summaryrefslogtreecommitdiff
path: root/drivers/acpi/apei
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2017-07-05 17:09:27 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2017-07-05 17:09:27 -0700
commit55a7b2125cf4739a8478d2d7223310ae7393408c (patch)
tree8beb7d6a335d744998f559745de8fb9702871a51 /drivers/acpi/apei
parente5f76a2e0e84ca2a215ecbf6feae88780d055c56 (diff)
parent425e1ed73e6574e4fe186ec82fd37213cbd47df0 (diff)
Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux
Pull arm64 updates from Will Deacon: - RAS reporting via GHES/APEI (ACPI) - Indirect ftrace trampolines for modules - Improvements to kernel fault reporting - Page poisoning - Sigframe cleanups and preparation for SVE context - Core dump fixes - Sparse fixes (mainly relating to endianness) - xgene SoC PMU v3 driver - Misc cleanups and non-critical fixes * tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (75 commits) arm64: fix endianness annotation for 'struct jit_ctx' and friends arm64: cpuinfo: constify attribute_group structures. arm64: ptrace: Fix incorrect get_user() use in compat_vfp_set() arm64: ptrace: Remove redundant overrun check from compat_vfp_set() arm64: ptrace: Avoid setting compat FP[SC]R to garbage if get_user fails arm64: fix endianness annotation for __apply_alternatives()/get_alt_insn() arm64: fix endianness annotation in get_kaslr_seed() arm64: add missing conversion to __wsum in ip_fast_csum() arm64: fix endianness annotation in acpi_parking_protocol.c arm64: use readq() instead of readl() to read 64bit entry_point arm64: fix endianness annotation for reloc_insn_movw() & reloc_insn_imm() arm64: fix endianness annotation for aarch64_insn_write() arm64: fix endianness annotation in aarch64_insn_read() arm64: fix endianness annotation in call_undef_hook() arm64: fix endianness annotation for debug-monitors.c ras: mark stub functions as 'inline' arm64: pass endianness info to sparse arm64: ftrace: fix !CONFIG_ARM64_MODULE_PLTS kernels arm64: signal: Allow expansion of the signal frame acpi: apei: check for pending errors when probing GHES entries ...
Diffstat (limited to 'drivers/acpi/apei')
-rw-r--r--drivers/acpi/apei/Kconfig15
-rw-r--r--drivers/acpi/apei/ghes.c206
-rw-r--r--drivers/acpi/apei/hest.c7
3 files changed, 196 insertions, 32 deletions
diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig
index b0140c8fc733..de14d49a5c90 100644
--- a/drivers/acpi/apei/Kconfig
+++ b/drivers/acpi/apei/Kconfig
@@ -39,6 +39,21 @@ config ACPI_APEI_PCIEAER
PCIe AER errors may be reported via APEI firmware first mode.
Turn on this option to enable the corresponding support.
+config ACPI_APEI_SEA
+ bool "APEI Synchronous External Abort logging/recovering support"
+ depends on ARM64 && ACPI_APEI_GHES
+ default y
+ help
+ This option should be enabled if the system supports
+ firmware first handling of SEA (Synchronous External Abort).
+ SEA happens with certain faults of data abort or instruction
+ abort synchronous exceptions on ARMv8 systems. If a system
+ supports firmware first handling of SEA, the platform analyzes
+ and handles hardware error notifications from SEA, and it may then
+ form a HW error record for the OS to parse and handle. This
+ option allows the OS to look for such hardware error record, and
+ take appropriate action.
