Merge tag 'nfs-for-6.11-1' of git://git.linux-nfs.org/projects/anna/linux-nfs

Pull NFS client updates from Anna Schumaker:
 "New Features:
   - Add support for large folios
   - Implement rpcrdma generic device removal notification
   - Add client support for attribute delegations
   - Use a LAYOUTRETURN during reboot recovery to report layoutstats
     and errors
   - Improve throughput for random buffered writes
   - Add NVMe support to pnfs/blocklayout

  Bugfixes:
   - Fix rpcrdma_reqs_reset()
   - Avoid soft lockups when using UDP
   - Fix an nfs/blocklayout premature PR key unregestration
   - Another fix for EXCHGID4_FLAG_USE_PNFS_DS for DS server
   - Do not extend writes to the entire folio
   - Pass explicit offset and count values to tracepoints
   - Fix a race to wake up sleeping SUNRPC sync tasks
   - Fix gss_status tracepoint output

  Cleanups:
   - Add missing MODULE_DESCRIPTION() macros
   - Add blocklayout / SCSI layout tracepoints
   - Remove asm-generic headers from xprtrdma verbs.c
   - Remove unused 'struct mnt_fhstatus'
   - Other delegation related cleanups
   - Other folio related cleanups
   - Other pNFS related cleanups
   - Other xprtrdma cleanups"

* tag 'nfs-for-6.11-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (63 commits)
  SUNRPC: Fixup gss_status tracepoint error output
  SUNRPC: Fix a race to wake a sync task
  nfs: split nfs_read_folio
  nfs: pass explicit offset/count to trace events
  nfs: do not extend writes to the entire folio
  nfs/blocklayout: add support for NVMe
  nfs: remove nfs_page_length
  nfs: remove the unused max_deviceinfo_size field from struct pnfs_layoutdriver_type
  nfs: don't reuse partially completed requests in nfs_lock_and_join_requests
  nfs: move nfs_wait_on_request to write.c
  nfs: fold nfs_page_group_lock_subrequests into nfs_lock_and_join_requests
  nfs: fold nfs_folio_find_and_lock_request into nfs_lock_and_join_requests
  nfs: simplify nfs_folio_find_and_lock_request
  nfs: remove nfs_folio_private_request
  nfs: remove dead code for the old swap over NFS implementation
  NFSv4.1 another fix for EXCHGID4_FLAG_USE_PNFS_DS for DS server
  nfs: Block on write congestion
  nfs: Properly initialize server->writeback
  nfs: Drop pointless check from nfs_commit_release_pages()
  nfs/blocklayout: SCSI layout trace points for reservation key reg/unreg
  ...

1 files changed, 48 insertions, 30 deletions

diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index cca80b5f54e0..a6103333b666 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -28,6 +28,7 @@
 #include "fscache.h"
 #include "pnfs.h"
 #include "nfstrace.h"
+#include "delegation.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PAGECACHE
 
@@ -286,7 +287,7 @@ int nfs_read_add_folio(struct nfs_pageio_descriptor *pgio,
 		       struct nfs_open_context *ctx,
 		       struct folio *folio)
 {
-	struct inode *inode = folio_file_mapping(folio)->host;
+	struct inode *inode = folio->mapping->host;
 	struct nfs_server *server = NFS_SERVER(inode);
 	size_t fsize = folio_size(folio);
 	unsigned int rsize = server->rsize;
@@ -322,21 +323,57 @@ out:
 }
 
 /*
- * Read a page over NFS.
- * We read the page synchronously in the following case:
- *  -	The error flag is set for this page. This happens only when a
- *	previous async read operation failed.
+ * Actually read a folio over the wire.
  */
-int nfs_read_folio(struct file *file, struct folio *folio)
+static int nfs_do_read_folio(struct file *file, struct folio *folio)
 {
 	struct inode *inode = file_inode(file);
 	struct nfs_pageio_descriptor pgio;
 	struct nfs_open_context *ctx;
 	int ret;
 
-	trace_nfs_aop_readpage(inode, folio);
+	ctx = get_nfs_open_context(nfs_file_open_context(file));
+
+	xchg(&ctx->error, 0);
+	nfs_pageio_init_read(&pgio, inode, false,
+			     &nfs_async_read_completion_ops);
+
+	ret = nfs_read_add_folio(&pgio, ctx, folio);
+	if (ret)
+		goto out_put;
+
+	nfs_pageio_complete_read(&pgio);
+	nfs_update_delegated_atime(inode);
+	if (pgio.pg_error < 0) {
+		ret = pgio.pg_error;
+		goto out_put;
+	}
+
+	ret = folio_wait_locked_killable(folio);
+	if (!folio_test_uptodate(folio) && !ret)
+		ret = xchg(&ctx->error, 0);
+
+out_put:
+	put_nfs_open_context(ctx);
+	return ret;
+}
+
+/*
+ * Synchronously read a folio.
+ *
+ * This is not heavily used as most users to try an asynchronous
+ * large read through ->readahead first.
+ */
+int nfs_read_folio(struct file *file, struct folio *folio)
+{
+	struct inode *inode = file_inode(file);
+	loff_t pos = folio_pos(folio);
+	size_t len = folio_size(folio);
+	int ret;
+
+	trace_nfs_aop_readpage(inode, pos, len);
 	nfs_inc_stats(inode, NFSIOS_VFSREADPAGE);
-	task_io_account_read(folio_size(folio));
+	task_io_account_read(len);
 
 	/*
 	 * Try to flush any pending writes to the file..
@@ -356,30 +393,10 @@ int nfs_read_folio(struct file *file, struct folio *folio)
 		goto out_unlock;
 
 	ret = nfs_netfs_read_folio(file, folio);
-	if (!ret)
-		goto out;
-
-	ctx = get_nfs_open_context(nfs_file_open_context(file));
-
-	xchg(&ctx->error, 0);
-	nfs_pageio_init_read(&pgio, inode, false,
-			     &nfs_async_read_completion_ops);
-
-	ret = nfs_read_add_folio(&pgio, ctx, folio);
 	if (ret)
-		goto out_put;
-
-	nfs_pageio_complete_read(&pgio);
-	ret = pgio.pg_error < 0 ? pgio.pg_error : 0;
-	if (!ret) {
-		ret = folio_wait_locked_killable(folio);
-		if (!folio_test_uptodate(folio) && !ret)
-			ret = xchg(&ctx->error, 0);
-	}
-out_put:
-	put_nfs_open_context(ctx);
+		ret = nfs_do_read_folio(file, folio);
 out:
-	trace_nfs_aop_readpage_done(inode, folio, ret);
+	trace_nfs_aop_readpage_done(inode, pos, len, ret);
 	return ret;
 out_unlock:
 	folio_unlock(folio);
@@ -426,6 +443,7 @@ void nfs_readahead(struct readahead_control *ractl)
 	}
 
 	nfs_pageio_complete_read(&pgio);
+	nfs_update_delegated_atime(inode);
 
 	put_nfs_open_context(ctx);
 out: