X-Git-Url: https://git.whamcloud.com/?p=fs%2Flustre-release.git;a=blobdiff_plain;f=lustre%2Fllite%2Fllite_internal.h;h=a0e3036cf00867688f16551cf3b0924175cae574;hp=f0b839fd97263325ea81f42a047274da80286064;hb=e5c8f6670fbeea9ec8c6092dfa4369508da54485;hpb=164231a7a29b7203cd27ab624eddd5fb7c557b90 diff --git a/lustre/llite/llite_internal.h b/lustre/llite/llite_internal.h index f0b839f..a0e3036 100644 --- a/lustre/llite/llite_internal.h +++ b/lustre/llite/llite_internal.h @@ -44,16 +44,18 @@ #include #include #include - #include +#include + #include "vvp_internal.h" #include "range_lock.h" +#include "pcc.h" #ifndef FMODE_EXEC #define FMODE_EXEC 0 #endif -#ifndef VM_FAULT_RETRY +#ifndef HAVE_VM_FAULT_RETRY #define VM_FAULT_RETRY 0 #endif @@ -71,10 +73,10 @@ #define LL_MAX_BLKSIZE_BITS 22 #define LL_IT2STR(it) ((it) ? ldlm_it2str((it)->it_op) : "0") -#define LUSTRE_FPRIVATE(file) ((file)->private_data) + +#define TIMES_SET_FLAGS (ATTR_MTIME_SET | ATTR_ATIME_SET | ATTR_TIMES_SET) struct ll_dentry_data { - struct lookup_intent *lld_it; unsigned int lld_sa_generation; unsigned int lld_invalid:1; unsigned int lld_nfs_dentry:1; @@ -102,6 +104,16 @@ struct ll_grouplock { unsigned long lg_gid; }; +/* See comment on trunc_sem_down_read_nowait */ +struct ll_trunc_sem { + /* when positive, this is a count of readers, when -1, it indicates + * the semaphore is held for write, and 0 is unlocked + */ + atomic_t ll_trunc_readers; + /* this tracks a count of waiting writers */ + atomic_t ll_trunc_waiters; +}; + struct ll_inode_info { __u32 lli_inode_magic; spinlock_t lli_lock; @@ -131,21 +143,14 @@ struct ll_inode_info { s64 lli_atime; s64 lli_mtime; s64 lli_ctime; + s64 lli_btime; spinlock_t lli_agl_lock; - /* update atime from MDS no matter if it's older than - * local inode atime. */ - unsigned int lli_update_atime:1, - lli_inode_locked:1; - /* Try to make the d::member and f::member are aligned. Before using * these members, make clear whether it is directory or not. */ union { /* for directory */ struct { - /* serialize normal readdir and statahead-readdir. */ - struct mutex lli_readdir_mutex; - /* metadata statahead */ /* since parent-child threads can share the same @file * struct, "opendir_key" is the token when dir close for @@ -166,29 +171,21 @@ struct ll_inode_info { unsigned int lli_sa_enabled:1; /* generation for statahead */ unsigned int lli_sa_generation; + /* rw lock protects lli_lsm_md */ + struct rw_semaphore lli_lsm_sem; /* directory stripe information */ struct lmv_stripe_md *lli_lsm_md; - /* default directory stripe offset. This is extracted - * from the "dmv" xattr in order to decide which MDT to - * create a subdirectory on. The MDS itself fetches - * "dmv" and gets the rest of the default layout itself - * (count, hash, etc). */ - __u32 lli_def_stripe_offset; + /* directory default LMV */ + struct lmv_stripe_md *lli_default_lsm_md; }; /* for non-directory */ struct { struct mutex lli_size_mutex; char *lli_symlink_name; - /* - * struct rw_semaphore { - * signed long count; // align d.d_def_acl - * spinlock_t wait_lock; // align d.d_sa_lock - * struct list_head wait_list; - * } - */ - struct rw_semaphore lli_trunc_sem; + struct ll_trunc_sem lli_trunc_sem; struct range_lock_tree lli_write_tree; + struct mutex lli_setattr_mutex; struct rw_semaphore lli_glimpse_sem; ktime_t lli_glimpse_time; @@ -198,6 +195,11 @@ struct ll_inode_info { /* for writepage() only to communicate to fsync */ int lli_async_rc; + /* protect the file heat fields */ + spinlock_t lli_heat_lock; + __u32 lli_heat_flags; + struct obd_heat_instance lli_heat_instances[OBD_HEAT_COUNT]; + /* * Whenever a process try to read/write the file, the * jobid of the process will be saved here, and it'll @@ -207,19 +209,46 @@ struct ll_inode_info { * accurate if the file is shared by different jobs. */ char lli_jobid[LUSTRE_JOBID_SIZE]; + + struct mutex lli_pcc_lock; + enum lu_pcc_state_flags lli_pcc_state; + /* + * @lli_pcc_generation saves the gobal PCC generation + * when the file was successfully attached into PCC. + * The flags of the PCC dataset are saved in + * @lli_pcc_dsflags. + * The gobal PCC generation will be increased when add + * or delete a PCC backend, or change the configuration + * parameters for PCC. + * If @lli_pcc_generation is same as the gobal PCC + * generation, we can use the saved flags of the PCC + * dataset to determine whether need to try auto attach + * safely. + */ + __u64 lli_pcc_generation; + enum pcc_dataset_flags lli_pcc_dsflags; + struct pcc_inode *lli_pcc_inode; + + struct mutex lli_group_mutex; + __u64 lli_group_users; + unsigned long lli_group_gid; + + __u64 lli_attr_valid; + __u64 lli_lazysize; + __u64 