On Thu, Oct 15, 2015 at 5:53 PM, Minchan Kim <minc...@kernel.org> wrote:
> On Thu, Oct 15, 2015 at 11:27:15AM +0200, Vlastimil Babka wrote:
>> On 10/15/2015 11:09 AM, Hui Zhu wrote:
>> >I got that add function interfaces is really not a good idea.
>> >So I add
Thanks. I will post a new version later.
Best,
Hui
On Tue, Oct 13, 2015 at 4:00 PM, Sergey Senozhatsky
wrote:
> On (10/13/15 14:31), Hui Zhu wrote:
>> Signed-off-by: Hui Zhu
>
> s/unless/useless/
>
> other than that
>
> Reviewed-by: Sergey Senozhatsky
>
Signed-off-by: Hui Zhu
Reviewed-by: Sergey Senozhatsky
---
mm/zsmalloc.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index f135b1b..c7338f0 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -1428,8 +1428,6 @@ static void obj_free(struct zs_pool *pool
Signed-off-by: Hui Zhu
---
mm/zsmalloc.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index f135b1b..c7338f0 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -1428,8 +1428,6 @@ static void obj_free(struct zs_pool *pool, struct
size_class *class
Signed-off-by: Hui Zhu <zhu...@xiaomi.com>
---
mm/zsmalloc.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index f135b1b..c7338f0 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -1428,8 +1428,6 @@ static void obj_free(struct zs_pool *pool,
Signed-off-by: Hui Zhu <zhu...@xiaomi.com>
Reviewed-by: Sergey Senozhatsky <sergey.senozhat...@gmail.com>
---
mm/zsmalloc.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index f135b1b..c7338f0 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -14
Thanks. I will post a new version later.
Best,
Hui
On Tue, Oct 13, 2015 at 4:00 PM, Sergey Senozhatsky
<sergey.senozhatsky.w...@gmail.com> wrote:
> On (10/13/15 14:31), Hui Zhu wrote:
>> Signed-off-by: Hui Zhu <zhu...@xiaomi.com>
>
> s/unless/useless/
>
> other
e reason why there is no problem until now is huge-class page is
born with ZS_FULL so it couldn't be migrated.
Therefore, it shouldn't be real bug in practice.
However, we need this patch for future-work "VM-aware zsmalloced
page migration" to reduce external fragmentation.
Signed-off-by: Hui
On Tue, Oct 6, 2015 at 9:54 PM, Minchan Kim wrote:
> Hello,
>
> On Mon, Oct 05, 2015 at 04:23:01PM +0800, Hui Zhu wrote:
>> In function obj_malloc:
>> if (!class->huge)
>> /* record handle in the header of allocated chunk */
>>
On Tue, Oct 6, 2015 at 9:54 PM, Minchan Kim <minc...@kernel.org> wrote:
> Hello,
>
> On Mon, Oct 05, 2015 at 04:23:01PM +0800, Hui Zhu wrote:
>> In function obj_malloc:
>> if (!class->huge)
>> /* record handle in the header of allocated ch
e reason why there is no problem until now is huge-class page is
born with ZS_FULL so it couldn't be migrated.
Therefore, it shouldn't be real bug in practice.
However, we need this patch for future-work "VM-aware zsmalloced
page migration" to reduce external fragmentation.
Signed-off-by: Hui
page_private(page) as value but not pointer
in obj_to_head.
Signed-off-by: Hui Zhu
---
mm/zsmalloc.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index f135b1b..e881d4f 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -824,7 +824,7 @@ static u
page_private(page) as value but not pointer
in obj_to_head.
Signed-off-by: Hui Zhu <zhu...@xiaomi.com>
---
mm/zsmalloc.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index f135b1b..e881d4f 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.
