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 we can't guarantee this will be
taken before we return.
Unless we interrupted a context with irqs-masked, we can call
irq_work_run() to do the work now. Otherwise return -EINPROGRESS to
indicate ghes_notify_sea() found some work to do, but it hasn't
finished yet.
With this we can take apei_claim_sea() returning '0' to mean 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>
Reviewed-by: Punit Agrawal <punit.agrawal@xxxxxxx>
Tested-by: Tyler Baicar <tbaicar@xxxxxxxxxxxxxx>
CC: Xie XiuQi <xiexiuqi@xxxxxxxxxx>
CC: gengdongjiu <gengdongjiu@xxxxxxxxxx>
---
Changes since v2:
* Removed IS_ENABLED() check, done by the caller unless we have a dummy
definition.
---
arch/arm64/kernel/acpi.c | 19 +++++++++++++++++++
arch/arm64/mm/fault.c | 9 ++++-----
2 files changed, 23 insertions(+), 5 deletions(-)
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index a9b8bba014b5..09744e2d15a0 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -23,6 +23,7 @@
#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>
@@ -270,10 +271,14 @@ int apei_claim_sea(struct pt_regs *regs)
{
int err = -ENOENT;
unsigned long current_flags = arch_local_save_flags();
+ unsigned long interrupted_flags = current_flags;
if (!IS_ENABLED(CONFIG_ACPI_APEI_SEA))
return err;
+ if (regs)
+ interrupted_flags = regs->pstate;
+
/*
* SEA can interrupt SError, mask it and describe this as an NMI so
* that APEI defers the handling.
@@ -282,6 +287,20 @@ 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 (!arch_irqs_disabled_flags(interrupted_flags)) {
+ local_daif_restore(DAIF_PROCCTX_NOIRQ);
+ irq_work_run();
+ } else {
+ err = -EINPROGRESS;
+ }
+ }
+
local_daif_restore(current_flags);
return err;
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 2c38776bb71f..97036e01522a 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -630,11 +630,10 @@ 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 (apei_claim_sea(regs) == 0) {
+ /* APEI claimed this as a firmware-first notification */
+ return 0;
+ }
clear_siginfo(&info);
info.si_signo = inf->sig;
--
2.19.0
