* [PATCH 01/13] powerpc/mce: Make machine_check_ue_event() static
2019-06-21 4:55 [PATCH 00/13] powerpc: implement machine check safe memcpy Santosh Sivaraj
@ 2019-06-21 4:55 ` Santosh Sivaraj
2019-06-21 4:55 ` [PATCH 02/13] powerpc/mce: Bug fixes for MCE handling in kernel space Santosh Sivaraj
` (11 subsequent siblings)
12 siblings, 0 replies; 21+ messages in thread
From: Santosh Sivaraj @ 2019-06-21 4:55 UTC (permalink / raw)
To: linuxppc-dev
Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
Chandan Rajendra, Reza Arbab
From: Reza Arbab <arbab@linux.ibm.com>
The function doesn't get used outside this file, so make it static.
Signed-off-by: Reza Arbab <arbab@linux.ibm.com>
---
arch/powerpc/kernel/mce.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index b18df633eae9..e78c4f18ea0a 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -33,7 +33,7 @@ static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT],
mce_ue_event_queue);
static void machine_check_process_queued_event(struct irq_work *work);
-void machine_check_ue_event(struct machine_check_event *evt);
+static void machine_check_ue_event(struct machine_check_event *evt);
static void machine_process_ue_event(struct work_struct *work);
static struct irq_work mce_event_process_work = {
@@ -203,7 +203,7 @@ void release_mce_event(void)
/*
* Queue up the MCE event which then can be handled later.
*/
-void machine_check_ue_event(struct machine_check_event *evt)
+static void machine_check_ue_event(struct machine_check_event *evt)
{
int index;
--
2.20.1
^ permalink raw reply related [flat|nested] 21+ messages in thread* [PATCH 02/13] powerpc/mce: Bug fixes for MCE handling in kernel space
2019-06-21 4:55 [PATCH 00/13] powerpc: implement machine check safe memcpy Santosh Sivaraj
2019-06-21 4:55 ` [PATCH 01/13] powerpc/mce: Make machine_check_ue_event() static Santosh Sivaraj
@ 2019-06-21 4:55 ` Santosh Sivaraj
2019-06-21 4:55 ` [PATCH 03/13] powerpc/mce: Add MCE notification chain Santosh Sivaraj
` (10 subsequent siblings)
12 siblings, 0 replies; 21+ messages in thread
From: Santosh Sivaraj @ 2019-06-21 4:55 UTC (permalink / raw)
To: linuxppc-dev
Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
Chandan Rajendra, Reza Arbab
From: Balbir Singh <bsingharora@gmail.com>
The code currently assumes PAGE_SHIFT as the shift value of
the pfn, this works correctly (mostly) for user space pages,
but the correct thing to do is
1. Extract the shift value returned via the pte-walk API's
2. Use the shift value to access the instruction address.
Note, the final physical address still use PAGE_SHIFT for
computation. handle_ierror() is not modified and handle_derror()
is modified just for extracting the correct instruction
address.
This is largely due to __find_linux_pte() returning pfn's
shifted by pdshift. The code is much more generic and can
handle shift values returned.
Fixes: ba41e1e1ccb9 ("powerpc/mce: Hookup derror (load/store) UE errors")
Signed-off-by: Balbir Singh <bsingharora@gmail.com>
[arbab@linux.ibm.com: Fixup pseries_do_memory_failure()]
---
arch/powerpc/include/asm/mce.h | 3 ++-
arch/powerpc/kernel/mce_power.c | 26 ++++++++++++++++----------
arch/powerpc/platforms/pseries/ras.c | 6 ++++--
3 files changed, 22 insertions(+), 13 deletions(-)
diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index a4c6a74ad2fb..94888a7025b3 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -209,7 +209,8 @@ extern void release_mce_event(void);
extern void machine_check_queue_event(void);
extern void machine_check_print_event_info(struct machine_check_event *evt,
bool user_mode, bool in_guest);
-unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr);
+unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr,
+ unsigned int *shift);
#ifdef CONFIG_PPC_BOOK3S_64
void flush_and_reload_slb(void);
#endif /* CONFIG_PPC_BOOK3S_64 */
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index e39536aad30d..04666c0b40a8 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -23,7 +23,8 @@
* Convert an address related to an mm to a PFN. NOTE: we are in real
* mode, we could potentially race with page table updates.
*/
-unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr)
+unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr,
+ unsigned int *shift)
{
pte_t *ptep;
unsigned long flags;
@@ -36,13 +37,15 @@ unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr)
local_irq_save(flags);
if (mm == current->mm)
- ptep = find_current_mm_pte(mm->pgd, addr, NULL, NULL);
+ ptep = find_current_mm_pte(mm->pgd, addr, NULL, shift);
else
- ptep = find_init_mm_pte(addr, NULL);
+ ptep = find_init_mm_pte(addr, shift);
local_irq_restore(flags);
if (!ptep || pte_special(*ptep))
return ULONG_MAX;
- return pte_pfn(*ptep);
+ if (!*shift)
+ *shift = PAGE_SHIFT;
+ return (pte_val(*ptep) & PTE_RPN_MASK) >> *shift;
}
/* flush SLBs and reload */
@@ -358,15 +361,16 @@ static int mce_find_instr_ea_and_pfn(struct pt_regs *regs, uint64_t *addr,
unsigned long pfn, instr_addr;
struct instruction_op op;
struct pt_regs tmp = *regs;
+ unsigned int shift;
- pfn = addr_to_pfn(regs, regs->nip);
+ pfn = addr_to_pfn(regs, regs->nip, &shift);
if (pfn != ULONG_MAX) {
- instr_addr = (pfn << PAGE_SHIFT) + (regs->nip & ~PAGE_MASK);
+ instr_addr = (pfn << shift) + (regs->nip & ((1 << shift) - 1));
instr = *(unsigned int *)(instr_addr);
if (!analyse_instr(&op, &tmp, instr)) {
- pfn = addr_to_pfn(regs, op.ea);
+ pfn = addr_to_pfn(regs, op.ea, &shift);
*addr = op.ea;
- *phys_addr = (pfn << PAGE_SHIFT);
+ *phys_addr = (pfn << shift);
return 0;
}
/*
@@ -442,12 +446,14 @@ static int mce_handle_ierror(struct pt_regs *regs,
if (mce_err->sync_error &&
table[i].error_type == MCE_ERROR_TYPE_UE) {
unsigned long pfn;
+ unsigned int shift;
if (get_paca()->in_mce < MAX_MCE_DEPTH) {
- pfn = addr_to_pfn(regs, regs->nip);
+ pfn = addr_to_pfn(regs, regs->nip,
+ &shift);
if (pfn != ULONG_MAX) {
*phys_addr =
- (pfn << PAGE_SHIFT);
+ (pfn << shift);
}
}
}
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index f16fdd0f71f7..5e43283d3300 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -740,12 +740,14 @@ static void pseries_do_memory_failure(struct pt_regs *regs,
paddr = be64_to_cpu(mce_log->logical_address);
} else if (mce_log->sub_err_type & UE_EFFECTIVE_ADDR_PROVIDED) {
unsigned long pfn;
+ unsigned int shift;
pfn = addr_to_pfn(regs,
- be64_to_cpu(mce_log->effective_address));
+ be64_to_cpu(mce_log->effective_address),
+ &shift);
if (pfn == ULONG_MAX)
return;
- paddr = pfn << PAGE_SHIFT;
+ paddr = pfn << shift;
} else {
return;
}
--
2.20.1
^ permalink raw reply related [flat|nested] 21+ messages in thread* [PATCH 03/13] powerpc/mce: Add MCE notification chain
2019-06-21 4:55 [PATCH 00/13] powerpc: implement machine check safe memcpy Santosh Sivaraj
2019-06-21 4:55 ` [PATCH 01/13] powerpc/mce: Make machine_check_ue_event() static Santosh Sivaraj
2019-06-21 4:55 ` [PATCH 02/13] powerpc/mce: Bug fixes for MCE handling in kernel space Santosh Sivaraj
@ 2019-06-21 4:55 ` Santosh Sivaraj
2019-06-21 4:55 ` [PATCH 04/13] powerpc/mce: Move machine_check_ue_event() call Santosh Sivaraj
` (9 subsequent siblings)
12 siblings, 0 replies; 21+ messages in thread
From: Santosh Sivaraj @ 2019-06-21 4:55 UTC (permalink / raw)
To: linuxppc-dev
Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
Chandan Rajendra, Reza Arbab
From: Reza Arbab <arbab@linux.ibm.com>
Signed-off-by: Reza Arbab <arbab@linux.ibm.com>
---
arch/powerpc/include/asm/asm-prototypes.h | 1 +
arch/powerpc/include/asm/mce.h | 4 ++++
arch/powerpc/kernel/exceptions-64s.S | 4 ++++
arch/powerpc/kernel/mce.c | 22 ++++++++++++++++++++++
4 files changed, 31 insertions(+)
diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
index ec1c97a8e8cb..f66f26ef3ce0 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -72,6 +72,7 @@ void machine_check_exception(struct pt_regs *regs);
void emulation_assist_interrupt(struct pt_regs *regs);
long do_slb_fault(struct pt_regs *regs, unsigned long ea);
void do_bad_slb_fault(struct pt_regs *regs, unsigned long ea, long err);
+void machine_check_notify(struct pt_regs *regs);
/* signals, syscalls and interrupts */
long sys_swapcontext(struct ucontext __user *old_ctx,
diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index 94888a7025b3..948bef579086 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -214,4 +214,8 @@ unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr,
#ifdef CONFIG_PPC_BOOK3S_64
void flush_and_reload_slb(void);
#endif /* CONFIG_PPC_BOOK3S_64 */
+
+int mce_register_notifier(struct notifier_block *nb);
+int mce_unregister_notifier(struct notifier_block *nb);
+
#endif /* __ASM_PPC64_MCE_H__ */
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 6b86055e5251..2e56014fca21 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -457,6 +457,10 @@ EXC_COMMON_BEGIN(machine_check_handle_early)
addi r3,r1,STACK_FRAME_OVERHEAD
bl machine_check_early
std r3,RESULT(r1) /* Save result */
+
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl machine_check_notify
+
ld r12,_MSR(r1)
BEGIN_FTR_SECTION
b 4f
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index e78c4f18ea0a..24d350a934e4 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -42,6 +42,18 @@ static struct irq_work mce_event_process_work = {
DECLARE_WORK(mce_ue_event_work, machine_process_ue_event);
+static BLOCKING_NOTIFIER_HEAD(mce_notifier_list);
+
+int mce_register_notifier(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_register(&mce_notifier_list, nb);
+}
+
+int mce_unregister_notifier(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_unregister(&mce_notifier_list, nb);
+}
+
static void mce_set_error_info(struct machine_check_event *mce,
struct mce_error_info *mce_err)
{
@@ -635,3 +647,13 @@ long hmi_exception_realmode(struct pt_regs *regs)
return 1;
}
+
+void machine_check_notify(struct pt_regs *regs)
+{
+ struct machine_check_event evt;
+
+ if (!get_mce_event(&evt, MCE_EVENT_DONTRELEASE))
+ return;
+
+ blocking_notifier_call_chain(&mce_notifier_list, 0, &evt);
+}
--
2.20.1
^ permalink raw reply related [flat|nested] 21+ messages in thread* [PATCH 04/13] powerpc/mce: Move machine_check_ue_event() call
2019-06-21 4:55 [PATCH 00/13] powerpc: implement machine check safe memcpy Santosh Sivaraj
` (2 preceding siblings ...)
