APEI is unable to do all of its error handling work in nmi-context, so
it defers non-fatal work onto the irq_work queue. arch_irq_work_raise()
sends an IPI to the calling cpu, but this is not guaranteed to be taken
before returning to user-space.
Unless the exception interrupted a context with irqs-masked,
irq_work_run() can run immediately. Otherwise return -EINPROGRESS to
indicate ghes_notify_sea() found some work to do, but it hasn't
finished yet.
With this apei_claim_sea() returning '0' means this external-abort was
also notification of a firmware-first RAS error, and that APEI has
processed the CPER records.
Signed-off-by: James Morse <james.morse@xxxxxxx>
---
Changes since $last_year:
* Dropped all the tags ... its been a year.
* Added user_mode() test in do_sea() and expanded the comment.
* Dont depend on daif value for return_to_irqs_enabled because of pNMI.
* pr_warn() should be ratelimited
---
arch/arm64/kernel/acpi.c | 25 +++++++++++++++++++++++++
arch/arm64/mm/fault.c | 12 +++++++-----
2 files changed, 32 insertions(+), 5 deletions(-)
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index a100483b47c4..46ec402e97ed 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -19,6 +19,7 @@
#include <linux/init.h>
#include <linux/irq.h>
#include <linux/irqdomain.h>
+#include <linux/irq_work.h>
#include <linux/memblock.h>
#include <linux/of_fdt.h>
#include <linux/smp.h>
@@ -269,6 +270,7 @@ pgprot_t __acpi_get_mem_attribute(phys_addr_t addr)
int apei_claim_sea(struct pt_regs *regs)
{
int err = -ENOENT;
+ bool return_to_irqs_enabled;
unsigned long current_flags;
if (!IS_ENABLED(CONFIG_ACPI_APEI_GHES))
@@ -276,6 +278,12 @@ int apei_claim_sea(struct pt_regs *regs)
current_flags = local_daif_save_flags();
+ /* current_flags isn't useful here as daif doesn't tell us about pNMI */
+ return_to_irqs_enabled = !irqs_disabled_flags(arch_local_save_flags());
+
+ if (regs)
+ return_to_irqs_enabled = interrupts_enabled(regs);
+
/*
* SEA can interrupt SError, mask it and describe this as an NMI so
* that APEI defers the handling.
@@ -284,6 +292,23 @@ int apei_claim_sea(struct pt_regs *regs)
nmi_enter();
err = ghes_notify_sea();
nmi_exit();
+
+ /*
+ * APEI NMI-like notifications are deferred to irq_work. Unless
+ * we interrupted irqs-masked code, we can do that now.
+ */
+ if (!err) {
+ if (return_to_irqs_enabled) {
+ local_daif_restore(DAIF_PROCCTX_NOIRQ);
+ __irq_enter();
+ irq_work_run();
+ __irq_exit();
+ } else {
+ pr_warn_ratelimited("APEI work queued but not completed");
+ err = -EINPROGRESS;
+ }
+ }
+
local_daif_restore(current_flags);
return err;
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 85566d32958f..cefeb34580da 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -645,11 +645,13 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
inf = esr_to_fault_info(esr);
- /*
- * Return value ignored as we rely on signal merging.
- * Future patches will make this more robust.
- */
- apei_claim_sea(regs);
+ if (user_mode(regs) && apei_claim_sea(regs) == 0) {
+ /*
+ * APEI claimed this as a firmware-first notification.
+ * Some processing deferred to task_work before ret_to_user().
+ */
+ return 0;
+ }
if (esr & ESR_ELx_FnV)
siaddr = NULL;
--
2.24.1
