[PATCH 6.18 233/377] netfs: Fix cancellation of a DIO and single read subrequests

[PATCH 6.18 233/377] netfs: Fix cancellation of a DIO and single read subrequests

[Greg Kroah-Hartman]

6.18-stable review patch.  If anyone has any objections, please let me know.

------------------

From: David Howells <dhowells@redhat.com>

[ Upstream commit 6f0f7ac1915abc0d202f0eb4b003a6548a5ba60d ]

When the preparation of a new subrequest for a read fails, if the
subrequest has already been added to the stream->subrequests list, it can't
simply be put and abandoned as the collector may see it.  Also, if it
hasn't been queued yet, it has two outstanding refs that both need to be
put.  Both DIO read and single-read dispatch fail at this; further, both
differ in the order they do things to the way buffered read works.

Fix cancellation of both DIO-read and single-read subrequests that failed
preparation by the following steps:

 (1) Harmonise all three reads (buffered, dio, single) to queue the subreq
     before prepping it.

 (2) Make all three call netfs_queue_read() to do the queuing.

 (3) Set NETFS_RREQ_ALL_QUEUED independently of the queuing as we don't
     know the length of the subreq at this point.

 (4) In all cases, set the error and NETFS_SREQ_FAILED flag on the subreq
     and then call netfs_read_subreq_terminated() to deal with it.  This
     will pass responsibility off to the collector for dealing with it.

Fixes: e2d46f2ec332 ("netfs: Change the read result collector to only use one work item")
Closes: https://sashiko.dev/#/patchset/20260425125426.3855807-1-dhowells%40redhat.com
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://patch.msgid.link/20260512123404.719402-2-dhowells@redhat.com
cc: Paulo Alcantara <pc@manguebit.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/netfs/buffered_read.c | 34 +++++++++++++-------------------
 fs/netfs/direct_read.c   | 42 +++++++++++++---------------------------
 fs/netfs/internal.h      |  3 +++
 fs/netfs/read_collect.c  | 11 +++++++++++
 fs/netfs/read_single.c   | 23 ++++++++++------------
 5 files changed, 50 insertions(+), 63 deletions(-)

diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index 88361e8c70961..10b13924ed543 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -156,9 +156,8 @@ static void netfs_read_cache_to_pagecache(struct netfs_io_request *rreq,
 			netfs_cache_read_terminated, subreq);
 }
 
-static void netfs_queue_read(struct netfs_io_request *rreq,
-			     struct netfs_io_subrequest *subreq,
-			     bool last_subreq)
+void netfs_queue_read(struct netfs_io_request *rreq,
+		      struct netfs_io_subrequest *subreq)
 {
 	struct netfs_io_stream *stream = &rreq->io_streams[0];
 
@@ -178,11 +177,6 @@ static void netfs_queue_read(struct netfs_io_request *rreq,
 		}
 	}
 
-	if (last_subreq) {
-		smp_wmb(); /* Write lists before ALL_QUEUED. */
-		set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags);
-	}
-
 	spin_unlock(&rreq->lock);
 }
 
@@ -233,6 +227,8 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq,
 		subreq->start	= start;
 		subreq->len	= size;
 
+		netfs_queue_read(rreq, subreq);
+
 		source = netfs_cache_prepare_read(rreq, subreq, rreq->i_size);
 		subreq->source = source;
 		if (source == NETFS_DOWNLOAD_FROM_SERVER) {
@@ -253,6 +249,7 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq,
 				       rreq->debug_id, subreq->debug_index,
 				       subreq->len, size,
 				       subreq->start, ictx->zero_point, rreq->i_size);
+				netfs_cancel_read(subreq, ret);
 				break;
 			}
 			subreq->len = len;
@@ -261,12 +258,7 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq,
 			if (rreq->netfs_ops->prepare_read) {
 				ret = rreq->netfs_ops->prepare_read(subreq);
 				if (ret < 0) {
-					subreq->error = ret;
-					/* Not queued - release both refs. */
-					netfs_put_subrequest(subreq,
-							     netfs_sreq_trace_put_cancel);
-					netfs_put_subrequest(subreq,
-							     netfs_sreq_trace_put_cancel);
+					netfs_cancel_read(subreq, ret);
 					break;
 				}
 				trace_netfs_sreq(subreq, netfs_sreq_trace_prepare);
@@ -289,23 +281,23 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq,
 
 		pr_err("Unexpected read source %u\n", source);
 		WARN_ON_ONCE(1);
+		netfs_cancel_read(subreq, ret);
 		break;
 
 	issue:
 		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, netfs_sreq_trace_put_cancel);
-			netfs_put_subrequest(subreq, netfs_sreq_trace_put_cancel);
+			netfs_cancel_read(subreq, ret);
 			break;
 		}
-		size -= slice;
 		start += slice;
+		size -= slice;
+		if (size <= 0) {
+			smp_wmb(); /* Write lists before ALL_QUEUED. */
+			set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags);
+		}
 
-		netfs_queue_read(rreq, subreq, size <= 0);
 		netfs_issue_read(rreq, subreq);
 		cond_resched();
 	} while (size > 0);
diff --git a/fs/netfs/direct_read.c b/fs/netfs/direct_read.c
index f72e6da88cca7..6a8fb0d55e040 100644
--- a/fs/netfs/direct_read.c
+++ b/fs/netfs/direct_read.c
@@ -45,12 +45,11 @@ static void netfs_prepare_dio_read_iterator(struct netfs_io_subrequest *subreq)
  * Perform a read to a buffer from the server, slicing up the region to be read
  * according to the network rsize.
  */
-static int netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq)
+static void netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq)
 {
-	struct netfs_io_stream *stream = &rreq->io_streams[0];
 	unsigned long long start = rreq->start;
 	ssize_t size = rreq->len;
-	int ret = 0;
+	int ret;
 
 	do {
 		struct netfs_io_subrequest *subreq;
@@ -58,7 +57,10 @@ static int netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq)
 
 		subreq = netfs_alloc_subrequest(rreq);
 		if (!subreq) {
-			ret = -ENOMEM;
+			/* Stash the error in the request if there's not
+			 * already an error set.
+			 */
+			cmpxchg(&rreq->error, 0, -ENOMEM);
 			break;
 		}
 
@@ -66,25 +68,13 @@ static int netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq)
 		subreq->start	= start;
 		subreq->len	= size;
 
-		__set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags);
-
-		spin_lock(&rreq->lock);
-		list_add_tail(&subreq->rreq_link, &stream->subrequests);
-		if (list_is_first(&subreq->rreq_link, &stream->subrequests)) {
-			if (!stream->active) {
-				stream->collected_to = subreq->start;
-				/* Store list pointers before active flag */
-				smp_store_release(&stream->active, true);
-			}
-		}
-		trace_netfs_sreq(subreq, netfs_sreq_trace_added);
-		spin_unlock(&rreq->lock);
+		netfs_queue_read(rreq, subreq);
 
 		netfs_stat(&netfs_n_rh_download);
 		if (rreq->netfs_ops->prepare_read) {
 			ret = rreq->netfs_ops->prepare_read(subreq);
 			if (ret < 0) {
-				netfs_put_subrequest(subreq, netfs_sreq_trace_put_cancel);
+				netfs_cancel_read(subreq, ret);
 				break;
 			}
 		}
@@ -113,8 +103,6 @@ static int netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq)
 		set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags);
 		netfs_wake_collector(rreq);
 	}
-
-	return ret;
 }
 
 /*
@@ -137,21 +125,17 @@ static ssize_t netfs_unbuffered_read(struct netfs_io_request *rreq, bool sync)
 	// TODO: Use bounce buffer if requested
 
 	inode_dio_begin(rreq->inode);
+	netfs_dispatch_unbuffered_reads(rreq);
 
-	ret = netfs_dispatch_unbuffered_reads(rreq);
-
-	if (!rreq->submitted) {
-		netfs_put_request(rreq, netfs_rreq_trace_put_no_submit);
-		inode_dio_end(rreq->inode);
-		ret = 0;
-		goto out;
-	}
+	/* The collector will get run, even if we don't manage to submit any
+	 * subreqs, so we shouldn't call inode_dio_end() here.
+	 */
 
 	if (sync)
 		ret = netfs_wait_for_read(rreq);
 	else
 		ret = -EIOCBQUEUED;
-out:
+
 	_leave(" = %zd", ret);
 	return ret;
 }
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index d436e20d34185..645996ecfc803 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -23,6 +23,8 @@
 /*
  * buffered_read.c
  */
+void netfs_queue_read(struct netfs_io_request *rreq,
+		      struct netfs_io_subrequest *subreq);
 void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error);
 int netfs_prefetch_for_write(struct file *file, struct folio *folio,
 			     size_t offset, size_t len);
@@ -108,6 +110,7 @@ static inline void netfs_see_subrequest(struct netfs_io_subrequest *subreq,
  */
 bool netfs_read_collection(struct netfs_io_request *rreq);
 void netfs_read_collection_worker(struct work_struct *work);
+void netfs_cancel_read(struct netfs_io_subrequest *subreq, int error);
 void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error);
 
 /*
diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c
index e5f6665b3341e..d2d902f466271 100644
--- a/fs/netfs/read_collect.c
+++ b/fs/netfs/read_collect.c
@@ -575,6 +575,17 @@ void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq)
 }
 EXPORT_SYMBOL(netfs_read_subreq_terminated);
 
+/*
+ * Cancel a read subrequest due to preparation failure.
+ */
+void netfs_cancel_read(struct netfs_io_subrequest *subreq, int error)
+{
+	trace_netfs_sreq(subreq, netfs_sreq_trace_cancel);
+	subreq->error = error;
+	__set_bit(NETFS_SREQ_FAILED, &subreq->flags);
+	netfs_read_subreq_terminated(subreq);
+}
+
 /*
  * Handle termination of a read from the cache.
  */
diff --git a/fs/netfs/read_single.c b/fs/netfs/read_single.c
index 9d48ced80d1fa..cb422de66d0c5 100644
--- a/fs/netfs/read_single.c
+++ b/fs/netfs/read_single.c
@@ -89,7 +89,6 @@ static void netfs_single_read_cache(struct netfs_io_request *rreq,
  */
 static int netfs_single_dispatch_read(struct netfs_io_request *rreq)
 {
-	struct netfs_io_stream *stream = &rreq->io_streams[0];
 	struct netfs_io_subrequest *subreq;
 	int ret = 0;
 