Signed-off-by: Hui Zhu
---
mm/zsmalloc.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index f135b1b..f62f2fb 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -38,6 +38,7 @@
* page->lru: links together first pages of various zspa
Signed-off-by: Hui Zhu <zhu...@xiaomi.com>
---
mm/zsmalloc.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index f135b1b..f62f2fb 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -38,6 +38,7 @@
* page->lru: links together first pages of variou
Signed-off-by: Hui Zhu
---
mm/zsmalloc.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index f135b1b..1f66d5b 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -38,6 +38,7 @@
* page->lru: links together first pages of various zspa
Signed-off-by: Hui Zhu <zhu...@xiaomi.com>
---
mm/zsmalloc.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index f135b1b..1f66d5b 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -38,6 +38,7 @@
* page->lru: links together first pages of variou
*
Call for Topics and Sponsors
Workshop on Open Source Development Tools 2015
Beijing, China
Sep. 12, 2015 (TBD)
HelloGCC Work Group (www.hellogcc.org)
*
*
Call for Topics and Sponsors
Workshop on Open Source Development Tools 2015
Beijing, China
Sep. 12, 2015 (TBD)
HelloGCC Work Group (www.hellogcc.org)
*
On Wed, May 6, 2015 at 2:28 PM, Joonsoo Kim wrote:
> On Tue, May 05, 2015 at 11:22:59AM +0800, Hui Zhu wrote:
>> Change pfn_present to pfn_valid_within according to the review of Laura.
>>
>> I got a issue:
>> [ 214.294917] Unable to handle kernel NULL pointer derefer
dx - page_idx);
if (!is_migrate_isolate_page(buddy)) {
But the begin addr of this part of CMA memory is very close to a part of
memory that is reserved in the boot time (not in buddy system).
So add a check before access it.
Suggested-by: Laura Abbott
Suggested-by: Joonsoo Kim
Signed-off-by: Hui Zhu
---
mm/page_is
On Wed, May 6, 2015 at 2:28 PM, Joonsoo Kim iamjoonsoo@lge.com wrote:
On Tue, May 05, 2015 at 11:22:59AM +0800, Hui Zhu wrote:
Change pfn_present to pfn_valid_within according to the review of Laura.
I got a issue:
[ 214.294917] Unable to handle kernel NULL pointer dereference at virtual
Abbott labb...@redhat.com
Suggested-by: Joonsoo Kim iamjoonsoo@lge.com
Signed-off-by: Hui Zhu zhu...@xiaomi.com
---
mm/page_isolation.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 755a42c..4a5624c 100644
--- a/mm
On Wed, May 6, 2015 at 5:29 AM, Andrew Morton wrote:
> On Tue, 5 May 2015 11:22:59 +0800 Hui Zhu wrote:
>
>> Change pfn_present to pfn_valid_within according to the review of Laura.
>>
>> I got a issue:
>> [ 214.294917] Unable to handle kernel NULL pointer dere
On Wed, May 6, 2015 at 5:29 AM, Andrew Morton a...@linux-foundation.org wrote:
On Tue, 5 May 2015 11:22:59 +0800 Hui Zhu zhu...@xiaomi.com wrote:
Change pfn_present to pfn_valid_within according to the review of Laura.
I got a issue:
[ 214.294917] Unable to handle kernel NULL pointer
emory is very close to a part of
memory that is reserved in the boot time (not in buddy system).
So add a check before access it.
Signed-off-by: Hui Zhu
---
mm/page_isolation.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 755
On Tue, May 5, 2015 at 2:34 AM, Laura Abbott wrote:
> On 05/04/2015 02:41 AM, Hui Zhu wrote:
>>
>> I got a issue:
>> [ 214.294917] Unable to handle kernel NULL pointer dereference at virtual
>> address 082a
>> [ 214.303013] pgd = cc97
>>
(not in buddy system).
So add a check before access it.
Signed-off-by: Hui Zhu
---
mm/page_isolation.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 755a42c..434730b 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@
memory is very close to a part of
memory that is reserved in the boot time (not in buddy system).
So add a check before access it.
Signed-off-by: Hui Zhu zhu...@xiaomi.com
---
mm/page_isolation.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/mm/page_isolation.c b/mm
On Tue, May 5, 2015 at 2:34 AM, Laura Abbott labb...@redhat.com wrote:
On 05/04/2015 02:41 AM, Hui Zhu wrote:
I got a issue:
[ 214.294917] Unable to handle kernel NULL pointer dereference at virtual
address 082a
[ 214.303013] pgd = cc97
[ 214.305721] [082a] *pgd=
);
if (!is_migrate_isolate_page(buddy)) {
But the begin addr of this part of CMA memory is very close to a part of
memory that is reserved in the boot time (not in buddy system).
So add a check before access it.
Signed-off-by: Hui Zhu zhu...@xiaomi.com
---
mm/page_isolation.c | 3 ++-
1 file changed, 2
On Mon, Jan 19, 2015 at 2:55 PM, Minchan Kim wrote:
> Hello,
>
> On Sun, Jan 18, 2015 at 04:32:59PM +0800, Hui Zhu wrote:
>> From: Hui Zhu
>>
>> The original of this patch [1] is part of Joonsoo's CMA patch series.
>> I made a patch [2] to fix the issue of
On Sun, Jan 18, 2015 at 6:19 PM, Vlastimil Babka wrote:
> On 18.1.2015 10:17, Hui Zhu wrote:
>>
>> From: Hui Zhu
>>
>> To test the patch [1], I use KGTP and a script [2] to show
>> NR_FREE_CMA_PAGES
>> and gross of cma_nr_free. The values are always not s
From: Hui Zhu
To test the patch [1], I use KGTP and a script [2] to show NR_FREE_CMA_PAGES
and gross of cma_nr_free. The values are always not same.
I check the code of pages alloc and free and found that race conditions
on getting migratetype in buffered_rmqueue.
Then I add move the code
From: Hui Zhu
The original of this patch [1] is part of Joonsoo's CMA patch series.
I made a patch [2] to fix the issue of this patch. Joonsoo reminded me
that this issue affect current kernel too. So made a new one for upstream.
Current code treat free cma pages as non-free if not ALLOC_CMA
On Sun, Jan 18, 2015 at 6:19 PM, Vlastimil Babka vba...@suse.cz wrote:
On 18.1.2015 10:17, Hui Zhu wrote:
From: Hui Zhu zhu...@xiaomi.com
To test the patch [1], I use KGTP and a script [2] to show
NR_FREE_CMA_PAGES
and gross of cma_nr_free. The values are always not same.
I check the code
On Mon, Jan 19, 2015 at 2:55 PM, Minchan Kim minc...@kernel.org wrote:
Hello,
On Sun, Jan 18, 2015 at 04:32:59PM +0800, Hui Zhu wrote:
From: Hui Zhu zhu...@xiaomi.com
The original of this patch [1] is part of Joonsoo's CMA patch series.
I made a patch [2] to fix the issue of this patch
From: Hui Zhu zhu...@xiaomi.com
The original of this patch [1] is part of Joonsoo's CMA patch series.
I made a patch [2] to fix the issue of this patch. Joonsoo reminded me
that this issue affect current kernel too. So made a new one for upstream.
Current code treat free cma pages as non-free
From: Hui Zhu zhu...@xiaomi.com
To test the patch [1], I use KGTP and a script [2] to show NR_FREE_CMA_PAGES
and gross of cma_nr_free. The values are always not same.
I check the code of pages alloc and free and found that race conditions
on getting migratetype in buffered_rmqueue.
Then I add
On Wed, Jan 7, 2015 at 4:45 PM, Vlastimil Babka wrote:
> On 12/30/2014 11:17 AM, Hui Zhu wrote:
>> The original of this patch [1] is used to fix the issue in Joonsoo's CMA
>> patch
>> "CMA: always treat free cma pages as non-free on watermark checking"
On Wed, Jan 7, 2015 at 4:45 PM, Vlastimil Babka vba...@suse.cz wrote:
On 12/30/2014 11:17 AM, Hui Zhu wrote:
The original of this patch [1] is used to fix the issue in Joonsoo's CMA
patch
CMA: always treat free cma pages as non-free on watermark checking [2].
