FAILED: patch "[PATCH] xhci: fix lost bounce buffers on TDs spanning several ring" failed to apply to 6.12-stable tree

The patch below does not apply to the 6.12-stable tree.
If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <[email protected]>.

To reproduce the conflict and resubmit, you may use the following commands:

git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.12.y
git checkout FETCH_HEAD
git cherry-pick -x ff44dfb03a293bf30e31f98772a1dd316a6071d1
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<[email protected]>' --in-reply-to '2026090810-remold-gleaming-2a4e@gregkh' --subject-prefix 'PATCH 6.12.y' 'HEAD^..'

Possible dependencies:

thanks,

greg k-h

------------------ original commit in Linus's tree ------------------

From ff44dfb03a293bf30e31f98772a1dd316a6071d1 Mon Sep 17 00:00:00 2001
From: Arthur Gautier <[email protected]>
Date: Mon, 31 Aug 2026 12:04:48 +0300
Subject: [PATCH] xhci: fix lost bounce buffers on TDs spanning several ring
segments

When a TD reaches a link TRB with data that is not aligned to the endpoint's wMaxPacketSize, xhci_align_td() stages the unalignable tail through the bounce buffer of the ring segment holding that link TRB. xhci_unmap_td_bounce_buffer() later unmaps it and, for IN transfers, copies the data back into the URB's buffer.

The enqueue path records the segment that was bounced in td->bounce_seg, under the assumption that a TD never spans more than two ring segments. That assumption does not hold: a TD large enough to span three or more segments crosses several link TRBs and can be bounced at each of them. Only the last one survives in td->bounce_seg, so every earlier bounce buffer is neither copied back nor DMA unmapped.

The URB still completes with actual_length equal to the requested length and no error, so the transfer looks successful while a wMaxPacketSize sized hole in the destination buffer silently keeps its previous contents. It also leaks a DMA mapping per dropped bounce.

Any sufficiently large and fragmented bulk transfer can hit this. It was found with a USB mass storage device behind xHCI backing a dm-verity target with 512 byte hash blocks, where the stale data is detected rather than silently consumed. The device enumerates as SuperSpeed, so wMaxPacketSize is 1024, while dm-bufio issues one 512 byte bio per hash block. verity_prefetch_io() makes the block layer merge hundreds of them into a single request of up to 512 scatterlist entries of 512 bytes each. At 256 TRBs per ring segment such a TD spans three segments, and every segment boundary falls on an odd multiple of 512, i.e. unaligned to wMaxPacketSize. dm-bufio then caches a hash block holding stale data and dm-verity declares the metadata block corrupted:

device-mapper: verity: 8:2: metadata block 10850 is corrupted

A reproducer running this under qemu is available at
https://github.com/baloo/xhci-verity

The bounce state (bounce_buf, bounce_dma, bounce_len, bounce_offs) already lives on the ring segment, so there is nothing extra to track. Keep recording the last bounced segment in td->bounce_seg and, on completion, walk the segments from td->start_seg up to it, unmapping every segment that still has a pending bounce.

Stopping at td->bounce_seg rather than td->end_seg matters: a bounce implies the TD continues past that segment's link TRB, so bounce_seg is always strictly before end_seg, and a later TD may already have started in end_seg and been bounced there. Walking that far would copy a foreign bounce buffer into this URB and unmap it twice. It also keeps the walk correct if a TD ever wraps the whole ring so that end_seg == start_seg.

