Add a new SGP_FIND mode for shmem_get_partial_folio that works like
SGP_READ, but does not check i_size. Use that instead of open coding
the page cache lookup in shmem_get_partial_folio. Note that this is
a behavior change in that it reads in swap cache entries for offsets
outside i_size, possibly causing a little bit of extra work.
Signed-off-by: Christoph Hellwig <[email protected]>
---
include/linux/shmem_fs.h | 1 +
mm/shmem.c | 46 ++++++++++++----------------------------
2 files changed, 15 insertions(+), 32 deletions(-)
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index d09d54be4ffd99..7ba160ac066e5e 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -105,6 +105,7 @@ enum sgp_type {
SGP_CACHE, /* don't exceed i_size, may allocate page */
SGP_WRITE, /* may exceed i_size, may allocate !Uptodate page */
SGP_FALLOC, /* like SGP_WRITE, but make existing page Uptodate */
+ SGP_FIND, /* like SGP_READ, but also read outside i_size */
};
int shmem_get_folio(struct inode *inode, pgoff_t index, struct folio **foliop,
diff --git a/mm/shmem.c b/mm/shmem.c
index 9e1015cbad29f9..e9500fea43a8dc 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -877,27 +877,6 @@ void shmem_unlock_mapping(struct address_space *mapping)
}
}
-static struct folio *shmem_get_partial_folio(struct inode *inode, pgoff_t index)
-{
- struct folio *folio;
-
- /*
- * At first avoid shmem_get_folio(,,,SGP_READ): that fails
- * beyond i_size, and reports fallocated pages as holes.
- */
- folio = __filemap_get_folio(inode->i_mapping, index,
- FGP_ENTRY | FGP_LOCK, 0);
- if (!xa_is_value(folio))
- return folio;
- /*
- * But read a page back from swap if any of it is within i_size
- * (although in some cases this is just a waste of time).
- */
- folio = NULL;
- shmem_get_folio(inode, index, &folio, SGP_READ);
- return folio;
-}
-
/*
* Remove range of pages and swap entries from page cache, and free them.
* If !unfalloc, truncate or punch hole; if unfalloc, undo failed fallocate.
@@ -957,7 +936,8 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
goto whole_folios;
same_folio = (lstart >> PAGE_SHIFT) == (lend >> PAGE_SHIFT);
- folio = shmem_get_partial_folio(inode, lstart >> PAGE_SHIFT);
+ folio = NULL;
+ shmem_get_folio(inode, lstart >> PAGE_SHIFT, &folio, SGP_FIND);
if (folio) {
same_folio = lend < folio_pos(folio) + folio_size(folio);
folio_mark_dirty(folio);
@@ -971,14 +951,16 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
folio = NULL;
}
- if (!same_folio)
- folio = shmem_get_partial_folio(inode, lend >> PAGE_SHIFT);
- if (folio) {
- folio_mark_dirty(folio);
- if (!truncate_inode_partial_folio(folio, lstart, lend))
- end = folio->index;
- folio_unlock(folio);
- folio_put(folio);
+ if (!same_folio) {
+ folio = NULL;
+ shmem_get_folio(inode, lend >> PAGE_SHIFT, &folio, SGP_FIND);
+ if (folio) {
+ folio_mark_dirty(folio);
+ if (!truncate_inode_partial_folio(folio, lstart, lend))
+ end = folio->index;
+ folio_unlock(folio);
+ folio_put(folio);
+ }
}
whole_folios:
@@ -1900,7 +1882,7 @@ static int shmem_get_folio_gfp(struct inode *inode, pgoff_t index,
if (folio_test_uptodate(folio))
goto out;
/* fallocated folio */
- if (sgp != SGP_READ)
+ if (sgp != SGP_READ && sgp != SGP_FIND)
goto clear;
folio_unlock(folio);
folio_put(folio);
@@ -1911,7 +1893,7 @@ static int shmem_get_folio_gfp(struct inode *inode, pgoff_t index,
* SGP_NOALLOC: fail on hole, with NULL folio, letting caller fail.
*/
*foliop = NULL;
- if (sgp == SGP_READ)
+ if (sgp == SGP_READ || sgp == SGP_FIND)
return 0;
if (sgp == SGP_NOALLOC)
return -ENOENT;
--
2.39.0
On Wed, Jan 18, 2023 at 10:43:24AM +0100, Christoph Hellwig wrote:
> Add a new SGP_FIND mode for shmem_get_partial_folio that works like
> SGP_READ, but does not check i_size. Use that instead of open coding
> the page cache lookup in shmem_get_partial_folio. Note that this is
> a behavior change in that it reads in swap cache entries for offsets
> outside i_size, possibly causing a little bit of extra work.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
> ---
> include/linux/shmem_fs.h | 1 +
> mm/shmem.c | 46 ++++++++++++----------------------------
> 2 files changed, 15 insertions(+), 32 deletions(-)
>
> diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
> index d09d54be4ffd99..7ba160ac066e5e 100644
> --- a/include/linux/shmem_fs.h
> +++ b/include/linux/shmem_fs.h
> @@ -105,6 +105,7 @@ enum sgp_type {
> SGP_CACHE, /* don't exceed i_size, may allocate page */
> SGP_WRITE, /* may exceed i_size, may allocate !Uptodate page */
> SGP_FALLOC, /* like SGP_WRITE, but make existing page Uptodate */
> + SGP_FIND, /* like SGP_READ, but also read outside i_size */
> };
>
> int shmem_get_folio(struct inode *inode, pgoff_t index, struct folio **foliop,
> diff --git a/mm/shmem.c b/mm/shmem.c
> index 9e1015cbad29f9..e9500fea43a8dc 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -877,27 +877,6 @@ void shmem_unlock_mapping(struct address_space *mapping)
> }
> }
>
> -static struct folio *shmem_get_partial_folio(struct inode *inode, pgoff_t index)
> -{
> - struct folio *folio;
> -
> - /*
> - * At first avoid shmem_get_folio(,,,SGP_READ): that fails
> - * beyond i_size, and reports fallocated pages as holes.
