1 files changed, 133 insertions, 44 deletions

diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h
index f8bb73d6ab68..b572d6b9730b 100644
--- a/fs/btrfs/fs.h
+++ b/fs/btrfs/fs.h
@@ -4,14 +4,49 @@
 #define BTRFS_FS_H
 
 #include <linux/blkdev.h>
-#include <linux/fs.h>
-#include <linux/btrfs_tree.h>
 #include <linux/sizes.h>
+#include <linux/time64.h>
+#include <linux/compiler.h>
+#include <linux/math.h>
+#include <linux/atomic.h>
+#include <linux/percpu_counter.h>
+#include <linux/completion.h>
+#include <linux/lockdep.h>
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+#include <linux/rwsem.h>
+#include <linux/semaphore.h>
+#include <linux/list.h>
+#include <linux/pagemap.h>
+#include <linux/radix-tree.h>
+#include <linux/workqueue.h>
+#include <linux/wait.h>
+#include <linux/wait_bit.h>
+#include <linux/sched.h>
+#include <linux/rbtree.h>
+#include <uapi/linux/btrfs.h>
+#include <uapi/linux/btrfs_tree.h>
 #include "extent-io-tree.h"
-#include "extent_map.h"
 #include "async-thread.h"
 #include "block-rsv.h"
 
+struct inode;
+struct super_block;
+struct kobject;
+struct reloc_control;
+struct crypto_shash;
+struct ulist;
+struct btrfs_device;
+struct btrfs_block_group;
+struct btrfs_root;
+struct btrfs_fs_devices;
+struct btrfs_transaction;
+struct btrfs_delayed_root;
+struct btrfs_balance_control;
+struct btrfs_subpage_info;
+struct btrfs_stripe_hash_table;
+struct btrfs_space_info;
+
 #define BTRFS_MAX_EXTENT_SIZE SZ_128M
 
 #define BTRFS_OLDEST_GENERATION	0ULL
@@ -63,7 +98,9 @@ enum {
 	/* The btrfs_fs_info created for self-tests */
 	BTRFS_FS_STATE_DUMMY_FS_INFO,
 
-	BTRFS_FS_STATE_NO_CSUMS,
+	/* Checksum errors are ignored. */
+	BTRFS_FS_STATE_NO_DATA_CSUMS,
+	BTRFS_FS_STATE_SKIP_META_CSUMS,
 
