* 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/
struct lookup_intent *lld_it;
unsigned int lld_sa_generation;
unsigned int lld_invalid:1;
+ unsigned int lld_nfs_dentry:1;
struct rcu_head lld_rcu_head;
};
#define LLI_INODE_MAGIC 0x111d0de5
#define LLI_INODE_DEAD 0xdeadd00d
-/* remote client permission cache */
-#define REMOTE_PERM_HASHSIZE 16
-
struct ll_getname_data {
#ifdef HAVE_DIR_CONTEXT
struct dir_context ctx;
int lgd_found; /* inode matched? */
};
-/* llite setxid/access permission for user on remote client */
-struct ll_remote_perm {
- struct hlist_node lrp_list;
- uid_t lrp_uid;
- gid_t lrp_gid;
- uid_t lrp_fsuid;
- gid_t lrp_fsgid;
- int lrp_access_perm; /* MAY_READ/WRITE/EXEC, this
- is access permission with
- lrp_fsuid/lrp_fsgid. */
-};
-
struct ll_grouplock {
struct lu_env *lg_env;
struct cl_io *lg_io;
volatile unsigned long lli_flags;
struct posix_acl *lli_posix_acl;
- struct hlist_head *lli_remote_perms;
- struct mutex lli_rmtperm_mutex;
-
/* identifying fields for both metadata and data stacks. */
struct lu_fid lli_fid;
/* master inode fid for stripe directory */
struct lu_fid lli_pfid;
- /* open count currently used by capability only, indicate whether
- * capability needs renewal */
- atomic_t lli_open_count;
- 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;
size_t size,
__u64 valid);
-int ll_init_security(struct dentry *dentry,
- struct inode *inode,
- struct inode *dir);
+int ll_dentry_init_security(struct dentry *dentry, int mode, struct qstr *name,
+ const char **secctx_name, void **secctx,
+ __u32 *secctx_size);
+int ll_inode_init_security(struct dentry *dentry, struct inode *inode,
+ struct inode *dir);
/*
* Locking to guarantee consistency of non-atomic updates to long long i_size,
return container_of(inode, struct ll_inode_info, lli_vfs_inode);
}
-/* default to about 40meg of readahead on a given system. That much tied
- * up in 512k readahead requests serviced at 40ms each is about 1GB/s. */
-#define SBI_DEFAULT_READAHEAD_MAX (40UL << (20 - PAGE_CACHE_SHIFT))
+/* default to about 64M of readahead on a given system. */
+#define SBI_DEFAULT_READAHEAD_MAX (64UL << (20 - PAGE_SHIFT))
/* default to read-ahead full files smaller than 2MB on the second read */
-#define SBI_DEFAULT_READAHEAD_WHOLE_MAX (2UL << (20 - PAGE_CACHE_SHIFT))
+#define SBI_DEFAULT_READAHEAD_WHOLE_MAX (2UL << (20 - PAGE_SHIFT))
enum ra_stat {
RA_STAT_HIT = 0,
* 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_FLOCK 0x04
#define LL_SBI_USER_XATTR 0x08 /* support user xattr */
#define LL_SBI_ACL 0x10 /* support ACL */
-#define LL_SBI_RMT_CLIENT 0x40 /* remote client */
+/* LL_SBI_RMT_CLIENT 0x40 remote client */
#define LL_SBI_MDS_CAPA 0x80 /* support mds capa, obsolete */
#define LL_SBI_OSS_CAPA 0x100 /* support oss capa, obsolete */
#define LL_SBI_LOCALFLOCK 0x200 /* Local flocks support by kernel */
#define LL_SBI_USER_FID2PATH 0x40000 /* allow fid2path by unprivileged users */
#define LL_SBI_XATTR_CACHE 0x80000 /* support for xattr cache */
#define LL_SBI_NOROOTSQUASH 0x100000 /* do not apply root squash */
+#define LL_SBI_ALWAYS_PING 0x200000 /* always ping even if server
+ * suppress_pings */
+#define LL_SBI_FAST_READ 0x400000 /* fast read support */
+#define LL_SBI_FILE_SECCTX 0x800000 /* set file security context at create */
#define LL_SBI_FLAGS { \
"nolck", \
"user_xattr", \
"acl", \
"???", \
- "rmt_client", \
+ "???", \
"mds_capa", \
"oss_capa", \
"flock", \
"user_fid2path",\
"xattr_cache", \
"norootsquash", \
+ "always_ping", \
+ "fast_read", \
+ "file_secctx", \
}
-#define RCE_HASHES 32
-
-struct rmtacl_ctl_entry {
- struct list_head rce_list;
- pid_t rce_key; /* hash key */
- int rce_ops; /* acl operation type */
-};
-
-struct rmtacl_ctl_table {
- spinlock_t rct_lock;
- struct list_head rct_entries[RCE_HASHES];
-};
-
