[2/2] mm, swap: introduce SWP_READ_SYNCHRONOUS_IO

Commit Message

Qun-wei Lin (林群崴) Sept. 19, 2024, 11:29 a.m. UTC

The existing SWP_SYNCHRONOUS_IO flag is not enough for certain swap
devices that support synchronous read operations but asynchronous write
operations, so we need to introduce a new flag SWP_READ_SYNCHRONOUS_IO.

Signed-off-by: Qun-Wei Lin <[e-mail]>
---
 include/linux/swap.h | 31 ++++++++++++++++---------------
 mm/memory.c          |  3 ++-
 mm/page_io.c         |  2 +-
 mm/swapfile.c        |  3 +++
 4 files changed, 22 insertions(+), 17 deletions(-)

Patch

diff --git a/include/linux/swap.h b/include/linux/swap.h
index ba7ea95d1c57..f595050f431b 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -205,21 +205,22 @@  struct swap_extent {
 	  offsetof(union swap_header, info.badpages)) / sizeof(int))
 
 enum {
-	SWP_USED	= (1 << 0),	/* is slot in swap_info[] used? */
-	SWP_WRITEOK	= (1 << 1),	/* ok to write to this swap?	*/
-	SWP_DISCARDABLE = (1 << 2),	/* blkdev support discard */
-	SWP_DISCARDING	= (1 << 3),	/* now discarding a free cluster */
-	SWP_SOLIDSTATE	= (1 << 4),	/* blkdev seeks are cheap */
-	SWP_CONTINUED	= (1 << 5),	/* swap_map has count continuation */
-	SWP_BLKDEV	= (1 << 6),	/* its a block device */
-	SWP_ACTIVATED	= (1 << 7),	/* set after swap_activate success */
-	SWP_FS_OPS	= (1 << 8),	/* swapfile operations go through fs */
-	SWP_AREA_DISCARD = (1 << 9),	/* single-time swap area discards */
-	SWP_PAGE_DISCARD = (1 << 10),	/* freed swap page-cluster discards */
-	SWP_STABLE_WRITES = (1 << 11),	/* no overwrite PG_writeback pages */
-	SWP_SYNCHRONOUS_IO = (1 << 12),	/* synchronous IO is efficient */
-					/* add others here before... */
-	SWP_SCANNING	= (1 << 14),	/* refcount in scan_swap_map */
+	SWP_USED	= (1 << 0),		/* is slot in swap_info[] used? */
+	SWP_WRITEOK	= (1 << 1),		/* ok to write to this swap?	*/
+	SWP_DISCARDABLE = (1 << 2),		/* blkdev support discard */
+	SWP_DISCARDING	= (1 << 3),		/* now discarding a free cluster */
+	SWP_SOLIDSTATE	= (1 << 4),		/* blkdev seeks are cheap */
+	SWP_CONTINUED	= (1 << 5),		/* swap_map has count continuation */
+	SWP_BLKDEV	= (1 << 6),		/* its a block device */
+	SWP_ACTIVATED	= (1 << 7),		/* set after swap_activate success */
+	SWP_FS_OPS	= (1 << 8),		/* swapfile operations go through fs */
+	SWP_AREA_DISCARD = (1 << 9),		/* single-time swap area discards */
+	SWP_PAGE_DISCARD = (1 << 10),		/* freed swap page-cluster discards */
+	SWP_STABLE_WRITES = (1 << 11),		/* no overwrite PG_writeback pages */
+	SWP_SYNCHRONOUS_IO = (1 << 12),		/* synchronous IO is efficient */
+	SWP_READ_SYNCHRONOUS_IO = (1 << 13),	/* synchronous IO is efficient */
+						/* add others here before... */
+	SWP_SCANNING	= (1 << 14),		/* refcount in scan_swap_map */
 };
 
 #define SWAP_CLUSTER_MAX 32UL
diff --git a/mm/memory.c b/mm/memory.c
index ebfc9768f801..f531a6bfea5b 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4089,7 +4089,8 @@  vm_fault_t do_swap_page(struct vm_fault *vmf)
 	swapcache = folio;
 
 	if (!folio) {
-		if (data_race(si->flags & SWP_SYNCHRONOUS_IO) &&
+		if ((data_race(si->flags & (SWP_SYNCHRONOUS_IO |
+		    SWP_READ_SYNCHRONOUS_IO))) &&
 		    __swap_count(entry) == 1) {
 			/*
 			 * Prevent parallel swapin from proceeding with
diff --git a/mm/page_io.c b/mm/page_io.c
index ff8c99ee3af7..98a00709e98c 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -499,7 +499,7 @@  static void swap_read_folio_bdev_async(struct folio *folio,
 void swap_read_folio(struct folio *folio, struct swap_iocb **plug)
 {
 	struct swap_info_struct *sis = swp_swap_info(folio->swap);
-	bool synchronous = sis->flags & SWP_SYNCHRONOUS_IO;
+	bool synchronous = sis->flags & (SWP_SYNCHRONOUS_IO | SWP_READ_SYNCHRONOUS_IO);
 	bool workingset = folio_test_workingset(folio);
 	unsigned long pflags;
 	bool in_thrashing;
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 38bdc439651a..7b8feb235aab 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3177,6 +3177,9 @@  SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	if (p->bdev && bdev_synchronous(p->bdev))
 		p->flags |= SWP_SYNCHRONOUS_IO;
 
+	if (p->bdev && bdev_read_synchronous(p->bdev))
+		p->flags |= SWP_READ_SYNCHRONOUS_IO;
+
 	if (p->bdev && bdev_nonrot(p->bdev)) {
 		int cpu, i;
 		unsigned long ci, nr_cluster;