 	/* Indicates there was an error cleaning up a log tree. */
 	BTRFS_FS_STATE_LOG_CLEANUP_ERROR,
@@ -158,37 +195,39 @@ enum {
  * Note: don't forget to add new options to btrfs_show_options()
  */
 enum {
-	BTRFS_MOUNT_NODATASUM			= (1UL << 0),
-	BTRFS_MOUNT_NODATACOW			= (1UL << 1),
-	BTRFS_MOUNT_NOBARRIER			= (1UL << 2),
-	BTRFS_MOUNT_SSD				= (1UL << 3),
-	BTRFS_MOUNT_DEGRADED			= (1UL << 4),
-	BTRFS_MOUNT_COMPRESS			= (1UL << 5),
-	BTRFS_MOUNT_NOTREELOG   		= (1UL << 6),
-	BTRFS_MOUNT_FLUSHONCOMMIT		= (1UL << 7),
-	BTRFS_MOUNT_SSD_SPREAD			= (1UL << 8),
-	BTRFS_MOUNT_NOSSD			= (1UL << 9),
-	BTRFS_MOUNT_DISCARD_SYNC		= (1UL << 10),
-	BTRFS_MOUNT_FORCE_COMPRESS      	= (1UL << 11),
-	BTRFS_MOUNT_SPACE_CACHE			= (1UL << 12),
-	BTRFS_MOUNT_CLEAR_CACHE			= (1UL << 13),
-	BTRFS_MOUNT_USER_SUBVOL_RM_ALLOWED	= (1UL << 14),
-	BTRFS_MOUNT_ENOSPC_DEBUG		= (1UL << 15),
-	BTRFS_MOUNT_AUTO_DEFRAG			= (1UL << 16),
-	BTRFS_MOUNT_USEBACKUPROOT		= (1UL << 17),
-	BTRFS_MOUNT_SKIP_BALANCE		= (1UL << 18),
-	BTRFS_MOUNT_PANIC_ON_FATAL_ERROR	= (1UL << 19),
-	BTRFS_MOUNT_RESCAN_UUID_TREE		= (1UL << 20),
-	BTRFS_MOUNT_FRAGMENT_DATA		= (1UL << 21),
-	BTRFS_MOUNT_FRAGMENT_METADATA		= (1UL << 22),
-	BTRFS_MOUNT_FREE_SPACE_TREE		= (1UL << 23),
-	BTRFS_MOUNT_NOLOGREPLAY			= (1UL << 24),
-	BTRFS_MOUNT_REF_VERIFY			= (1UL << 25),
-	BTRFS_MOUNT_DISCARD_ASYNC		= (1UL << 26),
-	BTRFS_MOUNT_IGNOREBADROOTS		= (1UL << 27),
-	BTRFS_MOUNT_IGNOREDATACSUMS		= (1UL << 28),
-	BTRFS_MOUNT_NODISCARD			= (1UL << 29),
-	BTRFS_MOUNT_NOSPACECACHE		= (1UL << 30),
+	BTRFS_MOUNT_NODATASUM			= (1ULL << 0),
+	BTRFS_MOUNT_NODATACOW			= (1ULL << 1),
+	BTRFS_MOUNT_NOBARRIER			= (1ULL << 2),
+	BTRFS_MOUNT_SSD				= (1ULL << 3),
+	BTRFS_MOUNT_DEGRADED			= (1ULL << 4),
+	BTRFS_MOUNT_COMPRESS			= (1ULL << 5),
+	BTRFS_MOUNT_NOTREELOG			= (1ULL << 6),
+	BTRFS_MOUNT_FLUSHONCOMMIT		= (1ULL << 7),
+	BTRFS_MOUNT_SSD_SPREAD			= (1ULL << 8),
+	BTRFS_MOUNT_NOSSD			= (1ULL << 9),
+	BTRFS_MOUNT_DISCARD_SYNC		= (1ULL << 10),
+	BTRFS_MOUNT_FORCE_COMPRESS		= (1ULL << 11),
+	BTRFS_MOUNT_SPACE_CACHE			= (1ULL << 12),
+	BTRFS_MOUNT_CLEAR_CACHE			= (1ULL << 13),
+	BTRFS_MOUNT_USER_SUBVOL_RM_ALLOWED	= (1ULL << 14),
+	BTRFS_MOUNT_ENOSPC_DEBUG		= (1ULL << 15),
+	BTRFS_MOUNT_AUTO_DEFRAG			= (1ULL << 16),
+	BTRFS_MOUNT_USEBACKUPROOT		= (1ULL << 17),
+	BTRFS_MOUNT_SKIP_BALANCE		= (1ULL << 18),
+	BTRFS_MOUNT_PANIC_ON_FATAL_ERROR	= (1ULL << 19),
+	BTRFS_MOUNT_RESCAN_UUID_TREE		= (1ULL << 20),
+	BTRFS_MOUNT_FRAGMENT_DATA		= (1ULL << 21),
+	BTRFS_MOUNT_FRAGMENT_METADATA		= (1ULL << 22),
+	BTRFS_MOUNT_FREE_SPACE_TREE		= (1ULL << 23),
+	BTRFS_MOUNT_NOLOGREPLAY			= (1ULL << 24),
+	BTRFS_MOUNT_REF_VERIFY			= (1ULL << 25),
+	BTRFS_MOUNT_DISCARD_ASYNC		= (1ULL << 26),
+	BTRFS_MOUNT_IGNOREBADROOTS		= (1ULL << 27),
+	BTRFS_MOUNT_IGNOREDATACSUMS		= (1ULL << 28),
+	BTRFS_MOUNT_NODISCARD			= (1ULL << 29),
+	BTRFS_MOUNT_NOSPACECACHE		= (1ULL << 30),
+	BTRFS_MOUNT_IGNOREMETACSUMS		= (1ULL << 31),
+	BTRFS_MOUNT_IGNORESUPERFLAGS		= (1ULL << 32),
 };
 
 /*
@@ -224,10 +263,10 @@ enum {
 	 BTRFS_FEATURE_INCOMPAT_ZONED		|	\
 	 BTRFS_FEATURE_INCOMPAT_SIMPLE_QUOTA)
 