+
config ACPI_APEI_MEMORY_FAILURE
bool "APEI memory error recovering support"
depends on ACPI_APEI && MEMORY_FAILURE
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 0968816f5755..d661d452b238 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -45,10 +45,14 @@
#include <linux/aer.h>
#include <linux/nmi.h>
#include <linux/sched/clock.h>
+#include <linux/uuid.h>
+#include <linux/ras.h>
+#include <acpi/actbl1.h>
#include <acpi/ghes.h>
#include <acpi/apei.h>
#include <asm/tlbflush.h>
+#include <ras/ras_event.h>
#include "apei-internal.h"
@@ -80,6 +84,11 @@
((struct acpi_hest_generic_status *) \
((struct ghes_estatus_node *)(estatus_node) + 1))
+static inline bool is_hest_type_generic_v2(struct ghes *ghes)
+{
+ return ghes->generic->header.type == ACPI_HEST_TYPE_GENERIC_ERROR_V2;
+}
+
/*
* This driver isn't really modular, however for the time being,
* continuing to use module_param is the easiest way to remain
@@ -110,11 +119,7 @@ static DEFINE_MUTEX(ghes_list_mutex);
* Two virtual pages are used, one for IRQ/PROCESS context, the other for
* NMI context (optionally).
*/
-#ifdef CONFIG_HAVE_ACPI_APEI_NMI
#define GHES_IOREMAP_PAGES 2
-#else
-#define GHES_IOREMAP_PAGES 1
-#endif
#define GHES_IOREMAP_IRQ_PAGE(base) (base)
#define GHES_IOREMAP_NMI_PAGE(base) ((base) + PAGE_SIZE)
@@ -133,6 +138,8 @@ static unsigned long ghes_estatus_pool_size_request;
static struct ghes_estatus_cache *ghes_estatus_caches[GHES_ESTATUS_CACHES_SIZE];
static atomic_t ghes_estatus_cache_alloced;
+static int ghes_panic_timeout __read_mostly = 30;
+
static int ghes_ioremap_init(void)
{
ghes_ioremap_area = __get_vm_area(PAGE_SIZE * GHES_IOREMAP_PAGES,
@@ -153,10 +160,14 @@ static void ghes_ioremap_exit(void)
static void __iomem *ghes_ioremap_pfn_nmi(u64 pfn)
{
unsigned long vaddr;
+ phys_addr_t paddr;
+ pgprot_t prot;
vaddr = (unsigned long)GHES_IOREMAP_NMI_PAGE(ghes_ioremap_area->addr);
- ioremap_page_range(vaddr, vaddr + PAGE_SIZE,
- pfn << PAGE_SHIFT, PAGE_KERNEL);
+
+ paddr = pfn << PAGE_SHIFT;
+ prot = arch_apei_get_mem_attribute(paddr);
+ ioremap_page_range(vaddr, vaddr + PAGE_SIZE, paddr, prot);
return (void __iomem *)vaddr;
}
@@ -240,6 +251,16 @@ static int ghes_estatus_pool_expand(unsigned long len)
return 0;
}
+static int map_gen_v2(struct ghes *ghes)
+{
+ return apei_map_generic_address(&ghes->generic_v2->read_ack_register);
+}
+
+static void unmap_gen_v2(struct ghes *ghes)
+{
+ apei_unmap_generic_address(&ghes->generic_v2->read_ack_register);
+}
+
static struct ghes *ghes_new(struct acpi_hest_generic *generic)
{
struct ghes *ghes;
@@ -249,10 +270,17 @@ static struct ghes *ghes_new(struct acpi_hest_generic *generic)
ghes = kzalloc(sizeof(*ghes), GFP_KERNEL);
if (!ghes)
return ERR_PTR(-ENOMEM);
+
ghes->generic = generic;
+ if (is_hest_type_generic_v2(ghes)) {
+ rc = map_gen_v2(ghes);
+ if (rc)
+ goto err_free;
+ }
+
rc = apei_map_generic_address(&generic->error_status_address);
if (rc)
- goto err_free;
+ goto err_unmap_read_ack_addr;
error_block_length = generic->error_block_length;
if (error_block_length > GHES_ESTATUS_MAX_SIZE) {
pr_warning(FW_WARN GHES_PFX
@@ -264,13 +292,16 @@ static struct ghes *ghes_new(struct acpi_hest_generic *generic)
ghes->estatus = kmalloc(error_block_length, GFP_KERNEL);
if (!ghes->estatus) {
rc = -ENOMEM;
- goto err_unmap;
+ goto err_unmap_status_addr;
}
return ghes;
-err_unmap:
+err_unmap_status_addr:
apei_unmap_generic_address(&generic->error_status_address);
+err_unmap_read_ack_addr:
+ if (is_hest_type_generic_v2(ghes))
+ unmap_gen_v2(ghes);
err_free:
kfree(ghes);
return ERR_PTR(rc);