@@ -102,14 +101,7 @@ static int netfs_single_dispatch_read(struct netfs_io_request *rreq)
 	subreq->len	= rreq->len;
 	subreq->io_iter	= rreq->buffer.iter;
 
-	__set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags);
-
-	spin_lock(&rreq->lock);
-	list_add_tail(&subreq->rreq_link, &stream->subrequests);
-	trace_netfs_sreq(subreq, netfs_sreq_trace_added);
-	/* Store list pointers before active flag */
-	smp_store_release(&stream->active, true);
-	spin_unlock(&rreq->lock);
+	netfs_queue_read(rreq, subreq);
 
 	netfs_single_cache_prepare_read(rreq, subreq);
 	switch (subreq->source) {
@@ -121,10 +113,14 @@ static int netfs_single_dispatch_read(struct netfs_io_request *rreq)
 				goto cancel;
 		}
 
+		smp_wmb(); /* Write lists before ALL_QUEUED. */
+		set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags);
 		rreq->netfs_ops->issue_read(subreq);
 		rreq->submitted += subreq->len;
 		break;
 	case NETFS_READ_FROM_CACHE:
+		smp_wmb(); /* Write lists before ALL_QUEUED. */
+		set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags);
 		trace_netfs_sreq(subreq, netfs_sreq_trace_submit);
 		netfs_single_read_cache(rreq, subreq);
 		rreq->submitted += subreq->len;
@@ -134,14 +130,15 @@ static int netfs_single_dispatch_read(struct netfs_io_request *rreq)
 		pr_warn("Unexpected single-read source %u\n", subreq->source);
 		WARN_ON_ONCE(true);
 		ret = -EIO;
-		break;
+		goto cancel;
 	}
 
-	smp_wmb(); /* Write lists before ALL_QUEUED. */
-	set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags);
 	return ret;
 cancel:
-	netfs_put_subrequest(subreq, netfs_sreq_trace_put_cancel);
+	netfs_cancel_read(subreq, ret);
+	smp_wmb(); /* Write lists before ALL_QUEUED. */
+	set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags);
+	netfs_wake_collector(rreq);
 	return ret;
 }
 
-- 
2.53.0

[PATCH 6.18 234/377] netfs: Fix netfs_read_to_pagecache() to pause on subreq failure

[Greg Kroah-Hartman]

6.18-stable review patch.  If anyone has any objections, please let me know.

------------------

From: David Howells <dhowells@redhat.com>

[ Upstream commit 8a8c0cfdf4658fc5b295b7fc87be56e0d76741f4 ]

Fix netfs_read_to_pagecache() so that it pauses the generation of new
subrequests if an already-issued subrequest fails.

Fixes: ee4cdf7ba857 ("netfs: Speed up buffered reading")
Closes: https://sashiko.dev/#/patchset/20260425125426.3855807-1-dhowells%40redhat.com
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://patch.msgid.link/20260512123404.719402-5-dhowells@redhat.com
cc: Paulo Alcantara <pc@manguebit.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/netfs/buffered_read.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index 10b13924ed543..e6157122da3a4 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -299,6 +299,11 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq,
 		}
 
 		netfs_issue_read(rreq, subreq);
+
+		if (test_bit(NETFS_RREQ_PAUSE, &rreq->flags))
+			netfs_wait_for_paused_read(rreq);
+		if (test_bit(NETFS_RREQ_FAILED, &rreq->flags))
+			break;
 		cond_resched();
 	} while (size > 0);
 
-- 
2.53.0

[PATCH 6.18 235/377] netfs: fix VM_BUG_ON_FOLIO() issue in netfs_write_begin() call

[Greg Kroah-Hartman]

6.18-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>

[ Upstream commit dc7832d05deb4d632e8035e3299e31a3528fa0d0 ]

The multiple runs of generic/013 test-case is capable
to reproduce a kernel BUG at mm/filemap.c:1504 with
probability of 30%.

while true; do
  sudo ./check generic/013
done

[ 9849.452376] page: refcount:3 mapcount:0 mapping:00000000e58ff252 index:0x10781 pfn:0x1c322
[ 9849.452412] memcg:ffff8881a1915800
[ 9849.452417] aops:ceph_aops ino:1000058db9e dentry name(?):"f9XXXXXX"
[ 9849.452432] flags: 0x17ffffc0000000(node=0|zone=2|lastcpupid=0x1fffff)
[ 9849.452441] raw: 0017ffffc0000000 0000000000000000 dead000000000122 ffff88816110d248
[ 9849.452445] raw: 0000000000010781 0000000000000000 00000003ffffffff ffff8881a1915800
[ 9849.452447] page dumped because: VM_BUG_ON_FOLIO(!folio_test_locked(folio))
[ 9849.452474] ------------[ cut here ]------------
[ 9849.452476] kernel BUG at mm/filemap.c:1504!
[ 9849.478635] Oops: invalid opcode: 0000 [#1] SMP KASAN NOPTI
[ 9849.481772] CPU: 2 UID: 0 PID: 84223 Comm: fsstress Not tainted 7.0.0-rc1+ #18 PREEMPT(full)
[ 9849.482881] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-9.fc43 06/1
0/2025
[ 9849.484539] RIP: 0010:folio_unlock+0x85/0xa0
[ 9849.485076] Code: 89 df 31 f6 e8 1c f3 ff ff 48 8b 5d f8 c9 31 c0 31 d2 31 f6 31 ff c3 cc
cc cc cc 48 c7 c6 80 6c d9 a7 48 89 df e8 4b b3 10 00 <0f> 0b 48 89 df e8 21 e6 2c 00 eb 9d 0f 1f 40 00 66 66 2e 0f 1f 84
[ 9849.493818] RSP: 0018:ffff8881bb8076b0 EFLAGS: 00010246
[ 9849.495740] RAX: 0000000000000000 RBX: ffffea00070c8980 RCX: 0000000000000000
[ 9849.498678] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
[ 9849.500559] RBP: ffff8881bb8076b8 R08: 0000000000000000 R09: 0000000000000000
[ 9849.501097] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000010782000
[ 9849.502108] R13: ffff8881935de738 R14: ffff88816110d010 R15: 0000000000001000
[ 9849.502516] FS:  00007e36cbe94740(0000) GS:ffff88824a899000(0000) knlGS:0000000000000000
[ 9849.502996] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 9849.503810] CR2: 000000c0002b0000 CR3: 000000011bbf6004 CR4: 0000000000772ef0
[ 9849.504459] PKRU: 55555554
[ 9849.504626] Call Trace:
[ 9849.505242]  <TASK>
[ 9849.505379]  netfs_write_begin+0x7c8/0x10a0
[ 9849.505877]  ? __kasan_check_read+0x11/0x20
[ 9849.506384]  ? __pfx_netfs_write_begin+0x10/0x10
[ 9849.507178]  ceph_write_begin+0x8c/0x1c0
[ 9849.507934]  generic_perform_write+0x391/0x8f0
[ 9849.508503]  ? __pfx_generic_perform_write+0x10/0x10
[ 9849.509062]  ? file_update_time_flags+0x19a/0x4b0
[ 9849.509581]  ? ceph_get_caps+0x63/0xf0
[ 9849.510259]  ? ceph_get_caps+0x63/0xf0
[ 9849.510530]  ceph_write_iter+0xe79/0x1ae0
[ 9849.511282]  ? __pfx_ceph_write_iter+0x10/0x10
[ 9849.511839]  ? lock_acquire+0x1ad/0x310
[ 9849.512334]  ? ksys_write+0xf9/0x230
[ 9849.512582]  ? lock_is_held_type+0xaa/0x140
[ 9849.513128]  vfs_write+0x512/0x1110
[ 9849.513634]  ? __fget_files+0x33/0x350
[ 9849.513893]  ? __pfx_vfs_write+0x10/0x10
[ 9849.514143]  ? mutex_lock_nested+0x1b/0x30
[ 9849.514394]  ksys_write+0xf9/0x230
[ 9849.514621]  ? __pfx_ksys_write+0x10/0x10
[ 9849.514887]  ? do_syscall_64+0x25e/0x1520
[ 9849.515122]  ? __kasan_check_read+0x11/0x20
[ 9849.515366]  ? trace_hardirqs_on_prepare+0x178/0x1c0
[ 9849.515655]  __x64_sys_write+0x72/0xd0
[ 9849.515885]  ? trace_hardirqs_on+0x24/0x1c0
[ 9849.516130]  x64_sys_call+0x22f/0x2390
[ 9849.516341]  do_syscall_64+0x12b/0x1520
[ 9849.516545]  ? do_syscall_64+0x27c/0x1520
[ 9849.516783]  ? do_syscall_64+0x27c/0x1520
[ 9849.517003]  ? lock_release+0x318/0x480
[ 9849.517220]  ? __x64_sys_io_getevents+0x143/0x2d0
[ 9849.517479]  ? percpu_ref_put_many.constprop.0+0x8f/0x210
[ 9849.517779]  ? entry_SYSCALL_64_after_hwframe+0x76/0x7e
[ 9849.518073]  ? do_syscall_64+0x25e/0x1520
[ 9849.518291]  ? __kasan_check_read+0x11/0x20
[ 9849.518519]  ? trace_hardirqs_on_prepare+0x178/0x1c0
[ 9849.518799]  ? do_syscall_64+0x27c/0x1520
[ 9849.519024]  ? local_clock_noinstr+0xf/0x120
[ 9849.519262]  ? entry_SYSCALL_64_after_hwframe+0x76/0x7e
[ 9849.519544]  ? do_syscall_64+0x25e/0x1520
[ 9849.519781]  ? __kasan_check_read+0x11/0x20
[ 9849.520008]  ? trace_hardirqs_on_prepare+0x178/0x1c0
[ 9849.520273]  ? do_syscall_64+0x27c/0x1520
[ 9849.520491]  ? trace_hardirqs_on_prepare+0x178/0x1c0
[ 9849.520767]  ? irqentry_exit+0x10c/0x6c0
[ 9849.520984]  ? trace_hardirqs_off+0x86/0x1b0
[ 9849.521224]  ? exc_page_fault+0xab/0x130
[ 9849.521472]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[ 9849.521766] RIP: 0033:0x7e36cbd14907
[ 9849.521989] Code: 10 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 48 89 54 24 18 48 89 74 24
[ 9849.523057] RSP: 002b:00007ffff2d2a968 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
[ 9849.523484] RAX: ffffffffffffffda RBX: 000000000000e549 RCX: 00007e36cbd14907
[ 9849.523885] RDX: 000000000000e549 RSI: 00005bd797ec6370 RDI: 0000000000000004
[ 9849.524277] RBP: 0000000000000004 R08: 0000000000000047 R09: 00005bd797ec6370
[ 9849.524652] R10: 0000000000000078 R11: 0000000000000246 R12: 0000000000000049
[ 9849.525062] R13: 0000000010781a37 R14: 00005bd797ec6370 R15: 0000000000000000
[ 9849.525447]  </TASK>
[ 9849.525574] Modules linked in: intel_rapl_msr intel_rapl_common intel_uncore_frequency_common intel_pmc_core pmt_telemetry pmt_discovery pmt_class intel_pmc_ssram_telemetry intel_vsec kvm_intel joydev kvm irqbypass ghash_clmulni_intel aesni_intel input_leds rapl mac_hid psmouse vga16fb serio_raw vgastate floppy i2c_piix4 bochs qemu_fw_cfg i2c_smbus pata_acpi sch_fq_codel rbd msr parport_pc ppdev lp parport efi_pstore
[ 9849.529150] ---[ end trace 0000000000000000 ]---
[ 9849.529502] RIP: 0010:folio_unlock+0x85/0xa0
[ 9849.530813] Code: 89 df 31 f6 e8 1c f3 ff ff 48 8b 5d f8 c9 31 c0 31 d2 31 f6 31 ff c3 cc cc cc cc 48 c7 c6 80 6c d9 a7 48 89 df e8 4b b3 10 00 <0f> 0b 48 89 df e8 21 e6 2c 00 eb 9d 0f 1f 40 00 66 66 2e 0f 1f 84
[ 9849.534986] RSP: 0018:ffff8881bb8076b0 EFLAGS: 00010246
[ 9849.536198] RAX: 0000000000000000 RBX: ffffea00070c8980 RCX: 0000000000000000
[ 9849.537718] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
[ 9849.539321] RBP: ffff8881bb8076b8 R08: 0000000000000000 R09: 0000000000000000
[ 9849.540862] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000010782000
[ 9849.542438] R13: ffff8881935de738 R14: ffff88816110d010 R15: 0000000000001000
[ 9849.543996] FS:  00007e36cbe94740(0000) GS:ffff88824b899000(0000) knlGS:0000000000000000
[ 9849.545854] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 9849.547092] CR2: 00007e36cb3ff000 CR3: 000000011bbf6006 CR4: 0000000000772ef0
[ 9849.548679] PKRU: 55555554

