From e77a7b4f01b4c7b02c1c15b5d5b4ce4bd147b043 Mon Sep 17 00:00:00 2001 From: Zach Brown Date: Mon, 6 Oct 2014 16:42:52 -0700 Subject: nfsd: fix inclusive vfs_fsync_range() end The vfs_fsync_range() call during write processing got the end of the range off by one. The range is inclusive, not exclusive. The error has nfsd sync more data than requested -- it's correct but unnecessary overhead. The call during commit processing is correct so I copied that pattern in write processing. Maybe a helper would be nice but I kept it trivial. This is untested. I found it while reviewing code for something else entirely. Signed-off-by: Zach Brown Signed-off-by: J. Bruce Fields --- fs/nfsd/vfs.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 989129e2d6ea..d16076bd9a7a 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -938,6 +938,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, int stable = *stablep; int use_wgather; loff_t pos = offset; + loff_t end = LLONG_MAX; unsigned int pflags = current->flags; if (rqstp->rq_local) @@ -969,10 +970,13 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, fsnotify_modify(file); if (stable) { - if (use_wgather) + if (use_wgather) { host_err = wait_for_concurrent_writes(file); - else - host_err = vfs_fsync_range(file, offset, offset+*cnt, 0); + } else { + if (*cnt) + end = offset + *cnt - 1; + host_err = vfs_fsync_range(file, offset, end, 0); + } } out_nfserr: -- cgit v1.2.3-59-g8ed1b From b0d2e42cce8fbf12998a24abf62a26c895dd2fd2 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 22 Aug 2014 15:10:59 -0400 Subject: NFSD: Always initialize cl_cb_addr A client may not want to use the back channel on a transport it sent CREATE_SESSION on, in which case it clears SESSION4_BACK_CHAN. However, cl_cb_addr should be populated anyway, to be used if the client binds other connections to this session. If cl_cb_addr is not initialized, rpc_create() fails when the server attempts to set up a back channel on such secondary transports. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index e9c3afe4b5d3..1afd7d4420bd 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1440,7 +1440,7 @@ static void init_session(struct svc_rqst *rqstp, struct nfsd4_session *new, stru list_add(&new->se_perclnt, &clp->cl_sessions); spin_unlock(&clp->cl_lock); - if (cses->flags & SESSION4_BACK_CHAN) { + { struct sockaddr *sa = svc_addr(rqstp); /* * This is a little silly; with sessions there's no real -- cgit v1.2.3-59-g8ed1b From ccc6398ea5d58fdedc6caccba0216ab30739773b Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 16 Oct 2014 08:49:37 -0400 Subject: nfsd: clean up comments over nfs4_file definition They're a bit outdated wrt to some recent changes. Signed-off-by: Jeff Layton Reviewed-by: Christoph Hellwig Signed-off-by: J. Bruce Fields --- fs/nfsd/state.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 2712042a66b1..8e85e07efce6 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -463,15 +463,19 @@ static inline struct nfs4_lockowner * lockowner(struct nfs4_stateowner *so) /* * nfs4_file: a file opened by some number of (open) nfs4_stateowners. * - * These objects are global. nfsd only keeps one instance of a nfs4_file per - * inode (though it may keep multiple file descriptors open per inode). These - * are tracked in the file_hashtbl which is protected by the state_lock - * spinlock. + * These objects are global. nfsd keeps one instance of a nfs4_file per + * filehandle (though it may keep multiple file descriptors for each). Each + * inode can have multiple filehandles associated with it, so there is + * (potentially) a many to one relationship between this struct and struct + * inode. + * + * These are hashed by filehandle in the file_hashtbl, which is protected by + * the global state_lock spinlock. */ struct nfs4_file { atomic_t fi_ref; spinlock_t fi_lock; - struct hlist_node fi_hash; /* hash by "struct inode *" */ + struct hlist_node fi_hash; /* hash on fi_fhandle */ struct list_head fi_stateids; struct list_head fi_delegations; /* One each for O_RDONLY, O_WRONLY, O_RDWR: */ -- cgit v1.2.3-59-g8ed1b From 9af94fc4e470deab3427d07551725f0bf844ebc8 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 31 Oct 2014 08:28:29 -0400 Subject: lockd: ratelimit "lockd: cannot monitor" messages When lockd can't talk to a remote statd, it'll spew a warning message to the ring buffer. If the application is really hammering on locks however, it's possible for that message to spam the logs. Ratelimit it to minimize the potential for harm. Reported-by: Ian Collier Signed-off-by: Jeff Layton Signed-off-by: J. Bruce Fields --- fs/lockd/mon.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 9106f42c472c..1cc6ec51e6b1 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -214,7 +214,7 @@ int nsm_monitor(const struct nlm_host *host) if (unlikely(res.status != 0)) status = -EIO; if (unlikely(status < 0)) { - printk(KERN_NOTICE "lockd: cannot monitor %s\n", nsm->sm_name); + pr_notice_ratelimited("lockd: cannot monitor %s\n", nsm->sm_name); return status; } -- cgit v1.2.3-59-g8ed1b From 72c72bdf7bf53353d2d8e055194d27f0128be92b Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 7 Nov 2014 14:44:25 -0500 Subject: VFS: Rename do_fallocate() to vfs_fallocate() This function needs to be exported so it can be used by the NFSD module when responding to the new ALLOCATE and DEALLOCATE operations in NFS v4.2. Christoph Hellwig suggested renaming the function to stay consistent with how other vfs functions are named. Signed-off-by: Anna Schumaker Signed-off-by: J. Bruce Fields --- drivers/staging/android/ashmem.c | 2 +- fs/ioctl.c | 2 +- fs/open.c | 5 +++-- include/linux/fs.h | 2 +- mm/madvise.c | 2 +- 5 files changed, 7 insertions(+), 6 deletions(-) (limited to 'fs') diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c index ad4f5790a76f..27eecfe1c410 100644 --- a/drivers/staging/android/ashmem.c +++ b/drivers/staging/android/ashmem.c @@ -446,7 +446,7 @@ ashmem_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) loff_t