powerpc: implement machine check safe memcpy
Subsystems (2)
v10 cover powerpc: implement machine check safe memcpy
During a memcpy from a pmem device, if a machine check exception is generated we end up in a panic. In case of fsdax read, this should only result in a -EIO. Avoid MCE by implementing memcpy_mcsafe.
Before this patch series:
``` bash-4.4# mount -o dax /dev/pmem0 /mnt/pmem/ [ 7621.714094] Disabling lock debugging due to kernel taint [ 7621.714099] MCE: CPU0: machine check (Severe) Host UE Load/Store [Not recovered] [ 7621.714104] MCE: CPU0: NIP: [c000000000088978] memcpy_power7+0x418/0x7e0 [ 7621.714107] MCE: CPU0: Hardware error [ 7621.714112] opal: Hardware platform error: Unrecoverable Machine Check exception [ 7621.714118] CPU: 0 PID: 1368 Comm: mount Tainted: G M 5.2.0-rc5-00239-g241e39004581 #50 [ 7621.714123] NIP: c000000000088978 LR: c0000000008e16f8 CTR: 00000000000001de [ 7621.714129] REGS: c0000000fffbfd70 TRAP: 0200 Tainted: G M (5.2.0-rc5-00239-g241e39004581) [ 7621.714131] MSR: 9000000002209033 <SF,HV,VEC,EE,ME,IR,DR,RI,LE> CR: 24428840 XER: 00040000 [ 7621.714160] CFAR: c0000000000889a8 DAR: deadbeefdeadbeef DSISR: 00008000 IRQMASK: 0 [ 7621.714171] GPR00: 000000000e000000 c0000000f0b8b1e0 c0000000012cf100 c0000000ed8e1100 [ 7621.714186] GPR04: c000020000001100 0000000000010000 0000000000000200 03fffffff1272000 [ 7621.714201] GPR08: 0000000080000000 0000000000000010 0000000000000020 0000000000000030 [ 7621.714216] GPR12: 0000000000000040 00007fffb8c6d390 0000000000000050 0000000000000060 [ 7621.714232] GPR16: 0000000000000070 0000000000000000 0000000000000001 c0000000f0b8b960 [ 7621.714247] GPR20: 0000000000000001 c0000000f0b8b940 0000000000000001 0000000000010000 [ 7621.714262] GPR24: c000000001382560 c00c0000003b6380 c00c0000003b6380 0000000000010000 [ 7621.714277] GPR28: 0000000000000000 0000000000010000 c000020000000000 0000000000010000 [ 7621.714294] NIP [c000000000088978] memcpy_power7+0x418/0x7e0 [ 7621.714298] LR [c0000000008e16f8] pmem_do_bvec+0xf8/0x430 ... <snip> ... ```
After this patch series:
``` bash-4.4# mount -o dax /dev/pmem0 /mnt/pmem/ [25302.883978] Buffer I/O error on dev pmem0, logical block 0, async page read [25303.020816] EXT4-fs (pmem0): DAX enabled. Warning: EXPERIMENTAL, use at your own risk [25303.021236] EXT4-fs (pmem0): Can't read superblock on 2nd try [25303.152515] EXT4-fs (pmem0): DAX enabled. Warning: EXPERIMENTAL, use at your own risk [25303.284031] EXT4-fs (pmem0): DAX enabled. Warning: EXPERIMENTAL, use at your own risk [25304.084100] UDF-fs: bad mount option "dax" or missing value mount: /mnt/pmem: wrong fs type, bad option, bad superblock on /dev/pmem0, missing codepage or helper program, or other error. ```
MCE is injected on a pmem address using mambo. The last patch which adds a nop is only for testing on mambo, where r13 is not restored upon hitting vector 200.
The memcpy code can be optimised by adding VMX optimizations and GAS macros can be used to enable code reusablity, which I will send as another series. --
v10: Fix authorship; add reviewed-bys and acks.
v9:
* Add a new IRQ work for UE events [mahesh]
* Reorder patches, and copy stable
v8:
* While ignoring UE events, return was used instead of continue.