The race sequence:
1. Read completes -> netfs_read_collection() runs
2. netfs_wake_rreq_flag(rreq, NETFS_RREQ_IN_PROGRESS, ...)
3. netfs_wait_for_read() returns -EFAULT to netfs_write_begin()
4. The netfs_unlock_abandoned_read_pages() unlocks the folio
5. netfs_write_begin() calls folio_unlock(folio) -> VM_BUG_ON_FOLIO()

The key reason of the issue that netfs_unlock_abandoned_read_pages()
doesn't check the flag NETFS_RREQ_NO_UNLOCK_FOLIO and executes
folio_unlock() unconditionally. This patch implements in
netfs_unlock_abandoned_read_pages() logic similar to
netfs_unlock_read_folio().

Fixes: ee4cdf7ba857 ("netfs: Speed up buffered reading")
Signed-off-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://patch.msgid.link/20260512123404.719402-8-dhowells@redhat.com
Reviewed-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
cc: Ceph Development <ceph-devel@vger.kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/netfs/read_retry.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/fs/netfs/read_retry.c b/fs/netfs/read_retry.c
index cca9ac43c0773..68fc869513ef1 100644
--- a/fs/netfs/read_retry.c
+++ b/fs/netfs/read_retry.c
@@ -288,8 +288,15 @@ void netfs_unlock_abandoned_read_pages(struct netfs_io_request *rreq)
 			struct folio *folio = folioq_folio(p, slot);
 
 			if (folio && !folioq_is_marked2(p, slot)) {
-				trace_netfs_folio(folio, netfs_folio_trace_abandon);
-				folio_unlock(folio);
+				if (folio->index == rreq->no_unlock_folio &&
+				    test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO,
+					     &rreq->flags)) {
+					_debug("no unlock");
+				} else {
+					trace_netfs_folio(folio,
+						netfs_folio_trace_abandon);
+					folio_unlock(folio);
+				}
 			}
 		}
 	}
-- 
2.53.0

[PATCH 6.18 236/377] netfs: Fix overrun check in netfs_extract_user_iter()

[Greg Kroah-Hartman]

6.18-stable review patch.  If anyone has any objections, please let me know.

------------------

From: David Howells <dhowells@redhat.com>

[ Upstream commit 0ef37eef83fad3542ee06db2940433ae1a92b39d ]

Fix netfs_extract_user_iter() so that if iov_iter_extract_pages() overfills
pages[], then those pages don't get included in the iterator constructed at
the end of the function.  If there was an overfill, memory corruption has
already happened.

Fixes: 85dd2c8ff368 ("netfs: Add a function to extract a UBUF or IOVEC into a BVEC iterator")
Closes: https://sashiko.dev/#/patchset/20260427154639.180684-1-dhowells%40redhat.com
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://patch.msgid.link/20260512123404.719402-11-dhowells@redhat.com
cc: Paulo Alcantara <pc@manguebit.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/netfs/iterator.c | 26 +++++++++++++++++---------
 1 file changed, 17 insertions(+), 9 deletions(-)

diff --git a/fs/netfs/iterator.c b/fs/netfs/iterator.c
index 429e4396e1b00..b375567e0520e 100644
--- a/fs/netfs/iterator.c
+++ b/fs/netfs/iterator.c
@@ -72,21 +72,24 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len,
 			break;
 		}
 
-		if (ret > count) {
-			pr_err("get_pages rc=%zd more than %zu\n", ret, count);
+		if (WARN(ret > count,
+			 "%s: extract_pages overrun %zd > %zu bytes\n",
+			 __func__, ret, count)) {
+			ret = -EIO;
 			break;
 		}
 
-		count -= ret;
-		ret += offset;
-		cur_npages = DIV_ROUND_UP(ret, PAGE_SIZE);
-
-		if (npages + cur_npages > max_pages) {
-			pr_err("Out of bvec array capacity (%u vs %u)\n",
-			       npages + cur_npages, max_pages);
+		cur_npages = DIV_ROUND_UP(offset + ret, PAGE_SIZE);
+		if (WARN(cur_npages > max_pages - npages,
+			 "%s: extract_pages overrun %u > %u pages\n",
+			 __func__, npages + cur_npages, max_pages)) {
+			ret = -EIO;
 			break;
 		}
 
+		count -= ret;
+		ret += offset;
+
 		for (i = 0; i < cur_npages; i++) {
 			len = ret > PAGE_SIZE ? PAGE_SIZE : ret;
 			bvec_set_page(bv + npages + i, *pages++, len - offset, offset);
@@ -97,6 +100,11 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len,
 		npages += cur_npages;
 	}
 
+	/* Note: Don't try to clean up after EIO.  Either we got no pages, so
+	 * nothing to clean up, or we got a buffer overrun, memory corruption
+	 * and can't trust the stuff in the buffer (a WARN was emitted).
+	 */
+
 	if (ret < 0 && (ret == -ENOMEM || npages == 0)) {
 		for (i = 0; i < npages; i++)
 			unpin_user_page(bv[i].bv_page);
-- 
2.53.0

[PATCH 6.18 237/377] netfs: Fix netfs_invalidate_folio() to clear dirty bit if all changes gone

[Greg Kroah-Hartman]

6.18-stable review patch.  If anyone has any objections, please let me know.

------------------

From: David Howells <dhowells@redhat.com>

[ Upstream commit 156ac2ec2ee77c44c4eb7439d6d165247ba12247 ]

If a streaming write is made, this will leave the relevant modified folio
in a not-uptodate, but dirty state with a netfs_folio struct hung off of
folio->private indicating the dirty range.  Subsequently truncating the
file such that the dirty data in the folio is removed, but the first part
of the folio theoretically remains will cause the netfs_folio struct to be
discarded... but will leave the dirty flag set.

If the folio is then read via mmap(), netfs_read_folio() will see that the
page is dirty and jump to netfs_read_gaps() to fill in the missing bits.
netfs_read_gaps(), however, expects there to be a netfs_folio struct
present and can oops because truncate removed it.

Fix this by calling folio_cancel_dirty() in netfs_invalidate_folio() in the
event that all the dirty data in the folio is erased (as nfs does).

Also add some tracepoints to log modifications to a dirty page.

This can be reproduced with something like:

    dd if=/dev/zero of=/xfstest.test/foo bs=1M count=1
    umount /xfstest.test
    mount /xfstest.test
    xfs_io -c "w 0xbbbf 0xf96c" \
           -c "truncate 0xbbbf" \
           -c "mmap -r 0xb000 0x11000" \
           -c "mr 0xb000 0x11000" \
           /xfstest.test/foo

with fscaching disabled (otherwise streaming writes are suppressed) and a
change to netfs_perform_write() to disallow streaming writes if the fd is
open O_RDWR:

	if (//(file->f_mode & FMODE_READ) || <--- comment this out
	    netfs_is_cache_enabled(ctx)) {

It should be reproducible even without this change, but if prevents the
above trivial xfs_io command from reproducing it.

Note that the initial dd is important: the file must start out sufficiently
large that the zero-point logic doesn't just clear the gaps because it
knows there's nothing in the file to read yet.  Unmounting and mounting is
needed to clear the pagecache (there are other ways to do that that may
also work).

