summaryrefslogtreecommitdiffstats
path: root/fs/nfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/nfs')
-rw-r--r--fs/nfs/blocklayout/blocklayout.c45
-rw-r--r--fs/nfs/callback_proc.c19
-rw-r--r--fs/nfs/delegation.c11
-rw-r--r--fs/nfs/dir.c98
-rw-r--r--fs/nfs/direct.c279
-rw-r--r--fs/nfs/file.c7
-rw-r--r--fs/nfs/inode.c153
-rw-r--r--fs/nfs/internal.h20
-rw-r--r--fs/nfs/nfs3acl.c295
-rw-r--r--fs/nfs/nfs3proc.c113
-rw-r--r--fs/nfs/nfs3super.c3
-rw-r--r--fs/nfs/nfs4_fs.h12
-rw-r--r--fs/nfs/nfs4client.c36
-rw-r--r--fs/nfs/nfs4filelayout.c34
-rw-r--r--fs/nfs/nfs4filelayoutdev.c2
-rw-r--r--fs/nfs/nfs4namespace.c12
-rw-r--r--fs/nfs/nfs4proc.c303
-rw-r--r--fs/nfs/nfs4session.c25
-rw-r--r--fs/nfs/nfs4session.h2
-rw-r--r--fs/nfs/nfs4state.c29
-rw-r--r--fs/nfs/nfs4super.c16
-rw-r--r--fs/nfs/nfs4xdr.c52
-rw-r--r--fs/nfs/nfstrace.h1
-rw-r--r--fs/nfs/pnfs.c84
-rw-r--r--fs/nfs/pnfs.h16
-rw-r--r--fs/nfs/proc.c25
-rw-r--r--fs/nfs/read.c12
-rw-r--r--fs/nfs/super.c2
-rw-r--r--fs/nfs/unlink.c35
-rw-r--r--fs/nfs/write.c26
30 files changed, 937 insertions, 830 deletions
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index e242bbf7297..65d849bdf77 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -134,8 +134,8 @@ bl_submit_bio(int rw, struct bio *bio)
if (bio) {
get_parallel(bio->bi_private);
dprintk("%s submitting %s bio %u@%llu\n", __func__,
- rw == READ ? "read" : "write",
- bio->bi_size, (unsigned long long)bio->bi_sector);
+ rw == READ ? "read" : "write", bio->bi_iter.bi_size,
+ (unsigned long long)bio->bi_iter.bi_sector);
submit_bio(rw, bio);
}
return NULL;
@@ -156,7 +156,8 @@ static struct bio *bl_alloc_init_bio(int npg, sector_t isect,
}
if (bio) {
- bio->bi_sector = isect - be->be_f_offset + be->be_v_offset;
+ bio->bi_iter.bi_sector = isect - be->be_f_offset +
+ be->be_v_offset;
bio->bi_bdev = be->be_mdev;
bio->bi_end_io = end_io;
bio->bi_private = par;
@@ -201,18 +202,14 @@ static struct bio *bl_add_page_to_bio(struct bio *bio, int npg, int rw,
static void bl_end_io_read(struct bio *bio, int err)
{
struct parallel_io *par = bio->bi_private;
- const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
- struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
+ struct bio_vec *bvec;
+ int i;
- do {
- struct page *page = bvec->bv_page;
+ if (!err)
+ bio_for_each_segment_all(bvec, bio, i)
+ SetPageUptodate(bvec->bv_page);
- if (--bvec >= bio->bi_io_vec)
- prefetchw(&bvec->bv_page->flags);
- if (uptodate)
- SetPageUptodate(page);
- } while (bvec >= bio->bi_io_vec);
- if (!uptodate) {
+ if (err) {
struct nfs_read_data *rdata = par->data;
struct nfs_pgio_header *header = rdata->header;
@@ -383,20 +380,16 @@ static void mark_extents_written(struct pnfs_block_layout *bl,
static void bl_end_io_write_zero(struct bio *bio, int err)
{
struct parallel_io *par = bio->bi_private;
- const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
- struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
-
- do {
- struct page *page = bvec->bv_page;
+ struct bio_vec *bvec;
+ int i;
- if (--bvec >= bio->bi_io_vec)
- prefetchw(&bvec->bv_page->flags);
+ bio_for_each_segment_all(bvec, bio, i) {
/* This is the zeroing page we added */
- end_page_writeback(page);
- page_cache_release(page);
- } while (bvec >= bio->bi_io_vec);
+ end_page_writeback(bvec->bv_page);
+ page_cache_release(bvec->bv_page);
+ }
- if (unlikely(!uptodate)) {
+ if (unlikely(err)) {
struct nfs_write_data *data = par->data;
struct nfs_pgio_header *header = data->header;
@@ -519,7 +512,7 @@ bl_do_readpage_sync(struct page *page, struct pnfs_block_extent *be,
isect = (page->index << PAGE_CACHE_SECTOR_SHIFT) +
(offset / SECTOR_SIZE);
- bio->bi_sector = isect - be->be_f_offset + be->be_v_offset;
+ bio->bi_iter.bi_sector = isect - be->be_f_offset + be->be_v_offset;
bio->bi_bdev = be->be_mdev;
bio->bi_end_io = bl_read_single_end_io;
@@ -1220,7 +1213,7 @@ static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx)
end = DIV_ROUND_UP(i_size_read(inode), PAGE_CACHE_SIZE);
if (end != NFS_I(inode)->npages) {
rcu_read_lock();
- end = radix_tree_next_hole(&mapping->page_tree, idx + 1, ULONG_MAX);
+ end = page_cache_next_hole(mapping, idx + 1, ULONG_MAX);
rcu_read_unlock();
}
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index ae2e87b9545..41db5258e7a 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -112,7 +112,8 @@ out:
* TODO: keep track of all layouts (and delegations) in a hash table
* hashed by filehandle.
*/
-static struct pnfs_layout_hdr * get_layout_by_fh_locked(struct nfs_client *clp, struct nfs_fh *fh)
+static struct pnfs_layout_hdr * get_layout_by_fh_locked(struct nfs_client *clp,
+ struct nfs_fh *fh, nfs4_stateid *stateid)
{
struct nfs_server *server;
struct inode *ino;
@@ -120,17 +121,19 @@ static struct pnfs_layout_hdr * get_layout_by_fh_locked(struct nfs_client *clp,
list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
list_for_each_entry(lo, &server->layouts, plh_layouts) {
+ if (!nfs4_stateid_match_other(&lo->plh_stateid, stateid))
+ continue;
if (nfs_compare_fh(fh, &NFS_I(lo->plh_inode)->fh))
continue;
ino = igrab(lo->plh_inode);
if (!ino)
- continue;
+ break;
spin_lock(&ino->i_lock);
/* Is this layout in the process of being freed? */
if (NFS_I(ino)->layout != lo) {
spin_unlock(&ino->i_lock);
iput(ino);
- continue;
+ break;
}
pnfs_get_layout_hdr(lo);
spin_unlock(&ino->i_lock);
@@ -141,13 +144,14 @@ static struct pnfs_layout_hdr * get_layout_by_fh_locked(struct nfs_client *clp,
return NULL;
}
-static struct pnfs_layout_hdr * get_layout_by_fh(struct nfs_client *clp, struct nfs_fh *fh)
+static struct pnfs_layout_hdr * get_layout_by_fh(struct nfs_client *clp,
+ struct nfs_fh *fh, nfs4_stateid *stateid)
{
struct pnfs_layout_hdr *lo;
spin_lock(&clp->cl_lock);
rcu_read_lock();
- lo = get_layout_by_fh_locked(clp, fh);
+ lo = get_layout_by_fh_locked(clp, fh, stateid);
rcu_read_unlock();
spin_unlock(&clp->cl_lock);
@@ -162,9 +166,9 @@ static u32 initiate_file_draining(struct nfs_client *clp,
u32 rv = NFS4ERR_NOMATCHING_LAYOUT;
LIST_HEAD(free_me_list);
- lo = get_layout_by_fh(clp, &args->cbl_fh);
+ lo = get_layout_by_fh(clp, &args->cbl_fh, &args->cbl_stateid);
if (!lo)
- return NFS4ERR_NOMATCHING_LAYOUT;
+ goto out;
ino = lo->plh_inode;
spin_lock(&ino->i_lock);
@@ -179,6 +183,7 @@ static u32 initiate_file_draining(struct nfs_client *clp,
pnfs_free_lseg_list(&free_me_list);
pnfs_put_layout_hdr(lo);
iput(ino);
+out:
return rv;
}
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index ef792f29f83..5d8ccecf5f5 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -659,16 +659,19 @@ int nfs_async_inode_return_delegation(struct inode *inode,
rcu_read_lock();
delegation = rcu_dereference(NFS_I(inode)->delegation);
+ if (delegation == NULL)
+ goto out_enoent;
- if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid)) {
- rcu_read_unlock();
- return -ENOENT;
- }
+ if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid))
+ goto out_enoent;
nfs_mark_return_delegation(server, delegation);
rcu_read_unlock();
nfs_delegation_run_state_manager(clp);
return 0;
+out_enoent:
+ rcu_read_unlock();
+ return -ENOENT;
}
static struct inode *
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 812154aff98..d9f3d067cd1 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -69,21 +69,28 @@ const struct address_space_operations nfs_dir_aops = {
static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir, struct rpc_cred *cred)
{
+ struct nfs_inode *nfsi = NFS_I(dir);
struct nfs_open_dir_context *ctx;
ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
if (ctx != NULL) {
ctx->duped = 0;
- ctx->attr_gencount = NFS_I(dir)->attr_gencount;
+ ctx->attr_gencount = nfsi->attr_gencount;
ctx->dir_cookie = 0;
ctx->dup_cookie = 0;
ctx->cred = get_rpccred(cred);
+ spin_lock(&dir->i_lock);
+ list_add(&ctx->list, &nfsi->open_files);
+ spin_unlock(&dir->i_lock);
return ctx;
}
return ERR_PTR(-ENOMEM);
}
-static void put_nfs_open_dir_context(struct nfs_open_dir_context *ctx)
+static void put_nfs_open_dir_context(struct inode *dir, struct nfs_open_dir_context *ctx)
{
+ spin_lock(&dir->i_lock);
+ list_del(&ctx->list);
+ spin_unlock(&dir->i_lock);
put_rpccred(ctx->cred);
kfree(ctx);
}
@@ -126,7 +133,7 @@ out:
static int
nfs_closedir(struct inode *inode, struct file *filp)
{
- put_nfs_open_dir_context(filp->private_data);
+ put_nfs_open_dir_context(filp->f_path.dentry->d_inode, filp->private_data);
return 0;
}
@@ -274,6 +281,15 @@ out_eof:
return -EBADCOOKIE;
}
+static bool
+nfs_readdir_inode_mapping_valid(struct nfs_inode *nfsi)
+{
+ if (nfsi->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA))
+ return false;
+ smp_rmb();
+ return !test_bit(NFS_INO_INVALIDATING, &nfsi->flags);
+}
+
static
int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_descriptor_t *desc)
{
@@ -287,8 +303,8 @@ int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_des
struct nfs_open_dir_context *ctx = desc->file->private_data;
new_pos = desc->current_index + i;
- if (ctx->attr_gencount != nfsi->attr_gencount
- || (nfsi->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA))) {
+ if (ctx->attr_gencount != nfsi->attr_gencount ||
+ !nfs_readdir_inode_mapping_valid(nfsi)) {
ctx->duped = 0;
ctx->attr_gencount = nfsi->attr_gencount;
} else if (new_pos < desc->ctx->pos) {
@@ -297,10 +313,9 @@ int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_des
if (printk_ratelimit()) {
pr_notice("NFS: directory %pD2 contains a readdir loop."
"Please contact your server vendor. "
- "The file: %s has duplicate cookie %llu\n",
- desc->file,
- array->array[i].string.name,
- *desc->dir_cookie);
+ "The file: %.*s has duplicate cookie %llu\n",
+ desc->file, array->array[i].string.len,
+ array->array[i].string.name, *desc->dir_cookie);
}
status = -ELOOP;
goto out;
@@ -428,6 +443,22 @@ void nfs_advise_use_readdirplus(struct inode *dir)
set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(dir)->flags);
}
+/*
+ * This function is mainly for use by nfs_getattr().
+ *
+ * If this is an 'ls -l', we want to force use of readdirplus.
+ * Do this by checking if there is an active file descriptor
+ * and calling nfs_advise_use_readdirplus, then forcing a
+ * cache flush.
+ */
+void nfs_force_use_readdirplus(struct inode *dir)
+{
+ if (!list_empty(&NFS_I(dir)->open_files)) {
+ nfs_advise_use_readdirplus(dir);
+ nfs_zap_mapping(dir, dir->i_mapping);
+ }
+}
+
static
void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
{
@@ -806,6 +837,17 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc)
goto out;
}
+static bool nfs_dir_mapping_need_revalidate(struct inode *dir)
+{
+ struct nfs_inode *nfsi = NFS_I(dir);
+
+ if (nfs_attribute_cache_expired(dir))
+ return true;
+ if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
+ return true;
+ return false;
+}
+
/* The file offset position represents the dirent entry number. A
last cookie cache takes care of the common case of reading the
whole directory.
@@ -838,7 +880,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
desc->plus = nfs_use_readdirplus(inode, ctx) ? 1 : 0;
nfs_block_sillyrename(dentry);
- if (ctx->pos == 0 || nfs_attribute_cache_expired(inode))
+ if (ctx->pos == 0 || nfs_dir_mapping_need_revalidate(inode))
res = nfs_revalidate_mapping(inode, file->f_mapping);
if (res < 0)
goto out;
@@ -1404,7 +1446,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
/* Expect a negative dentry */
BUG_ON(dentry->d_inode);
- dfprintk(VFS, "NFS: atomic_open(%s/%ld), %pd\n",
+ dfprintk(VFS, "NFS: atomic_open(%s/%lu), %pd\n",
dir->i_sb->s_id, dir->i_ino, dentry);
err = nfs_check_flags(open_flags);
@@ -1594,7 +1636,7 @@ int nfs_create(struct inode *dir, struct dentry *dentry,
int open_flags = excl ? O_CREAT | O_EXCL : O_CREAT;
int error;
- dfprintk(VFS, "NFS: create(%s/%ld), %pd\n",
+ dfprintk(VFS, "NFS: create(%s/%lu), %pd\n",
dir->i_sb->s_id, dir->i_ino, dentry);
attr.ia_mode = mode;
@@ -1621,7 +1663,7 @@ nfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev)
struct iattr attr;
int status;
- dfprintk(VFS, "NFS: mknod(%s/%ld), %pd\n",
+ dfprintk(VFS, "NFS: mknod(%s/%lu), %pd\n",
dir->i_sb->s_id, dir->i_ino, dentry);
if (!new_valid_dev(rdev))
@@ -1650,7 +1692,7 @@ int nfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
struct iattr attr;
int error;
- dfprintk(VFS, "NFS: mkdir(%s/%ld), %pd\n",
+ dfprintk(VFS, "NFS: mkdir(%s/%lu), %pd\n",
dir->i_sb->s_id, dir->i_ino, dentry);
attr.ia_valid = ATTR_MODE;
@@ -1678,7 +1720,7 @@ int nfs_rmdir(struct inode *dir, struct dentry *dentry)
{
int error;
- dfprintk(VFS, "NFS: rmdir(%s/%ld), %pd\n",
+ dfprintk(VFS, "NFS: rmdir(%s/%lu), %pd\n",
dir->i_sb->s_id, dir->i_ino, dentry);
trace_nfs_rmdir_enter(dir, dentry);
@@ -1747,7 +1789,7 @@ int nfs_unlink(struct inode *dir, struct dentry *dentry)
int error;
int need_rehash = 0;
- dfprintk(VFS, "NFS: unlink(%s/%ld, %pd)\n", dir->i_sb->s_id,
+ dfprintk(VFS, "NFS: unlink(%s/%lu, %pd)\n", dir->i_sb->s_id,
dir->i_ino, dentry);
trace_nfs_unlink_enter(dir, dentry);
@@ -1798,7 +1840,7 @@ int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
unsigned int pathlen = strlen(symname);
int error;
- dfprintk(VFS, "NFS: symlink(%s/%ld, %pd, %s)\n", dir->i_sb->s_id,
+ dfprintk(VFS, "NFS: symlink(%s/%lu, %pd, %s)\n", dir->i_sb->s_id,
dir->i_ino, dentry, symname);
if (pathlen > PAGE_SIZE)
@@ -1821,7 +1863,7 @@ int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
error = NFS_PROTO(dir)->symlink(dir, dentry, page, pathlen, &attr);
trace_nfs_symlink_exit(dir, dentry, error);
if (error != 0) {
- dfprintk(VFS, "NFS: symlink(%s/%ld, %pd, %s) error %d\n",
+ dfprintk(VFS, "NFS: symlink(%s/%lu, %pd, %s) error %d\n",
dir->i_sb->s_id, dir->i_ino,
dentry, symname, error);
d_drop(dentry);
@@ -1837,6 +1879,11 @@ int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
GFP_KERNEL)) {
SetPageUptodate(page);
unlock_page(page);
+ /*
+ * add_to_page_cache_lru() grabs an extra page refcount.