* Checkpatch fixups for commit log
v7:
* Move schedule_work to be called from irq_work.
v6:
* Don't return pfn, all callees are expecting physical address anyway [nick]
* Patch re-ordering: move exception table patch before memcpy_mcsafe patch [nick]
* Reword commit log for search_exception_tables patch [nick]
v5:
* Don't use search_exception_tables since it searches for module exception tables also [Nicholas]
* Fix commit message for patch 2 [Nicholas]
v4:
* Squash return remaining bytes patch to memcpy_mcsafe implemtation patch [christophe]
* Access ok should be checked for copy_to_user_mcsafe() [christophe]
v3:
* Drop patch which enables DR/IR for external modules
* Drop notifier call chain, we don't want to do that in real mode
* Return remaining bytes from memcpy_mcsafe correctly
* We no longer restore r13 for simulator tests, rather use a nop at vector 0x200 [workaround for simulator; not to be merged]
v2:
* Don't set RI bit explicitly [mahesh]
* Re-ordered series to get r13 workaround as the last patch
--
Balbir Singh (3):
powerpc/mce: Fix MCE handling for huge pages
powerpc/memcpy: Add memcpy_mcsafe for pmem
powerpc/mce: Handle UE event for memcpy_mcsafe
Reza Arbab (1):
powerpc/mce: Make machine_check_ue_event() static
Santosh Sivaraj (3):
powerpc/mce: Schedule work from irq_work
extable: Add function to search only kernel exception table
powerpc: add machine check safe copy_to_user
arch/powerpc/Kconfig | 1 + arch/powerpc/include/asm/mce.h | 6 +- arch/powerpc/include/asm/string.h | 2 + arch/powerpc/include/asm/uaccess.h | 14 ++ arch/powerpc/kernel/mce.c | 31 +++- arch/powerpc/kernel/mce_power.c | 70 ++++---- arch/powerpc/lib/Makefile | 2 +- arch/powerpc/lib/memcpy_mcsafe_64.S | 242 +++++++++++++++++++++++++++ arch/powerpc/platforms/pseries/ras.c | 9 +- include/linux/extable.h | 2 + kernel/extable.c | 11 +- 11 files changed, 347 insertions(+), 43 deletions(-) create mode 100644 arch/powerpc/lib/memcpy_mcsafe_64.S
Signature · 1 line
2.21.0
PATCH v10 1/7 powerpc/mce: Schedule work from irq_work
schedule_work() cannot be called from MCE exception context as MCE can interrupt even in interrupt disabled context.
--- arch/powerpc/kernel/mce.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-)
arch/powerpc/kernel/mce.c +10 -1
@@ -33,6 +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); +static void machine_check_ue_irq_work (struct irq_work *work);void machine_check_ue_event (struct machine_check_event *evt);static void machine_process_ue_event (struct work_struct *work);
@@ -40,6 +41,10 @@ static struct irq_work mce_event_process_work = { .func = machine_check_process_queued_event, }; +static struct irq_work mce_ue_event_irq_work = { + .func = machine_check_ue_irq_work, +}; +DECLARE_WORK (mce_ue_event_work, machine_process_ue_event); static void mce_set_error_info(struct machine_check_event *mce,
@@ -199,6 +204,10 @@ void release_mce_event(void)get_mce_event (NULL , true); } +static void machine_check_ue_irq_work (struct irq_work *work) +{ +schedule_work (&mce_ue_event_work); +}/* * Queue up the MCE event which then can be handled later.
@@ -216,7 +225,7 @@ void machine_check_ue_event(struct machine_check_event *evt)memcpy (this_cpu_ptr (&mce_ue_event_queue[index]), evt,sizeof (*evt));/* Queue work to process this event later. */ -schedule_work (&mce_ue_event_work); +irq_work_queue (&mce_ue_event_irq_work); }/*
Signature · 1 line
2.21.0
Re: [PATCH v10 1/7] powerpc/mce: Schedule work from irq_work
Santosh Sivaraj's on August 15, 2019 10:39 am:
Quoted 2 lines
schedule_work()cannot be called from MCE exception context as MCE can interrupt even in interrupt disabled context.
The powernv code doesn't do this in general, rather defers kernel MCEs. My patch series converts the pseries machine check exception code over to the same.
However there remain special cases where that's not true for powernv, e.g., the machine check stack overflow or unrecoverable MCE paths try to force it through so something gets printed. We probably shouldn't even try to do memory failure in these cases.
Still, shouldn't hurt to make this change and fixes the existing "different" pseries code.
Thanks,
Nick
Quoted 6 lines
Fixes 733e4a4c ("powerpc/mce: hookup memory_failure for UE errors")Suggested-by Mahesh Salgaonkar <[email protected]>Signed-off-by Santosh Sivaraj <[email protected]>Reviewed-by Mahesh Salgaonkar <[email protected]>Acked-by Balbir Singh <[email protected]>Cc [email protected] # v4.15+
PATCH v10 2/7 powerpc/mce: Fix MCE handling for huge pages
In reply to Santosh SivarajFrom: Balbir Singh <[email protected]>
The current code would fail on huge pages addresses, since the shift would be incorrect. Use the correct page shift value returned by __find_linux_pte() to get the correct physical address. The code is more generic and can handle both regular and compound pages.
