rpms/kernel/devel linux-2.6-ksm-updates.patch, NONE, 1.1 kernel.spec, 1.1703, 1.1704
Justin M. Forbes
jforbes at fedoraproject.org
Fri Aug 7 19:07:40 UTC 2009
Author: jforbes
Update of /cvs/pkgs/rpms/kernel/devel
In directory cvs1.fedora.phx.redhat.com:/tmp/cvs-serv18159
Modified Files:
kernel.spec
Added Files:
linux-2.6-ksm-updates.patch
Log Message:
Include KSM updates from upstream
linux-2.6-ksm-updates.patch:
Documentation/vm/00-INDEX | 2
Documentation/vm/ksm.txt | 89 ++++++
include/linux/ksm.h | 31 +-
kernel/fork.c | 1
mm/Kconfig | 2
mm/ksm.c | 665 ++++++++++++++++++++++++++++------------------
mm/memory.c | 5
mm/mmap.c | 16 -
8 files changed, 539 insertions(+), 272 deletions(-)
--- NEW FILE linux-2.6-ksm-updates.patch ---
Date: Mon, 3 Aug 2009 13:10:02 +0100 (BST)
From: Hugh Dickins <hugh.dickins at tiscali.co.uk>
Subject: [PATCH 1/12] ksm: rename kernel_pages_allocated
We're not implementing swapping of KSM pages in its first release;
but when that follows, "kernel_pages_allocated" will be a very poor
name for the sysfs file showing number of nodes in the stable tree:
rename that to "pages_shared" throughout.
But we already have a "pages_shared", counting those page slots
sharing the shared pages: first rename that to... "pages_sharing".
What will become of "max_kernel_pages" when the pages shared can
be swapped? I guess it will just be removed, so keep that name.
Signed-off-by: Hugh Dickins <hugh.dickins at tiscali.co.uk>
---
mm/ksm.c | 57 ++++++++++++++++++++++++++---------------------------
1 file changed, 28 insertions(+), 29 deletions(-)
--- ksm0/mm/ksm.c 2009-08-01 05:02:09.000000000 +0100
+++ ksm1/mm/ksm.c 2009-08-02 13:49:36.000000000 +0100
@@ -150,10 +150,10 @@ static struct kmem_cache *rmap_item_cach
static struct kmem_cache *mm_slot_cache;
/* The number of nodes in the stable tree */
-static unsigned long ksm_kernel_pages_allocated;
+static unsigned long ksm_pages_shared;
/* The number of page slots sharing those nodes */
-static unsigned long ksm_pages_shared;
+static unsigned long ksm_pages_sharing;
/* Limit on the number of unswappable pages used */
static unsigned long ksm_max_kernel_pages;
@@ -384,7 +384,7 @@ static void remove_rmap_item_from_tree(s
next_item->address |= NODE_FLAG;
} else {
rb_erase(&rmap_item->node, &root_stable_tree);
- ksm_kernel_pages_allocated--;
+ ksm_pages_shared--;
}
} else {
struct rmap_item *prev_item = rmap_item->prev;
@@ -398,7 +398,7 @@ static void remove_rmap_item_from_tree(s
}
rmap_item->next = NULL;
- ksm_pages_shared--;
+ ksm_pages_sharing--;
} else if (rmap_item->address & NODE_FLAG) {
unsigned char age;
@@ -748,7 +748,7 @@ static int try_to_merge_two_pages(struct
* is the number of kernel pages that we hold.
*/
if (ksm_max_kernel_pages &&
- ksm_max_kernel_pages <= ksm_kernel_pages_allocated)
+ ksm_max_kernel_pages <= ksm_pages_shared)
return err;
kpage = alloc_page(GFP_HIGHUSER);
@@ -787,7 +787,7 @@ static int try_to_merge_two_pages(struct
if (err)
break_cow(mm1, addr1);
else
- ksm_pages_shared += 2;
+ ksm_pages_sharing += 2;
}
put_page(kpage);
@@ -817,7 +817,7 @@ static int try_to_merge_with_ksm_page(st
up_read(&mm1->mmap_sem);
if (!err)
- ksm_pages_shared++;
+ ksm_pages_sharing++;
return err;
}
@@ -935,7 +935,7 @@ static struct rmap_item *stable_tree_ins
}
}
- ksm_kernel_pages_allocated++;
+ ksm_pages_shared++;
rmap_item->address |= NODE_FLAG | STABLE_FLAG;
rmap_item->next = NULL;
@@ -1051,7 +1051,7 @@ static void cmp_and_merge_page(struct pa
tree_rmap_item = stable_tree_search(page, page2, rmap_item);
if (tree_rmap_item) {
if (page == page2[0]) { /* forked */
- ksm_pages_shared++;
+ ksm_pages_sharing++;
err = 0;
} else
err = try_to_merge_with_ksm_page(rmap_item->mm,
@@ -1114,7 +1114,7 @@ static void cmp_and_merge_page(struct pa
break_cow(tree_rmap_item->mm,
tree_rmap_item->address);
break_cow(rmap_item->mm, rmap_item->address);
- ksm_pages_shared -= 2;
+ ksm_pages_sharing -= 2;
}
}
@@ -1430,7 +1430,7 @@ static ssize_t run_store(struct kobject
/*
* KSM_RUN_MERGE sets ksmd running, and 0 stops it running.
* KSM_RUN_UNMERGE stops it running and unmerges all rmap_items,
- * breaking COW to free the kernel_pages_allocated (but leaves
+ * breaking COW to free the unswappable pages_shared (but leaves
* mm_slots on the list for when ksmd may be set running again).
*/
@@ -1449,22 +1449,6 @@ static ssize_t run_store(struct kobject
}
KSM_ATTR(run);
-static ssize_t pages_shared_show(struct kobject *kobj,
- struct kobj_attribute *attr, char *buf)
-{
- return sprintf(buf, "%lu\n",
- ksm_pages_shared - ksm_kernel_pages_allocated);
-}
-KSM_ATTR_RO(pages_shared);
-
-static ssize_t kernel_pages_allocated_show(struct kobject *kobj,
- struct kobj_attribute *attr,
- char *buf)
-{
- return sprintf(buf, "%lu\n", ksm_kernel_pages_allocated);
-}
-KSM_ATTR_RO(kernel_pages_allocated);
-
static ssize_t max_kernel_pages_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
@@ -1488,13 +1472,28 @@ static ssize_t max_kernel_pages_show(str
}
KSM_ATTR(max_kernel_pages);
+static ssize_t pages_shared_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%lu\n", ksm_pages_shared);
+}
+KSM_ATTR_RO(pages_shared);
+
+static ssize_t pages_sharing_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%lu\n",
+ ksm_pages_sharing - ksm_pages_shared);
+}
+KSM_ATTR_RO(pages_sharing);
+
static struct attribute *ksm_attrs[] = {
&sleep_millisecs_attr.attr,
&pages_to_scan_attr.attr,
&run_attr.attr,
- &pages_shared_attr.attr,
- &kernel_pages_allocated_attr.attr,
&max_kernel_pages_attr.attr,
+ &pages_shared_attr.attr,
+ &pages_sharing_attr.attr,
NULL,
};
--
Date: Mon, 3 Aug 2009 13:11:00 +0100 (BST)
From: Hugh Dickins <hugh.dickins at tiscali.co.uk>
Subject: [PATCH 2/12] ksm: move pages_sharing updates
The pages_shared count is incremented and decremented when adding a node
to and removing a node from the stable tree: easy to understand. But the
pages_sharing count was hard to follow, being adjusted in various places:
increment and decrement it when adding to and removing from the stable tree.
And the pages_sharing variable used to include the pages_shared, then those
were subtracted when shown in the pages_sharing sysfs file: now keep it as
an exclusive count of leaves hanging off the stable tree nodes, throughout.
