aboutsummaryrefslogtreecommitdiff
path: root/fs/ceph/super.h
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ceph/super.h')
-rw-r--r--fs/ceph/super.h288
1 files changed, 186 insertions, 102 deletions
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 1886294e12f..12b20744e38 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -13,20 +13,28 @@
#include <linux/wait.h>
#include <linux/writeback.h>
#include <linux/slab.h>
+#include <linux/posix_acl.h>
#include <linux/ceph/libceph.h>
+#ifdef CONFIG_CEPH_FSCACHE
+#include <linux/fscache.h>
+#endif
+
/* f_type in struct statfs */
#define CEPH_SUPER_MAGIC 0x00c36400
/* large granularity for statfs utilization stats to facilitate
* large volume sizes on 32-bit machines. */
-#define CEPH_BLOCK_SHIFT 20 /* 1 MB */
+#define CEPH_BLOCK_SHIFT 22 /* 4 MB */
#define CEPH_BLOCK (1 << CEPH_BLOCK_SHIFT)
#define CEPH_MOUNT_OPT_DIRSTAT (1<<4) /* `cat dirname` for stats */
#define CEPH_MOUNT_OPT_RBYTES (1<<5) /* dir st_bytes = rbytes */
#define CEPH_MOUNT_OPT_NOASYNCREADDIR (1<<7) /* no dcache readdir */
+#define CEPH_MOUNT_OPT_INO32 (1<<8) /* 32 bit inos */
+#define CEPH_MOUNT_OPT_DCACHE (1<<9) /* use dcache for readdir etc */
+#define CEPH_MOUNT_OPT_FSCACHE (1<<10) /* use fscache */
#define CEPH_MOUNT_OPT_DEFAULT (CEPH_MOUNT_OPT_RBYTES)
@@ -35,6 +43,8 @@
#define ceph_test_mount_opt(fsc, opt) \
(!!((fsc)->mount_options->flags & CEPH_MOUNT_OPT_##opt))
+#define CEPH_RSIZE_DEFAULT 0 /* max read size */
+#define CEPH_RASIZE_DEFAULT (8192*1024) /* readahead */
#define CEPH_MAX_READDIR_DEFAULT 1024
#define CEPH_MAX_READDIR_BYTES_DEFAULT (512*1024)
#define CEPH_SNAPDIRNAME_DEFAULT ".snap"
@@ -43,8 +53,9 @@ struct ceph_mount_options {
int flags;
int sb_flags;
- int wsize;
- int rsize; /* max readahead */
+ int wsize; /* max write size */
+ int rsize; /* max read size */
+ int rasize; /* max readahead */
int congestion_kb; /* max writeback in flight */
int caps_wanted_delay_min, caps_wanted_delay_max;
int cap_release_safety;
@@ -85,6 +96,11 @@ struct ceph_fs_client {
struct dentry *debugfs_bdi;
struct dentry *debugfs_mdsc, *debugfs_mdsmap;
#endif
+
+#ifdef CONFIG_CEPH_FSCACHE
+ struct fscache_cookie *fscache;
+ struct workqueue_struct *revalidate_wq;
+#endif
};
@@ -132,9 +148,9 @@ struct ceph_cap_snap {
int issued, dirty;
struct ceph_snap_context *context;
- mode_t mode;
- uid_t uid;
- gid_t gid;
+ umode_t mode;
+ kuid_t uid;
+ kgid_t gid;
struct ceph_buffer *xattr_blob;
u64 xattr_version;
@@ -233,12 +249,16 @@ struct ceph_inode_xattrs_info {
struct ceph_inode_info {
struct ceph_vino i_vino; /* ceph ino + snap */
+ spinlock_t i_ceph_lock;
+
u64 i_version;
u32 i_time_warp_seq;
unsigned i_ceph_flags;
- unsigned long i_release_count;
+ atomic_t i_release_count;
+ atomic_t i_complete_count;
+ struct ceph_dir_layout i_dir_layout;
struct ceph_file_layout i_layout;
char *i_symlink;
@@ -246,14 +266,13 @@ struct ceph_inode_info {
struct timespec i_rctime;
