powerpc/book3s: Recover from MC in sapphire on SCOM read via MMIO.

Detect and recover from machine check when inside opal on a special
scom load instructions. On specific SCOM read via MMIO we may get a machine
check exception with SRR0 pointing inside opal. To recover from MC
in this scenario, get a recovery instruction address and return to it from
MC.

OPAL will export the machine check recoverable ranges through
device tree node mcheck-recoverable-ranges under ibm,opal:

# hexdump /proc/device-tree/ibm,opal/mcheck-recoverable-ranges
0000000 0000 0000 3000 2804 0000 000c 0000 0000
0000010 3000 2814 0000 0000 3000 27f0 0000 000c
0000020 0000 0000 3000 2814 xxxx xxxx xxxx xxxx
0000030 llll llll yyyy yyyy yyyy yyyy
...
...
#

where:
	xxxx xxxx xxxx xxxx = Starting instruction address
	llll llll           = Length of the address range.
	yyyy yyyy yyyy yyyy = recovery address

Each recoverable address range entry is (start address, len,
recovery address), 2 cells each for start and recovery address, 1 cell for
len, totalling 5 cells per entry. During kernel boot time, build up the
recovery table with the list of recovery ranges from device-tree node which
will be used during machine check exception to recover from MMIO SCOM UE.

Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

1 files changed, 33 insertions, 4 deletions

diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index 27c93f41166f..aa9aff3d6ad3 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -26,6 +26,7 @@
 #include <linux/ptrace.h>
 #include <asm/mmu.h>
 #include <asm/mce.h>
+#include <asm/machdep.h>
 
 /* flush SLBs and reload */
 static void flush_and_reload_slb(void)
@@ -197,13 +198,32 @@ static void mce_get_derror_p7(struct mce_error_info *mce_err, uint64_t dsisr)
 	}
 }
 
+static long mce_handle_ue_error(struct pt_regs *regs)
+{
+	long handled = 0;
+
+	/*
+	 * On specific SCOM read via MMIO we may get a machine check
+	 * exception with SRR0 pointing inside opal. If that is the
+	 * case OPAL may have recovery address to re-read SCOM data in
+	 * different way and hence we can recover from this MC.
+	 */
+
+	if (ppc_md.mce_check_early_recovery) {
+		if (ppc_md.mce_check_early_recovery(regs))
+			handled = 1;
+	}
+	return handled;
+}
+
 long __machine_check_early_realmode_p7(struct pt_regs *regs)
 {
-	uint64_t srr1, addr;
+	uint64_t srr1, nip, addr;
 	long handled = 1;
 	struct mce_error_info mce_error_info = { 0 };
 
 	srr1 = regs->msr;
+	nip = regs->nip;
 
 	/*
 	 * Handle memory errors depending whether this was a load/store or
@@ -221,7 +241,11 @@ long __machine_check_early_realmode_p7(struct pt_regs *regs)
 		addr = regs->nip;
 	}
 
-	save_mce_event(regs, handled, &mce_error_info, addr);
+	/* Handle UE error. */
+	if (mce_error_info.error_type == MCE_ERROR_TYPE_UE)
+		handled = mce_handle_ue_error(regs);
+
+	save_mce_event(regs, handled, &mce_error_info, nip, addr);
 	return handled;
 }
 
@@ -263,11 +287,12 @@ static long mce_handle_derror_p8(uint64_t dsisr)
 
 long __machine_check_early_realmode_p8(struct pt_regs *regs)
 {
-	uint64_t srr1, addr;
+	uint64_t srr1, nip, addr;
 	long handled = 1;
 	struct mce_error_info mce_error_info = { 0 };
 
 	srr1 = regs->msr;
+	nip = regs->nip;
 
 	if (P7_SRR1_MC_LOADSTORE(srr1)) {
 		handled = mce_handle_derror_p8(regs->dsisr);
@@ -279,6 +304,10 @@ long __machine_check_early_realmode_p8(struct pt_regs *regs)
 		addr = regs->nip;
 	}
 
-	save_mce_event(regs, handled, &mce_error_info, addr);
+	/* Handle UE error. */
+	if (mce_error_info.error_type == MCE_ERROR_TYPE_UE)
+		handled = mce_handle_ue_error(regs);
+
+	save_mce_event(regs, handled, &mce_error_info, nip, addr);
 	return handled;
 }