[PATCH 02/23] MM: extend block-plugging to cover all swap reads with read-ahead

[NeilBrown]

Code that does swap read-ahead uses blk_start_plug() and
blk_finish_plug() to allow lower levels to combine multiple read-ahead
pages into a single request, but calls blk_finish_plug() *before*
submitting the original (non-ahead) read request.
This missed an opportunity to combine read requests.

This patch moves the blk_finish_plug to *after* all the reads.
This will likely combine the primary read with some of the "ahead"
reads, and that may slightly increase the latency of that read, but it
should more than make up for this by making more efficient use of the
storage path.

The patch mostly makes the code look more consistent.  Performance
change is unlikely to be noticeable.

Fixes-no-auto-backport: 3fb5c298b04e ("swap: allow swap readahead to be merged")
Signed-off-by: NeilBrown <neilb@xxxxxxx>
---
 mm/swap_state.c |   14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/mm/swap_state.c b/mm/swap_state.c
index bb38453425c7..093ecf864200 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -625,6 +625,7 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
 	struct vm_area_struct *vma = vmf->vma;
 	unsigned long addr = vmf->address;
 
+	blk_start_plug(&plug);
 	mask = swapin_nr_pages(offset) - 1;
 	if (!mask)
 		goto skip;
@@ -638,7 +639,6 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
 	if (end_offset >= si->max)
 		end_offset = si->max - 1;
 
-	blk_start_plug(&plug);
 	for (offset = start_offset; offset <= end_offset ; offset++) {
 		/* Ok, do the async read-ahead now */
 		page = __read_swap_cache_async(
@@ -655,11 +655,12 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
 		}
 		put_page(page);
 	}
-	blk_finish_plug(&plug);
 
 	lru_add_drain();	/* Push any new pages onto the LRU now */
 skip:
-	return read_swap_cache_async(entry, gfp_mask, vma, addr, do_poll);
+	page = read_swap_cache_async(entry, gfp_mask, vma, addr, do_poll);
+	blk_finish_plug(&plug);
+	return page;
 }
 
 int init_swap_address_space(unsigned int type, unsigned long nr_pages)
@@ -800,11 +801,11 @@ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask,
 		.win = 1,
 	};
 
+	blk_start_plug(&plug);
 	swap_ra_info(vmf, &ra_info);
 	if (ra_info.win == 1)
 		goto skip;
 
-	blk_start_plug(&plug);
 	for (i = 0, pte = ra_info.ptes; i < ra_info.nr_pte;
 	     i++, pte++) {
 		pentry = *pte;
@@ -828,11 +829,12 @@ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask,
 		}
 		put_page(page);
 	}
-	blk_finish_plug(&plug);
 	lru_add_drain();
 skip:
-	return read_swap_cache_async(fentry, gfp_mask, vma, vmf->address,
+	page = read_swap_cache_async(fentry, gfp_mask, vma, vmf->address,
 				     ra_info.win == 1);
+	blk_finish_plug(&plug);
+	return page;
 }
 
 /**