Merge tag 'vfs-6.12.netfs' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull netfs updates from Christian Brauner:
 "This contains the work to improve read/write performance for the new
  netfs library.

  The main performance enhancing changes are:

   - Define a structure, struct folio_queue, and a new iterator type,
     ITER_FOLIOQ, to hold a buffer as a replacement for ITER_XARRAY. See
     that patch for questions about naming and form.

     ITER_FOLIOQ is provided as a replacement for ITER_XARRAY. The
     problem with an xarray is that accessing it requires the use of a
     lock (typically the RCU read lock) - and this means that we can't
     supply iterate_and_advance() with a step function that might sleep
     (crypto for example) without having to drop the lock between pages.
     ITER_FOLIOQ is the iterator for a chain of folio_queue structs,
     where each folio_queue holds a small list of folios. A folio_queue
     struct is a simpler structure than xarray and is not subject to
     concurrent manipulation by the VM. folio_queue is used rather than
     a bvec[] as it can form lists of indefinite size, adding to one end
     and removing from the other on the fly.

   - Provide a copy_folio_from_iter() wrapper.

   - Make cifs RDMA support ITER_FOLIOQ.

   - Use folio queues in the write-side helpers instead of xarrays.

   - Add a function to reset the iterator in a subrequest.

   - Simplify the write-side helpers to use sheaves to skip gaps rather
     than trying to work out where gaps are.

   - In afs, make the read subrequests asynchronous, putting them into
     work items to allow the next patch to do progressive
     unlocking/reading.

   - Overhaul the read-side helpers to improve performance.

   - Fix the caching of a partial block at the end of a file.

   - Allow a store to be cancelled.

  Then some changes for cifs to make it use folio queues instead of
  xarrays for crypto bufferage:

   - Use raw iteration functions rather than manually coding iteration
     when hashing data.

   - Switch to using folio_queue for crypto buffers.

   - Remove the xarray bits.

  Make some adjustments to the /proc/fs/netfs/stats file such that:

   - All the netfs stats lines begin 'Netfs:' but change this to
     something a bit more useful.

   - Add a couple of stats counters to track the numbers of skips and
     waits on the per-inode writeback serialisation lock to make it
     easier to check for this as a source of performance loss.

  Miscellaneous work:

   - Ensure that the sb_writers lock is taken around
     vfs_{set,remove}xattr() in the cachefiles code.

   - Reduce the number of conditional branches in netfs_perform_write().

   - Move the CIFS_INO_MODIFIED_ATTR flag to the netfs_inode struct and
     remove cifs_post_modify().

   - Move the max_len/max_nr_segs members from netfs_io_subrequest to
     netfs_io_request as they're only needed for one subreq at a time.

   - Add an 'unknown' source value for tracing purposes.

   - Remove NETFS_COPY_TO_CACHE as it's no longer used.

   - Set the request work function up front at allocation time.

   - Use bh-disabling spinlocks for rreq->lock as cachefiles completion
     may be run from block-filesystem DIO completion in softirq context.

   - Remove fs/netfs/io.c"

* tag 'vfs-6.12.netfs' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (25 commits)
  docs: filesystems: corrected grammar of netfs page
  cifs: Don't support ITER_XARRAY
  cifs: Switch crypto buffer to use a folio_queue rather than an xarray
  cifs: Use iterate_and_advance*() routines directly for hashing
  netfs: Cancel dirty folios that have no storage destination
  cachefiles, netfs: Fix write to partial block at EOF
  netfs: Remove fs/netfs/io.c
  netfs: Speed up buffered reading
  afs: Make read subreqs async
  netfs: Simplify the writeback code
  netfs: Provide an iterator-reset function
  netfs: Use new folio_queue data type and iterator instead of xarray iter
  cifs: Provide the capability to extract from ITER_FOLIOQ to RDMA SGEs
  iov_iter: Provide copy_folio_from_iter()
  mm: Define struct folio_queue and ITER_FOLIOQ to handle a sequence of folios
  netfs: Use bh-disabling spinlocks for rreq->lock
  netfs: Set the request work function upon allocation
  netfs: Remove NETFS_COPY_TO_CACHE
  netfs: Reserve netfs_sreq_source 0 as unset/unknown
  netfs: Move max_len/max_nr_segs from netfs_io_subrequest to netfs_io_stream
  ...

