summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
authorDave Hansen <dave@linux.vnet.ibm.com>2011-03-23 02:32:56 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2011-03-23 03:44:04 +0300
commit033193275b3ffcfe7f3fde7b569f3d207f6cd6a0 (patch)
treefc65fa02248f855f0f63e087f35a507b6abb5617 /fs
parent278df9f451dc71dcd002246be48358a473504ad0 (diff)
downloadlinux-033193275b3ffcfe7f3fde7b569f3d207f6cd6a0.tar.xz
pagewalk: only split huge pages when necessary
Right now, if a mm_walk has either ->pte_entry or ->pmd_entry set, it will unconditionally split any transparent huge pages it runs in to. In practice, that means that anyone doing a cat /proc/$pid/smaps will unconditionally break down every huge page in the process and depend on khugepaged to re-collapse it later. This is fairly suboptimal. This patch changes that behavior. It teaches each ->pmd_entry handler (there are five) that they must break down the THPs themselves. Also, the _generic_ code will never break down a THP unless a ->pte_entry handler is actually set. This means that the ->pmd_entry handlers can now choose to deal with THPs without breaking them down. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Dave Hansen <dave@linux.vnet.ibm.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Acked-by: David Rientjes <rientjes@google.com> Reviewed-by: Eric B Munson <emunson@mgebm.net> Tested-by: Eric B Munson <emunson@mgebm.net> Cc: Michael J Wolf <mjwolf@us.ibm.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Matt Mackall <mpm@selenic.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'fs')
-rw-r--r--fs/proc/task_mmu.c6
1 files changed, 6 insertions, 0 deletions
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 60b914860f81..78fd3621f565 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -343,6 +343,8 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
struct page *page;
int mapcount;
+ split_huge_page_pmd(walk->mm, pmd);
+
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
for (; addr != end; pte++, addr += PAGE_SIZE) {
ptent = *pte;
@@ -467,6 +469,8 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
spinlock_t *ptl;
struct page *page;
+ split_huge_page_pmd(walk->mm, pmd);
+
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
for (; addr != end; pte++, addr += PAGE_SIZE) {
ptent = *pte;
@@ -623,6 +627,8 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
pte_t *pte;
int err = 0;
+ split_huge_page_pmd(walk->mm, pmd);
+
/* find the first VMA at or above 'addr' */
vma = find_vma(walk->mm, addr);
for (; addr != end; addr += PAGE_SIZE) {