[PATCH] powerpc/vdso64: Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE

: syscall: 167 nsec/call clock-gettime-monotonic-coarse:libc: 15 nsec/call clock-gettime-monotonic-coarse:vdso: 11 nsec/call CC: Benjamin Herrenschmidt <b...@kernel.crashing.org> Signed-off-by: Santosh Sivaraj <sant...@fossix.org> --- arch/powerpc/kernel/asm-offsets.c

[PATCH] powerpc/vdso64: Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE

: syscall: 1347 nsec/call clock-gettime-monotonic-coarse:libc: 187 nsec/call clock-gettime-monotonic-coarse:vdso: 125 nsec/call Used https://github.com/nlynch-mentor/vdsotest.git for the benchmarks. CC: Benjamin Herrenschmidt <b...@kernel.crashing.org> Signed-off-by: Santosh Sivaraj

Re: [PATCH] powerpc/vdso64: Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE

* Michael Ellerman <m...@ellerman.id.au> wrote (on 2017-07-20 23:18:26 +1000): > Santosh Sivaraj <sant...@fossix.org> writes: > > > Current vDSO64 implementation does not have support for coarse > > clocks (CLOCK_MONOTONIC_COARSE, CLOCK_REALTIME_COARSE), for whi

[PATCH v2] powerpc/vdso64: Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE

: syscall: 1347 nsec/call clock-gettime-monotonic-coarse:libc: 187 nsec/call clock-gettime-monotonic-coarse:vdso: 125 nsec/call Used https://github.com/nlynch-mentor/vdsotest.git for the benchmarks. CC: Benjamin Herrenschmidt <b...@kernel.crashing.org> Signed-off-by: Santosh Sivaraj

Re: [PATCH v3] powerpc/vdso64: Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE

* Benjamin Herrenschmidt <b...@kernel.crashing.org> wrote (on 2017-07-25 20:07:28 +1000): > On Tue, 2017-07-25 at 12:26 +0530, Santosh Sivaraj wrote: > > > +static notrace void kernel_get_tspec(struct timespec *tp, > > +struct vdso_da

[PATCH v3] powerpc/vdso64: Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE

Herrenschmidt <b...@kernel.crashing.org> Signed-off-by: Santosh Sivaraj <sant...@fossix.org> --- V2 update: - moved syscall fallback to assembly. V3 update: - Restored "exact prototype" comment for __kernel_clock_gettime - Remove .hidden/.protected directives from _

[PATCH] powerpc/smp: Get cpu only after validity check

Check for validity of cpu before calling get_hard_smp_processor_id. Found with coverity. Signed-off-by: Santosh Sivaraj <sant...@fossix.org> --- arch/powerpc/platforms/powernv/smp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/platforms/powernv/sm

Re: [linux-next] SMT off triggers WARNING: CPU: 1 PID: 13 at arch/powerpc/kernel/watchdog.c:314 stop_wd_on_cpu+0x54/0xf0

* Abdul Haleem wrote (on 2017-07-03 11:25:18 +0530): > Hi, > > Today's next-20170630 on powerpc shows warnings in dmesg when SMT is > disabled. Fix provided by Nick: https://lkml.org/lkml/2017/6/30/143 Thanks, Santosh > > Test: SMT off > kernel:

[PATCH] powerpc/time: Fix tracing in time.c

: Naveen N. Rao <naveen.n@linux.vnet.ibm.com> Signed-off-by: Santosh Sivaraj <sant...@fossix.org> --- arch/powerpc/kernel/Makefile | 2 -- arch/powerpc/kernel/time.c | 6 +++--- 2 files changed, 3 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/kernel/Makefile b/arch/po

[PATCH] powerpc/time: Fix tracing in time.c

-by: Naveen N. Rao <naveen.n@linux.vnet.ibm.com> Signed-off-by: Santosh Sivaraj <sant...@fossix.org> --- arch/powerpc/kernel/Makefile | 2 -- arch/powerpc/kernel/time.c | 6 +++--- 2 files changed, 3 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/kernel/Makefile b/arch/po

