Update Linux to v5.10.157
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.157.tar.xz
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
Change-Id: I7b30d9e98d8c465d6b44de8e7433b4a40b3289ba
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index b44219c..bfdd212 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -283,6 +283,7 @@
rv = NFS4_OK;
break;
case -ENOENT:
+ set_bit(NFS_LAYOUT_DRAIN, &lo->plh_flags);
/* Embrace your forgetfulness! */
rv = NFS4ERR_NOMATCHING_LAYOUT;
@@ -353,12 +354,11 @@
struct cb_process_state *cps)
{
struct cb_devicenotifyargs *args = argp;
+ const struct pnfs_layoutdriver_type *ld = NULL;
uint32_t i;
__be32 res = 0;
- struct nfs_client *clp = cps->clp;
- struct nfs_server *server = NULL;
- if (!clp) {
+ if (!cps->clp) {
res = cpu_to_be32(NFS4ERR_OP_NOT_IN_SESSION);
goto out;
}
@@ -366,23 +366,15 @@
for (i = 0; i < args->ndevs; i++) {
struct cb_devicenotifyitem *dev = &args->devs[i];
- if (!server ||
- server->pnfs_curr_ld->id != dev->cbd_layout_type) {
- rcu_read_lock();
- list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link)
- if (server->pnfs_curr_ld &&
- server->pnfs_curr_ld->id == dev->cbd_layout_type) {
- rcu_read_unlock();
- goto found;
- }
- rcu_read_unlock();
- continue;
+ if (!ld || ld->id != dev->cbd_layout_type) {
+ pnfs_put_layoutdriver(ld);
+ ld = pnfs_find_layoutdriver(dev->cbd_layout_type);
+ if (!ld)
+ continue;
}
-
- found:
- nfs4_delete_deviceid(server->pnfs_curr_ld, clp, &dev->cbd_dev_id);
+ nfs4_delete_deviceid(ld, cps->clp, &dev->cbd_dev_id);
}
-
+ pnfs_put_layoutdriver(ld);
out:
kfree(args->devs);
return res;
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 1725079..ca8a4aa 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -272,10 +272,6 @@
n = ntohl(*p++);
if (n == 0)
goto out;
- if (n > ULONG_MAX / sizeof(*args->devs)) {
- status = htonl(NFS4ERR_BADXDR);
- goto out;
- }
args->devs = kmalloc_array(n, sizeof(*args->devs), GFP_KERNEL);
if (!args->devs) {
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index d6ac2c4..1eb6c7a 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -228,8 +228,7 @@
*
*/
void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred,
- fmode_t type,
- const nfs4_stateid *stateid,
+ fmode_t type, const nfs4_stateid *stateid,
unsigned long pagemod_limit)
{
struct nfs_delegation *delegation;
@@ -239,25 +238,24 @@
delegation = rcu_dereference(NFS_I(inode)->delegation);
if (delegation != NULL) {
spin_lock(&delegation->lock);
- if (nfs4_is_valid_delegation(delegation, 0)) {
- nfs4_stateid_copy(&delegation->stateid, stateid);
- delegation->type = type;
- delegation->pagemod_limit = pagemod_limit;
- oldcred = delegation->cred;
- delegation->cred = get_cred(cred);
- clear_bit(NFS_DELEGATION_NEED_RECLAIM,
- &delegation->flags);
- spin_unlock(&delegation->lock);
- rcu_read_unlock();
- put_cred(oldcred);
- trace_nfs4_reclaim_delegation(inode, type);
- return;
- }
- /* We appear to have raced with a delegation return. */
+ nfs4_stateid_copy(&delegation->stateid, stateid);
+ delegation->type = type;
+ delegation->pagemod_limit = pagemod_limit;
+ oldcred = delegation->cred;
+ delegation->cred = get_cred(cred);
+ clear_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags);
+ if (test_and_clear_bit(NFS_DELEGATION_REVOKED,
+ &delegation->flags))
+ atomic_long_inc(&nfs_active_delegations);
spin_unlock(&delegation->lock);
+ rcu_read_unlock();
+ put_cred(oldcred);
+ trace_nfs4_reclaim_delegation(inode, type);
+ } else {
+ rcu_read_unlock();
+ nfs_inode_set_delegation(inode, cred, type, stateid,
+ pagemod_limit);
}
- rcu_read_unlock();
- nfs_inode_set_delegation(inode, cred, type, stateid, pagemod_limit);
}
static int nfs_do_return_delegation(struct inode *inode, struct nfs_delegation *delegation, int issync)
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 2ad56ff..9f88ca7 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1628,16 +1628,6 @@
};
EXPORT_SYMBOL_GPL(nfs4_dentry_operations);
-static fmode_t flags_to_mode(int flags)
-{
- fmode_t res = (__force fmode_t)flags & FMODE_EXEC;
- if ((flags & O_ACCMODE) != O_WRONLY)
- res |= FMODE_READ;
- if ((flags & O_ACCMODE) != O_RDONLY)
- res |= FMODE_WRITE;
- return res;
-}
-
static struct nfs_open_context *create_nfs_open_context(struct dentry *dentry, int open_flags, struct file *filp)
{
return alloc_nfs_open_context(dentry, flags_to_mode(open_flags), filp);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 3c0335c..c220810 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -172,8 +172,8 @@
VM_BUG_ON(iov_iter_count(iter) != PAGE_SIZE);
if (iov_iter_rw(iter) == READ)
- return nfs_file_direct_read(iocb, iter);
- return nfs_file_direct_write(iocb, iter);
+ return nfs_file_direct_read(iocb, iter, true);
+ return nfs_file_direct_write(iocb, iter, true);
}
static void nfs_direct_release_pages(struct page **pages, unsigned int npages)
@@ -424,6 +424,7 @@
* nfs_file_direct_read - file direct read operation for NFS files
* @iocb: target I/O control block
* @iter: vector of user buffers into which to read data
+ * @swap: flag indicating this is swap IO, not O_DIRECT IO
*
* We use this function for direct reads instead of calling
* generic_file_aio_read() in order to avoid gfar's check to see if
@@ -439,7 +440,8 @@
* client must read the updated atime from the server back into its
* cache.
