aboutsummaryrefslogtreecommitdiff
path: root/drivers/acpi/apei
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/acpi/apei')
-rw-r--r--drivers/acpi/apei/apei-base.c2
-rw-r--r--drivers/acpi/apei/einj.c56
-rw-r--r--drivers/acpi/apei/ghes.c130
3 files changed, 123 insertions, 65 deletions
diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c
index 9b52482b4ed5..c7c26872f4ce 100644
--- a/drivers/acpi/apei/apei-base.c
+++ b/drivers/acpi/apei/apei-base.c
@@ -25,9 +25,9 @@
#include <linux/slab.h>
#include <linux/io.h>
#include <linux/kref.h>
-#include <linux/rculist.h>
#include <linux/interrupt.h>
#include <linux/debugfs.h>
+#include <acpi/apei.h>
#include <asm/unaligned.h>
#include "apei-internal.h"
diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c
index 6b583373c58a..ab86b2f4e719 100644
--- a/drivers/acpi/apei/einj.c
+++ b/drivers/acpi/apei/einj.c
@@ -358,6 +358,7 @@ static int __einj_error_trigger(u64 trigger_paddr, u32 type,
*/
if ((param_extension || acpi5) && (type & MEM_ERROR_MASK) && param2) {
struct apei_resources addr_resources;
+
apei_resources_init(&addr_resources);
trigger_param_region = einj_get_trigger_parameter_region(
trigger_tab, param1, param2);
@@ -432,11 +433,11 @@ static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
}
v5param->flags = vendor_flags;
} else if (flags) {
- v5param->flags = flags;
- v5param->memory_address = param1;
- v5param->memory_address_range = param2;
- v5param->apicid = param3;
- v5param->pcie_sbdf = param4;
+ v5param->flags = flags;
+ v5param->memory_address = param1;
+ v5param->memory_address_range = param2;
+ v5param->apicid = param3;
+ v5param->pcie_sbdf = param4;
} else {
switch (type) {
case ACPI_EINJ_PROCESSOR_CORRECTABLE:
@@ -466,6 +467,7 @@ static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
return rc;
if (einj_param) {
struct einj_parameter *v4param = einj_param;
+
v4param->param1 = param1;
v4param->param2 = param2;
}
@@ -569,6 +571,20 @@ static u64 error_param2;
static u64 error_param3;
static u64 error_param4;
static struct dentry *einj_debug_dir;
+static const char * const einj_error_type_string[] = {
+ "0x00000001\tProcessor Correctable\n",
+ "0x00000002\tProcessor Uncorrectable non-fatal\n",
+ "0x00000004\tProcessor Uncorrectable fatal\n",
+ "0x00000008\tMemory Correctable\n",
+ "0x00000010\tMemory Uncorrectable non-fatal\n",
+ "0x00000020\tMemory Uncorrectable fatal\n",
+ "0x00000040\tPCI Express Correctable\n",
+ "0x00000080\tPCI Express Uncorrectable non-fatal\n",
+ "0x00000100\tPCI Express Uncorrectable fatal\n",
+ "0x00000200\tPlatform Correctable\n",
+ "0x00000400\tPlatform Uncorrectable non-fatal\n",
+ "0x00000800\tPlatform Uncorrectable fatal\n",
+};
static int available_error_type_show(struct seq_file *m, void *v)
{
@@ -578,30 +594,9 @@ static int available_error_type_show(struct seq_file *m, void *v)
rc = einj_get_available_error_type(&available_error_type);
if (rc)
return rc;
- if (available_error_type & 0x0001)
- seq_printf(m, "0x00000001\tProcessor Correctable\n");
- if (available_error_type & 0x0002)
- seq_printf(m, "0x00000002\tProcessor Uncorrectable non-fatal\n");
- if (available_error_type & 0x0004)
- seq_printf(m, "0x00000004\tProcessor Uncorrectable fatal\n");
- if (available_error_type & 0x0008)
- seq_printf(m, "0x00000008\tMemory Correctable\n");
- if (available_error_type & 0x0010)
- seq_printf(m, "0x00000010\tMemory Uncorrectable non-fatal\n");
- if (available_error_type & 0x0020)
- seq_printf(m, "0x00000020\tMemory Uncorrectable fatal\n");
- if (available_error_type & 0x0040)
- seq_printf(m, "0x00000040\tPCI Express Correctable\n");
- if (available_error_type & 0x0080)
- seq_printf(m, "0x00000080\tPCI Express Uncorrectable non-fatal\n");
- if (available_error_type & 0x0100)
- seq_printf(m, "0x00000100\tPCI Express Uncorrectable fatal\n");
- if (available_error_type & 0x0200)
- seq_printf(m, "0x00000200\tPlatform Correctable\n");
- if (available_error_type & 0x0400)
- seq_printf(m, "0x00000400\tPlatform Uncorrectable non-fatal\n");
- if (available_error_type & 0x0800)
- seq_printf(m, "0x00000800\tPlatform Uncorrectable fatal\n");
+ for (int pos = 0; pos < ARRAY_SIZE(einj_error_type_string); pos++)
+ if (available_error_type & BIT(pos))
+ seq_puts(m, einj_error_type_string[pos]);
return 0;
}
@@ -689,8 +684,7 @@ static int __init einj_init(void)
if (status == AE_NOT_FOUND) {
pr_warn("EINJ table not found.\n");
return -ENODEV;
- }
- else if (ACPI_FAILURE(status)) {
+ } else if (ACPI_FAILURE(status)) {
pr_err("Failed to get EINJ table: %s\n",
acpi_format_exception(status));
return -EINVAL;
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 80ad530583c9..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;
@@ -163,7 +179,7 @@ static void ghes_unmap(void __iomem *vaddr, enum fixed_addresses fixmap_idx)
clear_fixmap(fixmap_idx);
}
-int ghes_estatus_pool_init(int num_ghes)
+int ghes_estatus_pool_init(unsigned int num_ghes)
{
unsigned long addr, len;
int rc;
@@ -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);
Powered by cgit, Gruvboxed by Blaster4385.