Merge tag 'mm-stable-2022-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:
 "Almost all of MM here. A few things are still getting finished off,
  reviewed, etc.

   - Yang Shi has improved the behaviour of khugepaged collapsing of
     readonly file-backed transparent hugepages.

   - Johannes Weiner has arranged for zswap memory use to be tracked and
     managed on a per-cgroup basis.

   - Munchun Song adds a /proc knob ("hugetlb_optimize_vmemmap") for
     runtime enablement of the recent huge page vmemmap optimization
     feature.

   - Baolin Wang contributes a series to fix some issues around hugetlb
     pagetable invalidation.

   - Zhenwei Pi has fixed some interactions between hwpoisoned pages and
     virtualization.

   - Tong Tiangen has enabled the use of the presently x86-only
     page_table_check debugging feature on arm64 and riscv.

   - David Vernet has done some fixup work on the memcg selftests.

   - Peter Xu has taught userfaultfd to handle write protection faults
     against shmem- and hugetlbfs-backed files.

   - More DAMON development from SeongJae Park - adding online tuning of
     the feature and support for monitoring of fixed virtual address
     ranges. Also easier discovery of which monitoring operations are
     available.

   - Nadav Amit has done some optimization of TLB flushing during
     mprotect().

   - Neil Brown continues to labor away at improving our swap-over-NFS
     support.

   - David Hildenbrand has some fixes to anon page COWing versus
     get_user_pages().

   - Peng Liu fixed some errors in the core hugetlb code.

   - Joao Martins has reduced the amount of memory consumed by
     device-dax's compound devmaps.

   - Some cleanups of the arch-specific pagemap code from Anshuman
     Khandual.

   - Muchun Song has found and fixed some errors in the TLB flushing of
     transparent hugepages.

   - Roman Gushchin has done more work on the memcg selftests.

  ... and, of course, many smaller fixes and cleanups. Notably, the
  customary million cleanup serieses from Miaohe Lin"

* tag 'mm-stable-2022-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (381 commits)
  mm: kfence: use PAGE_ALIGNED helper
  selftests: vm: add the "settings" file with timeout variable
  selftests: vm: add "test_hmm.sh" to TEST_FILES
  selftests: vm: check numa_available() before operating "merge_across_nodes" in ksm_tests
  selftests: vm: add migration to the .gitignore
  selftests/vm/pkeys: fix typo in comment
  ksm: fix typo in comment
  selftests: vm: add process_mrelease tests
  Revert "mm/vmscan: never demote for memcg reclaim"
  mm/kfence: print disabling or re-enabling message
  include/trace/events/percpu.h: cleanup for "percpu: improve percpu_alloc_percpu event trace"
  include/trace/events/mmflags.h: cleanup for "tracing: incorrect gfp_t conversion"
  mm: fix a potential infinite loop in start_isolate_page_range()
  MAINTAINERS: add Muchun as co-maintainer for HugeTLB
  zram: fix Kconfig dependency warning
  mm/shmem: fix shmem folio swapoff hang
  cgroup: fix an error handling path in alloc_pagecache_max_30M()
  mm: damon: use HPAGE_PMD_SIZE
  tracing: incorrect isolate_mote_t cast in mm_vmscan_lru_isolate
  nodemask.h: fix compilation error with GCC12
  ...

1 files changed, 192 insertions, 61 deletions

diff --git a/mm/page_io.c b/mm/page_io.c
index a9444e67ec20..68318134dc92 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -26,6 +26,7 @@
 #include <linux/uio.h>
 #include <linux/sched/task.h>
 #include <linux/delayacct.h>
+#include "swap.h"
 
 void end_swap_bio_write(struct bio *bio)
 {
@@ -234,55 +235,119 @@ static void bio_associate_blkg_from_page(struct bio *bio, struct page *page)
 #define bio_associate_blkg_from_page(bio, page)		do { } while (0)
 #endif /* CONFIG_MEMCG && CONFIG_BLK_CGROUP */
 
-int __swap_writepage(struct page *page, struct writeback_control *wbc,
-		bio_end_io_t end_write_func)
+struct swap_iocb {
+	struct kiocb		iocb;
+	struct bio_vec		bvec[SWAP_CLUSTER_MAX];
+	int			pages;
+	int			len;
+};
+static mempool_t *sio_pool;
+
+int sio_pool_init(void)
 {
-	struct bio *bio;
-	int ret;
-	struct swap_info_struct *sis = page_swap_info(page);
+	if (!sio_pool) {
+		mempool_t *pool = mempool_create_kmalloc_pool(
+			SWAP_CLUSTER_MAX, sizeof(struct swap_iocb));
+		if (cmpxchg(&sio_pool, NULL, pool))
+			mempool_destroy(pool);
+	}
+	if (!sio_pool)
+		return -ENOMEM;
+	return 0;
+}
 