1 files changed, 238 insertions, 2 deletions

diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 4a6a9f419bd7..97003155bfac 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -527,6 +527,39 @@ static void iov_iter_iovec_advance(struct iov_iter *i, size_t size)
 	i->__iov = iov;
 }
 
+static void iov_iter_folioq_advance(struct iov_iter *i, size_t size)
+{
+	const struct folio_queue *folioq = i->folioq;
+	unsigned int slot = i->folioq_slot;
+
+	if (!i->count)
+		return;
+	i->count -= size;
+
+	if (slot >= folioq_nr_slots(folioq)) {
+		folioq = folioq->next;
+		slot = 0;
+	}
+
+	size += i->iov_offset; /* From beginning of current segment. */
+	do {
+		size_t fsize = folioq_folio_size(folioq, slot);
+
+		if (likely(size < fsize))
+			break;
+		size -= fsize;
+		slot++;
+		if (slot >= folioq_nr_slots(folioq) && folioq->next) {
+			folioq = folioq->next;
+			slot = 0;
+		}
+	} while (size);
+
+	i->iov_offset = size;
+	i->folioq_slot = slot;
+	i->folioq = folioq;
+}
+
 void iov_iter_advance(struct iov_iter *i, size_t size)
 {
 	if (unlikely(i->count < size))
@@ -539,12 +572,40 @@ void iov_iter_advance(struct iov_iter *i, size_t size)
 		iov_iter_iovec_advance(i, size);
 	} else if (iov_iter_is_bvec(i)) {
 		iov_iter_bvec_advance(i, size);
+	} else if (iov_iter_is_folioq(i)) {
+		iov_iter_folioq_advance(i, size);
 	} else if (iov_iter_is_discard(i)) {
 		i->count -= size;
 	}
 }
 EXPORT_SYMBOL(iov_iter_advance);
 
+static void iov_iter_folioq_revert(struct iov_iter *i, size_t unroll)
+{
+	const struct folio_queue *folioq = i->folioq;
+	unsigned int slot = i->folioq_slot;
+
+	for (;;) {
+		size_t fsize;
+
+		if (slot == 0) {
+			folioq = folioq->prev;
+			slot = folioq_nr_slots(folioq);
+		}
+		slot--;
+
+		fsize = folioq_folio_size(folioq, slot);
+		if (unroll <= fsize) {
+			i->iov_offset = fsize - unroll;
+			break;
+		}
+		unroll -= fsize;
+	}
+
+	i->folioq_slot = slot;
+	i->folioq = folioq;
+}
+
 void iov_iter_revert(struct iov_iter *i, size_t unroll)
 {
 	if (!unroll)
@@ -576,6 +637,9 @@ void iov_iter_revert(struct iov_iter *i, size_t unroll)
 			}
 			unroll -= n;
 		}
+	} else if (iov_iter_is_folioq(i)) {
+		i->iov_offset = 0;
+		iov_iter_folioq_revert(i, unroll);
 	} else { /* same logics for iovec and kvec */
 		const struct iovec *iov = iter_iov(i);
 		while (1) {
@@ -603,6 +667,9 @@ size_t iov_iter_single_seg_count(const struct iov_iter *i)
 		if (iov_iter_is_bvec(i))
 			return min(i->count, i->bvec->bv_len - i->iov_offset);
 	}
+	if (unlikely(iov_iter_is_folioq(i)))
+		return !i->count ? 0 :
+			umin(folioq_folio_size(i->folioq, i->folioq_slot), i->count);
 	return i->count;
 }
 EXPORT_SYMBOL(iov_iter_single_seg_count);
@@ -640,6 +707,36 @@ void iov_iter_bvec(struct iov_iter *i, unsigned int direction,
 EXPORT_SYMBOL(iov_iter_bvec);
 