Signed-off-by: Hugh Dickins <hugh.dickins at tiscali.co.uk>
---
mm/ksm.c | 24 +++++++++---------------
1 file changed, 9 insertions(+), 15 deletions(-)
--- ksm1/mm/ksm.c 2009-08-02 13:49:36.000000000 +0100
+++ ksm2/mm/ksm.c 2009-08-02 13:49:43.000000000 +0100
@@ -152,7 +152,7 @@ static struct kmem_cache *mm_slot_cache;
/* The number of nodes in the stable tree */
static unsigned long ksm_pages_shared;
-/* The number of page slots sharing those nodes */
+/* The number of page slots additionally sharing those nodes */
static unsigned long ksm_pages_sharing;
/* Limit on the number of unswappable pages used */
@@ -382,6 +382,7 @@ static void remove_rmap_item_from_tree(s
&next_item->node,
&root_stable_tree);
next_item->address |= NODE_FLAG;
+ ksm_pages_sharing--;
} else {
rb_erase(&rmap_item->node, &root_stable_tree);
ksm_pages_shared--;
@@ -395,10 +396,10 @@ static void remove_rmap_item_from_tree(s
BUG_ON(next_item->prev != rmap_item);
next_item->prev = rmap_item->prev;
}
+ ksm_pages_sharing--;
}
rmap_item->next = NULL;
- ksm_pages_sharing--;
} else if (rmap_item->address & NODE_FLAG) {
unsigned char age;
@@ -786,8 +787,6 @@ static int try_to_merge_two_pages(struct
*/
if (err)
break_cow(mm1, addr1);
- else
- ksm_pages_sharing += 2;
}
put_page(kpage);
@@ -816,9 +815,6 @@ static int try_to_merge_with_ksm_page(st
err = try_to_merge_one_page(vma, page1, kpage);
up_read(&mm1->mmap_sem);
- if (!err)
- ksm_pages_sharing++;
-
return err;
}
@@ -935,13 +931,12 @@ static struct rmap_item *stable_tree_ins
}
}
- ksm_pages_shared++;
-
rmap_item->address |= NODE_FLAG | STABLE_FLAG;
rmap_item->next = NULL;
rb_link_node(&rmap_item->node, parent, new);
rb_insert_color(&rmap_item->node, &root_stable_tree);
+ ksm_pages_shared++;
return rmap_item;
}
@@ -1026,6 +1021,8 @@ static void stable_tree_append(struct rm
tree_rmap_item->next = rmap_item;
rmap_item->address |= STABLE_FLAG;
+
+ ksm_pages_sharing++;
}
/*
@@ -1050,10 +1047,9 @@ static void cmp_and_merge_page(struct pa
/* We first start with searching the page inside the stable tree */
tree_rmap_item = stable_tree_search(page, page2, rmap_item);
if (tree_rmap_item) {
- if (page == page2[0]) { /* forked */
- ksm_pages_sharing++;
+ if (page == page2[0]) /* forked */
err = 0;
- } else
+ else
err = try_to_merge_with_ksm_page(rmap_item->mm,
rmap_item->address,
page, page2[0]);
@@ -1114,7 +1110,6 @@ static void cmp_and_merge_page(struct pa
break_cow(tree_rmap_item->mm,
tree_rmap_item->address);
break_cow(rmap_item->mm, rmap_item->address);
- ksm_pages_sharing -= 2;
}
}
@@ -1482,8 +1477,7 @@ KSM_ATTR_RO(pages_shared);
static ssize_t pages_sharing_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
- return sprintf(buf, "%lu\n",
- ksm_pages_sharing - ksm_pages_shared);
+ return sprintf(buf, "%lu\n", ksm_pages_sharing);
}
KSM_ATTR_RO(pages_sharing);
--
Date: Mon, 3 Aug 2009 13:11:53 +0100 (BST)
From: Hugh Dickins <hugh.dickins at tiscali.co.uk>
Subject: [PATCH 3/12] ksm: pages_unshared and pages_volatile
The pages_shared and pages_sharing counts give a good picture of how
successful KSM is at sharing; but no clue to how much wasted work it's
doing to get there. Add pages_unshared (count of unique pages waiting
in the unstable tree, hoping to find a mate) and pages_volatile.
pages_volatile is harder to define. It includes those pages changing
too fast to get into the unstable tree, but also whatever other edge
conditions prevent a page getting into the trees: a high value may
deserve investigation. Don't try to calculate it from the various
conditions: it's the total of rmap_items less those accounted for.
Also show full_scans: the number of completed scans of everything
registered in the mm list.
The locking for all these counts is simply ksm_thread_mutex.
Signed-off-by: Hugh Dickins <hugh.dickins at tiscali.co.uk>
---
mm/ksm.c | 52 +++++++++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 51 insertions(+), 1 deletion(-)
--- ksm2/mm/ksm.c 2009-08-02 13:49:43.000000000 +0100
+++ ksm3/mm/ksm.c 2009-08-02 13:49:51.000000000 +0100
@@ -155,6 +155,12 @@ static unsigned long ksm_pages_shared;
/* The number of page slots additionally sharing those nodes */
static unsigned long ksm_pages_sharing;
+/* The number of nodes in the unstable tree */
+static unsigned long ksm_pages_unshared;
+
+/* The number of rmap_items in use: to calculate pages_volatile */
+static unsigned long ksm_rmap_items;
+
/* Limit on the number of unswappable pages used */
static unsigned long ksm_max_kernel_pages;
@@ -204,11 +210,17 @@ static void __init ksm_slab_free(void)
static inline struct rmap_item *alloc_rmap_item(void)
{
- return kmem_cache_zalloc(rmap_item_cache, GFP_KERNEL);
+ struct rmap_item *rmap_item;
+
+ rmap_item = kmem_cache_zalloc(rmap_item_cache, GFP_KERNEL);
+ if (rmap_item)
+ ksm_rmap_items++;
+ return rmap_item;
}
static inline void free_rmap_item(struct rmap_item *rmap_item)
{
+ ksm_rmap_items--;
rmap_item->mm = NULL; /* debug safety */
kmem_cache_free(rmap_item_cache, rmap_item);
}
@@ -419,6 +431,7 @@ static void remove_rmap_item_from_tree(s
BUG_ON(age > 2);
if (!age)
rb_erase(&rmap_item->node, &root_unstable_tree);
+ ksm_pages_unshared--;
}
rmap_item->address &= PAGE_MASK;
@@ -1002,6 +1015,7 @@ static struct rmap_item *unstable_tree_s
rb_link_node(&rmap_item->node, parent, new);
rb_insert_color(&rmap_item->node, &root_unstable_tree);
+ ksm_pages_unshared++;
return NULL;
}
@@ -1098,6 +1112,8 @@ static void cmp_and_merge_page(struct pa
if (!err) {
rb_erase(&tree_rmap_item->node, &root_unstable_tree);
tree_rmap_item->address &= ~NODE_FLAG;
+ ksm_pages_unshared--;
+
/*
* If we fail to insert the page into the stable tree,
* we will have 2 virtual addresses that are pointing
@@ -1481,6 +1497,37 @@ static ssize_t pages_sharing_show(struct
}
KSM_ATTR_RO(pages_sharing);
+static ssize_t pages_unshared_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%lu\n", ksm_pages_unshared);
+}
+KSM_ATTR_RO(pages_unshared);
+
+static ssize_t pages_volatile_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ long ksm_pages_volatile;
+
+ ksm_pages_volatile = ksm_rmap_items - ksm_pages_shared
+ - ksm_pages_sharing - ksm_pages_unshared;
+ /*
+ * It was not worth any locking to calculate that statistic,
+ * but it might therefore sometimes be negative: conceal that.
+ */
+ if (ksm_pages_volatile < 0)
+ ksm_pages_volatile = 0;
+ return sprintf(buf, "%ld\n", ksm_pages_volatile);
+}
+KSM_ATTR_RO(pages_volatile);
+
+static ssize_t full_scans_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%lu\n", ksm_scan.seqnr);
+}
+KSM_ATTR_RO(full_scans);
+
static struct attribute *ksm_attrs[] = {
&sleep_millisecs_attr.attr,
&pages_to_scan_attr.attr,
@@ -1488,6 +1535,9 @@ static struct attribute *ksm_attrs[] = {
&max_kernel_pages_attr.attr,
&pages_shared_attr.attr,
&pages_sharing_attr.attr,
+ &pages_unshared_attr.attr,
+ &pages_volatile_attr.attr,
+ &full_scans_attr.attr,
NULL,
};
--
Date: Mon, 3 Aug 2009 13:12:59 +0100 (BST)
From: Hugh Dickins <hugh.dickins at tiscali.co.uk>
Subject: [PATCH 4/12] ksm: break cow once unshared
We kept agreeing not to bother about the unswappable shared KSM pages
which later become unshared by others: observation suggests they're not
a significant proportion. But they are disadvantageous, and it is easier
to break COW to replace them by swappable pages, than offer statistics
to show that they don't matter; then we can stop worrying about them.
Doing this in ksm_do_scan, they don't go through cmp_and_merge_page on
this pass: give them a good chance of getting into the unstable tree
on the next pass, or back into the stable, by computing checksum now.
Signed-off-by: Hugh Dickins <hugh.dickins at tiscali.co.uk>
---
mm/ksm.c | 8 ++++++++
1 file changed, 8 insertions(+)
--- ksm3/mm/ksm.c 2009-08-02 13:49:51.000000000 +0100
+++ ksm4/mm/ksm.c 2009-08-02 13:49:59.000000000 +0100
@@ -1275,6 +1275,14 @@ static void ksm_do_scan(unsigned int sca
return;
if (!PageKsm(page) || !in_stable_tree(rmap_item))
cmp_and_merge_page(page, rmap_item);
+ else if (page_mapcount(page) == 1) {
+ /*
+ * Replace now-unshared ksm page by ordinary page.
+ */
+ break_cow(rmap_item->mm, rmap_item->address);
+ remove_rmap_item_from_tree(rmap_item);
+ rmap_item->oldchecksum = calc_checksum(page);
+ }
put_page(page);
}
}
--
Date: Mon, 3 Aug 2009 13:14:03 +0100 (BST)
From: Hugh Dickins <hugh.dickins at tiscali.co.uk>
Subject: [PATCH 5/12] ksm: keep quiet while list empty
ksm_scan_thread already sleeps in wait_event_interruptible until setting
ksm_run activates it; but if there's nothing on its list to look at, i.e.
nobody has yet said madvise MADV_MERGEABLE, it's a shame to be clocking
up system time and full_scans: ksmd_should_run added to check that too.
And move the mutex_lock out around it: the new counts showed that when
ksm_run is stopped, a little work often got done afterwards, because it
had been read before taking the mutex.
