From 91e0bf81258c07aad27a4833368569ce873cd83e Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Wed, 14 Jun 2017 17:37:13 +0100 Subject: ACPI/IORT: Remove iort_node_match() Commit 316ca8804ea8 ("ACPI/IORT: Remove linker section for IORT entries probing") removed the linker section for IORT entries probing. Since those IORT entries were the only iort_node_match() interface users, the iort_node_match() became obsolete and can then be removed. Remove the ACPI IORT iort_node_match() interface from the kernel. Acked-by: Marc Zyngier Acked-by: Hanjun Guo Signed-off-by: Lorenzo Pieralisi Cc: Hanjun Guo Signed-off-by: Will Deacon --- include/linux/acpi_iort.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index 3ff9acea8616..8379d406ad2e 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -31,7 +31,6 @@ void iort_deregister_domain_token(int trans_id); struct fwnode_handle *iort_find_domain_token(int trans_id); #ifdef CONFIG_ACPI_IORT void acpi_iort_init(void); -bool iort_node_match(u8 type); u32 iort_msi_map_rid(struct device *dev, u32 req_id); struct irq_domain *iort_get_device_domain(struct device *dev, u32 req_id); void acpi_configure_pmsi_domain(struct device *dev); @@ -41,7 +40,6 @@ void iort_set_dma_mask(struct device *dev); const struct iommu_ops *iort_iommu_configure(struct device *dev); #else static inline void acpi_iort_init(void) { } -static inline bool iort_node_match(u8 type) { return false; } static inline u32 iort_msi_map_rid(struct device *dev, u32 req_id) { return req_id; } static inline struct irq_domain *iort_get_device_domain(struct device *dev, -- cgit v1.2.3 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 ++++-- include/acpi/ghes.h | 5 +++- 3 files changed, 65 insertions(+), 6 deletions(-) (limited to 'include') 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) diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h index 720446cb243e..68f088a92398 100644 --- a/include/acpi/ghes.h +++ b/include/acpi/ghes.h @@ -13,7 +13,10 @@ #define GHES_EXITING 0x0002 struct ghes { - struct acpi_hest_generic *generic; + union { + struct acpi_hest_generic *generic; + struct acpi_hest_generic_v2 *generic_v2; + }; struct acpi_hest_generic_status *estatus; u64 buffer_paddr; unsigned long flags; -- 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 +++++------ drivers/firmware/efi/cper.c | 37 ++++++++++++++++++++++--------------- include/acpi/ghes.h | 36 ++++++++++++++++++++++++++++++++++++ 3 files changed, 63 insertions(+), 21 deletions(-) (limited to 'include') 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 && diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c index d42537425438..902475704311 100644 --- a/drivers/firmware/efi/cper.c +++ b/drivers/firmware/efi/cper.c @@ -32,6 +32,7 @@ #include #include #include +#include #define INDENT_SP " " @@ -386,8 +387,9 @@ static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie, pfx, pcie->bridge.secondary_status, pcie->bridge.control); } -static void cper_estatus_print_section( - const char *pfx, const struct acpi_hest_generic_data *gdata, int sec_no) +static void +cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata, + int sec_no) { uuid_le *sec_type = (uuid_le *)gdata->section_type; __u16 severity; @@ -403,14 +405,16 @@ static void cper_estatus_print_section( snprintf(newpfx, sizeof(newpfx), "%s%s", pfx, INDENT_SP); if (!uuid_le_cmp(*sec_type, CPER_SEC_PROC_GENERIC)) { - struct cper_sec_proc_generic *proc_err = (void *)(gdata + 1); + struct cper_sec_proc_generic *proc_err = acpi_hest_get_payload(gdata); + printk("%s""section_type: general processor error\n", newpfx); if (gdata->error_data_length >= sizeof(*proc_err)) cper_print_proc_generic(newpfx, proc_err); else goto err_section_too_small; } else if (!uuid_le_cmp(*sec_type, CPER_SEC_PLATFORM_MEM)) { - struct cper_sec_mem_err *mem_err = (void *)(gdata + 1); + struct cper_sec_mem_err *mem_err = acpi_hest_get_payload(gdata); + printk("%s""section_type: memory error\n", newpfx); if (gdata->error_data_length >= sizeof(struct cper_sec_mem_err_old)) @@ -419,7 +423,8 @@ static void cper_estatus_print_section( else goto