From 04c25997c97e57d95d1f5a7a6e5fff2411dbd48b Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Thu, 8 Dec 2011 11:25:40 +0800 Subject: [PATCH 01/11] ACPI, Add 64bit read/write support to atomicio on i386 There is no 64bit read/write support in ACPI atomicio because readq/writeq is used to implement 64bit read/write, but readq/writeq is not available on i386. This patch implement 64bit read/write support in atomicio via two readl/writel. Signed-off-by: Huang Ying Signed-off-by: Len Brown --- drivers/acpi/atomicio.c | 36 ++++++++++++++++++++++++++++++------ 1 file changed, 30 insertions(+), 6 deletions(-) diff --git a/drivers/acpi/atomicio.c b/drivers/acpi/atomicio.c index cfc0cc10af39..1016f186c17c 100644 --- a/drivers/acpi/atomicio.c +++ b/drivers/acpi/atomicio.c @@ -260,6 +260,21 @@ int acpi_post_unmap_gar(struct acpi_generic_address *reg) } EXPORT_SYMBOL_GPL(acpi_post_unmap_gar); +#ifdef readq +static inline u64 read64(const volatile void __iomem *addr) +{ + return readq(addr); +} +#else +static inline u64 read64(const volatile void __iomem *addr) +{ + u64 l, h; + l = readl(addr); + h = readl(addr+4); + return l | (h << 32); +} +#endif + /* * Can be used in atomic (including NMI) or process context. RCU read * lock can only be released after the IO memory area accessing. @@ -280,11 +295,9 @@ static int acpi_atomic_read_mem(u64 paddr, u64 *val, u32 width) case 32: *val = readl(addr); break; -#ifdef readq case 64: - *val = readq(addr); + *val = read64(addr); break; -#endif default: return -EINVAL; } @@ -293,6 +306,19 @@ static int acpi_atomic_read_mem(u64 paddr, u64 *val, u32 width) return 0; } +#ifdef writeq +static inline void write64(u64 val, volatile void __iomem *addr) +{ + writeq(val, addr); +} +#else +static inline void write64(u64 val, volatile void __iomem *addr) +{ + writel(val, addr); + writel(val>>32, addr+4); +} +#endif + static int acpi_atomic_write_mem(u64 paddr, u64 val, u32 width) { void __iomem *addr; @@ -309,11 +335,9 @@ static int acpi_atomic_write_mem(u64 paddr, u64 val, u32 width) case 32: writel(val, addr); break; -#ifdef writeq case 64: - writeq(val, addr); + write64(val, addr); break; -#endif default: return -EINVAL; } From a654e5ee4f2213844d23361eda4955fe9efaf35f Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Thu, 8 Dec 2011 11:25:41 +0800 Subject: [PATCH 02/11] ACPI, APEI, GHES: Add PCIe AER recovery support aer_recover_queue() is called when recoverable PCIe AER errors are notified by firmware to do the recovery work. Signed-off-by: Huang Ying Signed-off-by: Len Brown --- drivers/acpi/apei/ghes.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index b8e08cb67a18..511b971d1148 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -45,6 +45,8 @@ #include #include #include +#include +#include #include #include #include @@ -476,6 +478,27 @@ static void ghes_do_proc(const struct acpi_hest_generic_status *estatus) } #endif } +#ifdef CONFIG_ACPI_APEI_PCIEAER + else if (!uuid_le_cmp(*(uuid_le *)gdata->section_type, + CPER_SEC_PCIE)) { + struct cper_sec_pcie *pcie_err; + pcie_err = (struct cper_sec_pcie *)(gdata+1); + if (sev == GHES_SEV_RECOVERABLE && + sec_sev == GHES_SEV_RECOVERABLE && + pcie_err->validation_bits & CPER_PCIE_VALID_DEVICE_ID && + pcie_err->validation_bits & CPER_PCIE_VALID_AER_INFO) { + unsigned int devfn; + int aer_severity; + devfn = PCI_DEVFN(pcie_err->device_id.device, + pcie_err->device_id.function); + aer_severity = cper_severity_to_aer(sev); + aer_recover_queue(pcie_err->device_id.segment, + pcie_err->device_id.bus, + devfn, aer_severity); + } + + } +#endif } } From 46b91e379f7180b482b789fbe615946d91e3a07f Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 8 Dec 2011 11:25:42 +0800 Subject: [PATCH 03/11] ACPI, APEI, Print resource errors in conventional format Use the normal %pR-like format for MMIO and I/O port ranges. Signed-off-by: Bjorn Helgaas Signed-off-by: Huang Ying Signed-off-by: Len Brown --- drivers/acpi/apei/apei-base.c | 8 ++++---- drivers/acpi/apei/einj.c | 11 ++++++----- 2 files changed, 10 insertions(+), 9 deletions(-) diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c index 61540360d5ce..3492896b96f2 100644 --- a/drivers/acpi/apei/apei-base.c +++ b/drivers/acpi/apei/apei-base.c @@ -460,9 +460,9 @@ int apei_resources_request(struct apei_resources *resources, desc); if (!r) { pr_err(APEI_PFX - "Can not request iomem region <%016llx-%016llx> for GARs.