nfs_inc_stats(inode, NFSIOS_VFSLOCK);
- /* No mandatory locks over NFS */
- if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK)
- goto out_err;
-
+ if (fl->fl_flags & FL_RECLAIM)
+ return -ENOGRACE;
+
if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FCNTL)
is_local = 1;
trace_nfsd_clid_admin_expired(&clp->cl_clientid);
- spin_lock(&clp->cl_lock);
+ spin_lock(&nn->client_lock);
clp->cl_time = 0;
- spin_unlock(&clp->cl_lock);
+ spin_unlock(&nn->client_lock);
wait_event(expiry_wq, atomic_read(&clp->cl_rpc_users) == 0);
spin_lock(&nn->client_lock);
NFS4_SHARE_DENY_READ);
}
-/*
- * Allow READ/WRITE during grace period on recovered state only for files
- * that are not able to provide mandatory locking.
- */
-static inline int
-grace_disallows_io(struct net *net, struct inode *inode)
-{
- return opens_in_grace(net) && mandatory_lock(inode);
-}
-
static __be32 check_stateid_generation(stateid_t *in, stateid_t *ref, bool has_session)
{
/*
stateid_t *stateid, int flags, struct nfsd_file **nfp,
struct nfs4_stid **cstid)
{
- struct inode *ino = d_inode(fhp->fh_dentry);
struct net *net = SVC_NET(rqstp);
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
struct nfs4_stid *s = NULL;
if (nfp)
*nfp = NULL;
- if (grace_disallows_io(net, ino))
- return nfserr_grace;
-
if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) {
status = check_special_stateids(net, fhp, stateid, flags);
goto done;
struct nfsd4_blocked_lock *nbl = NULL;
struct file_lock *file_lock = NULL;
struct file_lock *conflock = NULL;
+ struct super_block *sb;
__be32 status = 0;
int lkflg;
int err;
dprintk("NFSD: nfsd4_lock: permission denied!\n");
return status;
}
+ sb = cstate->current_fh.fh_dentry->d_sb;
if (lock->lk_is_new) {
if (nfsd4_has_session(cstate))
if (!locks_in_grace(net) && lock->lk_reclaim)
goto out;
+ if (lock->lk_reclaim)
+ fl_flags |= FL_RECLAIM;
+
fp = lock_stp->st_stid.sc_file;
switch (lock->lk_type) {
case NFS4_READW_LT:
- if (nfsd4_has_session(cstate))
+ if (nfsd4_has_session(cstate) &&
+ !(sb->s_export_op->flags & EXPORT_OP_SYNC_LOCKS))
fl_flags |= FL_SLEEP;
fallthrough;
case NFS4_READ_LT:
fl_type = F_RDLCK;
break;
case NFS4_WRITEW_LT:
- if (nfsd4_has_session(cstate))
+ if (nfsd4_has_session(cstate) &&
+ !(sb->s_export_op->flags & EXPORT_OP_SYNC_LOCKS))
fl_flags |= FL_SLEEP;
fallthrough;
case NFS4_WRITE_LT:
/*
* The NFSv4 spec allows a client to do a LOCKT without holding an OPEN,
* so we do a temporary open here just to get an open file to pass to
- * vfs_test_lock. (Arguably perhaps test_lock should be done with an
- * inode operation.)
+ * vfs_test_lock.
*/
static __be32 nfsd_test_lock(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file_lock *lock)
{
NFSD_MAY_READ));
if (err)
goto out;
+ lock->fl_file = nf->nf_file;
err = nfserrno(vfs_test_lock(nf->nf_file, lock));
+ lock->fl_file = NULL;
out:
fh_unlock(fhp);
nfsd_file_put(nf);
* returned. Otherwise the covered directory is returned.
* NOTE: this mountpoint crossing is not supported properly by all
* clients and is explicitly disallowed for NFSv3
- * NeilBrown <neilb@cse.unsw.edu.au>
*/
__be32
nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name,
struct iattr *iap)
{
struct inode *inode = d_inode(fhp->fh_dentry);
- int host_err;
if (iap->ia_size < inode->i_size) {
__be32 err;
if (err)
return err;
}
-
- host_err = get_write_access(inode);
- if (host_err)
- goto out_nfserrno;
-
- host_err = locks_verify_truncate(inode, NULL, iap->ia_size);
- if (host_err)
- goto out_put_write_access;
- return 0;
-
-out_put_write_access:
- put_write_access(inode);
-out_nfserrno:
- return nfserrno(host_err);
+ return nfserrno(get_write_access(inode));
}
/*
err = nfserr_perm;
if (IS_APPEND(inode) && (may_flags & NFSD_MAY_WRITE))
goto out;
- /*
- * We must ignore files (but only files) which might have mandatory
- * locks on them because there is no way to know if the accesser has
- * the lock.