lli_lazyblocks; }; }; - /* XXX: For following frequent used members, although they maybe special - * used for non-directory object, it is some time-wasting to check - * whether the object is directory or not before using them. On the - * other hand, currently, sizeof(f) > sizeof(d), it cannot reduce - * the "ll_inode_info" size even if moving those members into u.f. - * So keep them out side. - * - * In the future, if more members are added only for directory, - * some of the following members can be moved into u.f. - */ + /* XXX: For following frequent used members, although they maybe special + * used for non-directory object, it is some time-wasting to check + * whether the object is directory or not before using them. On the + * other hand, currently, sizeof(f) > sizeof(d), it cannot reduce + * the "ll_inode_info" size even if moving those members into u.f. + * So keep them out side. + * + * In the future, if more members are added only for directory, + * some of the following members can be moved into u.f. + */ struct cl_object *lli_clob; /* mutex to request for layout lock exclusively. */ @@ -235,6 +264,116 @@ struct ll_inode_info { struct list_head lli_xattrs; /* ll_xattr_entry->xe_list */ }; +static inline void ll_trunc_sem_init(struct ll_trunc_sem *sem) +{ + atomic_set(&sem->ll_trunc_readers, 0); + atomic_set(&sem->ll_trunc_waiters, 0); +} + +/* This version of down read ignores waiting writers, meaning if the semaphore + * is already held for read, this down_read will 'join' that reader and also + * take the semaphore. + * + * This lets us avoid an unusual deadlock. + * + * 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 trunc_sem to exclude truncate. + * + * This means the locking order for trunc_sem and mmap_sem 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. + * + * However, if a write mode user (truncate, a setattr op) arrives in the + * middle of this, the second reader on the truncate_sem will wait behind that + * writer. + * + * 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) + * writer + * reader (holding truncate sem, waiting for mmap_sem) + * + * And so the readers deadlock. + * + * The solution is this modified semaphore, where this down_read ignores + * waiting write operations, and all waiters are woken up at once, so readers + * using down_read_nowait cannot get stuck behind waiting writers, regardless + * 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 + * (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. + * + * LU-12460 + */ +static inline void trunc_sem_down_read_nowait(struct ll_trunc_sem *sem) +{ + wait_var_event(&sem->ll_trunc_readers, + atomic_inc_unless_negative(&sem->ll_trunc_readers)); +} + +static inline void trunc_sem_down_read(struct ll_trunc_sem *sem) +{ + wait_var_event(&sem->ll_trunc_readers, + atomic_read(&sem->ll_trunc_waiters) == 0 && + atomic_inc_unless_negative(&sem->ll_trunc_readers)); +} + +static inline void trunc_sem_up_read(struct ll_trunc_sem *sem) +{ + if (atomic_dec_return(&sem->ll_trunc_readers) == 0 && + atomic_read(&sem->ll_trunc_waiters)) + wake_up_var(&sem->ll_trunc_readers); +} + +static inline void trunc_sem_down_write(struct ll_trunc_sem *sem) +{ + atomic_inc(&sem->ll_trunc_waiters); + wait_var_event(&sem->ll_trunc_readers, + atomic_cmpxchg(&sem->ll_trunc_readers, 0, -1) == 0); + atomic_dec(&sem->ll_trunc_waiters); +} + +static inline void trunc_sem_up_write(struct ll_trunc_sem *sem) +{ + atomic_set(&sem->ll_trunc_readers, 0); + wake_up_var(&sem->ll_trunc_readers); +} + +#ifdef CONFIG_LUSTRE_FS_POSIX_ACL +static inline void lli_clear_acl(struct ll_inode_info *lli) +{ + if (lli->lli_posix_acl) { + posix_acl_release(lli->lli_posix_acl); + lli->lli_posix_acl = NULL; + } +} + +static inline void lli_replace_acl(struct ll_inode_info *lli, + struct lustre_md *md) +{ + spin_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); +} +#else +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) +{ +} +#endif + static inline __u32 ll_layout_version_get(struct ll_inode_info *lli) { __u32 gen; @@ -260,6 +399,11 @@ enum ll_file_flags { LLIF_FILE_RESTORING = 1, /* Xattr cache is attached to the file */ LLIF_XATTR_CACHE = 2, + /* Project inherit */ + LLIF_PROJECT_INHERIT = 3, + /* update atime from MDS even if it's older than local inode atime. */ + LLIF_UPDATE_ATIME = 4, + }; static inline void ll_file_set_flag(struct ll_inode_info *lli, @@ -289,10 +433,32 @@ static inline bool ll_file_test_and_clear_flag(struct ll_inode_info *lli, int ll_xattr_cache_destroy(struct inode *inode); int ll_xattr_cache_get(struct inode *inode, - const char *name, - char *buffer, - size_t size, - __u64 valid); + const char *name, + char *buffer, + size_t