aboutsummaryrefslogtreecommitdiff
path: root/fs/nfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/nfs')
-rw-r--r--fs/nfs/blocklayout/blocklayout.c13
-rw-r--r--fs/nfs/callback_proc.c1
-rw-r--r--fs/nfs/dir.c10
-rw-r--r--fs/nfs/direct.c23
-rw-r--r--fs/nfs/file.c123
-rw-r--r--fs/nfs/filelayout/filelayout.c7
-rw-r--r--fs/nfs/fscache.c7
-rw-r--r--fs/nfs/fscache.h14
-rw-r--r--fs/nfs/internal.h7
-rw-r--r--fs/nfs/nfs4file.c5
-rw-r--r--fs/nfs/nfs4namespace.c9
-rw-r--r--fs/nfs/nfs4proc.c201
-rw-r--r--fs/nfs/nfs4state.c30
-rw-r--r--fs/nfs/nfs4xdr.c99
-rw-r--r--fs/nfs/pagelist.c3
-rw-r--r--fs/nfs/pnfs.c23
-rw-r--r--fs/nfs/pnfs.h1
-rw-r--r--fs/nfs/read.c7
-rw-r--r--fs/nfs/symlink.c16
-rw-r--r--fs/nfs/unlink.c8
-rw-r--r--fs/nfs/write.c70
21 files changed, 429 insertions, 248 deletions
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 79a8b451791f..943aeea1eb16 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -121,7 +121,7 @@ static bool offset_in_map(u64 offset, struct pnfs_block_dev_map *map)
}
static struct bio *
-do_add_page_to_bio(struct bio *bio, int npg, int rw, sector_t isect,
+do_add_page_to_bio(struct bio *bio, int npg, enum req_op op, sector_t isect,
struct page *page, struct pnfs_block_dev_map *map,
struct pnfs_block_extent *be, bio_end_io_t end_io,
struct parallel_io *par, unsigned int offset, int *len)
@@ -131,7 +131,7 @@ do_add_page_to_bio(struct bio *bio, int npg, int rw, sector_t isect,
u64 disk_addr, end;
dprintk("%s: npg %d rw %d isect %llu offset %u len %d\n", __func__,
- npg, rw, (unsigned long long)isect, offset, *len);
+ npg, (__force u32)op, (unsigned long long)isect, offset, *len);
/* translate to device offset */
isect += be->be_v_offset;
@@ -154,7 +154,7 @@ do_add_page_to_bio(struct bio *bio, int npg, int rw, sector_t isect,
retry:
if (!bio) {
- bio = bio_alloc(map->bdev, bio_max_segs(npg), rw, GFP_NOIO);
+ bio = bio_alloc(map->bdev, bio_max_segs(npg), op, GFP_NOIO);
bio->bi_iter.bi_sector = disk_addr >> SECTOR_SHIFT;
bio->bi_end_io = end_io;
bio->bi_private = par;
@@ -291,7 +291,7 @@ bl_read_pagelist(struct nfs_pgio_header *header)
} else {
bio = do_add_page_to_bio(bio,
header->page_array.npages - i,
- READ,
+ REQ_OP_READ,
isect, pages[i], &map, &be,
bl_end_io_read, par,
pg_offset, &pg_len);
@@ -420,9 +420,8 @@ bl_write_pagelist(struct nfs_pgio_header *header, int sync)
pg_len = PAGE_SIZE;
bio = do_add_page_to_bio(bio, header->page_array.npages - i,
- WRITE, isect, pages[i], &map, &be,
- bl_end_io_write, par,
- 0, &pg_len);
+ REQ_OP_WRITE, isect, pages[i], &map,
+ &be, bl_end_io_write, par, 0, &pg_len);
if (IS_ERR(bio)) {
header->pnfs_error = PTR_ERR(bio);
bio = NULL;
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index c8520284dda7..c1eda73254e1 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -288,6 +288,7 @@ static u32 initiate_file_draining(struct nfs_client *clp,
rv = NFS4_OK;
break;
case -ENOENT:
+ set_bit(NFS_LAYOUT_DRAIN, &lo->plh_flags);
/* Embrace your forgetfulness! */
rv = NFS4ERR_NOMATCHING_LAYOUT;
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index c6b263b5faf1..0c4e8dd6aa96 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -55,7 +55,7 @@ static int nfs_closedir(struct inode *, struct file *);
static int nfs_readdir(struct file *, struct dir_context *);
static int nfs_fsync_dir(struct file *, loff_t, loff_t, int);
static loff_t nfs_llseek_dir(struct file *, loff_t, int);
-static void nfs_readdir_clear_array(struct page*);
+static void nfs_readdir_free_folio(struct folio *);
const struct file_operations nfs_dir_operations = {
.llseek = nfs_llseek_dir,
@@ -67,7 +67,7 @@ const struct file_operations nfs_dir_operations = {
};
const struct address_space_operations nfs_dir_aops = {
- .freepage = nfs_readdir_clear_array,
+ .free_folio = nfs_readdir_free_folio,
};
#define NFS_INIT_DTSIZE PAGE_SIZE
@@ -228,6 +228,11 @@ static void nfs_readdir_clear_array(struct page *page)
kunmap_atomic(array);
}
+static void nfs_readdir_free_folio(struct folio *folio)
+{
+ nfs_readdir_clear_array(&folio->page);
+}
+
static void nfs_readdir_page_reinit_array(struct page *page, u64 last_cookie,
u64 change_attr)
{
@@ -2119,6 +2124,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
}
goto out;
}
+ file->f_mode |= FMODE_CAN_ODIRECT;
err = nfs_finish_open(ctx, ctx->dentry, file, open_flags);
trace_nfs_atomic_open_exit(dir, ctx, open_flags, err);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 11c566d8769f..4eb2a8380a28 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -153,28 +153,25 @@ nfs_direct_count_bytes(struct nfs_direct_req *dreq,
}
/**
- * nfs_direct_IO - NFS address space operation for direct I/O
+ * nfs_swap_rw - NFS address space operation for swap I/O
* @iocb: target I/O control block
* @iter: I/O buffer
*
- * The presence of this routine in the address space ops vector means
- * the NFS client supports direct I/O. However, for most direct IO, we
- * shunt off direct read and write requests before the VFS gets them,
- * so this method is only ever called for swap.
+ * Perform IO to the swap-file. This is much like direct IO.
*/
-ssize_t nfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
+int nfs_swap_rw(struct kiocb *iocb, struct iov_iter *iter)
{
- struct inode *inode = iocb->ki_filp->f_mapping->host;
-
- /* we only support swap file calling nfs_direct_IO */
- if (!IS_SWAPFILE(inode))
- return 0;
+ ssize_t ret;
VM_BUG_ON(iov_iter_count(iter) != PAGE_SIZE);
if (iov_iter_rw(iter) == READ)
- return nfs_file_direct_read(iocb, iter, true);
- return nfs_file_direct_write(iocb, iter, true);
+ ret = nfs_file_direct_read(iocb, iter, true);
+ else
+ ret = nfs_file_direct_write(iocb, iter, true);
+ if (ret < 0)
+ return ret;
+ return 0;
}
static void nfs_direct_release_pages(struct page **pages, unsigned int npages)
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 150b7fa8f0a7..549baed76351 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -69,6 +69,8 @@ nfs_file_open(struct inode *inode, struct file *filp)
return res;
res = nfs_open(inode, filp);
+ if (res == 0)
+ filp->f_mode |= FMODE_CAN_ODIRECT;
return res;
}
@@ -204,15 +206,16 @@ static int
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
@@ -313,7 +316,7 @@ static bool nfs_want_read_modify_write(struct file *file, struct page *page,
* increment the page use counts until he is done with the page.
