From 42aa560446622da6c33dce54fc8f4cd81516e906 Mon Sep 17 00:00:00 2001 From: Tyler Baicar Date: Wed, 21 Jun 2017 12:17:04 -0600 Subject: acpi: apei: read ack upon ghes record consumption A RAS (Reliability, Availability, Serviceability) controller may be a separate processor running in parallel with OS execution, and may generate error records for consumption by the OS. If the RAS controller produces multiple error records, then they may be overwritten before the OS has consumed them. The Generic Hardware Error Source (GHES) v2 structure introduces the capability for the OS to acknowledge the consumption of the error record generated by the RAS controller. A RAS controller supporting GHESv2 shall wait for the acknowledgment before writing a new error record, thus eliminating the race condition. Add support for parsing of GHESv2 sub-tables as well. Signed-off-by: Tyler Baicar CC: Jonathan (Zhixiong) Zhang Reviewed-by: James Morse Signed-off-by: Will Deacon --- drivers/acpi/apei/ghes.c | 59 +++++++++++++++++++++++++++++++++++++++++++++--- drivers/acpi/apei/hest.c | 7 ++++-- 2 files changed, 61 insertions(+), 5 deletions(-) (limited to 'drivers/acpi/apei') diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 980515e029fa..866d244c6311 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -46,6 +46,7 @@ #include #include +#include #include #include #include @@ -80,6 +81,11 @@ ((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 @@ -240,6 +246,16 @@ 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 +265,17 @@ 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 +287,16 @@ 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 +306,8 @@ 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) @@ -649,6 +677,21 @@ 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 int ghes_proc(struct ghes *ghes) { int rc; @@ -661,6 +704,16 @@ static int ghes_proc(struct ghes *ghes) 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; 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) -- cgit v1.2.3 From bbcc2e7b642ed241651fee50ac6ed59643cb1736 Mon Sep 17 00:00:00 2001 From: Tyler Baicar Date: Wed, 21 Jun 2017 12:17:05 -0600 Subject: ras: acpi/apei: cper: add support for generic data v3 structure The ACPI 6.1 spec adds a new revision of the generic error data entry structure. Add support to handle the new structure as well as properly verify and iterate through the generic data entries. Signed-off-by: Tyler Baicar CC: Jonathan (Zhixiong) Zhang Signed-off-by: Will Deacon --- drivers/acpi/apei/ghes.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'drivers/acpi/apei') diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 866d244c6311..81e06e3cb08f 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -428,8 +428,7 @@ 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; @@ -466,8 +465,8 @@ static void ghes_do_proc(struct ghes *ghes, sec_type = (guid_t *)gdata->section_type; sec_sev = ghes_severity(gdata->error_severity); 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); @@ -475,8 +474,8 @@ 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 && -- cgit v1.2.3 From 7edda0886bc3d1e5418951558a2555af1bc73b0a Mon Sep 17 00:00:00 2001 From: Tyler Baicar Date: Wed, 21 Jun 2017 12:17:09 -0600 Subject: acpi: apei: handle SEA notification type for ARMv8 ARM APEI extension proposal added SEA (Synchronous External Abort) notification type for ARMv8. Add a new GHES error source handling function for SEA. If an error source's notification type is SEA, then this function can be registered into the SEA exception handler. That way GHES will parse and report SEA exceptions when they occur. An SEA can interrupt code that had interrupts masked and is treated as an NMI. To aid this the page of address space for mapping APEI buffers while in_nmi() is always reserved, and ghes_ioremap_pfn_nmi() is changed to use the helper methods to find the prot_t to map with in the same way as ghes_ioremap_pfn_irq(). Signed-off-by: Tyler Baicar CC: Jonathan (Zhixiong) Zhang