size, + __u64 valid); + +int ll_xattr_cache_insert(struct inode *inode, + const char *name, + char *buffer, + size_t size); + +static inline bool obd_connect_has_secctx(struct obd_connect_data *data) +{ +#ifdef CONFIG_SECURITY + return data->ocd_connect_flags & OBD_CONNECT_FLAGS2 && + data->ocd_connect_flags2 & OBD_CONNECT2_FILE_SECCTX; +#else + return false; +#endif +} + +static inline void obd_connect_set_secctx(struct obd_connect_data *data) +{ +#ifdef CONFIG_SECURITY + data->ocd_connect_flags2 |= OBD_CONNECT2_FILE_SECCTX; +#endif +} int ll_dentry_init_security(struct dentry *dentry, int mode, struct qstr *name, const char **secctx_name, void **secctx, @@ -300,6 +466,26 @@ int ll_dentry_init_security(struct dentry *dentry, int mode, struct qstr *name, int ll_inode_init_security(struct dentry *dentry, struct inode *inode, struct inode *dir); +int ll_listsecurity(struct inode *inode, char *secctx_name, + size_t secctx_name_size); + +static inline bool obd_connect_has_enc(struct obd_connect_data *data) +{ +#ifdef HAVE_LUSTRE_CRYPTO + return data->ocd_connect_flags & OBD_CONNECT_FLAGS2 && + data->ocd_connect_flags2 & OBD_CONNECT2_ENCRYPT; +#else + return false; +#endif +} + +static inline void obd_connect_set_enc(struct obd_connect_data *data) +{ +#ifdef HAVE_LUSTRE_CRYPTO + data->ocd_connect_flags2 |= OBD_CONNECT2_ENCRYPT; +#endif +} + /* * Locking to guarantee consistency of non-atomic updates to long long i_size, * consistency between file size and KMS. @@ -310,18 +496,27 @@ int ll_inode_init_security(struct dentry *dentry, struct inode *inode, void ll_inode_size_lock(struct inode *inode); void ll_inode_size_unlock(struct inode *inode); -// FIXME: replace the name of this with LL_I to conform to kernel stuff -// static inline struct ll_inode_info *LL_I(struct inode *inode) static inline struct ll_inode_info *ll_i2info(struct inode *inode) { - return container_of(inode, struct ll_inode_info, lli_vfs_inode); + return container_of(inode, struct ll_inode_info, lli_vfs_inode); +} + +static inline struct pcc_inode *ll_i2pcci(struct inode *inode) +{ + return ll_i2info(inode)->lli_pcc_inode; } -/* default to about 64M of readahead on a given system. */ -#define SBI_DEFAULT_READAHEAD_MAX (64UL << (20 - PAGE_SHIFT)) +/* default to use at least 16M for fast read if possible */ +#define RA_REMAIN_WINDOW_MIN MiB_TO_PAGES(16UL) + +/* default read-ahead on a given client mountpoint. */ +#define SBI_DEFAULT_READ_AHEAD_MAX MiB_TO_PAGES(1024UL) + +/* default read-ahead for a single file descriptor */ +#define SBI_DEFAULT_READ_AHEAD_PER_FILE_MAX MiB_TO_PAGES(256UL) -/* default to read-ahead full files smaller than 2MB on the second read */ -#define SBI_DEFAULT_READAHEAD_WHOLE_MAX (2UL << (20 - PAGE_SHIFT)) +/* default read-ahead full files smaller than limit on the second read */ +#define SBI_DEFAULT_READ_AHEAD_WHOLE_MAX MiB_TO_PAGES(2UL) enum ra_stat { RA_STAT_HIT = 0, @@ -337,6 +532,8 @@ enum ra_stat { RA_STAT_MAX_IN_FLIGHT, RA_STAT_WRONG_GRAB_PAGE, RA_STAT_FAILED_REACH_END, + RA_STAT_ASYNC, + RA_STAT_FAILED_FAST_READ, _NR_RA_STAT, }; @@ -345,6 +542,16 @@ struct ll_ra_info { unsigned long ra_max_pages; unsigned long ra_max_pages_per_file; unsigned long ra_max_read_ahead_whole_pages; + struct workqueue_struct *ll_readahead_wq; + /* + * Max number of active works could be triggered + * for async readahead. + */ + unsigned int ra_async_max_active; + /* how many async readahead triggered in flight */ + atomic_t ra_async_inflight; + /* Threshold to control when to trigger async readahead */ + unsigned long ra_async_pages_per_file_threshold; }; /* ra_io_arg will be filled in the beginning of ll_readahead with @@ -353,20 +560,20 @@ struct ll_ra_info { * counted by page index. */ struct ra_io_arg { - unsigned long ria_start; /* start offset of read-ahead*/ - unsigned long ria_end; /* end offset of read-ahead*/ - unsigned long ria_reserved; /* reserved pages for read-ahead */ - unsigned long ria_end_min; /* minimum end to cover current read */ - bool ria_eof; /* reach end of file */ - /* If stride read pattern is detected, ria_stoff means where - * stride read is started. Note: for normal read-ahead, the + pgoff_t ria_start_idx; /* start offset of read-ahead*/ + pgoff_t ria_end_idx; /* end offset of read-ahead*/ + unsigned long ria_reserved; /* reserved pages for read-ahead */ + pgoff_t ria_end_idx_min;/* minimum end to cover current read */ + bool ria_eof; /* reach end of file */ + /* If stride read pattern is detected, ria_stoff is the byte offset + * where stride read is started. Note: for normal read-ahead, the * value here is meaningless, and also it will not be accessed*/ - pgoff_t ria_stoff; - /* ria_length