X-Git-Url: https://git.whamcloud.com/?p=fs%2Flustre-release.git;a=blobdiff_plain;f=lustre%2Fllite%2Fllite_internal.h;h=25b92b8f4d64db706af1f4651ce7820c16cafa01;hp=b4eb309ed74619671e7630756578673d5009e23f;hb=26bcb8fcd034f2edc993fa27a9158479836523b8;hpb=ecaba99677b28536f9c376b2b835b554a7792668 diff --git a/lustre/llite/llite_internal.h b/lustre/llite/llite_internal.h index b4eb309..25b92b8 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, 2012, Whamcloud, Inc. + * Copyright (c) 2011, 2013, Intel Corporation. */ /* * This file is part of Lustre, http://www.lustre.org/ @@ -36,19 +36,21 @@ #ifndef LLITE_INTERNAL_H #define LLITE_INTERNAL_H - -#include - #include #include #include /* for s2sbi */ #include +#include /* for struct cl_lock_descr and struct cl_io */ #include #include +#include #include -#include +#include +#include + +#include "range_lock.h" #ifndef FMODE_EXEC #define FMODE_EXEC 0 @@ -68,14 +70,13 @@ #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) struct ll_dentry_data { - int lld_cwd_count; - int lld_mnt_count; - struct obd_client_handle lld_cwd_och; - struct obd_client_handle lld_mnt_och; struct lookup_intent *lld_it; unsigned int lld_sa_generation; unsigned int lld_invalid:1; @@ -84,8 +85,6 @@ struct ll_dentry_data { #define ll_d2d(de) ((struct ll_dentry_data*)((de)->d_fsdata)) -extern struct file_operations ll_pgcache_seq_fops; - #define LLI_INODE_MAGIC 0x111d0de5 #define LLI_INODE_DEAD 0xdeadd00d @@ -93,14 +92,17 @@ extern struct file_operations ll_pgcache_seq_fops; #define REMOTE_PERM_HASHSIZE 16 struct ll_getname_data { - char *lgd_name; /* points to a buffer with NAME_MAX+1 size */ - struct lu_fid lgd_fid; /* target fid we are looking for */ - int lgd_found; /* inode matched? */ +#ifdef HAVE_DIR_CONTEXT + struct dir_context ctx; +#endif + char *lgd_name; /* points to a buffer with NAME_MAX+1 size */ + struct lu_fid lgd_fid; /* target fid we are looking for */ + int lgd_found; /* inode matched? */ }; /* llite setxid/access permission for user on remote client */ struct ll_remote_perm { - cfs_hlist_node_t lrp_list; + struct hlist_node lrp_list; uid_t lrp_uid; gid_t lrp_gid; uid_t lrp_fsuid; @@ -120,113 +122,118 @@ enum lli_flags { /* Sizeon-on-MDS attributes are changed. An attribute update needs to * be sent to MDS. */ LLIF_SOM_DIRTY = (1 << 3), - /* File is contented */ - LLIF_CONTENDED = (1 << 4), - /* Truncate uses server lock for this file */ - LLIF_SRVLOCK = (1 << 5), - + /* 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_inode_info { - __u32 lli_inode_magic; - __u32 lli_flags; - __u64 lli_ioepoch; - - cfs_spinlock_t lli_lock; - struct posix_acl *lli_posix_acl; - - cfs_hlist_head_t *lli_remote_perms; - cfs_mutex_t 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; - - cfs_list_t lli_close_list; - cfs_list_t lli_oss_capas; - /* open count currently used by capability only, indicate whether - * capability needs renewal */ - cfs_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 */ - cfs_mutex_t lli_och_mutex; - - struct inode lli_vfs_inode; - - /* the most recent timestamps obtained from mds */ - struct ost_lvb lli_lvb; - cfs_spinlock_t lli_agl_lock; - - /* Try to make the d::member and f::member are aligned. Before using - * these members, make clear whether it is directory or not. */ - union { - /* for directory */ - struct { - /* serialize normal readdir and statahead-readdir. */ - cfs_mutex_t 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; - struct posix_acl *d_def_acl; - /* protect statahead stuff. */ - cfs_spinlock_t d_sa_lock; - /* "opendir_pid" is the token when lookup/revalid - * -- I am the owner of dir statahead. */ - pid_t d_opendir_pid; - } 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_def_acl u.d.d_def_acl -#define lli_sa_lock u.d.d_sa_lock -#define lli_opendir_pid u.d.d_opendir_pid - - /* for non-directory */ - struct { - cfs_semaphore_t f_size_sem; - void *f_size_sem_owner; - char *f_symlink_name; - __u64 f_maxbytes; - /* - * cfs_rw_semaphore_t { - * signed long count; // align u.d.d_def_acl - * cfs_spinlock_t wait_lock; // align u.d.d_sa_lock - * struct list_head wait_list; - * } - */ - cfs_rw_semaphore_t f_trunc_sem; - cfs_mutex_t f_write_mutex; + __u32 lli_inode_magic; + __u32 lli_flags; + __u64 lli_ioepoch; + + spinlock_t lli_lock; + 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; + /* master inode fid for stripe directory */ + 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 */ + struct mutex lli_och_mutex; + + struct inode lli_vfs_inode; + + /* the most recent timestamps obtained from mds */ + struct ost_lvb lli_lvb; + spinlock_t lli_agl_lock; + + /* Try to make the d::member and f::member are