--- arch/powerpc/include/asm/mce.h | 2 +- arch/powerpc/kernel/mce_power.c | 55 ++++++++++++++-------------- arch/powerpc/platforms/pseries/ras.c | 9 ++--- 3 files changed, 32 insertions(+), 34 deletions(-)
arch/powerpc/include/asm/mce.h +1 -1
@@ -209,7 +209,7 @@ 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_phys (struct pt_regs *regs,unsigned long addr);#ifdef CONFIG_PPC_BOOK3S_64 void flush_and_reload_slb (void );#endif /* CONFIG_PPC_BOOK3S_64 */
arch/powerpc/kernel/mce_power.c +28 -27
102 lines not on this page · raw message
arch/powerpc/platforms/pseries/ras.c +3 -6
@@ -739,13 +739,10 @@ static void pseries_do_memory_failure(struct pt_regs *regs,if (mce_log->sub_err_type &UE_LOGICAL_ADDR_PROVIDED ) { paddr =be64_to_cpu (mce_log->logical_address); }else if (mce_log->sub_err_type &UE_EFFECTIVE_ADDR_PROVIDED ) { -unsigned long pfn; - - pfn =addr_to_pfn (regs, -be64_to_cpu (mce_log->effective_address)); -if (pfn ==ULONG_MAX ) + paddr =addr_to_phys (regs, +be64_to_cpu (mce_log->effective_address)); +if (paddr ==ULONG_MAX )return ; - paddr = pfn <<PAGE_SHIFT ; }else {return ; }
Signature · 1 line
2.21.0
Sasha Levin
maintainerRe: [PATCH v10 2/7] powerpc/mce: Fix MCE handling for huge pages
Hi,
[This is an automated email]
This commit has been processed because it contains a "Fixes:" tag, fixing commit: ba41e1e1ccb9 powerpc/mce: Hookup derror (load/store) UE errors.
The bot has tested the following trees: v5.2.8, v4.19.66.
v5.2.8: Build OK!
v4.19.66: Failed to apply! Possible dependencies:
360cae313702 ("KVM: PPC: Book3S HV: Nested guest entry via hypercall") 41f4e631daf8 ("KVM: PPC: Book3S HV: Extract PMU save/restore operations as C-callable functions") 884dfb722db8 ("KVM: PPC: Book3S HV: Simplify machine check handling") 89329c0be8bd ("KVM: PPC: Book3S HV: Clear partition table entry on vm teardown") 8e3f5fc1045d ("KVM: PPC: Book3S HV: Framework and hcall stubs for nested virtualization") 95a6432ce903 ("KVM: PPC: Book3S HV: Streamlined guest entry/exit path on P9 for radix guests") a43c1590426c ("powerpc/pseries: Flush SLB contents on SLB MCE errors.") c05772018491 ("powerpc/64s: Better printing of machine check info for guest MCEs") d24ea8a7336a ("KVM: PPC: Book3S: Simplify external interrupt handling") df709a296ef7 ("KVM: PPC: Book3S HV: Simplify real-mode interrupt handling") f7035ce9f1df ("KVM: PPC: Book3S HV: Move interrupt delivery on guest entry to C code")
NOTE: The patch will not be queued to stable trees until it is upstream.
How should we proceed with this patch?
