[PW_SID:986134] [v6] riscv: hwprobe: Fix stale vDSO data for late-initialized keys at boot

arch/riscv/include/asm/hwprobe.h

@@ -40,5 +40,11 @@ static inline bool riscv_hwprobe_pair_cmp(struct riscv_hwprobe *pair,
 
 	return pair->value == other_pair->value;
 }
-
+#ifdef CONFIG_MMU
+void riscv_hwprobe_register_async_probe(void);
+void riscv_hwprobe_complete_async_probe(void);
+#else
+static inline void riscv_hwprobe_register_async_probe(void) {}
+static inline void riscv_hwprobe_complete_async_probe(void) {}
+#endif
 #endif

arch/riscv/include/asm/vdso/arch_data.h

@@ -12,6 +12,12 @@ struct vdso_arch_data {
 
 	/* Boolean indicating all CPUs have the same static hwprobe values. */
 	__u8 homogeneous_cpus;
+
+	/*
+	 * A gate to check and see if the hwprobe data is actually ready, as
+	 * probing is deferred to avoid boot slowdowns.
+	 */
+	__u8 ready;
 };
 
 #endif /* __RISCV_ASM_VDSO_ARCH_DATA_H */

arch/riscv/kernel/sys_hwprobe.c

@@ -5,6 +5,8 @@
  * more details.
  */
 #include <linux/syscalls.h>
+#include <linux/completion.h>
+#include <linux/atomic.h>
 #include <asm/cacheflush.h>
 #include <asm/cpufeature.h>
 #include <asm/hwprobe.h>
@@ -452,28 +454,36 @@ static int hwprobe_get_cpus(struct riscv_hwprobe __user *pairs,
 	return 0;
 }
 
-static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs,
-			    size_t pair_count, size_t cpusetsize,
-			    unsigned long __user *cpus_user,
-			    unsigned int flags)
-{
-	if (flags & RISCV_HWPROBE_WHICH_CPUS)
-		return hwprobe_get_cpus(pairs, pair_count, cpusetsize,
-					cpus_user, flags);
+#ifdef CONFIG_MMU
 
-	return hwprobe_get_values(pairs, pair_count, cpusetsize,
-				  cpus_user, flags);
+static DECLARE_COMPLETION(boot_probes_done);
+static atomic_t pending_boot_probes = ATOMIC_INIT(1);
+
+void riscv_hwprobe_register_async_probe(void)
+{
+	atomic_inc(&pending_boot_probes);
 }
 
-#ifdef CONFIG_MMU
+void riscv_hwprobe_complete_async_probe(void)
+{
+	if (atomic_dec_and_test(&pending_boot_probes))
+		complete(&boot_probes_done);
+}
 
-static int __init init_hwprobe_vdso_data(void)
+static int complete_hwprobe_vdso_data(void)
 {
 	struct vdso_arch_data *avd = vdso_k_arch_data;
 	u64 id_bitsmash = 0;
 	struct riscv_hwprobe pair;
 	int key;
 
+	/* We've probably already produced these values. */
+	if (likely(avd->ready))
+		return 0;
+
+	if (unlikely(!atomic_dec_and_test(&pending_boot_probes)))
+		wait_for_completion(&boot_probes_done);
+
 	/*
 	 * Initialize vDSO data with the answers for the "all CPUs" case, to
 	 * save a syscall in the common case.
@@ -501,13 +511,48 @@ static int __init init_hwprobe_vdso_data(void)
 	 * vDSO should defer to the kernel for exotic cpu masks.
 	 */
 	avd->homogeneous_cpus = id_bitsmash != 0 && id_bitsmash != -1;
+
+	/*
+	 * Make sure all the VDSO values are visible before we look at them.
+	 * This pairs with the implicit "no speculativly visible accesses"
+	 * barrier in the VDSO hwprobe code.
+	 */
+	smp_wmb();
+	avd->ready = true;
+	return 0;
+}
+
+static int __init init_hwprobe_vdso_data(void)
+{
+	struct vdso_arch_data *avd = vdso_k_arch_data;
+
+	/*
+	 * Prevent the vDSO cached values from being used, as they're not ready
+	 * yet.
+	 */
+	avd->ready = false;
 	return 0;
 }
 
-arch_initcall_sync(init_hwprobe_vdso_data);
+late_initcall(init_hwprobe_vdso_data);
 
 #endif /* CONFIG_MMU */
 
+static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs,
+				size_t pair_count, size_t cpusetsize,
+				unsigned long __user *cpus_user,
+				unsigned int flags)
+{
+	complete_hwprobe_vdso_data();
+
+	if (flags & RISCV_HWPROBE_WHICH_CPUS)
+		return hwprobe_get_cpus(pairs, pair_count, cpusetsize,
+					cpus_user, flags);
+
+	return hwprobe_get_values(pairs, pair_count, cpusetsize,
+				cpus_user, flags);
+}
+
 SYSCALL_DEFINE5(riscv_hwprobe, struct riscv_hwprobe __user *, pairs,
 		size_t, pair_count, size_t, cpusetsize, unsigned long __user *,
 		cpus, unsigned int, flags)

arch/riscv/kernel/unaligned_access_speed.c

@@ -379,6 +379,7 @@ static void check_vector_unaligned_access(struct work_struct *work __always_unus
 static int __init vec_check_unaligned_access_speed_all_cpus(void *unused __always_unused)
 {
 	schedule_on_each_cpu(check_vector_unaligned_access);
+	riscv_hwprobe_complete_async_probe();
 
 	return 0;
 }
@@ -473,8 +474,12 @@ static int __init check_unaligned_access_all_cpus(void)
 			per_cpu(vector_misaligned_access, cpu) = unaligned_vector_speed_param;
 	} else if (!check_vector_unaligned_access_emulated_all_cpus() &&
 		   IS_ENABLED(CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS)) {
-		kthread_run(vec_check_unaligned_access_speed_all_cpus,
-			    NULL, "vec_check_unaligned_access_speed_all_cpus");
+		riscv_hwprobe_register_async_probe();
+		if (IS_ERR(kthread_run(vec_check_unaligned_access_speed_all_cpus,
+				NULL, "vec_check_unaligned_access_speed_all_cpus"))) {
+			pr_warn("Failed to create vec_unalign_check kthread\n");
+			riscv_hwprobe_complete_async_probe();
+		}
 	}
 
 	/*

arch/riscv/kernel/vdso/hwprobe.c

@@ -27,7 +27,7 @@ static int riscv_vdso_get_values(struct riscv_hwprobe *pairs, size_t pair_count,
 	 * homogeneous, then this function can handle requests for arbitrary
 	 * masks.
 	 */
-	if ((flags != 0) || (!all_cpus && !avd->homogeneous_cpus))
+	if ((flags != 0) || (!all_cpus && !avd->homogeneous_cpus) || unlikely(!avd->ready))
 		return riscv_hwprobe(pairs, pair_count, cpusetsize, cpus, flags);
 
 	/* This is something we can handle, fill out the pairs. */