start = range->pgstart * PAGE_SIZE; loff_t end = (range->pgend + 1) * PAGE_SIZE; - do_fallocate(range->asma->file, + vfs_fallocate(range->asma->file, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, start, end - start); range->purged = ASHMEM_WAS_PURGED; diff --git a/fs/ioctl.c b/fs/ioctl.c index 8ac3fad36192..0bd6142183ee 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -443,7 +443,7 @@ int ioctl_preallocate(struct file *filp, void __user *argp) return -EINVAL; } - return do_fallocate(filp, FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len); + return vfs_fallocate(filp, FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len); } static int file_ioctl(struct file *filp, unsigned int cmd, diff --git a/fs/open.c b/fs/open.c index d6fd3acde134..c94449b2e582 100644 --- a/fs/open.c +++ b/fs/open.c @@ -222,7 +222,7 @@ SYSCALL_DEFINE2(ftruncate64, unsigned int, fd, loff_t, length) #endif /* BITS_PER_LONG == 32 */ -int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len) +int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); long ret; @@ -298,6 +298,7 @@ int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len) sb_end_write(inode->i_sb); return ret; } +EXPORT_SYMBOL_GPL(vfs_fallocate); SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len) { @@ -305,7 +306,7 @@ SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len) int error = -EBADF; if (f.file) { - error = do_fallocate(f.file, mode, offset, len); + error = vfs_fallocate(f.file, mode, offset, len); fdput(f); } return error; diff --git a/include/linux/fs.h b/include/linux/fs.h index a957d4366c24..a88718677579 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2032,7 +2032,7 @@ struct filename { extern long vfs_truncate(struct path *, loff_t); extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs, struct file *filp); -extern int do_fallocate(struct file *file, int mode, loff_t offset, +extern int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len); extern long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode); diff --git a/mm/madvise.c b/mm/madvise.c index 0938b30da4ab..a271adc93289 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -326,7 +326,7 @@ static long madvise_remove(struct vm_area_struct *vma, */ get_file(f); up_read(¤t->mm->mmap_sem); - error = do_fallocate(f, + error = vfs_fallocate(f, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, offset, end - start); fput(f); -- cgit v1.2.3-59-g8ed1b From 95d871f03cae6b49de040265cf88cbe2a16b9f05 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 7 Nov 2014 14:44:26 -0500 Subject: nfsd: Add ALLOCATE support The ALLOCATE operation is used to preallocate space in a file. I can do this by using vfs_fallocate() to do the actual preallocation. ALLOCATE only returns a status indicator, so we don't need to write a special encode() function. Signed-off-by: Anna Schumaker Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4proc.c | 36 ++++++++++++++++++++++++++++++++++++ fs/nfsd/nfs4xdr.c | 19 ++++++++++++++++++- fs/nfsd/vfs.c | 21 +++++++++++++++++++++ fs/nfsd/vfs.h | 2 ++ fs/nfsd/xdr4.h | 8 ++++++++ 5 files changed, 85 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 0beb023f25ac..a261f1800922 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1013,6 +1013,36 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return status; } +static __be32 +nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, + struct nfsd4_fallocate *fallocate, int flags) +{ + __be32 status = nfserr_notsupp; + struct file *file; + + status = nfs4_preprocess_stateid_op(SVC_NET(rqstp), cstate, + &fallocate->falloc_stateid, + WR_STATE, &file); + if (status != nfs_ok) { + dprintk("NFSD: nfsd4_fallocate: couldn't process stateid!\n"); + return status; + } + + status = nfsd4_vfs_fallocate(rqstp, &cstate->current_fh, file, + fallocate->falloc_offset, + fallocate->falloc_length, + flags); + fput(file); + return status; +} + +static __be32 +nfsd4_allocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, + struct nfsd4_fallocate *fallocate) +{ + return nfsd4_fallocate(rqstp, cstate, fallocate, 0); +} + static __be32 nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_seek *seek) @@ -1929,6 +1959,12 @@ static struct nfsd4_operation nfsd4_ops[] = { }, /* NFSv4.2 operations */ + [OP_ALLOCATE] = { + .op_func = (nfsd4op_func)nfsd4_allocate, + .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, + .op_name = "OP_ALLOCATE", + .op_rsize_bop = (nfsd4op_rsize)nfsd4_write_rsize, + }, [OP_SEEK] = { .op_func = (nfsd4op_func)nfsd4_seek, .op_name = "OP_SEEK", diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index eeea7a90eb87..a60cff86fc28 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1513,6 +1513,23 @@ static __be32 nfsd4_decode_reclaim_complete(struct nfsd4_compoundargs *argp, str DECODE_TAIL; } +static __be32 +nfsd4_decode_fallocate(struct nfsd4_compoundargs *argp, + struct nfsd4_fallocate *fallocate) +{ + DECODE_HEAD; + + status = nfsd4_decode_stateid(argp, &fallocate->falloc_stateid); + if (status) + return status; + + READ_BUF(16); + p = xdr_decode_hyper(p, &fallocate->falloc_offset); + xdr_decode_hyper(p, &fallocate->falloc_length); + + DECODE_TAIL; +} + static __be32 nfsd4_decode_seek(struct nfsd4_compoundargs *argp, struct nfsd4_seek *seek) { @@ -1604,7 +1621,7 @@ static nfsd4_dec nfsd4_dec_ops[] = { [OP_RECLAIM_COMPLETE] = (nfsd4_dec)nfsd4_decode_reclaim_complete, /* new operations for NFSv4.2 */ - [OP_ALLOCATE] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_ALLOCATE] = (nfsd4_dec)nfsd4_decode_fallocate, [OP_COPY] = (nfsd4_dec)nfsd4_decode_notsupp, [OP_COPY_NOTIFY] = (nfsd4_dec)nfsd4_decode_notsupp, [OP_DEALLOCATE] = (nfsd4_dec)nfsd4_decode_notsupp, diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index d16076bd9a7a..f1999619d516 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -533,6 +534,26 @@ __be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp, } #endif +__be32 nfsd4_vfs_fallocate(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct file *file, loff_t offset, loff_t len, + int flags) +{ + __be32 err; + int error; + + if (!S_ISREG(file_inode(file)->i_mode)) + return nfserr_inval; + + err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry, NFSD_MAY_WRITE); + if (err) + return err; + + error = vfs_fallocate(file, flags, offset, len); + if (!error) + error = commit_metadata(fhp); + + return nfserrno(error); +} #endif /* defined(CONFIG_NFSD_V4) */ #ifdef CONFIG_NFSD_V3 diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index c2ff3f14e5f6..7ffdb144e486 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -54,6 +54,8 @@ int nfsd_mountpoint(struct dentry *, struct svc_export *); #ifdef CONFIG_NFSD_V4 __be32 nfsd4_set_nfs4_label(struct svc_rqst *, struct svc_fh *, struct xdr_netobj *); +__be32 nfsd4_vfs_fallocate(struct svc_rqst *, struct svc_fh *, + struct file *, loff_t, loff_t, int); #endif /* CONFIG_NFSD_V4 */ __be32 nfsd_create(struct svc_rqst *, struct svc_fh *, char *name, int len, struct iattr *attrs, diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 5720e9457f33..eeaa0d0c4f79 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -428,6 +428,13 @@ struct nfsd4_reclaim_complete { u32 rca_one_fs; }; +struct nfsd4_fallocate { + /* request */ + stateid_t falloc_stateid; + loff_t falloc_offset; + u64 falloc_length; +}; + struct nfsd4_seek { /* request */ stateid_t seek_stateid; @@ -486,6 +493,7 @@ struct nfsd4_op { struct nfsd4_free_stateid free_stateid; /* NFSv4.2 */ + struct nfsd4_fallocate allocate; struct nfsd4_seek seek; } u; struct nfs4_replay * replay; -- cgit v1.2.3-59-g8ed1b From b0cb9085239a20b7482ddd4839dd1d5476801dfa Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 7 Nov 2014 14:44:27 -0500 Subject: nfsd: Add DEALLOCATE support DEALLOCATE only returns a status value, meaning we can use the noop() xdr encoder to reply to the client. Signed-off-by: Anna Schumaker Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4proc.c | 15 +++++++++++++++ fs/nfsd/nfs4xdr.c | 2 +- fs/nfsd/xdr4.h | 1 + 3 files changed, 17 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index a261f1800922..74fb15eefc31 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -33,6 +33,7 @@ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ #include +#include #include #include "idmap.h" @@ -1043,6 +1044,14 @@ nfsd4_allocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return nfsd4_fallocate(rqstp, cstate, fallocate, 0); } +static __be32 +nfsd4_deallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, + struct nfsd4_fallocate *fallocate) +{ + return nfsd4_fallocate(rqstp, cstate, fallocate, + FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE); +} + static __be32 nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_seek *seek) @@ -1965,6 +1974,12 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_name = "OP_ALLOCATE", .op_rsize_bop = (nfsd4op_rsize)nfsd4_write_rsize, }, + [OP_DEALLOCATE] = { + .op_func = (nfsd4op_func)nfsd4_deallocate, + .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, + .op_name = "OP_DEALLOCATE", + .op_rsize_bop = (nfsd4op_rsize)nfsd4_write_rsize, + }, [OP_SEEK] = { .op_func = (nfsd4op_func)nfsd4_seek, .op_name = "OP_SEEK", diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index a60cff86fc28..0622d4f4a9a2 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1624,7 +1624,7 @@ static nfsd4_dec nfsd4_dec_ops[] = { [OP_ALLOCATE] = (nfsd4_dec)nfsd4_decode_fallocate, [OP_COPY] = (nfsd4_dec)nfsd4_decode_notsupp, [OP_COPY_NOTIFY] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_DEALLOCATE] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_DEALLOCATE] = (nfsd4_dec)nfsd4_decode_fallocate, [OP_IO_ADVISE] = (nfsd4_dec)nfsd4_decode_notsupp, [OP_LAYOUTERROR] = (nfsd4_dec)nfsd4_decode_notsupp, [OP_LAYOUTSTATS] = (nfsd4_dec)nfsd4_decode_notsupp, diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index eeaa0d0c4f79..90a5925bd6ab 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -494,6 +494,7 @@ struct nfsd4_op { /* NFSv4.2 */ struct nfsd4_fallocate allocate; + struct nfsd4_fallocate deallocate; struct nfsd4_seek seek; } u; struct nfs4_replay * replay; -- cgit v1.2.3-59-g8ed1b From 5b095e99928cc13332d364f7cca7a9ca684369b4 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 23 Oct 2014 08:01:02 -0400 Subject: nfsd: convert nfs4_file searches to use RCU The global state_lock protects the file_hashtbl, and that has the potential to be a scalability bottleneck. Address this by making the file_hashtbl use RCU. Add a rcu_head to the nfs4_file and use that when freeing ones that have been hashed. In order to conserve space, we union the fi_rcu field with the fi_delegations list_head which must be clear by the time the last reference to the file is dropped. Convert find_file_locked to use RCU lookup primitives and not to require that the state_lock be held, and convert find_file to do a lockless lookup. Convert find_or_add_file to attempt a lockless lookup first, and then fall back to doing a locked search and insert if that fails to find anything. Also, minimize the number of times we need to calculate the hash value by passing it in as an argument to the search and insert functions, and optimize the order of arguments in nfsd4_init_file. Reviewed-by: Christoph Hellwig Signed-off-by: Jeff Layton Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 51 +++++++++++++++++++++++++++++---------------------- fs/nfsd/state.h | 5 ++++- 2 files changed, 33 insertions(+), 23 deletions(-) (limited to 'fs') diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 1afd7d4420bd..1379d86f7b4f 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -275,9 +275,11 @@ opaque_hashval(const void *ptr, int nbytes) return x; } -static void nfsd4_free_file(struct nfs4_file *f) +static void nfsd4_free_file_rcu(struct rcu_head *rcu) { - kmem_cache_free(file_slab, f); + struct nfs4_file *fp = container_of(rcu, struct nfs4_file, fi_rcu); + + kmem_cache_free(file_slab, fp); } static inline void @@ -286,9 +288,10 @@ put_nfs4_file(struct nfs4_file *fi) might_lock(&state_lock); if (atomic_dec_and_lock(&fi->fi_ref, &state_lock)) { - hlist_del(&fi->fi_hash); + hlist_del_rcu(&fi->fi_hash); spin_unlock(&state_lock); - nfsd4_free_file(fi); + WARN_ON_ONCE(!list_empty(&fi->fi_delegations)); + call_rcu(&fi->fi_rcu, nfsd4_free_file_rcu); } } @@ -3057,10 +3060,9 @@ static struct nfs4_file *nfsd4_alloc_file(void) } /* OPEN Share state helper functions */ -static void nfsd4_init_file(struct nfs4_file *fp, struct knfsd_fh *fh) +static void nfsd4_init_file(struct knfsd_fh *fh, unsigned int hashval, + struct nfs4_file *fp) { - unsigned int hashval = file_hashval(fh); - lockdep_assert_held(&state_lock); atomic_set(&fp->fi_ref, 1); @@ -3073,7 +3075,7 @@ static void nfsd4_init_file(struct nfs4_file *fp, struct knfsd_fh *fh) fp->fi_share_deny = 0; memset(fp->fi_fds, 0, sizeof(fp->fi_fds)); memset(fp->fi_access, 0, sizeof(fp->fi_access)); - hlist_add_head(&fp->fi_hash, &file_hashtbl[hashval]); + hlist_add_head_rcu(&fp->fi_hash, &file_hashtbl[hashval]); } void @@ -3294,17 +3296,14 @@ move_to_close_lru(struct nfs4_ol_stateid *s, struct net *net) /* search file_hashtbl[] for file */ static struct nfs4_file * -find_file_locked(struct knfsd_fh *fh) +find_file_locked(struct knfsd_fh *fh, unsigned int hashval) { - unsigned int hashval = file_hashval(fh); struct nfs4_file *fp; - lockdep_assert_held(&state_lock); - - hlist_for_each_entry(fp, &file_hashtbl[hashval], fi_hash) { + hlist_for_each_entry_rcu(fp, &file_hashtbl[hashval], fi_hash) { if (nfsd_fh_match(&fp->fi_fhandle, fh)) { - get_nfs4_file(fp); - return fp; + if (atomic_inc_not_zero(&fp->fi_ref)) + return fp; } } return NULL; @@ -3314,10 +3313,11 @@ static struct nfs4_file * find_file(struct knfsd_fh *fh) { struct nfs4_file *fp; + unsigned int hashval = file_hashval(fh); - spin_lock(&state_lock); - fp = find_file_locked(fh); - spin_unlock(&state_lock); + rcu_read_lock(); + fp = find_file_locked(fh, hashval); + rcu_read_unlock(); return fp; } @@ -3325,11 +3325,18 @@ static struct nfs4_file * find_or_add_file(struct nfs4_file *new, struct knfsd_fh *fh) { struct nfs4_file *fp; + unsigned int hashval = file_hashval(fh); + + rcu_read_lock(); + fp = find_file_locked(fh, hashval); + rcu_read_unlock(); + if (fp) + return fp; spin_lock(&state_lock); - fp = find_file_locked(fh); - if (fp == NULL) { - nfsd4_init_file(new, fh); + fp = find_file_locked(fh, hashval); + if (likely(fp == NULL)) { + nfsd4_init_file(fh, hashval, new); fp = new; } spin_unlock(&state_lock); @@ -4127,7 +4134,7 @@ void nfsd4_cleanup_open_state(struct nfsd4_compound_state *cstate, nfs4_put_stateowner(so); } if (open->op_file) - nfsd4_free_file(open->op_file); + kmem_cache_free(file_slab, open->op_file); if (open->op_stp) nfs4_put_stid(&open->op_stp->st_stid); } diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 8e85e07efce6..9d3be371240a 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -477,7 +477,10 @@ struct nfs4_file { spinlock_t fi_lock; struct hlist_node fi_hash; /* hash on fi_fhandle */ struct list_head fi_stateids; - struct list_head fi_delegations; + union { + struct list_head fi_delegations; + struct rcu_head fi_rcu; + }; /* One each for O_RDONLY, O_WRONLY, O_RDWR: */ struct file * fi_fds[3]; /* -- cgit v1.2.3-59-g8ed1b From 818f2f57f20d0e9a9294180f304f34cd4e8f6066 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 27 Nov 2014 18:58:54 +0300 Subject: nfsd: minor off by one checks in __write_versions() My static checker complains that if "len == remaining" then it means we have truncated the last character off the version string. The intent of the code is that we print as many versions as we can without truncating a version. Then we put a newline at the end. If the newline can't fit we return -EINVAL. Signed-off-by: Dan Carpenter Reviewed-by: Jeff Layton Signed-off-by: J. Bruce Fields --- fs/nfsd/nfsctl.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index ca73ca79a0ee..0079b28270e9 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -606,7 +606,7 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) num); sep = " "; - if (len > remaining) + if (len >= remaining) break; remaining -= len; buf += len; @@ -621,7 +621,7 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) '+' : '-', minor); - if (len > remaining) + if (len >= remaining) break; remaining -= len; buf += len; @@ -629,7 +629,7 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) } len = snprintf(buf, remaining, "\n"); - if (len > remaining) + if (len >= remaining) return -EINVAL; return tlen + len; } -- cgit v1.2.3-59-g8ed1b From 4d152e2c9a6a3e3556ce5da7782a9e2836edbe0f Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 19 Nov 2014 07:51:14 -0500 Subject: sunrpc: add a generic rq_flags field to svc_rqst and move rq_secure to it In a later patch, we're going to need some atomic bit flags. Since that field will need to be an unsigned long, we mitigate that space consumption by migrating some other bitflags to the new field. Start with the rq_secure flag. Signed-off-by: Jeff Layton Signed-off-by: J. Bruce Fields --- fs/nfsd/nfscache.c | 4 ++-- fs/nfsd/nfsfh.c | 2 +- include/linux/sunrpc/svc.h | 4 ++-- include/trace/events/sunrpc.h | 17 +++++++++++++---- net/sunrpc/svc_xprt.c | 5 ++++- 5 files changed, 22 insertions(+), 10 deletions(-) (limited to 'fs') diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 122f69185ef5..83a9694ec485 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -490,7 +490,7 @@ found_entry: /* From the hall of fame of impractical attacks: * Is this a user who tries to snoop on the cache? */ rtn = RC_DOIT; - if (!rqstp->rq_secure && rp->c_secure) + if (!test_bit(RQ_SECURE, &rqstp->rq_flags) && rp->c_secure) goto out; /* Compose RPC reply header */ @@ -579,7 +579,7 @@ nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp) spin_lock(&b->cache_lock); drc_mem_usage += bufsize; lru_put_end(b, rp); - rp->c_secure = rqstp->rq_secure; + rp->c_secure = test_bit(RQ_SECURE, &rqstp->rq_flags); rp->c_type = cachetype; rp->c_state = RC_DONE; spin_unlock(&b->cache_lock); diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 88026fc6a981..965b478d50fc 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -86,7 +86,7 @@ static __be32 nfsd_setuser_and_check_port(struct svc_rqst *rqstp, int flags = nfsexp_flags(rqstp, exp); /* Check if the request originated from a secure port. */ - if (!rqstp->rq_secure && !