X-Git-Url: https://git.whamcloud.com/?p=fs%2Flustre-release.git;a=blobdiff_plain;f=lustre%2Fllite%2Fllite_internal.h;h=d066f98ff25b0a1484a575acd51cdcc55f479ca1;hp=2cb186fc43023327f7acab0ed5150fa4f8643657;hb=38c4c538f53fb5f0c7f6db6d4970c491184e81a0;hpb=4b47ec5a8e68950ced4895e1ccfdf2254c016194 diff --git a/lustre/llite/llite_internal.h b/lustre/llite/llite_internal.h index 2cb186f..d066f98 100644 --- a/lustre/llite/llite_internal.h +++ b/lustre/llite/llite_internal.h @@ -27,14 +27,12 @@ */ /* * This file is part of Lustre, http://www.lustre.org/ - * Lustre is a trademark of Sun Microsystems, Inc. */ #ifndef LLITE_INTERNAL_H #define LLITE_INTERNAL_H -#include +#include #include /* for s2sbi */ -#include #include /* for struct cl_lock_descr and struct cl_io */ @@ -44,12 +42,14 @@ #include #include #include +#include #include #include +#include #include "vvp_internal.h" -#include "range_lock.h" #include "pcc.h" +#include "foreign_symlink.h" #ifndef FMODE_EXEC #define FMODE_EXEC 0 @@ -116,7 +116,7 @@ struct ll_trunc_sem { struct ll_inode_info { __u32 lli_inode_magic; - spinlock_t lli_lock; + rwlock_t lli_lock; volatile unsigned long lli_flags; struct posix_acl *lli_posix_acl; @@ -134,6 +134,12 @@ struct ll_inode_info { __u64 lli_open_fd_read_count; __u64 lli_open_fd_write_count; __u64 lli_open_fd_exec_count; + + /* Number of times this inode was opened */ + u64 lli_open_fd_count; + /* When last close was performed on this inode */ + ktime_t lli_close_fd_time; + /* Protects access to och pointers and their usage counters */ struct mutex lli_och_mutex; @@ -163,12 +169,14 @@ struct ll_inode_info { /* "opendir_pid" is the token when lookup/revalid * -- I am the owner of dir statahead. */ pid_t lli_opendir_pid; + /* directory depth to ROOT */ + unsigned short lli_dir_depth; /* stat will try to access statahead entries or start * statahead if this flag is set, and this flag will be * set upon dir open, and cleared when dir is closed, * statahead hit ratio is too low, or start statahead * thread failed. */ - unsigned int lli_sa_enabled:1; + unsigned short lli_sa_enabled:1; /* generation for statahead */ unsigned int lli_sa_generation; /* rw lock protects lli_lsm_md */ @@ -262,6 +270,7 @@ struct ll_inode_info { struct rw_semaphore lli_xattrs_list_rwsem; struct mutex lli_xattrs_enq_lock; struct list_head lli_xattrs; /* ll_xattr_entry->xe_list */ + struct list_head lli_lccs; /* list of ll_cl_context */ }; static inline void ll_trunc_sem_init(struct ll_trunc_sem *sem) @@ -278,11 +287,11 @@ static inline void ll_trunc_sem_init(struct ll_trunc_sem *sem) * * We must take lli_trunc_sem in read mode on entry in to various i/o paths * in Lustre, in order to exclude truncates. Some of these paths then need to - * take the mmap_sem, while still holding the trunc_sem. The problem is that - * page faults hold the mmap_sem when calling in to Lustre, and then must also + * take the mmap_lock, while still holding the trunc_sem. The problem is that + * page faults hold the mmap_lock when calling in to Lustre, and then must also * take the trunc_sem to exclude truncate. * - * This means the locking order for trunc_sem and mmap_sem is sometimes AB, + * This means the locking order for trunc_sem and mmap_lock is sometimes AB, * sometimes BA. This is almost OK because in both cases, we take the trunc * sem for read, so it doesn't block. * @@ -292,9 +301,9 @@ static inline void ll_trunc_sem_init(struct ll_trunc_sem *sem) * * So we have, on our truncate sem, in order (where 'reader' and 'writer' refer * to the mode in which they take the semaphore): - * reader (holding mmap_sem, needs truncate_sem) + * reader (holding mmap_lock, needs truncate_sem) * writer - * reader (holding truncate sem, waiting for mmap_sem) + * reader (holding truncate sem, waiting for mmap_lock) * * And so the readers deadlock. * @@ -304,7 +313,7 @@ static inline void ll_trunc_sem_init(struct ll_trunc_sem *sem) * of the order they arrived in. * * down_read_nowait is only used in the page fault case, where we already hold - * the mmap_sem. This is because otherwise repeated read and write operations + * the mmap_lock. This is because otherwise repeated read and write operations * (which take the truncate sem) could prevent a truncate from ever starting. * This could still happen with page faults, but without an even more complex * mechanism, this is unavoidable. @@ -342,6 +351,8 @@ static inline void trunc_sem_down_write(struct ll_trunc_sem *sem) static inline void trunc_sem_up_write(struct ll_trunc_sem *sem) { atomic_set(&sem->ll_trunc_readers, 0); + /* match the smp_mb() in wait_var_event()->prepare_to_wait() */ + smp_mb(); wake_up_var(&sem->ll_trunc_readers); } @@ -357,11 +368,11 @@ static inline void lli_clear_acl(struct ll_inode_info *lli) static inline void lli_replace_acl(struct ll_inode_info *lli, struct lustre_md *md) { - spin_lock(&lli->lli_lock); + write_lock(&lli->lli_lock); if (lli->lli_posix_acl) posix_acl_release(lli->lli_posix_acl); lli->lli_posix_acl = md->posix_acl; - spin_unlock(&lli->lli_lock); + write_unlock(&lli->lli_lock); } #else static inline void lli_clear_acl(struct ll_inode_info *lli) @@ -403,34 +414,17 @@ enum ll_file_flags { LLIF_PROJECT_INHERIT = 3, /* update atime from MDS even if it's older than local inode atime. */ LLIF_UPDATE_ATIME = 4, + /* foreign file/dir can be unlinked unconditionnaly */ + LLIF_FOREIGN_REMOVABLE = 5, + /* setting encryption context in progress */ + LLIF_SET_ENC_CTX = 6, + /* Xattr cache is filled */ + LLIF_XATTR_CACHE_FILLED = 7, }; -static inline void ll_file_set_flag(struct ll_inode_info *lli, - enum ll_file_flags flag) -{ - set_bit(flag, &lli->lli_flags); -} - -static inline void ll_file_clear_flag(struct ll_inode_info *lli, - enum ll_file_flags flag) -{ - clear_bit(flag, &lli->lli_flags); -} - -static inline bool ll_file_test_flag(struct ll_inode_info *lli, - enum ll_file_flags flag) -{ - return test_bit(flag, &lli->lli_flags); -} - -static inline bool ll_file_test_and_clear_flag(struct ll_inode_info *lli, - enum ll_file_flags flag) -{ - return test_and_clear_bit(flag, &lli->lli_flags); -} - int ll_xattr_cache_destroy(struct inode *inode); +int ll_xattr_cache_empty(struct inode *inode); int ll_xattr_cache_get(struct inode *inode, const char *name, @@ -518,6 +512,12 @@ static inline struct pcc_inode *ll_i2pcci(struct inode *inode) /* default read-ahead full files smaller than limit on the second read */ #define SBI_DEFAULT_READ_AHEAD_WHOLE_MAX MiB_TO_PAGES(2UL) +/* default range pages */ +#define SBI_DEFAULT_RA_RANGE_PAGES MiB_TO_PAGES(1ULL) + +/* Min range pages */ +#define RA_MIN_MMAP_RANGE_PAGES 16UL + enum ra_stat { RA_STAT_HIT = 0, RA_STAT_MISS, @@ -534,6 +534,7 @@ enum ra_stat { RA_STAT_FAILED_REACH_END, RA_STAT_ASYNC, RA_STAT_FAILED_FAST_READ, + RA_STAT_MMAP_RANGE_READ, _NR_RA_STAT, }; @@ -541,6 +542,7 @@ struct ll_ra_info { atomic_t ra_cur_pages; unsigned long ra_max_pages; unsigned long ra_max_pages_per_file; + unsigned long ra_range_pages; unsigned long ra_max_read_ahead_whole_pages; struct workqueue_struct *ll_readahead_wq; /* @@ -581,14 +583,15 @@ struct ra_io_arg { #define LL_HIST_START 12 /* buckets start at 2^12 = 4k */ #define LL_PROCESS_HIST_MAX 10 struct per_process_info { - pid_t pid; - struct obd_histogram pp_r_hist; - struct obd_histogram pp_w_hist; + pid_t pid; + struct obd_histogram pp_r_hist; + struct obd_histogram pp_w_hist; }; /* pp_extents[LL_PROCESS_HIST_MAX] will hold the combined process info */ struct ll_rw_extents_info { - struct per_process_info pp_extents[LL_PROCESS_HIST_MAX + 1]; + ktime_t pp_init; + struct per_process_info pp_extents[LL_PROCESS_HIST_MAX + 1]; }; #define LL_OFFSET_HIST_MAX 100 @@ -613,67 +616,39 @@ enum stats_track_type { }; /* flags for sbi->ll_flags */ -#define LL_SBI_NOLCK 0x01 /* DLM locking disabled (directio-only) */ -#define LL_SBI_CHECKSUM 0x02 /* checksum each page as it's written */ -#define LL_SBI_FLOCK 0x04 -#define LL_SBI_USER_XATTR 0x08 /* support user xattr */ -#define LL_SBI_ACL 0x10 /* support ACL */ -/* LL_SBI_RMT_CLIENT 0x40 remote client */ -#define LL_SBI_MDS_CAPA 0x80 /* support mds capa, obsolete */ -#define LL_SBI_OSS_CAPA 0x100 /* support oss capa, obsolete */ -#define LL_SBI_LOCALFLOCK 0x200 /* Local flocks support by kernel */ -#define LL_SBI_LRU_RESIZE 0x400 /* lru resize support */ -#define LL_SBI_LAZYSTATFS 0x800 /* lazystatfs mount option */ -/* LL_SBI_SOM_PREVIEW 0x1000 SOM preview mount option, obsolete */ -#define LL_SBI_32BIT_API 0x2000 /* generate 32 bit inodes. */ -#define LL_SBI_64BIT_HASH 0x4000 /* support 64-bits dir hash/offset */ -#define LL_SBI_AGL_ENABLED 0x8000 /* enable agl */ -#define LL_SBI_VERBOSE 0x10000 /* verbose mount/umount */ -#define LL_SBI_LAYOUT_LOCK 0x20000 /* layout lock support */ -#define LL_SBI_USER_FID2PATH 0x40000 /* allow fid2path by unprivileged users */ -#define LL_SBI_XATTR_CACHE 0x80000 /* support for xattr cache */ -#define LL_SBI_NOROOTSQUASH 0x100000 /* do not apply root squash */ -#define LL_SBI_ALWAYS_PING 0x200000 /* always ping even if server - * suppress_pings */ -#define LL_SBI_FAST_READ 0x400000 /* fast read support */ -#define LL_SBI_FILE_SECCTX 0x800000 /* set file security context at create */ -/* LL_SBI_PIO 0x1000000 parallel IO support, introduced in - 2.10, abandoned */ -#define LL_SBI_TINY_WRITE 0x2000000 /* tiny write support */ -#define LL_SBI_FILE_HEAT 0x4000000 /* file heat support */ -#define LL_SBI_TEST_DUMMY_ENCRYPTION 0x8000000 /* test dummy encryption */ -#define LL_SBI_ENCRYPT 0x10000000 /* client side encryption */ -#define LL_SBI_FLAGS { \ - "nolck", \ - "checksum", \ - "flock", \ - "user_xattr", \ - "acl", \ - "???", \ - "???", \ - "mds_capa", \ - "oss_capa", \ - "flock", \ - "lru_resize", \ - "lazy_statfs", \ - "som", \ - "32bit_api", \ - "64bit_hash", \ - "agl", \ - "verbose", \ - "layout", \ - "user_fid2path",\ - "xattr_cache", \ - "norootsquash", \ - "always_ping", \ - "fast_read", \ - "file_secctx", \ - "pio", \ - "tiny_write", \ - "file_heat", \ - "test_dummy_encryption", \ - "noencrypt", \ -} +enum ll_sbi_flags { + LL_SBI_NOLCK, /* DLM locking disabled directio-only */ + LL_SBI_CHECKSUM, /* checksum each page as it's written */ + LL_SBI_LOCALFLOCK, /* local flocks instead of fs-wide */ + LL_SBI_FLOCK, /* flock enabled */ + LL_SBI_USER_XATTR, /* support user xattr */ + LL_SBI_LRU_RESIZE, /* lru resize support */ + LL_SBI_LAZYSTATFS, /* lazystatfs mount option */ + LL_SBI_32BIT_API, /* generate 32 bit inodes. */ + LL_SBI_USER_FID2PATH, /* fid2path by unprivileged users */ + LL_SBI_VERBOSE, /* verbose mount/umount */ + LL_SBI_ALWAYS_PING, /* ping even if server suppress_pings */ + LL_SBI_TEST_DUMMY_ENCRYPTION, /* test dummy encryption */ + LL_SBI_ENCRYPT, /* client side encryption */ + LL_SBI_FOREIGN_SYMLINK, /* foreign fake-symlink support */ + LL_SBI_FOREIGN_SYMLINK_UPCALL, /* foreign fake-symlink upcall set */ + LL_SBI_NUM_MOUNT_OPT, + + LL_SBI_ACL, /* support ACL */ + LL_SBI_AGL_ENABLED, /* enable agl */ + LL_SBI_64BIT_HASH, /* support 64-bits dir hash/offset */ + LL_SBI_LAYOUT_LOCK, /* layout lock support */ + LL_SBI_XATTR_CACHE, /* support for xattr cache */ + LL_SBI_NOROOTSQUASH, /* do not apply root squash */ + LL_SBI_FAST_READ, /* fast read support */ + LL_SBI_FILE_SECCTX, /* file security context at create */ + LL_SBI_TINY_WRITE, /* tiny write support */ + LL_SBI_FILE_HEAT, /* file heat support */ + LL_SBI_PARALLEL_DIO, /* parallel (async) O_DIRECT RPCs */ + LL_SBI_NUM_FLAGS +}; + +int ll_sbi_flags_seq_show(struct seq_file *m, void *v); /* This is embedded