X-Git-Url: https://git.whamcloud.com/?p=fs%2Flustre-release.git;a=blobdiff_plain;f=lustre%2Fllite%2Fllite_internal.h;h=480f21b89ef44f8dbded75f9f1c7ec99c2bdee7a;hp=4737a27f42211b48d468bbf044a0f18d27baebd5;hb=ea58c4cfb0fc255befbbb7754bd4ed71704a2a2c;hpb=fa1bff8f6f3afb858618a563b039af3bbf46153b diff --git a/lustre/llite/llite_internal.h b/lustre/llite/llite_internal.h index 4737a27..480f21b 100644 --- a/lustre/llite/llite_internal.h +++ b/lustre/llite/llite_internal.h @@ -23,7 +23,7 @@ * Copyright (c) 2003, 2010, Oracle and/or its affiliates. All rights reserved. * Use is subject to license terms. * - * Copyright (c) 2011, 2016, Intel Corporation. + * Copyright (c) 2011, 2017, Intel Corporation. */ /* * This file is part of Lustre, http://www.lustre.org/ @@ -33,7 +33,6 @@ #ifndef LLITE_INTERNAL_H #define LLITE_INTERNAL_H #include -#include #include /* for s2sbi */ #include #include @@ -45,10 +44,11 @@ #include #include #include - #include + #include "vvp_internal.h" #include "range_lock.h" +#include "pcc.h" #ifndef FMODE_EXEC #define FMODE_EXEC 0 @@ -136,17 +136,13 @@ struct ll_inode_info { /* update atime from MDS no matter if it's older than * local inode atime. */ - unsigned int lli_update_atime:1, - lli_inode_locked:1; + 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 @@ -167,20 +163,18 @@ 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 mutex lli_size_mutex; + char *lli_symlink_name; /* * struct rw_semaphore { * signed long count; // align d.d_def_acl @@ -188,26 +182,38 @@ struct ll_inode_info { * struct list_head wait_list; * } */ - struct rw_semaphore lli_trunc_sem; - struct range_lock_tree lli_write_tree; + struct rw_semaphore lli_trunc_sem; + struct range_lock_tree lli_write_tree; - struct rw_semaphore lli_glimpse_sem; - cfs_time_t lli_glimpse_time; - struct list_head lli_agl_list; - __u64 lli_agl_index; + struct rw_semaphore lli_glimpse_sem; + ktime_t lli_glimpse_time; + struct list_head lli_agl_list; + __u64 lli_agl_index; /* for writepage() only to communicate to fsync */ - int lli_async_rc; + 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 + * Whenever a process try to read/write the file, the * jobid of the process will be saved here, and it'll * be packed into the write PRC when flush later. * - * so the read/write statistics for jobid will not be + * So the read/write statistics for jobid will not be * 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; + struct pcc_inode *lli_pcc_inode; + struct mutex lli_group_mutex; + __u64 lli_group_users; + unsigned long lli_group_gid; }; }; @@ -261,6 +267,8 @@ 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, }; static inline void ll_file_set_flag(struct ll_inode_info *lli, @@ -295,12 +303,32 @@ int ll_xattr_cache_get(struct inode *inode, size_t size, __u64 valid); +static inline bool obd_connect_has_secctx(struct obd_connect_data *data) +{ +#if defined(HAVE_SECURITY_DENTRY_INIT_SECURITY) && defined(CONFIG_SECURITY) + return data->ocd_connect_flags & OBD_CONNECT_FLAGS2 && + data->ocd_connect_flags2 & OBD_CONNECT2_FILE_SECCTX; +#else + return false; +#endif /* HAVE_SECURITY_DENTRY_INIT_SECURITY */ +} + +static inline void obd_connect_set_secctx(struct obd_connect_data *data) +{ +#if defined(HAVE_SECURITY_DENTRY_INIT_SECURITY) && defined(CONFIG_SECURITY) + data->ocd_connect_flags2 |= OBD_CONNECT2_FILE_SECCTX; +#endif /* HAVE_SECURITY_DENTRY_INIT_SECURITY */ +} + int ll_dentry_init_security(struct dentry *dentry, int mode, struct qstr *name, const char **secctx_name, void **secctx, __u32 *secctx_size); 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); + /* * Locking to guarantee consistency of non-atomic updates to long long i_size, * consistency between file size and KMS. @@ -311,18 +339,24 @@ 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 use at least 16M for fast read if possible */ +#define RA_REMAIN_WINDOW_MIN MiB_TO_PAGES(16UL) + /* default to about 64M of readahead on a given system. */ -#define SBI_DEFAULT_READAHEAD_MAX (64UL << (20 - PAGE_SHIFT)) +#define SBI_DEFAULT_READAHEAD_MAX MiB_TO_PAGES(64UL) /* default to read-ahead full files smaller than 2MB on the second read */ -#define SBI_DEFAULT_READAHEAD_WHOLE_MAX (2UL << (20 - PAGE_SHIFT)) +#define SBI_DEFAULT_READAHEAD_WHOLE_MAX MiB_TO_PAGES(2UL) enum ra_stat { RA_STAT_HIT = 0, @@ -338,6 +372,8 @@ 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, }; @@ -346,6 +382,16 @@ 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 for readahead workqueue, + * default is 0 which make workqueue init number itself, + * unless there is a specific need for throttling the + * number of active work items, specifying '0' is recommended. + */ + unsigned int ra_async_max_active; + /* 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 @@ -354,20 +400,20 @@ 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*/ + pgoff_t ria_start; /* start offset of read-ahead*/ + pgoff_t 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 */ + pgoff_t 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 * 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 + unsigned long 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; + unsigned long ria_bytes; }; /* LL_HIST_MAX=32 causes an overflow */ @@ -431,8 +477,10 @@ 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_FLAGS { \ "nolck", \ "checksum", \ @@ -459,6 +507,8 @@ enum stats_track_type { "fast_read", \ "file_secctx", \ "pio", \ + "tiny_write", \ + "file_heat", \ } /* This is embedded into llite super-blocks to keep track of connect @@ -477,20 +527,22 @@ 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_client_common_fill_super_succeeded:1, + ll_checksum_set:1; struct lustre_client_ocd ll_lco; @@ -522,6 +574,8 @@ struct ll_sb_info { int ll_rw_stats_on; /* metadata stat-ahead */ + unsigned int ll_sa_running_max;/* max concurrent + * statahead instances */ unsigned int ll_sa_max; /* max statahead RPCs */ atomic_t ll_sa_total; /* statahead thread started * count */ @@ -539,23 +593,35 @@ 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; + /* End byte that read(2) try to read. */ + unsigned long ras_last_read_end; /* - * 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. * @@ -564,13 +630,13 @@ 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; + unsigned long 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, @@ -578,12 +644,12 @@ 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, ras_window_len; /* * Optimal RPC size. It decides how many pages will be sent * for each read-ahead. */ - unsigned long ras_rpc_size; + unsigned long ras_rpc_size; /* * Where next read-ahead should start at. This lies within read-ahead * window. Read-ahead window is read in pieces rather than at once @@ -591,39 +657,53 @@ 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; /* * 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; + 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_request_index; /* * 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. + */ + unsigned long ras_stride_length; + unsigned long ras_stride_bytes; + unsigned long ras_stride_offset; /* * 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; +}; + +struct ll_readahead_work { + /** File to readahead */ + struct file *lrw_file; + /** Start bytes */ + unsigned long lrw_start; + /** End bytes */ + unsigned long lrw_end; + + /* async worker to handler read */ + struct work_struct lrw_readahead_work; }; extern struct kmem_cache *ll_file_data_slab; @@ -643,11 +723,20 @@ struct ll_file_data { * true: failure is known, not report again. * 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; + /* 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); static inline struct inode *ll_info2i(struct ll_inode_info *lli) { @@ -685,6 +774,16 @@ static inline bool ll_sbi_has_fast_read(struct ll_sb_info *sbi) return !!(sbi->ll_flags & LL_SBI_FAST_READ); } +static inline bool ll_sbi_has_tiny_write(struct ll_sb_info *sbi) +{ + return !!