amdzen2/core.json and amdzen/core.json have the occasional trailing
comma. Since that goes against the JSON standard, lets remove it.
Signed-off-by: Henry Burns
---
tools/perf/pmu-events/arch/x86/amdzen1/core.json | 2 +-
tools/perf/pmu-events/arch/x86/amdzen2/core.json | 2 +-
2 files changed
, and found one other instance in
amdzen1. I'll send an updated patch now.
>
> - Arnaldo
>
> > Signed-off-by: Henry Burns
> > ---
> > tools/perf/pmu-events/arch/x86/amdzen2/core.json | 2 +-
> > 1 file changed, 1 insertion(+), 1 deletion(-)
> >
> > dif
amdzen2/core.json had a trailing comma on the x_ret_fus_brnch_inst
event. Since that goes against the JSON standard, lets remove it.
Signed-off-by: Henry Burns
---
tools/perf/pmu-events/arch/x86/amdzen2/core.json | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/perf/pmu
On Thu, Aug 22, 2019 at 7:23 PM Andrew Morton wrote:
>
> On Tue, 20 Aug 2019 11:59:39 +0900 Sergey Senozhatsky
> wrote:
>
> > On (08/09/19 11:17), Henry Burns wrote:
> > > In zs_destroy_pool() we call flush_work(&pool->free_work). However, we
> >
kqueue.
Signed-off-by: Henry Burns
---
Changelog since v1:
- Fixed a bug where migration could still queue work after we have
waited for it to drain. (added z3fold_pool->destroying in the
process)
mm/z3fold.c | 89 +
1 file chan
I've just CC'd a personal email here so that I can respond to any
replies after today.
On Fri, Aug 9, 2019 at 9:46 AM Henry Burns wrote:
>
> In z3fold_destroy_pool() we call destroy_workqueue(&pool->compact_wq).
> However, we have no guarantee that migration isn'
quot;zsmalloc: page migration support")
Signed-off-by: Henry Burns
---
Changelog since v1:
- Changed the class level isolated count to a pool level isolated count
(of zspages). Also added a pool level flag for when destruction
starts and a memory barrier to ensure this flag has
.
Fixes: 48b4800a1c6a ("zsmalloc: page migration support")
Signed-off-by: Henry Burns
---
Changelog since v1:
- Moved the comment from putback_zspage_deferred() to
zs_page_putback().
mm/zsmalloc.c | 19 +++
1 file changed, 15 insertions(+), 4 deletions(-)
diff
kqueue.
Signed-off-by: Henry Burns
---
mm/z3fold.c | 51 +++
1 file changed, 51 insertions(+)
diff --git a/mm/z3fold.c b/mm/z3fold.c
index 78447cecfffa..e136d97ce56e 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -40,6 +40,7 @@
#include
#inc
By the way, I will lose access to this email in 3 days, so I've cc'd a
personal email.
On Mon, Aug 5, 2019 at 6:38 PM Minchan Kim wrote:
> On Mon, Aug 05, 2019 at 10:34:41AM -0700, Henry Burns wrote:
> > On Sun, Aug 4, 2019 at 9:28 PM Minchan Kim wrote:
> > > On Thu
On Sun, Aug 4, 2019 at 9:28 PM Minchan Kim wrote:
>
> Hi Henry,
>
> On Thu, Aug 01, 2019 at 06:53:32PM -0700, Henry Burns wrote:
> > In zs_destroy_pool() we call flush_work(&pool->free_work). However, we
> > have no guarantee that migration isn't happenin
.
Signed-off-by: Henry Burns
---
mm/zsmalloc.c | 30 --
1 file changed, 20 insertions(+), 10 deletions(-)
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 1cda3fe0c2d9..efa660a87787 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -1901,6 +1901,22 @@ static void
) fails for fully-free
zspages). This means it is sufficient to track a "# isolated zspages"
count by class, and have the destroy logic ensure all such pages have
drained before proceeding. Keeping that state under the class
spinlock keeps the logic straightforward.
Signed-off-by: Henr
means that there can be allocated pages referencing a freed inode,
causing any thread in compaction to be able to trip over the bad
pointer in PageMovable().
Fixes: 1f862989b04a ("mm/z3fold.c: support page migration")
Signed-off-by: Henry Burns
> Reviewed-by: Shakeel Butt
> Revie
se_z3fold_page(zhdr, ...)
queue_work_on(pool->release_wq, &pool->work) *BOOM*
So compact_wq needs to be destroyed before release_wq.
Fixes: 5d03a6613957 ("mm/z3fold.c: use kref to prevent page free/compact race")
Signed-off-by: Henry Burns
> Reviewed-by: Shakeel But
se_z3fold_page(zhdr, ...)
queue_work_on(pool->release_wq, &pool->work) *BOOM*
So compact_wq needs to be destroyed before release_wq.
Fixes: 5d03a6613957 ("mm/z3fold.c: use kref to prevent page free/compact race")
Signed-off-by: Henry Burns
Cc:
---
mm/z3fold.c | 9 ++
means that there can be allocated pages referencing a freed inode,
causing any thread in compaction to be able to trip over the bad
pointer in PageMovable().