--
Thanks,
Sasha
Nicholas Piggin
reviewerRe: [PATCH v10 2/7] powerpc/mce: Fix MCE handling for huge pages
In reply to Santosh SivarajSantosh Sivaraj's on August 15, 2019 10:39 am:
Quoted 73 lines
From: Balbir Singh <[email protected]>
The current code would fail on huge pages addresses, since the shift would be incorrect. Use the correct page shift value returned by
__find_linux_pte()to get the correct physical address. The code is more generic and can handle both regular and compound pages.Fixes ba41e1e1ccb9 ("powerpc/mce: Hookup derror (load/store) UE errors")Signed-off-by Balbir Singh <[email protected]>[[email protected]: Fixup pseries_do_memory_failure()]Signed-off-by Reza Arbab <[email protected]>Co-developed-by Santosh Sivaraj <[email protected]>Signed-off-by Santosh Sivaraj <[email protected]>Tested-by Mahesh Salgaonkar <[email protected]>Cc [email protected] # v4.15+--- arch/powerpc/include/asm/mce.h | 2 +- arch/powerpc/kernel/mce_power.c | 55 ++++++++++++++-------------- arch/powerpc/platforms/pseries/ras.c | 9 ++--- 3 files changed, 32 insertions(+), 34 deletions(-)arch/powerpc/include/asm/mce.h +1
-1@@ -209,7 +209,7 @@ 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_phys (struct pt_regs *regs,unsigned long addr);#ifdef CONFIG_PPC_BOOK3S_64 void flush_and_reload_slb (void );#endif /* CONFIG_PPC_BOOK3S_64 */ arch/powerpc/kernel/mce_power.c +9
-10@@ -20,13 +20,14 @@#include <asm/exception-64s.h> /* -* Convert an address related to an mm to a PFN. NOTE: we are in real -* mode, we could potentially race with page table updates. +* Convert an address related to an mm to a physical address. +* 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_phys (struct pt_regs *regs,unsigned long addr) { -pte_t *ptep; -unsigned long flags; +pte_t *ptep, pte; +unsigned int shift; +unsigned long flags, phys_addr;struct mm_struct *mm;if (user_mode (regs))@@ -35,14 +36,21 @@ unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr) mm = &init_mm;local_irq_save (flags); -if (mm == current->mm) - ptep =find_current_mm_pte (mm->pgd, addr,NULL ,NULL ); -else - ptep =find_init_mm_pte (addr,NULL ); + ptep =__find_linux_pte (mm->pgd, addr,NULL , &shift);local_irq_restore (flags); +if (!ptep ||pte_special (*ptep))return ULONG_MAX ; -return pte_pfn (*ptep); +
arch/powerpc/kernel/mce_power.c unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr) · line 54
Quoted 10 lines
arch/powerpc/kernel/mce_power.c +9
-0+ pte = *ptep; +if (shift >PAGE_SHIFT ) { +unsigned long rpnmask = (1ul << shift) -PAGE_SIZE ; + + pte =__pte (pte_val (pte) | (addr & rpnmask)); + } + phys_addr =pte_pfn (pte) <<PAGE_SHIFT ; + +return phys_addr; }
This should remain addr_to_pfn I think. None of the callers care what size page the EA was mapped with. 'pfn' is referring to the Linux pfn, which is the small page number.
if (shift > PAGE_SHIFT)
return (pte_pfn(*ptep) | ((addr & ((1UL << shift) - 1)) >> PAGE_SHIFT);
else
return pte_pfn(*ptep);Something roughly like that, then you don't have to change any callers or am I missing something?
Thanks,
Nick
Re: [PATCH v10 2/7] powerpc/mce: Fix MCE handling for huge pages
Hi Nick,
Quoted 89 lines · Nicholas Piggin
Santosh Sivaraj's on August 15, 2019 10:39 am:
Quoted 73 lines
From: Balbir Singh <[email protected]>
The current code would fail on huge pages addresses, since the shift would be incorrect. Use the correct page shift value returned by
__find_linux_pte()to get the correct physical address. The code is more generic and can handle both regular and compound pages.Fixes ba41e1e1ccb9 ("powerpc/mce: Hookup derror (load/store) UE errors")Signed-off-by Balbir Singh <[email protected]>[[email protected]: Fixup pseries_do_memory_failure()]Signed-off-by Reza Arbab <[email protected]>Co-developed-by Santosh Sivaraj <[email protected]>Signed-off-by Santosh Sivaraj <[email protected]>Tested-by Mahesh Salgaonkar <[email protected]>Cc [email protected] # v4.15+--- arch/powerpc/include/asm/mce.h | 2 +- arch/powerpc/kernel/mce_power.c | 55 ++++++++++++++-------------- arch/powerpc/platforms/pseries/ras.c | 9 ++--- 3 files changed, 32 insertions(+), 34 deletions(-)arch/powerpc/include/asm/mce.h +1
-1@@ -209,7 +209,7 @@ 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_phys (struct pt_regs *regs,unsigned long addr);#ifdef CONFIG_PPC_BOOK3S_64 void flush_and_reload_slb (void );#endif /* CONFIG_PPC_BOOK3S_64 */ arch/powerpc/kernel/mce_power.c +9
-10@@ -20,13 +20,14 @@#include <asm/exception-64s.h> /* -* Convert an address related to an mm to a PFN. NOTE: we are in real -* mode, we could potentially race with page table updates. +* Convert an address related to an mm to a physical address. +* 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_phys (struct pt_regs *regs,unsigned long addr) { -pte_t *ptep; -unsigned long flags; +pte_t *ptep, pte; +unsigned int shift; +unsigned long flags, phys_addr;struct mm_struct *mm;if (user_mode (regs))@@ -35,14 +36,21 @@ unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr) mm = &init_mm;local_irq_save (flags); -if (mm == current->mm) - ptep =find_current_mm_pte (mm->pgd, addr,NULL ,NULL ); -else - ptep =find_init_mm_pte (addr,NULL ); + ptep =__find_linux_pte (mm->pgd, addr,NULL , &shift);local_irq_restore (flags); +if (!ptep ||pte_special (*ptep))return ULONG_MAX ; -return pte_pfn (*ptep); +arch/powerpc/kernel/mce_power.c unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr) · line 54
Quoted 10 lines
arch/powerpc/kernel/mce_power.c +9
-0+ pte = *ptep; +if (shift >PAGE_SHIFT ) { +unsigned long rpnmask = (1ul << shift) -PAGE_SIZE ; + + pte =__pte (pte_val (pte) | (addr & rpnmask)); + } + phys_addr =pte_pfn (pte) <<PAGE_SHIFT ; + +return phys_addr; }This should remain
addr_to_pfnI think. None of the callers care what size page the EA was mapped with. 'pfn' is referring to the Linux pfn, which is the small page number.
