Merge tag 'xfs-6.9-merge-8' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs updates from Chandan Babu:

 - Online repair updates:
    - More ondisk structures being repaired:
        - Inode's mode field by trying to obtain file type value from
          the a directory entry
        - Quota counters
        - Link counts of inodes
        - FS summary counters
        - Support for in-memory btrees has been added to support repair
          of rmap btrees
    - Misc changes:
        - Report corruption of metadata to the health tracking subsystem
        - Enable indirect health reporting when resources are scarce
        - Reduce memory usage while repairing refcount btree
        - Extend "Bmap update" intent item to support atomic extent
          swapping on the realtime device
        - Extend "Bmap update" intent item to support extended attribute
          fork and unwritten extents
    - Code cleanups:
        - Bmap log intent
        - Btree block pointer checking
        - Btree readahead
        - Buffer target
        - Symbolic link code

 - Remove mrlock wrapper around the rwsem

 - Convert all the GFP_NOFS flag usages to use the scoped
   memalloc_nofs_save() API instead of direct calls with the GFP_NOFS

 - Refactor and simplify xfile abstraction. Lower level APIs in shmem.c
   are required to be exported in order to achieve this

 - Skip checking alignment constraints for inode chunk allocations when
   block size is larger than inode chunk size

 - Do not submit delwri buffers collected during log recovery when an
   error has been encountered

 - Fix SEEK_HOLE/DATA for file regions which have active COW extents

 - Fix lock order inversion when executing error handling path during
   shrinking a filesystem

 - Remove duplicate ifdefs

* tag 'xfs-6.9-merge-8' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (183 commits)
  xfs: shrink failure needs to hold AGI buffer
  mm/shmem.c: Use new form of *@param in kernel-doc
  kernel-doc: Add unary operator * to $type_param_ref
  xfs: use kvfree() in xlog_cil_free_logvec()
  xfs: xfs_btree_bload_prep_block() should use __GFP_NOFAIL
  xfs: fix scrub stats file permissions
  xfs: fix log recovery erroring out on refcount recovery failure
  xfs: move symlink target write function to libxfs
  xfs: move remote symlink target read function to libxfs
  xfs: move xfs_symlink_remote.c declarations to xfs_symlink_remote.h
  xfs: xfs_bmap_finish_one should map unwritten extents properly
  xfs: support deferred bmap updates on the attr fork
  xfs: support recovering bmap intent items targetting realtime extents
  xfs: add a realtime flag to the bmap update log redo items
  xfs: add a xattr_entry helper
  xfs: fix xfs_bunmapi to allow unmapping of partial rt extents
  xfs: move xfs_bmap_defer_add to xfs_bmap_item.c
  xfs: reuse xfs_bmap_update_cancel_item
  xfs: add a bi_entry helper
  xfs: remove xfs_trans_set_bmap_flags
  ...

4 files changed, 51 insertions, 5 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 8df4797c5287..fef125d9508b 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -124,6 +124,15 @@
  *    ->private_lock		(zap_pte_range->block_dirty_folio)
  */
 
+static void mapping_set_update(struct xa_state *xas,
+		struct address_space *mapping)
+{
+	if (dax_mapping(mapping) || shmem_mapping(mapping))
+		return;
+	xas_set_update(xas, workingset_update_node);
+	xas_set_lru(xas, &shadow_nodes);
+}
+
 static void page_cache_delete(struct address_space *mapping,
 				   struct folio *folio, void *shadow)
 {
diff --git a/mm/internal.h b/mm/internal.h
index f309a010d50f..4398f572485f 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1266,4 +1266,8 @@ static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry,
 }
 #endif /* CONFIG_SHRINKER_DEBUG */
 
+/* Only track the nodes of mappings with shadow entries */
+void workingset_update_node(struct xa_node *node);
+extern struct list_lru shadow_nodes;
+
 #endif	/* __MM_INTERNAL_H */
diff --git a/mm/shmem.c b/mm/shmem.c
index 29d5a024df48..be890844fc92 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -254,7 +254,7 @@ static void shmem_inode_unacct_blocks(struct inode *inode, long pages)
 }
 
 static const struct super_operations shmem_ops;
-const struct address_space_operations shmem_aops;
+static const struct address_space_operations shmem_aops;
 static const struct file_operations shmem_file_operations;
 static const struct inode_operations shmem_inode_operations;
 static const struct inode_operations shmem_dir_inode_operations;
@@ -263,6 +263,12 @@ static const struct vm_operations_struct shmem_vm_ops;
 static const struct vm_operations_struct shmem_anon_vm_ops;
 static struct file_system_type shmem_fs_type;
 