Fixes: 1f862989b04a ("mm/z3fold.c: support page migration")
Signed-off-by: Henry Burns
Cc:
---
mm/z3fold.c | 5 -
1 file
empty
Additionally it is possible that zhdr->work has been placed in a
workqueue. In this case we shouldn't migrate the page, as zhdr->work
references zhdr as opposed to new_zhdr.
Fixes: bba4c5f96ce4 ("mm/z3fold.c: support page migration")
Signed-off-by: Henry Burns
---
C
Sorry Vitaly, I had the wrong impression from your email that
INIT_LIST_HEAD() was being ensured directly in migrate and got
confused. (I thought you were saying it happened through the call to
do_compact_page() queued).
That being said, I don't see where in migrate new_zhdr->buddy is being
checke
age() already ensures
>> that these lists are empty.
>>
>> Additionally it is possible that zhdr->work has been placed in a
>> workqueue. In this case we shouldn't migrate the page, as zhdr->work
>> references zhdr as opposed to new_zhdr.
>>
>> F
empty.
Additionally it is possible that zhdr->work has been placed in a
workqueue. In this case we shouldn't migrate the page, as zhdr->work
references zhdr as opposed to new_zhdr.
Fixes: bba4c5f96ce4 ("mm/z3fold.c: support page migration")
Signed-off-by: Henry Burns
---
mm/z
kernel allocation.
Signed-off-by: Henry Burns
---
mm/z3fold.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/mm/z3fold.c b/mm/z3fold.c
index e78f95284d7c..cb567ddf051c 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -193,7 +193,8 @@ static inline struct z3fold_buddy_slots
> > a_ops->migrate_page(oldpage, newpage)
> > z3fold_page_migrate(oldpage, newpage)
> > trylock_page(oldpage)
> >
> >
> > Signed-off-by: Henry Burns
>
> Reviewed-by: Shakeel Butt
>
> Please add the Fixes tag as well.
Fixes: 1f862989b0
age)
z3fold_page_migrate(oldpage, newpage)
trylock_page(oldpage)
Signed-off-by: Henry Burns
---
mm/z3fold.c | 6 --
1 file changed, 6 deletions(-)
diff --git a/mm/z3fold.c b/mm/z3fold.c
index 985732c8b025..9fe9330ab8ae 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -1335,16 +1335,11 @@ static
> > On Tue, Jul 2, 2019 at 12:45 AM Vitaly Wool wrote:
> > >
> > > Hi Henry,
> > >
> > > On Mon, Jul 1, 2019 at 8:31 PM Henry Burns wrote:
> > > >
> > > > Running z3fold stress testing with address sanitiz
On Tue, Jul 2, 2019 at 10:54 PM Vitaly Wool wrote:
>
> On Wed, Jul 3, 2019 at 12:24 AM Andrew Morton
> wrote:
> >
> > On Tue, 2 Jul 2019 15:17:47 -0700 Henry Burns wrote:
> >
> > > > > > > + if (can_sleep
On Tue, Jul 2, 2019 at 2:19 PM Andrew Morton wrote:
>
> On Mon, 1 Jul 2019 18:16:30 -0700 Henry Burns wrote:
>
> > Cc: Vitaly Wool , Vitaly Vul
>
> Are these the same person?
I Think it's the same person, but i wasn't sure which email to include
because one was
i
Following zsmalloc.c's example we call trylock_page() and unlock_page().
Also make z3fold_page_migrate() assert that newpage is passed in locked,
as per the documentation.
Link: http://lkml.kernel.org/r/20190702005122.41036-1-henrybu...@google.com
Signed-off-by: Henry Burns
Suggested-by: V
On Tue, Jul 2, 2019 at 12:45 AM Vitaly Wool wrote:
>
> Hi Henry,
>
> On Mon, Jul 1, 2019 at 8:31 PM Henry Burns wrote:
> >
> > Running z3fold stress testing with address sanitization
> > showed zhdr->slots was being used after it was freed.
> &
On Mon, Jul 1, 2019 at 6:00 PM Shakeel Butt wrote:
>
> On Mon, Jul 1, 2019 at 5:51 PM Henry Burns wrote:
> >
> > __SetPageMovable() expects it's page to be locked, but z3fold.c doesn't
> > lock the page. Following zsmalloc.c's example we call trylock_p
__SetPageMovable() expects it's page to be locked, but z3fold.c doesn't
lock the page. Following zsmalloc.c's example we call trylock_page() and
unlock_page(). Also makes z3fold_page_migrate() assert that newpage is
passed in locked, as documentation.
Signed-off-by: Henry Burn
__SetPageMovable() expects it's page to be locked, but z3fold.c doesn't
lock the page. Following zsmalloc.c's example we call trylock_page() and
unlock_page(). Also makes z3fold_page_migrate() assert that newpage is
passed in locked, as documentation.
Signed-off-by: Henry Burns
-
done.
Fixes: 7c2b8baa61fe ("mm/z3fold.c: add structure for buddy handles")
Signed-off-by: Henry Burns
---
mm/z3fold.c | 33 ++---
1 file changed, 14 insertions(+), 19 deletions(-)
diff --git a/mm/z3fold.c b/mm/z3fold.c
index f7993ff778df..e174d1549734 100644
---
33 matches
Mail list logo