+ * Drop it here to avoid leaking this page later.
+ */
+ page_cache_release(page);
} else
__free_page(page);
@@ -1897,6 +1944,7 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *old_inode = old_dentry->d_inode;
struct inode *new_inode = new_dentry->d_inode;
struct dentry *dentry = NULL, *rehash = NULL;
+ struct rpc_task *task;
int error = -EBUSY;
dfprintk(VFS, "NFS: rename(%pd2 -> %pd2, ct=%d)\n",
@@ -1944,8 +1992,16 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
if (new_inode != NULL)
NFS_PROTO(new_inode)->return_delegation(new_inode);
- error = NFS_PROTO(old_dir)->rename(old_dir, &old_dentry->d_name,
- new_dir, &new_dentry->d_name);
+ task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry, NULL);
+ if (IS_ERR(task)) {
+ error = PTR_ERR(task);
+ goto out;
+ }
+
+ error = rpc_wait_for_completion_task(task);
+ if (error == 0)
+ error = task->tk_status;
+ rpc_put_task(task);
nfs_mark_for_revalidate(old_inode);
out:
if (rehash)
@@ -2304,7 +2360,7 @@ out:
if (!res && (mask & MAY_EXEC) && !execute_ok(inode))
res = -EACCES;
- dfprintk(VFS, "NFS: permission(%s/%ld), mask=0x%x, res=%d\n",
+ dfprintk(VFS, "NFS: permission(%s/%lu), mask=0x%x, res=%d\n",
inode->i_sb->s_id, inode->i_ino, mask, res);
return res;
out_notsup:
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index d71d66c9e0a..b8797ae6831 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -222,14 +222,31 @@ out:
* Synchronous I/O uses a stack-allocated iocb. Thus we can't trust
* the iocb is still valid here if this is a synchronous request.
*/
-static void nfs_direct_complete(struct nfs_direct_req *dreq)
+static void nfs_direct_complete(struct nfs_direct_req *dreq, bool write)
{
+ struct inode *inode = dreq->inode;
+
+ if (dreq->iocb && write) {
+ loff_t pos = dreq->iocb->ki_pos + dreq->count;
+
+ spin_lock(&inode->i_lock);
+ if (i_size_read(inode) < pos)
+ i_size_write(inode, pos);
+ spin_unlock(&inode->i_lock);
+ }
+
+ if (write)
+ nfs_zap_mapping(inode, inode->i_mapping);
+
+ inode_dio_done(inode);
+
if (dreq->iocb) {
long res = (long) dreq->error;
if (!res)
res = (long) dreq->count;
aio_complete(dreq->iocb, res, 0);
}
+
complete_all(&dreq->completion);
nfs_direct_req_release(dreq);
@@ -237,9 +254,9 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq)
static void nfs_direct_readpage_release(struct nfs_page *req)
{
- dprintk("NFS: direct read done (%s/%lld %d@%lld)\n",
+ dprintk("NFS: direct read done (%s/%llu %d@%lld)\n",
req->wb_context->dentry->d_inode->i_sb->s_id,
- (long long)NFS_FILEID(req->wb_context->dentry->d_inode),
+ (unsigned long long)NFS_FILEID(req->wb_context->dentry->d_inode),
req->wb_bytes,
(long long)req_offset(req));
nfs_release_request(req);
@@ -272,7 +289,7 @@ static void nfs_direct_read_completion(struct nfs_pgio_header *hdr)
}
out_put:
if (put_dreq(dreq))
- nfs_direct_complete(dreq);
+ nfs_direct_complete(dreq, false);
hdr->release(hdr);
}
@@ -402,6 +419,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
loff_t pos, bool uio)
{
struct nfs_pageio_descriptor desc;
+ struct inode *inode = dreq->inode;
ssize_t result = -EINVAL;
size_t requested_bytes = 0;
unsigned long seg;
@@ -410,6 +428,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
&nfs_direct_read_completion_ops);
get_dreq(dreq);
desc.pg_dreq = dreq;
+ atomic_inc(&inode->i_dio_count);
for (seg = 0; seg < nr_segs; seg++) {
const struct iovec *vec = &iov[seg];
@@ -429,26 +448,69 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
* generic layer handle the completion.
*/
if (requested_bytes == 0) {
+ inode_dio_done(inode);
nfs_direct_req_release(dreq);
return result < 0 ? result : -EIO;
}
if (put_dreq(dreq))
- nfs_direct_complete(dreq);
+ nfs_direct_complete(dreq, false);
return 0;
}
-static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos, bool uio)
+/**
+ * nfs_file_direct_read - file direct read operation for NFS files
+ * @iocb: target I/O control block
+ * @iov: vector of user buffers into which to read data
+ * @nr_segs: size of iov vector
+ * @pos: byte offset in file where reading starts
+ *
+ * We use this function for direct reads instead of calling
+ * generic_file_aio_read() in order to avoid gfar's check to see if
+ * the request starts before the end of the file. For that check
+ * to work, we must generate a GETATTR before each direct read, and
+ * even then there is a window between the GETATTR and the subsequent
+ * READ where the file size could change. Our preference is simply
+ * to do all reads the application wants, and the server will take
+ * care of managing the end of file boundary.
+ *
+ * This function also eliminates unnecessarily updating the file's
+ * atime locally, as the NFS server sets the file's atime, and this
+ * client must read the updated atime from the server back into its
+ * cache.
+ */
+ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos, bool uio)
{
- ssize_t result = -ENOMEM;
- struct inode *inode = iocb->ki_filp->f_mapping->host;
+ struct file *file = iocb->ki_filp;
+ struct address_space *mapping = file->f_mapping;
+ struct inode *inode = mapping->host;
struct nfs_direct_req *dreq;
struct nfs_lock_context *l_ctx;
+ ssize_t result = -EINVAL;
+ size_t count;
+ count = iov_length(iov, nr_segs);
+ nfs_add_stats(mapping->host, NFSIOS_DIRECTREADBYTES, count);
+
+ dfprintk(FILE, "NFS: direct read(%pD2, %zd@%Ld)\n",
+ file, count, (long long) pos);
+
+ result = 0;
+ if (!count)
+ goto out;
+
+ mutex_lock(&inode->i_mutex);
+ result = nfs_sync_mapping(mapping);
+ if (result)
+ goto out_unlock;
+
+ task_io_account_read(count);
+
+ result = -ENOMEM;
dreq = nfs_direct_req_alloc();
if (dreq == NULL)
- goto out;
+ goto out_unlock;
dreq->inode = inode;
dreq->bytes_left = iov_length(iov, nr_segs);
@@ -464,20 +526,26 @@ static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov,
NFS_I(inode)->read_io += iov_length(iov, nr_segs);
result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos, uio);
- if (!result)
+
+ mutex_unlock(&inode->i_mutex);
+
+ if (!result) {
result = nfs_direct_wait(dreq);
+ if (result > 0)
+ iocb->ki_pos = pos + result;
+ }
+
+ nfs_direct_req_release(dreq);
+ return result;
+
out_release:
nfs_direct_req_release(dreq);
+out_unlock:
+ mutex_unlock(&inode->i_mutex);
out:
return result;
}
-static void nfs_inode_dio_write_done(struct inode *inode)
-{
- nfs_zap_mapping(inode, inode->i_mapping);
- inode_dio_done(inode);
-}
-
#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
{
@@ -593,8 +661,7 @@ static void nfs_direct_write_schedule_work(struct work_struct *work)
nfs_direct_write_reschedule(dreq);
break;
default:
- nfs_inode_dio_write_done(dreq->inode);
- nfs_direct_complete(dreq);
+ nfs_direct_complete(dreq, true);
}
}
@@ -610,8 +677,7 @@ static void nfs_direct_write_schedule_work(struct work_struct *work)
static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode *inode)
{
- nfs_inode_dio_write_done(inode);
- nfs_direct_complete(dreq);
+ nfs_direct_complete(dreq, true);
}
#endif
@@ -842,93 +908,6 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
return 0;
}
-static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos,
- size_t count, bool uio)
-{
- ssize_t result = -ENOMEM;
- struct inode *inode = iocb->ki_filp->f_mapping->host;
- struct nfs_direct_req *dreq;
- struct nfs_lock_context *l_ctx;
-
- dreq = nfs_direct_req_alloc();
- if (!dreq)
- goto out;
-
- dreq->inode = inode;
- dreq->bytes_left = count;
- dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
- l_ctx = nfs_get_lock_context(dreq->ctx);
- if (IS_ERR(l_ctx)) {
- result = PTR_ERR(l_ctx);
- goto out_release;
- }
- dreq->l_ctx = l_ctx;
- if (!is_sync_kiocb(iocb))
- dreq->iocb = iocb;
-
- result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos, uio);
- if (!result)
- result = nfs_direct_wait(dreq);
-out_release:
- nfs_direct_req_release(dreq);
-out:
- return result;
-}
-
-/**
- * nfs_file_direct_read - file direct read operation for NFS files
- * @iocb: target I/O control block
- * @iov: vector of user buffers into which to read data
- * @nr_segs: size of iov vector
- * @pos: byte offset in file where reading starts
- *
- * We use this function for direct reads instead of calling
- * generic_file_aio_read() in order to avoid gfar's check to see if
- * the request starts before the end of the file. For that check
- * to work, we must generate a GETATTR before each direct read, and
- * even then there is a window between the GETATTR and the subsequent
- * READ where the file size could change. Our preference is simply
- * to do all reads the application wants, and the server will take
- * care of managing the end of file boundary.
- *
- * This function also eliminates unnecessarily updating the file's
- * atime locally, as the NFS server sets the file's atime, and this
- * client must read the updated atime from the server back into its
- * cache.
- */
-ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos, bool uio)
-{
- ssize_t retval = -EINVAL;
- struct file *file = iocb->ki_filp;
- struct address_space *mapping = file->f_mapping;
- size_t count;
-
- count = iov_length(iov, nr_segs);
- nfs_add_stats(mapping->host, NFSIOS_DIRECTREADBYTES, count);
-
- dfprintk(FILE, "NFS: direct read(%pD2, %zd@%Ld)\n",
- file, count, (long long) pos);
-
- retval = 0;
- if (!count)
- goto out;
-
- retval = nfs_sync_mapping(mapping);
- if (retval)
- goto out;
-
- task_io_account_read(count);
-
- retval = nfs_direct_read(iocb, iov, nr_segs, pos, uio);
- if (retval > 0)
- iocb->ki_pos = pos + retval;
-
-out:
- return retval;
-}
-
/**
* nfs_file_direct_write - file direct write operation for NFS files
* @iocb: target I/O control block
@@ -954,46 +933,96 @@ out:
ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos, bool uio)
{
- ssize_t retval = -EINVAL;
+ ssize_t result = -EINVAL;
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
+ struct inode *inode = mapping->host;
+ struct nfs_direct_req *dreq;
+ struct nfs_lock_context *l_ctx;
+ loff_t end;
size_t count;
count = iov_length(iov, nr_segs);
+ end = (pos + count - 1) >> PAGE_CACHE_SHIFT;
+
nfs_add_stats(mapping->host, NFSIOS_DIRECTWRITTENBYTES, count);
dfprintk(FILE, "NFS: direct write(%pD2, %zd@%Ld)\n",
file, count, (long long) pos);
- retval = generic_write_checks(file, &pos, &count, 0);
- if (retval)
+ result = generic_write_checks(file, &pos, &count, 0);
+ if (result)
goto out;
- retval = -EINVAL;
+ result = -EINVAL;
if ((ssize_t) count < 0)
goto out;
- retval = 0;
+ result = 0;
if (!count)
goto out;
- retval = nfs_sync_mapping(mapping);
- if (retval)
- goto out;
+ mutex_lock(&inode->i_mutex);
+
+ result = nfs_sync_mapping(mapping);
+ if (result)
+ goto out_unlock;
+
+ if (mapping->nrpages) {
+ result = invalidate_inode_pages2_range(mapping,
+ pos >> PAGE_CACHE_SHIFT, end);
+ if (result)
+ goto out_unlock;
+ }
task_io_account_write(count);
- retval = nfs_direct_write(iocb, iov, nr_segs, pos, count, uio);
- if (retval > 0) {
- struct inode *inode = mapping->host;
+ result = -ENOMEM;
+ dreq = nfs_direct_req_alloc();
+ if (!dreq)
+ goto out_unlock;
- iocb->ki_pos = pos + retval;
- spin_lock(&inode->i_lock);
- if (i_size_read(inode) < iocb->ki_pos)
- i_size_write(inode, iocb->ki_pos);
- spin_unlock(&inode->i_lock);
+ dreq->inode = inode;
+ dreq->bytes_left = count;
+ dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
+ l_ctx = nfs_get_lock_context(dreq->ctx);
+ if (IS_ERR(l_ctx)) {
+ result = PTR_ERR(l_ctx);
+ goto out_release;
+ }
+ dreq->l_ctx = l_ctx;
+ if (!is_sync_kiocb(iocb))
+ dreq->iocb = iocb;
+
+ result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos, uio);
+
+ if (mapping->nrpages) {
+ invalidate_inode_pages2_range(mapping,
+ pos >> PAGE_CACHE_SHIFT, end);
}
+
+ mutex_unlock(&inode->i_mutex);
+
+ if (!result) {
+ result = nfs_direct_wait(dreq);
+ if (result > 0) {
+ struct inode *inode = mapping->host;
+
+ iocb->ki_pos = pos + result;
+ spin_lock(&inode->i_lock);
+ if (i_size_read(inode) < iocb->ki_pos)
+ i_size_write(inode, iocb->ki_pos);
+ spin_unlock(&inode->i_lock);
+ }
+ }
+ nfs_direct_req_release(dreq);
+ return result;
+
+out_release:
+ nfs_direct_req_release(dreq);
+out_unlock:
+ mutex_unlock(&inode->i_mutex);
out:
- return retval;
+ return result;
}
/**
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index e2fcacf07de..284ca901fe1 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -354,7 +354,7 @@ static int nfs_write_begin(struct file *file, struct address_space *mapping,
struct page *page;
int once_thru = 0;
- dfprintk(PAGECACHE, "NFS: write_begin(%pD2(%ld), %u@%lld)\n",
+ dfprintk(PAGECACHE, "NFS: write_begin(%pD2(%lu), %u@%lld)\n",
file, mapping->host->i_ino, len, (long long) pos);
start:
@@ -395,7 +395,7 @@ static int nfs_write_end(struct file *file, struct address_space *mapping,
struct nfs_open_context *ctx = nfs_file_open_context(file);
int status;
- dfprintk(PAGECACHE, "NFS: write_end(%pD2(%ld), %u@%lld)\n",
+ dfprintk(PAGECACHE, "NFS: write_end(%pD2(%lu), %u@%lld)\n",
file, mapping->host->i_ino, len, (long long) pos);
/*
@@ -585,7 +585,7 @@ static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
int ret = VM_FAULT_NOPAGE;
struct address_space *mapping;
- dfprintk(PAGECACHE, "NFS: vm_page_mkwrite(%pD2(%ld), offset %lld)\n",
+ dfprintk(PAGECACHE, "NFS: vm_page_mkwrite(%pD2(%lu), offset %lld)\n",
filp, filp->f_mapping->host->i_ino,
(long long)page_offset(page));
@@ -617,6 +617,7 @@ out:
static const struct vm_operations_struct nfs_file_vm_ops = {
.fault = filemap_fault,
+ .map_pages = filemap_map_pages,
.page_mkwrite = nfs_vm_page_mkwrite,
.remap_pages = generic_file_remap_pages,
};
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 00ad1c2b217..0c438973f3c 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -128,7 +128,7 @@ EXPORT_SYMBOL_GPL(nfs_clear_inode);
void nfs_evict_inode(struct inode *inode)
{
