zone_watermark_fast was introduced by commit 48ee5f3696f6 ("mm,
page_alloc: shortcut watermark checks for order-0 pages"). The commit
simply checks if free pages is bigger than watermark without additional
calculation such like reducing watermark.
It considered free cma pages but it did not consider highatomic
reserved. This may incur exhaustion of free pages except high order
atomic free pages.
Assume that reserved_highatomic pageblock is bigger than watermark min,
and there are only few free pages except high order atomic free. Because
zone_watermark_fast passes the allocation without considering high order
atomic free, normal reclaimable allocation like GFP_HIGHUSER will
consume all the free pages. Then finally order-0 atomic allocation may
fail on allocation.
This means watermark min is not protected against non-atomic allocation.
The order-0 atomic allocation with ALLOC_HARDER unwantedly can be
failed. Additionally the __GFP_MEMALLOC allocation with
ALLOC_NO_WATERMARKS also can be failed.
To avoid the problem, zone_watermark_fast should consider highatomic
reserve. If the actual size of high atomic free is counted accurately
like cma free, we may use it. On this patch just use
nr_reserved_highatomic. Additionally introduce
__zone_watermark_unusable_free to factor out common parts between
zone_watermark_fast and __zone_watermark_ok.
This is an example of ALLOC_HARDER allocation failure using v4.19 based
kernel.
Binder:9343_3: page allocation failure: order:0, mode:0x480020(GFP_ATOMIC), nodemask=(null)
Call trace:
[<ffffff8008f40f8c>] dump_stack+0xb8/0xf0
[<ffffff8008223320>] warn_alloc+0xd8/0x12c
[<ffffff80082245e4>] __alloc_pages_nodemask+0x120c/0x1250
[<ffffff800827f6e8>] new_slab+0x128/0x604
[<ffffff800827b0cc>] ___slab_alloc+0x508/0x670
[<ffffff800827ba00>] __kmalloc+0x2f8/0x310
[<ffffff80084ac3e0>] context_struct_to_string+0x104/0x1cc
[<ffffff80084ad8fc>] security_sid_to_context_core+0x74/0x144
[<ffffff80084ad880>] security_sid_to_context+0x10/0x18
[<ffffff800849bd80>] selinux_secid_to_secctx+0x20/0x28
[<ffffff800849109c>] security_secid_to_secctx+0x3c/0x70
[<ffffff8008bfe118>] binder_transaction+0xe68/0x454c
Mem-Info:
active_anon:102061 inactive_anon:81551 isolated_anon:0
active_file:59102 inactive_file:68924 isolated_file:64
unevictable:611 dirty:63 writeback:0 unstable:0
slab_reclaimable:13324 slab_unreclaimable:44354
mapped:83015 shmem:4858 pagetables:26316 bounce:0
free:2727 free_pcp:1035 free_cma:178
Node 0 active_anon:408244kB inactive_anon:326204kB active_file:236408kB inactive_file:275696kB unevictable:2444kB isolated(anon):0kB isolated(file):256kB mapped:332060kB dirty:252kB writeback:0kB shmem:19432kB writeback_tmp:0kB unstable:0kB all_unreclaimable? no
Normal free:10908kB min:6192kB low:44388kB high:47060kB active_anon:409160kB inactive_anon:325924kB active_file:235820kB inactive_file:276628kB unevictable:2444kB writepending:252kB present:3076096kB managed:2673676kB mlocked:2444kB kernel_stack:62512kB pagetables:105264kB bounce:0kB free_pcp:4140kB local_pcp:40kB free_cma:712kB
lowmem_reserve[]: 0 0
Normal: 505*4kB (H) 357*8kB (H) 201*16kB (H) 65*32kB (H) 1*64kB (H) 0*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB = 10236kB
138826 total pagecache pages
5460 pages in swap cache
Swap cache stats: add 8273090, delete 8267506, find 1004381/4060142
This is an example of ALLOC_NO_WATERMARKS allocation failure using v4.14
based kernel.
kswapd0: page allocation failure: order:0, mode:0x140000a(GFP_NOIO|__GFP_HIGHMEM|__GFP_MOVABLE), nodemask=(null)
kswapd0 cpuset=/ mems_allowed=0
CPU: 4 PID: 1221 Comm: kswapd0 Not tainted 4.14.113-18770262-userdebug #1
Call trace:
[<0000000000000000>] dump_backtrace+0x0/0x248
[<0000000000000000>] show_stack+0x18/0x20
[<0000000000000000>] __dump_stack+0x20/0x28
[<0000000000000000>] dump_stack+0x68/0x90
[<0000000000000000>] warn_alloc+0x104/0x198
[<0000000000000000>] __alloc_pages_nodemask+0xdc0/0xdf0
[<0000000000000000>] zs_malloc+0x148/0x3d0
[<0000000000000000>] zram_bvec_rw+0x410/0x798
[<0000000000000000>] zram_rw_page+0x88/0xdc
[<0000000000000000>] bdev_write_page+0x70/0xbc
[<0000000000000000>] __swap_writepage+0x58/0x37c
[<0000000000000000>] swap_writepage+0x40/0x4c
[<0000000000000000>] shrink_page_list+0xc30/0xf48
[<0000000000000000>] shrink_inactive_list+0x2b0/0x61c
[<0000000000000000>] shrink_node_memcg+0x23c/0x618
[<0000000000000000>] shrink_node+0x1c8/0x304
[<0000000000000000>] kswapd+0x680/0x7c4
[<0000000000000000>] kthread+0x110/0x120
[<0000000000000000>] ret_from_fork+0x10/0x18
Mem-Info:
active_anon:111826 inactive_anon:65557 isolated_anon:0\x0a active_file:44260 inactive_file:83422 isolated_file:0\x0a unevictable:4158 dirty:117 writeback:0 unstable:0\x0a slab_reclaimable:13943 slab_unreclaimable:43315\x0a mapped:102511 shmem:3299 pagetables:19566 bounce:0\x0a free:3510 free_pcp:553 free_cma:0
Node 0 active_anon:447304kB inactive_anon:262228kB active_file:177040kB inactive_file:333688kB unevictable:16632kB isolated(anon):0kB isolated(file):0kB mapped:410044kB d irty:468kB writeback:0kB shmem:13196kB writeback_tmp:0kB unstable:0kB all_unreclaimable? no
Normal free:14040kB min:7440kB low:94500kB high:98136kB reserved_highatomic:32768KB active_anon:447336kB inactive_anon:261668kB active_file:177572kB inactive_file:333768k B unevictable:16632kB writepending:480kB present:4081664kB managed:3637088kB mlocked:16632kB kernel_stack:47072kB pagetables:78264kB bounce:0kB free_pcp:2280kB local_pcp:720kB free_cma:0kB [ 4738.329607] lowmem_reserve[]: 0 0
Normal: 860*4kB (H) 453*8kB (H) 180*16kB (H) 26*32kB (H) 34*64kB (H) 6*128kB (H) 2*256kB (H) 0*512kB 0*1024kB 0*2048kB 0*4096kB = 14232kB
This is trace log which shows GFP_HIGHUSER consumes free pages right
before ALLOC_NO_WATERMARKS.
<...>-22275 [006] .... 889.213383: mm_page_alloc: page=00000000d2be5665 pfn=970744 order=0 migratetype=0 nr_free=3650 gfp_flags=GFP_HIGHUSER|__GFP_ZERO
<...>-22275 [006] .... 889.213385: mm_page_alloc: page=000000004b2335c2 pfn=970745 order=0 migratetype=0 nr_free=3650 gfp_flags=GFP_HIGHUSER|__GFP_ZERO
<...>-22275 [006] .... 889.213387: mm_page_alloc: page=00000000017272e1 pfn=970278 order=0 migratetype=0 nr_free=3650 gfp_flags=GFP_HIGHUSER|__GFP_ZERO
<...>-22275 [006] .... 889.213389: mm_page_alloc: page=00000000c4be79fb pfn=970279 order=0 migratetype=0 nr_free=3650 gfp_flags=GFP_HIGHUSER|__GFP_ZERO
<...>-22275 [006] .... 889.213391: mm_page_alloc: page=00000000f8a51d4f pfn=970260 order=0 migratetype=0 nr_free=3650 gfp_flags=GFP_HIGHUSER|__GFP_ZERO
<...>-22275 [006] .... 889.213393: mm_page_alloc: page=000000006ba8f5ac pfn=970261 order=0 migratetype=0 nr_free=3650 gfp_flags=GFP_HIGHUSER|__GFP_ZERO
<...>-22275 [006] .... 889.213395: mm_page_alloc: page=00000000819f1cd3 pfn=970196 order=0 migratetype=0 nr_free=3650 gfp_flags=GFP_HIGHUSER|__GFP_ZERO
<...>-22275 [006] .... 889.213396: mm_page_alloc: page=00000000f6b72a64 pfn=970197 order=0 migratetype=0 nr_free=3650 gfp_flags=GFP_HIGHUSER|__GFP_ZERO
kswapd0-1207 [005] ...1 889.213398: mm_page_alloc: page= (null) pfn=0 order=0 migratetype=1 nr_free=3650 gfp_flags=GFP_NOWAIT|__GFP_HIGHMEM|__GFP_NOWARN|__GFP_MOVABLE
Reported-by: Yong-Taek Lee <[email protected]>
Suggested-by: Minchan Kim <[email protected]>
Signed-off-by: Jaewon Kim <[email protected]>
Acked-by: Vlastimil Babka <[email protected]>
---
v4: change description only; typo and log
v3: change log in description to one having reserved_highatomic
change comment in code
v2: factor out common part
v1: consider highatomic reserve
---
mm/page_alloc.c | 66 +++++++++++++++++++++++++++----------------------
1 file changed, 36 insertions(+), 30 deletions(-)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 48eb0f1410d4..fe83f88ce188 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3487,6 +3487,29 @@ static noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
}
ALLOW_ERROR_INJECTION(should_fail_alloc_page, TRUE);
+static inline long __zone_watermark_unusable_free(struct zone *z,
+ unsigned int order, unsigned int alloc_flags)
+{
+ const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
+ long unusable_free = (1 << order) - 1;
+
+ /*
+ * If the caller does not have rights to ALLOC_HARDER then subtract
+ * the high-atomic reserves. This will over-estimate the size of the
+ * atomic reserve but it avoids a search.
+ */
+ if (likely(!alloc_harder))
+ unusable_free += z->nr_reserved_highatomic;
+
+#ifdef CONFIG_CMA
+ /* If allocation can't use CMA areas don't use free CMA pages */
+ if (!(alloc_flags & ALLOC_CMA))
+ unusable_free += zone_page_state(z, NR_FREE_CMA_PAGES);
+#endif
+
+ return unusable_free;
+}
+
/*
* Return true if free base pages are above 'mark'. For high-order checks it
* will return true of the order-0 watermark is reached and there is at least
@@ -3502,19 +3525,12 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
/* free_pages may go negative - that's OK */
- free_pages -= (1 << order) - 1;
+ free_pages -= __zone_watermark_unusable_free(z, order, alloc_flags);
if (alloc_flags & ALLOC_HIGH)
min -= min / 2;
- /*
- * If the caller does not have rights to ALLOC_HARDER then subtract
- * the high-atomic reserves. This will over-estimate the size of the
- * atomic reserve but it avoids a search.
