* [PATCH 1/9] powerpc/64s: machine check print NIP
2017-02-20 19:44 [PATCH 0/9] MCE handler for POWER9 Nicholas Piggin
@ 2017-02-20 19:44 ` Nicholas Piggin
2017-02-20 19:44 ` [PATCH 2/9] powerpc/64s: allow machine check handler to set severity and initiator Nicholas Piggin
` (7 subsequent siblings)
8 siblings, 0 replies; 10+ messages in thread
From: Nicholas Piggin @ 2017-02-20 19:44 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin, Michael Ellerman, Mahesh Salgaonkar
Print the faulting address of the machine check that may help
with debugging. The effective address reported can be a target
memory address rather than an instruction address.
Fix up a dangling bracket while here.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/mce.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index c6923ff45131..335f8a53f154 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -268,7 +268,8 @@ void machine_check_print_event_info(struct machine_check_event *evt)
printk("%s%s Machine check interrupt [%s]\n", level, sevstr,
evt->disposition == MCE_DISPOSITION_RECOVERED ?
- "Recovered" : "[Not recovered");
+ "Recovered" : "Not recovered");
+ printk("%s NIP: %016llx\n", level, evt->srr0);
printk("%s Initiator: %s\n", level,
evt->initiator == MCE_INITIATOR_CPU ? "CPU" : "Unknown");
switch (evt->error_type) {
--
2.11.0
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH 2/9] powerpc/64s: allow machine check handler to set severity and initiator
2017-02-20 19:44 [PATCH 0/9] MCE handler for POWER9 Nicholas Piggin
2017-02-20 19:44 ` [PATCH 1/9] powerpc/64s: machine check print NIP Nicholas Piggin
@ 2017-02-20 19:44 ` Nicholas Piggin
2017-02-20 19:44 ` [PATCH 3/9] powerpc/64s: clean up machine check recovery flushing Nicholas Piggin
` (6 subsequent siblings)
8 siblings, 0 replies; 10+ messages in thread
From: Nicholas Piggin @ 2017-02-20 19:44 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin, Michael Ellerman, Mahesh Salgaonkar
Currently these just hardcoded.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/mce.h | 3 ++-
arch/powerpc/kernel/mce.c | 5 +++--
arch/powerpc/kernel/mce_power.c | 6 ++++++
3 files changed, 11 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index f97d8cb6bdf6..b2a5865ccd87 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -177,7 +177,8 @@ struct mce_error_info {
enum MCE_EratErrorType erat_error_type:8;
enum MCE_TlbErrorType tlb_error_type:8;
} u;
- uint8_t reserved[2];
+ enum MCE_Severity severity:8;
+ enum MCE_Initiator initiator:8;
};
#define MAX_MC_EVT 100
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 335f8a53f154..ce340207ccb3 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -90,13 +90,14 @@ void save_mce_event(struct pt_regs *regs, long handled,
mce->gpr3 = regs->gpr[3];
mce->in_use = 1;
- mce->initiator = MCE_INITIATOR_CPU;
/* Mark it recovered if we have handled it and MSR(RI=1). */
if (handled && (regs->msr & MSR_RI))
mce->disposition = MCE_DISPOSITION_RECOVERED;
else
mce->disposition = MCE_DISPOSITION_NOT_RECOVERED;
- mce->severity = MCE_SEV_ERROR_SYNC;
+
+ mce->initiator = mce_err->initiator;
+ mce->severity = mce_err->severity;
/*
* Populate the mce error_type and type-specific error_type.
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index 7353991c4ece..c37fc5fdd433 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -281,6 +281,9 @@ long __machine_check_early_realmode_p7(struct pt_regs *regs)
long handled = 1;
struct mce_error_info mce_error_info = { 0 };
+ mce_error_info.severity = MCE_SEV_ERROR_SYNC;
+ mce_error_info.initiator = MCE_INITIATOR_CPU;
+
srr1 = regs->msr;
nip = regs->nip;
@@ -352,6 +355,9 @@ long __machine_check_early_realmode_p8(struct pt_regs *regs)
long handled = 1;
struct mce_error_info mce_error_info = { 0 };
+ mce_error_info.severity = MCE_SEV_ERROR_SYNC;
+ mce_error_info.initiator = MCE_INITIATOR_CPU;
+
srr1 = regs->msr;
nip = regs->nip;
--
2.11.0
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH 3/9] powerpc/64s: clean up machine check recovery flushing
2017-02-20 19:44 [PATCH 0/9] MCE handler for POWER9 Nicholas Piggin
2017-02-20 19:44 ` [PATCH 1/9] powerpc/64s: machine check print NIP Nicholas Piggin
2017-02-20 19:44 ` [PATCH 2/9] powerpc/64s: allow machine check handler to set severity and initiator Nicholas Piggin
@ 2017-02-20 19:44 ` Nicholas Piggin
2017-02-20 19:44 ` [PATCH 4/9] powerpc/64s: cope with non-synchronous machine checks Nicholas Piggin
` (5 subsequent siblings)
8 siblings, 0 replies; 10+ messages in thread
From: Nicholas Piggin @ 2017-02-20 19:44 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin, Michael Ellerman, Mahesh Salgaonkar
Put the ifdefs into a flush handler call, and have callers ask for
particular type of flushes. Also add an ERAT flush type (although
existing ERAT flushing goes to the SLB flush path).
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/mce_power.c | 124 +++++++++++++++++++---------------------
1 file changed, 59 insertions(+), 65 deletions(-)
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index c37fc5fdd433..07af815b5ba1 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -114,83 +114,74 @@ static void flush_and_reload_slb(void)
asm volatile("slbmte %0,%1" : : "r" (rs), "r" (rb));
}
}
-#endif
-static long mce_handle_derror(uint64_t dsisr, uint64_t slb_error_bits)
+static void flush_erat(void)
{
- long handled = 1;
+ asm volatile(PPC_INVALIDATE_ERAT : : :"memory");
+}
+#endif
- /*
- * flush and reload SLBs for SLB errors and flush TLBs for TLB errors.
- * reset the error bits whenever we handle them so that at the end
- * we can check whether we handled all of them or not.
- * */
+#define MCE_FLUSH_SLB 1
+#define MCE_FLUSH_TLB 2
+#define MCE_FLUSH_ERAT 3
+
+static int mce_flush(int what)
+{
#ifdef CONFIG_PPC_STD_MMU_64
- if (dsisr & slb_error_bits) {
+ if (what == MCE_FLUSH_SLB) {
flush_and_reload_slb();
- /* reset error bits */
- dsisr &= ~(slb_error_bits);
+ return 1;
}
- if (dsisr & P7_DSISR_MC_TLB_MULTIHIT_MFTLB) {
- if (cur_cpu_spec && cur_cpu_spec->flush_tlb)
- cur_cpu_spec->flush_tlb(TLB_INVAL_SCOPE_GLOBAL);
- /* reset error bits */
- dsisr &= ~P7_DSISR_MC_TLB_MULTIHIT_MFTLB;
+ if (what == MCE_FLUSH_ERAT) {
+ flush_erat();
+ return 1;
}
#endif
- /* Any other errors we don't understand? */
- if (dsisr & 0xffffffffUL)
- handled = 0;
+ if (what == MCE_FLUSH_TLB) {
+ if (cur_cpu_spec && cur_cpu_spec->flush_tlb) {
+ cur_cpu_spec->flush_tlb(TLB_INVAL_SCOPE_GLOBAL);
+ return 1;
+ }
+ }
- return handled;
+ return 0;
}
-static long mce_handle_derror_p7(uint64_t dsisr)
+static int mce_handle_flush_derrors(uint64_t dsisr, uint64_t slb, uint64_t tlb, uint64_t erat)
{
- return mce_handle_derror(dsisr, P7_DSISR_MC_SLB_ERRORS);
+ if ((dsisr & slb) && mce_flush(MCE_FLUSH_SLB))
+ dsisr &= ~slb;
+ if ((dsisr & erat) && mce_flush(MCE_FLUSH_ERAT))
+ dsisr &= ~erat;
+ if ((dsisr & tlb) && mce_flush(MCE_FLUSH_TLB))
+ dsisr &= ~tlb;
+ /* Any other errors we don't understand? */
+ if (dsisr)
+ return 0;
+ return 1;
}
-static long mce_handle_common_ierror(uint64_t srr1)
+static long mce_handle_derror_p7(uint64_t dsisr)
{
- long handled = 0;
+ return mce_handle_flush_derrors(dsisr,
+ P7_DSISR_MC_SLB_ERRORS,
+ P7_DSISR_MC_TLB_MULTIHIT_MFTLB,
+ 0);
+}
+static long mce_handle_ierror_p7(uint64_t srr1)
+{
switch (P7_SRR1_MC_IFETCH(srr1)) {
- case 0:
- break;
-#ifdef CONFIG_PPC_STD_MMU_64
case P7_SRR1_MC_IFETCH_SLB_PARITY:
case P7_SRR1_MC_IFETCH_SLB_MULTIHIT:
- /* flush and reload SLBs for SLB errors. */
- flush_and_reload_slb();
- handled = 1;
- break;
+ case P7_SRR1_MC_IFETCH_SLB_BOTH:
+ return mce_flush(MCE_FLUSH_SLB);
+
case P7_SRR1_MC_IFETCH_TLB_MULTIHIT:
- if (cur_cpu_spec && cur_cpu_spec->flush_tlb) {
- cur_cpu_spec->flush_tlb(TLB_INVAL_SCOPE_GLOBAL);
- handled = 1;
- }
- break;
-#endif
+ return mce_flush(MCE_FLUSH_TLB);
default:
- break;
- }
-
- return handled;
-}
-
-static long mce_handle_ierror_p7(uint64_t srr1)
-{
- long handled = 0;
-
- handled = mce_handle_common_ierror(srr1);
-
-#ifdef CONFIG_PPC_STD_MMU_64
- if (P7_SRR1_MC_IFETCH(srr1) == P7_SRR1_MC_IFETCH_SLB_BOTH) {
- flush_and_reload_slb();
- handled = 1;
+ return 0;
}
-#endif
- return handled;
}
static void mce_get_common_ierror(struct mce_error_info *mce_err, uint64_t srr1)
@@ -331,22 +322,25 @@ static void mce_get_derror_p8(struct mce_error_info *mce_err, uint64_t dsisr)
static long mce_handle_ierror_p8(uint64_t srr1)
{
- long handled = 0;
-
- handled = mce_handle_common_ierror(srr1);
+ switch (P7_SRR1_MC_IFETCH(srr1)) {
+ case P7_SRR1_MC_IFETCH_SLB_PARITY:
+ case P7_SRR1_MC_IFETCH_SLB_MULTIHIT:
+ case P8_SRR1_MC_IFETCH_ERAT_MULTIHIT:
+ return mce_flush(MCE_FLUSH_SLB);
-#ifdef CONFIG_PPC_STD_MMU_64
- if (P7_SRR1_MC_IFETCH(srr1) == P8_SRR1_MC_IFETCH_ERAT_MULTIHIT) {
- flush_and_reload_slb();
- handled = 1;
+ case P7_SRR1_MC_IFETCH_TLB_MULTIHIT:
+ return mce_flush(MCE_FLUSH_TLB);
+ default:
+ return 0;
}
-#endif
- return handled;
}
static long mce_handle_derror_p8(uint64_t dsisr)
{
- return mce_handle_derror(dsisr, P8_DSISR_MC_SLB_ERRORS);
+ return mce_handle_flush_derrors(dsisr,
+ P8_DSISR_MC_SLB_ERRORS,
+ P7_DSISR_MC_TLB_MULTIHIT_MFTLB,
+ 0);
}
long __machine_check_early_realmode_p8(struct pt_regs *regs)
--
2.11.0
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH 4/9] powerpc/64s: cope with non-synchronous machine checks
2017-02-20 19:44 [PATCH 0/9] MCE handler for POWER9 Nicholas Piggin
` (2 preceding siblings ...)
