* + thp-file-pages-support-for-split_huge_page.patch added to -mm tree
@ 2016-06-07 21:04 akpm
0 siblings, 0 replies; 2+ messages in thread
From: akpm @ 2016-06-07 21:04 UTC (permalink / raw)
To: kirill.shutemov, aarcange, andreslc, aneesh.kumar, cl,
dave.hansen, hughd, jmarchan, n-horiguchi, peterz, quning,
sasha.levin, vbabka, yang.shi, mm-commits
The patch titled
Subject: thp: file pages support for split_huge_page()
has been added to the -mm tree. Its filename is
thp-file-pages-support-for-split_huge_page.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/thp-file-pages-support-for-split_huge_page.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/thp-file-pages-support-for-split_huge_page.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Subject: thp: file pages support for split_huge_page()
Basic scheme is the same as for anon THP.
Main differences:
- File pages are on radix-tree, so we have head->_count offset by
HPAGE_PMD_NR. The count got distributed to small pages during split.
- mapping->tree_lock prevents non-lockless access to pages under split
over radix-tree;
- Lockless access is prevented by setting the head->_count to 0 during
split;
- After split, some pages can be beyond i_size. We drop them from
radix-tree.
- We don't setup migration entries. Just unmap pages. It helps
handling cases when i_size is in the middle of the page: no need
handle unmap pages beyond i_size manually.
Link: http://lkml.kernel.org/r/1465297246-98985-15-git-send-email-kirill.shutemov@linux.intel.com
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Christoph Lameter <cl@gentwo.org>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Yang Shi <yang.shi@linaro.org>
Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Ning Qu <quning@gmail.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/gup.c | 2
mm/huge_memory.c | 160 ++++++++++++++++++++++++++++++++-------------
2 files changed, 117 insertions(+), 45 deletions(-)
diff -puN mm/gup.c~thp-file-pages-support-for-split_huge_page mm/gup.c
--- a/mm/gup.c~thp-file-pages-support-for-split_huge_page
+++ a/mm/gup.c
@@ -288,6 +288,8 @@ struct page *follow_page_mask(struct vm_
ret = split_huge_page(page);
unlock_page(page);
put_page(page);
+ if (pmd_none(*pmd))
+ return no_page_table(vma, flags);
}
return ret ? ERR_PTR(ret) :
diff -puN mm/huge_memory.c~thp-file-pages-support-for-split_huge_page mm/huge_memory.c
--- a/mm/huge_memory.c~thp-file-pages-support-for-split_huge_page
+++ a/mm/huge_memory.c
@@ -30,6 +30,7 @@
#include <linux/hashtable.h>
#include <linux/userfaultfd_k.h>
#include <linux/page_idle.h>
+#include <linux/shmem_fs.h>
#include <asm/tlb.h>
#include <asm/pgalloc.h>
@@ -3206,12 +3207,15 @@ void vma_adjust_trans_huge(struct vm_are
static void freeze_page(struct page *page)
{
- enum ttu_flags ttu_flags = TTU_MIGRATION | TTU_IGNORE_MLOCK |
- TTU_IGNORE_ACCESS | TTU_RMAP_LOCKED;
+ enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS |
+ TTU_RMAP_LOCKED;
int i, ret;
VM_BUG_ON_PAGE(!PageHead(page), page);
+ if (PageAnon(page))
+ ttu_flags |= TTU_MIGRATION;
+
/* We only need TTU_SPLIT_HUGE_PMD once */
ret = try_to_unmap(page, ttu_flags | TTU_SPLIT_HUGE_PMD);
for (i = 1; !ret && i < HPAGE_PMD_NR; i++) {
@@ -3221,7 +3225,7 @@ static void freeze_page(struct page *pag
ret = try_to_unmap(page + i, ttu_flags);
}
- VM_BUG_ON(ret);
+ VM_BUG_ON_PAGE(ret, page + i - 1);
}
static void unfreeze_page(struct page *page)
@@ -3243,15 +3247,20 @@ static void __split_huge_page_tail(struc
/*
* tail_page->_refcount is zero and not changing from under us. But
* get_page_unless_zero() may be running from under us on the
- * tail_page. If we used atomic_set() below instead of atomic_inc(), we
- * would then run atomic_set() concurrently with
+ * tail_page. If we used atomic_set() below instead of atomic_inc() or
+ * atomic_add(), we would then run atomic_set() concurrently with
* get_page_unless_zero(), and atomic_set() is implemented in C not
* using locked ops. spin_unlock on x86 sometime uses locked ops
* because of PPro errata 66, 92, so unless somebody can guarantee
* atomic_set() here would be safe on all archs (and not only on x86),
- * it's safer to use atomic_inc().
