Re: [Devel] [PATCH rh7 2/2] mm/memcg: reclaim only kmem if kmem limit reached.
25.08.2017 18:38, Andrey Ryabinin пишет:
> If kmem limit on memcg reached, we go into memory reclaim,
> and reclaim everything we can, including page cache and anon.
> Reclaiming page cache or anon won't help since we need to lower
> only kmem usage. This patch fixes the problem by avoiding
> non-kmem reclaim on hitting the kmem limit.
>
Can't there be a situation, when some object in anon mem or page cache holds
some object in kmem (indirectly)?
> https://jira.sw.ru/browse/PSBM-69226
> Signed-off-by: Andrey Ryabinin
> ---
> include/linux/memcontrol.h | 10 ++
> include/linux/swap.h | 2 +-
> mm/memcontrol.c| 30 --
> mm/vmscan.c| 31 ---
> 4 files changed, 51 insertions(+), 22 deletions(-)
>
> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> index 1a52e58ab7de..1d6bc80c4c90 100644
> --- a/include/linux/memcontrol.h
> +++ b/include/linux/memcontrol.h
> @@ -45,6 +45,16 @@ struct mem_cgroup_reclaim_cookie {
> unsigned int generation;
> };
>
> +/*
> + * Reclaim flags for mem_cgroup_hierarchical_reclaim
> + */
> +#define MEM_CGROUP_RECLAIM_NOSWAP_BIT0x0
> +#define MEM_CGROUP_RECLAIM_NOSWAP(1 << MEM_CGROUP_RECLAIM_NOSWAP_BIT)
> +#define MEM_CGROUP_RECLAIM_SHRINK_BIT0x1
> +#define MEM_CGROUP_RECLAIM_SHRINK(1 << MEM_CGROUP_RECLAIM_SHRINK_BIT)
> +#define MEM_CGROUP_RECLAIM_KMEM_BIT 0x2
> +#define MEM_CGROUP_RECLAIM_KMEM (1 <<
> MEM_CGROUP_RECLAIM_KMEM_BIT)
> +
> #ifdef CONFIG_MEMCG
> int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
> gfp_t gfp_mask, struct mem_cgroup **memcgp);
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index bd162f9bef0d..bd47451ec95a 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -324,7 +324,7 @@ extern unsigned long try_to_free_pages(struct zonelist
> *zonelist, int order,
> extern int __isolate_lru_page(struct page *page, isolate_mode_t mode);
> extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem,
> unsigned long nr_pages,
> - gfp_t gfp_mask, bool noswap);
> + gfp_t gfp_mask, int flags);
> extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
> gfp_t gfp_mask, bool noswap,
> struct zone *zone,
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 97824e281d7a..f9a5f3819a31 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -511,16 +511,6 @@ enum res_type {
> #define OOM_CONTROL (0)
>
> /*
> - * Reclaim flags for mem_cgroup_hierarchical_reclaim
> - */
> -#define MEM_CGROUP_RECLAIM_NOSWAP_BIT0x0
> -#define MEM_CGROUP_RECLAIM_NOSWAP(1 << MEM_CGROUP_RECLAIM_NOSWAP_BIT)
> -#define MEM_CGROUP_RECLAIM_SHRINK_BIT0x1
> -#define MEM_CGROUP_RECLAIM_SHRINK(1 << MEM_CGROUP_RECLAIM_SHRINK_BIT)
> -#define MEM_CGROUP_RECLAIM_KMEM_BIT 0x2
> -#define MEM_CGROUP_RECLAIM_KMEM (1 <<
> MEM_CGROUP_RECLAIM_KMEM_BIT)
> -
> -/*
> * The memcg_create_mutex will be held whenever a new cgroup is created.
> * As a consequence, any change that needs to protect against new child
> cgroups
> * appearing has to hold it as well.
