From ea08eeccae9297f7aabd2ef7f0c2517ac4549acc Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:18:26 +0000
Subject: [PATCH] write in 30M
---
kernel/fs/f2fs/f2fs.h | 1112 +++++++++++++++++++++++++++++++++++++++------------------
1 files changed, 753 insertions(+), 359 deletions(-)
diff --git a/kernel/fs/f2fs/f2fs.h b/kernel/fs/f2fs/f2fs.h
index 2db8eb9..af70db6 100644
--- a/kernel/fs/f2fs/f2fs.h
+++ b/kernel/fs/f2fs/f2fs.h
@@ -22,6 +22,7 @@
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/quotaops.h>
+#include <linux/part_stat.h>
#include <crypto/hash.h>
#include <linux/fscrypt.h>
@@ -32,10 +33,8 @@
#else
#define f2fs_bug_on(sbi, condition) \
do { \
- if (unlikely(condition)) { \
- WARN_ON(1); \
+ if (WARN_ON(condition)) \
set_sbi_flag(sbi, SBI_NEED_FSCK); \
- } \
} while (0)
#endif
@@ -44,7 +43,6 @@
FAULT_KVMALLOC,
FAULT_PAGE_ALLOC,
FAULT_PAGE_GET,
- FAULT_ALLOC_BIO,
FAULT_ALLOC_NID,
FAULT_ORPHAN,
FAULT_BLOCK,
@@ -71,7 +69,7 @@
#define IS_FAULT_SET(fi, type) ((fi)->inject_type & (1 << (type)))
#endif
-#define MIN_ROOT_RESERVED_BLOCKS (128 * 1024 * 1024U)
+#define MIN_ROOT_RESERVED_BLOCKS (128 * 1024 * 1024)
/*
* For mount options
@@ -88,7 +86,7 @@
#define F2FS_MOUNT_FLUSH_MERGE 0x00000400
#define F2FS_MOUNT_NOBARRIER 0x00000800
#define F2FS_MOUNT_FASTBOOT 0x00001000
-#define F2FS_MOUNT_EXTENT_CACHE 0x00002000
+#define F2FS_MOUNT_READ_EXTENT_CACHE 0x00002000
#define F2FS_MOUNT_DATA_FLUSH 0x00008000
#define F2FS_MOUNT_FAULT_INJECTION 0x00010000
#define F2FS_MOUNT_USRQUOTA 0x00080000
@@ -99,6 +97,11 @@
#define F2FS_MOUNT_RESERVE_ROOT 0x01000000
#define F2FS_MOUNT_DISABLE_CHECKPOINT 0x02000000
#define F2FS_MOUNT_NORECOVERY 0x04000000
+#define F2FS_MOUNT_ATGC 0x08000000
+#define F2FS_MOUNT_MERGE_CHECKPOINT 0x10000000
+#define F2FS_MOUNT_GC_MERGE 0x20000000
+#define F2FS_MOUNT_COMPRESS_CACHE 0x40000000
+#define F2FS_MOUNT_AGE_EXTENT_CACHE 0x80000000
#define F2FS_OPTION(sbi) ((sbi)->mount_opt)
#define clear_opt(sbi, option) (F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option)
@@ -116,6 +119,18 @@
typedef u32 nid_t;
#define COMPRESS_EXT_NUM 16
+
+/*
+ * An implementation of an rwsem that is explicitly unfair to readers. This
+ * prevents priority inversion when a low-priority reader acquires the read lock
+ * while sleeping on the write lock but the write lock is needed by
+ * higher-priority clients.
+ */
+
+struct f2fs_rwsem {
+ struct rw_semaphore internal_rwsem;
+ wait_queue_head_t read_waiters;
+};
struct f2fs_mount_info {
unsigned int opt;
@@ -139,10 +154,8 @@
int fsync_mode; /* fsync policy */
int fs_mode; /* fs mode: LFS or ADAPTIVE */
int bggc_mode; /* bggc mode: off, on or sync */
- struct fscrypt_dummy_context dummy_enc_ctx; /* test dummy encryption */
-#ifdef CONFIG_FS_ENCRYPTION
- bool inlinecrypt; /* inline encryption enabled */
-#endif
+ int memory_mode; /* memory mode */
+ struct fscrypt_dummy_policy dummy_enc_policy; /* test dummy encryption */
block_t unusable_cap_perc; /* percentage for cap */
block_t unusable_cap; /* Amount of space allowed to be
* unusable when disabling checkpoint
@@ -150,8 +163,11 @@
/* For compression */
unsigned char compress_algorithm; /* algorithm type */
- unsigned compress_log_size; /* cluster log size */
+ unsigned char compress_log_size; /* cluster log size */
+ unsigned char compress_level; /* compress level */
+ bool compress_chksum; /* compressed data chksum */
unsigned char compress_ext_cnt; /* extension count */
+ int compress_mode; /* compression mode */
unsigned char extensions[COMPRESS_EXT_NUM][F2FS_EXTENSION_LEN]; /* extensions */
};
@@ -169,6 +185,7 @@
#define F2FS_FEATURE_SB_CHKSUM 0x0800
#define F2FS_FEATURE_CASEFOLD 0x1000
#define F2FS_FEATURE_COMPRESSION 0x2000
+#define F2FS_FEATURE_RO 0x4000
#define __F2FS_HAS_FEATURE(raw_super, mask) \
((raw_super->feature & cpu_to_le32(mask)) != 0)
@@ -238,6 +255,10 @@
* condition of read on truncated area
* by extent_cache
*/
+ DATA_GENERIC_ENHANCE_UPDATE, /*
+ * strong check on range and segment
+ * bitmap for update case
+ */
META_GENERIC,
};
@@ -267,6 +288,26 @@
struct list_head list; /* list head */
struct page *page; /* warm node page pointer */
unsigned int seq_id; /* sequence id */
+};
+
+struct ckpt_req {
+ struct completion wait; /* completion for checkpoint done */
+ struct llist_node llnode; /* llist_node to be linked in wait queue */
+ int ret; /* return code of checkpoint */
+ ktime_t queue_time; /* request queued time */
+};
+
+struct ckpt_req_control {
+ struct task_struct *f2fs_issue_ckpt; /* checkpoint task */
+ int ckpt_thread_ioprio; /* checkpoint merge thread ioprio */
+ wait_queue_head_t ckpt_wait_queue; /* waiting queue for wake-up */
+ atomic_t issued_ckpt; /* # of actually issued ckpts */
+ atomic_t total_ckpt; /* # of total ckpts */
+ atomic_t queued_ckpt; /* # of queued ckpts */
+ struct llist_head issue_list; /* list for command issue */
+ spinlock_t stat_lock; /* lock for below checkpoint time stats */
+ unsigned int cur_time; /* cur wait time in msec for currently issued checkpoint */
+ unsigned int peak_time; /* peak wait time in msec until now */
};
/* for the bitmap indicate blocks to be discarded */
@@ -405,93 +446,6 @@
return size <= MAX_SIT_JENTRIES(journal);
}
-/*
- * ioctl commands
- */
-#define F2FS_IOC_GETFLAGS FS_IOC_GETFLAGS
-#define F2FS_IOC_SETFLAGS FS_IOC_SETFLAGS
-#define F2FS_IOC_GETVERSION FS_IOC_GETVERSION
-
-#define F2FS_IOCTL_MAGIC 0xf5
-#define F2FS_IOC_START_ATOMIC_WRITE _IO(F2FS_IOCTL_MAGIC, 1)
-#define F2FS_IOC_COMMIT_ATOMIC_WRITE _IO(F2FS_IOCTL_MAGIC, 2)
-#define F2FS_IOC_START_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 3)
-#define F2FS_IOC_RELEASE_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 4)
-#define F2FS_IOC_ABORT_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 5)
-#define F2FS_IOC_GARBAGE_COLLECT _IOW(F2FS_IOCTL_MAGIC, 6, __u32)
-#define F2FS_IOC_WRITE_CHECKPOINT _IO(F2FS_IOCTL_MAGIC, 7)
-#define F2FS_IOC_DEFRAGMENT _IOWR(F2FS_IOCTL_MAGIC, 8, \
- struct f2fs_defragment)
-#define F2FS_IOC_MOVE_RANGE _IOWR(F2FS_IOCTL_MAGIC, 9, \
- struct f2fs_move_range)
-#define F2FS_IOC_FLUSH_DEVICE _IOW(F2FS_IOCTL_MAGIC, 10, \
- struct f2fs_flush_device)
-#define F2FS_IOC_GARBAGE_COLLECT_RANGE _IOW(F2FS_IOCTL_MAGIC, 11, \
- struct f2fs_gc_range)
-#define F2FS_IOC_GET_FEATURES _IOR(F2FS_IOCTL_MAGIC, 12, __u32)
-#define F2FS_IOC_SET_PIN_FILE _IOW(F2FS_IOCTL_MAGIC, 13, __u32)
-#define F2FS_IOC_GET_PIN_FILE _IOR(F2FS_IOCTL_MAGIC, 14, __u32)
-#define F2FS_IOC_PRECACHE_EXTENTS _IO(F2FS_IOCTL_MAGIC, 15)
-#define F2FS_IOC_RESIZE_FS _IOW(F2FS_IOCTL_MAGIC, 16, __u64)
-#define F2FS_IOC_GET_COMPRESS_BLOCKS _IOR(F2FS_IOCTL_MAGIC, 17, __u64)
-#define F2FS_IOC_RELEASE_COMPRESS_BLOCKS \
- _IOR(F2FS_IOCTL_MAGIC, 18, __u64)
-#define F2FS_IOC_RESERVE_COMPRESS_BLOCKS \
- _IOR(F2FS_IOCTL_MAGIC, 19, __u64)
-
-#define F2FS_IOC_GET_VOLUME_NAME FS_IOC_GETFSLABEL
-#define F2FS_IOC_SET_VOLUME_NAME FS_IOC_SETFSLABEL
-
-#define F2FS_IOC_SET_ENCRYPTION_POLICY FS_IOC_SET_ENCRYPTION_POLICY
-#define F2FS_IOC_GET_ENCRYPTION_POLICY FS_IOC_GET_ENCRYPTION_POLICY
-#define F2FS_IOC_GET_ENCRYPTION_PWSALT FS_IOC_GET_ENCRYPTION_PWSALT
-
-/*
- * should be same as XFS_IOC_GOINGDOWN.
