* 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, 2014, Intel Corporation.
*/
/*
* This file is part of Lustre, http://www.lustre.org/
#include <lustre_ver.h>
#include <lustre_disk.h> /* for s2sbi */
#include <lustre_eacl.h>
+#include <lustre_linkea.h>
/* for struct cl_lock_descr and struct cl_io */
#include <cl_object.h>
-#include <lclient.h>
+#include <lustre_lmv.h>
#include <lustre_mdc.h>
-#include <linux/lustre_intent.h>
+#include <lustre_intent.h>
#include <linux/compat.h>
+#include <linux/aio.h>
+
+#include "vvp_internal.h"
+#include "range_lock.h"
#ifndef FMODE_EXEC
#define FMODE_EXEC 0
#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;
#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
#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;
lrp_fsuid/lrp_fsgid. */
};
+struct ll_grouplock {
+ struct lu_env *lg_env;
+ struct cl_io *lg_io;
+ struct cl_lock *lg_lock;
+ unsigned long lg_gid;
+};
+
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 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 << 6),
+ LLIF_DATA_MODIFIED = 1 << 0,
/* File is being restored */
- LLIF_FILE_RESTORING = (1 << 7),
+ LLIF_FILE_RESTORING = 1 << 1,
/* Xattr cache is attached to the file */
- LLIF_XATTR_CACHE = (1 << 8),
+ LLIF_XATTR_CACHE = 1 << 2,
};
struct ll_inode_info {
__u32 lli_inode_magic;
__u32 lli_flags;
- __u64 lli_ioepoch;
spinlock_t lli_lock;
struct posix_acl *lli_posix_acl;
- cfs_hlist_head_t *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;
-
- 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 */
+ 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_oss_capas;
+ /* open count currently used by capability only, indicate whether
+ * capability needs renewal */
+ atomic_t lli_open_count;
+ struct obd_capa *lli_mds_capa;
+ cfs_time_t lli_rmtperm_time;
+
+ /* We need all three because every inode may be opened in different
+ * modes */
+ struct obd_client_handle *lli_mds_read_och;
+ 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
/* 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;
- struct posix_acl *d_def_acl;
- /* 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;
- } 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
+ 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;
+ /* 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 semaphore f_size_sem;
- void *f_size_sem_owner;
- 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
* 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;
- 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;
+ int lli_async_rc;
- /* volatile file criteria is based on file name, this
- * flag is used to keep the test result, so the strcmp
- * is done only once
- */
- bool f_volatile;
/*
* whenever a process try to read/write the file, the
* jobid of the process will be saved here, and it'll
* 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
-#define lli_volatile u.f.f_volatile
-
- } 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
* 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;
- /* valid only inside LAYOUT ibits lock, protected by 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,
size_t size,
__u64 valid);
-int ll_xattr_cache_update(struct inode *inode,
- const char *name,
- const char *newval,
- size_t size,
- __u64 valid,
- int flags);
-
/*
* 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);
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
#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 */
#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", \
- "xattr", \
+ "user_xattr", \
"acl", \
"???", \
"rmt_client", \
"verbose", \
"layout", \
"user_fid2path",\
- "xattr", \
+ "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 {
spinlock_t rct_lock;
- cfs_list_t rct_entries[RCE_HASHES];
+ 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 */
struct eacl_table {
spinlock_t et_lock;
- cfs_list_t et_entries[EE_HASHES];
+ 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;
+ struct list_head ll_list;
/* this protects pglist and ra_info. It isn't safe to
* grab from interrupt contexts */
spinlock_t ll_lock;
int ll_flags;
unsigned int ll_umounting:1,
- ll_xattr_cache_enabled:1;
- cfs_list_t ll_conn_chain; /* per-conn chain of SBs */
+ ll_xattr_cache_enabled:1,
+ ll_client_common_fill_super_succeeded: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*/
- struct ll_close_queue *ll_lcq;
+ /*please don't ask -p*/
+ struct list_head ll_orphan_dentry_list;
struct lprocfs_stats *ll_stats; /* lprocfs stats counter */
- struct cl_client_cache ll_cache;
+ /* 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;
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_size; /* used by readdir */
+ unsigned int ll_md_brw_pages; /* readdir pages per RPC */
struct lu_site *ll_site;
struct cl_device *ll_cl;
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;
- __kernel_fsid_t ll_fsid;
-};
-
-#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;
- cfs_list_t lrr_linkage;
+ /* 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;
};
/*
*/
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.