u64 i_rbytes, i_rfiles, i_rsubdirs;
u64 i_files, i_subdirs;
- u64 i_max_offset; /* largest readdir offset, set with I_COMPLETE */
struct rb_root i_fragtree;
struct mutex i_fragtree_mutex;
struct ceph_inode_xattrs_info i_xattrs;
- /* capabilities. protected _both_ by i_lock and cap->session's
+ /* capabilities. protected _both_ by i_ceph_lock and cap->session's
* s_mutex. */
struct rb_root i_caps; /* cap list */
struct ceph_cap *i_auth_cap; /* authoritative cap, if any */
@@ -268,9 +287,6 @@ struct ceph_inode_info {
unsigned long i_hold_caps_min; /* jiffies */
unsigned long i_hold_caps_max; /* jiffies */
struct list_head i_cap_delay_list; /* for delayed cap release to mds */
- int i_cap_exporting_mds; /* to handle cap migration between */
- unsigned i_cap_exporting_mseq; /* mds's. */
- unsigned i_cap_exporting_issued;
struct ceph_cap_reservation i_cap_migration_resv;
struct list_head i_cap_snaps; /* snapped state pending flush to mds */
struct ceph_snap_context *i_head_snapc; /* set if wr_buffer_head > 0 or
@@ -279,6 +295,7 @@ struct ceph_inode_info {
int i_nr_by_mode[CEPH_FILE_MODE_NUM]; /* open file counts */
+ struct mutex i_truncate_mutex;
u32 i_truncate_seq; /* last truncate to smaller size */
u64 i_truncate_size; /* and the size we last truncated down to */
int i_truncate_pending; /* still need to call vmtruncate */
@@ -290,12 +307,10 @@ struct ceph_inode_info {
/* held references to caps */
int i_pin_ref;
- int i_rd_ref, i_rdcache_ref, i_wr_ref;
+ int i_rd_ref, i_rdcache_ref, i_wr_ref, i_wb_ref;
int i_wrbuffer_ref, i_wrbuffer_ref_head;
u32 i_shared_gen; /* increment each time we get FILE_SHARED */
- u32 i_rdcache_gen; /* we increment this each time we get
- FILE_CACHE. If it's non-zero, we
- _may_ have cached pages. */
+ u32 i_rdcache_gen; /* incremented each time we get FILE_CACHE. */
u32 i_rdcache_revoking; /* RDCACHE gen to async invalidate, if any */
struct list_head i_unsafe_writes; /* uncommitted sync writes */
@@ -312,6 +327,11 @@ struct ceph_inode_info {
struct work_struct i_vmtruncate_work;
+#ifdef CONFIG_CEPH_FSCACHE
+ struct fscache_cookie *fscache;
+ u32 i_fscache_gen; /* sequence, for delayed fscache validate */
+ struct work_struct i_revalidate_work;
+#endif
struct inode vfs_inode; /* at end */
};
@@ -320,6 +340,16 @@ static inline struct ceph_inode_info *ceph_inode(struct inode *inode)
return container_of(inode, struct ceph_inode_info, vfs_inode);
}
+static inline struct ceph_fs_client *ceph_inode_to_client(struct inode *inode)
+{
+ return (struct ceph_fs_client *)inode->i_sb->s_fs_info;
+}
+
+static inline struct ceph_fs_client *ceph_sb_to_client(struct super_block *sb)
+{
+ return (struct ceph_fs_client *)sb->s_fs_info;
+}
+
static inline struct ceph_vino ceph_vino(struct inode *inode)
{
return ceph_inode(inode)->i_vino;
@@ -328,18 +358,49 @@ static inline struct ceph_vino ceph_vino(struct inode *inode)
/*
* ino_t is <64 bits on many architectures, blech.
