rom commit 3f70bd51cb4405dc5cf8624292ffa474679fc9c7)
Signed-off-by: Andrey Ryabinin
---
fs/dcache.c | 104 ++--
1 file changed, 52 insertions(+), 52 deletions(-)
diff --git a/fs/dcache.c b/fs/dcache.c
index 8ad0b6a57736..3f6a128e6c20 100644
--- a/fs/dcache.c
+++ b/f
at crosses into a subvolume. (Those aliases are currently
marked DCACHE_DISCONNECTED--but not really for any good reason, and
we'll change that soon.)
Signed-off-by: J. Bruce Fields
Signed-off-by: Al Viro
(cherry picked from commit da093a9b76efca0a7a217af538929e1ecb204466)
Signed-off-by: Andre
up with memory corruption.
Cc: sta...@vger.kernel.org # 3.12+, counting backports
Signed-off-by: Al Viro
(cherry picked from commit 3b821409632ab778d46e807516b457dfa72736ed)
Signed-off-by: Andrey Ryabinin
---
fs/dcache.c | 11 ---
1 file changed, 8 insertions(+), 3 deletions(-)
diff --git a
From: Al Viro
and lock the right list there
Cc: sta...@vger.kernel.org
Signed-off-by: Al Viro
Maybe fixes https://jira.sw.ru/browse/PSBM-95177
(cherry picked from commit 6f18493e541c690169c3b1479d47d95f624161cf)
Signed-off-by: Andrey Ryabinin
---
fs/dcache.c | 8 ++--
1 file
rom commit 908790fa3b779d37365e6b28e3aa0f6e833020c3)
Signed-off-by: Andrey Ryabinin
---
fs/dcache.c | 11 +--
1 file changed, 9 insertions(+), 2 deletions(-)
diff --git a/fs/dcache.c b/fs/dcache.c
index 59760ae9b3fa..549178a85e6c 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2792,6 +2792,9 @@ s
s
Signed-off-by: Al Viro
(cherry picked from commit e1a24bb0aa6abaa86b5a95638722ea2036dbaadd)
Signed-off-by: Andrey Ryabinin
---
fs/dcache.c | 13 +
1 file changed, 9 insertions(+), 4 deletions(-)
diff --git a/fs/dcache.c b/fs/dcache.c
index 8d625f8216e6..059277b23f8f 100644
--- a/
xb0
sock_sendmsg+0xb0/0xf0
SYSC_sendto+0x121/0x1c0
SyS_sendto+0xe/0x10
tracesys+0xa3/0xc9
https://jira.sw.ru/browse/PSBM-94717
Signed-off-by: Andrey Ryabinin
---
include/net/sock.h| 5 +
net/core/sock.c | 21 ++---
net/ipv4/ip_output.c | 5 +++--
net/i
On 5/28/19 7:06 PM, Konstantin Khorenko wrote:
> When mem cgroups are disabled in workingset_activation()
> lookup_page_cgroup() can return NULL and trigger crash on next step on
> page bit check.
>
> Fixes: f6a8b015027e ("ms/mm: workingset: per-cgroup cache
> thrash detection")
>
>
ca11b798998a62c2bf87ea0477b5c60af25ba46d)
Signed-off-by: Andrey Ryabinin
---
.../net/ethernet/mellanox/mlx5/core/en_main.c | 42 +--
1 file changed, 21 insertions(+), 21 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index
| 4 +++-
> 5 files changed, 25 insertions(+), 4 deletions(-)
>
Reviewed-by: Andrey Ryabinin
___
Devel mailing list
Devel@openvz.org
https://lists.openvz.org/mailman/listinfo/devel
and
Acked-by: Johannes Weiner
Signed-off-by: Jonathan Corbet
(cherry picked from commit e6507a00fd08986ce003012a10af78cc7e47eee8)
Signed-off-by: Andrey Ryabinin
---
Documentation/sysctl/vm.txt | 1 +
1 file changed, 1 insertion(+)
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm
commit 795ae7a0de6b834a0cc202aa55c190ef81496665)
Signed-off-by: Andrey Ryabinin
---
Documentation/sysctl/vm.txt | 18 ++
include/linux/mm.h | 1 +
include/linux/mmzone.h | 2 ++
kernel/sysctl.c | 10 ++
mm/page_alloc.c | 29
workingset_refault() releases RCU lock too soon, before the
memcg_inc_ws_activate() which may result in crash if memcg deletion
runs in parallel with workingset_refault()
Fixes: f6a8b015027e ("ms/mm: workingset: per-cgroup cache thrash detection")
Signed-off-by: Andrey Ryabini
is moving and NULL otherwise. Instead of mocking with
mem_cgroup_begin_update_page_stat() obtain memcg from page in
workingset_activation() directly.