- */
- if (likely(!alloc_harder)) {
- free_pages -= z->nr_reserved_highatomic;
- } else {
+ if (unlikely(alloc_harder)) {
/*
* OOM victims can try even harder than normal ALLOC_HARDER
* users on the grounds that it's definitely going to be in
@@ -3527,13 +3543,6 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
min -= min / 4;
}
-
-#ifdef CONFIG_CMA
- /* If allocation can't use CMA areas don't use free CMA pages */
- if (!(alloc_flags & ALLOC_CMA))
- free_pages -= zone_page_state(z, NR_FREE_CMA_PAGES);
-#endif
-
/*
* Check watermarks for an order-0 allocation request. If these
* are not met, then a high-order request also cannot go ahead
@@ -3582,25 +3591,22 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
unsigned long mark, int highest_zoneidx,
unsigned int alloc_flags)
{
- long free_pages = zone_page_state(z, NR_FREE_PAGES);
- long cma_pages = 0;
+ long free_pages;
+ long unusable_free;
-#ifdef CONFIG_CMA
- /* If allocation can't use CMA areas don't use free CMA pages */
- if (!(alloc_flags & ALLOC_CMA))
- cma_pages = zone_page_state(z, NR_FREE_CMA_PAGES);
-#endif
+ free_pages = zone_page_state(z, NR_FREE_PAGES);
+ unusable_free = __zone_watermark_unusable_free(z, order, alloc_flags);
/*
* Fast check for order-0 only. If this fails then the reserves
- * need to be calculated. There is a corner case where the check
- * passes but only the high-order atomic reserve are free. If
- * the caller is !atomic then it'll uselessly search the free
- * list. That corner case is then slower but it is harmless.
+ * need to be calculated.
*/
- if (!order && (free_pages - cma_pages) >
- mark + z->lowmem_reserve[highest_zoneidx])
- return true;
+ if (!order) {
+ long fast_free = free_pages - unusable_free;
+
+ if (fast_free > mark + z->lowmem_reserve[highest_zoneidx])
+ return true;
+ }
return __zone_watermark_ok(z, order, mark, highest_zoneidx, alloc_flags,
free_pages);
--
2.17.1
On 06/20/20 at 08:59am, Jaewon Kim wrote:
...
> kswapd0-1207 [005] ...1 889.213398: mm_page_alloc: page= (null) pfn=0 order=0 migratetype=1 nr_free=3650 gfp_flags=GFP_NOWAIT|__GFP_HIGHMEM|__GFP_NOWARN|__GFP_MOVABLE
>
> Reported-by: Yong-Taek Lee <[email protected]>
> Suggested-by: Minchan Kim <[email protected]>
> Signed-off-by: Jaewon Kim <[email protected]>
> Acked-by: Vlastimil Babka <[email protected]>
Reviewed-by: Baoquan He <[email protected]>
> ---
> v4: change description only; typo and log
> v3: change log in description to one having reserved_highatomic
> change comment in code
> v2: factor out common part
> v1: consider highatomic reserve
> ---
> mm/page_alloc.c | 66 +++++++++++++++++++++++++++----------------------
> 1 file changed, 36 insertions(+), 30 deletions(-)
>
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 48eb0f1410d4..fe83f88ce188 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -3487,6 +3487,29 @@ static noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
> }
> ALLOW_ERROR_INJECTION(should_fail_alloc_page, TRUE);
>
> +static inline long __zone_watermark_unusable_free(struct zone *z,
> + unsigned int order, unsigned int alloc_flags)
> +{
> + const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
> + long unusable_free = (1 << order) - 1;
> +
> + /*
> + * If the caller does not have rights to ALLOC_HARDER then subtract
> + * the high-atomic reserves. This will over-estimate the size of the
> + * atomic reserve but it avoids a search.
> + */
> + if (likely(!alloc_harder))
> + unusable_free += z->nr_reserved_highatomic;
> +
> +#ifdef CONFIG_CMA
> + /* If allocation can't use CMA areas don't use free CMA pages */
> + if (!(alloc_flags & ALLOC_CMA))
> + unusable_free += zone_page_state(z, NR_FREE_CMA_PAGES);
> +#endif
> +
> + return unusable_free;
> +}
> +
> /*
> * Return true if free base pages are above 'mark'. For high-order checks it
> * will return true of the order-0 watermark is reached and there is at least
> @@ -3502,19 +3525,12 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
> const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
>
> /* free_pages may go negative - that's OK */
> - free_pages -= (1 << order) - 1;
> + free_pages -= __zone_watermark_unusable_free(z, order, alloc_flags);
>
> if (alloc_flags & ALLOC_HIGH)
> min -= min / 2;
>
> - /*
> - * If the caller does not have rights to ALLOC_HARDER then subtract
> - * the high-atomic reserves. This will over-estimate the size of the
> - * atomic reserve but it avoids a search.
> - */
> - if (likely(!alloc_harder)) {
> - free_pages -= z->nr_reserved_highatomic;
> - } else {
> + if (unlikely(alloc_harder)) {
> /*
> * OOM victims can try even harder than normal ALLOC_HARDER
> * users on the grounds that it's definitely going to be in
> @@ -3527,13 +3543,6 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
> min -= min / 4;
> }
>
> -
> -#ifdef CONFIG_CMA
> - /* If allocation can't use CMA areas don't use free CMA pages */
> - if (!(alloc_flags & ALLOC_CMA))
> - free_pages -= zone_page_state(z, NR_FREE_CMA_PAGES);
> -#endif
> -
> /*
> * Check watermarks for an order-0 allocation request. If these
> * are not met, then a high-order request also cannot go ahead
> @@ -3582,25 +3591,22 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
> unsigned long mark, int highest_zoneidx,
> unsigned int alloc_flags)
> {
> - long free_pages = zone_page_state(z, NR_FREE_PAGES);
> - long cma_pages = 0;
> + long free_pages;
> + long unusable_free;
>
> -#ifdef CONFIG_CMA
> - /* If allocation can't use CMA areas don't use free CMA pages */
> - if (!(alloc_flags & ALLOC_CMA))
> - cma_pages = zone_page_state(z, NR_FREE_CMA_PAGES);
> -#endif
> + free_pages = zone_page_state(z, NR_FREE_PAGES);
> + unusable_free = __zone_watermark_unusable_free(z, order, alloc_flags);
>
> /*
> * Fast check for order-0 only. If this fails then the reserves
> - * need to be calculated. There is a corner case where the check
> - * passes but only the high-order atomic reserve are free. If
> - * the caller is !atomic then it'll uselessly search the free
> - * list. That corner case is then slower but it is harmless.
> + * need to be calculated.
> */
> - if (!order && (free_pages - cma_pages) >
> - mark + z->lowmem_reserve[highest_zoneidx])
> - return true;
> + if (!order) {
> + long fast_free = free_pages - unusable_free;
> +
> + if (fast_free > mark + z->lowmem_reserve[highest_zoneidx])
> + return true;
> + }
>
> return __zone_watermark_ok(z, order, mark, highest_zoneidx, alloc_flags,
> free_pages);
> --
> 2.17.1
>
>
On Sat, Jun 20, 2020 at 08:59:58AM +0900, Jaewon Kim wrote:
> zone_watermark_fast was introduced by commit 48ee5f3696f6 ("mm,
> page_alloc: shortcut watermark checks for order-0 pages"). The commit
> simply checks if free pages is bigger than watermark without additional
> calculation such like reducing watermark.
>
> It considered free cma pages but it did not consider highatomic
> reserved. This may incur exhaustion of free pages except high order
> atomic free pages.
>
> Assume that reserved_highatomic pageblock is bigger than watermark min,
> and there are only few free pages except high order atomic free. Because
> zone_watermark_fast passes the allocation without considering high order
> atomic free, normal reclaimable allocation like GFP_HIGHUSER will
> consume all the free pages. Then finally order-0 atomic allocation may
> fail on allocation.
>
> This means watermark min is not protected against non-atomic allocation.
> The order-0 atomic allocation with ALLOC_HARDER unwantedly can be
> failed. Additionally the __GFP_MEMALLOC allocation with
> ALLOC_NO_WATERMARKS also can be failed.
>
> To avoid the problem, zone_watermark_fast should consider highatomic
> reserve. If the actual size of high atomic free is counted accurately
> like cma free, we may use it. On this patch just use
> nr_reserved_highatomic. Additionally introduce
> __zone_watermark_unusable_free to factor out common parts between
> zone_watermark_fast and __zone_watermark_ok.
>
> This is an example of ALLOC_HARDER allocation failure using v4.19 based
> kernel.
>
> Binder:9343_3: page allocation failure: order:0, mode:0x480020(GFP_ATOMIC), nodemask=(null)
> Call trace:
> [<ffffff8008f40f8c>] dump_stack+0xb8/0xf0
> [<ffffff8008223320>] warn_alloc+0xd8/0x12c
> [<ffffff80082245e4>] __alloc_pages_nodemask+0x120c/0x1250
> [<ffffff800827f6e8>] new_slab+0x128/0x604
> [<ffffff800827b0cc>] ___slab_alloc+0x508/0x670
> [<ffffff800827ba00>] __kmalloc+0x2f8/0x310
> [<ffffff80084ac3e0>] context_struct_to_string+0x104/0x1cc
> [<ffffff80084ad8fc>] security_sid_to_context_core+0x74/0x144
> [<ffffff80084ad880>] security_sid_to_context+0x10/0x18
> [<ffffff800849bd80>] selinux_secid_to_secctx+0x20/0x28
> [<ffffff800849109c>] security_secid_to_secctx+0x3c/0x70
> [<ffffff8008bfe118>] binder_transaction+0xe68/0x454c
> Mem-Info:
> active_anon:102061 inactive_anon:81551 isolated_anon:0
> active_file:59102 inactive_file:68924 isolated_file:64
> unevictable:611 dirty:63 writeback:0 unstable:0
> slab_reclaimable:13324 slab_unreclaimable:44354
> mapped:83015 shmem:4858 pagetables:26316 bounce:0
> free:2727 free_pcp:1035 free_cma:178
> Node 0 active_anon:408244kB inactive_anon:326204kB active_file:236408kB inactive_file:275696kB unevictable:2444kB isolated(anon):0kB isolated(file):256kB mapped:332060kB dirty:252kB writeback:0kB shmem:19432kB writeback_tmp:0kB unstable:0kB all_unreclaimable? no
> Normal free:10908kB min:6192kB low:44388kB high:47060kB active_anon:409160kB inactive_anon:325924kB active_file:235820kB inactive_file:276628kB unevictable:2444kB writepending:252kB present:3076096kB managed:2673676kB mlocked:2444kB kernel_stack:62512kB pagetables:105264kB bounce:0kB free_pcp:4140kB local_pcp:40kB free_cma:712kB
> lowmem_reserve[]: 0 0
> Normal: 505*4kB (H) 357*8kB (H) 201*16kB (H) 65*32kB (H) 1*64kB (H) 0*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB = 10236kB
> 138826 total pagecache pages
> 5460 pages in swap cache
> Swap cache stats: add 8273090, delete 8267506, find 1004381/4060142
>
> This is an example of ALLOC_NO_WATERMARKS allocation failure using v4.14
> based kernel.