-	VM_BUG_ON_PAGE(!PageSwapCache(page), page);
-	if (data_race(sis->flags & SWP_FS_OPS)) {
-		struct kiocb kiocb;
-		struct file *swap_file = sis->swap_file;
-		struct address_space *mapping = swap_file->f_mapping;
-		struct bio_vec bv = {
-			.bv_page = page,
-			.bv_len  = PAGE_SIZE,
-			.bv_offset = 0
-		};
-		struct iov_iter from;
-
-		iov_iter_bvec(&from, WRITE, &bv, 1, PAGE_SIZE);
-		init_sync_kiocb(&kiocb, swap_file);
-		kiocb.ki_pos = page_file_offset(page);
+static void sio_write_complete(struct kiocb *iocb, long ret)
+{
+	struct swap_iocb *sio = container_of(iocb, struct swap_iocb, iocb);
+	struct page *page = sio->bvec[0].bv_page;
+	int p;
 
-		set_page_writeback(page);
-		unlock_page(page);
-		ret = mapping->a_ops->direct_IO(&kiocb, &from);
-		if (ret == PAGE_SIZE) {
-			count_vm_event(PSWPOUT);
-			ret = 0;
-		} else {
-			/*
-			 * In the case of swap-over-nfs, this can be a
-			 * temporary failure if the system has limited
-			 * memory for allocating transmit buffers.
-			 * Mark the page dirty and avoid
-			 * folio_rotate_reclaimable but rate-limit the
-			 * messages but do not flag PageError like
-			 * the normal direct-to-bio case as it could
-			 * be temporary.
-			 */
+	if (ret != sio->len) {
+		/*
+		 * In the case of swap-over-nfs, this can be a
+		 * temporary failure if the system has limited
+		 * memory for allocating transmit buffers.
+		 * Mark the page dirty and avoid
+		 * folio_rotate_reclaimable but rate-limit the
+		 * messages but do not flag PageError like
+		 * the normal direct-to-bio case as it could
+		 * be temporary.
+		 */
+		pr_err_ratelimited("Write error %ld on dio swapfile (%llu)\n",
+				   ret, page_file_offset(page));
+		for (p = 0; p < sio->pages; p++) {
+			page = sio->bvec[p].bv_page;
 			set_page_dirty(page);
 			ClearPageReclaim(page);
-			pr_err_ratelimited("Write error on dio swapfile (%llu)\n",
-					   page_file_offset(page));
 		}
-		end_page_writeback(page);
-		return ret;
+	} else {
+		for (p = 0; p < sio->pages; p++)
+			count_swpout_vm_event(sio->bvec[p].bv_page);
 	}
 
+	for (p = 0; p < sio->pages; p++)
+		end_page_writeback(sio->bvec[p].bv_page);
+
+	mempool_free(sio, sio_pool);
+}
+
+static int swap_writepage_fs(struct page *page, struct writeback_control *wbc)
+{
+	struct swap_iocb *sio = NULL;
+	struct swap_info_struct *sis = page_swap_info(page);
+	struct file *swap_file = sis->swap_file;
+	loff_t pos = page_file_offset(page);
+
+	set_page_writeback(page);
+	unlock_page(page);
+	if (wbc->swap_plug)
+		sio = *wbc->swap_plug;
+	if (sio) {
+		if (sio->iocb.ki_filp != swap_file ||
+		    sio->iocb.ki_pos + sio->len != pos) {
+			swap_write_unplug(sio);
+			sio = NULL;
+		}
+	}
+	if (!sio) {
+		sio = mempool_alloc(sio_pool, GFP_NOIO);
+		init_sync_kiocb(&sio->iocb, swap_file);
+		sio->iocb.ki_complete = sio_write_complete;
+		sio->iocb.ki_pos = pos;
+		sio->pages = 0;
+		sio->len = 0;
+	}
+	sio->bvec[sio->pages].bv_page = page;
+	sio->bvec[sio->pages].bv_len = thp_size(page);
+	sio->bvec[sio->pages].bv_offset = 0;
+	sio->len += thp_size(page);
+	sio->pages += 1;
+	if (sio->pages == ARRAY_SIZE(sio->bvec) || !wbc->swap_plug) {
+		swap_write_unplug(sio);
+		sio = NULL;
+	}
+	if (wbc->swap_plug)
+		*wbc->swap_plug = sio;
+
+	return 0;
+}
+
+int __swap_writepage(struct page *page, struct writeback_control *wbc,
+		     bio_end_io_t end_write_func)
+{
+	struct bio *bio;
+	int ret;
+	struct swap_info_struct *sis = page_swap_info(page);
+
+	VM_BUG_ON_PAGE(!PageSwapCache(page), page);
+	/*
+	 * ->flags can be updated non-atomicially (scan_swap_map_slots),
+	 * but that will never affect SWP_FS_OPS, so the data_race
+	 * is safe.
+	 */
+	if (data_race(sis->flags & SWP_FS_OPS))
+		return swap_writepage_fs(page, wbc);
+
 	ret = bdev_write_page(sis->bdev, swap_page_sector(page), page, wbc);
 	if (!ret) {
 		count_swpout_vm_event(page);
@@ -305,7 +370,83 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
 	return 0;
 }
 