*/
static int nfs_write_begin(struct file *file, struct address_space *mapping,
- loff_t pos, unsigned len, unsigned flags,
+ loff_t pos, unsigned len,
struct page **pagep, void **fsdata)
{
int ret;
@@ -325,7 +328,7 @@ static int nfs_write_begin(struct file *file, struct address_space *mapping,
file, mapping->host->i_ino, len, (long long) pos);
start:
- page = grab_cache_page_write_begin(mapping, index, flags);
+ page = grab_cache_page_write_begin(mapping, index);
if (!page)
return -ENOMEM;
*pagep = page;
@@ -337,7 +340,7 @@ start:
} else if (!once_thru &&
nfs_want_read_modify_write(file, page, pos, len)) {
once_thru = 1;
- ret = nfs_readpage(file, page);
+ ret = nfs_read_folio(file, page_folio(page));
put_page(page);
if (!ret)
goto start;
@@ -385,11 +388,8 @@ static int nfs_write_end(struct file *file, struct address_space *mapping,
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;
}
@@ -415,34 +415,31 @@ static void nfs_invalidate_folio(struct folio *folio, size_t offset,
}
/*
- * Attempt to release the private state associated with a page
- * - Called if either PG_private or PG_fscache is set on the page
- * - Caller holds page lock
- * - Return true (may release page) or false (may not)
+ * Attempt to release the private state associated with a folio
+ * - Called if either private or fscache flags are set on the folio
+ * - Caller holds folio lock
+ * - Return true (may release folio) or false (may not)
*/
-static int nfs_release_page(struct page *page, gfp_t gfp)
+static bool nfs_release_folio(struct folio *folio, gfp_t gfp)
{
- dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page);
+ dfprintk(PAGECACHE, "NFS: release_folio(%p)\n", folio);
- /* If PagePrivate() is set, then the page is not freeable */
- if (PagePrivate(page))
- return 0;
- return nfs_fscache_release_page(page, gfp);
+ /* If the private flag is set, then the folio is not freeable */
+ if (folio_test_private(folio))
+ return false;
+ return nfs_fscache_release_folio(folio, gfp);
}
-static void nfs_check_dirty_writeback(struct page *page,
+static void nfs_check_dirty_writeback(struct folio *folio,
bool *dirty, bool *writeback)
{
struct nfs_inode *nfsi;
- struct address_space *mapping = page_file_mapping(page);
-
- if (!mapping || PageSwapCache(page))
- return;
+ struct address_space *mapping = folio->mapping;
/*
- * Check if an unstable page is currently being committed and
- * if so, have the VM treat it as if the page is under writeback
- * so it will not block due to pages that will shortly be freeable.
+ * Check if an unstable folio is currently being committed and
+ * if so, have the VM treat it as if the folio is under writeback
+ * so it will not block due to folios that will shortly be freeable.
*/
nfsi = NFS_I(mapping->host);
if (atomic_read(&nfsi->commit_info.rpcs_out)) {
@@ -451,11 +448,11 @@ static void nfs_check_dirty_writeback(struct page *page,
}
/*
- * If PagePrivate() is set, then the page is not freeable and as the
- * inode is not being committed, it's not going to be cleaned in the
- * near future so treat it as dirty
+ * If the private flag is set, then the folio is not freeable
+ * and as the inode is not being committed, it's not going to
+ * be cleaned in the near future so treat it as dirty
*/
- if (PagePrivate(page))
+ if (folio_test_private(folio))
*dirty = true;
}
@@ -483,6 +480,7 @@ static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file,
{
unsigned long blocks;
long long isize;
+ int ret;
struct inode *inode = file_inode(file);
struct rpc_clnt *clnt = NFS_CLIENT(inode);
struct nfs_client *cl = NFS_SERVER(inode)->nfs_client;
@@ -496,13 +494,22 @@ static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file,
return -EINVAL;
}
- *span = sis->pages;
+ ret = rpc_clnt_swap_activate(clnt);
+ if (ret)
+ return ret;
+ ret = add_swap_extent(sis, 0, sis->max, 0);
+ if (ret < 0) {
+ rpc_clnt_swap_deactivate(clnt);
+ return ret;
+ }
+ *span = sis->pages;
if (cl->rpc_ops->enable_swap)
cl->rpc_ops->enable_swap(inode);
- return rpc_clnt_swap_activate(clnt);
+ sis->flags |= SWP_FS_OPS;
+ return ret;
}
static void nfs_swap_deactivate(struct file *file)
@@ -517,7 +524,7 @@ static void nfs_swap_deactivate(struct file *file)
}
const struct address_space_operations nfs_file_aops = {
- .readpage = nfs_readpage,
+ .read_folio = nfs_read_folio,
.readahead = nfs_readahead,
.dirty_folio = filemap_dirty_folio,
.writepage = nfs_writepage,
@@ -525,16 +532,14 @@ const struct address_space_operations nfs_file_aops = {
.write_begin = nfs_write_begin,
.write_end = nfs_write_end,
.invalidate_folio = nfs_invalidate_folio,
- .releasepage = nfs_release_page,
- .direct_IO = nfs_direct_IO,
-#ifdef CONFIG_MIGRATION
- .migratepage = nfs_migrate_page,
-#endif
+ .release_folio = nfs_release_folio,
+ .migrate_folio = nfs_migrate_folio,
.launder_folio = nfs_launder_folio,
.is_dirty_writeback = nfs_check_dirty_writeback,
.error_remove_page = generic_error_remove_page,
.swap_activate = nfs_swap_activate,
.swap_deactivate = nfs_swap_deactivate,
+ .swap_rw = nfs_swap_rw,
};
/*
@@ -597,18 +602,6 @@ static const struct vm_operations_struct nfs_file_vm_ops = {
.page_mkwrite = nfs_vm_page_mkwrite,
};
-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_error_is_fatal_on_server(error) ||
- nfs_ctx_key_to_expire(ctx, inode))
- return 1;
- return 0;
-}
-
ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
@@ -636,7 +629,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
if (iocb->ki_flags & IOCB_APPEND || iocb->ki_pos > i_size_read(inode)) {
result = nfs_revalidate_file_size(inode, file);
if (result)
- goto out;
+ return result;
}
nfs_clear_invalid_mapping(file->f_mapping);
@@ -655,6 +648,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
written = result;
iocb->ki_pos += written;
+ nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, written);
if (mntflags & NFS_MOUNT_WRITE_EAGER) {
result = filemap_fdatawrite_range(file->f_mapping,
@@ -672,17 +666,22 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
}
result = generic_write_sync(iocb, written);
if (result < 0)
- goto out;
+ return result;
+out:
/* Return error values */
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;
+ switch (error) {
+ default:
+ break;
+ case -EDQUOT:
+ case -EFBIG:
+ case -ENOSPC:
+ nfs_wb_all(inode);
+ error = file_check_and_advance_wb_err(file);
+ if (error < 0)
+ result = error;
}
- nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, written);
-out:
return result;
out_swapfile:
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index 76deddab0a8f..2b2661582bbe 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -839,7 +839,12 @@ fl_pnfs_update_layout(struct inode *ino,
lseg = pnfs_update_layout(ino, ctx, pos, count, iomode, strict_iomode,
gfp_flags);
- if (IS_ERR_OR_NULL(lseg))
+ if (IS_ERR(lseg)) {
+ /* Fall back to MDS on recoverable errors */
+ if (!nfs_error_is_fatal_on_server(PTR_ERR(lseg)))
+ lseg = NULL;
+ goto out;
+ } else if (!lseg)
goto out;
lo = NFS_I(ino)->layout;