>
> kswapd0: page allocation failure: order:0, mode:0x140000a(GFP_NOIO|__GFP_HIGHMEM|__GFP_MOVABLE), nodemask=(null)
> kswapd0 cpuset=/ mems_allowed=0
> CPU: 4 PID: 1221 Comm: kswapd0 Not tainted 4.14.113-18770262-userdebug #1
> Call trace:
> [<0000000000000000>] dump_backtrace+0x0/0x248
> [<0000000000000000>] show_stack+0x18/0x20
> [<0000000000000000>] __dump_stack+0x20/0x28
> [<0000000000000000>] dump_stack+0x68/0x90
> [<0000000000000000>] warn_alloc+0x104/0x198
> [<0000000000000000>] __alloc_pages_nodemask+0xdc0/0xdf0
> [<0000000000000000>] zs_malloc+0x148/0x3d0
> [<0000000000000000>] zram_bvec_rw+0x410/0x798
> [<0000000000000000>] zram_rw_page+0x88/0xdc
> [<0000000000000000>] bdev_write_page+0x70/0xbc
> [<0000000000000000>] __swap_writepage+0x58/0x37c
> [<0000000000000000>] swap_writepage+0x40/0x4c
> [<0000000000000000>] shrink_page_list+0xc30/0xf48
> [<0000000000000000>] shrink_inactive_list+0x2b0/0x61c
> [<0000000000000000>] shrink_node_memcg+0x23c/0x618
> [<0000000000000000>] shrink_node+0x1c8/0x304
> [<0000000000000000>] kswapd+0x680/0x7c4
> [<0000000000000000>] kthread+0x110/0x120
> [<0000000000000000>] ret_from_fork+0x10/0x18
> Mem-Info:
> active_anon:111826 inactive_anon:65557 isolated_anon:0\x0a active_file:44260 inactive_file:83422 isolated_file:0\x0a unevictable:4158 dirty:117 writeback:0 unstable:0\x0a slab_reclaimable:13943 slab_unreclaimable:43315\x0a mapped:102511 shmem:3299 pagetables:19566 bounce:0\x0a free:3510 free_pcp:553 free_cma:0
> Node 0 active_anon:447304kB inactive_anon:262228kB active_file:177040kB inactive_file:333688kB unevictable:16632kB isolated(anon):0kB isolated(file):0kB mapped:410044kB d irty:468kB writeback:0kB shmem:13196kB writeback_tmp:0kB unstable:0kB all_unreclaimable? no
> Normal free:14040kB min:7440kB low:94500kB high:98136kB reserved_highatomic:32768KB active_anon:447336kB inactive_anon:261668kB active_file:177572kB inactive_file:333768k B unevictable:16632kB writepending:480kB present:4081664kB managed:3637088kB mlocked:16632kB kernel_stack:47072kB pagetables:78264kB bounce:0kB free_pcp:2280kB local_pcp:720kB free_cma:0kB [ 4738.329607] lowmem_reserve[]: 0 0
> Normal: 860*4kB (H) 453*8kB (H) 180*16kB (H) 26*32kB (H) 34*64kB (H) 6*128kB (H) 2*256kB (H) 0*512kB 0*1024kB 0*2048kB 0*4096kB = 14232kB
>
> This is trace log which shows GFP_HIGHUSER consumes free pages right
> before ALLOC_NO_WATERMARKS.
>
> <...>-22275 [006] .... 889.213383: mm_page_alloc: page=00000000d2be5665 pfn=970744 order=0 migratetype=0 nr_free=3650 gfp_flags=GFP_HIGHUSER|__GFP_ZERO
> <...>-22275 [006] .... 889.213385: mm_page_alloc: page=000000004b2335c2 pfn=970745 order=0 migratetype=0 nr_free=3650 gfp_flags=GFP_HIGHUSER|__GFP_ZERO
> <...>-22275 [006] .... 889.213387: mm_page_alloc: page=00000000017272e1 pfn=970278 order=0 migratetype=0 nr_free=3650 gfp_flags=GFP_HIGHUSER|__GFP_ZERO
> <...>-22275 [006] .... 889.213389: mm_page_alloc: page=00000000c4be79fb pfn=970279 order=0 migratetype=0 nr_free=3650 gfp_flags=GFP_HIGHUSER|__GFP_ZERO
> <...>-22275 [006] .... 889.213391: mm_page_alloc: page=00000000f8a51d4f pfn=970260 order=0 migratetype=0 nr_free=3650 gfp_flags=GFP_HIGHUSER|__GFP_ZERO
> <...>-22275 [006] .... 889.213393: mm_page_alloc: page=000000006ba8f5ac pfn=970261 order=0 migratetype=0 nr_free=3650 gfp_flags=GFP_HIGHUSER|__GFP_ZERO
> <...>-22275 [006] .... 889.213395: mm_page_alloc: page=00000000819f1cd3 pfn=970196 order=0 migratetype=0 nr_free=3650 gfp_flags=GFP_HIGHUSER|__GFP_ZERO
> <...>-22275 [006] .... 889.213396: mm_page_alloc: page=00000000f6b72a64 pfn=970197 order=0 migratetype=0 nr_free=3650 gfp_flags=GFP_HIGHUSER|__GFP_ZERO
> kswapd0-1207 [005] ...1 889.213398: mm_page_alloc: page= (null) pfn=0 order=0 migratetype=1 nr_free=3650 gfp_flags=GFP_NOWAIT|__GFP_HIGHMEM|__GFP_NOWARN|__GFP_MOVABLE
>
> Reported-by: Yong-Taek Lee <[email protected]>
> Suggested-by: Minchan Kim <[email protected]>
> Signed-off-by: Jaewon Kim <[email protected]>
> Acked-by: Vlastimil Babka <[email protected]>
Acked-by: Mel Gorman <[email protected]>
--
Mel Gorman
SUSE Labs
On Sat 20-06-20 08:59:58, Jaewon Kim wrote:
[...]
> @@ -3502,19 +3525,12 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
> const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
>
> /* free_pages may go negative - that's OK */
> - free_pages -= (1 << order) - 1;
> + free_pages -= __zone_watermark_unusable_free(z, order, alloc_flags);
>
> if (alloc_flags & ALLOC_HIGH)
> min -= min / 2;
>
> - /*
> - * If the caller does not have rights to ALLOC_HARDER then subtract
> - * the high-atomic reserves. This will over-estimate the size of the
> - * atomic reserve but it avoids a search.
> - */
> - if (likely(!alloc_harder)) {
> - free_pages -= z->nr_reserved_highatomic;
> - } else {
> + if (unlikely(alloc_harder)) {
> /*
> * OOM victims can try even harder than normal ALLOC_HARDER
> * users on the grounds that it's definitely going to be in
[...]
> @@ -3582,25 +3591,22 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
> unsigned long mark, int highest_zoneidx,
> unsigned int alloc_flags)
> {
> - long free_pages = zone_page_state(z, NR_FREE_PAGES);
> - long cma_pages = 0;
> + long free_pages;
> + long unusable_free;
>
> -#ifdef CONFIG_CMA
> - /* If allocation can't use CMA areas don't use free CMA pages */
> - if (!(alloc_flags & ALLOC_CMA))
> - cma_pages = zone_page_state(z, NR_FREE_CMA_PAGES);
> -#endif
> + free_pages = zone_page_state(z, NR_FREE_PAGES);
> + unusable_free = __zone_watermark_unusable_free(z, order, alloc_flags);
>
> /*
> * Fast check for order-0 only. If this fails then the reserves
> - * need to be calculated. There is a corner case where the check
> - * passes but only the high-order atomic reserve are free. If
> - * the caller is !atomic then it'll uselessly search the free
> - * list. That corner case is then slower but it is harmless.
> + * need to be calculated.
> */
> - if (!order && (free_pages - cma_pages) >
> - mark + z->lowmem_reserve[highest_zoneidx])
> - return true;
> + if (!order) {
> + long fast_free = free_pages - unusable_free;
> +
> + if (fast_free > mark + z->lowmem_reserve[highest_zoneidx])
> + return true;
> + }
There is no user of unusable_free for order > 0. With you current code
__zone_watermark_unusable_free would be called twice for high order
allocations unless compiler tries to be clever..
But more importantly, I have hard time to follow why we need both
zone_watermark_fast and zone_watermark_ok now. They should be
essentially the same for anything but order == 0. For order 0 the
only difference between the two is that zone_watermark_ok checks for
ALLOC_HIGH resp ALLOC_HARDER, ALLOC_OOM. So what is exactly fast about
the former and why do we need it these days?
>
> return __zone_watermark_ok(z, order, mark, highest_zoneidx, alloc_flags,
> free_pages);
> --
> 2.17.1
>
--
Michal Hocko
SUSE Labs
>On Sat 20-06-20 08:59:58, Jaewon Kim wrote:
>[...]
>> @@ -3502,19 +3525,12 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
>> const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
>>
>> /* free_pages may go negative - that's OK */
>> - free_pages -= (1 << order) - 1;
>> + free_pages -= __zone_watermark_unusable_free(z, order, alloc_flags);
>>
>> if (alloc_flags & ALLOC_HIGH)
>> min -= min / 2;
>>
>> - /*
>> - * If the caller does not have rights to ALLOC_HARDER then subtract
>> - * the high-atomic reserves. This will over-estimate the size of the
>> - * atomic reserve but it avoids a search.
>> - */
>> - if (likely(!alloc_harder)) {
>> - free_pages -= z->nr_reserved_highatomic;
>> - } else {
>> + if (unlikely(alloc_harder)) {
>> /*
>> * OOM victims can try even harder than normal ALLOC_HARDER
>> * users on the grounds that it's definitely going to be in
>[...]
>> @@ -3582,25 +3591,22 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
>> unsigned long mark, int highest_zoneidx,
>> unsigned int alloc_flags)
>> {
>> - long free_pages = zone_page_state(z, NR_FREE_PAGES);
>> - long cma_pages = 0;
>> + long free_pages;
>> + long unusable_free;
>>
>> -#ifdef CONFIG_CMA
>> - /* If allocation can't use CMA areas don't use free CMA pages */
>> - if (!(alloc_flags & ALLOC_CMA))
>> - cma_pages = zone_page_state(z, NR_FREE_CMA_PAGES);
>> -#endif
>> + free_pages = zone_page_state(z, NR_FREE_PAGES);
>> + unusable_free = __zone_watermark_unusable_free(z, order, alloc_flags);
>>
>> /*
>> * Fast check for order-0 only. If this fails then the reserves
>> - * need to be calculated. There is a corner case where the check
>> - * passes but only the high-order atomic reserve are free. If
>> - * the caller is !atomic then it'll uselessly search the free
>> - * list. That corner case is then slower but it is harmless.
>> + * need to be calculated.