2019-06-21 4:55 ` [PATCH 03/13] powerpc/mce: Add MCE notification chain Santosh Sivaraj
@ 2019-06-21 4:55 ` Santosh Sivaraj
2019-06-21 4:55 ` [PATCH 05/13] powerpc/mce: Allow notifier callback to handle MCE Santosh Sivaraj
` (8 subsequent siblings)
12 siblings, 0 replies; 21+ messages in thread
From: Santosh Sivaraj @ 2019-06-21 4:55 UTC (permalink / raw)
To: linuxppc-dev
Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
Chandan Rajendra, Reza Arbab
From: Reza Arbab <arbab@linux.ibm.com>
Move the call site of machine_check_ue_event() slightly later in the MCE
codepath. No functional change intended--this is prep for a later patch
to conditionally skip the call.
Signed-off-by: Reza Arbab <arbab@linux.ibm.com>
---
arch/powerpc/kernel/mce.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 24d350a934e4..0ab171b41ede 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -156,7 +156,6 @@ 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);
}
}
return;
@@ -656,4 +655,8 @@ void machine_check_notify(struct pt_regs *regs)
return;
blocking_notifier_call_chain(&mce_notifier_list, 0, &evt);
+
+ if (evt.error_type == MCE_ERROR_TYPE_UE &&
+ evt.u.ue_error.physical_address_provided)
+ machine_check_ue_event(&evt);
}
--
2.20.1
^ permalink raw reply related [flat|nested] 21+ messages in thread* [PATCH 05/13] powerpc/mce: Allow notifier callback to handle MCE
2019-06-21 4:55 [PATCH 00/13] powerpc: implement machine check safe memcpy Santosh Sivaraj
` (3 preceding siblings ...)
2019-06-21 4:55 ` [PATCH 04/13] powerpc/mce: Move machine_check_ue_event() call Santosh Sivaraj
@ 2019-06-21 4:55 ` Santosh Sivaraj
2019-06-21 7:05 ` Mahesh Jagannath Salgaonkar
2019-06-21 4:55 ` [PATCH 06/13] powerpc/mce: Do not process notifier-handled UE events Santosh Sivaraj
` (7 subsequent siblings)
12 siblings, 1 reply; 21+ messages in thread
From: Santosh Sivaraj @ 2019-06-21 4:55 UTC (permalink / raw)
To: linuxppc-dev
Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
Chandan Rajendra, Reza Arbab
From: Reza Arbab <arbab@linux.ibm.com>
If a notifier returns NOTIFY_STOP, consider the MCE handled, just as we
do when machine_check_early() returns 1.
Signed-off-by: Reza Arbab <arbab@linux.ibm.com>
---
arch/powerpc/include/asm/asm-prototypes.h | 2 +-
arch/powerpc/kernel/exceptions-64s.S | 3 +++
arch/powerpc/kernel/mce.c | 28 ++++++++++++++++-------
3 files changed, 24 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
index f66f26ef3ce0..49ee8f08de2a 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -72,7 +72,7 @@ void machine_check_exception(struct pt_regs *regs);
void emulation_assist_interrupt(struct pt_regs *regs);
long do_slb_fault(struct pt_regs *regs, unsigned long ea);
void do_bad_slb_fault(struct pt_regs *regs, unsigned long ea, long err);
-void machine_check_notify(struct pt_regs *regs);
+long machine_check_notify(struct pt_regs *regs);
/* signals, syscalls and interrupts */
long sys_swapcontext(struct ucontext __user *old_ctx,
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 2e56014fca21..c83e38a403fd 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -460,6 +460,9 @@ EXC_COMMON_BEGIN(machine_check_handle_early)
addi r3,r1,STACK_FRAME_OVERHEAD
bl machine_check_notify
+ ld r11,RESULT(r1)
+ or r3,r3,r11
+ std r3,RESULT(r1)
ld r12,_MSR(r1)
BEGIN_FTR_SECTION
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 0ab171b41ede..912efe58e0b1 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -647,16 +647,28 @@ long hmi_exception_realmode(struct pt_regs *regs)
return 1;
}
-void machine_check_notify(struct pt_regs *regs)
+long machine_check_notify(struct pt_regs *regs)
{
- struct machine_check_event evt;
+ int index = __this_cpu_read(mce_nest_count) - 1;
+ struct machine_check_event *evt;
+ int rc;
- if (!get_mce_event(&evt, MCE_EVENT_DONTRELEASE))
- return;
+ if (index < 0 || index >= MAX_MC_EVT)
+ return 0;
+
+ evt = this_cpu_ptr(&mce_event[index]);
- blocking_notifier_call_chain(&mce_notifier_list, 0, &evt);
+ rc = blocking_notifier_call_chain(&mce_notifier_list, 0, evt);
+ if (rc & NOTIFY_STOP_MASK) {
+ evt->disposition = MCE_DISPOSITION_RECOVERED;
+ regs->msr |= MSR_RI;
- if (evt.error_type == MCE_ERROR_TYPE_UE &&
- evt.u.ue_error.physical_address_provided)
- machine_check_ue_event(&evt);
+ return 1;
+ }
+
+ if (evt->error_type == MCE_ERROR_TYPE_UE &&
+ evt->u.ue_error.physical_address_provided)
+ machine_check_ue_event(evt);
+
+ return 0;
}
--
2.20.1
^ permalink raw reply related [flat|nested] 21+ messages in thread* Re: [PATCH 05/13] powerpc/mce: Allow notifier callback to handle MCE
2019-06-21 4:55 ` [PATCH 05/13] powerpc/mce: Allow notifier callback to handle MCE Santosh Sivaraj
@ 2019-06-21 7:05 ` Mahesh Jagannath Salgaonkar
2019-06-23 2:14 ` Reza Arbab
0 siblings, 1 reply; 21+ messages in thread
From: Mahesh Jagannath Salgaonkar @ 2019-06-21 7:05 UTC (permalink / raw)
To: Santosh Sivaraj, linuxppc-dev
Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
Chandan Rajendra, Reza Arbab
On 6/21/19 6:27 AM, Santosh Sivaraj wrote:
> From: Reza Arbab <arbab@linux.ibm.com>
>
> If a notifier returns NOTIFY_STOP, consider the MCE handled, just as we
> do when machine_check_early() returns 1.
>
> Signed-off-by: Reza Arbab <arbab@linux.ibm.com>
> ---
> arch/powerpc/include/asm/asm-prototypes.h | 2 +-
> arch/powerpc/kernel/exceptions-64s.S | 3 +++
> arch/powerpc/kernel/mce.c | 28 ++++++++++++++++-------
> 3 files changed, 24 insertions(+), 9 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
> index f66f26ef3ce0..49ee8f08de2a 100644
> --- a/arch/powerpc/include/asm/asm-prototypes.h
> +++ b/arch/powerpc/include/asm/asm-prototypes.h
> @@ -72,7 +72,7 @@ void machine_check_exception(struct pt_regs *regs);
> void emulation_assist_interrupt(struct pt_regs *regs);
> long do_slb_fault(struct pt_regs *regs, unsigned long ea);
> void do_bad_slb_fault(struct pt_regs *regs, unsigned long ea, long err);
> -void machine_check_notify(struct pt_regs *regs);
> +long machine_check_notify(struct pt_regs *regs);
>
> /* signals, syscalls and interrupts */
> long sys_swapcontext(struct ucontext __user *old_ctx,
> diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
> index 2e56014fca21..c83e38a403fd 100644
> --- a/arch/powerpc/kernel/exceptions-64s.S
> +++ b/arch/powerpc/kernel/exceptions-64s.S
> @@ -460,6 +460,9 @@ EXC_COMMON_BEGIN(machine_check_handle_early)
>
> addi r3,r1,STACK_FRAME_OVERHEAD
> bl machine_check_notify
> + ld r11,RESULT(r1)
> + or r3,r3,r11
> + std r3,RESULT(r1)
>
> ld r12,_MSR(r1)
> BEGIN_FTR_SECTION
> diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
> index 0ab171b41ede..912efe58e0b1 100644
> --- a/arch/powerpc/kernel/mce.c
> +++ b/arch/powerpc/kernel/mce.c
> @@ -647,16 +647,28 @@ long hmi_exception_realmode(struct pt_regs *regs)
> return 1;
> }
>
> -void machine_check_notify(struct pt_regs *regs)
> +long machine_check_notify(struct pt_regs *regs)
> {
> - struct machine_check_event evt;
> + int index = __this_cpu_read(mce_nest_count) - 1;
> + struct machine_check_event *evt;
> + int rc;
>
> - if (!get_mce_event(&evt, MCE_EVENT_DONTRELEASE))
> - return;
> + if (index < 0 || index >= MAX_MC_EVT)
> + return 0;
> +
> + evt = this_cpu_ptr(&mce_event[index]);
>
> - blocking_notifier_call_chain(&mce_notifier_list, 0, &evt);
> + rc = blocking_notifier_call_chain(&mce_notifier_list, 0, evt);
> + if (rc & NOTIFY_STOP_MASK) {
> + evt->disposition = MCE_DISPOSITION_RECOVERED;
> + regs->msr |= MSR_RI;
What is the reason for setting MSR_RI ? I don't think this is a good
idea. MSR_RI = 0 means system got MCE interrupt when SRR0 and SRR1
contents were live and was overwritten by MCE interrupt. Hence this
interrupt is unrecoverable irrespective of whether machine check handler
recovers from it or not.
Thanks,
-Mahesh.
