Linux filesystem development
 help / color / mirror / Atom feed
From: Joanne Koong <joannelkoong@gmail.com>
To: brauner@kernel.org
Cc: willy@infradead.org, djwong@kernel.org, hch@infradead.org,
	bfoster@redhat.com, linux-fsdevel@vger.kernel.org
Subject: [PATCH v4 1/1] iomap: fix invalid folio access after folio_end_read()
Date: Fri, 23 Jan 2026 15:56:17 -0800	[thread overview]
Message-ID: <20260123235617.1026939-2-joannelkoong@gmail.com> (raw)
In-Reply-To: <20260123235617.1026939-1-joannelkoong@gmail.com>

If the folio does not have an iomap_folio_state (ifs) attached and the
folio gets read in by the filesystem's IO helper, folio_end_read() will
be called by the IO helper at any time. For this case, we cannot access
the folio after dispatching it to the IO helper, eg subsequent accesses
like

	if (ctx->cur_folio &&
                    offset_in_folio(ctx->cur_folio, iter->pos) == 0) {

are incorrect.

Fix these invalid accesses by invalidating ctx->cur_folio if all bytes
of the folio have been read in by the IO helper.

This allows us to also remove the +1 bias added for the ifs case. The
bias was previously added to ensure that if all bytes are read in, the
IO helper does not end the read on the folio until iomap has decremented
the bias.

Fixes: b2f35ac4146d ("iomap: add caller-provided callbacks for read and readahead")
Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
---
 fs/iomap/buffered-io.c | 69 ++++++++++++++++++++++--------------------
 1 file changed, 37 insertions(+), 32 deletions(-)

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 6beb876658c0..f8937fd5ee8e 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -409,8 +409,6 @@ static void iomap_read_init(struct folio *folio)
 	struct iomap_folio_state *ifs = folio->private;
 
 	if (ifs) {
-		size_t len = folio_size(folio);
-
 		/*
 		 * ifs->read_bytes_pending is used to track how many bytes are
 		 * read in asynchronously by the IO helper. We need to track
@@ -418,23 +416,19 @@ static void iomap_read_init(struct folio *folio)
 		 * reading in all the necessary ranges of the folio and can end
 		 * the read.
 		 *
-		 * Increase ->read_bytes_pending by the folio size to start, and
-		 * add a +1 bias. We'll subtract the bias and any uptodate /
-		 * zeroed ranges that did not require IO in iomap_read_end()
-		 * after we're done processing the folio.
+		 * Increase ->read_bytes_pending by the folio size to start.
+		 * We'll subtract any uptodate / zeroed ranges that did not
+		 * require IO in iomap_read_end() after we're done processing
+		 * the folio.
 		 *
 		 * We do this because otherwise, we would have to increment
 		 * ifs->read_bytes_pending every time a range in the folio needs
 		 * to be read in, which can get expensive since the spinlock
 		 * needs to be held whenever modifying ifs->read_bytes_pending.
-		 *
-		 * We add the bias to ensure the read has not been ended on the
-		 * folio when iomap_read_end() is called, even if the IO helper
-		 * has already finished reading in the entire folio.
 		 */
 		spin_lock_irq(&ifs->state_lock);
 		WARN_ON_ONCE(ifs->read_bytes_pending != 0);
-		ifs->read_bytes_pending = len + 1;
+		ifs->read_bytes_pending = folio_size(folio);
 		spin_unlock_irq(&ifs->state_lock);
 	}
 }
@@ -465,11 +459,9 @@ static void iomap_read_end(struct folio *folio, size_t bytes_submitted)
 
 		/*
 		 * Subtract any bytes that were initially accounted to
-		 * read_bytes_pending but skipped for IO. The +1 accounts for
-		 * the bias we added in iomap_read_init().
+		 * read_bytes_pending but skipped for IO.
 		 */
-		ifs->read_bytes_pending -=
-			(folio_size(folio) + 1 - bytes_submitted);
+		ifs->read_bytes_pending -= folio_size(folio) - bytes_submitted;
 