+ * it's safer to use atomic_inc()/atomic_add().
*/
- page_ref_inc(page_tail);
+ if (PageAnon(head)) {
+ page_ref_inc(page_tail);
+ } else {
+ /* Additional pin to radix tree */
+ page_ref_add(page_tail, 2);
+ }
page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
page_tail->flags |= (head->flags &
@@ -3287,25 +3296,44 @@ static void __split_huge_page_tail(struc
lru_add_page_tail(head, page_tail, lruvec, list);
}
-static void __split_huge_page(struct page *page, struct list_head *list)
+static void __split_huge_page(struct page *page, struct list_head *list,
+ unsigned long flags)
{
struct page *head = compound_head(page);
struct zone *zone = page_zone(head);
struct lruvec *lruvec;
+ pgoff_t end = -1;
int i;
- /* prevent PageLRU to go away from under us, and freeze lru stats */
- spin_lock_irq(&zone->lru_lock);
lruvec = mem_cgroup_page_lruvec(head, zone);
/* complete memcg works before add pages to LRU */
mem_cgroup_split_huge_fixup(head);
- for (i = HPAGE_PMD_NR - 1; i >= 1; i--)
+ if (!PageAnon(page))
+ end = DIV_ROUND_UP(i_size_read(head->mapping->host), PAGE_SIZE);
+
+ for (i = HPAGE_PMD_NR - 1; i >= 1; i--) {
__split_huge_page_tail(head, i, lruvec, list);
+ /* Some pages can be beyond i_size: drop them from page cache */
+ if (head[i].index >= end) {
+ __ClearPageDirty(head + i);
+ __delete_from_page_cache(head + i, NULL);
+ put_page(head + i);
+ }
+ }
ClearPageCompound(head);
- spin_unlock_irq(&zone->lru_lock);
+ /* See comment in __split_huge_page_tail() */
+ if (PageAnon(head)) {
+ page_ref_inc(head);
+ } else {
+ /* Additional pin to radix tree */
+ page_ref_add(head, 2);
+ spin_unlock(&head->mapping->tree_lock);
+ }
+
+ spin_unlock_irqrestore(&page_zone(head)->lru_lock, flags);
unfreeze_page(head);
@@ -3430,36 +3458,54 @@ int split_huge_page_to_list(struct page
{
struct page *head = compound_head(page);
struct pglist_data *pgdata = NODE_DATA(page_to_nid(head));
- struct anon_vma *anon_vma;
- int count, mapcount, ret;
+ struct anon_vma *anon_vma = NULL;
+ struct address_space *mapping = NULL;
+ int count, mapcount, extra_pins, ret;
bool mlocked;
unsigned long flags;
VM_BUG_ON_PAGE(is_huge_zero_page(page), page);
- VM_BUG_ON_PAGE(!PageAnon(page), page);
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(!PageSwapBacked(page), page);
VM_BUG_ON_PAGE(!PageCompound(page), page);
- /*
- * The caller does not necessarily hold an mmap_sem that would prevent
- * the anon_vma disappearing so we first we take a reference to it
- * and then lock the anon_vma for write. This is similar to
- * page_lock_anon_vma_read except the write lock is taken to serialise
- * against parallel split or collapse operations.
- */
- anon_vma = page_get_anon_vma(head);
- if (!anon_vma) {
- ret = -EBUSY;
- goto out;
+ if (PageAnon(head)) {
+ /*
+ * The caller does not necessarily hold an mmap_sem that would
+ * prevent the anon_vma disappearing so we first we take a
+ * reference to it and then lock the anon_vma for write. This
+ * is similar to page_lock_anon_vma_read except the write lock
+ * is taken to serialise against parallel split or collapse
+ * operations.
