OpenCloudOS-Kernel/drivers/usb/host/xhci-ring.c

4175 lines
126 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* xHCI host controller driver
*
* Copyright (C) 2008 Intel Corp.
*
* Author: Sarah Sharp
* Some code borrowed from the Linux EHCI driver.
*/
/*
* Ring initialization rules:
* 1. Each segment is initialized to zero, except for link TRBs.
* 2. Ring cycle state = 0. This represents Producer Cycle State (PCS) or
* Consumer Cycle State (CCS), depending on ring function.
* 3. Enqueue pointer = dequeue pointer = address of first TRB in the segment.
*
* Ring behavior rules:
* 1. A ring is empty if enqueue == dequeue. This means there will always be at
* least one free TRB in the ring. This is useful if you want to turn that
* into a link TRB and expand the ring.
* 2. When incrementing an enqueue or dequeue pointer, if the next TRB is a
* link TRB, then load the pointer with the address in the link TRB. If the
* link TRB had its toggle bit set, you may need to update the ring cycle
* state (see cycle bit rules). You may have to do this multiple times
* until you reach a non-link TRB.
* 3. A ring is full if enqueue++ (for the definition of increment above)
* equals the dequeue pointer.
*
* Cycle bit rules:
* 1. When a consumer increments a dequeue pointer and encounters a toggle bit
* in a link TRB, it must toggle the ring cycle state.
* 2. When a producer increments an enqueue pointer and encounters a toggle bit
* in a link TRB, it must toggle the ring cycle state.
*
* Producer rules:
* 1. Check if ring is full before you enqueue.
* 2. Write the ring cycle state to the cycle bit in the TRB you're enqueuing.
* Update enqueue pointer between each write (which may update the ring
* cycle state).
* 3. Notify consumer. If SW is producer, it rings the doorbell for command
* and endpoint rings. If HC is the producer for the event ring,
* and it generates an interrupt according to interrupt modulation rules.
*
* Consumer rules:
* 1. Check if TRB belongs to you. If the cycle bit == your ring cycle state,
* the TRB is owned by the consumer.
* 2. Update dequeue pointer (which may update the ring cycle state) and
* continue processing TRBs until you reach a TRB which is not owned by you.
* 3. Notify the producer. SW is the consumer for the event ring, and it
* updates event ring dequeue pointer. HC is the consumer for the command and
* endpoint rings; it generates events on the event ring for these.
*/
#include <linux/scatterlist.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/dma-mapping.h>
#include "xhci.h"
#include "xhci-trace.h"
#include "xhci-mtk.h"
/*
* Returns zero if the TRB isn't in this segment, otherwise it returns the DMA
* address of the TRB.
*/
dma_addr_t xhci_trb_virt_to_dma(struct xhci_segment *seg,
union xhci_trb *trb)
{
unsigned long segment_offset;
if (!seg || !trb || trb < seg->trbs)
return 0;
/* offset in TRBs */
segment_offset = trb - seg->trbs;
if (segment_offset >= TRBS_PER_SEGMENT)
return 0;
return seg->dma + (segment_offset * sizeof(*trb));
}
static bool trb_is_noop(union xhci_trb *trb)
{
return TRB_TYPE_NOOP_LE32(trb->generic.field[3]);
}
static bool trb_is_link(union xhci_trb *trb)
{
return TRB_TYPE_LINK_LE32(trb->link.control);
}
static bool last_trb_on_seg(struct xhci_segment *seg, union xhci_trb *trb)
{
return trb == &seg->trbs[TRBS_PER_SEGMENT - 1];
}
static bool last_trb_on_ring(struct xhci_ring *ring,
struct xhci_segment *seg, union xhci_trb *trb)
{
return last_trb_on_seg(seg, trb) && (seg->next == ring->first_seg);
}
static bool link_trb_toggles_cycle(union xhci_trb *trb)
{
return le32_to_cpu(trb->link.control) & LINK_TOGGLE;
}
static bool last_td_in_urb(struct xhci_td *td)
{
struct urb_priv *urb_priv = td->urb->hcpriv;
return urb_priv->num_tds_done == urb_priv->num_tds;
}
static void inc_td_cnt(struct urb *urb)
{
struct urb_priv *urb_priv = urb->hcpriv;
urb_priv->num_tds_done++;
}
static void trb_to_noop(union xhci_trb *trb, u32 noop_type)
{
if (trb_is_link(trb)) {
/* unchain chained link TRBs */
trb->link.control &= cpu_to_le32(~TRB_CHAIN);
} else {
trb->generic.field[0] = 0;
trb->generic.field[1] = 0;
trb->generic.field[2] = 0;
/* Preserve only the cycle bit of this TRB */
trb->generic.field[3] &= cpu_to_le32(TRB_CYCLE);
trb->generic.field[3] |= cpu_to_le32(TRB_TYPE(noop_type));
}
}
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
/* Updates trb to point to the next TRB in the ring, and updates seg if the next
* TRB is in a new segment. This does not skip over link TRBs, and it does not
* effect the ring dequeue or enqueue pointers.
*/
static void next_trb(struct xhci_hcd *xhci,
struct xhci_ring *ring,
struct xhci_segment **seg,
union xhci_trb **trb)
{
if (trb_is_link(*trb)) {
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
*seg = (*seg)->next;
*trb = ((*seg)->trbs);
} else {
(*trb)++;
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
}
}
/*
* See Cycle bit rules. SW is the consumer for the event ring only.
* Don't make a ring full of link TRBs. That would be dumb and this would loop.
*/
void inc_deq(struct xhci_hcd *xhci, struct xhci_ring *ring)
{
/* event ring doesn't have link trbs, check for last trb */
if (ring->type == TYPE_EVENT) {
if (!last_trb_on_seg(ring->deq_seg, ring->dequeue)) {
xhci: Fix bug after deq ptr set to link TRB. This patch fixes a particularly nasty bug that was revealed by the ring expansion patches. The bug has been present since the very beginning of the xHCI driver history, and could have caused general protection faults from bad memory accesses. The first thing to note is that a Set TR Dequeue Pointer command can move the dequeue pointer to a link TRB, if the canceled or stalled transfer TD ended just before a link TRB. The function to increment the dequeue pointer, inc_deq, was written before cancellation and stall support was added. It assumed that the dequeue pointer could never point to a link TRB. It would unconditionally increment the dequeue pointer at the start of the function, check if the pointer was now on a link TRB, and move it to the top of the next segment if so. This means that if a Set TR Dequeue Point command moved the dequeue pointer to a link TRB, a subsequent call to inc_deq() would move the pointer off the segment and into la-la-land. It would then read from that memory to determine if it was a link TRB. Other functions would often call inc_deq() until the dequeue pointer matched some other pointer, which means this function would quite happily read all of system memory before wrapping around to the right pointer value. Often, there would be another endpoint segment from a different ring allocated from the same DMA pool, which would be contiguous to the segment inc_deq just stepped off of. inc_deq would eventually find the link TRB in that segment, and blindly move the dequeue pointer back to the top of the correct ring segment. The only reason the original code worked at all is because there was only one ring segment. With the ring expansion patches, the dequeue pointer would eventually wrap into place, but the dequeue segment would be out-of-sync. On the second TD after the dequeue pointer was moved to a link TRB, trb_in_td() would fail (because the dequeue pointer and dequeue segment were out-of-sync), and this message would appear: ERROR Transfer event TRB DMA ptr not part of current TD This fixes bugzilla entry 4333 (option-based modem unhappy on USB 3.0 port: "Transfer event TRB DMA ptr not part of current TD", "rejecting I/O to offline device"), https://bugzilla.kernel.org/show_bug.cgi?id=43333 and possibly other general protection fault bugs as well. This patch should be backported to kernels as old as 2.6.31. A separate patch will be created for kernels older than 3.4, since inc_deq was modified in 3.4 and this patch will not apply. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Tested-by: James Ettle <theholyettlz@googlemail.com> Tested-by: Matthew Hall <mhall@mhcomputing.net> Cc: stable@vger.kernel.org
2012-07-27 03:03:59 +08:00
ring->dequeue++;
goto out;
}
if (last_trb_on_ring(ring, ring->deq_seg, ring->dequeue))
ring->cycle_state ^= 1;
ring->deq_seg = ring->deq_seg->next;
ring->dequeue = ring->deq_seg->trbs;
goto out;
}
/* All other rings have link trbs */
if (!trb_is_link(ring->dequeue)) {
ring->dequeue++;
ring->num_trbs_free++;
}
while (trb_is_link(ring->dequeue)) {
ring->deq_seg = ring->deq_seg->next;
ring->dequeue = ring->deq_seg->trbs;
}
out:
trace_xhci_inc_deq(ring);
return;
}
/*
* See Cycle bit rules. SW is the consumer for the event ring only.
* Don't make a ring full of link TRBs. That would be dumb and this would loop.
*
* If we've just enqueued a TRB that is in the middle of a TD (meaning the
* chain bit is set), then set the chain bit in all the following link TRBs.
* If we've enqueued the last TRB in a TD, make sure the following link TRBs
* have their chain bit cleared (so that each Link TRB is a separate TD).
*
* Section 6.4.4.1 of the 0.95 spec says link TRBs cannot have the chain bit
USB: xhci: Work around for chain bit in link TRBs. Different sections of the xHCI 0.95 specification had opposing requirements for the chain bit in a link transaction request buffer (TRB). The chain bit is used to designate that adjacent TRBs are all part of the same scatter gather list that should be sent to the device. Link TRBs can be in the middle, or at the beginning or end of these chained TRBs. Sections 4.11.5.1 and 6.4.4.1 both stated the link TRB "shall have the chain bit set to 1", meaning it is always chained to the next TRB. However, section 4.6.9 on the stop endpoint command has specific cases for what the hardware must do for a link TRB with the chain bit set to 0. The 0.96 specification errata later cleared up this issue by fixing the 4.11.5.1 and 6.4.4.1 sections to state that a link TRB can have the chain bit set to 1 or 0. The problem is that the xHCI cancellation code depends on the chain bit of the link TRB being cleared when it's at the end of a TD, and some 0.95 xHCI hardware simply stops processing the ring when it encounters a link TRB with the chain bit cleared. Allow users who are testing 0.95 xHCI prototypes to set a module parameter (link_quirk) to turn on this link TRB work around. Cancellation may not work if the ring is stopped exactly on a link TRB with chain bit set, but cancellation should be a relatively uncommon case. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Cc: stable <stable@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-08-08 05:04:36 +08:00
* set, but other sections talk about dealing with the chain bit set. This was
* fixed in the 0.96 specification errata, but we have to assume that all 0.95
* xHCI hardware can't handle the chain bit being cleared on a link TRB.
USB: xHCI: Fix bug in link TRB activation change. Commit 6c12db90f19727c76990e7f4801c67a148b30111 introduced a bug for control transfers. The patch was supposed to change when the link TRBs at the end of each ring segment were given to the hardware. If a transfer descriptor (TD) ended just before the link TRB, the code wouldn't give back the link TRB to the hardware; instead it would be given back in prepare_ring() just before the next TD was enqueued at the top of the ring. Unfortunately, the code relied on checking the chain bit of the TRB to determine whether the TD ended just before the link TRB. It assumed that the ring enqueuing code would call prepare_ring() before enqueuing the next TD. However, control transfers are made of multiple TDs, and prepare_ring() is only called once before enqueuing two or three TDs. If the first or second TD of the control transfer ended just before the link TRB, then the code in inc_enq() would not move the enqueue pointer past the link TRB, and the link TRB would get overwritten. This would cause the xHCI driver to start writing to memory past the ring segment, and eventually the system would crash or hang. The fix is to add a flag to inc_enq() that says whether the caller will enqueue more TDs before calling prepare_ring(). If the chain bit is cleared (meaning this is the last TRB in a TD), and the caller will not enqueue more TDs, then we defer giving back the link TRB. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Cc: stable <stable@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-06-11 03:25:28 +08:00
*
* @more_trbs_coming: Will you enqueue more TRBs before calling
* prepare_transfer()?
*/
USB: xHCI: Fix bug in link TRB activation change. Commit 6c12db90f19727c76990e7f4801c67a148b30111 introduced a bug for control transfers. The patch was supposed to change when the link TRBs at the end of each ring segment were given to the hardware. If a transfer descriptor (TD) ended just before the link TRB, the code wouldn't give back the link TRB to the hardware; instead it would be given back in prepare_ring() just before the next TD was enqueued at the top of the ring. Unfortunately, the code relied on checking the chain bit of the TRB to determine whether the TD ended just before the link TRB. It assumed that the ring enqueuing code would call prepare_ring() before enqueuing the next TD. However, control transfers are made of multiple TDs, and prepare_ring() is only called once before enqueuing two or three TDs. If the first or second TD of the control transfer ended just before the link TRB, then the code in inc_enq() would not move the enqueue pointer past the link TRB, and the link TRB would get overwritten. This would cause the xHCI driver to start writing to memory past the ring segment, and eventually the system would crash or hang. The fix is to add a flag to inc_enq() that says whether the caller will enqueue more TDs before calling prepare_ring(). If the chain bit is cleared (meaning this is the last TRB in a TD), and the caller will not enqueue more TDs, then we defer giving back the link TRB. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Cc: stable <stable@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-06-11 03:25:28 +08:00
static void inc_enq(struct xhci_hcd *xhci, struct xhci_ring *ring,
bool more_trbs_coming)
{
u32 chain;
union xhci_trb *next;
chain = le32_to_cpu(ring->enqueue->generic.field[3]) & TRB_CHAIN;
/* If this is not event ring, there is one less usable TRB */
if (!trb_is_link(ring->enqueue))
ring->num_trbs_free--;
next = ++(ring->enqueue);
/* Update the dequeue pointer further if that was a link TRB */
while (trb_is_link(next)) {
USB: xHCI: Fix bug in link TRB activation change. Commit 6c12db90f19727c76990e7f4801c67a148b30111 introduced a bug for control transfers. The patch was supposed to change when the link TRBs at the end of each ring segment were given to the hardware. If a transfer descriptor (TD) ended just before the link TRB, the code wouldn't give back the link TRB to the hardware; instead it would be given back in prepare_ring() just before the next TD was enqueued at the top of the ring. Unfortunately, the code relied on checking the chain bit of the TRB to determine whether the TD ended just before the link TRB. It assumed that the ring enqueuing code would call prepare_ring() before enqueuing the next TD. However, control transfers are made of multiple TDs, and prepare_ring() is only called once before enqueuing two or three TDs. If the first or second TD of the control transfer ended just before the link TRB, then the code in inc_enq() would not move the enqueue pointer past the link TRB, and the link TRB would get overwritten. This would cause the xHCI driver to start writing to memory past the ring segment, and eventually the system would crash or hang. The fix is to add a flag to inc_enq() that says whether the caller will enqueue more TDs before calling prepare_ring(). If the chain bit is cleared (meaning this is the last TRB in a TD), and the caller will not enqueue more TDs, then we defer giving back the link TRB. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Cc: stable <stable@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-06-11 03:25:28 +08:00
/*
* If the caller doesn't plan on enqueueing more TDs before
* ringing the doorbell, then we don't want to give the link TRB
* to the hardware just yet. We'll give the link TRB back in
* prepare_ring() just before we enqueue the TD at the top of
* the ring.
*/
if (!chain && !more_trbs_coming)
break;
/* If we're not dealing with 0.95 hardware or isoc rings on
* AMD 0.96 host, carry over the chain bit of the previous TRB
* (which may mean the chain bit is cleared).
*/
if (!(ring->type == TYPE_ISOC &&
(xhci->quirks & XHCI_AMD_0x96_HOST)) &&
!xhci_link_trb_quirk(xhci)) {
next->link.control &= cpu_to_le32(~TRB_CHAIN);
next->link.control |= cpu_to_le32(chain);
}
/* Give this link TRB to the hardware */
wmb();
next->link.control ^= cpu_to_le32(TRB_CYCLE);
/* Toggle the cycle bit after the last ring segment. */
if (link_trb_toggles_cycle(next))
ring->cycle_state ^= 1;
ring->enq_seg = ring->enq_seg->next;
ring->enqueue = ring->enq_seg->trbs;
next = ring->enqueue;
}
trace_xhci_inc_enq(ring);
}
/*
* Check to see if there's room to enqueue num_trbs on the ring and make sure
* enqueue pointer will not advance into dequeue segment. See rules above.
*/
static inline int room_on_ring(struct xhci_hcd *xhci, struct xhci_ring *ring,
unsigned int num_trbs)
{
int num_trbs_in_deq_seg;
if (ring->num_trbs_free < num_trbs)
return 0;
if (ring->type != TYPE_COMMAND && ring->type != TYPE_EVENT) {
num_trbs_in_deq_seg = ring->dequeue - ring->deq_seg->trbs;
if (ring->num_trbs_free < num_trbs + num_trbs_in_deq_seg)
return 0;
}
return 1;
}
/* Ring the host controller doorbell after placing a command on the ring */
void xhci_ring_cmd_db(struct xhci_hcd *xhci)
{
if (!(xhci->cmd_ring_state & CMD_RING_STATE_RUNNING))
return;
xhci_dbg(xhci, "// Ding dong!\n");
trace_xhci_ring_host_doorbell(0, DB_VALUE_HOST);
writel(DB_VALUE_HOST, &xhci->dba->doorbell[0]);
/* Flush PCI posted writes */
readl(&xhci->dba->doorbell[0]);
}
static bool xhci_mod_cmd_timer(struct xhci_hcd *xhci, unsigned long delay)
{
return mod_delayed_work(system_wq, &xhci->cmd_timer, delay);
}
static struct xhci_command *xhci_next_queued_cmd(struct xhci_hcd *xhci)
{
return list_first_entry_or_null(&xhci->cmd_list, struct xhci_command,
cmd_list);
}
/*
* Turn all commands on command ring with status set to "aborted" to no-op trbs.
* If there are other commands waiting then restart the ring and kick the timer.
* This must be called with command ring stopped and xhci->lock held.