[PATCH] powerpc/smp: Do not BUG_ON if invalid CPU during kick

During secondary start, we do not need to BUG_ON if an invalid CPU number is passed. We alreay print an error if secondary cannot be started, so just return an error instead. Signed-off-by: Santosh Sivaraj <sant...@fossix.org> --- arch/powerpc/kernel/smp.c| 3 ++- arch/p

[PATCH 1/2] powerpc/smp: Do not BUG_ON if invalid CPU during kick

During secondary start, we do not need to BUG_ON if an invalid CPU number is passed. We already print an error if secondary cannot be started, so just return an error instead. Signed-off-by: Santosh Sivaraj <sant...@fossix.org> --- arch/powerpc/kernel/smp.c| 3 ++- arch/p

[PATCH 2/2] powerpc/smp: Convert NR_CPUS to nr_cpu_ids

nr_cpu_ids can be limited by nr_cpus boot parameter, whereas NR_CPUS is a compile time constant, which shouldn't be compared against during cpu kick. Signed-off-by: Santosh Sivaraj <sant...@fossix.org> --- arch/powerpc/kernel/smp.c| 2 +- arch/powerpc/platforms/cell/smp.c

[PATCH 2/2] powerpc/vdso64: Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE

: syscall: 167 nsec/call clock-gettime-monotonic-coarse:libc: 15 nsec/call clock-gettime-monotonic-coarse:vdso: 11 nsec/call CC: Benjamin Herrenschmidt <b...@kernel.crashing.org> Signed-off-by: Santosh Sivaraj <sant...@fossix.org> --- arch/powerpc/kernel/asm-offsets.c |

[PATCH 1/2] powerpc/vdso64: Coarse timer support preparatory patch

Reorganize code to make it easy to introduce CLOCK_REALTIME_COARSE and CLOCK_MONOTONIC_COARSE timer support. Signed-off-by: Santosh Sivaraj <sant...@fossix.org> --- arch/powerpc/kernel/vdso64/gettimeofday.S | 14 -- 1 file changed, 8 insertions(+), 6 deletions(-) diff --git

Re: [RFC][PATCH v2 0/7] printk/ia64/ppc64/parisc64: let's deprecate %pF/%pf printk specifiers

ardware, so the patches are not > tested. Sorry about that! Tested patch series on ppc64 sucessfully. You may add tested by to the series. Tested-by: Santosh Sivaraj <sant...@fossix.org> Thanks, Santosh > > Another note: > I need to check what is BPF symbol l

Re: [RFC PATCH] powerpc/perf: Add compact mode pmu support for powernv

* Madhavan Srinivasan wrote (on 2017-10-03 12:25:15 +): > Most of the power processor generation performance monitoring > unit (PMU) driver code is bundled in the kernel and one of those > is enabled/registered based on the oprofile_cpu_type check at > the boot. >

Re: [PATCH] powerpc/perf: Fix for core/nest imc call trace on cpuhotplug

if the reference count is alreday zero, before > decrementing > the count, so that the ref count will not hit a negative value. > > > > Signed-off-by: Anju T Sudhakar <a...@linux.vnet.ibm.com> Reviewed-by: Santosh Sivaraj <sant...@fossix.org> > --- > arch/pow

Re: [PATCH v4] powerpc/vdso64: Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE

* Naveen N. Rao <naveen.n@linux.vnet.ibm.com> wrote (on 2017-10-09 10:39:18 +): > On 2017/10/09 08:09AM, Santosh Sivaraj wrote: > > Current vDSO64 implementation does not have support for coarse clocks > > (CLOCK_MONOTONIC_COARSE, CLOCK_REALTIME_COARSE), fo

[PATCH v6] powerpc/vdso64: Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE

/call clock-gettime-monotonic-coarse:vdso: 11 nsec/call CC: Benjamin Herrenschmidt <b...@kernel.crashing.org> Signed-off-by: Santosh Sivaraj <sant...@fossix.org> --- arch/powerpc/kernel/asm-offsets.c | 2 + arch/powerpc/kernel/vdso64/gettime