+ */
+ anon_vma = page_get_anon_vma(head);
+ if (!anon_vma) {
+ ret = -EBUSY;
+ goto out;
+ }
+ extra_pins = 0;
+ mapping = NULL;
+ anon_vma_lock_write(anon_vma);
+ } else {
+ mapping = head->mapping;
+
+ /* Truncated ? */
+ if (!mapping) {
+ ret = -EBUSY;
+ goto out;
+ }
+
+ /* Addidional pins from radix tree */
+ extra_pins = HPAGE_PMD_NR;
+ anon_vma = NULL;
+ i_mmap_lock_read(mapping);
}
- anon_vma_lock_write(anon_vma);
/*
* Racy check if we can split the page, before freeze_page() will
* split PMDs
*/
- if (total_mapcount(head) != page_count(head) - 1) {
+ if (total_mapcount(head) != page_count(head) - extra_pins - 1) {
ret = -EBUSY;
goto out_unlock;
}
@@ -3472,35 +3518,60 @@ int split_huge_page_to_list(struct page
if (mlocked)
lru_add_drain();
+ /* prevent PageLRU to go away from under us, and freeze lru stats */
+ spin_lock_irqsave(&page_zone(head)->lru_lock, flags);
+
+ if (mapping) {
+ void **pslot;
+
+ spin_lock(&mapping->tree_lock);
+ pslot = radix_tree_lookup_slot(&mapping->page_tree,
+ page_index(head));
+ /*
+ * Check if the head page is present in radix tree.
+ * We assume all tail are present too, if head is there.
+ */
+ if (radix_tree_deref_slot_protected(pslot,
+ &mapping->tree_lock) != head)
+ goto fail;
+ }
+
/* Prevent deferred_split_scan() touching ->_refcount */
- spin_lock_irqsave(&pgdata->split_queue_lock, flags);
+ spin_lock(&pgdata->split_queue_lock);
count = page_count(head);
mapcount = total_mapcount(head);
- if (!mapcount && count == 1) {
+ if (!mapcount && page_ref_freeze(head, 1 + extra_pins)) {
if (!list_empty(page_deferred_list(head))) {
pgdata->split_queue_len--;
list_del(page_deferred_list(head));
}
- spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
- __split_huge_page(page, list);
+ spin_unlock(&pgdata->split_queue_lock);
+ __split_huge_page(page, list, flags);
ret = 0;
- } else if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) {
- spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
- pr_alert("total_mapcount: %u, page_count(): %u\n",
- mapcount, count);
- if (PageTail(page))
- dump_page(head, NULL);
- dump_page(page, "total_mapcount(head) > 0");
- BUG();
} else {
- spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
+ if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) {
+ pr_alert("total_mapcount: %u, page_count(): %u\n",
+ mapcount, count);
+ if (PageTail(page))
+ dump_page(head, NULL);
+ dump_page(page, "total_mapcount(head) > 0");
+ BUG();
+ }
+ spin_unlock(&pgdata->split_queue_lock);
+fail: if (mapping)
+ spin_unlock(&mapping->tree_lock);
+ spin_unlock_irqrestore(&page_zone(head)->lru_lock, flags);
unfreeze_page(head);
ret = -EBUSY;
}
out_unlock:
- anon_vma_unlock_write(anon_vma);
- put_anon_vma(anon_vma);
+ if (anon_vma) {
+ anon_vma_unlock_write(anon_vma);
+ put_anon_vma(anon_vma);
+ }
+ if (mapping)
+ i_mmap_unlock_read(mapping);
out:
count_vm_event(!ret ? THP_SPLIT_PAGE : THP_SPLIT_PAGE_FAILED);
return ret;
@@ -3623,8 +3694,7 @@ static int split_huge_pages_set(void *da
if (zone != page_zone(page))
goto next;
- if (!PageHead(page) || !PageAnon(page) ||
- PageHuge(page))
+ if (!PageHead(page) || PageHuge(page) || !PageLRU(page))
goto next;
total++;
_