into llite super-blocks to keep track of connect * flags (capabilities) supported by all imports given mount is @@ -701,16 +676,17 @@ struct ll_sb_info { struct obd_device *ll_dt_obd; struct dentry *ll_debugfs_entry; struct lu_fid ll_root_fid; /* root object fid */ + struct mnt_namespace *ll_mnt_ns; - int ll_flags; - unsigned int ll_xattr_cache_enabled:1, - ll_xattr_cache_set:1, /* already set to 0/1 */ - ll_client_common_fill_super_succeeded:1, - ll_checksum_set:1; + DECLARE_BITMAP(ll_flags, LL_SBI_NUM_FLAGS); /* enum ll_sbi_flags */ + unsigned int ll_xattr_cache_enabled:1, + ll_xattr_cache_set:1, /* already set to 0/1 */ + ll_client_common_fill_super_succeeded:1, + ll_checksum_set:1; - struct lustre_client_ocd ll_lco; + struct lustre_client_ocd ll_lco; - struct lprocfs_stats *ll_stats; /* lprocfs stats counter */ + struct lprocfs_stats *ll_stats; /* lprocfs stats counter */ /* Used to track "unstable" pages on a client, and maintain a * LRU list of clean pages. An "unstable" page is defined as @@ -718,24 +694,26 @@ struct ll_sb_info { * but is uncommitted to stable storage. */ struct cl_client_cache *ll_cache; - struct lprocfs_stats *ll_ra_stats; - - struct ll_ra_info ll_ra_info; - unsigned int ll_namelen; - struct file_operations *ll_fop; - - struct lu_site *ll_site; - struct cl_device *ll_cl; - /* Statistics */ - struct ll_rw_extents_info ll_rw_extents_info; - int ll_extent_process_count; - struct ll_rw_process_info ll_rw_process_info[LL_PROCESS_HIST_MAX]; - unsigned int ll_offset_process_count; - struct ll_rw_process_info ll_rw_offset_info[LL_OFFSET_HIST_MAX]; - unsigned int ll_rw_offset_entry_count; - int ll_stats_track_id; - enum stats_track_type ll_stats_track_type; - int ll_rw_stats_on; + struct lprocfs_stats *ll_ra_stats; + + struct ll_ra_info ll_ra_info; + unsigned int ll_namelen; + const struct file_operations *ll_fop; + + struct lu_site *ll_site; + struct cl_device *ll_cl; + + /* Statistics */ + struct ll_rw_extents_info *ll_rw_extents_info; + int ll_extent_process_count; + unsigned int ll_offset_process_count; + struct ll_rw_process_info *ll_rw_process_info; + struct ll_rw_process_info *ll_rw_offset_info; + ktime_t ll_process_stats_init; + unsigned int ll_rw_offset_entry_count; + int ll_stats_track_id; + enum stats_track_type ll_stats_track_type; + int ll_rw_stats_on; /* metadata stat-ahead */ unsigned int ll_sa_running_max;/* max concurrent @@ -768,15 +746,44 @@ struct ll_sb_info { unsigned int ll_heat_decay_weight; unsigned int ll_heat_period_second; + /* Opens of the same inode before we start requesting open lock */ + u32 ll_oc_thrsh_count; + + /* Time in ms between last inode close and next open to be considered + * instant back to back and would trigger an open lock request + */ + u32 ll_oc_thrsh_ms; + + /* Time in ms after last file close that we no longer count prior opens*/ + u32 ll_oc_max_ms; + /* filesystem fsname */ char ll_fsname[LUSTRE_MAXFSNAME + 1]; /* Persistent Client Cache */ struct pcc_super ll_pcc_super; + + /* to protect vs updates in all following foreign symlink fields */ + struct rw_semaphore ll_foreign_symlink_sem; + /* foreign symlink path prefix */ + char *ll_foreign_symlink_prefix; + /* full prefix size including leading '\0' */ + size_t ll_foreign_symlink_prefix_size; + /* foreign symlink path upcall */ + char *ll_foreign_symlink_upcall; + /* foreign symlink path upcall infos */ + struct ll_foreign_symlink_upcall_item *ll_foreign_symlink_upcall_items; + /* foreign symlink path upcall nb infos */ + unsigned int ll_foreign_symlink_upcall_nb_items; }; #define SBI_DEFAULT_HEAT_DECAY_WEIGHT ((80 * 256 + 50) / 100) #define SBI_DEFAULT_HEAT_PERIOD_SECOND (60) + +#define SBI_DEFAULT_OPENCACHE_THRESHOLD_COUNT (5) +#define SBI_DEFAULT_OPENCACHE_THRESHOLD_MS (100) /* 0.1 second */ +#define SBI_DEFAULT_OPENCACHE_THRESHOLD_MAX_MS (60000) /* 