-int swap_readpage(struct page *page, bool synchronous)
+void swap_write_unplug(struct swap_iocb *sio)
+{
+	struct iov_iter from;
+	struct address_space *mapping = sio->iocb.ki_filp->f_mapping;
+	int ret;
+
+	iov_iter_bvec(&from, WRITE, sio->bvec, sio->pages, sio->len);
+	ret = mapping->a_ops->swap_rw(&sio->iocb, &from);
+	if (ret != -EIOCBQUEUED)
+		sio_write_complete(&sio->iocb, ret);
+}
+
+static void sio_read_complete(struct kiocb *iocb, long ret)
+{
+	struct swap_iocb *sio = container_of(iocb, struct swap_iocb, iocb);
+	int p;
+
+	if (ret == sio->len) {
+		for (p = 0; p < sio->pages; p++) {
+			struct page *page = sio->bvec[p].bv_page;
+
+			SetPageUptodate(page);
+			unlock_page(page);
+		}
+		count_vm_events(PSWPIN, sio->pages);
+	} else {
+		for (p = 0; p < sio->pages; p++) {
+			struct page *page = sio->bvec[p].bv_page;
+
+			SetPageError(page);
+			ClearPageUptodate(page);
+			unlock_page(page);
+		}
+		pr_alert_ratelimited("Read-error on swap-device\n");
+	}
+	mempool_free(sio, sio_pool);
+}
+
+static void swap_readpage_fs(struct page *page,
+			     struct swap_iocb **plug)
+{
+	struct swap_info_struct *sis = page_swap_info(page);
+	struct swap_iocb *sio = NULL;
+	loff_t pos = page_file_offset(page);
+
+	if (plug)
+		sio = *plug;
+	if (sio) {
+		if (sio->iocb.ki_filp != sis->swap_file ||
+		    sio->iocb.ki_pos + sio->len != pos) {
+			swap_read_unplug(sio);
+			sio = NULL;
+		}
+	}
+	if (!sio) {
+		sio = mempool_alloc(sio_pool, GFP_KERNEL);
+		init_sync_kiocb(&sio->iocb, sis->swap_file);
+		sio->iocb.ki_pos = pos;
+		sio->iocb.ki_complete = sio_read_complete;
+		sio->pages = 0;
+		sio->len = 0;
+	}
+	sio->bvec[sio->pages].bv_page = page;
+	sio->bvec[sio->pages].bv_len = thp_size(page);
+	sio->bvec[sio->pages].bv_offset = 0;
+	sio->len += thp_size(page);
+	sio->pages += 1;
+	if (sio->pages == ARRAY_SIZE(sio->bvec) || !plug) {
+		swap_read_unplug(sio);
+		sio = NULL;
+	}
+	if (plug)
+		*plug = sio;
+}
+
+int swap_readpage(struct page *page, bool synchronous,
+		  struct swap_iocb **plug)
 {
 	struct bio *bio;
 	int ret = 0;
@@ -333,12 +474,7 @@ int swap_readpage(struct page *page, bool synchronous)
 	}
 
 	if (data_race(sis->flags & SWP_FS_OPS)) {
-		struct file *swap_file = sis->swap_file;
-		struct address_space *mapping = swap_file->f_mapping;
-
-		ret = mapping->a_ops->read_folio(swap_file, page_folio(page));
-		if (!ret)
-			count_vm_event(PSWPIN);
+		swap_readpage_fs(page, plug);
 		goto out;
 	}
 
@@ -383,19 +519,14 @@ out:
 	return ret;
 }
 
-bool swap_dirty_folio(struct address_space *mapping, struct folio *folio)
+void __swap_read_unplug(struct swap_iocb *sio)
 {
-	struct swap_info_struct *sis = swp_swap_info(folio_swap_entry(folio));
-
-	if (data_race(sis->flags & SWP_FS_OPS)) {
-		const struct address_space_operations *aops;
-
-		mapping = sis->swap_file->f_mapping;
-		aops = mapping->a_ops;
+	struct iov_iter from;
+	struct address_space *mapping = sio->iocb.ki_filp->f_mapping;
+	int ret;
 
-		VM_BUG_ON_FOLIO(!folio_test_swapcache(folio), folio);
-		return aops->dirty_folio(mapping, folio);
-	} else {
-		return noop_dirty_folio(mapping, folio);
-	}
+	iov_iter_bvec(&from, READ, sio->bvec, sio->pages, sio->len);
+	ret = mapping->a_ops->swap_rw(&sio->iocb, &from);
+	if (ret != -EIOCBQUEUED)
+		sio_read_complete(&sio->iocb, ret);
 }