The patch titled
Subject: mm: support madvise(MADV_FREE)
has been added to the -mm tree. Its filename is
mm-support-madvisemadv_free.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-support-madvisemadv_free.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-support-madvisemadv_free.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: Minchan Kim <minchan@xxxxxxxxxx>
Subject: mm: support madvise(MADV_FREE)
Linux doesn't have an ability to free pages lazy while other OS already
have been supported that named by madvise(MADV_FREE).
The gain is clear that kernel can discard freed pages rather than swapping
out or OOM if memory pressure happens.
Without memory pressure, freed pages would be reused by userspace without
another additional overhead(ex, page fault + allocation + zeroing).
Jason Evans said:
: Facebook has been using MAP_UNINITIALIZED
: (https://lkml.org/lkml/2012/1/18/308) in some of its applications for
: several years, but there are operational costs to maintaining this
: out-of-tree in our kernel and in jemalloc, and we are anxious to retire it
: in favor of MADV_FREE. When we first enabled MAP_UNINITIALIZED it
: increased throughput for much of our workload by ~5%, and although the
: benefit has decreased using newer hardware and kernels, there is still
: enough benefit that we cannot reasonably retire it without a replacement.
:
: Aside from Facebook operations, there are numerous broadly used
: applications that would benefit from MADV_FREE. The ones that immediately
: come to mind are redis, varnish, and MariaDB. I don't have much insight
: into Android internals and development process, but I would hope to see
: MADV_FREE support eventually end up there as well to benefit applications
: linked with the integrated jemalloc.
:
: jemalloc will use MADV_FREE once it becomes available in the Linux kernel.
: In fact, jemalloc already uses MADV_FREE or equivalent everywhere it's
: available: *BSD, OS X, Windows, and Solaris -- every platform except Linux
: (and AIX, but I'm not sure it even compiles on AIX). The lack of
: MADV_FREE on Linux forced me down a long series of increasingly
: sophisticated heuristics for madvise() volume reduction, and even so this
: remains a common performance issue for people using jemalloc on Linux.
: Please integrate MADV_FREE; many people will benefit substantially.
How it works:
When madvise syscall is called, VM clears dirty bit of ptes of the range.
If memory pressure happens, VM checks dirty bit of page table and if it
found still "clean", it means it's a "lazyfree pages" so VM could discard
the page instead of swapping out. Once there was store operation for the
page before VM peek a page to reclaim, dirty bit is set so VM can swap out
the page instead of discarding.
One thing we should notice is that basically, MADV_FREE relies on dirty bit
in page table entry to decide whether VM allows to discard the page or not.
IOW, if page table entry includes marked dirty bit, VM shouldn't discard
the page.
However, as a example, if swap-in by read fault happens, page table entry
doesn't have dirty bit so MADV_FREE could discard the page wrongly.
For avoiding the problem, MADV_FREE did more checks with PageDirty
and PageSwapCache. It worked out because swapped-in page lives on
swap cache and since it is evicted from the swap cache, the page has
PG_dirty flag. So both page flags check effectively prevent
wrong discarding by MADV_FREE.
However, a problem in above logic is that swapped-in page has
PG_dirty still after they are removed from swap cache so VM cannot
consider the page as freeable any more even if madvise_free is
called in future.
Look at below example for detail.
ptr = malloc();
memset(ptr);
..
..
.. heavy memory pressure so all of pages are swapped out
..
..
var = *ptr; -> a page swapped-in and could be removed from
swapcache. Then, page table doesn't mark
dirty bit and page descriptor includes PG_dirty
..
..
madvise_free(ptr); -> It doesn't clear PG_dirty of the page.
..
..
..
.. heavy memory pressure again.
.. In this time, VM cannot discard the page because the page
.. has *PG_dirty*
To solve the problem, this patch clears PG_dirty if only the page is owned
exclusively by current process when madvise is called because PG_dirty
represents ptes's dirtiness in several processes so we could clear it only
if we own it exclusively.