 /**
+ * iov_iter_folio_queue - Initialise an I/O iterator to use the folios in a folio queue
+ * @i: The iterator to initialise.
+ * @direction: The direction of the transfer.
+ * @folioq: The starting point in the folio queue.
+ * @first_slot: The first slot in the folio queue to use
+ * @offset: The offset into the folio in the first slot to start at
+ * @count: The size of the I/O buffer in bytes.
+ *
+ * Set up an I/O iterator to either draw data out of the pages attached to an
+ * inode or to inject data into those pages.  The pages *must* be prevented
+ * from evaporation, either by taking a ref on them or locking them by the
+ * caller.
+ */
+void iov_iter_folio_queue(struct iov_iter *i, unsigned int direction,
+			  const struct folio_queue *folioq, unsigned int first_slot,
+			  unsigned int offset, size_t count)
+{
+	BUG_ON(direction & ~1);
+	*i = (struct iov_iter) {
+		.iter_type = ITER_FOLIOQ,
+		.data_source = direction,
+		.folioq = folioq,
+		.folioq_slot = first_slot,
+		.count = count,
+		.iov_offset = offset,
+	};
+}
+EXPORT_SYMBOL(iov_iter_folio_queue);
+
+/**
  * iov_iter_xarray - Initialise an I/O iterator to use the pages in an xarray
  * @i: The iterator to initialise.
  * @direction: The direction of the transfer.
@@ -765,12 +862,19 @@ bool iov_iter_is_aligned(const struct iov_iter *i, unsigned addr_mask,
 	if (iov_iter_is_bvec(i))
 		return iov_iter_aligned_bvec(i, addr_mask, len_mask);
 
+	/* With both xarray and folioq types, we're dealing with whole folios. */
 	if (iov_iter_is_xarray(i)) {
 		if (i->count & len_mask)
 			return false;
 		if ((i->xarray_start + i->iov_offset) & addr_mask)
 			return false;
 	}
+	if (iov_iter_is_folioq(i)) {
+		if (i->count & len_mask)
+			return false;
+		if (i->iov_offset & addr_mask)
+			return false;
+	}
 
 	return true;
 }
@@ -835,6 +939,9 @@ unsigned long iov_iter_alignment(const struct iov_iter *i)
 	if (iov_iter_is_bvec(i))
 		return iov_iter_alignment_bvec(i);
 
+	/* With both xarray and folioq types, we're dealing with whole folios. */
+	if (iov_iter_is_folioq(i))
+		return i->iov_offset | i->count;
 	if (iov_iter_is_xarray(i))
 		return (i->xarray_start + i->iov_offset) | i->count;
 
@@ -887,6 +994,62 @@ static int want_pages_array(struct page ***res, size_t size,
 	return count;
 }
 
+static ssize_t iter_folioq_get_pages(struct iov_iter *iter,
+				     struct page ***ppages, size_t maxsize,
+				     unsigned maxpages, size_t *_start_offset)
+{
+	const struct folio_queue *folioq = iter->folioq;
+	struct page **pages;
+	unsigned int slot = iter->folioq_slot;
+	size_t extracted = 0, count = iter->count, iov_offset = iter->iov_offset;
+
+	if (slot >= folioq_nr_slots(folioq)) {
+		folioq = folioq->next;
+		slot = 0;
+		if (WARN_ON(iov_offset != 0))
+			return -EIO;
+	}
+
+	maxpages = want_pages_array(ppages, maxsize, iov_offset & ~PAGE_MASK, maxpages);
+	if (!maxpages)
+		return -ENOMEM;
+	*_start_offset = iov_offset & ~PAGE_MASK;
+	pages = *ppages;
+
+	for (;;) {
+		struct folio *folio = folioq_folio(folioq, slot);
+		size_t offset = iov_offset, fsize = folioq_folio_size(folioq, slot);
+		size_t part = PAGE_SIZE - offset % PAGE_SIZE;
+
+		part = umin(part, umin(maxsize - extracted, fsize - offset));
+		count -= part;
+		iov_offset += part;
+		extracted += part;
+
+		*pages = folio_page(folio, offset / PAGE_SIZE);
+		get_page(*pages);
+		pages++;
+		maxpages--;
+		if (maxpages == 0 || extracted >= maxsize)
+			break;
+
+		if (offset >= fsize) {
+			iov_offset = 0;
+			slot++;
+			if (slot == folioq_nr_slots(folioq) && folioq->next) {
+				folioq = folioq->next;
+				slot = 0;
+			}
+		}
+	}
+
+	iter->count = count;
+	iter->iov_offset = iov_offset;
+	iter->folioq = folioq;
+	iter->folioq_slot = slot;
+	return extracted;
+}
+
 static ssize_t iter_xarray_populate_pages(struct page **pages, struct xarray *xa,
 					  pgoff_t index, unsigned int nr_pages)
 {
@@ -1034,6 +1197,8 @@ static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i,
 		}
 		return maxsize;
 	}
+	if (iov_iter_is_folioq(i))
+		return iter_folioq_get_pages(i, pages, maxsize, maxpages, start);
 	if (iov_iter_is_xarray(i))
 		return iter_xarray_get_pages(i, pages, maxsize, maxpages, start);
 	return -EFAULT;
@@ -1118,6 +1283,11 @@ int iov_iter_npages(const struct iov_iter *i, int maxpages)
 		return iov_npages(i, maxpages);
 	if (iov_iter_is_bvec(i))
 		return bvec_npages(i, maxpages);
+	if (iov_iter_is_folioq(i)) {
+		unsigned offset = i->iov_offset % PAGE_SIZE;
+		int npages = DIV_ROUND_UP(offset + i->count, PAGE_SIZE);
+		return min(npages, maxpages);
+	}
 	if (iov_iter_is_xarray(i)) {
 		unsigned offset = (i->xarray_start + i->iov_offset) % PAGE_SIZE;
 		int npages = DIV_ROUND_UP(offset + i->count, PAGE_SIZE);
@@ -1399,6 +1569,68 @@ void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state)
 }
 