Fixes: f6a8b015027e ("ms/mm: workingset: per-cgroup cache thrash detection")
Signed-off-by: Andrey Ryabinin
---
include/linux/memcontrol.h
When mem cgroups are disabled memcg_inc_ws_activate might be called with
NULL memcg and crash. Fix it.
Fixes: f6a8b015027e ("ms/mm: workingset: per-cgroup cache thrash detection")
Signed-off-by: Andrey Ryabinin
---
mm/memcontrol.c | 3 +++
1 file changed, 3 insertions(+)
diff
Correcting Kostya's email.
On 5/14/19 12:31 PM, Andrey Ryabinin wrote:
> After rebase to kernel-3.10.0-957.10.1.el7 memcg id freed
> in memcg offline callback instead of free. This makes possible
> to reuse id by another cgroup, thus mem_cgroup_uncharge_swap()
> may call css_put()
/browse/PSBM-94269
Signed-off-by: Andrey Ryabinin
---
mm/memcontrol.c | 9 ++---
1 file changed, 2 insertions(+), 7 deletions(-)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f2a81d72d3bf..e6e1b8e8c9c9 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6213,8 +6213,6 @@ unsigned short
userspace to make sure that oom_guarantee set
for all sub cgroups of cgroups like machine.slice wich has unreacheable high
oom_guarantee and we don't want this high guarantee on sub groups.
https://pmc.acronis.com/browse/VSTOR-22575
Signed-off-by: Andrey Ryabinin
---
mm/memcontrol.c | 2 +-
1 file chan
On 4/9/19 1:19 PM, Andrey Ryabinin wrote:
>
>
> On 4/9/19 12:34 PM, Konstantin Khorenko wrote:
>> From: Eric Dumazet
>>
>> tcp_send_rcvq() is used for re-injecting data into tcp receive queue.
>>
>> Problems :
>>
>> - No check aga
On 4/9/19 12:34 PM, Konstantin Khorenko wrote:
> From: Eric Dumazet
>
> tcp_send_rcvq() is used for re-injecting data into tcp receive queue.
>
> Problems :
>
> - No check against size is performed, allowed user to fool kernel in
> attempting very large memory allocations, eventually
On 4/8/19 4:24 PM, Alexey Kuznetsov wrote:
> Hello!
>
> Does not this mean that now we have a reserve,
> which nobody ever uses?
>
Don't think so.
> I am aware this reserve can be used in theory
> from mm itself.
Yes, it the whole idea of reserves - to use them only for memory reclaim.
>
is present in the
system.
https://pmc.acronis.com/browse/VSTOR-21390
Signed-off-by: Andrey Ryabinin
---
include/linux/skbuff.h | 21 +++--
include/net/sock.h | 15 ---
2 files changed, 19 insertions(+), 17 deletions(-)
diff --git a/include/linux/skbuff.h b/include/lin
GFP_ATOMIC can use
1/4 of memory reserves, while GFP_ATOMIC|__GFP_NOMEMALLOC can't. So it's seems
more reasonable to use GFP_ATOMIC all across receive path so all allocations
have similar chance of succeeding.
https://pmc.acronis.com/browse/VSTOR-21390
Signed-off-by: Andrey Ryabinin
---
net/core/sk
Since commit 191cfed565c0 ("RDMA/ocrdma: Remove old FRWR API")
the STAG array isn't used. Remove it.
https://pmc.acronis.com/browse/VSTOR-21732
Signed-off-by: Andrey Ryabinin
---
drivers/infiniband/hw/ocrdma/ocrdma.h | 1 -
drivers/infiniband/hw/ocrdma/ocrdma_main.c | 5
On 3/30/19 11:04 AM, Konstantin Khorenko wrote:
> From: Andrey Ryabinin
>
> At the moment inactive_list_is_low() mistakenly checks FILE list
> whatever (file or anon) list is asked to check.