Signed-off-by: Hugh Dickins <hugh.dickins at tiscali.co.uk>
---
mm/ksm.c | 28 ++++++++++++++++++++++------
1 file changed, 22 insertions(+), 6 deletions(-)
--- ksm4/mm/ksm.c 2009-08-02 13:49:59.000000000 +0100
+++ ksm5/mm/ksm.c 2009-08-02 13:50:07.000000000 +0100
@@ -1287,21 +1287,27 @@ static void ksm_do_scan(unsigned int sca
}
}
+static int ksmd_should_run(void)
+{
+ return (ksm_run & KSM_RUN_MERGE) && !list_empty(&ksm_mm_head.mm_list);
+}
+
static int ksm_scan_thread(void *nothing)
{
set_user_nice(current, 5);
while (!kthread_should_stop()) {
- if (ksm_run & KSM_RUN_MERGE) {
- mutex_lock(&ksm_thread_mutex);
+ mutex_lock(&ksm_thread_mutex);
+ if (ksmd_should_run())
ksm_do_scan(ksm_thread_pages_to_scan);
- mutex_unlock(&ksm_thread_mutex);
+ mutex_unlock(&ksm_thread_mutex);
+
+ if (ksmd_should_run()) {
schedule_timeout_interruptible(
msecs_to_jiffies(ksm_thread_sleep_millisecs));
} else {
wait_event_interruptible(ksm_thread_wait,
- (ksm_run & KSM_RUN_MERGE) ||
- kthread_should_stop());
+ ksmd_should_run() || kthread_should_stop());
}
}
return 0;
@@ -1346,10 +1352,16 @@ int ksm_madvise(struct vm_area_struct *v
int __ksm_enter(struct mm_struct *mm)
{
- struct mm_slot *mm_slot = alloc_mm_slot();
+ struct mm_slot *mm_slot;
+ int needs_wakeup;
+
+ mm_slot = alloc_mm_slot();
if (!mm_slot)
return -ENOMEM;
+ /* Check ksm_run too? Would need tighter locking */
+ needs_wakeup = list_empty(&ksm_mm_head.mm_list);
+
spin_lock(&ksm_mmlist_lock);
insert_to_mm_slots_hash(mm, mm_slot);
/*
@@ -1361,6 +1373,10 @@ int __ksm_enter(struct mm_struct *mm)
spin_unlock(&ksm_mmlist_lock);
set_bit(MMF_VM_MERGEABLE, &mm->flags);
+
+ if (needs_wakeup)
+ wake_up_interruptible(&ksm_thread_wait);
+
return 0;
}
--
Date: Mon, 3 Aug 2009 13:15:15 +0100 (BST)
From: Hugh Dickins <hugh.dickins at tiscali.co.uk>
Subject: [PATCH 6/12] ksm: five little cleanups
1. We don't use __break_cow entry point now: merge it into break_cow.
2. remove_all_slot_rmap_items is just a special case of
remove_trailing_rmap_items: use the latter instead.
3. Extend comment on unmerge_ksm_pages and rmap_items.
4. try_to_merge_two_pages should use try_to_merge_with_ksm_page
instead of duplicating its code; and so swap them around.
5. Comment on cmp_and_merge_page described last year's: update it.
Signed-off-by: Hugh Dickins <hugh.dickins at tiscali.co.uk>
---
mm/ksm.c | 112 ++++++++++++++++++++---------------------------------
1 file changed, 44 insertions(+), 68 deletions(-)
--- ksm5/mm/ksm.c 2009-08-02 13:50:07.000000000 +0100
+++ ksm6/mm/ksm.c 2009-08-02 13:50:15.000000000 +0100
@@ -315,22 +315,18 @@ static void break_ksm(struct vm_area_str
/* Which leaves us looping there if VM_FAULT_OOM: hmmm... */
}
-static void __break_cow(struct mm_struct *mm, unsigned long addr)
+static void break_cow(struct mm_struct *mm, unsigned long addr)
{
struct vm_area_struct *vma;
+ down_read(&mm->mmap_sem);
vma = find_vma(mm, addr);
if (!vma || vma->vm_start > addr)
- return;
+ goto out;
if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma)
- return;
+ goto out;
break_ksm(vma, addr);
-}
-
-static void break_cow(struct mm_struct *mm, unsigned long addr)
-{
- down_read(&mm->mmap_sem);
- __break_cow(mm, addr);
+out:
up_read(&mm->mmap_sem);
}
@@ -439,17 +435,6 @@ static void remove_rmap_item_from_tree(s
cond_resched(); /* we're called from many long loops */
}
-static void remove_all_slot_rmap_items(struct mm_slot *mm_slot)
-{
- struct rmap_item *rmap_item, *node;
-
- list_for_each_entry_safe(rmap_item, node, &mm_slot->rmap_list, link) {
- remove_rmap_item_from_tree(rmap_item);
- list_del(&rmap_item->link);
- free_rmap_item(rmap_item);
- }
-}
-
static void remove_trailing_rmap_items(struct mm_slot *mm_slot,
struct list_head *cur)
{
@@ -471,6 +456,11 @@ static void remove_trailing_rmap_items(s
* page and upping mmap_sem. Nor does it fit with the way we skip dup'ing
* rmap_items from parent to child at fork time (so as not to waste time
* if exit comes before the next scan reaches it).
+ *
+ * Similarly, although we'd like to remove rmap_items (so updating counts
+ * and freeing memory) when unmerging an area, it's easier to leave that
+ * to the next pass of ksmd - consider, for example, how ksmd might be
+ * in cmp_and_merge_page on one of the rmap_items we would be removing.
*/
static void unmerge_ksm_pages(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
@@ -495,7 +485,7 @@ static void unmerge_and_remove_all_rmap_
continue;
unmerge_ksm_pages(vma, vma->vm_start, vma->vm_end);
}
- remove_all_slot_rmap_items(mm_slot);
+ remove_trailing_rmap_items(mm_slot, mm_slot->rmap_list.next);
up_read(&mm->mmap_sem);
}
@@ -533,7 +523,7 @@ static void remove_mm_from_lists(struct
list_del(&mm_slot->mm_list);
spin_unlock(&ksm_mmlist_lock);
- remove_all_slot_rmap_items(mm_slot);
+ remove_trailing_rmap_items(mm_slot, mm_slot->rmap_list.next);
free_mm_slot(mm_slot);
clear_bit(MMF_VM_MERGEABLE, &mm->flags);
}
@@ -740,6 +730,29 @@ out:
}
/*
+ * try_to_merge_with_ksm_page - like try_to_merge_two_pages,
+ * but no new kernel page is allocated: kpage must already be a ksm page.
+ */
+static int try_to_merge_with_ksm_page(struct mm_struct *mm1,
+ unsigned long addr1,
+ struct page *page1,
+ struct page *kpage)
+{
+ struct vm_area_struct *vma;
+ int err = -EFAULT;
+
+ down_read(&mm1->mmap_sem);
+ vma = find_vma(mm1, addr1);
+ if (!vma || vma->vm_start > addr1)
+ goto out;
+
+ err = try_to_merge_one_page(vma, page1, kpage);
+out:
+ up_read(&mm1->mmap_sem);
+ return err;
+}
+
+/*
* try_to_merge_two_pages - take two identical pages and prepare them
* to be merged into one page.
*
@@ -772,9 +785,8 @@ static int try_to_merge_two_pages(struct
down_read(&mm1->mmap_sem);
vma = find_vma(mm1, addr1);
if (!vma || vma->vm_start > addr1) {
- put_page(kpage);
up_read(&mm1->mmap_sem);
- return err;
+ goto out;
}
copy_user_highpage(kpage, page1, addr1, vma);
@@ -782,56 +794,20 @@ static int try_to_merge_two_pages(struct
up_read(&mm1->mmap_sem);
if (!err) {
- down_read(&mm2->mmap_sem);
- vma = find_vma(mm2, addr2);
- if (!vma || vma->vm_start > addr2) {
- put_page(kpage);
- up_read(&mm2->mmap_sem);
- break_cow(mm1, addr1);
- return -EFAULT;
- }
-
- err = try_to_merge_one_page(vma, page2, kpage);
- up_read(&mm2->mmap_sem);
-
+ err = try_to_merge_with_ksm_page(mm2, addr2, page2, kpage);
/*
- * If the second try_to_merge_one_page failed, we have a
- * ksm page with just one pte pointing to it, so break it.
+ * If that fails, we have a ksm page with only one pte
+ * pointing to it: so break it.
*/
if (err)
break_cow(mm1, addr1);
}
-
+out:
put_page(kpage);
return err;
}
/*
- * try_to_merge_with_ksm_page - like try_to_merge_two_pages,
- * but no new kernel page is allocated: kpage must already be a ksm page.
- */
-static int try_to_merge_with_ksm_page(struct mm_struct *mm1,
- unsigned long addr1,
- struct page *page1,
- struct page *kpage)
-{
- struct vm_area_struct *vma;
- int err = -EFAULT;
-
- down_read(&mm1->mmap_sem);
- vma = find_vma(mm1, addr1);
- if (!vma || vma->vm_start > addr1) {
- up_read(&mm1->mmap_sem);
- return err;
- }
-
- err = try_to_merge_one_page(vma, page1, kpage);
- up_read(&mm1->mmap_sem);
-
- return err;
-}
-
-/*
* stable_tree_search - search page inside the stable tree
* @page: the page that we are searching identical pages to.
* @page2: pointer into identical page that we are holding inside the stable
@@ -1040,10 +1016,10 @@ static void stable_tree_append(struct rm
}
/*
- * cmp_and_merge_page - take a page computes its hash value and check if there
- * is similar hash value to different page,
- * in case we find that there is similar hash to different page we call to
- * try_to_merge_two_pages().
+ * cmp_and_merge_page - first see if page can be merged into the stable tree;
+ * if not, compare checksum to previous and if it's the same, see if page can
+ * be inserted into the unstable tree, or merged with a page already there and
+ * both transferred to the stable tree.
*
* @page: the page that we are searching identical page to.
* @rmap_item: the reverse mapping into the virtual address of this page
--
Date: Mon, 3 Aug 2009 13:16:15 +0100 (BST)
From: Hugh Dickins <hugh.dickins at tiscali.co.uk>
Subject: [PATCH 7/12] ksm: fix endless loop on oom
break_ksm has been looping endlessly ignoring VM_FAULT_OOM: that should
only be a problem for ksmd when a memory control group imposes limits
(normally the OOM killer will kill others with an mm until it succeeds);
but in general (especially for MADV_UNMERGEABLE and KSM_RUN_UNMERGE) we
do need to route the error (or kill) back to the caller (or sighandling).