>> */
>> - if (!order && (free_pages - cma_pages) >
>> - mark + z->lowmem_reserve[highest_zoneidx])
>> - return true;
>> + if (!order) {
>> + long fast_free = free_pages - unusable_free;
>> +
>> + if (fast_free > mark + z->lowmem_reserve[highest_zoneidx])
>> + return true;
>> + }
>
>There is no user of unusable_free for order > 0. With you current code
>__zone_watermark_unusable_free would be called twice for high order
>allocations unless compiler tries to be clever..
Yes you're right.
Following code could be moved only for order-0.
unusable_free = __zone_watermark_unusable_free(z, order, alloc_flags);
Let me fix it at v5.
>
>But more importantly, I have hard time to follow why we need both
>zone_watermark_fast and zone_watermark_ok now. They should be
>essentially the same for anything but order == 0. For order 0 the
>only difference between the two is that zone_watermark_ok checks for
>ALLOC_HIGH resp ALLOC_HARDER, ALLOC_OOM. So what is exactly fast about
>the former and why do we need it these days?
>
I think the author, Mel, may ansewr. But I think the wmark_fast may
fast by 1) not checking more condition about wmark and 2) using inline
rather than function. According to description on commit 48ee5f3696f6,
it seems to bring about 4% improvement.
>>
>> return __zone_watermark_ok(z, order, mark, highest_zoneidx, alloc_flags,
>> free_pages);
>> --
>> 2.17.1
>>
>
>--
>Michal Hocko
>SUSE Labs
>
On Mon, Jun 22, 2020 at 06:40:20PM +0900, ????????? wrote:
> >But more importantly, I have hard time to follow why we need both
> >zone_watermark_fast and zone_watermark_ok now. They should be
> >essentially the same for anything but order == 0. For order 0 the
> >only difference between the two is that zone_watermark_ok checks for
> >ALLOC_HIGH resp ALLOC_HARDER, ALLOC_OOM. So what is exactly fast about
> >the former and why do we need it these days?
> >
>
> I think the author, Mel, may ansewr. But I think the wmark_fast may
> fast by 1) not checking more condition about wmark and 2) using inline
> rather than function. According to description on commit 48ee5f3696f6,
> it seems to bring about 4% improvement.
>
The original intent was that watermark checks were expensive as some of the
calculations are only necessary when a zone is relatively low on memory
and the check does not always have to be 100% accurate. This is probably
still true given that __zone_watermark_ok() makes a number of calculations
depending on alloc flags even if a zone is almost completely free.
--
Mel Gorman
SUSE Labs
On Mon 22-06-20 11:04:39, Mel Gorman wrote:
> On Mon, Jun 22, 2020 at 06:40:20PM +0900, ????????? wrote:
> > >But more importantly, I have hard time to follow why we need both
> > >zone_watermark_fast and zone_watermark_ok now. They should be
> > >essentially the same for anything but order == 0. For order 0 the
> > >only difference between the two is that zone_watermark_ok checks for
> > >ALLOC_HIGH resp ALLOC_HARDER, ALLOC_OOM. So what is exactly fast about
> > >the former and why do we need it these days?
> > >
> >
> > I think the author, Mel, may ansewr. But I think the wmark_fast may
> > fast by 1) not checking more condition about wmark and 2) using inline
> > rather than function. According to description on commit 48ee5f3696f6,
> > it seems to bring about 4% improvement.
> >
>
> The original intent was that watermark checks were expensive as some of the
> calculations are only necessary when a zone is relatively low on memory
> and the check does not always have to be 100% accurate. This is probably
> still true given that __zone_watermark_ok() makes a number of calculations
> depending on alloc flags even if a zone is almost completely free.
OK, so we are talking about
if (alloc_flags & ALLOC_HIGH)
min -= min / 2;
if (unlikely((alloc_flags & (ALLOC_HARDER|ALLOC_OOM))) {
/*
* OOM victims can try even harder than normal ALLOC_HARDER
* users on the grounds that it's definitely going to be in
* the exit path shortly and free memory. Any allocation it
* makes during the free path will be small and short-lived.
*/
if (alloc_flags & ALLOC_OOM)
min -= min / 2;
else
min -= min / 4;
}
Is this something even measurable and something that would justify a
complex code? If we really want to keep it even after these changes
which are making the two closer in the cost then can we have it
documented at least?
--
Michal Hocko
SUSE Labs
On Mon, Jun 22, 2020 at 04:23:04PM +0200, Michal Hocko wrote:
> On Mon 22-06-20 11:04:39, Mel Gorman wrote:
> > On Mon, Jun 22, 2020 at 06:40:20PM +0900, ????????? wrote:
> > > >But more importantly, I have hard time to follow why we need both
> > > >zone_watermark_fast and zone_watermark_ok now. They should be
> > > >essentially the same for anything but order == 0. For order 0 the
> > > >only difference between the two is that zone_watermark_ok checks for
> > > >ALLOC_HIGH resp ALLOC_HARDER, ALLOC_OOM. So what is exactly fast about
> > > >the former and why do we need it these days?
> > > >
> > >
> > > I think the author, Mel, may ansewr. But I think the wmark_fast may
> > > fast by 1) not checking more condition about wmark and 2) using inline
> > > rather than function. According to description on commit 48ee5f3696f6,
> > > it seems to bring about 4% improvement.
> > >
> >
> > The original intent was that watermark checks were expensive as some of the
> > calculations are only necessary when a zone is relatively low on memory
> > and the check does not always have to be 100% accurate. This is probably
> > still true given that __zone_watermark_ok() makes a number of calculations
> > depending on alloc flags even if a zone is almost completely free.
>
> OK, so we are talking about
> if (alloc_flags & ALLOC_HIGH)
> min -= min / 2;
>
> if (unlikely((alloc_flags & (ALLOC_HARDER|ALLOC_OOM))) {
> /*
> * OOM victims can try even harder than normal ALLOC_HARDER
> * users on the grounds that it's definitely going to be in
> * the exit path shortly and free memory. Any allocation it
> * makes during the free path will be small and short-lived.
> */
> if (alloc_flags & ALLOC_OOM)
> min -= min / 2;
> else
> min -= min / 4;
> }
>
> Is this something even measurable and something that would justify a
> complex code? If we really want to keep it even after these changes
> which are making the two closer in the cost then can we have it
> documented at least?
It was originally documented as being roughly 4% for a page allocator
micro-benchmark but that was 4 years ago and I do not even remember what
type of machine that was on. Chances are the relative cost is different
now but I haven't measured it as the microbenchmark in question doesn't
even compile with recent kernels. For many allocations, the bulk of the
allocation cost is zeroing the page so I have no particular objection
to zone_watermark_fast being removed if it makes the code easier to
read. While I have not looked recently, the cost of allocation in general
and the increasing scope of the zone->lock with larger NUMA nodes for
high-order allocations like THP are more of a concern than two branches
and potentially two minor calculations.
--
Mel Gorman
SUSE Labs
On Mon 22-06-20 17:25:01, Mel Gorman wrote:
> On Mon, Jun 22, 2020 at 04:23:04PM +0200, Michal Hocko wrote:
> > On Mon 22-06-20 11:04:39, Mel Gorman wrote:
> > > On Mon, Jun 22, 2020 at 06:40:20PM +0900, ????????? wrote:
> > > > >But more importantly, I have hard time to follow why we need both
> > > > >zone_watermark_fast and zone_watermark_ok now. They should be
> > > > >essentially the same for anything but order == 0. For order 0 the
> > > > >only difference between the two is that zone_watermark_ok checks for
> > > > >ALLOC_HIGH resp ALLOC_HARDER, ALLOC_OOM. So what is exactly fast about
> > > > >the former and why do we need it these days?
> > > > >
> > > >
> > > > I think the author, Mel, may ansewr. But I think the wmark_fast may
> > > > fast by 1) not checking more condition about wmark and 2) using inline
> > > > rather than function. According to description on commit 48ee5f3696f6,
> > > > it seems to bring about 4% improvement.
> > > >
> > >
> > > The original intent was that watermark checks were expensive as some of the
> > > calculations are only necessary when a zone is relatively low on memory
> > > and the check does not always have to be 100% accurate. This is probably
> > > still true given that __zone_watermark_ok() makes a number of calculations
> > > depending on alloc flags even if a zone is almost completely free.
> >
> > OK, so we are talking about
> > if (alloc_flags & ALLOC_HIGH)
> > min -= min / 2;
> >
> > if (unlikely((alloc_flags & (ALLOC_HARDER|ALLOC_OOM))) {
> > /*
> > * OOM victims can try even harder than normal ALLOC_HARDER
> > * users on the grounds that it's definitely going to be in
> > * the exit path shortly and free memory. Any allocation it
> > * makes during the free path will be small and short-lived.
> > */
> > if (alloc_flags & ALLOC_OOM)
> > min -= min / 2;
> > else
> > min -= min / 4;
> > }
> >
> > Is this something even measurable and something that would justify a
> > complex code? If we really want to keep it even after these changes
> > which are making the two closer in the cost then can we have it
> > documented at least?
>
> It was originally documented as being roughly 4% for a page allocator
> micro-benchmark but that was 4 years ago and I do not even remember what
> type of machine that was on. Chances are the relative cost is different
> now but I haven't measured it as the microbenchmark in question doesn't
> even compile with recent kernels.
Thanks for the clarification.
> For many allocations, the bulk of the
> allocation cost is zeroing the page so I have no particular objection
> to zone_watermark_fast being removed if it makes the code easier to
> read. While I have not looked recently, the cost of allocation in general
> and the increasing scope of the zone->lock with larger NUMA nodes for
> high-order allocations like THP are more of a concern than two branches
> and potentially two minor calculations.
OK, then I would rather go with the code simplification for the future
maintainability. If somebody can test this and provide good numbers then
we can reintroduce a fast check.
Thanks!
--
Michal Hocko
SUSE Labs
Hello,
This patch is required to be patched in linux-5.4.y and linux-4.19.y.
In addition to that, the following two patches are somewhat related:
3334a45 mm/page_alloc: use ac->high_zoneidx for classzone_idx
9282012 page_alloc: fix invalid watermark check on a negative value
thanks.
On Tue, Sep 13, 2022 at 09:09:47PM +0800, yong wrote:
> Hello,
> This patch is required to be patched in linux-5.4.y and linux-4.19.y.
What is "this patch"? There is no context here :(
> In addition to that, the following two patches are somewhat related:
>
> 3334a45 mm/page_alloc: use ac->high_zoneidx for classzone_idx
> 9282012 page_alloc: fix invalid watermark check on a negative value
In what way? What should be done here by us?
confused,
greg k-h
Greg KH <[email protected]> 于2022年9月13日周二 21:54写道：
>
> On Tue, Sep 13, 2022 at 09:09:47PM +0800, yong wrote:
> > Hello,
> > This patch is required to be patched in linux-5.4.y and linux-4.19.y.
>
> What is "this patch"? There is no context here :(
>
Sorry, I forgot to quote the original patch. the patch is as follows
f27ce0e page_alloc: consider highatomic reserve in watermark fast
> > In addition to that, the following two patches are somewhat related:
> >
> > 3334a45 mm/page_alloc: use ac->high_zoneidx for classzone_idx
> > 9282012 page_alloc: fix invalid watermark check on a negative value
>
> In what way? What should be done here by us?