>
> Honor list type argument.
>
> Fixes: 1f45c6c57160 ("mm/vmscan:
igned-off-by: Andrey Ryabinin
---
mm/page_alloc.c | 8
1 file changed, 8 insertions(+)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5dc48331242a..45da030d8da2 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3576,6 +3576,14 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned i
sysfs_perms_open() replaces ve0 with NULL which results in always empty
output from cgroup/ve/ve.default_sysfs_permissions file. Fix that
by passing correct ve0 address.
Signed-off-by: Andrey Ryabinin
---
fs/sysfs/ve.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/sysfs
Signed-off-by: Andrey Ryabinin
---
mm/slub.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mm/slub.c b/mm/slub.c
index cfed91b0fdb8..7ea4138f96b6 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1440,7 +1440,7 @@ static struct page *allocate_slab(struct kmem_cache *s,
gfp_t flags, int
Since __entry->time wasn't assigned, mm_page_alloc trace point
shows always 0 lat.
Signed-off-by: Andrey Ryabinin
---
include/trace/events/kmem.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index af1a8ffb106b..74f69db5d2f7 100
Since transition from jiffies to sched_clock(), mm_page_alloc
garbadge since we substract from jiffies nanoseconds.
Fix this.
Signed-off-by: Andrey Ryabinin
---
include/trace/events/kmem.h | 2 +-
mm/page_alloc.c | 12 ++--
2 files changed, 7 insertions(+), 7 deletions
Move swapped in anon pages directly to active list. This should
help us to prevent anon thrashing. Recently swapped in pages
has more chances to stay in memory.
https://pmc.acronis.com/browse/VSTOR-20859
Signed-off-by: Andrey Ryabinin
---
include/linux/swap.h | 5 +++--
mm/madvise.c
an't to reclaim anon. With active list protection,
anon aging makes anon reclaiming a lot more aggressive than page cache
and leads to anon thrashing when page cache inactive is low.
Move aging under "if (sc->may_shrink_active)" to fix that.
https://pmc.acronis.com/browse/VSTOR
se/PSBM-91933
Signed-off-by: Andrey Ryabinin
---
mm/memcontrol.c | 17 -
1 file changed, 8 insertions(+), 9 deletions(-)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 052b11501b8e..88e6982c9e17 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6260,6 +6260,7 @@
picked from commit 0a6b76dd23fa08c5fd7b68acdb55018a37afd4aa)
Signed-off-by: Andrey Ryabinin
---
include/linux/memcontrol.h | 10 ++
mm/memcontrol.c| 2 +-
mm/workingset.c| 24 +++-
3 files changed, 26 insertions(+), 10 deletions(-)
diff --git
rry picked from commit 23047a96d7cfcfca1a6d026ecaec526ea4803e9e)
Signed-off-by: Andrey Ryabinin
---
include/linux/memcontrol.h | 53 +++---
include/linux/mmzone.h | 14 +++---
mm/memcontrol.c| 32 +
mm/vmscan.c| 71 ++-
Acked-by: Johannes Weiner
Cc: Michal Hocko
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
https://pmc.acronis.com/browse/VSTOR-19037
(cherry picked from commit 3337767850b490eec5ca822f871241c981664737)
Signed-off-by: Andrey Ryabinin
---
mm/vmscan.c | 32
162453bfbdf4c0f58cb3058aad9ad8cda1044cda)
Signed-off-by: Andrey Ryabinin
---
mm/workingset.c | 56 -
1 file changed, 28 insertions(+), 28 deletions(-)
diff --git a/mm/workingset.c b/mm/workingset.c
index 150223b6b161..22b66359d92d 100644
--- a/mm
-19037
(cherry picked from commit 689c94f03ae251181725fe853b4ffc870f05c7fe)
Signed-off-by: Andrey Ryabinin
---
mm/workingset.c | 10 ++
1 file changed, 6 insertions(+), 4 deletions(-)
diff --git a/mm/workingset.c b/mm/workingset.c
index 8da2955587fa..150223b6b161 100644
--- a/mm/workingset.c
Torvalds
https://pmc.acronis.com/browse/VSTOR-19037
(cherry picked from commit 612e44939c3c77245ac80843c0c7876c8cf97282)
Signed-off-by: Andrey Ryabinin
---
mm/workingset.c | 30 +-
1 file changed, 29 insertions(+), 1 deletion(-)
diff --git a/mm/workingset.c b/mm
se/PSBM-91933
Signed-off-by: Andrey Ryabinin
---
mm/memcontrol.c | 13 -