- * Flags for going down operation used by FS_IOC_GOINGDOWN
- */
-#define F2FS_IOC_SHUTDOWN _IOR('X', 125, __u32) /* Shutdown */
-#define F2FS_GOING_DOWN_FULLSYNC 0x0 /* going down with full sync */
-#define F2FS_GOING_DOWN_METASYNC 0x1 /* going down with metadata */
-#define F2FS_GOING_DOWN_NOSYNC 0x2 /* going down */
-#define F2FS_GOING_DOWN_METAFLUSH 0x3 /* going down with meta flush */
-#define F2FS_GOING_DOWN_NEED_FSCK 0x4 /* going down to trigger fsck */
-
-#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
-/*
- * ioctl commands in 32 bit emulation
- */
-#define F2FS_IOC32_GETFLAGS FS_IOC32_GETFLAGS
-#define F2FS_IOC32_SETFLAGS FS_IOC32_SETFLAGS
-#define F2FS_IOC32_GETVERSION FS_IOC32_GETVERSION
-#endif
-
-#define F2FS_IOC_FSGETXATTR FS_IOC_FSGETXATTR
-#define F2FS_IOC_FSSETXATTR FS_IOC_FSSETXATTR
-
-struct f2fs_gc_range {
- u32 sync;
- u64 start;
- u64 len;
-};
-
-struct f2fs_defragment {
- u64 start;
- u64 len;
-};
-
-struct f2fs_move_range {
- u32 dst_fd; /* destination fd */
- u64 pos_in; /* start position in src_fd */
- u64 pos_out; /* start position in dst_fd */
- u64 len; /* size to move */
-};
-
-struct f2fs_flush_device {
- u32 dev_num; /* device number to flush */
- u32 segments; /* # of segments to flush */
-};
-
/* for inline stuff */
#define DEF_INLINE_RESERVED_SIZE 1
static inline int get_extra_isize(struct inode *inode);
@@ -544,11 +498,11 @@
#ifdef CONFIG_UNICODE
/*
* For casefolded directories: the casefolded name, but it's left NULL
- * if the original name is not valid Unicode, if the directory is both
- * casefolded and encrypted and its encryption key is unavailable, or if
- * the filesystem is doing an internal operation where usr_fname is also
- * NULL. In all these cases we fall back to treating the name as an
- * opaque byte sequence.
+ * if the original name is not valid Unicode, if the original name is
+ * "." or "..", if the directory is both casefolded and encrypted and
+ * its encryption key is unavailable, or if the filesystem is doing an
+ * internal operation where usr_fname is also NULL. In all these cases
+ * we fall back to treating the name as an opaque byte sequence.
*/
struct fscrypt_str cf_name;
#endif
@@ -622,18 +576,59 @@
#define F2FS_MIN_EXTENT_LEN 64 /* minimum extent length */
/* number of extent info in extent cache we try to shrink */
-#define EXTENT_CACHE_SHRINK_NUMBER 128
+#define READ_EXTENT_CACHE_SHRINK_NUMBER 128
+
+/* number of age extent info in extent cache we try to shrink */
+#define AGE_EXTENT_CACHE_SHRINK_NUMBER 128
+#define LAST_AGE_WEIGHT 30
+#define SAME_AGE_REGION 1024
+
+/*
+ * Define data block with age less than 1GB as hot data
+ * define data block with age less than 10GB but more than 1GB as warm data
+ */
+#define DEF_HOT_DATA_AGE_THRESHOLD 262144
+#define DEF_WARM_DATA_AGE_THRESHOLD 2621440
+
+/* extent cache type */
+enum extent_type {
+ EX_READ,
+ EX_BLOCK_AGE,
+ NR_EXTENT_CACHES,
+};
struct rb_entry {
struct rb_node rb_node; /* rb node located in rb-tree */
- unsigned int ofs; /* start offset of the entry */
- unsigned int len; /* length of the entry */
+ union {
+ struct {
+ unsigned int ofs; /* start offset of the entry */
+ unsigned int len; /* length of the entry */
+ };
+ unsigned long long key; /* 64-bits key */
+ } __packed;
};
struct extent_info {
unsigned int fofs; /* start offset in a file */
unsigned int len; /* length of the extent */
- u32 blk; /* start block address of the extent */
+ union {
+ /* read extent_cache */
+ struct {
+ /* start block address of the extent */
+ block_t blk;
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+ /* physical extent length of compressed blocks */
+ unsigned int c_len;
+#endif
+ };
+ /* block age extent_cache */
+ struct {
+ /* block age of the extent */
+ unsigned long long age;
+ /* last total blocks allocated */
+ unsigned long long last_blocks;
+ };
+ };
};
struct extent_node {
@@ -645,13 +640,25 @@
struct extent_tree {
nid_t ino; /* inode number */
+ enum extent_type type; /* keep the extent tree type */
struct rb_root_cached root; /* root of extent info rb-tree */
struct extent_node *cached_en; /* recently accessed extent node */
- struct extent_info largest; /* largested extent info */
struct list_head list; /* to be used by sbi->zombie_list */
rwlock_t lock; /* protect extent info rb-tree */
atomic_t node_cnt; /* # of extent node in rb-tree*/
bool largest_updated; /* largest extent updated */
+ struct extent_info largest; /* largest cached extent for EX_READ */
+};
+
+struct extent_tree_info {
+ struct radix_tree_root extent_tree_root;/* cache extent cache entries */
+ struct mutex extent_tree_lock; /* locking extent radix tree */
+ struct list_head extent_list; /* lru list for shrinker */
+ spinlock_t extent_lock; /* locking extent lru list */
+ atomic_t total_ext_tree; /* extent tree count */
+ struct list_head zombie_list; /* extent zombie tree list */
+ atomic_t total_zombie_tree; /* extent zombie tree count */
+ atomic_t total_ext_node; /* extent info count */
};
/*
@@ -701,21 +708,26 @@
#define FADVISE_MODIFIABLE_BITS (FADVISE_COLD_BIT | FADVISE_HOT_BIT)
#define file_is_cold(inode) is_file(inode, FADVISE_COLD_BIT)
-#define file_wrong_pino(inode) is_file(inode, FADVISE_LOST_PINO_BIT)
#define file_set_cold(inode) set_file(inode, FADVISE_COLD_BIT)
-#define file_lost_pino(inode) set_file(inode, FADVISE_LOST_PINO_BIT)
#define file_clear_cold(inode) clear_file(inode, FADVISE_COLD_BIT)
+
+#define file_wrong_pino(inode) is_file(inode, FADVISE_LOST_PINO_BIT)
+#define file_lost_pino(inode) set_file(inode, FADVISE_LOST_PINO_BIT)
#define file_got_pino(inode) clear_file(inode, FADVISE_LOST_PINO_BIT)
+
#define file_is_encrypt(inode) is_file(inode, FADVISE_ENCRYPT_BIT)
#define file_set_encrypt(inode) set_file(inode, FADVISE_ENCRYPT_BIT)
-#define file_clear_encrypt(inode) clear_file(inode, FADVISE_ENCRYPT_BIT)
+
#define file_enc_name(inode) is_file(inode, FADVISE_ENC_NAME_BIT)
#define file_set_enc_name(inode) set_file(inode, FADVISE_ENC_NAME_BIT)
+
#define file_keep_isize(inode) is_file(inode, FADVISE_KEEP_SIZE_BIT)
#define file_set_keep_isize(inode) set_file(inode, FADVISE_KEEP_SIZE_BIT)
+
#define file_is_hot(inode) is_file(inode, FADVISE_HOT_BIT)
#define file_set_hot(inode) set_file(inode, FADVISE_HOT_BIT)
#define file_clear_hot(inode) clear_file(inode, FADVISE_HOT_BIT)
+
#define file_is_verity(inode) is_file(inode, FADVISE_VERITY_BIT)
#define file_set_verity(inode) set_file(inode, FADVISE_VERITY_BIT)
@@ -751,7 +763,8 @@
FI_DROP_CACHE, /* drop dirty page cache */
FI_DATA_EXIST, /* indicate data exists */
FI_INLINE_DOTS, /* indicate inline dot dentries */
- FI_DO_DEFRAG, /* indicate defragment is running */
+ FI_SKIP_WRITES, /* should skip data page writeback */
+ FI_OPU_WRITE, /* used for opu per file */
FI_DIRTY_FILE, /* indicate regular/symlink has dirty pages */
FI_NO_PREALLOC, /* indicate skipped preallocated blocks */
FI_HOT_DATA, /* indicate file is hot */
@@ -761,7 +774,11 @@
FI_ATOMIC_REVOKE_REQUEST, /* request to drop atomic data */
FI_VERITY_IN_PROGRESS, /* building fs-verity Merkle tree */
FI_COMPRESSED_FILE, /* indicate file's data can be compressed */
+ FI_COMPRESS_CORRUPT, /* indicate compressed cluster is corrupted */
FI_MMAP_FILE, /* indicate file was mmapped */
+ FI_ENABLE_COMPRESS, /* enable compression in "user" compression mode */
+ FI_COMPRESS_RELEASED, /* compressed blocks were released */
+ FI_ALIGNED_WRITE, /* enable aligned write */
FI_MAX, /* max flag, never be used */
};
@@ -778,12 +795,13 @@
/* Use below internally in f2fs*/
unsigned long flags[BITS_TO_LONGS(FI_MAX)]; /* use to pass per-file flags */
- struct rw_semaphore i_sem; /* protect fi info */
+ struct f2fs_rwsem i_sem; /* protect fi info */
atomic_t dirty_pages; /* # of dirty pages */
f2fs_hash_t chash; /* hash value of given file name */
unsigned int clevel; /* maximum level of given file name */
struct task_struct *task; /* lookup and create consistency */
struct task_struct *cp_task; /* separate cp/wb IO stats*/
+ struct task_struct *wb_task; /* indicate inode is in context of writeback */
nid_t i_xattr_nid; /* node id that contains xattrs */
loff_t last_disk_size; /* lastly written file size */
spinlock_t i_size_lock; /* protect last_disk_size */
@@ -800,12 +818,13 @@
struct list_head inmem_pages; /* inmemory pages managed by f2fs */
struct task_struct *inmem_task; /* store inmemory task */
struct mutex inmem_lock; /* lock for inmemory pages */
- struct extent_tree *extent_tree; /* cached extent_tree entry */
+ struct extent_tree *extent_tree[NR_EXTENT_CACHES];
+ /* cached extent_tree entry */
/* avoid racing between foreground op and gc */
- struct rw_semaphore i_gc_rwsem[2];
- struct rw_semaphore i_mmap_sem;