This was initially reproduced with the generic/522 xfstest on some patches
that remove the FMODE_READ restriction.

Fixes: 9ebff83e6481 ("netfs: Prep to use folio->private for write grouping and streaming write")
Reported-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://patch.msgid.link/20260512123404.719402-12-dhowells@redhat.com
cc: Paulo Alcantara <pc@manguebit.org>
cc: Matthew Wilcox <willy@infradead.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/netfs/misc.c              | 6 +++++-
 include/trace/events/netfs.h | 4 ++++
 2 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
index 486166460e177..eb309bef72608 100644
--- a/fs/netfs/misc.c
+++ b/fs/netfs/misc.c
@@ -256,6 +256,7 @@ void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length)
 			/* Move the start of the data. */
 			finfo->dirty_len = fend - iend;
 			finfo->dirty_offset = offset;
+			trace_netfs_folio(folio, netfs_folio_trace_invalidate_front);
 			return;
 		}
 
@@ -264,12 +265,14 @@ void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length)
 		 */
 		if (iend >= fend) {
 			finfo->dirty_len = offset - fstart;
+			trace_netfs_folio(folio, netfs_folio_trace_invalidate_tail);
 			return;
 		}
 
 		/* A partial write was split.  The caller has already zeroed
 		 * it, so just absorb the hole.
 		 */
+		trace_netfs_folio(folio, netfs_folio_trace_invalidate_middle);
 	}
 	return;
 
@@ -277,8 +280,9 @@ void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length)
 	netfs_put_group(netfs_folio_group(folio));
 	folio_detach_private(folio);
 	folio_clear_uptodate(folio);
+	folio_cancel_dirty(folio);
 	kfree(finfo);
-	return;
+	trace_netfs_folio(folio, netfs_folio_trace_invalidate_all);
 }
 EXPORT_SYMBOL(netfs_invalidate_folio);
 
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index cbe28211106c5..88d814ba1e697 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -194,6 +194,10 @@
 	EM(netfs_folio_trace_copy_to_cache,	"mark-copy")	\
 	EM(netfs_folio_trace_end_copy,		"end-copy")	\
 	EM(netfs_folio_trace_filled_gaps,	"filled-gaps")	\
+	EM(netfs_folio_trace_invalidate_all,	"inval-all")	\
+	EM(netfs_folio_trace_invalidate_front,	"inval-front")	\
+	EM(netfs_folio_trace_invalidate_middle,	"inval-mid")	\
+	EM(netfs_folio_trace_invalidate_tail,	"inval-tail")	\
 	EM(netfs_folio_trace_kill,		"kill")		\
 	EM(netfs_folio_trace_kill_cc,		"kill-cc")	\
 	EM(netfs_folio_trace_kill_g,		"kill-g")	\
-- 
2.53.0

[PATCH 6.18 238/377] netfs: Defer the emission of trace_netfs_folio()

[Greg Kroah-Hartman]

6.18-stable review patch.  If anyone has any objections, please let me know.

------------------

From: David Howells <dhowells@redhat.com>

[ Upstream commit daeb443b92817021c1234e8eded219e164b7c35d ]

Change netfs_perform_write() to keep the netfs_folio trace value in a
variable and emit it later to make it easier to choose the value displayed.
This is a prerequisite for a subsequent patch.

Closes: https://sashiko.dev/#/patchset/20260414082004.3756080-1-dhowells%40redhat.com
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://patch.msgid.link/20260512123404.719402-13-dhowells@redhat.com
cc: Paulo Alcantara <pc@manguebit.org>
cc: Matthew Wilcox <willy@infradead.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
Stable-dep-of: 7b4dcf1b9455 ("netfs: Fix streaming write being overwritten")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/netfs/buffered_write.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 09394ac2c180d..1fa13c2629a73 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -150,6 +150,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 	}
 
 	do {
+		enum netfs_folio_trace trace;
 		struct netfs_folio *finfo;
 		struct netfs_group *group;
 		unsigned long long fpos;
@@ -223,7 +224,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 			if (unlikely(copied == 0))
 				goto copy_failed;
 			netfs_set_group(folio, netfs_group);
-			trace_netfs_folio(folio, netfs_folio_is_uptodate);
+			trace = netfs_folio_is_uptodate;
 			goto copied;
 		}
 
@@ -239,7 +240,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 			folio_zero_segment(folio, offset + copied, flen);
 			__netfs_set_group(folio, netfs_group);
 			folio_mark_uptodate(folio);
-			trace_netfs_folio(folio, netfs_modify_and_clear);
+			trace = netfs_modify_and_clear;
 			goto copied;
 		}
 
@@ -257,7 +258,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 			}
 			__netfs_set_group(folio, netfs_group);
 			folio_mark_uptodate(folio);
-			trace_netfs_folio(folio, netfs_whole_folio_modify);
+			trace = netfs_whole_folio_modify;
 			goto copied;
 		}
 
@@ -284,7 +285,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 			if (unlikely(copied == 0))
 				goto copy_failed;
 			netfs_set_group(folio, netfs_group);
-			trace_netfs_folio(folio, netfs_just_prefetch);
+			trace = netfs_just_prefetch;
 			goto copied;
 		}
 
@@ -298,7 +299,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 			if (offset == 0 && copied == flen) {
 				__netfs_set_group(folio, netfs_group);
 				folio_mark_uptodate(folio);
-				trace_netfs_folio(folio, netfs_streaming_filled_page);
+				trace = netfs_streaming_filled_page;
 				goto copied;
 			}
 
@@ -313,7 +314,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 			finfo->dirty_len = copied;
 			folio_attach_private(folio, (void *)((unsigned long)finfo |
 							     NETFS_FOLIO_INFO));
-			trace_netfs_folio(folio, netfs_streaming_write);
+			trace = netfs_streaming_write;
 			goto copied;
 		}
 
@@ -333,9 +334,9 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 					folio_detach_private(folio);
 				folio_mark_uptodate(folio);
 				kfree(finfo);
-				trace_netfs_folio(folio, netfs_streaming_cont_filled_page);
+				trace = netfs_streaming_cont_filled_page;
 			} else {
-				trace_netfs_folio(folio, netfs_streaming_write_cont);
+				trace = netfs_streaming_write_cont;
 			}
 			goto copied;
 		}
@@ -351,6 +352,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 		continue;
 
 	copied:
+		trace_netfs_folio(folio, trace);
 		flush_dcache_folio(folio);
 
 		/* Update the inode size if we moved the EOF marker */
-- 
2.53.0

[PATCH 6.18 239/377] netfs: Fix streaming write being overwritten

[Greg Kroah-Hartman]

6.18-stable review patch.  If anyone has any objections, please let me know.

------------------

From: David Howells <dhowells@redhat.com>

[ Upstream commit 7b4dcf1b9455a6e52ac7478b4057dbe10359576d ]

In order to avoid reading whilst writing, netfslib will allow "streaming
writes" in which dirty data is stored directly into folios without reading
them first.  Such folios are marked dirty but may not be marked uptodate.
If a folio is entirely written by a streaming write, uptodate will be set,
otherwise it will have a netfs_folio struct attached to ->private recording
the dirty region.

In the event that a partially written streaming write page is to be
overwritten entirely by a single write(), netfs_perform_write() will try to
copy over it, but doesn't discard the netfs_folio if it succeeds; further,
it doesn't correctly handle a partial copy that overwrites some of the
dirty data.

Fix this by the following:

 (1) If the folio is successfully overwritten, free the netfs_folio struct
     before marking the page uptodate.

 (2) If the copy to the folio partially fails, but short of the dirty data,
     just ignore the copy.

 (3) If the copy partially fails and overwrites some of the dirty data,
     accept the copy, update the netfs_folio struct to record the new data.
     If the folio is now filled, free the netfs_folio and set uptodate,
     otherwise return a partial write.

Found with:

	fsx -q -N 1000000 -p 10000 -o 128000 -l 600000 \
	  /xfstest.test/junk --replay-ops=junk.fsxops

using the following as junk.fsxops:

	truncate 0x0 0 0x927c0
	write 0x63fb8 0x53c8 0
	copy_range 0xb704 0x19b9 0x24429 0x79380
	write 0x2402b 0x144a2 0x90660 *
	write 0x204d5 0x140a0 0x927c0 *
	copy_range 0x1f72c 0x137d0 0x7a906 0x927c0 *
	read 0x00000 0x20000 0x9157c
	read 0x20000 0x20000 0x9157c
	read 0x40000 0x20000 0x9157c
	read 0x60000 0x20000 0x9157c
	read 0x7e1a0 0xcfb9 0x9157c

on cifs with the default cache option.

It shows folio 0x24 misbehaving if the FMODE_READ check is commented out in
netfs_perform_write():

		if (//(file->f_mode & FMODE_READ) ||
		    netfs_is_cache_enabled(ctx)) {

and no fscache.  This was initially found with the generic/522 xfstest.