aligned. Before using + * these members, make clear whether it is directory or not. */ + union { + /* for directory */ + struct { + /* serialize normal readdir and statahead-readdir. */ + struct mutex lli_readdir_mutex; + + /* metadata statahead */ + /* since parent-child threads can share the same @file + * struct, "opendir_key" is the token when dir close for + * 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 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 *lli_lsm_md; + /* striped directory size */ + loff_t lli_stripe_dir_size; + /* striped directory nlink */ + __u64 lli_stripe_dir_nlink; + }; + + /* for non-directory */ + struct { + struct mutex lli_size_mutex; + char *lli_symlink_name; + __u64 lli_maxbytes; + /* + * struct rw_semaphore { + * signed long count; // align d.d_def_acl + * spinlock_t wait_lock; // align d.d_sa_lock + * struct list_head wait_list; + * } + */ + struct rw_semaphore lli_trunc_sem; + struct range_lock_tree lli_write_tree; - cfs_rw_semaphore_t f_glimpse_sem; - cfs_time_t f_glimpse_time; - cfs_list_t 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; + /* for writepage() only to communicate to fsync */ + int lli_async_rc; /* * whenever a process try to read/write the file, the @@ -236,23 +243,9 @@ 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_sem u.f.f_size_sem -#define lli_size_sem_owner u.f.f_size_sem_owner -#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 @@ -268,16 +261,47 @@ struct ll_inode_info { struct cl_object *lli_clob; /* mutex to request for layout lock exclusively. */ - cfs_mutex_t lli_layout_mutex; - /* valid only inside LAYOUT ibits lock, protected by lli_layout_mutex */ + struct mutex lli_layout_mutex; + /* Layout version, protected by lli_layout_lock */ __u32 lli_layout_gen; + spinlock_t lli_layout_lock; + + struct rw_semaphore lli_xattrs_list_rwsem; + struct mutex lli_xattrs_enq_lock; + struct list_head lli_xattrs; /* ll_xattr_entry->xe_list */ }; +static inline __u32 ll_layout_version_get(struct ll_inode_info *lli) +{ + __u32 gen; + + spin_lock(&lli->lli_layout_lock); + gen = lli->lli_layout_gen; + spin_unlock(&lli->lli_layout_lock); + + return gen; +} + +static inline void ll_layout_version_set(struct ll_inode_info *lli, __u32 gen) +{ + spin_lock(&lli->lli_layout_lock); + lli->lli_layout_gen = gen; + spin_unlock(&lli->lli_layout_lock); +} + +int ll_xattr_cache_destroy(struct inode *inode); + +int ll_xattr_cache_get(struct inode *inode, + const char *name, + char *buffer, + size_t size, + __u64 valid); + /* * Locking to guarantee consistency of non-atomic updates to long long i_size, * consistency between file size and KMS. * - * Implemented by ->lli_size_sem and ->lsm_lock, nested in that order. + * Implemented by ->lli_size_mutex and ->lsm_lock, nested in that order. */ void ll_inode_size_lock(struct inode *inode); @@ -292,10 +316,10 @@ static inline struct ll_inode_info *ll_i2info(struct inode *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 - CFS_PAGE_SHIFT)) +#define SBI_DEFAULT_READAHEAD_MAX (40UL << (20 - PAGE_CACHE_SHIFT)) /* default to read-ahead full files smaller than 2MB on the second read */ -#define SBI_DEFAULT_READAHEAD_WHOLE_MAX (2UL << (20 - CFS_PAGE_SHIFT)) +#define SBI_DEFAULT_READAHEAD_WHOLE_MAX (2UL << (20 - PAGE_CACHE_SHIFT)) enum ra_stat { RA_STAT_HIT = 0, @@ -310,14 +334,15 @@ enum ra_stat { RA_STAT_EOF, RA_STAT_MAX_IN_FLIGHT, RA_STAT_WRONG_GRAB_PAGE, - _NR_RA_STAT, + RA_STAT_FAILED_REACH_END, + _NR_RA_STAT, }; struct ll_ra_info { - cfs_atomic_t ra_cur_pages; - unsigned long ra_max_pages; - unsigned long ra_max_pages_per_file; - unsigned long ra_max_read_ahead_whole_pages; + atomic_t ra_cur_pages; + unsigned long ra_max_pages; + unsigned long ra_max_pages_per_file; + unsigned long ra_max_read_ahead_whole_pages; }; /* ra_io_arg will be filled in the beginning of ll_readahead with @@ -394,28 +419,50 @@ enum stats_track_type { #define LL_SBI_VERBOSE 0x10000 /* verbose mount/umount */ #define LL_SBI_LAYOUT_LOCK 0x20000 /* layout lock support */ #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_FLAGS { \ + "nolck", \ + "checksum", \ + "flock", \ + "user_xattr", \ + "acl", \ + "???", \ + "rmt_client", \ + "mds_capa", \ + "oss_capa", \ + "flock", \ + "lru_resize", \ + "lazy_statfs", \ + "som", \ + "32bit_api", \ + "64bit_hash", \ + "agl", \ + "verbose", \ + "layout", \ + "user_fid2path",\ + "xattr_cache", \ + "norootsquash", \ +} -/* default value for ll_sb_info->contention_time */ -#define SBI_DEFAULT_CONTENTION_SECONDS 60 -/* default value for lockless_truncate_enable */ -#define SBI_DEFAULT_LOCKLESS_TRUNCATE_ENABLE 1 #define RCE_HASHES 32 struct rmtacl_ctl_entry { - cfs_list_t