[PATCH 0/3] xhci fixes for usb-linus

[PATCH 0/3] xhci fixes for usb-linus

[Mathias Nyman]

Hi Greg

A few xhci fixes for usb-linus, solving a couple endianness issues, and a
use-after-free regression reported by Johan Hovold

-Mathias

Ben Dooks (Codethink) (1):
  usb: xhci: fix __le32/__le64 accessors in debugfs code

Mathias Nyman (1):
  xhci: Fix use-after-free regression in xhci clear hub TT
    implementation

Samuel Holland (1):
  usb: xhci: fix Immediate Data Transfer endianness

 drivers/usb/host/xhci-debugfs.c | 24 +++++++++---------
 drivers/usb/host/xhci-ring.c    |  2 ++
 drivers/usb/host/xhci.c         | 54 ++++++++++++++++++++++++++++++++++-------
 3 files changed, 59 insertions(+), 21 deletions(-)

-- 
2.7.4

[PATCH 1/3] xhci: Fix use-after-free regression in xhci clear hub TT implementation

[Mathias Nyman]

commit ef513be0a905 ("usb: xhci: Add Clear_TT_Buffer") schedules work
to clear TT buffer, but causes a use-after-free regression at the same time

Make sure hub_tt_work finishes before endpoint is disabled, otherwise
the work will dereference already freed endpoint and device related
pointers.

This was triggered when usb core failed to read the configuration
descriptor of a FS/LS device during enumeration.
xhci driver queued clear_tt_work while usb core freed and reallocated
a new device for the next enumeration attempt.

EHCI driver implents ehci_endpoint_disable() that makes sure
clear_tt_work has finished before it returns, but xhci lacks this support.
usb core will call hcd->driver->endpoint_disable() callback before
disabling endpoints, so we want this in xhci as well.

The added xhci_endpoint_disable() is based on ehci_endpoint_disable()

Fixes: ef513be0a905 ("usb: xhci: Add Clear_TT_Buffer")
Cc: <stable@vger.kernel.org> # v5.3
Reported-by: Johan Hovold <johan@kernel.org>
Suggested-by: Johan Hovold <johan@kernel.org>
Reviewed-by: Johan Hovold <johan@kernel.org>
Tested-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
---
 drivers/usb/host/xhci.c | 54 ++++++++++++++++++++++++++++++++++++++++---------
 1 file changed, 45 insertions(+), 9 deletions(-)

diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 517ec3206f6e..6c17e3fe181a 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -3071,6 +3071,48 @@ void xhci_cleanup_stalled_ring(struct xhci_hcd *xhci, unsigned int ep_index,
 	}
 }
 
+static void xhci_endpoint_disable(struct usb_hcd *hcd,
+				  struct usb_host_endpoint *host_ep)
+{
+	struct xhci_hcd		*xhci;
+	struct xhci_virt_device	*vdev;
+	struct xhci_virt_ep	*ep;
+	struct usb_device	*udev;
+	unsigned long		flags;
+	unsigned int		ep_index;
+
+	xhci = hcd_to_xhci(hcd);
+rescan:
+	spin_lock_irqsave(&xhci->lock, flags);
+
+	udev = (struct usb_device *)host_ep->hcpriv;
+	if (!udev || !udev->slot_id)
+		goto done;
+
+	vdev = xhci->devs[udev->slot_id];
+	if (!vdev)
+		goto done;
+
+	ep_index = xhci_get_endpoint_index(&host_ep->desc);
+	ep = &vdev->eps[ep_index];
+	if (!ep)
+		goto done;
+
+	/* wait for hub_tt_work to finish clearing hub TT */
+	if (ep->ep_state & EP_CLEARING_TT) {
+		spin_unlock_irqrestore(&xhci->lock, flags);
+		schedule_timeout_uninterruptible(1);
+		goto rescan;
+	}
+
+	if (ep->ep_state)
+		xhci_dbg(xhci, "endpoint disable with ep_state 0x%x\n",
+			 ep->ep_state);
+done:
+	host_ep->hcpriv = NULL;
+	spin_unlock_irqrestore(&xhci->lock, flags);
+}
+
 /*
  * Called after usb core issues a clear halt control message.
  * The host side of the halt should already be cleared by a reset endpoint
@@ -5238,20 +5280,13 @@ static void xhci_clear_tt_buffer_complete(struct usb_hcd *hcd,
 	unsigned int ep_index;
 	unsigned long flags;
 
-	/*
-	 * udev might be NULL if tt buffer is cleared during a failed device
-	 * enumeration due to a halted control endpoint. Usb core might
-	 * have allocated a new udev for the next enumeration attempt.
-	 */
-
 	xhci = hcd_to_xhci(hcd);
+
+	spin_lock_irqsave(&xhci->lock, flags);
 	udev = (struct usb_device *)ep->hcpriv;
-	if (!udev)
-		return;
 	slot_id = udev->slot_id;
 	ep_index = xhci_get_endpoint_index(&ep->desc);
 
-	spin_lock_irqsave(&xhci->lock, flags);
 	xhci->devs[slot_id]->eps[ep_index].ep_state &= ~EP_CLEARING_TT;
 	xhci_ring_doorbell_for_active_rings(xhci, slot_id, ep_index);
 	spin_unlock_irqrestore(&xhci->lock, flags);
@@ -5288,6 +5323,7 @@ static const struct hc_driver xhci_hc_driver = {
 	.free_streams =		xhci_free_streams,
 	.add_endpoint =		xhci_add_endpoint,
 	.drop_endpoint =	xhci_drop_endpoint,
+	.endpoint_disable =	xhci_endpoint_disable,
 	.endpoint_reset =	xhci_endpoint_reset,
 	.check_bandwidth =	xhci_check_bandwidth,
 	.reset_bandwidth =	xhci_reset_bandwidth,
-- 
2.7.4

[PATCH 2/3] usb: xhci: fix Immediate Data Transfer endianness

[Mathias Nyman]

From: Samuel Holland <samuel@sholland.org>

The arguments to queue_trb are always byteswapped to LE for placement in
the ring, but this should not happen in the case of immediate data; the
bytes copied out of transfer_buffer are already in the correct order.
Add a complementary byteswap so the bytes end up in the ring correctly.

