Update Linux to v5.4.148
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.4.148.tar.gz
Change-Id: Ib3d26c5ba9b022e2e03533005c4fed4d7c30b61b
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 295a7a2..e84c187 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -90,7 +90,7 @@
config NFS_SWAP
bool "Provide swap over NFS support"
default n
- depends on NFS_FS
+ depends on NFS_FS && SWAP
select SUNRPC_SWAP
help
This option enables swapon to work on files located on NFS mounts.
@@ -127,7 +127,7 @@
config PNFS_FLEXFILE_LAYOUT
tristate
depends on NFS_V4_1 && NFS_V3
- default m
+ default NFS_V4
config NFS_V4_1_IMPLEMENTATION_ID_DOMAIN
string "NFSv4.1 Implementation ID Domain"
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index f39924b..fc775b0 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -130,6 +130,8 @@
list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
list_for_each_entry(lo, &server->layouts, plh_layouts) {
+ if (!pnfs_layout_is_valid(lo))
+ continue;
if (stateid != NULL &&
!nfs4_stateid_match_other(stateid, &lo->plh_stateid))
continue;
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 3083830..af838d1 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -153,6 +153,7 @@
if ((clp = kzalloc(sizeof(*clp), GFP_KERNEL)) == NULL)
goto error_0;
+ clp->cl_minorversion = cl_init->minorversion;
clp->cl_nfs_mod = cl_init->nfs_mod;
if (!try_module_get(clp->cl_nfs_mod->owner))
goto error_dealloc;
@@ -398,7 +399,7 @@
if (cl_init->hostname == NULL) {
WARN_ON(1);
- return NULL;
+ return ERR_PTR(-EINVAL);
}
/* see if the client already exists */
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index e180033..e7c0790 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -162,6 +162,17 @@
bool eof;
} nfs_readdir_descriptor_t;
+static
+void nfs_readdir_init_array(struct page *page)
+{
+ struct nfs_cache_array *array;
+
+ array = kmap_atomic(page);
+ memset(array, 0, sizeof(struct nfs_cache_array));
+ array->eof_index = -1;
+ kunmap_atomic(array);
+}
+
/*
* we are freeing strings created by nfs_add_to_readdir_array()
*/
@@ -174,6 +185,7 @@
array = kmap_atomic(page);
for (i = 0; i < array->size; i++)
kfree(array->array[i].string.name);
+ array->size = 0;
kunmap_atomic(array);
}
@@ -541,6 +553,9 @@
xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
do {
+ if (entry->label)
+ entry->label->len = NFS4_MAXLABELLEN;
+
status = xdr_decode(desc, entry, &stream);
if (status != 0) {
if (status == -EAGAIN)
@@ -610,6 +625,8 @@
int status = -ENOMEM;
unsigned int array_size = ARRAY_SIZE(pages);
+ nfs_readdir_init_array(page);
+
entry.prev_cookie = 0;
entry.cookie = desc->last_cookie;
entry.eof = 0;
@@ -626,8 +643,6 @@
}
array = kmap(page);
- memset(array, 0, sizeof(struct nfs_cache_array));
- array->eof_index = -1;
status = nfs_readdir_alloc_pages(pages, array_size);
if (status < 0)
@@ -682,6 +697,7 @@
unlock_page(page);
return 0;
error:
+ nfs_readdir_clear_array(page);
unlock_page(page);
return ret;
}
@@ -689,8 +705,6 @@
static
void cache_page_release(nfs_readdir_descriptor_t *desc)
{
- if (!desc->page->mapping)
- nfs_readdir_clear_array(desc->page);
put_page(desc->page);
desc->page = NULL;
}
@@ -704,19 +718,28 @@
/*
* Returns 0 if desc->dir_cookie was found on page desc->page_index
+ * and locks the page to prevent removal from the page cache.
*/
static
-int find_cache_page(nfs_readdir_descriptor_t *desc)
+int find_and_lock_cache_page(nfs_readdir_descriptor_t *desc)
{
int res;
desc->page = get_cache_page(desc);
if (IS_ERR(desc->page))
return PTR_ERR(desc->page);
-
- res = nfs_readdir_search_array(desc);
+ res = lock_page_killable(desc->page);
if (res != 0)
- cache_page_release(desc);
+ goto error;
+ res = -EAGAIN;
+ if (desc->page->mapping != NULL) {
+ res = nfs_readdir_search_array(desc);
+ if (res == 0)
+ return 0;
+ }
+ unlock_page(desc->page);
+error:
+ cache_page_release(desc);
return res;
}
@@ -731,7 +754,7 @@
desc->last_cookie = 0;
}
do {
- res = find_cache_page(desc);
+ res = find_and_lock_cache_page(desc);
} while (res == -EAGAIN);
return res;
}
@@ -770,7 +793,6 @@
desc->eof = true;
kunmap(desc->page);
- cache_page_release(desc);
dfprintk(DIRCACHE, "NFS: nfs_do_filldir() filling ended @ cookie %Lu; returning = %d\n",
(unsigned long long)*desc->dir_cookie, res);
return res;
@@ -816,13 +838,13 @@
status = nfs_do_filldir(desc);
+ out_release:
+ nfs_readdir_clear_array(desc->page);
+ cache_page_release(desc);
out:
dfprintk(DIRCACHE, "NFS: %s: returns %d\n",
__func__, status);
return status;
- out_release:
- cache_page_release(desc);
- goto out;
}
/* The file offset position represents the dirent entry number. A
@@ -887,6 +909,8 @@
break;
res = nfs_do_filldir(desc);
+ unlock_page(desc->page);
+ cache_page_release(desc);
if (res < 0)
break;
} while (!desc->eof);
@@ -1049,6 +1073,15 @@
goto out;
}
+static void nfs_mark_dir_for_revalidate(struct inode *inode)
+{
+ struct nfs_inode *nfsi = NFS_I(inode);
+
+ spin_lock(&inode->i_lock);
+ nfsi->cache_validity |= NFS_INO_REVAL_PAGECACHE;
+ spin_unlock(&inode->i_lock);
+}
+
/*
* We judge how long we want to trust negative
* dentries by looking at the parent inode mtime.
@@ -1083,19 +1116,14 @@
__func__, dentry);
return 1;
case 0:
- nfs_mark_for_revalidate(dir);
- if (inode && S_ISDIR(inode->i_mode)) {
- /* Purge readdir caches. */
- nfs_zap_caches(inode);
- /*
- * We can't d_drop the root of a disconnected tree:
- * its d_hash is on the s_anon list and d_drop() would hide
- * it from shrink_dcache_for_unmount(), leading to busy
- * inodes on unmount and further oopses.
- */
- if (IS_ROOT(dentry))
- return 1;
- }
+ /*
+ * We can't d_drop the root of a disconnected tree:
+ * its d_hash is on the s_anon list and d_drop() would hide
+ * it from shrink_dcache_for_unmount(), leading to busy
+ * inodes on unmount and further oopses.
+ */
+ if (inode && IS_ROOT(dentry))
+ return 1;
dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is invalid\n",
__func__, dentry);
return 0;
@@ -1164,6 +1192,13 @@
nfs_free_fattr(fattr);
nfs_free_fhandle(fhandle);
nfs4_label_free(label);
+
+ /*
+ * If the lookup failed despite the dentry change attribute being
+ * a match, then we should revalidate the directory cache.
+ */
+ if (!ret && nfs_verify_change_attribute(dir, dentry->d_time))
+ nfs_mark_dir_for_revalidate(dir);
return nfs_lookup_revalidate_done(dir, dentry, inode, ret);
}
@@ -1206,7 +1241,7 @@
error = nfs_lookup_verify_inode(inode, flags);
if (error) {
if (error == -ESTALE)
- nfs_zap_caches(dir);
+ nfs_mark_dir_for_revalidate(dir);
goto out_bad;
}
nfs_advise_use_readdirplus(dir);
@@ -1701,7 +1736,6 @@
dput(parent);
return d;
out_error:
- nfs_mark_for_revalidate(dir);
d = ERR_PTR(error);
goto out;
}
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 040a50f..6b0bf4e 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -245,10 +245,10 @@
data->ds_commit_index);
/* verifier not set so always fail */
- if (verfp->committed < 0)
+ if (verfp->committed < 0 || data->res.verf->committed <= NFS_UNSTABLE)
return 1;
- return nfs_direct_cmp_verf(verfp, &data->verf);
+ return nfs_direct_cmp_verf(verfp, data->res.verf);
}
/**
@@ -571,6 +571,7 @@
l_ctx = nfs_get_lock_context(dreq->ctx);
if (IS_ERR(l_ctx)) {
result = PTR_ERR(l_ctx);
+ nfs_direct_req_release(dreq);
goto out_release;
}
dreq->l_ctx = l_ctx;
@@ -989,6 +990,7 @@
l_ctx = nfs_get_lock_context(dreq->ctx);
if (IS_ERR(l_ctx)) {
result = PTR_ERR(l_ctx);
+ nfs_direct_req_release(dreq);
goto out_release;
}
dreq->l_ctx = l_ctx;
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 95dc905..387a2cf 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -140,6 +140,7 @@
nfs_file_flush(struct file *file, fl_owner_t id)
{
struct inode *inode = file_inode(file);
+ errseq_t since;
dprintk("NFS: flush(%pD2)\n", file);
@@ -148,7 +149,9 @@
return 0;
/* Flush writes to the server and return any errors */
- return nfs_wb_all(inode);
+ since = filemap_sample_wb_err(file->f_mapping);
+ nfs_wb_all(inode);
+ return filemap_check_wb_err(file->f_mapping, since);
}
ssize_t
@@ -580,12 +583,14 @@
.page_mkwrite = nfs_vm_page_mkwrite,
};
-static int nfs_need_check_write(struct file *filp, struct inode *inode)
+static int nfs_need_check_write(struct file *filp, struct inode *inode,
+ int error)
{
struct nfs_open_context *ctx;
ctx = nfs_file_open_context(filp);
- if (nfs_ctx_key_to_expire(ctx, inode))
+ if (nfs_error_is_fatal_on_server(error) ||
+ nfs_ctx_key_to_expire(ctx, inode))
return 1;
return 0;
}
@@ -596,6 +601,8 @@
struct inode *inode = file_inode(file);
unsigned long written = 0;
ssize_t result;
+ errseq_t since;
+ int error;
result = nfs_key_timeout_notify(file, inode);
if (result)
@@ -620,6 +627,7 @@
if (iocb->ki_pos > i_size_read(inode))
nfs_revalidate_mapping(inode, file->f_mapping);
+ since = filemap_sample_wb_err(file->f_mapping);
nfs_start_io_write(inode);
result = generic_write_checks(iocb, from);
if (result > 0) {
@@ -638,7 +646,8 @@
goto out;
/* Return error values */
- if (nfs_need_check_write(file, inode)) {
+ error = filemap_check_wb_err(file->f_mapping, since);
+ if (nfs_need_check_write(file, inode, error)) {
int err = nfs_wb_all(inode);
if (err < 0)
result = err;
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index c9b605f..98b74cd 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -717,7 +717,7 @@
if (unlikely(!p))
goto out_err;
fl->fh_array[i]->size = be32_to_cpup(p++);
- if (sizeof(struct nfs_fh) < fl->fh_array[i]->size) {
+ if (fl->fh_array[i]->size > NFS_MAXFHSIZE) {
printk(KERN_ERR "NFS: Too big fh %d received %d\n",
i, fl->fh_array[i]->size);
goto out_err;
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 5657b7f..fa1c920 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -103,7 +103,7 @@
if (unlikely(!p))
return -ENOBUFS;
fh->size = be32_to_cpup(p++);
- if (fh->size > sizeof(struct nfs_fh)) {
+ if (fh->size > NFS_MAXFHSIZE) {
printk(KERN_ERR "NFS flexfiles: Too big fh received %d\n",
fh->size);
return -EOVERFLOW;
@@ -984,9 +984,8 @@
goto out_mds;
/* Use a direct mapping of ds_idx to pgio mirror_idx */
- if (WARN_ON_ONCE(pgio->pg_mirror_count !=
- FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg)))
- goto out_mds;
+ if (pgio->pg_mirror_count != FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg))
+ goto out_eagain;
for (i = 0; i < pgio->pg_mirror_count; i++) {
mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i);
@@ -1008,7 +1007,10 @@
(NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR))
pgio->pg_maxretrans = io_maxretrans;
return;
-
+out_eagain:
+ pnfs_generic_pg_cleanup(pgio);
+ pgio->pg_error = -EAGAIN;
+ return;
out_mds:
trace_pnfs_mds_fallback_pg_init_write(pgio->pg_inode,
0, NFS4_MAX_UINT64, IOMODE_RW,
@@ -1018,6 +1020,7 @@
pgio->pg_lseg = NULL;
pgio->pg_maxretrans = 0;
nfs_pageio_reset_write_mds(pgio);
+ pgio->pg_error = -EAGAIN;
}
static unsigned int
diff --git a/fs/nfs/fscache-index.c b/fs/nfs/fscache-index.c
index 15f2714..573b1da 100644
--- a/fs/nfs/fscache-index.c
+++ b/fs/nfs/fscache-index.c
@@ -84,8 +84,10 @@
return FSCACHE_CHECKAUX_OBSOLETE;
memset(&auxdata, 0, sizeof(auxdata));
- auxdata.mtime = timespec64_to_timespec(nfsi->vfs_inode.i_mtime);
- auxdata.ctime = timespec64_to_timespec(nfsi->vfs_inode.i_ctime);
+ auxdata.mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec;
+ auxdata.mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec;
+ auxdata.ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec;
+ auxdata.ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec;
if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
auxdata.change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode);
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index 3800ab6..7d6721e 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -31,6 +31,7 @@
struct nfs_server_key {
struct {
uint16_t nfsversion; /* NFS protocol version */
+ uint32_t minorversion; /* NFSv4 minor version */
uint16_t family; /* address family */
__be16 port; /* IP port */
} hdr;
@@ -55,6 +56,7 @@
memset(&key, 0, sizeof(key));
key.hdr.nfsversion = clp->rpc_ops->version;
+ key.hdr.minorversion = clp->cl_minorversion;
key.hdr.family = clp->cl_addr.ss_family;
switch (clp->cl_addr.ss_family) {
@@ -186,7 +188,8 @@
/* create a cache index for looking up filehandles */
nfss->fscache = fscache_acquire_cookie(nfss->nfs_client->fscache,
&nfs_fscache_super_index_def,
- key, sizeof(*key) + ulen,
+ &key->key,
+ sizeof(key->key) + ulen,
NULL, 0,
nfss, 0, true);
dfprintk(FSCACHE, "NFS: get superblock cookie (0x%p/0x%p)\n",
@@ -224,6 +227,19 @@
}
}
+static void nfs_fscache_update_auxdata(struct nfs_fscache_inode_auxdata *auxdata,
+ struct nfs_inode *nfsi)
+{
+ memset(auxdata, 0, sizeof(*auxdata));
+ auxdata->mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec;
+ auxdata->mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec;
+ auxdata->ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec;
+ auxdata->ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec;
+
+ if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
+ auxdata->change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode);
+}
+
/*
* Initialise the per-inode cache cookie pointer for an NFS inode.