\n", + "Can not request [mem %#010llx-%#010llx] for %s registers\n", (unsigned long long)res->start, - (unsigned long long)res->end); + (unsigned long long)res->end - 1, desc); res_bak = res; goto err_unmap_iomem; } @@ -472,9 +472,9 @@ int apei_resources_request(struct apei_resources *resources, r = request_region(res->start, res->end - res->start, desc); if (!r) { pr_err(APEI_PFX - "Can not request ioport region <%016llx-%016llx> for GARs.\n", + "Can not request [io %#06llx-%#06llx] for %s registers\n", (unsigned long long)res->start, - (unsigned long long)res->end); + (unsigned long long)res->end - 1, desc); res_bak = res; goto err_unmap_ioport; } diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c index 589b96c38704..d25390274d7b 100644 --- a/drivers/acpi/apei/einj.c +++ b/drivers/acpi/apei/einj.c @@ -209,9 +209,10 @@ static int __einj_error_trigger(u64 trigger_paddr) "APEI EINJ Trigger Table"); if (!r) { pr_err(EINJ_PFX - "Can not request iomem region <%016llx-%016llx> for Trigger table.\n", + "Can not request [mem %#010llx-%#010llx] for Trigger table\n", (unsigned long long)trigger_paddr, - (unsigned long long)trigger_paddr+sizeof(*trigger_tab)); + (unsigned long long)trigger_paddr + + sizeof(*trigger_tab) - 1); goto out; } trigger_tab = ioremap_cache(trigger_paddr, sizeof(*trigger_tab)); @@ -232,9 +233,9 @@ static int __einj_error_trigger(u64 trigger_paddr) "APEI EINJ Trigger Table"); if (!r) { pr_err(EINJ_PFX -"Can not request iomem region <%016llx-%016llx> for Trigger Table Entry.\n", - (unsigned long long)trigger_paddr+sizeof(*trigger_tab), - (unsigned long long)trigger_paddr + table_size); +"Can not request [mem %#010llx-%#010llx] for Trigger Table Entry\n", + (unsigned long long)trigger_paddr + sizeof(*trigger_tab), + (unsigned long long)trigger_paddr + table_size - 1); goto out_rel_header; } iounmap(trigger_tab); From ad6861547b52ad7c31eacc336b79ac91d7fded75 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Thu, 8 Dec 2011 11:25:43 +0800 Subject: [PATCH 04/11] ACPI, APEI, Remove table not found message Because APEI tables are optional, these message may confuse users, for example, https://bugs.launchpad.net/ubuntu/+source/linux/+bug/599715 Reported-by: Bjorn Helgaas Signed-off-by: Huang Ying Signed-off-by: Len Brown --- drivers/acpi/apei/einj.c | 5 ++--- drivers/acpi/apei/erst.c | 5 ++--- drivers/acpi/apei/hest.c | 5 ++--- 3 files changed, 6 insertions(+), 9 deletions(-) diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c index d25390274d7b..43eeb2e6e635 100644 --- a/drivers/acpi/apei/einj.c +++ b/drivers/acpi/apei/einj.c @@ -466,10 +466,9 @@ static int __init einj_init(void) status = acpi_get_table(ACPI_SIG_EINJ, 0, (struct acpi_table_header **)&einj_tab); - if (status == AE_NOT_FOUND) { - pr_info(EINJ_PFX "Table is not found!\n"); + if (status == AE_NOT_FOUND) return -ENODEV; - } else if (ACPI_FAILURE(status)) { + else if (ACPI_FAILURE(status)) { const char *msg = acpi_format_exception(status); pr_err(EINJ_PFX "Failed to get table, %s\n", msg); return -EINVAL; diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c index 631b9477b99c..8e8d786c5d23 100644 --- a/drivers/acpi/apei/erst.c +++ b/drivers/acpi/apei/erst.c @@ -1125,10 +1125,9 @@ static int __init erst_init(void) status = acpi_get_table(ACPI_SIG_ERST, 0, (struct acpi_table_header **)&erst_tab); - if (status == AE_NOT_FOUND) { - pr_info(ERST_PFX "Table is not found!