mm: submit multipage reads for SWP_FS_OPS swap-space
swap_readpage() is given one page at a time, but may be called repeatedly
in succession.
For block-device swap-space, the blk_plug functionality allows the
multiple pages to be combined together at lower layers. That cannot be
used for SWP_FS_OPS as blk_plug may not exist - it is only active when
CONFIG_BLOCK=y. Consequently all swap reads over NFS are single page
reads.
With this patch we pass in a pointer-to-pointer when swap_readpage can
store state between calls - much like the effect of blk_plug. After
calling swap_readpage() some number of times, the state will be passed to
swap_read_unplug() which can submit the combined request.
Link: https://lkml.kernel.org/r/164859778127.29473.14059420492644907783.stgit@noble.brown
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: David Howells <dhowells@redhat.com>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: Hugh Dickins <hughd@google.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
diff --git a/mm/swap_state.c b/mm/swap_state.c
index f3ab018..d41746a 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -520,14 +520,16 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
* the swap entry is no longer in use.
*/
struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
- struct vm_area_struct *vma, unsigned long addr, bool do_poll)
+ struct vm_area_struct *vma,
+ unsigned long addr, bool do_poll,
+ struct swap_iocb **plug)
{
bool page_was_allocated;
struct page *retpage = __read_swap_cache_async(entry, gfp_mask,
vma, addr, &page_was_allocated);
if (page_was_allocated)
- swap_readpage(retpage, do_poll);
+ swap_readpage(retpage, do_poll, plug);
return retpage;
}
@@ -621,6 +623,7 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
unsigned long mask;
struct swap_info_struct *si = swp_swap_info(entry);
struct blk_plug plug;
+ struct swap_iocb *splug = NULL;
bool do_poll = true, page_allocated;
struct vm_area_struct *vma = vmf->vma;
unsigned long addr = vmf->address;
@@ -647,7 +650,7 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
if (!page)
continue;
if (page_allocated) {
- swap_readpage(page, false);
+ swap_readpage(page, false, &splug);
if (offset != entry_offset) {
SetPageReadahead(page);
count_vm_event(SWAP_RA);
@@ -656,10 +659,12 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
put_page(page);
}
blk_finish_plug(&plug);
+ swap_read_unplug(splug);
lru_add_drain(); /* Push any new pages onto the LRU now */
skip:
- return read_swap_cache_async(entry, gfp_mask, vma, addr, do_poll);
+ /* The page was likely read above, so no need for plugging here */
+ return read_swap_cache_async(entry, gfp_mask, vma, addr, do_poll, NULL);
}
int init_swap_address_space(unsigned int type, unsigned long nr_pages)
@@ -790,6 +795,7 @@ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask,
struct vm_fault *vmf)
{
struct blk_plug plug;
+ struct swap_iocb *splug = NULL;
struct vm_area_struct *vma = vmf->vma;
struct page *page;
pte_t *pte, pentry;
@@ -820,7 +826,7 @@ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask,
if (!page)
continue;
if (page_allocated) {
- swap_readpage(page, false);
+ swap_readpage(page, false, &splug);
if (i != ra_info.offset) {
SetPageReadahead(page);
count_vm_event(SWAP_RA);
@@ -829,10 +835,12 @@ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask,
put_page(page);
}
blk_finish_plug(&plug);
+ swap_read_unplug(splug);
lru_add_drain();
skip:
+ /* The page was likely read above, so no need for plugging here */
return read_swap_cache_async(fentry, gfp_mask, vma, vmf->address,
- ra_info.win == 1);
+ ra_info.win == 1, NULL);
}
/**