*
- * don't include snap in ino hash, at least for now.
+ * i_ino (kernel inode) st_ino (userspace)
+ * i386 32 32
+ * x86_64+ino32 64 32
+ * x86_64 64 64
+ */
+static inline u32 ceph_ino_to_ino32(__u64 vino)
+{
+ u32 ino = vino & 0xffffffff;
+ ino ^= vino >> 32;
+ if (!ino)
+ ino = 2;
+ return ino;
+}
+
+/*
+ * kernel i_ino value
*/
static inline ino_t ceph_vino_to_ino(struct ceph_vino vino)
{
- ino_t ino = (ino_t)vino.ino; /* ^ (vino.snap << 20); */
#if BITS_PER_LONG == 32
- ino ^= vino.ino >> (sizeof(u64)-sizeof(ino_t)) * 8;
- if (!ino)
- ino = 1;
+ return ceph_ino_to_ino32(vino.ino);
+#else
+ return (ino_t)vino.ino;
#endif
+}
+
+/*
+ * user-visible ino (stat, filldir)
+ */
+#if BITS_PER_LONG == 32
+static inline ino_t ceph_translate_ino(struct super_block *sb, ino_t ino)
+{
+ return ino;
+}
+#else
+static inline ino_t ceph_translate_ino(struct super_block *sb, ino_t ino)
+{
+ if (ceph_test_mount_opt(ceph_sb_to_client(sb), INO32))
+ ino = ceph_ino_to_ino32(ino);
return ino;
}
+#endif
+
/* for printf-style formatting */
#define ceph_vinop(i) ceph_inode(i)->i_vino.ino, ceph_inode(i)->i_vino.snap
@@ -372,38 +433,35 @@ static inline struct inode *ceph_find_inode(struct super_block *sb,
/*
* Ceph inode.
*/
-#define CEPH_I_COMPLETE 1 /* we have complete directory cached */
#define CEPH_I_NODELAY 4 /* do not delay cap release */
#define CEPH_I_FLUSH 8 /* do not delay flush of dirty metadata */
#define CEPH_I_NOFLUSH 16 /* do not flush dirty caps */
-static inline void ceph_i_clear(struct inode *inode, unsigned mask)
+static inline void __ceph_dir_set_complete(struct ceph_inode_info *ci,
+ int release_count)
{
- struct ceph_inode_info *ci = ceph_inode(inode);
-
- spin_lock(&inode->i_lock);
- ci->i_ceph_flags &= ~mask;
- spin_unlock(&inode->i_lock);
+ atomic_set(&ci->i_complete_count, release_count);
}
-static inline void ceph_i_set(struct inode *inode, unsigned mask)
+static inline void __ceph_dir_clear_complete(struct ceph_inode_info *ci)
{
- struct ceph_inode_info *ci = ceph_inode(inode);
+ atomic_inc(&ci->i_release_count);
+}
- spin_lock(&inode->i_lock);
- ci->i_ceph_flags |= mask;
- spin_unlock(&inode->i_lock);
+static inline bool __ceph_dir_is_complete(struct ceph_inode_info *ci)
+{
+ return atomic_read(&ci->i_complete_count) ==
+ atomic_read(&ci->i_release_count);
}
-static inline bool ceph_i_test(struct inode *inode, unsigned mask)
+static inline void ceph_dir_clear_complete(struct inode *inode)
{
- struct ceph_inode_info *ci = ceph_inode(inode);
- bool r;
+ __ceph_dir_clear_complete(ceph_inode(inode));
+}
- spin_lock(&inode->i_lock);
- r = (ci->i_ceph_flags & mask) == mask;
- spin_unlock(&inode->i_lock);
- return r;
+static inline bool ceph_dir_is_complete(struct inode *inode)
+{
+ return __ceph_dir_is_complete(ceph_inode(inode));
}
@@ -429,13 +487,6 @@ static inline loff_t ceph_make_fpos(unsigned frag, unsigned off)
return ((loff_t)frag << 32) | (loff_t)off;
}
-static inline int ceph_set_ino_cb(struct inode *inode, void *data)
-{
- ceph_inode(inode)->i_vino = *(struct ceph_vino *)data;
- inode->i_ino = ceph_vino_to_ino(*(struct ceph_vino *)data);
- return 0;
-}
-
/*
* caps helpers
*/
@@ -452,9 +503,9 @@ extern int __ceph_caps_issued_other(struct ceph_inode_info *ci,
static inline int ceph_caps_issued(struct ceph_inode_info *ci)
{
int issued;