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index f73c09a9cf0a..e861d7bae305 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -231,11 +231,10 @@ void nfs_fscache_release_file(struct inode *inode, struct file *filp)
{
struct nfs_fscache_inode_auxdata auxdata;
struct fscache_cookie *cookie = nfs_i_fscache(inode);
+ loff_t i_size = i_size_read(inode);
- if (fscache_cookie_valid(cookie)) {
- nfs_fscache_update_auxdata(&auxdata, inode);
- fscache_unuse_cookie(cookie, &auxdata, NULL);
- }
+ nfs_fscache_update_auxdata(&auxdata, inode);
+ fscache_unuse_cookie(cookie, &auxdata, &i_size);
}
/*
diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h
index 4e980cc04779..2a37af880978 100644
--- a/fs/nfs/fscache.h
+++ b/fs/nfs/fscache.h
@@ -48,14 +48,14 @@ extern void nfs_fscache_release_file(struct inode *, struct file *);
extern int __nfs_fscache_read_page(struct inode *, struct page *);
extern void __nfs_fscache_write_page(struct inode *, struct page *);
-static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp)
+static inline bool nfs_fscache_release_folio(struct folio *folio, gfp_t gfp)
{
- if (PageFsCache(page)) {
+ if (folio_test_fscache(folio)) {
if (current_is_kswapd() || !(gfp & __GFP_FS))
return false;
- wait_on_page_fscache(page);
- fscache_note_page_release(nfs_i_fscache(page->mapping->host));
- nfs_inc_fscache_stats(page->mapping->host,
+ folio_wait_fscache(folio);
+ fscache_note_page_release(nfs_i_fscache(folio->mapping->host));
+ nfs_inc_fscache_stats(folio->mapping->host,
NFSIOS_FSCACHE_PAGES_UNCACHED);
}
return true;
@@ -129,9 +129,9 @@ static inline void nfs_fscache_open_file(struct inode *inode,
struct file *filp) {}
static inline void nfs_fscache_release_file(struct inode *inode, struct file *file) {}
-static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp)
+static inline bool nfs_fscache_release_folio(struct folio *folio, gfp_t gfp)
{
- return 1; /* True: may release page */
+ return true; /* may release folio */
}
static inline int nfs_fscache_read_page(struct inode *inode, struct page *page)
{
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 7eefa16ed381..437ebe544aaf 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -578,8 +578,10 @@ void nfs_clear_pnfs_ds_commit_verifiers(struct pnfs_ds_commit_info *cinfo)
#endif
#ifdef CONFIG_MIGRATION
-extern int nfs_migrate_page(struct address_space *,
- struct page *, struct page *, enum migrate_mode);
+int nfs_migrate_folio(struct address_space *, struct folio *dst,
+ struct folio *src, enum migrate_mode);
+#else
+#define nfs_migrate_folio NULL
#endif
static inline int
@@ -841,6 +843,7 @@ static inline bool nfs_error_is_fatal_on_server(int err)
case 0:
case -ERESTARTSYS:
case -EINTR:
+ case -ENOMEM:
return false;
}
return nfs_error_is_fatal(err);
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 7b861e4f0533..e88f6b18445e 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -93,6 +93,7 @@ nfs4_file_open(struct inode *inode, struct file *filp)
nfs_file_set_open_context(filp, ctx);
nfs_fscache_open_file(inode, filp);
err = 0;
+ filp->f_mode |= FMODE_CAN_ODIRECT;
out_put_ctx:
put_nfs_open_context(ctx);
@@ -328,7 +329,7 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt,
char *read_name = NULL;
int len, status = 0;
- server = NFS_SERVER(ss_mnt->mnt_root->d_inode);
+ server = NFS_SB(ss_mnt->mnt_sb);
if (!fattr)
return ERR_PTR(-ENOMEM);
@@ -346,7 +347,7 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt,
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_sb, src_fh, fattr);
if (IS_ERR(r_ino)) {
res = ERR_CAST(r_ino);
goto out_free_name;
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index 3680c8da510c..f2dbf904c598 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -417,6 +417,9 @@ static int nfs_do_refmount(struct fs_context *fc, struct rpc_clnt *client)
fs_locations = kmalloc(sizeof(struct nfs4_fs_locations), GFP_KERNEL);
if (!fs_locations)
goto out_free;
+ fs_locations->fattr = nfs_alloc_fattr();
+ if (!fs_locations->fattr)
+ goto out_free_2;
/* Get locations */
dentry = ctx->clone_data.dentry;
@@ -427,14 +430,16 @@ static int nfs_do_refmount(struct fs_context *fc, struct rpc_clnt *client)
err = nfs4_proc_fs_locations(client, d_inode(parent), &dentry->d_name, fs_locations, page);
dput(parent);
if (err != 0)
- goto out_free_2;
+ goto out_free_3;
err = -ENOENT;
if (fs_locations->nlocations <= 0 ||
fs_locations->fs_path.ncomponents <= 0)
- goto out_free_2;
+ goto out_free_3;
err = nfs_follow_referral(fc, fs_locations);
+out_free_3:
+ kfree(fs_locations->fattr);
out_free_2:
kfree(fs_locations);
out_free:
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index a79f66432bd3..bb0e84a46d61 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1162,7 +1162,7 @@ static int nfs4_call_sync_sequence(struct rpc_clnt *clnt,
{
unsigned short task_flags = 0;
- if (server->nfs_client->cl_minorversion)
+ if (server->caps & NFS_CAP_MOVEABLE)
task_flags = RPC_TASK_MOVEABLE;
return nfs4_do_call_sync(clnt, server, msg, args, res, task_flags);
}
@@ -2568,7 +2568,7 @@ static int nfs4_run_open_task(struct nfs4_opendata *data,
};
int status;
- if (server->nfs_client->cl_minorversion)
+ if (nfs_server_capable(dir, NFS_CAP_MOVEABLE))
task_setup_data.flags |= RPC_TASK_MOVEABLE;
kref_get(&data->kref);
@@ -3098,6 +3098,10 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
}
out:
+ if (opendata->lgp) {
+ nfs4_lgopen_release(opendata->lgp);
+ opendata->lgp = NULL;
+ }
if (!opendata->cancelled)
nfs4_sequence_free_slot(&opendata->o_res.seq_res);
return ret;
@@ -3733,7 +3737,7 @@ int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait)
};
int status = -ENOMEM;
- if (server->nfs_client->cl_minorversion)
+ if (nfs_server_capable(state->inode, NFS_CAP_MOVEABLE))
task_setup_data.flags |= RPC_TASK_MOVEABLE;
nfs4_state_protect(server->nfs_client, NFS_SP4_MACH_CRED_CLEANUP,
@@ -4008,22 +4012,29 @@ static int _nfs4_discover_trunking(struct nfs_server *server,
}
page = alloc_page(GFP_KERNEL);
+ if (!page)
+ return -ENOMEM;
locations = kmalloc(sizeof(struct nfs4_fs_locations), GFP_KERNEL);
- if (page == NULL || locations == NULL)
- goto out;
+ if (!locations)
+ goto out_free;
+ locations->fattr = nfs_alloc_fattr();
+ if (!locations->fattr)
+ goto out_free_2;
status = nfs4_proc_get_locations(server, fhandle, locations, page,
cred);
if (status)
- goto out;
+ goto out_free_3;
for (i = 0; i < locations->nlocations; i++)
test_fs_location_for_trunking(&locations->locations[i], clp,
server);
-out:
- if (page)
- __free_page(page);
+out_free_3:
+ kfree(locations->fattr);
+out_free_2:
kfree(locations);
+out_free:
+ __free_page(page);
return status;
}
@@ -4243,6 +4254,8 @@ static int nfs4_get_referral(struct rpc_clnt *client, struct inode *dir,
if (locations == NULL)
goto out;
+ locations->fattr = fattr;
+
status = nfs4_proc_fs_locations(client, dir, name, locations, page);
if (status != 0)
goto out;
@@ -4252,17 +4265,14 @@ static int nfs4_get_referral(struct rpc_clnt *client, struct inode *dir,
* referral. Cause us to drop into the exception handler, which
* will kick off migration recovery.