*/
@@ -237,12 +253,7 @@
if (!(nfss->fscache && S_ISREG(inode->i_mode)))
return;
- memset(&auxdata, 0, sizeof(auxdata));
- auxdata.mtime = timespec64_to_timespec(nfsi->vfs_inode.i_mtime);
- auxdata.ctime = timespec64_to_timespec(nfsi->vfs_inode.i_ctime);
-
- if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
- auxdata.change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode);
+ nfs_fscache_update_auxdata(&auxdata, nfsi);
nfsi->fscache = fscache_acquire_cookie(NFS_SB(inode->i_sb)->fscache,
&nfs_fscache_inode_object_def,
@@ -262,9 +273,7 @@
dfprintk(FSCACHE, "NFS: clear cookie (0x%p/0x%p)\n", nfsi, cookie);
- memset(&auxdata, 0, sizeof(auxdata));
- auxdata.mtime = timespec64_to_timespec(nfsi->vfs_inode.i_mtime);
- auxdata.ctime = timespec64_to_timespec(nfsi->vfs_inode.i_ctime);
+ nfs_fscache_update_auxdata(&auxdata, nfsi);
fscache_relinquish_cookie(cookie, &auxdata, false);
nfsi->fscache = NULL;
}
@@ -304,9 +313,7 @@
if (!fscache_cookie_valid(cookie))
return;
- memset(&auxdata, 0, sizeof(auxdata));
- auxdata.mtime = timespec64_to_timespec(nfsi->vfs_inode.i_mtime);
- auxdata.ctime = timespec64_to_timespec(nfsi->vfs_inode.i_ctime);
+ nfs_fscache_update_auxdata(&auxdata, nfsi);
if (inode_is_open_for_write(inode)) {
dfprintk(FSCACHE, "NFS: nfsi 0x%p disabling cache\n", nfsi);
diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h
index ad041cf..6754c86 100644
--- a/fs/nfs/fscache.h
+++ b/fs/nfs/fscache.h
@@ -62,9 +62,11 @@
* cache object.
*/
struct nfs_fscache_inode_auxdata {
- struct timespec mtime;
- struct timespec ctime;
- u64 change_attr;
+ s64 mtime_sec;
+ s64 mtime_nsec;
+ s64 ctime_sec;
+ s64 ctime_nsec;
+ u64 change_attr;
};
/*
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 2a03bfe..209263c 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -826,6 +826,8 @@
do_update |= cache_validity & NFS_INO_INVALID_ATIME;
if (request_mask & (STATX_CTIME|STATX_MTIME))
do_update |= cache_validity & NFS_INO_REVAL_PAGECACHE;
+ if (request_mask & STATX_BLOCKS)
+ do_update |= cache_validity & NFS_INO_INVALID_BLOCKS;
if (do_update) {
/* Update the attribute cache */
if (!(server->flags & NFS_MOUNT_NOAC))
@@ -959,16 +961,16 @@
struct file *filp)
{
struct nfs_open_context *ctx;
- const struct cred *cred = get_current_cred();
ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
- if (!ctx) {
- put_cred(cred);
+ if (!ctx)
return ERR_PTR(-ENOMEM);
- }
nfs_sb_active(dentry->d_sb);
ctx->dentry = dget(dentry);
- ctx->cred = cred;
+ if (filp)
+ ctx->cred = get_cred(filp->f_cred);
+ else
+ ctx->cred = get_current_cred();
ctx->ll_cred = NULL;
ctx->state = NULL;
ctx->mode = f_mode;
@@ -1046,6 +1048,7 @@
void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx)
{
filp->private_data = get_nfs_open_context(ctx);
+ set_bit(NFS_CONTEXT_FILE_OPEN, &ctx->flags);
if (list_empty(&ctx->list))
nfs_inode_attach_open_context(ctx);
}
@@ -1065,6 +1068,8 @@
continue;
if ((pos->mode & (FMODE_READ|FMODE_WRITE)) != mode)
continue;
+ if (!test_bit(NFS_CONTEXT_FILE_OPEN, &pos->flags))
+ continue;
ctx = get_nfs_open_context(pos);
if (ctx)
break;
@@ -1080,6 +1085,7 @@
if (ctx) {
struct inode *inode = d_inode(ctx->dentry);
+ clear_bit(NFS_CONTEXT_FILE_OPEN, &ctx->flags);
/*
* We fatal error on write before. Try to writeback
* every page again.
@@ -1616,10 +1622,10 @@
*/
static int nfs_inode_attrs_need_update(const struct inode *inode, const struct nfs_fattr *fattr)
{
- const struct nfs_inode *nfsi = NFS_I(inode);
+ unsigned long attr_gencount = NFS_I(inode)->attr_gencount;
- return ((long)fattr->gencount - (long)nfsi->attr_gencount) > 0 ||
- ((long)nfsi->attr_gencount - (long)nfs_read_attr_generation_counter() > 0);
+ return (long)(fattr->gencount - attr_gencount) > 0 ||
+ (long)(attr_gencount - nfs_read_attr_generation_counter()) > 0;
}
static int nfs_refresh_inode_locked(struct inode *inode, struct nfs_fattr *fattr)
@@ -1750,7 +1756,8 @@
status = nfs_post_op_update_inode_locked(inode, fattr,
NFS_INO_INVALID_CHANGE
| NFS_INO_INVALID_CTIME
- | NFS_INO_INVALID_MTIME);
+ | NFS_INO_INVALID_MTIME
+ | NFS_INO_INVALID_BLOCKS);
return status;
}
@@ -1857,7 +1864,8 @@
nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR
| NFS_INO_INVALID_ATIME
| NFS_INO_REVAL_FORCED
- | NFS_INO_REVAL_PAGECACHE);
+ | NFS_INO_REVAL_PAGECACHE
+ | NFS_INO_INVALID_BLOCKS);
/* Do atomic weak cache consistency updates */
nfs_wcc_update_inode(inode, fattr);
@@ -2019,8 +2027,12 @@
inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used);
} else if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED)
inode->i_blocks = fattr->du.nfs2.blocks;
- else
+ else {
+ nfsi->cache_validity |= save_cache_validity &
+ (NFS_INO_INVALID_BLOCKS
+ | NFS_INO_REVAL_FORCED);
cache_revalidated = false;
+ }
/* Update attrtimeo value if we're out of the unstable period */
if (attr_changed) {
@@ -2041,7 +2053,7 @@
nfsi->attrtimeo_timestamp = now;
}
/* Set the barrier to be more recent than this fattr */
- if ((long)fattr->gencount - (long)nfsi->attr_gencount > 0)
+ if ((long)(fattr->gencount - nfsi->attr_gencount) > 0)
nfsi->attr_gencount = fattr->gencount;
}
@@ -2143,7 +2155,7 @@
{
struct workqueue_struct *wq;
dprintk("RPC: creating workqueue nfsiod\n");
- wq = alloc_workqueue("nfsiod", WQ_MEM_RECLAIM, 0);
+ wq = alloc_workqueue("nfsiod", WQ_MEM_RECLAIM | WQ_UNBOUND, 0);
if (wq == NULL)
return -ENOMEM;
nfsiod_workqueue = wq;
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 447a3c1..9e71779 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -569,12 +569,14 @@
static inline struct inode *nfs_igrab_and_active(struct inode *inode)
{
- inode = igrab(inode);
- if (inode != NULL && !nfs_sb_active(inode->i_sb)) {
- iput(inode);
- inode = NULL;
+ struct super_block *sb = inode->i_sb;
+
+ if (sb && nfs_sb_active(sb)) {
+ if (igrab(inode))
+ return inode;
+ nfs_sb_deactive(sb);
}
- return inode;
+ return NULL;
}
static inline void nfs_iput_and_deactive(struct inode *inode)
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index cb7c10e..a2593b7 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -32,6 +32,7 @@
#define MNT_fhs_status_sz (1)
#define MNT_fhandle_sz XDR_QUADLEN(NFS2_FHSIZE)
#define MNT_fhandle3_sz (1 + XDR_QUADLEN(NFS3_FHSIZE))
+#define MNT_fhandlev3_sz XDR_QUADLEN(NFS3_FHSIZE)
#define MNT_authflav3_sz (1 + NFS_MAX_SECFLAVORS)
/*
@@ -39,7 +40,7 @@
*/
#define MNT_enc_dirpath_sz encode_dirpath_sz
#define MNT_dec_mountres_sz (MNT_status_sz + MNT_fhandle_sz)
-#define MNT_dec_mountres3_sz (MNT_status_sz + MNT_fhandle_sz + \
+#define MNT_dec_mountres3_sz (MNT_status_sz + MNT_fhandlev3_sz + \
MNT_authflav3_sz)
/*
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index 9287eb6..2db17fd 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -31,9 +31,9 @@
/*
* nfs_path - reconstruct the path given an arbitrary dentry
* @base - used to return pointer to the end of devname part of path
- * @dentry - pointer to dentry
+ * @dentry_in - pointer to dentry
* @buffer - result buffer
- * @buflen - length of buffer
+ * @buflen_in - length of buffer
* @flags - options (see below)
*
* Helper function for constructing the server pathname
@@ -48,15 +48,19 @@
* the original device (export) name
* (if unset, the original name is returned verbatim)
*/
-char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen,
- unsigned flags)
+char *nfs_path(char **p, struct dentry *dentry_in, char *buffer,
+ ssize_t buflen_in, unsigned flags)
{
char *end;
int namelen;
unsigned seq;
const char *base;
+ struct dentry *dentry;
+ ssize_t buflen;
rename_retry:
+ buflen = buflen_in;
+ dentry = dentry_in;
end = buffer+buflen;
*--end = '\0';
buflen--;
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index cbc17a2..887f913 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -370,7 +370,7 @@
} else
p = xdr_time_not_set(p);
if (attr->ia_valid & ATTR_MTIME_SET) {
- ts = timespec64_to_timespec(attr->ia_atime);
+ ts = timespec64_to_timespec(attr->ia_mtime);
xdr_encode_time(p, &ts);
} else if (attr->ia_valid & ATTR_MTIME) {
ts = timespec64_to_timespec(attr->ia_mtime);
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index c5c3fc6..26c94b3 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -253,37 +253,45 @@
int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type)
{
- struct posix_acl *alloc = NULL, *dfacl = NULL;
+ struct posix_acl *orig = acl, *dfacl = NULL, *alloc;
int status;
if (S_ISDIR(inode->i_mode)) {
switch(type) {
case ACL_TYPE_ACCESS:
- alloc = dfacl = get_acl(inode, ACL_TYPE_DEFAULT);
+ alloc = get_acl(inode, ACL_TYPE_DEFAULT);
if (IS_ERR(alloc))
goto fail;
+ dfacl = alloc;
break;
case ACL_TYPE_DEFAULT:
- dfacl = acl;
- alloc = acl = get_acl(inode, ACL_TYPE_ACCESS);
+ alloc = get_acl(inode, ACL_TYPE_ACCESS);
if (IS_ERR(alloc))
goto fail;
+ dfacl = acl;
+ acl = alloc;
break;
}
}