- spin_lock(&ci->vfs_inode.i_lock);
+ spin_lock(&ci->i_ceph_lock);
issued = __ceph_caps_issued(ci, NULL);
- spin_unlock(&ci->vfs_inode.i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return issued;
}
@@ -462,9 +513,9 @@ static inline int ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask,
int touch)
{
int r;
- spin_lock(&ci->vfs_inode.i_lock);
+ spin_lock(&ci->i_ceph_lock);
r = __ceph_caps_issued_mask(ci, mask, touch);
- spin_unlock(&ci->vfs_inode.i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return r;
}
@@ -472,8 +523,10 @@ static inline int __ceph_caps_dirty(struct ceph_inode_info *ci)
{
return ci->i_dirty_caps | ci->i_flushing_caps;
}
-extern void __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask);
+extern int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask);
+extern int __ceph_caps_revoking_other(struct ceph_inode_info *ci,
+ struct ceph_cap *ocap, int mask);
extern int ceph_caps_revoking(struct ceph_inode_info *ci, int mask);
extern int __ceph_caps_used(struct ceph_inode_info *ci);
@@ -496,7 +549,7 @@ extern int __ceph_caps_mds_wanted(struct ceph_inode_info *ci);
extern void ceph_caps_init(struct ceph_mds_client *mdsc);
extern void ceph_caps_finalize(struct ceph_mds_client *mdsc);
extern void ceph_adjust_min_caps(struct ceph_mds_client *mdsc, int delta);
-extern int ceph_reserve_caps(struct ceph_mds_client *mdsc,
+extern void ceph_reserve_caps(struct ceph_mds_client *mdsc,
struct ceph_cap_reservation *ctx, int need);
extern int ceph_unreserve_caps(struct ceph_mds_client *mdsc,
struct ceph_cap_reservation *ctx);
@@ -504,34 +557,28 @@ extern void ceph_reservation_status(struct ceph_fs_client *client,
int *total, int *avail, int *used,
int *reserved, int *min);
-static inline struct ceph_fs_client *ceph_inode_to_client(struct inode *inode)
-{
- return (struct ceph_fs_client *)inode->i_sb->s_fs_info;
-}
-
-static inline struct ceph_fs_client *ceph_sb_to_client(struct super_block *sb)
-{
- return (struct ceph_fs_client *)sb->s_fs_info;
-}
/*
* we keep buffered readdir results attached to file->private_data
*/
+#define CEPH_F_SYNC 1
+#define CEPH_F_ATEND 2
+
struct ceph_file_info {
- int fmode; /* initialized on open */
+ short fmode; /* initialized on open */
+ short flags; /* CEPH_F_* */
/* readdir: position within the dir */
u32 frag;
struct ceph_mds_request *last_readdir;
- int at_end;
/* readdir: position within a frag */
unsigned offset; /* offset of last chunk, adjusted for . and .. */
- u64 next_offset; /* offset of next chunk (last_name's + 1) */
+ unsigned next_offset; /* offset of next chunk (last_name's + 1) */
char *last_name; /* last entry in previous chunk */
struct dentry *dentry; /* next dentry (for dcache readdir) */
- unsigned long dir_release_count;
+ int dir_release_count;
/* used for -o dirstat read() on directory thing */
char *dir_info;
@@ -559,9 +606,9 @@ struct ceph_snap_realm {
u64 parent_since; /* snapid when our current parent became so */
u64 *prior_parent_snaps; /* snaps inherited from any parents we */
- int num_prior_parent_snaps; /* had prior to parent_since */
+ u32 num_prior_parent_snaps; /* had prior to parent_since */
u64 *snaps; /* snaps specific to this realm */
- int num_snaps;
+ u32 num_snaps;
struct ceph_snap_realm *parent;
struct list_head children; /* list of child realms */