1 file changed, 8 insertions(+), 5 deletions(-)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 052b11501b8e..98cf7b56eaaa 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6260,6 +6260,7 @@ static stru
ask+0xbd/0x130 [i40e]
[] i40e_service_task+0x62f/0x1360 [i40e]
[] process_one_work+0x182/0x440
[] worker_thread+0x126/0x3c0
[] kthread+0xd1/0xe0
[] ret_from_fork_nospec_begin+0x21/0x21
https://pmc.acronis.com/browse/VSTOR-20675
Signed-off-by: Andrey Ryabinin
---
drivers/infiniband/hw/i4
440
[] worker_thread+0x126/0x3c0
[] kthread+0xd1/0xe0
[] ret_from_fork_nospec_begin+0x21/0x21
https://pmc.acronis.com/browse/VSTOR-20675
Signed-off-by: Andrey Ryabinin
---
drivers/infiniband/hw/i40iw/i40iw_main.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/driv
0iw]
[] i40e_client_subtask+0xbd/0x130 [i40e]
[] i40e_service_task+0x62f/0x1360 [i40e]
[] process_one_work+0x182/0x440
[] worker_thread+0x126/0x3c0
[] kthread+0xd1/0xe0
[] ret_from_fork_nospec_begin+0x21/0x21
https://pmc.acronis.com/browse/VSTOR-20675
Signed-off-by: Andrey Ryabinin
---
drivers/infiniband
x21
https://pmc.acronis.com/browse/VSTOR-20675
Signed-off-by: Andrey Ryabinin
---
arch/x86/include/asm/dma-mapping.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/x86/include/asm/dma-mapping.h
b/arch/x86/include/asm/dma-mapping.h
index c313ddbaa109..3dc09005e934 100
sched_clock() (which is rdtsc() on x86) gives us more precise result
than jiffies.
https://pmc.acronis.com/browse/VSTOR-19040
Signed-off-by: Andrey Ryabinin
---
mm/page_alloc.c | 14 --
1 file changed, 8 insertions(+), 6 deletions(-)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
Acked-by: Johannes Weiner
Cc: Michal Hocko
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
(cherry picked from commit 3337767850b490eec5ca822f871241c981664737)
Signed-off-by: Andrey Ryabinin
---
mm/vmscan.c | 32 ++--
1 file changed, 14 insertions(+), 18
162453bfbdf4c0f58cb3058aad9ad8cda1044cda)
Signed-off-by: Andrey Ryabinin
---
mm/workingset.c | 56 -
1 file changed, 28 insertions(+), 28 deletions(-)
diff --git a/mm/workingset.c b/mm/workingset.c
index 150223b6b161..22b66359d92d 100644
--- a/mm
from commit 0a6b76dd23fa08c5fd7b68acdb55018a37afd4aa)
Signed-off-by: Andrey Ryabinin
---
include/linux/memcontrol.h | 10 ++
mm/memcontrol.c| 2 +-
mm/workingset.c| 10 +++---
3 files changed, 18 insertions(+), 4 deletions(-)
diff --git a/include/linux
-19037
(cherry picked from commit 689c94f03ae251181725fe853b4ffc870f05c7fe)
Signed-off-by: Andrey Ryabinin
---
mm/workingset.c | 10 ++
1 file changed, 6 insertions(+), 4 deletions(-)
diff --git a/mm/workingset.c b/mm/workingset.c
index 8da2955587fa..150223b6b161 100644
--- a/mm/workingset.c
-by: Andrey Ryabinin
---
mm/vmscan.c | 9 ++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index f64c8775ac9e..2ba4a11a67f7 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2043,12 +2043,15 @@ static unsigned long shrink_list(enum lru_list lru
Torvalds
https://pmc.acronis.com/browse/VSTOR-19037
(cherry picked from commit 612e44939c3c77245ac80843c0c7876c8cf97282)
Signed-off-by: Andrey Ryabinin
---
mm/workingset.c | 30 +-
1 file changed, 29 insertions(+), 1 deletion(-)
diff --git a/mm/workingset.c b/mm
rry picked from commit 23047a96d7cfcfca1a6d026ecaec526ea4803e9e)
Signed-off-by: Andrey Ryabinin
---
include/linux/memcontrol.h | 53 +++---
include/linux/mmzone.h | 14 +++---
mm/memcontrol.c| 32 +
mm/vmscan.c| 71 ++-
-19037
(cherry picked from commit 689c94f03ae251181725fe853b4ffc870f05c7fe)
Signed-off-by: Andrey Ryabinin
---
mm/workingset.c | 10 ++
1 file changed, 6 insertions(+), 4 deletions(-)
diff --git a/mm/workingset.c b/mm/workingset.c
index 8da2955587fa..150223b6b161 100644
--- a/mm/workingset.c
-by: Andrey Ryabinin
---
fs/proc/task_mmu.c | 3 ++-
include/linux/radix-tree.h | 15 ++-
mm/memcontrol.c| 3 ++-
mm/mincore.c | 3 ++-
mm/shmem.c | 12
mm/workingset.c| 4 ++--
6 files changed, 30 insertions
Instead of iterating from all cgroups, reclaim cgroup that triggered
allocation first. Don't reclaim cgroup if it causes refaults.