*/
static void xhci_handle_stopped_cmd_ring(struct xhci_hcd *xhci,
struct xhci_command *cur_cmd)
{
struct xhci_command *i_cmd;
/* Turn all aborted commands in list to no-ops, then restart */
list_for_each_entry(i_cmd, &xhci->cmd_list, cmd_list) {
if (i_cmd->status != COMP_COMMAND_ABORTED)
continue;
i_cmd->status = COMP_COMMAND_RING_STOPPED;
xhci_dbg(xhci, "Turn aborted command %p to no-op\n",
i_cmd->command_trb);
trb_to_noop(i_cmd->command_trb, TRB_CMD_NOOP);
/*
* caller waiting for completion is called when command
* completion event is received for these no-op commands
*/
}
xhci->cmd_ring_state = CMD_RING_STATE_RUNNING;
/* ring command ring doorbell to restart the command ring */
if ((xhci->cmd_ring->dequeue != xhci->cmd_ring->enqueue) &&
!(xhci->xhc_state & XHCI_STATE_DYING)) {
xhci->current_cmd = cur_cmd;
xhci_mod_cmd_timer(xhci, XHCI_CMD_DEFAULT_TIMEOUT);
xhci_ring_cmd_db(xhci);
}
}
/* Must be called with xhci->lock held, releases and aquires lock back */
static int xhci_abort_cmd_ring(struct xhci_hcd *xhci, unsigned long flags)
{
u64 temp_64;
int ret;
xhci_dbg(xhci, "Abort command ring\n");
reinit_completion(&xhci->cmd_ring_stop_completion);
temp_64 = xhci_read_64(xhci, &xhci->op_regs->cmd_ring);
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 also time the
* completion of the Command Abort operation. If CRR is not negated in 5
* seconds then driver handles it as if host died (-ENODEV).
* In the future we should distinguish between -ENODEV and -ETIMEDOUT
* and try to recover a -ETIMEDOUT with a host controller reset.
*/
ret = xhci_handshake(&xhci->op_regs->cmd_ring,
CMD_RING_RUNNING, 0, 5 * 1000 * 1000);
if (ret < 0) {
xhci_err(xhci, "Abort failed to stop command ring: %d\n", ret);
xhci_halt(xhci);
xhci_hc_died(xhci);
return ret;
}
/*
* Writing the CMD_RING_ABORT bit should cause a cmd completion event,
* however on some host hw the CMD_RING_RUNNING bit is correctly cleared
* but the completion event in never sent. Wait 2 secs (arbitrary
* number) to handle those cases after negation of CMD_RING_RUNNING.
*/
spin_unlock_irqrestore(&xhci->lock, flags);
ret = wait_for_completion_timeout(&xhci->cmd_ring_stop_completion,
msecs_to_jiffies(2000));
spin_lock_irqsave(&xhci->lock, flags);
if (!ret) {
xhci_dbg(xhci, "No stop event for abort, ring start fail?\n");
xhci_cleanup_command_queue(xhci);
} else {
xhci_handle_stopped_cmd_ring(xhci, xhci_next_queued_cmd(xhci));
}
return 0;
}
void xhci_ring_ep_doorbell(struct xhci_hcd *xhci,
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
unsigned int slot_id,
USB: xhci: Correct assumptions about number of rings per endpoint. Much of the xHCI driver code assumes that endpoints only have one ring. Now an endpoint can have one ring per enabled stream ID, so correct that assumption. Use functions that translate the stream_id field in the URB or the DMA address of a TRB into the correct stream ring. Correct the polling loop to print out all enabled stream rings. Make the URB cancellation routine find the correct stream ring if the URB has stream_id set. Make sure the URB enqueueing routine does the same. Also correct the code that handles stalled/halted endpoints. Check that commands and registers that can take stream IDs handle them properly. That includes ringing an endpoint doorbell, resetting a stalled/halted endpoint, and setting a transfer ring dequeue pointer (since that command can set the dequeue pointer in a stream context or an endpoint context). Correct the transfer event handler to translate a TRB DMA address into the stream ring it was enqueued to. Make the code to allocate and prepare TD structures adds the TD to the right td_list for the stream ring. Make sure the code to give the first TRB in a TD to the hardware manipulates the correct stream ring. When an endpoint stalls, store the stream ID of the stream ring that stalled in the xhci_virt_ep structure. Use that instead of the stream ID in the URB, since an URB may be re-used after it is given back after a non-control endpoint stall. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-03 06:34:43 +08:00
unsigned int ep_index,
unsigned int stream_id)
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
{
__le32 __iomem *db_addr = &xhci->dba->doorbell[slot_id];
struct xhci_virt_ep *ep = &xhci->devs[slot_id]->eps[ep_index];
unsigned int ep_state = ep->ep_state;
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
/* Don't ring the doorbell for this endpoint if there are pending
* cancellations because we don't want to interrupt processing.
USB: xhci: Add memory allocation for USB3 bulk streams. Add support for allocating streams for USB 3.0 bulk endpoints. See Documentation/usb/bulk-streams.txt for more information about how and why you would use streams. When an endpoint has streams enabled, instead of having one ring where all transfers are enqueued to the hardware, it has several rings. The ring dequeue pointer in the endpoint context is changed to point to a "Stream Context Array". This is basically an array of pointers to transfer rings, one for each stream ID that the driver wants to use. The Stream Context Array size must be a power of two, and host controllers can place a limit on the size of the array (4 to 2^16 entries). These two facts make calculating the size of the Stream Context Array and the number of entries actually used by the driver a bit tricky. Besides the Stream Context Array and rings for all the stream IDs, we need one more data structure. The xHCI hardware will not tell us which stream ID a transfer event was for, but it will give us the slot ID, endpoint index, and physical address for the TRB that caused the event. For every endpoint on a device, add a radix tree to map physical TRB addresses to virtual segments within a stream ring. Keep track of whether an endpoint is transitioning to using streams, and don't enqueue any URBs while that's taking place. Refuse to transition an endpoint to streams if there are already URBs enqueued for that endpoint. We need to make sure that freeing streams does not fail, since a driver's disconnect() function may attempt to do this, and it cannot fail. Pre-allocate the command structure used to issue the Configure Endpoint command, and reserve space on the command ring for each stream endpoint. This may be a bit overkill, but it is permissible for the driver to allocate all streams in one call and free them in multiple calls. (It is not advised, however, since it is a waste of resources and time.) Even with the memory and ring room pre-allocated, freeing streams can still fail because the xHC rejects the configure endpoint command. It is valid (by the xHCI 0.96 spec) to return a "Bandwidth Error" or a "Resource Error" for a configure endpoint command. We should never see a Bandwidth Error, since bulk endpoints do not effect the reserved bandwidth. The host controller can still return a Resource Error, but it's improbable since the xHC would be going from a more resource-intensive configuration (streams) to a less resource-intensive configuration (no streams). If the xHC returns a Resource Error, the endpoint will be stuck with streams and will be unusable for drivers. It's an unavoidable consequence of broken host controller hardware. Includes bug fixes from the original patch, contributed by John Youn <John.Youn@synopsys.com> and Andy Green <AGreen@PLXTech.com> Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-03 06:34:16 +08:00
* We don't want to restart any stream rings if there's a set dequeue
* pointer command pending because the device can choose to start any
* stream once the endpoint is on the HW schedule.
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
*/
if ((ep_state & EP_STOP_CMD_PENDING) || (ep_state & SET_DEQ_PENDING) ||
(ep_state & EP_HALTED) || (ep_state & EP_CLEARING_TT))
return;
trace_xhci_ring_ep_doorbell(slot_id, DB_VALUE(ep_index, stream_id));
writel(DB_VALUE(ep_index, stream_id), db_addr);
/* The CPU has better things to do at this point than wait for a
* write-posting flush. It'll get there soon enough.
*/
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
}
USB: xhci: Correct assumptions about number of rings per endpoint. Much of the xHCI driver code assumes that endpoints only have one ring. Now an endpoint can have one ring per enabled stream ID, so correct that assumption. Use functions that translate the stream_id field in the URB or the DMA address of a TRB into the correct stream ring. Correct the polling loop to print out all enabled stream rings. Make the URB cancellation routine find the correct stream ring if the URB has stream_id set. Make sure the URB enqueueing routine does the same. Also correct the code that handles stalled/halted endpoints. Check that commands and registers that can take stream IDs handle them properly. That includes ringing an endpoint doorbell, resetting a stalled/halted endpoint, and setting a transfer ring dequeue pointer (since that command can set the dequeue pointer in a stream context or an endpoint context). Correct the transfer event handler to translate a TRB DMA address into the stream ring it was enqueued to. Make the code to allocate and prepare TD structures adds the TD to the right td_list for the stream ring. Make sure the code to give the first TRB in a TD to the hardware manipulates the correct stream ring. When an endpoint stalls, store the stream ID of the stream ring that stalled in the xhci_virt_ep structure. Use that instead of the stream ID in the URB, since an URB may be re-used after it is given back after a non-control endpoint stall. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-03 06:34:43 +08:00
/* Ring the doorbell for any rings with pending URBs */
static void ring_doorbell_for_active_rings(struct xhci_hcd *xhci,
unsigned int slot_id,
unsigned int ep_index)
{
unsigned int stream_id;
struct xhci_virt_ep *ep;
ep = &xhci->devs[slot_id]->eps[ep_index];
/* A ring has pending URBs if its TD list is not empty */
if (!(ep->ep_state & EP_HAS_STREAMS)) {
if (ep->ring && !(list_empty(&ep->ring->td_list)))
xhci_ring_ep_doorbell(xhci, slot_id, ep_index, 0);
USB: xhci: Correct assumptions about number of rings per endpoint. Much of the xHCI driver code assumes that endpoints only have one ring. Now an endpoint can have one ring per enabled stream ID, so correct that assumption. Use functions that translate the stream_id field in the URB or the DMA address of a TRB into the correct stream ring. Correct the polling loop to print out all enabled stream rings. Make the URB cancellation routine find the correct stream ring if the URB has stream_id set. Make sure the URB enqueueing routine does the same. Also correct the code that handles stalled/halted endpoints. Check that commands and registers that can take stream IDs handle them properly. That includes ringing an endpoint doorbell, resetting a stalled/halted endpoint, and setting a transfer ring dequeue pointer (since that command can set the dequeue pointer in a stream context or an endpoint context). Correct the transfer event handler to translate a TRB DMA address into the stream ring it was enqueued to. Make the code to allocate and prepare TD structures adds the TD to the right td_list for the stream ring. Make sure the code to give the first TRB in a TD to the hardware manipulates the correct stream ring. When an endpoint stalls, store the stream ID of the stream ring that stalled in the xhci_virt_ep structure. Use that instead of the stream ID in the URB, since an URB may be re-used after it is given back after a non-control endpoint stall. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-03 06:34:43 +08:00
return;
}
for (stream_id = 1; stream_id < ep->stream_info->num_streams;
stream_id++) {
struct xhci_stream_info *stream_info = ep->stream_info;
if (!list_empty(&stream_info->stream_rings[stream_id]->td_list))
xhci_ring_ep_doorbell(xhci, slot_id, ep_index,
stream_id);
USB: xhci: Correct assumptions about number of rings per endpoint. Much of the xHCI driver code assumes that endpoints only have one ring. Now an endpoint can have one ring per enabled stream ID, so correct that assumption. Use functions that translate the stream_id field in the URB or the DMA address of a TRB into the correct stream ring. Correct the polling loop to print out all enabled stream rings. Make the URB cancellation routine find the correct stream ring if the URB has stream_id set. Make sure the URB enqueueing routine does the same. Also correct the code that handles stalled/halted endpoints. Check that commands and registers that can take stream IDs handle them properly. That includes ringing an endpoint doorbell, resetting a stalled/halted endpoint, and setting a transfer ring dequeue pointer (since that command can set the dequeue pointer in a stream context or an endpoint context). Correct the transfer event handler to translate a TRB DMA address into the stream ring it was enqueued to. Make the code to allocate and prepare TD structures adds the TD to the right td_list for the stream ring. Make sure the code to give the first TRB in a TD to the hardware manipulates the correct stream ring. When an endpoint stalls, store the stream ID of the stream ring that stalled in the xhci_virt_ep structure. Use that instead of the stream ID in the URB, since an URB may be re-used after it is given back after a non-control endpoint stall. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-03 06:34:43 +08:00
}
}
void xhci_ring_doorbell_for_active_rings(struct xhci_hcd *xhci,
unsigned int slot_id,
unsigned int ep_index)
{
ring_doorbell_for_active_rings(xhci, slot_id, ep_index);
}
/* Get the right ring for the given slot_id, ep_index and stream_id.
* If the endpoint supports streams, boundary check the URB's stream ID.
* If the endpoint doesn't support streams, return the singular endpoint ring.
*/
struct xhci_ring *xhci_triad_to_transfer_ring(struct xhci_hcd *xhci,
unsigned int slot_id, unsigned int ep_index,
unsigned int stream_id)
{
struct xhci_virt_ep *ep;
ep = &xhci->devs[slot_id]->eps[ep_index];
/* Common case: no streams */
if (!(ep->ep_state & EP_HAS_STREAMS))
return ep->ring;
if (stream_id == 0) {
xhci_warn(xhci,
"WARN: Slot ID %u, ep index %u has streams, "
"but URB has no stream ID.\n",
slot_id, ep_index);
return NULL;
}
if (stream_id < ep->stream_info->num_streams)
return ep->stream_info->stream_rings[stream_id];
xhci_warn(xhci,
"WARN: Slot ID %u, ep index %u has "
"stream IDs 1 to %u allocated, "
"but stream ID %u is requested.\n",
slot_id, ep_index,
ep->stream_info->num_streams - 1,
stream_id);
return NULL;
}
/*
* Get the hw dequeue pointer xHC stopped on, either directly from the
* endpoint context, or if streams are in use from the stream context.
* The returned hw_dequeue contains the lowest four bits with cycle state
* and possbile stream context type.
*/
static u64 xhci_get_hw_deq(struct xhci_hcd *xhci, struct xhci_virt_device *vdev,
unsigned int ep_index, unsigned int stream_id)
{
struct xhci_ep_ctx *ep_ctx;
struct xhci_stream_ctx *st_ctx;
struct xhci_virt_ep *ep;
ep = &vdev->eps[ep_index];
if (ep->ep_state & EP_HAS_STREAMS) {
st_ctx = &ep->stream_info->stream_ctx_array[stream_id];
return le64_to_cpu(st_ctx->stream_ring);
}
ep_ctx = xhci_get_ep_ctx(xhci, vdev->out_ctx, ep_index);
return le64_to_cpu(ep_ctx->deq);
}
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
/*
* Move the xHC's endpoint ring dequeue pointer past cur_td.
* Record the new state of the xHC's endpoint ring dequeue segment,
* dequeue pointer, stream id, and new consumer cycle state in state.
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
* Update our internal representation of the ring's dequeue pointer.
*
* We do this in three jumps:
* - First we update our new ring state to be the same as when the xHC stopped.
* - Then we traverse the ring to find the segment that contains
* the last TRB in the TD. We toggle the xHC's new cycle state when we pass
* any link TRBs with the toggle cycle bit set.
* - Finally we move the dequeue state one TRB further, toggling the cycle bit
* if we've moved it past a link TRB with the toggle cycle bit set.
*
* Some of the uses of xhci_generic_trb are grotty, but if they're done
* with correct __le32 accesses they should work fine. Only users of this are
* in here.
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
*/
void xhci_find_new_dequeue_state(struct xhci_hcd *xhci,
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
unsigned int slot_id, unsigned int ep_index,
USB: xhci: Correct assumptions about number of rings per endpoint. Much of the xHCI driver code assumes that endpoints only have one ring. Now an endpoint can have one ring per enabled stream ID, so correct that assumption. Use functions that translate the stream_id field in the URB or the DMA address of a TRB into the correct stream ring. Correct the polling loop to print out all enabled stream rings. Make the URB cancellation routine find the correct stream ring if the URB has stream_id set. Make sure the URB enqueueing routine does the same. Also correct the code that handles stalled/halted endpoints. Check that commands and registers that can take stream IDs handle them properly. That includes ringing an endpoint doorbell, resetting a stalled/halted endpoint, and setting a transfer ring dequeue pointer (since that command can set the dequeue pointer in a stream context or an endpoint context). Correct the transfer event handler to translate a TRB DMA address into the stream ring it was enqueued to. Make the code to allocate and prepare TD structures adds the TD to the right td_list for the stream ring. Make sure the code to give the first TRB in a TD to the hardware manipulates the correct stream ring. When an endpoint stalls, store the stream ID of the stream ring that stalled in the xhci_virt_ep structure. Use that instead of the stream ID in the URB, since an URB may be re-used after it is given back after a non-control endpoint stall. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-03 06:34:43 +08:00
unsigned int stream_id, struct xhci_td *cur_td,
struct xhci_dequeue_state *state)
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
{
struct xhci_virt_device *dev = xhci->devs[slot_id];
struct xhci_virt_ep *ep = &dev->eps[ep_index];
USB: xhci: Correct assumptions about number of rings per endpoint. Much of the xHCI driver code assumes that endpoints only have one ring. Now an endpoint can have one ring per enabled stream ID, so correct that assumption. Use functions that translate the stream_id field in the URB or the DMA address of a TRB into the correct stream ring. Correct the polling loop to print out all enabled stream rings. Make the URB cancellation routine find the correct stream ring if the URB has stream_id set. Make sure the URB enqueueing routine does the same. Also correct the code that handles stalled/halted endpoints. Check that commands and registers that can take stream IDs handle them properly. That includes ringing an endpoint doorbell, resetting a stalled/halted endpoint, and setting a transfer ring dequeue pointer (since that command can set the dequeue pointer in a stream context or an endpoint context). Correct the transfer event handler to translate a TRB DMA address into the stream ring it was enqueued to. Make the code to allocate and prepare TD structures adds the TD to the right td_list for the stream ring. Make sure the code to give the first TRB in a TD to the hardware manipulates the correct stream ring. When an endpoint stalls, store the stream ID of the stream ring that stalled in the xhci_virt_ep structure. Use that instead of the stream ID in the URB, since an URB may be re-used after it is given back after a non-control endpoint stall. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-03 06:34:43 +08:00
struct xhci_ring *ep_ring;
struct xhci_segment *new_seg;
union xhci_trb *new_deq;
dma_addr_t addr;
usb: xhci: Prefer endpoint context dequeue pointer over stopped_trb We have observed a rare cycle state desync bug after Set TR Dequeue Pointer commands on Intel LynxPoint xHCs (resulting in an endpoint that doesn't fetch new TRBs and thus an unresponsive USB device). It always triggers when a previous Set TR Dequeue Pointer command has set the pointer to the final Link TRB of a segment, and then another URB gets enqueued and cancelled again before it can be completed. Further investigation showed that the xHC had returned the Link TRB in the TRB Pointer field of the Transfer Event (CC == Stopped -- Length Invalid), but when xhci_find_new_dequeue_state() later accesses the Endpoint Context's TR Dequeue Pointer field it is set to the first TRB of the next segment. The driver expects those two values to be the same in this situation, and uses the cycle state of the latter together with the address of the former. This should be fine according to the XHCI specification, since the endpoint ring should be stopped when returning the Transfer Event and thus should not advance over the Link TRB before it gets restarted. However, real-world XHCI implementations apparently don't really care that much about these details, so the driver should follow a more defensive approach to try to work around HC spec violations. This patch removes the stopped_trb variable that had been used to store the TRB Pointer from the last Transfer Event of a stopped TRB. Instead, xhci_find_new_dequeue_state() now relies only on the Endpoint Context, requiring a small amount of additional processing to find the virtual address corresponding to the TR Dequeue Pointer. Some other parts of the function were slightly rearranged to better fit into this model. This patch should be backported to kernels as old as 2.6.31 that contain the commit ae636747146ea97efa18e04576acd3416e2514f5 "USB: xhci: URB cancellation support." Signed-off-by: Julius Werner <jwerner@chromium.org> Cc: stable@vger.kernel.org Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-04-26 00:20:13 +08:00
u64 hw_dequeue;
bool cycle_found = false;
bool td_last_trb_found = false;
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
USB: xhci: Correct assumptions about number of rings per endpoint. Much of the xHCI driver code assumes that endpoints only have one ring. Now an endpoint can have one ring per enabled stream ID, so correct that assumption. Use functions that translate the stream_id field in the URB or the DMA address of a TRB into the correct stream ring. Correct the polling loop to print out all enabled stream rings. Make the URB cancellation routine find the correct stream ring if the URB has stream_id set. Make sure the URB enqueueing routine does the same. Also correct the code that handles stalled/halted endpoints. Check that commands and registers that can take stream IDs handle them properly. That includes ringing an endpoint doorbell, resetting a stalled/halted endpoint, and setting a transfer ring dequeue pointer (since that command can set the dequeue pointer in a stream context or an endpoint context). Correct the transfer event handler to translate a TRB DMA address into the stream ring it was enqueued to. Make the code to allocate and prepare TD structures adds the TD to the right td_list for the stream ring. Make sure the code to give the first TRB in a TD to the hardware manipulates the correct stream ring. When an endpoint stalls, store the stream ID of the stream ring that stalled in the xhci_virt_ep structure. Use that instead of the stream ID in the URB, since an URB may be re-used after it is given back after a non-control endpoint stall. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-03 06:34:43 +08:00
ep_ring = xhci_triad_to_transfer_ring(xhci, slot_id,
ep_index, stream_id);
if (!ep_ring) {
xhci_warn(xhci, "WARN can't find new dequeue state "
"for invalid stream ID %u.\n",
stream_id);
return;
}
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
/* Dig out the cycle state saved by the xHC during the stop ep cmd */
xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
"Finding endpoint context");
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
hw_dequeue = xhci_get_hw_deq(xhci, dev, ep_index, stream_id);
new_seg = ep_ring->deq_seg;
new_deq = ep_ring->dequeue;
state->new_cycle_state = hw_dequeue & 0x1;
state->stream_id = stream_id;
usb: xhci: Prefer endpoint context dequeue pointer over stopped_trb We have observed a rare cycle state desync bug after Set TR Dequeue Pointer commands on Intel LynxPoint xHCs (resulting in an endpoint that doesn't fetch new TRBs and thus an unresponsive USB device). It always triggers when a previous Set TR Dequeue Pointer command has set the pointer to the final Link TRB of a segment, and then another URB gets enqueued and cancelled again before it can be completed. Further investigation showed that the xHC had returned the Link TRB in the TRB Pointer field of the Transfer Event (CC == Stopped -- Length Invalid), but when xhci_find_new_dequeue_state() later accesses the Endpoint Context's TR Dequeue Pointer field it is set to the first TRB of the next segment. The driver expects those two values to be the same in this situation, and uses the cycle state of the latter together with the address of the former. This should be fine according to the XHCI specification, since the endpoint ring should be stopped when returning the Transfer Event and thus should not advance over the Link TRB before it gets restarted. However, real-world XHCI implementations apparently don't really care that much about these details, so the driver should follow a more defensive approach to try to work around HC spec violations. This patch removes the stopped_trb variable that had been used to store the TRB Pointer from the last Transfer Event of a stopped TRB. Instead, xhci_find_new_dequeue_state() now relies only on the Endpoint Context, requiring a small amount of additional processing to find the virtual address corresponding to the TR Dequeue Pointer. Some other parts of the function were slightly rearranged to better fit into this model. This patch should be backported to kernels as old as 2.6.31 that contain the commit ae636747146ea97efa18e04576acd3416e2514f5 "USB: xhci: URB cancellation support." Signed-off-by: Julius Werner <jwerner@chromium.org> Cc: stable@vger.kernel.org Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-04-26 00:20:13 +08:00
/*
* We want to find the pointer, segment and cycle state of the new trb
* (the one after current TD's last_trb). We know the cycle state at
* hw_dequeue, so walk the ring until both hw_dequeue and last_trb are
* found.
usb: xhci: Prefer endpoint context dequeue pointer over stopped_trb We have observed a rare cycle state desync bug after Set TR Dequeue Pointer commands on Intel LynxPoint xHCs (resulting in an endpoint that doesn't fetch new TRBs and thus an unresponsive USB device). It always triggers when a previous Set TR Dequeue Pointer command has set the pointer to the final Link TRB of a segment, and then another URB gets enqueued and cancelled again before it can be completed. Further investigation showed that the xHC had returned the Link TRB in the TRB Pointer field of the Transfer Event (CC == Stopped -- Length Invalid), but when xhci_find_new_dequeue_state() later accesses the Endpoint Context's TR Dequeue Pointer field it is set to the first TRB of the next segment. The driver expects those two values to be the same in this situation, and uses the cycle state of the latter together with the address of the former. This should be fine according to the XHCI specification, since the endpoint ring should be stopped when returning the Transfer Event and thus should not advance over the Link TRB before it gets restarted. However, real-world XHCI implementations apparently don't really care that much about these details, so the driver should follow a more defensive approach to try to work around HC spec violations. This patch removes the stopped_trb variable that had been used to store the TRB Pointer from the last Transfer Event of a stopped TRB. Instead, xhci_find_new_dequeue_state() now relies only on the Endpoint Context, requiring a small amount of additional processing to find the virtual address corresponding to the TR Dequeue Pointer. Some other parts of the function were slightly rearranged to better fit into this model. This patch should be backported to kernels as old as 2.6.31 that contain the commit ae636747146ea97efa18e04576acd3416e2514f5 "USB: xhci: URB cancellation support." Signed-off-by: Julius Werner <jwerner@chromium.org> Cc: stable@vger.kernel.org Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-04-26 00:20:13 +08:00
*/
do {
if (!cycle_found && xhci_trb_virt_to_dma(new_seg, new_deq)
== (dma_addr_t)(hw_dequeue & ~0xf)) {
cycle_found = true;
if (td_last_trb_found)
break;
}
if (new_deq == cur_td->last_trb)
td_last_trb_found = true;
usb: xhci: Prefer endpoint context dequeue pointer over stopped_trb We have observed a rare cycle state desync bug after Set TR Dequeue Pointer commands on Intel LynxPoint xHCs (resulting in an endpoint that doesn't fetch new TRBs and thus an unresponsive USB device). It always triggers when a previous Set TR Dequeue Pointer command has set the pointer to the final Link TRB of a segment, and then another URB gets enqueued and cancelled again before it can be completed. Further investigation showed that the xHC had returned the Link TRB in the TRB Pointer field of the Transfer Event (CC == Stopped -- Length Invalid), but when xhci_find_new_dequeue_state() later accesses the Endpoint Context's TR Dequeue Pointer field it is set to the first TRB of the next segment. The driver expects those two values to be the same in this situation, and uses the cycle state of the latter together with the address of the former. This should be fine according to the XHCI specification, since the endpoint ring should be stopped when returning the Transfer Event and thus should not advance over the Link TRB before it gets restarted. However, real-world XHCI implementations apparently don't really care that much about these details, so the driver should follow a more defensive approach to try to work around HC spec violations. This patch removes the stopped_trb variable that had been used to store the TRB Pointer from the last Transfer Event of a stopped TRB. Instead, xhci_find_new_dequeue_state() now relies only on the Endpoint Context, requiring a small amount of additional processing to find the virtual address corresponding to the TR Dequeue Pointer. Some other parts of the function were slightly rearranged to better fit into this model. This patch should be backported to kernels as old as 2.6.31 that contain the commit ae636747146ea97efa18e04576acd3416e2514f5 "USB: xhci: URB cancellation support." Signed-off-by: Julius Werner <jwerner@chromium.org> Cc: stable@vger.kernel.org Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-04-26 00:20:13 +08:00
if (cycle_found && trb_is_link(new_deq) &&
link_trb_toggles_cycle(new_deq))
state->new_cycle_state ^= 0x1;
next_trb(xhci, ep_ring, &new_seg, &new_deq);
/* Search wrapped around, bail out */
if (new_deq == ep->ring->dequeue) {
xhci_err(xhci, "Error: Failed finding new dequeue state\n");
state->new_deq_seg = NULL;
state->new_deq_ptr = NULL;
return;
}
} while (!cycle_found || !td_last_trb_found);
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
state->new_deq_seg = new_seg;
state->new_deq_ptr = new_deq;
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
usb: xhci: Prefer endpoint context dequeue pointer over stopped_trb We have observed a rare cycle state desync bug after Set TR Dequeue Pointer commands on Intel LynxPoint xHCs (resulting in an endpoint that doesn't fetch new TRBs and thus an unresponsive USB device). It always triggers when a previous Set TR Dequeue Pointer command has set the pointer to the final Link TRB of a segment, and then another URB gets enqueued and cancelled again before it can be completed. Further investigation showed that the xHC had returned the Link TRB in the TRB Pointer field of the Transfer Event (CC == Stopped -- Length Invalid), but when xhci_find_new_dequeue_state() later accesses the Endpoint Context's TR Dequeue Pointer field it is set to the first TRB of the next segment. The driver expects those two values to be the same in this situation, and uses the cycle state of the latter together with the address of the former. This should be fine according to the XHCI specification, since the endpoint ring should be stopped when returning the Transfer Event and thus should not advance over the Link TRB before it gets restarted. However, real-world XHCI implementations apparently don't really care that much about these details, so the driver should follow a more defensive approach to try to work around HC spec violations. This patch removes the stopped_trb variable that had been used to store the TRB Pointer from the last Transfer Event of a stopped TRB. Instead, xhci_find_new_dequeue_state() now relies only on the Endpoint Context, requiring a small amount of additional processing to find the virtual address corresponding to the TR Dequeue Pointer. Some other parts of the function were slightly rearranged to better fit into this model. This patch should be backported to kernels as old as 2.6.31 that contain the commit ae636747146ea97efa18e04576acd3416e2514f5 "USB: xhci: URB cancellation support." Signed-off-by: Julius Werner <jwerner@chromium.org> Cc: stable@vger.kernel.org Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-04-26 00:20:13 +08:00
/* Don't update the ring cycle state for the producer (us). */
xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
"Cycle state = 0x%x", state->new_cycle_state);
xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
"New dequeue segment = %p (virtual)",
state->new_deq_seg);
addr = xhci_trb_virt_to_dma(state->new_deq_seg, state->new_deq_ptr);
xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
"New dequeue pointer = 0x%llx (DMA)",
(unsigned long long) addr);
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
}
xhci: Fix failed enqueue in the middle of isoch TD. When an isochronous transfer is enqueued, xhci_queue_isoc_tx_prepare() will ensure that there is enough room on the transfer rings for all of the isochronous TDs for that URB. However, when xhci_queue_isoc_tx() is enqueueing individual isoc TDs, the prepare_transfer() function can fail if the endpoint state has changed to disabled, error, or some other unknown state. With the current code, if Nth TD (not the first TD) fails, the ring is left in a sorry state. The partially enqueued TDs are left on the ring, and the first TRB of the TD is not given back to the hardware. The enqueue pointer is left on the TRB after the last successfully enqueued TD. This means the ring is basically useless. Any new transfers will be enqueued after the failed TDs, which the hardware will never read because the cycle bit indicates it does not own them. The ring will fill up with untransferred TDs, and the endpoint will be basically unusable. The untransferred TDs will also remain on the TD list. Since the td_list is a FIFO, this basically means the ring handler will be waiting on TDs that will never be completed (or worse, dereference memory that doesn't exist any more). Change the code to clean up the isochronous ring after a failed transfer. If the first TD failed, simply return and allow the xhci_urb_enqueue function to free the urb_priv. If the Nth TD failed, first remove the TDs from the td_list. Then convert the TRBs that were enqueued into No-op TRBs. Make sure to flip the cycle bit on all enqueued TRBs (including any link TRBs in the middle or between TDs), but leave the cycle bit of the first TRB (which will show software-owned) intact. Then move the ring enqueue pointer back to the first TRB and make sure to change the xhci_ring's cycle state to what is appropriate for that ring segment. This ensures that the No-op TRBs will be overwritten by subsequent TDs, and the hardware will not start executing random TRBs because the cycle bit was left as hardware-owned. This bug is unlikely to be hit, but it was something I noticed while tracking down the watchdog timer issue. I verified that the fix works by injecting some errors on the 250th isochronous URB queued, although I could not verify that the ring is in the correct state because uvcvideo refused to talk to the device after the first usb_submit_urb() failed. Ring debugging shows that the ring looks correct, however. This patch should be backported to kernels as old as 2.6.36. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Cc: Andiry Xu <andiry.xu@amd.com> Cc: stable@kernel.org
2011-07-30 03:44:32 +08:00
/* flip_cycle means flip the cycle bit of all but the first and last TRB.
* (The last TRB actually points to the ring enqueue pointer, which is not part
* of this TD.) This is used to remove partially enqueued isoc TDs from a ring.
