summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--Documentation/filesystems/nfs/client-identifier.rst4
-rw-r--r--fs/nfs/dir.c28
-rw-r--r--fs/nfs/direct.c12
-rw-r--r--fs/nfs/file.c124
-rw-r--r--fs/nfs/filelayout/filelayout.c2
-rw-r--r--fs/nfs/internal.h38
-rw-r--r--fs/nfs/nfs42proc.c3
-rw-r--r--fs/nfs/nfs4proc.c4
-rw-r--r--fs/nfs/nfs4trace.h42
-rw-r--r--fs/nfs/nfstrace.h58
-rw-r--r--fs/nfs/pagelist.c217
-rw-r--r--fs/nfs/pnfs.c2
-rw-r--r--fs/nfs/pnfs.h10
-rw-r--r--fs/nfs/pnfs_nfs.c18
-rw-r--r--fs/nfs/read.c94
-rw-r--r--fs/nfs/write.c380
-rw-r--r--include/linux/nfs_fs.h7
-rw-r--r--include/linux/nfs_page.h79
-rw-r--r--net/sunrpc/clnt.c2
-rw-r--r--net/sunrpc/sysfs.c8
20 files changed, 698 insertions, 434 deletions
diff --git a/Documentation/filesystems/nfs/client-identifier.rst b/Documentation/filesystems/nfs/client-identifier.rst
index 5147e15815a1..a94c7a9748d7 100644
--- a/Documentation/filesystems/nfs/client-identifier.rst
+++ b/Documentation/filesystems/nfs/client-identifier.rst
@@ -152,7 +152,7 @@ string:
via the kernel command line, or when the "nfs" module is
loaded.
- /sys/fs/nfs/client/net/identifier
+ /sys/fs/nfs/net/nfs_client/identifier
This virtual file, available since Linux 5.3, is local to the
network namespace in which it is accessed and so can provide
distinction between network namespaces (containers) when the
@@ -164,7 +164,7 @@ then that uniquifier can be used. For example, a uniquifier might
be formed at boot using the container's internal identifier:
sha256sum /etc/machine-id | awk '{print $1}' \\
- > /sys/fs/nfs/client/net/identifier
+ > /sys/fs/nfs/net/nfs_client/identifier
Security considerations
-----------------------
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index f8e420464b77..a41c3ee4549c 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -203,14 +203,14 @@ static void nfs_readdir_page_init_array(struct page *page, u64 last_cookie,
{
struct nfs_cache_array *array;
- array = kmap_atomic(page);
+ array = kmap_local_page(page);
array->change_attr = change_attr;
array->last_cookie = last_cookie;
array->size = 0;
array->page_full = 0;
array->page_is_eof = 0;
array->cookies_are_ordered = 1;
- kunmap_atomic(array);
+ kunmap_local(array);
}
/*
@@ -221,11 +221,11 @@ static void nfs_readdir_clear_array(struct page *page)
struct nfs_cache_array *array;
unsigned int i;
- array = kmap_atomic(page);
+ array = kmap_local_page(page);
for (i = 0; i < array->size; i++)
kfree(array->array[i].name);
array->size = 0;
- kunmap_atomic(array);
+ kunmap_local(array);
}
static void nfs_readdir_free_folio(struct folio *folio)
@@ -371,14 +371,14 @@ static pgoff_t nfs_readdir_page_cookie_hash(u64 cookie)
static bool nfs_readdir_page_validate(struct page *page, u64 last_cookie,
u64 change_attr)
{
- struct nfs_cache_array *array = kmap_atomic(page);
+ struct nfs_cache_array *array = kmap_local_page(page);
int ret = true;
if (array->change_attr != change_attr)
ret = false;
if (nfs_readdir_array_index_cookie(array) != last_cookie)
ret = false;
- kunmap_atomic(array);
+ kunmap_local(array);
return ret;
}
@@ -418,9 +418,9 @@ static u64 nfs_readdir_page_last_cookie(struct page *page)
struct nfs_cache_array *array;
u64 ret;
- array = kmap_atomic(page);
+ array = kmap_local_page(page);
ret = array->last_cookie;
- kunmap_atomic(array);
+ kunmap_local(array);
return ret;
}
@@ -429,9 +429,9 @@ static bool nfs_readdir_page_needs_filling(struct page *page)
struct nfs_cache_array *array;
bool ret;
- array = kmap_atomic(page);
+ array = kmap_local_page(page);
ret = !nfs_readdir_array_is_full(array);
- kunmap_atomic(array);
+ kunmap_local(array);
return ret;
}
@@ -439,9 +439,9 @@ static void nfs_readdir_page_set_eof(struct page *page)
{
struct nfs_cache_array *array;