https://pmc.acronis.com/browse/VSTOR-19037
Signed-off-by: Andrey Ryabinin
---
include/linux/memcontrol.h | 5 ++
include/linux/mmzone.h | 1 +
mm/vmscan.c
rry picked from commit 23047a96d7cfcfca1a6d026ecaec526ea4803e9e)
Signed-off-by: Andrey Ryabinin
---
include/linux/memcontrol.h | 53 +++---
include/linux/mmzone.h | 14 +++---
mm/memcontrol.c| 32 +
mm/vmscan.c| 56 +++--
Torvalds
https://pmc.acronis.com/browse/VSTOR-19037
(cherry picked from commit 612e44939c3c77245ac80843c0c7876c8cf97282)
Signed-off-by: Andrey Ryabinin
---
mm/workingset.c | 30 +-
1 file changed, 29 insertions(+), 1 deletion(-)
diff --git a/mm/workingset.c b/mm
from commit 0a6b76dd23fa08c5fd7b68acdb55018a37afd4aa)
Signed-off-by: Andrey Ryabinin
---
include/linux/memcontrol.h | 10 ++
mm/memcontrol.c| 2 +-
mm/workingset.c| 10 +++---
3 files changed, 18 insertions(+), 4 deletions(-)
diff --git a/include/linux
This mostly copy of page cache implementation. Record refault
information when page swapped out, read it on swap in.
https://pmc.acronis.com/browse/VSTOR-19037
Signed-off-by: Andrey Ryabinin
---
drivers/staging/zcache/zcache-main.c | 2 +-
include/linux/swap.h | 10 +--
mm
162453bfbdf4c0f58cb3058aad9ad8cda1044cda)
Signed-off-by: Andrey Ryabinin
---
mm/workingset.c | 56 -
1 file changed, 28 insertions(+), 28 deletions(-)
diff --git a/mm/workingset.c b/mm/workingset.c
index 150223b6b161..22b66359d92d 100644
--- a/mm
com/browse/VSTOR-20383
https://pmc.acronis.com/browse/VSTOR-20349
Signed-off-by: Andrey Ryabinin
---
arch/x86/kernel/pci-dma.c | 2 +-
include/linux/gfp.h | 2 ++
mm/page_alloc.c | 3 ++-
3 files changed, 5 insertions(+), 2 deletions(-)
diff --git a/arch/x86/kernel/pci-dma.c b/a
owse/PSBM-91566
>
> Signed-off-by: Konstantin Khorenko
> ---
Acked-by: Andrey Ryabinin
___
Devel mailing list
Devel@openvz.org
https://lists.openvz.org/mailman/listinfo/devel
ed-off-by: Michael S. Tsirkin
https://jira.sw.ru/browse/PSBM-91532
(cherry picked from commit 89da619bc18d79bca5304724c11d4ba3b67ce2c6)
Signed-off-by: Andrey Ryabinin
---
drivers/virtio/virtio_balloon.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/virtio/virtio_balloo
On 1/24/19 6:44 PM, Andrey Ryabinin wrote:
> From: Peter Zijlstra
>
> Waiman managed to trigger a PMI while in a emulate_vsyscall() fault,
> the PMI in turn managed to trigger a fault while obtaining a stack
> trace. This triggered the sig_on_uaccess_error recursive fault log
This is RK-worthy, please consider.