[mn: Add ring->num_segs check to prevent unlikely infinite for loop.]

index 9847c5bfc41b..ec278a9f9540 100644
@@ -824,21 +824,18 @@ static void xhci_giveback_urb_in_irq(struct xhci_hcd *xhci,
 	usb_hcd_giveback_urb(hcd, urb, status);
 }
 
-static void xhci_unmap_td_bounce_buffer(struct xhci_hcd *xhci,
-		struct xhci_ring *ring, struct xhci_td *td)
+static void xhci_unmap_one_bounce_buffer(struct xhci_hcd *xhci,
+		struct xhci_ring *ring, struct xhci_td *td,
+		struct xhci_segment *seg)
 {
 	struct device *dev = xhci_to_hcd(xhci)->self.sysdev;
-	struct xhci_segment *seg = td->bounce_seg;
 	struct urb *urb = td->urb;
 	size_t len;
 
-	if (!ring || !seg || !urb)
-		return;
-
 	if (usb_urb_dir_out(urb)) {
 		dma_unmap_single(dev, seg->bounce_dma, ring->bounce_buf_len,
 				 DMA_TO_DEVICE);
-		return;
+		goto done;
 	}
 
 	dma_unmap_single(dev, seg->bounce_dma, ring->bounce_buf_len,

@@ -854,10 +851,29 @@ static void xhci_unmap_td_bounce_buffer(struct xhci_hcd *xhci,
 		memcpy(urb->transfer_buffer + seg->bounce_offs, seg->bounce_buf,
 		       seg->bounce_len);
 	}
+done:
 	seg->bounce_len = 0;
 	seg->bounce_offs = 0;
 }
 
+static void xhci_unmap_td_bounce_buffer(struct xhci_hcd *xhci,
+		struct xhci_ring *ring, struct xhci_td *td)
+{
+	struct xhci_segment *seg;
+	int i = 0;
+
+	if (!td->bounce_seg || !ring || !td->urb)
+		return;
+
+	/* td->bounce_seg is the last one bounced, unmap them all */
+	for (seg = td->start_seg; i++ < ring->num_segs; seg = seg->next) {
+		if (seg->bounce_len)
+			xhci_unmap_one_bounce_buffer(xhci, ring, td, seg);
+		if (seg == td->bounce_seg)
+			break;
+	}
+}
+
 static void xhci_td_cleanup(struct xhci_hcd *xhci, struct xhci_td *td,
 			    struct xhci_ring *ep_ring, int status)
 {

@@ -3685,7 +3701,7 @@ int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 						  &trb_buff_len,
 						  ring->enq_seg)) {
 					send_addr = ring->enq_seg->bounce_dma;
-					/* assuming TD won't span 2 segs */
+					/* TD bounced at least, and last on this seg */
 					td->bounce_seg = ring->enq_seg;
 				}
 			}

When a TD reaches a link TRB with data that is not aligned to the endpoint's wMaxPacketSize, xhci_align_td() stages the unalignable tail through the bounce buffer of the ring segment holding that link TRB. xhci_unmap_td_bounce_buffer() later unmaps it and, for IN transfers, copies the data back into the URB's buffer.

The enqueue path records the segment that was bounced in td->bounce_seg, under the assumption that a TD never spans more than two ring segments. That assumption does not hold: a TD large enough to span three or more segments crosses several link TRBs and can be bounced at each of them. Only the last one survives in td->bounce_seg, so every earlier bounce buffer is neither copied back nor DMA unmapped.

The URB still completes with actual_length equal to the requested length and no error, so the transfer looks successful while a wMaxPacketSize sized hole in the destination buffer silently keeps its previous contents. It also leaks a DMA mapping per dropped bounce.

Any sufficiently large and fragmented bulk transfer can hit this. It was found with a USB mass storage device behind xHCI backing a dm-verity target with 512 byte hash blocks, where the stale data is detected rather than silently consumed. The device enumerates as SuperSpeed, so wMaxPacketSize is 1024, while dm-bufio issues one 512 byte bio per hash block. verity_prefetch_io() makes the block layer merge hundreds of them into a single request of up to 512 scatterlist entries of 512 bytes each. At 256 TRBs per ring segment such a TD spans three segments, and every segment boundary falls on an odd multiple of 512, i.e. unaligned to wMaxPacketSize. dm-bufio then caches a hash block holding stale data and dm-verity declares the metadata block corrupted:

device-mapper: verity: 8:2: metadata block 10850 is corrupted

A reproducer running this under qemu is available at
https://github.com/baloo/xhci-verity

The bounce state (bounce_buf, bounce_dma, bounce_len, bounce_offs) already lives on the ring segment, so there is nothing extra to track. Keep recording the last bounced segment in td->bounce_seg and, on completion, walk the segments from td->start_seg up to it, unmapping every segment that still has a pending bounce.