*/
-ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter)
+ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
+ bool swap)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
@@ -481,12 +483,14 @@
if (iter_is_iovec(iter))
dreq->flags = NFS_ODIRECT_SHOULD_DIRTY;
- nfs_start_io_direct(inode);
+ if (!swap)
+ nfs_start_io_direct(inode);
NFS_I(inode)->read_io += count;
requested = nfs_direct_read_schedule_iovec(dreq, iter, iocb->ki_pos);
- nfs_end_io_direct(inode);
+ if (!swap)
+ nfs_end_io_direct(inode);
if (requested > 0) {
result = nfs_direct_wait(dreq);
@@ -789,7 +793,7 @@
*/
static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
struct iov_iter *iter,
- loff_t pos)
+ loff_t pos, int ioflags)
{
struct nfs_pageio_descriptor desc;
struct inode *inode = dreq->inode;
@@ -797,7 +801,7 @@
size_t requested_bytes = 0;
size_t wsize = max_t(size_t, NFS_SERVER(inode)->wsize, PAGE_SIZE);
- nfs_pageio_init_write(&desc, inode, FLUSH_COND_STABLE, false,
+ nfs_pageio_init_write(&desc, inode, ioflags, false,
&nfs_direct_write_completion_ops);
desc.pg_dreq = dreq;
get_dreq(dreq);
@@ -875,6 +879,7 @@
* nfs_file_direct_write - file direct write operation for NFS files
* @iocb: target I/O control block
* @iter: vector of user buffers from which to write data
+ * @swap: flag indicating this is swap IO, not O_DIRECT IO
*
* We use this function for direct writes instead of calling
* generic_file_aio_write() in order to avoid taking the inode
@@ -891,7 +896,8 @@
* Note that O_APPEND is not supported for NFS direct writes, as there
* is no atomic O_APPEND write facility in the NFS protocol.
*/
-ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
+ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter,
+ bool swap)
{
ssize_t result, requested;
size_t count;
@@ -905,7 +911,11 @@
dfprintk(FILE, "NFS: direct write(%pD2, %zd@%Ld)\n",
file, iov_iter_count(iter), (long long) iocb->ki_pos);
- result = generic_write_checks(iocb, iter);
+ if (swap)
+ /* bypass generic checks */
+ result = iov_iter_count(iter);
+ else
+ result = generic_write_checks(iocb, iter);
if (result <= 0)
return result;
count = result;
@@ -936,17 +946,23 @@
dreq->iocb = iocb;
pnfs_init_ds_commit_info_ops(&dreq->ds_cinfo, inode);
- nfs_start_io_direct(inode);
+ if (swap) {
+ requested = nfs_direct_write_schedule_iovec(dreq, iter, pos,
+ FLUSH_STABLE);
+ } else {
+ nfs_start_io_direct(inode);
- requested = nfs_direct_write_schedule_iovec(dreq, iter, pos);
+ requested = nfs_direct_write_schedule_iovec(dreq, iter, pos,
+ FLUSH_COND_STABLE);
- if (mapping->nrpages) {
- invalidate_inode_pages2_range(mapping,
- pos >> PAGE_SHIFT, end);
+ if (mapping->nrpages) {
+ invalidate_inode_pages2_range(mapping,
+ pos >> PAGE_SHIFT, end);
+ }
+
+ nfs_end_io_direct(inode);
}
- nfs_end_io_direct(inode);
-
if (requested > 0) {
result = nfs_direct_wait(dreq);
if (result > 0) {
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 63940a7..ad856b7 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -161,7 +161,7 @@
ssize_t result;
if (iocb->ki_flags & IOCB_DIRECT)
- return nfs_file_direct_read(iocb, to);
+ return nfs_file_direct_read(iocb, to, false);
dprintk("NFS: read(%pD2, %zu@%lu)\n",
iocb->ki_filp,
@@ -208,15 +208,16 @@
nfs_file_fsync_commit(struct file *file, int datasync)
{
struct inode *inode = file_inode(file);
- int ret;
+ int ret, ret2;
dprintk("NFS: fsync file(%pD2) datasync %d\n", file, datasync);
nfs_inc_stats(inode, NFSIOS_VFSFSYNC);
ret = nfs_commit_inode(inode, FLUSH_SYNC);
- if (ret < 0)
- return ret;
- return file_check_and_advance_wb_err(file);
+ ret2 = file_check_and_advance_wb_err(file);
+ if (ret2 < 0)
+ return ret2;
+ return ret;
}
int
@@ -389,11 +390,8 @@
return status;
NFS_I(mapping->host)->write_io += copied;
- if (nfs_ctx_key_to_expire(ctx, mapping->host)) {
- status = nfs_wb_all(mapping->host);
- if (status < 0)
- return status;
- }
+ if (nfs_ctx_key_to_expire(ctx, mapping->host))
+ nfs_wb_all(mapping->host);
return copied;
}
@@ -616,7 +614,7 @@
return result;
if (iocb->ki_flags & IOCB_DIRECT)
- return nfs_file_direct_write(iocb, from);
+ return nfs_file_direct_write(iocb, from, false);
dprintk("NFS: write(%pD2, %zu@%Ld)\n",
file, iov_iter_count(from), (long long) iocb->ki_pos);
diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c