err_section_too_small; } else if (!uuid_le_cmp(*sec_type, CPER_SEC_PCIE)) { - struct cper_sec_pcie *pcie = (void *)(gdata + 1); + struct cper_sec_pcie *pcie = acpi_hest_get_payload(gdata); + printk("%s""section_type: PCIe error\n", newpfx); if (gdata->error_data_length >= sizeof(*pcie)) cper_print_pcie(newpfx, pcie, gdata); @@ -438,7 +443,7 @@ void cper_estatus_print(const char *pfx, const struct acpi_hest_generic_status *estatus) { struct acpi_hest_generic_data *gdata; - unsigned int data_len, gedata_len; + unsigned int data_len; int sec_no = 0; char newpfx[64]; __u16 severity; @@ -452,11 +457,11 @@ void cper_estatus_print(const char *pfx, data_len = estatus->data_length; gdata = (struct acpi_hest_generic_data *)(estatus + 1); snprintf(newpfx, sizeof(newpfx), "%s%s", pfx, INDENT_SP); - while (data_len >= sizeof(*gdata)) { - gedata_len = gdata->error_data_length; + + while (data_len >= acpi_hest_get_size(gdata)) { cper_estatus_print_section(newpfx, gdata, sec_no); - data_len -= gedata_len + sizeof(*gdata); - gdata = (void *)(gdata + 1) + gedata_len; + data_len -= acpi_hest_get_record_size(gdata); + gdata = acpi_hest_get_next(gdata); sec_no++; } } @@ -486,12 +491,14 @@ int cper_estatus_check(const struct acpi_hest_generic_status *estatus) return rc; data_len = estatus->data_length; gdata = (struct acpi_hest_generic_data *)(estatus + 1); - while (data_len >= sizeof(*gdata)) { - gedata_len = gdata->error_data_length; - if (gedata_len > data_len - sizeof(*gdata)) + + while (data_len >= acpi_hest_get_size(gdata)) { + gedata_len = acpi_hest_get_error_length(gdata); + if (gedata_len > data_len - acpi_hest_get_size(gdata)) return -EINVAL; - data_len -= gedata_len + sizeof(*gdata); - gdata = (void *)(gdata + 1) + gedata_len; + + data_len -= acpi_hest_get_record_size(gdata); + gdata = acpi_hest_get_next(gdata); } if (data_len) return -EINVAL; diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h index 68f088a92398..8f8fea004df5 100644 --- a/include/acpi/ghes.h +++ b/include/acpi/ghes.h @@ -73,3 +73,39 @@ static inline void ghes_edac_unregister(struct ghes *ghes) { } #endif + +static inline int acpi_hest_get_version(struct acpi_hest_generic_data *gdata) +{ + return gdata->revision >> 8; +} + +static inline void *acpi_hest_get_payload(struct acpi_hest_generic_data *gdata) +{ + if (acpi_hest_get_version(gdata) >= 3) + return (void *)(((struct acpi_hest_generic_data_v300 *)(gdata)) + 1); + + return gdata + 1; +} + +static inline int acpi_hest_get_error_length(struct acpi_hest_generic_data *gdata) +{ + return ((struct acpi_hest_generic_data *)(gdata))->error_data_length; +} + +static inline int acpi_hest_get_size(struct acpi_hest_generic_data *gdata) +{ + if (acpi_hest_get_version(gdata) >= 3) + return sizeof(struct acpi_hest_generic_data_v300); + + return sizeof(struct acpi_hest_generic_data); +} + +static inline int acpi_hest_get_record_size(struct acpi_hest_generic_data *gdata) +{ + return (acpi_hest_get_size(gdata) + acpi_hest_get_error_length(gdata)); +} + +static inline void *acpi_hest_get_next(struct acpi_hest_generic_data *gdata) +{ + return (void *)(gdata) + acpi_hest_get_record_size(gdata); +} -- cgit v1.2.3 From 2f74f09bce4f8d0236f20174a6daae63e10fe733 Mon Sep 17 00:00:00 2001 From: Tyler Baicar Date: Wed, 21 Jun 2017 12:17:07 -0600 Subject: efi: parse ARM processor error Add support for ARM Common Platform Error Record (CPER). UEFI 2.6 specification adds support for ARM specific processor error information to be reported as part of the CPER records. This provides more detail on for processor error logs. Signed-off-by: Tyler Baicar CC: Jonathan (Zhixiong) Zhang Reviewed-by: James Morse Reviewed-by: Ard Biesheuvel Signed-off-by: Will Deacon --- drivers/firmware/efi/cper.c | 129 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/cper.h | 54 +++++++++++++++++++ 2 files changed, 183 insertions(+) (limited to 'include') diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c index 229cf9277524..eac08548d233 100644 --- a/drivers/firmware/efi/cper.c +++ b/drivers/firmware/efi/cper.c @@ -110,12 +110,15 @@ void cper_print_bits(const char *pfx, unsigned int bits, static const