>
I think these two patches should also be merged.
The classzone_idx parameter is used in the zone_watermark_fast
functionzone, and 3334a45 use ac->high_zoneidx for classzone_idx.
"9282012 page_alloc: fix invalid watermark check on a negative
value" fix f27ce0e introduced issues
> confused,
>
> greg k-h
On Wed, Sep 14, 2022 at 08:46:15AM +0800, yong w wrote:
> Greg KH <[email protected]> 于2022年9月13日周二 21:54写道：
>
> >
> > On Tue, Sep 13, 2022 at 09:09:47PM +0800, yong wrote:
> > > Hello,
> > > This patch is required to be patched in linux-5.4.y and linux-4.19.y.
> >
> > What is "this patch"? There is no context here :(
> >
> Sorry, I forgot to quote the original patch. the patch is as follows
>
> f27ce0e page_alloc: consider highatomic reserve in watermark fast
>
> > > In addition to that, the following two patches are somewhat related:
> > >
> > > 3334a45 mm/page_alloc: use ac->high_zoneidx for classzone_idx
> > > 9282012 page_alloc: fix invalid watermark check on a negative value
> >
> > In what way? What should be done here by us?
> >
>
> I think these two patches should also be merged.
>
> The classzone_idx parameter is used in the zone_watermark_fast
> functionzone, and 3334a45 use ac->high_zoneidx for classzone_idx.
> "9282012 page_alloc: fix invalid watermark check on a negative
> value" fix f27ce0e introduced issues
Ok, I need an ack by all the developers involved in those commits, as
well as the subsystem maintainer so that I know it's ok to take them.
Can you provide a series of backported and tested patches so that they
are easy to review?
thanks,
greg k-h
Here are the corresponding backports to 4.19.
And fix classzone_idx context differences causing patch merge conflicts.
Jaewon Kim (2):
page_alloc: consider highatomic reserve in watermark fast
page_alloc: fix invalid watermark check on a negative value
Joonsoo Kim (1):
mm/page_alloc: use ac->high_zoneidx for classzone_idx
mm/internal.h | 2 +-
mm/page_alloc.c | 69 +++++++++++++++++++++++++++++++++------------------------
2 files changed, 41 insertions(+), 30 deletions(-)
--
2.7.4
From: Joonsoo Kim <[email protected]>
Patch series "integrate classzone_idx and high_zoneidx", v5.
This patchset is followup of the problem reported and discussed two years
ago [1, 2]. The problem this patchset solves is related to the
classzone_idx on the NUMA system. It causes a problem when the lowmem
reserve protection exists for some zones on a node that do not exist on
other nodes.
This problem was reported two years ago, and, at that time, the solution
got general agreements [2]. But it was not upstreamed.
[1]: http://lkml.kernel.org/r/20180102063528.GG30397@yexl-desktop
[2]: http://lkml.kernel.org/r/[email protected]
This patch (of 2):
Currently, we use classzone_idx to calculate lowmem reserve proetection
for an allocation request. This classzone_idx causes a problem on NUMA
systems when the lowmem reserve protection exists for some zones on a node
that do not exist on other nodes.
Before further explanation, I should first clarify how to compute the
classzone_idx and the high_zoneidx.
- ac->high_zoneidx is computed via the arcane gfp_zone(gfp_mask) and
represents the index of the highest zone the allocation can use
- classzone_idx was supposed to be the index of the highest zone on the
local node that the allocation can use, that is actually available in
the system
Think about following example. Node 0 has 4 populated zone,
DMA/DMA32/NORMAL/MOVABLE. Node 1 has 1 populated zone, NORMAL. Some
zones, such as MOVABLE, doesn't exist on node 1 and this makes following
difference.
Assume that there is an allocation request whose gfp_zone(gfp_mask) is the
zone, MOVABLE. Then, it's high_zoneidx is 3. If this allocation is
initiated on node 0, it's classzone_idx is 3 since actually
available/usable zone on local (node 0) is MOVABLE. If this allocation is
initiated on node 1, it's classzone_idx is 2 since actually
available/usable zone on local (node 1) is NORMAL.
You can see that classzone_idx of the allocation request are different
according to their starting node, even if their high_zoneidx is the same.
Think more about these two allocation requests. If they are processed on
local, there is no problem. However, if allocation is initiated on node 1
are processed on remote, in this example, at the NORMAL zone on node 0,
due to memory shortage, problem occurs. Their different classzone_idx
leads to different lowmem reserve and then different min watermark. See
the following example.
root@ubuntu:/sys/devices/system/memory# cat /proc/zoneinfo
Node 0, zone DMA
per-node stats
...
pages free 3965
min 5
low 8
high 11
spanned 4095
present 3998
managed 3977
protection: (0, 2961, 4928, 5440)
...
Node 0, zone DMA32
pages free 757955
min 1129
low 1887
high 2645
spanned 1044480
present 782303
managed 758116
protection: (0, 0, 1967, 2479)
...
Node 0, zone Normal
pages free 459806
min 750
low 1253
high 1756
spanned 524288
present 524288
managed 503620
protection: (0, 0, 0, 4096)
...
Node 0, zone Movable
pages free 130759
min 195
low 326
high 457
spanned 1966079
present 131072
managed 131072
protection: (0, 0, 0, 0)
...
Node 1, zone DMA
pages free 0
min 0
low 0
high 0
spanned 0
present 0
managed 0
protection: (0, 0, 1006, 1006)
Node 1, zone DMA32
pages free 0
min 0
low 0
high 0
spanned 0
present 0
managed 0
protection: (0, 0, 1006, 1006)
Node 1, zone Normal
per-node stats
...
pages free 233277
min 383
low 640
high 897
spanned 262144
present 262144
managed 257744
protection: (0, 0, 0, 0)
...
Node 1, zone Movable
pages free 0
min 0
low 0
high 0
spanned 262144
present 0
managed 0
protection: (0, 0, 0, 0)
- static min watermark for the NORMAL zone on node 0 is 750.
- lowmem reserve for the request with classzone idx 3 at the NORMAL on
node 0 is 4096.
- lowmem reserve for the request with classzone idx 2 at the NORMAL on
node 0 is 0.
So, overall min watermark is:
allocation initiated on node 0 (classzone_idx 3): 750 + 4096 = 4846
allocation initiated on node 1 (classzone_idx 2): 750 + 0 = 750
Allocation initiated on node 1 will have some precedence than allocation
initiated on node 0 because min watermark of the former allocation is
lower than the other. So, allocation initiated on node 1 could succeed on
node 0 when allocation initiated on node 0 could not, and, this could
cause too many numa_miss allocation. Then, performance could be
downgraded.
Recently, there was a regression report about this problem on CMA patches
since CMA memory are placed in ZONE_MOVABLE by those patches. I checked
that problem is disappeared with this fix that uses high_zoneidx for
classzone_idx.
http://lkml.kernel.org/r/20180102063528.GG30397@yexl-desktop
Using high_zoneidx for classzone_idx is more consistent way than previous
approach because system's memory layout doesn't affect anything to it.
With this patch, both classzone_idx on above example will be 3 so will
have the same min watermark.
allocation initiated on node 0: 750 + 4096 = 4846
allocation initiated on node 1: 750 + 4096 = 4846
One could wonder if there is a side effect that allocation initiated on
node 1 will use higher bar when allocation is handled on local since
classzone_idx could be higher than before. It will not happen because the
zone without managed page doesn't contributes lowmem_reserve at all.
Reported-by: Ye Xiaolong <[email protected]>
Signed-off-by: Joonsoo Kim <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Tested-by: Ye Xiaolong <[email protected]>
Reviewed-by: Baoquan He <[email protected]>
Acked-by: Vlastimil Babka <[email protected]>
Acked-by: David Rientjes <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Minchan Kim <[email protected]>
Cc: Mel Gorman <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Linus Torvalds <[email protected]>
---
mm/internal.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mm/internal.h b/mm/internal.h
index 3a2e973..922a173 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -123,7 +123,7 @@ struct alloc_context {
bool spread_dirty_pages;
};
-#define ac_classzone_idx(ac) zonelist_zone_idx(ac->preferred_zoneref)
+#define ac_classzone_idx(ac) (ac->high_zoneidx)
/*
* Locate the struct page for both the matching buddy in our
--
2.7.4
From: Jaewon Kim <[email protected]>
There was a report that a task is waiting at the
throttle_direct_reclaim. The pgscan_direct_throttle in vmstat was
increasing.
This is a bug where zone_watermark_fast returns true even when the free
is very low. The commit f27ce0e14088 ("page_alloc: consider highatomic
reserve in watermark fast") changed the watermark fast to consider
highatomic reserve. But it did not handle a negative value case which
can be happened when reserved_highatomic pageblock is bigger than the
actual free.
If watermark is considered as ok for the negative value, allocating
contexts for order-0 will consume all free pages without direct reclaim,
and finally free page may become depleted except highatomic free.
Then allocating contexts may fall into throttle_direct_reclaim. This
symptom may easily happen in a system where wmark min is low and other
reclaimers like kswapd does not make free pages quickly.
Handle the negative case by using MIN.
Link: https://lkml.kernel.org/r/[email protected]
Fixes: f27ce0e14088 ("page_alloc: consider highatomic reserve in watermark fast")
Signed-off-by: Jaewon Kim <[email protected]>
Reported-by: GyeongHwan Hong <[email protected]>
Acked-by: Mel Gorman <[email protected]>
Cc: Minchan Kim <[email protected]>
Cc: Baoquan He <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Yong-Taek Lee <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
---
mm/page_alloc.c | 12 ++++++++----
1 file changed, 8 insertions(+), 4 deletions(-)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 237463d..d6d8a37 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3243,11 +3243,15 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
* need to be calculated.
*/
if (!order) {
- long fast_free;
+ long usable_free;
+ long reserved;
- fast_free = free_pages;
- fast_free -= __zone_watermark_unusable_free(z, 0, alloc_flags);
- if (fast_free > mark + z->lowmem_reserve[classzone_idx])
+ usable_free = free_pages;
+ reserved = __zone_watermark_unusable_free(z, 0, alloc_flags);
+
+ /* reserved may over estimate high-atomic reserves. */
+ usable_free -= min(usable_free, reserved);
+ if (usable_free > mark + z->lowmem_reserve[classzone_idx])
return true;
}
--
2.7.4
>On Wed, Sep 14, 2022 at 08:46:15AM +0800, yong w wrote:
>> Greg KH <[email protected]> 于2022年9月13日周二 21:54?道：
>>
>> >
>> > On Tue, Sep 13, 2022 at 09:09:47PM +0800, yong wrote:
>> > > Hello,
>> > > This patch is required to be patched in linux-5.4.y and linux-4.19.y.
>> >
>> > What is "this patch"? There is no context here :(
>> >
>> Sorry, I forgot to quote the original patch. the patch is as follows
>>
>> f27ce0e page_alloc: consider highatomic reserve in watermark fast
>>
>> > > In addition to that, the following two patches are somewhat related:
>> > >
>> > > 3334a45 mm/page_alloc: use ac->high_zoneidx for classzone_idx
>> > > 9282012 page_alloc: fix invalid watermark check on a negative value
>> >
>> > In what way? What should be done here by us?