- array = kmap_atomic(page);
+ array = kmap_local_page(page);
nfs_readdir_array_set_eof(array);
- kunmap_atomic(array);
+ kunmap_local(array);
}
static struct page *nfs_readdir_page_get_next(struct address_space *mapping,
@@ -568,14 +568,14 @@ static int nfs_readdir_search_array(struct nfs_readdir_descriptor *desc)
struct nfs_cache_array *array;
int status;
- array = kmap_atomic(desc->page);
+ array = kmap_local_page(desc->page);
if (desc->dir_cookie == 0)
status = nfs_readdir_search_for_pos(array, desc);
else
status = nfs_readdir_search_for_cookie(array, desc);
- kunmap_atomic(array);
+ kunmap_local(array);
return status;
}
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 1707f46b1335..9a18c5a69ace 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -343,14 +343,12 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
struct nfs_page *req;
unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase);
/* XXX do we need to do the eof zeroing found in async_filler? */
- req = nfs_create_request(dreq->ctx, pagevec[i],
- pgbase, req_len);
+ req = nfs_page_create_from_page(dreq->ctx, pagevec[i],
+ pgbase, pos, req_len);
if (IS_ERR(req)) {
result = PTR_ERR(req);
break;
}
- req->wb_index = pos >> PAGE_SHIFT;
- req->wb_offset = pos & ~PAGE_MASK;
if (!nfs_pageio_add_request(&desc, req)) {
result = desc.pg_error;
nfs_release_request(req);
@@ -802,8 +800,8 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
struct nfs_page *req;
unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase);
- req = nfs_create_request(dreq->ctx, pagevec[i],
- pgbase, req_len);
+ req = nfs_page_create_from_page(dreq->ctx, pagevec[i],
+ pgbase, pos, req_len);
if (IS_ERR(req)) {
result = PTR_ERR(req);
break;
@@ -816,8 +814,6 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
}
nfs_lock_request(req);
- req->wb_index = pos >> PAGE_SHIFT;
- req->wb_offset = pos & ~PAGE_MASK;
if (!nfs_pageio_add_request(&desc, req)) {
result = desc.pg_error;
nfs_unlock_and_release_request(req);
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index b0f3c9339e70..893625eacab9 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -277,27 +277,28 @@ EXPORT_SYMBOL_GPL(nfs_file_fsync);
* and that the new data won't completely replace the old data in
* that range of the file.
*/
-static bool nfs_full_page_write(struct page *page, loff_t pos, unsigned int len)
+static bool nfs_folio_is_full_write(struct folio *folio, loff_t pos,
+ unsigned int len)
{
- unsigned int pglen = nfs_page_length(page);
- unsigned int offset = pos & (PAGE_SIZE - 1);
+ unsigned int pglen = nfs_folio_length(folio);
+ unsigned int offset = offset_in_folio(folio, pos);
unsigned int end = offset + len;
return !pglen || (end >= pglen && !offset);
}
-static bool nfs_want_read_modify_write(struct file *file, struct page *page,
- loff_t pos, unsigned int len)
+static bool nfs_want_read_modify_write(struct file *file, struct folio *folio,
+ loff_t pos, unsigned int len)
{
/*
* Up-to-date pages, those with ongoing or full-page write
* don't need read/modify/write
*/
- if (PageUptodate(page) || PagePrivate(page) ||
- nfs_full_page_write(page, pos, len))
+ if (folio_test_uptodate(folio) || folio_test_private(folio) ||
+ nfs_folio_is_full_write(folio, pos, len))
return false;
- if (pnfs_ld_read_whole_page(file->f_mapping->host))
+ if (pnfs_ld_read_whole_page(file_inode(file)))
return true;
/* Open for reading too? */
if (file->f_mode & FMODE_READ)
@@ -305,6 +306,15 @@ static bool nfs_want_read_modify_write(struct file *file, struct page *page,
return false;
}
+static struct folio *
+nfs_folio_grab_cache_write_begin(struct address_space *mapping, pgoff_t index)
+{
+ unsigned fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE;
+
+ return __filemap_get_folio(mapping, index, fgp_flags,
