* [PATCH] Ceph: Avoid data inconsistency due to d-cache aliasing in readpage()
@ 2013-11-13 7:22 Li Wang
2013-11-13 13:19 ` Yan, Zheng
0 siblings, 1 reply; 3+ messages in thread
From: Li Wang @ 2013-11-13 7:22 UTC (permalink / raw)
To: ceph-devel; +Cc: Sage Weil, linux-fsdevel, linux-kernel, Li Wang
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 <liwang@ubuntukylin.com>
---
fs/ceph/addr.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 6df8bd4..7b0000a 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -210,9 +210,13 @@ static int readpage_nounlock(struct file *filp, struct page *page)
if (err < 0) {
SetPageError(page);
goto out;
- } else if (err < PAGE_CACHE_SIZE) {
+ } else {
+ if (err < PAGE_CACHE_SIZE) {
/* zero fill remainder of page */
- zero_user_segment(page, err, PAGE_CACHE_SIZE);
+ zero_user_segment(page, err, PAGE_CACHE_SIZE);
+ } else {
+ flush_dcache_page(page);
+ }
}
SetPageUptodate(page);
--
1.7.9.5
^ permalink raw reply related [flat|nested] 3+ messages in thread
* Re: [PATCH] Ceph: Avoid data inconsistency due to d-cache aliasing in readpage()
2013-11-13 7:22 [PATCH] Ceph: Avoid data inconsistency due to d-cache aliasing in readpage() Li Wang
@ 2013-11-13 13:19 ` Yan, Zheng
2013-11-13 14:37 ` Li Wang
0 siblings, 1 reply; 3+ messages in thread
From: Yan, Zheng @ 2013-11-13 13:19 UTC (permalink / raw)
To: Li Wang; +Cc: ceph-devel, Sage Weil, linux-fsdevel, linux-kernel
On Wed, Nov 13, 2013 at 3:22 PM, Li Wang <liwang@ubuntukylin.com> wrote:
> 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 <liwang@ubuntukylin.com>
> ---
> fs/ceph/addr.c | 8 ++++++--
> 1 file changed, 6 insertions(+), 2 deletions(-)
>
> diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
> index 6df8bd4..7b0000a 100644
> --- a/fs/ceph/addr.c
> +++ b/fs/ceph/addr.c
> @@ -210,9 +210,13 @@ static int readpage_nounlock(struct file *filp, struct page *page)
> if (err < 0) {
> SetPageError(page);
> goto out;
> - } else if (err < PAGE_CACHE_SIZE) {
> + } else {
> + if (err < PAGE_CACHE_SIZE) {
> /* zero fill remainder of page */
> - zero_user_segment(page, err, PAGE_CACHE_SIZE);
> + zero_user_segment(page, err, PAGE_CACHE_SIZE);
> + } else {
> + flush_dcache_page(page);
> + }
this doesn't make sense for me. why not call flush_dcache_page unconditionally?
Regards
Yan, Zheng
> }
> SetPageUptodate(page);
>
> --
> 1.7.9.5
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [PATCH] Ceph: Avoid data inconsistency due to d-cache aliasing in readpage()
2013-11-13 13:19 ` Yan, Zheng
@ 2013-11-13 14:37 ` Li Wang
0 siblings, 0 replies; 3+ messages in thread
From: Li Wang @ 2013-11-13 14:37 UTC (permalink / raw)
To: Yan, Zheng; +Cc: ceph-devel, Sage Weil, linux-fsdevel, linux-kernel
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 <liwang@ubuntukylin.com> wrote:
>> 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 <liwang@ubuntukylin.com>
>> ---
>> fs/ceph/addr.c | 8 ++++++--
>> 1 file changed, 6 insertions(+), 2 deletions(-)
>>
>> diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
>> index 6df8bd4..7b0000a 100644
>> --- a/fs/ceph/addr.c
>> +++ b/fs/ceph/addr.c
>> @@ -210,9 +210,13 @@ static int readpage_nounlock(struct file *filp, struct page *page)
>> if (err < 0) {
>> SetPageError(page);
>> goto out;
>> - } else if (err < PAGE_CACHE_SIZE) {
>> + } else {
>> + if (err < PAGE_CACHE_SIZE) {
>> /* zero fill remainder of page */
>> - zero_user_segment(page, err, PAGE_CACHE_SIZE);
>> + zero_user_segment(page, err, PAGE_CACHE_SIZE);
>> + } else {
>> + flush_dcache_page(page);
>> + }
>
> this doesn't make sense for me. why not call flush_dcache_page unconditionally?
>
> Regards
> Yan, Zheng
>> }
>> SetPageUptodate(page);
>>
>> --
>> 1.7.9.5
>>
>> --
>> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
>> the body of a message to majordomo@vger.kernel.org
>> More majordomo info at http://vger.kernel.org/majordomo-info.html
>> Please read the FAQ at http://www.tux.org/lkml/
>
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2013-11-13 14:37 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2013-11-13 7:22 [PATCH] Ceph: Avoid data inconsistency due to d-cache aliasing in readpage() Li Wang
2013-11-13 13:19 ` Yan, Zheng
2013-11-13 14:37 ` Li Wang
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).