Re: [patch] fs, proc: unconditional cond_resched when reading smaps

[Kirill A. Shutemov]

On Mon, Aug 21, 2017 at 02:06:45PM -0700, David Rientjes wrote:
> If there are large numbers of hugepages to iterate while reading
> /proc/pid/smaps, the page walk never does cond_resched().  On archs
> without split pmd locks, there can be significant and observable
> contention on mm->page_table_lock which cause lengthy delays without
> rescheduling.
> 
> Always reschedule in smaps_pte_range() if necessary since the pagewalk
> iteration can be expensive.
> 
> Signed-off-by: David Rientjes 
> ---
>  fs/proc/task_mmu.c | 5 +++--
>  1 file changed, 3 insertions(+), 2 deletions(-)
> 
> diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
> --- a/fs/proc/task_mmu.c
> +++ b/fs/proc/task_mmu.c
> @@ -599,11 +599,11 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long 
> addr, unsigned long end,
>   if (ptl) {
>   smaps_pmd_entry(pmd, addr, walk);
>   spin_unlock(ptl);
> - return 0;
> + goto out;
>   }
>  
>   if (pmd_trans_unstable(pmd))
> - return 0;
> + goto out;
>   /*
>* The mmap_sem held all the way back in m_start() is what
>* keeps khugepaged out of here and from collapsing things
> @@ -613,6 +613,7 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long 
> addr, unsigned long end,
>   for (; addr != end; pte++, addr += PAGE_SIZE)
>   smaps_pte_entry(pte, addr, walk);
>   pte_unmap_unlock(pte - 1, ptl);
> +out:
>   cond_resched();
>   return 0;
>  }

Maybe just call cond_resched() at the beginning of the function and don't
bother with gotos?

-- 
 Kirill A. Shutemov

Re: [patch] fs, proc: unconditional cond_resched when reading smaps

[Kirill A. Shutemov]

On Mon, Aug 21, 2017 at 02:06:45PM -0700, David Rientjes wrote:
> If there are large numbers of hugepages to iterate while reading
> /proc/pid/smaps, the page walk never does cond_resched().  On archs
> without split pmd locks, there can be significant and observable
> contention on mm->page_table_lock which cause lengthy delays without
> rescheduling.
> 
> Always reschedule in smaps_pte_range() if necessary since the pagewalk
> iteration can be expensive.
> 
> Signed-off-by: David Rientjes 
> ---
>  fs/proc/task_mmu.c | 5 +++--
>  1 file changed, 3 insertions(+), 2 deletions(-)
> 
> diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
> --- a/fs/proc/task_mmu.c
> +++ b/fs/proc/task_mmu.c
> @@ -599,11 +599,11 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long 
> addr, unsigned long end,
>   if (ptl) {
>   smaps_pmd_entry(pmd, addr, walk);
>   spin_unlock(ptl);
> - return 0;
> + goto out;
>   }
>  
>   if (pmd_trans_unstable(pmd))
> - return 0;
> + goto out;
>   /*
>* The mmap_sem held all the way back in m_start() is what
>* keeps khugepaged out of here and from collapsing things
> @@ -613,6 +613,7 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long 
> addr, unsigned long end,
>   for (; addr != end; pte++, addr += PAGE_SIZE)
>   smaps_pte_entry(pte, addr, walk);
>   pte_unmap_unlock(pte - 1, ptl);
> +out:
>   cond_resched();
>   return 0;
>  }

Maybe just call cond_resched() at the beginning of the function and don't
bother with gotos?

-- 
 Kirill A. Shutemov

[patch] fs, proc: unconditional cond_resched when reading smaps

[David Rientjes]

If there are large numbers of hugepages to iterate while reading
/proc/pid/smaps, the page walk never does cond_resched().  On archs
without split pmd locks, there can be significant and observable
contention on mm->page_table_lock which cause lengthy delays without
rescheduling.

Always reschedule in smaps_pte_range() if necessary since the pagewalk
iteration can be expensive.

Signed-off-by: David Rientjes 
---
 fs/proc/task_mmu.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -599,11 +599,11 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long 
addr, unsigned long end,
if (ptl) {
smaps_pmd_entry(pmd, addr, walk);
spin_unlock(ptl);
-   return 0;
+   goto out;
}
 
if (pmd_trans_unstable(pmd))
-   return 0;
+   goto out;
/*
 * The mmap_sem held all the way back in m_start() is what
 * keeps khugepaged out of here and from collapsing things
@@ -613,6 +613,7 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, 
unsigned long end,
for (; addr != end; pte++, addr += PAGE_SIZE)
smaps_pte_entry(pte, addr, walk);
pte_unmap_unlock(pte - 1, ptl);
+out:
cond_resched();
return 0;
 }

[patch] fs, proc: unconditional cond_resched when reading smaps

[David Rientjes]

If there are large numbers of hugepages to iterate while reading
/proc/pid/smaps, the page walk never does cond_resched().  On archs
without split pmd locks, there can be significant and observable
contention on mm->page_table_lock which cause lengthy delays without
rescheduling.

Always reschedule in smaps_pte_range() if necessary since the pagewalk
iteration can be expensive.

Signed-off-by: David Rientjes 
---
 fs/proc/task_mmu.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -599,11 +599,11 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long 
addr, unsigned long end,
if (ptl) {
smaps_pmd_entry(pmd, addr, walk);
spin_unlock(ptl);
-   return 0;
+   goto out;
}
 
if (pmd_trans_unstable(pmd))
-   return 0;
+   goto out;
/*
 * The mmap_sem held all the way back in m_start() is what
 * keeps khugepaged out of here and from collapsing things
@@ -613,6 +613,7 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, 
unsigned long end,
for (; addr != end; pte++, addr += PAGE_SIZE)
smaps_pte_entry(pte, addr, walk);
pte_unmap_unlock(pte - 1, ptl);
+out:
cond_resched();
return 0;
 }