X-Git-Url: https://git.whamcloud.com/?p=fs%2Flustre-release.git;a=blobdiff_plain;f=lustre%2Fllite%2Fllite_internal.h;h=5bbe08932d6ec7a16e323929a3c4b81eeb487c0e;hp=36be655f9da6ef145f19e2fd9b3a478a6a83422f;hb=045c1a968a0478ee57aaa61deed8ec563bf50002;hpb=427e6a469722cf14b2cd80cec991a4154b4aae50 diff --git a/lustre/llite/llite_internal.h b/lustre/llite/llite_internal.h index 36be655..5bbe089 100644 --- a/lustre/llite/llite_internal.h +++ b/lustre/llite/llite_internal.h @@ -15,11 +15,7 @@ * * You should have received a copy of the GNU General Public License * version 2 along with this program; If not, see - * http://www.sun.com/software/products/lustre/docs/GPLv2.pdf - * - * Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara, - * CA 95054 USA or visit www.sun.com if you need additional information or - * have any questions. + * http://www.gnu.org/licenses/gpl-2.0.html * * GPL HEADER END */ @@ -27,7 +23,7 @@ * Copyright (c) 2003, 2010, Oracle and/or its affiliates. All rights reserved. * Use is subject to license terms. * - * Copyright (c) 2011, 2014, Intel Corporation. + * Copyright (c) 2011, 2017, Intel Corporation. */ /* * This file is part of Lustre, http://www.lustre.org/ @@ -37,7 +33,6 @@ #ifndef LLITE_INTERNAL_H #define LLITE_INTERNAL_H #include -#include #include /* for s2sbi */ #include #include @@ -49,6 +44,7 @@ #include #include #include +#include #include "vvp_internal.h" #include "range_lock.h" @@ -81,6 +77,7 @@ 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; struct rcu_head lld_rcu_head; }; @@ -89,9 +86,6 @@ struct ll_dentry_data { #define LLI_INODE_MAGIC 0x111d0de5 #define LLI_INODE_DEAD 0xdeadd00d -/* remote client permission cache */ -#define REMOTE_PERM_HASHSIZE 16 - struct ll_getname_data { #ifdef HAVE_DIR_CONTEXT struct dir_context ctx; @@ -101,18 +95,6 @@ struct ll_getname_data { int lgd_found; /* inode matched? */ }; -/* llite setxid/access permission for user on remote client */ -struct ll_remote_perm { - struct hlist_node lrp_list; - uid_t lrp_uid; - gid_t lrp_gid; - uid_t lrp_fsuid; - gid_t lrp_fsgid; - int lrp_access_perm; /* MAY_READ/WRITE/EXEC, this - is access permission with - lrp_fsuid/lrp_fsgid. */ -}; - struct ll_grouplock { struct lu_env *lg_env; struct cl_io *lg_io; @@ -120,37 +102,18 @@ struct ll_grouplock { unsigned long lg_gid; }; -enum lli_flags { - /* File data is modified. */ - LLIF_DATA_MODIFIED = 1 << 0, - /* File is being restored */ - LLIF_FILE_RESTORING = 1 << 1, - /* Xattr cache is attached to the file */ - LLIF_XATTR_CACHE = 1 << 2, -}; - struct ll_inode_info { __u32 lli_inode_magic; - __u32 lli_flags; - spinlock_t lli_lock; - struct posix_acl *lli_posix_acl; - struct hlist_head *lli_remote_perms; - struct mutex lli_rmtperm_mutex; + volatile unsigned long lli_flags; + struct posix_acl *lli_posix_acl; /* identifying fields for both metadata and data stacks. */ struct lu_fid lli_fid; /* master inode fid for stripe directory */ struct lu_fid lli_pfid; - struct list_head lli_oss_capas; - /* open count currently used by capability only, indicate whether - * capability needs renewal */ - atomic_t lli_open_count; - struct obd_capa *lli_mds_capa; - cfs_time_t lli_rmtperm_time; - /* We need all three because every inode may be opened in different * modes */ struct obd_client_handle *lli_mds_read_och; @@ -170,6 +133,10 @@ struct ll_inode_info { s64 lli_ctime; 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 { @@ -198,6 +165,8 @@ 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 @@ -210,9 +179,8 @@ struct ll_inode_info { /* for non-directory */ struct { - struct mutex