Patches currently in -mm which might be from kirill.shutemov@linux.intel.com are
mm-make-swapin-readahead-to-improve-thp-collapse-rate-fix.patch
mm-make-swapin-readahead-to-improve-thp-collapse-rate-fix-2.patch
mm-make-swapin-readahead-to-improve-thp-collapse-rate-fix-3.patch
mm-thp-make-swapin-readahead-under-down_read-of-mmap_sem-fix.patch
thp-mlock-update-unevictable-lrutxt.patch
mm-do-not-pass-mm_struct-into-handle_mm_fault.patch
mm-introduce-fault_env.patch
mm-postpone-page-table-allocation-until-we-have-page-to-map.patch
rmap-support-file-thp.patch
mm-introduce-do_set_pmd.patch
thp-vmstats-add-counters-for-huge-file-pages.patch
thp-support-file-pages-in-zap_huge_pmd.patch
thp-handle-file-pages-in-split_huge_pmd.patch
thp-handle-file-cow-faults.patch
thp-skip-file-huge-pmd-on-copy_huge_pmd.patch
thp-prepare-change_huge_pmd-for-file-thp.patch
thp-run-vma_adjust_trans_huge-outside-i_mmap_rwsem.patch
thp-file-pages-support-for-split_huge_page.patch
thp-mlock-do-not-mlock-pte-mapped-file-huge-pages.patch
vmscan-split-file-huge-pages-before-paging-them-out.patch
page-flags-relax-policy-for-pg_mappedtodisk-and-pg_reclaim.patch
radix-tree-implement-radix_tree_maybe_preload_order.patch
filemap-prepare-find-and-delete-operations-for-huge-pages.patch
truncate-handle-file-thp.patch
mm-rmap-account-shmem-thp-pages.patch
shmem-prepare-huge=-mount-option-and-sysfs-knob.patch
shmem-add-huge-pages-support.patch
shmem-thp-respect-madv_nohugepage-for-file-mappings.patch
thp-extract-khugepaged-from-mm-huge_memoryc.patch
khugepaged-move-up_readmmap_sem-out-of-khugepaged_alloc_page.patch
shmem-make-shmem_inode_info-lock-irq-safe.patch
khugepaged-add-support-of-collapse-for-tmpfs-shmem-pages.patch
thp-introduce-config_transparent_huge_pagecache.patch
shmem-split-huge-pages-beyond-i_size-under-memory-pressure.patch
thp-update-documentation-vm-transhugefilesystems-proctxt.patch
a.patch
^ permalink raw reply [flat|nested] 2+ messages in thread
* + thp-file-pages-support-for-split_huge_page.patch added to -mm tree
@ 2016-06-16 22:22 akpm
0 siblings, 0 replies; 2+ messages in thread
From: akpm @ 2016-06-16 22:22 UTC (permalink / raw)
To: kirill.shutemov, mm-commits
The patch titled
Subject: thp: file pages support for split_huge_page()
has been added to the -mm tree. Its filename is
thp-file-pages-support-for-split_huge_page.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/thp-file-pages-support-for-split_huge_page.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/thp-file-pages-support-for-split_huge_page.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Subject: thp: file pages support for split_huge_page()
Basic scheme is the same as for anon THP.
Main differences:
- File pages are on radix-tree, so we have head->_count offset by
HPAGE_PMD_NR. The count got distributed to small pages during split.
- mapping->tree_lock prevents non-lockless access to pages under split
over radix-tree;
- Lockless access is prevented by setting the head->_count to 0 during
split;
- After split, some pages can be beyond i_size. We drop them from
radix-tree.
- We don't setup migration entries. Just unmap pages. It helps
handling cases when i_size is in the middle of the page: no need
handle unmap pages beyond i_size manually.
