swap: add block io poll in swapin path

For fast flash disk, async IO could introduce overhead because of
context switch.  block-mq now supports IO poll, which improves
performance and latency a lot.  swapin is a good place to use this
technique, because the task is waiting for the swapin page to continue
execution.

In my virtual machine, directly read 4k data from a NVMe with iopoll is
about 60% better than that without poll.  With iopoll support in swapin
patch, my microbenchmark (a task does random memory write) is about
10%~25% faster.  CPU utilization increases a lot though, 2x and even 3x
CPU utilization.  This will depend on disk speed.

While iopoll in swapin isn't intended for all usage cases, it's a win
for latency sensistive workloads with high speed swap disk.  block layer
has knob to control poll in runtime.  If poll isn't enabled in block
layer, there should be no noticeable change in swapin.

I got a chance to run the same test in a NVMe with DRAM as the media.
In simple fio IO test, blkpoll boosts 50% performance in single thread
test and ~20% in 8 threads test.  So this is the base line.  In above
swap test, blkpoll boosts ~27% performance in single thread test.
blkpoll uses 2x CPU time though.

If we enable hybid polling, the performance gain has very slight drop
but CPU time is only 50% worse than that without blkpoll.  Also we can
adjust parameter of hybid poll, with it, the CPU time penality is
reduced further.  In 8 threads test, blkpoll doesn't help though.  The
performance is similar to that without blkpoll, but cpu utilization is
similar too.  There is lock contention in swap path.  The cpu time
spending on blkpoll isn't high.  So overall, blkpoll swapin isn't worse
than that without it.

The swapin readahead might read several pages in in the same time and
form a big IO request.  Since the IO will take longer time, it doesn't
make sense to do poll, so the patch only does iopoll for single page
swapin.

[akpm@linux-foundation.org: coding-style fixes]
Link: http://lkml.kernel.org/r/070c3c3e40b711e7b1390002c991e86a-b5408f0@7511894063d3764ff01ea8111f5a004d7dd700ed078797c204a24e620ddb965c
Signed-off-by: Shaohua Li <shli@fb.com>
Cc: Tim Chen <tim.c.chen@intel.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Jens Axboe <axboe@fb.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

4 files changed, 30 insertions, 9 deletions

diff --git a/mm/madvise.c b/mm/madvise.c
index 25b78ee4fc2c..8eda1841c576 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -205,7 +205,7 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start,
 			continue;
 
 		page = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE,
-								vma, index);
+							vma, index, false);
 		if (page)
 			put_page(page);
 	}
@@ -246,7 +246,7 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma,
 		}
 		swap = radix_to_swp_entry(page);
 		page = read_swap_cache_async(swap, GFP_HIGHUSER_MOVABLE,
-								NULL, 0);
+							NULL, 0, false);
 		if (page)
 			put_page(page);
 	}
diff --git a/mm/page_io.c b/mm/page_io.c
index 2da71e627812..b6c4ac388209 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -117,6 +117,7 @@ static void swap_slot_free_notify(struct page *page)
 static void end_swap_bio_read(struct bio *bio)
 {
 	struct page *page = bio->bi_io_vec[0].bv_page;
+	struct task_struct *waiter = bio->bi_private;
 
 	if (bio->bi_status) {
 		SetPageError(page);
@@ -132,7 +133,9 @@ static void end_swap_bio_read(struct bio *bio)
 	swap_slot_free_notify(page);
 out:
 	unlock_page(page);
+	WRITE_ONCE(bio->bi_private, NULL);
 	bio_put(bio);
+	wake_up_process(waiter);
 }
 
 int generic_swapfile_activate(struct swap_info_struct *sis,
@@ -329,11 +332,13 @@ out:
 	return ret;
 }
 
-int swap_readpage(struct page *page)
+int swap_readpage(struct page *page, bool do_poll)
 {
 	struct bio *bio;
 	int ret = 0;
 	struct swap_info_struct *sis = page_swap_info(page);
+	blk_qc_t qc;
+	struct block_device *bdev;
 
 	VM_BUG_ON_PAGE(!PageSwapCache(page), page);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
@@ -372,9 +377,23 @@ int swap_readpage(struct page *page)
 		ret = -ENOMEM;
 		goto out;
 	}
+	bdev = bio->bi_bdev;
+	bio->bi_private = current;
 	bio_set_op_attrs(bio, REQ_OP_READ, 0);
 	count_vm_event(PSWPIN);
-	submit_bio(bio);
+	bio_get(bio);
+	qc = submit_bio(bio);
+	while (do_poll) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		if (!READ_ONCE(bio->bi_private))
+			break;
+
+		if (!blk_mq_poll(bdev_get_queue(bdev), qc))
+			break;
+	}
+	__set_current_state(TASK_RUNNING);
+	bio_put(bio);
+
 out:
 	return ret;
 }
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 9c71b6b2562f..b68c93014f50 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -412,14 +412,14 @@ 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)
+		struct vm_area_struct *vma, unsigned long addr, bool do_poll)
 {
 	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);
+		swap_readpage(retpage, do_poll);
 
 	return retpage;
 }
@@ -496,11 +496,13 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
 	unsigned long start_offset, end_offset;
 	unsigned long mask;
 	struct blk_plug plug;
+	bool do_poll = true;
 
 	mask = swapin_nr_pages(offset) - 1;
 	if (!mask)
 		goto skip;
 
+	do_poll = false;
 	/* Read a page_cluster sized and aligned cluster around offset. */
 	start_offset = offset & ~mask;
 	end_offset = offset | mask;
@@ -511,7 +513,7 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
 	for (offset = start_offset; offset <= end_offset ; offset++) {
 		/* Ok, do the async read-ahead now */
 		page = read_swap_cache_async(swp_entry(swp_type(entry), offset),
-						gfp_mask, vma, addr);
+						gfp_mask, vma, addr, false);
 		if (!page)
 			continue;
 		if (offset != entry_offset && likely(!PageTransCompound(page)))
@@ -522,7 +524,7 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
 
 	lru_add_drain();	/* Push any new pages onto the LRU now */
 skip:
-	return read_swap_cache_async(entry, gfp_mask, vma, addr);
+	return read_swap_cache_async(entry, gfp_mask, vma, addr, do_poll);
 }
 
 int init_swap_address_space(unsigned int type, unsigned long nr_pages)
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 811d90e1c929..6ba4aab2db0b 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1868,7 +1868,7 @@ int try_to_unuse(unsigned int type, bool frontswap,
 		swap_map = &si->swap_map[i];
 		entry = swp_entry(type, i);
 		page = read_swap_cache_async(entry,
-					GFP_HIGHUSER_MOVABLE, NULL, 0);
+					GFP_HIGHUSER_MOVABLE, NULL, 0, false);
 		if (!page) {
 			/*
 			 * Either swap_duplicate() failed because entry