lli_size_mutex; - char *lli_symlink_name; - __u64 lli_maxbytes; + struct mutex lli_size_mutex; + char *lli_symlink_name; /* * struct rw_semaphore { * signed long count; // align d.d_def_acl @@ -220,23 +188,23 @@ 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; /* - * 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]; @@ -253,7 +221,6 @@ struct ll_inode_info { * In the future, if more members are added only for directory, * some of the following members can be moved into u.f. */ - bool lli_has_smd; struct cl_object *lli_clob; /* mutex to request for layout lock exclusively. */ @@ -262,6 +229,8 @@ struct ll_inode_info { __u32 lli_layout_gen; spinlock_t lli_layout_lock; + __u32 lli_projid; /* project id */ + struct rw_semaphore lli_xattrs_list_rwsem; struct mutex lli_xattrs_enq_lock; struct list_head lli_xattrs; /* ll_xattr_entry->xe_list */ @@ -285,6 +254,41 @@ static inline void ll_layout_version_set(struct ll_inode_info *lli, __u32 gen) spin_unlock(&lli->lli_layout_lock); } +enum ll_file_flags { + /* File data is modified. */ + LLIF_DATA_MODIFIED = 0, + /* File is being restored */ + 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, + enum ll_file_flags flag) +{ + set_bit(flag, &lli->lli_flags); +} + +static inline void ll_file_clear_flag(struct ll_inode_info *lli, + enum ll_file_flags flag) +{ + clear_bit(flag, &lli->lli_flags); +} + +static inline bool ll_file_test_flag(struct ll_inode_info *lli, + enum ll_file_flags flag) +{ + return test_bit(flag, &lli->lli_flags); +} + +static inline bool ll_file_test_and_clear_flag(struct ll_inode_info *lli, + enum ll_file_flags flag) +{ + return test_and_clear_bit(flag, &lli->lli_flags); +} + int ll_xattr_cache_destroy(struct inode *inode); int ll_xattr_cache_get(struct inode *inode, @@ -293,6 +297,29 @@ 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); + /* * Locking to guarantee consistency of non-atomic updates to long long i_size, * consistency between file size and KMS. @@ -310,12 +337,11 @@ static inline struct ll_inode_info *ll_i2info(struct inode *inode) return container_of(inode, struct ll_inode_info, lli_vfs_inode); } -/* default to about 40meg of readahead on a given system. That much tied - * up in 512k readahead requests serviced at 40ms each is about 1GB/s. */ -#define SBI_DEFAULT_READAHEAD_MAX (40UL << (20 - PAGE_CACHE_SHIFT)) +/* default to about 64M of readahead on a given system. */ +#define SBI_DEFAULT_READAHEAD_MAX (64UL << (20 - PAGE_SHIFT)) /* default to read-ahead full files smaller than 2MB on the second read */ -#define SBI_DEFAULT_READAHEAD_WHOLE_MAX (2UL << (20 - PAGE_CACHE_SHIFT)) +#define SBI_DEFAULT_READAHEAD_WHOLE_MAX (2UL << (20 - PAGE_SHIFT)) enum ra_stat { RA_STAT_HIT = 0, @@ -347,17 +373,20 @@ 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*/ - /* 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 - * 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_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 + * 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 + * 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; }; /* LL_HIST_MAX=32 causes an overflow */ @@ -402,9 +431,9 @@ enum stats_track_type { #define LL_SBI_FLOCK 0x04 #define LL_SBI_USER_XATTR 0x08 /* support user xattr */ #define LL_SBI_ACL 0x10 /* support ACL */ -#define LL_SBI_RMT_CLIENT 0x40 /* remote client */ -#define LL_SBI_MDS_CAPA 0x80 /* support mds capa */ -#define LL_SBI_OSS_CAPA 0x100 /* support oss capa */ +/* LL_SBI_RMT_CLIENT 0x40 remote client */ +#define LL_SBI_MDS_CAPA 0x80 /* support mds capa, obsolete */ +#define LL_SBI_OSS_CAPA 0x100 /* support oss capa, obsolete */ #define LL_SBI_LOCALFLOCK 0x200 /* Local flocks support by kernel */ #define LL_SBI_LRU_RESIZE 0x400 /* lru resize support */ #define LL_SBI_LAZYSTATFS 0x800 /* lazystatfs mount option */ @@ -417,6 +446,13 @@ enum stats_track_type { #define LL_SBI_USER_FID2PATH 0x40000 /* allow fid2path by unprivileged users */ #define LL_SBI_XATTR_CACHE 0x80000 /* support for xattr cache */ #define LL_SBI_NOROOTSQUASH 0x100000 /* do not apply root squash */ +#define LL_SBI_ALWAYS_PING 0x200000 /* always ping even if server + * suppress_pings */ +#define LL_SBI_FAST_READ 0x400000 /* fast read support */ +#define LL_SBI_FILE_SECCTX 0x800000 /* set file security context at create */ +/* LL_SBI_PIO 0x1000000 parallel IO support, introduced in + 2.10, abandoned */ +#define LL_SBI_TINY_WRITE 0x2000000 /* tiny write support */ #define LL_SBI_FLAGS { \ "nolck", \ @@ -425,7 +461,7 @@ enum stats_track_type { "user_xattr", \ "acl", \ "???", \ - "rmt_client", \ + "???", \ "mds_capa", \ "oss_capa", \ "flock", \ @@ -440,37 +476,13 @@ enum stats_track_type { "user_fid2path",\ "xattr_cache", \ "norootsquash", \ + "always_ping", \ + "fast_read", \ + "file_secctx", \ + "pio", \ + "tiny_write", \ } -#define RCE_HASHES 32 - -struct rmtacl_ctl_entry { - struct list_head rce_list; - pid_t rce_key; /* hash key */ - int rce_ops; /* acl operation type */ -}; - -struct rmtacl_ctl_table { - spinlock_t rct_lock; - struct list_head rct_entries[RCE_HASHES]; -}; - -#define EE_HASHES 32 - -struct eacl_entry { - struct list_head ee_list; - pid_t ee_key; /* hash key */ - struct lu_fid ee_fid; - int ee_type; /* ACL type for ACCESS or DEFAULT */ - ext_acl_xattr_header *ee_acl; -}; - -struct eacl_table { - spinlock_t et_lock; - struct list_head et_entries[EE_HASHES]; -}; - - /* This is embedded into llite super-blocks to keep track of connect * flags (capabilities) supported by all imports given mount is * connected to. */ @@ -485,30 +497,28 @@ struct lustre_client_ocd { }; struct ll_sb_info { - struct list_head ll_list; /* 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, - ll_client_common_fill_super_succeeded:1; + ll_xattr_cache_set:1, /* already set to 0/1 */ + ll_client_common_fill_super_succeeded:1, + ll_checksum_set:1; - /* per-conn chain of SBs */ - struct list_head ll_conn_chain; struct lustre_client_ocd ll_lco; - /*please don't ask -p*/ - struct list_head ll_orphan_dentry_list; - struct lprocfs_stats *ll_stats; /* lprocfs stats counter */ /* Used to track "unstable" pages on a client, and maintain a @@ -523,11 +533,6 @@ struct ll_sb_info { unsigned int ll_namelen; struct file_operations *ll_fop; - /* =0 - hold lock over whole read/write - * >0 - max. chunk to be read/written w/o lock re-acquiring */ - unsigned long ll_max_rw_chunk; - unsigned int ll_md_brw_pages; /* readdir pages per RPC */ - struct lu_site *ll_site; struct cl_device *ll_cl; /* Statistics */ @@ -542,6 +547,8 @@ 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 */ @@ -553,14 +560,16 @@ struct ll_sb_info { dev_t ll_sdev_orig; /* save s_dev before assign for * clustred nfs */ - struct rmtacl_ctl_table ll_rct; - struct eacl_table ll_et; - /* root squash */ struct root_squash_info ll_squash; -}; + struct path ll_mnt; -#define LL_DEFAULT_MAX_RW_CHUNK (32 * 1024 * 1024) + /* st_blksize returned by stat(2), when non-zero */ + unsigned int ll_stat_blksize; + + struct kset ll_kset; /* sysfs object */ + struct completion ll_kobj_unregister; +}; /* * per file-descriptor read-ahead data. @@ -600,6 +609,11 @@ struct ll_readahead_state { * PTLRPC_MAX_BRW_PAGES chunks