X-Git-Url: https://git.whamcloud.com/?p=fs%2Flustre-release.git;a=blobdiff_plain;f=lustre%2Fllite%2Fllite_internal.h;h=78f6b9730d7a142b7ef1fc1f098733c0eb4e0179;hp=1e86edd8e382ea63ef570998fbfc6ce19e74d22e;hb=7d5d004506650c3739898e70d72c9a86b8aeeb88;hpb=478f97b212714bc3af9a9a104efab314ca942758 diff --git a/lustre/llite/llite_internal.h b/lustre/llite/llite_internal.h index 1e86edd..78f6b97 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 */ @@ -45,16 +43,18 @@ #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 #endif -#ifndef VM_FAULT_RETRY +#ifndef HAVE_VM_FAULT_RETRY #define VM_FAULT_RETRY 0 #endif @@ -72,10 +72,10 @@ #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; @@ -103,6 +103,16 @@ 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; @@ -123,6 +133,12 @@ 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; @@ -132,20 +148,14 @@ 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; - /* 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 @@ -178,15 +188,9 @@ struct ll_inode_info { 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; @@ -213,20 +217,43 @@ struct ll_inode_info { 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. */ @@ -242,6 +269,116 @@ 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_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_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. + * + * 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_lock, needs truncate_sem) + * writer + * reader (holding truncate sem, waiting for mmap_lock) + * + * 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_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. + * + * 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; @@ -269,55 +406,43 @@ enum ll_file_flags { LLIF_XATTR_CACHE = 2, /* Project inherit */ LLIF_PROJECT_INHERIT = 3, -}; - -static inline void ll_file_set_flag(struct ll_inode_info *lli, - enum ll_file_flags flag) -{ - set_bit(flag, &lli->lli_flags); -} + /* 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, -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_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) { -#if defined(HAVE_SECURITY_DENTRY_INIT_SECURITY) && defined(CONFIG_SECURITY) +#ifdef CONFIG_SECURITY return data->ocd_connect_flags & OBD_CONNECT_FLAGS2 && - data->ocd_connect_flags2 & OBD_CONNECT2_FILE_SECCTX; + data->ocd_connect_flags2 & OBD_CONNECT2_FILE_SECCTX; #else return false; -#endif /* HAVE_SECURITY_DENTRY_INIT_SECURITY */ +#endif } static inline void obd_connect_set_secctx(struct obd_connect_data *data) { -#if defined(HAVE_SECURITY_DENTRY_INIT_SECURITY) && defined(CONFIG_SECURITY) +#ifdef CONFIG_SECURITY data->ocd_connect_flags2 |= OBD_CONNECT2_FILE_SECCTX; -#endif /* HAVE_SECURITY_DENTRY_INIT_SECURITY */ +#endif } int ll_dentry_init_security(struct dentry *dentry, int mode, struct qstr *name, @@ -329,6 +454,23 @@ int ll_inode_init_security(struct dentry *dentry, struct inode *inode, 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. @@ -349,11 +491,23 @@ 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 MiB_TO_PAGES(64UL) +/* 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 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) -/* default to read-ahead full files smaller than 2MB on the second read */ -#define SBI_DEFAULT_READAHEAD_WHOLE_MAX MiB_TO_PAGES(2UL) +/* Min range pages */ +#define RA_MIN_MMAP_RANGE_PAGES 16UL enum ra_stat { RA_STAT_HIT = 0, @@ -369,6 +523,9 @@ 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, + RA_STAT_MMAP_RANGE_READ, _NR_RA_STAT, }; @@ -376,7 +533,18 @@ 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; + /* + * 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 @@ -385,20 +553,20 @@ 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 */ @@ -466,6 +634,11 @@ enum stats_track_type { 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_FOREIGN_SYMLINK 0x20000000 /* foreign fake-symlink support */ +/* foreign fake-symlink upcall registered */ +#define LL_SBI_FOREIGN_SYMLINK_UPCALL 0x40000000 #define LL_SBI_FLAGS { \ "nolck", \ "checksum", \ @@ -494,6 +667,10 @@ enum stats_track_type { "pio", \ "tiny_write", \ "file_heat", \ + "test_dummy_encryption", \ + "noencrypt", \ + "foreign_symlink", \ + "foreign_symlink_upcall", \ } /* This is embedded into llite super-blocks to keep track of connect @@ -523,16 +700,15 @@ struct ll_sb_info { 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, + 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; - 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 @@ -540,24 +716,24 @@ 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; + 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; /* metadata stat-ahead */ unsigned int ll_sa_running_max;/* max concurrent @@ -580,6 +756,9 @@ 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; @@ -587,30 +766,53 @@ 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. */ 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. * @@ -619,13 +821,13 @@ 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, @@ -633,12 +835,23 @@ 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; + + /* 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. 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 @@ -646,39 +859,51 @@ 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; @@ -759,7 +984,12 @@ 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); +static inline bool ll_sbi_has_foreign_symlink(struct ll_sb_info *sbi) +{ + return !!(sbi->ll_flags & LL_SBI_FOREIGN_SYMLINK); +} + +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, @@ -771,19 +1001,17 @@ void cl_put_grouplock(struct ll_grouplock *lg); /* llite/lproc_llite.c */ 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, int count); +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, @@ -801,29 +1029,24 @@ 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_INODE_OCOUNT, + LPROC_LL_INODE_OPCLTM, LPROC_LL_FILE_OPCODES }; /* llite/dir.c */ -struct ll_dir_chain { +enum get_default_layout_type { + GET_DEFAULT_LAYOUT_ROOT = 1, }; -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 @@ -836,8 +1059,9 @@ 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 ll_sb_info *sbi, struct if_quotactl *qctl); /* llite/namei.c */ extern const struct inode_operations ll_special_inode_operations; @@ -869,10 +1093,8 @@ struct ll_cl_context *ll_cl_find(struct file *file); 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, @@ -883,6 +1105,7 @@ 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); @@ -892,29 +1115,37 @@ 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); +int ll_getattr_dentry(struct dentry *de, struct kstat *stat, u32 request_mask, + unsigned int flags, bool foreign); +#ifdef CONFIG_LUSTRE_FS_POSIX_ACL struct posix_acl *ll_get_acl(struct inode *inode, int type); -#ifdef HAVE_IOP_SET_ACL -#ifdef CONFIG_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_get_acl NULL #define ll_set_acl NULL -#endif /* CONFIG_FS_POSIX_ACL */ +#endif /* CONFIG_LUSTRE_FS_POSIX_ACL */ + +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 inode_flags) +{ + 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); +} -#endif 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); @@ -929,16 +1160,12 @@ 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); @@ -952,16 +1179,16 @@ 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); /* 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, 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); @@ -974,19 +1201,16 @@ 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); 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); 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 *); @@ -1008,8 +1232,7 @@ 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, - struct lookup_intent *it); +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) @@ -1035,31 +1258,25 @@ 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. */ 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; }; @@ -1078,7 +1295,6 @@ 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; @@ -1096,42 +1312,22 @@ 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); 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); 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 */ @@ -1271,11 +1467,10 @@ 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 */ @@ -1286,7 +1481,9 @@ 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); @@ -1347,7 +1544,7 @@ 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; /* @@ -1365,7 +1562,8 @@ 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; @@ -1376,12 +1574,12 @@ 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, @@ -1420,24 +1618,6 @@ 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); @@ -1455,28 +1635,18 @@ 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); } @@ -1527,4 +1697,23 @@ 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 +/* 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 */