*/
- if (nfs_fsid_equal(&NFS_SERVER(dir)->fsid, &locations->fattr.fsid)) {
+ if (nfs_fsid_equal(&NFS_SERVER(dir)->fsid, &fattr->fsid)) {
dprintk("%s: server did not return a different fsid for"
" a referral at %s\n", __func__, name->name);
status = -NFS4ERR_MOVED;
goto out;
}
/* Fixup attributes for the nfs_lookup() call to nfs_fhget() */
- nfs_fixup_referral_attributes(&locations->fattr);
-
- /* replace the lookup nfs_fattr with the locations nfs_fattr */
- memcpy(fattr, &locations->fattr, sizeof(struct nfs_fattr));
+ nfs_fixup_referral_attributes(fattr);
memset(fhandle, 0, sizeof(struct nfs_fh));
out:
if (page)
@@ -4404,7 +4414,7 @@ static int _nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir,
};
unsigned short task_flags = 0;
- if (server->nfs_client->cl_minorversion)
+ if (nfs_server_capable(dir, NFS_CAP_MOVEABLE))
task_flags = RPC_TASK_MOVEABLE;
/* Is this is an attribute revalidation, subject to softreval? */
@@ -5768,9 +5778,17 @@ static int nfs4_proc_renew(struct nfs_client *clp, const struct cred *cred)
return 0;
}
-static inline int nfs4_server_supports_acls(struct nfs_server *server)
+static bool nfs4_server_supports_acls(const struct nfs_server *server,
+ enum nfs4_acl_type type)
{
- return server->caps & NFS_CAP_ACLS;
+ switch (type) {
+ default:
+ return server->attr_bitmask[0] & FATTR4_WORD0_ACL;
+ case NFS4ACL_DACL:
+ return server->attr_bitmask[1] & FATTR4_WORD1_DACL;
+ case NFS4ACL_SACL:
+ return server->attr_bitmask[1] & FATTR4_WORD1_SACL;
+ }
}
/* Assuming that XATTR_SIZE_MAX is a multiple of PAGE_SIZE, and that
@@ -5809,6 +5827,7 @@ unwind:
}
struct nfs4_cached_acl {
+ enum nfs4_acl_type type;
int cached;
size_t len;
char data[];
@@ -5829,7 +5848,8 @@ static void nfs4_zap_acl_attr(struct inode *inode)
nfs4_set_cached_acl(inode, NULL);
}
-static inline ssize_t nfs4_read_cached_acl(struct inode *inode, char *buf, size_t buflen)
+static ssize_t nfs4_read_cached_acl(struct inode *inode, char *buf,
+ size_t buflen, enum nfs4_acl_type type)
{
struct nfs_inode *nfsi = NFS_I(inode);
struct nfs4_cached_acl *acl;
@@ -5839,6 +5859,8 @@ static inline ssize_t nfs4_read_cached_acl(struct inode *inode, char *buf, size_
acl = nfsi->nfs4_acl;
if (acl == NULL)
goto out;
+ if (acl->type != type)
+ goto out;
if (buf == NULL) /* user is just asking for length */
goto out_len;
if (acl->cached == 0)
@@ -5854,7 +5876,9 @@ out:
return ret;
}
-static void nfs4_write_cached_acl(struct inode *inode, struct page **pages, size_t pgbase, size_t acl_len)
+static void nfs4_write_cached_acl(struct inode *inode, struct page **pages,
+ size_t pgbase, size_t acl_len,
+ enum nfs4_acl_type type)
{
struct nfs4_cached_acl *acl;
size_t buflen = sizeof(*acl) + acl_len;
@@ -5871,6 +5895,7 @@ static void nfs4_write_cached_acl(struct inode *inode, struct page **pages, size
goto out;
acl->cached = 0;
}
+ acl->type = type;
acl->len = acl_len;
out:
nfs4_set_cached_acl(inode, acl);
@@ -5886,14 +5911,17 @@ out:
* length. The next getxattr call will then produce another round trip to
* the server, this time with the input buf of the required size.
*/
-static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t buflen)
+static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf,
+ size_t buflen, enum nfs4_acl_type type)
{
struct page **pages;
struct nfs_getaclargs args = {
.fh = NFS_FH(inode),
+ .acl_type = type,
.acl_len = buflen,
};
struct nfs_getaclres res = {
+ .acl_type = type,
.acl_len = buflen,
};
struct rpc_message msg = {
@@ -5943,7 +5971,8 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
ret = -ERANGE;
goto out_free;
}
- nfs4_write_cached_acl(inode, pages, res.acl_data_offset, res.acl_len);
+ nfs4_write_cached_acl(inode, pages, res.acl_data_offset, res.acl_len,
+ type);
if (buf) {
if (res.acl_len > buflen) {
ret = -ERANGE;
@@ -5963,14 +5992,15 @@ out_free:
return ret;
}
-static ssize_t nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t buflen)
+static ssize_t nfs4_get_acl_uncached(struct inode *inode, void *buf,
+ size_t buflen, enum nfs4_acl_type type)
{
struct nfs4_exception exception = {
.interruptible = true,
};
ssize_t ret;
do {
- ret = __nfs4_get_acl_uncached(inode, buf, buflen);
+ ret = __nfs4_get_acl_uncached(inode, buf, buflen, type);
trace_nfs4_get_acl(inode, ret);
if (ret >= 0)
break;
@@ -5979,34 +6009,37 @@ static ssize_t nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bufl
return ret;
}
-static ssize_t nfs4_proc_get_acl(struct inode *inode, void *buf, size_t buflen)
+static ssize_t nfs4_proc_get_acl(struct inode *inode, void *buf, size_t buflen,
+ enum nfs4_acl_type type)
{
struct nfs_server *server = NFS_SERVER(inode);
int ret;
- if (!nfs4_server_supports_acls(server))
+ if (!nfs4_server_supports_acls(server, type))
return -EOPNOTSUPP;
ret = nfs_revalidate_inode(inode, NFS_INO_INVALID_CHANGE);
if (ret < 0)
return ret;
if (NFS_I(inode)->cache_validity & NFS_INO_INVALID_ACL)
nfs_zap_acl_cache(inode);
- ret = nfs4_read_cached_acl(inode, buf, buflen);
+ ret = nfs4_read_cached_acl(inode, buf, buflen, type);
if (ret != -ENOENT)
/* -ENOENT is returned if there is no ACL or if there is an ACL
* but no cached acl data, just the acl length */
return ret;
- return nfs4_get_acl_uncached(inode, buf, buflen);
+ return nfs4_get_acl_uncached(inode, buf, buflen, type);
}
-static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t buflen)
+static int __nfs4_proc_set_acl(struct inode *inode, const void *buf,
+ size_t buflen, enum nfs4_acl_type type)
{
struct nfs_server *server = NFS_SERVER(inode);
struct page *pages[NFS4ACL_MAXPAGES];
struct nfs_setaclargs arg = {
- .fh = NFS_FH(inode),
- .acl_pages = pages,
- .acl_len = buflen,
+ .fh = NFS_FH(inode),
+ .acl_type = type,
+ .acl_len = buflen,
+ .acl_pages = pages,
};
struct nfs_setaclres res;
struct rpc_message msg = {