@@ -642,6 +689,7 @@ extern const struct inode_operations ceph_file_iops;
extern struct inode *ceph_alloc_inode(struct super_block *sb);
extern void ceph_destroy_inode(struct inode *inode);
+extern int ceph_drop_inode(struct inode *inode);
extern struct inode *ceph_get_inode(struct super_block *sb,
struct ceph_vino vino);
@@ -675,35 +723,75 @@ extern int ceph_getattr(struct vfsmount *mnt, struct dentry *dentry,
/* xattr.c */
extern int ceph_setxattr(struct dentry *, const char *, const void *,
size_t, int);
+int __ceph_setxattr(struct dentry *, const char *, const void *, size_t, int);
+ssize_t __ceph_getxattr(struct inode *, const char *, void *, size_t);
+int __ceph_removexattr(struct dentry *, const char *);
extern ssize_t ceph_getxattr(struct dentry *, const char *, void *, size_t);
extern ssize_t ceph_listxattr(struct dentry *, char *, size_t);
extern int ceph_removexattr(struct dentry *, const char *);
extern void __ceph_build_xattrs_blob(struct ceph_inode_info *ci);
extern void __ceph_destroy_xattrs(struct ceph_inode_info *ci);
+extern void __init ceph_xattr_init(void);
+extern void ceph_xattr_exit(void);
+
+/* acl.c */
+extern const struct xattr_handler *ceph_xattr_handlers[];
+
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+
+struct posix_acl *ceph_get_acl(struct inode *, int);
+int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+int ceph_init_acl(struct dentry *, struct inode *, struct inode *);
+
+static inline void ceph_forget_all_cached_acls(struct inode *inode)
+{
+ forget_all_cached_acls(inode);
+}
+
+#else
+
+#define ceph_get_acl NULL
+#define ceph_set_acl NULL
+
+static inline int ceph_init_acl(struct dentry *dentry, struct inode *inode,
+ struct inode *dir)
+{
+ return 0;
+}
+
+static inline int ceph_acl_chmod(struct dentry *dentry, struct inode *inode)
+{
+ return 0;
+}
+
+static inline void ceph_forget_all_cached_acls(struct inode *inode)
+{
+}
+
+#endif
/* caps.c */
extern const char *ceph_cap_string(int c);
extern void ceph_handle_caps(struct ceph_mds_session *session,
struct ceph_msg *msg);
-extern int ceph_add_cap(struct inode *inode,
- struct ceph_mds_session *session, u64 cap_id,
- int fmode, unsigned issued, unsigned wanted,
- unsigned cap, unsigned seq, u64 realmino, int flags,
- struct ceph_cap_reservation *caps_reservation);
-extern void __ceph_remove_cap(struct ceph_cap *cap);
-static inline void ceph_remove_cap(struct ceph_cap *cap)
-{
- struct inode *inode = &cap->ci->vfs_inode;
- spin_lock(&inode->i_lock);
- __ceph_remove_cap(cap);
- spin_unlock(&inode->i_lock);
-}
+extern struct ceph_cap *ceph_get_cap(struct ceph_mds_client *mdsc,
+ struct ceph_cap_reservation *ctx);
+extern void ceph_add_cap(struct inode *inode,
+ struct ceph_mds_session *session, u64 cap_id,
+ int fmode, unsigned issued, unsigned wanted,
+ unsigned cap, unsigned seq, u64 realmino, int flags,
+ struct ceph_cap **new_cap);
+extern void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release);
extern void ceph_put_cap(struct ceph_mds_client *mdsc,
struct ceph_cap *cap);
+extern int ceph_is_any_caps(struct inode *inode);
+extern void __queue_cap_release(struct ceph_mds_session *session, u64 ino,
+ u64 cap_id, u32 migrate_seq, u32 issue_seq);
extern void ceph_queue_caps_release(struct inode *inode);
extern int ceph_write_inode(struct inode *inode, struct writeback_control *wbc);