if (acl == NULL) {
- alloc = acl = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
+ alloc = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
if (IS_ERR(alloc))
goto fail;
+ acl = alloc;
}
status = __nfs3_proc_setacls(inode, acl, dfacl);
- posix_acl_release(alloc);
+out:
+ if (acl != orig)
+ posix_acl_release(acl);
+ if (dfacl != orig)
+ posix_acl_release(dfacl);
return status;
fail:
- return PTR_ERR(alloc);
+ status = PTR_ERR(alloc);
+ goto out;
}
const struct xattr_handler *nfs3_xattr_handlers[] = {
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 9eb2f1a..01a03ca 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -350,7 +350,7 @@
break;
case NFS3_CREATE_UNCHECKED:
- goto out;
+ goto out_release_acls;
}
nfs_fattr_init(data->res.dir_attr);
nfs_fattr_init(data->res.fattr);
@@ -717,7 +717,7 @@
break;
default:
status = -EINVAL;
- goto out;
+ goto out_release_acls;
}
d_alias = nfs3_do_create(dir, dentry, data);
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 6027678..23d75cd 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -35,6 +35,7 @@
*/
#define NFS3_fhandle_sz (1+16)
#define NFS3_fh_sz (NFS3_fhandle_sz) /* shorthand */
+#define NFS3_post_op_fh_sz (1+NFS3_fh_sz)
#define NFS3_sattr_sz (15)
#define NFS3_filename_sz (1+(NFS3_MAXNAMLEN>>2))
#define NFS3_path_sz (1+(NFS3_MAXPATHLEN>>2))
@@ -72,7 +73,7 @@
#define NFS3_readlinkres_sz (1+NFS3_post_op_attr_sz+1+1)
#define NFS3_readres_sz (1+NFS3_post_op_attr_sz+3+1)
#define NFS3_writeres_sz (1+NFS3_wcc_data_sz+4)
-#define NFS3_createres_sz (1+NFS3_fh_sz+NFS3_post_op_attr_sz+NFS3_wcc_data_sz)
+#define NFS3_createres_sz (1+NFS3_post_op_fh_sz+NFS3_post_op_attr_sz+NFS3_wcc_data_sz)
#define NFS3_renameres_sz (1+(2 * NFS3_wcc_data_sz))
#define NFS3_linkres_sz (1+NFS3_post_op_attr_sz+NFS3_wcc_data_sz)
#define NFS3_readdirres_sz (1+NFS3_post_op_attr_sz+2+1)
@@ -2338,6 +2339,7 @@
void *data)
{
struct nfs_commitres *result = data;
+ struct nfs_writeverf *verf = result->verf;
enum nfs_stat status;
int error;
@@ -2350,7 +2352,9 @@
result->op_status = status;
if (status != NFS3_OK)
goto out_status;
- error = decode_writeverf3(xdr, &result->verf->verifier);
+ error = decode_writeverf3(xdr, &verf->verifier);
+ if (!error)
+ verf->committed = NFS_FILE_SYNC;
out:
return error;
out_status:
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 5196bfa..6b7c926 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -59,7 +59,8 @@
static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
loff_t offset, loff_t len)
{
- struct nfs_server *server = NFS_SERVER(file_inode(filep));
+ struct inode *inode = file_inode(filep);
+ struct nfs_server *server = NFS_SERVER(inode);
struct nfs4_exception exception = { };
struct nfs_lock_context *lock;
int err;
@@ -68,9 +69,13 @@
if (IS_ERR(lock))
return PTR_ERR(lock);
- exception.inode = file_inode(filep);
+ exception.inode = inode;
exception.state = lock->open_context->state;
+ err = nfs_sync_inode(inode);
+ if (err)
+ goto out;
+
do {
err = _nfs42_proc_fallocate(msg, filep, lock, offset, len);
if (err == -ENOTSUPP) {
@@ -79,7 +84,7 @@
}
err = nfs4_handle_exception(server, err, &exception);
} while (exception.retry);
-
+out:
nfs_put_lock_context(lock);
return err;
}
@@ -117,16 +122,13 @@
return -EOPNOTSUPP;
inode_lock(inode);
- err = nfs_sync_inode(inode);
- if (err)
- goto out_unlock;
err = nfs42_proc_fallocate(&msg, filep, offset, len);
if (err == 0)
truncate_pagecache_range(inode, offset, (offset + len) -1);
if (err == -EOPNOTSUPP)
NFS_SERVER(inode)->caps &= ~NFS_CAP_DEALLOCATE;
-out_unlock:
+
inode_unlock(inode);
return err;
}
@@ -283,14 +285,14 @@
status = handle_async_copy(res, server, src, dst,
&args->src_stateid);
if (status)
- return status;
+ goto out;
}
if ((!res->synchronous || !args->sync) &&
res->write_res.verifier.committed != NFS_FILE_SYNC) {
status = process_copy_commit(dst, pos_dst, res);
if (status)
- return status;
+ goto out;
}
truncate_pagecache_range(dst_inode, pos_dst,
@@ -498,7 +500,10 @@
if (status)
return status;
- return vfs_setpos(filep, res.sr_offset, inode->i_sb->s_maxbytes);
+ if (whence == SEEK_DATA && res.sr_eof)
+ return -NFS4ERR_NXIO;
+ else
+ return vfs_setpos(filep, res.sr_offset, inode->i_sb->s_maxbytes);
}
loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 16b2e5c..5708b5a 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -203,6 +203,7 @@
struct inode *inode;
nfs4_stateid *stateid;
long timeout;
+ unsigned char task_is_privileged : 1;
unsigned char delay : 1,
recovering : 1,
retry : 1;
@@ -439,9 +440,7 @@
extern void nfs4_renewd_prepare_shutdown(struct nfs_server *);
extern void nfs4_kill_renewd(struct nfs_client *);
extern void nfs4_renew_state(struct work_struct *);
-extern void nfs4_set_lease_period(struct nfs_client *clp,
- unsigned long lease,
- unsigned long lastrenewed);
+extern void nfs4_set_lease_period(struct nfs_client *clp, unsigned long lease);
/* nfs4state.c */
@@ -572,6 +571,14 @@
return (s32)(be32_to_cpu(s1->seqid) - be32_to_cpu(s2->seqid)) > 0;
}
+static inline bool nfs4_stateid_is_next(const nfs4_stateid *s1, const nfs4_stateid *s2)
+{
+ u32 seq1 = be32_to_cpu(s1->seqid);
+ u32 seq2 = be32_to_cpu(s2->seqid);
+
+ return seq2 == seq1 + 1U || (seq2 == 1U && seq1 == 0xffffffffU);
+}
+
static inline void nfs4_stateid_seqid_inc(nfs4_stateid *s1)
{
u32 seqid = be32_to_cpu(s1->seqid);
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index da62040..8cace83 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -197,8 +197,11 @@
struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init)
{
- int err;
+ char buf[INET6_ADDRSTRLEN + 1];
+ const char *ip_addr = cl_init->ip_addr;
struct nfs_client *clp = nfs_alloc_client(cl_init);
+ int err;
+
if (IS_ERR(clp))
return clp;
@@ -216,13 +219,50 @@
INIT_LIST_HEAD(&clp->cl_ds_clients);
rpc_init_wait_queue(&clp->cl_rpcwaitq, "NFS client");
clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED;
- clp->cl_minorversion = cl_init->minorversion;
clp->cl_mvops = nfs_v4_minor_ops[cl_init->minorversion];
clp->cl_mig_gen = 1;
#if IS_ENABLED(CONFIG_NFS_V4_1)
init_waitqueue_head(&clp->cl_lock_waitq);
#endif
INIT_LIST_HEAD(&clp->pending_cb_stateids);
+
+ if (cl_init->minorversion != 0)
+ __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);
+
+ /*
+ * Set up the connection to the server before we add add to the
+ * global list.
+ */
+ err = nfs_create_rpc_client(clp, cl_init, RPC_AUTH_GSS_KRB5I);
+ if (err == -EINVAL)
+ err = nfs_create_rpc_client(clp, cl_init, RPC_AUTH_UNIX);
+ if (err < 0)
+ goto error;
+
+ /* If no clientaddr= option was specified, find a usable cb address */
+ if (ip_addr == NULL) {
+ struct sockaddr_storage cb_addr;
+ struct sockaddr *sap = (struct sockaddr *)&cb_addr;
+
+ err = rpc_localaddr(clp->cl_rpcclient, sap, sizeof(cb_addr));
+ if (err < 0)
+ goto error;
+ err = rpc_ntop(sap, buf, sizeof(buf));
+ if (err < 0)
+ goto error;
+ ip_addr = (const char *)buf;
+ }
+ strlcpy(clp->cl_ipaddr, ip_addr, sizeof(clp->cl_ipaddr));
+
+ err = nfs_idmap_new(clp);
+ if (err < 0) {
+ dprintk("%s: failed to create idmapper. Error = %d\n",
+ __func__, err);
+ goto error;
+ }
+ __set_bit(NFS_CS_IDMAP, &clp->cl_res_state);
return clp;
error:
@@ -373,8 +413,6 @@
struct nfs_client *nfs4_init_client(struct nfs_client *clp,
const struct nfs_client_initdata *cl_init)
{
- char buf[INET6_ADDRSTRLEN + 1];
- const char *ip_addr = cl_init->ip_addr;
struct nfs_client *old;
int error;
@@ -382,43 +420,6 @@
/* the client is initialised already */
return clp;
- /* Check NFS protocol revision and initialize RPC op vector */
- clp->rpc_ops = &nfs_v4_clientops;
-
- if (clp->cl_minorversion != 0)
- __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, cl_init, RPC_AUTH_GSS_KRB5I);
- if (error == -EINVAL)
- error = nfs_create_rpc_client(clp, cl_init, RPC_AUTH_UNIX);
- if (error < 0)
- goto error;
-
- /* If no clientaddr= option was specified, find a usable cb address */
- if (ip_addr == NULL) {
- struct sockaddr_storage cb_addr;
- struct sockaddr *sap = (struct sockaddr *)&cb_addr;
-
- error = rpc_localaddr(clp->cl_rpcclient, sap, sizeof(cb_addr));
- if (error < 0)
- goto error;
- error = rpc_ntop(sap, buf, sizeof(buf));
- if (error < 0)
- goto error;
- ip_addr = (const char *)buf;
- }
- strlcpy(clp->cl_ipaddr, ip_addr, sizeof(clp->cl_ipaddr));
-
- error = nfs_idmap_new(clp);
- if (error < 0) {
- dprintk("%s: failed to create idmapper. Error = %d\n",
- __func__, error);
- goto error;
- }
- __set_bit(NFS_CS_IDMAP, &clp->cl_res_state);
-
error = nfs4_init_client_minor_version(clp);
if (error < 0)
goto error;
@@ -436,8 +437,8 @@
*/
nfs_mark_client_ready(clp, -EPERM);
}
- nfs_put_client(clp);
clear_bit(NFS_CS_TSM_POSSIBLE, &clp->cl_flags);
+ nfs_put_client(clp);
return old;
error:
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 339663d..7c73097 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -86,7 +86,6 @@
if (inode != d_inode(dentry))
goto out_drop;
- nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
nfs_file_set_open_context(filp, ctx);
nfs_fscache_open_file(inode, filp);
err = 0;
@@ -110,6 +109,7 @@
nfs4_file_flush(struct file *file, fl_owner_t id)
{
struct inode *inode = file_inode(file);
+ errseq_t since;
dprintk("NFS: flush(%pD2)\n", file);
@@ -125,7 +125,9 @@
return filemap_fdatawrite(file->f_mapping);
/* Flush writes to the server and return any errors */
- return nfs_wb_all(inode);
+ since = filemap_sample_wb_err(file->f_mapping);
+ nfs_wb_all(inode);
+ return filemap_check_wb_err(file->f_mapping, since);
}
#ifdef CONFIG_NFS_V4_2
@@ -136,7 +138,8 @@
/* Only offload copy if superblock is the same */
if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb)
return -EXDEV;
- if (!nfs_server_capable(file_inode(file_out), NFS_CAP_COPY))
+ if (!nfs_server_capable(file_inode(file_out), NFS_CAP_COPY) ||
+ !nfs_server_capable(file_inode(file_in), NFS_CAP_COPY))
return -EOPNOTSUPP;
if (file_inode(file_in) == file_inode(file_out))
return -EOPNOTSUPP;
@@ -165,7 +168,7 @@
case SEEK_HOLE:
case SEEK_DATA:
ret = nfs42_proc_llseek(filep, offset, whence);
- if (ret != -ENOTSUPP)
+ if (ret != -EOPNOTSUPP)
return ret;
/* Fall through */
default:
@@ -211,6 +214,9 @@
if (remap_flags & ~REMAP_FILE_ADVISORY)
return -EINVAL;
+ if (IS_SWAPFILE(dst_inode) || IS_SWAPFILE(src_inode))
+ return -ETXTBSY;
+
/* check alignment w.r.t. clone_blksize */
ret = -EINVAL;
if (bs) {
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index caacf5e..5ecaf7b 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -521,9 +521,7 @@
case -NFS4ERR_DEADSESSION:
case -NFS4ERR_SEQ_FALSE_RETRY:
case -NFS4ERR_SEQ_MISORDERED:
- dprintk("%s ERROR: %d Reset session\n", __func__,
- errorcode);
- nfs4_schedule_session_recovery(clp->cl_session, errorcode);
+ /* Handled in nfs41_sequence_process() */
goto wait_on_recovery;
#endif /* defined(CONFIG_NFS_V4_1) */
case -NFS4ERR_FILE_OPEN:
@@ -583,6 +581,8 @@
goto out_retry;
}
if (exception->recovering) {
+ if (exception->task_is_privileged)
+ return -EDEADLOCK;
ret = nfs4_wait_clnt_recover(clp);
if (test_bit(NFS_MIG_FAILED, &server->mig_status))
return -EIO;
@@ -608,6 +608,8 @@
goto out_retry;
}
if (exception->recovering) {
+ if (exception->task_is_privileged)
+ return -EDEADLOCK;
rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL);
if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0)
rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task);
@@ -776,12 +778,21 @@
slot->seq_nr_last_acked = seqnr;
}
+static void nfs4_probe_sequence(struct nfs_client *client, const struct cred *cred,
+ struct nfs4_slot *slot)
+{
+ struct rpc_task *task = _nfs41_proc_sequence(client, cred, slot, true);
+ if (!IS_ERR(task))
+ rpc_put_task_async(task);
+}
+
static int nfs41_sequence_process(struct rpc_task *task,
struct nfs4_sequence_res *res)
{
struct nfs4_session *session;
struct nfs4_slot *slot = res->sr_slot;
struct nfs_client *clp;
+ int status;
int ret = 1;
if (slot == NULL)
@@ -791,16 +802,21 @@
goto out;
session = slot->table->session;
+ clp = session->clp;
trace_nfs4_sequence_done(session, res);
+
+ status = res->sr_status;
+ if (task->tk_status == -NFS4ERR_DEADSESSION)
+ status = -NFS4ERR_DEADSESSION;
+
/* Check the SEQUENCE operation status */
- switch (res->sr_status) {
+ switch (status) {
case 0:
/* Mark this sequence number as having been acked */
nfs4_slot_sequence_acked(slot, slot->seq_nr);
/* Update the slot's sequence and clientid lease timer */
slot->seq_done = 1;
- clp = session->clp;
do_renew_lease(clp, res->sr_timestamp);
/* Check sequence flags */
nfs41_handle_sequence_flag_errors(clp, res->sr_status_flags,
@@ -848,10 +864,18 @@
/*
* Were one or more calls using this slot interrupted?
* If the server never received the request, then our
- * transmitted slot sequence number may be too high.
+ * transmitted slot sequence number may be too high. However,
+ * if the server did receive the request then it might
+ * accidentally give us a reply with a mismatched operation.
+ * We can sort this out by sending a lone sequence operation
+ * to the server on the same slot.
*/
if ((s32)(slot->seq_nr - slot->seq_nr_last_acked) > 1) {
slot->seq_nr--;
+ if (task->tk_msg.rpc_proc != &nfs4_procedures[NFSPROC4_CLNT_SEQUENCE]) {
+ nfs4_probe_sequence(clp, task->tk_msg.rpc_cred, slot);
+ res->sr_slot = NULL;
+ }
goto retry_nowait;
}
/*
@@ -866,6 +890,10 @@
*/
slot->seq_nr = slot->seq_nr_highest_sent;
goto out_retry;
+ case -NFS4ERR_BADSESSION:
+ case -NFS4ERR_DEADSESSION:
+ case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+ goto session_recover;
default:
/* Just update the slot sequence no. */
slot->seq_done = 1;
@@ -876,8 +904,10 @@
out_noaction:
return ret;
session_recover:
- nfs4_schedule_session_recovery(session, res->sr_status);
- goto retry_nowait;
+ nfs4_schedule_session_recovery(session, status);
+ dprintk("%s ERROR: %d Reset session\n", __func__, status);
+ nfs41_sequence_free_slot(res);
+ goto out;
retry_new_seq:
++slot->seq_nr;
retry_nowait:
@@ -1489,19 +1519,6 @@
wake_up_all(&state->waitq);
}
-static void nfs_state_log_out_of_order_open_stateid(struct nfs4_state *state,
- const nfs4_stateid *stateid)
-{
- u32 state_seqid = be32_to_cpu(state->open_stateid.seqid);
- u32 stateid_seqid = be32_to_cpu(stateid->seqid);
-
- if (stateid_seqid == state_seqid + 1U ||
- (stateid_seqid == 1U && state_seqid == 0xffffffffU))
- nfs_state_log_update_open_stateid(state);
- else
- set_bit(NFS_STATE_CHANGE_WAIT, &state->flags);
-}
-
static void nfs_test_and_clear_all_open_stateid(struct nfs4_state *state)
{
struct nfs_client *clp = state->owner->so_server->nfs_client;
@@ -1527,21 +1544,19 @@
* i.e. The stateid seqids have to be initialised to 1, and
* are then incremented on every state transition.
*/
-static bool nfs_need_update_open_stateid(struct nfs4_state *state,
+static bool nfs_stateid_is_sequential(struct nfs4_state *state,
const nfs4_stateid *stateid)
{
- if (test_bit(NFS_OPEN_STATE, &state->flags) == 0 ||
- !nfs4_stateid_match_other(stateid, &state->open_stateid)) {
+ if (test_bit(NFS_OPEN_STATE, &state->flags)) {
+ /* The common case - we're updating to a new sequence number */
+ if (nfs4_stateid_match_other(stateid, &state->open_stateid) &&
+ nfs4_stateid_is_next(&state->open_stateid, stateid)) {
+ return true;
+ }
+ } else {
+ /* This is the first OPEN in this generation */
if (stateid->seqid == cpu_to_be32(1))
- nfs_state_log_update_open_stateid(state);
- else
- set_bit(NFS_STATE_CHANGE_WAIT, &state->flags);
- return true;
- }
-
- if (nfs4_stateid_is_newer(stateid, &state->open_stateid)) {
- nfs_state_log_out_of_order_open_stateid(state, stateid);
- return true;
+ return true;
}
return false;
}
@@ -1615,16 +1630,16 @@
int status = 0;
for (;;) {
- if (!nfs_need_update_open_stateid(state, stateid))
- return;
- if (!test_bit(NFS_STATE_CHANGE_WAIT, &state->flags))
+ if (nfs_stateid_is_sequential(state, stateid))
break;
+
if (status)
break;
/* Rely on seqids for serialisation with NFSv4.0 */
if (!nfs4_has_session(NFS_SERVER(state->inode)->nfs_client))
break;
+ set_bit(NFS_STATE_CHANGE_WAIT, &state->flags);
prepare_to_wait(&state->waitq, &wait, TASK_KILLABLE);
/*
* Ensure we process the state changes in the same order
@@ -1635,7 +1650,8 @@
spin_unlock(&state->owner->so_lock);
rcu_read_unlock();
trace_nfs4_open_stateid_update_wait(state->inode, stateid, 0);
- if (!signal_pending(current)) {
+
+ if (!fatal_signal_pending(current)) {
if (schedule_timeout(5*HZ) == 0)
status = -EAGAIN;
else
@@ -2188,7 +2204,6 @@
case -NFS4ERR_BAD_HIGH_SLOT:
case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
case -NFS4ERR_DEADSESSION:
- nfs4_schedule_session_recovery(server->nfs_client->cl_session, err);
return -EAGAIN;
case -NFS4ERR_STALE_CLIENTID:
case -NFS4ERR_STALE_STATEID:
@@ -2953,10 +2968,13 @@
struct dentry *dentry;
struct nfs4_state *state;
fmode_t acc_mode = _nfs4_ctx_to_accessmode(ctx);
+ struct inode *dir = d_inode(opendata->dir);
+ unsigned long dir_verifier;
unsigned int seq;
int ret;
seq = raw_seqcount_begin(&sp->so_reclaim_seqcount);
+ dir_verifier = nfs_save_change_attribute(dir);
ret = _nfs4_proc_open(opendata, ctx);
if (ret != 0)
@@ -2984,8 +3002,19 @@
dput(ctx->dentry);
ctx->dentry = dentry = alias;
}
- nfs_set_verifier(dentry,
- nfs_save_change_attribute(d_inode(opendata->dir)));
+ }
+
+ switch(opendata->o_arg.claim) {
+ default:
+ break;
+ case NFS4_OPEN_CLAIM_NULL:
+ case NFS4_OPEN_CLAIM_DELEGATE_CUR:
+ case NFS4_OPEN_CLAIM_DELEGATE_PREV:
+ if (!opendata->rpc_done)
+ break;
+ if (opendata->o_res.delegation_type != 0)
+ dir_verifier = nfs_save_change_attribute(dir);
+ nfs_set_verifier(dentry, dir_verifier);