and ria_pages are the length and pages length in the + loff_t ria_stoff; + /* ria_length and ria_bytes are the length and pages length in the * stride I/O mode. And they will also be used to check whether * it is stride I/O read-ahead in the read-ahead pages*/ - unsigned long ria_length; - unsigned long ria_pages; + loff_t ria_length; + loff_t ria_bytes; }; /* LL_HIST_MAX=32 causes an overflow */ @@ -430,9 +637,12 @@ enum stats_track_type { * suppress_pings */ #define LL_SBI_FAST_READ 0x400000 /* fast read support */ #define LL_SBI_FILE_SECCTX 0x800000 /* set file security context at create */ -#define LL_SBI_PIO 0x1000000 /* parallel IO support */ +/* 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", \ @@ -459,7 +669,10 @@ enum stats_track_type { "fast_read", \ "file_secctx", \ "pio", \ - "tiny_write", \ + "tiny_write", \ + "file_heat", \ + "test_dummy_encryption", \ + "noencrypt", \ } /* This is embedded into llite super-blocks to keep track of connect @@ -478,18 +691,19 @@ struct lustre_client_ocd { struct ll_sb_info { /* this protects pglist and ra_info. It isn't safe to * grab from interrupt contexts */ - spinlock_t ll_lock; - spinlock_t ll_pp_extent_lock; /* pp_extent entry*/ - spinlock_t ll_process_lock; /* ll_rw_process_info */ - struct obd_uuid ll_sb_uuid; - struct obd_export *ll_md_exp; - struct obd_export *ll_dt_exp; - struct proc_dir_entry* ll_proc_root; - struct lu_fid ll_root_fid; /* root object fid */ + spinlock_t ll_lock; + spinlock_t ll_pp_extent_lock; /* pp_extent entry*/ + spinlock_t ll_process_lock; /* ll_rw_process_info */ + struct obd_uuid ll_sb_uuid; + struct obd_export *ll_md_exp; + struct obd_export *ll_dt_exp; + struct obd_device *ll_md_obd; + struct obd_device *ll_dt_obd; + struct dentry *ll_debugfs_entry; + struct lu_fid ll_root_fid; /* root object fid */ int ll_flags; - unsigned int ll_umounting:1, - ll_xattr_cache_enabled:1, + 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; @@ -544,25 +758,34 @@ struct ll_sb_info { /* st_blksize returned by stat(2), when non-zero */ unsigned int ll_stat_blksize; + /* maximum relative age of cached statfs results */ + unsigned int ll_statfs_max_age; + struct kset ll_kset; /* sysfs object */ struct completion ll_kobj_unregister; + + /* File heat */ + unsigned int ll_heat_decay_weight; + unsigned int ll_heat_period_second; + + /* filesystem fsname */ + char ll_fsname[LUSTRE_MAXFSNAME + 1]; + + /* Persistent Client Cache */ + struct pcc_super ll_pcc_super; }; +#define SBI_DEFAULT_HEAT_DECAY_WEIGHT ((80 * 256 + 50) / 100) +#define SBI_DEFAULT_HEAT_PERIOD_SECOND (60) /* * per file-descriptor read-ahead data. */ struct ll_readahead_state { - spinlock_t ras_lock; + spinlock_t ras_lock; + /* End byte that read(2) try to read. */ + loff_t ras_last_read_end_bytes; /* - * index of the last page that read(2) needed and that wasn't in the - * cache. Used by ras_update() to detect seeks. - * - * XXX nikita: if access seeks into cached region, Lustre doesn't see - * this. - */ - unsigned long ras_last_readpage; - /* - * number of pages read after last read-ahead window reset. As window + * number of bytes read after last read-ahead window reset. As window * is reset on each seek, this is effectively a number of consecutive * accesses. Maybe ->ras_accessed_in_window is better name. * @@ -571,13 +794,13 @@ struct ll_readahead_state { * case, it probably doesn't make sense to expand window to * PTLRPC_MAX_BRW_PAGES on the third access. */ - unsigned long ras_consecutive_pages; + loff_t ras_consecutive_bytes; /* * number of read requests after the last read-ahead window reset * As window is reset on each seek, this is effectively the number * on consecutive read request and is used to trigger read-ahead. */ - unsigned long ras_consecutive_requests; + unsigned long ras_consecutive_requests; /* * Parameters of current read-ahead window. Handled by * ras_update(). On the initial access to the file or after a seek, @@ -585,12 +808,13 @@ struct ll_readahead_state { * expanded to PTLRPC_MAX_BRW_PAGES. Afterwards, window is enlarged by * PTLRPC_MAX_BRW_PAGES chunks up to ->ra_max_pages. */ - unsigned long ras_window_start, ras_window_len; + pgoff_t ras_window_start_idx; + pgoff_t ras_window_pages; /* - * Optimal RPC size. It decides how many pages will be sent - * for each read-ahead. + * Optimal RPC size in pages. + * It decides how many pages will be sent for each read-ahead. */ - unsigned long ras_rpc_size; + unsigned long ras_rpc_pages; /* * Where next read-ahead should start at. This lies within read-ahead * window. Read-ahead window is read in pieces rather than at once @@ -598,39 +822,51 @@ struct ll_readahead_state { * ->ra_max_pages (see ll_ra_count_get()), 2. client cannot read pages * not covered by DLM lock. */ - unsigned long ras_next_readahead; + pgoff_t ras_next_readahead_idx; /* * Total number of ll_file_read requests issued, reads originating * due to mmap are not counted in this total. This value is used to * trigger full file read-ahead after multiple reads to a small file. */ - unsigned long ras_requests; - /* - * Page index with respect to the current request, these value - * will not be accurate when dealing with reads issued via mmap. - */ - unsigned long ras_request_index; + unsigned long ras_requests; /* * The following 3 items are used for detecting the stride I/O * mode. * In stride I/O mode, * ...............