Firstly, heavy users would be general allocators(ex, jemalloc, tcmalloc
and hope glibc supports it) and jemalloc/tcmalloc already have supported
the feature for other OS(ex, FreeBSD)
barrios@blaptop:~/benchmark/ebizzy$ lscpu
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Byte Order: Little Endian
CPU(s): 12
On-line CPU(s) list: 0-11
Thread(s) per core: 1
Core(s) per socket: 1
Socket(s): 12
NUMA node(s): 1
Vendor ID: GenuineIntel
CPU family: 6
Model: 2
Stepping: 3
CPU MHz: 3200.185
BogoMIPS: 6400.53
Virtualization: VT-x
Hypervisor vendor: KVM
Virtualization type: full
L1d cache: 32K
L1i cache: 32K
L2 cache: 4096K
NUMA node0 CPU(s): 0-11
ebizzy benchmark(./ebizzy -S 10 -n 512)
Higher avg is better.
vanilla-jemalloc MADV_free-jemalloc
1 thread
records: 10 records: 10
avg: 2961.90 avg: 12069.70
std: 71.96(2.43%) std: 186.68(1.55%)
max: 3070.00 max: 12385.00
min: 2796.00 min: 11746.00
2 thread
records: 10 records: 10
avg: 5020.00 avg: 17827.00
std: 264.87(5.28%) std: 358.52(2.01%)
max: 5244.00 max: 18760.00
min: 4251.00 min: 17382.00
4 thread
records: 10 records: 10
avg: 8988.80 avg: 27930.80
std: 1175.33(13.08%) std: 3317.33(11.88%)
max: 9508.00 max: 30879.00
min: 5477.00 min: 21024.00
8 thread
records: 10 records: 10
avg: 13036.50 avg: 33739.40
std: 170.67(1.31%) std: 5146.22(15.25%)
max: 13371.00 max: 40572.00
min: 12785.00 min: 24088.00
16 thread
records: 10 records: 10
avg: 11092.40 avg: 31424.20
std: 710.60(6.41%) std: 3763.89(11.98%)
max: 12446.00 max: 36635.00
min: 9949.00 min: 25669.00
32 thread
records: 10 records: 10
avg: 11067.00 avg: 34495.80
std: 971.06(8.77%) std: 2721.36(7.89%)
max: 12010.00 max: 38598.00
min: 9002.00 min: 30636.00
In summary, MADV_FREE is about much faster than MADV_DONTNEED.
This patch (of 12):
Add core MADV_FREE implementation.
Signed-off-by: Minchan Kim <minchan@xxxxxxxxxx>
Acked-by: Michal Hocko <mhocko@xxxxxxxx>
Acked-by: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Mika Penttil <mika.penttila@xxxxxxxxxxxx>
Cc: Michael Kerrisk <mtk.manpages@xxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
Cc: Jason Evans <je@xxxxxx>
Cc: Daniel Micay <danielmicay@xxxxxxxxx>
Cc: "Kirill A. Shutemov" <kirill@xxxxxxxxxxxxx>
Cc: "Shaohua Li" <shli@xxxxxxxxxx>
Cc: <yalin.wang2010@xxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
Cc: "James E.J. Bottomley" <jejb@xxxxxxxxxxxxxxxx>
Cc: "Kirill A. Shutemov" <kirill@xxxxxxxxxxxxx>
Cc: "Shaohua Li" <shli@xxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Arnd Bergmann <arnd@xxxxxxxx>
Cc: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx>
Cc: Catalin Marinas <catalin.marinas@xxxxxxx>
Cc: Chen Gang <gang.chen.5i5j@xxxxxxxxx>
Cc: Chris Zankel <chris@xxxxxxxxxx>
Cc: Darrick J. Wong <darrick.wong@xxxxxxxxxx>
Cc: David S. Miller <davem@xxxxxxxxxxxxx>
Cc: Helge Deller <deller@xxxxxx>
Cc: Ivan Kokshaysky <ink@xxxxxxxxxxxxxxxxxxxx>
Cc: Matt Turner <mattst88@xxxxxxxxx>
Cc: Max Filippov <jcmvbkbc@xxxxxxxxx>
Cc: Ralf Baechle <ralf@xxxxxxxxxxxxxx>
Cc: Richard Henderson <rth@xxxxxxxxxxx>
Cc: Roland Dreier <roland@xxxxxxxxxx>
Cc: Russell King <rmk@xxxxxxxxxxxxxxxx>
Cc: Shaohua Li <shli@xxxxxxxxxx>
Cc: Will Deacon <will.deacon@xxxxxxx>
Cc: Wu Fengguang <fengguang.wu@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/rmap.h | 1
include/linux/vm_event_item.h | 1
include/uapi/asm-generic/mman-common.h | 1
mm/madvise.c | 168 +++++++++++++++++++++++
mm/rmap.c | 8 +
mm/swap_state.c | 5
mm/vmscan.c | 10 +
mm/vmstat.c | 1
8 files changed, 190 insertions(+), 5 deletions(-)