(sbi->ll_flags & LL_SBI_TINY_WRITE); +} + +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); /* llite/lcommon_misc.c */ @@ -695,33 +794,19 @@ 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_mountpoint(struct proc_dir_entry *parent, - struct super_block *sb); -int lprocfs_ll_register_obd(struct super_block *sb, const char *obdname); -void lprocfs_ll_unregister_mountpoint(struct ll_sb_info *sbi); -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 lprocfs_ll_register_mountpoint(struct proc_dir_entry *parent, - struct super_block *sb) {return 0; } -static inline int lprocfs_ll_register_obd(struct super_block *sb, - const char *obdname) {return 0; } -static inline void lprocfs_ll_unregister_mountpoint(struct ll_sb_info *sbi) {} -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, @@ -739,8 +824,7 @@ 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, @@ -793,6 +877,8 @@ void ll_update_times(struct ptlrpc_request *request, struct inode *inode); int ll_writepage(struct page *page, struct writeback_control *wbc); int ll_writepages(struct address_space *, struct writeback_control *wbc); int ll_readpage(struct file *file, struct page *page); +int ll_io_read_page(const struct lu_env *env, struct cl_io *io, + struct cl_page *page, struct file *file); 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); @@ -822,21 +908,28 @@ int ll_md_real_close(struct inode *inode, fmode_t fmode); 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); +#ifdef HAVE_INODEOPS_ENHANCED_GETATTR +int ll_getattr(const struct path *path, struct kstat *stat, + u32 request_mask, unsigned int flags); +#else int ll_getattr(struct vfsmount *mnt, struct dentry *de, struct kstat *stat); +#endif +int ll_getattr_dentry(struct dentry *de, struct kstat *stat); struct posix_acl *ll_get_acl(struct inode *inode, int type); -int ll_migrate(struct inode *parent, struct file *file, int mdtidx, - const char *name, int namelen); +#ifdef HAVE_IOP_SET_ACL +#ifdef CONFIG_LUSTRE_FS_POSIX_ACL +int ll_set_acl(struct inode *inode, struct posix_acl *acl, int type); +#else /* !CONFIG_LUSTRE_FS_POSIX_ACL */ +#define ll_set_acl NULL +#endif /* CONFIG_LUSTRE_FS_POSIX_ACL */ + +#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); int ll_ioctl_fssetxattr(struct inode *inode, unsigned int cmd, @@ -853,18 +946,13 @@ int ll_dir_setstripe(struct inode *inode, struct lov_user_md *lump, 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_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); int ll_hsm_release(struct inode *inode); int ll_hsm_state_set(struct inode *inode, struct hsm_state_set *hss); +void ll_io_set_mirror(struct cl_io *io, const struct file *file); /* llite/dcache.c */ @@ -887,12 +975,14 @@ 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 super_block *sb, struct obd_statfs *osfs, - __u64 max_age, __u32 flags); +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, @@ -912,28 +1002,23 @@ 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, + struct lookup_intent *it); + /* 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) { @@ -950,6 +1035,8 @@ 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; @@ -999,10 +1086,8 @@ 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 kiocb lti_kiocb; struct ll_cl_context lti_io_ctx; }; @@ -1028,6 +1113,9 @@ static inline struct vvp_io_args *ll_env_args(const struct lu_env *env, return via; } +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); @@ -1037,23 +1125,6 @@ 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 */ @@ -1102,6 +1173,13 @@ 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; @@ -1113,12 +1191,20 @@ static inline loff_t ll_file_maxbytes(struct inode *inode) } /* llite/xattr.c */ -int ll_setxattr(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags); -ssize_t ll_getxattr(struct dentry *dentry, const char *name, - void *buffer, size_t size); +extern const struct xattr_handler *ll_xattr_handlers[]; + +#define XATTR_USER_T 1 +#define XATTR_TRUSTED_T 2 +#define XATTR_SECURITY_T 3 +#define XATTR_ACL_ACCESS_T 4 +#define XATTR_ACL_DEFAULT_T 5 +#define XATTR_LUSTRE_T 6 +#define XATTR_OTHER_T 7 + ssize_t ll_listxattr(struct dentry *dentry, char *buffer, size_t size); -int ll_removexattr(struct dentry *dentry, const char *name); +int ll_xattr_list(struct inode *inode, const char *name, int type, + void *buffer, size_t size, u64 valid); +const struct xattr_handler *get_xattr_type(const char *name); /** * Common IO arguments for various VFS I/O interfaces. @@ -1137,7 +1223,14 @@ void ll_ra_stats_inc(struct inode *inode, enum ra_stat which); #define LL_SA_RPC_MIN 2 #define LL_SA_RPC_DEF 32 -#define LL_SA_RPC_MAX 8192 +#define LL_SA_RPC_MAX 