2017-02-20 19:44 ` [PATCH 3/9] powerpc/64s: clean up machine check recovery flushing Nicholas Piggin
@ 2017-02-20 19:44 ` Nicholas Piggin
2017-02-20 19:44 ` [PATCH 5/9] powerpc/64s: POWER9 machine check handler Nicholas Piggin
` (4 subsequent siblings)
8 siblings, 0 replies; 10+ messages in thread
From: Nicholas Piggin @ 2017-02-20 19:44 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin, Michael Ellerman, Mahesh Salgaonkar
Asynchronous machine checks don't correspond to the instruction or
even task that is currently running. Therefore only synchronous
machine checks should attempt to kill the currently running task
to recover.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/platforms/powernv/opal.c | 20 +++++---------------
1 file changed, 5 insertions(+), 15 deletions(-)
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 282293572dc8..f47430b417d2 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -395,7 +395,6 @@ static int opal_recover_mce(struct pt_regs *regs,
struct machine_check_event *evt)
{
int recovered = 0;
- uint64_t ea = get_mce_fault_addr(evt);
if (!(regs->msr & MSR_RI)) {
/* If MSR_RI isn't set, we cannot recover */
@@ -404,26 +403,17 @@ static int opal_recover_mce(struct pt_regs *regs,
} else if (evt->disposition == MCE_DISPOSITION_RECOVERED) {
/* Platform corrected itself */
recovered = 1;
- } else if (ea && !is_kernel_addr(ea)) {
+ } else if (evt->severity == MCE_SEV_FATAL) {
+ /* Async or otherwise fatal machine check */
+ pr_err("Machine check interrupt unrecoverable\n");
+ recovered = 0;
+ } else if (user_mode(regs) && !is_global_init(current)) {
/*
- * Faulting address is not in kernel text. We should be fine.
- * We need to find which process uses this address.
* For now, kill the task if we have received exception when
* in userspace.
*
* TODO: Queue up this address for hwpoisioning later.
*/
- if (user_mode(regs) && !is_global_init(current)) {
- _exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
- recovered = 1;
- } else
- recovered = 0;
- } else if (user_mode(regs) && !is_global_init(current) &&
- evt->severity == MCE_SEV_ERROR_SYNC) {
- /*
- * If we have received a synchronous error when in userspace
- * kill the task.
- */
_exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
recovered = 1;
}
--
2.11.0
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH 5/9] powerpc/64s: POWER9 machine check handler
2017-02-20 19:44 [PATCH 0/9] MCE handler for POWER9 Nicholas Piggin
` (3 preceding siblings ...)
2017-02-20 19:44 ` [PATCH 4/9] powerpc/64s: cope with non-synchronous machine checks Nicholas Piggin
@ 2017-02-20 19:44 ` Nicholas Piggin
2017-02-20 19:44 ` [PATCH 6/9] powerpc/64s: move POWER machine check defines into mce_power.c Nicholas Piggin
` (3 subsequent siblings)
8 siblings, 0 replies; 10+ messages in thread
From: Nicholas Piggin @ 2017-02-20 19:44 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin, Michael Ellerman, Mahesh Salgaonkar
Add POWER9 machine check handler. There are several new types of errors
and also asynchonous machine checks added.
This doesn't reuse the P7/8 defines and functions because it becomes too
complex. Instead, future changes will rework all to use a table driven
approach.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/bitops.h | 4 +
arch/powerpc/include/asm/mce.h | 105 +++++++++++++++++++++
arch/powerpc/kernel/cputable.c | 3 +
arch/powerpc/kernel/mce.c | 83 ++++++++++++++++
arch/powerpc/kernel/mce_power.c | 194 ++++++++++++++++++++++++++++++++++++++
5 files changed, 389 insertions(+)
diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h
index 59abc620f8e8..5f057c74bf21 100644
--- a/arch/powerpc/include/asm/bitops.h
+++ b/arch/powerpc/include/asm/bitops.h
@@ -51,6 +51,10 @@
#define PPC_BIT(bit) (1UL << PPC_BITLSHIFT(bit))
#define PPC_BITMASK(bs, be) ((PPC_BIT(bs) - PPC_BIT(be)) | PPC_BIT(bs))
+/* Put a PPC bit into a "normal" bit position */
+#define PPC_BITEXTRACT(bits, ppc_bit, dst_bit) \
+ ((((bits) >> PPC_BITLSHIFT(ppc_bit)) & 1) << (dst_bit))
+
#include <asm/barrier.h>
/* Macro for generating the ***_bits() functions */
diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index b2a5865ccd87..ed62efe01e49 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -66,6 +66,55 @@
#define P8_DSISR_MC_SLB_ERRORS (P7_DSISR_MC_SLB_ERRORS | \
P8_DSISR_MC_ERAT_MULTIHIT_SEC)
+
+/*
+ * Machine Check bits on power9
+ */
+#define P9_SRR1_MC_LOADSTORE(srr1) (((srr1) >> PPC_BITLSHIFT(42)) & 1)
+
+#define P9_SRR1_MC_IFETCH(srr1) ( \
+ PPC_BITEXTRACT(srr1, 45, 0) | \
+ PPC_BITEXTRACT(srr1, 44, 1) | \
+ PPC_BITEXTRACT(srr1, 43, 2) | \
+ PPC_BITEXTRACT(srr1, 36, 3) )
+
+/* 0 is reserved */
+#define P9_SRR1_MC_IFETCH_UE 1
+#define P9_SRR1_MC_IFETCH_SLB_PARITY 2
+#define P9_SRR1_MC_IFETCH_SLB_MULTIHIT 3
+#define P9_SRR1_MC_IFETCH_ERAT_MULTIHIT 4
+#define P9_SRR1_MC_IFETCH_TLB_MULTIHIT 5
+#define P9_SRR1_MC_IFETCH_UE_TLB_RELOAD 6
+/* 7 is reserved */
+#define P9_SRR1_MC_IFETCH_LINK_TIMEOUT 8
+#define P9_SRR1_MC_IFETCH_LINK_TABLEWALK_TIMEOUT 9
+/* 10 ? */
+#define P9_SRR1_MC_IFETCH_RA 11
+#define P9_SRR1_MC_IFETCH_RA_TABLEWALK 12
+#define P9_SRR1_MC_IFETCH_RA_ASYNC_STORE 13
+#define P9_SRR1_MC_IFETCH_LINK_ASYNC_STORE_TIMEOUT 14
+#define P9_SRR1_MC_IFETCH_RA_TABLEWALK_FOREIGN 15
+
+/* DSISR bits for machine check (On Power9) */
+#define P9_DSISR_MC_UE (PPC_BIT(48))
+#define P9_DSISR_MC_UE_TABLEWALK (PPC_BIT(49))
+#define P9_DSISR_MC_LINK_LOAD_TIMEOUT (PPC_BIT(50))
+#define P9_DSISR_MC_LINK_TABLEWALK_TIMEOUT (PPC_BIT(51))
+#define P9_DSISR_MC_ERAT_MULTIHIT (PPC_BIT(52))
+#define P9_DSISR_MC_TLB_MULTIHIT_MFTLB (PPC_BIT(53))
+#define P9_DSISR_MC_USER_TLBIE (PPC_BIT(54))
+#define P9_DSISR_MC_SLB_PARITY_MFSLB (PPC_BIT(55))
+#define P9_DSISR_MC_SLB_MULTIHIT_MFSLB (PPC_BIT(56))
+#define P9_DSISR_MC_RA_LOAD (PPC_BIT(57))
+#define P9_DSISR_MC_RA_TABLEWALK (PPC_BIT(58))
+#define P9_DSISR_MC_RA_TABLEWALK_FOREIGN (PPC_BIT(59))
+#define P9_DSISR_MC_RA_FOREIGN (PPC_BIT(60))
+
+/* SLB error bits */
+#define P9_DSISR_MC_SLB_ERRORS (P9_DSISR_MC_ERAT_MULTIHIT | \
+ P9_DSISR_MC_SLB_PARITY_MFSLB | \
+ P9_DSISR_MC_SLB_MULTIHIT_MFSLB)
+
enum MCE_Version {
MCE_V1 = 1,
};
@@ -93,6 +142,9 @@ enum MCE_ErrorType {
MCE_ERROR_TYPE_SLB = 2,
MCE_ERROR_TYPE_ERAT = 3,
MCE_ERROR_TYPE_TLB = 4,
+ MCE_ERROR_TYPE_USER = 5,
+ MCE_ERROR_TYPE_RA = 6,
+ MCE_ERROR_TYPE_LINK = 7,
};
enum MCE_UeErrorType {
@@ -121,6 +173,32 @@ enum MCE_TlbErrorType {
MCE_TLB_ERROR_MULTIHIT = 2,
};
+enum MCE_UserErrorType {
+ MCE_USER_ERROR_INDETERMINATE = 0,
+ MCE_USER_ERROR_TLBIE = 1,
+};
+
+enum MCE_RaErrorType {
+ MCE_RA_ERROR_INDETERMINATE = 0,
+ MCE_RA_ERROR_IFETCH = 1,
+ MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH = 2,
+ MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH_FOREIGN = 3,
+ MCE_RA_ERROR_LOAD = 4,
+ MCE_RA_ERROR_STORE = 5,
+ MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE = 6,
+ MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE_FOREIGN = 7,
+ MCE_RA_ERROR_LOAD_STORE_FOREIGN = 8,
+};
+
+enum MCE_LinkErrorType {
+ MCE_LINK_ERROR_INDETERMINATE = 0,
+ MCE_LINK_ERROR_IFETCH_TIMEOUT = 1,
+ MCE_LINK_ERROR_PAGE_TABLE_WALK_IFETCH_TIMEOUT = 2,
+ MCE_LINK_ERROR_LOAD_TIMEOUT = 3,
+ MCE_LINK_ERROR_STORE_TIMEOUT = 4,
+ MCE_LINK_ERROR_PAGE_TABLE_WALK_LOAD_STORE_TIMEOUT = 5,
+};
+
struct machine_check_event {
enum MCE_Version version:8; /* 0x00 */
uint8_t in_use; /* 0x01 */
@@ -166,6 +244,30 @@ struct machine_check_event {
uint64_t effective_address;
uint8_t reserved_2[16];
} tlb_error;
+
+ struct {
+ enum MCE_UserErrorType user_error_type:8;
+ uint8_t effective_address_provided;
+ uint8_t reserved_1[6];
+ uint64_t effective_address;
+ uint8_t reserved_2[16];
+ } user_error;
+
+ struct {
+ enum MCE_RaErrorType ra_error_type:8;
+ uint8_t effective_address_provided;
+ uint8_t reserved_1[6];
+ uint64_t effective_address;
+ uint8_t reserved_2[16];
+ } ra_error;
+
+ struct {
+ enum MCE_LinkErrorType link_error_type:8;
+ uint8_t effective_address_provided;
+ uint8_t reserved_1[6];
+ uint64_t effective_address;
+ uint8_t reserved_2[16];
+ } link_error;
} u;
};
@@ -176,6 +278,9 @@ struct mce_error_info {
enum MCE_SlbErrorType slb_error_type:8;
enum MCE_EratErrorType erat_error_type:8;
enum MCE_TlbErrorType tlb_error_type:8;
+ enum MCE_UserErrorType user_error_type:8;
+ enum MCE_RaErrorType ra_error_type:8;
+ enum MCE_LinkErrorType link_error_type:8;
} u;
enum MCE_Severity severity:8;
enum MCE_Initiator initiator:8;
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 6a82ef039c50..5feefdacaea8 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -77,6 +77,7 @@ extern void __flush_tlb_power8(unsigned int action);
extern void __flush_tlb_power9(unsigned int action);
extern long __machine_check_early_realmode_p7(struct pt_regs *regs);
extern long __machine_check_early_realmode_p8(struct pt_regs *regs);
+extern long __machine_check_early_realmode_p9(struct pt_regs *regs);
#endif /* CONFIG_PPC64 */
#if defined(CONFIG_E500)
extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec);
@@ -523,6 +524,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
.cpu_setup = __setup_cpu_power9,
.cpu_restore = __restore_cpu_power9,
.flush_tlb = __flush_tlb_power9,
+ .machine_check_early = __machine_check_early_realmode_p9,
.platform = "power9",
},
{ /* Power9 */
@@ -542,6 +544,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
.cpu_setup = __setup_cpu_power9,
.cpu_restore = __restore_cpu_power9,
.flush_tlb = __flush_tlb_power9,
+ .machine_check_early = __machine_check_early_realmode_p9,
.platform = "power9",
},
{ /* Cell Broadband Engine */
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index ce340207ccb3..399aeafb7dd4 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -58,6 +58,15 @@ static void mce_set_error_info(struct machine_check_event *mce,
case MCE_ERROR_TYPE_TLB:
mce->u.tlb_error.tlb_error_type = mce_err->u.tlb_error_type;
break;
+ case MCE_ERROR_TYPE_USER:
+ mce->u.user_error.user_error_type = mce_err->u.user_error_type;
+ break;
+ case MCE_ERROR_TYPE_RA:
+ mce->u.ra_error.ra_error_type = mce_err->u.ra_error_type;
+ break;
+ case MCE_ERROR_TYPE_LINK:
+ mce->u.link_error.link_error_type = mce_err->u.link_error_type;
+ break;
case MCE_ERROR_TYPE_UNKNOWN:
default:
break;
@@ -116,6 +125,15 @@ void save_mce_event(struct pt_regs *regs, long handled,
} else if (mce->error_type == MCE_ERROR_TYPE_ERAT) {
mce->u.erat_error.effective_address_provided = true;
mce->u.erat_error.effective_address = addr;
+ } else if (mce->error_type == MCE_ERROR_TYPE_USER) {
+ mce->u.user_error.effective_address_provided = true;
+ mce->u.user_error.effective_address = addr;
+ } else if (mce->error_type == MCE_ERROR_TYPE_RA) {
+ mce->u.ra_error.effective_address_provided = true;
+ mce->u.ra_error.effective_address = addr;
+ } else if (mce->error_type == MCE_ERROR_TYPE_LINK) {
+ mce->u.link_error.effective_address_provided = true;
+ mce->u.link_error.effective_address = addr;
} else if (mce->error_type == MCE_ERROR_TYPE_UE) {
mce->u.ue_error.effective_address_provided = true;
mce->u.ue_error.effective_address = addr;
@@ -240,6 +258,29 @@ void machine_check_print_event_info(struct machine_check_event *evt)
"Parity",
"Multihit",
};
+ static const char *mc_user_types[] = {
+ "Indeterminate",
+ "tlbie(l) invalid",
+ };
+ static const char *mc_ra_types[] = {
+ "Indeterminate",
+ "Instruction fetch (bad)",
+ "Page table walk ifetch (bad)",
+ "Page table walk ifetch (foreign)",
+ "Load (bad)",
+ "Store (bad)",
+ "Page table walk Load/Store (bad)",
+ "Page table walk Load/Store (foreign)",
+ "Load/Store (foreign)",
+ };
+ static const char *mc_link_types[] = {
+ "Indeterminate",
+ "Instruction fetch (timeout)",
+ "Page table walk ifetch (timeout)",
+ "Load (timeout)",
+ "Store (timeout)",
+ "Page table walk Load/Store (timeout)",
+ };
/* Print things out */
if (evt->version != MCE_V1) {
@@ -317,6 +358,36 @@ void machine_check_print_event_info(struct machine_check_event *evt)
printk("%s Effective address: %016llx\n",
level, evt->u.tlb_error.effective_address);
break;
+ case MCE_ERROR_TYPE_USER:
+ subtype = evt->u.user_error.user_error_type <
+ ARRAY_SIZE(mc_user_types) ?