diff -puN include/linux/rmap.h~mm-support-madvisemadv_free include/linux/rmap.h
--- a/include/linux/rmap.h~mm-support-madvisemadv_free
+++ a/include/linux/rmap.h
@@ -85,6 +85,7 @@ enum ttu_flags {
TTU_UNMAP = 1, /* unmap mode */
TTU_MIGRATION = 2, /* migration mode */
TTU_MUNLOCK = 4, /* munlock mode */
+ TTU_LZFREE = 8, /* lazy free mode */
TTU_IGNORE_MLOCK = (1 << 8), /* ignore mlock */
TTU_IGNORE_ACCESS = (1 << 9), /* don't age */
diff -puN include/linux/vm_event_item.h~mm-support-madvisemadv_free include/linux/vm_event_item.h
--- a/include/linux/vm_event_item.h~mm-support-madvisemadv_free
+++ a/include/linux/vm_event_item.h
@@ -25,6 +25,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PS
FOR_ALL_ZONES(PGALLOC),
PGFREE, PGACTIVATE, PGDEACTIVATE,
PGFAULT, PGMAJFAULT,
+ PGLAZYFREED,
FOR_ALL_ZONES(PGREFILL),
FOR_ALL_ZONES(PGSTEAL_KSWAPD),
FOR_ALL_ZONES(PGSTEAL_DIRECT),
diff -puN include/uapi/asm-generic/mman-common.h~mm-support-madvisemadv_free include/uapi/asm-generic/mman-common.h
--- a/include/uapi/asm-generic/mman-common.h~mm-support-madvisemadv_free
+++ a/include/uapi/asm-generic/mman-common.h
@@ -39,6 +39,7 @@
#define MADV_SEQUENTIAL 2 /* expect sequential page references */
#define MADV_WILLNEED 3 /* will need these pages */
#define MADV_DONTNEED 4 /* don't need these pages */
+#define MADV_FREE 5 /* free pages only if memory pressure */
/* common parameters: try to keep these consistent across architectures */
#define MADV_REMOVE 9 /* remove these pages & resources */
diff -puN mm/madvise.c~mm-support-madvisemadv_free mm/madvise.c
--- a/mm/madvise.c~mm-support-madvisemadv_free
+++ a/mm/madvise.c
@@ -20,6 +20,9 @@
#include <linux/backing-dev.h>
#include <linux/swap.h>
#include <linux/swapops.h>
+#include <linux/mmu_notifier.h>
+
+#include <asm/tlb.h>
/*
* Any behaviour which results in changes to the vma->vm_flags needs to
@@ -32,6 +35,7 @@ static int madvise_need_mmap_write(int b
case MADV_REMOVE:
case MADV_WILLNEED:
case MADV_DONTNEED:
+ case MADV_FREE:
return 0;
default:
/* be safe, default to 1. list exceptions explicitly */
@@ -256,6 +260,161 @@ static long madvise_willneed(struct vm_a
return 0;
}
+static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
+ unsigned long end, struct mm_walk *walk)
+
+{
+ struct mmu_gather *tlb = walk->private;
+ struct mm_struct *mm = tlb->mm;
+ struct vm_area_struct *vma = walk->vma;
+ spinlock_t *ptl;
+ pte_t *orig_pte, *pte, ptent;
+ struct page *page;
+
+ split_huge_pmd(vma, pmd, addr);
+ if (pmd_trans_unstable(pmd))
+ return 0;
+
+ orig_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+ arch_enter_lazy_mmu_mode();
+ for (; addr != end; pte++, addr += PAGE_SIZE) {
+ ptent = *pte;
+
+ if (!pte_present(ptent))
+ continue;
+
+ page = vm_normal_page(vma, addr, ptent);
+ if (!page)
+ continue;
+
+ /*
+ * If pmd isn't transhuge but the page is THP and
+ * is owned by only this process, split it and
+ * deactivate all pages.
+ */
+ if (PageTransCompound(page)) {
+ if (page_mapcount(page) != 1)
+ goto out;
+ get_page(page);
+ if (!trylock_page(page)) {
+ put_page(page);
+ goto out;
+ }
+ pte_unmap_unlock(orig_pte, ptl);
+ if (split_huge_page(page)) {
+ unlock_page(page);
+ put_page(page);
+ pte_offset_map_lock(mm, pmd, addr, &ptl);
+ goto out;
+ }
+ pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+ pte--;
+ addr -= PAGE_SIZE;
+ continue;
+ }
+
+ VM_BUG_ON_PAGE(PageTransCompound(page), page);
+
+ if (PageSwapCache(page) || PageDirty(page)) {
+ if (!trylock_page(page))
+ continue;
+ /*
+ * If page is shared with others, we couldn't clear
+ * PG_dirty of the page.