-#define EE_HASHES 32
-
-struct eacl_entry {
- struct list_head ee_list;
- pid_t ee_key; /* hash key */
- struct lu_fid ee_fid;
- int ee_type; /* ACL type for ACCESS or DEFAULT */
- ext_acl_xattr_header *ee_acl;
-};
-
-struct eacl_table {
- spinlock_t et_lock;
- struct list_head et_entries[EE_HASHES];
-};
-
-
/* This is embedded into llite super-blocks to keep track of connect
* flags (capabilities) supported by all imports given mount is
* connected to. */
};
struct 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;
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;
- /*please don't ask -p*/
- struct list_head ll_orphan_dentry_list;
-
struct lprocfs_stats *ll_stats; /* lprocfs stats counter */
/* Used to track "unstable" pages on a client, and maintain a
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;
};
* 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 */
};
-extern spinlock_t inode_lock;
-
extern struct proc_dir_entry *proc_lustre_fs_root;
static inline struct inode *ll_info2i(struct ll_inode_info *lli)
#if BITS_PER_LONG == 32
return 1;
#elif defined(CONFIG_COMPAT)
- return unlikely(is_compat_task() || (sbi->ll_flags & LL_SBI_32BIT_API));
+ return unlikely(in_compat_syscall() || (sbi->ll_flags & LL_SBI_32BIT_API));
#else
return unlikely(sbi->ll_flags & LL_SBI_32BIT_API);
#endif
}
+static inline bool ll_sbi_has_fast_read(struct ll_sb_info *sbi)
+{
+ return !!(sbi->ll_flags & LL_SBI_FAST_READ);
+}
+
void ll_ras_enter(struct file *f);
/* llite/lcommon_misc.c */
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_FAULT,
+ LPROC_LL_MKWRITE,
LPROC_LL_LLSEEK,
LPROC_LL_FSYNC,
LPROC_LL_READDIR,
int ll_readpage(struct file *file, struct page *page);
void ll_readahead_init(struct inode *inode, struct ll_readahead_state *ras);
int vvp_io_write_commit(const struct lu_env *env, struct cl_io *io);
-struct ll_cl_context *ll_cl_find(struct file *file);
-void ll_cl_add(struct file *file, const struct lu_env *env, struct cl_io *io);
+
+enum lcc_type;
+void ll_cl_add(struct file *file, const struct lu_env *env, struct cl_io *io,
+ enum lcc_type type);
void ll_cl_remove(struct file *file, const struct lu_env *env);
+struct ll_cl_context *ll_cl_find(struct file *file);
-#ifndef MS_HAS_NEW_AOPS
extern const struct address_space_operations ll_aops;
-#else
-extern const struct address_space_operations_ext ll_aops;
-#endif
/* llite/file.c */
extern struct file_operations ll_file_operations;
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_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
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);
} u;
};
+enum lcc_type {
+ LCC_RW = 1,
+ LCC_MMAP
+};
+
struct ll_cl_context {
struct list_head lcc_list;
void *lcc_cookie;
const struct lu_env *lcc_env;
struct cl_io *lcc_io;
struct cl_page *lcc_page;
+ enum lcc_type lcc_type;
};
struct ll_thread_info {
- struct iovec lti_local_iov;
+ struct iov_iter lti_iter;
struct vvp_io_args lti_args;
struct ra_io_arg lti_ria;
struct kiocb lti_kiocb;
int ll_teardown_mmaps(struct address_space *mapping, __u64 first, __u64 last);
int ll_file_mmap(struct file * file, struct vm_area_struct * vma);
-void policy_from_vma(ldlm_policy_data_t *policy,
- struct vm_area_struct *vma, unsigned long addr, size_t count);
+void policy_from_vma(union ldlm_policy_data *policy, struct vm_area_struct *vma,
+ unsigned long addr, size_t count);
struct vm_area_struct *our_vma(struct mm_struct *mm, unsigned long addr,
size_t count);
static inline void ll_invalidate_page(struct page *vmpage)
{
struct address_space *mapping = vmpage->mapping;
- loff_t offset = vmpage->index << PAGE_CACHE_SHIFT;
+ loff_t offset = vmpage->index << PAGE_SHIFT;
LASSERT(PageLocked(vmpage));
if (mapping == NULL)
* truncate_complete_page() calls
* a_ops->invalidatepage()->cl_page_delete()->vvp_page_delete().