*/
static void td_to_noop(struct xhci_hcd *xhci, struct xhci_ring *ep_ring,
struct xhci_td *td, bool flip_cycle)
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
{
struct xhci_segment *seg = td->start_seg;
union xhci_trb *trb = td->first_trb;
while (1) {
trb_to_noop(trb, TRB_TR_NOOP);
/* flip cycle if asked to */
if (flip_cycle && trb != td->first_trb && trb != td->last_trb)
trb->generic.field[3] ^= cpu_to_le32(TRB_CYCLE);
if (trb == td->last_trb)
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
break;
next_trb(xhci, ep_ring, &seg, &trb);
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
}
}
static void xhci_stop_watchdog_timer_in_irq(struct xhci_hcd *xhci,
USB: xhci: Add watchdog timer for URB cancellation. In order to giveback a canceled URB, we must ensure that the xHCI hardware will not access the buffer in an URB. We can't modify the buffer pointers on endpoint rings without issuing and waiting for a stop endpoint command. Since URBs can be canceled in interrupt context, we can't wait on that command. The old code trusted that the host controller would respond to the command, and would giveback the URBs in the event handler. If the hardware never responds to the stop endpoint command, the URBs will never be completed, and we might hang the USB subsystem. Implement a watchdog timer that is spawned whenever a stop endpoint command is queued. If a stop endpoint command event is found on the event ring during an interrupt, we need to stop the watchdog timer with del_timer(). Since del_timer() can fail if the timer is running and waiting on the xHCI lock, we need a way to signal to the timer that everything is fine and it should exit. If we simply clear EP_HALT_PENDING, a new stop endpoint command could sneak in and set it before the watchdog timer can grab the lock. Instead we use a combination of the EP_HALT_PENDING flag and a counter for the number of pending stop endpoint commands (xhci_virt_ep->stop_cmds_pending). If we need to cancel the watchdog timer and del_timer() succeeds, we decrement the number of pending stop endpoint commands. If del_timer() fails, we leave the number of pending stop endpoint commands alone. In either case, we clear the EP_HALT_PENDING flag. The timer will decrement the number of pending stop endpoint commands once it obtains the lock. If the timer is the tail end of the last stop endpoint command (xhci_virt_ep->stop_cmds_pending == 0), and the endpoint's command is still pending (EP_HALT_PENDING is set), we assume the host is dying. The watchdog timer will set XHCI_STATE_DYING, try to halt the xHCI host, and give back all pending URBs. Various other places in the driver need to check whether the xHCI host is dying. If the interrupt handler ever notices, it should immediately stop processing events. The URB enqueue function should also return -ESHUTDOWN. The URB dequeue function should simply return the value of usb_hcd_check_unlink_urb() and the watchdog timer will take care of giving the URB back. When a device is disconnected, the xHCI hardware structures should be freed without issuing a disable slot command (since the hardware probably won't respond to it anyway). The debugging polling loop should stop polling if the host is dying. When a device is disconnected, any pending watchdog timers are killed with del_timer_sync(). It must be synchronous so that the watchdog timer doesn't attempt to access the freed endpoint structures. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-10-28 01:57:01 +08:00
struct xhci_virt_ep *ep)
{
ep->ep_state &= ~EP_STOP_CMD_PENDING;
/* Can't del_timer_sync in interrupt */
del_timer(&ep->stop_cmd_timer);
USB: xhci: Add watchdog timer for URB cancellation. In order to giveback a canceled URB, we must ensure that the xHCI hardware will not access the buffer in an URB. We can't modify the buffer pointers on endpoint rings without issuing and waiting for a stop endpoint command. Since URBs can be canceled in interrupt context, we can't wait on that command. The old code trusted that the host controller would respond to the command, and would giveback the URBs in the event handler. If the hardware never responds to the stop endpoint command, the URBs will never be completed, and we might hang the USB subsystem. Implement a watchdog timer that is spawned whenever a stop endpoint command is queued. If a stop endpoint command event is found on the event ring during an interrupt, we need to stop the watchdog timer with del_timer(). Since del_timer() can fail if the timer is running and waiting on the xHCI lock, we need a way to signal to the timer that everything is fine and it should exit. If we simply clear EP_HALT_PENDING, a new stop endpoint command could sneak in and set it before the watchdog timer can grab the lock. Instead we use a combination of the EP_HALT_PENDING flag and a counter for the number of pending stop endpoint commands (xhci_virt_ep->stop_cmds_pending). If we need to cancel the watchdog timer and del_timer() succeeds, we decrement the number of pending stop endpoint commands. If del_timer() fails, we leave the number of pending stop endpoint commands alone. In either case, we clear the EP_HALT_PENDING flag. The timer will decrement the number of pending stop endpoint commands once it obtains the lock. If the timer is the tail end of the last stop endpoint command (xhci_virt_ep->stop_cmds_pending == 0), and the endpoint's command is still pending (EP_HALT_PENDING is set), we assume the host is dying. The watchdog timer will set XHCI_STATE_DYING, try to halt the xHCI host, and give back all pending URBs. Various other places in the driver need to check whether the xHCI host is dying. If the interrupt handler ever notices, it should immediately stop processing events. The URB enqueue function should also return -ESHUTDOWN. The URB dequeue function should simply return the value of usb_hcd_check_unlink_urb() and the watchdog timer will take care of giving the URB back. When a device is disconnected, the xHCI hardware structures should be freed without issuing a disable slot command (since the hardware probably won't respond to it anyway). The debugging polling loop should stop polling if the host is dying. When a device is disconnected, any pending watchdog timers are killed with del_timer_sync(). It must be synchronous so that the watchdog timer doesn't attempt to access the freed endpoint structures. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-10-28 01:57:01 +08:00
}
/*
* Must be called with xhci->lock held in interrupt context,
* releases and re-acquires xhci->lock
*/
USB: xhci: Add watchdog timer for URB cancellation. In order to giveback a canceled URB, we must ensure that the xHCI hardware will not access the buffer in an URB. We can't modify the buffer pointers on endpoint rings without issuing and waiting for a stop endpoint command. Since URBs can be canceled in interrupt context, we can't wait on that command. The old code trusted that the host controller would respond to the command, and would giveback the URBs in the event handler. If the hardware never responds to the stop endpoint command, the URBs will never be completed, and we might hang the USB subsystem. Implement a watchdog timer that is spawned whenever a stop endpoint command is queued. If a stop endpoint command event is found on the event ring during an interrupt, we need to stop the watchdog timer with del_timer(). Since del_timer() can fail if the timer is running and waiting on the xHCI lock, we need a way to signal to the timer that everything is fine and it should exit. If we simply clear EP_HALT_PENDING, a new stop endpoint command could sneak in and set it before the watchdog timer can grab the lock. Instead we use a combination of the EP_HALT_PENDING flag and a counter for the number of pending stop endpoint commands (xhci_virt_ep->stop_cmds_pending). If we need to cancel the watchdog timer and del_timer() succeeds, we decrement the number of pending stop endpoint commands. If del_timer() fails, we leave the number of pending stop endpoint commands alone. In either case, we clear the EP_HALT_PENDING flag. The timer will decrement the number of pending stop endpoint commands once it obtains the lock. If the timer is the tail end of the last stop endpoint command (xhci_virt_ep->stop_cmds_pending == 0), and the endpoint's command is still pending (EP_HALT_PENDING is set), we assume the host is dying. The watchdog timer will set XHCI_STATE_DYING, try to halt the xHCI host, and give back all pending URBs. Various other places in the driver need to check whether the xHCI host is dying. If the interrupt handler ever notices, it should immediately stop processing events. The URB enqueue function should also return -ESHUTDOWN. The URB dequeue function should simply return the value of usb_hcd_check_unlink_urb() and the watchdog timer will take care of giving the URB back. When a device is disconnected, the xHCI hardware structures should be freed without issuing a disable slot command (since the hardware probably won't respond to it anyway). The debugging polling loop should stop polling if the host is dying. When a device is disconnected, any pending watchdog timers are killed with del_timer_sync(). It must be synchronous so that the watchdog timer doesn't attempt to access the freed endpoint structures. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-10-28 01:57:01 +08:00
static void xhci_giveback_urb_in_irq(struct xhci_hcd *xhci,
struct xhci_td *cur_td, int status)
USB: xhci: Add watchdog timer for URB cancellation. In order to giveback a canceled URB, we must ensure that the xHCI hardware will not access the buffer in an URB. We can't modify the buffer pointers on endpoint rings without issuing and waiting for a stop endpoint command. Since URBs can be canceled in interrupt context, we can't wait on that command. The old code trusted that the host controller would respond to the command, and would giveback the URBs in the event handler. If the hardware never responds to the stop endpoint command, the URBs will never be completed, and we might hang the USB subsystem. Implement a watchdog timer that is spawned whenever a stop endpoint command is queued. If a stop endpoint command event is found on the event ring during an interrupt, we need to stop the watchdog timer with del_timer(). Since del_timer() can fail if the timer is running and waiting on the xHCI lock, we need a way to signal to the timer that everything is fine and it should exit. If we simply clear EP_HALT_PENDING, a new stop endpoint command could sneak in and set it before the watchdog timer can grab the lock. Instead we use a combination of the EP_HALT_PENDING flag and a counter for the number of pending stop endpoint commands (xhci_virt_ep->stop_cmds_pending). If we need to cancel the watchdog timer and del_timer() succeeds, we decrement the number of pending stop endpoint commands. If del_timer() fails, we leave the number of pending stop endpoint commands alone. In either case, we clear the EP_HALT_PENDING flag. The timer will decrement the number of pending stop endpoint commands once it obtains the lock. If the timer is the tail end of the last stop endpoint command (xhci_virt_ep->stop_cmds_pending == 0), and the endpoint's command is still pending (EP_HALT_PENDING is set), we assume the host is dying. The watchdog timer will set XHCI_STATE_DYING, try to halt the xHCI host, and give back all pending URBs. Various other places in the driver need to check whether the xHCI host is dying. If the interrupt handler ever notices, it should immediately stop processing events. The URB enqueue function should also return -ESHUTDOWN. The URB dequeue function should simply return the value of usb_hcd_check_unlink_urb() and the watchdog timer will take care of giving the URB back. When a device is disconnected, the xHCI hardware structures should be freed without issuing a disable slot command (since the hardware probably won't respond to it anyway). The debugging polling loop should stop polling if the host is dying. When a device is disconnected, any pending watchdog timers are killed with del_timer_sync(). It must be synchronous so that the watchdog timer doesn't attempt to access the freed endpoint structures. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-10-28 01:57:01 +08:00
{
struct urb *urb = cur_td->urb;
struct urb_priv *urb_priv = urb->hcpriv;
struct usb_hcd *hcd = bus_to_hcd(urb->dev->bus);
if (usb_pipetype(urb->pipe) == PIPE_ISOCHRONOUS) {
xhci_to_hcd(xhci)->self.bandwidth_isoc_reqs--;
if (xhci_to_hcd(xhci)->self.bandwidth_isoc_reqs == 0) {
if (xhci->quirks & XHCI_AMD_PLL_FIX)
usb_amd_quirk_pll_enable();
}
}
xhci_urb_free_priv(urb_priv);
usb_hcd_unlink_urb_from_ep(hcd, urb);
trace_xhci_urb_giveback(urb);
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)
{
struct device *dev = xhci_to_hcd(xhci)->self.controller;
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;
}
dma_unmap_single(dev, seg->bounce_dma, ring->bounce_buf_len,
DMA_FROM_DEVICE);
/* for in tranfers we need to copy the data from bounce to sg */
len = sg_pcopy_from_buffer(urb->sg, urb->num_sgs, seg->bounce_buf,
seg->bounce_len, seg->bounce_offs);
if (len != seg->bounce_len)
xhci_warn(xhci, "WARN Wrong bounce buffer read length: %zu != %d\n",
len, seg->bounce_len);
seg->bounce_len = 0;
seg->bounce_offs = 0;
}
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
/*
* When we get a command completion for a Stop Endpoint Command, we need to
* unlink any cancelled TDs from the ring. There are two ways to do that:
*
* 1. If the HW was in the middle of processing the TD that needs to be
* cancelled, then we must move the ring's dequeue pointer past the last TRB
* in the TD with a Set Dequeue Pointer Command.
* 2. Otherwise, we turn all the TRBs in the TD into No-op TRBs (with the chain
* bit cleared) so that the HW will skip over them.
*/
static void xhci_handle_cmd_stop_ep(struct xhci_hcd *xhci, int slot_id,
union xhci_trb *trb, struct xhci_event_cmd *event)
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
{
unsigned int ep_index;
struct xhci_ring *ep_ring;
struct xhci_virt_ep *ep;
USB: clean up some host controller sparse warnings Fix usb sparse warnings: drivers/usb/host/isp1362-hcd.c:2220:50: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:43:24: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:49:24: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:161:24: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:198:16: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:319:31: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:1231:33: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-pci.c:177:23: warning: non-ANSI function declaration of function 'xhci_register_pci' drivers/usb/host/xhci-pci.c:182:26: warning: non-ANSI function declaration of function 'xhci_unregister_pci' drivers/usb/host/xhci-ring.c:342:32: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:525:34: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:1009:32: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:1031:32: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:1041:16: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:1096:30: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:1100:27: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:224:27: warning: symbol 'xhci_alloc_container_ctx' was not declared. Should it be static? drivers/usb/host/xhci-mem.c:242:6: warning: symbol 'xhci_free_container_ctx' was not declared. Should it be static? Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Lothar Wassmann <LW@KARO-electronics.de> Signed-off By: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-19 23:53:50 +08:00
struct xhci_td *cur_td = NULL;
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
struct xhci_td *last_unlinked_td;
struct xhci_ep_ctx *ep_ctx;
struct xhci_virt_device *vdev;
u64 hw_deq;
struct xhci_dequeue_state deq_state;
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
if (unlikely(TRB_TO_SUSPEND_PORT(le32_to_cpu(trb->generic.field[3])))) {
if (!xhci->devs[slot_id])
xhci_warn(xhci, "Stop endpoint command "
"completion for disabled slot %u\n",
slot_id);
return;
}
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
memset(&deq_state, 0, sizeof(deq_state));
ep_index = TRB_TO_EP_INDEX(le32_to_cpu(trb->generic.field[3]));
vdev = xhci->devs[slot_id];
ep_ctx = xhci_get_ep_ctx(xhci, vdev->out_ctx, ep_index);
trace_xhci_handle_cmd_stop_ep(ep_ctx);
ep = &xhci->devs[slot_id]->eps[ep_index];
last_unlinked_td = list_last_entry(&ep->cancelled_td_list,
struct xhci_td, cancelled_td_list);
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
USB: xhci: Handle URB cancel, complete and resubmit race. In the old code, there was a race condition between the stop endpoint command and the URB submission process. When the stop endpoint command is handled by the event handler, the endpoint ring is assumed to be stopped. When a stop endpoint command is queued, URB submissions are to not ring the doorbell. The old code would check the number of pending URBs to be canceled, and would not ring the doorbell if it was non-zero. However, the following race condition could occur with the old code: 1. Cancel an URB, add it to the list of URBs to be canceled, queue the stop endpoint command, and increment ep->cancels_pending to 1. 2. The URB finishes on the HW, and an event is enqueued to the event ring (at the same time as 1). 3. The stop endpoint command finishes, and the endpoint is halted. An event is queued to the event ring. 4. The event handler sees the finished URB, notices it was to be canceled, decrements ep->cancels_pending to 0, and removes it from the to be canceled list. 5. The event handler drops the lock and gives back the URB. The completion handler requeues the URB (or a different driver enqueues a new URB). This causes the endpoint's doorbell to be rung, since ep->cancels_pending == 0. The endpoint is now running. 6. A second URB is canceled, and it's added to the canceled list. Since ep->cancels_pending == 0, a new stop endpoint command is queued, and ep->cancels_pending is incremented to 1. 7. The event handler then sees the completed stop endpoint command. The handler assumes the endpoint is stopped, but it isn't. It attempts to move the dequeue pointer or change TDs to cancel the second URB, while the hardware is actively accessing the endpoint ring. To eliminate this race condition, a new endpoint state bit is introduced, EP_HALT_PENDING. When this bit is set, a stop endpoint command has been queued, and the command handler has not begun to process the URB cancellation list yet. The endpoint doorbell should not be rung when this is set. Set this when a stop endpoint command is queued, clear it when the handler for that command runs, and check if it's set before ringing a doorbell. ep->cancels_pending is eliminated, because it is no longer used. Make sure to ring the doorbell for an endpoint when the stop endpoint command handler runs, even if the canceled URB list is empty. All canceled URBs could have completed and new URBs could have been enqueued without the doorbell being rung before the command was handled. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-10-28 01:55:52 +08:00
if (list_empty(&ep->cancelled_td_list)) {
USB: xhci: Add watchdog timer for URB cancellation. In order to giveback a canceled URB, we must ensure that the xHCI hardware will not access the buffer in an URB. We can't modify the buffer pointers on endpoint rings without issuing and waiting for a stop endpoint command. Since URBs can be canceled in interrupt context, we can't wait on that command. The old code trusted that the host controller would respond to the command, and would giveback the URBs in the event handler. If the hardware never responds to the stop endpoint command, the URBs will never be completed, and we might hang the USB subsystem. Implement a watchdog timer that is spawned whenever a stop endpoint command is queued. If a stop endpoint command event is found on the event ring during an interrupt, we need to stop the watchdog timer with del_timer(). Since del_timer() can fail if the timer is running and waiting on the xHCI lock, we need a way to signal to the timer that everything is fine and it should exit. If we simply clear EP_HALT_PENDING, a new stop endpoint command could sneak in and set it before the watchdog timer can grab the lock. Instead we use a combination of the EP_HALT_PENDING flag and a counter for the number of pending stop endpoint commands (xhci_virt_ep->stop_cmds_pending). If we need to cancel the watchdog timer and del_timer() succeeds, we decrement the number of pending stop endpoint commands. If del_timer() fails, we leave the number of pending stop endpoint commands alone. In either case, we clear the EP_HALT_PENDING flag. The timer will decrement the number of pending stop endpoint commands once it obtains the lock. If the timer is the tail end of the last stop endpoint command (xhci_virt_ep->stop_cmds_pending == 0), and the endpoint's command is still pending (EP_HALT_PENDING is set), we assume the host is dying. The watchdog timer will set XHCI_STATE_DYING, try to halt the xHCI host, and give back all pending URBs. Various other places in the driver need to check whether the xHCI host is dying. If the interrupt handler ever notices, it should immediately stop processing events. The URB enqueue function should also return -ESHUTDOWN. The URB dequeue function should simply return the value of usb_hcd_check_unlink_urb() and the watchdog timer will take care of giving the URB back. When a device is disconnected, the xHCI hardware structures should be freed without issuing a disable slot command (since the hardware probably won't respond to it anyway). The debugging polling loop should stop polling if the host is dying. When a device is disconnected, any pending watchdog timers are killed with del_timer_sync(). It must be synchronous so that the watchdog timer doesn't attempt to access the freed endpoint structures. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-10-28 01:57:01 +08:00
xhci_stop_watchdog_timer_in_irq(xhci, ep);
USB: xhci: Correct assumptions about number of rings per endpoint. Much of the xHCI driver code assumes that endpoints only have one ring. Now an endpoint can have one ring per enabled stream ID, so correct that assumption. Use functions that translate the stream_id field in the URB or the DMA address of a TRB into the correct stream ring. Correct the polling loop to print out all enabled stream rings. Make the URB cancellation routine find the correct stream ring if the URB has stream_id set. Make sure the URB enqueueing routine does the same. Also correct the code that handles stalled/halted endpoints. Check that commands and registers that can take stream IDs handle them properly. That includes ringing an endpoint doorbell, resetting a stalled/halted endpoint, and setting a transfer ring dequeue pointer (since that command can set the dequeue pointer in a stream context or an endpoint context). Correct the transfer event handler to translate a TRB DMA address into the stream ring it was enqueued to. Make the code to allocate and prepare TD structures adds the TD to the right td_list for the stream ring. Make sure the code to give the first TRB in a TD to the hardware manipulates the correct stream ring. When an endpoint stalls, store the stream ID of the stream ring that stalled in the xhci_virt_ep structure. Use that instead of the stream ID in the URB, since an URB may be re-used after it is given back after a non-control endpoint stall. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-03 06:34:43 +08:00
ring_doorbell_for_active_rings(xhci, slot_id, ep_index);
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
return;
USB: xhci: Handle URB cancel, complete and resubmit race. In the old code, there was a race condition between the stop endpoint command and the URB submission process. When the stop endpoint command is handled by the event handler, the endpoint ring is assumed to be stopped. When a stop endpoint command is queued, URB submissions are to not ring the doorbell. The old code would check the number of pending URBs to be canceled, and would not ring the doorbell if it was non-zero. However, the following race condition could occur with the old code: 1. Cancel an URB, add it to the list of URBs to be canceled, queue the stop endpoint command, and increment ep->cancels_pending to 1. 2. The URB finishes on the HW, and an event is enqueued to the event ring (at the same time as 1). 3. The stop endpoint command finishes, and the endpoint is halted. An event is queued to the event ring. 4. The event handler sees the finished URB, notices it was to be canceled, decrements ep->cancels_pending to 0, and removes it from the to be canceled list. 5. The event handler drops the lock and gives back the URB. The completion handler requeues the URB (or a different driver enqueues a new URB). This causes the endpoint's doorbell to be rung, since ep->cancels_pending == 0. The endpoint is now running. 6. A second URB is canceled, and it's added to the canceled list. Since ep->cancels_pending == 0, a new stop endpoint command is queued, and ep->cancels_pending is incremented to 1. 7. The event handler then sees the completed stop endpoint command. The handler assumes the endpoint is stopped, but it isn't. It attempts to move the dequeue pointer or change TDs to cancel the second URB, while the hardware is actively accessing the endpoint ring. To eliminate this race condition, a new endpoint state bit is introduced, EP_HALT_PENDING. When this bit is set, a stop endpoint command has been queued, and the command handler has not begun to process the URB cancellation list yet. The endpoint doorbell should not be rung when this is set. Set this when a stop endpoint command is queued, clear it when the handler for that command runs, and check if it's set before ringing a doorbell. ep->cancels_pending is eliminated, because it is no longer used. Make sure to ring the doorbell for an endpoint when the stop endpoint command handler runs, even if the canceled URB list is empty. All canceled URBs could have completed and new URBs could have been enqueued without the doorbell being rung before the command was handled. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-10-28 01:55:52 +08:00
}
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
/* Fix up the ep ring first, so HW stops executing cancelled TDs.