Quoted 7 lines
if (shift > PAGE_SHIFT) return (pte_pfn(*ptep) | ((addr & ((1UL << shift) - 1)) >> PAGE_SHIFT); else return pte_pfn(*ptep);Something roughly like that, then you don't have to change any callers or am I missing something?
Here[1] you asked to return the real address rather than pfn, which all callers care about. So made the changes accordingly.
[1] https://www.spinics.net/lists/kernel/msg3187658.html
Thanks,
Santosh
Quoted 3 lines
Thanks,
Nick
Nicholas Piggin
reviewerRe: [PATCH v10 2/7] powerpc/mce: Fix MCE handling for huge pages
Santosh Sivaraj's on August 20, 2019 11:47 am:
Quoted 98 lines
Hi Nick,
Quoted 94 lines · Nicholas Piggin
Santosh Sivaraj's on August 15, 2019 10:39 am:
Quoted 73 lines
From: Balbir Singh <[email protected]>
The current code would fail on huge pages addresses, since the shift would be incorrect. Use the correct page shift value returned by
__find_linux_pte()to get the correct physical address. The code is more generic and can handle both regular and compound pages.Fixes ba41e1e1ccb9 ("powerpc/mce: Hookup derror (load/store) UE errors")Signed-off-by Balbir Singh <[email protected]>[[email protected]: Fixup pseries_do_memory_failure()]Signed-off-by Reza Arbab <[email protected]>Co-developed-by Santosh Sivaraj <[email protected]>Signed-off-by Santosh Sivaraj <[email protected]>Tested-by Mahesh Salgaonkar <[email protected]>Cc [email protected] # v4.15+--- arch/powerpc/include/asm/mce.h | 2 +- arch/powerpc/kernel/mce_power.c | 55 ++++++++++++++-------------- arch/powerpc/platforms/pseries/ras.c | 9 ++--- 3 files changed, 32 insertions(+), 34 deletions(-)arch/powerpc/include/asm/mce.h +1
-1@@ -209,7 +209,7 @@ 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_phys (struct pt_regs *regs,unsigned long addr);#ifdef CONFIG_PPC_BOOK3S_64 void flush_and_reload_slb (void );#endif /* CONFIG_PPC_BOOK3S_64 */ arch/powerpc/kernel/mce_power.c +9
-10@@ -20,13 +20,14 @@#include <asm/exception-64s.h> /* -* Convert an address related to an mm to a PFN. NOTE: we are in real -* mode, we could potentially race with page table updates. +* Convert an address related to an mm to a physical address. +* 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_phys (struct pt_regs *regs,unsigned long addr) { -pte_t *ptep; -unsigned long flags; +pte_t *ptep, pte; +unsigned int shift; +unsigned long flags, phys_addr;struct mm_struct *mm;if (user_mode (regs))@@ -35,14 +36,21 @@ unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr) mm = &init_mm;local_irq_save (flags); -if (mm == current->mm) - ptep =find_current_mm_pte (mm->pgd, addr,NULL ,NULL ); -else - ptep =find_init_mm_pte (addr,NULL ); + ptep =__find_linux_pte (mm->pgd, addr,NULL , &shift);local_irq_restore (flags); +if (!ptep ||pte_special (*ptep))return ULONG_MAX ; -return pte_pfn (*ptep); +arch/powerpc/kernel/mce_power.c unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr) · line 54
Quoted 10 lines
arch/powerpc/kernel/mce_power.c +9
-0+ pte = *ptep; +if (shift >PAGE_SHIFT ) { +unsigned long rpnmask = (1ul << shift) -PAGE_SIZE ; + + pte =__pte (pte_val (pte) | (addr & rpnmask)); + } + phys_addr =pte_pfn (pte) <<PAGE_SHIFT ; + +return phys_addr; }This should remain
addr_to_pfnI think. None of the callers care what size page the EA was mapped with. 'pfn' is referring to the Linux pfn, which is the small page number.if (shift > PAGE_SHIFT) return (pte_pfn(*ptep) | ((addr & ((1UL << shift) - 1)) >> PAGE_SHIFT); else return pte_pfn(*ptep);
Quoted 7 lines
Quoted 2 lines
Something roughly like that, then you don't have to change any callers or am I missing something?