+ mapping_gfp_mask(mapping));
+}
+
/*
* This does the "real" work of the write. We must allocate and lock the
* page to be sent back to the generic routine, which then copies the
@@ -314,32 +324,31 @@ 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,
- struct page **pagep, void **fsdata)
+ loff_t pos, unsigned len, struct page **pagep,
+ void **fsdata)
{
- int ret;
- pgoff_t index = pos >> PAGE_SHIFT;
- struct page *page;
+ struct folio *folio;
int once_thru = 0;
+ int ret;
dfprintk(PAGECACHE, "NFS: write_begin(%pD2(%lu), %u@%lld)\n",
file, mapping->host->i_ino, len, (long long) pos);
start:
- page = grab_cache_page_write_begin(mapping, index);
- if (!page)
+ folio = nfs_folio_grab_cache_write_begin(mapping, pos >> PAGE_SHIFT);
+ if (!folio)
return -ENOMEM;
- *pagep = page;
+ *pagep = &folio->page;
- ret = nfs_flush_incompatible(file, page);
+ ret = nfs_flush_incompatible(file, folio);
if (ret) {
- unlock_page(page);
- put_page(page);
+ folio_unlock(folio);
+ folio_put(folio);
} else if (!once_thru &&
- nfs_want_read_modify_write(file, page, pos, len)) {
+ nfs_want_read_modify_write(file, folio, pos, len)) {
once_thru = 1;
- ret = nfs_read_folio(file, page_folio(page));
- put_page(page);
+ ret = nfs_read_folio(file, folio);
+ folio_put(folio);
if (!ret)
goto start;
}
@@ -347,11 +356,12 @@ start:
}
static int nfs_write_end(struct file *file, struct address_space *mapping,
- loff_t pos, unsigned len, unsigned copied,
- struct page *page, void *fsdata)
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page, void *fsdata)
{
- unsigned offset = pos & (PAGE_SIZE - 1);
struct nfs_open_context *ctx = nfs_file_open_context(file);
+ struct folio *folio = page_folio(page);
+ unsigned offset = offset_in_folio(folio, pos);
int status;
dfprintk(PAGECACHE, "NFS: write_end(%pD2(%lu), %u@%lld)\n",
@@ -361,26 +371,26 @@ static int nfs_write_end(struct file *file, struct address_space *mapping,
* Zero any uninitialised parts of the page, and then mark the page
* as up to date if it turns out that we're extending the file.
*/
- if (!PageUptodate(page)) {
- unsigned pglen = nfs_page_length(page);
+ if (!folio_test_uptodate(folio)) {
+ size_t fsize = folio_size(folio);
+ unsigned pglen = nfs_folio_length(folio);
unsigned end = offset + copied;
if (pglen == 0) {
- zero_user_segments(page, 0, offset,
- end, PAGE_SIZE);
- SetPageUptodate(page);
+ folio_zero_segments(folio, 0, offset, end, fsize);
+ folio_mark_uptodate(folio);
} else if (end >= pglen) {
- zero_user_segment(page, end, PAGE_SIZE);
+ folio_zero_segment(folio, end, fsize);
if (offset == 0)
- SetPageUptodate(page);
+ folio_mark_uptodate(folio);
} else
- zero_user_segment(page, pglen, PAGE_SIZE);
+ folio_zero_segment(folio, pglen, fsize);
}
- status = nfs_updatepage(file, page, offset, copied);
+ status = nfs_update_folio(file, folio, offset, copied);
- unlock_page(page);
- put_page(page);
+ folio_unlock(folio);
+ folio_put(folio);
if (status < 0)
return status;
@@ -402,14 +412,16 @@ static int nfs_write_end(struct file *file, struct address_space *mapping,
static void nfs_invalidate_folio(struct folio *folio, size_t offset,
size_t length)
{
+ struct inode *inode = folio_file_mapping(folio)->host;
dfprintk(PAGECACHE, "NFS: invalidate_folio(%lu, %zu, %zu)\n",
folio->index, offset, length);
if (offset != 0 || length < folio_size(folio))
return;
/* Cancel any unstarted writes on this page */
- nfs_wb_folio_cancel(folio->mapping->host, folio);
+ nfs_wb_folio_cancel(inode, folio);
folio_wait_fscache(folio);
+ trace_nfs_invalidate_folio(inode, folio);
}
/*
@@ -423,8 +435,13 @@ static bool nfs_release_folio(struct folio *folio, gfp_t gfp)
dfprintk(PAGECACHE, "NFS: release_folio(%p)\n", folio);
/* If the private flag is set, then the folio is not freeable */
