* Copyright (c) 2003, 2010, Oracle and/or its affiliates. All rights reserved.
* Use is subject to license terms.
*
- * Copyright (c) 2011, 2014, Intel Corporation.
+ * Copyright (c) 2011, 2015, Intel Corporation.
*/
/*
* This file is part of Lustre, http://www.lustre.org/
unsigned long lg_gid;
};
-enum lli_flags {
- /* File data is modified. */
- LLIF_DATA_MODIFIED = 1 << 0,
- /* File is being restored */
- LLIF_FILE_RESTORING = 1 << 1,
- /* Xattr cache is attached to the file */
- LLIF_XATTR_CACHE = 1 << 2,
-};
-
struct ll_inode_info {
__u32 lli_inode_magic;
- __u32 lli_flags;
-
spinlock_t lli_lock;
+
+ volatile unsigned long lli_flags;
struct posix_acl *lli_posix_acl;
struct hlist_head *lli_remote_perms;
/* 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
struct {
struct mutex lli_size_mutex;
char *lli_symlink_name;
- __u64 lli_maxbytes;
/*
* struct rw_semaphore {
* signed long count; // align d.d_def_acl
spin_unlock(&lli->lli_layout_lock);
}
+enum ll_file_flags {
+ /* File data is modified. */
+ LLIF_DATA_MODIFIED = 0,
+ /* File is being restored */
+ LLIF_FILE_RESTORING = 1,
+ /* Xattr cache is attached to the file */
+ LLIF_XATTR_CACHE = 2,
+};
+
+static inline void ll_file_set_flag(struct ll_inode_info *lli,
+ enum ll_file_flags flag)
+{
+ set_bit(flag, &lli->lli_flags);
+}
+
+static inline void ll_file_clear_flag(struct ll_inode_info *lli,
+ enum ll_file_flags flag)
+{
+ clear_bit(flag, &lli->lli_flags);
+}
+
+static inline bool ll_file_test_flag(struct ll_inode_info *lli,
+ enum ll_file_flags flag)
+{
+ return test_bit(flag, &lli->lli_flags);
+}
+
+static inline bool ll_file_test_and_clear_flag(struct ll_inode_info *lli,
+ enum ll_file_flags flag)
+{
+ return test_and_clear_bit(flag, &lli->lli_flags);
+}
+
int ll_xattr_cache_destroy(struct inode *inode);
int ll_xattr_cache_get(struct inode *inode,
size_t size,
__u64 valid);
+int ll_init_security(struct dentry *dentry,
+ struct inode *inode,
+ struct inode *dir);
+
/*
* Locking to guarantee consistency of non-atomic updates to long long i_size,
* consistency between file size and KMS.
return container_of(inode, struct ll_inode_info, lli_vfs_inode);
}
-/* default to about 40meg of readahead on a given system. That much tied
- * up in 512k readahead requests serviced at 40ms each is about 1GB/s. */
-#define SBI_DEFAULT_READAHEAD_MAX (40UL << (20 - PAGE_CACHE_SHIFT))
+/* default to about 64M of readahead on a given system. */
+#define SBI_DEFAULT_READAHEAD_MAX (64UL << (20 - PAGE_CACHE_SHIFT))
/* default to read-ahead full files smaller than 2MB on the second read */
-#define SBI_DEFAULT_READAHEAD_WHOLE_MAX (2UL << (20 - PAGE_CACHE_SHIFT))
+#define SBI_DEFAULT_READAHEAD_WHOLE_MAX (2UL << (20 - PAGE_CACHE_SHIFT))
enum ra_stat {
RA_STAT_HIT = 0,
* counted by page index.
