Merge tag 'for-6.9-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "Mostly stabilization, refactoring and cleanup changes. There rest are
  minor performance optimizations due to caching or lock contention
  reduction and a few notable fixes.

  Performance improvements:

   - minor speedup in logging when repeatedly allocated structure is
     preallocated only once, improves latency and decreases lock
     contention

   - minor throughput increase (+6%), reduced lock contention after
     clearing delayed allocation bits, applies to several common
     workload types

   - skip full quota rescan if a new relation is added in the same
     transaction

  Fixes:

   - zstd fix for inline compressed file in subpage mode, updated
     version from the 6.8 time

   - proper qgroup inheritance ioctl parameter validation

   - more fiemap followup fixes after reduced locking done in 6.8:
      - fix race when detecting delalloc ranges

  Core changes:

   - more debugging code:
      - added assertions for a very rare crash in raid56 calculation
      - tree-checker dumps page state to give more insights into
        possible reference counting issues

   - add checksum calculation offloading sysfs knob, for now enabled
     under DEBUG only to determine a good heuristic for deciding the
     offload or synchronous, depends on various factors (block group
     profile, device speed) and is not as clear as initially thought
     (checksum type)

   - error handling improvements, added assertions

   - more page to folio conversion (defrag, truncate), cached size and
     shift

   - preparation for more fine grained locking of sectors in subpage
     mode

   - cleanups and refactoring:
      - include cleanups, forward declarations
      - pointer-to-structure helpers
      - redundant argument removals
      - removed unused code
      - slab cache updates, last use of SLAB_MEM_SPREAD removed"

* tag 'for-6.9-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (114 commits)
  btrfs: reuse cloned extent buffer during fiemap to avoid re-allocations
  btrfs: fix race when detecting delalloc ranges during fiemap
  btrfs: fix off-by-one chunk length calculation at contains_pending_extent()
  btrfs: qgroup: allow quick inherit if snapshot is created and added to the same parent
  btrfs: qgroup: validate btrfs_qgroup_inherit parameter
  btrfs: include device major and minor numbers in the device scan notice
  btrfs: mark btrfs_put_caching_control() static
  btrfs: remove SLAB_MEM_SPREAD flag use
  btrfs: qgroup: always free reserved space for extent records
  btrfs: tree-checker: dump the page status if hit something wrong
  btrfs: compression: remove dead comments in btrfs_compress_heuristic()
  btrfs: subpage: make writer lock utilize bitmap
  btrfs: subpage: make reader lock utilize bitmap
  btrfs: unexport btrfs_subpage_start_writer() and btrfs_subpage_end_and_test_writer()
  btrfs: pass a valid extent map cache pointer to __get_extent_map()
  btrfs: merge btrfs_del_delalloc_inode() helpers
  btrfs: pass btrfs_device to btrfs_scratch_superblocks()
  btrfs: handle transaction commit errors in flush_reservations()
  btrfs: use KMEM_CACHE() to create btrfs_free_space cache
  btrfs: use KMEM_CACHE() to create delayed ref caches
  ...

1 files changed, 50 insertions, 54 deletions

diff --git a/fs/btrfs/defrag.c b/fs/btrfs/defrag.c
index 5b0b64571418..f015fa1b6301 100644
--- a/fs/btrfs/defrag.c
+++ b/fs/btrfs/defrag.c
@@ -6,7 +6,6 @@
 #include <linux/sched.h>
 #include "ctree.h"
 #include "disk-io.h"
-#include "print-tree.h"
 #include "transaction.h"
 #include "locking.h"
 #include "accessors.h"
@@ -521,7 +520,7 @@ static int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
 	 * keep_locks set and lowest_level is 1, regardless of the value of
 	 * path->slots[1].
 	 */
-	BUG_ON(path->locks[1] == 0);
+	ASSERT(path->locks[1] != 0);
 	ret = btrfs_realloc_node(trans, root,
 				 path->nodes[1], 0,
 				 &last_ret,
@@ -810,7 +809,7 @@ static u32 get_extent_max_capacity(const struct btrfs_fs_info *fs_info,
 static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em,
 				     u32 extent_thresh, u64 newer_than, bool locked)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	struct extent_map *next;
 	bool ret = false;
 