Reviewed-by: James Morse Acked-by: Catalin Marinas Signed-off-by: Will Deacon --- drivers/acpi/apei/Kconfig | 15 ++++++++++ drivers/acpi/apei/ghes.c | 70 +++++++++++++++++++++++++++++++++++++++++++---- 2 files changed, 79 insertions(+), 6 deletions(-) (limited to 'drivers/acpi/apei') 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 81e06e3cb08f..42ddc0eff25b 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -116,11 +116,7 @@ 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) @@ -159,10 +155,14 @@ 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; } @@ -774,6 +774,50 @@ static struct notifier_block ghes_notifier_sci = { .notifier_call = ghes_notify_sci, }; +#ifdef CONFIG_ACPI_APEI_SEA +static LIST_HEAD(ghes_sea); + +void ghes_notify_sea(void) +{ + struct ghes *ghes; + + /* + * synchronize_rcu() will wait for nmi_exit(), so no need to + * rcu_read_lock(). + */ + list_for_each_entry_rcu(ghes, &ghes_sea, list) { + ghes_proc(ghes); + } +} + +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 @@ -1019,6 +1063,14 @@ static int ghes_probe(struct platform_device *ghes_dev) case ACPI_HEST_NOTIFY_EXTERNAL: case ACPI_HEST_NOTIFY_SCI: 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", @@ -1083,6 +1135,9 @@ static int ghes_probe(struct platform_device *ghes_dev) list_add_rcu(&ghes->list, &ghes_sci); 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; @@ -1126,6 +1181,9 @@ static int ghes_remove(struct platform_device *ghes_dev) mutex_unlock(&ghes_list_mutex); synchronize_rcu(); break; + case ACPI_HEST_NOTIFY_SEA: + ghes_sea_remove(ghes); + break; case ACPI_HEST_NOTIFY_NMI: ghes_nmi_remove(ghes); break; -- cgit v1.2.3 From 2fb5853e4442334cb66fc2ab33a51c91d4434769 Mon Sep 17 00:00:00 2001 From: "Jonathan (Zhixiong) Zhang" Date: Wed, 21 Jun 2017 12:17:10 -0600 Subject: acpi: apei: panic OS with fatal error status block Even if an error status block's severity is fatal, the kernel does not honor the severity level and panic. With the firmware first model, the platform could inform the OS about a fatal hardware error through the non-NMI GHES notification type. The OS should panic when a hardware error record is received with this severity. Call panic() after CPER data in error status block is printed if severity is fatal, before each error section is handled. Signed-off-by: Jonathan (Zhixiong) Zhang Signed-off-by: Tyler Baicar Reviewed-by: James Morse Signed-off-by: Will Deacon --- drivers/acpi/apei/ghes.c | 36 +++++++++++++++++++++--------------- 1 file changed, 21 insertions(+), 15 deletions(-) (limited to 'drivers/acpi/apei') diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 42ddc0eff25b..7a91ac7d6b75 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -135,6 +135,8 @@ 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, @@ -691,6 +693,16 @@ static int ghes_ack_error(struct acpi_hest_generic_v2 *gv2) 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; @@ -698,6 +710,11 @@ 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); @@ -838,8 +855,6 @@ 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; @@ -925,18 +940,6 @@ 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; @@ -954,8 +957,11 @@ 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; -- cgit v1.2.3 From 297b64c74385fc7ea5dfff66105ab6465f2df49a Mon Sep 17 00:00:00 2001 From: Tyler Baicar Date: Wed, 21 Jun 2017 12:17:12 -0600 Subject: ras: acpi / apei: generate trace event for unrecognized CPER section The UEFI spec includes non-standard section type support in the Common Platform Error Record. This is defined in section N.2.3 of UEFI version 2.5. Currently if the CPER section's type (UUID) does not match any section type that the kernel knows how to parse, a trace event is not generated. Generate a trace event which contains the raw error data for non-standard section type error records. Signed-off-by: Tyler Baicar CC: Jonathan (Zhixiong) Zhang Tested-by: Shiju Jose Signed-off-by: Will Deacon --- drivers/acpi/apei/ghes.