}
/* Parse layoutget results before we check for access */
@@ -3178,6 +3207,11 @@
exception.retry = 1;
continue;
}
+ if (status == -NFS4ERR_EXPIRED) {
+ nfs4_schedule_lease_recovery(server->nfs_client);
+ exception.retry = 1;
+ continue;
+ }
if (status == -EAGAIN) {
/* We must have found a delegation */
exception.retry = 1;
@@ -3213,8 +3247,10 @@
/* Servers should only apply open mode checks for file size changes */
truncate = (arg->iap->ia_valid & ATTR_SIZE) ? true : false;
- if (!truncate)
+ if (!truncate) {
+ nfs4_inode_make_writeable(inode);
goto zero_stateid;
+ }
if (nfs4_copy_delegation_stateid(inode, FMODE_WRITE, &arg->stateid, &delegation_cred)) {
/* Use that stateid */
@@ -3351,7 +3387,8 @@
__be32 seqid_open;
u32 dst_seqid;
bool ret;
- int seq;
+ int seq, status = -EAGAIN;
+ DEFINE_WAIT(wait);
for (;;) {
ret = false;
@@ -3363,15 +3400,41 @@
continue;
break;
}
+
+ write_seqlock(&state->seqlock);
seqid_open = state->open_stateid.seqid;
- if (read_seqretry(&state->seqlock, seq))
- continue;
dst_seqid = be32_to_cpu(dst->seqid);
- if ((s32)(dst_seqid - be32_to_cpu(seqid_open)) >= 0)
- dst->seqid = cpu_to_be32(dst_seqid + 1);
- else
+
+ /* Did another OPEN bump the state's seqid? try again: */
+ if ((s32)(be32_to_cpu(seqid_open) - dst_seqid) > 0) {
dst->seqid = seqid_open;
+ write_sequnlock(&state->seqlock);
+ ret = true;
+ break;
+ }
+
+ /* server says we're behind but we haven't seen the update yet */
+ set_bit(NFS_STATE_CHANGE_WAIT, &state->flags);
+ prepare_to_wait(&state->waitq, &wait, TASK_KILLABLE);
+ write_sequnlock(&state->seqlock);
+ trace_nfs4_close_stateid_update_wait(state->inode, dst, 0);
+
+ if (fatal_signal_pending(current))
+ status = -EINTR;
+ else
+ if (schedule_timeout(5*HZ) != 0)
+ status = 0;
+
+ finish_wait(&state->waitq, &wait);
+
+ if (!status)
+ continue;
+ if (status == -EINTR)
+ break;
+
+ /* we slept the whole 5 seconds, we must have lost a seqid */
+ dst->seqid = cpu_to_be32(dst_seqid + 1);
ret = true;
break;
}
@@ -3429,10 +3492,8 @@
trace_nfs4_close(state, &calldata->arg, &calldata->res, task->tk_status);
/* Handle Layoutreturn errors */
- if (pnfs_roc_done(task, calldata->inode,
- &calldata->arg.lr_args,
- &calldata->res.lr_res,
- &calldata->res.lr_ret) == -EAGAIN)
+ if (pnfs_roc_done(task, &calldata->arg.lr_args, &calldata->res.lr_res,
+ &calldata->res.lr_ret) == -EAGAIN)
goto out_restart;
/* hmm. we are done with the inode, and in the process of freeing
@@ -4840,12 +4901,12 @@
u64 cookie, struct page **pages, unsigned int count, bool plus)
{
struct inode *dir = d_inode(dentry);
+ struct nfs_server *server = NFS_SERVER(dir);
struct nfs4_readdir_arg args = {
.fh = NFS_FH(dir),
.pages = pages,
.pgbase = 0,
.count = count,
- .bitmask = NFS_SERVER(d_inode(dentry))->attr_bitmask,
.plus = plus,
};
struct nfs4_readdir_res res;
@@ -4860,9 +4921,15 @@
dprintk("%s: dentry = %pd2, cookie = %Lu\n", __func__,
dentry,
(unsigned long long)cookie);
+ if (!(server->caps & NFS_CAP_SECURITY_LABEL))
+ args.bitmask = server->attr_bitmask_nl;
+ else
+ args.bitmask = server->attr_bitmask;
+
nfs4_setup_readdir(cookie, NFS_I(dir)->cookieverf, dentry, &args);
res.pgbase = args.pgbase;
- status = nfs4_call_sync(NFS_SERVER(dir)->client, NFS_SERVER(dir), &msg, &args.seq_args, &res.seq_res, 0);
+ status = nfs4_call_sync(server->client, server, &msg, &args.seq_args,
+ &res.seq_res, 0);
if (status >= 0) {
memcpy(NFS_I(dir)->cookieverf, res.verifier.data, NFS4_VERIFIER_SIZE);
status += args.pgbase;
@@ -5010,16 +5077,13 @@
struct nfs4_exception exception = {
.interruptible = true,
};
- unsigned long now = jiffies;
int err;
do {
err = _nfs4_do_fsinfo(server, fhandle, fsinfo);
trace_nfs4_fsinfo(server, fhandle, fsinfo->fattr, err);
if (err == 0) {
- nfs4_set_lease_period(server->nfs_client,
- fsinfo->lease_time * HZ,
- now);
+ nfs4_set_lease_period(server->nfs_client, fsinfo->lease_time * HZ);
break;
}
err = nfs4_handle_exception(server, err, &exception);
@@ -5282,7 +5346,7 @@
hdr->timestamp = jiffies;
msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_WRITE];
- nfs4_init_sequence(&hdr->args.seq_args, &hdr->res.seq_res, 1, 0);
+ nfs4_init_sequence(&hdr->args.seq_args, &hdr->res.seq_res, 0, 0);
nfs4_state_protect_write(server->nfs_client, clnt, msg, hdr);
}
@@ -5694,6 +5758,9 @@
unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE);
int ret, i;
+ /* You can't remove system.nfs4_acl: */
+ if (buflen == 0)
+ return -EINVAL;
if (!nfs4_server_supports_acls(server))
return -EOPNOTSUPP;
if (npages > ARRAY_SIZE(pages))
@@ -5732,6 +5799,14 @@
do {
err = __nfs4_proc_set_acl(inode, buf, buflen);
trace_nfs4_set_acl(inode, err);
+ if (err == -NFS4ERR_BADOWNER || err == -NFS4ERR_BADNAME) {
+ /*
+ * no need to retry since the kernel
+ * isn't involved in encoding the ACEs.
+ */
+ err = -EINVAL;
+ break;
+ }
err = nfs4_handle_exception(NFS_SERVER(inode), err,
&exception);
} while (exception.retry);
@@ -5770,9 +5845,7 @@
return ret;
if (!(fattr.valid & NFS_ATTR_FATTR_V4_SECURITY_LABEL))
return -ENOENT;
- if (buflen < label.len)
- return -ERANGE;
- return 0;
+ return label.len;
}
static int nfs4_get_security_label(struct inode *inode, void *buf,
@@ -6075,6 +6148,7 @@
.callback_data = &setclientid,
.flags = RPC_TASK_TIMEOUT | RPC_TASK_NO_ROUND_ROBIN,
};
+ unsigned long now = jiffies;
int status;
/* nfs_client_id4 */
@@ -6107,6 +6181,9 @@
clp->cl_acceptor = rpcauth_stringify_acceptor(setclientid.sc_cred);
put_rpccred(setclientid.sc_cred);
}
+
+ if (status == 0)
+ do_renew_lease(clp, now);
out:
trace_nfs4_setclientid(clp, status);
dprintk("NFS reply setclientid: %d\n", status);
@@ -6166,6 +6243,7 @@
struct nfs4_exception exception = {
.inode = data->inode,
.stateid = &data->stateid,
+ .task_is_privileged = data->args.seq_args.sa_privileged,
};
if (!nfs4_sequence_done(task, &data->res.seq_res))
@@ -6174,10 +6252,8 @@
trace_nfs4_delegreturn_exit(&data->args, &data->res, task->tk_status);
/* Handle Layoutreturn errors */
- if (pnfs_roc_done(task, data->inode,
- &data->args.lr_args,
- &data->res.lr_res,
- &data->res.lr_ret) == -EAGAIN)
+ if (pnfs_roc_done(task, &data->args.lr_args, &data->res.lr_res,
+ &data->res.lr_ret) == -EAGAIN)
goto out_restart;
switch (task->tk_status) {
@@ -6226,10 +6302,10 @@
struct nfs4_delegreturndata *data = calldata;
struct inode *inode = data->inode;
+ if (data->lr.roc)
+ pnfs_roc_release(&data->lr.arg, &data->lr.res,
+ data->res.lr_ret);
if (inode) {
- if (data->lr.roc)
- pnfs_roc_release(&data->lr.arg, &data->lr.res,
- data->res.lr_ret);
nfs_post_op_update_inode_force_wcc(inode, &data->fattr);
nfs_iput_and_deactive(inode);
}
@@ -6243,8 +6319,10 @@
d_data = (struct nfs4_delegreturndata *)data;
- if (!d_data->lr.roc && nfs4_wait_on_layoutreturn(d_data->inode, task))
+ if (!d_data->lr.roc && nfs4_wait_on_layoutreturn(d_data->inode, task)) {
+ nfs4_sequence_done(task, &d_data->res.seq_res);
return;
+ }
lo = d_data->args.lr_args ? d_data->args.lr_args->layout : NULL;
if (lo && !pnfs_layout_is_valid(lo)) {
@@ -6284,7 +6362,6 @@
data = kzalloc(sizeof(*data), GFP_NOFS);
if (data == NULL)
return -ENOMEM;
- nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1, 0);
nfs4_state_protect(server->nfs_client,
NFS_SP4_MACH_CRED_CLEANUP,
@@ -6302,18 +6379,22 @@
nfs_fattr_init(data->res.fattr);
data->timestamp = jiffies;
data->rpc_status = 0;
- data->lr.roc = pnfs_roc(inode, &data->lr.arg, &data->lr.res, cred);
data->inode = nfs_igrab_and_active(inode);
- if (data->inode) {
+ if (data->inode || issync) {
+ data->lr.roc = pnfs_roc(inode, &data->lr.arg, &data->lr.res,
+ cred);
if (data->lr.roc) {
data->args.lr_args = &data->lr.arg;
data->res.lr_res = &data->lr.res;
}
- } else if (data->lr.roc) {
- pnfs_roc_release(&data->lr.arg, &data->lr.res, 0);
- data->lr.roc = false;
}
+ if (!data->inode)
+ nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1,
+ 1);
+ else
+ nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1,
+ 0);
task_setup_data.callback_data = data;
msg.rpc_argp = &data->args;
msg.rpc_resp = &data->res;
@@ -6893,9 +6974,9 @@
data->arg.new_lock_owner, ret);
} else
data->cancelled = true;
+ trace_nfs4_set_lock(fl, state, &data->res.stateid, cmd, ret);
rpc_put_task(task);
dprintk("%s: done, ret = %d!\n", __func__, ret);
- trace_nfs4_set_lock(fl, state, &data->res.stateid, cmd, ret);
return ret;
}
@@ -7187,7 +7268,12 @@
err = nfs4_set_lock_state(state, fl);
if (err != 0)
return err;
- err = _nfs4_do_setlk(state, F_SETLK, fl, NFS_LOCK_NEW);
+ do {
+ err = _nfs4_do_setlk(state, F_SETLK, fl, NFS_LOCK_NEW);
+ if (err != -NFS4ERR_DELAY)
+ break;
+ ssleep(1);
+ } while (err == -NFS4ERR_DELAY);
return nfs4_handle_delegation_recall_error(server, state, stateid, fl, err);
}
@@ -7794,9 +7880,11 @@
* both PNFS and NON_PNFS flags set, and not having one of NON_PNFS, PNFS, or
* DS flags set.