@@ -861,20 +860,21 @@ out:
  * NOTE: Caller should also wait for page writeback after the cluster is
  * prepared, here we don't do writeback wait for each page.
  */
-static struct page *defrag_prepare_one_page(struct btrfs_inode *inode, pgoff_t index)
+static struct folio *defrag_prepare_one_folio(struct btrfs_inode *inode, pgoff_t index)
 {
 	struct address_space *mapping = inode->vfs_inode.i_mapping;
 	gfp_t mask = btrfs_alloc_write_mask(mapping);
 	u64 page_start = (u64)index << PAGE_SHIFT;
 	u64 page_end = page_start + PAGE_SIZE - 1;
 	struct extent_state *cached_state = NULL;
-	struct page *page;
+	struct folio *folio;
 	int ret;
 
 again:
-	page = find_or_create_page(mapping, index, mask);
-	if (!page)
-		return ERR_PTR(-ENOMEM);
+	folio = __filemap_get_folio(mapping, index,
+				    FGP_LOCK | FGP_ACCESSED | FGP_CREAT, mask);
+	if (IS_ERR(folio))
+		return folio;
 
 	/*
 	 * Since we can defragment files opened read-only, we can encounter
@@ -884,16 +884,16 @@ again:
 	 * executables that explicitly enable them, so this isn't very
 	 * restrictive.
 	 */
-	if (PageCompound(page)) {
-		unlock_page(page);
-		put_page(page);
+	if (folio_test_large(folio)) {
+		folio_unlock(folio);
+		folio_put(folio);
 		return ERR_PTR(-ETXTBSY);
 	}
 
-	ret = set_page_extent_mapped(page);
+	ret = set_folio_extent_mapped(folio);
 	if (ret < 0) {
-		unlock_page(page);
-		put_page(page);
+		folio_unlock(folio);
+		folio_put(folio);
 		return ERR_PTR(ret);
 	}
 
@@ -908,17 +908,17 @@ again:
 		if (!ordered)
 			break;
 
-		unlock_page(page);
+		folio_unlock(folio);
 		btrfs_start_ordered_extent(ordered);
 		btrfs_put_ordered_extent(ordered);
-		lock_page(page);
+		folio_lock(folio);
 		/*
-		 * We unlocked the page above, so we need check if it was
+		 * We unlocked the folio above, so we need check if it was
 		 * released or not.
 		 */
-		if (page->mapping != mapping || !PagePrivate(page)) {
-			unlock_page(page);
-			put_page(page);
+		if (folio->mapping != mapping || !folio->private) {
+			folio_unlock(folio);
+			folio_put(folio);
 			goto again;
 		}
 	}
@@ -927,21 +927,21 @@ again:
 	 * Now the page range has no ordered extent any more.  Read the page to
 	 * make it uptodate.
 	 */
-	if (!PageUptodate(page)) {
-		btrfs_read_folio(NULL, page_folio(page));
-		lock_page(page);
-		if (page->mapping != mapping || !PagePrivate(page)) {
-			unlock_page(page);
-			put_page(page);
+	if (!folio_test_uptodate(folio)) {
+		btrfs_read_folio(NULL, folio);
+		folio_lock(folio);
+		if (folio->mapping != mapping || !folio->private) {
+			folio_unlock(folio);
+			folio_put(folio);
 			goto again;
 		}
-		if (!PageUptodate(page)) {
-			unlock_page(page);
-			put_page(page);
+		if (!folio_test_uptodate(folio)) {
+			folio_unlock(folio);
+			folio_put(folio);
 			return ERR_PTR(-EIO);
 		}
 	}
-	return page;
+	return folio;
 }
 
 struct defrag_target_range {
@@ -1162,7 +1162,7 @@ static_assert(PAGE_ALIGNED(CLUSTER_SIZE));
  */
 static int defrag_one_locked_target(struct btrfs_inode *inode,
 				    struct defrag_target_range *target,
-				    struct page **pages, int nr_pages,
+				    struct folio **folios, int nr_pages,
 				    struct extent_state **cached_state)
 {
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
@@ -1171,7 +1171,7 @@ static int defrag_one_locked_target(struct btrfs_inode *inode,
 	const u64 len = target->len;
 	unsigned long last_index = (start + len - 1) >> PAGE_SHIFT;
 	unsigned long start_index = start >> PAGE_SHIFT;
-	unsigned long first_index = page_index(pages[0]);
+	unsigned long first_index = folios[0]->index;
 	int ret = 0;
 	int i;
 