(flags & NFSEXP_INSECURE_PORT)) { + if (!test_bit(RQ_SECURE, &rqstp->rq_flags) && !(flags & NFSEXP_INSECURE_PORT)) { RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]); dprintk("nfsd: request from insecure port %s!\n", svc_print_addr(rqstp, buf, sizeof(buf))); diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 21678464883a..b60eb7c3f3f7 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -253,8 +253,8 @@ struct svc_rqst { u32 rq_vers; /* program version */ u32 rq_proc; /* procedure number */ u32 rq_prot; /* IP protocol */ - unsigned short - rq_secure : 1; /* secure port */ +#define RQ_SECURE (0) /* secure port */ + unsigned long rq_flags; /* flags field */ unsigned short rq_local : 1; /* local request */ void * rq_argp; /* decoded arguments */ diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 171ca4ff6d99..5eb5f79d9794 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -412,6 +412,10 @@ TRACE_EVENT(xs_tcp_data_recv, __entry->copied, __entry->reclen, __entry->offset) ); +#define show_rqstp_flags(flags) \ + __print_flags(flags, "|", \ + { (1UL << RQ_SECURE), "RQ_SECURE"}) + TRACE_EVENT(svc_recv, TP_PROTO(struct svc_rqst *rqst, int status), @@ -421,16 +425,19 @@ TRACE_EVENT(svc_recv, __field(struct sockaddr *, addr) __field(__be32, xid) __field(int, status) + __field(unsigned long, flags) ), TP_fast_assign( __entry->addr = (struct sockaddr *)&rqst->rq_addr; __entry->xid = status > 0 ? rqst->rq_xid : 0; __entry->status = status; + __entry->flags = rqst->rq_flags; ), - TP_printk("addr=%pIScp xid=0x%x status=%d", __entry->addr, - be32_to_cpu(__entry->xid), __entry->status) + TP_printk("addr=%pIScp xid=0x%x status=%d flags=%s", __entry->addr, + be32_to_cpu(__entry->xid), __entry->status, + show_rqstp_flags(__entry->flags)) ); DECLARE_EVENT_CLASS(svc_rqst_status, @@ -444,6 +451,7 @@ DECLARE_EVENT_CLASS(svc_rqst_status, __field(__be32, xid) __field(int, dropme) __field(int, status) + __field(unsigned long, flags) ), TP_fast_assign( @@ -451,11 +459,12 @@ DECLARE_EVENT_CLASS(svc_rqst_status, __entry->xid = rqst->rq_xid; __entry->dropme = (int)rqst->rq_dropme; __entry->status = status; + __entry->flags = rqst->rq_flags; ), - TP_printk("addr=%pIScp rq_xid=0x%x dropme=%d status=%d", + TP_printk("addr=%pIScp rq_xid=0x%x dropme=%d status=%d flags=%s", __entry->addr, be32_to_cpu(__entry->xid), __entry->dropme, - __entry->status) + __entry->status, show_rqstp_flags(__entry->flags)) ); DEFINE_EVENT(svc_rqst_status, svc_process, diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 5c71ccb9659d..eaa9263c2d28 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -797,7 +797,10 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) clear_bit(XPT_OLD, &xprt->xpt_flags); - rqstp->rq_secure = xprt->xpt_ops->xpo_secure_port(rqstp); + if (xprt->xpt_ops->xpo_secure_port(rqstp)) + set_bit(RQ_SECURE, &rqstp->rq_flags); + else + clear_bit(RQ_SECURE, &rqstp->rq_flags); rqstp->rq_chandle.defer = svc_defer; rqstp->rq_xid = svc_getu32(&rqstp->rq_arg.head[0]); -- cgit v1.2.3-59-g8ed1b From 7501cc2bcf9a71cc1f19e38775c234815ee44578 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 19 Nov 2014 07:51:15 -0500 Subject: sunrpc: move rq_local field to rq_flags Signed-off-by: Jeff Layton Signed-off-by: J. Bruce Fields --- fs/nfsd/vfs.c | 4 ++-- include/linux/sunrpc/svc.h | 2 +- include/trace/events/sunrpc.h | 3 ++- net/sunrpc/svcsock.c | 5 ++++- 4 files changed, 9 insertions(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index f1999619d516..60c25850fb16 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -962,7 +962,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, loff_t end = LLONG_MAX; unsigned int pflags = current->flags; - if (rqstp->rq_local) + if (test_bit(RQ_LOCAL, &rqstp->rq_flags)) /* * We want less throttling in balance_dirty_pages() * and shrink_inactive_list() so that nfs to @@ -1006,7 +1006,7 @@ out_nfserr: err = 0; else err = nfserrno(host_err); - if (rqstp->rq_local) + if (test_bit(RQ_LOCAL, &rqstp->rq_flags)) tsk_restore_flags(current, pflags, PF_LESS_THROTTLE); return err; } diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index b60eb7c3f3f7..a91df9047f32 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -254,8 +254,8 @@ struct svc_rqst { u32 rq_proc; /* procedure number */ u32 rq_prot; /* IP protocol */ #define RQ_SECURE (0) /* secure port */ +#define RQ_LOCAL (1) /* local request */ unsigned long rq_flags; /* flags field */ - unsigned short rq_local : 1; /* local request */ void * rq_argp; /* decoded arguments */ void * rq_resp; /* xdr'd results */ diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 5eb5f79d9794..98259f163cd8 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -414,7 +414,8 @@ TRACE_EVENT(xs_tcp_data_recv, #define show_rqstp_flags(flags) \ __print_flags(flags, "|", \ - { (1UL << RQ_SECURE), "RQ_SECURE"}) + { (1UL << RQ_SECURE), "RQ_SECURE"}, \ + { (1UL << RQ_LOCAL), "RQ_LOCAL"}) TRACE_EVENT(svc_recv, TP_PROTO(struct svc_rqst *rqst, int status), diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index f9c052d508f0..cc331b6cf573 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1145,7 +1145,10 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) rqstp->rq_xprt_ctxt = NULL; rqstp->rq_prot = IPPROTO_TCP; - rqstp->rq_local = !!test_bit(XPT_LOCAL, &svsk->sk_xprt.xpt_flags); + if (test_bit(XPT_LOCAL, &svsk->sk_xprt.xpt_flags)) + set_bit(RQ_LOCAL, &rqstp->rq_flags); + else + clear_bit(RQ_LOCAL, &rqstp->rq_flags); p = (__be32 *)rqstp->rq_arg.head[0].iov_base; calldir = p[1]; -- cgit v1.2.3-59-g8ed1b From 30660e04b0d4bbbd15fd21098681f45a9f4080b9 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 19 Nov 2014 07:51:16 -0500 Subject: sunrpc: move rq_usedeferral flag to rq_flags Signed-off-by: Jeff Layton Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4proc.c | 4 ++-- include/linux/sunrpc/svc.h | 2 +- include/trace/events/sunrpc.h | 9 +++++---- net/sunrpc/svc.c | 2 +- net/sunrpc/svc_xprt.c | 2 +- 5 files changed, 10 insertions(+), 9 deletions(-) (limited to 'fs') diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 74fb15eefc31..6f98393ad0d9 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1370,7 +1370,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, * Don't use the deferral mechanism for NFSv4; compounds make it * too hard to avoid non-idempotency problems. */ - rqstp->rq_usedeferral = false; + clear_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); /* * According to RFC3010, this takes precedence over all other errors. @@ -1486,7 +1486,7 @@ encode_op: BUG_ON(cstate->replay_owner); out: /* Reset deferral mechanism for RPC deferrals */ - rqstp->rq_usedeferral = true; + set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); dprintk("nfsv4 compound returned %d\n", ntohl(status)); return status; } diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index a91df9047f32..6a3cf4c76dce 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -236,7 +236,6 @@ struct svc_rqst { struct svc_cred rq_cred; /* auth info */ void * rq_xprt_ctxt; /* transport specific context ptr */ struct svc_deferred_req*rq_deferred; /* deferred request we are replaying */ - bool rq_usedeferral; /* use deferral */ size_t rq_xprt_hlen; /* xprt header len */ struct xdr_buf rq_arg; @@ -255,6 +254,7 @@ struct svc_rqst { u32 rq_prot; /* IP protocol */ #define RQ_SECURE (0) /* secure port */ #define RQ_LOCAL (1) /* local request */ +#define RQ_USEDEFERRAL (2) /* use deferral */ unsigned long rq_flags; /* flags field */ void * rq_argp; /* decoded arguments */ diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 98259f163cd8..6d1facdebc92 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -412,10 +412,11 @@ TRACE_EVENT(xs_tcp_data_recv, __entry->copied, __entry->reclen, __entry->offset) ); -#define show_rqstp_flags(flags) \ - __print_flags(flags, "|", \ - { (1UL << RQ_SECURE), "RQ_SECURE"}, \ - { (1UL << RQ_LOCAL), "RQ_LOCAL"}) +#define show_rqstp_flags(flags) \ + __print_flags(flags, "|", \ + { (1UL << RQ_SECURE), "RQ_SECURE"}, \ + { (1UL << RQ_LOCAL), "RQ_LOCAL"}, \ + { (1UL << RQ_USEDEFERRAL), "RQ_USEDEFERRAL"}) TRACE_EVENT(svc_recv, TP_PROTO(struct svc_rqst *rqst, int status), diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 163df468d6d5..f6a8f2f7a253 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1090,7 +1090,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) /* Will be turned off only in gss privacy case: */ rqstp->rq_splice_ok = true; /* Will be turned off only when NFSv4 Sessions are used */ - rqstp->rq_usedeferral = true; + set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); rqstp->rq_dropme = false; /* Setup reply header */ diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index eaa9263c2d28..a40f3755a33d 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -1081,7 +1081,7 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req) struct svc_rqst *rqstp = container_of(req, struct svc_rqst, rq_chandle); struct svc_deferred_req *dr; - if (rqstp->rq_arg.page_len || !rqstp->rq_usedeferral) + if (rqstp->rq_arg.page_len || !test_bit(RQ_USEDEFERRAL, &rqstp->rq_flags)) return NULL; /* if more than a page, give up FIXME */ if (rqstp->rq_deferred) { dr = rqstp->rq_deferred; -- cgit v1.2.3-59-g8ed1b From 78b65eb3fda95c6d131c4bbb0536e21f0bd7a7d4 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 19 Nov 2014 07:51:17 -0500 Subject: sunrpc: move rq_dropme flag into rq_flags Signed-off-by: Jeff Layton Signed-off-by: J. Bruce Fields --- fs/nfsd/nfssvc.c | 2 +- include/linux/sunrpc/svc.h | 2 +- include/trace/events/sunrpc.h | 8 ++++---- net/sunrpc/svc.c | 4 ++-- net/sunrpc/svc_xprt.c | 2 +- 5 files changed, 9 insertions(+), 9 deletions(-) (limited to 'fs') diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 752d56bbe0ba..314f5c8f8f1a 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -692,7 +692,7 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) /* Now call the procedure handler, and encode NFS status. */ nfserr = proc->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp); nfserr = map_new_errors(rqstp->rq_vers, nfserr); - if (nfserr == nfserr_dropit || rqstp->rq_dropme) { + if (nfserr == nfserr_dropit || test_bit(RQ_DROPME, &rqstp->rq_flags)) { dprintk("nfsd: Dropping request; may be revisited later\n"); nfsd_cache_update(rqstp, RC_NOCACHE, NULL); return 0; diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 6a3cf4c76dce..d4ea3e5246b0 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -255,6 +255,7 @@ struct svc_rqst { #define RQ_SECURE (0) /* secure port */ #define RQ_LOCAL (1) /* local request */ #define RQ_USEDEFERRAL (2) /* use deferral */ +#define RQ_DROPME (3) /* drop current reply */ unsigned long rq_flags; /* flags field */ void * rq_argp; /* decoded arguments */ @@ -271,7 +272,6 @@ struct svc_rqst { struct cache_req rq_chandle; /* handle passed to caches for * request delaying */ - bool rq_dropme; /* Catering to nfsd */ struct auth_domain * rq_client; /* RPC peer info */ struct auth_domain * rq_gssclient; /* "gss/"-style peer info */ diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 6d1facdebc92..355671f19a9f 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -416,7 +416,8 @@ TRACE_EVENT(xs_tcp_data_recv, __print_flags(flags, "|", \ { (1UL << RQ_SECURE), "RQ_SECURE"}, \ { (1UL << RQ_LOCAL), "RQ_LOCAL"}, \ - { (1UL << RQ_USEDEFERRAL), "RQ_USEDEFERRAL"}) + { (1UL << RQ_USEDEFERRAL), "RQ_USEDEFERRAL"}, \ + { (1UL << RQ_DROPME), "RQ_DROPME"}) TRACE_EVENT(svc_recv, TP_PROTO(struct svc_rqst *rqst, int status), @@ -459,13 +460,12 @@ DECLARE_EVENT_CLASS(svc_rqst_status, TP_fast_assign( __entry->addr = (struct sockaddr *)&rqst->rq_addr; __entry->xid = rqst->rq_xid; - __entry->dropme = (int)rqst->rq_dropme; __entry->status = status; __entry->flags = rqst->rq_flags; ), - TP_printk("addr=%pIScp rq_xid=0x%x dropme=%d status=%d flags=%s", - __entry->addr, be32_to_cpu(__entry->xid), __entry->dropme, + TP_printk("addr=%pIScp rq_xid=0x%x status=%d flags=%s", + __entry->addr, be32_to_cpu(__entry->xid), __entry->status, show_rqstp_flags(__entry->flags)) ); diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index f6a8f2f7a253..d8a9d603b786 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1091,7 +1091,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) rqstp->rq_splice_ok = true; /* Will be turned off only when NFSv4 Sessions are used */ set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); - rqstp->rq_dropme = false; + clear_bit(RQ_DROPME, &rqstp->rq_flags); /* Setup reply header */ rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp); @@ -1191,7 +1191,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) *statp = procp->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp); /* Encode reply */ - if (rqstp->rq_dropme) { + if (test_bit(RQ_DROPME, &rqstp->rq_flags)) { if (procp->pc_release) procp->pc_release(rqstp, NULL, rqstp->rq_resp); goto dropit; diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index a40f3755a33d..143c4c8ea2f1 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -1110,7 +1110,7 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req) } svc_xprt_get(rqstp->rq_xprt); dr->xprt = rqstp->rq_xprt; - rqstp->rq_dropme = true; + set_bit(RQ_DROPME, &rqstp->rq_flags); dr->handle.revisit = svc_revisit; return &dr->handle; -- cgit v1.2.3-59-g8ed1b From 779fb0f3af3089daa2e88cf8ef0ef0c5d2fecb40 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 19 Nov 2014 07:51:18 -0500 Subject: sunrpc: move rq_splice_ok flag into rq_flags Signed-off-by: Jeff Layton Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4proc.c | 2 +- fs/nfsd/nfs4xdr.c | 8 ++++---- fs/nfsd/vfs.c | 2 +- include/linux/sunrpc/svc.h | 6 +++--- include/trace/events/sunrpc.h | 3 ++- net/sunrpc/auth_gss/svcauth_gss.c | 2 +- net/sunrpc/svc.c | 2 +- 7 files changed, 13 insertions(+), 12 deletions(-) (limited to 'fs') diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 6f98393ad0d9..ac71d13c69ef 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -773,7 +773,7 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, * the client wants us to do more in this compound: */ if (!nfsd4_last_compound_op(rqstp)) - rqstp->rq_splice_ok = false; + clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); /* check stateid */ if ((status = nfs4_preprocess_stateid_op(SVC_NET(rqstp), diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 0622d4f4a9a2..8880ec8cfd11 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1731,7 +1731,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) argp->rqstp->rq_cachetype = cachethis ? RC_REPLBUFF : RC_NOCACHE; if (readcount > 1 || max_reply > PAGE_SIZE - auth_slack) - argp->rqstp->rq_splice_ok = false; + clear_bit(RQ_SPLICE_OK, &argp->rqstp->rq_flags); DECODE_TAIL; } @@ -3253,10 +3253,10 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, p = xdr_reserve_space(xdr, 8); /* eof flag and byte count */ if (!p) { - WARN_ON_ONCE(resp->rqstp->rq_splice_ok); + WARN_ON_ONCE(test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)); return nfserr_resource; } - if (resp->xdr.buf->page_len && resp->rqstp->rq_splice_ok) { + if (resp->xdr.buf->page_len && test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)) { WARN_ON_ONCE(1); return nfserr_resource; } @@ -3273,7 +3273,7 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, goto err_truncate; } - if (file->f_op->splice_read && resp->rqstp->rq_splice_ok) + if (file->f_op->splice_read && test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)) err = nfsd4_encode_splice_read(resp, read, file, maxcount); else err = nfsd4_encode_readv(resp, read, file, maxcount); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 60c25850fb16..cb00e48bc2b0 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -902,7 +902,7 @@ static __be32 nfsd_vfs_read(struct svc_rqst *rqstp, struct file *file, loff_t offset, struct kvec *vec, int vlen, unsigned long *count) { - if (file->f_op->splice_read && rqstp->rq_splice_ok) + if (file->f_op->splice_read && test_bit(RQ_SPLICE_OK, &rqstp->rq_flags)) return nfsd_splice_read(rqstp, file, offset, count); else return nfsd_readv(file, offset, vec, vlen, count); diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index d4ea3e5246b0..2714287fc4f6 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -256,6 +256,9 @@ struct svc_rqst { #define RQ_LOCAL (1) /* local request */ #define RQ_USEDEFERRAL (2) /* use deferral */ #define RQ_DROPME (3) /* drop current reply */ +#define RQ_SPLICE_OK (4) /* turned off in gss privacy + * to prevent encrypting page + * cache pages */ unsigned long rq_flags; /* flags field */ void * rq_argp; /* decoded arguments */ @@ -277,9 +280,6 @@ struct svc_rqst { struct auth_domain * rq_gssclient; /* "gss/"-style peer info */ int rq_cachetype; struct svc_cacherep * rq_cacherep; /* cache info */ - bool rq_splice_ok; /* turned off in gss privacy - * to prevent encrypting page - * cache pages */ struct task_struct *rq_task; /* service thread */ }; diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 355671f19a9f..5848fc235869 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -417,7 +417,8 @@ TRACE_EVENT(xs_tcp_data_recv, { (1UL << RQ_SECURE), "RQ_SECURE"}, \ { (1UL << RQ_LOCAL), "RQ_LOCAL"}, \ { (1UL << RQ_USEDEFERRAL), "RQ_USEDEFERRAL"}, \ - { (1UL << RQ_DROPME), "RQ_DROPME"}) + { (1UL << RQ_DROPME), "RQ_DROPME"}, \ + { (1UL << RQ_SPLICE_OK), "RQ_SPLICE_OK"}) TRACE_EVENT(svc_recv, TP_PROTO(struct svc_rqst *rqst, int status), diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index de856ddf5fed..224a82f24d3c 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -886,7 +886,7 @@ unwrap_priv_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct gs u32 priv_len, maj_stat; int