 non-contiguous 1s value supported if 1
- *   - CPUID.0x10.2:ECX[3]: L2 non-contiguous 1s value supported if 1
- *
- * Haswell does not support a non-contiguous 1s value and additionally
- * requires at least two bits set.
- * AMD allows non-contiguous bitmasks.
- */
-static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
-{
-	u32 supported_bits = BIT_MASK(r->cache.cbm_len) - 1;
-	unsigned int cbm_len = r->cache.cbm_len;
-	unsigned long first_bit, zero_bit, val;
-	int ret;
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret) {
-		rdt_last_cmd_printf("Non-hex character in the mask %s\n", buf);
-		return false;
-	}
-
-	if ((r->cache.min_cbm_bits > 0 && val == 0) || val > supported_bits) {
-		rdt_last_cmd_puts("Mask out of range\n");
-		return false;
-	}
-
-	first_bit = find_first_bit(&val, cbm_len);
-	zero_bit = find_next_zero_bit(&val, cbm_len, first_bit);
-
-	/* Are non-contiguous bitmasks allowed? */
-	if (!r->cache.arch_has_sparse_bitmasks &&
-	    (find_next_bit(&val, cbm_len, zero_bit) < cbm_len)) {
-		rdt_last_cmd_printf("The mask %lx has non-consecutive 1-bits\n", val);
-		return false;
-	}
-
-	if ((zero_bit - first_bit) < r->cache.min_cbm_bits) {
-		rdt_last_cmd_printf("Need at least %d bits in the mask\n",
-				    r->cache.min_cbm_bits);
-		return false;
-	}
-
-	*data = val;
-	return true;
-}
-
-/*
- * Read one cache bit mask (hex). Check that it is valid for the current
- * resource type.
- */
-static int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s,
-		     struct rdt_ctrl_domain *d)
-{
-	struct rdtgroup *rdtgrp = data->rdtgrp;
-	struct resctrl_staged_config *cfg;
-	struct rdt_resource *r = s->res;
-	u32 cbm_val;
-
-	cfg = &d->staged_config[s->conf_type];
-	if (cfg->have_new_ctrl) {
-		rdt_last_cmd_printf("Duplicate domain %d\n", d->hdr.id);
-		return -EINVAL;
-	}
-
-	/*
-	 * Cannot set up more than one pseudo-locked region in a cache
-	 * hierarchy.
-	 */
-	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
-	    rdtgroup_pseudo_locked_in_hierarchy(d)) {
-		rdt_last_cmd_puts("Pseudo-locked region in hierarchy\n");
-		return -EINVAL;
-	}
-
-	if (!cbm_validate(data->buf, &cbm_val, r))
-		return -EINVAL;
-
-	if ((rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
-	     rdtgrp->mode == RDT_MODE_SHAREABLE) &&
-	    rdtgroup_cbm_overlaps_pseudo_locked(d, cbm_val)) {
-		rdt_last_cmd_puts("CBM overlaps with pseudo-locked region\n");
-		return -EINVAL;
-	}
-
-	/*
-	 * The CBM may not overlap with the CBM of another closid if
-	 * either is exclusive.
-	 */
-	if (rdtgroup_cbm_overlaps(s, d, cbm_val, rdtgrp->closid, true)) {
-		rdt_last_cmd_puts("Overlaps with exclusive group\n");
-		return -EINVAL;
-	}
-
-	if (rdtgroup_cbm_overlaps(s, d, cbm_val, rdtgrp->closid, false)) {
-		if (rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
-		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
-			rdt_last_cmd_puts("Overlaps with other group\n");
-			return -EINVAL;
-		}
-	}
-
-	cfg->new_ctrl = cbm_val;
-	cfg->have_new_ctrl = true;
-
-	return 0;
-}
-
-/*
- * For each domain in this resource we expect to find a series of:
- *	id=mask
- * separated by ";". The "id" is in decimal, and must match one of
- * the "id"s for this resource.
- */
-static int parse_line(char *line, struct resctrl_schema *s,
-		      struct rdtgroup *rdtgrp)
-{
-	enum resctrl_conf_type t = s->conf_type;
-	ctrlval_parser_t *parse_ctrlval = NULL;
-	struct resctrl_staged_config *cfg;
-	struct rdt_resource *r = s->res;
-	struct rdt_parse_data data;
-	struct rdt_ctrl_domain *d;
-	char *dom = NULL, *id;
-	unsigned long dom_id;
-
-	/* Walking r->domains, ensure it can't race with cpuhp */
-	lockdep_assert_cpus_held();
-
-	switch (r->schema_fmt) {
-	case RESCTRL_SCHEMA_BITMAP:
-		parse_ctrlval = &parse_cbm;
-		break;
-	case RESCTRL_SCHEMA_RANGE:
-		parse_ctrlval = &parse_bw;
-		break;
-	}
-
-	if (WARN_ON_ONCE(!parse_ctrlval))
-		return -EINVAL;
-
-	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
-	    (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)) {
-		rdt_last_cmd_puts("Cannot pseudo-lock MBA resource\n");
-		return -EINVAL;
-	}
-
-next:
-	if (!line || line[0] == '\0')
-		return 0;
-	dom = strsep(&line, ";");
-	id = strsep(&dom, "=");
-	if (!dom || kstrtoul(id, 10, &dom_id)) {
-		rdt_last_cmd_puts("Missing '=' or non-numeric domain\n");
-		return -EINVAL;
-	}
-	dom = strim(dom);
-	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
-		if (d->hdr.id == dom_id) {
-			data.buf = dom;
-			data.rdtgrp = rdtgrp;
-			if (parse_ctrlval(&data, s, d))
-				return -EINVAL;
-			if (rdtgrp->mode ==  RDT_MODE_PSEUDO_LOCKSETUP) {
-				cfg = &d->staged_config[t];
-				/*
-				 * In pseudo-locking setup mode and just
-				 * parsed a valid CBM that should be
-				 * pseudo-locked. Only one locked region per
-				 * resource group and domain so just do
-				 * the required initialization for single
-				 * region and return.
-				 */
-				rdtgrp->plr->s = s;
-				rdtgrp->plr->d = d;
-				rdtgrp->plr->cbm = cfg->new_ctrl;
-				d->plr = rdtgrp->plr;
-				return 0;
-			}
-			goto next;
-		}
-	}
-	return -EINVAL;
-}
-
 int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_ctrl_domain *d,
 			    u32 closid, enum resctrl_conf_type t, u32 cfg_val)
 {
@@ -351,100 +83,6 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 	return 0;
 }
 
-static int rdtgroup_parse_resource(char *resname, char *tok,
-				   struct rdtgroup *rdtgrp)
-{
-	struct resctrl_schema *s;
-
-	list_for_each_entry(s, &resctrl_schema_all, list) {
-		if (!strcmp(resname, s->name) && rdtgrp->closid < s->num_closid)
-			return parse_line(tok, s, rdtgrp);
-	}
-	rdt_last_cmd_printf("Unknown or unsupported resource name '%s'\n", resname);
-	return -EINVAL;
-}
-
-ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
-				char *buf, size_t nbytes, loff_t off)
-{
-	struct resctrl_schema *s;
-	struct rdtgroup *rdtgrp;
-	struct rdt_resource *r;
-	char *tok, *resname;
-	int ret = 0;
-
-	/* Valid input requires a trailing newline */
-	if (nbytes == 0 || buf[nbytes - 1] != '\n')
-		return -EINVAL;
-	buf[nbytes - 1] = '\0';
-
-	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-	if (!rdtgrp) {
-		rdtgroup_kn_unlock(of->kn);
-		return -ENOENT;
-	}
-	rdt_last_cmd_clear();
-
-	/*
-	 * No changes to pseudo-locked region allowed. It has to be removed
-	 * and re-created instead.
-	 */
-	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
-		ret = -EINVAL;
-		rdt_last_cmd_puts("Resource group is pseudo-locked\n");
-		goto out;
-	}
-
-	rdt_staged_configs_clear();
-
-	while ((tok = strsep(&buf, "\n")) != NULL) {
-		resname = strim(strsep(&tok, ":"));
-		if (!tok) {
-			rdt_last_cmd_puts("Missing ':'\n");
-			ret = -EINVAL;
-			goto out;
-		}
-		if (tok[0] == '\0') {
-			rdt_last_cmd_printf("Missing '%s' value\n", resname);
-			ret = -EINVAL;
-			goto out;
-		}
-		ret = rdtgroup_parse_resource(resname, tok, rdtgrp);
-		if (ret)
-			goto out;
-	}
-
-	list_for_each_entry(s, &resctrl_schema_all, list) {
-		r = s->res;
-
-		/*
-		 * Writes to mba_sc resources update the software controller,
-		 * not the control MSR.
-		 */
-		if (is_mba_sc(r))
-			continue;
-
-		ret = resctrl_arch_update_domains(r, rdtgrp->closid);
-		if (ret)
-			goto out;
-	}
-
-	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
-		/*
-		 * If pseudo-locking fails we keep the resource group in
-		 * mode RDT_MODE_PSEUDO_LOCKSETUP with its class of service
-		 * active and updated for just the domain the pseudo-locked
-		 * region was requested for.
-		 */
-		ret = rdtgroup_pseudo_lock_create(rdtgrp);
-	}
-
-out:
-	rdt_staged_configs_clear();
-	rdtgroup_kn_unlock(of->kn);
-	return ret ?: nbytes;
-}
-
 u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_ctrl_domain *d,
 			    u32 closid, enum resctrl_conf_type type)
 {
@@ -453,282 +91,3 @@ u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_ctrl_domain *d,
 
 	return hw_dom->ctrl_val[idx];
 }
-
-static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int closid)
-{
-	struct rdt_resource *r = schema->res;
-	struct rdt_ctrl_domain *dom;
-	bool sep = false;
-	u32 ctrl_val;
-
-	/* Walking r->domains, ensure it can't race with cpuhp */
-	lockdep_assert_cpus_held();
-
-	seq_printf(s, "%*s:", max_name_width, schema->name);
-	list_for_each_entry(dom, &r->ctrl_domains, hdr.list) {
-		if (sep)
-			seq_puts(s, ";");
-
-		if (is_mba_sc(r))
-			ctrl_val = dom->mbps_val[closid];
-		else
-			ctrl_val = resctrl_arch_get_config(r, dom, closid,
-							   schema->conf_type);
-
-		seq_printf(s, schema->fmt_str, dom->hdr.id, ctrl_val);
-		sep = true;
-	}
-	seq_puts(s, "\n");
-}
-
-int rdtgroup_schemata_show(struct kernfs_open_file *of,
-			   struct seq_file *s, void *v)
-{
-	struct resctrl_schema *schema;
-	struct rdtgroup *rdtgrp;
-	int ret = 0;
-	u32 closid;
-
-	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-	if (rdtgrp) {
-		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
-			list_for_each_entry(schema, &resctrl_schema_all, list) {
-				seq_printf(s, "%s:uninitialized\n", schema->name);
-			}
-		} else if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
-			if (!rdtgrp->plr->d) {
-				rdt_last_cmd_clear();
-				rdt_last_cmd_puts("Cache domain offline\n");
-				ret = -ENODEV;
-			} else {
-				seq_printf(s, "%s:%d=%x\n",
-					   rdtgrp->plr->s->res->name,
-					   rdtgrp->plr->d->hdr.id,
-					   rdtgrp->plr->cbm);
-			}
-		} else {
-			closid = rdtgrp->closid;
-			list_for_each_entry(schema, &resctrl_schema_all, list) {
-				if (closid < schema->num_closid)
-					show_doms(s, schema, closid);
-			}
-		}
-	} else {
-		ret = -ENOENT;
-	}
-	rdtgroup_kn_unlock(of->kn);
-	return ret;
-}
-
-static int smp_mon_event_count(void *arg)
-{
-	mon_event_count(arg);
-
-	return 0;
-}
-
-ssize_t rdtgroup_mba_mbps_event_write(struct kernfs_open_file *of,
-				      char *buf, size_t nbytes, loff_t off)
-{
-	struct rdtgroup *rdtgrp;
-	int ret = 0;
-
-	/* Valid input requires a trailing newline */
-	if (nbytes == 0 || buf[nbytes - 1] != '\n')
-		return -EINVAL;
-	buf[nbytes - 1] = '\0';
-
-	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-	if (!rdtgrp) {
-		rdtgroup_kn_unlock(of->kn);
-		return -ENOENT;
-	}
-	rdt_last_cmd_clear();
-
-	if (!strcmp(buf, "mbm_local_bytes")) {
-		if (resctrl_arch_is_mbm_local_enabled())
-			rdtgrp->mba_mbps_event = QOS_L3_MBM_LOCAL_EVENT_ID;
-		else
-			ret = -EINVAL;
-	} else if (!strcmp(buf, "mbm_total_bytes")) {
-		if (resctrl_arch_is_mbm_total_enabled())
-			rdtgrp->mba_mbps_event = QOS_L3_MBM_TOTAL_EVENT_ID;
-		else
-			ret = -EINVAL;
-	} else {
-		ret = -EINVAL;
-	}
-
-	if (ret)
-		rdt_last_cmd_printf("Unsupported event id '%s'\n", buf);
-
-	rdtgroup_kn_unlock(of->kn);
-
-	return ret ?: nbytes;
-}
-
-int rdtgroup_mba_mbps_event_show(struct kernfs_open_file *of,
-				 struct seq_file *s, void *v)
-{
-	struct rdtgroup *rdtgrp;
-	int ret = 0;
-
-	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-
-	if (rdtgrp) {
-		switch (rdtgrp->mba_mbps_event) {
-		case QOS_L3_MBM_LOCAL_EVENT_ID:
-			seq_puts(s, "mbm_local_bytes\n");
-			break;
-		case QOS_L3_MBM_TOTAL_EVENT_ID:
-			seq_puts(s, "mbm_total_bytes\n");
-			break;
-		default:
-			pr_warn_once("Bad event %d\n", rdtgrp->mba_mbps_event);
-			ret = -EINVAL;
-			break;
-		}
-	} else {
-		ret = -ENOENT;
-	}
-
-	rdtgroup_kn_unlock(of->kn);
-
-	return ret;
-}
-
-struct rdt_domain_hdr *resctrl_find_domain(struct list_head *h, int id,
-					   struct list_head **pos)
-{
-	struct rdt_domain_hdr *d;
-	struct list_head *l;
-
-	list_for_each(l, h) {
-		d = list_entry(l, struct rdt_domain_hdr, list);
-		/* When id is found, return its domain. */
-		if (id == d->id)
-			return d;
-		/* Stop searching when finding id's position in sorted list. */
-		if (id < d->id)
-			break;
-	}
-
-	if (pos)
-		*pos = l;
-
-	return NULL;
-}
-
-void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
-		    struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
-		    cpumask_t *cpumask, int evtid, int first)
-{
-	int cpu;
-
-	/* When picking a CPU from cpu_mask, ensure it can't race with cpuhp */
-	lockdep_assert_cpus_held();
-
-	/*
-	 * Setup the parameters to pass to mon_event_count() to read the data.
-	 */
-	rr->rgrp = rdtgrp;
-	rr->evtid = evtid;
-	rr->r = r;
-	rr->d = d;
-	rr->first = first;
-	rr->arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, evtid);
-	if (IS_ERR(rr->arch_mon_ctx)) {
-		rr->err = -EINVAL;
-		return;
-	}
-
-	cpu = cpumask_any_housekeeping(cpumask, RESCTRL_PICK_ANY_CPU);
-
-	/*
-	 * cpumask_any_housekeeping() prefers housekeeping CPUs, but
-	 * are all the CPUs nohz_full? If yes, pick a CPU to IPI.
-	 * MPAM's resctrl_arch_rmid_read() is unable to read the
-	 * counters on some platforms if its called in IRQ context.
-	 */
-	if (tick_nohz_full_cpu(cpu))
-		smp_call_function_any(cpumask, mon_event_count, rr, 1);
-	else
-		smp_call_on_cpu(cpu, smp_mon_event_count, rr, false);
-
-	resctrl_arch_mon_ctx_free(r, evtid, rr->arch_mon_ctx);
-}
-
-int rdtgroup_mondata_show(struct seq_file *m, void *arg)
-{
-	struct kernfs_open_file *of = m->private;
-	enum resctrl_res_level resid;
-	enum resctrl_event_id evtid;
-	struct rdt_domain_hdr *hdr;
-	struct rmid_read rr = {0};
-	struct rdt_mon_domain *d;
-	struct rdtgroup *rdtgrp;
-	struct rdt_resource *r;
-	struct mon_data *md;
-	int domid, ret = 0;
-
-	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-	if (!rdtgrp) {
-		ret = -ENOENT;
-		goto out;
-	}
-
-	md = of->kn->priv;
-	if (WARN_ON_ONCE(!md)) {
-		ret = -EIO;
-		goto out;
-	}
-
-	resid = md->rid;
-	domid = md->domid;
-	evtid = md->evtid;
-	r = resctrl_arch_get_resource(resid);
-
-	if (md->sum) {
-		/*
-		 * This file requires summing across all domains that share
-		 * the L3 cache id that was provided in the "domid" field of the
-		 * struct mon_data. Search all domains in the resource for
-		 * one that matches this cache id.
-		 */
-		list_for_each_entry(d, &r->mon_domains, hdr.list) {
-			if (d->ci->id == domid) {
-				rr.ci = d->ci;
-				mon_event_read(&rr, r, NULL, rdtgrp,
-					       &d->ci->shared_cpu_map, evtid, false);
-				goto checkresult;
-			}
-		}
-		ret = -ENOENT;
-		goto out;
-	} else {
-		/*
-		 * This file provides data from a single domain. Search
-		 * the resource to find the domain with "domid".
-		 */
-		hdr = resctrl_find_domain(&r->mon_domains, domid, NULL);
-		if (!hdr || WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN)) {
-			ret = -ENOENT;
-			goto out;
-		}
-		d = container_of(hdr, struct rdt_mon_domain, hdr);
-		mon_event_read(&rr, r, d, rdtgrp, &d->hdr.cpu_mask, evtid, false);
-	}
-
-checkresult:
-
-	if (rr.err == -EIO)
-		seq_puts(m, "Error\n");
-	else if (rr.err == -EINVAL)
-		seq_puts(m, "Unavailable\n");
-	else
-		seq_printf(m, "%llu\n", rr.val);
-
-out:
-	rdtgroup_kn_unlock(of->kn);
-	return ret;
-}
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 7006d9f044c3f..62f2693fd34fb 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -3,27 +3,24 @@
 #define _ASM_X86_RESCTRL_INTERNAL_H
 
 #include <linux/resctrl.h>
-#include <linux/sched.h>
-#include <linux/kernfs.h>
-#include <linux/fs_context.h>
-#include <linux/jump_label.h>
-#include <linux/tick.h>
 
 #define L3_QOS_CDP_ENABLE		0x01ULL
 
 #define L2_QOS_CDP_ENABLE		0x01ULL
 
-#define CQM_LIMBOCHECK_INTERVAL	1000
-
 #define MBM_CNTR_WIDTH_BASE		24
+
 #define MBA_IS_LINEAR			0x4
+
 #define MBM_CNTR_WIDTH_OFFSET_AMD	20
 
 /* Hygon MBM counter width as an offset from MBM_CNTR_WIDTH_BASE */
 #define MBM_CNTR_WIDTH_OFFSET_HYGON	8
 
 #define RMID_VAL_ERROR			BIT_ULL(63)
+
 #define RMID_VAL_UNAVAIL		BIT_ULL(62)
+
 /*
  * With the above fields in use 62 bits remain in MSR_IA32_QM_CTR for
  * data to be returned. The counter width is discovered from the hardware
@@ -31,263 +28,6 @@
  */
 #define MBM_CNTR_WIDTH_OFFSET_MAX (62 - MBM_CNTR_WIDTH_BASE)
 
-/**
- * cpumask_any_housekeeping() - Choose any CPU in @mask, preferring those that
- *			        aren't marked nohz_full
- * @mask:	The mask to pick a CPU from.
- * @exclude_cpu:The CPU to avoid picking.
- *
- * Returns a CPU from @mask, but not @exclude_cpu. If there are housekeeping
- * CPUs that don't use nohz_full, these are preferred. Pass
- * RESCTRL_PICK_ANY_CPU to avoid excluding any CPUs.
- *
- * When a CPU is excluded, returns >= nr_cpu_ids if no CPUs are available.
- */
-static inline unsigned int
-cpumask_any_housekeeping(const struct cpumask *mask, int exclude_cpu)
-{
-	unsigned int cpu;
-
-	/* Try to find a CPU that isn't nohz_full to use in preference */
-	if (tick_nohz_full_enabled()) {
-		cpu = cpumask_any_andnot_but(mask, tick_nohz_full_mask, exclude_cpu);
-		if (cpu < nr_cpu_ids)
-			return cpu;
-	}
-
-	return cpumask_any_but(mask, exclude_cpu);
-}
-
-struct rdt_fs_context {
-	struct kernfs_fs_context	kfc;
-	bool				enable_cdpl2;
-	bool				enable_cdpl3;
-	bool				enable_mba_mbps;
-	bool				enable_debug;
-};
-
-static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc)
-{
-	struct kernfs_fs_context *kfc = fc->fs_private;
-
-	return container_of(kfc, struct rdt_fs_context, kfc);
-}
-
-/**
- * struct mon_evt - Entry in the event list of a resource
- * @evtid:		event id
- * @name:		name of the event
- * @configurable:	true if the event is configurable
- * @list:		entry in &rdt_resource->evt_list
- */
-struct mon_evt {
-	enum resctrl_event_id	evtid;
-	char			*name;
-	bool			configurable;
-	struct list_head	list;
-};
-
-/**
- * struct mon_data - Monitoring details for each event file.
- * @list:            Member of the global @mon_data_kn_priv_list list.
- * @rid:             Resource id associated with the event file.
- * @evtid:           Event id associated with the event file.
- * @sum:             Set when event must be summed across multiple
- *                   domains.
- * @domid:           When @sum is zero this is the domain to which
- *                   the event file belongs. When @sum is one this
- *                   is the id of the L3 cache that all domains to be
- *                   summed share.
- *
- * Pointed to by the kernfs kn->priv field of monitoring event files.
- * Readers and writers must hold rdtgroup_mutex.
- */
-struct mon_data {
-	struct list_head	list;
-	enum resctrl_res_level	rid;
-	enum resctrl_event_id	evtid;
-	int			domid;
-	bool			sum;
-};
-
-/**
- * struct rmid_read - Data passed across smp_call*() to read event count.
- * @rgrp:  Resource group for which the counter is being read. If it is a parent
- *	   resource group then its event count is summed with the count from all
- *	   its child resource groups.
- * @r:	   Resource describing the properties of the event being read.
- * @d:	   Domain that the counter should be read from. If NULL then sum all
- *	   domains in @r sharing L3 @ci.id
- * @evtid: Which monitor event to read.
- * @first: Initialize MBM counter when true.
- * @ci:    Cacheinfo for L3. Only set when @d is NULL. Used when summing domains.
- * @err:   Error encountered when reading counter.
- * @val:   Returned value of event counter. If @rgrp is a parent resource group,
- *	   @val includes the sum of event counts from its child resource groups.
- *	   If @d is NULL, @val includes the sum of all domains in @r sharing @ci.id,
- *	   (summed across child resource groups if @rgrp is a parent resource group).
- * @arch_mon_ctx: Hardware monitor allocated for this read request (MPAM only).
- */
-struct rmid_read {
-	struct rdtgroup		*rgrp;
-	struct rdt_resource	*r;
-	struct rdt_mon_domain	*d;
-	enum resctrl_event_id	evtid;
-	bool			first;
-	struct cacheinfo	*ci;
-	int			err;
-	u64			val;
-	void			*arch_mon_ctx;
-};
-
-extern struct list_head resctrl_schema_all;
-extern bool resctrl_mounted;
-
-enum rdt_group_type {
-	RDTCTRL_GROUP = 0,
-	RDTMON_GROUP,
-	RDT_NUM_GROUP,
-};
-
-/**
- * enum rdtgrp_mode - Mode of a RDT resource group
- * @RDT_MODE_SHAREABLE: This resource group allows sharing of its allocations
- * @RDT_MODE_EXCLUSIVE: No sharing of this resource group's allocations allowed
- * @RDT_MODE_PSEUDO_LOCKSETUP: Resource group will be used for Pseudo-Locking
- * @RDT_MODE_PSEUDO_LOCKED: No sharing of this resource group's allocations
- *                          allowed AND the allocations are Cache Pseudo-Locked
- * @RDT_NUM_MODES: Total number of modes
- *
- * The mode of a resource group enables control over the allowed overlap
- * between allocations associated with different resource groups (classes
- * of service). User is able to modify the mode of a resource group by
- * writing to the "mode" resctrl file associated with the resource group.
- *
- * The "shareable", "exclusive", and "pseudo-locksetup" modes are set by
- * writing the appropriate text to the "mode" file. A resource group enters
- * "pseudo-locked" mode after the schemata is written while the resource
- * group is in "pseudo-locksetup" mode.
- */
-enum rdtgrp_mode {
-	RDT_MODE_SHAREABLE = 0,
-	RDT_MODE_EXCLUSIVE,
-	RDT_MODE_PSEUDO_LOCKSETUP,
-	RDT_MODE_PSEUDO_LOCKED,
-
-	/* Must be last */
-	RDT_NUM_MODES,
-};
-
-/**
- * struct mongroup - store mon group's data in resctrl fs.
- * @mon_data_kn:		kernfs node for the mon_data directory
- * @parent:			parent rdtgrp
- * @crdtgrp_list:		child rdtgroup node list
- * @rmid:			rmid for this rdtgroup
- */
-struct mongroup {
-	struct kernfs_node	*mon_data_kn;
-	struct rdtgroup		*parent;
-	struct list_head	crdtgrp_list;
-	u32			rmid;
-};
-
-/**
- * struct rdtgroup - store rdtgroup's data in resctrl file system.
- * @kn:				kernfs node
- * @rdtgroup_list:		linked list for all rdtgroups
- * @closid:			closid for this rdtgroup
- * @cpu_mask:			CPUs assigned to this rdtgroup
- * @flags:			status bits
- * @waitcount:			how many cpus expect to find this
- *				group when they acquire rdtgroup_mutex
- * @type:			indicates type of this rdtgroup - either
- *				monitor only or ctrl_mon group
- * @mon:			mongroup related data
- * @mode:			mode of resource group
- * @mba_mbps_event:		input monitoring event id when mba_sc is enabled
- * @plr:			pseudo-locked region
- */
-struct rdtgroup {
-	struct kernfs_node		*kn;
-	struct list_head		rdtgroup_list;
-	u32				closid;
-	struct cpumask			cpu_mask;
-	int				flags;
-	atomic_t			waitcount;
-	enum rdt_group_type		type;
-	struct mongroup			mon;
-	enum rdtgrp_mode		mode;
-	enum resctrl_event_id		mba_mbps_event;
-	struct pseudo_lock_region	*plr;
-};
-
-/* rdtgroup.flags */
-#define	RDT_DELETED		1
-
-/* rftype.flags */
-#define RFTYPE_FLAGS_CPUS_LIST	1
-
-/*
- * Define the file type flags for base and info directories.
- */
-#define RFTYPE_INFO			BIT(0)
-#define RFTYPE_BASE			BIT(1)
-#define RFTYPE_CTRL			BIT(4)
-#define RFTYPE_MON			BIT(5)
-#define RFTYPE_TOP			BIT(6)
-#define RFTYPE_RES_CACHE		BIT(8)
-#define RFTYPE_RES_MB			BIT(9)
-#define RFTYPE_DEBUG			BIT(10)
-#define RFTYPE_CTRL_INFO		(RFTYPE_INFO | RFTYPE_CTRL)
-#define RFTYPE_MON_INFO			(RFTYPE_INFO | RFTYPE_MON)
-#define RFTYPE_TOP_INFO			(RFTYPE_INFO | RFTYPE_TOP)
-#define RFTYPE_CTRL_BASE		(RFTYPE_BASE | RFTYPE_CTRL)
-#define RFTYPE_MON_BASE			(RFTYPE_BASE | RFTYPE_MON)
-
-/* List of all resource groups */
-extern struct list_head rdt_all_groups;
-
-extern int max_name_width;
-
-/**
- * struct rftype - describe each file in the resctrl file system
- * @name:	File name
- * @mode:	Access mode
- * @kf_ops:	File operations
- * @flags:	File specific RFTYPE_FLAGS_* flags
- * @fflags:	File specific RFTYPE_* flags
- * @seq_show:	Show content of the file
- * @write:	Write to the file
- */
-struct rftype {
-	char			*name;
-	umode_t			mode;
-	const struct kernfs_ops	*kf_ops;
-	unsigned long		flags;
-	unsigned long		fflags;
-
-	int (*seq_show)(struct kernfs_open_file *of,
-			struct seq_file *sf, void *v);
-	/*
-	 * write() is the generic write callback which maps directly to
-	 * kernfs write operation and overrides all other operations.
-	 * Maximum write size is determined by ->max_write_len.
-	 */
-	ssize_t (*write)(struct kernfs_open_file *of,
-			 char *buf, size_t nbytes, loff_t off);
-};
-
-/**
- * struct mbm_state - status for each MBM counter in each domain
- * @prev_bw_bytes: Previous bytes value read for bandwidth calculation
- * @prev_bw:	The most recent bandwidth in MBps
- */
-struct mbm_state {
-	u64	prev_bw_bytes;
-	u32	prev_bw;
-};
-
 /**
  * struct arch_mbm_state - values used to compute resctrl_arch_rmid_read()s
  *			   return value.
@@ -385,17 +125,7 @@ static inline struct rdt_hw_resource *resctrl_to_arch_res(struct rdt_resource *r
 	return container_of(r, struct rdt_hw_resource, r_resctrl);
 }
 
-extern struct mutex rdtgroup_mutex;
-
-static inline const char *rdt_kn_name(const struct kernfs_node *kn)
-{
-	return rcu_dereference_check(kn->name, lockdep_is_held(&rdtgroup_mutex));
-}
-
 extern struct rdt_hw_resource rdt_resources_all[];
-extern struct rdtgroup rdtgroup_default;
-extern struct dentry *debugfs_resctrl;
-extern enum resctrl_event_id mba_mbps_default_event;
 
 void arch_mon_domain_online(struct rdt_resource *r, struct rdt_mon_domain *d);
 
@@ -432,99 +162,14 @@ union cpuid_0x10_x_edx {
 	unsigned int full;
 };
 
-void rdt_last_cmd_clear(void);
-void rdt_last_cmd_puts(const char *s);
-__printf(1, 2)
-void rdt_last_cmd_printf(const char *fmt, ...);
-
 void rdt_ctrl_update(void *arg);
-struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn);
-void rdtgroup_kn_unlock(struct kernfs_node *kn);
-int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name);
-int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name,
-			     umode_t mask);
-ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
-				char *buf, size_t nbytes, loff_t off);
-int rdtgroup_schemata_show(struct kernfs_open_file *of,
-			   struct seq_file *s, void *v);
-ssize_t rdtgroup_mba_mbps_event_write(struct kernfs_open_file *of,
-				      char *buf, size_t nbytes, loff_t off);
-int rdtgroup_mba_mbps_event_show(struct kernfs_open_file *of,
-				 struct seq_file *s, void *v);
-bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_ctrl_domain *d,
-			   unsigned long cbm, int closid, bool exclusive);
-unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_ctrl_domain *d,
-				  unsigned long cbm);
-enum rdtgrp_mode rdtgroup_mode_by_closid(int closid);
-int rdtgroup_tasks_assigned(struct rdtgroup *r);
-int closids_supported(void);
-void closid_free(int closid);
-int alloc_rmid(u32 closid);
-void free_rmid(u32 closid, u32 rmid);
-int rdt_get_mon_l3_config(struct rdt_resource *r);
-void resctrl_mon_resource_exit(void);
-bool rdt_cpu_has(int flag);
-void mon_event_count(void *info);
-int rdtgroup_mondata_show(struct seq_file *m, void *arg);
-void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
-		    struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
-		    cpumask_t *cpumask, int evtid, int first);
-int resctrl_mon_resource_init(void);
-void mbm_setup_overflow_handler(struct rdt_mon_domain *dom,
-				unsigned long delay_ms,
-				int exclude_cpu);
-void mbm_handle_overflow(struct work_struct *work);
-void __init intel_rdt_mbm_apply_quirk(void);
-bool is_mba_sc(struct rdt_resource *r);
-void cqm_setup_limbo_handler(struct rdt_mon_domain *dom, unsigned long delay_ms,
-			     int exclude_cpu);
-void cqm_handle_limbo(struct work_struct *work);
-bool has_busy_rmid(struct rdt_mon_domain *d);
-void __check_limbo(struct rdt_mon_domain *d, bool force_free);
-void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
-void resctrl_file_fflags_init(const char *config, unsigned long fflags);
-void rdt_staged_configs_clear(void);
-bool closid_allocated(unsigned int closid);
-int resctrl_find_cleanest_closid(void);
-
-#ifdef CONFIG_RESCTRL_FS_PSEUDO_LOCK
-int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp);
-int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp);
-bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm);
-bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d);
-int rdt_pseudo_lock_init(void);
-void rdt_pseudo_lock_release(void);
-int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp);
-void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp);
-#else
-static inline int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp)
-{
-	return -EOPNOTSUPP;
-}
 
-static inline int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm)
-{
-	return false;
-}
+int rdt_get_mon_l3_config(struct rdt_resource *r);
 
-static inline bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d)
-{
-	return false;
-}
+bool rdt_cpu_has(int flag);
 
-static inline int rdt_pseudo_lock_init(void) { return 0; }
-static inline void rdt_pseudo_lock_release(void) { }
-static inline int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
-{
-	return -EOPNOTSUPP;
-}
+void __init intel_rdt_mbm_apply_quirk(void);
 
-static inline void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp) { }
-#endif /* CONFIG_RESCTRL_FS_PSEUDO_LOCK */
+void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
 
 #endif /* _ASM_X86_RESCTRL_INTERNAL_H */
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 2cfae5146fd1a..bbfb95ae13c2d 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -18,65 +18,12 @@
 #define pr_fmt(fmt)	"resctrl: " fmt
 
 #include <linux/cpu.h>
-#include <linux/module.h>
 #include <linux/resctrl.h>
-#include <linux/sizes.h>
-#include <linux/slab.h>
 
 #include <asm/cpu_device_id.h>
 
 #include "internal.h"
 
-#define CREATE_TRACE_POINTS
-#include "monitor_trace.h"
-
-/**
- * struct rmid_entry - dirty tracking for all RMID.
- * @closid:	The CLOSID for this entry.
- * @rmid:	The RMID for this entry.
- * @busy:	The number of domains with cached data using this RMID.
- * @list:	Member of the rmid_free_lru list when busy == 0.
- *
- * Depending on the architecture the correct monitor is accessed using
- * both @closid and @rmid, or @rmid only.
- *
- * Take the rdtgroup_mutex when accessing.
- */
-struct rmid_entry {
-	u32				closid;
-	u32				rmid;
-	int				busy;
-	struct list_head		list;
-};
-
-/*
- * @rmid_free_lru - A least recently used list of free RMIDs
- *     These RMIDs are guaranteed to have an occupancy less than the
- *     threshold occupancy
- */
-static LIST_HEAD(rmid_free_lru);
-
-/*
- * @closid_num_dirty_rmid    The number of dirty RMID each CLOSID has.
- *     Only allocated when CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID is defined.
- *     Indexed by CLOSID. Protected by rdtgroup_mutex.
- */
-static u32 *closid_num_dirty_rmid;
-
-/*
- * @rmid_limbo_count - count of currently unused but (potentially)
- *     dirty RMIDs.
- *     This counts RMIDs that no one is currently using but that
- *     may have a occupancy value > resctrl_rmid_realloc_threshold. User can
- *     change the threshold occupancy value.
- */
-static unsigned int rmid_limbo_count;
-
-/*
- * @rmid_entry - The entry in the limbo and free lists.
- */
-static struct rmid_entry	*rmid_ptrs;
-
 /*
  * Global boolean for rdt_monitor which is true if any
  * resource monitoring is enabled.
@@ -88,23 +35,12 @@ bool rdt_mon_capable;
  */
 unsigned int rdt_mon_features;
 
-/*
- * This is the threshold cache occupancy in bytes at which we will consider an
- * RMID available for re-allocation.
- */
-unsigned int resctrl_rmid_realloc_threshold;
-
-/*
- * This is the maximum value for the reallocation threshold, in bytes.
- */
-unsigned int resctrl_rmid_realloc_limit;
-
 #define CF(cf)	((unsigned long)(1048576 * (cf) + 0.5))
 
 static int snc_nodes_per_l3_cache = 1;
 
 /*
- * The correction factor table is documented in Documentation/arch/x86/resctrl.rst.
+ * The correction factor table is documented in Documentation/filesystems/resctrl.rst.
  * If rmid > rmid threshold, MBM total and local values should be multiplied
  * by the correction factor.
  *
@@ -153,6 +89,7 @@ static const struct mbm_correction_factor_table {
 };
 
 static u32 mbm_cf_rmidthreshold __read_mostly = UINT_MAX;
+
 static u64 mbm_cf __read_mostly;
 
 static inline u64 get_corrected_mbm_count(u32 rmid, unsigned long val)
@@ -164,33 +101,6 @@ static inline u64 get_corrected_mbm_count(u32 rmid, unsigned long val)
 	return val;
 }
 
-/*
- * x86 and arm64 differ in their handling of monitoring.
- * x86's RMID are independent numbers, there is only one source of traffic
- * with an RMID value of '1'.
- * arm64's PMG extends the PARTID/CLOSID space, there are multiple sources of
- * traffic with a PMG value of '1', one for each CLOSID, meaning the RMID
- * value is no longer unique.
- * To account for this, resctrl uses an index. On x86 this is just the RMID,
- * on arm64 it encodes the CLOSID and RMID. This gives a unique number.
- *
- * The domain's rmid_busy_llc and rmid_ptrs[] are sized by index. The arch code
- * must accept an attempt to read every index.
- */
-static inline struct rmid_entry *__rmid_entry(u32 idx)
-{
-	struct rmid_entry *entry;
-	u32 closid, rmid;
-
-	entry = &rmid_ptrs[idx];
-	resctrl_arch_rmid_idx_decode(idx, &closid, &rmid);
-
-	WARN_ON_ONCE(entry->closid != closid);
-	WARN_ON_ONCE(entry->rmid != rmid);
-
-	return entry;
-}
-
 /*
  * When Sub-NUMA Cluster (SNC) mode is not enabled (as indicated by
  * "snc_nodes_per_l3_cache == 1") no translation of the RMID value is
@@ -347,769 +257,6 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
 	return 0;
 }
 
-static void limbo_release_entry(struct rmid_entry *entry)
-{
-	lockdep_assert_held(&rdtgroup_mutex);
-
-	rmid_limbo_count--;
-	list_add_tail(&entry->list, &rmid_free_lru);
-
-	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID))
-		closid_num_dirty_rmid[entry->closid]--;
-}
-
-/*
- * Check the RMIDs that are marked as busy for this domain. If the
- * reported LLC occupancy is below the threshold clear the busy bit and
- * decrement the count. If the busy count gets to zero on an RMID, we
- * free the RMID
- */
-void __check_limbo(struct rdt_mon_domain *d, bool force_free)
-{
-	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
-	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
-	struct rmid_entry *entry;
-	u32 idx, cur_idx = 1;
-	void *arch_mon_ctx;
-	bool rmid_dirty;
-	u64 val = 0;
-
-	arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, QOS_L3_OCCUP_EVENT_ID);
-	if (IS_ERR(arch_mon_ctx)) {
-		pr_warn_ratelimited("Failed to allocate monitor context: %ld",
-				    PTR_ERR(arch_mon_ctx));
-		return;
-	}
-
-	/*
-	 * Skip RMID 0 and start from RMID 1 and check all the RMIDs that
-	 * are marked as busy for occupancy < threshold. If the occupancy
-	 * is less than the threshold decrement the busy counter of the
-	 * RMID and move it to the free list when the counter reaches 0.
-	 */
-	for (;;) {
-		idx = find_next_bit(d->rmid_busy_llc, idx_limit, cur_idx);
-		if (idx >= idx_limit)
-			break;
-
-		entry = __rmid_entry(idx);
-		if (resctrl_arch_rmid_read(r, d, entry->closid, entry->rmid,
-					   QOS_L3_OCCUP_EVENT_ID, &val,
-					   arch_mon_ctx)) {
-			rmid_dirty = true;
-		} else {
-			rmid_dirty = (val >= resctrl_rmid_realloc_threshold);
-
-			/*
-			 * x86's CLOSID and RMID are independent numbers, so the entry's
-			 * CLOSID is an empty CLOSID (X86_RESCTRL_EMPTY_CLOSID). On Arm the
-			 * RMID (PMG) extends the CLOSID (PARTID) space with bits that aren't
-			 * used to select the configuration. It is thus necessary to track both
-			 * CLOSID and RMID because there may be dependencies between them
-			 * on some architectures.
-			 */
-			trace_mon_llc_occupancy_limbo(entry->closid, entry->rmid, d->hdr.id, val);
-		}
-
-		if (force_free || !rmid_dirty) {
-			clear_bit(idx, d->rmid_busy_llc);
-			if (!--entry->busy)
-				limbo_release_entry(entry);
-		}
-		cur_idx = idx + 1;
-	}
-
-	resctrl_arch_mon_ctx_free(r, QOS_L3_OCCUP_EVENT_ID, arch_mon_ctx);
-}
-
-bool has_busy_rmid(struct rdt_mon_domain *d)
-{
-	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
-
-	return find_first_bit(d->rmid_busy_llc, idx_limit) != idx_limit;
-}
-
-static struct rmid_entry *resctrl_find_free_rmid(u32 closid)
-{
-	struct rmid_entry *itr;
-	u32 itr_idx, cmp_idx;
-
-	if (list_empty(&rmid_free_lru))
-		return rmid_limbo_count ? ERR_PTR(-EBUSY) : ERR_PTR(-ENOSPC);
-
-	list_for_each_entry(itr, &rmid_free_lru, list) {
-		/*
-		 * Get the index of this free RMID, and the index it would need
-		 * to be if it were used with this CLOSID.
-		 * If the CLOSID is irrelevant on this architecture, the two
-		 * index values are always the same on every entry and thus the
-		 * very first entry will be returned.
-		 */
-		itr_idx = resctrl_arch_rmid_idx_encode(itr->closid, itr->rmid);
-		cmp_idx = resctrl_arch_rmid_idx_encode(closid, itr->rmid);
-
-		if (itr_idx == cmp_idx)
-			return itr;
-	}
-
-	return ERR_PTR(-ENOSPC);
-}
-
-/**
- * resctrl_find_cleanest_closid() - Find a CLOSID where all the associated
- *                                  RMID are clean, or the CLOSID that has
- *                                  the most clean RMID.
- *
- * MPAM's equivalent of RMID are per-CLOSID, meaning a freshly allocated CLOSID
- * may not be able to allocate clean RMID. To avoid this the allocator will
- * choose the CLOSID with the most clean RMID.
- *
- * When the CLOSID and RMID are independent numbers, the first free CLOSID will
- * be returned.
- */
-int resctrl_find_cleanest_closid(void)
-{
-	u32 cleanest_closid = ~0;
-	int i = 0;
-
-	lockdep_assert_held(&rdtgroup_mutex);
-
-	if (!IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID))
-		return -EIO;
-
-	for (i = 0; i < closids_supported(); i++) {
-		int num_dirty;
-
-		if (closid_allocated(i))
-			continue;
-
-		num_dirty = closid_num_dirty_rmid[i];
-		if (num_dirty == 0)
-			return i;
-
-		if (cleanest_closid == ~0)
-			cleanest_closid = i;
-
-		if (num_dirty < closid_num_dirty_rmid[cleanest_closid])
-			cleanest_closid = i;
-	}
-
-	if (cleanest_closid == ~0)
-		return -ENOSPC;
-
-	return cleanest_closid;
-}
-
-/*
- * For MPAM the RMID value is not unique, and has to be considered with
- * the CLOSID. The (CLOSID, RMID) pair is allocated on all domains, which
- * allows all domains to be managed by a single free list.
- * Each domain also has a rmid_busy_llc to reduce the work of the limbo handler.
- */
-int alloc_rmid(u32 closid)
-{
-	struct rmid_entry *entry;
-
-	lockdep_assert_held(&rdtgroup_mutex);
-
-	entry = resctrl_find_free_rmid(closid);
-	if (IS_ERR(entry))
-		return PTR_ERR(entry);
-
-	list_del(&entry->list);
-	return entry->rmid;
-}
-
-static void add_rmid_to_limbo(struct rmid_entry *entry)
-{
-	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
-	struct rdt_mon_domain *d;
-	u32 idx;
-
-	lockdep_assert_held(&rdtgroup_mutex);
-
-	/* Walking r->domains, ensure it can't race with cpuhp */
-	lockdep_assert_cpus_held();
-
-	idx = resctrl_arch_rmid_idx_encode(entry->closid, entry->rmid);
-
-	entry->busy = 0;
-	list_for_each_entry(d, &r->mon_domains, hdr.list) {
-		/*
-		 * For the first limbo RMID in the domain,
-		 * setup up the limbo worker.
-		 */
-		if (!has_busy_rmid(d))
-			cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL,
-						RESCTRL_PICK_ANY_CPU);
-		set_bit(idx, d->rmid_busy_llc);
-		entry->busy++;
-	}
-
-	rmid_limbo_count++;
-	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID))
-		closid_num_dirty_rmid[entry->closid]++;
-}
-
-void free_rmid(u32 closid, u32 rmid)
-{
-	u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid);
-	struct rmid_entry *entry;
-
-	lockdep_assert_held(&rdtgroup_mutex);
-
-	/*
-	 * Do not allow the default rmid to be free'd. Comparing by index
-	 * allows architectures that ignore the closid parameter to avoid an
-	 * unnecessary check.
-	 */
-	if (!resctrl_arch_mon_capable() ||
-	    idx == resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID,
-						RESCTRL_RESERVED_RMID))
-		return;
-
-	entry = __rmid_entry(idx);
-
-	if (resctrl_arch_is_llc_occupancy_enabled())
-		add_rmid_to_limbo(entry);
-	else
-		list_add_tail(&entry->list, &rmid_free_lru);
-}
-
-static struct mbm_state *get_mbm_state(struct rdt_mon_domain *d, u32 closid,
-				       u32 rmid, enum resctrl_event_id evtid)
-{
-	u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid);
-
-	switch (evtid) {
-	case QOS_L3_MBM_TOTAL_EVENT_ID:
-		return &d->mbm_total[idx];
-	case QOS_L3_MBM_LOCAL_EVENT_ID:
-		return &d->mbm_local[idx];
-	default:
-		return NULL;
-	}
-}
-
-static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
-{
-	int cpu = smp_processor_id();
-	struct rdt_mon_domain *d;
-	struct mbm_state *m;
-	int err, ret;
-	u64 tval = 0;
-
-	if (rr->first) {
-		resctrl_arch_reset_rmid(rr->r, rr->d, closid, rmid, rr->evtid);
-		m = get_mbm_state(rr->d, closid, rmid, rr->evtid);
-		if (m)
-			memset(m, 0, sizeof(struct mbm_state));
-		return 0;
-	}
-
-	if (rr->d) {
-		/* Reading a single domain, must be on a CPU in that domain. */
-		if (!cpumask_test_cpu(cpu, &rr->d->hdr.cpu_mask))
-			return -EINVAL;
-		rr->err = resctrl_arch_rmid_read(rr->r, rr->d, closid, rmid,
-						 rr->evtid, &tval, rr->arch_mon_ctx);
-		if (rr->err)
-			return rr->err;
-
-		rr->val += tval;
-
-		return 0;
-	}
-
-	/* Summing domains that share a cache, must be on a CPU for that cache. */
-	if (!cpumask_test_cpu(cpu, &rr->ci->shared_cpu_map))
-		return -EINVAL;
-
-	/*
-	 * Legacy files must report the sum of an event across all
-	 * domains that share the same L3 cache instance.
-	 * Report success if a read from any domain succeeds, -EINVAL
-	 * (translated to "Unavailable" for user space) if reading from
-	 * all domains fail for any reason.
-	 */
-	ret = -EINVAL;
-	list_for_each_entry(d, &rr->r->mon_domains, hdr.list) {
-		if (d->ci->id != rr->ci->id)
-			continue;
-		err = resctrl_arch_rmid_read(rr->r, d, closid, rmid,
-					     rr->evtid, &tval, rr->arch_mon_ctx);
-		if (!err) {
-			rr->val += tval;
-			ret = 0;
-		}
-	}
-
-	if (ret)
-		rr->err = ret;
-
-	return ret;
-}
-
-/*
- * mbm_bw_count() - Update bw count from values previously read by
- *		    __mon_event_count().
- * @closid:	The closid used to identify the cached mbm_state.
- * @rmid:	The rmid used to identify the cached mbm_state.
- * @rr:		The struct rmid_read populated by __mon_event_count().
- *
- * Supporting function to calculate the memory bandwidth
- * and delta bandwidth in MBps. The chunks value previously read by
- * __mon_event_count() is compared with the chunks value from the previous
- * invocation. This must be called once per second to maintain values in MBps.
- */
-static void mbm_bw_count(u32 closid, u32 rmid, struct rmid_read *rr)
-{
-	u64 cur_bw, bytes, cur_bytes;
-	struct mbm_state *m;
-
-	m = get_mbm_state(rr->d, closid, rmid, rr->evtid);
-	if (WARN_ON_ONCE(!m))
-		return;
-
-	cur_bytes = rr->val;
-	bytes = cur_bytes - m->prev_bw_bytes;
-	m->prev_bw_bytes = cur_bytes;
-
-	cur_bw = bytes / SZ_1M;
-
-	m->prev_bw = cur_bw;
-}
-
-/*
- * This is scheduled by mon_event_read() to read the CQM/MBM counters
- * on a domain.
- */
-void mon_event_count(void *info)
-{
-	struct rdtgroup *rdtgrp, *entry;
-	struct rmid_read *rr = info;
-	struct list_head *head;
-	int ret;
-
-	rdtgrp = rr->rgrp;
-
-	ret = __mon_event_count(rdtgrp->closid, rdtgrp->mon.rmid, rr);
-
-	/*
-	 * For Ctrl groups read data from child monitor groups and
-	 * add them together. Count events which are read successfully.
-	 * Discard the rmid_read's reporting errors.
-	 */
-	head = &rdtgrp->mon.crdtgrp_list;
-
-	if (rdtgrp->type == RDTCTRL_GROUP) {
-		list_for_each_entry(entry, head, mon.crdtgrp_list) {
-			if (__mon_event_count(entry->closid, entry->mon.rmid,
-					      rr) == 0)
-				ret = 0;
-		}
-	}
-
-	/*
-	 * __mon_event_count() calls for newly created monitor groups may
-	 * report -EINVAL/Unavailable if the monitor hasn't seen any traffic.
-	 * Discard error if any of the monitor event reads succeeded.
-	 */
-	if (ret == 0)
-		rr->err = 0;
-}
-
-static struct rdt_ctrl_domain *get_ctrl_domain_from_cpu(int cpu,
-							struct rdt_resource *r)
-{
-	struct rdt_ctrl_domain *d;
-
-	lockdep_assert_cpus_held();
-
-	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
-		/* Find the domain that contains this CPU */
-		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask))
-			return d;
-	}
-
-	return NULL;
-}
-
-/*
- * Feedback loop for MBA software controller (mba_sc)
- *
- * mba_sc is a feedback loop where we periodically read MBM counters and
- * adjust the bandwidth percentage values via the IA32_MBA_THRTL_MSRs so
- * that:
- *
- *   current bandwidth(cur_bw) < user specified bandwidth(user_bw)
- *
- * This uses the MBM counters to measure the bandwidth and MBA throttle
- * MSRs to control the bandwidth for a particular rdtgrp. It builds on the
- * fact that resctrl rdtgroups have both monitoring and control.
- *
- * The frequency of the checks is 1s and we just tag along the MBM overflow
- * timer. Having 1s interval makes the calculation of bandwidth simpler.
- *
- * Although MBA's goal is to restrict the bandwidth to a maximum, there may
- * be a need to increase the bandwidth to avoid unnecessarily restricting
- * the L2 <-> L3 traffic.
- *
- * Since MBA controls the L2 external bandwidth where as MBM measures the
- * L3 external bandwidth the following sequence could lead to such a
- * situation.
- *
- * Consider an rdtgroup which had high L3 <-> memory traffic in initial
- * phases -> mba_sc kicks in and reduced bandwidth percentage values -> but
- * after some time rdtgroup has mostly L2 <-> L3 traffic.
- *
- * In this case we may restrict the rdtgroup's L2 <-> L3 traffic as its
- * throttle MSRs already have low percentage values.  To avoid
- * unnecessarily restricting such rdtgroups, we also increase the bandwidth.
- */
-static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm)
-{
-	u32 closid, rmid, cur_msr_val, new_msr_val;
-	struct mbm_state *pmbm_data, *cmbm_data;
-	struct rdt_ctrl_domain *dom_mba;
-	enum resctrl_event_id evt_id;
-	struct rdt_resource *r_mba;
-	struct list_head *head;
-	struct rdtgroup *entry;
-	u32 cur_bw, user_bw;
-
-	r_mba = resctrl_arch_get_resource(RDT_RESOURCE_MBA);
-	evt_id = rgrp->mba_mbps_event;
-
-	closid = rgrp->closid;
-	rmid = rgrp->mon.rmid;
-	pmbm_data = get_mbm_state(dom_mbm, closid, rmid, evt_id);
-	if (WARN_ON_ONCE(!pmbm_data))
-		return;
-
-	dom_mba = get_ctrl_domain_from_cpu(smp_processor_id(), r_mba);
-	if (!dom_mba) {
-		pr_warn_once("Failure to get domain for MBA update\n");
-		return;
-	}
-
-	cur_bw = pmbm_data->prev_bw;
-	user_bw = dom_mba->mbps_val[closid];
-
-	/* MBA resource doesn't support CDP */
-	cur_msr_val = resctrl_arch_get_config(r_mba, dom_mba, closid, CDP_NONE);
-
-	/*
-	 * For Ctrl groups read data from child monitor groups.
-	 */
-	head = &rgrp->mon.crdtgrp_list;
-	list_for_each_entry(entry, head, mon.crdtgrp_list) {
-		cmbm_data = get_mbm_state(dom_mbm, entry->closid, entry->mon.rmid, evt_id);
-		if (WARN_ON_ONCE(!cmbm_data))
-			return;
-		cur_bw += cmbm_data->prev_bw;
-	}
-
-	/*
-	 * Scale up/down the bandwidth linearly for the ctrl group.  The
-	 * bandwidth step is the bandwidth granularity specified by the
-	 * hardware.
-	 * Always increase throttling if current bandwidth is above the
-	 * target set by user.
-	 * But avoid thrashing up and down on every poll by checking
-	 * whether a decrease in throttling is likely to push the group
-	 * back over target. E.g. if currently throttling to 30% of bandwidth
-	 * on a system with 10% granularity steps, check whether moving to
-	 * 40% would go past the limit by multiplying current bandwidth by
-	 * "(30 + 10) / 30".
-	 */
-	if (cur_msr_val > r_mba->membw.min_bw && user_bw < cur_bw) {
-		new_msr_val = cur_msr_val - r_mba->membw.bw_gran;
-	} else if (cur_msr_val < MAX_MBA_BW &&
-		   (user_bw > (cur_bw * (cur_msr_val + r_mba->membw.min_bw) / cur_msr_val))) {
-		new_msr_val = cur_msr_val + r_mba->membw.bw_gran;
-	} else {
-		return;
-	}
-
-	resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val);
-}
-
-static void mbm_update_one_event(struct rdt_resource *r, struct rdt_mon_domain *d,
-				 u32 closid, u32 rmid, enum resctrl_event_id evtid)
-{
-	struct rmid_read rr = {0};
-
-	rr.r = r;
-	rr.d = d;
-	rr.evtid = evtid;
-	rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
-	if (IS_ERR(rr.arch_mon_ctx)) {
-		pr_warn_ratelimited("Failed to allocate monitor context: %ld",
-				    PTR_ERR(rr.arch_mon_ctx));
-		return;
-	}
-
-	__mon_event_count(closid, rmid, &rr);
-
-	/*
-	 * If the software controller is enabled, compute the
-	 * bandwidth for this event id.
-	 */
-	if (is_mba_sc(NULL))
-		mbm_bw_count(closid, rmid, &rr);
-
-	resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
-}
-
-static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d,
-		       u32 closid, u32 rmid)
-{
-	/*
-	 * This is protected from concurrent reads from user as both
-	 * the user and overflow handler hold the global mutex.
-	 */
-	if (resctrl_arch_is_mbm_total_enabled())
-		mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_TOTAL_EVENT_ID);
-
-	if (resctrl_arch_is_mbm_local_enabled())
-		mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_LOCAL_EVENT_ID);
-}
-
-/*
- * Handler to scan the limbo list and move the RMIDs
- * to free list whose occupancy < threshold_occupancy.
- */
-void cqm_handle_limbo(struct work_struct *work)
-{
-	unsigned long delay = msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL);
-	struct rdt_mon_domain *d;
-
-	cpus_read_lock();
-	mutex_lock(&rdtgroup_mutex);
-
-	d = container_of(work, struct rdt_mon_domain, cqm_limbo.work);
-
-	__check_limbo(d, false);
-
-	if (has_busy_rmid(d)) {
-		d->cqm_work_cpu = cpumask_any_housekeeping(&d->hdr.cpu_mask,
-							   RESCTRL_PICK_ANY_CPU);
-		schedule_delayed_work_on(d->cqm_work_cpu, &d->cqm_limbo,
-					 delay);
-	}
-
-	mutex_unlock(&rdtgroup_mutex);
-	cpus_read_unlock();
-}
-
-/**
- * cqm_setup_limbo_handler() - Schedule the limbo handler to run for this
- *                             domain.
- * @dom:           The domain the limbo handler should run for.
- * @delay_ms:      How far in the future the handler should run.
- * @exclude_cpu:   Which CPU the handler should not run on,
- *		   RESCTRL_PICK_ANY_CPU to pick any CPU.
- */
-void cqm_setup_limbo_handler(struct rdt_mon_domain *dom, unsigned long delay_ms,
-			     int exclude_cpu)
-{
-	unsigned long delay = msecs_to_jiffies(delay_ms);
-	int cpu;
-
-	cpu = cpumask_any_housekeeping(&dom->hdr.cpu_mask, exclude_cpu);
-	dom->cqm_work_cpu = cpu;
-
-	if (cpu < nr_cpu_ids)
-		schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay);
-}
-
-void mbm_handle_overflow(struct work_struct *work)
-{
-	unsigned long delay = msecs_to_jiffies(MBM_OVERFLOW_INTERVAL);
-	struct rdtgroup *prgrp, *crgrp;
-	struct rdt_mon_domain *d;
-	struct list_head *head;
-	struct rdt_resource *r;
-
-	cpus_read_lock();
-	mutex_lock(&rdtgroup_mutex);
-
-	/*
-	 * If the filesystem has been unmounted this work no longer needs to
-	 * run.
-	 */
-	if (!resctrl_mounted || !resctrl_arch_mon_capable())
-		goto out_unlock;
-
-	r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
-	d = container_of(work, struct rdt_mon_domain, mbm_over.work);
-
-	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
-		mbm_update(r, d, prgrp->closid, prgrp->mon.rmid);
-
-		head = &prgrp->mon.crdtgrp_list;
-		list_for_each_entry(crgrp, head, mon.crdtgrp_list)
-			mbm_update(r, d, crgrp->closid, crgrp->mon.rmid);
-
-		if (is_mba_sc(NULL))
-			update_mba_bw(prgrp, d);
-	}
-
-	/*
-	 * Re-check for housekeeping CPUs. This allows the overflow handler to
-	 * move off a nohz_full CPU quickly.
-	 */
-	d->mbm_work_cpu = cpumask_any_housekeeping(&d->hdr.cpu_mask,
-						   RESCTRL_PICK_ANY_CPU);
-	schedule_delayed_work_on(d->mbm_work_cpu, &d->mbm_over, delay);
-
-out_unlock:
-	mutex_unlock(&rdtgroup_mutex);
-	cpus_read_unlock();
-}
-
-/**
- * mbm_setup_overflow_handler() - Schedule the overflow handler to run for this
- *                                domain.
- * @dom:           The domain the overflow handler should run for.
- * @delay_ms:      How far in the future the handler should run.
- * @exclude_cpu:   Which CPU the handler should not run on,
- *		   RESCTRL_PICK_ANY_CPU to pick any CPU.
- */
-void mbm_setup_overflow_handler(struct rdt_mon_domain *dom, unsigned long delay_ms,
-				int exclude_cpu)
-{
-	unsigned long delay = msecs_to_jiffies(delay_ms);
-	int cpu;
-
-	/*
-	 * When a domain comes online there is no guarantee the filesystem is
-	 * mounted. If not, there is no need to catch counter overflow.
-	 */
-	if (!resctrl_mounted || !resctrl_arch_mon_capable())
-		return;
-	cpu = cpumask_any_housekeeping(&dom->hdr.cpu_mask, exclude_cpu);
-	dom->mbm_work_cpu = cpu;
-
-	if (cpu < nr_cpu_ids)
-		schedule_delayed_work_on(cpu, &dom->mbm_over, delay);
-}
-
-static int dom_data_init(struct rdt_resource *r)
-{
-	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
-	u32 num_closid = resctrl_arch_get_num_closid(r);
-	struct rmid_entry *entry = NULL;
-	int err = 0, i;
-	u32 idx;
-
-	mutex_lock(&rdtgroup_mutex);
-	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
-		u32 *tmp;
-
-		/*
-		 * If the architecture hasn't provided a sanitised value here,
-		 * this may result in larger arrays than necessary. Resctrl will
-		 * use a smaller system wide value based on the resources in
-		 * use.
-		 */
-		tmp = kcalloc(num_closid, sizeof(*tmp), GFP_KERNEL);
-		if (!tmp) {
-			err = -ENOMEM;
-			goto out_unlock;
-		}
-
-		closid_num_dirty_rmid = tmp;
-	}
-
-	rmid_ptrs = kcalloc(idx_limit, sizeof(struct rmid_entry), GFP_KERNEL);
-	if (!rmid_ptrs) {
-		if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
-			kfree(closid_num_dirty_rmid);
-			closid_num_dirty_rmid = NULL;
-		}
-		err = -ENOMEM;
-		goto out_unlock;
-	}
-
-	for (i = 0; i < idx_limit; i++) {
-		entry = &rmid_ptrs[i];
-		INIT_LIST_HEAD(&entry->list);
-
-		resctrl_arch_rmid_idx_decode(i, &entry->closid, &entry->rmid);
-		list_add_tail(&entry->list, &rmid_free_lru);
-	}
-
-	/*
-	 * RESCTRL_RESERVED_CLOSID and RESCTRL_RESERVED_RMID are special and
-	 * are always allocated. These are used for the rdtgroup_default
-	 * control group, which will be setup later in resctrl_init().
-	 */
-	idx = resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID,
-					   RESCTRL_RESERVED_RMID);
-	entry = __rmid_entry(idx);
-	list_del(&entry->list);
-
-out_unlock:
-	mutex_unlock(&rdtgroup_mutex);
-
-	return err;
-}
-
-static void dom_data_exit(struct rdt_resource *r)
-{
-	mutex_lock(&rdtgroup_mutex);
-
-	if (!r->mon_capable)
-		goto out_unlock;
-
-	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
-		kfree(closid_num_dirty_rmid);
-		closid_num_dirty_rmid = NULL;
-	}
-
-	kfree(rmid_ptrs);
-	rmid_ptrs = NULL;
-
-out_unlock:
-	mutex_unlock(&rdtgroup_mutex);
-}
-
-static struct mon_evt llc_occupancy_event = {
-	.name		= "llc_occupancy",
-	.evtid		= QOS_L3_OCCUP_EVENT_ID,
-};
-
-static struct mon_evt mbm_total_event = {
-	.name		= "mbm_total_bytes",
-	.evtid		= QOS_L3_MBM_TOTAL_EVENT_ID,
-};
-
-static struct mon_evt mbm_local_event = {
-	.name		= "mbm_local_bytes",
-	.evtid		= QOS_L3_MBM_LOCAL_EVENT_ID,
-};
-
-/*
- * Initialize the event list for the resource.
- *
- * Note that MBM events are also part of RDT_RESOURCE_L3 resource
- * because as per the SDM the total and local memory bandwidth
- * are enumerated as part of L3 monitoring.
- */
-static void l3_mon_evt_init(struct rdt_resource *r)
-{
-	INIT_LIST_HEAD(&r->evt_list);
-
-	if (resctrl_arch_is_llc_occupancy_enabled())
-		list_add_tail(&llc_occupancy_event.list, &r->evt_list);
-	if (resctrl_arch_is_mbm_total_enabled())
-		list_add_tail(&mbm_total_event.list, &r->evt_list);
-	if (resctrl_arch_is_mbm_local_enabled())
-		list_add_tail(&mbm_local_event.list, &r->evt_list);
-}
-
 /*
  * The power-on reset value of MSR_RMID_SNC_CONFIG is 0x1
  * which indicates that RMIDs are configured in legacy mode.
@@ -1193,51 +340,6 @@ static __init int snc_get_config(void)
 	return ret;
 }
 
-/**
- * resctrl_mon_resource_init() - Initialise global monitoring structures.
- *
- * Allocate and initialise global monitor resources that do not belong to a
- * specific domain. i.e. the rmid_ptrs[] used for the limbo and free lists.
- * Called once during boot after the struct rdt_resource's have been configured
- * but before the filesystem is mounted.
- * Resctrl's cpuhp callbacks may be called before this point to bring a domain
- * online.
- *
- * Returns 0 for success, or -ENOMEM.
- */
-int resctrl_mon_resource_init(void)
-{
-	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
-	int ret;
-
-	if (!r->mon_capable)
-		return 0;
-
-	ret = dom_data_init(r);
-	if (ret)
-		return ret;
-
-	l3_mon_evt_init(r);
-
-	if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_TOTAL_EVENT_ID)) {
-		mbm_total_event.configurable = true;
-		resctrl_file_fflags_init("mbm_total_bytes_config",
-					 RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
-	}
-	if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_LOCAL_EVENT_ID)) {
-		mbm_local_event.configurable = true;
-		resctrl_file_fflags_init("mbm_local_bytes_config",
-					 RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
-	}
-
-	if (resctrl_arch_is_mbm_local_enabled())
-		mba_mbps_default_event = QOS_L3_MBM_LOCAL_EVENT_ID;
-	else if (resctrl_arch_is_mbm_total_enabled())
-		mba_mbps_default_event = QOS_L3_MBM_TOTAL_EVENT_ID;
-
-	return 0;
-}
-
 int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 {
 	unsigned int mbm_offset = boot_cpu_data.x86_cache_mbm_width_offset;
@@ -1285,13 +387,6 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 	return 0;
 }
 
-void resctrl_mon_resource_exit(void)
-{
-	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
-
-	dom_data_exit(r);
-}
-
 void __init intel_rdt_mbm_apply_quirk(void)
 {
 	int cf_index;
diff --git a/arch/x86/kernel/cpu/resctrl/monitor_trace.h b/arch/x86/kernel/cpu/resctrl/monitor_trace.h
deleted file mode 100644
index ade67daf42c23..0000000000000
--- a/arch/x86/kernel/cpu/resctrl/monitor_trace.h
+++ /dev/null
@@ -1,31 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM resctrl
-
-#if !defined(_FS_RESCTRL_MONITOR_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _FS_RESCTRL_MONITOR_TRACE_H
-
-#include <linux/tracepoint.h>
-
-TRACE_EVENT(mon_llc_occupancy_limbo,
-	    TP_PROTO(u32 ctrl_hw_id, u32 mon_hw_id, int domain_id, u64 llc_occupancy_bytes),
-	    TP_ARGS(ctrl_hw_id, mon_hw_id, domain_id, llc_occupancy_bytes),
-	    TP_STRUCT__entry(__field(u32, ctrl_hw_id)
-			     __field(u32, mon_hw_id)
-			     __field(int, domain_id)
-			     __field(u64, llc_occupancy_bytes)),
-	    TP_fast_assign(__entry->ctrl_hw_id = ctrl_hw_id;
-			   __entry->mon_hw_id = mon_hw_id;
-			   __entry->domain_id = domain_id;
-			   __entry->llc_occupancy_bytes = llc_occupancy_bytes;),
-	    TP_printk("ctrl_hw_id=%u mon_hw_id=%u domain_id=%d llc_occupancy_bytes=%llu",
-		      __entry->ctrl_hw_id, __entry->mon_hw_id, __entry->domain_id,
-		      __entry->llc_occupancy_bytes)
-	   );
-
-#endif /* _FS_RESCTRL_MONITOR_TRACE_H */
-
-#undef TRACE_INCLUDE_PATH
-#define TRACE_INCLUDE_PATH .
-#define TRACE_INCLUDE_FILE monitor_trace
-#include <trace/define_trace.h>
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index 5698d7d273900..241d0d7e1cb5f 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -12,17 +12,10 @@
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
 #include <linux/cacheflush.h>
-#include <linux/cacheinfo.h>
 #include <linux/cpu.h>
-#include <linux/cpumask.h>
-#include <linux/debugfs.h>
-#include <linux/kthread.h>
-#include <linux/mman.h>
 #include <linux/perf_event.h>
 #include <linux/pm_qos.h>
 #include <linux/resctrl.h>
-#include <linux/slab.h>
-#include <linux/uaccess.h>
 
 #include <asm/cpu_device_id.h>
 #include <asm/perf_event.h>
@@ -31,6 +24,7 @@
 #include "internal.h"
 
 #define CREATE_TRACE_POINTS
+
 #include "pseudo_lock_trace.h"
 
 /*
@@ -39,29 +33,6 @@
  */
 static u64 prefetch_disable_bits;
 
-/*
- * Major number assigned to and shared by all devices exposing
- * pseudo-locked regions.
- */
-static unsigned int pseudo_lock_major;
-static unsigned long pseudo_lock_minor_avail = GENMASK(MINORBITS, 0);
-
-static char *pseudo_lock_devnode(const struct device *dev, umode_t *mode)
-{
-	const struct rdtgroup *rdtgrp;
-
-	rdtgrp = dev_get_drvdata(dev);
-	if (mode)
-		*mode = 0600;
-	guard(mutex)(&rdtgroup_mutex);
-	return kasprintf(GFP_KERNEL, "pseudo_lock/%s", rdt_kn_name(rdtgrp->kn));
-}
-
-static const struct class pseudo_lock_class = {
-	.name = "pseudo_lock",
-	.devnode = pseudo_lock_devnode,
-};
-
 /**
  * resctrl_arch_get_prefetch_disable_bits - prefetch disable bits of supported
  *                                          platforms
@@ -122,298 +93,6 @@ u64 resctrl_arch_get_prefetch_disable_bits(void)
 	return prefetch_disable_bits;
 }
 
-/**
- * pseudo_lock_minor_get - Obtain available minor number
- * @minor: Pointer to where new minor number will be stored
- *
- * A bitmask is used to track available minor numbers. Here the next free
- * minor number is marked as unavailable and returned.
- *
- * Return: 0 on success, <0 on failure.
- */
-static int pseudo_lock_minor_get(unsigned int *minor)
-{
-	unsigned long first_bit;
-
-	first_bit = find_first_bit(&pseudo_lock_minor_avail, MINORBITS);
-
-	if (first_bit == MINORBITS)
-		return -ENOSPC;
-
-	__clear_bit(first_bit, &pseudo_lock_minor_avail);
-	*minor = first_bit;
-
-	return 0;
-}
-
-/**
- * pseudo_lock_minor_release - Return minor number to available
- * @minor: The minor number made available
- */
-static void pseudo_lock_minor_release(unsigned int minor)
-{
-	__set_bit(minor, &pseudo_lock_minor_avail);
-}
-
-/**
- * region_find_by_minor - Locate a pseudo-lock region by inode minor number
- * @minor: The minor number of the device representing pseudo-locked region
- *
- * When the character device is accessed we need to determine which
- * pseudo-locked region it belongs to. This is done by matching the minor
- * number of the device to the pseudo-locked region it belongs.
- *
- * Minor numbers are assigned at the time a pseudo-locked region is associated
- * with a cache instance.
- *
- * Return: On success return pointer to resource group owning the pseudo-locked
- *         region, NULL on failure.
- */
-static struct rdtgroup *region_find_by_minor(unsigned int minor)
-{
-	struct rdtgroup *rdtgrp, *rdtgrp_match = NULL;
-
-	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
-		if (rdtgrp->plr && rdtgrp->plr->minor == minor) {
-			rdtgrp_match = rdtgrp;
-			break;
-		}
-	}
-	return rdtgrp_match;
-}
-
-/**
- * struct pseudo_lock_pm_req - A power management QoS request list entry
- * @list:	Entry within the @pm_reqs list for a pseudo-locked region
- * @req:	PM QoS request
- */
-struct pseudo_lock_pm_req {
-	struct list_head list;
-	struct dev_pm_qos_request req;
-};
-
-static void pseudo_lock_cstates_relax(struct pseudo_lock_region *plr)
-{
-	struct pseudo_lock_pm_req *pm_req, *next;
-
-	list_for_each_entry_safe(pm_req, next, &plr->pm_reqs, list) {
-		dev_pm_qos_remove_request(&pm_req->req);
-		list_del(&pm_req->list);
-		kfree(pm_req);
-	}
-}
-
-/**
- * pseudo_lock_cstates_constrain - Restrict cores from entering C6
- * @plr: Pseudo-locked region
- *
- * To prevent the cache from being affected by power management entering
- * C6 has to be avoided. This is accomplished by requesting a latency
- * requirement lower than lowest C6 exit latency of all supported
- * platforms as found in the cpuidle state tables in the intel_idle driver.
- * At this time it is possible to do so with a single latency requirement
- * for all supported platforms.
- *
- * Since Goldmont is supported, which is affected by X86_BUG_MONITOR,
- * the ACPI latencies need to be considered while keeping in mind that C2
- * may be set to map to deeper sleep states. In this case the latency
- * requirement needs to prevent entering C2 also.
- *
- * Return: 0 on success, <0 on failure
- */
-static int pseudo_lock_cstates_constrain(struct pseudo_lock_region *plr)
-{
-	struct pseudo_lock_pm_req *pm_req;
-	int cpu;
-	int ret;
-
-	for_each_cpu(cpu, &plr->d->hdr.cpu_mask) {
-		pm_req = kzalloc(sizeof(*pm_req), GFP_KERNEL);
-		if (!pm_req) {
-			rdt_last_cmd_puts("Failure to allocate memory for PM QoS\n");
-			ret = -ENOMEM;
-			goto out_err;
-		}
-		ret = dev_pm_qos_add_request(get_cpu_device(cpu),
-					     &pm_req->req,
-					     DEV_PM_QOS_RESUME_LATENCY,
-					     30);
-		if (ret < 0) {
-			rdt_last_cmd_printf("Failed to add latency req CPU%d\n",
-					    cpu);
-			kfree(pm_req);
-			ret = -1;
-			goto out_err;
-		}
-		list_add(&pm_req->list, &plr->pm_reqs);
-	}
-
-	return 0;
-
-out_err:
-	pseudo_lock_cstates_relax(plr);
-	return ret;
-}
-
-/**
- * pseudo_lock_region_clear - Reset pseudo-lock region data
- * @plr: pseudo-lock region
- *
- * All content of the pseudo-locked region is reset - any memory allocated
- * freed.
- *
- * Return: void
- */
-static void pseudo_lock_region_clear(struct pseudo_lock_region *plr)
-{
-	plr->size = 0;
-	plr->line_size = 0;
-	kfree(plr->kmem);
-	plr->kmem = NULL;
-	plr->s = NULL;
-	if (plr->d)
-		plr->d->plr = NULL;
-	plr->d = NULL;
-	plr->cbm = 0;
-	plr->debugfs_dir = NULL;
-}
-
-/**
- * pseudo_lock_region_init - Initialize pseudo-lock region information
- * @plr: pseudo-lock region
- *
- * Called after user provided a schemata to be pseudo-locked. From the
- * schemata the &struct pseudo_lock_region is on entry already initialized
- * with the resource, domain, and capacity bitmask. Here the information
- * required for pseudo-locking is deduced from this data and &struct
- * pseudo_lock_region initialized further. This information includes:
- * - size in bytes of the region to be pseudo-locked
- * - cache line size to know the stride with which data needs to be accessed
- *   to be pseudo-locked
- * - a cpu associated with the cache instance on which the pseudo-locking
- *   flow can be executed
- *
- * Return: 0 on success, <0 on failure. Descriptive error will be written
- * to last_cmd_status buffer.
- */
-static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
-{
-	enum resctrl_scope scope = plr->s->res->ctrl_scope;
-	struct cacheinfo *ci;
-	int ret;
-
-	if (WARN_ON_ONCE(scope != RESCTRL_L2_CACHE && scope != RESCTRL_L3_CACHE))
-		return -ENODEV;
-
-	/* Pick the first cpu we find that is associated with the cache. */
-	plr->cpu = cpumask_first(&plr->d->hdr.cpu_mask);
-
-	if (!cpu_online(plr->cpu)) {
-		rdt_last_cmd_printf("CPU %u associated with cache not online\n",
-				    plr->cpu);
-		ret = -ENODEV;
-		goto out_region;
-	}
-
-	ci = get_cpu_cacheinfo_level(plr->cpu, scope);
-	if (ci) {
-		plr->line_size = ci->coherency_line_size;
-		plr->size = rdtgroup_cbm_to_size(plr->s->res, plr->d, plr->cbm);
-		return 0;
-	}
-
-	ret = -1;
-	rdt_last_cmd_puts("Unable to determine cache line size\n");
-out_region:
-	pseudo_lock_region_clear(plr);
-	return ret;
-}
-
-/**
- * pseudo_lock_init - Initialize a pseudo-lock region
- * @rdtgrp: resource group to which new pseudo-locked region will belong
- *
- * A pseudo-locked region is associated with a resource group. When this
- * association is created the pseudo-locked region is initialized. The
- * details of the pseudo-locked region are not known at this time so only
- * allocation is done and association established.
- *
- * Return: 0 on success, <0 on failure
- */
-static int pseudo_lock_init(struct rdtgroup *rdtgrp)
-{
-	struct pseudo_lock_region *plr;
-
-	plr = kzalloc(sizeof(*plr), GFP_KERNEL);
-	if (!plr)
-		return -ENOMEM;
-
-	init_waitqueue_head(&plr->lock_thread_wq);
-	INIT_LIST_HEAD(&plr->pm_reqs);
-	rdtgrp->plr = plr;
-	return 0;
-}
-
-/**
- * pseudo_lock_region_alloc - Allocate kernel memory that will be pseudo-locked
- * @plr: pseudo-lock region
- *
- * Initialize the details required to set up the pseudo-locked region and
- * allocate the contiguous memory that will be pseudo-locked to the cache.
- *
- * Return: 0 on success, <0 on failure.  Descriptive error will be written
- * to last_cmd_status buffer.
- */
-static int pseudo_lock_region_alloc(struct pseudo_lock_region *plr)
-{
-	int ret;
-
-	ret = pseudo_lock_region_init(plr);
-	if (ret < 0)
-		return ret;
-
-	/*
-	 * We do not yet support contiguous regions larger than
-	 * KMALLOC_MAX_SIZE.
-	 */
-	if (plr->size > KMALLOC_MAX_SIZE) {
-		rdt_last_cmd_puts("Requested region exceeds maximum size\n");
-		ret = -E2BIG;
-		goto out_region;
-	}
-
-	plr->kmem = kzalloc(plr->size, GFP_KERNEL);
-	if (!plr->kmem) {
-		rdt_last_cmd_puts("Unable to allocate memory\n");
-		ret = -ENOMEM;
-		goto out_region;
-	}
-
-	ret = 0;
-	goto out;
-out_region:
-	pseudo_lock_region_clear(plr);
-out:
-	return ret;
-}
-
-/**
- * pseudo_lock_free - Free a pseudo-locked region
- * @rdtgrp: resource group to which pseudo-locked region belonged
- *
- * The pseudo-locked region's resources have already been released, or not
- * yet created at this point. Now it can be freed and disassociated from the
- * resource group.
- *
- * Return: void
- */
-static void pseudo_lock_free(struct rdtgroup *rdtgrp)
-{
-	pseudo_lock_region_clear(rdtgrp->plr);
-	kfree(rdtgrp->plr);
-	rdtgrp->plr = NULL;
-}
-
 /**
  * resctrl_arch_pseudo_lock_fn - Load kernel memory into cache
  * @_plr: the pseudo-lock region descriptor
@@ -543,340 +222,6 @@ int resctrl_arch_pseudo_lock_fn(void *_plr)
 	return 0;
 }
 
-/**
- * rdtgroup_monitor_in_progress - Test if monitoring in progress
- * @rdtgrp: resource group being queried
- *
- * Return: 1 if monitor groups have been created for this resource
- * group, 0 otherwise.
- */
-static int rdtgroup_monitor_in_progress(struct rdtgroup *rdtgrp)
-{
-	return !list_empty(&rdtgrp->mon.crdtgrp_list);
-}
-
-/**
- * rdtgroup_locksetup_user_restrict - Restrict user access to group
- * @rdtgrp: resource group needing access restricted
- *
- * A resource group used for cache pseudo-locking cannot have cpus or tasks
- * assigned to it. This is communicated to the user by restricting access
- * to all the files that can be used to make such changes.
- *
- * Permissions restored with rdtgroup_locksetup_user_restore()
- *
- * Return: 0 on success, <0 on failure. If a failure occurs during the
- * restriction of access an attempt will be made to restore permissions but
- * the state of the mode of these files will be uncertain when a failure
- * occurs.
- */
-static int rdtgroup_locksetup_user_restrict(struct rdtgroup *rdtgrp)
-{
-	int ret;
-
-	ret = rdtgroup_kn_mode_restrict(rdtgrp, "tasks");
-	if (ret)
-		return ret;
-
-	ret = rdtgroup_kn_mode_restrict(rdtgrp, "cpus");
-	if (ret)
-		goto err_tasks;
-
-	ret = rdtgroup_kn_mode_restrict(rdtgrp, "cpus_list");
-	if (ret)
-		goto err_cpus;
-
-	if (resctrl_arch_mon_capable()) {
-		ret = rdtgroup_kn_mode_restrict(rdtgrp, "mon_groups");
-		if (ret)
-			goto err_cpus_list;
-	}
-
-	ret = 0;
-	goto out;
-
-err_cpus_list:
-	rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0777);
-err_cpus:
-	rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0777);
-err_tasks:
-	rdtgroup_kn_mode_restore(rdtgrp, "tasks", 0777);
-out:
-	return ret;
-}
-
-/**
- * rdtgroup_locksetup_user_restore - Restore user access to group
- * @rdtgrp: resource group needing access restored
- *
- * Restore all file access previously removed using
- * rdtgroup_locksetup_user_restrict()
- *
- * Return: 0 on success, <0 on failure.  If a failure occurs during the
- * restoration of access an attempt will be made to restrict permissions
- * again but the state of the mode of these files will be uncertain when
- * a failure occurs.
- */
-static int rdtgroup_locksetup_user_restore(struct rdtgroup *rdtgrp)
-{
-	int ret;
-
-	ret = rdtgroup_kn_mode_restore(rdtgrp, "tasks", 0777);
-	if (ret)
-		return ret;
-
-	ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0777);
-	if (ret)
-		goto err_tasks;
-
-	ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0777);
-	if (ret)
-		goto err_cpus;
-
-	if (resctrl_arch_mon_capable()) {
-		ret = rdtgroup_kn_mode_restore(rdtgrp, "mon_groups", 0777);
-		if (ret)
-			goto err_cpus_list;
-	}
-
-	ret = 0;
-	goto out;
-
-err_cpus_list:
-	rdtgroup_kn_mode_restrict(rdtgrp, "cpus_list");
-err_cpus:
-	rdtgroup_kn_mode_restrict(rdtgrp, "cpus");
-err_tasks:
-	rdtgroup_kn_mode_restrict(rdtgrp, "tasks");
-out:
-	return ret;
-}
-
-/**
- * rdtgroup_locksetup_enter - Resource group enters locksetup mode
- * @rdtgrp: resource group requested to enter locksetup mode
- *
- * A resource group enters locksetup mode to reflect that it would be used
- * to represent a pseudo-locked region and is in the process of being set
- * up to do so. A resource group used for a pseudo-locked region would
- * lose the closid associated with it so we cannot allow it to have any
- * tasks or cpus assigned nor permit tasks or cpus to be assigned in the
- * future. Monitoring of a pseudo-locked region is not allowed either.
- *
- * The above and more restrictions on a pseudo-locked region are checked
- * for and enforced before the resource group enters the locksetup mode.
- *
- * Returns: 0 if the resource group successfully entered locksetup mode, <0
- * on failure. On failure the last_cmd_status buffer is updated with text to
- * communicate details of failure to the user.
- */
-int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp)
-{
-	int ret;
-
-	/*
-	 * The default resource group can neither be removed nor lose the
-	 * default closid associated with it.
-	 */
-	if (rdtgrp == &rdtgroup_default) {
-		rdt_last_cmd_puts("Cannot pseudo-lock default group\n");
-		return -EINVAL;
-	}
-
-	/*
-	 * Cache Pseudo-locking not supported when CDP is enabled.
-	 *
-	 * Some things to consider if you would like to enable this
-	 * support (using L3 CDP as example):
-	 * - When CDP is enabled two separate resources are exposed,
-	 *   L3DATA and L3CODE, but they are actually on the same cache.
-	 *   The implication for pseudo-locking is that if a
-	 *   pseudo-locked region is created on a domain of one
-	 *   resource (eg. L3CODE), then a pseudo-locked region cannot
-	 *   be created on that same domain of the other resource
-	 *   (eg. L3DATA). This is because the creation of a
-	 *   pseudo-locked region involves a call to wbinvd that will
-	 *   affect all cache allocations on particular domain.
-	 * - Considering the previous, it may be possible to only
-	 *   expose one of the CDP resources to pseudo-locking and
-	 *   hide the other. For example, we could consider to only
-	 *   expose L3DATA and since the L3 cache is unified it is
-	 *   still possible to place instructions there are execute it.
-	 * - If only one region is exposed to pseudo-locking we should
-	 *   still keep in mind that availability of a portion of cache
-	 *   for pseudo-locking should take into account both resources.
-	 *   Similarly, if a pseudo-locked region is created in one
-	 *   resource, the portion of cache used by it should be made
-	 *   unavailable to all future allocations from both resources.
-	 */
-	if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3) ||
-	    resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2)) {
-		rdt_last_cmd_puts("CDP enabled\n");
-		return -EINVAL;
-	}
-
-	/*
-	 * Not knowing the bits to disable prefetching implies that this
-	 * platform does not support Cache Pseudo-Locking.
-	 */
-	if (resctrl_arch_get_prefetch_disable_bits() == 0) {
-		rdt_last_cmd_puts("Pseudo-locking not supported\n");
-		return -EINVAL;
-	}
-
-	if (rdtgroup_monitor_in_progress(rdtgrp)) {
-		rdt_last_cmd_puts("Monitoring in progress\n");
-		return -EINVAL;
-	}
-
-	if (rdtgroup_tasks_assigned(rdtgrp)) {
-		rdt_last_cmd_puts("Tasks assigned to resource group\n");
-		return -EINVAL;
-	}
-
-	if (!cpumask_empty(&rdtgrp->cpu_mask)) {
-		rdt_last_cmd_puts("CPUs assigned to resource group\n");
-		return -EINVAL;
-	}
-
-	if (rdtgroup_locksetup_user_restrict(rdtgrp)) {
-		rdt_last_cmd_puts("Unable to modify resctrl permissions\n");
-		return -EIO;
-	}
-
-	ret = pseudo_lock_init(rdtgrp);
-	if (ret) {
-		rdt_last_cmd_puts("Unable to init pseudo-lock region\n");
-		goto out_release;
-	}
-
-	/*
-	 * If this system is capable of monitoring a rmid would have been
-	 * allocated when the control group was created. This is not needed
-	 * anymore when this group would be used for pseudo-locking. This
-	 * is safe to call on platforms not capable of monitoring.
-	 */
-	free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
-
-	ret = 0;
-	goto out;
-
-out_release:
-	rdtgroup_locksetup_user_restore(rdtgrp);
-out:
-	return ret;
-}
-
-/**
- * rdtgroup_locksetup_exit - resource group exist locksetup mode
- * @rdtgrp: resource group
- *
- * When a resource group exits locksetup mode the earlier restrictions are
- * lifted.
- *
- * Return: 0 on success, <0 on failure
- */
-int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
-{
-	int ret;
-
-	if (resctrl_arch_mon_capable()) {
-		ret = alloc_rmid(rdtgrp->closid);
-		if (ret < 0) {
-			rdt_last_cmd_puts("Out of RMIDs\n");
-			return ret;
-		}
-		rdtgrp->mon.rmid = ret;
-	}
-
-	ret = rdtgroup_locksetup_user_restore(rdtgrp);
-	if (ret) {
-		free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
-		return ret;
-	}
-
-	pseudo_lock_free(rdtgrp);
-	return 0;
-}
-
-/**
- * rdtgroup_cbm_overlaps_pseudo_locked - Test if CBM or portion is pseudo-locked
- * @d: RDT domain
- * @cbm: CBM to test
- *
- * @d represents a cache instance and @cbm a capacity bitmask that is
- * considered for it. Determine if @cbm overlaps with any existing
- * pseudo-locked region on @d.
- *
- * @cbm is unsigned long, even if only 32 bits are used, to make the
- * bitmap functions work correctly.
- *
- * Return: true if @cbm overlaps with pseudo-locked region on @d, false
- * otherwise.
- */
-bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm)
-{
-	unsigned int cbm_len;
-	unsigned long cbm_b;
-
-	if (d->plr) {
-		cbm_len = d->plr->s->res->cache.cbm_len;
-		cbm_b = d->plr->cbm;
-		if (bitmap_intersects(&cbm, &cbm_b, cbm_len))
-			return true;
-	}
-	return false;
-}
-
-/**
- * rdtgroup_pseudo_locked_in_hierarchy - Pseudo-locked region in cache hierarchy
- * @d: RDT domain under test
- *
- * The setup of a pseudo-locked region affects all cache instances within
- * the hierarchy of the region. It is thus essential to know if any
- * pseudo-locked regions exist within a cache hierarchy to prevent any
- * attempts to create new pseudo-locked regions in the same hierarchy.
- *
- * Return: true if a pseudo-locked region exists in the hierarchy of @d or
- *         if it is not possible to test due to memory allocation issue,
- *         false otherwise.
- */
-bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d)
-{
-	struct rdt_ctrl_domain *d_i;
-	cpumask_var_t cpu_with_psl;
-	struct rdt_resource *r;
-	bool ret = false;
-
-	/* Walking r->domains, ensure it can't race with cpuhp */
-	lockdep_assert_cpus_held();
-
-	if (!zalloc_cpumask_var(&cpu_with_psl, GFP_KERNEL))
-		return true;
-
-	/*
-	 * First determine which cpus have pseudo-locked regions
-	 * associated with them.
-	 */
-	for_each_alloc_capable_rdt_resource(r) {
-		list_for_each_entry(d_i, &r->ctrl_domains, hdr.list) {
-			if (d_i->plr)
-				cpumask_or(cpu_with_psl, cpu_with_psl,
-					   &d_i->hdr.cpu_mask);
-		}
-	}
-
-	/*
-	 * Next test if new pseudo-locked region would intersect with
-	 * existing region.
-	 */
-	if (cpumask_intersects(&d->hdr.cpu_mask, cpu_with_psl))
-		ret = true;
-
-	free_cpumask_var(cpu_with_psl);
-	return ret;
-}
-
 /**
  * resctrl_arch_measure_cycles_lat_fn - Measure cycle latency to read
  *                                      pseudo-locked memory
@@ -1169,434 +514,3 @@ int resctrl_arch_measure_l3_residency(void *_plr)
 	wake_up_interruptible(&plr->lock_thread_wq);
 	return 0;
 }
-
-/**
- * pseudo_lock_measure_cycles - Trigger latency measure to pseudo-locked region
- * @rdtgrp: Resource group to which the pseudo-locked region belongs.
- * @sel: Selector of which measurement to perform on a pseudo-locked region.
- *
- * The measurement of latency to access a pseudo-locked region should be
- * done from a cpu that is associated with that pseudo-locked region.
- * Determine which cpu is associated with this region and start a thread on
- * that cpu to perform the measurement, wait for that thread to complete.
- *
- * Return: 0 on success, <0 on failure
- */
-static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
-{
-	struct pseudo_lock_region *plr = rdtgrp->plr;
-	struct task_struct *thread;
-	unsigned int cpu;
-	int ret = -1;
-
-	cpus_read_lock();
-	mutex_lock(&rdtgroup_mutex);
-
-	if (rdtgrp->flags & RDT_DELETED) {
-		ret = -ENODEV;
-		goto out;
-	}
-
-	if (!plr->d) {
-		ret = -ENODEV;
-		goto out;
-	}
-
-	plr->thread_done = 0;
-	cpu = cpumask_first(&plr->d->hdr.cpu_mask);
-	if (!cpu_online(cpu)) {
-		ret = -ENODEV;
-		goto out;
-	}
-
-	plr->cpu = cpu;
-
-	if (sel == 1)
-		thread = kthread_run_on_cpu(resctrl_arch_measure_cycles_lat_fn,
-					    plr, cpu, "pseudo_lock_measure/%u");
-	else if (sel == 2)
-		thread = kthread_run_on_cpu(resctrl_arch_measure_l2_residency,
-					    plr, cpu, "pseudo_lock_measure/%u");
-	else if (sel == 3)
-		thread = kthread_run_on_cpu(resctrl_arch_measure_l3_residency,
-					    plr, cpu, "pseudo_lock_measure/%u");
-	else
-		goto out;
-
-	if (IS_ERR(thread)) {
-		ret = PTR_ERR(thread);
-		goto out;
-	}
-
-	ret = wait_event_interruptible(plr->lock_thread_wq,
-				       plr->thread_done == 1);
-	if (ret < 0)
-		goto out;
-
-	ret = 0;
-
-out:
-	mutex_unlock(&rdtgroup_mutex);
-	cpus_read_unlock();
-	return ret;
-}
-
-static ssize_t pseudo_lock_measure_trigger(struct file *file,
-					   const char __user *user_buf,
-					   size_t count, loff_t *ppos)
-{
-	struct rdtgroup *rdtgrp = file->private_data;
-	size_t buf_size;
-	char buf[32];
-	int ret;
-	int sel;
-
-	buf_size = min(count, (sizeof(buf) - 1));
-	if (copy_from_user(buf, user_buf, buf_size))
-		return -EFAULT;
-
-	buf[buf_size] = '\0';
-	ret = kstrtoint(buf, 10, &sel);
-	if (ret == 0) {
-		if (sel != 1 && sel != 2 && sel != 3)
-			return -EINVAL;
-		ret = debugfs_file_get(file->f_path.dentry);
-		if (ret)
-			return ret;
-		ret = pseudo_lock_measure_cycles(rdtgrp, sel);
-		if (ret == 0)
-			ret = count;
-		debugfs_file_put(file->f_path.dentry);
-	}
-
-	return ret;
-}
-
-static const struct file_operations pseudo_measure_fops = {
-	.write = pseudo_lock_measure_trigger,
-	.open = simple_open,
-	.llseek = default_llseek,
-};
-
-/**
- * rdtgroup_pseudo_lock_create - Create a pseudo-locked region
- * @rdtgrp: resource group to which pseudo-lock region belongs
- *
- * Called when a resource group in the pseudo-locksetup mode receives a
- * valid schemata that should be pseudo-locked. Since the resource group is
- * in pseudo-locksetup mode the &struct pseudo_lock_region has already been
- * allocated and initialized with the essential information. If a failure
- * occurs the resource group remains in the pseudo-locksetup mode with the
- * &struct pseudo_lock_region associated with it, but cleared from all
- * information and ready for the user to re-attempt pseudo-locking by
- * writing the schemata again.
- *
- * Return: 0 if the pseudo-locked region was successfully pseudo-locked, <0
- * on failure. Descriptive error will be written to last_cmd_status buffer.
- */
-int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
-{
-	struct pseudo_lock_region *plr = rdtgrp->plr;
-	struct task_struct *thread;
-	unsigned int new_minor;
-	struct device *dev;
-	char *kn_name __free(kfree) = NULL;
-	int ret;
-
-	ret = pseudo_lock_region_alloc(plr);
-	if (ret < 0)
-		return ret;
-
-	ret = pseudo_lock_cstates_constrain(plr);
-	if (ret < 0) {
-		ret = -EINVAL;
-		goto out_region;
-	}
-	kn_name = kstrdup(rdt_kn_name(rdtgrp->kn), GFP_KERNEL);
-	if (!kn_name) {
-		ret = -ENOMEM;
-		goto out_cstates;
-	}
-
-	plr->thread_done = 0;
-
-	thread = kthread_run_on_cpu(resctrl_arch_pseudo_lock_fn, plr,
-				    plr->cpu, "pseudo_lock/%u");
-	if (IS_ERR(thread)) {
-		ret = PTR_ERR(thread);
-		rdt_last_cmd_printf("Locking thread returned error %d\n", ret);
-		goto out_cstates;
-	}
-
-	ret = wait_event_interruptible(plr->lock_thread_wq,
-				       plr->thread_done == 1);
-	if (ret < 0) {
-		/*
-		 * If the thread does not get on the CPU for whatever
-		 * reason and the process which sets up the region is
-		 * interrupted then this will leave the thread in runnable
-		 * state and once it gets on the CPU it will dereference
-		 * the cleared, but not freed, plr struct resulting in an
-		 * empty pseudo-locking loop.
-		 */
-		rdt_last_cmd_puts("Locking thread interrupted\n");
-		goto out_cstates;
-	}
-
-	ret = pseudo_lock_minor_get(&new_minor);
-	if (ret < 0) {
-		rdt_last_cmd_puts("Unable to obtain a new minor number\n");
-		goto out_cstates;
-	}
-
-	/*
-	 * Unlock access but do not release the reference. The
-	 * pseudo-locked region will still be here on return.
-	 *
-	 * The mutex has to be released temporarily to avoid a potential
-	 * deadlock with the mm->mmap_lock which is obtained in the
-	 * device_create() and debugfs_create_dir() callpath below as well as
-	 * before the mmap() callback is called.
-	 */
-	mutex_unlock(&rdtgroup_mutex);
-
-	if (!IS_ERR_OR_NULL(debugfs_resctrl)) {
-		plr->debugfs_dir = debugfs_create_dir(kn_name, debugfs_resctrl);
-		if (!IS_ERR_OR_NULL(plr->debugfs_dir))
-			debugfs_create_file("pseudo_lock_measure", 0200,
-					    plr->debugfs_dir, rdtgrp,
-					    &pseudo_measure_fops);
-	}
-
-	dev = device_create(&pseudo_lock_class, NULL,
-			    MKDEV(pseudo_lock_major, new_minor),
-			    rdtgrp, "%s", kn_name);
-
-	mutex_lock(&rdtgroup_mutex);
-
-	if (IS_ERR(dev)) {
-		ret = PTR_ERR(dev);
-		rdt_last_cmd_printf("Failed to create character device: %d\n",
-				    ret);
-		goto out_debugfs;
-	}
-
-	/* We released the mutex - check if group was removed while we did so */
-	if (rdtgrp->flags & RDT_DELETED) {
-		ret = -ENODEV;
-		goto out_device;
-	}
-
-	plr->minor = new_minor;
-
-	rdtgrp->mode = RDT_MODE_PSEUDO_LOCKED;
-	closid_free(rdtgrp->closid);
-	rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0444);
-	rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0444);
-
-	ret = 0;
-	goto out;
-
-out_device:
-	device_destroy(&pseudo_lock_class, MKDEV(pseudo_lock_major, new_minor));
-out_debugfs:
-	debugfs_remove_recursive(plr->debugfs_dir);
-	pseudo_lock_minor_release(new_minor);
-out_cstates:
-	pseudo_lock_cstates_relax(plr);
-out_region:
-	pseudo_lock_region_clear(plr);
-out:
-	return ret;
-}
-
-/**
- * rdtgroup_pseudo_lock_remove - Remove a pseudo-locked region
- * @rdtgrp: resource group to which the pseudo-locked region belongs
- *
- * The removal of a pseudo-locked region can be initiated when the resource
- * group is removed from user space via a "rmdir" from userspace or the
- * unmount of the resctrl filesystem. On removal the resource group does
- * not go back to pseudo-locksetup mode before it is removed, instead it is
- * removed directly. There is thus asymmetry with the creation where the
- * &struct pseudo_lock_region is removed here while it was not created in
- * rdtgroup_pseudo_lock_create().
- *
- * Return: void
- */
-void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp)
-{
-	struct pseudo_lock_region *plr = rdtgrp->plr;
-
-	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
-		/*
-		 * Default group cannot be a pseudo-locked region so we can
-		 * free closid here.
-		 */
-		closid_free(rdtgrp->closid);
-		goto free;
-	}
-
-	pseudo_lock_cstates_relax(plr);
-	debugfs_remove_recursive(rdtgrp->plr->debugfs_dir);
-	device_destroy(&pseudo_lock_class, MKDEV(pseudo_lock_major, plr->minor));
-	pseudo_lock_minor_release(plr->minor);
-
-free:
-	pseudo_lock_free(rdtgrp);
-}
-
-static int pseudo_lock_dev_open(struct inode *inode, struct file *filp)
-{
-	struct rdtgroup *rdtgrp;
-
-	mutex_lock(&rdtgroup_mutex);
-
-	rdtgrp = region_find_by_minor(iminor(inode));
-	if (!rdtgrp) {
-		mutex_unlock(&rdtgroup_mutex);
-		return -ENODEV;
-	}
-
-	filp->private_data = rdtgrp;
-	atomic_inc(&rdtgrp->waitcount);
-	/* Perform a non-seekable open - llseek is not supported */
-	filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
-
-	mutex_unlock(&rdtgroup_mutex);
-
-	return 0;
-}
-
-static int pseudo_lock_dev_release(struct inode *inode, struct file *filp)
-{
-	struct rdtgroup *rdtgrp;
-
-	mutex_lock(&rdtgroup_mutex);
-	rdtgrp = filp->private_data;
-	WARN_ON(!rdtgrp);
-	if (!rdtgrp) {
-		mutex_unlock(&rdtgroup_mutex);
-		return -ENODEV;
-	}
-	filp->private_data = NULL;
-	atomic_dec(&rdtgrp->waitcount);
-	mutex_unlock(&rdtgroup_mutex);
-	return 0;
-}
-
-static int pseudo_lock_dev_mremap(struct vm_area_struct *area)
-{
-	/* Not supported */
-	return -EINVAL;
-}
-
-static const struct vm_operations_struct pseudo_mmap_ops = {
-	.mremap = pseudo_lock_dev_mremap,
-};
-
-static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma)
-{
-	unsigned long vsize = vma->vm_end - vma->vm_start;
-	unsigned long off = vma->vm_pgoff << PAGE_SHIFT;
-	struct pseudo_lock_region *plr;
-	struct rdtgroup *rdtgrp;
-	unsigned long physical;
-	unsigned long psize;
-
-	mutex_lock(&rdtgroup_mutex);
-
-	rdtgrp = filp->private_data;
-	WARN_ON(!rdtgrp);
-	if (!rdtgrp) {
-		mutex_unlock(&rdtgroup_mutex);
-		return -ENODEV;
-	}
-
-	plr = rdtgrp->plr;
-
-	if (!plr->d) {
-		mutex_unlock(&rdtgroup_mutex);
-		return -ENODEV;
-	}
-
-	/*
-	 * Task is required to run with affinity to the cpus associated
-	 * with the pseudo-locked region. If this is not the case the task
-	 * may be scheduled elsewhere and invalidate entries in the
-	 * pseudo-locked region.
-	 */
-	if (!cpumask_subset(current->cpus_ptr, &plr->d->hdr.cpu_mask)) {
-		mutex_unlock(&rdtgroup_mutex);
-		return -EINVAL;
-	}
-
-	physical = __pa(plr->kmem) >> PAGE_SHIFT;
-	psize = plr->size - off;
-
-	if (off > plr->size) {
-		mutex_unlock(&rdtgroup_mutex);
-		return -ENOSPC;
-	}
-
-	/*
-	 * Ensure changes are carried directly to the memory being mapped,
-	 * do not allow copy-on-write mapping.
-	 */
-	if (!(vma->vm_flags & VM_SHARED)) {
-		mutex_unlock(&rdtgroup_mutex);
-		return -EINVAL;
-	}
-
-	if (vsize > psize) {
-		mutex_unlock(&rdtgroup_mutex);
-		return -ENOSPC;
-	}
-
-	memset(plr->kmem + off, 0, vsize);
-
-	if (remap_pfn_range(vma, vma->vm_start, physical + vma->vm_pgoff,
-			    vsize, vma->vm_page_prot)) {
-		mutex_unlock(&rdtgroup_mutex);
-		return -EAGAIN;
-	}
-	vma->vm_ops = &pseudo_mmap_ops;
-	mutex_unlock(&rdtgroup_mutex);
-	return 0;
-}
-
-static const struct file_operations pseudo_lock_dev_fops = {
-	.owner =	THIS_MODULE,
-	.llseek =	no_llseek,
-	.read =		NULL,
-	.write =	NULL,
-	.open =		pseudo_lock_dev_open,
-	.release =	pseudo_lock_dev_release,
-	.mmap =		pseudo_lock_dev_mmap,
-};
-
-int rdt_pseudo_lock_init(void)
-{
-	int ret;
-
-	ret = register_chrdev(0, "pseudo_lock", &pseudo_lock_dev_fops);
-	if (ret < 0)
-		return ret;
-
-	pseudo_lock_major = ret;
-
-	ret = class_register(&pseudo_lock_class);
-	if (ret) {
-		unregister_chrdev(pseudo_lock_major, "pseudo_lock");
-		return ret;
-	}
-
-	return 0;
-}
-
-void rdt_pseudo_lock_release(void)
-{
-	class_unregister(&pseudo_lock_class);
-	unregister_chrdev(pseudo_lock_major, "pseudo_lock");
-	pseudo_lock_major = 0;
-}
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock_trace.h b/arch/x86/kernel/cpu/resctrl/pseudo_lock_trace.h
index 5a0fae61d3eeb..7c8aef08010f1 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock_trace.h
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock_trace.h
@@ -39,5 +39,7 @@ TRACE_EVENT(pseudo_lock_l3,
 
 #undef TRACE_INCLUDE_PATH
 #define TRACE_INCLUDE_PATH .
+
 #define TRACE_INCLUDE_FILE pseudo_lock_trace
+
 #include <trace/define_trace.h>
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index ace86b6dcedec..c7a7f0ae373ad 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -32,4547 +32,230 @@
 #include "internal.h"
 
 DEFINE_STATIC_KEY_FALSE(rdt_enable_key);
-DEFINE_STATIC_KEY_FALSE(rdt_mon_enable_key);
-DEFINE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
-
-/* Mutex to protect rdtgroup access. */
-DEFINE_MUTEX(rdtgroup_mutex);
-
-static struct kernfs_root *rdt_root;
-struct rdtgroup rdtgroup_default;
-LIST_HEAD(rdt_all_groups);
-
-/* list of entries for the schemata file */
-LIST_HEAD(resctrl_schema_all);
-
-/*
- * List of struct mon_data containing private data of event files for use by
- * rdtgroup_mondata_show(). Protected by rdtgroup_mutex.
- */
-static LIST_HEAD(mon_data_kn_priv_list);
-
-/* The filesystem can only be mounted once. */
-bool resctrl_mounted;
-
-/* Kernel fs node for "info" directory under root */
-static struct kernfs_node *kn_info;
-
-/* Kernel fs node for "mon_groups" directory under root */
-static struct kernfs_node *kn_mongrp;
-
-/* Kernel fs node for "mon_data" directory under root */
-static struct kernfs_node *kn_mondata;
-
-/*
- * Used to store the max resource name width to display the schemata names in
- * a tabular format.
- */
-int max_name_width;
-
-static struct seq_buf last_cmd_status;
-static char last_cmd_status_buf[512];
 
-static int rdtgroup_setup_root(struct rdt_fs_context *ctx);
-static void rdtgroup_destroy_root(void);
+DEFINE_STATIC_KEY_FALSE(rdt_mon_enable_key);
 
-struct dentry *debugfs_resctrl;
+DEFINE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
 
 /*
- * Memory bandwidth monitoring event to use for the default CTRL_MON group
- * and each new CTRL_MON group created by the user.  Only relevant when
- * the filesystem is mounted with the "mba_MBps" option so it does not
- * matter that it remains uninitialized on systems that do not support
- * the "mba_MBps" option.
+ * This is safe against resctrl_arch_sched_in() called from __switch_to()
+ * because __switch_to() is executed with interrupts disabled. A local call
+ * from update_closid_rmid() is protected against __switch_to() because
+ * preemption is disabled.
  */
-enum resctrl_event_id mba_mbps_default_event;
-
-static bool resctrl_debug;
-
-void rdt_last_cmd_clear(void)
-{
-	lockdep_assert_held(&rdtgroup_mutex);
-	seq_buf_clear(&last_cmd_status);
-}
-
-void rdt_last_cmd_puts(const char *s)
-{
-	lockdep_assert_held(&rdtgroup_mutex);
-	seq_buf_puts(&last_cmd_status, s);
-}
-
-void rdt_last_cmd_printf(const char *fmt, ...)
-{
-	va_list ap;
-
-	va_start(ap, fmt);
-	lockdep_assert_held(&rdtgroup_mutex);
-	seq_buf_vprintf(&last_cmd_status, fmt, ap);
-	va_end(ap);
-}
-
-void rdt_staged_configs_clear(void)
+void resctrl_arch_sync_cpu_closid_rmid(void *info)
 {
-	struct rdt_ctrl_domain *dom;
-	struct rdt_resource *r;
-
-	lockdep_assert_held(&rdtgroup_mutex);
+	struct resctrl_cpu_defaults *r = info;
 
-	for_each_alloc_capable_rdt_resource(r) {
-		list_for_each_entry(dom, &r->ctrl_domains, hdr.list)
-			memset(dom->staged_config, 0, sizeof(dom->staged_config));
+	if (r) {
+		this_cpu_write(pqr_state.default_closid, r->closid);
+		this_cpu_write(pqr_state.default_rmid, r->rmid);
 	}
-}
 
-static bool resctrl_is_mbm_enabled(void)
-{
-	return (resctrl_arch_is_mbm_total_enabled() ||
-		resctrl_arch_is_mbm_local_enabled());
+	/*
+	 * We cannot unconditionally write the MSR because the current
+	 * executing task might have its own closid selected. Just reuse
+	 * the context switch code.
+	 */
+	resctrl_arch_sched_in(current);
 }
 
-static bool resctrl_is_mbm_event(int e)
-{
-	return (e >= QOS_L3_MBM_TOTAL_EVENT_ID &&
-		e <= QOS_L3_MBM_LOCAL_EVENT_ID);
-}
+#define INVALID_CONFIG_INDEX   UINT_MAX
 
-/*
- * Trivial allocator for CLOSIDs. Use BITMAP APIs to manipulate a bitmap
- * of free CLOSIDs.
+/**
+ * mon_event_config_index_get - get the hardware index for the
+ *                              configurable event
+ * @evtid: event id.
  *
- * Using a global CLOSID across all resources has some advantages and
- * some drawbacks:
- * + We can simply set current's closid to assign a task to a resource
- *   group.
- * + Context switch code can avoid extra memory references deciding which
- *   CLOSID to load into the PQR_ASSOC MSR
- * - We give up some options in configuring resource groups across multi-socket
- *   systems.
- * - Our choices on how to configure each resource become progressively more
- *   limited as the number of resources grows.
+ * Return: 0 for evtid == QOS_L3_MBM_TOTAL_EVENT_ID
+ *         1 for evtid == QOS_L3_MBM_LOCAL_EVENT_ID
+ *         INVALID_CONFIG_INDEX for invalid evtid
  */
-static unsigned long *closid_free_map;
-static int closid_free_map_len;
-
-int closids_supported(void)
-{
-	return closid_free_map_len;
-}
-
-static int closid_init(void)
+static inline unsigned int mon_event_config_index_get(u32 evtid)
 {
-	struct resctrl_schema *s;
-	u32 rdt_min_closid = ~0;
-
-	/* Monitor only platforms still call closid_init() */
-	if (list_empty(&resctrl_schema_all))
+	switch (evtid) {
+	case QOS_L3_MBM_TOTAL_EVENT_ID:
 		return 0;
-
-	/* Compute rdt_min_closid across all resources */
-	list_for_each_entry(s, &resctrl_schema_all, list)
-		rdt_min_closid = min(rdt_min_closid, s->num_closid);
-
-	closid_free_map = bitmap_alloc(rdt_min_closid, GFP_KERNEL);
-	if (!closid_free_map)
-		return -ENOMEM;
-	bitmap_fill(closid_free_map, rdt_min_closid);
-
-	/* RESCTRL_RESERVED_CLOSID is always reserved for the default group */
-	__clear_bit(RESCTRL_RESERVED_CLOSID, closid_free_map);
-	closid_free_map_len = rdt_min_closid;
-
-	return 0;
-}
-
-static void closid_exit(void)
-{
-	bitmap_free(closid_free_map);
-	closid_free_map = NULL;
+	case QOS_L3_MBM_LOCAL_EVENT_ID:
+		return 1;
+	default:
+		/* Should never reach here */
+		return INVALID_CONFIG_INDEX;
+	}
 }
 
-static int closid_alloc(void)
+void resctrl_arch_mon_event_config_read(void *_config_info)
 {
-	int cleanest_closid;
-	u32 closid;
-
-	lockdep_assert_held(&rdtgroup_mutex);
+	struct resctrl_mon_config_info *config_info = _config_info;
+	unsigned int index;
+	u64 msrval;
 
-	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID) &&
-	    resctrl_arch_is_llc_occupancy_enabled()) {
-		cleanest_closid = resctrl_find_cleanest_closid();
-		if (cleanest_closid < 0)
-			return cleanest_closid;
-		closid = cleanest_closid;
-	} else {
-		closid = find_first_bit(closid_free_map, closid_free_map_len);
-		if (closid == closid_free_map_len)
-			return -ENOSPC;
+	index = mon_event_config_index_get(config_info->evtid);
+	if (index == INVALID_CONFIG_INDEX) {
+		pr_warn_once("Invalid event id %d\n", config_info->evtid);
+		return;
 	}
-	__clear_bit(closid, closid_free_map);
-
-	return closid;
-}
-
-void closid_free(int closid)
-{
-	lockdep_assert_held(&rdtgroup_mutex);
+	rdmsrl(MSR_IA32_EVT_CFG_BASE + index, msrval);
 
-	__set_bit(closid, closid_free_map);
+	/* Report only the valid event configuration bits */
+	config_info->mon_config = msrval & MAX_EVT_CONFIG_BITS;
 }
 
-/**
- * closid_allocated - test if provided closid is in use
- * @closid: closid to be tested
- *
- * Return: true if @closid is currently associated with a resource group,
- * false if @closid is free
- */
-bool closid_allocated(unsigned int closid)
+void resctrl_arch_mon_event_config_write(void *_config_info)
 {
-	lockdep_assert_held(&rdtgroup_mutex);
+	struct resctrl_mon_config_info *config_info = _config_info;
+	unsigned int index;
 
-	return !test_bit(closid, closid_free_map);
+	index = mon_event_config_index_get(config_info->evtid);
+	if (index == INVALID_CONFIG_INDEX) {
+		pr_warn_once("Invalid event id %d\n", config_info->evtid);
+		return;
+	}
+	wrmsr(MSR_IA32_EVT_CFG_BASE + index, config_info->mon_config, 0);
 }
 
-/**
- * rdtgroup_mode_by_closid - Return mode of resource group with closid
- * @closid: closid if the resource group
- *
- * Each resource group is associated with a @closid. Here the mode
- * of a resource group can be queried by searching for it using its closid.
- *
- * Return: mode as &enum rdtgrp_mode of resource group with closid @closid
- */
-enum rdtgrp_mode rdtgroup_mode_by_closid(int closid)
+static void l3_qos_cfg_update(void *arg)
 {
-	struct rdtgroup *rdtgrp;
-
-	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
-		if (rdtgrp->closid == closid)
-			return rdtgrp->mode;
-	}
+	bool *enable = arg;
 
-	return RDT_NUM_MODES;
+	wrmsrl(MSR_IA32_L3_QOS_CFG, *enable ? L3_QOS_CDP_ENABLE : 0ULL);
 }
 
-static const char * const rdt_mode_str[] = {
-	[RDT_MODE_SHAREABLE]		= "shareable",
-	[RDT_MODE_EXCLUSIVE]		= "exclusive",
-	[RDT_MODE_PSEUDO_LOCKSETUP]	= "pseudo-locksetup",
-	[RDT_MODE_PSEUDO_LOCKED]	= "pseudo-locked",
-};
-
-/**
- * rdtgroup_mode_str - Return the string representation of mode
- * @mode: the resource group mode as &enum rdtgroup_mode
- *
- * Return: string representation of valid mode, "unknown" otherwise
- */
-static const char *rdtgroup_mode_str(enum rdtgrp_mode mode)
+static void l2_qos_cfg_update(void *arg)
 {
-	if (mode < RDT_MODE_SHAREABLE || mode >= RDT_NUM_MODES)
-		return "unknown";
+	bool *enable = arg;
 
-	return rdt_mode_str[mode];
+	wrmsrl(MSR_IA32_L2_QOS_CFG, *enable ? L2_QOS_CDP_ENABLE : 0ULL);
 }
 
-/* set uid and gid of rdtgroup dirs and files to that of the creator */
-static int rdtgroup_kn_set_ugid(struct kernfs_node *kn)
+static int set_cache_qos_cfg(int level, bool enable)
 {
-	struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID,
-				.ia_uid = current_fsuid(),
-				.ia_gid = current_fsgid(), };
-
-	if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) &&
-	    gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID))
-		return 0;
+	void (*update)(void *arg);
+	struct rdt_ctrl_domain *d;
+	struct rdt_resource *r_l;
+	cpumask_var_t cpu_mask;
+	int cpu;
 
-	return kernfs_setattr(kn, &iattr);
-}
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
 
-static int rdtgroup_add_file(struct kernfs_node *parent_kn, struct rftype *rft)
-{
-	struct kernfs_node *kn;
-	int ret;
+	if (level == RDT_RESOURCE_L3)
+		update = l3_qos_cfg_update;
+	else if (level == RDT_RESOURCE_L2)
+		update = l2_qos_cfg_update;
+	else
+		return -EINVAL;
 
-	kn = __kernfs_create_file(parent_kn, rft->name, rft->mode,
-				  GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
-				  0, rft->kf_ops, rft, NULL, NULL);
-	if (IS_ERR(kn))
-		return PTR_ERR(kn);
+	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
+		return -ENOMEM;
 
-	ret = rdtgroup_kn_set_ugid(kn);
-	if (ret) {
-		kernfs_remove(kn);
-		return ret;
+	r_l = &rdt_resources_all[level].r_resctrl;
+	list_for_each_entry(d, &r_l->ctrl_domains, hdr.list) {
+		if (r_l->cache.arch_has_per_cpu_cfg)
+			/* Pick all the CPUs in the domain instance */
+			for_each_cpu(cpu, &d->hdr.cpu_mask)
+				cpumask_set_cpu(cpu, cpu_mask);
+		else
+			/* Pick one CPU from each domain instance to update MSR */
+			cpumask_set_cpu(cpumask_any(&d->hdr.cpu_mask), cpu_mask);
 	}
 
-	return 0;
-}
+	/* Update QOS_CFG MSR on all the CPUs in cpu_mask */
+	on_each_cpu_mask(cpu_mask, update, &enable, 1);
 
-static int rdtgroup_seqfile_show(struct seq_file *m, void *arg)
-{
-	struct kernfs_open_file *of = m->private;
-	struct rftype *rft = of->kn->priv;
+	free_cpumask_var(cpu_mask);
 
-	if (rft->seq_show)
-		return rft->seq_show(of, m, arg);
 	return 0;
 }
 
-static ssize_t rdtgroup_file_write(struct kernfs_open_file *of, char *buf,
-				   size_t nbytes, loff_t off)
+/* Restore the qos cfg state when a domain comes online */
+void rdt_domain_reconfigure_cdp(struct rdt_resource *r)
 {
-	struct rftype *rft = of->kn->priv;
-
-	if (rft->write)
-		return rft->write(of, buf, nbytes, off);
-
-	return -EINVAL;
-}
-
-static const struct kernfs_ops rdtgroup_kf_single_ops = {
-	.atomic_write_len	= PAGE_SIZE,
-	.write			= rdtgroup_file_write,
-	.seq_show		= rdtgroup_seqfile_show,
-};
+	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 
-static const struct kernfs_ops kf_mondata_ops = {
-	.atomic_write_len	= PAGE_SIZE,
-	.seq_show		= rdtgroup_mondata_show,
-};
+	if (!r->cdp_capable)
+		return;
 
-static bool is_cpu_list(struct kernfs_open_file *of)
-{
-	struct rftype *rft = of->kn->priv;
+	if (r->rid == RDT_RESOURCE_L2)
+		l2_qos_cfg_update(&hw_res->cdp_enabled);
 
-	return rft->flags & RFTYPE_FLAGS_CPUS_LIST;
+	if (r->rid == RDT_RESOURCE_L3)
+		l3_qos_cfg_update(&hw_res->cdp_enabled);
 }
 
-static int rdtgroup_cpus_show(struct kernfs_open_file *of,
-			      struct seq_file *s, void *v)
+static int cdp_enable(int level)
 {
-	struct rdtgroup *rdtgrp;
-	struct cpumask *mask;
-	int ret = 0;
+	struct rdt_resource *r_l = &rdt_resources_all[level].r_resctrl;
+	int ret;
 
-	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!r_l->alloc_capable)
+		return -EINVAL;
 
-	if (rdtgrp) {
-		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
-			if (!rdtgrp->plr->d) {
-				rdt_last_cmd_clear();
-				rdt_last_cmd_puts("Cache domain offline\n");
-				ret = -ENODEV;
-			} else {
-				mask = &rdtgrp->plr->d->hdr.cpu_mask;
-				seq_printf(s, is_cpu_list(of) ?
-					   "%*pbl\n" : "%*pb\n",
-					   cpumask_pr_args(mask));
-			}
-		} else {
-			seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
-				   cpumask_pr_args(&rdtgrp->cpu_mask));
-		}
-	} else {
-		ret = -ENOENT;
-	}
-	rdtgroup_kn_unlock(of->kn);
+	ret = set_cache_qos_cfg(level, true);
+	if (!ret)
+		rdt_resources_all[level].cdp_enabled = true;
 
 	return ret;
 }
 
-/*
- * This is safe against resctrl_arch_sched_in() called from __switch_to()
- * because __switch_to() is executed with interrupts disabled. A local call
- * from update_closid_rmid() is protected against __switch_to() because
- * preemption is disabled.
- */
-void resctrl_arch_sync_cpu_closid_rmid(void *info)
-{
-	struct resctrl_cpu_defaults *r = info;
-
-	if (r) {
-		this_cpu_write(pqr_state.default_closid, r->closid);
-		this_cpu_write(pqr_state.default_rmid, r->rmid);
-	}
-
-	/*
-	 * We cannot unconditionally write the MSR because the current
-	 * executing task might have its own closid selected. Just reuse
-	 * the context switch code.
-	 */
-	resctrl_arch_sched_in(current);
-}
-
-/*
- * Update the PGR_ASSOC MSR on all cpus in @cpu_mask,
- *
- * Per task closids/rmids must have been set up before calling this function.
- * @r may be NULL.
- */
-static void
-update_closid_rmid(const struct cpumask *cpu_mask, struct rdtgroup *r)
+static void cdp_disable(int level)
 {
-	struct resctrl_cpu_defaults defaults, *p = NULL;
+	struct rdt_hw_resource *r_hw = &rdt_resources_all[level];
 
-	if (r) {
-		defaults.closid = r->closid;
-		defaults.rmid = r->mon.rmid;
-		p = &defaults;
+	if (r_hw->cdp_enabled) {
+		set_cache_qos_cfg(level, false);
+		r_hw->cdp_enabled = false;
 	}
-
-	on_each_cpu_mask(cpu_mask, resctrl_arch_sync_cpu_closid_rmid, p, 1);
 }
 
-static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask,
-			  cpumask_var_t tmpmask)
+int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable)
 {
-	struct rdtgroup *prgrp = rdtgrp->mon.parent, *crgrp;
-	struct list_head *head;
+	struct rdt_hw_resource *hw_res = &rdt_resources_all[l];
 
-	/* Check whether cpus belong to parent ctrl group */
-	cpumask_andnot(tmpmask, newmask, &prgrp->cpu_mask);
-	if (!cpumask_empty(tmpmask)) {
-		rdt_last_cmd_puts("Can only add CPUs to mongroup that belong to parent\n");
+	if (!hw_res->r_resctrl.cdp_capable)
 		return -EINVAL;
-	}
-
-	/* Check whether cpus are dropped from this group */
-	cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask);
-	if (!cpumask_empty(tmpmask)) {
-		/* Give any dropped cpus to parent rdtgroup */
-		cpumask_or(&prgrp->cpu_mask, &prgrp->cpu_mask, tmpmask);
-		update_closid_rmid(tmpmask, prgrp);
-	}
 
-	/*
-	 * If we added cpus, remove them from previous group that owned them
-	 * and update per-cpu rmid
-	 */
-	cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask);
-	if (!cpumask_empty(tmpmask)) {
-		head = &prgrp->mon.crdtgrp_list;
-		list_for_each_entry(crgrp, head, mon.crdtgrp_list) {
-			if (crgrp == rdtgrp)
-				continue;
-			cpumask_andnot(&crgrp->cpu_mask, &crgrp->cpu_mask,
-				       tmpmask);
-		}
-		update_closid_rmid(tmpmask, rdtgrp);
-	}
+	if (enable)
+		return cdp_enable(l);
 
-	/* Done pushing/pulling - update this group with new mask */
-	cpumask_copy(&rdtgrp->cpu_mask, newmask);
+	cdp_disable(l);
 
 	return 0;
 }
 
-static void cpumask_rdtgrp_clear(struct rdtgroup *r, struct cpumask *m)
+bool resctrl_arch_get_cdp_enabled(enum resctrl_res_level l)
 {
-	struct rdtgroup *crgrp;
-
-	cpumask_andnot(&r->cpu_mask, &r->cpu_mask, m);
-	/* update the child mon group masks as well*/
-	list_for_each_entry(crgrp, &r->mon.crdtgrp_list, mon.crdtgrp_list)
-		cpumask_and(&crgrp->cpu_mask, &r->cpu_mask, &crgrp->cpu_mask);
+	return rdt_resources_all[l].cdp_enabled;
 }
 
-static int cpus_ctrl_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask,
-			   cpumask_var_t tmpmask, cpumask_var_t tmpmask1)
+void resctrl_arch_reset_all_ctrls(struct rdt_resource *r)
 {
-	struct rdtgroup *r, *crgrp;
-	struct list_head *head;
+	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
+	struct rdt_hw_ctrl_domain *hw_dom;
+	struct msr_param msr_param;
+	struct rdt_ctrl_domain *d;
+	int i;
 
-	/* Check whether cpus are dropped from this group */
-	cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask);
-	if (!cpumask_empty(tmpmask)) {
-		/* Can't drop from default group */
-		if (rdtgrp == &rdtgroup_default) {
-			rdt_last_cmd_puts("Can't drop CPUs from default group\n");
-			return -EINVAL;
-		}
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
 
-		/* Give any dropped cpus to rdtgroup_default */
-		cpumask_or(&rdtgroup_default.cpu_mask,
-			   &rdtgroup_default.cpu_mask, tmpmask);
-		update_closid_rmid(tmpmask, &rdtgroup_default);
-	}
+	msr_param.res = r;
+	msr_param.low = 0;
+	msr_param.high = hw_res->num_closid;
 
 	/*
-	 * If we added cpus, remove them from previous group and
-	 * the prev group's child groups that owned them
-	 * and update per-cpu closid/rmid.
+	 * Disable resource control for this resource by setting all
+	 * CBMs in all ctrl_domains to the maximum mask value. Pick one CPU
+	 * from each domain to update the MSRs below.
 	 */
-	cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask);
-	if (!cpumask_empty(tmpmask)) {
-		list_for_each_entry(r, &rdt_all_groups, rdtgroup_list) {
-			if (r == rdtgrp)
-				continue;
-			cpumask_and(tmpmask1, &r->cpu_mask, tmpmask);
-			if (!cpumask_empty(tmpmask1))
-				cpumask_rdtgrp_clear(r, tmpmask1);
-		}
-		update_closid_rmid(tmpmask, rdtgrp);
-	}
+	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
+		hw_dom = resctrl_to_arch_ctrl_dom(d);
 
-	/* Done pushing/pulling - update this group with new mask */
-	cpumask_copy(&rdtgrp->cpu_mask, newmask);
+		for (i = 0; i < hw_res->num_closid; i++)
+			hw_dom->ctrl_val[i] = resctrl_get_default_ctrl(r);
+		msr_param.dom = d;
+		smp_call_function_any(&d->hdr.cpu_mask, rdt_ctrl_update, &msr_param, 1);
+	}
 