@@ -1188,8 +1188,8 @@ static int defrag_one_locked_target(struct btrfs_inode *inode,
 
 	/* Update the page status */
 	for (i = start_index - first_index; i <= last_index - first_index; i++) {
-		ClearPageChecked(pages[i]);
-		btrfs_folio_clamp_set_dirty(fs_info, page_folio(pages[i]), start, len);
+		folio_clear_checked(folios[i]);
+		btrfs_folio_clamp_set_dirty(fs_info, folios[i], start, len);
 	}
 	btrfs_delalloc_release_extents(inode, len);
 	extent_changeset_free(data_reserved);
@@ -1205,7 +1205,7 @@ static int defrag_one_range(struct btrfs_inode *inode, u64 start, u32 len,
 	struct defrag_target_range *entry;
 	struct defrag_target_range *tmp;
 	LIST_HEAD(target_list);
-	struct page **pages;
+	struct folio **folios;
 	const u32 sectorsize = inode->root->fs_info->sectorsize;
 	u64 last_index = (start + len - 1) >> PAGE_SHIFT;
 	u64 start_index = start >> PAGE_SHIFT;
@@ -1216,21 +1216,21 @@ static int defrag_one_range(struct btrfs_inode *inode, u64 start, u32 len,
 	ASSERT(nr_pages <= CLUSTER_SIZE / PAGE_SIZE);
 	ASSERT(IS_ALIGNED(start, sectorsize) && IS_ALIGNED(len, sectorsize));
 
-	pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS);
-	if (!pages)
+	folios = kcalloc(nr_pages, sizeof(struct folio *), GFP_NOFS);
+	if (!folios)
 		return -ENOMEM;
 
 	/* Prepare all pages */
 	for (i = 0; i < nr_pages; i++) {
-		pages[i] = defrag_prepare_one_page(inode, start_index + i);
-		if (IS_ERR(pages[i])) {
-			ret = PTR_ERR(pages[i]);
-			pages[i] = NULL;
-			goto free_pages;
+		folios[i] = defrag_prepare_one_folio(inode, start_index + i);
+		if (IS_ERR(folios[i])) {
+			ret = PTR_ERR(folios[i]);
+			nr_pages = i;
+			goto free_folios;
 		}
 	}
 	for (i = 0; i < nr_pages; i++)
-		wait_on_page_writeback(pages[i]);
+		folio_wait_writeback(folios[i]);
 
 	/* Lock the pages range */
 	lock_extent(&inode->io_tree, start_index << PAGE_SHIFT,
@@ -1250,7 +1250,7 @@ static int defrag_one_range(struct btrfs_inode *inode, u64 start, u32 len,
 		goto unlock_extent;
 
 	list_for_each_entry(entry, &target_list, list) {
-		ret = defrag_one_locked_target(inode, entry, pages, nr_pages,
+		ret = defrag_one_locked_target(inode, entry, folios, nr_pages,
 					       &cached_state);
 		if (ret < 0)
 			break;
@@ -1264,14 +1264,12 @@ unlock_extent:
 	unlock_extent(&inode->io_tree, start_index << PAGE_SHIFT,
 		      (last_index << PAGE_SHIFT) + PAGE_SIZE - 1,
 		      &cached_state);
-free_pages:
+free_folios:
 	for (i = 0; i < nr_pages; i++) {
-		if (pages[i]) {
-			unlock_page(pages[i]);
-			put_page(pages[i]);
-		}
+		folio_unlock(folios[i]);
+		folio_put(folios[i]);
 	}
-	kfree(pages);
+	kfree(folios);
 	return ret;
 }
 
@@ -1366,7 +1364,7 @@ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra,
 		      struct btrfs_ioctl_defrag_range_args *range,
 		      u64 newer_than, unsigned long max_to_defrag)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
 	unsigned long sectors_defragged = 0;
 	u64 isize = i_size_read(inode);
 	u64 cur;
@@ -1512,9 +1510,7 @@ void __cold btrfs_auto_defrag_exit(void)
 int __init btrfs_auto_defrag_init(void)
 {
 	btrfs_inode_defrag_cachep = kmem_cache_create("btrfs_inode_defrag",
-					sizeof(struct inode_defrag), 0,
-					SLAB_MEM_SPREAD,
-					NULL);
+					sizeof(struct inode_defrag), 0, 0, NULL);
 	if (!btrfs_inode_defrag_cachep)
 		return -ENOMEM;