[PATCH] selftest/mm: Make hugetlb_reparenting_test tolerant to async reparenting

-v2 # exit=1 # 0 # SUMMARY: PASS=10 SKIP=0 FAIL=1 Signed-off-by: Li Wang Cc: Waiman Long Cc: Anshuman Khandual Cc: Dev Jain Cc: Kirill A. Shuemov Cc: Shuah Khan --- .../selftests/mm/hugetlb_reparenting_test.sh | 96 --- 1 file changed, 41 insertions(+), 55 deletions

[PATCH] selftest/mm: va_high_addr_switch: add ppc64 support check

ain: 0x - FAILED # mmap(ADDR_SWITCH_HINT - PAGE_SIZE, 2*HUGETLB_SIZE, MAP_HUGETLB): 0x - FAILED # mmap(ADDR_SWITCH_HINT , 2*HUGETLB_SIZE, MAP_FIXED | MAP_HUGETLB): 0x - FAILED Signed-off-by: Li Wang --- .../selftests/mm/va_high_addr_switch

[V2][PATCH] vt: keyboard, fix uninitialized variables warning

zed in this function [-Wmaybe-uninitialized] kfree(kbs); ^~~~~~ Signed-off-by: Li Wang --- drivers/tty/vt/keyboard.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c index 7763862..62f1ecb 100644 --- a/drivers/tty/vt/keyboard.c +

[PATCH] vt: keyboard, fix uninitialized variables warning

uninitialized in this function [-Wmaybe-uninitialized] kfree(kbs); ^~~~~~ Signed-off-by: Li Wang --- drivers/tty/vt/keyboard.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c index 7763862..3e73d55 100644 --- a/d

[PATCH] vhost: reduce stack usage in log_used

Fix the warning: [-Werror=-Wframe-larger-than=] drivers/vhost/vhost.c: In function log_used: drivers/vhost/vhost.c:1906:1: warning: the frame size of 1040 bytes is larger than 1024 bytes Signed-off-by: Li Wang --- drivers/vhost/vhost.c | 2 +- drivers/vhost/vhost.h | 1 + 2 files changed, 2

[PATCH] vhost: reduce stack usage in log_used

Fix the warning: [-Werror=-Wframe-larger-than=] drivers/vhost/vhost.c: In function log_used: drivers/vhost/vhost.c:1906:1: warning: the frame size of 1040 bytes is larger than 1024 bytes Signed-off-by: Li Wang --- drivers/vhost/vhost.c | 14 ++ 1 file changed, 10 insertions(+), 4

[5.3.0-rc4 Bug] WARNING: CPU: 17 PID: 25085 at lib/list_debug.c:47 __list_del_entry_valid+0x4e/0x90

m_region_hash dm_log dm_mod -- Regards, Li Wang

Re: ltp/read_all_sys (read_all -d /sys -q -r 10) cause system panic with kernel-4.18.0-rc1

ptsas libata nvme_fc scsi_transport_sas nvme_fabrics mptscsih nvme_core crc32c_intel mptbase scsi_transport_fc dca i2c_algo_bit dm_mirror dm_region_hash dm_log dm_mod [ 8162.621090] CR2: 00b8 On Tue, Jun 19, 2018 at 6:41 PM, Li Wang wrote: > Hi, > > I'm hitting t

Re: [PATCH v2] zswap: re-check zswap_is_full after do zswap_shrink

On 30 May 2018 at 20:53, Dan Streetman wrote: > On Wed, May 30, 2018 at 6:39 AM, Li Wang wrote: >> The '/sys/../zswap/stored_pages:' keep raising in zswap test with >> "zswap.max_pool_percent=0" parameter. But theoretically, it should >> not compress

ltp/read_all_sys (read_all -d /sys -q -r 10) cause system panic with kernel-4.18.0-rc1

ded: ltp_insmod01] [ 5916.043814] CR2: 00b8 [ 5916.047513] BUG: unable to handle kernel NULL pointer dereference at 00b8 [ 5916.047537] ---[ end trace 1dddacfb06305174 ]--- -- Regards, Li Wang

[PATCH v2] zswap: re-check zswap_is_full after do zswap_shrink

tored_pages will keep changing. To solve the issue, this patch adds zswap_is_full() check again after zswap_shrink() to make sure it's now under the max_pool_percent, and not to compress/store if reach its limitaion. Signed-off-by: Li Wang Cc: Seth Jennings Cc: Dan Streetman Cc: Huan

[PATCH RFC] zswap: reject to compress/store page if zswap_max_pool_percent is 0

size by zswap_shrink(). If the pool size has been shrinked a little success, zswap will do compress/store pages again. Then we get fails on that as above. Signed-off-by: Li Wang Cc: Seth Jennings Cc: Dan Streetman Cc: Huang Ying Cc: Yu Zhao --- mm/zswap.c | 5 + 1 file changed,

linux/drivers/cpuidle: cpuidle_enter_state() issue

x14 -8<--- Any response will be appreciated! -- Regards, Li Wang Email: wangli.a...@gmail.com

Re: [PATCH] s390/mm: return -ENOMEM in arch_get_unmapped_area[_topdown]

On Thu, Oct 26, 2017 at 6:16 PM, Martin Schwidefsky wrote: > On Thu, 26 Oct 2017 17:47:39 +0800 > Li Wang wrote: > >> On Thu, Oct 26, 2017 at 5:26 PM, Martin Schwidefsky >> wrote: >> > On Thu, 26 Oct 2017 15:36:10 +0800 >> > Li Wang wrote: >> >

Re: [PATCH] s390/mm: return -ENOMEM in arch_get_unmapped_area[_topdown]

On Thu, Oct 26, 2017 at 5:26 PM, Martin Schwidefsky wrote: > On Thu, 26 Oct 2017 15:36:10 +0800 > Li Wang wrote: > >> That would be very hard to get -ENOMEM returned in crst_table_upgrade() >> because the condition(addr + len <= TASK_SIZE) makes all 'end&#x

[PATCH] s390/mm: return -ENOMEM in arch_get_unmapped_area[_topdown]

table_upgrade) Signed-off-by: Li Wang --- arch/s390/mm/mmap.c| 6 ++ arch/s390/mm/pgalloc.c | 3 +-- 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index 5bea139..8ddb13a 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s39

[BUG] Unable to handle kernel paging request for unaligned access at address 0xc0000001c52c53df

cache: 64K L1i cache: 32K NUMA node0 CPU(s): 0-15 NUMA node1 CPU(s): -- Li Wang liw...@redhat.com

Re: [PATCH v2] vfs: fix put_compat_statfs64() does not handle errors

sorry, ping for comments~ On 15 November 2016 at 17:19, Li Wang wrote: > put_compat_statfs64() does NOT return -1 and setting errno to EOVERFLOW > when some variables(like: f_bsize) overflowed in the returned struct. > > The reason is that the ubuf->f_blocks is __u64 type,

[PATCH v2] vfs: fix put_compat_statfs64() does not handle errors

/a.out sizeof f_bsize = 4, f_bsize=0 Signed-off-by: Li Wang --- fs/compat.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/compat.c b/fs/compat.c index bd064a2..543b48c 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -253,9 +253,9 @@ static int put_compat_statfs(struct

Re: [PATCH] vfs: fix statfs64() does not handle errors

On Mon, Nov 07, 2016 at 11:03:11AM -0700, Andreas Dilger wrote: > On Nov 7, 2016, at 3:21 AM, Li Wang wrote: > > > > statfs64() does NOT return -1 and setting errno to EOVERFLOW when some > > variables(like: f_bsize) overflowed in the returned struct. > > >

[PATCH] vfs: fix statfs64() does not handle errors

return 0; } $ gcc -m32 statfs64_test.c $ ./a.out sizeof f_bsize = 4, f_bsize=0 Signed-off-by: Li Wang --- Notes: This is my first patch to kernel fs part, I'm not sure if this one useful, but just want someone have a look. thanks~ fs/statfs.c | 17 +++

mtd: put flash block erasing into wait queue, if has any thread in queue

flash erasing maybe block writing operation. make erasing operation sleep, when the other thread is in wait queue. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordo

[PATCH] mtd: put flash block erasing into wait queue, if has any thread in queue

b0] sys_ioctl+0x94/0x108 [dbc6df40] [c0010d04] ret_from_syscall+0x0/0x4 --- Exception: c01 at 0xff586a0 LR = 0xff58608 = So, if there is any thread in wait queue, puts erasing operation into queue. It makes writing operation have chance to run. Signed-off-by: Li Wang --- drivers/mtd/chips

Re: [PATCH 2/3] Add shrink_pagecache_parent

Hi, On 01/03/2014 07:55 AM, Andrew Morton wrote: On Mon, 30 Dec 2013 21:45:17 +0800 Li Wang wrote: Analogous to shrink_dcache_parent except that it collects inodes. It is not very appropriate to be put in dcache.c, but d_walk can only be invoked from here. Please cc Dave Chinner on future

Re: [PATCH 0/3] Fadvise: Directory level page cache cleaning support

Do we really need clean dcache/icache at the current stage? That will introduce more code work, so far, iput() will put those unreferenced inodes into superblock lru list. To free the inodes inside a specific directory, it seems we do not have a handy API to use, and need modify iput() to recogniz

[PATCH 0/3] Fadvise: Directory level page cache cleaning support

e enough to buffer all the four directories, so 'cp -r 3 4' will result in some entries of '1' to be evicted (due to LRU). When re-accessing '1', some entries need be reloaded from disk, which is time-consuming. In this case, cleaning '2' before 'cp -r 3 4'

[PATCH 3/3] Fadvise: Add the ability for directory level page cache cleaning

Signed-off-by: Li Wang Signed-off-by: Yunchuan Wen --- mm/fadvise.c |4 1 file changed, 4 insertions(+) diff --git a/mm/fadvise.c b/mm/fadvise.c index 3bcfd81..644d32d 100644 --- a/mm/fadvise.c +++ b/mm/fadvise.c @@ -113,6 +113,10 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t

[PATCH 1/3] VFS: Add the declaration of shrink_pagecache_parent

Signed-off-by: Li Wang Signed-off-by: Yunchuan Wen --- include/linux/dcache.h |1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/dcache.h b/include/linux/dcache.h index bf72e9a..6262171 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -249,6 +249,7

[PATCH 2/3] Add shrink_pagecache_parent

Analogous to shrink_dcache_parent except that it collects inodes. It is not very appropriate to be put in dcache.c, but d_walk can only be invoked from here. Signed-off-by: Li Wang Signed-off-by: Yunchuan Wen --- fs/dcache.c | 36 1 file changed, 36

Re: [PATCH 0/3] Ceph fscache: Fix kernel panic due to a race

that the page does not be cached in fscache, then it decides to write this page into fscache, during this process in cachefiles_write_page(), it found that object->store_limit_l < 4096 (page->index << 12), it causes panic. Does it make sense? Cheers, Li Wang On 2013/12/27 6:51,

[PATCH 1/3] Ceph fscache: Add an interface to synchronize object store limit

From: Yunchuan Wen Add an interface to explicitly synchronize object->store_limit[_l] with inode->i_size Signed-off-by: Yunchuan Wen Signed-off-by: Min Chen Signed-off-by: Li Wang --- fs/ceph/cache.h | 10 ++ 1 file changed, 10 insertions(+) diff --git a/fs/ceph/cache.h b/f

[PATCH 2/3] Ceph fscache: Update object store limit after file writing

From: Yunchuan Wen Synchronize object->store_limit[_l] with new inode->i_size after file writing. Signed-off-by: Yunchuan Wen Signed-off-by: Min Chen Signed-off-by: Li Wang --- fs/ceph/file.c |3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/ceph/file.c b/fs/ceph/file.c

[PATCH 0/3] Ceph fscache: Fix kernel panic due to a race

From: Yunchuan Wen The following scripts could easily panic the kernel, #!/bin/bash mount -t ceph -o fsc MONADDR:/ cephfs rm -rf cephfs/foo dd if=/dev/zero of=cephfs/foo bs=8 count=512 echo 3 > /proc/sys/vm/drop_caches dd if=cephfs/foo of=/dev/null bs=8 count=1024 This is due to when writing a

[PATCH 3/3] Ceph fscache: Wait for completion of object initialization

, the initialization may have not completed, the code will reach the ASSERT in fscache_submit_exclusive_op() to cause kernel bug. Signed-off-by: Yunchuan Wen Signed-off-by: Min Chen Signed-off-by: Li Wang --- fs/ceph/cache.c |1 + 1 file changed, 1 insertion(+) diff --git a/fs/ceph/cache.c

[PATCH 1/2] ceph fscache: Introduce a routine for uncaching single no data page from fscache

Signed-off-by: Li Wang --- fs/ceph/cache.h | 13 + 1 file changed, 13 insertions(+) diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h index ba94940..da95f61 100644 --- a/fs/ceph/cache.h +++ b/fs/ceph/cache.h @@ -67,6 +67,14 @@ static inline int ceph_release_fscache_page(struct page

[PATCH 0/2] ceph fscache: uncaching single no data page when error

Currently, if one new page allocated into fscache in readpage(), however, with no data read into due to error encountered during reading from OSDs, the slot in fscache is not uncached. This patch fixes this. Li Wang (2): ceph: Introduce a routine for uncaching single no data page from

[PATCH 2/2] ceph fscache: Uncaching no data page from fscache in readpage()

Currently, if one new page allocated into fscache in readpage(), however, with no data read into due to error encountered during reading from OSDs, the slot in fscache is not uncached. This patch fixes this. Signed-off-by: Li Wang --- fs/ceph/addr.c |1 + 1 file changed, 1 insertion

Re: [PATCH 0/5] VFS: Directory level cache cleaning

think we may start with making 'fadvise' could handle directory level page cache cleaning. On 2013/12/18 6:05, Dave Chinner wrote: On Mon, Dec 16, 2013 at 07:00:04AM -0800, Li Wang wrote: Currently, Linux only support file system wide VFS cache (dentry cache and page cache) cleaning thr

Re: [PATCH 0/5] VFS: Directory level cache cleaning

This extension is just add-on extension. The original debugging capability is still there, and more flexible debugging is now allowed. On 2013/12/17 17:12, Li Zefan wrote: On 2013/12/17 15:23, Li Wang wrote: If we do wanna equip fadvise() with directory level page cache cleaning, this could be

Re: [PATCH 0/5] VFS: Directory level cache cleaning

y, the old semantics keep unchanged, and with add-on features to do finer granularity cache cleaning should be also desirable. On 2013/12/17 11:58, Matthew Wilcox wrote: On Tue, Dec 17, 2013 at 11:08:16AM +0800, Li Wang wrote: As far as we know, fadvise(DONTNEED) does not support metadata cache cl

Re: [PATCH 0/5] VFS: Directory level cache cleaning

directory? On 2013/12/17 1:45, Cong Wang wrote: On Mon, Dec 16, 2013 at 7:00 AM, Li Wang wrote: This patch extend the 'drop_caches' interface to support directory level cache cleaning and has a complete backward compatibility. '{1,2,3}' keeps the same semantics as befo

[PATCH 5/5] VFS: Extend drop_caches sysctl handler to allow directory level cache cleaning

Signed-off-by: Li Wang Signed-off-by: Yunchuan Wen --- fs/drop_caches.c | 45 + 1 file changed, 37 insertions(+), 8 deletions(-) diff --git a/fs/drop_caches.c b/fs/drop_caches.c index 9fd702f..ab31393 100644 --- a/fs/drop_caches.c +++ b/fs

[PATCH 3/5] VFS: Add the declaration of shrink_pagecache_parent

Signed-off-by: Li Wang Signed-off-by: Yunchuan Wen --- include/linux/dcache.h |1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 57e87e7..ce11098 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -247,6 +247,7

[PATCH 1/5] VFS: Convert drop_caches to accept string

Signed-off-by: Li Wang Signed-off-by: Yunchuan Wen --- kernel/sysctl.c |6 ++ 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 34a6047..2f2d8ab 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1255,12 +1255,10 @@ static struct

[PATCH 2/5] VFS: Convert sysctl_drop_caches to string

Signed-off-by: Li Wang Signed-off-by: Yunchuan Wen --- include/linux/mm.h |3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 1cedd00..5e3cc5b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -17,6 +17,7 @@ #include

[PATCH 4/5] VFS: Add shrink_pagecache_parent

Analogous to shrink_dcache_parent except that it collects inodes. It is not very appropriate to be put in dcache.c, but d_walk can only be invoked from here. Signed-off-by: Li Wang Signed-off-by: Yunchuan Wen --- fs/dcache.c | 35 +++ 1 file changed, 35

[PATCH 0/5] VFS: Directory level cache cleaning

#x27; to be evicted (due to LRU). When re-accessing '1', some entries need be reloaded from disk, which is time-consuming. In this case, cleaning '2' before accessing '3' enjoys a good speedup, a maximum 4.29X performance improvements is achieved. The advantage of di

[PATCH 1/2] ceph: Clean up if error occurred in finish_read()

Clean up if error occurred rather than going through normal process Signed-off-by: Li Wang Signed-off-by: Yunchuan Wen --- fs/ceph/addr.c |3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 1e561c0..97845b4 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph

[PATCH 0/2] ceph: Add clean up if invalid osd reply received

Signed-off-by: Li Wang Signed-off-by: Yunchuan Wen Li Wang (2): ceph: Clean up if error occurred in finish_read() ceph: Add necessary clean up if invalid reply received in handle_reply() fs/ceph/addr.c|3 +++ net/ceph/osd_client.c |7 +++ 2 files changed, 10

[PATCH 2/2] ceph: Add necessary clean up if invalid reply received in handle_reply()

Wake up possible waiters, invoke the call back if any, unregister the request Signed-off-by: Li Wang Signed-off-by: Yunchuan Wen --- net/ceph/osd_client.c |7 +++ 1 file changed, 7 insertions(+) diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 2b4b32a..a17eaae 100644

Re: [PATCH] Ceph: Avoid data inconsistency due to d-cache aliasing in readpage()

Hi Yan, zero_user_segment() has invoked flush_dcache_page() for us, we donnot wanna flush d-cache twice. Cheers, Li Wang On 11/13/2013 09:19 PM, Yan, Zheng wrote: On Wed, Nov 13, 2013 at 3:22 PM, Li Wang wrote: If the length of data to be read in readpage() is exactly PAGE_CACHE_SIZE

[PATCH] Ceph: Avoid data inconsistency due to d-cache aliasing in readpage()

If the length of data to be read in readpage() is exactly PAGE_CACHE_SIZE, the original code does not flush d-cache for data consistency after finishing reading. This patches fixes this. Signed-off-by: Li Wang --- fs/ceph/addr.c |8 ++-- 1 file changed, 6 insertions(+), 2 deletions

[PATCH 7/7] Cifs: Uncaching no-data page in readpage()

Currently, if one page allocated into fscache in readpage(), however, with no-data read, it is not uncached. This patch fixes this. Signed-off-by: Li Wang --- fs/cifs/file.c |4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 7f2

[PATCH 4/7] Ceph: Uncaching no-data page in readpage()

Currently, if one page allocated into fscache in readpage(), however, with no-data read, it is not uncached. This patch fixes this. Signed-off-by: Li Wang --- fs/ceph/addr.c |1 + 1 file changed, 1 insertion(+) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 6df8bd4..be5f4b6 100644

[PATCH 3/7] Ceph: Introduce routine for uncaching single no-data page

Introduce a routine for uncaching single no-data page, typically in readpage(). Signed-off-by: Li Wang --- fs/ceph/cache.h | 13 + 1 file changed, 13 insertions(+) diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h index ba94940..eb0ec76 100644 --- a/fs/ceph/cache.h +++ b/fs/ceph

