#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 "range_lock.h"
+
#ifndef FMODE_EXEC
#define FMODE_EXEC 0
#endif
#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 hlist_head *lli_remote_perms;
struct mutex lli_rmtperm_mutex;
- /* identifying fields for both metadata and data stacks. */
- struct lu_fid lli_fid;
- /* Parent fid for accessing default stripe data on parent directory
- * for allocating OST objects after a mknod() and later open-by-FID. */
- struct lu_fid lli_pfid;
+ /* 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 */
+ 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;
/* serialize normal readdir and statahead-readdir. */
struct mutex d_readdir_mutex;
- /* metadata statahead */
- /* since parent-child threads can share the same @file
- * struct, "opendir_key" is the token when dir close for
- * case of parent exit before child -- it is me should
- * cleanup the dir readahead. */
- void *d_opendir_key;
- struct ll_statahead_info *d_sai;
- /* protect statahead stuff. */
+ /* metadata statahead */
+ /* since parent-child threads can share the same @file
+ * struct, "opendir_key" is the token when dir close for
+ * case of parent exit before child -- it is me should
+ * cleanup the dir readahead. */
+ void *d_opendir_key;
+ struct ll_statahead_info *d_sai;
+ /* protect statahead stuff. */
spinlock_t d_sa_lock;
/* "opendir_pid" is the token when lookup/revalid
* -- I am the owner of dir statahead. */
- pid_t d_opendir_pid;
+ pid_t d_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 d_sa_enabled:1;
/* directory stripe information */
struct lmv_stripe_md *d_lsm_md;
/* striped directory size */
#define lli_opendir_key u.d.d_opendir_key
#define lli_sai u.d.d_sai
#define lli_sa_lock u.d.d_sa_lock
+#define lli_sa_enabled u.d.d_sa_enabled
#define lli_opendir_pid u.d.d_opendir_pid
#define lli_lsm_md u.d.d_lsm_md
#define lli_stripe_dir_size u.d.d_stripe_size
* }
*/
struct rw_semaphore f_trunc_sem;
- struct mutex f_write_mutex;
+ struct range_lock_tree f_write_tree;
struct rw_semaphore f_glimpse_sem;
cfs_time_t f_glimpse_time;
* 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];
+ char f_jobid[LUSTRE_JOBID_SIZE];
} f;
#define lli_size_mutex u.f.f_size_mutex
#define lli_symlink_name u.f.f_symlink_name
#define lli_maxbytes u.f.f_maxbytes
#define lli_trunc_sem u.f.f_trunc_sem
-#define lli_write_mutex u.f.f_write_mutex
+#define lli_write_tree u.f.f_write_tree
#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
struct list_head et_entries[EE_HASHES];
};
+
+/* This is embedded into llite super-blocks to keep track of connect
+ * flags (capabilities) supported by all imports given mount is
+ * connected to. */
+struct lustre_client_ocd {
+ /* This is conjunction of connect_flags across all imports
+ * (LOVs) this mount is connected to. This field is updated by
+ * cl_ocd_update() under ->lco_lock. */
+ __u64 lco_flags;
+ struct mutex lco_lock;
+ struct obd_export *lco_md_exp;
+ struct obd_export *lco_dt_exp;
+};
+
struct ll_sb_info {
struct list_head ll_list;
/* this protects pglist and ra_info. It isn't safe to
int ll_rw_stats_on;
/* metadata stat-ahead */
- unsigned int ll_sa_max; /* max statahead RPCs */
- atomic_t ll_sa_total; /* statahead thread started
+ unsigned int ll_sa_max; /* max statahead RPCs */
+ atomic_t ll_sa_total; /* statahead thread started
* count */
- atomic_t ll_sa_wrong; /* statahead thread stopped for
+ atomic_t ll_sa_wrong; /* statahead thread stopped for
* low hit ratio */