*/
-static int nfs4_check_cl_exchange_flags(u32 flags)
+static int nfs4_check_cl_exchange_flags(u32 flags, u32 version)
{
- if (flags & ~EXCHGID4_FLAG_MASK_R)
+ if (version >= 2 && (flags & ~EXCHGID4_2_FLAG_MASK_R))
+ goto out_inval;
+ else if (version < 2 && (flags & ~EXCHGID4_FLAG_MASK_R))
goto out_inval;
if ((flags & EXCHGID4_FLAG_USE_PNFS_MDS) &&
(flags & EXCHGID4_FLAG_USE_NON_PNFS))
@@ -7820,10 +7908,26 @@
static void
nfs4_bind_one_conn_to_session_done(struct rpc_task *task, void *calldata)
{
+ struct nfs41_bind_conn_to_session_args *args = task->tk_msg.rpc_argp;
+ struct nfs41_bind_conn_to_session_res *res = task->tk_msg.rpc_resp;
+ struct nfs_client *clp = args->client;
+
+ switch (task->tk_status) {
+ case -NFS4ERR_BADSESSION:
+ case -NFS4ERR_DEADSESSION:
+ nfs4_schedule_session_recovery(clp->cl_session,
+ task->tk_status);
+ }
+ if (args->dir == NFS4_CDFC4_FORE_OR_BOTH &&
+ res->dir != NFS4_CDFS4_BOTH) {
+ rpc_task_close_connection(task);
+ if (args->retries++ < MAX_BIND_CONN_TO_SESSION_RETRIES)
+ rpc_restart_call(task);
+ }
}
static const struct rpc_call_ops nfs4_bind_one_conn_to_session_ops = {
- .rpc_call_done = &nfs4_bind_one_conn_to_session_done,
+ .rpc_call_done = nfs4_bind_one_conn_to_session_done,
};
/*
@@ -7842,6 +7946,7 @@
struct nfs41_bind_conn_to_session_args args = {
.client = clp,
.dir = NFS4_CDFC4_FORE_OR_BOTH,
+ .retries = 0,
};
struct nfs41_bind_conn_to_session_res res;
struct rpc_message msg = {
@@ -8179,6 +8284,7 @@
struct rpc_task *task;
struct nfs41_exchange_id_args *argp;
struct nfs41_exchange_id_res *resp;
+ unsigned long now = jiffies;
int status;
task = nfs4_run_exchange_id(clp, cred, sp4_how, NULL);
@@ -8191,7 +8297,8 @@
if (status != 0)
goto out;
- status = nfs4_check_cl_exchange_flags(resp->flags);
+ status = nfs4_check_cl_exchange_flags(resp->flags,
+ clp->cl_mvops->minor_version);
if (status != 0)
goto out;
@@ -8199,6 +8306,8 @@
if (status != 0)
goto out;
+ do_renew_lease(clp, now);
+
clp->cl_clientid = resp->clientid;
clp->cl_exchange_flags = resp->flags;
clp->cl_seqid = resp->seqid;
@@ -8867,8 +8976,6 @@
case -NFS4ERR_BADSESSION:
case -NFS4ERR_DEADSESSION:
case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
- nfs4_schedule_session_recovery(clp->cl_session,
- task->tk_status);
break;
default:
nfs4_schedule_lease_recovery(clp);
@@ -9243,15 +9350,20 @@
&task_setup_data.rpc_client, &msg);
dprintk("--> %s\n", __func__);
+ lrp->inode = nfs_igrab_and_active(lrp->args.inode);
if (!sync) {
- lrp->inode = nfs_igrab_and_active(lrp->args.inode);
if (!lrp->inode) {
nfs4_layoutreturn_release(lrp);
return -EAGAIN;
}
task_setup_data.flags |= RPC_TASK_ASYNC;
}
- nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1, 0);
+ if (!lrp->inode)
+ nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1,
+ 1);
+ else
+ nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1,
+ 0);
task = rpc_run_task(&task_setup_data);
if (IS_ERR(task))
return PTR_ERR(task);
diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c
index 6ea431b..ff876dd 100644
--- a/fs/nfs/nfs4renewd.c
+++ b/fs/nfs/nfs4renewd.c
@@ -138,15 +138,12 @@
*
* @clp: pointer to nfs_client
* @lease: new value for lease period
- * @lastrenewed: time at which lease was last renewed
*/
void nfs4_set_lease_period(struct nfs_client *clp,
- unsigned long lease,
- unsigned long lastrenewed)
+ unsigned long lease)
{
spin_lock(&clp->cl_lock);
clp->cl_lease_time = lease;
- clp->cl_last_renewal = lastrenewed;
spin_unlock(&clp->cl_lock);
/* Cap maximum reconnect timeout at 1/2 lease period */
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 0c6d53d..ea680f6 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -91,17 +91,15 @@
{
int status;
struct nfs_fsinfo fsinfo;
- unsigned long now;
if (!test_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state)) {
nfs4_schedule_state_renewal(clp);
return 0;
}
- now = jiffies;
status = nfs4_proc_get_lease_time(clp, &fsinfo);
if (status == 0) {
- nfs4_set_lease_period(clp, fsinfo.lease_time * HZ, now);
+ nfs4_set_lease_period(clp, fsinfo.lease_time * HZ);
nfs4_schedule_state_renewal(clp);
}
@@ -735,9 +733,9 @@
state = new;
state->owner = owner;
atomic_inc(&owner->so_count);
- list_add_rcu(&state->inode_states, &nfsi->open_states);
ihold(inode);
state->inode = inode;
+ list_add_rcu(&state->inode_states, &nfsi->open_states);
spin_unlock(&inode->i_lock);
/* Note: The reclaim code dictates that we add stateless
* and read-only stateids to the end of the list */
diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c
index 04c5706..b90642b 100644
--- a/fs/nfs/nfs4super.c
+++ b/fs/nfs/nfs4super.c
@@ -96,7 +96,7 @@
nfs_inode_return_delegation_noreclaim(inode);
/* Note that above delegreturn would trigger pnfs return-on-close */
pnfs_return_layout(inode);
- pnfs_destroy_layout(NFS_I(inode));
+ pnfs_destroy_layout_final(NFS_I(inode));
/* First call standard NFS clear_inode() code */
nfs_clear_inode(inode);
}
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index b2f395f..2295a93 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -352,7 +352,7 @@
),
TP_fast_assign(
- __entry->error = error;
+ __entry->error = error < 0 ? -error : 0;
__assign_str(dstaddr, clp->cl_hostname);
),
@@ -432,7 +432,8 @@
__entry->target_highest_slotid =
res->sr_target_highest_slotid;
__entry->status_flags = res->sr_status_flags;
- __entry->error = res->sr_status;
+ __entry->error = res->sr_status < 0 ?
+ -res->sr_status : 0;
),
TP_printk(
"error=%ld (%s) session=0x%08x slot_nr=%u seq_nr=%u "
@@ -566,7 +567,7 @@
TP_PROTO(
const struct xdr_stream *xdr,
u32 op,
- int error
+ u32 error
),
TP_ARGS(xdr, op, error),
@@ -756,7 +757,7 @@
__entry->fileid = NFS_FILEID(inode);
__entry->fhandle = nfs_fhandle_hash(NFS_FH(inode));
__entry->fmode = (__force unsigned int)state->state;
- __entry->error = error;
+ __entry->error = error < 0 ? -error : 0;
__entry->stateid_seq =
be32_to_cpu(args->stateid.seqid);
__entry->stateid_hash =
@@ -821,7 +822,7 @@
TP_fast_assign(
const struct inode *inode = state->inode;
- __entry->error = error;
+ __entry->error = error < 0 ? -error : 0;
__entry->cmd = cmd;
__entry->type = request->fl_type;
__entry->start = request->fl_start;
@@ -893,7 +894,7 @@
TP_fast_assign(
const struct inode *inode = state->inode;
- __entry->error = error;
+ __entry->error = error < 0 ? -error : 0;
__entry->cmd = cmd;
__entry->type = request->fl_type;
__entry->start = request->fl_start;
@@ -989,7 +990,7 @@
TP_fast_assign(
__entry->dev = res->server->s_dev;
__entry->fhandle = nfs_fhandle_hash(args->fhandle);
- __entry->error = error;
+ __entry->error = error < 0 ? -error : 0;
__entry->stateid_seq =
be32_to_cpu(args->stateid->seqid);
__entry->stateid_hash =
@@ -1029,7 +1030,7 @@
TP_fast_assign(
const struct inode *inode = state->inode;
- __entry->error = error;
+ __entry->error = error < 0 ? -error : 0;
__entry->dev = inode->i_sb->s_dev;
__entry->fileid = NFS_FILEID(inode);
__entry->fhandle = nfs_fhandle_hash(NFS_FH(inode));
@@ -1131,7 +1132,7 @@
TP_fast_assign(
__entry->dev = inode->i_sb->s_dev;
__entry->ino = NFS_FILEID(inode);
- __entry->error = error;
+ __entry->error = error < 0 ? -error : 0;
),
TP_printk(
@@ -1167,7 +1168,7 @@
__entry->dev = olddir->i_sb->s_dev;
__entry->olddir = NFS_FILEID(olddir);
__entry->newdir = NFS_FILEID(newdir);
- __entry->error = error;
+ __entry->error = error < 0 ? -error : 0;
__assign_str(oldname, oldname->name);
__assign_str(newname, newname->name);
),
@@ -1258,7 +1259,7 @@
__entry->dev = inode->i_sb->s_dev;
__entry->fileid = NFS_FILEID(inode);
__entry->fhandle = nfs_fhandle_hash(NFS_FH(inode));
- __entry->error = error;
+ __entry->error = error < 0 ? -error : 0;
__entry->stateid_seq =
be32_to_cpu(stateid->seqid);
__entry->stateid_hash =
@@ -1290,6 +1291,7 @@
DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_delegreturn);
DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_open_stateid_update);
DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_open_stateid_update_wait);
+DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_close_stateid_update_wait);
DECLARE_EVENT_CLASS(nfs4_getattr_event,
TP_PROTO(
@@ -1314,7 +1316,7 @@
__entry->valid = fattr->valid;
__entry->fhandle = nfs_fhandle_hash(fhandle);
__entry->fileid = (fattr->valid & NFS_ATTR_FATTR_FILEID) ? fattr->fileid : 0;
- __entry->error = error;
+ __entry->error = error < 0 ? -error : 0;
),
TP_printk(
@@ -1361,7 +1363,7 @@
),
TP_fast_assign(
- __entry->error = error;
+ __entry->error = error < 0 ? -error : 0;
__entry->fhandle = nfs_fhandle_hash(fhandle);
if (!IS_ERR_OR_NULL(inode)) {
__entry->fileid = NFS_FILEID(inode);
@@ -1418,7 +1420,7 @@
),
TP_fast_assign(
- __entry->error = error;
+ __entry->error = error < 0 ? -error : 0;
__entry->fhandle = nfs_fhandle_hash(fhandle);
if (!IS_ERR_OR_NULL(inode)) {
__entry->fileid = NFS_FILEID(inode);
@@ -1721,7 +1723,7 @@
__entry->iomode = args->iomode;
__entry->offset = args->offset;
__entry->count = args->length;
- __entry->error = error;
+ __entry->error = error < 0 ? -error : 0;
__entry->stateid_seq =
be32_to_cpu(state->stateid.seqid);
__entry->stateid_hash =
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index ab07db0..9a022a4 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -3012,15 +3012,19 @@
struct compound_hdr hdr = {
.minorversion = nfs4_xdr_minorversion(&args->seq_args),
};
+ uint32_t replen;
encode_compound_hdr(xdr, req, &hdr);
encode_sequence(xdr, &args->seq_args, &hdr);
+
+ replen = hdr.replen + op_decode_hdr_maxsz;
+
encode_getdeviceinfo(xdr, args, &hdr);
- /* set up reply kvec. Subtract notification bitmap max size (2)
- * so that notification bitmap is put in xdr_buf tail */
+ /* set up reply kvec. device_addr4 opaque data is read into the
+ * pages */
rpc_prepare_reply_pages(req, args->pdev->pages, args->pdev->pgbase,
- args->pdev->pglen, hdr.replen - 2);
+ args->pdev->pglen, replen + 2 + 1);
encode_nops(&hdr);
}
@@ -4169,7 +4173,11 @@
return -EIO;
if (len < NFS4_MAXLABELLEN) {
if (label) {
- memcpy(label->label, p, len);
+ if (label->len) {
+ if (label->len < len)
+ return -ERANGE;
+ memcpy(label->label, p, len);
+ }
label->len = len;
label->pi = pi;
label->lfs = lfs;
@@ -4316,11 +4324,14 @@
static int decode_commit(struct xdr_stream *xdr, struct nfs_commitres *res)
{
+ struct nfs_writeverf *verf = res->verf;
int status;
status = decode_op_hdr(xdr, OP_COMMIT);
if (!status)
- status = decode_write_verifier(xdr, &res->verf->verifier);
+ status = decode_write_verifier(xdr, &verf->verifier);
+ if (!status)
+ verf->committed = NFS_FILE_SYNC;
return status;
}
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 361cc10..c8081d2 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -1147,7 +1147,12 @@
__field(unsigned int, task_id)
__field(unsigned int, client_id)
__field(u32, xid)
+ __field(int, version)
__field(unsigned long, error)
+ __string(program,
+ xdr->rqst->rq_task->tk_client->cl_program->name)
+ __string(procedure,
+ xdr->rqst->rq_task->tk_msg.rpc_proc->p_name)
),
TP_fast_assign(
@@ -1157,13 +1162,19 @@
__entry->task_id = task->tk_pid;
__entry->client_id = task->tk_client->cl_clid;
__entry->xid = be32_to_cpu(rqstp->rq_xid);
+ __entry->version = task->tk_client->cl_vers;
__entry->error = error;
+ __assign_str(program,
+ task->tk_client->cl_program->name)
+ __assign_str(procedure, task->tk_msg.rpc_proc->p_name)
),
TP_printk(
