xHCI: add aborting command ring function

Software have to abort command ring and cancel command
when a command is failed or hang. Otherwise, the command
ring will hang up and can't handle the others. An example
of a command that may hang is the Address Device Command,
because waiting for a SET_ADDRESS request to be acknowledged
by a USB device is outside of the xHC's ability to control.

To cancel a command, software will initialize a command
descriptor for the cancel command, and add it into a
cancel_cmd_list of xhci.

Sarah: Fixed missing newline on "Have the command ring been stopped?"
debugging statement.

This patch should be backported to kernels as old as 3.0, that contain
the commit 7ed603ec "xhci: Add an
assertion to check for virt_dev=0 bug." That commit papers over a NULL
pointer dereference, and this patch fixes the underlying issue that
caused the NULL pointer dereference.
Signed-off-by: Elric Fu <elricfu1@gmail.com>
Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
Tested-by: Miroslav Sabljic <miroslav.sabljic@avl.com>
Cc: stable@vger.kernel.org

drivers/usb/host/xhci-mem.c

@@ -1772,6 +1772,7 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci)
 {
 	struct pci_dev	*pdev = to_pci_dev(xhci_to_hcd(xhci)->self.controller);
 	struct dev_info	*dev_info, *next;
+	struct xhci_cd  *cur_cd, *next_cd;
 	unsigned long	flags;
 	int size;
 	int i, j, num_ports;
@@ -1795,6 +1796,11 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci)
 		xhci_ring_free(xhci, xhci->cmd_ring);
 	xhci->cmd_ring = NULL;
 	xhci_dbg(xhci, "Freed command ring\n");
+	list_for_each_entry_safe(cur_cd, next_cd,
+			&xhci->cancel_cmd_list, cancel_cmd_list) {
+		list_del(&cur_cd->cancel_cmd_list);
+		kfree(cur_cd);
+	}
 
 	for (i = 1; i < MAX_HC_SLOTS; ++i)
 		xhci_free_virt_device(xhci, i);
@@ -2340,6 +2346,7 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 	xhci->cmd_ring = xhci_ring_alloc(xhci, 1, 1, TYPE_COMMAND, flags);
 	if (!xhci->cmd_ring)
 		goto fail;
+	INIT_LIST_HEAD(&xhci->cancel_cmd_list);
 	xhci_dbg(xhci, "Allocated command ring at %p\n", xhci->cmd_ring);
 	xhci_dbg(xhci, "First segment DMA is 0x%llx\n",
 			(unsigned long long)xhci->cmd_ring->first_seg->dma);

drivers/usb/host/xhci-ring.c

@@ -289,6 +289,114 @@ void xhci_ring_cmd_db(struct xhci_hcd *xhci)
 	xhci_readl(xhci, &xhci->dba->doorbell[0]);
 }
 