>> >
>>
>> I think these two patches should also be merged.
>>
>> The classzone_idx parameter is used in the zone_watermark_fast
>> functionzone, and 3334a45 use ac->high_zoneidx for classzone_idx.
>> "9282012 page_alloc: fix invalid watermark check on a negative
>> value" fix f27ce0e introduced issues
>
>Ok, I need an ack by all the developers involved in those commits, as
>well as the subsystem maintainer so that I know it's ok to take them.
>
>Can you provide a series of backported and tested patches so that they
>are easy to review?
>
>thanks,
>
>greg k-h
Hello I didn't know my Act is needed to merge it.
Acked-by: Jaewon Kim <[email protected]>
I don't understand well why the commit f27ce0e has dependency on 3334a45, though.
Thank you
Jaewon Kim
Jaewon Kim <[email protected]> 于2022年9月19日周一 09:08写道：
>
> >On Wed, Sep 14, 2022 at 08:46:15AM +0800, yong w wrote:
> >> Greg KH <[email protected]> 于2022年9月13日周二 21:54?道：
> >>
> >> >
> >> > On Tue, Sep 13, 2022 at 09:09:47PM +0800, yong wrote:
> >> > > Hello,
> >> > > This patch is required to be patched in linux-5.4.y and linux-4.19.y.
> >> >
> >> > What is "this patch"? There is no context here :(
> >> >
> >> Sorry, I forgot to quote the original patch. the patch is as follows
> >>
> >> f27ce0e page_alloc: consider highatomic reserve in watermark fast
> >>
> >> > > In addition to that, the following two patches are somewhat related:
> >> > >
> >> > > 3334a45 mm/page_alloc: use ac->high_zoneidx for classzone_idx
> >> > > 9282012 page_alloc: fix invalid watermark check on a negative value
> >> >
> >> > In what way? What should be done here by us?
> >> >
> >>
> >> I think these two patches should also be merged.
> >>
> >> The classzone_idx parameter is used in the zone_watermark_fast
> >> functionzone, and 3334a45 use ac->high_zoneidx for classzone_idx.
> >> "9282012 page_alloc: fix invalid watermark check on a negative
> >> value" fix f27ce0e introduced issues
> >
> >Ok, I need an ack by all the developers involved in those commits, as
> >well as the subsystem maintainer so that I know it's ok to take them.
> >
> >Can you provide a series of backported and tested patches so that they
> >are easy to review?
> >
> >thanks,
> >
> >greg k-h
>
> Hello I didn't know my Act is needed to merge it.
>
> Acked-by: Jaewon Kim <[email protected]>
>
> I don't understand well why the commit f27ce0e has dependency on 3334a45, though.
>
Hello, the classzone_idx is used in the zone_watermark_fast function, and
there will be conflicts when f27ce0e is merged.
Looking back, the following two patches adjust the classzone_idx parameter.
3334a45 mm/page_alloc: use ac->high_zoneidx for classzone_idx
97a225e mm/page_alloc: integrate classzone_idx and high_zoneidx
and 3334a45 is the key modification.
Actually, I think 3334a45 can be merged or not.
Thanks.
On Fri, Sep 16, 2022 at 10:05:46AM -0700, wangyong wrote:
> Here are the corresponding backports to 4.19.
> And fix classzone_idx context differences causing patch merge conflicts.
>
> Jaewon Kim (2):
> page_alloc: consider highatomic reserve in watermark fast
> page_alloc: fix invalid watermark check on a negative value
>
> Joonsoo Kim (1):
> mm/page_alloc: use ac->high_zoneidx for classzone_idx
>
> mm/internal.h | 2 +-
> mm/page_alloc.c | 69 +++++++++++++++++++++++++++++++++------------------------
> 2 files changed, 41 insertions(+), 30 deletions(-)
>
> --
> 2.7.4
>
What are the git commit ids of these commits? That needs to be in the
commit changelog.
Also you did not sign off on the backports, please fix that up when you
resend this series.
thanks,
greg k-h
Here are the corresponding backports to 4.19.
And fix classzone_idx context differences causing patch merge conflicts.
Original commit IDS:
3334a45 mm/page_alloc: use ac->high_zoneidx for classzone_idx
f27ce0e page_alloc: consider highatomic reserve in watermark fast
9282012 page_alloc: fix invalid watermark check on a negative value
Changes from v1:
- Add commit information of the original patches.
Jaewon Kim (2):
page_alloc: consider highatomic reserve in watermark fast
page_alloc: fix invalid watermark check on a negative value
Joonsoo Kim (1):
mm/page_alloc: use ac->high_zoneidx for classzone_idx
mm/internal.h | 2 +-
mm/page_alloc.c | 69 +++++++++++++++++++++++++++++++++------------------------
2 files changed, 41 insertions(+), 30 deletions(-)
--
2.7.4
From: Joonsoo Kim <[email protected]>
[ backport of commit 3334a45eb9e2bb040c880ef65e1d72357a0a008b ]
Patch series "integrate classzone_idx and high_zoneidx", v5.
This patchset is followup of the problem reported and discussed two years
ago [1, 2]. The problem this patchset solves is related to the
classzone_idx on the NUMA system. It causes a problem when the lowmem
reserve protection exists for some zones on a node that do not exist on
other nodes.
This problem was reported two years ago, and, at that time, the solution
got general agreements [2]. But it was not upstreamed.
[1]: http://lkml.kernel.org/r/20180102063528.GG30397@yexl-desktop
[2]: http://lkml.kernel.org/r/[email protected]
This patch (of 2):
Currently, we use classzone_idx to calculate lowmem reserve proetection
for an allocation request. This classzone_idx causes a problem on NUMA
systems when the lowmem reserve protection exists for some zones on a node
that do not exist on other nodes.
Before further explanation, I should first clarify how to compute the
classzone_idx and the high_zoneidx.
- ac->high_zoneidx is computed via the arcane gfp_zone(gfp_mask) and
represents the index of the highest zone the allocation can use
- classzone_idx was supposed to be the index of the highest zone on the
local node that the allocation can use, that is actually available in
the system
Think about following example. Node 0 has 4 populated zone,
DMA/DMA32/NORMAL/MOVABLE. Node 1 has 1 populated zone, NORMAL. Some
zones, such as MOVABLE, doesn't exist on node 1 and this makes following
difference.
Assume that there is an allocation request whose gfp_zone(gfp_mask) is the
zone, MOVABLE. Then, it's high_zoneidx is 3. If this allocation is
initiated on node 0, it's classzone_idx is 3 since actually
available/usable zone on local (node 0) is MOVABLE. If this allocation is
initiated on node 1, it's classzone_idx is 2 since actually
available/usable zone on local (node 1) is NORMAL.
You can see that classzone_idx of the allocation request are different
according to their starting node, even if their high_zoneidx is the same.
Think more about these two allocation requests. If they are processed on
local, there is no problem. However, if allocation is initiated on node 1
are processed on remote, in this example, at the NORMAL zone on node 0,
due to memory shortage, problem occurs. Their different classzone_idx
leads to different lowmem reserve and then different min watermark. See
the following example.
root@ubuntu:/sys/devices/system/memory# cat /proc/zoneinfo
Node 0, zone DMA
per-node stats
...
pages free 3965
min 5
low 8
high 11
spanned 4095
present 3998
managed 3977
protection: (0, 2961, 4928, 5440)
...
Node 0, zone DMA32
pages free 757955
min 1129
low 1887
high 2645
spanned 1044480
present 782303
managed 758116
protection: (0, 0, 1967, 2479)
...
Node 0, zone Normal
pages free 459806
min 750
low 1253
high 1756
spanned 524288
present 524288
managed 503620
protection: (0, 0, 0, 4096)
...
Node 0, zone Movable
pages free 130759
min 195
low 326
high 457
spanned 1966079
present 131072
managed 131072
protection: (0, 0, 0, 0)
...
Node 1, zone DMA
pages free 0
min 0
low 0
high 0
spanned 0
present 0
managed 0
protection: (0, 0, 1006, 1006)
Node 1, zone DMA32
pages free 0
min 0
low 0
high 0
spanned 0
present 0
managed 0
protection: (0, 0, 1006, 1006)
Node 1, zone Normal
per-node stats
...
pages free 233277
min 383
low 640
high 897
spanned 262144
present 262144
managed 257744
protection: (0, 0, 0, 0)
...
Node 1, zone Movable
pages free 0
min 0
low 0
high 0
spanned 262144
present 0
managed 0
protection: (0, 0, 0, 0)
- static min watermark for the NORMAL zone on node 0 is 750.
- lowmem reserve for the request with classzone idx 3 at the NORMAL on
node 0 is 4096.
- lowmem reserve for the request with classzone idx 2 at the NORMAL on
node 0 is 0.
So, overall min watermark is:
allocation initiated on node 0 (classzone_idx 3): 750 + 4096 = 4846
allocation initiated on node 1 (classzone_idx 2): 750 + 0 = 750
Allocation initiated on node 1 will have some precedence than allocation
initiated on node 0 because min watermark of the former allocation is
lower than the other. So, allocation initiated on node 1 could succeed on
node 0 when allocation initiated on node 0 could not, and, this could
cause too many numa_miss allocation. Then, performance could be
downgraded.
Recently, there was a regression report about this problem on CMA patches
since CMA memory are placed in ZONE_MOVABLE by those patches. I checked
that problem is disappeared with this fix that uses high_zoneidx for
classzone_idx.
http://lkml.kernel.org/r/20180102063528.GG30397@yexl-desktop
Using high_zoneidx for classzone_idx is more consistent way than previous
approach because system's memory layout doesn't affect anything to it.
With this patch, both classzone_idx on above example will be 3 so will
have the same min watermark.
allocation initiated on node 0: 750 + 4096 = 4846
allocation initiated on node 1: 750 + 4096 = 4846
One could wonder if there is a side effect that allocation initiated on
node 1 will use higher bar when allocation is handled on local since
classzone_idx could be higher than before. It will not happen because the
zone without managed page doesn't contributes lowmem_reserve at all.
Reported-by: Ye Xiaolong <[email protected]>
Signed-off-by: Joonsoo Kim <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Tested-by: Ye Xiaolong <[email protected]>
Reviewed-by: Baoquan He <[email protected]>
Acked-by: Vlastimil Babka <[email protected]>
Acked-by: David Rientjes <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Minchan Kim <[email protected]>
Cc: Mel Gorman <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Linus Torvalds <[email protected]>
---
mm/internal.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mm/internal.h b/mm/internal.h
index 3a2e973..922a173 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -123,7 +123,7 @@ struct alloc_context {
bool spread_dirty_pages;
};
-#define ac_classzone_idx(ac) zonelist_zone_idx(ac->preferred_zoneref)
+#define ac_classzone_idx(ac) (ac->high_zoneidx)
/*
* Locate the struct page for both the matching buddy in our
--
2.7.4
From: Jaewon Kim <[email protected]>
[ backport of commit 9282012fc0aa248b77a69f5eb802b67c5a16bb13 ]
There was a report that a task is waiting at the
throttle_direct_reclaim. The pgscan_direct_throttle in vmstat was
increasing.