- "task:%u@%d xid=0x%08x error=%ld (%s)",
+ "task:%u@%d xid=0x%08x %sv%d %s error=%ld (%s)",
__entry->task_id, __entry->client_id, __entry->xid,
- -__entry->error, nfs_show_status(__entry->error)
+ __get_str(program), __entry->version,
+ __get_str(procedure), -__entry->error,
+ nfs_show_status(__entry->error)
)
);
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 20b3717..e3b85bf 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -133,8 +133,43 @@
EXPORT_SYMBOL_GPL(nfs_async_iocounter_wait);
/*
+ * nfs_page_set_headlock - set the request PG_HEADLOCK
+ * @req: request that is to be locked
+ *
+ * this lock must be held when modifying req->wb_head
+ *
+ * return 0 on success, < 0 on error
+ */
+int
+nfs_page_set_headlock(struct nfs_page *req)
+{
+ if (!test_and_set_bit(PG_HEADLOCK, &req->wb_flags))
+ return 0;
+
+ set_bit(PG_CONTENDED1, &req->wb_flags);
+ smp_mb__after_atomic();
+ return wait_on_bit_lock(&req->wb_flags, PG_HEADLOCK,
+ TASK_UNINTERRUPTIBLE);
+}
+
+/*
+ * nfs_page_clear_headlock - clear the request PG_HEADLOCK
+ * @req: request that is to be locked
+ */
+void
+nfs_page_clear_headlock(struct nfs_page *req)
+{
+ smp_mb__before_atomic();
+ clear_bit(PG_HEADLOCK, &req->wb_flags);
+ smp_mb__after_atomic();
+ if (!test_bit(PG_CONTENDED1, &req->wb_flags))
+ return;
+ wake_up_bit(&req->wb_flags, PG_HEADLOCK);
+}
+
+/*
* nfs_page_group_lock - lock the head of the page group
- * @req - request in group that is to be locked
+ * @req: request in group that is to be locked
*
* this lock must be held when traversing or modifying the page
* group list
@@ -144,36 +179,24 @@
int
nfs_page_group_lock(struct nfs_page *req)
{
- struct nfs_page *head = req->wb_head;
+ int ret;
- WARN_ON_ONCE(head != head->wb_head);
-
- if (!test_and_set_bit(PG_HEADLOCK, &head->wb_flags))
- return 0;
-
- set_bit(PG_CONTENDED1, &head->wb_flags);
- smp_mb__after_atomic();
- return wait_on_bit_lock(&head->wb_flags, PG_HEADLOCK,
- TASK_UNINTERRUPTIBLE);
+ ret = nfs_page_set_headlock(req);
+ if (ret || req->wb_head == req)
+ return ret;
+ return nfs_page_set_headlock(req->wb_head);
}
/*
* nfs_page_group_unlock - unlock the head of the page group
- * @req - request in group that is to be unlocked
+ * @req: request in group that is to be unlocked
*/
void
nfs_page_group_unlock(struct nfs_page *req)
{
- struct nfs_page *head = req->wb_head;
-
- WARN_ON_ONCE(head != head->wb_head);
-
- smp_mb__before_atomic();
- clear_bit(PG_HEADLOCK, &head->wb_flags);
- smp_mb__after_atomic();
- if (!test_bit(PG_CONTENDED1, &head->wb_flags))
- return;
- wake_up_bit(&head->wb_flags, PG_HEADLOCK);
+ if (req != req->wb_head)
+ nfs_page_clear_headlock(req->wb_head);
+ nfs_page_clear_headlock(req);
}
/*
@@ -886,15 +909,6 @@
pgio->pg_mirror_count = mirror_count;
}
-/*
- * nfs_pageio_stop_mirroring - stop using mirroring (set mirror count to 1)
- */
-void nfs_pageio_stop_mirroring(struct nfs_pageio_descriptor *pgio)
-{
- pgio->pg_mirror_count = 1;
- pgio->pg_mirror_idx = 0;
-}
-
static void nfs_pageio_cleanup_mirroring(struct nfs_pageio_descriptor *pgio)
{
pgio->pg_mirror_count = 1;
@@ -972,15 +986,16 @@
struct nfs_page *prev = NULL;
- if (mirror->pg_count != 0) {
- prev = nfs_list_entry(mirror->pg_list.prev);
- } else {
+ if (list_empty(&mirror->pg_list)) {
if (desc->pg_ops->pg_init)
desc->pg_ops->pg_init(desc, req);
if (desc->pg_error < 0)
return 0;
mirror->pg_base = req->wb_pgbase;
- }
+ mirror->pg_count = 0;
+ mirror->pg_recoalesce = 0;
+ } else
+ prev = nfs_list_entry(mirror->pg_list.prev);
if (desc->pg_maxretrans && req->wb_nio > desc->pg_maxretrans) {
if (NFS_SERVER(desc->pg_inode)->flags & NFS_MOUNT_SOFTERR)
@@ -1004,17 +1019,16 @@
{
struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
-
if (!list_empty(&mirror->pg_list)) {
int error = desc->pg_ops->pg_doio(desc);
if (error < 0)
desc->pg_error = error;
- else
+ if (list_empty(&mirror->pg_list)) {
mirror->pg_bytes_written += mirror->pg_count;
- }
- if (list_empty(&mirror->pg_list)) {
- mirror->pg_count = 0;
- mirror->pg_base = 0;
+ mirror->pg_count = 0;
+ mirror->pg_base = 0;
+ mirror->pg_recoalesce = 0;
+ }
}
}
@@ -1108,7 +1122,6 @@
do {
list_splice_init(&mirror->pg_list, &head);
- mirror->pg_bytes_written -= mirror->pg_count;
mirror->pg_count = 0;
mirror->pg_base = 0;
mirror->pg_recoalesce = 0;
@@ -1177,38 +1190,38 @@
if (desc->pg_error < 0)
goto out_failed;
- for (midx = 0; midx < desc->pg_mirror_count; midx++) {
- if (midx) {
- nfs_page_group_lock(req);
+ /* Create the mirror instances first, and fire them off */
+ for (midx = 1; midx < desc->pg_mirror_count; midx++) {
+ nfs_page_group_lock(req);
- /* find the last request */
- for (lastreq = req->wb_head;
- lastreq->wb_this_page != req->wb_head;
- lastreq = lastreq->wb_this_page)
- ;
+ /* find the last request */
+ for (lastreq = req->wb_head;
+ lastreq->wb_this_page != req->wb_head;
+ lastreq = lastreq->wb_this_page)
+ ;
- dupreq = nfs_create_subreq(req, lastreq,
- pgbase, offset, bytes);
+ dupreq = nfs_create_subreq(req, lastreq,
+ pgbase, offset, bytes);
- nfs_page_group_unlock(req);
- if (IS_ERR(dupreq)) {
- desc->pg_error = PTR_ERR(dupreq);
- goto out_failed;
- }
- } else
- dupreq = req;
+ nfs_page_group_unlock(req);
+ if (IS_ERR(dupreq)) {
+ desc->pg_error = PTR_ERR(dupreq);
+ goto out_failed;
+ }
- if (nfs_pgio_has_mirroring(desc))
- desc->pg_mirror_idx = midx;
+ desc->pg_mirror_idx = midx;
if (!nfs_pageio_add_request_mirror(desc, dupreq))
goto out_cleanup_subreq;
}
+ desc->pg_mirror_idx = 0;
+ if (!nfs_pageio_add_request_mirror(desc, req))
+ goto out_failed;
+
return 1;
out_cleanup_subreq:
- if (req != dupreq)
- nfs_pageio_cleanup_request(desc, dupreq);
+ nfs_pageio_cleanup_request(desc, dupreq);
out_failed:
nfs_pageio_error_cleanup(desc);
return 0;
@@ -1320,6 +1333,14 @@
}
}
+/*
+ * nfs_pageio_stop_mirroring - stop using mirroring (set mirror count to 1)
+ */
+void nfs_pageio_stop_mirroring(struct nfs_pageio_descriptor *pgio)
+{
+ nfs_pageio_complete(pgio);
+}
+
int __init nfs_init_nfspagecache(void)
{
nfs_page_cachep = kmem_cache_create("nfs_page",
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index bb80034..1b512df 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -294,6 +294,7 @@
pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo)
{
struct inode *inode;
+ unsigned long i_state;
if (!lo)
return;
@@ -304,8 +305,12 @@
if (!list_empty(&lo->plh_segs))
WARN_ONCE(1, "NFS: BUG unfreed layout segments.\n");
pnfs_detach_layout_hdr(lo);
+ i_state = inode->i_state;
spin_unlock(&inode->i_lock);
pnfs_free_layout_hdr(lo);
+ /* Notify pnfs_destroy_layout_final() that we're done */
+ if (i_state & (I_FREEING | I_CLEAR))
+ wake_up_var(lo);
}
}
@@ -723,8 +728,7 @@
}
}
-void
-pnfs_destroy_layout(struct nfs_inode *nfsi)
+static struct pnfs_layout_hdr *__pnfs_destroy_layout(struct nfs_inode *nfsi)
{
struct pnfs_layout_hdr *lo;
LIST_HEAD(tmp_list);
@@ -742,9 +746,34 @@
pnfs_put_layout_hdr(lo);
} else
spin_unlock(&nfsi->vfs_inode.i_lock);
+ return lo;
+}
+
+void pnfs_destroy_layout(struct nfs_inode *nfsi)
+{
+ __pnfs_destroy_layout(nfsi);
}
EXPORT_SYMBOL_GPL(pnfs_destroy_layout);
+static bool pnfs_layout_removed(struct nfs_inode *nfsi,
+ struct pnfs_layout_hdr *lo)
+{
+ bool ret;
+
+ spin_lock(&nfsi->vfs_inode.i_lock);
+ ret = nfsi->layout != lo;
+ spin_unlock(&nfsi->vfs_inode.i_lock);
+ return ret;
+}
+
+void pnfs_destroy_layout_final(struct nfs_inode *nfsi)
+{
+ struct pnfs_layout_hdr *lo = __pnfs_destroy_layout(nfsi);
+
+ if (lo)
+ wait_var_event(lo, pnfs_layout_removed(nfsi, lo));
+}
+
static bool
pnfs_layout_add_bulk_destroy_list(struct inode *inode,
struct list_head *layout_list)
@@ -1198,31 +1227,27 @@
return status;
}
+static bool
+pnfs_layout_segments_returnable(struct pnfs_layout_hdr *lo,
+ enum pnfs_iomode iomode,
+ u32 seq)
+{
+ struct pnfs_layout_range recall_range = {
+ .length = NFS4_MAX_UINT64,
+ .iomode = iomode,
+ };
+ return pnfs_mark_matching_lsegs_return(lo, &lo->plh_return_segs,
+ &recall_range, seq) != -EBUSY;
+}
+
/* Return true if layoutreturn is needed */
static bool
pnfs_layout_need_return(struct pnfs_layout_hdr *lo)
{
- struct pnfs_layout_segment *s;
- enum pnfs_iomode iomode;
- u32 seq;
-
if (!test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags))
return false;
-
- seq = lo->plh_return_seq;
- iomode = lo->plh_return_iomode;
-
- /* Defer layoutreturn until all recalled lsegs are done */
- list_for_each_entry(s, &lo->plh_segs, pls_list) {
- if (seq && pnfs_seqid_is_newer(s->pls_seq, seq))
- continue;
- if (iomode != IOMODE_ANY && s->pls_range.iomode != iomode)
- continue;
- if (test_bit(NFS_LSEG_LAYOUTRETURN, &s->pls_flags))
- return false;
- }
-
- return true;
+ return pnfs_layout_segments_returnable(lo, lo->plh_return_iomode,
+ lo->plh_return_seq);
}
static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo)
@@ -1260,6 +1285,11 @@
{
struct pnfs_layout_hdr *lo = NULL;
struct nfs_inode *nfsi = NFS_I(ino);
+ struct pnfs_layout_range range = {
+ .iomode = IOMODE_ANY,
+ .offset = 0,
+ .length = NFS4_MAX_UINT64,
+ };
LIST_HEAD(tmp_list);
nfs4_stateid stateid;
int status = 0;
@@ -1286,16 +1316,10 @@
}
valid_layout = pnfs_layout_is_valid(lo);
pnfs_clear_layoutcommit(ino, &tmp_list);
- pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL, 0);
+ pnfs_mark_matching_lsegs_return(lo, &tmp_list, &range, 0);
- if (NFS_SERVER(ino)->pnfs_curr_ld->return_range) {
- struct pnfs_layout_range range = {
- .iomode = IOMODE_ANY,
- .offset = 0,
- .length = NFS4_MAX_UINT64,
- };
+ if (NFS_SERVER(ino)->pnfs_curr_ld->return_range)
NFS_SERVER(ino)->pnfs_curr_ld->return_range(lo, &range);
- }
/* Don't send a LAYOUTRETURN if list was initially empty */
if (!test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags) ||
@@ -1425,7 +1449,7 @@
/* lo ref dropped in pnfs_roc_release() */
layoutreturn = pnfs_prepare_layoutreturn(lo, &stateid, &iomode);
/* If the creds don't match, we can't compound the layoutreturn */
- if (!layoutreturn || cred != lo->plh_lc_cred)
+ if (!layoutreturn || cred_fscmp(cred, lo->plh_lc_cred) != 0)
goto out_noroc;
roc = layoutreturn;
@@ -1450,10 +1474,8 @@
return false;
}
-int pnfs_roc_done(struct rpc_task *task, struct inode *inode,
- struct nfs4_layoutreturn_args **argpp,
- struct nfs4_layoutreturn_res **respp,
- int *ret)
+int pnfs_roc_done(struct rpc_task *task, struct nfs4_layoutreturn_args **argpp,
+ struct nfs4_layoutreturn_res **respp, int *ret)
{
struct nfs4_layoutreturn_args *arg = *argpp;
int retval = -EAGAIN;
@@ -1486,7 +1508,7 @@
return 0;
case -NFS4ERR_OLD_STATEID:
if (!nfs4_layout_refresh_old_stateid(&arg->stateid,
- &arg->range, inode))
+ &arg->range, arg->inode))
break;
*ret = -NFS4ERR_NOMATCHING_LAYOUT;
return -EAGAIN;
@@ -1501,12 +1523,18 @@
int ret)
{
struct pnfs_layout_hdr *lo = args->layout;
+ struct inode *inode = args->inode;
const nfs4_stateid *arg_stateid = NULL;
const nfs4_stateid *res_stateid = NULL;
struct nfs4_xdr_opaque_data *ld_private = args->ld_private;
switch (ret) {
case -NFS4ERR_NOMATCHING_LAYOUT:
+ spin_lock(&inode->i_lock);
+ if (pnfs_layout_is_valid(lo) &&
+ nfs4_stateid_match_other(&args->stateid, &lo->plh_stateid))
+ pnfs_set_plh_return_info(lo, args->range.iomode, 0);
+ spin_unlock(&inode->i_lock);
break;
case 0:
if (res->lrs_present)
@@ -1957,6 +1985,27 @@
goto lookup_again;
}
+ /*
+ * Because we free lsegs when sending LAYOUTRETURN, we need to wait
+ * for LAYOUTRETURN.
+ */
+ if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) {
+ spin_unlock(&ino->i_lock);
+ dprintk("%s wait for layoutreturn\n", __func__);
+ lseg = ERR_PTR(pnfs_prepare_to_retry_layoutget(lo));
+ if (!IS_ERR(lseg)) {
+ pnfs_put_layout_hdr(lo);
+ dprintk("%s retrying\n", __func__);
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo,
+ lseg,
+ PNFS_UPDATE_LAYOUT_RETRY);
+ goto lookup_again;
+ }
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
+ PNFS_UPDATE_LAYOUT_RETURN);
+ goto out_put_layout_hdr;
+ }
+
lseg = pnfs_find_lseg(lo, &arg, strict_iomode);
if (lseg) {
trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
@@ -2010,28 +2059,6 @@
nfs4_stateid_copy(&stateid, &lo->plh_stateid);
}
- /*
- * Because we free lsegs before sending LAYOUTRETURN, we need to wait
- * for LAYOUTRETURN even if first is true.
- */
- if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) {
- spin_unlock(&ino->i_lock);
- dprintk("%s wait for layoutreturn\n", __func__);
- lseg = ERR_PTR(pnfs_prepare_to_retry_layoutget(lo));
- if (!IS_ERR(lseg)) {
- if (first)
- pnfs_clear_first_layoutget(lo);
- pnfs_put_layout_hdr(lo);
- dprintk("%s retrying\n", __func__);
- trace_pnfs_update_layout(ino, pos, count, iomode, lo,
- lseg, PNFS_UPDATE_LAYOUT_RETRY);
- goto lookup_again;
- }
- trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
- PNFS_UPDATE_LAYOUT_RETURN);
- goto out_put_layout_hdr;
- }
-
if (pnfs_layoutgets_blocked(lo)) {
trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
PNFS_UPDATE_LAYOUT_BLOCKED);
@@ -2187,6 +2214,7 @@
&rng, GFP_KERNEL);
if (!lgp) {
pnfs_clear_first_layoutget(lo);
+ nfs_layoutget_end(lo);
pnfs_put_layout_hdr(lo);
return;
}
@@ -2340,7 +2368,13 @@
* We got an entirely new state ID. Mark all segments for the
* inode invalid, and retry the layoutget
*/
- pnfs_mark_layout_stateid_invalid(lo, &free_me);
+ struct pnfs_layout_range range = {
+ .iomode = IOMODE_ANY,
+ .length = NFS4_MAX_UINT64,
+ };
+ pnfs_set_plh_return_info(lo, IOMODE_ANY, 0);
+ pnfs_mark_matching_lsegs_return(lo, &lo->plh_return_segs,
+ &range, 0);
goto out_forget;
}
@@ -2359,19 +2393,10 @@
spin_unlock(&ino->i_lock);
lseg->pls_layout = lo;
NFS_SERVER(ino)->pnfs_curr_ld->free_lseg(lseg);
+ pnfs_free_lseg_list(&free_me);
return ERR_PTR(-EAGAIN);
}
-static int
-mark_lseg_invalid_or_return(struct pnfs_layout_segment *lseg,
- struct list_head *tmp_list)
-{
- if (!mark_lseg_invalid(lseg, tmp_list))
- return 0;
- pnfs_cache_lseg_for_layoutreturn(lseg->pls_layout, lseg);
- return 1;
-}
-
/**
* pnfs_mark_matching_lsegs_return - Free or return matching layout segments
* @lo: pointer to layout header
@@ -2401,6 +2426,9 @@
assert_spin_locked(&lo->plh_inode->i_lock);
+ if (test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags))
+ tmp_list = &lo->plh_return_segs;
+
list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list)
if (pnfs_match_lseg_recall(lseg, return_range, seq)) {
dprintk("%s: marking lseg %p iomode %d "
@@ -2408,7 +2436,9 @@
lseg, lseg->pls_range.iomode,
lseg->pls_range.offset,
lseg->pls_range.length);
- if (mark_lseg_invalid_or_return(lseg, tmp_list))
+ if (test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags))
+ tmp_list = &lo->plh_return_segs;
+ if (mark_lseg_invalid(lseg, tmp_list))
continue;
remaining++;
set_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags);
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index f8a3806..3d55edd 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -255,6 +255,7 @@
void pnfs_layoutget_free(struct nfs4_layoutget *lgp);
void pnfs_free_lseg_list(struct list_head *tmp_list);
void pnfs_destroy_layout(struct nfs_inode *);
+void pnfs_destroy_layout_final(struct nfs_inode *);
void pnfs_destroy_all_layouts(struct nfs_client *);
int pnfs_destroy_layouts_byfsid(struct nfs_client *clp,
struct nfs_fsid *fsid,
@@ -282,10 +283,8 @@
struct nfs4_layoutreturn_args *args,
struct nfs4_layoutreturn_res *res,
const struct cred *cred);
-int pnfs_roc_done(struct rpc_task *task, struct inode *inode,
- struct nfs4_layoutreturn_args **argpp,
- struct nfs4_layoutreturn_res **respp,
- int *ret);
+int pnfs_roc_done(struct rpc_task *task, struct nfs4_layoutreturn_args **argpp,
+ struct nfs4_layoutreturn_res **respp, int *ret);
void pnfs_roc_release(struct nfs4_layoutreturn_args *args,
struct nfs4_layoutreturn_res *res,
int ret);
@@ -651,6 +650,10 @@
{
}
+static inline void pnfs_destroy_layout_final(struct nfs_inode *nfsi)
+{
+}
+
static inline struct pnfs_layout_segment *
pnfs_get_lseg(struct pnfs_layout_segment *lseg)
{
@@ -706,7 +709,7 @@
}
static inline int
-pnfs_roc_done(struct rpc_task *task, struct inode *inode,
+pnfs_roc_done(struct rpc_task *task,
struct nfs4_layoutreturn_args **argpp,
struct nfs4_layoutreturn_res **respp,
int *ret)
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index 82af480..249cf90 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -31,12 +31,11 @@
/* Fake up some data that will cause nfs_commit_release to retry the writes. */
void pnfs_generic_prepare_to_resend_writes(struct nfs_commit_data *data)
{
- struct nfs_page *first = nfs_list_entry(data->pages.next);
+ struct nfs_writeverf *verf = data->res.verf;
data->task.tk_status = 0;
- memcpy(&data->verf.verifier, &first->wb_verf,
- sizeof(data->verf.verifier));
- data->verf.verifier.data[0]++; /* ensure verifier mismatch */
+ memset(&verf->verifier, 0, sizeof(verf->verifier));
+ verf->committed = NFS_UNSTABLE;
}
EXPORT_SYMBOL_GPL(pnfs_generic_prepare_to_resend_writes);
@@ -557,19 +556,16 @@
}
EXPORT_SYMBOL_GPL(nfs4_pnfs_ds_add);
-static void nfs4_wait_ds_connect(struct nfs4_pnfs_ds *ds)
+static int nfs4_wait_ds_connect(struct nfs4_pnfs_ds *ds)
{
might_sleep();
- wait_on_bit(&ds->ds_state, NFS4DS_CONNECTING,
- TASK_KILLABLE);
+ return wait_on_bit(&ds->ds_state, NFS4DS_CONNECTING, TASK_KILLABLE);
}
static void nfs4_clear_ds_conn_bit(struct nfs4_pnfs_ds *ds)
{
smp_mb__before_atomic();
- clear_bit(NFS4DS_CONNECTING, &ds->ds_state);
- smp_mb__after_atomic();
- wake_up_bit(&ds->ds_state, NFS4DS_CONNECTING);
+ clear_and_wake_up_bit(NFS4DS_CONNECTING, &ds->ds_state);
}
static struct nfs_client *(*get_v3_ds_connect)(
@@ -735,30 +731,33 @@
{
int err;
-again:
- err = 0;
- if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) {
- if (version == 3) {
- err = _nfs4_pnfs_v3_ds_connect(mds_srv, ds, timeo,
- retrans);
- } else if (version == 4) {
- err = _nfs4_pnfs_v4_ds_connect(mds_srv, ds, timeo,
- retrans, minor_version);
- } else {
- dprintk("%s: unsupported DS version %d\n", __func__,
- version);
- err = -EPROTONOSUPPORT;
- }
+ do {
+ err = nfs4_wait_ds_connect(ds);
+ if (err || ds->ds_clp)
+ goto out;
+ if (nfs4_test_deviceid_unavailable(devid))
+ return -ENODEV;
+ } while (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) != 0);
- nfs4_clear_ds_conn_bit(ds);
- } else {
- nfs4_wait_ds_connect(ds);
+ if (ds->ds_clp)
+ goto connect_done;
- /* what was waited on didn't connect AND didn't mark unavail */
- if (!ds->ds_clp && !nfs4_test_deviceid_unavailable(devid))
- goto again;
+ switch (version) {
+ case 3:
+ err = _nfs4_pnfs_v3_ds_connect(mds_srv, ds, timeo, retrans);
+ break;
+ case 4:
+ err = _nfs4_pnfs_v4_ds_connect(mds_srv, ds, timeo, retrans,
+ minor_version);
+ break;
+ default:
+ dprintk("%s: unsupported DS version %d\n", __func__, version);
+ err = -EPROTONOSUPPORT;
}
+connect_done:
+ nfs4_clear_ds_conn_bit(ds);
+out:
/*
* At this point the ds->ds_clp should be ready, but it might have
* hit an error.
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 52cab65..613c3ef 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -243,7 +243,15 @@
/* A writeback failed: mark the page as bad, and invalidate the page cache */
static void nfs_set_pageerror(struct address_space *mapping)
{
+ struct inode *inode = mapping->host;
+
nfs_zap_mapping(mapping->host, mapping);
+ /* Force file size revalidation */
+ spin_lock(&inode->i_lock);
+ NFS_I(inode)->cache_validity |= NFS_INO_REVAL_FORCED |
+ NFS_INO_REVAL_PAGECACHE |
+ NFS_INO_INVALID_SIZE;
+ spin_unlock(&inode->i_lock);
}
static void nfs_mapping_set_error(struct page *page, int error)
@@ -417,22 +425,29 @@
destroy_list = (subreq->wb_this_page == old_head) ?
NULL : subreq->wb_this_page;
+ /* Note: lock subreq in order to change subreq->wb_head */
+ nfs_page_set_headlock(subreq);
WARN_ON_ONCE(old_head != subreq->wb_head);
/* make sure old group is not used */
subreq->wb_this_page = subreq;
+ subreq->wb_head = subreq;
clear_bit(PG_REMOVE, &subreq->wb_flags);
/* Note: races with nfs_page_group_destroy() */
if (!kref_read(&subreq->wb_kref)) {
/* Check if we raced with nfs_page_group_destroy() */
- if (test_and_clear_bit(PG_TEARDOWN, &subreq->wb_flags))
+ if (test_and_clear_bit(PG_TEARDOWN, &subreq->wb_flags)) {
+ nfs_page_clear_headlock(subreq);
nfs_free_request(subreq);
+ } else
+ nfs_page_clear_headlock(subreq);
continue;
}
+ nfs_page_clear_headlock(subreq);
- subreq->wb_head = subreq;
+ nfs_release_request(old_head);
if (test_and_clear_bit(PG_INODE_REF, &subreq->wb_flags)) {
nfs_release_request(subreq);
@@ -1829,6 +1844,7 @@
static void nfs_commit_release_pages(struct nfs_commit_data *data)
{
+ const struct nfs_writeverf *verf = data->res.verf;
struct nfs_page *req;
int status = data->task.tk_status;
struct nfs_commit_info cinfo;
@@ -1856,7 +1872,8 @@
/* Okay, COMMIT succeeded, apparently. Check the verifier
* returned by the server against all stored verfs. */
- if (!nfs_write_verifier_cmp(&req->wb_verf, &data->verf.verifier)) {
+ if (verf->committed > NFS_UNSTABLE &&
+ !nfs_write_verifier_cmp(&req->wb_verf, &verf->verifier)) {
/* We have a match */
if (req->wb_page)
nfs_inode_remove_request(req);