Here[1] you asked to return the real address rather than pfn, which all callers care about. So made the changes accordingly.
Ah I did suggest it, but I meant _exact_ physical address :) The one matching the effective address you gave it.
As it is now, the physical address is truncated at the small page size, so if you do that you might as well just keep it as a pfn and no change to callers.
I would also prefer getting the pfn as above rather than constructing a new pte, which is a neat hack but is not a normal pattern.
Thanks,
Nick
PATCH v10 3/7 powerpc/mce: Make machine_check_ue_event() static
In reply to Santosh SivarajFrom: Reza Arbab <[email protected]>
The function doesn't get used outside this file, so make it static.
--- arch/powerpc/kernel/mce.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
arch/powerpc/kernel/mce.c +2 -2
@@ -34,7 +34,7 @@ static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT],static void machine_check_process_queued_event (struct irq_work *work);static void machine_check_ue_irq_work (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 = {
@@ -212,7 +212,7 @@ static void machine_check_ue_irq_work(struct irq_work *work)/* * 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;
Signature · 1 line
2.21.0
PATCH v10 4/7 extable: Add function to search only kernel exception table
In reply to Santosh SivarajCertain architecture specific operating modes (e.g., in powerpc machine check handler that is unable to access vmalloc memory), the search_exception_tables cannot be called because it also searches the module exception tables if entry is not found in the kernel exception table.
--- include/linux/extable.h | 2 ++ kernel/extable.c | 11 +++++++++-- 2 files changed, 11 insertions(+), 2 deletions(-)
include/linux/extable.h +2 -0
@@ -19,6 +19,8 @@ void trim_init_extable(struct module *m);/* Given an address, look for it in the exception tables */ const struct exception_table_entry *search_exception_tables (unsigned long add); +const struct exception_table_entry * +search_kernel_exception_table (unsigned long addr);#ifdef CONFIG_MODULES /* For extable.c to search modules' exception tables. */
kernel/extable.c +9 -2
@@ -40,13 +40,20 @@ void __init sort_main_extable(void) } } +/* Given an address, look for it in the kernel exception table */ +const +struct exception_table_entry *search_kernel_exception_table (unsigned long addr) +{ +return search_extable (__start___ex_table, + __stop___ex_table - __start___ex_table, addr); +} +/* Given an address, look for it in the exception tables. */ const struct exception_table_entry *search_exception_tables (unsigned long addr) {const struct exception_table_entry *e; - e =search_extable (__start___ex_table, - __stop___ex_table - __start___ex_table, addr); + e =search_kernel_exception_table (addr);if (!e) e =search_module_extables (addr);return e;
Signature · 1 line
2.21.0
PATCH v10 5/7 powerpc/memcpy: Add memcpy_mcsafe for pmem
In reply to Santosh SivarajFrom: Balbir Singh <[email protected]>
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. The return value is the number of bytes remaining to be copied.
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.
--- arch/powerpc/include/asm/string.h | 2 + arch/powerpc/lib/Makefile | 2 +- arch/powerpc/lib/memcpy_mcsafe_64.S | 242 ++++++++++++++++++++++++++++ 3 files changed, 245 insertions(+), 1 deletion(-) create mode 100644 arch/powerpc/lib/memcpy_mcsafe_64.S
arch/powerpc/include/asm/string.h +2 -0
@@ -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 );
arch/powerpc/lib/Makefile +1 -1
@@ -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
arch/powerpc/lib/memcpy_mcsafe_64.S new file +242 -0
242 lines not on this page · raw message
Signature · 1 line
2.21.0
PATCH v10 6/7 powerpc/mce: Handle UE event for memcpy_mcsafe
In reply to Santosh SivarajFrom: Balbir Singh <[email protected]>
If we take a UE on one of the instructions with a fixup entry, set nip to continue execution at the fixup entry. Stop processing the event further or print it.