 /*
+ * Extract a list of contiguous pages from an ITER_FOLIOQ iterator.  This does
+ * not get references on the pages, nor does it get a pin on them.
+ */
+static ssize_t iov_iter_extract_folioq_pages(struct iov_iter *i,
+					     struct page ***pages, size_t maxsize,
+					     unsigned int maxpages,
+					     iov_iter_extraction_t extraction_flags,
+					     size_t *offset0)
+{
+	const struct folio_queue *folioq = i->folioq;
+	struct page **p;
+	unsigned int nr = 0;
+	size_t extracted = 0, offset, slot = i->folioq_slot;
+
+	if (slot >= folioq_nr_slots(folioq)) {
+		folioq = folioq->next;
+		slot = 0;
+		if (WARN_ON(i->iov_offset != 0))
+			return -EIO;
+	}
+
+	offset = i->iov_offset & ~PAGE_MASK;
+	*offset0 = offset;
+
+	maxpages = want_pages_array(pages, maxsize, offset, maxpages);
+	if (!maxpages)
+		return -ENOMEM;
+	p = *pages;
+
+	for (;;) {
+		struct folio *folio = folioq_folio(folioq, slot);
+		size_t offset = i->iov_offset, fsize = folioq_folio_size(folioq, slot);
+		size_t part = PAGE_SIZE - offset % PAGE_SIZE;
+
+		if (offset < fsize) {
+			part = umin(part, umin(maxsize - extracted, fsize - offset));
+			i->count -= part;
+			i->iov_offset += part;
+			extracted += part;
+
+			p[nr++] = folio_page(folio, offset / PAGE_SIZE);
+		}
+
+		if (nr >= maxpages || extracted >= maxsize)
+			break;
+
+		if (i->iov_offset >= fsize) {
+			i->iov_offset = 0;
+			slot++;
+			if (slot == folioq_nr_slots(folioq) && folioq->next) {
+				folioq = folioq->next;
+				slot = 0;
+			}
+		}
+	}
+
+	i->folioq = folioq;
+	i->folioq_slot = slot;
+	return extracted;
+}
+
+/*
  * Extract a list of contiguous pages from an ITER_XARRAY iterator.  This does not
  * get references on the pages, nor does it get a pin on them.
  */
@@ -1618,8 +1850,8 @@ static ssize_t iov_iter_extract_user_pages(struct iov_iter *i,
  *      added to the pages, but refs will not be taken.
  *      iov_iter_extract_will_pin() will return true.
  *
- *  (*) If the iterator is ITER_KVEC, ITER_BVEC or ITER_XARRAY, the pages are
- *      merely listed; no extra refs or pins are obtained.
+ *  (*) If the iterator is ITER_KVEC, ITER_BVEC, ITER_FOLIOQ or ITER_XARRAY, the
+ *      pages are merely listed; no extra refs or pins are obtained.
  *      iov_iter_extract_will_pin() will return 0.
  *
  * Note also:
@@ -1654,6 +1886,10 @@ ssize_t iov_iter_extract_pages(struct iov_iter *i,
 		return iov_iter_extract_bvec_pages(i, pages, maxsize,
 						   maxpages, extraction_flags,
 						   offset0);
+	if (iov_iter_is_folioq(i))
+		return iov_iter_extract_folioq_pages(i, pages, maxsize,
+						     maxpages, extraction_flags,
+						     offset0);
 	if (iov_iter_is_xarray(i))
 		return iov_iter_extract_xarray_pages(i, pages, maxsize,
 						     maxpages, extraction_flags,