- if (folio_test_private(folio))
- return false;
+ if (folio_test_private(folio)) {
+ if ((current_gfp_context(gfp) & GFP_KERNEL) != GFP_KERNEL ||
+ current_is_kswapd())
+ return false;
+ if (nfs_wb_folio(folio_file_mapping(folio)->host, folio) < 0)
+ return false;
+ }
return nfs_fscache_release_folio(folio, gfp);
}
@@ -465,12 +482,15 @@ static void nfs_check_dirty_writeback(struct folio *folio,
static int nfs_launder_folio(struct folio *folio)
{
struct inode *inode = folio->mapping->host;
+ int ret;
dfprintk(PAGECACHE, "NFS: launder_folio(%ld, %llu)\n",
inode->i_ino, folio_pos(folio));
folio_wait_fscache(folio);
- return nfs_wb_page(inode, &folio->page);
+ ret = nfs_wb_folio(inode, folio);
+ trace_nfs_launder_folio_done(inode, folio, ret);
+ return ret;
}
static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file,
@@ -547,22 +567,22 @@ const struct address_space_operations nfs_file_aops = {
*/
static vm_fault_t nfs_vm_page_mkwrite(struct vm_fault *vmf)
{
- struct page *page = vmf->page;
struct file *filp = vmf->vma->vm_file;
struct inode *inode = file_inode(filp);
unsigned pagelen;
vm_fault_t ret = VM_FAULT_NOPAGE;
struct address_space *mapping;
+ struct folio *folio = page_folio(vmf->page);
dfprintk(PAGECACHE, "NFS: vm_page_mkwrite(%pD2(%lu), offset %lld)\n",
- filp, filp->f_mapping->host->i_ino,
- (long long)page_offset(page));
+ filp, filp->f_mapping->host->i_ino,
+ (long long)folio_file_pos(folio));
sb_start_pagefault(inode->i_sb);
/* make sure the cache has finished storing the page */
- if (PageFsCache(page) &&
- wait_on_page_fscache_killable(vmf->page) < 0) {
+ if (folio_test_fscache(folio) &&
+ folio_wait_fscache_killable(folio) < 0) {
ret = VM_FAULT_RETRY;
goto out;
}
@@ -571,25 +591,25 @@ static vm_fault_t nfs_vm_page_mkwrite(struct vm_fault *vmf)
nfs_wait_bit_killable,
TASK_KILLABLE|TASK_FREEZABLE_UNSAFE);
- lock_page(page);
- mapping = page_file_mapping(page);
+ folio_lock(folio);
+ mapping = folio_file_mapping(folio);
if (mapping != inode->i_mapping)
goto out_unlock;
- wait_on_page_writeback(page);
+ folio_wait_writeback(folio);
- pagelen = nfs_page_length(page);
+ pagelen = nfs_folio_length(folio);
if (pagelen == 0)
goto out_unlock;
ret = VM_FAULT_LOCKED;
- if (nfs_flush_incompatible(filp, page) == 0 &&
- nfs_updatepage(filp, page, 0, pagelen) == 0)
+ if (nfs_flush_incompatible(filp, folio) == 0 &&
+ nfs_update_folio(filp, folio, 0, pagelen) == 0)
goto out;
ret = VM_FAULT_SIGBUS;
out_unlock:
- unlock_page(page);
+ folio_unlock(folio);
out:
sb_end_pagefault(inode->i_sb);
return ret;
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index 4974cd18ca46..ce8f8934bca5 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -862,6 +862,8 @@ fl_pnfs_update_layout(struct inode *ino,
status = filelayout_check_deviceid(lo, fl, gfp_flags);
if (status) {
+ pnfs_error_mark_layout_for_return(ino, lseg);
+ pnfs_set_lo_fail(lseg);
pnfs_put_lseg(lseg);
lseg = NULL;
}
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 41468c21291d..2a65fe2a63ab 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -760,17 +760,18 @@ void nfs_super_set_maxbytes(struct super_block *sb, __u64 maxfilesize)
* Record the page as unstable (an extra writeback period) and mark its
* inode as dirty.
*/
-static inline
-void nfs_mark_page_unstable(struct page *page, struct nfs_commit_info *cinfo)
+static inline void nfs_folio_mark_unstable(struct folio *folio,
+ struct nfs_commit_info *cinfo)
{
- if (!cinfo->dreq) {
- struct inode *inode = page_file_mapping(page)->host;
+ if (folio && !cinfo->dreq) {
+ struct inode *inode = folio_file_mapping(folio)->host;
+ long nr = folio_nr_pages(folio);
/* This page is really still in write-back - just that the
* writeback is happening on the server now.