\n"); + if (status == AE_NOT_FOUND) goto err; - } else if (ACPI_FAILURE(status)) { + else if (ACPI_FAILURE(status)) { const char *msg = acpi_format_exception(status); pr_err(ERST_PFX "Failed to get table, %s\n", msg); rc = -EINVAL; diff --git a/drivers/acpi/apei/hest.c b/drivers/acpi/apei/hest.c index 05fee06f4d6e..f709269d4932 100644 --- a/drivers/acpi/apei/hest.c +++ b/drivers/acpi/apei/hest.c @@ -221,10 +221,9 @@ void __init acpi_hest_init(void) status = acpi_get_table(ACPI_SIG_HEST, 0, (struct acpi_table_header **)&hest_tab); - if (status == AE_NOT_FOUND) { - pr_info(HEST_PFX "Table not found.\n"); + if (status == AE_NOT_FOUND) goto err; - } else if (ACPI_FAILURE(status)) { + else if (ACPI_FAILURE(status)) { const char *msg = acpi_format_exception(status); pr_err(HEST_PFX "Failed to get table, %s\n", msg); rc = -EINVAL; From 5ba82ab534a325d310fe02af1c149f1072792c7b Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Thu, 8 Dec 2011 11:25:44 +0800 Subject: [PATCH 05/11] ACPI, APEI, GHES, Distinguish interleaved error report in kernel log In most cases, printk only guarantees messages from different printk calling will not be interleaved between each other. But, one APEI GHES hardware error report will involve multiple printk calling, normally each for one line. So it is possible that the hardware error report comes from different generic hardware error source will be interleaved. In this patch, a sequence number is prefixed to each line of error report. So that, even if they are interleaved, they still can be distinguished by the prefixed sequence number. Signed-off-by: Huang Ying Signed-off-by: Len Brown --- drivers/acpi/apei/ghes.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 511b971d1148..9dcb2d86aeab 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -506,16 +506,22 @@ static void __ghes_print_estatus(const char *pfx, const struct acpi_hest_generic *generic, const struct acpi_hest_generic_status *estatus) { + static atomic_t seqno; + unsigned int curr_seqno; + char pfx_seq[64]; + if (pfx == NULL) { if (ghes_severity(estatus->error_severity) <= GHES_SEV_CORRECTED) - pfx = KERN_WARNING HW_ERR; + pfx = KERN_WARNING; else - pfx = KERN_ERR HW_ERR; + pfx = KERN_ERR; } + curr_seqno = atomic_inc_return(&seqno); + snprintf(pfx_seq, sizeof(pfx_seq), "%s{%u}" HW_ERR, pfx, curr_seqno); printk("%s""Hardware error from APEI Generic Hardware Error Source: %d\n", - pfx, generic->header.source_id); - apei_estatus_print(pfx, estatus); + pfx_seq, generic->header.source_id); + apei_estatus_print(pfx_seq, estatus); } static int ghes_print_estatus(const char *pfx, @@ -798,7 +804,7 @@ static int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs) if (sev_global >= GHES_SEV_PANIC) { oops_begin(); - __ghes_print_estatus(KERN_EMERG HW_ERR, ghes_global->generic, + __ghes_print_estatus(KERN_EMERG, ghes_global->generic, ghes_global->estatus); /* reboot to log the error! */ if (panic_timeout == 0) From 46d12f0bcb17b2de89a059114349d472b7eb1783 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Thu, 8 Dec 2011 11:25:45 +0800 Subject: [PATCH 06/11] ACPI, APEI, Printk queued error record before panic Because printk is not safe inside NMI handler, the recoverable error records received in NMI handler will be queued to be printked in a delayed IRQ context via irq_work. If a fatal error occurs after the recoverable error and before the irq_work processed, we lost a error report. To solve the issue, the queued error records are printked in NMI handler if system will go panic. Signed-off-by: Huang Ying Signed-off-by: Len Brown --- drivers/acpi/apei/ghes.c | 59 ++++++++++++++++++++++++++++++++-------- 1 file changed, 47 insertions(+), 12 deletions(-) diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 9dcb2d86aeab..aaf36090de1e 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -740,26 +740,34 @@ static int ghes_notify_sci(struct notifier_block *this, return ret; } -static void ghes_proc_in_irq(struct irq_work *irq_work) +static struct llist_node *llist_nodes_reverse(struct llist_node *llnode) { - struct