- struct rw_semaphore i_xattr_sem; /* avoid racing between reading and changing EAs */
+ struct f2fs_rwsem i_gc_rwsem[2];
+ struct f2fs_rwsem i_mmap_sem;
+ struct f2fs_rwsem i_xattr_sem; /* avoid racing between reading and changing EAs */
int i_extra_isize; /* size of extra space located in i_addr */
kprojid_t i_projid; /* id for project quota */
@@ -814,13 +833,15 @@
struct timespec64 i_disk_time[4];/* inode disk times */
/* for file compress */
- u64 i_compr_blocks; /* # of compressed blocks */
+ atomic_t i_compr_blocks; /* # of compressed blocks */
unsigned char i_compress_algorithm; /* algorithm type */
unsigned char i_log_cluster_size; /* log of cluster size */
+ unsigned char i_compress_level; /* compress level (lz4hc,zstd) */
+ unsigned short i_compress_flag; /* compress flag */
unsigned int i_cluster_size; /* cluster size */
};
-static inline void get_extent_info(struct extent_info *ext,
+static inline void get_read_extent_info(struct extent_info *ext,
struct f2fs_extent *i_ext)
{
ext->fofs = le32_to_cpu(i_ext->fofs);
@@ -828,20 +849,12 @@
ext->len = le32_to_cpu(i_ext->len);
}
-static inline void set_raw_extent(struct extent_info *ext,
+static inline void set_raw_read_extent(struct extent_info *ext,
struct f2fs_extent *i_ext)
{
i_ext->fofs = cpu_to_le32(ext->fofs);
i_ext->blk = cpu_to_le32(ext->blk);
i_ext->len = cpu_to_le32(ext->len);
-}
-
-static inline void set_extent_info(struct extent_info *ei, unsigned int fofs,
- u32 blk, unsigned int len)
-{
- ei->fofs = fofs;
- ei->blk = blk;
- ei->len = len;
}
static inline bool __is_discard_mergeable(struct discard_info *back,
@@ -863,35 +876,6 @@
return __is_discard_mergeable(cur, front, max_len);
}
-static inline bool __is_extent_mergeable(struct extent_info *back,
- struct extent_info *front)
-{
- return (back->fofs + back->len == front->fofs &&
- back->blk + back->len == front->blk);
-}
-
-static inline bool __is_back_mergeable(struct extent_info *cur,
- struct extent_info *back)
-{
- return __is_extent_mergeable(back, cur);
-}
-
-static inline bool __is_front_mergeable(struct extent_info *cur,
- struct extent_info *front)
-{
- return __is_extent_mergeable(cur, front);
-}
-
-extern void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync);
-static inline void __try_update_largest_extent(struct extent_tree *et,
- struct extent_node *en)
-{
- if (en->ei.len > et->largest.len) {
- et->largest = en->ei;
- et->largest_updated = true;
- }
-}
-
/*
* For free nid management
*/
@@ -899,6 +883,13 @@
FREE_NID, /* newly added to free nid list */
PREALLOC_NID, /* it is preallocated */
MAX_NID_STATE,
+};
+
+enum nat_state {
+ TOTAL_NAT,
+ DIRTY_NAT,
+ RECLAIMABLE_NAT,
+ MAX_NAT_STATE,
};
struct f2fs_nm_info {
@@ -913,11 +904,10 @@
/* NAT cache management */
struct radix_tree_root nat_root;/* root of the nat entry cache */
struct radix_tree_root nat_set_root;/* root of the nat set cache */
- struct rw_semaphore nat_tree_lock; /* protect nat_tree_lock */
+ struct f2fs_rwsem nat_tree_lock; /* protect nat entry tree */
struct list_head nat_entries; /* cached nat entry list (clean) */
spinlock_t nat_list_lock; /* protect clean nat entry list */
- unsigned int nat_cnt; /* the # of cached nat entries */
- unsigned int dirty_nat_cnt; /* total num of nat entries in set */
+ unsigned int nat_cnt[MAX_NAT_STATE]; /* the # of cached nat entries */
unsigned int nat_blocks; /* # of nat blocks */
/* free node ids management */
@@ -986,7 +976,10 @@
*/
#define NR_CURSEG_DATA_TYPE (3)
#define NR_CURSEG_NODE_TYPE (3)
-#define NR_CURSEG_TYPE (NR_CURSEG_DATA_TYPE + NR_CURSEG_NODE_TYPE)
+#define NR_CURSEG_INMEM_TYPE (2)
+#define NR_CURSEG_RO_TYPE (2)
+#define NR_CURSEG_PERSIST_TYPE (NR_CURSEG_DATA_TYPE + NR_CURSEG_NODE_TYPE)
+#define NR_CURSEG_TYPE (NR_CURSEG_INMEM_TYPE + NR_CURSEG_PERSIST_TYPE)
enum {
CURSEG_HOT_DATA = 0, /* directory entry blocks */
@@ -995,8 +988,11 @@
CURSEG_HOT_NODE, /* direct node blocks of directory files */
CURSEG_WARM_NODE, /* direct node blocks of normal files */
CURSEG_COLD_NODE, /* indirect node blocks */
- NO_CHECK_TYPE,
- CURSEG_COLD_DATA_PINNED,/* cold data for pinned file */
+ NR_PERSISTENT_LOG, /* number of persistent log */
+ CURSEG_COLD_DATA_PINNED = NR_PERSISTENT_LOG,
+ /* pinned file that needs consecutive block address */
+ CURSEG_ALL_DATA_ATGC, /* SSR alloctor in hot/warm/cold data area */
+ NO_CHECK_TYPE, /* number of persistent & inmem log */
};
struct flush_cmd {
@@ -1021,7 +1017,7 @@
struct dirty_seglist_info *dirty_info; /* dirty segment information */
struct curseg_info *curseg_array; /* active segment information */
- struct rw_semaphore curseg_lock; /* for preventing curseg change */
+ struct f2fs_rwsem curseg_lock; /* for preventing curseg change */
block_t seg0_blkaddr; /* block address of 0'th segment */
block_t main_blkaddr; /* start block address of main area */
@@ -1030,6 +1026,7 @@
unsigned int segment_count; /* total # of segments */
unsigned int main_segments; /* # of segments in main area */
unsigned int reserved_segments; /* # of reserved segments */
+ unsigned int additional_reserved_segments;/* reserved segs for IO align feature */
unsigned int ovp_segments; /* # of overprovision segments */
/* a threshold to reclaim prefree segments */
@@ -1095,8 +1092,8 @@
*/
#define PAGE_TYPE_OF_BIO(type) ((type) > META ? META : (type))
enum page_type {
- DATA,
- NODE,
+ DATA = 0,
+ NODE = 1, /* should not change this */
META,
NR_PAGE_TYPE,
META_FLUSH,
@@ -1186,6 +1183,7 @@
bool retry; /* need to reallocate block address */
int compr_blocks; /* # of compressed block addresses */
bool encrypted; /* indicate file is encrypted */
+ bool post_read; /* require post read */
enum iostat_type io_type; /* io type */
struct writeback_control *io_wbc; /* writeback control */
struct bio **bio; /* bio for ipu */
@@ -1204,11 +1202,11 @@
struct bio *bio; /* bios to merge */
sector_t last_block_in_bio; /* last block number */
struct f2fs_io_info fio; /* store buffered io info. */
- struct rw_semaphore io_rwsem; /* blocking op for bio */
+ struct f2fs_rwsem io_rwsem; /* blocking op for bio */
spinlock_t io_lock; /* serialize DATA/NODE IOs */
struct list_head io_list; /* track fios */
struct list_head bio_list; /* bio entry list head */
- struct rw_semaphore bio_list_lock; /* lock to protect bio entry list */
+ struct f2fs_rwsem bio_list_lock; /* lock to protect bio entry list */
};
#define FDEV(i) (sbi->devs[i])
@@ -1241,6 +1239,18 @@
unsigned long ino_num; /* number of entries */
};
+/* for GC_AT */
+struct atgc_management {
+ bool atgc_enabled; /* ATGC is enabled or not */
+ struct rb_root_cached root; /* root of victim rb-tree */
+ struct list_head victim_list; /* linked with all victim entries */
+ unsigned int victim_count; /* victim count in rb-tree */
+ unsigned int candidate_ratio; /* candidate ratio */
+ unsigned int max_candidate_count; /* max candidate count */
+ unsigned int age_weight; /* age weight, vblock_weight = 100 - age_weight */
+ unsigned long long age_threshold; /* age threshold */
+};
+
/* For s_flag in struct f2fs_sb_info */
enum {
SBI_IS_DIRTY, /* dirty flag for checkpoint */
@@ -1257,6 +1267,7 @@
SBI_QUOTA_SKIP_FLUSH, /* skip flushing quota in current CP */
SBI_QUOTA_NEED_REPAIR, /* quota file may be corrupted */
SBI_IS_RESIZEFS, /* resizefs is in process */
+ SBI_IS_FREEZING, /* freezefs is in process */
};
enum {
@@ -1273,7 +1284,11 @@
GC_NORMAL,
GC_IDLE_CB,
GC_IDLE_GREEDY,
- GC_URGENT,
+ GC_IDLE_AT,
+ GC_URGENT_HIGH,
+ GC_URGENT_LOW,
+ GC_URGENT_MID,
+ MAX_GC_MODE,
};
enum {
@@ -1307,36 +1322,158 @@
FSYNC_MODE_NOBARRIER, /* fsync behaves nobarrier based on posix */
};
+enum {
+ COMPR_MODE_FS, /*
+ * automatically compress compression
+ * enabled files
+ */
+ COMPR_MODE_USER, /*
+ * automatical compression is disabled.
+ * user can control the file compression
+ * using ioctls
+ */
+};
+
+enum {
+ MEMORY_MODE_NORMAL, /* memory mode for normal devices */
+ MEMORY_MODE_LOW, /* memory mode for low memry devices */
+};
+
+static inline int f2fs_test_bit(unsigned int nr, char *addr);
+static inline void f2fs_set_bit(unsigned int nr, char *addr);
+static inline void f2fs_clear_bit(unsigned int nr, char *addr);
+
/*
- * this value is set in page as a private data which indicate that
- * the page is atomically written, and it is in inmem_pages list.
+ * Layout of f2fs page.private:
+ *
+ * Layout A: lowest bit should be 1
+ * | bit0 = 1 | bit1 | bit2 | ... | bit MAX | private data .... |
+ * bit 0 PAGE_PRIVATE_NOT_POINTER
+ * bit 1 PAGE_PRIVATE_ATOMIC_WRITE
+ * bit 2 PAGE_PRIVATE_DUMMY_WRITE
+ * bit 3 PAGE_PRIVATE_ONGOING_MIGRATION
+ * bit 4 PAGE_PRIVATE_INLINE_INODE
+ * bit 5 PAGE_PRIVATE_REF_RESOURCE
+ * bit 6- f2fs private data
+ *
+ * Layout B: lowest bit should be 0
+ * page.private is a wrapped pointer.