> @@ -2137,7 +2127,7 @@ static unsigned long mem_cgroup_reclaim(struct
> mem_cgroup *memcg,
> if (loop)
> drain_all_stock_async(memcg);
> total += try_to_free_mem_cgroup_pages(memcg, SWAP_CLUSTER_MAX,
> - gfp_mask, noswap);
> + gfp_mask, flags);
> if (test_thread_flag(TIF_MEMDIE) ||
> fatal_signal_pending(current))
> return 1;
> @@ -2150,6 +2140,16 @@ static unsigned long mem_cgroup_reclaim(struct
> mem_cgroup *memcg,
> break;
> if (mem_cgroup_margin(memcg, flags & MEM_CGROUP_RECLAIM_KMEM))
> break;
> +
> + /*
> + * Try harder to reclaim dcache. dcache reclaim may
> + * temporarly fail due to dcache->dlock being held
> + * by someone else. We must try harder to avoid premature
> + * slab allocation failures.
> + */
> + if (flags & MEM_CGROUP_RECLAIM_KMEM &&
> + page_counter_read(&memcg->dcache))
> + continue;
> /*
>* If nothing was reclaimed after two attempts, there
>* may be no reclaimable pages in this hierarchy.
> @@ -2778,11 +2778,13 @@ static int try_charge(struct mem_cgroup *memcg, gfp_t
> gfp_mask, bool kmem_charge
> struct mem_cgroup *mem_over_limit;
> struc
Re: [Devel] [PATCH rh7 2/2] mm/memcg: reclaim only kmem if kmem limit reached.
On 08/28/2017 12:02 PM, Stanislav Kinsburskiy wrote: > > > 25.08.2017 18:38, Andrey Ryabinin пишет: >> If kmem limit on memcg reached, we go into memory reclaim, >> and reclaim everything we can, including page cache and anon. >> Reclaiming page cache or anon won't help since we need to lower >> only kmem usage. This patch fixes the problem by avoiding >> non-kmem reclaim on hitting the kmem limit. >> > > Can't there be a situation, when some object in anon mem or page cache holds > some object in kmem (indirectly)? > None that I know of. ___ Devel mailing list Devel@openvz.org https://lists.openvz.org/mailman/listinfo/devel
[Devel] [PATCH rh7] mm/hmm: Restore removed hunk in copy_one_pte()
Rebased "ms/mm: remove rest usage of VM_NONLINEAR and pte_file()"
removed huge hunk from copy_one_pte for no reason. Bring it back
https://jira.sw.ru/browse/PSBM-70740
Fixes: be8e22c9c444 ("ms/mm: remove rest usage of VM_NONLINEAR and pte_file()")
Signed-off-by: Andrey Ryabinin
---
mm/memory.c | 25 ++---
1 file changed, 22 insertions(+), 3 deletions(-)
diff --git a/mm/memory.c b/mm/memory.c
index e53e8dd288eb..c30a042cebf5 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -879,13 +879,32 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct
*src_mm,
pte = pte_swp_mksoft_dirty(pte);
set_pte_at(src_mm, addr, src_pte, pte);
}
- } else {
+ } else if (is_hmm_entry(entry)) {
+ page = hmm_entry_to_page(entry);
+
+ /*
+* Update rss count even for un-addressable
+* page as they should be consider just like
+* any other page.
+*/
+ get_page(page);
+ rss[mm_counter(page)]++;
+ page_dup_rmap(page);
+
+ if (is_write_hmm_entry(entry) &&
+ is_cow_mapping(vm_flags)) {
+ make_hmm_entry_read(&entry);
+ pte = swp_entry_to_pte(entry);
+ if (pte_swp_soft_dirty(*src_pte))
+ pte = pte_swp_mksoft_dirty(pte);
+ set_pte_at(src_mm, addr, src_pte, pte);
+ }
+ } else
/*
* This can not happen because HMM migration holds
* mmap_sem in read mode.