@@ -6020,7 +6053,7 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl
/* You can't remove system.nfs4_acl: */
if (buflen == 0)
return -EINVAL;
- if (!nfs4_server_supports_acls(server))
+ if (!nfs4_server_supports_acls(server, type))
return -EOPNOTSUPP;
if (npages > ARRAY_SIZE(pages))
return -ERANGE;
@@ -6051,12 +6084,13 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl
return ret;
}
-static int nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t buflen)
+static int nfs4_proc_set_acl(struct inode *inode, const void *buf,
+ size_t buflen, enum nfs4_acl_type type)
{
struct nfs4_exception exception = { };
int err;
do {
- err = __nfs4_proc_set_acl(inode, buf, buflen);
+ err = __nfs4_proc_set_acl(inode, buf, buflen, type);
trace_nfs4_set_acl(inode, err);
if (err == -NFS4ERR_BADOWNER || err == -NFS4ERR_BADNAME) {
/*
@@ -6612,10 +6646,13 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred,
.rpc_client = server->client,
.rpc_message = &msg,
.callback_ops = &nfs4_delegreturn_ops,
- .flags = RPC_TASK_ASYNC | RPC_TASK_TIMEOUT | RPC_TASK_MOVEABLE,
+ .flags = RPC_TASK_ASYNC | RPC_TASK_TIMEOUT,
};
int status = 0;
+ if (nfs_server_capable(inode, NFS_CAP_MOVEABLE))
+ task_setup_data.flags |= RPC_TASK_MOVEABLE;
+
data = kzalloc(sizeof(*data), GFP_KERNEL);
if (data == NULL)
return -ENOMEM;
@@ -6929,10 +6966,8 @@ static struct rpc_task *nfs4_do_unlck(struct file_lock *fl,
.workqueue = nfsiod_workqueue,
.flags = RPC_TASK_ASYNC,
};
- struct nfs_client *client =
- NFS_SERVER(lsp->ls_state->inode)->nfs_client;
- if (client->cl_minorversion)
+ if (nfs_server_capable(lsp->ls_state->inode, NFS_CAP_MOVEABLE))
task_setup_data.flags |= RPC_TASK_MOVEABLE;
nfs4_state_protect(NFS_SERVER(lsp->ls_state->inode)->nfs_client,
@@ -7203,9 +7238,8 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f
.flags = RPC_TASK_ASYNC | RPC_TASK_CRED_NOREF,
};
int ret;
- struct nfs_client *client = NFS_SERVER(state->inode)->nfs_client;
- if (client->cl_minorversion)
+ if (nfs_server_capable(state->inode, NFS_CAP_MOVEABLE))
task_setup_data.flags |= RPC_TASK_MOVEABLE;
data = nfs4_alloc_lockdata(fl, nfs_file_open_context(fl->fl_file),
@@ -7655,21 +7689,70 @@ static int nfs4_xattr_set_nfs4_acl(const struct xattr_handler *handler,
const char *key, const void *buf,
size_t buflen, int flags)
{
- return nfs4_proc_set_acl(inode, buf, buflen);
+ return nfs4_proc_set_acl(inode, buf, buflen, NFS4ACL_ACL);
}
static int nfs4_xattr_get_nfs4_acl(const struct xattr_handler *handler,
struct dentry *unused, struct inode *inode,
const char *key, void *buf, size_t buflen)
{
- return nfs4_proc_get_acl(inode, buf, buflen);
+ return nfs4_proc_get_acl(inode, buf, buflen, NFS4ACL_ACL);
}
static bool nfs4_xattr_list_nfs4_acl(struct dentry *dentry)
{
- return nfs4_server_supports_acls(NFS_SERVER(d_inode(dentry)));
+ return nfs4_server_supports_acls(NFS_SB(dentry->d_sb), NFS4ACL_ACL);
+}
+
+#if defined(CONFIG_NFS_V4_1)
+#define XATTR_NAME_NFSV4_DACL "system.nfs4_dacl"
+
+static int nfs4_xattr_set_nfs4_dacl(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
+ struct dentry *unused, struct inode *inode,
+ const char *key, const void *buf,
+ size_t buflen, int flags)
+{
+ return nfs4_proc_set_acl(inode, buf, buflen, NFS4ACL_DACL);
+}
+
+static int nfs4_xattr_get_nfs4_dacl(const struct xattr_handler *handler,
+ struct dentry *unused, struct inode *inode,
+ const char *key, void *buf, size_t buflen)
+{
+ return nfs4_proc_get_acl(inode, buf, buflen, NFS4ACL_DACL);
+}
+
+static bool nfs4_xattr_list_nfs4_dacl(struct dentry *dentry)
+{
+ return nfs4_server_supports_acls(NFS_SB(dentry->d_sb), NFS4ACL_DACL);
+}
+
+#define XATTR_NAME_NFSV4_SACL "system.nfs4_sacl"
+
+static int nfs4_xattr_set_nfs4_sacl(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
+ struct dentry *unused, struct inode *inode,
+ const char *key, const void *buf,
+ size_t buflen, int flags)
+{
+ return nfs4_proc_set_acl(inode, buf, buflen, NFS4ACL_SACL);
+}
+
+static int nfs4_xattr_get_nfs4_sacl(const struct xattr_handler *handler,
+ struct dentry *unused, struct inode *inode,
+ const char *key, void *buf, size_t buflen)
+{
+ return nfs4_proc_get_acl(inode, buf, buflen, NFS4ACL_SACL);
+}
+
+static bool nfs4_xattr_list_nfs4_sacl(struct dentry *dentry)
+{
+ return nfs4_server_supports_acls(NFS_SB(dentry->d_sb), NFS4ACL_SACL);
}
+#endif
+
#ifdef CONFIG_NFS_V4_SECURITY_LABEL
static int nfs4_xattr_set_nfs4_label(const struct xattr_handler *handler,
@@ -7902,7 +7985,7 @@ static int _nfs4_proc_fs_locations(struct rpc_clnt *client, struct inode *dir,
else
bitmask[1] &= ~FATTR4_WORD1_MOUNTED_ON_FILEID;
- nfs_fattr_init(&fs_locations->fattr);
+ nfs_fattr_init(fs_locations->fattr);
fs_locations->server = server;
fs_locations->nlocations = 0;
status = nfs4_call_sync(client, server, &msg, &args.seq_args, &res.seq_res, 0);
@@ -7967,7 +8050,7 @@ static int _nfs40_proc_get_locations(struct nfs_server *server,
unsigned long now = jiffies;
int status;
- nfs_fattr_init(&locations->fattr);
+ nfs_fattr_init(locations->fattr);
locations->server = server;
locations->nlocations = 0;
@@ -8032,7 +8115,7 @@ static int _nfs41_proc_get_locations(struct nfs_server *server,
};
int status;
- nfs_fattr_init(&locations->fattr);
+ nfs_fattr_init(locations->fattr);
locations->server = server;
locations->nlocations = 0;
@@ -10391,7 +10474,8 @@ static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = {
| NFS_CAP_POSIX_LOCK
| NFS_CAP_STATEID_NFSV41
| NFS_CAP_ATOMIC_OPEN_V1
- | NFS_CAP_LGOPEN,
+ | NFS_CAP_LGOPEN
+ | NFS_CAP_MOVEABLE,
.init_client = nfs41_init_client,
.shutdown_client = nfs41_shutdown_client,
.match_stateid = nfs41_match_stateid,
@@ -10426,7 +10510,8 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = {
| NFS_CAP_LAYOUTSTATS
| NFS_CAP_CLONE
| NFS_CAP_LAYOUTERROR
- | NFS_CAP_READ_PLUS,
+ | NFS_CAP_READ_PLUS
+ | NFS_CAP_MOVEABLE,