- */
- if (S_ISREG((inode)->i_mode) && mandatory_lock(inode))
- goto out;
if (!inode->i_fop)
goto out;
struct svc_rqst *rqstp = sd->u.data;
struct page **pp = rqstp->rq_next_page;
struct page *page = buf->page;
- size_t size;
-
- size = sd->len;
if (rqstp->rq_res.page_len == 0) {
- get_page(page);
- put_page(*rqstp->rq_next_page);
- *(rqstp->rq_next_page++) = page;
+ svc_rqst_replace_page(rqstp, page);
rqstp->rq_res.page_base = buf->offset;
- rqstp->rq_res.page_len = size;
} else if (page != pp[-1]) {
- get_page(page);
- if (*rqstp->rq_next_page)
- put_page(*rqstp->rq_next_page);
- *(rqstp->rq_next_page++) = page;
- rqstp->rq_res.page_len += size;
- } else
- rqstp->rq_res.page_len += size;
-
- return size;
+ svc_rqst_replace_page(rqstp, page);
+ }
+ rqstp->rq_res.page_len += sd->len;
+
+ return sd->len;
}
static int nfsd_direct_splice_actor(struct pipe_inode_info *pipe,
/* iocb->ki_waitq is valid */
#define IOCB_WAITQ (1 << 19)
#define IOCB_NOIO (1 << 20)
+/* can use bio alloc cache */
+#define IOCB_ALLOC_CACHE (1 << 21)
struct kiocb {
struct file *ki_filp;
* struct address_space - Contents of a cacheable, mappable object.
* @host: Owner, either the inode or the block_device.
* @i_pages: Cached pages.
+ * @invalidate_lock: Guards coherency between page cache contents and
+ * file offset->disk block mappings in the filesystem during invalidates.
+ * It is also used to block modification of page cache contents through
+ * memory mappings.
* @gfp_mask: Memory allocation flags to use for allocating pages.
* @i_mmap_writable: Number of VM_SHARED mappings.
* @nr_thps: Number of THPs in the pagecache (non-shmem only).
struct address_space {
struct inode *host;
struct xarray i_pages;
+ struct rw_semaphore invalidate_lock;
gfp_t gfp_mask;
atomic_t i_mmap_writable;
#ifdef CONFIG_READ_ONLY_THP_FOR_FS
down_read_nested(&inode->i_rwsem, subclass);
}
+static inline void filemap_invalidate_lock(struct address_space *mapping)
+{
+ down_write(&mapping->invalidate_lock);
+}
+
+static inline void filemap_invalidate_unlock(struct address_space *mapping)
+{
+ up_write(&mapping->invalidate_lock);
+}
+
+static inline void filemap_invalidate_lock_shared(struct address_space *mapping)
+{
+ down_read(&mapping->invalidate_lock);
+}
+
+static inline int filemap_invalidate_trylock_shared(
+ struct address_space *mapping)
+{
+ return down_read_trylock(&mapping->invalidate_lock);
+}
+
+static inline void filemap_invalidate_unlock_shared(
+ struct address_space *mapping)
+{
+ up_read(&mapping->invalidate_lock);
+}
+
void lock_two_nondirectories(struct inode *, struct inode*);
void unlock_two_nondirectories(struct inode *, struct inode*);
+void filemap_invalidate_lock_two(struct address_space *mapping1,
+ struct address_space *mapping2);
+void filemap_invalidate_unlock_two(struct address_space *mapping1,
+ struct address_space *mapping2);
+
+
/*
* NOTE: in a 32bit arch with a preemptable kernel and
* an UP compile the i_size_read/write must be atomic
#define FL_UNLOCK_PENDING 512 /* Lease is being broken */
#define FL_OFDLCK 1024 /* lock is "owned" by struct file */
#define FL_LAYOUT 2048 /* outstanding pNFS layout */
+ #define FL_RECLAIM 4096 /* reclaiming from a reboot server */
#define FL_CLOSE_POSIX (FL_POSIX | FL_CLOSE)
/* Number of inodes with nlink == 0 but still referenced */
atomic_long_t s_remove_count;
- /* Pending fsnotify inode refs */
- atomic_long_t s_fsnotify_inode_refs;
+ /*
+ * Number of inode/mount/sb objects that are being watched, note that
+ * inodes objects are currently double-accounted.