512 + +/* XXX: If want to support more concurrent statahead instances, + * please consider to decentralize the RPC lists attached + * on related import, such as imp_{sending,delayed}_list. + * LU-11079 */ +#define LL_SA_RUNNING_MAX 256 +#define LL_SA_RUNNING_DEF 16 #define LL_SA_CACHE_BIT 5 #define LL_SA_CACHE_SIZE (1 << LL_SA_CACHE_BIT) @@ -1202,11 +1295,18 @@ static inline int cl_glimpse_size(struct inode *inode) return cl_glimpse_size0(inode, 0); } +/* AGL is 'asychronous glimpse lock', which is a speculative lock taken as + * part of statahead */ static inline int cl_agl(struct inode *inode) { return cl_glimpse_size0(inode, 1); } +int ll_file_lock_ahead(struct file *file, struct llapi_lu_ladvise *ladvise); + +int cl_io_get(struct inode *inode, struct lu_env **envout, + struct cl_io **ioout, __u16 *refcheck); + static inline int ll_glimpse_size(struct inode *inode) { struct ll_inode_info *lli = ll_i2info(inode); @@ -1214,7 +1314,7 @@ static inline int ll_glimpse_size(struct inode *inode) down_read(&lli->lli_glimpse_sem); rc = cl_glimpse_size(inode); - lli->lli_glimpse_time = cfs_time_current(); + lli->lli_glimpse_time = ktime_get(); up_read(&lli->lli_glimpse_sem); return rc; } @@ -1264,71 +1364,9 @@ dentry_may_statahead(struct inode *dir, struct dentry *dentry) return true; } -/* llite ioctl register support rountine */ -enum llioc_iter { - LLIOC_CONT = 0, - LLIOC_STOP -}; - -#define LLIOC_MAX_CMD 256 - -/* - * Rules to write a callback function: - * - * Parameters: - * @magic: Dynamic ioctl call routine will feed this vaule with the pointer - * returned to ll_iocontrol_register. Callback functions should use this - * data to check the potential collasion of ioctl cmd. If collasion is - * found, callback function should return LLIOC_CONT. - * @rcp: The result of ioctl command. - * - * Return values: - * If @magic matches the pointer returned by ll_iocontrol_data, the - * callback should return LLIOC_STOP; return LLIOC_STOP otherwise. - */ -typedef enum llioc_iter (*llioc_callback_t)(struct inode *inode, - struct file *file, unsigned int cmd, unsigned long arg, - void *magic, int *rcp); - -/* export functions */ -/* Register ioctl block dynamatically for a regular file. - * - * @cmd: the array of ioctl command set - * @count: number of commands in the @cmd - * @cb: callback function, it will be called if an ioctl command is found to - * belong to the command list @cmd. - * - * Return vaule: - * A magic pointer will be returned if success; - * otherwise, NULL will be returned. - * */ -void *ll_iocontrol_register(llioc_callback_t cb, int count, unsigned int *cmd); -void ll_iocontrol_unregister(void *magic); - int cl_sync_file_range(struct inode *inode, loff_t start, loff_t end, enum cl_fsync_mode mode, int ignore_layout); -/** direct write pages */ -struct ll_dio_pages { - /** page array to be written. we don't support - * partial pages except the last one. */ - struct page **ldp_pages; - /* offset of each page */ - loff_t *ldp_offsets; - /** if ldp_offsets is NULL, it means a sequential - * pages to be written, then this is the file offset - * of the * first page. */ - loff_t ldp_start_offset; - /** how many bytes are to be written. */ - size_t ldp_size; - /** # of pages in the array. */ - int ldp_nr; -}; - -extern ssize_t ll_direct_rw_pages(const struct lu_env *env, struct cl_io *io, - int rw, struct inode *inode, - struct ll_dio_pages *pv); - static inline int ll_file_nolock(const struct file *file) { struct ll_file_data *fd = LUSTRE_FPRIVATE(file); @@ -1375,24 +1413,6 @@ 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); @@ -1443,16 +1463,27 @@ 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); -int ll_layout_write_intent(struct inode *inode, __u64 start, __u64 end); +int ll_layout_write_intent(struct inode *inode, enum layout_intent_opc opc, + struct lu_extent *ext); int ll_xattr_init(void); void ll_xattr_fini(void); -int ll_getxattr_common(struct inode *inode, const char *name, - void *buffer, size_t size, __u64 valid); int ll_page_sync_io(const struct lu_env *env, struct cl_io *io, struct cl_page *page, enum cl_req_type crt); @@ -1460,7 +1491,7 @@ 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;