X-Git-Url: https://git.whamcloud.com/?a=blobdiff_plain;f=lustre%2Fllite%2Fllite_internal.h;h=96770adb76465f5698ebb84425726b12b2be799c;hb=a259082d66ba482aa4044abd1b41ac4219585473;hp=85ea3abfb0472f487190dbae820d2a8752ed9fca;hpb=f1b9122ce683c78f83fe05850728fea3662fe006;p=fs%2Flustre-release.git diff --git a/lustre/llite/llite_internal.h b/lustre/llite/llite_internal.h index 85ea3ab..96770ad 100644 --- a/lustre/llite/llite_internal.h +++ b/lustre/llite/llite_internal.h @@ -27,7 +27,7 @@ * Copyright (c) 2003, 2010, Oracle and/or its affiliates. All rights reserved. * Use is subject to license terms. * - * Copyright (c) 2011, 2013, Intel Corporation. + * Copyright (c) 2011, 2015, Intel Corporation. */ /* * This file is part of Lustre, http://www.lustre.org/ @@ -40,14 +40,18 @@ #include #include /* for s2sbi */ #include +#include /* for struct cl_lock_descr and struct cl_io */ #include -#include #include #include -#include +#include #include +#include + +#include "vvp_internal.h" +#include "range_lock.h" #ifndef FMODE_EXEC #define FMODE_EXEC 0 @@ -67,6 +71,9 @@ #define LL_DIR_END_OFF 0x7fffffffffffffffULL #define LL_DIR_END_OFF_32BIT 0x7fffffffUL +/* 4UL * 1024 * 1024 */ +#define LL_MAX_BLKSIZE_BITS 22 + #define LL_IT2STR(it) ((it) ? ldlm_it2str((it)->it_op) : "0") #define LUSTRE_FPRIVATE(file) ((file)->private_data) @@ -74,6 +81,7 @@ 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; }; @@ -82,9 +90,6 @@ 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; @@ -94,81 +99,42 @@ 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. */ -}; - -enum lli_flags { - /* MDS has an authority for the Size-on-MDS attributes. */ - LLIF_MDS_SIZE_LOCK = (1 << 0), - /* Epoch close is postponed. */ - LLIF_EPOCH_PENDING = (1 << 1), - /* DONE WRITING is allowed. */ - LLIF_DONE_WRITING = (1 << 2), - /* Sizeon-on-MDS attributes are changed. An attribute update needs to - * be sent to MDS. */ - LLIF_SOM_DIRTY = (1 << 3), - /* File data is modified. */ - LLIF_DATA_MODIFIED = (1 << 4), - /* File is being restored */ - LLIF_FILE_RESTORING = (1 << 5), - /* Xattr cache is attached to the file */ - LLIF_XATTR_CACHE = (1 << 6), +struct ll_grouplock { + struct lu_env *lg_env; + struct cl_io *lg_io; + struct cl_lock *lg_lock; + unsigned long lg_gid; }; struct ll_inode_info { __u32 lli_inode_magic; - __u32 lli_flags; - __u64 lli_ioepoch; - spinlock_t lli_lock; + + volatile unsigned long lli_flags; struct posix_acl *lli_posix_acl; - struct hlist_head *lli_remote_perms; - struct mutex lli_rmtperm_mutex; - - /* identifying fields for both metadata and data stacks. */ - struct lu_fid lli_fid; - /* Parent fid for accessing default stripe data on parent directory - * for allocating OST objects after a mknod() and later open-by-FID. */ - struct lu_fid lli_pfid; - - struct list_head lli_close_list; - 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; - - /* handle is to be sent to MDS later on done_writing and setattr. - * Open handle data are needed for the recovery to reconstruct - * the inode state on the MDS. XXX: recovery is not ready yet. */ - struct obd_client_handle *lli_pending_och; - - /* We need all three because every inode may be opened in different - * modes */ - struct obd_client_handle *lli_mds_read_och; - struct obd_client_handle *lli_mds_write_och; - struct obd_client_handle *lli_mds_exec_och; - __u64 lli_open_fd_read_count; - __u64 lli_open_fd_write_count; - __u64 lli_open_fd_exec_count; - /* Protects access to och pointers and their usage counters */ + /* identifying fields for both metadata and data stacks. */ + struct lu_fid lli_fid; + /* master inode fid for stripe directory */ + struct lu_fid lli_pfid; + + /* We need all three because every inode may be opened in different + * modes */ + struct obd_client_handle *lli_mds_read_och; + struct obd_client_handle *lli_mds_write_och; + struct obd_client_handle *lli_mds_exec_och; + __u64 lli_open_fd_read_count; + __u64 lli_open_fd_write_count; + __u64 lli_open_fd_exec_count; + /* Protects access to och pointers and their usage counters */ struct mutex lli_och_mutex; struct inode lli_vfs_inode; /* the most recent timestamps obtained from mds */ - struct ost_lvb lli_lvb; + s64 lli_atime; + s64 lli_mtime; + s64 lli_ctime; spinlock_t lli_agl_lock; /* Try to make the d::member and f::member are aligned. Before using @@ -177,42 +143,42 @@ struct ll_inode_info { /* for directory */ struct { /* serialize normal readdir and