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
nfs_clear_inode(inode);
}
@@ -164,17 +164,16 @@ static void nfs_zap_caches_locked(struct inode *inode)
if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) {
nfs_fscache_invalidate(inode);
nfsi->cache_validity |= NFS_INO_INVALID_ATTR
- | NFS_INO_INVALID_LABEL
| NFS_INO_INVALID_DATA
| NFS_INO_INVALID_ACCESS
| NFS_INO_INVALID_ACL
| NFS_INO_REVAL_PAGECACHE;
} else
nfsi->cache_validity |= NFS_INO_INVALID_ATTR
- | NFS_INO_INVALID_LABEL
| NFS_INO_INVALID_ACCESS
| NFS_INO_INVALID_ACL
| NFS_INO_REVAL_PAGECACHE;
+ nfs_zap_label_cache_locked(nfsi);
}
void nfs_zap_caches(struct inode *inode)
@@ -266,6 +265,13 @@ nfs_init_locked(struct inode *inode, void *opaque)
}
#ifdef CONFIG_NFS_V4_SECURITY_LABEL
+static void nfs_clear_label_invalid(struct inode *inode)
+{
+ spin_lock(&inode->i_lock);
+ NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_LABEL;
+ spin_unlock(&inode->i_lock);
+}
+
void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr,
struct nfs4_label *label)
{
@@ -283,6 +289,7 @@ void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr,
__func__,
(char *)label->label,
label->len, error);
+ nfs_clear_label_invalid(inode);
}
}
@@ -458,9 +465,9 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
unlock_new_inode(inode);
} else
nfs_refresh_inode(inode, fattr);
- dprintk("NFS: nfs_fhget(%s/%Ld fh_crc=0x%08x ct=%d)\n",
+ dprintk("NFS: nfs_fhget(%s/%Lu fh_crc=0x%08x ct=%d)\n",
inode->i_sb->s_id,
- (long long)NFS_FILEID(inode),
+ (unsigned long long)NFS_FILEID(inode),
nfs_display_fhandle_hash(fh),
atomic_read(&inode->i_count));
@@ -581,6 +588,25 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr)
}
EXPORT_SYMBOL_GPL(nfs_setattr_update_inode);
+static void nfs_request_parent_use_readdirplus(struct dentry *dentry)
+{
+ struct dentry *parent;
+
+ parent = dget_parent(dentry);
+ nfs_force_use_readdirplus(parent->d_inode);
+ dput(parent);
+}
+
+static bool nfs_need_revalidate_inode(struct inode *inode)
+{
+ if (NFS_I(inode)->cache_validity &
+ (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_LABEL))
+ return true;
+ if (nfs_attribute_cache_expired(inode))
+ return true;
+ return false;
+}
+
int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
{
struct inode *inode = dentry->d_inode;
@@ -609,10 +635,13 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode)))
need_atime = 0;
- if (need_atime)
- err = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
- else
- err = nfs_revalidate_inode(NFS_SERVER(inode), inode);
+ if (need_atime || nfs_need_revalidate_inode(inode)) {
+ struct nfs_server *server = NFS_SERVER(inode);
+
+ if (server->caps & NFS_CAP_READDIRPLUS)
+ nfs_request_parent_use_readdirplus(dentry);
+ err = __nfs_revalidate_inode(server, inode);
+ }
if (!err) {
generic_fillattr(inode, stat);
stat->ino = nfs_compat_user_ino64(NFS_FILEID(inode));
@@ -870,8 +899,8 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
struct nfs_fattr *fattr = NULL;
struct nfs_inode *nfsi = NFS_I(inode);
- dfprintk(PAGECACHE, "NFS: revalidating (%s/%Ld)\n",
- inode->i_sb->s_id, (long long)NFS_FILEID(inode));
+ dfprintk(PAGECACHE, "NFS: revalidating (%s/%Lu)\n",
+ inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode));
trace_nfs_revalidate_inode_enter(inode);
@@ -895,9 +924,9 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
status = NFS_PROTO(inode)->getattr(server, NFS_FH(inode), fattr, label);
if (status != 0) {
- dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Ld) getattr failed, error=%d\n",
+ dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Lu) getattr failed, error=%d\n",
inode->i_sb->s_id,
- (long long)NFS_FILEID(inode), status);
+ (unsigned long long)NFS_FILEID(inode), status);
if (status == -ESTALE) {
nfs_zap_caches(inode);
if (!S_ISDIR(inode->i_mode))
@@ -908,9 +937,9 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
status = nfs_refresh_inode(inode, fattr);
if (status) {
- dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Ld) refresh failed, error=%d\n",
+ dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Lu) refresh failed, error=%d\n",
inode->i_sb->s_id,
- (long long)NFS_FILEID(inode), status);
+ (unsigned long long)NFS_FILEID(inode), status);
goto err_out;
}
@@ -919,9 +948,9 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
nfs_setsecurity(inode, fattr, label);
- dfprintk(PAGECACHE, "NFS: (%s/%Ld) revalidation complete\n",
+ dfprintk(PAGECACHE, "NFS: (%s/%Lu) revalidation complete\n",
inode->i_sb->s_id,
- (long long)NFS_FILEID(inode));
+ (unsigned long long)NFS_FILEID(inode));
err_out:
nfs4_label_free(label);
@@ -954,9 +983,7 @@ int nfs_attribute_cache_expired(struct inode *inode)
*/
int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
{
- if (!(NFS_I(inode)->cache_validity &
- (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_LABEL))
- && !nfs_attribute_cache_expired(inode))
+ if (!nfs_need_revalidate_inode(inode))
return NFS_STALE(inode) ? -ESTALE : 0;
return __nfs_revalidate_inode(server, inode);
}
@@ -977,16 +1004,17 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map
if (ret < 0)
return ret;
}
- spin_lock(&inode->i_lock);
- nfsi->cache_validity &= ~NFS_INO_INVALID_DATA;
- if (S_ISDIR(inode->i_mode))
+ if (S_ISDIR(inode->i_mode)) {
+ spin_lock(&inode->i_lock);
memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
- spin_unlock(&inode->i_lock);
+ spin_unlock(&inode->i_lock);
+ }
nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE);
nfs_fscache_wait_on_invalidate(inode);
- dfprintk(PAGECACHE, "NFS: (%s/%Ld) data cache invalidated\n",
- inode->i_sb->s_id, (long long)NFS_FILEID(inode));
+ dfprintk(PAGECACHE, "NFS: (%s/%Lu) data cache invalidated\n",
+ inode->i_sb->s_id,
+ (unsigned long long)NFS_FILEID(inode));
return 0;
}
@@ -1007,6 +1035,7 @@ static bool nfs_mapping_need_revalidate_inode(struct inode *inode)
int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
{
struct nfs_inode *nfsi = NFS_I(inode);
+ unsigned long *bitlock = &nfsi->flags;
int ret = 0;
/* swapfiles are not supposed to be shared. */
@@ -1018,12 +1047,46 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
if (ret < 0)
goto out;
}
- if (nfsi->cache_validity & NFS_INO_INVALID_DATA) {
- trace_nfs_invalidate_mapping_enter(inode);
- ret = nfs_invalidate_mapping(inode, mapping);
- trace_nfs_invalidate_mapping_exit(inode, ret);
+
+ /*
+ * We must clear NFS_INO_INVALID_DATA first to ensure that
+ * invalidations that come in while we're shooting down the mappings
+ * are respected. But, that leaves a race window where one revalidator
+ * can clear the flag, and then another checks it before the mapping
+ * gets invalidated. Fix that by serializing access to this part of
+ * the function.
+ *
+ * At the same time, we need to allow other tasks to see whether we
+ * might be in the middle of invalidating the pages, so we only set
+ * the bit lock here if it looks like we're going to be doing that.
+ */
+ for (;;) {
+ ret = wait_on_bit(bitlock, NFS_INO_INVALIDATING,
+ nfs_wait_bit_killable, TASK_KILLABLE);
+ if (ret)
+ goto out;
+ spin_lock(&inode->i_lock);
+ if (test_bit(NFS_INO_INVALIDATING, bitlock)) {
+ spin_unlock(&inode->i_lock);
+ continue;
+ }
+ if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
+ break;
+ spin_unlock(&inode->i_lock);
+ goto out;
}
+ set_bit(NFS_INO_INVALIDATING, bitlock);
+ smp_wmb();
+ nfsi->cache_validity &= ~NFS_INO_INVALID_DATA;
+ spin_unlock(&inode->i_lock);
+ trace_nfs_invalidate_mapping_enter(inode);
+ ret = nfs_invalidate_mapping(inode, mapping);
+ trace_nfs_invalidate_mapping_exit(inode, ret);
+
+ clear_bit_unlock(NFS_INO_INVALIDATING, bitlock);
+ smp_mb__after_clear_bit();
+ wake_up_bit(bitlock, NFS_INO_INVALIDATING);
out:
return ret;
}
@@ -1282,12 +1345,28 @@ static int nfs_inode_attrs_need_update(const struct inode *inode, const struct n
((long)nfsi->attr_gencount - (long)nfs_read_attr_generation_counter() > 0);
}
+/*
+ * Don't trust the change_attribute, mtime, ctime or size if
+ * a pnfs LAYOUTCOMMIT is outstanding
+ */
+static void nfs_inode_attrs_handle_layoutcommit(struct inode *inode,
+ struct nfs_fattr *fattr)
+{
+ if (pnfs_layoutcommit_outstanding(inode))
+ fattr->valid &= ~(NFS_ATTR_FATTR_CHANGE |
+ NFS_ATTR_FATTR_MTIME |
+ NFS_ATTR_FATTR_CTIME |
+ NFS_ATTR_FATTR_SIZE);
+}
+
static int nfs_refresh_inode_locked(struct inode *inode, struct nfs_fattr *fattr)
{
int ret;
trace_nfs_refresh_inode_enter(inode);
+ nfs_inode_attrs_handle_layoutcommit(inode, fattr);
+
if (nfs_inode_attrs_need_update(inode, fattr))
ret = nfs_update_inode(inode, fattr);
else
@@ -1434,7 +1513,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
unsigned long now = jiffies;
unsigned long save_cache_validity;
- dfprintk(VFS, "NFS: %s(%s/%ld fh_crc=0x%08x ct=%d info=0x%x)\n",
+ dfprintk(VFS, "NFS: %s(%s/%lu fh_crc=0x%08x ct=%d info=0x%x)\n",
__func__, inode->i_sb->s_id, inode->i_ino,
nfs_display_fhandle_hash(NFS_FH(inode)),
atomic_read(&inode->i_count), fattr->valid);
@@ -1455,7 +1534,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
/*
* Big trouble! The inode has become a different object.
*/
- printk(KERN_DEBUG "NFS: %s: inode %ld mode changed, %07o to %07o\n",
+ printk(KERN_DEBUG "NFS: %s: inode %lu mode changed, %07o to %07o\n",
__func__, inode->i_ino, inode->i_mode, fattr->mode);
goto out_err;
}
@@ -1517,8 +1596,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
if (new_isize != cur_isize) {
/* Do we perhaps have any outstanding writes, or has
* the file grown beyond our last write? */
- if ((nfsi->npages == 0 && !test_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) ||
- new_isize > cur_isize) {
+ if ((nfsi->npages == 0) || new_isize > cur_isize) {
i_size_write(inode, new_isize);
invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
}
@@ -1597,7 +1675,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
inode->i_blocks = fattr->du.nfs2.blocks;
/* Update attrtimeo value if we're out of the unstable period */
- if (invalid & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_LABEL)) {
+ if (invalid & NFS_INO_INVALID_ATTR) {
nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE);
nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
nfsi->attrtimeo_timestamp = now;
@@ -1610,7 +1688,6 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
}
}
invalid &= ~NFS_INO_INVALID_ATTR;
- invalid &= ~NFS_INO_INVALID_LABEL;
/* Don't invalidate the data if we were to blame */
if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)
|| S_ISLNK(inode->i_mode)))
@@ -1641,10 +1718,6 @@ struct inode *nfs_alloc_inode(struct super_block *sb)
return NULL;
nfsi->flags = 0UL;
nfsi->cache_validity = 0UL;
-#ifdef CONFIG_NFS_V3_ACL
- nfsi->acl_access = ERR_PTR(-EAGAIN);
- nfsi->acl_default = ERR_PTR(-EAGAIN);
-#endif
#if IS_ENABLED(CONFIG_NFS_V4)
nfsi->nfs4_acl = NULL;
#endif /* CONFIG_NFS_V4 */
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 8b5cc04a861..dd8bfc2e246 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -176,7 +176,8 @@ extern struct nfs_server *nfs4_create_server(
extern struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *,
struct nfs_fh *);
extern int nfs4_update_server(struct nfs_server *server, const char *hostname,
- struct sockaddr *sap, size_t salen);
+ struct sockaddr *sap, size_t salen,
+ struct net *net);
extern void nfs_free_server(struct nfs_server *server);
extern struct nfs_server *nfs_clone_server(struct nfs_server *,
struct nfs_fh *,
@@ -279,9 +280,18 @@ static inline void nfs4_label_free(struct nfs4_label *label)
}
return;
}
+
+static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi)
+{
+ if (nfs_server_capable(&nfsi->vfs_inode, NFS_CAP_SECURITY_LABEL))
+ nfsi->cache_validity |= NFS_INO_INVALID_LABEL;
+}
#else
static inline struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { return NULL; }
static inline void nfs4_label_free(void *label) {}
+static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi)
+{
+}
#endif /* CONFIG_NFS_V4_SECURITY_LABEL */
/* proc.c */
@@ -291,6 +301,7 @@ extern struct nfs_client *nfs_init_client(struct nfs_client *clp,
const char *ip_addr);
/* dir.c */
+extern void nfs_force_use_readdirplus(struct inode *dir);
extern unsigned long nfs_access_cache_count(struct shrinker *shrink,
struct shrink_control *sc);
extern unsigned long nfs_access_cache_scan(struct shrinker *shrink,
@@ -464,6 +475,13 @@ extern int nfs_migrate_page(struct address_space *,
#define nfs_migrate_page NULL
#endif
+/* unlink.c */
+extern struct rpc_task *
+nfs_async_rename(struct inode *old_dir, struct inode *new_dir,
+ struct dentry *old_dentry, struct dentry *new_dentry,
+ void (*complete)(struct rpc_task *, struct nfs_renamedata *));
+extern int nfs_sillyrename(struct inode *dir, struct dentry *dentry);
+
/* direct.c */
void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo,
struct nfs_direct_req *dreq);
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index 4a1aafba6a2..871d6eda8db 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -10,179 +10,7 @@
#define NFSDBG_FACILITY NFSDBG_PROC
-ssize_t nfs3_listxattr(struct dentry *dentry, char *buffer, size_t size)
-{
- struct inode *inode = dentry->d_inode;
- struct posix_acl *acl;
- int pos=0, len=0;
-
-# define output(s) do { \
- if (pos + sizeof(s) <= size) { \
- memcpy(buffer + pos, s, sizeof(s)); \
- pos += sizeof(s); \
- } \
- len += sizeof(s); \
- } while(0)
-
- acl = nfs3_proc_getacl(inode, ACL_TYPE_ACCESS);
- if (IS_ERR(acl))
- return PTR_ERR(acl);
- if (acl) {
- output("system.posix_acl_access");
- posix_acl_release(acl);
- }
-
- if (S_ISDIR(inode->i_mode)) {
- acl = nfs3_proc_getacl(inode, ACL_TYPE_DEFAULT);
- if (IS_ERR(acl))
- return PTR_ERR(acl);
- if (acl) {
- output("system.posix_acl_default");
- posix_acl_release(acl);
- }
- }
-
-# undef output
-
- if (!buffer || len <= size)
- return len;
- return -ERANGE;
-}
-