Joonsoo reminded me
data_breakpoint.ko can insert successful but cannot catch any change of
the data in my part because kallsyms_lookup_name rerurn 0 each time.
So add code to check the return value of kallsyms_lookup_name.
Signed-off-by: Hui Zhu
---
samples/hw_breakpoint/data_breakpoint.c | 17
data_breakpoint.ko can insert successful but cannot catch any change of
the data in my part because kallsyms_lookup_name rerurn 0 each time.
So add code to check the return value of kallsyms_lookup_name.
Signed-off-by: Hui Zhu zhu...@xiaomi.com
---
samples/hw_breakpoint/data_breakpoint.c | 17
ed twice. This bug will make
__zone_watermark_ok return more false.
This patch add cma_free_area to struct free_area that just record the number
of CMA pages. And add it back in the order loop to handle the substruct
twice issue.
[1] https://lkml.org/lkml/2014/12/25/43
[2] https://lkml.org/lkml/2014
On Tue, Dec 30, 2014 at 12:48 PM, Joonsoo Kim wrote:
> On Thu, Dec 25, 2014 at 05:43:26PM +0800, Hui Zhu wrote:
>> In Joonsoo's CMA patch "CMA: always treat free cma pages as non-free on
>> watermark checking" [1], it changes __zone_watermark_ok to substruct CMA
>&g
On Tue, Dec 30, 2014 at 12:48 PM, Joonsoo Kim iamjoonsoo@lge.com wrote:
On Thu, Dec 25, 2014 at 05:43:26PM +0800, Hui Zhu wrote:
In Joonsoo's CMA patch CMA: always treat free cma pages as non-free on
watermark checking [1], it changes __zone_watermark_ok to substruct CMA
pages number from
__zone_watermark_ok return more false.
This patch add cma_free_area to struct free_area that just record the number
of CMA pages. And add it back in the order loop to handle the substruct
twice issue.
[1] https://lkml.org/lkml/2014/12/25/43
[2] https://lkml.org/lkml/2014/5/28/110
Signed-off-by: Hui Zhu zhu
to
handle the issues.
And I merged cma_alloc_counter from [2] to cma_alloc work better.
This patchset is based on aa39477b5692611b91ac9455ae588738852b3f60 and [1].
[1] https://lkml.org/lkml/2014/5/28/64
[2] https://lkml.org/lkml/2014/10/15/623
Hui Zhu (3):
CMA: Fix the bug that CMA's page number
__rmqueue doesn't call __rmqueue_cma when
cma_alloc works.
[1] https://lkml.org/lkml/2014/10/24/26
Signed-off-by: Hui Zhu
---
include/linux/cma.h | 2 ++
mm/cma.c| 6 ++
mm/page_alloc.c | 8 +++-
3 files changed, 15 insertions(+), 1 deletion(-)
diff --git a/include/linux
t
twice issue.
[1] https://lkml.org/lkml/2014/5/28/110
Signed-off-by: Hui Zhu
Signed-off-by: Weixing Liu
---
include/linux/mmzone.h | 3 +++
mm/page_alloc.c| 29 -
2 files changed, 31 insertions(+), 1 deletion(-)
diff --git a/include/linux/mmzone.h b/include/l
thers. This device allocated a lot of
MIGRATE_UNMOVABLE memory affect the behavior of this zone memory allocation.
This patch change __rmqueue to let nr_try_movable record all the memory
allocation of normal memory.
[1] https://lkml.org/lkml/2014/5/28/64
Signed-off-by: Hui Zhu
Signed-off-by: W
allocated a lot of
MIGRATE_UNMOVABLE memory affect the behavior of this zone memory allocation.
This patch change __rmqueue to let nr_try_movable record all the memory
allocation of normal memory.
[1] https://lkml.org/lkml/2014/5/28/64
Signed-off-by: Hui Zhu zhu...@xiaomi.com
Signed-off-by: Weixing Liu
/28/110
Signed-off-by: Hui Zhu zhu...@xiaomi.com
Signed-off-by: Weixing Liu liuweix...@xiaomi.com
---
include/linux/mmzone.h | 3 +++
mm/page_alloc.c| 29 -
2 files changed, 31 insertions(+), 1 deletion(-)
diff --git a/include/linux/mmzone.h b/include/linux
__rmqueue doesn't call __rmqueue_cma when
cma_alloc works.