This was observed on BE ppc64 with a "Texas Instruments TUSB73x0
SuperSpeed USB 3.0 xHCI Host Controller [104c:8241]" as a ch341
usb-serial adapter ("1a86:7523 QinHeng Electronics HL-340 USB-Serial
adapter") always transmitting the same character (generally NUL) over
the serial link regardless of the key pressed.

Cc: <stable@vger.kernel.org> # 5.2+
Fixes: 33e39350ebd2 ("usb: xhci: add Immediate Data Transfer support")
Signed-off-by: Samuel Holland <samuel@sholland.org>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
---
 drivers/usb/host/xhci-ring.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 85ceb43e3405..e7aab31fd9a5 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -3330,6 +3330,7 @@ int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 			if (xhci_urb_suitable_for_idt(urb)) {
 				memcpy(&send_addr, urb->transfer_buffer,
 				       trb_buff_len);
+				le64_to_cpus(&send_addr);
 				field |= TRB_IDT;
 			}
 		}
@@ -3475,6 +3476,7 @@ int xhci_queue_ctrl_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 		if (xhci_urb_suitable_for_idt(urb)) {
 			memcpy(&addr, urb->transfer_buffer,
 			       urb->transfer_buffer_length);
+			le64_to_cpus(&addr);
 			field |= TRB_IDT;
 		} else {
 			addr = (u64) urb->transfer_dma;
-- 
2.7.4

[PATCH 3/3] usb: xhci: fix __le32/__le64 accessors in debugfs code

[Mathias Nyman]

From: "Ben Dooks (Codethink)" <ben.dooks@codethink.co.uk>

It looks like some of the xhci debug code is passing u32 to functions
directly from __le32/__le64 fields.
Fix this by using le{32,64}_to_cpu() on these to fix the following
sparse warnings;

xhci-debugfs.c:205:62: warning: incorrect type in argument 1 (different base types)
xhci-debugfs.c:205:62:    expected unsigned int [usertype] field0
xhci-debugfs.c:205:62:    got restricted __le32
xhci-debugfs.c:206:62: warning: incorrect type in argument 2 (different base types)
xhci-debugfs.c:206:62:    expected unsigned int [usertype] field1
xhci-debugfs.c:206:62:    got restricted __le32
...

[Trim down commit message, sparse warnings were similar -Mathias]
Cc: <stable@vger.kernel.org> # 4.15+
Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
---
 drivers/usb/host/xhci-debugfs.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/usb/host/xhci-debugfs.c b/drivers/usb/host/xhci-debugfs.c
index 7ba6afc7ef23..76c3f29562d2 100644
--- a/drivers/usb/host/xhci-debugfs.c
+++ b/drivers/usb/host/xhci-debugfs.c
@@ -202,10 +202,10 @@ static void xhci_ring_dump_segment(struct seq_file *s,
 		trb = &seg->trbs[i];
 		dma = seg->dma + i * sizeof(*trb);
 		seq_printf(s, "%pad: %s\n", &dma,
-			   xhci_decode_trb(trb->generic.field[0],
-					   trb->generic.field[1],
-					   trb->generic.field[2],
-					   trb->generic.field[3]));
+			   xhci_decode_trb(le32_to_cpu(trb->generic.field[0]),
+					   le32_to_cpu(trb->generic.field[1]),
+					   le32_to_cpu(trb->generic.field[2]),
+					   le32_to_cpu(trb->generic.field[3])));
 	}
 }
 
@@ -263,10 +263,10 @@ static int xhci_slot_context_show(struct seq_file *s, void *unused)
 	xhci = hcd_to_xhci(bus_to_hcd(dev->udev->bus));
 	slot_ctx = xhci_get_slot_ctx(xhci, dev->out_ctx);
 	seq_printf(s, "%pad: %s\n", &dev->out_ctx->dma,
-		   xhci_decode_slot_context(slot_ctx->dev_info,
-					    slot_ctx->dev_info2,
-					    slot_ctx->tt_info,
-					    slot_ctx->dev_state));
+		   xhci_decode_slot_context(le32_to_cpu(slot_ctx->dev_info),
+					    le32_to_cpu(slot_ctx->dev_info2),
+					    le32_to_cpu(slot_ctx->tt_info),
+					    le32_to_cpu(slot_ctx->dev_state)));
 
 	return 0;
 }
@@ -286,10 +286,10 @@ static int xhci_endpoint_context_show(struct seq_file *s, void *unused)
 		ep_ctx = xhci_get_ep_ctx(xhci, dev->out_ctx, dci);
 		dma = dev->out_ctx->dma + dci * CTX_SIZE(xhci->hcc_params);
 		seq_printf(s, "%pad: %s\n", &dma,
-			   xhci_decode_ep_context(ep_ctx->ep_info,
-						  ep_ctx->ep_info2,
-						  ep_ctx->deq,
-						  ep_ctx->tx_info));
+			   xhci_decode_ep_context(le32_to_cpu(ep_ctx->ep_info),
+						  le32_to_cpu(ep_ctx->ep_info2),
+						  le64_to_cpu(ep_ctx->deq),
+						  le32_to_cpu(ep_ctx->tx_info)));
 	}
 
 	return 0;
-- 
2.7.4