index 05b39e8..d60c086 100644
--- a/fs/nfs/fs_context.c
+++ b/fs/nfs/fs_context.c
@@ -476,7 +476,7 @@
if (result.negated)
ctx->flags &= ~NFS_MOUNT_SOFTREVAL;
else
- ctx->flags &= NFS_MOUNT_SOFTREVAL;
+ ctx->flags |= NFS_MOUNT_SOFTREVAL;
break;
case Opt_posix:
if (result.negated)
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index f27ecc2..1adece1 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -1139,7 +1139,6 @@
nfs_fscache_open_file(inode, filp);
return 0;
}
-EXPORT_SYMBOL_GPL(nfs_open);
/*
* This function is called whenever some part of NFS notices that
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 98554dd..a7e0970 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -42,6 +42,16 @@
return true;
}
+static inline fmode_t flags_to_mode(int flags)
+{
+ fmode_t res = (__force fmode_t)flags & FMODE_EXEC;
+ if ((flags & O_ACCMODE) != O_WRONLY)
+ res |= FMODE_READ;
+ if ((flags & O_ACCMODE) != O_RDONLY)
+ res |= FMODE_WRITE;
+ return res;
+}
+
/*
* Note: RFC 1813 doesn't limit the number of auth flavors that
* a server can return, so make something up.
@@ -578,6 +588,13 @@
!nfs_write_verifier_cmp(&req->wb_verf, &verf->verifier);
}
+static inline gfp_t nfs_io_gfp_mask(void)
+{
+ if (current->flags & PF_WQ_WORKER)
+ return GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN;
+ return GFP_KERNEL;
+}
+
/* unlink.c */
extern struct rpc_task *
nfs_async_rename(struct inode *old_dir, struct inode *new_dir,
@@ -815,6 +832,7 @@
case 0:
case -ERESTARTSYS:
case -EINTR:
+ case -ENOMEM:
return false;
}
return nfs_error_is_fatal(err);
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index f6676af..5e6453e 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -948,7 +948,7 @@
error = decode_filename_inline(xdr, &entry->name, &entry->len);
if (unlikely(error))
- return error;
+ return -EAGAIN;
/*
* The type (size and byte order) of nfscookie isn't defined in
diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c
index 5601e47..b49359a 100644
--- a/fs/nfs/nfs3client.c
+++ b/fs/nfs/nfs3client.c
@@ -108,7 +108,6 @@
if (mds_srv->flags & NFS_MOUNT_NORESVPORT)
__set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
- __set_bit(NFS_CS_NOPING, &cl_init.init_flags);
__set_bit(NFS_CS_DS, &cl_init.init_flags);
/* Use the MDS nfs_client cl_ipaddr. */
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index dff6b52..b5a9379 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -1964,7 +1964,6 @@
bool plus)
{
struct user_namespace *userns = rpc_userns(entry->server->client);
- struct nfs_entry old = *entry;
__be32 *p;
int error;
u64 new_cookie;
@@ -1984,15 +1983,15 @@
error = decode_fileid3(xdr, &entry->ino);
if (unlikely(error))
- return error;
+ return -EAGAIN;
error = decode_inline_filename3(xdr, &entry->name, &entry->len);
if (unlikely(error))
- return error;
+ return -EAGAIN;
error = decode_cookie3(xdr, &new_cookie);
if (unlikely(error))
- return error;
+ return -EAGAIN;
entry->d_type = DT_UNKNOWN;
@@ -2000,7 +1999,7 @@
entry->fattr->valid = 0;
error = decode_post_op_attr(xdr, entry->fattr, userns);
if (unlikely(error))
- return error;
+ return -EAGAIN;
if (entry->fattr->valid & NFS_ATTR_FATTR_V3)
entry->d_type = nfs_umode_to_dtype(entry->fattr->mode);
@@ -2015,11 +2014,8 @@
return -EAGAIN;
if (*p != xdr_zero) {
error = decode_nfs_fh3(xdr, entry->fh);
- if (unlikely(error)) {
- if (error == -E2BIG)
- goto out_truncated;
- return error;
- }
+ if (unlikely(error))
+ return -EAGAIN;
} else
zero_nfs_fh3(entry->fh);
}
@@ -2028,11 +2024,6 @@
entry->cookie = new_cookie;
return 0;
-
-out_truncated:
- dprintk("NFS: directory entry contains invalid file handle\n");
- *entry = old;
- return -EAGAIN;
}
/*
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 2587b1b..dad32b1 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -567,8 +567,10 @@
ctx = get_nfs_open_context(nfs_file_open_context(src));
l_ctx = nfs_get_lock_context(ctx);
- if (IS_ERR(l_ctx))
- return PTR_ERR(l_ctx);
+ if (IS_ERR(l_ctx)) {
+ status = PTR_ERR(l_ctx);
+ goto out;
+ }
status = nfs4_set_rw_stateid(&args->cna_src_stateid, ctx, l_ctx,
FMODE_READ);
@@ -576,7 +578,7 @@
if (status) {
if (status == -EAGAIN)
status = -NFS4ERR_BAD_STATEID;
- return status;
+ goto out;
}
status = nfs4_call_sync(src_server->client, src_server, &msg,