*/
- inc_node_page_state(page, NR_WRITEBACK);
- inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK);
+ node_stat_mod_folio(folio, NR_WRITEBACK, nr);
+ wb_stat_mod(&inode_to_bdi(inode)->wb, WB_WRITEBACK, nr);
__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
}
}
@@ -795,6 +796,24 @@ unsigned int nfs_page_length(struct page *page)
}
/*
+ * Determine the number of bytes of data the page contains
+ */
+static inline size_t nfs_folio_length(struct folio *folio)
+{
+ loff_t i_size = i_size_read(folio_file_mapping(folio)->host);
+
+ if (i_size > 0) {
+ pgoff_t index = folio_index(folio) >> folio_order(folio);
+ pgoff_t end_index = (i_size - 1) >> folio_shift(folio);
+ if (index < end_index)
+ return folio_size(folio);
+ if (index == end_index)
+ return offset_in_folio(folio, i_size - 1) + 1;
+ }
+ return 0;
+}
+
+/*
* Convert a umode to a dirent->d_type
*/
static inline
@@ -807,11 +826,10 @@ unsigned char nfs_umode_to_dtype(umode_t mode)
* Determine the number of pages in an array of length 'len' and
* with a base offset of 'base'
*/
-static inline
-unsigned int nfs_page_array_len(unsigned int base, size_t len)
+static inline unsigned int nfs_page_array_len(unsigned int base, size_t len)
{
- return ((unsigned long)len + (unsigned long)base +
- PAGE_SIZE - 1) >> PAGE_SHIFT;
+ return ((unsigned long)len + (unsigned long)base + PAGE_SIZE - 1) >>
+ PAGE_SHIFT;
}
/*
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index ecb428512fe1..93e306bf4430 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -460,7 +460,8 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
if (err >= 0)
break;
- if (err == -ENOTSUPP &&
+ if ((err == -ENOTSUPP ||
+ err == -NFS4ERR_OFFLOAD_DENIED) &&
nfs42_files_from_same_server(src, dst)) {
err = -EOPNOTSUPP;
break;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index d9c332019d06..22a93ae46cd7 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -10604,7 +10604,9 @@ static void nfs4_disable_swap(struct inode *inode)
/* The state manager thread will now exit once it is
* woken.
*/
- wake_up_var(&NFS_SERVER(inode)->nfs_client->cl_state);
+ struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
+
+ nfs4_schedule_state_manager(clp);
}
static const struct inode_operations nfs4_dir_inode_operations = {
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index 214bc56f92d2..d27919d7241d 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -292,32 +292,34 @@ TRACE_DEFINE_ENUM(NFS4CLNT_MOVED);
TRACE_DEFINE_ENUM(NFS4CLNT_LEASE_MOVED);
TRACE_DEFINE_ENUM(NFS4CLNT_DELEGATION_EXPIRED);
TRACE_DEFINE_ENUM(NFS4CLNT_RUN_MANAGER);
+TRACE_DEFINE_ENUM(NFS4CLNT_MANAGER_AVAILABLE);
TRACE_DEFINE_ENUM(NFS4CLNT_RECALL_RUNNING);
TRACE_DEFINE_ENUM(NFS4CLNT_RECALL_ANY_LAYOUT_READ);
TRACE_DEFINE_ENUM(NFS4CLNT_RECALL_ANY_LAYOUT_RW);
+TRACE_DEFINE_ENUM(NFS4CLNT_DELEGRETURN_DELAYED);
#define show_nfs4_clp_state(state) \
__print_flags(state, "|", \
- { NFS4CLNT_MANAGER_RUNNING, "MANAGER_RUNNING" }, \
- { NFS4CLNT_CHECK_LEASE, "CHECK_LEASE" }, \
- { NFS4CLNT_LEASE_EXPIRED, "LEASE_EXPIRED" }, \
- { NFS4CLNT_RECLAIM_REBOOT, "RECLAIM_REBOOT" }, \
- { NFS4CLNT_RECLAIM_NOGRACE, "RECLAIM_NOGRACE" }, \
- { NFS4CLNT_DELEGRETURN, "DELEGRETURN" }, \
- { NFS4CLNT_SESSION_RESET, "SESSION_RESET" }, \
- { NFS4CLNT_LEASE_CONFIRM, "LEASE_CONFIRM" }, \
- { NFS4CLNT_SERVER_SCOPE_MISMATCH, \