*/
struct ra_io_arg {
- unsigned long ria_start; /* start offset of read-ahead*/
- unsigned long ria_end; /* end offset of read-ahead*/
- /* If stride read pattern is detected, ria_stoff means where
- * stride read is started. Note: for normal read-ahead, the
- * value here is meaningless, and also it will not be accessed*/
- pgoff_t ria_stoff;
- /* ria_length and ria_pages are the length and pages length in the
- * stride I/O mode. And they will also be used to check whether
- * it is stride I/O read-ahead in the read-ahead pages*/
- unsigned long ria_length;
- unsigned long ria_pages;
+ unsigned long ria_start; /* start offset of read-ahead*/
+ unsigned long ria_end; /* end offset of read-ahead*/
+ unsigned long ria_reserved; /* reserved pages for read-ahead */
+ unsigned long ria_end_min; /* minimum end to cover current read */
+ bool ria_eof; /* reach end of file */
+ /* If stride read pattern is detected, ria_stoff means where
+ * stride read is started. Note: for normal read-ahead, the
+ * value here is meaningless, and also it will not be accessed*/
+ pgoff_t ria_stoff;
+ /* ria_length and ria_pages are the length and pages length in the
+ * stride I/O mode. And they will also be used to check whether
+ * it is stride I/O read-ahead in the read-ahead pages*/
+ unsigned long ria_length;
+ unsigned long ria_pages;
};
/* LL_HIST_MAX=32 causes an overflow */
#define LL_SBI_USER_XATTR 0x08 /* support user xattr */
#define LL_SBI_ACL 0x10 /* support ACL */
#define LL_SBI_RMT_CLIENT 0x40 /* remote client */
-#define LL_SBI_MDS_CAPA 0x80 /* support mds capa */
-#define LL_SBI_OSS_CAPA 0x100 /* support oss capa */
+#define LL_SBI_MDS_CAPA 0x80 /* support mds capa, obsolete */
+#define LL_SBI_OSS_CAPA 0x100 /* support oss capa, obsolete */
#define LL_SBI_LOCALFLOCK 0x200 /* Local flocks support by kernel */
#define LL_SBI_LRU_RESIZE 0x400 /* lru resize support */
#define LL_SBI_LAZYSTATFS 0x800 /* lazystatfs mount option */
#define LL_SBI_USER_FID2PATH 0x40000 /* allow fid2path by unprivileged users */
#define LL_SBI_XATTR_CACHE 0x80000 /* support for xattr cache */
#define LL_SBI_NOROOTSQUASH 0x100000 /* do not apply root squash */
+#define LL_SBI_ALWAYS_PING 0x200000 /* always ping even if server
+ * suppress_pings */
#define LL_SBI_FLAGS { \
"nolck", \
"user_fid2path",\
"xattr_cache", \
"norootsquash", \
+ "always_ping", \
}
#define RCE_HASHES 32
};
struct ll_sb_info {
- struct list_head ll_list;
/* this protects pglist and ra_info. It isn't safe to
* grab from interrupt contexts */
spinlock_t ll_lock;
unsigned int ll_namelen;
struct file_operations *ll_fop;
- /* =0 - hold lock over whole read/write
- * >0 - max. chunk to be read/written w/o lock re-acquiring */
- unsigned long ll_max_rw_chunk;
unsigned int ll_md_brw_pages; /* readdir pages per RPC */
struct lu_site *ll_site;
struct root_squash_info ll_squash;
};
-#define LL_DEFAULT_MAX_RW_CHUNK (32 * 1024 * 1024)
-
/*
* per file-descriptor read-ahead data.
*/
* PTLRPC_MAX_BRW_PAGES chunks up to ->ra_max_pages.
*/
unsigned long ras_window_start, ras_window_len;
+ /*
+ * Optimal RPC size. It decides how many pages will be sent
+ * for each read-ahead.
+ */
+ unsigned long ras_rpc_size;
/*
* Where next read-ahead should start at. This lies within read-ahead
* window. Read-ahead window is read in pieces rather than at once
struct list_head fd_lccs; /* list of ll_cl_context */
};
-struct lov_stripe_md;
-
extern spinlock_t inode_lock;
extern struct proc_dir_entry *proc_lustre_fs_root;
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,
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_noflock;
extern struct inode_operations ll_file_inode_operations;
extern int ll_have_md_lock(struct inode *inode, __u64 *bits,
- ldlm_mode_t l_req_mode);
-extern ldlm_mode_t ll_take_md_lock(struct inode *inode, __u64 bits,
- struct lustre_handle *lockh, __u64 flags,
- ldlm_mode_t mode);
+ enum ldlm_mode l_req_mode);
+extern enum ldlm_mode ll_take_md_lock(struct inode *inode, __u64 bits,