@@ -584,6 +586,7 @@
if (status == -ENOTSUPP)
src_server->caps &= ~NFS_CAP_COPY_NOTIFY;
+out:
put_nfs_open_context(nfs_file_open_context(src));
return status;
}
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 0e6437b..252c99c 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -346,6 +346,7 @@
ret = nfs4_setup_slot_table(tbl, NFS4_MAX_SLOT_TABLE,
"NFSv4.0 transport Slot table");
if (ret) {
+ nfs4_shutdown_slot_table(tbl);
kfree(tbl);
return ret;
}
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index a1e5c6b..70cd0d7 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -32,6 +32,7 @@
struct dentry *parent = NULL;
struct inode *dir;
unsigned openflags = filp->f_flags;
+ fmode_t f_mode;
struct iattr attr;
int err;
@@ -50,8 +51,9 @@
if (err)
return err;
+ f_mode = filp->f_mode;
if ((openflags & O_ACCMODE) == 3)
- return nfs_open(inode, filp);
+ f_mode |= flags_to_mode(openflags);
/* We can't create new files here */
openflags &= ~(O_CREAT|O_EXCL);
@@ -59,7 +61,7 @@
parent = dget_parent(dentry);
dir = d_inode(parent);
- ctx = alloc_nfs_open_context(file_dentry(filp), filp->f_mode, filp);
+ ctx = alloc_nfs_open_context(file_dentry(filp), f_mode, filp);
err = PTR_ERR(ctx);
if (IS_ERR(ctx))
goto out;
@@ -319,7 +321,7 @@
static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt,
struct nfs_fh *src_fh, nfs4_stateid *stateid)
{
- struct nfs_fattr fattr;
+ struct nfs_fattr *fattr = nfs_alloc_fattr();
struct file *filep, *res;
struct nfs_server *server;
struct inode *r_ino = NULL;
@@ -330,14 +332,20 @@
server = NFS_SERVER(ss_mnt->mnt_root->d_inode);
- nfs_fattr_init(&fattr);
+ if (!fattr)
+ return ERR_PTR(-ENOMEM);
- status = nfs4_proc_getattr(server, src_fh, &fattr, NULL, NULL);
+ status = nfs4_proc_getattr(server, src_fh, fattr, NULL, NULL);
if (status < 0) {
res = ERR_PTR(status);
goto out;
}
+ if (!S_ISREG(fattr->mode)) {
+ res = ERR_PTR(-EBADF);
+ goto out;
+ }
+
res = ERR_PTR(-ENOMEM);
len = strlen(SSC_READ_NAME_BODY) + 16;
read_name = kzalloc(len, GFP_NOFS);
@@ -345,7 +353,7 @@
goto out;
snprintf(read_name, len, SSC_READ_NAME_BODY, read_name_gen++);
- r_ino = nfs_fhget(ss_mnt->mnt_root->d_inode->i_sb, src_fh, &fattr,
+ r_ino = nfs_fhget(ss_mnt->mnt_root->d_inode->i_sb, src_fh, fattr,
NULL);
if (IS_ERR(r_ino)) {
res = ERR_CAST(r_ino);
@@ -356,6 +364,7 @@
r_ino->i_fop);
if (IS_ERR(filep)) {
res = ERR_CAST(filep);
+ iput(r_ino);
goto out_free_name;
}
filep->f_mode |= FMODE_READ;
@@ -390,6 +399,7 @@
out_free_name:
kfree(read_name);
out:
+ nfs_free_fattr(fattr);
return res;
out_stateowner:
nfs4_put_state_owner(sp);
diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c
index f331866..ec6afd3 100644
--- a/fs/nfs/nfs4idmap.c
+++ b/fs/nfs/nfs4idmap.c
@@ -561,22 +561,20 @@
return true;
}
-static void
-nfs_idmap_complete_pipe_upcall_locked(struct idmap *idmap, int ret)
+static void nfs_idmap_complete_pipe_upcall(struct idmap_legacy_upcalldata *data,
+ int ret)
{
- struct key *authkey = idmap->idmap_upcall_data->authkey;
-
- kfree(idmap->idmap_upcall_data);
- idmap->idmap_upcall_data = NULL;
- complete_request_key(authkey, ret);
- key_put(authkey);
+ complete_request_key(data->authkey, ret);
+ key_put(data->authkey);
+ kfree(data);
}
-static void
-nfs_idmap_abort_pipe_upcall(struct idmap *idmap, int ret)
+static void nfs_idmap_abort_pipe_upcall(struct idmap *idmap,
+ struct idmap_legacy_upcalldata *data,
+ int ret)
{
- if (idmap->idmap_upcall_data != NULL)
- nfs_idmap_complete_pipe_upcall_locked(idmap, ret);
+ if (cmpxchg(&idmap->idmap_upcall_data, data, NULL) == data)
+ nfs_idmap_complete_pipe_upcall(data, ret);
}
static int nfs_idmap_legacy_upcall(struct key *authkey, void *aux)
@@ -613,7 +611,7 @@
ret = rpc_queue_upcall(idmap->idmap_pipe, msg);
if (ret < 0)
- nfs_idmap_abort_pipe_upcall(idmap, ret);
+ nfs_idmap_abort_pipe_upcall(idmap, data, ret);
return ret;
out2:
@@ -669,6 +667,7 @@
struct request_key_auth *rka;
struct rpc_inode *rpci = RPC_I(file_inode(filp));
struct idmap *idmap = (struct idmap *)rpci->private;
+ struct idmap_legacy_upcalldata *data;
struct key *authkey;
struct idmap_msg im;
size_t namelen_in;
@@ -678,10 +677,11 @@
* will have been woken up and someone else may now have used
* idmap_key_cons - so after this point we may no longer touch it.