-extern int ceph_fsync(struct file *file, int datasync);
+extern int ceph_fsync(struct file *file, loff_t start, loff_t end,
+ int datasync);
extern void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc,
struct ceph_mds_session *session);
extern struct ceph_cap *ceph_get_cap_for_mds(struct ceph_inode_info *ci,
@@ -743,17 +831,11 @@ extern int ceph_mmap(struct file *file, struct vm_area_struct *vma);
/* file.c */
extern const struct file_operations ceph_file_fops;
extern const struct address_space_operations ceph_aops;
-extern int ceph_copy_to_page_vector(struct page **pages,
- const char *data,
- loff_t off, size_t len);
-extern int ceph_copy_from_page_vector(struct page **pages,
- char *data,
- loff_t off, size_t len);
-extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags);
+
extern int ceph_open(struct inode *inode, struct file *file);
-extern struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd, int mode,
- int locked_dir);
+extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
+ struct file *file, unsigned flags, umode_t mode,
+ int *opened);
extern int ceph_release(struct inode *inode, struct file *filp);
/* dir.c */
@@ -763,6 +845,8 @@ extern const struct dentry_operations ceph_dentry_ops, ceph_snap_dentry_ops,
ceph_snapdir_dentry_ops;
extern int ceph_handle_notrace_create(struct inode *dir, struct dentry *dentry);
+extern int ceph_handle_snapdir(struct ceph_mds_request *req,
+ struct dentry *dentry, int err);
extern struct dentry *ceph_finish_lookup(struct ceph_mds_request *req,
struct dentry *dentry, int err);
@@ -770,6 +854,8 @@ extern void ceph_dentry_lru_add(struct dentry *dn);
extern void ceph_dentry_lru_touch(struct dentry *dn);
extern void ceph_dentry_lru_del(struct dentry *dn);
extern void ceph_invalidate_dentry_lease(struct dentry *dentry);
+extern unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn);
+extern struct inode *ceph_get_dentry_parent_inode(struct dentry *dentry);
/*
* our d_ops vary depending on whether the inode is live,
@@ -785,21 +871,19 @@ extern long ceph_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
extern const struct export_operations ceph_export_ops;
/* locks.c */
+extern __init void ceph_flock_init(void);
extern int ceph_lock(struct file *file, int cmd, struct file_lock *fl);
extern int ceph_flock(struct file *file, int cmd, struct file_lock *fl);
extern void ceph_count_locks(struct inode *inode, int *p_num, int *f_num);
-extern int ceph_encode_locks(struct inode *i, struct ceph_pagelist *p,
- int p_locks, int f_locks);
+extern int ceph_encode_locks_to_buffer(struct inode *inode,
+ struct ceph_filelock *flocks,
+ int num_fcntl_locks,
+ int num_flock_locks);
+extern int ceph_locks_to_pagelist(struct ceph_filelock *flocks,
+ struct ceph_pagelist *pagelist,
+ int num_fcntl_locks, int num_flock_locks);
extern int lock_to_ceph_filelock(struct file_lock *fl, struct ceph_filelock *c);
-static inline struct inode *get_dentry_parent_inode(struct dentry *dentry)
-{
- if (dentry && dentry->d_parent)
- return dentry->d_parent->d_inode;
-
- return NULL;
-}
-
/* debugfs.c */
extern int ceph_fs_debugfs_init(struct ceph_fs_client *client);
extern void ceph_fs_debugfs_cleanup(struct ceph_fs_client *client);
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-05 08:51:15 +0000