 		/*
 		 * If !ifs->read_bytes_pending, this means all pending reads by
@@ -483,18 +475,30 @@ static void iomap_read_end(struct folio *folio, size_t bytes_submitted)
 		spin_unlock_irq(&ifs->state_lock);
 		if (end_read)
 			folio_end_read(folio, uptodate);
-	} else if (!bytes_submitted) {
+	} else {
 		/*
-		 * If there were no bytes submitted, this means we are
-		 * responsible for unlocking the folio here, since no IO helper
-		 * has taken ownership of it. If there were bytes submitted,
-		 * then the IO helper will end the read via
-		 * iomap_finish_folio_read().
+		 * If a folio without an ifs is submitted to the IO helper, the
+		 * read must be on the entire folio and the IO helper takes
+		 * ownership of the folio. This means we should only enter
+		 * iomap_read_end() for the !ifs case if no bytes were submitted
+		 * to the IO helper, in which case we are responsible for
+		 * unlocking the folio here.
 		 */
+		WARN_ON_ONCE(bytes_submitted);
 		folio_unlock(folio);
 	}
 }
 
+static void iomap_read_submit_and_end(struct iomap_read_folio_ctx *ctx,
+		size_t bytes_submitted)
+{
+	if (ctx->ops->submit_read)
+		ctx->ops->submit_read(ctx);
+
+	if (ctx->cur_folio)
+		iomap_read_end(ctx->cur_folio, bytes_submitted);
+}
+
 static int iomap_read_folio_iter(struct iomap_iter *iter,
 		struct iomap_read_folio_ctx *ctx, size_t *bytes_submitted)
 {
@@ -502,6 +506,7 @@ static int iomap_read_folio_iter(struct iomap_iter *iter,
 	loff_t pos = iter->pos;
 	loff_t length = iomap_length(iter);
 	struct folio *folio = ctx->cur_folio;
+	size_t folio_len = folio_size(folio);
 	size_t poff, plen;
 	loff_t pos_diff;
 	int ret;
@@ -515,8 +520,7 @@ static int iomap_read_folio_iter(struct iomap_iter *iter,
 
 	ifs_alloc(iter->inode, folio, iter->flags);
 
-	length = min_t(loff_t, length,
-			folio_size(folio) - offset_in_folio(folio, pos));
+	length = min_t(loff_t, length, folio_len - offset_in_folio(folio, pos));
 	while (length) {
 		iomap_adjust_read_range(iter->inode, folio, &pos, length, &poff,
 				&plen);
@@ -542,7 +546,15 @@ static int iomap_read_folio_iter(struct iomap_iter *iter,
 			ret = ctx->ops->read_folio_range(iter, ctx, plen);
 			if (ret)
 				return ret;
+
 			*bytes_submitted += plen;
+			/*
+			 * If the entire folio has been read in by the IO
+			 * helper, then the helper owns the folio and will end
+			 * the read on it.
+			 */
+			if (*bytes_submitted == folio_len)
+				ctx->cur_folio = NULL;
 		}
 
 		ret = iomap_iter_advance(iter, plen);
@@ -572,10 +584,7 @@ void iomap_read_folio(const struct iomap_ops *ops,
 		iter.status = iomap_read_folio_iter(&iter, ctx,
 				&bytes_submitted);
 
-	if (ctx->ops->submit_read)
-		ctx->ops->submit_read(ctx);
-
-	iomap_read_end(folio, bytes_submitted);
+	iomap_read_submit_and_end(ctx, bytes_submitted);
 }
 EXPORT_SYMBOL_GPL(iomap_read_folio);
 
@@ -636,11 +645,7 @@ void iomap_readahead(const struct iomap_ops *ops,
 		iter.status = iomap_readahead_iter(&iter, ctx,
 					&cur_bytes_submitted);
 
-	if (ctx->ops->submit_read)
-		ctx->ops->submit_read(ctx);
-
-	if (ctx->cur_folio)
-		iomap_read_end(ctx->cur_folio, cur_bytes_submitted);
+	iomap_read_submit_and_end(ctx, cur_bytes_submitted);
 }
 EXPORT_SYMBOL_GPL(iomap_readahead);
 
-- 
2.47.3


  reply	other threads:[~2026-01-23 23:59 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-01-23 23:56 [PATCH v4 0/1] iomap: fix invalid folio access after folio_end_read() Joanne Koong
2026-01-23 23:56 ` Joanne Koong [this message]
2026-01-26  5:46   ` [PATCH v4 1/1] " Christoph Hellwig
2026-01-26 14:55     ` Matthew Wilcox
2026-01-26 14:59       ` Christoph Hellwig
2026-01-26 21:36       ` Joanne Koong
2026-01-26 21:42         ` Matthew Wilcox
2026-01-26 22:10           ` Joanne Koong

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260123235617.1026939-2-joannelkoong@gmail.com \
    --to=joannelkoong@gmail.com \
    --cc=bfoster@redhat.com \
    --cc=brauner@kernel.org \
    --cc=djwong@kernel.org \
    --cc=hch@infradead.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=willy@infradead.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox