Merge tag 'vfs-6.16-rc1.netfs' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull netfs updates from Christian Brauner:

 - The main API document has been extensively updated/rewritten

 - Fix an oops in write-retry due to mis-resetting the I/O iterator

 - Fix the recording of transferred bytes for short DIO reads

 - Fix a request's work item to not require a reference, thereby
   avoiding the need to get rid of it in BH/IRQ context

 - Fix waiting and waking to be consistent about the waitqueue used

 - Remove NETFS_SREQ_SEEK_DATA_READ, NETFS_INVALID_WRITE,
   NETFS_ICTX_WRITETHROUGH, NETFS_READ_HOLE_CLEAR,
   NETFS_RREQ_DONT_UNLOCK_FOLIOS, and NETFS_RREQ_BLOCKED

 - Reorder structs to eliminate holes

 - Remove netfs_io_request::ractl

 - Only provide proc_link field if CONFIG_PROC_FS=y

 - Remove folio_queue::marks3

 - Fix undifferentiation of DIO reads from unbuffered reads

* tag 'vfs-6.16-rc1.netfs' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  netfs: Fix undifferentiation of DIO reads from unbuffered reads
  netfs: Fix wait/wake to be consistent about the waitqueue used
  netfs: Fix the request's work item to not require a ref
  netfs: Fix setting of transferred bytes with short DIO reads
  netfs: Fix oops in write-retry from mis-resetting the subreq iterator
  fs/netfs: remove unused flag NETFS_RREQ_BLOCKED
  fs/netfs: remove unused flag NETFS_RREQ_DONT_UNLOCK_FOLIOS
  folio_queue: remove unused field `marks3`
  fs/netfs: declare field `proc_link` only if CONFIG_PROC_FS=y
  fs/netfs: remove `netfs_io_request.ractl`
  fs/netfs: reorder struct fields to eliminate holes
  fs/netfs: remove unused enum choice NETFS_READ_HOLE_CLEAR
  fs/netfs: remove unused flag NETFS_ICTX_WRITETHROUGH
  fs/netfs: remove unused source NETFS_INVALID_WRITE
  fs/netfs: remove unused flag NETFS_SREQ_SEEK_DATA_READ

Author: torvalds

Documentation/core-api/folio_queue.rst

@@ -151,19 +151,16 @@ The marks can be set by::
 
 	void folioq_mark(struct folio_queue *folioq, unsigned int slot);
 	void folioq_mark2(struct folio_queue *folioq, unsigned int slot);
-	void folioq_mark3(struct folio_queue *folioq, unsigned int slot);
 
 Cleared by::
 
 	void folioq_unmark(struct folio_queue *folioq, unsigned int slot);
 	void folioq_unmark2(struct folio_queue *folioq, unsigned int slot);
-	void folioq_unmark3(struct folio_queue *folioq, unsigned int slot);
 
 And the marks can be queried by::
 
 	bool folioq_is_marked(const struct folio_queue *folioq, unsigned int slot);
 	bool folioq_is_marked2(const struct folio_queue *folioq, unsigned int slot);
-	bool folioq_is_marked3(const struct folio_queue *folioq, unsigned int slot);
 
 The marks can be used for any purpose and are not interpreted by this API.
 

Documentation/filesystems/netfs_library.rst

@@ -712,11 +712,6 @@ handle falling back from one source type to another.  The members are:
      at a boundary with the filesystem structure (e.g. at the end of a Ceph
      object).  It tells netfslib not to retile subrequests across it.
 