[PATCH v6] powerpc/vdso64: Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE

/call clock-gettime-monotonic-coarse:vdso: 11 nsec/call CC: Benjamin Herrenschmidt <b...@kernel.crashing.org> Reviewed-by: Naveen N. Rao <naveen.n@linux.vnet.ibm.com> Signed-off-by: Santosh Sivaraj <sant...@fossix.org> --- arch/powerpc/kernel/asm-offsets.c | 2 + a

Re: [PATCH v6] powerpc/vdso64: Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE

* Naveen N. Rao <naveen.n@linux.vnet.ibm.com> wrote (on 2017-10-11 07:04:43 +): > Hi Santosh, > This seems to have gone from v4 to v6 -- did I miss v5? Nope, this is indeed v5, a typo :-( > > On 2017/10/10 11:10PM, Santosh Sivaraj wrote: > > Current vDSO64 impl

[PATCH v5] powerpc/vdso64: Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE

/call clock-gettime-monotonic-coarse:vdso: 11 nsec/call CC: Benjamin Herrenschmidt <b...@kernel.crashing.org> Signed-off-by: Santosh Sivaraj <sant...@fossix.org> --- Changelog: v1: - gettimeofday was moved from asm to C - Coarse timer support addition v2: - Moved Syscall fallback

Re: [PATCH resend] powerpc/vdso64: Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE

Hi all, Any comments on the below patch? Thanks, Santosh * Santosh Sivaraj <sant...@fossix.org> wrote (on 2017-08-28 13:14:40 +0530): > Current vDSO64 implementation does not have support for coarse clocks > (CLOCK_MONOTONIC_COARSE, CLOCK_REALTIME_COARSE), for which it falls back

[PATCH resend] powerpc/vdso64: Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE

: syscall: 167 nsec/call clock-gettime-monotonic-coarse:libc: 15 nsec/call clock-gettime-monotonic-coarse:vdso: 11 nsec/call CC: Benjamin Herrenschmidt <b...@kernel.crashing.org> Signed-off-by: Santosh Sivaraj <sant...@fossix.org> --- arch/powerpc/kernel/asm-offsets.c

Re: [PATCH 2/2] powerpc/vdso64: Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE

* Naveen N. Rao <naveen.n@linux.vnet.ibm.com> wrote (on 2017-10-06 11:25:28 +): > On 2017/09/18 09:23AM, Santosh Sivaraj wrote: > > Current vDSO64 implementation does not have support for coarse clocks > > (CLOCK_MONOTONIC_COARSE, CLOCK_REALTIME_COARSE), fo

Re: [PATCH 2/2] powerpc/vdso64: Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE

* Naveen N. Rao <naveen.n@linux.vnet.ibm.com> wrote (on 2017-10-06 09:28:30 +): > On 2017/09/18 09:23AM, Santosh Sivaraj wrote: > > Current vDSO64 implementation does not have support for coarse clocks > > (CLOCK_MONOTONIC_COARSE, CLOCK_REALTIME_COARSE), fo

Re: [PATCH v5] powerpc/vdso64: Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE

* Segher Boessenkool <seg...@kernel.crashing.org> wrote (on 2017-10-11 17:02:16 +): Hi Segher, > Hi, > > On Wed, Oct 11, 2017 at 02:05:02PM +0530, Santosh Sivaraj wrote: > > +70:ld r8,CFG_TB_UPDATE_COUNT(r3) > > + andi. r0,r8,1

[PATCH v4] powerpc/vdso64: Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE

/call clock-gettime-monotonic-coarse:vdso: 11 nsec/call CC: Benjamin Herrenschmidt <b...@kernel.crashing.org> Signed-off-by: Santosh Sivaraj <sant...@fossix.org> --- arch/powerpc/kernel/asm-offsets.c | 2 + arch/powerpc/kernel/vdso64/gettime

Re: [PATCHv4 3/6] powerpc64: Add .opd based function descriptor dereference

at...@gmail.com> > --- > arch/powerpc/include/asm/module.h | 3 +++ > arch/powerpc/include/asm/sections.h | 12 > arch/powerpc/kernel/module_64.c | 14 ++ > arch/powerpc/kernel/vmlinux.lds.S | 2 ++ > 4 files changed, 31 insertions(+) > Looks go

[PATCH 06/13] powerpc/mce: Do not process notifier-handled UE events

From: Reza Arbab Signed-off-by: Reza Arbab --- 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

[PATCH 07/13] powerpc/mce: Add fixup address to UE events

From: Reza Arbab 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.