-ssize_t nfs3_getxattr(struct dentry *dentry, const char *name,
- void *buffer, size_t size)
-{
- struct inode *inode = dentry->d_inode;
- struct posix_acl *acl;
- int type, error = 0;
-
- if (strcmp(name, POSIX_ACL_XATTR_ACCESS) == 0)
- type = ACL_TYPE_ACCESS;
- else if (strcmp(name, POSIX_ACL_XATTR_DEFAULT) == 0)
- type = ACL_TYPE_DEFAULT;
- else
- return -EOPNOTSUPP;
-
- acl = nfs3_proc_getacl(inode, type);
- if (IS_ERR(acl))
- return PTR_ERR(acl);
- else if (acl) {
- if (type == ACL_TYPE_ACCESS && acl->a_count == 0)
- error = -ENODATA;
- else
- error = posix_acl_to_xattr(&init_user_ns, acl, buffer, size);
- posix_acl_release(acl);
- } else
- error = -ENODATA;
-
- return error;
-}
-
-int nfs3_setxattr(struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
-{
- struct inode *inode = dentry->d_inode;
- struct posix_acl *acl;
- int type, error;
-
- if (strcmp(name, POSIX_ACL_XATTR_ACCESS) == 0)
- type = ACL_TYPE_ACCESS;
- else if (strcmp(name, POSIX_ACL_XATTR_DEFAULT) == 0)
- type = ACL_TYPE_DEFAULT;
- else
- return -EOPNOTSUPP;
-
- acl = posix_acl_from_xattr(&init_user_ns, value, size);
- if (IS_ERR(acl))
- return PTR_ERR(acl);
- error = nfs3_proc_setacl(inode, type, acl);
- posix_acl_release(acl);
-
- return error;
-}
-
-int nfs3_removexattr(struct dentry *dentry, const char *name)
-{
- struct inode *inode = dentry->d_inode;
- int type;
-
- if (strcmp(name, POSIX_ACL_XATTR_ACCESS) == 0)
- type = ACL_TYPE_ACCESS;
- else if (strcmp(name, POSIX_ACL_XATTR_DEFAULT) == 0)
- type = ACL_TYPE_DEFAULT;
- else
- return -EOPNOTSUPP;
-
- return nfs3_proc_setacl(inode, type, NULL);
-}
-
-static void __nfs3_forget_cached_acls(struct nfs_inode *nfsi)
-{
- if (!IS_ERR(nfsi->acl_access)) {
- posix_acl_release(nfsi->acl_access);
- nfsi->acl_access = ERR_PTR(-EAGAIN);
- }
- if (!IS_ERR(nfsi->acl_default)) {
- posix_acl_release(nfsi->acl_default);
- nfsi->acl_default = ERR_PTR(-EAGAIN);
- }
-}
-
-void nfs3_forget_cached_acls(struct inode *inode)
-{
- dprintk("NFS: nfs3_forget_cached_acls(%s/%ld)\n", inode->i_sb->s_id,
- inode->i_ino);
- spin_lock(&inode->i_lock);
- __nfs3_forget_cached_acls(NFS_I(inode));
- spin_unlock(&inode->i_lock);
-}
-
-static struct posix_acl *nfs3_get_cached_acl(struct inode *inode, int type)
-{
- struct nfs_inode *nfsi = NFS_I(inode);
- struct posix_acl *acl = ERR_PTR(-EINVAL);
-
- spin_lock(&inode->i_lock);
- switch(type) {
- case ACL_TYPE_ACCESS:
- acl = nfsi->acl_access;
- break;
-
- case ACL_TYPE_DEFAULT:
- acl = nfsi->acl_default;
- break;
-
- default:
- goto out;
- }
- if (IS_ERR(acl))
- acl = ERR_PTR(-EAGAIN);
- else
- acl = posix_acl_dup(acl);
-out:
- spin_unlock(&inode->i_lock);
- dprintk("NFS: nfs3_get_cached_acl(%s/%ld, %d) = %p\n", inode->i_sb->s_id,
- inode->i_ino, type, acl);
- return acl;
-}
-
-static void nfs3_cache_acls(struct inode *inode, struct posix_acl *acl,
- struct posix_acl *dfacl)
-{
- struct nfs_inode *nfsi = NFS_I(inode);
-
- dprintk("nfs3_cache_acls(%s/%ld, %p, %p)\n", inode->i_sb->s_id,
- inode->i_ino, acl, dfacl);
- spin_lock(&inode->i_lock);
- __nfs3_forget_cached_acls(NFS_I(inode));
- if (!IS_ERR(acl))
- nfsi->acl_access = posix_acl_dup(acl);
- if (!IS_ERR(dfacl))
- nfsi->acl_default = posix_acl_dup(dfacl);
- spin_unlock(&inode->i_lock);
-}
-
-struct posix_acl *nfs3_proc_getacl(struct inode *inode, int type)
+struct posix_acl *nfs3_get_acl(struct inode *inode, int type)
{
struct nfs_server *server = NFS_SERVER(inode);
struct page *pages[NFSACL_MAXPAGES] = { };
@@ -198,7 +26,6 @@ struct posix_acl *nfs3_proc_getacl(struct inode *inode, int type)
.rpc_argp = &args,
.rpc_resp = &res,
};
- struct posix_acl *acl;
int status, count;
if (!nfs_server_capable(inode, NFS_CAP_ACLS))
@@ -207,10 +34,6 @@ struct posix_acl *nfs3_proc_getacl(struct inode *inode, int type)
status = nfs_revalidate_inode(server, inode);
if (status < 0)
return ERR_PTR(status);
- acl = nfs3_get_cached_acl(inode, type);
- if (acl != ERR_PTR(-EAGAIN))
- return acl;
- acl = NULL;
/*
* Only get the access acl when explicitly requested: We don't
@@ -257,40 +80,41 @@ struct posix_acl *nfs3_proc_getacl(struct inode *inode, int type)
}
if (res.acl_access != NULL) {
- if (posix_acl_equiv_mode(res.acl_access, NULL) == 0) {
+ if ((posix_acl_equiv_mode(res.acl_access, NULL) == 0) ||
+ res.acl_access->a_count == 0) {
posix_acl_release(res.acl_access);
res.acl_access = NULL;
}
}
- nfs3_cache_acls(inode,
- (res.mask & NFS_ACL) ? res.acl_access : ERR_PTR(-EINVAL),
- (res.mask & NFS_DFACL) ? res.acl_default : ERR_PTR(-EINVAL));
- switch(type) {
- case ACL_TYPE_ACCESS:
- acl = res.acl_access;
- res.acl_access = NULL;
- break;
+ if (res.mask & NFS_ACL)
+ set_cached_acl(inode, ACL_TYPE_ACCESS, res.acl_access);
+ else
+ forget_cached_acl(inode, ACL_TYPE_ACCESS);
- case ACL_TYPE_DEFAULT:
- acl = res.acl_default;
- res.acl_default = NULL;
+ if (res.mask & NFS_DFACL)
+ set_cached_acl(inode, ACL_TYPE_DEFAULT, res.acl_default);
+ else
+ forget_cached_acl(inode, ACL_TYPE_DEFAULT);
+
+ nfs_free_fattr(res.fattr);
+ if (type == ACL_TYPE_ACCESS) {
+ posix_acl_release(res.acl_default);
+ return res.acl_access;
+ } else {
+ posix_acl_release(res.acl_access);
+ return res.acl_default;
}
getout:
posix_acl_release(res.acl_access);
posix_acl_release(res.acl_default);
nfs_free_fattr(res.fattr);
-
- if (status != 0) {
- posix_acl_release(acl);
- acl = ERR_PTR(status);
- }
- return acl;
+ return ERR_PTR(status);
}
-static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
- struct posix_acl *dfacl)
+static int __nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
+ struct posix_acl *dfacl)
{
struct nfs_server *server = NFS_SERVER(inode);
struct nfs_fattr *fattr;
@@ -353,7 +177,8 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
switch (status) {
case 0:
status = nfs_refresh_inode(inode, fattr);
- nfs3_cache_acls(inode, acl, dfacl);
+ set_cached_acl(inode, ACL_TYPE_ACCESS, acl);
+ set_cached_acl(inode, ACL_TYPE_DEFAULT, dfacl);
break;
case -EPFNOSUPPORT:
case -EPROTONOSUPPORT:
@@ -373,40 +198,43 @@ out:
return status;
}
-int nfs3_proc_setacl(struct inode *inode, int type, struct posix_acl *acl)
+int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
+ struct posix_acl *dfacl)
+{
+ int ret;
+ ret = __nfs3_proc_setacls(inode, acl, dfacl);
+ return (ret == -EOPNOTSUPP) ? 0 : ret;
+
+}
+
+int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type)
{
struct posix_acl *alloc = NULL, *dfacl = NULL;
int status;
if (S_ISDIR(inode->i_mode)) {
switch(type) {
- case ACL_TYPE_ACCESS:
- alloc = dfacl = nfs3_proc_getacl(inode,
- ACL_TYPE_DEFAULT);
- if (IS_ERR(alloc))
- goto fail;
- break;
-
- case ACL_TYPE_DEFAULT:
- dfacl = acl;
- alloc = acl = nfs3_proc_getacl(inode,
- ACL_TYPE_ACCESS);
- if (IS_ERR(alloc))
- goto fail;
- break;
+ case ACL_TYPE_ACCESS:
+ alloc = dfacl = get_acl(inode, ACL_TYPE_DEFAULT);
+ if (IS_ERR(alloc))
+ goto fail;
+ break;
- default:
- return -EINVAL;
+ case ACL_TYPE_DEFAULT:
+ dfacl = acl;
+ alloc = acl = get_acl(inode, ACL_TYPE_ACCESS);
+ if (IS_ERR(alloc))
+ goto fail;
+ break;
}
- } else if (type != ACL_TYPE_ACCESS)
- return -EINVAL;
+ }
if (acl == NULL) {
alloc = acl = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
if (IS_ERR(alloc))
goto fail;
}
- status = nfs3_proc_setacls(inode, acl, dfacl);
+ status = __nfs3_proc_setacls(inode, acl, dfacl);
posix_acl_release(alloc);
return status;
@@ -414,27 +242,8 @@ fail:
return PTR_ERR(alloc);
}
-int nfs3_proc_set_default_acl(struct inode *dir, struct inode *inode,
- umode_t mode)
-{
- struct posix_acl *dfacl, *acl;
- int error = 0;
-
- dfacl = nfs3_proc_getacl(dir, ACL_TYPE_DEFAULT);
- if (IS_ERR(dfacl)) {
- error = PTR_ERR(dfacl);
- return (error == -EOPNOTSUPP) ? 0 : error;
- }
- if (!dfacl)
- return 0;
- acl = posix_acl_dup(dfacl);
- error = posix_acl_create(&acl, GFP_KERNEL, &mode);
- if (error < 0)
- goto out_release_dfacl;
- error = nfs3_proc_setacls(inode, acl, S_ISDIR(inode->i_mode) ?
- dfacl : NULL);
- posix_acl_release(acl);
-out_release_dfacl:
- posix_acl_release(dfacl);
- return error;
-}
+const struct xattr_handler *nfs3_xattr_handlers[] = {
+ &posix_acl_access_xattr_handler,
+ &posix_acl_default_xattr_handler,
+ NULL,
+};
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 01b6f6a49d1..db60149c457 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -18,6 +18,7 @@
#include <linux/lockd/bind.h>
#include <linux/nfs_mount.h>
#include <linux/freezer.h>
+#include <linux/xattr.h>
#include "iostat.h"
#include "internal.h"
@@ -317,8 +318,8 @@ static int
nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
int flags)
{
+ struct posix_acl *default_acl, *acl;
struct nfs3_createdata *data;
- umode_t mode = sattr->ia_mode;
int status = -ENOMEM;
dprintk("NFS call create %pd\n", dentry);
@@ -340,7 +341,9 @@ nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
data->arg.create.verifier[1] = cpu_to_be32(current->pid);
}
- sattr->ia_mode &= ~current_umask();
+ status = posix_acl_create(dir, &sattr->ia_mode, &default_acl, &acl);
+ if (status)
+ goto out;
for (;;) {
status = nfs3_do_create(dir, dentry, data);
@@ -366,7 +369,7 @@ nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
}
if (status != 0)
- goto out;
+ goto out_release_acls;
/* When we created the file with exclusive semantics, make
* sure we set the attributes afterwards. */
@@ -385,9 +388,14 @@ nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
nfs_post_op_update_inode(dentry->d_inode, data->res.fattr);
dprintk("NFS reply setattr (post-create): %d\n", status);
if (status != 0)
- goto out;
+ goto out_release_acls;
}
- status = nfs3_proc_set_default_acl(dir, dentry->d_inode, mode);
+
+ status = nfs3_proc_setacls(dentry->d_inode, acl, default_acl);
+
+out_release_acls:
+ posix_acl_release(acl);
+ posix_acl_release(default_acl);
out:
nfs3_free_createdata(data);
dprintk("NFS reply create: %d\n", status);
@@ -471,41 +479,6 @@ nfs3_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
}
static int
-nfs3_proc_rename(struct inode *old_dir, struct qstr *old_name,
- struct inode *new_dir, struct qstr *new_name)
-{
- struct nfs_renameargs arg = {
- .old_dir = NFS_FH(old_dir),
- .old_name = old_name,
- .new_dir = NFS_FH(new_dir),
- .new_name = new_name,
- };
- struct nfs_renameres res;
- struct rpc_message msg = {
- .rpc_proc = &nfs3_procedures[NFS3PROC_RENAME],
- .rpc_argp = &arg,
- .rpc_resp = &res,
- };
- int status = -ENOMEM;
-
- dprintk("NFS call rename %s -> %s\n", old_name->name, new_name->name);
-
- res.old_fattr = nfs_alloc_fattr();
- res.new_fattr = nfs_alloc_fattr();
- if (res.old_fattr == NULL || res.new_fattr == NULL)
- goto out;
-
- status = rpc_call_sync(NFS_CLIENT(old_dir), &msg, 0);
- nfs_post_op_update_inode(old_dir, res.old_fattr);
- nfs_post_op_update_inode(new_dir, res.new_fattr);
-out:
- nfs_free_fattr(res.old_fattr);
- nfs_free_fattr(res.new_fattr);
- dprintk("NFS reply rename: %d\n", status);
- return status;
-}
-
-static int
nfs3_proc_link(struct inode *inode, struct inode *dir, struct qstr *name)
{
struct nfs3_linkargs arg = {
@@ -572,18 +545,20 @@ out:
static int
nfs3_proc_mkdir(struct inode *dir, struct dentry *dentry, struct iattr *sattr)
{
+ struct posix_acl *default_acl, *acl;
struct nfs3_createdata *data;
- umode_t mode = sattr->ia_mode;
int status = -ENOMEM;
dprintk("NFS call mkdir %pd\n", dentry);
- sattr->ia_mode &= ~current_umask();
-
data = nfs3_alloc_createdata();
if (data == NULL)
goto out;
+ status = posix_acl_create(dir, &sattr->ia_mode, &default_acl, &acl);
+ if (status)
+ goto out;
+
data->msg.rpc_proc = &nfs3_procedures[NFS3PROC_MKDIR];
data->arg.mkdir.fh = NFS_FH(dir);
data->arg.mkdir.name = dentry->d_name.name;
@@ -592,9 +567,13 @@ nfs3_proc_mkdir(struct inode *dir, struct dentry *dentry, struct iattr *sattr)
status = nfs3_do_create(dir, dentry, data);
if (status != 0)
- goto out;
+ goto out_release_acls;
- status = nfs3_proc_set_default_acl(dir, dentry->d_inode, mode);
+ status = nfs3_proc_setacls(dentry->d_inode, acl, default_acl);
+
+out_release_acls:
+ posix_acl_release(acl);
+ posix_acl_release(default_acl);
out:
nfs3_free_createdata(data);
dprintk("NFS reply mkdir: %d\n", status);
@@ -691,19 +670,21 @@ static int
nfs3_proc_mknod(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
dev_t rdev)
{
+ struct posix_acl *default_acl, *acl;
struct nfs3_createdata *data;
- umode_t mode = sattr->ia_mode;
int status = -ENOMEM;
dprintk("NFS call mknod %pd %u:%u\n", dentry,
MAJOR(rdev), MINOR(rdev));
- sattr->ia_mode &= ~current_umask();
-
data = nfs3_alloc_createdata();
if (data == NULL)
goto out;
+ status = posix_acl_create(dir, &sattr->ia_mode, &default_acl, &acl);
+ if (status)
+ goto out;
+
data->msg.rpc_proc = &nfs3_procedures[NFS3PROC_MKNOD];
data->arg.mknod.fh = NFS_FH(dir);
data->arg.mknod.name = dentry->d_name.name;
@@ -731,8 +712,13 @@ nfs3_proc_mknod(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
status = nfs3_do_create(dir, dentry, data);
if (status != 0)
- goto out;
- status = nfs3_proc_set_default_acl(dir, dentry->d_inode, mode);
+ goto out_release_acls;
+
+ status = nfs3_proc_setacls(dentry->d_inode, acl, default_acl);
+
+out_release_acls:
+ posix_acl_release(acl);
+ posix_acl_release(default_acl);
out:
nfs3_free_createdata(data);
dprintk("NFS reply mknod: %d\n", status);
@@ -904,20 +890,28 @@ static const struct inode_operations nfs3_dir_inode_operations = {
.permission = nfs_permission,
.getattr = nfs_getattr,
.setattr = nfs_setattr,
- .listxattr = nfs3_listxattr,
- .getxattr = nfs3_getxattr,
- .setxattr = nfs3_setxattr,
- .removexattr = nfs3_removexattr,
+#ifdef CONFIG_NFS_V3_ACL
+ .listxattr = generic_listxattr,
+ .getxattr = generic_getxattr,
+ .setxattr = generic_setxattr,
+ .removexattr = generic_removexattr,
+ .get_acl = nfs3_get_acl,
+ .set_acl = nfs3_set_acl,
+#endif
};
static const struct inode_operations nfs3_file_inode_operations = {
.permission = nfs_permission,
