[v5 5/6] powerpc/mce: Handle UE event for memcpy_mcsafe
From: Santosh Sivaraj
Date: Tue Jul 09 2019 - 08:16:15 EST
If we take a UE on one of the instructions with a fixup entry, set nip
to continue execution at the fixup entry. Stop processing the event
further or print it.
Based-on-patch-by: Reza Arbab <arbab@xxxxxxxxxxxxx>
Cc: Reza Arbab <arbab@xxxxxxxxxxxxx>
Cc: Mahesh Salgaonkar <mahesh@xxxxxxxxxxxxx>
Signed-off-by: Santosh Sivaraj <santosh@xxxxxxxxxx>
---
arch/powerpc/include/asm/mce.h | 4 +++-
arch/powerpc/kernel/mce.c | 12 +++++++++++-
arch/powerpc/kernel/mce_power.c | 15 +++++++++++++--
3 files changed, 27 insertions(+), 4 deletions(-)
Nick, I didn't add has_fixup_handler in mce_event structure; if we do so we wil
have to access the mce_event from ue_handler code also. That is because Mahesh
did not want mce_event to be accessed outside of save_mce_event, get_mce_event
and remove_mce_event; that is why I added ignore_event in mce_err also.
I have added the comment you mentioned in your reply.
diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index 94888a7025b3..f74257eb013b 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -122,7 +122,8 @@ struct machine_check_event {
enum MCE_UeErrorType ue_error_type:8;
u8 effective_address_provided;
u8 physical_address_provided;
- u8 reserved_1[5];
+ u8 ignore_event;
+ u8 reserved_1[4];
u64 effective_address;
u64 physical_address;
u8 reserved_2[8];
@@ -193,6 +194,7 @@ struct mce_error_info {
enum MCE_Initiator initiator:8;
enum MCE_ErrorClass error_class:8;
bool sync_error;
+ bool ignore_event;
};
#define MAX_MC_EVT 100
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index e78c4f18ea0a..092e6bbc603f 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -144,7 +144,9 @@ void save_mce_event(struct pt_regs *regs, long handled,
if (phys_addr != ULONG_MAX) {
mce->u.ue_error.physical_address_provided = true;
mce->u.ue_error.physical_address = phys_addr;
- machine_check_ue_event(mce);
+ mce->u.ue_error.ignore_event = mce_err->ignore_event;
+ if (!mce->u.ue_error.ignore_event)
+ machine_check_ue_event(mce);
}
}
return;
@@ -230,6 +232,14 @@ void machine_check_queue_event(void)
if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
return;
+ /*
+ * Don't report this machine check because the caller has a asked us
+ * to ignore the event, it has a fixup handler which will do the
+ * appropriate error handling and reporting.
+ */
+ if (evt.error_type == MCE_ERROR_TYPE_UE && evt.u.ue_error.ignore_event)
+ return;
+
index = __this_cpu_inc_return(mce_queue_count) - 1;
/* If queue is full, just return for now. */
if (index >= MAX_MC_EVT) {
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index 04666c0b40a8..582a22b1acfb 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -11,6 +11,7 @@
#include <linux/types.h>
#include <linux/ptrace.h>
+#include <linux/extable.h>
#include <asm/mmu.h>
#include <asm/mce.h>
#include <asm/machdep.h>
@@ -18,6 +19,7 @@
#include <asm/pte-walk.h>
#include <asm/sstep.h>
#include <asm/exception-64s.h>
+#include <asm/extable.h>
/*
* Convert an address related to an mm to a PFN. NOTE: we are in real
@@ -565,9 +567,18 @@ static int mce_handle_derror(struct pt_regs *regs,
return 0;
}
-static long mce_handle_ue_error(struct pt_regs *regs)
+static long mce_handle_ue_error(struct pt_regs *regs,
+ struct mce_error_info *mce_err)
{
long handled = 0;
+ const struct exception_table_entry *entry;
+
+ entry = search_kernel_exception_table(regs->nip);
+ if (entry) {
+ mce_err->ignore_event = true;
+ regs->nip = extable_fixup(entry);
+ return 1;
+ }
/*
* On specific SCOM read via MMIO we may get a machine check
@@ -600,7 +611,7 @@ static long mce_handle_error(struct pt_regs *regs,
&phys_addr);
if (!handled && mce_err.error_type == MCE_ERROR_TYPE_UE)
- handled = mce_handle_ue_error(regs);
+ handled = mce_handle_ue_error(regs, &mce_err);
save_mce_event(regs, handled, &mce_err, regs->nip, addr, phys_addr);
--
2.20.1