-	/*
-	 * Clear child mon group masks since there is a new parent mask
-	 * now and update the rmid for the cpus the child lost.
-	 */
-	head = &rdtgrp->mon.crdtgrp_list;
-	list_for_each_entry(crgrp, head, mon.crdtgrp_list) {
-		cpumask_and(tmpmask, &rdtgrp->cpu_mask, &crgrp->cpu_mask);
-		update_closid_rmid(tmpmask, rdtgrp);
-		cpumask_clear(&crgrp->cpu_mask);
-	}
-
-	return 0;
-}
-
-static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
-				   char *buf, size_t nbytes, loff_t off)
-{
-	cpumask_var_t tmpmask, newmask, tmpmask1;
-	struct rdtgroup *rdtgrp;
-	int ret;
-
-	if (!buf)
-		return -EINVAL;
-
-	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
-		return -ENOMEM;
-	if (!zalloc_cpumask_var(&newmask, GFP_KERNEL)) {
-		free_cpumask_var(tmpmask);
-		return -ENOMEM;
-	}
-	if (!zalloc_cpumask_var(&tmpmask1, GFP_KERNEL)) {
-		free_cpumask_var(tmpmask);
-		free_cpumask_var(newmask);
-		return -ENOMEM;
-	}
-
-	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-	if (!rdtgrp) {
-		ret = -ENOENT;
-		goto unlock;
-	}
-
-	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED ||
-	    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
-		ret = -EINVAL;
-		rdt_last_cmd_puts("Pseudo-locking in progress\n");
-		goto unlock;
-	}
-
-	if (is_cpu_list(of))
-		ret = cpulist_parse(buf, newmask);
-	else
-		ret = cpumask_parse(buf, newmask);
-
-	if (ret) {
-		rdt_last_cmd_puts("Bad CPU list/mask\n");
-		goto unlock;
-	}
-
-	/* check that user didn't specify any offline cpus */
-	cpumask_andnot(tmpmask, newmask, cpu_online_mask);
-	if (!cpumask_empty(tmpmask)) {
-		ret = -EINVAL;
-		rdt_last_cmd_puts("Can only assign online CPUs\n");
-		goto unlock;
-	}
-
-	if (rdtgrp->type == RDTCTRL_GROUP)
-		ret = cpus_ctrl_write(rdtgrp, newmask, tmpmask, tmpmask1);
-	else if (rdtgrp->type == RDTMON_GROUP)
-		ret = cpus_mon_write(rdtgrp, newmask, tmpmask);
-	else
-		ret = -EINVAL;
-
-unlock:
-	rdtgroup_kn_unlock(of->kn);
-	free_cpumask_var(tmpmask);
-	free_cpumask_var(newmask);
-	free_cpumask_var(tmpmask1);
-
-	return ret ?: nbytes;
-}
-
-/**
- * rdtgroup_remove - the helper to remove resource group safely
- * @rdtgrp: resource group to remove
- *
- * On resource group creation via a mkdir, an extra kernfs_node reference is
- * taken to ensure that the rdtgroup structure remains accessible for the
- * rdtgroup_kn_unlock() calls where it is removed.
- *
- * Drop the extra reference here, then free the rdtgroup structure.
- *
- * Return: void
- */
-static void rdtgroup_remove(struct rdtgroup *rdtgrp)
-{
-	kernfs_put(rdtgrp->kn);
-	kfree(rdtgrp);
-}
-
-static void _update_task_closid_rmid(void *task)
-{
-	/*
-	 * If the task is still current on this CPU, update PQR_ASSOC MSR.
-	 * Otherwise, the MSR is updated when the task is scheduled in.
-	 */
-	if (task == current)
-		resctrl_arch_sched_in(task);
-}
-
-static void update_task_closid_rmid(struct task_struct *t)
-{
-	if (IS_ENABLED(CONFIG_SMP) && task_curr(t))
-		smp_call_function_single(task_cpu(t), _update_task_closid_rmid, t, 1);
-	else
-		_update_task_closid_rmid(t);
-}
-
-static bool task_in_rdtgroup(struct task_struct *tsk, struct rdtgroup *rdtgrp)
-{
-	u32 closid, rmid = rdtgrp->mon.rmid;
-
-	if (rdtgrp->type == RDTCTRL_GROUP)
-		closid = rdtgrp->closid;
-	else if (rdtgrp->type == RDTMON_GROUP)
-		closid = rdtgrp->mon.parent->closid;
-	else
-		return false;
-
-	return resctrl_arch_match_closid(tsk, closid) &&
-	       resctrl_arch_match_rmid(tsk, closid, rmid);
-}
-
-static int __rdtgroup_move_task(struct task_struct *tsk,
-				struct rdtgroup *rdtgrp)
-{
-	/* If the task is already in rdtgrp, no need to move the task. */
-	if (task_in_rdtgroup(tsk, rdtgrp))
-		return 0;
-
-	/*
-	 * Set the task's closid/rmid before the PQR_ASSOC MSR can be
-	 * updated by them.
-	 *
-	 * For ctrl_mon groups, move both closid and rmid.
-	 * For monitor groups, can move the tasks only from
-	 * their parent CTRL group.
-	 */
-	if (rdtgrp->type == RDTMON_GROUP &&
-	    !resctrl_arch_match_closid(tsk, rdtgrp->mon.parent->closid)) {
-		rdt_last_cmd_puts("Can't move task to different control group\n");
-		return -EINVAL;
-	}
-
-	if (rdtgrp->type == RDTMON_GROUP)
-		resctrl_arch_set_closid_rmid(tsk, rdtgrp->mon.parent->closid,
-					     rdtgrp->mon.rmid);
-	else
-		resctrl_arch_set_closid_rmid(tsk, rdtgrp->closid,
-					     rdtgrp->mon.rmid);
-
-	/*
-	 * Ensure the task's closid and rmid are written before determining if
-	 * the task is current that will decide if it will be interrupted.
-	 * This pairs with the full barrier between the rq->curr update and
-	 * resctrl_arch_sched_in() during context switch.
-	 */
-	smp_mb();
-
-	/*
-	 * By now, the task's closid and rmid are set. If the task is current
-	 * on a CPU, the PQR_ASSOC MSR needs to be updated to make the resource
-	 * group go into effect. If the task is not current, the MSR will be
-	 * updated when the task is scheduled in.
-	 */
-	update_task_closid_rmid(tsk);
-
-	return 0;
-}
-
-static bool is_closid_match(struct task_struct *t, struct rdtgroup *r)
-{
-	return (resctrl_arch_alloc_capable() && (r->type == RDTCTRL_GROUP) &&
-		resctrl_arch_match_closid(t, r->closid));
-}
-
-static bool is_rmid_match(struct task_struct *t, struct rdtgroup *r)
-{
-	return (resctrl_arch_mon_capable() && (r->type == RDTMON_GROUP) &&
-		resctrl_arch_match_rmid(t, r->mon.parent->closid,
-					r->mon.rmid));
-}
-
-/**
- * rdtgroup_tasks_assigned - Test if tasks have been assigned to resource group
- * @r: Resource group
- *
- * Return: 1 if tasks have been assigned to @r, 0 otherwise
- */
-int rdtgroup_tasks_assigned(struct rdtgroup *r)
-{
-	struct task_struct *p, *t;
-	int ret = 0;
-
-	lockdep_assert_held(&rdtgroup_mutex);
-
-	rcu_read_lock();
-	for_each_process_thread(p, t) {
-		if (is_closid_match(t, r) || is_rmid_match(t, r)) {
-			ret = 1;
-			break;
-		}
-	}
-	rcu_read_unlock();
-
-	return ret;
-}
-
-static int rdtgroup_task_write_permission(struct task_struct *task,
-					  struct kernfs_open_file *of)
-{
-	const struct cred *tcred = get_task_cred(task);
-	const struct cred *cred = current_cred();
-	int ret = 0;
-
-	/*
-	 * Even if we're attaching all tasks in the thread group, we only
-	 * need to check permissions on one of them.
-	 */
-	if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) &&
-	    !uid_eq(cred->euid, tcred->uid) &&
-	    !uid_eq(cred->euid, tcred->suid)) {
-		rdt_last_cmd_printf("No permission to move task %d\n", task->pid);
-		ret = -EPERM;
-	}
-
-	put_cred(tcred);
-	return ret;
-}
-
-static int rdtgroup_move_task(pid_t pid, struct rdtgroup *rdtgrp,
-			      struct kernfs_open_file *of)
-{
-	struct task_struct *tsk;
-	int ret;
-
-	rcu_read_lock();
-	if (pid) {
-		tsk = find_task_by_vpid(pid);
-		if (!tsk) {
-			rcu_read_unlock();
-			rdt_last_cmd_printf("No task %d\n", pid);
-			return -ESRCH;
-		}
-	} else {
-		tsk = current;
-	}
-
-	get_task_struct(tsk);
-	rcu_read_unlock();
-
-	ret = rdtgroup_task_write_permission(tsk, of);
-	if (!ret)
-		ret = __rdtgroup_move_task(tsk, rdtgrp);
-
-	put_task_struct(tsk);
-	return ret;
-}
-
-static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of,
-				    char *buf, size_t nbytes, loff_t off)
-{
-	struct rdtgroup *rdtgrp;
-	char *pid_str;
-	int ret = 0;
-	pid_t pid;
-
-	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-	if (!rdtgrp) {
-		rdtgroup_kn_unlock(of->kn);
-		return -ENOENT;
-	}
-	rdt_last_cmd_clear();
-
-	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED ||
-	    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
-		ret = -EINVAL;
-		rdt_last_cmd_puts("Pseudo-locking in progress\n");
-		goto unlock;
-	}
-
-	while (buf && buf[0] != '\0' && buf[0] != '\n') {
-		pid_str = strim(strsep(&buf, ","));
-
-		if (kstrtoint(pid_str, 0, &pid)) {
-			rdt_last_cmd_printf("Task list parsing error pid %s\n", pid_str);
-			ret = -EINVAL;
-			break;
-		}
-
-		if (pid < 0) {
-			rdt_last_cmd_printf("Invalid pid %d\n", pid);
-			ret = -EINVAL;
-			break;
-		}
-
-		ret = rdtgroup_move_task(pid, rdtgrp, of);
-		if (ret) {
-			rdt_last_cmd_printf("Error while processing task %d\n", pid);
-			break;
-		}
-	}
-
-unlock:
-	rdtgroup_kn_unlock(of->kn);
-
-	return ret ?: nbytes;
-}
-
-static void show_rdt_tasks(struct rdtgroup *r, struct seq_file *s)
-{
-	struct task_struct *p, *t;
-	pid_t pid;
-
-	rcu_read_lock();
-	for_each_process_thread(p, t) {
-		if (is_closid_match(t, r) || is_rmid_match(t, r)) {
-			pid = task_pid_vnr(t);
-			if (pid)
-				seq_printf(s, "%d\n", pid);
-		}
-	}
-	rcu_read_unlock();
-}
-
-static int rdtgroup_tasks_show(struct kernfs_open_file *of,
-			       struct seq_file *s, void *v)
-{
-	struct rdtgroup *rdtgrp;
-	int ret = 0;
-
-	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-	if (rdtgrp)
-		show_rdt_tasks(rdtgrp, s);
-	else
-		ret = -ENOENT;
-	rdtgroup_kn_unlock(of->kn);
-
-	return ret;
-}
-
-static int rdtgroup_closid_show(struct kernfs_open_file *of,
-				struct seq_file *s, void *v)
-{
-	struct rdtgroup *rdtgrp;
-	int ret = 0;
-
-	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-	if (rdtgrp)
-		seq_printf(s, "%u\n", rdtgrp->closid);
-	else
-		ret = -ENOENT;
-	rdtgroup_kn_unlock(of->kn);
-
-	return ret;
-}
-
-static int rdtgroup_rmid_show(struct kernfs_open_file *of,
-			      struct seq_file *s, void *v)
-{
-	struct rdtgroup *rdtgrp;
-	int ret = 0;
-
-	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-	if (rdtgrp)
-		seq_printf(s, "%u\n", rdtgrp->mon.rmid);
-	else
-		ret = -ENOENT;
-	rdtgroup_kn_unlock(of->kn);
-
-	return ret;
-}
-
-#ifdef CONFIG_PROC_CPU_RESCTRL
-
-/*
- * A task can only be part of one resctrl control group and of one monitor
- * group which is associated to that control group.
- *
- * 1)   res:
- *      mon:
- *
- *    resctrl is not available.
- *
- * 2)   res:/
- *      mon:
- *
- *    Task is part of the root resctrl control group, and it is not associated
- *    to any monitor group.
- *
- * 3)  res:/
- *     mon:mon0
- *
- *    Task is part of the root resctrl control group and monitor group mon0.
- *
- * 4)  res:group0
- *     mon:
- *
- *    Task is part of resctrl control group group0, and it is not associated
- *    to any monitor group.
- *
- * 5) res:group0
- *    mon:mon1
- *
- *    Task is part of resctrl control group group0 and monitor group mon1.
- */
-int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns,
-		      struct pid *pid, struct task_struct *tsk)
-{
-	struct rdtgroup *rdtg;
-	int ret = 0;
-
-	mutex_lock(&rdtgroup_mutex);
-
-	/* Return empty if resctrl has not been mounted. */
-	if (!resctrl_mounted) {
-		seq_puts(s, "res:\nmon:\n");
-		goto unlock;
-	}
-
-	list_for_each_entry(rdtg, &rdt_all_groups, rdtgroup_list) {
-		struct rdtgroup *crg;
-
-		/*
-		 * Task information is only relevant for shareable
-		 * and exclusive groups.
-		 */
-		if (rdtg->mode != RDT_MODE_SHAREABLE &&
-		    rdtg->mode != RDT_MODE_EXCLUSIVE)
-			continue;
-
-		if (!resctrl_arch_match_closid(tsk, rdtg->closid))
-			continue;
-
-		seq_printf(s, "res:%s%s\n", (rdtg == &rdtgroup_default) ? "/" : "",
-			   rdt_kn_name(rdtg->kn));
-		seq_puts(s, "mon:");
-		list_for_each_entry(crg, &rdtg->mon.crdtgrp_list,
-				    mon.crdtgrp_list) {
-			if (!resctrl_arch_match_rmid(tsk, crg->mon.parent->closid,
-						     crg->mon.rmid))
-				continue;
-			seq_printf(s, "%s", rdt_kn_name(crg->kn));
-			break;
-		}
-		seq_putc(s, '\n');
-		goto unlock;
-	}
-	/*
-	 * The above search should succeed. Otherwise return
-	 * with an error.
-	 */
-	ret = -ENOENT;
-unlock:
-	mutex_unlock(&rdtgroup_mutex);
-
-	return ret;
-}
-#endif
-
-static int rdt_last_cmd_status_show(struct kernfs_open_file *of,
-				    struct seq_file *seq, void *v)
-{
-	int len;
-
-	mutex_lock(&rdtgroup_mutex);
-	len = seq_buf_used(&last_cmd_status);
-	if (len)
-		seq_printf(seq, "%.*s", len, last_cmd_status_buf);
-	else
-		seq_puts(seq, "ok\n");
-	mutex_unlock(&rdtgroup_mutex);
-	return 0;
-}
-
-static void *rdt_kn_parent_priv(struct kernfs_node *kn)
-{
-	/*
-	 * The parent pointer is only valid within RCU section since it can be
-	 * replaced.
-	 */
-	guard(rcu)();
-	return rcu_dereference(kn->__parent)->priv;
-}
-
-static int rdt_num_closids_show(struct kernfs_open_file *of,
-				struct seq_file *seq, void *v)
-{
-	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
-
-	seq_printf(seq, "%u\n", s->num_closid);
-	return 0;
-}
-
-static int rdt_default_ctrl_show(struct kernfs_open_file *of,
-				 struct seq_file *seq, void *v)
-{
-	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
-	struct rdt_resource *r = s->res;
-
-	seq_printf(seq, "%x\n", resctrl_get_default_ctrl(r));
-	return 0;
-}
-
-static int rdt_min_cbm_bits_show(struct kernfs_open_file *of,
-				 struct seq_file *seq, void *v)
-{
-	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
-	struct rdt_resource *r = s->res;
-
-	seq_printf(seq, "%u\n", r->cache.min_cbm_bits);
-	return 0;
-}
-
-static int rdt_shareable_bits_show(struct kernfs_open_file *of,
-				   struct seq_file *seq, void *v)
-{
-	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
-	struct rdt_resource *r = s->res;
-
-	seq_printf(seq, "%x\n", r->cache.shareable_bits);
-	return 0;
-}
-
-/*
- * rdt_bit_usage_show - Display current usage of resources
- *
- * A domain is a shared resource that can now be allocated differently. Here
- * we display the current regions of the domain as an annotated bitmask.
- * For each domain of this resource its allocation bitmask
- * is annotated as below to indicate the current usage of the corresponding bit:
- *   0 - currently unused
- *   X - currently available for sharing and used by software and hardware
- *   H - currently used by hardware only but available for software use
- *   S - currently used and shareable by software only
- *   E - currently used exclusively by one resource group
- *   P - currently pseudo-locked by one resource group
- */
-static int rdt_bit_usage_show(struct kernfs_open_file *of,
-			      struct seq_file *seq, void *v)
-{
-	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
-	/*
-	 * Use unsigned long even though only 32 bits are used to ensure
-	 * test_bit() is used safely.
-	 */
-	unsigned long sw_shareable = 0, hw_shareable = 0;
-	unsigned long exclusive = 0, pseudo_locked = 0;
-	struct rdt_resource *r = s->res;
-	struct rdt_ctrl_domain *dom;
-	int i, hwb, swb, excl, psl;
-	enum rdtgrp_mode mode;
-	bool sep = false;
-	u32 ctrl_val;
-
-	cpus_read_lock();
-	mutex_lock(&rdtgroup_mutex);
-	hw_shareable = r->cache.shareable_bits;
-	list_for_each_entry(dom, &r->ctrl_domains, hdr.list) {
-		if (sep)
-			seq_putc(seq, ';');
-		sw_shareable = 0;
-		exclusive = 0;
-		seq_printf(seq, "%d=", dom->hdr.id);
-		for (i = 0; i < closids_supported(); i++) {
-			if (!closid_allocated(i))
-				continue;
-			ctrl_val = resctrl_arch_get_config(r, dom, i,
-							   s->conf_type);
-			mode = rdtgroup_mode_by_closid(i);
-			switch (mode) {
-			case RDT_MODE_SHAREABLE:
-				sw_shareable |= ctrl_val;
-				break;
-			case RDT_MODE_EXCLUSIVE:
-				exclusive |= ctrl_val;
-				break;
-			case RDT_MODE_PSEUDO_LOCKSETUP:
-			/*
-			 * RDT_MODE_PSEUDO_LOCKSETUP is possible
-			 * here but not included since the CBM
-			 * associated with this CLOSID in this mode
-			 * is not initialized and no task or cpu can be
-			 * assigned this CLOSID.
-			 */
-				break;
-			case RDT_MODE_PSEUDO_LOCKED:
-			case RDT_NUM_MODES:
-				WARN(1,
-				     "invalid mode for closid %d\n", i);
-				break;
-			}
-		}
-		for (i = r->cache.cbm_len - 1; i >= 0; i--) {
-			pseudo_locked = dom->plr ? dom->plr->cbm : 0;
-			hwb = test_bit(i, &hw_shareable);
-			swb = test_bit(i, &sw_shareable);
-			excl = test_bit(i, &exclusive);
-			psl = test_bit(i, &pseudo_locked);
-			if (hwb && swb)
-				seq_putc(seq, 'X');
-			else if (hwb && !swb)
-				seq_putc(seq, 'H');
-			else if (!hwb && swb)
-				seq_putc(seq, 'S');
-			else if (excl)
-				seq_putc(seq, 'E');
-			else if (psl)
-				seq_putc(seq, 'P');
-			else /* Unused bits remain */
-				seq_putc(seq, '0');
-		}
-		sep = true;
-	}
-	seq_putc(seq, '\n');
-	mutex_unlock(&rdtgroup_mutex);
-	cpus_read_unlock();
-	return 0;
-}
-
-static int rdt_min_bw_show(struct kernfs_open_file *of,
-			   struct seq_file *seq, void *v)
-{
-	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
-	struct rdt_resource *r = s->res;
-
-	seq_printf(seq, "%u\n", r->membw.min_bw);
-	return 0;
-}
-
-static int rdt_num_rmids_show(struct kernfs_open_file *of,
-			      struct seq_file *seq, void *v)
-{
-	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
-
-	seq_printf(seq, "%d\n", r->num_rmid);
-
-	return 0;
-}
-
-static int rdt_mon_features_show(struct kernfs_open_file *of,
-				 struct seq_file *seq, void *v)
-{
-	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
-	struct mon_evt *mevt;
-
-	list_for_each_entry(mevt, &r->evt_list, list) {
-		seq_printf(seq, "%s\n", mevt->name);
-		if (mevt->configurable)
-			seq_printf(seq, "%s_config\n", mevt->name);
-	}
-
-	return 0;
-}
-
-static int rdt_bw_gran_show(struct kernfs_open_file *of,
-			    struct seq_file *seq, void *v)
-{
-	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
-	struct rdt_resource *r = s->res;
-
-	seq_printf(seq, "%u\n", r->membw.bw_gran);
-	return 0;
-}
-
-static int rdt_delay_linear_show(struct kernfs_open_file *of,
-				 struct seq_file *seq, void *v)
-{
-	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
-	struct rdt_resource *r = s->res;
-
-	seq_printf(seq, "%u\n", r->membw.delay_linear);
-	return 0;
-}
-
-static int max_threshold_occ_show(struct kernfs_open_file *of,
-				  struct seq_file *seq, void *v)
-{
-	seq_printf(seq, "%u\n", resctrl_rmid_realloc_threshold);
-
-	return 0;
-}
-
-static int rdt_thread_throttle_mode_show(struct kernfs_open_file *of,
-					 struct seq_file *seq, void *v)
-{
-	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
-	struct rdt_resource *r = s->res;
-
-	switch (r->membw.throttle_mode) {
-	case THREAD_THROTTLE_PER_THREAD:
-		seq_puts(seq, "per-thread\n");
-		return 0;
-	case THREAD_THROTTLE_MAX:
-		seq_puts(seq, "max\n");
-		return 0;
-	case THREAD_THROTTLE_UNDEFINED:
-		seq_puts(seq, "undefined\n");
-		return 0;
-	}
-
-	WARN_ON_ONCE(1);
-
-	return 0;
-}
-
-static ssize_t max_threshold_occ_write(struct kernfs_open_file *of,
-				       char *buf, size_t nbytes, loff_t off)
-{
-	unsigned int bytes;
-	int ret;
-
-	ret = kstrtouint(buf, 0, &bytes);
-	if (ret)
-		return ret;
-
-	if (bytes > resctrl_rmid_realloc_limit)
-		return -EINVAL;
-
-	resctrl_rmid_realloc_threshold = resctrl_arch_round_mon_val(bytes);
-
-	return nbytes;
-}
-
-/*
- * rdtgroup_mode_show - Display mode of this resource group
- */
-static int rdtgroup_mode_show(struct kernfs_open_file *of,
-			      struct seq_file *s, void *v)
-{
-	struct rdtgroup *rdtgrp;
-
-	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-	if (!rdtgrp) {
-		rdtgroup_kn_unlock(of->kn);
-		return -ENOENT;
-	}
-
-	seq_printf(s, "%s\n", rdtgroup_mode_str(rdtgrp->mode));
-
-	rdtgroup_kn_unlock(of->kn);
-	return 0;
-}
-
-static enum resctrl_conf_type resctrl_peer_type(enum resctrl_conf_type my_type)
-{
-	switch (my_type) {
-	case CDP_CODE:
-		return CDP_DATA;
-	case CDP_DATA:
-		return CDP_CODE;
-	default:
-	case CDP_NONE:
-		return CDP_NONE;
-	}
-}
-
-static int rdt_has_sparse_bitmasks_show(struct kernfs_open_file *of,
-					struct seq_file *seq, void *v)
-{
-	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
-	struct rdt_resource *r = s->res;
-
-	seq_printf(seq, "%u\n", r->cache.arch_has_sparse_bitmasks);
-
-	return 0;
-}
-
-/**
- * __rdtgroup_cbm_overlaps - Does CBM for intended closid overlap with other
- * @r: Resource to which domain instance @d belongs.
- * @d: The domain instance for which @closid is being tested.
- * @cbm: Capacity bitmask being tested.
- * @closid: Intended closid for @cbm.
- * @type: CDP type of @r.
- * @exclusive: Only check if overlaps with exclusive resource groups
- *
- * Checks if provided @cbm intended to be used for @closid on domain
- * @d overlaps with any other closids or other hardware usage associated
- * with this domain. If @exclusive is true then only overlaps with
- * resource groups in exclusive mode will be considered. If @exclusive
- * is false then overlaps with any resource group or hardware entities
- * will be considered.
- *
- * @cbm is unsigned long, even if only 32 bits are used, to make the
- * bitmap functions work correctly.
- *
- * Return: false if CBM does not overlap, true if it does.
- */
-static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_ctrl_domain *d,
-				    unsigned long cbm, int closid,
-				    enum resctrl_conf_type type, bool exclusive)
-{
-	enum rdtgrp_mode mode;
-	unsigned long ctrl_b;
-	int i;
-
-	/* Check for any overlap with regions used by hardware directly */
-	if (!exclusive) {
-		ctrl_b = r->cache.shareable_bits;
-		if (bitmap_intersects(&cbm, &ctrl_b, r->cache.cbm_len))
-			return true;
-	}
-
-	/* Check for overlap with other resource groups */
-	for (i = 0; i < closids_supported(); i++) {
-		ctrl_b = resctrl_arch_get_config(r, d, i, type);
-		mode = rdtgroup_mode_by_closid(i);
-		if (closid_allocated(i) && i != closid &&
-		    mode != RDT_MODE_PSEUDO_LOCKSETUP) {
-			if (bitmap_intersects(&cbm, &ctrl_b, r->cache.cbm_len)) {
-				if (exclusive) {
-					if (mode == RDT_MODE_EXCLUSIVE)
-						return true;
-					continue;
-				}
-				return true;
-			}
-		}
-	}
-
-	return false;
-}
-
-/**
- * rdtgroup_cbm_overlaps - Does CBM overlap with other use of hardware
- * @s: Schema for the resource to which domain instance @d belongs.
- * @d: The domain instance for which @closid is being tested.
- * @cbm: Capacity bitmask being tested.
- * @closid: Intended closid for @cbm.
- * @exclusive: Only check if overlaps with exclusive resource groups
- *
- * Resources that can be allocated using a CBM can use the CBM to control
- * the overlap of these allocations. rdtgroup_cmb_overlaps() is the test
- * for overlap. Overlap test is not limited to the specific resource for
- * which the CBM is intended though - when dealing with CDP resources that
- * share the underlying hardware the overlap check should be performed on
- * the CDP resource sharing the hardware also.
- *
- * Refer to description of __rdtgroup_cbm_overlaps() for the details of the
- * overlap test.
- *
- * Return: true if CBM overlap detected, false if there is no overlap
- */
-bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_ctrl_domain *d,
-			   unsigned long cbm, int closid, bool exclusive)
-{
-	enum resctrl_conf_type peer_type = resctrl_peer_type(s->conf_type);
-	struct rdt_resource *r = s->res;
-
-	if (__rdtgroup_cbm_overlaps(r, d, cbm, closid, s->conf_type,
-				    exclusive))
-		return true;
-
-	if (!resctrl_arch_get_cdp_enabled(r->rid))
-		return false;
-	return  __rdtgroup_cbm_overlaps(r, d, cbm, closid, peer_type, exclusive);
-}
-
-/**
- * rdtgroup_mode_test_exclusive - Test if this resource group can be exclusive
- * @rdtgrp: Resource group identified through its closid.
- *
- * An exclusive resource group implies that there should be no sharing of
- * its allocated resources. At the time this group is considered to be
- * exclusive this test can determine if its current schemata supports this
- * setting by testing for overlap with all other resource groups.
- *
- * Return: true if resource group can be exclusive, false if there is overlap
- * with allocations of other resource groups and thus this resource group
- * cannot be exclusive.
- */
-static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp)
-{
-	int closid = rdtgrp->closid;
-	struct rdt_ctrl_domain *d;
-	struct resctrl_schema *s;
-	struct rdt_resource *r;
-	bool has_cache = false;
-	u32 ctrl;
-
-	/* Walking r->domains, ensure it can't race with cpuhp */
-	lockdep_assert_cpus_held();
-
-	list_for_each_entry(s, &resctrl_schema_all, list) {
-		r = s->res;
-		if (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)
-			continue;
-		has_cache = true;
-		list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
-			ctrl = resctrl_arch_get_config(r, d, closid,
-						       s->conf_type);
-			if (rdtgroup_cbm_overlaps(s, d, ctrl, closid, false)) {
-				rdt_last_cmd_puts("Schemata overlaps\n");
-				return false;
-			}
-		}
-	}
-
-	if (!has_cache) {
-		rdt_last_cmd_puts("Cannot be exclusive without CAT/CDP\n");
-		return false;
-	}
-
-	return true;
-}
-
-/*
- * rdtgroup_mode_write - Modify the resource group's mode
- */
-static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of,
-				   char *buf, size_t nbytes, loff_t off)
-{
-	struct rdtgroup *rdtgrp;
-	enum rdtgrp_mode mode;
-	int ret = 0;
-
-	/* Valid input requires a trailing newline */
-	if (nbytes == 0 || buf[nbytes - 1] != '\n')
-		return -EINVAL;
-	buf[nbytes - 1] = '\0';
-
-	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-	if (!rdtgrp) {
-		rdtgroup_kn_unlock(of->kn);
-		return -ENOENT;
-	}
-
-	rdt_last_cmd_clear();
-
-	mode = rdtgrp->mode;
-
-	if ((!strcmp(buf, "shareable") && mode == RDT_MODE_SHAREABLE) ||
-	    (!strcmp(buf, "exclusive") && mode == RDT_MODE_EXCLUSIVE) ||
-	    (!strcmp(buf, "pseudo-locksetup") &&
-	     mode == RDT_MODE_PSEUDO_LOCKSETUP) ||
-	    (!strcmp(buf, "pseudo-locked") && mode == RDT_MODE_PSEUDO_LOCKED))
-		goto out;
-
-	if (mode == RDT_MODE_PSEUDO_LOCKED) {
-		rdt_last_cmd_puts("Cannot change pseudo-locked group\n");
-		ret = -EINVAL;
-		goto out;
-	}
-
-	if (!strcmp(buf, "shareable")) {
-		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
-			ret = rdtgroup_locksetup_exit(rdtgrp);
-			if (ret)
-				goto out;
-		}
-		rdtgrp->mode = RDT_MODE_SHAREABLE;
-	} else if (!strcmp(buf, "exclusive")) {
-		if (!rdtgroup_mode_test_exclusive(rdtgrp)) {
-			ret = -EINVAL;
-			goto out;
-		}
-		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
-			ret = rdtgroup_locksetup_exit(rdtgrp);
-			if (ret)
-				goto out;
-		}
-		rdtgrp->mode = RDT_MODE_EXCLUSIVE;
-	} else if (IS_ENABLED(CONFIG_RESCTRL_FS_PSEUDO_LOCK) &&
-		   !strcmp(buf, "pseudo-locksetup")) {
-		ret = rdtgroup_locksetup_enter(rdtgrp);
-		if (ret)
-			goto out;
-		rdtgrp->mode = RDT_MODE_PSEUDO_LOCKSETUP;
-	} else {
-		rdt_last_cmd_puts("Unknown or unsupported mode\n");
-		ret = -EINVAL;
-	}
-
-out:
-	rdtgroup_kn_unlock(of->kn);
-	return ret ?: nbytes;
-}
-
-/**
- * rdtgroup_cbm_to_size - Translate CBM to size in bytes
- * @r: RDT resource to which @d belongs.
- * @d: RDT domain instance.
- * @cbm: bitmask for which the size should be computed.
- *
- * The bitmask provided associated with the RDT domain instance @d will be
- * translated into how many bytes it represents. The size in bytes is
- * computed by first dividing the total cache size by the CBM length to
- * determine how many bytes each bit in the bitmask represents. The result
- * is multiplied with the number of bits set in the bitmask.
- *
- * @cbm is unsigned long, even if only 32 bits are used to make the
- * bitmap functions work correctly.
- */
-unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
-				  struct rdt_ctrl_domain *d, unsigned long cbm)
-{
-	unsigned int size = 0;
-	struct cacheinfo *ci;
-	int num_b;
-
-	if (WARN_ON_ONCE(r->ctrl_scope != RESCTRL_L2_CACHE && r->ctrl_scope != RESCTRL_L3_CACHE))
-		return size;
-
-	num_b = bitmap_weight(&cbm, r->cache.cbm_len);
-	ci = get_cpu_cacheinfo_level(cpumask_any(&d->hdr.cpu_mask), r->ctrl_scope);
-	if (ci)
-		size = ci->size / r->cache.cbm_len * num_b;
-
-	return size;
-}
-
-bool is_mba_sc(struct rdt_resource *r)
-{
-	if (!r)
-		r = resctrl_arch_get_resource(RDT_RESOURCE_MBA);
-
-	/*
-	 * The software controller support is only applicable to MBA resource.
-	 * Make sure to check for resource type.
-	 */
-	if (r->rid != RDT_RESOURCE_MBA)
-		return false;
-
-	return r->membw.mba_sc;
-}
-
-/*
- * rdtgroup_size_show - Display size in bytes of allocated regions
- *
- * The "size" file mirrors the layout of the "schemata" file, printing the
- * size in bytes of each region instead of the capacity bitmask.
- */
-static int rdtgroup_size_show(struct kernfs_open_file *of,
-			      struct seq_file *s, void *v)
-{
-	struct resctrl_schema *schema;
-	enum resctrl_conf_type type;
-	struct rdt_ctrl_domain *d;
-	struct rdtgroup *rdtgrp;
-	struct rdt_resource *r;
-	unsigned int size;
-	int ret = 0;
-	u32 closid;
-	bool sep;
-	u32 ctrl;
-
-	rdtgrp = rdtgroup_kn_lock_live(of->kn);
-	if (!rdtgrp) {
-		rdtgroup_kn_unlock(of->kn);
-		return -ENOENT;
-	}
-
-	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
-		if (!rdtgrp->plr->d) {
-			rdt_last_cmd_clear();
-			rdt_last_cmd_puts("Cache domain offline\n");
-			ret = -ENODEV;
-		} else {
-			seq_printf(s, "%*s:", max_name_width,
-				   rdtgrp->plr->s->name);
-			size = rdtgroup_cbm_to_size(rdtgrp->plr->s->res,
-						    rdtgrp->plr->d,
-						    rdtgrp->plr->cbm);
-			seq_printf(s, "%d=%u\n", rdtgrp->plr->d->hdr.id, size);
-		}
-		goto out;
-	}
-
-	closid = rdtgrp->closid;
-
-	list_for_each_entry(schema, &resctrl_schema_all, list) {
-		r = schema->res;
-		type = schema->conf_type;
-		sep = false;
-		seq_printf(s, "%*s:", max_name_width, schema->name);
-		list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
-			if (sep)
-				seq_putc(s, ';');
-			if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
-				size = 0;
-			} else {
-				if (is_mba_sc(r))
-					ctrl = d->mbps_val[closid];
-				else
-					ctrl = resctrl_arch_get_config(r, d,
-								       closid,
-								       type);
-				if (r->rid == RDT_RESOURCE_MBA ||
-				    r->rid == RDT_RESOURCE_SMBA)
-					size = ctrl;
-				else
-					size = rdtgroup_cbm_to_size(r, d, ctrl);
-			}
-			seq_printf(s, "%d=%u", d->hdr.id, size);
-			sep = true;
-		}
-		seq_putc(s, '\n');
-	}
-
-out:
-	rdtgroup_kn_unlock(of->kn);
-
-	return ret;
-}
-
-#define INVALID_CONFIG_INDEX   UINT_MAX
-
-/**
- * mon_event_config_index_get - get the hardware index for the
- *                              configurable event
- * @evtid: event id.
- *
- * Return: 0 for evtid == QOS_L3_MBM_TOTAL_EVENT_ID
- *         1 for evtid == QOS_L3_MBM_LOCAL_EVENT_ID
- *         INVALID_CONFIG_INDEX for invalid evtid
- */
-static inline unsigned int mon_event_config_index_get(u32 evtid)
-{
-	switch (evtid) {
-	case QOS_L3_MBM_TOTAL_EVENT_ID:
-		return 0;
-	case QOS_L3_MBM_LOCAL_EVENT_ID:
-		return 1;
-	default:
-		/* Should never reach here */
-		return INVALID_CONFIG_INDEX;
-	}
-}
-
-void resctrl_arch_mon_event_config_read(void *_config_info)
-{
-	struct resctrl_mon_config_info *config_info = _config_info;
-	unsigned int index;
-	u64 msrval;
-
-	index = mon_event_config_index_get(config_info->evtid);
-	if (index == INVALID_CONFIG_INDEX) {
-		pr_warn_once("Invalid event id %d\n", config_info->evtid);
-		return;
-	}
-	rdmsrl(MSR_IA32_EVT_CFG_BASE + index, msrval);
-
-	/* Report only the valid event configuration bits */
-	config_info->mon_config = msrval & MAX_EVT_CONFIG_BITS;
-}
-
-static void mondata_config_read(struct resctrl_mon_config_info *mon_info)
-{
-	smp_call_function_any(&mon_info->d->hdr.cpu_mask,
-			      resctrl_arch_mon_event_config_read, mon_info, 1);
-}
-
-static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid)
-{
-	struct resctrl_mon_config_info mon_info;
-	struct rdt_mon_domain *dom;
-	bool sep = false;
-
-	cpus_read_lock();
-	mutex_lock(&rdtgroup_mutex);
-
-	list_for_each_entry(dom, &r->mon_domains, hdr.list) {
-		if (sep)
-			seq_puts(s, ";");
-
-		memset(&mon_info, 0, sizeof(struct resctrl_mon_config_info));
-		mon_info.r = r;
-		mon_info.d = dom;
-		mon_info.evtid = evtid;
-		mondata_config_read(&mon_info);
-
-		seq_printf(s, "%d=0x%02x", dom->hdr.id, mon_info.mon_config);
-		sep = true;
-	}
-	seq_puts(s, "\n");
-
-	mutex_unlock(&rdtgroup_mutex);
-	cpus_read_unlock();
-
-	return 0;
-}
-
-static int mbm_total_bytes_config_show(struct kernfs_open_file *of,
-				       struct seq_file *seq, void *v)
-{
-	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
-
-	mbm_config_show(seq, r, QOS_L3_MBM_TOTAL_EVENT_ID);
-
-	return 0;
-}
-
-static int mbm_local_bytes_config_show(struct kernfs_open_file *of,
-				       struct seq_file *seq, void *v)
-{
-	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
-
-	mbm_config_show(seq, r, QOS_L3_MBM_LOCAL_EVENT_ID);
-
-	return 0;
-}
-
-void resctrl_arch_mon_event_config_write(void *_config_info)
-{
-	struct resctrl_mon_config_info *config_info = _config_info;
-	unsigned int index;
-
-	index = mon_event_config_index_get(config_info->evtid);
-	if (index == INVALID_CONFIG_INDEX) {
-		pr_warn_once("Invalid event id %d\n", config_info->evtid);
-		return;
-	}
-	wrmsr(MSR_IA32_EVT_CFG_BASE + index, config_info->mon_config, 0);
-}
-
-static void mbm_config_write_domain(struct rdt_resource *r,
-				    struct rdt_mon_domain *d, u32 evtid, u32 val)
-{
-	struct resctrl_mon_config_info mon_info = {0};
-
-	/*
-	 * Read the current config value first. If both are the same then
-	 * no need to write it again.
-	 */
-	mon_info.r = r;
-	mon_info.d = d;
-	mon_info.evtid = evtid;
-	mondata_config_read(&mon_info);
-	if (mon_info.mon_config == val)
-		return;
-
-	mon_info.mon_config = val;
-
-	/*
-	 * Update MSR_IA32_EVT_CFG_BASE MSR on one of the CPUs in the
-	 * domain. The MSRs offset from MSR MSR_IA32_EVT_CFG_BASE
-	 * are scoped at the domain level. Writing any of these MSRs
-	 * on one CPU is observed by all the CPUs in the domain.
-	 */
-	smp_call_function_any(&d->hdr.cpu_mask, resctrl_arch_mon_event_config_write,
-			      &mon_info, 1);
-
-	/*
-	 * When an Event Configuration is changed, the bandwidth counters
-	 * for all RMIDs and Events will be cleared by the hardware. The
-	 * hardware also sets MSR_IA32_QM_CTR.Unavailable (bit 62) for
-	 * every RMID on the next read to any event for every RMID.
-	 * Subsequent reads will have MSR_IA32_QM_CTR.Unavailable (bit 62)
-	 * cleared while it is tracked by the hardware. Clear the
-	 * mbm_local and mbm_total counts for all the RMIDs.
-	 */
-	resctrl_arch_reset_rmid_all(r, d);
-}
-
-static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid)
-{
-	char *dom_str = NULL, *id_str;
-	unsigned long dom_id, val;
-	struct rdt_mon_domain *d;
-
-	/* Walking r->domains, ensure it can't race with cpuhp */
-	lockdep_assert_cpus_held();
-
-next:
-	if (!tok || tok[0] == '\0')
-		return 0;
-
-	/* Start processing the strings for each domain */
-	dom_str = strim(strsep(&tok, ";"));
-	id_str = strsep(&dom_str, "=");
-
-	if (!id_str || kstrtoul(id_str, 10, &dom_id)) {
-		rdt_last_cmd_puts("Missing '=' or non-numeric domain id\n");
-		return -EINVAL;
-	}
-
-	if (!dom_str || kstrtoul(dom_str, 16, &val)) {
-		rdt_last_cmd_puts("Non-numeric event configuration value\n");
-		return -EINVAL;
-	}
-
-	/* Value from user cannot be more than the supported set of events */
-	if ((val & r->mbm_cfg_mask) != val) {
-		rdt_last_cmd_printf("Invalid event configuration: max valid mask is 0x%02x\n",
-				    r->mbm_cfg_mask);
-		return -EINVAL;
-	}
-
-	list_for_each_entry(d, &r->mon_domains, hdr.list) {
-		if (d->hdr.id == dom_id) {
-			mbm_config_write_domain(r, d, evtid, val);
-			goto next;
-		}
-	}
-
-	return -EINVAL;
-}
-
-static ssize_t mbm_total_bytes_config_write(struct kernfs_open_file *of,
-					    char *buf, size_t nbytes,
-					    loff_t off)
-{
-	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
-	int ret;
-
-	/* Valid input requires a trailing newline */
-	if (nbytes == 0 || buf[nbytes - 1] != '\n')
-		return -EINVAL;
-
-	cpus_read_lock();
-	mutex_lock(&rdtgroup_mutex);
-
-	rdt_last_cmd_clear();
-
-	buf[nbytes - 1] = '\0';
-
-	ret = mon_config_write(r, buf, QOS_L3_MBM_TOTAL_EVENT_ID);
-
-	mutex_unlock(&rdtgroup_mutex);
-	cpus_read_unlock();
-
-	return ret ?: nbytes;
-}
-
-static ssize_t mbm_local_bytes_config_write(struct kernfs_open_file *of,
-					    char *buf, size_t nbytes,
-					    loff_t off)
-{
-	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
-	int ret;
-
-	/* Valid input requires a trailing newline */
-	if (nbytes == 0 || buf[nbytes - 1] != '\n')
-		return -EINVAL;
-
-	cpus_read_lock();
-	mutex_lock(&rdtgroup_mutex);
-
-	rdt_last_cmd_clear();
-
-	buf[nbytes - 1] = '\0';
-
-	ret = mon_config_write(r, buf, QOS_L3_MBM_LOCAL_EVENT_ID);
-
-	mutex_unlock(&rdtgroup_mutex);
-	cpus_read_unlock();
-
-	return ret ?: nbytes;
-}
-
-/* rdtgroup information files for one cache resource. */
-static struct rftype res_common_files[] = {
-	{
-		.name		= "last_cmd_status",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_last_cmd_status_show,
-		.fflags		= RFTYPE_TOP_INFO,
-	},
-	{
-		.name		= "num_closids",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_num_closids_show,
-		.fflags		= RFTYPE_CTRL_INFO,
-	},
-	{
-		.name		= "mon_features",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_mon_features_show,
-		.fflags		= RFTYPE_MON_INFO,
-	},
-	{
-		.name		= "num_rmids",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_num_rmids_show,
-		.fflags		= RFTYPE_MON_INFO,
-	},
-	{
-		.name		= "cbm_mask",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_default_ctrl_show,
-		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
-	},
-	{
-		.name		= "min_cbm_bits",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_min_cbm_bits_show,
-		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
-	},
-	{
-		.name		= "shareable_bits",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_shareable_bits_show,
-		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
-	},
-	{
-		.name		= "bit_usage",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_bit_usage_show,
-		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
-	},
-	{
-		.name		= "min_bandwidth",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_min_bw_show,
-		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_MB,
-	},
-	{
-		.name		= "bandwidth_gran",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_bw_gran_show,
-		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_MB,
-	},
-	{
-		.name		= "delay_linear",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_delay_linear_show,
-		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_MB,
-	},
-	/*
-	 * Platform specific which (if any) capabilities are provided by
-	 * thread_throttle_mode. Defer "fflags" initialization to platform
-	 * discovery.
-	 */
-	{
-		.name		= "thread_throttle_mode",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_thread_throttle_mode_show,
-	},
-	{
-		.name		= "max_threshold_occupancy",
-		.mode		= 0644,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.write		= max_threshold_occ_write,
-		.seq_show	= max_threshold_occ_show,
-		.fflags		= RFTYPE_MON_INFO | RFTYPE_RES_CACHE,
-	},
-	{
-		.name		= "mbm_total_bytes_config",
-		.mode		= 0644,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= mbm_total_bytes_config_show,
-		.write		= mbm_total_bytes_config_write,
-	},
-	{
-		.name		= "mbm_local_bytes_config",
-		.mode		= 0644,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= mbm_local_bytes_config_show,
-		.write		= mbm_local_bytes_config_write,
-	},
-	{
-		.name		= "cpus",
-		.mode		= 0644,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.write		= rdtgroup_cpus_write,
-		.seq_show	= rdtgroup_cpus_show,
-		.fflags		= RFTYPE_BASE,
-	},
-	{
-		.name		= "cpus_list",
-		.mode		= 0644,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.write		= rdtgroup_cpus_write,
-		.seq_show	= rdtgroup_cpus_show,
-		.flags		= RFTYPE_FLAGS_CPUS_LIST,
-		.fflags		= RFTYPE_BASE,
-	},
-	{
-		.name		= "tasks",
-		.mode		= 0644,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.write		= rdtgroup_tasks_write,
-		.seq_show	= rdtgroup_tasks_show,
-		.fflags		= RFTYPE_BASE,
-	},
-	{
-		.name		= "mon_hw_id",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdtgroup_rmid_show,
-		.fflags		= RFTYPE_MON_BASE | RFTYPE_DEBUG,
-	},
-	{
-		.name		= "schemata",
-		.mode		= 0644,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.write		= rdtgroup_schemata_write,
-		.seq_show	= rdtgroup_schemata_show,
-		.fflags		= RFTYPE_CTRL_BASE,
-	},
-	{
-		.name		= "mba_MBps_event",
-		.mode		= 0644,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.write		= rdtgroup_mba_mbps_event_write,
-		.seq_show	= rdtgroup_mba_mbps_event_show,
-	},
-	{
-		.name		= "mode",
-		.mode		= 0644,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.write		= rdtgroup_mode_write,
-		.seq_show	= rdtgroup_mode_show,
-		.fflags		= RFTYPE_CTRL_BASE,
-	},
-	{
-		.name		= "size",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdtgroup_size_show,
-		.fflags		= RFTYPE_CTRL_BASE,
-	},
-	{
-		.name		= "sparse_masks",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_has_sparse_bitmasks_show,
-		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
-	},
-	{
-		.name		= "ctrl_hw_id",
-		.mode		= 0444,
-		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdtgroup_closid_show,
-		.fflags		= RFTYPE_CTRL_BASE | RFTYPE_DEBUG,
-	},
-};
-
-static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags)
-{
-	struct rftype *rfts, *rft;
-	int ret, len;
-
-	rfts = res_common_files;
-	len = ARRAY_SIZE(res_common_files);
-
-	lockdep_assert_held(&rdtgroup_mutex);
-
-	if (resctrl_debug)
-		fflags |= RFTYPE_DEBUG;
-
-	for (rft = rfts; rft < rfts + len; rft++) {
-		if (rft->fflags && ((fflags & rft->fflags) == rft->fflags)) {
-			ret = rdtgroup_add_file(kn, rft);
-			if (ret)
-				goto error;
-		}
-	}
-
-	return 0;
-error:
-	pr_warn("Failed to add %s, err=%d\n", rft->name, ret);
-	while (--rft >= rfts) {
-		if ((fflags & rft->fflags) == rft->fflags)
-			kernfs_remove_by_name(kn, rft->name);
-	}
-	return ret;
-}
-
-static struct rftype *rdtgroup_get_rftype_by_name(const char *name)
-{
-	struct rftype *rfts, *rft;
-	int len;
-
-	rfts = res_common_files;
-	len = ARRAY_SIZE(res_common_files);
-
-	for (rft = rfts; rft < rfts + len; rft++) {
-		if (!strcmp(rft->name, name))
-			return rft;
-	}
-
-	return NULL;
-}
-
-static void thread_throttle_mode_init(void)
-{
-	enum membw_throttle_mode throttle_mode = THREAD_THROTTLE_UNDEFINED;
-	struct rdt_resource *r_mba, *r_smba;
-
-	r_mba = resctrl_arch_get_resource(RDT_RESOURCE_MBA);
-	if (r_mba->alloc_capable &&
-	    r_mba->membw.throttle_mode != THREAD_THROTTLE_UNDEFINED)
-		throttle_mode = r_mba->membw.throttle_mode;
-
-	r_smba = resctrl_arch_get_resource(RDT_RESOURCE_SMBA);
-	if (r_smba->alloc_capable &&
-	    r_smba->membw.throttle_mode != THREAD_THROTTLE_UNDEFINED)
-		throttle_mode = r_smba->membw.throttle_mode;
-
-	if (throttle_mode == THREAD_THROTTLE_UNDEFINED)
-		return;
-
-	resctrl_file_fflags_init("thread_throttle_mode",
-				 RFTYPE_CTRL_INFO | RFTYPE_RES_MB);
-}
-
-void resctrl_file_fflags_init(const char *config, unsigned long fflags)
-{
-	struct rftype *rft;
-
-	rft = rdtgroup_get_rftype_by_name(config);
-	if (rft)
-		rft->fflags = fflags;
-}
-
-/**
- * rdtgroup_kn_mode_restrict - Restrict user access to named resctrl file
- * @r: The resource group with which the file is associated.
- * @name: Name of the file
- *
- * The permissions of named resctrl file, directory, or link are modified
- * to not allow read, write, or execute by any user.
- *
- * WARNING: This function is intended to communicate to the user that the
- * resctrl file has been locked down - that it is not relevant to the
- * particular state the system finds itself in. It should not be relied
- * on to protect from user access because after the file's permissions
- * are restricted the user can still change the permissions using chmod
- * from the command line.
- *
- * Return: 0 on success, <0 on failure.
- */
-int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name)
-{
-	struct iattr iattr = {.ia_valid = ATTR_MODE,};
-	struct kernfs_node *kn;
-	int ret = 0;
-
-	kn = kernfs_find_and_get_ns(r->kn, name, NULL);
-	if (!kn)
-		return -ENOENT;
-
-	switch (kernfs_type(kn)) {
-	case KERNFS_DIR:
-		iattr.ia_mode = S_IFDIR;
-		break;
-	case KERNFS_FILE:
-		iattr.ia_mode = S_IFREG;
-		break;
-	case KERNFS_LINK:
-		iattr.ia_mode = S_IFLNK;
-		break;
-	}
-
-	ret = kernfs_setattr(kn, &iattr);
-	kernfs_put(kn);
-	return ret;
-}
-
-/**
- * rdtgroup_kn_mode_restore - Restore user access to named resctrl file
- * @r: The resource group with which the file is associated.
- * @name: Name of the file
- * @mask: Mask of permissions that should be restored
- *
- * Restore the permissions of the named file. If @name is a directory the
- * permissions of its parent will be used.
- *
- * Return: 0 on success, <0 on failure.
- */
-int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name,
-			     umode_t mask)
-{
-	struct iattr iattr = {.ia_valid = ATTR_MODE,};
-	struct kernfs_node *kn, *parent;
-	struct rftype *rfts, *rft;
-	int ret, len;
-
-	rfts = res_common_files;
-	len = ARRAY_SIZE(res_common_files);
-
-	for (rft = rfts; rft < rfts + len; rft++) {
-		if (!strcmp(rft->name, name))
-			iattr.ia_mode = rft->mode & mask;
-	}
-
-	kn = kernfs_find_and_get_ns(r->kn, name, NULL);
-	if (!kn)
-		return -ENOENT;
-
-	switch (kernfs_type(kn)) {
-	case KERNFS_DIR:
-		parent = kernfs_get_parent(kn);
-		if (parent) {
-			iattr.ia_mode |= parent->mode;
-			kernfs_put(parent);
-		}
-		iattr.ia_mode |= S_IFDIR;
-		break;
-	case KERNFS_FILE:
-		iattr.ia_mode |= S_IFREG;
-		break;
-	case KERNFS_LINK:
-		iattr.ia_mode |= S_IFLNK;
-		break;
-	}
-
-	ret = kernfs_setattr(kn, &iattr);
-	kernfs_put(kn);
-	return ret;
-}
-
-static int rdtgroup_mkdir_info_resdir(void *priv, char *name,
-				      unsigned long fflags)
-{
-	struct kernfs_node *kn_subdir;
-	int ret;
-
-	kn_subdir = kernfs_create_dir(kn_info, name,
-				      kn_info->mode, priv);
-	if (IS_ERR(kn_subdir))
-		return PTR_ERR(kn_subdir);
-
-	ret = rdtgroup_kn_set_ugid(kn_subdir);
-	if (ret)
-		return ret;
-
-	ret = rdtgroup_add_files(kn_subdir, fflags);
-	if (!ret)
-		kernfs_activate(kn_subdir);
-
-	return ret;
-}
-
-static unsigned long fflags_from_resource(struct rdt_resource *r)
-{
-	switch (r->rid) {
-	case RDT_RESOURCE_L3:
-	case RDT_RESOURCE_L2:
-		return RFTYPE_RES_CACHE;
-	case RDT_RESOURCE_MBA:
-	case RDT_RESOURCE_SMBA:
-		return RFTYPE_RES_MB;
-	}
-
-	return WARN_ON_ONCE(1);
-}
-
-static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
-{
-	struct resctrl_schema *s;
-	struct rdt_resource *r;
-	unsigned long fflags;
-	char name[32];
-	int ret;
-
-	/* create the directory */
-	kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL);
-	if (IS_ERR(kn_info))
-		return PTR_ERR(kn_info);
-
-	ret = rdtgroup_add_files(kn_info, RFTYPE_TOP_INFO);
-	if (ret)
-		goto out_destroy;
-
-	/* loop over enabled controls, these are all alloc_capable */
-	list_for_each_entry(s, &resctrl_schema_all, list) {
-		r = s->res;
-		fflags = fflags_from_resource(r) | RFTYPE_CTRL_INFO;
-		ret = rdtgroup_mkdir_info_resdir(s, s->name, fflags);
-		if (ret)
-			goto out_destroy;
-	}
-
-	for_each_mon_capable_rdt_resource(r) {
-		fflags = fflags_from_resource(r) | RFTYPE_MON_INFO;
-		sprintf(name, "%s_MON", r->name);
-		ret = rdtgroup_mkdir_info_resdir(r, name, fflags);
-		if (ret)
-			goto out_destroy;
-	}
-
-	ret = rdtgroup_kn_set_ugid(kn_info);
-	if (ret)
-		goto out_destroy;
-
-	kernfs_activate(kn_info);
-
-	return 0;
-
-out_destroy:
-	kernfs_remove(kn_info);
-	return ret;
-}
-
-static int
-mongroup_create_dir(struct kernfs_node *parent_kn, struct rdtgroup *prgrp,
-		    char *name, struct kernfs_node **dest_kn)
-{
-	struct kernfs_node *kn;
-	int ret;
-
-	/* create the directory */
-	kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp);
-	if (IS_ERR(kn))
-		return PTR_ERR(kn);
-
-	if (dest_kn)
-		*dest_kn = kn;
-
-	ret = rdtgroup_kn_set_ugid(kn);
-	if (ret)
-		goto out_destroy;
-
-	kernfs_activate(kn);
-
-	return 0;
-
-out_destroy:
-	kernfs_remove(kn);
-	return ret;
-}
-
-static void l3_qos_cfg_update(void *arg)
-{
-	bool *enable = arg;
-
-	wrmsrl(MSR_IA32_L3_QOS_CFG, *enable ? L3_QOS_CDP_ENABLE : 0ULL);
-}
-
-static void l2_qos_cfg_update(void *arg)
-{
-	bool *enable = arg;
-
-	wrmsrl(MSR_IA32_L2_QOS_CFG, *enable ? L2_QOS_CDP_ENABLE : 0ULL);
-}
-
-static inline bool is_mba_linear(void)
-{
-	return resctrl_arch_get_resource(RDT_RESOURCE_MBA)->membw.delay_linear;
-}
-
-static int set_cache_qos_cfg(int level, bool enable)
-{
-	void (*update)(void *arg);
-	struct rdt_ctrl_domain *d;
-	struct rdt_resource *r_l;
-	cpumask_var_t cpu_mask;
-	int cpu;
-
-	/* Walking r->domains, ensure it can't race with cpuhp */
-	lockdep_assert_cpus_held();
-
-	if (level == RDT_RESOURCE_L3)
-		update = l3_qos_cfg_update;
-	else if (level == RDT_RESOURCE_L2)
-		update = l2_qos_cfg_update;
-	else
-		return -EINVAL;
-
-	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
-		return -ENOMEM;
-
-	r_l = &rdt_resources_all[level].r_resctrl;
-	list_for_each_entry(d, &r_l->ctrl_domains, hdr.list) {
-		if (r_l->cache.arch_has_per_cpu_cfg)
-			/* Pick all the CPUs in the domain instance */
-			for_each_cpu(cpu, &d->hdr.cpu_mask)
-				cpumask_set_cpu(cpu, cpu_mask);
-		else
-			/* Pick one CPU from each domain instance to update MSR */
-			cpumask_set_cpu(cpumask_any(&d->hdr.cpu_mask), cpu_mask);
-	}
-
-	/* Update QOS_CFG MSR on all the CPUs in cpu_mask */
-	on_each_cpu_mask(cpu_mask, update, &enable, 1);
-
-	free_cpumask_var(cpu_mask);
-
-	return 0;
-}
-
-/* Restore the qos cfg state when a domain comes online */
-void rdt_domain_reconfigure_cdp(struct rdt_resource *r)
-{
-	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
-
-	if (!r->cdp_capable)
-		return;
-
-	if (r->rid == RDT_RESOURCE_L2)
-		l2_qos_cfg_update(&hw_res->cdp_enabled);
-
-	if (r->rid == RDT_RESOURCE_L3)
-		l3_qos_cfg_update(&hw_res->cdp_enabled);
-}
-
-static int mba_sc_domain_allocate(struct rdt_resource *r, struct rdt_ctrl_domain *d)
-{
-	u32 num_closid = resctrl_arch_get_num_closid(r);
-	int cpu = cpumask_any(&d->hdr.cpu_mask);
-	int i;
-
-	d->mbps_val = kcalloc_node(num_closid, sizeof(*d->mbps_val),
-				   GFP_KERNEL, cpu_to_node(cpu));
-	if (!d->mbps_val)
-		return -ENOMEM;
-
-	for (i = 0; i < num_closid; i++)
-		d->mbps_val[i] = MBA_MAX_MBPS;
-
-	return 0;
-}
-
-static void mba_sc_domain_destroy(struct rdt_resource *r,
-				  struct rdt_ctrl_domain *d)
-{
-	kfree(d->mbps_val);
-	d->mbps_val = NULL;
-}
-
-/*
- * MBA software controller is supported only if
- * MBM is supported and MBA is in linear scale,
- * and the MBM monitor scope is the same as MBA
- * control scope.
- */
-static bool supports_mba_mbps(void)
-{
-	struct rdt_resource *rmbm = resctrl_arch_get_resource(RDT_RESOURCE_L3);
-	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_MBA);
-
-	return (resctrl_is_mbm_enabled() &&
-		r->alloc_capable && is_mba_linear() &&
-		r->ctrl_scope == rmbm->mon_scope);
-}
-
-/*
- * Enable or disable the MBA software controller
- * which helps user specify bandwidth in MBps.
- */
-static int set_mba_sc(bool mba_sc)
-{
-	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_MBA);
-	u32 num_closid = resctrl_arch_get_num_closid(r);
-	struct rdt_ctrl_domain *d;
-	unsigned long fflags;
-	int i;
-
-	if (!supports_mba_mbps() || mba_sc == is_mba_sc(r))
-		return -EINVAL;
-
-	r->membw.mba_sc = mba_sc;
-
-	rdtgroup_default.mba_mbps_event = mba_mbps_default_event;
-
-	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
-		for (i = 0; i < num_closid; i++)
-			d->mbps_val[i] = MBA_MAX_MBPS;
-	}
-
-	fflags = mba_sc ? RFTYPE_CTRL_BASE | RFTYPE_MON_BASE : 0;
-	resctrl_file_fflags_init("mba_MBps_event", fflags);
-
-	return 0;
-}
-
-static int cdp_enable(int level)
-{
-	struct rdt_resource *r_l = &rdt_resources_all[level].r_resctrl;
-	int ret;
-
-	if (!r_l->alloc_capable)
-		return -EINVAL;
-
-	ret = set_cache_qos_cfg(level, true);
-	if (!ret)
-		rdt_resources_all[level].cdp_enabled = true;
-
-	return ret;
-}
-
-static void cdp_disable(int level)
-{
-	struct rdt_hw_resource *r_hw = &rdt_resources_all[level];
-
-	if (r_hw->cdp_enabled) {
-		set_cache_qos_cfg(level, false);
-		r_hw->cdp_enabled = false;
-	}
-}
-
-int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable)
-{
-	struct rdt_hw_resource *hw_res = &rdt_resources_all[l];
-
-	if (!hw_res->r_resctrl.cdp_capable)
-		return -EINVAL;
-
-	if (enable)
-		return cdp_enable(l);
-
-	cdp_disable(l);
-
-	return 0;
-}
-
-bool resctrl_arch_get_cdp_enabled(enum resctrl_res_level l)
-{
-	return rdt_resources_all[l].cdp_enabled;
-}
-
-/*
- * We don't allow rdtgroup directories to be created anywhere
- * except the root directory. Thus when looking for the rdtgroup
- * structure for a kernfs node we are either looking at a directory,
- * in which case the rdtgroup structure is pointed at by the "priv"
- * field, otherwise we have a file, and need only look to the parent
- * to find the rdtgroup.
- */
-static struct rdtgroup *kernfs_to_rdtgroup(struct kernfs_node *kn)
-{
-	if (kernfs_type(kn) == KERNFS_DIR) {
-		/*
-		 * All the resource directories use "kn->priv"
-		 * to point to the "struct rdtgroup" for the
-		 * resource. "info" and its subdirectories don't
-		 * have rdtgroup structures, so return NULL here.
-		 */
-		if (kn == kn_info ||
-		    rcu_access_pointer(kn->__parent) == kn_info)
-			return NULL;
-		else
-			return kn->priv;
-	} else {
-		return rdt_kn_parent_priv(kn);
-	}
-}
-
-static void rdtgroup_kn_get(struct rdtgroup *rdtgrp, struct kernfs_node *kn)
-{
-	atomic_inc(&rdtgrp->waitcount);
-	kernfs_break_active_protection(kn);
-}
-
-static void rdtgroup_kn_put(struct rdtgroup *rdtgrp, struct kernfs_node *kn)
-{
-	if (atomic_dec_and_test(&rdtgrp->waitcount) &&
-	    (rdtgrp->flags & RDT_DELETED)) {
-		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
-		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
-			rdtgroup_pseudo_lock_remove(rdtgrp);
-		kernfs_unbreak_active_protection(kn);
-		rdtgroup_remove(rdtgrp);
-	} else {
-		kernfs_unbreak_active_protection(kn);
-	}
-}
-
-struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn)
-{
-	struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn);
-
-	if (!rdtgrp)
-		return NULL;
-
-	rdtgroup_kn_get(rdtgrp, kn);
-
-	cpus_read_lock();
-	mutex_lock(&rdtgroup_mutex);
-
-	/* Was this group deleted while we waited? */
-	if (rdtgrp->flags & RDT_DELETED)
-		return NULL;
-
-	return rdtgrp;
-}
-
-void rdtgroup_kn_unlock(struct kernfs_node *kn)
-{
-	struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn);
-
-	if (!rdtgrp)
-		return;
-
-	mutex_unlock(&rdtgroup_mutex);
-	cpus_read_unlock();
-
-	rdtgroup_kn_put(rdtgrp, kn);
-}
-
-static int mkdir_mondata_all(struct kernfs_node *parent_kn,
-			     struct rdtgroup *prgrp,
-			     struct kernfs_node **mon_data_kn);
-
-static void rdt_disable_ctx(void)
-{
-	resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false);
-	resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false);
-	set_mba_sc(false);
-
-	resctrl_debug = false;
-}
-
-static int rdt_enable_ctx(struct rdt_fs_context *ctx)
-{
-	int ret = 0;
-
-	if (ctx->enable_cdpl2) {
-		ret = resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, true);
-		if (ret)
-			goto out_done;
-	}
-
-	if (ctx->enable_cdpl3) {
-		ret = resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, true);
-		if (ret)
-			goto out_cdpl2;
-	}
-
-	if (ctx->enable_mba_mbps) {
-		ret = set_mba_sc(true);
-		if (ret)
-			goto out_cdpl3;
-	}
-
-	if (ctx->enable_debug)
-		resctrl_debug = true;
-
-	return 0;
-
-out_cdpl3:
-	resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false);
-out_cdpl2:
-	resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false);
-out_done:
-	return ret;
-}
-
-static int schemata_list_add(struct rdt_resource *r, enum resctrl_conf_type type)
-{
-	struct resctrl_schema *s;
-	const char *suffix = "";
-	int ret, cl;
-
-	s = kzalloc(sizeof(*s), GFP_KERNEL);
-	if (!s)
-		return -ENOMEM;
-
-	s->res = r;
-	s->num_closid = resctrl_arch_get_num_closid(r);
-	if (resctrl_arch_get_cdp_enabled(r->rid))
-		s->num_closid /= 2;
-
-	s->conf_type = type;
-	switch (type) {
-	case CDP_CODE:
-		suffix = "CODE";
-		break;
-	case CDP_DATA:
-		suffix = "DATA";
-		break;
-	case CDP_NONE:
-		suffix = "";
-		break;
-	}
-
-	ret = snprintf(s->name, sizeof(s->name), "%s%s", r->name, suffix);
-	if (ret >= sizeof(s->name)) {
-		kfree(s);
-		return -EINVAL;
-	}
-
-	cl = strlen(s->name);
-
-	/*
-	 * If CDP is supported by this resource, but not enabled,
-	 * include the suffix. This ensures the tabular format of the
-	 * schemata file does not change between mounts of the filesystem.
-	 */
-	if (r->cdp_capable && !resctrl_arch_get_cdp_enabled(r->rid))
-		cl += 4;
-
-	if (cl > max_name_width)
-		max_name_width = cl;
-
-	switch (r->schema_fmt) {
-	case RESCTRL_SCHEMA_BITMAP:
-		s->fmt_str = "%d=%x";
-		break;
-	case RESCTRL_SCHEMA_RANGE:
-		s->fmt_str = "%d=%u";
-		break;
-	}
-
-	if (WARN_ON_ONCE(!s->fmt_str)) {
-		kfree(s);
-		return -EINVAL;
-	}
-
-	INIT_LIST_HEAD(&s->list);
-	list_add(&s->list, &resctrl_schema_all);
-
-	return 0;
-}
-
-static int schemata_list_create(void)
-{
-	struct rdt_resource *r;
-	int ret = 0;
-
-	for_each_alloc_capable_rdt_resource(r) {
-		if (resctrl_arch_get_cdp_enabled(r->rid)) {
-			ret = schemata_list_add(r, CDP_CODE);
-			if (ret)
-				break;
-
-			ret = schemata_list_add(r, CDP_DATA);
-		} else {
-			ret = schemata_list_add(r, CDP_NONE);
-		}
-
-		if (ret)
-			break;
-	}
-
-	return ret;
-}
-
-static void schemata_list_destroy(void)
-{
-	struct resctrl_schema *s, *tmp;
-
-	list_for_each_entry_safe(s, tmp, &resctrl_schema_all, list) {
-		list_del(&s->list);
-		kfree(s);
-	}
-}
-
-static int rdt_get_tree(struct fs_context *fc)
-{
-	struct rdt_fs_context *ctx = rdt_fc2context(fc);
-	unsigned long flags = RFTYPE_CTRL_BASE;
-	struct rdt_mon_domain *dom;
-	struct rdt_resource *r;
-	int ret;
-
-	cpus_read_lock();
-	mutex_lock(&rdtgroup_mutex);
-	/*
-	 * resctrl file system can only be mounted once.
-	 */
-	if (resctrl_mounted) {
-		ret = -EBUSY;
-		goto out;
-	}
-
-	ret = rdtgroup_setup_root(ctx);
-	if (ret)
-		goto out;
-
-	ret = rdt_enable_ctx(ctx);
-	if (ret)
-		goto out_root;
-
-	ret = schemata_list_create();
-	if (ret) {
-		schemata_list_destroy();
-		goto out_ctx;
-	}
-
-	ret = closid_init();
-	if (ret)
-		goto out_schemata_free;
-
-	if (resctrl_arch_mon_capable())
-		flags |= RFTYPE_MON;
-
-	ret = rdtgroup_add_files(rdtgroup_default.kn, flags);
-	if (ret)
-		goto out_closid_exit;
-
-	kernfs_activate(rdtgroup_default.kn);
-
-	ret = rdtgroup_create_info_dir(rdtgroup_default.kn);
-	if (ret < 0)
-		goto out_closid_exit;
-
-	if (resctrl_arch_mon_capable()) {
-		ret = mongroup_create_dir(rdtgroup_default.kn,
-					  &rdtgroup_default, "mon_groups",
-					  &kn_mongrp);
-		if (ret < 0)
-			goto out_info;
-
-		ret = mkdir_mondata_all(rdtgroup_default.kn,
-					&rdtgroup_default, &kn_mondata);
-		if (ret < 0)
-			goto out_mongrp;
-		rdtgroup_default.mon.mon_data_kn = kn_mondata;
-	}
-
-	ret = rdt_pseudo_lock_init();
-	if (ret)
-		goto out_mondata;
-
-	ret = kernfs_get_tree(fc);
-	if (ret < 0)
-		goto out_psl;
-
-	if (resctrl_arch_alloc_capable())
-		resctrl_arch_enable_alloc();
-	if (resctrl_arch_mon_capable())
-		resctrl_arch_enable_mon();
-
-	if (resctrl_arch_alloc_capable() || resctrl_arch_mon_capable())
-		resctrl_mounted = true;
-
-	if (resctrl_is_mbm_enabled()) {
-		r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
-		list_for_each_entry(dom, &r->mon_domains, hdr.list)
-			mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL,
-						   RESCTRL_PICK_ANY_CPU);
-	}
-
-	goto out;
-
-out_psl:
-	rdt_pseudo_lock_release();
-out_mondata:
-	if (resctrl_arch_mon_capable())
-		kernfs_remove(kn_mondata);
-out_mongrp:
-	if (resctrl_arch_mon_capable())
-		kernfs_remove(kn_mongrp);
-out_info:
-	kernfs_remove(kn_info);
-out_closid_exit:
-	closid_exit();
-out_schemata_free:
-	schemata_list_destroy();
-out_ctx:
-	rdt_disable_ctx();
-out_root:
-	rdtgroup_destroy_root();
-out:
-	rdt_last_cmd_clear();
-	mutex_unlock(&rdtgroup_mutex);
-	cpus_read_unlock();
-	return ret;
-}
-
-enum rdt_param {
-	Opt_cdp,
-	Opt_cdpl2,
-	Opt_mba_mbps,
-	Opt_debug,
-	nr__rdt_params
-};
-
-static const struct fs_parameter_spec rdt_fs_parameters[] = {
-	fsparam_flag("cdp",		Opt_cdp),
-	fsparam_flag("cdpl2",		Opt_cdpl2),
-	fsparam_flag("mba_MBps",	Opt_mba_mbps),
-	fsparam_flag("debug",		Opt_debug),
-	{}
-};
-
-static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param)
-{
-	struct rdt_fs_context *ctx = rdt_fc2context(fc);
-	struct fs_parse_result result;
-	const char *msg;
-	int opt;
-
-	opt = fs_parse(fc, rdt_fs_parameters, param, &result);
-	if (opt < 0)
-		return opt;
-
-	switch (opt) {
-	case Opt_cdp:
-		ctx->enable_cdpl3 = true;
-		return 0;
-	case Opt_cdpl2:
-		ctx->enable_cdpl2 = true;
-		return 0;
-	case Opt_mba_mbps:
-		msg = "mba_MBps requires MBM and linear scale MBA at L3 scope";
-		if (!supports_mba_mbps())
-			return invalfc(fc, msg);
-		ctx->enable_mba_mbps = true;
-		return 0;
-	case Opt_debug:
-		ctx->enable_debug = true;
-		return 0;
-	}
-
-	return -EINVAL;
-}
-
-static void rdt_fs_context_free(struct fs_context *fc)
-{
-	struct rdt_fs_context *ctx = rdt_fc2context(fc);
-
-	kernfs_free_fs_context(fc);
-	kfree(ctx);
-}
-
-static const struct fs_context_operations rdt_fs_context_ops = {
-	.free		= rdt_fs_context_free,
-	.parse_param	= rdt_parse_param,
-	.get_tree	= rdt_get_tree,
-};
-
-static int rdt_init_fs_context(struct fs_context *fc)
-{
-	struct rdt_fs_context *ctx;
-
-	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
-	if (!ctx)
-		return -ENOMEM;
-
-	ctx->kfc.magic = RDTGROUP_SUPER_MAGIC;
-	fc->fs_private = &ctx->kfc;
-	fc->ops = &rdt_fs_context_ops;
-	put_user_ns(fc->user_ns);
-	fc->user_ns = get_user_ns(&init_user_ns);
-	fc->global = true;
-	return 0;
-}
-
-void resctrl_arch_reset_all_ctrls(struct rdt_resource *r)
-{
-	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
-	struct rdt_hw_ctrl_domain *hw_dom;
-	struct msr_param msr_param;
-	struct rdt_ctrl_domain *d;
-	int i;
-
-	/* Walking r->domains, ensure it can't race with cpuhp */
-	lockdep_assert_cpus_held();
-
-	msr_param.res = r;
-	msr_param.low = 0;
-	msr_param.high = hw_res->num_closid;
-
-	/*
-	 * Disable resource control for this resource by setting all
-	 * CBMs in all ctrl_domains to the maximum mask value. Pick one CPU
-	 * from each domain to update the MSRs below.
-	 */
-	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
-		hw_dom = resctrl_to_arch_ctrl_dom(d);
-
-		for (i = 0; i < hw_res->num_closid; i++)
-			hw_dom->ctrl_val[i] = resctrl_get_default_ctrl(r);
-		msr_param.dom = d;
-		smp_call_function_any(&d->hdr.cpu_mask, rdt_ctrl_update, &msr_param, 1);
-	}
-
-	return;
-}
-
-/*
- * Move tasks from one to the other group. If @from is NULL, then all tasks
- * in the systems are moved unconditionally (used for teardown).
- *
- * If @mask is not NULL the cpus on which moved tasks are running are set
- * in that mask so the update smp function call is restricted to affected
- * cpus.
- */
-static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to,
-				 struct cpumask *mask)
-{
-	struct task_struct *p, *t;
-
-	read_lock(&tasklist_lock);
-	for_each_process_thread(p, t) {
-		if (!from || is_closid_match(t, from) ||
-		    is_rmid_match(t, from)) {
-			resctrl_arch_set_closid_rmid(t, to->closid,
-						     to->mon.rmid);
-
-			/*
-			 * Order the closid/rmid stores above before the loads
-			 * in task_curr(). This pairs with the full barrier
-			 * between the rq->curr update and
-			 * resctrl_arch_sched_in() during context switch.
-			 */
-			smp_mb();
-
-			/*
-			 * If the task is on a CPU, set the CPU in the mask.
-			 * The detection is inaccurate as tasks might move or
-			 * schedule before the smp function call takes place.
-			 * In such a case the function call is pointless, but
-			 * there is no other side effect.
-			 */
-			if (IS_ENABLED(CONFIG_SMP) && mask && task_curr(t))
-				cpumask_set_cpu(task_cpu(t), mask);
-		}
-	}
-	read_unlock(&tasklist_lock);
-}
-
-static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp)
-{
-	struct rdtgroup *sentry, *stmp;
-	struct list_head *head;
-
-	head = &rdtgrp->mon.crdtgrp_list;
-	list_for_each_entry_safe(sentry, stmp, head, mon.crdtgrp_list) {
-		free_rmid(sentry->closid, sentry->mon.rmid);
-		list_del(&sentry->mon.crdtgrp_list);
-
-		if (atomic_read(&sentry->waitcount) != 0)
-			sentry->flags = RDT_DELETED;
-		else
-			rdtgroup_remove(sentry);
-	}
-}
-
-/*
- * Forcibly remove all of subdirectories under root.
- */
-static void rmdir_all_sub(void)
-{
-	struct rdtgroup *rdtgrp, *tmp;
-
-	/* Move all tasks to the default resource group */
-	rdt_move_group_tasks(NULL, &rdtgroup_default, NULL);
-
-	list_for_each_entry_safe(rdtgrp, tmp, &rdt_all_groups, rdtgroup_list) {
-		/* Free any child rmids */
-		free_all_child_rdtgrp(rdtgrp);
-
-		/* Remove each rdtgroup other than root */
-		if (rdtgrp == &rdtgroup_default)
-			continue;
-
-		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
-		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
-			rdtgroup_pseudo_lock_remove(rdtgrp);
-
-		/*
-		 * Give any CPUs back to the default group. We cannot copy
-		 * cpu_online_mask because a CPU might have executed the
-		 * offline callback already, but is still marked online.
-		 */
-		cpumask_or(&rdtgroup_default.cpu_mask,
-			   &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);
-
-		free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
-
-		kernfs_remove(rdtgrp->kn);
-		list_del(&rdtgrp->rdtgroup_list);
-
-		if (atomic_read(&rdtgrp->waitcount) != 0)
-			rdtgrp->flags = RDT_DELETED;
-		else
-			rdtgroup_remove(rdtgrp);
-	}
-	/* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */
-	update_closid_rmid(cpu_online_mask, &rdtgroup_default);
-
-	kernfs_remove(kn_info);
-	kernfs_remove(kn_mongrp);
-	kernfs_remove(kn_mondata);
-}
-
-/**
- * mon_get_kn_priv() - Get the mon_data priv data for this event.
- *
- * The same values are used across the mon_data directories of all control and
- * monitor groups for the same event in the same domain. Keep a list of
- * allocated structures and re-use an existing one with the same values for
- * @rid, @domid, etc.
- *
- * @rid:    The resource id for the event file being created.
- * @domid:  The domain id for the event file being created.
- * @mevt:   The type of event file being created.
- * @do_sum: Whether SNC summing monitors are being created.
- */
-static struct mon_data *mon_get_kn_priv(enum resctrl_res_level rid, int domid,
-					struct mon_evt *mevt,
-					bool do_sum)
-{
-	struct mon_data *priv;
-
-	lockdep_assert_held(&rdtgroup_mutex);
-
-	list_for_each_entry(priv, &mon_data_kn_priv_list, list) {
-		if (priv->rid == rid && priv->domid == domid &&
-		    priv->sum == do_sum && priv->evtid == mevt->evtid)
-			return priv;
-	}
-
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (!priv)
-		return NULL;
-
-	priv->rid = rid;
-	priv->domid = domid;
-	priv->sum = do_sum;
-	priv->evtid = mevt->evtid;
-	list_add_tail(&priv->list, &mon_data_kn_priv_list);
-
-	return priv;
-}
-
-/**
- * mon_put_kn_priv() - Free all allocated mon_data structures.
- *
- * Called when resctrl file system is unmounted.
- */
-static void mon_put_kn_priv(void)
-{
-	struct mon_data *priv, *tmp;
-
-	lockdep_assert_held(&rdtgroup_mutex);
-
-	list_for_each_entry_safe(priv, tmp, &mon_data_kn_priv_list, list) {
-		list_del(&priv->list);
-		kfree(priv);
-	}
-}
-
-static void resctrl_fs_teardown(void)
-{
-	lockdep_assert_held(&rdtgroup_mutex);
-
-	/* Cleared by rdtgroup_destroy_root() */
-	if (!rdtgroup_default.kn)
-		return;
-
-	rmdir_all_sub();
-	mon_put_kn_priv();
-	rdt_pseudo_lock_release();
-	rdtgroup_default.mode = RDT_MODE_SHAREABLE;
-	closid_exit();
-	schemata_list_destroy();
-	rdtgroup_destroy_root();
-}
-
-static void rdt_kill_sb(struct super_block *sb)
-{
-	struct rdt_resource *r;
-
-	cpus_read_lock();
-	mutex_lock(&rdtgroup_mutex);
-
-	rdt_disable_ctx();
-
-	/* Put everything back to default values. */
-	for_each_alloc_capable_rdt_resource(r)
-		resctrl_arch_reset_all_ctrls(r);
-
-	resctrl_fs_teardown();
-	if (resctrl_arch_alloc_capable())
-		resctrl_arch_disable_alloc();
-	if (resctrl_arch_mon_capable())
-		resctrl_arch_disable_mon();
-	resctrl_mounted = false;
-	kernfs_kill_sb(sb);
-	mutex_unlock(&rdtgroup_mutex);
-	cpus_read_unlock();
-}
-
-static struct file_system_type rdt_fs_type = {
-	.name			= "resctrl",
-	.init_fs_context	= rdt_init_fs_context,
-	.parameters		= rdt_fs_parameters,
-	.kill_sb		= rdt_kill_sb,
-};
-
-static int mon_addfile(struct kernfs_node *parent_kn, const char *name,
-		       void *priv)
-{
-	struct kernfs_node *kn;
-	int ret = 0;
-
-	kn = __kernfs_create_file(parent_kn, name, 0444,
-				  GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, 0,
-				  &kf_mondata_ops, priv, NULL, NULL);
-	if (IS_ERR(kn))
-		return PTR_ERR(kn);
-
-	ret = rdtgroup_kn_set_ugid(kn);
-	if (ret) {
-		kernfs_remove(kn);
-		return ret;
-	}
-
-	return ret;
-}
-
-static void mon_rmdir_one_subdir(struct kernfs_node *pkn, char *name, char *subname)
-{
-	struct kernfs_node *kn;
-
-	kn = kernfs_find_and_get(pkn, name);
-	if (!kn)
-		return;
-	kernfs_put(kn);
-
-	if (kn->dir.subdirs <= 1)
-		kernfs_remove(kn);
-	else
-		kernfs_remove_by_name(kn, subname);
-}
-
-/*
- * Remove all subdirectories of mon_data of ctrl_mon groups
- * and monitor groups for the given domain.
- * Remove files and directories containing "sum" of domain data
- * when last domain being summed is removed.
- */
-static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
-					   struct rdt_mon_domain *d)
-{
-	struct rdtgroup *prgrp, *crgrp;
-	char subname[32];
-	bool snc_mode;
-	char name[32];
-
-	snc_mode = r->mon_scope == RESCTRL_L3_NODE;
-	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci->id : d->hdr.id);
-	if (snc_mode)
-		sprintf(subname, "mon_sub_%s_%02d", r->name, d->hdr.id);
-
-	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
-		mon_rmdir_one_subdir(prgrp->mon.mon_data_kn, name, subname);
-
-		list_for_each_entry(crgrp, &prgrp->mon.crdtgrp_list, mon.crdtgrp_list)
-			mon_rmdir_one_subdir(crgrp->mon.mon_data_kn, name, subname);
-	}
-}
-
-static int mon_add_all_files(struct kernfs_node *kn, struct rdt_mon_domain *d,
-			     struct rdt_resource *r, struct rdtgroup *prgrp,
-			     bool do_sum)
-{
-	struct rmid_read rr = {0};
-	struct mon_data *priv;
-	struct mon_evt *mevt;
-	int ret, domid;
-
-	if (WARN_ON(list_empty(&r->evt_list)))
-		return -EPERM;
-
-	list_for_each_entry(mevt, &r->evt_list, list) {
-		domid = do_sum ? d->ci->id : d->hdr.id;
-		priv = mon_get_kn_priv(r->rid, domid, mevt, do_sum);
-		if (WARN_ON_ONCE(!priv))
-			return -EINVAL;
-
-		ret = mon_addfile(kn, mevt->name, priv);
-		if (ret)
-			return ret;
-
-		if (!do_sum && resctrl_is_mbm_event(mevt->evtid))
-			mon_event_read(&rr, r, d, prgrp, &d->hdr.cpu_mask, mevt->evtid, true);
-	}
-
-	return 0;
-}
-
-static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
-				struct rdt_mon_domain *d,
-				struct rdt_resource *r, struct rdtgroup *prgrp)
-{
-	struct kernfs_node *kn, *ckn;
-	char name[32];
-	bool snc_mode;
-	int ret = 0;
-
-	lockdep_assert_held(&rdtgroup_mutex);
-
-	snc_mode = r->mon_scope == RESCTRL_L3_NODE;
-	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci->id : d->hdr.id);
-	kn = kernfs_find_and_get(parent_kn, name);
-	if (kn) {
-		/*
-		 * rdtgroup_mutex will prevent this directory from being
-		 * removed. No need to keep this hold.
-		 */
-		kernfs_put(kn);
-	} else {
-		kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp);
-		if (IS_ERR(kn))
-			return PTR_ERR(kn);
-
-		ret = rdtgroup_kn_set_ugid(kn);
-		if (ret)
-			goto out_destroy;
-		ret = mon_add_all_files(kn, d, r, prgrp, snc_mode);
-		if (ret)
-			goto out_destroy;
-	}
-
-	if (snc_mode) {
-		sprintf(name, "mon_sub_%s_%02d", r->name, d->hdr.id);
-		ckn = kernfs_create_dir(kn, name, parent_kn->mode, prgrp);
-		if (IS_ERR(ckn)) {
-			ret = -EINVAL;
-			goto out_destroy;
-		}
-
-		ret = rdtgroup_kn_set_ugid(ckn);
-		if (ret)
-			goto out_destroy;
-
-		ret = mon_add_all_files(ckn, d, r, prgrp, false);
-		if (ret)
-			goto out_destroy;
-	}
-
-	kernfs_activate(kn);
-	return 0;
-
-out_destroy:
-	kernfs_remove(kn);
-	return ret;
-}
-
-/*
- * Add all subdirectories of mon_data for "ctrl_mon" groups
- * and "monitor" groups with given domain id.
- */
-static void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
-					   struct rdt_mon_domain *d)
-{
-	struct kernfs_node *parent_kn;
-	struct rdtgroup *prgrp, *crgrp;
-	struct list_head *head;
-
-	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
-		parent_kn = prgrp->mon.mon_data_kn;
-		mkdir_mondata_subdir(parent_kn, d, r, prgrp);
-
-		head = &prgrp->mon.crdtgrp_list;
-		list_for_each_entry(crgrp, head, mon.crdtgrp_list) {
-			parent_kn = crgrp->mon.mon_data_kn;
-			mkdir_mondata_subdir(parent_kn, d, r, crgrp);
-		}
-	}
-}
-
-static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn,
-				       struct rdt_resource *r,
-				       struct rdtgroup *prgrp)
-{
-	struct rdt_mon_domain *dom;
-	int ret;
-
-	/* Walking r->domains, ensure it can't race with cpuhp */
-	lockdep_assert_cpus_held();
-
-	list_for_each_entry(dom, &r->mon_domains, hdr.list) {
-		ret = mkdir_mondata_subdir(parent_kn, dom, r, prgrp);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
-/*
- * This creates a directory mon_data which contains the monitored data.
- *
- * mon_data has one directory for each domain which are named
- * in the format mon_<domain_name>_<domain_id>. For ex: A mon_data
- * with L3 domain looks as below:
- * ./mon_data:
- * mon_L3_00
- * mon_L3_01
- * mon_L3_02
- * ...
- *
- * Each domain directory has one file per event:
- * ./mon_L3_00/:
- * llc_occupancy
- *
- */
-static int mkdir_mondata_all(struct kernfs_node *parent_kn,
-			     struct rdtgroup *prgrp,
-			     struct kernfs_node **dest_kn)
-{
-	struct rdt_resource *r;
-	struct kernfs_node *kn;
-	int ret;
-
-	/*
-	 * Create the mon_data directory first.
-	 */
-	ret = mongroup_create_dir(parent_kn, prgrp, "mon_data", &kn);
-	if (ret)
-		return ret;
-
-	if (dest_kn)
-		*dest_kn = kn;
-
-	/*
-	 * Create the subdirectories for each domain. Note that all events
-	 * in a domain like L3 are grouped into a resource whose domain is L3
-	 */
-	for_each_mon_capable_rdt_resource(r) {
-		ret = mkdir_mondata_subdir_alldom(kn, r, prgrp);
-		if (ret)
-			goto out_destroy;
-	}
-
-	return 0;
-
-out_destroy:
-	kernfs_remove(kn);
-	return ret;
-}
-
-/**
- * cbm_ensure_valid - Enforce validity on provided CBM
- * @_val:	Candidate CBM
- * @r:		RDT resource to which the CBM belongs
- *
- * The provided CBM represents all cache portions available for use. This
- * may be represented by a bitmap that does not consist of contiguous ones
- * and thus be an invalid CBM.
- * Here the provided CBM is forced to be a valid CBM by only considering
- * the first set of contiguous bits as valid and clearing all bits.
- * The intention here is to provide a valid default CBM with which a new
- * resource group is initialized. The user can follow this with a
- * modification to the CBM if the default does not satisfy the
- * requirements.
- */
-static u32 cbm_ensure_valid(u32 _val, struct rdt_resource *r)
-{
-	unsigned int cbm_len = r->cache.cbm_len;
-	unsigned long first_bit, zero_bit;
-	unsigned long val = _val;
-
-	if (!val)
-		return 0;
-
-	first_bit = find_first_bit(&val, cbm_len);
-	zero_bit = find_next_zero_bit(&val, cbm_len, first_bit);
-
-	/* Clear any remaining bits to ensure contiguous region */
-	bitmap_clear(&val, zero_bit, cbm_len - zero_bit);
-	return (u32)val;
-}
-
-/*
- * Initialize cache resources per RDT domain
- *
- * Set the RDT domain up to start off with all usable allocations. That is,
- * all shareable and unused bits. All-zero CBM is invalid.
- */
-static int __init_one_rdt_domain(struct rdt_ctrl_domain *d, struct resctrl_schema *s,
-				 u32 closid)
-{
-	enum resctrl_conf_type peer_type = resctrl_peer_type(s->conf_type);
-	enum resctrl_conf_type t = s->conf_type;
-	struct resctrl_staged_config *cfg;
-	struct rdt_resource *r = s->res;
-	u32 used_b = 0, unused_b = 0;
-	unsigned long tmp_cbm;
-	enum rdtgrp_mode mode;
-	u32 peer_ctl, ctrl_val;
-	int i;
-
-	cfg = &d->staged_config[t];
-	cfg->have_new_ctrl = false;
-	cfg->new_ctrl = r->cache.shareable_bits;
-	used_b = r->cache.shareable_bits;
-	for (i = 0; i < closids_supported(); i++) {
-		if (closid_allocated(i) && i != closid) {
-			mode = rdtgroup_mode_by_closid(i);
-			if (mode == RDT_MODE_PSEUDO_LOCKSETUP)
-				/*
-				 * ctrl values for locksetup aren't relevant
-				 * until the schemata is written, and the mode
-				 * becomes RDT_MODE_PSEUDO_LOCKED.
-				 */
-				continue;
-			/*
-			 * If CDP is active include peer domain's
-			 * usage to ensure there is no overlap
-			 * with an exclusive group.
-			 */
-			if (resctrl_arch_get_cdp_enabled(r->rid))
-				peer_ctl = resctrl_arch_get_config(r, d, i,
-								   peer_type);
-			else
-				peer_ctl = 0;
-			ctrl_val = resctrl_arch_get_config(r, d, i,
-							   s->conf_type);
-			used_b |= ctrl_val | peer_ctl;
-			if (mode == RDT_MODE_SHAREABLE)
-				cfg->new_ctrl |= ctrl_val | peer_ctl;
-		}
-	}
-	if (d->plr && d->plr->cbm > 0)
-		used_b |= d->plr->cbm;
-	unused_b = used_b ^ (BIT_MASK(r->cache.cbm_len) - 1);
-	unused_b &= BIT_MASK(r->cache.cbm_len) - 1;
-	cfg->new_ctrl |= unused_b;
-	/*
-	 * Force the initial CBM to be valid, user can
-	 * modify the CBM based on system availability.
-	 */
-	cfg->new_ctrl = cbm_ensure_valid(cfg->new_ctrl, r);
-	/*
-	 * Assign the u32 CBM to an unsigned long to ensure that
-	 * bitmap_weight() does not access out-of-bound memory.
-	 */
-	tmp_cbm = cfg->new_ctrl;
-	if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) < r->cache.min_cbm_bits) {
-		rdt_last_cmd_printf("No space on %s:%d\n", s->name, d->hdr.id);
-		return -ENOSPC;
-	}
-	cfg->have_new_ctrl = true;
-
-	return 0;
-}
-
-/*
- * Initialize cache resources with default values.
- *
- * A new RDT group is being created on an allocation capable (CAT)
- * supporting system. Set this group up to start off with all usable
- * allocations.
- *
- * If there are no more shareable bits available on any domain then
- * the entire allocation will fail.
- */
-static int rdtgroup_init_cat(struct resctrl_schema *s, u32 closid)
-{
-	struct rdt_ctrl_domain *d;
-	int ret;
-
-	list_for_each_entry(d, &s->res->ctrl_domains, hdr.list) {
-		ret = __init_one_rdt_domain(d, s, closid);
-		if (ret < 0)
-			return ret;
-	}
-
-	return 0;
-}
-
-/* Initialize MBA resource with default values. */
-static void rdtgroup_init_mba(struct rdt_resource *r, u32 closid)
-{
-	struct resctrl_staged_config *cfg;
-	struct rdt_ctrl_domain *d;
-
-	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
-		if (is_mba_sc(r)) {
-			d->mbps_val[closid] = MBA_MAX_MBPS;
-			continue;
-		}
-
-		cfg = &d->staged_config[CDP_NONE];
-		cfg->new_ctrl = resctrl_get_default_ctrl(r);
-		cfg->have_new_ctrl = true;
-	}
-}
-
-/* Initialize the RDT group's allocations. */
-static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
-{
-	struct resctrl_schema *s;
-	struct rdt_resource *r;
-	int ret = 0;
-
-	rdt_staged_configs_clear();
-
-	list_for_each_entry(s, &resctrl_schema_all, list) {
-		r = s->res;
-		if (r->rid == RDT_RESOURCE_MBA ||
-		    r->rid == RDT_RESOURCE_SMBA) {
-			rdtgroup_init_mba(r, rdtgrp->closid);
-			if (is_mba_sc(r))
-				continue;
-		} else {
-			ret = rdtgroup_init_cat(s, rdtgrp->closid);
-			if (ret < 0)
-				goto out;
-		}
-
-		ret = resctrl_arch_update_domains(r, rdtgrp->closid);
-		if (ret < 0) {
-			rdt_last_cmd_puts("Failed to initialize allocations\n");
-			goto out;
-		}
-	}
-
-	rdtgrp->mode = RDT_MODE_SHAREABLE;
-
-out:
-	rdt_staged_configs_clear();
-	return ret;
-}
-
-static int mkdir_rdt_prepare_rmid_alloc(struct rdtgroup *rdtgrp)
-{
-	int ret;
-
-	if (!resctrl_arch_mon_capable())
-		return 0;
-
-	ret = alloc_rmid(rdtgrp->closid);
-	if (ret < 0) {
-		rdt_last_cmd_puts("Out of RMIDs\n");
-		return ret;
-	}
-	rdtgrp->mon.rmid = ret;
-
-	ret = mkdir_mondata_all(rdtgrp->kn, rdtgrp, &rdtgrp->mon.mon_data_kn);
-	if (ret) {
-		rdt_last_cmd_puts("kernfs subdir error\n");
-		free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
-		return ret;
-	}
-
-	return 0;
-}
-
-static void mkdir_rdt_prepare_rmid_free(struct rdtgroup *rgrp)
-{
-	if (resctrl_arch_mon_capable())
-		free_rmid(rgrp->closid, rgrp->mon.rmid);
-}
-
-/*
- * We allow creating mon groups only with in a directory called "mon_groups"
- * which is present in every ctrl_mon group. Check if this is a valid
- * "mon_groups" directory.
- *
- * 1. The directory should be named "mon_groups".
- * 2. The mon group itself should "not" be named "mon_groups".
- *   This makes sure "mon_groups" directory always has a ctrl_mon group
- *   as parent.
- */
-static bool is_mon_groups(struct kernfs_node *kn, const char *name)
-{
-	return (!strcmp(rdt_kn_name(kn), "mon_groups") &&
-		strcmp(name, "mon_groups"));
-}
-
-static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
-			     const char *name, umode_t mode,
-			     enum rdt_group_type rtype, struct rdtgroup **r)
-{
-	struct rdtgroup *prdtgrp, *rdtgrp;
-	unsigned long files = 0;
-	struct kernfs_node *kn;
-	int ret;
-
-	prdtgrp = rdtgroup_kn_lock_live(parent_kn);
-	if (!prdtgrp) {
-		ret = -ENODEV;
-		goto out_unlock;
-	}
-
-	/*
-	 * Check that the parent directory for a monitor group is a "mon_groups"
-	 * directory.
-	 */
-	if (rtype == RDTMON_GROUP && !is_mon_groups(parent_kn, name)) {
-		ret = -EPERM;
-		goto out_unlock;
-	}
-
-	if (rtype == RDTMON_GROUP &&
-	    (prdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
-	     prdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)) {
-		ret = -EINVAL;
-		rdt_last_cmd_puts("Pseudo-locking in progress\n");
-		goto out_unlock;
-	}
-
-	/* allocate the rdtgroup. */
-	rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL);
-	if (!rdtgrp) {
-		ret = -ENOSPC;
-		rdt_last_cmd_puts("Kernel out of memory\n");
-		goto out_unlock;
-	}
-	*r = rdtgrp;
-	rdtgrp->mon.parent = prdtgrp;
-	rdtgrp->type = rtype;
-	INIT_LIST_HEAD(&rdtgrp->mon.crdtgrp_list);
-
-	/* kernfs creates the directory for rdtgrp */
-	kn = kernfs_create_dir(parent_kn, name, mode, rdtgrp);
-	if (IS_ERR(kn)) {
-		ret = PTR_ERR(kn);
-		rdt_last_cmd_puts("kernfs create error\n");
-		goto out_free_rgrp;
-	}
-	rdtgrp->kn = kn;
-
-	/*
-	 * kernfs_remove() will drop the reference count on "kn" which
-	 * will free it. But we still need it to stick around for the
-	 * rdtgroup_kn_unlock(kn) call. Take one extra reference here,
-	 * which will be dropped by kernfs_put() in rdtgroup_remove().
-	 */
-	kernfs_get(kn);
-
-	ret = rdtgroup_kn_set_ugid(kn);
-	if (ret) {
-		rdt_last_cmd_puts("kernfs perm error\n");
-		goto out_destroy;
-	}
-
-	if (rtype == RDTCTRL_GROUP) {
-		files = RFTYPE_BASE | RFTYPE_CTRL;
-		if (resctrl_arch_mon_capable())
-			files |= RFTYPE_MON;
-	} else {
-		files = RFTYPE_BASE | RFTYPE_MON;
-	}
-
-	ret = rdtgroup_add_files(kn, files);
-	if (ret) {
-		rdt_last_cmd_puts("kernfs fill error\n");
-		goto out_destroy;
-	}
-
-	/*
-	 * The caller unlocks the parent_kn upon success.
-	 */
-	return 0;
-
-out_destroy:
-	kernfs_put(rdtgrp->kn);
-	kernfs_remove(rdtgrp->kn);
-out_free_rgrp:
-	kfree(rdtgrp);
-out_unlock:
-	rdtgroup_kn_unlock(parent_kn);
-	return ret;
-}
-
-static void mkdir_rdt_prepare_clean(struct rdtgroup *rgrp)
-{
-	kernfs_remove(rgrp->kn);
-	rdtgroup_remove(rgrp);
-}
-
-/*
- * Create a monitor group under "mon_groups" directory of a control
- * and monitor group(ctrl_mon). This is a resource group
- * to monitor a subset of tasks and cpus in its parent ctrl_mon group.
- */
-static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn,
-			      const char *name, umode_t mode)
-{
-	struct rdtgroup *rdtgrp, *prgrp;
-	int ret;
-
-	ret = mkdir_rdt_prepare(parent_kn, name, mode, RDTMON_GROUP, &rdtgrp);
-	if (ret)
-		return ret;
-
-	prgrp = rdtgrp->mon.parent;
-	rdtgrp->closid = prgrp->closid;
-
-	ret = mkdir_rdt_prepare_rmid_alloc(rdtgrp);
-	if (ret) {
-		mkdir_rdt_prepare_clean(rdtgrp);
-		goto out_unlock;
-	}
-
-	kernfs_activate(rdtgrp->kn);
-
-	/*
-	 * Add the rdtgrp to the list of rdtgrps the parent
-	 * ctrl_mon group has to track.
-	 */
-	list_add_tail(&rdtgrp->mon.crdtgrp_list, &prgrp->mon.crdtgrp_list);
-
-out_unlock:
-	rdtgroup_kn_unlock(parent_kn);
-	return ret;
-}
-
-/*
- * These are rdtgroups created under the root directory. Can be used
- * to allocate and monitor resources.
- */
-static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
-				   const char *name, umode_t mode)
-{
-	struct rdtgroup *rdtgrp;
-	struct kernfs_node *kn;
-	u32 closid;
-	int ret;
-
-	ret = mkdir_rdt_prepare(parent_kn, name, mode, RDTCTRL_GROUP, &rdtgrp);
-	if (ret)
-		return ret;
-
-	kn = rdtgrp->kn;
-	ret = closid_alloc();
-	if (ret < 0) {
-		rdt_last_cmd_puts("Out of CLOSIDs\n");
-		goto out_common_fail;
-	}
-	closid = ret;
-	ret = 0;
-
-	rdtgrp->closid = closid;
-
-	ret = mkdir_rdt_prepare_rmid_alloc(rdtgrp);
-	if (ret)
-		goto out_closid_free;
-
-	kernfs_activate(rdtgrp->kn);
-
-	ret = rdtgroup_init_alloc(rdtgrp);
-	if (ret < 0)
-		goto out_rmid_free;
-
-	list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups);
-
-	if (resctrl_arch_mon_capable()) {
-		/*
-		 * Create an empty mon_groups directory to hold the subset
-		 * of tasks and cpus to monitor.
-		 */
-		ret = mongroup_create_dir(kn, rdtgrp, "mon_groups", NULL);
-		if (ret) {
-			rdt_last_cmd_puts("kernfs subdir error\n");
-			goto out_del_list;
-		}
-		if (is_mba_sc(NULL))
-			rdtgrp->mba_mbps_event = mba_mbps_default_event;
-	}
-
-	goto out_unlock;
-
-out_del_list:
-	list_del(&rdtgrp->rdtgroup_list);
-out_rmid_free:
-	mkdir_rdt_prepare_rmid_free(rdtgrp);
-out_closid_free:
-	closid_free(closid);
-out_common_fail:
-	mkdir_rdt_prepare_clean(rdtgrp);
-out_unlock:
-	rdtgroup_kn_unlock(parent_kn);
-	return ret;
-}
-
-static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
-			  umode_t mode)
-{
-	/* Do not accept '\n' to avoid unparsable situation. */
-	if (strchr(name, '\n'))
-		return -EINVAL;
-
-	/*
-	 * If the parent directory is the root directory and RDT
-	 * allocation is supported, add a control and monitoring
-	 * subdirectory
-	 */
-	if (resctrl_arch_alloc_capable() && parent_kn == rdtgroup_default.kn)
-		return rdtgroup_mkdir_ctrl_mon(parent_kn, name, mode);
-
-	/* Else, attempt to add a monitoring subdirectory. */
-	if (resctrl_arch_mon_capable())
-		return rdtgroup_mkdir_mon(parent_kn, name, mode);
-
-	return -EPERM;
-}
-
-static int rdtgroup_rmdir_mon(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask)
-{
-	struct rdtgroup *prdtgrp = rdtgrp->mon.parent;
-	u32 closid, rmid;
-	int cpu;
-
-	/* Give any tasks back to the parent group */
-	rdt_move_group_tasks(rdtgrp, prdtgrp, tmpmask);
-
-	/*
-	 * Update per cpu closid/rmid of the moved CPUs first.
-	 * Note: the closid will not change, but the arch code still needs it.
-	 */
-	closid = prdtgrp->closid;
-	rmid = prdtgrp->mon.rmid;
-	for_each_cpu(cpu, &rdtgrp->cpu_mask)
-		resctrl_arch_set_cpu_default_closid_rmid(cpu, closid, rmid);
-
-	/*
-	 * Update the MSR on moved CPUs and CPUs which have moved
-	 * task running on them.
-	 */
-	cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask);
-	update_closid_rmid(tmpmask, NULL);
-
-	rdtgrp->flags = RDT_DELETED;
-	free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
-
-	/*
-	 * Remove the rdtgrp from the parent ctrl_mon group's list
-	 */
-	WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list));
-	list_del(&rdtgrp->mon.crdtgrp_list);
-
-	kernfs_remove(rdtgrp->kn);
-
-	return 0;
-}
-
-static int rdtgroup_ctrl_remove(struct rdtgroup *rdtgrp)
-{
-	rdtgrp->flags = RDT_DELETED;
-	list_del(&rdtgrp->rdtgroup_list);
-
-	kernfs_remove(rdtgrp->kn);
-	return 0;
-}
-
-static int rdtgroup_rmdir_ctrl(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask)
-{
-	u32 closid, rmid;
-	int cpu;
-
-	/* Give any tasks back to the default group */
-	rdt_move_group_tasks(rdtgrp, &rdtgroup_default, tmpmask);
-
-	/* Give any CPUs back to the default group */
-	cpumask_or(&rdtgroup_default.cpu_mask,
-		   &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);
-
-	/* Update per cpu closid and rmid of the moved CPUs first */
-	closid = rdtgroup_default.closid;
-	rmid = rdtgroup_default.mon.rmid;
-	for_each_cpu(cpu, &rdtgrp->cpu_mask)
-		resctrl_arch_set_cpu_default_closid_rmid(cpu, closid, rmid);
-
-	/*
-	 * Update the MSR on moved CPUs and CPUs which have moved
-	 * task running on them.
-	 */
-	cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask);
-	update_closid_rmid(tmpmask, NULL);
-
-	free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
-	closid_free(rdtgrp->closid);
-
-	rdtgroup_ctrl_remove(rdtgrp);
-
-	/*
-	 * Free all the child monitor group rmids.
-	 */
-	free_all_child_rdtgrp(rdtgrp);
-
-	return 0;
-}
-
-static struct kernfs_node *rdt_kn_parent(struct kernfs_node *kn)
-{
-	/*
-	 * Valid within the RCU section it was obtained or while rdtgroup_mutex
-	 * is held.
-	 */
-	return rcu_dereference_check(kn->__parent, lockdep_is_held(&rdtgroup_mutex));
-}
-
-static int rdtgroup_rmdir(struct kernfs_node *kn)
-{
-	struct kernfs_node *parent_kn;
-	struct rdtgroup *rdtgrp;
-	cpumask_var_t tmpmask;
-	int ret = 0;
-
-	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
-		return -ENOMEM;
-
-	rdtgrp = rdtgroup_kn_lock_live(kn);
-	if (!rdtgrp) {
-		ret = -EPERM;
-		goto out;
-	}
-	parent_kn = rdt_kn_parent(kn);
-
-	/*
-	 * If the rdtgroup is a ctrl_mon group and parent directory
-	 * is the root directory, remove the ctrl_mon group.
-	 *
-	 * If the rdtgroup is a mon group and parent directory
-	 * is a valid "mon_groups" directory, remove the mon group.
-	 */
-	if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn &&
-	    rdtgrp != &rdtgroup_default) {
-		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
-		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
-			ret = rdtgroup_ctrl_remove(rdtgrp);
-		} else {
-			ret = rdtgroup_rmdir_ctrl(rdtgrp, tmpmask);
-		}
-	} else if (rdtgrp->type == RDTMON_GROUP &&
-		 is_mon_groups(parent_kn, rdt_kn_name(kn))) {
-		ret = rdtgroup_rmdir_mon(rdtgrp, tmpmask);
-	} else {
-		ret = -EPERM;
-	}
-
-out:
-	rdtgroup_kn_unlock(kn);
-	free_cpumask_var(tmpmask);
-	return ret;
-}
-
-/**
- * mongrp_reparent() - replace parent CTRL_MON group of a MON group
- * @rdtgrp:		the MON group whose parent should be replaced
- * @new_prdtgrp:	replacement parent CTRL_MON group for @rdtgrp
- * @cpus:		cpumask provided by the caller for use during this call
- *
- * Replaces the parent CTRL_MON group for a MON group, resulting in all member
- * tasks' CLOSID immediately changing to that of the new parent group.
- * Monitoring data for the group is unaffected by this operation.
- */
-static void mongrp_reparent(struct rdtgroup *rdtgrp,
-			    struct rdtgroup *new_prdtgrp,
-			    cpumask_var_t cpus)
-{
-	struct rdtgroup *prdtgrp = rdtgrp->mon.parent;
-
-	WARN_ON(rdtgrp->type != RDTMON_GROUP);
-	WARN_ON(new_prdtgrp->type != RDTCTRL_GROUP);
-
-	/* Nothing to do when simply renaming a MON group. */
-	if (prdtgrp == new_prdtgrp)
-		return;
-
-	WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list));
-	list_move_tail(&rdtgrp->mon.crdtgrp_list,
-		       &new_prdtgrp->mon.crdtgrp_list);
-
-	rdtgrp->mon.parent = new_prdtgrp;
-	rdtgrp->closid = new_prdtgrp->closid;
-
-	/* Propagate updated closid to all tasks in this group. */
-	rdt_move_group_tasks(rdtgrp, rdtgrp, cpus);
-
-	update_closid_rmid(cpus, NULL);
-}
-
-static int rdtgroup_rename(struct kernfs_node *kn,
-			   struct kernfs_node *new_parent, const char *new_name)
-{
-	struct kernfs_node *kn_parent;
-	struct rdtgroup *new_prdtgrp;
-	struct rdtgroup *rdtgrp;
-	cpumask_var_t tmpmask;
-	int ret;
-
-	rdtgrp = kernfs_to_rdtgroup(kn);
-	new_prdtgrp = kernfs_to_rdtgroup(new_parent);
-	if (!rdtgrp || !new_prdtgrp)
-		return -ENOENT;
-
-	/* Release both kernfs active_refs before obtaining rdtgroup mutex. */
-	rdtgroup_kn_get(rdtgrp, kn);
-	rdtgroup_kn_get(new_prdtgrp, new_parent);
-
-	mutex_lock(&rdtgroup_mutex);
-
-	rdt_last_cmd_clear();
-
-	/*
-	 * Don't allow kernfs_to_rdtgroup() to return a parent rdtgroup if
-	 * either kernfs_node is a file.
-	 */
-	if (kernfs_type(kn) != KERNFS_DIR ||
-	    kernfs_type(new_parent) != KERNFS_DIR) {
-		rdt_last_cmd_puts("Source and destination must be directories");
-		ret = -EPERM;
-		goto out;
-	}
-
-	if ((rdtgrp->flags & RDT_DELETED) || (new_prdtgrp->flags & RDT_DELETED)) {
-		ret = -ENOENT;
-		goto out;
-	}
-
-	kn_parent = rdt_kn_parent(kn);
-	if (rdtgrp->type != RDTMON_GROUP || !kn_parent ||
-	    !is_mon_groups(kn_parent, rdt_kn_name(kn))) {
-		rdt_last_cmd_puts("Source must be a MON group\n");
-		ret = -EPERM;
-		goto out;
-	}
-
-	if (!is_mon_groups(new_parent, new_name)) {
-		rdt_last_cmd_puts("Destination must be a mon_groups subdirectory\n");
-		ret = -EPERM;
-		goto out;
-	}
-
-	/*
-	 * If the MON group is monitoring CPUs, the CPUs must be assigned to the
-	 * current parent CTRL_MON group and therefore cannot be assigned to
-	 * the new parent, making the move illegal.
-	 */
-	if (!cpumask_empty(&rdtgrp->cpu_mask) &&
-	    rdtgrp->mon.parent != new_prdtgrp) {
-		rdt_last_cmd_puts("Cannot move a MON group that monitors CPUs\n");
-		ret = -EPERM;
-		goto out;
-	}
-
-	/*
-	 * Allocate the cpumask for use in mongrp_reparent() to avoid the
-	 * possibility of failing to allocate it after kernfs_rename() has
-	 * succeeded.
-	 */
-	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	/*
-	 * Perform all input validation and allocations needed to ensure
-	 * mongrp_reparent() will succeed before calling kernfs_rename(),
-	 * otherwise it would be necessary to revert this call if
-	 * mongrp_reparent() failed.
-	 */
-	ret = kernfs_rename(kn, new_parent, new_name);
-	if (!ret)
-		mongrp_reparent(rdtgrp, new_prdtgrp, tmpmask);
-
-	free_cpumask_var(tmpmask);
-
-out:
-	mutex_unlock(&rdtgroup_mutex);
-	rdtgroup_kn_put(rdtgrp, kn);
-	rdtgroup_kn_put(new_prdtgrp, new_parent);
-	return ret;
-}
-
-static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf)
-{
-	if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3))
-		seq_puts(seq, ",cdp");
-
-	if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2))
-		seq_puts(seq, ",cdpl2");
-
-	if (is_mba_sc(resctrl_arch_get_resource(RDT_RESOURCE_MBA)))
-		seq_puts(seq, ",mba_MBps");
-
-	if (resctrl_debug)
-		seq_puts(seq, ",debug");
-
-	return 0;
-}
-
-static struct kernfs_syscall_ops rdtgroup_kf_syscall_ops = {
-	.mkdir		= rdtgroup_mkdir,
-	.rmdir		= rdtgroup_rmdir,
-	.rename		= rdtgroup_rename,
-	.show_options	= rdtgroup_show_options,
-};
-
-static int rdtgroup_setup_root(struct rdt_fs_context *ctx)
-{
-	rdt_root = kernfs_create_root(&rdtgroup_kf_syscall_ops,
-				      KERNFS_ROOT_CREATE_DEACTIVATED |
-				      KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK,
-				      &rdtgroup_default);
-	if (IS_ERR(rdt_root))
-		return PTR_ERR(rdt_root);
-
-	ctx->kfc.root = rdt_root;
-	rdtgroup_default.kn = kernfs_root_to_node(rdt_root);
-
-	return 0;
-}
-
-static void rdtgroup_destroy_root(void)
-{
-	lockdep_assert_held(&rdtgroup_mutex);
-
-	kernfs_destroy_root(rdt_root);
-	rdtgroup_default.kn = NULL;
-}
-
-static void rdtgroup_setup_default(void)
-{
-	mutex_lock(&rdtgroup_mutex);
-
-	rdtgroup_default.closid = RESCTRL_RESERVED_CLOSID;
-	rdtgroup_default.mon.rmid = RESCTRL_RESERVED_RMID;
-	rdtgroup_default.type = RDTCTRL_GROUP;
-	INIT_LIST_HEAD(&rdtgroup_default.mon.crdtgrp_list);
-
-	list_add(&rdtgroup_default.rdtgroup_list, &rdt_all_groups);
-
-	mutex_unlock(&rdtgroup_mutex);
-}
-
-static void domain_destroy_mon_state(struct rdt_mon_domain *d)
-{
-	bitmap_free(d->rmid_busy_llc);
-	kfree(d->mbm_total);
-	kfree(d->mbm_local);
-}
-
-void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d)
-{
-	mutex_lock(&rdtgroup_mutex);
-
-	if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA)
-		mba_sc_domain_destroy(r, d);
-
-	mutex_unlock(&rdtgroup_mutex);
-}
-
-void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d)
-{
-	mutex_lock(&rdtgroup_mutex);
-
-	/*
-	 * If resctrl is mounted, remove all the
-	 * per domain monitor data directories.
-	 */
-	if (resctrl_mounted && resctrl_arch_mon_capable())
-		rmdir_mondata_subdir_allrdtgrp(r, d);
-
-	if (resctrl_is_mbm_enabled())
-		cancel_delayed_work(&d->mbm_over);
-	if (resctrl_arch_is_llc_occupancy_enabled() && has_busy_rmid(d)) {
-		/*
-		 * When a package is going down, forcefully
-		 * decrement rmid->ebusy. There is no way to know
-		 * that the L3 was flushed and hence may lead to
-		 * incorrect counts in rare scenarios, but leaving
-		 * the RMID as busy creates RMID leaks if the
-		 * package never comes back.
-		 */
-		__check_limbo(d, true);
-		cancel_delayed_work(&d->cqm_limbo);
-	}
-
-	domain_destroy_mon_state(d);
-
-	mutex_unlock(&rdtgroup_mutex);
-}
-
-/**
- * domain_setup_mon_state() -  Initialise domain monitoring structures.
- * @r:	The resource for the newly online domain.
- * @d:	The newly online domain.
- *
- * Allocate monitor resources that belong to this domain.
- * Called when the first CPU of a domain comes online, regardless of whether
- * the filesystem is mounted.
- * During boot this may be called before global allocations have been made by
- * resctrl_mon_resource_init().
- *
- * Returns 0 for success, or -ENOMEM.
- */
-static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_mon_domain *d)
-{
-	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
-	size_t tsize;
-
-	if (resctrl_arch_is_llc_occupancy_enabled()) {
-		d->rmid_busy_llc = bitmap_zalloc(idx_limit, GFP_KERNEL);
-		if (!d->rmid_busy_llc)
-			return -ENOMEM;
-	}
-	if (resctrl_arch_is_mbm_total_enabled()) {
-		tsize = sizeof(*d->mbm_total);
-		d->mbm_total = kcalloc(idx_limit, tsize, GFP_KERNEL);
-		if (!d->mbm_total) {
-			bitmap_free(d->rmid_busy_llc);
-			return -ENOMEM;
-		}
-	}
-	if (resctrl_arch_is_mbm_local_enabled()) {
-		tsize = sizeof(*d->mbm_local);
-		d->mbm_local = kcalloc(idx_limit, tsize, GFP_KERNEL);
-		if (!d->mbm_local) {
-			bitmap_free(d->rmid_busy_llc);
-			kfree(d->mbm_total);
-			return -ENOMEM;
-		}
-	}
-
-	return 0;
-}
-
-int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d)
-{
-	int err = 0;
-
-	mutex_lock(&rdtgroup_mutex);
-
-	if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA) {
-		/* RDT_RESOURCE_MBA is never mon_capable */
-		err = mba_sc_domain_allocate(r, d);
-	}
-
-	mutex_unlock(&rdtgroup_mutex);
-
-	return err;
-}
-
-int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d)
-{
-	int err;
-
-	mutex_lock(&rdtgroup_mutex);
-
-	err = domain_setup_mon_state(r, d);
-	if (err)
-		goto out_unlock;
-
-	if (resctrl_is_mbm_enabled()) {
-		INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow);
-		mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL,
-					   RESCTRL_PICK_ANY_CPU);
-	}
-
-	if (resctrl_arch_is_llc_occupancy_enabled())
-		INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo);
-
-	/*
-	 * If the filesystem is not mounted then only the default resource group
-	 * exists. Creation of its directories is deferred until mount time
-	 * by rdt_get_tree() calling mkdir_mondata_all().
-	 * If resctrl is mounted, add per domain monitor data directories.
-	 */
-	if (resctrl_mounted && resctrl_arch_mon_capable())
-		mkdir_mondata_subdir_allrdtgrp(r, d);
-
-out_unlock:
-	mutex_unlock(&rdtgroup_mutex);
-
-	return err;
-}
-
-void resctrl_online_cpu(unsigned int cpu)
-{
-	mutex_lock(&rdtgroup_mutex);
-	/* The CPU is set in default rdtgroup after online. */
-	cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask);
-	mutex_unlock(&rdtgroup_mutex);
-}
-
-static void clear_childcpus(struct rdtgroup *r, unsigned int cpu)
-{
-	struct rdtgroup *cr;
-
-	list_for_each_entry(cr, &r->mon.crdtgrp_list, mon.crdtgrp_list) {
-		if (cpumask_test_and_clear_cpu(cpu, &cr->cpu_mask))
-			break;
-	}
-}
-
-static struct rdt_mon_domain *get_mon_domain_from_cpu(int cpu,
-						      struct rdt_resource *r)
-{
-	struct rdt_mon_domain *d;
-
-	lockdep_assert_cpus_held();
-
-	list_for_each_entry(d, &r->mon_domains, hdr.list) {
-		/* Find the domain that contains this CPU */
-		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask))
-			return d;
-	}
-
-	return NULL;
-}
-
-void resctrl_offline_cpu(unsigned int cpu)
-{
-	struct rdt_resource *l3 = resctrl_arch_get_resource(RDT_RESOURCE_L3);
-	struct rdt_mon_domain *d;
-	struct rdtgroup *rdtgrp;
-
-	mutex_lock(&rdtgroup_mutex);
-	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
-		if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask)) {
-			clear_childcpus(rdtgrp, cpu);
-			break;
-		}
-	}
-
-	if (!l3->mon_capable)
-		goto out_unlock;
-
-	d = get_mon_domain_from_cpu(cpu, l3);
-	if (d) {
-		if (resctrl_is_mbm_enabled() && cpu == d->mbm_work_cpu) {
-			cancel_delayed_work(&d->mbm_over);
-			mbm_setup_overflow_handler(d, 0, cpu);
-		}
-		if (resctrl_arch_is_llc_occupancy_enabled() &&
-		    cpu == d->cqm_work_cpu && has_busy_rmid(d)) {
-			cancel_delayed_work(&d->cqm_limbo);
-			cqm_setup_limbo_handler(d, 0, cpu);
-		}
-	}
-
-out_unlock:
-	mutex_unlock(&rdtgroup_mutex);
-}
-
-/*
- * resctrl_init - resctrl filesystem initialization
- *
- * Setup resctrl file system including set up root, create mount point,
- * register resctrl filesystem, and initialize files under root directory.
- *
- * Return: 0 on success or -errno
- */
-int resctrl_init(void)
-{
-	int ret = 0;
-
-	seq_buf_init(&last_cmd_status, last_cmd_status_buf,
-		     sizeof(last_cmd_status_buf));
-
-	rdtgroup_setup_default();
-
-	thread_throttle_mode_init();
-
-	ret = resctrl_mon_resource_init();
-	if (ret)
-		return ret;
-
-	ret = sysfs_create_mount_point(fs_kobj, "resctrl");
-	if (ret) {
-		resctrl_mon_resource_exit();
-		return ret;
-	}
-
-	ret = register_filesystem(&rdt_fs_type);
-	if (ret)
-		goto cleanup_mountpoint;
-
-	/*
-	 * Adding the resctrl debugfs directory here may not be ideal since
-	 * it would let the resctrl debugfs directory appear on the debugfs
-	 * filesystem before the resctrl filesystem is mounted.
-	 * It may also be ok since that would enable debugging of RDT before
-	 * resctrl is mounted.
-	 * The reason why the debugfs directory is created here and not in
-	 * rdt_get_tree() is because rdt_get_tree() takes rdtgroup_mutex and
-	 * during the debugfs directory creation also &sb->s_type->i_mutex_key
-	 * (the lockdep class of inode->i_rwsem). Other filesystem
-	 * interactions (eg. SyS_getdents) have the lock ordering:
-	 * &sb->s_type->i_mutex_key --> &mm->mmap_lock
-	 * During mmap(), called with &mm->mmap_lock, the rdtgroup_mutex
-	 * is taken, thus creating dependency:
-	 * &mm->mmap_lock --> rdtgroup_mutex for the latter that can cause
-	 * issues considering the other two lock dependencies.
-	 * By creating the debugfs directory here we avoid a dependency
-	 * that may cause deadlock (even though file operations cannot
-	 * occur until the filesystem is mounted, but I do not know how to
-	 * tell lockdep that).
-	 */
-	debugfs_resctrl = debugfs_create_dir("resctrl", NULL);
-
-	return 0;
-
-cleanup_mountpoint:
-	sysfs_remove_mount_point(fs_kobj, "resctrl");
-	resctrl_mon_resource_exit();
-
-	return ret;
-}
-
-static bool resctrl_online_domains_exist(void)
-{
-	struct rdt_resource *r;
-
-	/*
-	 * Only walk capable resources to allow resctrl_arch_get_resource()
-	 * to return dummy 'not capable' resources.
-	 */
-	for_each_alloc_capable_rdt_resource(r) {
-		if (!list_empty(&r->ctrl_domains))
-			return true;
-	}
-
-	for_each_mon_capable_rdt_resource(r) {
-		if (!list_empty(&r->mon_domains))
-			return true;
-	}
-
-	return false;
-}
-
-/**
- * resctrl_exit() - Remove the resctrl filesystem and free resources.
- *
- * Called by the architecture code in response to a fatal error.
- * Removes resctrl files and structures from kernfs to prevent further
- * configuration.
- *
- * When called by the architecture code, all CPUs and resctrl domains must be
- * offline. This ensures the limbo and overflow handlers are not scheduled to
- * run, meaning the data structures they access can be freed by
- * resctrl_mon_resource_exit().
- *
- * After resctrl_exit() returns, the architecture code should return an
- * error from all resctrl_arch_ functions that can do this.
- * resctrl_arch_get_resource() must continue to return struct rdt_resources
- * with the correct rid field to ensure the filesystem can be unmounted.
- */
-void resctrl_exit(void)
-{
-	cpus_read_lock();
-	WARN_ON_ONCE(resctrl_online_domains_exist());
-
-	mutex_lock(&rdtgroup_mutex);
-	resctrl_fs_teardown();
-	mutex_unlock(&rdtgroup_mutex);
-
-	cpus_read_unlock();
-
-	debugfs_remove_recursive(debugfs_resctrl);
-	debugfs_resctrl = NULL;
-	unregister_filesystem(&rdt_fs_type);
-
-	/*
-	 * Do not remove the sysfs mount point added by resctrl_init() so that
-	 * it can be used to umount resctrl.
-	 */
-
-	resctrl_mon_resource_exit();
+	return;
 }
diff --git a/fs/resctrl/Kconfig b/fs/resctrl/Kconfig
index 478a8e2ad99ff..21671301bd8a4 100644
--- a/fs/resctrl/Kconfig
+++ b/fs/resctrl/Kconfig
@@ -21,7 +21,7 @@ config RESCTRL_FS
 	  On architectures where this can be disabled independently, it is
 	  safe to say N.
 
-	  See <file:Documentation/arch/x86/resctrl.rst> for more information.
+	  See <file:Documentation/filesystems/resctrl.rst> for more information.
 
