* [PATCH 17/26] mm/riscv: Use general page fault accounting
[not found] <20200619160538.8641-1-peterx@redhat.com>
@ 2020-06-19 16:13 ` Peter Xu
0 siblings, 0 replies; 6+ messages in thread
From: Peter Xu @ 2020-06-19 16:13 UTC (permalink / raw)
To: linux-kernel, linux-mm
Cc: Andrea Arcangeli, Albert Ou, Michael Ellerman, Peter Xu,
Linus Torvalds, Palmer Dabbelt, Paul Walmsley, Andrew Morton,
Will Deacon, linux-riscv, Gerald Schaefer
Use the general page fault accounting by passing regs into handle_mm_fault().
It naturally solve the issue of multiple page fault accounting when page fault
retry happened.
CC: Paul Walmsley <paul.walmsley@sifive.com>
CC: Palmer Dabbelt <palmer@dabbelt.com>
CC: Albert Ou <aou@eecs.berkeley.edu>
CC: linux-riscv@lists.infradead.org
Signed-off-by: Peter Xu <peterx@redhat.com>
---
arch/riscv/mm/fault.c | 16 +---------------
1 file changed, 1 insertion(+), 15 deletions(-)
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index 677ee1bb11ac..e796ba02b572 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -110,7 +110,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs)
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(vma, addr, flags, NULL);
+ fault = handle_mm_fault(vma, addr, flags, regs);
/*
* If we need to retry but a fatal signal is pending, handle the
@@ -128,21 +128,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs)
BUG();
}
- /*
- * Major/minor page fault accounting is only done on the
- * initial attempt. If we go through a retry, it is extremely
- * likely that the page will be found in page cache at that point.
- */
if (flags & FAULT_FLAG_ALLOW_RETRY) {
- if (fault & VM_FAULT_MAJOR) {
- tsk->maj_flt++;
- perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ,
- 1, regs, addr);
- } else {
- tsk->min_flt++;
- perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN,
- 1, regs, addr);
- }
if (fault & VM_FAULT_RETRY) {
flags |= FAULT_FLAG_TRIED;
--
2.26.2
^ permalink raw reply related [flat|nested] 6+ messages in thread
* Re: [PATCH 17/26] mm/riscv: Use general page fault accounting
2020-07-11 19:43 ` Palmer Dabbelt
@ 2020-07-14 15:12 ` Pekka Enberg
0 siblings, 0 replies; 6+ messages in thread
From: Pekka Enberg @ 2020-07-14 15:12 UTC (permalink / raw)
To: Palmer Dabbelt
Cc: Andrea Arcangeli, Albert Ou, Will Deacon, Paul Walmsley, LKML,
Peter Xu, linux-mm, Michael Ellerman, Andrew Morton,
Linus Torvalds, linux-riscv, Gerald Schaefer
Hi Palmer,
On Sat, Jul 11, 2020 at 10:43 PM Palmer Dabbelt <palmer@dabbelt.com> wrote:
> This still slightly changes the accounting numbers, but I don't think it does
> so in a way that's meaningful enough to care about. SIGBUS is the only one
> that might happen frequently enough to notice, I doubt anyone cares about
> whether faults are accounted for during OOM.
What do you mean?
AFAICT, this patch _fixes_ the accounting to be correct on page fault
restarts. I sent a patch to fix this up some time ago, but of course
this generic solutions is better:
http://lists.infradead.org/pipermail/linux-riscv/2020-June/000775.html
- Pekka
_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH 17/26] mm/riscv: Use general page fault accounting
2020-06-26 22:36 ` Peter Xu
2020-07-01 11:46 ` Pekka Enberg
@ 2020-07-11 19:43 ` Palmer Dabbelt
2020-07-14 15:12 ` Pekka Enberg
1 sibling, 1 reply; 6+ messages in thread
From: Palmer Dabbelt @ 2020-07-11 19:43 UTC (permalink / raw)
To: peterx
Cc: aarcange, aou, will, Paul Walmsley, linux-kernel, peterx,
linux-mm, mpe, akpm, Linus Torvalds, linux-riscv,
gerald.schaefer
On Fri, 26 Jun 2020 15:36:25 PDT (-0700), peterx@redhat.com wrote:
> Use the general page fault accounting by passing regs into handle_mm_fault().