*/
-#define ATOMIC_WRITTEN_PAGE ((unsigned long)-1)
-#define DUMMY_WRITTEN_PAGE ((unsigned long)-2)
+enum {
+ PAGE_PRIVATE_NOT_POINTER, /* private contains non-pointer data */
+ PAGE_PRIVATE_ATOMIC_WRITE, /* data page from atomic write path */
+ PAGE_PRIVATE_DUMMY_WRITE, /* data page for padding aligned IO */
+ PAGE_PRIVATE_ONGOING_MIGRATION, /* data page which is on-going migrating */
+ PAGE_PRIVATE_INLINE_INODE, /* inode page contains inline data */
+ PAGE_PRIVATE_REF_RESOURCE, /* dirty page has referenced resources */
+ PAGE_PRIVATE_MAX
+};
-#define IS_ATOMIC_WRITTEN_PAGE(page) \
- (page_private(page) == (unsigned long)ATOMIC_WRITTEN_PAGE)
-#define IS_DUMMY_WRITTEN_PAGE(page) \
- (page_private(page) == (unsigned long)DUMMY_WRITTEN_PAGE)
+#define PAGE_PRIVATE_GET_FUNC(name, flagname) \
+static inline bool page_private_##name(struct page *page) \
+{ \
+ return PagePrivate(page) && \
+ test_bit(PAGE_PRIVATE_NOT_POINTER, &page_private(page)) && \
+ test_bit(PAGE_PRIVATE_##flagname, &page_private(page)); \
+}
-#ifdef CONFIG_FS_ENCRYPTION
-#define DUMMY_ENCRYPTION_ENABLED(sbi) \
- (unlikely(F2FS_OPTION(sbi).dummy_enc_ctx.ctx != NULL))
-#else
-#define DUMMY_ENCRYPTION_ENABLED(sbi) (0)
-#endif
+#define PAGE_PRIVATE_SET_FUNC(name, flagname) \
+static inline void set_page_private_##name(struct page *page) \
+{ \
+ if (!PagePrivate(page)) { \
+ get_page(page); \
+ SetPagePrivate(page); \
+ set_page_private(page, 0); \
+ } \
+ set_bit(PAGE_PRIVATE_NOT_POINTER, &page_private(page)); \
+ set_bit(PAGE_PRIVATE_##flagname, &page_private(page)); \
+}
+
+#define PAGE_PRIVATE_CLEAR_FUNC(name, flagname) \
+static inline void clear_page_private_##name(struct page *page) \
+{ \
+ clear_bit(PAGE_PRIVATE_##flagname, &page_private(page)); \
+ if (page_private(page) == 1 << PAGE_PRIVATE_NOT_POINTER) { \
+ set_page_private(page, 0); \
+ if (PagePrivate(page)) { \
+ ClearPagePrivate(page); \
+ put_page(page); \
+ }\
+ } \
+}
+
+PAGE_PRIVATE_GET_FUNC(nonpointer, NOT_POINTER);
+PAGE_PRIVATE_GET_FUNC(reference, REF_RESOURCE);
+PAGE_PRIVATE_GET_FUNC(inline, INLINE_INODE);
+PAGE_PRIVATE_GET_FUNC(gcing, ONGOING_MIGRATION);
+PAGE_PRIVATE_GET_FUNC(atomic, ATOMIC_WRITE);
+PAGE_PRIVATE_GET_FUNC(dummy, DUMMY_WRITE);
+
+PAGE_PRIVATE_SET_FUNC(reference, REF_RESOURCE);
+PAGE_PRIVATE_SET_FUNC(inline, INLINE_INODE);
+PAGE_PRIVATE_SET_FUNC(gcing, ONGOING_MIGRATION);
+PAGE_PRIVATE_SET_FUNC(atomic, ATOMIC_WRITE);
+PAGE_PRIVATE_SET_FUNC(dummy, DUMMY_WRITE);
+
+PAGE_PRIVATE_CLEAR_FUNC(reference, REF_RESOURCE);
+PAGE_PRIVATE_CLEAR_FUNC(inline, INLINE_INODE);
+PAGE_PRIVATE_CLEAR_FUNC(gcing, ONGOING_MIGRATION);
+PAGE_PRIVATE_CLEAR_FUNC(atomic, ATOMIC_WRITE);
+PAGE_PRIVATE_CLEAR_FUNC(dummy, DUMMY_WRITE);
+
+static inline unsigned long get_page_private_data(struct page *page)
+{
+ unsigned long data = page_private(page);
+
+ if (!test_bit(PAGE_PRIVATE_NOT_POINTER, &data))
+ return 0;
+ return data >> PAGE_PRIVATE_MAX;
+}
+
+static inline void set_page_private_data(struct page *page, unsigned long data)
+{
+ if (!PagePrivate(page)) {
+ get_page(page);
+ SetPagePrivate(page);
+ set_page_private(page, 0);
+ }
+ set_bit(PAGE_PRIVATE_NOT_POINTER, &page_private(page));
+ page_private(page) |= data << PAGE_PRIVATE_MAX;
+}
+
+static inline void clear_page_private_data(struct page *page)
+{
+ page_private(page) &= (1 << PAGE_PRIVATE_MAX) - 1;
+ if (page_private(page) == 1 << PAGE_PRIVATE_NOT_POINTER) {
+ set_page_private(page, 0);
+ if (PagePrivate(page)) {
+ ClearPagePrivate(page);
+ put_page(page);
+ }
+ }
+}
/* For compression */
enum compress_algorithm_type {
COMPRESS_LZO,
COMPRESS_LZ4,
COMPRESS_ZSTD,
+ COMPRESS_LZORLE,
COMPRESS_MAX,
};
-#define COMPRESS_DATA_RESERVED_SIZE 5
+enum compress_flag {
+ COMPRESS_CHKSUM,
+ COMPRESS_MAX_FLAG,
+};
+
+#define COMPRESS_WATERMARK 20
+#define COMPRESS_PERCENT 20
+
+#define COMPRESS_DATA_RESERVED_SIZE 4
struct compress_data {
__le32 clen; /* compressed data size */
+ __le32 chksum; /* compressed data chksum */
__le32 reserved[COMPRESS_DATA_RESERVED_SIZE]; /* reserved */
u8 cdata[]; /* compressed data */
};
@@ -1344,6 +1481,8 @@
#define COMPRESS_HEADER_SIZE (sizeof(struct compress_data))
#define F2FS_COMPRESSED_PAGE_MAGIC 0xF5F2C000
+
+#define COMPRESS_LEVEL_OFFSET 8
/* compress context */
struct compress_ctx {
@@ -1369,10 +1508,10 @@
struct inode *inode; /* inode the context belong to */
struct page **rpages; /* pages store raw data in cluster */
unsigned int nr_rpages; /* total page number in rpages */
- refcount_t ref; /* referrence count of raw page */
+ atomic_t pending_pages; /* in-flight compressed page count */
};
-/* decompress io context for read IO path */
+/* Context for decompressing one cluster on the read IO path */
struct decompress_io_ctx {
u32 magic; /* magic number to indicate page is compressed */
struct inode *inode; /* inode the context belong to */
@@ -1388,22 +1527,50 @@
struct compress_data *cbuf; /* virtual mapped address on cpages */
size_t rlen; /* valid data length in rbuf */
size_t clen; /* valid data length in cbuf */
- refcount_t ref; /* referrence count of compressed page */
- bool failed; /* indicate IO error during decompression */
+
+ /*
+ * The number of compressed pages remaining to be read in this cluster.
+ * This is initially nr_cpages. It is decremented by 1 each time a page
+ * has been read (or failed to be read). When it reaches 0, the cluster
+ * is decompressed (or an error is reported).
+ *
+ * If an error occurs before all the pages have been submitted for I/O,
+ * then this will never reach 0. In this case the I/O submitter is
+ * responsible for calling f2fs_decompress_end_io() instead.
+ */
+ atomic_t remaining_pages;
+
+ /*
+ * Number of references to this decompress_io_ctx.
+ *
+ * One reference is held for I/O completion. This reference is dropped
+ * after the pagecache pages are updated and unlocked -- either after
+ * decompression (and verity if enabled), or after an error.
+ *
+ * In addition, each compressed page holds a reference while it is in a
+ * bio. These references are necessary prevent compressed pages from
+ * being freed while they are still in a bio.
+ */
+ refcount_t refcnt;
+
+ bool failed; /* IO error occurred before decompression? */
+ bool need_verity; /* need fs-verity verification after decompression? */
void *private; /* payload buffer for specified decompression algorithm */
void *private2; /* extra payload buffer */
+ struct work_struct verity_work; /* work to verify the decompressed pages */
+ struct work_struct free_work; /* work for late free this structure itself */
};
#define NULL_CLUSTER ((unsigned int)(~0))
#define MIN_COMPRESS_LOG_SIZE 2
#define MAX_COMPRESS_LOG_SIZE 8
-#define MAX_COMPRESS_WINDOW_SIZE ((PAGE_SIZE) << MAX_COMPRESS_LOG_SIZE)
+#define MAX_COMPRESS_WINDOW_SIZE(log_size) ((PAGE_SIZE) << (log_size))
struct f2fs_sb_info {
struct super_block *sb; /* pointer to VFS super block */
struct proc_dir_entry *s_proc; /* proc entry */
struct f2fs_super_block *raw_super; /* raw super block pointer */
- struct rw_semaphore sb_lock; /* lock for raw super block */
+ struct f2fs_rwsem sb_lock; /* lock for raw super block */
int valid_super_block; /* valid super block no */
unsigned long s_flag; /* flags for sbi */
struct mutex writepages; /* mutex for writepages() */
@@ -1423,7 +1590,7 @@
/* for bio operations */
struct f2fs_bio_info *write_io[NR_PAGE_TYPE]; /* for write bios */
/* keep migration IO order for LFS mode */
- struct rw_semaphore io_order_lock;
+ struct f2fs_rwsem io_order_lock;
mempool_t *write_io_dummy; /* Dummy pages */
/* for checkpoint */
@@ -1431,15 +1598,16 @@
int cur_cp_pack; /* remain current cp pack */
spinlock_t cp_lock; /* for flag in ckpt */
struct inode *meta_inode; /* cache meta blocks */
- struct mutex cp_mutex; /* checkpoint procedure lock */
- struct rw_semaphore cp_rwsem; /* blocking FS operations */
- struct rw_semaphore node_write; /* locking node writes */
- struct rw_semaphore node_change; /* locking node change */
+ struct f2fs_rwsem cp_global_sem; /* checkpoint procedure lock */
+ struct f2fs_rwsem cp_rwsem; /* blocking FS operations */
+ struct f2fs_rwsem node_write; /* locking node writes */
+ struct f2fs_rwsem node_change; /* locking node change */
wait_queue_head_t cp_wait;
unsigned long last_time[MAX_TIME]; /* to store time in jiffies */
long interval_time[MAX_TIME]; /* to store thresholds */
+ struct ckpt_req_control cprc_info; /* for checkpoint request control */
- struct inode_management im[MAX_INO_ENTRY]; /* manage inode cache */
+ struct inode_management im[MAX_INO_ENTRY]; /* manage inode cache */
spinlock_t fsync_node_lock; /* for node entry lock */
struct list_head fsync_node_list; /* node list head */
@@ -1455,14 +1623,13 @@
struct mutex flush_lock; /* for flush exclusion */
/* for extent tree cache */
- struct radix_tree_root extent_tree_root;/* cache extent cache entries */
- struct mutex extent_tree_lock; /* locking extent radix tree */
- struct list_head extent_list; /* lru list for shrinker */
- spinlock_t extent_lock; /* locking extent lru list */
- atomic_t total_ext_tree; /* extent tree count */
- struct list_head zombie_list; /* extent zombie tree list */
- atomic_t total_zombie_tree; /* extent zombie tree count */