- "SERVER_SCOPE_MISMATCH" }, \
- { NFS4CLNT_PURGE_STATE, "PURGE_STATE" }, \
- { NFS4CLNT_BIND_CONN_TO_SESSION, \
- "BIND_CONN_TO_SESSION" }, \
- { NFS4CLNT_MOVED, "MOVED" }, \
- { NFS4CLNT_LEASE_MOVED, "LEASE_MOVED" }, \
- { NFS4CLNT_DELEGATION_EXPIRED, "DELEGATION_EXPIRED" }, \
- { NFS4CLNT_RUN_MANAGER, "RUN_MANAGER" }, \
- { NFS4CLNT_RECALL_RUNNING, "RECALL_RUNNING" }, \
- { NFS4CLNT_RECALL_ANY_LAYOUT_READ, "RECALL_ANY_LAYOUT_READ" }, \
- { NFS4CLNT_RECALL_ANY_LAYOUT_RW, "RECALL_ANY_LAYOUT_RW" })
+ { BIT(NFS4CLNT_MANAGER_RUNNING), "MANAGER_RUNNING" }, \
+ { BIT(NFS4CLNT_CHECK_LEASE), "CHECK_LEASE" }, \
+ { BIT(NFS4CLNT_LEASE_EXPIRED), "LEASE_EXPIRED" }, \
+ { BIT(NFS4CLNT_RECLAIM_REBOOT), "RECLAIM_REBOOT" }, \
+ { BIT(NFS4CLNT_RECLAIM_NOGRACE), "RECLAIM_NOGRACE" }, \
+ { BIT(NFS4CLNT_DELEGRETURN), "DELEGRETURN" }, \
+ { BIT(NFS4CLNT_SESSION_RESET), "SESSION_RESET" }, \
+ { BIT(NFS4CLNT_LEASE_CONFIRM), "LEASE_CONFIRM" }, \
+ { BIT(NFS4CLNT_SERVER_SCOPE_MISMATCH), "SERVER_SCOPE_MISMATCH" }, \
+ { BIT(NFS4CLNT_PURGE_STATE), "PURGE_STATE" }, \
+ { BIT(NFS4CLNT_BIND_CONN_TO_SESSION), "BIND_CONN_TO_SESSION" }, \
+ { BIT(NFS4CLNT_MOVED), "MOVED" }, \
+ { BIT(NFS4CLNT_LEASE_MOVED), "LEASE_MOVED" }, \
+ { BIT(NFS4CLNT_DELEGATION_EXPIRED), "DELEGATION_EXPIRED" }, \
+ { BIT(NFS4CLNT_RUN_MANAGER), "RUN_MANAGER" }, \
+ { BIT(NFS4CLNT_MANAGER_AVAILABLE), "MANAGER_AVAILABLE" }, \
+ { BIT(NFS4CLNT_RECALL_RUNNING), "RECALL_RUNNING" }, \
+ { BIT(NFS4CLNT_RECALL_ANY_LAYOUT_READ), "RECALL_ANY_LAYOUT_READ" }, \
+ { BIT(NFS4CLNT_RECALL_ANY_LAYOUT_RW), "RECALL_ANY_LAYOUT_RW" }, \
+ { BIT(NFS4CLNT_DELEGRETURN_DELAYED), "DELERETURN_DELAYED" })
TRACE_EVENT(nfs4_state_mgr,
TP_PROTO(
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 642f6921852f..a778713343df 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -152,8 +152,6 @@ DEFINE_NFS_INODE_EVENT(nfs_getattr_enter);
DEFINE_NFS_INODE_EVENT_DONE(nfs_getattr_exit);
DEFINE_NFS_INODE_EVENT(nfs_setattr_enter);
DEFINE_NFS_INODE_EVENT_DONE(nfs_setattr_exit);
-DEFINE_NFS_INODE_EVENT(nfs_writeback_page_enter);
-DEFINE_NFS_INODE_EVENT_DONE(nfs_writeback_page_exit);
DEFINE_NFS_INODE_EVENT(nfs_writeback_inode_enter);
DEFINE_NFS_INODE_EVENT_DONE(nfs_writeback_inode_exit);
DEFINE_NFS_INODE_EVENT(nfs_fsync_enter);
@@ -933,13 +931,13 @@ TRACE_EVENT(nfs_sillyrename_unlink,
)
);
-TRACE_EVENT(nfs_aop_readpage,
+DECLARE_EVENT_CLASS(nfs_folio_event,
TP_PROTO(
const struct inode *inode,
- struct page *page
+ struct folio *folio
),
- TP_ARGS(inode, page),
+ TP_ARGS(inode, folio),
TP_STRUCT__entry(
__field(dev_t, dev)
@@ -947,6 +945,7 @@ TRACE_EVENT(nfs_aop_readpage,
__field(u64, fileid)
__field(u64, version)
__field(loff_t, offset)
+ __field(u32, count)
),
TP_fast_assign(
@@ -956,26 +955,36 @@ TRACE_EVENT(nfs_aop_readpage,
__entry->fileid = nfsi->fileid;
__entry->fhandle = nfs_fhandle_hash(&nfsi->fh);
__entry->version = inode_peek_iversion_raw(inode);
- __entry->offset = page_index(page) << PAGE_SHIFT;
+ __entry->offset = folio_file_pos(folio);
+ __entry->count = nfs_folio_length(folio);
),
TP_printk(
- "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu offset=%lld",
+ "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu "
+ "offset=%lld count=%u",
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
__entry->fhandle, __entry->version,
- __entry->offset