+bool shmem_mapping(struct address_space *mapping)
+{
+	return mapping->a_ops == &shmem_aops;
+}
+EXPORT_SYMBOL_GPL(shmem_mapping);
+
 bool vma_is_anon_shmem(struct vm_area_struct *vma)
 {
 	return vma->vm_ops == &shmem_anon_vm_ops;
@@ -1966,6 +1972,9 @@ static int shmem_get_folio_gfp(struct inode *inode, pgoff_t index,
 	int error;
 	bool alloced;
 
+	if (WARN_ON_ONCE(!shmem_mapping(inode->i_mapping)))
+		return -EINVAL;
+
 	if (index > (MAX_LFS_FILESIZE >> PAGE_SHIFT))
 		return -EFBIG;
 repeat:
@@ -2128,12 +2137,36 @@ unlock:
 	return error;
 }
 
+/**
+ * shmem_get_folio - find, and lock a shmem folio.
+ * @inode:	inode to search
+ * @index:	the page index.
+ * @foliop:	pointer to the folio if found
+ * @sgp:	SGP_* flags to control behavior
+ *
+ * Looks up the page cache entry at @inode & @index.  If a folio is
+ * present, it is returned locked with an increased refcount.
+ *
+ * If the caller modifies data in the folio, it must call folio_mark_dirty()
+ * before unlocking the folio to ensure that the folio is not reclaimed.
+ * There is no need to reserve space before calling folio_mark_dirty().
+ *
+ * When no folio is found, the behavior depends on @sgp:
+ *  - for SGP_READ, *@foliop is %NULL and 0 is returned
+ *  - for SGP_NOALLOC, *@foliop is %NULL and -ENOENT is returned
+ *  - for all other flags a new folio is allocated, inserted into the
+ *    page cache and returned locked in @foliop.
+ *
+ * Context: May sleep.
+ * Return: 0 if successful, else a negative error code.
+ */
 int shmem_get_folio(struct inode *inode, pgoff_t index, struct folio **foliop,
 		enum sgp_type sgp)
 {
 	return shmem_get_folio_gfp(inode, index, foliop, sgp,
 			mapping_gfp_mask(inode->i_mapping), NULL, NULL);
 }
+EXPORT_SYMBOL_GPL(shmem_get_folio);
 
 /*
  * This is like autoremove_wake_function, but it removes the wait queue
@@ -3500,10 +3533,10 @@ static int shmem_symlink(struct mnt_idmap *idmap, struct inode *dir,
 		inode->i_op = &shmem_short_symlink_operations;
 	} else {
 		inode_nohighmem(inode);
+		inode->i_mapping->a_ops = &shmem_aops;
 		error = shmem_get_folio(inode, 0, &folio, SGP_WRITE);
 		if (error)
 			goto out_remove_offset;
-		inode->i_mapping->a_ops = &shmem_aops;
 		inode->i_op = &shmem_symlink_inode_operations;
 		memcpy(folio_address(folio), symname, len);
 		folio_mark_uptodate(folio);
@@ -4468,7 +4501,7 @@ static int shmem_error_remove_folio(struct address_space *mapping,
 	return 0;
 }
 
-const struct address_space_operations shmem_aops = {
+static const struct address_space_operations shmem_aops = {
 	.writepage	= shmem_writepage,
 	.dirty_folio	= noop_dirty_folio,
 #ifdef CONFIG_TMPFS
@@ -4480,7 +4513,6 @@ const struct address_space_operations shmem_aops = {
 #endif
 	.error_remove_folio = shmem_error_remove_folio,
 };
-EXPORT_SYMBOL(shmem_aops);
 
 static const struct file_operations shmem_file_operations = {
 	.mmap		= shmem_mmap,
@@ -4835,6 +4867,7 @@ struct file *shmem_kernel_file_setup(const char *name, loff_t size, unsigned lon
 {
 	return __shmem_file_setup(shm_mnt, name, size, flags, S_PRIVATE);
 }
+EXPORT_SYMBOL_GPL(shmem_kernel_file_setup);
 
 /**
  * shmem_file_setup - get an unlinked file living in tmpfs
@@ -4912,7 +4945,6 @@ struct folio *shmem_read_folio_gfp(struct address_space *mapping,
 	struct folio *folio;
 	int error;
 
-	BUG_ON(!shmem_mapping(mapping));
 	error = shmem_get_folio_gfp(inode, index, &folio, SGP_CACHE,
 				    gfp, NULL, NULL);
 	if (error)
diff --git a/mm/workingset.c b/mm/workingset.c
index 226012974328..f2a0ecaf708d 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -16,6 +16,7 @@
 #include <linux/dax.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include "internal.h"
 
 /*
  *		Double CLOCK lists