- atomic_t total_ext_node; /* extent info count */
+ struct extent_tree_info extent_tree[NR_EXTENT_CACHES];
+ atomic64_t allocated_data_blocks; /* for block age extent_cache */
+
+ /* The threshold used for hot and warm data seperation*/
+ unsigned int hot_data_age_threshold;
+ unsigned int warm_data_age_threshold;
+ unsigned int last_age_weight;
/* basic filesystem units */
unsigned int log_sectors_per_block; /* log2 sectors per block */
@@ -1473,14 +1640,15 @@
unsigned int meta_ino_num; /* meta inode number*/
unsigned int log_blocks_per_seg; /* log2 blocks per segment */
unsigned int blocks_per_seg; /* blocks per segment */
+ unsigned int unusable_blocks_per_sec; /* unusable blocks per section */
unsigned int segs_per_sec; /* segments per section */
unsigned int secs_per_zone; /* sections per zone */
unsigned int total_sections; /* total section count */
unsigned int total_node_count; /* total node block count */
unsigned int total_valid_node_count; /* valid node block count */
- loff_t max_file_blocks; /* max block index of file */
int dir_level; /* directory level */
int readdir_ra; /* readahead inode in readdir */
+ u64 max_io_bytes; /* max io bytes to merge IOs */
block_t user_block_count; /* # of user blocks */
block_t total_valid_block_count; /* # of valid blocks */
@@ -1493,7 +1661,7 @@
block_t unusable_block_count; /* # of blocks saved by last cp */
unsigned int nquota_files; /* # of quota sysfile */
- struct rw_semaphore quota_sem; /* blocking cp for flags */
+ struct f2fs_rwsem quota_sem; /* blocking cp for flags */
/* # of pages, see count_type */
atomic_t nr_pages[NR_COUNT_TYPE];
@@ -1509,22 +1677,24 @@
struct f2fs_mount_info mount_opt; /* mount options */
/* for cleaning operations */
- struct rw_semaphore gc_lock; /*
+ struct f2fs_rwsem gc_lock; /*
* semaphore for GC, avoid
* race between GC and GC or CP
*/
struct f2fs_gc_kthread *gc_thread; /* GC thread */
+ struct atgc_management am; /* atgc management */
unsigned int cur_victim_sec; /* current victim section num */
unsigned int gc_mode; /* current GC state */
unsigned int next_victim_seg[2]; /* next segment in victim section */
+
/* for skip statistic */
- unsigned int atomic_files; /* # of opened atomic file */
+ unsigned int atomic_files; /* # of opened atomic file */
unsigned long long skipped_atomic_files[2]; /* FG_GC and BG_GC */
unsigned long long skipped_gc_rwsem; /* FG_GC only */
/* threshold for gc trials on pinned files */
u64 gc_pin_file_threshold;
- struct rw_semaphore pin_sem;
+ struct f2fs_rwsem pin_sem;
/* maximum # of trials to find a victim segment for SSR and GC */
unsigned int max_victim_search;
@@ -1543,15 +1713,19 @@
unsigned int segment_count[2]; /* # of allocated segments */
unsigned int block_count[2]; /* # of allocated blocks */
atomic_t inplace_count; /* # of inplace update */
- atomic64_t total_hit_ext; /* # of lookup extent cache */
- atomic64_t read_hit_rbtree; /* # of hit rbtree extent node */
- atomic64_t read_hit_largest; /* # of hit largest extent node */
- atomic64_t read_hit_cached; /* # of hit cached extent node */
+ /* # of lookup extent cache */
+ atomic64_t total_hit_ext[NR_EXTENT_CACHES];
+ /* # of hit rbtree extent node */
+ atomic64_t read_hit_rbtree[NR_EXTENT_CACHES];
+ /* # of hit cached extent node */
+ atomic64_t read_hit_cached[NR_EXTENT_CACHES];
+ /* # of hit largest extent node in read extent cache */
+ atomic64_t read_hit_largest;
atomic_t inline_xattr; /* # of inline_xattr inodes */
atomic_t inline_inode; /* # of inline_data inodes */
atomic_t inline_dir; /* # of inline_dentry inodes */
atomic_t compr_inode; /* # of compressed inodes */
- atomic_t compr_blocks; /* # of compressed blocks */
+ atomic64_t compr_blocks; /* # of compressed blocks */
atomic_t vw_cnt; /* # of volatile writes */
atomic_t max_aw_cnt; /* max # of atomic writes */
atomic_t max_vw_cnt; /* max # of volatile writes */
@@ -1574,8 +1748,14 @@
unsigned int node_io_flag;
/* For sysfs suppport */
- struct kobject s_kobj;
+ struct kobject s_kobj; /* /sys/fs/f2fs/<devname> */
struct completion s_kobj_unregister;
+
+ struct kobject s_stat_kobj; /* /sys/fs/f2fs/<devname>/stat */
+ struct completion s_stat_kobj_unregister;
+
+ struct kobject s_feature_list_kobj; /* /sys/fs/f2fs/<devname>/feature_list */
+ struct completion s_feature_list_kobj_unregister;
/* For shrinker support */
struct list_head s_list;
@@ -1600,6 +1780,26 @@
struct kmem_cache *inline_xattr_slab; /* inline xattr entry */
unsigned int inline_xattr_slab_size; /* default inline xattr slab size */
+
+ /* For reclaimed segs statistics per each GC mode */
+ unsigned int gc_segment_mode; /* GC state for reclaimed segments */
+ unsigned int gc_reclaimed_segs[MAX_GC_MODE]; /* Reclaimed segs for each mode */
+
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+ struct kmem_cache *page_array_slab; /* page array entry */
+ unsigned int page_array_slab_size; /* default page array slab size */
+
+ /* For runtime compression statistics */
+ u64 compr_written_block;
+ u64 compr_saved_block;
+ u32 compr_new_inode;
+
+ /* For compressed block cache */
+ struct inode *compress_inode; /* cache compressed blocks */
+ unsigned int compress_percent; /* cache page percentage */
+ unsigned int compress_watermark; /* cache page watermark */
+ atomic_t compress_page_hit; /* cache hit count */
+#endif
};
struct f2fs_private_dio {
@@ -1651,13 +1851,6 @@
return sbi->s_ndevs > 1;
}
-/* For write statistics. Suppose sector size is 512 bytes,
- * and the return value is in kbytes. s is of struct f2fs_sb_info.
- */
-#define BD_PART_WRITTEN(s) \
-(((u64)part_stat_read((s)->sb->s_bdev->bd_part, sectors[STAT_WRITE]) - \
- (s)->sectors_written_start) >> 1)
-
static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type)
{
unsigned long now = jiffies;
@@ -1707,7 +1900,6 @@
BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver) != sizeof(desc.ctx));
desc.shash.tfm = sbi->s_chksum_driver;
- desc.shash.flags = 0;
*(u32 *)desc.ctx = crc;
err = crypto_shash_update(&desc.shash, address, length);
@@ -1925,29 +2117,93 @@
return (cpc) ? (cpc->reason & CP_UMOUNT) && set : set;
}
+#define init_f2fs_rwsem(sem) \
+do { \
+ static struct lock_class_key __key; \
+ \
+ __init_f2fs_rwsem((sem), #sem, &__key); \
+} while (0)
+
+static inline void __init_f2fs_rwsem(struct f2fs_rwsem *sem,
+ const char *sem_name, struct lock_class_key *key)
+{
+ __init_rwsem(&sem->internal_rwsem, sem_name, key);
+ init_waitqueue_head(&sem->read_waiters);
+}
+
+static inline int f2fs_rwsem_is_locked(struct f2fs_rwsem *sem)
+{
+ return rwsem_is_locked(&sem->internal_rwsem);
+}
+
+static inline int f2fs_rwsem_is_contended(struct f2fs_rwsem *sem)
+{
+ return rwsem_is_contended(&sem->internal_rwsem);
+}
+
+static inline void f2fs_down_read(struct f2fs_rwsem *sem)
+{
+ wait_event(sem->read_waiters, down_read_trylock(&sem->internal_rwsem));
+}
+
+static inline int f2fs_down_read_trylock(struct f2fs_rwsem *sem)
+{
+ return down_read_trylock(&sem->internal_rwsem);
+}
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+static inline void f2fs_down_read_nested(struct f2fs_rwsem *sem, int subclass)
+{
+ down_read_nested(&sem->internal_rwsem, subclass);
+}
+#else
+#define f2fs_down_read_nested(sem, subclass) f2fs_down_read(sem)
+#endif
+
+static inline void f2fs_up_read(struct f2fs_rwsem *sem)
+{
+ up_read(&sem->internal_rwsem);
+}
+
+static inline void f2fs_down_write(struct f2fs_rwsem *sem)
+{
+ down_write(&sem->internal_rwsem);
+}
+
+static inline int f2fs_down_write_trylock(struct f2fs_rwsem *sem)
+{
+ return down_write_trylock(&sem->internal_rwsem);
+}
+
+static inline void f2fs_up_write(struct f2fs_rwsem *sem)
+{
+ up_write(&sem->internal_rwsem);
+ wake_up_all(&sem->read_waiters);
+}
+
static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
{
- down_read(&sbi->cp_rwsem);
+ f2fs_down_read(&sbi->cp_rwsem);
}
static inline int f2fs_trylock_op(struct f2fs_sb_info *sbi)
{
- return down_read_trylock(&sbi->cp_rwsem);
+ return f2fs_down_read_trylock(&sbi->cp_rwsem);
}
static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi)
{
- up_read(&sbi->cp_rwsem);
+ f2fs_up_read(&sbi->cp_rwsem);
}
static inline void f2fs_lock_all(struct f2fs_sb_info *sbi)
{
- down_write(&sbi->cp_rwsem);
+ f2fs_down_write(&sbi->cp_rwsem);
}
static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
{
- up_write(&sbi->cp_rwsem);
+ f2fs_up_write(&sbi->cp_rwsem);
}
static inline int __get_cp_reason(struct f2fs_sb_info *sbi)
@@ -2037,6 +2293,11 @@
if (!__allow_reserved_blocks(sbi, inode, true))
avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks;
+
+ if (F2FS_IO_ALIGNED(sbi))
+ avail_user_block_count -= sbi->blocks_per_seg *
+ SM_I(sbi)->additional_reserved_segments;
+
if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
if (avail_user_block_count > sbi->unusable_block_count)
avail_user_block_count -= sbi->unusable_block_count;
@@ -2199,6 +2460,7 @@
static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+ void *tmp_ptr = &ckpt->sit_nat_version_bitmap;
int offset;
if (is_set_ckpt_flags(sbi, CP_LARGE_NAT_BITMAP_FLAG)) {
@@ -2208,7 +2470,7 @@
* if large_nat_bitmap feature is enabled, leave checksum
* protection for all nat/sit bitmaps.