+ mc_user_types[evt->u.user_error.user_error_type]
+ : "Unknown";
+ printk("%s Error type: User [%s]\n", level, subtype);
+ if (evt->u.user_error.effective_address_provided)
+ printk("%s Effective address: %016llx\n",
+ level, evt->u.user_error.effective_address);
+ break;
+ case MCE_ERROR_TYPE_RA:
+ subtype = evt->u.ra_error.ra_error_type <
+ ARRAY_SIZE(mc_ra_types) ?
+ mc_ra_types[evt->u.ra_error.ra_error_type]
+ : "Unknown";
+ printk("%s Error type: Real address [%s]\n", level, subtype);
+ if (evt->u.ra_error.effective_address_provided)
+ printk("%s Effective address: %016llx\n",
+ level, evt->u.ra_error.effective_address);
+ break;
+ case MCE_ERROR_TYPE_LINK:
+ subtype = evt->u.link_error.link_error_type <
+ ARRAY_SIZE(mc_link_types) ?
+ mc_link_types[evt->u.link_error.link_error_type]
+ : "Unknown";
+ printk("%s Error type: Link [%s]\n", level, subtype);
+ if (evt->u.link_error.effective_address_provided)
+ printk("%s Effective address: %016llx\n",
+ level, evt->u.link_error.effective_address);
+ break;
default:
case MCE_ERROR_TYPE_UNKNOWN:
printk("%s Error type: Unknown\n", level);
@@ -343,6 +414,18 @@ uint64_t get_mce_fault_addr(struct machine_check_event *evt)
if (evt->u.tlb_error.effective_address_provided)
return evt->u.tlb_error.effective_address;
break;
+ case MCE_ERROR_TYPE_USER:
+ if (evt->u.user_error.effective_address_provided)
+ return evt->u.user_error.effective_address;
+ break;
+ case MCE_ERROR_TYPE_RA:
+ if (evt->u.ra_error.effective_address_provided)
+ return evt->u.ra_error.effective_address;
+ break;
+ case MCE_ERROR_TYPE_LINK:
+ if (evt->u.link_error.effective_address_provided)
+ return evt->u.link_error.effective_address;
+ break;
default:
case MCE_ERROR_TYPE_UNKNOWN:
break;
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index 07af815b5ba1..cd18314b569a 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -372,3 +372,197 @@ long __machine_check_early_realmode_p8(struct pt_regs *regs)
save_mce_event(regs, handled, &mce_error_info, nip, addr);
return handled;
}
+
+static int mce_handle_derror_p9(struct pt_regs *regs)
+{
+ uint64_t dsisr = regs->dsisr;
+
+#if 0
+ /* Could invalidate all tlbs then step over failing tlbie(l)? */
+ if (dsisr & P9_DSISR_MC_USER_TLBIE) {
+ regs->nip += 4;
+ dsisr &= ~P9_DSISR_MC_USER_TLBIE;
+ }
+#endif
+
+ return mce_handle_flush_derrors(dsisr,
+ P9_DSISR_MC_SLB_PARITY_MFSLB |
+ P9_DSISR_MC_SLB_MULTIHIT_MFSLB,
+
+ P9_DSISR_MC_TLB_MULTIHIT_MFTLB,
+
+ P9_DSISR_MC_ERAT_MULTIHIT);
+}
+
+static int mce_handle_ierror_p9(struct pt_regs *regs)
+{
+ uint64_t srr1 = regs->msr;
+
+ switch (P9_SRR1_MC_IFETCH(srr1)) {
+ case P9_SRR1_MC_IFETCH_SLB_PARITY:
+ case P9_SRR1_MC_IFETCH_SLB_MULTIHIT:
+ return mce_flush(MCE_FLUSH_SLB);
+ case P9_SRR1_MC_IFETCH_TLB_MULTIHIT:
+ return mce_flush(MCE_FLUSH_TLB);
+ case P9_SRR1_MC_IFETCH_ERAT_MULTIHIT:
+ return mce_flush(MCE_FLUSH_ERAT);
+ default:
+ return 0;
+ }
+}
+
+static void mce_get_derror_p9(struct pt_regs *regs,
+ struct mce_error_info *mce_err, uint64_t *addr)
+{
+ uint64_t dsisr = regs->dsisr;
+
+ mce_err->severity = MCE_SEV_ERROR_SYNC;
+ mce_err->initiator = MCE_INITIATOR_CPU;
+
+ if (dsisr & P9_DSISR_MC_USER_TLBIE)
+ *addr = regs->nip;
+ else
+ *addr = regs->dar;
+
+ if (dsisr & P9_DSISR_MC_UE) {
+ mce_err->error_type = MCE_ERROR_TYPE_UE;
+ mce_err->u.ue_error_type = MCE_UE_ERROR_LOAD_STORE;
+ } else if (dsisr & P9_DSISR_MC_UE_TABLEWALK) {
+ mce_err->error_type = MCE_ERROR_TYPE_UE;
+ mce_err->u.ue_error_type = MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE;
+ } else if (dsisr & P9_DSISR_MC_LINK_LOAD_TIMEOUT) {
+ mce_err->error_type = MCE_ERROR_TYPE_LINK;
+ mce_err->u.link_error_type = MCE_LINK_ERROR_LOAD_TIMEOUT;
+ } else if (dsisr & P9_DSISR_MC_LINK_TABLEWALK_TIMEOUT) {
+ mce_err->error_type = MCE_ERROR_TYPE_LINK;
+ mce_err->u.link_error_type = MCE_LINK_ERROR_PAGE_TABLE_WALK_LOAD_STORE_TIMEOUT;
+ } else if (dsisr & P9_DSISR_MC_ERAT_MULTIHIT) {
+ mce_err->error_type = MCE_ERROR_TYPE_ERAT;
+ mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
+ } else if (dsisr & P9_DSISR_MC_TLB_MULTIHIT_MFTLB) {
+ mce_err->error_type = MCE_ERROR_TYPE_TLB;
+ mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT;
+ } else if (dsisr & P9_DSISR_MC_USER_TLBIE) {
+ mce_err->error_type = MCE_ERROR_TYPE_USER;
+ mce_err->u.user_error_type = MCE_USER_ERROR_TLBIE;
+ } else if (dsisr & P9_DSISR_MC_SLB_PARITY_MFSLB) {
+ mce_err->error_type = MCE_ERROR_TYPE_SLB;
+ mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY;
+ } else if (dsisr & P9_DSISR_MC_SLB_MULTIHIT_MFSLB) {
+ mce_err->error_type = MCE_ERROR_TYPE_SLB;
+ mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT;
+ } else if (dsisr & P9_DSISR_MC_RA_LOAD) {
+ mce_err->error_type = MCE_ERROR_TYPE_RA;
+ mce_err->u.ra_error_type = MCE_RA_ERROR_LOAD;
+ } else if (dsisr & P9_DSISR_MC_RA_TABLEWALK) {
+ mce_err->error_type = MCE_ERROR_TYPE_RA;
+ mce_err->u.ra_error_type = MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE;
+ } else if (dsisr & P9_DSISR_MC_RA_TABLEWALK_FOREIGN) {
+ mce_err->error_type = MCE_ERROR_TYPE_RA;
+ mce_err->u.ra_error_type = MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE_FOREIGN;
+ } else if (dsisr & P9_DSISR_MC_RA_FOREIGN) {
+ mce_err->error_type = MCE_ERROR_TYPE_RA;
+ mce_err->u.ra_error_type = MCE_RA_ERROR_LOAD_STORE_FOREIGN;
+ }
+}
+
+static void mce_get_ierror_p9(struct pt_regs *regs,
+ struct mce_error_info *mce_err, uint64_t *addr)
+{
+ uint64_t srr1 = regs->msr;
+
+ switch (P9_SRR1_MC_IFETCH(srr1)) {
+ case P9_SRR1_MC_IFETCH_RA_ASYNC_STORE:
+ case P9_SRR1_MC_IFETCH_LINK_ASYNC_STORE_TIMEOUT:
+ mce_err->severity = MCE_SEV_FATAL;
+ break;
+ default:
+ mce_err->severity = MCE_SEV_ERROR_SYNC;
+ break;
+ }
+
+ mce_err->initiator = MCE_INITIATOR_CPU;
+
+ *addr = regs->nip;
+
+ switch (P9_SRR1_MC_IFETCH(srr1)) {
+ case P9_SRR1_MC_IFETCH_UE:
+ mce_err->error_type = MCE_ERROR_TYPE_UE;
+ mce_err->u.ue_error_type = MCE_UE_ERROR_IFETCH;
+ break;
+ case P9_SRR1_MC_IFETCH_SLB_PARITY:
+ mce_err->error_type = MCE_ERROR_TYPE_SLB;
+ mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY;
+ break;
+ case P9_SRR1_MC_IFETCH_SLB_MULTIHIT:
+ mce_err->error_type = MCE_ERROR_TYPE_SLB;
+ mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT;
+ break;
+ case P9_SRR1_MC_IFETCH_ERAT_MULTIHIT:
+ mce_err->error_type = MCE_ERROR_TYPE_ERAT;
+ mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
+ break;
+ case P9_SRR1_MC_IFETCH_TLB_MULTIHIT:
+ mce_err->error_type = MCE_ERROR_TYPE_TLB;
+ mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT;
+ break;
+ case P9_SRR1_MC_IFETCH_UE_TLB_RELOAD:
+ mce_err->error_type = MCE_ERROR_TYPE_UE;
+ mce_err->u.ue_error_type = MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH;
+ break;
+ case P9_SRR1_MC_IFETCH_LINK_TIMEOUT:
+ mce_err->error_type = MCE_ERROR_TYPE_LINK;
+ mce_err->u.link_error_type = MCE_LINK_ERROR_IFETCH_TIMEOUT;
+ break;
+ case P9_SRR1_MC_IFETCH_LINK_TABLEWALK_TIMEOUT:
+ mce_err->error_type = MCE_ERROR_TYPE_LINK;
+ mce_err->u.link_error_type = MCE_LINK_ERROR_PAGE_TABLE_WALK_IFETCH_TIMEOUT;
+ break;
+ case P9_SRR1_MC_IFETCH_RA:
+ mce_err->error_type = MCE_ERROR_TYPE_RA;
+ mce_err->u.ra_error_type = MCE_RA_ERROR_IFETCH;
+ break;
+ case P9_SRR1_MC_IFETCH_RA_TABLEWALK:
+ mce_err->error_type = MCE_ERROR_TYPE_RA;
+ mce_err->u.ra_error_type = MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH;
+ break;
+ case P9_SRR1_MC_IFETCH_RA_ASYNC_STORE:
+ mce_err->error_type = MCE_ERROR_TYPE_RA;
+ mce_err->u.ra_error_type = MCE_RA_ERROR_STORE;
+ break;
+ case P9_SRR1_MC_IFETCH_LINK_ASYNC_STORE_TIMEOUT:
+ mce_err->error_type = MCE_ERROR_TYPE_LINK;
+ mce_err->u.link_error_type = MCE_LINK_ERROR_STORE_TIMEOUT;
+ break;
+ case P9_SRR1_MC_IFETCH_RA_TABLEWALK_FOREIGN:
+ mce_err->error_type = MCE_ERROR_TYPE_RA;
+ mce_err->u.ra_error_type = MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH_FOREIGN;
+ break;
+ default:
+ break;
+ }
+}
+
+long __machine_check_early_realmode_p9(struct pt_regs *regs)
+{
+ uint64_t nip, addr;
+ long handled;
+ struct mce_error_info mce_error_info = { 0 };
+
+ nip = regs->nip;
+
+ if (P9_SRR1_MC_LOADSTORE(regs->msr)) {
+ handled = mce_handle_derror_p9(regs);
+ mce_get_derror_p9(regs, &mce_error_info, &addr);
+ } else {
+ handled = mce_handle_ierror_p9(regs);
+ mce_get_ierror_p9(regs, &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;
+}
--
2.11.0
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH 6/9] powerpc/64s: move POWER machine check defines into mce_power.c
2017-02-20 19:44 [PATCH 0/9] MCE handler for POWER9 Nicholas Piggin
` (4 preceding siblings ...)