up to ->ra_max_pages. */ unsigned long 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; /* * Where next read-ahead should start at. This lies within read-ahead * window. Read-ahead window is read in pieces rather than at once @@ -659,15 +673,19 @@ 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 lov_stripe_md; - -extern spinlock_t inode_lock; - -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) { @@ -682,34 +700,47 @@ static inline int ll_need_32bit_api(struct ll_sb_info *sbi) #if BITS_PER_LONG == 32 return 1; #elif defined(CONFIG_COMPAT) - return unlikely(is_compat_task() || (sbi->ll_flags & LL_SBI_32BIT_API)); + if (unlikely(sbi->ll_flags & LL_SBI_32BIT_API)) + return true; + +# ifdef CONFIG_X86_X32 + /* in_compat_syscall() returns true when called from a kthread + * and CONFIG_X86_X32 is enabled, which is wrong. So check + * whether the caller comes from a syscall (ie. not a kthread) + * before calling in_compat_syscall(). */ + if (current->flags & PF_KTHREAD) + return false; +# endif + + return unlikely(in_compat_syscall()); #else return unlikely(sbi->ll_flags & LL_SBI_32BIT_API); #endif } +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); +} + void ll_ras_enter(struct file *f); /* llite/lcommon_misc.c */ int cl_ocd_update(struct obd_device *host, struct obd_device *watched, - enum obd_notify_event ev, void *owner, void *data); + enum obd_notify_event ev, void *owner); int cl_get_grouplock(struct cl_object *obj, unsigned long gid, int nonblock, struct ll_grouplock *lg); void cl_put_grouplock(struct ll_grouplock *lg); /* llite/lproc_llite.c */ -#ifdef CONFIG_PROC_FS -int lprocfs_register_mountpoint(struct proc_dir_entry *parent, - struct super_block *sb, char *osc, char *mdc); -void lprocfs_unregister_mountpoint(struct ll_sb_info *sbi); +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); -extern struct lprocfs_vars lprocfs_llite_obd_vars[]; -#else -static inline int lprocfs_register_mountpoint(struct proc_dir_entry *parent, - struct super_block *sb, char *osc, char *mdc){return 0;} -static inline void lprocfs_unregister_mountpoint(struct ll_sb_info *sbi) {} -static void ll_stats_ops_tally(struct ll_sb_info *sbi, int op, int count) {} -#endif enum { LPROC_LL_DIRTY_HITS, @@ -718,12 +749,12 @@ enum { LPROC_LL_WRITE_BYTES, LPROC_LL_BRW_READ, LPROC_LL_BRW_WRITE, - LPROC_LL_OSC_READ, - LPROC_LL_OSC_WRITE, LPROC_LL_IOCTL, LPROC_LL_OPEN, LPROC_LL_RELEASE, LPROC_LL_MAP, + LPROC_LL_FAULT, + LPROC_LL_MKWRITE, LPROC_LL_LLSEEK, LPROC_LL_FSYNC, LPROC_LL_READDIR, @@ -793,17 +824,18 @@ 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); -struct ll_cl_context *ll_cl_find(struct file *file); -void ll_cl_add(struct file *file, const struct lu_env *env, struct cl_io *io); + +enum lcc_type; +void ll_cl_add(struct file *file, const struct lu_env *env, struct cl_io *io, + enum lcc_type type); void ll_cl_remove(struct file *file, const struct lu_env *env); +struct ll_cl_context *ll_cl_find(struct file *file); -#ifndef MS_HAS_NEW_AOPS extern const struct address_space_operations ll_aops; -#else -extern const struct address_space_operations_ext ll_aops; -#endif /* llite/file.c */ extern struct file_operations ll_file_operations; @@ -811,26 +843,37 @@ 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 int ll_have_md_lock(struct inode *inode, __u64 *bits, - ldlm_mode_t l_req_mode); -extern ldlm_mode_t ll_take_md_lock(struct inode *inode, __u64 bits, - struct lustre_handle *lockh, __u64 flags, - ldlm_mode_t mode); + enum ldlm_mode l_req_mode); +extern enum ldlm_mode ll_take_md_lock(struct inode *inode, __u64 