On 1/24/19 6:44 PM, Andrey Ryabinin wrote:
> From: Peter Zijlstra
>
> Waiman managed to trigger a PMI while in a emulate_vsyscall() fault,
> the PMI in turn managed to trigger a fault while obtaining a stack
> trace. This triggered the sig_o
Signed-off-by: Peter Zijlstra
Link:
http://lkml.kernel.org/r/20140110200603.gj7...@laptop.programming.kicks-ass.net
Signed-off-by: Ingo Molnar
(cherry picked from commit c026b3591e4f2a4993df773183704bb31634e0bd)
Signed-off-by: Andrey Ryabinin
---
arch/x86/mm/fault.c | 18 ++
1 fi
than size of inactive lru.
Signed-off-by: Vladimir Davydov
Acked-by: Johannes Weiner
Cc: Michal Hocko
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
https://jira.sw.ru/browse/PSBM-83199
(cherry picked from commit cdcbb72ebfec52373e57092eccaadd5a6e261c3e)
Signed-off-by: Andrey
er
Signed-off-by: Joonsoo Kim
Signed-off-by: Pekka Enberg
https://jira.sw.ru/browse/PSBM-83199
[ Setting SLUB_CPU_PARTIAL=n save us about a 1G in dvd-store test ]
(cherry picked from commit 345c905d13a4ec9f774b6b4bc038fe4aef26cced)
Signed-off-by: Andrey Ryabinin
---
init/Kconfig | 11 +
footprint.
Link: http://lkml.kernel.org/r/20161117214701.29000-1-han...@cmpxchg.org
Signed-off-by: Johannes Weiner
Cc: Rik van Riel
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
Fixes: 59dc76b0d4df ("mm: vmscan: reduce size of inactive file list")
Signed-off-by: Andr
096 bytes if
slub order is zero. But with slub order 3 and 1025-byte objects
we waste only 993-bytes per 32768 bytes => 124 bytes per 4096)
According to dvd-store test pros of this change is outweigh the cons.
https://jira.sw.ru/browse/PSBM-83199
Signed-off-by: Andrey Ryabinin
---
mm/
er
Signed-off-by: Joonsoo Kim
Signed-off-by: Pekka Enberg
https://jira.sw.ru/browse/PSBM-83199
[ Setting SLUB_CPU_PARTIAL=n save us about a 1G in dvd-store test ]
(cherry picked from commit 345c905d13a4ec9f774b6b4bc038fe4aef26cced)
Signed-off-by: Andrey Ryabinin
---
init/Kconfig | 11 +
footprint.
Link: http://lkml.kernel.org/r/20161117214701.29000-1-han...@cmpxchg.org
Signed-off-by: Johannes Weiner
Cc: Rik van Riel
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
Fixes: 59dc76b0d4df ("mm: vmscan: reduce size of inactive file list")
Signed-off-by: Andr
096 bytes if
slub order is zero. But with slub order 3 and 1025-byte objects
we waste only 993-bytes per 32768 bytes => 124 bytes per 4096)
According to dvd-store test pros of this change is outweigh the cons.
https://jira.sw.ru/browse/PSBM-83199
Signed-off-by: Andrey Ryabinin
---
mm/
than size of inactive lru.
Signed-off-by: Vladimir Davydov
Acked-by: Johannes Weiner
Cc: Michal Hocko
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
https://jira.sw.ru/browse/PSBM-83199
(cherry picked from commit cdcbb72ebfec52373e57092eccaadd5a6e261c3e)
Signed-off-by: Andrey
single_open() allocates seq_operations struct, which leaked because
some 'proc_stat_ops', proc_classify_ops, proc_classify6_ops use seq_release
'release' callback instead of single_release. Fix this.
Signed-off-by: Andrey Ryabinin
---
net/ipv4/netfilter/ip_vzprivnet.c | 4 ++--
net/ipv6
Add 'lat' field to the mm_page_alloc tracepoint. It shows allocation
latency in microseconds (0.01 second).