+ __entry->offset, __entry->count
)
);
-TRACE_EVENT(nfs_aop_readpage_done,
+#define DEFINE_NFS_FOLIO_EVENT(name) \
+ DEFINE_EVENT(nfs_folio_event, name, \
+ TP_PROTO( \
+ const struct inode *inode, \
+ struct folio *folio \
+ ), \
+ TP_ARGS(inode, folio))
+
+DECLARE_EVENT_CLASS(nfs_folio_event_done,
TP_PROTO(
const struct inode *inode,
- struct page *page,
+ struct folio *folio,
int ret
),
- TP_ARGS(inode, page, ret),
+ TP_ARGS(inode, folio, ret),
TP_STRUCT__entry(
__field(dev_t, dev)
@@ -984,6 +993,7 @@ TRACE_EVENT(nfs_aop_readpage_done,
__field(u64, fileid)
__field(u64, version)
__field(loff_t, offset)
+ __field(u32, count)
),
TP_fast_assign(
@@ -993,19 +1003,39 @@ TRACE_EVENT(nfs_aop_readpage_done,
__entry->fileid = nfsi->fileid;
__entry->fhandle = nfs_fhandle_hash(&nfsi->fh);
__entry->version = inode_peek_iversion_raw(inode);
- __entry->offset = page_index(page) << PAGE_SHIFT;
+ __entry->offset = folio_file_pos(folio);
+ __entry->count = nfs_folio_length(folio);
__entry->ret = ret;
),
TP_printk(
- "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu offset=%lld ret=%d",
+ "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu "
+ "offset=%lld count=%u ret=%d",
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
__entry->fhandle, __entry->version,
- __entry->offset, __entry->ret
+ __entry->offset, __entry->count, __entry->ret
)
);
+#define DEFINE_NFS_FOLIO_EVENT_DONE(name) \
+ DEFINE_EVENT(nfs_folio_event_done, name, \
+ TP_PROTO( \
+ const struct inode *inode, \
+ struct folio *folio, \
+ int ret \
+ ), \
+ TP_ARGS(inode, folio, ret))
+
+DEFINE_NFS_FOLIO_EVENT(nfs_aop_readpage);
+DEFINE_NFS_FOLIO_EVENT_DONE(nfs_aop_readpage_done);
+
+DEFINE_NFS_FOLIO_EVENT(nfs_writeback_folio);
+DEFINE_NFS_FOLIO_EVENT_DONE(nfs_writeback_folio_done);
+
+DEFINE_NFS_FOLIO_EVENT(nfs_invalidate_folio);
+DEFINE_NFS_FOLIO_EVENT_DONE(nfs_launder_folio_done);
+
TRACE_EVENT(nfs_aop_readahead,
TP_PROTO(
const struct inode *inode,
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 779bfc37233c..64fa8de199de 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -32,6 +32,42 @@
static struct kmem_cache *nfs_page_cachep;
static const struct rpc_call_ops nfs_pgio_common_ops;
+struct nfs_page_iter_page {
+ const struct nfs_page *req;
+ size_t count;
+};
+
+static void nfs_page_iter_page_init(struct nfs_page_iter_page *i,
+ const struct nfs_page *req)
+{
+ i->req = req;
+ i->count = 0;
+}
+
+static void nfs_page_iter_page_advance(struct nfs_page_iter_page *i, size_t sz)
+{
+ const struct nfs_page *req = i->req;
+ size_t tmp = i->count + sz;
+
+ i->count = (tmp < req->wb_bytes) ? tmp : req->wb_bytes;
+}
+
+static struct page *nfs_page_iter_page_get(struct nfs_page_iter_page *i)
+{
+ const struct nfs_page *req = i->req;
+ struct page *page;
+
+ if (i->count != req->wb_bytes) {
+ size_t base = i->count + req->wb_pgbase;
+ size_t len = PAGE_SIZE - offset_in_page(base);
+
+ page = nfs_page_to_page(req, base);
+ nfs_page_iter_page_advance(i, len);
+ return page;
+ }
+ return NULL;
+}
+
static struct nfs_pgio_mirror *
nfs_pgio_get_mirror(struct nfs_pageio_descriptor *desc, u32 idx)
{
@@ -391,7 +427,7 @@ nfs_page_group_init(struct nfs_page *req, struct nfs_page *prev)
* has extra ref from the write/commit path to handle handoff
* between write and commit lists. */
if (test_bit(PG_INODE_REF, &prev->wb_head->wb_flags)) {