rce_list; + struct list_head rce_list; pid_t rce_key; /* hash key */ int rce_ops; /* acl operation type */ }; struct rmtacl_ctl_table { - cfs_spinlock_t rct_lock; - cfs_list_t rct_entries[RCE_HASHES]; + spinlock_t rct_lock; + struct list_head rct_entries[RCE_HASHES]; }; #define EE_HASHES 32 struct eacl_entry { - cfs_list_t ee_list; + 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 */ @@ -423,17 +470,31 @@ struct eacl_entry { }; struct eacl_table { - cfs_spinlock_t et_lock; - cfs_list_t et_entries[EE_HASHES]; + 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 { - cfs_list_t ll_list; - /* this protects pglist and ra_info. It isn't safe to - * grab from interrupt contexts */ - cfs_spinlock_t ll_lock; - cfs_spinlock_t ll_pp_extent_lock; /* Lock for pp_extent entries */ - cfs_spinlock_t ll_process_lock; /* Lock for ll_rw_process_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; @@ -441,14 +502,22 @@ struct ll_sb_info { struct lu_fid ll_root_fid; /* root object fid */ int ll_flags; - cfs_list_t ll_conn_chain; /* per-conn chain of SBs */ + 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; - cfs_list_t ll_orphan_dentry_list; /*please don't ask -p*/ + /*please don't ask -p*/ + struct list_head ll_orphan_dentry_list; struct ll_close_queue *ll_lcq; struct lprocfs_stats *ll_stats; /* lprocfs stats counter */ + /* Used to track "unstable" pages on a client, and maintain a + * LRU list of clean pages. An "unstable" page is defined as + * 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 lprocfs_stats *ll_ra_stats; @@ -460,7 +529,7 @@ struct ll_sb_info { /* =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_size; /* used by readdir */ + unsigned int ll_md_brw_pages; /* readdir pages per RPC */ struct lu_site *ll_site; struct cl_device *ll_cl; @@ -475,18 +544,23 @@ struct ll_sb_info { enum stats_track_type ll_stats_track_type; int ll_rw_stats_on; - /* metadata stat-ahead */ - 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 - * low hit ratio */ - atomic_t ll_agl_total; /* AGL thread started count */ - - dev_t ll_sdev_orig; /* save s_dev before assign for - * clustred nfs */ - struct rmtacl_ctl_table ll_rct; - struct eacl_table ll_et; + /* metadata stat-ahead */ + 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 + * low hit ratio */ + 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 + * 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) @@ -495,14 +569,14 @@ struct ll_ra_read { pgoff_t lrr_start; pgoff_t lrr_count; struct task_struct *lrr_reader; - cfs_list_t lrr_linkage; + struct list_head lrr_linkage; }; /* * per file-descriptor read-ahead data. */ struct ll_readahead_state { - cfs_spinlock_t ras_lock; + spinlock_t ras_lock; /* * index of the last page that read(2) needed and that wasn't in the * cache. Used by ras_update() to detect seeks. @@ -560,7 +634,7 @@ struct ll_readahead_state { * progress against this file descriptor. Used by read-ahead code, * protected by ->ras_lock. */ - cfs_list_t ras_read_beads; + struct list_head ras_read_beads; /* * The following 3 items are used for detecting the stride I/O * mode. @@ -584,24 +658,30 @@ struct ll_readahead_state { unsigned long ras_consecutive_stride_requests; }; -extern cfs_mem_cache_t *ll_file_data_slab; +extern struct kmem_cache *ll_file_data_slab; struct lustre_handle; struct ll_file_data { - struct ll_readahead_state fd_ras; - int fd_omode; - struct ccc_grouplock fd_grouplock; + struct ll_readahead_state fd_ras; + struct ccc_grouplock fd_grouplock; __u64 lfd_pos; - __u32 fd_flags; - struct file *fd_file; + __u32 fd_flags; + fmode_t fd_omode; + /* openhandle if lease exists for this file. + * Borrow lli->lli_och_mutex to protect assignment */ + struct obd_client_handle *fd_lease_och; + struct obd_client_handle *fd_och; + struct file *fd_file; /* Indicate whether need to report failure when close. * true: failure is known, not report again. * false: unknown failure, should report. */ bool fd_write_failed; + rwlock_t fd_lock; /* protect lcc list */ + struct list_head fd_lccs; /* list of ll_cl_context */ }; struct lov_stripe_md; -extern cfs_spinlock_t inode_lock; +extern spinlock_t inode_lock; extern struct proc_dir_entry *proc_lustre_fs_root; @@ -610,29 +690,20 @@ static inline struct inode *ll_info2i(struct ll_inode_info *lli) return &lli->lli_vfs_inode; } -struct it_cb_data { - struct inode *icbd_parent; - struct dentry **icbd_childp; - obd_id hash; -}; - __u32 ll_i2suppgid(struct inode *i); void ll_i2gids(__u32 *suppgids, struct inode *i1,struct inode *i2); static inline int ll_need_32bit_api(struct ll_sb_info *sbi) { #if BITS_PER_LONG == 32 - return 1; + return 1; +#elif defined(CONFIG_COMPAT) + return