> - */
> - folio = __filemap_get_folio(inode->i_mapping, index,
> - FGP_ENTRY | FGP_LOCK, 0);
This all seems reasonable to me at a glance, FWIW, but I am a little
curious why this wouldn't split up into two changes. I.e., switch this
over to filemap_get_entry() to minimally remove the FGP_ENTRY dependency
without a behavior change, then (perhaps after the next patch) introduce
SGP_FIND in a separate patch. That makes it easier to review and
potentially undo if it happens to pose a problem in the future. Hm?
Brian
> - if (!xa_is_value(folio))
> - return folio;
> - /*
> - * But read a page back from swap if any of it is within i_size
> - * (although in some cases this is just a waste of time).
> - */
> - folio = NULL;
> - shmem_get_folio(inode, index, &folio, SGP_READ);
> - return folio;
> -}
> -
> /*
> * Remove range of pages and swap entries from page cache, and free them.
> * If !unfalloc, truncate or punch hole; if unfalloc, undo failed fallocate.
> @@ -957,7 +936,8 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
> goto whole_folios;
>
> same_folio = (lstart >> PAGE_SHIFT) == (lend >> PAGE_SHIFT);
> - folio = shmem_get_partial_folio(inode, lstart >> PAGE_SHIFT);
> + folio = NULL;
> + shmem_get_folio(inode, lstart >> PAGE_SHIFT, &folio, SGP_FIND);
> if (folio) {
> same_folio = lend < folio_pos(folio) + folio_size(folio);
> folio_mark_dirty(folio);
> @@ -971,14 +951,16 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
> folio = NULL;
> }
>
> - if (!same_folio)
> - folio = shmem_get_partial_folio(inode, lend >> PAGE_SHIFT);
> - if (folio) {
> - folio_mark_dirty(folio);
> - if (!truncate_inode_partial_folio(folio, lstart, lend))
> - end = folio->index;
> - folio_unlock(folio);
> - folio_put(folio);
> + if (!same_folio) {
> + folio = NULL;
> + shmem_get_folio(inode, lend >> PAGE_SHIFT, &folio, SGP_FIND);
> + if (folio) {
> + folio_mark_dirty(folio);
> + if (!truncate_inode_partial_folio(folio, lstart, lend))
> + end = folio->index;
> + folio_unlock(folio);
> + folio_put(folio);
> + }
> }
>
> whole_folios:
> @@ -1900,7 +1882,7 @@ static int shmem_get_folio_gfp(struct inode *inode, pgoff_t index,
> if (folio_test_uptodate(folio))
> goto out;
> /* fallocated folio */
> - if (sgp != SGP_READ)
> + if (sgp != SGP_READ && sgp != SGP_FIND)
> goto clear;
> folio_unlock(folio);
> folio_put(folio);
> @@ -1911,7 +1893,7 @@ static int shmem_get_folio_gfp(struct inode *inode, pgoff_t index,
> * SGP_NOALLOC: fail on hole, with NULL folio, letting caller fail.
> */
> *foliop = NULL;
> - if (sgp == SGP_READ)
> + if (sgp == SGP_READ || sgp == SGP_FIND)
> return 0;
> if (sgp == SGP_NOALLOC)
> return -ENOENT;
> --
> 2.39.0
>
>
On Wed, Jan 18, 2023 at 08:57:05AM -0500, Brian Foster wrote:
> This all seems reasonable to me at a glance, FWIW, but I am a little
> curious why this wouldn't split up into two changes. I.e., switch this
> over to filemap_get_entry() to minimally remove the FGP_ENTRY dependency
> without a behavior change, then (perhaps after the next patch) introduce
> SGP_FIND in a separate patch. That makes it easier to review and
> potentially undo if it happens to pose a problem in the future. Hm?
The minimal change to filemap_get_entry would require to add the
lock, check mapping and retry loop and thus add a fair amount of
code. So I looked for ways to avoid that and came up with this
version. But if there is a strong preference to first open code
the logic and then later consolidate it I could do that.
On Wed, Jan 18, 2023 at 05:43:58PM +0100, Christoph Hellwig wrote:
> On Wed, Jan 18, 2023 at 08:57:05AM -0500, Brian Foster wrote:
> > This all seems reasonable to me at a glance, FWIW, but I am a little
> > curious why this wouldn't split up into two changes. I.e., switch this
> > over to filemap_get_entry() to minimally remove the FGP_ENTRY dependency
> > without a behavior change, then (perhaps after the next patch) introduce
> > SGP_FIND in a separate patch. That makes it easier to review and
> > potentially undo if it happens to pose a problem in the future. Hm?
>
> The minimal change to filemap_get_entry would require to add the
> lock, check mapping and retry loop and thus add a fair amount of
> code. So I looked for ways to avoid that and came up with this
> version. But if there is a strong preference to first open code
> the logic and then later consolidate it I could do that.
>
Ok. Not a strong preference from me. I don't think it's worth
complicating that much just to split up.
Brian