[1] https://lkml.org/lkml/2014/10/24/26
Signed-off-by: Hui Zhu zhu...@xiaomi.com
---
include/linux/cma.h | 2 ++
mm/cma.c| 6 ++
mm/page_alloc.c | 8 +++-
3 files changed, 15 insertions(+), 1 deletion(-)
diff --git
to
handle the issues.
And I merged cma_alloc_counter from [2] to cma_alloc work better.
This patchset is based on aa39477b5692611b91ac9455ae588738852b3f60 and [1].
[1] https://lkml.org/lkml/2014/5/28/64
[2] https://lkml.org/lkml/2014/10/15/623
Hui Zhu (3):
CMA: Fix the bug that CMA's page number
On Fri, Oct 24, 2014 at 1:28 PM, Joonsoo Kim wrote:
> On Thu, Oct 16, 2014 at 11:35:51AM +0800, Hui Zhu wrote:
>> If page alloc function __rmqueue try to get pages from MIGRATE_MOVABLE and
>> conditions (cma_alloc_counter, cma_aggressive_free_min, cma_alloc_counter)
>&g
On Fri, Oct 24, 2014 at 1:28 PM, Joonsoo Kim iamjoonsoo@lge.com wrote:
On Thu, Oct 16, 2014 at 11:35:51AM +0800, Hui Zhu wrote:
If page alloc function __rmqueue try to get pages from MIGRATE_MOVABLE and
conditions (cma_alloc_counter, cma_aggressive_free_min, cma_alloc_counter)
allow
On Tue, Nov 4, 2014 at 3:53 PM, Minchan Kim wrote:
> Hello,
>
> On Wed, Oct 29, 2014 at 03:43:33PM +0100, Vlastimil Babka wrote:
>> On 10/16/2014 10:55 AM, Laura Abbott wrote:
>> >On 10/15/2014 8:35 PM, Hui Zhu wrote:
>> >
>> >It's good to see another pr
On Tue, Nov 4, 2014 at 3:53 PM, Minchan Kim minc...@kernel.org wrote:
Hello,
On Wed, Oct 29, 2014 at 03:43:33PM +0100, Vlastimil Babka wrote:
On 10/16/2014 10:55 AM, Laura Abbott wrote:
On 10/15/2014 8:35 PM, Hui Zhu wrote:
It's good to see another proposal to fix CMA utilization. Do you
On Wed, Oct 29, 2014 at 10:43 PM, Vlastimil Babka wrote:
> On 10/16/2014 10:55 AM, Laura Abbott wrote:
>>
>> On 10/15/2014 8:35 PM, Hui Zhu wrote:
>>
>> It's good to see another proposal to fix CMA utilization. Do you have
>> any data about the success rate o
On Mon, Nov 3, 2014 at 4:22 PM, Heesub Shin wrote:
> Hello,
>
>
> On 10/31/2014 04:25 PM, Joonsoo Kim wrote:
>>
>> In free_pcppages_bulk(), we use cached migratetype of freepage
>> to determine type of buddy list where freepage will be added.
>> This information is stored when freepage is added
On Mon, Nov 3, 2014 at 4:22 PM, Heesub Shin heesub.s...@samsung.com wrote:
Hello,
On 10/31/2014 04:25 PM, Joonsoo Kim wrote:
In free_pcppages_bulk(), we use cached migratetype of freepage
to determine type of buddy list where freepage will be added.
This information is stored when freepage
On Wed, Oct 29, 2014 at 10:43 PM, Vlastimil Babka vba...@suse.cz wrote:
On 10/16/2014 10:55 AM, Laura Abbott wrote:
On 10/15/2014 8:35 PM, Hui Zhu wrote:
It's good to see another proposal to fix CMA utilization. Do you have
any data about the success rate of CMA contiguous allocation after
On Fri, Oct 24, 2014 at 1:25 PM, Joonsoo Kim wrote:
> On Thu, Oct 16, 2014 at 11:35:47AM +0800, Hui Zhu wrote:
>> In fallbacks of page_alloc.c, MIGRATE_CMA is the fallback of
>> MIGRATE_MOVABLE.
>> MIGRATE_MOVABLE will use MIGRATE_CMA when it doesn't have a page in
>> o
On Fri, Oct 24, 2014 at 1:25 PM, Joonsoo Kim iamjoonsoo@lge.com wrote:
On Thu, Oct 16, 2014 at 11:35:47AM +0800, Hui Zhu wrote:
In fallbacks of page_alloc.c, MIGRATE_CMA is the fallback of
MIGRATE_MOVABLE.
MIGRATE_MOVABLE will use MIGRATE_CMA when it doesn't have a page in
order
On Wed, May 28, 2014 at 3:04 PM, Joonsoo Kim wrote:
> CMA is introduced to provide physically contiguous pages at runtime.
> For this purpose, it reserves memory at boot time. Although it reserve
> memory, this reserved memory can be used for movable memory allocation
> request. This usecase is
On Wed, May 28, 2014 at 3:04 PM, Joonsoo Kim iamjoonsoo@lge.com wrote:
CMA is introduced to provide physically contiguous pages at runtime.
For this purpose, it reserves memory at boot time. Although it reserve
memory, this reserved memory can be used for movable memory allocation
request.
guous area, increase the value of
cma_alloc_counter. CMA_AGGRESSIVE will not work in page alloc code.
After reserve custom contiguous area function return, decreases the value of
cma_alloc_counter.
Signed-off-by: Hui Zhu
---
include/linux/cma.h | 7 +++
kernel/sysctl.c | 27 +++
Update this patch according to the comments from Rafael.
Function shrink_all_memory_for_cma try to free `nr_to_reclaim' of memory.
CMA aggressive shrink function will call this functon to free `nr_to_reclaim' of
memory.
Signed-off-by: Hui Zhu
---
mm/vmscan.c | 58
Update this patch according to the comments from Rafael.
Function shrink_all_memory_for_cma try to free `nr_to_reclaim' of memory.
CMA aggressive shrink function will call this functon to free `nr_to_reclaim' of
memory.
Signed-off-by: Hui Zhu zhu...@xiaomi.com
---
mm/vmscan.c | 58
. CMA_AGGRESSIVE will not work in page alloc code.
After reserve custom contiguous area function return, decreases the value of
cma_alloc_counter.
Signed-off-by: Hui Zhu zhu...@xiaomi.com
---
include/linux/cma.h | 7 +++
kernel/sysctl.c | 27 +++
mm/cma.c
In fallbacks of page_alloc.c, MIGRATE_CMA is the fallback of
MIGRATE_MOVABLE.
MIGRATE_MOVABLE will use MIGRATE_CMA when it doesn't have a page in
order that Linux kernel want.
If a system that has a lot of user space program is running, for
instance, an Android board, most of memory is in
is hibernate_preallocate_memory.
if not, the caller is CMA alloc function.
Signed-off-by: Hui Zhu
---
include/linux/swap.h| 3 ++-
kernel/power/snapshot.c | 2 +-
mm/vmscan.c | 19 +--
3 files changed, 16 insertions(+), 8 deletions(-)
diff --git a/include/linux/swap.h b/include
If page alloc function __rmqueue try to get pages from MIGRATE_MOVABLE and
conditions (cma_alloc_counter, cma_aggressive_free_min, cma_alloc_counter)
allow, MIGRATE_CMA will be allocated as MIGRATE_MOVABLE first.
Signed-off-by: Hui Zhu
---
mm/page_alloc.c | 42
work in page alloc code.
After reserve custom contiguous area function return, decreases the value of
cma_alloc_counter.
Signed-off-by: Hui Zhu
---
include/linux/cma.h | 7 +++
kernel/sysctl.c | 27 +++
mm/cma.c| 54
switch (sysctl vm.cma-aggressive-switch)
will be opened.