.init_client = nfs41_init_client,
.shutdown_client = nfs41_shutdown_client,
.match_stateid = nfs41_match_stateid,
@@ -10587,6 +10672,22 @@ static const struct xattr_handler nfs4_xattr_nfs4_acl_handler = {
.set = nfs4_xattr_set_nfs4_acl,
};
+#if defined(CONFIG_NFS_V4_1)
+static const struct xattr_handler nfs4_xattr_nfs4_dacl_handler = {
+ .name = XATTR_NAME_NFSV4_DACL,
+ .list = nfs4_xattr_list_nfs4_dacl,
+ .get = nfs4_xattr_get_nfs4_dacl,
+ .set = nfs4_xattr_set_nfs4_dacl,
+};
+
+static const struct xattr_handler nfs4_xattr_nfs4_sacl_handler = {
+ .name = XATTR_NAME_NFSV4_SACL,
+ .list = nfs4_xattr_list_nfs4_sacl,
+ .get = nfs4_xattr_get_nfs4_sacl,
+ .set = nfs4_xattr_set_nfs4_sacl,
+};
+#endif
+
#ifdef CONFIG_NFS_V4_2
static const struct xattr_handler nfs4_xattr_nfs4_user_handler = {
.prefix = XATTR_USER_PREFIX,
@@ -10597,6 +10698,10 @@ static const struct xattr_handler nfs4_xattr_nfs4_user_handler = {
const struct xattr_handler *nfs4_xattr_handlers[] = {
&nfs4_xattr_nfs4_acl_handler,
+#if defined(CONFIG_NFS_V4_1)
+ &nfs4_xattr_nfs4_dacl_handler,
+ &nfs4_xattr_nfs4_sacl_handler,
+#endif
#ifdef CONFIG_NFS_V4_SECURITY_LABEL
&nfs4_xattr_nfs4_label_handler,
#endif
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 9e1c987c81e7..9bab3e9c702a 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1602,7 +1602,8 @@ static inline void nfs42_complete_copies(struct nfs4_state_owner *sp,
#endif /* CONFIG_NFS_V4_2 */
static int __nfs4_reclaim_open_state(struct nfs4_state_owner *sp, struct nfs4_state *state,
- const struct nfs4_state_recovery_ops *ops)
+ const struct nfs4_state_recovery_ops *ops,
+ int *lost_locks)
{
struct nfs4_lock_state *lock;
int status;
@@ -1620,7 +1621,7 @@ static int __nfs4_reclaim_open_state(struct nfs4_state_owner *sp, struct nfs4_st
list_for_each_entry(lock, &state->lock_states, ls_locks) {
trace_nfs4_state_lock_reclaim(state, lock);
if (!test_bit(NFS_LOCK_INITIALIZED, &lock->ls_flags))
- pr_warn_ratelimited("NFS: %s: Lock reclaim failed!\n", __func__);
+ *lost_locks += 1;
}
spin_unlock(&state->state_lock);
}
@@ -1630,7 +1631,9 @@ static int __nfs4_reclaim_open_state(struct nfs4_state_owner *sp, struct nfs4_st
return status;
}
-static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs4_state_recovery_ops *ops)
+static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp,
+ const struct nfs4_state_recovery_ops *ops,
+ int *lost_locks)
{
struct nfs4_state *state;
unsigned int loop = 0;
@@ -1666,7 +1669,7 @@ restart:
#endif /* CONFIG_NFS_V4_2 */
refcount_inc(&state->count);
spin_unlock(&sp->so_lock);
- status = __nfs4_reclaim_open_state(sp, state, ops);
+ status = __nfs4_reclaim_open_state(sp, state, ops, lost_locks);
switch (status) {
default:
@@ -1909,6 +1912,7 @@ static int nfs4_do_reclaim(struct nfs_client *clp, const struct nfs4_state_recov
struct rb_node *pos;
LIST_HEAD(freeme);
int status = 0;
+ int lost_locks = 0;
restart:
rcu_read_lock();
@@ -1928,8 +1932,11 @@ restart:
spin_unlock(&clp->cl_lock);
rcu_read_unlock();
- status = nfs4_reclaim_open_state(sp, ops);
+ status = nfs4_reclaim_open_state(sp, ops, &lost_locks);
if (status < 0) {
+ if (lost_locks)
+ pr_warn("NFS: %s: lost %d locks\n",
+ clp->cl_hostname, lost_locks);
set_bit(ops->owner_flag_bit, &sp->so_flags);
nfs4_put_state_owner(sp);
status = nfs4_recovery_handle_error(clp, status);
@@ -1943,6 +1950,9 @@ restart:
}
rcu_read_unlock();
nfs4_free_state_owners(&freeme);
+ if (lost_locks)
+ pr_warn("NFS: %s: lost %d locks\n",
+ clp->cl_hostname, lost_locks);
return 0;
}
@@ -2106,6 +2116,11 @@ static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred
dprintk("<-- %s: no memory\n", __func__);
goto out;
}
+ locations->fattr = nfs_alloc_fattr();
+ if (locations->fattr == NULL) {
+ dprintk("<-- %s: no memory\n", __func__);
+ goto out;
+ }
inode = d_inode(server->super->s_root);
result = nfs4_proc_get_locations(server, NFS_FH(inode), locations,
@@ -2120,7 +2135,7 @@ static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred
if (!locations->nlocations)
goto out;
- if (!(locations->fattr.valid & NFS_ATTR_FATTR_V4_LOCATIONS)) {
+ if (!(locations->fattr->valid & NFS_ATTR_FATTR_V4_LOCATIONS)) {
dprintk("<-- %s: No fs_locations data, migration skipped\n",
__func__);
goto out;
@@ -2145,6 +2160,8 @@ static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred
out:
if (page != NULL)
__free_page(page);
+ if (locations != NULL)
+ kfree(locations->fattr);
kfree(locations);
if (result) {
pr_err("NFS: migration recovery failed (server %s)\n",
@@ -2736,5 +2753,6 @@ again:
goto again;
nfs_put_client(clp);
+ module_put_and_kthread_exit(0);
return 0;
}
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 86a5f6516928..acfe5f4bda48 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -1680,19 +1680,35 @@ encode_restorefh(struct xdr_stream *xdr, struct compound_hdr *hdr)
encode_op_hdr(xdr, OP_RESTOREFH, decode_restorefh_maxsz, hdr);
}
-static void
-encode_setacl(struct xdr_stream *xdr, const struct nfs_setaclargs *arg,
- struct compound_hdr *hdr)
+static void nfs4_acltype_to_bitmap(enum nfs4_acl_type type, __u32 bitmap[2])
{
- __be32 *p;
+ switch (type) {
+ default:
+ bitmap[0] = FATTR4_WORD0_ACL;
+ bitmap[1] = 0;
+ break;
+ case NFS4ACL_DACL:
+ bitmap[0] = 0;
+ bitmap[1] = FATTR4_WORD1_DACL;
+ break;
+ case NFS4ACL_SACL:
+ bitmap[0] = 0;
+ bitmap[1] = FATTR4_WORD1_SACL;
+ }
+}
+
+static void encode_setacl(struct xdr_stream *xdr,
+ const struct nfs_setaclargs *arg,
+ struct compound_hdr *hdr)
+{
+ __u32 bitmap[2];
+
+ nfs4_acltype_to_bitmap(arg->acl_type, bitmap);
encode_op_hdr(xdr, OP_SETATTR, decode_setacl_maxsz, hdr);
encode_nfs4_stateid(xdr, &zero_stateid);
- p = reserve_space(xdr, 2*4);
- *p++ = cpu_to_be32(1);
- *p = cpu_to_be32(FATTR4_WORD0_ACL);
- p = reserve_space(xdr, 4);
- *p = cpu_to_be32(arg->acl_len);