 config RESCTRL_FS_PSEUDO_LOCK
 	bool
diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c
index e69de29bb2d1d..6ed2dfd4dbbd9 100644
--- a/fs/resctrl/ctrlmondata.c
+++ b/fs/resctrl/ctrlmondata.c
@@ -0,0 +1,661 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Resource Director Technology(RDT)
+ * - Cache Allocation code.
+ *
+ * Copyright (C) 2016 Intel Corporation
+ *
+ * Authors:
+ *    Fenghua Yu <fenghua.yu@intel.com>
+ *    Tony Luck <tony.luck@intel.com>
+ *
+ * More information about RDT be found in the Intel (R) x86 Architecture
+ * Software Developer Manual June 2016, volume 3, section 17.17.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/cpu.h>
+#include <linux/kernfs.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/tick.h>
+
+#include "internal.h"
+
+struct rdt_parse_data {
+	struct rdtgroup		*rdtgrp;
+	char			*buf;
+};
+
+typedef int (ctrlval_parser_t)(struct rdt_parse_data *data,
+			       struct resctrl_schema *s,
+			       struct rdt_ctrl_domain *d);
+
+/*
+ * Check whether MBA bandwidth percentage value is correct. The value is
+ * checked against the minimum and max bandwidth values specified by the
+ * hardware. The allocated bandwidth percentage is rounded to the next
+ * control step available on the hardware.
+ */
+static bool bw_validate(char *buf, u32 *data, struct rdt_resource *r)
+{
+	int ret;
+	u32 bw;
+
+	/*
+	 * Only linear delay values is supported for current Intel SKUs.
+	 */
+	if (!r->membw.delay_linear && r->membw.arch_needs_linear) {
+		rdt_last_cmd_puts("No support for non-linear MB domains\n");
+		return false;
+	}
+
+	ret = kstrtou32(buf, 10, &bw);
+	if (ret) {
+		rdt_last_cmd_printf("Invalid MB value %s\n", buf);
+		return false;
+	}
+
+	/* Nothing else to do if software controller is enabled. */
+	if (is_mba_sc(r)) {
+		*data = bw;
+		return true;
+	}
+
+	if (bw < r->membw.min_bw || bw > r->membw.max_bw) {
+		rdt_last_cmd_printf("MB value %u out of range [%d,%d]\n",
+				    bw, r->membw.min_bw, r->membw.max_bw);
+		return false;
+	}
+
+	*data = roundup(bw, (unsigned long)r->membw.bw_gran);
+	return true;
+}
+
+static int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s,
+		    struct rdt_ctrl_domain *d)
+{
+	struct resctrl_staged_config *cfg;
+	u32 closid = data->rdtgrp->closid;
+	struct rdt_resource *r = s->res;
+	u32 bw_val;
+
+	cfg = &d->staged_config[s->conf_type];
+	if (cfg->have_new_ctrl) {
+		rdt_last_cmd_printf("Duplicate domain %d\n", d->hdr.id);
+		return -EINVAL;
+	}
+
+	if (!bw_validate(data->buf, &bw_val, r))
+		return -EINVAL;
+
+	if (is_mba_sc(r)) {
+		d->mbps_val[closid] = bw_val;
+		return 0;
+	}
+
+	cfg->new_ctrl = bw_val;
+	cfg->have_new_ctrl = true;
+
+	return 0;
+}
+
+/*
+ * Check whether a cache bit mask is valid.
+ * On Intel CPUs, non-contiguous 1s value support is indicated by CPUID:
+ *   - CPUID.0x10.1:ECX[3]: L3 non-contiguous 1s value supported if 1
+ *   - CPUID.0x10.2:ECX[3]: L2 non-contiguous 1s value supported if 1
+ *
+ * Haswell does not support a non-contiguous 1s value and additionally
+ * requires at least two bits set.
+ * AMD allows non-contiguous bitmasks.
+ */
+static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
+{
+	u32 supported_bits = BIT_MASK(r->cache.cbm_len) - 1;
+	unsigned int cbm_len = r->cache.cbm_len;
+	unsigned long first_bit, zero_bit, val;
+	int ret;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret) {
+		rdt_last_cmd_printf("Non-hex character in the mask %s\n", buf);
+		return false;
+	}
+
+	if ((r->cache.min_cbm_bits > 0 && val == 0) || val > supported_bits) {
+		rdt_last_cmd_puts("Mask out of range\n");
+		return false;
+	}
+
+	first_bit = find_first_bit(&val, cbm_len);
+	zero_bit = find_next_zero_bit(&val, cbm_len, first_bit);
+
+	/* Are non-contiguous bitmasks allowed? */
+	if (!r->cache.arch_has_sparse_bitmasks &&
+	    (find_next_bit(&val, cbm_len, zero_bit) < cbm_len)) {
+		rdt_last_cmd_printf("The mask %lx has non-consecutive 1-bits\n", val);
+		return false;
+	}
+
+	if ((zero_bit - first_bit) < r->cache.min_cbm_bits) {
+		rdt_last_cmd_printf("Need at least %d bits in the mask\n",
+				    r->cache.min_cbm_bits);
+		return false;
+	}
+
+	*data = val;
+	return true;
+}
+
+/*
+ * Read one cache bit mask (hex). Check that it is valid for the current
+ * resource type.
+ */
+static int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s,
+		     struct rdt_ctrl_domain *d)
+{
+	struct rdtgroup *rdtgrp = data->rdtgrp;
+	struct resctrl_staged_config *cfg;
+	struct rdt_resource *r = s->res;
+	u32 cbm_val;
+
+	cfg = &d->staged_config[s->conf_type];
+	if (cfg->have_new_ctrl) {
+		rdt_last_cmd_printf("Duplicate domain %d\n", d->hdr.id);
+		return -EINVAL;
+	}
+
+	/*
+	 * Cannot set up more than one pseudo-locked region in a cache
+	 * hierarchy.
+	 */
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
+	    rdtgroup_pseudo_locked_in_hierarchy(d)) {
+		rdt_last_cmd_puts("Pseudo-locked region in hierarchy\n");
+		return -EINVAL;
+	}
+
+	if (!cbm_validate(data->buf, &cbm_val, r))
+		return -EINVAL;
+
+	if ((rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
+	     rdtgrp->mode == RDT_MODE_SHAREABLE) &&
+	    rdtgroup_cbm_overlaps_pseudo_locked(d, cbm_val)) {
+		rdt_last_cmd_puts("CBM overlaps with pseudo-locked region\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * The CBM may not overlap with the CBM of another closid if
+	 * either is exclusive.
+	 */
+	if (rdtgroup_cbm_overlaps(s, d, cbm_val, rdtgrp->closid, true)) {
+		rdt_last_cmd_puts("Overlaps with exclusive group\n");
+		return -EINVAL;
+	}
+
+	if (rdtgroup_cbm_overlaps(s, d, cbm_val, rdtgrp->closid, false)) {
+		if (rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
+		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+			rdt_last_cmd_puts("Overlaps with other group\n");
+			return -EINVAL;
+		}
+	}
+
+	cfg->new_ctrl = cbm_val;
+	cfg->have_new_ctrl = true;
+
+	return 0;
+}
+
+/*
+ * For each domain in this resource we expect to find a series of:
+ *	id=mask
+ * separated by ";". The "id" is in decimal, and must match one of
+ * the "id"s for this resource.
+ */
+static int parse_line(char *line, struct resctrl_schema *s,
+		      struct rdtgroup *rdtgrp)
+{
+	enum resctrl_conf_type t = s->conf_type;
+	ctrlval_parser_t *parse_ctrlval = NULL;
+	struct resctrl_staged_config *cfg;
+	struct rdt_resource *r = s->res;
+	struct rdt_parse_data data;
+	struct rdt_ctrl_domain *d;
+	char *dom = NULL, *id;
+	unsigned long dom_id;
+
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
+	switch (r->schema_fmt) {
+	case RESCTRL_SCHEMA_BITMAP:
+		parse_ctrlval = &parse_cbm;
+		break;
+	case RESCTRL_SCHEMA_RANGE:
+		parse_ctrlval = &parse_bw;
+		break;
+	}
+
+	if (WARN_ON_ONCE(!parse_ctrlval))
+		return -EINVAL;
+
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
+	    (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)) {
+		rdt_last_cmd_puts("Cannot pseudo-lock MBA resource\n");
+		return -EINVAL;
+	}
+
+next:
+	if (!line || line[0] == '\0')
+		return 0;
+	dom = strsep(&line, ";");
+	id = strsep(&dom, "=");
+	if (!dom || kstrtoul(id, 10, &dom_id)) {
+		rdt_last_cmd_puts("Missing '=' or non-numeric domain\n");
+		return -EINVAL;
+	}
+	dom = strim(dom);
+	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
+		if (d->hdr.id == dom_id) {
+			data.buf = dom;
+			data.rdtgrp = rdtgrp;
+			if (parse_ctrlval(&data, s, d))
+				return -EINVAL;
+			if (rdtgrp->mode ==  RDT_MODE_PSEUDO_LOCKSETUP) {
+				cfg = &d->staged_config[t];
+				/*
+				 * In pseudo-locking setup mode and just
+				 * parsed a valid CBM that should be
+				 * pseudo-locked. Only one locked region per
+				 * resource group and domain so just do
+				 * the required initialization for single
+				 * region and return.
+				 */
+				rdtgrp->plr->s = s;
+				rdtgrp->plr->d = d;
+				rdtgrp->plr->cbm = cfg->new_ctrl;
+				d->plr = rdtgrp->plr;
+				return 0;
+			}
+			goto next;
+		}
+	}
+	return -EINVAL;
+}
+
+static int rdtgroup_parse_resource(char *resname, char *tok,
+				   struct rdtgroup *rdtgrp)
+{
+	struct resctrl_schema *s;
+
+	list_for_each_entry(s, &resctrl_schema_all, list) {
+		if (!strcmp(resname, s->name) && rdtgrp->closid < s->num_closid)
+			return parse_line(tok, s, rdtgrp);
+	}
+	rdt_last_cmd_printf("Unknown or unsupported resource name '%s'\n", resname);
+	return -EINVAL;
+}
+
+ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
+				char *buf, size_t nbytes, loff_t off)
+{
+	struct resctrl_schema *s;
+	struct rdtgroup *rdtgrp;
+	struct rdt_resource *r;
+	char *tok, *resname;
+	int ret = 0;
+
+	/* Valid input requires a trailing newline */
+	if (nbytes == 0 || buf[nbytes - 1] != '\n')
+		return -EINVAL;
+	buf[nbytes - 1] = '\0';
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		rdtgroup_kn_unlock(of->kn);
+		return -ENOENT;
+	}
+	rdt_last_cmd_clear();
+
+	/*
+	 * No changes to pseudo-locked region allowed. It has to be removed
+	 * and re-created instead.
+	 */
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
+		ret = -EINVAL;
+		rdt_last_cmd_puts("Resource group is pseudo-locked\n");
+		goto out;
+	}
+
+	rdt_staged_configs_clear();
+
+	while ((tok = strsep(&buf, "\n")) != NULL) {
+		resname = strim(strsep(&tok, ":"));
+		if (!tok) {
+			rdt_last_cmd_puts("Missing ':'\n");
+			ret = -EINVAL;
+			goto out;
+		}
+		if (tok[0] == '\0') {
+			rdt_last_cmd_printf("Missing '%s' value\n", resname);
+			ret = -EINVAL;
+			goto out;
+		}
+		ret = rdtgroup_parse_resource(resname, tok, rdtgrp);
+		if (ret)
+			goto out;
+	}
+
+	list_for_each_entry(s, &resctrl_schema_all, list) {
+		r = s->res;
+
+		/*
+		 * Writes to mba_sc resources update the software controller,
+		 * not the control MSR.
+		 */
+		if (is_mba_sc(r))
+			continue;
+
+		ret = resctrl_arch_update_domains(r, rdtgrp->closid);
+		if (ret)
+			goto out;
+	}
+
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+		/*
+		 * If pseudo-locking fails we keep the resource group in
+		 * mode RDT_MODE_PSEUDO_LOCKSETUP with its class of service
+		 * active and updated for just the domain the pseudo-locked
+		 * region was requested for.
+		 */
+		ret = rdtgroup_pseudo_lock_create(rdtgrp);
+	}
+
+out:
+	rdt_staged_configs_clear();
+	rdtgroup_kn_unlock(of->kn);
+	return ret ?: nbytes;
+}
+
+static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int closid)
+{
+	struct rdt_resource *r = schema->res;
+	struct rdt_ctrl_domain *dom;
+	bool sep = false;
+	u32 ctrl_val;
+
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
+	seq_printf(s, "%*s:", max_name_width, schema->name);
+	list_for_each_entry(dom, &r->ctrl_domains, hdr.list) {
+		if (sep)
+			seq_puts(s, ";");
+
+		if (is_mba_sc(r))
+			ctrl_val = dom->mbps_val[closid];
+		else
+			ctrl_val = resctrl_arch_get_config(r, dom, closid,
+							   schema->conf_type);
+
+		seq_printf(s, schema->fmt_str, dom->hdr.id, ctrl_val);
+		sep = true;
+	}
+	seq_puts(s, "\n");
+}
+
+int rdtgroup_schemata_show(struct kernfs_open_file *of,
+			   struct seq_file *s, void *v)
+{
+	struct resctrl_schema *schema;
+	struct rdtgroup *rdtgrp;
+	int ret = 0;
+	u32 closid;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (rdtgrp) {
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+			list_for_each_entry(schema, &resctrl_schema_all, list) {
+				seq_printf(s, "%s:uninitialized\n", schema->name);
+			}
+		} else if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
+			if (!rdtgrp->plr->d) {
+				rdt_last_cmd_clear();
+				rdt_last_cmd_puts("Cache domain offline\n");
+				ret = -ENODEV;
+			} else {
+				seq_printf(s, "%s:%d=%x\n",
+					   rdtgrp->plr->s->res->name,
+					   rdtgrp->plr->d->hdr.id,
+					   rdtgrp->plr->cbm);
+			}
+		} else {
+			closid = rdtgrp->closid;
+			list_for_each_entry(schema, &resctrl_schema_all, list) {
+				if (closid < schema->num_closid)
+					show_doms(s, schema, closid);
+			}
+		}
+	} else {
+		ret = -ENOENT;
+	}
+	rdtgroup_kn_unlock(of->kn);
+	return ret;
+}
+
+static int smp_mon_event_count(void *arg)
+{
+	mon_event_count(arg);
+
+	return 0;
+}
+
+ssize_t rdtgroup_mba_mbps_event_write(struct kernfs_open_file *of,
+				      char *buf, size_t nbytes, loff_t off)
+{
+	struct rdtgroup *rdtgrp;
+	int ret = 0;
+
+	/* Valid input requires a trailing newline */
+	if (nbytes == 0 || buf[nbytes - 1] != '\n')
+		return -EINVAL;
+	buf[nbytes - 1] = '\0';
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		rdtgroup_kn_unlock(of->kn);
+		return -ENOENT;
+	}
+	rdt_last_cmd_clear();
+
+	if (!strcmp(buf, "mbm_local_bytes")) {
+		if (resctrl_arch_is_mbm_local_enabled())
+			rdtgrp->mba_mbps_event = QOS_L3_MBM_LOCAL_EVENT_ID;
+		else
+			ret = -EINVAL;
+	} else if (!strcmp(buf, "mbm_total_bytes")) {
+		if (resctrl_arch_is_mbm_total_enabled())
+			rdtgrp->mba_mbps_event = QOS_L3_MBM_TOTAL_EVENT_ID;
+		else
+			ret = -EINVAL;
+	} else {
+		ret = -EINVAL;
+	}
+
+	if (ret)
+		rdt_last_cmd_printf("Unsupported event id '%s'\n", buf);
+
+	rdtgroup_kn_unlock(of->kn);
+
+	return ret ?: nbytes;
+}
+
+int rdtgroup_mba_mbps_event_show(struct kernfs_open_file *of,
+				 struct seq_file *s, void *v)
+{
+	struct rdtgroup *rdtgrp;
+	int ret = 0;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+
+	if (rdtgrp) {
+		switch (rdtgrp->mba_mbps_event) {
+		case QOS_L3_MBM_LOCAL_EVENT_ID:
+			seq_puts(s, "mbm_local_bytes\n");
+			break;
+		case QOS_L3_MBM_TOTAL_EVENT_ID:
+			seq_puts(s, "mbm_total_bytes\n");
+			break;
+		default:
+			pr_warn_once("Bad event %d\n", rdtgrp->mba_mbps_event);
+			ret = -EINVAL;
+			break;
+		}
+	} else {
+		ret = -ENOENT;
+	}
+
+	rdtgroup_kn_unlock(of->kn);
+
+	return ret;
+}
+
+struct rdt_domain_hdr *resctrl_find_domain(struct list_head *h, int id,
+					   struct list_head **pos)
+{
+	struct rdt_domain_hdr *d;
+	struct list_head *l;
+
+	list_for_each(l, h) {
+		d = list_entry(l, struct rdt_domain_hdr, list);
+		/* When id is found, return its domain. */
+		if (id == d->id)
+			return d;
+		/* Stop searching when finding id's position in sorted list. */
+		if (id < d->id)
+			break;
+	}
+
+	if (pos)
+		*pos = l;
+
+	return NULL;
+}
+
+void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
+		    struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
+		    cpumask_t *cpumask, int evtid, int first)
+{
+	int cpu;
+
+	/* When picking a CPU from cpu_mask, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
+	/*
+	 * Setup the parameters to pass to mon_event_count() to read the data.
+	 */
+	rr->rgrp = rdtgrp;
+	rr->evtid = evtid;
+	rr->r = r;
+	rr->d = d;
+	rr->first = first;
+	rr->arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, evtid);
+	if (IS_ERR(rr->arch_mon_ctx)) {
+		rr->err = -EINVAL;
+		return;
+	}
+
+	cpu = cpumask_any_housekeeping(cpumask, RESCTRL_PICK_ANY_CPU);
+
+	/*
+	 * cpumask_any_housekeeping() prefers housekeeping CPUs, but
+	 * are all the CPUs nohz_full? If yes, pick a CPU to IPI.
+	 * MPAM's resctrl_arch_rmid_read() is unable to read the
+	 * counters on some platforms if its called in IRQ context.
+	 */
+	if (tick_nohz_full_cpu(cpu))
+		smp_call_function_any(cpumask, mon_event_count, rr, 1);
+	else
+		smp_call_on_cpu(cpu, smp_mon_event_count, rr, false);
+
+	resctrl_arch_mon_ctx_free(r, evtid, rr->arch_mon_ctx);
+}
+
+int rdtgroup_mondata_show(struct seq_file *m, void *arg)
+{
+	struct kernfs_open_file *of = m->private;
+	enum resctrl_res_level resid;
+	enum resctrl_event_id evtid;
+	struct rdt_domain_hdr *hdr;
+	struct rmid_read rr = {0};
+	struct rdt_mon_domain *d;
+	struct rdtgroup *rdtgrp;
+	struct rdt_resource *r;
+	struct mon_data *md;
+	int domid, ret = 0;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		ret = -ENOENT;
+		goto out;
+	}
+
+	md = of->kn->priv;
+	if (WARN_ON_ONCE(!md)) {
+		ret = -EIO;
+		goto out;
+	}
+
+	resid = md->rid;
+	domid = md->domid;
+	evtid = md->evtid;
+	r = resctrl_arch_get_resource(resid);
+
+	if (md->sum) {
+		/*
+		 * This file requires summing across all domains that share
+		 * the L3 cache id that was provided in the "domid" field of the
+		 * struct mon_data. Search all domains in the resource for
+		 * one that matches this cache id.
+		 */
+		list_for_each_entry(d, &r->mon_domains, hdr.list) {
+			if (d->ci->id == domid) {
+				rr.ci = d->ci;
+				mon_event_read(&rr, r, NULL, rdtgrp,
+					       &d->ci->shared_cpu_map, evtid, false);
+				goto checkresult;
+			}
+		}
+		ret = -ENOENT;
+		goto out;
+	} else {
+		/*
+		 * This file provides data from a single domain. Search
+		 * the resource to find the domain with "domid".
+		 */
+		hdr = resctrl_find_domain(&r->mon_domains, domid, NULL);
+		if (!hdr || WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN)) {
+			ret = -ENOENT;
+			goto out;
+		}
+		d = container_of(hdr, struct rdt_mon_domain, hdr);
+		mon_event_read(&rr, r, d, rdtgrp, &d->hdr.cpu_mask, evtid, false);
+	}
+
+checkresult:
+
+	if (rr.err == -EIO)
+		seq_puts(m, "Error\n");
+	else if (rr.err == -EINVAL)
+		seq_puts(m, "Unavailable\n");
+	else
+		seq_printf(m, "%llu\n", rr.val);
+
+out:
+	rdtgroup_kn_unlock(of->kn);
+	return ret;
+}
diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index e69de29bb2d1d..9a8cf6f11151d 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -0,0 +1,426 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _FS_RESCTRL_INTERNAL_H
+#define _FS_RESCTRL_INTERNAL_H
+
+#include <linux/resctrl.h>
+#include <linux/kernfs.h>
+#include <linux/fs_context.h>
+#include <linux/tick.h>
+
+#define CQM_LIMBOCHECK_INTERVAL	1000
+
+/**
+ * cpumask_any_housekeeping() - Choose any CPU in @mask, preferring those that
+ *			        aren't marked nohz_full
+ * @mask:	The mask to pick a CPU from.
+ * @exclude_cpu:The CPU to avoid picking.
+ *
+ * Returns a CPU from @mask, but not @exclude_cpu. If there are housekeeping
+ * CPUs that don't use nohz_full, these are preferred. Pass
+ * RESCTRL_PICK_ANY_CPU to avoid excluding any CPUs.
+ *
+ * When a CPU is excluded, returns >= nr_cpu_ids if no CPUs are available.
+ */
+static inline unsigned int
+cpumask_any_housekeeping(const struct cpumask *mask, int exclude_cpu)
+{
+	unsigned int cpu;
+
+	/* Try to find a CPU that isn't nohz_full to use in preference */
+	if (tick_nohz_full_enabled()) {
+		cpu = cpumask_any_andnot_but(mask, tick_nohz_full_mask, exclude_cpu);
+		if (cpu < nr_cpu_ids)
+			return cpu;
+	}
+
+	return cpumask_any_but(mask, exclude_cpu);
+}
+
+struct rdt_fs_context {
+	struct kernfs_fs_context	kfc;
+	bool				enable_cdpl2;
+	bool				enable_cdpl3;
+	bool				enable_mba_mbps;
+	bool				enable_debug;
+};
+
+static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc)
+{
+	struct kernfs_fs_context *kfc = fc->fs_private;
+
+	return container_of(kfc, struct rdt_fs_context, kfc);
+}
+
+/**
+ * struct mon_evt - Entry in the event list of a resource
+ * @evtid:		event id
+ * @name:		name of the event
+ * @configurable:	true if the event is configurable
+ * @list:		entry in &rdt_resource->evt_list
+ */
+struct mon_evt {
+	enum resctrl_event_id	evtid;
+	char			*name;
+	bool			configurable;
+	struct list_head	list;
+};
+
+/**
+ * struct mon_data - Monitoring details for each event file.
+ * @list:            Member of the global @mon_data_kn_priv_list list.
+ * @rid:             Resource id associated with the event file.
+ * @evtid:           Event id associated with the event file.
+ * @sum:             Set when event must be summed across multiple
+ *                   domains.
+ * @domid:           When @sum is zero this is the domain to which
+ *                   the event file belongs. When @sum is one this
+ *                   is the id of the L3 cache that all domains to be
+ *                   summed share.
+ *
+ * Pointed to by the kernfs kn->priv field of monitoring event files.
+ * Readers and writers must hold rdtgroup_mutex.
+ */
+struct mon_data {
+	struct list_head	list;
+	enum resctrl_res_level	rid;
+	enum resctrl_event_id	evtid;
+	int			domid;
+	bool			sum;
+};
+
+/**
+ * struct rmid_read - Data passed across smp_call*() to read event count.
+ * @rgrp:  Resource group for which the counter is being read. If it is a parent
+ *	   resource group then its event count is summed with the count from all
+ *	   its child resource groups.
+ * @r:	   Resource describing the properties of the event being read.
+ * @d:	   Domain that the counter should be read from. If NULL then sum all
+ *	   domains in @r sharing L3 @ci.id
+ * @evtid: Which monitor event to read.
+ * @first: Initialize MBM counter when true.
+ * @ci:    Cacheinfo for L3. Only set when @d is NULL. Used when summing domains.
+ * @err:   Error encountered when reading counter.
+ * @val:   Returned value of event counter. If @rgrp is a parent resource group,
+ *	   @val includes the sum of event counts from its child resource groups.
+ *	   If @d is NULL, @val includes the sum of all domains in @r sharing @ci.id,
+ *	   (summed across child resource groups if @rgrp is a parent resource group).
+ * @arch_mon_ctx: Hardware monitor allocated for this read request (MPAM only).
+ */
+struct rmid_read {
+	struct rdtgroup		*rgrp;
+	struct rdt_resource	*r;
+	struct rdt_mon_domain	*d;
+	enum resctrl_event_id	evtid;
+	bool			first;
+	struct cacheinfo	*ci;
+	int			err;
+	u64			val;
+	void			*arch_mon_ctx;
+};
+
+extern struct list_head resctrl_schema_all;
+
+extern bool resctrl_mounted;
+
+enum rdt_group_type {
+	RDTCTRL_GROUP = 0,
+	RDTMON_GROUP,
+	RDT_NUM_GROUP,
+};
+
+/**
+ * enum rdtgrp_mode - Mode of a RDT resource group
+ * @RDT_MODE_SHAREABLE: This resource group allows sharing of its allocations
+ * @RDT_MODE_EXCLUSIVE: No sharing of this resource group's allocations allowed
+ * @RDT_MODE_PSEUDO_LOCKSETUP: Resource group will be used for Pseudo-Locking
+ * @RDT_MODE_PSEUDO_LOCKED: No sharing of this resource group's allocations
+ *                          allowed AND the allocations are Cache Pseudo-Locked
+ * @RDT_NUM_MODES: Total number of modes
+ *
+ * The mode of a resource group enables control over the allowed overlap
+ * between allocations associated with different resource groups (classes
+ * of service). User is able to modify the mode of a resource group by
+ * writing to the "mode" resctrl file associated with the resource group.
+ *
+ * The "shareable", "exclusive", and "pseudo-locksetup" modes are set by
+ * writing the appropriate text to the "mode" file. A resource group enters
+ * "pseudo-locked" mode after the schemata is written while the resource
+ * group is in "pseudo-locksetup" mode.
+ */
+enum rdtgrp_mode {
+	RDT_MODE_SHAREABLE = 0,
+	RDT_MODE_EXCLUSIVE,
+	RDT_MODE_PSEUDO_LOCKSETUP,
+	RDT_MODE_PSEUDO_LOCKED,
+
+	/* Must be last */
+	RDT_NUM_MODES,
+};
+
+/**
+ * struct mongroup - store mon group's data in resctrl fs.
+ * @mon_data_kn:		kernfs node for the mon_data directory
+ * @parent:			parent rdtgrp
+ * @crdtgrp_list:		child rdtgroup node list
+ * @rmid:			rmid for this rdtgroup
+ */
+struct mongroup {
+	struct kernfs_node	*mon_data_kn;
+	struct rdtgroup		*parent;
+	struct list_head	crdtgrp_list;
+	u32			rmid;
+};
+
+/**
+ * struct rdtgroup - store rdtgroup's data in resctrl file system.
+ * @kn:				kernfs node
+ * @rdtgroup_list:		linked list for all rdtgroups
+ * @closid:			closid for this rdtgroup
+ * @cpu_mask:			CPUs assigned to this rdtgroup
+ * @flags:			status bits
+ * @waitcount:			how many cpus expect to find this
+ *				group when they acquire rdtgroup_mutex
+ * @type:			indicates type of this rdtgroup - either
+ *				monitor only or ctrl_mon group
+ * @mon:			mongroup related data
+ * @mode:			mode of resource group
+ * @mba_mbps_event:		input monitoring event id when mba_sc is enabled
+ * @plr:			pseudo-locked region
+ */
+struct rdtgroup {
+	struct kernfs_node		*kn;
+	struct list_head		rdtgroup_list;
+	u32				closid;
+	struct cpumask			cpu_mask;
+	int				flags;
+	atomic_t			waitcount;
+	enum rdt_group_type		type;
+	struct mongroup			mon;
+	enum rdtgrp_mode		mode;
+	enum resctrl_event_id		mba_mbps_event;
+	struct pseudo_lock_region	*plr;
+};
+
+/* rdtgroup.flags */
+#define	RDT_DELETED		1
+
+/* rftype.flags */
+#define RFTYPE_FLAGS_CPUS_LIST	1
+
+/*
+ * Define the file type flags for base and info directories.
+ */
+#define RFTYPE_INFO			BIT(0)
+
+#define RFTYPE_BASE			BIT(1)
+
+#define RFTYPE_CTRL			BIT(4)
+
+#define RFTYPE_MON			BIT(5)
+
+#define RFTYPE_TOP			BIT(6)
+
+#define RFTYPE_RES_CACHE		BIT(8)
+
+#define RFTYPE_RES_MB			BIT(9)
+
+#define RFTYPE_DEBUG			BIT(10)
+
+#define RFTYPE_CTRL_INFO		(RFTYPE_INFO | RFTYPE_CTRL)
+
+#define RFTYPE_MON_INFO			(RFTYPE_INFO | RFTYPE_MON)
+
+#define RFTYPE_TOP_INFO			(RFTYPE_INFO | RFTYPE_TOP)
+
+#define RFTYPE_CTRL_BASE		(RFTYPE_BASE | RFTYPE_CTRL)
+
+#define RFTYPE_MON_BASE			(RFTYPE_BASE | RFTYPE_MON)
+
+/* List of all resource groups */
+extern struct list_head rdt_all_groups;
+
+extern int max_name_width;
+
+/**
+ * struct rftype - describe each file in the resctrl file system
+ * @name:	File name
+ * @mode:	Access mode
+ * @kf_ops:	File operations
+ * @flags:	File specific RFTYPE_FLAGS_* flags
+ * @fflags:	File specific RFTYPE_* flags
+ * @seq_show:	Show content of the file
+ * @write:	Write to the file
+ */
+struct rftype {
+	char			*name;
+	umode_t			mode;
+	const struct kernfs_ops	*kf_ops;
+	unsigned long		flags;
+	unsigned long		fflags;
+
+	int (*seq_show)(struct kernfs_open_file *of,
+			struct seq_file *sf, void *v);
+	/*
+	 * write() is the generic write callback which maps directly to
+	 * kernfs write operation and overrides all other operations.
+	 * Maximum write size is determined by ->max_write_len.
+	 */
+	ssize_t (*write)(struct kernfs_open_file *of,
+			 char *buf, size_t nbytes, loff_t off);
+};
+
+/**
+ * struct mbm_state - status for each MBM counter in each domain
+ * @prev_bw_bytes: Previous bytes value read for bandwidth calculation
+ * @prev_bw:	The most recent bandwidth in MBps
+ */
+struct mbm_state {
+	u64	prev_bw_bytes;
+	u32	prev_bw;
+};
+
+extern struct mutex rdtgroup_mutex;
+
+static inline const char *rdt_kn_name(const struct kernfs_node *kn)
+{
+	return rcu_dereference_check(kn->name, lockdep_is_held(&rdtgroup_mutex));
+}
+
+extern struct rdtgroup rdtgroup_default;
+
+extern struct dentry *debugfs_resctrl;
+
+extern enum resctrl_event_id mba_mbps_default_event;
+
+void rdt_last_cmd_clear(void);
+
+void rdt_last_cmd_puts(const char *s);
+
+__printf(1, 2)
+void rdt_last_cmd_printf(const char *fmt, ...);
+
+struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn);
+
+void rdtgroup_kn_unlock(struct kernfs_node *kn);
+
+int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name);
+
+int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name,
+			     umode_t mask);
+
+ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
+				char *buf, size_t nbytes, loff_t off);
+
+int rdtgroup_schemata_show(struct kernfs_open_file *of,
+			   struct seq_file *s, void *v);
+
+ssize_t rdtgroup_mba_mbps_event_write(struct kernfs_open_file *of,
+				      char *buf, size_t nbytes, loff_t off);
+
+int rdtgroup_mba_mbps_event_show(struct kernfs_open_file *of,
+				 struct seq_file *s, void *v);
+
+bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_ctrl_domain *d,
+			   unsigned long cbm, int closid, bool exclusive);
+
+unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_ctrl_domain *d,
+				  unsigned long cbm);
+
+enum rdtgrp_mode rdtgroup_mode_by_closid(int closid);
+
+int rdtgroup_tasks_assigned(struct rdtgroup *r);
+
+int closids_supported(void);
+
+void closid_free(int closid);
+
+int alloc_rmid(u32 closid);
+
+void free_rmid(u32 closid, u32 rmid);
+
+void resctrl_mon_resource_exit(void);
+
+void mon_event_count(void *info);
+
+int rdtgroup_mondata_show(struct seq_file *m, void *arg);
+
+void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
+		    struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
+		    cpumask_t *cpumask, int evtid, int first);
+
+int resctrl_mon_resource_init(void);
+
+void mbm_setup_overflow_handler(struct rdt_mon_domain *dom,
+				unsigned long delay_ms,
+				int exclude_cpu);
+
+void mbm_handle_overflow(struct work_struct *work);
+
+bool is_mba_sc(struct rdt_resource *r);
+
+void cqm_setup_limbo_handler(struct rdt_mon_domain *dom, unsigned long delay_ms,
+			     int exclude_cpu);
+
+void cqm_handle_limbo(struct work_struct *work);
+
+bool has_busy_rmid(struct rdt_mon_domain *d);
+
+void __check_limbo(struct rdt_mon_domain *d, bool force_free);
+
+void resctrl_file_fflags_init(const char *config, unsigned long fflags);
+
+void rdt_staged_configs_clear(void);
+
+bool closid_allocated(unsigned int closid);
+
+int resctrl_find_cleanest_closid(void);
+
+#ifdef CONFIG_RESCTRL_FS_PSEUDO_LOCK
+int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp);
+
+int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp);
+
+bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm);
+
+bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d);
+
+int rdt_pseudo_lock_init(void);
+
+void rdt_pseudo_lock_release(void);
+
+int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp);
+
+void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp);
+
+#else
+static inline int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm)
+{
+	return false;
+}
+
+static inline bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d)
+{
+	return false;
+}
+
+static inline int rdt_pseudo_lock_init(void) { return 0; }
+static inline void rdt_pseudo_lock_release(void) { }
+static inline int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp) { }
+#endif /* CONFIG_RESCTRL_FS_PSEUDO_LOCK */
+
+#endif /* _FS_RESCTRL_INTERNAL_H */
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index e69de29bb2d1d..bde2801289d35 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -0,0 +1,929 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Resource Director Technology(RDT)
+ * - Monitoring code
+ *
+ * Copyright (C) 2017 Intel Corporation
+ *
+ * Author:
+ *    Vikas Shivappa <vikas.shivappa@intel.com>
+ *
+ * This replaces the cqm.c based on perf but we reuse a lot of
+ * code and datastructures originally from Peter Zijlstra and Matt Fleming.
+ *
+ * More information about RDT be found in the Intel (R) x86 Architecture
+ * Software Developer Manual June 2016, volume 3, section 17.17.
+ */
+
+#define pr_fmt(fmt)	"resctrl: " fmt
+
+#include <linux/cpu.h>
+#include <linux/resctrl.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+
+#include "internal.h"
+
+#define CREATE_TRACE_POINTS
+
+#include "monitor_trace.h"
+
+/**
+ * struct rmid_entry - dirty tracking for all RMID.
+ * @closid:	The CLOSID for this entry.
+ * @rmid:	The RMID for this entry.
+ * @busy:	The number of domains with cached data using this RMID.
+ * @list:	Member of the rmid_free_lru list when busy == 0.
+ *
+ * Depending on the architecture the correct monitor is accessed using
+ * both @closid and @rmid, or @rmid only.
+ *
+ * Take the rdtgroup_mutex when accessing.
+ */
+struct rmid_entry {
+	u32				closid;
+	u32				rmid;
+	int				busy;
+	struct list_head		list;
+};
+
+/*
+ * @rmid_free_lru - A least recently used list of free RMIDs
+ *     These RMIDs are guaranteed to have an occupancy less than the
+ *     threshold occupancy
+ */
+static LIST_HEAD(rmid_free_lru);
+
+/*
+ * @closid_num_dirty_rmid    The number of dirty RMID each CLOSID has.
+ *     Only allocated when CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID is defined.
+ *     Indexed by CLOSID. Protected by rdtgroup_mutex.
+ */
+static u32 *closid_num_dirty_rmid;
+
+/*
+ * @rmid_limbo_count - count of currently unused but (potentially)
+ *     dirty RMIDs.
+ *     This counts RMIDs that no one is currently using but that
+ *     may have a occupancy value > resctrl_rmid_realloc_threshold. User can
+ *     change the threshold occupancy value.
+ */
+static unsigned int rmid_limbo_count;
+
+/*
+ * @rmid_entry - The entry in the limbo and free lists.
+ */
+static struct rmid_entry	*rmid_ptrs;
+
+/*
+ * This is the threshold cache occupancy in bytes at which we will consider an
+ * RMID available for re-allocation.
+ */
+unsigned int resctrl_rmid_realloc_threshold;
+
+/*
+ * This is the maximum value for the reallocation threshold, in bytes.
+ */
+unsigned int resctrl_rmid_realloc_limit;
+
+/*
+ * x86 and arm64 differ in their handling of monitoring.
+ * x86's RMID are independent numbers, there is only one source of traffic
+ * with an RMID value of '1'.
+ * arm64's PMG extends the PARTID/CLOSID space, there are multiple sources of
+ * traffic with a PMG value of '1', one for each CLOSID, meaning the RMID
+ * value is no longer unique.
+ * To account for this, resctrl uses an index. On x86 this is just the RMID,
+ * on arm64 it encodes the CLOSID and RMID. This gives a unique number.
+ *
+ * The domain's rmid_busy_llc and rmid_ptrs[] are sized by index. The arch code
+ * must accept an attempt to read every index.
+ */
+static inline struct rmid_entry *__rmid_entry(u32 idx)
+{
+	struct rmid_entry *entry;
+	u32 closid, rmid;
+
+	entry = &rmid_ptrs[idx];
+	resctrl_arch_rmid_idx_decode(idx, &closid, &rmid);
+
+	WARN_ON_ONCE(entry->closid != closid);
+	WARN_ON_ONCE(entry->rmid != rmid);
+
+	return entry;
+}
+
+static void limbo_release_entry(struct rmid_entry *entry)
+{
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	rmid_limbo_count--;
+	list_add_tail(&entry->list, &rmid_free_lru);
+
+	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID))
+		closid_num_dirty_rmid[entry->closid]--;
+}
+
+/*
+ * Check the RMIDs that are marked as busy for this domain. If the
+ * reported LLC occupancy is below the threshold clear the busy bit and
+ * decrement the count. If the busy count gets to zero on an RMID, we
+ * free the RMID
+ */
+void __check_limbo(struct rdt_mon_domain *d, bool force_free)
+{
+	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
+	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
+	struct rmid_entry *entry;
+	u32 idx, cur_idx = 1;
+	void *arch_mon_ctx;
+	bool rmid_dirty;
+	u64 val = 0;
+
+	arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, QOS_L3_OCCUP_EVENT_ID);
+	if (IS_ERR(arch_mon_ctx)) {
+		pr_warn_ratelimited("Failed to allocate monitor context: %ld",
+				    PTR_ERR(arch_mon_ctx));
+		return;
+	}
+
+	/*
+	 * Skip RMID 0 and start from RMID 1 and check all the RMIDs that
+	 * are marked as busy for occupancy < threshold. If the occupancy
+	 * is less than the threshold decrement the busy counter of the
+	 * RMID and move it to the free list when the counter reaches 0.
+	 */
+	for (;;) {
+		idx = find_next_bit(d->rmid_busy_llc, idx_limit, cur_idx);
+		if (idx >= idx_limit)
+			break;
+
+		entry = __rmid_entry(idx);
+		if (resctrl_arch_rmid_read(r, d, entry->closid, entry->rmid,
+					   QOS_L3_OCCUP_EVENT_ID, &val,
+					   arch_mon_ctx)) {
+			rmid_dirty = true;
+		} else {
+			rmid_dirty = (val >= resctrl_rmid_realloc_threshold);
+
+			/*
+			 * x86's CLOSID and RMID are independent numbers, so the entry's
+			 * CLOSID is an empty CLOSID (X86_RESCTRL_EMPTY_CLOSID). On Arm the
+			 * RMID (PMG) extends the CLOSID (PARTID) space with bits that aren't
+			 * used to select the configuration. It is thus necessary to track both
+			 * CLOSID and RMID because there may be dependencies between them
+			 * on some architectures.
+			 */
+			trace_mon_llc_occupancy_limbo(entry->closid, entry->rmid, d->hdr.id, val);
+		}
+
+		if (force_free || !rmid_dirty) {
+			clear_bit(idx, d->rmid_busy_llc);
+			if (!--entry->busy)
+				limbo_release_entry(entry);
+		}
+		cur_idx = idx + 1;
+	}
+
+	resctrl_arch_mon_ctx_free(r, QOS_L3_OCCUP_EVENT_ID, arch_mon_ctx);
+}
+
+bool has_busy_rmid(struct rdt_mon_domain *d)
+{
+	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
+
+	return find_first_bit(d->rmid_busy_llc, idx_limit) != idx_limit;
+}
+
+static struct rmid_entry *resctrl_find_free_rmid(u32 closid)
+{
+	struct rmid_entry *itr;
+	u32 itr_idx, cmp_idx;
+
+	if (list_empty(&rmid_free_lru))
+		return rmid_limbo_count ? ERR_PTR(-EBUSY) : ERR_PTR(-ENOSPC);
+
+	list_for_each_entry(itr, &rmid_free_lru, list) {
+		/*
+		 * Get the index of this free RMID, and the index it would need
+		 * to be if it were used with this CLOSID.
+		 * If the CLOSID is irrelevant on this architecture, the two
+		 * index values are always the same on every entry and thus the
+		 * very first entry will be returned.
+		 */
+		itr_idx = resctrl_arch_rmid_idx_encode(itr->closid, itr->rmid);
+		cmp_idx = resctrl_arch_rmid_idx_encode(closid, itr->rmid);
+
+		if (itr_idx == cmp_idx)
+			return itr;
+	}
+
+	return ERR_PTR(-ENOSPC);
+}
+
+/**
+ * resctrl_find_cleanest_closid() - Find a CLOSID where all the associated
+ *                                  RMID are clean, or the CLOSID that has
+ *                                  the most clean RMID.
+ *
+ * MPAM's equivalent of RMID are per-CLOSID, meaning a freshly allocated CLOSID
+ * may not be able to allocate clean RMID. To avoid this the allocator will
+ * choose the CLOSID with the most clean RMID.
+ *
+ * When the CLOSID and RMID are independent numbers, the first free CLOSID will
+ * be returned.
+ */
+int resctrl_find_cleanest_closid(void)
+{
+	u32 cleanest_closid = ~0;
+	int i = 0;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	if (!IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID))
+		return -EIO;
+
+	for (i = 0; i < closids_supported(); i++) {
+		int num_dirty;
+
+		if (closid_allocated(i))
+			continue;
+
+		num_dirty = closid_num_dirty_rmid[i];
+		if (num_dirty == 0)
+			return i;
+
+		if (cleanest_closid == ~0)
+			cleanest_closid = i;
+
+		if (num_dirty < closid_num_dirty_rmid[cleanest_closid])
+			cleanest_closid = i;
+	}
+
+	if (cleanest_closid == ~0)
+		return -ENOSPC;
+
+	return cleanest_closid;
+}
+
+/*
+ * For MPAM the RMID value is not unique, and has to be considered with
+ * the CLOSID. The (CLOSID, RMID) pair is allocated on all domains, which
+ * allows all domains to be managed by a single free list.
+ * Each domain also has a rmid_busy_llc to reduce the work of the limbo handler.
+ */
+int alloc_rmid(u32 closid)
+{
+	struct rmid_entry *entry;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	entry = resctrl_find_free_rmid(closid);
+	if (IS_ERR(entry))
+		return PTR_ERR(entry);
+
+	list_del(&entry->list);
+	return entry->rmid;
+}
+
+static void add_rmid_to_limbo(struct rmid_entry *entry)
+{
+	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
+	struct rdt_mon_domain *d;
+	u32 idx;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
+	idx = resctrl_arch_rmid_idx_encode(entry->closid, entry->rmid);
+
+	entry->busy = 0;
+	list_for_each_entry(d, &r->mon_domains, hdr.list) {
+		/*
+		 * For the first limbo RMID in the domain,
+		 * setup up the limbo worker.
+		 */
+		if (!has_busy_rmid(d))
+			cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL,
+						RESCTRL_PICK_ANY_CPU);
+		set_bit(idx, d->rmid_busy_llc);
+		entry->busy++;
+	}
+
+	rmid_limbo_count++;
+	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID))
+		closid_num_dirty_rmid[entry->closid]++;
+}
+
+void free_rmid(u32 closid, u32 rmid)
+{
+	u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid);
+	struct rmid_entry *entry;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	/*
+	 * Do not allow the default rmid to be free'd. Comparing by index
+	 * allows architectures that ignore the closid parameter to avoid an
+	 * unnecessary check.
+	 */
+	if (!resctrl_arch_mon_capable() ||
+	    idx == resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID,
+						RESCTRL_RESERVED_RMID))
+		return;
+
+	entry = __rmid_entry(idx);
+
+	if (resctrl_arch_is_llc_occupancy_enabled())
+		add_rmid_to_limbo(entry);
+	else
+		list_add_tail(&entry->list, &rmid_free_lru);
+}
+
+static struct mbm_state *get_mbm_state(struct rdt_mon_domain *d, u32 closid,
+				       u32 rmid, enum resctrl_event_id evtid)
+{
+	u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid);
+
+	switch (evtid) {
+	case QOS_L3_MBM_TOTAL_EVENT_ID:
+		return &d->mbm_total[idx];
+	case QOS_L3_MBM_LOCAL_EVENT_ID:
+		return &d->mbm_local[idx];
+	default:
+		return NULL;
+	}
+}
+
+static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
+{
+	int cpu = smp_processor_id();
+	struct rdt_mon_domain *d;
+	struct mbm_state *m;
+	int err, ret;
+	u64 tval = 0;
+
+	if (rr->first) {
+		resctrl_arch_reset_rmid(rr->r, rr->d, closid, rmid, rr->evtid);
+		m = get_mbm_state(rr->d, closid, rmid, rr->evtid);
+		if (m)
+			memset(m, 0, sizeof(struct mbm_state));
+		return 0;
+	}
+
+	if (rr->d) {
+		/* Reading a single domain, must be on a CPU in that domain. */
+		if (!cpumask_test_cpu(cpu, &rr->d->hdr.cpu_mask))
+			return -EINVAL;
+		rr->err = resctrl_arch_rmid_read(rr->r, rr->d, closid, rmid,
+						 rr->evtid, &tval, rr->arch_mon_ctx);
+		if (rr->err)
+			return rr->err;
+
+		rr->val += tval;
+
+		return 0;
+	}
+
+	/* Summing domains that share a cache, must be on a CPU for that cache. */
+	if (!cpumask_test_cpu(cpu, &rr->ci->shared_cpu_map))
+		return -EINVAL;
+
+	/*
+	 * Legacy files must report the sum of an event across all
+	 * domains that share the same L3 cache instance.
+	 * Report success if a read from any domain succeeds, -EINVAL
+	 * (translated to "Unavailable" for user space) if reading from
+	 * all domains fail for any reason.
+	 */
+	ret = -EINVAL;
+	list_for_each_entry(d, &rr->r->mon_domains, hdr.list) {
+		if (d->ci->id != rr->ci->id)
+			continue;
+		err = resctrl_arch_rmid_read(rr->r, d, closid, rmid,
+					     rr->evtid, &tval, rr->arch_mon_ctx);
+		if (!err) {
+			rr->val += tval;
+			ret = 0;
+		}
+	}
+
+	if (ret)
+		rr->err = ret;
+
+	return ret;
+}
+
+/*
+ * mbm_bw_count() - Update bw count from values previously read by
+ *		    __mon_event_count().
+ * @closid:	The closid used to identify the cached mbm_state.
+ * @rmid:	The rmid used to identify the cached mbm_state.
+ * @rr:		The struct rmid_read populated by __mon_event_count().
+ *
+ * Supporting function to calculate the memory bandwidth
+ * and delta bandwidth in MBps. The chunks value previously read by
+ * __mon_event_count() is compared with the chunks value from the previous
+ * invocation. This must be called once per second to maintain values in MBps.
+ */
+static void mbm_bw_count(u32 closid, u32 rmid, struct rmid_read *rr)
+{
+	u64 cur_bw, bytes, cur_bytes;
+	struct mbm_state *m;
+
+	m = get_mbm_state(rr->d, closid, rmid, rr->evtid);
+	if (WARN_ON_ONCE(!m))
+		return;
+
+	cur_bytes = rr->val;
+	bytes = cur_bytes - m->prev_bw_bytes;
+	m->prev_bw_bytes = cur_bytes;
+
+	cur_bw = bytes / SZ_1M;
+
+	m->prev_bw = cur_bw;
+}
+
+/*
+ * This is scheduled by mon_event_read() to read the CQM/MBM counters
+ * on a domain.
+ */
+void mon_event_count(void *info)
+{
+	struct rdtgroup *rdtgrp, *entry;
+	struct rmid_read *rr = info;
+	struct list_head *head;
+	int ret;
+
+	rdtgrp = rr->rgrp;
+
+	ret = __mon_event_count(rdtgrp->closid, rdtgrp->mon.rmid, rr);
+
+	/*
+	 * For Ctrl groups read data from child monitor groups and
+	 * add them together. Count events which are read successfully.
+	 * Discard the rmid_read's reporting errors.
+	 */
+	head = &rdtgrp->mon.crdtgrp_list;
+
+	if (rdtgrp->type == RDTCTRL_GROUP) {
+		list_for_each_entry(entry, head, mon.crdtgrp_list) {
+			if (__mon_event_count(entry->closid, entry->mon.rmid,
+					      rr) == 0)
+				ret = 0;
+		}
+	}
+
+	/*
+	 * __mon_event_count() calls for newly created monitor groups may
+	 * report -EINVAL/Unavailable if the monitor hasn't seen any traffic.
+	 * Discard error if any of the monitor event reads succeeded.
+	 */
+	if (ret == 0)
+		rr->err = 0;
+}
+
+static struct rdt_ctrl_domain *get_ctrl_domain_from_cpu(int cpu,
+							struct rdt_resource *r)
+{
+	struct rdt_ctrl_domain *d;
+
+	lockdep_assert_cpus_held();
+
+	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
+		/* Find the domain that contains this CPU */
+		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask))
+			return d;
+	}
+
+	return NULL;
+}
+
+/*
+ * Feedback loop for MBA software controller (mba_sc)
+ *
+ * mba_sc is a feedback loop where we periodically read MBM counters and
+ * adjust the bandwidth percentage values via the IA32_MBA_THRTL_MSRs so
+ * that:
+ *
+ *   current bandwidth(cur_bw) < user specified bandwidth(user_bw)
+ *
+ * This uses the MBM counters to measure the bandwidth and MBA throttle
+ * MSRs to control the bandwidth for a particular rdtgrp. It builds on the
+ * fact that resctrl rdtgroups have both monitoring and control.
+ *
+ * The frequency of the checks is 1s and we just tag along the MBM overflow
+ * timer. Having 1s interval makes the calculation of bandwidth simpler.
+ *
+ * Although MBA's goal is to restrict the bandwidth to a maximum, there may
+ * be a need to increase the bandwidth to avoid unnecessarily restricting
+ * the L2 <-> L3 traffic.
+ *
+ * Since MBA controls the L2 external bandwidth where as MBM measures the
+ * L3 external bandwidth the following sequence could lead to such a
+ * situation.
+ *
+ * Consider an rdtgroup which had high L3 <-> memory traffic in initial
+ * phases -> mba_sc kicks in and reduced bandwidth percentage values -> but
+ * after some time rdtgroup has mostly L2 <-> L3 traffic.
+ *
+ * In this case we may restrict the rdtgroup's L2 <-> L3 traffic as its
+ * throttle MSRs already have low percentage values.  To avoid
+ * unnecessarily restricting such rdtgroups, we also increase the bandwidth.
+ */
+static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm)
+{
+	u32 closid, rmid, cur_msr_val, new_msr_val;
+	struct mbm_state *pmbm_data, *cmbm_data;
+	struct rdt_ctrl_domain *dom_mba;
+	enum resctrl_event_id evt_id;
+	struct rdt_resource *r_mba;
+	struct list_head *head;
+	struct rdtgroup *entry;
+	u32 cur_bw, user_bw;
+
+	r_mba = resctrl_arch_get_resource(RDT_RESOURCE_MBA);
+	evt_id = rgrp->mba_mbps_event;
+
+	closid = rgrp->closid;
+	rmid = rgrp->mon.rmid;
+	pmbm_data = get_mbm_state(dom_mbm, closid, rmid, evt_id);
+	if (WARN_ON_ONCE(!pmbm_data))
+		return;
+
+	dom_mba = get_ctrl_domain_from_cpu(smp_processor_id(), r_mba);
+	if (!dom_mba) {
+		pr_warn_once("Failure to get domain for MBA update\n");
+		return;
+	}
+
+	cur_bw = pmbm_data->prev_bw;
+	user_bw = dom_mba->mbps_val[closid];
+
+	/* MBA resource doesn't support CDP */
+	cur_msr_val = resctrl_arch_get_config(r_mba, dom_mba, closid, CDP_NONE);
+
+	/*
+	 * For Ctrl groups read data from child monitor groups.
+	 */
+	head = &rgrp->mon.crdtgrp_list;
+	list_for_each_entry(entry, head, mon.crdtgrp_list) {
+		cmbm_data = get_mbm_state(dom_mbm, entry->closid, entry->mon.rmid, evt_id);
+		if (WARN_ON_ONCE(!cmbm_data))
+			return;
+		cur_bw += cmbm_data->prev_bw;
+	}
+
+	/*
+	 * Scale up/down the bandwidth linearly for the ctrl group.  The
+	 * bandwidth step is the bandwidth granularity specified by the
+	 * hardware.
+	 * Always increase throttling if current bandwidth is above the
+	 * target set by user.
+	 * But avoid thrashing up and down on every poll by checking
+	 * whether a decrease in throttling is likely to push the group
+	 * back over target. E.g. if currently throttling to 30% of bandwidth
+	 * on a system with 10% granularity steps, check whether moving to
+	 * 40% would go past the limit by multiplying current bandwidth by
+	 * "(30 + 10) / 30".
+	 */
+	if (cur_msr_val > r_mba->membw.min_bw && user_bw < cur_bw) {
+		new_msr_val = cur_msr_val - r_mba->membw.bw_gran;
+	} else if (cur_msr_val < MAX_MBA_BW &&
+		   (user_bw > (cur_bw * (cur_msr_val + r_mba->membw.min_bw) / cur_msr_val))) {
+		new_msr_val = cur_msr_val + r_mba->membw.bw_gran;
+	} else {
+		return;
+	}
+
+	resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val);
+}
+
+static void mbm_update_one_event(struct rdt_resource *r, struct rdt_mon_domain *d,
+				 u32 closid, u32 rmid, enum resctrl_event_id evtid)
+{
+	struct rmid_read rr = {0};
+
+	rr.r = r;
+	rr.d = d;
+	rr.evtid = evtid;
+	rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
+	if (IS_ERR(rr.arch_mon_ctx)) {
+		pr_warn_ratelimited("Failed to allocate monitor context: %ld",
+				    PTR_ERR(rr.arch_mon_ctx));
+		return;
+	}
+
+	__mon_event_count(closid, rmid, &rr);
+
+	/*
+	 * If the software controller is enabled, compute the
+	 * bandwidth for this event id.
+	 */
+	if (is_mba_sc(NULL))
+		mbm_bw_count(closid, rmid, &rr);
+
+	resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
+}
+
+static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d,
+		       u32 closid, u32 rmid)
+{
+	/*
+	 * This is protected from concurrent reads from user as both
+	 * the user and overflow handler hold the global mutex.
+	 */
+	if (resctrl_arch_is_mbm_total_enabled())
+		mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_TOTAL_EVENT_ID);
+
+	if (resctrl_arch_is_mbm_local_enabled())
+		mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_LOCAL_EVENT_ID);
+}
+
+/*
+ * Handler to scan the limbo list and move the RMIDs
+ * to free list whose occupancy < threshold_occupancy.
+ */
+void cqm_handle_limbo(struct work_struct *work)
+{
+	unsigned long delay = msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL);
+	struct rdt_mon_domain *d;
+
+	cpus_read_lock();
+	mutex_lock(&rdtgroup_mutex);
+
+	d = container_of(work, struct rdt_mon_domain, cqm_limbo.work);
+
+	__check_limbo(d, false);
+
+	if (has_busy_rmid(d)) {
+		d->cqm_work_cpu = cpumask_any_housekeeping(&d->hdr.cpu_mask,
+							   RESCTRL_PICK_ANY_CPU);
+		schedule_delayed_work_on(d->cqm_work_cpu, &d->cqm_limbo,
+					 delay);
+	}
+
+	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
+}
+
+/**
+ * cqm_setup_limbo_handler() - Schedule the limbo handler to run for this
+ *                             domain.
+ * @dom:           The domain the limbo handler should run for.
+ * @delay_ms:      How far in the future the handler should run.
+ * @exclude_cpu:   Which CPU the handler should not run on,
+ *		   RESCTRL_PICK_ANY_CPU to pick any CPU.
+ */
+void cqm_setup_limbo_handler(struct rdt_mon_domain *dom, unsigned long delay_ms,
+			     int exclude_cpu)
+{
+	unsigned long delay = msecs_to_jiffies(delay_ms);
+	int cpu;
+
+	cpu = cpumask_any_housekeeping(&dom->hdr.cpu_mask, exclude_cpu);
+	dom->cqm_work_cpu = cpu;
+
+	if (cpu < nr_cpu_ids)
+		schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay);
+}
+
+void mbm_handle_overflow(struct work_struct *work)
+{
+	unsigned long delay = msecs_to_jiffies(MBM_OVERFLOW_INTERVAL);
+	struct rdtgroup *prgrp, *crgrp;
+	struct rdt_mon_domain *d;
+	struct list_head *head;
+	struct rdt_resource *r;
+
+	cpus_read_lock();
+	mutex_lock(&rdtgroup_mutex);
+
+	/*
+	 * If the filesystem has been unmounted this work no longer needs to
+	 * run.
+	 */
+	if (!resctrl_mounted || !resctrl_arch_mon_capable())
+		goto out_unlock;
+
+	r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
+	d = container_of(work, struct rdt_mon_domain, mbm_over.work);
+
+	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
+		mbm_update(r, d, prgrp->closid, prgrp->mon.rmid);
+
+		head = &prgrp->mon.crdtgrp_list;
+		list_for_each_entry(crgrp, head, mon.crdtgrp_list)
+			mbm_update(r, d, crgrp->closid, crgrp->mon.rmid);
+
+		if (is_mba_sc(NULL))
+			update_mba_bw(prgrp, d);
+	}
+
+	/*
+	 * Re-check for housekeeping CPUs. This allows the overflow handler to
+	 * move off a nohz_full CPU quickly.
+	 */
+	d->mbm_work_cpu = cpumask_any_housekeeping(&d->hdr.cpu_mask,
+						   RESCTRL_PICK_ANY_CPU);
+	schedule_delayed_work_on(d->mbm_work_cpu, &d->mbm_over, delay);
+
+out_unlock:
+	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
+}
+
+/**
+ * mbm_setup_overflow_handler() - Schedule the overflow handler to run for this
+ *                                domain.
+ * @dom:           The domain the overflow handler should run for.
+ * @delay_ms:      How far in the future the handler should run.
+ * @exclude_cpu:   Which CPU the handler should not run on,
+ *		   RESCTRL_PICK_ANY_CPU to pick any CPU.
+ */
+void mbm_setup_overflow_handler(struct rdt_mon_domain *dom, unsigned long delay_ms,
+				int exclude_cpu)
+{
+	unsigned long delay = msecs_to_jiffies(delay_ms);
+	int cpu;
+
+	/*
+	 * When a domain comes online there is no guarantee the filesystem is
+	 * mounted. If not, there is no need to catch counter overflow.
+	 */
+	if (!resctrl_mounted || !resctrl_arch_mon_capable())
+		return;
+	cpu = cpumask_any_housekeeping(&dom->hdr.cpu_mask, exclude_cpu);
+	dom->mbm_work_cpu = cpu;
+
+	if (cpu < nr_cpu_ids)
+		schedule_delayed_work_on(cpu, &dom->mbm_over, delay);
+}
+
+static int dom_data_init(struct rdt_resource *r)
+{
+	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
+	u32 num_closid = resctrl_arch_get_num_closid(r);
+	struct rmid_entry *entry = NULL;
+	int err = 0, i;
+	u32 idx;
+
+	mutex_lock(&rdtgroup_mutex);
+	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
+		u32 *tmp;
+
+		/*
+		 * If the architecture hasn't provided a sanitised value here,
+		 * this may result in larger arrays than necessary. Resctrl will
+		 * use a smaller system wide value based on the resources in
+		 * use.
+		 */
+		tmp = kcalloc(num_closid, sizeof(*tmp), GFP_KERNEL);
+		if (!tmp) {
+			err = -ENOMEM;
+			goto out_unlock;
+		}
+
+		closid_num_dirty_rmid = tmp;
+	}
+
+	rmid_ptrs = kcalloc(idx_limit, sizeof(struct rmid_entry), GFP_KERNEL);
+	if (!rmid_ptrs) {
+		if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
+			kfree(closid_num_dirty_rmid);
+			closid_num_dirty_rmid = NULL;
+		}
+		err = -ENOMEM;
+		goto out_unlock;
+	}
+
+	for (i = 0; i < idx_limit; i++) {
+		entry = &rmid_ptrs[i];
+		INIT_LIST_HEAD(&entry->list);
+
+		resctrl_arch_rmid_idx_decode(i, &entry->closid, &entry->rmid);
+		list_add_tail(&entry->list, &rmid_free_lru);
+	}
+
+	/*
+	 * RESCTRL_RESERVED_CLOSID and RESCTRL_RESERVED_RMID are special and
+	 * are always allocated. These are used for the rdtgroup_default
+	 * control group, which will be setup later in resctrl_init().
+	 */
+	idx = resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID,
+					   RESCTRL_RESERVED_RMID);
+	entry = __rmid_entry(idx);
+	list_del(&entry->list);
+
+out_unlock:
+	mutex_unlock(&rdtgroup_mutex);
+
+	return err;
+}
+
+static void dom_data_exit(struct rdt_resource *r)
+{
+	mutex_lock(&rdtgroup_mutex);
+
+	if (!r->mon_capable)
+		goto out_unlock;
+
+	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
+		kfree(closid_num_dirty_rmid);
+		closid_num_dirty_rmid = NULL;
+	}
+
+	kfree(rmid_ptrs);
+	rmid_ptrs = NULL;
+
+out_unlock:
+	mutex_unlock(&rdtgroup_mutex);
+}
+
+static struct mon_evt llc_occupancy_event = {
+	.name		= "llc_occupancy",
+	.evtid		= QOS_L3_OCCUP_EVENT_ID,
+};
+
+static struct mon_evt mbm_total_event = {
+	.name		= "mbm_total_bytes",
+	.evtid		= QOS_L3_MBM_TOTAL_EVENT_ID,
+};
+
+static struct mon_evt mbm_local_event = {
+	.name		= "mbm_local_bytes",
+	.evtid		= QOS_L3_MBM_LOCAL_EVENT_ID,
+};
+
+/*
+ * Initialize the event list for the resource.
+ *
+ * Note that MBM events are also part of RDT_RESOURCE_L3 resource
+ * because as per the SDM the total and local memory bandwidth
+ * are enumerated as part of L3 monitoring.
+ */
+static void l3_mon_evt_init(struct rdt_resource *r)
+{
+	INIT_LIST_HEAD(&r->evt_list);
+
+	if (resctrl_arch_is_llc_occupancy_enabled())
+		list_add_tail(&llc_occupancy_event.list, &r->evt_list);
+	if (resctrl_arch_is_mbm_total_enabled())
+		list_add_tail(&mbm_total_event.list, &r->evt_list);
+	if (resctrl_arch_is_mbm_local_enabled())
+		list_add_tail(&mbm_local_event.list, &r->evt_list);
+}
+
+/**
+ * resctrl_mon_resource_init() - Initialise global monitoring structures.
+ *
+ * Allocate and initialise global monitor resources that do not belong to a
+ * specific domain. i.e. the rmid_ptrs[] used for the limbo and free lists.
+ * Called once during boot after the struct rdt_resource's have been configured
+ * but before the filesystem is mounted.
+ * Resctrl's cpuhp callbacks may be called before this point to bring a domain
+ * online.
+ *
+ * Returns 0 for success, or -ENOMEM.
+ */
+int resctrl_mon_resource_init(void)
+{
+	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
+	int ret;
+
+	if (!r->mon_capable)
+		return 0;
+
+	ret = dom_data_init(r);
+	if (ret)
+		return ret;
+
+	l3_mon_evt_init(r);
+
+	if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_TOTAL_EVENT_ID)) {
+		mbm_total_event.configurable = true;
+		resctrl_file_fflags_init("mbm_total_bytes_config",
+					 RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
+	}
+	if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_LOCAL_EVENT_ID)) {
+		mbm_local_event.configurable = true;
+		resctrl_file_fflags_init("mbm_local_bytes_config",
+					 RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
+	}
+
+	if (resctrl_arch_is_mbm_local_enabled())
+		mba_mbps_default_event = QOS_L3_MBM_LOCAL_EVENT_ID;
+	else if (resctrl_arch_is_mbm_total_enabled())
+		mba_mbps_default_event = QOS_L3_MBM_TOTAL_EVENT_ID;
+
+	return 0;
+}
+
+void resctrl_mon_resource_exit(void)
+{
+	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
+
+	dom_data_exit(r);
+}
diff --git a/fs/resctrl/monitor_trace.h b/fs/resctrl/monitor_trace.h
index e69de29bb2d1d..fdf49f22576a9 100644
--- a/fs/resctrl/monitor_trace.h
+++ b/fs/resctrl/monitor_trace.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM resctrl
+
+#if !defined(_FS_RESCTRL_MONITOR_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _FS_RESCTRL_MONITOR_TRACE_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(mon_llc_occupancy_limbo,
+	    TP_PROTO(u32 ctrl_hw_id, u32 mon_hw_id, int domain_id, u64 llc_occupancy_bytes),
+	    TP_ARGS(ctrl_hw_id, mon_hw_id, domain_id, llc_occupancy_bytes),
+	    TP_STRUCT__entry(__field(u32, ctrl_hw_id)
+			     __field(u32, mon_hw_id)
+			     __field(int, domain_id)
+			     __field(u64, llc_occupancy_bytes)),
+	    TP_fast_assign(__entry->ctrl_hw_id = ctrl_hw_id;
+			   __entry->mon_hw_id = mon_hw_id;
+			   __entry->domain_id = domain_id;
+			   __entry->llc_occupancy_bytes = llc_occupancy_bytes;),
+	    TP_printk("ctrl_hw_id=%u mon_hw_id=%u domain_id=%d llc_occupancy_bytes=%llu",
+		      __entry->ctrl_hw_id, __entry->mon_hw_id, __entry->domain_id,
+		      __entry->llc_occupancy_bytes)
+	   );
+
+#endif /* _FS_RESCTRL_MONITOR_TRACE_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+
+#define TRACE_INCLUDE_FILE monitor_trace
+
+#include <trace/define_trace.h>
diff --git a/fs/resctrl/pseudo_lock.c b/fs/resctrl/pseudo_lock.c
index e69de29bb2d1d..5bbeb8416fa6b 100644
--- a/fs/resctrl/pseudo_lock.c
+++ b/fs/resctrl/pseudo_lock.c
@@ -0,0 +1,1106 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Resource Director Technology (RDT)
+ *
+ * Pseudo-locking support built on top of Cache Allocation Technology (CAT)
+ *
+ * Copyright (C) 2018 Intel Corporation
+ *
+ * Author: Reinette Chatre <reinette.chatre@intel.com>
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/cacheinfo.h>
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/debugfs.h>
+#include <linux/kthread.h>
+#include <linux/mman.h>
+#include <linux/pm_qos.h>
+#include <linux/resctrl.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+
+#include "internal.h"
+
+/*
+ * Major number assigned to and shared by all devices exposing
+ * pseudo-locked regions.
+ */
+static unsigned int pseudo_lock_major;
+
+static unsigned long pseudo_lock_minor_avail = GENMASK(MINORBITS, 0);
+
+static char *pseudo_lock_devnode(const struct device *dev, umode_t *mode)
+{
+	const struct rdtgroup *rdtgrp;
+
+	rdtgrp = dev_get_drvdata(dev);
+	if (mode)
+		*mode = 0600;
+	guard(mutex)(&rdtgroup_mutex);
+	return kasprintf(GFP_KERNEL, "pseudo_lock/%s", rdt_kn_name(rdtgrp->kn));
+}
+
+static const struct class pseudo_lock_class = {
+	.name = "pseudo_lock",
+	.devnode = pseudo_lock_devnode,
+};
+
+/**
+ * pseudo_lock_minor_get - Obtain available minor number
+ * @minor: Pointer to where new minor number will be stored
+ *
+ * A bitmask is used to track available minor numbers. Here the next free
+ * minor number is marked as unavailable and returned.
+ *
+ * Return: 0 on success, <0 on failure.
+ */
+static int pseudo_lock_minor_get(unsigned int *minor)
+{
+	unsigned long first_bit;
+
+	first_bit = find_first_bit(&pseudo_lock_minor_avail, MINORBITS);
+
+	if (first_bit == MINORBITS)
+		return -ENOSPC;
+
+	__clear_bit(first_bit, &pseudo_lock_minor_avail);
+	*minor = first_bit;
+
+	return 0;
+}
+
+/**
+ * pseudo_lock_minor_release - Return minor number to available
+ * @minor: The minor number made available
+ */
+static void pseudo_lock_minor_release(unsigned int minor)
+{
+	__set_bit(minor, &pseudo_lock_minor_avail);
+}
+
+/**
+ * region_find_by_minor - Locate a pseudo-lock region by inode minor number
+ * @minor: The minor number of the device representing pseudo-locked region
+ *
+ * When the character device is accessed we need to determine which
+ * pseudo-locked region it belongs to. This is done by matching the minor
+ * number of the device to the pseudo-locked region it belongs.
+ *
+ * Minor numbers are assigned at the time a pseudo-locked region is associated
+ * with a cache instance.
+ *
+ * Return: On success return pointer to resource group owning the pseudo-locked
+ *         region, NULL on failure.
+ */
+static struct rdtgroup *region_find_by_minor(unsigned int minor)
+{
+	struct rdtgroup *rdtgrp, *rdtgrp_match = NULL;
+
+	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
+		if (rdtgrp->plr && rdtgrp->plr->minor == minor) {
+			rdtgrp_match = rdtgrp;
+			break;
+		}
+	}
+	return rdtgrp_match;
+}
+
+/**
+ * struct pseudo_lock_pm_req - A power management QoS request list entry
+ * @list:	Entry within the @pm_reqs list for a pseudo-locked region
+ * @req:	PM QoS request
+ */
+struct pseudo_lock_pm_req {
+	struct list_head list;
+	struct dev_pm_qos_request req;
+};
+
+static void pseudo_lock_cstates_relax(struct pseudo_lock_region *plr)
+{
+	struct pseudo_lock_pm_req *pm_req, *next;
+
+	list_for_each_entry_safe(pm_req, next, &plr->pm_reqs, list) {
+		dev_pm_qos_remove_request(&pm_req->req);
+		list_del(&pm_req->list);
+		kfree(pm_req);
+	}
+}
+
+/**
+ * pseudo_lock_cstates_constrain - Restrict cores from entering C6
+ * @plr: Pseudo-locked region
+ *
+ * To prevent the cache from being affected by power management entering
+ * C6 has to be avoided. This is accomplished by requesting a latency
+ * requirement lower than lowest C6 exit latency of all supported
+ * platforms as found in the cpuidle state tables in the intel_idle driver.
+ * At this time it is possible to do so with a single latency requirement
+ * for all supported platforms.
+ *
+ * Since Goldmont is supported, which is affected by X86_BUG_MONITOR,
+ * the ACPI latencies need to be considered while keeping in mind that C2
+ * may be set to map to deeper sleep states. In this case the latency
+ * requirement needs to prevent entering C2 also.
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static int pseudo_lock_cstates_constrain(struct pseudo_lock_region *plr)
+{
+	struct pseudo_lock_pm_req *pm_req;
+	int cpu;
+	int ret;
+
+	for_each_cpu(cpu, &plr->d->hdr.cpu_mask) {
+		pm_req = kzalloc(sizeof(*pm_req), GFP_KERNEL);
+		if (!pm_req) {
+			rdt_last_cmd_puts("Failure to allocate memory for PM QoS\n");
+			ret = -ENOMEM;
+			goto out_err;
+		}
+		ret = dev_pm_qos_add_request(get_cpu_device(cpu),
+					     &pm_req->req,
+					     DEV_PM_QOS_RESUME_LATENCY,
+					     30);
+		if (ret < 0) {
+			rdt_last_cmd_printf("Failed to add latency req CPU%d\n",
+					    cpu);
+			kfree(pm_req);
+			ret = -1;
+			goto out_err;
+		}
+		list_add(&pm_req->list, &plr->pm_reqs);
+	}
+
+	return 0;
+
+out_err:
+	pseudo_lock_cstates_relax(plr);
+	return ret;
+}
+
+/**
+ * pseudo_lock_region_clear - Reset pseudo-lock region data
+ * @plr: pseudo-lock region
+ *
+ * All content of the pseudo-locked region is reset - any memory allocated
+ * freed.
+ *
+ * Return: void
+ */
+static void pseudo_lock_region_clear(struct pseudo_lock_region *plr)
+{
+	plr->size = 0;
+	plr->line_size = 0;
+	kfree(plr->kmem);
+	plr->kmem = NULL;
+	plr->s = NULL;
+	if (plr->d)
+		plr->d->plr = NULL;
+	plr->d = NULL;
+	plr->cbm = 0;
+	plr->debugfs_dir = NULL;
+}
+
+/**
+ * pseudo_lock_region_init - Initialize pseudo-lock region information
+ * @plr: pseudo-lock region
+ *
+ * Called after user provided a schemata to be pseudo-locked. From the
+ * schemata the &struct pseudo_lock_region is on entry already initialized
+ * with the resource, domain, and capacity bitmask. Here the information
+ * required for pseudo-locking is deduced from this data and &struct
+ * pseudo_lock_region initialized further. This information includes:
+ * - size in bytes of the region to be pseudo-locked
+ * - cache line size to know the stride with which data needs to be accessed
+ *   to be pseudo-locked
+ * - a cpu associated with the cache instance on which the pseudo-locking
+ *   flow can be executed
+ *
+ * Return: 0 on success, <0 on failure. Descriptive error will be written
+ * to last_cmd_status buffer.
+ */
+static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
+{
+	enum resctrl_scope scope = plr->s->res->ctrl_scope;
+	struct cacheinfo *ci;
+	int ret;
+
+	if (WARN_ON_ONCE(scope != RESCTRL_L2_CACHE && scope != RESCTRL_L3_CACHE))
+		return -ENODEV;
+
+	/* Pick the first cpu we find that is associated with the cache. */
+	plr->cpu = cpumask_first(&plr->d->hdr.cpu_mask);
+
+	if (!cpu_online(plr->cpu)) {
+		rdt_last_cmd_printf("CPU %u associated with cache not online\n",
+				    plr->cpu);
+		ret = -ENODEV;
+		goto out_region;
+	}
+
+	ci = get_cpu_cacheinfo_level(plr->cpu, scope);
+	if (ci) {
+		plr->line_size = ci->coherency_line_size;
+		plr->size = rdtgroup_cbm_to_size(plr->s->res, plr->d, plr->cbm);
+		return 0;
+	}
+
+	ret = -1;
+	rdt_last_cmd_puts("Unable to determine cache line size\n");
+out_region:
+	pseudo_lock_region_clear(plr);
+	return ret;
+}
+
+/**
+ * pseudo_lock_init - Initialize a pseudo-lock region
+ * @rdtgrp: resource group to which new pseudo-locked region will belong
+ *
+ * A pseudo-locked region is associated with a resource group. When this
+ * association is created the pseudo-locked region is initialized. The
+ * details of the pseudo-locked region are not known at this time so only
+ * allocation is done and association established.
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static int pseudo_lock_init(struct rdtgroup *rdtgrp)
+{
+	struct pseudo_lock_region *plr;
+
+	plr = kzalloc(sizeof(*plr), GFP_KERNEL);
+	if (!plr)
+		return -ENOMEM;
+
+	init_waitqueue_head(&plr->lock_thread_wq);
+	INIT_LIST_HEAD(&plr->pm_reqs);
+	rdtgrp->plr = plr;
+	return 0;
+}
+
+/**
+ * pseudo_lock_region_alloc - Allocate kernel memory that will be pseudo-locked
+ * @plr: pseudo-lock region
+ *
+ * Initialize the details required to set up the pseudo-locked region and
+ * allocate the contiguous memory that will be pseudo-locked to the cache.
+ *
+ * Return: 0 on success, <0 on failure.  Descriptive error will be written
+ * to last_cmd_status buffer.
+ */
+static int pseudo_lock_region_alloc(struct pseudo_lock_region *plr)
+{
+	int ret;
+
+	ret = pseudo_lock_region_init(plr);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * We do not yet support contiguous regions larger than
+	 * KMALLOC_MAX_SIZE.
+	 */
+	if (plr->size > KMALLOC_MAX_SIZE) {
+		rdt_last_cmd_puts("Requested region exceeds maximum size\n");
+		ret = -E2BIG;
+		goto out_region;
+	}
+
+	plr->kmem = kzalloc(plr->size, GFP_KERNEL);
+	if (!plr->kmem) {
+		rdt_last_cmd_puts("Unable to allocate memory\n");
+		ret = -ENOMEM;
+		goto out_region;
+	}
+
+	ret = 0;
+	goto out;
+out_region:
+	pseudo_lock_region_clear(plr);
+out:
+	return ret;
+}
+
+/**
+ * pseudo_lock_free - Free a pseudo-locked region
+ * @rdtgrp: resource group to which pseudo-locked region belonged
+ *
+ * The pseudo-locked region's resources have already been released, or not
+ * yet created at this point. Now it can be freed and disassociated from the
+ * resource group.
+ *
+ * Return: void
+ */
+static void pseudo_lock_free(struct rdtgroup *rdtgrp)
+{
+	pseudo_lock_region_clear(rdtgrp->plr);
+	kfree(rdtgrp->plr);
+	rdtgrp->plr = NULL;
+}
+
+/**
+ * rdtgroup_monitor_in_progress - Test if monitoring in progress
+ * @rdtgrp: resource group being queried
+ *
+ * Return: 1 if monitor groups have been created for this resource
+ * group, 0 otherwise.
+ */
+static int rdtgroup_monitor_in_progress(struct rdtgroup *rdtgrp)
+{
+	return !list_empty(&rdtgrp->mon.crdtgrp_list);
+}
+
+/**
+ * rdtgroup_locksetup_user_restrict - Restrict user access to group
+ * @rdtgrp: resource group needing access restricted
+ *
+ * A resource group used for cache pseudo-locking cannot have cpus or tasks
+ * assigned to it. This is communicated to the user by restricting access
+ * to all the files that can be used to make such changes.
+ *
+ * Permissions restored with rdtgroup_locksetup_user_restore()
+ *
+ * Return: 0 on success, <0 on failure. If a failure occurs during the
+ * restriction of access an attempt will be made to restore permissions but
+ * the state of the mode of these files will be uncertain when a failure
+ * occurs.
+ */
+static int rdtgroup_locksetup_user_restrict(struct rdtgroup *rdtgrp)
+{
+	int ret;
+
+	ret = rdtgroup_kn_mode_restrict(rdtgrp, "tasks");
+	if (ret)
+		return ret;
+
+	ret = rdtgroup_kn_mode_restrict(rdtgrp, "cpus");
+	if (ret)
+		goto err_tasks;
+
+	ret = rdtgroup_kn_mode_restrict(rdtgrp, "cpus_list");
+	if (ret)
+		goto err_cpus;
+
+	if (resctrl_arch_mon_capable()) {
+		ret = rdtgroup_kn_mode_restrict(rdtgrp, "mon_groups");
+		if (ret)
+			goto err_cpus_list;
+	}
+
+	ret = 0;
+	goto out;
+
+err_cpus_list:
+	rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0777);
+err_cpus:
+	rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0777);
+err_tasks:
+	rdtgroup_kn_mode_restore(rdtgrp, "tasks", 0777);
+out:
+	return ret;
+}
+
+/**
+ * rdtgroup_locksetup_user_restore - Restore user access to group
+ * @rdtgrp: resource group needing access restored
+ *
+ * Restore all file access previously removed using
+ * rdtgroup_locksetup_user_restrict()
+ *
+ * Return: 0 on success, <0 on failure.  If a failure occurs during the
+ * restoration of access an attempt will be made to restrict permissions
+ * again but the state of the mode of these files will be uncertain when
+ * a failure occurs.
+ */
+static int rdtgroup_locksetup_user_restore(struct rdtgroup *rdtgrp)
+{
+	int ret;
+
+	ret = rdtgroup_kn_mode_restore(rdtgrp, "tasks", 0777);
+	if (ret)
+		return ret;
+
+	ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0777);
+	if (ret)
+		goto err_tasks;
+
+	ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0777);
+	if (ret)
+		goto err_cpus;
+
+	if (resctrl_arch_mon_capable()) {
+		ret = rdtgroup_kn_mode_restore(rdtgrp, "mon_groups", 0777);
+		if (ret)
+			goto err_cpus_list;
+	}
+
+	ret = 0;
+	goto out;
+
+err_cpus_list:
+	rdtgroup_kn_mode_restrict(rdtgrp, "cpus_list");
+err_cpus:
+	rdtgroup_kn_mode_restrict(rdtgrp, "cpus");
+err_tasks:
+	rdtgroup_kn_mode_restrict(rdtgrp, "tasks");
+out:
+	return ret;
+}
+
+/**
+ * rdtgroup_locksetup_enter - Resource group enters locksetup mode
+ * @rdtgrp: resource group requested to enter locksetup mode
+ *
+ * A resource group enters locksetup mode to reflect that it would be used
+ * to represent a pseudo-locked region and is in the process of being set
+ * up to do so. A resource group used for a pseudo-locked region would
+ * lose the closid associated with it so we cannot allow it to have any
+ * tasks or cpus assigned nor permit tasks or cpus to be assigned in the
+ * future. Monitoring of a pseudo-locked region is not allowed either.
+ *
+ * The above and more restrictions on a pseudo-locked region are checked
+ * for and enforced before the resource group enters the locksetup mode.
+ *
+ * Returns: 0 if the resource group successfully entered locksetup mode, <0
+ * on failure. On failure the last_cmd_status buffer is updated with text to
+ * communicate details of failure to the user.
+ */
+int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp)
+{
+	int ret;
+
+	/*
+	 * The default resource group can neither be removed nor lose the
+	 * default closid associated with it.
+	 */
+	if (rdtgrp == &rdtgroup_default) {
+		rdt_last_cmd_puts("Cannot pseudo-lock default group\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Cache Pseudo-locking not supported when CDP is enabled.
+	 *
+	 * Some things to consider if you would like to enable this
+	 * support (using L3 CDP as example):
+	 * - When CDP is enabled two separate resources are exposed,
+	 *   L3DATA and L3CODE, but they are actually on the same cache.
+	 *   The implication for pseudo-locking is that if a
+	 *   pseudo-locked region is created on a domain of one
+	 *   resource (eg. L3CODE), then a pseudo-locked region cannot
+	 *   be created on that same domain of the other resource
+	 *   (eg. L3DATA). This is because the creation of a
+	 *   pseudo-locked region involves a call to wbinvd that will
+	 *   affect all cache allocations on particular domain.
+	 * - Considering the previous, it may be possible to only
+	 *   expose one of the CDP resources to pseudo-locking and
+	 *   hide the other. For example, we could consider to only
+	 *   expose L3DATA and since the L3 cache is unified it is
+	 *   still possible to place instructions there are execute it.
+	 * - If only one region is exposed to pseudo-locking we should
+	 *   still keep in mind that availability of a portion of cache
+	 *   for pseudo-locking should take into account both resources.
+	 *   Similarly, if a pseudo-locked region is created in one
+	 *   resource, the portion of cache used by it should be made
+	 *   unavailable to all future allocations from both resources.
+	 */
+	if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3) ||
+	    resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2)) {
+		rdt_last_cmd_puts("CDP enabled\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Not knowing the bits to disable prefetching implies that this
+	 * platform does not support Cache Pseudo-Locking.
+	 */
+	if (resctrl_arch_get_prefetch_disable_bits() == 0) {
+		rdt_last_cmd_puts("Pseudo-locking not supported\n");
+		return -EINVAL;
+	}
+
+	if (rdtgroup_monitor_in_progress(rdtgrp)) {
+		rdt_last_cmd_puts("Monitoring in progress\n");
+		return -EINVAL;
+	}
+
+	if (rdtgroup_tasks_assigned(rdtgrp)) {
+		rdt_last_cmd_puts("Tasks assigned to resource group\n");
+		return -EINVAL;
+	}
+
+	if (!cpumask_empty(&rdtgrp->cpu_mask)) {
+		rdt_last_cmd_puts("CPUs assigned to resource group\n");
+		return -EINVAL;
+	}
+
+	if (rdtgroup_locksetup_user_restrict(rdtgrp)) {
+		rdt_last_cmd_puts("Unable to modify resctrl permissions\n");
+		return -EIO;
+	}
+
+	ret = pseudo_lock_init(rdtgrp);
+	if (ret) {
+		rdt_last_cmd_puts("Unable to init pseudo-lock region\n");
+		goto out_release;
+	}
+
+	/*
+	 * If this system is capable of monitoring a rmid would have been
+	 * allocated when the control group was created. This is not needed
+	 * anymore when this group would be used for pseudo-locking. This
+	 * is safe to call on platforms not capable of monitoring.
+	 */
+	free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
+
+	ret = 0;
+	goto out;
+
+out_release:
+	rdtgroup_locksetup_user_restore(rdtgrp);
+out:
+	return ret;
+}
+
+/**
+ * rdtgroup_locksetup_exit - resource group exist locksetup mode
+ * @rdtgrp: resource group
+ *
+ * When a resource group exits locksetup mode the earlier restrictions are
+ * lifted.
+ *
+ * Return: 0 on success, <0 on failure
+ */
+int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
+{
+	int ret;
+
+	if (resctrl_arch_mon_capable()) {
+		ret = alloc_rmid(rdtgrp->closid);
+		if (ret < 0) {
+			rdt_last_cmd_puts("Out of RMIDs\n");
+			return ret;
+		}
+		rdtgrp->mon.rmid = ret;
+	}
+
+	ret = rdtgroup_locksetup_user_restore(rdtgrp);
+	if (ret) {
+		free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
+		return ret;
+	}
+
+	pseudo_lock_free(rdtgrp);
+	return 0;
+}
+
+/**
+ * rdtgroup_cbm_overlaps_pseudo_locked - Test if CBM or portion is pseudo-locked
+ * @d: RDT domain
+ * @cbm: CBM to test
+ *
+ * @d represents a cache instance and @cbm a capacity bitmask that is
+ * considered for it. Determine if @cbm overlaps with any existing
+ * pseudo-locked region on @d.
+ *
+ * @cbm is unsigned long, even if only 32 bits are used, to make the
+ * bitmap functions work correctly.
+ *
+ * Return: true if @cbm overlaps with pseudo-locked region on @d, false
+ * otherwise.
+ */
+bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm)
+{
+	unsigned int cbm_len;
+	unsigned long cbm_b;
+
+	if (d->plr) {
+		cbm_len = d->plr->s->res->cache.cbm_len;
+		cbm_b = d->plr->cbm;
+		if (bitmap_intersects(&cbm, &cbm_b, cbm_len))
+			return true;
+	}
+	return false;
+}
+
+/**
+ * rdtgroup_pseudo_locked_in_hierarchy - Pseudo-locked region in cache hierarchy
+ * @d: RDT domain under test
+ *
+ * The setup of a pseudo-locked region affects all cache instances within
+ * the hierarchy of the region. It is thus essential to know if any
+ * pseudo-locked regions exist within a cache hierarchy to prevent any
+ * attempts to create new pseudo-locked regions in the same hierarchy.
+ *
+ * Return: true if a pseudo-locked region exists in the hierarchy of @d or
+ *         if it is not possible to test due to memory allocation issue,
+ *         false otherwise.
+ */
+bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d)
+{
+	struct rdt_ctrl_domain *d_i;
+	cpumask_var_t cpu_with_psl;
+	struct rdt_resource *r;
+	bool ret = false;
+
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
+	if (!zalloc_cpumask_var(&cpu_with_psl, GFP_KERNEL))
+		return true;
+
+	/*
+	 * First determine which cpus have pseudo-locked regions
+	 * associated with them.
+	 */
+	for_each_alloc_capable_rdt_resource(r) {
+		list_for_each_entry(d_i, &r->ctrl_domains, hdr.list) {
+			if (d_i->plr)
+				cpumask_or(cpu_with_psl, cpu_with_psl,
+					   &d_i->hdr.cpu_mask);
+		}
+	}
+
+	/*
+	 * Next test if new pseudo-locked region would intersect with
+	 * existing region.
+	 */
+	if (cpumask_intersects(&d->hdr.cpu_mask, cpu_with_psl))
+		ret = true;
+
+	free_cpumask_var(cpu_with_psl);
+	return ret;
+}
+
+/**
+ * pseudo_lock_measure_cycles - Trigger latency measure to pseudo-locked region
+ * @rdtgrp: Resource group to which the pseudo-locked region belongs.
+ * @sel: Selector of which measurement to perform on a pseudo-locked region.
+ *
+ * The measurement of latency to access a pseudo-locked region should be
+ * done from a cpu that is associated with that pseudo-locked region.
+ * Determine which cpu is associated with this region and start a thread on
+ * that cpu to perform the measurement, wait for that thread to complete.
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
+{
+	struct pseudo_lock_region *plr = rdtgrp->plr;
+	struct task_struct *thread;
+	unsigned int cpu;
+	int ret = -1;
+
+	cpus_read_lock();
+	mutex_lock(&rdtgroup_mutex);
+
+	if (rdtgrp->flags & RDT_DELETED) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	if (!plr->d) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	plr->thread_done = 0;
+	cpu = cpumask_first(&plr->d->hdr.cpu_mask);
+	if (!cpu_online(cpu)) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	plr->cpu = cpu;
+
+	if (sel == 1)
+		thread = kthread_run_on_cpu(resctrl_arch_measure_cycles_lat_fn,
+					    plr, cpu, "pseudo_lock_measure/%u");
+	else if (sel == 2)
+		thread = kthread_run_on_cpu(resctrl_arch_measure_l2_residency,
+					    plr, cpu, "pseudo_lock_measure/%u");
+	else if (sel == 3)
+		thread = kthread_run_on_cpu(resctrl_arch_measure_l3_residency,
+					    plr, cpu, "pseudo_lock_measure/%u");
+	else
+		goto out;
+
+	if (IS_ERR(thread)) {
+		ret = PTR_ERR(thread);
+		goto out;
+	}
+
+	ret = wait_event_interruptible(plr->lock_thread_wq,
+				       plr->thread_done == 1);
+	if (ret < 0)
+		goto out;
+
+	ret = 0;
+
+out:
+	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
+	return ret;
+}
+
+static ssize_t pseudo_lock_measure_trigger(struct file *file,
+					   const char __user *user_buf,
+					   size_t count, loff_t *ppos)
+{
+	struct rdtgroup *rdtgrp = file->private_data;
+	size_t buf_size;
+	char buf[32];
+	int ret;
+	int sel;
+
+	buf_size = min(count, (sizeof(buf) - 1));
+	if (copy_from_user(buf, user_buf, buf_size))
+		return -EFAULT;
+
+	buf[buf_size] = '\0';
+	ret = kstrtoint(buf, 10, &sel);
+	if (ret == 0) {
+		if (sel != 1 && sel != 2 && sel != 3)
+			return -EINVAL;
+		ret = debugfs_file_get(file->f_path.dentry);
+		if (ret)
+			return ret;
+		ret = pseudo_lock_measure_cycles(rdtgrp, sel);
+		if (ret == 0)
+			ret = count;
+		debugfs_file_put(file->f_path.dentry);
+	}
+
+	return ret;
+}
+
+static const struct file_operations pseudo_measure_fops = {
+	.write = pseudo_lock_measure_trigger,
+	.open = simple_open,
+	.llseek = default_llseek,
+};
+
+/**
+ * rdtgroup_pseudo_lock_create - Create a pseudo-locked region
+ * @rdtgrp: resource group to which pseudo-lock region belongs
+ *
+ * Called when a resource group in the pseudo-locksetup mode receives a
+ * valid schemata that should be pseudo-locked. Since the resource group is
+ * in pseudo-locksetup mode the &struct pseudo_lock_region has already been
+ * allocated and initialized with the essential information. If a failure
+ * occurs the resource group remains in the pseudo-locksetup mode with the
+ * &struct pseudo_lock_region associated with it, but cleared from all
+ * information and ready for the user to re-attempt pseudo-locking by
+ * writing the schemata again.
+ *
+ * Return: 0 if the pseudo-locked region was successfully pseudo-locked, <0
+ * on failure. Descriptive error will be written to last_cmd_status buffer.
+ */
+int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
+{
+	struct pseudo_lock_region *plr = rdtgrp->plr;
+	struct task_struct *thread;
+	unsigned int new_minor;
+	struct device *dev;
+	char *kn_name __free(kfree) = NULL;
+	int ret;
+
+	ret = pseudo_lock_region_alloc(plr);
+	if (ret < 0)
+		return ret;
+
+	ret = pseudo_lock_cstates_constrain(plr);
+	if (ret < 0) {
+		ret = -EINVAL;
+		goto out_region;
+	}
+	kn_name = kstrdup(rdt_kn_name(rdtgrp->kn), GFP_KERNEL);
+	if (!kn_name) {
+		ret = -ENOMEM;
+		goto out_cstates;
+	}
+
+	plr->thread_done = 0;
+
+	thread = kthread_run_on_cpu(resctrl_arch_pseudo_lock_fn, plr,
+				    plr->cpu, "pseudo_lock/%u");
+	if (IS_ERR(thread)) {
+		ret = PTR_ERR(thread);
+		rdt_last_cmd_printf("Locking thread returned error %d\n", ret);
+		goto out_cstates;
+	}
+
+	ret = wait_event_interruptible(plr->lock_thread_wq,
+				       plr->thread_done == 1);
+	if (ret < 0) {
+		/*
+		 * If the thread does not get on the CPU for whatever
+		 * reason and the process which sets up the region is
+		 * interrupted then this will leave the thread in runnable
+		 * state and once it gets on the CPU it will dereference
+		 * the cleared, but not freed, plr struct resulting in an
+		 * empty pseudo-locking loop.
+		 */
+		rdt_last_cmd_puts("Locking thread interrupted\n");
+		goto out_cstates;
+	}
+
+	ret = pseudo_lock_minor_get(&new_minor);
+	if (ret < 0) {
+		rdt_last_cmd_puts("Unable to obtain a new minor number\n");
+		goto out_cstates;
+	}
+
+	/*
+	 * Unlock access but do not release the reference. The
+	 * pseudo-locked region will still be here on return.
+	 *
+	 * The mutex has to be released temporarily to avoid a potential
+	 * deadlock with the mm->mmap_lock which is obtained in the
+	 * device_create() and debugfs_create_dir() callpath below as well as
+	 * before the mmap() callback is called.
+	 */
+	mutex_unlock(&rdtgroup_mutex);
+
+	if (!IS_ERR_OR_NULL(debugfs_resctrl)) {
+		plr->debugfs_dir = debugfs_create_dir(kn_name, debugfs_resctrl);
+		if (!IS_ERR_OR_NULL(plr->debugfs_dir))
+			debugfs_create_file("pseudo_lock_measure", 0200,
+					    plr->debugfs_dir, rdtgrp,
+					    &pseudo_measure_fops);
+	}
+
+	dev = device_create(&pseudo_lock_class, NULL,
+			    MKDEV(pseudo_lock_major, new_minor),
+			    rdtgrp, "%s", kn_name);
+
+	mutex_lock(&rdtgroup_mutex);
+
+	if (IS_ERR(dev)) {
+		ret = PTR_ERR(dev);
+		rdt_last_cmd_printf("Failed to create character device: %d\n",
+				    ret);
+		goto out_debugfs;
+	}
+
+	/* We released the mutex - check if group was removed while we did so */
+	if (rdtgrp->flags & RDT_DELETED) {
+		ret = -ENODEV;
+		goto out_device;
+	}
+
+	plr->minor = new_minor;
+
+	rdtgrp->mode = RDT_MODE_PSEUDO_LOCKED;
+	closid_free(rdtgrp->closid);
+	rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0444);
+	rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0444);
+
+	ret = 0;
+	goto out;
+
+out_device:
+	device_destroy(&pseudo_lock_class, MKDEV(pseudo_lock_major, new_minor));
+out_debugfs:
+	debugfs_remove_recursive(plr->debugfs_dir);
+	pseudo_lock_minor_release(new_minor);
+out_cstates:
+	pseudo_lock_cstates_relax(plr);
+out_region:
+	pseudo_lock_region_clear(plr);
+out:
+	return ret;
+}
+
+/**
+ * rdtgroup_pseudo_lock_remove - Remove a pseudo-locked region
+ * @rdtgrp: resource group to which the pseudo-locked region belongs
+ *
+ * The removal of a pseudo-locked region can be initiated when the resource
+ * group is removed from user space via a "rmdir" from userspace or the
+ * unmount of the resctrl filesystem. On removal the resource group does
+ * not go back to pseudo-locksetup mode before it is removed, instead it is
+ * removed directly. There is thus asymmetry with the creation where the
+ * &struct pseudo_lock_region is removed here while it was not created in
+ * rdtgroup_pseudo_lock_create().
+ *
+ * Return: void
+ */
+void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp)
+{
+	struct pseudo_lock_region *plr = rdtgrp->plr;
+
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+		/*
+		 * Default group cannot be a pseudo-locked region so we can
+		 * free closid here.
+		 */
+		closid_free(rdtgrp->closid);
+		goto free;
+	}
+
+	pseudo_lock_cstates_relax(plr);
+	debugfs_remove_recursive(rdtgrp->plr->debugfs_dir);
+	device_destroy(&pseudo_lock_class, MKDEV(pseudo_lock_major, plr->minor));
+	pseudo_lock_minor_release(plr->minor);
+
+free:
+	pseudo_lock_free(rdtgrp);
+}
+
+static int pseudo_lock_dev_open(struct inode *inode, struct file *filp)
+{
+	struct rdtgroup *rdtgrp;
+
+	mutex_lock(&rdtgroup_mutex);
+
+	rdtgrp = region_find_by_minor(iminor(inode));
+	if (!rdtgrp) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -ENODEV;
+	}
+
+	filp->private_data = rdtgrp;
+	atomic_inc(&rdtgrp->waitcount);
+	/* Perform a non-seekable open - llseek is not supported */
+	filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
+
+	mutex_unlock(&rdtgroup_mutex);
+
+	return 0;
+}
+
+static int pseudo_lock_dev_release(struct inode *inode, struct file *filp)
+{
+	struct rdtgroup *rdtgrp;
+
+	mutex_lock(&rdtgroup_mutex);
+	rdtgrp = filp->private_data;
+	WARN_ON(!rdtgrp);
+	if (!rdtgrp) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -ENODEV;
+	}
+	filp->private_data = NULL;
+	atomic_dec(&rdtgrp->waitcount);
+	mutex_unlock(&rdtgroup_mutex);
+	return 0;
+}
+
+static int pseudo_lock_dev_mremap(struct vm_area_struct *area)
+{
+	/* Not supported */
+	return -EINVAL;
+}
+
+static const struct vm_operations_struct pseudo_mmap_ops = {
+	.mremap = pseudo_lock_dev_mremap,
+};
+
+static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	unsigned long vsize = vma->vm_end - vma->vm_start;
+	unsigned long off = vma->vm_pgoff << PAGE_SHIFT;
+	struct pseudo_lock_region *plr;
+	struct rdtgroup *rdtgrp;
+	unsigned long physical;
+	unsigned long psize;
+
+	mutex_lock(&rdtgroup_mutex);
+
+	rdtgrp = filp->private_data;
+	WARN_ON(!rdtgrp);
+	if (!rdtgrp) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -ENODEV;
+	}
+
+	plr = rdtgrp->plr;
+
+	if (!plr->d) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -ENODEV;
+	}
+
+	/*
+	 * Task is required to run with affinity to the cpus associated
+	 * with the pseudo-locked region. If this is not the case the task
+	 * may be scheduled elsewhere and invalidate entries in the
+	 * pseudo-locked region.
+	 */
+	if (!cpumask_subset(current->cpus_ptr, &plr->d->hdr.cpu_mask)) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -EINVAL;
+	}
+
+	physical = __pa(plr->kmem) >> PAGE_SHIFT;
+	psize = plr->size - off;
+
+	if (off > plr->size) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -ENOSPC;
+	}
+
+	/*
+	 * Ensure changes are carried directly to the memory being mapped,
+	 * do not allow copy-on-write mapping.
+	 */
+	if (!(vma->vm_flags & VM_SHARED)) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -EINVAL;
+	}
+
+	if (vsize > psize) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -ENOSPC;
+	}
+
+	memset(plr->kmem + off, 0, vsize);
+
+	if (remap_pfn_range(vma, vma->vm_start, physical + vma->vm_pgoff,
+			    vsize, vma->vm_page_prot)) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -EAGAIN;
+	}
+	vma->vm_ops = &pseudo_mmap_ops;
+	mutex_unlock(&rdtgroup_mutex);
+	return 0;
+}
+
+static const struct file_operations pseudo_lock_dev_fops = {
+	.owner =	THIS_MODULE,
+	.llseek =	no_llseek,
+	.read =		NULL,
+	.write =	NULL,
+	.open =		pseudo_lock_dev_open,
+	.release =	pseudo_lock_dev_release,
+	.mmap =		pseudo_lock_dev_mmap,
+};
+
+int rdt_pseudo_lock_init(void)
+{
+	int ret;
+
+	ret = register_chrdev(0, "pseudo_lock", &pseudo_lock_dev_fops);
+	if (ret < 0)
+		return ret;
+
+	pseudo_lock_major = ret;
+
+	ret = class_register(&pseudo_lock_class);
+	if (ret) {
+		unregister_chrdev(pseudo_lock_major, "pseudo_lock");
+		return ret;
+	}
+
+	return 0;
+}
+
+void rdt_pseudo_lock_release(void)
+{
+	class_unregister(&pseudo_lock_class);
+	unregister_chrdev(pseudo_lock_major, "pseudo_lock");
+	pseudo_lock_major = 0;
+}
diff --git a/fs/resctrl/pseudo_lock_trace.h b/fs/resctrl/pseudo_lock_trace.h
deleted file mode 100644
index e69de29bb2d1d..0000000000000
diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index e69de29bb2d1d..cc37f58b47dd7 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -0,0 +1,4353 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * User interface for Resource Allocation in Resource Director Technology(RDT)
+ *
+ * Copyright (C) 2016 Intel Corporation
+ *
+ * Author: Fenghua Yu <fenghua.yu@intel.com>
+ *
+ * More information about RDT be found in the Intel (R) x86 Architecture
+ * Software Developer Manual.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/cpu.h>
+#include <linux/debugfs.h>
+#include <linux/fs.h>
+#include <linux/fs_parser.h>
+#include <linux/sysfs.h>
+#include <linux/kernfs.h>
+#include <linux/resctrl.h>
+#include <linux/seq_buf.h>
+#include <linux/seq_file.h>
+#include <linux/sched/task.h>
+#include <linux/slab.h>
+#include <linux/user_namespace.h>
+
+#include <uapi/linux/magic.h>
+
+#include "internal.h"
+
+/* Mutex to protect rdtgroup access. */
+DEFINE_MUTEX(rdtgroup_mutex);
+
+static struct kernfs_root *rdt_root;
+
+struct rdtgroup rdtgroup_default;
+
+LIST_HEAD(rdt_all_groups);
+
+/* list of entries for the schemata file */
+LIST_HEAD(resctrl_schema_all);
+
+/*
+ * List of struct mon_data containing private data of event files for use by
+ * rdtgroup_mondata_show(). Protected by rdtgroup_mutex.
+ */
+static LIST_HEAD(mon_data_kn_priv_list);
+
+/* The filesystem can only be mounted once. */
+bool resctrl_mounted;
+
+/* Kernel fs node for "info" directory under root */
+static struct kernfs_node *kn_info;
+
+/* Kernel fs node for "mon_groups" directory under root */
+static struct kernfs_node *kn_mongrp;
+
+/* Kernel fs node for "mon_data" directory under root */
+static struct kernfs_node *kn_mondata;
+
+/*
+ * Used to store the max resource name width to display the schemata names in
+ * a tabular format.
+ */
+int max_name_width;
+
+static struct seq_buf last_cmd_status;
+
+static char last_cmd_status_buf[512];
+
+static int rdtgroup_setup_root(struct rdt_fs_context *ctx);
+
+static void rdtgroup_destroy_root(void);
+
+struct dentry *debugfs_resctrl;
+
+/*
+ * Memory bandwidth monitoring event to use for the default CTRL_MON group
+ * and each new CTRL_MON group created by the user.  Only relevant when
+ * the filesystem is mounted with the "mba_MBps" option so it does not
+ * matter that it remains uninitialized on systems that do not support
+ * the "mba_MBps" option.
+ */
+enum resctrl_event_id mba_mbps_default_event;
+
+static bool resctrl_debug;
+
+void rdt_last_cmd_clear(void)
+{
+	lockdep_assert_held(&rdtgroup_mutex);
+	seq_buf_clear(&last_cmd_status);
+}
+
+void rdt_last_cmd_puts(const char *s)
+{
+	lockdep_assert_held(&rdtgroup_mutex);
+	seq_buf_puts(&last_cmd_status, s);
+}
+
+void rdt_last_cmd_printf(const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	lockdep_assert_held(&rdtgroup_mutex);
+	seq_buf_vprintf(&last_cmd_status, fmt, ap);
+	va_end(ap);
+}
+
+void rdt_staged_configs_clear(void)
+{
+	struct rdt_ctrl_domain *dom;
+	struct rdt_resource *r;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	for_each_alloc_capable_rdt_resource(r) {
+		list_for_each_entry(dom, &r->ctrl_domains, hdr.list)
+			memset(dom->staged_config, 0, sizeof(dom->staged_config));
+	}
+}
+
+static bool resctrl_is_mbm_enabled(void)
+{
+	return (resctrl_arch_is_mbm_total_enabled() ||
+		resctrl_arch_is_mbm_local_enabled());
+}
+
+static bool resctrl_is_mbm_event(int e)
+{
+	return (e >= QOS_L3_MBM_TOTAL_EVENT_ID &&
+		e <= QOS_L3_MBM_LOCAL_EVENT_ID);
+}
+
+/*
+ * Trivial allocator for CLOSIDs. Use BITMAP APIs to manipulate a bitmap
+ * of free CLOSIDs.
+ *
+ * Using a global CLOSID across all resources has some advantages and
+ * some drawbacks:
+ * + We can simply set current's closid to assign a task to a resource
+ *   group.
+ * + Context switch code can avoid extra memory references deciding which
+ *   CLOSID to load into the PQR_ASSOC MSR
+ * - We give up some options in configuring resource groups across multi-socket
+ *   systems.
+ * - Our choices on how to configure each resource become progressively more
+ *   limited as the number of resources grows.
+ */
+static unsigned long *closid_free_map;
+
+static int closid_free_map_len;
+
+int closids_supported(void)
+{
+	return closid_free_map_len;
+}
+
+static int closid_init(void)
+{
+	struct resctrl_schema *s;
+	u32 rdt_min_closid = ~0;
+
+	/* Monitor only platforms still call closid_init() */
+	if (list_empty(&resctrl_schema_all))
+		return 0;
+
+	/* Compute rdt_min_closid across all resources */
+	list_for_each_entry(s, &resctrl_schema_all, list)
+		rdt_min_closid = min(rdt_min_closid, s->num_closid);
+
+	closid_free_map = bitmap_alloc(rdt_min_closid, GFP_KERNEL);
+	if (!closid_free_map)
+		return -ENOMEM;
+	bitmap_fill(closid_free_map, rdt_min_closid);
+
+	/* RESCTRL_RESERVED_CLOSID is always reserved for the default group */
+	__clear_bit(RESCTRL_RESERVED_CLOSID, closid_free_map);
+	closid_free_map_len = rdt_min_closid;
+
+	return 0;
+}
+
+static void closid_exit(void)
+{
+	bitmap_free(closid_free_map);
+	closid_free_map = NULL;
+}
+
+static int closid_alloc(void)
+{
+	int cleanest_closid;
+	u32 closid;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID) &&
+	    resctrl_arch_is_llc_occupancy_enabled()) {
+		cleanest_closid = resctrl_find_cleanest_closid();
+		if (cleanest_closid < 0)
+			return cleanest_closid;
+		closid = cleanest_closid;
+	} else {
+		closid = find_first_bit(closid_free_map, closid_free_map_len);
+		if (closid == closid_free_map_len)
+			return -ENOSPC;
+	}
+	__clear_bit(closid, closid_free_map);
+
+	return closid;
+}
+
+void closid_free(int closid)
+{
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	__set_bit(closid, closid_free_map);
+}
+
+/**
+ * closid_allocated - test if provided closid is in use
+ * @closid: closid to be tested
+ *
+ * Return: true if @closid is currently associated with a resource group,
+ * false if @closid is free
+ */
+bool closid_allocated(unsigned int closid)
+{
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	return !test_bit(closid, closid_free_map);
+}
+
+/**
+ * rdtgroup_mode_by_closid - Return mode of resource group with closid
+ * @closid: closid if the resource group
+ *
+ * Each resource group is associated with a @closid. Here the mode
+ * of a resource group can be queried by searching for it using its closid.
+ *
+ * Return: mode as &enum rdtgrp_mode of resource group with closid @closid
+ */
+enum rdtgrp_mode rdtgroup_mode_by_closid(int closid)
+{
+	struct rdtgroup *rdtgrp;
+
+	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
+		if (rdtgrp->closid == closid)
+			return rdtgrp->mode;
+	}
+
+	return RDT_NUM_MODES;
+}
+
+static const char * const rdt_mode_str[] = {
+	[RDT_MODE_SHAREABLE]		= "shareable",
+	[RDT_MODE_EXCLUSIVE]		= "exclusive",
+	[RDT_MODE_PSEUDO_LOCKSETUP]	= "pseudo-locksetup",
+	[RDT_MODE_PSEUDO_LOCKED]	= "pseudo-locked",
+};
+
+/**
+ * rdtgroup_mode_str - Return the string representation of mode
+ * @mode: the resource group mode as &enum rdtgroup_mode
+ *
+ * Return: string representation of valid mode, "unknown" otherwise
+ */
+static const char *rdtgroup_mode_str(enum rdtgrp_mode mode)
+{
+	if (mode < RDT_MODE_SHAREABLE || mode >= RDT_NUM_MODES)
+		return "unknown";
+
+	return rdt_mode_str[mode];
+}
+
+/* set uid and gid of rdtgroup dirs and files to that of the creator */
+static int rdtgroup_kn_set_ugid(struct kernfs_node *kn)
+{
+	struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID,
+				.ia_uid = current_fsuid(),
+				.ia_gid = current_fsgid(), };
+
+	if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) &&
+	    gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID))
+		return 0;
+
+	return kernfs_setattr(kn, &iattr);
+}
+
+static int rdtgroup_add_file(struct kernfs_node *parent_kn, struct rftype *rft)
+{
+	struct kernfs_node *kn;
+	int ret;
+
+	kn = __kernfs_create_file(parent_kn, rft->name, rft->mode,
+				  GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
+				  0, rft->kf_ops, rft, NULL, NULL);
+	if (IS_ERR(kn))
+		return PTR_ERR(kn);
+
+	ret = rdtgroup_kn_set_ugid(kn);
+	if (ret) {
+		kernfs_remove(kn);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int rdtgroup_seqfile_show(struct seq_file *m, void *arg)
+{
+	struct kernfs_open_file *of = m->private;
+	struct rftype *rft = of->kn->priv;
+
+	if (rft->seq_show)
+		return rft->seq_show(of, m, arg);
+	return 0;
+}
+
+static ssize_t rdtgroup_file_write(struct kernfs_open_file *of, char *buf,
+				   size_t nbytes, loff_t off)
+{
+	struct rftype *rft = of->kn->priv;
+
+	if (rft->write)
+		return rft->write(of, buf, nbytes, off);
+
+	return -EINVAL;
+}
+
+static const struct kernfs_ops rdtgroup_kf_single_ops = {
+	.atomic_write_len	= PAGE_SIZE,
+	.write			= rdtgroup_file_write,
+	.seq_show		= rdtgroup_seqfile_show,
+};
+
+static const struct kernfs_ops kf_mondata_ops = {
+	.atomic_write_len	= PAGE_SIZE,
+	.seq_show		= rdtgroup_mondata_show,
+};
+
+static bool is_cpu_list(struct kernfs_open_file *of)
+{
+	struct rftype *rft = of->kn->priv;
+
+	return rft->flags & RFTYPE_FLAGS_CPUS_LIST;
+}
+
+static int rdtgroup_cpus_show(struct kernfs_open_file *of,
+			      struct seq_file *s, void *v)
+{
+	struct rdtgroup *rdtgrp;
+	struct cpumask *mask;
+	int ret = 0;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+
+	if (rdtgrp) {
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
+			if (!rdtgrp->plr->d) {
+				rdt_last_cmd_clear();
+				rdt_last_cmd_puts("Cache domain offline\n");
+				ret = -ENODEV;
+			} else {
+				mask = &rdtgrp->plr->d->hdr.cpu_mask;
+				seq_printf(s, is_cpu_list(of) ?
+					   "%*pbl\n" : "%*pb\n",
+					   cpumask_pr_args(mask));
+			}
+		} else {
+			seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
+				   cpumask_pr_args(&rdtgrp->cpu_mask));
+		}
+	} else {
+		ret = -ENOENT;
+	}
+	rdtgroup_kn_unlock(of->kn);
+
+	return ret;
+}
+
+/*
+ * Update the PGR_ASSOC MSR on all cpus in @cpu_mask,
+ *
+ * Per task closids/rmids must have been set up before calling this function.
+ * @r may be NULL.
+ */
+static void
+update_closid_rmid(const struct cpumask *cpu_mask, struct rdtgroup *r)
+{
+	struct resctrl_cpu_defaults defaults, *p = NULL;
+
+	if (r) {
+		defaults.closid = r->closid;
+		defaults.rmid = r->mon.rmid;
+		p = &defaults;
+	}
+
+	on_each_cpu_mask(cpu_mask, resctrl_arch_sync_cpu_closid_rmid, p, 1);
+}
+
+static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask,
+			  cpumask_var_t tmpmask)
+{
+	struct rdtgroup *prgrp = rdtgrp->mon.parent, *crgrp;
+	struct list_head *head;
+
+	/* Check whether cpus belong to parent ctrl group */
+	cpumask_andnot(tmpmask, newmask, &prgrp->cpu_mask);
+	if (!cpumask_empty(tmpmask)) {
+		rdt_last_cmd_puts("Can only add CPUs to mongroup that belong to parent\n");
+		return -EINVAL;
+	}
+
+	/* Check whether cpus are dropped from this group */
+	cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask);
+	if (!cpumask_empty(tmpmask)) {
+		/* Give any dropped cpus to parent rdtgroup */
+		cpumask_or(&prgrp->cpu_mask, &prgrp->cpu_mask, tmpmask);
+		update_closid_rmid(tmpmask, prgrp);
+	}
+
+	/*
+	 * If we added cpus, remove them from previous group that owned them
+	 * and update per-cpu rmid
+	 */
+	cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask);
+	if (!cpumask_empty(tmpmask)) {
+		head = &prgrp->mon.crdtgrp_list;
+		list_for_each_entry(crgrp, head, mon.crdtgrp_list) {
+			if (crgrp == rdtgrp)
+				continue;
+			cpumask_andnot(&crgrp->cpu_mask, &crgrp->cpu_mask,
+				       tmpmask);
+		}
+		update_closid_rmid(tmpmask, rdtgrp);
+	}
+
+	/* Done pushing/pulling - update this group with new mask */
+	cpumask_copy(&rdtgrp->cpu_mask, newmask);
+
+	return 0;
+}
+
+static void cpumask_rdtgrp_clear(struct rdtgroup *r, struct cpumask *m)
+{
+	struct rdtgroup *crgrp;
+
+	cpumask_andnot(&r->cpu_mask, &r->cpu_mask, m);
+	/* update the child mon group masks as well*/
+	list_for_each_entry(crgrp, &r->mon.crdtgrp_list, mon.crdtgrp_list)
+		cpumask_and(&crgrp->cpu_mask, &r->cpu_mask, &crgrp->cpu_mask);
+}
+
+static int cpus_ctrl_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask,
+			   cpumask_var_t tmpmask, cpumask_var_t tmpmask1)
+{
+	struct rdtgroup *r, *crgrp;
+	struct list_head *head;
+
+	/* Check whether cpus are dropped from this group */
+	cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask);
+	if (!cpumask_empty(tmpmask)) {
+		/* Can't drop from default group */
+		if (rdtgrp == &rdtgroup_default) {
+			rdt_last_cmd_puts("Can't drop CPUs from default group\n");
+			return -EINVAL;
+		}
+
+		/* Give any dropped cpus to rdtgroup_default */
+		cpumask_or(&rdtgroup_default.cpu_mask,
+			   &rdtgroup_default.cpu_mask, tmpmask);
+		update_closid_rmid(tmpmask, &rdtgroup_default);
+	}
+
+	/*
+	 * If we added cpus, remove them from previous group and
+	 * the prev group's child groups that owned them
+	 * and update per-cpu closid/rmid.
+	 */
+	cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask);
+	if (!cpumask_empty(tmpmask)) {
+		list_for_each_entry(r, &rdt_all_groups, rdtgroup_list) {
+			if (r == rdtgrp)
+				continue;
+			cpumask_and(tmpmask1, &r->cpu_mask, tmpmask);
+			if (!cpumask_empty(tmpmask1))
+				cpumask_rdtgrp_clear(r, tmpmask1);
+		}
+		update_closid_rmid(tmpmask, rdtgrp);
+	}
+
+	/* Done pushing/pulling - update this group with new mask */
+	cpumask_copy(&rdtgrp->cpu_mask, newmask);
+
+	/*
+	 * Clear child mon group masks since there is a new parent mask
+	 * now and update the rmid for the cpus the child lost.
+	 */
+	head = &rdtgrp->mon.crdtgrp_list;
+	list_for_each_entry(crgrp, head, mon.crdtgrp_list) {
+		cpumask_and(tmpmask, &rdtgrp->cpu_mask, &crgrp->cpu_mask);
+		update_closid_rmid(tmpmask, rdtgrp);
+		cpumask_clear(&crgrp->cpu_mask);
+	}
+
+	return 0;
+}
+
+static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
+				   char *buf, size_t nbytes, loff_t off)
+{
+	cpumask_var_t tmpmask, newmask, tmpmask1;
+	struct rdtgroup *rdtgrp;
+	int ret;
+
+	if (!buf)
+		return -EINVAL;
+
+	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
+		return -ENOMEM;
+	if (!zalloc_cpumask_var(&newmask, GFP_KERNEL)) {
+		free_cpumask_var(tmpmask);
+		return -ENOMEM;
+	}
+	if (!zalloc_cpumask_var(&tmpmask1, GFP_KERNEL)) {
+		free_cpumask_var(tmpmask);
+		free_cpumask_var(newmask);
+		return -ENOMEM;
+	}
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		ret = -ENOENT;
+		goto unlock;
+	}
+
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED ||
+	    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+		ret = -EINVAL;
+		rdt_last_cmd_puts("Pseudo-locking in progress\n");
+		goto unlock;
+	}
+
+	if (is_cpu_list(of))
+		ret = cpulist_parse(buf, newmask);
+	else
+		ret = cpumask_parse(buf, newmask);
+
+	if (ret) {
+		rdt_last_cmd_puts("Bad CPU list/mask\n");
+		goto unlock;
+	}
+
+	/* check that user didn't specify any offline cpus */
+	cpumask_andnot(tmpmask, newmask, cpu_online_mask);
+	if (!cpumask_empty(tmpmask)) {
+		ret = -EINVAL;
+		rdt_last_cmd_puts("Can only assign online CPUs\n");
+		goto unlock;
+	}
+
+	if (rdtgrp->type == RDTCTRL_GROUP)
+		ret = cpus_ctrl_write(rdtgrp, newmask, tmpmask, tmpmask1);
+	else if (rdtgrp->type == RDTMON_GROUP)
+		ret = cpus_mon_write(rdtgrp, newmask, tmpmask);
+	else
+		ret = -EINVAL;
+
+unlock:
+	rdtgroup_kn_unlock(of->kn);
+	free_cpumask_var(tmpmask);
+	free_cpumask_var(newmask);
+	free_cpumask_var(tmpmask1);
+
+	return ret ?: nbytes;
+}
+
+/**
+ * rdtgroup_remove - the helper to remove resource group safely
+ * @rdtgrp: resource group to remove
+ *
+ * On resource group creation via a mkdir, an extra kernfs_node reference is
+ * taken to ensure that the rdtgroup structure remains accessible for the
+ * rdtgroup_kn_unlock() calls where it is removed.
+ *
+ * Drop the extra reference here, then free the rdtgroup structure.
+ *
+ * Return: void
+ */
+static void rdtgroup_remove(struct rdtgroup *rdtgrp)
+{
+	kernfs_put(rdtgrp->kn);
+	kfree(rdtgrp);
+}
+
+static void _update_task_closid_rmid(void *task)
+{
+	/*
+	 * If the task is still current on this CPU, update PQR_ASSOC MSR.
+	 * Otherwise, the MSR is updated when the task is scheduled in.
+	 */
+	if (task == current)
+		resctrl_arch_sched_in(task);
+}
+
+static void update_task_closid_rmid(struct task_struct *t)
+{
+	if (IS_ENABLED(CONFIG_SMP) && task_curr(t))
+		smp_call_function_single(task_cpu(t), _update_task_closid_rmid, t, 1);
+	else
+		_update_task_closid_rmid(t);
+}
+
+static bool task_in_rdtgroup(struct task_struct *tsk, struct rdtgroup *rdtgrp)
+{
+	u32 closid, rmid = rdtgrp->mon.rmid;
+
+	if (rdtgrp->type == RDTCTRL_GROUP)
+		closid = rdtgrp->closid;
+	else if (rdtgrp->type == RDTMON_GROUP)
+		closid = rdtgrp->mon.parent->closid;
+	else
+		return false;
+
+	return resctrl_arch_match_closid(tsk, closid) &&
+	       resctrl_arch_match_rmid(tsk, closid, rmid);
+}
+
+static int __rdtgroup_move_task(struct task_struct *tsk,
+				struct rdtgroup *rdtgrp)
+{
+	/* If the task is already in rdtgrp, no need to move the task. */
+	if (task_in_rdtgroup(tsk, rdtgrp))
+		return 0;
+
+	/*
+	 * Set the task's closid/rmid before the PQR_ASSOC MSR can be
+	 * updated by them.
+	 *
+	 * For ctrl_mon groups, move both closid and rmid.
+	 * For monitor groups, can move the tasks only from
+	 * their parent CTRL group.
+	 */
+	if (rdtgrp->type == RDTMON_GROUP &&
+	    !resctrl_arch_match_closid(tsk, rdtgrp->mon.parent->closid)) {
+		rdt_last_cmd_puts("Can't move task to different control group\n");
+		return -EINVAL;
+	}
+
+	if (rdtgrp->type == RDTMON_GROUP)
+		resctrl_arch_set_closid_rmid(tsk, rdtgrp->mon.parent->closid,
+					     rdtgrp->mon.rmid);
+	else
+		resctrl_arch_set_closid_rmid(tsk, rdtgrp->closid,
+					     rdtgrp->mon.rmid);
+
+	/*
+	 * Ensure the task's closid and rmid are written before determining if
+	 * the task is current that will decide if it will be interrupted.
+	 * This pairs with the full barrier between the rq->curr update and
+	 * resctrl_arch_sched_in() during context switch.
+	 */
+	smp_mb();
+
+	/*
+	 * By now, the task's closid and rmid are set. If the task is current
+	 * on a CPU, the PQR_ASSOC MSR needs to be updated to make the resource
+	 * group go into effect. If the task is not current, the MSR will be
+	 * updated when the task is scheduled in.
+	 */
+	update_task_closid_rmid(tsk);
+
+	return 0;
+}
+
+static bool is_closid_match(struct task_struct *t, struct rdtgroup *r)
+{
+	return (resctrl_arch_alloc_capable() && (r->type == RDTCTRL_GROUP) &&
+		resctrl_arch_match_closid(t, r->closid));
+}
+
+static bool is_rmid_match(struct task_struct *t, struct rdtgroup *r)
+{
+	return (resctrl_arch_mon_capable() && (r->type == RDTMON_GROUP) &&
+		resctrl_arch_match_rmid(t, r->mon.parent->closid,
+					r->mon.rmid));
+}
+
+/**
+ * rdtgroup_tasks_assigned - Test if tasks have been assigned to resource group
+ * @r: Resource group
+ *
+ * Return: 1 if tasks have been assigned to @r, 0 otherwise
+ */
+int rdtgroup_tasks_assigned(struct rdtgroup *r)
+{
+	struct task_struct *p, *t;
+	int ret = 0;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	rcu_read_lock();
+	for_each_process_thread(p, t) {
+		if (is_closid_match(t, r) || is_rmid_match(t, r)) {
+			ret = 1;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static int rdtgroup_task_write_permission(struct task_struct *task,
+					  struct kernfs_open_file *of)
+{
+	const struct cred *tcred = get_task_cred(task);
+	const struct cred *cred = current_cred();
+	int ret = 0;
+
+	/*
+	 * Even if we're attaching all tasks in the thread group, we only
+	 * need to check permissions on one of them.
+	 */
+	if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) &&
+	    !uid_eq(cred->euid, tcred->uid) &&
+	    !uid_eq(cred->euid, tcred->suid)) {
+		rdt_last_cmd_printf("No permission to move task %d\n", task->pid);
+		ret = -EPERM;
+	}
+
+	put_cred(tcred);
+	return ret;
+}
+
+static int rdtgroup_move_task(pid_t pid, struct rdtgroup *rdtgrp,
+			      struct kernfs_open_file *of)
+{
+	struct task_struct *tsk;
+	int ret;
+
+	rcu_read_lock();
+	if (pid) {
+		tsk = find_task_by_vpid(pid);
+		if (!tsk) {
+			rcu_read_unlock();
+			rdt_last_cmd_printf("No task %d\n", pid);
+			return -ESRCH;
+		}
+	} else {
+		tsk = current;
+	}
+
+	get_task_struct(tsk);
+	rcu_read_unlock();
+
+	ret = rdtgroup_task_write_permission(tsk, of);
+	if (!ret)
+		ret = __rdtgroup_move_task(tsk, rdtgrp);
+
+	put_task_struct(tsk);
+	return ret;
+}
+
+static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of,
+				    char *buf, size_t nbytes, loff_t off)
+{
+	struct rdtgroup *rdtgrp;
+	char *pid_str;
+	int ret = 0;
+	pid_t pid;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		rdtgroup_kn_unlock(of->kn);
+		return -ENOENT;
+	}
+	rdt_last_cmd_clear();
+
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED ||
+	    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+		ret = -EINVAL;
+		rdt_last_cmd_puts("Pseudo-locking in progress\n");
+		goto unlock;
+	}
+
+	while (buf && buf[0] != '\0' && buf[0] != '\n') {
+		pid_str = strim(strsep(&buf, ","));
+
+		if (kstrtoint(pid_str, 0, &pid)) {
+			rdt_last_cmd_printf("Task list parsing error pid %s\n", pid_str);
+			ret = -EINVAL;
+			break;
+		}
+
+		if (pid < 0) {
+			rdt_last_cmd_printf("Invalid pid %d\n", pid);
+			ret = -EINVAL;
+			break;
+		}
+
+		ret = rdtgroup_move_task(pid, rdtgrp, of);
+		if (ret) {
+			rdt_last_cmd_printf("Error while processing task %d\n", pid);
+			break;
+		}
+	}
+
+unlock:
+	rdtgroup_kn_unlock(of->kn);
+
+	return ret ?: nbytes;
+}
+
+static void show_rdt_tasks(struct rdtgroup *r, struct seq_file *s)
+{
+	struct task_struct *p, *t;
+	pid_t pid;
+
+	rcu_read_lock();
+	for_each_process_thread(p, t) {
+		if (is_closid_match(t, r) || is_rmid_match(t, r)) {
+			pid = task_pid_vnr(t);
+			if (pid)
+				seq_printf(s, "%d\n", pid);
+		}
+	}
+	rcu_read_unlock();
+}
+
+static int rdtgroup_tasks_show(struct kernfs_open_file *of,
+			       struct seq_file *s, void *v)
+{
+	struct rdtgroup *rdtgrp;
+	int ret = 0;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (rdtgrp)
+		show_rdt_tasks(rdtgrp, s);
+	else
+		ret = -ENOENT;
+	rdtgroup_kn_unlock(of->kn);
+
+	return ret;
+}
+
+static int rdtgroup_closid_show(struct kernfs_open_file *of,
+				struct seq_file *s, void *v)
+{
+	struct rdtgroup *rdtgrp;
+	int ret = 0;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (rdtgrp)
+		seq_printf(s, "%u\n", rdtgrp->closid);
+	else
+		ret = -ENOENT;
+	rdtgroup_kn_unlock(of->kn);
+
+	return ret;
+}
+
+static int rdtgroup_rmid_show(struct kernfs_open_file *of,
+			      struct seq_file *s, void *v)
+{
+	struct rdtgroup *rdtgrp;
+	int ret = 0;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (rdtgrp)
+		seq_printf(s, "%u\n", rdtgrp->mon.rmid);
+	else
+		ret = -ENOENT;
+	rdtgroup_kn_unlock(of->kn);
+
+	return ret;
+}
+
+#ifdef CONFIG_PROC_CPU_RESCTRL
+/*
+ * A task can only be part of one resctrl control group and of one monitor
+ * group which is associated to that control group.
+ *
+ * 1)   res:
+ *      mon:
+ *
+ *    resctrl is not available.
+ *
+ * 2)   res:/
+ *      mon:
+ *
+ *    Task is part of the root resctrl control group, and it is not associated
+ *    to any monitor group.
+ *
+ * 3)  res:/
+ *     mon:mon0
+ *
+ *    Task is part of the root resctrl control group and monitor group mon0.
+ *
+ * 4)  res:group0
+ *     mon:
+ *
+ *    Task is part of resctrl control group group0, and it is not associated
+ *    to any monitor group.
+ *
+ * 5) res:group0
+ *    mon:mon1
+ *
+ *    Task is part of resctrl control group group0 and monitor group mon1.
+ */
+int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns,
+		      struct pid *pid, struct task_struct *tsk)
+{
+	struct rdtgroup *rdtg;
+	int ret = 0;
+
+	mutex_lock(&rdtgroup_mutex);
+
+	/* Return empty if resctrl has not been mounted. */
+	if (!resctrl_mounted) {
+		seq_puts(s, "res:\nmon:\n");
+		goto unlock;
+	}
+
+	list_for_each_entry(rdtg, &rdt_all_groups, rdtgroup_list) {
+		struct rdtgroup *crg;
+
+		/*
+		 * Task information is only relevant for shareable
+		 * and exclusive groups.
+		 */
+		if (rdtg->mode != RDT_MODE_SHAREABLE &&
+		    rdtg->mode != RDT_MODE_EXCLUSIVE)
+			continue;
+
+		if (!resctrl_arch_match_closid(tsk, rdtg->closid))
+			continue;
+
+		seq_printf(s, "res:%s%s\n", (rdtg == &rdtgroup_default) ? "/" : "",
+			   rdt_kn_name(rdtg->kn));
+		seq_puts(s, "mon:");
+		list_for_each_entry(crg, &rdtg->mon.crdtgrp_list,
+				    mon.crdtgrp_list) {
+			if (!resctrl_arch_match_rmid(tsk, crg->mon.parent->closid,
+						     crg->mon.rmid))
+				continue;
+			seq_printf(s, "%s", rdt_kn_name(crg->kn));
+			break;
+		}
+		seq_putc(s, '\n');
+		goto unlock;
+	}
+	/*
+	 * The above search should succeed. Otherwise return
+	 * with an error.
+	 */
+	ret = -ENOENT;
+unlock:
+	mutex_unlock(&rdtgroup_mutex);
+
+	return ret;
+}
+#endif
+
+static int rdt_last_cmd_status_show(struct kernfs_open_file *of,
+				    struct seq_file *seq, void *v)
+{
+	int len;
+
+	mutex_lock(&rdtgroup_mutex);
+	len = seq_buf_used(&last_cmd_status);
+	if (len)
+		seq_printf(seq, "%.*s", len, last_cmd_status_buf);
+	else
+		seq_puts(seq, "ok\n");
+	mutex_unlock(&rdtgroup_mutex);
+	return 0;
+}
+
+static void *rdt_kn_parent_priv(struct kernfs_node *kn)
+{
+	/*
+	 * The parent pointer is only valid within RCU section since it can be
+	 * replaced.
+	 */
+	guard(rcu)();
+	return rcu_dereference(kn->__parent)->priv;
+}
+
+static int rdt_num_closids_show(struct kernfs_open_file *of,
+				struct seq_file *seq, void *v)
+{
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
+
+	seq_printf(seq, "%u\n", s->num_closid);
+	return 0;
+}
+
+static int rdt_default_ctrl_show(struct kernfs_open_file *of,
+				 struct seq_file *seq, void *v)
+{
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
+	struct rdt_resource *r = s->res;
+
+	seq_printf(seq, "%x\n", resctrl_get_default_ctrl(r));
+	return 0;
+}
+
+static int rdt_min_cbm_bits_show(struct kernfs_open_file *of,
+				 struct seq_file *seq, void *v)
+{
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
+	struct rdt_resource *r = s->res;
+
+	seq_printf(seq, "%u\n", r->cache.min_cbm_bits);
+	return 0;
+}
+
+static int rdt_shareable_bits_show(struct kernfs_open_file *of,
+				   struct seq_file *seq, void *v)
+{
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
+	struct rdt_resource *r = s->res;
+
+	seq_printf(seq, "%x\n", r->cache.shareable_bits);
+	return 0;
+}
+
+/*
+ * rdt_bit_usage_show - Display current usage of resources
+ *
+ * A domain is a shared resource that can now be allocated differently. Here
+ * we display the current regions of the domain as an annotated bitmask.
+ * For each domain of this resource its allocation bitmask
+ * is annotated as below to indicate the current usage of the corresponding bit:
+ *   0 - currently unused
+ *   X - currently available for sharing and used by software and hardware
+ *   H - currently used by hardware only but available for software use
+ *   S - currently used and shareable by software only
+ *   E - currently used exclusively by one resource group
+ *   P - currently pseudo-locked by one resource group
+ */
+static int rdt_bit_usage_show(struct kernfs_open_file *of,
+			      struct seq_file *seq, void *v)
+{
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
+	/*
+	 * Use unsigned long even though only 32 bits are used to ensure
+	 * test_bit() is used safely.
+	 */
+	unsigned long sw_shareable = 0, hw_shareable = 0;
+	unsigned long exclusive = 0, pseudo_locked = 0;
+	struct rdt_resource *r = s->res;
+	struct rdt_ctrl_domain *dom;
+	int i, hwb, swb, excl, psl;
+	enum rdtgrp_mode mode;
+	bool sep = false;
+	u32 ctrl_val;
+
+	cpus_read_lock();
+	mutex_lock(&rdtgroup_mutex);
+	hw_shareable = r->cache.shareable_bits;
+	list_for_each_entry(dom, &r->ctrl_domains, hdr.list) {
+		if (sep)
+			seq_putc(seq, ';');
+		sw_shareable = 0;
+		exclusive = 0;
+		seq_printf(seq, "%d=", dom->hdr.id);
+		for (i = 0; i < closids_supported(); i++) {
+			if (!closid_allocated(i))
+				continue;
+			ctrl_val = resctrl_arch_get_config(r, dom, i,
+							   s->conf_type);
+			mode = rdtgroup_mode_by_closid(i);
+			switch (mode) {
+			case RDT_MODE_SHAREABLE:
+				sw_shareable |= ctrl_val;
+				break;
+			case RDT_MODE_EXCLUSIVE:
+				exclusive |= ctrl_val;
+				break;
+			case RDT_MODE_PSEUDO_LOCKSETUP:
+			/*
+			 * RDT_MODE_PSEUDO_LOCKSETUP is possible
+			 * here but not included since the CBM
+			 * associated with this CLOSID in this mode
+			 * is not initialized and no task or cpu can be
+			 * assigned this CLOSID.
+			 */
+				break;
+			case RDT_MODE_PSEUDO_LOCKED:
+			case RDT_NUM_MODES:
+				WARN(1,
+				     "invalid mode for closid %d\n", i);
+				break;
+			}
+		}
+		for (i = r->cache.cbm_len - 1; i >= 0; i--) {
+			pseudo_locked = dom->plr ? dom->plr->cbm : 0;
+			hwb = test_bit(i, &hw_shareable);
+			swb = test_bit(i, &sw_shareable);
+			excl = test_bit(i, &exclusive);
+			psl = test_bit(i, &pseudo_locked);
+			if (hwb && swb)
+				seq_putc(seq, 'X');
+			else if (hwb && !swb)
+				seq_putc(seq, 'H');
+			else if (!hwb && swb)
+				seq_putc(seq, 'S');
+			else if (excl)
+				seq_putc(seq, 'E');
+			else if (psl)
+				seq_putc(seq, 'P');
+			else /* Unused bits remain */
+				seq_putc(seq, '0');
+		}
+		sep = true;
+	}
+	seq_putc(seq, '\n');
+	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
+	return 0;
+}
+
+static int rdt_min_bw_show(struct kernfs_open_file *of,
+			   struct seq_file *seq, void *v)
+{
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
+	struct rdt_resource *r = s->res;
+
+	seq_printf(seq, "%u\n", r->membw.min_bw);
+	return 0;
+}
+
+static int rdt_num_rmids_show(struct kernfs_open_file *of,
+			      struct seq_file *seq, void *v)
+{
+	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
+
+	seq_printf(seq, "%d\n", r->num_rmid);
+
+	return 0;
+}
+
+static int rdt_mon_features_show(struct kernfs_open_file *of,
+				 struct seq_file *seq, void *v)
+{
+	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
+	struct mon_evt *mevt;
+
+	list_for_each_entry(mevt, &r->evt_list, list) {
+		seq_printf(seq, "%s\n", mevt->name);
+		if (mevt->configurable)
+			seq_printf(seq, "%s_config\n", mevt->name);
+	}
+
+	return 0;
+}
+
+static int rdt_bw_gran_show(struct kernfs_open_file *of,
+			    struct seq_file *seq, void *v)
+{
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
+	struct rdt_resource *r = s->res;
+
+	seq_printf(seq, "%u\n", r->membw.bw_gran);
+	return 0;
+}
+
+static int rdt_delay_linear_show(struct kernfs_open_file *of,
+				 struct seq_file *seq, void *v)
+{
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
+	struct rdt_resource *r = s->res;
+
+	seq_printf(seq, "%u\n", r->membw.delay_linear);
+	return 0;
+}
+
+static int max_threshold_occ_show(struct kernfs_open_file *of,
+				  struct seq_file *seq, void *v)
+{
+	seq_printf(seq, "%u\n", resctrl_rmid_realloc_threshold);
+
+	return 0;
+}
+
+static int rdt_thread_throttle_mode_show(struct kernfs_open_file *of,
+					 struct seq_file *seq, void *v)
+{
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
+	struct rdt_resource *r = s->res;
+
+	switch (r->membw.throttle_mode) {
+	case THREAD_THROTTLE_PER_THREAD:
+		seq_puts(seq, "per-thread\n");
+		return 0;
+	case THREAD_THROTTLE_MAX:
+		seq_puts(seq, "max\n");
+		return 0;
+	case THREAD_THROTTLE_UNDEFINED:
+		seq_puts(seq, "undefined\n");
+		return 0;
+	}
+
+	WARN_ON_ONCE(1);
+
+	return 0;
+}
+
+static ssize_t max_threshold_occ_write(struct kernfs_open_file *of,
+				       char *buf, size_t nbytes, loff_t off)
+{
+	unsigned int bytes;
+	int ret;
+
+	ret = kstrtouint(buf, 0, &bytes);
+	if (ret)
+		return ret;
+
+	if (bytes > resctrl_rmid_realloc_limit)
+		return -EINVAL;
+
+	resctrl_rmid_realloc_threshold = resctrl_arch_round_mon_val(bytes);
+
+	return nbytes;
+}
+
+/*
+ * rdtgroup_mode_show - Display mode of this resource group
+ */
+static int rdtgroup_mode_show(struct kernfs_open_file *of,
+			      struct seq_file *s, void *v)
+{
+	struct rdtgroup *rdtgrp;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		rdtgroup_kn_unlock(of->kn);
+		return -ENOENT;
+	}
+
+	seq_printf(s, "%s\n", rdtgroup_mode_str(rdtgrp->mode));
+
+	rdtgroup_kn_unlock(of->kn);
+	return 0;
+}
+
+static enum resctrl_conf_type resctrl_peer_type(enum resctrl_conf_type my_type)
+{
+	switch (my_type) {
+	case CDP_CODE:
+		return CDP_DATA;
+	case CDP_DATA:
+		return CDP_CODE;
+	default:
+	case CDP_NONE:
+		return CDP_NONE;
+	}
+}
+
+static int rdt_has_sparse_bitmasks_show(struct kernfs_open_file *of,
+					struct seq_file *seq, void *v)
+{
+	struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
+	struct rdt_resource *r = s->res;
+
+	seq_printf(seq, "%u\n", r->cache.arch_has_sparse_bitmasks);
+
+	return 0;
+}
+
+/**
+ * __rdtgroup_cbm_overlaps - Does CBM for intended closid overlap with other
+ * @r: Resource to which domain instance @d belongs.
+ * @d: The domain instance for which @closid is being tested.
+ * @cbm: Capacity bitmask being tested.
+ * @closid: Intended closid for @cbm.
+ * @type: CDP type of @r.
+ * @exclusive: Only check if overlaps with exclusive resource groups
+ *
+ * Checks if provided @cbm intended to be used for @closid on domain
+ * @d overlaps with any other closids or other hardware usage associated
+ * with this domain. If @exclusive is true then only overlaps with
+ * resource groups in exclusive mode will be considered. If @exclusive
+ * is false then overlaps with any resource group or hardware entities
+ * will be considered.
+ *
+ * @cbm is unsigned long, even if only 32 bits are used, to make the
+ * bitmap functions work correctly.
+ *
+ * Return: false if CBM does not overlap, true if it does.
+ */
+static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_ctrl_domain *d,
+				    unsigned long cbm, int closid,
+				    enum resctrl_conf_type type, bool exclusive)
+{
+	enum rdtgrp_mode mode;
+	unsigned long ctrl_b;
+	int i;
+
+	/* Check for any overlap with regions used by hardware directly */
+	if (!exclusive) {
+		ctrl_b = r->cache.shareable_bits;
+		if (bitmap_intersects(&cbm, &ctrl_b, r->cache.cbm_len))
+			return true;
+	}
+
+	/* Check for overlap with other resource groups */
+	for (i = 0; i < closids_supported(); i++) {
+		ctrl_b = resctrl_arch_get_config(r, d, i, type);
+		mode = rdtgroup_mode_by_closid(i);
+		if (closid_allocated(i) && i != closid &&
+		    mode != RDT_MODE_PSEUDO_LOCKSETUP) {
+			if (bitmap_intersects(&cbm, &ctrl_b, r->cache.cbm_len)) {
+				if (exclusive) {
+					if (mode == RDT_MODE_EXCLUSIVE)
+						return true;
+					continue;
+				}
+				return true;
+			}
+		}
+	}
+
+	return false;
+}
+
+/**
+ * rdtgroup_cbm_overlaps - Does CBM overlap with other use of hardware
+ * @s: Schema for the resource to which domain instance @d belongs.
+ * @d: The domain instance for which @closid is being tested.
+ * @cbm: Capacity bitmask being tested.
+ * @closid: Intended closid for @cbm.
+ * @exclusive: Only check if overlaps with exclusive resource groups
+ *
+ * Resources that can be allocated using a CBM can use the CBM to control
+ * the overlap of these allocations. rdtgroup_cmb_overlaps() is the test
+ * for overlap. Overlap test is not limited to the specific resource for
+ * which the CBM is intended though - when dealing with CDP resources that
+ * share the underlying hardware the overlap check should be performed on
+ * the CDP resource sharing the hardware also.
+ *
+ * Refer to description of __rdtgroup_cbm_overlaps() for the details of the
+ * overlap test.
+ *
+ * Return: true if CBM overlap detected, false if there is no overlap
+ */
+bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_ctrl_domain *d,
+			   unsigned long cbm, int closid, bool exclusive)
+{
+	enum resctrl_conf_type peer_type = resctrl_peer_type(s->conf_type);
+	struct rdt_resource *r = s->res;
+
+	if (__rdtgroup_cbm_overlaps(r, d, cbm, closid, s->conf_type,
+				    exclusive))
+		return true;
+
+	if (!resctrl_arch_get_cdp_enabled(r->rid))
+		return false;
+	return  __rdtgroup_cbm_overlaps(r, d, cbm, closid, peer_type, exclusive);
+}
+
+/**
+ * rdtgroup_mode_test_exclusive - Test if this resource group can be exclusive
+ * @rdtgrp: Resource group identified through its closid.
+ *
+ * An exclusive resource group implies that there should be no sharing of
+ * its allocated resources. At the time this group is considered to be
+ * exclusive this test can determine if its current schemata supports this
+ * setting by testing for overlap with all other resource groups.
+ *
+ * Return: true if resource group can be exclusive, false if there is overlap
+ * with allocations of other resource groups and thus this resource group
+ * cannot be exclusive.
+ */
+static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp)
+{
+	int closid = rdtgrp->closid;
+	struct rdt_ctrl_domain *d;
+	struct resctrl_schema *s;
+	struct rdt_resource *r;
+	bool has_cache = false;
+	u32 ctrl;
+
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
+	list_for_each_entry(s, &resctrl_schema_all, list) {
+		r = s->res;
+		if (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)
+			continue;
+		has_cache = true;
+		list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
+			ctrl = resctrl_arch_get_config(r, d, closid,
+						       s->conf_type);
+			if (rdtgroup_cbm_overlaps(s, d, ctrl, closid, false)) {
+				rdt_last_cmd_puts("Schemata overlaps\n");
+				return false;
+			}
+		}
+	}
+
+	if (!has_cache) {
+		rdt_last_cmd_puts("Cannot be exclusive without CAT/CDP\n");
+		return false;
+	}
+
+	return true;
+}
+
+/*
+ * rdtgroup_mode_write - Modify the resource group's mode
+ */
+static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of,
+				   char *buf, size_t nbytes, loff_t off)
+{
+	struct rdtgroup *rdtgrp;
+	enum rdtgrp_mode mode;
+	int ret = 0;
+
+	/* Valid input requires a trailing newline */
+	if (nbytes == 0 || buf[nbytes - 1] != '\n')
+		return -EINVAL;
+	buf[nbytes - 1] = '\0';
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		rdtgroup_kn_unlock(of->kn);
+		return -ENOENT;
+	}
+
+	rdt_last_cmd_clear();
+
+	mode = rdtgrp->mode;
+
+	if ((!strcmp(buf, "shareable") && mode == RDT_MODE_SHAREABLE) ||
+	    (!strcmp(buf, "exclusive") && mode == RDT_MODE_EXCLUSIVE) ||
+	    (!strcmp(buf, "pseudo-locksetup") &&
+	     mode == RDT_MODE_PSEUDO_LOCKSETUP) ||
+	    (!strcmp(buf, "pseudo-locked") && mode == RDT_MODE_PSEUDO_LOCKED))
+		goto out;
+
+	if (mode == RDT_MODE_PSEUDO_LOCKED) {
+		rdt_last_cmd_puts("Cannot change pseudo-locked group\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (!strcmp(buf, "shareable")) {
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+			ret = rdtgroup_locksetup_exit(rdtgrp);
+			if (ret)
+				goto out;
+		}
+		rdtgrp->mode = RDT_MODE_SHAREABLE;
+	} else if (!strcmp(buf, "exclusive")) {
+		if (!rdtgroup_mode_test_exclusive(rdtgrp)) {
+			ret = -EINVAL;
+			goto out;
+		}
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+			ret = rdtgroup_locksetup_exit(rdtgrp);
+			if (ret)
+				goto out;
+		}
+		rdtgrp->mode = RDT_MODE_EXCLUSIVE;
+	} else if (IS_ENABLED(CONFIG_RESCTRL_FS_PSEUDO_LOCK) &&
+		   !strcmp(buf, "pseudo-locksetup")) {
+		ret = rdtgroup_locksetup_enter(rdtgrp);
+		if (ret)
+			goto out;
+		rdtgrp->mode = RDT_MODE_PSEUDO_LOCKSETUP;
+	} else {
+		rdt_last_cmd_puts("Unknown or unsupported mode\n");
+		ret = -EINVAL;
+	}
+
+out:
+	rdtgroup_kn_unlock(of->kn);
+	return ret ?: nbytes;
+}
+
+/**
+ * rdtgroup_cbm_to_size - Translate CBM to size in bytes
+ * @r: RDT resource to which @d belongs.
+ * @d: RDT domain instance.
+ * @cbm: bitmask for which the size should be computed.
+ *
+ * The bitmask provided associated with the RDT domain instance @d will be
+ * translated into how many bytes it represents. The size in bytes is
+ * computed by first dividing the total cache size by the CBM length to
+ * determine how many bytes each bit in the bitmask represents. The result
+ * is multiplied with the number of bits set in the bitmask.
+ *
+ * @cbm is unsigned long, even if only 32 bits are used to make the
+ * bitmap functions work correctly.
+ */
+unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
+				  struct rdt_ctrl_domain *d, unsigned long cbm)
+{
+	unsigned int size = 0;
+	struct cacheinfo *ci;
+	int num_b;
+
+	if (WARN_ON_ONCE(r->ctrl_scope != RESCTRL_L2_CACHE && r->ctrl_scope != RESCTRL_L3_CACHE))
+		return size;
+
+	num_b = bitmap_weight(&cbm, r->cache.cbm_len);
+	ci = get_cpu_cacheinfo_level(cpumask_any(&d->hdr.cpu_mask), r->ctrl_scope);
+	if (ci)
+		size = ci->size / r->cache.cbm_len * num_b;
+
+	return size;
+}
+
+bool is_mba_sc(struct rdt_resource *r)
+{
+	if (!r)
+		r = resctrl_arch_get_resource(RDT_RESOURCE_MBA);
+
+	/*
+	 * The software controller support is only applicable to MBA resource.
+	 * Make sure to check for resource type.
+	 */
+	if (r->rid != RDT_RESOURCE_MBA)
+		return false;
+
+	return r->membw.mba_sc;
+}
+
+/*
+ * rdtgroup_size_show - Display size in bytes of allocated regions
+ *
+ * The "size" file mirrors the layout of the "schemata" file, printing the
+ * size in bytes of each region instead of the capacity bitmask.
+ */
+static int rdtgroup_size_show(struct kernfs_open_file *of,
+			      struct seq_file *s, void *v)
+{
+	struct resctrl_schema *schema;
+	enum resctrl_conf_type type;
+	struct rdt_ctrl_domain *d;
+	struct rdtgroup *rdtgrp;
+	struct rdt_resource *r;
+	unsigned int size;
+	int ret = 0;
+	u32 closid;
+	bool sep;
+	u32 ctrl;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		rdtgroup_kn_unlock(of->kn);
+		return -ENOENT;
+	}
+
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
+		if (!rdtgrp->plr->d) {
+			rdt_last_cmd_clear();
+			rdt_last_cmd_puts("Cache domain offline\n");
+			ret = -ENODEV;
+		} else {
+			seq_printf(s, "%*s:", max_name_width,
+				   rdtgrp->plr->s->name);
+			size = rdtgroup_cbm_to_size(rdtgrp->plr->s->res,
+						    rdtgrp->plr->d,
+						    rdtgrp->plr->cbm);
+			seq_printf(s, "%d=%u\n", rdtgrp->plr->d->hdr.id, size);
+		}
+		goto out;
+	}
+
+	closid = rdtgrp->closid;
+
+	list_for_each_entry(schema, &resctrl_schema_all, list) {
+		r = schema->res;
+		type = schema->conf_type;
+		sep = false;
+		seq_printf(s, "%*s:", max_name_width, schema->name);
+		list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
+			if (sep)
+				seq_putc(s, ';');
+			if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+				size = 0;
+			} else {
+				if (is_mba_sc(r))
+					ctrl = d->mbps_val[closid];
+				else
+					ctrl = resctrl_arch_get_config(r, d,
+								       closid,
+								       type);
+				if (r->rid == RDT_RESOURCE_MBA ||
+				    r->rid == RDT_RESOURCE_SMBA)
+					size = ctrl;
+				else
+					size = rdtgroup_cbm_to_size(r, d, ctrl);
+			}
+			seq_printf(s, "%d=%u", d->hdr.id, size);
+			sep = true;
+		}
+		seq_putc(s, '\n');
+	}
+
+out:
+	rdtgroup_kn_unlock(of->kn);
+
+	return ret;
+}
+
+static void mondata_config_read(struct resctrl_mon_config_info *mon_info)
+{
+	smp_call_function_any(&mon_info->d->hdr.cpu_mask,
+			      resctrl_arch_mon_event_config_read, mon_info, 1);
+}
+
+static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid)
+{
+	struct resctrl_mon_config_info mon_info;
+	struct rdt_mon_domain *dom;
+	bool sep = false;
+
+	cpus_read_lock();
+	mutex_lock(&rdtgroup_mutex);
+
+	list_for_each_entry(dom, &r->mon_domains, hdr.list) {
+		if (sep)
+			seq_puts(s, ";");
+
+		memset(&mon_info, 0, sizeof(struct resctrl_mon_config_info));
+		mon_info.r = r;
+		mon_info.d = dom;
+		mon_info.evtid = evtid;
+		mondata_config_read(&mon_info);
+
+		seq_printf(s, "%d=0x%02x", dom->hdr.id, mon_info.mon_config);
+		sep = true;
+	}
+	seq_puts(s, "\n");
+
+	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
+
+	return 0;
+}
+
+static int mbm_total_bytes_config_show(struct kernfs_open_file *of,
+				       struct seq_file *seq, void *v)
+{
+	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
+
+	mbm_config_show(seq, r, QOS_L3_MBM_TOTAL_EVENT_ID);
+
+	return 0;
+}
+
+static int mbm_local_bytes_config_show(struct kernfs_open_file *of,
+				       struct seq_file *seq, void *v)
+{
+	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
+
+	mbm_config_show(seq, r, QOS_L3_MBM_LOCAL_EVENT_ID);
+
+	return 0;
+}
+
+static void mbm_config_write_domain(struct rdt_resource *r,
+				    struct rdt_mon_domain *d, u32 evtid, u32 val)
+{
+	struct resctrl_mon_config_info mon_info = {0};
+
+	/*
+	 * Read the current config value first. If both are the same then
+	 * no need to write it again.
+	 */
+	mon_info.r = r;
+	mon_info.d = d;
+	mon_info.evtid = evtid;
+	mondata_config_read(&mon_info);
+	if (mon_info.mon_config == val)
+		return;
+
+	mon_info.mon_config = val;
+
+	/*
+	 * Update MSR_IA32_EVT_CFG_BASE MSR on one of the CPUs in the
+	 * domain. The MSRs offset from MSR MSR_IA32_EVT_CFG_BASE
+	 * are scoped at the domain level. Writing any of these MSRs
+	 * on one CPU is observed by all the CPUs in the domain.
+	 */
+	smp_call_function_any(&d->hdr.cpu_mask, resctrl_arch_mon_event_config_write,
+			      &mon_info, 1);
+
+	/*
+	 * When an Event Configuration is changed, the bandwidth counters
+	 * for all RMIDs and Events will be cleared by the hardware. The
+	 * hardware also sets MSR_IA32_QM_CTR.Unavailable (bit 62) for
+	 * every RMID on the next read to any event for every RMID.
+	 * Subsequent reads will have MSR_IA32_QM_CTR.Unavailable (bit 62)
+	 * cleared while it is tracked by the hardware. Clear the
+	 * mbm_local and mbm_total counts for all the RMIDs.
+	 */
+	resctrl_arch_reset_rmid_all(r, d);
+}
+
+static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid)
+{
+	char *dom_str = NULL, *id_str;
+	unsigned long dom_id, val;
+	struct rdt_mon_domain *d;
+
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
+next:
+	if (!tok || tok[0] == '\0')
+		return 0;
+
+	/* Start processing the strings for each domain */
+	dom_str = strim(strsep(&tok, ";"));
+	id_str = strsep(&dom_str, "=");
+
+	if (!id_str || kstrtoul(id_str, 10, &dom_id)) {
+		rdt_last_cmd_puts("Missing '=' or non-numeric domain id\n");
+		return -EINVAL;
+	}
+
+	if (!dom_str || kstrtoul(dom_str, 16, &val)) {
+		rdt_last_cmd_puts("Non-numeric event configuration value\n");
+		return -EINVAL;
+	}
+
+	/* Value from user cannot be more than the supported set of events */
+	if ((val & r->mbm_cfg_mask) != val) {
+		rdt_last_cmd_printf("Invalid event configuration: max valid mask is 0x%02x\n",
+				    r->mbm_cfg_mask);
+		return -EINVAL;
+	}
+
+	list_for_each_entry(d, &r->mon_domains, hdr.list) {
+		if (d->hdr.id == dom_id) {
+			mbm_config_write_domain(r, d, evtid, val);
+			goto next;
+		}
+	}
+
+	return -EINVAL;
+}
+
+static ssize_t mbm_total_bytes_config_write(struct kernfs_open_file *of,
+					    char *buf, size_t nbytes,
+					    loff_t off)
+{
+	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
+	int ret;
+
+	/* Valid input requires a trailing newline */
+	if (nbytes == 0 || buf[nbytes - 1] != '\n')
+		return -EINVAL;
+
+	cpus_read_lock();
+	mutex_lock(&rdtgroup_mutex);
+
+	rdt_last_cmd_clear();
+
+	buf[nbytes - 1] = '\0';
+
+	ret = mon_config_write(r, buf, QOS_L3_MBM_TOTAL_EVENT_ID);
+
+	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
+
+	return ret ?: nbytes;
+}
+
+static ssize_t mbm_local_bytes_config_write(struct kernfs_open_file *of,
+					    char *buf, size_t nbytes,
+					    loff_t off)
+{
+	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
+	int ret;
+
+	/* Valid input requires a trailing newline */
+	if (nbytes == 0 || buf[nbytes - 1] != '\n')
+		return -EINVAL;
+
+	cpus_read_lock();
+	mutex_lock(&rdtgroup_mutex);
+
+	rdt_last_cmd_clear();
+
+	buf[nbytes - 1] = '\0';
+
+	ret = mon_config_write(r, buf, QOS_L3_MBM_LOCAL_EVENT_ID);
+
+	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
+
+	return ret ?: nbytes;
+}
+
+/* rdtgroup information files for one cache resource. */
+static struct rftype res_common_files[] = {
+	{
+		.name		= "last_cmd_status",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_last_cmd_status_show,
+		.fflags		= RFTYPE_TOP_INFO,
+	},
+	{
+		.name		= "num_closids",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_num_closids_show,
+		.fflags		= RFTYPE_CTRL_INFO,
+	},
+	{
+		.name		= "mon_features",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_mon_features_show,
+		.fflags		= RFTYPE_MON_INFO,
+	},
+	{
+		.name		= "num_rmids",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_num_rmids_show,
+		.fflags		= RFTYPE_MON_INFO,
+	},
+	{
+		.name		= "cbm_mask",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_default_ctrl_show,
+		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
+	},
+	{
+		.name		= "min_cbm_bits",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_min_cbm_bits_show,
+		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
+	},
+	{
+		.name		= "shareable_bits",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_shareable_bits_show,
+		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
+	},
+	{
+		.name		= "bit_usage",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_bit_usage_show,
+		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
+	},
+	{
+		.name		= "min_bandwidth",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_min_bw_show,
+		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_MB,
+	},
+	{
+		.name		= "bandwidth_gran",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_bw_gran_show,
+		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_MB,
+	},
+	{
+		.name		= "delay_linear",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_delay_linear_show,
+		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_MB,
+	},
+	/*
+	 * Platform specific which (if any) capabilities are provided by
+	 * thread_throttle_mode. Defer "fflags" initialization to platform
+	 * discovery.
+	 */
+	{
+		.name		= "thread_throttle_mode",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_thread_throttle_mode_show,
+	},
+	{
+		.name		= "max_threshold_occupancy",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.write		= max_threshold_occ_write,
+		.seq_show	= max_threshold_occ_show,
+		.fflags		= RFTYPE_MON_INFO | RFTYPE_RES_CACHE,
+	},
+	{
+		.name		= "mbm_total_bytes_config",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= mbm_total_bytes_config_show,
+		.write		= mbm_total_bytes_config_write,
+	},
+	{
+		.name		= "mbm_local_bytes_config",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= mbm_local_bytes_config_show,
+		.write		= mbm_local_bytes_config_write,
+	},
+	{
+		.name		= "cpus",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.write		= rdtgroup_cpus_write,
+		.seq_show	= rdtgroup_cpus_show,
+		.fflags		= RFTYPE_BASE,
+	},
+	{
+		.name		= "cpus_list",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.write		= rdtgroup_cpus_write,
+		.seq_show	= rdtgroup_cpus_show,
+		.flags		= RFTYPE_FLAGS_CPUS_LIST,
+		.fflags		= RFTYPE_BASE,
+	},
+	{
+		.name		= "tasks",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.write		= rdtgroup_tasks_write,
+		.seq_show	= rdtgroup_tasks_show,
+		.fflags		= RFTYPE_BASE,
+	},
+	{
+		.name		= "mon_hw_id",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdtgroup_rmid_show,
+		.fflags		= RFTYPE_MON_BASE | RFTYPE_DEBUG,
+	},
+	{
+		.name		= "schemata",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.write		= rdtgroup_schemata_write,
+		.seq_show	= rdtgroup_schemata_show,
+		.fflags		= RFTYPE_CTRL_BASE,
+	},
+	{
+		.name		= "mba_MBps_event",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.write		= rdtgroup_mba_mbps_event_write,
+		.seq_show	= rdtgroup_mba_mbps_event_show,
+	},
+	{
+		.name		= "mode",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.write		= rdtgroup_mode_write,
+		.seq_show	= rdtgroup_mode_show,
+		.fflags		= RFTYPE_CTRL_BASE,
+	},
+	{
+		.name		= "size",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdtgroup_size_show,
+		.fflags		= RFTYPE_CTRL_BASE,
+	},
+	{
+		.name		= "sparse_masks",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_has_sparse_bitmasks_show,
+		.fflags		= RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
+	},
+	{
+		.name		= "ctrl_hw_id",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdtgroup_closid_show,
+		.fflags		= RFTYPE_CTRL_BASE | RFTYPE_DEBUG,
+	},
+};
+
+static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags)
+{
+	struct rftype *rfts, *rft;
+	int ret, len;
+
+	rfts = res_common_files;
+	len = ARRAY_SIZE(res_common_files);
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	if (resctrl_debug)
+		fflags |= RFTYPE_DEBUG;
+
+	for (rft = rfts; rft < rfts + len; rft++) {
+		if (rft->fflags && ((fflags & rft->fflags) == rft->fflags)) {
+			ret = rdtgroup_add_file(kn, rft);
+			if (ret)
+				goto error;
+		}
+	}
+
+	return 0;
+error:
+	pr_warn("Failed to add %s, err=%d\n", rft->name, ret);
+	while (--rft >= rfts) {
+		if ((fflags & rft->fflags) == rft->fflags)
+			kernfs_remove_by_name(kn, rft->name);
+	}
+	return ret;
+}
+
+static struct rftype *rdtgroup_get_rftype_by_name(const char *name)
+{
+	struct rftype *rfts, *rft;
+	int len;
+
+	rfts = res_common_files;
+	len = ARRAY_SIZE(res_common_files);
+
+	for (rft = rfts; rft < rfts + len; rft++) {
+		if (!strcmp(rft->name, name))
+			return rft;
+	}
+
+	return NULL;
+}
+
+static void thread_throttle_mode_init(void)
+{
+	enum membw_throttle_mode throttle_mode = THREAD_THROTTLE_UNDEFINED;
+	struct rdt_resource *r_mba, *r_smba;
+
+	r_mba = resctrl_arch_get_resource(RDT_RESOURCE_MBA);
+	if (r_mba->alloc_capable &&
+	    r_mba->membw.throttle_mode != THREAD_THROTTLE_UNDEFINED)
+		throttle_mode = r_mba->membw.throttle_mode;
+
+	r_smba = resctrl_arch_get_resource(RDT_RESOURCE_SMBA);
+	if (r_smba->alloc_capable &&
+	    r_smba->membw.throttle_mode != THREAD_THROTTLE_UNDEFINED)
+		throttle_mode = r_smba->membw.throttle_mode;
+
+	if (throttle_mode == THREAD_THROTTLE_UNDEFINED)
+		return;
+
+	resctrl_file_fflags_init("thread_throttle_mode",
+				 RFTYPE_CTRL_INFO | RFTYPE_RES_MB);
+}
+
+void resctrl_file_fflags_init(const char *config, unsigned long fflags)
+{
+	struct rftype *rft;
+
+	rft = rdtgroup_get_rftype_by_name(config);
+	if (rft)
+		rft->fflags = fflags;
+}
+
+/**
+ * rdtgroup_kn_mode_restrict - Restrict user access to named resctrl file
+ * @r: The resource group with which the file is associated.
+ * @name: Name of the file
+ *
+ * The permissions of named resctrl file, directory, or link are modified
+ * to not allow read, write, or execute by any user.
+ *
+ * WARNING: This function is intended to communicate to the user that the
+ * resctrl file has been locked down - that it is not relevant to the
+ * particular state the system finds itself in. It should not be relied
+ * on to protect from user access because after the file's permissions
+ * are restricted the user can still change the permissions using chmod
+ * from the command line.
+ *
+ * Return: 0 on success, <0 on failure.
+ */
+int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name)
+{
+	struct iattr iattr = {.ia_valid = ATTR_MODE,};
+	struct kernfs_node *kn;
+	int ret = 0;
+
+	kn = kernfs_find_and_get_ns(r->kn, name, NULL);
+	if (!kn)
+		return -ENOENT;
+
+	switch (kernfs_type(kn)) {
+	case KERNFS_DIR:
+		iattr.ia_mode = S_IFDIR;
+		break;
+	case KERNFS_FILE:
+		iattr.ia_mode = S_IFREG;
+		break;
+	case KERNFS_LINK:
+		iattr.ia_mode = S_IFLNK;
+		break;
+	}
+
+	ret = kernfs_setattr(kn, &iattr);
+	kernfs_put(kn);
+	return ret;
+}
+
+/**
+ * rdtgroup_kn_mode_restore - Restore user access to named resctrl file
+ * @r: The resource group with which the file is associated.
+ * @name: Name of the file
+ * @mask: Mask of permissions that should be restored
+ *
+ * Restore the permissions of the named file. If @name is a directory the
+ * permissions of its parent will be used.
+ *
+ * Return: 0 on success, <0 on failure.
+ */
+int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name,
+			     umode_t mask)
+{
+	struct iattr iattr = {.ia_valid = ATTR_MODE,};
+	struct kernfs_node *kn, *parent;
+	struct rftype *rfts, *rft;
+	int ret, len;
+
+	rfts = res_common_files;
+	len = ARRAY_SIZE(res_common_files);
+
+	for (rft = rfts; rft < rfts + len; rft++) {
+		if (!strcmp(rft->name, name))
+			iattr.ia_mode = rft->mode & mask;
+	}
+
+	kn = kernfs_find_and_get_ns(r->kn, name, NULL);
+	if (!kn)
+		return -ENOENT;
+
+	switch (kernfs_type(kn)) {
+	case KERNFS_DIR:
+		parent = kernfs_get_parent(kn);
+		if (parent) {
+			iattr.ia_mode |= parent->mode;
+			kernfs_put(parent);
+		}
+		iattr.ia_mode |= S_IFDIR;
+		break;
+	case KERNFS_FILE:
+		iattr.ia_mode |= S_IFREG;
+		break;
+	case KERNFS_LINK:
+		iattr.ia_mode |= S_IFLNK;
+		break;
+	}
+
+	ret = kernfs_setattr(kn, &iattr);
+	kernfs_put(kn);
+	return ret;
+}
+
+static int rdtgroup_mkdir_info_resdir(void *priv, char *name,
+				      unsigned long fflags)
+{
+	struct kernfs_node *kn_subdir;
+	int ret;
+
+	kn_subdir = kernfs_create_dir(kn_info, name,
+				      kn_info->mode, priv);
+	if (IS_ERR(kn_subdir))
+		return PTR_ERR(kn_subdir);
+
+	ret = rdtgroup_kn_set_ugid(kn_subdir);
+	if (ret)
+		return ret;
+
+	ret = rdtgroup_add_files(kn_subdir, fflags);
+	if (!ret)
+		kernfs_activate(kn_subdir);
+
+	return ret;
+}
+
+static unsigned long fflags_from_resource(struct rdt_resource *r)
+{
+	switch (r->rid) {
+	case RDT_RESOURCE_L3:
+	case RDT_RESOURCE_L2:
+		return RFTYPE_RES_CACHE;
+	case RDT_RESOURCE_MBA:
+	case RDT_RESOURCE_SMBA:
+		return RFTYPE_RES_MB;
+	}
+
+	return WARN_ON_ONCE(1);
+}
+
+static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
+{
+	struct resctrl_schema *s;
+	struct rdt_resource *r;
+	unsigned long fflags;
+	char name[32];
+	int ret;
+
+	/* create the directory */
+	kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL);
+	if (IS_ERR(kn_info))
+		return PTR_ERR(kn_info);
+
+	ret = rdtgroup_add_files(kn_info, RFTYPE_TOP_INFO);
+	if (ret)
+		goto out_destroy;
+
+	/* loop over enabled controls, these are all alloc_capable */
+	list_for_each_entry(s, &resctrl_schema_all, list) {
+		r = s->res;
+		fflags = fflags_from_resource(r) | RFTYPE_CTRL_INFO;
+		ret = rdtgroup_mkdir_info_resdir(s, s->name, fflags);
+		if (ret)
+			goto out_destroy;
+	}
+
+	for_each_mon_capable_rdt_resource(r) {
+		fflags = fflags_from_resource(r) | RFTYPE_MON_INFO;
+		sprintf(name, "%s_MON", r->name);
+		ret = rdtgroup_mkdir_info_resdir(r, name, fflags);
+		if (ret)
+			goto out_destroy;
+	}
+
+	ret = rdtgroup_kn_set_ugid(kn_info);
+	if (ret)
+		goto out_destroy;
+
+	kernfs_activate(kn_info);
+
+	return 0;
+
+out_destroy:
+	kernfs_remove(kn_info);
+	return ret;
+}
+
+static int
+mongroup_create_dir(struct kernfs_node *parent_kn, struct rdtgroup *prgrp,
+		    char *name, struct kernfs_node **dest_kn)
+{
+	struct kernfs_node *kn;
+	int ret;
+
+	/* create the directory */
+	kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp);
+	if (IS_ERR(kn))
+		return PTR_ERR(kn);
+
+	if (dest_kn)
+		*dest_kn = kn;
+
+	ret = rdtgroup_kn_set_ugid(kn);
+	if (ret)
+		goto out_destroy;
+
+	kernfs_activate(kn);
+
+	return 0;
+
+out_destroy:
+	kernfs_remove(kn);
+	return ret;
+}
+
+static inline bool is_mba_linear(void)
+{
+	return resctrl_arch_get_resource(RDT_RESOURCE_MBA)->membw.delay_linear;
+}
+
+static int mba_sc_domain_allocate(struct rdt_resource *r, struct rdt_ctrl_domain *d)
+{
+	u32 num_closid = resctrl_arch_get_num_closid(r);
+	int cpu = cpumask_any(&d->hdr.cpu_mask);
+	int i;
+
+	d->mbps_val = kcalloc_node(num_closid, sizeof(*d->mbps_val),
+				   GFP_KERNEL, cpu_to_node(cpu));
+	if (!d->mbps_val)
+		return -ENOMEM;
+
+	for (i = 0; i < num_closid; i++)
+		d->mbps_val[i] = MBA_MAX_MBPS;
+
+	return 0;
+}
+
+static void mba_sc_domain_destroy(struct rdt_resource *r,
+				  struct rdt_ctrl_domain *d)
+{
+	kfree(d->mbps_val);
+	d->mbps_val = NULL;
+}
+
+/*
+ * MBA software controller is supported only if
+ * MBM is supported and MBA is in linear scale,
+ * and the MBM monitor scope is the same as MBA
+ * control scope.
+ */
+static bool supports_mba_mbps(void)
+{
+	struct rdt_resource *rmbm = resctrl_arch_get_resource(RDT_RESOURCE_L3);
+	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_MBA);
+
+	return (resctrl_is_mbm_enabled() &&
+		r->alloc_capable && is_mba_linear() &&
+		r->ctrl_scope == rmbm->mon_scope);
+}
+
+/*
+ * Enable or disable the MBA software controller
+ * which helps user specify bandwidth in MBps.
+ */
+static int set_mba_sc(bool mba_sc)
+{
+	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_MBA);
+	u32 num_closid = resctrl_arch_get_num_closid(r);
+	struct rdt_ctrl_domain *d;
+	unsigned long fflags;
+	int i;
+
+	if (!supports_mba_mbps() || mba_sc == is_mba_sc(r))
+		return -EINVAL;
+
+	r->membw.mba_sc = mba_sc;
+
+	rdtgroup_default.mba_mbps_event = mba_mbps_default_event;
+
+	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
+		for (i = 0; i < num_closid; i++)
+			d->mbps_val[i] = MBA_MAX_MBPS;
+	}
+
+	fflags = mba_sc ? RFTYPE_CTRL_BASE | RFTYPE_MON_BASE : 0;
+	resctrl_file_fflags_init("mba_MBps_event", fflags);
+
+	return 0;
+}
+
+/*
+ * We don't allow rdtgroup directories to be created anywhere
+ * except the root directory. Thus when looking for the rdtgroup
+ * structure for a kernfs node we are either looking at a directory,
+ * in which case the rdtgroup structure is pointed at by the "priv"
+ * field, otherwise we have a file, and need only look to the parent
+ * to find the rdtgroup.
+ */
+static struct rdtgroup *kernfs_to_rdtgroup(struct kernfs_node *kn)
+{
+	if (kernfs_type(kn) == KERNFS_DIR) {
+		/*
+		 * All the resource directories use "kn->priv"
+		 * to point to the "struct rdtgroup" for the
+		 * resource. "info" and its subdirectories don't
+		 * have rdtgroup structures, so return NULL here.
+		 */
+		if (kn == kn_info ||
+		    rcu_access_pointer(kn->__parent) == kn_info)
+			return NULL;
+		else
+			return kn->priv;
+	} else {
+		return rdt_kn_parent_priv(kn);
+	}
+}
+
+static void rdtgroup_kn_get(struct rdtgroup *rdtgrp, struct kernfs_node *kn)
+{
+	atomic_inc(&rdtgrp->waitcount);
+	kernfs_break_active_protection(kn);
+}
+
+static void rdtgroup_kn_put(struct rdtgroup *rdtgrp, struct kernfs_node *kn)
+{
+	if (atomic_dec_and_test(&rdtgrp->waitcount) &&
+	    (rdtgrp->flags & RDT_DELETED)) {
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
+		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
+			rdtgroup_pseudo_lock_remove(rdtgrp);
+		kernfs_unbreak_active_protection(kn);
+		rdtgroup_remove(rdtgrp);
+	} else {
+		kernfs_unbreak_active_protection(kn);
+	}
+}
+
+struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn)
+{
+	struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn);
+
+	if (!rdtgrp)
+		return NULL;
+
+	rdtgroup_kn_get(rdtgrp, kn);
+
+	cpus_read_lock();
+	mutex_lock(&rdtgroup_mutex);
+
+	/* Was this group deleted while we waited? */
+	if (rdtgrp->flags & RDT_DELETED)
+		return NULL;
+
+	return rdtgrp;
+}
+
+void rdtgroup_kn_unlock(struct kernfs_node *kn)
+{
+	struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn);
+
+	if (!rdtgrp)
+		return;
+
+	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
+
+	rdtgroup_kn_put(rdtgrp, kn);
+}
+
+static int mkdir_mondata_all(struct kernfs_node *parent_kn,
+			     struct rdtgroup *prgrp,
+			     struct kernfs_node **mon_data_kn);
+
+static void rdt_disable_ctx(void)
+{
+	resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false);
+	resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false);
+	set_mba_sc(false);
+
+	resctrl_debug = false;
+}
+
+static int rdt_enable_ctx(struct rdt_fs_context *ctx)
+{
+	int ret = 0;
+
+	if (ctx->enable_cdpl2) {
+		ret = resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, true);
+		if (ret)
+			goto out_done;
+	}
+
+	if (ctx->enable_cdpl3) {
+		ret = resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, true);
+		if (ret)
+			goto out_cdpl2;
+	}
+
+	if (ctx->enable_mba_mbps) {
+		ret = set_mba_sc(true);
+		if (ret)
+			goto out_cdpl3;
+	}
+
+	if (ctx->enable_debug)
+		resctrl_debug = true;
+
+	return 0;
+
+out_cdpl3:
+	resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false);
+out_cdpl2:
+	resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false);
+out_done:
+	return ret;
+}
+
+static int schemata_list_add(struct rdt_resource *r, enum resctrl_conf_type type)
+{
+	struct resctrl_schema *s;
+	const char *suffix = "";
+	int ret, cl;
+
+	s = kzalloc(sizeof(*s), GFP_KERNEL);
+	if (!s)
+		return -ENOMEM;
+
+	s->res = r;
+	s->num_closid = resctrl_arch_get_num_closid(r);
+	if (resctrl_arch_get_cdp_enabled(r->rid))
+		s->num_closid /= 2;
+
+	s->conf_type = type;
+	switch (type) {
+	case CDP_CODE:
+		suffix = "CODE";
+		break;
+	case CDP_DATA:
+		suffix = "DATA";
+		break;
+	case CDP_NONE:
+		suffix = "";
+		break;
+	}
+
+	ret = snprintf(s->name, sizeof(s->name), "%s%s", r->name, suffix);
+	if (ret >= sizeof(s->name)) {
+		kfree(s);
+		return -EINVAL;
+	}
+
+	cl = strlen(s->name);
+
+	/*
+	 * If CDP is supported by this resource, but not enabled,
+	 * include the suffix. This ensures the tabular format of the
+	 * schemata file does not change between mounts of the filesystem.
+	 */
+	if (r->cdp_capable && !resctrl_arch_get_cdp_enabled(r->rid))
+		cl += 4;
+
+	if (cl > max_name_width)
+		max_name_width = cl;
+
+	switch (r->schema_fmt) {
+	case RESCTRL_SCHEMA_BITMAP:
+		s->fmt_str = "%d=%x";
+		break;
+	case RESCTRL_SCHEMA_RANGE:
+		s->fmt_str = "%d=%u";
+		break;
+	}
+
+	if (WARN_ON_ONCE(!s->fmt_str)) {
+		kfree(s);
+		return -EINVAL;
+	}
+
+	INIT_LIST_HEAD(&s->list);
+	list_add(&s->list, &resctrl_schema_all);
+
+	return 0;
+}
+
+static int schemata_list_create(void)
+{
+	struct rdt_resource *r;
+	int ret = 0;
+
+	for_each_alloc_capable_rdt_resource(r) {
+		if (resctrl_arch_get_cdp_enabled(r->rid)) {
+			ret = schemata_list_add(r, CDP_CODE);
+			if (ret)
+				break;
+
+			ret = schemata_list_add(r, CDP_DATA);
+		} else {
+			ret = schemata_list_add(r, CDP_NONE);
+		}
+
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+static void schemata_list_destroy(void)
+{
+	struct resctrl_schema *s, *tmp;
+
+	list_for_each_entry_safe(s, tmp, &resctrl_schema_all, list) {
+		list_del(&s->list);
+		kfree(s);
+	}
+}
+
+static int rdt_get_tree(struct fs_context *fc)
+{
+	struct rdt_fs_context *ctx = rdt_fc2context(fc);
+	unsigned long flags = RFTYPE_CTRL_BASE;
+	struct rdt_mon_domain *dom;
+	struct rdt_resource *r;
+	int ret;
+
+	cpus_read_lock();
+	mutex_lock(&rdtgroup_mutex);
+	/*
+	 * resctrl file system can only be mounted once.
+	 */
+	if (resctrl_mounted) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	ret = rdtgroup_setup_root(ctx);
+	if (ret)
+		goto out;
+
+	ret = rdt_enable_ctx(ctx);
+	if (ret)
+		goto out_root;
+
+	ret = schemata_list_create();
+	if (ret) {
+		schemata_list_destroy();
+		goto out_ctx;
+	}
+
+	ret = closid_init();
+	if (ret)
+		goto out_schemata_free;
+
+	if (resctrl_arch_mon_capable())
+		flags |= RFTYPE_MON;
+
+	ret = rdtgroup_add_files(rdtgroup_default.kn, flags);
+	if (ret)
+		goto out_closid_exit;
+
+	kernfs_activate(rdtgroup_default.kn);
+
+	ret = rdtgroup_create_info_dir(rdtgroup_default.kn);
+	if (ret < 0)
+		goto out_closid_exit;
+
+	if (resctrl_arch_mon_capable()) {
+		ret = mongroup_create_dir(rdtgroup_default.kn,
+					  &rdtgroup_default, "mon_groups",
+					  &kn_mongrp);
+		if (ret < 0)
+			goto out_info;
+
+		ret = mkdir_mondata_all(rdtgroup_default.kn,
+					&rdtgroup_default, &kn_mondata);
+		if (ret < 0)
+			goto out_mongrp;
+		rdtgroup_default.mon.mon_data_kn = kn_mondata;
+	}
+
+	ret = rdt_pseudo_lock_init();
+	if (ret)
+		goto out_mondata;
+
+	ret = kernfs_get_tree(fc);
+	if (ret < 0)
+		goto out_psl;
+
+	if (resctrl_arch_alloc_capable())
+		resctrl_arch_enable_alloc();
+	if (resctrl_arch_mon_capable())
+		resctrl_arch_enable_mon();
+
+	if (resctrl_arch_alloc_capable() || resctrl_arch_mon_capable())
+		resctrl_mounted = true;
+
+	if (resctrl_is_mbm_enabled()) {
+		r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
+		list_for_each_entry(dom, &r->mon_domains, hdr.list)
+			mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL,
+						   RESCTRL_PICK_ANY_CPU);
+	}
+
+	goto out;
+
+out_psl:
+	rdt_pseudo_lock_release();
+out_mondata:
+	if (resctrl_arch_mon_capable())
+		kernfs_remove(kn_mondata);
+out_mongrp:
+	if (resctrl_arch_mon_capable())
+		kernfs_remove(kn_mongrp);
+out_info:
+	kernfs_remove(kn_info);
+out_closid_exit:
+	closid_exit();
+out_schemata_free:
+	schemata_list_destroy();
+out_ctx:
+	rdt_disable_ctx();
+out_root:
+	rdtgroup_destroy_root();
+out:
+	rdt_last_cmd_clear();
+	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
+	return ret;
+}
+
+enum rdt_param {
+	Opt_cdp,
+	Opt_cdpl2,
+	Opt_mba_mbps,
+	Opt_debug,
+	nr__rdt_params
+};
+
+static const struct fs_parameter_spec rdt_fs_parameters[] = {
+	fsparam_flag("cdp",		Opt_cdp),
+	fsparam_flag("cdpl2",		Opt_cdpl2),
+	fsparam_flag("mba_MBps",	Opt_mba_mbps),
+	fsparam_flag("debug",		Opt_debug),
+	{}
+};
+
+static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	struct rdt_fs_context *ctx = rdt_fc2context(fc);
+	struct fs_parse_result result;
+	const char *msg;
+	int opt;
+
+	opt = fs_parse(fc, rdt_fs_parameters, param, &result);
+	if (opt < 0)
+		return opt;
+
+	switch (opt) {
+	case Opt_cdp:
+		ctx->enable_cdpl3 = true;
+		return 0;
+	case Opt_cdpl2:
+		ctx->enable_cdpl2 = true;
+		return 0;
+	case Opt_mba_mbps:
+		msg = "mba_MBps requires MBM and linear scale MBA at L3 scope";
+		if (!supports_mba_mbps())
+			return invalfc(fc, msg);
+		ctx->enable_mba_mbps = true;
+		return 0;
+	case Opt_debug:
+		ctx->enable_debug = true;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static void rdt_fs_context_free(struct fs_context *fc)
+{
+	struct rdt_fs_context *ctx = rdt_fc2context(fc);
+
+	kernfs_free_fs_context(fc);
+	kfree(ctx);
+}
+
+static const struct fs_context_operations rdt_fs_context_ops = {
+	.free		= rdt_fs_context_free,
+	.parse_param	= rdt_parse_param,
+	.get_tree	= rdt_get_tree,
+};
+
+static int rdt_init_fs_context(struct fs_context *fc)
+{
+	struct rdt_fs_context *ctx;
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->kfc.magic = RDTGROUP_SUPER_MAGIC;
+	fc->fs_private = &ctx->kfc;
+	fc->ops = &rdt_fs_context_ops;
+	put_user_ns(fc->user_ns);
+	fc->user_ns = get_user_ns(&init_user_ns);
+	fc->global = true;
+	return 0;
+}
+
+/*
+ * Move tasks from one to the other group. If @from is NULL, then all tasks
+ * in the systems are moved unconditionally (used for teardown).
+ *
+ * If @mask is not NULL the cpus on which moved tasks are running are set
+ * in that mask so the update smp function call is restricted to affected
+ * cpus.
+ */
+static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to,
+				 struct cpumask *mask)
+{
+	struct task_struct *p, *t;
+
+	read_lock(&tasklist_lock);
+	for_each_process_thread(p, t) {
+		if (!from || is_closid_match(t, from) ||
+		    is_rmid_match(t, from)) {
+			resctrl_arch_set_closid_rmid(t, to->closid,
+						     to->mon.rmid);
+
+			/*
+			 * Order the closid/rmid stores above before the loads
+			 * in task_curr(). This pairs with the full barrier
+			 * between the rq->curr update and
+			 * resctrl_arch_sched_in() during context switch.
+			 */
+			smp_mb();
+
+			/*
+			 * If the task is on a CPU, set the CPU in the mask.
+			 * The detection is inaccurate as tasks might move or
+			 * schedule before the smp function call takes place.
+			 * In such a case the function call is pointless, but
+			 * there is no other side effect.
+			 */
+			if (IS_ENABLED(CONFIG_SMP) && mask && task_curr(t))
+				cpumask_set_cpu(task_cpu(t), mask);
+		}
+	}
+	read_unlock(&tasklist_lock);
+}
+
+static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp)
+{
+	struct rdtgroup *sentry, *stmp;
+	struct list_head *head;
+
+	head = &rdtgrp->mon.crdtgrp_list;
+	list_for_each_entry_safe(sentry, stmp, head, mon.crdtgrp_list) {
+		free_rmid(sentry->closid, sentry->mon.rmid);
+		list_del(&sentry->mon.crdtgrp_list);
+
+		if (atomic_read(&sentry->waitcount) != 0)
+			sentry->flags = RDT_DELETED;
+		else
+			rdtgroup_remove(sentry);
+	}
+}
+
+/*
+ * Forcibly remove all of subdirectories under root.
+ */
+static void rmdir_all_sub(void)
+{
+	struct rdtgroup *rdtgrp, *tmp;
+
+	/* Move all tasks to the default resource group */
+	rdt_move_group_tasks(NULL, &rdtgroup_default, NULL);
+
+	list_for_each_entry_safe(rdtgrp, tmp, &rdt_all_groups, rdtgroup_list) {
+		/* Free any child rmids */
+		free_all_child_rdtgrp(rdtgrp);
+
+		/* Remove each rdtgroup other than root */
+		if (rdtgrp == &rdtgroup_default)
+			continue;
+
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
+		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
+			rdtgroup_pseudo_lock_remove(rdtgrp);
+
+		/*
+		 * Give any CPUs back to the default group. We cannot copy
+		 * cpu_online_mask because a CPU might have executed the
+		 * offline callback already, but is still marked online.
+		 */
+		cpumask_or(&rdtgroup_default.cpu_mask,
+			   &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);
+
+		free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
+
+		kernfs_remove(rdtgrp->kn);
+		list_del(&rdtgrp->rdtgroup_list);
+
+		if (atomic_read(&rdtgrp->waitcount) != 0)
+			rdtgrp->flags = RDT_DELETED;
+		else
+			rdtgroup_remove(rdtgrp);
+	}
+	/* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */
+	update_closid_rmid(cpu_online_mask, &rdtgroup_default);
+
+	kernfs_remove(kn_info);
+	kernfs_remove(kn_mongrp);
+	kernfs_remove(kn_mondata);
+}
+
+/**
+ * mon_get_kn_priv() - Get the mon_data priv data for this event.
+ *
+ * The same values are used across the mon_data directories of all control and
+ * monitor groups for the same event in the same domain. Keep a list of
+ * allocated structures and re-use an existing one with the same values for
+ * @rid, @domid, etc.
+ *
+ * @rid:    The resource id for the event file being created.
+ * @domid:  The domain id for the event file being created.
+ * @mevt:   The type of event file being created.
+ * @do_sum: Whether SNC summing monitors are being created.
+ */
+static struct mon_data *mon_get_kn_priv(enum resctrl_res_level rid, int domid,
+					struct mon_evt *mevt,
+					bool do_sum)
+{
+	struct mon_data *priv;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	list_for_each_entry(priv, &mon_data_kn_priv_list, list) {
+		if (priv->rid == rid && priv->domid == domid &&
+		    priv->sum == do_sum && priv->evtid == mevt->evtid)
+			return priv;
+	}
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return NULL;
+
+	priv->rid = rid;
+	priv->domid = domid;
+	priv->sum = do_sum;
+	priv->evtid = mevt->evtid;
+	list_add_tail(&priv->list, &mon_data_kn_priv_list);
+
+	return priv;
+}
+
+/**
+ * mon_put_kn_priv() - Free all allocated mon_data structures.
+ *
+ * Called when resctrl file system is unmounted.
+ */
+static void mon_put_kn_priv(void)
+{
+	struct mon_data *priv, *tmp;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	list_for_each_entry_safe(priv, tmp, &mon_data_kn_priv_list, list) {
+		list_del(&priv->list);
+		kfree(priv);
+	}
+}
+
+static void resctrl_fs_teardown(void)
+{
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	/* Cleared by rdtgroup_destroy_root() */
+	if (!rdtgroup_default.kn)
+		return;
+
+	rmdir_all_sub();
+	mon_put_kn_priv();
+	rdt_pseudo_lock_release();
+	rdtgroup_default.mode = RDT_MODE_SHAREABLE;
+	closid_exit();
+	schemata_list_destroy();
+	rdtgroup_destroy_root();
+}
+
+static void rdt_kill_sb(struct super_block *sb)
+{
+	struct rdt_resource *r;
+
+	cpus_read_lock();
+	mutex_lock(&rdtgroup_mutex);
+
+	rdt_disable_ctx();
+
+	/* Put everything back to default values. */
+	for_each_alloc_capable_rdt_resource(r)
+		resctrl_arch_reset_all_ctrls(r);
+
+	resctrl_fs_teardown();
+	if (resctrl_arch_alloc_capable())
+		resctrl_arch_disable_alloc();
+	if (resctrl_arch_mon_capable())
+		resctrl_arch_disable_mon();
+	resctrl_mounted = false;
+	kernfs_kill_sb(sb);
+	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
+}
+
+static struct file_system_type rdt_fs_type = {
+	.name			= "resctrl",
+	.init_fs_context	= rdt_init_fs_context,
+	.parameters		= rdt_fs_parameters,
+	.kill_sb		= rdt_kill_sb,
+};
+
+static int mon_addfile(struct kernfs_node *parent_kn, const char *name,
+		       void *priv)
+{
+	struct kernfs_node *kn;
+	int ret = 0;
+
+	kn = __kernfs_create_file(parent_kn, name, 0444,
+				  GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, 0,
+				  &kf_mondata_ops, priv, NULL, NULL);
+	if (IS_ERR(kn))
+		return PTR_ERR(kn);
+
+	ret = rdtgroup_kn_set_ugid(kn);
+	if (ret) {
+		kernfs_remove(kn);
+		return ret;
+	}
+
+	return ret;
+}
+
+static void mon_rmdir_one_subdir(struct kernfs_node *pkn, char *name, char *subname)
+{
+	struct kernfs_node *kn;
+
+	kn = kernfs_find_and_get(pkn, name);
+	if (!kn)
+		return;
+	kernfs_put(kn);
+
+	if (kn->dir.subdirs <= 1)
+		kernfs_remove(kn);
+	else
+		kernfs_remove_by_name(kn, subname);
+}
+
+/*
+ * Remove all subdirectories of mon_data of ctrl_mon groups
+ * and monitor groups for the given domain.
+ * Remove files and directories containing "sum" of domain data
+ * when last domain being summed is removed.
+ */
+static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
+					   struct rdt_mon_domain *d)
+{
+	struct rdtgroup *prgrp, *crgrp;
+	char subname[32];
+	bool snc_mode;
+	char name[32];
+
+	snc_mode = r->mon_scope == RESCTRL_L3_NODE;
+	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci->id : d->hdr.id);
+	if (snc_mode)
+		sprintf(subname, "mon_sub_%s_%02d", r->name, d->hdr.id);
+
+	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
+		mon_rmdir_one_subdir(prgrp->mon.mon_data_kn, name, subname);
+
+		list_for_each_entry(crgrp, &prgrp->mon.crdtgrp_list, mon.crdtgrp_list)
+			mon_rmdir_one_subdir(crgrp->mon.mon_data_kn, name, subname);
+	}
+}
+
+static int mon_add_all_files(struct kernfs_node *kn, struct rdt_mon_domain *d,
+			     struct rdt_resource *r, struct rdtgroup *prgrp,
+			     bool do_sum)
+{
+	struct rmid_read rr = {0};
+	struct mon_data *priv;
+	struct mon_evt *mevt;
+	int ret, domid;
+
+	if (WARN_ON(list_empty(&r->evt_list)))
+		return -EPERM;
+
+	list_for_each_entry(mevt, &r->evt_list, list) {
+		domid = do_sum ? d->ci->id : d->hdr.id;
+		priv = mon_get_kn_priv(r->rid, domid, mevt, do_sum);
+		if (WARN_ON_ONCE(!priv))
+			return -EINVAL;
+
+		ret = mon_addfile(kn, mevt->name, priv);
+		if (ret)
+			return ret;
+
+		if (!do_sum && resctrl_is_mbm_event(mevt->evtid))
+			mon_event_read(&rr, r, d, prgrp, &d->hdr.cpu_mask, mevt->evtid, true);
+	}
+
+	return 0;
+}
+
+static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
+				struct rdt_mon_domain *d,
+				struct rdt_resource *r, struct rdtgroup *prgrp)
+{
+	struct kernfs_node *kn, *ckn;
+	char name[32];
+	bool snc_mode;
+	int ret = 0;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	snc_mode = r->mon_scope == RESCTRL_L3_NODE;
+	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci->id : d->hdr.id);
+	kn = kernfs_find_and_get(parent_kn, name);
+	if (kn) {
+		/*
+		 * rdtgroup_mutex will prevent this directory from being
+		 * removed. No need to keep this hold.
+		 */
+		kernfs_put(kn);
+	} else {
+		kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp);
+		if (IS_ERR(kn))
+			return PTR_ERR(kn);
+
+		ret = rdtgroup_kn_set_ugid(kn);
+		if (ret)
+			goto out_destroy;
+		ret = mon_add_all_files(kn, d, r, prgrp, snc_mode);
+		if (ret)
+			goto out_destroy;
+	}
+
+	if (snc_mode) {
+		sprintf(name, "mon_sub_%s_%02d", r->name, d->hdr.id);
+		ckn = kernfs_create_dir(kn, name, parent_kn->mode, prgrp);
+		if (IS_ERR(ckn)) {
+			ret = -EINVAL;
+			goto out_destroy;
+		}
+
+		ret = rdtgroup_kn_set_ugid(ckn);
+		if (ret)
+			goto out_destroy;
+
+		ret = mon_add_all_files(ckn, d, r, prgrp, false);
+		if (ret)
+			goto out_destroy;
+	}
+
+	kernfs_activate(kn);
+	return 0;
+
+out_destroy:
+	kernfs_remove(kn);
+	return ret;
+}
+
+/*
+ * Add all subdirectories of mon_data for "ctrl_mon" groups
+ * and "monitor" groups with given domain id.
+ */
+static void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
+					   struct rdt_mon_domain *d)
+{
+	struct kernfs_node *parent_kn;
+	struct rdtgroup *prgrp, *crgrp;
+	struct list_head *head;
+
+	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
+		parent_kn = prgrp->mon.mon_data_kn;
+		mkdir_mondata_subdir(parent_kn, d, r, prgrp);
+
+		head = &prgrp->mon.crdtgrp_list;
+		list_for_each_entry(crgrp, head, mon.crdtgrp_list) {
+			parent_kn = crgrp->mon.mon_data_kn;
+			mkdir_mondata_subdir(parent_kn, d, r, crgrp);
+		}
+	}
+}
+
+static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn,
+				       struct rdt_resource *r,
+				       struct rdtgroup *prgrp)
+{
+	struct rdt_mon_domain *dom;
+	int ret;
+
+	/* Walking r->domains, ensure it can't race with cpuhp */
+	lockdep_assert_cpus_held();
+
+	list_for_each_entry(dom, &r->mon_domains, hdr.list) {
+		ret = mkdir_mondata_subdir(parent_kn, dom, r, prgrp);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+/*
+ * This creates a directory mon_data which contains the monitored data.
+ *
+ * mon_data has one directory for each domain which are named
+ * in the format mon_<domain_name>_<domain_id>. For ex: A mon_data
+ * with L3 domain looks as below:
+ * ./mon_data:
+ * mon_L3_00
+ * mon_L3_01
+ * mon_L3_02
+ * ...
+ *
+ * Each domain directory has one file per event:
+ * ./mon_L3_00/:
+ * llc_occupancy
+ *
+ */
+static int mkdir_mondata_all(struct kernfs_node *parent_kn,
+			     struct rdtgroup *prgrp,
+			     struct kernfs_node **dest_kn)
+{
+	struct rdt_resource *r;
+	struct kernfs_node *kn;
+	int ret;
+
+	/*
+	 * Create the mon_data directory first.
+	 */
+	ret = mongroup_create_dir(parent_kn, prgrp, "mon_data", &kn);
+	if (ret)
+		return ret;
+
+	if (dest_kn)
+		*dest_kn = kn;
+
+	/*
+	 * Create the subdirectories for each domain. Note that all events
+	 * in a domain like L3 are grouped into a resource whose domain is L3
+	 */
+	for_each_mon_capable_rdt_resource(r) {
+		ret = mkdir_mondata_subdir_alldom(kn, r, prgrp);
+		if (ret)
+			goto out_destroy;
+	}
+
+	return 0;
+
+out_destroy:
+	kernfs_remove(kn);
+	return ret;
+}
+
+/**
+ * cbm_ensure_valid - Enforce validity on provided CBM
+ * @_val:	Candidate CBM
+ * @r:		RDT resource to which the CBM belongs
+ *
+ * The provided CBM represents all cache portions available for use. This
+ * may be represented by a bitmap that does not consist of contiguous ones
+ * and thus be an invalid CBM.
+ * Here the provided CBM is forced to be a valid CBM by only considering
+ * the first set of contiguous bits as valid and clearing all bits.
+ * The intention here is to provide a valid default CBM with which a new
+ * resource group is initialized. The user can follow this with a
+ * modification to the CBM if the default does not satisfy the
+ * requirements.
+ */
+static u32 cbm_ensure_valid(u32 _val, struct rdt_resource *r)
+{
+	unsigned int cbm_len = r->cache.cbm_len;
+	unsigned long first_bit, zero_bit;
+	unsigned long val = _val;
+
+	if (!val)
+		return 0;
+
+	first_bit = find_first_bit(&val, cbm_len);
+	zero_bit = find_next_zero_bit(&val, cbm_len, first_bit);
+
+	/* Clear any remaining bits to ensure contiguous region */
+	bitmap_clear(&val, zero_bit, cbm_len - zero_bit);
+	return (u32)val;
+}
+
+/*
+ * Initialize cache resources per RDT domain
+ *
+ * Set the RDT domain up to start off with all usable allocations. That is,
+ * all shareable and unused bits. All-zero CBM is invalid.
+ */
+static int __init_one_rdt_domain(struct rdt_ctrl_domain *d, struct resctrl_schema *s,
+				 u32 closid)
+{
+	enum resctrl_conf_type peer_type = resctrl_peer_type(s->conf_type);
+	enum resctrl_conf_type t = s->conf_type;
+	struct resctrl_staged_config *cfg;
+	struct rdt_resource *r = s->res;
+	u32 used_b = 0, unused_b = 0;
+	unsigned long tmp_cbm;
+	enum rdtgrp_mode mode;
+	u32 peer_ctl, ctrl_val;
+	int i;
+
+	cfg = &d->staged_config[t];
+	cfg->have_new_ctrl = false;
+	cfg->new_ctrl = r->cache.shareable_bits;
+	used_b = r->cache.shareable_bits;
+	for (i = 0; i < closids_supported(); i++) {
+		if (closid_allocated(i) && i != closid) {
+			mode = rdtgroup_mode_by_closid(i);
+			if (mode == RDT_MODE_PSEUDO_LOCKSETUP)
+				/*
+				 * ctrl values for locksetup aren't relevant
+				 * until the schemata is written, and the mode
+				 * becomes RDT_MODE_PSEUDO_LOCKED.
+				 */
+				continue;
+			/*
+			 * If CDP is active include peer domain's
+			 * usage to ensure there is no overlap
+			 * with an exclusive group.
+			 */
+			if (resctrl_arch_get_cdp_enabled(r->rid))
+				peer_ctl = resctrl_arch_get_config(r, d, i,
+								   peer_type);
+			else
+				peer_ctl = 0;
+			ctrl_val = resctrl_arch_get_config(r, d, i,
+							   s->conf_type);
+			used_b |= ctrl_val | peer_ctl;
+			if (mode == RDT_MODE_SHAREABLE)
+				cfg->new_ctrl |= ctrl_val | peer_ctl;
+		}
+	}
+	if (d->plr && d->plr->cbm > 0)
+		used_b |= d->plr->cbm;
+	unused_b = used_b ^ (BIT_MASK(r->cache.cbm_len) - 1);
+	unused_b &= BIT_MASK(r->cache.cbm_len) - 1;
+	cfg->new_ctrl |= unused_b;
+	/*
+	 * Force the initial CBM to be valid, user can
+	 * modify the CBM based on system availability.
+	 */
+	cfg->new_ctrl = cbm_ensure_valid(cfg->new_ctrl, r);
+	/*
+	 * Assign the u32 CBM to an unsigned long to ensure that
+	 * bitmap_weight() does not access out-of-bound memory.
+	 */
+	tmp_cbm = cfg->new_ctrl;
+	if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) < r->cache.min_cbm_bits) {
+		rdt_last_cmd_printf("No space on %s:%d\n", s->name, d->hdr.id);
+		return -ENOSPC;
+	}
+	cfg->have_new_ctrl = true;
+
+	return 0;
+}
+
+/*
+ * Initialize cache resources with default values.
+ *
+ * A new RDT group is being created on an allocation capable (CAT)
+ * supporting system. Set this group up to start off with all usable
+ * allocations.
+ *
+ * If there are no more shareable bits available on any domain then
+ * the entire allocation will fail.
+ */
+static int rdtgroup_init_cat(struct resctrl_schema *s, u32 closid)
+{
+	struct rdt_ctrl_domain *d;
+	int ret;
+
+	list_for_each_entry(d, &s->res->ctrl_domains, hdr.list) {
+		ret = __init_one_rdt_domain(d, s, closid);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+/* Initialize MBA resource with default values. */
+static void rdtgroup_init_mba(struct rdt_resource *r, u32 closid)
+{
+	struct resctrl_staged_config *cfg;
+	struct rdt_ctrl_domain *d;
+
+	list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
+		if (is_mba_sc(r)) {
+			d->mbps_val[closid] = MBA_MAX_MBPS;
+			continue;
+		}
+
+		cfg = &d->staged_config[CDP_NONE];
+		cfg->new_ctrl = resctrl_get_default_ctrl(r);
+		cfg->have_new_ctrl = true;
+	}
+}
+
+/* Initialize the RDT group's allocations. */
+static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
+{
+	struct resctrl_schema *s;
+	struct rdt_resource *r;
+	int ret = 0;
+
+	rdt_staged_configs_clear();
+
+	list_for_each_entry(s, &resctrl_schema_all, list) {
+		r = s->res;
+		if (r->rid == RDT_RESOURCE_MBA ||
+		    r->rid == RDT_RESOURCE_SMBA) {
+			rdtgroup_init_mba(r, rdtgrp->closid);
+			if (is_mba_sc(r))
+				continue;
+		} else {
+			ret = rdtgroup_init_cat(s, rdtgrp->closid);
+			if (ret < 0)
+				goto out;
+		}
+
+		ret = resctrl_arch_update_domains(r, rdtgrp->closid);
+		if (ret < 0) {
+			rdt_last_cmd_puts("Failed to initialize allocations\n");
+			goto out;
+		}
+	}
+
+	rdtgrp->mode = RDT_MODE_SHAREABLE;
+
+out:
+	rdt_staged_configs_clear();
+	return ret;
+}
+
+static int mkdir_rdt_prepare_rmid_alloc(struct rdtgroup *rdtgrp)
+{
+	int ret;
+
+	if (!resctrl_arch_mon_capable())
+		return 0;
+
+	ret = alloc_rmid(rdtgrp->closid);
+	if (ret < 0) {
+		rdt_last_cmd_puts("Out of RMIDs\n");
+		return ret;
+	}
+	rdtgrp->mon.rmid = ret;
+
+	ret = mkdir_mondata_all(rdtgrp->kn, rdtgrp, &rdtgrp->mon.mon_data_kn);
+	if (ret) {
+		rdt_last_cmd_puts("kernfs subdir error\n");
+		free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void mkdir_rdt_prepare_rmid_free(struct rdtgroup *rgrp)
+{
+	if (resctrl_arch_mon_capable())
+		free_rmid(rgrp->closid, rgrp->mon.rmid);
+}
+
+/*
+ * We allow creating mon groups only with in a directory called "mon_groups"
+ * which is present in every ctrl_mon group. Check if this is a valid
+ * "mon_groups" directory.
+ *
+ * 1. The directory should be named "mon_groups".
+ * 2. The mon group itself should "not" be named "mon_groups".
+ *   This makes sure "mon_groups" directory always has a ctrl_mon group
+ *   as parent.
+ */
+static bool is_mon_groups(struct kernfs_node *kn, const char *name)
+{
+	return (!strcmp(rdt_kn_name(kn), "mon_groups") &&
+		strcmp(name, "mon_groups"));
+}
+
+static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
+			     const char *name, umode_t mode,
+			     enum rdt_group_type rtype, struct rdtgroup **r)
+{
+	struct rdtgroup *prdtgrp, *rdtgrp;
+	unsigned long files = 0;
+	struct kernfs_node *kn;
+	int ret;
+
+	prdtgrp = rdtgroup_kn_lock_live(parent_kn);
+	if (!prdtgrp) {
+		ret = -ENODEV;
+		goto out_unlock;
+	}
+
+	/*
+	 * Check that the parent directory for a monitor group is a "mon_groups"
+	 * directory.
+	 */
+	if (rtype == RDTMON_GROUP && !is_mon_groups(parent_kn, name)) {
+		ret = -EPERM;
+		goto out_unlock;
+	}
+
+	if (rtype == RDTMON_GROUP &&
+	    (prdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
+	     prdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)) {
+		ret = -EINVAL;
+		rdt_last_cmd_puts("Pseudo-locking in progress\n");
+		goto out_unlock;
+	}
+
+	/* allocate the rdtgroup. */
+	rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL);
+	if (!rdtgrp) {
+		ret = -ENOSPC;
+		rdt_last_cmd_puts("Kernel out of memory\n");
+		goto out_unlock;
+	}
+	*r = rdtgrp;
+	rdtgrp->mon.parent = prdtgrp;
+	rdtgrp->type = rtype;
+	INIT_LIST_HEAD(&rdtgrp->mon.crdtgrp_list);
+
+	/* kernfs creates the directory for rdtgrp */
+	kn = kernfs_create_dir(parent_kn, name, mode, rdtgrp);
+	if (IS_ERR(kn)) {
+		ret = PTR_ERR(kn);
+		rdt_last_cmd_puts("kernfs create error\n");
+		goto out_free_rgrp;
+	}
+	rdtgrp->kn = kn;
+
+	/*
+	 * kernfs_remove() will drop the reference count on "kn" which
+	 * will free it. But we still need it to stick around for the
+	 * rdtgroup_kn_unlock(kn) call. Take one extra reference here,
+	 * which will be dropped by kernfs_put() in rdtgroup_remove().
+	 */
+	kernfs_get(kn);
+
+	ret = rdtgroup_kn_set_ugid(kn);
+	if (ret) {
+		rdt_last_cmd_puts("kernfs perm error\n");
+		goto out_destroy;
+	}
+
+	if (rtype == RDTCTRL_GROUP) {
+		files = RFTYPE_BASE | RFTYPE_CTRL;
+		if (resctrl_arch_mon_capable())
+			files |= RFTYPE_MON;
+	} else {
+		files = RFTYPE_BASE | RFTYPE_MON;
+	}
+
+	ret = rdtgroup_add_files(kn, files);
+	if (ret) {
+		rdt_last_cmd_puts("kernfs fill error\n");
+		goto out_destroy;
+	}
+
+	/*
+	 * The caller unlocks the parent_kn upon success.
+	 */
+	return 0;
+
+out_destroy:
+	kernfs_put(rdtgrp->kn);
+	kernfs_remove(rdtgrp->kn);
+out_free_rgrp:
+	kfree(rdtgrp);
+out_unlock:
+	rdtgroup_kn_unlock(parent_kn);
+	return ret;
+}
+
+static void mkdir_rdt_prepare_clean(struct rdtgroup *rgrp)
+{
+	kernfs_remove(rgrp->kn);
+	rdtgroup_remove(rgrp);
+}
+
+/*
+ * Create a monitor group under "mon_groups" directory of a control
+ * and monitor group(ctrl_mon). This is a resource group
+ * to monitor a subset of tasks and cpus in its parent ctrl_mon group.
+ */
+static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn,
+			      const char *name, umode_t mode)
+{
+	struct rdtgroup *rdtgrp, *prgrp;
+	int ret;
+
+	ret = mkdir_rdt_prepare(parent_kn, name, mode, RDTMON_GROUP, &rdtgrp);
+	if (ret)
+		return ret;
+
+	prgrp = rdtgrp->mon.parent;
+	rdtgrp->closid = prgrp->closid;
+
+	ret = mkdir_rdt_prepare_rmid_alloc(rdtgrp);
+	if (ret) {
+		mkdir_rdt_prepare_clean(rdtgrp);
+		goto out_unlock;
+	}
+
+	kernfs_activate(rdtgrp->kn);
+
+	/*
+	 * Add the rdtgrp to the list of rdtgrps the parent
+	 * ctrl_mon group has to track.
+	 */
+	list_add_tail(&rdtgrp->mon.crdtgrp_list, &prgrp->mon.crdtgrp_list);
+
+out_unlock:
+	rdtgroup_kn_unlock(parent_kn);
+	return ret;
+}
+
+/*
+ * These are rdtgroups created under the root directory. Can be used
+ * to allocate and monitor resources.
+ */
+static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
+				   const char *name, umode_t mode)
+{
+	struct rdtgroup *rdtgrp;
+	struct kernfs_node *kn;
+	u32 closid;
+	int ret;
+
+	ret = mkdir_rdt_prepare(parent_kn, name, mode, RDTCTRL_GROUP, &rdtgrp);
+	if (ret)
+		return ret;
+
+	kn = rdtgrp->kn;
+	ret = closid_alloc();
+	if (ret < 0) {
+		rdt_last_cmd_puts("Out of CLOSIDs\n");
+		goto out_common_fail;
+	}
+	closid = ret;
+	ret = 0;
+
+	rdtgrp->closid = closid;
+
+	ret = mkdir_rdt_prepare_rmid_alloc(rdtgrp);
+	if (ret)
+		goto out_closid_free;
+
+	kernfs_activate(rdtgrp->kn);
+
+	ret = rdtgroup_init_alloc(rdtgrp);
+	if (ret < 0)
+		goto out_rmid_free;
+
+	list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups);
+
+	if (resctrl_arch_mon_capable()) {
+		/*
+		 * Create an empty mon_groups directory to hold the subset
+		 * of tasks and cpus to monitor.
+		 */
+		ret = mongroup_create_dir(kn, rdtgrp, "mon_groups", NULL);
+		if (ret) {
+			rdt_last_cmd_puts("kernfs subdir error\n");
+			goto out_del_list;
+		}
+		if (is_mba_sc(NULL))
+			rdtgrp->mba_mbps_event = mba_mbps_default_event;
+	}
+
+	goto out_unlock;
+
+out_del_list:
+	list_del(&rdtgrp->rdtgroup_list);
+out_rmid_free:
+	mkdir_rdt_prepare_rmid_free(rdtgrp);
+out_closid_free:
+	closid_free(closid);
+out_common_fail:
+	mkdir_rdt_prepare_clean(rdtgrp);
+out_unlock:
+	rdtgroup_kn_unlock(parent_kn);
+	return ret;
+}
+
+static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
+			  umode_t mode)
+{
+	/* Do not accept '\n' to avoid unparsable situation. */
+	if (strchr(name, '\n'))
+		return -EINVAL;
+
+	/*
+	 * If the parent directory is the root directory and RDT
+	 * allocation is supported, add a control and monitoring
+	 * subdirectory
+	 */
+	if (resctrl_arch_alloc_capable() && parent_kn == rdtgroup_default.kn)
+		return rdtgroup_mkdir_ctrl_mon(parent_kn, name, mode);
+
+	/* Else, attempt to add a monitoring subdirectory. */
+	if (resctrl_arch_mon_capable())
+		return rdtgroup_mkdir_mon(parent_kn, name, mode);
+
+	return -EPERM;
+}
+
+static int rdtgroup_rmdir_mon(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask)
+{
+	struct rdtgroup *prdtgrp = rdtgrp->mon.parent;
+	u32 closid, rmid;
+	int cpu;
+
+	/* Give any tasks back to the parent group */
+	rdt_move_group_tasks(rdtgrp, prdtgrp, tmpmask);
+
+	/*
+	 * Update per cpu closid/rmid of the moved CPUs first.
+	 * Note: the closid will not change, but the arch code still needs it.
+	 */
+	closid = prdtgrp->closid;
+	rmid = prdtgrp->mon.rmid;
+	for_each_cpu(cpu, &rdtgrp->cpu_mask)
+		resctrl_arch_set_cpu_default_closid_rmid(cpu, closid, rmid);
+
+	/*
+	 * Update the MSR on moved CPUs and CPUs which have moved
+	 * task running on them.
+	 */
+	cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask);
+	update_closid_rmid(tmpmask, NULL);
+
+	rdtgrp->flags = RDT_DELETED;
+	free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
+
+	/*
+	 * Remove the rdtgrp from the parent ctrl_mon group's list
+	 */
+	WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list));
+	list_del(&rdtgrp->mon.crdtgrp_list);
+
+	kernfs_remove(rdtgrp->kn);
+
+	return 0;
+}
+
+static int rdtgroup_ctrl_remove(struct rdtgroup *rdtgrp)
+{
+	rdtgrp->flags = RDT_DELETED;
+	list_del(&rdtgrp->rdtgroup_list);
+
+	kernfs_remove(rdtgrp->kn);
+	return 0;
+}
+
+static int rdtgroup_rmdir_ctrl(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask)
+{
+	u32 closid, rmid;
+	int cpu;
+
+	/* Give any tasks back to the default group */
+	rdt_move_group_tasks(rdtgrp, &rdtgroup_default, tmpmask);
+
+	/* Give any CPUs back to the default group */
+	cpumask_or(&rdtgroup_default.cpu_mask,
+		   &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);
+
+	/* Update per cpu closid and rmid of the moved CPUs first */
+	closid = rdtgroup_default.closid;
+	rmid = rdtgroup_default.mon.rmid;
+	for_each_cpu(cpu, &rdtgrp->cpu_mask)
+		resctrl_arch_set_cpu_default_closid_rmid(cpu, closid, rmid);
+
+	/*
+	 * Update the MSR on moved CPUs and CPUs which have moved
+	 * task running on them.
+	 */
+	cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask);
+	update_closid_rmid(tmpmask, NULL);
+
+	free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
+	closid_free(rdtgrp->closid);
+
+	rdtgroup_ctrl_remove(rdtgrp);
+
+	/*
+	 * Free all the child monitor group rmids.
+	 */
+	free_all_child_rdtgrp(rdtgrp);
+
+	return 0;
+}
+
+static struct kernfs_node *rdt_kn_parent(struct kernfs_node *kn)
+{
+	/*
+	 * Valid within the RCU section it was obtained or while rdtgroup_mutex
+	 * is held.
+	 */
+	return rcu_dereference_check(kn->__parent, lockdep_is_held(&rdtgroup_mutex));
+}
+
+static int rdtgroup_rmdir(struct kernfs_node *kn)
+{
+	struct kernfs_node *parent_kn;
+	struct rdtgroup *rdtgrp;
+	cpumask_var_t tmpmask;
+	int ret = 0;
+
+	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
+		return -ENOMEM;
+
+	rdtgrp = rdtgroup_kn_lock_live(kn);
+	if (!rdtgrp) {
+		ret = -EPERM;
+		goto out;
+	}
+	parent_kn = rdt_kn_parent(kn);
+
+	/*
+	 * If the rdtgroup is a ctrl_mon group and parent directory
+	 * is the root directory, remove the ctrl_mon group.
+	 *
+	 * If the rdtgroup is a mon group and parent directory
+	 * is a valid "mon_groups" directory, remove the mon group.
+	 */
+	if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn &&
+	    rdtgrp != &rdtgroup_default) {
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
+		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
+			ret = rdtgroup_ctrl_remove(rdtgrp);
+		} else {
+			ret = rdtgroup_rmdir_ctrl(rdtgrp, tmpmask);
+		}
+	} else if (rdtgrp->type == RDTMON_GROUP &&
+		 is_mon_groups(parent_kn, rdt_kn_name(kn))) {
+		ret = rdtgroup_rmdir_mon(rdtgrp, tmpmask);
+	} else {
+		ret = -EPERM;
+	}
+
+out:
+	rdtgroup_kn_unlock(kn);
+	free_cpumask_var(tmpmask);
+	return ret;
+}
+
+/**
+ * mongrp_reparent() - replace parent CTRL_MON group of a MON group
+ * @rdtgrp:		the MON group whose parent should be replaced
+ * @new_prdtgrp:	replacement parent CTRL_MON group for @rdtgrp
+ * @cpus:		cpumask provided by the caller for use during this call
+ *
+ * Replaces the parent CTRL_MON group for a MON group, resulting in all member
+ * tasks' CLOSID immediately changing to that of the new parent group.
+ * Monitoring data for the group is unaffected by this operation.
+ */
+static void mongrp_reparent(struct rdtgroup *rdtgrp,
+			    struct rdtgroup *new_prdtgrp,
+			    cpumask_var_t cpus)
+{
+	struct rdtgroup *prdtgrp = rdtgrp->mon.parent;
+
+	WARN_ON(rdtgrp->type != RDTMON_GROUP);
+	WARN_ON(new_prdtgrp->type != RDTCTRL_GROUP);
+
+	/* Nothing to do when simply renaming a MON group. */
+	if (prdtgrp == new_prdtgrp)
+		return;
+
+	WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list));
+	list_move_tail(&rdtgrp->mon.crdtgrp_list,
+		       &new_prdtgrp->mon.crdtgrp_list);
+
+	rdtgrp->mon.parent = new_prdtgrp;
+	rdtgrp->closid = new_prdtgrp->closid;
+
+	/* Propagate updated closid to all tasks in this group. */
+	rdt_move_group_tasks(rdtgrp, rdtgrp, cpus);
+
+	update_closid_rmid(cpus, NULL);
+}
+
+static int rdtgroup_rename(struct kernfs_node *kn,
+			   struct kernfs_node *new_parent, const char *new_name)
+{
+	struct kernfs_node *kn_parent;
+	struct rdtgroup *new_prdtgrp;
+	struct rdtgroup *rdtgrp;
+	cpumask_var_t tmpmask;
+	int ret;
+
+	rdtgrp = kernfs_to_rdtgroup(kn);
+	new_prdtgrp = kernfs_to_rdtgroup(new_parent);
+	if (!rdtgrp || !new_prdtgrp)
+		return -ENOENT;
+
+	/* Release both kernfs active_refs before obtaining rdtgroup mutex. */
+	rdtgroup_kn_get(rdtgrp, kn);
+	rdtgroup_kn_get(new_prdtgrp, new_parent);
+
+	mutex_lock(&rdtgroup_mutex);
+
+	rdt_last_cmd_clear();
+
+	/*
+	 * Don't allow kernfs_to_rdtgroup() to return a parent rdtgroup if
+	 * either kernfs_node is a file.
+	 */
+	if (kernfs_type(kn) != KERNFS_DIR ||
+	    kernfs_type(new_parent) != KERNFS_DIR) {
+		rdt_last_cmd_puts("Source and destination must be directories");
+		ret = -EPERM;
+		goto out;
+	}
+
+	if ((rdtgrp->flags & RDT_DELETED) || (new_prdtgrp->flags & RDT_DELETED)) {
+		ret = -ENOENT;
+		goto out;
+	}
+
+	kn_parent = rdt_kn_parent(kn);
+	if (rdtgrp->type != RDTMON_GROUP || !kn_parent ||
+	    !is_mon_groups(kn_parent, rdt_kn_name(kn))) {
+		rdt_last_cmd_puts("Source must be a MON group\n");
+		ret = -EPERM;
+		goto out;
+	}
+
+	if (!is_mon_groups(new_parent, new_name)) {
+		rdt_last_cmd_puts("Destination must be a mon_groups subdirectory\n");
+		ret = -EPERM;
+		goto out;
+	}
+
+	/*
+	 * If the MON group is monitoring CPUs, the CPUs must be assigned to the
+	 * current parent CTRL_MON group and therefore cannot be assigned to
+	 * the new parent, making the move illegal.
+	 */
+	if (!cpumask_empty(&rdtgrp->cpu_mask) &&
+	    rdtgrp->mon.parent != new_prdtgrp) {
+		rdt_last_cmd_puts("Cannot move a MON group that monitors CPUs\n");
+		ret = -EPERM;
+		goto out;
+	}
+
+	/*
+	 * Allocate the cpumask for use in mongrp_reparent() to avoid the
+	 * possibility of failing to allocate it after kernfs_rename() has
+	 * succeeded.
+	 */
+	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	/*
+	 * Perform all input validation and allocations needed to ensure
+	 * mongrp_reparent() will succeed before calling kernfs_rename(),
+	 * otherwise it would be necessary to revert this call if
+	 * mongrp_reparent() failed.
+	 */
+	ret = kernfs_rename(kn, new_parent, new_name);
+	if (!ret)
+		mongrp_reparent(rdtgrp, new_prdtgrp, tmpmask);
+
+	free_cpumask_var(tmpmask);
+
+out:
+	mutex_unlock(&rdtgroup_mutex);
+	rdtgroup_kn_put(rdtgrp, kn);
+	rdtgroup_kn_put(new_prdtgrp, new_parent);
+	return ret;
+}
+
+static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf)
+{
+	if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3))
+		seq_puts(seq, ",cdp");
+
+	if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2))
+		seq_puts(seq, ",cdpl2");
+
+	if (is_mba_sc(resctrl_arch_get_resource(RDT_RESOURCE_MBA)))
+		seq_puts(seq, ",mba_MBps");
+
+	if (resctrl_debug)
+		seq_puts(seq, ",debug");
+
+	return 0;
+}
+
+static struct kernfs_syscall_ops rdtgroup_kf_syscall_ops = {
+	.mkdir		= rdtgroup_mkdir,
+	.rmdir		= rdtgroup_rmdir,
+	.rename		= rdtgroup_rename,
+	.show_options	= rdtgroup_show_options,
+};
+
+static int rdtgroup_setup_root(struct rdt_fs_context *ctx)
+{
+	rdt_root = kernfs_create_root(&rdtgroup_kf_syscall_ops,
+				      KERNFS_ROOT_CREATE_DEACTIVATED |
+				      KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK,
+				      &rdtgroup_default);
+	if (IS_ERR(rdt_root))
+		return PTR_ERR(rdt_root);
+
+	ctx->kfc.root = rdt_root;
+	rdtgroup_default.kn = kernfs_root_to_node(rdt_root);
+
+	return 0;
+}
+
+static void rdtgroup_destroy_root(void)
+{
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	kernfs_destroy_root(rdt_root);
+	rdtgroup_default.kn = NULL;
+}
+
+static void rdtgroup_setup_default(void)
+{
+	mutex_lock(&rdtgroup_mutex);
+
+	rdtgroup_default.closid = RESCTRL_RESERVED_CLOSID;
+	rdtgroup_default.mon.rmid = RESCTRL_RESERVED_RMID;
+	rdtgroup_default.type = RDTCTRL_GROUP;
+	INIT_LIST_HEAD(&rdtgroup_default.mon.crdtgrp_list);
+
+	list_add(&rdtgroup_default.rdtgroup_list, &rdt_all_groups);
+
+	mutex_unlock(&rdtgroup_mutex);
+}
+
+static void domain_destroy_mon_state(struct rdt_mon_domain *d)
+{
+	bitmap_free(d->rmid_busy_llc);
+	kfree(d->mbm_total);
+	kfree(d->mbm_local);
+}
+
+void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d)
+{
+	mutex_lock(&rdtgroup_mutex);
+
+	if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA)
+		mba_sc_domain_destroy(r, d);
+
+	mutex_unlock(&rdtgroup_mutex);
+}
+
+void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d)
+{
+	mutex_lock(&rdtgroup_mutex);
+
+	/*
+	 * If resctrl is mounted, remove all the
+	 * per domain monitor data directories.
+	 */
+	if (resctrl_mounted && resctrl_arch_mon_capable())
+		rmdir_mondata_subdir_allrdtgrp(r, d);
+
+	if (resctrl_is_mbm_enabled())
+		cancel_delayed_work(&d->mbm_over);
+	if (resctrl_arch_is_llc_occupancy_enabled() && has_busy_rmid(d)) {
+		/*
+		 * When a package is going down, forcefully
+		 * decrement rmid->ebusy. There is no way to know
+		 * that the L3 was flushed and hence may lead to
+		 * incorrect counts in rare scenarios, but leaving
+		 * the RMID as busy creates RMID leaks if the
+		 * package never comes back.
+		 */
+		__check_limbo(d, true);
+		cancel_delayed_work(&d->cqm_limbo);
+	}
+
+	domain_destroy_mon_state(d);
+
+	mutex_unlock(&rdtgroup_mutex);
+}
+
+/**
+ * domain_setup_mon_state() -  Initialise domain monitoring structures.
+ * @r:	The resource for the newly online domain.
+ * @d:	The newly online domain.
+ *
+ * Allocate monitor resources that belong to this domain.
+ * Called when the first CPU of a domain comes online, regardless of whether
+ * the filesystem is mounted.
+ * During boot this may be called before global allocations have been made by
+ * resctrl_mon_resource_init().
+ *
+ * Returns 0 for success, or -ENOMEM.
+ */
+static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_mon_domain *d)
+{
+	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
+	size_t tsize;
+
+	if (resctrl_arch_is_llc_occupancy_enabled()) {
+		d->rmid_busy_llc = bitmap_zalloc(idx_limit, GFP_KERNEL);
+		if (!d->rmid_busy_llc)
+			return -ENOMEM;
+	}
+	if (resctrl_arch_is_mbm_total_enabled()) {
+		tsize = sizeof(*d->mbm_total);
+		d->mbm_total = kcalloc(idx_limit, tsize, GFP_KERNEL);
+		if (!d->mbm_total) {
+			bitmap_free(d->rmid_busy_llc);
+			return -ENOMEM;
+		}
+	}
+	if (resctrl_arch_is_mbm_local_enabled()) {
+		tsize = sizeof(*d->mbm_local);
+		d->mbm_local = kcalloc(idx_limit, tsize, GFP_KERNEL);
+		if (!d->mbm_local) {
+			bitmap_free(d->rmid_busy_llc);
+			kfree(d->mbm_total);
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d)
+{
+	int err = 0;
+
+	mutex_lock(&rdtgroup_mutex);
+
+	if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA) {
+		/* RDT_RESOURCE_MBA is never mon_capable */
+		err = mba_sc_domain_allocate(r, d);
+	}
+
+	mutex_unlock(&rdtgroup_mutex);
+
+	return err;
+}
+
+int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d)
+{
+	int err;
+
+	mutex_lock(&rdtgroup_mutex);
+
+	err = domain_setup_mon_state(r, d);
+	if (err)
+		goto out_unlock;
+
+	if (resctrl_is_mbm_enabled()) {
+		INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow);
+		mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL,
+					   RESCTRL_PICK_ANY_CPU);
+	}
+
+	if (resctrl_arch_is_llc_occupancy_enabled())
+		INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo);
+
+	/*
+	 * If the filesystem is not mounted then only the default resource group
+	 * exists. Creation of its directories is deferred until mount time
+	 * by rdt_get_tree() calling mkdir_mondata_all().
+	 * If resctrl is mounted, add per domain monitor data directories.
+	 */
+	if (resctrl_mounted && resctrl_arch_mon_capable())
+		mkdir_mondata_subdir_allrdtgrp(r, d);
+
+out_unlock:
+	mutex_unlock(&rdtgroup_mutex);
+
+	return err;
+}
+
+void resctrl_online_cpu(unsigned int cpu)
+{
+	mutex_lock(&rdtgroup_mutex);
+	/* The CPU is set in default rdtgroup after online. */
+	cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask);
+	mutex_unlock(&rdtgroup_mutex);
+}
+
+static void clear_childcpus(struct rdtgroup *r, unsigned int cpu)
+{
+	struct rdtgroup *cr;
+
+	list_for_each_entry(cr, &r->mon.crdtgrp_list, mon.crdtgrp_list) {
+		if (cpumask_test_and_clear_cpu(cpu, &cr->cpu_mask))
+			break;
+	}
+}
+
+static struct rdt_mon_domain *get_mon_domain_from_cpu(int cpu,
+						      struct rdt_resource *r)
+{
+	struct rdt_mon_domain *d;
+
+	lockdep_assert_cpus_held();
+
+	list_for_each_entry(d, &r->mon_domains, hdr.list) {
+		/* Find the domain that contains this CPU */
+		if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask))
+			return d;
+	}
+
+	return NULL;
+}
+
+void resctrl_offline_cpu(unsigned int cpu)
+{
+	struct rdt_resource *l3 = resctrl_arch_get_resource(RDT_RESOURCE_L3);
+	struct rdt_mon_domain *d;
+	struct rdtgroup *rdtgrp;
+
+	mutex_lock(&rdtgroup_mutex);
+	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
+		if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask)) {
+			clear_childcpus(rdtgrp, cpu);
+			break;
+		}
+	}
+
+	if (!l3->mon_capable)
+		goto out_unlock;
+
+	d = get_mon_domain_from_cpu(cpu, l3);
+	if (d) {
+		if (resctrl_is_mbm_enabled() && cpu == d->mbm_work_cpu) {
+			cancel_delayed_work(&d->mbm_over);
+			mbm_setup_overflow_handler(d, 0, cpu);
+		}
+		if (resctrl_arch_is_llc_occupancy_enabled() &&
+		    cpu == d->cqm_work_cpu && has_busy_rmid(d)) {
+			cancel_delayed_work(&d->cqm_limbo);
+			cqm_setup_limbo_handler(d, 0, cpu);
+		}
+	}
+
+out_unlock:
+	mutex_unlock(&rdtgroup_mutex);
+}
+
+/*
+ * resctrl_init - resctrl filesystem initialization
+ *
+ * Setup resctrl file system including set up root, create mount point,
+ * register resctrl filesystem, and initialize files under root directory.
+ *
+ * Return: 0 on success or -errno
+ */
+int resctrl_init(void)
+{
+	int ret = 0;
+
+	seq_buf_init(&last_cmd_status, last_cmd_status_buf,
+		     sizeof(last_cmd_status_buf));
+
+	rdtgroup_setup_default();
+
+	thread_throttle_mode_init();
+
+	ret = resctrl_mon_resource_init();
+	if (ret)
+		return ret;
+
+	ret = sysfs_create_mount_point(fs_kobj, "resctrl");
+	if (ret) {
+		resctrl_mon_resource_exit();
+		return ret;
+	}
+
+	ret = register_filesystem(&rdt_fs_type);
+	if (ret)
+		goto cleanup_mountpoint;
+
+	/*
+	 * Adding the resctrl debugfs directory here may not be ideal since
+	 * it would let the resctrl debugfs directory appear on the debugfs
+	 * filesystem before the resctrl filesystem is mounted.
+	 * It may also be ok since that would enable debugging of RDT before
+	 * resctrl is mounted.
+	 * The reason why the debugfs directory is created here and not in
+	 * rdt_get_tree() is because rdt_get_tree() takes rdtgroup_mutex and
+	 * during the debugfs directory creation also &sb->s_type->i_mutex_key
+	 * (the lockdep class of inode->i_rwsem). Other filesystem
+	 * interactions (eg. SyS_getdents) have the lock ordering:
+	 * &sb->s_type->i_mutex_key --> &mm->mmap_lock
+	 * During mmap(), called with &mm->mmap_lock, the rdtgroup_mutex
+	 * is taken, thus creating dependency:
+	 * &mm->mmap_lock --> rdtgroup_mutex for the latter that can cause
+	 * issues considering the other two lock dependencies.
+	 * By creating the debugfs directory here we avoid a dependency
+	 * that may cause deadlock (even though file operations cannot
+	 * occur until the filesystem is mounted, but I do not know how to
+	 * tell lockdep that).
+	 */
+	debugfs_resctrl = debugfs_create_dir("resctrl", NULL);
+
+	return 0;
+
+cleanup_mountpoint:
+	sysfs_remove_mount_point(fs_kobj, "resctrl");
+	resctrl_mon_resource_exit();
+
+	return ret;
+}
+
+static bool resctrl_online_domains_exist(void)
+{
+	struct rdt_resource *r;
+
+	/*
+	 * Only walk capable resources to allow resctrl_arch_get_resource()
+	 * to return dummy 'not capable' resources.
+	 */
+	for_each_alloc_capable_rdt_resource(r) {
+		if (!list_empty(&r->ctrl_domains))
+			return true;
+	}
+
+	for_each_mon_capable_rdt_resource(r) {
+		if (!list_empty(&r->mon_domains))
+			return true;
+	}
+
+	return false;
+}
+
+/**
+ * resctrl_exit() - Remove the resctrl filesystem and free resources.
+ *
+ * Called by the architecture code in response to a fatal error.
+ * Removes resctrl files and structures from kernfs to prevent further
+ * configuration.
+ *
+ * When called by the architecture code, all CPUs and resctrl domains must be
+ * offline. This ensures the limbo and overflow handlers are not scheduled to
+ * run, meaning the data structures they access can be freed by
+ * resctrl_mon_resource_exit().
+ *
+ * After resctrl_exit() returns, the architecture code should return an
+ * error from all resctrl_arch_ functions that can do this.
+ * resctrl_arch_get_resource() must continue to return struct rdt_resources
+ * with the correct rid field to ensure the filesystem can be unmounted.
+ */
+void resctrl_exit(void)
+{
+	cpus_read_lock();
+	WARN_ON_ONCE(resctrl_online_domains_exist());
+
+	mutex_lock(&rdtgroup_mutex);
+	resctrl_fs_teardown();
+	mutex_unlock(&rdtgroup_mutex);
+
+	cpus_read_unlock();
+
+	debugfs_remove_recursive(debugfs_resctrl);
+	debugfs_resctrl = NULL;
+	unregister_filesystem(&rdt_fs_type);
+
+	/*
+	 * Do not remove the sysfs mount point added by resctrl_init() so that
+	 * it can be used to umount resctrl.
+	 */
+
+	resctrl_mon_resource_exit();
+}

From 6cebc8856f7773d1b9235e71236ae94eb5aa3efa Mon Sep 17 00:00:00 2001
From: Zeng Heng <zengheng4@huawei.com>
Date: Tue, 3 Jun 2025 20:58:28 +0800
Subject: [PATCH 087/236] fs/resctrl: Restore the rdt_last_cmd_clear() calls
 after acquiring rdtgroup_mutex

commit dd2922dcfaa3296846265e113309e5f7f138839f upstream.

A lockdep fix removed two rdt_last_cmd_clear() calls that were used to
clear the last_cmd_status buffer but called without holding the required
rdtgroup_mutex.

The impacted resctrl commands are writing to the cpus or cpus_list files
and creating a new monitor or control group. With stale data in the
last_cmd_status buffer the impacted resctrl commands report the stale error
on success, or append its own failure message to the stale error on
failure.

Consequently, restore the rdt_last_cmd_clear() calls after acquiring
rdtgroup_mutex.

Fixes: c8eafe149530 ("x86/resctrl: Fix potential lockdep warning")
Signed-off-by: Zeng Heng <zengheng4@huawei.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/all/20250603125828.1590067-1-zengheng4@huawei.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 fs/resctrl/rdtgroup.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index cc37f58b47dd7..1beb124e25f6f 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -536,6 +536,8 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
 		goto unlock;
 	}
 
+	rdt_last_cmd_clear();
+
 	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED ||
 	    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
 		ret = -EINVAL;
@@ -3472,6 +3474,8 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 		goto out_unlock;
 	}
 
+	rdt_last_cmd_clear();
+
 	/*
 	 * Check that the parent directory for a monitor group is a "mon_groups"
 	 * directory.

From 40ac10f9827cff704fffd9111738f973a97e06bd Mon Sep 17 00:00:00 2001
From: Qinyun Tan <qinyuntan@linux.alibaba.com>
Date: Sat, 31 May 2025 02:20:53 +0800
Subject: [PATCH 088/236] x86,fs/resctrl: Remove inappropriate references to
 cacheinfo in the resctrl subsystem

commit 594902c986e269660302f09df9ec4bf1cf017b77 upstream.

In the resctrl subsystem's Sub-NUMA Cluster (SNC) mode, the rdt_mon_domain
structure representing a NUMA node relies on the cacheinfo interface
(rdt_mon_domain::ci) to store L3 cache information (e.g., shared_cpu_map)
for monitoring. The L3 cache information of a SNC NUMA node determines
which domains are summed for the "top level" L3-scoped events.

rdt_mon_domain::ci is initialized using the first online CPU of a NUMA
node. When this CPU goes offline, its shared_cpu_map is cleared to contain
only the offline CPU itself. Subsequently, attempting to read counters
via smp_call_on_cpu(offline_cpu) fails (and error ignored), returning
zero values for "top-level events" without any error indication.

Replace the cacheinfo references in struct rdt_mon_domain and struct
rmid_read with the cacheinfo ID (a unique identifier for the L3 cache).

rdt_domain_hdr::cpu_mask contains the online CPUs associated with that
domain. When reading "top-level events", select a CPU from
rdt_domain_hdr::cpu_mask and utilize its L3 shared_cpu_map to determine
valid CPUs for reading RMID counter via the MSR interface.

Considering all CPUs associated with the L3 cache improves the chances
of picking a housekeeping CPU on which the counter reading work can be
queued, avoiding an unnecessary IPI.

Fixes: 328ea68874642 ("x86/resctrl: Prepare for new Sub-NUMA Cluster (SNC) monitor files")
Signed-off-by: Qinyun Tan <qinyuntan@linux.alibaba.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250530182053.37502-2-qinyuntan@linux.alibaba.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c |  6 ++++--
 fs/resctrl/ctrlmondata.c           | 13 +++++++++----
 fs/resctrl/internal.h              |  4 ++--
 fs/resctrl/monitor.c               |  6 ++++--
 fs/resctrl/rdtgroup.c              |  6 +++---
 include/linux/resctrl.h            |  4 ++--
 6 files changed, 24 insertions(+), 15 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index d0f69c8623d73..794eddd4e6497 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -497,6 +497,7 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
 	struct rdt_hw_mon_domain *hw_dom;
 	struct rdt_domain_hdr *hdr;
 	struct rdt_mon_domain *d;
+	struct cacheinfo *ci;
 	int err;
 
 	lockdep_assert_held(&domain_list_lock);
@@ -524,12 +525,13 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
 	d = &hw_dom->d_resctrl;
 	d->hdr.id = id;
 	d->hdr.type = RESCTRL_MON_DOMAIN;
-	d->ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
-	if (!d->ci) {
+	ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
+	if (!ci) {
 		pr_warn_once("Can't find L3 cache for CPU:%d resource %s\n", cpu, r->name);
 		mon_domain_free(hw_dom);
 		return;
 	}
+	d->ci_id = ci->id;
 	cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
 
 	arch_mon_domain_online(r, d);
diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c
index 6ed2dfd4dbbd9..d98e0d2de09fd 100644
--- a/fs/resctrl/ctrlmondata.c
+++ b/fs/resctrl/ctrlmondata.c
@@ -594,9 +594,10 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 	struct rmid_read rr = {0};
 	struct rdt_mon_domain *d;
 	struct rdtgroup *rdtgrp;
+	int domid, cpu, ret = 0;
 	struct rdt_resource *r;
+	struct cacheinfo *ci;
 	struct mon_data *md;
-	int domid, ret = 0;
 
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
 	if (!rdtgrp) {
@@ -623,10 +624,14 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 		 * one that matches this cache id.
 		 */
 		list_for_each_entry(d, &r->mon_domains, hdr.list) {
-			if (d->ci->id == domid) {
-				rr.ci = d->ci;
+			if (d->ci_id == domid) {
+				rr.ci_id = d->ci_id;
+				cpu = cpumask_any(&d->hdr.cpu_mask);
+				ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
+				if (!ci)
+					continue;
 				mon_event_read(&rr, r, NULL, rdtgrp,
-					       &d->ci->shared_cpu_map, evtid, false);
+					       &ci->shared_cpu_map, evtid, false);
 				goto checkresult;
 			}
 		}
diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index 9a8cf6f11151d..0a1eedba2b03a 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -98,7 +98,7 @@ struct mon_data {
  *	   domains in @r sharing L3 @ci.id
  * @evtid: Which monitor event to read.
  * @first: Initialize MBM counter when true.
- * @ci:    Cacheinfo for L3. Only set when @d is NULL. Used when summing domains.
+ * @ci_id: Cacheinfo id for L3. Only set when @d is NULL. Used when summing domains.
  * @err:   Error encountered when reading counter.
  * @val:   Returned value of event counter. If @rgrp is a parent resource group,
  *	   @val includes the sum of event counts from its child resource groups.
@@ -112,7 +112,7 @@ struct rmid_read {
 	struct rdt_mon_domain	*d;
 	enum resctrl_event_id	evtid;
 	bool			first;
-	struct cacheinfo	*ci;
+	unsigned int		ci_id;
 	int			err;
 	u64			val;
 	void			*arch_mon_ctx;
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index bde2801289d35..f5637855c3aca 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -361,6 +361,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 {
 	int cpu = smp_processor_id();
 	struct rdt_mon_domain *d;
+	struct cacheinfo *ci;
 	struct mbm_state *m;
 	int err, ret;
 	u64 tval = 0;
@@ -388,7 +389,8 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 	}
 
 	/* Summing domains that share a cache, must be on a CPU for that cache. */
-	if (!cpumask_test_cpu(cpu, &rr->ci->shared_cpu_map))
+	ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
+	if (!ci || ci->id != rr->ci_id)
 		return -EINVAL;
 
 	/*
@@ -400,7 +402,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 	 */
 	ret = -EINVAL;
 	list_for_each_entry(d, &rr->r->mon_domains, hdr.list) {
-		if (d->ci->id != rr->ci->id)
+		if (d->ci_id != rr->ci_id)
 			continue;
 		err = resctrl_arch_rmid_read(rr->r, d, closid, rmid,
 					     rr->evtid, &tval, rr->arch_mon_ctx);
diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index 1beb124e25f6f..77d08229d8550 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -3036,7 +3036,7 @@ static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
 	char name[32];
 
 	snc_mode = r->mon_scope == RESCTRL_L3_NODE;
-	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci->id : d->hdr.id);
+	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci_id : d->hdr.id);
 	if (snc_mode)
 		sprintf(subname, "mon_sub_%s_%02d", r->name, d->hdr.id);
 
@@ -3061,7 +3061,7 @@ static int mon_add_all_files(struct kernfs_node *kn, struct rdt_mon_domain *d,
 		return -EPERM;
 
 	list_for_each_entry(mevt, &r->evt_list, list) {
-		domid = do_sum ? d->ci->id : d->hdr.id;
+		domid = do_sum ? d->ci_id : d->hdr.id;
 		priv = mon_get_kn_priv(r->rid, domid, mevt, do_sum);
 		if (WARN_ON_ONCE(!priv))
 			return -EINVAL;
@@ -3089,7 +3089,7 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
 	lockdep_assert_held(&rdtgroup_mutex);
 
 	snc_mode = r->mon_scope == RESCTRL_L3_NODE;
-	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci->id : d->hdr.id);
+	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci_id : d->hdr.id);
 	kn = kernfs_find_and_get(parent_kn, name);
 	if (kn) {
 		/*
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 9ba771f2ddead..6fb4894b8cfd1 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -159,7 +159,7 @@ struct rdt_ctrl_domain {
 /**
  * struct rdt_mon_domain - group of CPUs sharing a resctrl monitor resource
  * @hdr:		common header for different domain types
- * @ci:			cache info for this domain
+ * @ci_id:		cache info id for this domain
  * @rmid_busy_llc:	bitmap of which limbo RMIDs are above threshold
  * @mbm_total:		saved state for MBM total bandwidth
  * @mbm_local:		saved state for MBM local bandwidth
@@ -170,7 +170,7 @@ struct rdt_ctrl_domain {
  */
 struct rdt_mon_domain {
 	struct rdt_domain_hdr		hdr;
-	struct cacheinfo		*ci;
+	unsigned int			ci_id;
 	unsigned long			*rmid_busy_llc;
 	struct mbm_state		*mbm_total;
 	struct mbm_state		*mbm_local;

From e73e31988077487d4031d2cf1fe3ab5809841a96 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 2 Jul 2025 22:16:50 +0100
Subject: [PATCH 089/236] resctrl: get rid of pointless
 debugfs_file_{get,put}()

commit 460e36ee6f84c2df4d194ee788e3ca116e8c563b upstream.

->write() of file_operations that gets used only via debugfs_create_file()
is called only under debugfs_file_get()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Acked-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/r/20250702211650.GD3406663@ZenIV
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 fs/resctrl/pseudo_lock.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/fs/resctrl/pseudo_lock.c b/fs/resctrl/pseudo_lock.c
index 5bbeb8416fa6b..6a358fc7124d9 100644
--- a/fs/resctrl/pseudo_lock.c
+++ b/fs/resctrl/pseudo_lock.c
@@ -764,13 +764,9 @@ static ssize_t pseudo_lock_measure_trigger(struct file *file,
 	if (ret == 0) {
 		if (sel != 1 && sel != 2 && sel != 3)
 			return -EINVAL;
-		ret = debugfs_file_get(file->f_path.dentry);
-		if (ret)
-			return ret;
 		ret = pseudo_lock_measure_cycles(rdtgrp, sel);
 		if (ret == 0)
 			ret = count;
-		debugfs_file_put(file->f_path.dentry);
 	}
 
 	return ret;

From 9fa48809aebc3e5896523f863586bd77bed4966b Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Mon, 8 Sep 2025 15:15:51 -0700
Subject: [PATCH 090/236] fs/resctrl: Eliminate false positive lockdep warning
 when reading SNC counters

commit d2e1b84c5141ff2ad465279acfc3cf943c960b78 upstream.

Running resctrl_tests on an SNC-2 system with lockdep debugging enabled
triggers several warnings with following trace:

  WARNING: CPU: 0 PID: 1914 at kernel/cpu.c:528 lockdep_assert_cpus_held
  ...
  Call Trace:
  __mon_event_count
  ? __lock_acquire
  ? __pfx___mon_event_count
  mon_event_count
  ? __pfx_smp_mon_event_count
  smp_mon_event_count
  smp_call_on_cpu_callback

get_cpu_cacheinfo_level() called from __mon_event_count() requires CPU hotplug
lock to be held. The hotplug lock is indeed held during this time, as
confirmed by the lockdep_assert_cpus_held() within mon_event_read() that calls
mon_event_count() via IPI, but the lockdep tracking is not able to follow the
IPI.

Fresh CPU cache information via get_cpu_cacheinfo_level() from
__mon_event_count() was added to support the fix for the issue where resctrl
inappropriately maintained links to L3 cache information that will be stale in
the case when the associated CPU goes offline.

Keep the cacheinfo ID in struct rdt_mon_domain to ensure that resctrl does not
maintain stale cache information while CPUs can go offline. Return to using
a pointer to the L3 cache information (struct cacheinfo) in struct rmid_read,
rmid_read::ci. Initialize rmid_read::ci before the IPI where it is used. CPU
hotplug lock is held across rmid_read::ci initialization and use to ensure
that it points to accurate cache information.

Fixes: 594902c986e2 ("x86,fs/resctrl: Remove inappropriate references to cacheinfo in the resctrl subsystem")
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 fs/resctrl/ctrlmondata.c | 2 +-
 fs/resctrl/internal.h    | 4 ++--
 fs/resctrl/monitor.c     | 6 ++----
 3 files changed, 5 insertions(+), 7 deletions(-)

diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c
index d98e0d2de09fd..3c39cfacb2518 100644
--- a/fs/resctrl/ctrlmondata.c
+++ b/fs/resctrl/ctrlmondata.c
@@ -625,11 +625,11 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 		 */
 		list_for_each_entry(d, &r->mon_domains, hdr.list) {
 			if (d->ci_id == domid) {
-				rr.ci_id = d->ci_id;
 				cpu = cpumask_any(&d->hdr.cpu_mask);
 				ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
 				if (!ci)
 					continue;
+				rr.ci = ci;
 				mon_event_read(&rr, r, NULL, rdtgrp,
 					       &ci->shared_cpu_map, evtid, false);
 				goto checkresult;
diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index 0a1eedba2b03a..9a8cf6f11151d 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -98,7 +98,7 @@ struct mon_data {
  *	   domains in @r sharing L3 @ci.id
  * @evtid: Which monitor event to read.
  * @first: Initialize MBM counter when true.
- * @ci_id: Cacheinfo id for L3. Only set when @d is NULL. Used when summing domains.
+ * @ci:    Cacheinfo for L3. Only set when @d is NULL. Used when summing domains.
  * @err:   Error encountered when reading counter.
  * @val:   Returned value of event counter. If @rgrp is a parent resource group,
  *	   @val includes the sum of event counts from its child resource groups.
@@ -112,7 +112,7 @@ struct rmid_read {
 	struct rdt_mon_domain	*d;
 	enum resctrl_event_id	evtid;
 	bool			first;
-	unsigned int		ci_id;
+	struct cacheinfo	*ci;
 	int			err;
 	u64			val;
 	void			*arch_mon_ctx;
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index f5637855c3aca..7326c28a7908f 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -361,7 +361,6 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 {
 	int cpu = smp_processor_id();
 	struct rdt_mon_domain *d;
-	struct cacheinfo *ci;
 	struct mbm_state *m;
 	int err, ret;
 	u64 tval = 0;
@@ -389,8 +388,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 	}
 
 	/* Summing domains that share a cache, must be on a CPU for that cache. */
-	ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
-	if (!ci || ci->id != rr->ci_id)
+	if (!cpumask_test_cpu(cpu, &rr->ci->shared_cpu_map))
 		return -EINVAL;
 
 	/*
@@ -402,7 +400,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 	 */
 	ret = -EINVAL;
 	list_for_each_entry(d, &rr->r->mon_domains, hdr.list) {
-		if (d->ci_id != rr->ci_id)
+		if (d->ci_id != rr->ci->id)
 			continue;
 		err = resctrl_arch_rmid_read(rr->r, d, closid, rmid,
 					     rr->evtid, &tval, rr->arch_mon_ctx);

From 9d9aea6cddceb276821d02f35de657e429535af2 Mon Sep 17 00:00:00 2001
From: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Date: Mon, 23 Jun 2025 16:50:50 +0900
Subject: [PATCH 091/236] fs/resctrl: Optimize code in rdt_get_tree()

commit 0e58f6a7dd689c73d67e6a2164b46d4618f2698a upstream.

schemata_list_destroy() has to be called if schemata_list_create() fails.

rdt_get_tree() calls schemata_list_destroy() in two different ways:
directly if schemata_list_create() itself fails and
on the exit path via the out_schemata_free goto label.

Remove schemata_list_destroy() call on schemata_list_create() failure.
Use existing out_schemata_free goto label instead.

Signed-off-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: James Morse <james.morse@arm.com>
Reviewed-by: Koba Ko <kobak@nvidia.com>
Link: https://lore.kernel.org/20250623075051.3610592-1-tan.shaopeng@jp.fujitsu.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 fs/resctrl/rdtgroup.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index 77d08229d8550..5f0b7cfa1cc2a 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -2608,10 +2608,8 @@ static int rdt_get_tree(struct fs_context *fc)
 		goto out_root;
 
 	ret = schemata_list_create();
-	if (ret) {
-		schemata_list_destroy();
-		goto out_ctx;
-	}
+	if (ret)
+		goto out_schemata_free;
 
 	ret = closid_init();
 	if (ret)
@@ -2683,7 +2681,6 @@ static int rdt_get_tree(struct fs_context *fc)
 	closid_exit();
 out_schemata_free:
 	schemata_list_destroy();
-out_ctx:
 	rdt_disable_ctx();
 out_root:
 	rdtgroup_destroy_root();

From 5e8d87b0dc2e892d325885397d965e110123f9af Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Fri, 5 Sep 2025 16:34:00 -0500
Subject: [PATCH 092/236] x86,fs/resctrl: Consolidate monitor event
 descriptions

commit 09f37134464cc03baf5cb8eab2d99db27ee73217 upstream.

There are currently only three monitor events, all associated with the
RDT_RESOURCE_L3 resource. Growing support for additional events will be easier
with some restructuring to have a single point in file system code where all
attributes of all events are defined.

Place all event descriptions into an array mon_event_all[]. Doing this has the
beneficial side effect of removing the need for rdt_resource::evt_list.

Add resctrl_event_id::QOS_FIRST_EVENT for a lower bound on range checks for
event ids and as the starting index to scan mon_event_all[].

Drop the code that builds evt_list and change the two places where the list is
scanned to scan mon_event_all[] instead using a new helper macro
for_each_mon_event().

Architecture code now informs file system code which events are available with
resctrl_enable_mon_event().

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Babu Moger <babu.moger@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/cover.1757108044.git.babu.moger@amd.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c | 12 ++++--
 fs/resctrl/internal.h              | 13 ++++--
 fs/resctrl/monitor.c               | 63 +++++++++++++++---------------
 fs/resctrl/rdtgroup.c              | 11 +++---
 include/linux/resctrl.h            |  4 +-
 include/linux/resctrl_types.h      | 12 ++++--
 6 files changed, 66 insertions(+), 49 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 794eddd4e6497..528fc1bd86d32 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -864,12 +864,18 @@ static __init bool get_rdt_mon_resources(void)
 {
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
 
-	if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC))
+	if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC)) {
+		resctrl_enable_mon_event(QOS_L3_OCCUP_EVENT_ID);
 		rdt_mon_features |= (1 << QOS_L3_OCCUP_EVENT_ID);
-	if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL))
+	}
+	if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) {
+		resctrl_enable_mon_event(QOS_L3_MBM_TOTAL_EVENT_ID);
 		rdt_mon_features |= (1 << QOS_L3_MBM_TOTAL_EVENT_ID);
-	if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL))
+	}
+	if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) {
+		resctrl_enable_mon_event(QOS_L3_MBM_LOCAL_EVENT_ID);
 		rdt_mon_features |= (1 << QOS_L3_MBM_LOCAL_EVENT_ID);
+	}
 
 	if (!rdt_mon_features)
 		return false;
diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index 9a8cf6f11151d..7a57366d1abce 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -52,19 +52,26 @@ static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc)
 }
 
 /**
- * struct mon_evt - Entry in the event list of a resource
+ * struct mon_evt - Properties of a monitor event
  * @evtid:		event id
+ * @rid:		resource id for this event
  * @name:		name of the event
  * @configurable:	true if the event is configurable
- * @list:		entry in &rdt_resource->evt_list
+ * @enabled:		true if the event is enabled
  */
 struct mon_evt {
 	enum resctrl_event_id	evtid;
+	enum resctrl_res_level	rid;
 	char			*name;
 	bool			configurable;
-	struct list_head	list;
+	bool			enabled;
 };
 
+extern struct mon_evt mon_event_all[QOS_NUM_EVENTS];
+
+#define for_each_mon_event(mevt) for (mevt = &mon_event_all[QOS_FIRST_EVENT];	\
+				      mevt < &mon_event_all[QOS_NUM_EVENTS]; mevt++)
+
 /**
  * struct mon_data - Monitoring details for each event file.
  * @list:            Member of the global @mon_data_kn_priv_list list.
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index 7326c28a7908f..d5bf3e0334b69 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -842,38 +842,39 @@ static void dom_data_exit(struct rdt_resource *r)
 	mutex_unlock(&rdtgroup_mutex);
 }
 
-static struct mon_evt llc_occupancy_event = {
-	.name		= "llc_occupancy",
-	.evtid		= QOS_L3_OCCUP_EVENT_ID,
-};
-
-static struct mon_evt mbm_total_event = {
-	.name		= "mbm_total_bytes",
-	.evtid		= QOS_L3_MBM_TOTAL_EVENT_ID,
-};
-
-static struct mon_evt mbm_local_event = {
-	.name		= "mbm_local_bytes",
-	.evtid		= QOS_L3_MBM_LOCAL_EVENT_ID,
-};
-
 /*
- * Initialize the event list for the resource.
- *
- * Note that MBM events are also part of RDT_RESOURCE_L3 resource
- * because as per the SDM the total and local memory bandwidth
- * are enumerated as part of L3 monitoring.
+ * All available events. Architecture code marks the ones that
+ * are supported by a system using resctrl_enable_mon_event()
+ * to set .enabled.
  */
-static void l3_mon_evt_init(struct rdt_resource *r)
+struct mon_evt mon_event_all[QOS_NUM_EVENTS] = {
+	[QOS_L3_OCCUP_EVENT_ID] = {
+		.name	= "llc_occupancy",
+		.evtid	= QOS_L3_OCCUP_EVENT_ID,
+		.rid	= RDT_RESOURCE_L3,
+	},
+	[QOS_L3_MBM_TOTAL_EVENT_ID] = {
+		.name	= "mbm_total_bytes",
+		.evtid	= QOS_L3_MBM_TOTAL_EVENT_ID,
+		.rid	= RDT_RESOURCE_L3,
+	},
+	[QOS_L3_MBM_LOCAL_EVENT_ID] = {
+		.name	= "mbm_local_bytes",
+		.evtid	= QOS_L3_MBM_LOCAL_EVENT_ID,
+		.rid	= RDT_RESOURCE_L3,
+	},
+};
+
+void resctrl_enable_mon_event(enum resctrl_event_id eventid)
 {
-	INIT_LIST_HEAD(&r->evt_list);
+	if (WARN_ON_ONCE(eventid < QOS_FIRST_EVENT || eventid >= QOS_NUM_EVENTS))
+		return;
+	if (mon_event_all[eventid].enabled) {
+		pr_warn("Duplicate enable for event %d\n", eventid);
+		return;
+	}
 
-	if (resctrl_arch_is_llc_occupancy_enabled())
-		list_add_tail(&llc_occupancy_event.list, &r->evt_list);
-	if (resctrl_arch_is_mbm_total_enabled())
-		list_add_tail(&mbm_total_event.list, &r->evt_list);
-	if (resctrl_arch_is_mbm_local_enabled())
-		list_add_tail(&mbm_local_event.list, &r->evt_list);
+	mon_event_all[eventid].enabled = true;
 }
 
 /**
@@ -900,15 +901,13 @@ int resctrl_mon_resource_init(void)
 	if (ret)
 		return ret;
 
-	l3_mon_evt_init(r);
-
 	if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_TOTAL_EVENT_ID)) {
-		mbm_total_event.configurable = true;
+		mon_event_all[QOS_L3_MBM_TOTAL_EVENT_ID].configurable = true;
 		resctrl_file_fflags_init("mbm_total_bytes_config",
 					 RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
 	}
 	if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_LOCAL_EVENT_ID)) {
-		mbm_local_event.configurable = true;
+		mon_event_all[QOS_L3_MBM_LOCAL_EVENT_ID].configurable = true;
 		resctrl_file_fflags_init("mbm_local_bytes_config",
 					 RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
 	}
diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index 5f0b7cfa1cc2a..ab943a5907c5c 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -1152,7 +1152,9 @@ static int rdt_mon_features_show(struct kernfs_open_file *of,
 	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
 	struct mon_evt *mevt;
 
-	list_for_each_entry(mevt, &r->evt_list, list) {
+	for_each_mon_event(mevt) {
+		if (mevt->rid != r->rid || !mevt->enabled)
+			continue;
 		seq_printf(seq, "%s\n", mevt->name);
 		if (mevt->configurable)
 			seq_printf(seq, "%s_config\n", mevt->name);
@@ -3054,10 +3056,9 @@ static int mon_add_all_files(struct kernfs_node *kn, struct rdt_mon_domain *d,
 	struct mon_evt *mevt;
 	int ret, domid;
 
-	if (WARN_ON(list_empty(&r->evt_list)))
-		return -EPERM;
-
-	list_for_each_entry(mevt, &r->evt_list, list) {
+	for_each_mon_event(mevt) {
+		if (mevt->rid != r->rid || !mevt->enabled)
+			continue;
 		domid = do_sum ? d->ci_id : d->hdr.id;
 		priv = mon_get_kn_priv(r->rid, domid, mevt, do_sum);
 		if (WARN_ON_ONCE(!priv))
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 6fb4894b8cfd1..2944042bd84c5 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -269,7 +269,6 @@ enum resctrl_schema_fmt {
  * @mon_domains:	RCU list of all monitor domains for this resource
  * @name:		Name to use in "schemata" file.
  * @schema_fmt:		Which format string and parser is used for this schema.
- * @evt_list:		List of monitoring events
  * @mbm_cfg_mask:	Bandwidth sources that can be tracked when bandwidth
  *			monitoring events can be configured.
  * @cdp_capable:	Is the CDP feature available on this resource
@@ -287,7 +286,6 @@ struct rdt_resource {
 	struct list_head	mon_domains;
 	char			*name;
 	enum resctrl_schema_fmt	schema_fmt;
-	struct list_head	evt_list;
 	unsigned int		mbm_cfg_mask;
 	bool			cdp_capable;
 };
@@ -372,6 +370,8 @@ u32 resctrl_arch_get_num_closid(struct rdt_resource *r);
 u32 resctrl_arch_system_num_rmid_idx(void);
 int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid);
 
+void resctrl_enable_mon_event(enum resctrl_event_id eventid);
+
 bool resctrl_arch_is_evt_configurable(enum resctrl_event_id evt);
 
 /**
diff --git a/include/linux/resctrl_types.h b/include/linux/resctrl_types.h
index a25fb9c4070d3..2dadbc54e4b35 100644
--- a/include/linux/resctrl_types.h
+++ b/include/linux/resctrl_types.h
@@ -34,11 +34,15 @@
 /* Max event bits supported */
 #define MAX_EVT_CONFIG_BITS		GENMASK(6, 0)
 
-/*
- * Event IDs, the values match those used to program IA32_QM_EVTSEL before
- * reading IA32_QM_CTR on RDT systems.
- */
+/* Event IDs */
 enum resctrl_event_id {
+	/* Must match value of first event below */
+	QOS_FIRST_EVENT			= 0x01,
+
+	/*
+	 * These values match those used to program IA32_QM_EVTSEL before
+	 * reading IA32_QM_CTR on RDT systems.
+	 */
 	QOS_L3_OCCUP_EVENT_ID		= 0x01,
 	QOS_L3_MBM_TOTAL_EVENT_ID	= 0x02,
 	QOS_L3_MBM_LOCAL_EVENT_ID	= 0x03,

From df12f5a5b9391f836565671db54a8d495cdc60bc Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Fri, 5 Sep 2025 16:34:01 -0500
Subject: [PATCH 093/236] x86,fs/resctrl: Replace architecture event enabled
 checks

commit d257cc2e5c8bb8236cb161360d6c0529fd442712 upstream.

The resctrl file system now has complete knowledge of the status of every
event. So there is no need for per-event function calls to check.

Replace each of the resctrl_arch_is_{event}enabled() calls with
resctrl_is_mon_event_enabled(QOS_{EVENT}).

No functional change.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Babu Moger <babu.moger@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/cover.1757108044.git.babu.moger@amd.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/include/asm/resctrl.h        | 15 ---------------
 arch/x86/kernel/cpu/resctrl/core.c    |  4 ++--
 arch/x86/kernel/cpu/resctrl/monitor.c |  4 ++--
 fs/resctrl/ctrlmondata.c              |  4 ++--
 fs/resctrl/monitor.c                  | 16 +++++++++++-----
 fs/resctrl/rdtgroup.c                 | 18 +++++++++---------
 include/linux/resctrl.h               |  2 ++
 7 files changed, 28 insertions(+), 35 deletions(-)

diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h
index ad497ab196d1e..9c889f51b7f14 100644
--- a/arch/x86/include/asm/resctrl.h
+++ b/arch/x86/include/asm/resctrl.h
@@ -82,21 +82,6 @@ static inline void resctrl_arch_disable_mon(void)
 	static_branch_dec_cpuslocked(&rdt_enable_key);
 }
 
-static inline bool resctrl_arch_is_llc_occupancy_enabled(void)
-{
-	return (rdt_mon_features & (1 << QOS_L3_OCCUP_EVENT_ID));
-}
-
-static inline bool resctrl_arch_is_mbm_total_enabled(void)
-{
-	return (rdt_mon_features & (1 << QOS_L3_MBM_TOTAL_EVENT_ID));
-}
-
-static inline bool resctrl_arch_is_mbm_local_enabled(void)
-{
-	return (rdt_mon_features & (1 << QOS_L3_MBM_LOCAL_EVENT_ID));
-}
-
 /*
  * __resctrl_sched_in() - Writes the task's CLOSid/RMID to IA32_PQR_MSR
  *
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 528fc1bd86d32..e655da6d4038c 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -401,13 +401,13 @@ static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_mon_domain *hw_dom)
 {
 	size_t tsize;
 
-	if (resctrl_arch_is_mbm_total_enabled()) {
+	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID)) {
 		tsize = sizeof(*hw_dom->arch_mbm_total);
 		hw_dom->arch_mbm_total = kcalloc(num_rmid, tsize, GFP_KERNEL);
 		if (!hw_dom->arch_mbm_total)
 			return -ENOMEM;
 	}
-	if (resctrl_arch_is_mbm_local_enabled()) {
+	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)) {
 		tsize = sizeof(*hw_dom->arch_mbm_local);
 		hw_dom->arch_mbm_local = kcalloc(num_rmid, tsize, GFP_KERNEL);
 		if (!hw_dom->arch_mbm_local) {
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index bbfb95ae13c2d..1d01c4b64f77a 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -206,11 +206,11 @@ void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *
 {
 	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
 
-	if (resctrl_arch_is_mbm_total_enabled())
+	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID))
 		memset(hw_dom->arch_mbm_total, 0,
 		       sizeof(*hw_dom->arch_mbm_total) * r->num_rmid);
 
-	if (resctrl_arch_is_mbm_local_enabled())
+	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID))
 		memset(hw_dom->arch_mbm_local, 0,
 		       sizeof(*hw_dom->arch_mbm_local) * r->num_rmid);
 }
diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c
index 3c39cfacb2518..42b281b3852ff 100644
--- a/fs/resctrl/ctrlmondata.c
+++ b/fs/resctrl/ctrlmondata.c
@@ -473,12 +473,12 @@ ssize_t rdtgroup_mba_mbps_event_write(struct kernfs_open_file *of,
 	rdt_last_cmd_clear();
 
 	if (!strcmp(buf, "mbm_local_bytes")) {
-		if (resctrl_arch_is_mbm_local_enabled())
+		if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID))
 			rdtgrp->mba_mbps_event = QOS_L3_MBM_LOCAL_EVENT_ID;
 		else
 			ret = -EINVAL;
 	} else if (!strcmp(buf, "mbm_total_bytes")) {
-		if (resctrl_arch_is_mbm_total_enabled())
+		if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID))
 			rdtgrp->mba_mbps_event = QOS_L3_MBM_TOTAL_EVENT_ID;
 		else
 			ret = -EINVAL;
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index d5bf3e0334b69..b0b1dcc367955 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -336,7 +336,7 @@ void free_rmid(u32 closid, u32 rmid)
 
 	entry = __rmid_entry(idx);
 
-	if (resctrl_arch_is_llc_occupancy_enabled())
+	if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID))
 		add_rmid_to_limbo(entry);
 	else
 		list_add_tail(&entry->list, &rmid_free_lru);
@@ -635,10 +635,10 @@ static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d,
 	 * This is protected from concurrent reads from user as both
 	 * the user and overflow handler hold the global mutex.
 	 */
-	if (resctrl_arch_is_mbm_total_enabled())
+	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID))
 		mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_TOTAL_EVENT_ID);
 
-	if (resctrl_arch_is_mbm_local_enabled())
+	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID))
 		mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_LOCAL_EVENT_ID);
 }
 
@@ -877,6 +877,12 @@ void resctrl_enable_mon_event(enum resctrl_event_id eventid)
 	mon_event_all[eventid].enabled = true;
 }
 
+bool resctrl_is_mon_event_enabled(enum resctrl_event_id eventid)
+{
+	return eventid >= QOS_FIRST_EVENT && eventid < QOS_NUM_EVENTS &&
+	       mon_event_all[eventid].enabled;
+}
+
 /**
  * resctrl_mon_resource_init() - Initialise global monitoring structures.
  *
@@ -912,9 +918,9 @@ int resctrl_mon_resource_init(void)
 					 RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
 	}
 
-	if (resctrl_arch_is_mbm_local_enabled())
+	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID))
 		mba_mbps_default_event = QOS_L3_MBM_LOCAL_EVENT_ID;
-	else if (resctrl_arch_is_mbm_total_enabled())
+	else if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID))
 		mba_mbps_default_event = QOS_L3_MBM_TOTAL_EVENT_ID;
 
 	return 0;
diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index ab943a5907c5c..2ca8e66c0d204 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -123,8 +123,8 @@ void rdt_staged_configs_clear(void)
 
 static bool resctrl_is_mbm_enabled(void)
 {
-	return (resctrl_arch_is_mbm_total_enabled() ||
-		resctrl_arch_is_mbm_local_enabled());
+	return (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID) ||
+		resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID));
 }
 
 static bool resctrl_is_mbm_event(int e)
@@ -196,7 +196,7 @@ static int closid_alloc(void)
 	lockdep_assert_held(&rdtgroup_mutex);
 
 	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID) &&
-	    resctrl_arch_is_llc_occupancy_enabled()) {
+	    resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID)) {
 		cleanest_closid = resctrl_find_cleanest_closid();
 		if (cleanest_closid < 0)
 			return cleanest_closid;
@@ -4048,7 +4048,7 @@ void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d
 
 	if (resctrl_is_mbm_enabled())
 		cancel_delayed_work(&d->mbm_over);
-	if (resctrl_arch_is_llc_occupancy_enabled() && has_busy_rmid(d)) {
+	if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID) && has_busy_rmid(d)) {
 		/*
 		 * When a package is going down, forcefully
 		 * decrement rmid->ebusy. There is no way to know
@@ -4084,12 +4084,12 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_mon_domain
 	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
 	size_t tsize;
 
-	if (resctrl_arch_is_llc_occupancy_enabled()) {
+	if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID)) {
 		d->rmid_busy_llc = bitmap_zalloc(idx_limit, GFP_KERNEL);
 		if (!d->rmid_busy_llc)
 			return -ENOMEM;
 	}
-	if (resctrl_arch_is_mbm_total_enabled()) {
+	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID)) {
 		tsize = sizeof(*d->mbm_total);
 		d->mbm_total = kcalloc(idx_limit, tsize, GFP_KERNEL);
 		if (!d->mbm_total) {
@@ -4097,7 +4097,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_mon_domain
 			return -ENOMEM;
 		}
 	}
-	if (resctrl_arch_is_mbm_local_enabled()) {
+	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)) {
 		tsize = sizeof(*d->mbm_local);
 		d->mbm_local = kcalloc(idx_limit, tsize, GFP_KERNEL);
 		if (!d->mbm_local) {
@@ -4142,7 +4142,7 @@ int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d)
 					   RESCTRL_PICK_ANY_CPU);
 	}
 
-	if (resctrl_arch_is_llc_occupancy_enabled())
+	if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID))
 		INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo);
 
 	/*
@@ -4217,7 +4217,7 @@ void resctrl_offline_cpu(unsigned int cpu)
 			cancel_delayed_work(&d->mbm_over);
 			mbm_setup_overflow_handler(d, 0, cpu);
 		}
-		if (resctrl_arch_is_llc_occupancy_enabled() &&
+		if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID) &&
 		    cpu == d->cqm_work_cpu && has_busy_rmid(d)) {
 			cancel_delayed_work(&d->cqm_limbo);
 			cqm_setup_limbo_handler(d, 0, cpu);
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 2944042bd84c5..40aba6b5d4f08 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -372,6 +372,8 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid);
 
 void resctrl_enable_mon_event(enum resctrl_event_id eventid);
 
+bool resctrl_is_mon_event_enabled(enum resctrl_event_id eventid);
+
 bool resctrl_arch_is_evt_configurable(enum resctrl_event_id evt);
 
 /**

From 3259c75e7ac19b259b6c3f9cb50d7c2556114c0e Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Fri, 5 Sep 2025 16:34:02 -0500
Subject: [PATCH 094/236] x86/resctrl: Remove the rdt_mon_features global
 variable

commit 63cc9811aa874e6fab671599ba93a989f4f93a5d upstream.

rdt_mon_features is used as a bitmask of enabled monitor events. A monitor
event's status is now maintained in mon_evt::enabled with all monitor events'
mon_evt structures found in the filesystem's mon_event_all[] array.

Remove the remaining uses of rdt_mon_features.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Babu Moger <babu.moger@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/cover.1757108044.git.babu.moger@amd.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/include/asm/resctrl.h        | 1 -
 arch/x86/kernel/cpu/resctrl/core.c    | 9 +++++----
 arch/x86/kernel/cpu/resctrl/monitor.c | 5 -----
 3 files changed, 5 insertions(+), 10 deletions(-)

diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h
index 9c889f51b7f14..089742970cc14 100644
--- a/arch/x86/include/asm/resctrl.h
+++ b/arch/x86/include/asm/resctrl.h
@@ -42,7 +42,6 @@ DECLARE_PER_CPU(struct resctrl_pqr_state, pqr_state);
 
 extern bool rdt_alloc_capable;
 extern bool rdt_mon_capable;
-extern unsigned int rdt_mon_features;
 
 DECLARE_STATIC_KEY_FALSE(rdt_enable_key);
 DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index e655da6d4038c..1809fab986876 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -863,21 +863,22 @@ static __init bool get_rdt_alloc_resources(void)
 static __init bool get_rdt_mon_resources(void)
 {
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+	bool ret = false;
 
 	if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC)) {
 		resctrl_enable_mon_event(QOS_L3_OCCUP_EVENT_ID);
-		rdt_mon_features |= (1 << QOS_L3_OCCUP_EVENT_ID);
+		ret = true;
 	}
 	if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) {
 		resctrl_enable_mon_event(QOS_L3_MBM_TOTAL_EVENT_ID);
-		rdt_mon_features |= (1 << QOS_L3_MBM_TOTAL_EVENT_ID);
+		ret = true;
 	}
 	if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) {
 		resctrl_enable_mon_event(QOS_L3_MBM_LOCAL_EVENT_ID);
-		rdt_mon_features |= (1 << QOS_L3_MBM_LOCAL_EVENT_ID);
+		ret = true;
 	}
 
-	if (!rdt_mon_features)
+	if (!ret)
 		return false;
 
 	return !rdt_get_mon_l3_config(r);
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 1d01c4b64f77a..684f78532b182 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -30,11 +30,6 @@
  */
 bool rdt_mon_capable;
 
-/*
- * Global to indicate which monitoring events are enabled.
- */
-unsigned int rdt_mon_features;
-
 #define CF(cf)	((unsigned long)(1048576 * (cf) + 0.5))
 
 static int snc_nodes_per_l3_cache = 1;

From b434a23d933bf08cfc64d7f780a9f51aa6b3316e Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Fri, 5 Sep 2025 16:34:03 -0500
Subject: [PATCH 095/236] x86,fs/resctrl: Prepare for more monitor events

commit 83b039877310ae1eb614eef17b780df1e10d9fb5 upstream.

There's a rule in computer programming that objects appear zero, once, or many
times. So code accordingly.

There are two MBM events and resctrl is coded with a lot of

  if (local)
          do one thing
  if (total)
          do a different thing

Change the rdt_mon_domain and rdt_hw_mon_domain structures to hold arrays of
pointers to per event data instead of explicit fields for total and local
bandwidth.

Simplify by coding for many events using loops on which are enabled.

Move resctrl_is_mbm_event() to <linux/resctrl.h> so it can be used more
widely. Also provide a for_each_mbm_event_id() helper macro.

Cleanup variable names in functions touched to consistently use "eventid" for
those with type enum resctrl_event_id.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Babu Moger <babu.moger@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/cover.1757108044.git.babu.moger@amd.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c     | 40 +++++++++++----------
 arch/x86/kernel/cpu/resctrl/internal.h |  8 ++---
 arch/x86/kernel/cpu/resctrl/monitor.c  | 36 +++++++++----------
 fs/resctrl/monitor.c                   | 13 ++++---
 fs/resctrl/rdtgroup.c                  | 50 +++++++++++++-------------
 include/linux/resctrl.h                | 23 +++++++++---
 include/linux/resctrl_types.h          |  3 ++
 7 files changed, 96 insertions(+), 77 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 1809fab986876..3885ec1c61ef5 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -364,8 +364,10 @@ static void ctrl_domain_free(struct rdt_hw_ctrl_domain *hw_dom)
 
 static void mon_domain_free(struct rdt_hw_mon_domain *hw_dom)
 {
-	kfree(hw_dom->arch_mbm_total);
-	kfree(hw_dom->arch_mbm_local);
+	int idx;
+
+	for_each_mbm_idx(idx)
+		kfree(hw_dom->arch_mbm_states[idx]);
 	kfree(hw_dom);
 }
 
@@ -399,25 +401,27 @@ static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_ctrl_domain *
  */
 static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_mon_domain *hw_dom)
 {
-	size_t tsize;
-
-	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID)) {
-		tsize = sizeof(*hw_dom->arch_mbm_total);
-		hw_dom->arch_mbm_total = kcalloc(num_rmid, tsize, GFP_KERNEL);
-		if (!hw_dom->arch_mbm_total)
-			return -ENOMEM;
-	}
-	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)) {
-		tsize = sizeof(*hw_dom->arch_mbm_local);
-		hw_dom->arch_mbm_local = kcalloc(num_rmid, tsize, GFP_KERNEL);
-		if (!hw_dom->arch_mbm_local) {
-			kfree(hw_dom->arch_mbm_total);
-			hw_dom->arch_mbm_total = NULL;
-			return -ENOMEM;
-		}
+	size_t tsize = sizeof(*hw_dom->arch_mbm_states[0]);
+	enum resctrl_event_id eventid;
+	int idx;
+
+	for_each_mbm_event_id(eventid) {
+		if (!resctrl_is_mon_event_enabled(eventid))
+			continue;
+		idx = MBM_STATE_IDX(eventid);
+		hw_dom->arch_mbm_states[idx] = kcalloc(num_rmid, tsize, GFP_KERNEL);
+		if (!hw_dom->arch_mbm_states[idx])
+			goto cleanup;
 	}
 
 	return 0;
+cleanup:
+	for_each_mbm_idx(idx) {
+		kfree(hw_dom->arch_mbm_states[idx]);
+		hw_dom->arch_mbm_states[idx] = NULL;
+	}
+
+	return -ENOMEM;
 }
 
 static int get_domain_id_from_scope(int cpu, enum resctrl_scope scope)
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 62f2693fd34fb..30d9cac5ec72f 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -57,15 +57,15 @@ struct rdt_hw_ctrl_domain {
  * struct rdt_hw_mon_domain - Arch private attributes of a set of CPUs that share
  *			      a resource for a monitor function
  * @d_resctrl:	Properties exposed to the resctrl file system
- * @arch_mbm_total:	arch private state for MBM total bandwidth
- * @arch_mbm_local:	arch private state for MBM local bandwidth
+ * @arch_mbm_states:	Per-event pointer to the MBM event's saved state.
+ *			An MBM event's state is an array of struct arch_mbm_state
+ *			indexed by RMID on x86.
  *
  * Members of this structure are accessed via helpers that provide abstraction.
  */
 struct rdt_hw_mon_domain {
 	struct rdt_mon_domain		d_resctrl;
-	struct arch_mbm_state		*arch_mbm_total;
-	struct arch_mbm_state		*arch_mbm_local;
+	struct arch_mbm_state		*arch_mbm_states[QOS_NUM_L3_MBM_EVENTS];
 };
 
 static inline struct rdt_hw_ctrl_domain *resctrl_to_arch_ctrl_dom(struct rdt_ctrl_domain *r)
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 684f78532b182..3c7c21d8c175b 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -160,18 +160,14 @@ static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_mon_domain *hw_do
 						 u32 rmid,
 						 enum resctrl_event_id eventid)
 {
-	switch (eventid) {
-	case QOS_L3_OCCUP_EVENT_ID:
-		return NULL;
-	case QOS_L3_MBM_TOTAL_EVENT_ID:
-		return &hw_dom->arch_mbm_total[rmid];
-	case QOS_L3_MBM_LOCAL_EVENT_ID:
-		return &hw_dom->arch_mbm_local[rmid];
-	default:
-		/* Never expect to get here */
-		WARN_ON_ONCE(1);
+	struct arch_mbm_state *state;
+
+	if (!resctrl_is_mbm_event(eventid))
 		return NULL;
-	}
+
+	state = hw_dom->arch_mbm_states[MBM_STATE_IDX(eventid)];
+
+	return state ? &state[rmid] : NULL;
 }
 
 void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d,
@@ -200,14 +196,16 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d,
 void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d)
 {
 	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
-
-	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID))
-		memset(hw_dom->arch_mbm_total, 0,
-		       sizeof(*hw_dom->arch_mbm_total) * r->num_rmid);
-
-	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID))
-		memset(hw_dom->arch_mbm_local, 0,
-		       sizeof(*hw_dom->arch_mbm_local) * r->num_rmid);
+	enum resctrl_event_id eventid;
+	int idx;
+
+	for_each_mbm_event_id(eventid) {
+		if (!resctrl_is_mon_event_enabled(eventid))
+			continue;
+		idx = MBM_STATE_IDX(eventid);
+		memset(hw_dom->arch_mbm_states[idx], 0,
+		       sizeof(*hw_dom->arch_mbm_states[0]) * r->num_rmid);
+	}
 }
 
 static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index b0b1dcc367955..e0dfa5fb969e4 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -346,15 +346,14 @@ static struct mbm_state *get_mbm_state(struct rdt_mon_domain *d, u32 closid,
 				       u32 rmid, enum resctrl_event_id evtid)
 {
 	u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid);
+	struct mbm_state *state;
 
-	switch (evtid) {
-	case QOS_L3_MBM_TOTAL_EVENT_ID:
-		return &d->mbm_total[idx];
-	case QOS_L3_MBM_LOCAL_EVENT_ID:
-		return &d->mbm_local[idx];
-	default:
+	if (!resctrl_is_mbm_event(evtid))
 		return NULL;
-	}
+
+	state = d->mbm_states[MBM_STATE_IDX(evtid)];
+
+	return state ? &state[idx] : NULL;
 }
 
 static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index 2ca8e66c0d204..a6047e9345cda 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -127,12 +127,6 @@ static bool resctrl_is_mbm_enabled(void)
 		resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID));
 }
 
-static bool resctrl_is_mbm_event(int e)
-{
-	return (e >= QOS_L3_MBM_TOTAL_EVENT_ID &&
-		e <= QOS_L3_MBM_LOCAL_EVENT_ID);
-}
-
 /*
  * Trivial allocator for CLOSIDs. Use BITMAP APIs to manipulate a bitmap
  * of free CLOSIDs.
@@ -4020,9 +4014,13 @@ static void rdtgroup_setup_default(void)
 
 static void domain_destroy_mon_state(struct rdt_mon_domain *d)
 {
+	int idx;
+
 	bitmap_free(d->rmid_busy_llc);
-	kfree(d->mbm_total);
-	kfree(d->mbm_local);
+	for_each_mbm_idx(idx) {
+		kfree(d->mbm_states[idx]);
+		d->mbm_states[idx] = NULL;
+	}
 }
 
 void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d)
@@ -4082,32 +4080,34 @@ void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d
 static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_mon_domain *d)
 {
 	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
-	size_t tsize;
+	size_t tsize = sizeof(*d->mbm_states[0]);
+	enum resctrl_event_id eventid;
+	int idx;
 
 	if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID)) {
 		d->rmid_busy_llc = bitmap_zalloc(idx_limit, GFP_KERNEL);
 		if (!d->rmid_busy_llc)
 			return -ENOMEM;
 	}
-	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID)) {
-		tsize = sizeof(*d->mbm_total);
-		d->mbm_total = kcalloc(idx_limit, tsize, GFP_KERNEL);
-		if (!d->mbm_total) {
-			bitmap_free(d->rmid_busy_llc);
-			return -ENOMEM;
-		}
-	}
-	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)) {
-		tsize = sizeof(*d->mbm_local);
-		d->mbm_local = kcalloc(idx_limit, tsize, GFP_KERNEL);
-		if (!d->mbm_local) {
-			bitmap_free(d->rmid_busy_llc);
-			kfree(d->mbm_total);
-			return -ENOMEM;
-		}
+
+	for_each_mbm_event_id(eventid) {
+		if (!resctrl_is_mon_event_enabled(eventid))
+			continue;
+		idx = MBM_STATE_IDX(eventid);
+		d->mbm_states[idx] = kcalloc(idx_limit, tsize, GFP_KERNEL);
+		if (!d->mbm_states[idx])
+			goto cleanup;
 	}
 
 	return 0;
+cleanup:
+	bitmap_free(d->rmid_busy_llc);
+	for_each_mbm_idx(idx) {
+		kfree(d->mbm_states[idx]);
+		d->mbm_states[idx] = NULL;
+	}
+
+	return -ENOMEM;
 }
 
 int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d)
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 40aba6b5d4f08..478d7a935ca36 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -161,8 +161,9 @@ struct rdt_ctrl_domain {
  * @hdr:		common header for different domain types
  * @ci_id:		cache info id for this domain
  * @rmid_busy_llc:	bitmap of which limbo RMIDs are above threshold
- * @mbm_total:		saved state for MBM total bandwidth
- * @mbm_local:		saved state for MBM local bandwidth
+ * @mbm_states:		Per-event pointer to the MBM event's saved state.
+ *			An MBM event's state is an array of struct mbm_state
+ *			indexed by RMID on x86 or combined CLOSID, RMID on Arm.
  * @mbm_over:		worker to periodically read MBM h/w counters
  * @cqm_limbo:		worker to periodically read CQM h/w counters
  * @mbm_work_cpu:	worker CPU for MBM h/w counters
@@ -172,8 +173,7 @@ struct rdt_mon_domain {
 	struct rdt_domain_hdr		hdr;
 	unsigned int			ci_id;
 	unsigned long			*rmid_busy_llc;
-	struct mbm_state		*mbm_total;
-	struct mbm_state		*mbm_local;
+	struct mbm_state		*mbm_states[QOS_NUM_L3_MBM_EVENTS];
 	struct delayed_work		mbm_over;
 	struct delayed_work		cqm_limbo;
 	int				mbm_work_cpu;
@@ -376,6 +376,21 @@ bool resctrl_is_mon_event_enabled(enum resctrl_event_id eventid);
 
 bool resctrl_arch_is_evt_configurable(enum resctrl_event_id evt);
 
+static inline bool resctrl_is_mbm_event(enum resctrl_event_id eventid)
+{
+	return (eventid >= QOS_L3_MBM_TOTAL_EVENT_ID &&
+		eventid <= QOS_L3_MBM_LOCAL_EVENT_ID);
+}
+
+/* Iterate over all memory bandwidth events */
+#define for_each_mbm_event_id(eventid)				\
+	for (eventid = QOS_L3_MBM_TOTAL_EVENT_ID;		\
+	     eventid <= QOS_L3_MBM_LOCAL_EVENT_ID; eventid++)
+
+/* Iterate over memory bandwidth arrays in domain structures */
+#define for_each_mbm_idx(idx)					\
+	for (idx = 0; idx < QOS_NUM_L3_MBM_EVENTS; idx++)
+
 /**
  * resctrl_arch_mon_event_config_write() - Write the config for an event.
  * @config_info: struct resctrl_mon_config_info describing the resource, domain
diff --git a/include/linux/resctrl_types.h b/include/linux/resctrl_types.h
index 2dadbc54e4b35..d98351663c2c6 100644
--- a/include/linux/resctrl_types.h
+++ b/include/linux/resctrl_types.h
@@ -51,4 +51,7 @@ enum resctrl_event_id {
 	QOS_NUM_EVENTS,
 };
 
+#define QOS_NUM_L3_MBM_EVENTS	(QOS_L3_MBM_LOCAL_EVENT_ID - QOS_L3_MBM_TOTAL_EVENT_ID + 1)
+#define MBM_STATE_IDX(evt)	((evt) - QOS_L3_MBM_TOTAL_EVENT_ID)
+
 #endif /* __LINUX_RESCTRL_TYPES_H */

From 3226f1b1c2ecf757ad06867a9c1223d40a2c2fe4 Mon Sep 17 00:00:00 2001
From: Babu Moger <babu.moger@amd.com>
Date: Fri, 5 Sep 2025 16:34:04 -0500
Subject: [PATCH 096/236] x86/cpufeatures: Add support for Assignable Bandwidth
 Monitoring Counters (ABMC)

commit e19c06219985f2beb9d71959d80f56e318abf744 upstream.

Users can create as many monitor groups as RMIDs supported by the hardware.
However, the bandwidth monitoring feature on AMD only guarantees that RMIDs
currently assigned to a processor will be tracked by hardware. The counters of
any other RMIDs which are no longer being tracked will be reset to zero.

The MBM event counters return "Unavailable" for the RMIDs that are not tracked
by hardware. So, there can be only limited number of groups that can give
guaranteed monitoring numbers. With ever changing configurations there is no
way to definitely know which of these groups are being tracked during
a particular time. Users do not have the option to monitor a group or set of
groups for a certain period of time without worrying about RMID being reset in
between.

The ABMC feature allows users to assign a hardware counter to an RMID, event
pair and monitor bandwidth usage as long as it is assigned. The hardware
continues to track the assigned counter until it is explicitly unassigned by
the user. There is no need to worry about counters being reset during this
period. Additionally, the user can specify the type of memory transactions
(e.g., reads, writes) for the counter to track.

Without ABMC enabled, monitoring will work in current mode without assignment
option.

The Linux resctrl subsystem provides an interface that allows monitoring of up
to two memory bandwidth events per group, selected from a combination of
available total and local events. When ABMC is enabled, two events will be
assigned to each group by default, in line with the current interface design.
Users will also have the option to configure which types of memory
transactions are counted by these events.

Due to the limited number of available counters (32), users may quickly
exhaust the available counters. If the system runs out of assignable ABMC
counters, the kernel will report an error. In such cases, users will need to
unassign one or more active counters to free up counters for new assignments.
resctrl will provide options to assign or unassign events through the
group-specific interface file.

The feature is detected via CPUID_Fn80000020_EBX_x00 bit 5: ABMC (Assignable
Bandwidth Monitoring Counters).

The ABMC feature details are documented in APM [1] available from [2]. [1]
AMD64 Architecture Programmer's Manual Volume 2: System Programming
Publication # 24593 Revision 3.41 section 19.3.3.3 Assignable Bandwidth
Monitoring (ABMC).

  [ bp: Massage commit message, fixup enumeration due to VMSCAPE ]

Signed-off-by: Babu Moger <babu.moger@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/cover.1757108044.git.babu.moger@amd.com
Link: https://bugzilla.kernel.org/show_bug.cgi?id=206537 # [2]

 Conflicts:
	arch/x86/include/asm/cpufeatures.h
	arch/x86/kernel/cpu/scattered.c
[jz: resolve simple context conflicts]
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/include/asm/cpufeatures.h | 1 +
 arch/x86/kernel/cpu/scattered.c    | 1 +
 2 files changed, 2 insertions(+)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index c21b60114384c..eb88f39b172b0 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -485,6 +485,7 @@
 #define X86_FEATURE_TSA_L1_NO          (21*32+12) /* "" AMD CPU not vulnerable to TSA-L1 */
 #define X86_FEATURE_CLEAR_CPU_BUF_VM   (21*32+13) /* "" Clear CPU buffers using VERW before VMRUN */
 #define X86_FEATURE_IBPB_EXIT_TO_USER  (21*32+14) /* Use IBPB on exit-to-userspace, see VMSCAPE bug */
+#define X86_FEATURE_ABMC		(21*32+15) /* Assignable Bandwidth Monitoring Counters */
 
 /*
  * BUG word(s)
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 5adf08a2aca30..a2f075879776e 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -50,6 +50,7 @@ static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_COHERENCY_SFW_NO,	CPUID_EBX, 31, 0x8000001f, 0 },
 	{ X86_FEATURE_SMBA,		CPUID_EBX,  2, 0x80000020, 0 },
 	{ X86_FEATURE_BMEC,		CPUID_EBX,  3, 0x80000020, 0 },
+	{ X86_FEATURE_ABMC,		CPUID_EBX,  5, 0x80000020, 0 },
 	{ X86_FEATURE_AMD_WORKLOAD_CLASS,	CPUID_EAX,  22, 0x80000021, 0 },
 	{ X86_FEATURE_TSA_SQ_NO,	CPUID_ECX,  1, 0x80000021, 0 },
 	{ X86_FEATURE_TSA_L1_NO,	CPUID_ECX,  2, 0x80000021, 0 },

From e53bf377d3cc6e3f0da560cf29498977775a9004 Mon Sep 17 00:00:00 2001
From: Babu Moger <babu.moger@amd.com>
Date: Fri, 5 Sep 2025 16:34:06 -0500
Subject: [PATCH 097/236] x86,fs/resctrl: Consolidate monitoring related data
 from rdt_resource

commit 5ad68c8f965fed78c61f2ac7aea933f06bb50032 upstream.

The cache allocation and memory bandwidth allocation feature properties are
consolidated into struct resctrl_cache and struct resctrl_membw respectively.

In preparation for more monitoring properties that will clobber the existing
resource struct more, re-organize the monitoring specific properties to also
be in a separate structure.

Also convert "bandwidth sources" terminology to "memory transactions" to have
consistency within resctrl for related monitoring features.

  [ bp: Massage commit message. ]

Suggested-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Babu Moger <babu.moger@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/cover.1757108044.git.babu.moger@amd.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c    |  4 ++--
 arch/x86/kernel/cpu/resctrl/monitor.c | 10 +++++-----
 fs/resctrl/rdtgroup.c                 |  6 +++---
 include/linux/resctrl.h               | 18 +++++++++++++-----
 4 files changed, 23 insertions(+), 15 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 3885ec1c61ef5..2dbaa145fbfe5 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -106,7 +106,7 @@ u32 resctrl_arch_system_num_rmid_idx(void)
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
 
 	/* RMID are independent numbers for x86. num_rmid_idx == num_rmid */
-	return r->num_rmid;
+	return r->mon.num_rmid;
 }
 
 struct rdt_resource *resctrl_arch_get_resource(enum resctrl_res_level l)
@@ -540,7 +540,7 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
 
 	arch_mon_domain_online(r, d);
 
-	if (arch_domain_mbm_alloc(r->num_rmid, hw_dom)) {
+	if (arch_domain_mbm_alloc(r->mon.num_rmid, hw_dom)) {
 		mon_domain_free(hw_dom);
 		return;
 	}
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 3c7c21d8c175b..c514428f841f9 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -129,7 +129,7 @@ static int logical_rmid_to_physical_rmid(int cpu, int lrmid)
 	if (snc_nodes_per_l3_cache == 1)
 		return lrmid;
 
-	return lrmid + (cpu_to_node(cpu) % snc_nodes_per_l3_cache) * r->num_rmid;
+	return lrmid + (cpu_to_node(cpu) % snc_nodes_per_l3_cache) * r->mon.num_rmid;
 }
 
 static int __rmid_read_phys(u32 prmid, enum resctrl_event_id eventid, u64 *val)
@@ -204,7 +204,7 @@ void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *
 			continue;
 		idx = MBM_STATE_IDX(eventid);
 		memset(hw_dom->arch_mbm_states[idx], 0,
-		       sizeof(*hw_dom->arch_mbm_states[0]) * r->num_rmid);
+		       sizeof(*hw_dom->arch_mbm_states[0]) * r->mon.num_rmid);
 	}
 }
 
@@ -343,7 +343,7 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 
 	resctrl_rmid_realloc_limit = boot_cpu_data.x86_cache_size * 1024;
 	hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale / snc_nodes_per_l3_cache;
-	r->num_rmid = (boot_cpu_data.x86_cache_max_rmid + 1) / snc_nodes_per_l3_cache;
+	r->mon.num_rmid = (boot_cpu_data.x86_cache_max_rmid + 1) / snc_nodes_per_l3_cache;
 	hw_res->mbm_width = MBM_CNTR_WIDTH_BASE;
 
 	if (mbm_offset > 0 && mbm_offset <= MBM_CNTR_WIDTH_OFFSET_MAX)
@@ -358,7 +358,7 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 	 *
 	 * For a 35MB LLC and 56 RMIDs, this is ~1.8% of the LLC.
 	 */
-	threshold = resctrl_rmid_realloc_limit / r->num_rmid;
+	threshold = resctrl_rmid_realloc_limit / r->mon.num_rmid;
 
 	/*
 	 * Because num_rmid may not be a power of two, round the value
@@ -372,7 +372,7 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 
 		/* Detect list of bandwidth sources that can be tracked */
 		cpuid_count(0x80000020, 3, &eax, &ebx, &ecx, &edx);
-		r->mbm_cfg_mask = ecx & MAX_EVT_CONFIG_BITS;
+		r->mon.mbm_cfg_mask = ecx & MAX_EVT_CONFIG_BITS;
 	}
 
 	r->mon_capable = true;
diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index a6047e9345cda..b6ab107049939 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -1135,7 +1135,7 @@ static int rdt_num_rmids_show(struct kernfs_open_file *of,
 {
 	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
 
-	seq_printf(seq, "%d\n", r->num_rmid);
+	seq_printf(seq, "%d\n", r->mon.num_rmid);
 
 	return 0;
 }
@@ -1731,9 +1731,9 @@ static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid)
 	}
 
 	/* Value from user cannot be more than the supported set of events */
-	if ((val & r->mbm_cfg_mask) != val) {
+	if ((val & r->mon.mbm_cfg_mask) != val) {
 		rdt_last_cmd_printf("Invalid event configuration: max valid mask is 0x%02x\n",
-				    r->mbm_cfg_mask);
+				    r->mon.mbm_cfg_mask);
 		return -EINVAL;
 	}
 
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 478d7a935ca36..fe2af6cb96d4b 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -255,38 +255,46 @@ enum resctrl_schema_fmt {
 	RESCTRL_SCHEMA_RANGE,
 };
 
+/**
+ * struct resctrl_mon - Monitoring related data of a resctrl resource.
+ * @num_rmid:		Number of RMIDs available.
+ * @mbm_cfg_mask:	Memory transactions that can be tracked when bandwidth
+ *			monitoring events can be configured.
+ */
+struct resctrl_mon {
+	int			num_rmid;
+	unsigned int		mbm_cfg_mask;
+};
+
 /**
  * struct rdt_resource - attributes of a resctrl resource
  * @rid:		The index of the resource
  * @alloc_capable:	Is allocation available on this machine
  * @mon_capable:	Is monitor feature available on this machine
- * @num_rmid:		Number of RMIDs available
  * @ctrl_scope:		Scope of this resource for control functions
  * @mon_scope:		Scope of this resource for monitor functions
  * @cache:		Cache allocation related data
  * @membw:		If the component has bandwidth controls, their properties.
+ * @mon:		Monitoring related data.
  * @ctrl_domains:	RCU list of all control domains for this resource
  * @mon_domains:	RCU list of all monitor domains for this resource
  * @name:		Name to use in "schemata" file.
  * @schema_fmt:		Which format string and parser is used for this schema.
- * @mbm_cfg_mask:	Bandwidth sources that can be tracked when bandwidth
- *			monitoring events can be configured.
  * @cdp_capable:	Is the CDP feature available on this resource
  */
 struct rdt_resource {
 	int			rid;
 	bool			alloc_capable;
 	bool			mon_capable;
-	int			num_rmid;
 	enum resctrl_scope	ctrl_scope;
 	enum resctrl_scope	mon_scope;
 	struct resctrl_cache	cache;
 	struct resctrl_membw	membw;
+	struct resctrl_mon	mon;
 	struct list_head	ctrl_domains;
 	struct list_head	mon_domains;
 	char			*name;
 	enum resctrl_schema_fmt	schema_fmt;
-	unsigned int		mbm_cfg_mask;
 	bool			cdp_capable;
 };
 

From 05e278bdfbb40d35bfedfc02d94c0340e0b865c5 Mon Sep 17 00:00:00 2001
From: Babu Moger <babu.moger@amd.com>
Date: Fri, 5 Sep 2025 16:34:07 -0500
Subject: [PATCH 098/236] x86,fs/resctrl: Detect Assignable Bandwidth
 Monitoring feature details

commit 13390861b426e936db20d675804a5b405622bc79 upstream.

ABMC feature details are reported via CPUID Fn8000_0020_EBX_x5.
Bits Description
15:0 MAX_ABMC Maximum Supported Assignable Bandwidth
     Monitoring Counter ID + 1

The ABMC feature details are documented in APM [1] available from [2].

  [1] AMD64 Architecture Programmer's Manual Volume 2: System Programming
  Publication # 24593 Revision 3.41 section 19.3.3.3 Assignable Bandwidth
  Monitoring (ABMC).

Detect the feature and number of assignable counters supported. For backward
compatibility, upon detecting the assignable counter feature, enable the
mbm_total_bytes and mbm_local_bytes events that users are familiar with as
part of original L3 MBM support.

Signed-off-by: Babu Moger <babu.moger@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/cover.1757108044.git.babu.moger@amd.com
Link: https://bugzilla.kernel.org/show_bug.cgi?id=206537 # [2]
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c    |  7 +++++--
 arch/x86/kernel/cpu/resctrl/monitor.c | 11 ++++++++---
 fs/resctrl/monitor.c                  |  7 +++++++
 include/linux/resctrl.h               |  4 ++++
 4 files changed, 24 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 2dbaa145fbfe5..eeb271dbb54c0 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -881,6 +881,8 @@ static __init bool get_rdt_mon_resources(void)
 		resctrl_enable_mon_event(QOS_L3_MBM_LOCAL_EVENT_ID);
 		ret = true;
 	}
+	if (rdt_cpu_has(X86_FEATURE_ABMC))
+		ret = true;
 
 	if (!ret)
 		return false;
@@ -977,7 +979,7 @@ static enum cpuhp_state rdt_online;
 /* Runs once on the BSP during boot. */
 void resctrl_cpu_detect(struct cpuinfo_x86 *c)
 {
-	if (!cpu_has(c, X86_FEATURE_CQM_LLC)) {
+	if (!cpu_has(c, X86_FEATURE_CQM_LLC) && !cpu_has(c, X86_FEATURE_ABMC)) {
 		c->x86_cache_max_rmid  = -1;
 		c->x86_cache_occ_scale = -1;
 		c->x86_cache_mbm_width_offset = -1;
@@ -989,7 +991,8 @@ void resctrl_cpu_detect(struct cpuinfo_x86 *c)
 
 	if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC) ||
 	    cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL) ||
-	    cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)) {
+	    cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL) ||
+	    cpu_has(c, X86_FEATURE_ABMC)) {
 		u32 eax, ebx, ecx, edx;
 
 		/* QoS sub-leaf, EAX=0Fh, ECX=1 */
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index c514428f841f9..f120592331be0 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -338,6 +338,7 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 	unsigned int mbm_offset = boot_cpu_data.x86_cache_mbm_width_offset;
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 	unsigned int threshold;
+	u32 eax, ebx, ecx, edx;
 
 	snc_nodes_per_l3_cache = snc_get_config();
 
@@ -367,14 +368,18 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 	 */
 	resctrl_rmid_realloc_threshold = resctrl_arch_round_mon_val(threshold);
 
-	if (rdt_cpu_has(X86_FEATURE_BMEC)) {
-		u32 eax, ebx, ecx, edx;
-
+	if (rdt_cpu_has(X86_FEATURE_BMEC) || rdt_cpu_has(X86_FEATURE_ABMC)) {
 		/* Detect list of bandwidth sources that can be tracked */
 		cpuid_count(0x80000020, 3, &eax, &ebx, &ecx, &edx);
 		r->mon.mbm_cfg_mask = ecx & MAX_EVT_CONFIG_BITS;
 	}
 
+	if (rdt_cpu_has(X86_FEATURE_ABMC)) {
+		r->mon.mbm_cntr_assignable = true;
+		cpuid_count(0x80000020, 5, &eax, &ebx, &ecx, &edx);
+		r->mon.num_mbm_cntrs = (ebx & GENMASK(15, 0)) + 1;
+	}
+
 	r->mon_capable = true;
 
 	return 0;
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index e0dfa5fb969e4..b578451de2b50 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -922,6 +922,13 @@ int resctrl_mon_resource_init(void)
 	else if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID))
 		mba_mbps_default_event = QOS_L3_MBM_TOTAL_EVENT_ID;
 
+	if (r->mon.mbm_cntr_assignable) {
+		if (!resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID))
+			resctrl_enable_mon_event(QOS_L3_MBM_TOTAL_EVENT_ID);
+		if (!resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID))
+			resctrl_enable_mon_event(QOS_L3_MBM_LOCAL_EVENT_ID);
+	}
+
 	return 0;
 }
 
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index fe2af6cb96d4b..eb80cc233be43 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -260,10 +260,14 @@ enum resctrl_schema_fmt {
  * @num_rmid:		Number of RMIDs available.
  * @mbm_cfg_mask:	Memory transactions that can be tracked when bandwidth
  *			monitoring events can be configured.
+ * @num_mbm_cntrs:	Number of assignable counters.
+ * @mbm_cntr_assignable:Is system capable of supporting counter assignment?
  */
 struct resctrl_mon {
 	int			num_rmid;
 	unsigned int		mbm_cfg_mask;
+	int			num_mbm_cntrs;
+	bool			mbm_cntr_assignable;
 };
 
 /**

From f9e4b565c498fb9f332313ca377fe8ab6762568e Mon Sep 17 00:00:00 2001
From: Babu Moger <babu.moger@amd.com>
Date: Fri, 5 Sep 2025 16:34:08 -0500
Subject: [PATCH 099/236] x86/resctrl: Add support to enable/disable AMD ABMC
 feature

commit faebbc58cde9d8f6050ac152c34c88195ed4abaa upstream.

Add the functionality to enable/disable the AMD ABMC feature.

The AMD ABMC feature is enabled by setting enabled bit(0) in the
L3_QOS_EXT_CFG MSR. When the state of ABMC is changed, the MSR needs to be
updated on all the logical processors in the QOS Domain.

Hardware counters will reset when ABMC state is changed.

  [ bp: Massage commit message. ]

Signed-off-by: Babu Moger <babu.moger@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/cover.1757108044.git.babu.moger@amd.com
Link: https://bugzilla.kernel.org/show_bug.cgi?id=206537 # [2]
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/include/asm/msr-index.h       |  1 +
 arch/x86/kernel/cpu/resctrl/internal.h |  5 +++
 arch/x86/kernel/cpu/resctrl/monitor.c  | 45 ++++++++++++++++++++++++++
 include/linux/resctrl.h                | 20 ++++++++++++
 4 files changed, 71 insertions(+)

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 7bdbee2da3b60..6311ad98cb325 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -1234,6 +1234,7 @@
 /* - AMD: */
 #define MSR_IA32_MBA_BW_BASE		0xc0000200
 #define MSR_IA32_SMBA_BW_BASE		0xc0000280
+#define MSR_IA32_L3_QOS_EXT_CFG		0xc00003ff
 #define MSR_IA32_EVT_CFG_BASE		0xc0000400
 
 /* MSR_IA32_VMX_MISC bits */
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 30d9cac5ec72f..71a9cc0307b99 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -40,6 +40,9 @@ struct arch_mbm_state {
 	u64	prev_msr;
 };
 
+/* Setting bit 0 in L3_QOS_EXT_CFG enables the ABMC feature. */
+#define ABMC_ENABLE_BIT			0
+
 /**
  * struct rdt_hw_ctrl_domain - Arch private attributes of a set of CPUs that share
  *			       a resource for a control function
@@ -105,6 +108,7 @@ struct msr_param {
  * @mon_scale:		cqm counter * mon_scale = occupancy in bytes
  * @mbm_width:		Monitor width, to detect and correct for overflow.
  * @cdp_enabled:	CDP state of this resource
+ * @mbm_cntr_assign_enabled:	ABMC feature is enabled
  *
  * Members of this structure are either private to the architecture
  * e.g. mbm_width, or accessed via helpers that provide abstraction. e.g.
@@ -118,6 +122,7 @@ struct rdt_hw_resource {
 	unsigned int		mon_scale;
 	unsigned int		mbm_width;
 	bool			cdp_enabled;
+	bool			mbm_cntr_assign_enabled;
 };
 
 static inline struct rdt_hw_resource *resctrl_to_arch_res(struct rdt_resource *r)
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index f120592331be0..6dc64984deaef 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -398,3 +398,48 @@ void __init intel_rdt_mbm_apply_quirk(void)
 	mbm_cf_rmidthreshold = mbm_cf_table[cf_index].rmidthreshold;
 	mbm_cf = mbm_cf_table[cf_index].cf;
 }
+
+static void resctrl_abmc_set_one_amd(void *arg)
+{
+	bool *enable = arg;
+
+	if (*enable)
+		msr_set_bit(MSR_IA32_L3_QOS_EXT_CFG, ABMC_ENABLE_BIT);
+	else
+		msr_clear_bit(MSR_IA32_L3_QOS_EXT_CFG, ABMC_ENABLE_BIT);
+}
+
+/*
+ * ABMC enable/disable requires update of L3_QOS_EXT_CFG MSR on all the CPUs
+ * associated with all monitor domains.
+ */
+static void _resctrl_abmc_enable(struct rdt_resource *r, bool enable)
+{
+	struct rdt_mon_domain *d;
+
+	lockdep_assert_cpus_held();
+
+	list_for_each_entry(d, &r->mon_domains, hdr.list) {
+		on_each_cpu_mask(&d->hdr.cpu_mask, resctrl_abmc_set_one_amd,
+				 &enable, 1);
+		resctrl_arch_reset_rmid_all(r, d);
+	}
+}
+
+int resctrl_arch_mbm_cntr_assign_set(struct rdt_resource *r, bool enable)
+{
+	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
+
+	if (r->mon.mbm_cntr_assignable &&
+	    hw_res->mbm_cntr_assign_enabled != enable) {
+		_resctrl_abmc_enable(r, enable);
+		hw_res->mbm_cntr_assign_enabled = enable;
+	}
+
+	return 0;
+}
+
+bool resctrl_arch_mbm_cntr_assign_enabled(struct rdt_resource *r)
+{
+	return resctrl_to_arch_res(r)->mbm_cntr_assign_enabled;
+}
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index eb80cc233be43..919806122c509 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -445,6 +445,26 @@ static inline u32 resctrl_get_config_index(u32 closid,
 bool resctrl_arch_get_cdp_enabled(enum resctrl_res_level l);
 int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable);
 
+/**
+ * resctrl_arch_mbm_cntr_assign_enabled() - Check if MBM counter assignment
+ *					    mode is enabled.
+ * @r:		Pointer to the resource structure.
+ *
+ * Return:
+ * true if the assignment mode is enabled, false otherwise.
+ */
+bool resctrl_arch_mbm_cntr_assign_enabled(struct rdt_resource *r);
+
+/**
+ * resctrl_arch_mbm_cntr_assign_set() - Configure the MBM counter assignment mode.
+ * @r:		Pointer to the resource structure.
+ * @enable:	Set to true to enable, false to disable the assignment mode.
+ *
+ * Return:
+ * 0 on success, < 0 on error.
+ */
+int resctrl_arch_mbm_cntr_assign_set(struct rdt_resource *r, bool enable);
+
 /*
  * Update the ctrl_val and apply this config right now.
  * Must be called on one of the domain's CPUs.

From 7e50f950e314e647c88f441cfb363a2542851b1d Mon Sep 17 00:00:00 2001
From: Babu Moger <babu.moger@amd.com>
Date: Fri, 5 Sep 2025 16:34:11 -0500
Subject: [PATCH 100/236] fs/resctrl: Introduce mbm_cntr_cfg to track
 assignable counters per domain

commit 4d32c24a74f2c12ff440d381ba01de574f6631ce upstream.

The "mbm_event" counter assignment mode allows users to assign a hardware
counter to an RMID, event pair and monitor bandwidth usage as long as it is
assigned.  The hardware continues to track the assigned counter until it is
explicitly unassigned by the user. Counters are assigned/unassigned at
monitoring domain level.

Manage a monitoring domain's hardware counters using a per monitoring
domain array of struct mbm_cntr_cfg that is indexed by the hardware
counter ID. A hardware counter's configuration contains the MBM event
ID and points to the monitoring group that it is assigned to, with a NULL
pointer meaning that the hardware counter is available for assignment.

There is no direct way to determine which hardware counters are assigned
to a particular monitoring group. Check every entry of every hardware
counter configuration array in every monitoring domain to query which
MBM events of a monitoring group is tracked by hardware. Such queries are
acceptable because of a very small number of assignable counters (32
to 64).

Suggested-by: Peter Newman <peternewman@google.com>
Signed-off-by: Babu Moger <babu.moger@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/cover.1757108044.git.babu.moger@amd.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 fs/resctrl/rdtgroup.c   |  8 ++++++++
 include/linux/resctrl.h | 15 +++++++++++++++
 2 files changed, 23 insertions(+)

diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index b6ab107049939..df12dfeced084 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -4016,6 +4016,7 @@ static void domain_destroy_mon_state(struct rdt_mon_domain *d)
 {
 	int idx;
 
+	kfree(d->cntr_cfg);
 	bitmap_free(d->rmid_busy_llc);
 	for_each_mbm_idx(idx) {
 		kfree(d->mbm_states[idx]);
@@ -4099,6 +4100,13 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_mon_domain
 			goto cleanup;
 	}
 
+	if (resctrl_is_mbm_enabled() && r->mon.mbm_cntr_assignable) {
+		tsize = sizeof(*d->cntr_cfg);
+		d->cntr_cfg = kcalloc(r->mon.num_mbm_cntrs, tsize, GFP_KERNEL);
+		if (!d->cntr_cfg)
+			goto cleanup;
+	}
+
 	return 0;
 cleanup:
 	bitmap_free(d->rmid_busy_llc);
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 919806122c509..e013caba66414 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -156,6 +156,18 @@ struct rdt_ctrl_domain {
 	u32				*mbps_val;
 };
 
+/**
+ * struct mbm_cntr_cfg - Assignable counter configuration.
+ * @evtid:		MBM event to which the counter is assigned. Only valid
+ *			if @rdtgroup is not NULL.
+ * @rdtgrp:		resctrl group assigned to the counter. NULL if the
+ *			counter is free.
+ */
+struct mbm_cntr_cfg {
+	enum resctrl_event_id	evtid;
+	struct rdtgroup		*rdtgrp;
+};
+
 /**
  * struct rdt_mon_domain - group of CPUs sharing a resctrl monitor resource
  * @hdr:		common header for different domain types
@@ -168,6 +180,8 @@ struct rdt_ctrl_domain {
  * @cqm_limbo:		worker to periodically read CQM h/w counters
  * @mbm_work_cpu:	worker CPU for MBM h/w counters
  * @cqm_work_cpu:	worker CPU for CQM h/w counters
+ * @cntr_cfg:		array of assignable counters' configuration (indexed
+ *			by counter ID)
  */
 struct rdt_mon_domain {
 	struct rdt_domain_hdr		hdr;
@@ -178,6 +192,7 @@ struct rdt_mon_domain {
 	struct delayed_work		cqm_limbo;
 	int				mbm_work_cpu;
 	int				cqm_work_cpu;
+	struct mbm_cntr_cfg		*cntr_cfg;
 };
 
 /**

From 5c3652c2f46fb7994a562c307a508ebba1094dbb Mon Sep 17 00:00:00 2001
From: Babu Moger <babu.moger@amd.com>
Date: Fri, 5 Sep 2025 16:34:13 -0500
Subject: [PATCH 101/236] x86/resctrl: Add data structures and definitions for
 ABMC assignment
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 84ecefb766748916099f5b7444a973a623611d63 upstream.

The ABMC feature allows users to assign a hardware counter to an RMID,
event pair and monitor bandwidth usage as long as it is assigned. The
hardware continues to track the assigned counter until it is explicitly
unassigned by the user.

The ABMC feature implements an MSR L3_QOS_ABMC_CFG (C000_03FDh).
ABMC counter assignment is done by setting the counter id, bandwidth
source (RMID) and bandwidth configuration.

Attempts to read or write the MSR when ABMC is not enabled will result
in a #GP(0) exception.

Introduce the data structures and definitions for MSR L3_QOS_ABMC_CFG
(0xC000_03FDh):
=========================================================================
Bits 	Mnemonic	Description			Access Reset
							Type   Value
=========================================================================
63 	CfgEn 		Configuration Enable 		R/W 	0

62 	CtrEn 		Enable/disable counting		R/W 	0

61:53 	– 		Reserved 			MBZ 	0

52:48 	CtrID 		Counter Identifier		R/W	0

47 	IsCOS		BwSrc field is a CLOSID		R/W	0
			(not an RMID)

46:44 	–		Reserved			MBZ	0

43:32	BwSrc		Bandwidth Source		R/W	0
			(RMID or CLOSID)

31:0	BwType		Bandwidth configuration		R/W	0
			tracked by the CtrID
==========================================================================

The ABMC feature details are documented in APM [1] available from [2].
[1] AMD64 Architecture Programmer's Manual Volume 2: System Programming
Publication # 24593 Revision 3.41 section 19.3.3.3 Assignable Bandwidth
Monitoring (ABMC).

  [ bp: Touchups. ]

Signed-off-by: Babu Moger <babu.moger@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/cover.1757108044.git.babu.moger@amd.com
Link: https://bugzilla.kernel.org/show_bug.cgi?id=206537 # [2]
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/include/asm/msr-index.h       |  1 +
 arch/x86/kernel/cpu/resctrl/internal.h | 36 ++++++++++++++++++++++++++
 2 files changed, 37 insertions(+)

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 6311ad98cb325..0fa669ff32343 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -1234,6 +1234,7 @@
 /* - AMD: */
 #define MSR_IA32_MBA_BW_BASE		0xc0000200
 #define MSR_IA32_SMBA_BW_BASE		0xc0000280
+#define MSR_IA32_L3_QOS_ABMC_CFG	0xc00003fd
 #define MSR_IA32_L3_QOS_EXT_CFG		0xc00003ff
 #define MSR_IA32_EVT_CFG_BASE		0xc0000400
 
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 71a9cc0307b99..63166be49ea67 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -167,6 +167,42 @@ union cpuid_0x10_x_edx {
 	unsigned int full;
 };
 
+/*
+ * ABMC counters are configured by writing to MSR_IA32_L3_QOS_ABMC_CFG.
+ *
+ * @bw_type		: Event configuration that represents the memory
+ *			  transactions being tracked by the @cntr_id.
+ * @bw_src		: Bandwidth source (RMID or CLOSID).
+ * @reserved1		: Reserved.
+ * @is_clos		: @bw_src field is a CLOSID (not an RMID).
+ * @cntr_id		: Counter identifier.
+ * @reserved		: Reserved.
+ * @cntr_en		: Counting enable bit.
+ * @cfg_en		: Configuration enable bit.
+ *
+ * Configuration and counting:
+ * Counter can be configured across multiple writes to MSR. Configuration
+ * is applied only when @cfg_en = 1. Counter @cntr_id is reset when the
+ * configuration is applied.
+ * @cfg_en = 1, @cntr_en = 0 : Apply @cntr_id configuration but do not
+ *                             count events.
+ * @cfg_en = 1, @cntr_en = 1 : Apply @cntr_id configuration and start
+ *                             counting events.
+ */
+union l3_qos_abmc_cfg {
+	struct {
+		unsigned long bw_type  :32,
+			      bw_src   :12,
+			      reserved1: 3,
+			      is_clos  : 1,
+			      cntr_id  : 5,
+			      reserved : 9,
+			      cntr_en  : 1,
+			      cfg_en   : 1;
+	} split;
+	unsigned long full;
+};
+
 void rdt_ctrl_update(void *arg);
 
 int rdt_get_mon_l3_config(struct rdt_resource *r);

From 5b8b2768dc724234d90fea5e0910e529241fdc4b Mon Sep 17 00:00:00 2001
From: Babu Moger <babu.moger@amd.com>
Date: Fri, 5 Sep 2025 16:34:14 -0500
Subject: [PATCH 102/236] fs/resctrl: Introduce event configuration field in
 struct mon_evt

commit ebebda853633de389ba2c6737f8ca38405713e90 upstream.

When supported, mbm_event counter assignment mode allows the user to configure
events to track specific types of memory transactions.

Introduce an evt_cfg field in struct mon_evt to define the type of memory
transactions tracked by a monitoring event. Also add a helper function to get
the evt_cfg value.

Signed-off-by: Babu Moger <babu.moger@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/cover.1757108044.git.babu.moger@amd.com

 Conflicts:
	fs/resctrl/monitor.c
[jz: resolve context conflicts]
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 fs/resctrl/internal.h   |  5 +++++
 fs/resctrl/monitor.c    | 10 ++++++++++
 include/linux/resctrl.h |  2 ++
 3 files changed, 17 insertions(+)

diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index 7a57366d1abce..c1f59c46689f4 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -56,6 +56,10 @@ static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc)
  * @evtid:		event id
  * @rid:		resource id for this event
  * @name:		name of the event
+ * @evt_cfg:		Event configuration value that represents the
+ *			memory transactions (e.g., READS_TO_LOCAL_MEM,
+ *			READS_TO_REMOTE_MEM) being tracked by @evtid.
+ *			Only valid if @evtid is an MBM event.
  * @configurable:	true if the event is configurable
  * @enabled:		true if the event is enabled
  */
@@ -63,6 +67,7 @@ struct mon_evt {
 	enum resctrl_event_id	evtid;
 	enum resctrl_res_level	rid;
 	char			*name;
+	u32			evt_cfg;
 	bool			configurable;
 	bool			enabled;
 };
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index b578451de2b50..31ee5396c00ea 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -882,6 +882,11 @@ bool resctrl_is_mon_event_enabled(enum resctrl_event_id eventid)
 	       mon_event_all[eventid].enabled;
 }
 
+u32 resctrl_get_mon_evt_cfg(enum resctrl_event_id evtid)
+{
+	return mon_event_all[evtid].evt_cfg;
+}
+
 /**
  * resctrl_mon_resource_init() - Initialise global monitoring structures.
  *
@@ -927,6 +932,11 @@ int resctrl_mon_resource_init(void)
 			resctrl_enable_mon_event(QOS_L3_MBM_TOTAL_EVENT_ID);
 		if (!resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID))
 			resctrl_enable_mon_event(QOS_L3_MBM_LOCAL_EVENT_ID);
+		mon_event_all[QOS_L3_MBM_TOTAL_EVENT_ID].evt_cfg = r->mon.mbm_cfg_mask;
+		mon_event_all[QOS_L3_MBM_LOCAL_EVENT_ID].evt_cfg = r->mon.mbm_cfg_mask &
+								   (READS_TO_LOCAL_MEM |
+								    READS_TO_LOCAL_S_MEM |
+								    NON_TEMP_WRITE_TO_LOCAL_MEM);
 	}
 
 	return 0;
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index e013caba66414..87daa4ca312dd 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -409,6 +409,8 @@ static inline bool resctrl_is_mbm_event(enum resctrl_event_id eventid)
 		eventid <= QOS_L3_MBM_LOCAL_EVENT_ID);
 }
 
+u32 resctrl_get_mon_evt_cfg(enum resctrl_event_id eventid);
+
 /* Iterate over all memory bandwidth events */
 #define for_each_mbm_event_id(eventid)				\
 	for (eventid = QOS_L3_MBM_TOTAL_EVENT_ID;		\

From 738499acaaf4b1d84a32def865f4850ee669c5eb Mon Sep 17 00:00:00 2001
From: Babu Moger <babu.moger@amd.com>
Date: Fri, 5 Sep 2025 16:34:15 -0500
Subject: [PATCH 103/236] x86,fs/resctrl: Implement resctrl_arch_config_cntr()
 to assign a counter with ABMC

commit f7a4fb22312646329ba21bc58958fd83fb9fc15d upstream.

The ABMC feature allows users to assign a hardware counter to an RMID,
event pair and monitor bandwidth usage as long as it is assigned. The
hardware continues to track the assigned counter until it is explicitly
unassigned by the user.

Implement an x86 architecture-specific handler to configure a counter. This
architecture specific handler is called by resctrl fs when a counter is
assigned or unassigned as well as when an already assigned counter's
configuration should be updated. Configure counters by writing to the
L3_QOS_ABMC_CFG MSR, specifying the counter ID, bandwidth source (RMID),
and event configuration.

The ABMC feature details are documented in APM [1] available from [2].
[1] AMD64 Architecture Programmer's Manual Volume 2: System Programming
    Publication # 24593 Revision 3.41 section 19.3.3.3 Assignable Bandwidth
    Monitoring (ABMC).

Signed-off-by: Babu Moger <babu.moger@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/cover.1757108044.git.babu.moger@amd.com
Link: https://bugzilla.kernel.org/show_bug.cgi?id=206537 # [2]
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/monitor.c | 36 +++++++++++++++++++++++++++
 include/linux/resctrl.h               | 19 ++++++++++++++
 2 files changed, 55 insertions(+)

diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 6dc64984deaef..4a48d23f5ac43 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -443,3 +443,39 @@ bool resctrl_arch_mbm_cntr_assign_enabled(struct rdt_resource *r)
 {
 	return resctrl_to_arch_res(r)->mbm_cntr_assign_enabled;
 }
+
+static void resctrl_abmc_config_one_amd(void *info)
+{
+	union l3_qos_abmc_cfg *abmc_cfg = info;
+
+	wrmsrl(MSR_IA32_L3_QOS_ABMC_CFG, abmc_cfg->full);
+}
+
+/*
+ * Send an IPI to the domain to assign the counter to RMID, event pair.
+ */
+void resctrl_arch_config_cntr(struct rdt_resource *r, struct rdt_mon_domain *d,
+			      enum resctrl_event_id evtid, u32 rmid, u32 closid,
+			      u32 cntr_id, bool assign)
+{
+	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
+	union l3_qos_abmc_cfg abmc_cfg = { 0 };
+	struct arch_mbm_state *am;
+
+	abmc_cfg.split.cfg_en = 1;
+	abmc_cfg.split.cntr_en = assign ? 1 : 0;
+	abmc_cfg.split.cntr_id = cntr_id;
+	abmc_cfg.split.bw_src = rmid;
+	if (assign)
+		abmc_cfg.split.bw_type = resctrl_get_mon_evt_cfg(evtid);
+
+	smp_call_function_any(&d->hdr.cpu_mask, resctrl_abmc_config_one_amd, &abmc_cfg, 1);
+
+	/*
+	 * The hardware counter is reset (because cfg_en == 1) so there is no
+	 * need to record initial non-zero counts.
+	 */
+	am = get_arch_mbm_state(hw_dom, rmid, evtid);
+	if (am)
+		memset(am, 0, sizeof(*am));
+}
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 87daa4ca312dd..50e38445183a8 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -594,6 +594,25 @@ void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *
  */
 void resctrl_arch_reset_all_ctrls(struct rdt_resource *r);
 
+/**
+ * resctrl_arch_config_cntr() - Configure the counter with its new RMID
+ *				and event details.
+ * @r:			Resource structure.
+ * @d:			The domain in which counter with ID @cntr_id should be configured.
+ * @evtid:		Monitoring event type (e.g., QOS_L3_MBM_TOTAL_EVENT_ID
+ *			or QOS_L3_MBM_LOCAL_EVENT_ID).
+ * @rmid:		RMID.
+ * @closid:		CLOSID.
+ * @cntr_id:		Counter ID to configure.
+ * @assign:		True to assign the counter or update an existing assignment,
+ *			false to unassign the counter.
+ *
+ * This can be called from any CPU.
+ */
+void resctrl_arch_config_cntr(struct rdt_resource *r, struct rdt_mon_domain *d,
+			      enum resctrl_event_id evtid, u32 rmid, u32 closid,
+			      u32 cntr_id, bool assign);
+
 extern unsigned int resctrl_rmid_realloc_threshold;
 extern unsigned int resctrl_rmid_realloc_limit;
 

From 1fbbf4eec8eaec4658da13d233fb0f54ee9af972 Mon Sep 17 00:00:00 2001
From: Babu Moger <babu.moger@amd.com>
Date: Fri, 5 Sep 2025 16:34:16 -0500
Subject: [PATCH 104/236] fs/resctrl: Add the functionality to assign MBM
 events

commit bd85310efd71b9e7809e1b95fe7a60fde42e62db upstream.

When supported, "mbm_event" counter assignment mode offers "num_mbm_cntrs"
number of counters that can be assigned to RMID, event pairs and monitor
bandwidth usage as long as it is assigned.

Add the functionality to allocate and assign a counter to an RMID, event
pair in the domain. Also, add the helper rdtgroup_assign_cntrs() to assign
counters in the group.

Log the error message "Failed to allocate counter for <event> in domain
<id>" in /sys/fs/resctrl/info/last_cmd_status if all the counters are in
use. Exit on the first failure when assigning counters across all the
domains.

Signed-off-by: Babu Moger <babu.moger@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/cover.1757108044.git.babu.moger@amd.com

 Conflicts:
	fs/resctrl/internal.h
	fs/resctrl/monitor.c
[jz: resolve context conflicts]
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 fs/resctrl/internal.h |   2 +
 fs/resctrl/monitor.c  | 156 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 158 insertions(+)

diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index c1f59c46689f4..be1858eaaa7b2 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -387,6 +387,8 @@ bool closid_allocated(unsigned int closid);
 
 int resctrl_find_cleanest_closid(void);
 
+void rdtgroup_assign_cntrs(struct rdtgroup *rdtgrp);
+
 #ifdef CONFIG_RESCTRL_FS_PSEUDO_LOCK
 int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp);
 
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index 31ee5396c00ea..18b57c5473e1b 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -356,6 +356,55 @@ static struct mbm_state *get_mbm_state(struct rdt_mon_domain *d, u32 closid,
 	return state ? &state[idx] : NULL;
 }
 
+/*
+ * mbm_cntr_get() - Return the counter ID for the matching @evtid and @rdtgrp.
+ *
+ * Return:
+ * Valid counter ID on success, or -ENOENT on failure.
+ */
+static int mbm_cntr_get(struct rdt_resource *r, struct rdt_mon_domain *d,
+			struct rdtgroup *rdtgrp, enum resctrl_event_id evtid)
+{
+	int cntr_id;
+
+	if (!r->mon.mbm_cntr_assignable)
+		return -ENOENT;
+
+	if (!resctrl_is_mbm_event(evtid))
+		return -ENOENT;
+
+	for (cntr_id = 0; cntr_id < r->mon.num_mbm_cntrs; cntr_id++) {
+		if (d->cntr_cfg[cntr_id].rdtgrp == rdtgrp &&
+		    d->cntr_cfg[cntr_id].evtid == evtid)
+			return cntr_id;
+	}
+
+	return -ENOENT;
+}
+
+/*
+ * mbm_cntr_alloc() - Initialize and return a new counter ID in the domain @d.
+ * Caller must ensure that the specified event is not assigned already.
+ *
+ * Return:
+ * Valid counter ID on success, or -ENOSPC on failure.
+ */
+static int mbm_cntr_alloc(struct rdt_resource *r, struct rdt_mon_domain *d,
+			  struct rdtgroup *rdtgrp, enum resctrl_event_id evtid)
+{
+	int cntr_id;
+
+	for (cntr_id = 0; cntr_id < r->mon.num_mbm_cntrs; cntr_id++) {
+		if (!d->cntr_cfg[cntr_id].rdtgrp) {
+			d->cntr_cfg[cntr_id].rdtgrp = rdtgrp;
+			d->cntr_cfg[cntr_id].evtid = evtid;
+			return cntr_id;
+		}
+	}
+
+	return -ENOSPC;
+}
+
 static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 {
 	int cpu = smp_processor_id();
@@ -887,6 +936,113 @@ u32 resctrl_get_mon_evt_cfg(enum resctrl_event_id evtid)
 	return mon_event_all[evtid].evt_cfg;
 }
 
+/*
+ * rdtgroup_assign_cntr() - Assign/unassign the counter ID for the event, RMID
+ * pair in the domain.
+ *
+ * Assign the counter if @assign is true else unassign the counter. Reset the
+ * associated non-architectural state.
+ */
+static void rdtgroup_assign_cntr(struct rdt_resource *r, struct rdt_mon_domain *d,
+				 enum resctrl_event_id evtid, u32 rmid, u32 closid,
+				 u32 cntr_id, bool assign)
+{
+	struct mbm_state *m;
+
+	resctrl_arch_config_cntr(r, d, evtid, rmid, closid, cntr_id, assign);
+
+	m = get_mbm_state(d, closid, rmid, evtid);
+	if (m)
+		memset(m, 0, sizeof(*m));
+}
+
+/*
+ * rdtgroup_alloc_assign_cntr() - Allocate a counter ID and assign it to the event
+ * pointed to by @mevt and the resctrl group @rdtgrp within the domain @d.
+ *
+ * Return:
+ * 0 on success, < 0 on failure.
+ */
+static int rdtgroup_alloc_assign_cntr(struct rdt_resource *r, struct rdt_mon_domain *d,
+				      struct rdtgroup *rdtgrp, struct mon_evt *mevt)
+{
+	int cntr_id;
+
+	/* No action required if the counter is assigned already. */
+	cntr_id = mbm_cntr_get(r, d, rdtgrp, mevt->evtid);
+	if (cntr_id >= 0)
+		return 0;
+
+	cntr_id = mbm_cntr_alloc(r, d, rdtgrp, mevt->evtid);
+	if (cntr_id < 0) {
+		rdt_last_cmd_printf("Failed to allocate counter for %s in domain %d\n",
+				    mevt->name, d->hdr.id);
+		return cntr_id;
+	}
+
+	rdtgroup_assign_cntr(r, d, mevt->evtid, rdtgrp->mon.rmid, rdtgrp->closid, cntr_id, true);
+
+	return 0;
+}
+
+/*
+ * rdtgroup_assign_cntr_event() - Assign a hardware counter for the event in
+ * @mevt to the resctrl group @rdtgrp. Assign counters to all domains if @d is
+ * NULL; otherwise, assign the counter to the specified domain @d.
+ *
+ * If all counters in a domain are already in use, rdtgroup_alloc_assign_cntr()
+ * will fail. The assignment process will abort at the first failure encountered
+ * during domain traversal, which may result in the event being only partially
+ * assigned.
+ *
+ * Return:
+ * 0 on success, < 0 on failure.
+ */
+static int rdtgroup_assign_cntr_event(struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
+				      struct mon_evt *mevt)
+{
+	struct rdt_resource *r = resctrl_arch_get_resource(mevt->rid);
+	int ret = 0;
+
+	if (!d) {
+		list_for_each_entry(d, &r->mon_domains, hdr.list) {
+			ret = rdtgroup_alloc_assign_cntr(r, d, rdtgrp, mevt);
+			if (ret)
+				return ret;
+		}
+	} else {
+		ret = rdtgroup_alloc_assign_cntr(r, d, rdtgrp, mevt);
+	}
+
+	return ret;
+}
+
+/*
+ * rdtgroup_assign_cntrs() - Assign counters to MBM events. Called when
+ *			     a new group is created.
+ *
+ * Each group can accommodate two counters per domain: one for the total
+ * event and one for the local event. Assignments may fail due to the limited
+ * number of counters. However, it is not necessary to fail the group creation
+ * and thus no failure is returned. Users have the option to modify the
+ * counter assignments after the group has been created.
+ */
+void rdtgroup_assign_cntrs(struct rdtgroup *rdtgrp)
+{
+	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
+
+	if (!r->mon_capable || !resctrl_arch_mbm_cntr_assign_enabled(r))
+		return;
+
+	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID))
+		rdtgroup_assign_cntr_event(NULL, rdtgrp,
+					   &mon_event_all[QOS_L3_MBM_TOTAL_EVENT_ID]);
+
+	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID))
+		rdtgroup_assign_cntr_event(NULL, rdtgrp,
+					   &mon_event_all[QOS_L3_MBM_LOCAL_EVENT_ID]);
+}
+
 /**
  * resctrl_mon_resource_init() - Initialise global monitoring structures.
  *

From 3c60dafc23f0354b78033e3f8607c3e94a6bb99d Mon Sep 17 00:00:00 2001
From: Babu Moger <babu.moger@amd.com>
Date: Fri, 5 Sep 2025 16:34:17 -0500
Subject: [PATCH 105/236] fs/resctrl: Add the functionality to unassign MBM
 events

commit aab2c5088cdb26e80d51ffbe72d24ab23fa1533e upstream.

The "mbm_event" counter assignment mode offers "num_mbm_cntrs" number of
counters that can be assigned to RMID, event pairs and monitor bandwidth usage
as long as it is assigned. If all the counters are in use, the kernel logs the
error message "Failed to allocate counter for <event> in domain <id>" in
/sys/fs/resctrl/info/last_cmd_status when a new assignment is requested.

To make space for a new assignment, users must unassign an already assigned
counter and retry the assignment again.

Add the functionality to unassign and free the counters in the domain.  Also,
add the helper rdtgroup_unassign_cntrs() to unassign counters in the group.

Signed-off-by: Babu Moger <babu.moger@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/cover.1757108044.git.babu.moger@amd.com

 Conflicts:
	fs/resctrl/monitor.c
[jz: resolve context conflicts]
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 fs/resctrl/internal.h |  2 ++
 fs/resctrl/monitor.c  | 66 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 68 insertions(+)

diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index be1858eaaa7b2..2a227f22e0d5c 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -389,6 +389,8 @@ int resctrl_find_cleanest_closid(void);
 
 void rdtgroup_assign_cntrs(struct rdtgroup *rdtgrp);
 
+void rdtgroup_unassign_cntrs(struct rdtgroup *rdtgrp);
+
 #ifdef CONFIG_RESCTRL_FS_PSEUDO_LOCK
 int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp);
 
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index 18b57c5473e1b..a906e3be12b0c 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -405,6 +405,14 @@ static int mbm_cntr_alloc(struct rdt_resource *r, struct rdt_mon_domain *d,
 	return -ENOSPC;
 }
 
+/*
+ * mbm_cntr_free() - Clear the counter ID configuration details in the domain @d.
+ */
+static void mbm_cntr_free(struct rdt_mon_domain *d, int cntr_id)
+{
+	memset(&d->cntr_cfg[cntr_id], 0, sizeof(*d->cntr_cfg));
+}
+
 static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 {
 	int cpu = smp_processor_id();
@@ -1043,6 +1051,64 @@ void rdtgroup_assign_cntrs(struct rdtgroup *rdtgrp)
 					   &mon_event_all[QOS_L3_MBM_LOCAL_EVENT_ID]);
 }
 
+/*
+ * rdtgroup_free_unassign_cntr() - Unassign and reset the counter ID configuration
+ * for the event pointed to by @mevt within the domain @d and resctrl group @rdtgrp.
+ */
+static void rdtgroup_free_unassign_cntr(struct rdt_resource *r, struct rdt_mon_domain *d,
+					struct rdtgroup *rdtgrp, struct mon_evt *mevt)
+{
+	int cntr_id;
+
+	cntr_id = mbm_cntr_get(r, d, rdtgrp, mevt->evtid);
+
+	/* If there is no cntr_id assigned, nothing to do */
+	if (cntr_id < 0)
+		return;
+
+	rdtgroup_assign_cntr(r, d, mevt->evtid, rdtgrp->mon.rmid, rdtgrp->closid, cntr_id, false);
+
+	mbm_cntr_free(d, cntr_id);
+}
+
+/*
+ * rdtgroup_unassign_cntr_event() - Unassign a hardware counter associated with
+ * the event structure @mevt from the domain @d and the group @rdtgrp. Unassign
+ * the counters from all the domains if @d is NULL else unassign from @d.
+ */
+static void rdtgroup_unassign_cntr_event(struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
+					 struct mon_evt *mevt)
+{
+	struct rdt_resource *r = resctrl_arch_get_resource(mevt->rid);
+
+	if (!d) {
+		list_for_each_entry(d, &r->mon_domains, hdr.list)
+			rdtgroup_free_unassign_cntr(r, d, rdtgrp, mevt);
+	} else {
+		rdtgroup_free_unassign_cntr(r, d, rdtgrp, mevt);
+	}
+}
+
+/*
+ * rdtgroup_unassign_cntrs() - Unassign the counters associated with MBM events.
+ *			       Called when a group is deleted.
+ */
+void rdtgroup_unassign_cntrs(struct rdtgroup *rdtgrp)
+{
+	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
+
+	if (!r->mon_capable || !resctrl_arch_mbm_cntr_assign_enabled(r))
+		return;
+
+	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID))
+		rdtgroup_unassign_cntr_event(NULL, rdtgrp,
+					     &mon_event_all[QOS_L3_MBM_TOTAL_EVENT_ID]);
+
+	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID))
+		rdtgroup_unassign_cntr_event(NULL, rdtgrp,
+					     &mon_event_all[QOS_L3_MBM_LOCAL_EVENT_ID]);
+}
+
 /**
  * resctrl_mon_resource_init() - Initialise global monitoring structures.
  *

From e7078c9403f6e07b566cb185ebfe1200618aa65b Mon Sep 17 00:00:00 2001
From: Babu Moger <babu.moger@amd.com>
Date: Fri, 5 Sep 2025 16:34:18 -0500
Subject: [PATCH 106/236] fs/resctrl: Pass struct rdtgroup instead of
 individual members

commit bc53eea6c2a1dea152a0073a2f2814b697ad197e upstream.

Reading monitoring data for a monitoring group requires both the RMID and
CLOSID. The RMID and CLOSID are members of struct rdtgroup but passed
separately to several functions involved in retrieving event data.

When "mbm_event" counter assignment mode is enabled, a counter ID is required
to read event data. The counter ID is obtained through mbm_cntr_get(), which
expects a struct rdtgroup pointer.

Provide a pointer to the struct rdtgroup as parameter to functions involved in
retrieving event data to simplify access to RMID, CLOSID, and counter ID.

Suggested-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Babu Moger <babu.moger@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/cover.1757108044.git.babu.moger@amd.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 fs/resctrl/monitor.c | 33 ++++++++++++++++++---------------
 1 file changed, 18 insertions(+), 15 deletions(-)

diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index a906e3be12b0c..21fd1d5a6b665 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -413,9 +413,11 @@ static void mbm_cntr_free(struct rdt_mon_domain *d, int cntr_id)
 	memset(&d->cntr_cfg[cntr_id], 0, sizeof(*d->cntr_cfg));
 }
 
-static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
+static int __mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
 {
 	int cpu = smp_processor_id();
+	u32 closid = rdtgrp->closid;
+	u32 rmid = rdtgrp->mon.rmid;
 	struct rdt_mon_domain *d;
 	struct mbm_state *m;
 	int err, ret;
@@ -475,8 +477,8 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 /*
  * mbm_bw_count() - Update bw count from values previously read by
  *		    __mon_event_count().
- * @closid:	The closid used to identify the cached mbm_state.
- * @rmid:	The rmid used to identify the cached mbm_state.
+ * @rdtgrp:	resctrl group associated with the CLOSID and RMID to identify
+ *		the cached mbm_state.
  * @rr:		The struct rmid_read populated by __mon_event_count().
  *
  * Supporting function to calculate the memory bandwidth
@@ -484,9 +486,11 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
  * __mon_event_count() is compared with the chunks value from the previous
  * invocation. This must be called once per second to maintain values in MBps.
  */
-static void mbm_bw_count(u32 closid, u32 rmid, struct rmid_read *rr)
+static void mbm_bw_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
 {
 	u64 cur_bw, bytes, cur_bytes;
+	u32 closid = rdtgrp->closid;
+	u32 rmid = rdtgrp->mon.rmid;
 	struct mbm_state *m;
 
 	m = get_mbm_state(rr->d, closid, rmid, rr->evtid);
@@ -515,7 +519,7 @@ void mon_event_count(void *info)
 
 	rdtgrp = rr->rgrp;
 
-	ret = __mon_event_count(rdtgrp->closid, rdtgrp->mon.rmid, rr);
+	ret = __mon_event_count(rdtgrp, rr);
 
 	/*
 	 * For Ctrl groups read data from child monitor groups and
@@ -526,8 +530,7 @@ void mon_event_count(void *info)
 
 	if (rdtgrp->type == RDTCTRL_GROUP) {
 		list_for_each_entry(entry, head, mon.crdtgrp_list) {
-			if (__mon_event_count(entry->closid, entry->mon.rmid,
-					      rr) == 0)
+			if (__mon_event_count(entry, rr) == 0)
 				ret = 0;
 		}
 	}
@@ -658,7 +661,7 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm)
 }
 
 static void mbm_update_one_event(struct rdt_resource *r, struct rdt_mon_domain *d,
-				 u32 closid, u32 rmid, enum resctrl_event_id evtid)
+				 struct rdtgroup *rdtgrp, enum resctrl_event_id evtid)
 {
 	struct rmid_read rr = {0};
 
@@ -672,30 +675,30 @@ static void mbm_update_one_event(struct rdt_resource *r, struct rdt_mon_domain *
 		return;
 	}
 
-	__mon_event_count(closid, rmid, &rr);
+	__mon_event_count(rdtgrp, &rr);
 
 	/*
 	 * If the software controller is enabled, compute the
 	 * bandwidth for this event id.
 	 */
 	if (is_mba_sc(NULL))
-		mbm_bw_count(closid, rmid, &rr);
+		mbm_bw_count(rdtgrp, &rr);
 
 	resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
 }
 
 static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d,
-		       u32 closid, u32 rmid)
+		       struct rdtgroup *rdtgrp)
 {
 	/*
 	 * This is protected from concurrent reads from user as both
 	 * the user and overflow handler hold the global mutex.
 	 */
 	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID))
-		mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_TOTAL_EVENT_ID);
+		mbm_update_one_event(r, d, rdtgrp, QOS_L3_MBM_TOTAL_EVENT_ID);
 
 	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID))
-		mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_LOCAL_EVENT_ID);
+		mbm_update_one_event(r, d, rdtgrp, QOS_L3_MBM_LOCAL_EVENT_ID);
 }
 
 /*
@@ -768,11 +771,11 @@ void mbm_handle_overflow(struct work_struct *work)
 	d = container_of(work, struct rdt_mon_domain, mbm_over.work);
 
 	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
-		mbm_update(r, d, prgrp->closid, prgrp->mon.rmid);
+		mbm_update(r, d, prgrp);
 
 		head = &prgrp->mon.crdtgrp_list;
 		list_for_each_entry(crgrp, head, mon.crdtgrp_list)
-			mbm_update(r, d, crgrp->closid, crgrp->mon.rmid);
+			mbm_update(r, d, crgrp);
 
 		if (is_mba_sc(NULL))
 			update_mba_bw(prgrp, d);

From 950941051e623be60c4ce6bda17f46857f093ee9 Mon Sep 17 00:00:00 2001
From: Babu Moger <babu.moger@amd.com>
Date: Fri, 5 Sep 2025 16:34:19 -0500
Subject: [PATCH 107/236] fs/resctrl: Introduce counter ID read, reset calls in
 mbm_event mode

commit 862314fd1f93d96eddb0559a807c66cb1f6ee520 upstream.

When supported, "mbm_event" counter assignment mode allows users to assign
a hardware counter to an RMID, event pair and monitor the bandwidth usage as
long as it is assigned. The hardware continues to track the assigned counter
until it is explicitly unassigned by the user.

Introduce the architecture calls resctrl_arch_cntr_read() and
resctrl_arch_reset_cntr() to read and reset event counters when "mbm_event"
mode is supported. Function names match existing resctrl_arch_rmid_read() and
resctrl_arch_reset_rmid().

Suggested-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Babu Moger <babu.moger@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/cover.1757108044.git.babu.moger@amd.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 include/linux/resctrl.h | 38 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 50e38445183a8..04152654827d4 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -613,6 +613,44 @@ void resctrl_arch_config_cntr(struct rdt_resource *r, struct rdt_mon_domain *d,
 			      enum resctrl_event_id evtid, u32 rmid, u32 closid,
 			      u32 cntr_id, bool assign);
 
+/**
+ * resctrl_arch_cntr_read() - Read the event data corresponding to the counter ID
+ *			      assigned to the RMID, event pair for this resource
+ *			      and domain.
+ * @r:		Resource that the counter should be read from.
+ * @d:		Domain that the counter should be read from.
+ * @closid:	CLOSID that matches the RMID.
+ * @rmid:	The RMID to which @cntr_id is assigned.
+ * @cntr_id:	The counter to read.
+ * @eventid:	The MBM event to which @cntr_id is assigned.
+ * @val:	Result of the counter read in bytes.
+ *
+ * Called on a CPU that belongs to domain @d when "mbm_event" mode is enabled.
+ * Called from a non-migrateable process context via smp_call_on_cpu() unless all
+ * CPUs are nohz_full, in which case it is called via IPI (smp_call_function_any()).
+ *
+ * Return:
+ * 0 on success, or -EIO, -EINVAL etc on error.
+ */
+int resctrl_arch_cntr_read(struct rdt_resource *r, struct rdt_mon_domain *d,
+			   u32 closid, u32 rmid, int cntr_id,
+			   enum resctrl_event_id eventid, u64 *val);
+
+/**
+ * resctrl_arch_reset_cntr() - Reset any private state associated with counter ID.
+ * @r:		The domain's resource.
+ * @d:		The counter ID's domain.
+ * @closid:	CLOSID that matches the RMID.
+ * @rmid:	The RMID to which @cntr_id is assigned.
+ * @cntr_id:	The counter to reset.
+ * @eventid:	The MBM event to which @cntr_id is assigned.
+ *
+ * This can be called from any CPU.
+ */
+void resctrl_arch_reset_cntr(struct rdt_resource *r, struct rdt_mon_domain *d,
+			     u32 closid, u32 rmid, int cntr_id,
+			     enum resctrl_event_id eventid);
+
 extern unsigned int resctrl_rmid_realloc_threshold;
 extern unsigned int resctrl_rmid_realloc_limit;
 

From d78caf8c4dd246f29425a36472e2526f36f7bdf6 Mon Sep 17 00:00:00 2001
From: Babu Moger <babu.moger@amd.com>
Date: Fri, 5 Sep 2025 16:34:20 -0500
Subject: [PATCH 108/236] x86/resctrl: Refactor resctrl_arch_rmid_read()

commit 7c9ac605e202c4668e441fc8146a993577131ca1 upstream.

resctrl_arch_rmid_read() adjusts the value obtained from MSR_IA32_QM_CTR to
account for the overflow for MBM events and apply counter scaling for all the
events. This logic is common to both reading an RMID and reading a hardware
counter directly.

Refactor the hardware value adjustment logic into get_corrected_val() to
prepare for support of reading a hardware counter.

Signed-off-by: Babu Moger <babu.moger@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/cover.1757108044.git.babu.moger@amd.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/monitor.c | 38 ++++++++++++++++-----------
 1 file changed, 23 insertions(+), 15 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 4a48d23f5ac43..938d2d56a4615 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -216,24 +216,13 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
 	return chunks >> shift;
 }
 
-int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
-			   u32 unused, u32 rmid, enum resctrl_event_id eventid,
-			   u64 *val, void *ignored)
+static u64 get_corrected_val(struct rdt_resource *r, struct rdt_mon_domain *d,
+			     u32 rmid, enum resctrl_event_id eventid, u64 msr_val)
 {
 	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
-	int cpu = cpumask_any(&d->hdr.cpu_mask);
 	struct arch_mbm_state *am;
-	u64 msr_val, chunks;
-	u32 prmid;
-	int ret;
-
-	resctrl_arch_rmid_read_context_check();
-
-	prmid = logical_rmid_to_physical_rmid(cpu, rmid);
-	ret = __rmid_read_phys(prmid, eventid, &msr_val);
-	if (ret)
-		return ret;
+	u64 chunks;
 
 	am = get_arch_mbm_state(hw_dom, rmid, eventid);
 	if (am) {
@@ -245,7 +234,26 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
 		chunks = msr_val;
 	}
 
-	*val = chunks * hw_res->mon_scale;
+	return chunks * hw_res->mon_scale;
+}
+
+int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
+			   u32 unused, u32 rmid, enum resctrl_event_id eventid,
+			   u64 *val, void *ignored)
+{
+	int cpu = cpumask_any(&d->hdr.cpu_mask);
+	u64 msr_val;
+	u32 prmid;
+	int ret;
+
+	resctrl_arch_rmid_read_context_check();
+
+	prmid = logical_rmid_to_physical_rmid(cpu, rmid);
+	ret = __rmid_read_phys(prmid, eventid, &msr_val);
+	if (ret)
+		return ret;
+
+	*val = get_corrected_val(r, d, rmid, eventid, msr_val);
 
 	return 0;
 }

From e628e93ba20377690fdb343732ab43a8521f630e Mon Sep 17 00:00:00 2001
From: Babu Moger <babu.moger@amd.com>
Date: Fri, 5 Sep 2025 16:34:21 -0500
Subject: [PATCH 109/236] x86/resctrl: Implement resctrl_arch_reset_cntr() and
 resctrl_arch_cntr_read()

commit 2a65b72c1603a74f35228acbb8de2ecff9c13efe upstream.

System software reads resctrl event data for a particular resource by writing
the RMID and Event Identifier (EvtID) to the QM_EVTSEL register and then
reading the event data from the QM_CTR register.

In ABMC mode, the event data of a specific counter ID is read by setting the
following fields: QM_EVTSEL.ExtendedEvtID = 1, QM_EVTSEL.EvtID = L3CacheABMC
(=1) and setting QM_EVTSEL.RMID to the desired counter ID.  Reading the QM_CTR
then returns the contents of the specified counter ID.  RMID_VAL_ERROR bit is
set if the counter configuration is invalid, or if an invalid counter ID is
set in the QM_EVTSEL.RMID field.  RMID_VAL_UNAVAIL bit is set if the counter
data is unavailable.

Introduce resctrl_arch_reset_cntr() and resctrl_arch_cntr_read() to reset and
read event data for a specific counter.

Signed-off-by: Babu Moger <babu.moger@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/cover.1757108044.git.babu.moger@amd.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/internal.h |  6 +++
 arch/x86/kernel/cpu/resctrl/monitor.c  | 69 ++++++++++++++++++++++++++
 2 files changed, 75 insertions(+)

diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 63166be49ea67..93eb9ccc7c536 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -43,6 +43,12 @@ struct arch_mbm_state {
 /* Setting bit 0 in L3_QOS_EXT_CFG enables the ABMC feature. */
 #define ABMC_ENABLE_BIT			0
 
+/*
+ * Qos Event Identifiers.
+ */
+#define ABMC_EXTENDED_EVT_ID		BIT(31)
+#define ABMC_EVT_ID			BIT(0)
+
 /**
  * struct rdt_hw_ctrl_domain - Arch private attributes of a set of CPUs that share
  *			       a resource for a control function
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 938d2d56a4615..9a9e68f819bf6 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -258,6 +258,75 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
 	return 0;
 }
 
+static int __cntr_id_read(u32 cntr_id, u64 *val)
+{
+	u64 msr_val;
+
+	/*
+	 * QM_EVTSEL Register definition:
+	 * =======================================================
+	 * Bits    Mnemonic        Description
+	 * =======================================================
+	 * 63:44   --              Reserved
+	 * 43:32   RMID            RMID or counter ID in ABMC mode
+	 *                         when reading an MBM event
+	 * 31      ExtendedEvtID   Extended Event Identifier
+	 * 30:8    --              Reserved
+	 * 7:0     EvtID           Event Identifier
+	 * =======================================================
+	 * The contents of a specific counter can be read by setting the
+	 * following fields in QM_EVTSEL.ExtendedEvtID(=1) and
+	 * QM_EVTSEL.EvtID = L3CacheABMC (=1) and setting QM_EVTSEL.RMID
+	 * to the desired counter ID. Reading the QM_CTR then returns the
+	 * contents of the specified counter. The RMID_VAL_ERROR bit is set
+	 * if the counter configuration is invalid, or if an invalid counter
+	 * ID is set in the QM_EVTSEL.RMID field.  The RMID_VAL_UNAVAIL bit
+	 * is set if the counter data is unavailable.
+	 */
+	wrmsr(MSR_IA32_QM_EVTSEL, ABMC_EXTENDED_EVT_ID | ABMC_EVT_ID, cntr_id);
+	rdmsrl(MSR_IA32_QM_CTR, msr_val);
+
+	if (msr_val & RMID_VAL_ERROR)
+		return -EIO;
+	if (msr_val & RMID_VAL_UNAVAIL)
+		return -EINVAL;
+
+	*val = msr_val;
+	return 0;
+}
+
+void resctrl_arch_reset_cntr(struct rdt_resource *r, struct rdt_mon_domain *d,
+			     u32 unused, u32 rmid, int cntr_id,
+			     enum resctrl_event_id eventid)
+{
+	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
+	struct arch_mbm_state *am;
+
+	am = get_arch_mbm_state(hw_dom, rmid, eventid);
+	if (am) {
+		memset(am, 0, sizeof(*am));
+
+		/* Record any initial, non-zero count value. */
+		__cntr_id_read(cntr_id, &am->prev_msr);
+	}
+}
+
+int resctrl_arch_cntr_read(struct rdt_resource *r, struct rdt_mon_domain *d,
+			   u32 unused, u32 rmid, int cntr_id,
+			   enum resctrl_event_id eventid, u64 *val)
+{
+	u64 msr_val;
+	int ret;
+
+	ret = __cntr_id_read(cntr_id, &msr_val);
+	if (ret)
+		return ret;
+
+	*val = get_corrected_val(r, d, rmid, eventid, msr_val);
+
+	return 0;
+}
+
 /*
  * The power-on reset value of MSR_RMID_SNC_CONFIG is 0x1
  * which indicates that RMIDs are configured in legacy mode.

From abfc577daef4a8302dde64325f25b671b04834c6 Mon Sep 17 00:00:00 2001
From: Babu Moger <babu.moger@amd.com>
Date: Fri, 5 Sep 2025 16:34:22 -0500
Subject: [PATCH 110/236] fs/resctrl: Support counter read/reset with mbm_event
 assignment mode

commit 159f36cd4de7718779fd0b232de5137b4ffd2d1e upstream.

When "mbm_event" counter assignment mode is enabled, the architecture requires
a counter ID to read the event data.

Introduce an is_mbm_cntr field in struct rmid_read to indicate whether counter
assignment mode is in use.

Update the logic to call resctrl_arch_cntr_read() and resctrl_arch_reset_cntr()
when the assignment mode is active. Report 'Unassigned' in case the user attempts
to read an event without assigning a hardware counter.

Suggested-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Babu Moger <babu.moger@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/cover.1757108044.git.babu.moger@amd.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 Documentation/filesystems/resctrl.rst |  6 ++++
 fs/resctrl/ctrlmondata.c              | 22 ++++++++++---
 fs/resctrl/internal.h                 |  3 ++
 fs/resctrl/monitor.c                  | 47 ++++++++++++++++++++-------
 4 files changed, 62 insertions(+), 16 deletions(-)

diff --git a/Documentation/filesystems/resctrl.rst b/Documentation/filesystems/resctrl.rst
index 4201da8dad5f1..db7ab26e05f8b 100644
--- a/Documentation/filesystems/resctrl.rst
+++ b/Documentation/filesystems/resctrl.rst
@@ -380,6 +380,12 @@ When monitoring is enabled all MON groups will also contain:
 	for the L3 cache they occupy). These are named "mon_sub_L3_YY"
 	where "YY" is the node number.
 
+	When the 'mbm_event' counter assignment mode is enabled, reading
+	an MBM event of a MON group returns 'Unassigned' if no hardware
+	counter is assigned to it. For CTRL_MON groups, 'Unassigned' is
+	returned if the MBM event does not have an assigned counter in the
+	CTRL_MON group nor in any of its associated MON groups.
+
 "mon_hw_id":
 	Available only with debug option. The identifier used by hardware
 	for the monitor group. On x86 this is the RMID.
diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c
index 42b281b3852ff..0d0ef54fc4de1 100644
--- a/fs/resctrl/ctrlmondata.c
+++ b/fs/resctrl/ctrlmondata.c
@@ -563,10 +563,15 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 	rr->r = r;
 	rr->d = d;
 	rr->first = first;
-	rr->arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, evtid);
-	if (IS_ERR(rr->arch_mon_ctx)) {
-		rr->err = -EINVAL;
-		return;
+	if (resctrl_arch_mbm_cntr_assign_enabled(r) &&
+	    resctrl_is_mbm_event(evtid)) {
+		rr->is_mbm_cntr = true;
+	} else {
+		rr->arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, evtid);
+		if (IS_ERR(rr->arch_mon_ctx)) {
+			rr->err = -EINVAL;
+			return;
+		}
 	}
 
 	cpu = cpumask_any_housekeeping(cpumask, RESCTRL_PICK_ANY_CPU);
@@ -582,7 +587,8 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 	else
 		smp_call_on_cpu(cpu, smp_mon_event_count, rr, false);
 
-	resctrl_arch_mon_ctx_free(r, evtid, rr->arch_mon_ctx);
+	if (rr->arch_mon_ctx)
+		resctrl_arch_mon_ctx_free(r, evtid, rr->arch_mon_ctx);
 }
 
 int rdtgroup_mondata_show(struct seq_file *m, void *arg)
@@ -653,10 +659,16 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 
 checkresult:
 
+	/*
+	 * -ENOENT is a special case, set only when "mbm_event" counter assignment
+	 * mode is enabled and no counter has been assigned.
+	 */
 	if (rr.err == -EIO)
 		seq_puts(m, "Error\n");
 	else if (rr.err == -EINVAL)
 		seq_puts(m, "Unavailable\n");
+	else if (rr.err == -ENOENT)
+		seq_puts(m, "Unassigned\n");
 	else
 		seq_printf(m, "%llu\n", rr.val);
 
diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index 2a227f22e0d5c..8a654bf414326 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -111,6 +111,8 @@ struct mon_data {
  * @evtid: Which monitor event to read.
  * @first: Initialize MBM counter when true.
  * @ci:    Cacheinfo for L3. Only set when @d is NULL. Used when summing domains.
+ * @is_mbm_cntr: true if "mbm_event" counter assignment mode is enabled and it
+ *	   is an MBM event.
  * @err:   Error encountered when reading counter.
  * @val:   Returned value of event counter. If @rgrp is a parent resource group,
  *	   @val includes the sum of event counts from its child resource groups.
@@ -125,6 +127,7 @@ struct rmid_read {
 	enum resctrl_event_id	evtid;
 	bool			first;
 	struct cacheinfo	*ci;
+	bool			is_mbm_cntr;
 	int			err;
 	u64			val;
 	void			*arch_mon_ctx;
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index 21fd1d5a6b665..f274d66466ddc 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -419,12 +419,24 @@ static int __mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
 	u32 closid = rdtgrp->closid;
 	u32 rmid = rdtgrp->mon.rmid;
 	struct rdt_mon_domain *d;
+	int cntr_id = -ENOENT;
 	struct mbm_state *m;
 	int err, ret;
 	u64 tval = 0;
 
+	if (rr->is_mbm_cntr) {
+		cntr_id = mbm_cntr_get(rr->r, rr->d, rdtgrp, rr->evtid);
+		if (cntr_id < 0) {
+			rr->err = -ENOENT;
+			return -EINVAL;
+		}
+	}
+
 	if (rr->first) {
-		resctrl_arch_reset_rmid(rr->r, rr->d, closid, rmid, rr->evtid);
+		if (rr->is_mbm_cntr)
+			resctrl_arch_reset_cntr(rr->r, rr->d, closid, rmid, cntr_id, rr->evtid);
+		else
+			resctrl_arch_reset_rmid(rr->r, rr->d, closid, rmid, rr->evtid);
 		m = get_mbm_state(rr->d, closid, rmid, rr->evtid);
 		if (m)
 			memset(m, 0, sizeof(struct mbm_state));
@@ -435,8 +447,12 @@ static int __mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
 		/* Reading a single domain, must be on a CPU in that domain. */
 		if (!cpumask_test_cpu(cpu, &rr->d->hdr.cpu_mask))
 			return -EINVAL;
-		rr->err = resctrl_arch_rmid_read(rr->r, rr->d, closid, rmid,
-						 rr->evtid, &tval, rr->arch_mon_ctx);
+		if (rr->is_mbm_cntr)
+			rr->err = resctrl_arch_cntr_read(rr->r, rr->d, closid, rmid, cntr_id,
+							 rr->evtid, &tval);
+		else
+			rr->err = resctrl_arch_rmid_read(rr->r, rr->d, closid, rmid,
+							 rr->evtid, &tval, rr->arch_mon_ctx);
 		if (rr->err)
 			return rr->err;
 
@@ -460,8 +476,12 @@ static int __mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
 	list_for_each_entry(d, &rr->r->mon_domains, hdr.list) {
 		if (d->ci_id != rr->ci->id)
 			continue;
-		err = resctrl_arch_rmid_read(rr->r, d, closid, rmid,
-					     rr->evtid, &tval, rr->arch_mon_ctx);
+		if (rr->is_mbm_cntr)
+			err = resctrl_arch_cntr_read(rr->r, d, closid, rmid, cntr_id,
+						     rr->evtid, &tval);
+		else
+			err = resctrl_arch_rmid_read(rr->r, d, closid, rmid,
+						     rr->evtid, &tval, rr->arch_mon_ctx);
 		if (!err) {
 			rr->val += tval;
 			ret = 0;
@@ -668,11 +688,15 @@ static void mbm_update_one_event(struct rdt_resource *r, struct rdt_mon_domain *
 	rr.r = r;
 	rr.d = d;
 	rr.evtid = evtid;
-	rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
-	if (IS_ERR(rr.arch_mon_ctx)) {
-		pr_warn_ratelimited("Failed to allocate monitor context: %ld",
-				    PTR_ERR(rr.arch_mon_ctx));
-		return;
+	if (resctrl_arch_mbm_cntr_assign_enabled(r)) {
+		rr.is_mbm_cntr = true;
+	} else {
+		rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
+		if (IS_ERR(rr.arch_mon_ctx)) {
+			pr_warn_ratelimited("Failed to allocate monitor context: %ld",
+					    PTR_ERR(rr.arch_mon_ctx));
+			return;
+		}
 	}
 
 	__mon_event_count(rdtgrp, &rr);
@@ -684,7 +708,8 @@ static void mbm_update_one_event(struct rdt_resource *r, struct rdt_mon_domain *
 	if (is_mba_sc(NULL))
 		mbm_bw_count(rdtgrp, &rr);
 
-	resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
+	if (rr.arch_mon_ctx)
+		resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
 }
 
 static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d,

From 3666d57babb52fe333fc9a521df1b47865c7e0a5 Mon Sep 17 00:00:00 2001
From: Babu Moger <babu.moger@amd.com>
Date: Fri, 5 Sep 2025 16:34:31 -0500
Subject: [PATCH 111/236] x86/resctrl: Configure mbm_event mode if supported

commit 0f1576e43adc62756879a240e66e89ce386b6eb9 upstream.

Configure mbm_event mode on AMD platforms. On AMD platforms, it is
recommended to use the mbm_event mode, if supported, to prevent the
hardware from resetting counters between reads. This can result in
misleading values or display "Unavailable" if no counter is assigned
to the event.

Enable mbm_event mode, known as ABMC (Assignable Bandwidth Monitoring
Counters) on AMD, by default if the system supports it.

Update ABMC across all logical processors within the resctrl domain to
ensure proper functionality.

Signed-off-by: Babu Moger <babu.moger@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/cover.1757108044.git.babu.moger@amd.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c     | 7 +++++++
 arch/x86/kernel/cpu/resctrl/internal.h | 1 +
 arch/x86/kernel/cpu/resctrl/monitor.c  | 8 ++++++++
 3 files changed, 16 insertions(+)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index eeb271dbb54c0..123a8abadc178 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -519,6 +519,9 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
 		d = container_of(hdr, struct rdt_mon_domain, hdr);
 
 		cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
+		/* Update the mbm_assign_mode state for the CPU if supported */
+		if (r->mon.mbm_cntr_assignable)
+			resctrl_arch_mbm_cntr_assign_set_one(r);
 		return;
 	}
 
@@ -538,6 +541,10 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
 	d->ci_id = ci->id;
 	cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
 
+	/* Update the mbm_assign_mode state for the CPU if supported */
+	if (r->mon.mbm_cntr_assignable)
+		resctrl_arch_mbm_cntr_assign_set_one(r);
+
 	arch_mon_domain_online(r, d);
 
 	if (arch_domain_mbm_alloc(r->mon.num_rmid, hw_dom)) {
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 93eb9ccc7c536..6da9bd1a188b9 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -218,5 +218,6 @@ bool rdt_cpu_has(int flag);
 void __init intel_rdt_mbm_apply_quirk(void);
 
 void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
+void resctrl_arch_mbm_cntr_assign_set_one(struct rdt_resource *r);
 
 #endif /* _ASM_X86_RESCTRL_INTERNAL_H */
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 9a9e68f819bf6..f1f0cd9290ac2 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -455,6 +455,7 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 		r->mon.mbm_cntr_assignable = true;
 		cpuid_count(0x80000020, 5, &eax, &ebx, &ecx, &edx);
 		r->mon.num_mbm_cntrs = (ebx & GENMASK(15, 0)) + 1;
+		hw_res->mbm_cntr_assign_enabled = true;
 	}
 
 	r->mon_capable = true;
@@ -556,3 +557,10 @@ void resctrl_arch_config_cntr(struct rdt_resource *r, struct rdt_mon_domain *d,
 	if (am)
 		memset(am, 0, sizeof(*am));
 }
+
+void resctrl_arch_mbm_cntr_assign_set_one(struct rdt_resource *r)
+{
+	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
+
+	resctrl_abmc_set_one_amd(&hw_res->mbm_cntr_assign_enabled);
+}

From 13efd351433a6e9e5e71f401fa9de91aa92a1f12 Mon Sep 17 00:00:00 2001
From: Babu Moger <babu.moger@amd.com>
Date: Fri, 10 Oct 2025 12:08:35 -0500
Subject: [PATCH 112/236] x86/resctrl: Fix miscount of bandwidth event when
 reactivating previously unavailable RMID

commit 15292f1b4c55a3a7c940dbcb6cb8793871ed3d92 upstream.

Users can create as many monitoring groups as the number of RMIDs supported
by the hardware. However, on AMD systems, only a limited number of RMIDs
are guaranteed to be actively tracked by the hardware. RMIDs that exceed
this limit are placed in an "Unavailable" state.

When a bandwidth counter is read for such an RMID, the hardware sets
MSR_IA32_QM_CTR.Unavailable (bit 62). When such an RMID starts being tracked
again the hardware counter is reset to zero. MSR_IA32_QM_CTR.Unavailable
remains set on first read after tracking re-starts and is clear on all
subsequent reads as long as the RMID is tracked.

resctrl miscounts the bandwidth events after an RMID transitions from the
"Unavailable" state back to being tracked. This happens because when the
hardware starts counting again after resetting the counter to zero, resctrl
in turn compares the new count against the counter value stored from the
previous time the RMID was tracked.

This results in resctrl computing an event value that is either undercounting
(when new counter is more than stored counter) or a mistaken overflow (when
new counter is less than stored counter).

Reset the stored value (arch_mbm_state::prev_msr) of MSR_IA32_QM_CTR to
zero whenever the RMID is in the "Unavailable" state to ensure accurate
counting after the RMID resets to zero when it starts to be tracked again.

Example scenario that results in mistaken overflow
==================================================
1. The resctrl filesystem is mounted, and a task is assigned to a
   monitoring group.

   $mount -t resctrl resctrl /sys/fs/resctrl
   $mkdir /sys/fs/resctrl/mon_groups/test1/
   $echo 1234 > /sys/fs/resctrl/mon_groups/test1/tasks

   $cat /sys/fs/resctrl/mon_groups/test1/mon_data/mon_L3_*/mbm_total_bytes
   21323            <- Total bytes on domain 0
   "Unavailable"    <- Total bytes on domain 1

   Task is running on domain 0. Counter on domain 1 is "Unavailable".

2. The task runs on domain 0 for a while and then moves to domain 1. The
   counter starts incrementing on domain 1.

   $cat /sys/fs/resctrl/mon_groups/test1/mon_data/mon_L3_*/mbm_total_bytes
   7345357          <- Total bytes on domain 0
   4545             <- Total bytes on domain 1

3. At some point, the RMID in domain 0 transitions to the "Unavailable"
   state because the task is no longer executing in that domain.

   $cat /sys/fs/resctrl/mon_groups/test1/mon_data/mon_L3_*/mbm_total_bytes
   "Unavailable"    <- Total bytes on domain 0
   434341           <- Total bytes on domain 1

4.  Since the task continues to migrate between domains, it may eventually
    return to domain 0.

    $cat /sys/fs/resctrl/mon_groups/test1/mon_data/mon_L3_*/mbm_total_bytes
    17592178699059  <- Overflow on domain 0
    3232332         <- Total bytes on domain 1

In this case, the RMID on domain 0 transitions from "Unavailable" state to
active state. The hardware sets MSR_IA32_QM_CTR.Unavailable (bit 62) when
the counter is read and begins tracking the RMID counting from 0.

Subsequent reads succeed but return a value smaller than the previously
saved MSR value (7345357). Consequently, the resctrl's overflow logic is
triggered, it compares the previous value (7345357) with the new, smaller
value and incorrectly interprets this as a counter overflow, adding a large
delta.

In reality, this is a false positive: the counter did not overflow but was
simply reset when the RMID transitioned from "Unavailable" back to active
state.

Here is the text from APM [1] available from [2].

"In PQOS Version 2.0 or higher, the MBM hardware will set the U bit on the
first QM_CTR read when it begins tracking an RMID that it was not
previously tracking. The U bit will be zero for all subsequent reads from
that RMID while it is still tracked by the hardware. Therefore, a QM_CTR
read with the U bit set when that RMID is in use by a processor can be
considered 0 when calculating the difference with a subsequent read."

[1] AMD64 Architecture Programmer's Manual Volume 2: System Programming
    Publication # 24593 Revision 3.41 section 19.3.3 Monitoring L3 Memory
    Bandwidth (MBM).

  [ bp: Split commit message into smaller paragraph chunks for better
    consumption. ]

Fixes: 4d05bf71f157d ("x86/resctrl: Introduce AMD QOS feature")
Signed-off-by: Babu Moger <babu.moger@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Reinette Chatre <reinette.chatre@intel.com>
Cc: stable@vger.kernel.org # needs adjustments for <= v6.17
Link: https://bugzilla.kernel.org/show_bug.cgi?id=206537 # [2]
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/monitor.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index f1f0cd9290ac2..881673aeab59f 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -241,7 +241,9 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
 			   u32 unused, u32 rmid, enum resctrl_event_id eventid,
 			   u64 *val, void *ignored)
 {
+	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
 	int cpu = cpumask_any(&d->hdr.cpu_mask);
+	struct arch_mbm_state *am;
 	u64 msr_val;
 	u32 prmid;
 	int ret;
@@ -250,12 +252,16 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
 
 	prmid = logical_rmid_to_physical_rmid(cpu, rmid);
 	ret = __rmid_read_phys(prmid, eventid, &msr_val);
-	if (ret)
-		return ret;
 
-	*val = get_corrected_val(r, d, rmid, eventid, msr_val);
+	if (!ret) {
+		*val = get_corrected_val(r, d, rmid, eventid, msr_val);
+	} else if (ret == -EINVAL) {
+		am = get_arch_mbm_state(hw_dom, rmid, eventid);
+		if (am)
+			am->prev_msr = 0;
+	}
 
-	return 0;
+	return ret;
 }
 
 static int __cntr_id_read(u32 cntr_id, u64 *val)

From 8148dffeeda2fa17a23e1de47667d818e7a1329b Mon Sep 17 00:00:00 2001
From: Babu Moger <babu.moger@amd.com>
Date: Thu, 16 Oct 2025 08:34:19 -0500
Subject: [PATCH 113/236] x86,fs/resctrl: Fix NULL pointer dereference with
 events force-disabled in mbm_event mode

commit 19de7113bfac33ba92c004a9b510612bb745cfa0 upstream.

The following NULL pointer dereference is encountered on mount of resctrl fs
after booting a system that supports assignable counters with the
"rdt=!mbmtotal,!mbmlocal" kernel parameters:

  BUG: kernel NULL pointer dereference, address: 0000000000000008
  RIP: 0010:mbm_cntr_get
  Call Trace:
  rdtgroup_assign_cntr_event
  rdtgroup_assign_cntrs
  rdt_get_tree

Specifying the kernel parameter "rdt=!mbmtotal,!mbmlocal" effectively disables
the legacy X86_FEATURE_CQM_MBM_TOTAL and X86_FEATURE_CQM_MBM_LOCAL features
and the MBM events they represent. This results in the per-domain MBM event
related data structures to not be allocated during early initialization.

resctrl fs initialization follows by implicitly enabling both MBM total and
local events on a system that supports assignable counters (mbm_event mode),
but this enabling occurs after the per-domain data structures have been
created.

After booting, resctrl fs assumes that an enabled event can access all its
state. This results in NULL pointer dereference when resctrl attempts to
access the un-allocated structures of an enabled event.

Remove the late MBM event enabling from resctrl fs.

This leaves a problem where the X86_FEATURE_CQM_MBM_TOTAL and
X86_FEATURE_CQM_MBM_LOCAL features may be disabled while assignable counter
(mbm_event) mode is enabled without any events to support. Switching between
the "default" and "mbm_event" mode without any events is not practical.

Create a dependency between the X86_FEATURE_{CQM_MBM_TOTAL,CQM_MBM_LOCAL} and
X86_FEATURE_ABMC (assignable counter) hardware features. An x86 system that
supports assignable counters now requires support of X86_FEATURE_CQM_MBM_TOTAL
or X86_FEATURE_CQM_MBM_LOCAL.

This ensures all needed MBM related data structures are created before use and
that it is only possible to switch between "default" and "mbm_event" mode when
the same events are available in both modes. This dependency does not exist in
the hardware but this usage of these feature settings work for known systems.

  [ bp: Massage commit message. ]

Fixes: 13390861b426e ("x86,fs/resctrl: Detect Assignable Bandwidth Monitoring feature details")
Co-developed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Babu Moger <babu.moger@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://patch.msgid.link/a62e6ac063d0693475615edd213d5be5e55443e6.1760560934.git.babu.moger@amd.com

 Conflicts:
	fs/resctrl/monitor.c
[jz: resolve context conflict]
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/monitor.c | 11 ++++++++++-
 fs/resctrl/monitor.c                  | 16 +++++++---------
 2 files changed, 17 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 881673aeab59f..e86f8694edead 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -457,7 +457,16 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 		r->mon.mbm_cfg_mask = ecx & MAX_EVT_CONFIG_BITS;
 	}
 
-	if (rdt_cpu_has(X86_FEATURE_ABMC)) {
+	/*
+	 * resctrl assumes a system that supports assignable counters can
+	 * switch to "default" mode. Ensure that there is a "default" mode
+	 * to switch to. This enforces a dependency between the independent
+	 * X86_FEATURE_ABMC and X86_FEATURE_CQM_MBM_TOTAL/X86_FEATURE_CQM_MBM_LOCAL
+	 * hardware features.
+	 */
+	if (rdt_cpu_has(X86_FEATURE_ABMC) &&
+	    (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL) ||
+	     rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL))) {
 		r->mon.mbm_cntr_assignable = true;
 		cpuid_count(0x80000020, 5, &eax, &ebx, &ecx, &edx);
 		r->mon.num_mbm_cntrs = (ebx & GENMASK(15, 0)) + 1;
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index f274d66466ddc..e3f80fd5e85b0 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -1178,15 +1178,13 @@ int resctrl_mon_resource_init(void)
 		mba_mbps_default_event = QOS_L3_MBM_TOTAL_EVENT_ID;
 
 	if (r->mon.mbm_cntr_assignable) {
-		if (!resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID))
-			resctrl_enable_mon_event(QOS_L3_MBM_TOTAL_EVENT_ID);
-		if (!resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID))
-			resctrl_enable_mon_event(QOS_L3_MBM_LOCAL_EVENT_ID);
-		mon_event_all[QOS_L3_MBM_TOTAL_EVENT_ID].evt_cfg = r->mon.mbm_cfg_mask;
-		mon_event_all[QOS_L3_MBM_LOCAL_EVENT_ID].evt_cfg = r->mon.mbm_cfg_mask &
-								   (READS_TO_LOCAL_MEM |
-								    READS_TO_LOCAL_S_MEM |
-								    NON_TEMP_WRITE_TO_LOCAL_MEM);
+		if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID))
+			mon_event_all[QOS_L3_MBM_TOTAL_EVENT_ID].evt_cfg = r->mon.mbm_cfg_mask;
+		if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID))
+			mon_event_all[QOS_L3_MBM_LOCAL_EVENT_ID].evt_cfg = r->mon.mbm_cfg_mask &
+									   (READS_TO_LOCAL_MEM |
+									    READS_TO_LOCAL_S_MEM |
+									    NON_TEMP_WRITE_TO_LOCAL_MEM);
 	}
 
 	return 0;

From a6c53738b8a4ffe2d0fd63994a82b60eb548a37c Mon Sep 17 00:00:00 2001
From: Chen Yu <yu.c.chen@intel.com>
Date: Fri, 26 Sep 2025 12:17:22 +0800
Subject: [PATCH 114/236] x86/resctrl: Support Sub-NUMA Cluster (SNC) mode on
 Clearwater Forest

commit a0a0999507752574b80d7fbd179cce052c92791b upstream.

Clearwater Forest supports SNC mode. Add it to the snc_cpu_ids[] table.

Signed-off-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Acked-by: Tony Luck <tony.luck@intel.com>

 Conflicts:
	arch/x86/kernel/cpu/resctrl/monitor.c
[jz: adapt to X86_MATCH_INTEL_FAM6_MODEL]
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/monitor.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index e86f8694edead..294cff073c9ca 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -360,6 +360,7 @@ static const struct x86_cpu_id snc_cpu_ids[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, 0),
 	X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_X, 0),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT_X, 0),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_DARKMONT_X, 0),
 	{}
 };
 

From f8a84a1de7eddcfe3ae071c5fdb7ba484d069ee9 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Mon, 17 Nov 2025 16:42:45 -0800
Subject: [PATCH 115/236] fs/resctrl: Consider sparse masks when initializing
 new group's allocation

commit 5a88a6e92bbf5963fadeb0e8f8c747c2fb425ba8 upstream.

A new resource group is intended to be created with sane defaults. For a cache
resource this means all cache portions the new group could possibly allocate
into. This includes unused cache portions and shareable cache portions used by
other groups and hardware.

New resource group creation does not take sparse masks into account. After
determining the bitmask reflecting the new group's possible allocations the
bitmask is forced to be contiguous even if the system supports sparse masks.
For example, a new group could by default allocate into a large portion of
cache represented by 0xff0f, but it is instead created with a mask of 0xf.

Do not force a contiguous allocation range if the system supports sparse masks.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://patch.msgid.link/abbbb008bc09d982d715e79d3b885c10f92c64e0.1763426240.git.reinette.chatre@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 fs/resctrl/rdtgroup.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index df12dfeced084..0cfb302dab3ea 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -3240,11 +3240,12 @@ static u32 cbm_ensure_valid(u32 _val, struct rdt_resource *r)
 {
 	unsigned int cbm_len = r->cache.cbm_len;
 	unsigned long first_bit, zero_bit;
-	unsigned long val = _val;
+	unsigned long val;
 
-	if (!val)
-		return 0;
+	if (!_val || r->cache.arch_has_sparse_bitmasks)
+		return _val;
 
+	val = _val;
 	first_bit = find_first_bit(&val, cbm_len);
 	zero_bit = find_next_zero_bit(&val, cbm_len, first_bit);
 

From 5f4867c2db88d358be2de12e604cfea76c336acc Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 17 Dec 2025 09:20:48 -0800
Subject: [PATCH 116/236] x86,fs/resctrl: Improve domain type checking

commit 03eb578b37659e10bed14c2d9e7cc45dfe24123b upstream.

Every resctrl resource has a list of domain structures. struct rdt_ctrl_domain
and struct rdt_mon_domain both begin with struct rdt_domain_hdr with
rdt_domain_hdr::type used in validity checks before accessing the domain of
a particular type.

Add the resource id to struct rdt_domain_hdr in preparation for a new monitoring
domain structure that will be associated with a new monitoring resource. Improve
existing domain validity checks with a new helper domain_header_is_valid()
that checks both domain type and resource id.  domain_header_is_valid() should
be used before every call to container_of() that accesses a domain structure.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c | 10 ++++++----
 fs/resctrl/ctrlmondata.c           |  2 +-
 include/linux/resctrl.h            |  9 +++++++++
 3 files changed, 16 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 123a8abadc178..0f81f7a72d5ab 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -458,7 +458,7 @@ static void domain_add_cpu_ctrl(int cpu, struct rdt_resource *r)
 
 	hdr = resctrl_find_domain(&r->ctrl_domains, id, &add_pos);
 	if (hdr) {
-		if (WARN_ON_ONCE(hdr->type != RESCTRL_CTRL_DOMAIN))
+		if (!domain_header_is_valid(hdr, RESCTRL_CTRL_DOMAIN, r->rid))
 			return;
 		d = container_of(hdr, struct rdt_ctrl_domain, hdr);
 
@@ -475,6 +475,7 @@ static void domain_add_cpu_ctrl(int cpu, struct rdt_resource *r)
 	d = &hw_dom->d_resctrl;
 	d->hdr.id = id;
 	d->hdr.type = RESCTRL_CTRL_DOMAIN;
+	d->hdr.rid = r->rid;
 	cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
 
 	rdt_domain_reconfigure_cdp(r);
@@ -514,7 +515,7 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
 
 	hdr = resctrl_find_domain(&r->mon_domains, id, &add_pos);
 	if (hdr) {
-		if (WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN))
+		if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, r->rid))
 			return;
 		d = container_of(hdr, struct rdt_mon_domain, hdr);
 
@@ -532,6 +533,7 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
 	d = &hw_dom->d_resctrl;
 	d->hdr.id = id;
 	d->hdr.type = RESCTRL_MON_DOMAIN;
+	d->hdr.rid = r->rid;
 	ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
 	if (!ci) {
 		pr_warn_once("Can't find L3 cache for CPU:%d resource %s\n", cpu, r->name);
@@ -592,7 +594,7 @@ static void domain_remove_cpu_ctrl(int cpu, struct rdt_resource *r)
 		return;
 	}
 
-	if (WARN_ON_ONCE(hdr->type != RESCTRL_CTRL_DOMAIN))
+	if (!domain_header_is_valid(hdr, RESCTRL_CTRL_DOMAIN, r->rid))
 		return;
 
 	d = container_of(hdr, struct rdt_ctrl_domain, hdr);
@@ -638,7 +640,7 @@ static void domain_remove_cpu_mon(int cpu, struct rdt_resource *r)
 		return;
 	}
 
-	if (WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN))
+	if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, r->rid))
 		return;
 
 	d = container_of(hdr, struct rdt_mon_domain, hdr);
diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c
index 0d0ef54fc4de1..f248eaf50d3cb 100644
--- a/fs/resctrl/ctrlmondata.c
+++ b/fs/resctrl/ctrlmondata.c
@@ -649,7 +649,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 		 * the resource to find the domain with "domid".
 		 */
 		hdr = resctrl_find_domain(&r->mon_domains, domid, NULL);
-		if (!hdr || WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN)) {
+		if (!hdr || !domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, resid)) {
 			ret = -ENOENT;
 			goto out;
 		}
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 04152654827d4..9dd4be7552625 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -131,15 +131,24 @@ enum resctrl_domain_type {
  * @list:		all instances of this resource
  * @id:			unique id for this instance
  * @type:		type of this instance
+ * @rid:		resource id for this instance
  * @cpu_mask:		which CPUs share this resource
  */
 struct rdt_domain_hdr {
 	struct list_head		list;
 	int				id;
 	enum resctrl_domain_type	type;
+	enum resctrl_res_level		rid;
 	struct cpumask			cpu_mask;
 };
 
+static inline bool domain_header_is_valid(struct rdt_domain_hdr *hdr,
+					  enum resctrl_domain_type type,
+					  enum resctrl_res_level rid)
+{
+	return !WARN_ON_ONCE(hdr->type != type || hdr->rid != rid);
+}
+
 /**
  * struct rdt_ctrl_domain - group of CPUs sharing a resctrl control resource
  * @hdr:		common header for different domain types

From 6e115794bc4186e61d8ff71c9b0b449151648737 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 17 Dec 2025 09:20:49 -0800
Subject: [PATCH 117/236] x86/resctrl: Move L3 initialization into new helper
 function

commit 0d6447623d788806b5504182032a0837ffa2174c upstream.

Carve out the resource monitoring domain init code into a separate helper in
order to be able to initialize new types of monitoring domains besides the
usual L3 ones.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c | 64 ++++++++++++++++--------------
 1 file changed, 34 insertions(+), 30 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 0f81f7a72d5ab..2f9f34b44cce3 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -495,37 +495,13 @@ static void domain_add_cpu_ctrl(int cpu, struct rdt_resource *r)
 	}
 }
 
-static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
+static void l3_mon_domain_setup(int cpu, int id, struct rdt_resource *r, struct list_head *add_pos)
 {
-	int id = get_domain_id_from_scope(cpu, r->mon_scope);
-	struct list_head *add_pos = NULL;
 	struct rdt_hw_mon_domain *hw_dom;
-	struct rdt_domain_hdr *hdr;
 	struct rdt_mon_domain *d;
 	struct cacheinfo *ci;
 	int err;
 
-	lockdep_assert_held(&domain_list_lock);
-
-	if (id < 0) {
-		pr_warn_once("Can't find monitor domain id for CPU:%d scope:%d for resource %s\n",
-			     cpu, r->mon_scope, r->name);
-		return;
-	}
-
-	hdr = resctrl_find_domain(&r->mon_domains, id, &add_pos);
-	if (hdr) {
-		if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, r->rid))
-			return;
-		d = container_of(hdr, struct rdt_mon_domain, hdr);
-
-		cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
-		/* Update the mbm_assign_mode state for the CPU if supported */
-		if (r->mon.mbm_cntr_assignable)
-			resctrl_arch_mbm_cntr_assign_set_one(r);
-		return;
-	}
-
 	hw_dom = kzalloc_node(sizeof(*hw_dom), GFP_KERNEL, cpu_to_node(cpu));
 	if (!hw_dom)
 		return;
@@ -533,7 +509,7 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
 	d = &hw_dom->d_resctrl;
 	d->hdr.id = id;
 	d->hdr.type = RESCTRL_MON_DOMAIN;
-	d->hdr.rid = r->rid;
+	d->hdr.rid = RDT_RESOURCE_L3;
 	ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
 	if (!ci) {
 		pr_warn_once("Can't find L3 cache for CPU:%d resource %s\n", cpu, r->name);
@@ -543,10 +519,6 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
 	d->ci_id = ci->id;
 	cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
 
-	/* Update the mbm_assign_mode state for the CPU if supported */
-	if (r->mon.mbm_cntr_assignable)
-		resctrl_arch_mbm_cntr_assign_set_one(r);
-
 	arch_mon_domain_online(r, d);
 
 	if (arch_domain_mbm_alloc(r->mon.num_rmid, hw_dom)) {
@@ -564,6 +536,38 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
 	}
 }
 
+static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
+{
+	int id = get_domain_id_from_scope(cpu, r->mon_scope);
+	struct list_head *add_pos = NULL;
+	struct rdt_domain_hdr *hdr;
+
+	lockdep_assert_held(&domain_list_lock);
+
+	if (id < 0) {
+		pr_warn_once("Can't find monitor domain id for CPU:%d scope:%d for resource %s\n",
+			     cpu, r->mon_scope, r->name);
+		return;
+	}
+
+	hdr = resctrl_find_domain(&r->mon_domains, id, &add_pos);
+	if (hdr)
+		cpumask_set_cpu(cpu, &hdr->cpu_mask);
+
+	switch (r->rid) {
+	case RDT_RESOURCE_L3:
+		/* Update the mbm_assign_mode state for the CPU if supported */
+		if (r->mon.mbm_cntr_assignable)
+			resctrl_arch_mbm_cntr_assign_set_one(r);
+		if (!hdr)
+			l3_mon_domain_setup(cpu, id, r, add_pos);
+		break;
+	default:
+		pr_warn_once("Unknown resource rid=%d\n", r->rid);
+		break;
+	}
+}
+
 static void domain_add_cpu(int cpu, struct rdt_resource *r)
 {
 	if (r->alloc_capable)

From 59a869a1b8d3c1d0e1b569b26de875610c6afa56 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 17 Dec 2025 09:20:50 -0800
Subject: [PATCH 118/236] x86/resctrl: Refactor domain_remove_cpu_mon() ready
 for new domain types

commit 6396fc5351ea9130a72f6a2fc58eb7298ce6c15a upstream.

New telemetry events will be associated with a new package scoped resource
with a new domain structure.

Refactor domain_remove_cpu_mon() so all the L3 domain processing is separate
from the general domain action of clearing the CPU bit in the mask.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c | 27 +++++++++++++++++----------
 1 file changed, 17 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 2f9f34b44cce3..60de42e822360 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -625,9 +625,7 @@ static void domain_remove_cpu_ctrl(int cpu, struct rdt_resource *r)
 static void domain_remove_cpu_mon(int cpu, struct rdt_resource *r)
 {
 	int id = get_domain_id_from_scope(cpu, r->mon_scope);
-	struct rdt_hw_mon_domain *hw_dom;
 	struct rdt_domain_hdr *hdr;
-	struct rdt_mon_domain *d;
 
 	lockdep_assert_held(&domain_list_lock);
 
@@ -644,20 +642,29 @@ static void domain_remove_cpu_mon(int cpu, struct rdt_resource *r)
 		return;
 	}
 
-	if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, r->rid))
+	cpumask_clear_cpu(cpu, &hdr->cpu_mask);
+	if (!cpumask_empty(&hdr->cpu_mask))
 		return;
 
-	d = container_of(hdr, struct rdt_mon_domain, hdr);
-	hw_dom = resctrl_to_arch_mon_dom(d);
+	switch (r->rid) {
+	case RDT_RESOURCE_L3: {
+		struct rdt_hw_mon_domain *hw_dom;
+		struct rdt_mon_domain *d;
 
-	cpumask_clear_cpu(cpu, &d->hdr.cpu_mask);
-	if (cpumask_empty(&d->hdr.cpu_mask)) {
+		if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3))
+			return;
+
+		d = container_of(hdr, struct rdt_mon_domain, hdr);
+		hw_dom = resctrl_to_arch_mon_dom(d);
 		resctrl_offline_mon_domain(r, d);
-		list_del_rcu(&d->hdr.list);
+		list_del_rcu(&hdr->list);
 		synchronize_rcu();
 		mon_domain_free(hw_dom);
-
-		return;
+		break;
+	}
+	default:
+		pr_warn_once("Unknown resource rid=%d\n", r->rid);
+		break;
 	}
 }
 

From a8c7b2a35976b256dfc1b869317089a12bf9500b Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 17 Dec 2025 09:20:51 -0800
Subject: [PATCH 119/236] x86/resctrl: Clean up domain_remove_cpu_ctrl()

commit c1b630573c8ca51a89bd480f7eeaf8754c7609f2 upstream.

For symmetry with domain_remove_cpu_mon() refactor domain_remove_cpu_ctrl()
to take an early return when removing a CPU does not empty the domain.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c | 29 ++++++++++++++---------------
 1 file changed, 14 insertions(+), 15 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 60de42e822360..40f8a04f8536a 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -598,28 +598,27 @@ static void domain_remove_cpu_ctrl(int cpu, struct rdt_resource *r)
 		return;
 	}
 
+	cpumask_clear_cpu(cpu, &hdr->cpu_mask);
+	if (!cpumask_empty(&hdr->cpu_mask))
+		return;
+
 	if (!domain_header_is_valid(hdr, RESCTRL_CTRL_DOMAIN, r->rid))
 		return;
 
 	d = container_of(hdr, struct rdt_ctrl_domain, hdr);
 	hw_dom = resctrl_to_arch_ctrl_dom(d);
 
-	cpumask_clear_cpu(cpu, &d->hdr.cpu_mask);
-	if (cpumask_empty(&d->hdr.cpu_mask)) {
-		resctrl_offline_ctrl_domain(r, d);
-		list_del_rcu(&d->hdr.list);
-		synchronize_rcu();
-
-		/*
-		 * rdt_ctrl_domain "d" is going to be freed below, so clear
-		 * its pointer from pseudo_lock_region struct.
-		 */
-		if (d->plr)
-			d->plr->d = NULL;
-		ctrl_domain_free(hw_dom);
+	resctrl_offline_ctrl_domain(r, d);
+	list_del_rcu(&hdr->list);
+	synchronize_rcu();
 
-		return;
-	}
+	/*
+	 * rdt_ctrl_domain "d" is going to be freed below, so clear
+	 * its pointer from pseudo_lock_region struct.
+	 */
+	if (d->plr)
+		d->plr->d = NULL;
+	ctrl_domain_free(hw_dom);
 }
 
 static void domain_remove_cpu_mon(int cpu, struct rdt_resource *r)

From 123fa75db0d33aa4d71cc21865f5b97a7e94d629 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 17 Dec 2025 09:20:52 -0800
Subject: [PATCH 120/236] x86,fs/resctrl: Refactor domain create/remove using
 struct rdt_domain_hdr

commit 97fec06d35b2c1ce6d80cf3b01bfddd82c720a2d upstream.

Up until now, all monitoring events were associated with the L3 resource and it
made sense to use the L3 specific "struct rdt_mon_domain *" argument to functions
operating on domains.

Telemetry events will be tied to a new resource with its instances represented
by a new domain structure that, just like struct rdt_mon_domain, starts with
the generic struct rdt_domain_hdr.

Prepare to support domains belonging to different resources by changing the
calling convention of functions operating on domains.  Pass the generic header
and use that to find the domain specific structure where needed.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c |  4 +-
 fs/resctrl/ctrlmondata.c           | 14 ++++--
 fs/resctrl/internal.h              |  2 +-
 fs/resctrl/rdtgroup.c              | 69 +++++++++++++++++++++---------
 include/linux/resctrl.h            |  4 +-
 5 files changed, 63 insertions(+), 30 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 40f8a04f8536a..48fb106681c1b 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -528,7 +528,7 @@ static void l3_mon_domain_setup(int cpu, int id, struct rdt_resource *r, struct
 
 	list_add_tail_rcu(&d->hdr.list, add_pos);
 
-	err = resctrl_online_mon_domain(r, d);
+	err = resctrl_online_mon_domain(r, &d->hdr);
 	if (err) {
 		list_del_rcu(&d->hdr.list);
 		synchronize_rcu();
@@ -655,7 +655,7 @@ static void domain_remove_cpu_mon(int cpu, struct rdt_resource *r)
 
 		d = container_of(hdr, struct rdt_mon_domain, hdr);
 		hw_dom = resctrl_to_arch_mon_dom(d);
-		resctrl_offline_mon_domain(r, d);
+		resctrl_offline_mon_domain(r, hdr);
 		list_del_rcu(&hdr->list);
 		synchronize_rcu();
 		mon_domain_free(hw_dom);
diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c
index f248eaf50d3cb..a2ea6a66fa67b 100644
--- a/fs/resctrl/ctrlmondata.c
+++ b/fs/resctrl/ctrlmondata.c
@@ -547,14 +547,21 @@ struct rdt_domain_hdr *resctrl_find_domain(struct list_head *h, int id,
 }
 
 void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
-		    struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
+		    struct rdt_domain_hdr *hdr, struct rdtgroup *rdtgrp,
 		    cpumask_t *cpumask, int evtid, int first)
 {
+	struct rdt_mon_domain *d = NULL;
 	int cpu;
 
 	/* When picking a CPU from cpu_mask, ensure it can't race with cpuhp */
 	lockdep_assert_cpus_held();
 
+	if (hdr) {
+		if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3))
+			return;
+		d = container_of(hdr, struct rdt_mon_domain, hdr);
+	}
+
 	/*
 	 * Setup the parameters to pass to mon_event_count() to read the data.
 	 */
@@ -649,12 +656,11 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 		 * the resource to find the domain with "domid".
 		 */
 		hdr = resctrl_find_domain(&r->mon_domains, domid, NULL);
-		if (!hdr || !domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, resid)) {
+		if (!hdr) {
 			ret = -ENOENT;
 			goto out;
 		}
-		d = container_of(hdr, struct rdt_mon_domain, hdr);
-		mon_event_read(&rr, r, d, rdtgrp, &d->hdr.cpu_mask, evtid, false);
+		mon_event_read(&rr, r, hdr, rdtgrp, &hdr->cpu_mask, evtid, false);
 	}
 
 checkresult:
diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index 8a654bf414326..be5aa0ba4309c 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -360,7 +360,7 @@ void mon_event_count(void *info);
 int rdtgroup_mondata_show(struct seq_file *m, void *arg);
 
 void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
-		    struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
+		    struct rdt_domain_hdr *hdr, struct rdtgroup *rdtgrp,
 		    cpumask_t *cpumask, int evtid, int first);
 
 int resctrl_mon_resource_init(void);
diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index 0cfb302dab3ea..4d5f0fd861ef4 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -3021,17 +3021,22 @@ static void mon_rmdir_one_subdir(struct kernfs_node *pkn, char *name, char *subn
  * when last domain being summed is removed.
  */
 static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
-					   struct rdt_mon_domain *d)
+					   struct rdt_domain_hdr *hdr)
 {
 	struct rdtgroup *prgrp, *crgrp;
+	struct rdt_mon_domain *d;
 	char subname[32];
 	bool snc_mode;
 	char name[32];
 
+	if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3))
+		return;
+
+	d = container_of(hdr, struct rdt_mon_domain, hdr);
 	snc_mode = r->mon_scope == RESCTRL_L3_NODE;
-	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci_id : d->hdr.id);
+	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci_id : hdr->id);
 	if (snc_mode)
-		sprintf(subname, "mon_sub_%s_%02d", r->name, d->hdr.id);
+		sprintf(subname, "mon_sub_%s_%02d", r->name, hdr->id);
 
 	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
 		mon_rmdir_one_subdir(prgrp->mon.mon_data_kn, name, subname);
@@ -3041,15 +3046,20 @@ static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
 	}
 }
 
-static int mon_add_all_files(struct kernfs_node *kn, struct rdt_mon_domain *d,
+static int mon_add_all_files(struct kernfs_node *kn, struct rdt_domain_hdr *hdr,
 			     struct rdt_resource *r, struct rdtgroup *prgrp,
 			     bool do_sum)
 {
 	struct rmid_read rr = {0};
+	struct rdt_mon_domain *d;
 	struct mon_data *priv;
 	struct mon_evt *mevt;
 	int ret, domid;
 
+	if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3))
+		return -EINVAL;
+
+	d = container_of(hdr, struct rdt_mon_domain, hdr);
 	for_each_mon_event(mevt) {
 		if (mevt->rid != r->rid || !mevt->enabled)
 			continue;
@@ -3063,23 +3073,28 @@ static int mon_add_all_files(struct kernfs_node *kn, struct rdt_mon_domain *d,
 			return ret;
 
 		if (!do_sum && resctrl_is_mbm_event(mevt->evtid))
-			mon_event_read(&rr, r, d, prgrp, &d->hdr.cpu_mask, mevt->evtid, true);
+			mon_event_read(&rr, r, hdr, prgrp, &hdr->cpu_mask, mevt->evtid, true);
 	}
 
 	return 0;
 }
 
 static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
-				struct rdt_mon_domain *d,
+				struct rdt_domain_hdr *hdr,
 				struct rdt_resource *r, struct rdtgroup *prgrp)
 {
 	struct kernfs_node *kn, *ckn;
+	struct rdt_mon_domain *d;
 	char name[32];
 	bool snc_mode;
 	int ret = 0;
 
 	lockdep_assert_held(&rdtgroup_mutex);
 
+	if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3))
+		return -EINVAL;
+
+	d = container_of(hdr, struct rdt_mon_domain, hdr);
 	snc_mode = r->mon_scope == RESCTRL_L3_NODE;
 	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci_id : d->hdr.id);
 	kn = kernfs_find_and_get(parent_kn, name);
@@ -3097,13 +3112,13 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
 		ret = rdtgroup_kn_set_ugid(kn);
 		if (ret)
 			goto out_destroy;
-		ret = mon_add_all_files(kn, d, r, prgrp, snc_mode);
+		ret = mon_add_all_files(kn, hdr, r, prgrp, snc_mode);
 		if (ret)
 			goto out_destroy;
 	}
 
 	if (snc_mode) {
-		sprintf(name, "mon_sub_%s_%02d", r->name, d->hdr.id);
+		sprintf(name, "mon_sub_%s_%02d", r->name, hdr->id);
 		ckn = kernfs_create_dir(kn, name, parent_kn->mode, prgrp);
 		if (IS_ERR(ckn)) {
 			ret = -EINVAL;
@@ -3114,7 +3129,7 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
 		if (ret)
 			goto out_destroy;
 
-		ret = mon_add_all_files(ckn, d, r, prgrp, false);
+		ret = mon_add_all_files(ckn, hdr, r, prgrp, false);
 		if (ret)
 			goto out_destroy;
 	}
@@ -3132,7 +3147,7 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
  * and "monitor" groups with given domain id.
  */
 static void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
-					   struct rdt_mon_domain *d)
+					   struct rdt_domain_hdr *hdr)
 {
 	struct kernfs_node *parent_kn;
 	struct rdtgroup *prgrp, *crgrp;
@@ -3140,12 +3155,12 @@ static void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
 
 	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
 		parent_kn = prgrp->mon.mon_data_kn;
-		mkdir_mondata_subdir(parent_kn, d, r, prgrp);
+		mkdir_mondata_subdir(parent_kn, hdr, r, prgrp);
 
 		head = &prgrp->mon.crdtgrp_list;
 		list_for_each_entry(crgrp, head, mon.crdtgrp_list) {
 			parent_kn = crgrp->mon.mon_data_kn;
-			mkdir_mondata_subdir(parent_kn, d, r, crgrp);
+			mkdir_mondata_subdir(parent_kn, hdr, r, crgrp);
 		}
 	}
 }
@@ -3154,14 +3169,14 @@ static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn,
 				       struct rdt_resource *r,
 				       struct rdtgroup *prgrp)
 {
-	struct rdt_mon_domain *dom;
+	struct rdt_domain_hdr *hdr;
 	int ret;
 
 	/* Walking r->domains, ensure it can't race with cpuhp */
 	lockdep_assert_cpus_held();
 
-	list_for_each_entry(dom, &r->mon_domains, hdr.list) {
-		ret = mkdir_mondata_subdir(parent_kn, dom, r, prgrp);
+	list_for_each_entry(hdr, &r->mon_domains, list) {
+		ret = mkdir_mondata_subdir(parent_kn, hdr, r, prgrp);
 		if (ret)
 			return ret;
 	}
@@ -4035,16 +4050,23 @@ void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain
 	mutex_unlock(&rdtgroup_mutex);
 }
 
-void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d)
+void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_domain_hdr *hdr)
 {
+	struct rdt_mon_domain *d;
+
 	mutex_lock(&rdtgroup_mutex);
 
+	if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3))
+		goto out_unlock;
+
+	d = container_of(hdr, struct rdt_mon_domain, hdr);
+
 	/*
 	 * If resctrl is mounted, remove all the
 	 * per domain monitor data directories.
 	 */
 	if (resctrl_mounted && resctrl_arch_mon_capable())
-		rmdir_mondata_subdir_allrdtgrp(r, d);
+		rmdir_mondata_subdir_allrdtgrp(r, hdr);
 
 	if (resctrl_is_mbm_enabled())
 		cancel_delayed_work(&d->mbm_over);
@@ -4062,7 +4084,7 @@ void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d
 	}
 
 	domain_destroy_mon_state(d);
-
+out_unlock:
 	mutex_unlock(&rdtgroup_mutex);
 }
 
@@ -4135,12 +4157,17 @@ int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d
 	return err;
 }
 
-int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d)
+int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_domain_hdr *hdr)
 {
-	int err;
+	struct rdt_mon_domain *d;
+	int err = -EINVAL;
 
 	mutex_lock(&rdtgroup_mutex);
 
+	if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3))
+		goto out_unlock;
+
+	d = container_of(hdr, struct rdt_mon_domain, hdr);
 	err = domain_setup_mon_state(r, d);
 	if (err)
 		goto out_unlock;
@@ -4161,7 +4188,7 @@ int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d)
 	 * If resctrl is mounted, add per domain monitor data directories.
 	 */
 	if (resctrl_mounted && resctrl_arch_mon_capable())
-		mkdir_mondata_subdir_allrdtgrp(r, d);
+		mkdir_mondata_subdir_allrdtgrp(r, hdr);
 
 out_unlock:
 	mutex_unlock(&rdtgroup_mutex);
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 9dd4be7552625..fd77f4d5d718f 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -501,9 +501,9 @@ int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_ctrl_domain *d,
 u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_ctrl_domain *d,
 			    u32 closid, enum resctrl_conf_type type);
 int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d);
-int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d);
+int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_domain_hdr *hdr);
 void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d);
-void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d);
+void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_domain_hdr *hdr);
 void resctrl_online_cpu(unsigned int cpu);
 void resctrl_offline_cpu(unsigned int cpu);
 

From e503282ccb132ad0add26fb42e2069e060ea3708 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 17 Dec 2025 09:20:53 -0800
Subject: [PATCH 121/236] fs/resctrl: Split L3 dependent parts out of
 __mon_event_count()

commit ad5c2ff75e0c53d2588dfc10eb87458e759b6bbe upstream.

Carve out the L3 resource specific event reading code into a separate helper
to support reading event data from a new monitoring resource.

Suggested-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 fs/resctrl/monitor.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index e3f80fd5e85b0..6eebcb88b313f 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -413,7 +413,7 @@ static void mbm_cntr_free(struct rdt_mon_domain *d, int cntr_id)
 	memset(&d->cntr_cfg[cntr_id], 0, sizeof(*d->cntr_cfg));
 }
 
-static int __mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
+static int __l3_mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
 {
 	int cpu = smp_processor_id();
 	u32 closid = rdtgrp->closid;
@@ -494,6 +494,17 @@ static int __mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
 	return ret;
 }
 
+static int __mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
+{
+	switch (rr->r->rid) {
+	case RDT_RESOURCE_L3:
+		return __l3_mon_event_count(rdtgrp, rr);
+	default:
+		rr->err = -EINVAL;
+		return -EINVAL;
+	}
+}
+
 /*
  * mbm_bw_count() - Update bw count from values previously read by
  *		    __mon_event_count().

From b813e02b0870045a6102c416037555632b4a4fe6 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 17 Dec 2025 09:20:54 -0800
Subject: [PATCH 122/236] x86,fs/resctrl: Use struct rdt_domain_hdr when
 reading counters

commit 6b10cf7b6ea857cdf9570e21c077a05803f60575 upstream.

Convert the whole call sequence from mon_event_read() to resctrl_arch_rmid_read() to
pass resource independent struct rdt_domain_hdr instead of an L3 specific domain
structure to prepare for monitoring events in other resources.

This additional layer of indirection obscures which aspects of event counting depend
on a valid domain. Event initialization, support for assignable counters, and normal
event counting implicitly depend on a valid domain while summing of domains does not.
Split summing domains from the core event counting handling to make their respective
dependencies obvious.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/monitor.c | 12 +++-
 fs/resctrl/ctrlmondata.c              |  9 +--
 fs/resctrl/internal.h                 | 18 +++---
 fs/resctrl/monitor.c                  | 85 ++++++++++++++++++---------
 include/linux/resctrl.h               |  4 +-
 5 files changed, 78 insertions(+), 50 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 294cff073c9ca..9b946c92943ab 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -237,19 +237,25 @@ static u64 get_corrected_val(struct rdt_resource *r, struct rdt_mon_domain *d,
 	return chunks * hw_res->mon_scale;
 }
 
-int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
+int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain_hdr *hdr,
 			   u32 unused, u32 rmid, enum resctrl_event_id eventid,
 			   u64 *val, void *ignored)
 {
-	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
-	int cpu = cpumask_any(&d->hdr.cpu_mask);
+	struct rdt_hw_mon_domain *hw_dom;
 	struct arch_mbm_state *am;
+	struct rdt_mon_domain *d;
 	u64 msr_val;
 	u32 prmid;
+	int cpu;
 	int ret;
 
 	resctrl_arch_rmid_read_context_check();
+	if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3))
+		return -EINVAL;
 
+	d = container_of(hdr, struct rdt_mon_domain, hdr);
+	hw_dom = resctrl_to_arch_mon_dom(d);
+	cpu = cpumask_any(&hdr->cpu_mask);
 	prmid = logical_rmid_to_physical_rmid(cpu, rmid);
 	ret = __rmid_read_phys(prmid, eventid, &msr_val);
 
diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c
index a2ea6a66fa67b..ad347ab4ed292 100644
--- a/fs/resctrl/ctrlmondata.c
+++ b/fs/resctrl/ctrlmondata.c
@@ -550,25 +550,18 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 		    struct rdt_domain_hdr *hdr, struct rdtgroup *rdtgrp,
 		    cpumask_t *cpumask, int evtid, int first)
 {
-	struct rdt_mon_domain *d = NULL;
 	int cpu;
 
 	/* When picking a CPU from cpu_mask, ensure it can't race with cpuhp */
 	lockdep_assert_cpus_held();
 
-	if (hdr) {
-		if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3))
-			return;
-		d = container_of(hdr, struct rdt_mon_domain, hdr);
-	}
-
 	/*
 	 * Setup the parameters to pass to mon_event_count() to read the data.
 	 */
 	rr->rgrp = rdtgrp;
 	rr->evtid = evtid;
 	rr->r = r;
-	rr->d = d;
+	rr->hdr = hdr;
 	rr->first = first;
 	if (resctrl_arch_mbm_cntr_assign_enabled(r) &&
 	    resctrl_is_mbm_event(evtid)) {
diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index be5aa0ba4309c..66a5459db2597 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -106,24 +106,26 @@ struct mon_data {
  *	   resource group then its event count is summed with the count from all
  *	   its child resource groups.
  * @r:	   Resource describing the properties of the event being read.
- * @d:	   Domain that the counter should be read from. If NULL then sum all
- *	   domains in @r sharing L3 @ci.id
+ * @hdr:   Header of domain that the counter should be read from. If NULL then
+ *	   sum all domains in @r sharing L3 @ci.id
  * @evtid: Which monitor event to read.
  * @first: Initialize MBM counter when true.
- * @ci:    Cacheinfo for L3. Only set when @d is NULL. Used when summing domains.
+ * @ci:    Cacheinfo for L3. Only set when @hdr is NULL. Used when summing
+ *	   domains.
  * @is_mbm_cntr: true if "mbm_event" counter assignment mode is enabled and it
  *	   is an MBM event.
  * @err:   Error encountered when reading counter.
- * @val:   Returned value of event counter. If @rgrp is a parent resource group,
- *	   @val includes the sum of event counts from its child resource groups.
- *	   If @d is NULL, @val includes the sum of all domains in @r sharing @ci.id,
- *	   (summed across child resource groups if @rgrp is a parent resource group).
+ * @val:   Returned value of event counter. If @rgrp is a parent resource
+ *	   group, @val includes the sum of event counts from its child
+ *	   resource groups.  If @hdr is NULL, @val includes the sum of all
+ *	   domains in @r sharing @ci.id, (summed across child resource groups
+ *	   if @rgrp is a parent resource group).
  * @arch_mon_ctx: Hardware monitor allocated for this read request (MPAM only).
  */
 struct rmid_read {
 	struct rdtgroup		*rgrp;
 	struct rdt_resource	*r;
-	struct rdt_mon_domain	*d;
+	struct rdt_domain_hdr	*hdr;
 	enum resctrl_event_id	evtid;
 	bool			first;
 	struct cacheinfo	*ci;
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index 6eebcb88b313f..9e073eb8cef7b 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -159,7 +159,7 @@ void __check_limbo(struct rdt_mon_domain *d, bool force_free)
 			break;
 
 		entry = __rmid_entry(idx);
-		if (resctrl_arch_rmid_read(r, d, entry->closid, entry->rmid,
+		if (resctrl_arch_rmid_read(r, &d->hdr, entry->closid, entry->rmid,
 					   QOS_L3_OCCUP_EVENT_ID, &val,
 					   arch_mon_ctx)) {
 			rmid_dirty = true;
@@ -421,11 +421,16 @@ static int __l3_mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
 	struct rdt_mon_domain *d;
 	int cntr_id = -ENOENT;
 	struct mbm_state *m;
-	int err, ret;
 	u64 tval = 0;
 
+	if (!domain_header_is_valid(rr->hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3)) {
+		rr->err = -EIO;
+		return -EINVAL;
+	}
+	d = container_of(rr->hdr, struct rdt_mon_domain, hdr);
+
 	if (rr->is_mbm_cntr) {
-		cntr_id = mbm_cntr_get(rr->r, rr->d, rdtgrp, rr->evtid);
+		cntr_id = mbm_cntr_get(rr->r, d, rdtgrp, rr->evtid);
 		if (cntr_id < 0) {
 			rr->err = -ENOENT;
 			return -EINVAL;
@@ -434,31 +439,50 @@ static int __l3_mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
 
 	if (rr->first) {
 		if (rr->is_mbm_cntr)
-			resctrl_arch_reset_cntr(rr->r, rr->d, closid, rmid, cntr_id, rr->evtid);
+			resctrl_arch_reset_cntr(rr->r, d, closid, rmid, cntr_id, rr->evtid);
 		else
-			resctrl_arch_reset_rmid(rr->r, rr->d, closid, rmid, rr->evtid);
-		m = get_mbm_state(rr->d, closid, rmid, rr->evtid);
+			resctrl_arch_reset_rmid(rr->r, d, closid, rmid, rr->evtid);
+		m = get_mbm_state(d, closid, rmid, rr->evtid);
 		if (m)
 			memset(m, 0, sizeof(struct mbm_state));
 		return 0;
 	}
 
-	if (rr->d) {
-		/* Reading a single domain, must be on a CPU in that domain. */
-		if (!cpumask_test_cpu(cpu, &rr->d->hdr.cpu_mask))
-			return -EINVAL;
-		if (rr->is_mbm_cntr)
-			rr->err = resctrl_arch_cntr_read(rr->r, rr->d, closid, rmid, cntr_id,
-							 rr->evtid, &tval);
-		else
-			rr->err = resctrl_arch_rmid_read(rr->r, rr->d, closid, rmid,
-							 rr->evtid, &tval, rr->arch_mon_ctx);
-		if (rr->err)
-			return rr->err;
+	/* Reading a single domain, must be on a CPU in that domain. */
+	if (!cpumask_test_cpu(cpu, &d->hdr.cpu_mask))
+		return -EINVAL;
+	if (rr->is_mbm_cntr)
+		rr->err = resctrl_arch_cntr_read(rr->r, d, closid, rmid, cntr_id,
+						 rr->evtid, &tval);
+	else
+		rr->err = resctrl_arch_rmid_read(rr->r, rr->hdr, closid, rmid,
+						 rr->evtid, &tval, rr->arch_mon_ctx);
+	if (rr->err)
+		return rr->err;
 
-		rr->val += tval;
+	rr->val += tval;
 
-		return 0;
+	return 0;
+}
+
+static int __l3_mon_event_count_sum(struct rdtgroup *rdtgrp, struct rmid_read *rr)
+{
+	int cpu = smp_processor_id();
+	u32 closid = rdtgrp->closid;
+	u32 rmid = rdtgrp->mon.rmid;
+	struct rdt_mon_domain *d;
+	u64 tval = 0;
+	int err, ret;
+
+	/*
+	 * Summing across domains is only done for systems that implement
+	 * Sub-NUMA Cluster. There is no overlap with systems that support
+	 * assignable counters.
+	 */
+	if (rr->is_mbm_cntr) {
+		pr_warn_once("Summing domains using assignable counters is not supported\n");
+		rr->err = -EINVAL;
+		return -EINVAL;
 	}
 
 	/* Summing domains that share a cache, must be on a CPU for that cache. */
@@ -476,12 +500,8 @@ static int __l3_mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
 	list_for_each_entry(d, &rr->r->mon_domains, hdr.list) {
 		if (d->ci_id != rr->ci->id)
 			continue;
-		if (rr->is_mbm_cntr)
-			err = resctrl_arch_cntr_read(rr->r, d, closid, rmid, cntr_id,
-						     rr->evtid, &tval);
-		else
-			err = resctrl_arch_rmid_read(rr->r, d, closid, rmid,
-						     rr->evtid, &tval, rr->arch_mon_ctx);
+		err = resctrl_arch_rmid_read(rr->r, &d->hdr, closid, rmid,
+					     rr->evtid, &tval, rr->arch_mon_ctx);
 		if (!err) {
 			rr->val += tval;
 			ret = 0;
@@ -498,7 +518,10 @@ static int __mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
 {
 	switch (rr->r->rid) {
 	case RDT_RESOURCE_L3:
-		return __l3_mon_event_count(rdtgrp, rr);
+		if (rr->hdr)
+			return __l3_mon_event_count(rdtgrp, rr);
+		else
+			return __l3_mon_event_count_sum(rdtgrp, rr);
 	default:
 		rr->err = -EINVAL;
 		return -EINVAL;
@@ -522,9 +545,13 @@ static void mbm_bw_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
 	u64 cur_bw, bytes, cur_bytes;
 	u32 closid = rdtgrp->closid;
 	u32 rmid = rdtgrp->mon.rmid;
+	struct rdt_mon_domain *d;
 	struct mbm_state *m;
 
-	m = get_mbm_state(rr->d, closid, rmid, rr->evtid);
+	if (!domain_header_is_valid(rr->hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3))
+		return;
+	d = container_of(rr->hdr, struct rdt_mon_domain, hdr);
+	m = get_mbm_state(d, closid, rmid, rr->evtid);
 	if (WARN_ON_ONCE(!m))
 		return;
 
@@ -697,7 +724,7 @@ static void mbm_update_one_event(struct rdt_resource *r, struct rdt_mon_domain *
 	struct rmid_read rr = {0};
 
 	rr.r = r;
-	rr.d = d;
+	rr.hdr = &d->hdr;
 	rr.evtid = evtid;
 	if (resctrl_arch_mbm_cntr_assign_enabled(r)) {
 		rr.is_mbm_cntr = true;
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index fd77f4d5d718f..f94882f638cf8 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -511,7 +511,7 @@ void resctrl_offline_cpu(unsigned int cpu);
  * resctrl_arch_rmid_read() - Read the eventid counter corresponding to rmid
  *			      for this resource and domain.
  * @r:			resource that the counter should be read from.
- * @d:			domain that the counter should be read from.
+ * @hdr:		Header of domain that the counter should be read from.
  * @closid:		closid that matches the rmid. Depending on the architecture, the
  *			counter may match traffic of both @closid and @rmid, or @rmid
  *			only.
@@ -532,7 +532,7 @@ void resctrl_offline_cpu(unsigned int cpu);
  * Return:
  * 0 on success, or -EIO, -EINVAL etc on error.
  */
-int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
+int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain_hdr *hdr,
 			   u32 closid, u32 rmid, enum resctrl_event_id eventid,
 			   u64 *val, void *arch_mon_ctx);
 

From a8e874f633d864f660697277549dddbc6b267d1a Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 17 Dec 2025 09:20:55 -0800
Subject: [PATCH 123/236] x86,fs/resctrl: Rename struct rdt_mon_domain and
 rdt_hw_mon_domain

commit 4bc3ef46ff41d5e7ba557e56e9cd2031527cd7f8 upstream.

The upcoming telemetry event monitoring is not tied to the L3 resource and
will have a new domain structure.

Rename the L3 resource specific domain data structures to include "l3_"
in their names to avoid confusion between the different resource specific
domain structures:
rdt_mon_domain		-> rdt_l3_mon_domain
rdt_hw_mon_domain	-> rdt_hw_l3_mon_domain

No functional change.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com

 Conflicts:
	fs/resctrl/monitor.c
[jz: resolve context conflicts]
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c     | 14 +++----
 arch/x86/kernel/cpu/resctrl/internal.h | 16 ++++----
 arch/x86/kernel/cpu/resctrl/monitor.c  | 36 +++++++++---------
 fs/resctrl/ctrlmondata.c               |  2 +-
 fs/resctrl/internal.h                  |  8 ++--
 fs/resctrl/monitor.c                   | 52 +++++++++++++-------------
 fs/resctrl/rdtgroup.c                  | 40 ++++++++++----------
 include/linux/resctrl.h                | 22 +++++------
 8 files changed, 95 insertions(+), 95 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 48fb106681c1b..62148cba9ed5f 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -362,7 +362,7 @@ static void ctrl_domain_free(struct rdt_hw_ctrl_domain *hw_dom)
 	kfree(hw_dom);
 }
 
-static void mon_domain_free(struct rdt_hw_mon_domain *hw_dom)
+static void mon_domain_free(struct rdt_hw_l3_mon_domain *hw_dom)
 {
 	int idx;
 
@@ -399,7 +399,7 @@ static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_ctrl_domain *
  * @num_rmid:	The size of the MBM counter array
  * @hw_dom:	The domain that owns the allocated arrays
  */
-static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_mon_domain *hw_dom)
+static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_l3_mon_domain *hw_dom)
 {
 	size_t tsize = sizeof(*hw_dom->arch_mbm_states[0]);
 	enum resctrl_event_id eventid;
@@ -497,8 +497,8 @@ static void domain_add_cpu_ctrl(int cpu, struct rdt_resource *r)
 
 static void l3_mon_domain_setup(int cpu, int id, struct rdt_resource *r, struct list_head *add_pos)
 {
-	struct rdt_hw_mon_domain *hw_dom;
-	struct rdt_mon_domain *d;
+	struct rdt_hw_l3_mon_domain *hw_dom;
+	struct rdt_l3_mon_domain *d;
 	struct cacheinfo *ci;
 	int err;
 
@@ -647,13 +647,13 @@ static void domain_remove_cpu_mon(int cpu, struct rdt_resource *r)
 
 	switch (r->rid) {
 	case RDT_RESOURCE_L3: {
-		struct rdt_hw_mon_domain *hw_dom;
-		struct rdt_mon_domain *d;
+		struct rdt_hw_l3_mon_domain *hw_dom;
+		struct rdt_l3_mon_domain *d;
 
 		if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3))
 			return;
 
-		d = container_of(hdr, struct rdt_mon_domain, hdr);
+		d = container_of(hdr, struct rdt_l3_mon_domain, hdr);
 		hw_dom = resctrl_to_arch_mon_dom(d);
 		resctrl_offline_mon_domain(r, hdr);
 		list_del_rcu(&hdr->list);
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 6da9bd1a188b9..5b3ccebdd39c9 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -63,17 +63,17 @@ struct rdt_hw_ctrl_domain {
 };
 
 /**
- * struct rdt_hw_mon_domain - Arch private attributes of a set of CPUs that share
- *			      a resource for a monitor function
- * @d_resctrl:	Properties exposed to the resctrl file system
+ * struct rdt_hw_l3_mon_domain - Arch private attributes of a set of CPUs sharing
+ *				 RDT_RESOURCE_L3 monitoring
+ * @d_resctrl:		Properties exposed to the resctrl file system
  * @arch_mbm_states:	Per-event pointer to the MBM event's saved state.
  *			An MBM event's state is an array of struct arch_mbm_state
  *			indexed by RMID on x86.
  *
  * Members of this structure are accessed via helpers that provide abstraction.
  */
-struct rdt_hw_mon_domain {
-	struct rdt_mon_domain		d_resctrl;
+struct rdt_hw_l3_mon_domain {
+	struct rdt_l3_mon_domain	d_resctrl;
 	struct arch_mbm_state		*arch_mbm_states[QOS_NUM_L3_MBM_EVENTS];
 };
 
@@ -82,9 +82,9 @@ static inline struct rdt_hw_ctrl_domain *resctrl_to_arch_ctrl_dom(struct rdt_ctr
 	return container_of(r, struct rdt_hw_ctrl_domain, d_resctrl);
 }
 
-static inline struct rdt_hw_mon_domain *resctrl_to_arch_mon_dom(struct rdt_mon_domain *r)
+static inline struct rdt_hw_l3_mon_domain *resctrl_to_arch_mon_dom(struct rdt_l3_mon_domain *r)
 {
-	return container_of(r, struct rdt_hw_mon_domain, d_resctrl);
+	return container_of(r, struct rdt_hw_l3_mon_domain, d_resctrl);
 }
 
 /**
@@ -138,7 +138,7 @@ static inline struct rdt_hw_resource *resctrl_to_arch_res(struct rdt_resource *r
 
 extern struct rdt_hw_resource rdt_resources_all[];
 
-void arch_mon_domain_online(struct rdt_resource *r, struct rdt_mon_domain *d);
+void arch_mon_domain_online(struct rdt_resource *r, struct rdt_l3_mon_domain *d);
 
 /* CPUID.(EAX=10H, ECX=ResID=1).EAX */
 union cpuid_0x10_1_eax {
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 9b946c92943ab..d304e9f738d9e 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -108,7 +108,7 @@ static inline u64 get_corrected_mbm_count(u32 rmid, unsigned long val)
  *
  * In RMID sharing mode there are fewer "logical RMID" values available
  * to accumulate data ("physical RMIDs" are divided evenly between SNC
- * nodes that share an L3 cache). Linux creates an rdt_mon_domain for
+ * nodes that share an L3 cache). Linux creates an rdt_l3_mon_domain for
  * each SNC node.
  *
  * The value loaded into IA32_PQR_ASSOC is the "logical RMID".
@@ -156,7 +156,7 @@ static int __rmid_read_phys(u32 prmid, enum resctrl_event_id eventid, u64 *val)
 	return 0;
 }
 
-static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_mon_domain *hw_dom,
+static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_l3_mon_domain *hw_dom,
 						 u32 rmid,
 						 enum resctrl_event_id eventid)
 {
@@ -170,11 +170,11 @@ static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_mon_domain *hw_do
 	return state ? &state[rmid] : NULL;
 }
 
-void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d,
+void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_l3_mon_domain *d,
 			     u32 unused, u32 rmid,
 			     enum resctrl_event_id eventid)
 {
-	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
+	struct rdt_hw_l3_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
 	int cpu = cpumask_any(&d->hdr.cpu_mask);
 	struct arch_mbm_state *am;
 	u32 prmid;
@@ -193,9 +193,9 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d,
  * Assumes that hardware counters are also reset and thus that there is
  * no need to record initial non-zero counts.
  */
-void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d)
+void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_l3_mon_domain *d)
 {
-	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
+	struct rdt_hw_l3_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
 	enum resctrl_event_id eventid;
 	int idx;
 
@@ -216,10 +216,10 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
 	return chunks >> shift;
 }
 
-static u64 get_corrected_val(struct rdt_resource *r, struct rdt_mon_domain *d,
+static u64 get_corrected_val(struct rdt_resource *r, struct rdt_l3_mon_domain *d,
 			     u32 rmid, enum resctrl_event_id eventid, u64 msr_val)
 {
-	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
+	struct rdt_hw_l3_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 	struct arch_mbm_state *am;
 	u64 chunks;
@@ -241,9 +241,9 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain_hdr *hdr,
 			   u32 unused, u32 rmid, enum resctrl_event_id eventid,
 			   u64 *val, void *ignored)
 {
-	struct rdt_hw_mon_domain *hw_dom;
+	struct rdt_hw_l3_mon_domain *hw_dom;
+	struct rdt_l3_mon_domain *d;
 	struct arch_mbm_state *am;
-	struct rdt_mon_domain *d;
 	u64 msr_val;
 	u32 prmid;
 	int cpu;
@@ -253,7 +253,7 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain_hdr *hdr,
 	if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3))
 		return -EINVAL;
 
-	d = container_of(hdr, struct rdt_mon_domain, hdr);
+	d = container_of(hdr, struct rdt_l3_mon_domain, hdr);
 	hw_dom = resctrl_to_arch_mon_dom(d);
 	cpu = cpumask_any(&hdr->cpu_mask);
 	prmid = logical_rmid_to_physical_rmid(cpu, rmid);
@@ -307,11 +307,11 @@ static int __cntr_id_read(u32 cntr_id, u64 *val)
 	return 0;
 }
 
-void resctrl_arch_reset_cntr(struct rdt_resource *r, struct rdt_mon_domain *d,
+void resctrl_arch_reset_cntr(struct rdt_resource *r, struct rdt_l3_mon_domain *d,
 			     u32 unused, u32 rmid, int cntr_id,
 			     enum resctrl_event_id eventid)
 {
-	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
+	struct rdt_hw_l3_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
 	struct arch_mbm_state *am;
 
 	am = get_arch_mbm_state(hw_dom, rmid, eventid);
@@ -323,7 +323,7 @@ void resctrl_arch_reset_cntr(struct rdt_resource *r, struct rdt_mon_domain *d,
 	}
 }
 
-int resctrl_arch_cntr_read(struct rdt_resource *r, struct rdt_mon_domain *d,
+int resctrl_arch_cntr_read(struct rdt_resource *r, struct rdt_l3_mon_domain *d,
 			   u32 unused, u32 rmid, int cntr_id,
 			   enum resctrl_event_id eventid, u64 *val)
 {
@@ -353,7 +353,7 @@ int resctrl_arch_cntr_read(struct rdt_resource *r, struct rdt_mon_domain *d,
  * must adjust RMID counter numbers based on SNC node. See
  * logical_rmid_to_physical_rmid() for code that does this.
  */
-void arch_mon_domain_online(struct rdt_resource *r, struct rdt_mon_domain *d)
+void arch_mon_domain_online(struct rdt_resource *r, struct rdt_l3_mon_domain *d)
 {
 	if (snc_nodes_per_l3_cache > 1)
 		msr_clear_bit(MSR_RMID_SNC_CONFIG, 0);
@@ -515,7 +515,7 @@ static void resctrl_abmc_set_one_amd(void *arg)
  */
 static void _resctrl_abmc_enable(struct rdt_resource *r, bool enable)
 {
-	struct rdt_mon_domain *d;
+	struct rdt_l3_mon_domain *d;
 
 	lockdep_assert_cpus_held();
 
@@ -554,11 +554,11 @@ static void resctrl_abmc_config_one_amd(void *info)
 /*
  * Send an IPI to the domain to assign the counter to RMID, event pair.
  */
-void resctrl_arch_config_cntr(struct rdt_resource *r, struct rdt_mon_domain *d,
+void resctrl_arch_config_cntr(struct rdt_resource *r, struct rdt_l3_mon_domain *d,
 			      enum resctrl_event_id evtid, u32 rmid, u32 closid,
 			      u32 cntr_id, bool assign)
 {
-	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
+	struct rdt_hw_l3_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
 	union l3_qos_abmc_cfg abmc_cfg = { 0 };
 	struct arch_mbm_state *am;
 
diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c
index ad347ab4ed292..b74c69f2d54e7 100644
--- a/fs/resctrl/ctrlmondata.c
+++ b/fs/resctrl/ctrlmondata.c
@@ -596,9 +596,9 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 	struct kernfs_open_file *of = m->private;
 	enum resctrl_res_level resid;
 	enum resctrl_event_id evtid;
+	struct rdt_l3_mon_domain *d;
 	struct rdt_domain_hdr *hdr;
 	struct rmid_read rr = {0};
-	struct rdt_mon_domain *d;
 	struct rdtgroup *rdtgrp;
 	int domid, cpu, ret = 0;
 	struct rdt_resource *r;
diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index 66a5459db2597..ee63ba4843858 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -367,7 +367,7 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 
 int resctrl_mon_resource_init(void);
 
-void mbm_setup_overflow_handler(struct rdt_mon_domain *dom,
+void mbm_setup_overflow_handler(struct rdt_l3_mon_domain *dom,
 				unsigned long delay_ms,
 				int exclude_cpu);
 
@@ -375,14 +375,14 @@ void mbm_handle_overflow(struct work_struct *work);
 
 bool is_mba_sc(struct rdt_resource *r);
 
-void cqm_setup_limbo_handler(struct rdt_mon_domain *dom, unsigned long delay_ms,
+void cqm_setup_limbo_handler(struct rdt_l3_mon_domain *dom, unsigned long delay_ms,
 			     int exclude_cpu);
 
 void cqm_handle_limbo(struct work_struct *work);
 
-bool has_busy_rmid(struct rdt_mon_domain *d);
+bool has_busy_rmid(struct rdt_l3_mon_domain *d);
 
-void __check_limbo(struct rdt_mon_domain *d, bool force_free);
+void __check_limbo(struct rdt_l3_mon_domain *d, bool force_free);
 
 void resctrl_file_fflags_init(const char *config, unsigned long fflags);
 
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index 9e073eb8cef7b..a1b0847c5db29 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -130,7 +130,7 @@ static void limbo_release_entry(struct rmid_entry *entry)
  * decrement the count. If the busy count gets to zero on an RMID, we
  * free the RMID
  */
-void __check_limbo(struct rdt_mon_domain *d, bool force_free)
+void __check_limbo(struct rdt_l3_mon_domain *d, bool force_free)
 {
 	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
 	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
@@ -188,7 +188,7 @@ void __check_limbo(struct rdt_mon_domain *d, bool force_free)
 	resctrl_arch_mon_ctx_free(r, QOS_L3_OCCUP_EVENT_ID, arch_mon_ctx);
 }
 
-bool has_busy_rmid(struct rdt_mon_domain *d)
+bool has_busy_rmid(struct rdt_l3_mon_domain *d)
 {
 	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
 
@@ -289,7 +289,7 @@ int alloc_rmid(u32 closid)
 static void add_rmid_to_limbo(struct rmid_entry *entry)
 {
 	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
-	struct rdt_mon_domain *d;
+	struct rdt_l3_mon_domain *d;
 	u32 idx;
 
 	lockdep_assert_held(&rdtgroup_mutex);
@@ -342,7 +342,7 @@ void free_rmid(u32 closid, u32 rmid)
 		list_add_tail(&entry->list, &rmid_free_lru);
 }
 
-static struct mbm_state *get_mbm_state(struct rdt_mon_domain *d, u32 closid,
+static struct mbm_state *get_mbm_state(struct rdt_l3_mon_domain *d, u32 closid,
 				       u32 rmid, enum resctrl_event_id evtid)
 {
 	u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid);
@@ -362,7 +362,7 @@ static struct mbm_state *get_mbm_state(struct rdt_mon_domain *d, u32 closid,
  * Return:
  * Valid counter ID on success, or -ENOENT on failure.
  */
-static int mbm_cntr_get(struct rdt_resource *r, struct rdt_mon_domain *d,
+static int mbm_cntr_get(struct rdt_resource *r, struct rdt_l3_mon_domain *d,
 			struct rdtgroup *rdtgrp, enum resctrl_event_id evtid)
 {
 	int cntr_id;
@@ -389,7 +389,7 @@ static int mbm_cntr_get(struct rdt_resource *r, struct rdt_mon_domain *d,
  * Return:
  * Valid counter ID on success, or -ENOSPC on failure.
  */
-static int mbm_cntr_alloc(struct rdt_resource *r, struct rdt_mon_domain *d,
+static int mbm_cntr_alloc(struct rdt_resource *r, struct rdt_l3_mon_domain *d,
 			  struct rdtgroup *rdtgrp, enum resctrl_event_id evtid)
 {
 	int cntr_id;
@@ -408,7 +408,7 @@ static int mbm_cntr_alloc(struct rdt_resource *r, struct rdt_mon_domain *d,
 /*
  * mbm_cntr_free() - Clear the counter ID configuration details in the domain @d.
  */
-static void mbm_cntr_free(struct rdt_mon_domain *d, int cntr_id)
+static void mbm_cntr_free(struct rdt_l3_mon_domain *d, int cntr_id)
 {
 	memset(&d->cntr_cfg[cntr_id], 0, sizeof(*d->cntr_cfg));
 }
@@ -418,7 +418,7 @@ static int __l3_mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
 	int cpu = smp_processor_id();
 	u32 closid = rdtgrp->closid;
 	u32 rmid = rdtgrp->mon.rmid;
-	struct rdt_mon_domain *d;
+	struct rdt_l3_mon_domain *d;
 	int cntr_id = -ENOENT;
 	struct mbm_state *m;
 	u64 tval = 0;
@@ -427,7 +427,7 @@ static int __l3_mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
 		rr->err = -EIO;
 		return -EINVAL;
 	}
-	d = container_of(rr->hdr, struct rdt_mon_domain, hdr);
+	d = container_of(rr->hdr, struct rdt_l3_mon_domain, hdr);
 
 	if (rr->is_mbm_cntr) {
 		cntr_id = mbm_cntr_get(rr->r, d, rdtgrp, rr->evtid);
@@ -470,7 +470,7 @@ static int __l3_mon_event_count_sum(struct rdtgroup *rdtgrp, struct rmid_read *r
 	int cpu = smp_processor_id();
 	u32 closid = rdtgrp->closid;
 	u32 rmid = rdtgrp->mon.rmid;
-	struct rdt_mon_domain *d;
+	struct rdt_l3_mon_domain *d;
 	u64 tval = 0;
 	int err, ret;
 
@@ -545,12 +545,12 @@ static void mbm_bw_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
 	u64 cur_bw, bytes, cur_bytes;
 	u32 closid = rdtgrp->closid;
 	u32 rmid = rdtgrp->mon.rmid;
-	struct rdt_mon_domain *d;
+	struct rdt_l3_mon_domain *d;
 	struct mbm_state *m;
 
 	if (!domain_header_is_valid(rr->hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3))
 		return;
-	d = container_of(rr->hdr, struct rdt_mon_domain, hdr);
+	d = container_of(rr->hdr, struct rdt_l3_mon_domain, hdr);
 	m = get_mbm_state(d, closid, rmid, rr->evtid);
 	if (WARN_ON_ONCE(!m))
 		return;
@@ -650,7 +650,7 @@ static struct rdt_ctrl_domain *get_ctrl_domain_from_cpu(int cpu,
  * throttle MSRs already have low percentage values.  To avoid
  * unnecessarily restricting such rdtgroups, we also increase the bandwidth.
  */
-static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm)
+static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_l3_mon_domain *dom_mbm)
 {
 	u32 closid, rmid, cur_msr_val, new_msr_val;
 	struct mbm_state *pmbm_data, *cmbm_data;
@@ -718,7 +718,7 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm)
 	resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val);
 }
 
-static void mbm_update_one_event(struct rdt_resource *r, struct rdt_mon_domain *d,
+static void mbm_update_one_event(struct rdt_resource *r, struct rdt_l3_mon_domain *d,
 				 struct rdtgroup *rdtgrp, enum resctrl_event_id evtid)
 {
 	struct rmid_read rr = {0};
@@ -750,7 +750,7 @@ static void mbm_update_one_event(struct rdt_resource *r, struct rdt_mon_domain *
 		resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
 }
 
-static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d,
+static void mbm_update(struct rdt_resource *r, struct rdt_l3_mon_domain *d,
 		       struct rdtgroup *rdtgrp)
 {
 	/*
@@ -771,12 +771,12 @@ static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d,
 void cqm_handle_limbo(struct work_struct *work)
 {
 	unsigned long delay = msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL);
-	struct rdt_mon_domain *d;
+	struct rdt_l3_mon_domain *d;
 
 	cpus_read_lock();
 	mutex_lock(&rdtgroup_mutex);
 
-	d = container_of(work, struct rdt_mon_domain, cqm_limbo.work);
+	d = container_of(work, struct rdt_l3_mon_domain, cqm_limbo.work);
 
 	__check_limbo(d, false);
 
@@ -799,7 +799,7 @@ void cqm_handle_limbo(struct work_struct *work)
  * @exclude_cpu:   Which CPU the handler should not run on,
  *		   RESCTRL_PICK_ANY_CPU to pick any CPU.
  */
-void cqm_setup_limbo_handler(struct rdt_mon_domain *dom, unsigned long delay_ms,
+void cqm_setup_limbo_handler(struct rdt_l3_mon_domain *dom, unsigned long delay_ms,
 			     int exclude_cpu)
 {
 	unsigned long delay = msecs_to_jiffies(delay_ms);
@@ -816,7 +816,7 @@ void mbm_handle_overflow(struct work_struct *work)
 {
 	unsigned long delay = msecs_to_jiffies(MBM_OVERFLOW_INTERVAL);
 	struct rdtgroup *prgrp, *crgrp;
-	struct rdt_mon_domain *d;
+	struct rdt_l3_mon_domain *d;
 	struct list_head *head;
 	struct rdt_resource *r;
 
@@ -831,7 +831,7 @@ void mbm_handle_overflow(struct work_struct *work)
 		goto out_unlock;
 
 	r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
-	d = container_of(work, struct rdt_mon_domain, mbm_over.work);
+	d = container_of(work, struct rdt_l3_mon_domain, mbm_over.work);
 
 	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
 		mbm_update(r, d, prgrp);
@@ -865,7 +865,7 @@ void mbm_handle_overflow(struct work_struct *work)
  * @exclude_cpu:   Which CPU the handler should not run on,
  *		   RESCTRL_PICK_ANY_CPU to pick any CPU.
  */
-void mbm_setup_overflow_handler(struct rdt_mon_domain *dom, unsigned long delay_ms,
+void mbm_setup_overflow_handler(struct rdt_l3_mon_domain *dom, unsigned long delay_ms,
 				int exclude_cpu)
 {
 	unsigned long delay = msecs_to_jiffies(delay_ms);
@@ -1017,7 +1017,7 @@ u32 resctrl_get_mon_evt_cfg(enum resctrl_event_id evtid)
  * Assign the counter if @assign is true else unassign the counter. Reset the
  * associated non-architectural state.
  */
-static void rdtgroup_assign_cntr(struct rdt_resource *r, struct rdt_mon_domain *d,
+static void rdtgroup_assign_cntr(struct rdt_resource *r, struct rdt_l3_mon_domain *d,
 				 enum resctrl_event_id evtid, u32 rmid, u32 closid,
 				 u32 cntr_id, bool assign)
 {
@@ -1037,7 +1037,7 @@ static void rdtgroup_assign_cntr(struct rdt_resource *r, struct rdt_mon_domain *
  * Return:
  * 0 on success, < 0 on failure.
  */
-static int rdtgroup_alloc_assign_cntr(struct rdt_resource *r, struct rdt_mon_domain *d,
+static int rdtgroup_alloc_assign_cntr(struct rdt_resource *r, struct rdt_l3_mon_domain *d,
 				      struct rdtgroup *rdtgrp, struct mon_evt *mevt)
 {
 	int cntr_id;
@@ -1072,7 +1072,7 @@ static int rdtgroup_alloc_assign_cntr(struct rdt_resource *r, struct rdt_mon_dom
  * Return:
  * 0 on success, < 0 on failure.
  */
-static int rdtgroup_assign_cntr_event(struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
+static int rdtgroup_assign_cntr_event(struct rdt_l3_mon_domain *d, struct rdtgroup *rdtgrp,
 				      struct mon_evt *mevt)
 {
 	struct rdt_resource *r = resctrl_arch_get_resource(mevt->rid);
@@ -1121,7 +1121,7 @@ void rdtgroup_assign_cntrs(struct rdtgroup *rdtgrp)
  * rdtgroup_free_unassign_cntr() - Unassign and reset the counter ID configuration
  * for the event pointed to by @mevt within the domain @d and resctrl group @rdtgrp.
  */
-static void rdtgroup_free_unassign_cntr(struct rdt_resource *r, struct rdt_mon_domain *d,
+static void rdtgroup_free_unassign_cntr(struct rdt_resource *r, struct rdt_l3_mon_domain *d,
 					struct rdtgroup *rdtgrp, struct mon_evt *mevt)
 {
 	int cntr_id;
@@ -1142,7 +1142,7 @@ static void rdtgroup_free_unassign_cntr(struct rdt_resource *r, struct rdt_mon_d
  * the event structure @mevt from the domain @d and the group @rdtgrp. Unassign
  * the counters from all the domains if @d is NULL else unassign from @d.
  */
-static void rdtgroup_unassign_cntr_event(struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
+static void rdtgroup_unassign_cntr_event(struct rdt_l3_mon_domain *d, struct rdtgroup *rdtgrp,
 					 struct mon_evt *mevt)
 {
 	struct rdt_resource *r = resctrl_arch_get_resource(mevt->rid);
diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index 4d5f0fd861ef4..4546f43303a10 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -1617,7 +1617,7 @@ static void mondata_config_read(struct resctrl_mon_config_info *mon_info)
 static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid)
 {
 	struct resctrl_mon_config_info mon_info;
-	struct rdt_mon_domain *dom;
+	struct rdt_l3_mon_domain *dom;
 	bool sep = false;
 
 	cpus_read_lock();
@@ -1665,7 +1665,7 @@ static int mbm_local_bytes_config_show(struct kernfs_open_file *of,
 }
 
 static void mbm_config_write_domain(struct rdt_resource *r,
-				    struct rdt_mon_domain *d, u32 evtid, u32 val)
+				    struct rdt_l3_mon_domain *d, u32 evtid, u32 val)
 {
 	struct resctrl_mon_config_info mon_info = {0};
 
@@ -1706,8 +1706,8 @@ static void mbm_config_write_domain(struct rdt_resource *r,
 static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid)
 {
 	char *dom_str = NULL, *id_str;
+	struct rdt_l3_mon_domain *d;
 	unsigned long dom_id, val;
-	struct rdt_mon_domain *d;
 
 	/* Walking r->domains, ensure it can't race with cpuhp */
 	lockdep_assert_cpus_held();
@@ -2581,7 +2581,7 @@ static int rdt_get_tree(struct fs_context *fc)
 {
 	struct rdt_fs_context *ctx = rdt_fc2context(fc);
 	unsigned long flags = RFTYPE_CTRL_BASE;
-	struct rdt_mon_domain *dom;
+	struct rdt_l3_mon_domain *dom;
 	struct rdt_resource *r;
 	int ret;
 
@@ -3024,7 +3024,7 @@ static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
 					   struct rdt_domain_hdr *hdr)
 {
 	struct rdtgroup *prgrp, *crgrp;
-	struct rdt_mon_domain *d;
+	struct rdt_l3_mon_domain *d;
 	char subname[32];
 	bool snc_mode;
 	char name[32];
@@ -3032,7 +3032,7 @@ static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
 	if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3))
 		return;
 
-	d = container_of(hdr, struct rdt_mon_domain, hdr);
+	d = container_of(hdr, struct rdt_l3_mon_domain, hdr);
 	snc_mode = r->mon_scope == RESCTRL_L3_NODE;
 	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci_id : hdr->id);
 	if (snc_mode)
@@ -3050,8 +3050,8 @@ static int mon_add_all_files(struct kernfs_node *kn, struct rdt_domain_hdr *hdr,
 			     struct rdt_resource *r, struct rdtgroup *prgrp,
 			     bool do_sum)
 {
+	struct rdt_l3_mon_domain *d;
 	struct rmid_read rr = {0};
-	struct rdt_mon_domain *d;
 	struct mon_data *priv;
 	struct mon_evt *mevt;
 	int ret, domid;
@@ -3059,7 +3059,7 @@ static int mon_add_all_files(struct kernfs_node *kn, struct rdt_domain_hdr *hdr,
 	if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3))
 		return -EINVAL;
 
-	d = container_of(hdr, struct rdt_mon_domain, hdr);
+	d = container_of(hdr, struct rdt_l3_mon_domain, hdr);
 	for_each_mon_event(mevt) {
 		if (mevt->rid != r->rid || !mevt->enabled)
 			continue;
@@ -3084,7 +3084,7 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
 				struct rdt_resource *r, struct rdtgroup *prgrp)
 {
 	struct kernfs_node *kn, *ckn;
-	struct rdt_mon_domain *d;
+	struct rdt_l3_mon_domain *d;
 	char name[32];
 	bool snc_mode;
 	int ret = 0;
@@ -3094,7 +3094,7 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
 	if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3))
 		return -EINVAL;
 
-	d = container_of(hdr, struct rdt_mon_domain, hdr);
+	d = container_of(hdr, struct rdt_l3_mon_domain, hdr);
 	snc_mode = r->mon_scope == RESCTRL_L3_NODE;
 	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci_id : d->hdr.id);
 	kn = kernfs_find_and_get(parent_kn, name);
@@ -4028,7 +4028,7 @@ static void rdtgroup_setup_default(void)
 	mutex_unlock(&rdtgroup_mutex);
 }
 
-static void domain_destroy_mon_state(struct rdt_mon_domain *d)
+static void domain_destroy_mon_state(struct rdt_l3_mon_domain *d)
 {
 	int idx;
 
@@ -4052,14 +4052,14 @@ void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain
 
 void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_domain_hdr *hdr)
 {
-	struct rdt_mon_domain *d;
+	struct rdt_l3_mon_domain *d;
 
 	mutex_lock(&rdtgroup_mutex);
 
 	if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3))
 		goto out_unlock;
 
-	d = container_of(hdr, struct rdt_mon_domain, hdr);
+	d = container_of(hdr, struct rdt_l3_mon_domain, hdr);
 
 	/*
 	 * If resctrl is mounted, remove all the
@@ -4101,7 +4101,7 @@ void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_domain_hdr *h
  *
  * Returns 0 for success, or -ENOMEM.
  */
-static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_mon_domain *d)
+static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_l3_mon_domain *d)
 {
 	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
 	size_t tsize = sizeof(*d->mbm_states[0]);
@@ -4159,7 +4159,7 @@ int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d
 
 int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_domain_hdr *hdr)
 {
-	struct rdt_mon_domain *d;
+	struct rdt_l3_mon_domain *d;
 	int err = -EINVAL;
 
 	mutex_lock(&rdtgroup_mutex);
@@ -4167,7 +4167,7 @@ int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_domain_hdr *hdr
 	if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3))
 		goto out_unlock;
 
-	d = container_of(hdr, struct rdt_mon_domain, hdr);
+	d = container_of(hdr, struct rdt_l3_mon_domain, hdr);
 	err = domain_setup_mon_state(r, d);
 	if (err)
 		goto out_unlock;
@@ -4214,10 +4214,10 @@ static void clear_childcpus(struct rdtgroup *r, unsigned int cpu)
 	}
 }
 
-static struct rdt_mon_domain *get_mon_domain_from_cpu(int cpu,
-						      struct rdt_resource *r)
+static struct rdt_l3_mon_domain *get_mon_domain_from_cpu(int cpu,
+							 struct rdt_resource *r)
 {
-	struct rdt_mon_domain *d;
+	struct rdt_l3_mon_domain *d;
 
 	lockdep_assert_cpus_held();
 
@@ -4233,7 +4233,7 @@ static struct rdt_mon_domain *get_mon_domain_from_cpu(int cpu,
 void resctrl_offline_cpu(unsigned int cpu)
 {
 	struct rdt_resource *l3 = resctrl_arch_get_resource(RDT_RESOURCE_L3);
-	struct rdt_mon_domain *d;
+	struct rdt_l3_mon_domain *d;
 	struct rdtgroup *rdtgrp;
 
 	mutex_lock(&rdtgroup_mutex);
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index f94882f638cf8..28ea47119692b 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -178,7 +178,7 @@ struct mbm_cntr_cfg {
 };
 
 /**
- * struct rdt_mon_domain - group of CPUs sharing a resctrl monitor resource
+ * struct rdt_l3_mon_domain - group of CPUs sharing RDT_RESOURCE_L3 monitoring
  * @hdr:		common header for different domain types
  * @ci_id:		cache info id for this domain
  * @rmid_busy_llc:	bitmap of which limbo RMIDs are above threshold
@@ -192,7 +192,7 @@ struct mbm_cntr_cfg {
  * @cntr_cfg:		array of assignable counters' configuration (indexed
  *			by counter ID)
  */
-struct rdt_mon_domain {
+struct rdt_l3_mon_domain {
 	struct rdt_domain_hdr		hdr;
 	unsigned int			ci_id;
 	unsigned long			*rmid_busy_llc;
@@ -361,10 +361,10 @@ struct resctrl_cpu_defaults {
 };
 
 struct resctrl_mon_config_info {
-	struct rdt_resource	*r;
-	struct rdt_mon_domain	*d;
-	u32			evtid;
-	u32			mon_config;
+	struct rdt_resource		*r;
+	struct rdt_l3_mon_domain	*d;
+	u32				evtid;
+	u32				mon_config;
 };
 
 /**
@@ -579,7 +579,7 @@ struct rdt_domain_hdr *resctrl_find_domain(struct list_head *h, int id,
  *
  * This can be called from any CPU.
  */
-void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d,
+void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_l3_mon_domain *d,
 			     u32 closid, u32 rmid,
 			     enum resctrl_event_id eventid);
 
@@ -592,7 +592,7 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d,
  *
  * This can be called from any CPU.
  */
-void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d);
+void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_l3_mon_domain *d);
 
 /**
  * resctrl_arch_reset_all_ctrls() - Reset the control for each CLOSID to its
@@ -618,7 +618,7 @@ void resctrl_arch_reset_all_ctrls(struct rdt_resource *r);
  *
  * This can be called from any CPU.
  */
-void resctrl_arch_config_cntr(struct rdt_resource *r, struct rdt_mon_domain *d,
+void resctrl_arch_config_cntr(struct rdt_resource *r, struct rdt_l3_mon_domain *d,
 			      enum resctrl_event_id evtid, u32 rmid, u32 closid,
 			      u32 cntr_id, bool assign);
 
@@ -641,7 +641,7 @@ void resctrl_arch_config_cntr(struct rdt_resource *r, struct rdt_mon_domain *d,
  * Return:
  * 0 on success, or -EIO, -EINVAL etc on error.
  */
-int resctrl_arch_cntr_read(struct rdt_resource *r, struct rdt_mon_domain *d,
+int resctrl_arch_cntr_read(struct rdt_resource *r, struct rdt_l3_mon_domain *d,
 			   u32 closid, u32 rmid, int cntr_id,
 			   enum resctrl_event_id eventid, u64 *val);
 
@@ -656,7 +656,7 @@ int resctrl_arch_cntr_read(struct rdt_resource *r, struct rdt_mon_domain *d,
  *
  * This can be called from any CPU.
  */
-void resctrl_arch_reset_cntr(struct rdt_resource *r, struct rdt_mon_domain *d,
+void resctrl_arch_reset_cntr(struct rdt_resource *r, struct rdt_l3_mon_domain *d,
 			     u32 closid, u32 rmid, int cntr_id,
 			     enum resctrl_event_id eventid);
 

From fd32fef68c3e3f1a8b5e6b6c035e2074e6dc3d0e Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 17 Dec 2025 09:20:56 -0800
Subject: [PATCH 124/236] x86,fs/resctrl: Rename some L3 specific functions

commit 9c214d10c50990c7a61b95887493df9ae713eec5 upstream.

With the arrival of monitor events tied to new domains associated with a
different resource it would be clearer if the L3 resource specific functions
are more accurately named.

Rename three groups of functions:

Functions that allocate/free architecture per-RMID MBM state information:
arch_domain_mbm_alloc()		-> l3_mon_domain_mbm_alloc()
mon_domain_free()		-> l3_mon_domain_free()

Functions that allocate/free filesystem per-RMID MBM state information:
domain_setup_mon_state()	-> domain_setup_l3_mon_state()
domain_destroy_mon_state()	-> domain_destroy_l3_mon_state()

Initialization/exit:
rdt_get_mon_l3_config()		-> rdt_get_l3_mon_config()
resctrl_mon_resource_init()	-> resctrl_l3_mon_resource_init()
resctrl_mon_resource_exit()	-> resctrl_l3_mon_resource_exit()

Ensure kernel-doc descriptions of these functions' return values are present
and correctly formatted.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com

 Conflicts:
	fs/resctrl/rdtgroup.c
[jz: resolve context conflicts]
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c     | 20 +++++++++++---------
 arch/x86/kernel/cpu/resctrl/internal.h |  2 +-
 arch/x86/kernel/cpu/resctrl/monitor.c  |  2 +-
 fs/resctrl/internal.h                  |  6 +++---
 fs/resctrl/monitor.c                   |  8 ++++----
 fs/resctrl/rdtgroup.c                  | 24 ++++++++++++------------
 6 files changed, 32 insertions(+), 30 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 62148cba9ed5f..9febdb41de382 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -362,7 +362,7 @@ static void ctrl_domain_free(struct rdt_hw_ctrl_domain *hw_dom)
 	kfree(hw_dom);
 }
 
-static void mon_domain_free(struct rdt_hw_l3_mon_domain *hw_dom)
+static void l3_mon_domain_free(struct rdt_hw_l3_mon_domain *hw_dom)
 {
 	int idx;
 
@@ -395,11 +395,13 @@ static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_ctrl_domain *
 }
 
 /**
- * arch_domain_mbm_alloc() - Allocate arch private storage for the MBM counters
+ * l3_mon_domain_mbm_alloc() - Allocate arch private storage for the MBM counters
  * @num_rmid:	The size of the MBM counter array
  * @hw_dom:	The domain that owns the allocated arrays
+ *
+ * Return:	0 for success, or -ENOMEM.
  */
-static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_l3_mon_domain *hw_dom)
+static int l3_mon_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_l3_mon_domain *hw_dom)
 {
 	size_t tsize = sizeof(*hw_dom->arch_mbm_states[0]);
 	enum resctrl_event_id eventid;
@@ -513,7 +515,7 @@ static void l3_mon_domain_setup(int cpu, int id, struct rdt_resource *r, struct
 	ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
 	if (!ci) {
 		pr_warn_once("Can't find L3 cache for CPU:%d resource %s\n", cpu, r->name);
-		mon_domain_free(hw_dom);
+		l3_mon_domain_free(hw_dom);
 		return;
 	}
 	d->ci_id = ci->id;
@@ -521,8 +523,8 @@ static void l3_mon_domain_setup(int cpu, int id, struct rdt_resource *r, struct
 
 	arch_mon_domain_online(r, d);
 
-	if (arch_domain_mbm_alloc(r->mon.num_rmid, hw_dom)) {
-		mon_domain_free(hw_dom);
+	if (l3_mon_domain_mbm_alloc(r->mon.num_rmid, hw_dom)) {
+		l3_mon_domain_free(hw_dom);
 		return;
 	}
 
@@ -532,7 +534,7 @@ static void l3_mon_domain_setup(int cpu, int id, struct rdt_resource *r, struct
 	if (err) {
 		list_del_rcu(&d->hdr.list);
 		synchronize_rcu();
-		mon_domain_free(hw_dom);
+		l3_mon_domain_free(hw_dom);
 	}
 }
 
@@ -658,7 +660,7 @@ static void domain_remove_cpu_mon(int cpu, struct rdt_resource *r)
 		resctrl_offline_mon_domain(r, hdr);
 		list_del_rcu(&hdr->list);
 		synchronize_rcu();
-		mon_domain_free(hw_dom);
+		l3_mon_domain_free(hw_dom);
 		break;
 	}
 	default:
@@ -906,7 +908,7 @@ static __init bool get_rdt_mon_resources(void)
 	if (!ret)
 		return false;
 
-	return !rdt_get_mon_l3_config(r);
+	return !rdt_get_l3_mon_config(r);
 }
 
 static __init void __check_quirks_intel(void)
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 5b3ccebdd39c9..6c9e75440c10e 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -211,7 +211,7 @@ union l3_qos_abmc_cfg {
 
 void rdt_ctrl_update(void *arg);
 
-int rdt_get_mon_l3_config(struct rdt_resource *r);
+int rdt_get_l3_mon_config(struct rdt_resource *r);
 
 bool rdt_cpu_has(int flag);
 
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index d304e9f738d9e..d5cecb48e8d51 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -423,7 +423,7 @@ static __init int snc_get_config(void)
 	return ret;
 }
 
-int __init rdt_get_mon_l3_config(struct rdt_resource *r)
+int __init rdt_get_l3_mon_config(struct rdt_resource *r)
 {
 	unsigned int mbm_offset = boot_cpu_data.x86_cache_mbm_width_offset;
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index ee63ba4843858..61afe626aedb3 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -355,7 +355,9 @@ int alloc_rmid(u32 closid);
 
 void free_rmid(u32 closid, u32 rmid);
 
-void resctrl_mon_resource_exit(void);
+int resctrl_l3_mon_resource_init(void);
+
+void resctrl_l3_mon_resource_exit(void);
 
 void mon_event_count(void *info);
 
@@ -365,8 +367,6 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 		    struct rdt_domain_hdr *hdr, struct rdtgroup *rdtgrp,
 		    cpumask_t *cpumask, int evtid, int first);
 
-int resctrl_mon_resource_init(void);
-
 void mbm_setup_overflow_handler(struct rdt_l3_mon_domain *dom,
 				unsigned long delay_ms,
 				int exclude_cpu);
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index a1b0847c5db29..9d814dcb11a2b 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -1176,7 +1176,7 @@ void rdtgroup_unassign_cntrs(struct rdtgroup *rdtgrp)
 }
 
 /**
- * resctrl_mon_resource_init() - Initialise global monitoring structures.
+ * resctrl_l3_mon_resource_init() - Initialise global monitoring structures.
  *
  * Allocate and initialise global monitor resources that do not belong to a
  * specific domain. i.e. the rmid_ptrs[] used for the limbo and free lists.
@@ -1185,9 +1185,9 @@ void rdtgroup_unassign_cntrs(struct rdtgroup *rdtgrp)
  * Resctrl's cpuhp callbacks may be called before this point to bring a domain
  * online.
  *
- * Returns 0 for success, or -ENOMEM.
+ * Return: 0 for success, or -ENOMEM.
  */
-int resctrl_mon_resource_init(void)
+int resctrl_l3_mon_resource_init(void)
 {
 	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
 	int ret;
@@ -1228,7 +1228,7 @@ int resctrl_mon_resource_init(void)
 	return 0;
 }
 
-void resctrl_mon_resource_exit(void)
+void resctrl_l3_mon_resource_exit(void)
 {
 	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
 
diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index 4546f43303a10..e6ee91594a953 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -4028,7 +4028,7 @@ static void rdtgroup_setup_default(void)
 	mutex_unlock(&rdtgroup_mutex);
 }
 
-static void domain_destroy_mon_state(struct rdt_l3_mon_domain *d)
+static void domain_destroy_l3_mon_state(struct rdt_l3_mon_domain *d)
 {
 	int idx;
 
@@ -4083,13 +4083,13 @@ void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_domain_hdr *h
 		cancel_delayed_work(&d->cqm_limbo);
 	}
 
-	domain_destroy_mon_state(d);
+	domain_destroy_l3_mon_state(d);
 out_unlock:
 	mutex_unlock(&rdtgroup_mutex);
 }
 
 /**
- * domain_setup_mon_state() -  Initialise domain monitoring structures.
+ * domain_setup_l3_mon_state() -  Initialise domain monitoring structures.
  * @r:	The resource for the newly online domain.
  * @d:	The newly online domain.
  *
@@ -4097,11 +4097,11 @@ void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_domain_hdr *h
  * Called when the first CPU of a domain comes online, regardless of whether
  * the filesystem is mounted.
  * During boot this may be called before global allocations have been made by
- * resctrl_mon_resource_init().
+ * resctrl_l3_mon_resource_init().
  *
- * Returns 0 for success, or -ENOMEM.
+ * Return: 0 for success, or -ENOMEM.
  */
-static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_l3_mon_domain *d)
+static int domain_setup_l3_mon_state(struct rdt_resource *r, struct rdt_l3_mon_domain *d)
 {
 	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
 	size_t tsize = sizeof(*d->mbm_states[0]);
@@ -4168,7 +4168,7 @@ int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_domain_hdr *hdr
 		goto out_unlock;
 
 	d = container_of(hdr, struct rdt_l3_mon_domain, hdr);
-	err = domain_setup_mon_state(r, d);
+	err = domain_setup_l3_mon_state(r, d);
 	if (err)
 		goto out_unlock;
 
@@ -4283,13 +4283,13 @@ int resctrl_init(void)
 
 	thread_throttle_mode_init();
 
-	ret = resctrl_mon_resource_init();
+	ret = resctrl_l3_mon_resource_init();
 	if (ret)
 		return ret;
 
 	ret = sysfs_create_mount_point(fs_kobj, "resctrl");
 	if (ret) {
-		resctrl_mon_resource_exit();
+		resctrl_l3_mon_resource_exit();
 		return ret;
 	}
 
@@ -4324,7 +4324,7 @@ int resctrl_init(void)
 
 cleanup_mountpoint:
 	sysfs_remove_mount_point(fs_kobj, "resctrl");
-	resctrl_mon_resource_exit();
+	resctrl_l3_mon_resource_exit();
 
 	return ret;
 }
@@ -4360,7 +4360,7 @@ static bool resctrl_online_domains_exist(void)
  * When called by the architecture code, all CPUs and resctrl domains must be
  * offline. This ensures the limbo and overflow handlers are not scheduled to
  * run, meaning the data structures they access can be freed by
- * resctrl_mon_resource_exit().
+ * resctrl_l3_mon_resource_exit().
  *
  * After resctrl_exit() returns, the architecture code should return an
  * error from all resctrl_arch_ functions that can do this.
@@ -4387,5 +4387,5 @@ void resctrl_exit(void)
 	 * it can be used to umount resctrl.
 	 */
 
-	resctrl_mon_resource_exit();
+	resctrl_l3_mon_resource_exit();
 }

From b098744f952db656b16dba8d85827d9d9684a59f Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 17 Dec 2025 09:20:57 -0800
Subject: [PATCH 125/236] fs/resctrl: Make event details accessible to
 functions when reading events

commit dd110880e80d35ad07e460e7a8da007c8058e7bf upstream.

Reading monitoring event data from MMIO requires more context than the event id
to be able to read the correct memory location. struct mon_evt is the appropriate
place for this event specific context.

Prepare for addition of extra fields to struct mon_evt by changing the calling
conventions to pass a pointer to the mon_evt structure instead of just the
event id.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 fs/resctrl/ctrlmondata.c | 18 +++++++++---------
 fs/resctrl/internal.h    | 10 +++++-----
 fs/resctrl/monitor.c     | 22 +++++++++++-----------
 fs/resctrl/rdtgroup.c    |  6 +++---
 4 files changed, 28 insertions(+), 28 deletions(-)

diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c
index b74c69f2d54e7..c3656812848b2 100644
--- a/fs/resctrl/ctrlmondata.c
+++ b/fs/resctrl/ctrlmondata.c
@@ -548,7 +548,7 @@ struct rdt_domain_hdr *resctrl_find_domain(struct list_head *h, int id,
 
 void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 		    struct rdt_domain_hdr *hdr, struct rdtgroup *rdtgrp,
-		    cpumask_t *cpumask, int evtid, int first)
+		    cpumask_t *cpumask, struct mon_evt *evt, int first)
 {
 	int cpu;
 
@@ -559,15 +559,15 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 	 * Setup the parameters to pass to mon_event_count() to read the data.
 	 */
 	rr->rgrp = rdtgrp;
-	rr->evtid = evtid;
+	rr->evt = evt;
 	rr->r = r;
 	rr->hdr = hdr;
 	rr->first = first;
 	if (resctrl_arch_mbm_cntr_assign_enabled(r) &&
-	    resctrl_is_mbm_event(evtid)) {
+	    resctrl_is_mbm_event(evt->evtid)) {
 		rr->is_mbm_cntr = true;
 	} else {
-		rr->arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, evtid);
+		rr->arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, evt->evtid);
 		if (IS_ERR(rr->arch_mon_ctx)) {
 			rr->err = -EINVAL;
 			return;
@@ -588,14 +588,13 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 		smp_call_on_cpu(cpu, smp_mon_event_count, rr, false);
 
 	if (rr->arch_mon_ctx)
-		resctrl_arch_mon_ctx_free(r, evtid, rr->arch_mon_ctx);
+		resctrl_arch_mon_ctx_free(r, evt->evtid, rr->arch_mon_ctx);
 }
 
 int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 {
 	struct kernfs_open_file *of = m->private;
 	enum resctrl_res_level resid;
-	enum resctrl_event_id evtid;
 	struct rdt_l3_mon_domain *d;
 	struct rdt_domain_hdr *hdr;
 	struct rmid_read rr = {0};
@@ -603,6 +602,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 	int domid, cpu, ret = 0;
 	struct rdt_resource *r;
 	struct cacheinfo *ci;
+	struct mon_evt *evt;
 	struct mon_data *md;
 
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
@@ -619,7 +619,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 
 	resid = md->rid;
 	domid = md->domid;
-	evtid = md->evtid;
+	evt = md->evt;
 	r = resctrl_arch_get_resource(resid);
 
 	if (md->sum) {
@@ -637,7 +637,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 					continue;
 				rr.ci = ci;
 				mon_event_read(&rr, r, NULL, rdtgrp,
-					       &ci->shared_cpu_map, evtid, false);
+					       &ci->shared_cpu_map, evt, false);
 				goto checkresult;
 			}
 		}
@@ -653,7 +653,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 			ret = -ENOENT;
 			goto out;
 		}
-		mon_event_read(&rr, r, hdr, rdtgrp, &hdr->cpu_mask, evtid, false);
+		mon_event_read(&rr, r, hdr, rdtgrp, &hdr->cpu_mask, evt, false);
 	}
 
 checkresult:
diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index 61afe626aedb3..4df506585b459 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -81,7 +81,7 @@ extern struct mon_evt mon_event_all[QOS_NUM_EVENTS];
  * struct mon_data - Monitoring details for each event file.
  * @list:            Member of the global @mon_data_kn_priv_list list.
  * @rid:             Resource id associated with the event file.
- * @evtid:           Event id associated with the event file.
+ * @evt:             Event structure associated with the event file.
  * @sum:             Set when event must be summed across multiple
  *                   domains.
  * @domid:           When @sum is zero this is the domain to which
@@ -95,7 +95,7 @@ extern struct mon_evt mon_event_all[QOS_NUM_EVENTS];
 struct mon_data {
 	struct list_head	list;
 	enum resctrl_res_level	rid;
-	enum resctrl_event_id	evtid;
+	struct mon_evt		*evt;
 	int			domid;
 	bool			sum;
 };
@@ -108,7 +108,7 @@ struct mon_data {
  * @r:	   Resource describing the properties of the event being read.
  * @hdr:   Header of domain that the counter should be read from. If NULL then
  *	   sum all domains in @r sharing L3 @ci.id
- * @evtid: Which monitor event to read.
+ * @evt:   Which monitor event to read.
  * @first: Initialize MBM counter when true.
  * @ci:    Cacheinfo for L3. Only set when @hdr is NULL. Used when summing
  *	   domains.
@@ -126,7 +126,7 @@ struct rmid_read {
 	struct rdtgroup		*rgrp;
 	struct rdt_resource	*r;
 	struct rdt_domain_hdr	*hdr;
-	enum resctrl_event_id	evtid;
+	struct mon_evt		*evt;
 	bool			first;
 	struct cacheinfo	*ci;
 	bool			is_mbm_cntr;
@@ -365,7 +365,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg);
 
 void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 		    struct rdt_domain_hdr *hdr, struct rdtgroup *rdtgrp,
-		    cpumask_t *cpumask, int evtid, int first);
+		    cpumask_t *cpumask, struct mon_evt *evt, int first);
 
 void mbm_setup_overflow_handler(struct rdt_l3_mon_domain *dom,
 				unsigned long delay_ms,
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index 9d814dcb11a2b..9ce6057fc2110 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -430,7 +430,7 @@ static int __l3_mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
 	d = container_of(rr->hdr, struct rdt_l3_mon_domain, hdr);
 
 	if (rr->is_mbm_cntr) {
-		cntr_id = mbm_cntr_get(rr->r, d, rdtgrp, rr->evtid);
+		cntr_id = mbm_cntr_get(rr->r, d, rdtgrp, rr->evt->evtid);
 		if (cntr_id < 0) {
 			rr->err = -ENOENT;
 			return -EINVAL;
@@ -439,10 +439,10 @@ static int __l3_mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
 
 	if (rr->first) {
 		if (rr->is_mbm_cntr)
-			resctrl_arch_reset_cntr(rr->r, d, closid, rmid, cntr_id, rr->evtid);
+			resctrl_arch_reset_cntr(rr->r, d, closid, rmid, cntr_id, rr->evt->evtid);
 		else
-			resctrl_arch_reset_rmid(rr->r, d, closid, rmid, rr->evtid);
-		m = get_mbm_state(d, closid, rmid, rr->evtid);
+			resctrl_arch_reset_rmid(rr->r, d, closid, rmid, rr->evt->evtid);
+		m = get_mbm_state(d, closid, rmid, rr->evt->evtid);
 		if (m)
 			memset(m, 0, sizeof(struct mbm_state));
 		return 0;
@@ -453,10 +453,10 @@ static int __l3_mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
 		return -EINVAL;
 	if (rr->is_mbm_cntr)
 		rr->err = resctrl_arch_cntr_read(rr->r, d, closid, rmid, cntr_id,
-						 rr->evtid, &tval);
+						 rr->evt->evtid, &tval);
 	else
 		rr->err = resctrl_arch_rmid_read(rr->r, rr->hdr, closid, rmid,
-						 rr->evtid, &tval, rr->arch_mon_ctx);
+						 rr->evt->evtid, &tval, rr->arch_mon_ctx);
 	if (rr->err)
 		return rr->err;
 
@@ -501,7 +501,7 @@ static int __l3_mon_event_count_sum(struct rdtgroup *rdtgrp, struct rmid_read *r
 		if (d->ci_id != rr->ci->id)
 			continue;
 		err = resctrl_arch_rmid_read(rr->r, &d->hdr, closid, rmid,
-					     rr->evtid, &tval, rr->arch_mon_ctx);
+					     rr->evt->evtid, &tval, rr->arch_mon_ctx);
 		if (!err) {
 			rr->val += tval;
 			ret = 0;
@@ -551,7 +551,7 @@ static void mbm_bw_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
 	if (!domain_header_is_valid(rr->hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3))
 		return;
 	d = container_of(rr->hdr, struct rdt_l3_mon_domain, hdr);
-	m = get_mbm_state(d, closid, rmid, rr->evtid);
+	m = get_mbm_state(d, closid, rmid, rr->evt->evtid);
 	if (WARN_ON_ONCE(!m))
 		return;
 
@@ -725,11 +725,11 @@ static void mbm_update_one_event(struct rdt_resource *r, struct rdt_l3_mon_domai
 
 	rr.r = r;
 	rr.hdr = &d->hdr;
-	rr.evtid = evtid;
+	rr.evt = &mon_event_all[evtid];
 	if (resctrl_arch_mbm_cntr_assign_enabled(r)) {
 		rr.is_mbm_cntr = true;
 	} else {
-		rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
+		rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, evtid);
 		if (IS_ERR(rr.arch_mon_ctx)) {
 			pr_warn_ratelimited("Failed to allocate monitor context: %ld",
 					    PTR_ERR(rr.arch_mon_ctx));
@@ -747,7 +747,7 @@ static void mbm_update_one_event(struct rdt_resource *r, struct rdt_l3_mon_domai
 		mbm_bw_count(rdtgrp, &rr);
 
 	if (rr.arch_mon_ctx)
-		resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
+		resctrl_arch_mon_ctx_free(rr.r, evtid, rr.arch_mon_ctx);
 }
 
 static void mbm_update(struct rdt_resource *r, struct rdt_l3_mon_domain *d,
diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index e6ee91594a953..6af6ee04a267a 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -2896,7 +2896,7 @@ static struct mon_data *mon_get_kn_priv(enum resctrl_res_level rid, int domid,
 
 	list_for_each_entry(priv, &mon_data_kn_priv_list, list) {
 		if (priv->rid == rid && priv->domid == domid &&
-		    priv->sum == do_sum && priv->evtid == mevt->evtid)
+		    priv->sum == do_sum && priv->evt == mevt)
 			return priv;
 	}
 
@@ -2907,7 +2907,7 @@ static struct mon_data *mon_get_kn_priv(enum resctrl_res_level rid, int domid,
 	priv->rid = rid;
 	priv->domid = domid;
 	priv->sum = do_sum;
-	priv->evtid = mevt->evtid;
+	priv->evt = mevt;
 	list_add_tail(&priv->list, &mon_data_kn_priv_list);
 
 	return priv;
@@ -3073,7 +3073,7 @@ static int mon_add_all_files(struct kernfs_node *kn, struct rdt_domain_hdr *hdr,
 			return ret;
 
 		if (!do_sum && resctrl_is_mbm_event(mevt->evtid))
-			mon_event_read(&rr, r, hdr, prgrp, &hdr->cpu_mask, mevt->evtid, true);
+			mon_event_read(&rr, r, hdr, prgrp, &hdr->cpu_mask, mevt, true);
 	}
 
 	return 0;

From bfefcd78bacc3419712918e5278e70270c555b24 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 17 Dec 2025 09:20:58 -0800
Subject: [PATCH 126/236] x86,fs/resctrl: Handle events that can be read from
 any CPU

commit ab0308aee3819a3eccde42f9eb5bb01d6733be38 upstream.

resctrl assumes that monitor events can only be read from a CPU in the
cpumask_t set of each domain.  This is true for x86 events accessed with an
MSR interface, but may not be true for other access methods such as MMIO.

Introduce and use flag mon_evt::any_cpu, settable by architecture, that
indicates there are no restrictions on which CPU can read that event.  This
flag is not supported by the L3 event reading that requires to be run on a CPU
that belongs to the L3 domain of the event being read.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c | 6 +++---
 fs/resctrl/ctrlmondata.c           | 6 ++++++
 fs/resctrl/internal.h              | 2 ++
 fs/resctrl/monitor.c               | 4 +++-
 include/linux/resctrl.h            | 2 +-
 5 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 9febdb41de382..f647ce84e851d 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -891,15 +891,15 @@ static __init bool get_rdt_mon_resources(void)
 	bool ret = false;
 
 	if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC)) {
-		resctrl_enable_mon_event(QOS_L3_OCCUP_EVENT_ID);
+		resctrl_enable_mon_event(QOS_L3_OCCUP_EVENT_ID, false);
 		ret = true;
 	}
 	if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) {
-		resctrl_enable_mon_event(QOS_L3_MBM_TOTAL_EVENT_ID);
+		resctrl_enable_mon_event(QOS_L3_MBM_TOTAL_EVENT_ID, false);
 		ret = true;
 	}
 	if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) {
-		resctrl_enable_mon_event(QOS_L3_MBM_LOCAL_EVENT_ID);
+		resctrl_enable_mon_event(QOS_L3_MBM_LOCAL_EVENT_ID, false);
 		ret = true;
 	}
 	if (rdt_cpu_has(X86_FEATURE_ABMC))
diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c
index c3656812848b2..883be6f0810f5 100644
--- a/fs/resctrl/ctrlmondata.c
+++ b/fs/resctrl/ctrlmondata.c
@@ -574,6 +574,11 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 		}
 	}
 
+	if (evt->any_cpu) {
+		mon_event_count(rr);
+		goto out_ctx_free;
+	}
+
 	cpu = cpumask_any_housekeeping(cpumask, RESCTRL_PICK_ANY_CPU);
 
 	/*
@@ -587,6 +592,7 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 	else
 		smp_call_on_cpu(cpu, smp_mon_event_count, rr, false);
 
+out_ctx_free:
 	if (rr->arch_mon_ctx)
 		resctrl_arch_mon_ctx_free(r, evt->evtid, rr->arch_mon_ctx);
 }
diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index 4df506585b459..6e0c2964891b8 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -61,6 +61,7 @@ static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc)
  *			READS_TO_REMOTE_MEM) being tracked by @evtid.
  *			Only valid if @evtid is an MBM event.
  * @configurable:	true if the event is configurable
+ * @any_cpu:		true if the event can be read from any CPU
  * @enabled:		true if the event is enabled
  */
 struct mon_evt {
@@ -69,6 +70,7 @@ struct mon_evt {
 	char			*name;
 	u32			evt_cfg;
 	bool			configurable;
+	bool			any_cpu;
 	bool			enabled;
 };
 
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index 9ce6057fc2110..45e77ce2eeace 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -518,6 +518,7 @@ static int __mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
 {
 	switch (rr->r->rid) {
 	case RDT_RESOURCE_L3:
+		WARN_ON_ONCE(rr->evt->any_cpu);
 		if (rr->hdr)
 			return __l3_mon_event_count(rdtgrp, rr);
 		else
@@ -987,7 +988,7 @@ struct mon_evt mon_event_all[QOS_NUM_EVENTS] = {
 	},
 };
 
-void resctrl_enable_mon_event(enum resctrl_event_id eventid)
+void resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu)
 {
 	if (WARN_ON_ONCE(eventid < QOS_FIRST_EVENT || eventid >= QOS_NUM_EVENTS))
 		return;
@@ -996,6 +997,7 @@ void resctrl_enable_mon_event(enum resctrl_event_id eventid)
 		return;
 	}
 
+	mon_event_all[eventid].any_cpu = any_cpu;
 	mon_event_all[eventid].enabled = true;
 }
 
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 28ea47119692b..262f32694c65b 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -406,7 +406,7 @@ u32 resctrl_arch_get_num_closid(struct rdt_resource *r);
 u32 resctrl_arch_system_num_rmid_idx(void);
 int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid);
 
-void resctrl_enable_mon_event(enum resctrl_event_id eventid);
+void resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu);
 
 bool resctrl_is_mon_event_enabled(enum resctrl_event_id eventid);
 

From e8ab6399ef5de40f9325bda1f009880dfdb9d1d3 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 17 Dec 2025 09:20:59 -0800
Subject: [PATCH 127/236] x86,fs/resctrl: Support binary fixed point event
 counters

commit e37c9a3dc9f9645532780d5ef34ea3b8fcf9ddef upstream.

resctrl assumes that all monitor events can be displayed as unsigned decimal
integers.

Hardware architecture counters may provide some telemetry events with greater
precision where the event is not a simple count, but is a measurement of some
sort (e.g. Joules for energy consumed).

Add a new argument to resctrl_enable_mon_event() for architecture code to
inform the file system that the value for a counter is a fixed-point value
with a specific number of binary places.

Only allow architecture to use floating point format on events that the file
system has marked with mon_evt::is_floating_point which reflects the contract
with user space on how the event values are displayed.

Display fixed point values with values rounded to ceil(binary_bits * log10(2))
decimal places. Special case for zero binary bits to print "{value}.0".

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c |  6 +--
 fs/resctrl/ctrlmondata.c           | 74 ++++++++++++++++++++++++++++++
 fs/resctrl/internal.h              |  8 ++++
 fs/resctrl/monitor.c               | 10 +++-
 include/linux/resctrl.h            |  3 +-
 5 files changed, 95 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index f647ce84e851d..8cfaed36d5b24 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -891,15 +891,15 @@ static __init bool get_rdt_mon_resources(void)
 	bool ret = false;
 
 	if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC)) {
-		resctrl_enable_mon_event(QOS_L3_OCCUP_EVENT_ID, false);
+		resctrl_enable_mon_event(QOS_L3_OCCUP_EVENT_ID, false, 0);
 		ret = true;
 	}
 	if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) {
-		resctrl_enable_mon_event(QOS_L3_MBM_TOTAL_EVENT_ID, false);
+		resctrl_enable_mon_event(QOS_L3_MBM_TOTAL_EVENT_ID, false, 0);
 		ret = true;
 	}
 	if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) {
-		resctrl_enable_mon_event(QOS_L3_MBM_LOCAL_EVENT_ID, false);
+		resctrl_enable_mon_event(QOS_L3_MBM_LOCAL_EVENT_ID, false, 0);
 		ret = true;
 	}
 	if (rdt_cpu_has(X86_FEATURE_ABMC))
diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c
index 883be6f0810f5..f329e5dfac475 100644
--- a/fs/resctrl/ctrlmondata.c
+++ b/fs/resctrl/ctrlmondata.c
@@ -17,6 +17,7 @@
 
 #include <linux/cpu.h>
 #include <linux/kernfs.h>
+#include <linux/math.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/tick.h>
@@ -597,6 +598,77 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 		resctrl_arch_mon_ctx_free(r, evt->evtid, rr->arch_mon_ctx);
 }
 
+/*
+ * Decimal place precision to use for each number of fixed-point
+ * binary bits computed from ceil(binary_bits * log10(2)) except
+ * binary_bits == 0 which will print "value.0"
+ */
+static const unsigned int decplaces[MAX_BINARY_BITS + 1] = {
+	[0]  =  1,
+	[1]  =  1,
+	[2]  =  1,
+	[3]  =  1,
+	[4]  =  2,
+	[5]  =  2,
+	[6]  =  2,
+	[7]  =  3,
+	[8]  =  3,
+	[9]  =  3,
+	[10] =  4,
+	[11] =  4,
+	[12] =  4,
+	[13] =  4,
+	[14] =  5,
+	[15] =  5,
+	[16] =  5,
+	[17] =  6,
+	[18] =  6,
+	[19] =  6,
+	[20] =  7,
+	[21] =  7,
+	[22] =  7,
+	[23] =  7,
+	[24] =  8,
+	[25] =  8,
+	[26] =  8,
+	[27] =  9
+};
+
+static void print_event_value(struct seq_file *m, unsigned int binary_bits, u64 val)
+{
+	unsigned long long frac = 0;
+
+	if (binary_bits) {
+		/* Mask off the integer part of the fixed-point value. */
+		frac = val & GENMASK_ULL(binary_bits - 1, 0);
+
+		/*
+		 * Multiply by 10^{desired decimal places}. The integer part of
+		 * the fixed point value is now almost what is needed.
+		 */
+		frac *= int_pow(10ull, decplaces[binary_bits]);
+
+		/*
+		 * Round to nearest by adding a value that would be a "1" in the
+		 * binary_bits + 1 place.  Integer part of fixed point value is
+		 * now the needed value.
+		 */
+		frac += 1ull << (binary_bits - 1);
+
+		/*
+		 * Extract the integer part of the value. This is the decimal
+		 * representation of the original fixed-point fractional value.
+		 */
+		frac >>= binary_bits;
+	}
+
+	/*
+	 * "frac" is now in the range [0 .. 10^decplaces).  I.e. string
+	 * representation will fit into chosen number of decimal places.
+	 */
+	seq_printf(m, "%llu.%0*llu\n", val >> binary_bits, decplaces[binary_bits], frac);
+}
+
 int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 {
 	struct kernfs_open_file *of = m->private;
@@ -674,6 +746,8 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 		seq_puts(m, "Unavailable\n");
 	else if (rr.err == -ENOENT)
 		seq_puts(m, "Unassigned\n");
+	else if (evt->is_floating_point)
+		print_event_value(m, evt->binary_bits, rr.val);
 	else
 		seq_printf(m, "%llu\n", rr.val);
 
diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index 6e0c2964891b8..7efa93e6ebcf6 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -62,6 +62,9 @@ static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc)
  *			Only valid if @evtid is an MBM event.
  * @configurable:	true if the event is configurable
  * @any_cpu:		true if the event can be read from any CPU
+ * @is_floating_point:	event values are displayed in floating point format
+ * @binary_bits:	number of fixed-point binary bits from architecture,
+ *			only valid if @is_floating_point is true
  * @enabled:		true if the event is enabled
  */
 struct mon_evt {
@@ -71,6 +74,8 @@ struct mon_evt {
 	u32			evt_cfg;
 	bool			configurable;
 	bool			any_cpu;
+	bool			is_floating_point;
+	unsigned int		binary_bits;
 	bool			enabled;
 };
 
@@ -79,6 +84,9 @@ extern struct mon_evt mon_event_all[QOS_NUM_EVENTS];
 #define for_each_mon_event(mevt) for (mevt = &mon_event_all[QOS_FIRST_EVENT];	\
 				      mevt < &mon_event_all[QOS_NUM_EVENTS]; mevt++)
 
+/* Limit for mon_evt::binary_bits */
+#define MAX_BINARY_BITS	27
+
 /**
  * struct mon_data - Monitoring details for each event file.
  * @list:            Member of the global @mon_data_kn_priv_list list.
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index 45e77ce2eeace..dc0237a45b8bc 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -988,16 +988,22 @@ struct mon_evt mon_event_all[QOS_NUM_EVENTS] = {
 	},
 };
 
-void resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu)
+void resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu, unsigned int binary_bits)
 {
-	if (WARN_ON_ONCE(eventid < QOS_FIRST_EVENT || eventid >= QOS_NUM_EVENTS))
+	if (WARN_ON_ONCE(eventid < QOS_FIRST_EVENT || eventid >= QOS_NUM_EVENTS ||
+			 binary_bits > MAX_BINARY_BITS))
 		return;
 	if (mon_event_all[eventid].enabled) {
 		pr_warn("Duplicate enable for event %d\n", eventid);
 		return;
 	}
+	if (binary_bits && !mon_event_all[eventid].is_floating_point) {
+		pr_warn("Event %d may not be floating point\n", eventid);
+		return;
+	}
 
 	mon_event_all[eventid].any_cpu = any_cpu;
+	mon_event_all[eventid].binary_bits = binary_bits;
 	mon_event_all[eventid].enabled = true;
 }
 
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 262f32694c65b..11b9aa14c9e1c 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -406,7 +406,8 @@ u32 resctrl_arch_get_num_closid(struct rdt_resource *r);
 u32 resctrl_arch_system_num_rmid_idx(void);
 int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid);
 
-void resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu);
+void resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu,
+			      unsigned int binary_bits);
 
 bool resctrl_is_mon_event_enabled(enum resctrl_event_id eventid);
 

From 5b338d5ab1342d920e0f1f7ba40a9ace604f5922 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Thu, 8 Jan 2026 09:42:25 -0800
Subject: [PATCH 128/236] x86,fs/resctrl: Add an architectural hook called for
 first mount

commit 39208e73a40e0e81a5b12ddc11157c0a414df307 upstream.

Enumeration of Intel telemetry events is an asynchronous process involving
several mutually dependent drivers added as auxiliary devices during the
device_initcall() phase of Linux boot. The process finishes after the probe
functions of these drivers completes. But this happens after
resctrl_arch_late_init() is executed.

Tracing the enumeration process shows that it does complete a full seven
seconds before the earliest possible mount of the resctrl file system (when
included in /etc/fstab for automatic mount by systemd).

Add a hook for use by telemetry event enumeration and initialization and
run it once at the beginning of resctrl mount without any locks held.
The architecture is responsible for any required locking.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20260105191711.GBaVwON5nZn-uO6Sqg@fat_crate.local
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c | 4 ++++
 fs/resctrl/rdtgroup.c              | 3 +++
 include/linux/resctrl.h            | 6 ++++++
 3 files changed, 13 insertions(+)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 8cfaed36d5b24..616d0054b48af 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -720,6 +720,10 @@ static int resctrl_arch_offline_cpu(unsigned int cpu)
 	return 0;
 }
 
+void resctrl_arch_pre_mount(void)
+{
+}
+
 enum {
 	RDT_FLAG_CMT,
 	RDT_FLAG_MBM_TOTAL,
diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index 6af6ee04a267a..fef7a0cc53cd9 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -18,6 +18,7 @@
 #include <linux/fs_parser.h>
 #include <linux/sysfs.h>
 #include <linux/kernfs.h>
+#include <linux/once.h>
 #include <linux/resctrl.h>
 #include <linux/seq_buf.h>
 #include <linux/seq_file.h>
@@ -2585,6 +2586,8 @@ static int rdt_get_tree(struct fs_context *fc)
 	struct rdt_resource *r;
 	int ret;
 
+	DO_ONCE_SLEEPABLE(resctrl_arch_pre_mount);
+
 	cpus_read_lock();
 	mutex_lock(&rdtgroup_mutex);
 	/*
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 11b9aa14c9e1c..23925d988d155 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -508,6 +508,12 @@ void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_domain_hdr *h
 void resctrl_online_cpu(unsigned int cpu);
 void resctrl_offline_cpu(unsigned int cpu);
 
+/*
+ * Architecture hook called at beginning of first file system mount attempt.
+ * No locks are held.
+ */
+void resctrl_arch_pre_mount(void);
+
 /**
  * resctrl_arch_rmid_read() - Read the eventid counter corresponding to rmid
  *			      for this resource and domain.

From dda45093b59113218217d2a593d31976be3039ec Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 17 Dec 2025 09:21:01 -0800
Subject: [PATCH 129/236] x86,fs/resctrl: Add and initialize a resource for
 package scope monitoring

commit 2e53ad66686a46b141c3395719afeee3057ffe2f upstream.

Add a new PERF_PKG resource and introduce package level scope for monitoring
telemetry events so that CPU hotplug notifiers can build domains at the
package granularity.

Use the physical package ID available via topology_physical_package_id()
to identify the monitoring domains with package level scope. This enables
user space to use:

  /sys/devices/system/cpu/cpuX/topology/physical_package_id

to identify the monitoring domain a CPU is associated with.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com

 Conflicts:
	fs/resctrl/internal.h
[jz: resolve context conflict]
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c | 10 ++++++++++
 fs/resctrl/internal.h              |  2 ++
 fs/resctrl/rdtgroup.c              |  2 ++
 include/linux/resctrl.h            |  2 ++
 4 files changed, 16 insertions(+)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 616d0054b48af..8de060168b70b 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -99,6 +99,14 @@ struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESOURCES] = {
 			.schema_fmt		= RESCTRL_SCHEMA_RANGE,
 		},
 	},
+	[RDT_RESOURCE_PERF_PKG] =
+	{
+		.r_resctrl = {
+			.name			= "PERF_PKG",
+			.mon_scope		= RESCTRL_PACKAGE,
+			.mon_domains		= mon_domain_init(RDT_RESOURCE_PERF_PKG),
+		},
+	},
 };
 
 u32 resctrl_arch_system_num_rmid_idx(void)
@@ -434,6 +442,8 @@ static int get_domain_id_from_scope(int cpu, enum resctrl_scope scope)
 		return get_cpu_cacheinfo_id(cpu, scope);
 	case RESCTRL_L3_NODE:
 		return cpu_to_node(cpu);
+	case RESCTRL_PACKAGE:
+		return topology_physical_package_id(cpu);
 	default:
 		break;
 	}
diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index 7efa93e6ebcf6..8a017214d9035 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -253,6 +253,8 @@ struct rdtgroup {
 
 #define RFTYPE_DEBUG			BIT(10)
 
+#define RFTYPE_RES_PERF_PKG		BIT(12)
+
 #define RFTYPE_CTRL_INFO		(RFTYPE_INFO | RFTYPE_CTRL)
 
 #define RFTYPE_MON_INFO			(RFTYPE_INFO | RFTYPE_MON)
diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index fef7a0cc53cd9..3a462315c805f 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -2196,6 +2196,8 @@ static unsigned long fflags_from_resource(struct rdt_resource *r)
 	case RDT_RESOURCE_MBA:
 	case RDT_RESOURCE_SMBA:
 		return RFTYPE_RES_MB;
+	case RDT_RESOURCE_PERF_PKG:
+		return RFTYPE_RES_PERF_PKG;
 	}
 
 	return WARN_ON_ONCE(1);
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 23925d988d155..555683fc66168 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -53,6 +53,7 @@ enum resctrl_res_level {
 	RDT_RESOURCE_L2,
 	RDT_RESOURCE_MBA,
 	RDT_RESOURCE_SMBA,
+	RDT_RESOURCE_PERF_PKG,
 
 	/* Must be the last */
 	RDT_NUM_RESOURCES,
@@ -267,6 +268,7 @@ enum resctrl_scope {
 	RESCTRL_L2_CACHE = 2,
 	RESCTRL_L3_CACHE = 3,
 	RESCTRL_L3_NODE,
+	RESCTRL_PACKAGE,
 };
 
 /**

From 2a195b4c6955e60b0244da6d5ce0dad0bdd7e8ab Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 17 Dec 2025 09:21:02 -0800
Subject: [PATCH 130/236] fs/resctrl: Emphasize that L3 monitoring resource is
 required for summing domains

commit db64994d115e7c2cd72fec11b854467e97169379 upstream.

The feature to sum event data across multiple domains supports systems with
Sub-NUMA Cluster (SNC) mode enabled. The top-level monitoring files in each
"mon_L3_XX" directory provide the sum of data across all SNC nodes sharing an
L3 cache instance while the "mon_sub_L3_YY" sub-directories provide the event
data of the individual nodes.

SNC is only associated with the L3 resource and domains and as a result the
flow handling the sum of event data implicitly assumes it is working with
the L3 resource and domains.

Reading of telemetry events does not require to sum event data so this feature
can remain dedicated to SNC and keep the implicit assumption of working with
the L3 resource and domains.

Add a WARN to where the implicit assumption of working with the L3 resource
is made and add comments on how the structure controlling the event sum
feature is used.

Suggested-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 fs/resctrl/ctrlmondata.c | 8 +++++++-
 fs/resctrl/internal.h    | 4 ++--
 fs/resctrl/rdtgroup.c    | 3 ++-
 3 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c
index f329e5dfac475..0c6f9a8230664 100644
--- a/fs/resctrl/ctrlmondata.c
+++ b/fs/resctrl/ctrlmondata.c
@@ -673,7 +673,6 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 {
 	struct kernfs_open_file *of = m->private;
 	enum resctrl_res_level resid;
-	struct rdt_l3_mon_domain *d;
 	struct rdt_domain_hdr *hdr;
 	struct rmid_read rr = {0};
 	struct rdtgroup *rdtgrp;
@@ -701,6 +700,13 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 	r = resctrl_arch_get_resource(resid);
 
 	if (md->sum) {
+		struct rdt_l3_mon_domain *d;
+
+		if (WARN_ON_ONCE(resid != RDT_RESOURCE_L3)) {
+			ret = -EINVAL;
+			goto out;
+		}
+
 		/*
 		 * This file requires summing across all domains that share
 		 * the L3 cache id that was provided in the "domid" field of the
diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index 8a017214d9035..e692c908733d5 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -92,8 +92,8 @@ extern struct mon_evt mon_event_all[QOS_NUM_EVENTS];
  * @list:            Member of the global @mon_data_kn_priv_list list.
  * @rid:             Resource id associated with the event file.
  * @evt:             Event structure associated with the event file.
- * @sum:             Set when event must be summed across multiple
- *                   domains.
+ * @sum:             Set for RDT_RESOURCE_L3 when event must be summed
+ *                   across multiple domains.
  * @domid:           When @sum is zero this is the domain to which
  *                   the event file belongs. When @sum is one this
  *                   is the id of the L3 cache that all domains to be
diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index 3a462315c805f..2c8927adf213c 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -2889,7 +2889,8 @@ static void rmdir_all_sub(void)
  * @rid:    The resource id for the event file being created.
  * @domid:  The domain id for the event file being created.
  * @mevt:   The type of event file being created.
- * @do_sum: Whether SNC summing monitors are being created.
+ * @do_sum: Whether SNC summing monitors are being created. Only set
+ *	    when @rid == RDT_RESOURCE_L3.
  */
 static struct mon_data *mon_get_kn_priv(enum resctrl_res_level rid, int domid,
 					struct mon_evt *mevt,

From 3708efe5eae3d6c18912555b4c74e7c995aaeb89 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Thu, 8 Jan 2026 09:42:26 -0800
Subject: [PATCH 131/236] x86/resctrl: Discover hardware telemetry events
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 1fb2daa60de640efb13f907d43d72d28763f696c upstream.

Each CPU collects data for telemetry events that it sends to the nearest
telemetry event aggregator either when the value of MSR_IA32_PQR_ASSOC.RMID
changes, or when a two millisecond timer expires.

There is a feature type ("energy" or "perf"), GUID, and MMIO region associated
with each aggregator. This combination links to an XML description of the
set of telemetry events tracked by the aggregator. XML files are published
by Intel in a GitHub repository¹.

The telemetry event aggregators maintain per-RMID per-event counts of the
total seen for all the CPUs. There may be multiple telemetry event aggregators
per package.

There are separate sets of aggregators for each feature type. Aggregators
in a set may have different GUIDs. All aggregators with the same feature
type and GUID are symmetric keeping counts for the same set of events for
the CPUs that provide data to them.

The XML file for each aggregator provides the following information:
0) Feature type of the events ("perf" or "energy")
1) Which telemetry events are tracked by the aggregator.
2) The order in which the event counters appear for each RMID.
3) The value type of each event counter (integer or fixed-point).
4) The number of RMIDs supported.
5) Which additional aggregator status registers are included.
6) The total size of the MMIO region for an aggregator.

Introduce struct event_group that condenses the relevant information from
an XML file. Hereafter an "event group" refers to a group of events of a
particular feature type (event_group::pfname set to "energy" or "perf") with
a particular GUID.

Use event_group::pfname to determine the feature id needed to obtain the
aggregator details. It will later be used in console messages and with the
rdt= boot parameter.

The INTEL_PMT_TELEMETRY driver enumerates support for telemetry events.
This driver provides intel_pmt_get_regions_by_feature() to list all available
telemetry event aggregators of a given feature type. The list includes the
"guid", the base address in MMIO space for the region where the event counters
are exposed, and the package id where the all the CPUs that report to this
aggregator are located.

Call INTEL_PMT_TELEMETRY's intel_pmt_get_regions_by_feature() for each event
group to obtain a private copy of that event group's aggregator data. Duplicate
the aggregator data between event groups that have the same feature type
but different GUID. Further processing on this private copy will be unique
to the event group.

  ¹https://github.com/intel/Intel-PMT

  [ bp: Zap text explaining the code, s/guid/GUID/g ]

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com

 Conflicts:
	arch/x86/Kconfig
[jz: resolve context conflicts]
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/Kconfig                        |  13 +++
 arch/x86/kernel/cpu/resctrl/Makefile    |   1 +
 arch/x86/kernel/cpu/resctrl/core.c      |   4 +
 arch/x86/kernel/cpu/resctrl/intel_aet.c | 109 ++++++++++++++++++++++++
 arch/x86/kernel/cpu/resctrl/internal.h  |   8 ++
 5 files changed, 135 insertions(+)
 create mode 100644 arch/x86/kernel/cpu/resctrl/intel_aet.c

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 11f1ca432c715..306851c5a1f41 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -502,6 +502,19 @@ config X86_CPU_RESCTRL
 
 	  Say N if unsure.
 
+config X86_CPU_RESCTRL_INTEL_AET
+	bool "Intel Application Energy Telemetry"
+	depends on X86_CPU_RESCTRL && CPU_SUP_INTEL && INTEL_PMT_TELEMETRY=y && INTEL_TPMI=y
+	help
+	  Enable per-RMID telemetry events in resctrl.
+
+	  Intel feature that collects per-RMID execution data
+	  about energy consumption, measure of frequency independent
+	  activity and other performance metrics. Data is aggregated
+	  per package.
+
+	  Say N if unsure.
+
 if X86_32
 config X86_BIGSMP
 	bool "Support for big SMP systems with more than 8 CPUs"
diff --git a/arch/x86/kernel/cpu/resctrl/Makefile b/arch/x86/kernel/cpu/resctrl/Makefile
index d8a04b195da21..273ddfa308366 100644
--- a/arch/x86/kernel/cpu/resctrl/Makefile
+++ b/arch/x86/kernel/cpu/resctrl/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_X86_CPU_RESCTRL)		+= core.o rdtgroup.o monitor.o
 obj-$(CONFIG_X86_CPU_RESCTRL)		+= ctrlmondata.o
+obj-$(CONFIG_X86_CPU_RESCTRL_INTEL_AET)	+= intel_aet.o
 obj-$(CONFIG_RESCTRL_FS_PSEUDO_LOCK)	+= pseudo_lock.o
 
 # To allow define_trace.h's recursive include:
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 8de060168b70b..ba3994cf86996 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -732,6 +732,8 @@ static int resctrl_arch_offline_cpu(unsigned int cpu)
 
 void resctrl_arch_pre_mount(void)
 {
+	if (!intel_aet_get_events())
+		return;
 }
 
 enum {
@@ -1100,6 +1102,8 @@ late_initcall(resctrl_arch_late_init);
 
 static void __exit resctrl_arch_exit(void)
 {
+	intel_aet_exit();
+
 	cpuhp_remove_state(rdt_online);
 
 	resctrl_exit();
diff --git a/arch/x86/kernel/cpu/resctrl/intel_aet.c b/arch/x86/kernel/cpu/resctrl/intel_aet.c
new file mode 100644
index 0000000000000..404564739befe
--- /dev/null
+++ b/arch/x86/kernel/cpu/resctrl/intel_aet.c
@@ -0,0 +1,109 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Resource Director Technology(RDT)
+ * - Intel Application Energy Telemetry
+ *
+ * Copyright (C) 2025 Intel Corporation
+ *
+ * Author:
+ *    Tony Luck <tony.luck@intel.com>
+ */
+
+#define pr_fmt(fmt)   "resctrl: " fmt
+
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/intel_pmt_features.h>
+#include <linux/intel_vsec.h>
+#include <linux/resctrl.h>
+#include <linux/stddef.h>
+
+#include "internal.h"
+
+/**
+ * struct event_group - Events with the same feature type ("energy" or "perf") and GUID.
+ * @pfname:		PMT feature name ("energy" or "perf") of this event group.
+ * @pfg:		Points to the aggregated telemetry space information
+ *			returned by the intel_pmt_get_regions_by_feature()
+ *			call to the INTEL_PMT_TELEMETRY driver that contains
+ *			data for all telemetry regions of type @pfname.
+ *			Valid if the system supports the event group,
+ *			NULL otherwise.
+ */
+struct event_group {
+	/* Data fields for additional structures to manage this group. */
+	const char			*pfname;
+	struct pmt_feature_group	*pfg;
+};
+
+static struct event_group *known_event_groups[] = {
+};
+
+#define for_each_event_group(_peg)						\
+	for (_peg = known_event_groups;						\
+	     _peg < &known_event_groups[ARRAY_SIZE(known_event_groups)];	\
+	     _peg++)
+
+/* Stub for now */
+static bool enable_events(struct event_group *e, struct pmt_feature_group *p)
+{
+	return false;
+}
+
+static enum pmt_feature_id lookup_pfid(const char *pfname)
+{
+	if (!strcmp(pfname, "energy"))
+		return FEATURE_PER_RMID_ENERGY_TELEM;
+	else if (!strcmp(pfname, "perf"))
+		return FEATURE_PER_RMID_PERF_TELEM;
+
+	pr_warn("Unknown PMT feature name '%s'\n", pfname);
+
+	return FEATURE_INVALID;
+}
+
+/*
+ * Request a copy of struct pmt_feature_group for each event group. If there is
+ * one, the returned structure has an array of telemetry_region structures,
+ * each element of the array describes one telemetry aggregator. The
+ * telemetry aggregators may have different GUIDs so obtain duplicate struct
+ * pmt_feature_group for event groups with same feature type but different
+ * GUID. Post-processing ensures an event group can only use the telemetry
+ * aggregators that match its GUID. An event group keeps a pointer to its
+ * struct pmt_feature_group to indicate that its events are successfully
+ * enabled.
+ */
+bool intel_aet_get_events(void)
+{
+	struct pmt_feature_group *p;
+	enum pmt_feature_id pfid;
+	struct event_group **peg;
+	bool ret = false;
+
+	for_each_event_group(peg) {
+		pfid = lookup_pfid((*peg)->pfname);
+		p = intel_pmt_get_regions_by_feature(pfid);
+		if (IS_ERR_OR_NULL(p))
+			continue;
+		if (enable_events(*peg, p)) {
+			(*peg)->pfg = p;
+			ret = true;
+		} else {
+			intel_pmt_put_feature_group(p);
+		}
+	}
+
+	return ret;
+}
+
+void __exit intel_aet_exit(void)
+{
+	struct event_group **peg;
+
+	for_each_event_group(peg) {
+		if ((*peg)->pfg) {
+			intel_pmt_put_feature_group((*peg)->pfg);
+			(*peg)->pfg = NULL;
+		}
+	}
+}
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 6c9e75440c10e..bdef7f91a2b90 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -220,4 +220,12 @@ void __init intel_rdt_mbm_apply_quirk(void);
 void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
 void resctrl_arch_mbm_cntr_assign_set_one(struct rdt_resource *r);
 
+#ifdef CONFIG_X86_CPU_RESCTRL_INTEL_AET
+bool intel_aet_get_events(void);
+void __exit intel_aet_exit(void);
+#else
+static inline bool intel_aet_get_events(void) { return false; }
+static inline void __exit intel_aet_exit(void) { }
+#endif
+
 #endif /* _ASM_X86_RESCTRL_INTERNAL_H */

From 6fafafed68cbe7e9f8708f0ed8ef000c89511b37 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 17 Dec 2025 09:21:04 -0800
Subject: [PATCH 132/236] x86,fs/resctrl: Fill in details of events for
 performance and energy GUIDs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 8f6b6ad69b50bf16bb762ffafbfa44a4884f9a17 upstream.

The telemetry event aggregators of the Intel Clearwater Forest CPU support two
RMID-based feature types: "energy" with GUID 0x26696143¹, and "perf" with
GUID 0x26557651².

The event counter offsets in an aggregator's MMIO space are arranged in groups
for each RMID.

E.g., the "energy" counters for GUID 0x26696143 are arranged like this:

  MMIO offset:0x0000 Counter for RMID 0 PMT_EVENT_ENERGY
  MMIO offset:0x0008 Counter for RMID 0 PMT_EVENT_ACTIVITY
  MMIO offset:0x0010 Counter for RMID 1 PMT_EVENT_ENERGY
  MMIO offset:0x0018 Counter for RMID 1 PMT_EVENT_ACTIVITY
  ...
  MMIO offset:0x23F0 Counter for RMID 575 PMT_EVENT_ENERGY
  MMIO offset:0x23F8 Counter for RMID 575 PMT_EVENT_ACTIVITY

After all counters there are three status registers that provide indications
of how many times an aggregator was unable to process event counts, the time
stamp for the most recent loss of data, and the time stamp of the most recent
successful update.

  MMIO offset:0x2400 AGG_DATA_LOSS_COUNT
  MMIO offset:0x2408 AGG_DATA_LOSS_TIMESTAMP
  MMIO offset:0x2410 LAST_UPDATE_TIMESTAMP

Define event_group structures for both of these aggregator types and define
the events tracked by the aggregators in the file system code.

PMT_EVENT_ENERGY and PMT_EVENT_ACTIVITY are produced in fixed point format.
File system code must output as floating point values.

  ¹https://github.com/intel/Intel-PMT/blob/main/xml/CWF/OOBMSM/RMID-ENERGY/cwf_aggregator.xml
  ²https://github.com/intel/Intel-PMT/blob/main/xml/CWF/OOBMSM/RMID-PERF/cwf_aggregator.xml

  [ bp: Massage commit message. ]

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/intel_aet.c | 66 +++++++++++++++++++++++++
 fs/resctrl/monitor.c                    | 35 +++++++------
 include/linux/resctrl_types.h           | 11 +++++
 3 files changed, 97 insertions(+), 15 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/intel_aet.c b/arch/x86/kernel/cpu/resctrl/intel_aet.c
index 404564739befe..8e042b530c914 100644
--- a/arch/x86/kernel/cpu/resctrl/intel_aet.c
+++ b/arch/x86/kernel/cpu/resctrl/intel_aet.c
@@ -11,15 +11,33 @@
 
 #define pr_fmt(fmt)   "resctrl: " fmt
 
+#include <linux/compiler_types.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/intel_pmt_features.h>
 #include <linux/intel_vsec.h>
 #include <linux/resctrl.h>
+#include <linux/resctrl_types.h>
 #include <linux/stddef.h>
+#include <linux/types.h>
 
 #include "internal.h"
 
+/**
+ * struct pmt_event - Telemetry event.
+ * @id:		Resctrl event id.
+ * @idx:	Counter index within each per-RMID block of counters.
+ * @bin_bits:	Zero for integer valued events, else number bits in fraction
+ *		part of fixed-point.
+ */
+struct pmt_event {
+	enum resctrl_event_id	id;
+	unsigned int		idx;
+	unsigned int		bin_bits;
+};
+
+#define EVT(_id, _idx, _bits) { .id = _id, .idx = _idx, .bin_bits = _bits }
+
 /**
  * struct event_group - Events with the same feature type ("energy" or "perf") and GUID.
  * @pfname:		PMT feature name ("energy" or "perf") of this event group.
@@ -29,14 +47,62 @@
  *			data for all telemetry regions of type @pfname.
  *			Valid if the system supports the event group,
  *			NULL otherwise.
+ * @guid:		Unique number per XML description file.
+ * @mmio_size:		Number of bytes of MMIO registers for this group.
+ * @num_events:		Number of events in this group.
+ * @evts:		Array of event descriptors.
  */
 struct event_group {
 	/* Data fields for additional structures to manage this group. */
 	const char			*pfname;
 	struct pmt_feature_group	*pfg;
+
+	/* Remaining fields initialized from XML file. */
+	u32				guid;
+	size_t				mmio_size;
+	unsigned int			num_events;
+	struct pmt_event		evts[] __counted_by(num_events);
+};
+
+#define XML_MMIO_SIZE(num_rmids, num_events, num_extra_status) \
+		      (((num_rmids) * (num_events) + (num_extra_status)) * sizeof(u64))
+
+/*
+ * Link: https://github.com/intel/Intel-PMT/blob/main/xml/CWF/OOBMSM/RMID-ENERGY/cwf_aggregator.xml
+ */
+static struct event_group energy_0x26696143 = {
+	.pfname		= "energy",
+	.guid		= 0x26696143,
+	.mmio_size	= XML_MMIO_SIZE(576, 2, 3),
+	.num_events	= 2,
+	.evts		= {
+		EVT(PMT_EVENT_ENERGY, 0, 18),
+		EVT(PMT_EVENT_ACTIVITY, 1, 18),
+	}
+};
+
+/*
+ * Link: https://github.com/intel/Intel-PMT/blob/main/xml/CWF/OOBMSM/RMID-PERF/cwf_aggregator.xml
+ */
+static struct event_group perf_0x26557651 = {
+	.pfname		= "perf",
+	.guid		= 0x26557651,
+	.mmio_size	= XML_MMIO_SIZE(576, 7, 3),
+	.num_events	= 7,
+	.evts		= {
+		EVT(PMT_EVENT_STALLS_LLC_HIT, 0, 0),
+		EVT(PMT_EVENT_C1_RES, 1, 0),
+		EVT(PMT_EVENT_UNHALTED_CORE_CYCLES, 2, 0),
+		EVT(PMT_EVENT_STALLS_LLC_MISS, 3, 0),
+		EVT(PMT_EVENT_AUTO_C6_RES, 4, 0),
+		EVT(PMT_EVENT_UNHALTED_REF_CYCLES, 5, 0),
+		EVT(PMT_EVENT_UOPS_RETIRED, 6, 0),
+	}
 };
 
 static struct event_group *known_event_groups[] = {
+	&energy_0x26696143,
+	&perf_0x26557651,
 };
 
 #define for_each_event_group(_peg)						\
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index dc0237a45b8bc..d57793e2f88b4 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -965,27 +965,32 @@ static void dom_data_exit(struct rdt_resource *r)
 	mutex_unlock(&rdtgroup_mutex);
 }
 
+#define MON_EVENT(_eventid, _name, _res, _fp)	\
+	[_eventid] = {				\
+	.name			= _name,	\
+	.evtid			= _eventid,	\
+	.rid			= _res,		\
+	.is_floating_point	= _fp,		\
+}
+
 /*
  * All available events. Architecture code marks the ones that
  * are supported by a system using resctrl_enable_mon_event()
  * to set .enabled.
  */
 struct mon_evt mon_event_all[QOS_NUM_EVENTS] = {
-	[QOS_L3_OCCUP_EVENT_ID] = {
-		.name	= "llc_occupancy",
-		.evtid	= QOS_L3_OCCUP_EVENT_ID,
-		.rid	= RDT_RESOURCE_L3,
-	},
-	[QOS_L3_MBM_TOTAL_EVENT_ID] = {
-		.name	= "mbm_total_bytes",
-		.evtid	= QOS_L3_MBM_TOTAL_EVENT_ID,
-		.rid	= RDT_RESOURCE_L3,
-	},
-	[QOS_L3_MBM_LOCAL_EVENT_ID] = {
-		.name	= "mbm_local_bytes",
-		.evtid	= QOS_L3_MBM_LOCAL_EVENT_ID,
-		.rid	= RDT_RESOURCE_L3,
-	},
+	MON_EVENT(QOS_L3_OCCUP_EVENT_ID,		"llc_occupancy",	RDT_RESOURCE_L3,	false),
+	MON_EVENT(QOS_L3_MBM_TOTAL_EVENT_ID,		"mbm_total_bytes",	RDT_RESOURCE_L3,	false),
+	MON_EVENT(QOS_L3_MBM_LOCAL_EVENT_ID,		"mbm_local_bytes",	RDT_RESOURCE_L3,	false),
+	MON_EVENT(PMT_EVENT_ENERGY,			"core_energy",		RDT_RESOURCE_PERF_PKG,	true),
+	MON_EVENT(PMT_EVENT_ACTIVITY,			"activity",		RDT_RESOURCE_PERF_PKG,	true),
+	MON_EVENT(PMT_EVENT_STALLS_LLC_HIT,		"stalls_llc_hit",	RDT_RESOURCE_PERF_PKG,	false),
+	MON_EVENT(PMT_EVENT_C1_RES,			"c1_res",		RDT_RESOURCE_PERF_PKG,	false),
+	MON_EVENT(PMT_EVENT_UNHALTED_CORE_CYCLES,	"unhalted_core_cycles",	RDT_RESOURCE_PERF_PKG,	false),
+	MON_EVENT(PMT_EVENT_STALLS_LLC_MISS,		"stalls_llc_miss",	RDT_RESOURCE_PERF_PKG,	false),
+	MON_EVENT(PMT_EVENT_AUTO_C6_RES,		"c6_res",		RDT_RESOURCE_PERF_PKG,	false),
+	MON_EVENT(PMT_EVENT_UNHALTED_REF_CYCLES,	"unhalted_ref_cycles",	RDT_RESOURCE_PERF_PKG,	false),
+	MON_EVENT(PMT_EVENT_UOPS_RETIRED,		"uops_retired",		RDT_RESOURCE_PERF_PKG,	false),
 };
 
 void resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu, unsigned int binary_bits)
diff --git a/include/linux/resctrl_types.h b/include/linux/resctrl_types.h
index d98351663c2c6..6838b02d5ca3a 100644
--- a/include/linux/resctrl_types.h
+++ b/include/linux/resctrl_types.h
@@ -47,6 +47,17 @@ enum resctrl_event_id {
 	QOS_L3_MBM_TOTAL_EVENT_ID	= 0x02,
 	QOS_L3_MBM_LOCAL_EVENT_ID	= 0x03,
 
+	/* Intel Telemetry Events */
+	PMT_EVENT_ENERGY,
+	PMT_EVENT_ACTIVITY,
+	PMT_EVENT_STALLS_LLC_HIT,
+	PMT_EVENT_C1_RES,
+	PMT_EVENT_UNHALTED_CORE_CYCLES,
+	PMT_EVENT_STALLS_LLC_MISS,
+	PMT_EVENT_AUTO_C6_RES,
+	PMT_EVENT_UNHALTED_REF_CYCLES,
+	PMT_EVENT_UOPS_RETIRED,
+
 	/* Must be the last */
 	QOS_NUM_EVENTS,
 };

From 0e731d3428479ec947e97d27268430776fbaed4d Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 17 Dec 2025 09:21:05 -0800
Subject: [PATCH 133/236] x86,fs/resctrl: Add architectural event pointer

commit 8ccb1f8fa6a3dfde32cf33e7ded3558014e6cca2 upstream.

The resctrl file system layer passes the domain, RMID, and event id to the
architecture to fetch an event counter.

Fetching a telemetry event counter requires additional information that is
private to the architecture, for example, the offset into MMIO space from
where the counter should be read.

Add mon_evt::arch_priv that architecture can use for any private data related
to the event. The resctrl filesystem initializes mon_evt::arch_priv when the
architecture enables the event and passes it back to architecture when needing
to fetch an event counter.

Suggested-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c    |  6 +++---
 arch/x86/kernel/cpu/resctrl/monitor.c |  2 +-
 fs/resctrl/internal.h                 |  4 ++++
 fs/resctrl/monitor.c                  | 14 ++++++++++----
 include/linux/resctrl.h               |  7 +++++--
 5 files changed, 23 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index ba3994cf86996..0f770d108a448 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -907,15 +907,15 @@ static __init bool get_rdt_mon_resources(void)
 	bool ret = false;
 
 	if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC)) {
-		resctrl_enable_mon_event(QOS_L3_OCCUP_EVENT_ID, false, 0);
+		resctrl_enable_mon_event(QOS_L3_OCCUP_EVENT_ID, false, 0, NULL);
 		ret = true;
 	}
 	if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) {
-		resctrl_enable_mon_event(QOS_L3_MBM_TOTAL_EVENT_ID, false, 0);
+		resctrl_enable_mon_event(QOS_L3_MBM_TOTAL_EVENT_ID, false, 0, NULL);
 		ret = true;
 	}
 	if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) {
-		resctrl_enable_mon_event(QOS_L3_MBM_LOCAL_EVENT_ID, false, 0);
+		resctrl_enable_mon_event(QOS_L3_MBM_LOCAL_EVENT_ID, false, 0, NULL);
 		ret = true;
 	}
 	if (rdt_cpu_has(X86_FEATURE_ABMC))
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index d5cecb48e8d51..e49d508ac12b5 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -239,7 +239,7 @@ static u64 get_corrected_val(struct rdt_resource *r, struct rdt_l3_mon_domain *d
 
 int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain_hdr *hdr,
 			   u32 unused, u32 rmid, enum resctrl_event_id eventid,
-			   u64 *val, void *ignored)
+			   void *arch_priv, u64 *val, void *ignored)
 {
 	struct rdt_hw_l3_mon_domain *hw_dom;
 	struct rdt_l3_mon_domain *d;
diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index e692c908733d5..a3fd6a33777be 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -66,6 +66,9 @@ static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc)
  * @binary_bits:	number of fixed-point binary bits from architecture,
  *			only valid if @is_floating_point is true
  * @enabled:		true if the event is enabled
+ * @arch_priv:		Architecture private data for this event.
+ *			The @arch_priv provided by the architecture via
+ *			resctrl_enable_mon_event().
  */
 struct mon_evt {
 	enum resctrl_event_id	evtid;
@@ -77,6 +80,7 @@ struct mon_evt {
 	bool			is_floating_point;
 	unsigned int		binary_bits;
 	bool			enabled;
+	void			*arch_priv;
 };
 
 extern struct mon_evt mon_event_all[QOS_NUM_EVENTS];
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index d57793e2f88b4..5971b2c015d71 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -137,9 +137,11 @@ void __check_limbo(struct rdt_l3_mon_domain *d, bool force_free)
 	struct rmid_entry *entry;
 	u32 idx, cur_idx = 1;
 	void *arch_mon_ctx;
+	void *arch_priv;
 	bool rmid_dirty;
 	u64 val = 0;
 
+	arch_priv = mon_event_all[QOS_L3_OCCUP_EVENT_ID].arch_priv;
 	arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, QOS_L3_OCCUP_EVENT_ID);
 	if (IS_ERR(arch_mon_ctx)) {
 		pr_warn_ratelimited("Failed to allocate monitor context: %ld",
@@ -160,7 +162,7 @@ void __check_limbo(struct rdt_l3_mon_domain *d, bool force_free)
 
 		entry = __rmid_entry(idx);
 		if (resctrl_arch_rmid_read(r, &d->hdr, entry->closid, entry->rmid,
-					   QOS_L3_OCCUP_EVENT_ID, &val,
+					   QOS_L3_OCCUP_EVENT_ID, arch_priv, &val,
 					   arch_mon_ctx)) {
 			rmid_dirty = true;
 		} else {
@@ -456,7 +458,8 @@ static int __l3_mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
 						 rr->evt->evtid, &tval);
 	else
 		rr->err = resctrl_arch_rmid_read(rr->r, rr->hdr, closid, rmid,
-						 rr->evt->evtid, &tval, rr->arch_mon_ctx);
+						 rr->evt->evtid, rr->evt->arch_priv,
+						 &tval, rr->arch_mon_ctx);
 	if (rr->err)
 		return rr->err;
 
@@ -501,7 +504,8 @@ static int __l3_mon_event_count_sum(struct rdtgroup *rdtgrp, struct rmid_read *r
 		if (d->ci_id != rr->ci->id)
 			continue;
 		err = resctrl_arch_rmid_read(rr->r, &d->hdr, closid, rmid,
-					     rr->evt->evtid, &tval, rr->arch_mon_ctx);
+					     rr->evt->evtid, rr->evt->arch_priv,
+					     &tval, rr->arch_mon_ctx);
 		if (!err) {
 			rr->val += tval;
 			ret = 0;
@@ -993,7 +997,8 @@ struct mon_evt mon_event_all[QOS_NUM_EVENTS] = {
 	MON_EVENT(PMT_EVENT_UOPS_RETIRED,		"uops_retired",		RDT_RESOURCE_PERF_PKG,	false),
 };
 
-void resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu, unsigned int binary_bits)
+void resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu,
+			      unsigned int binary_bits, void *arch_priv)
 {
 	if (WARN_ON_ONCE(eventid < QOS_FIRST_EVENT || eventid >= QOS_NUM_EVENTS ||
 			 binary_bits > MAX_BINARY_BITS))
@@ -1009,6 +1014,7 @@ void resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu, unsig
 
 	mon_event_all[eventid].any_cpu = any_cpu;
 	mon_event_all[eventid].binary_bits = binary_bits;
+	mon_event_all[eventid].arch_priv = arch_priv;
 	mon_event_all[eventid].enabled = true;
 }
 
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 555683fc66168..c5a1d5ba21437 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -409,7 +409,7 @@ u32 resctrl_arch_system_num_rmid_idx(void);
 int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid);
 
 void resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu,
-			      unsigned int binary_bits);
+			      unsigned int binary_bits, void *arch_priv);
 
 bool resctrl_is_mon_event_enabled(enum resctrl_event_id eventid);
 
@@ -526,6 +526,9 @@ void resctrl_arch_pre_mount(void);
  *			only.
  * @rmid:		rmid of the counter to read.
  * @eventid:		eventid to read, e.g. L3 occupancy.
+ * @arch_priv:		Architecture private data for this event.
+ *			The @arch_priv provided by the architecture via
+ *			resctrl_enable_mon_event().
  * @val:		result of the counter read in bytes.
  * @arch_mon_ctx:	An architecture specific value from
  *			resctrl_arch_mon_ctx_alloc(), for MPAM this identifies
@@ -543,7 +546,7 @@ void resctrl_arch_pre_mount(void);
  */
 int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain_hdr *hdr,
 			   u32 closid, u32 rmid, enum resctrl_event_id eventid,
-			   u64 *val, void *arch_mon_ctx);
+			   void *arch_priv, u64 *val, void *arch_mon_ctx);
 
 /**
  * resctrl_arch_rmid_read_context_check()  - warn about invalid contexts

From 9ab572d537b810cb3880bf6760a8722eba585958 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 17 Dec 2025 09:21:06 -0800
Subject: [PATCH 134/236] x86/resctrl: Find and enable usable telemetry events

commit 7e6df9614546ae7eb1f1b2074d7b6039bb01540d upstream.

Every event group has a private copy of the data of all telemetry event
aggregators (aka "telemetry regions") tracking its feature type. Included
may be regions that have the same feature type but tracking different GUID
from the event group's.

Traverse the event group's telemetry region data and mark all regions that
are not usable by the event group as unusable by clearing those regions'
MMIO addresses. A region is considered unusable if:
1) GUID does not match the GUID of the event group.
2) Package ID is invalid.
3) The enumerated size of the MMIO region does not match the expected
   value from the XML description file.

Hereafter any telemetry region with an MMIO address is considered valid for
the event group it is associated with.

Enable all the event group's events as long as there is at least one usable
region from where data for its events can be read. Enabling of an event can
fail if the same event has already been enabled as part of another event
group. It should never happen that the same event is described by different
GUID supported by the same system so just WARN (via resctrl_enable_mon_event())
and skip the event.

Note that it is architecturally possible that some telemetry events are only
supported by a subset of the packages in the system. It is not expected that
systems will ever do this. If they do the user will see event files in resctrl
that always return "Unavailable".

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/intel_aet.c | 63 ++++++++++++++++++++++++-
 fs/resctrl/monitor.c                    | 10 ++--
 include/linux/resctrl.h                 |  2 +-
 3 files changed, 68 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/intel_aet.c b/arch/x86/kernel/cpu/resctrl/intel_aet.c
index 8e042b530c914..7d0bd7b070a79 100644
--- a/arch/x86/kernel/cpu/resctrl/intel_aet.c
+++ b/arch/x86/kernel/cpu/resctrl/intel_aet.c
@@ -16,9 +16,11 @@
 #include <linux/init.h>
 #include <linux/intel_pmt_features.h>
 #include <linux/intel_vsec.h>
+#include <linux/printk.h>
 #include <linux/resctrl.h>
 #include <linux/resctrl_types.h>
 #include <linux/stddef.h>
+#include <linux/topology.h>
 #include <linux/types.h>
 
 #include "internal.h"
@@ -110,12 +112,69 @@ static struct event_group *known_event_groups[] = {
 	     _peg < &known_event_groups[ARRAY_SIZE(known_event_groups)];	\
 	     _peg++)
 
-/* Stub for now */
-static bool enable_events(struct event_group *e, struct pmt_feature_group *p)
+static bool skip_telem_region(struct telemetry_region *tr, struct event_group *e)
 {
+	if (tr->guid != e->guid)
+		return true;
+	if (tr->plat_info.package_id >= topology_max_packages()) {
+		pr_warn("Bad package %u in guid 0x%x\n", tr->plat_info.package_id,
+			tr->guid);
+		return true;
+	}
+	if (tr->size != e->mmio_size) {
+		pr_warn("MMIO space wrong size (%zu bytes) for guid 0x%x. Expected %zu bytes.\n",
+			tr->size, e->guid, e->mmio_size);
+		return true;
+	}
+
 	return false;
 }
 
+static bool group_has_usable_regions(struct event_group *e, struct pmt_feature_group *p)
+{
+	bool usable_regions = false;
+
+	for (int i = 0; i < p->count; i++) {
+		if (skip_telem_region(&p->regions[i], e)) {
+			/*
+			 * Clear the address field of regions that did not pass the checks in
+			 * skip_telem_region() so they will not be used by intel_aet_read_event().
+			 * This is safe to do because intel_pmt_get_regions_by_feature() allocates
+			 * a new pmt_feature_group structure to return to each caller and only makes
+			 * use of the pmt_feature_group::kref field when intel_pmt_put_feature_group()
+			 * returns the structure.
+			 */
+			p->regions[i].addr = NULL;
+
+			continue;
+		}
+		usable_regions = true;
+	}
+
+	return usable_regions;
+}
+
+static bool enable_events(struct event_group *e, struct pmt_feature_group *p)
+{
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_PERF_PKG].r_resctrl;
+	int skipped_events = 0;
+
+	if (!group_has_usable_regions(e, p))
+		return false;
+
+	for (int j = 0; j < e->num_events; j++) {
+		if (!resctrl_enable_mon_event(e->evts[j].id, true,
+					      e->evts[j].bin_bits, &e->evts[j]))
+			skipped_events++;
+	}
+	if (e->num_events == skipped_events) {
+		pr_info("No events enabled in %s %s:0x%x\n", r->name, e->pfname, e->guid);
+		return false;
+	}
+
+	return true;
+}
+
 static enum pmt_feature_id lookup_pfid(const char *pfname)
 {
 	if (!strcmp(pfname, "energy"))
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index 5971b2c015d71..15bed7c7c1b73 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -997,25 +997,27 @@ struct mon_evt mon_event_all[QOS_NUM_EVENTS] = {
 	MON_EVENT(PMT_EVENT_UOPS_RETIRED,		"uops_retired",		RDT_RESOURCE_PERF_PKG,	false),
 };
 
-void resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu,
+bool resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu,
 			      unsigned int binary_bits, void *arch_priv)
 {
 	if (WARN_ON_ONCE(eventid < QOS_FIRST_EVENT || eventid >= QOS_NUM_EVENTS ||
 			 binary_bits > MAX_BINARY_BITS))
-		return;
+		return false;
 	if (mon_event_all[eventid].enabled) {
 		pr_warn("Duplicate enable for event %d\n", eventid);
-		return;
+		return false;
 	}
 	if (binary_bits && !mon_event_all[eventid].is_floating_point) {
 		pr_warn("Event %d may not be floating point\n", eventid);
-		return;
+		return false;
 	}
 
 	mon_event_all[eventid].any_cpu = any_cpu;
 	mon_event_all[eventid].binary_bits = binary_bits;
 	mon_event_all[eventid].arch_priv = arch_priv;
 	mon_event_all[eventid].enabled = true;
+
+	return true;
 }
 
 bool resctrl_is_mon_event_enabled(enum resctrl_event_id eventid)
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index c5a1d5ba21437..a075d67679f37 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -408,7 +408,7 @@ u32 resctrl_arch_get_num_closid(struct rdt_resource *r);
 u32 resctrl_arch_system_num_rmid_idx(void);
 int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid);
 
-void resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu,
+bool resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu,
 			      unsigned int binary_bits, void *arch_priv);
 
 bool resctrl_is_mon_event_enabled(enum resctrl_event_id eventid);

From 66242d3c17c7aab2b1b8144737506bbde48cc7d1 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 17 Dec 2025 09:21:07 -0800
Subject: [PATCH 135/236] x86/resctrl: Read telemetry events

commit 51541f6ca7718d8278e12fe80af80033268743b2 upstream.

Introduce intel_aet_read_event() to read telemetry events for resource
RDT_RESOURCE_PERF_PKG. There may be multiple aggregators tracking each
package, so scan all of them and add up all counters. Aggregators may return
an invalid data indication if they have received no records for a given RMID.
The user will see "Unavailable" if none of the aggregators on a package
provide valid counts.

Resctrl now uses readq() so depends on X86_64. Update Kconfig.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/Kconfig                        |  2 +-
 arch/x86/kernel/cpu/resctrl/intel_aet.c | 51 +++++++++++++++++++++++++
 arch/x86/kernel/cpu/resctrl/internal.h  |  5 +++
 arch/x86/kernel/cpu/resctrl/monitor.c   |  4 ++
 fs/resctrl/monitor.c                    | 14 +++++++
 5 files changed, 75 insertions(+), 1 deletion(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 306851c5a1f41..aa8bcd0a1b1bc 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -504,7 +504,7 @@ config X86_CPU_RESCTRL
 
 config X86_CPU_RESCTRL_INTEL_AET
 	bool "Intel Application Energy Telemetry"
-	depends on X86_CPU_RESCTRL && CPU_SUP_INTEL && INTEL_PMT_TELEMETRY=y && INTEL_TPMI=y
+	depends on X86_64 && X86_CPU_RESCTRL && CPU_SUP_INTEL && INTEL_PMT_TELEMETRY=y && INTEL_TPMI=y
 	help
 	  Enable per-RMID telemetry events in resctrl.
 
diff --git a/arch/x86/kernel/cpu/resctrl/intel_aet.c b/arch/x86/kernel/cpu/resctrl/intel_aet.c
index 7d0bd7b070a79..96d627e2c52d0 100644
--- a/arch/x86/kernel/cpu/resctrl/intel_aet.c
+++ b/arch/x86/kernel/cpu/resctrl/intel_aet.c
@@ -11,11 +11,15 @@
 
 #define pr_fmt(fmt)   "resctrl: " fmt
 
+#include <linux/bits.h>
 #include <linux/compiler_types.h>
+#include <linux/container_of.h>
 #include <linux/err.h>
+#include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/intel_pmt_features.h>
 #include <linux/intel_vsec.h>
+#include <linux/io.h>
 #include <linux/printk.h>
 #include <linux/resctrl.h>
 #include <linux/resctrl_types.h>
@@ -232,3 +236,50 @@ void __exit intel_aet_exit(void)
 		}
 	}
 }
+
+#define DATA_VALID	BIT_ULL(63)
+#define DATA_BITS	GENMASK_ULL(62, 0)
+
+/*
+ * Read counter for an event on a domain (summing all aggregators on the
+ * domain). If an aggregator hasn't received any data for a specific RMID,
+ * the MMIO read indicates that data is not valid.  Return success if at
+ * least one aggregator has valid data.
+ */
+int intel_aet_read_event(int domid, u32 rmid, void *arch_priv, u64 *val)
+{
+	struct pmt_event *pevt = arch_priv;
+	struct event_group *e;
+	bool valid = false;
+	u64 total = 0;
+	u64 evtcount;
+	void *pevt0;
+	u32 idx;
+
+	pevt0 = pevt - pevt->idx;
+	e = container_of(pevt0, struct event_group, evts);
+	idx = rmid * e->num_events;
+	idx += pevt->idx;
+
+	if (idx * sizeof(u64) + sizeof(u64) > e->mmio_size) {
+		pr_warn_once("MMIO index %u out of range\n", idx);
+		return -EIO;
+	}
+
+	for (int i = 0; i < e->pfg->count; i++) {
+		if (!e->pfg->regions[i].addr)
+			continue;
+		if (e->pfg->regions[i].plat_info.package_id != domid)
+			continue;
+		evtcount = readq(e->pfg->regions[i].addr + idx * sizeof(u64));
+		if (!(evtcount & DATA_VALID))
+			continue;
+		total += evtcount & DATA_BITS;
+		valid = true;
+	}
+
+	if (valid)
+		*val = total;
+
+	return valid ? 0 : -EINVAL;
+}
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index bdef7f91a2b90..a7b4ff6e9957c 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -223,9 +223,14 @@ void resctrl_arch_mbm_cntr_assign_set_one(struct rdt_resource *r);
 #ifdef CONFIG_X86_CPU_RESCTRL_INTEL_AET
 bool intel_aet_get_events(void);
 void __exit intel_aet_exit(void);
+int intel_aet_read_event(int domid, u32 rmid, void *arch_priv, u64 *val);
 #else
 static inline bool intel_aet_get_events(void) { return false; }
 static inline void __exit intel_aet_exit(void) { }
+static inline int intel_aet_read_event(int domid, u32 rmid, void *arch_priv, u64 *val)
+{
+	return -EINVAL;
+}
 #endif
 
 #endif /* _ASM_X86_RESCTRL_INTERNAL_H */
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index e49d508ac12b5..091a3dbd6aaf3 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -250,6 +250,10 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain_hdr *hdr,
 	int ret;
 
 	resctrl_arch_rmid_read_context_check();
+
+	if (r->rid == RDT_RESOURCE_PERF_PKG)
+		return intel_aet_read_event(hdr->id, rmid, arch_priv, val);
+
 	if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3))
 		return -EINVAL;
 
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index 15bed7c7c1b73..793f7ca9a8b24 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -527,6 +527,20 @@ static int __mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
 			return __l3_mon_event_count(rdtgrp, rr);
 		else
 			return __l3_mon_event_count_sum(rdtgrp, rr);
+	case RDT_RESOURCE_PERF_PKG: {
+		u64 tval = 0;
+
+		rr->err = resctrl_arch_rmid_read(rr->r, rr->hdr, rdtgrp->closid,
+						 rdtgrp->mon.rmid, rr->evt->evtid,
+						 rr->evt->arch_priv,
+						 &tval, rr->arch_mon_ctx);
+		if (rr->err)
+			return rr->err;
+
+		rr->val += tval;
+
+		return 0;
+	}
 	default:
 		rr->err = -EINVAL;
 		return -EINVAL;

From 4c888a2acc22ce0041a9ed79aa098d79d5aa9065 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 17 Dec 2025 09:21:08 -0800
Subject: [PATCH 136/236] fs/resctrl: Refactor mkdir_mondata_subdir()

commit 0ec1db4cac8239bb32da87586c3638200b65dd8c upstream.

Population of a monitor group's mon_data directory is unreasonably complicated
because of the support for Sub-NUMA Cluster (SNC) mode.

Split out the SNC code into a helper function to make it easier to add support
for a new telemetry resource.

Move all the duplicated code to make and set owner of domain directories into
the mon_add_all_files() helper and rename to _mkdir_mondata_subdir().

Suggested-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 fs/resctrl/rdtgroup.c | 108 +++++++++++++++++++++++-------------------
 1 file changed, 58 insertions(+), 50 deletions(-)

diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index 2c8927adf213c..4562acf3b8a5e 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -3052,57 +3052,65 @@ static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
 	}
 }
 
-static int mon_add_all_files(struct kernfs_node *kn, struct rdt_domain_hdr *hdr,
-			     struct rdt_resource *r, struct rdtgroup *prgrp,
-			     bool do_sum)
+/*
+ * Create a directory for a domain and populate it with monitor files. Create
+ * summing monitors when @hdr is NULL. No need to initialize summing monitors.
+ */
+static struct kernfs_node *_mkdir_mondata_subdir(struct kernfs_node *parent_kn, char *name,
+						 struct rdt_domain_hdr *hdr,
+						 struct rdt_resource *r,
+						 struct rdtgroup *prgrp, int domid)
 {
-	struct rdt_l3_mon_domain *d;
 	struct rmid_read rr = {0};
+	struct kernfs_node *kn;
 	struct mon_data *priv;
 	struct mon_evt *mevt;
-	int ret, domid;
+	int ret;
 
-	if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3))
-		return -EINVAL;
+	kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp);
+	if (IS_ERR(kn))
+		return kn;
+
+	ret = rdtgroup_kn_set_ugid(kn);
+	if (ret)
+		goto out_destroy;
 
-	d = container_of(hdr, struct rdt_l3_mon_domain, hdr);
 	for_each_mon_event(mevt) {
 		if (mevt->rid != r->rid || !mevt->enabled)
 			continue;
-		domid = do_sum ? d->ci_id : d->hdr.id;
-		priv = mon_get_kn_priv(r->rid, domid, mevt, do_sum);
-		if (WARN_ON_ONCE(!priv))
-			return -EINVAL;
+		priv = mon_get_kn_priv(r->rid, domid, mevt, !hdr);
+		if (WARN_ON_ONCE(!priv)) {
+			ret = -EINVAL;
+			goto out_destroy;
+		}
 
 		ret = mon_addfile(kn, mevt->name, priv);
 		if (ret)
-			return ret;
+			goto out_destroy;
 
-		if (!do_sum && resctrl_is_mbm_event(mevt->evtid))
+		if (hdr && resctrl_is_mbm_event(mevt->evtid))
 			mon_event_read(&rr, r, hdr, prgrp, &hdr->cpu_mask, mevt, true);
 	}
 
-	return 0;
+	return kn;
+out_destroy:
+	kernfs_remove(kn);
+	return ERR_PTR(ret);
 }
 
-static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
-				struct rdt_domain_hdr *hdr,
-				struct rdt_resource *r, struct rdtgroup *prgrp)
+static int mkdir_mondata_subdir_snc(struct kernfs_node *parent_kn,
+				    struct rdt_domain_hdr *hdr,
+				    struct rdt_resource *r, struct rdtgroup *prgrp)
 {
-	struct kernfs_node *kn, *ckn;
+	struct kernfs_node *ckn, *kn;
 	struct rdt_l3_mon_domain *d;
 	char name[32];
-	bool snc_mode;
-	int ret = 0;
-
-	lockdep_assert_held(&rdtgroup_mutex);
 
 	if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3))
 		return -EINVAL;
 
 	d = container_of(hdr, struct rdt_l3_mon_domain, hdr);
-	snc_mode = r->mon_scope == RESCTRL_L3_NODE;
-	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci_id : d->hdr.id);
+	sprintf(name, "mon_%s_%02d", r->name, d->ci_id);
 	kn = kernfs_find_and_get(parent_kn, name);
 	if (kn) {
 		/*
@@ -3111,41 +3119,41 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
 		 */
 		kernfs_put(kn);
 	} else {
-		kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp);
+		kn = _mkdir_mondata_subdir(parent_kn, name, NULL, r, prgrp, d->ci_id);
 		if (IS_ERR(kn))
 			return PTR_ERR(kn);
+	}
 
-		ret = rdtgroup_kn_set_ugid(kn);
-		if (ret)
-			goto out_destroy;
-		ret = mon_add_all_files(kn, hdr, r, prgrp, snc_mode);
-		if (ret)
-			goto out_destroy;
+	sprintf(name, "mon_sub_%s_%02d", r->name, hdr->id);
+	ckn = _mkdir_mondata_subdir(kn, name, hdr, r, prgrp, hdr->id);
+	if (IS_ERR(ckn)) {
+		kernfs_remove(kn);
+		return PTR_ERR(ckn);
 	}
 
-	if (snc_mode) {
-		sprintf(name, "mon_sub_%s_%02d", r->name, hdr->id);
-		ckn = kernfs_create_dir(kn, name, parent_kn->mode, prgrp);
-		if (IS_ERR(ckn)) {
-			ret = -EINVAL;
-			goto out_destroy;
-		}
+	kernfs_activate(kn);
+	return 0;
+}
 
-		ret = rdtgroup_kn_set_ugid(ckn);
-		if (ret)
-			goto out_destroy;
+static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
+				struct rdt_domain_hdr *hdr,
+				struct rdt_resource *r, struct rdtgroup *prgrp)
+{
+	struct kernfs_node *kn;
+	char name[32];
 
-		ret = mon_add_all_files(ckn, hdr, r, prgrp, false);
-		if (ret)
-			goto out_destroy;
-	}
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	if (r->rid == RDT_RESOURCE_L3 && r->mon_scope == RESCTRL_L3_NODE)
+		return mkdir_mondata_subdir_snc(parent_kn, hdr, r, prgrp);
+
+	sprintf(name, "mon_%s_%02d", r->name, hdr->id);
+	kn = _mkdir_mondata_subdir(parent_kn, name, hdr, r, prgrp, hdr->id);
+	if (IS_ERR(kn))
+		return PTR_ERR(kn);
 
 	kernfs_activate(kn);
 	return 0;
-
-out_destroy:
-	kernfs_remove(kn);
-	return ret;
 }
 
 /*

From cf60c3283bbc59fb4d0033c7195bebd5ef4aa277 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 17 Dec 2025 09:21:09 -0800
Subject: [PATCH 137/236] fs/resctrl: Refactor rmdir_mondata_subdir_allrdtgrp()

commit 93d9fd89995181d7ff420752328cc8b4b228f100 upstream.

Clearing a monitor group's mon_data directory is complicated because of the
support for Sub-NUMA Cluster (SNC) mode.

Refactor the SNC case into a helper function to make it easier to add support
for a new telemetry resource.

Suggested-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 fs/resctrl/rdtgroup.c | 42 +++++++++++++++++++++++++++++++-----------
 1 file changed, 31 insertions(+), 11 deletions(-)

diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index 4562acf3b8a5e..f2061daee9a6e 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -3021,28 +3021,24 @@ static void mon_rmdir_one_subdir(struct kernfs_node *pkn, char *name, char *subn
 }
 
 /*
- * Remove all subdirectories of mon_data of ctrl_mon groups
- * and monitor groups for the given domain.
- * Remove files and directories containing "sum" of domain data
- * when last domain being summed is removed.
+ * Remove files and directories for one SNC node. If it is the last node
+ * sharing an L3 cache, then remove the upper level directory containing
+ * the "sum" files too.
  */
-static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
-					   struct rdt_domain_hdr *hdr)
+static void rmdir_mondata_subdir_allrdtgrp_snc(struct rdt_resource *r,
+					       struct rdt_domain_hdr *hdr)
 {
 	struct rdtgroup *prgrp, *crgrp;
 	struct rdt_l3_mon_domain *d;
 	char subname[32];
-	bool snc_mode;
 	char name[32];
 
 	if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3))
 		return;
 
 	d = container_of(hdr, struct rdt_l3_mon_domain, hdr);
-	snc_mode = r->mon_scope == RESCTRL_L3_NODE;
-	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci_id : hdr->id);
-	if (snc_mode)
-		sprintf(subname, "mon_sub_%s_%02d", r->name, hdr->id);
+	sprintf(name, "mon_%s_%02d", r->name, d->ci_id);
+	sprintf(subname, "mon_sub_%s_%02d", r->name, hdr->id);
 
 	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
 		mon_rmdir_one_subdir(prgrp->mon.mon_data_kn, name, subname);
@@ -3052,6 +3048,30 @@ static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
 	}
 }
 
+/*
+ * Remove all subdirectories of mon_data of ctrl_mon groups
+ * and monitor groups for the given domain.
+ */
+static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
+					   struct rdt_domain_hdr *hdr)
+{
+	struct rdtgroup *prgrp, *crgrp;
+	char name[32];
+
+	if (r->rid == RDT_RESOURCE_L3 && r->mon_scope == RESCTRL_L3_NODE) {
+		rmdir_mondata_subdir_allrdtgrp_snc(r, hdr);
+		return;
+	}
+
+	sprintf(name, "mon_%s_%02d", r->name, hdr->id);
+	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
+		kernfs_remove_by_name(prgrp->mon.mon_data_kn, name);
+
+		list_for_each_entry(crgrp, &prgrp->mon.crdtgrp_list, mon.crdtgrp_list)
+			kernfs_remove_by_name(crgrp->mon.mon_data_kn, name);
+	}
+}
+
 /*
  * Create a directory for a domain and populate it with monitor files. Create
  * summing monitors when @hdr is NULL. No need to initialize summing monitors.

From adee4fb5abe8d73287896a038ab540655f4d5f51 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 17 Dec 2025 09:21:10 -0800
Subject: [PATCH 138/236] x86,fs/resctrl: Handle domain creation/deletion for
 RDT_RESOURCE_PERF_PKG

commit f4e0cd80d3e7c31327459008b01d63804838a89d upstream.

The L3 resource has several requirements for domains. There are per-domain
structures that hold the 64-bit values of counters, and elements to keep
track of the overflow and limbo threads.

None of these are needed for the PERF_PKG resource. The hardware counters
are wide enough that they do not wrap around for decades.

Define a new rdt_perf_pkg_mon_domain structure which just consists of the
standard rdt_domain_hdr to keep track of domain id and CPU mask.

Update resctrl_online_mon_domain() for RDT_RESOURCE_PERF_PKG. The only action
needed for this resource is to create and populate domain directories if a
domain is added while resctrl is mounted.

Similarly resctrl_offline_mon_domain() only needs to remove domain directories.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c      | 17 +++++++++++++++
 arch/x86/kernel/cpu/resctrl/intel_aet.c | 29 +++++++++++++++++++++++++
 arch/x86/kernel/cpu/resctrl/internal.h  | 13 +++++++++++
 fs/resctrl/rdtgroup.c                   | 17 ++++++++++-----
 4 files changed, 71 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 0f770d108a448..aff141f215b7e 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -574,6 +574,10 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
 		if (!hdr)
 			l3_mon_domain_setup(cpu, id, r, add_pos);
 		break;
+	case RDT_RESOURCE_PERF_PKG:
+		if (!hdr)
+			intel_aet_mon_domain_setup(cpu, id, r, add_pos);
+		break;
 	default:
 		pr_warn_once("Unknown resource rid=%d\n", r->rid);
 		break;
@@ -673,6 +677,19 @@ static void domain_remove_cpu_mon(int cpu, struct rdt_resource *r)
 		l3_mon_domain_free(hw_dom);
 		break;
 	}
+	case RDT_RESOURCE_PERF_PKG: {
+		struct rdt_perf_pkg_mon_domain *pkgd;
+
+		if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_PERF_PKG))
+			return;
+
+		pkgd = container_of(hdr, struct rdt_perf_pkg_mon_domain, hdr);
+		resctrl_offline_mon_domain(r, hdr);
+		list_del_rcu(&hdr->list);
+		synchronize_rcu();
+		kfree(pkgd);
+		break;
+	}
 	default:
 		pr_warn_once("Unknown resource rid=%d\n", r->rid);
 		break;
diff --git a/arch/x86/kernel/cpu/resctrl/intel_aet.c b/arch/x86/kernel/cpu/resctrl/intel_aet.c
index 96d627e2c52d0..9351fe5b645af 100644
--- a/arch/x86/kernel/cpu/resctrl/intel_aet.c
+++ b/arch/x86/kernel/cpu/resctrl/intel_aet.c
@@ -14,15 +14,20 @@
 #include <linux/bits.h>
 #include <linux/compiler_types.h>
 #include <linux/container_of.h>
+#include <linux/cpumask.h>
 #include <linux/err.h>
 #include <linux/errno.h>
+#include <linux/gfp_types.h>
 #include <linux/init.h>
 #include <linux/intel_pmt_features.h>
 #include <linux/intel_vsec.h>
 #include <linux/io.h>
 #include <linux/printk.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
 #include <linux/resctrl.h>
 #include <linux/resctrl_types.h>
+#include <linux/slab.h>
 #include <linux/stddef.h>
 #include <linux/topology.h>
 #include <linux/types.h>
@@ -283,3 +288,27 @@ int intel_aet_read_event(int domid, u32 rmid, void *arch_priv, u64 *val)
 
 	return valid ? 0 : -EINVAL;
 }
+
+void intel_aet_mon_domain_setup(int cpu, int id, struct rdt_resource *r,
+				struct list_head *add_pos)
+{
+	struct rdt_perf_pkg_mon_domain *d;
+	int err;
+
+	d = kzalloc_node(sizeof(*d), GFP_KERNEL, cpu_to_node(cpu));
+	if (!d)
+		return;
+
+	d->hdr.id = id;
+	d->hdr.type = RESCTRL_MON_DOMAIN;
+	d->hdr.rid = RDT_RESOURCE_PERF_PKG;
+	cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
+	list_add_tail_rcu(&d->hdr.list, add_pos);
+
+	err = resctrl_online_mon_domain(r, &d->hdr);
+	if (err) {
+		list_del_rcu(&d->hdr.list);
+		synchronize_rcu();
+		kfree(d);
+	}
+}
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index a7b4ff6e9957c..2b5be30240377 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -87,6 +87,14 @@ static inline struct rdt_hw_l3_mon_domain *resctrl_to_arch_mon_dom(struct rdt_l3
 	return container_of(r, struct rdt_hw_l3_mon_domain, d_resctrl);
 }
 
+/**
+ * struct rdt_perf_pkg_mon_domain - CPUs sharing an package scoped resctrl monitor resource
+ * @hdr:	common header for different domain types
+ */
+struct rdt_perf_pkg_mon_domain {
+	struct rdt_domain_hdr	hdr;
+};
+
 /**
  * struct msr_param - set a range of MSRs from a domain
  * @res:       The resource to use
@@ -224,6 +232,8 @@ void resctrl_arch_mbm_cntr_assign_set_one(struct rdt_resource *r);
 bool intel_aet_get_events(void);
 void __exit intel_aet_exit(void);
 int intel_aet_read_event(int domid, u32 rmid, void *arch_priv, u64 *val);
+void intel_aet_mon_domain_setup(int cpu, int id, struct rdt_resource *r,
+				struct list_head *add_pos);
 #else
 static inline bool intel_aet_get_events(void) { return false; }
 static inline void __exit intel_aet_exit(void) { }
@@ -231,6 +241,9 @@ static inline int intel_aet_read_event(int domid, u32 rmid, void *arch_priv, u64
 {
 	return -EINVAL;
 }
+
+static inline void intel_aet_mon_domain_setup(int cpu, int id, struct rdt_resource *r,
+					      struct list_head *add_pos) { }
 #endif
 
 #endif /* _ASM_X86_RESCTRL_INTERNAL_H */
diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index f2061daee9a6e..6ca53248c3a09 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -4090,11 +4090,6 @@ void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_domain_hdr *h
 
 	mutex_lock(&rdtgroup_mutex);
 
-	if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3))
-		goto out_unlock;
-
-	d = container_of(hdr, struct rdt_l3_mon_domain, hdr);
-
 	/*
 	 * If resctrl is mounted, remove all the
 	 * per domain monitor data directories.
@@ -4102,6 +4097,13 @@ void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_domain_hdr *h
 	if (resctrl_mounted && resctrl_arch_mon_capable())
 		rmdir_mondata_subdir_allrdtgrp(r, hdr);
 
+	if (r->rid != RDT_RESOURCE_L3)
+		goto out_unlock;
+
+	if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3))
+		goto out_unlock;
+
+	d = container_of(hdr, struct rdt_l3_mon_domain, hdr);
 	if (resctrl_is_mbm_enabled())
 		cancel_delayed_work(&d->mbm_over);
 	if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID) && has_busy_rmid(d)) {
@@ -4198,6 +4200,9 @@ int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_domain_hdr *hdr
 
 	mutex_lock(&rdtgroup_mutex);
 
+	if (r->rid != RDT_RESOURCE_L3)
+		goto mkdir;
+
 	if (!domain_header_is_valid(hdr, RESCTRL_MON_DOMAIN, RDT_RESOURCE_L3))
 		goto out_unlock;
 
@@ -4215,6 +4220,8 @@ int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_domain_hdr *hdr
 	if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID))
 		INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo);
 
+mkdir:
+	err = 0;
 	/*
 	 * If the filesystem is not mounted then only the default resource group
 	 * exists. Creation of its directories is deferred until mount time

From 347298c4197b54786ff43cd4aedce7e2e691784c Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 17 Dec 2025 09:21:11 -0800
Subject: [PATCH 139/236] x86/resctrl: Add energy/perf choices to rdt boot
 option

commit 842e7f97d71a4116a650ec0045d6444b4377b512 upstream.

Legacy resctrl features are enumerated by X86_FEATURE_* flags. These may be
overridden by quirks to disable features in the case of errata.  Users can use
kernel command line options to either disable a feature, or to force enable
a feature that was disabled by a quirk.

A different approach is needed for hardware features that do not have an
X86_FEATURE_* flag.

Update parsing of the "rdt=" boot parameter to call the telemetry driver
directly to handle new "perf" and "energy" options that controls activation of
telemetry monitoring of the named type. By itself a "perf" or "energy" option
controls the forced enabling or disabling (with ! prefix) of all event groups
of the named type. A ":guid" suffix allows for fine grained control per event
group.

  [ bp: s/intel_aet_option/intel_handle_aet_option/g ]

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com

 Conflicts:
	Documentation/admin-guide/kernel-parameters.txt
[jz: resolve context conflict]
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 .../admin-guide/kernel-parameters.txt         |  6 ++-
 arch/x86/kernel/cpu/resctrl/core.c            |  2 +
 arch/x86/kernel/cpu/resctrl/intel_aet.c       | 38 +++++++++++++++++++
 arch/x86/kernel/cpu/resctrl/internal.h        |  2 +
 4 files changed, 47 insertions(+), 1 deletion(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index a7b7e778a1f7a..f9618febb65ef 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -5483,9 +5483,13 @@
 	rdt=		[HW,X86,RDT]
 			Turn on/off individual RDT features. List is:
 			cmt, mbmtotal, mbmlocal, l3cat, l3cdp, l2cat, l2cdp,
-			mba, smba, bmec.
+			mba, smba, bmec, energy[:guid], perf[:guid].
 			E.g. to turn on cmt and turn off mba use:
 				rdt=cmt,!mba
+			To turn off all energy telemetry monitoring and ensure that
+			perf telemetry monitoring associated with guid 0x12345
+			is enabled use:
+				rdt=!energy,perf:0x12345
 
 	reboot=		[KNL]
 			Format (x86 or x86_64):
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index aff141f215b7e..f6de7042aa8d5 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -804,6 +804,8 @@ static int __init set_rdt_options(char *str)
 		force_off = *tok == '!';
 		if (force_off)
 			tok++;
+		if (intel_handle_aet_option(force_off, tok))
+			continue;
 		for (o = rdt_options; o < &rdt_options[NUM_RDT_OPTIONS]; o++) {
 			if (strcmp(tok, o->name) == 0) {
 				if (force_off)
diff --git a/arch/x86/kernel/cpu/resctrl/intel_aet.c b/arch/x86/kernel/cpu/resctrl/intel_aet.c
index 9351fe5b645af..dc25e8d2527dc 100644
--- a/arch/x86/kernel/cpu/resctrl/intel_aet.c
+++ b/arch/x86/kernel/cpu/resctrl/intel_aet.c
@@ -52,12 +52,17 @@ struct pmt_event {
 /**
  * struct event_group - Events with the same feature type ("energy" or "perf") and GUID.
  * @pfname:		PMT feature name ("energy" or "perf") of this event group.
+ *			Used by boot rdt= option.
  * @pfg:		Points to the aggregated telemetry space information
  *			returned by the intel_pmt_get_regions_by_feature()
  *			call to the INTEL_PMT_TELEMETRY driver that contains
  *			data for all telemetry regions of type @pfname.
  *			Valid if the system supports the event group,
  *			NULL otherwise.
+ * @force_off:		True when "rdt" command line or architecture code disables
+ *			this event group.
+ * @force_on:		True when "rdt" command line overrides disable of this
+ *			event group.
  * @guid:		Unique number per XML description file.
  * @mmio_size:		Number of bytes of MMIO registers for this group.
  * @num_events:		Number of events in this group.
@@ -67,6 +72,7 @@ struct event_group {
 	/* Data fields for additional structures to manage this group. */
 	const char			*pfname;
 	struct pmt_feature_group	*pfg;
+	bool				force_off, force_on;
 
 	/* Remaining fields initialized from XML file. */
 	u32				guid;
@@ -121,6 +127,35 @@ static struct event_group *known_event_groups[] = {
 	     _peg < &known_event_groups[ARRAY_SIZE(known_event_groups)];	\
 	     _peg++)
 
+bool intel_handle_aet_option(bool force_off, char *tok)
+{
+	struct event_group **peg;
+	bool ret = false;
+	u32 guid = 0;
+	char *name;
+
+	if (!tok)
+		return false;
+
+	name = strsep(&tok, ":");
+	if (tok && kstrtou32(tok, 16, &guid))
+		return false;
+
+	for_each_event_group(peg) {
+		if (strcmp(name, (*peg)->pfname))
+			continue;
+		if (guid && (*peg)->guid != guid)
+			continue;
+		if (force_off)
+			(*peg)->force_off = true;
+		else
+			(*peg)->force_on = true;
+		ret = true;
+	}
+
+	return ret;
+}
+
 static bool skip_telem_region(struct telemetry_region *tr, struct event_group *e)
 {
 	if (tr->guid != e->guid)
@@ -168,6 +203,9 @@ static bool enable_events(struct event_group *e, struct pmt_feature_group *p)
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_PERF_PKG].r_resctrl;
 	int skipped_events = 0;
 
+	if (e->force_off)
+		return false;
+
 	if (!group_has_usable_regions(e, p))
 		return false;
 
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 2b5be30240377..2d76a02872e0c 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -234,6 +234,7 @@ void __exit intel_aet_exit(void);
 int intel_aet_read_event(int domid, u32 rmid, void *arch_priv, u64 *val);
 void intel_aet_mon_domain_setup(int cpu, int id, struct rdt_resource *r,
 				struct list_head *add_pos);
+bool intel_handle_aet_option(bool force_off, char *tok);
 #else
 static inline bool intel_aet_get_events(void) { return false; }
 static inline void __exit intel_aet_exit(void) { }
@@ -244,6 +245,7 @@ static inline int intel_aet_read_event(int domid, u32 rmid, void *arch_priv, u64
 
 static inline void intel_aet_mon_domain_setup(int cpu, int id, struct rdt_resource *r,
 					      struct list_head *add_pos) { }
+static inline bool intel_handle_aet_option(bool force_off, char *tok) { return false; }
 #endif
 
 #endif /* _ASM_X86_RESCTRL_INTERNAL_H */

From 80401772d404ebfda16ec258b4f2c77aea09563c Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 17 Dec 2025 09:21:12 -0800
Subject: [PATCH 140/236] x86/resctrl: Handle number of RMIDs supported by
 RDT_RESOURCE_PERF_PKG

commit 67640e333b983298be624a41c43e3a8ed4713a73 upstream.

There are now three meanings for "number of RMIDs":

1) The number for legacy features enumerated by CPUID leaf 0xF. This is the
   maximum number of distinct values that can be loaded into MSR_IA32_PQR_ASSOC.
   Note that systems with Sub-NUMA Cluster mode enabled will force scaling down
   the CPUID enumerated value by the number of SNC nodes per L3-cache.

2) The number of registers in MMIO space for each event. This is enumerated in
   the XML files and is the value initialized into event_group::num_rmid.

3) The number of "hardware counters" (this isn't a strictly accurate
   description of how things work, but serves as a useful analogy that does
   describe the limitations) feeding to those MMIO registers. This is enumerated
   in telemetry_region::num_rmids returned by intel_pmt_get_regions_by_feature().

Event groups with insufficient "hardware counters" to track all RMIDs are
difficult for users to use, since the system may reassign "hardware counters"
at any time. This means that users cannot reliably collect two consecutive
event counts to compute the rate at which events are occurring.

Disable such event groups by default. The user may override this with
a command line "rdt=" option. In this case limit an under-resourced event
group's number of possible monitor resource groups to the lowest number of
"hardware counters".

Scan all enabled event groups and assign the RDT_RESOURCE_PERF_PKG resource
"num_rmid" value to the smallest of these values as this value will be used
later to compare against the number of RMIDs supported by other resources to
determine how many monitoring resource groups are supported.

N.B. Change type of resctrl_mon::num_rmid to u32 to match its usage and the
type of event_group::num_rmid so that min(r->num_rmid, e->num_rmid) won't
complain about mixing signed and unsigned types.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/intel_aet.c | 53 ++++++++++++++++++++++++-
 fs/resctrl/rdtgroup.c                   |  2 +-
 include/linux/resctrl.h                 |  2 +-
 3 files changed, 54 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/intel_aet.c b/arch/x86/kernel/cpu/resctrl/intel_aet.c
index dc25e8d2527dc..aba9971350031 100644
--- a/arch/x86/kernel/cpu/resctrl/intel_aet.c
+++ b/arch/x86/kernel/cpu/resctrl/intel_aet.c
@@ -22,6 +22,7 @@
 #include <linux/intel_pmt_features.h>
 #include <linux/intel_vsec.h>
 #include <linux/io.h>
+#include <linux/minmax.h>
 #include <linux/printk.h>
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
@@ -60,10 +61,14 @@ struct pmt_event {
  *			Valid if the system supports the event group,
  *			NULL otherwise.
  * @force_off:		True when "rdt" command line or architecture code disables
- *			this event group.
+ *			this event group due to insufficient RMIDs.
  * @force_on:		True when "rdt" command line overrides disable of this
  *			event group.
  * @guid:		Unique number per XML description file.
+ * @num_rmid:		Number of RMIDs supported by this group. May be
+ *			adjusted downwards if enumeration from
+ *			intel_pmt_get_regions_by_feature() indicates fewer
+ *			RMIDs can be tracked simultaneously.
  * @mmio_size:		Number of bytes of MMIO registers for this group.
  * @num_events:		Number of events in this group.
  * @evts:		Array of event descriptors.
@@ -76,6 +81,7 @@ struct event_group {
 
 	/* Remaining fields initialized from XML file. */
 	u32				guid;
+	u32				num_rmid;
 	size_t				mmio_size;
 	unsigned int			num_events;
 	struct pmt_event		evts[] __counted_by(num_events);
@@ -90,6 +96,7 @@ struct event_group {
 static struct event_group energy_0x26696143 = {
 	.pfname		= "energy",
 	.guid		= 0x26696143,
+	.num_rmid	= 576,
 	.mmio_size	= XML_MMIO_SIZE(576, 2, 3),
 	.num_events	= 2,
 	.evts		= {
@@ -104,6 +111,7 @@ static struct event_group energy_0x26696143 = {
 static struct event_group perf_0x26557651 = {
 	.pfname		= "perf",
 	.guid		= 0x26557651,
+	.num_rmid	= 576,
 	.mmio_size	= XML_MMIO_SIZE(576, 7, 3),
 	.num_events	= 7,
 	.evts		= {
@@ -198,6 +206,23 @@ static bool group_has_usable_regions(struct event_group *e, struct pmt_feature_g
 	return usable_regions;
 }
 
+static bool all_regions_have_sufficient_rmid(struct event_group *e, struct pmt_feature_group *p)
+{
+	struct telemetry_region *tr;
+
+	for (int i = 0; i < p->count; i++) {
+		if (!p->regions[i].addr)
+			continue;
+		tr = &p->regions[i];
+		if (tr->num_rmids < e->num_rmid) {
+			e->force_off = true;
+			return false;
+		}
+	}
+
+	return true;
+}
+
 static bool enable_events(struct event_group *e, struct pmt_feature_group *p)
 {
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_PERF_PKG].r_resctrl;
@@ -209,6 +234,27 @@ static bool enable_events(struct event_group *e, struct pmt_feature_group *p)
 	if (!group_has_usable_regions(e, p))
 		return false;
 
+	/*
+	 * Only enable event group with insufficient RMIDs if the user requested
+	 * it from the kernel command line.
+	 */
+	if (!all_regions_have_sufficient_rmid(e, p) && !e->force_on) {
+		pr_info("%s %s:0x%x monitoring not enabled due to insufficient RMIDs\n",
+			r->name, e->pfname, e->guid);
+		return false;
+	}
+
+	for (int i = 0; i < p->count; i++) {
+		if (!p->regions[i].addr)
+			continue;
+		/*
+		 * e->num_rmid only adjusted lower if user (via rdt= kernel
+		 * parameter) forces an event group with insufficient RMID
+		 * to be enabled.
+		 */
+		e->num_rmid = min(e->num_rmid, p->regions[i].num_rmids);
+	}
+
 	for (int j = 0; j < e->num_events; j++) {
 		if (!resctrl_enable_mon_event(e->evts[j].id, true,
 					      e->evts[j].bin_bits, &e->evts[j]))
@@ -219,6 +265,11 @@ static bool enable_events(struct event_group *e, struct pmt_feature_group *p)
 		return false;
 	}
 
+	if (r->mon.num_rmid)
+		r->mon.num_rmid = min(r->mon.num_rmid, e->num_rmid);
+	else
+		r->mon.num_rmid = e->num_rmid;
+
 	return true;
 }
 
diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index 6ca53248c3a09..a48221438bfe6 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -1136,7 +1136,7 @@ static int rdt_num_rmids_show(struct kernfs_open_file *of,
 {
 	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
 
-	seq_printf(seq, "%d\n", r->mon.num_rmid);
+	seq_printf(seq, "%u\n", r->mon.num_rmid);
 
 	return 0;
 }
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index a075d67679f37..7a5bb93599ca2 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -290,7 +290,7 @@ enum resctrl_schema_fmt {
  * @mbm_cntr_assignable:Is system capable of supporting counter assignment?
  */
 struct resctrl_mon {
-	int			num_rmid;
+	u32			num_rmid;
 	unsigned int		mbm_cfg_mask;
 	int			num_mbm_cntrs;
 	bool			mbm_cntr_assignable;

From 3a18c04bdd633e07589cb5d8a469e0e868beff05 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 17 Dec 2025 09:21:13 -0800
Subject: [PATCH 141/236] fs/resctrl: Move allocation/free of
 closid_num_dirty_rmid[]

commit ee7f6af79f0916b6c49e15edd4cba020b3e4c4ac upstream.

closid_num_dirty_rmid[] and rmid_ptrs[] are allocated together during resctrl
initialization and freed together during resctrl exit.

Telemetry events are enumerated on resctrl mount so only at resctrl mount will
the number of RMID supported by all monitoring resources and needed as size
for rmid_ptrs[] be known.

Separate closid_num_dirty_rmid[] and rmid_ptrs[] allocation and free in
preparation for rmid_ptrs[] to be allocated on resctrl mount.

Keep the rdtgroup_mutex protection around the allocation and free of
closid_num_dirty_rmid[] as ARM needs this to guarantee memory ordering.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com

 Conflicts:
	fs/resctrl/monitor.c
[jz: resolve context conflicts]
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 fs/resctrl/monitor.c | 79 ++++++++++++++++++++++++++++----------------
 1 file changed, 51 insertions(+), 28 deletions(-)

diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index 793f7ca9a8b24..028b3e2bd9420 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -906,36 +906,14 @@ void mbm_setup_overflow_handler(struct rdt_l3_mon_domain *dom, unsigned long del
 static int dom_data_init(struct rdt_resource *r)
 {
 	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
-	u32 num_closid = resctrl_arch_get_num_closid(r);
 	struct rmid_entry *entry = NULL;
 	int err = 0, i;
 	u32 idx;
 
 	mutex_lock(&rdtgroup_mutex);
-	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
-		u32 *tmp;
-
-		/*
-		 * If the architecture hasn't provided a sanitised value here,
-		 * this may result in larger arrays than necessary. Resctrl will
-		 * use a smaller system wide value based on the resources in
-		 * use.
-		 */
-		tmp = kcalloc(num_closid, sizeof(*tmp), GFP_KERNEL);
-		if (!tmp) {
-			err = -ENOMEM;
-			goto out_unlock;
-		}
-
-		closid_num_dirty_rmid = tmp;
-	}
 
 	rmid_ptrs = kcalloc(idx_limit, sizeof(struct rmid_entry), GFP_KERNEL);
 	if (!rmid_ptrs) {
-		if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
-			kfree(closid_num_dirty_rmid);
-			closid_num_dirty_rmid = NULL;
-		}
 		err = -ENOMEM;
 		goto out_unlock;
 	}
@@ -971,11 +949,6 @@ static void dom_data_exit(struct rdt_resource *r)
 	if (!r->mon_capable)
 		goto out_unlock;
 
-	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
-		kfree(closid_num_dirty_rmid);
-		closid_num_dirty_rmid = NULL;
-	}
-
 	kfree(rmid_ptrs);
 	rmid_ptrs = NULL;
 
@@ -1210,6 +1183,45 @@ void rdtgroup_unassign_cntrs(struct rdtgroup *rdtgrp)
 					     &mon_event_all[QOS_L3_MBM_LOCAL_EVENT_ID]);
 }
 
+static int closid_num_dirty_rmid_alloc(struct rdt_resource *r)
+{
+	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
+		u32 num_closid = resctrl_arch_get_num_closid(r);
+		u32 *tmp;
+
+		/* For ARM memory ordering access to closid_num_dirty_rmid */
+		mutex_lock(&rdtgroup_mutex);
+
+		/*
+		 * If the architecture hasn't provided a sanitised value here,
+		 * this may result in larger arrays than necessary. Resctrl will
+		 * use a smaller system wide value based on the resources in
+		 * use.
+		 */
+		tmp = kcalloc(num_closid, sizeof(*tmp), GFP_KERNEL);
+		if (!tmp) {
+			mutex_unlock(&rdtgroup_mutex);
+			return -ENOMEM;
+		}
+
+		closid_num_dirty_rmid = tmp;
+
+		mutex_unlock(&rdtgroup_mutex);
+	}
+
+	return 0;
+}
+
+static void closid_num_dirty_rmid_free(void)
+{
+	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
+		mutex_lock(&rdtgroup_mutex);
+		kfree(closid_num_dirty_rmid);
+		closid_num_dirty_rmid = NULL;
+		mutex_unlock(&rdtgroup_mutex);
+	}
+}
+
 /**
  * resctrl_l3_mon_resource_init() - Initialise global monitoring structures.
  *
@@ -1230,10 +1242,16 @@ int resctrl_l3_mon_resource_init(void)
 	if (!r->mon_capable)
 		return 0;
 
-	ret = dom_data_init(r);
+	ret = closid_num_dirty_rmid_alloc(r);
 	if (ret)
 		return ret;
 
+	ret = dom_data_init(r);
+	if (ret) {
+		closid_num_dirty_rmid_free();
+		return ret;
+	}
+
 	if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_TOTAL_EVENT_ID)) {
 		mon_event_all[QOS_L3_MBM_TOTAL_EVENT_ID].configurable = true;
 		resctrl_file_fflags_init("mbm_total_bytes_config",
@@ -1267,5 +1285,10 @@ void resctrl_l3_mon_resource_exit(void)
 {
 	struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
 
+	if (!r->mon_capable)
+		return;
+
+	closid_num_dirty_rmid_free();
+
 	dom_data_exit(r);
 }

From 67b7472629c0b12cdbeddf2c153b730f2b5652e0 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 17 Dec 2025 09:21:14 -0800
Subject: [PATCH 142/236] x86,fs/resctrl: Compute number of RMIDs as minimum
 across resources

commit 0ecc988b0232259cbdb2b7e452bda74f550f0911 upstream.

resctrl assumes that only the L3 resource supports monitor events, so it
simply takes the rdt_resource::num_rmid from RDT_RESOURCE_L3 as the system's
number of RMIDs.

The addition of telemetry events in a different resource breaks that
assumption.

Compute the number of available RMIDs as the minimum value across all
mon_capable resources (analogous to how the number of CLOSIDs is computed
across alloc_capable resources).

Note that mount time enumeration of the telemetry resource means that
this number can be reduced. If this happens, then some memory will
be wasted as the allocations for rdt_l3_mon_domain::mbm_states[] and
rdt_l3_mon_domain::rmid_busy_llc created during resctrl initialization will
be larger than needed.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c | 15 +++++++++++++--
 fs/resctrl/rdtgroup.c              |  6 ++++++
 2 files changed, 19 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index f6de7042aa8d5..f44e54f43aa0d 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -109,12 +109,23 @@ struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESOURCES] = {
 	},
 };
 
+/**
+ * resctrl_arch_system_num_rmid_idx - Compute number of supported RMIDs
+ *				      (minimum across all mon_capable resource)
+ *
+ * Return: Number of supported RMIDs at time of call. Note that mount time
+ * enumeration of resources may reduce the number.
+ */
 u32 resctrl_arch_system_num_rmid_idx(void)
 {
-	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+	u32 num_rmids = U32_MAX;
+	struct rdt_resource *r;
+
+	for_each_mon_capable_rdt_resource(r)
+		num_rmids = min(num_rmids, r->mon.num_rmid);
 
 	/* RMID are independent numbers for x86. num_rmid_idx == num_rmid */
-	return r->mon.num_rmid;
+	return num_rmids == U32_MAX ? 0 : num_rmids;
 }
 
 struct rdt_resource *resctrl_arch_get_resource(enum resctrl_res_level l)
diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index a48221438bfe6..f2d18f5aba280 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -4135,6 +4135,12 @@ void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_domain_hdr *h
  * During boot this may be called before global allocations have been made by
  * resctrl_l3_mon_resource_init().
  *
+ * Called during CPU online that may run as soon as CPU online callbacks
+ * are set up during resctrl initialization. The number of supported RMIDs
+ * may be reduced if additional mon_capable resources are enumerated
+ * at mount time. This means the rdt_l3_mon_domain::mbm_states[] and
+ * rdt_l3_mon_domain::rmid_busy_llc allocations may be larger than needed.
+ *
  * Return: 0 for success, or -ENOMEM.
  */
 static int domain_setup_l3_mon_state(struct rdt_resource *r, struct rdt_l3_mon_domain *d)

From b97284f363e84fa7065603a1b12364d01c37e71b Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 17 Dec 2025 09:21:15 -0800
Subject: [PATCH 143/236] fs/resctrl: Move RMID initialization to first mount

commit d0891647fbc6e931f27517364cbc4ee1811d76db upstream.

L3 monitor features are enumerated during resctrl initialization and
rmid_ptrs[] that tracks all RMIDs and depends on the number of supported
RMIDs is allocated during this time.

Telemetry monitor features are enumerated during first resctrl mount and
may support a different number of RMIDs compared to L3 monitor features.

Delay allocation and initialization of rmid_ptrs[] until first mount.
Since the number of RMIDs cannot change on later mounts, keep the same set of
rmid_ptrs[] until resctrl_exit(). This is required because the limbo handler
keeps running after resctrl is unmounted and needs to access rmid_ptrs[]
as it keeps tracking busy RMIDs after unmount.

Rename routines to match what they now do:
dom_data_init() -> setup_rmid_lru_list()
dom_data_exit() -> free_rmid_lru_list()

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 fs/resctrl/internal.h |  4 ++++
 fs/resctrl/monitor.c  | 54 ++++++++++++++++++++-----------------------
 fs/resctrl/rdtgroup.c |  5 ++++
 3 files changed, 34 insertions(+), 29 deletions(-)

diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index a3fd6a33777be..15270fb757b26 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -367,6 +367,10 @@ int closids_supported(void);
 
 void closid_free(int closid);
 
+int setup_rmid_lru_list(void);
+
+void free_rmid_lru_list(void);
+
 int alloc_rmid(u32 closid);
 
 void free_rmid(u32 closid, u32 rmid);
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index 028b3e2bd9420..78dbc8c069ea8 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -903,20 +903,29 @@ void mbm_setup_overflow_handler(struct rdt_l3_mon_domain *dom, unsigned long del
 		schedule_delayed_work_on(cpu, &dom->mbm_over, delay);
 }
 
-static int dom_data_init(struct rdt_resource *r)
+int setup_rmid_lru_list(void)
 {
-	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
 	struct rmid_entry *entry = NULL;
-	int err = 0, i;
+	u32 idx_limit;
 	u32 idx;
+	int i;
 
-	mutex_lock(&rdtgroup_mutex);
+	if (!resctrl_arch_mon_capable())
+		return 0;
+
+	/*
+	 * Called on every mount, but the number of RMIDs cannot change
+	 * after the first mount, so keep using the same set of rmid_ptrs[]
+	 * until resctrl_exit(). Note that the limbo handler continues to
+	 * access rmid_ptrs[] after resctrl is unmounted.
+	 */
+	if (rmid_ptrs)
+		return 0;
 
+	idx_limit = resctrl_arch_system_num_rmid_idx();
 	rmid_ptrs = kcalloc(idx_limit, sizeof(struct rmid_entry), GFP_KERNEL);
-	if (!rmid_ptrs) {
-		err = -ENOMEM;
-		goto out_unlock;
-	}
+	if (!rmid_ptrs)
+		return -ENOMEM;
 
 	for (i = 0; i < idx_limit; i++) {
 		entry = &rmid_ptrs[i];
@@ -929,30 +938,24 @@ static int dom_data_init(struct rdt_resource *r)
 	/*
 	 * RESCTRL_RESERVED_CLOSID and RESCTRL_RESERVED_RMID are special and
 	 * are always allocated. These are used for the rdtgroup_default
-	 * control group, which will be setup later in resctrl_init().
+	 * control group, which was setup earlier in rdtgroup_setup_default().
 	 */
 	idx = resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID,
 					   RESCTRL_RESERVED_RMID);
 	entry = __rmid_entry(idx);
 	list_del(&entry->list);
 
-out_unlock:
-	mutex_unlock(&rdtgroup_mutex);
-
-	return err;
+	return 0;
 }
 
-static void dom_data_exit(struct rdt_resource *r)
+void free_rmid_lru_list(void)
 {
-	mutex_lock(&rdtgroup_mutex);
-
-	if (!r->mon_capable)
-		goto out_unlock;
+	if (!resctrl_arch_mon_capable())
+		return;
 
+	mutex_lock(&rdtgroup_mutex);
 	kfree(rmid_ptrs);
 	rmid_ptrs = NULL;
-
-out_unlock:
 	mutex_unlock(&rdtgroup_mutex);
 }
 
@@ -1226,7 +1229,8 @@ static void closid_num_dirty_rmid_free(void)
  * resctrl_l3_mon_resource_init() - Initialise global monitoring structures.
  *
  * Allocate and initialise global monitor resources that do not belong to a
- * specific domain. i.e. the rmid_ptrs[] used for the limbo and free lists.
+ * specific domain. i.e. the closid_num_dirty_rmid[] used to find the CLOSID
+ * with the cleanest set of RMIDs.
  * Called once during boot after the struct rdt_resource's have been configured
  * but before the filesystem is mounted.
  * Resctrl's cpuhp callbacks may be called before this point to bring a domain
@@ -1246,12 +1250,6 @@ int resctrl_l3_mon_resource_init(void)
 	if (ret)
 		return ret;
 
-	ret = dom_data_init(r);
-	if (ret) {
-		closid_num_dirty_rmid_free();
-		return ret;
-	}
-
 	if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_TOTAL_EVENT_ID)) {
 		mon_event_all[QOS_L3_MBM_TOTAL_EVENT_ID].configurable = true;
 		resctrl_file_fflags_init("mbm_total_bytes_config",
@@ -1289,6 +1287,4 @@ void resctrl_l3_mon_resource_exit(void)
 		return;
 
 	closid_num_dirty_rmid_free();
-
-	dom_data_exit(r);
 }
diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index f2d18f5aba280..c909977765be7 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -2600,6 +2600,10 @@ static int rdt_get_tree(struct fs_context *fc)
 		goto out;
 	}
 
+	ret = setup_rmid_lru_list();
+	if (ret)
+		goto out;
+
 	ret = rdtgroup_setup_root(ctx);
 	if (ret)
 		goto out;
@@ -4435,4 +4439,5 @@ void resctrl_exit(void)
 	 */
 
 	resctrl_l3_mon_resource_exit();
+	free_rmid_lru_list();
 }

From 2293195898ef67a900d5956311d1230766f4b013 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Thu, 8 Jan 2026 09:42:27 -0800
Subject: [PATCH 144/236] x86/resctrl: Enable RDT_RESOURCE_PERF_PKG

commit 4bbfc90122e974ccbd9aa80c964413052b9519f3 upstream.