*/
- if (idmap->idmap_upcall_data == NULL)
+ data = xchg(&idmap->idmap_upcall_data, NULL);
+ if (data == NULL)
goto out_noupcall;
- authkey = idmap->idmap_upcall_data->authkey;
+ authkey = data->authkey;
rka = get_request_key_auth(authkey);
if (mlen != sizeof(im)) {
@@ -703,18 +703,17 @@
if (namelen_in == 0 || namelen_in == IDMAP_NAMESZ) {
ret = -EINVAL;
goto out;
-}
+ }
- ret = nfs_idmap_read_and_verify_message(&im,
- &idmap->idmap_upcall_data->idmap_msg,
- rka->target_key, authkey);
+ ret = nfs_idmap_read_and_verify_message(&im, &data->idmap_msg,
+ rka->target_key, authkey);
if (ret >= 0) {
key_set_timeout(rka->target_key, nfs_idmap_cache_timeout);
ret = mlen;
}
out:
- nfs_idmap_complete_pipe_upcall_locked(idmap, ret);
+ nfs_idmap_complete_pipe_upcall(data, ret);
out_noupcall:
return ret;
}
@@ -728,7 +727,7 @@
struct idmap *idmap = data->idmap;
if (msg->errno)
- nfs_idmap_abort_pipe_upcall(idmap, msg->errno);
+ nfs_idmap_abort_pipe_upcall(idmap, data, msg->errno);
}
static void
@@ -736,8 +735,11 @@
{
struct rpc_inode *rpci = RPC_I(inode);
struct idmap *idmap = (struct idmap *)rpci->private;
+ struct idmap_legacy_upcalldata *data;
- nfs_idmap_abort_pipe_upcall(idmap, -EPIPE);
+ data = xchg(&idmap->idmap_upcall_data, NULL);
+ if (data)
+ nfs_idmap_complete_pipe_upcall(data, -EPIPE);
}
int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_t namelen, kuid_t *uid)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index d222a98..36af373 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -369,6 +369,14 @@
kunmap_atomic(start);
}
+static void nfs4_fattr_set_prechange(struct nfs_fattr *fattr, u64 version)
+{
+ if (!(fattr->valid & NFS_ATTR_FATTR_PRECHANGE)) {
+ fattr->pre_change_attr = version;
+ fattr->valid |= NFS_ATTR_FATTR_PRECHANGE;
+ }
+}
+
static void nfs4_test_and_free_stateid(struct nfs_server *server,
nfs4_stateid *stateid,
const struct cred *cred)
@@ -782,10 +790,9 @@
if ((s32)(seqnr - slot->seq_nr_highest_sent) > 0)
slot->seq_nr_highest_sent = seqnr;
}
-static void nfs4_slot_sequence_acked(struct nfs4_slot *slot,
- u32 seqnr)
+static void nfs4_slot_sequence_acked(struct nfs4_slot *slot, u32 seqnr)
{
- slot->seq_nr_highest_sent = seqnr;
+ nfs4_slot_sequence_record_sent(slot, seqnr);
slot->seq_nr_last_acked = seqnr;
}
@@ -852,7 +859,6 @@
__func__,
slot->slot_nr,
slot->seq_nr);
- nfs4_slot_sequence_acked(slot, slot->seq_nr);
goto out_retry;
case -NFS4ERR_RETRY_UNCACHED_REP:
case -NFS4ERR_SEQ_FALSE_RETRY:
@@ -3078,8 +3084,13 @@
}
out:
- if (!opendata->cancelled)
+ if (!opendata->cancelled) {
+ if (opendata->lgp) {
+ nfs4_lgopen_release(opendata->lgp);
+ opendata->lgp = NULL;
+ }
nfs4_sequence_free_slot(&opendata->o_res.seq_res);
+ }
return ret;
}
@@ -6464,7 +6475,9 @@
pnfs_roc_release(&data->lr.arg, &data->lr.res,
data->res.lr_ret);
if (inode) {
- nfs_post_op_update_inode_force_wcc(inode, &data->fattr);
+ nfs4_fattr_set_prechange(&data->fattr,
+ inode_peek_iversion_raw(inode));
+ nfs_refresh_inode(inode, &data->fattr);
nfs_iput_and_deactive(inode);
}
kfree(calldata);
@@ -7001,6 +7014,7 @@
{
struct nfs4_lockdata *data = calldata;
struct nfs4_lock_state *lsp = data->lsp;
+ struct nfs_server *server = NFS_SERVER(d_inode(data->ctx->dentry));
dprintk("%s: begin!\n", __func__);
@@ -7010,8 +7024,7 @@
data->rpc_status = task->tk_status;
switch (task->tk_status) {
case 0:
- renew_lease(NFS_SERVER(d_inode(data->ctx->dentry)),
- data->timestamp);
+ renew_lease(server, data->timestamp);
if (data->arg.new_lock && !data->cancelled) {
data->fl.fl_flags &= ~(FL_SLEEP | FL_ACCESS);
if (locks_lock_inode_wait(lsp->ls_state->inode, &data->fl) < 0)
@@ -7032,6 +7045,8 @@
if (!nfs4_stateid_match(&data->arg.open_stateid,
&lsp->ls_state->open_stateid))
goto out_restart;
+ else if (nfs4_async_handle_error(task, server, lsp->ls_state, NULL) == -EAGAIN)
+ goto out_restart;
} else if (!nfs4_stateid_match(&data->arg.lock_stateid,
&lsp->ls_stateid))
goto out_restart;
@@ -8205,6 +8220,7 @@
case -NFS4ERR_DEADSESSION:
nfs4_schedule_session_recovery(clp->cl_session,
task->tk_status);
+ return;
}
if (args->dir == NFS4_CDFC4_FORE_OR_BOTH &&
res->dir != NFS4_CDFS4_BOTH) {
@@ -9260,6 +9276,9 @@
rpc_delay(task, NFS4_POLL_RETRY_MAX);
fallthrough;
case -NFS4ERR_RETRY_UNCACHED_REP:
+ case -EACCES:
+ dprintk("%s: failed to reclaim complete error %d for server %s, retrying\n",
+ __func__, task->tk_status, clp->cl_hostname);
return -EAGAIN;
case -NFS4ERR_BADSESSION:
case -NFS4ERR_DEADSESSION:
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index cbeec29..a77a3d8 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -49,6 +49,7 @@
#include <linux/workqueue.h>
#include <linux/bitops.h>
#include <linux/jiffies.h>
+#include <linux/sched/mm.h>
#include <linux/sunrpc/clnt.h>
@@ -1776,6 +1777,7 @@
static void nfs4_state_start_reclaim_reboot(struct nfs_client *clp)
{
+ set_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state);
/* Mark all delegations for reclaim */
nfs_delegation_mark_reclaim(clp);
nfs4_state_mark_reclaim_helper(clp, nfs4_state_mark_reclaim_reboot);
@@ -2557,9 +2559,17 @@
static void nfs4_state_manager(struct nfs_client *clp)
{
+ unsigned int memflags;
int status = 0;
const char *section = "", *section_sep = "";
+ /*
+ * State recovery can deadlock if the direct reclaim code tries
+ * start NFS writeback. So ensure memory allocations are all
+ * GFP_NOFS.
+ */
+ memflags = memalloc_nofs_save();
+
/* Ensure exclusive access to NFSv4 state */
do {
trace_nfs4_state_mgr(clp);
@@ -2633,6 +2643,7 @@
if (status < 0)
goto out_error;
nfs4_state_end_reclaim_reboot(clp);
+ continue;
}
/* Detect expired delegations... */
@@ -2654,6 +2665,7 @@
clear_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state);
}
+ memalloc_nofs_restore(memflags);
nfs4_end_drain_session(clp);
nfs4_clear_state_manager_bit(clp);
@@ -2671,6 +2683,7 @@
return;
if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0)
return;
+ memflags = memalloc_nofs_save();
} while (refcount_read(&clp->cl_count) > 1 && !signalled());
goto out_drain;
@@ -2683,6 +2696,7 @@
clp->cl_hostname, -status);
ssleep(1);
out_drain:
+ memalloc_nofs_restore(memflags);
nfs4_end_drain_session(clp);
nfs4_clear_state_manager_bit(clp);
}
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 98b9c1e..17fef6e 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -90,10 +90,10 @@
}
}
-static inline struct nfs_page *
-nfs_page_alloc(void)
+static inline struct nfs_page *nfs_page_alloc(void)
{
- struct nfs_page *p = kmem_cache_zalloc(nfs_page_cachep, GFP_KERNEL);
+ struct nfs_page *p =
+ kmem_cache_zalloc(nfs_page_cachep, nfs_io_gfp_mask());
if (p)
INIT_LIST_HEAD(&p->wb_list);
return p;
@@ -901,7 +901,7 @@
struct nfs_commit_info cinfo;
struct nfs_page_array *pg_array = &hdr->page_array;
unsigned int pagecount, pageused;
- gfp_t gfp_flags = GFP_KERNEL;
+ gfp_t gfp_flags = nfs_io_gfp_mask();
pagecount = nfs_page_array_len(mirror->pg_base, mirror->pg_count);
pg_array->npages = pagecount;
@@ -984,7 +984,7 @@
desc->pg_mirrors_dynamic = NULL;
if (mirror_count == 1)
return desc->pg_mirrors_static;
- ret = kmalloc_array(mirror_count, sizeof(*ret), GFP_KERNEL);
+ ret = kmalloc_array(mirror_count, sizeof(*ret), nfs_io_gfp_mask());
if (ret != NULL) {
for (i = 0; i < mirror_count; i++)
nfs_pageio_mirror_init(&ret[i], desc->pg_bsize);
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 5370e08..2143672 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -92,6 +92,17 @@
return local;
}
+const struct pnfs_layoutdriver_type *pnfs_find_layoutdriver(u32 id)
+{
+ return find_pnfs_driver(id);
+}
+
+void pnfs_put_layoutdriver(const struct pnfs_layoutdriver_type *ld)
+{
+ if (ld)
+ module_put(ld->owner);
+}
+
void
unset_pnfs_layoutdriver(struct nfs_server *nfss)
{
@@ -458,6 +469,7 @@
pnfs_clear_lseg_state(lseg, lseg_list);
pnfs_clear_layoutreturn_info(lo);
pnfs_free_returned_lsegs(lo, lseg_list, &range, 0);
+ set_bit(NFS_LAYOUT_DRAIN, &lo->plh_flags);
if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags) &&
!test_and_set_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags))