> It naturally solve the issue of multiple page fault accounting when page fault
> retry happened.
>
> CC: Paul Walmsley <paul.walmsley@sifive.com>
> CC: Palmer Dabbelt <palmer@dabbelt.com>
> CC: Albert Ou <aou@eecs.berkeley.edu>
> CC: linux-riscv@lists.infradead.org
> Signed-off-by: Peter Xu <peterx@redhat.com>
> ---
> arch/riscv/mm/fault.c | 16 +---------------
> 1 file changed, 1 insertion(+), 15 deletions(-)
>
> diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
> index 677ee1bb11ac..e796ba02b572 100644
> --- a/arch/riscv/mm/fault.c
> +++ b/arch/riscv/mm/fault.c
> @@ -110,7 +110,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs)
> * make sure we exit gracefully rather than endlessly redo
> * the fault.
> */
> - fault = handle_mm_fault(vma, addr, flags, NULL);
> + fault = handle_mm_fault(vma, addr, flags, regs);
>
> /*
> * If we need to retry but a fatal signal is pending, handle the
> @@ -128,21 +128,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs)
> BUG();
> }
>
> - /*
> - * Major/minor page fault accounting is only done on the
> - * initial attempt. If we go through a retry, it is extremely
> - * likely that the page will be found in page cache at that point.
> - */
> if (flags & FAULT_FLAG_ALLOW_RETRY) {
> - if (fault & VM_FAULT_MAJOR) {
> - tsk->maj_flt++;
> - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ,
> - 1, regs, addr);
> - } else {
> - tsk->min_flt++;
> - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN,
> - 1, regs, addr);
> - }
> if (fault & VM_FAULT_RETRY) {
> flags |= FAULT_FLAG_TRIED;
This still slightly changes the accounting numbers, but I don't think it does
so in a way that's meaningful enough to care about. SIGBUS is the only one
that might happen frequently enough to notice, I doubt anyone cares about
whether faults are accounted for during OOM.
Acked-by: Palmer Dabbelt <palmerdabbelt@google.com>
Thanks!
_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH 17/26] mm/riscv: Use general page fault accounting
2020-07-01 11:46 ` Pekka Enberg
@ 2020-07-02 15:51 ` Peter Xu
0 siblings, 0 replies; 6+ messages in thread
From: Peter Xu @ 2020-07-02 15:51 UTC (permalink / raw)
To: Pekka Enberg
Cc: Andrea Arcangeli, Albert Ou, Will Deacon, Paul Walmsley, LKML,
linux-mm, Palmer Dabbelt, Michael Ellerman, Andrew Morton,
Linus Torvalds, linux-riscv, Gerald Schaefer
On Wed, Jul 01, 2020 at 02:46:24PM +0300, Pekka Enberg wrote:
> Hi Peter,
Hi, Pekka,
>
> On Sat, Jun 27, 2020 at 1:36 AM Peter Xu <peterx@redhat.com> wrote:
> > Use the general page fault accounting by passing regs into handle_mm_fault().
> > It naturally solve the issue of multiple page fault accounting when page fault
> > retry happened.
>
> I sent a patch to fix up riscv page fault accounting some days ago:
>
> http://lists.infradead.org/pipermail/linux-riscv/2020-June/000775.html
Yes, this is a valid fix too.
>
> However, your fix is obviously even better. For the generic and riscv parts:
>
> Reviewed-by: Pekka Enberg <penberg@kernel.org>
Thanks!