+ xdr_encode_bitmap4(xdr, bitmap, ARRAY_SIZE(bitmap));
+ encode_uint32(xdr, arg->acl_len);
xdr_write_pages(xdr, arg->acl_pages, 0, arg->acl_len);
}
@@ -2587,11 +2603,11 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr,
struct compound_hdr hdr = {
.minorversion = nfs4_xdr_minorversion(&args->seq_args),
};
- const __u32 nfs4_acl_bitmap[1] = {
- [0] = FATTR4_WORD0_ACL,
- };
+ __u32 nfs4_acl_bitmap[2];
uint32_t replen;
+ nfs4_acltype_to_bitmap(args->acl_type, nfs4_acl_bitmap);
+
encode_compound_hdr(xdr, req, &hdr);
encode_sequence(xdr, &args->seq_args, &hdr);
encode_putfh(xdr, args->fh, &hdr);
@@ -5386,7 +5402,7 @@ decode_restorefh(struct xdr_stream *xdr)
}
static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
- struct nfs_getaclres *res)
+ struct nfs_getaclres *res, enum nfs4_acl_type type)
{
unsigned int savep;
uint32_t attrlen,
@@ -5404,26 +5420,39 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
if ((status = decode_attr_length(xdr, &attrlen, &savep)) != 0)
goto out;
- if (unlikely(bitmap[0] & (FATTR4_WORD0_ACL - 1U)))
- return -EIO;
- if (likely(bitmap[0] & FATTR4_WORD0_ACL)) {
-
- /* The bitmap (xdr len + bitmaps) and the attr xdr len words
- * are stored with the acl data to handle the problem of
- * variable length bitmaps.*/
- res->acl_data_offset = xdr_page_pos(xdr);
- res->acl_len = attrlen;
-
- /* Check for receive buffer overflow */
- if (res->acl_len > xdr_stream_remaining(xdr) ||
- res->acl_len + res->acl_data_offset > xdr->buf->page_len) {
- res->acl_flags |= NFS4_ACL_TRUNC;
- dprintk("NFS: acl reply: attrlen %u > page_len %zu\n",
- attrlen, xdr_stream_remaining(xdr));
- }
- } else
- status = -EOPNOTSUPP;
+ switch (type) {
+ default:
+ if (unlikely(bitmap[0] & (FATTR4_WORD0_ACL - 1U)))
+ return -EIO;
+ if (!(bitmap[0] & FATTR4_WORD0_ACL))
+ return -EOPNOTSUPP;
+ break;
+ case NFS4ACL_DACL:
+ if (unlikely(bitmap[0] || bitmap[1] & (FATTR4_WORD1_DACL - 1U)))
+ return -EIO;
+ if (!(bitmap[1] & FATTR4_WORD1_DACL))
+ return -EOPNOTSUPP;
+ break;
+ case NFS4ACL_SACL:
+ if (unlikely(bitmap[0] || bitmap[1] & (FATTR4_WORD1_SACL - 1U)))
+ return -EIO;
+ if (!(bitmap[1] & FATTR4_WORD1_SACL))
+ return -EOPNOTSUPP;
+ }
+ /* The bitmap (xdr len + bitmaps) and the attr xdr len words
+ * are stored with the acl data to handle the problem of
+ * variable length bitmaps.*/
+ res->acl_data_offset = xdr_page_pos(xdr);
+ res->acl_len = attrlen;
+
+ /* Check for receive buffer overflow */
+ if (res->acl_len > xdr_stream_remaining(xdr) ||
+ res->acl_len + res->acl_data_offset > xdr->buf->page_len) {
+ res->acl_flags |= NFS4_ACL_TRUNC;
+ dprintk("NFS: acl reply: attrlen %u > page_len %zu\n",
+ attrlen, xdr_stream_remaining(xdr));
+ }
out:
return status;
}
@@ -6486,7 +6515,7 @@ nfs4_xdr_dec_getacl(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
status = decode_putfh(xdr);
if (status)
goto out;
- status = decode_getacl(xdr, rqstp, res);
+ status = decode_getacl(xdr, rqstp, res, res->acl_type);
out:
return status;
@@ -7051,7 +7080,7 @@ static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req,
if (res->migration) {
xdr_enter_page(xdr, PAGE_SIZE);
status = decode_getfattr_generic(xdr,
- &res->fs_locations->fattr,
+ res->fs_locations->fattr,
NULL, res->fs_locations,
res->fs_locations->server);
if (status)
@@ -7064,7 +7093,7 @@ static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req,
goto out;
xdr_enter_page(xdr, PAGE_SIZE);
status = decode_getfattr_generic(xdr,
- &res->fs_locations->fattr,
+ res->fs_locations->fattr,
NULL, res->fs_locations,
res->fs_locations->server);
}
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 9157dd19b8b4..317cedfa52bf 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -767,6 +767,9 @@ int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr,
.flags = RPC_TASK_ASYNC | flags,
};
+ if (nfs_server_capable(hdr->inode, NFS_CAP_MOVEABLE))
+ task_setup_data.flags |= RPC_TASK_MOVEABLE;
+
hdr->rw_ops->rw_initiate(hdr, &msg, rpc_ops, &task_setup_data, how);
dprintk("NFS: initiated pgio call "
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 856c962273c7..41a9b6b58fb9 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -469,6 +469,7 @@ pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo,
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);
@@ -1917,8 +1918,9 @@ static void nfs_layoutget_begin(struct pnfs_layout_hdr *lo)
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)
@@ -2000,6 +2002,7 @@ lookup_again:
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;
@@ -2024,11 +2027,11 @@ lookup_again:
* 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);
@@ -2128,6 +2131,7 @@ lookup_again:
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);
@@ -2150,6 +2154,12 @@ lookup_again:
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));
@@ -2405,7 +2415,8 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
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 07f11489e4e9..f331f067691b 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -105,6 +105,7 @@ enum {
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 {
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 5e7657374bc3..8ae2c8d1219d 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -120,12 +120,8 @@ static void nfs_readpage_release(struct nfs_page *req, int error)
if (nfs_error_is_fatal_on_server(error) && error != -ETIMEDOUT)
SetPageError(page);
if (nfs_page_group_sync_on_bit(req, PG_UNLOCKPAGE)) {
- struct address_space *mapping = page_file_mapping(page);
-
if (PageUptodate(page))
nfs_fscache_write_page(inode, page);
- else if (!PageError(page) && !PagePrivate(page))
- generic_error_remove_page(mapping, page);
unlock_page(page);
}
nfs_release_request(req);
@@ -333,8 +329,9 @@ out:
* - The error flag is set for this page. This happens only when a
* previous async read operation failed.