pnfs_clear_layoutreturn_waitbit(lo);
@@ -1912,8 +1924,9 @@
static void nfs_layoutget_end(struct pnfs_layout_hdr *lo)
{
- if (atomic_dec_and_test(&lo->plh_outstanding))
- wake_up_var(&lo->plh_outstanding);
+ if (atomic_dec_and_test(&lo->plh_outstanding) &&
+ test_and_clear_bit(NFS_LAYOUT_DRAIN, &lo->plh_flags))
+ wake_up_bit(&lo->plh_flags, NFS_LAYOUT_DRAIN);
}
static bool pnfs_is_first_layoutget(struct pnfs_layout_hdr *lo)
@@ -1995,6 +2008,7 @@
lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags);
if (lo == NULL) {
spin_unlock(&ino->i_lock);
+ lseg = ERR_PTR(-ENOMEM);
trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
PNFS_UPDATE_LAYOUT_NOMEM);
goto out;
@@ -2019,11 +2033,11 @@
* If the layout segment list is empty, but there are outstanding
* layoutget calls, then they might be subject to a layoutrecall.
*/
- if ((list_empty(&lo->plh_segs) || !pnfs_layout_is_valid(lo)) &&
+ if (test_bit(NFS_LAYOUT_DRAIN, &lo->plh_flags) &&
atomic_read(&lo->plh_outstanding) != 0) {
spin_unlock(&ino->i_lock);
- lseg = ERR_PTR(wait_var_event_killable(&lo->plh_outstanding,
- !atomic_read(&lo->plh_outstanding)));
+ lseg = ERR_PTR(wait_on_bit(&lo->plh_flags, NFS_LAYOUT_DRAIN,
+ TASK_KILLABLE));
if (IS_ERR(lseg))
goto out_put_layout_hdr;
pnfs_put_layout_hdr(lo);
@@ -2123,6 +2137,7 @@
lgp = pnfs_alloc_init_layoutget_args(ino, ctx, &stateid, &arg, gfp_flags);
if (!lgp) {
+ lseg = ERR_PTR(-ENOMEM);
trace_pnfs_update_layout(ino, pos, count, iomode, lo, NULL,
PNFS_UPDATE_LAYOUT_NOMEM);
nfs_layoutget_end(lo);
@@ -2142,6 +2157,12 @@
case -ERECALLCONFLICT:
case -EAGAIN:
break;
+ case -ENODATA:
+ /* The server returned NFS4ERR_LAYOUTUNAVAILABLE */
+ pnfs_layout_set_fail_bit(
+ lo, pnfs_iomode_to_fail_bit(iomode));
+ lseg = NULL;
+ goto out_put_layout_hdr;
default:
if (!nfs_error_is_fatal(PTR_ERR(lseg))) {
pnfs_layout_clear_fail_bit(lo, pnfs_iomode_to_fail_bit(iomode));
@@ -2395,7 +2416,8 @@
goto out_forget;
}
- if (!pnfs_layout_is_valid(lo) && !pnfs_is_first_layoutget(lo))
+ if (test_bit(NFS_LAYOUT_DRAIN, &lo->plh_flags) &&
+ !pnfs_is_first_layoutget(lo))
goto out_forget;
if (nfs4_stateid_match_other(&lo->plh_stateid, &res->stateid)) {
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 0212fe3..a7cf84a 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -107,6 +107,7 @@
NFS_LAYOUT_FIRST_LAYOUTGET, /* Serialize first layoutget */
NFS_LAYOUT_INODE_FREEING, /* The inode is being freed */
NFS_LAYOUT_HASHED, /* The layout visible */
+ NFS_LAYOUT_DRAIN,
};
enum layoutdriver_policy_flags {
@@ -236,6 +237,8 @@
extern int pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *);
extern void pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *);
+extern const struct pnfs_layoutdriver_type *pnfs_find_layoutdriver(u32 id);
+extern void pnfs_put_layoutdriver(const struct pnfs_layoutdriver_type *ld);
/* nfs4proc.c */
extern size_t max_response_pages(struct nfs_server *server);
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index 7b9d701..a2ad8bb 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -419,7 +419,7 @@
pnfs_bucket_fetch_commitdata(struct pnfs_commit_bucket *bucket,
struct nfs_commit_info *cinfo)
{
- struct nfs_commit_data *data = nfs_commitdata_alloc(false);
+ struct nfs_commit_data *data = nfs_commitdata_alloc();
if (!data)
return NULL;
@@ -515,7 +515,11 @@
unsigned int nreq = 0;
if (!list_empty(mds_pages)) {
- data = nfs_commitdata_alloc(true);
+ data = nfs_commitdata_alloc();
+ if (!data) {
+ nfs_retry_commit(mds_pages, NULL, cinfo, -1);
+ return -ENOMEM;
+ }
data->ds_commit_index = -1;
list_splice_init(mds_pages, &data->pages);
list_add_tail(&data->list, &list);
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 4034102..b3fcc27 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1029,22 +1029,31 @@
if (ctx && ctx->bsize)
sb->s_blocksize = nfs_block_size(ctx->bsize, &sb->s_blocksize_bits);
- if (server->nfs_client->rpc_ops->version != 2) {
- /* The VFS shouldn't apply the umask to mode bits. We will do
- * so ourselves when necessary.
