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, 25 insertions, 15 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 657bcd887fdb..ca8c8d889eef 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3982,21 +3982,24 @@ ssize_t generic_perform_write(struct kiocb *iocb, struct iov_iter *i)
 	loff_t pos = iocb->ki_pos;
 	struct address_space *mapping = file->f_mapping;
 	const struct address_space_operations *a_ops = mapping->a_ops;
+	size_t chunk = mapping_max_folio_size(mapping);
 	long status = 0;
 	ssize_t written = 0;
 
 	do {
 		struct page *page;
-		unsigned long offset;	/* Offset into pagecache page */
-		unsigned long bytes;	/* Bytes to write to page */
+		struct folio *folio;
+		size_t offset;		/* Offset into folio */
+		size_t bytes;		/* Bytes to write to folio */
 		size_t copied;		/* Bytes copied from user */
 		void *fsdata = NULL;
 
-		offset = (pos & (PAGE_SIZE - 1));
-		bytes = min_t(unsigned long, PAGE_SIZE - offset,
-						iov_iter_count(i));
+		bytes = iov_iter_count(i);
+retry:
+		offset = pos & (chunk - 1);
+		bytes = min(chunk - offset, bytes);
+		balance_dirty_pages_ratelimited(mapping);
 
-again:
 		/*
 		 * Bring in the user page that we will copy from _first_.
 		 * Otherwise there's a nasty deadlock on copying from the
@@ -4018,11 +4021,16 @@ again:
 		if (unlikely(status < 0))
 			break;
 
+		folio = page_folio(page);
+		offset = offset_in_folio(folio, pos);
+		if (bytes > folio_size(folio) - offset)
+			bytes = folio_size(folio) - offset;
+
 		if (mapping_writably_mapped(mapping))
-			flush_dcache_page(page);
+			flush_dcache_folio(folio);
 
-		copied = copy_page_from_iter_atomic(page, offset, bytes, i);
-		flush_dcache_page(page);
+		copied = copy_folio_from_iter_atomic(folio, offset, bytes, i);
+		flush_dcache_folio(folio);
 
 		status = a_ops->write_end(file, mapping, pos, bytes, copied,
 						page, fsdata);
@@ -4040,14 +4048,16 @@ again:
 			 * halfway through, might be a race with munmap,
 			 * might be severe memory pressure.
 			 */
-			if (copied)
+			if (chunk > PAGE_SIZE)
+				chunk /= 2;
+			if (copied) {
 				bytes = copied;
-			goto again;
+				goto retry;
+			}
+		} else {
+			pos += status;
+			written += status;
 		}
-		pos += status;
-		written += status;
-
-		balance_dirty_pages_ratelimited(mapping);
 	} while (iov_iter_count(i));
 
 	if (!written)