[PATCH 6/7] Cifs: Implement uncaching single no-data page

Implement the routine for uncaching single no-data page, typically in readpage(). Signed-off-by: Li Wang --- fs/cifs/fscache.c |7 +++ 1 file changed, 7 insertions(+) diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c index 8d4b7bc..168f184 100644 --- a/fs/cifs/fscache.c +++ b/fs/cifs

[PATCH 1/7] Fscache: Introduce new API fscache_readpage_cancel()

Introduce a new API fscache_readpage_cancel() for uncaching one single no-data page from fscache. Signed-off-by: Li Wang --- include/linux/fscache.h | 11 +++ 1 file changed, 11 insertions(+) diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 115bb81..f1ed21f 100644

[PATCH 2/7] Fscache: Implement uncaching single no-data page

Similar to the routine for multiple pages except that it takes page * as input rather than list head *. Signed-off-by: Li Wang --- fs/fscache/page.c |8 1 file changed, 8 insertions(+) diff --git a/fs/fscache/page.c b/fs/fscache/page.c index 7f5c658..0c69f72 100644 --- a/fs

[PATCH 0/7] Cifs and Ceph: Uncache single no-data page in readpage()

Currently, the page allocated into fscache in readpage() for Cifs and Ceph does not be uncached if no data read due to io error. This patch fixes this. fscache_readpages_cancel() is for this kind of job but taking list read * as input, so a new routine take page * as input is introduced. Li

[PATCH 5/7] Cifs: Introduce routine for uncaching single no-data page

Introduce a routine for uncaching single no-data page, typically in readpage(). Signed-off-by: Li Wang --- fs/cifs/fscache.h | 13 + 1 file changed, 13 insertions(+) diff --git a/fs/cifs/fscache.h b/fs/cifs/fscache.h index 24794b6..c712f42 100644 --- a/fs/cifs/fscache.h +++ b/fs

[PATCH] Ceph: allocate non-zero page to fscache in readpage()

ceph_osdc_readpages() returns number of bytes read, currently, the code only allocate full-zero page into fscache, this patch fixes this. Signed-off-by: Li Wang --- fs/ceph/addr.c |2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index

Re: [RFC PATCH] ceph: Write through cache support based on fscache

will not bother too much. So our goal is to implement both, we plan to submit it as a blueprint at the incoming CDS. It would be great if you could help review and give comments on our codes during the development. Again, thanks very much. Cheers, Li Wang On 11/02/2013 12:51 AM, Milosz Tanski

[RFC PATCH] ceph: Write through cache support based on fscache

. Signed-off-by: Min Chen Signed-off-by: Li Wang Signed-off-by: Yunchuan Wen --- fs/ceph/addr.c | 10 +++--- fs/ceph/cache.c | 29 + fs/ceph/cache.h | 13 + 3 files changed, 49 insertions(+), 3 deletions(-) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c

[PATCH] ceph: Update the pages in fscache in writepages() path

Currently, the pages in fscache only are updated in writepage() path, add the process in writepages(). Signed-off-by: Min Chen Signed-off-by: Li Wang Signed-off-by: Yunchuan Wen --- fs/ceph/addr.c |8 +--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/fs/ceph/addr.c b

[PATCH v5] Ceph: Punch hole support for kernel client

This patch implements fallocate and punch hole support for Ceph kernel client. Signed-off-by: Li Wang Signed-off-by: Yunchuan Wen --- Against v3: Passed the fsx test from xfstests. Truncate rather than delete the first object. Thanks go to Sage and Zheng for the explanation. Silence the OSD

[PATCH v4] Ceph: Punch hole support for kernel client

This patch implements fallocate and punch hole support for Ceph kernel client. Signed-off-by: Li Wang Signed-off-by: Yunchuan Wen --- Passed the fsx test from xfstests. Truncate rather than delete the first object. Thanks go to Sage and Zheng for the explanation. --- fs/ceph/file.c

[PATCH] x86: remove redundant local_irq_enable() after cpuidle_idle_call()