.getattr = nfs_getattr,
.setattr = nfs_setattr,
- .listxattr = nfs3_listxattr,
- .getxattr = nfs3_getxattr,
- .setxattr = nfs3_setxattr,
- .removexattr = nfs3_removexattr,
+#ifdef CONFIG_NFS_V3_ACL
+ .listxattr = generic_listxattr,
+ .getxattr = generic_getxattr,
+ .setxattr = generic_setxattr,
+ .removexattr = generic_removexattr,
+ .get_acl = nfs3_get_acl,
+ .set_acl = nfs3_set_acl,
+#endif
};
const struct nfs_rpc_ops nfs_v3_clientops = {
@@ -939,7 +933,6 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
.unlink_setup = nfs3_proc_unlink_setup,
.unlink_rpc_prepare = nfs3_proc_unlink_rpc_prepare,
.unlink_done = nfs3_proc_unlink_done,
- .rename = nfs3_proc_rename,
.rename_setup = nfs3_proc_rename_setup,
.rename_rpc_prepare = nfs3_proc_rename_rpc_prepare,
.rename_done = nfs3_proc_rename_done,
@@ -965,7 +958,7 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
.commit_rpc_prepare = nfs3_proc_commit_rpc_prepare,
.commit_done = nfs3_commit_done,
.lock = nfs3_proc_lock,
- .clear_acl_cache = nfs3_forget_cached_acls,
+ .clear_acl_cache = forget_all_cached_acls,
.close_context = nfs_close_context,
.have_delegation = nfs3_have_delegation,
.return_delegation = nfs3_return_delegation,
diff --git a/fs/nfs/nfs3super.c b/fs/nfs/nfs3super.c
index cc471c72523..d6a98949af1 100644
--- a/fs/nfs/nfs3super.c
+++ b/fs/nfs/nfs3super.c
@@ -12,6 +12,9 @@ static struct nfs_subversion nfs_v3 = {
.rpc_vers = &nfs_version3,
.rpc_ops = &nfs_v3_clientops,
.sops = &nfs_sops,
+#ifdef CONFIG_NFS_V3_ACL
+ .xattr = nfs3_xattr_handlers,
+#endif
};
static int __init init_nfs_v3(void)
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 5609edc742a..e1d1badbe53 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -270,6 +270,7 @@ static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *ser
extern int nfs41_setup_sequence(struct nfs4_session *session,
struct nfs4_sequence_args *args, struct nfs4_sequence_res *res,
struct rpc_task *task);
+extern int nfs41_sequence_done(struct rpc_task *, struct nfs4_sequence_res *);
extern int nfs4_proc_create_session(struct nfs_client *, struct rpc_cred *);
extern int nfs4_proc_destroy_session(struct nfs4_session *, struct rpc_cred *);
extern int nfs4_proc_get_lease_time(struct nfs_client *clp,
@@ -426,6 +427,7 @@ extern void nfs4_close_sync(struct nfs4_state *, fmode_t);
extern void nfs4_state_set_mode_locked(struct nfs4_state *, fmode_t);
extern void nfs_inode_find_state_and_recover(struct inode *inode,
const nfs4_stateid *stateid);
+extern int nfs4_state_mark_reclaim_nograce(struct nfs_client *, struct nfs4_state *);
extern void nfs4_schedule_lease_recovery(struct nfs_client *);
extern int nfs4_wait_clnt_recover(struct nfs_client *clp);
extern int nfs4_client_recover_expired_lease(struct nfs_client *clp);
@@ -499,6 +501,16 @@ static inline bool nfs4_stateid_match(const nfs4_stateid *dst, const nfs4_statei
return memcmp(dst, src, sizeof(*dst)) == 0;
}
+static inline bool nfs4_stateid_match_other(const nfs4_stateid *dst, const nfs4_stateid *src)
+{
+ return memcmp(dst->other, src->other, NFS4_STATEID_OTHER_SIZE) == 0;
+}
+
+static inline bool nfs4_stateid_is_newer(const nfs4_stateid *s1, const nfs4_stateid *s2)
+{
+ return (s32)(be32_to_cpu(s1->seqid) - be32_to_cpu(s2->seqid)) > 0;
+}
+
static inline bool nfs4_valid_open_stateid(const struct nfs4_state *state)
{
return test_bit(NFS_STATE_RECOVERY_FAILED, &state->flags) == 0;
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index b4a160a405c..aa9ef487604 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -10,6 +10,7 @@
#include <linux/sunrpc/auth.h>
#include <linux/sunrpc/xprt.h>
#include <linux/sunrpc/bc_xprt.h>
+#include <linux/sunrpc/rpc_pipe_fs.h>
#include "internal.h"
#include "callback.h"
#include "delegation.h"
@@ -169,7 +170,7 @@ void nfs41_shutdown_client(struct nfs_client *clp)
void nfs40_shutdown_client(struct nfs_client *clp)
{
if (clp->cl_slot_tbl) {
- nfs4_release_slot_table(clp->cl_slot_tbl);
+ nfs4_shutdown_slot_table(clp->cl_slot_tbl);
kfree(clp->cl_slot_tbl);
}
}
@@ -370,6 +371,7 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp,
__set_bit(NFS_CS_INFINITE_SLOTS, &clp->cl_flags);
__set_bit(NFS_CS_DISCRTRY, &clp->cl_flags);
__set_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags);
+
error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_GSS_KRB5I);
if (error == -EINVAL)
error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_UNIX);
@@ -409,13 +411,11 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp,
error = nfs4_discover_server_trunking(clp, &old);
if (error < 0)
goto error;
- nfs_put_client(clp);
- if (clp != old) {
- clp->cl_preserve_clid = true;
- clp = old;
- }
- return clp;
+ if (clp != old)
+ clp->cl_preserve_clid = true;
+ nfs_put_client(clp);
+ return old;
error:
nfs_mark_client_ready(clp, error);
@@ -493,9 +493,10 @@ int nfs40_walk_client_list(struct nfs_client *new,
prev = pos;
status = nfs_wait_client_init_complete(pos);
- spin_lock(&nn->nfs_client_lock);
if (status < 0)
- continue;
+ goto out;
+ status = -NFS4ERR_STALE_CLIENTID;
+ spin_lock(&nn->nfs_client_lock);
}
if (pos->cl_cons_state != NFS_CS_READY)
continue;
@@ -530,6 +531,13 @@ int nfs40_walk_client_list(struct nfs_client *new,
*result = pos;
dprintk("NFS: <-- %s using nfs_client = %p ({%d})\n",
__func__, pos, atomic_read(&pos->cl_count));
+ goto out;
+ case -ERESTARTSYS:
+ case -ETIMEDOUT:
+ /* The callback path may have been inadvertently
+ * changed. Schedule recovery!
+ */
+ nfs4_schedule_path_down_recovery(pos);
default:
goto out;
}
@@ -633,7 +641,8 @@ int nfs41_walk_client_list(struct nfs_client *new,
}
spin_lock(&nn->nfs_client_lock);
if (status < 0)
- continue;
+ break;
+ status = -NFS4ERR_STALE_CLIENTID;
}
if (pos->cl_cons_state != NFS_CS_READY)
continue;
@@ -1133,6 +1142,7 @@ static int nfs_probe_destination(struct nfs_server *server)
* @hostname: new end-point's hostname
* @sap: new end-point's socket address
* @salen: size of "sap"
+ * @net: net namespace
*
* The nfs_server must be quiescent before this function is invoked.
* Either its session is drained (NFSv4.1+), or its transport is
@@ -1141,13 +1151,13 @@ static int nfs_probe_destination(struct nfs_server *server)
* Returns zero on success, or a negative errno value.
*/
int nfs4_update_server(struct nfs_server *server, const char *hostname,
- struct sockaddr *sap, size_t salen)
+ struct sockaddr *sap, size_t salen, struct net *net)
{
struct nfs_client *clp = server->nfs_client;
struct rpc_clnt *clnt = server->client;
struct xprt_create xargs = {
.ident = clp->cl_proto,
- .net = &init_net,
+ .net = net,
.dstaddr = sap,
.addrlen = salen,
.servername = hostname,
@@ -1187,7 +1197,7 @@ int nfs4_update_server(struct nfs_server *server, const char *hostname,
error = nfs4_set_client(server, hostname, sap, salen, buf,
clp->cl_rpcclient->cl_auth->au_flavor,
clp->cl_proto, clnt->cl_timeout,
- clp->cl_minorversion, clp->cl_net);
+ clp->cl_minorversion, net);
nfs_put_client(clp);
if (error != 0) {
nfs_server_insert_lists(server);
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index b86464ba25e..b9a35c05b60 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -91,10 +91,10 @@ static void filelayout_reset_write(struct nfs_write_data *data)
if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
dprintk("%s Reset task %5u for i/o through MDS "
- "(req %s/%lld, %u bytes @ offset %llu)\n", __func__,
+ "(req %s/%llu, %u bytes @ offset %llu)\n", __func__,
data->task.tk_pid,
hdr->inode->i_sb->s_id,
- (long long)NFS_FILEID(hdr->inode),
+ (unsigned long long)NFS_FILEID(hdr->inode),
data->args.count,
(unsigned long long)data->args.offset);
@@ -112,10 +112,10 @@ static void filelayout_reset_read(struct nfs_read_data *data)
if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
dprintk("%s Reset task %5u for i/o through MDS "
- "(req %s/%lld, %u bytes @ offset %llu)\n", __func__,
+ "(req %s/%llu, %u bytes @ offset %llu)\n", __func__,
data->task.tk_pid,
hdr->inode->i_sb->s_id,
- (long long)NFS_FILEID(hdr->inode),
+ (unsigned long long)NFS_FILEID(hdr->inode),
data->args.count,
(unsigned long long)data->args.offset);
@@ -324,8 +324,9 @@ static void filelayout_read_prepare(struct rpc_task *task, void *data)
&rdata->res.seq_res,
task))
return;
- nfs4_set_rw_stateid(&rdata->args.stateid, rdata->args.context,
- rdata->args.lock_context, FMODE_READ);
+ if (nfs4_set_rw_stateid(&rdata->args.stateid, rdata->args.context,
+ rdata->args.lock_context, FMODE_READ) == -EIO)
+ rpc_exit(task, -EIO); /* lost lock, terminate I/O */
}
static void filelayout_read_call_done(struct rpc_task *task, void *data)
@@ -335,8 +336,10 @@ static void filelayout_read_call_done(struct rpc_task *task, void *data)
dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status);
if (test_bit(NFS_IOHDR_REDO, &rdata->header->flags) &&
- task->tk_status == 0)
+ task->tk_status == 0) {
+ nfs41_sequence_done(task, &rdata->res.seq_res);
return;
+ }
/* Note this may cause RPC to be resent */
rdata->header->mds_ops->rpc_call_done(task, data);
@@ -433,8 +436,9 @@ static void filelayout_write_prepare(struct rpc_task *task, void *data)
&wdata->res.seq_res,
task))
return;
- nfs4_set_rw_stateid(&wdata->args.stateid, wdata->args.context,
- wdata->args.lock_context, FMODE_WRITE);
+ if (nfs4_set_rw_stateid(&wdata->args.stateid, wdata->args.context,
+ wdata->args.lock_context, FMODE_WRITE) == -EIO)
+ rpc_exit(task, -EIO); /* lost lock, terminate I/O */
}
static void filelayout_write_call_done(struct rpc_task *task, void *data)
@@ -442,8 +446,10 @@ static void filelayout_write_call_done(struct rpc_task *task, void *data)
struct nfs_write_data *wdata = data;
if (test_bit(NFS_IOHDR_REDO, &wdata->header->flags) &&
- task->tk_status == 0)
+ task->tk_status == 0) {
+ nfs41_sequence_done(task, &wdata->res.seq_res);
return;
+ }
/* Note this may cause RPC to be resent */
wdata->header->mds_ops->rpc_call_done(task, data);
@@ -1216,17 +1222,17 @@ static void filelayout_recover_commit_reqs(struct list_head *dst,
struct pnfs_commit_bucket *b;
int i;
- /* NOTE cinfo->lock is NOT held, relying on fact that this is
- * only called on single thread per dreq.
- * Can't take the lock because need to do pnfs_put_lseg
- */
+ spin_lock(cinfo->lock);
for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) {
if (transfer_commit_list(&b->written, dst, cinfo, 0)) {
+ spin_unlock(cinfo->lock);
pnfs_put_lseg(b->wlseg);
b->wlseg = NULL;
+ spin_lock(cinfo->lock);
}
}
cinfo->ds->nwritten = 0;
+ spin_unlock(cinfo->lock);
}
static unsigned int
diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
index c7c295e556e..efac602edb3 100644
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -95,7 +95,7 @@ same_sockaddr(struct sockaddr *addr1, struct sockaddr *addr2)
b6 = (struct sockaddr_in6 *)addr2;
/* LINKLOCAL addresses must have matching scope_id */
- if (ipv6_addr_scope(&a6->sin6_addr) ==
+ if (ipv6_addr_src_scope(&a6->sin6_addr) ==
IPV6_ADDR_SCOPE_LINKLOCAL &&
a6->sin6_scope_id != b6->sin6_scope_id)
return false;
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index 4e7f05d3e9d..3d5dbf80d46 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -121,9 +121,8 @@ static int nfs4_validate_fspath(struct dentry *dentry,
}
static size_t nfs_parse_server_name(char *string, size_t len,
- struct sockaddr *sa, size_t salen, struct nfs_server *server)
+ struct sockaddr *sa, size_t salen, struct net *net)
{
- struct net *net = rpc_net_ns(server->client);
ssize_t ret;
ret = rpc_pton(net, string, len, sa, salen);
@@ -223,6 +222,7 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
const struct nfs4_fs_location *location)
{
const size_t addr_bufsize = sizeof(struct sockaddr_storage);
+ struct net *net = rpc_net_ns(NFS_SB(mountdata->sb)->client);
struct vfsmount *mnt = ERR_PTR(-ENOENT);
char *mnt_path;
unsigned int maxbuflen;
@@ -248,8 +248,7 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
continue;
mountdata->addrlen = nfs_parse_server_name(buf->data, buf->len,
- mountdata->addr, addr_bufsize,
- NFS_SB(mountdata->sb));
+ mountdata->addr, addr_bufsize, net);
if (mountdata->addrlen == 0)
continue;
@@ -419,6 +418,7 @@ static int nfs4_try_replacing_one_location(struct nfs_server *server,
const struct nfs4_fs_location *location)
{
const size_t addr_bufsize = sizeof(struct sockaddr_storage);
+ struct net *net = rpc_net_ns(server->client);
struct sockaddr *sap;
unsigned int s;
size_t salen;
@@ -440,7 +440,7 @@ static int nfs4_try_replacing_one_location(struct nfs_server *server,
continue;
salen = nfs_parse_server_name(buf->data, buf->len,
- sap, addr_bufsize, server);
+ sap, addr_bufsize, net);
if (salen == 0)
continue;
rpc_set_port(sap, NFS_PORT);
@@ -450,7 +450,7 @@ static int nfs4_try_replacing_one_location(struct nfs_server *server,
if (hostname == NULL)
break;
- error = nfs4_update_server(server, hostname, sap, salen);
+ error = nfs4_update_server(server, hostname, sap, salen, net);
kfree(hostname);
if (error == 0)
break;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 15052b81df4..397be39c6dc 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -539,7 +539,7 @@ static int nfs40_sequence_done(struct rpc_task *task,
struct nfs4_slot *slot = res->sr_slot;
struct nfs4_slot_table *tbl;
- if (!RPC_WAS_SENT(task))
+ if (slot == NULL)
goto out;
tbl = slot->table;
@@ -559,15 +559,10 @@ static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res)
{
struct nfs4_session *session;
struct nfs4_slot_table *tbl;
+ struct nfs4_slot *slot = res->sr_slot;
bool send_new_highest_used_slotid = false;
- if (!res->sr_slot) {
- /* just wake up the next guy waiting since
- * we may have not consumed a slot after all */
- dprintk("%s: No slot\n", __func__);
- return;
- }
- tbl = res->sr_slot->table;
+ tbl = slot->table;
session = tbl->session;
spin_lock(&tbl->slot_tbl_lock);