-   * ``NETFS_SREQ_SEEK_DATA_READ``
-
-     This is a hint from netfslib to the cache that it might want to try
-     skipping ahead to the next data (ie. using SEEK_DATA).
-
  * ``error``
 
    This is for the filesystem to store result of the subrequest.  It should be

fs/9p/vfs_addr.c

@@ -59,7 +59,7 @@ static void v9fs_issue_write(struct netfs_io_subrequest *subreq)
 	len = p9_client_write(fid, subreq->start, &subreq->io_iter, &err);
 	if (len > 0)
 		__set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags);
-	netfs_write_subrequest_terminated(subreq, len ?: err, false);
+	netfs_write_subrequest_terminated(subreq, len ?: err);
 }
 
 /**
@@ -77,7 +77,8 @@ static void v9fs_issue_read(struct netfs_io_subrequest *subreq)
 
 	/* if we just extended the file size, any portion not in
 	 * cache won't be on server and is zeroes */
-	if (subreq->rreq->origin != NETFS_DIO_READ)
+	if (subreq->rreq->origin != NETFS_UNBUFFERED_READ &&
+	    subreq->rreq->origin != NETFS_DIO_READ)
 		__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
 	if (pos + total >= i_size_read(rreq->inode))
 		__set_bit(NETFS_SREQ_HIT_EOF, &subreq->flags);

fs/afs/write.c

@@ -120,17 +120,17 @@ static void afs_issue_write_worker(struct work_struct *work)
 
 #if 0 // Error injection
 	if (subreq->debug_index == 3)
-		return netfs_write_subrequest_terminated(subreq, -ENOANO, false);
+		return netfs_write_subrequest_terminated(subreq, -ENOANO);
 
 	if (!subreq->retry_count) {
 		set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags);
-		return netfs_write_subrequest_terminated(subreq, -EAGAIN, false);
+		return netfs_write_subrequest_terminated(subreq, -EAGAIN);
 	}
 #endif
 
 	op = afs_alloc_operation(wreq->netfs_priv, vnode->volume);
 	if (IS_ERR(op))
-		return netfs_write_subrequest_terminated(subreq, -EAGAIN, false);
+		return netfs_write_subrequest_terminated(subreq, -EAGAIN);
 
 	afs_op_set_vnode(op, 0, vnode);
 	op->file[0].dv_delta	= 1;
@@ -166,7 +166,7 @@ static void afs_issue_write_worker(struct work_struct *work)
 		break;
 	}
 
-	netfs_write_subrequest_terminated(subreq, ret < 0 ? ret : subreq->len, false);
+	netfs_write_subrequest_terminated(subreq, ret < 0 ? ret : subreq->len);
 }
 
 void afs_issue_write(struct netfs_io_subrequest *subreq)
@@ -202,6 +202,7 @@ void afs_retry_request(struct netfs_io_request *wreq, struct netfs_io_stream *st
 	case NETFS_READ_GAPS:
 	case NETFS_READ_SINGLE:
 	case NETFS_READ_FOR_WRITE:
+	case NETFS_UNBUFFERED_READ:
 	case NETFS_DIO_READ:
 		return;
 	default:

fs/cachefiles/io.c

@@ -63,7 +63,7 @@ static void cachefiles_read_complete(struct kiocb *iocb, long ret)
 				ret = -ESTALE;
 		}
 
-		ki->term_func(ki->term_func_priv, ret, ki->was_async);
+		ki->term_func(ki->term_func_priv, ret);
 	}
 
 	cachefiles_put_kiocb(ki);
@@ -188,7 +188,7 @@ static int cachefiles_read(struct netfs_cache_resources *cres,
 
 presubmission_error:
 	if (term_func)
-		term_func(term_func_priv, ret < 0 ? ret : skipped, false);
+		term_func(term_func_priv, ret < 0 ? ret : skipped);
 	return ret;
 }
 
@@ -271,7 +271,7 @@ static void cachefiles_write_complete(struct kiocb *iocb, long ret)
 	atomic_long_sub(ki->b_writing, &object->volume->cache->b_writing);
 	set_bit(FSCACHE_COOKIE_HAVE_DATA, &object->cookie->flags);
 	if (ki->term_func)
-		ki->term_func(ki->term_func_priv, ret, ki->was_async);
+		ki->term_func(ki->term_func_priv, ret);
 	cachefiles_put_kiocb(ki);
 }
 
@@ -301,7 +301,7 @@ int __cachefiles_write(struct cachefiles_object *object,
 	ki = kzalloc(sizeof(struct cachefiles_kiocb), GFP_KERNEL);
 	if (!ki) {
 		if (term_func)
-			term_func(term_func_priv, -ENOMEM, false);
+			term_func(term_func_priv, -ENOMEM);
 		return -ENOMEM;
 	}
 