--- arch/powerpc/include/asm/mce.h | 4 +++- arch/powerpc/kernel/mce.c | 16 ++++++++++++++++ arch/powerpc/kernel/mce_power.c | 15 +++++++++++++-- 3 files changed, 32 insertions(+), 3 deletions(-)
arch/powerpc/include/asm/mce.h +3 -1
@@ -122,7 +122,8 @@ struct machine_check_event { enum MCE_UeErrorType ue_error_type:8;u8 effective_address_provided;u8 physical_address_provided; -u8 reserved_1[5 ]; +u8 ignore_event; +u8 reserved_1[4 ];u64 effective_address;u64 physical_address;u8 reserved_2[8 ];
@@ -193,6 +194,7 @@ struct mce_error_info { enum MCE_Initiator initiator:8; enum MCE_ErrorClass error_class:8;bool sync_error; +bool ignore_event; };#define MAX_MC_EVT 100
arch/powerpc/kernel/mce.c +16 -0
@@ -149,6 +149,7 @@ 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; + mce->u.ue_error.ignore_event = mce_err->ignore_event;machine_check_ue_event (mce); } }
@@ -266,8 +267,17 @@ static void machine_process_ue_event(struct work_struct *work)/* * This should probably queued elsewhere, but * oh! well +* +* Don't report this machine check because the caller has a +* asked us to ignore the event, it has a fixup handler which +* will do the appropriate error handling and reporting. */ if (evt->error_type ==MCE_ERROR_TYPE_UE ) { +if (evt->u.ue_error.ignore_event) { +__this_cpu_dec (mce_ue_count); +continue ; + } +if (evt->u.ue_error.physical_address_provided) {unsigned long pfn;
@@ -301,6 +311,12 @@ static void machine_check_process_queued_event(struct irq_work *work)while (__this_cpu_read (mce_queue_count) >0 ) { index =__this_cpu_read (mce_queue_count) -1 ; evt =this_cpu_ptr (&mce_event_queue[index]); + +if (evt->error_type ==MCE_ERROR_TYPE_UE && + evt->u.ue_error.ignore_event) { +__this_cpu_dec (mce_queue_count); +continue ; + }machine_check_print_event_info (evt, false, false);__this_cpu_dec (mce_queue_count); }
arch/powerpc/kernel/mce_power.c +13 -2
@@ -11,6 +11,7 @@#include <linux/types.h> #include <linux/ptrace.h> +#include <linux/extable.h> #include <asm/mmu.h> #include <asm/mce.h> #include <asm/machdep.h>
@@ -18,6 +19,7 @@#include <asm/pte-walk.h> #include <asm/sstep.h> #include <asm/exception-64s.h> +#include <asm/extable.h> /* * Convert an address related to an mm to a physical address.
@@ -559,9 +561,18 @@ static int mce_handle_derror(struct pt_regs *regs,return 0 ; } -static long mce_handle_ue_error (struct pt_regs *regs) +static long mce_handle_ue_error (struct pt_regs *regs, +struct mce_error_info *mce_err) {long handled =0 ; +const struct exception_table_entry *entry; + + entry =search_kernel_exception_table (regs->nip); +if (entry) { + mce_err->ignore_event = true; + regs->nip =extable_fixup (entry); +return 1 ; + }/* * On specific SCOM read via MMIO we may get a machine check
@@ -594,7 +605,7 @@ static long mce_handle_error(struct pt_regs *regs, &phys_addr);if (!handled && mce_err.error_type ==MCE_ERROR_TYPE_UE ) - handled =mce_handle_ue_error (regs); + handled =mce_handle_ue_error (regs, &mce_err);save_mce_event (regs, handled, &mce_err, regs->nip, addr, phys_addr);
Signature · 1 line
2.21.0
Re: [PATCH v10 6/7] powerpc/mce: Handle UE event for memcpy_mcsafe
Santosh Sivaraj's on August 15, 2019 10:39 am:
Quoted 5 lines
From: Balbir Singh <[email protected]>
If we take a UE on one of the instructions with a fixup entry, set nip to continue execution at the fixup entry. Stop processing the event further or print it.
The previous patch added these fixup entries and now you handle them here. Which in theory seems to break bisecting. The patches should either be merged, or this one moved ahead in the series.
I'm still not entirely happy with the ignore_event thing, but that's probably more a symptom of the convoluted way machine check handling and reporting is structured. For now it's probably fine.