@@ -577,11 +572,11 @@ static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res)
if (tbl->highest_used_slotid > tbl->target_highest_slotid)
send_new_highest_used_slotid = true;
- if (nfs41_wake_and_assign_slot(tbl, res->sr_slot)) {
+ if (nfs41_wake_and_assign_slot(tbl, slot)) {
send_new_highest_used_slotid = false;
goto out_unlock;
}
- nfs4_free_slot(tbl, res->sr_slot);
+ nfs4_free_slot(tbl, slot);
if (tbl->highest_used_slotid != NFS4_NO_SLOT)
send_new_highest_used_slotid = false;
@@ -592,19 +587,20 @@ out_unlock:
nfs41_server_notify_highest_slotid_update(session->clp);
}
-static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
+int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
{
struct nfs4_session *session;
- struct nfs4_slot *slot;
+ struct nfs4_slot *slot = res->sr_slot;
struct nfs_client *clp;
bool interrupted = false;
int ret = 1;
+ if (slot == NULL)
+ goto out_noaction;
/* don't increment the sequence number if the task wasn't sent */
if (!RPC_WAS_SENT(task))
goto out;
- slot = res->sr_slot;
session = slot->table->session;
if (slot->interrupted) {
@@ -679,6 +675,7 @@ out:
/* The session may be reset by one of the error handlers. */
dprintk("%s: Error %d free the slot \n", __func__, res->sr_status);
nfs41_sequence_free_slot(res);
+out_noaction:
return ret;
retry_nowait:
if (rpc_restart_call_prepare(task)) {
@@ -692,6 +689,7 @@ out_retry:
rpc_delay(task, NFS4_POLL_RETRY_MAX);
return 0;
}
+EXPORT_SYMBOL_GPL(nfs41_sequence_done);
static int nfs4_sequence_done(struct rpc_task *task,
struct nfs4_sequence_res *res)
@@ -1070,6 +1068,7 @@ static void nfs4_opendata_free(struct kref *kref)
dput(p->dentry);
nfs_sb_deactive(sb);
nfs_fattr_free_names(&p->f_attr);
+ kfree(p->f_attr.mdsthreshold);
kfree(p);
}
@@ -1139,12 +1138,71 @@ static void update_open_stateflags(struct nfs4_state *state, fmode_t fmode)
nfs4_state_set_mode_locked(state, state->state | fmode);
}
-static void nfs_set_open_stateid_locked(struct nfs4_state *state, nfs4_stateid *stateid, fmode_t fmode)
+static void nfs_test_and_clear_all_open_stateid(struct nfs4_state *state)
{
+ struct nfs_client *clp = state->owner->so_server->nfs_client;
+ bool need_recover = false;
+
+ if (test_and_clear_bit(NFS_O_RDONLY_STATE, &state->flags) && state->n_rdonly)
+ need_recover = true;
+ if (test_and_clear_bit(NFS_O_WRONLY_STATE, &state->flags) && state->n_wronly)
+ need_recover = true;
+ if (test_and_clear_bit(NFS_O_RDWR_STATE, &state->flags) && state->n_rdwr)
+ need_recover = true;
+ if (need_recover)
+ nfs4_state_mark_reclaim_nograce(clp, state);
+}
+
+static bool nfs_need_update_open_stateid(struct nfs4_state *state,
+ nfs4_stateid *stateid)
+{
+ if (test_and_set_bit(NFS_OPEN_STATE, &state->flags) == 0)
+ return true;
+ if (!nfs4_stateid_match_other(stateid, &state->open_stateid)) {
+ nfs_test_and_clear_all_open_stateid(state);
+ return true;
+ }
+ if (nfs4_stateid_is_newer(stateid, &state->open_stateid))
+ return true;
+ return false;
+}
+
+static void nfs_clear_open_stateid_locked(struct nfs4_state *state,
+ nfs4_stateid *stateid, fmode_t fmode)
+{
+ clear_bit(NFS_O_RDWR_STATE, &state->flags);
+ switch (fmode & (FMODE_READ|FMODE_WRITE)) {
+ case FMODE_WRITE:
+ clear_bit(NFS_O_RDONLY_STATE, &state->flags);
+ break;
+ case FMODE_READ:
+ clear_bit(NFS_O_WRONLY_STATE, &state->flags);
+ break;
+ case 0:
+ clear_bit(NFS_O_RDONLY_STATE, &state->flags);
+ clear_bit(NFS_O_WRONLY_STATE, &state->flags);
+ clear_bit(NFS_OPEN_STATE, &state->flags);
+ }
+ if (stateid == NULL)
+ return;
+ if (!nfs_need_update_open_stateid(state, stateid))
+ return;
if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0)
nfs4_stateid_copy(&state->stateid, stateid);
nfs4_stateid_copy(&state->open_stateid, stateid);
- set_bit(NFS_OPEN_STATE, &state->flags);
+}
+
+static void nfs_clear_open_stateid(struct nfs4_state *state, nfs4_stateid *stateid, fmode_t fmode)
+{
+ write_seqlock(&state->seqlock);
+ nfs_clear_open_stateid_locked(state, stateid, fmode);
+ write_sequnlock(&state->seqlock);
+ if (test_bit(NFS_STATE_RECLAIM_NOGRACE, &state->flags))
+ nfs4_schedule_state_manager(state->owner->so_server->nfs_client);
+}
+
+static void nfs_set_open_stateid_locked(struct nfs4_state *state, nfs4_stateid *stateid, fmode_t fmode)
+{
switch (fmode) {
case FMODE_READ:
set_bit(NFS_O_RDONLY_STATE, &state->flags);
@@ -1155,13 +1213,11 @@ static void nfs_set_open_stateid_locked(struct nfs4_state *state, nfs4_stateid *
case FMODE_READ|FMODE_WRITE:
set_bit(NFS_O_RDWR_STATE, &state->flags);
}
-}
-
-static void nfs_set_open_stateid(struct nfs4_state *state, nfs4_stateid *stateid, fmode_t fmode)
-{
- write_seqlock(&state->seqlock);
- nfs_set_open_stateid_locked(state, stateid, fmode);
- write_sequnlock(&state->seqlock);
+ if (!nfs_need_update_open_stateid(state, stateid))
+ return;
+ if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0)
+ nfs4_stateid_copy(&state->stateid, stateid);
+ nfs4_stateid_copy(&state->open_stateid, stateid);
}
static void __update_open_stateid(struct nfs4_state *state, nfs4_stateid *open_stateid, const nfs4_stateid *deleg_stateid, fmode_t fmode)
@@ -1219,6 +1275,8 @@ no_delegation:
__update_open_stateid(state, open_stateid, NULL, fmode);
ret = 1;
}
+ if (test_bit(NFS_STATE_RECLAIM_NOGRACE, &state->flags))
+ nfs4_schedule_state_manager(state->owner->so_server->nfs_client);
return ret;
}
@@ -1452,12 +1510,15 @@ static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state *
struct nfs4_state *newstate;
int ret;
+ /* Don't trigger recovery in nfs_test_and_clear_all_open_stateid */
+ clear_bit(NFS_O_RDWR_STATE, &state->flags);
+ clear_bit(NFS_O_WRONLY_STATE, &state->flags);
+ clear_bit(NFS_O_RDONLY_STATE, &state->flags);
/* memory barrier prior to reading state->n_* */
clear_bit(NFS_DELEGATED_STATE, &state->flags);
clear_bit(NFS_OPEN_STATE, &state->flags);
smp_rmb();
if (state->n_rdwr != 0) {
- clear_bit(NFS_O_RDWR_STATE, &state->flags);
ret = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE, &newstate);
if (ret != 0)
return ret;
@@ -1465,7 +1526,6 @@ static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state *
return -ESTALE;
}
if (state->n_wronly != 0) {
- clear_bit(NFS_O_WRONLY_STATE, &state->flags);
ret = nfs4_open_recover_helper(opendata, FMODE_WRITE, &newstate);
if (ret != 0)
return ret;
@@ -1473,7 +1533,6 @@ static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state *
return -ESTALE;
}
if (state->n_rdonly != 0) {
- clear_bit(NFS_O_RDONLY_STATE, &state->flags);
ret = nfs4_open_recover_helper(opendata, FMODE_READ, &newstate);
if (ret != 0)
return ret;
@@ -1622,15 +1681,15 @@ static void nfs4_open_confirm_prepare(struct rpc_task *task, void *calldata)
{
struct nfs4_opendata *data = calldata;
- nfs40_setup_sequence(data->o_arg.server, &data->o_arg.seq_args,
- &data->o_res.seq_res, task);
+ nfs40_setup_sequence(data->o_arg.server, &data->c_arg.seq_args,
+ &data->c_res.seq_res, task);
}
static void nfs4_open_confirm_done(struct rpc_task *task, void *calldata)
{
struct nfs4_opendata *data = calldata;
- nfs40_sequence_done(task, &data->o_res.seq_res);
+ nfs40_sequence_done(task, &data->c_res.seq_res);
data->rpc_status = task->tk_status;
if (data->rpc_status == 0) {
@@ -1688,7 +1747,7 @@ static int _nfs4_proc_open_confirm(struct nfs4_opendata *data)
};
int status;
- nfs4_init_sequence(&data->o_arg.seq_args, &data->o_res.seq_res, 1);
+ nfs4_init_sequence(&data->c_arg.seq_args, &data->c_res.seq_res, 1);
kref_get(&data->kref);
data->rpc_done = 0;
data->rpc_status = 0;
@@ -2246,10 +2305,12 @@ static int _nfs4_do_open(struct inode *dir,
}
}
- if (ctx_th && server->attr_bitmask[2] & FATTR4_WORD2_MDSTHRESHOLD) {
- opendata->f_attr.mdsthreshold = pnfs_mdsthreshold_alloc();
- if (!opendata->f_attr.mdsthreshold)
- goto err_free_label;
+ if (server->attr_bitmask[2] & FATTR4_WORD2_MDSTHRESHOLD) {
+ if (!opendata->f_attr.mdsthreshold) {
+ opendata->f_attr.mdsthreshold = pnfs_mdsthreshold_alloc();
+ if (!opendata->f_attr.mdsthreshold)
+ goto err_free_label;
+ }
opendata->o_arg.open_bitmap = &nfs4_pnfs_open_bitmap[0];
}
if (dentry->d_inode != NULL)
@@ -2277,11 +2338,10 @@ static int _nfs4_do_open(struct inode *dir,
if (opendata->file_created)
*opened |= FILE_CREATED;
- if (pnfs_use_threshold(ctx_th, opendata->f_attr.mdsthreshold, server))
+ if (pnfs_use_threshold(ctx_th, opendata->f_attr.mdsthreshold, server)) {
*ctx_th = opendata->f_attr.mdsthreshold;
- else
- kfree(opendata->f_attr.mdsthreshold);
- opendata->f_attr.mdsthreshold = NULL;
+ opendata->f_attr.mdsthreshold = NULL;
+ }
nfs4_label_free(olabel);
@@ -2291,7 +2351,6 @@ static int _nfs4_do_open(struct inode *dir,
err_free_label:
nfs4_label_free(olabel);
err_opendata_put:
- kfree(opendata->f_attr.mdsthreshold);
nfs4_opendata_put(opendata);
err_put_state_owner:
nfs4_put_state_owner(sp);
@@ -2400,13 +2459,16 @@ static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
if (nfs4_copy_delegation_stateid(&arg.stateid, inode, fmode)) {
/* Use that stateid */
- } else if (truncate && state != NULL && nfs4_valid_open_stateid(state)) {
+ } else if (truncate && state != NULL) {
struct nfs_lockowner lockowner = {
.l_owner = current->files,
.l_pid = current->tgid,
};
- nfs4_select_rw_stateid(&arg.stateid, state, FMODE_WRITE,
- &lockowner);
+ if (!nfs4_valid_open_stateid(state))
+ return -EBADF;
+ if (nfs4_select_rw_stateid(&arg.stateid, state, FMODE_WRITE,
+ &lockowner) == -EIO)
+ return -EBADF;
} else
nfs4_stateid_copy(&arg.stateid, &zero_stateid);
@@ -2478,26 +2540,6 @@ static void nfs4_free_closedata(void *data)
kfree(calldata);
}
-static void nfs4_close_clear_stateid_flags(struct nfs4_state *state,
- fmode_t fmode)
-{
- spin_lock(&state->owner->so_lock);
- clear_bit(NFS_O_RDWR_STATE, &state->flags);
- switch (fmode & (FMODE_READ|FMODE_WRITE)) {
- case FMODE_WRITE:
- clear_bit(NFS_O_RDONLY_STATE, &state->flags);
- break;
- case FMODE_READ:
- clear_bit(NFS_O_WRONLY_STATE, &state->flags);
- break;
- case 0:
- clear_bit(NFS_O_RDONLY_STATE, &state->flags);
- clear_bit(NFS_O_WRONLY_STATE, &state->flags);
- clear_bit(NFS_OPEN_STATE, &state->flags);
- }
- spin_unlock(&state->owner->so_lock);
-}
-
static void nfs4_close_done(struct rpc_task *task, void *data)
{
struct nfs4_closedata *calldata = data;
@@ -2516,9 +2558,9 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
if (calldata->roc)
pnfs_roc_set_barrier(state->inode,
calldata->roc_barrier);
- nfs_set_open_stateid(state, &calldata->res.stateid, 0);
+ nfs_clear_open_stateid(state, &calldata->res.stateid, 0);
renew_lease(server, calldata->timestamp);
- break;
+ goto out_release;
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_STALE_STATEID:
case -NFS4ERR_OLD_STATEID:
@@ -2532,7 +2574,7 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
goto out_release;
}
}
- nfs4_close_clear_stateid_flags(state, calldata->arg.fmode);
+ nfs_clear_open_stateid(state, NULL, calldata->arg.fmode);
out_release:
nfs_release_seqid(calldata->arg.seqid);
nfs_refresh_inode(calldata->inode, calldata->res.fattr);
@@ -2744,7 +2786,8 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
NFS_CAP_OWNER_GROUP|NFS_CAP_ATIME|
NFS_CAP_CTIME|NFS_CAP_MTIME|
NFS_CAP_SECURITY_LABEL);
- if (res.attr_bitmask[0] & FATTR4_WORD0_ACL)
+ if (res.attr_bitmask[0] & FATTR4_WORD0_ACL &&
+ res.acl_bitmask & ACL4_SUPPORT_ALLOW_ACL)
server->caps |= NFS_CAP_ACLS;
if (res.has_links != 0)
server->caps |= NFS_CAP_HARDLINKS;
@@ -3505,49 +3548,6 @@ static int nfs4_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
return 1;
}
-static int _nfs4_proc_rename(struct inode *old_dir, struct qstr *old_name,
- struct inode *new_dir, struct qstr *new_name)
-{
- struct nfs_server *server = NFS_SERVER(old_dir);
- struct nfs_renameargs arg = {
- .old_dir = NFS_FH(old_dir),
- .new_dir = NFS_FH(new_dir),
- .old_name = old_name,
- .new_name = new_name,
- };
- struct nfs_renameres res = {
- .server = server,
- };
- struct rpc_message msg = {
- .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RENAME],
- .rpc_argp = &arg,
- .rpc_resp = &res,
- };
- int status = -ENOMEM;
-
- status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1);
- if (!status) {
- update_changeattr(old_dir, &res.old_cinfo);
- update_changeattr(new_dir, &res.new_cinfo);
- }
- return status;
-}
-
-static int nfs4_proc_rename(struct inode *old_dir, struct qstr *old_name,
- struct inode *new_dir, struct qstr *new_name)
-{
- struct nfs4_exception exception = { };
- int err;
- do {
- err = _nfs4_proc_rename(old_dir, old_name,
- new_dir, new_name);
- trace_nfs4_rename(old_dir, old_name, new_dir, new_name, err);
- err = nfs4_handle_exception(NFS_SERVER(old_dir), err,
- &exception);
- } while (exception.retry);
- return err;
-}
-
static int _nfs4_proc_link(struct inode *inode, struct inode *dir, struct qstr *name)
{
struct nfs_server *server = NFS_SERVER(inode);
@@ -4012,8 +4012,9 @@ static bool nfs4_stateid_is_current(nfs4_stateid *stateid,
{
nfs4_stateid current_stateid;
- if (nfs4_set_rw_stateid(&current_stateid, ctx, l_ctx, fmode))
- return false;
+ /* If the current stateid represents a lost lock, then exit */
+ if (nfs4_set_rw_stateid(&current_stateid, ctx, l_ctx, fmode) == -EIO)
+ return true;
return nfs4_stateid_match(stateid, &current_stateid);
}
@@ -4321,9 +4322,7 @@ static int nfs4_proc_renew(struct nfs_client *clp, struct rpc_cred *cred)
static inline int nfs4_server_supports_acls(struct nfs_server *server)
{
- return (server->caps & NFS_CAP_ACLS)
- && (server->acl_bitmask & ACL4_SUPPORT_ALLOW_ACL)
- && (server->acl_bitmask & ACL4_SUPPORT_DENY_ACL);
+ return server->caps & NFS_CAP_ACLS;
}
/* Assuming that XATTR_SIZE_MAX is a multiple of PAGE_SIZE, and that
@@ -4883,6 +4882,20 @@ nfs4_init_uniform_client_string(const struct nfs_client *clp,
nodename);
}
+/*
+ * nfs4_callback_up_net() starts only "tcp" and "tcp6" callback
+ * services. Advertise one based on the address family of the
+ * clientaddr.