char * const proc_type_strs[] = { "IA32/X64", "IA64", + "ARM", }; static const char * const proc_isa_strs[] = { "IA32", "IA64", "X64", + "ARM A32/T32", + "ARM A64", }; static const char * const proc_error_type_strs[] = { @@ -184,6 +187,122 @@ static void cper_print_proc_generic(const char *pfx, printk("%s""IP: 0x%016llx\n", pfx, proc->ip); } +#if defined(CONFIG_ARM64) || defined(CONFIG_ARM) +static const char * const arm_reg_ctx_strs[] = { + "AArch32 general purpose registers", + "AArch32 EL1 context registers", + "AArch32 EL2 context registers", + "AArch32 secure context registers", + "AArch64 general purpose registers", + "AArch64 EL1 context registers", + "AArch64 EL2 context registers", + "AArch64 EL3 context registers", + "Misc. system register structure", +}; + +static void cper_print_proc_arm(const char *pfx, + const struct cper_sec_proc_arm *proc) +{ + int i, len, max_ctx_type; + struct cper_arm_err_info *err_info; + struct cper_arm_ctx_info *ctx_info; + char newpfx[64]; + + printk("%sMIDR: 0x%016llx\n", pfx, proc->midr); + + len = proc->section_length - (sizeof(*proc) + + proc->err_info_num * (sizeof(*err_info))); + if (len < 0) { + printk("%ssection length: %d\n", pfx, proc->section_length); + printk("%ssection length is too small\n", pfx); + printk("%sfirmware-generated error record is incorrect\n", pfx); + printk("%sERR_INFO_NUM is %d\n", pfx, proc->err_info_num); + return; + } + + if (proc->validation_bits & CPER_ARM_VALID_MPIDR) + printk("%sMultiprocessor Affinity Register (MPIDR): 0x%016llx\n", + pfx, proc->mpidr); + + if (proc->validation_bits & CPER_ARM_VALID_AFFINITY_LEVEL) + printk("%serror affinity level: %d\n", pfx, + proc->affinity_level); + + if (proc->validation_bits & CPER_ARM_VALID_RUNNING_STATE) { + printk("%srunning state: 0x%x\n", pfx, proc->running_state); + printk("%sPower State Coordination Interface state: %d\n", + pfx, proc->psci_state); + } + + snprintf(newpfx, sizeof(newpfx), "%s%s", pfx, INDENT_SP); + + err_info = (struct cper_arm_err_info *)(proc + 1); + for (i = 0; i < proc->err_info_num; i++) { + printk("%sError info structure %d:\n", pfx, i); + + printk("%snum errors: %d\n", pfx, err_info->multiple_error + 1); + + if (err_info->validation_bits & CPER_ARM_INFO_VALID_FLAGS) { + if (err_info->flags & CPER_ARM_INFO_FLAGS_FIRST) + printk("%sfirst error captured\n", newpfx); + if (err_info->flags & CPER_ARM_INFO_FLAGS_LAST) + printk("%slast error captured\n", newpfx); + if (err_info->flags & CPER_ARM_INFO_FLAGS_PROPAGATED) + printk("%spropagated error captured\n", + newpfx); + if (err_info->flags & CPER_ARM_INFO_FLAGS_OVERFLOW) + printk("%soverflow occurred, error info is incomplete\n", + newpfx); + } + + printk("%serror_type: %d, %s\n", newpfx, err_info->type, + err_info->type < ARRAY_SIZE(proc_error_type_strs) ? + proc_error_type_strs[err_info->type] : "unknown"); + if (err_info->validation_bits & CPER_ARM_INFO_VALID_ERR_INFO) + printk("%serror_info: 0x%016llx\n", newpfx, + err_info->error_info); + if (err_info->validation_bits & CPER_ARM_INFO_VALID_VIRT_ADDR) + printk("%svirtual fault address: 0x%016llx\n", + newpfx, err_info->virt_fault_addr); + if (err_info->validation_bits & CPER_ARM_INFO_VALID_PHYSICAL_ADDR) + printk("%sphysical fault address: 0x%016llx\n", + newpfx, err_info->physical_fault_addr); + err_info += 1; + } + + ctx_info = (struct cper_arm_ctx_info *)err_info; + max_ctx_type = ARRAY_SIZE(arm_reg_ctx_strs) - 1; + for (i = 0; i < proc->context_info_num; i++) { + int size = sizeof(*ctx_info) + ctx_info->size; + + printk("%sContext info structure %d:\n", pfx, i); + if (len < size) { + printk("%ssection length is too small\n", newpfx); + printk("%sfirmware-generated error record is incorrect\n", pfx); + return; + } + if (ctx_info->type > max_ctx_type) { + printk("%sInvalid context type: %d (max: %d)\n", + newpfx, ctx_info->type, max_ctx_type); + return; + } + printk("%sregister context type: %s\n", newpfx, + arm_reg_ctx_strs[ctx_info->type]); + print_hex_dump(newpfx, "", DUMP_PREFIX_OFFSET, 16, 4, + (ctx_info + 1), ctx_info->size, 0); + len -= size; + ctx_info = (struct cper_arm_ctx_info *)((long)ctx_info + size); + } + + if (len > 0) { + printk("%sVendor specific error info has %u bytes:\n", pfx, + len); + print_hex_dump(newpfx, "", DUMP_PREFIX_OFFSET, 16, 4, ctx_info, + len, true); + } +} +#endif + static const char * const mem_err_type_strs[] = { "unknown", "no error", @@ -456,6 +575,16 @@ cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata cper_print_pcie(newpfx, pcie, gdata); else goto err_section_too_small; +#if defined(CONFIG_ARM64) || defined(CONFIG_ARM) + } else if (!uuid_le_cmp(*sec_type, CPER_SEC_PROC_ARM)) { + struct cper_sec_proc_arm *arm_err = acpi_hest_get_payload(gdata); + + printk("%ssection_type: ARM processor error\n", newpfx); + if (gdata->error_data_length >= sizeof(*arm_err)) + cper_print_proc_arm(newpfx, arm_err); + else + goto err_section_too_small; +#endif } else printk("%s""section type: unknown, %pUl\n", newpfx, sec_type); diff --git a/include/linux/cper.h b/include/linux/cper.h index dcacb1a72e26..4c671fc2081e 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -180,6 +180,10 @@ enum { #define CPER_SEC_PROC_IPF \ UUID_LE(0xE429FAF1, 0x3CB7, 0x11D4, 0x0B, 0xCA, 0x07, 0x00, \ 0x80, 0xC7, 0x3C, 0x88, 0x81) +/* Processor Specific: ARM */ +#define CPER_SEC_PROC_ARM \ + UUID_LE(0xE19E3D16, 0xBC11, 0x11E4, 0x9C, 0xAA, 0xC2, 0x05, \ + 0x1D, 0x5D, 0x46, 0xB0) /* Platform Memory */ #define CPER_SEC_PLATFORM_MEM \ UUID_LE(0xA5BC1114, 0x6F64, 0x4EDE, 0xB8, 0x63, 0x3E, 0x83, \ @@ -255,6 +259,22 @@ enum { #define CPER_PCIE_SLOT_SHIFT 3 +#define CPER_ARM_VALID_MPIDR BIT(0) +#define CPER_ARM_VALID_AFFINITY_LEVEL BIT(1) +#define CPER_ARM_VALID_RUNNING_STATE BIT(2) +#define CPER_ARM_VALID_VENDOR_INFO BIT(3) + +#define CPER_ARM_INFO_VALID_MULTI_ERR BIT(0) +#define CPER_ARM_INFO_VALID_FLAGS BIT(1) +#define CPER_ARM_INFO_VALID_ERR_INFO BIT(2) +#define CPER_ARM_INFO_VALID_VIRT_ADDR BIT(3) +#define CPER_ARM_INFO_VALID_PHYSICAL_ADDR BIT(4) + +#define CPER_ARM_INFO_FLAGS_FIRST BIT(0) +#define CPER_ARM_INFO_FLAGS_LAST BIT(1) +#define CPER_ARM_INFO_FLAGS_PROPAGATED BIT(2) +#define CPER_ARM_INFO_FLAGS_OVERFLOW BIT(3) + /* * All tables and structs must be byte-packed to match CPER * specification, since the tables are provided by the system BIOS @@ -340,6 +360,40 @@ struct cper_ia_proc_ctx { __u64 mm_reg_addr; }; +/* ARM Processor Error Section */ +struct cper_sec_proc_arm { + __u32 validation_bits; + __u16 err_info_num; /* Number of Processor Error Info */ + __u16 context_info_num; /* Number of Processor Context Info Records*/ + __u32 section_length; + __u8 affinity_level; + __u8 reserved[3]; /* must be zero */ + __u64 mpidr; + __u64 midr; + __u32 running_state; /* Bit 0 set - Processor running. PSCI = 0 */ + __u32 psci_state; +}; + +/* ARM Processor Error Information Structure */ +struct cper_arm_err_info { + __u8 version; + __u8 length; + __u16 validation_bits; + __u8 type; + __u16 multiple_error; + __u8 flags; + __u64 error_info; + __u64 virt_fault_addr; + __u64 physical_fault_addr; +}; + +/* ARM Processor Context Information Structure */ +struct cper_arm_ctx_info { + __u16 version; + __u16 type; + __u32 size; +}; + /* Old Memory Error Section UEFI 2.1, 2.2 */ struct cper_sec_mem_err_old { __u64 validation_bits; -- 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 --- arch/arm64/Kconfig | 2 ++ arch/arm64/mm/fault.c | 17 ++++++++++++ drivers/acpi/apei/Kconfig | 15 ++++++++++ drivers/acpi/apei/ghes.c | 70 +++++++++++++++++++++++++++++++++++++++++++---- include/acpi/ghes.h | 7 +++++ 5 files changed, 105 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 3dcd7ec69bca..80559977a83e 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -19,6 +19,7 @@ config ARM64 select ARCH_HAS_STRICT_KERNEL_RWX select ARCH_HAS_STRICT_MODULE_RWX select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST + select ARCH_HAVE_NMI_SAFE_CMPXCHG if ACPI_APEI_SEA select ARCH_USE_CMPXCHG_LOCKREF select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_NUMA_BALANCING @@ -92,6 +93,7 @@ config ARM64 select HAVE_IRQ_TIME_ACCOUNTING select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP if NUMA + select HAVE_NMI if ACPI_APEI_SEA select HAVE_PATA_PLATFORM select HAVE_PERF_EVENTS