@@ -280,6 +311,8 @@ static void ghes_fini(struct ghes *ghes)
{
kfree(ghes->estatus);
apei_unmap_generic_address(&ghes->generic->error_status_address);
+ if (is_hest_type_generic_v2(ghes))
+ unmap_gen_v2(ghes);
}
static inline int ghes_severity(int severity)
@@ -400,8 +433,7 @@ static void ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, int
unsigned long pfn;
int flags = -1;
int sec_sev = ghes_severity(gdata->error_severity);
- struct cper_sec_mem_err *mem_err;
- mem_err = (struct cper_sec_mem_err *)(gdata + 1);
+ struct cper_sec_mem_err *mem_err = acpi_hest_get_payload(gdata);
if (!(mem_err->validation_bits & CPER_MEM_VALID_PA))
return;
@@ -432,14 +464,22 @@ static void ghes_do_proc(struct ghes *ghes,
int sev, sec_sev;
struct acpi_hest_generic_data *gdata;
guid_t *sec_type;
+ guid_t *fru_id = &NULL_UUID_LE;
+ char *fru_text = "";
sev = ghes_severity(estatus->error_severity);
apei_estatus_for_each_section(estatus, gdata) {
sec_type = (guid_t *)gdata->section_type;
sec_sev = ghes_severity(gdata->error_severity);
+ if (gdata->validation_bits & CPER_SEC_VALID_FRU_ID)
+ fru_id = (guid_t *)gdata->fru_id;
+
+ if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT)
+ fru_text = gdata->fru_text;
+
if (guid_equal(sec_type, &CPER_SEC_PLATFORM_MEM)) {
- struct cper_sec_mem_err *mem_err;
- mem_err = (struct cper_sec_mem_err *)(gdata+1);
+ struct cper_sec_mem_err *mem_err = acpi_hest_get_payload(gdata);
+
ghes_edac_report_mem_error(ghes, sev, mem_err);
arch_apei_report_mem_error(sev, mem_err);
@@ -447,8 +487,8 @@ static void ghes_do_proc(struct ghes *ghes,
}
#ifdef CONFIG_ACPI_APEI_PCIEAER
else if (guid_equal(sec_type, &CPER_SEC_PCIE)) {
- struct cper_sec_pcie *pcie_err;
- pcie_err = (struct cper_sec_pcie *)(gdata+1);
+ struct cper_sec_pcie *pcie_err = acpi_hest_get_payload(gdata);
+
if (sev == GHES_SEV_RECOVERABLE &&
sec_sev == GHES_SEV_RECOVERABLE &&
pcie_err->validation_bits & CPER_PCIE_VALID_DEVICE_ID &&
@@ -477,6 +517,17 @@ static void ghes_do_proc(struct ghes *ghes,
}
#endif
+ else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
+ struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
+
+ log_arm_hw_error(err);
+ } else {
+ void *err = acpi_hest_get_payload(gdata);
+
+ log_non_standard_event(sec_type, fru_id, fru_text,
+ sec_sev, err,
+ gdata->error_data_length);
+ }
}
}
@@ -649,6 +700,31 @@ static void ghes_estatus_cache_add(
rcu_read_unlock();
}
+static int ghes_ack_error(struct acpi_hest_generic_v2 *gv2)
+{
+ int rc;
+ u64 val = 0;
+
+ rc = apei_read(&val, &gv2->read_ack_register);
+ if (rc)
+ return rc;
+
+ val &= gv2->read_ack_preserve << gv2->read_ack_register.bit_offset;
+ val |= gv2->read_ack_write << gv2->read_ack_register.bit_offset;
+
+ return apei_write(val, &gv2->read_ack_register);
+}
+
+static void __ghes_panic(struct ghes *ghes)
+{
+ __ghes_print_estatus(KERN_EMERG, ghes->generic, ghes->estatus);
+
+ /* reboot to log the error! */
+ if (!panic_timeout)
+ panic_timeout = ghes_panic_timeout;
+ panic("Fatal hardware error!");
+}
+
static int ghes_proc(struct ghes *ghes)
{
int rc;
@@ -656,11 +732,26 @@ static int ghes_proc(struct ghes *ghes)
rc = ghes_read_estatus(ghes, 0);
if (rc)
goto out;
+
+ if (ghes_severity(ghes->estatus->error_severity) >= GHES_SEV_PANIC) {
+ __ghes_panic(ghes);
+ }
+
if (!ghes_estatus_cached(ghes->estatus)) {
if (ghes_print_estatus(NULL, ghes->generic, ghes->estatus))
ghes_estatus_cache_add(ghes->generic, ghes->estatus);
}
ghes_do_proc(ghes, ghes->estatus);
+
+ /*
+ * GHESv2 type HEST entries introduce support for error acknowledgment,
+ * so only acknowledge the error if this support is present.