+ */
+static unsigned int
+nfs4_init_callback_netid(const struct nfs_client *clp, char *buf, size_t len)
+{
+ if (strchr(clp->cl_ipaddr, ':') != NULL)
+ return scnprintf(buf, len, "tcp6");
+ else
+ return scnprintf(buf, len, "tcp");
+}
+
/**
* nfs4_proc_setclientid - Negotiate client ID
* @clp: state data structure
@@ -4924,12 +4937,10 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program,
setclientid.sc_name,
sizeof(setclientid.sc_name));
/* cb_client4 */
- rcu_read_lock();
- setclientid.sc_netid_len = scnprintf(setclientid.sc_netid,
- sizeof(setclientid.sc_netid), "%s",
- rpc_peeraddr2str(clp->cl_rpcclient,
- RPC_DISPLAY_NETID));
- rcu_read_unlock();
+ setclientid.sc_netid_len =
+ nfs4_init_callback_netid(clp,
+ setclientid.sc_netid,
+ sizeof(setclientid.sc_netid));
setclientid.sc_uaddr_len = scnprintf(setclientid.sc_uaddr,
sizeof(setclientid.sc_uaddr), "%s.%u.%u",
clp->cl_ipaddr, port >> 8, port & 255);
@@ -5831,8 +5842,7 @@ struct nfs_release_lockowner_data {
struct nfs4_lock_state *lsp;
struct nfs_server *server;
struct nfs_release_lockowner_args args;
- struct nfs4_sequence_args seq_args;
- struct nfs4_sequence_res seq_res;
+ struct nfs_release_lockowner_res res;
unsigned long timestamp;
};
@@ -5840,7 +5850,7 @@ static void nfs4_release_lockowner_prepare(struct rpc_task *task, void *calldata
{
struct nfs_release_lockowner_data *data = calldata;
nfs40_setup_sequence(data->server,
- &data->seq_args, &data->seq_res, task);
+ &data->args.seq_args, &data->res.seq_res, task);
data->timestamp = jiffies;
}
@@ -5849,7 +5859,7 @@ static void nfs4_release_lockowner_done(struct rpc_task *task, void *calldata)
struct nfs_release_lockowner_data *data = calldata;
struct nfs_server *server = data->server;
- nfs40_sequence_done(task, &data->seq_res);
+ nfs40_sequence_done(task, &data->res.seq_res);
switch (task->tk_status) {
case 0:
@@ -5890,7 +5900,6 @@ static int nfs4_release_lockowner(struct nfs_server *server, struct nfs4_lock_st
data = kmalloc(sizeof(*data), GFP_NOFS);
if (!data)
return -ENOMEM;
- nfs4_init_sequence(&data->seq_args, &data->seq_res, 0);
data->lsp = lsp;
data->server = server;
data->args.lock_owner.clientid = server->nfs_client->cl_clientid;
@@ -5898,6 +5907,8 @@ static int nfs4_release_lockowner(struct nfs_server *server, struct nfs4_lock_st
data->args.lock_owner.s_dev = server->s_dev;
msg.rpc_argp = &data->args;
+ msg.rpc_resp = &data->res;
+ nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 0);
rpc_call_async(server->client, &msg, 0, &nfs4_release_lockowner_ops, data);
return 0;
}
@@ -7409,9 +7420,9 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
struct nfs_server *server = NFS_SERVER(inode);
struct pnfs_layout_hdr *lo;
struct nfs4_state *state = NULL;
- unsigned long timeo, giveup;
+ unsigned long timeo, now, giveup;
- dprintk("--> %s\n", __func__);
+ dprintk("--> %s tk_status => %d\n", __func__, -task->tk_status);
if (!nfs41_sequence_done(task, &lgp->res.seq_res))
goto out;
@@ -7419,12 +7430,38 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
switch (task->tk_status) {
case 0:
goto out;
+ /*
+ * NFS4ERR_LAYOUTTRYLATER is a conflict with another client
+ * (or clients) writing to the same RAID stripe
+ */
case -NFS4ERR_LAYOUTTRYLATER:
+ /*
+ * NFS4ERR_RECALLCONFLICT is when conflict with self (must recall
+ * existing layout before getting a new one).
+ */
case -NFS4ERR_RECALLCONFLICT:
timeo = rpc_get_timeout(task->tk_client);
giveup = lgp->args.timestamp + timeo;
- if (time_after(giveup, jiffies))
- task->tk_status = -NFS4ERR_DELAY;
+ now = jiffies;
+ if (time_after(giveup, now)) {
+ unsigned long delay;
+
+ /* Delay for:
+ * - Not less then NFS4_POLL_RETRY_MIN.
+ * - One last time a jiffie before we give up
+ * - exponential backoff (time_now minus start_attempt)
+ */
+ delay = max_t(unsigned long, NFS4_POLL_RETRY_MIN,
+ min((giveup - now - 1),
+ now - lgp->args.timestamp));
+
+ dprintk("%s: NFS4ERR_RECALLCONFLICT waiting %lu\n",
+ __func__, delay);
+ rpc_delay(task, delay);
+ task->tk_status = 0;
+ rpc_restart_call_prepare(task);
+ goto out; /* Do not call nfs4_async_handle_error() */
+ }
break;
case -NFS4ERR_EXPIRED:
case -NFS4ERR_BAD_STATEID:
@@ -7780,10 +7817,7 @@ nfs4_layoutcommit_done(struct rpc_task *task, void *calldata)
case -NFS4ERR_BADLAYOUT: /* no layout */
case -NFS4ERR_GRACE: /* loca_recalim always false */
task->tk_status = 0;
- break;
case 0:
- nfs_post_op_update_inode_force_wcc(data->args.inode,
- data->res.fattr);
break;
default:
if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN) {
@@ -7798,6 +7832,8 @@ static void nfs4_layoutcommit_release(void *calldata)
struct nfs4_layoutcommit_data *data = calldata;
pnfs_cleanup_layoutcommit(data);
+ nfs_post_op_update_inode_force_wcc(data->args.inode,
+ data->res.fattr);
put_rpccred(data->cred);
kfree(data);
}
@@ -7920,7 +7956,7 @@ nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle,
switch (err) {
case 0:
case -NFS4ERR_WRONGSEC:
- case -NFS4ERR_NOTSUPP:
+ case -ENOTSUPP:
goto out;
default:
err = nfs4_handle_exception(server, err, &exception);
@@ -7954,7 +7990,7 @@ nfs41_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
* Fall back on "guess and check" method if
* the server doesn't support SECINFO_NO_NAME
*/
- if (err == -NFS4ERR_WRONGSEC || err == -NFS4ERR_NOTSUPP) {
+ if (err == -NFS4ERR_WRONGSEC || err == -ENOTSUPP) {
err = nfs4_find_root_sec(server, fhandle, info);
goto out_freepage;
}
@@ -8382,7 +8418,6 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
.unlink_setup = nfs4_proc_unlink_setup,
.unlink_rpc_prepare = nfs4_proc_unlink_rpc_prepare,
.unlink_done = nfs4_proc_unlink_done,
- .rename = nfs4_proc_rename,
.rename_setup = nfs4_proc_rename_setup,
.rename_rpc_prepare = nfs4_proc_rename_rpc_prepare,
.rename_done = nfs4_proc_rename_done,
diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c
index cf883c7ae05..e799dc3c3b1 100644
--- a/fs/nfs/nfs4session.c
+++ b/fs/nfs/nfs4session.c
@@ -231,14 +231,23 @@ out:
return ret;
}
+/*
+ * nfs4_release_slot_table - release all slot table entries
+ */
+static void nfs4_release_slot_table(struct nfs4_slot_table *tbl)
+{
+ nfs4_shrink_slot_table(tbl, 0);
+}
+
/**
- * nfs4_release_slot_table - release resources attached to a slot table
+ * nfs4_shutdown_slot_table - release resources attached to a slot table
* @tbl: slot table to shut down
*
*/
-void nfs4_release_slot_table(struct nfs4_slot_table *tbl)
+void nfs4_shutdown_slot_table(struct nfs4_slot_table *tbl)
{
- nfs4_shrink_slot_table(tbl, 0);
+ nfs4_release_slot_table(tbl);
+ rpc_destroy_wait_queue(&tbl->slot_tbl_waitq);
}
/**
@@ -422,7 +431,7 @@ void nfs41_update_target_slotid(struct nfs4_slot_table *tbl,
spin_unlock(&tbl->slot_tbl_lock);
}
-static void nfs4_destroy_session_slot_tables(struct nfs4_session *session)
+static void nfs4_release_session_slot_tables(struct nfs4_session *session)
{
nfs4_release_slot_table(&session->fc_slot_table);
nfs4_release_slot_table(&session->bc_slot_table);
@@ -450,7 +459,7 @@ int nfs4_setup_session_slot_tables(struct nfs4_session *ses)
if (status && tbl->slots == NULL)
/* Fore and back channel share a connection so get
* both slot tables or neither */
- nfs4_destroy_session_slot_tables(ses);
+ nfs4_release_session_slot_tables(ses);
return status;
}
@@ -470,6 +479,12 @@ struct nfs4_session *nfs4_alloc_session(struct nfs_client *clp)
return session;
}
+static void nfs4_destroy_session_slot_tables(struct nfs4_session *session)
+{
+ nfs4_shutdown_slot_table(&session->fc_slot_table);
+ nfs4_shutdown_slot_table(&session->bc_slot_table);
+}
+
void nfs4_destroy_session(struct nfs4_session *session)
{
struct rpc_xprt *xprt;
diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h
index 23230610065..b34ada9bc6a 100644
--- a/fs/nfs/nfs4session.h
+++ b/fs/nfs/nfs4session.h
@@ -74,7 +74,7 @@ enum nfs4_session_state {
extern int nfs4_setup_slot_table(struct nfs4_slot_table *tbl,
unsigned int max_reqs, const char *queue);
-extern void nfs4_release_slot_table(struct nfs4_slot_table *tbl);
+extern void nfs4_shutdown_slot_table(struct nfs4_slot_table *tbl);
extern struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl);
extern void nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot);
extern void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl);
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 059c01b67a7..2349518eef2 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -974,9 +974,6 @@ static int nfs4_copy_lock_stateid(nfs4_stateid *dst,
else if (lsp != NULL && test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) != 0) {
nfs4_stateid_copy(dst, &lsp->ls_stateid);
ret = 0;
- smp_rmb();
- if (!list_empty(&lsp->ls_seqid.list))
- ret = -EWOULDBLOCK;
}
spin_unlock(&state->state_lock);
nfs4_put_lock_state(lsp);
@@ -984,10 +981,9 @@ out:
return ret;
}
-static int nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
+static void nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
{
const nfs4_stateid *src;
- int ret;
int seq;
do {
@@ -996,12 +992,7 @@ static int nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
if (test_bit(NFS_OPEN_STATE, &state->flags))
src = &state->open_stateid;
nfs4_stateid_copy(dst, src);
- ret = 0;
- smp_rmb();
- if (!list_empty(&state->owner->so_seqid.list))
- ret = -EWOULDBLOCK;
} while (read_seqretry(&state->seqlock, seq));
- return ret;
}
/*
@@ -1015,15 +1006,19 @@ int nfs4_select_rw_stateid(nfs4_stateid *dst, struct nfs4_state *state,
if (ret == -EIO)
/* A lost lock - don't even consider delegations */
goto out;
- if (nfs4_copy_delegation_stateid(dst, state->inode, fmode))
+ /* returns true if delegation stateid found and copied */
+ if (nfs4_copy_delegation_stateid(dst, state->inode, fmode)) {
+ ret = 0;
goto out;
+ }
if (ret != -ENOENT)
/* nfs4_copy_delegation_stateid() didn't over-write
* dst, so it still has the lock stateid which we now
* choose to use.
*/
goto out;
- ret = nfs4_copy_open_stateid(dst, state);
+ nfs4_copy_open_stateid(dst, state);
+ ret = 0;
out:
if (nfs_server_capable(state->inode, NFS_CAP_STATEID_NFSV41))
dst->seqid = 0;
@@ -1071,7 +1066,7 @@ void nfs_free_seqid(struct nfs_seqid *seqid)
/*
* Increment the seqid if the OPEN/OPEN_DOWNGRADE/CLOSE succeeded, or
* failed with a seqid incrementing error -
- * see comments nfs_fs.h:seqid_mutating_error()
+ * see comments nfs4.h:seqid_mutating_error()
*/
static void nfs_increment_seqid(int status, struct nfs_seqid *seqid)
{
@@ -1116,7 +1111,7 @@ void nfs_increment_open_seqid(int status, struct nfs_seqid *seqid)
/*
* Increment the seqid if the LOCK/LOCKU succeeded, or
* failed with a seqid incrementing error -
- * see comments nfs_fs.h:seqid_mutating_error()
+ * see comments nfs4.h:seqid_mutating_error()
*/
void nfs_increment_lock_seqid(int status, struct nfs_seqid *seqid)
{
@@ -1321,7 +1316,7 @@ static int nfs4_state_mark_reclaim_reboot(struct nfs_client *clp, struct nfs4_st
return 1;
}
-static int nfs4_state_mark_reclaim_nograce(struct nfs_client *clp, struct nfs4_state *state)
+int nfs4_state_mark_reclaim_nograce(struct nfs_client *clp, struct nfs4_state *state)
{
set_bit(NFS_STATE_RECLAIM_NOGRACE, &state->flags);
clear_bit(NFS_STATE_RECLAIM_REBOOT, &state->flags);
@@ -2080,8 +2075,10 @@ again:
switch (status) {
case 0:
break;
- case -NFS4ERR_DELAY:
case -ETIMEDOUT:
+ if (clnt->cl_softrtry)
+ break;
+ case -NFS4ERR_DELAY:
case -EAGAIN:
ssleep(1);
case -NFS4ERR_STALE_CLIENTID:
diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c
index 65ab0a0ca1c..6f340f02f2b 100644
--- a/fs/nfs/nfs4super.c
+++ b/fs/nfs/nfs4super.c
@@ -77,17 +77,9 @@ static int nfs4_write_inode(struct inode *inode, struct writeback_control *wbc)
{
int ret = nfs_write_inode(inode, wbc);
- if (ret >= 0 && test_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(inode)->flags)) {
- int status;
- bool sync = true;
-
- if (wbc->sync_mode == WB_SYNC_NONE)
- sync = false;
-
- status = pnfs_layoutcommit_inode(inode, sync);
- if (status < 0)
- return status;
- }
+ if (ret == 0)
+ ret = pnfs_layoutcommit_inode(inode,
+ wbc->sync_mode == WB_SYNC_ALL);
return ret;
}
@@ -98,7 +90,7 @@ static int nfs4_write_inode(struct inode *inode, struct writeback_control *wbc)
*/
static void nfs4_evict_inode(struct inode *inode)
{
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
pnfs_return_layout(inode);
pnfs_destroy_layout(NFS_I(inode));
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 5be2868c02f..73ce8d4fe2c 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -203,8 +203,7 @@ static int nfs4_stat_to_errno(int);
2 + encode_verifier_maxsz + 5 + \
nfs4_label_maxsz)
#define decode_readdir_maxsz (op_decode_hdr_maxsz + \
- decode_verifier_maxsz + \
- nfs4_label_maxsz + nfs4_fattr_maxsz)
+ decode_verifier_maxsz)
#define encode_readlink_maxsz (op_encode_hdr_maxsz)
#define decode_readlink_maxsz (op_decode_hdr_maxsz + 1)
#define encode_write_maxsz (op_encode_hdr_maxsz + \
@@ -3097,7 +3096,8 @@ out_overflow:
return -EIO;
}
-static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected)
+static bool __decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected,
+ int *nfs_retval)
{
__be32 *p;
uint32_t opnum;
@@ -3107,19 +3107,32 @@ static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected)
if (unlikely(!p))
goto out_overflow;
opnum = be32_to_cpup(p++);
- if (opnum != expected) {
- dprintk("nfs: Server returned operation"
- " %d but we issued a request for %d\n",
- opnum, expected);
- return -EIO;
- }
+ if (unlikely(opnum != expected))
+ goto out_bad_operation;
nfserr = be32_to_cpup(p);
- if (nfserr != NFS_OK)
- return nfs4_stat_to_errno(nfserr);
- return 0;
+ if (nfserr == NFS_OK)
+ *nfs_retval = 0;
+ else
+ *nfs_retval = nfs4_stat_to_errno(nfserr);
+ return true;
+out_bad_operation:
+ dprintk("nfs: Server returned operation"
+ " %d but we issued a request for %d\n",
+ opnum, expected);
+ *nfs_retval = -EREMOTEIO;
+ return false;
out_overflow:
print_overflow_msg(__func__, xdr);
- return -EIO;
+ *nfs_retval = -EIO;
+ return false;
+}
+
+static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected)
+{
+ int retval;
+
+ __decode_op_hdr(xdr, expected, &retval);
+ return retval;
}
/* Dummy routine */
@@ -3435,7 +3448,7 @@ static int decode_attr_aclsupport(struct xdr_stream *xdr, uint32_t *bitmap, uint
{
__be32 *p;
- *res = ACL4_SUPPORT_ALLOW_ACL|ACL4_SUPPORT_DENY_ACL;
+ *res = 0;
if (unlikely(bitmap[0] & (FATTR4_WORD0_ACLSUPPORT - 1U)))
return -EIO;
if (likely(bitmap[0] & FATTR4_WORD0_ACLSUPPORT)) {
@@ -5001,11 +5014,12 @@ static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res)
uint32_t savewords, bmlen, i;
int status;
- status = decode_op_hdr(xdr, OP_OPEN);
- if (status != -EIO)
- nfs_increment_open_seqid(status, res->seqid);
- if (!status)
- status = decode_stateid(xdr, &res->stateid);
+ if (!__decode_op_hdr(xdr, OP_OPEN, &status))
+ return status;
+ nfs_increment_open_seqid(status, res->seqid);
+ if (status)
+ return status;
+ status = decode_stateid(xdr, &res->stateid);
if (unlikely(status))
return status;
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 89fe741e58b..59f838cdc00 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -36,6 +36,7 @@
__print_flags(v, "|", \
{ 1 << NFS_INO_ADVISE_RDPLUS, "ADVISE_RDPLUS" }, \
{ 1 << NFS_INO_STALE, "STALE" }, \
+ { 1 << NFS_INO_INVALIDATING, "INVALIDATING" }, \
{ 1 << NFS_INO_FLUSHING, "FLUSHING" }, \
{ 1 << NFS_INO_FSCACHE, "FSCACHE" }, \
{ 1 << NFS_INO_COMMIT, "COMMIT" }, \
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index d75d938d36c..cb53d450ae3 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -662,7 +662,18 @@ pnfs_destroy_all_layouts(struct nfs_client *clp)
*/
static bool pnfs_seqid_is_newer(u32 s1, u32 s2)
{
- return (s32)s1 - (s32)s2 > 0;
+ return (s32)(s1 - s2) > 0;
+}
+
+static void
+pnfs_verify_layout_stateid(struct pnfs_layout_hdr *lo,
+ const nfs4_stateid *new,
+ struct list_head *free_me_list)
+{
+ if (nfs4_stateid_match_other(&lo->plh_stateid, new))
+ return;
+ /* Layout is new! Kill existing layout segments */
+ pnfs_mark_matching_lsegs_invalid(lo, free_me_list, NULL);
}
/* update lo->plh_stateid with new if is more recent */
@@ -1315,6 +1326,7 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
struct nfs4_layoutget_res *res = &lgp->res;
struct pnfs_layout_segment *lseg;
struct inode *ino = lo->plh_inode;
+ LIST_HEAD(free_me);
int status = 0;
/* Inject layout blob into I/O device driver */
@@ -1341,6 +1353,8 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
goto out_forget_reply;
}
+ /* Check that the new stateid matches the old stateid */
+ pnfs_verify_layout_stateid(lo, &res->stateid, &free_me);
/* Done processing layoutget. Set the layout stateid */
pnfs_set_layout_stateid(lo, &res->stateid, false);
@@ -1355,6 +1369,7 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
}
spin_unlock(&ino->i_lock);
+ pnfs_free_lseg_list(&free_me);
return lseg;
out:
return ERR_PTR(status);
@@ -1790,6 +1805,15 @@ pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
}
EXPORT_SYMBOL_GPL(pnfs_generic_pg_readpages);
+static void pnfs_clear_layoutcommitting(struct inode *inode)
+{
+ unsigned long *bitlock = &NFS_I(inode)->flags;
+
+ clear_bit_unlock(NFS_INO_LAYOUTCOMMITTING, bitlock);
+ smp_mb__after_clear_bit();
+ wake_up_bit(bitlock, NFS_INO_LAYOUTCOMMITTING);
+}
+
/*
* There can be multiple RW segments.