Test signal_pending in unmerge_ksm_pages, which could be a lengthy
procedure if it has to spill into swap: returning -ERESTARTSYS so that
trivial signals will restart but fatals will terminate (is that right?
we do different things in different places in mm, none exactly this).
unmerge_and_remove_all_rmap_items was forgetting to lock when going
down the mm_list: fix that. Whether it's successful or not, reset
ksm_scan cursor to head; but only if it's successful, reset seqnr
(shown in full_scans) - page counts will have gone down to zero.
This patch leaves a significant OOM deadlock, but it's a good step
on the way, and that deadlock is fixed in a subsequent patch.
Signed-off-by: Hugh Dickins <hugh.dickins at tiscali.co.uk>
---
mm/ksm.c | 108 +++++++++++++++++++++++++++++++++++++++++------------
1 file changed, 85 insertions(+), 23 deletions(-)
--- ksm6/mm/ksm.c 2009-08-02 13:50:15.000000000 +0100
+++ ksm7/mm/ksm.c 2009-08-02 13:50:25.000000000 +0100
@@ -294,10 +294,10 @@ static inline int in_stable_tree(struct
* Could a ksm page appear anywhere else? Actually yes, in a VM_PFNMAP
* mmap of /dev/mem or /dev/kmem, where we would not want to touch it.
*/
-static void break_ksm(struct vm_area_struct *vma, unsigned long addr)
+static int break_ksm(struct vm_area_struct *vma, unsigned long addr)
{
struct page *page;
- int ret;
+ int ret = 0;
do {
cond_resched();
@@ -310,9 +310,36 @@ static void break_ksm(struct vm_area_str
else
ret = VM_FAULT_WRITE;
put_page(page);
- } while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS)));
-
- /* Which leaves us looping there if VM_FAULT_OOM: hmmm... */
+ } while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_OOM)));
+ /*
+ * We must loop because handle_mm_fault() may back out if there's
+ * any difficulty e.g. if pte accessed bit gets updated concurrently.
+ *
+ * VM_FAULT_WRITE is what we have been hoping for: it indicates that
+ * COW has been broken, even if the vma does not permit VM_WRITE;
+ * but note that a concurrent fault might break PageKsm for us.
+ *
+ * VM_FAULT_SIGBUS could occur if we race with truncation of the
+ * backing file, which also invalidates anonymous pages: that's
+ * okay, that truncation will have unmapped the PageKsm for us.
+ *
+ * VM_FAULT_OOM: at the time of writing (late July 2009), setting
+ * aside mem_cgroup limits, VM_FAULT_OOM would only be set if the
+ * current task has TIF_MEMDIE set, and will be OOM killed on return
+ * to user; and ksmd, having no mm, would never be chosen for that.
+ *
+ * But if the mm is in a limited mem_cgroup, then the fault may fail
+ * with VM_FAULT_OOM even if the current task is not TIF_MEMDIE; and
+ * even ksmd can fail in this way - though it's usually breaking ksm
+ * just to undo a merge it made a moment before, so unlikely to oom.
+ *
+ * That's a pity: we might therefore have more kernel pages allocated
+ * than we're counting as nodes in the stable tree; but ksm_do_scan
+ * will retry to break_cow on each pass, so should recover the page
+ * in due course. The important thing is to not let VM_MERGEABLE
+ * be cleared while any such pages might remain in the area.
+ */
+ return (ret & VM_FAULT_OOM) ? -ENOMEM : 0;
}
static void break_cow(struct mm_struct *mm, unsigned long addr)
@@ -462,39 +489,61 @@ static void remove_trailing_rmap_items(s
* to the next pass of ksmd - consider, for example, how ksmd might be
* in cmp_and_merge_page on one of the rmap_items we would be removing.
*/
-static void unmerge_ksm_pages(struct vm_area_struct *vma,
- unsigned long start, unsigned long end)
+static int unmerge_ksm_pages(struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
{
unsigned long addr;
+ int err = 0;
- for (addr = start; addr < end; addr += PAGE_SIZE)
- break_ksm(vma, addr);
+ for (addr = start; addr < end && !err; addr += PAGE_SIZE) {
+ if (signal_pending(current))
+ err = -ERESTARTSYS;
+ else
+ err = break_ksm(vma, addr);
+ }
+ return err;
}
-static void unmerge_and_remove_all_rmap_items(void)
+static int unmerge_and_remove_all_rmap_items(void)
{
struct mm_slot *mm_slot;
struct mm_struct *mm;
struct vm_area_struct *vma;
+ int err = 0;
+
+ spin_lock(&ksm_mmlist_lock);
+ mm_slot = list_entry(ksm_mm_head.mm_list.next,
+ struct mm_slot, mm_list);
+ spin_unlock(&ksm_mmlist_lock);
- list_for_each_entry(mm_slot, &ksm_mm_head.mm_list, mm_list) {
+ while (mm_slot != &ksm_mm_head) {
mm = mm_slot->mm;
down_read(&mm->mmap_sem);
for (vma = mm->mmap; vma; vma = vma->vm_next) {
if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma)
continue;
- unmerge_ksm_pages(vma, vma->vm_start, vma->vm_end);
+ err = unmerge_ksm_pages(vma,
+ vma->vm_start, vma->vm_end);
+ if (err) {
+ up_read(&mm->mmap_sem);
+ goto out;
+ }
}
remove_trailing_rmap_items(mm_slot, mm_slot->rmap_list.next);
up_read(&mm->mmap_sem);
+
+ spin_lock(&ksm_mmlist_lock);
+ mm_slot = list_entry(mm_slot->mm_list.next,
+ struct mm_slot, mm_list);
+ spin_unlock(&ksm_mmlist_lock);
}
+ ksm_scan.seqnr = 0;
+out:
spin_lock(&ksm_mmlist_lock);
- if (ksm_scan.mm_slot != &ksm_mm_head) {
- ksm_scan.mm_slot = &ksm_mm_head;
- ksm_scan.seqnr++;
- }
+ ksm_scan.mm_slot = &ksm_mm_head;
spin_unlock(&ksm_mmlist_lock);
+ return err;
}
static void remove_mm_from_lists(struct mm_struct *mm)
@@ -1058,6 +1107,8 @@ static void cmp_and_merge_page(struct pa
/*
* A ksm page might have got here by fork, but its other
* references have already been removed from the stable tree.
+ * Or it might be left over from a break_ksm which failed
+ * when the mem_cgroup had reached its limit: try again now.
*/
if (PageKsm(page))
break_cow(rmap_item->mm, rmap_item->address);
@@ -1293,6 +1344,7 @@ int ksm_madvise(struct vm_area_struct *v
unsigned long end, int advice, unsigned long *vm_flags)
{
struct mm_struct *mm = vma->vm_mm;
+ int err;
switch (advice) {
case MADV_MERGEABLE:
@@ -1305,9 +1357,11 @@ int ksm_madvise(struct vm_area_struct *v
VM_MIXEDMAP | VM_SAO))
return 0; /* just ignore the advice */
- if (!test_bit(MMF_VM_MERGEABLE, &mm->flags))
- if (__ksm_enter(mm) < 0)
- return -EAGAIN;
+ if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) {
+ err = __ksm_enter(mm);
+ if (err)
+ return err;
+ }
*vm_flags |= VM_MERGEABLE;
break;
@@ -1316,8 +1370,11 @@ int ksm_madvise(struct vm_area_struct *v
if (!(*vm_flags & VM_MERGEABLE))
return 0; /* just ignore the advice */
- if (vma->anon_vma)
- unmerge_ksm_pages(vma, start, end);
+ if (vma->anon_vma) {
+ err = unmerge_ksm_pages(vma, start, end);
+ if (err)
+ return err;
+ }
*vm_flags &= ~VM_MERGEABLE;
break;
@@ -1448,8 +1505,13 @@ static ssize_t run_store(struct kobject
mutex_lock(&ksm_thread_mutex);
if (ksm_run != flags) {
ksm_run = flags;
- if (flags & KSM_RUN_UNMERGE)
- unmerge_and_remove_all_rmap_items();
+ if (flags & KSM_RUN_UNMERGE) {
+ err = unmerge_and_remove_all_rmap_items();
+ if (err) {
+ ksm_run = KSM_RUN_STOP;
+ count = err;
+ }
+ }
}
mutex_unlock(&ksm_thread_mutex);
--
Date: Mon, 3 Aug 2009 13:17:15 +0100 (BST)
From: Hugh Dickins <hugh.dickins at tiscali.co.uk>
Subject: [PATCH 8/12] ksm: distribute remove_mm_from_lists
Do some housekeeping in ksm.c, to help make the next patch easier
to understand: remove the function remove_mm_from_lists, distributing
its code to its callsites scan_get_next_rmap_item and __ksm_exit.
That turns out to be a win in scan_get_next_rmap_item: move its
remove_trailing_rmap_items and cursor advancement up, and it becomes
simpler than before. __ksm_exit becomes messier, but will change
again; and moving its remove_trailing_rmap_items up lets us strengthen
the unstable tree item's age condition in remove_rmap_item_from_tree.
Signed-off-by: Hugh Dickins <hugh.dickins at tiscali.co.uk>
---
mm/ksm.c | 97 ++++++++++++++++++++++-------------------------------
1 file changed, 42 insertions(+), 55 deletions(-)
--- ksm7/mm/ksm.c 2009-08-02 13:50:25.000000000 +0100
+++ ksm8/mm/ksm.c 2009-08-02 13:50:32.000000000 +0100
@@ -444,14 +444,9 @@ static void remove_rmap_item_from_tree(s
* But __ksm_exit has to be careful: do the rb_erase
* if it's interrupting a scan, and this rmap_item was
* inserted by this scan rather than left from before.