Link: http://lkml.kernel.org/r/1466021202-61880-20-git-send-email-kirill.shutemov@linux.intel.com
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/gup.c | 2
mm/huge_memory.c | 160 ++++++++++++++++++++++++++++++++-------------
2 files changed, 117 insertions(+), 45 deletions(-)
diff -puN mm/gup.c~thp-file-pages-support-for-split_huge_page mm/gup.c
--- a/mm/gup.c~thp-file-pages-support-for-split_huge_page
+++ a/mm/gup.c
@@ -288,6 +288,8 @@ struct page *follow_page_mask(struct vm_
ret = split_huge_page(page);
unlock_page(page);
put_page(page);
+ if (pmd_none(*pmd))
+ return no_page_table(vma, flags);
}
return ret ? ERR_PTR(ret) :
diff -puN mm/huge_memory.c~thp-file-pages-support-for-split_huge_page mm/huge_memory.c
--- a/mm/huge_memory.c~thp-file-pages-support-for-split_huge_page
+++ a/mm/huge_memory.c
@@ -30,6 +30,7 @@
#include <linux/hashtable.h>
#include <linux/userfaultfd_k.h>
#include <linux/page_idle.h>
+#include <linux/shmem_fs.h>
#include <asm/tlb.h>
#include <asm/pgalloc.h>
@@ -3199,12 +3200,15 @@ void vma_adjust_trans_huge(struct vm_are
static void freeze_page(struct page *page)
{
- enum ttu_flags ttu_flags = TTU_MIGRATION | TTU_IGNORE_MLOCK |
- TTU_IGNORE_ACCESS | TTU_RMAP_LOCKED;
+ enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS |
+ TTU_RMAP_LOCKED;
int i, ret;
VM_BUG_ON_PAGE(!PageHead(page), page);
+ if (PageAnon(page))
+ ttu_flags |= TTU_MIGRATION;
+
/* We only need TTU_SPLIT_HUGE_PMD once */
ret = try_to_unmap(page, ttu_flags | TTU_SPLIT_HUGE_PMD);
for (i = 1; !ret && i < HPAGE_PMD_NR; i++) {
@@ -3214,7 +3218,7 @@ static void freeze_page(struct page *pag
ret = try_to_unmap(page + i, ttu_flags);
}
- VM_BUG_ON(ret);
+ VM_BUG_ON_PAGE(ret, page + i - 1);
}
static void unfreeze_page(struct page *page)
@@ -3236,15 +3240,20 @@ static void __split_huge_page_tail(struc
/*
* tail_page->_refcount is zero and not changing from under us. But
* get_page_unless_zero() may be running from under us on the
- * tail_page. If we used atomic_set() below instead of atomic_inc(), we
- * would then run atomic_set() concurrently with
+ * tail_page. If we used atomic_set() below instead of atomic_inc() or
+ * atomic_add(), we would then run atomic_set() concurrently with
* get_page_unless_zero(), and atomic_set() is implemented in C not
* using locked ops. spin_unlock on x86 sometime uses locked ops
* because of PPro errata 66, 92, so unless somebody can guarantee
* atomic_set() here would be safe on all archs (and not only on x86),
- * it's safer to use atomic_inc().
+ * it's safer to use atomic_inc()/atomic_add().
*/
- page_ref_inc(page_tail);
+ if (PageAnon(head)) {
+ page_ref_inc(page_tail);
+ } else {
+ /* Additional pin to radix tree */
+ page_ref_add(page_tail, 2);
+ }
page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
page_tail->flags |= (head->flags &
@@ -3280,25 +3289,44 @@ static void __split_huge_page_tail(struc
lru_add_page_tail(head, page_tail, lruvec, list);
}
-static void __split_huge_page(struct page *page, struct list_head *list)
+static void __split_huge_page(struct page *page, struct list_head *list,
+ unsigned long flags)
{
struct page *head = compound_head(page);
struct zone *zone = page_zone(head);
struct lruvec *lruvec;
+ pgoff_t end = -1;
int i;
- /* prevent PageLRU to go away from under us, and freeze lru stats */
- spin_lock_irq(&zone->lru_lock);
lruvec = mem_cgroup_page_lruvec(head, zone);
/* complete memcg works before add pages to LRU */
mem_cgroup_split_huge_fixup(head);
- for (i = HPAGE_PMD_NR - 1; i >= 1; i--)
+ if (!PageAnon(page))
+ end = DIV_ROUND_UP(i_size_read(head->mapping->host), PAGE_SIZE);
+
+ for (i = HPAGE_PMD_NR - 1; i >= 1; i--) {
__split_huge_page_tail(head, i, lruvec, list);
+ /* Some pages can be beyond i_size: drop them from page cache */
+ if (head[i].index >= end) {
+ __ClearPageDirty(head + i);
+ __delete_from_page_cache(head + i, NULL);
+ put_page(head + i);
+ }
+ }
ClearPageCompound(head);
- spin_unlock_irq(&zone->lru_lock);
+ /* See comment in __split_huge_page_tail() */
+ if (PageAnon(head)) {
+ page_ref_inc(head);
+ } else {
+ /* Additional pin to radix tree */
+ page_ref_add(head, 2);
+ spin_unlock(&head->mapping->tree_lock);
+ }
+
+ spin_unlock_irqrestore(&page_zone(head)->lru_lock, flags);
unfreeze_page(head);
@@ -3423,36 +3451,54 @@ int split_huge_page_to_list(struct page
{
struct page *head = compound_head(page);
struct pglist_data *pgdata = NODE_DATA(page_to_nid(head));
- struct anon_vma *anon_vma;
- int count, mapcount, ret;
+ struct anon_vma *anon_vma = NULL;
+ struct address_space *mapping = NULL;
+ int count, mapcount, extra_pins, ret;
bool mlocked;
unsigned long flags;
VM_BUG_ON_PAGE(is_huge_zero_page(page), page);
- VM_BUG_ON_PAGE(!PageAnon(page), page);
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(!PageSwapBacked(page), page);
VM_BUG_ON_PAGE(!PageCompound(page), page);
- /*
- * The caller does not necessarily hold an mmap_sem that would prevent
- * the anon_vma disappearing so we first we take a reference to it
- * and then lock the anon_vma for write. This is similar to
- * page_lock_anon_vma_read except the write lock is taken to serialise
- * against parallel split or collapse operations.
- */
- anon_vma = page_get_anon_vma(head);
- if (!anon_vma) {
- ret = -EBUSY;
- goto out;
+ if (PageAnon(head)) {
+ /*
+ * The caller does not necessarily hold an mmap_sem that would
+ * prevent the anon_vma disappearing so we first we take a
+ * reference to it and then lock the anon_vma for write. This
+ * is similar to page_lock_anon_vma_read except the write lock
+ * is taken to serialise against parallel split or collapse
+ * operations.
+ */
+ anon_vma = page_get_anon_vma(head);
+ if (!anon_vma) {
+ ret = -EBUSY;
+ goto out;
+ }
+ extra_pins = 0;
+ mapping = NULL;
+ anon_vma_lock_write(anon_vma);
+ } else {
+ mapping = head->mapping;
+
+ /* Truncated ? */
+ if (!mapping) {
+ ret = -EBUSY;
+ goto out;
+ }
+
+ /* Addidional pins from radix tree */
+ extra_pins = HPAGE_PMD_NR;
+ anon_vma = NULL;
+ i_mmap_lock_read(mapping);
}
- anon_vma_lock_write(anon_vma);
/*
* Racy check if we can split the page, before freeze_page() will
* split PMDs
*/
- if (total_mapcount(head) != page_count(head) - 1) {
+ if (total_mapcount(head) != page_count(head) - extra_pins - 1) {
ret = -EBUSY;
goto out_unlock;
}
@@ -3465,35 +3511,60 @@ int split_huge_page_to_list(struct page
if (mlocked)
lru_add_drain();
+ /* prevent PageLRU to go away from under us, and freeze lru stats */
+ spin_lock_irqsave(&page_zone(head)->lru_lock, flags);
+
+ if (mapping) {
+ void **pslot;
+
+ spin_lock(&mapping->tree_lock);
+ pslot = radix_tree_lookup_slot(&mapping->page_tree,
+ page_index(head));
+ /*
+ * Check if the head page is present in radix tree.
+ * We assume all tail are present too, if head is there.
+ */
+ if (radix_tree_deref_slot_protected(pslot,
+ &mapping->tree_lock) != head)
+ goto fail;
+ }
+
/* Prevent deferred_split_scan() touching ->_refcount */
- spin_lock_irqsave(&pgdata->split_queue_lock, flags);
+ spin_lock(&pgdata->split_queue_lock);
count = page_count(head);
mapcount = total_mapcount(head);
- if (!mapcount && count == 1) {
+ if (!mapcount && page_ref_freeze(head, 1 + extra_pins)) {
if (!list_empty(page_deferred_list(head))) {
pgdata->split_queue_len--;
list_del(page_deferred_list(head));
}
- spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
- __split_huge_page(page, list);
+ spin_unlock(&pgdata->split_queue_lock);
+ __split_huge_page(page, list, flags);
ret = 0;
- } else if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) {
- spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
- pr_alert("total_mapcount: %u, page_count(): %u\n",
- mapcount, count);
- if (PageTail(page))
- dump_page(head, NULL);
- dump_page(page, "total_mapcount(head) > 0");
- BUG();
} else {
- spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
+ if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) {
+ pr_alert("total_mapcount: %u, page_count(): %u\n",
+ mapcount, count);
+ if (PageTail(page))
+ dump_page(head, NULL);
+ dump_page(page, "total_mapcount(head) > 0");
+ BUG();
+ }
+ spin_unlock(&pgdata->split_queue_lock);
+fail: if (mapping)
+ spin_unlock(&mapping->tree_lock);
+ spin_unlock_irqrestore(&page_zone(head)->lru_lock, flags);
unfreeze_page(head);
ret = -EBUSY;
}
out_unlock:
- anon_vma_unlock_write(anon_vma);
- put_anon_vma(anon_vma);
+ if (anon_vma) {
+ anon_vma_unlock_write(anon_vma);
+ put_anon_vma(anon_vma);
+ }
+ if (mapping)
+ i_mmap_unlock_read(mapping);
out:
count_vm_event(!ret ? THP_SPLIT_PAGE : THP_SPLIT_PAGE_FAILED);
return ret;
@@ -3616,8 +3687,7 @@ static int split_huge_pages_set(void *da
if (zone != page_zone(page))
goto next;
- if (!PageHead(page) || !PageAnon(page) ||
- PageHuge(page))
+ if (!PageHead(page) || PageHuge(page) || !PageLRU(page))
goto next;
total++;
_
Patches currently in -mm which might be from kirill.shutemov@linux.intel.com are
revert-mm-make-faultaround-produce-old-ptes.patch
revert-mm-disable-fault-around-on-emulated-access-bit-architecture.patch
mm-make-swapin-readahead-to-improve-thp-collapse-rate-fix.patch
mm-make-swapin-readahead-to-improve-thp-collapse-rate-fix-2.patch
mm-make-swapin-readahead-to-improve-thp-collapse-rate-fix-3.patch
mm-thp-make-swapin-readahead-under-down_read-of-mmap_sem-fix.patch
khugepaged-recheck-pmd-after-mmap_sem-re-acquired.patch
thp-mlock-update-unevictable-lrutxt.patch
mm-do-not-pass-mm_struct-into-handle_mm_fault.patch
mm-introduce-fault_env.patch
mm-postpone-page-table-allocation-until-we-have-page-to-map.patch
rmap-support-file-thp.patch
mm-introduce-do_set_pmd.patch
thp-vmstats-add-counters-for-huge-file-pages.patch
thp-support-file-pages-in-zap_huge_pmd.patch
thp-handle-file-pages-in-split_huge_pmd.patch
thp-handle-file-cow-faults.patch
thp-skip-file-huge-pmd-on-copy_huge_pmd.patch
thp-prepare-change_huge_pmd-for-file-thp.patch
thp-run-vma_adjust_trans_huge-outside-i_mmap_rwsem.patch
thp-file-pages-support-for-split_huge_page.patch
thp-mlock-do-not-mlock-pte-mapped-file-huge-pages.patch
vmscan-split-file-huge-pages-before-paging-them-out.patch
page-flags-relax-policy-for-pg_mappedtodisk-and-pg_reclaim.patch
radix-tree-implement-radix_tree_maybe_preload_order.patch
filemap-prepare-find-and-delete-operations-for-huge-pages.patch
truncate-handle-file-thp.patch
mm-rmap-account-shmem-thp-pages.patch
shmem-prepare-huge=-mount-option-and-sysfs-knob.patch
shmem-add-huge-pages-support.patch
shmem-thp-respect-madv_nohugepage-for-file-mappings.patch
thp-extract-khugepaged-from-mm-huge_memoryc.patch
khugepaged-move-up_readmmap_sem-out-of-khugepaged_alloc_page.patch
shmem-make-shmem_inode_info-lock-irq-safe.patch
khugepaged-add-support-of-collapse-for-tmpfs-shmem-pages.patch
thp-introduce-config_transparent_huge_pagecache.patch
shmem-split-huge-pages-beyond-i_size-under-memory-pressure.patch
thp-update-documentation-vm-transhugefilesystems-proctxt.patch
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2016-06-16 22:22 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2016-06-07 21:04 + thp-file-pages-support-for-split_huge_page.patch added to -mm tree akpm
2016-06-16 22:22 akpm
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.