*/
@@ -1807,7 +1831,6 @@ static void pnfs_list_write_lseg(struct inode *inode, struct list_head *listp)
static void pnfs_list_write_lseg_done(struct inode *inode, struct list_head *listp)
{
struct pnfs_layout_segment *lseg, *tmp;
- unsigned long *bitlock = &NFS_I(inode)->flags;
/* Matched by references in pnfs_set_layoutcommit */
list_for_each_entry_safe(lseg, tmp, listp, pls_lc_list) {
@@ -1815,9 +1838,7 @@ static void pnfs_list_write_lseg_done(struct inode *inode, struct list_head *lis
pnfs_put_lseg(lseg);
}
- clear_bit_unlock(NFS_INO_LAYOUTCOMMITTING, bitlock);
- smp_mb__after_clear_bit();
- wake_up_bit(bitlock, NFS_INO_LAYOUTCOMMITTING);
+ pnfs_clear_layoutcommitting(inode);
}
void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg)
@@ -1881,43 +1902,37 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
struct nfs4_layoutcommit_data *data;
struct nfs_inode *nfsi = NFS_I(inode);
loff_t end_pos;
- int status = 0;
+ int status;
- dprintk("--> %s inode %lu\n", __func__, inode->i_ino);
-
- if (!test_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags))
+ if (!pnfs_layoutcommit_outstanding(inode))
return 0;
- /* Note kzalloc ensures data->res.seq_res.sr_slot == NULL */
- data = kzalloc(sizeof(*data), GFP_NOFS);
- if (!data) {
- status = -ENOMEM;
- goto out;
- }
-
- if (!test_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags))
- goto out_free;
+ dprintk("--> %s inode %lu\n", __func__, inode->i_ino);
+ status = -EAGAIN;
if (test_and_set_bit(NFS_INO_LAYOUTCOMMITTING, &nfsi->flags)) {
- if (!sync) {
- status = -EAGAIN;
- goto out_free;
- }
- status = wait_on_bit_lock(&nfsi->flags, NFS_INO_LAYOUTCOMMITTING,
- nfs_wait_bit_killable, TASK_KILLABLE);
+ if (!sync)
+ goto out;
+ status = wait_on_bit_lock(&nfsi->flags,
+ NFS_INO_LAYOUTCOMMITTING,
+ nfs_wait_bit_killable,
+ TASK_KILLABLE);
if (status)
- goto out_free;
+ goto out;
}
- INIT_LIST_HEAD(&data->lseg_list);
+ status = -ENOMEM;
+ /* Note kzalloc ensures data->res.seq_res.sr_slot == NULL */
+ data = kzalloc(sizeof(*data), GFP_NOFS);
+ if (!data)
+ goto clear_layoutcommitting;
+
+ status = 0;
spin_lock(&inode->i_lock);
- if (!test_and_clear_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) {
- clear_bit(NFS_INO_LAYOUTCOMMITTING, &nfsi->flags);
- spin_unlock(&inode->i_lock);
- wake_up_bit(&nfsi->flags, NFS_INO_LAYOUTCOMMITTING);
- goto out_free;
- }
+ if (!test_and_clear_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags))
+ goto out_unlock;
+ INIT_LIST_HEAD(&data->lseg_list);
pnfs_list_write_lseg(inode, &data->lseg_list);
end_pos = nfsi->layout->plh_lwb;
@@ -1940,8 +1955,11 @@ out:
mark_inode_dirty_sync(inode);
dprintk("<-- %s status %d\n", __func__, status);
return status;
-out_free:
+out_unlock:
+ spin_unlock(&inode->i_lock);
kfree(data);
+clear_layoutcommitting:
+ pnfs_clear_layoutcommitting(inode);
goto out;
}
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index a4f41810a7f..02379390977 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -359,6 +359,15 @@ pnfs_ld_layoutret_on_setattr(struct inode *inode)
PNFS_LAYOUTRET_ON_SETATTR;
}
+static inline bool
+pnfs_layoutcommit_outstanding(struct inode *inode)
+{
+ struct nfs_inode *nfsi = NFS_I(inode);
+
+ return test_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags) != 0 ||
+ test_bit(NFS_INO_LAYOUTCOMMITTING, &nfsi->flags) != 0;
+}
+
static inline int pnfs_return_layout(struct inode *ino)
{
struct nfs_inode *nfsi = NFS_I(ino);
@@ -515,6 +524,13 @@ pnfs_use_threshold(struct nfs4_threshold **dst, struct nfs4_threshold *src,
return false;
}
+static inline bool
+pnfs_layoutcommit_outstanding(struct inode *inode)
+{
+ return false;
+}
+
+
static inline struct nfs4_threshold *pnfs_mdsthreshold_alloc(void)
{
return NULL;
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index fddbba2d9ef..e55ce9e8b03 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -357,30 +357,6 @@ nfs_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
}
static int
-nfs_proc_rename(struct inode *old_dir, struct qstr *old_name,
- struct inode *new_dir, struct qstr *new_name)
-{
- struct nfs_renameargs arg = {
- .old_dir = NFS_FH(old_dir),
- .old_name = old_name,
- .new_dir = NFS_FH(new_dir),
- .new_name = new_name,
- };
- struct rpc_message msg = {
- .rpc_proc = &nfs_procedures[NFSPROC_RENAME],
- .rpc_argp = &arg,
- };
- int status;
-
- dprintk("NFS call rename %s -> %s\n", old_name->name, new_name->name);
- status = rpc_call_sync(NFS_CLIENT(old_dir), &msg, 0);
- nfs_mark_for_revalidate(old_dir);
- nfs_mark_for_revalidate(new_dir);
- dprintk("NFS reply rename: %d\n", status);
- return status;
-}
-
-static int
nfs_proc_link(struct inode *inode, struct inode *dir, struct qstr *name)
{
struct nfs_linkargs arg = {
@@ -745,7 +721,6 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
.unlink_setup = nfs_proc_unlink_setup,
.unlink_rpc_prepare = nfs_proc_unlink_rpc_prepare,
.unlink_done = nfs_proc_unlink_done,
- .rename = nfs_proc_rename,
.rename_setup = nfs_proc_rename_setup,
.rename_rpc_prepare = nfs_proc_rename_rpc_prepare,
.rename_done = nfs_proc_rename_done,
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 31db5c366b8..411aedda14b 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -163,9 +163,9 @@ static void nfs_readpage_release(struct nfs_page *req)
unlock_page(req->wb_page);
- dprintk("NFS: read done (%s/%Ld %d@%Ld)\n",
+ dprintk("NFS: read done (%s/%Lu %d@%Ld)\n",
req->wb_context->dentry->d_inode->i_sb->s_id,
- (long long)NFS_FILEID(req->wb_context->dentry->d_inode),
+ (unsigned long long)NFS_FILEID(req->wb_context->dentry->d_inode),
req->wb_bytes,
(long long)req_offset(req));
nfs_release_request(req);
@@ -228,11 +228,11 @@ int nfs_initiate_read(struct rpc_clnt *clnt,
/* Set up the initial task struct. */
NFS_PROTO(inode)->read_setup(data, &msg);
- dprintk("NFS: %5u initiated read call (req %s/%lld, %u bytes @ "
+ dprintk("NFS: %5u initiated read call (req %s/%llu, %u bytes @ "
"offset %llu)\n",
data->task.tk_pid,
inode->i_sb->s_id,
- (long long)NFS_FILEID(inode),
+ (unsigned long long)NFS_FILEID(inode),
data->args.count,
(unsigned long long)data->args.offset);
@@ -630,9 +630,9 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
unsigned long npages;
int ret = -ESTALE;
- dprintk("NFS: nfs_readpages (%s/%Ld %d)\n",
+ dprintk("NFS: nfs_readpages (%s/%Lu %d)\n",
inode->i_sb->s_id,
- (long long)NFS_FILEID(inode),
+ (unsigned long long)NFS_FILEID(inode),
nr_pages);
nfs_inc_stats(inode, NFSIOS_VFSREADPAGES);
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 910ed906eb8..2cb56943e23 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2215,6 +2215,8 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data)
struct nfs4_mount_data *options4 = (struct nfs4_mount_data *)raw_data;
u32 nfsvers = nfss->nfs_client->rpc_ops->version;
+ sync_filesystem(sb);
+
/*
* Userspace mount programs that send binary options generally send
* them populated with default values. We have no way to know which
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 11d78944de7..de54129336c 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -14,6 +14,7 @@
#include <linux/sched.h>
#include <linux/wait.h>
#include <linux/namei.h>
+#include <linux/fsnotify.h>
#include "internal.h"
#include "nfs4_fs.h"
@@ -353,8 +354,8 @@ static void nfs_async_rename_done(struct rpc_task *task, void *calldata)
return;
}
- if (task->tk_status != 0)
- nfs_cancel_async_unlink(old_dentry);
+ if (data->complete)
+ data->complete(task, data);
}
/**
@@ -399,9 +400,10 @@ static const struct rpc_call_ops nfs_rename_ops = {
*
* It's expected that valid references to the dentries and inodes are held
*/
-static struct rpc_task *
+struct rpc_task *
nfs_async_rename(struct inode *old_dir, struct inode *new_dir,
- struct dentry *old_dentry, struct dentry *new_dentry)
+ struct dentry *old_dentry, struct dentry *new_dentry,
+ void (*complete)(struct rpc_task *, struct nfs_renamedata *))
{
struct nfs_renamedata *data;
struct rpc_message msg = { };
@@ -438,6 +440,7 @@ nfs_async_rename(struct inode *old_dir, struct inode *new_dir,
data->new_dentry = dget(new_dentry);
nfs_fattr_init(&data->old_fattr);
nfs_fattr_init(&data->new_fattr);
+ data->complete = complete;
/* set up nfs_renameargs */
data->args.old_dir = NFS_FH(old_dir);
@@ -456,6 +459,27 @@ nfs_async_rename(struct inode *old_dir, struct inode *new_dir,
return rpc_run_task(&task_setup_data);
}
+/*
+ * Perform tasks needed when a sillyrename is done such as cancelling the
+ * queued async unlink if it failed.
+ */
+static void
+nfs_complete_sillyrename(struct rpc_task *task, struct nfs_renamedata *data)
+{
+ struct dentry *dentry = data->old_dentry;
+
+ if (task->tk_status != 0) {
+ nfs_cancel_async_unlink(dentry);
+ return;
+ }
+
+ /*
+ * vfs_unlink and the like do not issue this when a file is
+ * sillyrenamed, so do it here.
+ */
+ fsnotify_nameremove(dentry, 0);
+}
+
#define SILLYNAME_PREFIX ".nfs"
#define SILLYNAME_PREFIX_LEN ((unsigned)sizeof(SILLYNAME_PREFIX) - 1)
#define SILLYNAME_FILEID_LEN ((unsigned)sizeof(u64) << 1)
@@ -548,7 +572,8 @@ nfs_sillyrename(struct inode *dir, struct dentry *dentry)
}
/* run the rename task, undo unlink if it fails */
- task = nfs_async_rename(dir, dir, dentry, sdentry);
+ task = nfs_async_rename(dir, dir, dentry, sdentry,
+ nfs_complete_sillyrename);
if (IS_ERR(task)) {
error = -EBUSY;
nfs_cancel_async_unlink(dentry);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index c1d548211c3..9a3b6a4cd6b 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -909,9 +909,14 @@ bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx)
*/
static bool nfs_write_pageuptodate(struct page *page, struct inode *inode)
{
+ struct nfs_inode *nfsi = NFS_I(inode);
+
if (nfs_have_delegated_attributes(inode))
goto out;
- if (NFS_I(inode)->cache_validity & (NFS_INO_INVALID_DATA|NFS_INO_REVAL_PAGECACHE))
+ if (nfsi->cache_validity & (NFS_INO_INVALID_DATA|NFS_INO_REVAL_PAGECACHE))
+ return false;
+ smp_rmb();
+ if (test_bit(NFS_INO_INVALIDATING, &nfsi->flags))
return false;
out:
return PageUptodate(page) != 0;
@@ -922,19 +927,20 @@ out:
* extend the write to cover the entire page in order to avoid fragmentation
* inefficiencies.
*
- * If the file is opened for synchronous writes or if we have a write delegation
- * from the server then we can just skip the rest of the checks.
+ * If the file is opened for synchronous writes then we can just skip the rest
+ * of the checks.
*/
static int nfs_can_extend_write(struct file *file, struct page *page, struct inode *inode)
{
if (file->f_flags & O_DSYNC)
return 0;
+ if (!nfs_write_pageuptodate(page, inode))
+ return 0;
if (NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE))
return 1;
- if (nfs_write_pageuptodate(page, inode) && (inode->i_flock == NULL ||
- (inode->i_flock->fl_start == 0 &&
+ if (inode->i_flock == NULL || (inode->i_flock->fl_start == 0 &&
inode->i_flock->fl_end == OFFSET_MAX &&
- inode->i_flock->fl_type != F_RDLCK)))
+ inode->i_flock->fl_type != F_RDLCK))
return 1;
return 0;
}
@@ -1013,10 +1019,10 @@ int nfs_initiate_write(struct rpc_clnt *clnt,
NFS_PROTO(inode)->write_setup(data, &msg);
dprintk("NFS: %5u initiated write call "
- "(req %s/%lld, %u bytes @ offset %llu)\n",
+ "(req %s/%llu, %u bytes @ offset %llu)\n",
data->task.tk_pid,
inode->i_sb->s_id,
- (long long)NFS_FILEID(inode),
+ (unsigned long long)NFS_FILEID(inode),
data->args.count,
(unsigned long long)data->args.offset);
@@ -1606,9 +1612,9 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
nfs_list_remove_request(req);
nfs_clear_page_commit(req->wb_page);
- dprintk("NFS: commit (%s/%lld %d@%lld)",
+ dprintk("NFS: commit (%s/%llu %d@%lld)",
req->wb_context->dentry->d_sb->s_id,
- (long long)NFS_FILEID(req->wb_context->dentry->d_inode),
+ (unsigned long long)NFS_FILEID(req->wb_context->dentry->d_inode),
req->wb_bytes,
(long long)req_offset(req));
if (status < 0) {
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-09-23 02:18:53 +0000