Fixes: 8f52de0077ba ("netfs: Reduce number of conditional branches in netfs_perform_write()")
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://patch.msgid.link/20260512123404.719402-14-dhowells@redhat.com
cc: Paulo Alcantara <pc@manguebit.org>
cc: Matthew Wilcox <willy@infradead.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/netfs/buffered_write.c    | 47 ++++++++++++++++++++++++++----------
 include/trace/events/netfs.h |  3 +++
 2 files changed, 37 insertions(+), 13 deletions(-)

diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 1fa13c2629a73..99736895e964f 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -247,18 +247,38 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 		/* See if we can write a whole folio in one go. */
 		if (!maybe_trouble && offset == 0 && part >= flen) {
 			copied = copy_folio_from_iter_atomic(folio, offset, part, iter);
-			if (unlikely(copied == 0))
+			if (likely(copied == part)) {
+				if (finfo) {
+					trace = netfs_whole_folio_modify_filled;
+					goto folio_now_filled;
+				}
+				__netfs_set_group(folio, netfs_group);
+				folio_mark_uptodate(folio);
+				trace = netfs_whole_folio_modify;
+				goto copied;
+			}
+			if (copied == 0)
 				goto copy_failed;
-			if (unlikely(copied < part)) {
+			if (!finfo || copied <= finfo->dirty_offset) {
 				maybe_trouble = true;
 				iov_iter_revert(iter, copied);
 				copied = 0;
 				folio_unlock(folio);
 				goto retry;
 			}
-			__netfs_set_group(folio, netfs_group);
-			folio_mark_uptodate(folio);
-			trace = netfs_whole_folio_modify;
+
+			/* We overwrote some existing dirty data, so we have to
+			 * accept the partial write.
+			 */
+			finfo->dirty_len += finfo->dirty_offset;
+			if (finfo->dirty_len == flen) {
+				trace = netfs_whole_folio_modify_filled_efault;
+				goto folio_now_filled;
+			}
+			if (copied > finfo->dirty_len)
+				finfo->dirty_len = copied;
+			finfo->dirty_offset = 0;
+			trace = netfs_whole_folio_modify_efault;
 			goto copied;
 		}
 
@@ -328,16 +348,10 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 				goto copy_failed;
 			finfo->dirty_len += copied;
 			if (finfo->dirty_offset == 0 && finfo->dirty_len == flen) {
-				if (finfo->netfs_group)
-					folio_change_private(folio, finfo->netfs_group);
-				else
-					folio_detach_private(folio);
-				folio_mark_uptodate(folio);
-				kfree(finfo);
 				trace = netfs_streaming_cont_filled_page;
-			} else {
-				trace = netfs_streaming_write_cont;
+				goto folio_now_filled;
 			}
+			trace = netfs_streaming_write_cont;
 			goto copied;
 		}
 
@@ -351,6 +365,13 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 			goto out;
 		continue;
 
+	folio_now_filled:
+		if (finfo->netfs_group)
+			folio_change_private(folio, finfo->netfs_group);
+		else
+			folio_detach_private(folio);
+		folio_mark_uptodate(folio);
+		kfree(finfo);
 	copied:
 		trace_netfs_folio(folio, trace);
 		flush_dcache_folio(folio);
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index 88d814ba1e697..db045135406c9 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -177,6 +177,9 @@
 	EM(netfs_folio_is_uptodate,		"mod-uptodate")	\
 	EM(netfs_just_prefetch,			"mod-prefetch")	\
 	EM(netfs_whole_folio_modify,		"mod-whole-f")	\
+	EM(netfs_whole_folio_modify_efault,	"mod-whole-f!")	\
+	EM(netfs_whole_folio_modify_filled,	"mod-whole-f+")	\
+	EM(netfs_whole_folio_modify_filled_efault, "mod-whole-f+!") \
 	EM(netfs_modify_and_clear,		"mod-n-clear")	\
 	EM(netfs_streaming_write,		"mod-streamw")	\
 	EM(netfs_streaming_write_cont,		"mod-streamw+")	\
-- 
2.53.0

[PATCH 6.18 240/377] netfs: Fix potential deadlock in write-through mode

[Greg Kroah-Hartman]

6.18-stable review patch.  If anyone has any objections, please let me know.

------------------

From: David Howells <dhowells@redhat.com>

[ Upstream commit b6a4ae1634b3ad2aaa05222e53d36da532852faf ]

Fix netfs_advance_writethrough() to always unlock the supplied folio and to
mark it dirty if it isn't yet written to the end.  Unfortunately, it can't
be marked for writeback until the folio is done with as that may cause a
deadlock against mmapped reads and writes.

Even though it has been marked dirty, premature writeback can't occur as
the caller is holding both inode->i_rwsem (which will prevent concurrent
truncation, fallocation, DIO and other writes) and ictx->wb_lock (which
will cause flushing to wait and writeback to skip or wait).

Note that this may be easier to deal with once the queuing of folios is
split from the generation of subrequests.

Fixes: 288ace2f57c9 ("netfs: New writeback implementation")
Closes: https://sashiko.dev/#/patchset/20260427154639.180684-1-dhowells%40redhat.com
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://patch.msgid.link/20260512123404.719402-15-dhowells@redhat.com
cc: Paulo Alcantara <pc@manguebit.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/netfs/write_issue.c | 39 +++++++++++++++++++++++++--------------
 1 file changed, 25 insertions(+), 14 deletions(-)

diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c
index 2db688f941251..9bf05099155dc 100644
--- a/fs/netfs/write_issue.c
+++ b/fs/netfs/write_issue.c
@@ -413,12 +413,7 @@ static int netfs_write_folio(struct netfs_io_request *wreq,
 	if (streamw)
 		netfs_issue_write(wreq, cache);
 
-	/* Flip the page to the writeback state and unlock.  If we're called
-	 * from write-through, then the page has already been put into the wb
-	 * state.
-	 */
-	if (wreq->origin == NETFS_WRITEBACK)
-		folio_start_writeback(folio);
+	folio_start_writeback(folio);
 	folio_unlock(folio);
 
 	if (fgroup == NETFS_FOLIO_COPY_TO_CACHE) {
@@ -646,29 +641,41 @@ int netfs_advance_writethrough(struct netfs_io_request *wreq, struct writeback_c
 			       struct folio *folio, size_t copied, bool to_page_end,
 			       struct folio **writethrough_cache)
 {
+	int ret;
+
 	_enter("R=%x ic=%zu ws=%u cp=%zu tp=%u",
 	       wreq->debug_id, wreq->buffer.iter.count, wreq->wsize, copied, to_page_end);
 
-	if (!*writethrough_cache) {
-		if (folio_test_dirty(folio))
-			/* Sigh.  mmap. */
-			folio_clear_dirty_for_io(folio);
+	/* The folio is locked. */
 
+	if (*writethrough_cache != folio) {
+		if (*writethrough_cache) {
+			/* Did the folio get moved? */
+			folio_put(*writethrough_cache);
+			*writethrough_cache = NULL;
+		}
 		/* We can make multiple writes to the folio... */
-		folio_start_writeback(folio);
 		if (wreq->len == 0)
 			trace_netfs_folio(folio, netfs_folio_trace_wthru);
 		else
 			trace_netfs_folio(folio, netfs_folio_trace_wthru_plus);
 		*writethrough_cache = folio;
+		folio_get(folio);
 	}
 
 	wreq->len += copied;
-	if (!to_page_end)
+
+	if (!to_page_end) {
+		folio_mark_dirty(folio);
+		folio_unlock(folio);
 		return 0;
+	}
 
+	ret = netfs_write_folio(wreq, wbc, folio);
+	folio_put(*writethrough_cache);
 	*writethrough_cache = NULL;
-	return netfs_write_folio(wreq, wbc, folio);
+	wreq->submitted = wreq->len;
+	return ret;
 }
 
 /*
@@ -682,8 +689,12 @@ ssize_t netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_c
 
 	_enter("R=%x", wreq->debug_id);
 
-	if (writethrough_cache)
+	if (writethrough_cache) {
+		folio_lock(writethrough_cache);
 		netfs_write_folio(wreq, wbc, writethrough_cache);
+		folio_put(writethrough_cache);
+		wreq->submitted = wreq->len;
+	}
 
 	netfs_end_issue_write(wreq);
 
-- 
2.53.0

[PATCH 6.18 241/377] netfs: Fix read-gaps to remove netfs_folio from filled folio

[Greg Kroah-Hartman]

6.18-stable review patch.  If anyone has any objections, please let me know.

------------------

From: David Howells <dhowells@redhat.com>

[ Upstream commit a41168aef634356a9b87ec44349e3c82835700a5 ]

Fix netfs_read_gaps() to remove the netfs_folio record from the folio
record before marking the folio uptodate if it successfully fills the gaps
around the dirty data in a streaming write folio (dirty, but not uptodate).

Found with:

    fsx -q -N 1000000 -p 10000 -o 128000 -l 600000 \
        /xfstest.test/junk --replay-ops=junk.fsxops

using the following as junk.fsxops:

    truncate 0x0 0x138b1 0x8b15d *
    write 0x507ee 0x10df7 0x927c0
    write 0x19993 0x10e04 0x927c0 *
    mapwrite 0x66214 0x1a253 0x927c0
    copy_range 0xb704 0x89b9 0x24429 0x79380
    write 0x2402b 0x144a2 0x90660 *
    mapwrite 0x204d5 0x140a0 0x927c0 *
    copy_range 0x1f72c 0x137d0 0x7a906 0x927c0 *
    read 0 0x9157c 0x9157c

on cifs with the default cache option.

It shows folio 0x24 misbehaving if the FMODE_READ check is commented out in
netfs_perform_write():

                if (//(file->f_mode & FMODE_READ) ||
                    netfs_is_cache_enabled(ctx)) {

and no fscache.  This was initially found with the generic/522 xfstest.

Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://patch.msgid.link/20260512123404.719402-16-dhowells@redhat.com
Fixes: ee4cdf7ba857 ("netfs: Speed up buffered reading")
cc: Paulo Alcantara <pc@manguebit.org>
cc: Matthew Wilcox <willy@infradead.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/netfs/buffered_read.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index e6157122da3a4..3531c19eea97a 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -394,6 +394,7 @@ static int netfs_read_gaps(struct file *file, struct folio *folio)
 {
 	struct netfs_io_request *rreq;
 	struct address_space *mapping = folio->mapping;
+	struct netfs_group *group = netfs_folio_group(folio);
 	struct netfs_folio *finfo = netfs_folio_info(folio);
 	struct netfs_inode *ctx = netfs_inode(mapping->host);
 	struct folio *sink = NULL;
@@ -460,6 +461,12 @@ static int netfs_read_gaps(struct file *file, struct folio *folio)
 
 	ret = netfs_wait_for_read(rreq);
 	if (ret >= 0) {
+		if (group)
+			folio_change_private(folio, group);
+		else
+			folio_detach_private(folio);
+		kfree(finfo);
+		trace_netfs_folio(folio, netfs_folio_trace_filled_gaps);
 		flush_dcache_folio(folio);
 		folio_mark_uptodate(folio);
 	}
@@ -495,10 +502,8 @@ int netfs_read_folio(struct file *file, struct folio *folio)
 	struct netfs_inode *ctx = netfs_inode(mapping->host);
 	int ret;
 
-	if (folio_test_dirty(folio)) {
-		trace_netfs_folio(folio, netfs_folio_trace_read_gaps);
+	if (folio_test_dirty(folio))
 		return netfs_read_gaps(file, folio);
-	}
 
 	_enter("%lx", folio->index);
 
-- 
2.53.0

[PATCH 6.18 242/377] netfs: Fix write streaming disablement if fd open O_RDWR

[Greg Kroah-Hartman]

6.18-stable review patch.  If anyone has any objections, please let me know.

