The use of kmap() is being deprecated in favor of kmap_local_page().
There are two main problems with kmap(): (1) It comes with an overhead as
mapping space is restricted and protected by a global lock for
synchronization and (2) it also requires global TLB invalidation when the
kmap’s pool wraps and it might block when the mapping space is fully
utilized until a slot becomes available.
With kmap_local_page() the mappings are per thread, CPU local, can take
page faults, and can be called from any context (including interrupts).
Tasks can be preempted and, when scheduled to run again, the kernel
virtual addresses are restored and still valid. It is faster than kmap()
in kernels with HIGHMEM enabled.
Since kmap_local_page() can be safely used in compress.c, it should be
called everywhere instead of kmap().
Therefore, replace kmap() with kmap_local_page() in compress.c. Where it
is needed, use memzero_page() instead of open coding kmap_local_page()
plus memset() to fill the pages with zeros. Delete the redundant
flush_dcache_page() in the two call sites of memzero_page().
Tested with mkisofs on a QEMU/KVM x86_32 VM, 6GB RAM, booting a kernel
with HIGHMEM64GB enabled.
Cc: Andrew Morton <[email protected]>
Cc: Jan Kara <[email protected]>
Suggested-by: Ira Weiny <[email protected]>
Signed-off-by: Fabio M. De Francesco <[email protected]>
---
Some days ago Andrew requested a resend of this patch.[1]
v1->v2: Cast zisofs_sink_page to pointer to unsigned char.
Reported-by: kernel test robot <[email protected]>
Many thanks to Jan Kara for the comments and suggestions provided with
replying to my previous RFC.[2] Furthermore, I want to thank Ira Weiny for
the advices he provided, especially about how to use mkisofs to test that
this patch is working properly.
[1] https://lore.kernel.org/all/[email protected]/
[2] https://lore.kernel.org/lkml/20220726145024.rryvw7ot7j2c6tqv@quack3/
fs/isofs/compress.c | 20 ++++++++++----------
1 file changed, 10 insertions(+), 10 deletions(-)
diff --git a/fs/isofs/compress.c b/fs/isofs/compress.c
index 95a19f25d61c..107007c38d08 100644
--- a/fs/isofs/compress.c
+++ b/fs/isofs/compress.c
@@ -67,8 +67,7 @@ static loff_t zisofs_uncompress_block(struct inode *inode, loff_t block_start,
for ( i = 0 ; i < pcount ; i++ ) {
if (!pages[i])
continue;
- memset(page_address(pages[i]), 0, PAGE_SIZE);
- flush_dcache_page(pages[i]);
+ memzero_page(pages[i], 0, PAGE_SIZE);
SetPageUptodate(pages[i]);
}
return ((loff_t)pcount) << PAGE_SHIFT;
@@ -120,7 +119,7 @@ static loff_t zisofs_uncompress_block(struct inode *inode, loff_t block_start,
zerr != Z_STREAM_END) {
if (!stream.avail_out) {
if (pages[curpage]) {
- stream.next_out = page_address(pages[curpage])
+ stream.next_out = kmap_local_page(pages[curpage])
+ poffset;
stream.avail_out = PAGE_SIZE - poffset;
poffset = 0;
@@ -176,6 +175,10 @@ static loff_t zisofs_uncompress_block(struct inode *inode, loff_t block_start,
flush_dcache_page(pages[curpage]);
SetPageUptodate(pages[curpage]);
}
+ if (stream.next_out != (unsigned char *)zisofs_sink_page) {
+ kunmap_local(stream.next_out);
+ stream.next_out = NULL;
+ }
curpage++;
}
if (!stream.avail_in)
@@ -183,6 +186,8 @@ static loff_t zisofs_uncompress_block(struct inode *inode, loff_t block_start,
}
inflate_out:
zlib_inflateEnd(&stream);
+ if (stream.next_out && stream.next_out != (unsigned char *)zisofs_sink_page)
+ kunmap_local(stream.next_out);
z_eio:
mutex_unlock(&zisofs_zlib_lock);
@@ -283,9 +288,7 @@ static int zisofs_fill_pages(struct inode *inode, int full_page, int pcount,
}
if (poffset && *pages) {
- memset(page_address(*pages) + poffset, 0,
- PAGE_SIZE - poffset);
- flush_dcache_page(*pages);
+ memzero_page(*pages, poffset, PAGE_SIZE - poffset);
SetPageUptodate(*pages);
}
return 0;
@@ -343,10 +346,8 @@ static int zisofs_read_folio(struct file *file, struct folio *folio)
for (i = 0; i < pcount; i++, index++) {
if (i != full_page)
pages[i] = grab_cache_page_nowait(mapping, index);
- if (pages[i]) {
+ if (pages[i])
ClearPageError(pages[i]);
- kmap(pages[i]);
- }
}
err = zisofs_fill_pages(inode, full_page, pcount, pages);
@@ -357,7 +358,6 @@ static int zisofs_read_folio(struct file *file, struct folio *folio)
flush_dcache_page(pages[i]);
if (i == full_page && err)
SetPageError(pages[i]);
- kunmap(pages[i]);
unlock_page(pages[i]);
if (i != full_page)
put_page(pages[i]);
--
2.37.1
On Sun 21-08-22 19:50:12, Fabio M. De Francesco wrote:
> The use of kmap() is being deprecated in favor of kmap_local_page().
>
> There are two main problems with kmap(): (1) It comes with an overhead as
> mapping space is restricted and protected by a global lock for
> synchronization and (2) it also requires global TLB invalidation when the
> kmap’s pool wraps and it might block when the mapping space is fully
> utilized until a slot becomes available.