*/
- return &ckpt->sit_nat_version_bitmap + offset + sizeof(__le32);
+ return tmp_ptr + offset + sizeof(__le32);
}
if (__cp_payload(sbi) > 0) {
@@ -2219,7 +2481,7 @@
} else {
offset = (flag == NAT_BITMAP) ?
le32_to_cpu(ckpt->sit_ver_bitmap_bytesize) : 0;
- return &ckpt->sit_nat_version_bitmap + offset;
+ return tmp_ptr + offset;
}
}
@@ -2251,6 +2513,7 @@
return le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum);
}
+extern void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync);
static inline int inc_valid_node_count(struct f2fs_sb_info *sbi,
struct inode *inode, bool is_inode)
{
@@ -2282,6 +2545,11 @@
if (!__allow_reserved_blocks(sbi, inode, false))
valid_block_count += F2FS_OPTION(sbi).root_reserved_blocks;
+
+ if (F2FS_IO_ALIGNED(sbi))
+ valid_block_count += sbi->blocks_per_seg *
+ SM_I(sbi)->additional_reserved_segments;
+
user_block_count = sbi->user_block_count;
if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
user_block_count -= sbi->unusable_block_count;
@@ -2326,11 +2594,17 @@
{
spin_lock(&sbi->stat_lock);
- f2fs_bug_on(sbi, !sbi->total_valid_block_count);
- f2fs_bug_on(sbi, !sbi->total_valid_node_count);
+ if (unlikely(!sbi->total_valid_block_count ||
+ !sbi->total_valid_node_count)) {
+ f2fs_warn(sbi, "dec_valid_node_count: inconsistent block counts, total_valid_block:%u, total_valid_node:%u",
+ sbi->total_valid_block_count,
+ sbi->total_valid_node_count);
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ } else {
+ sbi->total_valid_block_count--;
+ sbi->total_valid_node_count--;
+ }
- sbi->total_valid_node_count--;
- sbi->total_valid_block_count--;
if (sbi->reserved_blocks &&
sbi->current_reserved_blocks < sbi->reserved_blocks)
sbi->current_reserved_blocks++;
@@ -2458,25 +2732,39 @@
return entry;
}
-static inline bool is_idle(struct f2fs_sb_info *sbi, int type)
+static inline bool is_inflight_io(struct f2fs_sb_info *sbi, int type)
{
- if (sbi->gc_mode == GC_URGENT)
- return true;
-
if (get_pages(sbi, F2FS_RD_DATA) || get_pages(sbi, F2FS_RD_NODE) ||
get_pages(sbi, F2FS_RD_META) || get_pages(sbi, F2FS_WB_DATA) ||
get_pages(sbi, F2FS_WB_CP_DATA) ||
get_pages(sbi, F2FS_DIO_READ) ||
get_pages(sbi, F2FS_DIO_WRITE))
- return false;
+ return true;
if (type != DISCARD_TIME && SM_I(sbi) && SM_I(sbi)->dcc_info &&
atomic_read(&SM_I(sbi)->dcc_info->queued_discard))
- return false;
+ return true;
if (SM_I(sbi) && SM_I(sbi)->fcc_info &&
atomic_read(&SM_I(sbi)->fcc_info->queued_flush))
+ return true;
+ return false;
+}
+
+static inline bool is_idle(struct f2fs_sb_info *sbi, int type)
+{
+ if (sbi->gc_mode == GC_URGENT_HIGH)
+ return true;
+
+ if (is_inflight_io(sbi, type))
return false;
+
+ if (sbi->gc_mode == GC_URGENT_MID)
+ return true;
+
+ if (sbi->gc_mode == GC_URGENT_LOW &&
+ (type == DISCARD_TIME || type == GC_TIME))
+ return true;
return f2fs_time_over(sbi, type);
}
@@ -2643,17 +2931,18 @@
case FI_NEW_INODE:
if (set)
return;
- /* fall through */
+ fallthrough;
case FI_DATA_EXIST:
case FI_INLINE_DOTS:
case FI_PIN_FILE:
+ case FI_COMPRESS_RELEASED:
f2fs_mark_inode_dirty_sync(inode, true);
}
}
static inline void set_inode_flag(struct inode *inode, int flag)
{
- test_and_set_bit(flag, F2FS_I(inode)->flags);
+ set_bit(flag, F2FS_I(inode)->flags);
__mark_inode_dirty_flag(inode, flag, true);
}
@@ -2664,7 +2953,7 @@
static inline void clear_inode_flag(struct inode *inode, int flag)
{
- test_and_clear_bit(flag, F2FS_I(inode)->flags);
+ clear_bit(flag, F2FS_I(inode)->flags);
__mark_inode_dirty_flag(inode, flag, false);
}
@@ -2768,6 +3057,8 @@
set_bit(FI_EXTRA_ATTR, fi->flags);
if (ri->i_inline & F2FS_PIN_FILE)
set_bit(FI_PIN_FILE, fi->flags);
+ if (ri->i_inline & F2FS_COMPRESS_RELEASED)
+ set_bit(FI_COMPRESS_RELEASED, fi->flags);
}
static inline void set_raw_inline(struct inode *inode, struct f2fs_inode *ri)
@@ -2788,6 +3079,8 @@
ri->i_inline |= F2FS_EXTRA_ATTR;
if (is_inode_flag_set(inode, FI_PIN_FILE))
ri->i_inline |= F2FS_PIN_FILE;
+ if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED))
+ ri->i_inline |= F2FS_COMPRESS_RELEASED;
}
static inline int f2fs_has_extra_attr(struct inode *inode)
@@ -2804,6 +3097,22 @@
{
return S_ISREG(inode->i_mode) &&
is_inode_flag_set(inode, FI_COMPRESSED_FILE);
+}
+
+static inline bool f2fs_need_compress_data(struct inode *inode)
+{
+ int compress_mode = F2FS_OPTION(F2FS_I_SB(inode)).compress_mode;
+
+ if (!f2fs_compressed_file(inode))
+ return false;
+
+ if (compress_mode == COMPR_MODE_FS)
+ return true;
+ else if (compress_mode == COMPR_MODE_USER &&
+ is_inode_flag_set(inode, FI_ENABLE_COMPRESS))
+ return true;
+
+ return false;
}
static inline unsigned int addrs_per_inode(struct inode *inode)
@@ -2980,25 +3289,6 @@
return false;
}
-static inline bool f2fs_may_extent_tree(struct inode *inode)
-{
- struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-
- if (!test_opt(sbi, EXTENT_CACHE) ||
- is_inode_flag_set(inode, FI_NO_EXTENT) ||
- is_inode_flag_set(inode, FI_COMPRESSED_FILE))
- return false;
-
- /*
- * for recovered files during mount do not create extents
- * if shrinker is not registered.
- */
- if (list_empty(&sbi->s_list))
- return false;
-
- return S_ISREG(inode->i_mode);
-}
-
static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi,
size_t size, gfp_t flags)
{
@@ -3122,27 +3412,6 @@
return true;
}
-static inline void f2fs_set_page_private(struct page *page,
- unsigned long data)
-{
- if (PagePrivate(page))
- return;
-
- get_page(page);
- SetPagePrivate(page);
- set_page_private(page, data);
-}
-
-static inline void f2fs_clear_page_private(struct page *page)
-{
- if (!PagePrivate(page))
- return;
-
- set_page_private(page, 0);
- ClearPagePrivate(page);
- f2fs_put_page(page, 0);
-}
-
/*
* file.c
*/
@@ -3248,7 +3517,9 @@
void f2fs_inode_synced(struct inode *inode);
int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly);
int f2fs_quota_sync(struct super_block *sb, int type);
+loff_t max_file_blocks(struct inode *inode);
void f2fs_quota_off_umount(struct super_block *sb);
+void f2fs_handle_stop(struct f2fs_sb_info *sbi, unsigned char reason);
int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover);
int f2fs_sync_fs(struct super_block *sb, int sync);
int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi);
@@ -3261,7 +3532,6 @@
/*
* node.c
*/
-struct dnode_of_data;
struct node_info;
int f2fs_check_nid_range(struct f2fs_sb_info *sbi, nid_t nid);
@@ -3274,7 +3544,7 @@
bool f2fs_is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid);
bool f2fs_need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino);
int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
- struct node_info *ni);
+ struct node_info *ni, bool checkpoint_context);
pgoff_t f2fs_get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs);
int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode);
int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from);
@@ -3288,7 +3558,7 @@
struct page *f2fs_get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid);
struct page *f2fs_get_node_page_ra(struct page *parent, int start);
int f2fs_move_node_page(struct page *node_page, int gc_type);
-int f2fs_flush_inline_data(struct f2fs_sb_info *sbi);
+void f2fs_flush_inline_data(struct f2fs_sb_info *sbi);
int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
struct writeback_control *wbc, bool atomic,
unsigned int *seq_id);
@@ -3338,9 +3608,16 @@
int f2fs_disable_cp_again(struct f2fs_sb_info *sbi, block_t unusable);
void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi);
int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra);
-void allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
+bool f2fs_segment_has_free_slot(struct f2fs_sb_info *sbi, int segno);
+void f2fs_init_inmem_curseg(struct f2fs_sb_info *sbi);
+void f2fs_save_inmem_curseg(struct f2fs_sb_info *sbi);
+void f2fs_restore_inmem_curseg(struct f2fs_sb_info *sbi);
+void f2fs_get_new_segment(struct f2fs_sb_info *sbi,
+ unsigned int *newseg, bool new_sec, int dir);
+void f2fs_allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
unsigned int start, unsigned int end);
-void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi, int type);
+void f2fs_allocate_new_section(struct f2fs_sb_info *sbi, int type, bool force);
+void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi);
int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range);
bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi,
struct cp_control *cpc);
@@ -3355,7 +3632,8 @@
int f2fs_inplace_write_data(struct f2fs_io_info *fio);
void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
block_t old_blkaddr, block_t new_blkaddr,
- bool recover_curseg, bool recover_newaddr);
+ bool recover_curseg, bool recover_newaddr,
+ bool from_gc);
void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
block_t old_addr, block_t new_addr,
unsigned char version, bool recover_curseg,
@@ -3363,7 +3641,7 @@
void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
block_t old_blkaddr, block_t *new_blkaddr,
struct f2fs_summary *sum, int type,
- struct f2fs_io_info *fio, bool add_list);
+ struct f2fs_io_info *fio);
void f2fs_wait_on_page_writeback(struct page *page,
enum page_type type, bool ordered, bool locked);
void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr);
@@ -3374,6 +3652,8 @@
int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
unsigned int val, int alloc);
void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
+int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi);
+int f2fs_check_write_pointer(struct f2fs_sb_info *sbi);
int f2fs_build_segment_manager(struct f2fs_sb_info *sbi);
void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi);
int __init f2fs_create_segment_manager_caches(void);
@@ -3381,14 +3661,20 @@
int f2fs_rw_hint_to_seg_type(enum rw_hint hint);
enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi,
enum page_type type, enum temp_type temp);
+unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi,
+ unsigned int segno);
+unsigned int f2fs_usable_blks_in_seg(struct f2fs_sb_info *sbi,
+ unsigned int segno);
/*
* checkpoint.c
*/
-void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io);