Since telemetry events are enumerated on resctrl mount the RDT_RESOURCE_PERF_PKG
resource is not considered "monitoring capable" during early resctrl initialization.
This means that the domain list for RDT_RESOURCE_PERF_PKG is not built when the CPU
hotplug notifiers are registered and run for the first time right after resctrl
initialization.

Mark the RDT_RESOURCE_PERF_PKG as "monitoring capable" upon successful telemetry
event enumeration to ensure future CPU hotplug events include this resource and
initialize its domain list for CPUs that are already online.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/kernel/cpu/resctrl/core.c      | 16 ++++++++++++++++
 arch/x86/kernel/cpu/resctrl/intel_aet.c |  6 ++++++
 2 files changed, 22 insertions(+)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index f44e54f43aa0d..18fef31e16e9a 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -760,8 +760,24 @@ static int resctrl_arch_offline_cpu(unsigned int cpu)
 
 void resctrl_arch_pre_mount(void)
 {
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_PERF_PKG].r_resctrl;
+	int cpu;
+
 	if (!intel_aet_get_events())
 		return;
+
+	/*
+	 * Late discovery of telemetry events means the domains for the
+	 * resource were not built. Do that now.
+	 */
+	cpus_read_lock();
+	mutex_lock(&domain_list_lock);
+	r->mon_capable = true;
+	rdt_mon_capable = true;
+	for_each_online_cpu(cpu)
+		domain_add_cpu_mon(cpu, r);
+	mutex_unlock(&domain_list_lock);
+	cpus_read_unlock();
 }
 
 enum {
diff --git a/arch/x86/kernel/cpu/resctrl/intel_aet.c b/arch/x86/kernel/cpu/resctrl/intel_aet.c
index aba9971350031..89b8b619d5d53 100644
--- a/arch/x86/kernel/cpu/resctrl/intel_aet.c
+++ b/arch/x86/kernel/cpu/resctrl/intel_aet.c
@@ -270,6 +270,12 @@ static bool enable_events(struct event_group *e, struct pmt_feature_group *p)
 	else
 		r->mon.num_rmid = e->num_rmid;
 
+	if (skipped_events)
+		pr_info("%s %s:0x%x monitoring detected (skipped %d events)\n", r->name,
+			e->pfname, e->guid, skipped_events);
+	else
+		pr_info("%s %s:0x%x monitoring detected\n", r->name, e->pfname, e->guid);
+
 	return true;
 }
 

From 72e98fc130eee451809e63ed6eb16750ebb57221 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Wed, 17 Dec 2025 09:21:19 -0800
Subject: [PATCH 145/236] x86,fs/resctrl: Update documentation for telemetry
 events

commit a8848c4b43ad00c8a18db080206e3ffa53a08b91 upstream.

Update resctrl filesystem documentation with the details about the resctrl
files that support telemetry events.

  [ bp: Drop the debugfs hunk of the documentation until a better debugging
    solution is found. ]

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 Documentation/filesystems/resctrl.rst | 66 ++++++++++++++++++++++-----
 1 file changed, 54 insertions(+), 12 deletions(-)

diff --git a/Documentation/filesystems/resctrl.rst b/Documentation/filesystems/resctrl.rst
index db7ab26e05f8b..2918c856cf978 100644
--- a/Documentation/filesystems/resctrl.rst
+++ b/Documentation/filesystems/resctrl.rst
@@ -167,13 +167,12 @@ with respect to allocation:
 			bandwidth percentages are directly applied to
 			the threads running on the core
 
-If RDT monitoring is available there will be an "L3_MON" directory
+If L3 monitoring is available there will be an "L3_MON" directory
 with the following files:
 
 "num_rmids":
-		The number of RMIDs available. This is the
-		upper bound for how many "CTRL_MON" + "MON"
-		groups can be created.
+		The number of RMIDs supported by hardware for
+		L3 monitoring events.
 
 "mon_features":
 		Lists the monitoring events if
@@ -261,6 +260,24 @@ with the following files:
 		bytes) at which a previously used LLC_occupancy
 		counter can be considered for re-use.
 
+If telemetry monitoring is available there will be a "PERF_PKG_MON" directory
+with the following files:
+
+"num_rmids":
+		The number of RMIDs for telemetry monitoring events.
+
+		On Intel resctrl will not enable telemetry events if the number of
+		RMIDs that can be tracked concurrently is lower than the total number
+		of RMIDs supported. Telemetry events can be force-enabled with the
+		"rdt=" kernel parameter, but this may reduce the number of
+		monitoring groups that can be created.
+
+"mon_features":
+		Lists the telemetry monitoring events that are enabled on this system.
+
+The upper bound for how many "CTRL_MON" + "MON" can be created
+is the smaller of the L3_MON and PERF_PKG_MON "num_rmids" values.
+
 Finally, in the top level of the "info" directory there is a file
 named "last_cmd_status". This is reset with every "command" issued
 via the file system (making new directories or writing to any of the
@@ -366,15 +383,40 @@ When control is enabled all CTRL_MON groups will also contain:
 When monitoring is enabled all MON groups will also contain:
 
 "mon_data":
-	This contains a set of files organized by L3 domain and by
-	RDT event. E.g. on a system with two L3 domains there will
-	be subdirectories "mon_L3_00" and "mon_L3_01".	Each of these
-	directories have one file per event (e.g. "llc_occupancy",
-	"mbm_total_bytes", and "mbm_local_bytes"). In a MON group these
-	files provide a read out of the current value of the event for
-	all tasks in the group. In CTRL_MON groups these files provide
-	the sum for all tasks in the CTRL_MON group and all tasks in
+	This contains directories for each monitor domain.
+
+	If L3 monitoring is enabled, there will be a "mon_L3_XX" directory for
+	each instance of an L3 cache. Each directory contains files for the enabled
+	L3 events (e.g. "llc_occupancy", "mbm_total_bytes", and "mbm_local_bytes").
+
+	If telemetry monitoring is enabled, there will be a "mon_PERF_PKG_YY"
+	directory for each physical processor package. Each directory contains
+	files for the enabled telemetry events (e.g. "core_energy". "activity",
+	"uops_retired", etc.)
+
+	The info/`*`/mon_features files provide the full list of enabled
+	event/file names.
+
+	"core energy" reports a floating point number for the energy (in Joules)
+	consumed by cores (registers, arithmetic units, TLB and L1/L2 caches)
+	during execution of instructions summed across all logical CPUs on a
+	package for the current monitoring group.
+
+	"activity" also reports a floating point value (in Farads).  This provides
+	an estimate of work done independent of the frequency that the CPUs used
+	for execution.
+
+	Note that "core energy" and "activity" only measure energy/activity in the
+	"core" of the CPU (arithmetic units, TLB, L1 and L2 caches, etc.). They
+	do not include L3 cache, memory, I/O devices etc.
+
+	All other events report decimal integer values.
+
+	In a MON group these files provide a read out of the current value of
+	the event for all tasks in the group. In CTRL_MON groups these files
+	provide the sum for all tasks in the CTRL_MON group and all tasks in
 	MON groups. Please see example section for more details on usage.
+
 	On systems with Sub-NUMA Cluster (SNC) enabled there are extra
 	directories for each node (located within the "mon_L3_XX" directory
 	for the L3 cache they occupy). These are named "mon_sub_L3_YY"

From a5548c684483178eb407a72de82ce5e7767ea72a Mon Sep 17 00:00:00 2001
From: Zide Chen <zide.chen@intel.com>
Date: Mon, 9 Feb 2026 16:52:25 -0800
Subject: [PATCH 146/236] perf/x86/intel/uncore: Add per-scheduler IMC CAS
 count events

commit 6a8a48644c4b804123e59dbfc5d6cd29a0194046 upstream.

IMC on SPR and EMR does not support sub-channels.  In contrast, CPUs
that use gnr_uncores[] (e.g. Granite Rapids and Sierra Forest)
implement two command schedulers (SCH0/SCH1) per memory channel,
providing logically independent command and data paths.

Do not reuse the spr_uncore_imc[] configuration for these CPUs.
Instead, introduce a dedicated gnr_uncore_imc[] with per-scheduler
events, so userspace can monitor SCH0 and SCH1 independently.

On these CPUs, replace cas_count_{read,write} with
cas_count_{read,write}_sch{0,1}.  This may break existing userspace
that relies on cas_count_{read,write}, prompting it to switch to the
per-scheduler events, as the legacy event reports only partial
traffic (SCH0).

Fixes: 632c4bf6d007 ("perf/x86/intel/uncore: Support Granite Rapids")
Fixes: cb4a6ccf3583 ("perf/x86/intel/uncore: Support Sierra Forest and Grand Ridge")
Reported-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Zide Chen <zide.chen@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260210005225.20311-1-zide.chen@intel.com
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 arch/x86/events/intel/uncore_snbep.c | 28 +++++++++++++++++++++++++++-
 1 file changed, 27 insertions(+), 1 deletion(-)

diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 08faac3693972..d6bdef6194ae1 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -6605,6 +6605,32 @@ static struct intel_uncore_type gnr_uncore_ubox = {
 	.attr_update		= uncore_alias_groups,
 };
 
+static struct uncore_event_desc gnr_uncore_imc_events[] = {
+	INTEL_UNCORE_EVENT_DESC(clockticks,      "event=0x01,umask=0x00"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch0,  "event=0x05,umask=0xcf"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch0.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch0.unit, "MiB"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch1,  "event=0x06,umask=0xcf"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch1.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch1.unit, "MiB"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch0, "event=0x05,umask=0xf0"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch0.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch0.unit, "MiB"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch1, "event=0x06,umask=0xf0"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch1.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch1.unit, "MiB"),
+	{ /* end: all zeroes */ },
+};
+
+static struct intel_uncore_type gnr_uncore_imc = {
+	SPR_UNCORE_MMIO_COMMON_FORMAT(),
+	.name			= "imc",
+	.fixed_ctr_bits		= 48,
+	.fixed_ctr		= SNR_IMC_MMIO_PMON_FIXED_CTR,
+	.fixed_ctl		= SNR_IMC_MMIO_PMON_FIXED_CTL,
+	.event_descs		= gnr_uncore_imc_events,
+};
+
 static struct intel_uncore_type gnr_uncore_pciex8 = {
 	SPR_UNCORE_PCI_COMMON_FORMAT(),
 	.name			= "pciex8",
@@ -6652,7 +6678,7 @@ static struct intel_uncore_type *gnr_uncores[UNCORE_GNR_NUM_UNCORE_TYPES] = {
 	NULL,
 	&spr_uncore_pcu,
 	&gnr_uncore_ubox,
-	&spr_uncore_imc,
+	&gnr_uncore_imc,
 	NULL,
 	&gnr_uncore_upi,
 	NULL,

From af8196361865b0a926a5076398c5d9732e0d122d Mon Sep 17 00:00:00 2001
From: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Date: Fri, 13 Oct 2023 13:36:32 +0200
Subject: [PATCH 147/236] selftests/resctrl: Fix wrong format specifier
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 27c734f4402243f478348108d8a2ebd6e3e5e8a3 upstream.

Compiling resctrl selftest after adding a __printf() attribute to
ksft_print_msg() exposes -Wformat warning in show_cache_info().
The format specifier used expects a variable of type int but a long
unsigned int variable is passed instead.

Change the format specifier to match the passed variable.

Signed-off-by: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cache.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c
index 601ab78dbf421..992bac8c352ba 100644
--- a/tools/testing/selftests/resctrl/cache.c
+++ b/tools/testing/selftests/resctrl/cache.c
@@ -295,7 +295,7 @@ int show_cache_info(unsigned long sum_llc_val, int no_of_bits,
 	ret = platform && abs((int)diff_percent) > max_diff_percent &&
 	      (cmt ? (abs(avg_diff) > max_diff) : true);
 
-	ksft_print_msg("%s Check cache miss rate within %d%%\n",
+	ksft_print_msg("%s Check cache miss rate within %lu%%\n",
 		       ret ? "Fail:" : "Pass:", max_diff_percent);
 
 	ksft_print_msg("Percent diff=%d\n", abs((int)diff_percent));

From 241e377ff05d3443d93c52067d819e9f14564a9b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Mon, 4 Sep 2023 12:53:33 +0300
Subject: [PATCH 148/236] selftests/resctrl: Correct benchmark command help
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 5eb6360eeeb661c7589bc344c1c51e9dfcb63451 upstream.

Benchmark command must be the last argument because it consumes all the
remaining arguments but help misleadingly shows it as the first
argument. The benchmark command is also shown in quotes but it does not
match with the code.

Correct -b argument place in the help message and remove the quotes.
Tweak also how the options are presented by using ... notation.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: "Wieczor-Retman, Maciej" <maciej.wieczor-retman@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/resctrl_tests.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c
index 31373b69e675d..355be14a42895 100644
--- a/tools/testing/selftests/resctrl/resctrl_tests.c
+++ b/tools/testing/selftests/resctrl/resctrl_tests.c
@@ -49,8 +49,8 @@ int get_vendor(void)
 
 static void cmd_help(void)
 {
-	printf("usage: resctrl_tests [-h] [-b \"benchmark_cmd [options]\"] [-t test list] [-n no_of_bits]\n");
-	printf("\t-b benchmark_cmd [options]: run specified benchmark for MBM, MBA and CMT\n");
+	printf("usage: resctrl_tests [-h] [-t test list] [-n no_of_bits] [-b benchmark_cmd [option]...]\n");
+	printf("\t-b benchmark_cmd [option]...: run specified benchmark for MBM, MBA and CMT\n");
 	printf("\t   default benchmark is builtin fill_buf\n");
 	printf("\t-t test list: run tests specified in the test list, ");
 	printf("e.g. -t mbm,mba,cmt,cat\n");

From d3faf39123994d11f3704879c886521b365db919 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Mon, 4 Sep 2023 12:53:36 +0300
Subject: [PATCH 149/236] selftests/resctrl: Reorder resctrl FS prep code and
 benchmark_cmd init
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 47809eb70cdc81221e03baafe8c1768801a9184e upstream.

Benchmark command is initialized before resctrl FS check and
preparation code that can call ksft_exit_skip(). There is no strong
reason why the resctrl FS support check and unmounting it (if already
mounted), has to be done after the benchmark command initialization.

Move benchmark command initialization such that it is done not until
right before the tests commence. This simplifies rollback handling when
benchmark command initialization starts to use dynamic allocation (in a
change following this).

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: "Wieczor-Retman, Maciej" <maciej.wieczor-retman@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/resctrl_tests.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c
index 355be14a42895..a1de7a8fa1d1d 100644
--- a/tools/testing/selftests/resctrl/resctrl_tests.c
+++ b/tools/testing/selftests/resctrl/resctrl_tests.c
@@ -276,6 +276,14 @@ int main(int argc, char **argv)
 	if (geteuid() != 0)
 		return ksft_exit_skip("Not running as root. Skipping...\n");
 
+	if (!check_resctrlfs_support())
+		return ksft_exit_skip("resctrl FS does not exist. Enable X86_CPU_RESCTRL config option.\n");
+
+	if (umount_resctrlfs())
+		return ksft_exit_skip("resctrl FS unmount failed.\n");
+
+	filter_dmesg();
+
 	if (has_ben) {
 		if (argc - ben_ind >= BENCHMARK_ARGS)
 			ksft_exit_fail_msg("Too long benchmark command.\n");
@@ -297,14 +305,6 @@ int main(int argc, char **argv)
 		benchmark_cmd[5] = NULL;
 	}
 
-	if (!check_resctrlfs_support())
-		return ksft_exit_skip("resctrl FS does not exist. Enable X86_CPU_RESCTRL config option.\n");
-
-	if (umount_resctrlfs())
-		return ksft_exit_skip("resctrl FS unmount failed.\n");
-
-	filter_dmesg();
-
 	ksft_set_plan(tests ? : 4);
 
 	if (mbm_test)

From 0bdbcac3b047686284133188da7c7e9acfed426a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Mon, 4 Sep 2023 12:53:38 +0300
Subject: [PATCH 150/236] selftests/resctrl: Remove ben_count variable
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 149ff729538aabaa85c44dc58a45fb99798e5e7e upstream.

ben_count is only used to write the terminator for the list. It is
enough to use i from the loop so no need for another variable.

Remove ben_count variable as it is not needed.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: "Wieczor-Retman, Maciej" <maciej.wieczor-retman@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/resctrl_tests.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c
index a1de7a8fa1d1d..ddf9500e6b889 100644
--- a/tools/testing/selftests/resctrl/resctrl_tests.c
+++ b/tools/testing/selftests/resctrl/resctrl_tests.c
@@ -198,7 +198,7 @@ int main(int argc, char **argv)
 	bool has_ben = false, mbm_test = true, mba_test = true, cmt_test = true;
 	int c, cpu_no = 1, argc_new = argc, i, no_of_bits = 0;
 	const char *benchmark_cmd[BENCHMARK_ARGS];
-	int ben_ind, ben_count, tests = 0;
+	int ben_ind, tests = 0;
 	char *span_str = NULL;
 	bool cat_test = true;
 	int ret;
@@ -206,7 +206,6 @@ int main(int argc, char **argv)
 	for (i = 0; i < argc; i++) {
 		if (strcmp(argv[i], "-b") == 0) {
 			ben_ind = i + 1;
-			ben_count = argc - ben_ind;
 			argc_new = ben_ind - 1;
 			has_ben = true;
 			break;
@@ -291,7 +290,7 @@ int main(int argc, char **argv)
 		/* Extract benchmark command from command line. */
 		for (i = 0; i < argc - ben_ind; i++)
 			benchmark_cmd[i] = argv[i + ben_ind];
-		benchmark_cmd[ben_count] = NULL;
+		benchmark_cmd[i] = NULL;
 	} else {
 		/* If no benchmark is given by "-b" argument, use fill_buf. */
 		benchmark_cmd[0] = "fill_buf";

From 2c188b676c04770a67d5483b8bcb93b63168479b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Mon, 4 Sep 2023 12:53:39 +0300
Subject: [PATCH 151/236] selftests/resctrl: Cleanup benchmark argument parsing
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit f23c7925e98a1f0d9e3ee93a856dfe3d1288a3f0 upstream.

Benchmark argument is handled by custom argument parsing code which is
more complicated than it needs to be.

Process benchmark argument within the normal getopt() handling and drop
unnecessary ben_ind and has_ben variables. When -b is given, terminate
the argument processing as -b consumes all remaining arguments.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: "Wieczor-Retman, Maciej" <maciej.wieczor-retman@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 .../testing/selftests/resctrl/resctrl_tests.c | 46 +++++++++----------
 1 file changed, 23 insertions(+), 23 deletions(-)

diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c
index ddf9500e6b889..2bbe3045a018e 100644
--- a/tools/testing/selftests/resctrl/resctrl_tests.c
+++ b/tools/testing/selftests/resctrl/resctrl_tests.c
@@ -195,27 +195,34 @@ static void run_cat_test(int cpu_no, int no_of_bits)
 
 int main(int argc, char **argv)
 {
-	bool has_ben = false, mbm_test = true, mba_test = true, cmt_test = true;
-	int c, cpu_no = 1, argc_new = argc, i, no_of_bits = 0;
-	const char *benchmark_cmd[BENCHMARK_ARGS];
-	int ben_ind, tests = 0;
+	bool mbm_test = true, mba_test = true, cmt_test = true;
+	const char *benchmark_cmd[BENCHMARK_ARGS] = {};
+	int c, cpu_no = 1, i, no_of_bits = 0;
 	char *span_str = NULL;
 	bool cat_test = true;
+	int tests = 0;
 	int ret;
 
-	for (i = 0; i < argc; i++) {
-		if (strcmp(argv[i], "-b") == 0) {
-			ben_ind = i + 1;
-			argc_new = ben_ind - 1;
-			has_ben = true;
-			break;
-		}
-	}
-
-	while ((c = getopt(argc_new, argv, "ht:b:n:p:")) != -1) {
+	while ((c = getopt(argc, argv, "ht:b:n:p:")) != -1) {
 		char *token;
 
 		switch (c) {
+		case 'b':
+			/*
+			 * First move optind back to the (first) optarg and
+			 * then build the benchmark command using the
+			 * remaining arguments.
+			 */
+			optind--;
+			if (argc - optind >= BENCHMARK_ARGS)
+				ksft_exit_fail_msg("Too long benchmark command");
+
+			/* Extract benchmark command from command line. */
+			for (i = 0; i < argc - optind; i++)
+				benchmark_cmd[i] = argv[i + optind];
+			benchmark_cmd[i] = NULL;
+
+			goto last_arg;
 		case 't':
 			token = strtok(optarg, ",");
 
@@ -264,6 +271,7 @@ int main(int argc, char **argv)
 			return -1;
 		}
 	}
+last_arg:
 
 	ksft_print_header();
 
@@ -283,15 +291,7 @@ int main(int argc, char **argv)
 
 	filter_dmesg();
 
-	if (has_ben) {
-		if (argc - ben_ind >= BENCHMARK_ARGS)
-			ksft_exit_fail_msg("Too long benchmark command.\n");
-
-		/* Extract benchmark command from command line. */
-		for (i = 0; i < argc - ben_ind; i++)
-			benchmark_cmd[i] = argv[i + ben_ind];
-		benchmark_cmd[i] = NULL;
-	} else {
+	if (!benchmark_cmd[0]) {
 		/* If no benchmark is given by "-b" argument, use fill_buf. */
 		benchmark_cmd[0] = "fill_buf";
 		ret = asprintf(&span_str, "%u", DEFAULT_SPAN);

From 47a40a74255b529a3a770d7fffd7abc9b4538060 Mon Sep 17 00:00:00 2001
From: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Date: Tue, 10 Oct 2023 09:56:11 +0200
Subject: [PATCH 152/236] selftests/resctrl: Fix schemata write error check
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 20d96b25cc4c45823fbec5406ae5ae45da6a892e upstream.

Writing bitmasks to the schemata can fail when the bitmask doesn't
adhere to constraints defined by what a particular CPU supports.
Some example of constraints are max length or having contiguous bits.
The driver should properly return errors when any rule concerning
bitmask format is broken.

Resctrl FS returns error codes from fprintf() only when fclose() is
called. Current error checking scheme allows invalid bitmasks to be
written into schemata file and the selftest doesn't notice because the
fclose() error code isn't checked.

Substitute fopen(), flose() and fprintf() with open(), close() and
write() to avoid error code buffering between fprintf() and fclose().

Remove newline character from the schema string after writing it to
the schemata file so it prints correctly before function return.

Pass the string generated with strerror() to the "reason" buffer so
the error message is more verbose. Extend "reason" buffer so it can hold
longer messages.

Signed-off-by: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/resctrlfs.c | 41 +++++++++++++--------
 1 file changed, 26 insertions(+), 15 deletions(-)

diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index fe3241799841b..38126d57e8701 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -8,6 +8,7 @@
  *    Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>,
  *    Fenghua Yu <fenghua.yu@intel.com>
  */
+#include <fcntl.h>
 #include <limits.h>
 
 #include "resctrl.h"
@@ -438,9 +439,8 @@ int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp,
  */
 int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, char *resctrl_val)
 {
-	char controlgroup[1024], schema[1024], reason[64];
-	int resource_id, ret = 0;
-	FILE *fp;
+	char controlgroup[1024], reason[128], schema[1024] = {};
+	int resource_id, fd, schema_len = -1, ret = 0;
 
 	if (strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR)) &&
 	    strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)) &&
@@ -468,28 +468,39 @@ int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, char *resctrl_val)
 
 	if (!strncmp(resctrl_val, CAT_STR, sizeof(CAT_STR)) ||
 	    !strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR)))
-		sprintf(schema, "%s%d%c%s", "L3:", resource_id, '=', schemata);
+		schema_len = snprintf(schema, sizeof(schema), "%s%d%c%s\n",
+				      "L3:", resource_id, '=', schemata);
 	if (!strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR)) ||
 	    !strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)))
-		sprintf(schema, "%s%d%c%s", "MB:", resource_id, '=', schemata);
-
-	fp = fopen(controlgroup, "w");
-	if (!fp) {
-		sprintf(reason, "Failed to open control group");
+		schema_len = snprintf(schema, sizeof(schema), "%s%d%c%s\n",
+				      "MB:", resource_id, '=', schemata);
+	if (schema_len < 0 || schema_len >= sizeof(schema)) {
+		snprintf(reason, sizeof(reason),
+			 "snprintf() failed with return value : %d", schema_len);
 		ret = -1;
-
 		goto out;
 	}
 
-	if (fprintf(fp, "%s\n", schema) < 0) {
-		sprintf(reason, "Failed to write schemata in control group");
-		fclose(fp);
+	fd = open(controlgroup, O_WRONLY);
+	if (fd < 0) {
+		snprintf(reason, sizeof(reason),
+			 "open() failed : %s", strerror(errno));
 		ret = -1;
 
-		goto out;
+		goto err_schema_not_empty;
 	}
-	fclose(fp);
+	if (write(fd, schema, schema_len) < 0) {
+		snprintf(reason, sizeof(reason),
+			 "write() failed : %s", strerror(errno));
+		close(fd);
+		ret = -1;
+
+		goto err_schema_not_empty;
+	}
+	close(fd);
 
+err_schema_not_empty:
+	schema[schema_len - 1] = 0;
 out:
 	ksft_print_msg("Write schema \"%s\" to resctrl FS%s%s\n",
 		       schema, ret ? " # " : "",

From a5cf59a24eb5de7d1e24405929d10ec0e7a81ea4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Wed, 18 Oct 2023 10:55:26 +0300
Subject: [PATCH 153/236] selftests/resctrl: Fix MBM test failure when MBA
 unavailable
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 5247e6dbed0041147a83137f89cd45043301de5c upstream.

Commit 20d96b25cc4c ("selftests/resctrl: Fix schemata write error
check") exposed a problem in feature detection logic in MBM selftest.
If schemata does not support MB:x=x entries, the schemata write to
initialize 100% memory bandwidth allocation in mbm_setup() will now
fail with -EINVAL due to the error handling corrected by the commit
20d96b25cc4c ("selftests/resctrl: Fix schemata write error check").
That commit just uncovers the failed write, it is not wrong itself.

If MB:x=x is not supported by schemata, it is safe to assume 100%
memory bandwidth is always set. Therefore, the previously ignored error
does not make the MBM test itself wrong.

Restore the previous behavior of MBM test by checking MB support before
attempting to write it into schemata which results in behavior
equivalent to ignoring the write error.

Fixes: 20d96b25cc4c ("selftests/resctrl: Fix schemata write error check")
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/mbm_test.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c
index eb488aabb9ae6..045cd7818c79f 100644
--- a/tools/testing/selftests/resctrl/mbm_test.c
+++ b/tools/testing/selftests/resctrl/mbm_test.c
@@ -95,7 +95,7 @@ static int mbm_setup(struct resctrl_val_param *p)
 		return END_OF_TESTS;
 
 	/* Set up shemata with 100% allocation on the first run. */
-	if (p->num_of_runs == 0)
+	if (p->num_of_runs == 0 && validate_resctrl_feature_request("MB", NULL))
 		ret = write_schemata(p->ctrlgrp, "100", p->cpu_no,
 				     p->resctrl_val);
 

From 493433e6b39898ac9115dcb968b271ff61e464b8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 15 Dec 2023 17:04:48 +0200
Subject: [PATCH 154/236] selftests/resctrl: Return -1 instead of errno on
 error
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit c90fba60f274b182f8b4df0f5a5dd23a2457f4a3 upstream.

A number of functions in the resctrl selftests return errno. It is
problematic because errno is positive which is often counterintuitive.
Also, every site returning errno prints the error message already with
ksft_perror() so there is not much added value in returning the precise
error code.

Simply convert all places returning errno to return -1 that is typical
userspace error code in case of failures.

While at it, improve resctrl_val() comment to state that 0 means the
test was run (either pass or fail).

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cache.c       |  6 +++---
 tools/testing/selftests/resctrl/cat_test.c    |  4 ++--
 tools/testing/selftests/resctrl/cmt_test.c    |  2 +-
 tools/testing/selftests/resctrl/mba_test.c    |  2 +-
 tools/testing/selftests/resctrl/mbm_test.c    |  2 +-
 tools/testing/selftests/resctrl/resctrl_val.c | 10 +++++-----
 tools/testing/selftests/resctrl/resctrlfs.c   |  2 +-
 7 files changed, 14 insertions(+), 14 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c
index 992bac8c352ba..1fa4b86e1459b 100644
--- a/tools/testing/selftests/resctrl/cache.c
+++ b/tools/testing/selftests/resctrl/cache.c
@@ -126,7 +126,7 @@ static int get_llc_occu_resctrl(unsigned long *llc_occupancy)
 	if (!fp) {
 		ksft_perror("Failed to open results file");
 
-		return errno;
+		return -1;
 	}
 	if (fscanf(fp, "%lu", llc_occupancy) <= 0) {
 		ksft_perror("Could not get llc occupancy");
@@ -146,7 +146,7 @@ static int get_llc_occu_resctrl(unsigned long *llc_occupancy)
  * @llc_value:		perf miss value /
  *			llc occupancy value reported by resctrl FS
  *
- * Return:		0 on success. non-zero on failure.
+ * Return:		0 on success, < 0 on error.
  */
 static int print_results_cache(char *filename, int bm_pid,
 			       unsigned long llc_value)
@@ -161,7 +161,7 @@ static int print_results_cache(char *filename, int bm_pid,
 		if (!fp) {
 			ksft_perror("Cannot open results file");
 
-			return errno;
+			return -1;
 		}
 		fprintf(fp, "Pid: %d \t llc_value: %lu\n", bm_pid, llc_value);
 		fclose(fp);
diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
index 9bb8ba93f4335..fabb56ff68d16 100644
--- a/tools/testing/selftests/resctrl/cat_test.c
+++ b/tools/testing/selftests/resctrl/cat_test.c
@@ -53,7 +53,7 @@ static int check_results(struct resctrl_val_param *param, size_t span)
 	if (!fp) {
 		ksft_perror("Cannot open file");
 
-		return errno;
+		return -1;
 	}
 
 	while (fgets(temp, sizeof(temp), fp)) {
@@ -150,7 +150,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type)
 
 	if (pipe(pipefd)) {
 		ksft_perror("Unable to create pipe");
-		return errno;
+		return -1;
 	}
 
 	fflush(stdout);
diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c
index 16fc0488e0a54..ffd302bd5c738 100644
--- a/tools/testing/selftests/resctrl/cmt_test.c
+++ b/tools/testing/selftests/resctrl/cmt_test.c
@@ -39,7 +39,7 @@ static int check_results(struct resctrl_val_param *param, size_t span, int no_of
 	if (!fp) {
 		ksft_perror("Error in opening file");
 
-		return errno;
+		return -1;
 	}
 
 	while (fgets(temp, sizeof(temp), fp)) {
diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c
index 4988b93add6a7..e907adf7cd254 100644
--- a/tools/testing/selftests/resctrl/mba_test.c
+++ b/tools/testing/selftests/resctrl/mba_test.c
@@ -111,7 +111,7 @@ static int check_results(void)
 	if (!fp) {
 		ksft_perror(output);
 
-		return errno;
+		return -1;
 	}
 
 	runs = 0;
diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c
index 045cd7818c79f..721b3ecbc1588 100644
--- a/tools/testing/selftests/resctrl/mbm_test.c
+++ b/tools/testing/selftests/resctrl/mbm_test.c
@@ -61,7 +61,7 @@ static int check_results(size_t span)
 	if (!fp) {
 		ksft_perror(output);
 
-		return errno;
+		return -1;
 	}
 
 	runs = 0;
diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index 710058eb25407..bf1f9e627b6bc 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -543,7 +543,7 @@ void signal_handler_unregister(void)
  * @bw_imc:		perf imc counter value
  * @bw_resc:		memory bandwidth value
  *
- * Return:		0 on success. non-zero on failure.
+ * Return:		0 on success, < 0 on error.
  */
 static int print_results_bw(char *filename,  int bm_pid, float bw_imc,
 			    unsigned long bw_resc)
@@ -559,14 +559,14 @@ static int print_results_bw(char *filename,  int bm_pid, float bw_imc,
 		if (!fp) {
 			ksft_perror("Cannot open results file");
 
-			return errno;
+			return -1;
 		}
 		if (fprintf(fp, "Pid: %d \t Mem_BW_iMC: %f \t Mem_BW_resc: %lu \t Difference: %lu\n",
 			    bm_pid, bw_imc, bw_resc, diff) <= 0) {
 			ksft_print_msg("Could not log results\n");
 			fclose(fp);
 
-			return errno;
+			return -1;
 		}
 		fclose(fp);
 	}
@@ -703,7 +703,7 @@ static void run_benchmark(int signum, siginfo_t *info, void *ucontext)
  * @benchmark_cmd:	benchmark command and its arguments
  * @param:		parameters passed to resctrl_val()
  *
- * Return:		0 on success. non-zero on failure.
+ * Return:		0 when the test was run, < 0 on error.
  */
 int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *param)
 {
@@ -831,7 +831,7 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
 	/* Signal child to start benchmark */
 	if (sigqueue(bm_pid, SIGUSR1, value) == -1) {
 		ksft_perror("sigqueue SIGUSR1 to child");
-		ret = errno;
+		ret = -1;
 		goto out;
 	}
 
diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index 38126d57e8701..dbd2f951df199 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -88,7 +88,7 @@ int umount_resctrlfs(void)
 	if (umount(mountpoint)) {
 		ksft_perror("Unable to umount resctrl");
 
-		return errno;
+		return -1;
 	}
 
 	return 0;

From 05e3e143ae47644bf1ae40c43255c11eb66e21ba Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 15 Dec 2023 17:04:49 +0200
Subject: [PATCH 155/236] selftests/resctrl: Don't use ctrlc_handler() outside
 signal handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit bcd8a929a5387178d917da785896e53b0845ab37 upstream.

perf_event_open_llc_miss() calls ctrlc_handler() to cleanup if
perf_event_open() returns an error. Those cleanups, however, are not
the responsibility of perf_event_open_llc_miss() and it thus interferes
unnecessarily with the usual cleanup pattern. Worse yet,
ctrlc_handler() calls exit() in the end preventing the ordinary cleanup
done in the calling function from executing.

ctrlc_handler() should only be used as a signal handler, not during
normal error handling.

Remove call to ctrlc_handler() from perf_event_open_llc_miss(). As
unmounting resctrlfs and test cleanup are already handled properly
by error rollbacks in the calling functions, no other changes are
necessary.

Suggested-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cache.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c
index 1fa4b86e1459b..6d60a2f1b3aa9 100644
--- a/tools/testing/selftests/resctrl/cache.c
+++ b/tools/testing/selftests/resctrl/cache.c
@@ -41,7 +41,6 @@ static int perf_event_open_llc_miss(pid_t pid, int cpu_no)
 				PERF_FLAG_FD_CLOEXEC);
 	if (fd_lm == -1) {
 		ksft_perror("Error opening leader");
-		ctrlc_handler(0, NULL, NULL);
 		return -1;
 	}
 

From aa731d0a9eb35c4e25505f19829f4e08d4ecb9a3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 15 Dec 2023 17:04:50 +0200
Subject: [PATCH 156/236] selftests/resctrl: Change function comments to say <
 0 on error
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 348139384ba30eccd4ce4f01fcf575b08ce81b83 upstream.

A number function comments state the function return non-zero on
failure but in reality they can only return 0 on success and < 0 on
error.

Update the comments to say < 0 on error to match the behavior.

While at it, improve cat_val() comment to state that 0 means the test
was run (either pass or fail).

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cache.c     |  2 +-
 tools/testing/selftests/resctrl/resctrlfs.c | 10 +++++-----
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c
index 6d60a2f1b3aa9..a9a0394b3d08b 100644
--- a/tools/testing/selftests/resctrl/cache.c
+++ b/tools/testing/selftests/resctrl/cache.c
@@ -206,7 +206,7 @@ int measure_cache_vals(struct resctrl_val_param *param, int bm_pid)
  * @param:		parameters passed to cache_val()
  * @span:		buffer size for the benchmark
  *
- * Return:		0 on success. non-zero on failure.
+ * Return:		0 when the test was run, < 0 on error.
  */
 int cat_val(struct resctrl_val_param *param, size_t span)
 {
diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index dbd2f951df199..72b3dc22bbf3b 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -56,7 +56,7 @@ static int find_resctrl_mount(char *buffer)
  * Mounts resctrl FS. Fails if resctrl FS is already mounted to avoid
  * pre-existing settings interfering with the test results.
  *
- * Return: 0 on success, non-zero on failure
+ * Return: 0 on success, < 0 on error.
  */
 int mount_resctrlfs(void)
 {
@@ -276,7 +276,7 @@ int get_core_sibling(int cpu_no)
  * @bm_pid:	PID that should be binded
  * @cpu_no:	CPU number at which the PID would be binded
  *
- * Return: 0 on success, non-zero on failure
+ * Return: 0 on success, < 0 on error.
  */
 int taskset_benchmark(pid_t bm_pid, int cpu_no)
 {
@@ -300,7 +300,7 @@ int taskset_benchmark(pid_t bm_pid, int cpu_no)
  * @grp:	Full path and name of the group
  * @parent_grp:	Full path and name of the parent group
  *
- * Return: 0 on success, non-zero on failure
+ * Return: 0 on success, < 0 on error.
  */
 static int create_grp(const char *grp_name, char *grp, const char *parent_grp)
 {
@@ -376,7 +376,7 @@ static int write_pid_to_tasks(char *tasks, pid_t pid)
  * pid is not written, this means that pid is in con_mon grp and hence
  * should consult con_mon grp's mon_data directory for results.
  *
- * Return: 0 on success, non-zero on failure
+ * Return: 0 on success, < 0 on error.
  */
 int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp,
 			    char *resctrl_val)
@@ -435,7 +435,7 @@ int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp,
  * Update schemata of a con_mon grp *only* if requested resctrl feature is
  * allocation type
  *
- * Return: 0 on success, non-zero on failure
+ * Return: 0 on success, < 0 on error.
  */
 int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, char *resctrl_val)
 {

From 0e8910d47b74ff43b95ca01b3a26bd55dc2be8cd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 15 Dec 2023 17:04:53 +0200
Subject: [PATCH 157/236] selftests/resctrl: Refactor get_cbm_mask() and rename
 to get_full_cbm()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 4b357e2a6d6c364a88d50526675fe596a30766cb upstream.

Callers of get_cbm_mask() are required to pass a string into which the
capacity bitmask (CBM) is read. Neither CAT nor CMT tests need the
bitmask as string but just convert it into an unsigned long value.

Another limitation is that the bit mask reader can only read
.../cbm_mask files.

Generalize the bit mask reading function into get_bit_mask() such that
it can be used to handle other files besides the .../cbm_mask and
handles the unsigned long conversion within get_bit_mask() using
fscanf(). Change get_cbm_mask() to use get_bit_mask() and rename it to
get_full_cbm() to better indicate what the function does.

Return error from get_full_cbm() if the bitmask is zero for some reason
because it makes the code more robust as the selftests naturally assume
the bitmask has some bits.

Also mark cache_type const while at it and remove useless comments that
are related to processing of CBM bits.

Co-developed-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cat_test.c  |  7 +--
 tools/testing/selftests/resctrl/cmt_test.c  |  5 +-
 tools/testing/selftests/resctrl/resctrl.h   |  2 +-
 tools/testing/selftests/resctrl/resctrlfs.c | 51 +++++++++++++++------
 4 files changed, 41 insertions(+), 24 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
index fabb56ff68d16..242c4c6200aa2 100644
--- a/tools/testing/selftests/resctrl/cat_test.c
+++ b/tools/testing/selftests/resctrl/cat_test.c
@@ -93,25 +93,20 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type)
 	int ret, pipefd[2], sibling_cpu_no;
 	unsigned long cache_size = 0;
 	unsigned long long_mask;
-	char cbm_mask[256];
 	int count_of_bits;
 	char pipe_message;
 	size_t span;
 
-	/* Get default cbm mask for L3/L2 cache */
-	ret = get_cbm_mask(cache_type, cbm_mask);
+	ret = get_full_cbm(cache_type, &long_mask);
 	if (ret)
 		return ret;
 
-	long_mask = strtoul(cbm_mask, NULL, 16);
-
 	/* Get L3/L2 cache size */
 	ret = get_cache_size(cpu_no, cache_type, &cache_size);
 	if (ret)
 		return ret;
 	ksft_print_msg("Cache size :%lu\n", cache_size);
 
-	/* Get max number of bits from default-cabm mask */
 	count_of_bits = count_bits(long_mask);
 
 	if (!n)
diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c
index ffd302bd5c738..a18c6825802c1 100644
--- a/tools/testing/selftests/resctrl/cmt_test.c
+++ b/tools/testing/selftests/resctrl/cmt_test.c
@@ -75,17 +75,14 @@ int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd)
 	unsigned long cache_size = 0;
 	unsigned long long_mask;
 	char *span_str = NULL;
-	char cbm_mask[256];
 	int count_of_bits;
 	size_t span;
 	int ret, i;
 
-	ret = get_cbm_mask("L3", cbm_mask);
+	ret = get_full_cbm("L3", &long_mask);
 	if (ret)
 		return ret;
 
-	long_mask = strtoul(cbm_mask, NULL, 16);
-
 	ret = get_cache_size(cpu_no, "L3", &cache_size);
 	if (ret)
 		return ret;
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index a848e9c755787..89cd89507891a 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -98,7 +98,7 @@ void tests_cleanup(void);
 void mbm_test_cleanup(void);
 int mba_schemata_change(int cpu_no, const char * const *benchmark_cmd);
 void mba_test_cleanup(void);
-int get_cbm_mask(char *cache_type, char *cbm_mask);
+int get_full_cbm(const char *cache_type, unsigned long *mask);
 int get_cache_size(int cpu_no, char *cache_type, unsigned long *cache_size);
 void ctrlc_handler(int signum, siginfo_t *info, void *ptr);
 int signal_handler_register(void);
diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index 72b3dc22bbf3b..5608690adb073 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -196,30 +196,29 @@ int get_cache_size(int cpu_no, char *cache_type, unsigned long *cache_size)
 #define CORE_SIBLINGS_PATH	"/sys/bus/cpu/devices/cpu"
 
 /*
- * get_cbm_mask - Get cbm mask for given cache
- * @cache_type:	Cache level L2/L3
- * @cbm_mask:	cbm_mask returned as a string
+ * get_bit_mask - Get bit mask from given file
+ * @filename:	File containing the mask
+ * @mask:	The bit mask returned as unsigned long
  *
  * Return: = 0 on success, < 0 on failure.
  */
-int get_cbm_mask(char *cache_type, char *cbm_mask)
+static int get_bit_mask(const char *filename, unsigned long *mask)
 {
-	char cbm_mask_path[1024];
 	FILE *fp;
 
-	if (!cbm_mask)
+	if (!filename || !mask)
 		return -1;
 
-	sprintf(cbm_mask_path, "%s/%s/cbm_mask", INFO_PATH, cache_type);
-
-	fp = fopen(cbm_mask_path, "r");
+	fp = fopen(filename, "r");
 	if (!fp) {
-		ksft_perror("Failed to open cache level");
-
+		ksft_print_msg("Failed to open bit mask file '%s': %s\n",
+			       filename, strerror(errno));
 		return -1;
 	}
-	if (fscanf(fp, "%s", cbm_mask) <= 0) {
-		ksft_perror("Could not get max cbm_mask");
+
+	if (fscanf(fp, "%lx", mask) <= 0) {
+		ksft_print_msg("Could not read bit mask file '%s': %s\n",
+			       filename, strerror(errno));
 		fclose(fp);
 
 		return -1;
@@ -229,6 +228,32 @@ int get_cbm_mask(char *cache_type, char *cbm_mask)
 	return 0;
 }
 
+/*
+ * get_full_cbm - Get full Cache Bit Mask (CBM)
+ * @cache_type:	Cache type as "L2" or "L3"
+ * @mask:	Full cache bit mask representing the maximal portion of cache
+ *		available for allocation, returned as unsigned long.
+ *
+ * Return: = 0 on success, < 0 on failure.
+ */
+int get_full_cbm(const char *cache_type, unsigned long *mask)
+{
+	char cbm_path[PATH_MAX];
+	int ret;
+
+	if (!cache_type)
+		return -1;
+
+	snprintf(cbm_path, sizeof(cbm_path), "%s/%s/cbm_mask",
+		 INFO_PATH, cache_type);
+
+	ret = get_bit_mask(cbm_path, mask);
+	if (ret || !*mask)
+		return -1;
+
+	return 0;
+}
+
 /*
  * get_core_sibling - Get sibling core id from the same socket for given CPU
  * @cpu_no:	CPU number

From 34416303100920bcb63b0d8bfe8a47d920b1de75 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 15 Dec 2023 17:04:54 +0200
Subject: [PATCH 158/236] selftests/resctrl: Mark get_cache_size() cache_type
 const
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 60c2a6926cc94dcd8a60ab593b4092bc354061c3 upstream.

get_cache_size() does not modify cache_type so it could be const.

Mark cache_type const so that const char * can be passed to it. This
prevents warnings once many of the test parameters are marked const.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/resctrl.h   | 2 +-
 tools/testing/selftests/resctrl/resctrlfs.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 89cd89507891a..9e5777e1eee34 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -99,7 +99,7 @@ void mbm_test_cleanup(void);
 int mba_schemata_change(int cpu_no, const char * const *benchmark_cmd);
 void mba_test_cleanup(void);
 int get_full_cbm(const char *cache_type, unsigned long *mask);
-int get_cache_size(int cpu_no, char *cache_type, unsigned long *cache_size);
+int get_cache_size(int cpu_no, const char *cache_type, unsigned long *cache_size);
 void ctrlc_handler(int signum, siginfo_t *info, void *ptr);
 int signal_handler_register(void);
 void signal_handler_unregister(void);
diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index 5608690adb073..a830b438c6b75 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -138,7 +138,7 @@ int get_resource_id(int cpu_no, int *resource_id)
  *
  * Return: = 0 on success, < 0 on failure.
  */
-int get_cache_size(int cpu_no, char *cache_type, unsigned long *cache_size)
+int get_cache_size(int cpu_no, const char *cache_type, unsigned long *cache_size)
 {
 	char cache_path[1024], cache_str[64];
 	int length, i, cache_num;

From f1e09b3261db5774395af6704fe445ba96a0a787 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 15 Dec 2023 17:04:55 +0200
Subject: [PATCH 159/236] selftests/resctrl: Create cache_portion_size() helper
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 19e94a2333c2babc773e51a9ed844cfc35a36064 upstream.

CAT and CMT tests calculate size of the cache portion for the n-bits
cache allocation on their own.

Add cache_portion_size() helper that calculates size of the cache
portion for the given number of bits and use it to replace the existing
span calculations. This also prepares for the new CAT test that will
need to determine the size of the cache portion also during results
processing.

Rename also 'cache_size' local variables to 'cache_total_size' to
prevent misinterpretations.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cat_test.c | 10 ++++-----
 tools/testing/selftests/resctrl/cmt_test.c |  8 ++++----
 tools/testing/selftests/resctrl/resctrl.h  | 24 ++++++++++++++++++++++
 3 files changed, 33 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
index 242c4c6200aa2..f18c95dda5d36 100644
--- a/tools/testing/selftests/resctrl/cat_test.c
+++ b/tools/testing/selftests/resctrl/cat_test.c
@@ -91,7 +91,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type)
 {
 	unsigned long l_mask, l_mask_1;
 	int ret, pipefd[2], sibling_cpu_no;
-	unsigned long cache_size = 0;
+	unsigned long cache_total_size = 0;
 	unsigned long long_mask;
 	int count_of_bits;
 	char pipe_message;
@@ -102,10 +102,10 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type)
 		return ret;
 
 	/* Get L3/L2 cache size */
-	ret = get_cache_size(cpu_no, cache_type, &cache_size);
+	ret = get_cache_size(cpu_no, cache_type, &cache_total_size);
 	if (ret)
 		return ret;
-	ksft_print_msg("Cache size :%lu\n", cache_size);
+	ksft_print_msg("Cache size :%lu\n", cache_total_size);
 
 	count_of_bits = count_bits(long_mask);
 
@@ -136,7 +136,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type)
 	/* Set param values for parent thread which will be allocated bitmask
 	 * with (max_bits - n) bits
 	 */
-	span = cache_size * (count_of_bits - n) / count_of_bits;
+	span = cache_portion_size(cache_total_size, l_mask, long_mask);
 	strcpy(param.ctrlgrp, "c2");
 	strcpy(param.mongrp, "m2");
 	strcpy(param.filename, RESULT_FILE_NAME2);
@@ -158,7 +158,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type)
 		param.mask = l_mask_1;
 		strcpy(param.ctrlgrp, "c1");
 		strcpy(param.mongrp, "m1");
-		span = cache_size * n / count_of_bits;
+		span = cache_portion_size(cache_total_size, l_mask_1, long_mask);
 		strcpy(param.filename, RESULT_FILE_NAME1);
 		param.num_of_runs = 0;
 		param.cpu_no = sibling_cpu_no;
diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c
index a18c6825802c1..a14d46353865c 100644
--- a/tools/testing/selftests/resctrl/cmt_test.c
+++ b/tools/testing/selftests/resctrl/cmt_test.c
@@ -72,7 +72,7 @@ int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd)
 {
 	const char * const *cmd = benchmark_cmd;
 	const char *new_cmd[BENCHMARK_ARGS];
-	unsigned long cache_size = 0;
+	unsigned long cache_total_size = 0;
 	unsigned long long_mask;
 	char *span_str = NULL;
 	int count_of_bits;
@@ -83,10 +83,10 @@ int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd)
 	if (ret)
 		return ret;
 
-	ret = get_cache_size(cpu_no, "L3", &cache_size);
+	ret = get_cache_size(cpu_no, "L3", &cache_total_size);
 	if (ret)
 		return ret;
-	ksft_print_msg("Cache size :%lu\n", cache_size);
+	ksft_print_msg("Cache size :%lu\n", cache_total_size);
 
 	count_of_bits = count_bits(long_mask);
 
@@ -107,7 +107,7 @@ int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd)
 		.setup		= cmt_setup,
 	};
 
-	span = cache_size * n / count_of_bits;
+	span = cache_portion_size(cache_total_size, param.mask, long_mask);
 
 	if (strcmp(cmd[0], "fill_buf") == 0) {
 		/* Duplicate the command to be able to replace span in it */
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 9e5777e1eee34..08647f2c07f50 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -116,4 +116,28 @@ int show_cache_info(unsigned long sum_llc_val, int no_of_bits,
 		    unsigned long max_diff_percent, unsigned long num_of_runs,
 		    bool platform, bool cmt);
 
+/*
+ * cache_portion_size - Calculate the size of a cache portion
+ * @cache_size:		Total cache size in bytes
+ * @portion_mask:	Cache portion mask
+ * @full_cache_mask:	Full Cache Bit Mask (CBM) for the cache
+ *
+ * Return: The size of the cache portion in bytes.
+ */
+static inline unsigned long cache_portion_size(unsigned long cache_size,
+					       unsigned long portion_mask,
+					       unsigned long full_cache_mask)
+{
+	unsigned int bits = count_bits(full_cache_mask);
+
+	/*
+	 * With no bits the full CBM, assume cache cannot be split into
+	 * smaller portions. To avoid divide by zero, return cache_size.
+	 */
+	if (!bits)
+		return cache_size;
+
+	return cache_size * count_bits(portion_mask) / bits;
+}
+
 #endif /* RESCTRL_H */

From 7250fb24fd04f6d7ee37bd073e1ff612ca54529b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 15 Dec 2023 17:04:56 +0200
Subject: [PATCH 160/236] selftests/resctrl: Exclude shareable bits from
 schemata in CAT test
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit b6dfac948686799169c899557a179b84d0d1f47e upstream.

CAT test doesn't take shareable bits into account, i.e., the test might
be sharing cache with some devices (e.g., graphics).

Introduce get_mask_no_shareable() and use it to provision an
environment for CAT test where the allocated LLC is isolated better.
Excluding shareable_bits may create hole(s) into the cbm_mask, thus add
a new helper count_contiguous_bits() to find the longest contiguous set
of CBM bits.

create_bit_mask() is needed by an upcoming CAT test rewrite so make it
available in resctrl.h right away.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cat_test.c  | 12 ++-
 tools/testing/selftests/resctrl/resctrl.h   |  2 +
 tools/testing/selftests/resctrl/resctrlfs.c | 89 +++++++++++++++++++++
 3 files changed, 99 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
index f18c95dda5d36..1e3c5432ecffa 100644
--- a/tools/testing/selftests/resctrl/cat_test.c
+++ b/tools/testing/selftests/resctrl/cat_test.c
@@ -89,15 +89,19 @@ void cat_test_cleanup(void)
 
 int cat_perf_miss_val(int cpu_no, int n, char *cache_type)
 {
+	unsigned long full_cache_mask, long_mask;
 	unsigned long l_mask, l_mask_1;
 	int ret, pipefd[2], sibling_cpu_no;
 	unsigned long cache_total_size = 0;
-	unsigned long long_mask;
 	int count_of_bits;
 	char pipe_message;
 	size_t span;
 
-	ret = get_full_cbm(cache_type, &long_mask);
+	ret = get_full_cbm(cache_type, &full_cache_mask);
+	if (ret)
+		return ret;
+	/* Get the largest contiguous exclusive portion of the cache */
+	ret = get_mask_no_shareable(cache_type, &long_mask);
 	if (ret)
 		return ret;
 
@@ -136,7 +140,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type)
 	/* Set param values for parent thread which will be allocated bitmask
 	 * with (max_bits - n) bits
 	 */
-	span = cache_portion_size(cache_total_size, l_mask, long_mask);
+	span = cache_portion_size(cache_total_size, l_mask, full_cache_mask);
 	strcpy(param.ctrlgrp, "c2");
 	strcpy(param.mongrp, "m2");
 	strcpy(param.filename, RESULT_FILE_NAME2);
@@ -158,7 +162,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type)
 		param.mask = l_mask_1;
 		strcpy(param.ctrlgrp, "c1");
 		strcpy(param.mongrp, "m1");
-		span = cache_portion_size(cache_total_size, l_mask_1, long_mask);
+		span = cache_portion_size(cache_total_size, l_mask_1, full_cache_mask);
 		strcpy(param.filename, RESULT_FILE_NAME1);
 		param.num_of_runs = 0;
 		param.cpu_no = sibling_cpu_no;
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 08647f2c07f50..72381b51cf5f2 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -98,7 +98,9 @@ void tests_cleanup(void);
 void mbm_test_cleanup(void);
 int mba_schemata_change(int cpu_no, const char * const *benchmark_cmd);
 void mba_test_cleanup(void);
+unsigned long create_bit_mask(unsigned int start, unsigned int len);
 int get_full_cbm(const char *cache_type, unsigned long *mask);
+int get_mask_no_shareable(const char *cache_type, unsigned long *mask);
 int get_cache_size(int cpu_no, const char *cache_type, unsigned long *cache_size);
 void ctrlc_handler(int signum, siginfo_t *info, void *ptr);
 int signal_handler_register(void);
diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index a830b438c6b75..a51f2018e2c5d 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -228,6 +228,44 @@ static int get_bit_mask(const char *filename, unsigned long *mask)
 	return 0;
 }
 
+/*
+ * create_bit_mask- Create bit mask from start, len pair
+ * @start:	LSB of the mask
+ * @len		Number of bits in the mask
+ */
+unsigned long create_bit_mask(unsigned int start, unsigned int len)
+{
+	return ((1UL << len) - 1UL) << start;
+}
+
+/*
+ * count_contiguous_bits - Returns the longest train of bits in a bit mask
+ * @val		A bit mask
+ * @start	The location of the least-significant bit of the longest train
+ *
+ * Return:	The length of the contiguous bits in the longest train of bits
+ */
+static unsigned int count_contiguous_bits(unsigned long val, unsigned int *start)
+{
+	unsigned long last_val;
+	unsigned int count = 0;
+
+	while (val) {
+		last_val = val;
+		val &= (val >> 1);
+		count++;
+	}
+
+	if (start) {
+		if (count)
+			*start = ffsl(last_val) - 1;
+		else
+			*start = 0;
+	}
+
+	return count;
+}
+
 /*
  * get_full_cbm - Get full Cache Bit Mask (CBM)
  * @cache_type:	Cache type as "L2" or "L3"
@@ -254,6 +292,57 @@ int get_full_cbm(const char *cache_type, unsigned long *mask)
 	return 0;
 }
 
+/*
+ * get_shareable_mask - Get shareable mask from shareable_bits
+ * @cache_type:		Cache type as "L2" or "L3"
+ * @shareable_mask:	Shareable mask returned as unsigned long
+ *
+ * Return: = 0 on success, < 0 on failure.
+ */
+static int get_shareable_mask(const char *cache_type, unsigned long *shareable_mask)
+{
+	char mask_path[PATH_MAX];
+
+	if (!cache_type)
+		return -1;
+
+	snprintf(mask_path, sizeof(mask_path), "%s/%s/shareable_bits",
+		 INFO_PATH, cache_type);
+
+	return get_bit_mask(mask_path, shareable_mask);
+}
+
+/*
+ * get_mask_no_shareable - Get Cache Bit Mask (CBM) without shareable bits
+ * @cache_type:		Cache type as "L2" or "L3"
+ * @mask:		The largest exclusive portion of the cache out of the
+ *			full CBM, returned as unsigned long
+ *
+ * Parts of a cache may be shared with other devices such as GPU. This function
+ * calculates the largest exclusive portion of the cache where no other devices
+ * besides CPU have access to the cache portion.
+ *
+ * Return: = 0 on success, < 0 on failure.
+ */
+int get_mask_no_shareable(const char *cache_type, unsigned long *mask)
+{
+	unsigned long full_mask, shareable_mask;
+	unsigned int start, len;
+
+	if (get_full_cbm(cache_type, &full_mask) < 0)
+		return -1;
+	if (get_shareable_mask(cache_type, &shareable_mask) < 0)
+		return -1;
+
+	len = count_contiguous_bits(full_mask & ~shareable_mask, &start);
+	if (!len)
+		return -1;
+
+	*mask = create_bit_mask(start, len);
+
+	return 0;
+}
+
 /*
  * get_core_sibling - Get sibling core id from the same socket for given CPU
  * @cpu_no:	CPU number

From bd4f8c3f2b507258bc0a64624edc66a535e2c032 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 15 Dec 2023 17:04:57 +0200
Subject: [PATCH 161/236] selftests/resctrl: Split measure_cache_vals()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit a575c9734f3021f1fc81c2477ecaee4d9841fd59 upstream.

measure_cache_vals() does a different thing depending on the test case
that called it:
  - For CAT, it measures LLC misses through perf.
  - For CMT, it measures LLC occupancy through resctrl.

Split these two functionalities into own functions the CAT and CMT
tests can call directly. Replace passing the struct resctrl_val_param
parameter with the filename because it's more generic and all those
functions need out of resctrl_val.

Co-developed-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cache.c       | 64 +++++++++++--------
 tools/testing/selftests/resctrl/resctrl.h     |  2 +-
 tools/testing/selftests/resctrl/resctrl_val.c |  2 +-
 3 files changed, 41 insertions(+), 27 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c
index a9a0394b3d08b..0c18603435c8a 100644
--- a/tools/testing/selftests/resctrl/cache.c
+++ b/tools/testing/selftests/resctrl/cache.c
@@ -147,7 +147,7 @@ static int get_llc_occu_resctrl(unsigned long *llc_occupancy)
  *
  * Return:		0 on success, < 0 on error.
  */
-static int print_results_cache(char *filename, int bm_pid,
+static int print_results_cache(const char *filename, int bm_pid,
 			       unsigned long llc_value)
 {
 	FILE *fp;
@@ -169,35 +169,49 @@ static int print_results_cache(char *filename, int bm_pid,
 	return 0;
 }
 
-int measure_cache_vals(struct resctrl_val_param *param, int bm_pid)
+/*
+ * perf_event_measure - Measure perf events
+ * @filename:	Filename for writing the results
+ * @bm_pid:	PID that runs the benchmark
+ *
+ * Measures perf events (e.g., cache misses) and writes the results into
+ * @filename. @bm_pid is written to the results file along with the measured
+ * value.
+ *
+ * Return: =0 on success. <0 on failure.
+ */
+static int perf_event_measure(const char *filename, int bm_pid)
 {
-	unsigned long llc_perf_miss = 0, llc_occu_resc = 0, llc_value = 0;
+	unsigned long llc_perf_miss = 0;
 	int ret;
 
-	/*
-	 * Measure cache miss from perf.
-	 */
-	if (!strncmp(param->resctrl_val, CAT_STR, sizeof(CAT_STR))) {
-		ret = get_llc_perf(&llc_perf_miss);
-		if (ret < 0)
-			return ret;
-		llc_value = llc_perf_miss;
-	}
+	ret = get_llc_perf(&llc_perf_miss);
+	if (ret < 0)
+		return ret;
 
-	/*
-	 * Measure llc occupancy from resctrl.
-	 */
-	if (!strncmp(param->resctrl_val, CMT_STR, sizeof(CMT_STR))) {
-		ret = get_llc_occu_resctrl(&llc_occu_resc);
-		if (ret < 0)
-			return ret;
-		llc_value = llc_occu_resc;
-	}
-	ret = print_results_cache(param->filename, bm_pid, llc_value);
-	if (ret)
+	return print_results_cache(filename, bm_pid, llc_perf_miss);
+}
+
+/*
+ * measure_llc_resctrl - Measure resctrl LLC value from resctrl
+ * @filename:	Filename for writing the results
+ * @bm_pid:	PID that runs the benchmark
+ *
+ * Measures LLC occupancy from resctrl and writes the results into @filename.
+ * @bm_pid is written to the results file along with the measured value.
+ *
+ * Return: =0 on success. <0 on failure.
+ */
+int measure_llc_resctrl(const char *filename, int bm_pid)
+{
+	unsigned long llc_occu_resc = 0;
+	int ret;
+
+	ret = get_llc_occu_resctrl(&llc_occu_resc);
+	if (ret < 0)
 		return ret;
 
-	return 0;
+	return print_results_cache(filename, bm_pid, llc_occu_resc);
 }
 
 /*
@@ -252,7 +266,7 @@ int cat_val(struct resctrl_val_param *param, size_t span)
 		}
 
 		sleep(1);
-		ret = measure_cache_vals(param, bm_pid);
+		ret = perf_event_measure(param->filename, bm_pid);
 		if (ret)
 			goto pe_close;
 	}
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 72381b51cf5f2..3983226065f38 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -112,7 +112,7 @@ int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd);
 unsigned int count_bits(unsigned long n);
 void cmt_test_cleanup(void);
 int get_core_sibling(int cpu_no);
-int measure_cache_vals(struct resctrl_val_param *param, int bm_pid);
+int measure_llc_resctrl(const char *filename, int bm_pid);
 int show_cache_info(unsigned long sum_llc_val, int no_of_bits,
 		    size_t cache_span, unsigned long max_diff,
 		    unsigned long max_diff_percent, unsigned long num_of_runs,
diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index bf1f9e627b6bc..836cfa2ec1e98 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -855,7 +855,7 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
 				break;
 		} else if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) {
 			sleep(1);
-			ret = measure_cache_vals(param, bm_pid);
+			ret = measure_llc_resctrl(param->filename, bm_pid);
 			if (ret)
 				break;
 		}

From 8619b245c3b3bf173f2edc2e8cc0883473808244 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 15 Dec 2023 17:04:58 +0200
Subject: [PATCH 162/236] selftests/resctrl: Split show_cache_info() to test
 specific and generic parts
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 5caf1b6400d30a31363063314bddea4e5680d639 upstream.

show_cache_info() calculates results and provides generic cache
information. This makes it hard to alter pass/fail conditions.

Separate the test specific checks into CAT and CMT test files and
leave only the generic information part into show_cache_info().

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cache.c    | 42 +++++-----------------
 tools/testing/selftests/resctrl/cat_test.c | 30 ++++++++++++++--
 tools/testing/selftests/resctrl/cmt_test.c | 32 +++++++++++++++--
 tools/testing/selftests/resctrl/resctrl.h  |  6 ++--
 4 files changed, 66 insertions(+), 44 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c
index 0c18603435c8a..32e262fa2a6cb 100644
--- a/tools/testing/selftests/resctrl/cache.c
+++ b/tools/testing/selftests/resctrl/cache.c
@@ -279,43 +279,17 @@ int cat_val(struct resctrl_val_param *param, size_t span)
 }
 
 /*
- * show_cache_info:	show cache test result information
- * @sum_llc_val:	sum of LLC cache result data
- * @no_of_bits:		number of bits
- * @cache_span:		cache span in bytes for CMT or in lines for CAT
- * @max_diff:		max difference
- * @max_diff_percent:	max difference percentage
- * @num_of_runs:	number of runs
- * @platform:		show test information on this platform
- * @cmt:		CMT test or CAT test
- *
- * Return:		0 on success. non-zero on failure.
+ * show_cache_info - Show generic cache test information
+ * @no_of_bits:		Number of bits
+ * @avg_llc_val:	Average of LLC cache result data
+ * @cache_span:		Cache span
+ * @lines:		@cache_span in lines or bytes
  */
-int show_cache_info(unsigned long sum_llc_val, int no_of_bits,
-		    size_t cache_span, unsigned long max_diff,
-		    unsigned long max_diff_percent, unsigned long num_of_runs,
-		    bool platform, bool cmt)
+void show_cache_info(int no_of_bits, unsigned long avg_llc_val,
+		     size_t cache_span, bool lines)
 {
-	unsigned long avg_llc_val = 0;
-	float diff_percent;
-	long avg_diff = 0;
-	int ret;
-
-	avg_llc_val = sum_llc_val / num_of_runs;
-	avg_diff = (long)abs(cache_span - avg_llc_val);
-	diff_percent = ((float)cache_span - avg_llc_val) / cache_span * 100;
-
-	ret = platform && abs((int)diff_percent) > max_diff_percent &&
-	      (cmt ? (abs(avg_diff) > max_diff) : true);
-
-	ksft_print_msg("%s Check cache miss rate within %lu%%\n",
-		       ret ? "Fail:" : "Pass:", max_diff_percent);
-
-	ksft_print_msg("Percent diff=%d\n", abs((int)diff_percent));
 	ksft_print_msg("Number of bits: %d\n", no_of_bits);
 	ksft_print_msg("Average LLC val: %lu\n", avg_llc_val);
-	ksft_print_msg("Cache span (%s): %zu\n", cmt ? "bytes" : "lines",
+	ksft_print_msg("Cache span (%s): %zu\n", lines ? "lines" : "bytes",
 		       cache_span);
-
-	return ret;
 }
diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
index 1e3c5432ecffa..0955f819bd83d 100644
--- a/tools/testing/selftests/resctrl/cat_test.c
+++ b/tools/testing/selftests/resctrl/cat_test.c
@@ -41,6 +41,30 @@ static int cat_setup(struct resctrl_val_param *p)
 	return ret;
 }
 
+static int show_results_info(unsigned long sum_llc_val, int no_of_bits,
+			     unsigned long cache_span, unsigned long max_diff,
+			     unsigned long max_diff_percent, unsigned long num_of_runs,
+			     bool platform)
+{
+	unsigned long avg_llc_val = 0;
+	float diff_percent;
+	int ret;
+
+	avg_llc_val = sum_llc_val / num_of_runs;
+	diff_percent = ((float)cache_span - avg_llc_val) / cache_span * 100;
+
+	ret = platform && abs((int)diff_percent) > max_diff_percent;
+
+	ksft_print_msg("%s Check cache miss rate within %lu%%\n",
+		       ret ? "Fail:" : "Pass:", max_diff_percent);
+
+	ksft_print_msg("Percent diff=%d\n", abs((int)diff_percent));
+
+	show_cache_info(no_of_bits, avg_llc_val, cache_span, true);
+
+	return ret;
+}
+
 static int check_results(struct resctrl_val_param *param, size_t span)
 {
 	char *token_array[8], temp[512];
@@ -76,9 +100,9 @@ static int check_results(struct resctrl_val_param *param, size_t span)
 	fclose(fp);
 	no_of_bits = count_bits(param->mask);
 
-	return show_cache_info(sum_llc_perf_miss, no_of_bits, span / 64,
-			       MAX_DIFF, MAX_DIFF_PERCENT, runs - 1,
-			       get_vendor() == ARCH_INTEL, false);
+	return show_results_info(sum_llc_perf_miss, no_of_bits, span / 64,
+				 MAX_DIFF, MAX_DIFF_PERCENT, runs - 1,
+				 get_vendor() == ARCH_INTEL);
 }
 
 void cat_test_cleanup(void)
diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c
index a14d46353865c..604690cd8b3e9 100644
--- a/tools/testing/selftests/resctrl/cmt_test.c
+++ b/tools/testing/selftests/resctrl/cmt_test.c
@@ -27,6 +27,33 @@ static int cmt_setup(struct resctrl_val_param *p)
 	return 0;
 }
 
+static int show_results_info(unsigned long sum_llc_val, int no_of_bits,
+			     unsigned long cache_span, unsigned long max_diff,
+			     unsigned long max_diff_percent, unsigned long num_of_runs,
+			     bool platform)
+{
+	unsigned long avg_llc_val = 0;
+	float diff_percent;
+	long avg_diff = 0;
+	int ret;
+
+	avg_llc_val = sum_llc_val / num_of_runs;
+	avg_diff = (long)abs(cache_span - avg_llc_val);
+	diff_percent = ((float)cache_span - avg_llc_val) / cache_span * 100;
+
+	ret = platform && abs((int)diff_percent) > max_diff_percent &&
+	      abs(avg_diff) > max_diff;
+
+	ksft_print_msg("%s Check cache miss rate within %lu%%\n",
+		       ret ? "Fail:" : "Pass:", max_diff_percent);
+
+	ksft_print_msg("Percent diff=%d\n", abs((int)diff_percent));
+
+	show_cache_info(no_of_bits, avg_llc_val, cache_span, false);
+
+	return ret;
+}
+
 static int check_results(struct resctrl_val_param *param, size_t span, int no_of_bits)
 {
 	char *token_array[8], temp[512];
@@ -58,9 +85,8 @@ static int check_results(struct resctrl_val_param *param, size_t span, int no_of
 	}
 	fclose(fp);
 
-	return show_cache_info(sum_llc_occu_resc, no_of_bits, span,
-			       MAX_DIFF, MAX_DIFF_PERCENT, runs - 1,
-			       true, true);
+	return show_results_info(sum_llc_occu_resc, no_of_bits, span,
+				 MAX_DIFF, MAX_DIFF_PERCENT, runs - 1, true);
 }
 
 void cmt_test_cleanup(void)
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 3983226065f38..47b871df2b0e6 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -113,10 +113,8 @@ unsigned int count_bits(unsigned long n);
 void cmt_test_cleanup(void);
 int get_core_sibling(int cpu_no);
 int measure_llc_resctrl(const char *filename, int bm_pid);
-int show_cache_info(unsigned long sum_llc_val, int no_of_bits,
-		    size_t cache_span, unsigned long max_diff,
-		    unsigned long max_diff_percent, unsigned long num_of_runs,
-		    bool platform, bool cmt);
+void show_cache_info(int no_of_bits, unsigned long avg_llc_val,
+		     size_t cache_span, bool lines);
 
 /*
  * cache_portion_size - Calculate the size of a cache portion

From 167cb99c286af35835180c404e71de1662495216 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 15 Dec 2023 17:04:59 +0200
Subject: [PATCH 163/236] selftests/resctrl: Remove unnecessary __u64 ->
 unsigned long conversion
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 33403bc7fe2ec35cd87e4f11db4d1a1da1e5ce12 upstream.

Perf counters are __u64 but the code converts them to unsigned long
before printing them out.

Remove unnecessary type conversion and retain the perf originating
value as __u64.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cache.c    | 21 ++++++++-------------
 tools/testing/selftests/resctrl/cat_test.c |  8 ++++----
 tools/testing/selftests/resctrl/resctrl.h  |  3 +--
 3 files changed, 13 insertions(+), 19 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c
index 32e262fa2a6cb..11d1a6ce14c21 100644
--- a/tools/testing/selftests/resctrl/cache.c
+++ b/tools/testing/selftests/resctrl/cache.c
@@ -83,9 +83,8 @@ static int reset_enable_llc_perf(pid_t pid, int cpu_no)
  *
  * Return: =0 on success.  <0 on failure.
  */
-static int get_llc_perf(unsigned long *llc_perf_miss)
+static int get_llc_perf(__u64 *llc_perf_miss)
 {
-	__u64 total_misses;
 	int ret;
 
 	/* Stop counters after one span to get miss rate */
@@ -98,8 +97,7 @@ static int get_llc_perf(unsigned long *llc_perf_miss)
 		return -1;
 	}
 
-	total_misses = rf_cqm.values[0].value;
-	*llc_perf_miss = total_misses;
+	*llc_perf_miss = rf_cqm.values[0].value;
 
 	return 0;
 }
@@ -147,14 +145,12 @@ static int get_llc_occu_resctrl(unsigned long *llc_occupancy)
  *
  * Return:		0 on success, < 0 on error.
  */
-static int print_results_cache(const char *filename, int bm_pid,
-			       unsigned long llc_value)
+static int print_results_cache(const char *filename, int bm_pid, __u64 llc_value)
 {
 	FILE *fp;
 
 	if (strcmp(filename, "stdio") == 0 || strcmp(filename, "stderr") == 0) {
-		printf("Pid: %d \t LLC_value: %lu\n", bm_pid,
-		       llc_value);
+		printf("Pid: %d \t LLC_value: %llu\n", bm_pid, llc_value);
 	} else {
 		fp = fopen(filename, "a");
 		if (!fp) {
@@ -162,7 +158,7 @@ static int print_results_cache(const char *filename, int bm_pid,
 
 			return -1;
 		}
-		fprintf(fp, "Pid: %d \t llc_value: %lu\n", bm_pid, llc_value);
+		fprintf(fp, "Pid: %d \t llc_value: %llu\n", bm_pid, llc_value);
 		fclose(fp);
 	}
 
@@ -182,7 +178,7 @@ static int print_results_cache(const char *filename, int bm_pid,
  */
 static int perf_event_measure(const char *filename, int bm_pid)
 {
-	unsigned long llc_perf_miss = 0;
+	__u64 llc_perf_miss = 0;
 	int ret;
 
 	ret = get_llc_perf(&llc_perf_miss);
@@ -285,11 +281,10 @@ int cat_val(struct resctrl_val_param *param, size_t span)
  * @cache_span:		Cache span
  * @lines:		@cache_span in lines or bytes
  */
-void show_cache_info(int no_of_bits, unsigned long avg_llc_val,
-		     size_t cache_span, bool lines)
+void show_cache_info(int no_of_bits, __u64 avg_llc_val, size_t cache_span, bool lines)
 {
 	ksft_print_msg("Number of bits: %d\n", no_of_bits);
-	ksft_print_msg("Average LLC val: %lu\n", avg_llc_val);
+	ksft_print_msg("Average LLC val: %llu\n", avg_llc_val);
 	ksft_print_msg("Cache span (%s): %zu\n", lines ? "lines" : "bytes",
 		       cache_span);
 }
diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
index 0955f819bd83d..516eaa08e967d 100644
--- a/tools/testing/selftests/resctrl/cat_test.c
+++ b/tools/testing/selftests/resctrl/cat_test.c
@@ -41,12 +41,12 @@ static int cat_setup(struct resctrl_val_param *p)
 	return ret;
 }
 
-static int show_results_info(unsigned long sum_llc_val, int no_of_bits,
+static int show_results_info(__u64 sum_llc_val, int no_of_bits,
 			     unsigned long cache_span, unsigned long max_diff,
 			     unsigned long max_diff_percent, unsigned long num_of_runs,
 			     bool platform)
 {
-	unsigned long avg_llc_val = 0;
+	__u64 avg_llc_val = 0;
 	float diff_percent;
 	int ret;
 
@@ -68,8 +68,8 @@ static int show_results_info(unsigned long sum_llc_val, int no_of_bits,
 static int check_results(struct resctrl_val_param *param, size_t span)
 {
 	char *token_array[8], temp[512];
-	unsigned long sum_llc_perf_miss = 0;
 	int runs = 0, no_of_bits = 0;
+	__u64 sum_llc_perf_miss = 0;
 	FILE *fp;
 
 	ksft_print_msg("Checking for pass/fail\n");
@@ -93,7 +93,7 @@ static int check_results(struct resctrl_val_param *param, size_t span)
 		 * setup transition phase.
 		 */
 		if (runs > 0)
-			sum_llc_perf_miss += strtoul(token_array[3], NULL, 0);
+			sum_llc_perf_miss += strtoull(token_array[3], NULL, 0);
 		runs++;
 	}
 
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 47b871df2b0e6..f813fcdcb5e0e 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -113,8 +113,7 @@ unsigned int count_bits(unsigned long n);
 void cmt_test_cleanup(void);
 int get_core_sibling(int cpu_no);
 int measure_llc_resctrl(const char *filename, int bm_pid);
-void show_cache_info(int no_of_bits, unsigned long avg_llc_val,
-		     size_t cache_span, bool lines);
+void show_cache_info(int no_of_bits, __u64 avg_llc_val, size_t cache_span, bool lines);
 
 /*
  * cache_portion_size - Calculate the size of a cache portion

From 691a5ca429a32d204a3ace8df5da1190e0d59c41 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 15 Dec 2023 17:05:00 +0200
Subject: [PATCH 164/236] selftests/resctrl: Remove nested calls in perf event
 handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 3c6bfc9cc7f0e3bed76ff0a7ed5bf89059b7b0bd upstream.

Perf event handling has functions that are the sole caller of another
perf event handling related function:
  - reset_enable_llc_perf() calls perf_event_open_llc_miss()
  - perf_event_measure() calls get_llc_perf()

Remove the extra layer of calls to make the code easier to follow by
moving the code into the calling function.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cache.c | 64 ++++++-------------------
 1 file changed, 14 insertions(+), 50 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c
index 11d1a6ce14c21..4f846a2e5e266 100644
--- a/tools/testing/selftests/resctrl/cache.c
+++ b/tools/testing/selftests/resctrl/cache.c
@@ -29,24 +29,13 @@ static void initialize_perf_event_attr(void)
 	pea_llc_miss.disabled = 1;
 }
 
+/* Start counters to log values */
 static void ioctl_perf_event_ioc_reset_enable(void)
 {
 	ioctl(fd_lm, PERF_EVENT_IOC_RESET, 0);
 	ioctl(fd_lm, PERF_EVENT_IOC_ENABLE, 0);
 }
 
-static int perf_event_open_llc_miss(pid_t pid, int cpu_no)
-{
-	fd_lm = perf_event_open(&pea_llc_miss, pid, cpu_no, -1,
-				PERF_FLAG_FD_CLOEXEC);
-	if (fd_lm == -1) {
-		ksft_perror("Error opening leader");
-		return -1;
-	}
-
-	return 0;
-}
-
 static void initialize_llc_perf(void)
 {
 	memset(&pea_llc_miss, 0, sizeof(struct perf_event_attr));
@@ -62,42 +51,13 @@ static void initialize_llc_perf(void)
 
 static int reset_enable_llc_perf(pid_t pid, int cpu_no)
 {
-	int ret = 0;
-
-	ret = perf_event_open_llc_miss(pid, cpu_no);
-	if (ret < 0)
-		return ret;
-
-	/* Start counters to log values */
-	ioctl_perf_event_ioc_reset_enable();
-
-	return 0;
-}
-
-/*
- * get_llc_perf:	llc cache miss through perf events
- * @llc_perf_miss:	LLC miss counter that is filled on success
- *
- * Perf events like HW_CACHE_MISSES could be used to validate number of
- * cache lines allocated.
- *
- * Return: =0 on success.  <0 on failure.
- */
-static int get_llc_perf(__u64 *llc_perf_miss)
-{
-	int ret;
-
-	/* Stop counters after one span to get miss rate */
-
-	ioctl(fd_lm, PERF_EVENT_IOC_DISABLE, 0);
-
-	ret = read(fd_lm, &rf_cqm, sizeof(struct read_format));
-	if (ret == -1) {
-		ksft_perror("Could not get llc misses through perf");
+	fd_lm = perf_event_open(&pea_llc_miss, pid, cpu_no, -1, PERF_FLAG_FD_CLOEXEC);
+	if (fd_lm == -1) {
+		ksft_perror("Error opening leader");
 		return -1;
 	}
 
-	*llc_perf_miss = rf_cqm.values[0].value;
+	ioctl_perf_event_ioc_reset_enable();
 
 	return 0;
 }
@@ -178,14 +138,18 @@ static int print_results_cache(const char *filename, int bm_pid, __u64 llc_value
  */
 static int perf_event_measure(const char *filename, int bm_pid)
 {
-	__u64 llc_perf_miss = 0;
 	int ret;
 
-	ret = get_llc_perf(&llc_perf_miss);
-	if (ret < 0)
-		return ret;
+	/* Stop counters after one span to get miss rate */
+	ioctl(fd_lm, PERF_EVENT_IOC_DISABLE, 0);
+
+	ret = read(fd_lm, &rf_cqm, sizeof(struct read_format));
+	if (ret == -1) {
+		ksft_perror("Could not get perf value");
+		return -1;
+	}
 
-	return print_results_cache(filename, bm_pid, llc_perf_miss);
+	return print_results_cache(filename, bm_pid, rf_cqm.values[0].value);
 }
 
 /*

From e86d004e440ca56f14a1d9e78984eb3a8774b946 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 15 Dec 2023 17:05:01 +0200
Subject: [PATCH 165/236] selftests/resctrl: Consolidate naming of perf event
 related things
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit b6e6a582f2b357b6f74849b715de12cc38b1ee91 upstream.

Naming for perf event related functions, types, and variables is
inconsistent.

Make struct read_format and all functions related to perf events start
with "perf_". Adjust variable names towards the same direction but use
shorter names for variables where appropriate (pe prefix).

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cache.c | 42 ++++++++++++-------------
 1 file changed, 21 insertions(+), 21 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c
index 4f846a2e5e266..7f45c4957f816 100644
--- a/tools/testing/selftests/resctrl/cache.c
+++ b/tools/testing/selftests/resctrl/cache.c
@@ -3,7 +3,7 @@
 #include <stdint.h>
 #include "resctrl.h"
 
-struct read_format {
+struct perf_event_read {
 	__u64 nr;			/* The number of events */
 	struct {
 		__u64 value;		/* The value of the event */
@@ -11,11 +11,11 @@ struct read_format {
 };
 
 static struct perf_event_attr pea_llc_miss;
-static struct read_format rf_cqm;
-static int fd_lm;
+static struct perf_event_read pe_read;
+static int pe_fd;
 char llc_occup_path[1024];
 
-static void initialize_perf_event_attr(void)
+static void perf_event_attr_initialize(void)
 {
 	pea_llc_miss.type = PERF_TYPE_HARDWARE;
 	pea_llc_miss.size = sizeof(struct perf_event_attr);
@@ -30,34 +30,34 @@ static void initialize_perf_event_attr(void)
 }
 
 /* Start counters to log values */
-static void ioctl_perf_event_ioc_reset_enable(void)
+static void perf_event_reset_enable(void)
 {
-	ioctl(fd_lm, PERF_EVENT_IOC_RESET, 0);
-	ioctl(fd_lm, PERF_EVENT_IOC_ENABLE, 0);
+	ioctl(pe_fd, PERF_EVENT_IOC_RESET, 0);
+	ioctl(pe_fd, PERF_EVENT_IOC_ENABLE, 0);
 }
 
-static void initialize_llc_perf(void)
+static void perf_event_initialize(void)
 {
 	memset(&pea_llc_miss, 0, sizeof(struct perf_event_attr));
-	memset(&rf_cqm, 0, sizeof(struct read_format));
+	memset(&pe_read, 0, sizeof(struct perf_event_read));
 
 	/* Initialize perf_event_attr structures for HW_CACHE_MISSES */
-	initialize_perf_event_attr();
+	perf_event_attr_initialize();
 
 	pea_llc_miss.config = PERF_COUNT_HW_CACHE_MISSES;
 
-	rf_cqm.nr = 1;
+	pe_read.nr = 1;
 }
 
-static int reset_enable_llc_perf(pid_t pid, int cpu_no)
+static int perf_open(pid_t pid, int cpu_no)
 {
-	fd_lm = perf_event_open(&pea_llc_miss, pid, cpu_no, -1, PERF_FLAG_FD_CLOEXEC);
-	if (fd_lm == -1) {
+	pe_fd = perf_event_open(&pea_llc_miss, pid, cpu_no, -1, PERF_FLAG_FD_CLOEXEC);
+	if (pe_fd == -1) {
 		ksft_perror("Error opening leader");
 		return -1;
 	}
 
-	ioctl_perf_event_ioc_reset_enable();
+	perf_event_reset_enable();
 
 	return 0;
 }
@@ -141,15 +141,15 @@ static int perf_event_measure(const char *filename, int bm_pid)
 	int ret;
 
 	/* Stop counters after one span to get miss rate */
-	ioctl(fd_lm, PERF_EVENT_IOC_DISABLE, 0);
+	ioctl(pe_fd, PERF_EVENT_IOC_DISABLE, 0);
 
-	ret = read(fd_lm, &rf_cqm, sizeof(struct read_format));
+	ret = read(pe_fd, &pe_read, sizeof(struct perf_event_read));
 	if (ret == -1) {
 		ksft_perror("Could not get perf value");
 		return -1;
 	}
 
-	return print_results_cache(filename, bm_pid, rf_cqm.values[0].value);
+	return print_results_cache(filename, bm_pid, pe_read.values[0].value);
 }
 
 /*
@@ -204,7 +204,7 @@ int cat_val(struct resctrl_val_param *param, size_t span)
 	if (ret)
 		return ret;
 
-	initialize_llc_perf();
+	perf_event_initialize();
 
 	/* Test runs until the callback setup() tells the test to stop. */
 	while (1) {
@@ -215,7 +215,7 @@ int cat_val(struct resctrl_val_param *param, size_t span)
 		}
 		if (ret < 0)
 			break;
-		ret = reset_enable_llc_perf(bm_pid, param->cpu_no);
+		ret = perf_open(bm_pid, param->cpu_no);
 		if (ret)
 			break;
 
@@ -234,7 +234,7 @@ int cat_val(struct resctrl_val_param *param, size_t span)
 	return ret;
 
 pe_close:
-	close(fd_lm);
+	close(pe_fd);
 	return ret;
 }
 

From 03e17115c8de2ecd11c2853cde3321a5e0a6666f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 15 Dec 2023 17:05:02 +0200
Subject: [PATCH 166/236] selftests/resctrl: Improve perf init
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 038ce802e248a985150156da84bc3f118236b898 upstream.

struct perf_event_attr initialization is spread into
perf_event_initialize() and perf_event_attr_initialize() and setting
->config is hardcoded by the deepest level.

perf_event_attr init belongs to perf_event_attr_initialize() so move it
entirely there. Rename the other function
perf_event_initialized_read_format().

Call each init function directly from the test as they will take
different parameters (especially true after the perf related global
variables are moved to local variables).

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cache.c | 16 ++++++----------
 1 file changed, 6 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c
index 7f45c4957f816..58ee6f6b0edff 100644
--- a/tools/testing/selftests/resctrl/cache.c
+++ b/tools/testing/selftests/resctrl/cache.c
@@ -15,8 +15,9 @@ static struct perf_event_read pe_read;
 static int pe_fd;
 char llc_occup_path[1024];
 
-static void perf_event_attr_initialize(void)
+static void perf_event_attr_initialize(__u64 config)
 {
+	memset(&pea_llc_miss, 0, sizeof(struct perf_event_attr));
 	pea_llc_miss.type = PERF_TYPE_HARDWARE;
 	pea_llc_miss.size = sizeof(struct perf_event_attr);
 	pea_llc_miss.read_format = PERF_FORMAT_GROUP;
@@ -27,6 +28,7 @@ static void perf_event_attr_initialize(void)
 	pea_llc_miss.inherit = 1;
 	pea_llc_miss.exclude_guest = 1;
 	pea_llc_miss.disabled = 1;
+	pea_llc_miss.config = config;
 }
 
 /* Start counters to log values */
@@ -36,16 +38,9 @@ static void perf_event_reset_enable(void)
 	ioctl(pe_fd, PERF_EVENT_IOC_ENABLE, 0);
 }
 
-static void perf_event_initialize(void)
+static void perf_event_initialize_read_format(void)
 {
-	memset(&pea_llc_miss, 0, sizeof(struct perf_event_attr));
 	memset(&pe_read, 0, sizeof(struct perf_event_read));
-
-	/* Initialize perf_event_attr structures for HW_CACHE_MISSES */
-	perf_event_attr_initialize();
-
-	pea_llc_miss.config = PERF_COUNT_HW_CACHE_MISSES;
-
 	pe_read.nr = 1;
 }
 
@@ -204,7 +199,8 @@ int cat_val(struct resctrl_val_param *param, size_t span)
 	if (ret)
 		return ret;
 
-	perf_event_initialize();
+	perf_event_attr_initialize(PERF_COUNT_HW_CACHE_MISSES);
+	perf_event_initialize_read_format();
 
 	/* Test runs until the callback setup() tells the test to stop. */
 	while (1) {

From 3e999f7c6fe1dbda52968ddab92c4de9c24d9fb4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 15 Dec 2023 17:05:03 +0200
Subject: [PATCH 167/236] selftests/resctrl: Convert perf related globals to
 locals
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 3cdad0a5a6cf581519748612cb449b43379510a4 upstream.

Perf related variables pea_llc_miss, pe_read, and pe_fd are globals in
cache.c.

Convert them to locals for better scoping and make pea_llc_miss simpler
by renaming it to pea. Make close(pe_fd) handling easier to understand
by doing it inside cat_val().

Make also sizeof()s use safer way to determine the right struct.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cache.c | 72 ++++++++++++++-----------
 1 file changed, 40 insertions(+), 32 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c
index 58ee6f6b0edff..335415eaa4064 100644
--- a/tools/testing/selftests/resctrl/cache.c
+++ b/tools/testing/selftests/resctrl/cache.c
@@ -10,51 +10,50 @@ struct perf_event_read {
 	} values[2];
 };
 
-static struct perf_event_attr pea_llc_miss;
-static struct perf_event_read pe_read;
-static int pe_fd;
 char llc_occup_path[1024];
 
-static void perf_event_attr_initialize(__u64 config)
+static void perf_event_attr_initialize(struct perf_event_attr *pea, __u64 config)
 {
-	memset(&pea_llc_miss, 0, sizeof(struct perf_event_attr));
-	pea_llc_miss.type = PERF_TYPE_HARDWARE;
-	pea_llc_miss.size = sizeof(struct perf_event_attr);
-	pea_llc_miss.read_format = PERF_FORMAT_GROUP;
-	pea_llc_miss.exclude_kernel = 1;
-	pea_llc_miss.exclude_hv = 1;
-	pea_llc_miss.exclude_idle = 1;
-	pea_llc_miss.exclude_callchain_kernel = 1;
-	pea_llc_miss.inherit = 1;
-	pea_llc_miss.exclude_guest = 1;
-	pea_llc_miss.disabled = 1;
-	pea_llc_miss.config = config;
+	memset(pea, 0, sizeof(*pea));
+	pea->type = PERF_TYPE_HARDWARE;
+	pea->size = sizeof(*pea);
+	pea->read_format = PERF_FORMAT_GROUP;
+	pea->exclude_kernel = 1;
+	pea->exclude_hv = 1;
+	pea->exclude_idle = 1;
+	pea->exclude_callchain_kernel = 1;
+	pea->inherit = 1;
+	pea->exclude_guest = 1;
+	pea->disabled = 1;
+	pea->config = config;
 }
 
 /* Start counters to log values */
-static void perf_event_reset_enable(void)
+static void perf_event_reset_enable(int pe_fd)
 {
 	ioctl(pe_fd, PERF_EVENT_IOC_RESET, 0);
 	ioctl(pe_fd, PERF_EVENT_IOC_ENABLE, 0);
 }
 
-static void perf_event_initialize_read_format(void)
+static void perf_event_initialize_read_format(struct perf_event_read *pe_read)
 {
-	memset(&pe_read, 0, sizeof(struct perf_event_read));
-	pe_read.nr = 1;
+	memset(pe_read, 0, sizeof(*pe_read));
+	pe_read->nr = 1;
 }
 
-static int perf_open(pid_t pid, int cpu_no)
+static int perf_open(struct perf_event_attr *pea, pid_t pid, int cpu_no)
 {
-	pe_fd = perf_event_open(&pea_llc_miss, pid, cpu_no, -1, PERF_FLAG_FD_CLOEXEC);
+	int pe_fd;
+
+	pe_fd = perf_event_open(pea, pid, cpu_no, -1, PERF_FLAG_FD_CLOEXEC);
 	if (pe_fd == -1) {
 		ksft_perror("Error opening leader");
 		return -1;
 	}
 
-	perf_event_reset_enable();
+	perf_event_reset_enable(pe_fd);
 
-	return 0;
+	return pe_fd;
 }
 
 /*
@@ -131,20 +130,21 @@ static int print_results_cache(const char *filename, int bm_pid, __u64 llc_value
  *
  * Return: =0 on success. <0 on failure.
  */
-static int perf_event_measure(const char *filename, int bm_pid)
+static int perf_event_measure(int pe_fd, struct perf_event_read *pe_read,
+			      const char *filename, int bm_pid)
 {
 	int ret;
 
 	/* Stop counters after one span to get miss rate */
 	ioctl(pe_fd, PERF_EVENT_IOC_DISABLE, 0);
 
-	ret = read(pe_fd, &pe_read, sizeof(struct perf_event_read));
+	ret = read(pe_fd, pe_read, sizeof(*pe_read));
 	if (ret == -1) {
 		ksft_perror("Could not get perf value");
 		return -1;
 	}
 
-	return print_results_cache(filename, bm_pid, pe_read.values[0].value);
+	return print_results_cache(filename, bm_pid, pe_read->values[0].value);
 }
 
 /*
@@ -181,7 +181,10 @@ int cat_val(struct resctrl_val_param *param, size_t span)
 {
 	int memflush = 1, operation = 0, ret = 0;
 	char *resctrl_val = param->resctrl_val;
+	struct perf_event_read pe_read;
+	struct perf_event_attr pea;
 	pid_t bm_pid;
+	int pe_fd;
 
 	if (strcmp(param->filename, "") == 0)
 		sprintf(param->filename, "stdio");
@@ -199,8 +202,8 @@ int cat_val(struct resctrl_val_param *param, size_t span)
 	if (ret)
 		return ret;
 
-	perf_event_attr_initialize(PERF_COUNT_HW_CACHE_MISSES);
-	perf_event_initialize_read_format();
+	perf_event_attr_initialize(&pea, PERF_COUNT_HW_CACHE_MISSES);
+	perf_event_initialize_read_format(&pe_read);
 
 	/* Test runs until the callback setup() tells the test to stop. */
 	while (1) {
@@ -211,9 +214,12 @@ int cat_val(struct resctrl_val_param *param, size_t span)
 		}
 		if (ret < 0)
 			break;
-		ret = perf_open(bm_pid, param->cpu_no);
-		if (ret)
+
+		pe_fd = perf_open(&pea, bm_pid, param->cpu_no);
+		if (pe_fd < 0) {
+			ret = -1;
 			break;
+		}
 
 		if (run_fill_buf(span, memflush, operation, true)) {
 			fprintf(stderr, "Error-running fill buffer\n");
@@ -222,9 +228,11 @@ int cat_val(struct resctrl_val_param *param, size_t span)
 		}
 
 		sleep(1);
-		ret = perf_event_measure(param->filename, bm_pid);
+		ret = perf_event_measure(pe_fd, &pe_read, param->filename, bm_pid);
 		if (ret)
 			goto pe_close;
+
+		close(pe_fd);
 	}
 
 	return ret;

From adbf6910e79ce4f0531709e7754e54431750f3ab Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 15 Dec 2023 17:05:04 +0200
Subject: [PATCH 168/236] selftests/resctrl: Move cat_val() to cat_test.c and
 rename to cat_test()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 433f437b3ae2ed4e318ecd5233c82f6936e78e82 upstream.

The main CAT test function is called cat_val() and resides in cache.c
which is illogical.

Rename the function to cat_test() and move it into cat_test.c.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cache.c    | 90 ++--------------------
 tools/testing/selftests/resctrl/cat_test.c | 73 +++++++++++++++++-
 tools/testing/selftests/resctrl/resctrl.h  | 14 +++-
 3 files changed, 90 insertions(+), 87 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c
index 335415eaa4064..319d0cdd7225f 100644
--- a/tools/testing/selftests/resctrl/cache.c
+++ b/tools/testing/selftests/resctrl/cache.c
@@ -3,16 +3,9 @@
 #include <stdint.h>
 #include "resctrl.h"
 
-struct perf_event_read {
-	__u64 nr;			/* The number of events */
-	struct {
-		__u64 value;		/* The value of the event */
-	} values[2];
-};
-
 char llc_occup_path[1024];
 
-static void perf_event_attr_initialize(struct perf_event_attr *pea, __u64 config)
+void perf_event_attr_initialize(struct perf_event_attr *pea, __u64 config)
 {
 	memset(pea, 0, sizeof(*pea));
 	pea->type = PERF_TYPE_HARDWARE;
@@ -35,13 +28,13 @@ static void perf_event_reset_enable(int pe_fd)
 	ioctl(pe_fd, PERF_EVENT_IOC_ENABLE, 0);
 }
 
-static void perf_event_initialize_read_format(struct perf_event_read *pe_read)
+void perf_event_initialize_read_format(struct perf_event_read *pe_read)
 {
 	memset(pe_read, 0, sizeof(*pe_read));
 	pe_read->nr = 1;
 }
 
-static int perf_open(struct perf_event_attr *pea, pid_t pid, int cpu_no)
+int perf_open(struct perf_event_attr *pea, pid_t pid, int cpu_no)
 {
 	int pe_fd;
 
@@ -130,8 +123,8 @@ static int print_results_cache(const char *filename, int bm_pid, __u64 llc_value
  *
  * Return: =0 on success. <0 on failure.
  */
-static int perf_event_measure(int pe_fd, struct perf_event_read *pe_read,
-			      const char *filename, int bm_pid)
+int perf_event_measure(int pe_fd, struct perf_event_read *pe_read,
+		       const char *filename, int bm_pid)
 {
 	int ret;
 
@@ -169,79 +162,6 @@ int measure_llc_resctrl(const char *filename, int bm_pid)
 	return print_results_cache(filename, bm_pid, llc_occu_resc);
 }
 
-/*
- * cache_val:		execute benchmark and measure LLC occupancy resctrl
- * and perf cache miss for the benchmark
- * @param:		parameters passed to cache_val()
- * @span:		buffer size for the benchmark
- *
- * Return:		0 when the test was run, < 0 on error.
- */
-int cat_val(struct resctrl_val_param *param, size_t span)
-{
-	int memflush = 1, operation = 0, ret = 0;
-	char *resctrl_val = param->resctrl_val;
-	struct perf_event_read pe_read;
-	struct perf_event_attr pea;
-	pid_t bm_pid;
-	int pe_fd;
-
-	if (strcmp(param->filename, "") == 0)
-		sprintf(param->filename, "stdio");
-
-	bm_pid = getpid();
-
-	/* Taskset benchmark to specified cpu */
-	ret = taskset_benchmark(bm_pid, param->cpu_no);
-	if (ret)
-		return ret;
-
-	/* Write benchmark to specified con_mon grp, mon_grp in resctrl FS*/
-	ret = write_bm_pid_to_resctrl(bm_pid, param->ctrlgrp, param->mongrp,
-				      resctrl_val);
-	if (ret)
-		return ret;
-
-	perf_event_attr_initialize(&pea, PERF_COUNT_HW_CACHE_MISSES);
-	perf_event_initialize_read_format(&pe_read);
-
-	/* Test runs until the callback setup() tells the test to stop. */
-	while (1) {
-		ret = param->setup(param);
-		if (ret == END_OF_TESTS) {
-			ret = 0;
-			break;
-		}
-		if (ret < 0)
-			break;
-
-		pe_fd = perf_open(&pea, bm_pid, param->cpu_no);
-		if (pe_fd < 0) {
-			ret = -1;
-			break;
-		}
-
-		if (run_fill_buf(span, memflush, operation, true)) {
-			fprintf(stderr, "Error-running fill buffer\n");
-			ret = -1;
-			goto pe_close;
-		}
-
-		sleep(1);
-		ret = perf_event_measure(pe_fd, &pe_read, param->filename, bm_pid);
-		if (ret)
-			goto pe_close;
-
-		close(pe_fd);
-	}
-
-	return ret;
-
-pe_close:
-	close(pe_fd);
-	return ret;
-}
-
 /*
  * show_cache_info - Show generic cache test information
  * @no_of_bits:		Number of bits
diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
index 516eaa08e967d..bfb607b134919 100644
--- a/tools/testing/selftests/resctrl/cat_test.c
+++ b/tools/testing/selftests/resctrl/cat_test.c
@@ -111,6 +111,77 @@ void cat_test_cleanup(void)
 	remove(RESULT_FILE_NAME2);
 }
 
+/*
+ * cat_test - Execute CAT benchmark and measure cache misses
+ * @param:		Parameters passed to cat_test()
+ * @span:		Buffer size for the benchmark
+ *
+ * Return:		0 when the test was run, < 0 on error.
+ */
+static int cat_test(struct resctrl_val_param *param, size_t span)
+{
+	int memflush = 1, operation = 0, ret = 0;
+	char *resctrl_val = param->resctrl_val;
+	struct perf_event_read pe_read;
+	struct perf_event_attr pea;
+	pid_t bm_pid;
+	int pe_fd;
+
+	if (strcmp(param->filename, "") == 0)
+		sprintf(param->filename, "stdio");
+
+	bm_pid = getpid();
+
+	/* Taskset benchmark to specified cpu */
+	ret = taskset_benchmark(bm_pid, param->cpu_no);
+	if (ret)
+		return ret;
+
+	/* Write benchmark to specified con_mon grp, mon_grp in resctrl FS*/
+	ret = write_bm_pid_to_resctrl(bm_pid, param->ctrlgrp, param->mongrp,
+				      resctrl_val);
+	if (ret)
+		return ret;
+
+	perf_event_attr_initialize(&pea, PERF_COUNT_HW_CACHE_MISSES);
+	perf_event_initialize_read_format(&pe_read);
+
+	/* Test runs until the callback setup() tells the test to stop. */
+	while (1) {
+		ret = param->setup(param);
+		if (ret == END_OF_TESTS) {
+			ret = 0;
+			break;
+		}
+		if (ret < 0)
+			break;
+		pe_fd = perf_open(&pea, bm_pid, param->cpu_no);
+		if (pe_fd < 0) {
+			ret = -1;
+			break;
+		}
+
+		if (run_fill_buf(span, memflush, operation, true)) {
+			fprintf(stderr, "Error-running fill buffer\n");
+			ret = -1;
+			goto pe_close;
+		}
+
+		sleep(1);
+		ret = perf_event_measure(pe_fd, &pe_read, param->filename, bm_pid);
+		if (ret)
+			goto pe_close;
+
+		close(pe_fd);
+	}
+
+	return ret;
+
+pe_close:
+	close(pe_fd);
+	return ret;
+}
+
 int cat_perf_miss_val(int cpu_no, int n, char *cache_type)
 {
 	unsigned long full_cache_mask, long_mask;
@@ -194,7 +265,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type)
 
 	remove(param.filename);
 
-	ret = cat_val(&param, span);
+	ret = cat_test(&param, span);
 	if (ret == 0)
 		ret = check_results(&param, span);
 
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index f813fcdcb5e0e..4aabf7ac0ab9d 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -66,6 +66,13 @@ struct resctrl_val_param {
 	int		(*setup)(struct resctrl_val_param *param);
 };
 
+struct perf_event_read {
+	__u64 nr;			/* The number of events */
+	struct {
+		__u64 value;		/* The value of the event */
+	} values[2];
+};
+
 #define MBM_STR			"mbm"
 #define MBA_STR			"mba"
 #define CMT_STR			"cmt"
@@ -105,13 +112,18 @@ int get_cache_size(int cpu_no, const char *cache_type, unsigned long *cache_size
 void ctrlc_handler(int signum, siginfo_t *info, void *ptr);
 int signal_handler_register(void);
 void signal_handler_unregister(void);
-int cat_val(struct resctrl_val_param *param, size_t span);
 void cat_test_cleanup(void);
 int cat_perf_miss_val(int cpu_no, int no_of_bits, char *cache_type);
 int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd);
 unsigned int count_bits(unsigned long n);
 void cmt_test_cleanup(void);
 int get_core_sibling(int cpu_no);
+
+void perf_event_attr_initialize(struct perf_event_attr *pea, __u64 config);
+void perf_event_initialize_read_format(struct perf_event_read *pe_read);
+int perf_open(struct perf_event_attr *pea, pid_t pid, int cpu_no);
+int perf_event_measure(int pe_fd, struct perf_event_read *pe_read,
+		       const char *filename, int bm_pid);
 int measure_llc_resctrl(const char *filename, int bm_pid);
 void show_cache_info(int no_of_bits, __u64 avg_llc_val, size_t cache_span, bool lines);
 

From f853eb608ca85d19d2d4017cdc796d5dad590a23 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 15 Dec 2023 17:05:05 +0200
Subject: [PATCH 169/236] selftests/resctrl: Open perf fd before start & add
 error handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 2892731ec2893252cdbc256a2bd5436b7fd94cf7 upstream.

Perf fd (pe_fd) is opened, reset, and enabled during every test the CAT
selftest runs. Also, ioctl(pe_fd, ...) calls are not error checked even
if ioctl() could return an error.

Open perf fd only once before the tests and only reset and enable the
counter within the test loop. Add error checking to pe_fd ioctl()
calls.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cache.c    | 19 +++++++++++++++----
 tools/testing/selftests/resctrl/cat_test.c | 14 +++++++-------
 tools/testing/selftests/resctrl/resctrl.h  |  1 +
 3 files changed, 23 insertions(+), 11 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c
index 319d0cdd7225f..1b339d6bbff1c 100644
--- a/tools/testing/selftests/resctrl/cache.c
+++ b/tools/testing/selftests/resctrl/cache.c
@@ -22,10 +22,19 @@ void perf_event_attr_initialize(struct perf_event_attr *pea, __u64 config)
 }
 
 /* Start counters to log values */
-static void perf_event_reset_enable(int pe_fd)
+int perf_event_reset_enable(int pe_fd)
 {
-	ioctl(pe_fd, PERF_EVENT_IOC_RESET, 0);
-	ioctl(pe_fd, PERF_EVENT_IOC_ENABLE, 0);
+	int ret;
+
+	ret = ioctl(pe_fd, PERF_EVENT_IOC_RESET, 0);
+	if (ret < 0)
+		return ret;
+
+	ret = ioctl(pe_fd, PERF_EVENT_IOC_ENABLE, 0);
+	if (ret < 0)
+		return ret;
+
+	return 0;
 }
 
 void perf_event_initialize_read_format(struct perf_event_read *pe_read)
@@ -129,7 +138,9 @@ int perf_event_measure(int pe_fd, struct perf_event_read *pe_read,
 	int ret;
 
 	/* Stop counters after one span to get miss rate */
-	ioctl(pe_fd, PERF_EVENT_IOC_DISABLE, 0);
+	ret = ioctl(pe_fd, PERF_EVENT_IOC_DISABLE, 0);
+	if (ret < 0)
+		return ret;
 
 	ret = read(pe_fd, pe_read, sizeof(*pe_read));
 	if (ret == -1) {
diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
index bfb607b134919..36e62baebf4f8 100644
--- a/tools/testing/selftests/resctrl/cat_test.c
+++ b/tools/testing/selftests/resctrl/cat_test.c
@@ -145,6 +145,9 @@ static int cat_test(struct resctrl_val_param *param, size_t span)
 
 	perf_event_attr_initialize(&pea, PERF_COUNT_HW_CACHE_MISSES);
 	perf_event_initialize_read_format(&pe_read);
+	pe_fd = perf_open(&pea, bm_pid, param->cpu_no);
+	if (pe_fd < 0)
+		return pe_fd;
 
 	/* Test runs until the callback setup() tells the test to stop. */
 	while (1) {
@@ -155,11 +158,10 @@ static int cat_test(struct resctrl_val_param *param, size_t span)
 		}
 		if (ret < 0)
 			break;
-		pe_fd = perf_open(&pea, bm_pid, param->cpu_no);
-		if (pe_fd < 0) {
-			ret = -1;
-			break;
-		}
+
+		ret = perf_event_reset_enable(pe_fd);
+		if (ret)
+			goto pe_close;
 
 		if (run_fill_buf(span, memflush, operation, true)) {
 			fprintf(stderr, "Error-running fill buffer\n");
@@ -171,8 +173,6 @@ static int cat_test(struct resctrl_val_param *param, size_t span)
 		ret = perf_event_measure(pe_fd, &pe_read, param->filename, bm_pid);
 		if (ret)
 			goto pe_close;
-
-		close(pe_fd);
 	}
 
 	return ret;
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 4aabf7ac0ab9d..f22b7897251e5 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -122,6 +122,7 @@ int get_core_sibling(int cpu_no);
 void perf_event_attr_initialize(struct perf_event_attr *pea, __u64 config);
 void perf_event_initialize_read_format(struct perf_event_read *pe_read);
 int perf_open(struct perf_event_attr *pea, pid_t pid, int cpu_no);
+int perf_event_reset_enable(int pe_fd);
 int perf_event_measure(int pe_fd, struct perf_event_read *pe_read,
 		       const char *filename, int bm_pid);
 int measure_llc_resctrl(const char *filename, int bm_pid);

From 297e3b45cdcb42720c2e728f06eb887f10a1166e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 15 Dec 2023 17:05:06 +0200
Subject: [PATCH 170/236] selftests/resctrl: Replace file write with volatile
 variable
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 90a009db09e2b91990df28e47844d44ae0ef9aa8 upstream.

The fill_buf code prevents compiler optimizating the entire read loop
away by writing the final value of the variable into a file. While it
achieves the goal, writing into a file requires significant amount of
work within the innermost test loop and also error handling.

A simpler approach is to take advantage of volatile. Writing through
a pointer to a volatile variable is enough to prevent compiler from
optimizing the write away, and therefore compiler cannot remove the
read loop either.

Add a volatile 'value_sink' into resctrl_tests.c and make fill_buf to
write into it. As a result, the error handling in fill_buf.c can be
simplified.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/fill_buf.c    | 26 ++++---------------
 tools/testing/selftests/resctrl/resctrl.h     |  7 +++++
 .../testing/selftests/resctrl/resctrl_tests.c |  4 +++
 3 files changed, 16 insertions(+), 21 deletions(-)

diff --git a/tools/testing/selftests/resctrl/fill_buf.c b/tools/testing/selftests/resctrl/fill_buf.c
index a85ae8148db84..3add514f9995b 100644
--- a/tools/testing/selftests/resctrl/fill_buf.c
+++ b/tools/testing/selftests/resctrl/fill_buf.c
@@ -78,10 +78,9 @@ static void fill_one_span_write(unsigned char *buf, size_t buf_size)
 	}
 }
 
-static int fill_cache_read(unsigned char *buf, size_t buf_size, bool once)
+static void fill_cache_read(unsigned char *buf, size_t buf_size, bool once)
 {
 	int ret = 0;
-	FILE *fp;
 
 	while (1) {
 		ret = fill_one_span_read(buf, buf_size);
@@ -90,26 +89,16 @@ static int fill_cache_read(unsigned char *buf, size_t buf_size, bool once)
 	}
 
 	/* Consume read result so that reading memory is not optimized out. */
-	fp = fopen("/dev/null", "w");
-	if (!fp) {
-		ksft_perror("Unable to write to /dev/null");
-		return -1;
-	}
-	fprintf(fp, "Sum: %d ", ret);
-	fclose(fp);
-
-	return 0;
+	*value_sink = ret;
 }
 
-static int fill_cache_write(unsigned char *buf, size_t buf_size, bool once)
+static void fill_cache_write(unsigned char *buf, size_t buf_size, bool once)
 {
 	while (1) {
 		fill_one_span_write(buf, buf_size);
 		if (once)
 			break;
 	}
-
-	return 0;
 }
 
 static unsigned char *alloc_buffer(size_t buf_size, int memflush)
@@ -143,21 +132,16 @@ static unsigned char *alloc_buffer(size_t buf_size, int memflush)
 int run_fill_buf(size_t buf_size, int memflush, int op, bool once)
 {
 	unsigned char *buf;
-	int ret;
 
 	buf = alloc_buffer(buf_size, memflush);
 	if (!buf)
 		return -1;
 
 	if (op == 0)
-		ret = fill_cache_read(buf, buf_size, once);
+		fill_cache_read(buf, buf_size, once);
 	else
-		ret = fill_cache_write(buf, buf_size, once);
+		fill_cache_write(buf, buf_size, once);
 	free(buf);
-	if (ret) {
-		printf("\n Error in fill cache\n");
-		return -1;
-	}
 
 	return 0;
 }
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index f22b7897251e5..5b9bea5051201 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -78,6 +78,13 @@ struct perf_event_read {
 #define CMT_STR			"cmt"
 #define CAT_STR			"cat"
 
+/*
+ * Memory location that consumes values compiler must not optimize away.
+ * Volatile ensures writes to this location cannot be optimized away by
+ * compiler.
+ */
+extern volatile int *value_sink;
+
 extern pid_t bm_pid, ppid;
 
 extern char llc_occup_path[1024];
diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c
index 2bbe3045a018e..f0d573aa363b8 100644
--- a/tools/testing/selftests/resctrl/resctrl_tests.c
+++ b/tools/testing/selftests/resctrl/resctrl_tests.c
@@ -10,6 +10,10 @@
  */
 #include "resctrl.h"
 
+/* Volatile memory sink to prevent compiler optimizations */
+static volatile int sink_target;
+volatile int *value_sink = &sink_target;
+
 static int detect_vendor(void)
 {
 	FILE *inf = fopen("/proc/cpuinfo", "r");

From f7ee799fccd42eb1eae657fb454df4c9aaa2d88e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 15 Dec 2023 17:05:07 +0200
Subject: [PATCH 171/236] selftests/resctrl: Read in less obvious order to
 defeat prefetch optimizations
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit bcdb2e9d9f319935938a5addee040e37b60192ff upstream.

When reading memory in order, HW prefetching optimizations will
interfere with measuring how caches and memory are being accessed. This
adds noise into the results.

Change the fill_buf reading loop to not use an obvious in-order access
using multiply by a prime and modulo.

Using a prime multiplier with modulo ensures the entire buffer is
eventually read. 23 is small enough that the reads are spread out but
wrapping does not occur very frequently (wrapping too often can trigger
L2 hits more frequently which causes noise to the test because getting
the data from LLC is not required).

It was discovered that not all primes work equally well and some can
cause wildly unstable results (e.g., in an earlier version of this
patch, the reads were done in reversed order and 59 was used as the
prime resulting in unacceptably high and unstable results in MBA and
MBM test on some architectures).

Link: https://lore.kernel.org/linux-kselftest/TYAPR01MB6330025B5E6537F94DA49ACB8B499@TYAPR01MB6330.jpnprd01.prod.outlook.com/
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/fill_buf.c | 38 +++++++++++++++++-----
 1 file changed, 30 insertions(+), 8 deletions(-)

diff --git a/tools/testing/selftests/resctrl/fill_buf.c b/tools/testing/selftests/resctrl/fill_buf.c
index 3add514f9995b..835adddb40be5 100644
--- a/tools/testing/selftests/resctrl/fill_buf.c
+++ b/tools/testing/selftests/resctrl/fill_buf.c
@@ -51,16 +51,38 @@ static void mem_flush(unsigned char *buf, size_t buf_size)
 	sb();
 }
 
+/*
+ * Buffer index step advance to workaround HW prefetching interfering with
+ * the measurements.
+ *
+ * Must be a prime to step through all indexes of the buffer.
+ *
+ * Some primes work better than others on some architectures (from MBA/MBM
+ * result stability point of view).
+ */
+#define FILL_IDX_MULT	23
+
 static int fill_one_span_read(unsigned char *buf, size_t buf_size)
 {
-	unsigned char *end_ptr = buf + buf_size;
-	unsigned char sum, *p;
-
-	sum = 0;
-	p = buf;
-	while (p < end_ptr) {
-		sum += *p;
-		p += (CL_SIZE / 2);
+	unsigned int size = buf_size / (CL_SIZE / 2);
+	unsigned int i, idx = 0;
+	unsigned char sum = 0;
+
+	/*
+	 * Read the buffer in an order that is unexpected by HW prefetching
+	 * optimizations to prevent them interfering with the caching pattern.
+	 *
+	 * The read order is (in terms of halves of cachelines):
+	 *	i * FILL_IDX_MULT % size
+	 * The formula is open-coded below to avoiding modulo inside the loop
+	 * as it improves MBA/MBM result stability on some architectures.
+	 */
+	for (i = 0; i < size; i++) {
+		sum += buf[idx * (CL_SIZE / 2)];
+
+		idx += FILL_IDX_MULT;
+		while (idx >= size)
+			idx -= size;
 	}
 
 	return sum;

From fd81cf0b8a82b6d78e5ecc18e0fb682b963d5745 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 15 Dec 2023 17:05:08 +0200
Subject: [PATCH 172/236] selftests/resctrl: Rewrite Cache Allocation
 Technology (CAT) test
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 205de6ddd7fff9340bd5e4b68105f28120671c6b upstream.

CAT test spawns two processes into two different control groups with
exclusive schemata. Both the processes alloc a buffer from memory
matching their allocated LLC block size and flush the entire buffer out
of caches. Since the processes are reading through the buffer only once
during the measurement and initially all the buffer was flushed, the
test isn't testing CAT.

Rewrite the CAT test to allocate a buffer sized to half of LLC. Then
perform a sequence of tests with different LLC alloc sizes starting
from half of the CBM bits down to 1-bit CBM. Flush the buffer before
each test and read the buffer twice. Observe the LLC misses on the
second read through the buffer. As the allocated LLC block gets smaller
and smaller, the LLC misses will become larger and larger giving a
strong signal on CAT working properly.

The new CAT test is using only a single process because it relies on
measured effect against another run of itself rather than another
process adding noise. The rest of the system is set to use the CBM bits
not used by the CAT test to keep the test isolated.

Replace count_bits() with count_contiguous_bits() to get the first bit
position in order to be able to calculate masks based on it.

This change has been tested with a number of systems from different
generations.

Suggested-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cat_test.c  | 283 +++++++++-----------
 tools/testing/selftests/resctrl/fill_buf.c  |   6 +-
 tools/testing/selftests/resctrl/resctrl.h   |   5 +-
 tools/testing/selftests/resctrl/resctrlfs.c |  44 +--
 4 files changed, 139 insertions(+), 199 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
index 36e62baebf4f8..b799160697882 100644
--- a/tools/testing/selftests/resctrl/cat_test.c
+++ b/tools/testing/selftests/resctrl/cat_test.c
@@ -11,65 +11,70 @@
 #include "resctrl.h"
 #include <unistd.h>
 
-#define RESULT_FILE_NAME1	"result_cat1"
-#define RESULT_FILE_NAME2	"result_cat2"
+#define RESULT_FILE_NAME	"result_cat"
 #define NUM_OF_RUNS		5
-#define MAX_DIFF_PERCENT	4
-#define MAX_DIFF		1000000
 
 /*
- * Change schemata. Write schemata to specified
- * con_mon grp, mon_grp in resctrl FS.
- * Run 5 times in order to get average values.
+ * Minimum difference in LLC misses between a test with n+1 bits CBM to the
+ * test with n bits is MIN_DIFF_PERCENT_PER_BIT * (n - 1). With e.g. 5 vs 4
+ * bits in the CBM mask, the minimum difference must be at least
+ * MIN_DIFF_PERCENT_PER_BIT * (4 - 1) = 3 percent.
+ *
+ * The relationship between number of used CBM bits and difference in LLC
+ * misses is not expected to be linear. With a small number of bits, the
+ * margin is smaller than with larger number of bits. For selftest purposes,
+ * however, linear approach is enough because ultimately only pass/fail
+ * decision has to be made and distinction between strong and stronger
+ * signal is irrelevant.
  */
-static int cat_setup(struct resctrl_val_param *p)
-{
-	char schemata[64];
-	int ret = 0;
-
-	/* Run NUM_OF_RUNS times */
-	if (p->num_of_runs >= NUM_OF_RUNS)
-		return END_OF_TESTS;
-
-	if (p->num_of_runs == 0) {
-		sprintf(schemata, "%lx", p->mask);
-		ret = write_schemata(p->ctrlgrp, schemata, p->cpu_no,
-				     p->resctrl_val);
-	}
-	p->num_of_runs++;
-
-	return ret;
-}
+#define MIN_DIFF_PERCENT_PER_BIT	1UL
 
 static int show_results_info(__u64 sum_llc_val, int no_of_bits,
-			     unsigned long cache_span, unsigned long max_diff,
-			     unsigned long max_diff_percent, unsigned long num_of_runs,
-			     bool platform)
+			     unsigned long cache_span,
+			     unsigned long min_diff_percent,
+			     unsigned long num_of_runs, bool platform,
+			     __s64 *prev_avg_llc_val)
 {
 	__u64 avg_llc_val = 0;
-	float diff_percent;
-	int ret;
+	float avg_diff;
+	int ret = 0;
 
 	avg_llc_val = sum_llc_val / num_of_runs;
-	diff_percent = ((float)cache_span - avg_llc_val) / cache_span * 100;
+	if (*prev_avg_llc_val) {
+		float delta = (__s64)(avg_llc_val - *prev_avg_llc_val);
 
-	ret = platform && abs((int)diff_percent) > max_diff_percent;
+		avg_diff = delta / *prev_avg_llc_val;
+		ret = platform && (avg_diff * 100) < (float)min_diff_percent;
 
-	ksft_print_msg("%s Check cache miss rate within %lu%%\n",
-		       ret ? "Fail:" : "Pass:", max_diff_percent);
+		ksft_print_msg("%s Check cache miss rate changed more than %.1f%%\n",
+			       ret ? "Fail:" : "Pass:", (float)min_diff_percent);
 
-	ksft_print_msg("Percent diff=%d\n", abs((int)diff_percent));
+		ksft_print_msg("Percent diff=%.1f\n", avg_diff * 100);
+	}
+	*prev_avg_llc_val = avg_llc_val;
 
 	show_cache_info(no_of_bits, avg_llc_val, cache_span, true);
 
 	return ret;
 }
 
-static int check_results(struct resctrl_val_param *param, size_t span)
+/* Remove the highest bit from CBM */
+static unsigned long next_mask(unsigned long current_mask)
+{
+	return current_mask & (current_mask >> 1);
+}
+
+static int check_results(struct resctrl_val_param *param, const char *cache_type,
+			 unsigned long cache_total_size, unsigned long full_cache_mask,
+			 unsigned long current_mask)
 {
 	char *token_array[8], temp[512];
-	int runs = 0, no_of_bits = 0;
 	__u64 sum_llc_perf_miss = 0;
+	__s64 prev_avg_llc_val = 0;
+	unsigned long alloc_size;
+	int runs = 0;
+	int fail = 0;
+	int ret;
 	FILE *fp;
 
 	ksft_print_msg("Checking for pass/fail\n");
@@ -83,49 +88,78 @@ static int check_results(struct resctrl_val_param *param, size_t span)
 	while (fgets(temp, sizeof(temp), fp)) {
 		char *token = strtok(temp, ":\t");
 		int fields = 0;
+		int bits;
 
 		while (token) {
 			token_array[fields++] = token;
 			token = strtok(NULL, ":\t");
 		}
-		/*
-		 * Discard the first value which is inaccurate due to monitoring
-		 * setup transition phase.
-		 */
-		if (runs > 0)
-			sum_llc_perf_miss += strtoull(token_array[3], NULL, 0);
+
+		sum_llc_perf_miss += strtoull(token_array[3], NULL, 0);
 		runs++;
+
+		if (runs < NUM_OF_RUNS)
+			continue;
+
+		if (!current_mask) {
+			ksft_print_msg("Unexpected empty cache mask\n");
+			break;
+		}
+
+		alloc_size = cache_portion_size(cache_total_size, current_mask, full_cache_mask);
+
+		bits = count_bits(current_mask);
+
+		ret = show_results_info(sum_llc_perf_miss, bits,
+					alloc_size / 64,
+					MIN_DIFF_PERCENT_PER_BIT * (bits - 1),
+					runs, get_vendor() == ARCH_INTEL,
+					&prev_avg_llc_val);
+		if (ret)
+			fail = 1;
+
+		runs = 0;
+		sum_llc_perf_miss = 0;
+		current_mask = next_mask(current_mask);
 	}
 
 	fclose(fp);
-	no_of_bits = count_bits(param->mask);
 
-	return show_results_info(sum_llc_perf_miss, no_of_bits, span / 64,
-				 MAX_DIFF, MAX_DIFF_PERCENT, runs - 1,
-				 get_vendor() == ARCH_INTEL);
+	return fail;
 }
 
 void cat_test_cleanup(void)
 {
-	remove(RESULT_FILE_NAME1);
-	remove(RESULT_FILE_NAME2);
+	remove(RESULT_FILE_NAME);
 }
 
 /*
  * cat_test - Execute CAT benchmark and measure cache misses
  * @param:		Parameters passed to cat_test()
  * @span:		Buffer size for the benchmark
+ * @current_mask	Start mask for the first iteration
+ *
+ * Run CAT selftest by varying the allocated cache portion and comparing the
+ * impact on cache misses (the result analysis is done in check_results()
+ * and show_results_info(), not in this function).
+ *
+ * One bit is removed from the CAT allocation bit mask (in current_mask) for
+ * each subsequent test which keeps reducing the size of the allocated cache
+ * portion. A single test flushes the buffer, reads it to warm up the cache,
+ * and reads the buffer again. The cache misses are measured during the last
+ * read pass.
  *
  * Return:		0 when the test was run, < 0 on error.
  */
-static int cat_test(struct resctrl_val_param *param, size_t span)
+static int cat_test(struct resctrl_val_param *param, size_t span, unsigned long current_mask)
 {
-	int memflush = 1, operation = 0, ret = 0;
 	char *resctrl_val = param->resctrl_val;
 	struct perf_event_read pe_read;
 	struct perf_event_attr pea;
+	unsigned char *buf;
+	char schemata[64];
+	int ret, i, pe_fd;
 	pid_t bm_pid;
-	int pe_fd;
 
 	if (strcmp(param->filename, "") == 0)
 		sprintf(param->filename, "stdio");
@@ -149,48 +183,55 @@ static int cat_test(struct resctrl_val_param *param, size_t span)
 	if (pe_fd < 0)
 		return pe_fd;
 
-	/* Test runs until the callback setup() tells the test to stop. */
-	while (1) {
-		ret = param->setup(param);
-		if (ret == END_OF_TESTS) {
-			ret = 0;
-			break;
-		}
-		if (ret < 0)
-			break;
+	buf = alloc_buffer(span, 1);
+	if (!buf) {
+		ret = -1;
+		goto pe_close;
+	}
 
-		ret = perf_event_reset_enable(pe_fd);
+	while (current_mask) {
+		snprintf(schemata, sizeof(schemata), "%lx", param->mask & ~current_mask);
+		ret = write_schemata("", schemata, param->cpu_no, param->resctrl_val);
 		if (ret)
-			goto pe_close;
+			goto free_buf;
+		snprintf(schemata, sizeof(schemata), "%lx", current_mask);
+		ret = write_schemata(param->ctrlgrp, schemata, param->cpu_no, param->resctrl_val);
+		if (ret)
+			goto free_buf;
 
-		if (run_fill_buf(span, memflush, operation, true)) {
-			fprintf(stderr, "Error-running fill buffer\n");
-			ret = -1;
-			goto pe_close;
-		}
+		for (i = 0; i < NUM_OF_RUNS; i++) {
+			mem_flush(buf, span);
+			fill_cache_read(buf, span, true);
 
-		sleep(1);
-		ret = perf_event_measure(pe_fd, &pe_read, param->filename, bm_pid);
-		if (ret)
-			goto pe_close;
-	}
+			ret = perf_event_reset_enable(pe_fd);
+			if (ret)
+				goto free_buf;
 
-	return ret;
+			fill_cache_read(buf, span, true);
 
+			ret = perf_event_measure(pe_fd, &pe_read, param->filename, bm_pid);
+			if (ret)
+				goto free_buf;
+		}
+		current_mask = next_mask(current_mask);
+	}
+
+free_buf:
+	free(buf);
 pe_close:
 	close(pe_fd);
+
 	return ret;
 }
 
 int cat_perf_miss_val(int cpu_no, int n, char *cache_type)
 {
-	unsigned long full_cache_mask, long_mask;
-	unsigned long l_mask, l_mask_1;
-	int ret, pipefd[2], sibling_cpu_no;
+	unsigned long long_mask, start_mask, full_cache_mask;
 	unsigned long cache_total_size = 0;
+	unsigned int start;
 	int count_of_bits;
-	char pipe_message;
 	size_t span;
+	int ret;
 
 	ret = get_full_cbm(cache_type, &full_cache_mask);
 	if (ret)
@@ -206,7 +247,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type)
 		return ret;
 	ksft_print_msg("Cache size :%lu\n", cache_total_size);
 
-	count_of_bits = count_bits(long_mask);
+	count_of_bits = count_contiguous_bits(long_mask, &start);
 
 	if (!n)
 		n = count_of_bits / 2;
@@ -217,88 +258,26 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type)
 			       count_of_bits - 1);
 		return -1;
 	}
-
-	/* Get core id from same socket for running another thread */
-	sibling_cpu_no = get_core_sibling(cpu_no);
-	if (sibling_cpu_no < 0)
-		return -1;
+	start_mask = create_bit_mask(start, n);
 
 	struct resctrl_val_param param = {
 		.resctrl_val	= CAT_STR,
 		.cpu_no		= cpu_no,
-		.setup		= cat_setup,
+		.ctrlgrp	= "c1",
+		.filename	= RESULT_FILE_NAME,
+		.num_of_runs	= 0,
 	};
-
-	l_mask = long_mask >> n;
-	l_mask_1 = ~l_mask & long_mask;
-
-	/* Set param values for parent thread which will be allocated bitmask
-	 * with (max_bits - n) bits
-	 */
-	span = cache_portion_size(cache_total_size, l_mask, full_cache_mask);
-	strcpy(param.ctrlgrp, "c2");
-	strcpy(param.mongrp, "m2");
-	strcpy(param.filename, RESULT_FILE_NAME2);
-	param.mask = l_mask;
-	param.num_of_runs = 0;
-
-	if (pipe(pipefd)) {
-		ksft_perror("Unable to create pipe");
-		return -1;
-	}
-
-	fflush(stdout);
-	bm_pid = fork();
-
-	/* Set param values for child thread which will be allocated bitmask
-	 * with n bits
-	 */
-	if (bm_pid == 0) {
-		param.mask = l_mask_1;
-		strcpy(param.ctrlgrp, "c1");
-		strcpy(param.mongrp, "m1");
-		span = cache_portion_size(cache_total_size, l_mask_1, full_cache_mask);
-		strcpy(param.filename, RESULT_FILE_NAME1);
-		param.num_of_runs = 0;
-		param.cpu_no = sibling_cpu_no;
-	}
+	param.mask = long_mask;
+	span = cache_portion_size(cache_total_size, start_mask, full_cache_mask);
 
 	remove(param.filename);
 
-	ret = cat_test(&param, span);
-	if (ret == 0)
-		ret = check_results(&param, span);
-
-	if (bm_pid == 0) {
-		/* Tell parent that child is ready */
-		close(pipefd[0]);
-		pipe_message = 1;
-		if (write(pipefd[1], &pipe_message, sizeof(pipe_message)) <
-		    sizeof(pipe_message))
-			/*
-			 * Just print the error message.
-			 * Let while(1) run and wait for itself to be killed.
-			 */
-			ksft_perror("Failed signaling parent process");
-
-		close(pipefd[1]);
-		while (1)
-			;
-	} else {
-		/* Parent waits for child to be ready. */
-		close(pipefd[1]);
-		pipe_message = 0;
-		while (pipe_message != 1) {
-			if (read(pipefd[0], &pipe_message,
-				 sizeof(pipe_message)) < sizeof(pipe_message)) {
-				ksft_perror("Failed reading from child process");
-				break;
-			}
-		}
-		close(pipefd[0]);
-		kill(bm_pid, SIGKILL);
-	}
+	ret = cat_test(&param, span, start_mask);
+	if (ret)
+		goto out;
 
+	ret = check_results(&param, cache_type, cache_total_size, full_cache_mask, start_mask);
+out:
 	cat_test_cleanup();
 
 	return ret;
diff --git a/tools/testing/selftests/resctrl/fill_buf.c b/tools/testing/selftests/resctrl/fill_buf.c
index 835adddb40be5..34e5df721430e 100644
--- a/tools/testing/selftests/resctrl/fill_buf.c
+++ b/tools/testing/selftests/resctrl/fill_buf.c
@@ -38,7 +38,7 @@ static void cl_flush(void *p)
 #endif
 }
 
-static void mem_flush(unsigned char *buf, size_t buf_size)
+void mem_flush(unsigned char *buf, size_t buf_size)
 {
 	unsigned char *cp = buf;
 	size_t i = 0;
@@ -100,7 +100,7 @@ static void fill_one_span_write(unsigned char *buf, size_t buf_size)
 	}
 }
 
-static void fill_cache_read(unsigned char *buf, size_t buf_size, bool once)
+void fill_cache_read(unsigned char *buf, size_t buf_size, bool once)
 {
 	int ret = 0;
 
@@ -123,7 +123,7 @@ static void fill_cache_write(unsigned char *buf, size_t buf_size, bool once)
 	}
 }
 
-static unsigned char *alloc_buffer(size_t buf_size, int memflush)
+unsigned char *alloc_buffer(size_t buf_size, int memflush)
 {
 	void *buf = NULL;
 	uint64_t *p64;
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 5b9bea5051201..4f040e999eea5 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -105,6 +105,9 @@ int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp,
 			    char *resctrl_val);
 int perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu,
 		    int group_fd, unsigned long flags);
+unsigned char *alloc_buffer(size_t buf_size, int memflush);
+void mem_flush(unsigned char *buf, size_t buf_size);
+void fill_cache_read(unsigned char *buf, size_t buf_size, bool once);
 int run_fill_buf(size_t buf_size, int memflush, int op, bool once);
 int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *param);
 int mbm_bw_change(int cpu_no, const char * const *benchmark_cmd);
@@ -113,6 +116,7 @@ void mbm_test_cleanup(void);
 int mba_schemata_change(int cpu_no, const char * const *benchmark_cmd);
 void mba_test_cleanup(void);
 unsigned long create_bit_mask(unsigned int start, unsigned int len);
+unsigned int count_contiguous_bits(unsigned long val, unsigned int *start);
 int get_full_cbm(const char *cache_type, unsigned long *mask);
 int get_mask_no_shareable(const char *cache_type, unsigned long *mask);
 int get_cache_size(int cpu_no, const char *cache_type, unsigned long *cache_size);
@@ -124,7 +128,6 @@ int cat_perf_miss_val(int cpu_no, int no_of_bits, char *cache_type);
 int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd);
 unsigned int count_bits(unsigned long n);
 void cmt_test_cleanup(void);
-int get_core_sibling(int cpu_no);
 
 void perf_event_attr_initialize(struct perf_event_attr *pea, __u64 config);
 void perf_event_initialize_read_format(struct perf_event_read *pe_read);
diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index a51f2018e2c5d..2b70600304a20 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -245,7 +245,7 @@ unsigned long create_bit_mask(unsigned int start, unsigned int len)
  *
  * Return:	The length of the contiguous bits in the longest train of bits
  */
-static unsigned int count_contiguous_bits(unsigned long val, unsigned int *start)
+unsigned int count_contiguous_bits(unsigned long val, unsigned int *start)
 {
 	unsigned long last_val;
 	unsigned int count = 0;
@@ -343,48 +343,6 @@ int get_mask_no_shareable(const char *cache_type, unsigned long *mask)
 	return 0;
 }
 
-/*
- * get_core_sibling - Get sibling core id from the same socket for given CPU
- * @cpu_no:	CPU number
- *
- * Return:	> 0 on success, < 0 on failure.
- */
-int get_core_sibling(int cpu_no)
-{
-	char core_siblings_path[1024], cpu_list_str[64];
-	int sibling_cpu_no = -1;
-	FILE *fp;
-
-	sprintf(core_siblings_path, "%s%d/topology/core_siblings_list",
-		CORE_SIBLINGS_PATH, cpu_no);
-
-	fp = fopen(core_siblings_path, "r");
-	if (!fp) {
-		ksft_perror("Failed to open core siblings path");
-
-		return -1;
-	}
-	if (fscanf(fp, "%s", cpu_list_str) <= 0) {
-		ksft_perror("Could not get core_siblings list");
-		fclose(fp);
-
-		return -1;
-	}
-	fclose(fp);
-
-	char *token = strtok(cpu_list_str, "-,");
-
-	while (token) {
-		sibling_cpu_no = atoi(token);
-		/* Skipping core 0 as we don't want to run test on core 0 */
-		if (sibling_cpu_no != 0 && sibling_cpu_no != cpu_no)
-			break;
-		token = strtok(NULL, "-,");
-	}
-
-	return sibling_cpu_no;
-}
-
 /*
  * taskset_benchmark - Taskset PID (i.e. benchmark) to a specified cpu
  * @bm_pid:	PID that should be binded

From 90876bede5e1232d295f3ee81a8cd05724859630 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 15 Dec 2023 17:05:09 +0200
Subject: [PATCH 173/236] selftests/resctrl: Restore the CPU affinity after CAT
 test
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 6c8cb747d071cf72c2930e09bb20ab3eabfe62ff upstream.

CAT test does not reset the CPU affinity after the benchmark.
This is relatively harmless as is because CAT test is the last
benchmark to run, however, more tests may be added later.

Store the CPU affinity the first time taskset_benchmark() is run and
add taskset_restore() which the test can call to reset the CPU mask to
its original value.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cat_test.c    | 13 +++++---
 tools/testing/selftests/resctrl/resctrl.h     |  3 +-
 tools/testing/selftests/resctrl/resctrl_val.c |  2 +-
 tools/testing/selftests/resctrl/resctrlfs.c   | 33 +++++++++++++++++--
 4 files changed, 42 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
index b799160697882..fa95433297c91 100644
--- a/tools/testing/selftests/resctrl/cat_test.c
+++ b/tools/testing/selftests/resctrl/cat_test.c
@@ -156,6 +156,7 @@ static int cat_test(struct resctrl_val_param *param, size_t span, unsigned long
 	char *resctrl_val = param->resctrl_val;
 	struct perf_event_read pe_read;
 	struct perf_event_attr pea;
+	cpu_set_t old_affinity;
 	unsigned char *buf;
 	char schemata[64];
 	int ret, i, pe_fd;
@@ -167,7 +168,7 @@ static int cat_test(struct resctrl_val_param *param, size_t span, unsigned long
 	bm_pid = getpid();
 
 	/* Taskset benchmark to specified cpu */
-	ret = taskset_benchmark(bm_pid, param->cpu_no);
+	ret = taskset_benchmark(bm_pid, param->cpu_no, &old_affinity);
 	if (ret)
 		return ret;
 
@@ -175,13 +176,15 @@ static int cat_test(struct resctrl_val_param *param, size_t span, unsigned long
 	ret = write_bm_pid_to_resctrl(bm_pid, param->ctrlgrp, param->mongrp,
 				      resctrl_val);
 	if (ret)
-		return ret;
+		goto reset_affinity;
 
 	perf_event_attr_initialize(&pea, PERF_COUNT_HW_CACHE_MISSES);
 	perf_event_initialize_read_format(&pe_read);
 	pe_fd = perf_open(&pea, bm_pid, param->cpu_no);
-	if (pe_fd < 0)
-		return pe_fd;
+	if (pe_fd < 0) {
+		ret = -1;
+		goto reset_affinity;
+	}
 
 	buf = alloc_buffer(span, 1);
 	if (!buf) {
@@ -220,6 +223,8 @@ static int cat_test(struct resctrl_val_param *param, size_t span, unsigned long
 	free(buf);
 pe_close:
 	close(pe_fd);
+reset_affinity:
+	taskset_restore(bm_pid, &old_affinity);
 
 	return ret;
 }
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 4f040e999eea5..94347acafe55e 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -98,7 +98,8 @@ int umount_resctrlfs(void);
 int validate_bw_report_request(char *bw_report);
 bool validate_resctrl_feature_request(const char *resource, const char *feature);
 char *fgrep(FILE *inf, const char *str);
-int taskset_benchmark(pid_t bm_pid, int cpu_no);
+int taskset_benchmark(pid_t bm_pid, int cpu_no, cpu_set_t *old_affinity);
+int taskset_restore(pid_t bm_pid, cpu_set_t *old_affinity);
 int write_schemata(char *ctrlgrp, char *schemata, int cpu_no,
 		   char *resctrl_val);
 int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp,
diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index 836cfa2ec1e98..78e4d91896280 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -794,7 +794,7 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
 	value.sival_ptr = (void *)benchmark_cmd;
 
 	/* Taskset benchmark to specified cpu */
-	ret = taskset_benchmark(bm_pid, param->cpu_no);
+	ret = taskset_benchmark(bm_pid, param->cpu_no, NULL);
 	if (ret)
 		goto out;
 
diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index 2b70600304a20..2de371af9ae72 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -345,15 +345,25 @@ int get_mask_no_shareable(const char *cache_type, unsigned long *mask)
 
 /*
  * taskset_benchmark - Taskset PID (i.e. benchmark) to a specified cpu
- * @bm_pid:	PID that should be binded
- * @cpu_no:	CPU number at which the PID would be binded
+ * @bm_pid:		PID that should be binded
+ * @cpu_no:		CPU number at which the PID would be binded
+ * @old_affinity:	When not NULL, set to old CPU affinity
  *
  * Return: 0 on success, < 0 on error.
  */
-int taskset_benchmark(pid_t bm_pid, int cpu_no)
+int taskset_benchmark(pid_t bm_pid, int cpu_no, cpu_set_t *old_affinity)
 {
 	cpu_set_t my_set;
 
+	if (old_affinity) {
+		CPU_ZERO(old_affinity);
+		if (sched_getaffinity(bm_pid, sizeof(*old_affinity),
+				      old_affinity)) {
+			ksft_perror("Unable to read CPU affinity");
+			return -1;
+		}
+	}
+
 	CPU_ZERO(&my_set);
 	CPU_SET(cpu_no, &my_set);
 
@@ -366,6 +376,23 @@ int taskset_benchmark(pid_t bm_pid, int cpu_no)
 	return 0;
 }
 
+/*
+ * taskset_restore - Taskset PID to the earlier CPU affinity
+ * @bm_pid:		PID that should be reset
+ * @old_affinity:	The old CPU affinity to restore
+ *
+ * Return: 0 on success, < 0 on error.
+ */
+int taskset_restore(pid_t bm_pid, cpu_set_t *old_affinity)
+{
+	if (sched_setaffinity(bm_pid, sizeof(*old_affinity), old_affinity)) {
+		ksft_perror("Unable to restore CPU affinity");
+		return -1;
+	}
+
+	return 0;
+}
+
 /*
  * create_grp - Create a group only if one doesn't exist
  * @grp_name:	Name of the group

From 306583cb1bb0c886e98b7cc9fe19f2969c297d09 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 15 Dec 2023 17:05:10 +0200
Subject: [PATCH 174/236] selftests/resctrl: Create struct for input parameters
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 15f298821289d3efba87bb34db29d0ba9780a443 upstream.

resctrl_tests reads a set of parameters and passes them individually
for each tests which causes variations in the call signature between
the tests.

Add struct input_params to hold all input parameters. It can be easily
passed to every test without varying the call signature.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cat_test.c    | 20 +++---
 tools/testing/selftests/resctrl/cmt_test.c    | 16 ++---
 tools/testing/selftests/resctrl/mba_test.c    |  9 ++-
 tools/testing/selftests/resctrl/mbm_test.c    |  9 ++-
 tools/testing/selftests/resctrl/resctrl.h     | 28 ++++++---
 .../testing/selftests/resctrl/resctrl_tests.c | 63 +++++++++++--------
 tools/testing/selftests/resctrl/resctrl_val.c | 21 ++++---
 7 files changed, 95 insertions(+), 71 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
index fa95433297c91..272132ff73377 100644
--- a/tools/testing/selftests/resctrl/cat_test.c
+++ b/tools/testing/selftests/resctrl/cat_test.c
@@ -135,6 +135,7 @@ void cat_test_cleanup(void)
 
 /*
  * cat_test - Execute CAT benchmark and measure cache misses
+ * @uparams:		User supplied parameters
  * @param:		Parameters passed to cat_test()
  * @span:		Buffer size for the benchmark
  * @current_mask	Start mask for the first iteration
@@ -151,7 +152,8 @@ void cat_test_cleanup(void)
  *
  * Return:		0 when the test was run, < 0 on error.
  */
-static int cat_test(struct resctrl_val_param *param, size_t span, unsigned long current_mask)
+static int cat_test(const struct user_params *uparams, struct resctrl_val_param *param,
+		    size_t span, unsigned long current_mask)
 {
 	char *resctrl_val = param->resctrl_val;
 	struct perf_event_read pe_read;
@@ -168,7 +170,7 @@ static int cat_test(struct resctrl_val_param *param, size_t span, unsigned long
 	bm_pid = getpid();
 
 	/* Taskset benchmark to specified cpu */
-	ret = taskset_benchmark(bm_pid, param->cpu_no, &old_affinity);
+	ret = taskset_benchmark(bm_pid, uparams->cpu, &old_affinity);
 	if (ret)
 		return ret;
 
@@ -180,7 +182,7 @@ static int cat_test(struct resctrl_val_param *param, size_t span, unsigned long
 
 	perf_event_attr_initialize(&pea, PERF_COUNT_HW_CACHE_MISSES);
 	perf_event_initialize_read_format(&pe_read);
-	pe_fd = perf_open(&pea, bm_pid, param->cpu_no);
+	pe_fd = perf_open(&pea, bm_pid, uparams->cpu);
 	if (pe_fd < 0) {
 		ret = -1;
 		goto reset_affinity;
@@ -194,11 +196,11 @@ static int cat_test(struct resctrl_val_param *param, size_t span, unsigned long
 
 	while (current_mask) {
 		snprintf(schemata, sizeof(schemata), "%lx", param->mask & ~current_mask);
-		ret = write_schemata("", schemata, param->cpu_no, param->resctrl_val);
+		ret = write_schemata("", schemata, uparams->cpu, param->resctrl_val);
 		if (ret)
 			goto free_buf;
 		snprintf(schemata, sizeof(schemata), "%lx", current_mask);
-		ret = write_schemata(param->ctrlgrp, schemata, param->cpu_no, param->resctrl_val);
+		ret = write_schemata(param->ctrlgrp, schemata, uparams->cpu, param->resctrl_val);
 		if (ret)
 			goto free_buf;
 
@@ -229,10 +231,11 @@ static int cat_test(struct resctrl_val_param *param, size_t span, unsigned long
 	return ret;
 }
 
-int cat_perf_miss_val(int cpu_no, int n, char *cache_type)
+int cat_perf_miss_val(const struct user_params *uparams, char *cache_type)
 {
 	unsigned long long_mask, start_mask, full_cache_mask;
 	unsigned long cache_total_size = 0;
+	int n = uparams->bits;
 	unsigned int start;
 	int count_of_bits;
 	size_t span;
@@ -247,7 +250,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type)
 		return ret;
 
 	/* Get L3/L2 cache size */
-	ret = get_cache_size(cpu_no, cache_type, &cache_total_size);
+	ret = get_cache_size(uparams->cpu, cache_type, &cache_total_size);
 	if (ret)
 		return ret;
 	ksft_print_msg("Cache size :%lu\n", cache_total_size);
@@ -267,7 +270,6 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type)
 
 	struct resctrl_val_param param = {
 		.resctrl_val	= CAT_STR,
-		.cpu_no		= cpu_no,
 		.ctrlgrp	= "c1",
 		.filename	= RESULT_FILE_NAME,
 		.num_of_runs	= 0,
@@ -277,7 +279,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type)
 
 	remove(param.filename);
 
-	ret = cat_test(&param, span, start_mask);
+	ret = cat_test(uparams, &param, span, start_mask);
 	if (ret)
 		goto out;
 
diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c
index 604690cd8b3e9..a5d0c0878c425 100644
--- a/tools/testing/selftests/resctrl/cmt_test.c
+++ b/tools/testing/selftests/resctrl/cmt_test.c
@@ -16,7 +16,7 @@
 #define MAX_DIFF		2000000
 #define MAX_DIFF_PERCENT	15
 
-static int cmt_setup(struct resctrl_val_param *p)
+static int cmt_setup(const struct user_params *uparams, struct resctrl_val_param *p)
 {
 	/* Run NUM_OF_RUNS times */
 	if (p->num_of_runs >= NUM_OF_RUNS)
@@ -94,11 +94,12 @@ void cmt_test_cleanup(void)
 	remove(RESULT_FILE_NAME);
 }
 
-int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd)
+int cmt_resctrl_val(const struct user_params *uparams)
 {
-	const char * const *cmd = benchmark_cmd;
+	const char * const *cmd = uparams->benchmark_cmd;
 	const char *new_cmd[BENCHMARK_ARGS];
 	unsigned long cache_total_size = 0;
+	int n = uparams->bits ? : 5;
 	unsigned long long_mask;
 	char *span_str = NULL;
 	int count_of_bits;
@@ -109,7 +110,7 @@ int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd)
 	if (ret)
 		return ret;
 
-	ret = get_cache_size(cpu_no, "L3", &cache_total_size);
+	ret = get_cache_size(uparams->cpu, "L3", &cache_total_size);
 	if (ret)
 		return ret;
 	ksft_print_msg("Cache size :%lu\n", cache_total_size);
@@ -126,7 +127,6 @@ int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd)
 		.resctrl_val	= CMT_STR,
 		.ctrlgrp	= "c1",
 		.mongrp		= "m1",
-		.cpu_no		= cpu_no,
 		.filename	= RESULT_FILE_NAME,
 		.mask		= ~(long_mask << n) & long_mask,
 		.num_of_runs	= 0,
@@ -137,8 +137,8 @@ int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd)
 
 	if (strcmp(cmd[0], "fill_buf") == 0) {
 		/* Duplicate the command to be able to replace span in it */
-		for (i = 0; benchmark_cmd[i]; i++)
-			new_cmd[i] = benchmark_cmd[i];
+		for (i = 0; uparams->benchmark_cmd[i]; i++)
+			new_cmd[i] = uparams->benchmark_cmd[i];
 		new_cmd[i] = NULL;
 
 		ret = asprintf(&span_str, "%zu", span);
@@ -150,7 +150,7 @@ int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd)
 
 	remove(RESULT_FILE_NAME);
 
-	ret = resctrl_val(cmd, &param);
+	ret = resctrl_val(uparams, cmd, &param);
 	if (ret)
 		goto out;
 
diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c
index e907adf7cd254..8e54bc508a754 100644
--- a/tools/testing/selftests/resctrl/mba_test.c
+++ b/tools/testing/selftests/resctrl/mba_test.c
@@ -22,7 +22,7 @@
  * con_mon grp, mon_grp in resctrl FS.
  * For each allocation, run 5 times in order to get average values.
  */
-static int mba_setup(struct resctrl_val_param *p)
+static int mba_setup(const struct user_params *uparams, struct resctrl_val_param *p)
 {
 	static int runs_per_allocation, allocation = 100;
 	char allocation_str[64];
@@ -40,7 +40,7 @@ static int mba_setup(struct resctrl_val_param *p)
 
 	sprintf(allocation_str, "%d", allocation);
 
-	ret = write_schemata(p->ctrlgrp, allocation_str, p->cpu_no,
+	ret = write_schemata(p->ctrlgrp, allocation_str, uparams->cpu,
 			     p->resctrl_val);
 	if (ret < 0)
 		return ret;
@@ -141,13 +141,12 @@ void mba_test_cleanup(void)
 	remove(RESULT_FILE_NAME);
 }
 
-int mba_schemata_change(int cpu_no, const char * const *benchmark_cmd)
+int mba_schemata_change(const struct user_params *uparams)
 {
 	struct resctrl_val_param param = {
 		.resctrl_val	= MBA_STR,
 		.ctrlgrp	= "c1",
 		.mongrp		= "m1",
-		.cpu_no		= cpu_no,
 		.filename	= RESULT_FILE_NAME,
 		.bw_report	= "reads",
 		.setup		= mba_setup
@@ -156,7 +155,7 @@ int mba_schemata_change(int cpu_no, const char * const *benchmark_cmd)
 
 	remove(RESULT_FILE_NAME);
 
-	ret = resctrl_val(benchmark_cmd, &param);
+	ret = resctrl_val(uparams, uparams->benchmark_cmd, &param);
 	if (ret)
 		goto out;
 
diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c
index 721b3ecbc1588..ea951cfae5fe4 100644
--- a/tools/testing/selftests/resctrl/mbm_test.c
+++ b/tools/testing/selftests/resctrl/mbm_test.c
@@ -86,7 +86,7 @@ static int check_results(size_t span)
 	return ret;
 }
 
-static int mbm_setup(struct resctrl_val_param *p)
+static int mbm_setup(const struct user_params *uparams, struct resctrl_val_param *p)
 {
 	int ret = 0;
 
@@ -96,7 +96,7 @@ static int mbm_setup(struct resctrl_val_param *p)
 
 	/* Set up shemata with 100% allocation on the first run. */
 	if (p->num_of_runs == 0 && validate_resctrl_feature_request("MB", NULL))
-		ret = write_schemata(p->ctrlgrp, "100", p->cpu_no,
+		ret = write_schemata(p->ctrlgrp, "100", uparams->cpu,
 				     p->resctrl_val);
 
 	p->num_of_runs++;
@@ -109,13 +109,12 @@ void mbm_test_cleanup(void)
 	remove(RESULT_FILE_NAME);
 }
 
-int mbm_bw_change(int cpu_no, const char * const *benchmark_cmd)
+int mbm_bw_change(const struct user_params *uparams)
 {
 	struct resctrl_val_param param = {
 		.resctrl_val	= MBM_STR,
 		.ctrlgrp	= "c1",
 		.mongrp		= "m1",
-		.cpu_no		= cpu_no,
 		.filename	= RESULT_FILE_NAME,
 		.bw_report	= "reads",
 		.setup		= mbm_setup
@@ -124,7 +123,7 @@ int mbm_bw_change(int cpu_no, const char * const *benchmark_cmd)
 
 	remove(RESULT_FILE_NAME);
 
-	ret = resctrl_val(benchmark_cmd, &param);
+	ret = resctrl_val(uparams, uparams->benchmark_cmd, &param);
 	if (ret)
 		goto out;
 
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 94347acafe55e..199ba91a78f73 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -44,12 +44,23 @@
 		exit(EXIT_FAILURE);		\
 	} while (0)
 
+/*
+ * user_params:		User supplied parameters
+ * @cpu:		CPU number to which the benchmark will be bound to
+ * @bits:		Number of bits used for cache allocation size
+ * @benchmark_cmd:	Benchmark command to run during (some of the) tests
+ */
+struct user_params {
+	int cpu;
+	int bits;
+	const char *benchmark_cmd[BENCHMARK_ARGS];
+};
+
 /*
  * resctrl_val_param:	resctrl test parameters
  * @resctrl_val:	Resctrl feature (Eg: mbm, mba.. etc)
  * @ctrlgrp:		Name of the control monitor group (con_mon grp)
  * @mongrp:		Name of the monitor group (mon grp)
- * @cpu_no:		CPU number to which the benchmark would be binded
  * @filename:		Name of file to which the o/p should be written
  * @bw_report:		Bandwidth report type (reads vs writes)
  * @setup:		Call back function to setup test environment
@@ -58,12 +69,12 @@ struct resctrl_val_param {
 	char		*resctrl_val;
 	char		ctrlgrp[64];
 	char		mongrp[64];
-	int		cpu_no;
 	char		filename[64];
 	char		*bw_report;
 	unsigned long	mask;
 	int		num_of_runs;
-	int		(*setup)(struct resctrl_val_param *param);
+	int		(*setup)(const struct user_params *uparams,
+				 struct resctrl_val_param *param);
 };
 
 struct perf_event_read {
@@ -110,11 +121,12 @@ unsigned char *alloc_buffer(size_t buf_size, int memflush);
 void mem_flush(unsigned char *buf, size_t buf_size);
 void fill_cache_read(unsigned char *buf, size_t buf_size, bool once);
 int run_fill_buf(size_t buf_size, int memflush, int op, bool once);
-int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *param);
-int mbm_bw_change(int cpu_no, const char * const *benchmark_cmd);
+int resctrl_val(const struct user_params *uparams, const char * const *benchmark_cmd,
+		struct resctrl_val_param *param);
+int mbm_bw_change(const struct user_params *uparams);
 void tests_cleanup(void);
 void mbm_test_cleanup(void);
-int mba_schemata_change(int cpu_no, const char * const *benchmark_cmd);
+int mba_schemata_change(const struct user_params *uparams);
 void mba_test_cleanup(void);
 unsigned long create_bit_mask(unsigned int start, unsigned int len);
 unsigned int count_contiguous_bits(unsigned long val, unsigned int *start);
@@ -125,8 +137,8 @@ void ctrlc_handler(int signum, siginfo_t *info, void *ptr);
 int signal_handler_register(void);
 void signal_handler_unregister(void);
 void cat_test_cleanup(void);
-int cat_perf_miss_val(int cpu_no, int no_of_bits, char *cache_type);
-int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd);
+int cat_perf_miss_val(const struct user_params *uparams, char *cache_type);
+int cmt_resctrl_val(const struct user_params *uparams);
 unsigned int count_bits(unsigned long n);
 void cmt_test_cleanup(void);
 
diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c
index f0d573aa363b8..3059a124ac592 100644
--- a/tools/testing/selftests/resctrl/resctrl_tests.c
+++ b/tools/testing/selftests/resctrl/resctrl_tests.c
@@ -96,7 +96,7 @@ static void test_cleanup(void)
 	signal_handler_unregister();
 }
 
-static void run_mbm_test(const char * const *benchmark_cmd, int cpu_no)
+static void run_mbm_test(const struct user_params *uparams)
 {
 	int res;
 
@@ -114,7 +114,7 @@ static void run_mbm_test(const char * const *benchmark_cmd, int cpu_no)
 		goto cleanup;
 	}
 
-	res = mbm_bw_change(cpu_no, benchmark_cmd);
+	res = mbm_bw_change(uparams);
 	ksft_test_result(!res, "MBM: bw change\n");
 	if ((get_vendor() == ARCH_INTEL) && res)
 		ksft_print_msg("Intel MBM may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n");
@@ -123,7 +123,7 @@ static void run_mbm_test(const char * const *benchmark_cmd, int cpu_no)
 	test_cleanup();
 }
 
-static void run_mba_test(const char * const *benchmark_cmd, int cpu_no)
+static void run_mba_test(const struct user_params *uparams)
 {
 	int res;
 
@@ -141,14 +141,14 @@ static void run_mba_test(const char * const *benchmark_cmd, int cpu_no)
 		goto cleanup;
 	}
 
-	res = mba_schemata_change(cpu_no, benchmark_cmd);
+	res = mba_schemata_change(uparams);
 	ksft_test_result(!res, "MBA: schemata change\n");
 
 cleanup:
 	test_cleanup();
 }
 
-static void run_cmt_test(const char * const *benchmark_cmd, int cpu_no)
+static void run_cmt_test(const struct user_params *uparams)
 {
 	int res;
 
@@ -165,7 +165,7 @@ static void run_cmt_test(const char * const *benchmark_cmd, int cpu_no)
 		goto cleanup;
 	}
 
-	res = cmt_resctrl_val(cpu_no, 5, benchmark_cmd);
+	res = cmt_resctrl_val(uparams);
 	ksft_test_result(!res, "CMT: test\n");
 	if ((get_vendor() == ARCH_INTEL) && res)
 		ksft_print_msg("Intel CMT may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n");
@@ -174,7 +174,7 @@ static void run_cmt_test(const char * const *benchmark_cmd, int cpu_no)
 	test_cleanup();
 }
 
-static void run_cat_test(int cpu_no, int no_of_bits)
+static void run_cat_test(const struct user_params *uparams)
 {
 	int res;
 
@@ -190,22 +190,31 @@ static void run_cat_test(int cpu_no, int no_of_bits)
 		goto cleanup;
 	}
 
-	res = cat_perf_miss_val(cpu_no, no_of_bits, "L3");
+	res = cat_perf_miss_val(uparams, "L3");
 	ksft_test_result(!res, "CAT: test\n");
 
 cleanup:
 	test_cleanup();
 }
 
+static void init_user_params(struct user_params *uparams)
+{
+	memset(uparams, 0, sizeof(*uparams));
+
+	uparams->cpu = 1;
+	uparams->bits = 0;
+}
+
 int main(int argc, char **argv)
 {
 	bool mbm_test = true, mba_test = true, cmt_test = true;
-	const char *benchmark_cmd[BENCHMARK_ARGS] = {};
-	int c, cpu_no = 1, i, no_of_bits = 0;
+	struct user_params uparams;
 	char *span_str = NULL;
 	bool cat_test = true;
 	int tests = 0;
-	int ret;
+	int ret, c, i;
+
+	init_user_params(&uparams);
 
 	while ((c = getopt(argc, argv, "ht:b:n:p:")) != -1) {
 		char *token;
@@ -223,8 +232,8 @@ int main(int argc, char **argv)
 
 			/* Extract benchmark command from command line. */
 			for (i = 0; i < argc - optind; i++)
-				benchmark_cmd[i] = argv[i + optind];
-			benchmark_cmd[i] = NULL;
+				uparams.benchmark_cmd[i] = argv[i + optind];
+			uparams.benchmark_cmd[i] = NULL;
 
 			goto last_arg;
 		case 't':
@@ -256,11 +265,11 @@ int main(int argc, char **argv)
 			}
 			break;
 		case 'p':
-			cpu_no = atoi(optarg);
+			uparams.cpu = atoi(optarg);
 			break;
 		case 'n':
-			no_of_bits = atoi(optarg);
-			if (no_of_bits <= 0) {
+			uparams.bits = atoi(optarg);
+			if (uparams.bits <= 0) {
 				printf("Bail out! invalid argument for no_of_bits\n");
 				return -1;
 			}
@@ -295,32 +304,32 @@ int main(int argc, char **argv)
 
 	filter_dmesg();
 
-	if (!benchmark_cmd[0]) {
+	if (!uparams.benchmark_cmd[0]) {
 		/* If no benchmark is given by "-b" argument, use fill_buf. */
-		benchmark_cmd[0] = "fill_buf";
+		uparams.benchmark_cmd[0] = "fill_buf";
 		ret = asprintf(&span_str, "%u", DEFAULT_SPAN);
 		if (ret < 0)
 			ksft_exit_fail_msg("Out of memory!\n");
-		benchmark_cmd[1] = span_str;
-		benchmark_cmd[2] = "1";
-		benchmark_cmd[3] = "0";
-		benchmark_cmd[4] = "false";
-		benchmark_cmd[5] = NULL;
+		uparams.benchmark_cmd[1] = span_str;
+		uparams.benchmark_cmd[2] = "1";
+		uparams.benchmark_cmd[3] = "0";
+		uparams.benchmark_cmd[4] = "false";
+		uparams.benchmark_cmd[5] = NULL;
 	}
 
 	ksft_set_plan(tests ? : 4);
 
 	if (mbm_test)
-		run_mbm_test(benchmark_cmd, cpu_no);
+		run_mbm_test(&uparams);
 
 	if (mba_test)
-		run_mba_test(benchmark_cmd, cpu_no);
+		run_mba_test(&uparams);
 
 	if (cmt_test)
-		run_cmt_test(benchmark_cmd, cpu_no);
+		run_cmt_test(&uparams);
 
 	if (cat_test)
-		run_cat_test(cpu_no, no_of_bits);
+		run_cat_test(&uparams);
 
 	free(span_str);
 	ksft_finished();
diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index 78e4d91896280..68ad0b3e8dc58 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -610,8 +610,9 @@ static void initialize_llc_occu_resctrl(const char *ctrlgrp, const char *mongrp,
 		set_cmt_path(ctrlgrp, mongrp, resource_id);
 }
 
-static int
-measure_vals(struct resctrl_val_param *param, unsigned long *bw_resc_start)
+static int measure_vals(const struct user_params *uparams,
+			struct resctrl_val_param *param,
+			unsigned long *bw_resc_start)
 {
 	unsigned long bw_resc, bw_resc_end;
 	float bw_imc;
@@ -624,7 +625,7 @@ measure_vals(struct resctrl_val_param *param, unsigned long *bw_resc_start)
 	 * Compare the two values to validate resctrl value.
 	 * It takes 1sec to measure the data.
 	 */
-	ret = get_mem_bw_imc(param->cpu_no, param->bw_report, &bw_imc);
+	ret = get_mem_bw_imc(uparams->cpu, param->bw_report, &bw_imc);
 	if (ret < 0)
 		return ret;
 
@@ -700,12 +701,14 @@ static void run_benchmark(int signum, siginfo_t *info, void *ucontext)
 /*
  * resctrl_val:	execute benchmark and measure memory bandwidth on
  *			the benchmark
+ * @uparams:		user supplied parameters
  * @benchmark_cmd:	benchmark command and its arguments
  * @param:		parameters passed to resctrl_val()
  *
  * Return:		0 when the test was run, < 0 on error.
  */
-int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *param)
+int resctrl_val(const struct user_params *uparams, const char * const *benchmark_cmd,
+		struct resctrl_val_param *param)
 {
 	char *resctrl_val = param->resctrl_val;
 	unsigned long bw_resc_start = 0;
@@ -794,7 +797,7 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
 	value.sival_ptr = (void *)benchmark_cmd;
 
 	/* Taskset benchmark to specified cpu */
-	ret = taskset_benchmark(bm_pid, param->cpu_no, NULL);
+	ret = taskset_benchmark(bm_pid, uparams->cpu, NULL);
 	if (ret)
 		goto out;
 
@@ -811,10 +814,10 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
 			goto out;
 
 		initialize_mem_bw_resctrl(param->ctrlgrp, param->mongrp,
-					  param->cpu_no, resctrl_val);
+					  uparams->cpu, resctrl_val);
 	} else if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR)))
 		initialize_llc_occu_resctrl(param->ctrlgrp, param->mongrp,
-					    param->cpu_no, resctrl_val);
+					    uparams->cpu, resctrl_val);
 
 	/* Parent waits for child to be ready. */
 	close(pipefd[1]);
@@ -840,7 +843,7 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
 
 	/* Test runs until the callback setup() tells the test to stop. */
 	while (1) {
-		ret = param->setup(param);
+		ret = param->setup(uparams, param);
 		if (ret == END_OF_TESTS) {
 			ret = 0;
 			break;
@@ -850,7 +853,7 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par
 
 		if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)) ||
 		    !strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR))) {
-			ret = measure_vals(param, &bw_resc_start);
+			ret = measure_vals(uparams, param, &bw_resc_start);
 			if (ret)
 				break;
 		} else if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) {

From d4b80ec01c4ca6385c424ab030cdbc9ea7088120 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 15 Dec 2023 17:05:11 +0200
Subject: [PATCH 175/236] selftests/resctrl: Introduce generalized test
 framework
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit c603ff5bb830b8c22dae56ca3ca5ceb5c103525b upstream.

Each test currently has a "run test" function in per test file and
another resctrl_tests.c. The functions in resctrl_tests.c are almost
identical.

Generalize the one in resctrl_tests.c such that it can be shared
between all of the tests. It makes adding new tests easier and removes
the per test if () forests.