llist_node *llnode, *next, *tail = NULL; - struct ghes_estatus_node *estatus_node; - struct acpi_hest_generic *generic; - struct acpi_hest_generic_status *estatus; - u32 len, node_len; + struct llist_node *next, *tail = NULL; - /* - * Because the time order of estatus in list is reversed, - * revert it back to proper order. - */ - llnode = llist_del_all(&ghes_estatus_llist); while (llnode) { next = llnode->next; llnode->next = tail; tail = llnode; llnode = next; } - llnode = tail; + + return tail; +} + +static void ghes_proc_in_irq(struct irq_work *irq_work) +{ + struct llist_node *llnode, *next; + struct ghes_estatus_node *estatus_node; + struct acpi_hest_generic *generic; + struct acpi_hest_generic_status *estatus; + u32 len, node_len; + + llnode = llist_del_all(&ghes_estatus_llist); + /* + * Because the time order of estatus in list is reversed, + * revert it back to proper order. + */ + llnode = llist_nodes_reverse(llnode); while (llnode) { next = llnode->next; estatus_node = llist_entry(llnode, struct ghes_estatus_node, @@ -779,6 +787,32 @@ static void ghes_proc_in_irq(struct irq_work *irq_work) } } +static void ghes_print_queued_estatus(void) +{ + struct llist_node *llnode; + struct ghes_estatus_node *estatus_node; + struct acpi_hest_generic *generic; + struct acpi_hest_generic_status *estatus; + u32 len, node_len; + + llnode = llist_del_all(&ghes_estatus_llist); + /* + * Because the time order of estatus in list is reversed, + * revert it back to proper order. + */ + llnode = llist_nodes_reverse(llnode); + while (llnode) { + estatus_node = llist_entry(llnode, struct ghes_estatus_node, + llnode); + estatus = GHES_ESTATUS_FROM_NODE(estatus_node); + len = apei_estatus_len(estatus); + node_len = GHES_ESTATUS_NODE_LEN(len); + generic = estatus_node->generic; + ghes_print_estatus(NULL, generic, estatus); + llnode = llnode->next; + } +} + static int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs) { struct ghes *ghes, *ghes_global = NULL; @@ -804,6 +838,7 @@ static int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs) if (sev_global >= GHES_SEV_PANIC) { oops_begin(); + ghes_print_queued_estatus(); __ghes_print_estatus(KERN_EMERG, ghes_global->generic, ghes_global->estatus); /* reboot to log the error! */ From 76da3fb3575e39fb23b2c072997ccd1187a2ce9d Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Thu, 8 Dec 2011 11:25:46 +0800 Subject: [PATCH 07/11] ACPI, Add RAM mapping support to ACPI atomic IO support On one of our testing machine, the following EINJ command lines: # echo 0x10000000 > param1 # echo 0xfffffffffffff000 > param2 # echo 0x8 > error_type # echo 1 > error_inject Will get: echo: write error: Input/output error The EIO comes from: rc = apei_exec_pre_map_gars(&trigger_ctx); The root cause is as follow. Normally, ACPI atomic IO support is used to access IO memory. But in EINJ of that machine, it is used to access RAM to trigger the injected error. And the ioremap() called by apei_exec_pre_map_gars() can not map the RAM. This patch add RAM mapping support to ACPI atomic IO support to satisfy EINJ requirement. Signed-off-by: Huang Ying Tested-by: Tony Luck Signed-off-by: Len Brown --- drivers/acpi/atomicio.c | 41 +++++++++++++++++++++++++++++++++++++---- 1 file changed, 37 insertions(+), 4 deletions(-) diff --git a/drivers/acpi/atomicio.c b/drivers/acpi/atomicio.c index 1016f186c17c..d4a5b3d3657b 100644 --- a/drivers/acpi/atomicio.c +++ b/drivers/acpi/atomicio.c @@ -32,6 +32,8 @@ #include #include #include +#include +#include #include #define ACPI_PFX "ACPI: " @@ -97,6 +99,37 @@ static void __iomem *__acpi_try_ioremap(phys_addr_t paddr, return NULL; } +#ifndef CONFIG_IA64 +#define should_use_kmap(pfn) page_is_ram(pfn) +#else +/* ioremap will take care of cache attributes */ +#define should_use_kmap(pfn) 0 +#endif + +static void __iomem *acpi_map(phys_addr_t pg_off, unsigned long pg_sz) +{ + unsigned long pfn; + + pfn = pg_off >> PAGE_SHIFT; + if (should_use_kmap(pfn)) { + if (pg_sz > PAGE_SIZE) + return NULL; + return (void __iomem __force *)kmap(pfn_to_page(pfn)); + } else + return ioremap(pg_off, pg_sz); +} + +static void acpi_unmap(phys_addr_t pg_off, void __iomem *vaddr) +{ + unsigned long pfn; + + pfn = pg_off >> PAGE_SHIFT; + if (page_is_ram(pfn)) + kunmap(pfn_to_page(pfn)); + else + iounmap(vaddr); +} + /* * Used to pre-map the specified IO memory area. First try to find * whether the area is already pre-mapped, if it is, increase the @@ -119,7 +152,7 @@ static void __iomem *acpi_pre_map(phys_addr_t paddr, pg_off = paddr & PAGE_MASK; pg_sz = ((paddr + size + PAGE_SIZE - 1) & PAGE_MASK) - pg_off; - vaddr = ioremap(pg_off, pg_sz); + vaddr = acpi_map(pg_off, pg_sz); if (!vaddr) return NULL; map = kmalloc(sizeof(*map), GFP_KERNEL); @@ -135,7 +168,7 @@ static void __iomem *acpi_pre_map(phys_addr_t paddr, vaddr = __acpi_try_ioremap(paddr, size); if (vaddr) { spin_unlock_irqrestore(&acpi_iomaps_lock, flags); - iounmap(map->vaddr); + acpi_unmap(pg_off, map->vaddr); kfree(map); return vaddr; } @@ -144,7 +177,7 @@ static void __iomem *acpi_pre_map(phys_addr_t paddr, return map->vaddr + (paddr - map->paddr); err_unmap: - iounmap(vaddr); + acpi_unmap(pg_off, vaddr); return NULL; } @@ -177,7 +210,7 @@ static void acpi_post_unmap(phys_addr_t paddr, unsigned long size) return; synchronize_rcu(); - iounmap(map->vaddr); + acpi_unmap(map->paddr, map->vaddr); kfree(map); } From fdea163d8c17ba08814142259a467ba3e899010d Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Thu, 8 Dec 2011 11:25:47 +0800 Subject: [PATCH 08/11] ACPI, APEI, EINJ, Fix resource conflict on some machine Some APEI firmware implementation will access injected address specified in param1 to trigger the error when injecting memory error. This will cause resource conflict with RAM. On one of our testing machine, if injecting at memory address 0x10000000, the following error will be reported in dmesg: APEI: Can not request iomem region <0000000010000000-0000000010000008> for GARs. This patch removes the injecting memory address range from trigger table resources to avoid conflict. Signed-off-by: Huang Ying Tested-by: Tony Luck Signed-off-by: Len Brown --- drivers/acpi/apei/apei-base.c | 11 +++++++++++ drivers/acpi/apei/apei-internal.h | 3 +++ drivers/acpi/apei/einj.c | 24 ++++++++++++++++++++++-- 3 files changed, 36 insertions(+), 2 deletions(-) diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c index 3492896b96f2..f2c5062e2b32 100644 --- a/drivers/acpi/apei/apei-base.c +++ b/drivers/acpi/apei/apei-base.c @@ -421,6 +421,17 @@ static int apei_resources_merge(struct apei_resources *resources1, return 0; } +int apei_resources_add(struct apei_resources *resources, + unsigned long start, unsigned long size, + bool iomem) +{ + if (iomem) + return apei_res_add(&resources->iomem, start, size); + else + return apei_res_add(&resources->ioport, start, size); +} +EXPORT_SYMBOL_GPL(apei_resources_add); + /* * EINJ has two groups of GARs (EINJ table entry and trigger table * entry), so common resources are subtracted from the trigger table diff --git a/drivers/acpi/apei/apei-internal.h b/drivers/acpi/apei/apei-internal.h index f57050e7a5e7..d778edd34fba 100644 --- a/drivers/acpi/apei/apei-internal.h +++ b/drivers/acpi/apei/apei-internal.h @@ -95,6 +95,9 @@ static inline void apei_resources_init(struct apei_resources *resources) } void apei_resources_fini(struct apei_resources *resources); +int apei_resources_add(struct apei_resources *resources, + unsigned long start, unsigned long size, + bool iomem); int apei_resources_sub(struct apei_resources *resources1, struct apei_resources *resources2); int apei_resources_request(struct apei_resources *resources, diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c index 43eeb2e6e635..4fdc8a3b4f6c 100644 --- a/drivers/acpi/apei/einj.c +++ b/drivers/acpi/apei/einj.c @@ -195,7 +195,8 @@ static int einj_check_trigger_header(struct acpi_einj_trigger *trigger_tab) } /* Execute instructions in trigger error action table */ -static int __einj_error_trigger(u64 trigger_paddr) +static int __einj_error_trigger(u64 trigger_paddr, u32 type, + u64 param1, u64 param2) { struct acpi_einj_trigger *trigger_tab = NULL; struct apei_exec_context trigger_ctx; @@ -256,6 +257,25 @@ static int __einj_error_trigger(u64 trigger_paddr) rc = apei_resources_sub(&trigger_resources, &einj_resources); if (rc) goto out_fini; + /* + * Some firmware will access target address specified in + * param1 to trigger the error when injecting memory error. + * This will cause resource conflict with regular memory. So + * remove it from trigger table resources. + */ + if (param_extension && (type & 0x0038) && param2) { + struct apei_resources addr_resources; + apei_resources_init(&addr_resources); + rc = apei_resources_add(&addr_resources, + param1 & param2, + ~param2 + 1, true); + if (rc) + goto out_fini; + rc = apei_resources_sub(&trigger_resources, &addr_resources); + apei_resources_fini(&addr_resources); + if (rc) + goto out_fini; + } rc = apei_resources_request(&trigger_resources, "APEI EINJ Trigger"); if (rc) goto out_fini; @@ -325,7 +345,7 @@ static int __einj_error_inject(u32 type, u64 param1, u64 param2) if (rc) return rc; trigger_paddr = apei_exec_ctx_get_output(&ctx); - rc = __einj_error_trigger(trigger_paddr); + rc = __einj_error_trigger(trigger_paddr, type, param1, param2); if (rc) return rc; rc = apei_exec_run_optional(&ctx, ACPI_EINJ_END_OPERATION); From b4e008dc53a31cb4bf6a12d9dbaf1d5c6070a838 Mon Sep 17 00:00:00 2001 From: "Xiao, Hui" Date: Thu, 8 Dec 2011 11:25:48 +0800 Subject: [PATCH 09/11] ACPI, APEI, EINJ, Refine the fix of resource conflict Current fix for resource conflict is to remove the address region from trigger resource, which is highly relies on valid user input. This patch is trying to avoid such potential issues by fetching the exact address region from trigger action table entry. Signed-off-by: Xiao, Hui Signed-off-by: Huang Ying Signed-off-by: Len Brown --- drivers/acpi/apei/einj.c | 38 ++++++++++++++++++++++++++++++++------ 1 file changed, 32 insertions(+), 6 deletions(-) diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c index 4fdc8a3b4f6c..6e6512e68a2d 100644 --- a/drivers/acpi/apei/einj.c +++ b/drivers/acpi/apei/einj.c @@ -194,6 +194,26 @@ static int einj_check_trigger_header(struct acpi_einj_trigger *trigger_tab) return 0; } +static struct acpi_generic_address *einj_get_trigger_parameter_region( + struct acpi_einj_trigger *trigger_tab, u64 param1, u64 param2) +{ + int i; + struct acpi_whea_header *entry; + + entry = (struct acpi_whea_header *) + ((char *)trigger_tab + sizeof(struct acpi_einj_trigger)); + for (i = 0; i < trigger_tab->entry_count; i++) { + if (entry->action == ACPI_EINJ_TRIGGER_ERROR && + entry->instruction == ACPI_EINJ_WRITE_REGISTER_VALUE && + entry->register_region.space_id == + ACPI_ADR_SPACE_SYSTEM_MEMORY && + (entry->register_region.address & param2) == (param1 & param2)) + return &entry->register_region; + entry++; + } + + return NULL; +} /* Execute instructions in trigger error action table */ static int __einj_error_trigger(u64 trigger_paddr, u32 type, u64 param1, u64 param2) @@ -205,6 +225,7 @@ static int __einj_error_trigger(u64 trigger_paddr, u32 type, struct resource *r; u32 table_size; int rc = -EIO; + struct acpi_generic_address *trigger_param_region = NULL; r = request_mem_region(trigger_paddr, sizeof(*trigger_tab), "APEI EINJ Trigger Table"); @@ -266,12 +287,17 @@ static int __einj_error_trigger(u64 trigger_paddr, u32 type, if (param_extension && (type & 0x0038) && param2) { struct apei_resources addr_resources; apei_resources_init(&addr_resources); - rc = apei_resources_add(&addr_resources, - param1 & param2, - ~param2 + 1, true); - if (rc) - goto out_fini; - rc = apei_resources_sub(&trigger_resources, &addr_resources); + trigger_param_region = einj_get_trigger_parameter_region( + trigger_tab, param1, param2); + if (trigger_param_region) { + rc = apei_resources_add(&addr_resources, + trigger_param_region->address, + trigger_param_region->bit_width/8, true); + if (rc) + goto out_fini; + rc = apei_resources_sub(&trigger_resources, + &addr_resources); + } apei_resources_fini(&addr_resources); if (rc) goto out_fini; From b54ac6d2a25084667da781c7ca2cebef52a2bcdd Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Thu, 8 Dec 2011 11:25:49 +0800 Subject: [PATCH 10/11] ACPI, Record ACPI NVS regions Some firmware will access memory in ACPI NVS region via APEI. That is, instructions in APEI ERST/EINJ table will read/write ACPI NVS region. The original resource conflict checking in APEI code will check memory/ioport accessed by APEI via general resource management mechanism. But ACPI NVS region is marked as busy already, so that the false resource conflict will prevent APEI ERST/EINJ to work. To fix this, this patch record ACPI NVS regions, so that we can avoid request resources for memory region inside it. Signed-off-by: Huang Ying Signed-off-by: Len Brown --- arch/x86/kernel/e820.c | 4 ++-- drivers/acpi/Makefile | 3 ++- drivers/acpi/nvs.c | 53 +++++++++++++++++++++++++++++++++++++++++- include/linux/acpi.h | 20 +++++++++++----- 4 files changed, 70 insertions(+), 10 deletions(-) diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 303a0e48f076..51c3b186e5b9 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -714,7 +714,7 @@ void __init e820_mark_nosave_regions(unsigned long limit_pfn) } #endif -#ifdef CONFIG_HIBERNATION +#ifdef CONFIG_ACPI /** * Mark ACPI NVS memory region, so that we can save/restore it during * hibernation and the subsequent resume. @@ -727,7 +727,7 @@ static int __init e820_mark_nvs_memory(void) struct e820entry *ei = &e820.map[i]; if (ei->type == E820_NVS) - suspend_nvs_register(ei->addr, ei->size); + acpi_nvs_register(ei->addr, ei->size); } return 0; diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile index ecb26b4f29a0..c07f44f05f9d 100644 --- a/drivers/acpi/Makefile +++ b/drivers/acpi/Makefile @@ -20,11 +20,12 @@ obj-y += acpi.o \ # All the builtin files are in the "acpi." module_param namespace. acpi-y += osl.o utils.o reboot.o acpi-y += atomicio.o +acpi-y += nvs.o # sleep related files acpi-y += wakeup.o acpi-y += sleep.o -acpi-$(CONFIG_ACPI_SLEEP) += proc.o nvs.o +acpi-$(CONFIG_ACPI_SLEEP) += proc.o # diff --git a/drivers/acpi/nvs.c b/drivers/acpi/nvs.c index 096787b43c96..7a2035fa8c71 100644 --- a/drivers/acpi/nvs.c +++ b/drivers/acpi/nvs.c @@ -15,6 +15,56 @@ #include #include +/* ACPI NVS regions, APEI may use it */ + +struct nvs_region { + __u64 phys_start; + __u64 size; + struct list_head node; +}; + +static LIST_HEAD(nvs_region_list); + +#ifdef CONFIG_ACPI_SLEEP +static int suspend_nvs_register(unsigned long start, unsigned long size); +#else +static inline int suspend_nvs_register(unsigned long a, unsigned long b) +{ + return 0; +} +#endif + +int acpi_nvs_register(__u64 start, __u64 size) +{ + struct nvs_region *region; + + region = kmalloc(sizeof(*region), GFP_KERNEL); + if (!region) + return -ENOMEM; + region->phys_start = start; + region->size = size; + list_add_tail(®ion->node, &nvs_region_list); + + return suspend_nvs_register(start, size); +} + +int acpi_nvs_for_each_region(int (*func)(__u64 start, __u64 size, void *data), + void *data) +{ + int rc; + struct nvs_region *region; + + list_for_each_entry(region, &nvs_region_list, node) { + rc = func(region->phys_start, region->size, data); + if (rc) + return rc; + } + + return 0; +} + + +#ifdef CONFIG_ACPI_SLEEP /* * Platforms, like ACPI, may want us to save some memory used by them during * suspend and to restore the contents of this memory during the subsequent @@ -41,7 +91,7 @@ static LIST_HEAD(nvs_list); * things so that the data from page-aligned addresses in this region will * be copied into separate RAM pages. */ -int suspend_nvs_register(unsigned long start, unsigned long size) +static int