From 3729e0ec59a20825bd4c8c70996b2df63915e1dd Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Tue, 18 May 2021 00:03:55 +1000
Subject: [PATCH] powerpc/powernv: Fix machine check reporting of async store
 errors

References: bsc#1065729
Patch-mainline: v5.14-rc1
Git-commit: 3729e0ec59a20825bd4c8c70996b2df63915e1dd

POWER9 and POWER10 asynchronous machine checks due to stores have their
cause reported in SRR1 but SRR1[42] is set, which in other cases
indicates DSISR cause.

Check for these cases and clear SRR1[42], so the cause matching uses
the i-side (SRR1) table.

Fixes: 7b9f71f974a1 ("powerpc/64s: POWER9 machine check handler")
Fixes: 201220bb0e8c ("powerpc/powernv: Machine check handler for POWER10")
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210517140355.2325406-1-npiggin@gmail.com
Acked-by: Michal Suchanek <msuchanek@suse.de>
---
 arch/powerpc/kernel/mce_power.c | 48 +++++++++++++++++++++++++++------
 1 file changed, 40 insertions(+), 8 deletions(-)

diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -481,11 +481,10 @@ static int mce_find_instr_ea_and_phys(struct pt_regs *regs, uint64_t *addr,
   MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
 { 0, false, 0, 0, 0, 0 } };
 
-static int mce_handle_ierror(struct pt_regs *regs,
+static int mce_handle_ierror(struct pt_regs *regs, unsigned long srr1,
 		const struct mce_ierror_table table[],
 		struct mce_error_info *mce_err, uint64_t *addr)
 {
-	uint64_t srr1 = regs->msr;
 	int handled = 0;
 	int i;
 
@@ -695,18 +694,18 @@ static long mce_handle_ue_error(struct pt_regs *regs,
 }
 
 static long mce_handle_error(struct pt_regs *regs,
+		unsigned long srr1,
 		const struct mce_derror_table dtable[],
 		const struct mce_ierror_table itable[])
 {
 	struct mce_error_info mce_err = { 0 };
 	uint64_t addr;
-	uint64_t srr1 = regs->msr;
 	long handled;
 
 	if (SRR1_MC_LOADSTORE(srr1))
 		handled = mce_handle_derror(regs, dtable, &mce_err, &addr);
 	else
-		handled = mce_handle_ierror(regs, itable, &mce_err, &addr);
+		handled = mce_handle_ierror(regs, srr1, itable, &mce_err, &addr);
 
 	if (!handled && mce_err.error_type == MCE_ERROR_TYPE_UE)
 		handled = mce_handle_ue_error(regs);
@@ -723,16 +722,20 @@ long __machine_check_early_realmode_p7(struct pt_regs *regs)
 	/* P7 DD1 leaves top bits of DSISR undefined */
 	regs->dsisr &= 0x0000ffff;
 
-	return mce_handle_error(regs, mce_p7_derror_table, mce_p7_ierror_table);
+	return mce_handle_error(regs, regs->msr,
+			mce_p7_derror_table, mce_p7_ierror_table);
 }
 
 long __machine_check_early_realmode_p8(struct pt_regs *regs)
 {
-	return mce_handle_error(regs, mce_p8_derror_table, mce_p8_ierror_table);
+	return mce_handle_error(regs, regs->msr,
+			mce_p8_derror_table, mce_p8_ierror_table);
 }
 
 long __machine_check_early_realmode_p9(struct pt_regs *regs)
 {
+	unsigned long srr1 = regs->msr;
+
 	/*
 	 * On POWER9 DD2.1 and below, it's possible to get a machine check
 	 * caused by a paste instruction where only DSISR bit 25 is set. This
@@ -746,5 +749,19 @@ long __machine_check_early_realmode_p9(struct pt_regs *regs)
 	if (SRR1_MC_LOADSTORE(regs->msr) && regs->dsisr == 0x02000000)
 		return 1;
 
-	return mce_handle_error(regs, mce_p9_derror_table, mce_p9_ierror_table);
+	/*
+	 * Async machine check due to bad real address from store or foreign
+	 * link time out comes with the load/store bit (PPC bit 42) set in
+	 * SRR1, but the cause comes in SRR1 not DSISR. Clear bit 42 so we're
+	 * directed to the ierror table so it will find the cause (which
+	 * describes it correctly as a store error).
+	 */
+	if (SRR1_MC_LOADSTORE(srr1) &&
+			((srr1 & 0x081c0000) == 0x08140000 ||
+			 (srr1 & 0x081c0000) == 0x08180000)) {
+		srr1 &= ~PPC_BIT(42);
+	}
+
+	return mce_handle_error(regs, srr1,
+			mce_p9_derror_table, mce_p9_ierror_table);
 }