>
> With kmap_local_page() the mappings are per thread, CPU local, can take
> page faults, and can be called from any context (including interrupts).
> Tasks can be preempted and, when scheduled to run again, the kernel
> virtual addresses are restored and still valid. It is faster than kmap()
> in kernels with HIGHMEM enabled.
>
> Since kmap_local_page() can be safely used in compress.c, it should be
> called everywhere instead of kmap().
>
> Therefore, replace kmap() with kmap_local_page() in compress.c. Where it
> is needed, use memzero_page() instead of open coding kmap_local_page()
> plus memset() to fill the pages with zeros. Delete the redundant
> flush_dcache_page() in the two call sites of memzero_page().
>
> Tested with mkisofs on a QEMU/KVM x86_32 VM, 6GB RAM, booting a kernel
> with HIGHMEM64GB enabled.
>
> Cc: Andrew Morton <[email protected]>
> Cc: Jan Kara <[email protected]>
> Suggested-by: Ira Weiny <[email protected]>
> Signed-off-by: Fabio M. De Francesco <[email protected]>
Thanks for the patch! It looks good to me. Feel free to add:
Reviewed-by: Jan Kara <[email protected]>
Honza
> ---
>
> Some days ago Andrew requested a resend of this patch.[1]
>
> v1->v2: Cast zisofs_sink_page to pointer to unsigned char.
> Reported-by: kernel test robot <[email protected]>
>
> Many thanks to Jan Kara for the comments and suggestions provided with
> replying to my previous RFC.[2] Furthermore, I want to thank Ira Weiny for
> the advices he provided, especially about how to use mkisofs to test that
> this patch is working properly.
>
> [1] https://lore.kernel.org/all/[email protected]/
> [2] https://lore.kernel.org/lkml/20220726145024.rryvw7ot7j2c6tqv@quack3/
>
> fs/isofs/compress.c | 20 ++++++++++----------
> 1 file changed, 10 insertions(+), 10 deletions(-)
>
> diff --git a/fs/isofs/compress.c b/fs/isofs/compress.c
> index 95a19f25d61c..107007c38d08 100644
> --- a/fs/isofs/compress.c
> +++ b/fs/isofs/compress.c
> @@ -67,8 +67,7 @@ static loff_t zisofs_uncompress_block(struct inode *inode, loff_t block_start,
> for ( i = 0 ; i < pcount ; i++ ) {
> if (!pages[i])
> continue;
> - memset(page_address(pages[i]), 0, PAGE_SIZE);
> - flush_dcache_page(pages[i]);
> + memzero_page(pages[i], 0, PAGE_SIZE);
> SetPageUptodate(pages[i]);
> }
> return ((loff_t)pcount) << PAGE_SHIFT;
> @@ -120,7 +119,7 @@ static loff_t zisofs_uncompress_block(struct inode *inode, loff_t block_start,
> zerr != Z_STREAM_END) {
> if (!stream.avail_out) {
> if (pages[curpage]) {
> - stream.next_out = page_address(pages[curpage])
> + stream.next_out = kmap_local_page(pages[curpage])
> + poffset;
> stream.avail_out = PAGE_SIZE - poffset;
> poffset = 0;
> @@ -176,6 +175,10 @@ static loff_t zisofs_uncompress_block(struct inode *inode, loff_t block_start,
> flush_dcache_page(pages[curpage]);
> SetPageUptodate(pages[curpage]);
> }
> + if (stream.next_out != (unsigned char *)zisofs_sink_page) {
> + kunmap_local(stream.next_out);
> + stream.next_out = NULL;
> + }
> curpage++;
> }
> if (!stream.avail_in)
> @@ -183,6 +186,8 @@ static loff_t zisofs_uncompress_block(struct inode *inode, loff_t block_start,
> }
> inflate_out:
> zlib_inflateEnd(&stream);
> + if (stream.next_out && stream.next_out != (unsigned char *)zisofs_sink_page)
> + kunmap_local(stream.next_out);
>
> z_eio:
> mutex_unlock(&zisofs_zlib_lock);
> @@ -283,9 +288,7 @@ static int zisofs_fill_pages(struct inode *inode, int full_page, int pcount,
> }
>
> if (poffset && *pages) {
> - memset(page_address(*pages) + poffset, 0,
> - PAGE_SIZE - poffset);
> - flush_dcache_page(*pages);
> + memzero_page(*pages, poffset, PAGE_SIZE - poffset);
> SetPageUptodate(*pages);
> }
> return 0;
> @@ -343,10 +346,8 @@ static int zisofs_read_folio(struct file *file, struct folio *folio)
> for (i = 0; i < pcount; i++, index++) {
> if (i != full_page)
> pages[i] = grab_cache_page_nowait(mapping, index);
> - if (pages[i]) {
> + if (pages[i])
> ClearPageError(pages[i]);
> - kmap(pages[i]);
> - }
> }
>
> err = zisofs_fill_pages(inode, full_page, pcount, pages);
> @@ -357,7 +358,6 @@ static int zisofs_read_folio(struct file *file, struct folio *folio)
> flush_dcache_page(pages[i]);
> if (i == full_page && err)
> SetPageError(pages[i]);
> - kunmap(pages[i]);
> unlock_page(pages[i]);
> if (i != full_page)
> put_page(pages[i]);
> --
> 2.37.1
>
--
Jan Kara <[email protected]>
SUSE Labs, CR