+ struct lustre_handle *lockh, __u64 flags,
+ enum ldlm_mode mode);
int ll_file_open(struct inode *inode, struct file *file);
int ll_file_release(struct inode *inode, struct file *file);
int ll_release_openhandle(struct dentry *, struct lookup_intent *);
int ll_md_real_close(struct inode *inode, fmode_t fmode);
-void ll_pack_inode2opdata(struct inode *inode, struct md_op_data *op_data,
- struct lustre_handle *fh);
extern void ll_rw_stats_tally(struct ll_sb_info *sbi, pid_t pid,
struct ll_file_data *file, loff_t pos,
size_t count, int rw);
int ll_migrate(struct inode *parent, struct file *file, int mdtidx,
const char *name, int namelen);
int ll_get_fid_by_name(struct inode *parent, const char *name,
- int namelen, struct lu_fid *fid);
+ int namelen, struct lu_fid *fid, struct inode **inode);
#ifdef HAVE_GENERIC_PERMISSION_4ARGS
int ll_inode_permission(struct inode *inode, int mask, unsigned int flags);
#else
int ll_fid2path(struct inode *inode, void __user *arg);
int ll_data_version(struct inode *inode, __u64 *data_version, int flags);
int ll_hsm_release(struct inode *inode);
+int ll_hsm_state_set(struct inode *inode, struct hsm_state_set *hss);
/* llite/dcache.c */
void ll_put_super(struct super_block *sb);
void ll_kill_super(struct super_block *sb);
struct inode *ll_inode_from_resource_lock(struct ldlm_lock *lock);
+void ll_dir_clear_lsm_md(struct inode *inode);
void ll_clear_inode(struct inode *inode);
int ll_setattr_raw(struct dentry *dentry, struct iattr *attr, bool hsm_import);
int ll_setattr(struct dentry *de, struct iattr *attr);
int ll_get_max_mdsize(struct ll_sb_info *sbi, int *max_mdsize);
int ll_get_default_mdsize(struct ll_sb_info *sbi, int *default_mdsize);
int ll_set_default_mdsize(struct ll_sb_info *sbi, int default_mdsize);
-int ll_get_max_cookiesize(struct ll_sb_info *sbi, int *max_cookiesize);
-int ll_get_default_cookiesize(struct ll_sb_info *sbi, int *default_cookiesize);
int ll_process_config(struct lustre_cfg *lcfg);
enum {
union {
struct {
struct kiocb *via_iocb;
- struct iovec *via_iov;
- unsigned long via_nrsegs;
+ struct iov_iter *via_iter;
} normal;
struct {
struct pipe_inode_info *via_pipe;
int ll_teardown_mmaps(struct address_space *mapping, __u64 first, __u64 last);
int ll_file_mmap(struct file * file, struct vm_area_struct * vma);
-void policy_from_vma(ldlm_policy_data_t *policy,
- struct vm_area_struct *vma, unsigned long addr, size_t count);
+void policy_from_vma(union ldlm_policy_data *policy, struct vm_area_struct *vma,
+ unsigned long addr, size_t count);
struct vm_area_struct *our_vma(struct mm_struct *mm, unsigned long addr,
size_t count);
return fid;
}
-static inline __u64 ll_file_maxbytes(struct inode *inode)
+static inline loff_t ll_file_maxbytes(struct inode *inode)
{
- return ll_i2info(inode)->lli_maxbytes;
+ struct cl_object *obj = ll_i2info(inode)->lli_clob;
+
+ if (obj == NULL)
+ return MAX_LFS_FILESIZE;
+
+ return min_t(loff_t, cl_object_maxbytes(obj), MAX_LFS_FILESIZE);
}
/* llite/xattr.c */
int ll_update_remote_perm(struct inode *inode, struct mdt_remote_perm *perm);
int lustre_check_remote_perm(struct inode *inode, int mask);
-/* llite/llite_capa.c */
-extern struct timer_list ll_capa_timer;
-
-int ll_capa_thread_start(void);
-void ll_capa_thread_stop(void);
-void ll_capa_timer_callback(unsigned long unused);
-
-struct obd_capa *ll_add_capa(struct inode *inode, struct obd_capa *ocapa);
-
-void ll_capa_open(struct inode *inode);
-void ll_capa_close(struct inode *inode);
-
-struct obd_capa *ll_mdscapa_get(struct inode *inode);
-struct obd_capa *ll_osscapa_get(struct inode *inode, __u64 opc);
-
-void ll_truncate_free_capa(struct obd_capa *ocapa);
-void ll_clear_inode_capas(struct inode *inode);
-void ll_print_capa_stat(struct ll_sb_info *sbi);
-
/**
* 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 ras_update_flags {
+ LL_RAS_HIT = 0x1,
+ LL_RAS_MMAP = 0x2
+};
void ll_ra_count_put(struct ll_sb_info *sbi, unsigned long len);