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'drivers/acpi/apei') diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 7a91ac7d6b75..ab36ad628c68 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -45,11 +45,14 @@ #include #include #include +#include +#include #include #include #include #include +#include #include "apei-internal.h" @@ -461,11 +464,19 @@ 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 = acpi_hest_get_payload(gdata); @@ -506,6 +517,13 @@ static void ghes_do_proc(struct ghes *ghes, } #endif + 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); + } } } -- cgit v1.2.3 From e9279e83ad1f4b5af541a522a81888f828210b40 Mon Sep 17 00:00:00 2001 From: Tyler Baicar Date: Wed, 21 Jun 2017 12:17:13 -0600 Subject: trace, ras: add ARM processor error trace event Currently there are trace events for the various RAS errors with the exception of ARM processor type errors. Add a new trace event for such errors so that the user will know when they occur. These trace events are consistent with the ARM processor error section type defined in UEFI 2.6 spec section N.2.4.4. Signed-off-by: Tyler Baicar Acked-by: Steven Rostedt Reviewed-by: Xie XiuQi Signed-off-by: Will Deacon --- drivers/acpi/apei/ghes.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'drivers/acpi/apei') diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index ab36ad628c68..5073d035bb6e 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -517,7 +517,11 @@ static void ghes_do_proc(struct ghes *ghes, } #endif - else { + 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, -- cgit v1.2.3 From 621f48e40ee9b0100a802531069166d7d94796e0 Mon Sep 17 00:00:00 2001 From: Tyler Baicar Date: Wed, 21 Jun 2017 12:17:14 -0600 Subject: arm/arm64: KVM: add guest SEA support Currently external aborts are unsupported by the guest abort handling. Add handling for SEAs so that the host kernel reports SEAs which occur in the guest kernel. When an SEA occurs in the guest kernel, the guest exits and is routed to kvm_handle_guest_abort(). Prior to this patch, a print message of an unsupported FSC would be printed and nothing else would happen. With this patch, the code gets routed to the APEI handling of SEAs in the host kernel to report the SEA information. Signed-off-by: Tyler Baicar Acked-by: Catalin Marinas Acked-by: Marc Zyngier Acked-by: Christoffer Dall Signed-off-by: Will Deacon --- drivers/acpi/apei/ghes.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'drivers/acpi/apei') diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 5073d035bb6e..bc717bdf50f1 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -816,17 +816,22 @@ static struct notifier_block ghes_notifier_sci = { #ifdef CONFIG_ACPI_APEI_SEA static LIST_HEAD(ghes_sea); -void ghes_notify_sea(void) +/* + * 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; - /* - * synchronize_rcu() will wait for nmi_exit(), so no need to - * rcu_read_lock(). - */ + rcu_read_lock(); list_for_each_entry_rcu(ghes, &ghes_sea, list) { - ghes_proc(ghes); + if (!ghes_proc(ghes)) + ret = 0; } + rcu_read_unlock(); + return ret; } static void ghes_sea_add(struct ghes *ghes) -- cgit v1.2.3 From 77b246b32b2c4bc21e352dcb8b53a8aba81ee5a4 Mon Sep 17 00:00:00 2001 From: Tyler Baicar Date: Wed, 21 Jun 2017 12:17:15 -0600 Subject: acpi: apei: check for pending errors when probing GHES entries Check for pending errors when probing GHES entries. It is possible that a fatal error is already pending at this point, so we should handle it as soon as the driver is probed. This also avoids a potential issue if there was an interrupt that was already cleared for an error since the GHES driver wasn't present. Signed-off-by: Tyler Baicar Signed-off-by: Will Deacon --- drivers/acpi/apei/ghes.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers/acpi/apei') diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index bc717bdf50f1..bb830444df28 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -1179,6 +1179,9 @@ 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); -- cgit v1.2.3