bits, + struct lustre_handle *lockh, __u64 flags, + enum ldlm_mode mode); 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_pack_inode2opdata(struct inode *inode, struct md_op_data *op_data, - struct lustre_handle *fh); 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 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_FS_POSIX_ACL +int ll_set_acl(struct inode *inode, struct posix_acl *acl, int type); +#else /* !CONFIG_FS_POSIX_ACL */ +#define ll_set_acl NULL +#endif /* CONFIG_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); + 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 @@ -840,9 +883,14 @@ int ll_inode_permission(struct inode *inode, int mask, struct nameidata *nd); int ll_inode_permission(struct inode *inode, int mask); # endif #endif - -int ll_lov_setstripe_ea_info(struct inode *inode, struct file *file, - __u64 flags, struct lov_user_md *lum, +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, + unsigned long arg); + +int ll_lov_setstripe_ea_info(struct inode *inode, struct dentry *dentry, + __u64 flags, struct lov_user_md *lum, int lum_size); int ll_lov_getstripe_ea_info(struct inode *inode, const char *filename, struct lov_mds_md **lmm, int *lmm_size, @@ -863,6 +911,8 @@ 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 */ @@ -883,13 +933,16 @@ int ll_fill_super(struct super_block *sb, struct vfsmount *mnt); 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 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, @@ -905,14 +958,10 @@ int ll_show_options(struct seq_file *seq, struct vfsmount *vfs); 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 *); -void lustre_dump_dentry(struct dentry *, int recur); 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_get_max_cookiesize(struct ll_sb_info *sbi, int *max_cookiesize); -int ll_get_default_cookiesize(struct ll_sb_info *sbi, int *default_cookiesize); -int ll_process_config(struct lustre_cfg *lcfg); enum { LUSTRE_OPC_MKDIR = 0, @@ -922,6 +971,7 @@ enum { 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, @@ -934,6 +984,9 @@ 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) { @@ -948,6 +1001,8 @@ static inline ssize_t ll_lov_user_md_size(const struct lov_user_md *lum) return lov_user_md_size(lum->lmm_stripe_count, LOV_USER_MAGIC_SPECIFIC); + case LOV_USER_MAGIC_COMP_V1: + return ((struct lov_comp_md_v1 *)lum)->lcm_size; } return -EINVAL; @@ -973,8 +1028,7 @@ struct vvp_io_args { union { struct { struct kiocb *via_iocb; - struct iovec *via_iov; - unsigned long via_nrsegs; + struct iov_iter *via_iter; } normal; struct { struct pipe_inode_info *via_pipe; @@ -983,19 +1037,24 @@ struct vvp_io_args { } u; }; +enum lcc_type { + LCC_RW = 1, + LCC_MMAP +}; + struct ll_cl_context { struct list_head lcc_list; void *lcc_cookie; const struct lu_env *lcc_env; struct cl_io *lcc_io; struct cl_page *lcc_page; + enum lcc_type lcc_type; }; struct ll_thread_info { - struct iovec lti_local_iov; + 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; }; @@ -1025,15 +1084,15 @@ static inline struct vvp_io_args *ll_env_args(const struct lu_env *env, 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(ldlm_policy_data_t *policy, - struct vm_area_struct *vma, unsigned long addr, size_t count); +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_CACHE_SHIFT; + loff_t offset = vmpage->index << PAGE_SHIFT; LASSERT(PageLocked(vmpage)); if (mapping == NULL) @@ -1043,7 +1102,7 @@ static inline void ll_invalidate_page(struct page *vmpage) * truncate_complete_page() calls * a_ops->invalidatepage()->cl_page_delete()->vvp_page_delete(). */ - ll_teardown_mmaps(mapping, offset, offset + PAGE_CACHE_SIZE); + ll_teardown_mmaps(mapping, offset, offset + PAGE_SIZE); truncate_complete_page(mapping, vmpage); } @@ -1095,45 +1154,31 @@ static inline struct lu_fid *ll_inode2fid(struct inode *inode) return fid; } -static inline __u64 ll_file_maxbytes(struct inode *inode) +static inline loff_t ll_file_maxbytes(struct inode *inode) { - return ll_i2info(inode)->lli_maxbytes; -} + struct cl_object *obj = ll_i2info(inode)->lli_clob; -/* 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); -ssize_t ll_listxattr(struct dentry *dentry, char *buffer, size_t size); -int ll_removexattr(struct dentry *dentry, const char *name); - -/* llite/remote_perm.c */ -extern struct kmem_cache *ll_remote_perm_cachep; -extern struct kmem_cache *ll_rmtperm_hash_cachep; - -void free_rmtperm_hash(struct hlist_head *hash); -int ll_update_remote_perm(struct inode *inode, struct mdt_remote_perm *perm); -int lustre_check_remote_perm(struct inode *inode, int mask); + if (obj == NULL) + return MAX_LFS_FILESIZE; -/* llite/llite_capa.c */ -extern struct timer_list ll_capa_timer; - -int ll_capa_thread_start(void); -void ll_capa_thread_stop(void); -void ll_capa_timer_callback(unsigned long unused); - -struct obd_capa *ll_add_capa(struct inode *inode, struct obd_capa *ocapa); + return min_t(loff_t, cl_object_maxbytes(obj), MAX_LFS_FILESIZE); +} -void ll_capa_open(struct inode *inode); -void ll_capa_close(struct inode *inode); +/* llite/xattr.c */ +extern const struct xattr_handler *ll_xattr_handlers[]; -struct obd_capa *ll_mdscapa_get(struct inode *inode); -struct obd_capa *ll_osscapa_get(struct inode *inode, __u64 opc); +#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 -void ll_truncate_free_capa(struct obd_capa *ocapa); -void ll_clear_inode_capas(struct inode *inode); -void ll_print_capa_stat(struct ll_sb_info *sbi); +ssize_t ll_listxattr(struct dentry *dentry, char *buffer, size_t size); +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. @@ -1141,33 +1186,25 @@ void ll_print_capa_stat(struct ll_sb_info *sbi); int cl_sb_init(struct super_block *sb); int cl_sb_fini(struct super_block *sb); +enum ras_update_flags { + LL_RAS_HIT = 0x1, + LL_RAS_MMAP = 0x2 +}; void ll_ra_count_put(struct ll_sb_info *sbi, unsigned long len); void ll_ra_stats_inc(struct inode *inode, enum ra_stat which); -/* llite/llite_rmtacl.c */ -#ifdef CONFIG_FS_POSIX_ACL -u64 rce_ops2valid(int ops); -struct rmtacl_ctl_entry *rct_search(struct rmtacl_ctl_table *rct, pid_t key); -int rct_add(struct rmtacl_ctl_table *rct, pid_t key, int ops); -int rct_del(struct rmtacl_ctl_table *rct, pid_t key); -void rct_init(struct rmtacl_ctl_table *rct); -void rct_fini(struct rmtacl_ctl_table *rct); - -void ee_free(struct eacl_entry *ee); -int ee_add(struct eacl_table *et, pid_t key, struct lu_fid *fid, int type, - ext_acl_xattr_header *header); -struct eacl_entry *et_search_del(struct eacl_table *et, pid_t key, - struct lu_fid *fid, int type); -void et_search_free(struct eacl_table *et, pid_t key); -void et_init(struct eacl_table *et); -void et_fini(struct eacl_table *et); -#endif - /* statahead.c */ #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) @@ -1232,11 +1269,18 @@ 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); @@ -1244,7 +1288,7 @@ 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; } @@ -1294,86 +1338,13 @@ 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); - -struct obd_capa *cl_capa_lookup(struct inode *inode, enum cl_req_type crt); - 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; -}; - -static inline void