+void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io,
+ unsigned char reason);
+void f2fs_flush_ckpt_thread(struct f2fs_sb_info *sbi);
struct page *f2fs_grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
-struct page *f2fs_get_meta_page_nofail(struct f2fs_sb_info *sbi, pgoff_t index);
+struct page *f2fs_get_meta_page_retry(struct f2fs_sb_info *sbi, pgoff_t index);
struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index);
bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
block_t blkaddr, int type);
@@ -3414,19 +3700,24 @@
int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi);
void f2fs_update_dirty_page(struct inode *inode, struct page *page);
void f2fs_remove_dirty_inode(struct inode *inode);
-int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type);
+int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type,
+ bool from_cp);
void f2fs_wait_on_all_pages(struct f2fs_sb_info *sbi, int type);
+u64 f2fs_get_sectors_written(struct f2fs_sb_info *sbi);
int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc);
void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi);
int __init f2fs_create_checkpoint_caches(void);
void f2fs_destroy_checkpoint_caches(void);
+int f2fs_issue_checkpoint(struct f2fs_sb_info *sbi);
+int f2fs_start_ckpt_thread(struct f2fs_sb_info *sbi);
+void f2fs_stop_ckpt_thread(struct f2fs_sb_info *sbi);
+void f2fs_init_ckpt_req_control(struct f2fs_sb_info *sbi);
/*
* data.c
*/
int __init f2fs_init_bioset(void);
void f2fs_destroy_bioset(void);
-struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, int npages, bool noio);
int f2fs_init_bio_entry_cache(void);
void f2fs_destroy_bio_entry_cache(void);
void f2fs_submit_bio(struct f2fs_sb_info *sbi,
@@ -3451,9 +3742,6 @@
int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index);
int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from);
int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index);
-int f2fs_mpage_readpages(struct address_space *mapping,
- struct list_head *pages, struct page *page,
- unsigned nr_pages, bool is_readahead);
struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
int op_flags, bool for_write);
struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index);
@@ -3462,7 +3750,7 @@
struct page *f2fs_get_new_data_page(struct inode *inode,
struct page *ipage, pgoff_t index, bool new_i_size);
int f2fs_do_write_data_page(struct f2fs_io_info *fio);
-void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock);
+void f2fs_do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock);
int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
int create, int flag);
int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
@@ -3474,7 +3762,7 @@
struct bio **bio, sector_t *last_block,
struct writeback_control *wbc,
enum iostat_type io_type,
- int compr_blocks);
+ int compr_blocks, bool allow_balance);
void f2fs_invalidate_page(struct page *page, unsigned int offset,
unsigned int length);
int f2fs_release_page(struct page *page, gfp_t wait);
@@ -3483,7 +3771,7 @@
struct page *page, enum migrate_mode mode);
#endif
bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len);
-void f2fs_clear_radix_tree_dirty_tag(struct page *page);
+void f2fs_clear_page_cache_dirty_tag(struct page *page);
int f2fs_init_post_read_processing(void);
void f2fs_destroy_post_read_processing(void);
int f2fs_init_post_read_wq(struct f2fs_sb_info *sbi);
@@ -3495,16 +3783,20 @@
int f2fs_start_gc_thread(struct f2fs_sb_info *sbi);
void f2fs_stop_gc_thread(struct f2fs_sb_info *sbi);
block_t f2fs_start_bidx_of_node(unsigned int node_ofs, struct inode *inode);
-int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background,
+int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background, bool force,
unsigned int segno);
void f2fs_build_gc_manager(struct f2fs_sb_info *sbi);
-int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count);
+int f2fs_resize_fs(struct file *filp, __u64 block_count);
+int __init f2fs_create_garbage_collection_cache(void);
+void f2fs_destroy_garbage_collection_cache(void);
/*
* recovery.c
*/
int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only);
bool f2fs_space_for_roll_forward(struct f2fs_sb_info *sbi);
+int __init f2fs_create_recovery_cache(void);
+void f2fs_destroy_recovery_cache(void);
/*
* debug.c
@@ -3515,9 +3807,19 @@
struct f2fs_sb_info *sbi;
int all_area_segs, sit_area_segs, nat_area_segs, ssa_area_segs;
int main_area_segs, main_area_sections, main_area_zones;
- unsigned long long hit_largest, hit_cached, hit_rbtree;
- unsigned long long hit_total, total_ext;
- int ext_tree, zombie_tree, ext_node;
+ unsigned long long hit_cached[NR_EXTENT_CACHES];
+ unsigned long long hit_rbtree[NR_EXTENT_CACHES];
+ unsigned long long total_ext[NR_EXTENT_CACHES];
+ unsigned long long hit_total[NR_EXTENT_CACHES];
+ int ext_tree[NR_EXTENT_CACHES];
+ int zombie_tree[NR_EXTENT_CACHES];
+ int ext_node[NR_EXTENT_CACHES];
+ /* to count memory footprint */
+ unsigned long long ext_mem[NR_EXTENT_CACHES];
+ /* for read extent cache */
+ unsigned long long hit_largest;
+ /* for block age extent cache */
+ unsigned long long allocated_data_blocks;
int ndirty_node, ndirty_dent, ndirty_meta, ndirty_imeta;
int ndirty_data, ndirty_qdata;
int inmem_pages;
@@ -3533,14 +3835,18 @@
int nr_discarding, nr_discarded;
int nr_discard_cmd;
unsigned int undiscard_blks;
+ int nr_issued_ckpt, nr_total_ckpt, nr_queued_ckpt;
+ unsigned int cur_ckpt_time, peak_ckpt_time;
int inline_xattr, inline_inode, inline_dir, append, update, orphans;
- int compr_inode, compr_blocks;
+ int compr_inode;
+ unsigned long long compr_blocks;
int aw_cnt, max_aw_cnt, vw_cnt, max_vw_cnt;
unsigned int valid_count, valid_node_count, valid_inode_count, discard_blks;
unsigned int bimodal, avg_vblocks;
int util_free, util_valid, util_invalid;
int rsvd_segs, overp_segs;
- int dirty_count, node_pages, meta_pages;
+ int dirty_count, node_pages, meta_pages, compress_pages;
+ int compress_page_hit;
int prefree_count, call_count, cp_count, bg_cp_count;
int tot_segs, node_segs, data_segs, free_segs, free_secs;
int bg_node_segs, bg_data_segs;
@@ -3550,6 +3856,9 @@
int curseg[NR_CURSEG_TYPE];
int cursec[NR_CURSEG_TYPE];
int curzone[NR_CURSEG_TYPE];
+ unsigned int dirty_seg[NR_CURSEG_TYPE];
+ unsigned int full_seg[NR_CURSEG_TYPE];
+ unsigned int valid_blks[NR_CURSEG_TYPE];
unsigned int meta_count[META_MAX];
unsigned int segment_count[2];
@@ -3571,10 +3880,10 @@
#define stat_other_skip_bggc_count(sbi) ((sbi)->other_skip_bggc++)
#define stat_inc_dirty_inode(sbi, type) ((sbi)->ndirty_inode[type]++)
#define stat_dec_dirty_inode(sbi, type) ((sbi)->ndirty_inode[type]--)
-#define stat_inc_total_hit(sbi) (atomic64_inc(&(sbi)->total_hit_ext))
-#define stat_inc_rbtree_node_hit(sbi) (atomic64_inc(&(sbi)->read_hit_rbtree))
+#define stat_inc_total_hit(sbi, type) (atomic64_inc(&(sbi)->total_hit_ext[type]))
+#define stat_inc_rbtree_node_hit(sbi, type) (atomic64_inc(&(sbi)->read_hit_rbtree[type]))
#define stat_inc_largest_node_hit(sbi) (atomic64_inc(&(sbi)->read_hit_largest))
-#define stat_inc_cached_node_hit(sbi) (atomic64_inc(&(sbi)->read_hit_cached))
+#define stat_inc_cached_node_hit(sbi, type) (atomic64_inc(&(sbi)->read_hit_cached[type]))
#define stat_inc_inline_xattr(inode) \
do { \
if (f2fs_has_inline_xattr(inode)) \
@@ -3616,9 +3925,9 @@
(atomic_dec(&F2FS_I_SB(inode)->compr_inode)); \
} while (0)
#define stat_add_compr_blocks(inode, blocks) \
- (atomic_add(blocks, &F2FS_I_SB(inode)->compr_blocks))
+ (atomic64_add(blocks, &F2FS_I_SB(inode)->compr_blocks))
#define stat_sub_compr_blocks(inode, blocks) \
- (atomic_sub(blocks, &F2FS_I_SB(inode)->compr_blocks))
+ (atomic64_sub(blocks, &F2FS_I_SB(inode)->compr_blocks))
#define stat_inc_meta_count(sbi, blkaddr) \
do { \
if (blkaddr < SIT_I(sbi)->sit_base_addr) \
@@ -3700,10 +4009,10 @@
#define stat_other_skip_bggc_count(sbi) do { } while (0)
#define stat_inc_dirty_inode(sbi, type) do { } while (0)
#define stat_dec_dirty_inode(sbi, type) do { } while (0)
-#define stat_inc_total_hit(sbi) do { } while (0)
-#define stat_inc_rbtree_node_hit(sbi) do { } while (0)
+#define stat_inc_total_hit(sbi, type) do { } while (0)
+#define stat_inc_rbtree_node_hit(sbi, type) do { } while (0)
#define stat_inc_largest_node_hit(sbi) do { } while (0)
-#define stat_inc_cached_node_hit(sbi) do { } while (0)
+#define stat_inc_cached_node_hit(sbi, type) do { } while (0)
#define stat_inc_inline_xattr(inode) do { } while (0)
#define stat_dec_inline_xattr(inode) do { } while (0)
#define stat_inc_inline_inode(inode) do { } while (0)
@@ -3714,8 +4023,6 @@
#define stat_dec_compr_inode(inode) do { } while (0)
#define stat_add_compr_blocks(inode, blocks) do { } while (0)
#define stat_sub_compr_blocks(inode, blocks) do { } while (0)
-#define stat_inc_atomic_write(inode) do { } while (0)
-#define stat_dec_atomic_write(inode) do { } while (0)
#define stat_update_max_atomic_write(inode) do { } while (0)
#define stat_inc_volatile_write(inode) do { } while (0)
#define stat_dec_volatile_write(inode) do { } while (0)
@@ -3752,6 +4059,7 @@
* inline.c
*/
bool f2fs_may_inline_data(struct inode *inode);
+bool f2fs_sanity_check_inline_data(struct inode *inode);
bool f2fs_may_inline_dentry(struct inode *inode);
void f2fs_do_read_inline_data(struct page *page, struct page *ipage);
void f2fs_truncate_inline_inode(struct inode *inode,
@@ -3794,6 +4102,10 @@
*/
struct rb_entry *f2fs_lookup_rb_tree(struct rb_root_cached *root,
struct rb_entry *cached_re, unsigned int ofs);
+struct rb_node **f2fs_lookup_rb_tree_ext(struct f2fs_sb_info *sbi,
+ struct rb_root_cached *root,
+ struct rb_node **parent,
+ unsigned long long key, bool *left_most);
struct rb_node **f2fs_lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi,
struct rb_root_cached *root,
struct rb_node **parent,
@@ -3804,20 +4116,34 @@
struct rb_node ***insert_p, struct rb_node **insert_parent,
bool force, bool *leftmost);
bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi,
- struct rb_root_cached *root);
-unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink);
-bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext);
+ struct rb_root_cached *root, bool check_key);