^ permalink raw reply [flat|nested] 21+ messages in thread* Re: [PATCH 05/13] powerpc/mce: Allow notifier callback to handle MCE
2019-06-21 7:05 ` Mahesh Jagannath Salgaonkar
@ 2019-06-23 2:14 ` Reza Arbab
2019-06-24 5:19 ` Mahesh Jagannath Salgaonkar
0 siblings, 1 reply; 21+ messages in thread
From: Reza Arbab @ 2019-06-23 2:14 UTC (permalink / raw)
To: Mahesh Jagannath Salgaonkar
Cc: Santosh Sivaraj, Aneesh Kumar K.V, Mahesh Salgaonkar,
Nicholas Piggin, Chandan Rajendra, linuxppc-dev
Hi Mahesh,
On Fri, Jun 21, 2019 at 12:35:08PM +0530, Mahesh Jagannath Salgaonkar wrote:
>On 6/21/19 6:27 AM, Santosh Sivaraj wrote:
>> - blocking_notifier_call_chain(&mce_notifier_list, 0, &evt);
>> + rc = blocking_notifier_call_chain(&mce_notifier_list, 0, evt);
>> + if (rc & NOTIFY_STOP_MASK) {
>> + evt->disposition = MCE_DISPOSITION_RECOVERED;
>> + regs->msr |= MSR_RI;
>
>What is the reason for setting MSR_RI ? I don't think this is a good
>idea. MSR_RI = 0 means system got MCE interrupt when SRR0 and SRR1
>contents were live and was overwritten by MCE interrupt. Hence this
>interrupt is unrecoverable irrespective of whether machine check handler
>recovers from it or not.
Good catch! I think this is an artifact from when I was first trying to
get all this working.
Instead of setting MSR_RI, we should probably just check for it. Ie,
if ((rc & NOTIFY_STOP_MASK) && (regs->msr & MSR_RI)) {
evt->disposition = MCE_DISPOSITION_RECOVERED;
--
Reza Arbab
^ permalink raw reply [flat|nested] 21+ messages in thread* Re: [PATCH 05/13] powerpc/mce: Allow notifier callback to handle MCE
2019-06-23 2:14 ` Reza Arbab
@ 2019-06-24 5:19 ` Mahesh Jagannath Salgaonkar
0 siblings, 0 replies; 21+ messages in thread
From: Mahesh Jagannath Salgaonkar @ 2019-06-24 5:19 UTC (permalink / raw)
To: Reza Arbab
Cc: Santosh Sivaraj, Aneesh Kumar K.V, Mahesh Salgaonkar,
Nicholas Piggin, Chandan Rajendra, linuxppc-dev
On 6/23/19 7:44 AM, Reza Arbab wrote:
> Hi Mahesh,
>
> On Fri, Jun 21, 2019 at 12:35:08PM +0530, Mahesh Jagannath Salgaonkar
> wrote:
>> On 6/21/19 6:27 AM, Santosh Sivaraj wrote:
>>> - blocking_notifier_call_chain(&mce_notifier_list, 0, &evt);
>>> + rc = blocking_notifier_call_chain(&mce_notifier_list, 0, evt);
>>> + if (rc & NOTIFY_STOP_MASK) {
>>> + evt->disposition = MCE_DISPOSITION_RECOVERED;
>>> + regs->msr |= MSR_RI;
>>
>> What is the reason for setting MSR_RI ? I don't think this is a good
>> idea. MSR_RI = 0 means system got MCE interrupt when SRR0 and SRR1
>> contents were live and was overwritten by MCE interrupt. Hence this
>> interrupt is unrecoverable irrespective of whether machine check handler
>> recovers from it or not.
>
> Good catch! I think this is an artifact from when I was first trying to
> get all this working.
>
> Instead of setting MSR_RI, we should probably just check for it. Ie,
>
> if ((rc & NOTIFY_STOP_MASK) && (regs->msr & MSR_RI)) {
> evt->disposition = MCE_DISPOSITION_RECOVERED;
Yup, looks good to me.
Thanks,
-Mahesh.
^ permalink raw reply [flat|nested] 21+ messages in thread
* [PATCH 06/13] powerpc/mce: Do not process notifier-handled UE events
2019-06-21 4:55 [PATCH 00/13] powerpc: implement machine check safe memcpy Santosh Sivaraj
` (4 preceding siblings ...)
2019-06-21 4:55 ` [PATCH 05/13] powerpc/mce: Allow notifier callback to handle MCE Santosh Sivaraj
@ 2019-06-21 4:55 ` Santosh Sivaraj
2019-06-21 4:55 ` [PATCH 07/13] powerpc/mce: Add fixup address to " Santosh Sivaraj
` (6 subsequent siblings)
12 siblings, 0 replies; 21+ messages in thread
From: Santosh Sivaraj @ 2019-06-21 4:55 UTC (permalink / raw)
To: linuxppc-dev
Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
Chandan Rajendra, Reza Arbab
From: Reza Arbab <arbab@linux.ibm.com>
Signed-off-by: Reza Arbab <arbab@linux.ibm.com>
---
arch/powerpc/include/asm/mce.h | 3 ++-
arch/powerpc/kernel/mce.c | 9 +++++++++
2 files changed, 11 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index 948bef579086..240dd1fdfe35 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 process_event;
+ u8 reserved_1[4];
u64 effective_address;
u64 physical_address;
u8 reserved_2[8];
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 912efe58e0b1..2616f1f71734 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -157,6 +157,8 @@ void save_mce_event(struct pt_regs *regs, long handled,
mce->u.ue_error.physical_address_provided = true;
mce->u.ue_error.physical_address = phys_addr;
}
+
+ mce->u.ue_error.process_event = true;
}
return;
}
@@ -241,6 +243,10 @@ void machine_check_queue_event(void)
if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
return;
+ if (evt.error_type == MCE_ERROR_TYPE_UE &&
+ !evt.u.ue_error.process_event)
+ return;
+
index = __this_cpu_inc_return(mce_queue_count) - 1;
/* If queue is full, just return for now. */
if (index >= MAX_MC_EVT) {
@@ -660,6 +666,9 @@ long machine_check_notify(struct pt_regs *regs)
rc = blocking_notifier_call_chain(&mce_notifier_list, 0, evt);
if (rc & NOTIFY_STOP_MASK) {
+ if (evt->error_type == MCE_ERROR_TYPE_UE)
+ evt->u.ue_error.process_event = false;
+
evt->disposition = MCE_DISPOSITION_RECOVERED;
regs->msr |= MSR_RI;
--
2.20.1
^ permalink raw reply related [flat|nested] 21+ messages in thread* [PATCH 07/13] powerpc/mce: Add fixup address to UE events
2019-06-21 4:55 [PATCH 00/13] powerpc: implement machine check safe memcpy Santosh Sivaraj
` (5 preceding siblings ...)
2019-06-21 4:55 ` [PATCH 06/13] powerpc/mce: Do not process notifier-handled UE events Santosh Sivaraj
@ 2019-06-21 4:55 ` Santosh Sivaraj
2019-06-21 4:55 ` [PATCH 08/13] powerpc/memcpy: Add memcpy_mcsafe for pmem Santosh Sivaraj
` (5 subsequent siblings)
12 siblings, 0 replies; 21+ messages in thread
From: Santosh Sivaraj @ 2019-06-21 4:55 UTC (permalink / raw)
To: linuxppc-dev
Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
Chandan Rajendra, Reza Arbab
From: Reza Arbab <arbab@linux.ibm.com>
If the instruction causing a UE has an exception table entry with fixup
address, save it in the machine_check_event struct.
If a machine check notifier callback returns NOTIFY_STOP to indicate it
has handled the error, set nip to continue execution from the fixup
address.
Signed-off-by: Reza Arbab <arbab@linux.ibm.com>
---
arch/powerpc/include/asm/mce.h | 5 +++--
arch/powerpc/kernel/mce.c | 16 +++++++++++++++-
2 files changed, 18 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index 240dd1fdfe35..9d9661747adf 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -122,11 +122,12 @@ struct machine_check_event {
enum MCE_UeErrorType ue_error_type:8;
u8 effective_address_provided;
u8 physical_address_provided;
+ u8 fixup_address_provided;
u8 process_event;
- u8 reserved_1[4];
+ u8 reserved_1[3];
u64 effective_address;
u64 physical_address;
- u8 reserved_2[8];
+ u64 fixup_address;
} ue_error;
struct {
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 2616f1f71734..8afda1ab7358 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -15,10 +15,12 @@
#include <linux/percpu.h>
#include <linux/export.h>
#include <linux/irq_work.h>
+#include <linux/extable.h>
#include <asm/machdep.h>
#include <asm/mce.h>
#include <asm/nmi.h>
+#include <asm/extable.h>
static DEFINE_PER_CPU(int, mce_nest_count);
static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event);
@@ -151,6 +153,8 @@ void save_mce_event(struct pt_regs *regs, long handled,
mce->u.link_error.effective_address_provided = true;
mce->u.link_error.effective_address = addr;
} else if (mce->error_type == MCE_ERROR_TYPE_UE) {
+ const struct exception_table_entry *entry;
+
mce->u.ue_error.effective_address_provided = true;
mce->u.ue_error.effective_address = addr;
if (phys_addr != ULONG_MAX) {
@@ -158,6 +162,12 @@ void save_mce_event(struct pt_regs *regs, long handled,
mce->u.ue_error.physical_address = phys_addr;
}
+ entry = search_exception_tables(regs->nip);
+ if (entry) {
+ mce->u.ue_error.fixup_address_provided = true;
+ mce->u.ue_error.fixup_address = extable_fixup(entry);
+ }
+
mce->u.ue_error.process_event = true;
}
return;
@@ -666,8 +676,12 @@ long machine_check_notify(struct pt_regs *regs)
rc = blocking_notifier_call_chain(&mce_notifier_list, 0, evt);
if (rc & NOTIFY_STOP_MASK) {
- if (evt->error_type == MCE_ERROR_TYPE_UE)
+ if (evt->error_type == MCE_ERROR_TYPE_UE) {
+ if (evt->u.ue_error.fixup_address_provided)
+ regs->nip = evt->u.ue_error.fixup_address;
+
evt->u.ue_error.process_event = false;
+ }
evt->disposition = MCE_DISPOSITION_RECOVERED;
regs->msr |= MSR_RI;
--
2.20.1
^ permalink raw reply related [flat|nested] 21+ messages in thread* [PATCH 08/13] powerpc/memcpy: Add memcpy_mcsafe for pmem
2019-06-21 4:55 [PATCH 00/13] powerpc: implement machine check safe memcpy Santosh Sivaraj
` (6 preceding siblings ...)