[PATCH 08/13] powerpc/memcpy: Add memcpy_mcsafe for pmem

From: Balbir Singh 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

[PATCH 01/13] powerpc/mce: Make machine_check_ue_event() static

From: Reza Arbab The function doesn't get used outside this file, so make it static. Signed-off-by: Reza Arbab --- 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

[PATCH 00/13] powerpc: implement machine check safe memcpy

mce: Allow notifier callback to handle MCE powerpc/mce: Do not process notifier-handled UE events powerpc/mce: Add fixup address to UE events powerpc/mce: Handle memcpy_mcsafe() powerpc/mce: Enable MCE notifiers in external modules powerpc/64s: Save r13 in machine_check_common_early Santosh

[PATCH 13/13] powerpc: add machine check safe copy_to_user

Use memcpy_mcsafe() implementation to define copy_to_user_mcsafe() Signed-off-by: Santosh Sivaraj --- 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

[PATCH 12/13] powerpc/memcpy_mcsafe: return remaining bytes

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 --- arch/powerpc/lib/memcpy_mcsafe_64.S

[PATCH 03/13] powerpc/mce: Add MCE notification chain

From: Reza Arbab Signed-off-by: Reza Arbab --- 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

[PATCH 04/13] powerpc/mce: Move machine_check_ue_event() call

From: Reza Arbab 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 --- arch/powerpc/kernel/mce.c | 5 - 1 file changed, 4 insertions(+),

[PATCH 05/13] powerpc/mce: Allow notifier callback to handle MCE

From: Reza Arbab 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 --- arch/powerpc/include/asm/asm-prototypes.h | 2 +- arch/powerpc/kernel/exceptions-64s.S | 3 +++ arch/powerpc/kernel/mce.c

[PATCH 02/13] powerpc/mce: Bug fixes for MCE handling in kernel space

From: Balbir Singh 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,

[PATCH 11/13] powerpc/64s: Save r13 in machine_check_common_early

From: Reza Arbab 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: 0xc008009c00b0 Oops: Kernel access of bad area, sig: 11

[PATCH 10/13] powerpc/mce: Enable MCE notifiers in external modules

From: Reza Arbab Signed-off-by: Reza Arbab --- 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

[PATCH 09/13] powerpc/mce: Handle memcpy_mcsafe()

From: Reza Arbab 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

[v3 2/7] powerpc/mce: Bug fixes for MCE handling in kernel space

handle shift values returned. Fixes: ba41e1e1ccb9 ("powerpc/mce: Hookup derror (load/store) UE errors") Signed-off-by: Balbir Singh [ar...@linux.ibm.com: Fixup pseries_do_memory_failure()] Signed-off-by: Reza Arbab Signed-off-by: Santosh Sivaraj --- arch/powerpc/include/asm/mce.h

[v3 1/7] powerpc/mce: Make machine_check_ue_event() static

From: Reza Arbab The function doesn't get used outside this file, so make it static. Signed-off-by: Reza Arbab Signed-off-by: Santosh Sivaraj --- 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

[v3 3/7] powerpc/memcpy: Add memcpy_mcsafe for pmem

the VMX optimizations, largely to keep the patch simple. If needed those optimizations can be folded in. Signed-off-by: Balbir Singh Acked-by: Nicholas Piggin [ar...@linux.ibm.com: Added symbol export] Signed-off-by: Santosh Sivaraj --- arch/powerpc/include/asm/string.h | 2 + arch/powerpc