Quoted 130 lines
Co-developed-by Reza Arbab <[email protected]>Signed-off-by Reza Arbab <[email protected]>Signed-off-by Balbir Singh <[email protected]>Signed-off-by Santosh Sivaraj <[email protected]>Reviewed-by Mahesh Salgaonkar <[email protected]>--- arch/powerpc/include/asm/mce.h | 4 +++- arch/powerpc/kernel/mce.c | 16 ++++++++++++++++ arch/powerpc/kernel/mce_power.c | 15 +++++++++++++-- 3 files changed, 32 insertions(+), 3 deletions(-)arch/powerpc/include/asm/mce.h +3
-1@@ -122,7 +122,8 @@ struct machine_check_event { enum MCE_UeErrorType ue_error_type:8;u8 effective_address_provided;u8 physical_address_provided; -u8 reserved_1[5 ]; +u8 ignore_event; +u8 reserved_1[4 ];u64 effective_address;u64 physical_address;u8 reserved_2[8 ];@@ -193,6 +194,7 @@ struct mce_error_info { enum MCE_Initiator initiator:8; enum MCE_ErrorClass error_class:8;bool sync_error; +bool ignore_event; };#define MAX_MC_EVT 100arch/powerpc/kernel/mce.c +16
-0@@ -149,6 +149,7 @@ 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; + mce->u.ue_error.ignore_event = mce_err->ignore_event;machine_check_ue_event (mce); } }@@ -266,8 +267,17 @@ static void machine_process_ue_event(struct work_struct *work)/* * This should probably queued elsewhere, but * oh! well +* +* Don't report this machine check because the caller has a +* asked us to ignore the event, it has a fixup handler which +* will do the appropriate error handling and reporting. */ if (evt->error_type ==MCE_ERROR_TYPE_UE ) { +if (evt->u.ue_error.ignore_event) { +__this_cpu_dec (mce_ue_count); +continue ; + } +if (evt->u.ue_error.physical_address_provided) {unsigned long pfn;@@ -301,6 +311,12 @@ static void machine_check_process_queued_event(struct irq_work *work)while (__this_cpu_read (mce_queue_count) >0 ) { index =__this_cpu_read (mce_queue_count) -1 ; evt =this_cpu_ptr (&mce_event_queue[index]); + +if (evt->error_type ==MCE_ERROR_TYPE_UE && + evt->u.ue_error.ignore_event) { +__this_cpu_dec (mce_queue_count); +continue ; + }machine_check_print_event_info (evt, false, false);__this_cpu_dec (mce_queue_count); }arch/powerpc/kernel/mce_power.c +13
-2@@ -11,6 +11,7 @@#include <linux/types.h> #include <linux/ptrace.h> +#include <linux/extable.h> #include <asm/mmu.h> #include <asm/mce.h> #include <asm/machdep.h> @@ -18,6 +19,7 @@#include <asm/pte-walk.h> #include <asm/sstep.h> #include <asm/exception-64s.h> +#include <asm/extable.h> /* * Convert an address related to an mm to a physical address. @@ -559,9 +561,18 @@ static int mce_handle_derror(struct pt_regs *regs,return 0 ; } -static long mce_handle_ue_error (struct pt_regs *regs) +static long mce_handle_ue_error (struct pt_regs *regs, +struct mce_error_info *mce_err) {long handled =0 ; +const struct exception_table_entry *entry; + + entry =search_kernel_exception_table (regs->nip); +if (entry) { + mce_err->ignore_event = true; + regs->nip =extable_fixup (entry); +return 1 ; + }/* * On specific SCOM read via MMIO we may get a machine check @@ -594,7 +605,7 @@ static long mce_handle_error(struct pt_regs *regs, &phys_addr);if (!handled && mce_err.error_type ==MCE_ERROR_TYPE_UE ) - handled =mce_handle_ue_error (regs); + handled =mce_handle_ue_error (regs, &mce_err);save_mce_event (regs, handled, &mce_err, regs->nip, addr, phys_addr);Signature · 1 line
2.21.0
PATCH v10 7/7 powerpc: add machine check safe copy_to_user
In reply to Santosh SivarajUse memcpy_mcsafe() implementation to define copy_to_user_mcsafe()
--- arch/powerpc/Kconfig | 1 + arch/powerpc/include/asm/uaccess.h | 14 ++++++++++++++ 2 files changed, 15 insertions(+)
arch/powerpc/Kconfig +1 -0
@@ -137,6 +137,7 @@ 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_HAVE_NMI_SAFE_CMPXCHG select ARCH_KEEP_MEMBLOCK
arch/powerpc/include/asm/uaccess.h +14 -0
@@ -387,6 +387,20 @@ 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))) { +if (access_ok (to, n)) { +allow_write_to_user (to, n); + n =memcpy_mcsafe ((void *)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)
Signature · 1 line
2.21.0