2019-06-21 4:55 ` [PATCH 07/13] powerpc/mce: Add fixup address to " Santosh Sivaraj
@ 2019-06-21 4:55 ` Santosh Sivaraj
2019-06-29 8:55 ` christophe leroy
2019-06-21 4:55 ` [PATCH 09/13] powerpc/mce: Handle memcpy_mcsafe() Santosh Sivaraj
` (4 subsequent siblings)
12 siblings, 1 reply; 21+ messages in thread
From: Santosh Sivaraj @ 2019-06-21 4:55 UTC (permalink / raw)
To: linuxppc-dev
Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
Chandan Rajendra, Reza Arbab
From: Balbir Singh <bsingharora@gmail.com>
The pmem infrastructure uses memcpy_mcsafe in the pmem
layer so as to convert machine check exceptions into
a return value on failure in case a machine check
exception is encountered during the memcpy.
This patch largely borrows from the copyuser_power7
logic and does not add the VMX optimizations, largely
to keep the patch simple. If needed those optimizations
can be folded in.
Signed-off-by: Balbir Singh <bsingharora@gmail.com>
Acked-by: Nicholas Piggin <npiggin@gmail.com>
[arbab@linux.ibm.com: Added symbol export]
---
arch/powerpc/include/asm/string.h | 2 +
arch/powerpc/lib/Makefile | 2 +-
arch/powerpc/lib/memcpy_mcsafe_64.S | 215 ++++++++++++++++++++++++++++
3 files changed, 218 insertions(+), 1 deletion(-)
create mode 100644 arch/powerpc/lib/memcpy_mcsafe_64.S
diff --git a/arch/powerpc/include/asm/string.h b/arch/powerpc/include/asm/string.h
index 9bf6dffb4090..b72692702f35 100644
--- a/arch/powerpc/include/asm/string.h
+++ b/arch/powerpc/include/asm/string.h
@@ -53,7 +53,9 @@ void *__memmove(void *to, const void *from, __kernel_size_t n);
#ifndef CONFIG_KASAN
#define __HAVE_ARCH_MEMSET32
#define __HAVE_ARCH_MEMSET64
+#define __HAVE_ARCH_MEMCPY_MCSAFE
+extern int memcpy_mcsafe(void *dst, const void *src, __kernel_size_t sz);
extern void *__memset16(uint16_t *, uint16_t v, __kernel_size_t);
extern void *__memset32(uint32_t *, uint32_t v, __kernel_size_t);
extern void *__memset64(uint64_t *, uint64_t v, __kernel_size_t);
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index c55f9c27bf79..529d6536eb4a 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -39,7 +39,7 @@ obj-$(CONFIG_PPC_BOOK3S_64) += copyuser_power7.o copypage_power7.o \
memcpy_power7.o
obj64-y += copypage_64.o copyuser_64.o mem_64.o hweight_64.o \
- memcpy_64.o pmem.o
+ memcpy_64.o pmem.o memcpy_mcsafe_64.o
obj64-$(CONFIG_SMP) += locks.o
obj64-$(CONFIG_ALTIVEC) += vmx-helper.o
diff --git a/arch/powerpc/lib/memcpy_mcsafe_64.S b/arch/powerpc/lib/memcpy_mcsafe_64.S
new file mode 100644
index 000000000000..50f865db0338
--- /dev/null
+++ b/arch/powerpc/lib/memcpy_mcsafe_64.S
@@ -0,0 +1,215 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) IBM Corporation, 2011
+ * Derived from copyuser_power7.s by Anton Blanchard <anton@au.ibm.com>
+ * Author - Balbir Singh <bsingharora@gmail.com>
+ */
+#include <asm/ppc_asm.h>
+#include <asm/errno.h>
+#include <asm/export.h>
+
+ .macro err1
+100:
+ EX_TABLE(100b,.Ldo_err1)
+ .endm
+
+ .macro err2
+200:
+ EX_TABLE(200b,.Ldo_err2)
+ .endm
+
+.Ldo_err2:
+ ld r22,STK_REG(R22)(r1)
+ ld r21,STK_REG(R21)(r1)
+ ld r20,STK_REG(R20)(r1)
+ ld r19,STK_REG(R19)(r1)
+ ld r18,STK_REG(R18)(r1)
+ ld r17,STK_REG(R17)(r1)
+ ld r16,STK_REG(R16)(r1)
+ ld r15,STK_REG(R15)(r1)
+ ld r14,STK_REG(R14)(r1)
+ addi r1,r1,STACKFRAMESIZE
+.Ldo_err1:
+ li r3,-EFAULT
+ blr
+
+
+_GLOBAL(memcpy_mcsafe)
+ cmpldi r5,16
+ blt .Lshort_copy
+
+.Lcopy:
+ /* Get the source 8B aligned */
+ neg r6,r4
+ mtocrf 0x01,r6
+ clrldi r6,r6,(64-3)
+
+ bf cr7*4+3,1f
+err1; lbz r0,0(r4)
+ addi r4,r4,1
+err1; stb r0,0(r3)
+ addi r3,r3,1
+
+1: bf cr7*4+2,2f
+err1; lhz r0,0(r4)
+ addi r4,r4,2
+err1; sth r0,0(r3)
+ addi r3,r3,2
+
+2: bf cr7*4+1,3f
+err1; lwz r0,0(r4)
+ addi r4,r4,4
+err1; stw r0,0(r3)
+ addi r3,r3,4
+
+3: sub r5,r5,r6
+ cmpldi r5,128
+ blt 5f
+
+ mflr r0
+ stdu r1,-STACKFRAMESIZE(r1)
+ std r14,STK_REG(R14)(r1)
+ std r15,STK_REG(R15)(r1)
+ std r16,STK_REG(R16)(r1)
+ std r17,STK_REG(R17)(r1)
+ std r18,STK_REG(R18)(r1)
+ std r19,STK_REG(R19)(r1)
+ std r20,STK_REG(R20)(r1)
+ std r21,STK_REG(R21)(r1)
+ std r22,STK_REG(R22)(r1)
+ std r0,STACKFRAMESIZE+16(r1)
+
+ srdi r6,r5,7
+ mtctr r6
+
+ /* Now do cacheline (128B) sized loads and stores. */
+ .align 5
+4:
+err2; ld r0,0(r4)
+err2; ld r6,8(r4)
+err2; ld r7,16(r4)
+err2; ld r8,24(r4)
+err2; ld r9,32(r4)
+err2; ld r10,40(r4)
+err2; ld r11,48(r4)
+err2; ld r12,56(r4)
+err2; ld r14,64(r4)
+err2; ld r15,72(r4)
+err2; ld r16,80(r4)
+err2; ld r17,88(r4)
+err2; ld r18,96(r4)
+err2; ld r19,104(r4)
+err2; ld r20,112(r4)
+err2; ld r21,120(r4)
+ addi r4,r4,128
+err2; std r0,0(r3)
+err2; std r6,8(r3)
+err2; std r7,16(r3)
+err2; std r8,24(r3)
+err2; std r9,32(r3)
+err2; std r10,40(r3)
+err2; std r11,48(r3)
+err2; std r12,56(r3)
+err2; std r14,64(r3)
+err2; std r15,72(r3)
+err2; std r16,80(r3)
+err2; std r17,88(r3)
+err2; std r18,96(r3)
+err2; std r19,104(r3)
+err2; std r20,112(r3)
+err2; std r21,120(r3)
+ addi r3,r3,128
+ bdnz 4b
+
+ clrldi r5,r5,(64-7)
+
+ ld r14,STK_REG(R14)(r1)
+ ld r15,STK_REG(R15)(r1)
+ ld r16,STK_REG(R16)(r1)
+ ld r17,STK_REG(R17)(r1)
+ ld r18,STK_REG(R18)(r1)
+ ld r19,STK_REG(R19)(r1)
+ ld r20,STK_REG(R20)(r1)
+ ld r21,STK_REG(R21)(r1)
+ ld r22,STK_REG(R22)(r1)
+ addi r1,r1,STACKFRAMESIZE
+
+ /* Up to 127B to go */
+5: srdi r6,r5,4
+ mtocrf 0x01,r6
+
+6: bf cr7*4+1,7f
+err1; ld r0,0(r4)
+err1; ld r6,8(r4)
+err1; ld r7,16(r4)
+err1; ld r8,24(r4)
+err1; ld r9,32(r4)
+err1; ld r10,40(r4)
+err1; ld r11,48(r4)
+err1; ld r12,56(r4)
+ addi r4,r4,64
+err1; std r0,0(r3)
+err1; std r6,8(r3)
+err1; std r7,16(r3)
+err1; std r8,24(r3)
+err1; std r9,32(r3)
+err1; std r10,40(r3)
+err1; std r11,48(r3)
+err1; std r12,56(r3)
+ addi r3,r3,64
+
+ /* Up to 63B to go */
+7: bf cr7*4+2,8f
+err1; ld r0,0(r4)
+err1; ld r6,8(r4)
+err1; ld r7,16(r4)
+err1; ld r8,24(r4)
+ addi r4,r4,32
+err1; std r0,0(r3)
+err1; std r6,8(r3)
+err1; std r7,16(r3)
+err1; std r8,24(r3)
+ addi r3,r3,32
+
+ /* Up to 31B to go */
+8: bf cr7*4+3,9f
+err1; ld r0,0(r4)
+err1; ld r6,8(r4)
+ addi r4,r4,16
+err1; std r0,0(r3)
+err1; std r6,8(r3)
+ addi r3,r3,16
+
+9: clrldi r5,r5,(64-4)
+
+ /* Up to 15B to go */
+.Lshort_copy:
+ mtocrf 0x01,r5
+ bf cr7*4+0,12f
+err1; lwz r0,0(r4) /* Less chance of a reject with word ops */
+err1; lwz r6,4(r4)
+ addi r4,r4,8
+err1; stw r0,0(r3)
+err1; stw r6,4(r3)
+ addi r3,r3,8
+
+12: bf cr7*4+1,13f
+err1; lwz r0,0(r4)
+ addi r4,r4,4
+err1; stw r0,0(r3)
+ addi r3,r3,4
+
+13: bf cr7*4+2,14f
+err1; lhz r0,0(r4)
+ addi r4,r4,2
+err1; sth r0,0(r3)
+ addi r3,r3,2
+
+14: bf cr7*4+3,15f
+err1; lbz r0,0(r4)
+err1; stb r0,0(r3)
+
+15: li r3,0
+ blr
+
+EXPORT_SYMBOL_GPL(memcpy_mcsafe);
--
2.20.1
^ permalink raw reply related [flat|nested] 21+ messages in thread* Re: [PATCH 08/13] powerpc/memcpy: Add memcpy_mcsafe for pmem
2019-06-21 4:55 ` [PATCH 08/13] powerpc/memcpy: Add memcpy_mcsafe for pmem Santosh Sivaraj
@ 2019-06-29 8:55 ` christophe leroy
0 siblings, 0 replies; 21+ messages in thread
From: christophe leroy @ 2019-06-29 8:55 UTC (permalink / raw)
To: Santosh Sivaraj, linuxppc-dev
Cc: Aneesh Kumar K.V, Chandan Rajendra, Reza Arbab,
Mahesh Salgaonkar, Nicholas Piggin
Le 21/06/2019 à 06:55, Santosh Sivaraj a écrit :
> From: Balbir Singh <bsingharora@gmail.com>
>
> The pmem infrastructure uses memcpy_mcsafe in the pmem
> layer so as to convert machine check exceptions into
> a return value on failure in case a machine check
> exception is encountered during the memcpy.