-#ifdef CONFIG_BTRFS_DEBUG
+#ifdef CONFIG_BTRFS_EXPERIMENTAL
 	/*
 	 * Features under developmen like Extent tree v2 support is enabled
-	 * only under CONFIG_BTRFS_DEBUG.
+	 * only under CONFIG_BTRFS_EXPERIMENTAL
 	 */
 #define BTRFS_FEATURE_INCOMPAT_SUPP		\
 	(BTRFS_FEATURE_INCOMPAT_SUPP_STABLE |	\
@@ -278,6 +317,8 @@ struct btrfs_dev_replace {
 
 	struct percpu_counter bio_counter;
 	wait_queue_head_t replace_wait;
+
+	struct task_struct *replace_task;
 };
 
 /*
@@ -442,7 +483,7 @@ struct btrfs_fs_info {
 	 * required instead of the faster short fsync log commits
 	 */
 	u64 last_trans_log_full_commit;
-	unsigned long mount_opt;
+	unsigned long long mount_opt;
 
 	unsigned long compress_type:4;
 	unsigned int compress_level;
@@ -586,6 +627,9 @@ struct btrfs_fs_info {
 	struct kobject *qgroups_kobj;
 	struct kobject *discard_kobj;
 
+	/* Track the number of blocks (sectors) read by the filesystem. */
+	struct percpu_counter stats_read_blocks;
+
 	/* Used to keep from writing metadata until there is a nice batch */
 	struct percpu_counter dirty_metadata_bytes;
 	struct percpu_counter delalloc_bytes;
@@ -593,6 +637,12 @@ struct btrfs_fs_info {
 	s32 dirty_metadata_batch;
 	s32 delalloc_batch;
 
+	struct percpu_counter evictable_extent_maps;
+	u64 em_shrinker_last_root;
+	u64 em_shrinker_last_ino;
+	atomic64_t em_shrinker_nr_to_scan;
+	struct work_struct em_shrinker_work;
+
 	/* Protected by 'trans_lock'. */
 	struct list_head dirty_cowonly_roots;
 
@@ -659,8 +709,8 @@ struct btrfs_fs_info {
 	 * running.
 	 */
 	refcount_t scrub_workers_refcnt;
+	u32 sectors_per_page;
 	struct workqueue_struct *scrub_workers;
-	struct btrfs_subpage_info *subpage_info;
 
 	struct btrfs_discard_ctl discard_ctl;
 
@@ -732,10 +782,13 @@ struct btrfs_fs_info {
 
 	/* Reclaim partially filled block groups in the background */
 	struct work_struct reclaim_bgs_work;
+	/* Protected by unused_bgs_lock. */
 	struct list_head reclaim_bgs;
 	int bg_reclaim_threshold;
 
+	/* Protects the lists unused_bgs and reclaim_bgs. */
 	spinlock_t unused_bgs_lock;
+	/* Protected by unused_bgs_lock. */
 	struct list_head unused_bgs;
 	struct mutex unused_bg_unpin_mutex;
 	/* Protect block groups that are going to be deleted */
@@ -829,6 +882,19 @@ struct btrfs_fs_info {
 #endif
 };
 
+#define folio_to_inode(_folio)	(BTRFS_I(_Generic((_folio),			\
+					  struct folio *: (_folio))->mapping->host))
+
+#define folio_to_fs_info(_folio) (folio_to_inode(_folio)->root->fs_info)
+
+#define inode_to_fs_info(_inode) (BTRFS_I(_Generic((_inode),			\
+					   struct inode *: (_inode)))->root->fs_info)
+
+static inline gfp_t btrfs_alloc_write_mask(struct address_space *mapping)
+{
+	return mapping_gfp_constraint(mapping, ~__GFP_FS);
+}
+
 static inline u64 btrfs_get_fs_generation(const struct btrfs_fs_info *fs_info)
 {
 	return READ_ONCE(fs_info->generation);
@@ -895,6 +961,8 @@ static inline u64 btrfs_calc_metadata_size(const struct btrfs_fs_info *fs_info,
 #define BTRFS_MAX_EXTENT_ITEM_SIZE(r) ((BTRFS_LEAF_DATA_SIZE(r->fs_info) >> 4) - \
 					sizeof(struct btrfs_item))
 
+#define BTRFS_BYTES_TO_BLKS(fs_info, bytes) ((bytes) >> (fs_info)->sectorsize_bits)
+
 static inline bool btrfs_is_zoned(const struct btrfs_fs_info *fs_info)
 {
 	return IS_ENABLED(CONFIG_BLK_DEV_ZONED) && fs_info->zone_size > 0;
@@ -903,7 +971,7 @@ static inline bool btrfs_is_zoned(const struct btrfs_fs_info *fs_info)
 /*
  * Count how many fs_info->max_extent_size cover the @size
  */
-static inline u32 count_max_extents(struct btrfs_fs_info *fs_info, u64 size)
+static inline u32 count_max_extents(const struct btrfs_fs_info *fs_info, u64 size)
 {
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 	if (!fs_info)
@@ -922,6 +990,19 @@ void btrfs_exclop_finish(struct btrfs_fs_info *fs_info);
 void btrfs_exclop_balance(struct btrfs_fs_info *fs_info,
 			  enum btrfs_exclusive_operation op);
 
+int btrfs_check_ioctl_vol_args_path(const struct btrfs_ioctl_vol_args *vol_args);
+
+u16 btrfs_csum_type_size(u16 type);
+int btrfs_super_csum_size(const struct btrfs_super_block *s);
+const char *btrfs_super_csum_name(u16 csum_type);
+const char *btrfs_super_csum_driver(u16 csum_type);
+size_t __attribute_const__ btrfs_get_num_csums(void);
+
+static inline bool btrfs_is_empty_uuid(const u8 *uuid)
+{
+	return uuid_is_null((const uuid_t *)uuid);
+}
+
 /* Compatibility and incompatibility defines */
 void __btrfs_set_fs_incompat(struct btrfs_fs_info *fs_info, u64 flag,
 			     const char *name);
@@ -962,7 +1043,7 @@ void __btrfs_clear_fs_compat_ro(struct btrfs_fs_info *fs_info, u64 flag,
 #define btrfs_test_opt(fs_info, opt)	((fs_info)->mount_opt & \
 					 BTRFS_MOUNT_##opt)
 
-static inline int btrfs_fs_closing(struct btrfs_fs_info *fs_info)
+static inline int btrfs_fs_closing(const struct btrfs_fs_info *fs_info)
 {
 	/* Do it this way so we only ever do one test_bit in the normal case. */
 	if (test_bit(BTRFS_FS_CLOSING_START, &fs_info->flags)) {
@@ -981,7 +1062,7 @@ static inline int btrfs_fs_closing(struct btrfs_fs_info *fs_info)
  * since setting and checking for SB_RDONLY in the superblock's flags is not
  * atomic.
  */
-static inline int btrfs_need_cleaner_sleep(struct btrfs_fs_info *fs_info)
+static inline int btrfs_need_cleaner_sleep(const struct btrfs_fs_info *fs_info)
 {
 	return test_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state) ||
 		btrfs_fs_closing(fs_info);
@@ -998,11 +1079,19 @@ static inline void btrfs_wake_unfinished_drop(struct btrfs_fs_info *fs_info)
 	(unlikely(test_bit(BTRFS_FS_STATE_LOG_CLEANUP_ERROR,		\
 			   &(fs_info)->fs_state)))
 
+/*
+ * We use folio flag owner_2 to indicate there is an ordered extent with
+ * unfinished IO.
+ */
+#define folio_test_ordered(folio)	folio_test_owner_2(folio)
+#define folio_set_ordered(folio)	folio_set_owner_2(folio)
+#define folio_clear_ordered(folio)	folio_clear_owner_2(folio)
+
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 
 #define EXPORT_FOR_TESTS
 
-static inline int btrfs_is_testing(struct btrfs_fs_info *fs_info)
+static inline int btrfs_is_testing(const struct btrfs_fs_info *fs_info)
 {
 	return test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state);
 }
@@ -1013,7 +1102,7 @@ void btrfs_test_destroy_inode(struct inode *inode);
 
 #define EXPORT_FOR_TESTS static
 
-static inline int btrfs_is_testing(struct btrfs_fs_info *fs_info)
+static inline int btrfs_is_testing(const struct btrfs_fs_info *fs_info)
 {
 	return 0;
 }