unlikely(is_compat_task() || (sbi->ll_flags & LL_SBI_32BIT_API)); #else - return unlikely(cfs_curproc_is_32bit() || (sbi->ll_flags & LL_SBI_32BIT_API)); + return unlikely(sbi->ll_flags & LL_SBI_32BIT_API); #endif } -#define LLAP_MAGIC 98764321 - -extern cfs_mem_cache_t *ll_async_page_slab; -extern size_t ll_async_page_slab_size; - 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); @@ -643,103 +714,146 @@ 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); -void lprocfs_llite_init_vars(struct lprocfs_static_vars *lvars); +extern struct lprocfs_seq_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) {} -static void lprocfs_llite_init_vars(struct lprocfs_static_vars *lvars) -{ - memset(lvars, 0, sizeof(*lvars)); -} #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_OSC_READ, + LPROC_LL_OSC_WRITE, + LPROC_LL_IOCTL, + LPROC_LL_OPEN, + LPROC_LL_RELEASE, + LPROC_LL_MAP, + 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 */ -void ll_release_page(struct page *page, int remove); -extern struct file_operations ll_dir_operations; -extern struct inode_operations ll_dir_inode_operations; -struct page *ll_get_dir_page(struct inode *dir, __u64 hash, - struct ll_dir_chain *chain); -int ll_dir_read(struct inode *inode, __u64 *_pos, void *cookie, - filldir_t filldir); +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, __u64 *pos, struct md_op_data *op_data, + struct dir_context *ctx); +#else +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); + /* llite/namei.c */ -int ll_objects_destroy(struct ptlrpc_request *request, - struct inode *dir); +extern const struct inode_operations ll_special_inode_operations; + 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); int ll_md_blocking_ast(struct ldlm_lock *, struct ldlm_lock_desc *, void *data, int flag); -struct lookup_intent *ll_convert_intent(struct open_intent *oit, - int lookup_flags); -int ll_lookup_it_finish(struct ptlrpc_request *request, - struct lookup_intent *it, void *data); struct dentry *ll_splice_alias(struct inode *inode, struct dentry *de); +int ll_rmdir_entry(struct inode *dir, char *name, int namelen); +void ll_update_times(struct ptlrpc_request *request, struct inode *inode); /* llite/rw.c */ -int ll_prepare_write(struct file *, struct page *, unsigned from, unsigned to); -int ll_commit_write(struct file *, struct page *, unsigned from, unsigned to); int ll_writepage(struct page *page, struct writeback_control *wbc); int ll_writepages(struct address_space *, struct writeback_control *wbc); -void ll_removepage(struct page *page); int ll_readpage(struct file *file, struct page *page); void ll_readahead_init(struct inode *inode, struct ll_readahead_state *ras); -int ll_file_punch(struct inode *, loff_t, int); -ssize_t ll_file_lockless_io(struct file *, char *, size_t, loff_t *, int); -void ll_clear_file_contended(struct inode*); -int ll_sync_page_range(struct inode *, struct address_space *, loff_t, size_t); int ll_readahead(const struct lu_env *env, struct cl_io *io, - struct ll_readahead_state *ras, struct address_space *mapping, - struct cl_page_list *queue, int flags); + 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); +void ll_cl_remove(struct file *file, const struct lu_env *env); + +#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; 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_inode_revalidate_it(struct dentry *, struct lookup_intent *, - __u64); 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); -int __ll_inode_revalidate_it(struct dentry *, struct lookup_intent *, - __u64 bits); -int ll_revalidate_nd(struct dentry *dentry, struct nameidata *nd); + struct lustre_handle *lockh, __u64 flags, + ldlm_mode_t 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_local_open(struct file *file, - struct lookup_intent *it, struct ll_file_data *fd, - struct obd_client_handle *och); int ll_release_openhandle(struct dentry *, struct lookup_intent *); -int ll_md_close(struct obd_export *md_exp, struct inode *inode, - struct file *file); -int ll_md_real_close(struct inode *inode, int flags); +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); -int ll_md_setattr(struct dentry *dentry, struct md_op_data *op_data, - struct md_open_data **mod); 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); -int ll_getattr_it(struct vfsmount *mnt, struct dentry *de, - struct lookup_intent *it, struct kstat *stat); int ll_getattr(struct vfsmount *mnt, struct dentry *de, struct kstat *stat); -struct ll_file_data *ll_file_data_get(void); -struct posix_acl * ll_get_acl(struct inode *inode, int type); - +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); #ifdef HAVE_GENERIC_PERMISSION_4ARGS int