>
> This patch largely borrows from the copyuser_power7
> logic and does not add the VMX optimizations, largely
> to keep the patch simple. If needed those optimizations
> can be folded in.
Could we avoid duplicating source code by using GAS macros to share
source code between copyuser_power7 and memcpy_mcsafe ?
Christophe
>
> Signed-off-by: Balbir Singh <bsingharora@gmail.com>
> Acked-by: Nicholas Piggin <npiggin@gmail.com>
> [arbab@linux.ibm.com: Added symbol export]
> ---
> arch/powerpc/include/asm/string.h | 2 +
> arch/powerpc/lib/Makefile | 2 +-
> arch/powerpc/lib/memcpy_mcsafe_64.S | 215 ++++++++++++++++++++++++++++
> 3 files changed, 218 insertions(+), 1 deletion(-)
> create mode 100644 arch/powerpc/lib/memcpy_mcsafe_64.S
>
> diff --git a/arch/powerpc/include/asm/string.h b/arch/powerpc/include/asm/string.h
> index 9bf6dffb4090..b72692702f35 100644
> --- a/arch/powerpc/include/asm/string.h
> +++ b/arch/powerpc/include/asm/string.h
> @@ -53,7 +53,9 @@ void *__memmove(void *to, const void *from, __kernel_size_t n);
> #ifndef CONFIG_KASAN
> #define __HAVE_ARCH_MEMSET32
> #define __HAVE_ARCH_MEMSET64
> +#define __HAVE_ARCH_MEMCPY_MCSAFE
>
> +extern int memcpy_mcsafe(void *dst, const void *src, __kernel_size_t sz);
> extern void *__memset16(uint16_t *, uint16_t v, __kernel_size_t);
> extern void *__memset32(uint32_t *, uint32_t v, __kernel_size_t);
> extern void *__memset64(uint64_t *, uint64_t v, __kernel_size_t);
> diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
> index c55f9c27bf79..529d6536eb4a 100644
> --- a/arch/powerpc/lib/Makefile
> +++ b/arch/powerpc/lib/Makefile
> @@ -39,7 +39,7 @@ obj-$(CONFIG_PPC_BOOK3S_64) += copyuser_power7.o copypage_power7.o \
> memcpy_power7.o
>
> obj64-y += copypage_64.o copyuser_64.o mem_64.o hweight_64.o \
> - memcpy_64.o pmem.o
> + memcpy_64.o pmem.o memcpy_mcsafe_64.o
>
> obj64-$(CONFIG_SMP) += locks.o
> obj64-$(CONFIG_ALTIVEC) += vmx-helper.o
> diff --git a/arch/powerpc/lib/memcpy_mcsafe_64.S b/arch/powerpc/lib/memcpy_mcsafe_64.S
> new file mode 100644
> index 000000000000..50f865db0338
> --- /dev/null
> +++ b/arch/powerpc/lib/memcpy_mcsafe_64.S
> @@ -0,0 +1,215 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +/*
> + * Copyright (C) IBM Corporation, 2011
> + * Derived from copyuser_power7.s by Anton Blanchard <anton@au.ibm.com>
> + * Author - Balbir Singh <bsingharora@gmail.com>
> + */
> +#include <asm/ppc_asm.h>
> +#include <asm/errno.h>
> +#include <asm/export.h>
> +
> + .macro err1
> +100:
> + EX_TABLE(100b,.Ldo_err1)
> + .endm
> +
> + .macro err2
> +200:
> + EX_TABLE(200b,.Ldo_err2)
> + .endm
> +
> +.Ldo_err2:
> + ld r22,STK_REG(R22)(r1)
> + ld r21,STK_REG(R21)(r1)
> + ld r20,STK_REG(R20)(r1)
> + ld r19,STK_REG(R19)(r1)
> + ld r18,STK_REG(R18)(r1)
> + ld r17,STK_REG(R17)(r1)
> + ld r16,STK_REG(R16)(r1)
> + ld r15,STK_REG(R15)(r1)
> + ld r14,STK_REG(R14)(r1)
> + addi r1,r1,STACKFRAMESIZE
> +.Ldo_err1:
> + li r3,-EFAULT
> + blr
> +
> +
> +_GLOBAL(memcpy_mcsafe)
> + cmpldi r5,16
> + blt .Lshort_copy
> +
> +.Lcopy:
> + /* Get the source 8B aligned */
> + neg r6,r4
> + mtocrf 0x01,r6
> + clrldi r6,r6,(64-3)
> +
> + bf cr7*4+3,1f
> +err1; lbz r0,0(r4)
> + addi r4,r4,1
> +err1; stb r0,0(r3)
> + addi r3,r3,1
> +
> +1: bf cr7*4+2,2f
> +err1; lhz r0,0(r4)
> + addi r4,r4,2
> +err1; sth r0,0(r3)
> + addi r3,r3,2
> +
> +2: bf cr7*4+1,3f
> +err1; lwz r0,0(r4)
> + addi r4,r4,4
> +err1; stw r0,0(r3)
> + addi r3,r3,4
> +
> +3: sub r5,r5,r6
> + cmpldi r5,128
> + blt 5f
> +
> + mflr r0
> + stdu r1,-STACKFRAMESIZE(r1)
> + std r14,STK_REG(R14)(r1)
> + std r15,STK_REG(R15)(r1)
> + std r16,STK_REG(R16)(r1)
> + std r17,STK_REG(R17)(r1)
> + std r18,STK_REG(R18)(r1)
> + std r19,STK_REG(R19)(r1)
> + std r20,STK_REG(R20)(r1)
> + std r21,STK_REG(R21)(r1)
> + std r22,STK_REG(R22)(r1)
> + std r0,STACKFRAMESIZE+16(r1)
> +
> + srdi r6,r5,7
> + mtctr r6
> +
> + /* Now do cacheline (128B) sized loads and stores. */
> + .align 5
> +4:
> +err2; ld r0,0(r4)
> +err2; ld r6,8(r4)
> +err2; ld r7,16(r4)
> +err2; ld r8,24(r4)
> +err2; ld r9,32(r4)
> +err2; ld r10,40(r4)
> +err2; ld r11,48(r4)
> +err2; ld r12,56(r4)
> +err2; ld r14,64(r4)
> +err2; ld r15,72(r4)
> +err2; ld r16,80(r4)
> +err2; ld r17,88(r4)
> +err2; ld r18,96(r4)
> +err2; ld r19,104(r4)
> +err2; ld r20,112(r4)
> +err2; ld r21,120(r4)
> + addi r4,r4,128
> +err2; std r0,0(r3)
> +err2; std r6,8(r3)
> +err2; std r7,16(r3)
> +err2; std r8,24(r3)
> +err2; std r9,32(r3)
> +err2; std r10,40(r3)
> +err2; std r11,48(r3)
> +err2; std r12,56(r3)
> +err2; std r14,64(r3)
> +err2; std r15,72(r3)
> +err2; std r16,80(r3)
> +err2; std r17,88(r3)
> +err2; std r18,96(r3)
> +err2; std r19,104(r3)
> +err2; std r20,112(r3)
> +err2; std r21,120(r3)
> + addi r3,r3,128
> + bdnz 4b
> +
> + clrldi r5,r5,(64-7)
> +
> + ld r14,STK_REG(R14)(r1)
> + ld r15,STK_REG(R15)(r1)
> + ld r16,STK_REG(R16)(r1)
> + ld r17,STK_REG(R17)(r1)
> + ld r18,STK_REG(R18)(r1)
> + ld r19,STK_REG(R19)(r1)
> + ld r20,STK_REG(R20)(r1)
> + ld r21,STK_REG(R21)(r1)
> + ld r22,STK_REG(R22)(r1)
> + addi r1,r1,STACKFRAMESIZE
> +
> + /* Up to 127B to go */
> +5: srdi r6,r5,4
> + mtocrf 0x01,r6
> +
> +6: bf cr7*4+1,7f
> +err1; ld r0,0(r4)
> +err1; ld r6,8(r4)
> +err1; ld r7,16(r4)
> +err1; ld r8,24(r4)
> +err1; ld r9,32(r4)
> +err1; ld r10,40(r4)
> +err1; ld r11,48(r4)
> +err1; ld r12,56(r4)
> + addi r4,r4,64
> +err1; std r0,0(r3)
> +err1; std r6,8(r3)
> +err1; std r7,16(r3)
> +err1; std r8,24(r3)
> +err1; std r9,32(r3)
> +err1; std r10,40(r3)
> +err1; std r11,48(r3)
> +err1; std r12,56(r3)
> + addi r3,r3,64
> +
> + /* Up to 63B to go */
> +7: bf cr7*4+2,8f
> +err1; ld r0,0(r4)
> +err1; ld r6,8(r4)
> +err1; ld r7,16(r4)
> +err1; ld r8,24(r4)
> + addi r4,r4,32
> +err1; std r0,0(r3)
> +err1; std r6,8(r3)
> +err1; std r7,16(r3)
> +err1; std r8,24(r3)
> + addi r3,r3,32
> +
> + /* Up to 31B to go */
> +8: bf cr7*4+3,9f
> +err1; ld r0,0(r4)
> +err1; ld r6,8(r4)
> + addi r4,r4,16
> +err1; std r0,0(r3)
> +err1; std r6,8(r3)
> + addi r3,r3,16
> +
> +9: clrldi r5,r5,(64-4)
> +
> + /* Up to 15B to go */
> +.Lshort_copy:
> + mtocrf 0x01,r5
> + bf cr7*4+0,12f
> +err1; lwz r0,0(r4) /* Less chance of a reject with word ops */
> +err1; lwz r6,4(r4)
> + addi r4,r4,8
> +err1; stw r0,0(r3)
> +err1; stw r6,4(r3)
> + addi r3,r3,8
> +
> +12: bf cr7*4+1,13f
> +err1; lwz r0,0(r4)
> + addi r4,r4,4
> +err1; stw r0,0(r3)
> + addi r3,r3,4
> +
> +13: bf cr7*4+2,14f
> +err1; lhz r0,0(r4)
> + addi r4,r4,2
> +err1; sth r0,0(r3)
> + addi r3,r3,2
> +
> +14: bf cr7*4+3,15f
> +err1; lbz r0,0(r4)
> +err1; stb r0,0(r3)
> +
> +15: li r3,0
> + blr
> +
> +EXPORT_SYMBOL_GPL(memcpy_mcsafe);
>
---
L'absence de virus dans ce courrier électronique a été vérifiée par le logiciel antivirus Avast.
https://www.avast.com/antivirus
^ permalink raw reply [flat|nested] 21+ messages in thread
* [PATCH 09/13] powerpc/mce: Handle memcpy_mcsafe()
2019-06-21 4:55 [PATCH 00/13] powerpc: implement machine check safe memcpy Santosh Sivaraj
` (7 preceding siblings ...)