------------------

From: David Howells <dhowells@redhat.com>

[ Upstream commit 70a7b9193bbbfceaab5974de66834c64ccc875dd ]

In netfs_perform_write(), "write streaming" (the caching of dirty data in
dirty but !uptodate folios) is performed to avoid the need to read data
that is just going to get immediately overwritten.  However, this is/will
be disabled in three circumstances: if the fd is open O_RDWR, if fscache is
in use (as we need to round out the blocks for DIO) or if content
encryption is enabled (again for rounding out purposes).

The idea behind disabling it if the fd is open O_RDWR is that we'd need to
flush the write-streaming page before we could read the data, particularly
through mmap.  But netfs now fills in the gaps if ->read_folio() is called
on the page, so that is unnecessary.  Further, this doesn't actually work
if a separate fd is open for reading.

Fix this by removing the check for O_RDWR, thereby allowing streaming
writes even when we might read.

This caused a number of problems with the generic/522 xfstest, but those
are now fixed.

Fixes: c38f4e96e605 ("netfs: Provide func to copy data to pagecache for buffered write")
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://patch.msgid.link/20260512123404.719402-17-dhowells@redhat.com
cc: Paulo Alcantara <pc@manguebit.org>
cc: Matthew Wilcox <willy@infradead.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/netfs/buffered_write.c | 17 +++++++----------
 1 file changed, 7 insertions(+), 10 deletions(-)

diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 99736895e964f..60215a7723574 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -204,11 +204,11 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 		}
 
 		/* Decide how we should modify a folio.  We might be attempting
-		 * to do write-streaming, in which case we don't want to a
-		 * local RMW cycle if we can avoid it.  If we're doing local
-		 * caching or content crypto, we award that priority over
-		 * avoiding RMW.  If the file is open readably, then we also
-		 * assume that we may want to read what we wrote.
+		 * to do write-streaming, as we don't want to a local RMW cycle
+		 * if we can avoid it.  If we're doing local caching or content
+		 * crypto, we award that priority over avoiding RMW.  If the
+		 * file is open readably, then we let ->read_folio() fill in
+		 * the gaps.
 		 */
 		finfo = netfs_folio_info(folio);
 		group = netfs_folio_group(folio);
@@ -284,12 +284,9 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 
 		/* We don't want to do a streaming write on a file that loses
 		 * caching service temporarily because the backing store got
-		 * culled and we don't really want to get a streaming write on
-		 * a file that's open for reading as ->read_folio() then has to
-		 * be able to flush it.
+		 * culled.
 		 */
-		if ((file->f_mode & FMODE_READ) ||
-		    netfs_is_cache_enabled(ctx)) {
+		if (netfs_is_cache_enabled(ctx)) {
 			if (finfo) {
 				netfs_stat(&netfs_n_wh_wstream_conflict);
 				goto flush_content;
-- 
2.53.0

[PATCH 6.18 243/377] netfs: Fix early put of sink folio in netfs_read_gaps()

[Greg Kroah-Hartman]

6.18-stable review patch.  If anyone has any objections, please let me know.

------------------

From: David Howells <dhowells@redhat.com>

[ Upstream commit 3e5dd91b87a8b1450217b56a336bee315f40da7d ]

Fix netfs_read_gaps() to release the sink page it uses after waiting for
the request to complete.  The way the sink page is used is that an
ITER_BVEC-class iterator is created that has the gaps from the target folio
at either end, but has the sink page tiled over the middle so that a single
read op can fill in both gaps.

The bug was found by KASAN detecting a UAF on the generic/075 xfstest in
the cifsd kernel thread that handles reception of data from the TCP socket:

 BUG: KASAN: use-after-free in _copy_to_iter+0x48a/0xa20
 Write of size 885 at addr ffff888107f92000 by task cifsd/1285
 CPU: 2 UID: 0 PID: 1285 Comm: cifsd Not tainted 7.0.0 #6 PREEMPT(lazy)
 Call Trace:
  dump_stack_lvl+0x5d/0x80
  print_report+0x17f/0x4f1
  kasan_report+0x100/0x1e0
  kasan_check_range+0x10f/0x1e0
  __asan_memcpy+0x3c/0x60
  _copy_to_iter+0x48a/0xa20
  __skb_datagram_iter+0x2c9/0x430
  skb_copy_datagram_iter+0x6e/0x160
  tcp_recvmsg_locked+0xce0/0x1130
  tcp_recvmsg+0xeb/0x300
  inet_recvmsg+0xcf/0x3a0
  sock_recvmsg+0xea/0x100
  cifs_readv_from_socket+0x3a6/0x4d0 [cifs]
  cifs_read_iter_from_socket+0xdd/0x130 [cifs]
  cifs_readv_receive+0xaad/0xb10 [cifs]
  cifs_demultiplex_thread+0x1148/0x1740 [cifs]
  kthread+0x1cf/0x210

Fixes: ee4cdf7ba857 ("netfs: Speed up buffered reading")
Reported-by: Steve French <sfrench@samba.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://patch.msgid.link/20260512123404.719402-18-dhowells@redhat.com
Reviewed-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
cc: Paulo Alcantara <pc@manguebit.org>
cc: Matthew Wilcox <willy@infradead.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/netfs/buffered_read.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index 3531c19eea97a..762ff928bc878 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -456,9 +456,6 @@ static int netfs_read_gaps(struct file *file, struct folio *folio)
 
 	netfs_read_to_pagecache(rreq, NULL);
 
-	if (sink)
-		folio_put(sink);
-
 	ret = netfs_wait_for_read(rreq);
 	if (ret >= 0) {
 		if (group)
@@ -470,6 +467,9 @@ static int netfs_read_gaps(struct file *file, struct folio *folio)
 		flush_dcache_folio(folio);
 		folio_mark_uptodate(folio);
 	}
+
+	if (sink)
+		folio_put(sink);
 	folio_unlock(folio);
 	netfs_put_request(rreq, netfs_rreq_trace_put_return);
 	return ret < 0 ? ret : 0;
-- 
2.53.0

[PATCH 6.18 244/377] netfs: Fix leak of request in netfs_write_begin() error handling

[Greg Kroah-Hartman]

6.18-stable review patch.  If anyone has any objections, please let me know.

------------------

From: David Howells <dhowells@redhat.com>

[ Upstream commit 5046a34f0643441f05b0253ea64e1a3af87efe14 ]

Fix netfs_write_begin() to not leak our ref on the request in the event
that we get an error from netfs_wait_for_read().

Fixes: 4090b31422a6 ("netfs: Add a function to consolidate beginning a read")
Closes: https://sashiko.dev/#/patchset/20260414082004.3756080-1-dhowells%40redhat.com
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://patch.msgid.link/20260512123404.719402-19-dhowells@redhat.com
cc: Paulo Alcantara <pc@manguebit.org>
cc: Matthew Wilcox <willy@infradead.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/netfs/buffered_read.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index 762ff928bc878..085cd392bf5ac 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -686,9 +686,9 @@ int netfs_write_begin(struct netfs_inode *ctx,
 
 	netfs_read_to_pagecache(rreq, NULL);
 	ret = netfs_wait_for_read(rreq);
+	netfs_put_request(rreq, netfs_rreq_trace_put_return);
 	if (ret < 0)
 		goto error;
-	netfs_put_request(rreq, netfs_rreq_trace_put_return);
 
 have_folio:
 	ret = folio_wait_private_2_killable(folio);
-- 
2.53.0

[PATCH 6.18 245/377] netfs: Fix potential UAF in netfs_unlock_abandoned_read_pages()

[Greg Kroah-Hartman]

6.18-stable review patch.  If anyone has any objections, please let me know.

------------------

From: David Howells <dhowells@redhat.com>

[ Upstream commit dbe556972100fabb8e5a1b3d2163831ff07b1e8e ]

netfs_unlock_abandoned_read_pages(rreq) accesses the index of the folios it
is wanting to unlock and compares that to rreq->no_unlock_folio so that it
doesn't unlock a folio being read for netfs_perform_write() or
netfs_write_begin().

However, given that netfs_unlock_abandoned_read_pages() is called _after_
NETFS_RREQ_IN_PROGRESS is cleared, the one folio that it's not allowed to
dereference is the one specified by ->no_unlock_folio as ownership
immediately reverts to the caller.

Fix this by storing the folio pointer instead and using that rather than
the index.  Also fix netfs_unlock_read_folio() where the same applies.

