arm64: KVM/mm: Move SEA handling behind a single 'claim' interface

fix #28612342

commit d44f1b8dd7e66d80cc4205809e5ace866bd851da upstream

To split up APEIs in_nmi() path, the caller needs to always be
in_nmi(). Add a helper to do the work and claim the notification.

When KVM or the arch code takes an exception that might be a RAS
notification, it asks the APEI firmware-first code whether it wants
to claim the exception. A future kernel-first mechanism may be queried
afterwards, and claim the notification, otherwise we fall through
to the existing default behaviour.

The NOTIFY_SEA code was merged before considering multiple, possibly
interacting, NMI-like notifications and the need to consider kernel
first in the future. Make the 'claiming' behaviour explicit.

Restructuring the APEI code to allow multiple NMI-like notifications
means any notification that might interrupt interrupts-masked
code must always be wrapped in nmi_enter()/nmi_exit(). This will
allow APEI to use in_nmi() to use the right fixmap entries.

Mask SError over this window to prevent an asynchronous RAS error
arriving and tripping 'nmi_enter()'s BUG_ON(in_nmi()).
Signed-off-by: NJames Morse <james.morse@arm.com>
Acked-by: NMarc Zyngier <marc.zyngier@arm.com>
Tested-by: NTyler Baicar <tbaicar@codeaurora.org>
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/include/asm/acpi.h

@@ -18,6 +18,7 @@
 
 #include <asm/cputype.h>
 #include <asm/io.h>
+#include <asm/ptrace.h>
 #include <asm/smp_plat.h>
 #include <asm/tlbflush.h>
 
@@ -99,9 +100,10 @@ static inline u32 get_acpi_id_for_cpu(unsigned int cpu)
 
 static inline void arch_fix_phys_package_id(int num, u32 slot) { }
 void __init acpi_init_cpus(void);
-
+int apei_claim_sea(struct pt_regs *regs);
 #else
 static inline void acpi_init_cpus(void) { }
+static inline int apei_claim_sea(struct pt_regs *regs) { return -ENOENT; }
 #endif /* CONFIG_ACPI */
 
 #ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL

arch/arm64/include/asm/daifflags.h

@@ -20,6 +20,7 @@
 
 #define DAIF_PROCCTX		0
 #define DAIF_PROCCTX_NOIRQ	PSR_I_BIT
+#define DAIF_ERRCTX		(PSR_I_BIT | PSR_A_BIT)
 
 /* mask/save/unmask/restore all exceptions, including interrupts. */
 static inline void local_daif_mask(void)

arch/arm64/include/asm/kvm_ras.h

@@ -4,8 +4,22 @@
 #ifndef __ARM64_KVM_RAS_H__
 #define __ARM64_KVM_RAS_H__
 
+#include <linux/acpi.h>
+#include <linux/errno.h>
 #include <linux/types.h>
 
-int kvm_handle_guest_sea(phys_addr_t addr, unsigned int esr);
+#include <asm/acpi.h>
+
+/*
+ * Was this synchronous external abort a RAS notification?
+ * Returns '0' for errors handled by some RAS subsystem, or -ENOENT.
+ */
+static inline int kvm_handle_guest_sea(phys_addr_t addr, unsigned int esr)
+{
+	/* apei_claim_sea(NULL) expects to mask interrupts itself */
+	lockdep_assert_irqs_enabled();
+
+	return apei_claim_sea(NULL);
+}
 
 #endif /* __ARM64_KVM_RAS_H__ */

arch/arm64/kernel/acpi.c

@@ -28,8 +28,10 @@
 #include <linux/smp.h>
 #include <linux/serial_core.h>
 
+#include <acpi/ghes.h>
 #include <asm/cputype.h>
 #include <asm/cpu_ops.h>
+#include <asm/daifflags.h>
 #include <asm/pgtable.h>
 #include <asm/smp_plat.h>
 
@@ -261,3 +263,33 @@ pgprot_t __acpi_get_mem_attribute(phys_addr_t addr)
 		return __pgprot(PROT_NORMAL_NC);
 	return __pgprot(PROT_DEVICE_nGnRnE);
 }
+
+/*
+ * Claim Synchronous External Aborts as a firmware first notification.
+ *
+ * Used by KVM and the arch do_sea handler.
+ * @regs may be NULL when called from process context.
+ */
+int apei_claim_sea(struct pt_regs *regs)
+{
+	int err = -ENOENT;
+	unsigned long current_flags;
+
+	if (!IS_ENABLED(CONFIG_ACPI_APEI_GHES))
+		return err;
+
+	current_flags = arch_local_save_flags();
+
+	/*
+	 * SEA can interrupt SError, mask it and describe this as an NMI so
+	 * that APEI defers the handling.
+	 */
+	local_daif_restore(DAIF_ERRCTX);
+	nmi_enter();
+	err = ghes_notify_sea();
+	nmi_exit();
+	local_daif_restore(current_flags);
+
+	return err;
+}
+EXPORT_SYMBOL(apei_claim_sea);

arch/arm64/mm/fault.c

@@ -18,6 +18,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/acpi.h>
 #include <linux/extable.h>
 #include <linux/signal.h>
 #include <linux/mm.h>
@@ -33,6 +34,7 @@
 #include <linux/preempt.h>
 #include <linux/hugetlb.h>
 
+#include <asm/acpi.h>
 #include <asm/bug.h>
 #include <asm/cmpxchg.h>
 #include <asm/cpufeature.h>
@@ -45,8 +47,6 @@
 #include <asm/tlbflush.h>
 #include <asm/traps.h>
 
-#include <acpi/ghes.h>
-
 struct fault_info {
 	int	(*fn)(unsigned long addr, unsigned int esr,
 		      struct pt_regs *regs);
@@ -631,20 +631,11 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 	inf = esr_to_fault_info(esr);
 
 	/*
-	 * Synchronous aborts may interrupt code which had interrupts masked.
-	 * Before calling out into the wider kernel tell the interested
-	 * subsystems.
+	 * Return value ignored as we rely on signal merging.
+	 * Future patches will make this more robust.
 	 */
-	if (IS_ENABLED(CONFIG_ACPI_APEI_SEA)) {
-		if (interrupts_enabled(regs))
-			nmi_enter();
-
-		ghes_notify_sea();
-
-		if (interrupts_enabled(regs))
-			nmi_exit();
-	}
 
+	apei_claim_sea(regs);
 	clear_siginfo(&info);
 	info.si_signo = inf->sig;
 	info.si_errno = 0;
@@ -725,12 +716,6 @@ static const struct fault_info fault_info[] = {
 	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 63"			},
 };
 
-int kvm_handle_guest_sea(phys_addr_t addr, unsigned int esr)
-{
-	return ghes_notify_sea();
-}
-EXPORT_SYMBOL(kvm_handle_guest_sea);
-
 asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
 					 struct pt_regs *regs)
 {