+ */
+ if (is_hest_type_generic_v2(ghes)) {
+ rc = ghes_ack_error(ghes->generic_v2);
+ if (rc)
+ return rc;
+ }
out:
ghes_clear_estatus(ghes);
return rc;
@@ -722,6 +813,55 @@ static struct notifier_block ghes_notifier_hed = {
.notifier_call = ghes_notify_hed,
};
+#ifdef CONFIG_ACPI_APEI_SEA
+static LIST_HEAD(ghes_sea);
+
+/*
+ * Return 0 only if one of the SEA error sources successfully reported an error
+ * record sent from the firmware.
+ */
+int ghes_notify_sea(void)
+{
+ struct ghes *ghes;
+ int ret = -ENOENT;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(ghes, &ghes_sea, list) {
+ if (!ghes_proc(ghes))
+ ret = 0;
+ }
+ rcu_read_unlock();
+ return ret;
+}
+
+static void ghes_sea_add(struct ghes *ghes)
+{
+ mutex_lock(&ghes_list_mutex);
+ list_add_rcu(&ghes->list, &ghes_sea);
+ mutex_unlock(&ghes_list_mutex);
+}
+
+static void ghes_sea_remove(struct ghes *ghes)
+{
+ mutex_lock(&ghes_list_mutex);
+ list_del_rcu(&ghes->list);
+ mutex_unlock(&ghes_list_mutex);
+ synchronize_rcu();
+}
+#else /* CONFIG_ACPI_APEI_SEA */
+static inline void ghes_sea_add(struct ghes *ghes)
+{
+ pr_err(GHES_PFX "ID: %d, trying to add SEA notification which is not supported\n",
+ ghes->generic->header.source_id);
+}
+
+static inline void ghes_sea_remove(struct ghes *ghes)
+{
+ pr_err(GHES_PFX "ID: %d, trying to remove SEA notification which is not supported\n",
+ ghes->generic->header.source_id);
+}
+#endif /* CONFIG_ACPI_APEI_SEA */
+
#ifdef CONFIG_HAVE_ACPI_APEI_NMI
/*
* printk is not safe in NMI context. So in NMI handler, we allocate
@@ -742,8 +882,6 @@ static atomic_t ghes_in_nmi = ATOMIC_INIT(0);
static LIST_HEAD(ghes_nmi);
-static int ghes_panic_timeout __read_mostly = 30;
-
static void ghes_proc_in_irq(struct irq_work *irq_work)
{
struct llist_node *llnode, *next;
@@ -829,18 +967,6 @@ static void __process_error(struct ghes *ghes)
#endif
}
-static void __ghes_panic(struct ghes *ghes)
-{
- oops_begin();
- ghes_print_queued_estatus();
- __ghes_print_estatus(KERN_EMERG, ghes->generic, ghes->estatus);
-
- /* reboot to log the error! */
- if (panic_timeout == 0)
- panic_timeout = ghes_panic_timeout;
- panic("Fatal hardware error!");
-}
-
static int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs)
{
struct ghes *ghes;
@@ -858,8 +984,11 @@ static int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs)
}
sev = ghes_severity(ghes->estatus->error_severity);
- if (sev >= GHES_SEV_PANIC)
+ if (sev >= GHES_SEV_PANIC) {
+ oops_begin();
+ ghes_print_queued_estatus();
__ghes_panic(ghes);
+ }