@@ -366,7 +366,7 @@ static int cachefiles_write(struct netfs_cache_resources *cres,
 {
 	if (!fscache_wait_for_operation(cres, FSCACHE_WANT_WRITE)) {
 		if (term_func)
-			term_func(term_func_priv, -ENOBUFS, false);
+			term_func(term_func_priv, -ENOBUFS);
 		trace_netfs_sreq(term_func_priv, netfs_sreq_trace_cache_nowrite);
 		return -ENOBUFS;
 	}
@@ -665,7 +665,7 @@ static void cachefiles_issue_write(struct netfs_io_subrequest *subreq)
 		pre = CACHEFILES_DIO_BLOCK_SIZE - off;
 		if (pre >= len) {
 			fscache_count_dio_misfit();
-			netfs_write_subrequest_terminated(subreq, len, false);
+			netfs_write_subrequest_terminated(subreq, len);
 			return;
 		}
 		subreq->transferred += pre;
@@ -691,7 +691,7 @@ static void cachefiles_issue_write(struct netfs_io_subrequest *subreq)
 		len -= post;
 		if (len == 0) {
 			fscache_count_dio_misfit();
-			netfs_write_subrequest_terminated(subreq, post, false);
+			netfs_write_subrequest_terminated(subreq, post);
 			return;
 		}
 		iov_iter_truncate(&subreq->io_iter, len);
@@ -703,7 +703,7 @@ static void cachefiles_issue_write(struct netfs_io_subrequest *subreq)
 					 &start, &len, len, true);
 	cachefiles_end_secure(cache, saved_cred);
 	if (ret < 0) {
-		netfs_write_subrequest_terminated(subreq, ret, false);
+		netfs_write_subrequest_terminated(subreq, ret);
 		return;
 	}
 

fs/ceph/addr.c

@@ -238,6 +238,7 @@ static void finish_netfs_read(struct ceph_osd_request *req)
 		if (sparse && err > 0)
 			err = ceph_sparse_ext_map_end(op);
 		if (err < subreq->len &&
+		    subreq->rreq->origin != NETFS_UNBUFFERED_READ &&
 		    subreq->rreq->origin != NETFS_DIO_READ)
 			__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
 		if (IS_ENCRYPTED(inode) && err > 0) {
@@ -281,7 +282,8 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq)
 	size_t len;
 	int mode;
 
-	if (rreq->origin != NETFS_DIO_READ)
+	if (rreq->origin != NETFS_UNBUFFERED_READ &&
+	    rreq->origin != NETFS_DIO_READ)
 		__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
 	__clear_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags);
 
@@ -539,7 +541,7 @@ static void ceph_set_page_fscache(struct page *page)
 	folio_start_private_2(page_folio(page)); /* [DEPRECATED] */
 }
 
-static void ceph_fscache_write_terminated(void *priv, ssize_t error, bool was_async)
+static void ceph_fscache_write_terminated(void *priv, ssize_t error)
 {
 	struct inode *inode = priv;
 

fs/erofs/fscache.c

@@ -102,8 +102,7 @@ static void erofs_fscache_req_io_put(struct erofs_fscache_io *io)
 		erofs_fscache_req_put(req);
 }
 
-static void erofs_fscache_req_end_io(void *priv,
-		ssize_t transferred_or_error, bool was_async)
+static void erofs_fscache_req_end_io(void *priv, ssize_t transferred_or_error)
 {
 	struct erofs_fscache_io *io = priv;
 	struct erofs_fscache_rq *req = io->private;
@@ -180,8 +179,7 @@ struct erofs_fscache_bio {
 	struct bio_vec bvecs[BIO_MAX_VECS];
 };
 
