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 <tbaicar@codeaurora.org>
CC: Jonathan (Zhixiong) Zhang <zjzhang@codeaurora.org>
Reviewed-by: James Morse <james.morse@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 3dcd7ec69bca8f939dba09e9087902fbd1561e8a..80559977a83e7614cbfae84f4ae9a32d6503ca28 100644 (file)
--- 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 246e64f60610407407b2870da0d77c189f07e7f7..07481af15fd7dbd44da69ae0d3ca0e7e4bbfe8e6 100644 (file)
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -42,6 +42,8 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 
+#include <acpi/ghes.h>
+
 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 b0140c8fc733de73c8abad0fab10380a3cbae0a0..de14d49a5c903276ed8442feb6831cfe93f0dc7d 100644 (file)
--- 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 81e06e3cb08f8880317643b81ed341e7175e4655..42ddc0eff25bebbe1ef148cb0d601d8a00570c58 100644 (file)
--- 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 8f8fea004df52409be73d339545f0af6f5884ec5..95305aeb13ff79265dea8c33f3a12145722d8134 100644 (file)
--- a/include/acpi/ghes.h
+++ b/include/acpi/ghes.h
@@ -1,3 +1,6 @@
+#ifndef GHES_H
+#define GHES_H
+
 #include <acpi/apei.h>
 #include <acpi/hed.h>
 
@@ -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 */