[17/26] mm/riscv: Use general page fault accounting
diff mbox series

Message ID 20200626223625.199813-1-peterx@redhat.com
State New
Headers show
Series
  • mm: Page fault accounting cleanups
Related show

Commit Message

Peter Xu June 26, 2020, 10:36 p.m. UTC
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(-)

Comments

Pekka Enberg July 1, 2020, 11:46 a.m. UTC | #1
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
Peter Xu July 2, 2020, 3:51 p.m. UTC | #2
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!
Palmer Dabbelt July 11, 2020, 7:43 p.m. UTC | #3
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!
Pekka Enberg July 14, 2020, 3:12 p.m. UTC | #4
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

Patch
diff mbox series

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;