* [PATCH-v3] pnfsblock: bail out partial page IO
@ 2012-05-29 5:57 Peng Tao
2012-05-29 7:16 ` Boaz Harrosh
0 siblings, 1 reply; 2+ messages in thread
From: Peng Tao @ 2012-05-29 5:57 UTC (permalink / raw)
To: Trond.Myklebust; +Cc: rees, bharrosh, jrnieder, linux-nfs, stable, Peng Tao
Current block layout driver read/write code assumes page
aligned IO in many places. Add a checker to validate the assumption.
Otherwise there would be data corruption like when application does
open(O_WRONLY) and page unaliged write.
Cc: stable@vger.kernel.org
Signed-off-by: Peng Tao <tao.peng@emc.com>
---
Change from v2:
Add symptom in commit log.
fs/nfs/blocklayout/blocklayout.c | 39 +++++++++++++++++++++++++++++++++++--
1 files changed, 36 insertions(+), 3 deletions(-)
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 7ae8a60..dd392ed 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -228,6 +228,14 @@ bl_end_par_io_read(void *data, int unused)
schedule_work(&rdata->task.u.tk_work);
}
+static bool
+bl_check_alignment(u64 offset, u32 len, unsigned long blkmask)
+{
+ if ((offset & blkmask) || (len & blkmask))
+ return false;
+ return true;
+}
+
static enum pnfs_try_status
bl_read_pagelist(struct nfs_read_data *rdata)
{
@@ -244,6 +252,9 @@ bl_read_pagelist(struct nfs_read_data *rdata)
dprintk("%s enter nr_pages %u offset %lld count %u\n", __func__,
rdata->pages.npages, f_offset, (unsigned int)rdata->args.count);
+ if (!bl_check_alignment(f_offset, rdata->args.count, PAGE_CACHE_MASK))
+ goto use_mds;
+
par = alloc_parallel(rdata);
if (!par)
goto use_mds;
@@ -552,7 +563,7 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync)
struct bio *bio = NULL;
struct pnfs_block_extent *be = NULL, *cow_read = NULL;
sector_t isect, last_isect = 0, extent_length = 0;
- struct parallel_io *par;
+ struct parallel_io *par = NULL;
loff_t offset = wdata->args.offset;
size_t count = wdata->args.count;
struct page **pages = wdata->args.pages;
@@ -563,6 +574,10 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync)
NFS_SERVER(header->inode)->pnfs_blksize >> PAGE_CACHE_SHIFT;
dprintk("%s enter, %Zu@%lld\n", __func__, count, offset);
+ /* Check for alignment first */
+ if (!bl_check_alignment(offset, count, PAGE_CACHE_MASK))
+ goto out_mds;
+
/* At this point, wdata->pages is a (sequential) list of nfs_pages.
* We want to write each, and if there is an error set pnfs_error
* to have it redone using nfs.
@@ -996,14 +1011,32 @@ bl_clear_layoutdriver(struct nfs_server *server)
return 0;
}
+static void
+bl_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
+{
+ if (!bl_check_alignment(req->wb_offset, req->wb_bytes, PAGE_CACHE_MASK))
+ nfs_pageio_reset_read_mds(pgio);
+ else
+ pnfs_generic_pg_init_read(pgio, req);
+}
+
+static void
+bl_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
+{
+ if (!bl_check_alignment(req->wb_offset, req->wb_bytes, PAGE_CACHE_MASK))
+ nfs_pageio_reset_write_mds(pgio);
+ else
+ pnfs_generic_pg_init_write(pgio, req);
+}
+
static const struct nfs_pageio_ops bl_pg_read_ops = {
- .pg_init = pnfs_generic_pg_init_read,
+ .pg_init = bl_pg_init_read,
.pg_test = pnfs_generic_pg_test,
.pg_doio = pnfs_generic_pg_readpages,
};
static const struct nfs_pageio_ops bl_pg_write_ops = {
- .pg_init = pnfs_generic_pg_init_write,
+ .pg_init = bl_pg_init_write,
.pg_test = pnfs_generic_pg_test,
.pg_doio = pnfs_generic_pg_writepages,
};
--
1.7.1.262.g5ef3d
^ permalink raw reply related [flat|nested] 2+ messages in thread* Re: [PATCH-v3] pnfsblock: bail out partial page IO
2012-05-29 5:57 [PATCH-v3] pnfsblock: bail out partial page IO Peng Tao
@ 2012-05-29 7:16 ` Boaz Harrosh
0 siblings, 0 replies; 2+ messages in thread
From: Boaz Harrosh @ 2012-05-29 7:16 UTC (permalink / raw)
To: Peng Tao; +Cc: Trond.Myklebust, rees, jrnieder, linux-nfs, stable, Peng Tao
On 05/29/2012 08:57 AM, Peng Tao wrote:
> Current block layout driver read/write code assumes page
> aligned IO in many places. Add a checker to validate the assumption.
> Otherwise there would be data corruption like when application does
> open(O_WRONLY) and page unaliged write.
>
Please add the dprints
> Cc: stable@vger.kernel.org
> Signed-off-by: Peng Tao <tao.peng@emc.com>
> ---
> Change from v2:
> Add symptom in commit log.
>
> fs/nfs/blocklayout/blocklayout.c | 39 +++++++++++++++++++++++++++++++++++--
> 1 files changed, 36 insertions(+), 3 deletions(-)
>
> diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
> index 7ae8a60..dd392ed 100644
> --- a/fs/nfs/blocklayout/blocklayout.c
> +++ b/fs/nfs/blocklayout/blocklayout.c
> @@ -228,6 +228,14 @@ bl_end_par_io_read(void *data, int unused)
> schedule_work(&rdata->task.u.tk_work);
> }
>
> +static bool
> +bl_check_alignment(u64 offset, u32 len, unsigned long blkmask)
> +{
> + if ((offset & blkmask) || (len & blkmask))
> + return false;
> + return true;
> +}
> +
> static enum pnfs_try_status
> bl_read_pagelist(struct nfs_read_data *rdata)
> {
> @@ -244,6 +252,9 @@ bl_read_pagelist(struct nfs_read_data *rdata)
> dprintk("%s enter nr_pages %u offset %lld count %u\n", __func__,
> rdata->pages.npages, f_offset, (unsigned int)rdata->args.count);
>
> + if (!bl_check_alignment(f_offset, rdata->args.count, PAGE_CACHE_MASK))
> + goto use_mds;
> +
> par = alloc_parallel(rdata);
> if (!par)
> goto use_mds;
> @@ -552,7 +563,7 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync)
> struct bio *bio = NULL;
> struct pnfs_block_extent *be = NULL, *cow_read = NULL;
> sector_t isect, last_isect = 0, extent_length = 0;
> - struct parallel_io *par;
> + struct parallel_io *par = NULL;
> loff_t offset = wdata->args.offset;
> size_t count = wdata->args.count;
> struct page **pages = wdata->args.pages;
> @@ -563,6 +574,10 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync)
> NFS_SERVER(header->inode)->pnfs_blksize >> PAGE_CACHE_SHIFT;
>
> dprintk("%s enter, %Zu@%lld\n", __func__, count, offset);
> + /* Check for alignment first */
> + if (!bl_check_alignment(offset, count, PAGE_CACHE_MASK))
> + goto out_mds;
> +
> /* At this point, wdata->pages is a (sequential) list of nfs_pages.
> * We want to write each, and if there is an error set pnfs_error
> * to have it redone using nfs.
> @@ -996,14 +1011,32 @@ bl_clear_layoutdriver(struct nfs_server *server)
> return 0;
> }
>
> +static void
> +bl_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
> +{
> + if (!bl_check_alignment(req->wb_offset, req->wb_bytes, PAGE_CACHE_MASK))
> + nfs_pageio_reset_read_mds(pgio);
> + else
> + pnfs_generic_pg_init_read(pgio, req);
> +}
> +
> +static void
> +bl_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
> +{
> + if (!bl_check_alignment(req->wb_offset, req->wb_bytes, PAGE_CACHE_MASK))
> + nfs_pageio_reset_write_mds(pgio);
> + else
> + pnfs_generic_pg_init_write(pgio, req);
> +}
> +
> static const struct nfs_pageio_ops bl_pg_read_ops = {
> - .pg_init = pnfs_generic_pg_init_read,
> + .pg_init = bl_pg_init_read,
> .pg_test = pnfs_generic_pg_test,
> .pg_doio = pnfs_generic_pg_readpages,
> };
>
> static const struct nfs_pageio_ops bl_pg_write_ops = {
> - .pg_init = pnfs_generic_pg_init_write,
> + .pg_init = bl_pg_init_write,
> .pg_test = pnfs_generic_pg_test,
> .pg_doio = pnfs_generic_pg_writepages,
> };
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2012-05-29 7:17 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2012-05-29 5:57 [PATCH-v3] pnfsblock: bail out partial page IO Peng Tao
2012-05-29 7:16 ` Boaz Harrosh
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).