2017-02-20 19:44 ` [PATCH 5/9] powerpc/64s: POWER9 machine check handler Nicholas Piggin
@ 2017-02-20 19:44 ` Nicholas Piggin
2017-02-20 19:44 ` [PATCH 7/9] powerpc/64s: data driven machine check evaluation Nicholas Piggin
` (2 subsequent siblings)
8 siblings, 0 replies; 10+ messages in thread
From: Nicholas Piggin @ 2017-02-20 19:44 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin, Michael Ellerman, Mahesh Salgaonkar
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/mce.h | 91 ----------------------------------------
arch/powerpc/kernel/mce_power.c | 92 +++++++++++++++++++++++++++++++++++++++++
2 files changed, 92 insertions(+), 91 deletions(-)
diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index ed62efe01e49..e3498b446788 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -24,97 +24,6 @@
#include <linux/bitops.h>
-/*
- * Machine Check bits on power7 and power8
- */
-#define P7_SRR1_MC_LOADSTORE(srr1) ((srr1) & PPC_BIT(42)) /* P8 too */
-
-/* SRR1 bits for machine check (On Power7 and Power8) */
-#define P7_SRR1_MC_IFETCH(srr1) ((srr1) & PPC_BITMASK(43, 45)) /* P8 too */
-
-#define P7_SRR1_MC_IFETCH_UE (0x1 << PPC_BITLSHIFT(45)) /* P8 too */
-#define P7_SRR1_MC_IFETCH_SLB_PARITY (0x2 << PPC_BITLSHIFT(45)) /* P8 too */
-#define P7_SRR1_MC_IFETCH_SLB_MULTIHIT (0x3 << PPC_BITLSHIFT(45)) /* P8 too */
-#define P7_SRR1_MC_IFETCH_SLB_BOTH (0x4 << PPC_BITLSHIFT(45))
-#define P7_SRR1_MC_IFETCH_TLB_MULTIHIT (0x5 << PPC_BITLSHIFT(45)) /* P8 too */
-#define P7_SRR1_MC_IFETCH_UE_TLB_RELOAD (0x6 << PPC_BITLSHIFT(45)) /* P8 too */
-#define P7_SRR1_MC_IFETCH_UE_IFU_INTERNAL (0x7 << PPC_BITLSHIFT(45))
-
-/* SRR1 bits for machine check (On Power8) */
-#define P8_SRR1_MC_IFETCH_ERAT_MULTIHIT (0x4 << PPC_BITLSHIFT(45))
-
-/* DSISR bits for machine check (On Power7 and Power8) */
-#define P7_DSISR_MC_UE (PPC_BIT(48)) /* P8 too */
-#define P7_DSISR_MC_UE_TABLEWALK (PPC_BIT(49)) /* P8 too */
-#define P7_DSISR_MC_ERAT_MULTIHIT (PPC_BIT(52)) /* P8 too */
-#define P7_DSISR_MC_TLB_MULTIHIT_MFTLB (PPC_BIT(53)) /* P8 too */
-#define P7_DSISR_MC_SLB_PARITY_MFSLB (PPC_BIT(55)) /* P8 too */
-#define P7_DSISR_MC_SLB_MULTIHIT (PPC_BIT(56)) /* P8 too */
-#define P7_DSISR_MC_SLB_MULTIHIT_PARITY (PPC_BIT(57)) /* P8 too */
-
-/*
- * DSISR bits for machine check (Power8) in addition to above.
- * Secondary DERAT Multihit
- */
-#define P8_DSISR_MC_ERAT_MULTIHIT_SEC (PPC_BIT(54))
-
-/* SLB error bits */
-#define P7_DSISR_MC_SLB_ERRORS (P7_DSISR_MC_ERAT_MULTIHIT | \
- P7_DSISR_MC_SLB_PARITY_MFSLB | \
- P7_DSISR_MC_SLB_MULTIHIT | \
- P7_DSISR_MC_SLB_MULTIHIT_PARITY)
-
-#define P8_DSISR_MC_SLB_ERRORS (P7_DSISR_MC_SLB_ERRORS | \
- P8_DSISR_MC_ERAT_MULTIHIT_SEC)
-
-/*
- * Machine Check bits on power9
- */
-#define P9_SRR1_MC_LOADSTORE(srr1) (((srr1) >> PPC_BITLSHIFT(42)) & 1)
-
-#define P9_SRR1_MC_IFETCH(srr1) ( \
- PPC_BITEXTRACT(srr1, 45, 0) | \
- PPC_BITEXTRACT(srr1, 44, 1) | \
- PPC_BITEXTRACT(srr1, 43, 2) | \
- PPC_BITEXTRACT(srr1, 36, 3) )
-
-/* 0 is reserved */
-#define P9_SRR1_MC_IFETCH_UE 1
-#define P9_SRR1_MC_IFETCH_SLB_PARITY 2
-#define P9_SRR1_MC_IFETCH_SLB_MULTIHIT 3
-#define P9_SRR1_MC_IFETCH_ERAT_MULTIHIT 4
-#define P9_SRR1_MC_IFETCH_TLB_MULTIHIT 5
-#define P9_SRR1_MC_IFETCH_UE_TLB_RELOAD 6
-/* 7 is reserved */
-#define P9_SRR1_MC_IFETCH_LINK_TIMEOUT 8
-#define P9_SRR1_MC_IFETCH_LINK_TABLEWALK_TIMEOUT 9
-/* 10 ? */
-#define P9_SRR1_MC_IFETCH_RA 11
-#define P9_SRR1_MC_IFETCH_RA_TABLEWALK 12
-#define P9_SRR1_MC_IFETCH_RA_ASYNC_STORE 13
-#define P9_SRR1_MC_IFETCH_LINK_ASYNC_STORE_TIMEOUT 14
-#define P9_SRR1_MC_IFETCH_RA_TABLEWALK_FOREIGN 15
-
-/* DSISR bits for machine check (On Power9) */
-#define P9_DSISR_MC_UE (PPC_BIT(48))
-#define P9_DSISR_MC_UE_TABLEWALK (PPC_BIT(49))
-#define P9_DSISR_MC_LINK_LOAD_TIMEOUT (PPC_BIT(50))
-#define P9_DSISR_MC_LINK_TABLEWALK_TIMEOUT (PPC_BIT(51))
-#define P9_DSISR_MC_ERAT_MULTIHIT (PPC_BIT(52))
-#define P9_DSISR_MC_TLB_MULTIHIT_MFTLB (PPC_BIT(53))
-#define P9_DSISR_MC_USER_TLBIE (PPC_BIT(54))
-#define P9_DSISR_MC_SLB_PARITY_MFSLB (PPC_BIT(55))
-#define P9_DSISR_MC_SLB_MULTIHIT_MFSLB (PPC_BIT(56))
-#define P9_DSISR_MC_RA_LOAD (PPC_BIT(57))
-#define P9_DSISR_MC_RA_TABLEWALK (PPC_BIT(58))
-#define P9_DSISR_MC_RA_TABLEWALK_FOREIGN (PPC_BIT(59))
-#define P9_DSISR_MC_RA_FOREIGN (PPC_BIT(60))
-
-/* SLB error bits */
-#define P9_DSISR_MC_SLB_ERRORS (P9_DSISR_MC_ERAT_MULTIHIT | \
- P9_DSISR_MC_SLB_PARITY_MFSLB | \
- P9_DSISR_MC_SLB_MULTIHIT_MFSLB)
-
enum MCE_Version {
MCE_V1 = 1,
};
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index cd18314b569a..788a1f53551d 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -161,6 +161,98 @@ static int mce_handle_flush_derrors(uint64_t dsisr, uint64_t slb, uint64_t tlb,
return 1;
}
+
+/*
+ * Machine Check bits on power7 and power8
+ */
+#define P7_SRR1_MC_LOADSTORE(srr1) ((srr1) & PPC_BIT(42)) /* P8 too */
+
+/* SRR1 bits for machine check (On Power7 and Power8) */
+#define P7_SRR1_MC_IFETCH(srr1) ((srr1) & PPC_BITMASK(43, 45)) /* P8 too */
+
+#define P7_SRR1_MC_IFETCH_UE (0x1 << PPC_BITLSHIFT(45)) /* P8 too */
+#define P7_SRR1_MC_IFETCH_SLB_PARITY (0x2 << PPC_BITLSHIFT(45)) /* P8 too */
+#define P7_SRR1_MC_IFETCH_SLB_MULTIHIT (0x3 << PPC_BITLSHIFT(45)) /* P8 too */
+#define P7_SRR1_MC_IFETCH_SLB_BOTH (0x4 << PPC_BITLSHIFT(45))
+#define P7_SRR1_MC_IFETCH_TLB_MULTIHIT (0x5 << PPC_BITLSHIFT(45)) /* P8 too */
+#define P7_SRR1_MC_IFETCH_UE_TLB_RELOAD (0x6 << PPC_BITLSHIFT(45)) /* P8 too */
+#define P7_SRR1_MC_IFETCH_UE_IFU_INTERNAL (0x7 << PPC_BITLSHIFT(45))
+
+/* SRR1 bits for machine check (On Power8) */
+#define P8_SRR1_MC_IFETCH_ERAT_MULTIHIT (0x4 << PPC_BITLSHIFT(45))
+
+/* DSISR bits for machine check (On Power7 and Power8) */
+#define P7_DSISR_MC_UE (PPC_BIT(48)) /* P8 too */
+#define P7_DSISR_MC_UE_TABLEWALK (PPC_BIT(49)) /* P8 too */
+#define P7_DSISR_MC_ERAT_MULTIHIT (PPC_BIT(52)) /* P8 too */
+#define P7_DSISR_MC_TLB_MULTIHIT_MFTLB (PPC_BIT(53)) /* P8 too */
+#define P7_DSISR_MC_SLB_PARITY_MFSLB (PPC_BIT(55)) /* P8 too */
+#define P7_DSISR_MC_SLB_MULTIHIT (PPC_BIT(56)) /* P8 too */
+#define P7_DSISR_MC_SLB_MULTIHIT_PARITY (PPC_BIT(57)) /* P8 too */
+
+/*
+ * DSISR bits for machine check (Power8) in addition to above.