- *
- * Because of the case in which remove_mm_from_lists
- * increments seqnr before removing rmaps, unstable_nr
- * may even be 2 behind seqnr, but should never be
- * further behind. Yes, I did have trouble with this!
*/
age = (unsigned char)(ksm_scan.seqnr - rmap_item->address);
- BUG_ON(age > 2);
+ BUG_ON(age > 1);
if (!age)
rb_erase(&rmap_item->node, &root_unstable_tree);
ksm_pages_unshared--;
@@ -546,37 +541,6 @@ out:
return err;
}
-static void remove_mm_from_lists(struct mm_struct *mm)
-{
- struct mm_slot *mm_slot;
-
- spin_lock(&ksm_mmlist_lock);
- mm_slot = get_mm_slot(mm);
-
- /*
- * This mm_slot is always at the scanning cursor when we're
- * called from scan_get_next_rmap_item; but it's a special
- * case when we're called from __ksm_exit.
- */
- if (ksm_scan.mm_slot == mm_slot) {
- ksm_scan.mm_slot = list_entry(
- mm_slot->mm_list.next, struct mm_slot, mm_list);
- ksm_scan.address = 0;
- ksm_scan.rmap_item = list_entry(
- &ksm_scan.mm_slot->rmap_list, struct rmap_item, link);
- if (ksm_scan.mm_slot == &ksm_mm_head)
- ksm_scan.seqnr++;
- }
-
- hlist_del(&mm_slot->link);
- list_del(&mm_slot->mm_list);
- spin_unlock(&ksm_mmlist_lock);
-
- remove_trailing_rmap_items(mm_slot, mm_slot->rmap_list.next);
- free_mm_slot(mm_slot);
- clear_bit(MMF_VM_MERGEABLE, &mm->flags);
-}
-
static u32 calc_checksum(struct page *page)
{
u32 checksum;
@@ -1248,33 +1212,31 @@ next_mm:
}
}
- if (!ksm_scan.address) {
- /*
- * We've completed a full scan of all vmas, holding mmap_sem
- * throughout, and found no VM_MERGEABLE: so do the same as
- * __ksm_exit does to remove this mm from all our lists now.
- */
- remove_mm_from_lists(mm);
- up_read(&mm->mmap_sem);
- slot = ksm_scan.mm_slot;
- if (slot != &ksm_mm_head)
- goto next_mm;
- return NULL;
- }
-
/*
* Nuke all the rmap_items that are above this current rmap:
* because there were no VM_MERGEABLE vmas with such addresses.
*/
remove_trailing_rmap_items(slot, ksm_scan.rmap_item->link.next);
- up_read(&mm->mmap_sem);
spin_lock(&ksm_mmlist_lock);
- slot = list_entry(slot->mm_list.next, struct mm_slot, mm_list);
- ksm_scan.mm_slot = slot;
+ ksm_scan.mm_slot = list_entry(slot->mm_list.next,
+ struct mm_slot, mm_list);
+ if (ksm_scan.address == 0) {
+ /*
+ * We've completed a full scan of all vmas, holding mmap_sem
+ * throughout, and found no VM_MERGEABLE: so do the same as
+ * __ksm_exit does to remove this mm from all our lists now.
+ */
+ hlist_del(&slot->link);
+ list_del(&slot->mm_list);
+ free_mm_slot(slot);
+ clear_bit(MMF_VM_MERGEABLE, &mm->flags);
+ }
spin_unlock(&ksm_mmlist_lock);
+ up_read(&mm->mmap_sem);
/* Repeat until we've completed scanning the whole list */
+ slot = ksm_scan.mm_slot;
if (slot != &ksm_mm_head)
goto next_mm;
@@ -1415,13 +1377,38 @@ int __ksm_enter(struct mm_struct *mm)
void __ksm_exit(struct mm_struct *mm)
{
+ struct mm_slot *mm_slot;
+
/*
* This process is exiting: doesn't hold and doesn't need mmap_sem;
* but we do need to exclude ksmd and other exiters while we modify
* the various lists and trees.
*/
mutex_lock(&ksm_thread_mutex);
- remove_mm_from_lists(mm);
+ spin_lock(&ksm_mmlist_lock);
+ mm_slot = get_mm_slot(mm);
+ if (!list_empty(&mm_slot->rmap_list)) {
+ spin_unlock(&ksm_mmlist_lock);
+ remove_trailing_rmap_items(mm_slot, mm_slot->rmap_list.next);
+ spin_lock(&ksm_mmlist_lock);
+ }
+
+ if (ksm_scan.mm_slot == mm_slot) {
+ ksm_scan.mm_slot = list_entry(
+ mm_slot->mm_list.next, struct mm_slot, mm_list);
+ ksm_scan.address = 0;
+ ksm_scan.rmap_item = list_entry(
+ &ksm_scan.mm_slot->rmap_list, struct rmap_item, link);
+ if (ksm_scan.mm_slot == &ksm_mm_head)
+ ksm_scan.seqnr++;
+ }
+
+ hlist_del(&mm_slot->link);
+ list_del(&mm_slot->mm_list);
+ spin_unlock(&ksm_mmlist_lock);
+
+ free_mm_slot(mm_slot);
+ clear_bit(MMF_VM_MERGEABLE, &mm->flags);
mutex_unlock(&ksm_thread_mutex);
}
--
Date: Mon, 3 Aug 2009 13:18:16 +0100 (BST)
From: Hugh Dickins <hugh.dickins at tiscali.co.uk>
Subject: [PATCH 9/12] ksm: fix oom deadlock
There's a now-obvious deadlock in KSM's out-of-memory handling:
imagine ksmd or KSM_RUN_UNMERGE handling, holding ksm_thread_mutex,
trying to allocate a page to break KSM in an mm which becomes the
OOM victim (quite likely in the unmerge case): it's killed and goes
to exit, and hangs there waiting to acquire ksm_thread_mutex.
Clearly we must not require ksm_thread_mutex in __ksm_exit, simple
though that made everything else: perhaps use mmap_sem somehow?
And part of the answer lies in the comments on unmerge_ksm_pages:
__ksm_exit should also leave all the rmap_item removal to ksmd.
But there's a fundamental problem, that KSM relies upon mmap_sem to
guarantee the consistency of the mm it's dealing with, yet exit_mmap
tears down an mm without taking mmap_sem. And bumping mm_users won't
help at all, that just ensures that the pages the OOM killer assumes
are on their way to being freed will not be freed.
The best answer seems to be, to move the ksm_exit callout from just
before exit_mmap, to the middle of exit_mmap: after the mm's pages
have been freed (if the mmu_gather is flushed), but before its page
tables and vma structures have been freed; and down_write,up_write
mmap_sem there to serialize with KSM's own reliance on mmap_sem.
But KSM then needs to be careful, whenever it downs mmap_sem, to
check that the mm is not already exiting: there's a danger of using
find_vma on a layout that's being torn apart, or writing into page
tables which have been freed for reuse; and even do_anonymous_page
and __do_fault need to check they're not being called by break_ksm
to reinstate a pte after zap_pte_range has zapped that page table.
Though it might be clearer to add an exiting flag, set while holding
mmap_sem in __ksm_exit, that wouldn't cover the issue of reinstating
a zapped pte. All we need is to check whether mm_users is 0 - but
must remember that ksmd may detect that before __ksm_exit is reached.
So, ksm_test_exit(mm) added to comment such checks on mm->mm_users.
__ksm_exit now has to leave clearing up the rmap_items to ksmd,
that needs ksm_thread_mutex; but shift the exiting mm just after the
ksm_scan cursor so that it will soon be dealt with. __ksm_enter raise
mm_count to hold the mm_struct, ksmd's exit processing (exactly like
its processing when it finds all VM_MERGEABLEs unmapped) mmdrop it,
similar procedure for KSM_RUN_UNMERGE (which has stopped ksmd).
But also give __ksm_exit a fast path: when there's no complication
(no rmap_items attached to mm and it's not at the ksm_scan cursor),
it can safely do all the exiting work itself. This is not just an
optimization: when ksmd is not running, the raised mm_count would
otherwise leak mm_structs.
Signed-off-by: Hugh Dickins <hugh.dickins at tiscali.co.uk>
---
include/linux/ksm.h | 31 +++++++--
kernel/fork.c | 1
mm/ksm.c | 144 ++++++++++++++++++++++++++++--------------
mm/memory.c | 5 -
mm/mmap.c | 9 ++
5 files changed, 137 insertions(+), 53 deletions(-)
--- ksm8/include/linux/ksm.h 2009-08-01 05:02:09.000000000 +0100
+++ ksm9/include/linux/ksm.h 2009-08-02 13:50:41.000000000 +0100
@@ -12,11 +12,14 @@
#include <linux/sched.h>
#include <linux/vmstat.h>
+struct mmu_gather;
+
#ifdef CONFIG_KSM
int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
unsigned long end, int advice, unsigned long *vm_flags);
int __ksm_enter(struct mm_struct *mm);
-void __ksm_exit(struct mm_struct *mm);
+void __ksm_exit(struct mm_struct *mm,
+ struct mmu_gather **tlbp, unsigned long end);
static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
{
@@ -25,10 +28,24 @@ static inline int ksm_fork(struct mm_str
return 0;
}
-static inline void ksm_exit(struct mm_struct *mm)
+/*
+ * For KSM to handle OOM without deadlock when it's breaking COW in a
+ * likely victim of the OOM killer, exit_mmap() has to serialize with
+ * ksm_exit() after freeing mm's pages but before freeing its page tables.
