arm64: acpi: Make apei_claim_sea() synchronise with APEI's irq work

fix #28612342

commit 8fcc4ae6faf8b455eeef00bc9ae70744e3b0f462 upstream

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: NJames Morse <james.morse@arm.com>
Tested-by: NTyler Baicar <baicar@os.amperecomputing.com>
Acked-by: NCatalin Marinas <catalin.marinas@arm.com>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: NBaolin Wang <baolin.wang@linux.alibaba.com>
Reviewed-by: NAlex Shi <alex.shi@linux.alibaba.com>
Acked-by: NCaspar Zhang <caspar@linux.alibaba.com>
Reviewed-by: Nluanshi <zhangliguang@linux.alibaba.com>

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>
@@ -273,6 +274,7 @@ 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))
@@ -280,6 +282,12 @@ int apei_claim_sea(struct pt_regs *regs)
 
 	current_flags = arch_local_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.
@@ -288,6 +296,23 @@ 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;

arch/arm64/mm/fault.c

@@ -630,12 +630,14 @@ 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.
-	 */
+	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;
+	}
 
-	apei_claim_sea(regs);
 	clear_siginfo(&info);
 	info.si_signo = inf->sig;
 	info.si_errno = 0;