+ * Secondary DERAT Multihit
+ */
+#define P8_DSISR_MC_ERAT_MULTIHIT_SEC (PPC_BIT(54))
+
+/* SLB error bits */
+#define P7_DSISR_MC_SLB_ERRORS (P7_DSISR_MC_ERAT_MULTIHIT | \
+ P7_DSISR_MC_SLB_PARITY_MFSLB | \
+ P7_DSISR_MC_SLB_MULTIHIT | \
+ P7_DSISR_MC_SLB_MULTIHIT_PARITY)
+
+#define P8_DSISR_MC_SLB_ERRORS (P7_DSISR_MC_SLB_ERRORS | \
+ P8_DSISR_MC_ERAT_MULTIHIT_SEC)
+
+/*
+ * Machine Check bits on power9
+ */
+#define P9_SRR1_MC_LOADSTORE(srr1) (((srr1) >> PPC_BITLSHIFT(42)) & 1)
+
+#define P9_SRR1_MC_IFETCH(srr1) ( \
+ PPC_BITEXTRACT(srr1, 45, 0) | \
+ PPC_BITEXTRACT(srr1, 44, 1) | \
+ PPC_BITEXTRACT(srr1, 43, 2) | \
+ PPC_BITEXTRACT(srr1, 36, 3) )
+
+/* 0 is reserved */
+#define P9_SRR1_MC_IFETCH_UE 1
+#define P9_SRR1_MC_IFETCH_SLB_PARITY 2
+#define P9_SRR1_MC_IFETCH_SLB_MULTIHIT 3
+#define P9_SRR1_MC_IFETCH_ERAT_MULTIHIT 4
+#define P9_SRR1_MC_IFETCH_TLB_MULTIHIT 5
+#define P9_SRR1_MC_IFETCH_UE_TLB_RELOAD 6
+/* 7 is reserved */
+#define P9_SRR1_MC_IFETCH_LINK_TIMEOUT 8
+#define P9_SRR1_MC_IFETCH_LINK_TABLEWALK_TIMEOUT 9
+/* 10 ? */
+#define P9_SRR1_MC_IFETCH_RA 11
+#define P9_SRR1_MC_IFETCH_RA_TABLEWALK 12
+#define P9_SRR1_MC_IFETCH_RA_ASYNC_STORE 13
+#define P9_SRR1_MC_IFETCH_LINK_ASYNC_STORE_TIMEOUT 14
+#define P9_SRR1_MC_IFETCH_RA_TABLEWALK_FOREIGN 15
+
+/* DSISR bits for machine check (On Power9) */
+#define P9_DSISR_MC_UE (PPC_BIT(48))
+#define P9_DSISR_MC_UE_TABLEWALK (PPC_BIT(49))
+#define P9_DSISR_MC_LINK_LOAD_TIMEOUT (PPC_BIT(50))
+#define P9_DSISR_MC_LINK_TABLEWALK_TIMEOUT (PPC_BIT(51))
+#define P9_DSISR_MC_ERAT_MULTIHIT (PPC_BIT(52))
+#define P9_DSISR_MC_TLB_MULTIHIT_MFTLB (PPC_BIT(53))
+#define P9_DSISR_MC_USER_TLBIE (PPC_BIT(54))
+#define P9_DSISR_MC_SLB_PARITY_MFSLB (PPC_BIT(55))
+#define P9_DSISR_MC_SLB_MULTIHIT_MFSLB (PPC_BIT(56))
+#define P9_DSISR_MC_RA_LOAD (PPC_BIT(57))
+#define P9_DSISR_MC_RA_TABLEWALK (PPC_BIT(58))
+#define P9_DSISR_MC_RA_TABLEWALK_FOREIGN (PPC_BIT(59))
+#define P9_DSISR_MC_RA_FOREIGN (PPC_BIT(60))
+
+/* SLB error bits */
+#define P9_DSISR_MC_SLB_ERRORS (P9_DSISR_MC_ERAT_MULTIHIT | \
+ P9_DSISR_MC_SLB_PARITY_MFSLB | \
+ P9_DSISR_MC_SLB_MULTIHIT_MFSLB)
+
static long mce_handle_derror_p7(uint64_t dsisr)
{
return mce_handle_flush_derrors(dsisr,
--
2.11.0
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH 7/9] powerpc/64s: data driven machine check evaluation
2017-02-20 19:44 [PATCH 0/9] MCE handler for POWER9 Nicholas Piggin
` (5 preceding siblings ...)
2017-02-20 19:44 ` [PATCH 6/9] powerpc/64s: move POWER machine check defines into mce_power.c Nicholas Piggin
@ 2017-02-20 19:44 ` Nicholas Piggin
2017-02-20 19:44 ` [PATCH 8/9] powerpc/64s: data driven machine check handling Nicholas Piggin
2017-02-20 19:44 ` [PATCH 9/9] powerpc/64s: POWER8 add missing machine check definitions Nicholas Piggin
8 siblings, 0 replies; 10+ messages in thread
From: Nicholas Piggin @ 2017-02-20 19:44 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin, Michael Ellerman, Mahesh Salgaonkar
This makes a change in that it no longer passes undefined DAR as
the effective address for those errors that don't define it.
This was tested with a userspace harness to exercise valid SRR1
and DSISR combinations.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/mce_power.c | 569 +++++++++++++++++++++++-----------------
1 file changed, 326 insertions(+), 243 deletions(-)
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index 788a1f53551d..42e85f7bb9e2 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -253,91 +253,305 @@ static int mce_handle_flush_derrors(uint64_t dsisr, uint64_t slb, uint64_t tlb,
P9_DSISR_MC_SLB_PARITY_MFSLB | \
P9_DSISR_MC_SLB_MULTIHIT_MFSLB)
-static long mce_handle_derror_p7(uint64_t dsisr)
-{
- return mce_handle_flush_derrors(dsisr,
- P7_DSISR_MC_SLB_ERRORS,
- P7_DSISR_MC_TLB_MULTIHIT_MFTLB,
- 0);
-}
-
-static long mce_handle_ierror_p7(uint64_t srr1)
+struct mce_ierror_table {
+ unsigned long srr1_mask;
+ unsigned long srr1_value;
+ bool nip_valid; /* nip is a valid indicator of faulting address */
+ unsigned int error_type;
+ unsigned int error_subtype;
+ unsigned int initiator;
+ unsigned int severity;
+};
+
+static const struct mce_ierror_table mce_p7_ierror_table[] = {
+{ 0x00000000001c0000, 0x0000000000040000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_IFETCH,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000001c0000, 0x0000000000080000, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000001c0000, 0x00000000000c0000, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000001c0000, 0x0000000000100000, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_INDETERMINATE, /* BOTH */
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000001c0000, 0x0000000000140000, true,
+ MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000001c0000, 0x0000000000180000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000001c0000, 0x00000000001c0000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_IFETCH,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0, 0, 0, 0, 0, 0 } };
+
+static const struct mce_ierror_table mce_p8_ierror_table[] = {
+{ 0x00000000001c0000, 0x0000000000040000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_IFETCH,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000001c0000, 0x0000000000080000, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000001c0000, 0x00000000000c0000, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000001c0000, 0x0000000000100000, true,
+ MCE_ERROR_TYPE_ERAT,MCE_ERAT_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000001c0000, 0x0000000000140000, true,
+ MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000001c0000, 0x0000000000180000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000001c0000, 0x00000000001c0000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_IFETCH,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0, 0, 0, 0, 0, 0 } };
+
+static const struct mce_ierror_table mce_p9_ierror_table[] = {
+{ 0x00000000081c0000, 0x0000000000040000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_IFETCH,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x0000000000080000, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x00000000000c0000, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x0000000000100000, true,
+ MCE_ERROR_TYPE_ERAT,MCE_ERAT_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x0000000000140000, true,
+ MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x0000000000180000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x0000000008000000, true,
+ MCE_ERROR_TYPE_LINK,MCE_LINK_ERROR_IFETCH_TIMEOUT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x0000000008040000, true,
+ MCE_ERROR_TYPE_LINK,MCE_LINK_ERROR_PAGE_TABLE_WALK_IFETCH_TIMEOUT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x00000000080c0000, true,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_IFETCH,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x0000000008100000, true,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x0000000008140000, false,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_STORE,
+ MCE_INITIATOR_CPU, MCE_SEV_FATAL, }, /* ASYNC is fatal */
+{ 0x00000000081c0000, 0x0000000008180000, false,
+ MCE_ERROR_TYPE_LINK,MCE_LINK_ERROR_STORE_TIMEOUT,
+ MCE_INITIATOR_CPU, MCE_SEV_FATAL, }, /* ASYNC is fatal */
+{ 0x00000000081c0000, 0x00000000081c0000, true,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH_FOREIGN,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0, 0, 0, 0, 0, 0 } };
+
+struct mce_derror_table {
+ unsigned long dsisr_value;
+ bool dar_valid; /* dar is a valid indicator of faulting address */
+ unsigned int error_type;
+ unsigned int error_subtype;
+ unsigned int initiator;
+ unsigned int severity;
+};
+
+static const struct mce_derror_table mce_p7_derror_table[] = {
+{ 0x00008000, false,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_LOAD_STORE,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00004000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000800, true,
+ MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000400, true,
+ MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000100, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000080, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000040, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_INDETERMINATE, /* BOTH */
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0, false, 0, 0, 0, 0 } };
+
+static const struct mce_derror_table mce_p8_derror_table[] = {
+{ 0x00008000, false,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_LOAD_STORE,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00004000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000800, true,
+ MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000400, true,
+ MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000200, true,
+ MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, /* SECONDARY ERAT */
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000100, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000080, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0, false, 0, 0, 0, 0 } };
+
+static const struct mce_derror_table mce_p9_derror_table[] = {
+{ 0x00008000, false,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_LOAD_STORE,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00004000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00002000, true,
+ MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_LOAD_TIMEOUT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00001000, true,
+ MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_PAGE_TABLE_WALK_LOAD_STORE_TIMEOUT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000800, true,
+ MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000400, true,
+ MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000200, false,
+ MCE_ERROR_TYPE_USER, MCE_USER_ERROR_TLBIE,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000100, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000080, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000040, true,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_LOAD,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000020, false,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000010, false,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE_FOREIGN,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000008, false,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_LOAD_STORE_FOREIGN,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0, false, 0, 0, 0, 0 } };