*/
- VM_BUG_ON(is_hmm_entry(entry));
- }
+VM_BUG_ON(is_hmm_entry(entry));
goto out_set_pte;
}
--
2.13.5
___
Devel mailing list
Devel@openvz.org
https://lists.openvz.org/mailman/listinfo/devel
[Devel] [PATCH rh7 2/2] ms/x86, efi, kasan: #undef memset/memcpy/memmove per arch
From: Andrey Ryabinin commit 769a8089c1fd2fe94c13e66fe6e03d7820953ee3 upstream. In not-instrumented code KASAN replaces instrumented memset/memcpy/memmove with not-instrumented analogues __memset/__memcpy/__memove. However, on x86 the EFI stub is not linked with the kernel. It uses not-instrumented mem*() functions from arch/x86/boot/compressed/string.c So we don't replace them with __mem*() variants in EFI stub. On ARM64 the EFI stub is linked with the kernel, so we should replace mem*() functions with __mem*(), because the EFI stub runs before KASAN sets up early shadow. So let's move these #undef mem* into arch's asm/efi.h which is also included by the EFI stub. Also, this will fix the warning in 32-bit build reported by kbuild test robot: efi-stub-helper.c:599:2: warning: implicit declaration of function 'memcpy' [a...@linux-foundation.org: use 80 cols in comment] Signed-off-by: Andrey Ryabinin Reported-by: Fengguang Wu Cc: Will Deacon Cc: Catalin Marinas Cc: Matt Fleming Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Andrey Ryabinin --- arch/x86/include/asm/efi.h | 10 ++ 1 file changed, 10 insertions(+) diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 2215cd26512d..8e70dd8bde6c 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -68,6 +68,16 @@ extern u64 asmlinkage efi_call(void *fp, ...); extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size, u32 type, u64 attribute); +/* + * CONFIG_KASAN may redefine memset to __memset. __memset function is present + * only in kernel binary. Since the EFI stub linked into a separate binary it + * doesn't have __memset(). So we should use standard memset from + * arch/x86/boot/compressed/string.c. The same applies to memcpy and memmove. + */ +#undef memcpy +#undef memset +#undef memmove + #endif /* CONFIG_X86_32 */ extern int add_efi_memmap; -- 2.13.5 ___ Devel mailing list Devel@openvz.org https://lists.openvz.org/mailman/listinfo/devel
[Devel] [PATCH rh7 1/2] fixup for - ms/x86_64: kasan: add interceptors for memset/memmove/memcpy functions
This hunk shoud have been in the following patch: 796752003a42b70d1f32eb5771885f59febada0d Author: Andrey Ryabinin Date: Thu Sep 3 19:27:42 2015 +0400 ms/x86_64: kasan: add interceptors for memset/memmove/memcpy functions This fixes: In file included from ./arch/x86/include/asm/string.h:4:0, from include/linux/string.h:18, from include/linux/efi.h:15, from arch/x86/boot/compressed/eboot.c:12: ./arch/x86/include/asm/string_64.h:79:0: warning: "memset" redefined #define memset(s, c, n) __memset(s, c, n) In file included from arch/x86/boot/compressed/eboot.c:11:0: arch/x86/boot/compressed/../string.h:18:0: note: this is the location of the previous definition #define memset(d,c,l) __builtin_memset(d,c,l) Signed-off-by: Andrey Ryabinin --- arch/x86/boot/compressed/eboot.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index ec76e778d101..b4a6e12a2800 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -8,7 +8,6 @@ * --- */ #include -#include "../string.h" #include #include #include @@ -16,6 +15,7 @@ #include #include +#include "../string.h" #include "eboot.h" static efi_system_table_t *sys_table; -- 2.13.5 ___ Devel mailing list Devel@openvz.org https://lists.openvz.org/mailman/listinfo/devel
[Devel] [PATCH RHEL7 COMMIT] fixup for - ms/x86_64: kasan: add interceptors for memset/memmove/memcpy functions