When system boot, this value will set to sysctl "vm.cma-aggressive-free-min".
If this value is true, sysctl "vm.cma-aggressive-shrink-switch" will be set to
true when Linux boot.
Signed-off-by: Hui Zhu
reserve custom contiguous area function return, decreases the value of
cma_alloc_counter.
Signed-off-by: Hui Zhu zhu...@xiaomi.com
---
include/linux/cma.h | 7 +++
kernel/sysctl.c | 27 +++
mm/cma.c| 54
switch (sysctl vm.cma-aggressive-switch)
will be opened.
When system boot, this value will set to sysctl vm.cma-aggressive-free-min.
If this value is true, sysctl vm.cma-aggressive-shrink-switch will be set to
true when Linux boot.
Signed-off-by: Hui Zhu zhu...@xiaomi.com
---
mm/Kconfig | 43
is hibernate_preallocate_memory.
if not, the caller is CMA alloc function.
Signed-off-by: Hui Zhu zhu...@xiaomi.com
---
include/linux/swap.h| 3 ++-
kernel/power/snapshot.c | 2 +-
mm/vmscan.c | 19 +--
3 files changed, 16 insertions(+), 8 deletions(-)
diff --git a/include/linux
If page alloc function __rmqueue try to get pages from MIGRATE_MOVABLE and
conditions (cma_alloc_counter, cma_aggressive_free_min, cma_alloc_counter)
allow, MIGRATE_CMA will be allocated as MIGRATE_MOVABLE first.
Signed-off-by: Hui Zhu zhu...@xiaomi.com
---
mm/page_alloc.c | 42
In fallbacks of page_alloc.c, MIGRATE_CMA is the fallback of
MIGRATE_MOVABLE.
MIGRATE_MOVABLE will use MIGRATE_CMA when it doesn't have a page in
order that Linux kernel want.
If a system that has a lot of user space program is running, for
instance, an Android board, most of memory is in
-off-by: Hui Zhu
---
drivers/staging/android/lowmemorykiller.c | 4
1 file changed, 4 insertions(+)
diff --git a/drivers/staging/android/lowmemorykiller.c
b/drivers/staging/android/lowmemorykiller.c
index b545d3d..ca1ffac 100644
--- a/drivers/staging/android/lowmemorykiller.c
+++ b/drivers
-off-by: Hui Zhu zhu...@xiaomi.com
---
drivers/staging/android/lowmemorykiller.c | 4
1 file changed, 4 insertions(+)
diff --git a/drivers/staging/android/lowmemorykiller.c
b/drivers/staging/android/lowmemorykiller.c
index b545d3d..ca1ffac 100644
--- a/drivers/staging/android/lowmemorykiller.c
Ping.
Thanks,
Hui
On Mon, May 5, 2014 at 8:00 PM, Hui Zhu wrote:
> cat gdb.base/interrupt.c
> #include
> #include
> #include
> #include
>
> #ifdef SIGNALS
> #include
>
> static void
> sigint_handler (int signo)
> {
> }
> #endif
>
> int
&g
Ping.
Thanks,
Hui
On Mon, May 5, 2014 at 8:00 PM, Hui Zhu h...@codesourcery.com wrote:
cat gdb.base/interrupt.c
#include errno.h
#include stdio.h
#include unistd.h
#include stdlib.h
#ifdef SIGNALS
#include signal.h
static void
sigint_handler (int signo)
{
}
#endif
int
main
KGTP (http://teawater.github.io/kgtp/) is a comprehensive dynamic tracer for
analysing Linux kernel and application (including Android) problems on
production systems in real time.
I think people use KGTP first trouble is to configure complex.
So the main change of this version is add a script
KGTP (http://teawater.github.io/kgtp/) is a comprehensive dynamic tracer for
analysing Linux kernel and application (including Android) problems on
production systems in real time.
I think people use KGTP first trouble is to configure complex.