+
+static void mce_get_ierror(struct pt_regs *regs,
+ const struct mce_ierror_table table[],
+ struct mce_error_info *mce_err, uint64_t *addr)
{
- switch (P7_SRR1_MC_IFETCH(srr1)) {
- case P7_SRR1_MC_IFETCH_SLB_PARITY:
- case P7_SRR1_MC_IFETCH_SLB_MULTIHIT:
- case P7_SRR1_MC_IFETCH_SLB_BOTH:
- return mce_flush(MCE_FLUSH_SLB);
-
- case P7_SRR1_MC_IFETCH_TLB_MULTIHIT:
- return mce_flush(MCE_FLUSH_TLB);
- default:
- return 0;
+ uint64_t srr1 = regs->msr;
+ int i;
+
+ *addr = 0;
+
+ for (i = 0; table[i].srr1_mask; i++) {
+ if ((srr1 & table[i].srr1_mask) != table[i].srr1_value)
+ continue;
+
+ mce_err->error_type = table[i].error_type;
+ switch (table[i].error_type) {
+ case MCE_ERROR_TYPE_UE:
+ mce_err->u.ue_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_SLB:
+ mce_err->u.slb_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_ERAT:
+ mce_err->u.erat_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_TLB:
+ mce_err->u.tlb_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_USER:
+ mce_err->u.user_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_RA:
+ mce_err->u.ra_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_LINK:
+ mce_err->u.link_error_type = table[i].error_subtype;
+ break;
+ }
+ mce_err->severity = table[i].severity;
+ mce_err->initiator = table[i].initiator;
+ if (table[i].nip_valid)
+ *addr = regs->nip;
+ return;
}
-}
-static void mce_get_common_ierror(struct mce_error_info *mce_err, uint64_t srr1)
-{
- switch (P7_SRR1_MC_IFETCH(srr1)) {
- case P7_SRR1_MC_IFETCH_SLB_PARITY:
- mce_err->error_type = MCE_ERROR_TYPE_SLB;
- mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY;
- break;
- case P7_SRR1_MC_IFETCH_SLB_MULTIHIT:
- mce_err->error_type = MCE_ERROR_TYPE_SLB;
- mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT;
- break;
- case P7_SRR1_MC_IFETCH_TLB_MULTIHIT:
- mce_err->error_type = MCE_ERROR_TYPE_TLB;
- mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT;
- break;
- case P7_SRR1_MC_IFETCH_UE:
- case P7_SRR1_MC_IFETCH_UE_IFU_INTERNAL:
- mce_err->error_type = MCE_ERROR_TYPE_UE;
- mce_err->u.ue_error_type = MCE_UE_ERROR_IFETCH;
- break;
- case P7_SRR1_MC_IFETCH_UE_TLB_RELOAD:
- mce_err->error_type = MCE_ERROR_TYPE_UE;
- mce_err->u.ue_error_type =
- MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH;
- break;
- }
+ mce_err->error_type = MCE_ERROR_TYPE_UNKNOWN;
+ mce_err->severity = MCE_SEV_ERROR_SYNC;
+ mce_err->initiator = MCE_INITIATOR_CPU;
}
-static void mce_get_ierror_p7(struct mce_error_info *mce_err, uint64_t srr1)
+static void mce_get_derror(struct pt_regs *regs,
+ const struct mce_derror_table table[],
+ struct mce_error_info *mce_err, uint64_t *addr)
{
- mce_get_common_ierror(mce_err, srr1);
- if (P7_SRR1_MC_IFETCH(srr1) == P7_SRR1_MC_IFETCH_SLB_BOTH) {
- mce_err->error_type = MCE_ERROR_TYPE_SLB;
- mce_err->u.slb_error_type = MCE_SLB_ERROR_INDETERMINATE;
- }
-}
+ /* P7 DD1 leaves top bits undefined */
+ uint64_t dsisr = regs->dsisr & 0x0000ffff;
+ int i;
+
+ *addr = 0;
+
+ for (i = 0; table[i].dsisr_value; i++) {
+ if (!(dsisr & table[i].dsisr_value))
+ continue;
+
+ mce_err->error_type = table[i].error_type;
+ switch (table[i].error_type) {
+ case MCE_ERROR_TYPE_UE:
+ mce_err->u.ue_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_SLB:
+ mce_err->u.slb_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_ERAT:
+ mce_err->u.erat_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_TLB:
+ mce_err->u.tlb_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_USER:
+ mce_err->u.user_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_RA:
+ mce_err->u.ra_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_LINK:
+ mce_err->u.link_error_type = table[i].error_subtype;
+ break;
+ }
+ mce_err->severity = table[i].severity;
+ mce_err->initiator = table[i].initiator;
+ if (table[i].dar_valid)
+ *addr = regs->dar;
+ else
+ *addr = regs->nip;
-static void mce_get_derror_p7(struct mce_error_info *mce_err, uint64_t dsisr)
-{
- if (dsisr & P7_DSISR_MC_UE) {
- mce_err->error_type = MCE_ERROR_TYPE_UE;
- mce_err->u.ue_error_type = MCE_UE_ERROR_LOAD_STORE;
- } else if (dsisr & P7_DSISR_MC_UE_TABLEWALK) {
- mce_err->error_type = MCE_ERROR_TYPE_UE;
- mce_err->u.ue_error_type =
- MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE;
- } else if (dsisr & P7_DSISR_MC_ERAT_MULTIHIT) {
- mce_err->error_type = MCE_ERROR_TYPE_ERAT;
- mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
- } else if (dsisr & P7_DSISR_MC_SLB_MULTIHIT) {
- mce_err->error_type = MCE_ERROR_TYPE_SLB;
- mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT;
- } else if (dsisr & P7_DSISR_MC_SLB_PARITY_MFSLB) {
- mce_err->error_type = MCE_ERROR_TYPE_SLB;
- mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY;
- } else if (dsisr & P7_DSISR_MC_TLB_MULTIHIT_MFTLB) {
- mce_err->error_type = MCE_ERROR_TYPE_TLB;
- mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT;
- } else if (dsisr & P7_DSISR_MC_SLB_MULTIHIT_PARITY) {
- mce_err->error_type = MCE_ERROR_TYPE_SLB;
- mce_err->u.slb_error_type = MCE_SLB_ERROR_INDETERMINATE;
+ return;
}
+
+ mce_err->error_type = MCE_ERROR_TYPE_UNKNOWN;
+ mce_err->severity = MCE_SEV_ERROR_SYNC;
+ mce_err->initiator = MCE_INITIATOR_CPU;
}
static long mce_handle_ue_error(struct pt_regs *regs)
@@ -358,15 +572,35 @@ static long mce_handle_ue_error(struct pt_regs *regs)
return handled;
}
+static long mce_handle_derror_p7(uint64_t dsisr)
+{
+ return mce_handle_flush_derrors(dsisr,
+ P7_DSISR_MC_SLB_ERRORS,
+ P7_DSISR_MC_TLB_MULTIHIT_MFTLB,
+ 0);
+}
+
+static long mce_handle_ierror_p7(uint64_t srr1)
+{
+ switch (P7_SRR1_MC_IFETCH(srr1)) {
+ case P7_SRR1_MC_IFETCH_SLB_PARITY:
+ case P7_SRR1_MC_IFETCH_SLB_MULTIHIT:
+ case P7_SRR1_MC_IFETCH_SLB_BOTH:
+ return mce_flush(MCE_FLUSH_SLB);
+
+ case P7_SRR1_MC_IFETCH_TLB_MULTIHIT:
+ return mce_flush(MCE_FLUSH_TLB);
+ default:
+ return 0;
+ }
+}
+
long __machine_check_early_realmode_p7(struct pt_regs *regs)
{
uint64_t srr1, nip, addr;
long handled = 1;
struct mce_error_info mce_error_info = { 0 };
- mce_error_info.severity = MCE_SEV_ERROR_SYNC;
- mce_error_info.initiator = MCE_INITIATOR_CPU;
-
srr1 = regs->msr;
nip = regs->nip;
@@ -378,12 +612,12 @@ long __machine_check_early_realmode_p7(struct pt_regs *regs)
*/
if (P7_SRR1_MC_LOADSTORE(srr1)) {
handled = mce_handle_derror_p7(regs->dsisr);
- mce_get_derror_p7(&mce_error_info, regs->dsisr);
- addr = regs->dar;
+ mce_get_derror(regs, mce_p7_derror_table,
+ &mce_error_info, &addr);
} else {
handled = mce_handle_ierror_p7(srr1);
- mce_get_ierror_p7(&mce_error_info, srr1);
- addr = regs->nip;
+ mce_get_ierror(regs, mce_p7_ierror_table,
+ &mce_error_info, &addr);
}
/* Handle UE error. */
@@ -394,24 +628,6 @@ long __machine_check_early_realmode_p7(struct pt_regs *regs)
return handled;
}
-static void mce_get_ierror_p8(struct mce_error_info *mce_err, uint64_t srr1)
-{
- mce_get_common_ierror(mce_err, srr1);
- if (P7_SRR1_MC_IFETCH(srr1) == P8_SRR1_MC_IFETCH_ERAT_MULTIHIT) {
- mce_err->error_type = MCE_ERROR_TYPE_ERAT;
- mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
- }
-}
-
-static void mce_get_derror_p8(struct mce_error_info *mce_err, uint64_t dsisr)
-{
- mce_get_derror_p7(mce_err, dsisr);
- if (dsisr & P8_DSISR_MC_ERAT_MULTIHIT_SEC) {
- mce_err->error_type = MCE_ERROR_TYPE_ERAT;
- mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
- }
-}
-
static long mce_handle_ierror_p8(uint64_t srr1)
{
switch (P7_SRR1_MC_IFETCH(srr1)) {
@@ -441,20 +657,17 @@ long __machine_check_early_realmode_p8(struct pt_regs *regs)
long handled = 1;
struct mce_error_info mce_error_info = { 0 };
- mce_error_info.severity = MCE_SEV_ERROR_SYNC;
- mce_error_info.initiator = MCE_INITIATOR_CPU;
-
srr1 = regs->msr;
nip = regs->nip;
if (P7_SRR1_MC_LOADSTORE(srr1)) {
handled = mce_handle_derror_p8(regs->dsisr);
- mce_get_derror_p8(&mce_error_info, regs->dsisr);
- addr = regs->dar;
+ mce_get_derror(regs, mce_p8_derror_table,
+ &mce_error_info, &addr);
} else {
handled = mce_handle_ierror_p8(srr1);
- mce_get_ierror_p8(&mce_error_info, srr1);
- addr = regs->nip;
+ mce_get_ierror(regs, mce_p8_ierror_table,
+ &mce_error_info, &addr);
}
/* Handle UE error. */
@@ -503,138 +716,6 @@ static int mce_handle_ierror_p9(struct pt_regs *regs)
}
}
-static void mce_get_derror_p9(struct pt_regs *regs,
- struct mce_error_info *mce_err, uint64_t *addr)
-{
- uint64_t dsisr = regs->dsisr;
-
- mce_err->severity = MCE_SEV_ERROR_SYNC;
- mce_err->initiator = MCE_INITIATOR_CPU;
-
- if (dsisr & P9_DSISR_MC_USER_TLBIE)
- *addr = regs->nip;
- else
- *addr = regs->dar;
-
- if (dsisr & P9_DSISR_MC_UE) {
- mce_err->error_type = MCE_ERROR_TYPE_UE;
- mce_err->u.ue_error_type = MCE_UE_ERROR_LOAD_STORE;
- } else if (dsisr & P9_DSISR_MC_UE_TABLEWALK) {
- mce_err->error_type = MCE_ERROR_TYPE_UE;
- mce_err->u.ue_error_type = MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE;
- } else if (dsisr & P9_DSISR_MC_LINK_LOAD_TIMEOUT) {
- mce_err->error_type = MCE_ERROR_TYPE_LINK;
- mce_err->u.link_error_type = MCE_LINK_ERROR_LOAD_TIMEOUT;
- } else if (dsisr & P9_DSISR_MC_LINK_TABLEWALK_TIMEOUT) {
- mce_err->error_type = MCE_ERROR_TYPE_LINK;
- mce_err->u.link_error_type = MCE_LINK_ERROR_PAGE_TABLE_WALK_LOAD_STORE_TIMEOUT;
- } else if (dsisr & P9_DSISR_MC_ERAT_MULTIHIT) {
- mce_err->error_type = MCE_ERROR_TYPE_ERAT;
- mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
- } else if (dsisr & P9_DSISR_MC_TLB_MULTIHIT_MFTLB) {
- mce_err->error_type = MCE_ERROR_TYPE_TLB;
- mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT;
- } else if (dsisr & P9_DSISR_MC_USER_TLBIE) {
- mce_err->error_type = MCE_ERROR_TYPE_USER;
- mce_err->u.user_error_type = MCE_USER_ERROR_TLBIE;
- } else if (dsisr & P9_DSISR_MC_SLB_PARITY_MFSLB) {
- mce_err->error_type = MCE_ERROR_TYPE_SLB;
- mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY;
- } else if (dsisr & P9_DSISR_MC_SLB_MULTIHIT_MFSLB) {
- mce_err->error_type = MCE_ERROR_TYPE_SLB;
- mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT;
- } else if (dsisr & P9_DSISR_MC_RA_LOAD) {
- mce_err->error_type = MCE_ERROR_TYPE_RA;
- mce_err->u.ra_error_type = MCE_RA_ERROR_LOAD;
- } else if (dsisr & P9_DSISR_MC_RA_TABLEWALK) {
- mce_err->error_type = MCE_ERROR_TYPE_RA;
- mce_err->u.ra_error_type = MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE;
- } else if (dsisr & P9_DSISR_MC_RA_TABLEWALK_FOREIGN) {
- mce_err->error_type = MCE_ERROR_TYPE_RA;
- mce_err->u.ra_error_type = MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE_FOREIGN;
- } else if (dsisr & P9_DSISR_MC_RA_FOREIGN) {