Signed-off-by: Andrey Ryabinin
---
Changes since v2:
- Use the 'unsigned int' type - the same as the result of jiffies_to_usec,
instead of u64
include/trace/events/kmem.h
Add 'lat' field to the mm_page_alloc tracepoint. It shows allocation
latency in microseconds (0.01 second).
Signed-off-by: Andrey Ryabinin
---
Changes since v1:
- s/%ld/%lld
include/trace/events/kmem.h | 10 ++
mm/page_alloc.c | 3 ++-
2 files changed, 8 insertions
Add 'lat' field to the mm_page_alloc tracepoint. It shows allocation
latency in microseconds (0.01 second).
Signed-off-by: Andrey Ryabinin
---
include/trace/events/kmem.h | 10 ++
mm/page_alloc.c | 3 ++-
2 files changed, 8 insertions(+), 5 deletions(-)
diff --git
uarantee proper load ordering.
>
> https://pmc.acronis.com/browse/VSTOR-18694
>
> Found-by: Andrey Ryabinin
> Signed-off-by: Konstantin Khorenko
Acked-by: Andrey Ryabinin
___
Devel mailing list
Devel@openvz.org
https://lists.openvz.org/mailman/listinfo/devel
:[] []
mem_cgroup_swappiness+0xc/0x30
Call Trace:
[] balance_pgdat+0x4ca/0x820
[] kswapd+0x173/0x440
[] kthread+0xd1/0xe0
[] ret_from_fork_nospec_begin+0x21/0x21
https://pmc.acronis.com/browse/VSTOR-18694
Signed-off-by: Andrey Ryabinin
---
mm/memcontrol.c | 4 +---
1 file changed, 1 insertion
Hocko
Acked-by: Johannes Weiner
Cc: Tejun Heo
Signed-off-by: Hugh Dickins
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
https://jira.sw.ru/browse/PSBM-89726
(cherry picked from commit 688eb988d15af55c1d1b70b1ca9f6ce58f277c20)
Signed-off-by: Andrey Ryabinin
---
Documentation/cgrou
enabled and have anything to reclaim.
https://jira.sw.ru/browse/HCI-168
Fixes: fe87c15bf3ac ("mm/vmscan: shrink tcache, tswap upfront everything else")
Signed-off-by: Andrey Ryabinin
---
mm/internal.h | 28 ++--
mm/tcache.c | 4 ++--
mm/tswap.c| 4 ++-
We don't want to evict page cache or anon to swap while
there are a lot of reclaimable pages in tcache/tswap.
Reclaim them first, and only after that go to traditional reclaim
https://jira.sw.ru/browse/PSBM-89403
Signed-off-by: Andrey Ryabinin
---
mm/internal.h | 32
We don't want to evict page cache or anon to swap while
there are a lot of reclaimable pages in tcache/tswap.
Reclaim them first, and only after that go to traditional reclaim
https://jira.sw.ru/browse/PSBM-89403
Signed-off-by: Andrey Ryabinin
---
mm/internal.h | 32
If tcache_lru_del() deletes last page from node we don't need to
insert reclaim node into tree.
https://jira.sw.ru/browse/PSBM-89403
Signed-off-by: Andrey Ryabinin
---
mm/tcache.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/mm/tcache.c b/mm/tcache.c
index 9fc7cbf1c40b
tcache_lru_isolate() doesn't rebalance reclaim tree if isolation
failed. If the first pool in tree is empty, without rebalancing it
may stay first indefinitely long preventing reclaim.
https://jira.sw.ru/browse/PSBM-89403
Signed-off-by: Andrey Ryabinin
---
mm/tcache.c | 5 +
1 file changed
We don't want to evict page cache or anon to swap while
there are a lot of reclaimable pages in tcache/tswap.
Reclaim them first, and only after that go to traditional reclaim
https://jira.sw.ru/browse/PSBM-89403
Signed-off-by: Andrey Ryabinin
---
mm/internal.h | 14 ++
mm/tcache.c
())
^
is_xen_pv_domain
Signed-off-by: Andrey Ryabinin
---
arch/x86/mm/kaiser.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/x86/mm/kaiser.c b/arch/x86/mm/kaiser.c
index 5996f64b9b75..c4f6044eb57b 100644
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -620,7 +620,7 @@ static
of CONFIG_KAISER,
so use it instead.