if (!(ghes->flags & GHES_TO_CLEAR))
continue;
@@ -970,6 +1099,14 @@ static int ghes_probe(struct platform_device *ghes_dev)
case ACPI_HEST_NOTIFY_GPIO:
break;
+ case ACPI_HEST_NOTIFY_SEA:
+ if (!IS_ENABLED(CONFIG_ACPI_APEI_SEA)) {
+ pr_warn(GHES_PFX "Generic hardware error source: %d notified via SEA is not supported\n",
+ generic->header.source_id);
+ rc = -ENOTSUPP;
+ goto err;
+ }
+ break;
case ACPI_HEST_NOTIFY_NMI:
if (!IS_ENABLED(CONFIG_HAVE_ACPI_APEI_NMI)) {
pr_warn(GHES_PFX "Generic hardware error source: %d notified via NMI interrupt is not supported!\n",
@@ -1038,6 +1175,9 @@ static int ghes_probe(struct platform_device *ghes_dev)
mutex_unlock(&ghes_list_mutex);
break;
+ case ACPI_HEST_NOTIFY_SEA:
+ ghes_sea_add(ghes);
+ break;
case ACPI_HEST_NOTIFY_NMI:
ghes_nmi_add(ghes);
break;
@@ -1046,6 +1186,9 @@ static int ghes_probe(struct platform_device *ghes_dev)
}
platform_set_drvdata(ghes_dev, ghes);
+ /* Handle any pending errors right away */
+ ghes_proc(ghes);
+
return 0;
err_edac_unreg:
ghes_edac_unregister(ghes);
@@ -1085,6 +1228,9 @@ static int ghes_remove(struct platform_device *ghes_dev)
synchronize_rcu();
break;
+ case ACPI_HEST_NOTIFY_SEA:
+ ghes_sea_remove(ghes);
+ break;
case ACPI_HEST_NOTIFY_NMI:
ghes_nmi_remove(ghes);
break;
diff --git a/drivers/acpi/apei/hest.c b/drivers/acpi/apei/hest.c
index 8f2a98e23bba..456b488eb1df 100644
--- a/drivers/acpi/apei/hest.c
+++ b/drivers/acpi/apei/hest.c
@@ -52,6 +52,7 @@ static const int hest_esrc_len_tab[ACPI_HEST_TYPE_RESERVED] = {
[ACPI_HEST_TYPE_AER_ENDPOINT] = sizeof(struct acpi_hest_aer),
[ACPI_HEST_TYPE_AER_BRIDGE] = sizeof(struct acpi_hest_aer_bridge),
[ACPI_HEST_TYPE_GENERIC_ERROR] = sizeof(struct acpi_hest_generic),
+ [ACPI_HEST_TYPE_GENERIC_ERROR_V2] = sizeof(struct acpi_hest_generic_v2),
};
static int hest_esrc_len(struct acpi_hest_header *hest_hdr)
@@ -141,7 +142,8 @@ static int __init hest_parse_ghes_count(struct acpi_hest_header *hest_hdr, void
{
int *count = data;
- if (hest_hdr->type == ACPI_HEST_TYPE_GENERIC_ERROR)
+ if (hest_hdr->type == ACPI_HEST_TYPE_GENERIC_ERROR ||
+ hest_hdr->type == ACPI_HEST_TYPE_GENERIC_ERROR_V2)
(*count)++;
return 0;
}
@@ -152,7 +154,8 @@ static int __init hest_parse_ghes(struct acpi_hest_header *hest_hdr, void *data)
struct ghes_arr *ghes_arr = data;
int rc, i;
- if (hest_hdr->type != ACPI_HEST_TYPE_GENERIC_ERROR)
+ if (hest_hdr->type != ACPI_HEST_TYPE_GENERIC_ERROR &&
+ hest_hdr->type != ACPI_HEST_TYPE_GENERIC_ERROR_V2)
return 0;
if (!((struct acpi_hest_generic *)hest_hdr)->enabled)