1 minute */ + /* * per file-descriptor read-ahead data. */ @@ -810,6 +817,16 @@ struct ll_readahead_state { */ pgoff_t ras_window_start_idx; pgoff_t ras_window_pages; + + /* Page index where min range read starts */ + pgoff_t ras_range_min_start_idx; + /* Page index where mmap range read ends */ + pgoff_t ras_range_max_end_idx; + /* number of mmap pages where last time detected */ + pgoff_t ras_last_range_pages; + /* number of mmap range requests */ + pgoff_t ras_range_requests; + /* * Optimal RPC size in pages. * It decides how many pages will be sent for each read-ahead. @@ -887,8 +904,6 @@ struct ll_file_data { * false: unknown failure, should report. */ bool fd_write_failed; bool ll_lock_no_expand; - rwlock_t fd_lock; /* protect lcc list */ - struct list_head fd_lccs; /* list of ll_cl_context */ /* Used by mirrored file to lead IOs to a specific mirror, usually * for mirror resync. 0 means default. */ __u32 fd_designated_mirror; @@ -914,7 +929,7 @@ static inline int ll_need_32bit_api(struct ll_sb_info *sbi) #if BITS_PER_LONG == 32 return 1; #elif defined(CONFIG_COMPAT) - if (unlikely(sbi->ll_flags & LL_SBI_32BIT_API)) + if (unlikely(test_bit(LL_SBI_32BIT_API, sbi->ll_flags))) return true; # ifdef CONFIG_X86_X32 @@ -928,23 +943,33 @@ static inline int ll_need_32bit_api(struct ll_sb_info *sbi) return unlikely(in_compat_syscall()); #else - return unlikely(sbi->ll_flags & LL_SBI_32BIT_API); + return unlikely(test_bit(LL_SBI_32BIT_API, sbi->ll_flags)); #endif } static inline bool ll_sbi_has_fast_read(struct ll_sb_info *sbi) { - return !!(sbi->ll_flags & LL_SBI_FAST_READ); + return test_bit(LL_SBI_FAST_READ, sbi->ll_flags); } static inline bool ll_sbi_has_tiny_write(struct ll_sb_info *sbi) { - return !!(sbi->ll_flags & LL_SBI_TINY_WRITE); + return test_bit(LL_SBI_TINY_WRITE, sbi->ll_flags); } static inline bool ll_sbi_has_file_heat(struct ll_sb_info *sbi) { - return !!(sbi->ll_flags & LL_SBI_FILE_HEAT); + return test_bit(LL_SBI_FILE_HEAT, sbi->ll_flags); +} + +static inline bool ll_sbi_has_foreign_symlink(struct ll_sb_info *sbi) +{ + return test_bit(LL_SBI_FOREIGN_SYMLINK, sbi->ll_flags); +} + +static inline bool ll_sbi_has_parallel_dio(struct ll_sb_info *sbi) +{ + return test_bit(LL_SBI_PARALLEL_DIO, sbi->ll_flags); } void ll_ras_enter(struct file *f, loff_t pos, size_t count); @@ -960,6 +985,7 @@ void cl_put_grouplock(struct ll_grouplock *lg); int ll_debugfs_register_super(struct super_block *sb, const char *name); void ll_debugfs_unregister_super(struct super_block *sb); void ll_stats_ops_tally(struct ll_sb_info *sbi, int op, long count); +void ll_free_rw_stats_info(struct ll_sb_info *sbi); enum { LPROC_LL_READ_BYTES, @@ -995,6 +1021,8 @@ enum { LPROC_LL_REMOVEXATTR, LPROC_LL_INODE_PERM, LPROC_LL_FALLOCATE, + LPROC_LL_INODE_OCOUNT, + LPROC_LL_INODE_OPCLTM, LPROC_LL_FILE_OPCODES }; @@ -1003,17 +1031,6 @@ enum get_default_layout_type { GET_DEFAULT_LAYOUT_ROOT = 1, }; -struct ll_dir_chain { -}; - -static inline void ll_dir_chain_init(struct ll_dir_chain *chain) -{ -} - -static inline void ll_dir_chain_fini(struct ll_dir_chain *chain) -{ -} - extern const struct file_operations ll_dir_operations; extern const struct inode_operations ll_dir_inode_operations; #ifdef HAVE_DIR_CONTEXT @@ -1026,8 +1043,9 @@ int ll_dir_read(struct inode *inode, __u64 *pos, struct md_op_data *op_data, int ll_get_mdt_idx(struct inode *inode); int ll_get_mdt_idx_by_fid(struct ll_sb_info *sbi, const struct lu_fid *fid); struct page *ll_get_dir_page(struct inode *dir, struct md_op_data *op_data, - __u64 offset, struct ll_dir_chain *chain); + __u64 offset); void ll_release_page(struct inode *inode, struct page *page, bool remove); +int quotactl_ioctl(struct super_block *sb, struct if_quotactl *qctl); /* llite/namei.c */ extern const struct inode_operations ll_special_inode_operations; @@ -1051,18 +1069,16 @@ void ll_readahead_init(struct inode *inode, struct ll_readahead_state *ras); int vvp_io_write_commit(const struct lu_env *env, struct cl_io *io); enum lcc_type; -void ll_cl_add(struct file *file, const struct lu_env *env, struct cl_io *io, +void ll_cl_add(struct inode *inode, const struct lu_env *env, struct cl_io *io, enum lcc_type type); -void ll_cl_remove(struct file *file, const struct lu_env *env); -struct ll_cl_context *ll_cl_find(struct file *file); +void ll_cl_remove(struct inode *inode, const struct lu_env *env); +struct ll_cl_context *ll_cl_find(struct inode *inode); extern const struct address_space_operations ll_aops; /* llite/file.c */ -extern struct file_operations ll_file_operations; -extern struct file_operations ll_file_operations_flock; -extern struct file_operations ll_file_operations_noflock; -extern struct inode_operations ll_file_inode_operations; +extern const struct inode_operations ll_file_inode_operations; +const struct file_operations *ll_select_file_operations(struct ll_sb_info *sbi); extern int ll_have_md_lock(struct inode *inode, __u64 *bits, enum ldlm_mode l_req_mode); extern enum ldlm_mode ll_take_md_lock(struct inode *inode, __u64 bits, @@ -1073,6 +1089,7 @@ int ll_file_open(struct inode *inode, struct file *file); int ll_file_release(struct inode *inode, struct file *file); int ll_release_openhandle(struct dentry *, struct lookup_intent *); int ll_md_real_close(struct inode *inode, fmode_t fmode); +void ll_track_file_opens(struct inode *inode); extern void ll_rw_stats_tally(struct ll_sb_info *sbi, pid_t pid, struct ll_file_data *file, loff_t pos, size_t count, int rw); @@ -1083,17 +1100,15 @@ int ll_getattr(const struct path *path, struct kstat *stat, int ll_getattr(struct vfsmount *mnt, struct dentry *de, struct kstat *stat); #endif int ll_getattr_dentry(struct dentry *de, struct kstat *stat, u32 request_mask, - unsigned int flags); -struct posix_acl *ll_get_acl(struct inode *inode, int type); -#ifdef HAVE_IOP_SET_ACL + unsigned int flags, bool foreign); #ifdef CONFIG_LUSTRE_FS_POSIX_ACL +struct posix_acl *ll_get_acl(struct inode *inode, int type); int ll_set_acl(struct inode *inode, struct posix_acl *acl, int type); #else /* !CONFIG_LUSTRE_FS_POSIX_ACL */ +#define ll_get_acl NULL #define ll_set_acl NULL #endif /* CONFIG_LUSTRE_FS_POSIX_ACL */ -#endif - static inline int ll_xflags_to_inode_flags(int xflags) { return ((xflags & FS_XFLAG_SYNC) ? S_SYNC : 0) | @@ -1102,24 +1117,26 @@ static inline int ll_xflags_to_inode_flags(int xflags) ((xflags & FS_XFLAG_IMMUTABLE) ? S_IMMUTABLE : 0); } -static inline int ll_inode_flags_to_xflags(int flags) +static inline int ll_inode_flags_to_xflags(int inode_flags) { - return ((flags & S_SYNC) ? FS_XFLAG_SYNC : 0) | - ((flags & S_NOATIME) ? FS_XFLAG_NOATIME : 0) | - ((flags & S_APPEND) ? FS_XFLAG_APPEND : 0) | - ((flags & S_IMMUTABLE) ? FS_XFLAG_IMMUTABLE : 0); + return ((inode_flags & S_SYNC) ? FS_XFLAG_SYNC : 0) | + ((inode_flags & S_NOATIME) ? FS_XFLAG_NOATIME : 0) | + ((inode_flags & S_APPEND) ? FS_XFLAG_APPEND : 0) | + ((inode_flags & S_IMMUTABLE) ? FS_XFLAG_IMMUTABLE : 0); } int ll_migrate(struct inode *parent, struct file *file, - struct lmv_user_md *lum, const char *name); + struct lmv_user_md *lum, const char *name, __u32 flags); int ll_get_fid_by_name(struct inode *parent, const char *name, int namelen, struct lu_fid *fid, struct inode **inode); int ll_inode_permission(struct inode *inode, int mask); -int ll_ioctl_check_project(struct inode *inode, struct fsxattr *fa); +int ll_ioctl_check_project(struct inode *inode, __u32 xflags, __u32 projid); int ll_ioctl_fsgetxattr(struct inode *inode, unsigned int cmd, unsigned long arg); int ll_ioctl_fssetxattr(struct inode *inode, unsigned int cmd, unsigned long arg); +int ll_ioctl_project(struct file *file, unsigned int cmd, + unsigned long arg); int