select HAVE_PERF_REGS diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 246e64f60610..07481af15fd7 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -42,6 +42,8 @@ #include #include +#include + struct fault_info { int (*fn)(unsigned long addr, unsigned int esr, struct pt_regs *regs); @@ -535,6 +537,21 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs) pr_err("Synchronous External Abort: %s (0x%08x) at 0x%016lx\n", inf->name, esr, addr); + /* + * Synchronous aborts may interrupt code which had interrupts masked. + * Before calling out into the wider kernel tell the interested + * subsystems. + */ + if (IS_ENABLED(CONFIG_ACPI_APEI_SEA)) { + if (interrupts_enabled(regs)) + nmi_enter(); + + ghes_notify_sea(); + + if (interrupts_enabled(regs)) + nmi_exit(); + } + info.si_signo = SIGBUS; info.si_errno = 0; info.si_code = 0; 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; diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h index 8f8fea004df5..95305aeb13ff 100644 --- a/include/acpi/ghes.h +++ b/include/acpi/ghes.h @@ -1,3 +1,6 @@ +#ifndef GHES_H +#define GHES_H + #include #include @@ -109,3 +112,7 @@ static inline void *acpi_hest_get_next(struct acpi_hest_generic_data *gdata) { return (void *)(gdata) + acpi_hest_get_record_size(gdata); } + +void ghes_notify_sea(void); + +#endif /* GHES_H */ -- 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 ++++++++++++++++++ drivers/ras/ras.c | 10 +++++++++- include/linux/ras.h | 12 ++++++++++++ include/linux/uuid.h | 4 +++- include/ras/ras_event.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 87 insertions(+), 2 deletions(-) (limited to 'include') 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); + } } } diff --git a/drivers/ras/ras.c b/drivers/ras/ras.c index 94f8038864b4..e87fd9e32ee2 100644 --- a/drivers/ras/ras.c +++ b/drivers/ras/ras.c @@ -7,11 +7,19 @@ #include #include +#include #define CREATE_TRACE_POINTS #define TRACE_INCLUDE_PATH ../../include/ras #include +void log_non_standard_event(const uuid_le *sec_type, const uuid_le *fru_id, + const char *fru_text, const u8 sev, const u8 *err, + const u32 len) +{ + trace_non_standard_event(sec_type, fru_id, fru_text, sev, err, len); +} + static int __init ras_init(void) { int rc = 0; @@ -27,7 +35,7 @@ subsys_initcall(ras_init); EXPORT_TRACEPOINT_SYMBOL_GPL(extlog_mem_event); #endif EXPORT_TRACEPOINT_SYMBOL_GPL(mc_event); - +EXPORT_TRACEPOINT_SYMBOL_GPL(non_standard_event); int __init parse_ras_param(char *str) { diff --git a/include/linux/ras.h b/include/linux/ras.h index ffb147185e8d..62fac3042dce 100644 --- a/include/linux/ras.h +++ b/include/linux/ras.h @@ -2,6 +2,7 @@ #define __RAS_H__ #include +#include #ifdef CONFIG_DEBUG_FS int ras_userspace_consumers(void); @@ -22,4 +23,15 @@ static inline void __init cec_init(void) { } static inline int cec_add_elem(u64 pfn) { return -ENODEV; } #endif +#ifdef CONFIG_RAS +void log_non_standard_event(const guid_t *sec_type, + const guid_t *fru_id, const char *fru_text, + const u8 sev, const u8 *err, const u32 len); +#else +static void log_non_standard_event(const guid_t *sec_type, + const guid_t *fru_id, const char *fru_text, + const u8 sev, const u8 *err, + const u32 len) { return; } +#endif + #endif /* __RAS_H__ */ diff --git a/include/linux/uuid.h b/include/linux/uuid.h index 75f7182d5360..61641faca38b 100644 --- a/include/linux/uuid.h +++ b/include/linux/uuid.h @@ -18,8 +18,10 @@ #include +#define UUID_SIZE 16 + typedef struct { - __u8 b[16]; + __u8 b[UUID_SIZE]; } uuid_t; #define UUID_INIT(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) \ diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h index 1791a12cfa85..4f79ba94fa6b 100644 --- a/include/ras/ras_event.h +++ b/include/ras/ras_event.h @@ -161,6 +161,51 @@ TRACE_EVENT(mc_event, __get_str(driver_detail)) ); +/* + * Non-Standard Section Report + * + * This event is generated when hardware detected a hardware + * error event, which may be of non-standard section as defined + * in UEFI spec appendix "Common Platform Error Record", or may + * be of sections for which TRACE_EVENT is not defined. + * + */ +TRACE_EVENT(non_standard_event, + + TP_PROTO(const uuid_le *sec_type, + const uuid_le *fru_id, + const char *fru_text, + const u8 sev, + const u8 *err, + const u32 len), + + TP_ARGS(sec_type, fru_id, fru_text, sev, err, len), + + TP_STRUCT__entry( + __array(char, sec_type, UUID_SIZE) + __array(char, fru_id, UUID_SIZE) + __string(fru_text, fru_text) + __field(u8, sev) + __field(u32, len) + __dynamic_array(u8, buf, len) + ), + + TP_fast_assign( + memcpy(__entry->sec_type, sec_type, UUID_SIZE); + memcpy(__entry->fru_id, fru_id, UUID_SIZE); + __assign_str(fru_text, fru_text); + __entry->sev = sev; + __entry->len = len; + memcpy(__get_dynamic_array(buf), err, len); + ), + + TP_printk("severity: %d; sec type:%pU; FRU: %pU %s; data len:%d; raw data:%s", + __entry->sev, __entry->sec_type, + __entry->fru_id, __get_str(fru_text), + __entry->len, + __print_hex(__get_dynamic_array(buf), __entry->len)) +); + /* * PCIe AER Trace event * -- 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 +++++- drivers/firmware/efi/cper.c | 1 + drivers/ras/ras.c | 6 ++++++ include/linux/ras.h | 3 +++ include/ras/ras_event.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 60 insertions(+), 1 deletion(-) (limited to 'include') 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, diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c index d5a5855906d6..48a8f69da42a 100644 --- a/drivers/firmware/efi/cper.c +++ b/drivers/firmware/efi/cper.c @@ -35,6 +35,7 @@ #include #include #include +#include #define INDENT_SP " " diff --git a/drivers/ras/ras.c b/drivers/ras/ras.c index e87fd9e32ee2..39701a5c3f49 100644 --- a/drivers/ras/ras.c +++ b/drivers/ras/ras.c @@ -20,6 +20,11 @@ void log_non_standard_event(const uuid_le *sec_type, const uuid_le *fru_id, trace_non_standard_event(sec_type, fru_id, fru_text, sev, err, len); } +void log_arm_hw_error(struct cper_sec_proc_arm *err) +{ + trace_arm_event(err); +} + static int __init ras_init(void) { int rc = 0; @@ -36,6 +41,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(extlog_mem_event); #endif EXPORT_TRACEPOINT_SYMBOL_GPL(mc_event); EXPORT_TRACEPOINT_SYMBOL_GPL(non_standard_event); +EXPORT_TRACEPOINT_SYMBOL_GPL(arm_event); int __init parse_ras_param(char *str) { diff --git a/include/linux/ras.h b/include/linux/ras.h index 62fac3042dce..7d61863ff265 100644 --- a/include/linux/ras.h +++ b/include/linux/ras.h @@ -3,6 +3,7 @@ #include #include +#include #ifdef CONFIG_DEBUG_FS int ras_userspace_consumers(void); @@ -27,11 +28,13 @@ static inline int cec_add_elem(u64 pfn) { return -ENODEV; } void log_non_standard_event(const guid_t *sec_type, const guid_t *fru_id, const char *fru_text, const u8 sev, const u8 *err, const u32 len); +void log_arm_hw_error(struct cper_sec_proc_arm *err); #else static void log_non_standard_event(const guid_t *sec_type, const guid_t *fru_id, const char *fru_text, const u8 sev, const u8 *err, const u32 len) { return; } +static void log_arm_hw_error(struct cper_sec_proc_arm *err) { return; } #endif #endif /* __RAS_H__ */ diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h index 4f79ba94fa6b..429f46fb61e4 100644 --- a/include/ras/ras_event.h +++ b/include/ras/ras_event.h @@ -161,6 +161,51 @@ TRACE_EVENT(mc_event, __get_str(driver_detail)) ); +/* + * ARM Processor Events Report + * + * This event is generated when hardware detects an ARM processor error + * has occurred. UEFI 2.6 spec section N.2.4.4. + */ +TRACE_EVENT(arm_event, + + TP_PROTO(const struct cper_sec_proc_arm *proc), + + TP_ARGS(proc), + + TP_STRUCT__entry( + __field(u64, mpidr) + __field(u64, midr) + __field(u32, running_state) + __field(u32, psci_state) + __field(u8, affinity) + ), + + TP_fast_assign( + if (proc->validation_bits & CPER_ARM_VALID_AFFINITY_LEVEL) + __entry->affinity = proc->affinity_level; + else + __entry->affinity = ~0; + if (proc->validation_bits & CPER_ARM_VALID_MPIDR) + __entry->mpidr = proc->mpidr; + else + __entry->mpidr = 0ULL; + __entry->midr = proc->midr; + if (proc->validation_bits & CPER_ARM_VALID_RUNNING_STATE) { + __entry->running_state = proc->running_state; + __entry->psci_state = proc->psci_state; + } else { + __entry->running_state = ~0; + __entry->psci_state = ~0; + } + ), + + TP_printk("affinity level: %d; MPIDR: %016llx; MIDR: %016llx; " + "running state: %d; PSCI state: %d", + __entry->affinity, __entry->mpidr, __entry->midr, + __entry->running_state, __entry->psci_state) +); + /* * Non-Standard Section Report * -- 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 --- arch/arm/include/asm/kvm_arm.h | 10 ++++++++++ arch/arm/include/asm/system_misc.h | 5 +++++ arch/arm64/include/asm/kvm_arm.h | 10 ++++++++++ arch/arm64/include/asm/system_misc.h | 2 ++ arch/arm64/mm/fault.c | 22 ++++++++++++++++++++-- drivers/acpi/apei/ghes.c | 17 +++++++++++------ include/acpi/ghes.h | 2 +- virt/kvm/arm/mmu.c | 36 +++++++++++++++++++++++++++++++++--- 8 files changed, 92 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h index a3f0b3d50089..ebf020b02bc8 100644 --- a/arch/arm/include/asm/kvm_arm.h +++ b/arch/arm/include/asm/kvm_arm.h @@ -187,6 +187,16 @@ #define FSC_FAULT (0x04) #define FSC_ACCESS (0x08) #define FSC_PERM (0x0c) +#define FSC_SEA (0x10) +#define FSC_SEA_TTW0 (0x14) +#define FSC_SEA_TTW1 (0x15) +#define FSC_SEA_TTW2 (0x16) +#define FSC_SEA_TTW3 (0x17) +#define FSC_SECC (0x18) +#define FSC_SECC_TTW0 (0x1c) +#define FSC_SECC_TTW1 (0x1d) +#define FSC_SECC_TTW2 (0x1e) +#define FSC_SECC_TTW3 (0x1f) /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */ #define HPFAR_MASK (~0xf) diff --git a/arch/arm/include/asm/system_misc.h b/arch/arm/include/asm/system_misc.h index a3d61ad984af..8c4a89f5ce7d 100644 --- a/arch/arm/include/asm/system_misc.h +++ b/arch/arm/include/asm/system_misc.h @@ -22,6 +22,11 @@ extern void (*arm_pm_idle)(void); extern unsigned int user_debug; +static inline int handle_guest_sea(phys_addr_t addr, unsigned int esr) +{ + return -1; +} + #endif /* !__ASSEMBLY__ */ #endif /* __ASM_ARM_SYSTEM_MISC_H */ diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 6e99978e83bd..61d694c2eae5 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -204,6 +204,16 @@ #define FSC_FAULT ESR_ELx_FSC_FAULT #define FSC_ACCESS ESR_ELx_FSC_ACCESS #define FSC_PERM ESR_ELx_FSC_PERM +#define FSC_SEA ESR_ELx_FSC_EXTABT +#define FSC_SEA_TTW0 (0x14) +#define FSC_SEA_TTW1 (0x15) +#define FSC_SEA_TTW2 (0x16) +#define FSC_SEA_TTW3 (0x17) +#define FSC_SECC (0x18) +#define FSC_SECC_TTW0 (0x1c) +#define FSC_SECC_TTW1 (0x1d) +#define FSC_SECC_TTW2 (0x1e) +#define FSC_SECC_TTW3 (0x1f) /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */ #define HPFAR_MASK (~UL(0xf)) diff --git a/arch/arm64/include/asm/system_misc.h b/arch/arm64/include/asm/system_misc.h index bc812435bc76..95aa4423247d 100644 --- a/arch/arm64/include/asm/system_misc.h +++ b/arch/arm64/include/asm/system_misc.h @@ -56,6 +56,8 @@ extern void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd); __show_ratelimited; \ }) +int handle_guest_sea(phys_addr_t addr, unsigned int esr); + #endif /* __ASSEMBLY__ */ #endif /* __ASM_SYSTEM_MISC_H */ diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 07481af15fd7..a8c9f2db20ba 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -532,6 +532,7 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs) { struct siginfo info; const struct fault_info *inf; + int ret = 0; inf = esr_to_fault_info(esr); pr_err("Synchronous External Abort: %s (0x%08x) at 0x%016lx\n", @@ -546,7 +547,7 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs) if (interrupts_enabled(regs)) nmi_enter(); - ghes_notify_sea(); + ret = ghes_notify_sea(); if (interrupts_enabled(regs)) nmi_exit(); @@ -561,7 +562,7 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs) info.si_addr = (void __user *)addr; arm64_notify_die("", regs, &info, esr); - return 0; + return ret; } static const struct fault_info fault_info[] = { @@ -631,6 +632,23 @@ static const struct fault_info fault_info[] = { { do_bad, SIGBUS, 0, "unknown 63" }, }; +/* + * Handle Synchronous External Aborts that occur in a guest kernel. + * + * The return value will be zero if the SEA was successfully handled + * and non-zero if there was an error processing the error or there was + * no error to process. + */ +int handle_guest_sea(phys_addr_t addr, unsigned int esr) +{ + int