Stopping at td->bounce_seg rather than td->end_seg matters: a bounce implies the TD continues past that segment's link TRB, so bounce_seg is always strictly before end_seg, and a later TD may already have started in end_seg and been bounced there. Walking that far would copy a foreign bounce buffer into this URB and unmap it twice. It also keeps the walk correct if a TD ever wraps the whole ring so that end_seg == start_seg.

[mn: Add ring->num_segs check to prevent unlikely infinite for loop.]

---

cherry-picked on 6.12, built and tested with artificial repro on 5.10, looks like it will work for everything in between.

 drivers/usb/host/xhci-ring.c | 32 ++++++++++++++++++++++++--------
 1 file changed, 24 insertions(+), 8 deletions(-)

index a337e1fda33d..67804954e146 100644
@@ -739,21 +739,18 @@ static void xhci_giveback_urb_in_irq(struct xhci_hcd *xhci,
 	usb_hcd_giveback_urb(hcd, urb, status);
 }
 
-static void xhci_unmap_td_bounce_buffer(struct xhci_hcd *xhci,
-		struct xhci_ring *ring, struct xhci_td *td)
+static void xhci_unmap_one_bounce_buffer(struct xhci_hcd *xhci,
+		struct xhci_ring *ring, struct xhci_td *td,
+		struct xhci_segment *seg)
 {
 	struct device *dev = xhci_to_hcd(xhci)->self.sysdev;
-	struct xhci_segment *seg = td->bounce_seg;
 	struct urb *urb = td->urb;
 	size_t len;
 
-	if (!ring || !seg || !urb)
-		return;
-
 	if (usb_urb_dir_out(urb)) {
 		dma_unmap_single(dev, seg->bounce_dma, ring->bounce_buf_len,
 				 DMA_TO_DEVICE);
-		return;
+		goto done;
 	}
 
 	dma_unmap_single(dev, seg->bounce_dma, ring->bounce_buf_len,

@@ -769,10 +766,29 @@ static void xhci_unmap_td_bounce_buffer(struct xhci_hcd *xhci,
 		memcpy(urb->transfer_buffer + seg->bounce_offs, seg->bounce_buf,
 		       seg->bounce_len);
 	}
+done:
 	seg->bounce_len = 0;
 	seg->bounce_offs = 0;
 }
 
+static void xhci_unmap_td_bounce_buffer(struct xhci_hcd *xhci,
+		struct xhci_ring *ring, struct xhci_td *td)
+{
+	struct xhci_segment *seg;
+	int i = 0;
+
+	if (!td->bounce_seg || !ring || !td->urb)
+		return;
+
+	/* td->bounce_seg is the last one bounced, unmap them all */
+	for (seg = td->start_seg; i++ < ring->num_segs; seg = seg->next) {
+		if (seg->bounce_len)
+			xhci_unmap_one_bounce_buffer(xhci, ring, td, seg);
+		if (seg == td->bounce_seg)
+			break;
+	}
+}
+
 static int xhci_td_cleanup(struct xhci_hcd *xhci, struct xhci_td *td,
 			   struct xhci_ring *ep_ring, int status)
 {

@@ -3530,7 +3546,7 @@ int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 						  &trb_buff_len,
 						  ring->enq_seg)) {
 					send_addr = ring->enq_seg->bounce_dma;
-					/* assuming TD won't span 2 segs */
+					/* TD bounced at least, and last on this seg */
 					td->bounce_seg = ring->enq_seg;
 				}
 			}

2.48.1