pad, saved_len, remaining_len, offset; - rqstp->rq_splice_ok = false; + clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); priv_len = svc_getnl(&buf->head[0]); if (rqstp->rq_deferred) { diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index d8a9d603b786..2c1c49ebd84d 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1088,7 +1088,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) goto err_short_len; /* Will be turned off only in gss privacy case: */ - rqstp->rq_splice_ok = true; + set_bit(RQ_SPLICE_OK, &rqstp->rq_flags); /* Will be turned off only when NFSv4 Sessions are used */ set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); clear_bit(RQ_DROPME, &rqstp->rq_flags); -- cgit v1.2.3-59-g8ed1b From 0b5707e4524eb817b7b02863887820d27b56910a Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 19 Nov 2014 07:51:22 -0500 Subject: sunrpc: require svc_create callers to pass in meaningful shutdown routine Currently all svc_create callers pass in NULL for the shutdown parm, which then gets fixed up to be svc_rpcb_cleanup if the service uses rpcbind. Simplify this by instead having the the only caller that requires it (lockd) pass in svc_rpcb_cleanup and get rid of the special casing. Signed-off-by: Jeff Layton Signed-off-by: J. Bruce Fields --- fs/lockd/svc.c | 2 +- net/sunrpc/svc.c | 3 --- 2 files changed, 1 insertion(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index d1bb7ecfd201..e94c887da2d7 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -350,7 +350,7 @@ static struct svc_serv *lockd_create_svc(void) printk(KERN_WARNING "lockd_up: no pid, %d users??\n", nlmsvc_users); - serv = svc_create(&nlmsvc_program, LOCKD_BUFSIZE, NULL); + serv = svc_create(&nlmsvc_program, LOCKD_BUFSIZE, svc_rpcb_cleanup); if (!serv) { printk(KERN_WARNING "lockd_up: create service failed\n"); return ERR_PTR(-ENOMEM); diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 2c1c49ebd84d..a06a891012e5 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -482,9 +482,6 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools, spin_lock_init(&pool->sp_lock); } - if (svc_uses_rpcbind(serv) && (!serv->sv_shutdown)) - serv->sv_shutdown = svc_rpcb_cleanup; - return serv; } -- cgit v1.2.3-59-g8ed1b From ef17af2a817db97d42dd2ec0a425231748e23dbc Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Fri, 5 Dec 2014 16:40:07 +0100 Subject: fs: nfsd: Fix signedness bug in compare_blob Bugs similar to the one in acbbe6fbb240 (kcmp: fix standard comparison bug) are in rich supply. In this variant, the problem is that struct xdr_netobj::len has type unsigned int, so the expression o1->len - o2->len _also_ has type unsigned int; it has completely well-defined semantics, and the result is some non-negative integer, which is always representable in a long long. But this means that if the conditional triggers, we are guaranteed to return a positive value from compare_blob. In this case it could be fixed by - res = o1->len - o2->len; + res = (long long)o1->len - (long long)o2->len; but I'd rather eliminate the usually broken 'return a - b;' idiom. Reviewed-by: Jeff Layton Cc: Signed-off-by: Rasmus Villemoes Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'fs') diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 1379d86f7b4f..8770ba75b7b4 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1714,15 +1714,14 @@ static int copy_cred(struct svc_cred *target, struct svc_cred *source) return 0; } -static long long +static int compare_blob(const struct xdr_netobj *o1, const struct xdr_netobj *o2) { - long long res; - - res = o1->len - o2->len; - if (res) - return res; - return (long long)memcmp(o1->data, o2->data, o1->len); + if (o1->len < o2->len) + return -1; + if (o1->len > o2->len) + return 1; + return memcmp(o1->data, o2->data, o1->len); } static int same_name(const char *n1, const char *n2) @@ -1910,7 +1909,7 @@ add_clp_to_name_tree(struct nfs4_client *new_clp, struct rb_root *root) static struct nfs4_client * find_clp_in_name_tree(struct xdr_netobj *name, struct rb_root *root) { - long long cmp; + int cmp; struct rb_node *node = root->rb_node; struct nfs4_client *clp; -- cgit v1.2.3-59-g8ed1b From 5a64e56976f1ba98743e1678c0029a98e9034c81 Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Sun, 7 Dec 2014 16:05:47 -0500 Subject: nfsd4: fix xdr4 inclusion of escaped char Fix a bug where nfsd4_encode_components_esc() includes the esc_end char as an additional string encoding. Signed-off-by: Benjamin Coddington Cc: stable@vger.kernel.org Fixes: e7a0444aef4a "nfsd: add IPv6 addr escaping to fs_location hosts" Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4xdr.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'fs') diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 8880ec8cfd11..a8549f8fef57 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1812,6 +1812,9 @@ static __be32 nfsd4_encode_components_esc(struct xdr_stream *xdr, char sep, } else end++; + if (found_esc) + end = next; + str = end; } pathlen = htonl(xdr->buf->len - pathlen_offset); -- cgit v1.2.3-59-g8ed1b From bf7491f1be5e125eece2ec67e0f79d513caa6c7e Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Sun, 7 Dec 2014 16:05:48 -0500 Subject: nfsd4: fix xdr4 count of server in fs_location4 Fix a bug where nfsd4_encode_components_esc() incorrectly calculates the length of server array in fs_location4--note that it is a count of the number of array elements, not a length in bytes. Signed-off-by: Benjamin Coddington Fixes: 082d4bd72a45 (nfsd4: "backfill" using write_bytes_to_xdr_buf) Cc: stable@vger.kernel.org Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4xdr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index a8549f8fef57..e578c87d5527 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1817,7 +1817,7 @@ static __be32 nfsd4_encode_components_esc(struct xdr_stream *xdr, char sep, str = end; } - pathlen = htonl(xdr->buf->len - pathlen_offset); + pathlen = htonl(count); write_bytes_to_xdr_buf(xdr->buf, pathlen_offset, &pathlen, 4); return 0; } -- cgit v1.2.3-59-g8ed1b