ret = -ENOENT; + + if (IS_ENABLED(CONFIG_ACPI_APEI_SEA)) + ret = ghes_notify_sea(); + + return ret; +} + /* * Dispatch a data abort to the relevant handler. */ 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) diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h index 95305aeb13ff..9f26e01186ae 100644 --- a/include/acpi/ghes.h +++ b/include/acpi/ghes.h @@ -113,6 +113,6 @@ static inline void *acpi_hest_get_next(struct acpi_hest_generic_data *gdata) return (void *)(gdata) + acpi_hest_get_record_size(gdata); } -void ghes_notify_sea(void); +int ghes_notify_sea(void); #endif /* GHES_H */ diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c index a2d63247d1bb..bde0cdd60997 100644 --- a/virt/kvm/arm/mmu.c +++ b/virt/kvm/arm/mmu.c @@ -29,6 +29,7 @@ #include #include #include +#include #include "trace.h" @@ -1427,6 +1428,25 @@ out: kvm_set_pfn_accessed(pfn); } +static bool is_abort_sea(unsigned long fault_status) +{ + switch (fault_status) { + case FSC_SEA: + case FSC_SEA_TTW0: + case FSC_SEA_TTW1: + case FSC_SEA_TTW2: + case FSC_SEA_TTW3: + case FSC_SECC: + case FSC_SECC_TTW0: + case FSC_SECC_TTW1: + case FSC_SECC_TTW2: + case FSC_SECC_TTW3: + return true; + default: + return false; + } +} + /** * kvm_handle_guest_abort - handles all 2nd stage aborts * @vcpu: the VCPU pointer @@ -1449,19 +1469,29 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) gfn_t gfn; int ret, idx; + fault_status = kvm_vcpu_trap_get_fault_type(vcpu); + + fault_ipa = kvm_vcpu_get_fault_ipa(vcpu); + + /* + * The host kernel will handle the synchronous external abort. There + * is no need to pass the error into the guest. + */ + if (is_abort_sea(fault_status)) { + if (!handle_guest_sea(fault_ipa, kvm_vcpu_get_hsr(vcpu))) + return 1; + } + is_iabt = kvm_vcpu_trap_is_iabt(vcpu); if (unlikely(!is_iabt && kvm_vcpu_dabt_isextabt(vcpu))) { kvm_inject_vabt(vcpu); return 1; } - fault_ipa = kvm_vcpu_get_fault_ipa(vcpu); - trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_hsr(vcpu), kvm_vcpu_get_hfar(vcpu), fault_ipa); /* Check the stage-2 fault is trans. fault or write fault */ - fault_status = kvm_vcpu_trap_get_fault_type(vcpu); if (fault_status != FSC_FAULT && fault_status != FSC_PERM && fault_status != FSC_ACCESS) { kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n", -- cgit v1.2.3 From 0607512d0a8d7fac86667466b884095e04b10a59 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 27 Jun 2017 17:35:41 +0200 Subject: ras: mark stub functions as 'inline' With CONFIG_RAS disabled, we get two harmless warnings about unused functions: include/linux/ras.h:37:13: error: 'log_arm_hw_error' defined but not used [-Werror=unused-function] static void log_arm_hw_error(struct cper_sec_proc_arm *err) { return; } include/linux/ras.h:33:13: error: 'log_non_standard_event' defined but not used [-Werror=unused-function] static void log_non_standard_event(const guid_t *sec_type, Clearly these are meant to be 'inline', like the other stubs in the same header. Fixes: 297b64c74385 ("ras: acpi / apei: generate trace event for unrecognized CPER section") Fixes: e9279e83ad1f ("trace, ras: add ARM processor error trace event") Acked-by: Borislav Petkov Signed-off-by: Arnd Bergmann Signed-off-by: Will Deacon --- include/linux/ras.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/ras.h b/include/linux/ras.h index 7d61863ff265..be5338a35d57 100644 --- a/include/linux/ras.h +++ b/include/linux/ras.h @@ -30,11 +30,13 @@ void log_non_standard_event(const guid_t *sec_type, const u8 sev, const u8 *err, const u32 len); void log_arm_hw_error(struct cper_sec_proc_arm *err); #else -static void log_non_standard_event(const guid_t *sec_type, - const guid_t *fru_id, const char *fru_text, - const u8 sev, const u8 *err, - const u32 len) { return; } -static void log_arm_hw_error(struct cper_sec_proc_arm *err) { return; } +static inline void +log_non_standard_event(const guid_t *sec_type, + const guid_t *fru_id, const char *fru_text, + const u8 sev, const u8 *err, const u32 len) +{ return; } +static inline void +log_arm_hw_error(struct cper_sec_proc_arm *err) { return; } #endif #endif /* __RAS_H__ */ -- cgit v1.2.3