ll_inode_permission(struct inode *inode, int mask, unsigned int flags); #else @@ -751,15 +865,16 @@ int ll_inode_permission(struct inode *inode, int mask); #endif int ll_lov_setstripe_ea_info(struct inode *inode, struct file *file, - int flags, struct lov_user_md *lum, - int lum_size); + __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, struct ptlrpc_request **request); int ll_dir_setstripe(struct inode *inode, struct lov_user_md *lump, int set_default); -int ll_dir_getstripe(struct inode *inode, struct lov_mds_md **lmm, - int *lmm_size, struct ptlrpc_request **request); +int ll_dir_getstripe(struct inode *inode, void **lmmp, + int *lmm_size, struct ptlrpc_request **request, + obd_valid 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) @@ -767,99 +882,106 @@ int ll_fsync(struct file *file, int data); #else int ll_fsync(struct file *file, struct dentry *dentry, int data); #endif -int ll_do_fiemap(struct inode *inode, struct ll_user_fiemap *fiemap, - int num_bytes); -int ll_merge_lvb(struct inode *inode); -int ll_get_grouplock(struct inode *inode, struct file *file, unsigned long arg); -int ll_put_grouplock(struct inode *inode, struct file *file, unsigned long arg); -int ll_fid2path(struct inode *inode, void *arg); +int ll_merge_lvb(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); /* llite/dcache.c */ -int ll_dops_init(struct dentry *de, int block, int init_sa); -extern struct dentry_operations ll_d_ops; +int ll_d_init(struct dentry *de); +extern const struct dentry_operations ll_d_ops; void ll_intent_drop_lock(struct lookup_intent *); void ll_intent_release(struct lookup_intent *); void ll_invalidate_aliases(struct inode *); -void ll_frob_intent(struct lookup_intent **itp, struct lookup_intent *deft); void ll_lookup_finish_locks(struct lookup_intent *it, struct dentry *dentry); -#ifdef HAVE_D_COMPARE_7ARGS -int ll_dcompare(const struct dentry *parent, const struct inode *pinode, - const struct dentry *dentry, const struct inode *inode, - unsigned int len, const char *str, const struct qstr *d_name); -#else -int ll_dcompare(struct dentry *parent, struct qstr *d_name, struct qstr *name); -#endif int ll_revalidate_it_finish(struct ptlrpc_request *request, struct lookup_intent *it, struct dentry *de); /* llite/llite_lib.c */ extern struct super_operations lustre_super_operations; -char *ll_read_opt(const char *opt, char *data); void ll_lli_init(struct ll_inode_info *lli); 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_lock(struct ldlm_lock *lock); +struct inode *ll_inode_from_resource_lock(struct ldlm_lock *lock); void ll_clear_inode(struct inode *inode); -int ll_setattr_raw(struct dentry *dentry, struct iattr *attr); +int ll_setattr_raw(struct dentry *dentry, struct iattr *attr, 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); -void ll_update_inode(struct inode *inode, struct lustre_md *md); -void ll_read_inode2(struct inode *inode, void *opaque); +int ll_update_inode(struct inode *inode, struct lustre_md *md); +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, unsigned int cmd, unsigned long arg); int ll_flush_ctx(struct inode *inode); -#ifdef HAVE_UMOUNTBEGIN_VFSMOUNT -void ll_umount_begin(struct vfsmount *vfsmnt, int flags); -#else void ll_umount_begin(struct super_block *sb); -#endif int ll_remount_fs(struct super_block *sb, int *flags, char *data); +#ifdef HAVE_SUPEROPS_USE_DENTRY +int ll_show_options(struct seq_file *seq, struct dentry *dentry); +#else int ll_show_options(struct seq_file *seq, struct vfsmount *vfs); -void ll_dirty_page_discard_warn(cfs_page_t *page, int ioret); +#endif +void ll_dirty_page_discard_warn(struct page *page, int ioret); int ll_prep_inode(struct inode **inode, struct ptlrpc_request *req, - struct super_block *); + struct super_block *, struct lookup_intent *); void lustre_dump_dentry(struct dentry *, int recur); -void lustre_dump_inode(struct inode *); -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_process_config(struct lustre_cfg *lcfg); 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); + +/* 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; __u32 get_uuid2int(const char *name, int len); - -/* llite/special.c */ -extern struct inode_operations ll_special_inode_operations; -extern struct file_operations ll_special_chr_inode_fops; -extern struct file_operations ll_special_chr_file_fops; -extern struct file_operations ll_special_blk_inode_fops; -extern struct file_operations ll_special_fifo_inode_fops; -extern struct file_operations ll_special_fifo_file_fops; -extern struct file_operations ll_special_sock_inode_fops; +struct inode *search_inode_for_lustre(struct super_block *sb, + const struct lu_fid *fid); +int