The commit is pushed to "branch-rh7-3.10.0-693.1.1.vz7.37.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git after rh7-3.10.0-693.1.1.el7 --> commit 2b22264b4e695b658fc71b472796c8728b119cc8 Author: Andrey Ryabinin Date: Mon Aug 28 15:57:43 2017 +0300 fixup for - ms/x86_64: kasan: add interceptors for memset/memmove/memcpy functions This hunk shoud have been in the following patch: 796752003a42b70d1f32eb5771885f59febada0d Author: Andrey Ryabinin Date: Thu Sep 3 19:27:42 2015 +0400 ms/x86_64: kasan: add interceptors for memset/memmove/memcpy functions This fixes: In file included from ./arch/x86/include/asm/string.h:4:0, from include/linux/string.h:18, from include/linux/efi.h:15, from arch/x86/boot/compressed/eboot.c:12: ./arch/x86/include/asm/string_64.h:79:0: warning: "memset" redefined #define memset(s, c, n) __memset(s, c, n) In file included from arch/x86/boot/compressed/eboot.c:11:0: arch/x86/boot/compressed/../string.h:18:0: note: this is the location of the previous definition #define memset(d,c,l) __builtin_memset(d,c,l) Signed-off-by: Andrey Ryabinin --- arch/x86/boot/compressed/eboot.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index ec76e77..b4a6e12 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -8,7 +8,6 @@ * --- */ #include -#include "../string.h" #include #include #include @@ -16,6 +15,7 @@ #include #include +#include "../string.h" #include "eboot.h" static efi_system_table_t *sys_table; ___ Devel mailing list Devel@openvz.org https://lists.openvz.org/mailman/listinfo/devel
[Devel] [PATCH RHEL7 COMMIT] ms/x86, efi, kasan: #undef memset/memcpy/memmove per arch
The commit is pushed to "branch-rh7-3.10.0-693.1.1.vz7.37.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git after rh7-3.10.0-693.1.1.el7 --> commit f4b5ab2e530bf8bc46c79d4effa14e51a6643e69 Author: Andrey Ryabinin Date: Mon Aug 28 15:57:45 2017 +0300 ms/x86, efi, kasan: #undef memset/memcpy/memmove per arch commit 769a8089c1fd2fe94c13e66fe6e03d7820953ee3 upstream. In not-instrumented code KASAN replaces instrumented memset/memcpy/memmove with not-instrumented analogues __memset/__memcpy/__memove. However, on x86 the EFI stub is not linked with the kernel. It uses not-instrumented mem*() functions from arch/x86/boot/compressed/string.c So we don't replace them with __mem*() variants in EFI stub. On ARM64 the EFI stub is linked with the kernel, so we should replace mem*() functions with __mem*(), because the EFI stub runs before KASAN sets up early shadow. So let's move these #undef mem* into arch's asm/efi.h which is also included by the EFI stub. Also, this will fix the warning in 32-bit build reported by kbuild test robot: efi-stub-helper.c:599:2: warning: implicit declaration of function 'memcpy' [a...@linux-foundation.org: use 80 cols in comment] Signed-off-by: Andrey Ryabinin Reported-by: Fengguang Wu Cc: Will Deacon Cc: Catalin Marinas Cc: Matt Fleming Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Andrey Ryabinin --- arch/x86/include/asm/efi.h | 10 ++ 1 file changed, 10 insertions(+) diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 2215cd2..8e70dd8 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -68,6 +68,16 @@ extern u64 asmlinkage efi_call(void *fp, ...); extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size, u32 type, u64 attribute); +/* + * CONFIG_KASAN may redefine memset to __memset. __memset function is present + * only in kernel binary. Since the EFI stub linked into a separate binary it + * doesn't have __memset(). So we should use standard memset from + * arch/x86/boot/compressed/string.c. The same applies to memcpy and memmove. + */ +#undef memcpy +#undef memset +#undef memmove + #endif /* CONFIG_X86_32 */ extern int add_efi_memmap; ___ Devel mailing list Devel@openvz.org https://lists.openvz.org/mailman/listinfo/devel