- mce_err->error_type = MCE_ERROR_TYPE_RA;
- mce_err->u.ra_error_type = MCE_RA_ERROR_LOAD_STORE_FOREIGN;
- }
-}
-
-static void mce_get_ierror_p9(struct pt_regs *regs,
- struct mce_error_info *mce_err, uint64_t *addr)
-{
- uint64_t srr1 = regs->msr;
-
- switch (P9_SRR1_MC_IFETCH(srr1)) {
- case P9_SRR1_MC_IFETCH_RA_ASYNC_STORE:
- case P9_SRR1_MC_IFETCH_LINK_ASYNC_STORE_TIMEOUT:
- mce_err->severity = MCE_SEV_FATAL;
- break;
- default:
- mce_err->severity = MCE_SEV_ERROR_SYNC;
- break;
- }
-
- mce_err->initiator = MCE_INITIATOR_CPU;
-
- *addr = regs->nip;
-
- switch (P9_SRR1_MC_IFETCH(srr1)) {
- case P9_SRR1_MC_IFETCH_UE:
- mce_err->error_type = MCE_ERROR_TYPE_UE;
- mce_err->u.ue_error_type = MCE_UE_ERROR_IFETCH;
- break;
- case P9_SRR1_MC_IFETCH_SLB_PARITY:
- mce_err->error_type = MCE_ERROR_TYPE_SLB;
- mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY;
- break;
- case P9_SRR1_MC_IFETCH_SLB_MULTIHIT:
- mce_err->error_type = MCE_ERROR_TYPE_SLB;
- mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT;
- break;
- case P9_SRR1_MC_IFETCH_ERAT_MULTIHIT:
- mce_err->error_type = MCE_ERROR_TYPE_ERAT;
- mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
- break;
- case P9_SRR1_MC_IFETCH_TLB_MULTIHIT:
- mce_err->error_type = MCE_ERROR_TYPE_TLB;
- mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT;
- break;
- case P9_SRR1_MC_IFETCH_UE_TLB_RELOAD:
- mce_err->error_type = MCE_ERROR_TYPE_UE;
- mce_err->u.ue_error_type = MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH;
- break;
- case P9_SRR1_MC_IFETCH_LINK_TIMEOUT:
- mce_err->error_type = MCE_ERROR_TYPE_LINK;
- mce_err->u.link_error_type = MCE_LINK_ERROR_IFETCH_TIMEOUT;
- break;
- case P9_SRR1_MC_IFETCH_LINK_TABLEWALK_TIMEOUT:
- mce_err->error_type = MCE_ERROR_TYPE_LINK;
- mce_err->u.link_error_type = MCE_LINK_ERROR_PAGE_TABLE_WALK_IFETCH_TIMEOUT;
- break;
- case P9_SRR1_MC_IFETCH_RA:
- mce_err->error_type = MCE_ERROR_TYPE_RA;
- mce_err->u.ra_error_type = MCE_RA_ERROR_IFETCH;
- break;
- case P9_SRR1_MC_IFETCH_RA_TABLEWALK:
- mce_err->error_type = MCE_ERROR_TYPE_RA;
- mce_err->u.ra_error_type = MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH;
- break;
- case P9_SRR1_MC_IFETCH_RA_ASYNC_STORE:
- mce_err->error_type = MCE_ERROR_TYPE_RA;
- mce_err->u.ra_error_type = MCE_RA_ERROR_STORE;
- break;
- case P9_SRR1_MC_IFETCH_LINK_ASYNC_STORE_TIMEOUT:
- mce_err->error_type = MCE_ERROR_TYPE_LINK;
- mce_err->u.link_error_type = MCE_LINK_ERROR_STORE_TIMEOUT;
- break;
- case P9_SRR1_MC_IFETCH_RA_TABLEWALK_FOREIGN:
- mce_err->error_type = MCE_ERROR_TYPE_RA;
- mce_err->u.ra_error_type = MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH_FOREIGN;
- break;
- default:
- break;
- }
-}
-
long __machine_check_early_realmode_p9(struct pt_regs *regs)
{
uint64_t nip, addr;
@@ -645,10 +726,12 @@ long __machine_check_early_realmode_p9(struct pt_regs *regs)
if (P9_SRR1_MC_LOADSTORE(regs->msr)) {
handled = mce_handle_derror_p9(regs);
- mce_get_derror_p9(regs, &mce_error_info, &addr);
+ mce_get_derror(regs, mce_p9_derror_table,
+ &mce_error_info, &addr);
} else {
handled = mce_handle_ierror_p9(regs);
- mce_get_ierror_p9(regs, &mce_error_info, &addr);
+ mce_get_ierror(regs, mce_p9_ierror_table,
+ &mce_error_info, &addr);
}
/* Handle UE error. */
--
2.11.0
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH 8/9] powerpc/64s: data driven machine check handling
2017-02-20 19:44 [PATCH 0/9] MCE handler for POWER9 Nicholas Piggin
` (6 preceding siblings ...)
2017-02-20 19:44 ` [PATCH 7/9] powerpc/64s: data driven machine check evaluation Nicholas Piggin
@ 2017-02-20 19:44 ` Nicholas Piggin
2017-02-20 19:44 ` [PATCH 9/9] powerpc/64s: POWER8 add missing machine check definitions Nicholas Piggin
8 siblings, 0 replies; 10+ messages in thread
From: Nicholas Piggin @ 2017-02-20 19:44 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin, Michael Ellerman, Mahesh Salgaonkar
Merge the evaluation and handling of machine checks into the
same table matching loop.
This changes P7 and P8 ERAT flushing from using SLB flush to
using ERAT flush.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/mce_power.c | 325 ++++++++++------------------------------
1 file changed, 83 insertions(+), 242 deletions(-)
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index 42e85f7bb9e2..3e4149a6d469 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -147,111 +147,7 @@ static int mce_flush(int what)
return 0;
}
-static int mce_handle_flush_derrors(uint64_t dsisr, uint64_t slb, uint64_t tlb, uint64_t erat)
-{
- if ((dsisr & slb) && mce_flush(MCE_FLUSH_SLB))
- dsisr &= ~slb;
- if ((dsisr & erat) && mce_flush(MCE_FLUSH_ERAT))
- dsisr &= ~erat;
- if ((dsisr & tlb) && mce_flush(MCE_FLUSH_TLB))
- dsisr &= ~tlb;
- /* Any other errors we don't understand? */
- if (dsisr)
- return 0;
- return 1;
-}
-
-
-/*
- * Machine Check bits on power7 and power8
- */
-#define P7_SRR1_MC_LOADSTORE(srr1) ((srr1) & PPC_BIT(42)) /* P8 too */
-
-/* SRR1 bits for machine check (On Power7 and Power8) */
-#define P7_SRR1_MC_IFETCH(srr1) ((srr1) & PPC_BITMASK(43, 45)) /* P8 too */
-
-#define P7_SRR1_MC_IFETCH_UE (0x1 << PPC_BITLSHIFT(45)) /* P8 too */
-#define P7_SRR1_MC_IFETCH_SLB_PARITY (0x2 << PPC_BITLSHIFT(45)) /* P8 too */
-#define P7_SRR1_MC_IFETCH_SLB_MULTIHIT (0x3 << PPC_BITLSHIFT(45)) /* P8 too */
-#define P7_SRR1_MC_IFETCH_SLB_BOTH (0x4 << PPC_BITLSHIFT(45))
-#define P7_SRR1_MC_IFETCH_TLB_MULTIHIT (0x5 << PPC_BITLSHIFT(45)) /* P8 too */
-#define P7_SRR1_MC_IFETCH_UE_TLB_RELOAD (0x6 << PPC_BITLSHIFT(45)) /* P8 too */
-#define P7_SRR1_MC_IFETCH_UE_IFU_INTERNAL (0x7 << PPC_BITLSHIFT(45))
-
-/* SRR1 bits for machine check (On Power8) */
-#define P8_SRR1_MC_IFETCH_ERAT_MULTIHIT (0x4 << PPC_BITLSHIFT(45))
-
-/* DSISR bits for machine check (On Power7 and Power8) */
-#define P7_DSISR_MC_UE (PPC_BIT(48)) /* P8 too */
-#define P7_DSISR_MC_UE_TABLEWALK (PPC_BIT(49)) /* P8 too */
-#define P7_DSISR_MC_ERAT_MULTIHIT (PPC_BIT(52)) /* P8 too */
-#define P7_DSISR_MC_TLB_MULTIHIT_MFTLB (PPC_BIT(53)) /* P8 too */
-#define P7_DSISR_MC_SLB_PARITY_MFSLB (PPC_BIT(55)) /* P8 too */
-#define P7_DSISR_MC_SLB_MULTIHIT (PPC_BIT(56)) /* P8 too */
-#define P7_DSISR_MC_SLB_MULTIHIT_PARITY (PPC_BIT(57)) /* P8 too */
-
-/*
- * DSISR bits for machine check (Power8) in addition to above.
- * Secondary DERAT Multihit
- */
-#define P8_DSISR_MC_ERAT_MULTIHIT_SEC (PPC_BIT(54))
-
-/* SLB error bits */
-#define P7_DSISR_MC_SLB_ERRORS (P7_DSISR_MC_ERAT_MULTIHIT | \
- P7_DSISR_MC_SLB_PARITY_MFSLB | \
- P7_DSISR_MC_SLB_MULTIHIT | \
- P7_DSISR_MC_SLB_MULTIHIT_PARITY)
-
-#define P8_DSISR_MC_SLB_ERRORS (P7_DSISR_MC_SLB_ERRORS | \
- P8_DSISR_MC_ERAT_MULTIHIT_SEC)
-
-/*
- * Machine Check bits on power9
- */
-#define P9_SRR1_MC_LOADSTORE(srr1) (((srr1) >> PPC_BITLSHIFT(42)) & 1)
-
-#define P9_SRR1_MC_IFETCH(srr1) ( \
- PPC_BITEXTRACT(srr1, 45, 0) | \
- PPC_BITEXTRACT(srr1, 44, 1) | \
- PPC_BITEXTRACT(srr1, 43, 2) | \
- PPC_BITEXTRACT(srr1, 36, 3) )
-
-/* 0 is reserved */
-#define P9_SRR1_MC_IFETCH_UE 1
-#define P9_SRR1_MC_IFETCH_SLB_PARITY 2
-#define P9_SRR1_MC_IFETCH_SLB_MULTIHIT 3
-#define P9_SRR1_MC_IFETCH_ERAT_MULTIHIT 4
-#define P9_SRR1_MC_IFETCH_TLB_MULTIHIT 5
-#define P9_SRR1_MC_IFETCH_UE_TLB_RELOAD 6
-/* 7 is reserved */
-#define P9_SRR1_MC_IFETCH_LINK_TIMEOUT 8
-#define P9_SRR1_MC_IFETCH_LINK_TABLEWALK_TIMEOUT 9
-/* 10 ? */
-#define P9_SRR1_MC_IFETCH_RA 11
-#define P9_SRR1_MC_IFETCH_RA_TABLEWALK 12
-#define P9_SRR1_MC_IFETCH_RA_ASYNC_STORE 13
-#define P9_SRR1_MC_IFETCH_LINK_ASYNC_STORE_TIMEOUT 14
-#define P9_SRR1_MC_IFETCH_RA_TABLEWALK_FOREIGN 15
-
-/* DSISR bits for machine check (On Power9) */
-#define P9_DSISR_MC_UE (PPC_BIT(48))
-#define P9_DSISR_MC_UE_TABLEWALK (PPC_BIT(49))
-#define P9_DSISR_MC_LINK_LOAD_TIMEOUT (PPC_BIT(50))
-#define P9_DSISR_MC_LINK_TABLEWALK_TIMEOUT (PPC_BIT(51))
-#define P9_DSISR_MC_ERAT_MULTIHIT (PPC_BIT(52))
-#define P9_DSISR_MC_TLB_MULTIHIT_MFTLB (PPC_BIT(53))
-#define P9_DSISR_MC_USER_TLBIE (PPC_BIT(54))
-#define P9_DSISR_MC_SLB_PARITY_MFSLB (PPC_BIT(55))
-#define P9_DSISR_MC_SLB_MULTIHIT_MFSLB (PPC_BIT(56))
-#define P9_DSISR_MC_RA_LOAD (PPC_BIT(57))
-#define P9_DSISR_MC_RA_TABLEWALK (PPC_BIT(58))
-#define P9_DSISR_MC_RA_TABLEWALK_FOREIGN (PPC_BIT(59))
-#define P9_DSISR_MC_RA_FOREIGN (PPC_BIT(60))
-
-/* SLB error bits */
-#define P9_DSISR_MC_SLB_ERRORS (P9_DSISR_MC_ERAT_MULTIHIT | \
- P9_DSISR_MC_SLB_PARITY_MFSLB | \
- P9_DSISR_MC_SLB_MULTIHIT_MFSLB)
+#define SRR1_MC_LOADSTORE(srr1) ((srr1) & PPC_BIT(42))
struct mce_ierror_table {
unsigned long srr1_mask;
@@ -452,11 +348,12 @@ static const struct mce_derror_table mce_p9_derror_table[] = {
MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
{ 0, false, 0, 0, 0, 0 } };
-static void mce_get_ierror(struct pt_regs *regs,
+static int mce_handle_ierror(struct pt_regs *regs,
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;
*addr = 0;
@@ -465,6 +362,18 @@ static void mce_get_ierror(struct pt_regs *regs,
if ((srr1 & table[i].srr1_mask) != table[i].srr1_value)
continue;
+ switch (table[i].error_type) {
+ case MCE_ERROR_TYPE_SLB:
+ handled = mce_flush(MCE_FLUSH_SLB);
+ break;
+ case MCE_ERROR_TYPE_ERAT:
+ handled = mce_flush(MCE_FLUSH_ERAT);
+ break;
+ case MCE_ERROR_TYPE_TLB:
+ handled = mce_flush(MCE_FLUSH_TLB);
+ break;
+ }
+
mce_err->error_type = table[i].error_type;
switch (table[i].error_type) {
case MCE_ERROR_TYPE_UE:
@@ -493,20 +402,24 @@ static void mce_get_ierror(struct pt_regs *regs,
mce_err->initiator = table[i].initiator;
if (table[i].nip_valid)
*addr = regs->nip;
- return;
+ return handled;
}
mce_err->error_type = MCE_ERROR_TYPE_UNKNOWN;
mce_err->severity = MCE_SEV_ERROR_SYNC;
mce_err->initiator = MCE_INITIATOR_CPU;
+
+ return 0;
}
-static void mce_get_derror(struct pt_regs *regs,
+static int mce_handle_derror(struct pt_regs *regs,
const struct mce_derror_table table[],
struct mce_error_info *mce_err, uint64_t *addr)
{
/* P7 DD1 leaves top bits undefined */
uint64_t dsisr = regs->dsisr & 0x0000ffff;
+ int handled = 0;
+ int found = 0;
int i;
*addr = 0;
@@ -515,6 +428,29 @@ static void mce_get_derror(struct pt_regs *regs,
if (!(dsisr & table[i].dsisr_value))
continue;
+ switch (table[i].error_type) {
+ case MCE_ERROR_TYPE_SLB:
+ if (mce_flush(MCE_FLUSH_SLB))
+ handled = 1;
+ break;
+ case MCE_ERROR_TYPE_ERAT:
+ if (mce_flush(MCE_FLUSH_ERAT))
+ handled = 1;
+ break;
+ case MCE_ERROR_TYPE_TLB:
+ if (mce_flush(MCE_FLUSH_TLB))
+ handled = 1;
+ break;
+ }
+
+ /*
+ * Attempt to handle multiple conditions, but only return
+ * one. Ensure uncorrectable errors are first in the table
+ * to match first.