ll_dir_get_parent_fid(struct inode *dir, struct lu_fid *parent_fid); /* llite/symlink.c */ extern struct inode_operations ll_fast_symlink_inode_operations; /* llite/llite_close.c */ struct ll_close_queue { - cfs_spinlock_t lcq_lock; - cfs_list_t lcq_head; - cfs_waitq_t lcq_waitq; - cfs_completion_t lcq_comp; - cfs_atomic_t lcq_stop; + 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); @@ -872,8 +994,6 @@ void vvp_write_complete(struct ccc_object *club, struct ccc_page *page); enum vvp_io_subtype { /** normal IO */ IO_NORMAL, - /** io called from .sendfile */ - IO_SENDFILE, /** io started from splice_{read|write} */ IO_SPLICE }; @@ -885,10 +1005,6 @@ struct vvp_io { union { struct { - read_actor_t cui_actor; - void *cui_target; - } sendfile; - struct { struct pipe_inode_info *cui_pipe; unsigned int cui_flags; } splice; @@ -902,20 +1018,7 @@ struct vvp_io { /** * locked page returned from vvp_io */ - cfs_page_t *ft_vmpage; -#ifndef HAVE_VM_OP_FAULT - struct vm_nopage_api { - /** - * Virtual address at which fault occurred. - */ - unsigned long ft_address; - /** - * Fault type, as to be supplied to - * filemap_nopage(). - */ - int *ft_type; - } nopage; -#else + struct page *ft_vmpage; struct vm_fault_api { /** * kernel fault info @@ -925,8 +1028,11 @@ struct vvp_io { * fault API used bitflags for return code. */ unsigned int ft_flags; + /** + * check that flags are from filemap_fault + */ + bool ft_flags_valid; } fault; -#endif } fault; } u; /** @@ -937,11 +1043,6 @@ struct vvp_io { * Set when cui_bead has been initialized. */ int cui_ra_window_set; - /** - * Partially truncated page, that vvp_io_trunc_start() keeps locked - * across truncate. - */ - struct cl_page *cui_partpage; }; /** @@ -953,17 +1054,11 @@ struct vvp_io_args { union { struct { -#ifndef HAVE_FILE_WRITEV struct kiocb *via_iocb; -#endif struct iovec *via_iov; unsigned long via_nrsegs; } normal; struct { - read_actor_t via_actor; - void *via_target; - } sendfile; - struct { struct pipe_inode_info *via_pipe; unsigned int via_flags; } splice; @@ -971,17 +1066,14 @@ struct vvp_io_args { }; struct ll_cl_context { - void *lcc_cookie; - struct cl_io *lcc_io; - struct cl_page *lcc_page; - struct lu_env *lcc_env; - int lcc_refcheck; - int lcc_created; + struct list_head lcc_list; + void *lcc_cookie; + const struct lu_env *lcc_env; + struct cl_io *lcc_io; + struct cl_page *lcc_page; }; struct vvp_thread_info { - struct ost_lvb vti_lvb; - struct cl_2queue vti_queue; struct iovec vti_local_iov; struct vvp_io_args vti_args; struct ra_io_arg vti_ria; @@ -989,9 +1081,10 @@ struct vvp_thread_info { struct ll_cl_context vti_io_ctx; }; +extern struct lu_context_key vvp_key; + 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; info = lu_context_key_get(&env->le_ctx, &vvp_key); @@ -1013,9 +1106,10 @@ struct vvp_session { struct vvp_io vs_ios; }; +extern struct lu_context_key vvp_session_key; + static inline struct vvp_session *vvp_env_session(const struct lu_env *env) { - extern struct lu_context_key vvp_session_key; struct vvp_session *ses; ses = lu_context_key_get(env->le_ses, &vvp_session_key); @@ -1028,25 +1122,17 @@ static inline struct vvp_io *vvp_env_io(const struct lu_env *env) return &vvp_env_session(env)->vs_ios; } +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 */ -typedef struct rb_root rb_root_t; -typedef struct rb_node rb_node_t; - -struct ll_lock_tree_node; -struct ll_lock_tree { - rb_root_t lt_root; - cfs_list_t lt_locked_list; - struct ll_file_data *lt_fd; -}; int ll_teardown_mmaps(struct address_space *mapping, __u64 first, __u64 last); int ll_file_mmap(struct file * file, struct vm_area_struct * vma); -struct ll_lock_tree_node * ll_node_from_inode(struct inode *inode, __u64 start, - __u64 end, ldlm_mode_t mode); void policy_from_vma(ldlm_policy_data_t *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, @@ -1054,15 +1140,19 @@ struct vm_area_struct *our_vma(struct mm_struct *mm, unsigned long addr, static inline void ll_invalidate_page(struct page *vmpage) { - struct address_space *mapping = vmpage->mapping; - loff_t offset = vmpage->index << PAGE_CACHE_SHIFT; - - LASSERT(PageLocked(vmpage)); - if (mapping == NULL) - return; - - ll_teardown_mmaps(mapping, offset, offset + CFS_PAGE_SIZE); - truncate_complete_page(mapping, vmpage); + struct address_space *mapping = vmpage->mapping; + loff_t offset = vmpage->index << PAGE_CACHE_SHIFT; + + LASSERT(PageLocked(vmpage)); + if (mapping == NULL) + return; + + /* + * truncate_complete_page() calls + * a_ops->invalidatepage()->cl_page_delete()->vvp_page_delete(). + */ + ll_teardown_mmaps(mapping, offset, offset + PAGE_CACHE_SIZE); + truncate_complete_page(mapping, vmpage); } #define