+ * That leaves a window in which KSM might refault pages which have just
+ * been finally unmapped: guard against that with ksm_test_exit(), and
+ * use it after getting mmap_sem in ksm.c, to check if mm is exiting.
+ */
+static inline bool ksm_test_exit(struct mm_struct *mm)
+{
+ return atomic_read(&mm->mm_users) == 0;
+}
+
+static inline void ksm_exit(struct mm_struct *mm,
+ struct mmu_gather **tlbp, unsigned long end)
{
if (test_bit(MMF_VM_MERGEABLE, &mm->flags))
- __ksm_exit(mm);
+ __ksm_exit(mm, tlbp, end);
}
/*
@@ -64,7 +81,13 @@ static inline int ksm_fork(struct mm_str
return 0;
}
-static inline void ksm_exit(struct mm_struct *mm)
+static inline bool ksm_test_exit(struct mm_struct *mm)
+{
+ return 0;
+}
+
+static inline void ksm_exit(struct mm_struct *mm,
+ struct mmu_gather **tlbp, unsigned long end)
{
}
--- ksm8/kernel/fork.c 2009-08-01 05:02:09.000000000 +0100
+++ ksm9/kernel/fork.c 2009-08-02 13:50:41.000000000 +0100
@@ -492,7 +492,6 @@ void mmput(struct mm_struct *mm)
if (atomic_dec_and_test(&mm->mm_users)) {
exit_aio(mm);
- ksm_exit(mm);
exit_mmap(mm);
set_mm_exe_file(mm, NULL);
if (!list_empty(&mm->mmlist)) {
--- ksm8/mm/ksm.c 2009-08-02 13:50:32.000000000 +0100
+++ ksm9/mm/ksm.c 2009-08-02 13:50:41.000000000 +0100
@@ -32,6 +32,7 @@
#include <linux/mmu_notifier.h>
#include <linux/ksm.h>
+#include <asm/tlb.h>
#include <asm/tlbflush.h>
/*
@@ -347,6 +348,8 @@ static void break_cow(struct mm_struct *
struct vm_area_struct *vma;
down_read(&mm->mmap_sem);
+ if (ksm_test_exit(mm))
+ goto out;
vma = find_vma(mm, addr);
if (!vma || vma->vm_start > addr)
goto out;
@@ -365,6 +368,8 @@ static struct page *get_mergeable_page(s
struct page *page;
down_read(&mm->mmap_sem);
+ if (ksm_test_exit(mm))
+ goto out;
vma = find_vma(mm, addr);
if (!vma || vma->vm_start > addr)
goto out;
@@ -439,11 +444,11 @@ static void remove_rmap_item_from_tree(s
} else if (rmap_item->address & NODE_FLAG) {
unsigned char age;
/*
- * ksm_thread can and must skip the rb_erase, because
+ * Usually ksmd can and must skip the rb_erase, because
* root_unstable_tree was already reset to RB_ROOT.
- * But __ksm_exit has to be careful: do the rb_erase
- * if it's interrupting a scan, and this rmap_item was
- * inserted by this scan rather than left from before.
+ * But be careful when an mm is exiting: do the rb_erase
+ * if this rmap_item was inserted by this scan, rather
+ * than left over from before.
*/
age = (unsigned char)(ksm_scan.seqnr - rmap_item->address);
BUG_ON(age > 1);
@@ -491,6 +496,8 @@ static int unmerge_ksm_pages(struct vm_a
int err = 0;
for (addr = start; addr < end && !err; addr += PAGE_SIZE) {
+ if (ksm_test_exit(vma->vm_mm))
+ break;
if (signal_pending(current))
err = -ERESTARTSYS;
else
@@ -507,34 +514,50 @@ static int unmerge_and_remove_all_rmap_i
int err = 0;
spin_lock(&ksm_mmlist_lock);
- mm_slot = list_entry(ksm_mm_head.mm_list.next,
+ ksm_scan.mm_slot = list_entry(ksm_mm_head.mm_list.next,
struct mm_slot, mm_list);
spin_unlock(&ksm_mmlist_lock);
- while (mm_slot != &ksm_mm_head) {
+ for (mm_slot = ksm_scan.mm_slot;
+ mm_slot != &ksm_mm_head; mm_slot = ksm_scan.mm_slot) {
mm = mm_slot->mm;
down_read(&mm->mmap_sem);
for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ if (ksm_test_exit(mm))
+ break;
if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma)
continue;
err = unmerge_ksm_pages(vma,
vma->vm_start, vma->vm_end);
- if (err) {
- up_read(&mm->mmap_sem);
- goto out;
- }
+ if (err)
+ goto error;
}
+
remove_trailing_rmap_items(mm_slot, mm_slot->rmap_list.next);
- up_read(&mm->mmap_sem);
spin_lock(&ksm_mmlist_lock);
- mm_slot = list_entry(mm_slot->mm_list.next,
+ ksm_scan.mm_slot = list_entry(mm_slot->mm_list.next,
struct mm_slot, mm_list);
- spin_unlock(&ksm_mmlist_lock);
+ if (ksm_test_exit(mm)) {
+ hlist_del(&mm_slot->link);
+ list_del(&mm_slot->mm_list);
+ spin_unlock(&ksm_mmlist_lock);
+
+ free_mm_slot(mm_slot);
+ clear_bit(MMF_VM_MERGEABLE, &mm->flags);
+ up_read(&mm->mmap_sem);
+ mmdrop(mm);
+ } else {
+ spin_unlock(&ksm_mmlist_lock);
+ up_read(&mm->mmap_sem);
+ }
}
ksm_scan.seqnr = 0;
-out:
+ return 0;
+
+error:
+ up_read(&mm->mmap_sem);
spin_lock(&ksm_mmlist_lock);
ksm_scan.mm_slot = &ksm_mm_head;
spin_unlock(&ksm_mmlist_lock);
@@ -755,6 +778,9 @@ static int try_to_merge_with_ksm_page(st
int err = -EFAULT;
down_read(&mm1->mmap_sem);
+ if (ksm_test_exit(mm1))
+ goto out;
+
vma = find_vma(mm1, addr1);
if (!vma || vma->vm_start > addr1)
goto out;
@@ -796,6 +822,10 @@ static int try_to_merge_two_pages(struct
return err;
down_read(&mm1->mmap_sem);
+ if (ksm_test_exit(mm1)) {
+ up_read(&mm1->mmap_sem);
+ goto out;
+ }
vma = find_vma(mm1, addr1);
if (!vma || vma->vm_start > addr1) {
up_read(&mm1->mmap_sem);
@@ -1181,7 +1211,12 @@ next_mm:
mm = slot->mm;
down_read(&mm->mmap_sem);
- for (vma = find_vma(mm, ksm_scan.address); vma; vma = vma->vm_next) {
+ if (ksm_test_exit(mm))
+ vma = NULL;
+ else
+ vma = find_vma(mm, ksm_scan.address);
+
+ for (; vma; vma = vma->vm_next) {
if (!(vma->vm_flags & VM_MERGEABLE))
continue;
if (ksm_scan.address < vma->vm_start)
@@ -1190,6 +1225,8 @@ next_mm:
ksm_scan.address = vma->vm_end;
while (ksm_scan.address < vma->vm_end) {
+ if (ksm_test_exit(mm))
+ break;
*page = follow_page(vma, ksm_scan.address, FOLL_GET);
if (*page && PageAnon(*page)) {
flush_anon_page(vma, *page, ksm_scan.address);
@@ -1212,6 +1249,11 @@ next_mm:
}
}
+ if (ksm_test_exit(mm)) {
+ ksm_scan.address = 0;
+ ksm_scan.rmap_item = list_entry(&slot->rmap_list,
+ struct rmap_item, link);
+ }
/*
* Nuke all the rmap_items that are above this current rmap:
* because there were no VM_MERGEABLE vmas with such addresses.
@@ -1226,24 +1268,29 @@ next_mm:
* We've completed a full scan of all vmas, holding mmap_sem
* throughout, and found no VM_MERGEABLE: so do the same as
* __ksm_exit does to remove this mm from all our lists now.
+ * This applies either when cleaning up after __ksm_exit
+ * (but beware: we can reach here even before __ksm_exit),
+ * or when all VM_MERGEABLE areas have been unmapped (and
+ * mmap_sem then protects against race with MADV_MERGEABLE).
*/
hlist_del(&slot->link);
list_del(&slot->mm_list);
+ spin_unlock(&ksm_mmlist_lock);
+
free_mm_slot(slot);
clear_bit(MMF_VM_MERGEABLE, &mm->flags);
+ up_read(&mm->mmap_sem);
+ mmdrop(mm);
+ } else {
+ spin_unlock(&ksm_mmlist_lock);
+ up_read(&mm->mmap_sem);
}
- spin_unlock(&ksm_mmlist_lock);
- up_read(&mm->mmap_sem);
/* Repeat until we've completed scanning the whole list */
slot = ksm_scan.mm_slot;
if (slot != &ksm_mm_head)
goto next_mm;
- /*
- * Bump seqnr here rather than at top, so that __ksm_exit
- * can skip rb_erase on unstable tree until we run again.