- inode = page_file_mapping(req->wb_page)->host;
+ inode = nfs_page_to_inode(req);
set_bit(PG_INODE_REF, &req->wb_flags);
kref_get(&req->wb_kref);
atomic_long_inc(&NFS_I(inode)->nrequests);
@@ -431,10 +467,9 @@ out:
nfs_release_request(head);
}
-static struct nfs_page *
-__nfs_create_request(struct nfs_lock_context *l_ctx, struct page *page,
- unsigned int pgbase, unsigned int offset,
- unsigned int count)
+static struct nfs_page *nfs_page_create(struct nfs_lock_context *l_ctx,
+ unsigned int pgbase, pgoff_t index,
+ unsigned int offset, unsigned int count)
{
struct nfs_page *req;
struct nfs_open_context *ctx = l_ctx->open_context;
@@ -453,42 +488,90 @@ __nfs_create_request(struct nfs_lock_context *l_ctx, struct page *page,
/* Initialize the request struct. Initially, we assume a
* long write-back delay. This will be adjusted in
* update_nfs_request below if the region is not locked. */
- req->wb_page = page;
- if (page) {
- req->wb_index = page_index(page);
- get_page(page);
- }
- req->wb_offset = offset;
- req->wb_pgbase = pgbase;
- req->wb_bytes = count;
+ req->wb_pgbase = pgbase;
+ req->wb_index = index;
+ req->wb_offset = offset;
+ req->wb_bytes = count;
kref_init(&req->wb_kref);
req->wb_nio = 0;
return req;
}
+static void nfs_page_assign_folio(struct nfs_page *req, struct folio *folio)
+{
+ if (folio != NULL) {
+ req->wb_folio = folio;
+ folio_get(folio);
+ set_bit(PG_FOLIO, &req->wb_flags);
+ }
+}
+
+static void nfs_page_assign_page(struct nfs_page *req, struct page *page)
+{
+ if (page != NULL) {
+ req->wb_page = page;
+ get_page(page);
+ }
+}
+
/**
- * nfs_create_request - Create an NFS read/write request.
+ * nfs_page_create_from_page - Create an NFS read/write request.
* @ctx: open context to use
* @page: page to write
- * @offset: starting offset within the page for the write
+ * @pgbase: starting offset within the page for the write
+ * @offset: file offset for the write
* @count: number of bytes to read/write
*
* The page must be locked by the caller. This makes sure we never
* create two different requests for the same page.
* User should ensure it is safe to sleep in this function.
*/
-struct nfs_page *
-nfs_create_request(struct nfs_open_context *ctx, struct page *page,
- unsigned int offset, unsigned int count)
+struct nfs_page *nfs_page_create_from_page(struct nfs_open_context *ctx,
+ struct page *page,
+ unsigned int pgbase, loff_t offset,
+ unsigned int count)
+{
+ struct nfs_lock_context *l_ctx = nfs_get_lock_context(ctx);
+ struct nfs_page *ret;
+
+ if (IS_ERR(l_ctx))
+ return ERR_CAST(l_ctx);
+ ret = nfs_page_create(l_ctx, pgbase, offset >> PAGE_SHIFT,
+ offset_in_page(offset), count);
+ if (!IS_ERR(ret)) {
+ nfs_page_assign_page(ret, page);
+ nfs_page_group_init(ret, NULL);
+ }
+ nfs_put_lock_context(l_ctx);
+ return ret;
+}
+
+/**
+ * nfs_page_create_from_folio - Create an NFS read/write request.
+ * @ctx: open context to use
+ * @folio: folio to write
+ * @offset: starting offset within the folio for the write
+ * @count: number of bytes to read/write
+ *
+ * The page must be locked by the caller. This makes sure we never
+ * create two different requests for the same page.
+ * User should ensure it is safe to sleep in this function.
+ */
+struct nfs_page *nfs_page_create_from_folio(struct nfs_open_context *ctx,
+ struct folio *folio,
+ unsigned int of