statahead-readdir. */ - struct mutex d_readdir_mutex; - - /* metadata statahead */ - /* since parent-child threads can share the same @file - * struct, "opendir_key" is the token when dir close for - * case of parent exit before child -- it is me should - * cleanup the dir readahead. */ - void *d_opendir_key; - struct ll_statahead_info *d_sai; - /* protect statahead stuff. */ - spinlock_t d_sa_lock; + 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 + * case of parent exit before child -- it is me should + * cleanup the dir readahead. */ + void *lli_opendir_key; + struct ll_statahead_info *lli_sai; + /* protect statahead stuff. */ + spinlock_t lli_sa_lock; /* "opendir_pid" is the token when lookup/revalid * -- I am the owner of dir statahead. */ - pid_t d_opendir_pid; + pid_t lli_opendir_pid; + /* stat will try to access statahead entries or start + * statahead if this flag is set, and this flag will be + * set upon dir open, and cleared when dir is closed, + * statahead hit ratio is too low, or start statahead + * thread failed. */ + unsigned int lli_sa_enabled:1; + /* generation for statahead */ + unsigned int lli_sa_generation; /* directory stripe information */ - struct lmv_stripe_md *d_lsm_md; - /* striped directory size */ - loff_t d_stripe_size; - /* striped directory nlink */ - __u64 d_stripe_nlink; - } d; - -#define lli_readdir_mutex u.d.d_readdir_mutex -#define lli_opendir_key u.d.d_opendir_key -#define lli_sai u.d.d_sai -#define lli_sa_lock u.d.d_sa_lock -#define lli_opendir_pid u.d.d_opendir_pid -#define lli_lsm_md u.d.d_lsm_md -#define lli_stripe_dir_size u.d.d_stripe_size -#define lli_stripe_dir_nlink u.d.d_stripe_nlink + 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; + }; /* for non-directory */ struct { - struct mutex f_size_mutex; - char *f_symlink_name; - __u64 f_maxbytes; + struct mutex lli_size_mutex; + char *lli_symlink_name; /* * struct rw_semaphore { * signed long count; // align d.d_def_acl @@ -220,16 +186,16 @@ struct ll_inode_info { * struct list_head wait_list; * } */ - struct rw_semaphore f_trunc_sem; - struct mutex f_write_mutex; + struct rw_semaphore lli_trunc_sem; + struct range_lock_tree lli_write_tree; - struct rw_semaphore f_glimpse_sem; - cfs_time_t f_glimpse_time; - struct list_head f_agl_list; - __u64 f_agl_index; + struct rw_semaphore lli_glimpse_sem; + cfs_time_t lli_glimpse_time; + struct list_head lli_agl_list; + __u64 lli_agl_index; /* for writepage() only to communicate to fsync */ - int f_async_rc; + int lli_async_rc; /* * whenever a process try to read/write the file, the @@ -239,22 +205,9 @@ struct ll_inode_info { * so the read/write statistics for jobid will not be * accurate if the file is shared by different jobs. */ - char f_jobid[JOBSTATS_JOBID_SIZE]; - } f; - -#define lli_size_mutex u.f.f_size_mutex -#define lli_symlink_name u.f.f_symlink_name -#define lli_maxbytes u.f.f_maxbytes -#define lli_trunc_sem u.f.f_trunc_sem -#define lli_write_mutex u.f.f_write_mutex -#define lli_glimpse_sem u.f.f_glimpse_sem -#define lli_glimpse_time u.f.f_glimpse_time -#define lli_agl_list u.f.f_agl_list -#define lli_agl_index u.f.f_agl_index -#define lli_async_rc u.f.f_async_rc -#define lli_jobid u.f.f_jobid - - } u; + char lli_jobid[LUSTRE_JOBID_SIZE]; + }; + }; /* XXX: For following frequent used members, although they maybe special * used for non-directory object, it is some time-wasting to check @@ -266,8 +219,7 @@ 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; + struct cl_object *lli_clob; /* mutex to request for layout lock exclusively. */ struct mutex lli_layout_mutex; @@ -298,6 +250,39 @@ 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, +}; + +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, @@ -306,6 +291,12 @@ int ll_xattr_cache_get(struct inode *inode, size_t size, __u64 valid); +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. @@ -323,12 +314,11 @@ 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, @@ -360,17 +350,20 @@ 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 */ @@ -415,13 +408,13 @@ 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 */ -#define LL_SBI_SOM_PREVIEW 0x1000 /* SOM preview mount option */ +/* LL_SBI_SOM_PREVIEW 0x1000 SOM preview mount option, obsolete */ #define LL_SBI_32BIT_API 0x2000 /* generate 32 bit inodes. */ #define LL_SBI_64BIT_HASH 0x4000 /* support 64-bits dir hash/offset */ #define LL_SBI_AGL_ENABLED 0x8000 /* enable agl */ @@ -430,15 +423,19 @@ 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 */ #define LL_SBI_FLAGS { \ "nolck", \ "checksum", \ "flock", \ - "xattr", \ + "user_xattr", \ "acl", \ "???", \ - "rmt_client", \ + "???", \ "mds_capa", \ "oss_capa", \ "flock", \ @@ -451,40 +448,27 @@ enum stats_track_type { "verbose", \ "layout", \ "user_fid2path",\ - "xattr", \ + "xattr_cache", \ "norootsquash", \ + "always_ping", \ + "fast_read", \ + "file_secctx", \ } -#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. */ +struct lustre_client_ocd { + /* This is conjunction of connect_flags across all imports + * (LOVs) this mount is connected to. This field is updated by + * cl_ocd_update() under ->lco_lock. */ + __u64 lco_flags; + struct mutex lco_lock; + struct obd_export *lco_md_exp; + struct obd_export *lco_dt_exp; }; 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; @@ -498,14 +482,10 @@ struct ll_sb_info { int ll_flags; unsigned int ll_umounting:1, - ll_xattr_cache_enabled:1; - /* per-conn chain of SBs */ - struct list_head ll_conn_chain; - struct lustre_client_ocd ll_lco; + ll_xattr_cache_enabled:1, + ll_client_common_fill_super_succeeded:1; - /*please don't ask -p*/ - struct list_head ll_orphan_dentry_list; - struct ll_close_queue *ll_lcq; + struct lustre_client_ocd ll_lco; struct lprocfs_stats *ll_stats; /* lprocfs stats counter */ @@ -513,7 +493,7 @@ struct ll_sb_info { * LRU list of clean pages. An "unstable" page is defined as * any page which is sent to a server as part of a bulk request, * but is uncommitted to stable storage. */ - struct cl_client_cache ll_cache; + struct cl_client_cache *ll_cache; struct lprocfs_stats *ll_ra_stats; @@ -521,9 +501,6 @@ 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; @@ -540,29 +517,19 @@ struct ll_sb_info { int ll_rw_stats_on; /* metadata stat-ahead */ - unsigned int ll_sa_max; /* max statahead RPCs */ - atomic_t ll_sa_total; /* statahead thread started + unsigned int ll_sa_max; /* max statahead RPCs */ + atomic_t ll_sa_total; /* statahead thread started * count */ - atomic_t ll_sa_wrong; /* statahead thread stopped for + atomic_t ll_sa_wrong; /* statahead thread stopped for * low hit ratio */ - atomic_t ll_agl_total; /* AGL thread started count */ + atomic_t ll_sa_running; /* running statahead thread + * count */ + atomic_t ll_agl_total; /* AGL thread started count */ - dev_t ll_sdev_orig; /* save s_dev before assign for + 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; -}; - -#define LL_DEFAULT_MAX_RW_CHUNK (32 * 1024 * 1024) - -struct ll_ra_read { - pgoff_t lrr_start; - pgoff_t lrr_count; - struct task_struct *lrr_reader; - struct list_head lrr_linkage; + struct root_squash_info ll_squash; }; /* @@ -603,6 +570,11 @@ 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 @@ -623,12 +595,6 @@ struct ll_readahead_state { */ unsigned long ras_request_index; /* - * list of struct ll_ra_read's one per read(2) call current in - * progress against this file descriptor. Used by read-ahead code, - * protected by ->ras_lock. - */ - struct list_head ras_read_beads; - /* * The following 3 items are used for detecting the stride I/O * mode. * In stride I/O mode, @@ -655,7 +621,7 @@ extern struct kmem_cache *ll_file_data_slab; struct lustre_handle; struct ll_file_data { struct ll_readahead_state fd_ras; - struct ccc_grouplock fd_grouplock; + struct ll_grouplock fd_grouplock; __u64 lfd_pos; __u32 fd_flags; fmode_t fd_omode; @@ -672,10 +638,6 @@ struct ll_file_data { struct list_head fd_lccs; /* list of ll_cl_context */ }; -struct lov_stripe_md; - -extern spinlock_t inode_lock; - extern struct proc_dir_entry *proc_lustre_fs_root; static inline struct inode *ll_info2i(struct ll_inode_info *lli) @@ -691,23 +653,33 @@ 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)); + return unlikely(in_compat_syscall() || (sbi->ll_flags & LL_SBI_32BIT_API)); #else return unlikely(sbi->ll_flags & LL_SBI_32BIT_API); #endif } -void ll_ra_read_in(struct file *f, struct ll_ra_read *rar); -void ll_ra_read_ex(struct file *f, struct ll_ra_read *rar); -struct ll_ra_read *ll_ra_read_get(struct file *f); +static inline bool ll_sbi_has_fast_read(struct ll_sb_info *sbi) +{ + return !!