+ */
+ atomic_long_t s_fsnotify_connectors;
/* Being remounted read-only */
int s_readonly_remount;
extern int file_modified(struct file *file);
-int sync_inode(struct inode *inode, struct writeback_control *wbc);
int sync_inode_metadata(struct inode *inode, int wait);
struct file_system_type {
struct lock_class_key i_lock_key;
struct lock_class_key i_mutex_key;
+ struct lock_class_key invalidate_lock_key;
struct lock_class_key i_mutex_dir_key;
};
#define MAX_RW_COUNT (INT_MAX & PAGE_MASK)
-#ifdef CONFIG_MANDATORY_FILE_LOCKING
-extern int locks_mandatory_locked(struct file *);
-extern int locks_mandatory_area(struct inode *, struct file *, loff_t, loff_t, unsigned char);
-
-/*
- * Candidates for mandatory locking have the setgid bit set
- * but no group execute bit - an otherwise meaningless combination.
- */
-
-static inline int __mandatory_lock(struct inode *ino)
-{
- return (ino->i_mode & (S_ISGID | S_IXGRP)) == S_ISGID;
-}
-
-/*
- * ... and these candidates should be on SB_MANDLOCK mounted fs,
- * otherwise these will be advisory locks
- */
-
-static inline int mandatory_lock(struct inode *ino)
-{
- return IS_MANDLOCK(ino) && __mandatory_lock(ino);
-}
-
-static inline int locks_verify_locked(struct file *file)
-{
- if (mandatory_lock(locks_inode(file)))
- return locks_mandatory_locked(file);
- return 0;
-}
-
-static inline int locks_verify_truncate(struct inode *inode,
- struct file *f,
- loff_t size)
-{
- if (!inode->i_flctx || !mandatory_lock(inode))
- return 0;
-
- if (size < inode->i_size) {
- return locks_mandatory_area(inode, f, size, inode->i_size - 1,
- F_WRLCK);
- } else {
- return locks_mandatory_area(inode, f, inode->i_size, size - 1,
- F_WRLCK);
- }
-}
-
-#else /* !CONFIG_MANDATORY_FILE_LOCKING */
-
-static inline int locks_mandatory_locked(struct file *file)
-{
- return 0;
-}
-
-static inline int locks_mandatory_area(struct inode *inode, struct file *filp,
- loff_t start, loff_t end, unsigned char type)
-{
- return 0;
-}
-
-static inline int __mandatory_lock(struct inode *inode)
-{
- return 0;
-}
-
-static inline int mandatory_lock(struct inode *inode)
-{
- return 0;
-}
-
-static inline int locks_verify_locked(struct file *file)
-{
- return 0;
-}
-
-static inline int locks_verify_truncate(struct inode *inode, struct file *filp,
- size_t size)
-{
- return 0;
-}
-
-#endif /* CONFIG_MANDATORY_FILE_LOCKING */
-
-
#ifdef CONFIG_FILE_LOCKING
static inline int break_lease(struct inode *inode, unsigned int mode)
{
extern int filp_close(struct file *, fl_owner_t id);
extern struct filename *getname_flags(const char __user *, int, int *);
+extern struct filename *getname_uflags(const char __user *, int);
extern struct filename *getname(const char __user *);
extern struct filename *getname_kernel(const char *);
extern void putname(struct filename *name);
loff_t start, loff_t end);
extern int filemap_check_errors(struct address_space *mapping);
extern void __filemap_set_wb_err(struct address_space *mapping, int err);
+int filemap_fdatawrite_wbc(struct address_space *mapping,
+ struct writeback_control *wbc);
static inline int filemap_write_and_wait(struct address_space *mapping)
{
ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb,
struct iov_iter *iter);
-/* fs/block_dev.c */
-extern int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
- int datasync);
-
/* fs/splice.c */
extern ssize_t generic_file_splice_read(struct file *, loff_t *,
struct pipe_inode_info *, size_t, unsigned int);
depends on DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT
select LOCKDEP
select DEBUG_SPINLOCK
- select DEBUG_MUTEXES
+ select DEBUG_MUTEXES if !PREEMPT_RT
select DEBUG_RT_MUTEXES if RT_MUTEXES
select DEBUG_RWSEMS
select DEBUG_WW_MUTEX_SLOWPATH
depends on DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT
select LOCKDEP
select DEBUG_SPINLOCK
- select DEBUG_MUTEXES
+ select DEBUG_MUTEXES if !PREEMPT_RT
select DEBUG_RT_MUTEXES if RT_MUTEXES
select DEBUG_LOCK_ALLOC
default n
config DEBUG_MUTEXES
bool "Mutex debugging: basic checks"
- depends on DEBUG_KERNEL
+ depends on DEBUG_KERNEL && !PREEMPT_RT
help
This feature allows mutex semantics violations to be detected and
reported.
