Re: [PATCH mmotm] add the pagefault count into memcg stats: shmem fix

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 





On Tue, May 17, 2011 at 11:24 AM, Hugh Dickins <hughd@xxxxxxxxxx> wrote:
mem_cgroup_count_vm_event() should update the PGMAJFAULT count for the
target mm, not for current mm (but of course they're usually the same).

We don't know the target mm in shmem_getpage(), so do it at the outer
level in shmem_fault(); and it's easier to follow if we move the
count_vm_event(PGMAJFAULT) there too.

Hah, it was using __count_vm_event() before, sneaking that update into
the unpreemptible section under info->lock: well, it comes to the same
on x86 at least, and I still think it's best to keep these together.

Signed-off-by: Hugh Dickins <hughd@xxxxxxxxxx>
---

 mm/shmem.c |   13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

--- mmotm/mm/shmem.c    2011-05-13 14:57:45.367884578 -0700
+++ linux/mm/shmem.c    2011-05-17 10:27:19.901934756 -0700
@@ -1293,14 +1293,10 @@ repeat:
               swappage = lookup_swap_cache(swap);
               if (!swappage) {
                       shmem_swp_unmap(entry);
+                       spin_unlock(&info->lock);
                       /* here we actually do the io */
-                       if (type && !(*type & VM_FAULT_MAJOR)) {
-                               __count_vm_event(PGMAJFAULT);
-                               mem_cgroup_count_vm_event(current->mm,
-                                                         PGMAJFAULT);
+                       if (type)
                               *type |= VM_FAULT_MAJOR;
-                       }
-                       spin_unlock(&info->lock);
                       swappage = shmem_swapin(swap, gfp, info, idx);
                       if (!swappage) {
                               spin_lock(&info->lock);
@@ -1539,7 +1535,10 @@ static int shmem_fault(struct vm_area_st
       error = shmem_getpage(inode, vmf->pgoff, &vmf->page, SGP_CACHE, &ret);
       if (error)
               return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS);
-
+       if (ret & VM_FAULT_MAJOR) {
+               count_vm_event(PGMAJFAULT);
+               mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
+       }
       return ret | VM_FAULT_LOCKED;
 }

Thank you Hugh for the fix.
 
Acked-by: Ying Han<yinghan@xxxxxxxxxx>

--Ying

[Index of Archives]     [Linux ARM Kernel]     [Linux ARM]     [Linux Omap]     [Fedora ARM]     [IETF Annouce]     [Bugtraq]     [Linux]     [Linux OMAP]     [Linux MIPS]     [ECOS]     [Asterisk Internet PBX]     [Linux API]