- */
- cfs_list_t ras_read_beads;
- /*
* The following 3 items are used for detecting the stride I/O
* mode.
* In stride I/O mode,
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;
* 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;
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(
-#ifdef CONFIG_COMPAT
- is_compat_task() ||
-#endif
- (sbi->ll_flags & LL_SBI_32BIT_API)
- );
+ return unlikely(sbi->ll_flags & LL_SBI_32BIT_API);
#endif
}
-#define LLAP_MAGIC 98764321
-
-extern struct kmem_cache *ll_async_page_slab;
-extern size_t ll_async_page_slab_size;
+void ll_ras_enter(struct file *f);
-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);
+/* 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);
-void lprocfs_llite_init_vars(struct lprocfs_static_vars *lvars);
+extern struct lprocfs_vars lprocfs_llite_obd_vars[];
#else
static inline int lprocfs_register_mountpoint(struct proc_dir_entry *parent,
struct super_block *sb, char *osc, char *mdc){return 0;}
static inline void lprocfs_unregister_mountpoint(struct ll_sb_info *sbi) {}
static void ll_stats_ops_tally(struct ll_sb_info *sbi, int op, int count) {}
-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);
-#ifndef HAVE_IOP_ATOMIC_OPEN
-struct lookup_intent *ll_convert_intent(struct open_intent *oit,
- int lookup_flags);
-#endif
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);
+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,
ldlm_mode_t mode);
-int __ll_inode_revalidate_it(struct dentry *, struct lookup_intent *,
- __u64 bits);
-#ifdef HAVE_IOP_ATOMIC_OPEN
-int ll_revalidate_nd(struct dentry *dentry, unsigned int flags);
-#else
-int ll_revalidate_nd(struct dentry *dentry, struct nameidata *nd);
-#endif
+
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);
-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);
+int ll_md_real_close(struct inode *inode, fmode_t fmode);
void ll_pack_inode2opdata(struct inode *inode, struct md_op_data *op_data,
struct lustre_handle *fh);
extern void ll_rw_stats_tally(struct ll_sb_info *sbi, pid_t pid,
struct ll_file_data *file, loff_t pos,
size_t count, int rw);
-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
#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 **lmmp,
- int *lmm_size, struct ptlrpc_request **request);
+int ll_dir_getstripe(struct inode *inode, void **lmmp,
+ int *lmm_size, struct ptlrpc_request **request,
+ u64 valid);
#ifdef HAVE_FILE_FSYNC_4ARGS
int ll_fsync(struct file *file, loff_t start, loff_t end, int data);
#elif defined(HAVE_FILE_FSYNC_2ARGS)
#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(const struct lu_env *env, 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_data_version(struct inode *inode, __u64 *data_version, int extent_lock);
+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);
-struct obd_client_handle *ll_lease_open(struct inode *inode, struct file *file,
- fmode_t mode, __u64 flags);
-int ll_lease_close(struct obd_client_handle *och, struct inode *inode,
- bool *lease_broken);
-
/* llite/dcache.c */
int ll_d_init(struct dentry *de);
-extern struct dentry_operations ll_d_ops;
+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_resource_lock(struct ldlm_lock *lock);
-struct inode *ll_inode_from_lock(struct ldlm_lock *lock);
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);
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_prep_inode(struct inode **inode, struct ptlrpc_request *req,
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_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;
__u32 get_uuid2int(const char *name, int len);
-void get_uuid2fsid(const char *name, int len, __kernel_fsid_t *fsid);
struct inode *search_inode_for_lustre(struct super_block *sb,
const struct lu_fid *fid);
-
-/* 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;
+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;
- cfs_list_t lcq_head;
- cfs_waitq_t lcq_waitq;
- struct completion lcq_comp;
- cfs_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 called from .sendfile */
- IO_SENDFILE,
- /** io started from splice_{read|write} */
- IO_SPLICE
-};
-
-/* IO subtypes */
-struct vvp_io {
- /** io subtype */
- enum vvp_io_subtype cui_io_subtype;
-
- union {
- struct {
- read_actor_t cui_actor;
- void *cui_target;
- } sendfile;
- 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;
- /**
- * Partially truncated page, that vvp_io_trunc_start() keeps locked
- * across truncate.
