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>
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 60b9148..78fd362 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -343,6 +343,8 @@
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 @@
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 @@
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) {
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 901435e..294104e0 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -914,6 +914,9 @@
* @pgd_entry: if set, called for each non-empty PGD (top-level) entry
* @pud_entry: if set, called for each non-empty PUD (2nd-level) entry
* @pmd_entry: if set, called for each non-empty PMD (3rd-level) entry
+ * this handler is required to be able to handle
+ * pmd_trans_huge() pmds. They may simply choose to
+ * split_huge_page() instead of handling it explicitly.
* @pte_entry: if set, called for each non-empty PTE (4th-level) entry
* @pte_hole: if set, called for each hole at all levels
* @hugetlb_entry: if set, called for each hugetlb entry
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 9e0f05e..e1ee6ad 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4763,7 +4763,8 @@
pte_t *pte;
spinlock_t *ptl;
- VM_BUG_ON(pmd_trans_huge(*pmd));
+ 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)
if (is_target_pte_for_mc(vma, addr, *pte, NULL))
@@ -4925,8 +4926,8 @@
pte_t *pte;
spinlock_t *ptl;
+ split_huge_page_pmd(walk->mm, pmd);
retry:
- VM_BUG_ON(pmd_trans_huge(*pmd));
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
for (; addr != end; addr += PAGE_SIZE) {
pte_t ptent = *(pte++);
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 7cfa6ae..c3450d5 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -33,19 +33,35 @@
pmd = pmd_offset(pud, addr);
do {
+again:
next = pmd_addr_end(addr, end);
- split_huge_page_pmd(walk->mm, pmd);
- if (pmd_none_or_clear_bad(pmd)) {
+ if (pmd_none(*pmd)) {
if (walk->pte_hole)
err = walk->pte_hole(addr, next, walk);
if (err)
break;
continue;
}
+ /*
+ * This implies that each ->pmd_entry() handler
+ * needs to know about pmd_trans_huge() pmds
+ */
if (walk->pmd_entry)
err = walk->pmd_entry(pmd, addr, next, walk);
- if (!err && walk->pte_entry)
- err = walk_pte_range(pmd, addr, next, walk);
+ if (err)
+ break;
+
+ /*
+ * Check this here so we only break down trans_huge
+ * pages when we _need_ to
+ */
+ if (!walk->pte_entry)
+ continue;
+
+ split_huge_page_pmd(walk->mm, pmd);
+ if (pmd_none_or_clear_bad(pmd))
+ goto again;
+ err = walk_pte_range(pmd, addr, next, walk);
if (err)
break;
} while (pmd++, addr = next, addr != end);