*/
- ll_teardown_mmaps(mapping, offset, offset + PAGE_CACHE_SIZE);
+ ll_teardown_mmaps(mapping, offset, offset + PAGE_SIZE);
truncate_complete_page(mapping, vmpage);
}
ssize_t ll_listxattr(struct dentry *dentry, char *buffer, size_t size);
int ll_removexattr(struct dentry *dentry, const char *name);
-/* llite/remote_perm.c */
-extern struct kmem_cache *ll_remote_perm_cachep;
-extern struct kmem_cache *ll_rmtperm_hash_cachep;
-
-void free_rmtperm_hash(struct hlist_head *hash);
-int ll_update_remote_perm(struct inode *inode, struct mdt_remote_perm *perm);
-int lustre_check_remote_perm(struct inode *inode, int mask);
-
/**
* 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);
-/* llite/llite_rmtacl.c */
-#ifdef CONFIG_FS_POSIX_ACL
-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);
-void rct_init(struct rmtacl_ctl_table *rct);
-void rct_fini(struct rmtacl_ctl_table *rct);
-
-void ee_free(struct eacl_entry *ee);
-int ee_add(struct eacl_table *et, pid_t key, struct lu_fid *fid, int type,
- ext_acl_xattr_header *header);
-struct eacl_entry *et_search_del(struct eacl_table *et, pid_t key,
- struct lu_fid *fid, int type);
-void et_search_free(struct eacl_table *et, pid_t key);
-void et_init(struct eacl_table *et);
-void et_fini(struct eacl_table *et);
-#endif
-
/* statahead.c */
#define LL_SA_RPC_MIN 2
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_path.dentry->d_inode;
+ struct inode *inode = file_inode((struct file *)file);
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",
+ "(%p) for remote lock %#llx\n",
PFID(ll_inode2fid(inode)), inode,
handle.cookie);
- md_set_lock_data(exp, &handle.cookie, inode, NULL);
+ md_set_lock_data(exp, &handle, inode, NULL);
}
- handle.cookie = it->d.lustre.it_lock_handle;
+ handle.cookie = it->it_lock_handle;
CDEBUG(D_DLMTRACE, "setting l_data to inode "DFID"(%p)"
- " for lock "LPX64"\n",
+ " for lock %#llx\n",
PFID(ll_inode2fid(inode)), inode, handle.cookie);
- md_set_lock_data(exp, &handle.cookie, inode,
- &it->d.lustre.it_lock_bits);
- it->d.lustre.it_lock_set = 1;
+ md_set_lock_data(exp, &handle, inode, &it->it_lock_bits);
+ it->it_lock_set = 1;
}
if (bits != NULL)
- *bits = it->d.lustre.it_lock_bits;
+ *bits = it->it_lock_bits;
}
static inline void ll_lock_dcache(struct inode *inode)
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);
u64 cl_fid_build_ino(const struct lu_fid *fid, int api32);
u32 cl_fid_build_gen(const struct lu_fid *fid);
+#ifndef HAVE_IOV_ITER_TRUNCATE
+static inline void iov_iter_truncate(struct iov_iter *i, u64 count)
+{
+ if (i->count > count)
+ i->count = count;
+}
+#endif
+
+#ifndef HAVE_IS_SXID
+static inline bool is_sxid(umode_t mode)
+{
+ return (mode & S_ISUID) || ((mode & S_ISGID) && (mode & S_IXGRP));
+}
+#endif
+
+#ifndef IS_NOSEC
+#define IS_NOSEC(inode) (!is_sxid(inode->i_mode))
+#endif
+
+#ifndef HAVE_FILE_OPERATIONS_READ_WRITE_ITER
+static inline void iov_iter_reexpand(struct iov_iter *i, size_t count)
+{
+ i->count = count;
+}
+
+static inline struct iovec iov_iter_iovec(const struct iov_iter *iter)
+{
+ return (struct iovec) {
+ .iov_base = iter->iov->iov_base + iter->iov_offset,
+ .iov_len = min(iter->count,
+ iter->iov->iov_len - iter->iov_offset),
+ };
+}
+
+#define iov_for_each(iov, iter, start) \
+ for (iter = (start); \
+ (iter).count && ((iov = iov_iter_iovec(&(iter))), 1); \
+ iov_iter_advance(&(iter), (iov).iov_len))
+
+static inline ssize_t
+generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+ struct iovec iov;
+ struct iov_iter i;
+ ssize_t bytes = 0;
+
+ iov_for_each(iov, i, *iter) {
+ ssize_t res;
+
+ res = generic_file_aio_read(iocb, &iov, 1, iocb->ki_pos);
+ if (res <= 0) {
+ if (bytes == 0)
+ bytes = res;
+ break;
+ }
+
+ bytes += res;
+ if (res < iov.iov_len)
+ break;
+ }
+
+ if (bytes > 0)
+ iov_iter_advance(iter, bytes);
+ return bytes;
+}
+
+static inline ssize_t
+__generic_file_write_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+ struct iovec iov;
+ struct iov_iter i;
+ ssize_t bytes = 0;
+
+ iov_for_each(iov, i, *iter) {
+ ssize_t res;
+
+ res = __generic_file_aio_write(iocb, &iov, 1, &iocb->ki_pos);
+ if (res <= 0) {
+ if (bytes == 0)
+ bytes = res;
+ break;
+ }
+
+ bytes += res;
+ if (res < iov.iov_len)
+ break;
+ }
+
+ if (bytes > 0)
+ iov_iter_advance(iter, bytes);
+ return bytes;
+}
+#endif /* HAVE_FILE_OPERATIONS_READ_WRITE_ITER */
#endif /* LLITE_INTERNAL_H */