(sbi->ll_flags & LL_SBI_FAST_READ); +} + +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); +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 LPROCFS +#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); void ll_stats_ops_tally(struct ll_sb_info *sbi, int op, int count); -extern struct lprocfs_seq_vars lprocfs_llite_obd_vars[]; +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;} @@ -715,33 +687,75 @@ 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, + LPROC_LL_DIRTY_MISSES, + LPROC_LL_READ_BYTES, + LPROC_LL_WRITE_BYTES, + LPROC_LL_BRW_READ, + LPROC_LL_BRW_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, + LPROC_LL_SETATTR, + LPROC_LL_TRUNC, + LPROC_LL_FLOCK, + LPROC_LL_GETATTR, + LPROC_LL_CREATE, + LPROC_LL_LINK, + LPROC_LL_UNLINK, + LPROC_LL_SYMLINK, + LPROC_LL_MKDIR, + LPROC_LL_RMDIR, + LPROC_LL_MKNOD, + LPROC_LL_RENAME, + LPROC_LL_STAFS, + LPROC_LL_ALLOC_INODE, + LPROC_LL_SETXATTR, + LPROC_LL_GETXATTR, + LPROC_LL_GETXATTR_HITS, + LPROC_LL_LISTXATTR, + LPROC_LL_REMOVEXATTR, + LPROC_LL_INODE_PERM, + LPROC_LL_FILE_OPCODES +}; /* llite/dir.c */ +struct ll_dir_chain { +}; + +static inline void ll_dir_chain_init(struct ll_dir_chain *chain) +{ +} + +static inline void ll_dir_chain_fini(struct ll_dir_chain *chain) +{ +} + extern const struct file_operations ll_dir_operations; extern const struct inode_operations ll_dir_inode_operations; #ifdef HAVE_DIR_CONTEXT -int ll_dir_read(struct inode *inode, struct md_op_data *op_data, +int ll_dir_read(struct inode *inode, __u64 *pos, struct md_op_data *op_data, struct dir_context *ctx); #else -int ll_dir_read(struct inode *inode, struct md_op_data *op_data, +int ll_dir_read(struct inode *inode, __u64 *pos, struct md_op_data *op_data, void *cookie, filldir_t filldir); #endif 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); +void ll_release_page(struct inode *inode, struct page *page, bool remove); -struct lu_dirent *ll_dir_entry_start(struct inode *dir, - struct md_op_data *op_data, - struct page **ppage); - -struct lu_dirent *ll_dir_entry_next(struct inode *dir, - struct md_op_data *op_data, - struct lu_dirent *ent, - struct page **ppage); /* llite/namei.c */ extern const struct inode_operations ll_special_inode_operations; -int ll_objects_destroy(struct ptlrpc_request *request, - struct inode *dir); struct inode *ll_iget(struct super_block *sb, ino_t hash, struct lustre_md *lic); int ll_test_inode_by_fid(struct inode *inode, void *opaque); @@ -756,19 +770,15 @@ 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); void ll_readahead_init(struct inode *inode, struct ll_readahead_state *ras); -int ll_readahead(const struct lu_env *env, struct cl_io *io, - struct cl_page_list *queue, struct ll_readahead_state *ras, - bool hit); 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; @@ -776,26 +786,15 @@ 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_glimpse_ioctl(struct ll_sb_info *sbi, - struct lov_stripe_md *lsm, lstat_t *st); -void ll_ioepoch_open(struct ll_inode_info *lli, __u64 ioepoch); int ll_release_openhandle(struct dentry *, struct lookup_intent *); int ll_md_real_close(struct inode *inode, fmode_t fmode); -void ll_ioepoch_close(struct inode *inode, struct md_op_data *op_data, - struct obd_client_handle **och, unsigned long flags); -void ll_done_writing_attr(struct inode *inode, struct md_op_data *op_data); -int ll_som_update(struct inode *inode, struct md_op_data *op_data); -int ll_inode_getattr(struct inode *inode, struct obdo *obdo, - __u64 ioepoch, int sync); -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); @@ -804,7 +803,7 @@ 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); 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 @@ -825,7 +824,7 @@ 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, - obd_valid valid); + 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) @@ -833,10 +832,11 @@ int ll_fsync(struct file *file, int data); #else int ll_fsync(struct file *file, struct dentry *dentry, int data); #endif -int ll_merge_lvb(const struct lu_env *env, struct inode *inode); -int ll_fid2path(struct inode *inode, void *arg); +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); /* llite/dcache.c */ @@ -857,6 +857,7 @@ 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(struct dentry *de, struct iattr *attr); @@ -880,20 +881,50 @@ 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 *arg); +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_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_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, +}; + struct md_op_data *ll_prep_md_op_data(struct md_op_data *op_data, - struct inode *i1, struct inode *i2, - const char *name, int namelen, - int mode, __u32 