+ */
+ if (page_mapcount(page) != 1) {
+ unlock_page(page);
+ continue;
+ }
+
+ if (PageSwapCache(page) && !try_to_free_swap(page)) {
+ unlock_page(page);
+ continue;
+ }
+
+ ClearPageDirty(page);
+ unlock_page(page);
+ }
+
+ if (pte_young(ptent) || pte_dirty(ptent)) {
+ /*
+ * Some of architecture(ex, PPC) don't update TLB
+ * with set_pte_at and tlb_remove_tlb_entry so for
+ * the portability, remap the pte with old|clean
+ * after pte clearing.
+ */
+ ptent = ptep_get_and_clear_full(mm, addr, pte,
+ tlb->fullmm);
+
+ ptent = pte_mkold(ptent);
+ ptent = pte_mkclean(ptent);
+ set_pte_at(mm, addr, pte, ptent);
+ tlb_remove_tlb_entry(tlb, pte, addr);
+ }
+ }
+out:
+ arch_leave_lazy_mmu_mode();
+ pte_unmap_unlock(orig_pte, ptl);
+ cond_resched();
+ return 0;
+}
+
+static void madvise_free_page_range(struct mmu_gather *tlb,
+ struct vm_area_struct *vma,
+ unsigned long addr, unsigned long end)
+{
+ struct mm_walk free_walk = {
+ .pmd_entry = madvise_free_pte_range,
+ .mm = vma->vm_mm,
+ .private = tlb,
+ };
+
+ tlb_start_vma(tlb, vma);
+ walk_page_range(addr, end, &free_walk);
+ tlb_end_vma(tlb, vma);
+}
+
+static int madvise_free_single_vma(struct vm_area_struct *vma,
+ unsigned long start_addr, unsigned long end_addr)
+{
+ unsigned long start, end;
+ struct mm_struct *mm = vma->vm_mm;
+ struct mmu_gather tlb;
+
+ if (vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP))
+ return -EINVAL;
+
+ /* MADV_FREE works for only anon vma at the moment */
+ if (!vma_is_anonymous(vma))
+ return -EINVAL;
+
+ start = max(vma->vm_start, start_addr);
+ if (start >= vma->vm_end)
+ return -EINVAL;
+ end = min(vma->vm_end, end_addr);
+ if (end <= vma->vm_start)
+ return -EINVAL;
+
+ lru_add_drain();
+ tlb_gather_mmu(&tlb, mm, start, end);
+ update_hiwater_rss(mm);
+
+ mmu_notifier_invalidate_range_start(mm, start, end);
+ madvise_free_page_range(&tlb, vma, start, end);
+ mmu_notifier_invalidate_range_end(mm, start, end);
+ tlb_finish_mmu(&tlb, start, end);
+
+ return 0;
+}
+
+static long madvise_free(struct vm_area_struct *vma,
+ struct vm_area_struct **prev,
+ unsigned long start, unsigned long end)
+{
+ *prev = vma;
+ return madvise_free_single_vma(vma, start, end);
+}
+
/*
* Application no longer needs these pages. If the pages are dirty,
* it's OK to just throw them away. The app will be more careful about
@@ -379,6 +538,14 @@ madvise_vma(struct vm_area_struct *vma,
return madvise_remove(vma, prev, start, end);
case MADV_WILLNEED:
return madvise_willneed(vma, prev, start, end);
+ case MADV_FREE:
+ /*
+ * XXX: In this implementation, MADV_FREE works like
+ * MADV_DONTNEED on swapless system or full swap.
+ */
+ if (get_nr_swap_pages() > 0)
+ return madvise_free(vma, prev, start, end);
+ /* passthrough */
case MADV_DONTNEED:
return madvise_dontneed(vma, prev, start, end);
default:
@@ -398,6 +565,7 @@ madvise_behavior_valid(int behavior)
case MADV_REMOVE:
case MADV_WILLNEED:
case MADV_DONTNEED:
+ case MADV_FREE:
#ifdef CONFIG_KSM
case MADV_MERGEABLE:
case MADV_UNMERGEABLE:
diff -puN mm/rmap.c~mm-support-madvisemadv_free mm/rmap.c
--- a/mm/rmap.c~mm-support-madvisemadv_free
+++ a/mm/rmap.c
@@ -1511,6 +1511,13 @@ static int try_to_unmap_one(struct page
* See handle_pte_fault() ...