Also add comment to CPU vendor IDs that they must be defined as bits
for a bitmask.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cat_test.c    |  18 +-
 tools/testing/selftests/resctrl/cmt_test.c    |  17 +-
 tools/testing/selftests/resctrl/mba_test.c    |  16 +-
 tools/testing/selftests/resctrl/mbm_test.c    |  18 +-
 tools/testing/selftests/resctrl/resctrl.h     |  35 +++-
 .../testing/selftests/resctrl/resctrl_tests.c | 160 ++++++------------
 tools/testing/selftests/resctrl/resctrlfs.c   |   5 +
 7 files changed, 148 insertions(+), 121 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
index 272132ff73377..a9b4583620d0a 100644
--- a/tools/testing/selftests/resctrl/cat_test.c
+++ b/tools/testing/selftests/resctrl/cat_test.c
@@ -231,7 +231,7 @@ static int cat_test(const struct user_params *uparams, struct resctrl_val_param
 	return ret;
 }
 
-int cat_perf_miss_val(const struct user_params *uparams, char *cache_type)
+static int cat_run_test(const struct resctrl_test *test, const struct user_params *uparams)
 {
 	unsigned long long_mask, start_mask, full_cache_mask;
 	unsigned long cache_total_size = 0;
@@ -241,16 +241,16 @@ int cat_perf_miss_val(const struct user_params *uparams, char *cache_type)
 	size_t span;
 	int ret;
 
-	ret = get_full_cbm(cache_type, &full_cache_mask);
+	ret = get_full_cbm(test->resource, &full_cache_mask);
 	if (ret)
 		return ret;
 	/* Get the largest contiguous exclusive portion of the cache */
-	ret = get_mask_no_shareable(cache_type, &long_mask);
+	ret = get_mask_no_shareable(test->resource, &long_mask);
 	if (ret)
 		return ret;
 
 	/* Get L3/L2 cache size */
-	ret = get_cache_size(uparams->cpu, cache_type, &cache_total_size);
+	ret = get_cache_size(uparams->cpu, test->resource, &cache_total_size);
 	if (ret)
 		return ret;
 	ksft_print_msg("Cache size :%lu\n", cache_total_size);
@@ -283,9 +283,17 @@ int cat_perf_miss_val(const struct user_params *uparams, char *cache_type)
 	if (ret)
 		goto out;
 
-	ret = check_results(&param, cache_type, cache_total_size, full_cache_mask, start_mask);
+	ret = check_results(&param, test->resource,
+			    cache_total_size, full_cache_mask, start_mask);
 out:
 	cat_test_cleanup();
 
 	return ret;
 }
+
+struct resctrl_test l3_cat_test = {
+	.name = "CAT",
+	.resource = "L3",
+	.feature_check = test_resource_feature_check,
+	.run_test = cat_run_test,
+};
diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c
index a5d0c0878c425..c01980039118e 100644
--- a/tools/testing/selftests/resctrl/cmt_test.c
+++ b/tools/testing/selftests/resctrl/cmt_test.c
@@ -94,7 +94,7 @@ void cmt_test_cleanup(void)
 	remove(RESULT_FILE_NAME);
 }
 
-int cmt_resctrl_val(const struct user_params *uparams)
+static int cmt_run_test(const struct resctrl_test *test, const struct user_params *uparams)
 {
 	const char * const *cmd = uparams->benchmark_cmd;
 	const char *new_cmd[BENCHMARK_ARGS];
@@ -155,6 +155,8 @@ int cmt_resctrl_val(const struct user_params *uparams)
 		goto out;
 
 	ret = check_results(&param, span, n);
+	if (ret && (get_vendor() == ARCH_INTEL))
+		ksft_print_msg("Intel CMT may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n");
 
 out:
 	cmt_test_cleanup();
@@ -162,3 +164,16 @@ int cmt_resctrl_val(const struct user_params *uparams)
 
 	return ret;
 }
+
+static bool cmt_feature_check(const struct resctrl_test *test)
+{
+	return test_resource_feature_check(test) &&
+	       validate_resctrl_feature_request("L3_MON", "llc_occupancy");
+}
+
+struct resctrl_test cmt_test = {
+	.name = "CMT",
+	.resource = "L3",
+	.feature_check = cmt_feature_check,
+	.run_test = cmt_run_test,
+};
diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c
index 8e54bc508a754..c218af24f91d9 100644
--- a/tools/testing/selftests/resctrl/mba_test.c
+++ b/tools/testing/selftests/resctrl/mba_test.c
@@ -141,7 +141,7 @@ void mba_test_cleanup(void)
 	remove(RESULT_FILE_NAME);
 }
 
-int mba_schemata_change(const struct user_params *uparams)
+static int mba_run_test(const struct resctrl_test *test, const struct user_params *uparams)
 {
 	struct resctrl_val_param param = {
 		.resctrl_val	= MBA_STR,
@@ -166,3 +166,17 @@ int mba_schemata_change(const struct user_params *uparams)
 
 	return ret;
 }
+
+static bool mba_feature_check(const struct resctrl_test *test)
+{
+	return test_resource_feature_check(test) &&
+	       validate_resctrl_feature_request("L3_MON", "mbm_local_bytes");
+}
+
+struct resctrl_test mba_test = {
+	.name = "MBA",
+	.resource = "MB",
+	.vendor_specific = ARCH_INTEL,
+	.feature_check = mba_feature_check,
+	.run_test = mba_run_test,
+};
diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c
index ea951cfae5fe4..919b10459c223 100644
--- a/tools/testing/selftests/resctrl/mbm_test.c
+++ b/tools/testing/selftests/resctrl/mbm_test.c
@@ -109,7 +109,7 @@ void mbm_test_cleanup(void)
 	remove(RESULT_FILE_NAME);
 }
 
-int mbm_bw_change(const struct user_params *uparams)
+static int mbm_run_test(const struct resctrl_test *test, const struct user_params *uparams)
 {
 	struct resctrl_val_param param = {
 		.resctrl_val	= MBM_STR,
@@ -128,9 +128,25 @@ int mbm_bw_change(const struct user_params *uparams)
 		goto out;
 
 	ret = check_results(DEFAULT_SPAN);
+	if (ret && (get_vendor() == ARCH_INTEL))
+		ksft_print_msg("Intel MBM may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n");
 
 out:
 	mbm_test_cleanup();
 
 	return ret;
 }
+
+static bool mbm_feature_check(const struct resctrl_test *test)
+{
+	return validate_resctrl_feature_request("L3_MON", "mbm_total_bytes") &&
+	       validate_resctrl_feature_request("L3_MON", "mbm_local_bytes");
+}
+
+struct resctrl_test mbm_test = {
+	.name = "MBM",
+	.resource = "MB",
+	.vendor_specific = ARCH_INTEL,
+	.feature_check = mbm_feature_check,
+	.run_test = mbm_run_test,
+};
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 199ba91a78f73..1168364b4cc2f 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -28,6 +28,12 @@
 #define PHYS_ID_PATH		"/sys/devices/system/cpu/cpu"
 #define INFO_PATH		"/sys/fs/resctrl/info"
 
+/*
+ * CPU vendor IDs
+ *
+ * Define as bits because they're used for vendor_specific bitmask in
+ * the struct resctrl_test.
+ */
 #define ARCH_INTEL     1
 #define ARCH_AMD       2
 
@@ -56,6 +62,25 @@ struct user_params {
 	const char *benchmark_cmd[BENCHMARK_ARGS];
 };
 
+/*
+ * resctrl_test:	resctrl test definition
+ * @name:		Test name
+ * @resource:		Resource to test (e.g., MB, L3, L2, etc.)
+ * @vendor_specific:	Bitmask for vendor-specific tests (can be 0 for universal tests)
+ * @disabled:		Test is disabled
+ * @feature_check:	Callback to check required resctrl features
+ * @run_test:		Callback to run the test
+ */
+struct resctrl_test {
+	const char	*name;
+	const char	*resource;
+	unsigned int	vendor_specific;
+	bool		disabled;
+	bool		(*feature_check)(const struct resctrl_test *test);
+	int		(*run_test)(const struct resctrl_test *test,
+				    const struct user_params *uparams);
+};
+
 /*
  * resctrl_val_param:	resctrl test parameters
  * @resctrl_val:	Resctrl feature (Eg: mbm, mba.. etc)
@@ -108,6 +133,7 @@ int mount_resctrlfs(void);
 int umount_resctrlfs(void);
 int validate_bw_report_request(char *bw_report);
 bool validate_resctrl_feature_request(const char *resource, const char *feature);
+bool test_resource_feature_check(const struct resctrl_test *test);
 char *fgrep(FILE *inf, const char *str);
 int taskset_benchmark(pid_t bm_pid, int cpu_no, cpu_set_t *old_affinity);
 int taskset_restore(pid_t bm_pid, cpu_set_t *old_affinity);
@@ -123,10 +149,8 @@ void fill_cache_read(unsigned char *buf, size_t buf_size, bool once);
 int run_fill_buf(size_t buf_size, int memflush, int op, bool once);
 int resctrl_val(const struct user_params *uparams, const char * const *benchmark_cmd,
 		struct resctrl_val_param *param);
-int mbm_bw_change(const struct user_params *uparams);
 void tests_cleanup(void);
 void mbm_test_cleanup(void);
-int mba_schemata_change(const struct user_params *uparams);
 void mba_test_cleanup(void);
 unsigned long create_bit_mask(unsigned int start, unsigned int len);
 unsigned int count_contiguous_bits(unsigned long val, unsigned int *start);
@@ -137,8 +161,6 @@ void ctrlc_handler(int signum, siginfo_t *info, void *ptr);
 int signal_handler_register(void);
 void signal_handler_unregister(void);
 void cat_test_cleanup(void);
-int cat_perf_miss_val(const struct user_params *uparams, char *cache_type);
-int cmt_resctrl_val(const struct user_params *uparams);
 unsigned int count_bits(unsigned long n);
 void cmt_test_cleanup(void);
 
@@ -175,4 +197,9 @@ static inline unsigned long cache_portion_size(unsigned long cache_size,
 	return cache_size * count_bits(portion_mask) / bits;
 }
 
+extern struct resctrl_test mbm_test;
+extern struct resctrl_test mba_test;
+extern struct resctrl_test cmt_test;
+extern struct resctrl_test l3_cat_test;
+
 #endif /* RESCTRL_H */
diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c
index 3059a124ac592..75fc49ba3efb0 100644
--- a/tools/testing/selftests/resctrl/resctrl_tests.c
+++ b/tools/testing/selftests/resctrl/resctrl_tests.c
@@ -14,6 +14,13 @@
 static volatile int sink_target;
 volatile int *value_sink = &sink_target;
 
+static struct resctrl_test *resctrl_tests[] = {
+	&mbm_test,
+	&mba_test,
+	&cmt_test,
+	&l3_cat_test,
+};
+
 static int detect_vendor(void)
 {
 	FILE *inf = fopen("/proc/cpuinfo", "r");
@@ -53,11 +60,16 @@ int get_vendor(void)
 
 static void cmd_help(void)
 {
+	int i;
+
 	printf("usage: resctrl_tests [-h] [-t test list] [-n no_of_bits] [-b benchmark_cmd [option]...]\n");
 	printf("\t-b benchmark_cmd [option]...: run specified benchmark for MBM, MBA and CMT\n");
 	printf("\t   default benchmark is builtin fill_buf\n");
 	printf("\t-t test list: run tests specified in the test list, ");
 	printf("e.g. -t mbm,mba,cmt,cat\n");
+	printf("\t\tSupported tests:\n");
+	for (i = 0; i < ARRAY_SIZE(resctrl_tests); i++)
+		printf("\t\t\t%s\n", resctrl_tests[i]->name);
 	printf("\t-n no_of_bits: run cache tests using specified no of bits in cache bit mask\n");
 	printf("\t-p cpu_no: specify CPU number to run the test. 1 is default\n");
 	printf("\t-h: help\n");
@@ -96,102 +108,41 @@ static void test_cleanup(void)
 	signal_handler_unregister();
 }
 
-static void run_mbm_test(const struct user_params *uparams)
+static bool test_vendor_specific_check(const struct resctrl_test *test)
 {
-	int res;
-
-	ksft_print_msg("Starting MBM BW change ...\n");
-
-	if (test_prepare()) {
-		ksft_exit_fail_msg("Abnormal failure when preparing for the test\n");
-		return;
-	}
-
-	if (!validate_resctrl_feature_request("L3_MON", "mbm_total_bytes") ||
-	    !validate_resctrl_feature_request("L3_MON", "mbm_local_bytes") ||
-	    (get_vendor() != ARCH_INTEL)) {
-		ksft_test_result_skip("Hardware does not support MBM or MBM is disabled\n");
-		goto cleanup;
-	}
-
-	res = mbm_bw_change(uparams);
-	ksft_test_result(!res, "MBM: bw change\n");
-	if ((get_vendor() == ARCH_INTEL) && res)
-		ksft_print_msg("Intel MBM may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n");
+	if (!test->vendor_specific)
+		return true;
 
-cleanup:
-	test_cleanup();
+	return get_vendor() & test->vendor_specific;
 }
 
-static void run_mba_test(const struct user_params *uparams)
+static void run_single_test(const struct resctrl_test *test, const struct user_params *uparams)
 {
-	int res;
-
-	ksft_print_msg("Starting MBA Schemata change ...\n");
+	int ret;
 
-	if (test_prepare()) {
-		ksft_exit_fail_msg("Abnormal failure when preparing for the test\n");
+	if (test->disabled)
 		return;
-	}
 
-	if (!validate_resctrl_feature_request("MB", NULL) ||
-	    !validate_resctrl_feature_request("L3_MON", "mbm_local_bytes") ||
-	    (get_vendor() != ARCH_INTEL)) {
-		ksft_test_result_skip("Hardware does not support MBA or MBA is disabled\n");
-		goto cleanup;
-	}
-
-	res = mba_schemata_change(uparams);
-	ksft_test_result(!res, "MBA: schemata change\n");
-
-cleanup:
-	test_cleanup();
-}
-
-static void run_cmt_test(const struct user_params *uparams)
-{
-	int res;
-
-	ksft_print_msg("Starting CMT test ...\n");
-
-	if (test_prepare()) {
-		ksft_exit_fail_msg("Abnormal failure when preparing for the test\n");
+	if (!test_vendor_specific_check(test)) {
+		ksft_test_result_skip("Hardware does not support %s\n", test->name);
 		return;
 	}
 
-	if (!validate_resctrl_feature_request("L3_MON", "llc_occupancy") ||
-	    !validate_resctrl_feature_request("L3", NULL)) {
-		ksft_test_result_skip("Hardware does not support CMT or CMT is disabled\n");
-		goto cleanup;
-	}
-
-	res = cmt_resctrl_val(uparams);
-	ksft_test_result(!res, "CMT: test\n");
-	if ((get_vendor() == ARCH_INTEL) && res)
-		ksft_print_msg("Intel CMT may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n");
-
-cleanup:
-	test_cleanup();
-}
-
-static void run_cat_test(const struct user_params *uparams)
-{
-	int res;
-
-	ksft_print_msg("Starting CAT test ...\n");
+	ksft_print_msg("Starting %s test ...\n", test->name);
 
 	if (test_prepare()) {
 		ksft_exit_fail_msg("Abnormal failure when preparing for the test\n");
 		return;
 	}
 
-	if (!validate_resctrl_feature_request("L3", NULL)) {
-		ksft_test_result_skip("Hardware does not support CAT or CAT is disabled\n");
+	if (!test->feature_check(test)) {
+		ksft_test_result_skip("Hardware does not support %s or %s is disabled\n",
+				      test->name, test->name);
 		goto cleanup;
 	}
 
-	res = cat_perf_miss_val(uparams, "L3");
-	ksft_test_result(!res, "CAT: test\n");
+	ret = test->run_test(test, uparams);
+	ksft_test_result(!ret, "%s: test\n", test->name);
 
 cleanup:
 	test_cleanup();
@@ -207,11 +158,10 @@ static void init_user_params(struct user_params *uparams)
 
 int main(int argc, char **argv)
 {
-	bool mbm_test = true, mba_test = true, cmt_test = true;
+	int tests = ARRAY_SIZE(resctrl_tests);
+	bool test_param_seen = false;
 	struct user_params uparams;
 	char *span_str = NULL;
-	bool cat_test = true;
-	int tests = 0;
 	int ret, c, i;
 
 	init_user_params(&uparams);
@@ -239,25 +189,26 @@ int main(int argc, char **argv)
 		case 't':
 			token = strtok(optarg, ",");
 
-			mbm_test = false;
-			mba_test = false;
-			cmt_test = false;
-			cat_test = false;
+			if (!test_param_seen) {
+				for (i = 0; i < ARRAY_SIZE(resctrl_tests); i++)
+					resctrl_tests[i]->disabled = true;
+				tests = 0;
+				test_param_seen = true;
+			}
 			while (token) {
-				if (!strncmp(token, MBM_STR, sizeof(MBM_STR))) {
-					mbm_test = true;
-					tests++;
-				} else if (!strncmp(token, MBA_STR, sizeof(MBA_STR))) {
-					mba_test = true;
-					tests++;
-				} else if (!strncmp(token, CMT_STR, sizeof(CMT_STR))) {
-					cmt_test = true;
-					tests++;
-				} else if (!strncmp(token, CAT_STR, sizeof(CAT_STR))) {
-					cat_test = true;
-					tests++;
-				} else {
-					printf("invalid argument\n");
+				bool found = false;
+
+				for (i = 0; i < ARRAY_SIZE(resctrl_tests); i++) {
+					if (!strcasecmp(token, resctrl_tests[i]->name)) {
+						if (resctrl_tests[i]->disabled)
+							tests++;
+						resctrl_tests[i]->disabled = false;
+						found = true;
+					}
+				}
+
+				if (!found) {
+					printf("invalid test: %s\n", token);
 
 					return -1;
 				}
@@ -317,19 +268,10 @@ int main(int argc, char **argv)
 		uparams.benchmark_cmd[5] = NULL;
 	}
 
-	ksft_set_plan(tests ? : 4);
-
-	if (mbm_test)
-		run_mbm_test(&uparams);
-
-	if (mba_test)
-		run_mba_test(&uparams);
-
-	if (cmt_test)
-		run_cmt_test(&uparams);
+	ksft_set_plan(tests);
 
-	if (cat_test)
-		run_cat_test(&uparams);
+	for (i = 0; i < ARRAY_SIZE(resctrl_tests); i++)
+		run_single_test(resctrl_tests[i], &uparams);
 
 	free(span_str);
 	ksft_finished();
diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index 2de371af9ae72..a2cfa9e8b448d 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -706,6 +706,11 @@ bool validate_resctrl_feature_request(const char *resource, const char *feature)
 	return !!res;
 }
 
+bool test_resource_feature_check(const struct resctrl_test *test)
+{
+	return validate_resctrl_feature_request(test->resource, NULL);
+}
+
 int filter_dmesg(void)
 {
 	char line[1024];

From 69721ca51192f3ffeec1d598ebe7138b702932ab Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 15 Dec 2023 17:05:12 +0200
Subject: [PATCH 176/236] selftests/resctrl: Pass write_schemata() resource
 instead of test name
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit ca1608875ae21bb40a7731b81bc0e2c95622d502 upstream.

write_schemata() takes the test name as an argument and determines the
relevant resource based on the test name. Such mapping from name to
resource does not really belong to resctrlfs.c that should provide
only generic, test-independent functions.

Pass the resource stored in the test information structure to
write_schemata() instead of the test name. The new API is also more
flexible as it enables to use write_schemata() for more than one
resource within a test.

While touching the sprintf(), move the unnecessary %c that is always
'=' directly into the format string.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cat_test.c    | 11 +++++----
 tools/testing/selftests/resctrl/cmt_test.c    |  6 +++--
 tools/testing/selftests/resctrl/mba_test.c    |  9 +++----
 tools/testing/selftests/resctrl/mbm_test.c    |  9 +++----
 tools/testing/selftests/resctrl/resctrl.h     | 10 ++++----
 tools/testing/selftests/resctrl/resctrl_val.c |  7 ++++--
 tools/testing/selftests/resctrl/resctrlfs.c   | 24 +++++--------------
 7 files changed, 38 insertions(+), 38 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
index a9b4583620d0a..24af8310288aa 100644
--- a/tools/testing/selftests/resctrl/cat_test.c
+++ b/tools/testing/selftests/resctrl/cat_test.c
@@ -135,6 +135,7 @@ void cat_test_cleanup(void)
 
 /*
  * cat_test - Execute CAT benchmark and measure cache misses
+ * @test:		Test information structure
  * @uparams:		User supplied parameters
  * @param:		Parameters passed to cat_test()
  * @span:		Buffer size for the benchmark
@@ -152,7 +153,9 @@ void cat_test_cleanup(void)
  *
  * Return:		0 when the test was run, < 0 on error.
  */
-static int cat_test(const struct user_params *uparams, struct resctrl_val_param *param,
+static int cat_test(const struct resctrl_test *test,
+		    const struct user_params *uparams,
+		    struct resctrl_val_param *param,
 		    size_t span, unsigned long current_mask)
 {
 	char *resctrl_val = param->resctrl_val;
@@ -196,11 +199,11 @@ static int cat_test(const struct user_params *uparams, struct resctrl_val_param
 
 	while (current_mask) {
 		snprintf(schemata, sizeof(schemata), "%lx", param->mask & ~current_mask);
-		ret = write_schemata("", schemata, uparams->cpu, param->resctrl_val);
+		ret = write_schemata("", schemata, uparams->cpu, test->resource);
 		if (ret)
 			goto free_buf;
 		snprintf(schemata, sizeof(schemata), "%lx", current_mask);
-		ret = write_schemata(param->ctrlgrp, schemata, uparams->cpu, param->resctrl_val);
+		ret = write_schemata(param->ctrlgrp, schemata, uparams->cpu, test->resource);
 		if (ret)
 			goto free_buf;
 
@@ -279,7 +282,7 @@ static int cat_run_test(const struct resctrl_test *test, const struct user_param
 
 	remove(param.filename);
 
-	ret = cat_test(uparams, &param, span, start_mask);
+	ret = cat_test(test, uparams, &param, span, start_mask);
 	if (ret)
 		goto out;
 
diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c
index c01980039118e..dd5ca343c4691 100644
--- a/tools/testing/selftests/resctrl/cmt_test.c
+++ b/tools/testing/selftests/resctrl/cmt_test.c
@@ -16,7 +16,9 @@
 #define MAX_DIFF		2000000
 #define MAX_DIFF_PERCENT	15
 
-static int cmt_setup(const struct user_params *uparams, struct resctrl_val_param *p)
+static int cmt_setup(const struct resctrl_test *test,
+		     const struct user_params *uparams,
+		     struct resctrl_val_param *p)
 {
 	/* Run NUM_OF_RUNS times */
 	if (p->num_of_runs >= NUM_OF_RUNS)
@@ -150,7 +152,7 @@ static int cmt_run_test(const struct resctrl_test *test, const struct user_param
 
 	remove(RESULT_FILE_NAME);
 
-	ret = resctrl_val(uparams, cmd, &param);
+	ret = resctrl_val(test, uparams, cmd, &param);
 	if (ret)
 		goto out;
 
diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c
index c218af24f91d9..da256d2dbe5ca 100644
--- a/tools/testing/selftests/resctrl/mba_test.c
+++ b/tools/testing/selftests/resctrl/mba_test.c
@@ -22,7 +22,9 @@
  * con_mon grp, mon_grp in resctrl FS.
  * For each allocation, run 5 times in order to get average values.
  */
-static int mba_setup(const struct user_params *uparams, struct resctrl_val_param *p)
+static int mba_setup(const struct resctrl_test *test,
+		     const struct user_params *uparams,
+		     struct resctrl_val_param *p)
 {
 	static int runs_per_allocation, allocation = 100;
 	char allocation_str[64];
@@ -40,8 +42,7 @@ static int mba_setup(const struct user_params *uparams, struct resctrl_val_param
 
 	sprintf(allocation_str, "%d", allocation);
 
-	ret = write_schemata(p->ctrlgrp, allocation_str, uparams->cpu,
-			     p->resctrl_val);
+	ret = write_schemata(p->ctrlgrp, allocation_str, uparams->cpu, test->resource);
 	if (ret < 0)
 		return ret;
 
@@ -155,7 +156,7 @@ static int mba_run_test(const struct resctrl_test *test, const struct user_param
 
 	remove(RESULT_FILE_NAME);
 
-	ret = resctrl_val(uparams, uparams->benchmark_cmd, &param);
+	ret = resctrl_val(test, uparams, uparams->benchmark_cmd, &param);
 	if (ret)
 		goto out;
 
diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c
index 919b10459c223..34879e7b71a08 100644
--- a/tools/testing/selftests/resctrl/mbm_test.c
+++ b/tools/testing/selftests/resctrl/mbm_test.c
@@ -86,7 +86,9 @@ static int check_results(size_t span)
 	return ret;
 }
 
-static int mbm_setup(const struct user_params *uparams, struct resctrl_val_param *p)
+static int mbm_setup(const struct resctrl_test *test,
+		     const struct user_params *uparams,
+		     struct resctrl_val_param *p)
 {
 	int ret = 0;
 
@@ -96,8 +98,7 @@ static int mbm_setup(const struct user_params *uparams, struct resctrl_val_param
 
 	/* Set up shemata with 100% allocation on the first run. */
 	if (p->num_of_runs == 0 && validate_resctrl_feature_request("MB", NULL))
-		ret = write_schemata(p->ctrlgrp, "100", uparams->cpu,
-				     p->resctrl_val);
+		ret = write_schemata(p->ctrlgrp, "100", uparams->cpu, test->resource);
 
 	p->num_of_runs++;
 
@@ -123,7 +124,7 @@ static int mbm_run_test(const struct resctrl_test *test, const struct user_param
 
 	remove(RESULT_FILE_NAME);
 
-	ret = resctrl_val(uparams, uparams->benchmark_cmd, &param);
+	ret = resctrl_val(test, uparams, uparams->benchmark_cmd, &param);
 	if (ret)
 		goto out;
 
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 1168364b4cc2f..97d16daf81907 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -98,7 +98,8 @@ struct resctrl_val_param {
 	char		*bw_report;
 	unsigned long	mask;
 	int		num_of_runs;
-	int		(*setup)(const struct user_params *uparams,
+	int		(*setup)(const struct resctrl_test *test,
+				 const struct user_params *uparams,
 				 struct resctrl_val_param *param);
 };
 
@@ -137,8 +138,7 @@ bool test_resource_feature_check(const struct resctrl_test *test);
 char *fgrep(FILE *inf, const char *str);
 int taskset_benchmark(pid_t bm_pid, int cpu_no, cpu_set_t *old_affinity);
 int taskset_restore(pid_t bm_pid, cpu_set_t *old_affinity);
-int write_schemata(char *ctrlgrp, char *schemata, int cpu_no,
-		   char *resctrl_val);
+int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, const char *resource);
 int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp,
 			    char *resctrl_val);
 int perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu,
@@ -147,7 +147,9 @@ unsigned char *alloc_buffer(size_t buf_size, int memflush);
 void mem_flush(unsigned char *buf, size_t buf_size);
 void fill_cache_read(unsigned char *buf, size_t buf_size, bool once);
 int run_fill_buf(size_t buf_size, int memflush, int op, bool once);
-int resctrl_val(const struct user_params *uparams, const char * const *benchmark_cmd,
+int resctrl_val(const struct resctrl_test *test,
+		const struct user_params *uparams,
+		const char * const *benchmark_cmd,
 		struct resctrl_val_param *param);
 void tests_cleanup(void);
 void mbm_test_cleanup(void);
diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index 68ad0b3e8dc58..1f21aee2f95a0 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -701,13 +701,16 @@ static void run_benchmark(int signum, siginfo_t *info, void *ucontext)
 /*
  * resctrl_val:	execute benchmark and measure memory bandwidth on
  *			the benchmark
+ * @test:		test information structure
  * @uparams:		user supplied parameters
  * @benchmark_cmd:	benchmark command and its arguments
  * @param:		parameters passed to resctrl_val()
  *
  * Return:		0 when the test was run, < 0 on error.
  */
-int resctrl_val(const struct user_params *uparams, const char * const *benchmark_cmd,
+int resctrl_val(const struct resctrl_test *test,
+		const struct user_params *uparams,
+		const char * const *benchmark_cmd,
 		struct resctrl_val_param *param)
 {
 	char *resctrl_val = param->resctrl_val;
@@ -843,7 +846,7 @@ int resctrl_val(const struct user_params *uparams, const char * const *benchmark
 
 	/* Test runs until the callback setup() tells the test to stop. */
 	while (1) {
-		ret = param->setup(uparams, param);
+		ret = param->setup(test, uparams, param);
 		if (ret == END_OF_TESTS) {
 			ret = 0;
 			break;
diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index a2cfa9e8b448d..636987e193a79 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -529,23 +529,17 @@ int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp,
  * @ctrlgrp:		Name of the con_mon grp
  * @schemata:		Schemata that should be updated to
  * @cpu_no:		CPU number that the benchmark PID is binded to
- * @resctrl_val:	Resctrl feature (Eg: mbm, mba.. etc)
+ * @resource:		Resctrl resource (Eg: MB, L3, L2, etc.)
  *
- * Update schemata of a con_mon grp *only* if requested resctrl feature is
+ * Update schemata of a con_mon grp *only* if requested resctrl resource is
  * allocation type
  *
  * Return: 0 on success, < 0 on error.
  */
-int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, char *resctrl_val)
+int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, const char *resource)
 {
 	char controlgroup[1024], reason[128], schema[1024] = {};
-	int resource_id, fd, schema_len = -1, ret = 0;
-
-	if (strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR)) &&
-	    strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)) &&
-	    strncmp(resctrl_val, CAT_STR, sizeof(CAT_STR)) &&
-	    strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR)))
-		return -ENOENT;
+	int resource_id, fd, schema_len, ret = 0;
 
 	if (!schemata) {
 		ksft_print_msg("Skipping empty schemata update\n");
@@ -565,14 +559,8 @@ int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, char *resctrl_val)
 	else
 		sprintf(controlgroup, "%s/schemata", RESCTRL_PATH);
 
-	if (!strncmp(resctrl_val, CAT_STR, sizeof(CAT_STR)) ||
-	    !strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR)))
-		schema_len = snprintf(schema, sizeof(schema), "%s%d%c%s\n",
-				      "L3:", resource_id, '=', schemata);
-	if (!strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR)) ||
-	    !strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)))
-		schema_len = snprintf(schema, sizeof(schema), "%s%d%c%s\n",
-				      "MB:", resource_id, '=', schemata);
+	schema_len = snprintf(schema, sizeof(schema), "%s:%d=%s\n",
+			      resource, resource_id, schemata);
 	if (schema_len < 0 || schema_len >= sizeof(schema)) {
 		snprintf(reason, sizeof(reason),
 			 "snprintf() failed with return value : %d", schema_len);

From b2b41d90cd6f3053a5dfe23e8f1499cba1059ced Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 15 Dec 2023 17:05:13 +0200
Subject: [PATCH 177/236] selftests/resctrl: Add helper to convert L2/3 to
 integer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit e73dda7ffd858a58ddeb9c53603ae14f2af8927c upstream.

"L2"/"L3" conversion to integer is embedded into get_cache_size()
which prevents reuse.

Create a helper for the cache string to integer conversion to make
it reusable.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/resctrlfs.c | 28 +++++++++++++++------
 1 file changed, 20 insertions(+), 8 deletions(-)

diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index 636987e193a79..1e297a2e8b7ce 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -94,6 +94,23 @@ int umount_resctrlfs(void)
 	return 0;
 }
 
+/*
+ * get_cache_level - Convert cache level from string to integer
+ * @cache_type:		Cache level as string
+ *
+ * Return: cache level as integer or -1 if @cache_type is invalid.
+ */
+static int get_cache_level(const char *cache_type)
+{
+	if (!strcmp(cache_type, "L3"))
+		return 3;
+	if (!strcmp(cache_type, "L2"))
+		return 2;
+
+	ksft_print_msg("Invalid cache level\n");
+	return -1;
+}
+
 /*
  * get_resource_id - Get socket number/l3 id for a specified CPU
  * @cpu_no:	CPU number
@@ -144,14 +161,9 @@ int get_cache_size(int cpu_no, const char *cache_type, unsigned long *cache_size
 	int length, i, cache_num;
 	FILE *fp;
 
-	if (!strcmp(cache_type, "L3")) {
-		cache_num = 3;
-	} else if (!strcmp(cache_type, "L2")) {
-		cache_num = 2;
-	} else {
-		ksft_print_msg("Invalid cache level\n");
-		return -1;
-	}
+	cache_num = get_cache_level(cache_type);
+	if (cache_num < 0)
+		return cache_num;
 
 	sprintf(cache_path, "/sys/bus/cpu/devices/cpu%d/cache/index%d/size",
 		cpu_no, cache_num);

From f555904550a2f1bd60eea9d3ba2137019e838bb2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 15 Dec 2023 17:05:14 +0200
Subject: [PATCH 178/236] selftests/resctrl: Rename resource ID to domain ID
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 6874f6ed92df1e95ff815692b6bf6aa98e4c925b upstream.

Kernel-side calls the instances of a resource domains.

Change the resource_id naming in the selftest code to domain_id to
match the kernel side better.

Suggested-by: Maciej Wieczór-Retman <maciej.wieczor-retman@intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/resctrl.h     |  2 +-
 tools/testing/selftests/resctrl/resctrl_val.c | 30 +++++++++----------
 tools/testing/selftests/resctrl/resctrlfs.c   | 18 +++++------
 3 files changed, 25 insertions(+), 25 deletions(-)

diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 97d16daf81907..d4eef20723fcd 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -129,7 +129,7 @@ extern char llc_occup_path[1024];
 int get_vendor(void);
 bool check_resctrlfs_support(void);
 int filter_dmesg(void);
-int get_resource_id(int cpu_no, int *resource_id);
+int get_domain_id(int cpu_no, int *domain_id);
 int mount_resctrlfs(void);
 int umount_resctrlfs(void);
 int validate_bw_report_request(char *bw_report);
diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index 1f21aee2f95a0..0f90b72f7d608 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -404,20 +404,20 @@ static int get_mem_bw_imc(int cpu_no, char *bw_report, float *bw_imc)
 	return -1;
 }
 
-void set_mbm_path(const char *ctrlgrp, const char *mongrp, int resource_id)
+void set_mbm_path(const char *ctrlgrp, const char *mongrp, int domain_id)
 {
 	if (ctrlgrp && mongrp)
 		sprintf(mbm_total_path, CON_MON_MBM_LOCAL_BYTES_PATH,
-			RESCTRL_PATH, ctrlgrp, mongrp, resource_id);
+			RESCTRL_PATH, ctrlgrp, mongrp, domain_id);
 	else if (!ctrlgrp && mongrp)
 		sprintf(mbm_total_path, MON_MBM_LOCAL_BYTES_PATH, RESCTRL_PATH,
-			mongrp, resource_id);
+			mongrp, domain_id);
 	else if (ctrlgrp && !mongrp)
 		sprintf(mbm_total_path, CON_MBM_LOCAL_BYTES_PATH, RESCTRL_PATH,
-			ctrlgrp, resource_id);
+			ctrlgrp, domain_id);
 	else if (!ctrlgrp && !mongrp)
 		sprintf(mbm_total_path, MBM_LOCAL_BYTES_PATH, RESCTRL_PATH,
-			resource_id);
+			domain_id);
 }
 
 /*
@@ -430,23 +430,23 @@ void set_mbm_path(const char *ctrlgrp, const char *mongrp, int resource_id)
 static void initialize_mem_bw_resctrl(const char *ctrlgrp, const char *mongrp,
 				      int cpu_no, char *resctrl_val)
 {
-	int resource_id;
+	int domain_id;
 
-	if (get_resource_id(cpu_no, &resource_id) < 0) {
-		ksft_print_msg("Could not get resource_id\n");
+	if (get_domain_id(cpu_no, &domain_id) < 0) {
+		ksft_print_msg("Could not get domain ID\n");
 		return;
 	}
 
 	if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)))
-		set_mbm_path(ctrlgrp, mongrp, resource_id);
+		set_mbm_path(ctrlgrp, mongrp, domain_id);
 
 	if (!strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR))) {
 		if (ctrlgrp)
 			sprintf(mbm_total_path, CON_MBM_LOCAL_BYTES_PATH,
-				RESCTRL_PATH, ctrlgrp, resource_id);
+				RESCTRL_PATH, ctrlgrp, domain_id);
 		else
 			sprintf(mbm_total_path, MBM_LOCAL_BYTES_PATH,
-				RESCTRL_PATH, resource_id);
+				RESCTRL_PATH, domain_id);
 	}
 }
 
@@ -599,15 +599,15 @@ static void set_cmt_path(const char *ctrlgrp, const char *mongrp, char sock_num)
 static void initialize_llc_occu_resctrl(const char *ctrlgrp, const char *mongrp,
 					int cpu_no, char *resctrl_val)
 {
-	int resource_id;
+	int domain_id;
 
-	if (get_resource_id(cpu_no, &resource_id) < 0) {
-		ksft_print_msg("Could not get resource_id\n");
+	if (get_domain_id(cpu_no, &domain_id) < 0) {
+		ksft_print_msg("Could not get domain ID\n");
 		return;
 	}
 
 	if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR)))
-		set_cmt_path(ctrlgrp, mongrp, resource_id);
+		set_cmt_path(ctrlgrp, mongrp, domain_id);
 }
 
 static int measure_vals(const struct user_params *uparams,
diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index 1e297a2e8b7ce..176ea27861a6f 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -112,13 +112,13 @@ static int get_cache_level(const char *cache_type)
 }
 
 /*
- * get_resource_id - Get socket number/l3 id for a specified CPU
+ * get_domain_id - Get resctrl domain ID for a specified CPU
  * @cpu_no:	CPU number
- * @resource_id: Socket number or l3_id
+ * @domain_id:	domain ID (cache ID; for MB, L3 cache ID)
  *
  * Return: >= 0 on success, < 0 on failure.
  */
-int get_resource_id(int cpu_no, int *resource_id)
+int get_domain_id(int cpu_no, int *domain_id)
 {
 	char phys_pkg_path[1024];
 	FILE *fp;
@@ -136,8 +136,8 @@ int get_resource_id(int cpu_no, int *resource_id)
 
 		return -1;
 	}
-	if (fscanf(fp, "%d", resource_id) <= 0) {
-		ksft_perror("Could not get socket number or l3 id");
+	if (fscanf(fp, "%d", domain_id) <= 0) {
+		ksft_perror("Could not get domain ID");
 		fclose(fp);
 
 		return -1;
@@ -551,7 +551,7 @@ int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp,
 int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, const char *resource)
 {
 	char controlgroup[1024], reason[128], schema[1024] = {};
-	int resource_id, fd, schema_len, ret = 0;
+	int domain_id, fd, schema_len, ret = 0;
 
 	if (!schemata) {
 		ksft_print_msg("Skipping empty schemata update\n");
@@ -559,8 +559,8 @@ int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, const char *resour
 		return -1;
 	}
 
-	if (get_resource_id(cpu_no, &resource_id) < 0) {
-		sprintf(reason, "Failed to get resource id");
+	if (get_domain_id(cpu_no, &domain_id) < 0) {
+		sprintf(reason, "Failed to get domain ID");
 		ret = -1;
 
 		goto out;
@@ -572,7 +572,7 @@ int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, const char *resour
 		sprintf(controlgroup, "%s/schemata", RESCTRL_PATH);
 
 	schema_len = snprintf(schema, sizeof(schema), "%s:%d=%s\n",
-			      resource, resource_id, schemata);
+			      resource, domain_id, schemata);
 	if (schema_len < 0 || schema_len >= sizeof(schema)) {
 		snprintf(reason, sizeof(reason),
 			 "snprintf() failed with return value : %d", schema_len);

From 20f9a5ee41f54c8861480c131a1ba368c56475db Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 15 Dec 2023 17:05:15 +0200
Subject: [PATCH 179/236] selftests/resctrl: Get domain id from cache id
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 345e8abe4c355bc24bab3f4a5634122e55be8665 upstream.

Domain id is acquired differently depending on CPU. AMD tests use id
from L3 cache, whereas CPUs from other vendors base the id on topology
package id. In order to support L2 CAT test, this has to be
generalized.

The driver side code seems to get the domain ids from cache ids so the
approach used by the AMD branch seems to match the kernel-side code. It
will also work with L2 domain IDs as long as the cache level is
generalized.

Using the topology id was always fragile due to mismatch with the
kernel-side way to acquire the domain id. It got incorrect domain id,
e.g., when Cluster-on-Die (CoD) is enabled for CPU (but CoD is not well
suited for resctrl in the first place so it has not been a big issue if
tests don't work correctly with it).

Taking all the above into account, generalize acquiring the domain id
by taking it from the cache id and do not hard-code the cache level.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/resctrl.h     |  2 +-
 tools/testing/selftests/resctrl/resctrl_val.c |  4 +--
 tools/testing/selftests/resctrl/resctrlfs.c   | 27 ++++++++++++-------
 3 files changed, 21 insertions(+), 12 deletions(-)

diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index d4eef20723fcd..c52eaf46f24de 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -129,7 +129,7 @@ extern char llc_occup_path[1024];
 int get_vendor(void);
 bool check_resctrlfs_support(void);
 int filter_dmesg(void);
-int get_domain_id(int cpu_no, int *domain_id);
+int get_domain_id(const char *resource, int cpu_no, int *domain_id);
 int mount_resctrlfs(void);
 int umount_resctrlfs(void);
 int validate_bw_report_request(char *bw_report);
diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index 0f90b72f7d608..c1257b78e09e5 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -432,7 +432,7 @@ static void initialize_mem_bw_resctrl(const char *ctrlgrp, const char *mongrp,
 {
 	int domain_id;
 
-	if (get_domain_id(cpu_no, &domain_id) < 0) {
+	if (get_domain_id("MB", cpu_no, &domain_id) < 0) {
 		ksft_print_msg("Could not get domain ID\n");
 		return;
 	}
@@ -601,7 +601,7 @@ static void initialize_llc_occu_resctrl(const char *ctrlgrp, const char *mongrp,
 {
 	int domain_id;
 
-	if (get_domain_id(cpu_no, &domain_id) < 0) {
+	if (get_domain_id("L3", cpu_no, &domain_id) < 0) {
 		ksft_print_msg("Could not get domain ID\n");
 		return;
 	}
diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index 176ea27861a6f..c12ab81a13377 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -111,28 +111,37 @@ static int get_cache_level(const char *cache_type)
 	return -1;
 }
 
+static int get_resource_cache_level(const char *resource)
+{
+	/* "MB" use L3 (LLC) as resource */
+	if (!strcmp(resource, "MB"))
+		return 3;
+	return get_cache_level(resource);
+}
+
 /*
  * get_domain_id - Get resctrl domain ID for a specified CPU
+ * @resource:	resource name
  * @cpu_no:	CPU number
  * @domain_id:	domain ID (cache ID; for MB, L3 cache ID)
  *
  * Return: >= 0 on success, < 0 on failure.
  */
-int get_domain_id(int cpu_no, int *domain_id)
+int get_domain_id(const char *resource, int cpu_no, int *domain_id)
 {
 	char phys_pkg_path[1024];
+	int cache_num;
 	FILE *fp;
 
-	if (get_vendor() == ARCH_AMD)
-		sprintf(phys_pkg_path, "%s%d/cache/index3/id",
-			PHYS_ID_PATH, cpu_no);
-	else
-		sprintf(phys_pkg_path, "%s%d/topology/physical_package_id",
-			PHYS_ID_PATH, cpu_no);
+	cache_num = get_resource_cache_level(resource);
+	if (cache_num < 0)
+		return cache_num;
+
+	sprintf(phys_pkg_path, "%s%d/cache/index%d/id", PHYS_ID_PATH, cpu_no, cache_num);
 
 	fp = fopen(phys_pkg_path, "r");
 	if (!fp) {
-		ksft_perror("Failed to open physical_package_id");
+		ksft_perror("Failed to open cache id file");
 
 		return -1;
 	}
@@ -559,7 +568,7 @@ int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, const char *resour
 		return -1;
 	}
 
-	if (get_domain_id(cpu_no, &domain_id) < 0) {
+	if (get_domain_id(resource, cpu_no, &domain_id) < 0) {
 		sprintf(reason, "Failed to get domain ID");
 		ret = -1;
 

From cef47ae01921b992d8e3f3f3951b622224b536b9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Fri, 16 Feb 2024 09:34:56 +0100
Subject: [PATCH 180/236] selftests/resctrl: Add test groups and name L3 CAT
 test L3_CAT
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 5339792bd64bd1605d3d51f8e52e94dfc385959b upstream.

To select test to run -t parameter can be used. However, -t cat
currently maps to L3 CAT test which will be confusing after more CAT
related tests will be added.

Allow selecting tests as groups and call L3 CAT test "L3_CAT", "CAT"
group will enable all CAT related tests.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cat_test.c      |  3 ++-
 tools/testing/selftests/resctrl/resctrl.h       |  3 +++
 tools/testing/selftests/resctrl/resctrl_tests.c | 16 +++++++++++-----
 3 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
index 24af8310288aa..39fc9303b8e8a 100644
--- a/tools/testing/selftests/resctrl/cat_test.c
+++ b/tools/testing/selftests/resctrl/cat_test.c
@@ -295,7 +295,8 @@ static int cat_run_test(const struct resctrl_test *test, const struct user_param
 }
 
 struct resctrl_test l3_cat_test = {
-	.name = "CAT",
+	.name = "L3_CAT",
+	.group = "CAT",
 	.resource = "L3",
 	.feature_check = test_resource_feature_check,
 	.run_test = cat_run_test,
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index c52eaf46f24de..a1462029998e5 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -65,6 +65,8 @@ struct user_params {
 /*
  * resctrl_test:	resctrl test definition
  * @name:		Test name
+ * @group:		Test group - a common name for tests that share some characteristic
+ *			(e.g., L3 CAT test belongs to the CAT group). Can be NULL
  * @resource:		Resource to test (e.g., MB, L3, L2, etc.)
  * @vendor_specific:	Bitmask for vendor-specific tests (can be 0 for universal tests)
  * @disabled:		Test is disabled
@@ -73,6 +75,7 @@ struct user_params {
  */
 struct resctrl_test {
 	const char	*name;
+	const char	*group;
 	const char	*resource;
 	unsigned int	vendor_specific;
 	bool		disabled;
diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c
index 75fc49ba3efb0..3044179ee6e99 100644
--- a/tools/testing/selftests/resctrl/resctrl_tests.c
+++ b/tools/testing/selftests/resctrl/resctrl_tests.c
@@ -65,11 +65,15 @@ static void cmd_help(void)
 	printf("usage: resctrl_tests [-h] [-t test list] [-n no_of_bits] [-b benchmark_cmd [option]...]\n");
 	printf("\t-b benchmark_cmd [option]...: run specified benchmark for MBM, MBA and CMT\n");
 	printf("\t   default benchmark is builtin fill_buf\n");
-	printf("\t-t test list: run tests specified in the test list, ");
+	printf("\t-t test list: run tests/groups specified by the list, ");
 	printf("e.g. -t mbm,mba,cmt,cat\n");
-	printf("\t\tSupported tests:\n");
-	for (i = 0; i < ARRAY_SIZE(resctrl_tests); i++)
-		printf("\t\t\t%s\n", resctrl_tests[i]->name);
+	printf("\t\tSupported tests (group):\n");
+	for (i = 0; i < ARRAY_SIZE(resctrl_tests); i++) {
+		if (resctrl_tests[i]->group)
+			printf("\t\t\t%s (%s)\n", resctrl_tests[i]->name, resctrl_tests[i]->group);
+		else
+			printf("\t\t\t%s\n", resctrl_tests[i]->name);
+	}
 	printf("\t-n no_of_bits: run cache tests using specified no of bits in cache bit mask\n");
 	printf("\t-p cpu_no: specify CPU number to run the test. 1 is default\n");
 	printf("\t-h: help\n");
@@ -199,7 +203,9 @@ int main(int argc, char **argv)
 				bool found = false;
 
 				for (i = 0; i < ARRAY_SIZE(resctrl_tests); i++) {
-					if (!strcasecmp(token, resctrl_tests[i]->name)) {
+					if (!strcasecmp(token, resctrl_tests[i]->name) ||
+					    (resctrl_tests[i]->group &&
+					     !strcasecmp(token, resctrl_tests[i]->group))) {
 						if (resctrl_tests[i]->disabled)
 							tests++;
 						resctrl_tests[i]->disabled = false;

From 1978c6118d2082fb9b0fdd23f027d6badde41bb7 Mon Sep 17 00:00:00 2001
From: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Date: Fri, 16 Feb 2024 09:35:15 +0100
Subject: [PATCH 181/236] selftests/resctrl: Add a helper for the
 non-contiguous test
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit e331ac141f1df6d151d24e60ff16e93ec075509e upstream.

The CAT non-contiguous selftests have to read the file responsible for
reporting support of non-contiguous CBMs in kernel (resctrl). Then the
test compares if that information matches what is reported by CPUID
output.

Add a generic helper function to read an unsigned number from
/sys/fs/resctrl/info/<RESOURCE>/<FILE>.

Signed-off-by: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/resctrl.h   |  1 +
 tools/testing/selftests/resctrl/resctrlfs.c | 36 +++++++++++++++++++++
 2 files changed, 37 insertions(+)

diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index a1462029998e5..5116ea082d031 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -162,6 +162,7 @@ unsigned int count_contiguous_bits(unsigned long val, unsigned int *start);
 int get_full_cbm(const char *cache_type, unsigned long *mask);
 int get_mask_no_shareable(const char *cache_type, unsigned long *mask);
 int get_cache_size(int cpu_no, const char *cache_type, unsigned long *cache_size);
+int resource_info_unsigned_get(const char *resource, const char *filename, unsigned int *val);
 void ctrlc_handler(int signum, siginfo_t *info, void *ptr);
 int signal_handler_register(void);
 void signal_handler_unregister(void);
diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index c12ab81a13377..5b02f4b7b66f3 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -249,6 +249,42 @@ static int get_bit_mask(const char *filename, unsigned long *mask)
 	return 0;
 }
 
+/*
+ * resource_info_unsigned_get - Read an unsigned value from
+ * /sys/fs/resctrl/info/@resource/@filename
+ * @resource:	Resource name that matches directory name in
+ *		/sys/fs/resctrl/info
+ * @filename:	File in /sys/fs/resctrl/info/@resource
+ * @val:	Contains read value on success.
+ *
+ * Return: = 0 on success, < 0 on failure. On success the read
+ * value is saved into @val.
+ */
+int resource_info_unsigned_get(const char *resource, const char *filename,
+			       unsigned int *val)
+{
+	char file_path[PATH_MAX];
+	FILE *fp;
+
+	snprintf(file_path, sizeof(file_path), "%s/%s/%s", INFO_PATH, resource,
+		 filename);
+
+	fp = fopen(file_path, "r");
+	if (!fp) {
+		ksft_print_msg("Error opening %s: %m\n", file_path);
+		return -1;
+	}
+
+	if (fscanf(fp, "%u", val) <= 0) {
+		ksft_print_msg("Could not get contents of %s: %m\n", file_path);
+		fclose(fp);
+		return -1;
+	}
+
+	fclose(fp);
+	return 0;
+}
+
 /*
  * create_bit_mask- Create bit mask from start, len pair
  * @start:	LSB of the mask

From 693dafe3f91a1e40da9645b34cb1efd04e233f4e Mon Sep 17 00:00:00 2001
From: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Date: Fri, 16 Feb 2024 09:35:28 +0100
Subject: [PATCH 182/236] selftests/resctrl: Split
 validate_resctrl_feature_request()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 00616416488868a8b98343863e5ac078506e44e8 upstream.

validate_resctrl_feature_request() is used to test both if a resource is
present in the info directory, and if a passed monitoring feature is
present in the mon_features file.

Refactor validate_resctrl_feature_request() into two smaller functions
that each accomplish one check to give feature checking more
granularity:
- Resource directory presence in the /sys/fs/resctrl/info directory.
- Feature name presence in the /sys/fs/resctrl/info/<RESOURCE>/mon_features
  file.

Signed-off-by: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cmt_test.c  |  2 +-
 tools/testing/selftests/resctrl/mba_test.c  |  2 +-
 tools/testing/selftests/resctrl/mbm_test.c  |  6 ++--
 tools/testing/selftests/resctrl/resctrl.h   |  3 +-
 tools/testing/selftests/resctrl/resctrlfs.c | 35 ++++++++++++++-------
 5 files changed, 31 insertions(+), 17 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c
index dd5ca343c4691..a81f91222a89a 100644
--- a/tools/testing/selftests/resctrl/cmt_test.c
+++ b/tools/testing/selftests/resctrl/cmt_test.c
@@ -170,7 +170,7 @@ static int cmt_run_test(const struct resctrl_test *test, const struct user_param
 static bool cmt_feature_check(const struct resctrl_test *test)
 {
 	return test_resource_feature_check(test) &&
-	       validate_resctrl_feature_request("L3_MON", "llc_occupancy");
+	       resctrl_mon_feature_exists("L3_MON", "llc_occupancy");
 }
 
 struct resctrl_test cmt_test = {
diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c
index da256d2dbe5ca..7946e32e85c83 100644
--- a/tools/testing/selftests/resctrl/mba_test.c
+++ b/tools/testing/selftests/resctrl/mba_test.c
@@ -171,7 +171,7 @@ static int mba_run_test(const struct resctrl_test *test, const struct user_param
 static bool mba_feature_check(const struct resctrl_test *test)
 {
 	return test_resource_feature_check(test) &&
-	       validate_resctrl_feature_request("L3_MON", "mbm_local_bytes");
+	       resctrl_mon_feature_exists("L3_MON", "mbm_local_bytes");
 }
 
 struct resctrl_test mba_test = {
diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c
index 34879e7b71a08..d67ffa3ec63a3 100644
--- a/tools/testing/selftests/resctrl/mbm_test.c
+++ b/tools/testing/selftests/resctrl/mbm_test.c
@@ -97,7 +97,7 @@ static int mbm_setup(const struct resctrl_test *test,
 		return END_OF_TESTS;
 
 	/* Set up shemata with 100% allocation on the first run. */
-	if (p->num_of_runs == 0 && validate_resctrl_feature_request("MB", NULL))
+	if (p->num_of_runs == 0 && resctrl_resource_exists("MB"))
 		ret = write_schemata(p->ctrlgrp, "100", uparams->cpu, test->resource);
 
 	p->num_of_runs++;
@@ -140,8 +140,8 @@ static int mbm_run_test(const struct resctrl_test *test, const struct user_param
 
 static bool mbm_feature_check(const struct resctrl_test *test)
 {
-	return validate_resctrl_feature_request("L3_MON", "mbm_total_bytes") &&
-	       validate_resctrl_feature_request("L3_MON", "mbm_local_bytes");
+	return resctrl_mon_feature_exists("L3_MON", "mbm_total_bytes") &&
+	       resctrl_mon_feature_exists("L3_MON", "mbm_local_bytes");
 }
 
 struct resctrl_test mbm_test = {
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 5116ea082d031..6d99ed44ec60b 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -136,7 +136,8 @@ int get_domain_id(const char *resource, int cpu_no, int *domain_id);
 int mount_resctrlfs(void);
 int umount_resctrlfs(void);
 int validate_bw_report_request(char *bw_report);
-bool validate_resctrl_feature_request(const char *resource, const char *feature);
+bool resctrl_resource_exists(const char *resource);
+bool resctrl_mon_feature_exists(const char *resource, const char *feature);
 bool test_resource_feature_check(const struct resctrl_test *test);
 char *fgrep(FILE *inf, const char *str);
 int taskset_benchmark(pid_t bm_pid, int cpu_no, cpu_set_t *old_affinity);
diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index 5b02f4b7b66f3..93a41a262fcae 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -708,20 +708,16 @@ char *fgrep(FILE *inf, const char *str)
 }
 
 /*
- * validate_resctrl_feature_request - Check if requested feature is valid.
- * @resource:	Required resource (e.g., MB, L3, L2, L3_MON, etc.)
- * @feature:	Required monitor feature (in mon_features file). Can only be
- *		set for L3_MON. Must be NULL for all other resources.
+ * resctrl_resource_exists - Check if a resource is supported.
+ * @resource:	Resctrl resource (e.g., MB, L3, L2, L3_MON, etc.)
  *
- * Return: True if the resource/feature is supported, else false. False is
+ * Return: True if the resource is supported, else false. False is
  *         also returned if resctrl FS is not mounted.
  */
-bool validate_resctrl_feature_request(const char *resource, const char *feature)
+bool resctrl_resource_exists(const char *resource)
 {
 	char res_path[PATH_MAX];
 	struct stat statbuf;
-	char *res;
-	FILE *inf;
 	int ret;
 
 	if (!resource)
@@ -736,8 +732,25 @@ bool validate_resctrl_feature_request(const char *resource, const char *feature)
 	if (stat(res_path, &statbuf))
 		return false;
 
-	if (!feature)
-		return true;
+	return true;
+}
+
+/*
+ * resctrl_mon_feature_exists - Check if requested monitoring feature is valid.
+ * @resource:	Resource that uses the mon_features file. Currently only L3_MON
+ *		is valid.
+ * @feature:	Required monitor feature (in mon_features file).
+ *
+ * Return: True if the feature is supported, else false.
+ */
+bool resctrl_mon_feature_exists(const char *resource, const char *feature)
+{
+	char res_path[PATH_MAX];
+	char *res;
+	FILE *inf;
+
+	if (!feature || !resource)
+		return false;
 
 	snprintf(res_path, sizeof(res_path), "%s/%s/mon_features", INFO_PATH, resource);
 	inf = fopen(res_path, "r");
@@ -753,7 +766,7 @@ bool validate_resctrl_feature_request(const char *resource, const char *feature)
 
 bool test_resource_feature_check(const struct resctrl_test *test)
 {
-	return validate_resctrl_feature_request(test->resource, NULL);
+	return resctrl_resource_exists(test->resource);
 }
 
 int filter_dmesg(void)

From 3a992bf60eadbdbc9b1caa36a812cdb8a22022c7 Mon Sep 17 00:00:00 2001
From: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Date: Fri, 16 Feb 2024 09:35:41 +0100
Subject: [PATCH 183/236] selftests/resctrl: Add resource_info_file_exists()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 74e76cbabd7f71f46afdf125dd4f6a54447d87e0 upstream.

Feature checking done by resctrl_mon_feature_exists() covers features
represented by the feature name presence inside the 'mon_features' file
in /sys/fs/resctrl/info/L3_MON directory. There exists a different way
to represent feature support and that is by the presence of 0 or 1 in a
single file in the info/resource directory. In this case the filename
represents what feature support is being indicated.

Add a generic function to check file presence in the
/sys/fs/resctrl/info/<RESOURCE> directory.

Signed-off-by: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/resctrl.h   |  1 +
 tools/testing/selftests/resctrl/resctrlfs.c | 25 +++++++++++++++++++++
 2 files changed, 26 insertions(+)

diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 6d99ed44ec60b..f434a6543b4f7 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -138,6 +138,7 @@ int umount_resctrlfs(void);
 int validate_bw_report_request(char *bw_report);
 bool resctrl_resource_exists(const char *resource);
 bool resctrl_mon_feature_exists(const char *resource, const char *feature);
+bool resource_info_file_exists(const char *resource, const char *file);
 bool test_resource_feature_check(const struct resctrl_test *test);
 char *fgrep(FILE *inf, const char *str);
 int taskset_benchmark(pid_t bm_pid, int cpu_no, cpu_set_t *old_affinity);
diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index 93a41a262fcae..f08344fee9ef7 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -764,6 +764,31 @@ bool resctrl_mon_feature_exists(const char *resource, const char *feature)
 	return !!res;
 }
 
+/*
+ * resource_info_file_exists - Check if a file is present inside
+ * /sys/fs/resctrl/info/@resource.
+ * @resource:	Required resource (Eg: MB, L3, L2, etc.)
+ * @file:	Required file.
+ *
+ * Return: True if the /sys/fs/resctrl/info/@resource/@file exists, else false.
+ */
+bool resource_info_file_exists(const char *resource, const char *file)
+{
+	char res_path[PATH_MAX];
+	struct stat statbuf;
+
+	if (!file || !resource)
+		return false;
+
+	snprintf(res_path, sizeof(res_path), "%s/%s/%s", INFO_PATH, resource,
+		 file);
+
+	if (stat(res_path, &statbuf))
+		return false;
+
+	return true;
+}
+
 bool test_resource_feature_check(const struct resctrl_test *test)
 {
 	return resctrl_resource_exists(test->resource);

From 45f7e0c3de642bea1a1bba0b4dfbe7fd40ff0f8f Mon Sep 17 00:00:00 2001
From: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Date: Fri, 16 Feb 2024 09:35:52 +0100
Subject: [PATCH 184/236] selftests/resctrl: Add non-contiguous CBMs CAT test
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit ae638551ab64a216364a63c4ee5061f82702fde2 upstream.

Add tests for both L2 and L3 CAT to verify the return values
generated by writing non-contiguous CBMs don't contradict the
reported non-contiguous support information.

Use a logical XOR to confirm return value of write_schemata() and
non-contiguous CBMs support information match.

Signed-off-by: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cat_test.c    | 89 +++++++++++++++++++
 tools/testing/selftests/resctrl/resctrl.h     |  2 +
 .../testing/selftests/resctrl/resctrl_tests.c |  2 +
 3 files changed, 93 insertions(+)

diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
index 39fc9303b8e8a..4cb991be8e31b 100644
--- a/tools/testing/selftests/resctrl/cat_test.c
+++ b/tools/testing/selftests/resctrl/cat_test.c
@@ -294,6 +294,79 @@ static int cat_run_test(const struct resctrl_test *test, const struct user_param
 	return ret;
 }
 
+static int noncont_cat_run_test(const struct resctrl_test *test,
+				const struct user_params *uparams)
+{
+	unsigned long full_cache_mask, cont_mask, noncont_mask;
+	unsigned int eax, ebx, ecx, edx, sparse_masks;
+	int bit_center, ret;
+	char schemata[64];
+
+	/* Check to compare sparse_masks content to CPUID output. */
+	ret = resource_info_unsigned_get(test->resource, "sparse_masks", &sparse_masks);
+	if (ret)
+		return ret;
+
+	if (!strcmp(test->resource, "L3"))
+		__cpuid_count(0x10, 1, eax, ebx, ecx, edx);
+	else if (!strcmp(test->resource, "L2"))
+		__cpuid_count(0x10, 2, eax, ebx, ecx, edx);
+	else
+		return -EINVAL;
+
+	if (sparse_masks != ((ecx >> 3) & 1)) {
+		ksft_print_msg("CPUID output doesn't match 'sparse_masks' file content!\n");
+		return 1;
+	}
+
+	/* Write checks initialization. */
+	ret = get_full_cbm(test->resource, &full_cache_mask);
+	if (ret < 0)
+		return ret;
+	bit_center = count_bits(full_cache_mask) / 2;
+
+	/*
+	 * The bit_center needs to be at least 3 to properly calculate the CBM
+	 * hole in the noncont_mask. If it's smaller return an error since the
+	 * cache mask is too short and that shouldn't happen.
+	 */
+	if (bit_center < 3)
+		return -EINVAL;
+	cont_mask = full_cache_mask >> bit_center;
+
+	/* Contiguous mask write check. */
+	snprintf(schemata, sizeof(schemata), "%lx", cont_mask);
+	ret = write_schemata("", schemata, uparams->cpu, test->resource);
+	if (ret) {
+		ksft_print_msg("Write of contiguous CBM failed\n");
+		return 1;
+	}
+
+	/*
+	 * Non-contiguous mask write check. CBM has a 0xf hole approximately in the middle.
+	 * Output is compared with support information to catch any edge case errors.
+	 */
+	noncont_mask = ~(0xfUL << (bit_center - 2)) & full_cache_mask;
+	snprintf(schemata, sizeof(schemata), "%lx", noncont_mask);
+	ret = write_schemata("", schemata, uparams->cpu, test->resource);
+	if (ret && sparse_masks)
+		ksft_print_msg("Non-contiguous CBMs supported but write of non-contiguous CBM failed\n");
+	else if (ret && !sparse_masks)
+		ksft_print_msg("Non-contiguous CBMs not supported and write of non-contiguous CBM failed as expected\n");
+	else if (!ret && !sparse_masks)
+		ksft_print_msg("Non-contiguous CBMs not supported but write of non-contiguous CBM succeeded\n");
+
+	return !ret == !sparse_masks;
+}
+
+static bool noncont_cat_feature_check(const struct resctrl_test *test)
+{
+	if (!resctrl_resource_exists(test->resource))
+		return false;
+
+	return resource_info_file_exists(test->resource, "sparse_masks");
+}
+
 struct resctrl_test l3_cat_test = {
 	.name = "L3_CAT",
 	.group = "CAT",
@@ -301,3 +374,19 @@ struct resctrl_test l3_cat_test = {
 	.feature_check = test_resource_feature_check,
 	.run_test = cat_run_test,
 };
+
+struct resctrl_test l3_noncont_cat_test = {
+	.name = "L3_NONCONT_CAT",
+	.group = "CAT",
+	.resource = "L3",
+	.feature_check = noncont_cat_feature_check,
+	.run_test = noncont_cat_run_test,
+};
+
+struct resctrl_test l2_noncont_cat_test = {
+	.name = "L2_NONCONT_CAT",
+	.group = "CAT",
+	.resource = "L2",
+	.feature_check = noncont_cat_feature_check,
+	.run_test = noncont_cat_run_test,
+};
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index f434a6543b4f7..2051bd135e0d0 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -209,5 +209,7 @@ extern struct resctrl_test mbm_test;
 extern struct resctrl_test mba_test;
 extern struct resctrl_test cmt_test;
 extern struct resctrl_test l3_cat_test;
+extern struct resctrl_test l3_noncont_cat_test;
+extern struct resctrl_test l2_noncont_cat_test;
 
 #endif /* RESCTRL_H */
diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c
index 3044179ee6e99..f3dc1b9696e71 100644
--- a/tools/testing/selftests/resctrl/resctrl_tests.c
+++ b/tools/testing/selftests/resctrl/resctrl_tests.c
@@ -19,6 +19,8 @@ static struct resctrl_test *resctrl_tests[] = {
 	&mba_test,
 	&cmt_test,
 	&l3_cat_test,
+	&l3_noncont_cat_test,
+	&l2_noncont_cat_test,
 };
 
 static int detect_vendor(void)

From 275575098b92e3f60faba6157668dd952dc11ecd Mon Sep 17 00:00:00 2001
From: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Date: Tue, 27 Feb 2024 08:21:41 +0100
Subject: [PATCH 185/236] selftests/resctrl: Add cleanup function to test
 framework

commit 8780bc88d4c86cdb7e9591bde9dd1110156a203b upstream.

Resctrl selftests use very similar functions to cleanup after
themselves. This creates a lot of code duplication. Also not being
hooked to the test framework means that ctrl-c handler isn't aware of
what test is currently running and executes all cleanups even though
only one is needed.

Add a function pointer to the resctrl_test struct and attach to it
cleanup functions from individual tests.

Signed-off-by: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cat_test.c | 1 +
 tools/testing/selftests/resctrl/cmt_test.c | 1 +
 tools/testing/selftests/resctrl/mba_test.c | 1 +
 tools/testing/selftests/resctrl/mbm_test.c | 1 +
 tools/testing/selftests/resctrl/resctrl.h  | 2 ++
 5 files changed, 6 insertions(+)

diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
index 4cb991be8e31b..8fa4348ab4611 100644
--- a/tools/testing/selftests/resctrl/cat_test.c
+++ b/tools/testing/selftests/resctrl/cat_test.c
@@ -373,6 +373,7 @@ struct resctrl_test l3_cat_test = {
 	.resource = "L3",
 	.feature_check = test_resource_feature_check,
 	.run_test = cat_run_test,
+	.cleanup = cat_test_cleanup,
 };
 
 struct resctrl_test l3_noncont_cat_test = {
diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c
index a81f91222a89a..a01ccf86e6ced 100644
--- a/tools/testing/selftests/resctrl/cmt_test.c
+++ b/tools/testing/selftests/resctrl/cmt_test.c
@@ -178,4 +178,5 @@ struct resctrl_test cmt_test = {
 	.resource = "L3",
 	.feature_check = cmt_feature_check,
 	.run_test = cmt_run_test,
+	.cleanup = cmt_test_cleanup,
 };
diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c
index 7946e32e85c83..189fbe20dc7bc 100644
--- a/tools/testing/selftests/resctrl/mba_test.c
+++ b/tools/testing/selftests/resctrl/mba_test.c
@@ -180,4 +180,5 @@ struct resctrl_test mba_test = {
 	.vendor_specific = ARCH_INTEL,
 	.feature_check = mba_feature_check,
 	.run_test = mba_run_test,
+	.cleanup = mba_test_cleanup,
 };
diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c
index d67ffa3ec63a3..73d6a8b989f57 100644
--- a/tools/testing/selftests/resctrl/mbm_test.c
+++ b/tools/testing/selftests/resctrl/mbm_test.c
@@ -150,4 +150,5 @@ struct resctrl_test mbm_test = {
 	.vendor_specific = ARCH_INTEL,
 	.feature_check = mbm_feature_check,
 	.run_test = mbm_run_test,
+	.cleanup = mbm_test_cleanup,
 };
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 2051bd135e0d0..221c945327331 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -72,6 +72,7 @@ struct user_params {
  * @disabled:		Test is disabled
  * @feature_check:	Callback to check required resctrl features
  * @run_test:		Callback to run the test
+ * @cleanup:		Callback to cleanup after the test
  */
 struct resctrl_test {
 	const char	*name;
@@ -82,6 +83,7 @@ struct resctrl_test {
 	bool		(*feature_check)(const struct resctrl_test *test);
 	int		(*run_test)(const struct resctrl_test *test,
 				    const struct user_params *uparams);
+	void		(*cleanup)(void);
 };
 
 /*

From 3f81d27080f5bb84845da1cbd58a7637852f0007 Mon Sep 17 00:00:00 2001
From: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Date: Tue, 27 Feb 2024 08:21:42 +0100
Subject: [PATCH 186/236] selftests/resctrl: Simplify cleanup in ctrl-c handler

commit e6487230e952cfd4070c61141f011608841f36eb upstream.

Ctrl-c handler isn't aware of what test is currently running. Because of
that it executes all cleanups even if they aren't necessary. Since the
ctrl-c handler uses the sa_sigaction system no parameters can be passed
to it as function arguments.

Add a global variable to make ctrl-c handler aware of the currently run
test and only execute the correct cleanup callback.

Signed-off-by: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/resctrl.h       |  3 +--
 tools/testing/selftests/resctrl/resctrl_tests.c | 14 +++-----------
 tools/testing/selftests/resctrl/resctrl_val.c   |  8 ++++++--
 3 files changed, 10 insertions(+), 15 deletions(-)

diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 221c945327331..bc486f92aceb7 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -158,7 +158,6 @@ int resctrl_val(const struct resctrl_test *test,
 		const struct user_params *uparams,
 		const char * const *benchmark_cmd,
 		struct resctrl_val_param *param);
-void tests_cleanup(void);
 void mbm_test_cleanup(void);
 void mba_test_cleanup(void);
 unsigned long create_bit_mask(unsigned int start, unsigned int len);
@@ -168,7 +167,7 @@ int get_mask_no_shareable(const char *cache_type, unsigned long *mask);
 int get_cache_size(int cpu_no, const char *cache_type, unsigned long *cache_size);
 int resource_info_unsigned_get(const char *resource, const char *filename, unsigned int *val);
 void ctrlc_handler(int signum, siginfo_t *info, void *ptr);
-int signal_handler_register(void);
+int signal_handler_register(const struct resctrl_test *test);
 void signal_handler_unregister(void);
 void cat_test_cleanup(void);
 unsigned int count_bits(unsigned long n);
diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c
index f3dc1b9696e71..0590daec2f44a 100644
--- a/tools/testing/selftests/resctrl/resctrl_tests.c
+++ b/tools/testing/selftests/resctrl/resctrl_tests.c
@@ -81,19 +81,11 @@ static void cmd_help(void)
 	printf("\t-h: help\n");
 }
 
-void tests_cleanup(void)
-{
-	mbm_test_cleanup();
-	mba_test_cleanup();
-	cmt_test_cleanup();
-	cat_test_cleanup();
-}
-
-static int test_prepare(void)
+static int test_prepare(const struct resctrl_test *test)
 {
 	int res;
 
-	res = signal_handler_register();
+	res = signal_handler_register(test);
 	if (res) {
 		ksft_print_msg("Failed to register signal handler\n");
 		return res;
@@ -136,7 +128,7 @@ static void run_single_test(const struct resctrl_test *test, const struct user_p
 
 	ksft_print_msg("Starting %s test ...\n", test->name);
 
-	if (test_prepare()) {
+	if (test_prepare(test)) {
 		ksft_exit_fail_msg("Abnormal failure when preparing for the test\n");
 		return;
 	}
diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index c1257b78e09e5..36864bcf20537 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -62,6 +62,7 @@ struct imc_counter_config {
 static char mbm_total_path[1024];
 static int imcs;
 static struct imc_counter_config imc_counters_config[MAX_IMCS][2];
+static const struct resctrl_test *current_test;
 
 void membw_initialize_perf_event_attr(int i, int j)
 {
@@ -489,7 +490,8 @@ void ctrlc_handler(int signum, siginfo_t *info, void *ptr)
 	if (bm_pid)
 		kill(bm_pid, SIGKILL);
 	umount_resctrlfs();
-	tests_cleanup();
+	if (current_test && current_test->cleanup)
+		current_test->cleanup();
 	ksft_print_msg("Ending\n\n");
 
 	exit(EXIT_SUCCESS);
@@ -499,13 +501,14 @@ void ctrlc_handler(int signum, siginfo_t *info, void *ptr)
  * Register CTRL-C handler for parent, as it has to kill
  * child process before exiting.
  */
-int signal_handler_register(void)
+int signal_handler_register(const struct resctrl_test *test)
 {
 	struct sigaction sigact = {};
 	int ret = 0;
 
 	bm_pid = 0;
 
+	current_test = test;
 	sigact.sa_sigaction = ctrlc_handler;
 	sigemptyset(&sigact.sa_mask);
 	sigact.sa_flags = SA_SIGINFO;
@@ -527,6 +530,7 @@ void signal_handler_unregister(void)
 {
 	struct sigaction sigact = {};
 
+	current_test = NULL;
 	sigact.sa_handler = SIG_DFL;
 	sigemptyset(&sigact.sa_mask);
 	if (sigaction(SIGINT, &sigact, NULL) ||

From 86ca5a1c564ced6291cbe49c29f212ccbc959712 Mon Sep 17 00:00:00 2001
From: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Date: Tue, 27 Feb 2024 08:21:43 +0100
Subject: [PATCH 187/236] selftests/resctrl: Move cleanups out of individual
 tests

commit 6cd368982cf3f972e5298025af0a9d2b69045cfe upstream.

Every test calls its cleanup function at the end of it's test function.
After the cleanup function pointer is added to the test framework this
can be simplified to executing the callback function at the end of the
generic test running function.

Make test cleanup functions static and call them from the end of
run_single_test() from the resctrl_test's cleanup function pointer.

Signed-off-by: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cat_test.c      | 7 ++-----
 tools/testing/selftests/resctrl/cmt_test.c      | 3 +--
 tools/testing/selftests/resctrl/mba_test.c      | 7 ++-----
 tools/testing/selftests/resctrl/mbm_test.c      | 7 ++-----
 tools/testing/selftests/resctrl/resctrl.h       | 4 ----
 tools/testing/selftests/resctrl/resctrl_tests.c | 6 ++++--
 6 files changed, 11 insertions(+), 23 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
index 8fa4348ab4611..c7686fb6641a7 100644
--- a/tools/testing/selftests/resctrl/cat_test.c
+++ b/tools/testing/selftests/resctrl/cat_test.c
@@ -128,7 +128,7 @@ static int check_results(struct resctrl_val_param *param, const char *cache_type
 	return fail;
 }
 
-void cat_test_cleanup(void)
+static void cat_test_cleanup(void)
 {
 	remove(RESULT_FILE_NAME);
 }
@@ -284,13 +284,10 @@ static int cat_run_test(const struct resctrl_test *test, const struct user_param
 
 	ret = cat_test(test, uparams, &param, span, start_mask);
 	if (ret)
-		goto out;
+		return ret;
 
 	ret = check_results(&param, test->resource,
 			    cache_total_size, full_cache_mask, start_mask);
-out:
-	cat_test_cleanup();
-
 	return ret;
 }
 
diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c
index a01ccf86e6ced..a44e6fcd37b73 100644
--- a/tools/testing/selftests/resctrl/cmt_test.c
+++ b/tools/testing/selftests/resctrl/cmt_test.c
@@ -91,7 +91,7 @@ static int check_results(struct resctrl_val_param *param, size_t span, int no_of
 				 MAX_DIFF, MAX_DIFF_PERCENT, runs - 1, true);
 }
 
-void cmt_test_cleanup(void)
+static void cmt_test_cleanup(void)
 {
 	remove(RESULT_FILE_NAME);
 }
@@ -161,7 +161,6 @@ static int cmt_run_test(const struct resctrl_test *test, const struct user_param
 		ksft_print_msg("Intel CMT may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n");
 
 out:
-	cmt_test_cleanup();
 	free(span_str);
 
 	return ret;
diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c
index 189fbe20dc7bc..5d6af9e8afedd 100644
--- a/tools/testing/selftests/resctrl/mba_test.c
+++ b/tools/testing/selftests/resctrl/mba_test.c
@@ -137,7 +137,7 @@ static int check_results(void)
 	return show_mba_info(bw_imc, bw_resc);
 }
 
-void mba_test_cleanup(void)
+static void mba_test_cleanup(void)
 {
 	remove(RESULT_FILE_NAME);
 }
@@ -158,13 +158,10 @@ static int mba_run_test(const struct resctrl_test *test, const struct user_param
 
 	ret = resctrl_val(test, uparams, uparams->benchmark_cmd, &param);
 	if (ret)
-		goto out;
+		return ret;
 
 	ret = check_results();
 
-out:
-	mba_test_cleanup();
-
 	return ret;
 }
 
diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c
index 73d6a8b989f57..3059ccc51a5ab 100644
--- a/tools/testing/selftests/resctrl/mbm_test.c
+++ b/tools/testing/selftests/resctrl/mbm_test.c
@@ -105,7 +105,7 @@ static int mbm_setup(const struct resctrl_test *test,
 	return ret;
 }
 
-void mbm_test_cleanup(void)
+static void mbm_test_cleanup(void)
 {
 	remove(RESULT_FILE_NAME);
 }
@@ -126,15 +126,12 @@ static int mbm_run_test(const struct resctrl_test *test, const struct user_param
 
 	ret = resctrl_val(test, uparams, uparams->benchmark_cmd, &param);
 	if (ret)
-		goto out;
+		return ret;
 
 	ret = check_results(DEFAULT_SPAN);
 	if (ret && (get_vendor() == ARCH_INTEL))
 		ksft_print_msg("Intel MBM may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n");
 
-out:
-	mbm_test_cleanup();
-
 	return ret;
 }
 
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index bc486f92aceb7..00d51fa7531ce 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -158,8 +158,6 @@ int resctrl_val(const struct resctrl_test *test,
 		const struct user_params *uparams,
 		const char * const *benchmark_cmd,
 		struct resctrl_val_param *param);
-void mbm_test_cleanup(void);
-void mba_test_cleanup(void);
 unsigned long create_bit_mask(unsigned int start, unsigned int len);
 unsigned int count_contiguous_bits(unsigned long val, unsigned int *start);
 int get_full_cbm(const char *cache_type, unsigned long *mask);
@@ -169,9 +167,7 @@ int resource_info_unsigned_get(const char *resource, const char *filename, unsig
 void ctrlc_handler(int signum, siginfo_t *info, void *ptr);
 int signal_handler_register(const struct resctrl_test *test);
 void signal_handler_unregister(void);
-void cat_test_cleanup(void);
 unsigned int count_bits(unsigned long n);
-void cmt_test_cleanup(void);
 
 void perf_event_attr_initialize(struct perf_event_attr *pea, __u64 config);
 void perf_event_initialize_read_format(struct perf_event_read *pe_read);
diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c
index 0590daec2f44a..348d17cb2a84a 100644
--- a/tools/testing/selftests/resctrl/resctrl_tests.c
+++ b/tools/testing/selftests/resctrl/resctrl_tests.c
@@ -100,8 +100,10 @@ static int test_prepare(const struct resctrl_test *test)
 	return 0;
 }
 
-static void test_cleanup(void)
+static void test_cleanup(const struct resctrl_test *test)
 {
+	if (test->cleanup)
+		test->cleanup();
 	umount_resctrlfs();
 	signal_handler_unregister();
 }
@@ -143,7 +145,7 @@ static void run_single_test(const struct resctrl_test *test, const struct user_p
 	ksft_test_result(!ret, "%s: test\n", test->name);
 
 cleanup:
-	test_cleanup();
+	test_cleanup(test);
 }
 
 static void init_user_params(struct user_params *uparams)

From a386998d7ef7669bee858cfe4a7cc5d13804e715 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Wed, 24 Apr 2024 10:24:09 -0700
Subject: [PATCH 188/236] selftests/resctrl: ksft_exit_skip() does not return

commit 47b59f3603d49d4898aafb256405b16ccdc68cc7 upstream.

After commit f7d5bcd35d42 ("selftests: kselftest: Mark functions that
unconditionally call exit() as __noreturn"), ksft_exit_...() functions
are marked as __noreturn, which means the return type should not be
'int' but 'void' because they are not returning anything (and never were
since exit() has always been called).

To facilitate updating the return type of these functions, remove
'return' before the calls to ksft_exit_skip(), as __noreturn prevents
the compiler from warning that a caller of ksft_exit_skip() does not
return a value because the program will terminate upon calling these
functions.

Reviewed-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/resctrl_tests.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c
index 348d17cb2a84a..ecbb7605a9815 100644
--- a/tools/testing/selftests/resctrl/resctrl_tests.c
+++ b/tools/testing/selftests/resctrl/resctrl_tests.c
@@ -247,13 +247,13 @@ int main(int argc, char **argv)
 	 * 2. We execute perf commands
 	 */
 	if (geteuid() != 0)
-		return ksft_exit_skip("Not running as root. Skipping...\n");
+		ksft_exit_skip("Not running as root. Skipping...\n");
 
 	if (!check_resctrlfs_support())
-		return ksft_exit_skip("resctrl FS does not exist. Enable X86_CPU_RESCTRL config option.\n");
+		ksft_exit_skip("resctrl FS does not exist. Enable X86_CPU_RESCTRL config option.\n");
 
 	if (umount_resctrlfs())
-		return ksft_exit_skip("resctrl FS unmount failed.\n");
+		ksft_exit_skip("resctrl FS unmount failed.\n");
 
 	filter_dmesg();
 

From 3ff36e58c98703baaff94d917484d445eb461130 Mon Sep 17 00:00:00 2001
From: John Hubbard <jhubbard@nvidia.com>
Date: Wed, 8 May 2024 13:41:01 -0700
Subject: [PATCH 189/236] selftests/resctrl: fix clang build warnings related
 to abs(), labs() calls
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 14d28ec6f821622211aa65b4da156399c9a4a9c6 upstream.

When building with clang, via:

    make LLVM=1 -C tools/testing/selftests

...two types of warnings occur:

    warning: absolute value function 'abs' given an argument of type
    'long' but has parameter of type 'int' which may cause truncation of
    value

    warning: taking the absolute value of unsigned type 'unsigned long'
    has no effect

Fix these by:

a) using labs() in place of abs(), when long integers are involved, and

b) Change to use signed integer data types, in places where subtraction
   is used (and could end up with negative values).

c) Remove a duplicate abs() call in cmt_test.c.

Cc: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cmt_test.c | 4 ++--
 tools/testing/selftests/resctrl/mba_test.c | 2 +-
 tools/testing/selftests/resctrl/mbm_test.c | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c
index a44e6fcd37b73..0105afec6188a 100644
--- a/tools/testing/selftests/resctrl/cmt_test.c
+++ b/tools/testing/selftests/resctrl/cmt_test.c
@@ -40,11 +40,11 @@ static int show_results_info(unsigned long sum_llc_val, int no_of_bits,
 	int ret;
 
 	avg_llc_val = sum_llc_val / num_of_runs;
-	avg_diff = (long)abs(cache_span - avg_llc_val);
+	avg_diff = (long)(cache_span - avg_llc_val);
 	diff_percent = ((float)cache_span - avg_llc_val) / cache_span * 100;
 
 	ret = platform && abs((int)diff_percent) > max_diff_percent &&
-	      abs(avg_diff) > max_diff;
+	      labs(avg_diff) > max_diff;
 
 	ksft_print_msg("%s Check cache miss rate within %lu%%\n",
 		       ret ? "Fail:" : "Pass:", max_diff_percent);
diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c
index 5d6af9e8afedd..a6ad39aae1623 100644
--- a/tools/testing/selftests/resctrl/mba_test.c
+++ b/tools/testing/selftests/resctrl/mba_test.c
@@ -60,8 +60,8 @@ static bool show_mba_info(unsigned long *bw_imc, unsigned long *bw_resc)
 	/* Memory bandwidth from 100% down to 10% */
 	for (allocation = 0; allocation < ALLOCATION_MAX / ALLOCATION_STEP;
 	     allocation++) {
-		unsigned long avg_bw_imc, avg_bw_resc;
 		unsigned long sum_bw_imc = 0, sum_bw_resc = 0;
+		long avg_bw_imc, avg_bw_resc;
 		int avg_diff_per;
 		float avg_diff;
 
diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c
index 3059ccc51a5ab..6fec51e1ff465 100644
--- a/tools/testing/selftests/resctrl/mbm_test.c
+++ b/tools/testing/selftests/resctrl/mbm_test.c
@@ -17,8 +17,8 @@
 static int
 show_bw_info(unsigned long *bw_imc, unsigned long *bw_resc, size_t span)
 {
-	unsigned long avg_bw_imc = 0, avg_bw_resc = 0;
 	unsigned long sum_bw_imc = 0, sum_bw_resc = 0;
+	long avg_bw_imc = 0, avg_bw_resc = 0;
 	int runs, ret, avg_diff_per;
 	float avg_diff = 0;
 

From 3e9b26c4c56a73e18476156768cf9d806a81d1f6 Mon Sep 17 00:00:00 2001
From: Babu Moger <babu.moger@amd.com>
Date: Tue, 11 Jun 2024 17:18:30 -0500
Subject: [PATCH 190/236] selftests/resctrl: Fix non-contiguous CBM for AMD
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 48236960c06d32370bfa6f2cc408e786873262c8 upstream.

The non-contiguous CBM test fails on AMD with:
Starting L3_NONCONT_CAT test ...
Mounting resctrl to "/sys/fs/resctrl"
CPUID output doesn't match 'sparse_masks' file content!
not ok 5 L3_NONCONT_CAT: test

AMD always supports non-contiguous CBM but does not report it via CPUID.

Fix the non-contiguous CBM test to use CPUID to discover non-contiguous
CBM support only on Intel.

Fixes: ae638551ab64 ("selftests/resctrl: Add non-contiguous CBMs CAT test")
Signed-off-by: Babu Moger <babu.moger@amd.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cat_test.c | 32 +++++++++++++++-------
 1 file changed, 22 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
index c7686fb6641a7..55315ed695f47 100644
--- a/tools/testing/selftests/resctrl/cat_test.c
+++ b/tools/testing/selftests/resctrl/cat_test.c
@@ -291,11 +291,30 @@ static int cat_run_test(const struct resctrl_test *test, const struct user_param
 	return ret;
 }
 
+static bool arch_supports_noncont_cat(const struct resctrl_test *test)
+{
+	unsigned int eax, ebx, ecx, edx;
+
+	/* AMD always supports non-contiguous CBM. */
+	if (get_vendor() == ARCH_AMD)
+		return true;
+
+	/* Intel support for non-contiguous CBM needs to be discovered. */
+	if (!strcmp(test->resource, "L3"))
+		__cpuid_count(0x10, 1, eax, ebx, ecx, edx);
+	else if (!strcmp(test->resource, "L2"))
+		__cpuid_count(0x10, 2, eax, ebx, ecx, edx);
+	else
+		return false;
+
+	return ((ecx >> 3) & 1);
+}
+
 static int noncont_cat_run_test(const struct resctrl_test *test,
 				const struct user_params *uparams)
 {
 	unsigned long full_cache_mask, cont_mask, noncont_mask;
-	unsigned int eax, ebx, ecx, edx, sparse_masks;
+	unsigned int sparse_masks;
 	int bit_center, ret;
 	char schemata[64];
 
@@ -304,15 +323,8 @@ static int noncont_cat_run_test(const struct resctrl_test *test,
 	if (ret)
 		return ret;
 
-	if (!strcmp(test->resource, "L3"))
-		__cpuid_count(0x10, 1, eax, ebx, ecx, edx);
-	else if (!strcmp(test->resource, "L2"))
-		__cpuid_count(0x10, 2, eax, ebx, ecx, edx);
-	else
-		return -EINVAL;
-
-	if (sparse_masks != ((ecx >> 3) & 1)) {
-		ksft_print_msg("CPUID output doesn't match 'sparse_masks' file content!\n");
+	if (arch_supports_noncont_cat(test) != sparse_masks) {
+		ksft_print_msg("Hardware and kernel differ on non-contiguous CBM support!\n");
 		return 1;
 	}
 

From 5e42a066ab08d1c91c22ce022482817c73a2542f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Mon, 10 Jun 2024 18:14:43 +0300
Subject: [PATCH 191/236] selftests/resctrl: Calculate resctrl FS derived mem
 bw over sleep(1) only
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit da50de0a92f31605423e39e6ccf3ce7508e88a7a upstream.

For MBM/MBA tests, measure_vals() calls get_mem_bw_imc() that performs
the measurement over a duration of sleep(1) call. The memory bandwidth
numbers from IMC are derived over this duration. The resctrl FS derived
memory bandwidth, however, is calculated inside measure_vals() and only
takes delta between the previous value and the current one which
besides the actual test, also samples inter-test noise.

Rework the logic in measure_vals() and get_mem_bw_imc() such that the
resctrl FS memory bandwidth section covers much shorter duration
closely matching that of the IMC perf counters to improve measurement
accuracy.

For the second read after rewind() to return a fresh value, also
newline has to be consumed by the fscanf().

Suggested-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/resctrl_val.c | 141 +++++++++++-------
 1 file changed, 91 insertions(+), 50 deletions(-)

diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index 36864bcf20537..9a8ab088130ec 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -305,18 +305,13 @@ static void perf_close_imc_mem_bw(void)
 }
 
 /*
- * get_mem_bw_imc:	Memory band width as reported by iMC counters
- * @cpu_no:		CPU number that the benchmark PID is binded to
- * @bw_report:		Bandwidth report type (reads, writes)
- *
- * Memory B/W utilized by a process on a socket can be calculated using
- * iMC counters. Perf events are used to read these counters.
+ * perf_open_imc_mem_bw - Open perf fds for IMCs
+ * @cpu_no: CPU number that the benchmark PID is bound to
  *
  * Return: = 0 on success. < 0 on failure.
  */
-static int get_mem_bw_imc(int cpu_no, char *bw_report, float *bw_imc)
+static int perf_open_imc_mem_bw(int cpu_no)
 {
-	float reads, writes, of_mul_read, of_mul_write;
 	int imc, ret;
 
 	for (imc = 0; imc < imcs; imc++) {
@@ -324,8 +319,6 @@ static int get_mem_bw_imc(int cpu_no, char *bw_report, float *bw_imc)
 		imc_counters_config[imc][WRITE].fd = -1;
 	}
 
-	/* Start all iMC counters to log values (both read and write) */
-	reads = 0, writes = 0, of_mul_read = 1, of_mul_write = 1;
 	for (imc = 0; imc < imcs; imc++) {
 		ret = open_perf_event(imc, cpu_no, READ);
 		if (ret)
@@ -333,7 +326,26 @@ static int get_mem_bw_imc(int cpu_no, char *bw_report, float *bw_imc)
 		ret = open_perf_event(imc, cpu_no, WRITE);
 		if (ret)
 			goto close_fds;
+	}
+
+	return 0;
 
+close_fds:
+	perf_close_imc_mem_bw();
+	return -1;
+}
+
+/*
+ * do_mem_bw_test - Perform memory bandwidth test
+ *
+ * Runs memory bandwidth test over one second period. Also, handles starting
+ * and stopping of the IMC perf counters around the test.
+ */
+static void do_imc_mem_bw_test(void)
+{
+	int imc;
+
+	for (imc = 0; imc < imcs; imc++) {
 		membw_ioctl_perf_event_ioc_reset_enable(imc, READ);
 		membw_ioctl_perf_event_ioc_reset_enable(imc, WRITE);
 	}
@@ -345,6 +357,24 @@ static int get_mem_bw_imc(int cpu_no, char *bw_report, float *bw_imc)
 		membw_ioctl_perf_event_ioc_disable(imc, READ);
 		membw_ioctl_perf_event_ioc_disable(imc, WRITE);
 	}
+}
+
+/*
+ * get_mem_bw_imc - Memory band width as reported by iMC counters
+ * @bw_report: Bandwidth report type (reads, writes)
+ *
+ * Memory B/W utilized by a process on a socket can be calculated using
+ * iMC counters. Perf events are used to read these counters.
+ *
+ * Return: = 0 on success. < 0 on failure.
+ */
+static int get_mem_bw_imc(char *bw_report, float *bw_imc)
+{
+	float reads, writes, of_mul_read, of_mul_write;
+	int imc;
+
+	/* Start all iMC counters to log values (both read and write) */
+	reads = 0, writes = 0, of_mul_read = 1, of_mul_write = 1;
 
 	/*
 	 * Get results which are stored in struct type imc_counter_config
@@ -359,13 +389,13 @@ static int get_mem_bw_imc(int cpu_no, char *bw_report, float *bw_imc)
 		if (read(r->fd, &r->return_value,
 			 sizeof(struct membw_read_format)) == -1) {
 			ksft_perror("Couldn't get read b/w through iMC");
-			goto close_fds;
+			return -1;
 		}
 
 		if (read(w->fd, &w->return_value,
 			 sizeof(struct membw_read_format)) == -1) {
 			ksft_perror("Couldn't get write bw through iMC");
-			goto close_fds;
+			return -1;
 		}
 
 		__u64 r_time_enabled = r->return_value.time_enabled;
@@ -385,8 +415,6 @@ static int get_mem_bw_imc(int cpu_no, char *bw_report, float *bw_imc)
 		writes += w->return_value.value * of_mul_write * SCALE;
 	}
 
-	perf_close_imc_mem_bw();
-
 	if (strcmp(bw_report, "reads") == 0) {
 		*bw_imc = reads;
 		return 0;
@@ -399,10 +427,6 @@ static int get_mem_bw_imc(int cpu_no, char *bw_report, float *bw_imc)
 
 	*bw_imc = reads + writes;
 	return 0;
-
-close_fds:
-	perf_close_imc_mem_bw();
-	return -1;
 }
 
 void set_mbm_path(const char *ctrlgrp, const char *mongrp, int domain_id)
@@ -461,24 +485,23 @@ static void initialize_mem_bw_resctrl(const char *ctrlgrp, const char *mongrp,
  * 1. If con_mon grp is given, then read from it
  * 2. If con_mon grp is not given, then read from root con_mon grp
  */
-static int get_mem_bw_resctrl(unsigned long *mbm_total)
+static FILE *open_mem_bw_resctrl(const char *mbm_bw_file)
 {
 	FILE *fp;
 
-	fp = fopen(mbm_total_path, "r");
-	if (!fp) {
+	fp = fopen(mbm_bw_file, "r");
+	if (!fp)
 		ksft_perror("Failed to open total bw file");
 
-		return -1;
-	}
-	if (fscanf(fp, "%lu", mbm_total) <= 0) {
-		ksft_perror("Could not get mbm local bytes");
-		fclose(fp);
+	return fp;
+}
 
+static int get_mem_bw_resctrl(FILE *fp, unsigned long *mbm_total)
+{
+	if (fscanf(fp, "%lu\n", mbm_total) <= 0) {
+		ksft_perror("Could not get MBM local bytes");
 		return -1;
 	}
-	fclose(fp);
-
 	return 0;
 }
 
@@ -614,37 +637,56 @@ static void initialize_llc_occu_resctrl(const char *ctrlgrp, const char *mongrp,
 		set_cmt_path(ctrlgrp, mongrp, domain_id);
 }
 
+/*
+ * Measure memory bandwidth from resctrl and from another source which is
+ * perf imc value or could be something else if perf imc event is not
+ * available. Compare the two values to validate resctrl value. It takes
+ * 1 sec to measure the data.
+ */
 static int measure_vals(const struct user_params *uparams,
-			struct resctrl_val_param *param,
-			unsigned long *bw_resc_start)
+			struct resctrl_val_param *param)
 {
-	unsigned long bw_resc, bw_resc_end;
+	unsigned long bw_resc, bw_resc_start, bw_resc_end;
+	FILE *mem_bw_fp;
 	float bw_imc;
 	int ret;
 
-	/*
-	 * Measure memory bandwidth from resctrl and from
-	 * another source which is perf imc value or could
-	 * be something else if perf imc event is not available.
-	 * Compare the two values to validate resctrl value.
-	 * It takes 1sec to measure the data.
-	 */
-	ret = get_mem_bw_imc(uparams->cpu, param->bw_report, &bw_imc);
+	mem_bw_fp = open_mem_bw_resctrl(mbm_total_path);
+	if (!mem_bw_fp)
+		return -1;
+
+	ret = perf_open_imc_mem_bw(uparams->cpu);
 	if (ret < 0)
-		return ret;
+		goto close_fp;
 
-	ret = get_mem_bw_resctrl(&bw_resc_end);
+	ret = get_mem_bw_resctrl(mem_bw_fp, &bw_resc_start);
 	if (ret < 0)
-		return ret;
+		goto close_imc;
 
-	bw_resc = (bw_resc_end - *bw_resc_start) / MB;
-	ret = print_results_bw(param->filename, bm_pid, bw_imc, bw_resc);
-	if (ret)
-		return ret;
+	rewind(mem_bw_fp);
 
-	*bw_resc_start = bw_resc_end;
+	do_imc_mem_bw_test();
 
-	return 0;
+	ret = get_mem_bw_resctrl(mem_bw_fp, &bw_resc_end);
+	if (ret < 0)
+		goto close_imc;
+
+	ret = get_mem_bw_imc(param->bw_report, &bw_imc);
+	if (ret < 0)
+		goto close_imc;
+
+	perf_close_imc_mem_bw();
+	fclose(mem_bw_fp);
+
+	bw_resc = (bw_resc_end - bw_resc_start) / MB;
+
+	return print_results_bw(param->filename, bm_pid, bw_imc, bw_resc);
+
+close_imc:
+	perf_close_imc_mem_bw();
+close_fp:
+	fclose(mem_bw_fp);
+	return ret;
 }
 
 /*
@@ -718,7 +760,6 @@ int resctrl_val(const struct resctrl_test *test,
 		struct resctrl_val_param *param)
 {
 	char *resctrl_val = param->resctrl_val;
-	unsigned long bw_resc_start = 0;
 	struct sigaction sigact;
 	int ret = 0, pipefd[2];
 	char pipe_message = 0;
@@ -860,7 +901,7 @@ int resctrl_val(const struct resctrl_test *test,
 
 		if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)) ||
 		    !strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR))) {
-			ret = measure_vals(uparams, param, &bw_resc_start);
+			ret = measure_vals(uparams, param);
 			if (ret)
 				break;
 		} else if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) {

From 7eee09af329d28e9d67965d9561cd6a5cef45ff3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Mon, 10 Jun 2024 18:14:44 +0300
Subject: [PATCH 192/236] selftests/resctrl: Make "bandwidth" consistent in
 comments & prints
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 2704b2d117c52cd156bcdcad1eefd9c2dad1794d upstream.

Resctrl selftests refer to "bandwidth" currently in two other forms in
the code ("B/W" and "band width").

Use "bandwidth" consistently everywhere. While at it, fix also one
"over flow" -> "overflow" on a line that is touched by the change.

Suggested-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/resctrl_val.c | 14 +++++++-------
 tools/testing/selftests/resctrl/resctrlfs.c   |  2 +-
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index 9a8ab088130ec..cef2c0227868c 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -360,11 +360,11 @@ static void do_imc_mem_bw_test(void)
 }
 
 /*
- * get_mem_bw_imc - Memory band width as reported by iMC counters
+ * get_mem_bw_imc - Memory bandwidth as reported by iMC counters
  * @bw_report: Bandwidth report type (reads, writes)
  *
- * Memory B/W utilized by a process on a socket can be calculated using
- * iMC counters. Perf events are used to read these counters.
+ * Memory bandwidth utilized by a process on a socket can be calculated
+ * using iMC counters. Perf events are used to read these counters.
  *
  * Return: = 0 on success. < 0 on failure.
  */
@@ -378,7 +378,7 @@ static int get_mem_bw_imc(char *bw_report, float *bw_imc)
 
 	/*
 	 * Get results which are stored in struct type imc_counter_config
-	 * Take over flow into consideration before calculating total b/w
+	 * Take overflow into consideration before calculating total bandwidth.
 	 */
 	for (imc = 0; imc < imcs; imc++) {
 		struct imc_counter_config *r =
@@ -388,13 +388,13 @@ static int get_mem_bw_imc(char *bw_report, float *bw_imc)
 
 		if (read(r->fd, &r->return_value,
 			 sizeof(struct membw_read_format)) == -1) {
-			ksft_perror("Couldn't get read b/w through iMC");
+			ksft_perror("Couldn't get read bandwidth through iMC");
 			return -1;
 		}
 
 		if (read(w->fd, &w->return_value,
 			 sizeof(struct membw_read_format)) == -1) {
-			ksft_perror("Couldn't get write bw through iMC");
+			ksft_perror("Couldn't get write bandwidth through iMC");
 			return -1;
 		}
 
@@ -491,7 +491,7 @@ static FILE *open_mem_bw_resctrl(const char *mbm_bw_file)
 
 	fp = fopen(mbm_bw_file, "r");
 	if (!fp)
-		ksft_perror("Failed to open total bw file");
+		ksft_perror("Failed to open total memory bandwidth file");
 
 	return fp;
 }
diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index f08344fee9ef7..9c410f2c89942 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -850,7 +850,7 @@ int validate_bw_report_request(char *bw_report)
 	if (strcmp(bw_report, "total") == 0)
 		return 0;
 
-	fprintf(stderr, "Requested iMC B/W report type unavailable\n");
+	fprintf(stderr, "Requested iMC bandwidth report type unavailable\n");
 
 	return -1;
 }

From 3c693eea19c01511c400c755bd4a2bd4912db013 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Mon, 10 Jun 2024 18:14:45 +0300
Subject: [PATCH 193/236] selftests/resctrl: Consolidate get_domain_id() into
 resctrl_val()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 9224db5180f244f169fb81a3c88c48bf612ba238 upstream.

Both initialize_mem_bw_resctrl() and initialize_llc_occu_resctrl() that
are called from resctrl_val() need to determine domain ID to construct
resctrl fs related paths. Both functions do it by taking CPU ID which
neither needs for any other purpose than determining the domain ID.

Consolidate determining the domain ID into resctrl_val() and pass the
domain ID instead of CPU ID to initialize_mem_bw_resctrl() and
initialize_llc_occu_resctrl().

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/resctrl_val.c | 33 ++++++++-----------
 1 file changed, 13 insertions(+), 20 deletions(-)

diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index cef2c0227868c..375b6657fc3cf 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -449,19 +449,12 @@ void set_mbm_path(const char *ctrlgrp, const char *mongrp, int domain_id)
  * initialize_mem_bw_resctrl:	Appropriately populate "mbm_total_path"
  * @ctrlgrp:			Name of the control monitor group (con_mon grp)
  * @mongrp:			Name of the monitor group (mon grp)
- * @cpu_no:			CPU number that the benchmark PID is binded to
+ * @domain_id:			Domain ID (cache ID; for MB, L3 cache ID)
  * @resctrl_val:		Resctrl feature (Eg: mbm, mba.. etc)
  */
 static void initialize_mem_bw_resctrl(const char *ctrlgrp, const char *mongrp,
-				      int cpu_no, char *resctrl_val)
+				      int domain_id, char *resctrl_val)
 {
-	int domain_id;
-
-	if (get_domain_id("MB", cpu_no, &domain_id) < 0) {
-		ksft_print_msg("Could not get domain ID\n");
-		return;
-	}
-
 	if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)))
 		set_mbm_path(ctrlgrp, mongrp, domain_id);
 
@@ -620,19 +613,12 @@ static void set_cmt_path(const char *ctrlgrp, const char *mongrp, char sock_num)
  * initialize_llc_occu_resctrl:	Appropriately populate "llc_occup_path"
  * @ctrlgrp:			Name of the control monitor group (con_mon grp)
  * @mongrp:			Name of the monitor group (mon grp)
- * @cpu_no:			CPU number that the benchmark PID is binded to
+ * @domain_id:			Domain ID (cache ID; for MB, L3 cache ID)
  * @resctrl_val:		Resctrl feature (Eg: cat, cmt.. etc)
  */
 static void initialize_llc_occu_resctrl(const char *ctrlgrp, const char *mongrp,
-					int cpu_no, char *resctrl_val)
+					int domain_id, char *resctrl_val)
 {
-	int domain_id;
-
-	if (get_domain_id("L3", cpu_no, &domain_id) < 0) {
-		ksft_print_msg("Could not get domain ID\n");
-		return;
-	}
-
 	if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR)))
 		set_cmt_path(ctrlgrp, mongrp, domain_id);
 }
@@ -764,10 +750,17 @@ int resctrl_val(const struct resctrl_test *test,
 	int ret = 0, pipefd[2];
 	char pipe_message = 0;
 	union sigval value;
+	int domain_id;
 
 	if (strcmp(param->filename, "") == 0)
 		sprintf(param->filename, "stdio");
 
+	ret = get_domain_id(test->resource, uparams->cpu, &domain_id);
+	if (ret < 0) {
+		ksft_print_msg("Could not get domain ID\n");
+		return ret;
+	}
+
 	if (!strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR)) ||
 	    !strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR))) {
 		ret = validate_bw_report_request(param->bw_report);
@@ -862,10 +855,10 @@ int resctrl_val(const struct resctrl_test *test,
 			goto out;
 
 		initialize_mem_bw_resctrl(param->ctrlgrp, param->mongrp,
-					  uparams->cpu, resctrl_val);
+					  domain_id, resctrl_val);
 	} else if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR)))
 		initialize_llc_occu_resctrl(param->ctrlgrp, param->mongrp,
-					    uparams->cpu, resctrl_val);
+					    domain_id, resctrl_val);
 
 	/* Parent waits for child to be ready. */
 	close(pipefd[1]);

From a99bb2fd91d11c3f8348d6d01de23361755b9962 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Mon, 10 Jun 2024 18:14:46 +0300
Subject: [PATCH 194/236] selftests/resctrl: Use correct type for pids
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 8245a70edad18e5eba479c5ea91beb590590b237 upstream.

A few functions receive PIDs through int arguments. PIDs variables
should be of type pid_t, not int.

Convert pid arguments from int to pid_t.

Before printing PID, match the type to %d by casting to int which is
enough for Linux (standard would allow using a longer integer type but
generalizing for that would complicate the code unnecessarily, the
selftest code does not need to be portable).

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cache.c       | 10 +++++-----
 tools/testing/selftests/resctrl/resctrl.h     |  4 ++--
 tools/testing/selftests/resctrl/resctrl_val.c |  8 ++++----
 tools/testing/selftests/resctrl/resctrlfs.c   |  2 +-
 4 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c
index 1b339d6bbff1c..1ff1104e65753 100644
--- a/tools/testing/selftests/resctrl/cache.c
+++ b/tools/testing/selftests/resctrl/cache.c
@@ -101,12 +101,12 @@ static int get_llc_occu_resctrl(unsigned long *llc_occupancy)
  *
  * Return:		0 on success, < 0 on error.
  */
-static int print_results_cache(const char *filename, int bm_pid, __u64 llc_value)
+static int print_results_cache(const char *filename, pid_t bm_pid, __u64 llc_value)
 {
 	FILE *fp;
 
 	if (strcmp(filename, "stdio") == 0 || strcmp(filename, "stderr") == 0) {
-		printf("Pid: %d \t LLC_value: %llu\n", bm_pid, llc_value);
+		printf("Pid: %d \t LLC_value: %llu\n", (int)bm_pid, llc_value);
 	} else {
 		fp = fopen(filename, "a");
 		if (!fp) {
@@ -114,7 +114,7 @@ static int print_results_cache(const char *filename, int bm_pid, __u64 llc_value
 
 			return -1;
 		}
-		fprintf(fp, "Pid: %d \t llc_value: %llu\n", bm_pid, llc_value);
+		fprintf(fp, "Pid: %d \t llc_value: %llu\n", (int)bm_pid, llc_value);
 		fclose(fp);
 	}
 
@@ -133,7 +133,7 @@ static int print_results_cache(const char *filename, int bm_pid, __u64 llc_value
  * Return: =0 on success. <0 on failure.
  */
 int perf_event_measure(int pe_fd, struct perf_event_read *pe_read,
-		       const char *filename, int bm_pid)
+		       const char *filename, pid_t bm_pid)
 {
 	int ret;
 
@@ -161,7 +161,7 @@ int perf_event_measure(int pe_fd, struct perf_event_read *pe_read,
  *
  * Return: =0 on success. <0 on failure.
  */
-int measure_llc_resctrl(const char *filename, int bm_pid)
+int measure_llc_resctrl(const char *filename, pid_t bm_pid)
 {
 	unsigned long llc_occu_resc = 0;
 	int ret;
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 00d51fa7531ce..e6f221236c79a 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -174,8 +174,8 @@ void perf_event_initialize_read_format(struct perf_event_read *pe_read);
 int perf_open(struct perf_event_attr *pea, pid_t pid, int cpu_no);
 int perf_event_reset_enable(int pe_fd);
 int perf_event_measure(int pe_fd, struct perf_event_read *pe_read,
-		       const char *filename, int bm_pid);
-int measure_llc_resctrl(const char *filename, int bm_pid);
+		       const char *filename, pid_t bm_pid);
+int measure_llc_resctrl(const char *filename, pid_t bm_pid);
 void show_cache_info(int no_of_bits, __u64 avg_llc_val, size_t cache_span, bool lines);
 
 /*
diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index 375b6657fc3cf..22ad7f8b25160 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -565,14 +565,14 @@ void signal_handler_unregister(void)
  *
  * Return:		0 on success, < 0 on error.
  */
-static int print_results_bw(char *filename,  int bm_pid, float bw_imc,
+static int print_results_bw(char *filename, pid_t bm_pid, float bw_imc,
 			    unsigned long bw_resc)
 {
 	unsigned long diff = fabs(bw_imc - bw_resc);
 	FILE *fp;
 
 	if (strcmp(filename, "stdio") == 0 || strcmp(filename, "stderr") == 0) {
-		printf("Pid: %d \t Mem_BW_iMC: %f \t ", bm_pid, bw_imc);
+		printf("Pid: %d \t Mem_BW_iMC: %f \t ", (int)bm_pid, bw_imc);
 		printf("Mem_BW_resc: %lu \t Difference: %lu\n", bw_resc, diff);
 	} else {
 		fp = fopen(filename, "a");
@@ -582,7 +582,7 @@ static int print_results_bw(char *filename,  int bm_pid, float bw_imc,
 			return -1;
 		}
 		if (fprintf(fp, "Pid: %d \t Mem_BW_iMC: %f \t Mem_BW_resc: %lu \t Difference: %lu\n",
-			    bm_pid, bw_imc, bw_resc, diff) <= 0) {
+			    (int)bm_pid, bw_imc, bw_resc, diff) <= 0) {
 			ksft_print_msg("Could not log results\n");
 			fclose(fp);
 
@@ -827,7 +827,7 @@ int resctrl_val(const struct resctrl_test *test,
 		PARENT_EXIT();
 	}
 
-	ksft_print_msg("Benchmark PID: %d\n", bm_pid);
+	ksft_print_msg("Benchmark PID: %d\n", (int)bm_pid);
 
 	/*
 	 * The cast removes constness but nothing mutates benchmark_cmd within
diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index 9c410f2c89942..b6db95090e6ec 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -508,7 +508,7 @@ static int write_pid_to_tasks(char *tasks, pid_t pid)
 
 		return -1;
 	}
-	if (fprintf(fp, "%d\n", pid) < 0) {
+	if (fprintf(fp, "%d\n", (int)pid) < 0) {
 		ksft_print_msg("Failed to write pid to tasks file\n");
 		fclose(fp);
 

From 44c0b6ba784d40b6e6851e46f64334f549d8121e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Mon, 10 Jun 2024 18:14:47 +0300
Subject: [PATCH 195/236] selftests/resctrl: Cleanup bm_pid and ppid usage &
 limit scope
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit b0bd742a1379dff238efcf67c2cb0c518ee0b691 upstream.

'bm_pid' and 'ppid' are global variables. As they are used by different
processes and in signal handler, they cannot be entirely converted into
local variables.

The scope of those variables can still be reduced into resctrl_val.c
only. As PARENT_EXIT() macro is using 'ppid', make it a function in
resctrl_val.c and pass ppid to it as an argument because it is easier
to understand than using the global variable directly.

Pass 'bm_pid' into measure_vals() instead of relying on the global
variable which helps to make the call signatures of measure_vals() and
measure_llc_resctrl() more similar to each other.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/resctrl.h     |  9 --------
 tools/testing/selftests/resctrl/resctrl_val.c | 23 ++++++++++++-------
 2 files changed, 15 insertions(+), 17 deletions(-)

diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index e6f221236c79a..e4b6dc672ecc7 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -43,13 +43,6 @@
 
 #define DEFAULT_SPAN		(250 * MB)
 
-#define PARENT_EXIT()				\
-	do {					\
-		kill(ppid, SIGKILL);		\
-		umount_resctrlfs();		\
-		exit(EXIT_FAILURE);		\
-	} while (0)
-
 /*
  * user_params:		User supplied parameters
  * @cpu:		CPU number to which the benchmark will be bound to
@@ -127,8 +120,6 @@ struct perf_event_read {
  */
 extern volatile int *value_sink;
 
-extern pid_t bm_pid, ppid;
-
 extern char llc_occup_path[1024];
 
 int get_vendor(void);
diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index 22ad7f8b25160..9a1855360c85a 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -498,7 +498,7 @@ static int get_mem_bw_resctrl(FILE *fp, unsigned long *mbm_total)
 	return 0;
 }
 
-pid_t bm_pid, ppid;
+static pid_t bm_pid, ppid;
 
 void ctrlc_handler(int signum, siginfo_t *info, void *ptr)
 {
@@ -556,6 +556,13 @@ void signal_handler_unregister(void)
 	}
 }
 
+static void parent_exit(pid_t ppid)
+{
+	kill(ppid, SIGKILL);
+	umount_resctrlfs();
+	exit(EXIT_FAILURE);
+}
+
 /*
  * print_results_bw:	the memory bandwidth results are stored in a file
  * @filename:		file that stores the results
@@ -630,7 +637,7 @@ static void initialize_llc_occu_resctrl(const char *ctrlgrp, const char *mongrp,
  * 1 sec to measure the data.
  */
 static int measure_vals(const struct user_params *uparams,
-			struct resctrl_val_param *param)
+			struct resctrl_val_param *param, pid_t bm_pid)
 {
 	unsigned long bw_resc, bw_resc_start, bw_resc_end;
 	FILE *mem_bw_fp;
@@ -699,7 +706,7 @@ static void run_benchmark(int signum, siginfo_t *info, void *ucontext)
 	fp = freopen("/dev/null", "w", stdout);
 	if (!fp) {
 		ksft_perror("Unable to direct benchmark status to /dev/null");
-		PARENT_EXIT();
+		parent_exit(ppid);
 	}
 
 	if (strcmp(benchmark_cmd[0], "fill_buf") == 0) {
@@ -713,7 +720,7 @@ static void run_benchmark(int signum, siginfo_t *info, void *ucontext)
 			once = false;
 		} else {
 			ksft_print_msg("Invalid once parameter\n");
-			PARENT_EXIT();
+			parent_exit(ppid);
 		}
 
 		if (run_fill_buf(span, memflush, operation, once))
@@ -727,7 +734,7 @@ static void run_benchmark(int signum, siginfo_t *info, void *ucontext)
 
 	fclose(stdout);
 	ksft_print_msg("Unable to run specified benchmark\n");
-	PARENT_EXIT();
+	parent_exit(ppid);
 }
 
 /*
@@ -806,7 +813,7 @@ int resctrl_val(const struct resctrl_test *test,
 		/* Register for "SIGUSR1" signal from parent */
 		if (sigaction(SIGUSR1, &sigact, NULL)) {
 			ksft_perror("Can't register child for signal");
-			PARENT_EXIT();
+			parent_exit(ppid);
 		}
 
 		/* Tell parent that child is ready */
@@ -824,7 +831,7 @@ int resctrl_val(const struct resctrl_test *test,
 		sigsuspend(&sigact.sa_mask);
 
 		ksft_perror("Child is done");
-		PARENT_EXIT();
+		parent_exit(ppid);
 	}
 
 	ksft_print_msg("Benchmark PID: %d\n", (int)bm_pid);
@@ -894,7 +901,7 @@ int resctrl_val(const struct resctrl_test *test,
 
 		if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)) ||
 		    !strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR))) {
-			ret = measure_vals(uparams, param);
+			ret = measure_vals(uparams, param, bm_pid);
 			if (ret)
 				break;
 		} else if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) {

From d9c6c4b8b4505c4eed0f8ae11ea28595d84d8791 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Mon, 10 Jun 2024 18:14:48 +0300
Subject: [PATCH 196/236] selftests/resctrl: Rename measure_vals() to
 measure_mem_bw_vals() & document
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit bc074b6321d73295dcfe8c450c8f5245c530bb4e upstream.

measure_vals() is awfully generic name so rename it to measure_mem_bw()
to describe better what it does and document the function parameters.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/resctrl_val.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index 9a1855360c85a..2cdf5dfda879d 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -631,13 +631,18 @@ static void initialize_llc_occu_resctrl(const char *ctrlgrp, const char *mongrp,
 }
 
 /*
+ * measure_mem_bw - Measures memory bandwidth numbers while benchmark runs
+ * @uparams:		User supplied parameters
+ * @param:		Parameters passed to resctrl_val()
+ * @bm_pid:		PID that runs the benchmark
+ *
  * Measure memory bandwidth from resctrl and from another source which is
  * perf imc value or could be something else if perf imc event is not
  * available. Compare the two values to validate resctrl value. It takes
  * 1 sec to measure the data.
  */
-static int measure_vals(const struct user_params *uparams,
-			struct resctrl_val_param *param, pid_t bm_pid)
+static int measure_mem_bw(const struct user_params *uparams,
+			  struct resctrl_val_param *param, pid_t bm_pid)
 {
 	unsigned long bw_resc, bw_resc_start, bw_resc_end;
 	FILE *mem_bw_fp;
@@ -901,7 +906,7 @@ int resctrl_val(const struct resctrl_test *test,
 
 		if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)) ||
 		    !strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR))) {
-			ret = measure_vals(uparams, param, bm_pid);
+			ret = measure_mem_bw(uparams, param, bm_pid);
 			if (ret)
 				break;
 		} else if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) {

From be32a68d3678e830c5d83f7853f286fcc79dd249 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Mon, 10 Jun 2024 18:14:49 +0300
Subject: [PATCH 197/236] selftests/resctrl: Simplify mem bandwidth file code
 for MBA & MBM tests
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 711d27b05a97cd5c8e62c858c2c940d79f8445e1 upstream.

initialize_mem_bw_resctrl() and set_mbm_path() contain complicated set
of conditions, each yielding different file to be opened to measure
memory bandwidth through resctrl FS. In practice, only two of them are
used. For MBA test, ctrlgrp is always provided, and for MBM test both
ctrlgrp and mongrp are set.

The file used differ between MBA/MBM test, however, MBM test
unnecessarily create monitor group because resctrl FS already provides
monitoring interface underneath any ctrlgrp too, which is what the MBA
selftest uses.

Consolidate memory bandwidth file used to the one used by the MBA
selftest. Remove all unused branches opening other files to simplify
the code.

Suggested-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/mbm_test.c    |  1 -
 tools/testing/selftests/resctrl/resctrl_val.c | 45 ++-----------------
 2 files changed, 4 insertions(+), 42 deletions(-)

diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c
index 6fec51e1ff465..9fc162a0d5630 100644
--- a/tools/testing/selftests/resctrl/mbm_test.c
+++ b/tools/testing/selftests/resctrl/mbm_test.c
@@ -115,7 +115,6 @@ static int mbm_run_test(const struct resctrl_test *test, const struct user_param
 	struct resctrl_val_param param = {
 		.resctrl_val	= MBM_STR,
 		.ctrlgrp	= "c1",
-		.mongrp		= "m1",
 		.filename	= RESULT_FILE_NAME,
 		.bw_report	= "reads",
 		.setup		= mbm_setup
diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index 2cdf5dfda879d..04965e6407ee1 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -19,18 +19,10 @@
 #define MAX_TOKENS		5
 #define READ			0
 #define WRITE			1
-#define CON_MON_MBM_LOCAL_BYTES_PATH				\
-	"%s/%s/mon_groups/%s/mon_data/mon_L3_%02d/mbm_local_bytes"
 
 #define CON_MBM_LOCAL_BYTES_PATH		\
 	"%s/%s/mon_data/mon_L3_%02d/mbm_local_bytes"
 
-#define MON_MBM_LOCAL_BYTES_PATH		\
-	"%s/mon_groups/%s/mon_data/mon_L3_%02d/mbm_local_bytes"
-
-#define MBM_LOCAL_BYTES_PATH			\
-	"%s/mon_data/mon_L3_%02d/mbm_local_bytes"
-
 #define CON_MON_LCC_OCCUP_PATH		\
 	"%s/%s/mon_groups/%s/mon_data/mon_L3_%02d/llc_occupancy"
 
@@ -429,43 +421,15 @@ static int get_mem_bw_imc(char *bw_report, float *bw_imc)
 	return 0;
 }
 
-void set_mbm_path(const char *ctrlgrp, const char *mongrp, int domain_id)
-{
-	if (ctrlgrp && mongrp)
-		sprintf(mbm_total_path, CON_MON_MBM_LOCAL_BYTES_PATH,
-			RESCTRL_PATH, ctrlgrp, mongrp, domain_id);
-	else if (!ctrlgrp && mongrp)
-		sprintf(mbm_total_path, MON_MBM_LOCAL_BYTES_PATH, RESCTRL_PATH,
-			mongrp, domain_id);
-	else if (ctrlgrp && !mongrp)
-		sprintf(mbm_total_path, CON_MBM_LOCAL_BYTES_PATH, RESCTRL_PATH,
-			ctrlgrp, domain_id);
-	else if (!ctrlgrp && !mongrp)
-		sprintf(mbm_total_path, MBM_LOCAL_BYTES_PATH, RESCTRL_PATH,
-			domain_id);
-}
-
 /*
  * initialize_mem_bw_resctrl:	Appropriately populate "mbm_total_path"
  * @ctrlgrp:			Name of the control monitor group (con_mon grp)
- * @mongrp:			Name of the monitor group (mon grp)
  * @domain_id:			Domain ID (cache ID; for MB, L3 cache ID)
- * @resctrl_val:		Resctrl feature (Eg: mbm, mba.. etc)
  */
-static void initialize_mem_bw_resctrl(const char *ctrlgrp, const char *mongrp,
-				      int domain_id, char *resctrl_val)
+static void initialize_mem_bw_resctrl(const char *ctrlgrp, int domain_id)
 {
-	if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)))
-		set_mbm_path(ctrlgrp, mongrp, domain_id);
-
-	if (!strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR))) {
-		if (ctrlgrp)
-			sprintf(mbm_total_path, CON_MBM_LOCAL_BYTES_PATH,
-				RESCTRL_PATH, ctrlgrp, domain_id);
-		else
-			sprintf(mbm_total_path, MBM_LOCAL_BYTES_PATH,
-				RESCTRL_PATH, domain_id);
-	}
+	sprintf(mbm_total_path, CON_MBM_LOCAL_BYTES_PATH, RESCTRL_PATH,
+		ctrlgrp, domain_id);
 }
 
 /*
@@ -866,8 +830,7 @@ int resctrl_val(const struct resctrl_test *test,
 		if (ret)
 			goto out;
 
-		initialize_mem_bw_resctrl(param->ctrlgrp, param->mongrp,
-					  domain_id, resctrl_val);
+		initialize_mem_bw_resctrl(param->ctrlgrp, domain_id);
 	} else if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR)))
 		initialize_llc_occu_resctrl(param->ctrlgrp, param->mongrp,
 					    domain_id, resctrl_val);

From 9e056c721b6e55bffccd47a9a7e5c3fdeb94de46 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Mon, 10 Jun 2024 18:14:50 +0300
Subject: [PATCH 198/236] selftests/resctrl: Add ->measure() callback to
 resctrl_val_param
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 0e251816995a1972062fc7ad32047c1aee9cd704 upstream.

The measurement done in resctrl_val() varies depending on test type.
The decision for how to measure is decided based on the string compare
to test name which is quite inflexible.

Add ->measure() callback into the struct resctrl_val_param to allow
each test to provide necessary code as a function which simplifies what
resctrl_val() has to do.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cmt_test.c    |  8 ++++++++
 tools/testing/selftests/resctrl/mba_test.c    |  9 ++++++++-
 tools/testing/selftests/resctrl/mbm_test.c    |  9 ++++++++-
 tools/testing/selftests/resctrl/resctrl.h     |  6 ++++++
 tools/testing/selftests/resctrl/resctrl_val.c | 18 +++++-------------
 5 files changed, 35 insertions(+), 15 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c
index 0105afec6188a..f6cb258f873d8 100644
--- a/tools/testing/selftests/resctrl/cmt_test.c
+++ b/tools/testing/selftests/resctrl/cmt_test.c
@@ -29,6 +29,13 @@ static int cmt_setup(const struct resctrl_test *test,
 	return 0;
 }
 
+static int cmt_measure(const struct user_params *uparams,
+		       struct resctrl_val_param *param, pid_t bm_pid)
+{
+	sleep(1);
+	return measure_llc_resctrl(param->filename, bm_pid);
+}
+
 static int show_results_info(unsigned long sum_llc_val, int no_of_bits,
 			     unsigned long cache_span, unsigned long max_diff,
 			     unsigned long max_diff_percent, unsigned long num_of_runs,
@@ -133,6 +140,7 @@ static int cmt_run_test(const struct resctrl_test *test, const struct user_param
 		.mask		= ~(long_mask << n) & long_mask,
 		.num_of_runs	= 0,
 		.setup		= cmt_setup,
+		.measure	= cmt_measure,
 	};
 
 	span = cache_portion_size(cache_total_size, param.mask, long_mask);
diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c
index a6ad39aae1623..68d92c7c1cab2 100644
--- a/tools/testing/selftests/resctrl/mba_test.c
+++ b/tools/testing/selftests/resctrl/mba_test.c
@@ -51,6 +51,12 @@ static int mba_setup(const struct resctrl_test *test,
 	return 0;
 }
 
+static int mba_measure(const struct user_params *uparams,
+		       struct resctrl_val_param *param, pid_t bm_pid)
+{
+	return measure_mem_bw(uparams, param, bm_pid);
+}
+
 static bool show_mba_info(unsigned long *bw_imc, unsigned long *bw_resc)
 {
 	int allocation, runs;
@@ -150,7 +156,8 @@ static int mba_run_test(const struct resctrl_test *test, const struct user_param
 		.mongrp		= "m1",
 		.filename	= RESULT_FILE_NAME,
 		.bw_report	= "reads",
-		.setup		= mba_setup
+		.setup		= mba_setup,
+		.measure	= mba_measure,
 	};
 	int ret;
 
diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c
index 9fc162a0d5630..7c6f60b1dd186 100644
--- a/tools/testing/selftests/resctrl/mbm_test.c
+++ b/tools/testing/selftests/resctrl/mbm_test.c
@@ -105,6 +105,12 @@ static int mbm_setup(const struct resctrl_test *test,
 	return ret;
 }
 
+static int mbm_measure(const struct user_params *uparams,
+		       struct resctrl_val_param *param, pid_t bm_pid)
+{
+	return measure_mem_bw(uparams, param, bm_pid);
+}
+
 static void mbm_test_cleanup(void)
 {
 	remove(RESULT_FILE_NAME);
@@ -117,7 +123,8 @@ static int mbm_run_test(const struct resctrl_test *test, const struct user_param
 		.ctrlgrp	= "c1",
 		.filename	= RESULT_FILE_NAME,
 		.bw_report	= "reads",
-		.setup		= mbm_setup
+		.setup		= mbm_setup,
+		.measure	= mbm_measure,
 	};
 	int ret;
 
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index e4b6dc672ecc7..5dc3def706697 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -87,6 +87,7 @@ struct resctrl_test {
  * @filename:		Name of file to which the o/p should be written
  * @bw_report:		Bandwidth report type (reads vs writes)
  * @setup:		Call back function to setup test environment
+ * @measure:		Callback that performs the measurement (a single test)
  */
 struct resctrl_val_param {
 	char		*resctrl_val;
@@ -99,6 +100,9 @@ struct resctrl_val_param {
 	int		(*setup)(const struct resctrl_test *test,
 				 const struct user_params *uparams,
 				 struct resctrl_val_param *param);
+	int		(*measure)(const struct user_params *uparams,
+				   struct resctrl_val_param *param,
+				   pid_t bm_pid);
 };
 
 struct perf_event_read {
@@ -145,6 +149,8 @@ unsigned char *alloc_buffer(size_t buf_size, int memflush);
 void mem_flush(unsigned char *buf, size_t buf_size);
 void fill_cache_read(unsigned char *buf, size_t buf_size, bool once);
 int run_fill_buf(size_t buf_size, int memflush, int op, bool once);
+int measure_mem_bw(const struct user_params *uparams,
+		   struct resctrl_val_param *param, pid_t bm_pid);
 int resctrl_val(const struct resctrl_test *test,
 		const struct user_params *uparams,
 		const char * const *benchmark_cmd,
diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index 04965e6407ee1..b59679f0875ea 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -605,8 +605,8 @@ static void initialize_llc_occu_resctrl(const char *ctrlgrp, const char *mongrp,
  * available. Compare the two values to validate resctrl value. It takes
  * 1 sec to measure the data.
  */
-static int measure_mem_bw(const struct user_params *uparams,
-			  struct resctrl_val_param *param, pid_t bm_pid)
+int measure_mem_bw(const struct user_params *uparams,
+		   struct resctrl_val_param *param, pid_t bm_pid)
 {
 	unsigned long bw_resc, bw_resc_start, bw_resc_end;
 	FILE *mem_bw_fp;
@@ -867,17 +867,9 @@ int resctrl_val(const struct resctrl_test *test,
 		if (ret < 0)
 			break;
 
-		if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)) ||
-		    !strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR))) {
-			ret = measure_mem_bw(uparams, param, bm_pid);
-			if (ret)
-				break;
-		} else if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) {
-			sleep(1);
-			ret = measure_llc_resctrl(param->filename, bm_pid);
-			if (ret)
-				break;
-		}
+		ret = param->measure(uparams, param, bm_pid);
+		if (ret)
+			break;
 	}
 
 out:

From 6160a60dd4570e5a50a8e94ed4b7cfd9a3484445 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Mon, 10 Jun 2024 18:14:51 +0300
Subject: [PATCH 199/236] selftests/resctrl: Add ->init() callback into
 resctrl_val_param
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit aef5efa64426396cac5b0126cbb6071e92d5da24 upstream.

The struct resctrl_val_param is there to customize behavior inside
resctrl_val() which is currently not used to full extent and there are
number of strcmp()s for test name in resctrl_val done by resctrl_val().

Create ->init() hook into the struct resctrl_val_param to cleanly
do per test initialization.

Remove also unused branches to setup paths and the related #defines
for CMT test.

While touching kerneldoc, make the adjacent line consistent with the
newly added form (callback vs call back).

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cmt_test.c    | 12 +++
 tools/testing/selftests/resctrl/mba_test.c    | 14 ++++
 tools/testing/selftests/resctrl/mbm_test.c    | 14 ++++
 tools/testing/selftests/resctrl/resctrl.h     |  8 +-
 tools/testing/selftests/resctrl/resctrl_val.c | 75 ++++---------------
 5 files changed, 60 insertions(+), 63 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c
index f6cb258f873d8..491574c118053 100644
--- a/tools/testing/selftests/resctrl/cmt_test.c
+++ b/tools/testing/selftests/resctrl/cmt_test.c
@@ -16,6 +16,17 @@
 #define MAX_DIFF		2000000
 #define MAX_DIFF_PERCENT	15
 
+#define CON_MON_LCC_OCCUP_PATH		\
+	"%s/%s/mon_groups/%s/mon_data/mon_L3_%02d/llc_occupancy"
+
+static int cmt_init(const struct resctrl_val_param *param, int domain_id)
+{
+	sprintf(llc_occup_path, CON_MON_LCC_OCCUP_PATH, RESCTRL_PATH,
+		param->ctrlgrp, param->mongrp, domain_id);
+
+	return 0;
+}
+
 static int cmt_setup(const struct resctrl_test *test,
 		     const struct user_params *uparams,
 		     struct resctrl_val_param *p)
@@ -139,6 +150,7 @@ static int cmt_run_test(const struct resctrl_test *test, const struct user_param
 		.filename	= RESULT_FILE_NAME,
 		.mask		= ~(long_mask << n) & long_mask,
 		.num_of_runs	= 0,
+		.init		= cmt_init,
 		.setup		= cmt_setup,
 		.measure	= cmt_measure,
 	};
diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c
index 68d92c7c1cab2..20427bdb5c6d9 100644
--- a/tools/testing/selftests/resctrl/mba_test.c
+++ b/tools/testing/selftests/resctrl/mba_test.c
@@ -17,6 +17,19 @@
 #define ALLOCATION_MIN		10
 #define ALLOCATION_STEP		10
 
+static int mba_init(const struct resctrl_val_param *param, int domain_id)
+{
+	int ret;
+
+	ret = initialize_mem_bw_imc();
+	if (ret)
+		return ret;
+
+	initialize_mem_bw_resctrl(param, domain_id);
+
+	return 0;
+}
+
 /*
  * Change schemata percentage from 100 to 10%. Write schemata to specified
  * con_mon grp, mon_grp in resctrl FS.
@@ -156,6 +169,7 @@ static int mba_run_test(const struct resctrl_test *test, const struct user_param
 		.mongrp		= "m1",
 		.filename	= RESULT_FILE_NAME,
 		.bw_report	= "reads",
+		.init		= mba_init,
 		.setup		= mba_setup,
 		.measure	= mba_measure,
 	};
diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c
index 7c6f60b1dd186..adc205bf9e51a 100644
--- a/tools/testing/selftests/resctrl/mbm_test.c
+++ b/tools/testing/selftests/resctrl/mbm_test.c
@@ -86,6 +86,19 @@ static int check_results(size_t span)
 	return ret;
 }
 
+static int mbm_init(const struct resctrl_val_param *param, int domain_id)
+{
+	int ret;
+
+	ret = initialize_mem_bw_imc();
+	if (ret)
+		return ret;
+
+	initialize_mem_bw_resctrl(param, domain_id);
+
+	return 0;
+}
+
 static int mbm_setup(const struct resctrl_test *test,
 		     const struct user_params *uparams,
 		     struct resctrl_val_param *p)
@@ -123,6 +136,7 @@ static int mbm_run_test(const struct resctrl_test *test, const struct user_param
 		.ctrlgrp	= "c1",
 		.filename	= RESULT_FILE_NAME,
 		.bw_report	= "reads",
+		.init		= mbm_init,
 		.setup		= mbm_setup,
 		.measure	= mbm_measure,
 	};
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 5dc3def706697..d3fbb957309d6 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -86,7 +86,8 @@ struct resctrl_test {
  * @mongrp:		Name of the monitor group (mon grp)
  * @filename:		Name of file to which the o/p should be written
  * @bw_report:		Bandwidth report type (reads vs writes)
- * @setup:		Call back function to setup test environment
+ * @init:		Callback function to initialize test environment
+ * @setup:		Callback function to setup per test run environment
  * @measure:		Callback that performs the measurement (a single test)
  */
 struct resctrl_val_param {
@@ -97,6 +98,8 @@ struct resctrl_val_param {
 	char		*bw_report;
 	unsigned long	mask;
 	int		num_of_runs;
+	int		(*init)(const struct resctrl_val_param *param,
+				int domain_id);
 	int		(*setup)(const struct resctrl_test *test,
 				 const struct user_params *uparams,
 				 struct resctrl_val_param *param);
@@ -149,8 +152,11 @@ unsigned char *alloc_buffer(size_t buf_size, int memflush);
 void mem_flush(unsigned char *buf, size_t buf_size);
 void fill_cache_read(unsigned char *buf, size_t buf_size, bool once);
 int run_fill_buf(size_t buf_size, int memflush, int op, bool once);
+int initialize_mem_bw_imc(void);
 int measure_mem_bw(const struct user_params *uparams,
 		   struct resctrl_val_param *param, pid_t bm_pid);
+void initialize_mem_bw_resctrl(const struct resctrl_val_param *param,
+			       int domain_id);
 int resctrl_val(const struct resctrl_test *test,
 		const struct user_params *uparams,
 		const char * const *benchmark_cmd,
diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index b59679f0875ea..9cbdd7baa2a27 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -23,18 +23,6 @@
 #define CON_MBM_LOCAL_BYTES_PATH		\
 	"%s/%s/mon_data/mon_L3_%02d/mbm_local_bytes"
 
-#define CON_MON_LCC_OCCUP_PATH		\
-	"%s/%s/mon_groups/%s/mon_data/mon_L3_%02d/llc_occupancy"
-
-#define CON_LCC_OCCUP_PATH		\
-	"%s/%s/mon_data/mon_L3_%02d/llc_occupancy"
-
-#define MON_LCC_OCCUP_PATH		\
-	"%s/mon_groups/%s/mon_data/mon_L3_%02d/llc_occupancy"
-
-#define LCC_OCCUP_PATH			\
-	"%s/mon_data/mon_L3_%02d/llc_occupancy"
-
 struct membw_read_format {
 	__u64 value;         /* The value of the event */
 	__u64 time_enabled;  /* if PERF_FORMAT_TOTAL_TIME_ENABLED */
@@ -267,7 +255,7 @@ static int num_of_imcs(void)
 	return count;
 }
 
-static int initialize_mem_bw_imc(void)
+int initialize_mem_bw_imc(void)
 {
 	int imc, j;
 
@@ -423,24 +411,18 @@ static int get_mem_bw_imc(char *bw_report, float *bw_imc)
 
 /*
  * initialize_mem_bw_resctrl:	Appropriately populate "mbm_total_path"
- * @ctrlgrp:			Name of the control monitor group (con_mon grp)
- * @domain_id:			Domain ID (cache ID; for MB, L3 cache ID)
+ * @param:	Parameters passed to resctrl_val()
+ * @domain_id:	Domain ID (cache ID; for MB, L3 cache ID)
  */
-static void initialize_mem_bw_resctrl(const char *ctrlgrp, int domain_id)
+void initialize_mem_bw_resctrl(const struct resctrl_val_param *param,
+			       int domain_id)
 {
 	sprintf(mbm_total_path, CON_MBM_LOCAL_BYTES_PATH, RESCTRL_PATH,
-		ctrlgrp, domain_id);
+		param->ctrlgrp, domain_id);
 }
 
 /*
- * Get MBM Local bytes as reported by resctrl FS
- * For MBM,
- * 1. If con_mon grp and mon grp are given, then read from con_mon grp's mon grp
- * 2. If only con_mon grp is given, then read from con_mon grp
- * 3. If both are not given, then read from root con_mon grp
- * For MBA,
- * 1. If con_mon grp is given, then read from it
- * 2. If con_mon grp is not given, then read from root con_mon grp
+ * Open file to read MBM local bytes from resctrl FS
  */
 static FILE *open_mem_bw_resctrl(const char *mbm_bw_file)
 {
@@ -453,6 +435,9 @@ static FILE *open_mem_bw_resctrl(const char *mbm_bw_file)
 	return fp;
 }
 
+/*
+ * Get MBM Local bytes as reported by resctrl FS
+ */
 static int get_mem_bw_resctrl(FILE *fp, unsigned long *mbm_total)
 {
 	if (fscanf(fp, "%lu\n", mbm_total) <= 0) {
@@ -565,35 +550,6 @@ static int print_results_bw(char *filename, pid_t bm_pid, float bw_imc,
 	return 0;
 }
 
-static void set_cmt_path(const char *ctrlgrp, const char *mongrp, char sock_num)
-{
-	if (strlen(ctrlgrp) && strlen(mongrp))
-		sprintf(llc_occup_path,	CON_MON_LCC_OCCUP_PATH,	RESCTRL_PATH,
-			ctrlgrp, mongrp, sock_num);
-	else if (!strlen(ctrlgrp) && strlen(mongrp))
-		sprintf(llc_occup_path,	MON_LCC_OCCUP_PATH, RESCTRL_PATH,
-			mongrp, sock_num);
-	else if (strlen(ctrlgrp) && !strlen(mongrp))
-		sprintf(llc_occup_path,	CON_LCC_OCCUP_PATH, RESCTRL_PATH,
-			ctrlgrp, sock_num);
-	else if (!strlen(ctrlgrp) && !strlen(mongrp))
-		sprintf(llc_occup_path, LCC_OCCUP_PATH,	RESCTRL_PATH, sock_num);
-}
-
-/*
- * initialize_llc_occu_resctrl:	Appropriately populate "llc_occup_path"
- * @ctrlgrp:			Name of the control monitor group (con_mon grp)
- * @mongrp:			Name of the monitor group (mon grp)
- * @domain_id:			Domain ID (cache ID; for MB, L3 cache ID)
- * @resctrl_val:		Resctrl feature (Eg: cat, cmt.. etc)
- */
-static void initialize_llc_occu_resctrl(const char *ctrlgrp, const char *mongrp,
-					int domain_id, char *resctrl_val)
-{
-	if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR)))
-		set_cmt_path(ctrlgrp, mongrp, domain_id);
-}
-
 /*
  * measure_mem_bw - Measures memory bandwidth numbers while benchmark runs
  * @uparams:		User supplied parameters
@@ -824,16 +780,11 @@ int resctrl_val(const struct resctrl_test *test,
 	if (ret)
 		goto out;
 
-	if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)) ||
-	    !strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR))) {
-		ret = initialize_mem_bw_imc();
+	if (param->init) {
+		ret = param->init(param, domain_id);
 		if (ret)
 			goto out;
-
-		initialize_mem_bw_resctrl(param->ctrlgrp, domain_id);
-	} else if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR)))
-		initialize_llc_occu_resctrl(param->ctrlgrp, param->mongrp,
-					    domain_id, resctrl_val);
+	}
 
 	/* Parent waits for child to be ready. */
 	close(pipefd[1]);

From 1d7ed02eeae3c12ee363a28a4ca0f9f27f36acbe Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Mon, 10 Jun 2024 18:14:52 +0300
Subject: [PATCH 200/236] selftests/resctrl: Simplify bandwidth report type
 handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit fa1116d06ebc4673c4e8ca23d8e7ef73db544480 upstream.

bw_report is only needed for selecting the correct value from the
values IMC measured. It is a member in the resctrl_val_param struct and
is always set to "reads". The value is then checked in resctrl_val()
using validate_bw_report_request() that besides validating the input,
assumes it can mutate the string which is questionable programming
practice.

Simplify handling bw_report:

- Convert validate_bw_report_request() into get_bw_report_type() that
  inputs and returns const char *. Use NULL to indicate error.

- Validate the report types inside measure_mem_bw(), not in
  resctrl_val().

- Pass bw_report to measure_mem_bw() from ->measure() hook because
  resctrl_val() no longer needs bw_report for anything.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/mba_test.c    |  3 +--
 tools/testing/selftests/resctrl/mbm_test.c    |  3 +--
 tools/testing/selftests/resctrl/resctrl.h     |  7 +++----
 tools/testing/selftests/resctrl/resctrl_val.c | 19 +++++++++----------
 tools/testing/selftests/resctrl/resctrlfs.c   | 13 ++++++-------
 5 files changed, 20 insertions(+), 25 deletions(-)

diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c
index 20427bdb5c6d9..5538a0032c0e7 100644
--- a/tools/testing/selftests/resctrl/mba_test.c
+++ b/tools/testing/selftests/resctrl/mba_test.c
@@ -67,7 +67,7 @@ static int mba_setup(const struct resctrl_test *test,
 static int mba_measure(const struct user_params *uparams,
 		       struct resctrl_val_param *param, pid_t bm_pid)
 {
-	return measure_mem_bw(uparams, param, bm_pid);
+	return measure_mem_bw(uparams, param, bm_pid, "reads");
 }
 
 static bool show_mba_info(unsigned long *bw_imc, unsigned long *bw_resc)
@@ -168,7 +168,6 @@ static int mba_run_test(const struct resctrl_test *test, const struct user_param
 		.ctrlgrp	= "c1",
 		.mongrp		= "m1",
 		.filename	= RESULT_FILE_NAME,
-		.bw_report	= "reads",
 		.init		= mba_init,
 		.setup		= mba_setup,
 		.measure	= mba_measure,
diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c
index adc205bf9e51a..40eca4a9eec9b 100644
--- a/tools/testing/selftests/resctrl/mbm_test.c
+++ b/tools/testing/selftests/resctrl/mbm_test.c
@@ -121,7 +121,7 @@ static int mbm_setup(const struct resctrl_test *test,
 static int mbm_measure(const struct user_params *uparams,
 		       struct resctrl_val_param *param, pid_t bm_pid)
 {
-	return measure_mem_bw(uparams, param, bm_pid);
+	return measure_mem_bw(uparams, param, bm_pid, "reads");
 }
 
 static void mbm_test_cleanup(void)
@@ -135,7 +135,6 @@ static int mbm_run_test(const struct resctrl_test *test, const struct user_param
 		.resctrl_val	= MBM_STR,
 		.ctrlgrp	= "c1",
 		.filename	= RESULT_FILE_NAME,
-		.bw_report	= "reads",
 		.init		= mbm_init,
 		.setup		= mbm_setup,
 		.measure	= mbm_measure,
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index d3fbb957309d6..4446a0e493ef1 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -85,7 +85,6 @@ struct resctrl_test {
  * @ctrlgrp:		Name of the control monitor group (con_mon grp)
  * @mongrp:		Name of the monitor group (mon grp)
  * @filename:		Name of file to which the o/p should be written
- * @bw_report:		Bandwidth report type (reads vs writes)
  * @init:		Callback function to initialize test environment
  * @setup:		Callback function to setup per test run environment
  * @measure:		Callback that performs the measurement (a single test)
@@ -95,7 +94,6 @@ struct resctrl_val_param {
 	char		ctrlgrp[64];
 	char		mongrp[64];
 	char		filename[64];
-	char		*bw_report;
 	unsigned long	mask;
 	int		num_of_runs;
 	int		(*init)(const struct resctrl_val_param *param,
@@ -135,7 +133,7 @@ int filter_dmesg(void);
 int get_domain_id(const char *resource, int cpu_no, int *domain_id);
 int mount_resctrlfs(void);
 int umount_resctrlfs(void);
-int validate_bw_report_request(char *bw_report);
+const char *get_bw_report_type(const char *bw_report);
 bool resctrl_resource_exists(const char *resource);
 bool resctrl_mon_feature_exists(const char *resource, const char *feature);
 bool resource_info_file_exists(const char *resource, const char *file);
@@ -154,7 +152,8 @@ void fill_cache_read(unsigned char *buf, size_t buf_size, bool once);
 int run_fill_buf(size_t buf_size, int memflush, int op, bool once);
 int initialize_mem_bw_imc(void);
 int measure_mem_bw(const struct user_params *uparams,
-		   struct resctrl_val_param *param, pid_t bm_pid);
+		   struct resctrl_val_param *param, pid_t bm_pid,
+		   const char *bw_report);
 void initialize_mem_bw_resctrl(const struct resctrl_val_param *param,
 			       int domain_id);
 int resctrl_val(const struct resctrl_test *test,
diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index 9cbdd7baa2a27..f10bcd000912b 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -348,7 +348,7 @@ static void do_imc_mem_bw_test(void)
  *
  * Return: = 0 on success. < 0 on failure.
  */
-static int get_mem_bw_imc(char *bw_report, float *bw_imc)
+static int get_mem_bw_imc(const char *bw_report, float *bw_imc)
 {
 	float reads, writes, of_mul_read, of_mul_write;
 	int imc;
@@ -555,6 +555,7 @@ static int print_results_bw(char *filename, pid_t bm_pid, float bw_imc,
  * @uparams:		User supplied parameters
  * @param:		Parameters passed to resctrl_val()
  * @bm_pid:		PID that runs the benchmark
+ * @bw_report:		Bandwidth report type (reads, writes)
  *
  * Measure memory bandwidth from resctrl and from another source which is
  * perf imc value or could be something else if perf imc event is not
@@ -562,13 +563,18 @@ static int print_results_bw(char *filename, pid_t bm_pid, float bw_imc,
  * 1 sec to measure the data.
  */
 int measure_mem_bw(const struct user_params *uparams,
-		   struct resctrl_val_param *param, pid_t bm_pid)
+		   struct resctrl_val_param *param, pid_t bm_pid,
+		   const char *bw_report)
 {
 	unsigned long bw_resc, bw_resc_start, bw_resc_end;
 	FILE *mem_bw_fp;
 	float bw_imc;
 	int ret;
 
+	bw_report = get_bw_report_type(bw_report);
+	if (!bw_report)
+		return -1;
+
 	mem_bw_fp = open_mem_bw_resctrl(mbm_total_path);
 	if (!mem_bw_fp)
 		return -1;
@@ -589,7 +595,7 @@ int measure_mem_bw(const struct user_params *uparams,
 	if (ret < 0)
 		goto close_imc;
 
-	ret = get_mem_bw_imc(param->bw_report, &bw_imc);
+	ret = get_mem_bw_imc(bw_report, &bw_imc);
 	if (ret < 0)
 		goto close_imc;
 
@@ -693,13 +699,6 @@ int resctrl_val(const struct resctrl_test *test,
 		return ret;
 	}
 
-	if (!strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR)) ||
-	    !strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR))) {
-		ret = validate_bw_report_request(param->bw_report);
-		if (ret)
-			return ret;
-	}
-
 	/*
 	 * If benchmark wasn't successfully started by child, then child should
 	 * kill parent, so save parent's pid
diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index b6db95090e6ec..ec53b14c8412d 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -837,22 +837,21 @@ int filter_dmesg(void)
 	return 0;
 }
 
-int validate_bw_report_request(char *bw_report)
+const char *get_bw_report_type(const char *bw_report)
 {
 	if (strcmp(bw_report, "reads") == 0)
-		return 0;
+		return bw_report;
 	if (strcmp(bw_report, "writes") == 0)
-		return 0;
+		return bw_report;
 	if (strcmp(bw_report, "nt-writes") == 0) {
-		strcpy(bw_report, "writes");
-		return 0;
+		return "writes";
 	}
 	if (strcmp(bw_report, "total") == 0)
-		return 0;
+		return bw_report;
 
 	fprintf(stderr, "Requested iMC bandwidth report type unavailable\n");
 
-	return -1;
+	return NULL;
 }
 
 int perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu,

From 40703f56cf3aafb9bba8636550f3537b5150b9d9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Mon, 10 Jun 2024 18:14:53 +0300
Subject: [PATCH 201/236] selftests/resctrl: Make some strings passed to
 resctrlfs functions const
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 909592b5dafa3680994b1d5144b6d5781eb49ab8 upstream.

Control group, monitor group and resctrl_val are not mutated and
should not be mutated within resctrlfs.c functions.

Mark this by using const char * for the arguments.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/resctrl.h   | 7 ++++---
 tools/testing/selftests/resctrl/resctrlfs.c | 7 ++++---
 2 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 4446a0e493ef1..5967389038d4b 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -141,9 +141,10 @@ bool test_resource_feature_check(const struct resctrl_test *test);
 char *fgrep(FILE *inf, const char *str);
 int taskset_benchmark(pid_t bm_pid, int cpu_no, cpu_set_t *old_affinity);
 int taskset_restore(pid_t bm_pid, cpu_set_t *old_affinity);
-int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, const char *resource);
-int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp,
-			    char *resctrl_val);
+int write_schemata(const char *ctrlgrp, char *schemata, int cpu_no,
+		   const char *resource);
+int write_bm_pid_to_resctrl(pid_t bm_pid, const char *ctrlgrp,
+			    const char *mongrp, const char *resctrl_val);
 int perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu,
 		    int group_fd, unsigned long flags);
 unsigned char *alloc_buffer(size_t buf_size, int memflush);
diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index ec53b14c8412d..7c7da32606575 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -534,8 +534,8 @@ static int write_pid_to_tasks(char *tasks, pid_t pid)
  *
  * Return: 0 on success, < 0 on error.
  */
-int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp,
-			    char *resctrl_val)
+int write_bm_pid_to_resctrl(pid_t bm_pid, const char *ctrlgrp,
+			    const char *mongrp, const char *resctrl_val)
 {
 	char controlgroup[128], monitorgroup[512], monitorgroup_p[256];
 	char tasks[1024];
@@ -593,7 +593,8 @@ int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp,
  *
  * Return: 0 on success, < 0 on error.
  */
-int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, const char *resource)
+int write_schemata(const char *ctrlgrp, char *schemata, int cpu_no,
+		   const char *resource)
 {
 	char controlgroup[1024], reason[128], schema[1024] = {};
 	int domain_id, fd, schema_len, ret = 0;

From 9265db5114ebaa7a2f0f3c77a9589002dcea83a3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Mon, 10 Jun 2024 18:14:54 +0300
Subject: [PATCH 202/236] selftests/resctrl: Convert ctrlgrp & mongrp to
 pointers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit d14d94da0e3f1d7e598f88204cf37ee41a06f900 upstream.

The struct resctrl_val_param has control and monitor groups as char
arrays but they are not supposed to be mutated within resctrl_val().

Convert the ctrlgrp and mongrp char array within resctrl_val_param to
plain const char pointers and adjust the strlen() based checks to
check NULL instead.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/resctrl.h   |  4 ++--
 tools/testing/selftests/resctrl/resctrlfs.c | 16 +++++++---------
 2 files changed, 9 insertions(+), 11 deletions(-)

diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 5967389038d4b..a999fbc13fd32 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -91,8 +91,8 @@ struct resctrl_test {
  */
 struct resctrl_val_param {
 	char		*resctrl_val;
-	char		ctrlgrp[64];
-	char		mongrp[64];
+	const char	*ctrlgrp;
+	const char	*mongrp;
 	char		filename[64];
 	unsigned long	mask;
 	int		num_of_runs;
diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index 7c7da32606575..7acb30b421209 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -456,6 +456,9 @@ int taskset_restore(pid_t bm_pid, cpu_set_t *old_affinity)
  * @grp:	Full path and name of the group
  * @parent_grp:	Full path and name of the parent group
  *
+ * Creates a group @grp_name if it does not exist yet. If @grp_name is NULL,
+ * it is interpreted as the root group which always results in success.
+ *
  * Return: 0 on success, < 0 on error.
  */
 static int create_grp(const char *grp_name, char *grp, const char *parent_grp)
@@ -464,12 +467,7 @@ static int create_grp(const char *grp_name, char *grp, const char *parent_grp)
 	struct dirent *ep;
 	DIR *dp;
 
-	/*
-	 * At this point, we are guaranteed to have resctrl FS mounted and if
-	 * length of grp_name == 0, it means, user wants to use root con_mon
-	 * grp, so do nothing
-	 */
-	if (strlen(grp_name) == 0)
+	if (!grp_name)
 		return 0;
 
 	/* Check if requested grp exists or not */
@@ -541,7 +539,7 @@ int write_bm_pid_to_resctrl(pid_t bm_pid, const char *ctrlgrp,
 	char tasks[1024];
 	int ret = 0;
 
-	if (strlen(ctrlgrp))
+	if (ctrlgrp)
 		sprintf(controlgroup, "%s/%s", RESCTRL_PATH, ctrlgrp);
 	else
 		sprintf(controlgroup, "%s", RESCTRL_PATH);
@@ -558,7 +556,7 @@ int write_bm_pid_to_resctrl(pid_t bm_pid, const char *ctrlgrp,
 	/* Create mon grp and write pid into it for "mbm" and "cmt" test */
 	if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR)) ||
 	    !strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR))) {
-		if (strlen(mongrp)) {
+		if (mongrp) {
 			sprintf(monitorgroup_p, "%s/mon_groups", controlgroup);
 			sprintf(monitorgroup, "%s/%s", monitorgroup_p, mongrp);
 			ret = create_grp(mongrp, monitorgroup, monitorgroup_p);
@@ -612,7 +610,7 @@ int write_schemata(const char *ctrlgrp, char *schemata, int cpu_no,
 		goto out;
 	}
 
-	if (strlen(ctrlgrp) != 0)
+	if (ctrlgrp)
 		sprintf(controlgroup, "%s/%s/schemata", RESCTRL_PATH, ctrlgrp);
 	else
 		sprintf(controlgroup, "%s/schemata", RESCTRL_PATH);

From 6b844f45b43b9f5477ba780a8e4230d55b9268ce Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Mon, 10 Jun 2024 18:14:55 +0300
Subject: [PATCH 203/236] selftests/resctrl: Remove mongrp from MBA test
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 64b0795192a8f7fa6baaeda2631a4134aa2c7e12 upstream.

Nothing during MBA test uses mongrp even if it has been defined ever
since the introduction of the MBA test in the commit 01fee6b4d1f9
("selftests/resctrl: Add MBA test").

Remove the mongrp from MBA test.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/mba_test.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c
index 5538a0032c0e7..725227caf1c72 100644
--- a/tools/testing/selftests/resctrl/mba_test.c
+++ b/tools/testing/selftests/resctrl/mba_test.c
@@ -166,7 +166,6 @@ static int mba_run_test(const struct resctrl_test *test, const struct user_param
 	struct resctrl_val_param param = {
 		.resctrl_val	= MBA_STR,
 		.ctrlgrp	= "c1",
-		.mongrp		= "m1",
 		.filename	= RESULT_FILE_NAME,
 		.init		= mba_init,
 		.setup		= mba_setup,

From 9e6cf499b42e79ed47554265a8bce82feced7bf3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Mon, 10 Jun 2024 18:14:56 +0300
Subject: [PATCH 204/236] selftests/resctrl: Remove mongrp from CMT test
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit f58e66bed1b4563c8afd35d43dbd4fd361705789 upstream.

The CMT selftest instantiates a monitor group to read LLC occupancy.
Since the test also creates a control group, it is unnecessary to
create another one for monitoring because control groups already
provide monitoring too.

Remove the unnecessary monitor group from the CMT selftest.

Suggested-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cmt_test.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c
index 491574c118053..2713263a001e8 100644
--- a/tools/testing/selftests/resctrl/cmt_test.c
+++ b/tools/testing/selftests/resctrl/cmt_test.c
@@ -17,12 +17,12 @@
 #define MAX_DIFF_PERCENT	15
 
 #define CON_MON_LCC_OCCUP_PATH		\
-	"%s/%s/mon_groups/%s/mon_data/mon_L3_%02d/llc_occupancy"
+	"%s/%s/mon_data/mon_L3_%02d/llc_occupancy"
 
 static int cmt_init(const struct resctrl_val_param *param, int domain_id)
 {
 	sprintf(llc_occup_path, CON_MON_LCC_OCCUP_PATH, RESCTRL_PATH,
-		param->ctrlgrp, param->mongrp, domain_id);
+		param->ctrlgrp, domain_id);
 
 	return 0;
 }
@@ -146,7 +146,6 @@ static int cmt_run_test(const struct resctrl_test *test, const struct user_param
 	struct resctrl_val_param param = {
 		.resctrl_val	= CMT_STR,
 		.ctrlgrp	= "c1",
-		.mongrp		= "m1",
 		.filename	= RESULT_FILE_NAME,
 		.mask		= ~(long_mask << n) & long_mask,
 		.num_of_runs	= 0,

From 137b3d5cf60f62b6ca816d0e19b916115db3a9ce Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Mon, 10 Jun 2024 18:14:57 +0300
Subject: [PATCH 205/236] selftests/resctrl: Remove test name comparing from
 write_bm_pid_to_resctrl()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 0d66ddb296cc46d7b72d67cfaef0de03da092fcd upstream.

write_bm_pid_to_resctrl() uses resctrl_val to check test name which is
not a good interface generic resctrl FS functions should provide.

Tests define mongrp when needed. Remove the test name check in
write_bm_pid_to_resctrl() to only rely on the mongrp parameter being
non-NULL.

Remove write_bm_pid_to_resctrl() resctrl_val parameter and resctrl_val
member from the struct resctrl_val_param that are not used anymore.
Similarly, remove the test name constants that are no longer used.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cat_test.c    |  5 +--
 tools/testing/selftests/resctrl/cmt_test.c    |  1 -
 tools/testing/selftests/resctrl/mba_test.c    |  1 -
 tools/testing/selftests/resctrl/mbm_test.c    |  1 -
 tools/testing/selftests/resctrl/resctrl.h     | 10 +-----
 tools/testing/selftests/resctrl/resctrl_val.c |  4 +--
 tools/testing/selftests/resctrl/resctrlfs.c   | 33 ++++++++-----------
 7 files changed, 17 insertions(+), 38 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
index 55315ed695f47..742782438ca3b 100644
--- a/tools/testing/selftests/resctrl/cat_test.c
+++ b/tools/testing/selftests/resctrl/cat_test.c
@@ -158,7 +158,6 @@ static int cat_test(const struct resctrl_test *test,
 		    struct resctrl_val_param *param,
 		    size_t span, unsigned long current_mask)
 {
-	char *resctrl_val = param->resctrl_val;
 	struct perf_event_read pe_read;
 	struct perf_event_attr pea;
 	cpu_set_t old_affinity;
@@ -178,8 +177,7 @@ static int cat_test(const struct resctrl_test *test,
 		return ret;
 
 	/* Write benchmark to specified con_mon grp, mon_grp in resctrl FS*/
-	ret = write_bm_pid_to_resctrl(bm_pid, param->ctrlgrp, param->mongrp,
-				      resctrl_val);
+	ret = write_bm_pid_to_resctrl(bm_pid, param->ctrlgrp, param->mongrp);
 	if (ret)
 		goto reset_affinity;
 
@@ -272,7 +270,6 @@ static int cat_run_test(const struct resctrl_test *test, const struct user_param
 	start_mask = create_bit_mask(start, n);
 
 	struct resctrl_val_param param = {
-		.resctrl_val	= CAT_STR,
 		.ctrlgrp	= "c1",
 		.filename	= RESULT_FILE_NAME,
 		.num_of_runs	= 0,
diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c
index 2713263a001e8..0c045080d8085 100644
--- a/tools/testing/selftests/resctrl/cmt_test.c
+++ b/tools/testing/selftests/resctrl/cmt_test.c
@@ -144,7 +144,6 @@ static int cmt_run_test(const struct resctrl_test *test, const struct user_param
 	}
 
 	struct resctrl_val_param param = {
-		.resctrl_val	= CMT_STR,
 		.ctrlgrp	= "c1",
 		.filename	= RESULT_FILE_NAME,
 		.mask		= ~(long_mask << n) & long_mask,
diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c
index 725227caf1c72..ab8496a4925b4 100644
--- a/tools/testing/selftests/resctrl/mba_test.c
+++ b/tools/testing/selftests/resctrl/mba_test.c
@@ -164,7 +164,6 @@ static void mba_test_cleanup(void)
 static int mba_run_test(const struct resctrl_test *test, const struct user_params *uparams)
 {
 	struct resctrl_val_param param = {
-		.resctrl_val	= MBA_STR,
 		.ctrlgrp	= "c1",
 		.filename	= RESULT_FILE_NAME,
 		.init		= mba_init,
diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c
index 40eca4a9eec9b..6b5a3b52d861b 100644
--- a/tools/testing/selftests/resctrl/mbm_test.c
+++ b/tools/testing/selftests/resctrl/mbm_test.c
@@ -132,7 +132,6 @@ static void mbm_test_cleanup(void)
 static int mbm_run_test(const struct resctrl_test *test, const struct user_params *uparams)
 {
 	struct resctrl_val_param param = {
-		.resctrl_val	= MBM_STR,
 		.ctrlgrp	= "c1",
 		.filename	= RESULT_FILE_NAME,
 		.init		= mbm_init,
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index a999fbc13fd32..2dda560845880 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -81,7 +81,6 @@ struct resctrl_test {
 
 /*
  * resctrl_val_param:	resctrl test parameters
- * @resctrl_val:	Resctrl feature (Eg: mbm, mba.. etc)
  * @ctrlgrp:		Name of the control monitor group (con_mon grp)
  * @mongrp:		Name of the monitor group (mon grp)
  * @filename:		Name of file to which the o/p should be written
@@ -90,7 +89,6 @@ struct resctrl_test {
  * @measure:		Callback that performs the measurement (a single test)
  */
 struct resctrl_val_param {
-	char		*resctrl_val;
 	const char	*ctrlgrp;
 	const char	*mongrp;
 	char		filename[64];
@@ -113,11 +111,6 @@ struct perf_event_read {
 	} values[2];
 };
 
-#define MBM_STR			"mbm"
-#define MBA_STR			"mba"
-#define CMT_STR			"cmt"
-#define CAT_STR			"cat"
-
 /*
  * Memory location that consumes values compiler must not optimize away.
  * Volatile ensures writes to this location cannot be optimized away by
@@ -143,8 +136,7 @@ int taskset_benchmark(pid_t bm_pid, int cpu_no, cpu_set_t *old_affinity);
 int taskset_restore(pid_t bm_pid, cpu_set_t *old_affinity);
 int write_schemata(const char *ctrlgrp, char *schemata, int cpu_no,
 		   const char *resource);
-int write_bm_pid_to_resctrl(pid_t bm_pid, const char *ctrlgrp,
-			    const char *mongrp, const char *resctrl_val);
+int write_bm_pid_to_resctrl(pid_t bm_pid, const char *ctrlgrp, const char *mongrp);
 int perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu,
 		    int group_fd, unsigned long flags);
 unsigned char *alloc_buffer(size_t buf_size, int memflush);
diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index f10bcd000912b..e92e4f463f37b 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -683,7 +683,6 @@ int resctrl_val(const struct resctrl_test *test,
 		const char * const *benchmark_cmd,
 		struct resctrl_val_param *param)
 {
-	char *resctrl_val = param->resctrl_val;
 	struct sigaction sigact;
 	int ret = 0, pipefd[2];
 	char pipe_message = 0;
@@ -774,8 +773,7 @@ int resctrl_val(const struct resctrl_test *test,
 		goto out;
 
 	/* Write benchmark to specified control&monitoring grp in resctrl FS */
-	ret = write_bm_pid_to_resctrl(bm_pid, param->ctrlgrp, param->mongrp,
-				      resctrl_val);
+	ret = write_bm_pid_to_resctrl(bm_pid, param->ctrlgrp, param->mongrp);
 	if (ret)
 		goto out;
 
diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index 7acb30b421209..a53cd1cb6e0c6 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -522,7 +522,6 @@ static int write_pid_to_tasks(char *tasks, pid_t pid)
  * @bm_pid:		PID that should be written
  * @ctrlgrp:		Name of the control monitor group (con_mon grp)
  * @mongrp:		Name of the monitor group (mon grp)
- * @resctrl_val:	Resctrl feature (Eg: mbm, mba.. etc)
  *
  * If a con_mon grp is requested, create it and write pid to it, otherwise
  * write pid to root con_mon grp.
@@ -532,8 +531,7 @@ static int write_pid_to_tasks(char *tasks, pid_t pid)
  *
  * Return: 0 on success, < 0 on error.
  */
-int write_bm_pid_to_resctrl(pid_t bm_pid, const char *ctrlgrp,
-			    const char *mongrp, const char *resctrl_val)
+int write_bm_pid_to_resctrl(pid_t bm_pid, const char *ctrlgrp, const char *mongrp)
 {
 	char controlgroup[128], monitorgroup[512], monitorgroup_p[256];
 	char tasks[1024];
@@ -553,22 +551,19 @@ int write_bm_pid_to_resctrl(pid_t bm_pid, const char *ctrlgrp,
 	if (ret)
 		goto out;
 
-	/* Create mon grp and write pid into it for "mbm" and "cmt" test */
-	if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR)) ||
-	    !strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR))) {
-		if (mongrp) {
-			sprintf(monitorgroup_p, "%s/mon_groups", controlgroup);
-			sprintf(monitorgroup, "%s/%s", monitorgroup_p, mongrp);
-			ret = create_grp(mongrp, monitorgroup, monitorgroup_p);
-			if (ret)
-				goto out;
-
-			sprintf(tasks, "%s/mon_groups/%s/tasks",
-				controlgroup, mongrp);
-			ret = write_pid_to_tasks(tasks, bm_pid);
-			if (ret)
-				goto out;
-		}
+	/* Create monitor group and write pid into if it is used */
+	if (mongrp) {
+		sprintf(monitorgroup_p, "%s/mon_groups", controlgroup);
+		sprintf(monitorgroup, "%s/%s", monitorgroup_p, mongrp);
+		ret = create_grp(mongrp, monitorgroup, monitorgroup_p);
+		if (ret)
+			goto out;
+
+		sprintf(tasks, "%s/mon_groups/%s/tasks",
+			controlgroup, mongrp);
+		ret = write_pid_to_tasks(tasks, bm_pid);
+		if (ret)
+			goto out;
 	}
 
 out:

From 801837ff92d8734139ca3539102eb5a9f87fc574 Mon Sep 17 00:00:00 2001
From: Shuah Khan <skhan@linuxfoundation.org>
Date: Thu, 5 Sep 2024 12:02:31 -0600
Subject: [PATCH 206/236] selftests:resctrl: Fix build failure on archs without
 __cpuid_count()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 7beaf1da074f7ea25454d6c11da142c3892d3c4e upstream.

When resctrl is built on architectures without __cpuid_count()
support, build fails. resctrl uses __cpuid_count() defined in
kselftest.h.

Even though the problem is seen while building resctrl on aarch64,
this error can be seen on any platform that doesn't support CPUID.

CPUID is a x86/x86-64 feature and code paths with CPUID asm commands
will fail to build on all other architectures.

All others tests call __cpuid_count() do so from x86/x86_64 code paths
when _i386__ or __x86_64__ are defined. resctrl is an exception.

Fix the problem by defining __cpuid_count() only when __i386__ or
__x86_64__ are defined in kselftest.h and changing resctrl to call
__cpuid_count() only when __i386__ or __x86_64__ are defined.