*/
-int nfs_readpage(struct file *file, struct page *page)
+int nfs_read_folio(struct file *file, struct folio *folio)
{
+ struct page *page = &folio->page;
struct nfs_readdesc desc;
struct inode *inode = page_file_mapping(page)->host;
int ret;
diff --git a/fs/nfs/symlink.c b/fs/nfs/symlink.c
index 25ba299fdac2..0e27a2e4e68b 100644
--- a/fs/nfs/symlink.c
+++ b/fs/nfs/symlink.c
@@ -26,21 +26,21 @@
* and straight-forward than readdir caching.
*/
-static int nfs_symlink_filler(void *data, struct page *page)
+static int nfs_symlink_filler(struct file *file, struct folio *folio)
{
- struct inode *inode = data;
+ struct inode *inode = folio->mapping->host;
int error;
- error = NFS_PROTO(inode)->readlink(inode, page, 0, PAGE_SIZE);
+ error = NFS_PROTO(inode)->readlink(inode, &folio->page, 0, PAGE_SIZE);
if (error < 0)
goto error;
- SetPageUptodate(page);
- unlock_page(page);
+ folio_mark_uptodate(folio);
+ folio_unlock(folio);
return 0;
error:
- SetPageError(page);
- unlock_page(page);
+ folio_set_error(folio);
+ folio_unlock(folio);
return -EIO;
}
@@ -67,7 +67,7 @@ static const char *nfs_get_link(struct dentry *dentry,
if (err)
return err;
page = read_cache_page(&inode->i_data, 0, nfs_symlink_filler,
- inode);
+ NULL);
if (IS_ERR(page))
return ERR_CAST(page);
}
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 6f325e10056c..9697cd5d2561 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -102,6 +102,10 @@ static void nfs_do_call_unlink(struct inode *inode, struct nfs_unlinkdata *data)
};
struct rpc_task *task;
struct inode *dir = d_inode(data->dentry->d_parent);
+
+ if (nfs_server_capable(inode, NFS_CAP_MOVEABLE))
+ task_setup_data.flags |= RPC_TASK_MOVEABLE;
+
nfs_sb_active(dir->i_sb);
data->args.fh = NFS_FH(dir);
nfs_fattr_init(data->res.dir_attr);
@@ -344,6 +348,10 @@ nfs_async_rename(struct inode *old_dir, struct inode *new_dir,
.flags = RPC_TASK_ASYNC | RPC_TASK_CRED_NOREF,
};
+ if (nfs_server_capable(old_dir, NFS_CAP_MOVEABLE) &&
+ nfs_server_capable(new_dir, NFS_CAP_MOVEABLE))
+ task_setup_data.flags |= RPC_TASK_MOVEABLE;
+
data = kzalloc(sizeof(*data), GFP_KERNEL);
if (data == NULL)
return ERR_PTR(-ENOMEM);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index f00d45cf80ef..69569696dde0 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -603,8 +603,9 @@ static void nfs_write_error(struct nfs_page *req, int error)
* Find an associated nfs write request, and prepare to flush it out
* May return an error if the user signalled nfs_wait_on_request().
*/
-static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
- struct page *page)
+static int nfs_page_async_flush(struct page *page,
+ struct writeback_control *wbc,
+ struct nfs_pageio_descriptor *pgio)
{
struct nfs_page *req;
int ret = 0;
@@ -630,11 +631,11 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
/*
* Remove the problematic req upon fatal errors on the server
*/
- if (nfs_error_is_fatal(ret)) {
- if (nfs_error_is_fatal_on_server(ret))
- goto out_launder;
- } else
- ret = -EAGAIN;
+ if (nfs_error_is_fatal_on_server(ret))
+ goto out_launder;
+ if (wbc->sync_mode == WB_SYNC_NONE)
+ ret = AOP_WRITEPAGE_ACTIVATE;
+ redirty_page_for_writepage(wbc, page);
nfs_redirty_request(req);
pgio->pg_error = 0;
} else
@@ -650,15 +651,8 @@ out_launder:
static int nfs_do_writepage(struct page *page, struct writeback_control *wbc,
struct nfs_pageio_descriptor *pgio)
{
- int ret;
-
nfs_pageio_cond_complete(pgio, page_index(page));
- ret = nfs_page_async_flush(pgio, page);
- if (ret == -EAGAIN) {
- redirty_page_for_writepage(wbc, page);
- ret = AOP_WRITEPAGE_ACTIVATE;
- }
- return ret;
+ return nfs_page_async_flush(page, wbc, pgio);
}
/*
@@ -681,11 +675,7 @@ static int nfs_writepage_locked(struct page *page,
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)
@@ -737,19 +727,19 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
priority = wb_priority(wbc);
}
- nfs_pageio_init_write(&pgio, inode, priority, false,
- &nfs_async_write_completion_ops);
- pgio.pg_io_completion = ioc;
- err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio);
- pgio.pg_error = 0;
- nfs_pageio_complete(&pgio);
+ do {
+ nfs_pageio_init_write(&pgio, inode, priority, false,
+ &nfs_async_write_completion_ops);
+ pgio.pg_io_completion = ioc;
+ err = write_cache_pages(mapping, wbc, nfs_writepages_callback,
+ &pgio);
+ pgio.pg_error = 0;
+ nfs_pageio_complete(&pgio);
+ } while (err < 0 && !nfs_error_is_fatal(err));
nfs_io_completion_put(ioc);
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;
@@ -1444,7 +1434,7 @@ static void nfs_async_write_error(struct list_head *head, int error)
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);
@@ -1719,6 +1709,10 @@ int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data,
.flags = RPC_TASK_ASYNC | flags,
.priority = priority,
};
+
+ if (nfs_server_capable(data->inode, NFS_CAP_MOVEABLE))
+ task_setup_data.flags |= RPC_TASK_MOVEABLE;
+
/* Set up the initial task struct. */
nfs_ops->commit_setup(data, &msg, &task_setup_data.rpc_client);
trace_nfs_initiate_commit(data);
@@ -2125,27 +2119,27 @@ out_error:
}
#ifdef CONFIG_MIGRATION
-int nfs_migrate_page(struct address_space *mapping, struct page *newpage,
- struct page *page, enum migrate_mode mode)
+int nfs_migrate_folio(struct address_space *mapping, struct folio *dst,
+ struct folio *src, enum migrate_mode mode)
{
/*
- * If PagePrivate is set, then the page is currently associated with
+ * If the private flag is set, the folio is currently associated with
* an in-progress read or write request. Don't try to migrate it.
*
* FIXME: we could do this in principle, but we'll need a way to ensure
* that we can safely release the inode reference while holding
- * the page lock.
+ * the folio lock.
*/
- if (PagePrivate(page))
+ if (folio_test_private(src))
return -EBUSY;
- if (PageFsCache(page)) {
+ if (folio_test_fscache(src)) {
if (mode == MIGRATE_ASYNC)
return -EBUSY;
- wait_on_page_fscache(page);
+ folio_wait_fscache(src);
}
- return migrate_page(mapping, newpage, page, mode);
+ return migrate_folio(mapping, dst, src, mode);
}
#endif
Powered by cgit, Gruvboxed by Blaster4385.