[v3 4/7] powerpc/mce: Handle UE event for memcpy_mcsafe

If we take a UE on one of the instructions with a fixup entry, set nip to continue exucution at the fixup entry. Stop processing the event further or print it. Based-on-patch-by: Reza Arbab Cc: Reza Arbab Cc: Mahesh Salgaonkar Signed-off-by: Santosh Sivaraj --- arch/powerpc/include/asm/mce.h

[v3 7/7] powerpc/64s: save r13 in MCE handler (simulator workaroud)

From: Reza Arbab 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: 0xc008009c00b0 Oops: Kernel access of bad area, sig: 11

[v3 0/7] powerpc: implement machine check safe memcpy

/64s: save r13 in MCE handler (simulator workaroud) Santosh Sivaraj (3): powerpc/mce: Handle UE event for memcpy_mcsafe powerpc/memcpy_mcsafe: return remaining bytes powerpc: add machine check safe copy_to_user arch/powerpc/Kconfig | 1 + arch/powerpc/include/asm/mce.h

[v3 5/7] powerpc/memcpy_mcsafe: return remaining bytes

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 --- arch/powerpc/lib/memcpy_mcsafe_64.S

[v3 6/7] powerpc: add machine check safe copy_to_user

Use memcpy_mcsafe() implementation to define copy_to_user_mcsafe() Signed-off-by: Santosh Sivaraj --- 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

[v4 0/6] powerpc: implement machine check safe memcpy

Bug fixes for MCE handling in kernel space powerpc/memcpy: Add memcpy_mcsafe for pmem Reza Arbab (2): powerpc/mce: Make machine_check_ue_event() static powerpc/64s: save r13 in MCE handler (simulator workaroud) Santosh Sivaraj (2): powerpc/mce: Handle UE event for memcpy_mcsafe powerpc: a

[v4 1/6] powerpc/mce: Make machine_check_ue_event() static

From: Reza Arbab The function doesn't get used outside this file, so make it static. Signed-off-by: Reza Arbab Signed-off-by: Santosh Sivaraj Reviewed-by: Nicholas Piggin --- arch/powerpc/kernel/mce.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc

[v4 3/6] powerpc/memcpy: Add memcpy_mcsafe for pmem

] Signed-off-by: Santosh Sivaraj --- arch/powerpc/include/asm/string.h | 2 + arch/powerpc/lib/Makefile | 2 +- arch/powerpc/lib/memcpy_mcsafe_64.S | 239 3 files changed, 242 insertions(+), 1 deletion(-) create mode 100644 arch/powerpc/lib/memcpy_mcsafe_64

[v4 2/6] powerpc/mce: Bug fixes for MCE handling in kernel space

handle shift values returned. Fixes: ba41e1e1ccb9 ("powerpc/mce: Hookup derror (load/store) UE errors") Signed-off-by: Balbir Singh [ar...@linux.ibm.com: Fixup pseries_do_memory_failure()] Signed-off-by: Reza Arbab Signed-off-by: Santosh Sivaraj --- arch/powerpc/include/asm/mce.h

[v4 4/6] powerpc/mce: Handle UE event for memcpy_mcsafe

If we take a UE on one of the instructions with a fixup entry, set nip to continue exucution at the fixup entry. Stop processing the event further or print it. Based-on-patch-by: Reza Arbab Cc: Reza Arbab Cc: Mahesh Salgaonkar Signed-off-by: Santosh Sivaraj --- arch/powerpc/include/asm/mce.h

[v4 5/6] powerpc: add machine check safe copy_to_user

Use memcpy_mcsafe() implementation to define copy_to_user_mcsafe() Signed-off-by: Santosh Sivaraj --- arch/powerpc/Kconfig | 1 + arch/powerpc/include/asm/uaccess.h | 14 ++ 2 files changed, 15 insertions(+) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig

[v4 6/6] powerpc/64s: save r13 in MCE handler (simulator workaroud)

From: Reza Arbab 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: 0xc008009c00b0 Oops: Kernel access of bad area, sig: 11

[v5 4/6] extable: Add function to search only kernel exception table

In real mode, the search_exception tables cannot be called because it also searches the module exception tables if entry is not found in the kernel exception tables. Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Nicholas Piggin Signed-off-by: Santosh Sivaraj --- include/linux/extable.h | 2