+static int xhci_abort_cmd_ring(struct xhci_hcd *xhci)
+{
+	u64 temp_64;
+	int ret;
+
+	xhci_dbg(xhci, "Abort command ring\n");
+
+	if (!(xhci->cmd_ring_state & CMD_RING_STATE_RUNNING)) {
+		xhci_dbg(xhci, "The command ring isn't running, "
+				"Have the command ring been stopped?\n");
+		return 0;
+	}
+
+	temp_64 = xhci_read_64(xhci, &xhci->op_regs->cmd_ring);
+	if (!(temp_64 & CMD_RING_RUNNING)) {
+		xhci_dbg(xhci, "Command ring had been stopped\n");
+		return 0;
+	}
+	xhci->cmd_ring_state = CMD_RING_STATE_ABORTED;
+	xhci_write_64(xhci, temp_64 | CMD_RING_ABORT,
+			&xhci->op_regs->cmd_ring);
+
+	/* Section 4.6.1.2 of xHCI 1.0 spec says software should
+	 * time the completion od all xHCI commands, including
+	 * the Command Abort operation. If software doesn't see
+	 * CRR negated in a timely manner (e.g. longer than 5
+	 * seconds), then it should assume that the there are
+	 * larger problems with the xHC and assert HCRST.
+	 */
+	ret = handshake(xhci, &xhci->op_regs->cmd_ring,
+			CMD_RING_RUNNING, 0, 5 * 1000 * 1000);
+	if (ret < 0) {
+		xhci_err(xhci, "Stopped the command ring failed, "
+				"maybe the host is dead\n");
+		xhci->xhc_state |= XHCI_STATE_DYING;
+		xhci_quiesce(xhci);
+		xhci_halt(xhci);
+		return -ESHUTDOWN;
+	}
+
+	return 0;
+}
+
+static int xhci_queue_cd(struct xhci_hcd *xhci,
+		struct xhci_command *command,
+		union xhci_trb *cmd_trb)
+{
+	struct xhci_cd *cd;
+	cd = kzalloc(sizeof(struct xhci_cd), GFP_ATOMIC);
+	if (!cd)
+		return -ENOMEM;
+	INIT_LIST_HEAD(&cd->cancel_cmd_list);
+
+	cd->command = command;
+	cd->cmd_trb = cmd_trb;
+	list_add_tail(&cd->cancel_cmd_list, &xhci->cancel_cmd_list);
+
+	return 0;
+}
+
+/*
+ * Cancel the command which has issue.
+ *
+ * Some commands may hang due to waiting for acknowledgement from
+ * usb device. It is outside of the xHC's ability to control and
+ * will cause the command ring is blocked. When it occurs software
+ * should intervene to recover the command ring.
+ * See Section 4.6.1.1 and 4.6.1.2
+ */
+int xhci_cancel_cmd(struct xhci_hcd *xhci, struct xhci_command *command,
+		union xhci_trb *cmd_trb)
+{
+	int retval = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&xhci->lock, flags);
+
+	if (xhci->xhc_state & XHCI_STATE_DYING) {
+		xhci_warn(xhci, "Abort the command ring,"
+				" but the xHCI is dead.\n");
+		retval = -ESHUTDOWN;
+		goto fail;
+	}
+
+	/* queue the cmd desriptor to cancel_cmd_list */
+	retval = xhci_queue_cd(xhci, command, cmd_trb);
+	if (retval) {
+		xhci_warn(xhci, "Queuing command descriptor failed.\n");
+		goto fail;
+	}
+
+	/* abort command ring */
+	retval = xhci_abort_cmd_ring(xhci);
+	if (retval) {
+		xhci_err(xhci, "Abort command ring failed\n");
+		if (unlikely(retval == -ESHUTDOWN)) {
+			spin_unlock_irqrestore(&xhci->lock, flags);
+			usb_hc_died(xhci_to_hcd(xhci)->primary_hcd);
+			xhci_dbg(xhci, "xHCI host controller is dead.\n");
+			return retval;
+		}
+	}
+
+fail:
+	spin_unlock_irqrestore(&xhci->lock, flags);
+	return retval;
+}
+
 void xhci_ring_ep_doorbell(struct xhci_hcd *xhci,
 		unsigned int slot_id,
 		unsigned int ep_index,

drivers/usb/host/xhci.c

@@ -51,7 +51,7 @@ MODULE_PARM_DESC(link_quirk, "Don't clear the chain bit on a link TRB");
  * handshake done).  There are two failure modes:  "usec" have passed (major
  * hardware flakeout), or the register reads as all-ones (hardware removed).
  */
-static int handshake(struct xhci_hcd *xhci, void __iomem *ptr,
+int handshake(struct xhci_hcd *xhci, void __iomem *ptr,
 		      u32 mask, u32 done, int usec)
 {
 	u32	result;

drivers/usb/host/xhci.h

@@ -1256,6 +1256,13 @@ struct xhci_td {
 	union xhci_trb		*last_trb;
 };
 
+/* command descriptor */
+struct xhci_cd {
+	struct list_head	cancel_cmd_list;
+	struct xhci_command	*command;
+	union xhci_trb		*cmd_trb;
+};
+
 struct xhci_dequeue_state {
 	struct xhci_segment *new_deq_seg;
 	union xhci_trb *new_deq_ptr;
@@ -1425,6 +1432,7 @@ struct xhci_hcd {
 #define CMD_RING_STATE_RUNNING         (1 << 0)
 #define CMD_RING_STATE_ABORTED         (1 << 1)
 #define CMD_RING_STATE_STOPPED         (1 << 2)
+	struct list_head        cancel_cmd_list;
 	unsigned int		cmd_ring_reserved_trbs;
 	struct xhci_ring	*event_ring;
 	struct xhci_erst	erst;
@@ -1702,6 +1710,8 @@ static inline void xhci_unregister_plat(void)
 
 /* xHCI host controller glue */
 typedef void (*xhci_get_quirks_t)(struct device *, struct xhci_hcd *);
+int handshake(struct xhci_hcd *xhci, void __iomem *ptr,
+		u32 mask, u32 done, int usec);
 void xhci_quiesce(struct xhci_hcd *xhci);
 int xhci_halt(struct xhci_hcd *xhci);
 int xhci_reset(struct xhci_hcd *xhci);
@@ -1792,6 +1802,8 @@ void xhci_queue_config_ep_quirk(struct xhci_hcd *xhci,
 		unsigned int slot_id, unsigned int ep_index,
 		struct xhci_dequeue_state *deq_state);
 void xhci_stop_endpoint_command_watchdog(unsigned long arg);
+int xhci_cancel_cmd(struct xhci_hcd *xhci, struct xhci_command *command,
+		union xhci_trb *cmd_trb);
 void xhci_ring_ep_doorbell(struct xhci_hcd *xhci, unsigned int slot_id,
 		unsigned int ep_index, unsigned int stream_id);