suspend_nvs_register(unsigned long start, unsigned long size) { struct nvs_page *entry, *next; @@ -159,3 +209,4 @@ void suspend_nvs_restore(void) if (entry->data) memcpy(entry->kaddr, entry->data, entry->size); } +#endif diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 6001b4da39dd..26b75442ff7a 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -306,6 +306,11 @@ extern acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 *mask, u32 req); extern void acpi_early_init(void); +extern int acpi_nvs_register(__u64 start, __u64 size); + +extern int acpi_nvs_for_each_region(int (*func)(__u64, __u64, void *), + void *data); + #else /* !CONFIG_ACPI */ #define acpi_disabled 1 @@ -348,15 +353,18 @@ static inline int acpi_table_parse(char *id, { return -1; } -#endif /* !CONFIG_ACPI */ -#ifdef CONFIG_ACPI_SLEEP -int suspend_nvs_register(unsigned long start, unsigned long size); -#else -static inline int suspend_nvs_register(unsigned long a, unsigned long b) +static inline int acpi_nvs_register(__u64 start, __u64 size) { return 0; } -#endif + +static inline int acpi_nvs_for_each_region(int (*func)(__u64, __u64, void *), + void *data) +{ + return 0; +} + +#endif /* !CONFIG_ACPI */ #endif /*_LINUX_ACPI_H*/ From 4134b8c8811f23aa8a281db50dcee64dda414736 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Thu, 8 Dec 2011 11:25:50 +0800 Subject: [PATCH 11/11] ACPI, APEI, Resolve false conflict between ACPI NVS and APEI Some firmware will access memory in ACPI NVS region via APEI. That is, instructions in APEI ERST/EINJ table will read/write ACPI NVS region. The original resource conflict checking in APEI code will check memory/ioport accessed by APEI via general resource management mech. But ACPI NVS region is marked as busy already, so that the false resource conflict will prevent APEI ERST/EINJ to work. To fix this, this patch excludes ACPI NVS regions when APEI components request resources. So that they will not conflict with ACPI NVS regions. Reported-and-tested-by: Pavel Ivanov Signed-off-by: Huang Ying Signed-off-by: Len Brown --- drivers/acpi/apei/apei-base.c | 29 ++++++++++++++++++++++++++++- 1 file changed, 28 insertions(+), 1 deletion(-) diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c index f2c5062e2b32..4abb6c74a938 100644 --- a/drivers/acpi/apei/apei-base.c +++ b/drivers/acpi/apei/apei-base.c @@ -449,8 +449,19 @@ int apei_resources_sub(struct apei_resources *resources1, } EXPORT_SYMBOL_GPL(apei_resources_sub); +static int apei_get_nvs_callback(__u64 start, __u64 size, void *data) +{ + struct apei_resources *resources = data; + return apei_res_add(&resources->iomem, start, size); +} + +static int apei_get_nvs_resources(struct apei_resources *resources) +{ + return acpi_nvs_for_each_region(apei_get_nvs_callback, resources); +} + /* - * IO memory/port rersource management mechanism is used to check + * IO memory/port resource management mechanism is used to check * whether memory/port area used by GARs conflicts with normal memory * or IO memory/port of devices. */ @@ -459,12 +470,26 @@ int apei_resources_request(struct apei_resources *resources, { struct apei_res *res, *res_bak = NULL; struct resource *r; + struct apei_resources nvs_resources; int rc; rc = apei_resources_sub(resources, &apei_resources_all); if (rc) return rc; + /* + * Some firmware uses ACPI NVS region, that has been marked as + * busy, so exclude it from APEI resources to avoid false + * conflict. + */ + apei_resources_init(&nvs_resources); + rc = apei_get_nvs_resources(&nvs_resources); + if (rc) + goto res_fini; + rc = apei_resources_sub(resources, &nvs_resources); + if (rc) + goto res_fini; + rc = -EINVAL; list_for_each_entry(res, &resources->iomem, list) { r = request_mem_region(res->start, res->end - res->start, @@ -511,6 +536,8 @@ err_unmap_iomem: break; release_mem_region(res->start, res->end - res->start); } +res_fini: + apei_resources_fini(&nvs_resources); return rc; } EXPORT_SYMBOL_GPL(apei_resources_request);