This is a bug where zone_watermark_fast returns true even when the free
is very low. The commit f27ce0e14088 ("page_alloc: consider highatomic
reserve in watermark fast") changed the watermark fast to consider
highatomic reserve. But it did not handle a negative value case which
can be happened when reserved_highatomic pageblock is bigger than the
actual free.
If watermark is considered as ok for the negative value, allocating
contexts for order-0 will consume all free pages without direct reclaim,
and finally free page may become depleted except highatomic free.
Then allocating contexts may fall into throttle_direct_reclaim. This
symptom may easily happen in a system where wmark min is low and other
reclaimers like kswapd does not make free pages quickly.
Handle the negative case by using MIN.
Link: https://lkml.kernel.org/r/[email protected]
Fixes: f27ce0e14088 ("page_alloc: consider highatomic reserve in watermark fast")
Signed-off-by: Jaewon Kim <[email protected]>
Reported-by: GyeongHwan Hong <[email protected]>
Acked-by: Mel Gorman <[email protected]>
Cc: Minchan Kim <[email protected]>
Cc: Baoquan He <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Yong-Taek Lee <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
---
mm/page_alloc.c | 12 ++++++++----
1 file changed, 8 insertions(+), 4 deletions(-)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 237463d..d6d8a37 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3243,11 +3243,15 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
* need to be calculated.
*/
if (!order) {
- long fast_free;
+ long usable_free;
+ long reserved;
- fast_free = free_pages;
- fast_free -= __zone_watermark_unusable_free(z, 0, alloc_flags);
- if (fast_free > mark + z->lowmem_reserve[classzone_idx])
+ usable_free = free_pages;
+ reserved = __zone_watermark_unusable_free(z, 0, alloc_flags);
+
+ /* reserved may over estimate high-atomic reserves. */
+ usable_free -= min(usable_free, reserved);
+ if (usable_free > mark + z->lowmem_reserve[classzone_idx])
return true;
}
--
2.7.4
On Sun, Sep 25, 2022 at 03:35:27AM -0700, wangyong wrote:
> From: Joonsoo Kim <[email protected]>
>
> [ backport of commit 3334a45eb9e2bb040c880ef65e1d72357a0a008b ]
This is from 5.8. What about the 5.4.y kernel? Why would someone
upgrading from 4.19.y to 5.4.y suffer a regression here?
And why wouldn't someone who has this issue just not use 5.10.y instead?
What prevents someone from moving off of 4.19.y at this point in time?
thanks,
greg k-h
From: Jaewon Kim <[email protected]>
[ backport of commit f27ce0e14088b23f8d54ae4a44f70307ec420e64 ]
zone_watermark_fast was introduced by commit 48ee5f3696f6 ("mm,
page_alloc: shortcut watermark checks for order-0 pages"). The commit
simply checks if free pages is bigger than watermark without additional
calculation such like reducing watermark.
It considered free cma pages but it did not consider highatomic reserved.
This may incur exhaustion of free pages except high order atomic free
pages.
Assume that reserved_highatomic pageblock is bigger than watermark min,
and there are only few free pages except high order atomic free. Because
zone_watermark_fast passes the allocation without considering high order
atomic free, normal reclaimable allocation like GFP_HIGHUSER will consume
all the free pages. Then finally order-0 atomic allocation may fail on
allocation.
This means watermark min is not protected against non-atomic allocation.
The order-0 atomic allocation with ALLOC_HARDER unwantedly can be failed.
Additionally the __GFP_MEMALLOC allocation with ALLOC_NO_WATERMARKS also
can be failed.
To avoid the problem, zone_watermark_fast should consider highatomic
reserve. If the actual size of high atomic free is counted accurately
like cma free, we may use it. On this patch just use
nr_reserved_highatomic. Additionally introduce
__zone_watermark_unusable_free to factor out common parts between
zone_watermark_fast and __zone_watermark_ok.
This is an example of ALLOC_HARDER allocation failure using v4.19 based
kernel.
Binder:9343_3: page allocation failure: order:0, mode:0x480020(GFP_ATOMIC), nodemask=(null)
Call trace:
[<ffffff8008f40f8c>] dump_stack+0xb8/0xf0
[<ffffff8008223320>] warn_alloc+0xd8/0x12c
[<ffffff80082245e4>] __alloc_pages_nodemask+0x120c/0x1250
[<ffffff800827f6e8>] new_slab+0x128/0x604
[<ffffff800827b0cc>] ___slab_alloc+0x508/0x670
[<ffffff800827ba00>] __kmalloc+0x2f8/0x310
[<ffffff80084ac3e0>] context_struct_to_string+0x104/0x1cc
[<ffffff80084ad8fc>] security_sid_to_context_core+0x74/0x144
[<ffffff80084ad880>] security_sid_to_context+0x10/0x18
[<ffffff800849bd80>] selinux_secid_to_secctx+0x20/0x28
[<ffffff800849109c>] security_secid_to_secctx+0x3c/0x70
[<ffffff8008bfe118>] binder_transaction+0xe68/0x454c
Mem-Info:
active_anon:102061 inactive_anon:81551 isolated_anon:0
active_file:59102 inactive_file:68924 isolated_file:64
unevictable:611 dirty:63 writeback:0 unstable:0
slab_reclaimable:13324 slab_unreclaimable:44354
mapped:83015 shmem:4858 pagetables:26316 bounce:0
free:2727 free_pcp:1035 free_cma:178
Node 0 active_anon:408244kB inactive_anon:326204kB active_file:236408kB inactive_file:275696kB unevictable:2444kB isolated(anon):0kB isolated(file):256kB mapped:332060kB dirty:252kB writeback:0kB shmem:19432kB writeback_tmp:0kB unstable:0kB all_unreclaimable? no
Normal free:10908kB min:6192kB low:44388kB high:47060kB active_anon:409160kB inactive_anon:325924kB active_file:235820kB inactive_file:276628kB unevictable:2444kB writepending:252kB present:3076096kB managed:2673676kB mlocked:2444kB kernel_stack:62512kB pagetables:105264kB bounce:0kB free_pcp:4140kB local_pcp:40kB free_cma:712kB
lowmem_reserve[]: 0 0
Normal: 505*4kB (H) 357*8kB (H) 201*16kB (H) 65*32kB (H) 1*64kB (H) 0*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB = 10236kB
138826 total pagecache pages
5460 pages in swap cache
Swap cache stats: add 8273090, delete 8267506, find 1004381/4060142
This is an example of ALLOC_NO_WATERMARKS allocation failure using v4.14
based kernel.
kswapd0: page allocation failure: order:0, mode:0x140000a(GFP_NOIO|__GFP_HIGHMEM|__GFP_MOVABLE), nodemask=(null)
kswapd0 cpuset=/ mems_allowed=0
CPU: 4 PID: 1221 Comm: kswapd0 Not tainted 4.14.113-18770262-userdebug #1
Call trace:
[<0000000000000000>] dump_backtrace+0x0/0x248
[<0000000000000000>] show_stack+0x18/0x20
[<0000000000000000>] __dump_stack+0x20/0x28
[<0000000000000000>] dump_stack+0x68/0x90
[<0000000000000000>] warn_alloc+0x104/0x198
[<0000000000000000>] __alloc_pages_nodemask+0xdc0/0xdf0
[<0000000000000000>] zs_malloc+0x148/0x3d0
[<0000000000000000>] zram_bvec_rw+0x410/0x798
[<0000000000000000>] zram_rw_page+0x88/0xdc
[<0000000000000000>] bdev_write_page+0x70/0xbc
[<0000000000000000>] __swap_writepage+0x58/0x37c
[<0000000000000000>] swap_writepage+0x40/0x4c
[<0000000000000000>] shrink_page_list+0xc30/0xf48
[<0000000000000000>] shrink_inactive_list+0x2b0/0x61c
[<0000000000000000>] shrink_node_memcg+0x23c/0x618
[<0000000000000000>] shrink_node+0x1c8/0x304
[<0000000000000000>] kswapd+0x680/0x7c4
[<0000000000000000>] kthread+0x110/0x120
[<0000000000000000>] ret_from_fork+0x10/0x18
Mem-Info:
active_anon:111826 inactive_anon:65557 isolated_anon:0\x0a active_file:44260 inactive_file:83422 isolated_file:0\x0a unevictable:4158 dirty:117 writeback:0 unstable:0\x0a slab_reclaimable:13943 slab_unreclaimable:43315\x0a mapped:102511 shmem:3299 pagetables:19566 bounce:0\x0a free:3510 free_pcp:553 free_cma:0
Node 0 active_anon:447304kB inactive_anon:262228kB active_file:177040kB inactive_file:333688kB unevictable:16632kB isolated(anon):0kB isolated(file):0kB mapped:410044kB d irty:468kB writeback:0kB shmem:13196kB writeback_tmp:0kB unstable:0kB all_unreclaimable? no
Normal free:14040kB min:7440kB low:94500kB high:98136kB reserved_highatomic:32768KB active_anon:447336kB inactive_anon:261668kB active_file:177572kB inactive_file:333768k B unevictable:16632kB writepending:480kB present:4081664kB managed:3637088kB mlocked:16632kB kernel_stack:47072kB pagetables:78264kB bounce:0kB free_pcp:2280kB local_pcp:720kB free_cma:0kB [ 4738.329607] lowmem_reserve[]: 0 0
Normal: 860*4kB (H) 453*8kB (H) 180*16kB (H) 26*32kB (H) 34*64kB (H) 6*128kB (H) 2*256kB (H) 0*512kB 0*1024kB 0*2048kB 0*4096kB = 14232kB
This is trace log which shows GFP_HIGHUSER consumes free pages right
before ALLOC_NO_WATERMARKS.