Fixes: ee4cdf7ba857 ("netfs: Speed up buffered reading")
Closes: https://sashiko.dev/#/patchset/20260414082004.3756080-1-dhowells%40redhat.com
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://patch.msgid.link/20260512123404.719402-20-dhowells@redhat.com
cc: Paulo Alcantara <pc@manguebit.org>
cc: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
cc: Matthew Wilcox <willy@infradead.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/netfs/buffered_read.c | 4 ++--
 fs/netfs/read_collect.c  | 2 +-
 fs/netfs/read_retry.c    | 2 +-
 include/linux/netfs.h    | 2 +-
 4 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index 085cd392bf5ac..ebaabec376326 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -669,7 +669,7 @@ int netfs_write_begin(struct netfs_inode *ctx,
 		ret = PTR_ERR(rreq);
 		goto error;
 	}
-	rreq->no_unlock_folio	= folio->index;
+	rreq->no_unlock_folio	= folio;
 	__set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags);
 
 	ret = netfs_begin_cache_read(rreq, ctx);
@@ -735,7 +735,7 @@ int netfs_prefetch_for_write(struct file *file, struct folio *folio,
 		goto error;
 	}
 
-	rreq->no_unlock_folio = folio->index;
+	rreq->no_unlock_folio = folio;
 	__set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags);
 	ret = netfs_begin_cache_read(rreq, ctx);
 	if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c
index d2d902f466271..4c7312a4c8597 100644
--- a/fs/netfs/read_collect.c
+++ b/fs/netfs/read_collect.c
@@ -83,7 +83,7 @@ static void netfs_unlock_read_folio(struct netfs_io_request *rreq,
 	}
 
 just_unlock:
-	if (folio->index == rreq->no_unlock_folio &&
+	if (folio == rreq->no_unlock_folio &&
 	    test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) {
 		_debug("no unlock");
 	} else {
diff --git a/fs/netfs/read_retry.c b/fs/netfs/read_retry.c
index 68fc869513ef1..999177426141a 100644
--- a/fs/netfs/read_retry.c
+++ b/fs/netfs/read_retry.c
@@ -288,7 +288,7 @@ void netfs_unlock_abandoned_read_pages(struct netfs_io_request *rreq)
 			struct folio *folio = folioq_folio(p, slot);
 
 			if (folio && !folioq_is_marked2(p, slot)) {
-				if (folio->index == rreq->no_unlock_folio &&
+				if (folio == rreq->no_unlock_folio &&
 				    test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO,
 					     &rreq->flags)) {
 					_debug("no unlock");
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index ba17ac5bf356a..62a528f90666b 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -252,7 +252,7 @@ struct netfs_io_request {
 	unsigned long long	collected_to;	/* Point we've collected to */
 	unsigned long long	cleaned_to;	/* Position we've cleaned folios to */
 	unsigned long long	abandon_to;	/* Position to abandon folios to */
-	pgoff_t			no_unlock_folio; /* Don't unlock this folio after read */
+	const struct folio	*no_unlock_folio; /* Don't unlock this folio after read */
 	unsigned int		direct_bv_count; /* Number of elements in direct_bv[] */
 	unsigned int		debug_id;
 	unsigned int		rsize;		/* Maximum read size (0 for none) */
-- 
2.53.0

[PATCH 6.18 246/377] netfs: Fix partial invalidation of streaming-write folio

[Greg Kroah-Hartman]

6.18-stable review patch.  If anyone has any objections, please let me know.

------------------

From: David Howells <dhowells@redhat.com>

[ Upstream commit 6d91acc7fb85d33ea58fca9b964a32a453937f4b ]

In netfs_invalidate_folio(), if the region of a partial invalidation
overlaps the front (but not all) of a dirty write cached in a streaming
write page (dirty, but not uptodate, with the dirty region tracked by a
netfs_folio struct), the function modifies the dirty region - but
incorrectly as it moves the region forward by setting the start to the
start, not the end, of the invalidation region.

Fix this by setting finfo->dirty_offset to the end of the invalidation
region (iend).

Fixes: cce6bfa6ca0e ("netfs: Fix trimming of streaming-write folios in netfs_inval_folio()")
Closes: https://sashiko.dev/#/patchset/20260414082004.3756080-1-dhowells%40redhat.com
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://patch.msgid.link/20260512123404.719402-21-dhowells@redhat.com
cc: Paulo Alcantara <pc@manguebit.org>
cc: Matthew Wilcox <willy@infradead.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/netfs/misc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
index eb309bef72608..1109ac3791281 100644
--- a/fs/netfs/misc.c
+++ b/fs/netfs/misc.c
@@ -255,7 +255,7 @@ void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length)
 				goto erase_completely;
 			/* Move the start of the data. */
 			finfo->dirty_len = fend - iend;
-			finfo->dirty_offset = offset;
+			finfo->dirty_offset = iend;
 			trace_netfs_folio(folio, netfs_folio_trace_invalidate_front);
 			return;
 		}
-- 
2.53.0

[PATCH 6.18 247/377] netfs: Fix folio->private handling in netfs_perform_write()

[Greg Kroah-Hartman]

6.18-stable review patch.  If anyone has any objections, please let me know.

------------------

From: David Howells <dhowells@redhat.com>

[ Upstream commit ccde2ac757c713535b224233a296de40efe5212d ]

Under some circumstances, netfs_perform_write() doesn't correctly
manipulate folio->private between NULL, NETFS_FOLIO_COPY_TO_CACHE, pointing
to a group and pointing to a netfs_folio struct, leading to potential
multiple attachments of private data with associated folio ref leaks and
also leaks of netfs_folio structs or netfs_group refs.

Fix this by consolidating the place at which a folio is marked uptodate in
one place and having that look at what's attached to folio->private and
decide how to clean it up and then set the new group.  Also, the content
shouldn't be flushed if group is NULL, even if a group is specified in the
netfs_group parameter, as that would be the case for a new folio.  A
filesystem should always specify netfs_group or never specify netfs_group.

The Sashiko auto-review tool noted that it was theoretically possible that
the fpos >= ctx->zero_point section might leak if it modified a streaming
write folio.  This is unlikely, but with a network filesystem, third party
changes can happen.  It also pointed out that __netfs_set_group() would
leak if called multiple times on the same folio from the "whole folio
modify section".

Fixes: 8f52de0077ba ("netfs: Reduce number of conditional branches in netfs_perform_write()")
Closes: https://sashiko.dev/#/patchset/20260414082004.3756080-1-dhowells%40redhat.com
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://patch.msgid.link/20260512123404.719402-22-dhowells@redhat.com
cc: Paulo Alcantara <pc@manguebit.org>
cc: Matthew Wilcox <willy@infradead.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/netfs/buffered_write.c    | 134 +++++++++++++++++++++--------------
 include/trace/events/netfs.h |   1 +
 2 files changed, 82 insertions(+), 53 deletions(-)

diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 60215a7723574..dd0ce7b769ce0 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -13,24 +13,6 @@
 #include <linux/pagevec.h>
 #include "internal.h"
 
-static void __netfs_set_group(struct folio *folio, struct netfs_group *netfs_group)
-{
-	if (netfs_group)
-		folio_attach_private(folio, netfs_get_group(netfs_group));
-}
-
-static void netfs_set_group(struct folio *folio, struct netfs_group *netfs_group)
-{
-	void *priv = folio_get_private(folio);
-
-	if (unlikely(priv != netfs_group)) {
-		if (netfs_group && (!priv || priv == NETFS_FOLIO_COPY_TO_CACHE))
-			folio_attach_private(folio, netfs_get_group(netfs_group));
-		else if (!netfs_group && priv == NETFS_FOLIO_COPY_TO_CACHE)
-			folio_detach_private(folio);
-	}
-}
-
 /*
  * Grab a folio for writing and lock it.  Attempt to allocate as large a folio
  * as possible to hold as much of the remaining length as possible in one go.
@@ -158,6 +140,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 		size_t offset;	/* Offset into pagecache folio */
 		size_t part;	/* Bytes to write to folio */
 		size_t copied;	/* Bytes copied from user */
+		void *priv;
 
 		offset = pos & (max_chunk - 1);
 		part = min(max_chunk - offset, iov_iter_count(iter));
@@ -203,6 +186,25 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 			goto error_folio_unlock;
 		}
 
+		finfo = netfs_folio_info(folio);
+		group = netfs_folio_group(folio);
+
+		/* If the requested group differs from the group set on the
+		 * page, then we need to flush out the folio if it has a group
+		 * set (ie. is non-NULL).  Note that COPY_TO_CACHE is a special
+		 * case, being a netfs annotation rather than an actual group.
+		 *
+		 * The filesystem isn't permitted to mix writes with groups and
+		 * writes without groups as the NULL group is used to indicate
+		 * that no group is set.
+		 */
+		if (unlikely(group != netfs_group) &&
+		    group != NETFS_FOLIO_COPY_TO_CACHE &&
+		    group) {
+			WARN_ON_ONCE(!netfs_group);
+			goto flush_content;
+		}
+
 		/* Decide how we should modify a folio.  We might be attempting
 		 * to do write-streaming, as we don't want to a local RMW cycle
 		 * if we can avoid it.  If we're doing local caching or content
@@ -210,22 +212,14 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 		 * file is open readably, then we let ->read_folio() fill in
 		 * the gaps.
 		 */
-		finfo = netfs_folio_info(folio);
-		group = netfs_folio_group(folio);
-
-		if (unlikely(group != netfs_group) &&
-		    group != NETFS_FOLIO_COPY_TO_CACHE)
-			goto flush_content;
-
 		if (folio_test_uptodate(folio)) {
 			if (mapping_writably_mapped(mapping))
 				flush_dcache_folio(folio);
 			copied = copy_folio_from_iter_atomic(folio, offset, part, iter);
 			if (unlikely(copied == 0))
 				goto copy_failed;
-			netfs_set_group(folio, netfs_group);
 			trace = netfs_folio_is_uptodate;
-			goto copied;
+			goto copied_uptodate;
 		}
 
 		/* If the page is above the zero-point then we assume that the
@@ -238,24 +232,22 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 			if (unlikely(copied == 0))
 				goto copy_failed;
 			folio_zero_segment(folio, offset + copied, flen);
-			__netfs_set_group(folio, netfs_group);
-			folio_mark_uptodate(folio);
-			trace = netfs_modify_and_clear;
-			goto copied;
+			if (finfo)
+				trace = netfs_modify_and_clear_rm_finfo;
+			else
+				trace = netfs_modify_and_clear;
+			goto mark_uptodate;
 		}
 
 		/* See if we can write a whole folio in one go. */
 		if (!maybe_trouble && offset == 0 && part >= flen) {
 			copied = copy_folio_from_iter_atomic(folio, offset, part, iter);
 			if (likely(copied == part)) {
-				if (finfo) {
+				if (finfo)
 					trace = netfs_whole_folio_modify_filled;
-					goto folio_now_filled;
-				}
-				__netfs_set_group(folio, netfs_group);
-				folio_mark_uptodate(folio);
-				trace = netfs_whole_folio_modify;
-				goto copied;
+				else
+					trace = netfs_whole_folio_modify;
+				goto mark_uptodate;
 			}
 			if (copied == 0)
 				goto copy_failed;
@@ -273,7 +265,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 			finfo->dirty_len += finfo->dirty_offset;
 			if (finfo->dirty_len == flen) {
 				trace = netfs_whole_folio_modify_filled_efault;
-				goto folio_now_filled;
+				goto mark_uptodate;
 			}
 			if (copied > finfo->dirty_len)
 				finfo->dirty_len = copied;
@@ -301,11 +293,11 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 			copied = copy_folio_from_iter_atomic(folio, offset, part, iter);
 			if (unlikely(copied == 0))
 				goto copy_failed;
-			netfs_set_group(folio, netfs_group);
 			trace = netfs_just_prefetch;
-			goto copied;
+			goto copied_uptodate;
 		}
 