- */
ksm_scan.seqnr++;
return NULL;
}
@@ -1368,6 +1415,7 @@ int __ksm_enter(struct mm_struct *mm)
spin_unlock(&ksm_mmlist_lock);
set_bit(MMF_VM_MERGEABLE, &mm->flags);
+ atomic_inc(&mm->mm_count);
if (needs_wakeup)
wake_up_interruptible(&ksm_thread_wait);
@@ -1375,41 +1423,45 @@ int __ksm_enter(struct mm_struct *mm)
return 0;
}
-void __ksm_exit(struct mm_struct *mm)
+void __ksm_exit(struct mm_struct *mm,
+ struct mmu_gather **tlbp, unsigned long end)
{
struct mm_slot *mm_slot;
+ int easy_to_free = 0;
/*
- * This process is exiting: doesn't hold and doesn't need mmap_sem;
- * but we do need to exclude ksmd and other exiters while we modify
- * the various lists and trees.
+ * This process is exiting: if it's straightforward (as is the
+ * case when ksmd was never running), free mm_slot immediately.
+ * But if it's at the cursor or has rmap_items linked to it, use
+ * mmap_sem to synchronize with any break_cows before pagetables
+ * are freed, and leave the mm_slot on the list for ksmd to free.
+ * Beware: ksm may already have noticed it exiting and freed the slot.
*/
- mutex_lock(&ksm_thread_mutex);
+
spin_lock(&ksm_mmlist_lock);
mm_slot = get_mm_slot(mm);
- if (!list_empty(&mm_slot->rmap_list)) {
- spin_unlock(&ksm_mmlist_lock);
- remove_trailing_rmap_items(mm_slot, mm_slot->rmap_list.next);
- spin_lock(&ksm_mmlist_lock);
- }
-
- if (ksm_scan.mm_slot == mm_slot) {
- ksm_scan.mm_slot = list_entry(
- mm_slot->mm_list.next, struct mm_slot, mm_list);
- ksm_scan.address = 0;
- ksm_scan.rmap_item = list_entry(
- &ksm_scan.mm_slot->rmap_list, struct rmap_item, link);
- if (ksm_scan.mm_slot == &ksm_mm_head)
- ksm_scan.seqnr++;
+ if (mm_slot && ksm_scan.mm_slot != mm_slot) {
+ if (list_empty(&mm_slot->rmap_list)) {
+ hlist_del(&mm_slot->link);
+ list_del(&mm_slot->mm_list);
+ easy_to_free = 1;
+ } else {
+ list_move(&mm_slot->mm_list,
+ &ksm_scan.mm_slot->mm_list);
+ }
}
-
- hlist_del(&mm_slot->link);
- list_del(&mm_slot->mm_list);
spin_unlock(&ksm_mmlist_lock);
- free_mm_slot(mm_slot);
- clear_bit(MMF_VM_MERGEABLE, &mm->flags);
- mutex_unlock(&ksm_thread_mutex);
+ if (easy_to_free) {
+ free_mm_slot(mm_slot);
+ clear_bit(MMF_VM_MERGEABLE, &mm->flags);
+ mmdrop(mm);
+ } else if (mm_slot) {
+ tlb_finish_mmu(*tlbp, 0, end);
+ down_write(&mm->mmap_sem);
+ up_write(&mm->mmap_sem);
+ *tlbp = tlb_gather_mmu(mm, 1);
+ }
}
#define KSM_ATTR_RO(_name) \
--- ksm8/mm/memory.c 2009-08-01 05:02:09.000000000 +0100
+++ ksm9/mm/memory.c 2009-08-02 13:50:41.000000000 +0100
@@ -2647,8 +2647,9 @@ static int do_anonymous_page(struct mm_s
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
- if (!pte_none(*page_table))
+ if (!pte_none(*page_table) || ksm_test_exit(mm))
goto release;
+
inc_mm_counter(mm, anon_rss);
page_add_new_anon_rmap(page, vma, address);
set_pte_at(mm, address, page_table, entry);
@@ -2790,7 +2791,7 @@ static int __do_fault(struct mm_struct *
* handle that later.
*/
/* Only go through if we didn't race with anybody else... */
- if (likely(pte_same(*page_table, orig_pte))) {
+ if (likely(pte_same(*page_table, orig_pte) && !ksm_test_exit(mm))) {
flush_icache_page(vma, page);
entry = mk_pte(page, vma->vm_page_prot);
if (flags & FAULT_FLAG_WRITE)
--- ksm8/mm/mmap.c 2009-06-25 05:18:10.000000000 +0100
+++ ksm9/mm/mmap.c 2009-08-02 13:50:41.000000000 +0100
@@ -27,6 +27,7 @@
#include <linux/mount.h>
#include <linux/mempolicy.h>
#include <linux/rmap.h>
+#include <linux/ksm.h>
#include <linux/mmu_notifier.h>
#include <linux/perf_counter.h>
@@ -2114,6 +2115,14 @@ void exit_mmap(struct mm_struct *mm)
/* Use -1 here to ensure all VMAs in the mm are unmapped */
end = unmap_vmas(&tlb, vma, 0, -1, &nr_accounted, NULL);
vm_unacct_memory(nr_accounted);
+
+ /*
+ * For KSM to handle OOM without deadlock when it's breaking COW in a
+ * likely victim of the OOM killer, we must serialize with ksm_exit()
+ * after freeing mm's pages but before freeing its page tables.
+ */
+ ksm_exit(mm, &tlb, end);
+
free_pgtables(tlb, vma, FIRST_USER_ADDRESS, 0);
tlb_finish_mmu(tlb, 0, end);
--
Date: Mon, 3 Aug 2009 13:19:13 +0100 (BST)
From: Hugh Dickins <hugh.dickins at tiscali.co.uk>
Subject: [PATCH 10/12] ksm: sysfs and defaults
At present KSM is just a waste of space if you don't have CONFIG_SYSFS=y
to provide the /sys/kernel/mm/ksm files to tune and activate it.
Make KSM depend on SYSFS? Could do, but it might be better to provide
some defaults so that KSM works out-of-the-box, ready for testers to
madvise MADV_MERGEABLE, even without SYSFS.
Though anyone serious is likely to want to retune the numbers to their
taste once they have experience; and whether these settings ever reach
2.6.32 can be discussed along the way.
Save 1kB from tiny kernels by #ifdef'ing the SYSFS side of it.
Signed-off-by: Hugh Dickins <hugh.dickins at tiscali.co.uk>
---
mm/ksm.c | 26 +++++++++++++++++++-------
1 file changed, 19 insertions(+), 7 deletions(-)
--- ksm9/mm/ksm.c 2009-08-02 13:50:41.000000000 +0100
+++ ksm10/mm/ksm.c 2009-08-02 13:50:48.000000000 +0100
@@ -163,18 +163,18 @@ static unsigned long ksm_pages_unshared;
static unsigned long ksm_rmap_items;
/* Limit on the number of unswappable pages used */
-static unsigned long ksm_max_kernel_pages;
+static unsigned long ksm_max_kernel_pages = 2000;
/* Number of pages ksmd should scan in one batch */
-static unsigned int ksm_thread_pages_to_scan;
+static unsigned int ksm_thread_pages_to_scan = 200;
/* Milliseconds ksmd should sleep between batches */
-static unsigned int ksm_thread_sleep_millisecs;
+static unsigned int ksm_thread_sleep_millisecs = 20;
#define KSM_RUN_STOP 0
#define KSM_RUN_MERGE 1
#define KSM_RUN_UNMERGE 2
-static unsigned int ksm_run;
+static unsigned int ksm_run = KSM_RUN_MERGE;
static DECLARE_WAIT_QUEUE_HEAD(ksm_thread_wait);
static DEFINE_MUTEX(ksm_thread_mutex);
@@ -506,6 +506,10 @@ static int unmerge_ksm_pages(struct vm_a
return err;
}
+#ifdef CONFIG_SYSFS
+/*
+ * Only called through the sysfs control interface:
+ */
static int unmerge_and_remove_all_rmap_items(void)
{
struct mm_slot *mm_slot;
@@ -563,6 +567,7 @@ error:
spin_unlock(&ksm_mmlist_lock);
return err;
}
+#endif /* CONFIG_SYSFS */
static u32 calc_checksum(struct page *page)
{
@@ -1464,6 +1469,11 @@ void __ksm_exit(struct mm_struct *mm,
}
}
+#ifdef CONFIG_SYSFS
+/*
+ * This all compiles without CONFIG_SYSFS, but is a waste of space.
+ */
+
#define KSM_ATTR_RO(_name) \
static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
#define KSM_ATTR(_name) \
@@ -1646,6 +1656,7 @@ static struct attribute_group ksm_attr_g
.attrs = ksm_attrs,
.name = "ksm",
};
+#endif /* CONFIG_SYSFS */
static int __init ksm_init(void)
{
@@ -1667,16 +1678,17 @@ static int __init ksm_init(void)
goto out_free2;
}
+#ifdef CONFIG_SYSFS
err = sysfs_create_group(mm_kobj, &ksm_attr_group);
if (err) {
printk(KERN_ERR "ksm: register sysfs failed\n");
- goto out_free3;
+ kthread_stop(ksm_thread);
+ goto out_free2;
}
+#endif /* CONFIG_SYSFS */
return 0;
-out_free3:
- kthread_stop(ksm_thread);
out_free2:
mm_slots_hash_free();
out_free1:
--
Date: Mon, 3 Aug 2009 13:21:34 +0100 (BST)
From: Hugh Dickins <hugh.dickins at tiscali.co.uk>
Subject: [PATCH 11/12] ksm: add some documentation
Add Documentation/vm/ksm.txt: how to use the Kernel Samepage Merging feature
Signed-off-by: Hugh Dickins <hugh.dickins at tiscali.co.uk>
Cc: Michael Kerrisk <mtk.manpages at googlemail.com>
Cc: Randy Dunlap <randy.dunlap at oracle.com>
---
Documentation/vm/00-INDEX | 2
Documentation/vm/ksm.txt | 89 ++++++++++++++++++++++++++++++++++++
mm/Kconfig | 1
3 files changed, 92 insertions(+)
--- ksm10/Documentation/vm/00-INDEX 2009-06-10 04:05:27.000000000 +0100
+++ ksm11/Documentation/vm/00-INDEX 2009-08-02 13:50:57.000000000 +0100
@@ -6,6 +6,8 @@ balance
- various information on memory balancing.
hugetlbpage.txt
- a brief summary of hugetlbpage support in the Linux kernel.
