1 files changed, 96 insertions, 32 deletions

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 9952f3a792ba..066dc1f5c235 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -94,6 +94,8 @@
 #define FIX_APEI_GHES_SDEI_CRITICAL	__end_of_fixed_addresses
 #endif
 
+static ATOMIC_NOTIFIER_HEAD(ghes_report_chain);
+
 static inline bool is_hest_type_generic_v2(struct ghes *ghes)
 {
 	return ghes->generic->header.type == ACPI_HEST_TYPE_GENERIC_ERROR_V2;
@@ -108,6 +110,13 @@ bool ghes_disable;
 module_param_named(disable, ghes_disable, bool, 0);
 
 /*
+ * "ghes.edac_force_enable" forcibly enables ghes_edac and skips the platform
+ * check.
+ */
+static bool ghes_edac_force_enable;
+module_param_named(edac_force_enable, ghes_edac_force_enable, bool, 0);
+
+/*
  * All error sources notified with HED (Hardware Error Device) share a
  * single notifier callback, so they need to be linked and checked one
  * by one. This holds true for NMI too.
@@ -119,6 +128,13 @@ static LIST_HEAD(ghes_hed);
 static DEFINE_MUTEX(ghes_list_mutex);
 
 /*
+ * A list of GHES devices which are given to the corresponding EDAC driver
+ * ghes_edac for further use.
+ */
+static LIST_HEAD(ghes_devs);
+static DEFINE_MUTEX(ghes_devs_mutex);
+
+/*
  * Because the memory area used to transfer hardware error information
  * from BIOS to Linux can be determined only in NMI, IRQ or timer
  * handler, but general ioremap can not be used in atomic context, so
@@ -138,7 +154,7 @@ struct ghes_vendor_record_entry {
 static struct gen_pool *ghes_estatus_pool;
 static unsigned long ghes_estatus_pool_size_request;
 
-static struct ghes_estatus_cache *ghes_estatus_caches[GHES_ESTATUS_CACHES_SIZE];
+static struct ghes_estatus_cache __rcu *ghes_estatus_caches[GHES_ESTATUS_CACHES_SIZE];
 static atomic_t ghes_estatus_cache_alloced;
 
 static int ghes_panic_timeout __read_mostly = 30;
@@ -645,7 +661,7 @@ static bool ghes_do_proc(struct ghes *ghes,
 		if (guid_equal(sec_type, &CPER_SEC_PLATFORM_MEM)) {
 			struct cper_sec_mem_err *mem_err = acpi_hest_get_payload(gdata);
 
-			ghes_edac_report_mem_error(sev, mem_err);
+			atomic_notifier_call_chain(&ghes_report_chain, sev, mem_err);
 
 			arch_apei_report_mem_error(sev, mem_err);
 			queued = ghes_handle_memory_failure(gdata, sev);
@@ -773,48 +789,42 @@ static struct ghes_estatus_cache *ghes_estatus_cache_alloc(
 	return cache;
 }
 
-static void ghes_estatus_cache_free(struct ghes_estatus_cache *cache)
+static void ghes_estatus_cache_rcu_free(struct rcu_head *head)
 {
+	struct ghes_estatus_cache *cache;
 	u32 len;
 
+	cache = container_of(head, struct ghes_estatus_cache, rcu);
 	len = cper_estatus_len(GHES_ESTATUS_FROM_CACHE(cache));
 	len = GHES_ESTATUS_CACHE_LEN(len);
 	gen_pool_free(ghes_estatus_pool, (unsigned long)cache, len);
 	atomic_dec(&ghes_estatus_cache_alloced);
 }
 
-static void ghes_estatus_cache_rcu_free(struct rcu_head *head)
+static void
+ghes_estatus_cache_add(struct acpi_hest_generic *generic,
+		       struct acpi_hest_generic_status *estatus)
 {
-	struct ghes_estatus_cache *cache;
-
-	cache = container_of(head, struct ghes_estatus_cache, rcu);
-	ghes_estatus_cache_free(cache);
-}
-
-static void ghes_estatus_cache_add(
-	struct acpi_hest_generic *generic,
-	struct acpi_hest_generic_status *estatus)
-{
-	int i, slot = -1, count;
 	unsigned long long now, duration, period, max_period = 0;
-	struct ghes_estatus_cache *cache, *slot_cache = NULL, *new_cache;
+	struct ghes_estatus_cache *cache, *new_cache;
+	struct ghes_estatus_cache __rcu *victim;
+	int i, slot = -1, count;
 