2019-06-21 4:55 ` [PATCH 08/13] powerpc/memcpy: Add memcpy_mcsafe for pmem Santosh Sivaraj
@ 2019-06-21 4:55 ` Santosh Sivaraj
2019-06-21 4:55 ` [PATCH 10/13] powerpc/mce: Enable MCE notifiers in external modules Santosh Sivaraj
` (3 subsequent siblings)
12 siblings, 0 replies; 21+ messages in thread
From: Santosh Sivaraj @ 2019-06-21 4:55 UTC (permalink / raw)
To: linuxppc-dev
Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
Chandan Rajendra, Reza Arbab
From: Reza Arbab <arbab@linux.ibm.com>
Add an mce notifier intended to service memcpy_mcsafe().
The notifier uses this heuristic; if a UE occurs when accessing device
memory, and the faulting instruction had a fixup entry, the callback
will return NOTIFY_STOP.
This causes the notification mechanism to consider the MCE handled and
continue execution at the fixup address, which returns -EFAULT from the
memcpy_mcsafe() call.
Signed-off-by: Reza Arbab <arbab@linux.ibm.com>
---
arch/powerpc/kernel/mce.c | 34 ++++++++++++++++++++++++++++++++++
1 file changed, 34 insertions(+)
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 8afda1ab7358..9cb5a731377b 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -56,6 +56,40 @@ int mce_unregister_notifier(struct notifier_block *nb)
return blocking_notifier_chain_unregister(&mce_notifier_list, nb);
}
+static int check_memcpy_mcsafe(struct notifier_block *nb, unsigned long val,
+ void *data)
+{
+ struct machine_check_event *evt = data;
+ unsigned long pfn;
+ struct page *page;
+
+ if (evt->error_type != MCE_ERROR_TYPE_UE ||
+ !evt->u.ue_error.physical_address_provided)
+ return NOTIFY_DONE;
+
+ pfn = evt->u.ue_error.physical_address >> PAGE_SHIFT;
+ page = pfn_to_page(pfn);
+ if (!page)
+ return NOTIFY_DONE;
+
+ /* HMM and PMEM */
+ if (is_zone_device_page(page) && evt->u.ue_error.fixup_address_provided)
+ return NOTIFY_STOP;
+
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block memcpy_mcsafe_nb = {
+ .notifier_call = check_memcpy_mcsafe
+};
+
+static int __init mce_mcsafe_register(void)
+{
+ mce_register_notifier(&memcpy_mcsafe_nb);
+ return 0;
+}
+arch_initcall(mce_mcsafe_register);
+
static void mce_set_error_info(struct machine_check_event *mce,
struct mce_error_info *mce_err)
{
--
2.20.1
^ permalink raw reply related [flat|nested] 21+ messages in thread* [PATCH 10/13] powerpc/mce: Enable MCE notifiers in external modules
2019-06-21 4:55 [PATCH 00/13] powerpc: implement machine check safe memcpy Santosh Sivaraj
` (8 preceding siblings ...)
2019-06-21 4:55 ` [PATCH 09/13] powerpc/mce: Handle memcpy_mcsafe() Santosh Sivaraj
@ 2019-06-21 4:55 ` Santosh Sivaraj
2019-06-21 4:55 ` [PATCH 11/13] powerpc/64s: Save r13 in machine_check_common_early Santosh Sivaraj
` (2 subsequent siblings)
12 siblings, 0 replies; 21+ messages in thread
From: Santosh Sivaraj @ 2019-06-21 4:55 UTC (permalink / raw)
To: linuxppc-dev
Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
Chandan Rajendra, Reza Arbab
From: Reza Arbab <arbab@linux.ibm.com>
Signed-off-by: Reza Arbab <arbab@linux.ibm.com>
---
arch/powerpc/kernel/exceptions-64s.S | 6 ++++++
arch/powerpc/kernel/mce.c | 2 ++
2 files changed, 8 insertions(+)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index c83e38a403fd..311f1392a2ec 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -458,6 +458,12 @@ EXC_COMMON_BEGIN(machine_check_handle_early)
bl machine_check_early
std r3,RESULT(r1) /* Save result */
+ /* Notifiers may be in a module, so enable virtual addressing. */
+ mfmsr r11
+ ori r11,r11,MSR_IR
+ ori r11,r11,MSR_DR
+ mtmsr r11
+
addi r3,r1,STACK_FRAME_OVERHEAD
bl machine_check_notify
ld r11,RESULT(r1)
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 9cb5a731377b..413f7866a9c4 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -50,11 +50,13 @@ int mce_register_notifier(struct notifier_block *nb)
{
return blocking_notifier_chain_register(&mce_notifier_list, nb);
}
+EXPORT_SYMBOL_GPL(mce_register_notifier);
int mce_unregister_notifier(struct notifier_block *nb)
{
return blocking_notifier_chain_unregister(&mce_notifier_list, nb);
}
+EXPORT_SYMBOL_GPL(mce_unregister_notifier);
static int check_memcpy_mcsafe(struct notifier_block *nb, unsigned long val,
void *data)
--
2.20.1
^ permalink raw reply related [flat|nested] 21+ messages in thread* [PATCH 11/13] powerpc/64s: Save r13 in machine_check_common_early
2019-06-21 4:55 [PATCH 00/13] powerpc: implement machine check safe memcpy Santosh Sivaraj
` (9 preceding siblings ...)
2019-06-21 4:55 ` [PATCH 10/13] powerpc/mce: Enable MCE notifiers in external modules Santosh Sivaraj
@ 2019-06-21 4:55 ` Santosh Sivaraj
2019-06-21 11:47 ` Mahesh J Salgaonkar
2019-06-21 4:55 ` [PATCH 12/13] powerpc/memcpy_mcsafe: return remaining bytes Santosh Sivaraj
2019-06-21 4:55 ` [PATCH 13/13] powerpc: add machine check safe copy_to_user Santosh Sivaraj
12 siblings, 1 reply; 21+ messages in thread
From: Santosh Sivaraj @ 2019-06-21 4:55 UTC (permalink / raw)
To: linuxppc-dev
Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
Chandan Rajendra, Reza Arbab
From: Reza Arbab <arbab@linux.ibm.com>
Testing my memcpy_mcsafe() work in progress with an injected UE, I get
an error like this immediately after the function returns:
BUG: Unable to handle kernel data access at 0x7fff84dec8f8
Faulting instruction address: 0xc0080000009c00b0
Oops: Kernel access of bad area, sig: 11 [#1]
LE PAGE_SIZE=64K MMU=Radix MMU=Hash SMP NR_CPUS=2048 NUMA PowerNV
Modules linked in: mce(O+) vmx_crypto crc32c_vpmsum
CPU: 0 PID: 1375 Comm: modprobe Tainted: G O 5.1.0-rc6 #267
NIP: c0080000009c00b0 LR: c0080000009c00a8 CTR: c000000000095f90
REGS: c0000000ee197790 TRAP: 0300 Tainted: G O (5.1.0-rc6)
MSR: 900000000280b033 <SF,HV,VEC,VSX,EE,FP,ME,IR,DR,RI,LE> CR: 88002826 XER: 00040000
CFAR: c000000000095f8c DAR: 00007fff84dec8f8 DSISR: 40000000 IRQMASK: 0
GPR00: 000000006c6c6568 c0000000ee197a20 c0080000009c8400 fffffffffffffff2
GPR04: c0080000009c02e0 0000000000000006 0000000000000000 c000000003c834c8
GPR08: 0080000000000000 776a6681b7fb5100 0000000000000000 c0080000009c01c8
GPR12: c000000000095f90 00007fff84debc00 000000004d071440 0000000000000000
GPR16: 0000000100000601 c0080000009e0000 c000000000c98dd8 c000000000c98d98
GPR20: c000000003bba970 c0080000009c04d0 c0080000009c0618 c0000000001e5820
GPR24: 0000000000000000 0000000000000100 0000000000000001 c000000003bba958
GPR28: c0080000009c02e8 c0080000009c0318 c0080000009c02e0 0000000000000000
NIP [c0080000009c00b0] cause_ue+0xa8/0xe8 [mce]
LR [c0080000009c00a8] cause_ue+0xa0/0xe8 [mce]
To fix, ensure that r13 is properly restored after an MCE.