*/
VM_BUG_ON_PAGE(!PageSwapCache(page), page);
+
+ if (!PageDirty(page) && (flags & TTU_LZFREE)) {
+ /* It's a freeable page by MADV_FREE */
+ dec_mm_counter(mm, MM_ANONPAGES);
+ goto discard;
+ }
+
if (swap_duplicate(entry) < 0) {
set_pte_at(mm, address, pte, pteval);
ret = SWAP_FAIL;
@@ -1531,6 +1538,7 @@ static int try_to_unmap_one(struct page
} else
dec_mm_counter(mm, mm_counter_file(page));
+discard:
page_remove_rmap(page, PageHuge(page));
page_cache_release(page);
diff -puN mm/swap_state.c~mm-support-madvisemadv_free mm/swap_state.c
--- a/mm/swap_state.c~mm-support-madvisemadv_free
+++ a/mm/swap_state.c
@@ -185,13 +185,12 @@ int add_to_swap(struct page *page, struc
* deadlock in the swap out path.
*/
/*
- * Add it to the swap cache and mark it dirty
+ * Add it to the swap cache.
*/
err = add_to_swap_cache(page, entry,
__GFP_HIGH|__GFP_NOMEMALLOC|__GFP_NOWARN);
- if (!err) { /* Success */
- SetPageDirty(page);
+ if (!err) {
return 1;
} else { /* -ENOMEM radix-tree allocation failure */
/*
diff -puN mm/vmscan.c~mm-support-madvisemadv_free mm/vmscan.c
--- a/mm/vmscan.c~mm-support-madvisemadv_free
+++ a/mm/vmscan.c
@@ -908,6 +908,7 @@ static unsigned long shrink_page_list(st
int may_enter_fs;
enum page_references references = PAGEREF_RECLAIM_CLEAN;
bool dirty, writeback;
+ bool lazyfree = false;
cond_resched();
@@ -1051,6 +1052,7 @@ static unsigned long shrink_page_list(st
goto keep_locked;
if (!add_to_swap(page, page_list))
goto activate_locked;
+ lazyfree = true;
may_enter_fs = 1;
/* Adding to swap updated mapping */
@@ -1062,8 +1064,9 @@ static unsigned long shrink_page_list(st
* processes. Try to unmap it here.
*/
if (page_mapped(page) && mapping) {
- switch (try_to_unmap(page,
- ttu_flags|TTU_BATCH_FLUSH)) {
+ switch (try_to_unmap(page, lazyfree ?
+ (ttu_flags | TTU_BATCH_FLUSH | TTU_LZFREE) :
+ (ttu_flags | TTU_BATCH_FLUSH))) {
case SWAP_FAIL:
goto activate_locked;
case SWAP_AGAIN:
@@ -1188,6 +1191,9 @@ static unsigned long shrink_page_list(st
*/
__ClearPageLocked(page);
free_it:
+ if (lazyfree && !PageDirty(page))
+ count_vm_event(PGLAZYFREED);
+
nr_reclaimed++;
/*
diff -puN mm/vmstat.c~mm-support-madvisemadv_free mm/vmstat.c
--- a/mm/vmstat.c~mm-support-madvisemadv_free
+++ a/mm/vmstat.c
@@ -781,6 +781,7 @@ const char * const vmstat_text[] = {
"pgfault",
"pgmajfault",
+ "pglazyfreed",
TEXTS_FOR_ZONES("pgrefill")
TEXTS_FOR_ZONES("pgsteal_kswapd")
_
Patches currently in -mm which might be from minchan@xxxxxxxxxx are
zram-pass-gfp-from-zcomp-frontend-to-backend.patch
mm-support-madvisemadv_free.patch
mm-support-madvisemadv_free-fix.patch
mm-define-madv_free-for-some-arches.patch
mm-free-swp_entry-in-madvise_free.patch
mm-move-lazily-freed-pages-to-inactive-list.patch
mm-mark-stable-page-dirty-in-ksm.patch
x86-add-pmd_-for-thp.patch
sparc-add-pmd_-for-thp.patch
powerpc-add-pmd_-for-thp.patch
arm-add-pmd_mkclean-for-thp.patch
arm64-add-pmd_mkclean-for-thp.patch
mm-dont-split-thp-page-when-syscall-is-called.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