ll_lov_setstripe_ea_info(struct inode *inode, struct dentry *dentry, __u64 flags, struct lov_user_md *lum, @@ -1144,8 +1161,19 @@ void ll_io_set_mirror(struct cl_io *io, const struct file *file); /* llite/dcache.c */ -int ll_d_init(struct dentry *de); extern const struct dentry_operations ll_d_ops; +#ifndef HAVE_D_INIT +bool ll_d_setup(struct dentry *de, bool do_put); + +static inline bool lld_is_init(struct dentry *dentry) +{ + return ll_d2d(dentry); +} +#else +#define ll_d_setup(de, do_put) (true) +#define lld_is_init(dentry) (true) +#endif + void ll_intent_drop_lock(struct lookup_intent *); void ll_intent_release(struct lookup_intent *); void ll_prune_aliases(struct inode *inode); @@ -1154,7 +1182,7 @@ int ll_revalidate_it_finish(struct ptlrpc_request *request, struct lookup_intent *it, struct dentry *de); /* llite/llite_lib.c */ -extern struct super_operations lustre_super_operations; +extern const struct super_operations lustre_super_operations; void ll_lli_init(struct ll_inode_info *lli); int ll_fill_super(struct super_block *sb); @@ -1163,6 +1191,8 @@ void ll_kill_super(struct super_block *sb); struct inode *ll_inode_from_resource_lock(struct ldlm_lock *lock); void ll_dir_clear_lsm_md(struct inode *inode); void ll_clear_inode(struct inode *inode); +int volatile_ref_file(const char *volatile_name, int volatile_len, + struct file **ref_file); int ll_setattr_raw(struct dentry *dentry, struct iattr *attr, enum op_xvalid xvalid, bool hsm_import); int ll_setattr(struct dentry *de, struct iattr *attr); @@ -1170,8 +1200,10 @@ int ll_statfs(struct dentry *de, struct kstatfs *sfs); int ll_statfs_internal(struct ll_sb_info *sbi, struct obd_statfs *osfs, u32 flags); int ll_update_inode(struct inode *inode, struct lustre_md *md); -void ll_update_inode_flags(struct inode *inode, int ext_flags); +void ll_update_inode_flags(struct inode *inode, unsigned int ext_flags); +void ll_update_dir_depth(struct inode *dir, struct inode *inode); int ll_read_inode2(struct inode *inode, void *opaque); +void ll_truncate_inode_pages_final(struct inode *inode); void ll_delete_inode(struct inode *inode); int ll_iocontrol(struct inode *inode, struct file *file, unsigned int cmd, unsigned long arg); @@ -1180,8 +1212,8 @@ void ll_umount_begin(struct super_block *sb); int ll_remount_fs(struct super_block *sb, int *flags, char *data); int ll_show_options(struct seq_file *seq, struct dentry *dentry); void ll_dirty_page_discard_warn(struct page *page, int ioret); -int ll_prep_inode(struct inode **inode, struct ptlrpc_request *req, - struct super_block *, struct lookup_intent *); +int ll_prep_inode(struct inode **inode, struct req_capsule *pill, + struct super_block *sb, struct lookup_intent *it); int ll_obd_statfs(struct inode *inode, void __user *arg); int ll_get_max_mdsize(struct ll_sb_info *sbi, int *max_mdsize); int ll_get_default_mdsize(struct ll_sb_info *sbi, int *default_mdsize); @@ -1198,7 +1230,7 @@ int ll_get_obd_name(struct inode *inode, unsigned int cmd, unsigned long arg); void ll_compute_rootsquash_state(struct ll_sb_info *sbi); ssize_t ll_copy_user_md(const struct lov_user_md __user *md, struct lov_user_md **kbuf); -void ll_open_cleanup(struct super_block *sb, struct ptlrpc_request *open_req); +void ll_open_cleanup(struct super_block *sb, struct req_capsule *pill); void ll_dom_finish_open(struct inode *inode, struct ptlrpc_request *req); @@ -1226,14 +1258,14 @@ static inline ssize_t ll_lov_user_md_size(const struct lov_user_md *lum) } /* llite/llite_nfs.c */ -extern struct export_operations lustre_export_operations; +extern const struct export_operations lustre_export_operations; __u32 get_uuid2int(const char *name, int len); struct inode *search_inode_for_lustre(struct super_block *sb, const struct lu_fid *fid); int ll_dir_get_parent_fid(struct inode *dir, struct lu_fid *parent_fid); /* llite/symlink.c */ -extern struct inode_operations ll_fast_symlink_inode_operations; +extern const struct inode_operations ll_fast_symlink_inode_operations; /** * IO arguments for various VFS I/O interfaces. @@ -1260,6 +1292,11 @@ struct ll_cl_context { struct cl_io *lcc_io; struct cl_page *lcc_page; enum lcc_type lcc_type; + /** + * Get encryption context operation in progress, + * allow getxattr of LL_XATTR_NAME_ENCRYPTION_CONTEXT xattr + */ + unsigned lcc_getencctx:1; }; struct ll_thread_info { @@ -1290,7 +1327,6 @@ void ll_io_init(struct cl_io *io, struct file *file, enum cl_io_type iot, /* llite/llite_mmap.c */ -int ll_teardown_mmaps(struct address_space *mapping, __u64 first, __u64 last); int ll_file_mmap(struct file * file, struct vm_area_struct * vma); void policy_from_vma(union ldlm_policy_data *policy, struct vm_area_struct *vma, unsigned long addr, size_t count); @@ -1436,7 +1472,6 @@ struct ll_statahead_info { */ unsigned int sai_ls_all:1, /* "ls -al", do stat-ahead for * hidden entries */ - sai_agl_valid:1,/* AGL is valid for the dir */ sai_in_readpage:1;/* statahead is in readdir()*/ wait_queue_head_t sai_waitq; /* stat-ahead wait queue */ struct task_struct *sai_task; /* stat-ahead thread */ @@ -1549,7 +1584,7 @@ static inline int ll_file_nolock(const struct file *file) LASSERT(fd != NULL); return ((fd->fd_flags & LL_FILE_IGNORE_LOCK) || - (ll_i2sbi(inode)->ll_flags & LL_SBI_NOLCK)); + test_bit(LL_SBI_NOLCK, ll_i2sbi(inode)->ll_flags)); } static inline void ll_set_lock_data(struct obd_export *exp, struct inode *inode, @@ -1590,17 +1625,7 @@ static inline void ll_set_lock_data(struct obd_export *exp, struct inode *inode, static inline int d_lustre_invalid(const struct dentry *dentry) { - struct ll_dentry_data *lld = ll_d2d(dentry); - - return (lld == NULL) || lld->lld_invalid; -} - -static inline void __d_lustre_invalidate(struct dentry *dentry) -{ - struct ll_dentry_data *lld = ll_d2d(dentry); - - if (lld != NULL) - lld->lld_invalid = 1; + return !ll_d2d(dentry) || ll_d2d(dentry)->lld_invalid; } /* @@ -1616,14 +1641,15 @@ static inline void d_lustre_invalidate(struct dentry *dentry) dentry->d_parent, dentry->d_inode, ll_d_count(dentry)); spin_lock(&dentry->d_lock); - __d_lustre_invalidate(dentry); + if (lld_is_init(dentry)) + ll_d2d(dentry)->lld_invalid = 1; spin_unlock(&dentry->d_lock); } static inline void d_lustre_revalidate(struct dentry *dentry) { spin_lock(&dentry->d_lock); - LASSERT(ll_d2d(dentry) != NULL); + LASSERT(ll_d2d(dentry)); ll_d2d(dentry)->lld_invalid = 0; spin_unlock(&dentry->d_lock); } @@ -1677,9 +1703,32 @@ static inline struct pcc_super *ll_info2pccs(struct ll_inode_info *lli) return ll_i2pccs(ll_info2i(lli)); } -#ifdef HAVE_LUSTRE_CRYPTO /* crypto.c */ +/* The digested form is made of a FID (16 bytes) followed by the second-to-last + * ciphertext block (16 bytes), so a total length of 32 bytes. + * That way, llcrypt does not compute a digested form of this digest. + */ +struct ll_digest_filename { + struct lu_fid ldf_fid; + char ldf_excerpt[LLCRYPT_FNAME_DIGEST_SIZE]; +}; + +int ll_setup_filename(struct inode *dir, const struct qstr *iname, + int lookup, struct llcrypt_name *fname, + struct lu_fid *fid); +int ll_fname_disk_to_usr(struct inode *inode, + u32 hash, u32 minor_hash, + struct llcrypt_str *iname, struct llcrypt_str *oname, + struct lu_fid *fid); +int ll_revalidate_d_crypto(struct dentry *dentry, unsigned int flags); +int ll_file_open_encrypt(struct inode *inode, struct file *filp); +#ifdef HAVE_LUSTRE_CRYPTO extern const struct llcrypt_operations lustre_cryptops; #endif +/* llite/llite_foreign.c */ +int ll_manage_foreign(struct inode *inode, struct lustre_md *lmd); +bool ll_foreign_is_openable(struct dentry *dentry, unsigned int flags); +bool ll_foreign_is_removable(struct dentry *dentry, bool unset); + #endif /* LLITE_INTERNAL_H */