+ switch (server->nfs_client->rpc_ops->version) {
+ case 2:
+ sb->s_time_gran = 1000;
+ sb->s_time_min = 0;
+ sb->s_time_max = U32_MAX;
+ break;
+ case 3:
+ /*
+ * The VFS shouldn't apply the umask to mode bits.
+ * We will do so ourselves when necessary.
*/
sb->s_flags |= SB_POSIXACL;
sb->s_time_gran = 1;
- sb->s_export_op = &nfs_export_ops;
- } else
- sb->s_time_gran = 1000;
-
- if (server->nfs_client->rpc_ops->version != 4) {
sb->s_time_min = 0;
sb->s_time_max = U32_MAX;
- } else {
+ sb->s_export_op = &nfs_export_ops;
+ break;
+ case 4:
+ sb->s_flags |= SB_POSIXACL;
+ sb->s_time_gran = 1;
sb->s_time_min = S64_MIN;
sb->s_time_max = S64_MAX;
+ if (server->caps & NFS_CAP_ATOMIC_OPEN_V1)
+ sb->s_export_op = &nfs_export_ops;
+ break;
}
sb->s_magic = NFS_SUPER_MAGIC;
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index bde4c36..dc08a0c 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -70,27 +70,17 @@
static struct kmem_cache *nfs_cdata_cachep;
static mempool_t *nfs_commit_mempool;
-struct nfs_commit_data *nfs_commitdata_alloc(bool never_fail)
+struct nfs_commit_data *nfs_commitdata_alloc(void)
{
struct nfs_commit_data *p;
- if (never_fail)
- p = mempool_alloc(nfs_commit_mempool, GFP_NOIO);
- else {
- /* It is OK to do some reclaim, not no safe to wait
- * for anything to be returned to the pool.
- * mempool_alloc() cannot handle that particular combination,
- * so we need two separate attempts.
- */
+ p = kmem_cache_zalloc(nfs_cdata_cachep, nfs_io_gfp_mask());
+ if (!p) {
p = mempool_alloc(nfs_commit_mempool, GFP_NOWAIT);
if (!p)
- p = kmem_cache_alloc(nfs_cdata_cachep, GFP_NOIO |
- __GFP_NOWARN | __GFP_NORETRY);
- if (!p)
return NULL;
+ memset(p, 0, sizeof(*p));
}
-
- memset(p, 0, sizeof(*p));
INIT_LIST_HEAD(&p->pages);
return p;
}
@@ -104,9 +94,15 @@
static struct nfs_pgio_header *nfs_writehdr_alloc(void)
{
- struct nfs_pgio_header *p = mempool_alloc(nfs_wdata_mempool, GFP_KERNEL);
+ struct nfs_pgio_header *p;
- memset(p, 0, sizeof(*p));
+ p = kmem_cache_zalloc(nfs_wdata_cachep, nfs_io_gfp_mask());
+ if (!p) {
+ p = mempool_alloc(nfs_wdata_mempool, GFP_NOWAIT);
+ if (!p)
+ return NULL;
+ memset(p, 0, sizeof(*p));
+ }
p->rw_mode = FMODE_WRITE;
return p;
}
@@ -314,7 +310,10 @@
struct address_space *mapping = page_file_mapping(page);
SetPageError(page);
- mapping_set_error(mapping, error);
+ filemap_set_wb_err(mapping, error);
+ if (mapping->host)
+ errseq_set(&mapping->host->i_sb->s_wb_err,
+ error == -ENOSPC ? -ENOSPC : -EIO);
nfs_set_pageerror(mapping);
}
@@ -676,11 +675,7 @@
err = nfs_do_writepage(page, wbc, &pgio);
pgio.pg_error = 0;
nfs_pageio_complete(&pgio);
- if (err < 0)
- return err;
- if (nfs_error_is_fatal(pgio.pg_error))
- return pgio.pg_error;
- return 0;
+ return err;
}
int nfs_writepage(struct page *page, struct writeback_control *wbc)
@@ -731,9 +726,6 @@
if (err < 0)
goto out_err;
- err = pgio.pg_error;
- if (nfs_error_is_fatal(err))
- goto out_err;
return 0;
out_err:
return err;
@@ -1412,7 +1404,7 @@
while (!list_empty(head)) {
req = nfs_list_entry(head->next);
nfs_list_remove_request(req);
- if (nfs_error_is_fatal(error))
+ if (nfs_error_is_fatal_on_server(error))
nfs_write_error(req, error);
else
nfs_redirty_request(req);
@@ -1797,7 +1789,11 @@
if (list_empty(head))
return 0;
- data = nfs_commitdata_alloc(true);
+ data = nfs_commitdata_alloc();
+ if (!data) {
+ nfs_retry_commit(head, NULL, cinfo, -1);
+ return -ENOMEM;
+ }
/* Set up the argument struct */
nfs_init_commit(data, head, NULL, cinfo);