|-----data-----|****gap*****|--------|******|.... - * offset |-stride_pages-|-stride_gap-| + * offset |-stride_bytes-|-stride_gap-| * ras_stride_offset = offset; - * ras_stride_length = stride_pages + stride_gap; - * ras_stride_pages = stride_pages; - * Note: all these three items are counted by pages. - */ - unsigned long ras_stride_length; - unsigned long ras_stride_pages; - pgoff_t ras_stride_offset; + * ras_stride_length = stride_bytes + stride_gap; + * ras_stride_bytes = stride_bytes; + * Note: all these three items are counted by bytes. + */ + loff_t ras_stride_offset; + loff_t ras_stride_length; + loff_t ras_stride_bytes; /* * number of consecutive stride request count, and it is similar as * ras_consecutive_requests, but used for stride I/O mode. * Note: only more than 2 consecutive stride request are detected, * stride read-ahead will be enable */ - unsigned long ras_consecutive_stride_requests; + unsigned long ras_consecutive_stride_requests; + /* index of the last page that async readahead starts */ + pgoff_t ras_async_last_readpage_idx; + /* whether we should increase readahead window */ + bool ras_need_increase_window; + /* whether ra miss check should be skipped */ + bool ras_no_miss_check; +}; + +struct ll_readahead_work { + /** File to readahead */ + struct file *lrw_file; + pgoff_t lrw_start_idx; + pgoff_t lrw_end_idx; + + /* async worker to handler read */ + struct work_struct lrw_readahead_work; + char lrw_jobid[LUSTRE_JOBID_SIZE]; }; extern struct kmem_cache *ll_file_data_slab; @@ -659,9 +895,9 @@ struct ll_file_data { /* The layout version when resync starts. Resync I/O should carry this * layout version for verification to OST objects */ __u32 fd_layout_version; + struct pcc_file fd_pcc_file; }; -extern struct proc_dir_entry *proc_lustre_fs_root; void llite_tunables_unregister(void); int llite_tunables_register(void); @@ -706,7 +942,12 @@ static inline bool ll_sbi_has_tiny_write(struct ll_sb_info *sbi) return !!(sbi->ll_flags & LL_SBI_TINY_WRITE); } -void ll_ras_enter(struct file *f); +static inline bool ll_sbi_has_file_heat(struct ll_sb_info *sbi) +{ + return !!(sbi->ll_flags & LL_SBI_FILE_HEAT); +} + +void ll_ras_enter(struct file *f, loff_t pos, size_t count); /* llite/lcommon_misc.c */ int cl_ocd_update(struct obd_device *host, struct obd_device *watched, @@ -716,30 +957,19 @@ int cl_get_grouplock(struct cl_object *obj, unsigned long gid, int nonblock, void cl_put_grouplock(struct ll_grouplock *lg); /* llite/lproc_llite.c */ -#ifdef CONFIG_PROC_FS -int lprocfs_ll_register_obd(struct super_block *sb, const char *obdname); -void ll_stats_ops_tally(struct ll_sb_info *sbi, int op, int count); -extern struct lprocfs_vars lprocfs_llite_obd_vars[]; -#else -static inline int ll_debugs_register_super(struct super_block *sb, - const char *name) -{ return 0; } -static void ll_stats_ops_tally(struct ll_sb_info *sbi, int op, int count) {} -#endif 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); enum { - LPROC_LL_DIRTY_HITS, - LPROC_LL_DIRTY_MISSES, LPROC_LL_READ_BYTES, LPROC_LL_WRITE_BYTES, - LPROC_LL_BRW_READ, - LPROC_LL_BRW_WRITE, + LPROC_LL_READ, + LPROC_LL_WRITE, LPROC_LL_IOCTL, LPROC_LL_OPEN, LPROC_LL_RELEASE, - LPROC_LL_MAP, + LPROC_LL_MMAP, LPROC_LL_FAULT, LPROC_LL_MKWRITE, LPROC_LL_LLSEEK, @@ -757,18 +987,22 @@ enum { LPROC_LL_RMDIR, LPROC_LL_MKNOD, LPROC_LL_RENAME, - LPROC_LL_STAFS, - LPROC_LL_ALLOC_INODE, + LPROC_LL_STATFS, LPROC_LL_SETXATTR, LPROC_LL_GETXATTR, LPROC_LL_GETXATTR_HITS, LPROC_LL_LISTXATTR, LPROC_LL_REMOVEXATTR, LPROC_LL_INODE_PERM, + LPROC_LL_FALLOCATE, LPROC_LL_FILE_OPCODES }; /* llite/dir.c */ +enum get_default_layout_type { + GET_DEFAULT_LAYOUT_ROOT = 1, +}; + struct ll_dir_chain { }; @@ -794,6 +1028,7 @@ 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); void ll_release_page(struct inode *inode, struct page *page, bool remove); +int quotactl_ioctl(struct ll_sb_info *sbi, struct if_quotactl *qctl); /* llite/namei.c */ extern const struct inode_operations