So the main change of this version is add a script
On 05/01/14 00:28, Hui Zhu wrote:
On Wed, Apr 30, 2014 at 9:35 PM, Mark Kettenis wrote:
>>> Date: Tue, 29 Apr 2014 22:10:15 -0700
>>> From: "H. Peter Anvin"
>>>
>>> On 04/29/2014 10:08 PM, Andrew Pinski wrote:
>>>>
>>>
xtension in arch/x86/asm/syscall.h:syscall_get_error(),
> we could work around to problem in GDB by checking "orig_ax" to see if
> we're continuing an interrupted system call and sign extend the error
> code in the real "eax" register if we are.
I will update patch in
http
register if we are.
I will update patch in
https://sourceware.org/ml/gdb-patches/2014-04/msg00429.html
according to this comments.
Thanks,
Hui
Signed-off-by: Hui Zhu h...@codesourcery.com
---
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -452,6 +452,23 @@ static int putreg
On 05/01/14 00:28, Hui Zhu wrote:
On Wed, Apr 30, 2014 at 9:35 PM, Mark Kettenis mark.kette...@xs4all.nl wrote:
Date: Tue, 29 Apr 2014 22:10:15 -0700
From: H. Peter Anvin h...@zytor.com
On 04/29/2014 10:08 PM, Andrew Pinski wrote:
restoring the values is hard since even the ptrace
On Tue, Apr 22, 2014 at 12:33 AM, H. Peter Anvin wrote:
> On 04/21/2014 09:19 AM, Hui Zhu wrote:
>> }
>> Now ax is in 32 bits now, need sign-extend to 64 bits. But
>> current_thread_info()->status TS_COMPAT is cleared when GDB call "call
>> func1()".
>
On Tue, Apr 22, 2014 at 12:33 AM, H. Peter Anvin h...@zytor.com wrote:
On 04/21/2014 09:19 AM, Hui Zhu wrote:
}
Now ax is in 32 bits now, need sign-extend to 64 bits. But
current_thread_info()-status TS_COMPAT is cleared when GDB call call
func1().
Linux kernel don't know this is a 32 bits
*
Call for Topics and Sponsors
Workshop on Open Source Development Tools 2014 (i.e. HelloGCC Workshop)
Beijing, China
Sep. 13rd, 2014 (TBD)
HelloGCC Work Group (www.hellogcc.org)
*
Call for Topics and Sponsors
Workshop on Open Source Development Tools 2014 (i.e. HelloGCC Workshop)
Beijing, China
Sep. 13rd, 2014 (TBD)
HelloGCC Work Group (www.hellogcc.org)
a errno in ERESTARTSYS.
To fix this issue, I tried to add a local variable to "do_signal" but
it is not works. The stack is cleared before GDB "continue".
so I make a patch that add "test_thread_flag (TIF_IA32)" to syscall_get_error.
Signed-off-by: H
but
it is not works. The stack is cleared before GDB continue.
so I make a patch that add test_thread_flag (TIF_IA32) to syscall_get_error.
Signed-off-by: Hui Zhu h...@codesourcery.com
---
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -48,7 +48,8 @@ static inline long
t the data of module list, this script is
slower than getmod.
Signed-off-by: Hui Zhu
---
--- /dev/null
+++ b/scripts/getmod.py
@@ -0,0 +1,151 @@
+#!/usr/bin/python
+
+# This script is used by GDB to load the symbols from Linux kernel modules
+# Copyright(C) KGTP team (https://kgtp.googlecode.com),
tory.
-hDisplay this information.
Signed-off-by: Hui Zhu
---
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -16,6 +16,7 @@ help:
@echo ' vm - misc vm tools'
@echo ' x86_energy_perf_policy - Intel energy policy tool'
@echo ' tmon - thermal monitoring and t
Display this information.
Signed-off-by: Hui Zhu teawa...@gmail.com
---
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -16,6 +16,7 @@ help:
@echo ' vm - misc vm tools'
@echo ' x86_energy_perf_policy - Intel energy policy tool'
@echo ' tmon - thermal monitoring
101 - 200 of 225 matches
Mail list logo