[v5 6/6] powerpc: add machine check safe copy_to_user

Use memcpy_mcsafe() implementation to define copy_to_user_mcsafe() Signed-off-by: Santosh Sivaraj --- arch/powerpc/Kconfig | 1 + arch/powerpc/include/asm/uaccess.h | 14 ++ 2 files changed, 15 insertions(+) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig

[v5 5/6] powerpc/mce: Handle UE event for memcpy_mcsafe

If we take a UE on one of the instructions with a fixup entry, set nip to continue execution at the fixup entry. Stop processing the event further or print it. Based-on-patch-by: Reza Arbab Cc: Reza Arbab Cc: Mahesh Salgaonkar Signed-off-by: Santosh Sivaraj --- arch/powerpc/include/asm/mce.h

[v5 0/6] powerpc: implement machine check safe memcpy

erged] v2: * Don't set RI bit explicitly [mahesh] * Re-ordered series to get r13 workaround as the last patch --- Balbir Singh (2): powerpc/mce: Fix MCE handling for huge pages powerpc/memcpy: Add memcpy_mcsafe for pmem Reza Arbab (1): powerpc/mce: Make machine_check_ue_event() static Santosh

[v5 1/6] powerpc/mce: Make machine_check_ue_event() static

From: Reza Arbab The function doesn't get used outside this file, so make it static. Signed-off-by: Reza Arbab Signed-off-by: Santosh Sivaraj Reviewed-by: Nicholas Piggin --- arch/powerpc/kernel/mce.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc

[v5 2/6] powerpc/mce: Fix MCE handling for huge pages

("powerpc/mce: Hookup derror (load/store) UE errors") Signed-off-by: Balbir Singh [ar...@linux.ibm.com: Fixup pseries_do_memory_failure()] Signed-off-by: Reza Arbab Signed-off-by: Santosh Sivaraj --- arch/powerpc/include/asm/mce.h | 3 ++- arch/powerpc/kernel/mce_power.c

[v5 3/6] powerpc/memcpy: Add memcpy_mcsafe for pmem

] Signed-off-by: Santosh Sivaraj --- arch/powerpc/include/asm/string.h | 2 + arch/powerpc/lib/Makefile | 2 +- arch/powerpc/lib/memcpy_mcsafe_64.S | 239 3 files changed, 242 insertions(+), 1 deletion(-) create mode 100644 arch/powerpc/lib/memcpy_mcsafe_64

[v2 12/12] powerpc/64s: Save r13 in machine_check_common_early

From: Reza Arbab 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: 0xc008009c00b0 Oops: Kernel access of bad area, sig: 11

[v2 04/12] powerpc/mce: Move machine_check_ue_event() call

From: Reza Arbab 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 --- arch/powerpc/kernel/mce.c | 5 - 1 file changed, 4 insertions(+),

[v2 06/12] powerpc/mce: Add fixup address to UE events

From: Reza Arbab 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.

[v2 02/12] powerpc/mce: Bug fixes for MCE handling in kernel space

From: Balbir Singh 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,

[v2 07/12] powerpc/memcpy: Add memcpy_mcsafe for pmem

From: Balbir Singh 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

[v2 08/12] powerpc/mce: Handle memcpy_mcsafe()

From: Reza Arbab 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

[v2 03/12] powerpc/mce: Add MCE notification chain

From: Reza Arbab Signed-off-by: Reza Arbab --- 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

[v2 09/12] powerpc/mce: Enable MCE notifiers in external modules

From: Reza Arbab Signed-off-by: Reza Arbab --- 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

[v2 11/12] powerpc: add machine check safe copy_to_user

Use memcpy_mcsafe() implementation to define copy_to_user_mcsafe() Signed-off-by: Santosh Sivaraj --- 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

[v2 00/12] powerpc: implement machine check safe memcpy

handle MCE powerpc/mce: Add fixup address to UE events powerpc/mce: Handle memcpy_mcsafe() powerpc/mce: Enable MCE notifiers in external modules powerpc/64s: Save r13 in machine_check_common_early Santosh Sivaraj (2): powerpc/memcpy_mcsafe: return remaining bytes powerpc: add machine