 	new_cache = ghes_estatus_cache_alloc(generic, estatus);
-	if (new_cache == NULL)
+	if (!new_cache)
 		return;
+
 	rcu_read_lock();
 	now = sched_clock();
 	for (i = 0; i < GHES_ESTATUS_CACHES_SIZE; i++) {
 		cache = rcu_dereference(ghes_estatus_caches[i]);
 		if (cache == NULL) {
 			slot = i;
-			slot_cache = NULL;
 			break;
 		}
 		duration = now - cache->time_in;
 		if (duration >= GHES_ESTATUS_IN_CACHE_MAX_NSEC) {
 			slot = i;
-			slot_cache = cache;
 			break;
 		}
 		count = atomic_read(&cache->count);
@@ -823,18 +833,30 @@ static void ghes_estatus_cache_add(
 		if (period > max_period) {
 			max_period = period;
 			slot = i;
-			slot_cache = cache;
 		}
 	}
-	/* new_cache must be put into array after its contents are written */
-	smp_wmb();
-	if (slot != -1 && cmpxchg(ghes_estatus_caches + slot,
-				  slot_cache, new_cache) == slot_cache) {
-		if (slot_cache)
-			call_rcu(&slot_cache->rcu, ghes_estatus_cache_rcu_free);
-	} else
-		ghes_estatus_cache_free(new_cache);
 	rcu_read_unlock();
+
+	if (slot != -1) {
+		/*
+		 * Use release semantics to ensure that ghes_estatus_cached()
+		 * running on another CPU will see the updated cache fields if
+		 * it can see the new value of the pointer.
+		 */
+		victim = xchg_release(&ghes_estatus_caches[slot],
+				      RCU_INITIALIZER(new_cache));
+
+		/*
+		 * At this point, victim may point to a cached item different
+		 * from the one based on which we selected the slot. Instead of
+		 * going to the loop again to pick another slot, let's just
+		 * drop the other item anyway: this may cause a false cache
+		 * miss later on, but that won't cause any problems.
+		 */
+		if (victim)
+			call_rcu(&unrcu_pointer(victim)->rcu,
+				 ghes_estatus_cache_rcu_free);
+	}
 }
 
 static void __ghes_panic(struct ghes *ghes,
@@ -1376,7 +1398,11 @@ static int ghes_probe(struct platform_device *ghes_dev)
 
 	platform_set_drvdata(ghes_dev, ghes);
 
-	ghes_edac_register(ghes, &ghes_dev->dev);
+	ghes->dev = &ghes_dev->dev;
+
+	mutex_lock(&ghes_devs_mutex);
+	list_add_tail(&ghes->elist, &ghes_devs);
+	mutex_unlock(&ghes_devs_mutex);
 
 	/* Handle any pending errors right away */
 	spin_lock_irqsave(&ghes_notify_lock_irq, flags);
@@ -1440,12 +1466,12 @@ static int ghes_remove(struct platform_device *ghes_dev)
 
 	ghes_fini(ghes);
 
-	ghes_edac_unregister(ghes);
+	mutex_lock(&ghes_devs_mutex);
+	list_del(&ghes->elist);
+	mutex_unlock(&ghes_devs_mutex);
 
 	kfree(ghes);
 
-	platform_set_drvdata(ghes_dev, NULL);
-
 	return 0;
 }
 
@@ -1497,3 +1523,41 @@ void __init acpi_ghes_init(void)
 	else
 		pr_info(GHES_PFX "Failed to enable APEI firmware first mode.\n");
 }
+
+/*
+ * Known x86 systems that prefer GHES error reporting:
+ */
+static struct acpi_platform_list plat_list[] = {
+	{"HPE   ", "Server  ", 0, ACPI_SIG_FADT, all_versions},
+	{ } /* End */
+};
+
+struct list_head *ghes_get_devices(void)
+{
+	int idx = -1;
+
+	if (IS_ENABLED(CONFIG_X86)) {
+		idx = acpi_match_platform_list(plat_list);
+		if (idx < 0) {
+			if (!ghes_edac_force_enable)
+				return NULL;
+
+			pr_warn_once("Force-loading ghes_edac on an unsupported platform. You're on your own!\n");
+		}
+	}
+
+	return &ghes_devs;
+}
+EXPORT_SYMBOL_GPL(ghes_get_devices);
+
+void ghes_register_report_chain(struct notifier_block *nb)
+{
+	atomic_notifier_chain_register(&ghes_report_chain, nb);
+}
+EXPORT_SYMBOL_GPL(ghes_register_report_chain);
+
+void ghes_unregister_report_chain(struct notifier_block *nb)
+{
+	atomic_notifier_chain_unregister(&ghes_report_chain, nb);
+}
+EXPORT_SYMBOL_GPL(ghes_unregister_report_chain);