depends on DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT
select DEBUG_LOCK_ALLOC
select DEBUG_SPINLOCK
- select DEBUG_MUTEXES
+ select DEBUG_MUTEXES if !PREEMPT_RT
+ select DEBUG_RT_MUTEXES if PREEMPT_RT
help
This feature enables slowpath testing for w/w mutex users by
injecting additional -EDEADLK wound/backoff cases. Together with
bool "Lock debugging: detect incorrect freeing of live locks"
depends on DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT
select DEBUG_SPINLOCK
- select DEBUG_MUTEXES
+ select DEBUG_MUTEXES if !PREEMPT_RT
select DEBUG_RT_MUTEXES if RT_MUTEXES
select LOCKDEP
help
feature by default. When enabled, memory and cache locality will
be impacted.
-config DEBUG_BLOCK_EXT_DEVT
- bool "Force extended block device numbers and spread them"
- depends on DEBUG_KERNEL
- depends on BLOCK
- default n
- help
- BIG FAT WARNING: ENABLING THIS OPTION MIGHT BREAK BOOTING ON
- SOME DISTRIBUTIONS. DO NOT ENABLE THIS UNLESS YOU KNOW WHAT
- YOU ARE DOING. Distros, please enable this and fix whatever
- is broken.
-
- Conventionally, block device numbers are allocated from
- predetermined contiguous area. However, extended block area
- may introduce non-contiguous block device numbers. This
- option forces most block device numbers to be allocated from
- the extended space and spreads them to discover kernel or
- userland code paths which assume predetermined contiguous
- device number allocation.
-
- Note that turning on this debug option shuffles all the
- device numbers for all IDE and SCSI devices including libata
- ones, so root partition specified using device number
- directly (via rdev or root=MAJ:MIN) won't work anymore.
- Textual device names (root=/dev/sdXn) will continue to work.
-
- Say N if you are unsure.
-
config CPU_HOTPLUG_STATE_CONTROL
bool "Enable CPU hotplug state control"
depends on DEBUG_KERNEL
and to test how the mmc host driver handles retries from
the block device.
+ config FAIL_SUNRPC
+ bool "Fault-injection capability for SunRPC"
+ depends on FAULT_INJECTION_DEBUG_FS && SUNRPC_DEBUG
+ help
+ Provide fault-injection capability for SunRPC and
+ its consumers.
+
config FAULT_INJECTION_STACKTRACE_FILTER
bool "stacktrace filter for fault-injection capabilities"
depends on FAULT_INJECTION_DEBUG_FS && STACKTRACE_SUPPORT
kfree(rqstp->rq_deferred);
rqstp->rq_deferred = NULL;
+ pagevec_release(&rqstp->rq_pvec);
svc_free_res_pages(rqstp);
rqstp->rq_res.page_len = 0;
rqstp->rq_res.page_base = 0;
struct xdr_buf *arg = &rqstp->rq_arg;
unsigned long pages, filled;
+ pagevec_init(&rqstp->rq_pvec);
+
pages = (serv->sv_max_mesg + 2 * PAGE_SIZE) >> PAGE_SHIFT;
if (pages > RPCSVC_MAXPAGES) {
pr_warn_once("svc: warning: pages=%lu > RPCSVC_MAXPAGES=%lu\n",
rqstp->rq_stime = ktime_get();
rqstp->rq_reserved = serv->sv_max_mesg;
atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved);
- }
+ } else
+ svc_xprt_received(xprt);
out:
trace_svc_handle_xprt(xprt, len);
return len;