In file included from resctrl.h:24,
                 from cat_test.c:11:
In function ‘arch_supports_noncont_cat’,
    inlined from ‘noncont_cat_run_test’ at cat_test.c:326:6:
../kselftest.h:74:9: error: impossible constraint in ‘asm’
   74 |         __asm__ __volatile__ ("cpuid\n\t"                               \
      |         ^~~~~~~
cat_test.c:304:17: note: in expansion of macro ‘__cpuid_count’
  304 |                 __cpuid_count(0x10, 1, eax, ebx, ecx, edx);
      |                 ^~~~~~~~~~~~~
../kselftest.h:74:9: error: impossible constraint in ‘asm’
   74 |         __asm__ __volatile__ ("cpuid\n\t"                               \
      |         ^~~~~~~
cat_test.c:306:17: note: in expansion of macro ‘__cpuid_count’
  306 |                 __cpuid_count(0x10, 2, eax, ebx, ecx, edx);

Fixes: ae638551ab64 ("selftests/resctrl: Add non-contiguous CBMs CAT test")
Reported-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Closes: https://lore.kernel.org/lkml/20240809071059.265914-1-usama.anjum@collabora.com/
Reported-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Acked-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/kselftest.h        | 2 ++
 tools/testing/selftests/resctrl/cat_test.c | 7 +++++--
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h
index ad7b97e16f37e..5cc84e0e78617 100644
--- a/tools/testing/selftests/kselftest.h
+++ b/tools/testing/selftests/kselftest.h
@@ -57,6 +57,7 @@
 #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
 #endif
 
+#if defined(__i386__) || defined(__x86_64__) /* arch */
 /*
  * gcc cpuid.h provides __cpuid_count() since v4.4.
  * Clang/LLVM cpuid.h provides  __cpuid_count() since v3.4.0.
@@ -71,6 +72,7 @@
 			      : "=a" (a), "=b" (b), "=c" (c), "=d" (d)	\
 			      : "0" (level), "2" (count))
 #endif
+#endif /* end arch */
 
 /* define kselftest exit codes */
 #define KSFT_PASS  0
diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
index 742782438ca3b..94cfdba5308d8 100644
--- a/tools/testing/selftests/resctrl/cat_test.c
+++ b/tools/testing/selftests/resctrl/cat_test.c
@@ -290,12 +290,12 @@ static int cat_run_test(const struct resctrl_test *test, const struct user_param
 
 static bool arch_supports_noncont_cat(const struct resctrl_test *test)
 {
-	unsigned int eax, ebx, ecx, edx;
-
 	/* AMD always supports non-contiguous CBM. */
 	if (get_vendor() == ARCH_AMD)
 		return true;
 
+#if defined(__i386__) || defined(__x86_64__) /* arch */
+	unsigned int eax, ebx, ecx, edx;
 	/* Intel support for non-contiguous CBM needs to be discovered. */
 	if (!strcmp(test->resource, "L3"))
 		__cpuid_count(0x10, 1, eax, ebx, ecx, edx);
@@ -305,6 +305,9 @@ static bool arch_supports_noncont_cat(const struct resctrl_test *test)
 		return false;
 
 	return ((ecx >> 3) & 1);
+#endif /* end arch */
+
+	return false;
 }
 
 static int noncont_cat_run_test(const struct resctrl_test *test,

From fce188c0036690a4fe3e592d9b45e6b875f6e207 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Thu, 24 Oct 2024 14:18:38 -0700
Subject: [PATCH 207/236] selftests/resctrl: Make functions only used in same
 file static
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 18f5744e8200e3c2bfeb896d6d3c10c3f0946318 upstream.

Fix following sparse warnings:
 tools/testing/selftests/resctrl/resctrl_val.c:47:6: warning: symbol 'membw_initialize_perf_event_attr' was not declared. Should it be static?
 tools/testing/selftests/resctrl/resctrl_val.c:64:6: warning: symbol 'membw_ioctl_perf_event_ioc_reset_enable' was not declared. Should it be
static?
 tools/testing/selftests/resctrl/resctrl_val.c:70:6: warning: symbol 'membw_ioctl_perf_event_ioc_disable' was not declared. Should it be static?
 tools/testing/selftests/resctrl/resctrl_val.c:81:6: warning: symbol 'get_event_and_umask' was not declared. Should it be static?

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/resctrl_val.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index e92e4f463f37b..c9dd70ce3ea87 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -44,7 +44,7 @@ static int imcs;
 static struct imc_counter_config imc_counters_config[MAX_IMCS][2];
 static const struct resctrl_test *current_test;
 
-void membw_initialize_perf_event_attr(int i, int j)
+static void membw_initialize_perf_event_attr(int i, int j)
 {
 	memset(&imc_counters_config[i][j].pe, 0,
 	       sizeof(struct perf_event_attr));
@@ -61,13 +61,13 @@ void membw_initialize_perf_event_attr(int i, int j)
 		PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING;
 }
 
-void membw_ioctl_perf_event_ioc_reset_enable(int i, int j)
+static void membw_ioctl_perf_event_ioc_reset_enable(int i, int j)
 {
 	ioctl(imc_counters_config[i][j].fd, PERF_EVENT_IOC_RESET, 0);
 	ioctl(imc_counters_config[i][j].fd, PERF_EVENT_IOC_ENABLE, 0);
 }
 
-void membw_ioctl_perf_event_ioc_disable(int i, int j)
+static void membw_ioctl_perf_event_ioc_disable(int i, int j)
 {
 	ioctl(imc_counters_config[i][j].fd, PERF_EVENT_IOC_DISABLE, 0);
 }
@@ -78,7 +78,7 @@ void membw_ioctl_perf_event_ioc_disable(int i, int j)
  * @count:		iMC number
  * @op:			Operation (read/write)
  */
-void get_event_and_umask(char *cas_count_cfg, int count, bool op)
+static void get_event_and_umask(char *cas_count_cfg, int count, bool op)
 {
 	char *token[MAX_TOKENS];
 	int i = 0;

From 826d035b508fa2ae33a2917e9148253d1cbb208f Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Thu, 24 Oct 2024 14:18:39 -0700
Subject: [PATCH 208/236] selftests/resctrl: Print accurate buffer size as part
 of MBM results
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 1b4840395f08e9723a15fea42c2d31090e8375f3 upstream.

By default the MBM test uses the "fill_buf" benchmark to keep reading
from a buffer with size DEFAULT_SPAN while measuring memory bandwidth.
User space can provide an alternate benchmark or amend the size of
the buffer "fill_buf" should use.

Analysis of the MBM measurements do not require that a buffer be used
and thus do not require knowing the size of the buffer if it was used
during testing. Even so, the buffer size is printed as informational
as part of the MBM test results. What is printed as buffer size is
hardcoded as DEFAULT_SPAN, even if the test relied on another benchmark
(that may or may not use a buffer) or if user space amended the buffer
size.

Ensure that accurate buffer size is printed when using "fill_buf"
benchmark and omit the buffer size information if another benchmark
is used.

Fixes: ecdbb911f22d ("selftests/resctrl: Add MBM test")
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/mbm_test.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c
index 6b5a3b52d861b..cf08ba5e314e2 100644
--- a/tools/testing/selftests/resctrl/mbm_test.c
+++ b/tools/testing/selftests/resctrl/mbm_test.c
@@ -40,7 +40,8 @@ show_bw_info(unsigned long *bw_imc, unsigned long *bw_resc, size_t span)
 	ksft_print_msg("%s Check MBM diff within %d%%\n",
 		       ret ? "Fail:" : "Pass:", MAX_DIFF_PERCENT);
 	ksft_print_msg("avg_diff_per: %d%%\n", avg_diff_per);
-	ksft_print_msg("Span (MB): %zu\n", span / MB);
+	if (span)
+		ksft_print_msg("Span (MB): %zu\n", span / MB);
 	ksft_print_msg("avg_bw_imc: %lu\n", avg_bw_imc);
 	ksft_print_msg("avg_bw_resc: %lu\n", avg_bw_resc);
 
@@ -138,15 +139,26 @@ static int mbm_run_test(const struct resctrl_test *test, const struct user_param
 		.setup		= mbm_setup,
 		.measure	= mbm_measure,
 	};
+	char *endptr = NULL;
+	size_t span = 0;
 	int ret;
 
 	remove(RESULT_FILE_NAME);
 
+	if (uparams->benchmark_cmd[0] && strcmp(uparams->benchmark_cmd[0], "fill_buf") == 0) {
+		if (uparams->benchmark_cmd[1] && *uparams->benchmark_cmd[1] != '\0') {
+			errno = 0;
+			span = strtoul(uparams->benchmark_cmd[1], &endptr, 10);
+			if (errno || *endptr != '\0')
+				return -EINVAL;
+		}
+	}
+
 	ret = resctrl_val(test, uparams, uparams->benchmark_cmd, &param);
 	if (ret)
 		return ret;
 
-	ret = check_results(DEFAULT_SPAN);
+	ret = check_results(span);
 	if (ret && (get_vendor() == ARCH_INTEL))
 		ksft_print_msg("Intel MBM may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n");
 

From 6bbcd19e5b19d200a3a5df7c3b482f0364d49dfb Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Thu, 24 Oct 2024 14:18:43 -0700
Subject: [PATCH 209/236] selftests/resctrl: Make wraparound handling obvious
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit efffa8c40166af680959c030a815afa8d06af66a upstream.

Within mba_setup() the programmed bandwidth delay value starts
at the maximum (100, or rather ALLOCATION_MAX) and progresses
towards ALLOCATION_MIN by decrementing with ALLOCATION_STEP.

The programmed bandwidth delay should never be negative, so
representing it with an unsigned int is most appropriate. This
may introduce confusion because of the "allocation > ALLOCATION_MAX"
check used to check wraparound of the subtraction.

Modify the mba_setup() flow to start at the minimum, ALLOCATION_MIN,
and incrementally, with ALLOCATION_STEP steps, adjust the
bandwidth delay value. This avoids wraparound while making the purpose
of "allocation > ALLOCATION_MAX" clear and eliminates the
need for the "allocation < ALLOCATION_MIN" check.

Reported-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Closes: https://lore.kernel.org/lkml/1903ac13-5c9c-ef8d-78e0-417ac34a971b@linux.intel.com/
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/mba_test.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c
index ab8496a4925b4..da40a8ed44138 100644
--- a/tools/testing/selftests/resctrl/mba_test.c
+++ b/tools/testing/selftests/resctrl/mba_test.c
@@ -39,7 +39,8 @@ static int mba_setup(const struct resctrl_test *test,
 		     const struct user_params *uparams,
 		     struct resctrl_val_param *p)
 {
-	static int runs_per_allocation, allocation = 100;
+	static unsigned int allocation = ALLOCATION_MIN;
+	static int runs_per_allocation;
 	char allocation_str[64];
 	int ret;
 
@@ -50,7 +51,7 @@ static int mba_setup(const struct resctrl_test *test,
 	if (runs_per_allocation++ != 0)
 		return 0;
 
-	if (allocation < ALLOCATION_MIN || allocation > ALLOCATION_MAX)
+	if (allocation > ALLOCATION_MAX)
 		return END_OF_TESTS;
 
 	sprintf(allocation_str, "%d", allocation);
@@ -59,7 +60,7 @@ static int mba_setup(const struct resctrl_test *test,
 	if (ret < 0)
 		return ret;
 
-	allocation -= ALLOCATION_STEP;
+	allocation += ALLOCATION_STEP;
 
 	return 0;
 }
@@ -72,8 +73,9 @@ static int mba_measure(const struct user_params *uparams,
 
 static bool show_mba_info(unsigned long *bw_imc, unsigned long *bw_resc)
 {
-	int allocation, runs;
+	unsigned int allocation;
 	bool ret = false;
+	int runs;
 
 	ksft_print_msg("Results are displayed in (MB)\n");
 	/* Memory bandwidth from 100% down to 10% */
@@ -103,7 +105,7 @@ static bool show_mba_info(unsigned long *bw_imc, unsigned long *bw_resc)
 			       avg_diff_per > MAX_DIFF_PERCENT ?
 			       "Fail:" : "Pass:",
 			       MAX_DIFF_PERCENT,
-			       ALLOCATION_MAX - ALLOCATION_STEP * allocation);
+			       ALLOCATION_MIN + ALLOCATION_STEP * allocation);
 
 		ksft_print_msg("avg_diff_per: %d%%\n", avg_diff_per);
 		ksft_print_msg("avg_bw_imc: %lu\n", avg_bw_imc);

From 92bed072ff3785fb3d8587d092a4679abe2d4d1b Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Thu, 24 Oct 2024 14:18:44 -0700
Subject: [PATCH 210/236] selftests/resctrl: Remove "once" parameter required
 to be false
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit f3069136c95f15c05d166281cbb55f0509a42ae1 upstream.

The CMT, MBM, and MBA tests rely on a benchmark that runs while
the test makes changes to needed configuration (for example memory
bandwidth allocation) and takes needed measurements. By default
the "fill_buf" benchmark is used and by default (via its
"once = false" setting) "fill_buf" is configured to run until
terminated after the test completes.

An unintended consequence of enabling the user to override the
benchmark also enables the user to change parameters to the
"fill_buf" benchmark. This enables the user to set "fill_buf" to
only cycle through the buffer once (by setting "once = true")
and thus breaking the CMT, MBA, and MBM tests that expect
workload/interference to be reflected by their measurements.

Prevent user space from changing the "once" parameter and ensure
that it is always false for the CMT, MBA, and MBM tests.

Suggested-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/fill_buf.c      |  7 ++++---
 tools/testing/selftests/resctrl/resctrl.h       |  2 +-
 tools/testing/selftests/resctrl/resctrl_tests.c |  9 +++++++--
 tools/testing/selftests/resctrl/resctrl_val.c   | 11 +----------
 4 files changed, 13 insertions(+), 16 deletions(-)

diff --git a/tools/testing/selftests/resctrl/fill_buf.c b/tools/testing/selftests/resctrl/fill_buf.c
index 34e5df721430e..854f0108d8e62 100644
--- a/tools/testing/selftests/resctrl/fill_buf.c
+++ b/tools/testing/selftests/resctrl/fill_buf.c
@@ -151,7 +151,7 @@ unsigned char *alloc_buffer(size_t buf_size, int memflush)
 	return buf;
 }
 
-int run_fill_buf(size_t buf_size, int memflush, int op, bool once)
+int run_fill_buf(size_t buf_size, int memflush, int op)
 {
 	unsigned char *buf;
 
@@ -160,9 +160,10 @@ int run_fill_buf(size_t buf_size, int memflush, int op, bool once)
 		return -1;
 
 	if (op == 0)
-		fill_cache_read(buf, buf_size, once);
+		fill_cache_read(buf, buf_size, false);
 	else
-		fill_cache_write(buf, buf_size, once);
+		fill_cache_write(buf, buf_size, false);
+
 	free(buf);
 
 	return 0;
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 2dda560845880..51f5f4b25e066 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -142,7 +142,7 @@ int perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu,
 unsigned char *alloc_buffer(size_t buf_size, int memflush);
 void mem_flush(unsigned char *buf, size_t buf_size);
 void fill_cache_read(unsigned char *buf, size_t buf_size, bool once);
-int run_fill_buf(size_t buf_size, int memflush, int op, bool once);
+int run_fill_buf(size_t buf_size, int memflush, int op);
 int initialize_mem_bw_imc(void);
 int measure_mem_bw(const struct user_params *uparams,
 		   struct resctrl_val_param *param, pid_t bm_pid,
diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c
index ecbb7605a9815..e7878077883f0 100644
--- a/tools/testing/selftests/resctrl/resctrl_tests.c
+++ b/tools/testing/selftests/resctrl/resctrl_tests.c
@@ -266,8 +266,13 @@ int main(int argc, char **argv)
 		uparams.benchmark_cmd[1] = span_str;
 		uparams.benchmark_cmd[2] = "1";
 		uparams.benchmark_cmd[3] = "0";
-		uparams.benchmark_cmd[4] = "false";
-		uparams.benchmark_cmd[5] = NULL;
+		/*
+		 * Fourth parameter was previously used to indicate
+		 * how long "fill_buf" should run for, with "false"
+		 * ("fill_buf" will keep running until terminated)
+		 * the only option that works.
+		 */
+		uparams.benchmark_cmd[4] = NULL;
 	}
 
 	ksft_set_plan(tests);
diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index c9dd70ce3ea87..b0f3c594c4da4 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -625,7 +625,6 @@ static void run_benchmark(int signum, siginfo_t *info, void *ucontext)
 	int operation, ret, memflush;
 	char **benchmark_cmd;
 	size_t span;
-	bool once;
 	FILE *fp;
 
 	benchmark_cmd = info->si_ptr;
@@ -645,16 +644,8 @@ static void run_benchmark(int signum, siginfo_t *info, void *ucontext)
 		span = strtoul(benchmark_cmd[1], NULL, 10);
 		memflush =  atoi(benchmark_cmd[2]);
 		operation = atoi(benchmark_cmd[3]);
-		if (!strcmp(benchmark_cmd[4], "true")) {
-			once = true;
-		} else if (!strcmp(benchmark_cmd[4], "false")) {
-			once = false;
-		} else {
-			ksft_print_msg("Invalid once parameter\n");
-			parent_exit(ppid);
-		}
 
-		if (run_fill_buf(span, memflush, operation, once))
+		if (run_fill_buf(span, memflush, operation))
 			fprintf(stderr, "Error in running fill buffer\n");
 	} else {
 		/* Execute specified benchmark */

From cf64af9303dfc974760818d44627aa0d9423202b Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Thu, 24 Oct 2024 14:18:45 -0700
Subject: [PATCH 211/236] selftests/resctrl: Only support measured read
 operation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 138424170eb06c956bc7e77e8740479161f65463 upstream.

The CMT, MBM, and MBA tests rely on a benchmark to generate
memory traffic. By default this is the "fill_buf" benchmark that
can be replaced via the "-b" command line argument.

The original intent of the "-b" command line parameter was
to replace the default "fill_buf" benchmark, but the implementation
also exposes an alternative use case where the "fill_buf" parameters
itself can be modified. One of the parameters to "fill_buf" is the
"operation" that can be either "read" or "write" and indicates
whether the "fill_buf" should use "read" or "write" operations on the
allocated buffer.

While replacing "fill_buf" default parameters is technically possible,
replacing the default "read" parameter with "write" is not supported
because the MBA and MBM tests only measure "read" operations. The
"read" operation is also most appropriate for the CMT test that aims
to use the benchmark to allocate into the cache.

Avoid any potential inconsistencies between test and measurement by
removing code for unsupported "write" operations to the buffer.
Ignore any attempt from user space to enable this unsupported test
configuration, instead always use read operations.

Keep the initialization of the, now unused, "fill_buf" parameters
to reserve these parameter positions since it has been exposed as an API.
Future parameter additions cannot use these parameter positions.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/fill_buf.c    | 28 ++-----------------
 tools/testing/selftests/resctrl/resctrl.h     |  2 +-
 .../testing/selftests/resctrl/resctrl_tests.c |  5 +++-
 tools/testing/selftests/resctrl/resctrl_val.c |  5 ++--
 4 files changed, 9 insertions(+), 31 deletions(-)

diff --git a/tools/testing/selftests/resctrl/fill_buf.c b/tools/testing/selftests/resctrl/fill_buf.c
index 854f0108d8e62..e4f1cea317f12 100644
--- a/tools/testing/selftests/resctrl/fill_buf.c
+++ b/tools/testing/selftests/resctrl/fill_buf.c
@@ -88,18 +88,6 @@ static int fill_one_span_read(unsigned char *buf, size_t buf_size)
 	return sum;
 }
 
-static void fill_one_span_write(unsigned char *buf, size_t buf_size)
-{
-	unsigned char *end_ptr = buf + buf_size;
-	unsigned char *p;
-
-	p = buf;
-	while (p < end_ptr) {
-		*p = '1';
-		p += (CL_SIZE / 2);
-	}
-}
-
 void fill_cache_read(unsigned char *buf, size_t buf_size, bool once)
 {
 	int ret = 0;
@@ -114,15 +102,6 @@ void fill_cache_read(unsigned char *buf, size_t buf_size, bool once)
 	*value_sink = ret;
 }
 
-static void fill_cache_write(unsigned char *buf, size_t buf_size, bool once)
-{
-	while (1) {
-		fill_one_span_write(buf, buf_size);
-		if (once)
-			break;
-	}
-}
-
 unsigned char *alloc_buffer(size_t buf_size, int memflush)
 {
 	void *buf = NULL;
@@ -151,7 +130,7 @@ unsigned char *alloc_buffer(size_t buf_size, int memflush)
 	return buf;
 }
 
-int run_fill_buf(size_t buf_size, int memflush, int op)
+int run_fill_buf(size_t buf_size, int memflush)
 {
 	unsigned char *buf;
 
@@ -159,10 +138,7 @@ int run_fill_buf(size_t buf_size, int memflush, int op)
 	if (!buf)
 		return -1;
 
-	if (op == 0)
-		fill_cache_read(buf, buf_size, false);
-	else
-		fill_cache_write(buf, buf_size, false);
+	fill_cache_read(buf, buf_size, false);
 
 	free(buf);
 
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 51f5f4b25e066..ba1ce1b356992 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -142,7 +142,7 @@ int perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu,
 unsigned char *alloc_buffer(size_t buf_size, int memflush);
 void mem_flush(unsigned char *buf, size_t buf_size);
 void fill_cache_read(unsigned char *buf, size_t buf_size, bool once);
-int run_fill_buf(size_t buf_size, int memflush, int op);
+int run_fill_buf(size_t buf_size, int memflush);
 int initialize_mem_bw_imc(void);
 int measure_mem_bw(const struct user_params *uparams,
 		   struct resctrl_val_param *param, pid_t bm_pid,
diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c
index e7878077883f0..0f91c475b255a 100644
--- a/tools/testing/selftests/resctrl/resctrl_tests.c
+++ b/tools/testing/selftests/resctrl/resctrl_tests.c
@@ -265,13 +265,16 @@ int main(int argc, char **argv)
 			ksft_exit_fail_msg("Out of memory!\n");
 		uparams.benchmark_cmd[1] = span_str;
 		uparams.benchmark_cmd[2] = "1";
-		uparams.benchmark_cmd[3] = "0";
 		/*
+		 * Third parameter was previously used for "operation"
+		 * (read/write) of which only (now default) "read"/"0"
+		 * works.
 		 * Fourth parameter was previously used to indicate
 		 * how long "fill_buf" should run for, with "false"
 		 * ("fill_buf" will keep running until terminated)
 		 * the only option that works.
 		 */
+		uparams.benchmark_cmd[3] = NULL;
 		uparams.benchmark_cmd[4] = NULL;
 	}
 
diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index b0f3c594c4da4..113ca18d67c16 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -622,8 +622,8 @@ int measure_mem_bw(const struct user_params *uparams,
  */
 static void run_benchmark(int signum, siginfo_t *info, void *ucontext)
 {
-	int operation, ret, memflush;
 	char **benchmark_cmd;
+	int ret, memflush;
 	size_t span;
 	FILE *fp;
 
@@ -643,9 +643,8 @@ static void run_benchmark(int signum, siginfo_t *info, void *ucontext)
 		/* Execute default fill_buf benchmark */
 		span = strtoul(benchmark_cmd[1], NULL, 10);
 		memflush =  atoi(benchmark_cmd[2]);
-		operation = atoi(benchmark_cmd[3]);
 
-		if (run_fill_buf(span, memflush, operation))
+		if (run_fill_buf(span, memflush))
 			fprintf(stderr, "Error in running fill buffer\n");
 	} else {
 		/* Execute specified benchmark */

From 4aa5167a6a66f7ea4e01cfcabc03924592d0a6b9 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Thu, 24 Oct 2024 14:18:46 -0700
Subject: [PATCH 212/236] selftests/resctrl: Remove unused measurement code
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 76f8f009f6bc89fd08edae69ccc705a9781fe42e upstream.

The MBM and MBA resctrl selftests run a benchmark during which
it takes measurements of read memory bandwidth via perf.
Code exists to support measurements of write memory bandwidth
but there exists no path with which this code can execute.

While code exists for write memory bandwidth measurement
there has not yet been a use case for it. Remove this unused code.
Rename relevant functions to include "read" so that it is clear
that it relates only to memory bandwidth reads, while renaming
the functions also add consistency by changing the "membw"
instances to more prevalent "mem_bw".

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/mba_test.c    |   4 +-
 tools/testing/selftests/resctrl/mbm_test.c    |   4 +-
 tools/testing/selftests/resctrl/resctrl.h     |   8 +-
 tools/testing/selftests/resctrl/resctrl_val.c | 234 ++++++------------
 tools/testing/selftests/resctrl/resctrlfs.c   |  17 --
 5 files changed, 85 insertions(+), 182 deletions(-)

diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c
index da40a8ed44138..be0ead73e55da 100644
--- a/tools/testing/selftests/resctrl/mba_test.c
+++ b/tools/testing/selftests/resctrl/mba_test.c
@@ -21,7 +21,7 @@ static int mba_init(const struct resctrl_val_param *param, int domain_id)
 {
 	int ret;
 
-	ret = initialize_mem_bw_imc();
+	ret = initialize_read_mem_bw_imc();
 	if (ret)
 		return ret;
 
@@ -68,7 +68,7 @@ static int mba_setup(const struct resctrl_test *test,
 static int mba_measure(const struct user_params *uparams,
 		       struct resctrl_val_param *param, pid_t bm_pid)
 {
-	return measure_mem_bw(uparams, param, bm_pid, "reads");
+	return measure_read_mem_bw(uparams, param, bm_pid);
 }
 
 static bool show_mba_info(unsigned long *bw_imc, unsigned long *bw_resc)
diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c
index cf08ba5e314e2..defa942939157 100644
--- a/tools/testing/selftests/resctrl/mbm_test.c
+++ b/tools/testing/selftests/resctrl/mbm_test.c
@@ -91,7 +91,7 @@ static int mbm_init(const struct resctrl_val_param *param, int domain_id)
 {
 	int ret;
 
-	ret = initialize_mem_bw_imc();
+	ret = initialize_read_mem_bw_imc();
 	if (ret)
 		return ret;
 
@@ -122,7 +122,7 @@ static int mbm_setup(const struct resctrl_test *test,
 static int mbm_measure(const struct user_params *uparams,
 		       struct resctrl_val_param *param, pid_t bm_pid)
 {
-	return measure_mem_bw(uparams, param, bm_pid, "reads");
+	return measure_read_mem_bw(uparams, param, bm_pid);
 }
 
 static void mbm_test_cleanup(void)
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index ba1ce1b356992..82801245e4c15 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -126,7 +126,6 @@ int filter_dmesg(void);
 int get_domain_id(const char *resource, int cpu_no, int *domain_id);
 int mount_resctrlfs(void);
 int umount_resctrlfs(void);
-const char *get_bw_report_type(const char *bw_report);
 bool resctrl_resource_exists(const char *resource);
 bool resctrl_mon_feature_exists(const char *resource, const char *feature);
 bool resource_info_file_exists(const char *resource, const char *file);
@@ -143,10 +142,9 @@ unsigned char *alloc_buffer(size_t buf_size, int memflush);
 void mem_flush(unsigned char *buf, size_t buf_size);
 void fill_cache_read(unsigned char *buf, size_t buf_size, bool once);
 int run_fill_buf(size_t buf_size, int memflush);
-int initialize_mem_bw_imc(void);
-int measure_mem_bw(const struct user_params *uparams,
-		   struct resctrl_val_param *param, pid_t bm_pid,
-		   const char *bw_report);
+int initialize_read_mem_bw_imc(void);
+int measure_read_mem_bw(const struct user_params *uparams,
+			struct resctrl_val_param *param, pid_t bm_pid);
 void initialize_mem_bw_resctrl(const struct resctrl_val_param *param,
 			       int domain_id);
 int resctrl_val(const struct resctrl_test *test,
diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index 113ca18d67c16..c4ebf70a46ef9 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -12,13 +12,10 @@
 
 #define UNCORE_IMC		"uncore_imc"
 #define READ_FILE_NAME		"events/cas_count_read"
-#define WRITE_FILE_NAME		"events/cas_count_write"
 #define DYN_PMU_PATH		"/sys/bus/event_source/devices"
 #define SCALE			0.00006103515625
 #define MAX_IMCS		20
 #define MAX_TOKENS		5
-#define READ			0
-#define WRITE			1
 
 #define CON_MBM_LOCAL_BYTES_PATH		\
 	"%s/%s/mon_data/mon_L3_%02d/mbm_local_bytes"
@@ -41,44 +38,43 @@ struct imc_counter_config {
 
 static char mbm_total_path[1024];
 static int imcs;
-static struct imc_counter_config imc_counters_config[MAX_IMCS][2];
+static struct imc_counter_config imc_counters_config[MAX_IMCS];
 static const struct resctrl_test *current_test;
 
-static void membw_initialize_perf_event_attr(int i, int j)
+static void read_mem_bw_initialize_perf_event_attr(int i)
 {
-	memset(&imc_counters_config[i][j].pe, 0,
+	memset(&imc_counters_config[i].pe, 0,
 	       sizeof(struct perf_event_attr));
-	imc_counters_config[i][j].pe.type = imc_counters_config[i][j].type;
-	imc_counters_config[i][j].pe.size = sizeof(struct perf_event_attr);
-	imc_counters_config[i][j].pe.disabled = 1;
-	imc_counters_config[i][j].pe.inherit = 1;
-	imc_counters_config[i][j].pe.exclude_guest = 0;
-	imc_counters_config[i][j].pe.config =
-		imc_counters_config[i][j].umask << 8 |
-		imc_counters_config[i][j].event;
-	imc_counters_config[i][j].pe.sample_type = PERF_SAMPLE_IDENTIFIER;
-	imc_counters_config[i][j].pe.read_format =
+	imc_counters_config[i].pe.type = imc_counters_config[i].type;
+	imc_counters_config[i].pe.size = sizeof(struct perf_event_attr);
+	imc_counters_config[i].pe.disabled = 1;
+	imc_counters_config[i].pe.inherit = 1;
+	imc_counters_config[i].pe.exclude_guest = 0;
+	imc_counters_config[i].pe.config =
+		imc_counters_config[i].umask << 8 |
+		imc_counters_config[i].event;
+	imc_counters_config[i].pe.sample_type = PERF_SAMPLE_IDENTIFIER;
+	imc_counters_config[i].pe.read_format =
 		PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING;
 }
 
-static void membw_ioctl_perf_event_ioc_reset_enable(int i, int j)
+static void read_mem_bw_ioctl_perf_event_ioc_reset_enable(int i)
 {
-	ioctl(imc_counters_config[i][j].fd, PERF_EVENT_IOC_RESET, 0);
-	ioctl(imc_counters_config[i][j].fd, PERF_EVENT_IOC_ENABLE, 0);
+	ioctl(imc_counters_config[i].fd, PERF_EVENT_IOC_RESET, 0);
+	ioctl(imc_counters_config[i].fd, PERF_EVENT_IOC_ENABLE, 0);
 }
 
-static void membw_ioctl_perf_event_ioc_disable(int i, int j)
+static void read_mem_bw_ioctl_perf_event_ioc_disable(int i)
 {
-	ioctl(imc_counters_config[i][j].fd, PERF_EVENT_IOC_DISABLE, 0);
+	ioctl(imc_counters_config[i].fd, PERF_EVENT_IOC_DISABLE, 0);
 }
 
 /*
- * get_event_and_umask:	Parse config into event and umask
+ * get_read_event_and_umask:	Parse config into event and umask
  * @cas_count_cfg:	Config
  * @count:		iMC number
- * @op:			Operation (read/write)
  */
-static void get_event_and_umask(char *cas_count_cfg, int count, bool op)
+static void get_read_event_and_umask(char *cas_count_cfg, int count)
 {
 	char *token[MAX_TOKENS];
 	int i = 0;
@@ -91,34 +87,22 @@ static void get_event_and_umask(char *cas_count_cfg, int count, bool op)
 	for (i = 0; i < MAX_TOKENS - 1; i++) {
 		if (!token[i])
 			break;
-		if (strcmp(token[i], "event") == 0) {
-			if (op == READ)
-				imc_counters_config[count][READ].event =
-				strtol(token[i + 1], NULL, 16);
-			else
-				imc_counters_config[count][WRITE].event =
-				strtol(token[i + 1], NULL, 16);
-		}
-		if (strcmp(token[i], "umask") == 0) {
-			if (op == READ)
-				imc_counters_config[count][READ].umask =
-				strtol(token[i + 1], NULL, 16);
-			else
-				imc_counters_config[count][WRITE].umask =
-				strtol(token[i + 1], NULL, 16);
-		}
+		if (strcmp(token[i], "event") == 0)
+			imc_counters_config[count].event = strtol(token[i + 1], NULL, 16);
+		if (strcmp(token[i], "umask") == 0)
+			imc_counters_config[count].umask = strtol(token[i + 1], NULL, 16);
 	}
 }
 
-static int open_perf_event(int i, int cpu_no, int j)
+static int open_perf_read_event(int i, int cpu_no)
 {
-	imc_counters_config[i][j].fd =
-		perf_event_open(&imc_counters_config[i][j].pe, -1, cpu_no, -1,
+	imc_counters_config[i].fd =
+		perf_event_open(&imc_counters_config[i].pe, -1, cpu_no, -1,
 				PERF_FLAG_FD_CLOEXEC);
 
-	if (imc_counters_config[i][j].fd == -1) {
+	if (imc_counters_config[i].fd == -1) {
 		fprintf(stderr, "Error opening leader %llx\n",
-			imc_counters_config[i][j].pe.config);
+			imc_counters_config[i].pe.config);
 
 		return -1;
 	}
@@ -126,7 +110,7 @@ static int open_perf_event(int i, int cpu_no, int j)
 	return 0;
 }
 
-/* Get type and config (read and write) of an iMC counter */
+/* Get type and config of an iMC counter's read event. */
 static int read_from_imc_dir(char *imc_dir, int count)
 {
 	char cas_count_cfg[1024], imc_counter_cfg[1024], imc_counter_type[1024];
@@ -140,7 +124,7 @@ static int read_from_imc_dir(char *imc_dir, int count)
 
 		return -1;
 	}
-	if (fscanf(fp, "%u", &imc_counters_config[count][READ].type) <= 0) {
+	if (fscanf(fp, "%u", &imc_counters_config[count].type) <= 0) {
 		ksft_perror("Could not get iMC type");
 		fclose(fp);
 
@@ -148,9 +132,6 @@ static int read_from_imc_dir(char *imc_dir, int count)
 	}
 	fclose(fp);
 
-	imc_counters_config[count][WRITE].type =
-				imc_counters_config[count][READ].type;
-
 	/* Get read config */
 	sprintf(imc_counter_cfg, "%s%s", imc_dir, READ_FILE_NAME);
 	fp = fopen(imc_counter_cfg, "r");
@@ -167,34 +148,19 @@ static int read_from_imc_dir(char *imc_dir, int count)
 	}
 	fclose(fp);
 
-	get_event_and_umask(cas_count_cfg, count, READ);
-
-	/* Get write config */
-	sprintf(imc_counter_cfg, "%s%s", imc_dir, WRITE_FILE_NAME);
-	fp = fopen(imc_counter_cfg, "r");
-	if (!fp) {
-		ksft_perror("Failed to open iMC config file");
-
-		return -1;
-	}
-	if  (fscanf(fp, "%1023s", cas_count_cfg) <= 0) {
-		ksft_perror("Could not get iMC cas count write");
-		fclose(fp);
-
-		return -1;
-	}
-	fclose(fp);
-
-	get_event_and_umask(cas_count_cfg, count, WRITE);
+	get_read_event_and_umask(cas_count_cfg, count);
 
 	return 0;
 }
 
 /*
  * A system can have 'n' number of iMC (Integrated Memory Controller)
- * counters, get that 'n'. For each iMC counter get it's type and config.
- * Also, each counter has two configs, one for read and the other for write.
- * A config again has two parts, event and umask.
+ * counters, get that 'n'. Discover the properties of the available
+ * counters in support of needed performance measurement via perf.
+ * For each iMC counter get it's type and config. Also obtain each
+ * counter's event and umask for the memory read events that will be
+ * measured.
+ *
  * Enumerate all these details into an array of structures.
  *
  * Return: >= 0 on success. < 0 on failure.
@@ -255,55 +221,46 @@ static int num_of_imcs(void)
 	return count;
 }
 
-int initialize_mem_bw_imc(void)
+int initialize_read_mem_bw_imc(void)
 {
-	int imc, j;
+	int imc;
 
 	imcs = num_of_imcs();
 	if (imcs <= 0)
 		return imcs;
 
 	/* Initialize perf_event_attr structures for all iMC's */
-	for (imc = 0; imc < imcs; imc++) {
-		for (j = 0; j < 2; j++)
-			membw_initialize_perf_event_attr(imc, j);
-	}
+	for (imc = 0; imc < imcs; imc++)
+		read_mem_bw_initialize_perf_event_attr(imc);
 
 	return 0;
 }
 
-static void perf_close_imc_mem_bw(void)
+static void perf_close_imc_read_mem_bw(void)
 {
 	int mc;
 
 	for (mc = 0; mc < imcs; mc++) {
-		if (imc_counters_config[mc][READ].fd != -1)
-			close(imc_counters_config[mc][READ].fd);
-		if (imc_counters_config[mc][WRITE].fd != -1)
-			close(imc_counters_config[mc][WRITE].fd);
+		if (imc_counters_config[mc].fd != -1)
+			close(imc_counters_config[mc].fd);
 	}
 }
 
 /*
- * perf_open_imc_mem_bw - Open perf fds for IMCs
+ * perf_open_imc_read_mem_bw - Open perf fds for IMCs
  * @cpu_no: CPU number that the benchmark PID is bound to
  *
  * Return: = 0 on success. < 0 on failure.
  */
-static int perf_open_imc_mem_bw(int cpu_no)
+static int perf_open_imc_read_mem_bw(int cpu_no)
 {
 	int imc, ret;
 
-	for (imc = 0; imc < imcs; imc++) {
-		imc_counters_config[imc][READ].fd = -1;
-		imc_counters_config[imc][WRITE].fd = -1;
-	}
+	for (imc = 0; imc < imcs; imc++)
+		imc_counters_config[imc].fd = -1;
 
 	for (imc = 0; imc < imcs; imc++) {
-		ret = open_perf_event(imc, cpu_no, READ);
-		if (ret)
-			goto close_fds;
-		ret = open_perf_event(imc, cpu_no, WRITE);
+		ret = open_perf_read_event(imc, cpu_no);
 		if (ret)
 			goto close_fds;
 	}
@@ -311,60 +268,52 @@ static int perf_open_imc_mem_bw(int cpu_no)
 	return 0;
 
 close_fds:
-	perf_close_imc_mem_bw();
+	perf_close_imc_read_mem_bw();
 	return -1;
 }
 
 /*
- * do_mem_bw_test - Perform memory bandwidth test
+ * do_imc_read_mem_bw_test - Perform memory bandwidth test
  *
  * Runs memory bandwidth test over one second period. Also, handles starting
  * and stopping of the IMC perf counters around the test.
  */
-static void do_imc_mem_bw_test(void)
+static void do_imc_read_mem_bw_test(void)
 {
 	int imc;
 
-	for (imc = 0; imc < imcs; imc++) {
-		membw_ioctl_perf_event_ioc_reset_enable(imc, READ);
-		membw_ioctl_perf_event_ioc_reset_enable(imc, WRITE);
-	}
+	for (imc = 0; imc < imcs; imc++)
+		read_mem_bw_ioctl_perf_event_ioc_reset_enable(imc);
 
 	sleep(1);
 
-	/* Stop counters after a second to get results (both read and write) */
-	for (imc = 0; imc < imcs; imc++) {
-		membw_ioctl_perf_event_ioc_disable(imc, READ);
-		membw_ioctl_perf_event_ioc_disable(imc, WRITE);
-	}
+	/* Stop counters after a second to get results. */
+	for (imc = 0; imc < imcs; imc++)
+		read_mem_bw_ioctl_perf_event_ioc_disable(imc);
 }
 
 /*
- * get_mem_bw_imc - Memory bandwidth as reported by iMC counters
- * @bw_report: Bandwidth report type (reads, writes)
+ * get_read_mem_bw_imc - Memory read bandwidth as reported by iMC counters
  *
- * Memory bandwidth utilized by a process on a socket can be calculated
- * using iMC counters. Perf events are used to read these counters.
+ * Memory read bandwidth utilized by a process on a socket can be calculated
+ * using iMC counters' read events. Perf events are used to read these
+ * counters.
  *
  * Return: = 0 on success. < 0 on failure.
  */
-static int get_mem_bw_imc(const char *bw_report, float *bw_imc)
+static int get_read_mem_bw_imc(float *bw_imc)
 {
-	float reads, writes, of_mul_read, of_mul_write;
+	float reads = 0, of_mul_read = 1;
 	int imc;
 
-	/* Start all iMC counters to log values (both read and write) */
-	reads = 0, writes = 0, of_mul_read = 1, of_mul_write = 1;
-
 	/*
-	 * Get results which are stored in struct type imc_counter_config
+	 * Log read event values from all iMC counters into
+	 * struct imc_counter_config.
 	 * Take overflow into consideration before calculating total bandwidth.
 	 */
 	for (imc = 0; imc < imcs; imc++) {
 		struct imc_counter_config *r =
-			&imc_counters_config[imc][READ];
-		struct imc_counter_config *w =
-			&imc_counters_config[imc][WRITE];
+			&imc_counters_config[imc];
 
 		if (read(r->fd, &r->return_value,
 			 sizeof(struct membw_read_format)) == -1) {
@@ -372,12 +321,6 @@ static int get_mem_bw_imc(const char *bw_report, float *bw_imc)
 			return -1;
 		}
 
-		if (read(w->fd, &w->return_value,
-			 sizeof(struct membw_read_format)) == -1) {
-			ksft_perror("Couldn't get write bandwidth through iMC");
-			return -1;
-		}
-
 		__u64 r_time_enabled = r->return_value.time_enabled;
 		__u64 r_time_running = r->return_value.time_running;
 
@@ -385,27 +328,10 @@ static int get_mem_bw_imc(const char *bw_report, float *bw_imc)
 			of_mul_read = (float)r_time_enabled /
 					(float)r_time_running;
 
-		__u64 w_time_enabled = w->return_value.time_enabled;
-		__u64 w_time_running = w->return_value.time_running;
-
-		if (w_time_enabled != w_time_running)
-			of_mul_write = (float)w_time_enabled /
-					(float)w_time_running;
 		reads += r->return_value.value * of_mul_read * SCALE;
-		writes += w->return_value.value * of_mul_write * SCALE;
-	}
-
-	if (strcmp(bw_report, "reads") == 0) {
-		*bw_imc = reads;
-		return 0;
-	}
-
-	if (strcmp(bw_report, "writes") == 0) {
-		*bw_imc = writes;
-		return 0;
 	}
 
-	*bw_imc = reads + writes;
+	*bw_imc = reads;
 	return 0;
 }
 
@@ -551,35 +477,31 @@ static int print_results_bw(char *filename, pid_t bm_pid, float bw_imc,
 }
 
 /*
- * measure_mem_bw - Measures memory bandwidth numbers while benchmark runs
+ * measure_read_mem_bw - Measures read memory bandwidth numbers while benchmark runs
  * @uparams:		User supplied parameters
  * @param:		Parameters passed to resctrl_val()
  * @bm_pid:		PID that runs the benchmark
- * @bw_report:		Bandwidth report type (reads, writes)
  *
  * Measure memory bandwidth from resctrl and from another source which is
  * perf imc value or could be something else if perf imc event is not
  * available. Compare the two values to validate resctrl value. It takes
  * 1 sec to measure the data.
+ * resctrl does not distinguish between read and write operations so
+ * its data includes all memory operations.
  */
-int measure_mem_bw(const struct user_params *uparams,
-		   struct resctrl_val_param *param, pid_t bm_pid,
-		   const char *bw_report)
+int measure_read_mem_bw(const struct user_params *uparams,
+			struct resctrl_val_param *param, pid_t bm_pid)
 {
 	unsigned long bw_resc, bw_resc_start, bw_resc_end;
 	FILE *mem_bw_fp;
 	float bw_imc;
 	int ret;
 
-	bw_report = get_bw_report_type(bw_report);
-	if (!bw_report)
-		return -1;
-
 	mem_bw_fp = open_mem_bw_resctrl(mbm_total_path);
 	if (!mem_bw_fp)
 		return -1;
 
-	ret = perf_open_imc_mem_bw(uparams->cpu);
+	ret = perf_open_imc_read_mem_bw(uparams->cpu);
 	if (ret < 0)
 		goto close_fp;
 
@@ -589,17 +511,17 @@ int measure_mem_bw(const struct user_params *uparams,
 
 	rewind(mem_bw_fp);
 
-	do_imc_mem_bw_test();
+	do_imc_read_mem_bw_test();
 
 	ret = get_mem_bw_resctrl(mem_bw_fp, &bw_resc_end);
 	if (ret < 0)
 		goto close_imc;
 
-	ret = get_mem_bw_imc(bw_report, &bw_imc);
+	ret = get_read_mem_bw_imc(&bw_imc);
 	if (ret < 0)
 		goto close_imc;
 
-	perf_close_imc_mem_bw();
+	perf_close_imc_read_mem_bw();
 	fclose(mem_bw_fp);
 
 	bw_resc = (bw_resc_end - bw_resc_start) / MB;
@@ -607,7 +529,7 @@ int measure_mem_bw(const struct user_params *uparams,
 	return print_results_bw(param->filename, bm_pid, bw_imc, bw_resc);
 
 close_imc:
-	perf_close_imc_mem_bw();
+	perf_close_imc_read_mem_bw();
 close_fp:
 	fclose(mem_bw_fp);
 	return ret;
diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index a53cd1cb6e0c6..d38d6dd90be44 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -831,23 +831,6 @@ int filter_dmesg(void)
 	return 0;
 }
 
-const char *get_bw_report_type(const char *bw_report)
-{
-	if (strcmp(bw_report, "reads") == 0)
-		return bw_report;
-	if (strcmp(bw_report, "writes") == 0)
-		return bw_report;
-	if (strcmp(bw_report, "nt-writes") == 0) {
-		return "writes";
-	}
-	if (strcmp(bw_report, "total") == 0)
-		return bw_report;
-
-	fprintf(stderr, "Requested iMC bandwidth report type unavailable\n");
-
-	return NULL;
-}
-
 int perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu,
 		    int group_fd, unsigned long flags)
 {

From 305cfcadceee4e709de6d49497302938dd13887b Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Thu, 24 Oct 2024 14:18:47 -0700
Subject: [PATCH 213/236] selftests/resctrl: Make benchmark parameter passing
 robust
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit e958c21e2edecd17c87c4a2df39d1e47a3f7c039 upstream.

The benchmark used during the CMT, MBM, and MBA tests can be provided by
the user via (-b) parameter, if not provided the default "fill_buf"
benchmark is used. The user is additionally able to override
any of the "fill_buf" default parameters when running the tests with
"-b fill_buf <fill_buf parameters>".

The "fill_buf" parameters are managed as an array of strings. Using an
array of strings is complex because it requires transformations to/from
strings at every producer and consumer. This is made worse for the
individual tests where the default benchmark parameters values may not
be appropriate and additional data wrangling is required. For example,
the CMT test duplicates the entire array of strings in order to replace
one of the parameters.

More issues appear when combining the usage of an array of strings with
the use case of user overriding default parameters by specifying
"-b fill_buf <parameters>". This use case is fragile with opportunities
to trigger a SIGSEGV because of opportunities for NULL pointers to exist
in the array of strings. For example, by running below (thus by specifying
"fill_buf" should be used but all parameters are NULL):
	$ sudo resctrl_tests -t mbm -b fill_buf

Replace the "array of strings" parameters used for "fill_buf" with
new struct fill_buf_param that contains the "fill_buf" parameters that
can be used directly without transformations to/from strings. Two
instances of struct fill_buf_param may exist at any point in time:
	* If the user provides new parameters to "fill_buf", the
	  user parameter structure (struct user_params) will point to a
	  fully initialized and immutable struct fill_buf_param
	  containing the user provided parameters.
	* If "fill_buf" is the benchmark that should be used by a test,
	  then the test parameter structure (struct resctrl_val_param)
	  will point to a fully initialized struct fill_buf_param. The
	  latter may contain (a) the user provided parameters verbatim,
	  (b) user provided parameters adjusted to be appropriate for
	  the test, or (c) the default parameters for "fill_buf" that
	  is appropriate for the test if the user did not provide
	  "fill_buf" parameters nor an alternate benchmark.

The existing behavior of CMT test is to use test defined value for the
buffer size even if the user provides another value via command line.
This behavior is maintained since the test requires that the buffer size
matches the size of the cache allocated, and the amount of cache
allocated can instead be changed by the user with the "-n" command line
parameter.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cmt_test.c    |  32 ++----
 tools/testing/selftests/resctrl/fill_buf.c    |   4 +-
 tools/testing/selftests/resctrl/mba_test.c    |  13 ++-
 tools/testing/selftests/resctrl/mbm_test.c    |  22 ++--
 tools/testing/selftests/resctrl/resctrl.h     |  59 +++++++---
 .../testing/selftests/resctrl/resctrl_tests.c | 103 ++++++++++++++----
 tools/testing/selftests/resctrl/resctrl_val.c |  41 ++++---
 7 files changed, 178 insertions(+), 96 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c
index 0c045080d8085..4c3cf2c25a38f 100644
--- a/tools/testing/selftests/resctrl/cmt_test.c
+++ b/tools/testing/selftests/resctrl/cmt_test.c
@@ -116,15 +116,13 @@ static void cmt_test_cleanup(void)
 
 static int cmt_run_test(const struct resctrl_test *test, const struct user_params *uparams)
 {
-	const char * const *cmd = uparams->benchmark_cmd;
-	const char *new_cmd[BENCHMARK_ARGS];
+	struct fill_buf_param fill_buf = {};
 	unsigned long cache_total_size = 0;
 	int n = uparams->bits ? : 5;
 	unsigned long long_mask;
-	char *span_str = NULL;
 	int count_of_bits;
 	size_t span;
-	int ret, i;
+	int ret;
 
 	ret = get_full_cbm("L3", &long_mask);
 	if (ret)
@@ -155,32 +153,26 @@ static int cmt_run_test(const struct resctrl_test *test, const struct user_param
 
 	span = cache_portion_size(cache_total_size, param.mask, long_mask);
 
-	if (strcmp(cmd[0], "fill_buf") == 0) {
-		/* Duplicate the command to be able to replace span in it */
-		for (i = 0; uparams->benchmark_cmd[i]; i++)
-			new_cmd[i] = uparams->benchmark_cmd[i];
-		new_cmd[i] = NULL;
-
-		ret = asprintf(&span_str, "%zu", span);
-		if (ret < 0)
-			return -1;
-		new_cmd[1] = span_str;
-		cmd = new_cmd;
+	if (uparams->fill_buf) {
+		fill_buf.buf_size = span;
+		fill_buf.memflush = uparams->fill_buf->memflush;
+		param.fill_buf = &fill_buf;
+	} else if (!uparams->benchmark_cmd[0]) {
+		fill_buf.buf_size = span;
+		fill_buf.memflush = true;
+		param.fill_buf = &fill_buf;
 	}
 
 	remove(RESULT_FILE_NAME);
 
-	ret = resctrl_val(test, uparams, cmd, &param);
+	ret = resctrl_val(test, uparams, &param);
 	if (ret)
-		goto out;
+		return ret;
 
 	ret = check_results(&param, span, n);
 	if (ret && (get_vendor() == ARCH_INTEL))
 		ksft_print_msg("Intel CMT may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n");
 
-out:
-	free(span_str);
-
 	return ret;
 }
 
diff --git a/tools/testing/selftests/resctrl/fill_buf.c b/tools/testing/selftests/resctrl/fill_buf.c
index e4f1cea317f12..39545f9369e85 100644
--- a/tools/testing/selftests/resctrl/fill_buf.c
+++ b/tools/testing/selftests/resctrl/fill_buf.c
@@ -102,7 +102,7 @@ void fill_cache_read(unsigned char *buf, size_t buf_size, bool once)
 	*value_sink = ret;
 }
 
-unsigned char *alloc_buffer(size_t buf_size, int memflush)
+unsigned char *alloc_buffer(size_t buf_size, bool memflush)
 {
 	void *buf = NULL;
 	uint64_t *p64;
@@ -130,7 +130,7 @@ unsigned char *alloc_buffer(size_t buf_size, int memflush)
 	return buf;
 }
 
-int run_fill_buf(size_t buf_size, int memflush)
+int run_fill_buf(size_t buf_size, bool memflush)
 {
 	unsigned char *buf;
 
diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c
index be0ead73e55da..74d95c460bd0f 100644
--- a/tools/testing/selftests/resctrl/mba_test.c
+++ b/tools/testing/selftests/resctrl/mba_test.c
@@ -172,11 +172,22 @@ static int mba_run_test(const struct resctrl_test *test, const struct user_param
 		.setup		= mba_setup,
 		.measure	= mba_measure,
 	};
+	struct fill_buf_param fill_buf = {};
 	int ret;
 
 	remove(RESULT_FILE_NAME);
 
-	ret = resctrl_val(test, uparams, uparams->benchmark_cmd, &param);
+	if (uparams->fill_buf) {
+		fill_buf.buf_size = uparams->fill_buf->buf_size;
+		fill_buf.memflush = uparams->fill_buf->memflush;
+		param.fill_buf = &fill_buf;
+	} else if (!uparams->benchmark_cmd[0]) {
+		fill_buf.buf_size = DEFAULT_SPAN;
+		fill_buf.memflush = true;
+		param.fill_buf = &fill_buf;
+	}
+
+	ret = resctrl_val(test, uparams, &param);
 	if (ret)
 		return ret;
 
diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c
index defa942939157..72261413c868a 100644
--- a/tools/testing/selftests/resctrl/mbm_test.c
+++ b/tools/testing/selftests/resctrl/mbm_test.c
@@ -139,26 +139,26 @@ static int mbm_run_test(const struct resctrl_test *test, const struct user_param
 		.setup		= mbm_setup,
 		.measure	= mbm_measure,
 	};
-	char *endptr = NULL;
-	size_t span = 0;
+	struct fill_buf_param fill_buf = {};
 	int ret;
 
 	remove(RESULT_FILE_NAME);
 
-	if (uparams->benchmark_cmd[0] && strcmp(uparams->benchmark_cmd[0], "fill_buf") == 0) {
-		if (uparams->benchmark_cmd[1] && *uparams->benchmark_cmd[1] != '\0') {
-			errno = 0;
-			span = strtoul(uparams->benchmark_cmd[1], &endptr, 10);
-			if (errno || *endptr != '\0')
-				return -EINVAL;
-		}
+	if (uparams->fill_buf) {
+		fill_buf.buf_size = uparams->fill_buf->buf_size;
+		fill_buf.memflush = uparams->fill_buf->memflush;
+		param.fill_buf = &fill_buf;
+	} else if (!uparams->benchmark_cmd[0]) {
+		fill_buf.buf_size = DEFAULT_SPAN;
+		fill_buf.memflush = true;
+		param.fill_buf = &fill_buf;
 	}
 
-	ret = resctrl_val(test, uparams, uparams->benchmark_cmd, &param);
+	ret = resctrl_val(test, uparams, &param);
 	if (ret)
 		return ret;
 
-	ret = check_results(span);
+	ret = check_results(param.fill_buf ? param.fill_buf->buf_size : 0);
 	if (ret && (get_vendor() == ARCH_INTEL))
 		ksft_print_msg("Intel MBM may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n");
 
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 82801245e4c15..c9336f9c2caed 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -43,16 +43,36 @@
 
 #define DEFAULT_SPAN		(250 * MB)
 
+/*
+ * fill_buf_param:	"fill_buf" benchmark parameters
+ * @buf_size:		Size (in bytes) of buffer used in benchmark.
+ *			"fill_buf" allocates and initializes buffer of
+ *			@buf_size. User can change value via command line.
+ * @memflush:		If false the buffer will not be flushed after
+ *			allocation and initialization, otherwise the
+ *			buffer will be flushed. User can change value via
+ *			command line (via integers with 0 interpreted as
+ *			false and anything else as true).
+ */
+struct fill_buf_param {
+	size_t		buf_size;
+	bool		memflush;
+};
+
 /*
  * user_params:		User supplied parameters
  * @cpu:		CPU number to which the benchmark will be bound to
  * @bits:		Number of bits used for cache allocation size
  * @benchmark_cmd:	Benchmark command to run during (some of the) tests
+ * @fill_buf:		Pointer to user provided parameters for "fill_buf",
+ *			NULL if user did not provide parameters and test
+ *			specific defaults should be used.
  */
 struct user_params {
 	int cpu;
 	int bits;
 	const char *benchmark_cmd[BENCHMARK_ARGS];
+	const struct fill_buf_param *fill_buf;
 };
 
 /*
@@ -87,21 +107,29 @@ struct resctrl_test {
  * @init:		Callback function to initialize test environment
  * @setup:		Callback function to setup per test run environment
  * @measure:		Callback that performs the measurement (a single test)
+ * @fill_buf:		Parameters for default "fill_buf" benchmark.
+ *			Initialized with user provided parameters, possibly
+ *			adapted to be relevant to the test. If user does
+ *			not provide parameters for "fill_buf" nor a
+ *			replacement benchmark then initialized with defaults
+ *			appropriate for test. NULL if user provided
+ *			benchmark.
  */
 struct resctrl_val_param {
-	const char	*ctrlgrp;
-	const char	*mongrp;
-	char		filename[64];
-	unsigned long	mask;
-	int		num_of_runs;
-	int		(*init)(const struct resctrl_val_param *param,
-				int domain_id);
-	int		(*setup)(const struct resctrl_test *test,
-				 const struct user_params *uparams,
-				 struct resctrl_val_param *param);
-	int		(*measure)(const struct user_params *uparams,
-				   struct resctrl_val_param *param,
-				   pid_t bm_pid);
+	const char		*ctrlgrp;
+	const char		*mongrp;
+	char			filename[64];
+	unsigned long		mask;
+	int			num_of_runs;
+	int			(*init)(const struct resctrl_val_param *param,
+					int domain_id);
+	int			(*setup)(const struct resctrl_test *test,
+					 const struct user_params *uparams,
+					 struct resctrl_val_param *param);
+	int			(*measure)(const struct user_params *uparams,
+					   struct resctrl_val_param *param,
+					   pid_t bm_pid);
+	struct fill_buf_param	*fill_buf;
 };
 
 struct perf_event_read {
@@ -138,10 +166,10 @@ int write_schemata(const char *ctrlgrp, char *schemata, int cpu_no,
 int write_bm_pid_to_resctrl(pid_t bm_pid, const char *ctrlgrp, const char *mongrp);
 int perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu,
 		    int group_fd, unsigned long flags);
-unsigned char *alloc_buffer(size_t buf_size, int memflush);
+unsigned char *alloc_buffer(size_t buf_size, bool memflush);
 void mem_flush(unsigned char *buf, size_t buf_size);
 void fill_cache_read(unsigned char *buf, size_t buf_size, bool once);
-int run_fill_buf(size_t buf_size, int memflush);
+int run_fill_buf(size_t buf_size, bool memflush);
 int initialize_read_mem_bw_imc(void);
 int measure_read_mem_bw(const struct user_params *uparams,
 			struct resctrl_val_param *param, pid_t bm_pid);
@@ -149,7 +177,6 @@ void initialize_mem_bw_resctrl(const struct resctrl_val_param *param,
 			       int domain_id);
 int resctrl_val(const struct resctrl_test *test,
 		const struct user_params *uparams,
-		const char * const *benchmark_cmd,
 		struct resctrl_val_param *param);
 unsigned long create_bit_mask(unsigned int start, unsigned int len);
 unsigned int count_contiguous_bits(unsigned long val, unsigned int *start);
diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c
index 0f91c475b255a..24daf76b40395 100644
--- a/tools/testing/selftests/resctrl/resctrl_tests.c
+++ b/tools/testing/selftests/resctrl/resctrl_tests.c
@@ -148,6 +148,78 @@ static void run_single_test(const struct resctrl_test *test, const struct user_p
 	test_cleanup(test);
 }
 
+/*
+ * Allocate and initialize a struct fill_buf_param with user provided
+ * (via "-b fill_buf <fill_buf parameters>") parameters.
+ *
+ * Use defaults (that may not be appropriate for all tests) for any
+ * fill_buf parameters omitted by the user.
+ *
+ * Historically it may have been possible for user space to provide
+ * additional parameters, "operation" ("read" vs "write") in
+ * benchmark_cmd[3] and "once" (run "once" or until terminated) in
+ * benchmark_cmd[4]. Changing these parameters have never been
+ * supported with the default of "read" operation and running until
+ * terminated built into the tests. Any unsupported values for
+ * (original) "fill_buf" parameters are treated as failure.
+ *
+ * Return: On failure, forcibly exits the test on any parsing failure,
+ *         returns NULL if no parsing needed (user did not actually provide
+ *         "-b fill_buf").
+ *         On success, returns pointer to newly allocated and fully
+ *         initialized struct fill_buf_param that caller must free.
+ */
+static struct fill_buf_param *alloc_fill_buf_param(struct user_params *uparams)
+{
+	struct fill_buf_param *fill_param = NULL;
+	char *endptr = NULL;
+
+	if (!uparams->benchmark_cmd[0] || strcmp(uparams->benchmark_cmd[0], "fill_buf"))
+		return NULL;
+
+	fill_param = malloc(sizeof(*fill_param));
+	if (!fill_param)
+		ksft_exit_skip("Unable to allocate memory for fill_buf parameters.\n");
+
+	if (uparams->benchmark_cmd[1] && *uparams->benchmark_cmd[1] != '\0') {
+		errno = 0;
+		fill_param->buf_size = strtoul(uparams->benchmark_cmd[1], &endptr, 10);
+		if (errno || *endptr != '\0') {
+			free(fill_param);
+			ksft_exit_skip("Unable to parse benchmark buffer size.\n");
+		}
+	} else {
+		fill_param->buf_size = DEFAULT_SPAN;
+	}
+
+	if (uparams->benchmark_cmd[2] && *uparams->benchmark_cmd[2] != '\0') {
+		errno = 0;
+		fill_param->memflush = strtol(uparams->benchmark_cmd[2], &endptr, 10) != 0;
+		if (errno || *endptr != '\0') {
+			free(fill_param);
+			ksft_exit_skip("Unable to parse benchmark memflush parameter.\n");
+		}
+	} else {
+		fill_param->memflush = true;
+	}
+
+	if (uparams->benchmark_cmd[3] && *uparams->benchmark_cmd[3] != '\0') {
+		if (strcmp(uparams->benchmark_cmd[3], "0")) {
+			free(fill_param);
+			ksft_exit_skip("Only read operations supported.\n");
+		}
+	}
+
+	if (uparams->benchmark_cmd[4] && *uparams->benchmark_cmd[4] != '\0') {
+		if (strcmp(uparams->benchmark_cmd[4], "false")) {
+			free(fill_param);
+			ksft_exit_skip("fill_buf is required to run until termination.\n");
+		}
+	}
+
+	return fill_param;
+}
+
 static void init_user_params(struct user_params *uparams)
 {
 	memset(uparams, 0, sizeof(*uparams));
@@ -158,11 +230,11 @@ static void init_user_params(struct user_params *uparams)
 
 int main(int argc, char **argv)
 {
+	struct fill_buf_param *fill_param = NULL;
 	int tests = ARRAY_SIZE(resctrl_tests);
 	bool test_param_seen = false;
 	struct user_params uparams;
-	char *span_str = NULL;
-	int ret, c, i;
+	int c, i;
 
 	init_user_params(&uparams);
 
@@ -239,6 +311,10 @@ int main(int argc, char **argv)
 	}
 last_arg:
 
+	fill_param = alloc_fill_buf_param(&uparams);
+	if (fill_param)
+		uparams.fill_buf = fill_param;
+
 	ksft_print_header();
 
 	/*
@@ -257,32 +333,11 @@ int main(int argc, char **argv)
 
 	filter_dmesg();
 
-	if (!uparams.benchmark_cmd[0]) {
-		/* If no benchmark is given by "-b" argument, use fill_buf. */
-		uparams.benchmark_cmd[0] = "fill_buf";
-		ret = asprintf(&span_str, "%u", DEFAULT_SPAN);
-		if (ret < 0)
-			ksft_exit_fail_msg("Out of memory!\n");
-		uparams.benchmark_cmd[1] = span_str;
-		uparams.benchmark_cmd[2] = "1";
-		/*
-		 * Third parameter was previously used for "operation"
-		 * (read/write) of which only (now default) "read"/"0"
-		 * works.
-		 * Fourth parameter was previously used to indicate
-		 * how long "fill_buf" should run for, with "false"
-		 * ("fill_buf" will keep running until terminated)
-		 * the only option that works.
-		 */
-		uparams.benchmark_cmd[3] = NULL;
-		uparams.benchmark_cmd[4] = NULL;
-	}
-
 	ksft_set_plan(tests);
 
 	for (i = 0; i < ARRAY_SIZE(resctrl_tests); i++)
 		run_single_test(resctrl_tests[i], &uparams);
 
-	free(span_str);
+	free(fill_param);
 	ksft_finished();
 }
diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index c4ebf70a46ef9..00b3808d3bca6 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -535,6 +535,11 @@ int measure_read_mem_bw(const struct user_params *uparams,
 	return ret;
 }
 
+struct benchmark_info {
+	const struct user_params *uparams;
+	struct resctrl_val_param *param;
+};
+
 /*
  * run_benchmark - Run a specified benchmark or fill_buf (default benchmark)
  *		   in specified signal. Direct benchmark stdio to /dev/null.
@@ -544,12 +549,11 @@ int measure_read_mem_bw(const struct user_params *uparams,
  */
 static void run_benchmark(int signum, siginfo_t *info, void *ucontext)
 {
-	char **benchmark_cmd;
-	int ret, memflush;
-	size_t span;
+	struct benchmark_info *benchmark_info = info->si_ptr;
+	const struct user_params *uparams = benchmark_info->uparams;
+	struct resctrl_val_param *param = benchmark_info->param;
 	FILE *fp;
-
-	benchmark_cmd = info->si_ptr;
+	int ret;
 
 	/*
 	 * Direct stdio of child to /dev/null, so that only parent writes to
@@ -561,16 +565,13 @@ static void run_benchmark(int signum, siginfo_t *info, void *ucontext)
 		parent_exit(ppid);
 	}
 
-	if (strcmp(benchmark_cmd[0], "fill_buf") == 0) {
-		/* Execute default fill_buf benchmark */
-		span = strtoul(benchmark_cmd[1], NULL, 10);
-		memflush =  atoi(benchmark_cmd[2]);
-
-		if (run_fill_buf(span, memflush))
+	if (param->fill_buf) {
+		if (run_fill_buf(param->fill_buf->buf_size,
+				 param->fill_buf->memflush))
 			fprintf(stderr, "Error in running fill buffer\n");
-	} else {
+	} else if (uparams->benchmark_cmd[0]) {
 		/* Execute specified benchmark */
-		ret = execvp(benchmark_cmd[0], benchmark_cmd);
+		ret = execvp(uparams->benchmark_cmd[0], (char **)uparams->benchmark_cmd);
 		if (ret)
 			ksft_perror("execvp");
 	}
@@ -585,16 +586,15 @@ static void run_benchmark(int signum, siginfo_t *info, void *ucontext)
  *			the benchmark
  * @test:		test information structure
  * @uparams:		user supplied parameters
- * @benchmark_cmd:	benchmark command and its arguments
  * @param:		parameters passed to resctrl_val()
  *
  * Return:		0 when the test was run, < 0 on error.
  */
 int resctrl_val(const struct resctrl_test *test,
 		const struct user_params *uparams,
-		const char * const *benchmark_cmd,
 		struct resctrl_val_param *param)
 {
+	struct benchmark_info benchmark_info;
 	struct sigaction sigact;
 	int ret = 0, pipefd[2];
 	char pipe_message = 0;
@@ -610,6 +610,9 @@ int resctrl_val(const struct resctrl_test *test,
 		return ret;
 	}
 
+	benchmark_info.uparams = uparams;
+	benchmark_info.param = param;
+
 	/*
 	 * If benchmark wasn't successfully started by child, then child should
 	 * kill parent, so save parent's pid
@@ -671,13 +674,7 @@ int resctrl_val(const struct resctrl_test *test,
 
 	ksft_print_msg("Benchmark PID: %d\n", (int)bm_pid);
 
-	/*
-	 * The cast removes constness but nothing mutates benchmark_cmd within
-	 * the context of this process. At the receiving process, it becomes
-	 * argv, which is mutable, on exec() but that's after fork() so it
-	 * doesn't matter for the process running the tests.
-	 */
-	value.sival_ptr = (void *)benchmark_cmd;
+	value.sival_ptr = (void *)&benchmark_info;
 
 	/* Taskset benchmark to specified cpu */
 	ret = taskset_benchmark(bm_pid, uparams->cpu, NULL);

From 8f00f8eaf07d465361887cb84fd27d94e8224121 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Thu, 24 Oct 2024 14:18:48 -0700
Subject: [PATCH 214/236] selftests/resctrl: Ensure measurements skip
 initialization of default benchmark
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 3cb3f0b8755919648281064d44c06319743db343 upstream.

The CMT, MBA, and MBM tests rely on the resctrl_val() wrapper to
start and run a benchmark while providing test specific flows
via callbacks to do test specific configuration and measurements.

At a high level, the resctrl_val() flow is:
	a) Start by fork()ing a child process that installs a signal
	   handler for SIGUSR1 that, on receipt of SIGUSR1, will
	   start running a benchmark.
	b) Assign the child process created in (a) to the resctrl
	   control and monitoring group that dictates the memory and
	   cache allocations with which the process can run and will
	   contain all resctrl monitoring data of that process.
	c) Once parent and child are considered "ready" (determined via
	   a message over a pipe) the parent signals the child (via
	   SIGUSR1) to start the benchmark, waits one second for the
	   benchmark to run, and then starts collecting monitoring data
	   for the tests, potentially also changing allocation
	   configuration depending on the various test callbacks.

A problem with the above flow is the "black box" view of the
benchmark that is combined with an arbitrarily chosen
"wait one second" before measurements start. No matter what
the benchmark does, it is given one second to initialize before
measurements start.

The default benchmark "fill_buf" consists of two parts,
first it prepares a buffer (allocate, initialize, then flush), then it
reads from the buffer (in unpredictable ways) until terminated.
Depending on the system and the size of the buffer, the first "prepare"
part may not be complete by the time the one second delay expires. Test
measurements may thus start before the work needing to be measured runs.

Split the default benchmark into its "prepare" and "runtime" parts and
simplify the resctrl_val() wrapper while doing so. This same split
cannot be done for the user provided benchmark (without a user
interface change), so the current behavior is maintained for user
provided benchmark.

Assign the test itself to the control and monitoring group and run the
"prepare" part of the benchmark in this context, ensuring it runs with
required cache and memory bandwidth allocations. With the benchmark
preparation complete it is only needed to fork() the "runtime" part
of the benchmark (or entire user provided benchmark).

Keep the "wait one second" delay before measurements start. For the
default "fill_buf" benchmark this time now covers only the "runtime"
portion that needs to be measured. For the user provided benchmark this
delay maintains current behavior.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/fill_buf.c    |  15 --
 tools/testing/selftests/resctrl/resctrl.h     |   1 -
 tools/testing/selftests/resctrl/resctrl_val.c | 195 +++++-------------
 3 files changed, 50 insertions(+), 161 deletions(-)

diff --git a/tools/testing/selftests/resctrl/fill_buf.c b/tools/testing/selftests/resctrl/fill_buf.c
index 39545f9369e85..380cc35f10c63 100644
--- a/tools/testing/selftests/resctrl/fill_buf.c
+++ b/tools/testing/selftests/resctrl/fill_buf.c
@@ -129,18 +129,3 @@ unsigned char *alloc_buffer(size_t buf_size, bool memflush)
 
 	return buf;
 }
-
-int run_fill_buf(size_t buf_size, bool memflush)
-{
-	unsigned char *buf;
-
-	buf = alloc_buffer(buf_size, memflush);
-	if (!buf)
-		return -1;
-
-	fill_cache_read(buf, buf_size, false);
-
-	free(buf);
-
-	return 0;
-}
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index c9336f9c2caed..032cd9ebd7614 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -169,7 +169,6 @@ int perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu,
 unsigned char *alloc_buffer(size_t buf_size, bool memflush);
 void mem_flush(unsigned char *buf, size_t buf_size);
 void fill_cache_read(unsigned char *buf, size_t buf_size, bool once);
-int run_fill_buf(size_t buf_size, bool memflush);
 int initialize_read_mem_bw_imc(void);
 int measure_read_mem_bw(const struct user_params *uparams,
 			struct resctrl_val_param *param, pid_t bm_pid);
diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index 00b3808d3bca6..7c08e936572d2 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -373,7 +373,7 @@ static int get_mem_bw_resctrl(FILE *fp, unsigned long *mbm_total)
 	return 0;
 }
 
-static pid_t bm_pid, ppid;
+static pid_t bm_pid;
 
 void ctrlc_handler(int signum, siginfo_t *info, void *ptr)
 {
@@ -431,13 +431,6 @@ void signal_handler_unregister(void)
 	}
 }
 
-static void parent_exit(pid_t ppid)
-{
-	kill(ppid, SIGKILL);
-	umount_resctrlfs();
-	exit(EXIT_FAILURE);
-}
-
 /*
  * print_results_bw:	the memory bandwidth results are stored in a file
  * @filename:		file that stores the results
@@ -535,52 +528,6 @@ int measure_read_mem_bw(const struct user_params *uparams,
 	return ret;
 }
 
-struct benchmark_info {
-	const struct user_params *uparams;
-	struct resctrl_val_param *param;
-};
-
-/*
- * run_benchmark - Run a specified benchmark or fill_buf (default benchmark)
- *		   in specified signal. Direct benchmark stdio to /dev/null.
- * @signum:	signal number
- * @info:	signal info
- * @ucontext:	user context in signal handling
- */
-static void run_benchmark(int signum, siginfo_t *info, void *ucontext)
-{
-	struct benchmark_info *benchmark_info = info->si_ptr;
-	const struct user_params *uparams = benchmark_info->uparams;
-	struct resctrl_val_param *param = benchmark_info->param;
-	FILE *fp;
-	int ret;
-
-	/*
-	 * Direct stdio of child to /dev/null, so that only parent writes to
-	 * stdio (console)
-	 */
-	fp = freopen("/dev/null", "w", stdout);
-	if (!fp) {
-		ksft_perror("Unable to direct benchmark status to /dev/null");
-		parent_exit(ppid);
-	}
-
-	if (param->fill_buf) {
-		if (run_fill_buf(param->fill_buf->buf_size,
-				 param->fill_buf->memflush))
-			fprintf(stderr, "Error in running fill buffer\n");
-	} else if (uparams->benchmark_cmd[0]) {
-		/* Execute specified benchmark */
-		ret = execvp(uparams->benchmark_cmd[0], (char **)uparams->benchmark_cmd);
-		if (ret)
-			ksft_perror("execvp");
-	}
-
-	fclose(stdout);
-	ksft_print_msg("Unable to run specified benchmark\n");
-	parent_exit(ppid);
-}
-
 /*
  * resctrl_val:	execute benchmark and measure memory bandwidth on
  *			the benchmark
@@ -594,12 +541,11 @@ int resctrl_val(const struct resctrl_test *test,
 		const struct user_params *uparams,
 		struct resctrl_val_param *param)
 {
-	struct benchmark_info benchmark_info;
-	struct sigaction sigact;
-	int ret = 0, pipefd[2];
-	char pipe_message = 0;
-	union sigval value;
+	unsigned char *buf = NULL;
+	cpu_set_t old_affinity;
 	int domain_id;
+	int ret = 0;
+	pid_t ppid;
 
 	if (strcmp(param->filename, "") == 0)
 		sprintf(param->filename, "stdio");
@@ -610,108 +556,65 @@ int resctrl_val(const struct resctrl_test *test,
 		return ret;
 	}
 
-	benchmark_info.uparams = uparams;
-	benchmark_info.param = param;
-
-	/*
-	 * If benchmark wasn't successfully started by child, then child should
-	 * kill parent, so save parent's pid
-	 */
 	ppid = getpid();
 
-	if (pipe(pipefd)) {
-		ksft_perror("Unable to create pipe");
+	/* Taskset test to specified CPU. */
+	ret = taskset_benchmark(ppid, uparams->cpu, &old_affinity);
+	if (ret)
+		return ret;
+
+	/* Write test to specified control & monitoring group in resctrl FS. */
+	ret = write_bm_pid_to_resctrl(ppid, param->ctrlgrp, param->mongrp);
+	if (ret)
+		goto reset_affinity;
 
-		return -1;
+	if (param->init) {
+		ret = param->init(param, domain_id);
+		if (ret)
+			goto reset_affinity;
 	}
 
 	/*
-	 * Fork to start benchmark, save child's pid so that it can be killed
-	 * when needed
+	 * If not running user provided benchmark, run the default
+	 * "fill_buf". First phase of "fill_buf" is to prepare the
+	 * buffer that the benchmark will operate on. No measurements
+	 * are needed during this phase and prepared memory will be
+	 * passed to next part of benchmark via copy-on-write thus
+	 * no impact on the benchmark that relies on reading from
+	 * memory only.
 	 */
+	if (param->fill_buf) {
+		buf = alloc_buffer(param->fill_buf->buf_size,
+				   param->fill_buf->memflush);
+		if (!buf) {
+			ret = -ENOMEM;
+			goto reset_affinity;
+		}
+	}
+
 	fflush(stdout);
 	bm_pid = fork();
 	if (bm_pid == -1) {
+		ret = -errno;
 		ksft_perror("Unable to fork");
-
-		return -1;
+		goto free_buf;
 	}
 
+	/*
+	 * What needs to be measured runs in separate process until
+	 * terminated.
+	 */
 	if (bm_pid == 0) {
-		/*
-		 * Mask all signals except SIGUSR1, parent uses SIGUSR1 to
-		 * start benchmark
-		 */
-		sigfillset(&sigact.sa_mask);
-		sigdelset(&sigact.sa_mask, SIGUSR1);
-
-		sigact.sa_sigaction = run_benchmark;
-		sigact.sa_flags = SA_SIGINFO;
-
-		/* Register for "SIGUSR1" signal from parent */
-		if (sigaction(SIGUSR1, &sigact, NULL)) {
-			ksft_perror("Can't register child for signal");
-			parent_exit(ppid);
-		}
-
-		/* Tell parent that child is ready */
-		close(pipefd[0]);
-		pipe_message = 1;
-		if (write(pipefd[1], &pipe_message, sizeof(pipe_message)) <
-		    sizeof(pipe_message)) {
-			ksft_perror("Failed signaling parent process");
-			close(pipefd[1]);
-			return -1;
-		}
-		close(pipefd[1]);
-
-		/* Suspend child until delivery of "SIGUSR1" from parent */
-		sigsuspend(&sigact.sa_mask);
-
-		ksft_perror("Child is done");
-		parent_exit(ppid);
+		if (param->fill_buf)
+			fill_cache_read(buf, param->fill_buf->buf_size, false);
+		else if (uparams->benchmark_cmd[0])
+			execvp(uparams->benchmark_cmd[0], (char **)uparams->benchmark_cmd);
+		exit(EXIT_SUCCESS);
 	}
 
 	ksft_print_msg("Benchmark PID: %d\n", (int)bm_pid);
 
-	value.sival_ptr = (void *)&benchmark_info;
-
-	/* Taskset benchmark to specified cpu */
-	ret = taskset_benchmark(bm_pid, uparams->cpu, NULL);
-	if (ret)
-		goto out;
-
-	/* Write benchmark to specified control&monitoring grp in resctrl FS */
-	ret = write_bm_pid_to_resctrl(bm_pid, param->ctrlgrp, param->mongrp);
-	if (ret)
-		goto out;
-
-	if (param->init) {
-		ret = param->init(param, domain_id);
-		if (ret)
-			goto out;
-	}
-
-	/* Parent waits for child to be ready. */
-	close(pipefd[1]);
-	while (pipe_message != 1) {
-		if (read(pipefd[0], &pipe_message, sizeof(pipe_message)) <
-		    sizeof(pipe_message)) {
-			ksft_perror("Failed reading message from child process");
-			close(pipefd[0]);
-			goto out;
-		}
-	}
-	close(pipefd[0]);
-
-	/* Signal child to start benchmark */
-	if (sigqueue(bm_pid, SIGUSR1, value) == -1) {
-		ksft_perror("sigqueue SIGUSR1 to child");
-		ret = -1;
-		goto out;
-	}
-
-	/* Give benchmark enough time to fully run */
+	/* Give benchmark enough time to fully run. */
 	sleep(1);
 
 	/* Test runs until the callback setup() tells the test to stop. */
@@ -729,8 +632,10 @@ int resctrl_val(const struct resctrl_test *test,
 			break;
 	}
 
-out:
 	kill(bm_pid, SIGKILL);
-
+free_buf:
+	free(buf);
+reset_affinity:
+	taskset_restore(ppid, &old_affinity);
 	return ret;
 }

From ceb4201489dcfa58ac2fc0d9ad01462ab635785f Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Thu, 24 Oct 2024 14:18:49 -0700
Subject: [PATCH 215/236] selftests/resctrl: Use cache size to determine
 "fill_buf" buffer size
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit f77b9672536e581c945b2623b521a284fdbf75ff upstream.

By default the MBM and MBA tests use the "fill_buf" benchmark to
read from a buffer with the goal to measure the memory bandwidth
generated by this buffer access.

Care should be taken when sizing the buffer used by the "fill_buf"
benchmark. If the buffer is small enough to fit in the cache then
it cannot be expected that the benchmark will generate much memory
bandwidth. For example, on a system with 320MB L3 cache the existing
hardcoded default of 250MB is insufficient.

Use the measured cache size to determine a buffer size that can be
expected to trigger memory access while keeping the existing default
as minimum, now renamed to MINIMUM_SPAN, that has been appropriate for
testing so far.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/fill_buf.c      | 13 +++++++++++++
 tools/testing/selftests/resctrl/mba_test.c      |  7 ++++++-
 tools/testing/selftests/resctrl/mbm_test.c      |  7 ++++++-
 tools/testing/selftests/resctrl/resctrl.h       |  3 ++-
 tools/testing/selftests/resctrl/resctrl_tests.c |  2 +-
 5 files changed, 28 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/resctrl/fill_buf.c b/tools/testing/selftests/resctrl/fill_buf.c
index 380cc35f10c63..19a01a52dc1a3 100644
--- a/tools/testing/selftests/resctrl/fill_buf.c
+++ b/tools/testing/selftests/resctrl/fill_buf.c
@@ -129,3 +129,16 @@ unsigned char *alloc_buffer(size_t buf_size, bool memflush)
 
 	return buf;
 }
+
+ssize_t get_fill_buf_size(int cpu_no, const char *cache_type)
+{
+	unsigned long cache_total_size = 0;
+	int ret;
+
+	ret = get_cache_size(cpu_no, cache_type, &cache_total_size);
+	if (ret)
+		return ret;
+
+	return cache_total_size * 2 > MINIMUM_SPAN ?
+			cache_total_size * 2 : MINIMUM_SPAN;
+}
diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c
index 74d95c460bd0f..bf37f35556607 100644
--- a/tools/testing/selftests/resctrl/mba_test.c
+++ b/tools/testing/selftests/resctrl/mba_test.c
@@ -182,7 +182,12 @@ static int mba_run_test(const struct resctrl_test *test, const struct user_param
 		fill_buf.memflush = uparams->fill_buf->memflush;
 		param.fill_buf = &fill_buf;
 	} else if (!uparams->benchmark_cmd[0]) {
-		fill_buf.buf_size = DEFAULT_SPAN;
+		ssize_t buf_size;
+
+		buf_size = get_fill_buf_size(uparams->cpu, "L3");
+		if (buf_size < 0)
+			return buf_size;
+		fill_buf.buf_size = buf_size;
 		fill_buf.memflush = true;
 		param.fill_buf = &fill_buf;
 	}
diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c
index 72261413c868a..4224f8ce35385 100644
--- a/tools/testing/selftests/resctrl/mbm_test.c
+++ b/tools/testing/selftests/resctrl/mbm_test.c
@@ -149,7 +149,12 @@ static int mbm_run_test(const struct resctrl_test *test, const struct user_param
 		fill_buf.memflush = uparams->fill_buf->memflush;
 		param.fill_buf = &fill_buf;
 	} else if (!uparams->benchmark_cmd[0]) {
-		fill_buf.buf_size = DEFAULT_SPAN;
+		ssize_t buf_size;
+
+		buf_size = get_fill_buf_size(uparams->cpu, "L3");
+		if (buf_size < 0)
+			return buf_size;
+		fill_buf.buf_size = buf_size;
 		fill_buf.memflush = true;
 		param.fill_buf = &fill_buf;
 	}
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 032cd9ebd7614..a553fe975938e 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -41,7 +41,7 @@
 
 #define BENCHMARK_ARGS		64
 
-#define DEFAULT_SPAN		(250 * MB)
+#define MINIMUM_SPAN		(250 * MB)
 
 /*
  * fill_buf_param:	"fill_buf" benchmark parameters
@@ -169,6 +169,7 @@ int perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu,
 unsigned char *alloc_buffer(size_t buf_size, bool memflush);
 void mem_flush(unsigned char *buf, size_t buf_size);
 void fill_cache_read(unsigned char *buf, size_t buf_size, bool once);
+ssize_t get_fill_buf_size(int cpu_no, const char *cache_type);
 int initialize_read_mem_bw_imc(void);
 int measure_read_mem_bw(const struct user_params *uparams,
 			struct resctrl_val_param *param, pid_t bm_pid);
diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c
index 24daf76b40395..3335af815b210 100644
--- a/tools/testing/selftests/resctrl/resctrl_tests.c
+++ b/tools/testing/selftests/resctrl/resctrl_tests.c
@@ -189,7 +189,7 @@ static struct fill_buf_param *alloc_fill_buf_param(struct user_params *uparams)
 			ksft_exit_skip("Unable to parse benchmark buffer size.\n");
 		}
 	} else {
-		fill_param->buf_size = DEFAULT_SPAN;
+		fill_param->buf_size = MINIMUM_SPAN;
 	}
 
 	if (uparams->benchmark_cmd[2] && *uparams->benchmark_cmd[2] != '\0') {

From ded4b40d1c06778eac41dde9a1de3455cf104814 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Thu, 24 Oct 2024 14:18:50 -0700
Subject: [PATCH 216/236] selftests/resctrl: Do not compare performance
 counters and resctrl at low bandwidth
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 501cfdba0a400e70ea220a4b02f1805e0e9de6a1 upstream.

The MBA test incrementally throttles memory bandwidth, each time
followed by a comparison between the memory bandwidth observed
by the performance counters and resctrl respectively.

While a comparison between performance counters and resctrl is
generally appropriate, they do not have an identical view of
memory bandwidth. For example RAS features or memory performance
features that generate memory traffic may drive accesses that are
counted differently by performance counters and MBM respectively,
for instance generating "overhead" traffic which is not counted
against any specific RMID. As a ratio, this different view of memory
bandwidth becomes more apparent at low memory bandwidths.

It is not practical to enable/disable the various features that
may generate memory bandwidth to give performance counters and
resctrl an identical view. Instead, do not compare performance
counters and resctrl view of memory bandwidth when the memory
bandwidth is low.

Bandwidth throttling behaves differently across platforms
so it is not appropriate to drop measurement data simply based
on the throttling level. Instead, use a threshold of 750MiB
that has been observed to support adequate comparison between
performance counters and resctrl.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/mba_test.c |  7 +++++++
 tools/testing/selftests/resctrl/resctrl.h  | 10 ++++++++++
 2 files changed, 17 insertions(+)

diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c
index bf37f35556607..5b4f0aa7a3a47 100644
--- a/tools/testing/selftests/resctrl/mba_test.c
+++ b/tools/testing/selftests/resctrl/mba_test.c
@@ -98,6 +98,13 @@ static bool show_mba_info(unsigned long *bw_imc, unsigned long *bw_resc)
 
 		avg_bw_imc = sum_bw_imc / (NUM_OF_RUNS - 1);
 		avg_bw_resc = sum_bw_resc / (NUM_OF_RUNS - 1);
+		if (avg_bw_imc < THROTTLE_THRESHOLD || avg_bw_resc < THROTTLE_THRESHOLD) {
+			ksft_print_msg("Bandwidth below threshold (%d MiB). Dropping results from MBA schemata %u.\n",
+				       THROTTLE_THRESHOLD,
+				       ALLOCATION_MIN + ALLOCATION_STEP * allocation);
+			continue;
+		}
+
 		avg_diff = (float)labs(avg_bw_resc - avg_bw_imc) / avg_bw_imc;
 		avg_diff_per = (int)(avg_diff * 100);
 
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index a553fe975938e..dab1953fc7a06 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -43,6 +43,16 @@
 
 #define MINIMUM_SPAN		(250 * MB)
 
+/*
+ * Memory bandwidth (in MiB) below which the bandwidth comparisons
+ * between iMC and resctrl are considered unreliable. For example RAS
+ * features or memory performance features that generate memory traffic
+ * may drive accesses that are counted differently by performance counters
+ * and MBM respectively, for instance generating "overhead" traffic which
+ * is not counted against any specific RMID.
+ */
+#define THROTTLE_THRESHOLD	750
+
 /*
  * fill_buf_param:	"fill_buf" benchmark parameters
  * @buf_size:		Size (in bytes) of buffer used in benchmark.

From ce860588d8347a84c97858d02b053a4e8fab9b26 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Thu, 24 Oct 2024 14:18:51 -0700
Subject: [PATCH 217/236] selftests/resctrl: Keep results from first test run
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 295b898426d8fb5b79672d1dae358ca8070f2196 upstream.

The resctrl selftests drop the results from every first test run
to avoid (per comment) "inaccurate due to monitoring setup transition
phase" data. Previously inaccurate data resulted from workloads needing
some time to "settle" and also the measurements themselves to
account for earlier measurements to measure across needed timeframe.

commit da50de0a92f3 ("selftests/resctrl: Calculate resctrl FS derived mem
bw over sleep(1) only")

ensured that measurements accurately measure just the time frame of
interest. The default "fill_buf" benchmark since separated the buffer
prepare phase from the benchmark run phase reducing the need for the
tests themselves to accommodate the benchmark's "settle" time.

With these enhancements there are no remaining portions needing
to "settle" and the first test run can contribute to measurements.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cmt_test.c |  5 ++---
 tools/testing/selftests/resctrl/mba_test.c | 10 +++-------
 tools/testing/selftests/resctrl/mbm_test.c | 10 +++-------
 3 files changed, 8 insertions(+), 17 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c
index 4c3cf2c25a38f..3bbf3042fb06e 100644
--- a/tools/testing/selftests/resctrl/cmt_test.c
+++ b/tools/testing/selftests/resctrl/cmt_test.c
@@ -99,14 +99,13 @@ static int check_results(struct resctrl_val_param *param, size_t span, int no_of
 		}
 
 		/* Field 3 is llc occ resc value */
-		if (runs > 0)
-			sum_llc_occu_resc += strtoul(token_array[3], NULL, 0);
+		sum_llc_occu_resc += strtoul(token_array[3], NULL, 0);
 		runs++;
 	}
 	fclose(fp);
 
 	return show_results_info(sum_llc_occu_resc, no_of_bits, span,
-				 MAX_DIFF, MAX_DIFF_PERCENT, runs - 1, true);
+				 MAX_DIFF, MAX_DIFF_PERCENT, runs, true);
 }
 
 static void cmt_test_cleanup(void)
diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c
index 5b4f0aa7a3a47..4e6645b172e3c 100644
--- a/tools/testing/selftests/resctrl/mba_test.c
+++ b/tools/testing/selftests/resctrl/mba_test.c
@@ -86,18 +86,14 @@ static bool show_mba_info(unsigned long *bw_imc, unsigned long *bw_resc)
 		int avg_diff_per;
 		float avg_diff;
 
-		/*
-		 * The first run is discarded due to inaccurate value from
-		 * phase transition.
-		 */
-		for (runs = NUM_OF_RUNS * allocation + 1;
+		for (runs = NUM_OF_RUNS * allocation;
 		     runs < NUM_OF_RUNS * allocation + NUM_OF_RUNS ; runs++) {
 			sum_bw_imc += bw_imc[runs];
 			sum_bw_resc += bw_resc[runs];
 		}
 
-		avg_bw_imc = sum_bw_imc / (NUM_OF_RUNS - 1);
-		avg_bw_resc = sum_bw_resc / (NUM_OF_RUNS - 1);
+		avg_bw_imc = sum_bw_imc / NUM_OF_RUNS;
+		avg_bw_resc = sum_bw_resc / NUM_OF_RUNS;
 		if (avg_bw_imc < THROTTLE_THRESHOLD || avg_bw_resc < THROTTLE_THRESHOLD) {
 			ksft_print_msg("Bandwidth below threshold (%d MiB). Dropping results from MBA schemata %u.\n",
 				       THROTTLE_THRESHOLD,
diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c
index 4224f8ce35385..315b2ef3b3bcb 100644
--- a/tools/testing/selftests/resctrl/mbm_test.c
+++ b/tools/testing/selftests/resctrl/mbm_test.c
@@ -22,17 +22,13 @@ show_bw_info(unsigned long *bw_imc, unsigned long *bw_resc, size_t span)
 	int runs, ret, avg_diff_per;
 	float avg_diff = 0;
 
-	/*
-	 * Discard the first value which is inaccurate due to monitoring setup
-	 * transition phase.
-	 */
-	for (runs = 1; runs < NUM_OF_RUNS ; runs++) {
+	for (runs = 0; runs < NUM_OF_RUNS; runs++) {
 		sum_bw_imc += bw_imc[runs];
 		sum_bw_resc += bw_resc[runs];
 	}
 
-	avg_bw_imc = sum_bw_imc / 4;
-	avg_bw_resc = sum_bw_resc / 4;
+	avg_bw_imc = sum_bw_imc / NUM_OF_RUNS;
+	avg_bw_resc = sum_bw_resc / NUM_OF_RUNS;
 	avg_diff = (float)labs(avg_bw_resc - avg_bw_imc) / avg_bw_imc;
 	avg_diff_per = (int)(avg_diff * 100);
 

From 02bdac6d2df944a353278036cc1e94b0bd182677 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Thu, 24 Oct 2024 14:18:52 -0700
Subject: [PATCH 218/236] selftests/resctrl: Replace magic constants used as
 array size
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit a44c26d7fa74a5f4d2795a5c55a2d6ec1ebf1e38 upstream.

The Memory Bandwidth Allocation (MBA) test iterates through all possible
MBA allocations, from 10% (ALLOCATION_MIN) to 100% (ALLOCATION_MAX) with
increments of 10% (ALLOCATION_STEP) at each iteration. During each
iteration the test measures the actual memory bandwidth NUM_OF_RUNS times
to determine the impact of MBA on actual memory bandwidth.

After the MBA test completes all the memory bandwidth measurements are
parsed into an array. One array for resctrl Memory Bandwidth Monitoring
(MBM) measurements and one array for the Integrated Memory Controller
(iMC) measurements. Each array has a hardcoded size of 1024 that is
large enough to hold the current test data, but this hardcoded value makes
the implementation difficult to understand. It will not be clear that this
array needs to be reconsidered if any of the test parameters are changed.

Replace the magic constant as array size with the test parameters the
array size depends on.

Reported-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Closes: https://lore.kernel.org/all/45af2a8c-517d-8f0d-137d-ad0f3f6a3c68@linux.intel.com/
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/mba_test.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c
index 4e6645b172e3c..536d9089d2f6c 100644
--- a/tools/testing/selftests/resctrl/mba_test.c
+++ b/tools/testing/selftests/resctrl/mba_test.c
@@ -127,8 +127,9 @@ static bool show_mba_info(unsigned long *bw_imc, unsigned long *bw_resc)
 
 static int check_results(void)
 {
+	unsigned long bw_resc[NUM_OF_RUNS * ALLOCATION_MAX / ALLOCATION_STEP];
+	unsigned long bw_imc[NUM_OF_RUNS * ALLOCATION_MAX / ALLOCATION_STEP];
 	char *token_array[8], output[] = RESULT_FILE_NAME, temp[512];
-	unsigned long bw_imc[1024], bw_resc[1024];
 	int runs;
 	FILE *fp;
 

From 6470a22b5f8c43737f01f8e49a4d04b322ae9e5b Mon Sep 17 00:00:00 2001
From: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Date: Mon, 16 Dec 2024 16:18:53 +0100
Subject: [PATCH 219/236] selftests/resctrl: Adjust effective L3 cache size
 with SNC enabled

commit a1cd99e700ec006c36c4f01be984e2a19eb3e2f1 upstream.

Sub-NUMA Cluster divides CPUs sharing an L3 cache into separate NUMA
nodes. Systems may support splitting into either two, three, four or six
nodes. When SNC mode is enabled the effective amount of L3 cache
available for allocation is divided by the number of nodes per L3.

It's possible to detect which SNC mode is active by comparing the number
of CPUs that share a cache with CPU0, with the number of CPUs on node0.

Detect SNC mode once and let other tests inherit that information.

Update CFLAGS after including lib.mk in the Makefile so that fallthrough
macro can be used.

To check if SNC detection is reliable one can check the
/sys/devices/system/cpu/offline file. If it's empty, it means all cores
are operational and the ratio should be calculated correctly. If it has
any contents, it means the detected SNC mode can't be trusted and should
be disabled.

Check if detection was not reliable due to offline cpus. If it was skip
running tests since the results couldn't be trusted.

Co-developed-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/Makefile      |   1 +
 tools/testing/selftests/resctrl/resctrl.h     |   5 +
 .../testing/selftests/resctrl/resctrl_tests.c |   9 +-
 tools/testing/selftests/resctrl/resctrlfs.c   | 105 ++++++++++++++++++
 4 files changed, 119 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/resctrl/Makefile b/tools/testing/selftests/resctrl/Makefile
index 021863f86053a..bad806e0a4f4e 100644
--- a/tools/testing/selftests/resctrl/Makefile
+++ b/tools/testing/selftests/resctrl/Makefile
@@ -8,5 +8,6 @@ TEST_GEN_PROGS := resctrl_tests
 LOCAL_HDRS += $(wildcard *.h)
 
 include ../lib.mk
+CFLAGS += -I$(top_srcdir)/tools/include
 
 $(OUTPUT)/resctrl_tests: $(wildcard *.c)
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index dab1953fc7a06..35fa3afee9c3c 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -11,6 +11,7 @@
 #include <signal.h>
 #include <dirent.h>
 #include <stdbool.h>
+#include <ctype.h>
 #include <sys/stat.h>
 #include <sys/ioctl.h>
 #include <sys/mount.h>
@@ -21,6 +22,7 @@
 #include <sys/eventfd.h>
 #include <asm/unistd.h>
 #include <linux/perf_event.h>
+#include <linux/compiler.h>
 #include "../kselftest.h"
 
 #define MB			(1024 * 1024)
@@ -156,8 +158,11 @@ struct perf_event_read {
  */
 extern volatile int *value_sink;
 
+extern int snc_unreliable;
+
 extern char llc_occup_path[1024];
 
+int snc_nodes_per_l3_cache(void);
 int get_vendor(void);
 bool check_resctrlfs_support(void);
 int filter_dmesg(void);
diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c
index 3335af815b210..5154ffd821c44 100644
--- a/tools/testing/selftests/resctrl/resctrl_tests.c
+++ b/tools/testing/selftests/resctrl/resctrl_tests.c
@@ -118,7 +118,7 @@ static bool test_vendor_specific_check(const struct resctrl_test *test)
 
 static void run_single_test(const struct resctrl_test *test, const struct user_params *uparams)
 {
-	int ret;
+	int ret, snc_mode;
 
 	if (test->disabled)
 		return;
@@ -128,8 +128,15 @@ static void run_single_test(const struct resctrl_test *test, const struct user_p
 		return;
 	}
 
+	snc_mode = snc_nodes_per_l3_cache();
+
 	ksft_print_msg("Starting %s test ...\n", test->name);
 
+	if (snc_mode == 1 && snc_unreliable && get_vendor() == ARCH_INTEL) {
+		ksft_test_result_skip("SNC detection unreliable due to offline CPUs. Test results may not be accurate if SNC enabled.\n");
+		return;
+	}
+
 	if (test_prepare(test)) {
 		ksft_exit_fail_msg("Abnormal failure when preparing for the test\n");
 		return;
diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index d38d6dd90be44..dc7ce3cbdb271 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -13,6 +13,8 @@
 
 #include "resctrl.h"
 
+int snc_unreliable;
+
 static int find_resctrl_mount(char *buffer)
 {
 	FILE *mounts;
@@ -156,6 +158,98 @@ int get_domain_id(const char *resource, int cpu_no, int *domain_id)
 	return 0;
 }
 
+/*
+ * Count number of CPUs in a /sys bitmap
+ */
+static unsigned int count_sys_bitmap_bits(char *name)
+{
+	FILE *fp = fopen(name, "r");
+	int count = 0, c;
+
+	if (!fp)
+		return 0;
+
+	while ((c = fgetc(fp)) != EOF) {
+		if (!isxdigit(c))
+			continue;
+		switch (c) {
+		case 'f':
+			count++;
+			fallthrough;
+		case '7': case 'b': case 'd': case 'e':
+			count++;
+			fallthrough;
+		case '3': case '5': case '6': case '9': case 'a': case 'c':
+			count++;
+			fallthrough;
+		case '1': case '2': case '4': case '8':
+			count++;
+			break;
+		}
+	}
+	fclose(fp);
+
+	return count;
+}
+
+static bool cpus_offline_empty(void)
+{
+	char offline_cpus_str[64];
+	FILE *fp;
+
+	fp = fopen("/sys/devices/system/cpu/offline", "r");
+	if (!fp) {
+		ksft_perror("Could not open /sys/devices/system/cpu/offline");
+		return 0;
+	}
+
+	if (fscanf(fp, "%63s", offline_cpus_str) < 0) {
+		if (!errno) {
+			fclose(fp);
+			return 1;
+		}
+		ksft_perror("Could not read /sys/devices/system/cpu/offline");
+	}
+
+	fclose(fp);
+
+	return 0;
+}
+
+/*
+ * Detect SNC by comparing #CPUs in node0 with #CPUs sharing LLC with CPU0.
+ * If any CPUs are offline declare the detection as unreliable.
+ */
+int snc_nodes_per_l3_cache(void)
+{
+	int node_cpus, cache_cpus;
+	static int snc_mode;
+
+	if (!snc_mode) {
+		snc_mode = 1;
+		if (!cpus_offline_empty()) {
+			ksft_print_msg("Runtime SNC detection unreliable due to offline CPUs.\n");
+			ksft_print_msg("Setting SNC mode to disabled.\n");
+			snc_unreliable = 1;
+			return snc_mode;
+		}
+		node_cpus = count_sys_bitmap_bits("/sys/devices/system/node/node0/cpumap");
+		cache_cpus = count_sys_bitmap_bits("/sys/devices/system/cpu/cpu0/cache/index3/shared_cpu_map");
+
+		if (!node_cpus || !cache_cpus) {
+			ksft_print_msg("Could not determine Sub-NUMA Cluster mode.\n");
+			snc_unreliable = 1;
+			return snc_mode;
+		}
+		snc_mode = cache_cpus / node_cpus;
+
+		if (snc_mode > 1)
+			ksft_print_msg("SNC-%d mode discovered.\n", snc_mode);
+	}
+
+	return snc_mode;
+}
+
 /*
  * get_cache_size - Get cache size for a specified CPU
  * @cpu_no:	CPU number
@@ -211,6 +305,17 @@ int get_cache_size(int cpu_no, const char *cache_type, unsigned long *cache_size
 			break;
 	}
 
+	/*
+	 * The amount of cache represented by each bit in the masks
+	 * in the schemata file is reduced by a factor equal to SNC
+	 * nodes per L3 cache.
+	 * E.g. on a SNC-2 system with a 100MB L3 cache a test that
+	 * allocates memory from its local SNC node (default behavior
+	 * without using libnuma) will only see 50 MB llc_occupancy
+	 * with a fully populated L3 mask in the schemata file.
+	 */
+	if (cache_num == 3)
+		*cache_size /= snc_nodes_per_l3_cache();
 	return 0;
 }
 

From 02af41cc59d5472b2764d6162ee7f16bf703b541 Mon Sep 17 00:00:00 2001
From: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Date: Mon, 16 Dec 2024 16:18:54 +0100
Subject: [PATCH 220/236] selftests/resctrl: Discover SNC kernel support and
 adjust messages

commit d6d35d0b0f4267612eb905305f3f2f7aa048bfd4 upstream.

Resctrl selftest prints a message on test failure that Sub-Numa
Clustering (SNC) could be enabled and points the user to check their BIOS
settings. No actual check is performed before printing that message so
it is not very accurate in pinpointing a problem.

When there is SNC support for kernel's resctrl subsystem and SNC is
enabled then sub node files are created for each node in the resctrlfs.
The sub node files exist in each regular node's L3 monitoring directory.
The reliable path to check for existence of sub node files is
/sys/fs/resctrl/mon_data/mon_L3_00/mon_sub_L3_00.

Add helper that checks for mon_sub_L3_00 existence.

Correct old messages to account for kernel support of SNC in
resctrl.

Signed-off-by: Maciej Wieczor-Retman <maciej.wieczor-retman@intel.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cmt_test.c  |  4 +--
 tools/testing/selftests/resctrl/mba_test.c  |  2 ++
 tools/testing/selftests/resctrl/mbm_test.c  |  4 +--
 tools/testing/selftests/resctrl/resctrl.h   |  1 +
 tools/testing/selftests/resctrl/resctrlfs.c | 32 +++++++++++++++++++++
 5 files changed, 39 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c
index 3bbf3042fb06e..d09e693dc739c 100644
--- a/tools/testing/selftests/resctrl/cmt_test.c
+++ b/tools/testing/selftests/resctrl/cmt_test.c
@@ -169,8 +169,8 @@ static int cmt_run_test(const struct resctrl_test *test, const struct user_param
 		return ret;
 
 	ret = check_results(&param, span, n);
-	if (ret && (get_vendor() == ARCH_INTEL))
-		ksft_print_msg("Intel CMT may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n");
+	if (ret && (get_vendor() == ARCH_INTEL) && !snc_kernel_support())
+		ksft_print_msg("Kernel doesn't support Sub-NUMA Clustering but it is enabled on the system.\n");
 
 	return ret;
 }
diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c
index 536d9089d2f6c..c7e9adc0368f3 100644
--- a/tools/testing/selftests/resctrl/mba_test.c
+++ b/tools/testing/selftests/resctrl/mba_test.c
@@ -201,6 +201,8 @@ static int mba_run_test(const struct resctrl_test *test, const struct user_param
 		return ret;
 
 	ret = check_results();
+	if (ret && (get_vendor() == ARCH_INTEL) && !snc_kernel_support())
+		ksft_print_msg("Kernel doesn't support Sub-NUMA Clustering but it is enabled on the system.\n");
 
 	return ret;
 }
diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c
index 315b2ef3b3bcb..84d8bc2505392 100644
--- a/tools/testing/selftests/resctrl/mbm_test.c
+++ b/tools/testing/selftests/resctrl/mbm_test.c
@@ -160,8 +160,8 @@ static int mbm_run_test(const struct resctrl_test *test, const struct user_param
 		return ret;
 
 	ret = check_results(param.fill_buf ? param.fill_buf->buf_size : 0);
-	if (ret && (get_vendor() == ARCH_INTEL))
-		ksft_print_msg("Intel MBM may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n");
+	if (ret && (get_vendor() == ARCH_INTEL) && !snc_kernel_support())
+		ksft_print_msg("Kernel doesn't support Sub-NUMA Clustering but it is enabled on the system.\n");
 
 	return ret;
 }
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 35fa3afee9c3c..cd3adfc14969f 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -203,6 +203,7 @@ void ctrlc_handler(int signum, siginfo_t *info, void *ptr);
 int signal_handler_register(const struct resctrl_test *test);
 void signal_handler_unregister(void);
 unsigned int count_bits(unsigned long n);
+int snc_kernel_support(void);
 
 void perf_event_attr_initialize(struct perf_event_attr *pea, __u64 config);
 void perf_event_initialize_read_format(struct perf_event_read *pe_read);
diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index dc7ce3cbdb271..195f04c4d1586 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -957,3 +957,35 @@ unsigned int count_bits(unsigned long n)
 
 	return count;
 }
+
+/**
+ * snc_kernel_support - Check for existence of mon_sub_L3_00 file that indicates
+ * SNC resctrl support on the kernel side.
+ *
+ * Return: 0 if not supported, 1 if SNC is disabled or SNC discovery is
+ * unreliable or SNC is both enabled and supported.
+ */
+int snc_kernel_support(void)
+{
+	char node_path[PATH_MAX];
+	struct stat statbuf;
+	int ret;
+
+	ret = snc_nodes_per_l3_cache();
+	/*
+	 * If SNC is disabled then its kernel support isn't important. If SNC
+	 * got disabled because the discovery process was unreliable the
+	 * snc_unreliable variable was set. It can be used to verify the SNC
+	 * discovery reliability elsewhere in the selftest.
+	 */
+	if (ret == 1)
+		return ret;
+
+	snprintf(node_path, sizeof(node_path), "%s/%s", RESCTRL_PATH,
+		 "mon_data/mon_L3_00/mon_sub_L3_00");
+
+	if (!stat(node_path, &statbuf))
+		return 1;
+
+	return 0;
+}

From 7a9cb79f250d25a6f27d3ad18a16b826cffb8948 Mon Sep 17 00:00:00 2001
From: Xiaochen Shen <shenxiaochen@open-hieco.net>
Date: Wed, 17 Dec 2025 11:04:53 +0800
Subject: [PATCH 221/236] selftests/resctrl: Fix a division by zero error on
 Hygon

commit 671ef08d9455f5754d1fc96f5a14e357d6b80936 upstream.

Change to adjust effective L3 cache size with SNC enabled change
introduced the snc_nodes_per_l3_cache() function to detect the Intel
Sub-NUMA Clustering (SNC) feature by comparing #CPUs in node0 with #CPUs
sharing LLC with CPU0. The function was designed to return:
  (1) >1: SNC mode is enabled.
  (2)  1: SNC mode is not enabled or not supported.

However, on certain Hygon CPUs, #CPUs sharing LLC with CPU0 is actually
less than #CPUs in node0. This results in snc_nodes_per_l3_cache()
returning 0 (calculated as cache_cpus / node_cpus).

This leads to a division by zero error in get_cache_size():
  *cache_size /= snc_nodes_per_l3_cache();

Causing the resctrl selftest to fail with:
  "Floating point exception (core dumped)"

Fix the issue by ensuring snc_nodes_per_l3_cache() returns 1 when SNC
mode is not supported on the platform.

Updated commit log to fix commit has issues:
Shuah Khan <skhan@linuxfoundation.org>

Link: https://lore.kernel.org/r/20251217030456.3834956-2-shenxiaochen@open-hieco.net
Fixes: a1cd99e700ec ("selftests/resctrl: Adjust effective L3 cache size with SNC enabled")
Signed-off-by: Xiaochen Shen <shenxiaochen@open-hieco.net>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/resctrlfs.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c
index 195f04c4d1586..b9c1bfb6cc029 100644
--- a/tools/testing/selftests/resctrl/resctrlfs.c
+++ b/tools/testing/selftests/resctrl/resctrlfs.c
@@ -243,6 +243,16 @@ int snc_nodes_per_l3_cache(void)
 		}
 		snc_mode = cache_cpus / node_cpus;
 
+		/*
+		 * On some platforms (e.g. Hygon),
+		 * cache_cpus < node_cpus, the calculated snc_mode is 0.
+		 *
+		 * Set snc_mode = 1 to indicate that SNC mode is not
+		 * supported on the platform.
+		 */
+		if (!snc_mode)
+			snc_mode = 1;
+
 		if (snc_mode > 1)
 			ksft_print_msg("SNC-%d mode discovered.\n", snc_mode);
 	}

From 5a4fa7e277978f1ed30780f47d94f1a5b678dcf5 Mon Sep 17 00:00:00 2001
From: Xiaochen Shen <shenxiaochen@open-hieco.net>
Date: Wed, 17 Dec 2025 11:04:54 +0800
Subject: [PATCH 222/236] selftests/resctrl: Define CPU vendor IDs as bits to
 match usage

commit 4f4f01cc333e97b0e63b61ed1a65c928aa662f99 upstream.

The CPU vendor IDs are required to be unique bits because they're used
for vendor_specific bitmask in the struct resctrl_test.
Consider for example their usage in test_vendor_specific_check():
	return get_vendor() & test->vendor_specific

However, the definitions of CPU vendor IDs in file resctrl.h is quite
subtle as a bitmask value:
  #define ARCH_INTEL     1
  #define ARCH_AMD       2

A clearer and more maintainable approach is to define these CPU vendor
IDs using BIT(). This ensures each vendor corresponds to a distinct bit
and makes it obvious when adding new vendor IDs.

Accordingly, update the return types of detect_vendor() and get_vendor()
from 'int' to 'unsigned int' to align with their usage as bitmask values
and to prevent potentially risky type conversions.

Furthermore, introduce a bool flag 'initialized' to simplify the
get_vendor() -> detect_vendor() logic. This ensures the vendor ID is
detected only once and resolves the ambiguity of using the same variable
'vendor' both as a value and as a state.

Link: https://lore.kernel.org/r/20251217030456.3834956-3-shenxiaochen@open-hieco.net
Suggested-by: Reinette Chatre <reinette.chatre@intel.com>
Suggested-by: Fenghua Yu <fenghuay@nvidia.com>
Signed-off-by: Xiaochen Shen <shenxiaochen@open-hieco.net>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>

 Conflicts:
	tools/testing/selftests/resctrl/resctrl.h
[jz: resolve context conflict due to e6fbd1759c9e
     ("selftests: complete kselftest include centralization") not
     backported]
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/resctrl.h     |  7 ++---
 .../testing/selftests/resctrl/resctrl_tests.c | 26 +++++++++++++------
 2 files changed, 22 insertions(+), 11 deletions(-)

diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index cd3adfc14969f..d0f094360e6f1 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -23,6 +23,7 @@
 #include <asm/unistd.h>
 #include <linux/perf_event.h>
 #include <linux/compiler.h>
+#include <linux/bits.h>
 #include "../kselftest.h"
 
 #define MB			(1024 * 1024)
@@ -36,8 +37,8 @@
  * Define as bits because they're used for vendor_specific bitmask in
  * the struct resctrl_test.
  */
-#define ARCH_INTEL     1
-#define ARCH_AMD       2
+#define ARCH_INTEL	BIT(0)
+#define ARCH_AMD	BIT(1)
 
 #define END_OF_TESTS	1
 
@@ -163,7 +164,7 @@ extern int snc_unreliable;
 extern char llc_occup_path[1024];
 
 int snc_nodes_per_l3_cache(void);
-int get_vendor(void);
+unsigned int get_vendor(void);
 bool check_resctrlfs_support(void);
 int filter_dmesg(void);
 int get_domain_id(const char *resource, int cpu_no, int *domain_id);
diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c
index 5154ffd821c44..42605e2a3b66d 100644
--- a/tools/testing/selftests/resctrl/resctrl_tests.c
+++ b/tools/testing/selftests/resctrl/resctrl_tests.c
@@ -23,16 +23,24 @@ static struct resctrl_test *resctrl_tests[] = {
 	&l2_noncont_cat_test,
 };
 
-static int detect_vendor(void)
+static unsigned int detect_vendor(void)
 {
-	FILE *inf = fopen("/proc/cpuinfo", "r");
-	int vendor_id = 0;
+	static unsigned int vendor_id;
+	static bool initialized;
 	char *s = NULL;
+	FILE *inf;
 	char *res;
 
-	if (!inf)
+	if (initialized)
 		return vendor_id;
 
+	inf = fopen("/proc/cpuinfo", "r");
+	if (!inf) {
+		vendor_id = 0;
+		initialized = true;
+		return vendor_id;
+	}
+
 	res = fgrep(inf, "vendor_id");
 
 	if (res)
@@ -45,15 +53,17 @@ static int detect_vendor(void)
 
 	fclose(inf);
 	free(res);
+
+	initialized = true;
 	return vendor_id;
 }
 
-int get_vendor(void)
+unsigned int get_vendor(void)
 {
-	static int vendor = -1;
+	unsigned int vendor;
+
+	vendor = detect_vendor();
 
-	if (vendor == -1)
-		vendor = detect_vendor();
 	if (vendor == 0)
 		ksft_print_msg("Can not get vendor info...\n");
 

From 4bcfdd23a4c644d67d12846c47be8e296b579aa9 Mon Sep 17 00:00:00 2001
From: Xiaochen Shen <shenxiaochen@open-hieco.net>
Date: Wed, 17 Dec 2025 11:04:55 +0800
Subject: [PATCH 223/236] selftests/resctrl: Add CPU vendor detection for Hygon

commit 367f931e6476747edbde4e7c7b95fc5d5b724934 upstream.

The resctrl selftest currently fails on Hygon CPUs that support Platform
QoS features, printing the error:

  "# Can not get vendor info..."

This occurs because vendor detection is missing for Hygon CPUs.

Fix this by extending the CPU vendor detection logic to include
Hygon's vendor ID.

Link: https://lore.kernel.org/r/20251217030456.3834956-4-shenxiaochen@open-hieco.net
Signed-off-by: Xiaochen Shen <shenxiaochen@open-hieco.net>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/resctrl.h       | 1 +
 tools/testing/selftests/resctrl/resctrl_tests.c | 2 ++
 2 files changed, 3 insertions(+)

diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index d0f094360e6f1..2817c9e41797c 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -39,6 +39,7 @@
  */
 #define ARCH_INTEL	BIT(0)
 #define ARCH_AMD	BIT(1)
+#define ARCH_HYGON	BIT(2)
 
 #define END_OF_TESTS	1
 
diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c
index 42605e2a3b66d..dbcd5eea9fbc9 100644
--- a/tools/testing/selftests/resctrl/resctrl_tests.c
+++ b/tools/testing/selftests/resctrl/resctrl_tests.c
@@ -50,6 +50,8 @@ static unsigned int detect_vendor(void)
 		vendor_id = ARCH_INTEL;
 	else if (s && !strcmp(s, ": AuthenticAMD\n"))
 		vendor_id = ARCH_AMD;
+	else if (s && !strcmp(s, ": HygonGenuine\n"))
+		vendor_id = ARCH_HYGON;
 
 	fclose(inf);
 	free(res);

From 509c45efc458b16ecfe3a9155079aee9e699c50d Mon Sep 17 00:00:00 2001
From: Xiaochen Shen <shenxiaochen@open-hieco.net>
Date: Wed, 17 Dec 2025 11:04:56 +0800
Subject: [PATCH 224/236] selftests/resctrl: Fix non-contiguous CBM check for
 Hygon

commit 86063a2568b8f2eeb68da1411b320c0ff778f852 upstream.

The resctrl selftest currently fails on Hygon CPUs that always supports
non-contiguous CBM, printing the error:

  "# Hardware and kernel differ on non-contiguous CBM support!"

This occurs because the arch_supports_noncont_cat() function lacks
vendor detection for Hygon CPUs, preventing proper identification of
their non-contiguous CBM capability.

Fix this by adding Hygon vendor ID detection to
arch_supports_noncont_cat().

Link: https://lore.kernel.org/r/20251217030456.3834956-5-shenxiaochen@open-hieco.net
Signed-off-by: Xiaochen Shen <shenxiaochen@open-hieco.net>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Fenghua Yu <fenghuay@nvidia.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cat_test.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
index 94cfdba5308d8..f00b622c14608 100644
--- a/tools/testing/selftests/resctrl/cat_test.c
+++ b/tools/testing/selftests/resctrl/cat_test.c
@@ -290,8 +290,10 @@ static int cat_run_test(const struct resctrl_test *test, const struct user_param
 
 static bool arch_supports_noncont_cat(const struct resctrl_test *test)
 {
-	/* AMD always supports non-contiguous CBM. */
-	if (get_vendor() == ARCH_AMD)
+	unsigned int vendor_id = get_vendor();
+
+	/* AMD and Hygon always support non-contiguous CBM. */
+	if (vendor_id == ARCH_AMD || vendor_id == ARCH_HYGON)
 		return true;
 
 #if defined(__i386__) || defined(__x86_64__) /* arch */

From 0ba8c5bf406d1170655692ae5aa6e0c8fb4cf58a Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 3 Apr 2026 18:56:00 -0700
Subject: [PATCH 225/236] selftests/resctrl: Improve accuracy of cache
 occupancy test
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 7a214b4ec1c967533439b4ef16941cabb52a88a8 upstream.

Dave Martin reported inconsistent CMT test failures. In one experiment
the first run of the CMT test failed because of too large (24%) difference
between measured and achievable cache occupancy while the second run passed
with an acceptable 4% difference.

The CMT test is susceptible to interference from the rest of the system.
This can be demonstrated with a utility like stress-ng by running the CMT
test while introducing cache misses using:

   stress-ng --matrix-3d 0 --matrix-3d-zyx

Below shows an example of the CMT test failing because of a significant
difference between measured and achievable cache occupancy when run with
interference:
    # Starting CMT test ...
    # Mounting resctrl to "/sys/fs/resctrl"
    # Cache size :335544320
    # Writing benchmark parameters to resctrl FS
    # Benchmark PID: 7011
    # Checking for pass/fail
    # Fail: Check cache miss rate within 15%
    # Percent diff=99
    # Number of bits: 5
    # Average LLC val: 235929
    # Cache span (bytes): 83886080
    not ok 1 CMT: test

The CMT test creates a new control group that is also capable of monitoring
and assigns the workload to it. The workload allocates a buffer that by
default fills a portion of the L3 and keeps reading from the buffer,
measuring the L3 occupancy at intervals. The test passes if the workload's
L3 occupancy is within 15% of the buffer size.

By not adjusting any capacity bitmasks the workload shares the cache with
the rest of the system. Any other task that may be running could evict
the workload's data from the cache causing it to have low cache occupancy.

Reduce interference from the rest of the system by ensuring that the
workload's control group uses the capacity bitmask found in the user
parameters for L3 and that the rest of the system can only allocate into
the inverse of the workload's L3 cache portion. Other tasks can thus no
longer evict the workload's data from L3.

With the above adjustments the CMT test is more consistent. Repeating the
CMT test while generating interference with stress-ng on a sample
system after applying the fixes show significant improvement in test
accuracy:

    # Starting CMT test ...
    # Mounting resctrl to "/sys/fs/resctrl"
    # Cache size :335544320
    # Writing benchmark parameters to resctrl FS
    # Write schema "L3:0=fffe0" to resctrl FS
    # Write schema "L3:0=1f" to resctrl FS
    # Benchmark PID: 7089
    # Checking for pass/fail
    # Pass: Check cache miss rate within 15%
    # Percent diff=12
    # Number of bits: 5
    # Average LLC val: 73269248
    # Cache span (bytes): 83886080
    ok 1 CMT: test

Link: https://lore.kernel.org/r/b160592179f88069cdc679563e152007998a0d76.1775266384.git.reinette.chatre@intel.com
Reported-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Chen Yu <yu.c.chen@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/lkml/aO+7MeSMV29VdbQs@e133380.arm.com/
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cmt_test.c    | 26 +++++++++++++++++--
 tools/testing/selftests/resctrl/mba_test.c    |  4 ++-
 tools/testing/selftests/resctrl/mbm_test.c    |  4 ++-
 tools/testing/selftests/resctrl/resctrl.h     |  4 ++-
 tools/testing/selftests/resctrl/resctrl_val.c |  2 +-
 5 files changed, 34 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c
index d09e693dc739c..7bc6cf49c1c5b 100644
--- a/tools/testing/selftests/resctrl/cmt_test.c
+++ b/tools/testing/selftests/resctrl/cmt_test.c
@@ -19,12 +19,34 @@
 #define CON_MON_LCC_OCCUP_PATH		\
 	"%s/%s/mon_data/mon_L3_%02d/llc_occupancy"
 
-static int cmt_init(const struct resctrl_val_param *param, int domain_id)
+/*
+ * Initialize capacity bitmasks (CBMs) of:
+ * - control group being tested per test parameters,
+ * - default resource group as inverse of control group being tested to prevent
+ *   other tasks from interfering with test.
+ */
+static int cmt_init(const struct resctrl_test *test,
+		    const struct user_params *uparams,
+		    const struct resctrl_val_param *param, int domain_id)
 {
+	unsigned long full_mask;
+	char schemata[64];
+	int ret;
+
 	sprintf(llc_occup_path, CON_MON_LCC_OCCUP_PATH, RESCTRL_PATH,
 		param->ctrlgrp, domain_id);
 
-	return 0;
+	ret = get_full_cbm(test->resource, &full_mask);
+	if (ret)
+		return ret;
+
+	snprintf(schemata, sizeof(schemata), "%lx", ~param->mask & full_mask);
+	ret = write_schemata("", schemata, uparams->cpu, test->resource);
+	if (ret)
+		return ret;
+
+	snprintf(schemata, sizeof(schemata), "%lx", param->mask);
+	return write_schemata(param->ctrlgrp, schemata, uparams->cpu, test->resource);
 }
 
 static int cmt_setup(const struct resctrl_test *test,
diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c
index c7e9adc0368f3..cd4c715b7ffd2 100644
--- a/tools/testing/selftests/resctrl/mba_test.c
+++ b/tools/testing/selftests/resctrl/mba_test.c
@@ -17,7 +17,9 @@
 #define ALLOCATION_MIN		10
 #define ALLOCATION_STEP		10
 
-static int mba_init(const struct resctrl_val_param *param, int domain_id)
+static int mba_init(const struct resctrl_test *test,
+		    const struct user_params *uparams,
+		    const struct resctrl_val_param *param, int domain_id)
 {
 	int ret;
 
diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c
index 84d8bc2505392..58201f8447404 100644
--- a/tools/testing/selftests/resctrl/mbm_test.c
+++ b/tools/testing/selftests/resctrl/mbm_test.c
@@ -83,7 +83,9 @@ static int check_results(size_t span)
 	return ret;
 }
 
-static int mbm_init(const struct resctrl_val_param *param, int domain_id)
+static int mbm_init(const struct resctrl_test *test,
+		    const struct user_params *uparams,
+		    const struct resctrl_val_param *param, int domain_id)
 {
 	int ret;
 
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 2817c9e41797c..8de935f0d4f0a 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -135,7 +135,9 @@ struct resctrl_val_param {
 	char			filename[64];
 	unsigned long		mask;
 	int			num_of_runs;
-	int			(*init)(const struct resctrl_val_param *param,
+	int			(*init)(const struct resctrl_test *test,
+					const struct user_params *uparams,
+					const struct resctrl_val_param *param,
 					int domain_id);
 	int			(*setup)(const struct resctrl_test *test,
 					 const struct user_params *uparams,
diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index 7c08e936572d2..a5a8badb83d45 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -569,7 +569,7 @@ int resctrl_val(const struct resctrl_test *test,
 		goto reset_affinity;
 
 	if (param->init) {
-		ret = param->init(param, domain_id);
+		ret = param->init(test, uparams, param, domain_id);
 		if (ret)
 			goto reset_affinity;
 	}

From 73c90968177f6c73e34ecba75fc32dd2e8deb978 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 3 Apr 2026 18:56:01 -0700
Subject: [PATCH 226/236] selftests/resctrl: Reduce interference from L2
 occupancy during cache occupancy test
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit ca0ea39288c980741283a1f4f272b1e92ace8f52 upstream.

The CMT test creates a new control group that is also capable of monitoring
and assigns the workload to it. The workload allocates a buffer that by
default fills a portion of the L3 and keeps reading from the buffer,
measuring the L3 occupancy at intervals. The test passes if the workload's
L3 occupancy is within 15% of the buffer size.

The CMT test does not take into account that some of the workload's data
may land in L2/L1. Matching L3 occupancy to the size of the buffer while
a portion of the buffer can be allocated into L2 is not accurate.

Take the L2 cache into account to improve test accuracy:
 - Reduce the workload's L2 cache allocation to the minimum on systems that
   support L2 cache allocation. Do so with a new utility in preparation for
   all L3 cache allocation tests needing the same capability.
 - Increase the buffer size to accommodate data that may be allocated into
   the L2 cache. Use a buffer size double the L3 portion to keep using the
   L3 portion size as goal for L3 occupancy while taking into account that
   some of the data may be in L2.

Running the CMT test on a sample system while introducing significant
cache misses using "stress-ng --matrix-3d 0 --matrix-3d-zyx" shows
significant improvement in L3 cache occupancy:

Before:

    # Starting CMT test ...
    # Mounting resctrl to "/sys/fs/resctrl"
    # Cache size :335544320
    # Writing benchmark parameters to resctrl FS
    # Write schema "L3:0=fffe0" to resctrl FS
    # Write schema "L3:0=1f" to resctrl FS
    # Benchmark PID: 7089
    # Checking for pass/fail
    # Pass: Check cache miss rate within 15%
    # Percent diff=12
    # Number of bits: 5
    # Average LLC val: 73269248
    # Cache span (bytes): 83886080
    ok 1 CMT: test

After:
    # Starting CMT test ...
    # Mounting resctrl to "/sys/fs/resctrl"
    # Cache size :335544320
    # Writing benchmark parameters to resctrl FS
    # Write schema "L3:0=fffe0" to resctrl FS
    # Write schema "L3:0=1f" to resctrl FS
    # Write schema "L2:1=0x1" to resctrl FS
    # Benchmark PID: 7171
    # Checking for pass/fail
    # Pass: Check cache miss rate within 15%
    # Percent diff=0
    # Number of bits: 5
    # Average LLC val: 83755008
    # Cache span (bytes): 83886080
    ok 1 CMT: test

Link: https://lore.kernel.org/r/00445fa64c251b86b86023f87220ee1ad8561460.1775266384.git.reinette.chatre@intel.com
Reported-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Chen Yu <yu.c.chen@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/lkml/aO+7MeSMV29VdbQs@e133380.arm.com/
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cache.c    | 13 +++++++++++++
 tools/testing/selftests/resctrl/cmt_test.c | 14 ++++++++++----
 tools/testing/selftests/resctrl/resctrl.h  |  3 +++
 3 files changed, 26 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c
index 1ff1104e65753..bef71b6feacc6 100644
--- a/tools/testing/selftests/resctrl/cache.c
+++ b/tools/testing/selftests/resctrl/cache.c
@@ -173,6 +173,19 @@ int measure_llc_resctrl(const char *filename, pid_t bm_pid)
 	return print_results_cache(filename, bm_pid, llc_occu_resc);
 }
 
+/*
+ * Reduce L2 allocation to minimum when testing L3 cache allocation.
+ */
+int minimize_l2_occupancy(const struct resctrl_test *test,
+			  const struct user_params *uparams,
+			  const struct resctrl_val_param *param)
+{
+	if (!strcmp(test->resource, "L3") && resctrl_resource_exists("L2"))
+		return write_schemata(param->ctrlgrp, "0x1", uparams->cpu, "L2");
+
+	return 0;
+}
+
 /*
  * show_cache_info - Show generic cache test information
  * @no_of_bits:		Number of bits
diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c
index 7bc6cf49c1c5b..ccb6fe881a948 100644
--- a/tools/testing/selftests/resctrl/cmt_test.c
+++ b/tools/testing/selftests/resctrl/cmt_test.c
@@ -23,7 +23,9 @@
  * Initialize capacity bitmasks (CBMs) of:
  * - control group being tested per test parameters,
  * - default resource group as inverse of control group being tested to prevent
- *   other tasks from interfering with test.
+ *   other tasks from interfering with test,
+ * - L2 resource of control group being tested to minimize allocations into
+ *   L2 if possible to better predict L3 occupancy.
  */
 static int cmt_init(const struct resctrl_test *test,
 		    const struct user_params *uparams,
@@ -46,7 +48,11 @@ static int cmt_init(const struct resctrl_test *test,
 		return ret;
 
 	snprintf(schemata, sizeof(schemata), "%lx", param->mask);
-	return write_schemata(param->ctrlgrp, schemata, uparams->cpu, test->resource);
+	ret = write_schemata(param->ctrlgrp, schemata, uparams->cpu, test->resource);
+	if (ret)
+		return ret;
+
+	return minimize_l2_occupancy(test, uparams, param);
 }
 
 static int cmt_setup(const struct resctrl_test *test,
@@ -175,11 +181,11 @@ static int cmt_run_test(const struct resctrl_test *test, const struct user_param
 	span = cache_portion_size(cache_total_size, param.mask, long_mask);
 
 	if (uparams->fill_buf) {
-		fill_buf.buf_size = span;
+		fill_buf.buf_size = span * 2;
 		fill_buf.memflush = uparams->fill_buf->memflush;
 		param.fill_buf = &fill_buf;
 	} else if (!uparams->benchmark_cmd[0]) {
-		fill_buf.buf_size = span;
+		fill_buf.buf_size = span * 2;
 		fill_buf.memflush = true;
 		param.fill_buf = &fill_buf;
 	}
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 8de935f0d4f0a..bac44eacf94dd 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -216,6 +216,9 @@ int perf_event_reset_enable(int pe_fd);
 int perf_event_measure(int pe_fd, struct perf_event_read *pe_read,
 		       const char *filename, pid_t bm_pid);
 int measure_llc_resctrl(const char *filename, pid_t bm_pid);
+int minimize_l2_occupancy(const struct resctrl_test *test,
+			  const struct user_params *uparams,
+			  const struct resctrl_val_param *param);
 void show_cache_info(int no_of_bits, __u64 avg_llc_val, size_t cache_span, bool lines);
 
 /*

From b258a52c035440dcbb55157d410563700915ac86 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 3 Apr 2026 18:56:02 -0700
Subject: [PATCH 227/236] selftests/resctrl: Do not store iMC counter value in
 counter config structure
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit c066a681ac2f331cc2e493cb0b4072d86c5291b5 upstream.

The MBM and MBA tests compare MBM memory bandwidth measurements against
the memory bandwidth event values obtained from each memory controller's
PMU. The memory bandwidth event settings are discovered from the memory
controller details found in /sys/bus/event_source/devices/uncore_imc_N and
stored in struct imc_counter_config.

In addition to event settings struct imc_counter_config contains
imc_counter_config::return_value in which the associated event value is
stored on every read.

The event value is consumed and immediately recorded at regular intervals.
The stored value is never consumed afterwards, making its storage as part
of event configuration unnecessary.

Remove the return_value member from struct imc_counter_config. Instead
just use a more aptly named "measurement" local variable for use during
event reading.

Link: https://lore.kernel.org/r/e0b6ad2755e2fd802f54b0bc07eeb90247baca19.1775266384.git.reinette.chatre@intel.com
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Chen Yu <yu.c.chen@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/resctrl_val.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index a5a8badb83d45..71d6f88cc1f7a 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -32,7 +32,6 @@ struct imc_counter_config {
 	__u64 event;
 	__u64 umask;
 	struct perf_event_attr pe;
-	struct membw_read_format return_value;
 	int fd;
 };
 
@@ -312,23 +311,23 @@ static int get_read_mem_bw_imc(float *bw_imc)
 	 * Take overflow into consideration before calculating total bandwidth.
 	 */
 	for (imc = 0; imc < imcs; imc++) {
+		struct membw_read_format measurement;
 		struct imc_counter_config *r =
 			&imc_counters_config[imc];
 
-		if (read(r->fd, &r->return_value,
-			 sizeof(struct membw_read_format)) == -1) {
+		if (read(r->fd, &measurement, sizeof(measurement)) == -1) {
 			ksft_perror("Couldn't get read bandwidth through iMC");
 			return -1;
 		}
 
-		__u64 r_time_enabled = r->return_value.time_enabled;
-		__u64 r_time_running = r->return_value.time_running;
+		__u64 r_time_enabled = measurement.time_enabled;
+		__u64 r_time_running = measurement.time_running;
 
 		if (r_time_enabled != r_time_running)
 			of_mul_read = (float)r_time_enabled /
 					(float)r_time_running;
 
-		reads += r->return_value.value * of_mul_read * SCALE;
+		reads += measurement.value * of_mul_read * SCALE;
 	}
 
 	*bw_imc = reads;

From 04b1242d80eeaa792abb5317e996e3d061f06764 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 3 Apr 2026 18:56:03 -0700
Subject: [PATCH 228/236] selftests/resctrl: Prepare for parsing multiple
 events per iMC
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit f3d3a8fcecc3e2a0d577b607f8812214c02e30d6 upstream.

The events needed to read memory bandwidth are discovered by iterating
over every memory controller (iMC) within /sys/bus/event_source/devices.
Each iMC's PMU is assumed to have one event to measure read memory
bandwidth that is represented by the sysfs cas_count_read file. The event's
configuration is read from "cas_count_read" and stored as an element of
imc_counters_config[] by read_from_imc_dir() that receives the
index of the array where to store the configuration as argument.

It is possible that an iMC's PMU may have more than one event that should
be used to measure memory bandwidth.

Change semantics to not provide the index of the array to
read_from_imc_dir() but instead a pointer to the index. This enables
read_from_imc_dir() to store configurations for more than one event by
incrementing the index to imc_counters_config[] itself.

Ensure that the same type is consistently used for the index as it is
passed around during counter configuration.

Link: https://lore.kernel.org/r/549e026d20af0381349e645c912e6470fce8bd7e.1775266384.git.reinette.chatre@intel.com
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Chen Yu <yu.c.chen@intel.com>
Reviewed-by: Zide Chen <zide.chen@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/resctrl_val.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index 71d6f88cc1f7a..6d766347e3fc9 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -73,7 +73,7 @@ static void read_mem_bw_ioctl_perf_event_ioc_disable(int i)
  * @cas_count_cfg:	Config
  * @count:		iMC number
  */
-static void get_read_event_and_umask(char *cas_count_cfg, int count)
+static void get_read_event_and_umask(char *cas_count_cfg, unsigned int count)
 {
 	char *token[MAX_TOKENS];
 	int i = 0;
@@ -110,7 +110,7 @@ static int open_perf_read_event(int i, int cpu_no)
 }
 
 /* Get type and config of an iMC counter's read event. */
-static int read_from_imc_dir(char *imc_dir, int count)
+static int read_from_imc_dir(char *imc_dir, unsigned int *count)
 {
 	char cas_count_cfg[1024], imc_counter_cfg[1024], imc_counter_type[1024];
 	FILE *fp;
@@ -123,7 +123,7 @@ static int read_from_imc_dir(char *imc_dir, int count)
 
 		return -1;
 	}
-	if (fscanf(fp, "%u", &imc_counters_config[count].type) <= 0) {
+	if (fscanf(fp, "%u", &imc_counters_config[*count].type) <= 0) {
 		ksft_perror("Could not get iMC type");
 		fclose(fp);
 
@@ -147,7 +147,8 @@ static int read_from_imc_dir(char *imc_dir, int count)
 	}
 	fclose(fp);
 
-	get_read_event_and_umask(cas_count_cfg, count);
+	get_read_event_and_umask(cas_count_cfg, *count);
+	*count += 1;
 
 	return 0;
 }
@@ -196,13 +197,12 @@ static int num_of_imcs(void)
 			if (temp[0] >= '0' && temp[0] <= '9') {
 				sprintf(imc_dir, "%s/%s/", DYN_PMU_PATH,
 					ep->d_name);
-				ret = read_from_imc_dir(imc_dir, count);
+				ret = read_from_imc_dir(imc_dir, &count);
 				if (ret) {
 					closedir(dp);
 
 					return ret;
 				}
-				count++;
 			}
 		}
 		closedir(dp);

From 2a1a72791c6370693dc0366872b3338c989a42b9 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 3 Apr 2026 18:56:04 -0700
Subject: [PATCH 229/236] selftests/resctrl: Support multiple events associated
 with iMC
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 7d97dfeae329921ac7cf0f55a0ec98dfc1886064 upstream.

The resctrl selftests discover needed parameters to perf_event_open() via
sysfs. The PMU associated with every memory controller (iMC) is discovered
via the /sys/bus/event_source/devices/uncore_imc_N/type file while
the read memory bandwidth event type and umask is discovered via
/sys/bus/event_source/devices/uncore_imc_N/events/cas_count_read.

Newer systems may have multiple events that expose read memory bandwidth.
Running a recent kernel that includes
commit 6a8a48644c4b ("perf/x86/intel/uncore: Add per-scheduler IMC CAS count events")
on these systems expose the multiple events. For example,
 /sys/bus/event_source/devices/uncore_imc_N/events/cas_count_read_sch0
 /sys/bus/event_source/devices/uncore_imc_N/events/cas_count_read_sch1

Support parsing of iMC PMU properties when the PMU may have multiple events
to measure read memory bandwidth. The PMU only needs to be discovered once.
Split the parsing of event details from actual PMU discovery in order to
loop over all events associated with the PMU. Match all events with the
cas_count_read prefix instead of requiring there to be one file with that
name.

Make the parsing code more robust. With strings passed around to create
needed paths, use snprintf() instead of sprintf() to ensure there is
always enough space to create the path while using the standard PATH_MAX
for path lengths. Ensure there is enough room in imc_counters_config[]
before attempting to add an entry.

Link: https://lore.kernel.org/r/b03ca0fa21a09500c56ee589e32516c2c5effeaf.1775266384.git.reinette.chatre@intel.com
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Chen Yu <yu.c.chen@intel.com>
Reviewed-by: Zide Chen <zide.chen@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/resctrl_val.c | 118 ++++++++++++++----
 1 file changed, 93 insertions(+), 25 deletions(-)

diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
index 6d766347e3fc9..f20d2194c35fb 100644
--- a/tools/testing/selftests/resctrl/resctrl_val.c
+++ b/tools/testing/selftests/resctrl/resctrl_val.c
@@ -11,10 +11,10 @@
 #include "resctrl.h"
 
 #define UNCORE_IMC		"uncore_imc"
-#define READ_FILE_NAME		"events/cas_count_read"
+#define READ_FILE_NAME		"cas_count_read"
 #define DYN_PMU_PATH		"/sys/bus/event_source/devices"
 #define SCALE			0.00006103515625
-#define MAX_IMCS		20
+#define MAX_IMCS		40
 #define MAX_TOKENS		5
 
 #define CON_MBM_LOCAL_BYTES_PATH		\
@@ -109,46 +109,114 @@ static int open_perf_read_event(int i, int cpu_no)
 	return 0;
 }
 
-/* Get type and config of an iMC counter's read event. */
-static int read_from_imc_dir(char *imc_dir, unsigned int *count)
+static int parse_imc_read_bw_events(char *imc_dir, unsigned int type,
+				    unsigned int *count)
 {
-	char cas_count_cfg[1024], imc_counter_cfg[1024], imc_counter_type[1024];
+	char imc_events_dir[PATH_MAX], imc_counter_cfg[PATH_MAX];
+	unsigned int orig_count = *count;
+	char cas_count_cfg[1024];
+	struct dirent *ep;
+	int path_len;
+	int ret = -1;
+	int num_cfg;
 	FILE *fp;
+	DIR *dp;
 
-	/* Get type of iMC counter */
-	sprintf(imc_counter_type, "%s%s", imc_dir, "type");
-	fp = fopen(imc_counter_type, "r");
-	if (!fp) {
-		ksft_perror("Failed to open iMC counter type file");
+	path_len = snprintf(imc_events_dir, sizeof(imc_events_dir), "%sevents",
+			    imc_dir);
+	if (path_len >= sizeof(imc_events_dir)) {
+		ksft_print_msg("Unable to create path to %sevents\n", imc_dir);
+		return -1;
+	}
 
+	dp = opendir(imc_events_dir);
+	if (!dp) {
+		ksft_perror("Unable to open PMU events directory");
 		return -1;
 	}
-	if (fscanf(fp, "%u", &imc_counters_config[*count].type) <= 0) {
-		ksft_perror("Could not get iMC type");
+
+	while ((ep = readdir(dp))) {
+		/*
+		 * Parse all event files with READ_FILE_NAME prefix that
+		 * contain the event number and umask. Skip files containing
+		 * "." that contain unused properties of event.
+		 */
+		if (!strstr(ep->d_name, READ_FILE_NAME) ||
+		    strchr(ep->d_name, '.'))
+			continue;
+
+		path_len = snprintf(imc_counter_cfg, sizeof(imc_counter_cfg),
+				    "%s/%s", imc_events_dir, ep->d_name);
+		if (path_len >= sizeof(imc_counter_cfg)) {
+			ksft_print_msg("Unable to create path to %s/%s\n",
+				       imc_events_dir, ep->d_name);
+			goto out_close;
+		}
+		fp = fopen(imc_counter_cfg, "r");
+		if (!fp) {
+			ksft_perror("Failed to open iMC config file");
+			goto out_close;
+		}
+		num_cfg = fscanf(fp, "%1023s", cas_count_cfg);
 		fclose(fp);
+		if (num_cfg <= 0) {
+			ksft_perror("Could not get iMC cas count read");
+			goto out_close;
+		}
+		if (*count >= MAX_IMCS) {
+			ksft_print_msg("Maximum iMC count exceeded\n");
+			goto out_close;
+		}
 
-		return -1;
+		imc_counters_config[*count].type = type;
+		get_read_event_and_umask(cas_count_cfg, *count);
+		/* Do not fail after incrementing *count. */
+		*count += 1;
 	}
-	fclose(fp);
+	if (*count == orig_count) {
+		ksft_print_msg("Unable to find events in %s\n", imc_events_dir);
+		goto out_close;
+	}
+	ret = 0;
+out_close:
+	closedir(dp);
+	return ret;
+}
 
-	/* Get read config */
-	sprintf(imc_counter_cfg, "%s%s", imc_dir, READ_FILE_NAME);
-	fp = fopen(imc_counter_cfg, "r");
-	if (!fp) {
-		ksft_perror("Failed to open iMC config file");
+/* Get type and config of an iMC counter's read event. */
+static int read_from_imc_dir(char *imc_dir, unsigned int *count)
+{
+	char imc_counter_type[PATH_MAX];
+	unsigned int type;
+	int path_len;
+	FILE *fp;
+	int ret;
 
+	/* Get type of iMC counter */
+	path_len = snprintf(imc_counter_type, sizeof(imc_counter_type),
+			    "%s%s", imc_dir, "type");
+	if (path_len >= sizeof(imc_counter_type)) {
+		ksft_print_msg("Unable to create path to %s%s\n",
+			       imc_dir, "type");
 		return -1;
 	}
-	if (fscanf(fp, "%1023s", cas_count_cfg) <= 0) {
-		ksft_perror("Could not get iMC cas count read");
-		fclose(fp);
+	fp = fopen(imc_counter_type, "r");
+	if (!fp) {
+		ksft_perror("Failed to open iMC counter type file");
 
 		return -1;
 	}
+	ret = fscanf(fp, "%u", &type);
 	fclose(fp);
-
-	get_read_event_and_umask(cas_count_cfg, *count);
-	*count += 1;
+	if (ret <= 0) {
+		ksft_perror("Could not get iMC type");
+		return -1;
+	}
+	ret = parse_imc_read_bw_events(imc_dir, type, count);
+	if (ret) {
+		ksft_print_msg("Unable to parse bandwidth event and umask\n");
+		return ret;
+	}
 
 	return 0;
 }

From 4ad2314373d86d91eb65e7dbdd30f959ec76b9a0 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 3 Apr 2026 18:56:05 -0700
Subject: [PATCH 230/236] selftests/resctrl: Increase size of buffer used in
 MBM and MBA tests
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 752b6939951f40ac93a6add05cadee488d9cf8e7 upstream.

Errata for Sierra Forest [1] (SRF42) and Granite Rapids [2] (GNR12)
describe the problem that MBM on Intel RDT may overcount memory bandwidth
measurements. The resctrl tests compare memory bandwidth reported by iMC
PMU to that reported by MBM causing the tests to fail on these systems
depending on the settings of the platform related to the errata.

Since the resctrl tests need to run under various conditions it is not
possible to ensure system settings are such that MBM will not overcount.
It has been observed that the overcounting can be controlled via the
buffer size used in the MBM and MBA tests that rely on comparisons
between iMC PMU and MBM measurements.

Running the MBM test on affected platforms with different buffer sizes it
can be observed that the difference between iMC PMU and MBM counts reduce
as the buffer size increases. After increasing the buffer size to more
than 4X the differences between iMC PMU and MBM become insignificant.

Increase the buffer size used in MBM and MBA tests to 4X L3 size to reduce
possibility of tests failing due to difference in counts reported by iMC
PMU and MBM.

Link: https://lore.kernel.org/r/1bd4d8c5fc791234b0a9da94f29a3e278ba2f7ee.1775266384.git.reinette.chatre@intel.com
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Chen Yu <yu.c.chen@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://edc.intel.com/content/www/us/en/design/products-and-solutions/processors-and-chipsets/sierra-forest/xeon-6700-series-processor-with-e-cores-specification-update/errata-details/ # [1]
Link: https://edc.intel.com/content/www/us/en/design/products-and-solutions/processors-and-chipsets/birch-stream/xeon-6900-6700-6500-series-processors-with-p-cores-specification-update/011US/errata-details/ # [2]
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/fill_buf.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/resctrl/fill_buf.c b/tools/testing/selftests/resctrl/fill_buf.c
index 19a01a52dc1a3..b9fa7968cd6e1 100644
--- a/tools/testing/selftests/resctrl/fill_buf.c
+++ b/tools/testing/selftests/resctrl/fill_buf.c
@@ -139,6 +139,6 @@ ssize_t get_fill_buf_size(int cpu_no, const char *cache_type)
 	if (ret)
 		return ret;
 
-	return cache_total_size * 2 > MINIMUM_SPAN ?
-			cache_total_size * 2 : MINIMUM_SPAN;
+	return cache_total_size * 4 > MINIMUM_SPAN ?
+			cache_total_size * 4 : MINIMUM_SPAN;
 }

From 6e240e94ab321b83655d0b93e927d04a1ff62eb5 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 3 Apr 2026 18:56:06 -0700
Subject: [PATCH 231/236] selftests/resctrl: Raise threshold at which MBM and
 PMU values are compared
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit d2ec0e8e2d024b67763670421678f723c817a901 upstream.

Commit 501cfdba0a40 ("selftests/resctrl: Do not compare performance
counters and resctrl at low bandwidth") introduced a threshold under which
memory bandwidth values from MBM and performance counters are not compared.
This is needed because MBM and the PMUs do not have an identical view of
memory bandwidth since PMUs can count all memory traffic while MBM does not
count "overhead" (for example RAS) traffic that cannot be attributed to an
RMID. As a ratio this difference in view of memory bandwidth is pronounced
at low memory bandwidths.

The 750MiB threshold was chosen arbitrarily after comparisons on different
platforms. Exposed to more platforms after introduction this threshold has
proven to be inadequate.

Having accurate comparison between performance counters and MBM requires
careful management of system load as well as control of features that
introduce extra memory traffic, for example, patrol scrub. This is not
appropriate for the resctrl selftests that are intended to run on a
variety of systems with various configurations.

Increase the memory bandwidth threshold under which no comparison is made
between performance counters and MBM. Add additional leniency by increasing
the percentage of difference that will be tolerated between these counts.

There is no impact to the validity of the resctrl selftests results as a
measure of resctrl subsystem health.

Link: https://lore.kernel.org/r/b374c33ddd324130d6255cbb91c3dd500e8277e7.1775266384.git.reinette.chatre@intel.com
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Chen Yu <yu.c.chen@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/mba_test.c | 2 +-
 tools/testing/selftests/resctrl/mbm_test.c | 2 +-
 tools/testing/selftests/resctrl/resctrl.h  | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c
index cd4c715b7ffd2..39cee98983592 100644
--- a/tools/testing/selftests/resctrl/mba_test.c
+++ b/tools/testing/selftests/resctrl/mba_test.c
@@ -12,7 +12,7 @@
 
 #define RESULT_FILE_NAME	"result_mba"
 #define NUM_OF_RUNS		5
-#define MAX_DIFF_PERCENT	8
+#define MAX_DIFF_PERCENT	15
 #define ALLOCATION_MAX		100
 #define ALLOCATION_MIN		10
 #define ALLOCATION_STEP		10
diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c
index 58201f8447404..6dbbc3b760033 100644
--- a/tools/testing/selftests/resctrl/mbm_test.c
+++ b/tools/testing/selftests/resctrl/mbm_test.c
@@ -11,7 +11,7 @@
 #include "resctrl.h"
 
 #define RESULT_FILE_NAME	"result_mbm"
-#define MAX_DIFF_PERCENT	8
+#define MAX_DIFF_PERCENT	15
 #define NUM_OF_RUNS		5
 
 static int
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index bac44eacf94dd..37a8cb9a2a8d1 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -55,7 +55,7 @@
  * and MBM respectively, for instance generating "overhead" traffic which
  * is not counted against any specific RMID.
  */
-#define THROTTLE_THRESHOLD	750
+#define THROTTLE_THRESHOLD	2500
 
 /*
  * fill_buf_param:	"fill_buf" benchmark parameters

From 0418626ff22ce1ec8084e93422c5f0d710436ced Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 3 Apr 2026 18:56:07 -0700
Subject: [PATCH 232/236] selftests/resctrl: Remove requirement on cache miss
 rate
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit ca2e4f4ba15a00218bff3b89ff57b20d0164de0a upstream.

As the CAT test reads the same buffer into different sized cache portions
it compares the number of cache misses against an expected percentage
based on the size of the cache portion.

Systems and test conditions vary. The CAT test is a test of resctrl
subsystem health and not a test of the hardware architecture so it is not
required to place requirements on the size of the difference in cache
misses, just that the number of cache misses when reading a buffer
increase as the cache portion used for the buffer decreases.

Remove additional constraint on how big the difference between cache
misses should be as the cache portion size changes. Only test that the
cache misses increase as the cache portion size decreases. This remains
a good sanity check of resctrl subsystem health while reducing impact
of hardware architectural differences and the various conditions under
which the test may run.

Increase the size difference between cache portions to additionally avoid
any consequences resulting from smaller increments.

Link: https://lore.kernel.org/r/6de4da5486354c0f25fef0d194956470cb744041.1775266384.git.reinette.chatre@intel.com
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Chen Yu <yu.c.chen@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cat_test.c | 33 ++++------------------
 1 file changed, 5 insertions(+), 28 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
index f00b622c14608..8bc47f06679a6 100644
--- a/tools/testing/selftests/resctrl/cat_test.c
+++ b/tools/testing/selftests/resctrl/cat_test.c
@@ -14,42 +14,20 @@
 #define RESULT_FILE_NAME	"result_cat"
 #define NUM_OF_RUNS		5
 
-/*
- * Minimum difference in LLC misses between a test with n+1 bits CBM to the
- * test with n bits is MIN_DIFF_PERCENT_PER_BIT * (n - 1). With e.g. 5 vs 4
- * bits in the CBM mask, the minimum difference must be at least
- * MIN_DIFF_PERCENT_PER_BIT * (4 - 1) = 3 percent.
- *
- * The relationship between number of used CBM bits and difference in LLC
- * misses is not expected to be linear. With a small number of bits, the
- * margin is smaller than with larger number of bits. For selftest purposes,
- * however, linear approach is enough because ultimately only pass/fail
- * decision has to be made and distinction between strong and stronger
- * signal is irrelevant.
- */
-#define MIN_DIFF_PERCENT_PER_BIT	1UL
-
 static int show_results_info(__u64 sum_llc_val, int no_of_bits,
 			     unsigned long cache_span,
-			     unsigned long min_diff_percent,
 			     unsigned long num_of_runs, bool platform,
 			     __s64 *prev_avg_llc_val)
 {
 	__u64 avg_llc_val = 0;
-	float avg_diff;
 	int ret = 0;
 
 	avg_llc_val = sum_llc_val / num_of_runs;
 	if (*prev_avg_llc_val) {
-		float delta = (__s64)(avg_llc_val - *prev_avg_llc_val);
-
-		avg_diff = delta / *prev_avg_llc_val;
-		ret = platform && (avg_diff * 100) < (float)min_diff_percent;
-
-		ksft_print_msg("%s Check cache miss rate changed more than %.1f%%\n",
-			       ret ? "Fail:" : "Pass:", (float)min_diff_percent);
+		ret = platform && (avg_llc_val < *prev_avg_llc_val);
 
-		ksft_print_msg("Percent diff=%.1f\n", avg_diff * 100);
+		ksft_print_msg("%s Check cache miss rate increased\n",
+			       ret ? "Fail:" : "Pass:");
 	}
 	*prev_avg_llc_val = avg_llc_val;
 
@@ -58,10 +36,10 @@ static int show_results_info(__u64 sum_llc_val, int no_of_bits,
 	return ret;
 }
 
-/* Remove the highest bit from CBM */
+/* Remove the highest bits from CBM */
 static unsigned long next_mask(unsigned long current_mask)
 {
-	return current_mask & (current_mask >> 1);
+	return current_mask & (current_mask >> 2);
 }
 
 static int check_results(struct resctrl_val_param *param, const char *cache_type,
@@ -112,7 +90,6 @@ static int check_results(struct resctrl_val_param *param, const char *cache_type
 
 		ret = show_results_info(sum_llc_perf_miss, bits,
 					alloc_size / 64,
-					MIN_DIFF_PERCENT_PER_BIT * (bits - 1),
 					runs, get_vendor() == ARCH_INTEL,
 					&prev_avg_llc_val);
 		if (ret)

From 481f739ed9588640bd7adc3c7ef4fb1fa50d2a99 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 3 Apr 2026 18:56:08 -0700
Subject: [PATCH 233/236] selftests/resctrl: Simplify perf usage in CAT test
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit da707d9fedabf71d1973543f0cf244d2ef597c0d upstream.

The CAT test relies on the PERF_COUNT_HW_CACHE_MISSES event to determine if
modifying a cache portion size is successful. This event is configured to
report the data as part of an event group, but no other events are added to
the group.

Remove the unnecessary PERF_FORMAT_GROUP format setting. This eliminates
the need for struct perf_event_read and results in read() of the associated
file descriptor to return just one value associated with the
PERF_COUNT_HW_CACHE_MISSES event of interest.

Link: https://lore.kernel.org/r/fb69325eba5031b735fa79effaaacd797c9c6040.1775266384.git.reinette.chatre@intel.com
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Chen Yu <yu.c.chen@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cache.c    | 17 +++++------------
 tools/testing/selftests/resctrl/cat_test.c |  4 +---
 tools/testing/selftests/resctrl/resctrl.h  | 11 +----------
 3 files changed, 7 insertions(+), 25 deletions(-)

diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c
index bef71b6feacc6..df9bea584a2d4 100644
--- a/tools/testing/selftests/resctrl/cache.c
+++ b/tools/testing/selftests/resctrl/cache.c
@@ -10,7 +10,6 @@ void perf_event_attr_initialize(struct perf_event_attr *pea, __u64 config)
 	memset(pea, 0, sizeof(*pea));
 	pea->type = PERF_TYPE_HARDWARE;
 	pea->size = sizeof(*pea);
-	pea->read_format = PERF_FORMAT_GROUP;
 	pea->exclude_kernel = 1;
 	pea->exclude_hv = 1;
 	pea->exclude_idle = 1;
@@ -37,19 +36,13 @@ int perf_event_reset_enable(int pe_fd)
 	return 0;
 }
 
-void perf_event_initialize_read_format(struct perf_event_read *pe_read)
-{
-	memset(pe_read, 0, sizeof(*pe_read));
-	pe_read->nr = 1;
-}
-
 int perf_open(struct perf_event_attr *pea, pid_t pid, int cpu_no)
 {
 	int pe_fd;
 
 	pe_fd = perf_event_open(pea, pid, cpu_no, -1, PERF_FLAG_FD_CLOEXEC);
 	if (pe_fd == -1) {
-		ksft_perror("Error opening leader");
+		ksft_perror("Unable to set up performance monitoring");
 		return -1;
 	}
 
@@ -132,9 +125,9 @@ static int print_results_cache(const char *filename, pid_t bm_pid, __u64 llc_val
  *
  * Return: =0 on success. <0 on failure.
  */
-int perf_event_measure(int pe_fd, struct perf_event_read *pe_read,
-		       const char *filename, pid_t bm_pid)
+int perf_event_measure(int pe_fd, const char *filename, pid_t bm_pid)
 {
+	__u64 value;
 	int ret;
 
 	/* Stop counters after one span to get miss rate */
@@ -142,13 +135,13 @@ int perf_event_measure(int pe_fd, struct perf_event_read *pe_read,
 	if (ret < 0)
 		return ret;
 
-	ret = read(pe_fd, pe_read, sizeof(*pe_read));
+	ret = read(pe_fd, &value, sizeof(value));
 	if (ret == -1) {
 		ksft_perror("Could not get perf value");
 		return -1;
 	}
 
-	return print_results_cache(filename, bm_pid, pe_read->values[0].value);
+	return print_results_cache(filename, bm_pid, value);
 }
 
 /*
diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
index 8bc47f06679a6..6aac03147d411 100644
--- a/tools/testing/selftests/resctrl/cat_test.c
+++ b/tools/testing/selftests/resctrl/cat_test.c
@@ -135,7 +135,6 @@ static int cat_test(const struct resctrl_test *test,
 		    struct resctrl_val_param *param,
 		    size_t span, unsigned long current_mask)
 {
-	struct perf_event_read pe_read;
 	struct perf_event_attr pea;
 	cpu_set_t old_affinity;
 	unsigned char *buf;
@@ -159,7 +158,6 @@ static int cat_test(const struct resctrl_test *test,
 		goto reset_affinity;
 
 	perf_event_attr_initialize(&pea, PERF_COUNT_HW_CACHE_MISSES);
-	perf_event_initialize_read_format(&pe_read);
 	pe_fd = perf_open(&pea, bm_pid, uparams->cpu);
 	if (pe_fd < 0) {
 		ret = -1;
@@ -192,7 +190,7 @@ static int cat_test(const struct resctrl_test *test,
 
 			fill_cache_read(buf, span, true);
 
-			ret = perf_event_measure(pe_fd, &pe_read, param->filename, bm_pid);
+			ret = perf_event_measure(pe_fd, param->filename, bm_pid);
 			if (ret)
 				goto free_buf;
 		}
diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h
index 37a8cb9a2a8d1..df624890e3da1 100644
--- a/tools/testing/selftests/resctrl/resctrl.h
+++ b/tools/testing/selftests/resctrl/resctrl.h
@@ -148,13 +148,6 @@ struct resctrl_val_param {
 	struct fill_buf_param	*fill_buf;
 };
 
-struct perf_event_read {
-	__u64 nr;			/* The number of events */
-	struct {
-		__u64 value;		/* The value of the event */
-	} values[2];
-};
-
 /*
  * Memory location that consumes values compiler must not optimize away.
  * Volatile ensures writes to this location cannot be optimized away by
@@ -210,11 +203,9 @@ unsigned int count_bits(unsigned long n);
 int snc_kernel_support(void);
 
 void perf_event_attr_initialize(struct perf_event_attr *pea, __u64 config);
-void perf_event_initialize_read_format(struct perf_event_read *pe_read);
 int perf_open(struct perf_event_attr *pea, pid_t pid, int cpu_no);
 int perf_event_reset_enable(int pe_fd);
-int perf_event_measure(int pe_fd, struct perf_event_read *pe_read,
-		       const char *filename, pid_t bm_pid);
+int perf_event_measure(int pe_fd, const char *filename, pid_t bm_pid);
 int measure_llc_resctrl(const char *filename, pid_t bm_pid);
 int minimize_l2_occupancy(const struct resctrl_test *test,
 			  const struct user_params *uparams,

From 01a280cbe1f7a25e328a052aaaf44055fe7fd6cc Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 3 Apr 2026 18:56:09 -0700
Subject: [PATCH 234/236] selftests/resctrl: Reduce L2 impact on CAT test
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 08d592641ed06c28222e499103257752ace4b167 upstream.

The L3 CAT test loads a buffer into cache that is proportional to the L3
size allocated for the workload and measures cache misses when accessing
the buffer as a test of L3 occupancy. When loading the buffer it can be
assumed that a portion of the buffer will be loaded into the L2 cache and
depending on cache design may not be present in L3. It is thus possible
for data to not be in L3 but also not trigger an L3 cache miss when
accessed.

Reduce impact of L2 on the L3 CAT test by, if L2 allocation is supported,
minimizing the portion of L2 that the workload can allocate into. This
encourages most of buffer to be loaded into L3 and support better
comparison between buffer size, cache portion, and cache misses when
accessing the buffer.

Link: https://lore.kernel.org/r/1f5aad318889cd6d4f9a8d8b0fbe83e3848d41a9.1775266384.git.reinette.chatre@intel.com
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Chen Yu <yu.c.chen@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 tools/testing/selftests/resctrl/cat_test.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
index 6aac03147d411..371a2f26dc47b 100644
--- a/tools/testing/selftests/resctrl/cat_test.c
+++ b/tools/testing/selftests/resctrl/cat_test.c
@@ -157,6 +157,10 @@ static int cat_test(const struct resctrl_test *test,
 	if (ret)
 		goto reset_affinity;
 
+	ret = minimize_l2_occupancy(test, uparams, param);
+	if (ret)
+		goto reset_affinity;
+
 	perf_event_attr_initialize(&pea, PERF_COUNT_HW_CACHE_MISSES);
 	pe_fd = perf_open(&pea, bm_pid, uparams->cpu);
 	if (pe_fd < 0) {

From 1ad2b876f87c918d64a2434ede0bc0fbdcd37a15 Mon Sep 17 00:00:00 2001
From: Jason Zeng <jason.zeng@intel.com>
Date: Tue, 12 May 2026 19:14:17 -0700
Subject: [PATCH 235/236] x86: config: Enable Intel AET

Enable Intel Application Energy Telemetry (AET), this also requires to
enable following configs:

CONFIG_INTEL_VSEC=y
CONFIG_INTEL_TPMI=y
CONFIG_INTEL_PMT_CLASS=y
CONFIG_INTEL_PMT_DISCOVERY=y
CONFIG_INTEL_PMT_TELEMETRY=y

Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 config.x86_64 | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/config.x86_64 b/config.x86_64
index adcdaca218081..e1edcb4700103 100644
--- a/config.x86_64
+++ b/config.x86_64
@@ -326,6 +326,7 @@ CONFIG_X86_X2APIC=y
 CONFIG_X86_MPPARSE=y
 # CONFIG_GOLDFISH is not set
 CONFIG_X86_CPU_RESCTRL=y
+CONFIG_X86_CPU_RESCTRL_INTEL_AET=y
 # CONFIG_X86_EXTENDED_PLATFORM is not set
 CONFIG_X86_INTEL_LPSS=y
 CONFIG_X86_AMD_PLATFORM_DEVICE=y
@@ -8187,10 +8188,10 @@ CONFIG_INTEL_IFS=m
 # CONFIG_INTEL_SAR_INT1092 is not set
 # CONFIG_INTEL_SKL_INT3472 is not set
 # CONFIG_INTEL_PMC_CORE is not set
-CONFIG_INTEL_PMT_CLASS=m
-CONFIG_INTEL_PMT_TELEMETRY=m
+CONFIG_INTEL_PMT_CLASS=y
+CONFIG_INTEL_PMT_TELEMETRY=y
 CONFIG_INTEL_PMT_CRASHLOG=m
-CONFIG_INTEL_PMT_DISCOVERY=m
+CONFIG_INTEL_PMT_DISCOVERY=y
 
 #
 # Intel Speed Select Technology interface support
@@ -8217,10 +8218,10 @@ CONFIG_INTEL_OAKTRAIL=m
 # CONFIG_INTEL_PUNIT_IPC is not set
 CONFIG_INTEL_RST=m
 CONFIG_INTEL_SMARTCONNECT=m
-CONFIG_INTEL_TPMI=m
+CONFIG_INTEL_TPMI=y
 CONFIG_INTEL_PLR_TPMI=m
 # CONFIG_INTEL_TURBO_MAX_3 is not set
-CONFIG_INTEL_VSEC=m
+CONFIG_INTEL_VSEC=y
 # CONFIG_MSI_EC is not set
 CONFIG_MSI_LAPTOP=m
 CONFIG_MSI_WMI=m

From ae9f46c293cd1ec9dae922ec70594d4f005d50ea Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Mon, 6 Jul 2026 15:46:23 -0700
Subject: [PATCH 236/236] fs/resctrl: Fix double-add of pseudo-locked region's
 RMID to free list

commit b9f089723aee892efc77c349ae47a6b452b293c4 upstream.

A pseudo-locked group's RMID is freed when it is created. On unmount
rmdir_all_sub() unconditionally frees all RMID of all groups, resulting
in a double-free of the pseudo-locked group's RMID. The consequence of this
is that the original free results in the pseudo-locked group's RMID being
added to the rmid_free_lru linked list and the second free then attempts
to add the same RMID entry to the rmid_free_lru again.

Do not double-free a pseudo-locked group's RMID.

Fixes: e0bdfe8e36f3 ("x86/intel_rdt: Support creation/removal of pseudo-locked region")
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Cc: <stable@kernel.org>
Link: https://patch.msgid.link/551432dd7e624a862b8e58314c38aaba0afff3e9.1783377598.git.reinette.chatre@intel.com

 Conflicts:
	fs/resctrl/rdtgroup.c
[jz: resolve context conflict]
Signed-off-by: Jason Zeng <jason.zeng@intel.com>
---
 fs/resctrl/rdtgroup.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index c909977765be7..fd6877eb58171 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -2852,10 +2852,6 @@ static void rmdir_all_sub(void)
 		if (rdtgrp == &rdtgroup_default)
 			continue;
 
-		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
-		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
-			rdtgroup_pseudo_lock_remove(rdtgrp);
-
 		/*
 		 * Give any CPUs back to the default group. We cannot copy
 		 * cpu_online_mask because a CPU might have executed the
@@ -2864,7 +2860,13 @@ static void rmdir_all_sub(void)
 		cpumask_or(&rdtgroup_default.cpu_mask,
 			   &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);
 
-		free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
+		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
+			rdtgroup_pseudo_lock_remove(rdtgrp);
+		} else {
+			/* Pseudo-locked group's RMID is freed during setup. */
+			free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
+		}
 
 		kernfs_remove(rdtgrp->kn);
 		list_del(&rdtgrp->rdtgroup_list);