+		/* Do a streaming write on a folio that has nothing in it yet. */
 		if (!finfo) {
 			ret = -EIO;
 			if (WARN_ON(folio_get_private(folio)))
@@ -314,10 +306,8 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 			if (unlikely(copied == 0))
 				goto copy_failed;
 			if (offset == 0 && copied == flen) {
-				__netfs_set_group(folio, netfs_group);
-				folio_mark_uptodate(folio);
 				trace = netfs_streaming_filled_page;
-				goto copied;
+				goto mark_uptodate;
 			}
 
 			finfo = kzalloc(sizeof(*finfo), GFP_KERNEL);
@@ -346,7 +336,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 			finfo->dirty_len += copied;
 			if (finfo->dirty_offset == 0 && finfo->dirty_len == flen) {
 				trace = netfs_streaming_cont_filled_page;
-				goto folio_now_filled;
+				goto mark_uptodate;
 			}
 			trace = netfs_streaming_write_cont;
 			goto copied;
@@ -362,13 +352,36 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 			goto out;
 		continue;
 
-	folio_now_filled:
-		if (finfo->netfs_group)
-			folio_change_private(folio, finfo->netfs_group);
-		else
-			folio_detach_private(folio);
+		/* Mark a folio as being up to data when we've filled it
+		 * completely.  If the folio has a group attached, then it must
+		 * be the same group, otherwise we should have flushed it out
+		 * above.  We have to get rid of the netfs_folio struct if
+		 * there was one.
+		 */
+	mark_uptodate:
 		folio_mark_uptodate(folio);
-		kfree(finfo);
+
+	copied_uptodate:
+		priv = folio_get_private(folio);
+		if (likely(priv == netfs_group)) {
+			/* Already set correctly; no change required. */
+		} else if (priv == NETFS_FOLIO_COPY_TO_CACHE) {
+			if (!netfs_group)
+				folio_detach_private(folio);
+			else
+				folio_change_private(folio, netfs_get_group(netfs_group));
+		} else if (!priv) {
+			folio_attach_private(folio, netfs_get_group(netfs_group));
+		} else {
+			WARN_ON_ONCE(!finfo);
+			if (netfs_group)
+				/* finfo->netfs_group has a ref */
+				folio_change_private(folio, netfs_group);
+			else
+				folio_detach_private(folio);
+			kfree(finfo);
+		}
+
 	copied:
 		trace_netfs_folio(folio, trace);
 		flush_dcache_folio(folio);
@@ -531,6 +544,7 @@ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_gr
 	struct inode *inode = file_inode(file);
 	struct netfs_inode *ictx = netfs_inode(inode);
 	vm_fault_t ret = VM_FAULT_NOPAGE;
+	void *priv;
 	int err;
 
 	_enter("%lx", folio->index);
@@ -551,7 +565,9 @@ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_gr
 	}
 
 	group = netfs_folio_group(folio);
-	if (group != netfs_group && group != NETFS_FOLIO_COPY_TO_CACHE) {
+	if (group &&
+	    group != netfs_group &&
+	    group != NETFS_FOLIO_COPY_TO_CACHE) {
 		folio_unlock(folio);
 		err = filemap_fdatawrite_range(mapping,
 					       folio_pos(folio),
@@ -573,7 +589,19 @@ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_gr
 		trace_netfs_folio(folio, netfs_folio_trace_mkwrite_plus);
 	else
 		trace_netfs_folio(folio, netfs_folio_trace_mkwrite);
-	netfs_set_group(folio, netfs_group);
+
+	priv = folio_get_private(folio);
+	if (priv != netfs_group) {
+		if (!netfs_group && priv == NETFS_FOLIO_COPY_TO_CACHE)
+			folio_detach_private(folio);
+		else if (netfs_group && priv == NETFS_FOLIO_COPY_TO_CACHE)
+			folio_change_private(folio, netfs_get_group(netfs_group));
+		else if (netfs_group && !priv)
+			folio_attach_private(folio, netfs_get_group(netfs_group));
+		else
+			WARN_ON_ONCE(1);
+	}
+
 	file_update_time(file);
 	set_bit(NETFS_ICTX_MODIFIED_ATTR, &ictx->flags);
 	if (ictx->ops->post_modify)
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index db045135406c9..3fe3980902c24 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -181,6 +181,7 @@
 	EM(netfs_whole_folio_modify_filled,	"mod-whole-f+")	\
 	EM(netfs_whole_folio_modify_filled_efault, "mod-whole-f+!") \
 	EM(netfs_modify_and_clear,		"mod-n-clear")	\
+	EM(netfs_modify_and_clear_rm_finfo,	"mod-n-clear+")	\
 	EM(netfs_streaming_write,		"mod-streamw")	\
 	EM(netfs_streaming_write_cont,		"mod-streamw+")	\
 	EM(netfs_flush_content,			"flush")	\
-- 
2.53.0

[PATCH 6.18 248/377] netfs: Fix netfs_read_folio() to wait on writeback

[Greg Kroah-Hartman]

6.18-stable review patch.  If anyone has any objections, please let me know.

------------------

From: David Howells <dhowells@redhat.com>

[ Upstream commit ded0c6f1606061148c202825f7e53d711f9f84cf ]

Fix netfs_read_folio() to wait for an ongoing writeback to complete so that
it can trust the dirty flag and whatever is attached to folio->private
(folio->private may get cleaned up by the collector before it clears the
writeback flag).

Fixes: ee4cdf7ba857 ("netfs: Speed up buffered reading")
Closes: https://sashiko.dev/#/patchset/20260414082004.3756080-1-dhowells%40redhat.com
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://patch.msgid.link/20260512123404.719402-23-dhowells@redhat.com
cc: Paulo Alcantara <pc@manguebit.org>
cc: Matthew Wilcox <willy@infradead.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/netfs/buffered_read.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index ebaabec376326..fab3181c7f869 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -502,6 +502,8 @@ int netfs_read_folio(struct file *file, struct folio *folio)
 	struct netfs_inode *ctx = netfs_inode(mapping->host);
 	int ret;
 
+	folio_wait_writeback(folio);
+
 	if (folio_test_dirty(folio))
 		return netfs_read_gaps(file, folio);
 
-- 
2.53.0

[PATCH 6.18 249/377] netfs, afs: Fix write skipping in dir/link writepages

[Greg Kroah-Hartman]

6.18-stable review patch.  If anyone has any objections, please let me know.

------------------

From: David Howells <dhowells@redhat.com>

[ Upstream commit 9871938f99cc6cb266a77265491660e2375271f5 ]

Fix netfs_write_single() and afs_single_writepages() to better handle a
write that would be skipped due to lock contention and WB_SYNC_NONE by
returning 1 from netfs_write_single() if it skipped and making
afs_single_writepages() skip also.  If a skip occurs, the inode must be
re-marked as the VFS may have cleared the mark.

This is really only theoretical for directories in netfs_write_single() as
the only path to that is through afs_single_writepages() that takes the
->validate_lock around it, thereby serialising it.

Fixes: 6dd80936618c ("afs: Use netfslib for directories")
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://patch.msgid.link/20260512123404.719402-24-dhowells@redhat.com
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/afs/dir.c           | 11 ++++++++++-
 fs/netfs/write_issue.c |  7 ++++++-
 2 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 89d36e3e5c799..fa84610e0b0d9 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -2207,7 +2207,14 @@ int afs_single_writepages(struct address_space *mapping,
 	/* Need to lock to prevent the folio queue and folios from being thrown
 	 * away.
 	 */
-	down_read(&dvnode->validate_lock);
+	if (!down_read_trylock(&dvnode->validate_lock)) {
+		if (wbc->sync_mode == WB_SYNC_NONE) {
+			/* The VFS will have undirtied the inode. */
+			netfs_single_mark_inode_dirty(&dvnode->netfs.inode);
+			return 0;
+		}
+		down_read(&dvnode->validate_lock);
+	}
 
 	if (is_dir ?
 	    test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) :
@@ -2215,6 +2222,8 @@ int afs_single_writepages(struct address_space *mapping,
 		iov_iter_folio_queue(&iter, ITER_SOURCE, dvnode->directory, 0, 0,
 				     i_size_read(&dvnode->netfs.inode));
 		ret = netfs_writeback_single(mapping, wbc, &iter);
+		if (ret == 1)
+			ret = 0; /* Skipped write due to lock conflict. */
 	}
 
 	up_read(&dvnode->validate_lock);
diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c
index 9bf05099155dc..03d170b9022b7 100644
--- a/fs/netfs/write_issue.c
+++ b/fs/netfs/write_issue.c
@@ -829,6 +829,9 @@ static int netfs_write_folio_single(struct netfs_io_request *wreq,
  *
  * Write a monolithic, non-pagecache object back to the server and/or
  * the cache.
+ *
+ * Return: 0 if successful; 1 if skipped due to lock conflict and WB_SYNC_NONE;
+ * or a negative error code.
  */
 int netfs_writeback_single(struct address_space *mapping,
 			   struct writeback_control *wbc,
@@ -845,8 +848,10 @@ int netfs_writeback_single(struct address_space *mapping,
 
 	if (!mutex_trylock(&ictx->wb_lock)) {
 		if (wbc->sync_mode == WB_SYNC_NONE) {
+			/* The VFS will have undirtied the inode. */
+			netfs_single_mark_inode_dirty(&ictx->inode);
 			netfs_stat(&netfs_n_wb_lock_skip);
-			return 0;
+			return 1;
 		}
 		netfs_stat(&netfs_n_wb_lock_wait);
 		mutex_lock(&ictx->wb_lock);
-- 
2.53.0