: Fix idle consolidation fallout") In that defect, it does not use idle framework driver, just call amd_e400_idle(). That problem is that amd_e400_idle() does not enable irq. Signed-off-by: Li Wang --- arch/x86/kernel/process.c |2 -- 1 file changed, 2 deletions(-) diff --git a/arch/

[PATCH v3] Ceph: Punch hole support for kernel client

This patch implements fallocate and punch hole support for Ceph kernel client. Signed-off-by: Li Wang Signed-off-by: Yunchuan Wen --- Passed the fsx test from xfstests. --- fs/ceph/file.c| 191 + net/ceph/osd_client.c |8 ++- 2 files

[RFC] Ceph: Kernel client part of inline data support

h // leave MDS to merge mark cap and inode dirty to send (maybe part of) written data to MDS if (pos + len >= CEPH_INLINE_SIZE) let state = CEPH_INLINE_MIGRATION write the remaining data to OSD else do the normal write to OSD Signed-off-by: Li Wang Signed-off-by: Yunchu

[PATCH v2] Ceph: Punch hole support

This patch implements punch hole (fallocate) support for Ceph. Signed-off-by: Li Wang Signed-off-by: Yunchuan Wen --- fs/ceph/file.c| 313 + net/ceph/osd_client.c |8 +- 2 files changed, 319 insertions(+), 2 deletions(-) diff

[PATCH 1/2] Punch hole support against 3.8-rc3

This patch implements punch hole (fallocate) support against Linux kernel 3.8-rc3. Signed-off-by: Li Wang Signed-off-by: Yunchuan Wen --- fs/ceph/file.c| 248 + net/ceph/osd_client.c | 17 +++- 2 files changed, 260 insertions(+), 5

[PATCH 0/2] Kernel file system client support for punch hole

This patch implements punch hole (fallocate) support for Ceph kernel file system client. We prepared two patches based on different kernel versions, one against kernel 3.8-rc3, the other against the latest 3.10-rc5. It is because unfortunately, we failed to set up a workable Ceph system with the cl

[PATCH 2/2] Punch hole support against 3.10-rc5

This patch implements punch hole (fallocate) support against Linux kernel 3.10-rc5. Signed-off-by: Li Wang Signed-off-by: Yunchuan Wen --- fs/ceph/file.c| 245 + net/ceph/osd_client.c |8 +- 2 files changed, 251 insertions(+), 2

[PATCH v4] ext4: Avoid unnecessarily writing back dirty pages before hole punching

For hole punching, currently ext4 will synchronously write back the dirty pages fit into the hole, since the data on the disk responding to those pages are to be deleted, it is benefical to directly release those pages, no matter they are dirty or not, except the ordered case. Signed-off-by: Li

[PATCH] ext4: Avoid unnecessarily writing back dirty pages before hole punching

For hole punching, currently ext4 will synchronously write back the dirty pages fit into the hole, since the data on the disk responding to those pages are to be deleted, it is benefical to directly release those pages, no matter they are dirty or not, except the ordered case. Signed-off-by: Li

[PATCH v2] ext4: Avoid unnecessarily writing back dirty pages before hole punching

For hole punching, currently ext4 will synchronously write back the dirty pages fit into the hole, since the data on the disk responding to those pages are to be deleted, it is benefical to directly release those pages, no matter they are dirty or not, except the ordered case. Signed-off-by: Li

[PATCH] eCryptfs: Avoid unnecessary disk read and data decryption during writing

to our test on a machine with Intel Core 2 Duo processor, iozone 'write' operation on an existing file with write size being multiple of page size will enjoy a steady 3x speedup. Signed-off-by: Li Wang Signed-off-by: Yunchuan Wen Reviewed-by: Tyler Hicks --- fs/ecryptfs/mma

[RFC] VFS: File System Mount Wide O_DIRECT Support

For file system created on file-backed loop device, there will be two-levels of page cache present, which typically doubles the memory consumption. In many cases, it is beneficial to turn on the O_DIRECT option while performing the upper file system file IO, to bypass the upper page cache, which