- atomic_t ll_agl_total; /* AGL thread started count */
+ atomic_t ll_sa_running; /* running statahead thread
+ * count */
+ atomic_t ll_agl_total; /* AGL thread started count */
- dev_t ll_sdev_orig; /* save s_dev before assign for
+ dev_t ll_sdev_orig; /* save s_dev before assign for
* clustred nfs */
- struct rmtacl_ctl_table ll_rct;
- struct eacl_table ll_et;
+ struct rmtacl_ctl_table ll_rct;
+ struct eacl_table ll_et;
/* root squash */
- struct root_squash_info ll_squash;
+ struct root_squash_info ll_squash;
};
#define LL_DEFAULT_MAX_RW_CHUNK (32 * 1024 * 1024)
* 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;
static void ll_stats_ops_tally(struct ll_sb_info *sbi, int op, int count) {}
#endif
+enum {
+ LPROC_LL_DIRTY_HITS,
+ LPROC_LL_DIRTY_MISSES,
+ LPROC_LL_READ_BYTES,
+ LPROC_LL_WRITE_BYTES,
+ LPROC_LL_BRW_READ,
+ LPROC_LL_BRW_WRITE,
+ LPROC_LL_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 */
+struct ll_dir_chain {
+};
+
+static inline void ll_dir_chain_init(struct ll_dir_chain *chain)
+{
+}
+
+static inline void ll_dir_chain_fini(struct ll_dir_chain *chain)
+{
+}
+
extern const struct file_operations ll_dir_operations;
extern const struct inode_operations ll_dir_inode_operations;
#ifdef HAVE_DIR_CONTEXT
-int ll_dir_read(struct inode *inode, struct md_op_data *op_data,
+int ll_dir_read(struct inode *inode, __u64 *pos, struct md_op_data *op_data,
struct dir_context *ctx);
#else
-int ll_dir_read(struct inode *inode, struct md_op_data *op_data,
+int ll_dir_read(struct inode *inode, __u64 *pos, struct md_op_data *op_data,
void *cookie, filldir_t filldir);
#endif
int ll_get_mdt_idx(struct inode *inode);
int ll_get_mdt_idx_by_fid(struct ll_sb_info *sbi, const struct lu_fid *fid);
+struct page *ll_get_dir_page(struct inode *dir, struct md_op_data *op_data,
+ __u64 offset, struct ll_dir_chain *chain);
+void ll_release_page(struct inode *inode, struct page *page, bool remove);
-struct lu_dirent *ll_dir_entry_start(struct inode *dir,
- struct md_op_data *op_data,
- struct page **ppage);
-
-struct lu_dirent *ll_dir_entry_next(struct inode *dir,
- struct md_op_data *op_data,
- struct lu_dirent *ent,
- struct page **ppage);
/* llite/namei.c */
extern const struct inode_operations ll_special_inode_operations;
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_init(struct file *file, struct page *vmpage);
-void ll_cl_fini(struct ll_cl_context *lcc);
+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;
int ll_fsync(struct file *file, struct dentry *dentry, int data);
#endif
int ll_merge_lvb(const struct lu_env *env, struct inode *inode);
-int ll_fid2path(struct inode *inode, void *arg);
+int ll_fid2path(struct inode *inode, void __user *arg);
int ll_data_version(struct inode *inode, __u64 *data_version, int flags);
int ll_hsm_release(struct inode *inode);
int ll_prep_inode(struct inode **inode, struct ptlrpc_request *req,
struct super_block *, struct lookup_intent *);
void lustre_dump_dentry(struct dentry *, int recur);
-int ll_obd_statfs(struct inode *inode, void *arg);
+int ll_obd_statfs(struct inode *inode, void __user *arg);
int ll_get_max_mdsize(struct ll_sb_info *sbi, int *max_mdsize);
int ll_get_default_mdsize(struct ll_sb_info *sbi, int *default_mdsize);
int ll_get_max_cookiesize(struct ll_sb_info *sbi, int *max_cookiesize);
int ll_get_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);
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;
* fault API used bitflags for return code.