opc, void *data); + struct inode *i1, struct inode *i2, + const char *name, size_t namelen, + __u32 mode, __u32 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); + +/* 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) +{ + switch (lum->lmm_magic) { + case LOV_USER_MAGIC_V1: + return sizeof(struct lov_user_md_v1); + case LOV_USER_MAGIC_V3: + return sizeof(struct lov_user_md_v3); + case LOV_USER_MAGIC_SPECIFIC: + if (lum->lmm_stripe_count > LOV_MAX_STRIPE_COUNT) + return -EINVAL; + + return lov_user_md_size(lum->lmm_stripe_count, + LOV_USER_MAGIC_SPECIFIC); + } + + return -EINVAL; +} /* llite/llite_nfs.c */ extern struct export_operations lustre_export_operations; @@ -905,72 +936,6 @@ 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; -/* llite/llite_close.c */ -struct ll_close_queue { - spinlock_t lcq_lock; - struct list_head lcq_head; - wait_queue_head_t lcq_waitq; - struct completion lcq_comp; - atomic_t lcq_stop; -}; - -struct ccc_object *cl_inode2ccc(struct inode *inode); - - -void vvp_write_pending (struct ccc_object *club, struct ccc_page *page); -void vvp_write_complete(struct ccc_object *club, struct ccc_page *page); - -/* specific achitecture can implement only part of this list */ -enum vvp_io_subtype { - /** normal IO */ - IO_NORMAL, - /** io started from splice_{read|write} */ - IO_SPLICE -}; - -/* IO subtypes */ -struct vvp_io { - /** io subtype */ - enum vvp_io_subtype cui_io_subtype; - - union { - struct { - struct pipe_inode_info *cui_pipe; - unsigned int cui_flags; - } splice; - struct vvp_fault_io { - /** - * Inode modification time that is checked across DLM - * lock request. - */ - time_t ft_mtime; - struct vm_area_struct *ft_vma; - /** - * locked page returned from vvp_io - */ - struct page *ft_vmpage; - struct vm_fault_api { - /** - * kernel fault info - */ - struct vm_fault *ft_vmf; - /** - * fault API used bitflags for return code. - */ - unsigned int ft_flags; - } fault; - } fault; - } u; - /** - * Read-ahead state used by read and page-fault IO contexts. - */ - struct ll_ra_read cui_bead; - /** - * Set when cui_bead has been initialized. - */ - int cui_ra_window_set; -}; - /** * IO arguments for various VFS I/O interfaces. */ @@ -981,8 +946,7 @@ 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; @@ -991,81 +955,63 @@ 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 vvp_thread_info { - struct iovec vti_local_iov; - struct vvp_io_args vti_args; - struct ra_io_arg vti_ria; - struct kiocb vti_kiocb; - struct ll_cl_context vti_io_ctx; +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; }; -static inline struct vvp_thread_info *vvp_env_info(const struct lu_env *env) -{ - extern struct lu_context_key vvp_key; - struct vvp_thread_info *info; +extern struct lu_context_key ll_thread_key; - info = lu_context_key_get(&env->le_ctx, &vvp_key); - LASSERT(info != NULL); - return info; -} - -static inline struct vvp_io_args *vvp_env_args(const struct lu_env *env, - enum vvp_io_subtype type) +static inline struct ll_thread_info *ll_env_info(const struct lu_env *env) { - struct vvp_io_args *ret = &vvp_env_info(env)->vti_args; + struct ll_thread_info *lti; - ret->via_io_subtype = type; + lti = lu_context_key_get(&env->le_ctx, &ll_thread_key); + LASSERT(lti != NULL); - return ret; + return lti; } -struct vvp_session { - struct vvp_io vs_ios; -}; - -static inline struct vvp_session *vvp_env_session(const struct lu_env *env) +static inline struct vvp_io_args *ll_env_args(const struct lu_env *env, + enum vvp_io_subtype type) { - extern struct lu_context_key vvp_session_key; - struct vvp_session *ses; + struct vvp_io_args *via = &ll_env_info(env)->lti_args; - ses = lu_context_key_get(env->le_ses, &vvp_session_key); - LASSERT(ses != NULL); - return ses; -} + via->via_io_subtype = type; -static inline struct vvp_io *vvp_env_io(const struct lu_env *env) -{ - return &vvp_env_session(env)->vs_ios; + return via; } -int vvp_global_init(void); -void vvp_global_fini(void); - -void ll_queue_done_writing(struct inode *inode, unsigned long flags); -void ll_close_thread_shutdown(struct ll_close_queue *lcq); -int ll_close_thread_start(struct ll_close_queue **lcq_ret); - /* 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(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) @@ -1075,7 +1021,7 @@ 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); } @@ -1127,9 +1073,14 @@ 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; + + if (obj == NULL) + return MAX_LFS_FILESIZE; + + return min_t(loff_t, cl_object_maxbytes(obj), MAX_LFS_FILESIZE); } /* llite/xattr.c */ @@ -1140,67 +1091,19 @@ ssize_t ll_getxattr(struct dentry *dentry, const char *name, 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); - -/* 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); - -void ll_capa_open(struct inode *inode); -void ll_capa_close(struct inode *inode); - -struct obd_capa *ll_mdscapa_get(struct inode *inode); -struct obd_capa *ll_osscapa_get(struct inode *inode, __u64 opc); - -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); - -/* llite/llite_cl.c */ -extern struct lu_device_type vvp_device_type; - /** * Common IO arguments for various VFS I/O interfaces. */ int cl_sb_init(struct super_block *sb); int cl_sb_fini(struct super_block *sb); -void ras_update(struct ll_sb_info *sbi, struct inode *inode, - struct ll_readahead_state *ras, unsigned long index, - unsigned hit); +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 -obd_valid 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 @@ -1213,48 +1116,67 @@ void et_fini(struct eacl_table *et); /* per inode struct, for dir only */ struct ll_statahead_info { - struct inode *sai_inode; - atomic_t sai_refcount; /* when access this struct, hold + struct dentry *sai_dentry; + atomic_t sai_refcount; /* when access this struct, hold * refcount */ - unsigned int sai_generation; /* generation for statahead */ - unsigned int sai_max; /* max ahead of lookup */ - __u64 sai_sent; /* stat requests sent count */ - __u64 sai_replied; /* stat requests which received + unsigned int sai_max; /* max ahead of lookup */ + __u64 sai_sent; /* stat requests sent count */ + __u64 sai_replied; /* stat requests which received * reply */ - __u64 sai_index; /* index of statahead entry */ - __u64 sai_index_wait; /* index of entry which is the + __u64 sai_index; /* index of statahead entry */ + __u64 sai_index_wait; /* index of entry which is the * caller is waiting for */ - __u64 sai_hit; /* hit count */ - __u64 sai_miss; /* miss count: - * for "ls -al" case, it - * includes hidden dentry miss; + __u64 sai_hit; /* hit count */ + __u64 sai_miss; /* miss count: + * for "ls -al" case, includes + * hidden dentry miss; * for "ls -l" case, it does not * include hidden dentry miss. * "sai_miss_hidden" is used for * the later case. */ - unsigned int sai_consecutive_miss; /* consecutive miss */ - unsigned int sai_miss_hidden;/* "ls -al", but first dentry - * is not a hidden one */ - unsigned int sai_skip_hidden;/* skipped hidden dentry count */ - unsigned int sai_ls_all:1, /* "ls -al", do stat-ahead for + unsigned int sai_consecutive_miss; /* consecutive miss */ + unsigned int sai_miss_hidden;/* "ls -al", but first dentry + * is not a hidden one */ + unsigned int sai_skip_hidden;/* skipped hidden dentry count + */ + 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_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 list_head sai_entries; /* entry list */ - struct list_head sai_entries_received; /* entries returned */ - struct list_head sai_entries_stated; /* entries stated */ - struct list_head sai_entries_agl; /* AGL entries to be sent */ + struct list_head sai_interim_entries; /* entries which got async + * stat reply, but not + * instantiated */ + struct list_head sai_entries; /* completed entries */ + struct list_head sai_agls; /* AGLs to be sent */ struct list_head sai_cache[LL_SA_CACHE_SIZE]; spinlock_t sai_cache_lock[LL_SA_CACHE_SIZE]; atomic_t sai_cache_count; /* entry count in cache */ }; -int do_statahead_enter(struct inode *dir, struct dentry **dentry, - int only_unplug); -void ll_stop_statahead(struct inode *dir, void *key); +int ll_statahead(struct inode *dir, struct dentry **dentry, bool unplug); +void ll_authorize_statahead(struct inode *dir, void *key); +void ll_deauthorize_statahead(struct inode *dir, void *key); + +/* glimpse.c */ +blkcnt_t dirty_cnt(struct inode *inode); + +int cl_glimpse_size0(struct inode *inode, int agl); +int cl_glimpse_lock(const struct lu_env *env, struct cl_io *io, + struct inode *inode, struct cl_object *clob, int agl); + +static inline int cl_glimpse_size(struct inode *inode) +{ + return cl_glimpse_size0(inode, 0); +} + +static inline int cl_agl(struct inode *inode) +{ + return cl_glimpse_size0(inode, 1); +} static inline int ll_glimpse_size(struct inode *inode) { @@ -1268,77 +1190,52 @@ static inline int ll_glimpse_size(struct