cl_stats_tally(struct cl_device *dev, enum cl_req_type crt, - int rc) -{ - int opc = (crt == CRT_READ) ? LPROC_LL_OSC_READ : - LPROC_LL_OSC_WRITE; - - ll_stats_ops_tally(ll_s2sbi(cl2vvp_dev(dev)->vdv_sb), opc, rc); -} - -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); - struct inode *inode = file->f_dentry->d_inode; + struct inode *inode = file_inode((struct file *)file); LASSERT(fd != NULL); return ((fd->fd_flags & LL_FILE_IGNORE_LOCK) || @@ -1383,7 +1354,7 @@ static inline int ll_file_nolock(const struct file *file) static inline void ll_set_lock_data(struct obd_export *exp, struct inode *inode, struct lookup_intent *it, __u64 *bits) { - if (!it->d.lustre.it_lock_set) { + if (!it->it_lock_set) { struct lustre_handle handle; /* If this inode is a remote object, it will get two @@ -1393,28 +1364,27 @@ static inline void ll_set_lock_data(struct obd_export *exp, struct inode *inode, * UPDATE|PERM lock. The inode will be attched to both * LOOKUP and PERM locks, so revoking either locks will * case the dcache being cleared */ - if (it->d.lustre.it_remote_lock_mode) { - handle.cookie = it->d.lustre.it_remote_lock_handle; + if (it->it_remote_lock_mode) { + handle.cookie = it->it_remote_lock_handle; CDEBUG(D_DLMTRACE, "setting l_data to inode "DFID - "(%p) for remote lock "LPX64"\n", + "(%p) for remote lock %#llx\n", PFID(ll_inode2fid(inode)), inode, handle.cookie); - md_set_lock_data(exp, &handle.cookie, inode, NULL); + md_set_lock_data(exp, &handle, inode, NULL); } - handle.cookie = it->d.lustre.it_lock_handle; + handle.cookie = it->it_lock_handle; CDEBUG(D_DLMTRACE, "setting l_data to inode "DFID"(%p)" - " for lock "LPX64"\n", + " for lock %#llx\n", PFID(ll_inode2fid(inode)), inode, handle.cookie); - md_set_lock_data(exp, &handle.cookie, inode, - &it->d.lustre.it_lock_bits); - it->d.lustre.it_lock_set = 1; + md_set_lock_data(exp, &handle, inode, &it->it_lock_bits); + it->it_lock_set = 1; } if (bits != NULL) - *bits = it->d.lustre.it_lock_bits; + *bits = it->it_lock_bits; } static inline void ll_lock_dcache(struct inode *inode) @@ -1464,7 +1434,15 @@ static inline void d_lustre_invalidate(struct dentry *dentry, int nested) spin_lock_nested(&dentry->d_lock, nested ? DENTRY_D_LOCK_NESTED : DENTRY_D_LOCK_NORMAL); __d_lustre_invalidate(dentry); - if (ll_d_count(dentry) == 0) + /* + * 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); } @@ -1477,31 +1455,15 @@ static inline void d_lustre_revalidate(struct dentry *dentry) spin_unlock(&dentry->d_lock); } -#if LUSTRE_VERSION_CODE < OBD_OCD_VERSION(2, 7, 53, 0) -/* Compatibility for old (1.8) compiled userspace quota code */ -struct if_quotactl_18 { - __u32 qc_cmd; - __u32 qc_type; - __u32 qc_id; - __u32 qc_stat; - struct obd_dqinfo qc_dqinfo; - struct obd_dqblk qc_dqblk; - char obd_type[16]; - struct obd_uuid obd_uuid; -}; -#define LL_IOC_QUOTACTL_18 _IOWR('f', 162, struct if_quotactl_18 *) -/* End compatibility for old (1.8) compiled userspace quota code */ -#endif /* LUSTRE_VERSION_CODE < OBD_OCD_VERSION(2, 7, 53, 0) */ - 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, 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); @@ -1509,14 +1471,13 @@ 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, struct obd_capa *capa); + enum op_xvalid xvalid, unsigned int attr_flags); extern struct lu_env *cl_inode_fini_env; -extern int cl_inode_fini_refcheck; +extern __u16 cl_inode_fini_refcheck; int cl_file_inode_init(struct inode *inode, struct lustre_md *md); void cl_inode_fini(struct inode *inode); -int cl_local_size(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);