*/
unsigned int ft_flags;
+ /**
+ * check that flags are from filemap_fault
+ */
+ bool ft_flags_valid;
} fault;
} fault;
} u;
};
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;
+ 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 {
unsigned int sai_skip_hidden;/* skipped hidden dentry count */
unsigned int sai_ls_all:1, /* "ls -al", do stat-ahead for
* hidden entries */
- sai_agl_valid:1;/* AGL is valid for the dir */
+ sai_agl_valid:1,/* AGL is valid for the dir */
+ sai_in_readpage:1;/* statahead is in readdir()*/
wait_queue_head_t sai_waitq; /* stat-ahead wait queue */
struct ptlrpc_thread sai_thread; /* stat-ahead thread */
struct ptlrpc_thread sai_agl_thread; /* AGL thread */
- struct list_head sai_entries; /* entry list */
- struct list_head sai_entries_received; /* entries returned */
- struct list_head sai_entries_stated; /* entries stated */
- struct list_head sai_entries_agl; /* AGL entries to be sent */
+ struct list_head sai_interim_entries; /* entries which got async
+ * stat reply, but not
+ * instantiated */
+ struct list_head sai_entries; /* completed entries */
+ struct list_head sai_agls; /* AGLs to be sent */
struct list_head sai_cache[LL_SA_CACHE_SIZE];
spinlock_t sai_cache_lock[LL_SA_CACHE_SIZE];
atomic_t sai_cache_count; /* entry count in cache */
int do_statahead_enter(struct inode *dir, struct dentry **dentry,
int only_unplug);
-void ll_stop_statahead(struct inode *dir, void *key);
+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)
{
ldd->lld_sa_generation = sai->sai_generation;
}
-static inline int
-d_need_statahead(struct inode *dir, struct dentry *dentryp)
+static inline bool
+dentry_need_statahead(struct inode *dir, struct dentry *dentry)
{
struct ll_inode_info *lli;
struct ll_dentry_data *ldd;
if (ll_i2sbi(dir)->ll_sa_max == 0)
- return -EAGAIN;
+ return false;
lli = ll_i2info(dir);
+
+ /* statahead is not allowed for this dir, there may be three causes:
+ * 1. dir is not opened.
+ * 2. statahead hit ratio is too low.
+ * 3. previous stat started statahead thread failed. */
+ if (!lli->lli_sa_enabled)
+ return false;
+
/* not the same process, don't statahead */
if (lli->lli_opendir_pid != current_pid())
- return -EAGAIN;
+ return false;
- /* statahead has been stopped */
- if (lli->lli_opendir_key == NULL)
- return -EAGAIN;
-
- ldd = ll_d2d(dentryp);
+ ldd = ll_d2d(dentry);
/*
* When stats a dentry, the system trigger more than once "revalidate"
* or "lookup", for "getattr", for "getxattr", and maybe for others.
*/
if (ldd && lli->lli_sai &&
ldd->lld_sa_generation == lli->lli_sai->sai_generation)
- return -EAGAIN;
+ return false;
- return 1;
+ return true;
}
static inline int
ll_statahead_enter(struct inode *dir, struct dentry **dentryp, int only_unplug)
{
- int ret;
-
- ret = d_need_statahead(dir, *dentryp);
- if (ret <= 0)
- return ret;
+ if (!dentry_need_statahead(dir, *dentryp))
+ return -EAGAIN;
return do_statahead_enter(dir, dentryp, only_unplug);
}
/* llite ioctl register support rountine */
-#ifdef __KERNEL__
enum llioc_iter {
LLIOC_CONT = 0,
LLIOC_STOP
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
{
CDEBUG(D_DENTRY, "invalidate dentry %.*s (%p) parent %p inode %p "
"refc %d\n", dentry->d_name.len, dentry->d_name.name, dentry,
- dentry->d_parent, dentry->d_inode, d_count(dentry));
+ dentry->d_parent, dentry->d_inode, ll_d_count(dentry));
spin_lock_nested(&dentry->d_lock,
nested ? DENTRY_D_LOCK_NESTED : DENTRY_D_LOCK_NORMAL);
__d_lustre_invalidate(dentry);
- if (d_count(dentry) == 0)
+ 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)
+#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 */
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 */