+ksm.txt
+ - how to use the Kernel Samepage Merging feature.
locking
- info on how locking and synchronization is done in the Linux vm code.
numa
--- ksm10/Documentation/vm/ksm.txt 1970-01-01 01:00:00.000000000 +0100
+++ ksm11/Documentation/vm/ksm.txt 2009-08-02 13:50:57.000000000 +0100
@@ -0,0 +1,89 @@
+How to use the Kernel Samepage Merging feature
+----------------------------------------------
+
+KSM is a memory-saving de-duplication feature, enabled by CONFIG_KSM=y,
+added to the Linux kernel in 2.6.32. See mm/ksm.c for its implementation,
+and http://lwn.net/Articles/306704/ and http://lwn.net/Articles/330589/
+
+The KSM daemon ksmd periodically scans those areas of user memory which
+have been registered with it, looking for pages of identical content which
+can be replaced by a single write-protected page (which is automatically
+copied if a process later wants to update its content).
+
+KSM was originally developed for use with KVM (where it was known as
+Kernel Shared Memory), to fit more virtual machines into physical memory,
+by sharing the data common between them. But it can be useful to any
+application which generates many instances of the same data.
+
+KSM only merges anonymous (private) pages, never pagecache (file) pages.
+KSM's merged pages are at present locked into kernel memory for as long
+as they are shared: so cannot be swapped out like the user pages they
+replace (but swapping KSM pages should follow soon in a later release).
+
+KSM only operates on those areas of address space which an application
+has advised to be likely candidates for merging, by using the madvise(2)
+system call: int madvise(addr, length, MADV_MERGEABLE).
+
+The app may call int madvise(addr, length, MADV_UNMERGEABLE) to cancel
+that advice and restore unshared pages: whereupon KSM unmerges whatever
+it merged in that range. Note: this unmerging call may suddenly require
+more memory than is available - possibly failing with EAGAIN, but more
+probably arousing the Out-Of-Memory killer.
+
+If KSM is not configured into the running kernel, madvise MADV_MERGEABLE
+and MADV_UNMERGEABLE simply fail with EINVAL. If the running kernel was
+built with CONFIG_KSM=y, those calls will normally succeed: even if the
+the KSM daemon is not currently running, MADV_MERGEABLE still registers
+the range for whenever the KSM daemon is started; even if the range
+cannot contain any pages which KSM could actually merge; even if
+MADV_UNMERGEABLE is applied to a range which was never MADV_MERGEABLE.
+
+Like other madvise calls, they are intended for use on mapped areas of
+the user address space: they will report ENOMEM if the specified range
+includes unmapped gaps (though working on the intervening mapped areas),
+and might fail with EAGAIN if not enough memory for internal structures.
+
+Applications should be considerate in their use of MADV_MERGEABLE,
+restricting its use to areas likely to benefit. KSM's scans may use
+a lot of processing power, and its kernel-resident pages are a limited
+resource. Some installations will disable KSM for these reasons.
+
+The KSM daemon is controlled by sysfs files in /sys/kernel/mm/ksm/,
+readable by all but writable only by root:
+
+max_kernel_pages - set to maximum number of kernel pages that KSM may use
+ e.g. "echo 2000 > /sys/kernel/mm/ksm/max_kernel_pages"
+ Value 0 imposes no limit on the kernel pages KSM may use;
+ but note that any process using MADV_MERGEABLE can cause
+ KSM to allocate these pages, unswappable until it exits.
+ Default: 2000 (chosen for demonstration purposes)
+
+pages_to_scan - how many present pages to scan before ksmd goes to sleep
+ e.g. "echo 200 > /sys/kernel/mm/ksm/pages_to_scan"
+ Default: 200 (chosen for demonstration purposes)
+
+sleep_millisecs - how many milliseconds ksmd should sleep before next scan
+ e.g. "echo 20 > /sys/kernel/mm/ksm/sleep_millisecs"
+ Default: 20 (chosen for demonstration purposes)
+
+run - set 0 to stop ksmd from running but keep merged pages,
+ set 1 to run ksmd e.g. "echo 1 > /sys/kernel/mm/ksm/run",
+ set 2 to stop ksmd and unmerge all pages currently merged,
+ but leave mergeable areas registered for next run
+ Default: 1 (for immediate use by apps which register)
+
+The effectiveness of KSM and MADV_MERGEABLE is shown in /sys/kernel/mm/ksm/:
+
+pages_shared - how many shared unswappable kernel pages KSM is using
+pages_sharing - how many more sites are sharing them i.e. how much saved
+pages_unshared - how many pages unique but repeatedly checked for merging
+pages_volatile - how many pages changing too fast to be placed in a tree
+full_scans - how many times all mergeable areas have been scanned
+
+A high ratio of pages_sharing to pages_shared indicates good sharing, but
+a high ratio of pages_unshared to pages_sharing indicates wasted effort.
+pages_volatile embraces several different kinds of activity, but a high
+proportion there would also indicate poor use of madvise MADV_MERGEABLE.
+
+Izik Eidus,
+Hugh Dickins, 30 July 2009
--- ksm10/mm/Kconfig 2009-08-01 05:02:09.000000000 +0100
+++ ksm11/mm/Kconfig 2009-08-02 13:50:57.000000000 +0100
@@ -224,6 +224,7 @@ config KSM
the many instances by a single resident page with that content, so
saving memory until one or another app needs to modify the content.
Recommended for use with KVM, or with other duplicative applications.
+ See Documentation/vm/ksm.txt for more information.
config DEFAULT_MMAP_MIN_ADDR
int "Low address space to protect from user allocation"
--
Date: Mon, 3 Aug 2009 13:22:53 +0100 (BST)
From: Hugh Dickins <hugh.dickins at tiscali.co.uk>
Subject: [PATCH 12/12] ksm: remove VM_MERGEABLE_FLAGS
KSM originally stood for Kernel Shared Memory: but the kernel has long
supported shared memory, and VM_SHARED and VM_MAYSHARE vmas, and KSM is
something else. So we switched to saying "merge" instead of "share".
But Chris Wright points out that this is confusing where mmap.c merges
adjacent vmas: most especially in the name VM_MERGEABLE_FLAGS, used by
is_mergeable_vma() to let vmas be merged despite flags being different.
Call it VMA_MERGE_DESPITE_FLAGS? Perhaps, but at present it consists
only of VM_CAN_NONLINEAR: so for now it's clearer on all sides to use
that directly, with a comment on it in is_mergeable_vma().
Signed-off-by: Hugh Dickins <hugh.dickins at tiscali.co.uk>
---
This patch got lost along the way last time: no big deal but try again.
mm/mmap.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
--- ksm11/mm/mmap.c 2009-08-02 13:50:41.000000000 +0100
+++ ksm12/mm/mmap.c 2009-08-02 13:51:04.000000000 +0100
@@ -660,9 +660,6 @@ again: remove_next = 1 + (end > next->
validate_mm(mm);
}
-/* Flags that can be inherited from an existing mapping when merging */
-#define VM_MERGEABLE_FLAGS (VM_CAN_NONLINEAR)
-
/*
* If the vma has a ->close operation then the driver probably needs to release
* per-vma resources, so we don't attempt to merge those.
@@ -670,7 +667,8 @@ again: remove_next = 1 + (end > next->
static inline int is_mergeable_vma(struct vm_area_struct *vma,
struct file *file, unsigned long vm_flags)
{
- if ((vma->vm_flags ^ vm_flags) & ~VM_MERGEABLE_FLAGS)
+ /* VM_CAN_NONLINEAR may get set later by f_op->mmap() */
+ if ((vma->vm_flags ^ vm_flags) & ~VM_CAN_NONLINEAR)
return 0;
if (vma->vm_file != file)
return 0;
Index: kernel.spec
===================================================================
RCS file: /cvs/pkgs/rpms/kernel/devel/kernel.spec,v
retrieving revision 1.1703
retrieving revision 1.1704
diff -u -p -r1.1703 -r1.1704
--- kernel.spec 7 Aug 2009 16:12:21 -0000 1.1703
+++ kernel.spec 7 Aug 2009 19:07:39 -0000 1.1704
@@ -668,6 +668,7 @@ Patch1518: hid-ignore-all-recent-imon-de
Patch1550: linux-2.6-ksm.patch
Patch1551: linux-2.6-ksm-kvm.patch
+Patch1552: linux-2.6-ksm-updates.patch
# nouveau + drm fixes
Patch1810: drm-radeon-fixes.patch
@@ -1278,6 +1279,7 @@ ApplyPatch hid-ignore-all-recent-imon-de
# Add kernel KSM support
ApplyPatch linux-2.6-ksm.patch
+ApplyPatch linux-2.6-ksm-updates.patch
# Optimize KVM for KSM support
ApplyPatch linux-2.6-ksm-kvm.patch
@@ -1964,6 +1966,9 @@ fi
# and build.
%changelog
+* Fri Aug 07 2009 Justin M. Forbes <jforbes at redhat.com>
+- Apply KSM updates from upstream
+
* Fri Aug 07 2009 Hans de Goede <hdegoede at redhat.com>
- When building a dracut generic initrd tell new-kernel-pkg to use that
instead of running mkinitrd
More information about the scm-commits
mailing list