[v2 05/12] powerpc/mce: Allow notifier callback to handle MCE

From: Reza Arbab 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 --- arch/powerpc/include/asm/asm-prototypes.h | 2 +- arch/powerpc/include/asm/mce.h| 3 +-

[v2 01/12] powerpc/mce: Make machine_check_ue_event() static

From: Reza Arbab The function doesn't get used outside this file, so make it static. Signed-off-by: Reza Arbab --- 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

[v2 10/12] powerpc/memcpy_mcsafe: return remaining bytes

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 --- arch/powerpc/lib/memcpy_mcsafe_64.S

[PATCH 1/3] powerpc/mce: Add MCE notification chain

This is needed to report bad blocks for persistent memory. Signed-off-by: Santosh Sivaraj --- arch/powerpc/include/asm/mce.h | 3 +++ arch/powerpc/kernel/mce.c | 15 +++ 2 files changed, 18 insertions(+) diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm

[PATCH 3/3] papr/scm: Add bad memory ranges to nvdimm bad ranges

Subscribe to the MCE notification and add the physical address which generated a memory error to nvdimm bad range. Signed-off-by: Santosh Sivaraj --- arch/powerpc/platforms/pseries/papr_scm.c | 65 +++ 1 file changed, 65 insertions(+) diff --git a/arch/powerpc/platforms

[PATCH 0/3] Add bad pmem bad blocks to bad range

This series, which should be based on top of the still un-merged "powerpc: implement machine check safe memcpy" series, adds support to add the bad blocks which generated an MCE to the NVDIMM bad blocks. The next access of the same memory will be blocked by the NVDIMM layer itself

[PATCH 2/3] of_pmem: Add memory ranges which took a mce to bad range

Subscribe to the MCE notification and add the physical address which generated a memory error to nvdimm bad range. Signed-off-by: Santosh Sivaraj --- drivers/nvdimm/of_pmem.c | 122 +-- 1 file changed, 103 insertions(+), 19 deletions(-) diff --git a/drivers

[PATCH v9 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. fixes: 733e4a4c ("powerpc/mce: hookup memory_failure for UE errors") Suggested-by: Mahesh Salgaonkar Signed-off-by: Santosh Sivaraj Cc: sta...@vger.kernel.org # v4.15+

[PATCH v9 0/7] powerpc: implement machine check safe memcpy

owerpc/mce: Fix MCE handling for huge pages powerpc/memcpy: Add memcpy_mcsafe for pmem Reza Arbab (1): powerpc/mce: Make machine_check_ue_event() static Santosh Sivaraj (4): powerpc/mce: Schedule work from irq_work extable: Add function to search only kernel exception table powerpc/mce:

[PATCH v9 7/7] powerpc: add machine check safe copy_to_user

Use memcpy_mcsafe() implementation to define copy_to_user_mcsafe() Signed-off-by: Santosh Sivaraj --- arch/powerpc/Kconfig | 1 + arch/powerpc/include/asm/uaccess.h | 14 ++ 2 files changed, 15 insertions(+) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig

[PATCH v9 3/7] powerpc/mce: Make machine_check_ue_event() static

From: Reza Arbab The function doesn't get used outside this file, so make it static. Signed-off-by: Reza Arbab Signed-off-by: Santosh Sivaraj Reviewed-by: Nicholas Piggin --- arch/powerpc/kernel/mce.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc

[PATCH v9 4/7] extable: Add function to search only kernel exception table

Gleixner Cc: Ingo Molnar Cc: Nicholas Piggin Signed-off-by: Santosh Sivaraj Reviewed-by: Nicholas Piggin --- include/linux/extable.h | 2 ++ kernel/extable.c| 11 +-- 2 files changed, 11 insertions(+), 2 deletions(-) diff --git a/include/linux/extable.h b/include/linux/extable.h

[PATCH v9 2/7] powerpc/mce: Fix MCE handling for huge pages

: ba41e1e1ccb9 ("powerpc/mce: Hookup derror (load/store) UE errors") Signed-off-by: Balbir Singh [ar...@linux.ibm.com: Fixup pseries_do_memory_failure()] Signed-off-by: Reza Arbab Co-developed-by: Santosh Sivaraj Signed-off-by: Santosh Sivaraj Tested-by: Mahesh Salgaonkar Cc: sta...@vger.