--
Peter Xu
_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH 17/26] mm/riscv: Use general page fault accounting
2020-06-26 22:36 ` Peter Xu
@ 2020-07-01 11:46 ` Pekka Enberg
2020-07-02 15:51 ` Peter Xu
2020-07-11 19:43 ` Palmer Dabbelt
1 sibling, 1 reply; 6+ messages in thread
From: Pekka Enberg @ 2020-07-01 11:46 UTC (permalink / raw)
To: Peter Xu
Cc: Andrea Arcangeli, Albert Ou, Will Deacon, Paul Walmsley, LKML,
linux-mm, Palmer Dabbelt, Michael Ellerman, Andrew Morton,
Linus Torvalds, linux-riscv, Gerald Schaefer
Hi Peter,
On Sat, Jun 27, 2020 at 1:36 AM Peter Xu <peterx@redhat.com> wrote:
> Use the general page fault accounting by passing regs into handle_mm_fault().
> It naturally solve the issue of multiple page fault accounting when page fault
> retry happened.
I sent a patch to fix up riscv page fault accounting some days ago:
http://lists.infradead.org/pipermail/linux-riscv/2020-June/000775.html
However, your fix is obviously even better. For the generic and riscv parts:
Reviewed-by: Pekka Enberg <penberg@kernel.org>
- Pekka
_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv
^ permalink raw reply [flat|nested] 6+ messages in thread
* [PATCH 17/26] mm/riscv: Use general page fault accounting
[not found] <20200626223130.199227-1-peterx@redhat.com>
@ 2020-06-26 22:36 ` Peter Xu
2020-07-01 11:46 ` Pekka Enberg
2020-07-11 19:43 ` Palmer Dabbelt
0 siblings, 2 replies; 6+ messages in thread
From: Peter Xu @ 2020-06-26 22:36 UTC (permalink / raw)
To: linux-mm, linux-kernel
Cc: Andrea Arcangeli, Albert Ou, Linus Torvalds, Paul Walmsley,
Peter Xu, Palmer Dabbelt, Michael Ellerman, Andrew Morton,
Will Deacon, linux-riscv, Gerald Schaefer
Use the general page fault accounting by passing regs into handle_mm_fault().
It naturally solve the issue of multiple page fault accounting when page fault
retry happened.
CC: Paul Walmsley <paul.walmsley@sifive.com>
CC: Palmer Dabbelt <palmer@dabbelt.com>
CC: Albert Ou <aou@eecs.berkeley.edu>
CC: linux-riscv@lists.infradead.org
Signed-off-by: Peter Xu <peterx@redhat.com>
---
arch/riscv/mm/fault.c | 16 +---------------
1 file changed, 1 insertion(+), 15 deletions(-)
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index 677ee1bb11ac..e796ba02b572 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -110,7 +110,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs)
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(vma, addr, flags, NULL);
+ fault = handle_mm_fault(vma, addr, flags, regs);
/*
* If we need to retry but a fatal signal is pending, handle the
@@ -128,21 +128,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs)
BUG();
}
- /*
- * Major/minor page fault accounting is only done on the
- * initial attempt. If we go through a retry, it is extremely
- * likely that the page will be found in page cache at that point.
- */
if (flags & FAULT_FLAG_ALLOW_RETRY) {
- if (fault & VM_FAULT_MAJOR) {
- tsk->maj_flt++;
- perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ,
- 1, regs, addr);
- } else {
- tsk->min_flt++;
- perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN,
- 1, regs, addr);
- }
if (fault & VM_FAULT_RETRY) {
flags |= FAULT_FLAG_TRIED;
--
2.26.2
_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv
^ permalink raw reply related [flat|nested] 6+ messages in thread
end of thread, other threads:[~2020-07-14 15:12 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
[not found] <20200619160538.8641-1-peterx@redhat.com>
2020-06-19 16:13 ` [PATCH 17/26] mm/riscv: Use general page fault accounting Peter Xu
[not found] <20200626223130.199227-1-peterx@redhat.com>
2020-06-26 22:36 ` Peter Xu
2020-07-01 11:46 ` Pekka Enberg
2020-07-02 15:51 ` Peter Xu
2020-07-11 19:43 ` Palmer Dabbelt
2020-07-14 15:12 ` Pekka Enberg
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).