+ */
+ if (found)
+ continue;
+
mce_err->error_type = table[i].error_type;
switch (table[i].error_type) {
case MCE_ERROR_TYPE_UE:
@@ -546,12 +482,30 @@ static void mce_get_derror(struct pt_regs *regs,
else
*addr = regs->nip;
- return;
+ found = 1;
}
+ if (found)
+ return handled;
+
mce_err->error_type = MCE_ERROR_TYPE_UNKNOWN;
mce_err->severity = MCE_SEV_ERROR_SYNC;
mce_err->initiator = MCE_INITIATOR_CPU;
+
+ return 0;
+}
+
+static int mce_handle_error(struct pt_regs *regs,
+ const struct mce_derror_table dtable[],
+ const struct mce_ierror_table itable[],
+ struct mce_error_info *mce_err, uint64_t *addr)
+{
+ uint64_t srr1 = regs->msr;
+
+ if (SRR1_MC_LOADSTORE(srr1))
+ return mce_handle_derror(regs, dtable, mce_err, addr);
+ else
+ return mce_handle_ierror(regs, itable, mce_err, addr);
}
static long mce_handle_ue_error(struct pt_regs *regs)
@@ -572,172 +526,59 @@ static long mce_handle_ue_error(struct pt_regs *regs)
return handled;
}
-static long mce_handle_derror_p7(uint64_t dsisr)
-{
- return mce_handle_flush_derrors(dsisr,
- P7_DSISR_MC_SLB_ERRORS,
- P7_DSISR_MC_TLB_MULTIHIT_MFTLB,
- 0);
-}
-
-static long mce_handle_ierror_p7(uint64_t srr1)
-{
- switch (P7_SRR1_MC_IFETCH(srr1)) {
- case P7_SRR1_MC_IFETCH_SLB_PARITY:
- case P7_SRR1_MC_IFETCH_SLB_MULTIHIT:
- case P7_SRR1_MC_IFETCH_SLB_BOTH:
- return mce_flush(MCE_FLUSH_SLB);
-
- case P7_SRR1_MC_IFETCH_TLB_MULTIHIT:
- return mce_flush(MCE_FLUSH_TLB);
- default:
- return 0;
- }
-}
-
long __machine_check_early_realmode_p7(struct pt_regs *regs)
{
- uint64_t srr1, nip, addr;
- long handled = 1;
+ uint64_t addr;
+ long handled;
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
- * ifetch exception. Also, populate the mce error_type and
- * type-specific error_type from either SRR1 or DSISR, depending
- * whether this was a load/store or ifetch exception
- */
- if (P7_SRR1_MC_LOADSTORE(srr1)) {
- handled = mce_handle_derror_p7(regs->dsisr);
- mce_get_derror(regs, mce_p7_derror_table,
- &mce_error_info, &addr);
- } else {
- handled = mce_handle_ierror_p7(srr1);
- mce_get_ierror(regs, mce_p7_ierror_table,
+ handled = mce_handle_error(regs,
+ mce_p7_derror_table,
+ mce_p7_ierror_table,
&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;
-}
-
-static long mce_handle_ierror_p8(uint64_t srr1)
-{
- switch (P7_SRR1_MC_IFETCH(srr1)) {
- case P7_SRR1_MC_IFETCH_SLB_PARITY:
- case P7_SRR1_MC_IFETCH_SLB_MULTIHIT:
- case P8_SRR1_MC_IFETCH_ERAT_MULTIHIT:
- return mce_flush(MCE_FLUSH_SLB);
-
- case P7_SRR1_MC_IFETCH_TLB_MULTIHIT:
- return mce_flush(MCE_FLUSH_TLB);
- default:
- return 0;
- }
-}
+ save_mce_event(regs, handled, &mce_error_info, regs->nip, addr);
-static long mce_handle_derror_p8(uint64_t dsisr)
-{
- return mce_handle_flush_derrors(dsisr,
- P8_DSISR_MC_SLB_ERRORS,
- P7_DSISR_MC_TLB_MULTIHIT_MFTLB,
- 0);
+ return handled;
}
long __machine_check_early_realmode_p8(struct pt_regs *regs)
{
- uint64_t srr1, nip, addr;
- long handled = 1;
+ uint64_t addr;
+ long handled;
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);
- mce_get_derror(regs, mce_p8_derror_table,
+ handled = mce_handle_error(regs,
+ mce_p8_derror_table,
+ mce_p8_ierror_table,
&mce_error_info, &addr);
- } else {
- handled = mce_handle_ierror_p8(srr1);
- mce_get_ierror(regs, mce_p8_ierror_table,
- &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;
-}
-
-static int mce_handle_derror_p9(struct pt_regs *regs)
-{
- uint64_t dsisr = regs->dsisr;
-
-#if 0
- /* Could invalidate all tlbs then step over failing tlbie(l)? */
- if (dsisr & P9_DSISR_MC_USER_TLBIE) {
- regs->nip += 4;
- dsisr &= ~P9_DSISR_MC_USER_TLBIE;
- }
-#endif
-
- return mce_handle_flush_derrors(dsisr,
- P9_DSISR_MC_SLB_PARITY_MFSLB |
- P9_DSISR_MC_SLB_MULTIHIT_MFSLB,
-
- P9_DSISR_MC_TLB_MULTIHIT_MFTLB,
+ save_mce_event(regs, handled, &mce_error_info, regs->nip, addr);
- P9_DSISR_MC_ERAT_MULTIHIT);
-}
-
-static int mce_handle_ierror_p9(struct pt_regs *regs)
-{
- uint64_t srr1 = regs->msr;
-
- switch (P9_SRR1_MC_IFETCH(srr1)) {
- case P9_SRR1_MC_IFETCH_SLB_PARITY:
- case P9_SRR1_MC_IFETCH_SLB_MULTIHIT:
- return mce_flush(MCE_FLUSH_SLB);
- case P9_SRR1_MC_IFETCH_TLB_MULTIHIT:
- return mce_flush(MCE_FLUSH_TLB);
- case P9_SRR1_MC_IFETCH_ERAT_MULTIHIT:
- return mce_flush(MCE_FLUSH_ERAT);
- default:
- return 0;
- }
+ return handled;
}
long __machine_check_early_realmode_p9(struct pt_regs *regs)
{
- uint64_t nip, addr;
+ uint64_t addr;
long handled;
struct mce_error_info mce_error_info = { 0 };
- nip = regs->nip;
-
- if (P9_SRR1_MC_LOADSTORE(regs->msr)) {
- handled = mce_handle_derror_p9(regs);
- mce_get_derror(regs, mce_p9_derror_table,
- &mce_error_info, &addr);
- } else {
- handled = mce_handle_ierror_p9(regs);
- mce_get_ierror(regs, mce_p9_ierror_table,
+ handled = mce_handle_error(regs,
+ mce_p9_derror_table,
+ mce_p9_ierror_table,
&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);
+ save_mce_event(regs, handled, &mce_error_info, regs->nip, addr);
+
return handled;
}
--
2.11.0
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH 9/9] powerpc/64s: POWER8 add missing machine check definitions
2017-02-20 19:44 [PATCH 0/9] MCE handler for POWER9 Nicholas Piggin
` (7 preceding siblings ...)
2017-02-20 19:44 ` [PATCH 8/9] powerpc/64s: data driven machine check handling Nicholas Piggin
@ 2017-02-20 19:44 ` Nicholas Piggin
8 siblings, 0 replies; 10+ messages in thread
From: Nicholas Piggin @ 2017-02-20 19:44 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin, Michael Ellerman, Mahesh Salgaonkar
POWER8 uses bit 36 in SRR1 like POWER9 for i-side machine checks,
and contains several similar conditions for link timeouts that
are not currently handled.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/mce_power.c | 26 +++++++++++++++++++-------
1 file changed, 19 insertions(+), 7 deletions(-)
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index 3e4149a6d469..e7da3b7dedf3 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -184,27 +184,33 @@ static const struct mce_ierror_table mce_p7_ierror_table[] = {
{ 0, 0, 0, 0, 0, 0 } };
static const struct mce_ierror_table mce_p8_ierror_table[] = {
-{ 0x00000000001c0000, 0x0000000000040000, true,
+{ 0x00000000081c0000, 0x0000000000040000, true,
MCE_ERROR_TYPE_UE, MCE_UE_ERROR_IFETCH,
MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
-{ 0x00000000001c0000, 0x0000000000080000, true,
+{ 0x00000000081c0000, 0x0000000000080000, true,
MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY,
MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
-{ 0x00000000001c0000, 0x00000000000c0000, true,
+{ 0x00000000081c0000, 0x00000000000c0000, true,
MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT,
MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
-{ 0x00000000001c0000, 0x0000000000100000, true,
+{ 0x00000000081c0000, 0x0000000000100000, true,
MCE_ERROR_TYPE_ERAT,MCE_ERAT_ERROR_MULTIHIT,
MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
-{ 0x00000000001c0000, 0x0000000000140000, true,
+{ 0x00000000081c0000, 0x0000000000140000, true,
MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT,
MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
-{ 0x00000000001c0000, 0x0000000000180000, true,
+{ 0x00000000081c0000, 0x0000000000180000, true,
MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH,
MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
-{ 0x00000000001c0000, 0x00000000001c0000, true,
+{ 0x00000000081c0000, 0x00000000001c0000, true,
MCE_ERROR_TYPE_UE, MCE_UE_ERROR_IFETCH,
MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x0000000008000000, true,
+ MCE_ERROR_TYPE_LINK,MCE_LINK_ERROR_IFETCH_TIMEOUT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x0000000008040000, true,
+ MCE_ERROR_TYPE_LINK,MCE_LINK_ERROR_PAGE_TABLE_WALK_IFETCH_TIMEOUT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
{ 0, 0, 0, 0, 0, 0 } };
static const struct mce_ierror_table mce_p9_ierror_table[] = {
@@ -289,6 +295,12 @@ static const struct mce_derror_table mce_p8_derror_table[] = {
{ 0x00004000, true,
MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00002000, true,
+ MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_LOAD_TIMEOUT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
+{ 0x00001000, true,
+ MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_PAGE_TABLE_WALK_LOAD_STORE_TIMEOUT,
+ MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
{ 0x00000800, true,
MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT,
MCE_INITIATOR_CPU, MCE_SEV_ERROR_SYNC, },
--
2.11.0
^ permalink raw reply related [flat|nested] 10+ messages in thread