[PATCH v9 6/7] powerpc/mce: Handle UE event for memcpy_mcsafe

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. Co-developed-by: Reza Arbab Signed-off-by: Reza Arbab Cc: Mahesh Salgaonkar Signed-off-by: Santosh Sivaraj --- arch/powerpc/include

[PATCH v9 5/7] powerpc/memcpy: Add memcpy_mcsafe for pmem

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 [ar...@linux.ibm.com: Added symbol export] Co-developed-by: Santosh Sivaraj Signed-off-by: Santosh

Re: [PATCH v9 6/7] powerpc/mce: Handle UE event for memcpy_mcsafe

Hi Balbir, Balbir Singh writes: > On 12/8/19 7:22 pm, Santosh Sivaraj wrote: >> 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. >> >> Co-develo

[PATCH v10 2/7] powerpc/mce: Fix MCE handling for huge pages

: ba41e1e1ccb9 ("powerpc/mce: Hookup derror (load/store) UE errors") Signed-off-by: Balbir Singh [ar...@linux.ibm.com: Fixup pseries_do_memory_failure()] Signed-off-by: Reza Arbab Co-developed-by: Santosh Sivaraj Signed-off-by: Santosh Sivaraj Tested-by: Mahesh Salgaonkar Cc: sta...@vger.

[PATCH v10 5/7] powerpc/memcpy: Add memcpy_mcsafe for pmem

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 [ar...@linux.ibm.com: Added symbol export] Co-developed-by: Santosh Sivaraj Signed-off-by: Santosh

[PATCH v10 6/7] powerpc/mce: Handle UE event for memcpy_mcsafe

From: Balbir Singh 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. Co-developed-by: Reza Arbab Signed-off-by: Reza Arbab Signed-off-by: Balbir Singh Signed-off-by: Santosh Sivaraj

[PATCH v10 7/7] powerpc: add machine check safe copy_to_user

Use memcpy_mcsafe() implementation to define copy_to_user_mcsafe() Signed-off-by: Santosh Sivaraj --- arch/powerpc/Kconfig | 1 + arch/powerpc/include/asm/uaccess.h | 14 ++ 2 files changed, 15 insertions(+) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig

[PATCH v10 4/7] extable: Add function to search only kernel exception table

Gleixner Cc: Ingo Molnar Cc: Nicholas Piggin Signed-off-by: Santosh Sivaraj Reviewed-by: Nicholas Piggin --- include/linux/extable.h | 2 ++ kernel/extable.c| 11 +-- 2 files changed, 11 insertions(+), 2 deletions(-) diff --git a/include/linux/extable.h b/include/linux/extable.h

[PATCH v10 3/7] powerpc/mce: Make machine_check_ue_event() static

From: Reza Arbab The function doesn't get used outside this file, so make it static. Signed-off-by: Reza Arbab Signed-off-by: Santosh Sivaraj Reviewed-by: Nicholas Piggin --- arch/powerpc/kernel/mce.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc

Re: [PATCH v9 7/7] powerpc: add machine check safe copy_to_user

Hi Balbir, Balbir Singh writes: > On 12/8/19 7:22 pm, Santosh Sivaraj wrote: >> Use memcpy_mcsafe() implementation to define copy_to_user_mcsafe() >> >> Signed-off-by: Santosh Sivaraj >> --- >> arch/powerpc/Kconfig | 1 + >>

[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. fixes: 733e4a4c ("powerpc/mce: hookup memory_failure for UE errors") Suggested-by: Mahesh Salgaonkar Signed-off-by: Santosh Sivaraj Reviewed-by: Mahesh Salgaon

  1   2   3   >