ll_s2sbi(sb) (s2lsi(sb)->lsi_llsbi) @@ -1106,15 +1196,11 @@ static inline struct obd_export *ll_i2mdexp(struct inode *inode) static inline struct lu_fid *ll_inode2fid(struct inode *inode) { struct lu_fid *fid; + LASSERT(inode != NULL); fid = &ll_i2info(inode)->lli_fid; - LASSERT(fid_is_igif(fid) || fid_ver(fid) == 0); - return fid; -} -static inline int ll_mds_max_easize(struct super_block *sb) -{ - return sbi2mdc(ll_s2sbi(sb))->cl_max_mds_easize; + return fid; } static inline __u64 ll_file_maxbytes(struct inode *inode) @@ -1131,23 +1217,21 @@ 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 cfs_mem_cache_t *ll_remote_perm_cachep; -extern cfs_mem_cache_t *ll_rmtperm_hash_cachep; +extern struct kmem_cache *ll_remote_perm_cachep; +extern struct kmem_cache *ll_rmtperm_hash_cachep; -cfs_hlist_head_t *alloc_rmtperm_hash(void); -void free_rmtperm_hash(cfs_hlist_head_t *hash); +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 cfs_timer_t ll_capa_timer; +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); -int ll_update_capa(struct obd_capa *ocapa, struct lustre_capa *capa); void ll_capa_open(struct inode *inode); void ll_capa_close(struct inode *inode); @@ -1167,15 +1251,12 @@ extern struct lu_device_type vvp_device_type; */ int cl_sb_init(struct super_block *sb); int cl_sb_fini(struct super_block *sb); -enum cl_lock_mode vvp_mode_from_vma(struct vm_area_struct *vma); -void ll_io_init(struct cl_io *io, const struct file *file, int write); void ras_update(struct ll_sb_info *sbi, struct inode *inode, struct ll_readahead_state *ras, unsigned long index, unsigned hit); void ll_ra_count_put(struct ll_sb_info *sbi, unsigned long len); -int ll_is_file_contended(struct file *file); -void ll_ra_stats_inc(struct address_space *mapping, enum ra_stat which); +void ll_ra_stats_inc(struct inode *inode, enum ra_stat which); /* llite/llite_rmtacl.c */ #ifdef CONFIG_FS_POSIX_ACL @@ -1208,116 +1289,109 @@ void et_fini(struct eacl_table *et); /* per inode struct, for dir only */ struct ll_statahead_info { - struct inode *sai_inode; - cfs_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 - * reply */ - __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; - * 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 - * hidden entries */ - sai_in_readpage:1,/* statahead is in readdir()*/ - sai_agl_valid:1;/* AGL is valid for the dir */ - cfs_waitq_t sai_waitq; /* stat-ahead wait queue */ - struct ptlrpc_thread sai_thread; /* stat-ahead thread */ - struct ptlrpc_thread sai_agl_thread; /* AGL thread */ - cfs_list_t sai_entries_sent; /* entries sent out */ - cfs_list_t sai_entries_received; /* entries returned */ - cfs_list_t sai_entries_stated; /* entries stated */ - cfs_list_t sai_entries_agl; /* AGL entries to be sent */ - cfs_list_t sai_cache[LL_SA_CACHE_SIZE]; - cfs_spinlock_t sai_cache_lock[LL_SA_CACHE_SIZE]; - cfs_atomic_t sai_cache_count; /* entry count in cache */ + struct dentry *sai_dentry; + atomic_t sai_refcount; /* when access this struct, hold + * refcount */ + 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 + * caller is waiting for */ + __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 + * hidden entries */ + sai_agl_valid:1,/* AGL is valid for the dir */ + sai_in_readpage:1;/* statahead is in readdir()*/ + wait_queue_head_t sai_waitq; /* stat-ahead wait queue */ + struct ptlrpc_thread sai_thread; /* stat-ahead thread */ + struct ptlrpc_thread sai_agl_thread; /* AGL thread */ + struct 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); static inline int ll_glimpse_size(struct inode *inode) { - struct ll_inode_info *lli = ll_i2info(inode); - int rc; - - cfs_down_read(&lli->lli_glimpse_sem); - rc = cl_glimpse_size(inode); - lli->lli_glimpse_time = cfs_time_current(); - cfs_up_read(&lli->lli_glimpse_sem); - return rc; + struct ll_inode_info *lli = ll_i2info(inode); + int rc; + + down_read(&lli->lli_glimpse_sem); + rc = cl_glimpse_size(inode); + lli->lli_glimpse_time = cfs_time_current(); + up_read(&lli->lli_glimpse_sem); + return rc; } -static inline void -ll_statahead_mark(struct inode *dir, struct dentry *dentry) +/* 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 = 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 != cfs_curproc_pid()) - return; - - if (sai != NULL && ldd != NULL) - ldd->lld_sa_generation = sai->sai_generation; -} - -static inline int -ll_statahead_enter(struct inode *dir, struct dentry **dentryp, int only_unplug) -{ - struct ll_inode_info *lli; - struct ll_dentry_data *ldd; - - if (ll_i2sbi(dir)->ll_sa_max == 0) - return -EAGAIN; - - lli = ll_i2info(dir); - /* not the same process, don't statahead */ - if (lli->lli_opendir_pid != cfs_curproc_pid()) - return -EAGAIN; - - 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. - * 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" - */ - if (ldd && lli->lli_sai && - ldd->lld_sa_generation == lli->lli_sai->sai_generation) - return -EAGAIN; - - return do_statahead_enter(dir, dentryp, only_unplug); + struct ll_inode_info *lli; + struct ll_dentry_data *ldd; + + if (ll_i2sbi(dir)->ll_sa_max == 0) + 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 false; + + /* + * 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 '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'. + */ + ldd = ll_d2d(dentry); + if (ldd != NULL && ldd->lld_sa_generation == lli->lli_sa_generation) + return false; + + return true; } /* llite ioctl register support rountine */ -#ifdef __KERNEL__ enum llioc_iter { LLIOC_CONT = 0, LLIOC_STOP @@ -1343,9 +1417,6 @@ typedef enum llioc_iter (*llioc_callback_t)(struct inode *inode, struct file *file, unsigned int cmd, unsigned long arg, void *magic, int *rcp); -enum llioc_iter ll_iocontrol_call(struct inode *inode, struct file *file, - unsigned int cmd, unsigned long arg, int *rcp); - /* export functions */ /* Register ioctl block dynamatically for a regular file. * @@ -1361,7 +1432,6 @@ enum llioc_iter ll_iocontrol_call(struct inode *inode, struct file *file, 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 @@ -1388,8 +1458,8 @@ static inline void cl_isize_unlock(struct inode *inode) static inline void cl_isize_write_nolock(struct inode *inode, loff_t kms) { - LASSERT_SEM_LOCKED(&ll_i2info(inode)->lli_size_sem); - i_size_write(inode, 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) @@ -1401,9 +1471,9 @@ static inline void cl_isize_write(struct inode *inode, loff_t kms) #define cl_isize_read(inode) i_size_read(inode) -static inline int cl_merge_lvb(struct inode *inode) +static inline int cl_merge_lvb(const struct lu_env *env, struct inode *inode) { - return ll_merge_lvb(inode); + return ll_merge_lvb(env, inode); } #define cl_inode_atime(inode) LTIME_S((inode)->i_atime) @@ -1413,7 +1483,7 @@ static inline int cl_merge_lvb(struct inode *inode) 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); + enum cl_fsync_mode mode, int ignore_layout); /** direct write pages */ struct ll_dio_pages { @@ -1458,16 +1528,38 @@ 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) { - CDEBUG(D_DLMTRACE, "setting l_data to inode %p (%lu/%u)\n", - inode, inode->i_ino, inode->i_generation); - md_set_lock_data(exp, &it->d.lustre.it_lock_handle, - inode, &it->d.lustre.it_lock_bits); - it->d.lustre.it_lock_set = 1; - } - - if (bits != NULL) - *bits = it->d.lustre.it_lock_bits; + if (!it->d.lustre.it_lock_set) { + struct lustre_handle handle; + + /* If this inode is a remote object, it will get two + * separate locks in different namespaces, Master MDT, + * where the name entry is, will grant LOOKUP lock, + * remote MDT, where the object is, will grant + * 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; + CDEBUG(D_DLMTRACE, "setting l_data to inode "DFID + "(%p) for remote lock "LPX64"\n", + PFID(ll_inode2fid(inode)), inode, + handle.cookie); + md_set_lock_data(exp, &handle.cookie, inode, NULL); + } + + handle.cookie = it->d.lustre.it_lock_handle; + + CDEBUG(D_DLMTRACE, "setting l_data to inode "DFID"(%p)" + " for lock "LPX64"\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; + } + + if (bits != NULL) + *bits = it->d.lustre.it_lock_bits; } static inline void ll_lock_dcache(struct inode *inode) @@ -1508,15 +1600,16 @@ static inline void __d_lustre_invalidate(struct dentry *dentry) * ll_md_blocking_ast), unhash this dentry, and let dcache to reclaim it later; * else dput() of the last refcount will unhash this dentry and kill it. */ -static inline void d_lustre_invalidate(struct dentry *dentry) +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_refcount(dentry)); + dentry->d_parent, dentry->d_inode, ll_d_count(dentry)); - spin_lock(&dentry->d_lock); + spin_lock_nested(&dentry->d_lock, + nested ? DENTRY_D_LOCK_NESTED : DENTRY_D_LOCK_NORMAL); __d_lustre_invalidate(dentry); - if (d_refcount(dentry) == 0) + if (ll_d_count(dentry) == 0) __d_drop(dentry); spin_unlock(&dentry->d_lock); } @@ -1529,25 +1622,37 @@ 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) +#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; + __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) */ +#endif /* LUSTRE_VERSION_CODE < OBD_OCD_VERSION(2, 7, 53, 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); + +int ll_xattr_init(void); +void ll_xattr_fini(void); + +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); #endif /* LLITE_INTERNAL_H */