void ll_ra_stats_inc(struct inode *inode, enum ra_stat which);
void *ll_iocontrol_register(llioc_callback_t cb, int count, unsigned int *cmd);
void ll_iocontrol_unregister(void *magic);
-struct obd_capa *cl_capa_lookup(struct inode *inode, enum cl_req_type crt);
-
int cl_sync_file_range(struct inode *inode, loff_t start, loff_t end,
enum cl_fsync_mode mode, int ignore_layout);
int ldp_nr;
};
-static inline void cl_stats_tally(struct cl_device *dev, enum cl_req_type crt,
- int rc)
-{
- int opc = (crt == CRT_READ) ? LPROC_LL_OSC_READ :
- LPROC_LL_OSC_WRITE;
-
- ll_stats_ops_tally(ll_s2sbi(cl2vvp_dev(dev)->vdv_sb), opc, rc);
-}
-
extern ssize_t ll_direct_rw_pages(const struct lu_env *env, struct cl_io *io,
int rw, struct inode *inode,
struct ll_dio_pages *pv);
static inline int ll_file_nolock(const struct file *file)
{
struct ll_file_data *fd = LUSTRE_FPRIVATE(file);
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file->f_path.dentry->d_inode;
LASSERT(fd != NULL);
return ((fd->fd_flags & LL_FILE_IGNORE_LOCK) ||
static inline void ll_set_lock_data(struct obd_export *exp, struct inode *inode,
struct lookup_intent *it, __u64 *bits)
{
- if (!it->d.lustre.it_lock_set) {
+ if (!it->it_lock_set) {
struct lustre_handle handle;
/* If this inode is a remote object, it will get two
* UPDATE|PERM lock. The inode will be attched to both
* LOOKUP and PERM locks, so revoking either locks will
* case the dcache being cleared */
- if (it->d.lustre.it_remote_lock_mode) {
- handle.cookie = it->d.lustre.it_remote_lock_handle;
+ if (it->it_remote_lock_mode) {
+ handle.cookie = it->it_remote_lock_handle;
CDEBUG(D_DLMTRACE, "setting l_data to inode "DFID
"(%p) for remote lock "LPX64"\n",
PFID(ll_inode2fid(inode)), inode,
md_set_lock_data(exp, &handle.cookie, inode, NULL);
}
- handle.cookie = it->d.lustre.it_lock_handle;
+ handle.cookie = it->it_lock_handle;
CDEBUG(D_DLMTRACE, "setting l_data to inode "DFID"(%p)"
" for lock "LPX64"\n",
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;
+ &it->it_lock_bits);
+ it->it_lock_set = 1;
}
if (bits != NULL)
- *bits = it->d.lustre.it_lock_bits;
+ *bits = it->it_lock_bits;
}
static inline void ll_lock_dcache(struct inode *inode)
spin_lock_nested(&dentry->d_lock,
nested ? DENTRY_D_LOCK_NESTED : DENTRY_D_LOCK_NORMAL);
__d_lustre_invalidate(dentry);
- if (ll_d_count(dentry) == 0)
+ /*
+ * We should be careful about dentries created by d_obtain_alias().
+ * These dentries are not put in the dentry tree, instead they are
+ * linked to sb->s_anon through dentry->d_hash.
+ * shrink_dcache_for_umount() shrinks the tree and sb->s_anon list.
+ * If we unhashed such a dentry, unmount would not be able to find
+ * it and busy inodes would be reported.
+ */
+ if (ll_d_count(dentry) == 0 && !(dentry->d_flags & DCACHE_DISCONNECTED))
__d_drop(dentry);
spin_unlock(&dentry->d_lock);
}
spin_unlock(&dentry->d_lock);
}
-#if LUSTRE_VERSION_CODE < OBD_OCD_VERSION(2, 7, 53, 0)
-/* Compatibility for old (1.8) compiled userspace quota code */
-struct if_quotactl_18 {
- __u32 qc_cmd;
- __u32 qc_type;
- __u32 qc_id;
- __u32 qc_stat;
- struct obd_dqinfo qc_dqinfo;
- struct obd_dqblk qc_dqblk;
- char obd_type[16];
- struct obd_uuid obd_uuid;
-};
-#define LL_IOC_QUOTACTL_18 _IOWR('f', 162, struct if_quotactl_18 *)
-/* End compatibility for old (1.8) compiled userspace quota code */
-#endif /* LUSTRE_VERSION_CODE < OBD_OCD_VERSION(2, 7, 53, 0) */
-
int ll_layout_conf(struct inode *inode, const struct cl_object_conf *conf);
int ll_layout_refresh(struct inode *inode, __u32 *gen);
int ll_layout_restore(struct inode *inode, loff_t start, __u64 length);
/* lcommon_cl.c */
int cl_setattr_ost(struct cl_object *obj, const struct iattr *attr,
- unsigned int attr_flags, struct obd_capa *capa);
+ unsigned int attr_flags);
extern struct lu_env *cl_inode_fini_env;
-extern int cl_inode_fini_refcheck;
+extern __u16 cl_inode_fini_refcheck;
int cl_file_inode_init(struct inode *inode, struct lustre_md *md);
void cl_inode_fini(struct inode *inode);