- */
- struct cl_page *cui_partpage;
-};
-
/**
* IO arguments for various VFS I/O interfaces.
*/
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;
};
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;
- struct kiocb vti_kiocb;
- struct ll_cl_context vti_io_ctx;
+struct ll_thread_info {
+ struct iovec lti_local_iov;
+ 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;
}
-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,
static inline void ll_invalidate_page(struct page *vmpage)
{
- struct address_space *mapping = vmpage->mapping;
- loff_t offset = vmpage->index << PAGE_CACHE_SHIFT;
+ struct address_space *mapping = vmpage->mapping;
+ loff_t offset = vmpage->index << PAGE_CACHE_SHIFT;
- LASSERT(PageLocked(vmpage));
- if (mapping == NULL)
- return;
+ 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);
+ truncate_complete_page(mapping, vmpage);
}
#define ll_s2sbi(sb) (s2lsi(sb)->lsi_llsbi)
return fid;
}
-static inline int ll_mds_max_easize(struct super_block *sb)
+static inline loff_t ll_file_maxbytes(struct inode *inode)
{
- return sbi2mdc(ll_s2sbi(sb))->cl_max_mds_easize;
-}
+ struct cl_object *obj = ll_i2info(inode)->lli_clob;
-static inline __u64 ll_file_maxbytes(struct inode *inode)
-{
- return ll_i2info(inode)->lli_maxbytes;
+ if (obj == NULL)
+ return MAX_LFS_FILESIZE;
+
+ return min_t(loff_t, cl_object_maxbytes(obj), MAX_LFS_FILESIZE);
}
/* llite/xattr.c */
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);
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);
-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
-obd_valid rce_ops2valid(int ops);
+u64 rce_ops2valid(int ops);
struct rmtacl_ctl_entry *rct_search(struct rmtacl_ctl_table *rct, pid_t key);
int rct_add(struct rmtacl_ctl_table *rct, pid_t key, int ops);
int rct_del(struct rmtacl_ctl_table *rct, pid_t key);
/* 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; /* entry list */
- 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];
+ 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];
- cfs_atomic_t sai_cache_count; /* entry count in cache */
+ 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)
{
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 != cfs_curproc_pid())
- return;
-
- LASSERT(ldd != NULL);
- if (sai != NULL)
- ldd->lld_sa_generation = sai->sai_generation;
-}
-
-static inline int
-ll_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);
- /* not the same process, don't statahead */
- if (lli->lli_opendir_pid != cfs_curproc_pid())
- return -EAGAIN;
- /* statahead has been stopped */
- if (lli->lli_opendir_key == NULL)
- return -EAGAIN;
+ /* 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;
- 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;
+ ldd = ll_d2d(dentry);
+ if (ldd != NULL && ldd->lld_sa_generation == lli->lli_sa_generation)
+ return false;
- return 1;
-}
-
-static inline int
-ll_statahead_enter(struct inode *dir, struct dentry **dentryp, int only_unplug)
-{
- int ret;
-
- ret = ll_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
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.
*
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_SEM_LOCKED(&ll_i2info(inode)->lli_size_sem);
- 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,
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);
+ ll_stats_ops_tally(ll_s2sbi(cl2vvp_dev(dev)->vdv_sb), opc, rc);
}
extern ssize_t ll_direct_rw_pages(const struct lu_env *env, struct cl_io *io,
* 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 %p"
- "(%lu/%u) for remote lock "LPX64"\n", inode,
- inode->i_ino, inode->i_generation,
+ 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 %p (%lu/%u)"
- " for lock "LPX64"\n", inode, inode->i_ino,
- inode->i_generation, handle.cookie);
+ 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);
{
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_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);
}
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);
+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, struct obd_capa *capa);
+
+extern struct lu_env *cl_inode_fini_env;
+extern int 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);
+
#endif /* LLITE_INTERNAL_H */