inode *inode) return rc; } -static inline void -ll_statahead_mark(struct inode *dir, struct dentry *dentry) -{ - struct ll_inode_info *lli = ll_i2info(dir); - struct ll_statahead_info *sai = lli->lli_sai; - struct ll_dentry_data *ldd = ll_d2d(dentry); - - /* not the same process, don't mark */ - if (lli->lli_opendir_pid != current_pid()) - return; - - LASSERT(ldd != NULL); - if (sai != NULL) - ldd->lld_sa_generation = sai->sai_generation; -} - -static inline int -d_need_statahead(struct inode *dir, struct dentry *dentryp) +/* dentry may statahead when statahead is enabled and current process has opened + * parent directory, and this dentry hasn't accessed statahead cache before */ +static inline bool +dentry_may_statahead(struct inode *dir, struct dentry *dentry) { struct ll_inode_info *lli; struct ll_dentry_data *ldd; if (ll_i2sbi(dir)->ll_sa_max == 0) - return -EAGAIN; + return false; lli = ll_i2info(dir); + + /* statahead is not allowed for this dir, there may be three causes: + * 1. dir is not opened. + * 2. statahead hit ratio is too low. + * 3. previous stat started statahead thread failed. */ + if (!lli->lli_sa_enabled) + return false; + /* not the same process, don't statahead */ if (lli->lli_opendir_pid != current_pid()) - return -EAGAIN; - - /* statahead has been stopped */ - if (lli->lli_opendir_key == NULL) - return -EAGAIN; + return false; - ldd = ll_d2d(dentryp); /* - * When stats a dentry, the system trigger more than once "revalidate" - * or "lookup", for "getattr", for "getxattr", and maybe for others. - * Under patchless client mode, the operation intent is not accurate, - * which maybe misguide the statahead thread. For example: - * The "revalidate" call for "getattr" and "getxattr" of a dentry maybe - * have the same operation intent -- "IT_GETATTR". - * In fact, one dentry should has only one chance to interact with the - * statahead thread, otherwise the statahead windows will be confused. + * When stating a dentry, kernel may trigger 'revalidate' or 'lookup' + * multiple times, eg. for 'getattr', 'getxattr' and etc. + * For patchless client, lookup intent is not accurate, which may + * misguide statahead. For example: + * The 'revalidate' call for 'getattr' and 'getxattr' of a dentry will + * have the same intent -- IT_GETATTR, while one dentry should access + * statahead cache once, otherwise statahead windows is messed up. * The solution is as following: - * Assign "lld_sa_generation" with "sai_generation" when a dentry - * "IT_GETATTR" for the first time, and the subsequent "IT_GETATTR" - * will bypass interacting with statahead thread for checking: - * "lld_sa_generation == lli_sai->sai_generation" + * Assign 'lld_sa_generation' with 'lli_sa_generation' when a dentry + * IT_GETATTR for the first time, and subsequent IT_GETATTR will + * bypass interacting with statahead cache by checking + * 'lld_sa_generation == lli->lli_sa_generation'. */ - if (ldd && lli->lli_sai && - ldd->lld_sa_generation == lli->lli_sai->sai_generation) - return -EAGAIN; - - return 1; -} + ldd = ll_d2d(dentry); + if (ldd != NULL && ldd->lld_sa_generation == lli->lli_sa_generation) + return false; -static inline int -ll_statahead_enter(struct inode *dir, struct dentry **dentryp, int only_unplug) -{ - int ret; - - ret = d_need_statahead(dir, *dentryp); - if (ret <= 0) - return ret; - - return do_statahead_enter(dir, dentryp, only_unplug); + return true; } /* llite ioctl register support rountine */ -#ifdef __KERNEL__ enum llioc_iter { LLIOC_CONT = 0, LLIOC_STOP @@ -1379,57 +1276,6 @@ typedef enum llioc_iter (*llioc_callback_t)(struct inode *inode, void *ll_iocontrol_register(llioc_callback_t cb, int count, unsigned int *cmd); void ll_iocontrol_unregister(void *magic); -#endif - -/* lclient compat stuff */ -#define cl_inode_info ll_inode_info -#define cl_i2info(info) ll_i2info(info) -#define cl_inode_mode(inode) ((inode)->i_mode) -#define cl_i2sbi ll_i2sbi - -static inline struct ll_file_data *cl_iattr2fd(struct inode *inode, - const struct iattr *attr) -{ - LASSERT(attr->ia_valid & ATTR_FILE); - return LUSTRE_FPRIVATE(attr->ia_file); -} - -static inline void cl_isize_lock(struct inode *inode) -{ - ll_inode_size_lock(inode); -} - -static inline void cl_isize_unlock(struct inode *inode) -{ - ll_inode_size_unlock(inode); -} - -static inline void cl_isize_write_nolock(struct inode *inode, loff_t kms) -{ - LASSERT(mutex_is_locked(&ll_i2info(inode)->lli_size_mutex)); - i_size_write(inode, kms); -} - -static inline void cl_isize_write(struct inode *inode, loff_t kms) -{ - ll_inode_size_lock(inode); - i_size_write(inode, kms); - ll_inode_size_unlock(inode); -} - -#define cl_isize_read(inode) i_size_read(inode) - -static inline int cl_merge_lvb(const struct lu_env *env, struct inode *inode) -{ - return ll_merge_lvb(env, inode); -} - -#define cl_inode_atime(inode) LTIME_S((inode)->i_atime) -#define cl_inode_ctime(inode) LTIME_S((inode)->i_ctime) -#define cl_inode_mtime(inode) LTIME_S((inode)->i_mtime) - -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); @@ -1450,15 +1296,6 @@ struct ll_dio_pages { 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(cl2ccc_dev(dev)->cdv_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); @@ -1466,7 +1303,7 @@ extern ssize_t ll_direct_rw_pages(const struct lu_env *env, struct cl_io *io, 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) || @@ -1476,7 +1313,7 @@ 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 @@ -1486,28 +1323,27 @@ 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) @@ -1552,12 +1388,20 @@ static inline void d_lustre_invalidate(struct dentry *dentry, int nested) { CDEBUG(D_DENTRY, "invalidate dentry %.*s (%p) parent %p inode %p " "refc %d\n", dentry->d_name.len, dentry->d_name.name, dentry, - dentry->d_parent, dentry->d_inode, d_count(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); __d_lustre_invalidate(dentry); - if (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); } @@ -1570,29 +1414,6 @@ static inline void d_lustre_revalidate(struct dentry *dentry) spin_unlock(&dentry->d_lock); } -#if LUSTRE_VERSION_CODE < OBD_OCD_VERSION(2, 7, 50, 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 */ -#else -#warning "remove old LL_IOC_QUOTACTL_18 compatibility code" -#endif /* LUSTRE_VERSION_CODE < OBD_OCD_VERSION(2, 7, 50, 0) */ - -enum { - LL_LAYOUT_GEN_NONE = ((__u32)-2), /* layout lock was cancelled */ - LL_LAYOUT_GEN_EMPTY = ((__u32)-1) /* for empty layout */ -}; - 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); @@ -1600,7 +1421,117 @@ int ll_layout_restore(struct inode *inode, loff_t start, __u64 length); 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); +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); + +extern struct lu_env *cl_inode_fini_env; +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); + +u64 cl_fid_build_ino(const struct lu_fid *fid, int api32); +u32 cl_fid_build_gen(const struct lu_fid *fid); + +#ifndef HAVE_IOV_ITER_TRUNCATE +static inline void iov_iter_truncate(struct iov_iter *i, u64 count) +{ + if (i->count > count) + i->count = count; +} +#endif + +#ifndef HAVE_IS_SXID +static inline bool is_sxid(umode_t mode) +{ + return (mode & S_ISUID) || ((mode & S_ISGID) && (mode & S_IXGRP)); +} +#endif + +#ifndef IS_NOSEC +#define IS_NOSEC(inode) (!is_sxid(inode->i_mode)) +#endif + +#ifndef HAVE_FILE_OPERATIONS_READ_WRITE_ITER +static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) +{ + i->count = count; +} + +static inline struct iovec iov_iter_iovec(const struct iov_iter *iter) +{ + return (struct iovec) { + .iov_base = iter->iov->iov_base + iter->iov_offset, + .iov_len = min(iter->count, + iter->iov->iov_len - iter->iov_offset), + }; +} + +#define iov_for_each(iov, iter, start) \ + for (iter = (start); \ + (iter).count && ((iov = iov_iter_iovec(&(iter))), 1); \ + iov_iter_advance(&(iter), (iov).iov_len)) + +static inline ssize_t +generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) +{ + struct iovec iov; + struct iov_iter i; + ssize_t bytes = 0; + + iov_for_each(iov, i, *iter) { + ssize_t res; + + res = generic_file_aio_read(iocb, &iov, 1, iocb->ki_pos); + if (res <= 0) { + if (bytes == 0) + bytes = res; + break; + } + + bytes += res; + if (res < iov.iov_len) + break; + } + + if (bytes > 0) + iov_iter_advance(iter, bytes); + return bytes; +} + +static inline ssize_t +__generic_file_write_iter(struct kiocb *iocb, struct iov_iter *iter) +{ + struct iovec iov; + struct iov_iter i; + ssize_t bytes = 0; + + iov_for_each(iov, i, *iter) { + ssize_t res; + + res = __generic_file_aio_write(iocb, &iov, 1, &iocb->ki_pos); + if (res <= 0) { + if (bytes == 0) + bytes = res; + break; + } + + bytes += res; + if (res < iov.iov_len) + break; + } + + if (bytes > 0) + iov_iter_advance(iter, bytes); + return bytes; +} +#endif /* HAVE_FILE_OPERATIONS_READ_WRITE_ITER */ #endif /* LLITE_INTERNAL_H */