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.

BugLink: https://launchpad.net/bugs/1696570
Signed-off-by: Jonathan (Zhixiong) Zhang <zjzhang@codeaurora.org>
Signed-off-by: Tyler Baicar <tbaicar@codeaurora.org>
Reviewed-by: James Morse <james.morse@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
(cherry picked from commit 2fb5853e4442334cb66fc2ab33a51c91d4434769)
Signed-off-by: Manoj Iyer <manoj.iyer@canonical.com>
Acked-by: Stefan Bader <stefan.bader@canonical.com>
Acked-by: Seth Forshee <seth.forshee@canonical.com>
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@canonical.com>

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 3c407598a327a0390a6307ce75354b9763cd50b0..67830aa8712e989968de6066e091135ca0e9459f 100644 (file)
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -134,6 +134,8 @@ 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,
@@ -690,6 +692,16 @@ 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;
@@ -697,6 +709,11 @@ 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);
@@ -837,8 +854,6 @@ 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;
@@ -924,18 +939,6 @@ 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;
@@ -953,8 +956,11 @@ 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;