Before:
cat /sys/devices/system/cpu/vulnerabilities/meltdown
Vulnerable
After:
cat /sys/devices/system/cpu/vulnerabilities/meltdown
Mitigation: PTI
Signed-off-by: Andrey Ryabinin
---
arch/x86/kernel/cpu/bugs.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion
. Fix up the offset.
https://jira.sw.ru/browse/PSBM-88323
Signed-off-by: Andrey Ryabinin
---
include/linux/vmstat.h | 7 +++
kernel/bc/io_acct.c| 3 ++-
mm/vmstat.c| 6 --
3 files changed, 9 insertions(+), 7 deletions(-)
diff --git a/include/linux/vmstat.h b/include/linux
/browse/PSBM-88323
Signed-off-by: Andrey Ryabinin
---
include/linux/memcontrol.h | 7 +++
kernel/bc/vm_pages.c | 9 -
mm/memcontrol.c| 50 ++
3 files changed, 65 insertions(+), 1 deletion(-)
diff --git a/include/linux
ner
Link:
http://lkml.kernel.org/r/20150415113105.gt5...@twins.programming.kicks-ass.net
Signed-off-by: Thomas Gleixner
https://jira.sw.ru/browse/PSBM-88818
(cherry picked from commit 5de2755c8c8b3a6b8414870e2c284914a2b42e4d)
Signed-off-by: Andrey Ryabinin
---
kernel/hrtimer.c | 12 +---
1
On 09/19/2018 12:13 PM, Kirill Tkhai wrote:
> On 17.09.2018 14:45, Andrey Ryabinin wrote:
>> spin_unlock(_mddevs_lock);
>> }
>> +if (name && dev)
>> +/*
>> + * Creating /dev/md
his approach to create *all* arrays,
which will allow the transition to only using the new-way.
Signed-off-by: NeilBrown
Acted-by: Coly Li
Signed-off-by: Shaohua Li
https://pmc.acronis.com/browse/VSTOR-14964
(cherry picked from commit 039b7225e6e98783a7a7e79c52b29c437f29967d)
Sign
jira.sw.ru/browse/PSBM-88577
(cherry picked from commit c28a45cb9503cbfbebfdb60491f06ae84b49)
Signed-off-by: Andrey Ryabinin
---
net/xfrm/xfrm_policy.c | 10 +-
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index dd
On 09/12/2018 12:59 AM, Alexey Kuznetsov wrote:
> Hello!
>
> The support looks very simple. I think we should implement it at least
> for ixgbe used at our ssd-only high perf cluster p[4-9].perf.sw.ru
> This way we can estimate real advantages.
>
It looks simple of sfc driver, but adding
contiguous, use kvmalloc_node() to allocate it.
https://jira.sw.ru/browse/HCI-132
https://pmc.acronis.com/browse/VSTOR-14758
Signed-off-by: Andrey Ryabinin
---
mm/mempool.c | 14 --
1 file changed, 8 insertions(+), 6 deletions(-)
diff --git a/mm/mempool.c b/mm/mempool.c
index
/browse/VSTOR-14758
https://jira.sw.ru/browse/HCI-132
(cherry picked from commit ce91f6ee5b3bbbad8caff61b1c46d845c8db19bf)
Signed-off-by: Andrey Ryabinin
---
mm/util.c | 6 --
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/mm/util.c b/mm/util.c
index b9afaef17dfd..5f27a98cbb2d
From: Edward Cree
Generally the check should be very cheap, as the sk_buff_head is in cache.
Signed-off-by: Edward Cree
Signed-off-by: David S. Miller
https://jira.sw.ru/browse/PSBM-88420
(cherry picked from commit b9f463d6c9849230043123a6335d59ac7fea4d5a)
Signed-off-by: Andrey Ryabinin
onverted code, but the change makes
it more robust.
Link: http://lkml.kernel.org/r/20170405074700.29871-3-vba...@suse.cz
Signed-off-by: Vlastimil Babka
Suggested-by: Michal Hocko
Acked-by: Michal Hocko
Acked-by: Hillf Danton
Cc: Mel Gorman
Cc: Johannes Weiner
Cc: Andrey Ryabinin
Cc: Boris Brezillon
Cc
301 - 400 of 1007 matches
Mail list logo