<...>-22275 [006] .... 889.213383: mm_page_alloc: page=00000000d2be5665 pfn=970744 order=0 migratetype=0 nr_free=3650 gfp_flags=GFP_HIGHUSER|__GFP_ZERO
<...>-22275 [006] .... 889.213385: mm_page_alloc: page=000000004b2335c2 pfn=970745 order=0 migratetype=0 nr_free=3650 gfp_flags=GFP_HIGHUSER|__GFP_ZERO
<...>-22275 [006] .... 889.213387: mm_page_alloc: page=00000000017272e1 pfn=970278 order=0 migratetype=0 nr_free=3650 gfp_flags=GFP_HIGHUSER|__GFP_ZERO
<...>-22275 [006] .... 889.213389: mm_page_alloc: page=00000000c4be79fb pfn=970279 order=0 migratetype=0 nr_free=3650 gfp_flags=GFP_HIGHUSER|__GFP_ZERO
<...>-22275 [006] .... 889.213391: mm_page_alloc: page=00000000f8a51d4f pfn=970260 order=0 migratetype=0 nr_free=3650 gfp_flags=GFP_HIGHUSER|__GFP_ZERO
<...>-22275 [006] .... 889.213393: mm_page_alloc: page=000000006ba8f5ac pfn=970261 order=0 migratetype=0 nr_free=3650 gfp_flags=GFP_HIGHUSER|__GFP_ZERO
<...>-22275 [006] .... 889.213395: mm_page_alloc: page=00000000819f1cd3 pfn=970196 order=0 migratetype=0 nr_free=3650 gfp_flags=GFP_HIGHUSER|__GFP_ZERO
<...>-22275 [006] .... 889.213396: mm_page_alloc: page=00000000f6b72a64 pfn=970197 order=0 migratetype=0 nr_free=3650 gfp_flags=GFP_HIGHUSER|__GFP_ZERO
kswapd0-1207 [005] ...1 889.213398: mm_page_alloc: page= (null) pfn=0 order=0 migratetype=1 nr_free=3650 gfp_flags=GFP_NOWAIT|__GFP_HIGHMEM|__GFP_NOWARN|__GFP_MOVABLE
[[email protected]: remove redundant code for high-order]
Link: http://lkml.kernel.org/r/[email protected]
Reported-by: Yong-Taek Lee <[email protected]>
Suggested-by: Minchan Kim <[email protected]>
Signed-off-by: Jaewon Kim <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Reviewed-by: Baoquan He <[email protected]>
Acked-by: Vlastimil Babka <[email protected]>
Acked-by: Mel Gorman <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Yong-Taek Lee <[email protected]>
Cc: Michal Hocko <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Linus Torvalds <[email protected]>
---
mm/page_alloc.c | 65 ++++++++++++++++++++++++++++++++-------------------------
1 file changed, 36 insertions(+), 29 deletions(-)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9c35403..237463d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3130,6 +3130,29 @@ static inline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
#endif /* CONFIG_FAIL_PAGE_ALLOC */
+static inline long __zone_watermark_unusable_free(struct zone *z,
+ unsigned int order, unsigned int alloc_flags)
+{
+ const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
+ long unusable_free = (1 << order) - 1;
+
+ /*
+ * If the caller does not have rights to ALLOC_HARDER then subtract
+ * the high-atomic reserves. This will over-estimate the size of the
+ * atomic reserve but it avoids a search.
+ */
+ if (likely(!alloc_harder))
+ unusable_free += z->nr_reserved_highatomic;
+
+#ifdef CONFIG_CMA
+ /* If allocation can't use CMA areas don't use free CMA pages */
+ if (!(alloc_flags & ALLOC_CMA))
+ unusable_free += zone_page_state(z, NR_FREE_CMA_PAGES);
+#endif
+
+ return unusable_free;
+}
+
/*
* Return true if free base pages are above 'mark'. For high-order checks it
* will return true of the order-0 watermark is reached and there is at least
@@ -3145,19 +3168,12 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
/* free_pages may go negative - that's OK */
- free_pages -= (1 << order) - 1;
+ free_pages -= __zone_watermark_unusable_free(z, order, alloc_flags);
if (alloc_flags & ALLOC_HIGH)
min -= min / 2;
- /*
- * If the caller does not have rights to ALLOC_HARDER then subtract
- * the high-atomic reserves. This will over-estimate the size of the
- * atomic reserve but it avoids a search.
- */
- if (likely(!alloc_harder)) {
- free_pages -= z->nr_reserved_highatomic;
- } else {
+ if (unlikely(alloc_harder)) {
/*
* OOM victims can try even harder than normal ALLOC_HARDER
* users on the grounds that it's definitely going to be in
@@ -3170,13 +3186,6 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
min -= min / 4;
}
-
-#ifdef CONFIG_CMA
- /* If allocation can't use CMA areas don't use free CMA pages */
- if (!(alloc_flags & ALLOC_CMA))
- free_pages -= zone_page_state(z, NR_FREE_CMA_PAGES);
-#endif
-
/*
* Check watermarks for an order-0 allocation request. If these
* are not met, then a high-order request also cannot go ahead
@@ -3225,24 +3234,22 @@ bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
unsigned long mark, int classzone_idx, unsigned int alloc_flags)
{
- long free_pages = zone_page_state(z, NR_FREE_PAGES);
- long cma_pages = 0;
+ long free_pages;
-#ifdef CONFIG_CMA
- /* If allocation can't use CMA areas don't use free CMA pages */
- if (!(alloc_flags & ALLOC_CMA))
- cma_pages = zone_page_state(z, NR_FREE_CMA_PAGES);
-#endif
+ free_pages = zone_page_state(z, NR_FREE_PAGES);
/*
* Fast check for order-0 only. If this fails then the reserves
- * need to be calculated. There is a corner case where the check
- * passes but only the high-order atomic reserve are free. If
- * the caller is !atomic then it'll uselessly search the free
- * list. That corner case is then slower but it is harmless.
+ * need to be calculated.
*/
- if (!order && (free_pages - cma_pages) > mark + z->lowmem_reserve[classzone_idx])
- return true;
+ if (!order) {
+ long fast_free;
+
+ fast_free = free_pages;
+ fast_free -= __zone_watermark_unusable_free(z, 0, alloc_flags);
+ if (fast_free > mark + z->lowmem_reserve[classzone_idx])
+ return true;
+ }
return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
free_pages);
--
2.7.4
Greg KH <[email protected]> 于2022年9月25日周日 19:00写道：
>
> On Sun, Sep 25, 2022 at 03:35:27AM -0700, wangyong wrote:
> > From: Joonsoo Kim <[email protected]>
> >
> > [ backport of commit 3334a45eb9e2bb040c880ef65e1d72357a0a008b ]
>
> This is from 5.8. What about the 5.4.y kernel? Why would someone
> upgrading from 4.19.y to 5.4.y suffer a regression here?
>
I encountered this problem on 4.19, but I haven't encountered it on 5.4.
However, this should be a common problem, so 5.4 may also need to be
merged.
Hello, Joonsoo, what do you think?
> And why wouldn't someone who has this issue just not use 5.10.y instead?
> What prevents someone from moving off of 4.19.y at this point in time?
>
This is a solution, but upgrading the kernel version requires time and overhead,
so use the patch is the most effective way, if there is.
Thanks.
> thanks,
>
> greg k-h
On Sun, Sep 25, 2022 at 10:32:32PM +0800, yong w wrote:
> Greg KH <[email protected]> 于2022年9月25日周日 19:00写道：
> >
> > On Sun, Sep 25, 2022 at 03:35:27AM -0700, wangyong wrote:
> > > From: Joonsoo Kim <[email protected]>
> > >
> > > [ backport of commit 3334a45eb9e2bb040c880ef65e1d72357a0a008b ]
> >
> > This is from 5.8. What about the 5.4.y kernel? Why would someone
> > upgrading from 4.19.y to 5.4.y suffer a regression here?
> >
> I encountered this problem on 4.19, but I haven't encountered it on 5.4.
> However, this should be a common problem, so 5.4 may also need to be
> merged.
>
> Hello, Joonsoo, what do you think?
>
> > And why wouldn't someone who has this issue just not use 5.10.y instead?
> > What prevents someone from moving off of 4.19.y at this point in time?
> >
> This is a solution, but upgrading the kernel version requires time and overhead,
> so use the patch is the most effective way, if there is.
You will have to move off of 4.19 soon anyway, so why delay the change?
thanks,
greg k-h
On Sun, Sep 25, 2022 at 03:35:26AM -0700, wangyong wrote:
> Here are the corresponding backports to 4.19.
> And fix classzone_idx context differences causing patch merge conflicts.
>
> Original commit IDS:
> 3334a45 mm/page_alloc: use ac->high_zoneidx for classzone_idx
> f27ce0e page_alloc: consider highatomic reserve in watermark fast
> 9282012 page_alloc: fix invalid watermark check on a negative value
>
> Changes from v1:
> - Add commit information of the original patches.
None of these have your signed-off-by on them showing that the backport
came from you and that you are responsible for them.
So even if we did think they were valid to backport, I can't take them
as-is :(
thanks,
greg k-h
A: http://en.wikipedia.org/wiki/Top_post
Q: Were do I find info about this thing called top-posting?
A: Because it messes up the order in which people normally read text.
Q: Why is top-posting such a bad thing?
A: Top-posting.
Q: What is the most annoying thing in e-mail?
A: No.
Q: Should I include quotations after my reply?
http://daringfireball.net/2007/07/on_top
On Fri, Oct 07, 2022 at 04:53:50PM +0800, yong w wrote:
> Is it ok to add my signed-off-by? my signed-off-by is as follows:
>
> Signed-off-by: wangyong <[email protected]>
For obvious reasons, I can not take that from a random gmail account
(nor should ZTE want me to do that.)
Please fix up your email systems and do this properly and send the
series again.
thanks,
greg k-h
Greg KH <[email protected]> 于2022年10月8日周六 00:40写道：
>
> A: http://en.wikipedia.org/wiki/Top_post
> Q: Were do I find info about this thing called top-posting?
> A: Because it messes up the order in which people normally read text.
> Q: Why is top-posting such a bad thing?
> A: Top-posting.
> Q: What is the most annoying thing in e-mail?
>
> A: No.
> Q: Should I include quotations after my reply?
>
> http://daringfireball.net/2007/07/on_top
>
>
> On Fri, Oct 07, 2022 at 04:53:50PM +0800, yong w wrote:
> > Is it ok to add my signed-off-by? my signed-off-by is as follows:
> >
> > Signed-off-by: wangyong <[email protected]>
>
> For obvious reasons, I can not take that from a random gmail account
> (nor should ZTE want me to do that.)
>
> Please fix up your email systems and do this properly and send the
> series again.
>
> thanks,
>
> greg k-h
Sorry, our mail system cannot send external mail for some reason.
And this is my email, I can receive an email and reply to it.
thanks.
On Mon, Oct 10, 2022 at 11:47:30PM +0800, yong w wrote:
> Greg KH <[email protected]> 于2022年10月8日周六 00:40写道：
> >
> > A: http://en.wikipedia.org/wiki/Top_post
> > Q: Were do I find info about this thing called top-posting?
> > A: Because it messes up the order in which people normally read text.
> > Q: Why is top-posting such a bad thing?
> > A: Top-posting.
> > Q: What is the most annoying thing in e-mail?
> >
> > A: No.
> > Q: Should I include quotations after my reply?
> >
> > http://daringfireball.net/2007/07/on_top
> >
> >
> > On Fri, Oct 07, 2022 at 04:53:50PM +0800, yong w wrote:
> > > Is it ok to add my signed-off-by? my signed-off-by is as follows:
> > >
> > > Signed-off-by: wangyong <[email protected]>
> >
> > For obvious reasons, I can not take that from a random gmail account
> > (nor should ZTE want me to do that.)
> >
> > Please fix up your email systems and do this properly and send the
> > series again.
> >
> > thanks,
> >
> > greg k-h
>
> Sorry, our mail system cannot send external mail for some reason.
Sorry, then I can not attribute anything to your company. It has
already been warned that it can not continue to contribute to the Linux
kernel and some of your gmail "aliases" have been banned from the
mailing lists.
Please fix your email system so that you can properly contribute to
Linux.
> And this is my email, I can receive an email and reply to it.
Yes, but I have no proof that your ZTE email is correct, only that this
is a random gmail.com address :(
What would you do if you were in my situation?
Please work with your IT group to fix their email systems.
good luck,
greg k-h