Signed-off-by: Reza Arbab <arbab@linux.ibm.com>
---
arch/powerpc/kernel/exceptions-64s.S | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 311f1392a2ec..932d8d05892c 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -265,6 +265,7 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
EXC_REAL_END(machine_check, 0x200, 0x100)
EXC_VIRT_NONE(0x4200, 0x100)
TRAMP_REAL_BEGIN(machine_check_common_early)
+ SET_SCRATCH0(r13) /* save r13 */
EXCEPTION_PROLOG_1(PACA_EXMC, NOTEST, 0x200)
/*
* Register contents:
--
2.20.1
^ permalink raw reply related [flat|nested] 21+ messages in thread* Re: [PATCH 11/13] powerpc/64s: Save r13 in machine_check_common_early
2019-06-21 4:55 ` [PATCH 11/13] powerpc/64s: Save r13 in machine_check_common_early Santosh Sivaraj
@ 2019-06-21 11:47 ` Mahesh J Salgaonkar
2019-06-21 23:21 ` Nicholas Piggin
0 siblings, 1 reply; 21+ messages in thread
From: Mahesh J Salgaonkar @ 2019-06-21 11:47 UTC (permalink / raw)
To: Santosh Sivaraj
Cc: Aneesh Kumar K.V, linuxppc-dev, Nicholas Piggin,
Mahesh Salgaonkar, Chandan Rajendra, Reza Arbab
On 2019-06-21 06:27:15 Fri, Santosh Sivaraj wrote:
> From: Reza Arbab <arbab@linux.ibm.com>
>
> Testing my memcpy_mcsafe() work in progress with an injected UE, I get
> an error like this immediately after the function returns:
>
> BUG: Unable to handle kernel data access at 0x7fff84dec8f8
> Faulting instruction address: 0xc0080000009c00b0
> Oops: Kernel access of bad area, sig: 11 [#1]
> LE PAGE_SIZE=64K MMU=Radix MMU=Hash SMP NR_CPUS=2048 NUMA PowerNV
> Modules linked in: mce(O+) vmx_crypto crc32c_vpmsum
> CPU: 0 PID: 1375 Comm: modprobe Tainted: G O 5.1.0-rc6 #267
> NIP: c0080000009c00b0 LR: c0080000009c00a8 CTR: c000000000095f90
> REGS: c0000000ee197790 TRAP: 0300 Tainted: G O (5.1.0-rc6)
> MSR: 900000000280b033 <SF,HV,VEC,VSX,EE,FP,ME,IR,DR,RI,LE> CR: 88002826 XER: 00040000
> CFAR: c000000000095f8c DAR: 00007fff84dec8f8 DSISR: 40000000 IRQMASK: 0
> GPR00: 000000006c6c6568 c0000000ee197a20 c0080000009c8400 fffffffffffffff2
> GPR04: c0080000009c02e0 0000000000000006 0000000000000000 c000000003c834c8
> GPR08: 0080000000000000 776a6681b7fb5100 0000000000000000 c0080000009c01c8
> GPR12: c000000000095f90 00007fff84debc00 000000004d071440 0000000000000000
> GPR16: 0000000100000601 c0080000009e0000 c000000000c98dd8 c000000000c98d98
> GPR20: c000000003bba970 c0080000009c04d0 c0080000009c0618 c0000000001e5820
> GPR24: 0000000000000000 0000000000000100 0000000000000001 c000000003bba958
> GPR28: c0080000009c02e8 c0080000009c0318 c0080000009c02e0 0000000000000000
> NIP [c0080000009c00b0] cause_ue+0xa8/0xe8 [mce]
> LR [c0080000009c00a8] cause_ue+0xa0/0xe8 [mce]
>
> To fix, ensure that r13 is properly restored after an MCE.
>
> Signed-off-by: Reza Arbab <arbab@linux.ibm.com>
> ---
> arch/powerpc/kernel/exceptions-64s.S | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
> index 311f1392a2ec..932d8d05892c 100644
> --- a/arch/powerpc/kernel/exceptions-64s.S
> +++ b/arch/powerpc/kernel/exceptions-64s.S
> @@ -265,6 +265,7 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
> EXC_REAL_END(machine_check, 0x200, 0x100)
> EXC_VIRT_NONE(0x4200, 0x100)
> TRAMP_REAL_BEGIN(machine_check_common_early)
> + SET_SCRATCH0(r13) /* save r13 */
> EXCEPTION_PROLOG_1(PACA_EXMC, NOTEST, 0x200)
> /*
> * Register contents:
We do save r13 before we call machine_check_common_early(). I don't
think I understood clearly how this change fixes the issue you are
seeing. What am I missing here ?
Above change will push the paca pointer to scratch0 overwriting the
original saved r13.
EXC_REAL_BEGIN(machine_check, 0x200, 0x100)
/* This is moved out of line as it can be patched by FW, but
* some code path might still want to branch into the original
* vector
*/
SET_SCRATCH0(r13) /* save r13 */
EXCEPTION_PROLOG_0(PACA_EXMC)
BEGIN_FTR_SECTION
b machine_check_common_early
Thanks,
-Mahesh.
^ permalink raw reply [flat|nested] 21+ messages in thread
* Re: [PATCH 11/13] powerpc/64s: Save r13 in machine_check_common_early
2019-06-21 11:47 ` Mahesh J Salgaonkar
@ 2019-06-21 23:21 ` Nicholas Piggin
2019-06-23 2:33 ` Reza Arbab
0 siblings, 1 reply; 21+ messages in thread
From: Nicholas Piggin @ 2019-06-21 23:21 UTC (permalink / raw)
To: mahesh, Santosh Sivaraj
Cc: Aneesh Kumar K.V, linuxppc-dev, Mahesh Salgaonkar,
Chandan Rajendra, Reza Arbab
Mahesh J Salgaonkar's on June 21, 2019 9:47 pm:
> On 2019-06-21 06:27:15 Fri, Santosh Sivaraj wrote:
>> From: Reza Arbab <arbab@linux.ibm.com>
>>
>> Testing my memcpy_mcsafe() work in progress with an injected UE, I get
>> an error like this immediately after the function returns:
>>
>> BUG: Unable to handle kernel data access at 0x7fff84dec8f8
>> Faulting instruction address: 0xc0080000009c00b0
>> Oops: Kernel access of bad area, sig: 11 [#1]
>> LE PAGE_SIZE=64K MMU=Radix MMU=Hash SMP NR_CPUS=2048 NUMA PowerNV
>> Modules linked in: mce(O+) vmx_crypto crc32c_vpmsum
>> CPU: 0 PID: 1375 Comm: modprobe Tainted: G O 5.1.0-rc6 #267
>> NIP: c0080000009c00b0 LR: c0080000009c00a8 CTR: c000000000095f90
>> REGS: c0000000ee197790 TRAP: 0300 Tainted: G O (5.1.0-rc6)
>> MSR: 900000000280b033 <SF,HV,VEC,VSX,EE,FP,ME,IR,DR,RI,LE> CR: 88002826 XER: 00040000
>> CFAR: c000000000095f8c DAR: 00007fff84dec8f8 DSISR: 40000000 IRQMASK: 0
>> GPR00: 000000006c6c6568 c0000000ee197a20 c0080000009c8400 fffffffffffffff2
>> GPR04: c0080000009c02e0 0000000000000006 0000000000000000 c000000003c834c8
>> GPR08: 0080000000000000 776a6681b7fb5100 0000000000000000 c0080000009c01c8
>> GPR12: c000000000095f90 00007fff84debc00 000000004d071440 0000000000000000
>> GPR16: 0000000100000601 c0080000009e0000 c000000000c98dd8 c000000000c98d98
>> GPR20: c000000003bba970 c0080000009c04d0 c0080000009c0618 c0000000001e5820
>> GPR24: 0000000000000000 0000000000000100 0000000000000001 c000000003bba958
>> GPR28: c0080000009c02e8 c0080000009c0318 c0080000009c02e0 0000000000000000
>> NIP [c0080000009c00b0] cause_ue+0xa8/0xe8 [mce]
>> LR [c0080000009c00a8] cause_ue+0xa0/0xe8 [mce]
>>
>> To fix, ensure that r13 is properly restored after an MCE.
>>
>> Signed-off-by: Reza Arbab <arbab@linux.ibm.com>
>> ---
>> arch/powerpc/kernel/exceptions-64s.S | 1 +
>> 1 file changed, 1 insertion(+)
>>
>> diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
>> index 311f1392a2ec..932d8d05892c 100644
>> --- a/arch/powerpc/kernel/exceptions-64s.S
>> +++ b/arch/powerpc/kernel/exceptions-64s.S
>> @@ -265,6 +265,7 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
>> EXC_REAL_END(machine_check, 0x200, 0x100)
>> EXC_VIRT_NONE(0x4200, 0x100)
>> TRAMP_REAL_BEGIN(machine_check_common_early)
>> + SET_SCRATCH0(r13) /* save r13 */
>> EXCEPTION_PROLOG_1(PACA_EXMC, NOTEST, 0x200)
>> /*
>> * Register contents:
>
> We do save r13 before we call machine_check_common_early(). I don't
> think I understood clearly how this change fixes the issue you are
> seeing. What am I missing here ?
>
> Above change will push the paca pointer to scratch0 overwriting the
> original saved r13.
>
> EXC_REAL_BEGIN(machine_check, 0x200, 0x100)
> /* This is moved out of line as it can be patched by FW, but
> * some code path might still want to branch into the original
> * vector
> */
> SET_SCRATCH0(r13) /* save r13 */
> EXCEPTION_PROLOG_0(PACA_EXMC)
> BEGIN_FTR_SECTION
> b machine_check_common_early
Yep, from the stack trace, r13 is corrupted. So r13 must have got
corrupted before the machine check and this just happens to have
corrected it.
How does cause_ue work? It or memcpy_mcsafe must be corrupting
r13.
Thanks,
Nick
^ permalink raw reply [flat|nested] 21+ messages in thread
* Re: [PATCH 11/13] powerpc/64s: Save r13 in machine_check_common_early
2019-06-21 23:21 ` Nicholas Piggin
@ 2019-06-23 2:33 ` Reza Arbab
0 siblings, 0 replies; 21+ messages in thread
From: Reza Arbab @ 2019-06-23 2:33 UTC (permalink / raw)
To: Nicholas Piggin
Cc: Santosh Sivaraj, mahesh, Mahesh Salgaonkar, Chandan Rajendra,
Aneesh Kumar K.V, linuxppc-dev
On Sat, Jun 22, 2019 at 09:21:55AM +1000, Nicholas Piggin wrote:
>Yep, from the stack trace, r13 is corrupted. So r13 must have got
>corrupted before the machine check and this just happens to have
>corrected it.
>
>How does cause_ue work? It or memcpy_mcsafe must be corrupting
>r13.
Well, cause_ue() is just my little testcase using inject_mce_ue_on_addr
from skiboot/external/mambo/mambo_utils.tcl:
static noinline void cause_ue(void)
{
static const char src[] = "hello";
char dst[10];
int rc;
/* During the pause, break into mambo and run the following */
pr_info("inject_mce_ue_on_addr 0x%px\n", src);
pause(10);
rc = memcpy_mcsafe(dst, src, sizeof(src));
pr_info("memcpy_mcsafe() returns %d\n", rc);
if (!rc)
pr_info("dst=\"%s\"\n", dst);
}
I can't see how memcpy_mcsafe() would be causing it. I tried changing it
to save/restore r13 where it already does r14-r22, but that didn't make
a difference. Any ideas?
--
Reza Arbab
^ permalink raw reply [flat|nested] 21+ messages in thread
* [PATCH 12/13] powerpc/memcpy_mcsafe: return remaining bytes
2019-06-21 4:55 [PATCH 00/13] powerpc: implement machine check safe memcpy Santosh Sivaraj
` (10 preceding siblings ...)
2019-06-21 4:55 ` [PATCH 11/13] powerpc/64s: Save r13 in machine_check_common_early Santosh Sivaraj
@ 2019-06-21 4:55 ` Santosh Sivaraj
2019-06-21 4:55 ` [PATCH 13/13] powerpc: add machine check safe copy_to_user Santosh Sivaraj
12 siblings, 0 replies; 21+ messages in thread
From: Santosh Sivaraj @ 2019-06-21 4:55 UTC (permalink / raw)
To: linuxppc-dev
Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
Chandan Rajendra, Reza Arbab
memcpy_mcsafe currently return -EFAULT on a machine check exception, change
it to return the remaining bytes that needs to be copied, so that machine
check safe copy_to_user can maintain the same behavior as copy_to_user.
Signed-off-by: Santosh Sivaraj <santosh@fossix.org>
---
arch/powerpc/lib/memcpy_mcsafe_64.S | 129 +++++++++++++++-------------
1 file changed, 70 insertions(+), 59 deletions(-)
diff --git a/arch/powerpc/lib/memcpy_mcsafe_64.S b/arch/powerpc/lib/memcpy_mcsafe_64.S
index 50f865db0338..566c664aa640 100644
--- a/arch/powerpc/lib/memcpy_mcsafe_64.S
+++ b/arch/powerpc/lib/memcpy_mcsafe_64.S
@@ -30,11 +30,12 @@
ld r14,STK_REG(R14)(r1)
addi r1,r1,STACKFRAMESIZE
.Ldo_err1:
- li r3,-EFAULT
+ mr r3,r7
blr
_GLOBAL(memcpy_mcsafe)
+ mr r7,r5
cmpldi r5,16
blt .Lshort_copy
@@ -49,18 +50,21 @@ err1; lbz r0,0(r4)
addi r4,r4,1
err1; stb r0,0(r3)
addi r3,r3,1
+ subi r7,r7,1
1: bf cr7*4+2,2f
err1; lhz r0,0(r4)
addi r4,r4,2
err1; sth r0,0(r3)
addi r3,r3,2
+ subi r7,r7,2
2: bf cr7*4+1,3f
err1; lwz r0,0(r4)
addi r4,r4,4
err1; stw r0,0(r3)
addi r3,r3,4
+ subi r7,r7,4
3: sub r5,r5,r6
cmpldi r5,128
@@ -87,43 +91,69 @@ err1; stw r0,0(r3)
4:
err2; ld r0,0(r4)
err2; ld r6,8(r4)
-err2; ld r7,16(r4)
-err2; ld r8,24(r4)
-err2; ld r9,32(r4)
-err2; ld r10,40(r4)
-err2; ld r11,48(r4)
-err2; ld r12,56(r4)
-err2; ld r14,64(r4)
-err2; ld r15,72(r4)
-err2; ld r16,80(r4)
-err2; ld r17,88(r4)
-err2; ld r18,96(r4)
-err2; ld r19,104(r4)
-err2; ld r20,112(r4)
-err2; ld r21,120(r4)
+err2; ld r8,16(r4)
+err2; ld r9,24(r4)
+err2; ld r10,32(r4)
+err2; ld r11,40(r4)
+err2; ld r12,48(r4)
+err2; ld r14,56(r4)
+err2; ld r15,64(r4)
+err2; ld r16,72(r4)
+err2; ld r17,80(r4)
+err2; ld r18,88(r4)
+err2; ld r19,96(r4)
+err2; ld r20,104(r4)
+err2; ld r21,112(r4)
+err2; ld r22,120(r4)
addi r4,r4,128
err2; std r0,0(r3)
err2; std r6,8(r3)
-err2; std r7,16(r3)
-err2; std r8,24(r3)
-err2; std r9,32(r3)
-err2; std r10,40(r3)
-err2; std r11,48(r3)
-err2; std r12,56(r3)
-err2; std r14,64(r3)
-err2; std r15,72(r3)
-err2; std r16,80(r3)
-err2; std r17,88(r3)
-err2; std r18,96(r3)
-err2; std r19,104(r3)
-err2; std r20,112(r3)
-err2; std r21,120(r3)
+err2; std r8,16(r3)
+err2; std r9,24(r3)
+err2; std r10,32(r3)
+err2; std r11,40(r3)
+err2; std r12,48(r3)
+err2; std r14,56(r3)
+err2; std r15,64(r3)
+err2; std r16,72(r3)
+err2; std r17,80(r3)
+err2; std r18,88(r3)
+err2; std r19,96(r3)
+err2; std r20,104(r3)
+err2; std r21,112(r3)
+err2; std r22,120(r3)
addi r3,r3,128
+ subi r7,r7,128
bdnz 4b
clrldi r5,r5,(64-7)
- ld r14,STK_REG(R14)(r1)
+ /* Up to 127B to go */
+5: srdi r6,r5,4
+ mtocrf 0x01,r6
+
+6: bf cr7*4+1,7f
+err2; ld r0,0(r4)
+err2; ld r6,8(r4)
+err2; ld r8,16(r4)
+err2; ld r9,24(r4)
+err2; ld r10,32(r4)
+err2; ld r11,40(r4)
+err2; ld r12,48(r4)
+err2; ld r14,56(r4)
+ addi r4,r4,64
+err2; std r0,0(r3)
+err2; std r6,8(r3)
+err2; std r8,16(r3)
+err2; std r9,24(r3)
+err2; std r10,32(r3)
+err2; std r11,40(r3)
+err2; std r12,48(r3)
+err2; std r14,56(r3)
+ addi r3,r3,64
+ subi r7,r7,64
+
+7: ld r14,STK_REG(R14)(r1)
ld r15,STK_REG(R15)(r1)
ld r16,STK_REG(R16)(r1)
ld r17,STK_REG(R17)(r1)
@@ -134,42 +164,19 @@ err2; std r21,120(r3)
ld r22,STK_REG(R22)(r1)
addi r1,r1,STACKFRAMESIZE
- /* Up to 127B to go */
-5: srdi r6,r5,4
- mtocrf 0x01,r6
-
-6: bf cr7*4+1,7f
-err1; ld r0,0(r4)
-err1; ld r6,8(r4)
-err1; ld r7,16(r4)
-err1; ld r8,24(r4)
-err1; ld r9,32(r4)
-err1; ld r10,40(r4)
-err1; ld r11,48(r4)
-err1; ld r12,56(r4)
- addi r4,r4,64
-err1; std r0,0(r3)
-err1; std r6,8(r3)
-err1; std r7,16(r3)
-err1; std r8,24(r3)
-err1; std r9,32(r3)
-err1; std r10,40(r3)
-err1; std r11,48(r3)
-err1; std r12,56(r3)
- addi r3,r3,64
-
/* Up to 63B to go */
-7: bf cr7*4+2,8f
+ bf cr7*4+2,8f
err1; ld r0,0(r4)
err1; ld r6,8(r4)
-err1; ld r7,16(r4)
-err1; ld r8,24(r4)
+err1; ld r8,16(r4)
+err1; ld r9,24(r4)
addi r4,r4,32
err1; std r0,0(r3)
err1; std r6,8(r3)
-err1; std r7,16(r3)
-err1; std r8,24(r3)
+err1; std r8,16(r3)
+err1; std r9,24(r3)
addi r3,r3,32
+ subi r7,r7,32
/* Up to 31B to go */
8: bf cr7*4+3,9f
@@ -179,6 +186,7 @@ err1; ld r6,8(r4)
err1; std r0,0(r3)
err1; std r6,8(r3)
addi r3,r3,16
+ subi r7,r7,16
9: clrldi r5,r5,(64-4)
@@ -192,18 +200,21 @@ err1; lwz r6,4(r4)
err1; stw r0,0(r3)
err1; stw r6,4(r3)
addi r3,r3,8
+ subi r7,r7,8
12: bf cr7*4+1,13f
err1; lwz r0,0(r4)
addi r4,r4,4
err1; stw r0,0(r3)
addi r3,r3,4
+ subi r7,r7,4
13: bf cr7*4+2,14f
err1; lhz r0,0(r4)
addi r4,r4,2
err1; sth r0,0(r3)
addi r3,r3,2
+ subi r7,r7,2
14: bf cr7*4+3,15f
err1; lbz r0,0(r4)
--
2.20.1
^ permalink raw reply related [flat|nested] 21+ messages in thread* [PATCH 13/13] powerpc: add machine check safe copy_to_user
2019-06-21 4:55 [PATCH 00/13] powerpc: implement machine check safe memcpy Santosh Sivaraj
` (11 preceding siblings ...)
2019-06-21 4:55 ` [PATCH 12/13] powerpc/memcpy_mcsafe: return remaining bytes Santosh Sivaraj
@ 2019-06-21 4:55 ` Santosh Sivaraj
12 siblings, 0 replies; 21+ messages in thread
From: Santosh Sivaraj @ 2019-06-21 4:55 UTC (permalink / raw)
To: linuxppc-dev
Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
Chandan Rajendra, Reza Arbab
Use memcpy_mcsafe() implementation to define copy_to_user_mcsafe()
Signed-off-by: Santosh Sivaraj <santosh@fossix.org>
---
arch/powerpc/Kconfig | 1 +
arch/powerpc/include/asm/uaccess.h | 12 ++++++++++++
2 files changed, 13 insertions(+)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 8c1c636308c8..a173b392c272 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -134,6 +134,7 @@ config PPC
select ARCH_HAS_STRICT_KERNEL_RWX if ((PPC_BOOK3S_64 || PPC32) && !RELOCATABLE && !HIBERNATION)
select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
select ARCH_HAS_UACCESS_FLUSHCACHE if PPC64
+ select ARCH_HAS_UACCESS_MCSAFE if PPC64
select ARCH_HAS_UBSAN_SANITIZE_ALL
select ARCH_HAS_ZONE_DEVICE if PPC_BOOK3S_64
select ARCH_HAVE_NMI_SAFE_CMPXCHG
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index 76f34346b642..f8fcaab4c5bc 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -386,6 +386,18 @@ static inline unsigned long raw_copy_to_user(void __user *to,
return ret;
}
+static __always_inline unsigned long __must_check
+copy_to_user_mcsafe(void __user *to, const void *from, unsigned long n)
+{
+ if (likely(check_copy_size(from, n, true))) {
+ allow_write_to_user(to, n);
+ n = memcpy_mcsafe(to, from, n);
+ prevent_write_to_user(to, n);
+ }
+
+ return n;
+}
+
extern unsigned long __clear_user(void __user *addr, unsigned long size);
static inline unsigned long clear_user(void __user *addr, unsigned long size)
--
2.20.1
^ permalink raw reply related [flat|nested] 21+ messages in thread