ll_special_inode_operations; @@ -848,28 +1083,40 @@ int ll_getattr(const struct path *path, struct kstat *stat, #else 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 -#ifdef CONFIG_FS_POSIX_ACL +#ifdef CONFIG_LUSTRE_FS_POSIX_ACL int ll_set_acl(struct inode *inode, struct posix_acl *acl, int type); -#else /* !CONFIG_FS_POSIX_ACL */ +#else /* !CONFIG_LUSTRE_FS_POSIX_ACL */ #define ll_set_acl NULL -#endif /* CONFIG_FS_POSIX_ACL */ +#endif /* CONFIG_LUSTRE_FS_POSIX_ACL */ #endif -int ll_migrate(struct inode *parent, struct file *file, int mdtidx, - const char *name, int namelen); + +static inline int ll_xflags_to_inode_flags(int xflags) +{ + return ((xflags & FS_XFLAG_SYNC) ? S_SYNC : 0) | + ((xflags & FS_XFLAG_NOATIME) ? S_NOATIME : 0) | + ((xflags & FS_XFLAG_APPEND) ? S_APPEND : 0) | + ((xflags & FS_XFLAG_IMMUTABLE) ? S_IMMUTABLE : 0); +} + +static inline int ll_inode_flags_to_xflags(int 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); +} + +int ll_migrate(struct inode *parent, struct file *file, + struct lmv_user_md *lum, const char *name); int ll_get_fid_by_name(struct inode *parent, const char *name, int namelen, struct lu_fid *fid, struct inode **inode); -#ifdef HAVE_GENERIC_PERMISSION_4ARGS -int ll_inode_permission(struct inode *inode, int mask, unsigned int flags); -#else -# ifndef HAVE_INODE_PERMISION_2ARGS -int ll_inode_permission(struct inode *inode, int mask, struct nameidata *nd); -# else int ll_inode_permission(struct inode *inode, int mask); -# endif -#endif +int ll_ioctl_check_project(struct inode *inode, struct fsxattr *fa); int ll_ioctl_fsgetxattr(struct inode *inode, unsigned int cmd, unsigned long arg); int ll_ioctl_fssetxattr(struct inode *inode, unsigned int cmd, @@ -883,16 +1130,12 @@ int ll_lov_getstripe_ea_info(struct inode *inode, const char *filename, struct ptlrpc_request **request); int ll_dir_setstripe(struct inode *inode, struct lov_user_md *lump, int set_default); -int ll_dir_getstripe(struct inode *inode, void **lmmp, - int *lmm_size, struct ptlrpc_request **request, - u64 valid); -#ifdef HAVE_FILE_FSYNC_4ARGS +int ll_dir_getstripe_default(struct inode *inode, void **lmmp, + int *lmm_size, struct ptlrpc_request **request, + struct ptlrpc_request **root_request, u64 valid); +int ll_dir_getstripe(struct inode *inode, void **plmm, int *plmm_size, + struct ptlrpc_request **request, u64 valid); int ll_fsync(struct file *file, loff_t start, loff_t end, int data); -#elif defined(HAVE_FILE_FSYNC_2ARGS) -int ll_fsync(struct file *file, int data); -#else -int ll_fsync(struct file *file, struct dentry *dentry, int data); -#endif int ll_merge_attr(const struct lu_env *env, struct inode *inode); int ll_fid2path(struct inode *inode, void __user *arg); int ll_data_version(struct inode *inode, __u64 *data_version, int flags); @@ -906,7 +1149,7 @@ int ll_d_init(struct dentry *de); extern const struct dentry_operations ll_d_ops; void ll_intent_drop_lock(struct lookup_intent *); void ll_intent_release(struct lookup_intent *); -void ll_invalidate_aliases(struct inode *); +void ll_prune_aliases(struct inode *inode); void ll_lookup_finish_locks(struct lookup_intent *it, struct dentry *dentry); int ll_revalidate_it_finish(struct ptlrpc_request *request, struct lookup_intent *it, struct dentry *de); @@ -915,18 +1158,20 @@ int ll_revalidate_it_finish(struct ptlrpc_request *request, extern struct super_operations lustre_super_operations; void ll_lli_init(struct ll_inode_info *lli); -int ll_fill_super(struct super_block *sb, struct vfsmount *mnt); +int ll_fill_super(struct super_block *sb); void ll_put_super(struct super_block *sb); 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 ll_setattr_raw(struct dentry *dentry, struct iattr *attr, bool hsm_import); +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); 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); int ll_read_inode2(struct inode *inode, void *opaque); void ll_delete_inode(struct inode *inode); int ll_iocontrol(struct inode *inode, struct file *file, @@ -934,11 +1179,7 @@ int ll_iocontrol(struct inode *inode, struct file *file, int ll_flush_ctx(struct inode *inode); void ll_umount_begin(struct super_block *sb); int ll_remount_fs(struct super_block *sb, int *flags, char *data); -#ifdef HAVE_SUPEROPS_USE_DENTRY int ll_show_options(struct seq_file *seq, struct dentry *dentry); -#else -int ll_show_options(struct seq_file *seq, struct vfsmount *vfs); -#endif 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 *); @@ -946,28 +1187,22 @@ 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); int ll_set_default_mdsize(struct ll_sb_info *sbi, int default_mdsize); -int ll_process_config(struct lustre_cfg *lcfg); - -enum { - LUSTRE_OPC_MKDIR = 0, - LUSTRE_OPC_SYMLINK = 1, - LUSTRE_OPC_MKNOD = 2, - LUSTRE_OPC_CREATE = 3, - LUSTRE_OPC_ANY = 5, -}; +void ll_unlock_md_op_lsm(struct md_op_data *op_data); struct md_op_data *ll_prep_md_op_data(struct md_op_data *op_data, struct inode *i1, struct inode *i2, const char *name, size_t namelen, - __u32 mode, __u32 opc, void *data); + __u32 mode, enum md_op_code opc, + void *data); void ll_finish_md_op_data(struct md_op_data *op_data); int ll_get_obd_name(struct inode *inode, unsigned int cmd, unsigned long arg); -char *ll_get_fsname(struct super_block *sb, char *buf, int buflen); 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_dom_finish_open(struct inode *inode, struct ptlrpc_request *req); + /* Compute expected user md size when passing in a md from user space */ static inline ssize_t ll_lov_user_md_size(const struct lov_user_md *lum) { @@ -984,6 +1219,8 @@ static inline ssize_t ll_lov_user_md_size(const struct lov_user_md *lum) LOV_USER_MAGIC_SPECIFIC); case LOV_USER_MAGIC_COMP_V1: return ((struct lov_comp_md_v1 *)lum)->lcm_size; + case LOV_USER_MAGIC_FOREIGN: + return foreign_size(lum); } return -EINVAL; @@ -1004,17 +1241,11 @@ extern struct inode_operations ll_fast_symlink_inode_operations; */ struct vvp_io_args { /** normal/sendfile/splice */ - enum vvp_io_subtype via_io_subtype; - union { struct { struct kiocb *via_iocb; struct iov_iter *via_iter; } normal; - struct { - struct pipe_inode_info *via_pipe; - unsigned int via_flags; - } splice; } u; }; @@ -1033,7 +1264,6 @@ struct ll_cl_context { }; struct ll_thread_info { - struct iov_iter lti_iter; struct vvp_io_args lti_args; struct ra_io_arg lti_ria; struct ll_cl_context lti_io_ctx; @@ -1051,16 +1281,14 @@ static inline struct ll_thread_info *ll_env_info(const struct lu_env *env) return lti; } -static inline struct vvp_io_args *ll_env_args(const struct lu_env *env, - enum vvp_io_subtype type) +static inline struct vvp_io_args *ll_env_args(const struct lu_env *env) { - struct vvp_io_args *via = &ll_env_info(env)->lti_args; - - via->via_io_subtype = type; - - return via; + return &ll_env_info(env)->lti_args; } +void ll_io_init(struct cl_io *io, struct file *file, enum cl_io_type iot, + struct vvp_io_args *args); + /* llite/llite_mmap.c */ int ll_teardown_mmaps(struct address_space *mapping, __u64 first, __u64 last); @@ -1070,23 +1298,6 @@ void policy_from_vma(union ldlm_policy_data *policy, struct vm_area_struct *vma, struct vm_area_struct *our_vma(struct mm_struct *mm, unsigned long addr, size_t count); -static inline void ll_invalidate_page(struct page *vmpage) -{ - struct address_space *mapping = vmpage->mapping; - loff_t offset = vmpage->index << PAGE_SHIFT; - - LASSERT(PageLocked(vmpage)); - if (mapping == NULL) - return; - - /* - * truncate_complete_page() calls - * a_ops->invalidatepage()->cl_page_delete()->vvp_page_delete(). - */ - ll_teardown_mmaps(mapping, offset, offset + PAGE_SIZE); - truncate_complete_page(mapping, vmpage); -} - #define ll_s2sbi(sb) (s2lsi(sb)->lsi_llsbi) /* don't need an addref as the sb_info should be holding one */ @@ -1135,6 +1346,13 @@ static inline struct lu_fid *ll_inode2fid(struct inode *inode) return fid; } +static inline bool ll_dir_striped(struct inode *inode) +{ + LASSERT(inode); + return S_ISDIR(inode->i_mode) && + lmv_dir_striped(ll_i2info(inode)->lli_lsm_md); +} + static inline loff_t ll_file_maxbytes(struct inode *inode) { struct cl_object *obj = ll_i2info(inode)->lli_clob; @@ -1219,11 +1437,10 @@ 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 ptlrpc_thread sai_thread; /* stat-ahead thread */ - struct ptlrpc_thread sai_agl_thread; /* AGL thread */ + struct task_struct *sai_task; /* stat-ahead thread */ + struct task_struct *sai_agl_task; /* AGL thread */ struct list_head sai_interim_entries; /* entries which got async * stat reply, but not * instantiated */ @@ -1234,7 +1451,9 @@ struct ll_statahead_info { atomic_t sai_cache_count; /* entry count in cache */ }; -int ll_statahead(struct inode *dir, struct dentry **dentry, bool unplug); +int ll_revalidate_statahead(struct inode *dir, struct dentry **dentry, + bool unplug); +int ll_start_statahead(struct inode *dir, struct dentry *dentry, bool agl); void ll_authorize_statahead(struct inode *dir, void *key); void ll_deauthorize_statahead(struct inode *dir, void *key); @@ -1295,7 +1514,7 @@ dentry_may_statahead(struct inode *dir, struct dentry *dentry) return false; /* not the same process, don't statahead */ - if (lli->lli_opendir_pid != current_pid()) + if (lli->lli_opendir_pid != current->pid) return false; /* @@ -1313,7 +1532,8 @@ dentry_may_statahead(struct inode *dir, struct dentry *dentry) * 'lld_sa_generation == lli->lli_sa_generation'. */ ldd = ll_d2d(dentry); - if (ldd != NULL && ldd->lld_sa_generation == lli->lli_sa_generation) + if (ldd != NULL && lli->lli_sa_generation && + ldd->lld_sa_generation == lli->lli_sa_generation) return false; return true; @@ -1324,12 +1544,12 @@ int cl_sync_file_range(struct inode *inode, loff_t start, loff_t end, static inline int ll_file_nolock(const struct file *file) { - struct ll_file_data *fd = LUSTRE_FPRIVATE(file); + struct ll_file_data *fd = file->private_data; struct inode *inode = file_inode((struct file *)file); - LASSERT(fd != NULL); - return ((fd->fd_flags & LL_FILE_IGNORE_LOCK) || - (ll_i2sbi(inode)->ll_flags & LL_SBI_NOLCK)); + LASSERT(fd != NULL); + return ((fd->fd_flags & LL_FILE_IGNORE_LOCK) || + (ll_i2sbi(inode)->ll_flags & LL_SBI_NOLCK)); } static inline void ll_set_lock_data(struct obd_export *exp, struct inode *inode, @@ -1368,24 +1588,6 @@ static inline void ll_set_lock_data(struct obd_export *exp, struct inode *inode, *bits = it->it_lock_bits; } -static inline void ll_lock_dcache(struct inode *inode) -{ -#ifdef HAVE_DCACHE_LOCK - spin_lock(&dcache_lock); -#else - spin_lock(&inode->i_lock); -#endif -} - -static inline void ll_unlock_dcache(struct inode *inode) -{ -#ifdef HAVE_DCACHE_LOCK - spin_unlock(&dcache_lock); -#else - spin_unlock(&inode->i_lock); -#endif -} - static inline int d_lustre_invalid(const struct dentry *dentry) { struct ll_dentry_data *lld = ll_d2d(dentry); @@ -1403,28 +1605,18 @@ static inline void __d_lustre_invalidate(struct dentry *dentry) /* * Mark dentry INVALID, if dentry refcount is zero (this is normally case for - * ll_md_blocking_ast), unhash this dentry, and let dcache to reclaim it later; - * else dput() of the last refcount will unhash this dentry and kill it. + * ll_md_blocking_ast), it will be pruned by ll_prune_aliases() and + * ll_prune_negative_children(); otherwise dput() of the last refcount will + * unhash this dentry and kill it. */ -static inline void d_lustre_invalidate(struct dentry *dentry, int nested) +static inline void d_lustre_invalidate(struct dentry *dentry) { - CDEBUG(D_DENTRY, "invalidate dentry %.*s (%p) parent %p inode %p " - "refc %d\n", dentry->d_name.len, dentry->d_name.name, dentry, + CDEBUG(D_DENTRY, "invalidate dentry %pd (%p) parent %p inode %p refc %d\n", + dentry, dentry, dentry->d_parent, dentry->d_inode, ll_d_count(dentry)); - spin_lock_nested(&dentry->d_lock, - nested ? DENTRY_D_LOCK_NESTED : DENTRY_D_LOCK_NORMAL); + spin_lock(&dentry->d_lock); __d_lustre_invalidate(dentry); - /* - * We should be careful about dentries created by d_obtain_alias(). - * These dentries are not put in the dentry tree, instead they are - * linked to sb->s_anon through dentry->d_hash. - * shrink_dcache_for_umount() shrinks the tree and sb->s_anon list. - * If we unhashed such a dentry, unmount would not be able to find - * it and busy inodes would be reported. - */ - if (ll_d_count(dentry) == 0 && !(dentry->d_flags & DCACHE_DISCONNECTED)) - __d_drop(dentry); spin_unlock(&dentry->d_lock); } @@ -1436,6 +1628,18 @@ static inline void d_lustre_revalidate(struct dentry *dentry) spin_unlock(&dentry->d_lock); } +static inline dev_t ll_compat_encode_dev(dev_t dev) +{ + /* The compat_sys_*stat*() syscalls will fail unless the + * device majors and minors are both less than 256. Note that + * the value returned here will be passed through + * old_encode_dev() in cp_compat_stat(). And so we are not + * trying to return a valid compat (u16) device number, just + * one that will pass the old_valid_dev() check. */ + + return MKDEV(MAJOR(dev) & 0xff, MINOR(dev) & 0xff); +} + int ll_layout_conf(struct inode *inode, const struct cl_object_conf *conf); int ll_layout_refresh(struct inode *inode, __u32 *gen); int ll_layout_restore(struct inode *inode, loff_t start, __u64 length); @@ -1452,7 +1656,7 @@ int ll_getparent(struct file *file, struct getparent __user *arg); /* lcommon_cl.c */ int cl_setattr_ost(struct cl_object *obj, const struct iattr *attr, - unsigned int attr_flags); + enum op_xvalid xvalid, unsigned int attr_flags); extern struct lu_env *cl_inode_fini_env; extern __u16 cl_inode_fini_refcheck; @@ -1463,4 +1667,19 @@ void cl_inode_fini(struct inode *inode); u64 cl_fid_build_ino(const struct lu_fid *fid, int api32); u32 cl_fid_build_gen(const struct lu_fid *fid); +static inline struct pcc_super *ll_i2pccs(struct inode *inode) +{ + return &ll_i2sbi(inode)->ll_pcc_super; +} + +static inline struct pcc_super *ll_info2pccs(struct ll_inode_info *lli) +{ + return ll_i2pccs(ll_info2i(lli)); +} + +#ifdef HAVE_LUSTRE_CRYPTO +/* crypto.c */ +extern const struct llcrypt_operations lustre_cryptops; +#endif + #endif /* LLITE_INTERNAL_H */