-static void erofs_fscache_bio_endio(void *priv,
-		ssize_t transferred_or_error, bool was_async)
+static void erofs_fscache_bio_endio(void *priv, ssize_t transferred_or_error)
 {
 	struct erofs_fscache_bio *io = priv;
 

fs/netfs/buffered_read.c

@@ -78,15 +78,16 @@ static int netfs_begin_cache_read(struct netfs_io_request *rreq, struct netfs_in
  * [!] NOTE: This must be run in the same thread as ->issue_read() was called
  * in as we access the readahead_control struct.
  */
-static ssize_t netfs_prepare_read_iterator(struct netfs_io_subrequest *subreq)
+static ssize_t netfs_prepare_read_iterator(struct netfs_io_subrequest *subreq,
+					   struct readahead_control *ractl)
 {
 	struct netfs_io_request *rreq = subreq->rreq;
 	size_t rsize = subreq->len;
 
 	if (subreq->source == NETFS_DOWNLOAD_FROM_SERVER)
 		rsize = umin(rsize, rreq->io_streams[0].sreq_max_len);
 
-	if (rreq->ractl) {
+	if (ractl) {
 		/* If we don't have sufficient folios in the rolling buffer,
 		 * extract a folioq's worth from the readahead region at a time
 		 * into the buffer.  Note that this acquires a ref on each page
@@ -99,7 +100,7 @@ static ssize_t netfs_prepare_read_iterator(struct netfs_io_subrequest *subreq)
 		while (rreq->submitted < subreq->start + rsize) {
 			ssize_t added;
 
-			added = rolling_buffer_load_from_ra(&rreq->buffer, rreq->ractl,
+			added = rolling_buffer_load_from_ra(&rreq->buffer, ractl,
 							    &put_batch);
 			if (added < 0)
 				return added;
@@ -211,7 +212,8 @@ static void netfs_issue_read(struct netfs_io_request *rreq,
  * slicing up the region to be read according to available cache blocks and
  * network rsize.
  */
-static void netfs_read_to_pagecache(struct netfs_io_request *rreq)
+static void netfs_read_to_pagecache(struct netfs_io_request *rreq,
+				    struct readahead_control *ractl)
 {
 	struct netfs_inode *ictx = netfs_inode(rreq->inode);
 	unsigned long long start = rreq->start;
@@ -262,9 +264,9 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq)
 				if (ret < 0) {
 					subreq->error = ret;
 					/* Not queued - release both refs. */
-					netfs_put_subrequest(subreq, false,
+					netfs_put_subrequest(subreq,
 							     netfs_sreq_trace_put_cancel);
-					netfs_put_subrequest(subreq, false,
+					netfs_put_subrequest(subreq,
 							     netfs_sreq_trace_put_cancel);
 					break;
 				}
@@ -291,14 +293,14 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq)
 		break;
 
 	issue:
-		slice = netfs_prepare_read_iterator(subreq);
+		slice = netfs_prepare_read_iterator(subreq, ractl);
 		if (slice < 0) {
 			ret = slice;
 			subreq->error = ret;
 			trace_netfs_sreq(subreq, netfs_sreq_trace_cancel);
 			/* Not queued - release both refs. */
-			netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel);
-			netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel);
+			netfs_put_subrequest(subreq, netfs_sreq_trace_put_cancel);
+			netfs_put_subrequest(subreq, netfs_sreq_trace_put_cancel);
 			break;
 		}
 		size -= slice;
@@ -312,7 +314,7 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq)
 	if (unlikely(size > 0)) {
 		smp_wmb(); /* Write lists before ALL_QUEUED. */
 		set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags);
-		netfs_wake_read_collector(rreq);
+		netfs_wake_collector(rreq);
 	}
 
 	/* Defer error return as we may need to wait for outstanding I/O. */
@@ -359,18 +361,15 @@ void netfs_readahead(struct readahead_control *ractl)
 
 	netfs_rreq_expand(rreq, ractl);
 
-	rreq->ractl = ractl;
 	rreq->submitted = rreq->start;
 	if (rolling_buffer_init(&rreq->buffer, rreq->debug_id, ITER_DEST) < 0)
 		goto cleanup_free;
-	netfs_read_to_pagecache(rreq);
+	netfs_read_to_pagecache(rreq, ractl);
 