+void f2fs_init_extent_tree(struct inode *inode);
void f2fs_drop_extent_tree(struct inode *inode);
-unsigned int f2fs_destroy_extent_node(struct inode *inode);
+void f2fs_destroy_extent_node(struct inode *inode);
void f2fs_destroy_extent_tree(struct inode *inode);
-bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs,
- struct extent_info *ei);
-void f2fs_update_extent_cache(struct dnode_of_data *dn);
-void f2fs_update_extent_cache_range(struct dnode_of_data *dn,
- pgoff_t fofs, block_t blkaddr, unsigned int len);
void f2fs_init_extent_cache_info(struct f2fs_sb_info *sbi);
int __init f2fs_create_extent_cache(void);
void f2fs_destroy_extent_cache(void);
+
+/* read extent cache ops */
+void f2fs_init_read_extent_tree(struct inode *inode, struct page *ipage);
+bool f2fs_lookup_read_extent_cache(struct inode *inode, pgoff_t pgofs,
+ struct extent_info *ei);
+void f2fs_update_read_extent_cache(struct dnode_of_data *dn);
+void f2fs_update_read_extent_cache_range(struct dnode_of_data *dn,
+ pgoff_t fofs, block_t blkaddr, unsigned int len);
+unsigned int f2fs_shrink_read_extent_tree(struct f2fs_sb_info *sbi,
+ int nr_shrink);
+
+/* block age extent cache ops */
+void f2fs_init_age_extent_tree(struct inode *inode);
+bool f2fs_lookup_age_extent_cache(struct inode *inode, pgoff_t pgofs,
+ struct extent_info *ei);
+void f2fs_update_age_extent_cache(struct dnode_of_data *dn);
+void f2fs_update_age_extent_cache_range(struct dnode_of_data *dn,
+ pgoff_t fofs, unsigned int len);
+unsigned int f2fs_shrink_age_extent_tree(struct f2fs_sb_info *sbi,
+ int nr_shrink);
/*
* sysfs.c
@@ -3871,7 +4197,9 @@
bool f2fs_is_compress_backend_ready(struct inode *inode);
int f2fs_init_compress_mempool(void);
void f2fs_destroy_compress_mempool(void);
-void f2fs_decompress_pages(struct bio *bio, struct page *page, bool verity);
+void f2fs_decompress_cluster(struct decompress_io_ctx *dic, bool in_task);
+void f2fs_end_read_compressed_page(struct page *page, bool failed,
+ block_t blkaddr, bool in_task);
bool f2fs_cluster_is_empty(struct compress_ctx *cc);
bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index);
void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct page *page);
@@ -3880,16 +4208,45 @@
struct writeback_control *wbc,
enum iostat_type io_type);
int f2fs_is_compressed_cluster(struct inode *inode, pgoff_t index);
+void f2fs_update_read_extent_tree_range_compressed(struct inode *inode,
+ pgoff_t fofs, block_t blkaddr,
+ unsigned int llen, unsigned int c_len);
int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
unsigned nr_pages, sector_t *last_block_in_bio,
bool is_readahead, bool for_write);
struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc);
-void f2fs_free_dic(struct decompress_io_ctx *dic);
-void f2fs_decompress_end_io(struct page **rpages,
- unsigned int cluster_size, bool err, bool verity);
+void f2fs_decompress_end_io(struct decompress_io_ctx *dic, bool failed,
+ bool in_task);
+void f2fs_put_page_dic(struct page *page, bool in_task);
+unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn);
int f2fs_init_compress_ctx(struct compress_ctx *cc);
-void f2fs_destroy_compress_ctx(struct compress_ctx *cc);
+void f2fs_destroy_compress_ctx(struct compress_ctx *cc, bool reuse);
void f2fs_init_compress_info(struct f2fs_sb_info *sbi);
+int f2fs_init_compress_inode(struct f2fs_sb_info *sbi);
+void f2fs_destroy_compress_inode(struct f2fs_sb_info *sbi);
+int f2fs_init_page_array_cache(struct f2fs_sb_info *sbi);
+void f2fs_destroy_page_array_cache(struct f2fs_sb_info *sbi);
+int __init f2fs_init_compress_cache(void);
+void f2fs_destroy_compress_cache(void);
+struct address_space *COMPRESS_MAPPING(struct f2fs_sb_info *sbi);
+void f2fs_invalidate_compress_page(struct f2fs_sb_info *sbi, block_t blkaddr);
+void f2fs_cache_compressed_page(struct f2fs_sb_info *sbi, struct page *page,
+ nid_t ino, block_t blkaddr);
+bool f2fs_load_compressed_page(struct f2fs_sb_info *sbi, struct page *page,
+ block_t blkaddr);
+void f2fs_invalidate_compress_pages(struct f2fs_sb_info *sbi, nid_t ino);
+#define inc_compr_inode_stat(inode) \
+ do { \
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode); \
+ sbi->compr_new_inode++; \
+ } while (0)
+#define add_compr_block_stat(inode, blocks) \
+ do { \
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode); \
+ int diff = F2FS_I(inode)->i_cluster_size - blocks; \
+ sbi->compr_written_block += blocks; \
+ sbi->compr_saved_block += diff; \
+ } while (0)
#else
static inline bool f2fs_is_compressed_page(struct page *page) { return false; }
static inline bool f2fs_is_compress_backend_ready(struct inode *inode)
@@ -3906,42 +4263,83 @@
}
static inline int f2fs_init_compress_mempool(void) { return 0; }
static inline void f2fs_destroy_compress_mempool(void) { }
+static inline void f2fs_decompress_cluster(struct decompress_io_ctx *dic,
+ bool in_task) { }
+static inline void f2fs_end_read_compressed_page(struct page *page,
+ bool failed, block_t blkaddr, bool in_task)
+{
+ WARN_ON_ONCE(1);
+}
+static inline void f2fs_put_page_dic(struct page *page, bool in_task)
+{
+ WARN_ON_ONCE(1);
+}
+static inline unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn) { return 0; }
+static inline int f2fs_init_compress_inode(struct f2fs_sb_info *sbi) { return 0; }
+static inline void f2fs_destroy_compress_inode(struct f2fs_sb_info *sbi) { }
+static inline int f2fs_init_page_array_cache(struct f2fs_sb_info *sbi) { return 0; }
+static inline void f2fs_destroy_page_array_cache(struct f2fs_sb_info *sbi) { }
+static inline int __init f2fs_init_compress_cache(void) { return 0; }
+static inline void f2fs_destroy_compress_cache(void) { }
+static inline void f2fs_invalidate_compress_page(struct f2fs_sb_info *sbi,
+ block_t blkaddr) { }
+static inline void f2fs_cache_compressed_page(struct f2fs_sb_info *sbi,
+ struct page *page, nid_t ino, block_t blkaddr) { }
+static inline bool f2fs_load_compressed_page(struct f2fs_sb_info *sbi,
+ struct page *page, block_t blkaddr) { return false; }
+static inline void f2fs_invalidate_compress_pages(struct f2fs_sb_info *sbi,
+ nid_t ino) { }
+#define inc_compr_inode_stat(inode) do { } while (0)
+static inline void f2fs_update_read_extent_tree_range_compressed(
+ struct inode *inode,
+ pgoff_t fofs, block_t blkaddr,
+ unsigned int llen, unsigned int c_len) { }
#endif
-static inline void set_compress_context(struct inode *inode)
+static inline int set_compress_context(struct inode *inode)
{
+#ifdef CONFIG_F2FS_FS_COMPRESSION
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
F2FS_I(inode)->i_compress_algorithm =
F2FS_OPTION(sbi).compress_algorithm;
F2FS_I(inode)->i_log_cluster_size =
F2FS_OPTION(sbi).compress_log_size;
+ F2FS_I(inode)->i_compress_flag =
+ F2FS_OPTION(sbi).compress_chksum ?
+ 1 << COMPRESS_CHKSUM : 0;
F2FS_I(inode)->i_cluster_size =
1 << F2FS_I(inode)->i_log_cluster_size;
+ if (F2FS_I(inode)->i_compress_algorithm == COMPRESS_LZ4 &&
+ F2FS_OPTION(sbi).compress_level)
+ F2FS_I(inode)->i_compress_flag |=
+ F2FS_OPTION(sbi).compress_level <<
+ COMPRESS_LEVEL_OFFSET;
F2FS_I(inode)->i_flags |= F2FS_COMPR_FL;
set_inode_flag(inode, FI_COMPRESSED_FILE);
stat_inc_compr_inode(inode);
+ inc_compr_inode_stat(inode);
f2fs_mark_inode_dirty_sync(inode, true);
+ return 0;
+#else
+ return -EOPNOTSUPP;
+#endif
}
-static inline u64 f2fs_disable_compressed_file(struct inode *inode)
+static inline bool f2fs_disable_compressed_file(struct inode *inode)
{
struct f2fs_inode_info *fi = F2FS_I(inode);
if (!f2fs_compressed_file(inode))
- return 0;
- if (S_ISREG(inode->i_mode)) {
- if (get_dirty_pages(inode))
- return 1;
- if (fi->i_compr_blocks)
- return fi->i_compr_blocks;
- }
+ return true;
+ if (S_ISREG(inode->i_mode) && F2FS_HAS_BLOCKS(inode))
+ return false;
fi->i_flags &= ~F2FS_COMPR_FL;
stat_dec_compr_inode(inode);
clear_inode_flag(inode, FI_COMPRESSED_FILE);
f2fs_mark_inode_dirty_sync(inode, true);
- return 0;
+ return true;
}
#define F2FS_FEATURE_FUNCS(name, flagname) \
@@ -3963,6 +4361,7 @@
F2FS_FEATURE_FUNCS(sb_chksum, SB_CHKSUM);
F2FS_FEATURE_FUNCS(casefold, CASEFOLD);
F2FS_FEATURE_FUNCS(compression, COMPRESSION);
+F2FS_FEATURE_FUNCS(readonly, RO);
#ifdef CONFIG_BLK_DEV_ZONED
static inline bool f2fs_blkz_is_seq(struct f2fs_sb_info *sbi, int devi,
@@ -4022,20 +4421,9 @@
return F2FS_OPTION(sbi).fs_mode == FS_MODE_LFS;
}
-static inline bool f2fs_may_encrypt(struct inode *dir, struct inode *inode)
+static inline bool f2fs_low_mem_mode(struct f2fs_sb_info *sbi)
{
-#ifdef CONFIG_FS_ENCRYPTION
- struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
- umode_t mode = inode->i_mode;
-
- /*
- * If the directory encrypted or dummy encryption enabled,
- * then we should encrypt the inode.
- */
- if (IS_ENCRYPTED(dir) || DUMMY_ENCRYPTION_ENABLED(sbi))
- return (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode));
-#endif
- return false;
+ return F2FS_OPTION(sbi).memory_mode == MEMORY_MODE_LOW;
}
static inline bool f2fs_may_compress(struct inode *inode)
@@ -4051,16 +4439,17 @@
u64 blocks, bool add)
{
int diff = F2FS_I(inode)->i_cluster_size - blocks;
+ struct f2fs_inode_info *fi = F2FS_I(inode);
/* don't update i_compr_blocks if saved blocks were released */
- if (!add && !F2FS_I(inode)->i_compr_blocks)
+ if (!add && !atomic_read(&fi->i_compr_blocks))
return;
if (add) {
- F2FS_I(inode)->i_compr_blocks += diff;
+ atomic_add(diff, &fi->i_compr_blocks);
stat_add_compr_blocks(inode, diff);
} else {
- F2FS_I(inode)->i_compr_blocks -= diff;
+ atomic_sub(diff, &fi->i_compr_blocks);
stat_sub_compr_blocks(inode, diff);
}
f2fs_mark_inode_dirty_sync(inode, true);
@@ -4113,13 +4502,18 @@
if (F2FS_IO_ALIGNED(sbi))
return true;
}
- if (is_sbi_flag_set(F2FS_I_SB(inode), SBI_CP_DISABLED) &&
- !IS_SWAPFILE(inode))
+ if (is_sbi_flag_set(F2FS_I_SB(inode), SBI_CP_DISABLED))
return true;
return false;
}
+static inline bool f2fs_need_verity(const struct inode *inode, pgoff_t idx)
+{
+ return fsverity_active(inode) &&
+ idx < DIV_ROUND_UP(inode->i_size, PAGE_SIZE);
+}
+
#ifdef CONFIG_F2FS_FAULT_INJECTION
extern void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate,
unsigned int type);
--
Gitblit v1.6.2