-	netfs_put_request(rreq, true, netfs_rreq_trace_put_return);
-	return;
+	return netfs_put_request(rreq, netfs_rreq_trace_put_return);
 
 cleanup_free:
-	netfs_put_request(rreq, false, netfs_rreq_trace_put_failed);
-	return;
+	return netfs_put_request(rreq, netfs_rreq_trace_put_failed);
 }
 EXPORT_SYMBOL(netfs_readahead);
 
@@ -389,7 +388,6 @@ static int netfs_create_singular_buffer(struct netfs_io_request *rreq, struct fo
 	if (added < 0)
 		return added;
 	rreq->submitted = rreq->start + added;
-	rreq->ractl = (struct readahead_control *)1UL;
 	return 0;
 }
 
@@ -459,7 +457,7 @@ static int netfs_read_gaps(struct file *file, struct folio *folio)
 	iov_iter_bvec(&rreq->buffer.iter, ITER_DEST, bvec, i, rreq->len);
 	rreq->submitted = rreq->start + flen;
 
-	netfs_read_to_pagecache(rreq);
+	netfs_read_to_pagecache(rreq, NULL);
 
 	if (sink)
 		folio_put(sink);
@@ -470,11 +468,11 @@ static int netfs_read_gaps(struct file *file, struct folio *folio)
 		folio_mark_uptodate(folio);
 	}
 	folio_unlock(folio);
-	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
+	netfs_put_request(rreq, netfs_rreq_trace_put_return);
 	return ret < 0 ? ret : 0;
 
 discard:
-	netfs_put_request(rreq, false, netfs_rreq_trace_put_discard);
+	netfs_put_request(rreq, netfs_rreq_trace_put_discard);
 alloc_error:
 	folio_unlock(folio);
 	return ret;
@@ -528,13 +526,13 @@ int netfs_read_folio(struct file *file, struct folio *folio)
 	if (ret < 0)
 		goto discard;
 
-	netfs_read_to_pagecache(rreq);
+	netfs_read_to_pagecache(rreq, NULL);
 	ret = netfs_wait_for_read(rreq);
-	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
+	netfs_put_request(rreq, netfs_rreq_trace_put_return);
 	return ret < 0 ? ret : 0;
 
 discard:
-	netfs_put_request(rreq, false, netfs_rreq_trace_put_discard);
+	netfs_put_request(rreq, netfs_rreq_trace_put_discard);
 alloc_error:
 	folio_unlock(folio);
 	return ret;
@@ -685,11 +683,11 @@ int netfs_write_begin(struct netfs_inode *ctx,
 	if (ret < 0)
 		goto error_put;
 
-	netfs_read_to_pagecache(rreq);
+	netfs_read_to_pagecache(rreq, NULL);
 	ret = netfs_wait_for_read(rreq);
 	if (ret < 0)
 		goto error;
-	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
+	netfs_put_request(rreq, netfs_rreq_trace_put_return);
 
 have_folio:
 	ret = folio_wait_private_2_killable(folio);
@@ -701,7 +699,7 @@ int netfs_write_begin(struct netfs_inode *ctx,
 	return 0;
 
 error_put:
-	netfs_put_request(rreq, false, netfs_rreq_trace_put_failed);
+	netfs_put_request(rreq, netfs_rreq_trace_put_failed);
 error:
 	if (folio) {
 		folio_unlock(folio);
@@ -750,13 +748,13 @@ int netfs_prefetch_for_write(struct file *file, struct folio *folio,
 	if (ret < 0)
 		goto error_put;
 
-	netfs_read_to_pagecache(rreq);
+	netfs_read_to_pagecache(rreq, NULL);
 	ret = netfs_wait_for_read(rreq);
-	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
+	netfs_put_request(rreq, netfs_rreq_trace_put_return);
 	return ret < 0 ? ret : 0;
 
 error_put:
-	netfs_put_request(rreq, false, netfs_rreq_trace_put_discard);
+	netfs_put_request(rreq, netfs_rreq_trace_put_discard);
 error:
 	_leave(" = %d", ret);
 	return ret;