* We have the xHCI lock, so nothing can modify this list until we drop
* it. We're also in the event handler, so we can't get re-interrupted
* if another Stop Endpoint command completes
*/
list_for_each_entry(cur_td, &ep->cancelled_td_list, cancelled_td_list) {
xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
"Removing canceled TD starting at 0x%llx (dma).",
(unsigned long long)xhci_trb_virt_to_dma(
cur_td->start_seg, cur_td->first_trb));
USB: xhci: Correct assumptions about number of rings per endpoint. Much of the xHCI driver code assumes that endpoints only have one ring. Now an endpoint can have one ring per enabled stream ID, so correct that assumption. Use functions that translate the stream_id field in the URB or the DMA address of a TRB into the correct stream ring. Correct the polling loop to print out all enabled stream rings. Make the URB cancellation routine find the correct stream ring if the URB has stream_id set. Make sure the URB enqueueing routine does the same. Also correct the code that handles stalled/halted endpoints. Check that commands and registers that can take stream IDs handle them properly. That includes ringing an endpoint doorbell, resetting a stalled/halted endpoint, and setting a transfer ring dequeue pointer (since that command can set the dequeue pointer in a stream context or an endpoint context). Correct the transfer event handler to translate a TRB DMA address into the stream ring it was enqueued to. Make the code to allocate and prepare TD structures adds the TD to the right td_list for the stream ring. Make sure the code to give the first TRB in a TD to the hardware manipulates the correct stream ring. When an endpoint stalls, store the stream ID of the stream ring that stalled in the xhci_virt_ep structure. Use that instead of the stream ID in the URB, since an URB may be re-used after it is given back after a non-control endpoint stall. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-03 06:34:43 +08:00
ep_ring = xhci_urb_to_transfer_ring(xhci, cur_td->urb);
if (!ep_ring) {
/* This shouldn't happen unless a driver is mucking
* with the stream ID after submission. This will
* leave the TD on the hardware ring, and the hardware
* will try to execute it, and may access a buffer
* that has already been freed. In the best case, the
* hardware will execute it, and the event handler will
* ignore the completion event for that TD, since it was
* removed from the td_list for that endpoint. In
* short, don't muck with the stream ID after
* submission.
*/
xhci_warn(xhci, "WARN Cancelled URB %p "
"has invalid stream ID %u.\n",
cur_td->urb,
cur_td->urb->stream_id);
goto remove_finished_td;
}
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
/*
* If we stopped on the TD we need to cancel, then we have to
* move the xHC endpoint ring dequeue pointer past this TD.
*/
hw_deq = xhci_get_hw_deq(xhci, vdev, ep_index,
cur_td->urb->stream_id);
hw_deq &= ~0xf;
if (trb_in_td(xhci, cur_td->start_seg, cur_td->first_trb,
cur_td->last_trb, hw_deq, false)) {
USB: xhci: Correct assumptions about number of rings per endpoint. Much of the xHCI driver code assumes that endpoints only have one ring. Now an endpoint can have one ring per enabled stream ID, so correct that assumption. Use functions that translate the stream_id field in the URB or the DMA address of a TRB into the correct stream ring. Correct the polling loop to print out all enabled stream rings. Make the URB cancellation routine find the correct stream ring if the URB has stream_id set. Make sure the URB enqueueing routine does the same. Also correct the code that handles stalled/halted endpoints. Check that commands and registers that can take stream IDs handle them properly. That includes ringing an endpoint doorbell, resetting a stalled/halted endpoint, and setting a transfer ring dequeue pointer (since that command can set the dequeue pointer in a stream context or an endpoint context). Correct the transfer event handler to translate a TRB DMA address into the stream ring it was enqueued to. Make the code to allocate and prepare TD structures adds the TD to the right td_list for the stream ring. Make sure the code to give the first TRB in a TD to the hardware manipulates the correct stream ring. When an endpoint stalls, store the stream ID of the stream ring that stalled in the xhci_virt_ep structure. Use that instead of the stream ID in the URB, since an URB may be re-used after it is given back after a non-control endpoint stall. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-03 06:34:43 +08:00
xhci_find_new_dequeue_state(xhci, slot_id, ep_index,
cur_td->urb->stream_id,
cur_td, &deq_state);
} else {
xhci: Fix failed enqueue in the middle of isoch TD. When an isochronous transfer is enqueued, xhci_queue_isoc_tx_prepare() will ensure that there is enough room on the transfer rings for all of the isochronous TDs for that URB. However, when xhci_queue_isoc_tx() is enqueueing individual isoc TDs, the prepare_transfer() function can fail if the endpoint state has changed to disabled, error, or some other unknown state. With the current code, if Nth TD (not the first TD) fails, the ring is left in a sorry state. The partially enqueued TDs are left on the ring, and the first TRB of the TD is not given back to the hardware. The enqueue pointer is left on the TRB after the last successfully enqueued TD. This means the ring is basically useless. Any new transfers will be enqueued after the failed TDs, which the hardware will never read because the cycle bit indicates it does not own them. The ring will fill up with untransferred TDs, and the endpoint will be basically unusable. The untransferred TDs will also remain on the TD list. Since the td_list is a FIFO, this basically means the ring handler will be waiting on TDs that will never be completed (or worse, dereference memory that doesn't exist any more). Change the code to clean up the isochronous ring after a failed transfer. If the first TD failed, simply return and allow the xhci_urb_enqueue function to free the urb_priv. If the Nth TD failed, first remove the TDs from the td_list. Then convert the TRBs that were enqueued into No-op TRBs. Make sure to flip the cycle bit on all enqueued TRBs (including any link TRBs in the middle or between TDs), but leave the cycle bit of the first TRB (which will show software-owned) intact. Then move the ring enqueue pointer back to the first TRB and make sure to change the xhci_ring's cycle state to what is appropriate for that ring segment. This ensures that the No-op TRBs will be overwritten by subsequent TDs, and the hardware will not start executing random TRBs because the cycle bit was left as hardware-owned. This bug is unlikely to be hit, but it was something I noticed while tracking down the watchdog timer issue. I verified that the fix works by injecting some errors on the 250th isochronous URB queued, although I could not verify that the ring is in the correct state because uvcvideo refused to talk to the device after the first usb_submit_urb() failed. Ring debugging shows that the ring looks correct, however. This patch should be backported to kernels as old as 2.6.36. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Cc: Andiry Xu <andiry.xu@amd.com> Cc: stable@kernel.org
2011-07-30 03:44:32 +08:00
td_to_noop(xhci, ep_ring, cur_td, false);
}
USB: xhci: Correct assumptions about number of rings per endpoint. Much of the xHCI driver code assumes that endpoints only have one ring. Now an endpoint can have one ring per enabled stream ID, so correct that assumption. Use functions that translate the stream_id field in the URB or the DMA address of a TRB into the correct stream ring. Correct the polling loop to print out all enabled stream rings. Make the URB cancellation routine find the correct stream ring if the URB has stream_id set. Make sure the URB enqueueing routine does the same. Also correct the code that handles stalled/halted endpoints. Check that commands and registers that can take stream IDs handle them properly. That includes ringing an endpoint doorbell, resetting a stalled/halted endpoint, and setting a transfer ring dequeue pointer (since that command can set the dequeue pointer in a stream context or an endpoint context). Correct the transfer event handler to translate a TRB DMA address into the stream ring it was enqueued to. Make the code to allocate and prepare TD structures adds the TD to the right td_list for the stream ring. Make sure the code to give the first TRB in a TD to the hardware manipulates the correct stream ring. When an endpoint stalls, store the stream ID of the stream ring that stalled in the xhci_virt_ep structure. Use that instead of the stream ID in the URB, since an URB may be re-used after it is given back after a non-control endpoint stall. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-03 06:34:43 +08:00
remove_finished_td:
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
/*
* The event handler won't see a completion for this TD anymore,
* so remove it from the endpoint ring's TD list. Keep it in
* the cancelled TD list for URB completion later.
*/
list_del_init(&cur_td->td_list);
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
}
USB: xhci: Add watchdog timer for URB cancellation. In order to giveback a canceled URB, we must ensure that the xHCI hardware will not access the buffer in an URB. We can't modify the buffer pointers on endpoint rings without issuing and waiting for a stop endpoint command. Since URBs can be canceled in interrupt context, we can't wait on that command. The old code trusted that the host controller would respond to the command, and would giveback the URBs in the event handler. If the hardware never responds to the stop endpoint command, the URBs will never be completed, and we might hang the USB subsystem. Implement a watchdog timer that is spawned whenever a stop endpoint command is queued. If a stop endpoint command event is found on the event ring during an interrupt, we need to stop the watchdog timer with del_timer(). Since del_timer() can fail if the timer is running and waiting on the xHCI lock, we need a way to signal to the timer that everything is fine and it should exit. If we simply clear EP_HALT_PENDING, a new stop endpoint command could sneak in and set it before the watchdog timer can grab the lock. Instead we use a combination of the EP_HALT_PENDING flag and a counter for the number of pending stop endpoint commands (xhci_virt_ep->stop_cmds_pending). If we need to cancel the watchdog timer and del_timer() succeeds, we decrement the number of pending stop endpoint commands. If del_timer() fails, we leave the number of pending stop endpoint commands alone. In either case, we clear the EP_HALT_PENDING flag. The timer will decrement the number of pending stop endpoint commands once it obtains the lock. If the timer is the tail end of the last stop endpoint command (xhci_virt_ep->stop_cmds_pending == 0), and the endpoint's command is still pending (EP_HALT_PENDING is set), we assume the host is dying. The watchdog timer will set XHCI_STATE_DYING, try to halt the xHCI host, and give back all pending URBs. Various other places in the driver need to check whether the xHCI host is dying. If the interrupt handler ever notices, it should immediately stop processing events. The URB enqueue function should also return -ESHUTDOWN. The URB dequeue function should simply return the value of usb_hcd_check_unlink_urb() and the watchdog timer will take care of giving the URB back. When a device is disconnected, the xHCI hardware structures should be freed without issuing a disable slot command (since the hardware probably won't respond to it anyway). The debugging polling loop should stop polling if the host is dying. When a device is disconnected, any pending watchdog timers are killed with del_timer_sync(). It must be synchronous so that the watchdog timer doesn't attempt to access the freed endpoint structures. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-10-28 01:57:01 +08:00
xhci_stop_watchdog_timer_in_irq(xhci, ep);
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
/* If necessary, queue a Set Transfer Ring Dequeue Pointer command */
if (deq_state.new_deq_ptr && deq_state.new_deq_seg) {
xhci_queue_new_dequeue_state(xhci, slot_id, ep_index,
&deq_state);
xhci_ring_cmd_db(xhci);
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
} else {
USB: xhci: Correct assumptions about number of rings per endpoint. Much of the xHCI driver code assumes that endpoints only have one ring. Now an endpoint can have one ring per enabled stream ID, so correct that assumption. Use functions that translate the stream_id field in the URB or the DMA address of a TRB into the correct stream ring. Correct the polling loop to print out all enabled stream rings. Make the URB cancellation routine find the correct stream ring if the URB has stream_id set. Make sure the URB enqueueing routine does the same. Also correct the code that handles stalled/halted endpoints. Check that commands and registers that can take stream IDs handle them properly. That includes ringing an endpoint doorbell, resetting a stalled/halted endpoint, and setting a transfer ring dequeue pointer (since that command can set the dequeue pointer in a stream context or an endpoint context). Correct the transfer event handler to translate a TRB DMA address into the stream ring it was enqueued to. Make the code to allocate and prepare TD structures adds the TD to the right td_list for the stream ring. Make sure the code to give the first TRB in a TD to the hardware manipulates the correct stream ring. When an endpoint stalls, store the stream ID of the stream ring that stalled in the xhci_virt_ep structure. Use that instead of the stream ID in the URB, since an URB may be re-used after it is given back after a non-control endpoint stall. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-03 06:34:43 +08:00
/* Otherwise ring the doorbell(s) to restart queued transfers */
ring_doorbell_for_active_rings(xhci, slot_id, ep_index);
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
}
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
/*
* Drop the lock and complete the URBs in the cancelled TD list.
* New TDs to be cancelled might be added to the end of the list before
* we can complete all the URBs for the TDs we already unlinked.
* So stop when we've completed the URB for the last TD we unlinked.
*/
do {
cur_td = list_first_entry(&ep->cancelled_td_list,
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
struct xhci_td, cancelled_td_list);
list_del_init(&cur_td->cancelled_td_list);
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
/* Clean up the cancelled URB */
/* Doesn't matter what we pass for status, since the core will
* just overwrite it (because the URB has been unlinked).
*/
ep_ring = xhci_urb_to_transfer_ring(xhci, cur_td->urb);
xhci_unmap_td_bounce_buffer(xhci, ep_ring, cur_td);
inc_td_cnt(cur_td->urb);
if (last_td_in_urb(cur_td))
xhci_giveback_urb_in_irq(xhci, cur_td, 0);
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
USB: xhci: Add watchdog timer for URB cancellation. In order to giveback a canceled URB, we must ensure that the xHCI hardware will not access the buffer in an URB. We can't modify the buffer pointers on endpoint rings without issuing and waiting for a stop endpoint command. Since URBs can be canceled in interrupt context, we can't wait on that command. The old code trusted that the host controller would respond to the command, and would giveback the URBs in the event handler. If the hardware never responds to the stop endpoint command, the URBs will never be completed, and we might hang the USB subsystem. Implement a watchdog timer that is spawned whenever a stop endpoint command is queued. If a stop endpoint command event is found on the event ring during an interrupt, we need to stop the watchdog timer with del_timer(). Since del_timer() can fail if the timer is running and waiting on the xHCI lock, we need a way to signal to the timer that everything is fine and it should exit. If we simply clear EP_HALT_PENDING, a new stop endpoint command could sneak in and set it before the watchdog timer can grab the lock. Instead we use a combination of the EP_HALT_PENDING flag and a counter for the number of pending stop endpoint commands (xhci_virt_ep->stop_cmds_pending). If we need to cancel the watchdog timer and del_timer() succeeds, we decrement the number of pending stop endpoint commands. If del_timer() fails, we leave the number of pending stop endpoint commands alone. In either case, we clear the EP_HALT_PENDING flag. The timer will decrement the number of pending stop endpoint commands once it obtains the lock. If the timer is the tail end of the last stop endpoint command (xhci_virt_ep->stop_cmds_pending == 0), and the endpoint's command is still pending (EP_HALT_PENDING is set), we assume the host is dying. The watchdog timer will set XHCI_STATE_DYING, try to halt the xHCI host, and give back all pending URBs. Various other places in the driver need to check whether the xHCI host is dying. If the interrupt handler ever notices, it should immediately stop processing events. The URB enqueue function should also return -ESHUTDOWN. The URB dequeue function should simply return the value of usb_hcd_check_unlink_urb() and the watchdog timer will take care of giving the URB back. When a device is disconnected, the xHCI hardware structures should be freed without issuing a disable slot command (since the hardware probably won't respond to it anyway). The debugging polling loop should stop polling if the host is dying. When a device is disconnected, any pending watchdog timers are killed with del_timer_sync(). It must be synchronous so that the watchdog timer doesn't attempt to access the freed endpoint structures. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-10-28 01:57:01 +08:00
/* Stop processing the cancelled list if the watchdog timer is
* running.
*/
if (xhci->xhc_state & XHCI_STATE_DYING)
return;
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
} while (cur_td != last_unlinked_td);
/* Return to the event handler with xhci->lock re-acquired */
}
static void xhci_kill_ring_urbs(struct xhci_hcd *xhci, struct xhci_ring *ring)
{
struct xhci_td *cur_td;
struct xhci_td *tmp;
list_for_each_entry_safe(cur_td, tmp, &ring->td_list, td_list) {
list_del_init(&cur_td->td_list);
if (!list_empty(&cur_td->cancelled_td_list))
list_del_init(&cur_td->cancelled_td_list);
xhci_unmap_td_bounce_buffer(xhci, ring, cur_td);
inc_td_cnt(cur_td->urb);
if (last_td_in_urb(cur_td))
xhci_giveback_urb_in_irq(xhci, cur_td, -ESHUTDOWN);
}
}
static void xhci_kill_endpoint_urbs(struct xhci_hcd *xhci,
int slot_id, int ep_index)
{
struct xhci_td *cur_td;
struct xhci_td *tmp;
struct xhci_virt_ep *ep;
struct xhci_ring *ring;
ep = &xhci->devs[slot_id]->eps[ep_index];
if ((ep->ep_state & EP_HAS_STREAMS) ||
(ep->ep_state & EP_GETTING_NO_STREAMS)) {
int stream_id;
for (stream_id = 1; stream_id < ep->stream_info->num_streams;
stream_id++) {
ring = ep->stream_info->stream_rings[stream_id];
if (!ring)
continue;
xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
"Killing URBs for slot ID %u, ep index %u, stream %u",
slot_id, ep_index, stream_id);
xhci_kill_ring_urbs(xhci, ring);
}
} else {
ring = ep->ring;
if (!ring)
return;
xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
"Killing URBs for slot ID %u, ep index %u",
slot_id, ep_index);
xhci_kill_ring_urbs(xhci, ring);
}
list_for_each_entry_safe(cur_td, tmp, &ep->cancelled_td_list,
cancelled_td_list) {
list_del_init(&cur_td->cancelled_td_list);
inc_td_cnt(cur_td->urb);
if (last_td_in_urb(cur_td))
xhci_giveback_urb_in_irq(xhci, cur_td, -ESHUTDOWN);
}
}
/*
* host controller died, register read returns 0xffffffff
* Complete pending commands, mark them ABORTED.
* URBs need to be given back as usb core might be waiting with device locks
* held for the URBs to finish during device disconnect, blocking host remove.
*
* Call with xhci->lock held.
* lock is relased and re-acquired while giving back urb.
*/
void xhci_hc_died(struct xhci_hcd *xhci)
{
int i, j;
if (xhci->xhc_state & XHCI_STATE_DYING)
return;
xhci_err(xhci, "xHCI host controller not responding, assume dead\n");
xhci->xhc_state |= XHCI_STATE_DYING;
xhci_cleanup_command_queue(xhci);
/* return any pending urbs, remove may be waiting for them */
for (i = 0; i <= HCS_MAX_SLOTS(xhci->hcs_params1); i++) {
if (!xhci->devs[i])
continue;
for (j = 0; j < 31; j++)
xhci_kill_endpoint_urbs(xhci, i, j);
}
/* inform usb core hc died if PCI remove isn't already handling it */
if (!(xhci->xhc_state & XHCI_STATE_REMOVING))
usb_hc_died(xhci_to_hcd(xhci));
}
USB: xhci: Add watchdog timer for URB cancellation. In order to giveback a canceled URB, we must ensure that the xHCI hardware will not access the buffer in an URB. We can't modify the buffer pointers on endpoint rings without issuing and waiting for a stop endpoint command. Since URBs can be canceled in interrupt context, we can't wait on that command. The old code trusted that the host controller would respond to the command, and would giveback the URBs in the event handler. If the hardware never responds to the stop endpoint command, the URBs will never be completed, and we might hang the USB subsystem. Implement a watchdog timer that is spawned whenever a stop endpoint command is queued. If a stop endpoint command event is found on the event ring during an interrupt, we need to stop the watchdog timer with del_timer(). Since del_timer() can fail if the timer is running and waiting on the xHCI lock, we need a way to signal to the timer that everything is fine and it should exit. If we simply clear EP_HALT_PENDING, a new stop endpoint command could sneak in and set it before the watchdog timer can grab the lock. Instead we use a combination of the EP_HALT_PENDING flag and a counter for the number of pending stop endpoint commands (xhci_virt_ep->stop_cmds_pending). If we need to cancel the watchdog timer and del_timer() succeeds, we decrement the number of pending stop endpoint commands. If del_timer() fails, we leave the number of pending stop endpoint commands alone. In either case, we clear the EP_HALT_PENDING flag. The timer will decrement the number of pending stop endpoint commands once it obtains the lock. If the timer is the tail end of the last stop endpoint command (xhci_virt_ep->stop_cmds_pending == 0), and the endpoint's command is still pending (EP_HALT_PENDING is set), we assume the host is dying. The watchdog timer will set XHCI_STATE_DYING, try to halt the xHCI host, and give back all pending URBs. Various other places in the driver need to check whether the xHCI host is dying. If the interrupt handler ever notices, it should immediately stop processing events. The URB enqueue function should also return -ESHUTDOWN. The URB dequeue function should simply return the value of usb_hcd_check_unlink_urb() and the watchdog timer will take care of giving the URB back. When a device is disconnected, the xHCI hardware structures should be freed without issuing a disable slot command (since the hardware probably won't respond to it anyway). The debugging polling loop should stop polling if the host is dying. When a device is disconnected, any pending watchdog timers are killed with del_timer_sync(). It must be synchronous so that the watchdog timer doesn't attempt to access the freed endpoint structures. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-10-28 01:57:01 +08:00
/* Watchdog timer function for when a stop endpoint command fails to complete.
* In this case, we assume the host controller is broken or dying or dead. The
* host may still be completing some other events, so we have to be careful to
* let the event ring handler and the URB dequeueing/enqueueing functions know
* through xhci->state.
*
* The timer may also fire if the host takes a very long time to respond to the
* command, and the stop endpoint command completion handler cannot delete the
* timer before the timer function is called. Another endpoint cancellation may
* sneak in before the timer function can grab the lock, and that may queue
* another stop endpoint command and add the timer back. So we cannot use a
* simple flag to say whether there is a pending stop endpoint command for a
* particular endpoint.
*
* Instead we use a combination of that flag and checking if a new timer is
* pending.
USB: xhci: Add watchdog timer for URB cancellation. In order to giveback a canceled URB, we must ensure that the xHCI hardware will not access the buffer in an URB. We can't modify the buffer pointers on endpoint rings without issuing and waiting for a stop endpoint command. Since URBs can be canceled in interrupt context, we can't wait on that command. The old code trusted that the host controller would respond to the command, and would giveback the URBs in the event handler. If the hardware never responds to the stop endpoint command, the URBs will never be completed, and we might hang the USB subsystem. Implement a watchdog timer that is spawned whenever a stop endpoint command is queued. If a stop endpoint command event is found on the event ring during an interrupt, we need to stop the watchdog timer with del_timer(). Since del_timer() can fail if the timer is running and waiting on the xHCI lock, we need a way to signal to the timer that everything is fine and it should exit. If we simply clear EP_HALT_PENDING, a new stop endpoint command could sneak in and set it before the watchdog timer can grab the lock. Instead we use a combination of the EP_HALT_PENDING flag and a counter for the number of pending stop endpoint commands (xhci_virt_ep->stop_cmds_pending). If we need to cancel the watchdog timer and del_timer() succeeds, we decrement the number of pending stop endpoint commands. If del_timer() fails, we leave the number of pending stop endpoint commands alone. In either case, we clear the EP_HALT_PENDING flag. The timer will decrement the number of pending stop endpoint commands once it obtains the lock. If the timer is the tail end of the last stop endpoint command (xhci_virt_ep->stop_cmds_pending == 0), and the endpoint's command is still pending (EP_HALT_PENDING is set), we assume the host is dying. The watchdog timer will set XHCI_STATE_DYING, try to halt the xHCI host, and give back all pending URBs. Various other places in the driver need to check whether the xHCI host is dying. If the interrupt handler ever notices, it should immediately stop processing events. The URB enqueue function should also return -ESHUTDOWN. The URB dequeue function should simply return the value of usb_hcd_check_unlink_urb() and the watchdog timer will take care of giving the URB back. When a device is disconnected, the xHCI hardware structures should be freed without issuing a disable slot command (since the hardware probably won't respond to it anyway). The debugging polling loop should stop polling if the host is dying. When a device is disconnected, any pending watchdog timers are killed with del_timer_sync(). It must be synchronous so that the watchdog timer doesn't attempt to access the freed endpoint structures. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-10-28 01:57:01 +08:00
*/
void xhci_stop_endpoint_command_watchdog(struct timer_list *t)
USB: xhci: Add watchdog timer for URB cancellation. In order to giveback a canceled URB, we must ensure that the xHCI hardware will not access the buffer in an URB. We can't modify the buffer pointers on endpoint rings without issuing and waiting for a stop endpoint command. Since URBs can be canceled in interrupt context, we can't wait on that command. The old code trusted that the host controller would respond to the command, and would giveback the URBs in the event handler. If the hardware never responds to the stop endpoint command, the URBs will never be completed, and we might hang the USB subsystem. Implement a watchdog timer that is spawned whenever a stop endpoint command is queued. If a stop endpoint command event is found on the event ring during an interrupt, we need to stop the watchdog timer with del_timer(). Since del_timer() can fail if the timer is running and waiting on the xHCI lock, we need a way to signal to the timer that everything is fine and it should exit. If we simply clear EP_HALT_PENDING, a new stop endpoint command could sneak in and set it before the watchdog timer can grab the lock. Instead we use a combination of the EP_HALT_PENDING flag and a counter for the number of pending stop endpoint commands (xhci_virt_ep->stop_cmds_pending). If we need to cancel the watchdog timer and del_timer() succeeds, we decrement the number of pending stop endpoint commands. If del_timer() fails, we leave the number of pending stop endpoint commands alone. In either case, we clear the EP_HALT_PENDING flag. The timer will decrement the number of pending stop endpoint commands once it obtains the lock. If the timer is the tail end of the last stop endpoint command (xhci_virt_ep->stop_cmds_pending == 0), and the endpoint's command is still pending (EP_HALT_PENDING is set), we assume the host is dying. The watchdog timer will set XHCI_STATE_DYING, try to halt the xHCI host, and give back all pending URBs. Various other places in the driver need to check whether the xHCI host is dying. If the interrupt handler ever notices, it should immediately stop processing events. The URB enqueue function should also return -ESHUTDOWN. The URB dequeue function should simply return the value of usb_hcd_check_unlink_urb() and the watchdog timer will take care of giving the URB back. When a device is disconnected, the xHCI hardware structures should be freed without issuing a disable slot command (since the hardware probably won't respond to it anyway). The debugging polling loop should stop polling if the host is dying. When a device is disconnected, any pending watchdog timers are killed with del_timer_sync(). It must be synchronous so that the watchdog timer doesn't attempt to access the freed endpoint structures. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-10-28 01:57:01 +08:00
{
struct xhci_virt_ep *ep = from_timer(ep, t, stop_cmd_timer);
struct xhci_hcd *xhci = ep->xhci;
usb, xhci: fix lockdep warning on endpoint timeout While debugging a usb3 problem, I stumbled upon this lockdep warning. Oct 18 21:41:17 dhcp47-74 kernel: ================================= Oct 18 21:41:17 dhcp47-74 kernel: [ INFO: inconsistent lock state ] Oct 18 21:41:17 dhcp47-74 kernel: 3.1.0-rc4nmi+ #456 Oct 18 21:41:17 dhcp47-74 kernel: --------------------------------- Oct 18 21:41:17 dhcp47-74 kernel: inconsistent {IN-HARDIRQ-W} -> {HARDIRQ-ON-W} usage. Oct 18 21:41:17 dhcp47-74 kernel: swapper/0 [HC0[0]:SC1[1]:HE1:SE0] takes: Oct 18 21:41:17 dhcp47-74 kernel: (&(&xhci->lock)->rlock){?.-...}, at: [<ffffffffa0228990>] xhci_stop_endpoint_command_watchdog+0x30/0x340 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: {IN-HARDIRQ-W} state was registered at: Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8109a941>] __lock_acquire+0x781/0x1660 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8109bed7>] lock_acquire+0x97/0x170 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81501b46>] _raw_spin_lock+0x46/0x80 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa02299fa>] xhci_irq+0x3a/0x1960 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa022b351>] xhci_msi_irq+0x31/0x40 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810d2305>] handle_irq_event_percpu+0x85/0x320 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810d25e8>] handle_irq_event+0x48/0x70 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810d537d>] handle_edge_irq+0x6d/0x130 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810048c9>] handle_irq+0x49/0xa0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8150d56d>] do_IRQ+0x5d/0xe0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff815029b0>] ret_from_intr+0x0/0x13 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81388aca>] usb_set_device_state+0x8a/0x180 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8138f038>] usb_add_hcd+0x2b8/0x730 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa022ed7e>] xhci_pci_probe+0x9e/0xd4 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8127915f>] local_pci_probe+0x5f/0xd0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8127a569>] pci_device_probe+0x119/0x120 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81334473>] driver_probe_device+0xa3/0x2c0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8133473b>] __driver_attach+0xab/0xb0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8133373c>] bus_for_each_dev+0x6c/0xa0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff813341fe>] driver_attach+0x1e/0x20 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81333b88>] bus_add_driver+0x1f8/0x2b0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81334df6>] driver_register+0x76/0x140 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8127a7c6>] __pci_register_driver+0x66/0xe0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa013c04a>] snd_timer_find+0x4a/0x70 [snd_timer] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa013c00e>] snd_timer_find+0xe/0x70 [snd_timer] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810001d3>] do_one_initcall+0x43/0x180 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810a9ed2>] sys_init_module+0x92/0x1f0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8150ab6b>] system_call_fastpath+0x16/0x1b Oct 18 21:41:17 dhcp47-74 kernel: irq event stamp: 631984 Oct 18 21:41:17 dhcp47-74 kernel: hardirqs last enabled at (631984): [<ffffffff81502720>] _raw_spin_unlock_irq+0x30/0x50 Oct 18 21:41:17 dhcp47-74 kernel: hardirqs last disabled at (631983): [<ffffffff81501c49>] _raw_spin_lock_irq+0x19/0x90 Oct 18 21:41:17 dhcp47-74 kernel: softirqs last enabled at (631980): [<ffffffff8105ff63>] _local_bh_enable+0x13/0x20 Oct 18 21:41:17 dhcp47-74 kernel: softirqs last disabled at (631981): [<ffffffff8150ce6c>] call_softirq+0x1c/0x30 Oct 18 21:41:17 dhcp47-74 kernel: Oct 18 21:41:17 dhcp47-74 kernel: other info that might help us debug this: Oct 18 21:41:17 dhcp47-74 kernel: Possible unsafe locking scenario: Oct 18 21:41:17 dhcp47-74 kernel: Oct 18 21:41:17 dhcp47-74 kernel: CPU0 Oct 18 21:41:17 dhcp47-74 kernel: ---- Oct 18 21:41:17 dhcp47-74 kernel: lock(&(&xhci->lock)->rlock); Oct 18 21:41:17 dhcp47-74 kernel: <Interrupt> Oct 18 21:41:17 dhcp47-74 kernel: lock(&(&xhci->lock)->rlock); Oct 18 21:41:17 dhcp47-74 kernel: Oct 18 21:41:17 dhcp47-74 kernel: *** DEADLOCK *** Oct 18 21:41:17 dhcp47-74 kernel: Oct 18 21:41:17 dhcp47-74 kernel: 1 lock held by swapper/0: Oct 18 21:41:17 dhcp47-74 kernel: #0: (&ep->stop_cmd_timer){+.-...}, at: [<ffffffff8106abf2>] run_timer_softirq+0x162/0x570 Oct 18 21:41:17 dhcp47-74 kernel: Oct 18 21:41:17 dhcp47-74 kernel: stack backtrace: Oct 18 21:41:17 dhcp47-74 kernel: Pid: 0, comm: swapper Tainted: G W 3.1.0-rc4nmi+ #456 Oct 18 21:41:17 dhcp47-74 kernel: Call Trace: Oct 18 21:41:17 dhcp47-74 kernel: <IRQ> [<ffffffff81098ed7>] print_usage_bug+0x227/0x270 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810999c6>] mark_lock+0x346/0x410 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8109a7de>] __lock_acquire+0x61e/0x1660 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81099893>] ? mark_lock+0x213/0x410 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8109bed7>] lock_acquire+0x97/0x170 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa0228990>] ? xhci_stop_endpoint_command_watchdog+0x30/0x340 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81501b46>] _raw_spin_lock+0x46/0x80 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa0228990>] ? xhci_stop_endpoint_command_watchdog+0x30/0x340 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa0228990>] xhci_stop_endpoint_command_watchdog+0x30/0x340 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8106abf2>] ? run_timer_softirq+0x162/0x570 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8106ac9d>] run_timer_softirq+0x20d/0x570 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8106abf2>] ? run_timer_softirq+0x162/0x570 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa0228960>] ? xhci_queue_isoc_tx_prepare+0x8e0/0x8e0 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810604d2>] __do_softirq+0xf2/0x3f0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81020edd>] ? lapic_next_event+0x1d/0x30 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81090d4e>] ? clockevents_program_event+0x5e/0x90 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8150ce6c>] call_softirq+0x1c/0x30 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8100484d>] do_softirq+0x8d/0xc0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8105ff35>] irq_exit+0xe5/0x100 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8150d65e>] smp_apic_timer_interrupt+0x6e/0x99 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8150b6f0>] apic_timer_interrupt+0x70/0x80 Oct 18 21:41:17 dhcp47-74 kernel: <EOI> [<ffffffff81095d8d>] ? trace_hardirqs_off+0xd/0x10 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff812ddb76>] ? acpi_idle_enter_bm+0x227/0x25b Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff812ddb71>] ? acpi_idle_enter_bm+0x222/0x25b Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff813eda63>] cpuidle_idle_call+0x103/0x290 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81002155>] cpu_idle+0xe5/0x160 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff814e7f50>] rest_init+0xe0/0xf0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff814e7e70>] ? csum_partial_copy_generic+0x170/0x170 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81df8e23>] start_kernel+0x3fc/0x407 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81df8321>] x86_64_start_reservations+0x131/0x135 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81df8412>] x86_64_start_kernel+0xed/0xf4 Oct 18 21:41:17 dhcp47-74 kernel: xhci_hcd 0000:00:14.0: xHCI host not responding to stop endpoint command. Oct 18 21:41:17 dhcp47-74 kernel: xhci_hcd 0000:00:14.0: Assuming host is dying, halting host. Oct 18 21:41:17 dhcp47-74 kernel: xhci_hcd 0000:00:14.0: HC died; cleaning up Oct 18 21:41:17 dhcp47-74 kernel: usb 3-4: device descriptor read/8, error -110 Oct 18 21:41:17 dhcp47-74 kernel: usb 3-4: device descriptor read/8, error -22 Oct 18 21:41:17 dhcp47-74 kernel: hub 3-0:1.0: cannot disable port 4 (err = -19) Basically what is happening is in xhci_stop_endpoint_command_watchdog() the xhci->lock is grabbed with just spin_lock. What lockdep deduces is that if an interrupt occurred while in this function it would deadlock with xhci_irq because that function also grabs the xhci->lock. Fixing it is trivial by using spin_lock_irqsave instead. This should be queued to stable kernels as far back as 2.6.33. Signed-off-by: Don Zickus <dzickus@redhat.com> Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Cc: stable@kernel.org
2011-10-21 11:52:14 +08:00
unsigned long flags;
u32 usbsts;
USB: xhci: Add watchdog timer for URB cancellation. In order to giveback a canceled URB, we must ensure that the xHCI hardware will not access the buffer in an URB. We can't modify the buffer pointers on endpoint rings without issuing and waiting for a stop endpoint command. Since URBs can be canceled in interrupt context, we can't wait on that command. The old code trusted that the host controller would respond to the command, and would giveback the URBs in the event handler. If the hardware never responds to the stop endpoint command, the URBs will never be completed, and we might hang the USB subsystem. Implement a watchdog timer that is spawned whenever a stop endpoint command is queued. If a stop endpoint command event is found on the event ring during an interrupt, we need to stop the watchdog timer with del_timer(). Since del_timer() can fail if the timer is running and waiting on the xHCI lock, we need a way to signal to the timer that everything is fine and it should exit. If we simply clear EP_HALT_PENDING, a new stop endpoint command could sneak in and set it before the watchdog timer can grab the lock. Instead we use a combination of the EP_HALT_PENDING flag and a counter for the number of pending stop endpoint commands (xhci_virt_ep->stop_cmds_pending). If we need to cancel the watchdog timer and del_timer() succeeds, we decrement the number of pending stop endpoint commands. If del_timer() fails, we leave the number of pending stop endpoint commands alone. In either case, we clear the EP_HALT_PENDING flag. The timer will decrement the number of pending stop endpoint commands once it obtains the lock. If the timer is the tail end of the last stop endpoint command (xhci_virt_ep->stop_cmds_pending == 0), and the endpoint's command is still pending (EP_HALT_PENDING is set), we assume the host is dying. The watchdog timer will set XHCI_STATE_DYING, try to halt the xHCI host, and give back all pending URBs. Various other places in the driver need to check whether the xHCI host is dying. If the interrupt handler ever notices, it should immediately stop processing events. The URB enqueue function should also return -ESHUTDOWN. The URB dequeue function should simply return the value of usb_hcd_check_unlink_urb() and the watchdog timer will take care of giving the URB back. When a device is disconnected, the xHCI hardware structures should be freed without issuing a disable slot command (since the hardware probably won't respond to it anyway). The debugging polling loop should stop polling if the host is dying. When a device is disconnected, any pending watchdog timers are killed with del_timer_sync(). It must be synchronous so that the watchdog timer doesn't attempt to access the freed endpoint structures. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-10-28 01:57:01 +08:00
usb, xhci: fix lockdep warning on endpoint timeout While debugging a usb3 problem, I stumbled upon this lockdep warning. Oct 18 21:41:17 dhcp47-74 kernel: ================================= Oct 18 21:41:17 dhcp47-74 kernel: [ INFO: inconsistent lock state ] Oct 18 21:41:17 dhcp47-74 kernel: 3.1.0-rc4nmi+ #456 Oct 18 21:41:17 dhcp47-74 kernel: --------------------------------- Oct 18 21:41:17 dhcp47-74 kernel: inconsistent {IN-HARDIRQ-W} -> {HARDIRQ-ON-W} usage. Oct 18 21:41:17 dhcp47-74 kernel: swapper/0 [HC0[0]:SC1[1]:HE1:SE0] takes: Oct 18 21:41:17 dhcp47-74 kernel: (&(&xhci->lock)->rlock){?.-...}, at: [<ffffffffa0228990>] xhci_stop_endpoint_command_watchdog+0x30/0x340 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: {IN-HARDIRQ-W} state was registered at: Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8109a941>] __lock_acquire+0x781/0x1660 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8109bed7>] lock_acquire+0x97/0x170 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81501b46>] _raw_spin_lock+0x46/0x80 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa02299fa>] xhci_irq+0x3a/0x1960 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa022b351>] xhci_msi_irq+0x31/0x40 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810d2305>] handle_irq_event_percpu+0x85/0x320 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810d25e8>] handle_irq_event+0x48/0x70 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810d537d>] handle_edge_irq+0x6d/0x130 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810048c9>] handle_irq+0x49/0xa0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8150d56d>] do_IRQ+0x5d/0xe0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff815029b0>] ret_from_intr+0x0/0x13 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81388aca>] usb_set_device_state+0x8a/0x180 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8138f038>] usb_add_hcd+0x2b8/0x730 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa022ed7e>] xhci_pci_probe+0x9e/0xd4 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8127915f>] local_pci_probe+0x5f/0xd0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8127a569>] pci_device_probe+0x119/0x120 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81334473>] driver_probe_device+0xa3/0x2c0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8133473b>] __driver_attach+0xab/0xb0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8133373c>] bus_for_each_dev+0x6c/0xa0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff813341fe>] driver_attach+0x1e/0x20 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81333b88>] bus_add_driver+0x1f8/0x2b0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81334df6>] driver_register+0x76/0x140 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8127a7c6>] __pci_register_driver+0x66/0xe0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa013c04a>] snd_timer_find+0x4a/0x70 [snd_timer] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa013c00e>] snd_timer_find+0xe/0x70 [snd_timer] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810001d3>] do_one_initcall+0x43/0x180 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810a9ed2>] sys_init_module+0x92/0x1f0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8150ab6b>] system_call_fastpath+0x16/0x1b Oct 18 21:41:17 dhcp47-74 kernel: irq event stamp: 631984 Oct 18 21:41:17 dhcp47-74 kernel: hardirqs last enabled at (631984): [<ffffffff81502720>] _raw_spin_unlock_irq+0x30/0x50 Oct 18 21:41:17 dhcp47-74 kernel: hardirqs last disabled at (631983): [<ffffffff81501c49>] _raw_spin_lock_irq+0x19/0x90 Oct 18 21:41:17 dhcp47-74 kernel: softirqs last enabled at (631980): [<ffffffff8105ff63>] _local_bh_enable+0x13/0x20 Oct 18 21:41:17 dhcp47-74 kernel: softirqs last disabled at (631981): [<ffffffff8150ce6c>] call_softirq+0x1c/0x30 Oct 18 21:41:17 dhcp47-74 kernel: Oct 18 21:41:17 dhcp47-74 kernel: other info that might help us debug this: Oct 18 21:41:17 dhcp47-74 kernel: Possible unsafe locking scenario: Oct 18 21:41:17 dhcp47-74 kernel: Oct 18 21:41:17 dhcp47-74 kernel: CPU0 Oct 18 21:41:17 dhcp47-74 kernel: ---- Oct 18 21:41:17 dhcp47-74 kernel: lock(&(&xhci->lock)->rlock); Oct 18 21:41:17 dhcp47-74 kernel: <Interrupt> Oct 18 21:41:17 dhcp47-74 kernel: lock(&(&xhci->lock)->rlock); Oct 18 21:41:17 dhcp47-74 kernel: Oct 18 21:41:17 dhcp47-74 kernel: *** DEADLOCK *** Oct 18 21:41:17 dhcp47-74 kernel: Oct 18 21:41:17 dhcp47-74 kernel: 1 lock held by swapper/0: Oct 18 21:41:17 dhcp47-74 kernel: #0: (&ep->stop_cmd_timer){+.-...}, at: [<ffffffff8106abf2>] run_timer_softirq+0x162/0x570 Oct 18 21:41:17 dhcp47-74 kernel: Oct 18 21:41:17 dhcp47-74 kernel: stack backtrace: Oct 18 21:41:17 dhcp47-74 kernel: Pid: 0, comm: swapper Tainted: G W 3.1.0-rc4nmi+ #456 Oct 18 21:41:17 dhcp47-74 kernel: Call Trace: Oct 18 21:41:17 dhcp47-74 kernel: <IRQ> [<ffffffff81098ed7>] print_usage_bug+0x227/0x270 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810999c6>] mark_lock+0x346/0x410 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8109a7de>] __lock_acquire+0x61e/0x1660 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81099893>] ? mark_lock+0x213/0x410 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8109bed7>] lock_acquire+0x97/0x170 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa0228990>] ? xhci_stop_endpoint_command_watchdog+0x30/0x340 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81501b46>] _raw_spin_lock+0x46/0x80 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa0228990>] ? xhci_stop_endpoint_command_watchdog+0x30/0x340 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa0228990>] xhci_stop_endpoint_command_watchdog+0x30/0x340 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8106abf2>] ? run_timer_softirq+0x162/0x570 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8106ac9d>] run_timer_softirq+0x20d/0x570 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8106abf2>] ? run_timer_softirq+0x162/0x570 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa0228960>] ? xhci_queue_isoc_tx_prepare+0x8e0/0x8e0 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810604d2>] __do_softirq+0xf2/0x3f0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81020edd>] ? lapic_next_event+0x1d/0x30 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81090d4e>] ? clockevents_program_event+0x5e/0x90 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8150ce6c>] call_softirq+0x1c/0x30 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8100484d>] do_softirq+0x8d/0xc0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8105ff35>] irq_exit+0xe5/0x100 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8150d65e>] smp_apic_timer_interrupt+0x6e/0x99 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8150b6f0>] apic_timer_interrupt+0x70/0x80 Oct 18 21:41:17 dhcp47-74 kernel: <EOI> [<ffffffff81095d8d>] ? trace_hardirqs_off+0xd/0x10 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff812ddb76>] ? acpi_idle_enter_bm+0x227/0x25b Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff812ddb71>] ? acpi_idle_enter_bm+0x222/0x25b Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff813eda63>] cpuidle_idle_call+0x103/0x290 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81002155>] cpu_idle+0xe5/0x160 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff814e7f50>] rest_init+0xe0/0xf0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff814e7e70>] ? csum_partial_copy_generic+0x170/0x170 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81df8e23>] start_kernel+0x3fc/0x407 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81df8321>] x86_64_start_reservations+0x131/0x135 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81df8412>] x86_64_start_kernel+0xed/0xf4 Oct 18 21:41:17 dhcp47-74 kernel: xhci_hcd 0000:00:14.0: xHCI host not responding to stop endpoint command. Oct 18 21:41:17 dhcp47-74 kernel: xhci_hcd 0000:00:14.0: Assuming host is dying, halting host. Oct 18 21:41:17 dhcp47-74 kernel: xhci_hcd 0000:00:14.0: HC died; cleaning up Oct 18 21:41:17 dhcp47-74 kernel: usb 3-4: device descriptor read/8, error -110 Oct 18 21:41:17 dhcp47-74 kernel: usb 3-4: device descriptor read/8, error -22 Oct 18 21:41:17 dhcp47-74 kernel: hub 3-0:1.0: cannot disable port 4 (err = -19) Basically what is happening is in xhci_stop_endpoint_command_watchdog() the xhci->lock is grabbed with just spin_lock. What lockdep deduces is that if an interrupt occurred while in this function it would deadlock with xhci_irq because that function also grabs the xhci->lock. Fixing it is trivial by using spin_lock_irqsave instead. This should be queued to stable kernels as far back as 2.6.33. Signed-off-by: Don Zickus <dzickus@redhat.com> Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Cc: stable@kernel.org
2011-10-21 11:52:14 +08:00
spin_lock_irqsave(&xhci->lock, flags);
USB: xhci: Add watchdog timer for URB cancellation. In order to giveback a canceled URB, we must ensure that the xHCI hardware will not access the buffer in an URB. We can't modify the buffer pointers on endpoint rings without issuing and waiting for a stop endpoint command. Since URBs can be canceled in interrupt context, we can't wait on that command. The old code trusted that the host controller would respond to the command, and would giveback the URBs in the event handler. If the hardware never responds to the stop endpoint command, the URBs will never be completed, and we might hang the USB subsystem. Implement a watchdog timer that is spawned whenever a stop endpoint command is queued. If a stop endpoint command event is found on the event ring during an interrupt, we need to stop the watchdog timer with del_timer(). Since del_timer() can fail if the timer is running and waiting on the xHCI lock, we need a way to signal to the timer that everything is fine and it should exit. If we simply clear EP_HALT_PENDING, a new stop endpoint command could sneak in and set it before the watchdog timer can grab the lock. Instead we use a combination of the EP_HALT_PENDING flag and a counter for the number of pending stop endpoint commands (xhci_virt_ep->stop_cmds_pending). If we need to cancel the watchdog timer and del_timer() succeeds, we decrement the number of pending stop endpoint commands. If del_timer() fails, we leave the number of pending stop endpoint commands alone. In either case, we clear the EP_HALT_PENDING flag. The timer will decrement the number of pending stop endpoint commands once it obtains the lock. If the timer is the tail end of the last stop endpoint command (xhci_virt_ep->stop_cmds_pending == 0), and the endpoint's command is still pending (EP_HALT_PENDING is set), we assume the host is dying. The watchdog timer will set XHCI_STATE_DYING, try to halt the xHCI host, and give back all pending URBs. Various other places in the driver need to check whether the xHCI host is dying. If the interrupt handler ever notices, it should immediately stop processing events. The URB enqueue function should also return -ESHUTDOWN. The URB dequeue function should simply return the value of usb_hcd_check_unlink_urb() and the watchdog timer will take care of giving the URB back. When a device is disconnected, the xHCI hardware structures should be freed without issuing a disable slot command (since the hardware probably won't respond to it anyway). The debugging polling loop should stop polling if the host is dying. When a device is disconnected, any pending watchdog timers are killed with del_timer_sync(). It must be synchronous so that the watchdog timer doesn't attempt to access the freed endpoint structures. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-10-28 01:57:01 +08:00
/* bail out if cmd completed but raced with stop ep watchdog timer.*/
if (!(ep->ep_state & EP_STOP_CMD_PENDING) ||
timer_pending(&ep->stop_cmd_timer)) {
usb, xhci: fix lockdep warning on endpoint timeout While debugging a usb3 problem, I stumbled upon this lockdep warning. Oct 18 21:41:17 dhcp47-74 kernel: ================================= Oct 18 21:41:17 dhcp47-74 kernel: [ INFO: inconsistent lock state ] Oct 18 21:41:17 dhcp47-74 kernel: 3.1.0-rc4nmi+ #456 Oct 18 21:41:17 dhcp47-74 kernel: --------------------------------- Oct 18 21:41:17 dhcp47-74 kernel: inconsistent {IN-HARDIRQ-W} -> {HARDIRQ-ON-W} usage. Oct 18 21:41:17 dhcp47-74 kernel: swapper/0 [HC0[0]:SC1[1]:HE1:SE0] takes: Oct 18 21:41:17 dhcp47-74 kernel: (&(&xhci->lock)->rlock){?.-...}, at: [<ffffffffa0228990>] xhci_stop_endpoint_command_watchdog+0x30/0x340 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: {IN-HARDIRQ-W} state was registered at: Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8109a941>] __lock_acquire+0x781/0x1660 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8109bed7>] lock_acquire+0x97/0x170 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81501b46>] _raw_spin_lock+0x46/0x80 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa02299fa>] xhci_irq+0x3a/0x1960 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa022b351>] xhci_msi_irq+0x31/0x40 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810d2305>] handle_irq_event_percpu+0x85/0x320 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810d25e8>] handle_irq_event+0x48/0x70 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810d537d>] handle_edge_irq+0x6d/0x130 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810048c9>] handle_irq+0x49/0xa0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8150d56d>] do_IRQ+0x5d/0xe0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff815029b0>] ret_from_intr+0x0/0x13 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81388aca>] usb_set_device_state+0x8a/0x180 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8138f038>] usb_add_hcd+0x2b8/0x730 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa022ed7e>] xhci_pci_probe+0x9e/0xd4 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8127915f>] local_pci_probe+0x5f/0xd0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8127a569>] pci_device_probe+0x119/0x120 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81334473>] driver_probe_device+0xa3/0x2c0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8133473b>] __driver_attach+0xab/0xb0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8133373c>] bus_for_each_dev+0x6c/0xa0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff813341fe>] driver_attach+0x1e/0x20 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81333b88>] bus_add_driver+0x1f8/0x2b0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81334df6>] driver_register+0x76/0x140 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8127a7c6>] __pci_register_driver+0x66/0xe0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa013c04a>] snd_timer_find+0x4a/0x70 [snd_timer] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa013c00e>] snd_timer_find+0xe/0x70 [snd_timer] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810001d3>] do_one_initcall+0x43/0x180 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810a9ed2>] sys_init_module+0x92/0x1f0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8150ab6b>] system_call_fastpath+0x16/0x1b Oct 18 21:41:17 dhcp47-74 kernel: irq event stamp: 631984 Oct 18 21:41:17 dhcp47-74 kernel: hardirqs last enabled at (631984): [<ffffffff81502720>] _raw_spin_unlock_irq+0x30/0x50 Oct 18 21:41:17 dhcp47-74 kernel: hardirqs last disabled at (631983): [<ffffffff81501c49>] _raw_spin_lock_irq+0x19/0x90 Oct 18 21:41:17 dhcp47-74 kernel: softirqs last enabled at (631980): [<ffffffff8105ff63>] _local_bh_enable+0x13/0x20 Oct 18 21:41:17 dhcp47-74 kernel: softirqs last disabled at (631981): [<ffffffff8150ce6c>] call_softirq+0x1c/0x30 Oct 18 21:41:17 dhcp47-74 kernel: Oct 18 21:41:17 dhcp47-74 kernel: other info that might help us debug this: Oct 18 21:41:17 dhcp47-74 kernel: Possible unsafe locking scenario: Oct 18 21:41:17 dhcp47-74 kernel: Oct 18 21:41:17 dhcp47-74 kernel: CPU0 Oct 18 21:41:17 dhcp47-74 kernel: ---- Oct 18 21:41:17 dhcp47-74 kernel: lock(&(&xhci->lock)->rlock); Oct 18 21:41:17 dhcp47-74 kernel: <Interrupt> Oct 18 21:41:17 dhcp47-74 kernel: lock(&(&xhci->lock)->rlock); Oct 18 21:41:17 dhcp47-74 kernel: Oct 18 21:41:17 dhcp47-74 kernel: *** DEADLOCK *** Oct 18 21:41:17 dhcp47-74 kernel: Oct 18 21:41:17 dhcp47-74 kernel: 1 lock held by swapper/0: Oct 18 21:41:17 dhcp47-74 kernel: #0: (&ep->stop_cmd_timer){+.-...}, at: [<ffffffff8106abf2>] run_timer_softirq+0x162/0x570 Oct 18 21:41:17 dhcp47-74 kernel: Oct 18 21:41:17 dhcp47-74 kernel: stack backtrace: Oct 18 21:41:17 dhcp47-74 kernel: Pid: 0, comm: swapper Tainted: G W 3.1.0-rc4nmi+ #456 Oct 18 21:41:17 dhcp47-74 kernel: Call Trace: Oct 18 21:41:17 dhcp47-74 kernel: <IRQ> [<ffffffff81098ed7>] print_usage_bug+0x227/0x270 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810999c6>] mark_lock+0x346/0x410 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8109a7de>] __lock_acquire+0x61e/0x1660 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81099893>] ? mark_lock+0x213/0x410 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8109bed7>] lock_acquire+0x97/0x170 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa0228990>] ? xhci_stop_endpoint_command_watchdog+0x30/0x340 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81501b46>] _raw_spin_lock+0x46/0x80 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa0228990>] ? xhci_stop_endpoint_command_watchdog+0x30/0x340 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa0228990>] xhci_stop_endpoint_command_watchdog+0x30/0x340 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8106abf2>] ? run_timer_softirq+0x162/0x570 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8106ac9d>] run_timer_softirq+0x20d/0x570 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8106abf2>] ? run_timer_softirq+0x162/0x570 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa0228960>] ? xhci_queue_isoc_tx_prepare+0x8e0/0x8e0 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810604d2>] __do_softirq+0xf2/0x3f0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81020edd>] ? lapic_next_event+0x1d/0x30 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81090d4e>] ? clockevents_program_event+0x5e/0x90 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8150ce6c>] call_softirq+0x1c/0x30 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8100484d>] do_softirq+0x8d/0xc0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8105ff35>] irq_exit+0xe5/0x100 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8150d65e>] smp_apic_timer_interrupt+0x6e/0x99 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8150b6f0>] apic_timer_interrupt+0x70/0x80 Oct 18 21:41:17 dhcp47-74 kernel: <EOI> [<ffffffff81095d8d>] ? trace_hardirqs_off+0xd/0x10 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff812ddb76>] ? acpi_idle_enter_bm+0x227/0x25b Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff812ddb71>] ? acpi_idle_enter_bm+0x222/0x25b Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff813eda63>] cpuidle_idle_call+0x103/0x290 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81002155>] cpu_idle+0xe5/0x160 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff814e7f50>] rest_init+0xe0/0xf0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff814e7e70>] ? csum_partial_copy_generic+0x170/0x170 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81df8e23>] start_kernel+0x3fc/0x407 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81df8321>] x86_64_start_reservations+0x131/0x135 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81df8412>] x86_64_start_kernel+0xed/0xf4 Oct 18 21:41:17 dhcp47-74 kernel: xhci_hcd 0000:00:14.0: xHCI host not responding to stop endpoint command. Oct 18 21:41:17 dhcp47-74 kernel: xhci_hcd 0000:00:14.0: Assuming host is dying, halting host. Oct 18 21:41:17 dhcp47-74 kernel: xhci_hcd 0000:00:14.0: HC died; cleaning up Oct 18 21:41:17 dhcp47-74 kernel: usb 3-4: device descriptor read/8, error -110 Oct 18 21:41:17 dhcp47-74 kernel: usb 3-4: device descriptor read/8, error -22 Oct 18 21:41:17 dhcp47-74 kernel: hub 3-0:1.0: cannot disable port 4 (err = -19) Basically what is happening is in xhci_stop_endpoint_command_watchdog() the xhci->lock is grabbed with just spin_lock. What lockdep deduces is that if an interrupt occurred while in this function it would deadlock with xhci_irq because that function also grabs the xhci->lock. Fixing it is trivial by using spin_lock_irqsave instead. This should be queued to stable kernels as far back as 2.6.33. Signed-off-by: Don Zickus <dzickus@redhat.com> Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Cc: stable@kernel.org
2011-10-21 11:52:14 +08:00
spin_unlock_irqrestore(&xhci->lock, flags);
xhci_dbg(xhci, "Stop EP timer raced with cmd completion, exit");
USB: xhci: Add watchdog timer for URB cancellation. In order to giveback a canceled URB, we must ensure that the xHCI hardware will not access the buffer in an URB. We can't modify the buffer pointers on endpoint rings without issuing and waiting for a stop endpoint command. Since URBs can be canceled in interrupt context, we can't wait on that command. The old code trusted that the host controller would respond to the command, and would giveback the URBs in the event handler. If the hardware never responds to the stop endpoint command, the URBs will never be completed, and we might hang the USB subsystem. Implement a watchdog timer that is spawned whenever a stop endpoint command is queued. If a stop endpoint command event is found on the event ring during an interrupt, we need to stop the watchdog timer with del_timer(). Since del_timer() can fail if the timer is running and waiting on the xHCI lock, we need a way to signal to the timer that everything is fine and it should exit. If we simply clear EP_HALT_PENDING, a new stop endpoint command could sneak in and set it before the watchdog timer can grab the lock. Instead we use a combination of the EP_HALT_PENDING flag and a counter for the number of pending stop endpoint commands (xhci_virt_ep->stop_cmds_pending). If we need to cancel the watchdog timer and del_timer() succeeds, we decrement the number of pending stop endpoint commands. If del_timer() fails, we leave the number of pending stop endpoint commands alone. In either case, we clear the EP_HALT_PENDING flag. The timer will decrement the number of pending stop endpoint commands once it obtains the lock. If the timer is the tail end of the last stop endpoint command (xhci_virt_ep->stop_cmds_pending == 0), and the endpoint's command is still pending (EP_HALT_PENDING is set), we assume the host is dying. The watchdog timer will set XHCI_STATE_DYING, try to halt the xHCI host, and give back all pending URBs. Various other places in the driver need to check whether the xHCI host is dying. If the interrupt handler ever notices, it should immediately stop processing events. The URB enqueue function should also return -ESHUTDOWN. The URB dequeue function should simply return the value of usb_hcd_check_unlink_urb() and the watchdog timer will take care of giving the URB back. When a device is disconnected, the xHCI hardware structures should be freed without issuing a disable slot command (since the hardware probably won't respond to it anyway). The debugging polling loop should stop polling if the host is dying. When a device is disconnected, any pending watchdog timers are killed with del_timer_sync(). It must be synchronous so that the watchdog timer doesn't attempt to access the freed endpoint structures. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-10-28 01:57:01 +08:00
return;
}
usbsts = readl(&xhci->op_regs->status);
USB: xhci: Add watchdog timer for URB cancellation. In order to giveback a canceled URB, we must ensure that the xHCI hardware will not access the buffer in an URB. We can't modify the buffer pointers on endpoint rings without issuing and waiting for a stop endpoint command. Since URBs can be canceled in interrupt context, we can't wait on that command. The old code trusted that the host controller would respond to the command, and would giveback the URBs in the event handler. If the hardware never responds to the stop endpoint command, the URBs will never be completed, and we might hang the USB subsystem. Implement a watchdog timer that is spawned whenever a stop endpoint command is queued. If a stop endpoint command event is found on the event ring during an interrupt, we need to stop the watchdog timer with del_timer(). Since del_timer() can fail if the timer is running and waiting on the xHCI lock, we need a way to signal to the timer that everything is fine and it should exit. If we simply clear EP_HALT_PENDING, a new stop endpoint command could sneak in and set it before the watchdog timer can grab the lock. Instead we use a combination of the EP_HALT_PENDING flag and a counter for the number of pending stop endpoint commands (xhci_virt_ep->stop_cmds_pending). If we need to cancel the watchdog timer and del_timer() succeeds, we decrement the number of pending stop endpoint commands. If del_timer() fails, we leave the number of pending stop endpoint commands alone. In either case, we clear the EP_HALT_PENDING flag. The timer will decrement the number of pending stop endpoint commands once it obtains the lock. If the timer is the tail end of the last stop endpoint command (xhci_virt_ep->stop_cmds_pending == 0), and the endpoint's command is still pending (EP_HALT_PENDING is set), we assume the host is dying. The watchdog timer will set XHCI_STATE_DYING, try to halt the xHCI host, and give back all pending URBs. Various other places in the driver need to check whether the xHCI host is dying. If the interrupt handler ever notices, it should immediately stop processing events. The URB enqueue function should also return -ESHUTDOWN. The URB dequeue function should simply return the value of usb_hcd_check_unlink_urb() and the watchdog timer will take care of giving the URB back. When a device is disconnected, the xHCI hardware structures should be freed without issuing a disable slot command (since the hardware probably won't respond to it anyway). The debugging polling loop should stop polling if the host is dying. When a device is disconnected, any pending watchdog timers are killed with del_timer_sync(). It must be synchronous so that the watchdog timer doesn't attempt to access the freed endpoint structures. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-10-28 01:57:01 +08:00
xhci_warn(xhci, "xHCI host not responding to stop endpoint command.\n");
xhci_warn(xhci, "USBSTS:%s\n", xhci_decode_usbsts(usbsts));
ep->ep_state &= ~EP_STOP_CMD_PENDING;
xhci_halt(xhci);
USB: xhci: Add watchdog timer for URB cancellation. In order to giveback a canceled URB, we must ensure that the xHCI hardware will not access the buffer in an URB. We can't modify the buffer pointers on endpoint rings without issuing and waiting for a stop endpoint command. Since URBs can be canceled in interrupt context, we can't wait on that command. The old code trusted that the host controller would respond to the command, and would giveback the URBs in the event handler. If the hardware never responds to the stop endpoint command, the URBs will never be completed, and we might hang the USB subsystem. Implement a watchdog timer that is spawned whenever a stop endpoint command is queued. If a stop endpoint command event is found on the event ring during an interrupt, we need to stop the watchdog timer with del_timer(). Since del_timer() can fail if the timer is running and waiting on the xHCI lock, we need a way to signal to the timer that everything is fine and it should exit. If we simply clear EP_HALT_PENDING, a new stop endpoint command could sneak in and set it before the watchdog timer can grab the lock. Instead we use a combination of the EP_HALT_PENDING flag and a counter for the number of pending stop endpoint commands (xhci_virt_ep->stop_cmds_pending). If we need to cancel the watchdog timer and del_timer() succeeds, we decrement the number of pending stop endpoint commands. If del_timer() fails, we leave the number of pending stop endpoint commands alone. In either case, we clear the EP_HALT_PENDING flag. The timer will decrement the number of pending stop endpoint commands once it obtains the lock. If the timer is the tail end of the last stop endpoint command (xhci_virt_ep->stop_cmds_pending == 0), and the endpoint's command is still pending (EP_HALT_PENDING is set), we assume the host is dying. The watchdog timer will set XHCI_STATE_DYING, try to halt the xHCI host, and give back all pending URBs. Various other places in the driver need to check whether the xHCI host is dying. If the interrupt handler ever notices, it should immediately stop processing events. The URB enqueue function should also return -ESHUTDOWN. The URB dequeue function should simply return the value of usb_hcd_check_unlink_urb() and the watchdog timer will take care of giving the URB back. When a device is disconnected, the xHCI hardware structures should be freed without issuing a disable slot command (since the hardware probably won't respond to it anyway). The debugging polling loop should stop polling if the host is dying. When a device is disconnected, any pending watchdog timers are killed with del_timer_sync(). It must be synchronous so that the watchdog timer doesn't attempt to access the freed endpoint structures. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-10-28 01:57:01 +08:00
/*
* handle a stop endpoint cmd timeout as if host died (-ENODEV).
* In the future we could distinguish between -ENODEV and -ETIMEDOUT
* and try to recover a -ETIMEDOUT with a host controller reset
*/
xhci_hc_died(xhci);
USB: xhci: Add watchdog timer for URB cancellation. In order to giveback a canceled URB, we must ensure that the xHCI hardware will not access the buffer in an URB. We can't modify the buffer pointers on endpoint rings without issuing and waiting for a stop endpoint command. Since URBs can be canceled in interrupt context, we can't wait on that command. The old code trusted that the host controller would respond to the command, and would giveback the URBs in the event handler. If the hardware never responds to the stop endpoint command, the URBs will never be completed, and we might hang the USB subsystem. Implement a watchdog timer that is spawned whenever a stop endpoint command is queued. If a stop endpoint command event is found on the event ring during an interrupt, we need to stop the watchdog timer with del_timer(). Since del_timer() can fail if the timer is running and waiting on the xHCI lock, we need a way to signal to the timer that everything is fine and it should exit. If we simply clear EP_HALT_PENDING, a new stop endpoint command could sneak in and set it before the watchdog timer can grab the lock. Instead we use a combination of the EP_HALT_PENDING flag and a counter for the number of pending stop endpoint commands (xhci_virt_ep->stop_cmds_pending). If we need to cancel the watchdog timer and del_timer() succeeds, we decrement the number of pending stop endpoint commands. If del_timer() fails, we leave the number of pending stop endpoint commands alone. In either case, we clear the EP_HALT_PENDING flag. The timer will decrement the number of pending stop endpoint commands once it obtains the lock. If the timer is the tail end of the last stop endpoint command (xhci_virt_ep->stop_cmds_pending == 0), and the endpoint's command is still pending (EP_HALT_PENDING is set), we assume the host is dying. The watchdog timer will set XHCI_STATE_DYING, try to halt the xHCI host, and give back all pending URBs. Various other places in the driver need to check whether the xHCI host is dying. If the interrupt handler ever notices, it should immediately stop processing events. The URB enqueue function should also return -ESHUTDOWN. The URB dequeue function should simply return the value of usb_hcd_check_unlink_urb() and the watchdog timer will take care of giving the URB back. When a device is disconnected, the xHCI hardware structures should be freed without issuing a disable slot command (since the hardware probably won't respond to it anyway). The debugging polling loop should stop polling if the host is dying. When a device is disconnected, any pending watchdog timers are killed with del_timer_sync(). It must be synchronous so that the watchdog timer doesn't attempt to access the freed endpoint structures. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-10-28 01:57:01 +08:00
usb, xhci: fix lockdep warning on endpoint timeout While debugging a usb3 problem, I stumbled upon this lockdep warning. Oct 18 21:41:17 dhcp47-74 kernel: ================================= Oct 18 21:41:17 dhcp47-74 kernel: [ INFO: inconsistent lock state ] Oct 18 21:41:17 dhcp47-74 kernel: 3.1.0-rc4nmi+ #456 Oct 18 21:41:17 dhcp47-74 kernel: --------------------------------- Oct 18 21:41:17 dhcp47-74 kernel: inconsistent {IN-HARDIRQ-W} -> {HARDIRQ-ON-W} usage. Oct 18 21:41:17 dhcp47-74 kernel: swapper/0 [HC0[0]:SC1[1]:HE1:SE0] takes: Oct 18 21:41:17 dhcp47-74 kernel: (&(&xhci->lock)->rlock){?.-...}, at: [<ffffffffa0228990>] xhci_stop_endpoint_command_watchdog+0x30/0x340 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: {IN-HARDIRQ-W} state was registered at: Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8109a941>] __lock_acquire+0x781/0x1660 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8109bed7>] lock_acquire+0x97/0x170 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81501b46>] _raw_spin_lock+0x46/0x80 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa02299fa>] xhci_irq+0x3a/0x1960 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa022b351>] xhci_msi_irq+0x31/0x40 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810d2305>] handle_irq_event_percpu+0x85/0x320 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810d25e8>] handle_irq_event+0x48/0x70 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810d537d>] handle_edge_irq+0x6d/0x130 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810048c9>] handle_irq+0x49/0xa0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8150d56d>] do_IRQ+0x5d/0xe0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff815029b0>] ret_from_intr+0x0/0x13 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81388aca>] usb_set_device_state+0x8a/0x180 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8138f038>] usb_add_hcd+0x2b8/0x730 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa022ed7e>] xhci_pci_probe+0x9e/0xd4 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8127915f>] local_pci_probe+0x5f/0xd0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8127a569>] pci_device_probe+0x119/0x120 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81334473>] driver_probe_device+0xa3/0x2c0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8133473b>] __driver_attach+0xab/0xb0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8133373c>] bus_for_each_dev+0x6c/0xa0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff813341fe>] driver_attach+0x1e/0x20 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81333b88>] bus_add_driver+0x1f8/0x2b0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81334df6>] driver_register+0x76/0x140 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8127a7c6>] __pci_register_driver+0x66/0xe0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa013c04a>] snd_timer_find+0x4a/0x70 [snd_timer] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa013c00e>] snd_timer_find+0xe/0x70 [snd_timer] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810001d3>] do_one_initcall+0x43/0x180 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810a9ed2>] sys_init_module+0x92/0x1f0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8150ab6b>] system_call_fastpath+0x16/0x1b Oct 18 21:41:17 dhcp47-74 kernel: irq event stamp: 631984 Oct 18 21:41:17 dhcp47-74 kernel: hardirqs last enabled at (631984): [<ffffffff81502720>] _raw_spin_unlock_irq+0x30/0x50 Oct 18 21:41:17 dhcp47-74 kernel: hardirqs last disabled at (631983): [<ffffffff81501c49>] _raw_spin_lock_irq+0x19/0x90 Oct 18 21:41:17 dhcp47-74 kernel: softirqs last enabled at (631980): [<ffffffff8105ff63>] _local_bh_enable+0x13/0x20 Oct 18 21:41:17 dhcp47-74 kernel: softirqs last disabled at (631981): [<ffffffff8150ce6c>] call_softirq+0x1c/0x30 Oct 18 21:41:17 dhcp47-74 kernel: Oct 18 21:41:17 dhcp47-74 kernel: other info that might help us debug this: Oct 18 21:41:17 dhcp47-74 kernel: Possible unsafe locking scenario: Oct 18 21:41:17 dhcp47-74 kernel: Oct 18 21:41:17 dhcp47-74 kernel: CPU0 Oct 18 21:41:17 dhcp47-74 kernel: ---- Oct 18 21:41:17 dhcp47-74 kernel: lock(&(&xhci->lock)->rlock); Oct 18 21:41:17 dhcp47-74 kernel: <Interrupt> Oct 18 21:41:17 dhcp47-74 kernel: lock(&(&xhci->lock)->rlock); Oct 18 21:41:17 dhcp47-74 kernel: Oct 18 21:41:17 dhcp47-74 kernel: *** DEADLOCK *** Oct 18 21:41:17 dhcp47-74 kernel: Oct 18 21:41:17 dhcp47-74 kernel: 1 lock held by swapper/0: Oct 18 21:41:17 dhcp47-74 kernel: #0: (&ep->stop_cmd_timer){+.-...}, at: [<ffffffff8106abf2>] run_timer_softirq+0x162/0x570 Oct 18 21:41:17 dhcp47-74 kernel: Oct 18 21:41:17 dhcp47-74 kernel: stack backtrace: Oct 18 21:41:17 dhcp47-74 kernel: Pid: 0, comm: swapper Tainted: G W 3.1.0-rc4nmi+ #456 Oct 18 21:41:17 dhcp47-74 kernel: Call Trace: Oct 18 21:41:17 dhcp47-74 kernel: <IRQ> [<ffffffff81098ed7>] print_usage_bug+0x227/0x270 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810999c6>] mark_lock+0x346/0x410 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8109a7de>] __lock_acquire+0x61e/0x1660 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81099893>] ? mark_lock+0x213/0x410 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8109bed7>] lock_acquire+0x97/0x170 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa0228990>] ? xhci_stop_endpoint_command_watchdog+0x30/0x340 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81501b46>] _raw_spin_lock+0x46/0x80 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa0228990>] ? xhci_stop_endpoint_command_watchdog+0x30/0x340 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa0228990>] xhci_stop_endpoint_command_watchdog+0x30/0x340 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8106abf2>] ? run_timer_softirq+0x162/0x570 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8106ac9d>] run_timer_softirq+0x20d/0x570 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8106abf2>] ? run_timer_softirq+0x162/0x570 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffffa0228960>] ? xhci_queue_isoc_tx_prepare+0x8e0/0x8e0 [xhci_hcd] Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff810604d2>] __do_softirq+0xf2/0x3f0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81020edd>] ? lapic_next_event+0x1d/0x30 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81090d4e>] ? clockevents_program_event+0x5e/0x90 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8150ce6c>] call_softirq+0x1c/0x30 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8100484d>] do_softirq+0x8d/0xc0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8105ff35>] irq_exit+0xe5/0x100 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8150d65e>] smp_apic_timer_interrupt+0x6e/0x99 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff8150b6f0>] apic_timer_interrupt+0x70/0x80 Oct 18 21:41:17 dhcp47-74 kernel: <EOI> [<ffffffff81095d8d>] ? trace_hardirqs_off+0xd/0x10 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff812ddb76>] ? acpi_idle_enter_bm+0x227/0x25b Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff812ddb71>] ? acpi_idle_enter_bm+0x222/0x25b Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff813eda63>] cpuidle_idle_call+0x103/0x290 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81002155>] cpu_idle+0xe5/0x160 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff814e7f50>] rest_init+0xe0/0xf0 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff814e7e70>] ? csum_partial_copy_generic+0x170/0x170 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81df8e23>] start_kernel+0x3fc/0x407 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81df8321>] x86_64_start_reservations+0x131/0x135 Oct 18 21:41:17 dhcp47-74 kernel: [<ffffffff81df8412>] x86_64_start_kernel+0xed/0xf4 Oct 18 21:41:17 dhcp47-74 kernel: xhci_hcd 0000:00:14.0: xHCI host not responding to stop endpoint command. Oct 18 21:41:17 dhcp47-74 kernel: xhci_hcd 0000:00:14.0: Assuming host is dying, halting host. Oct 18 21:41:17 dhcp47-74 kernel: xhci_hcd 0000:00:14.0: HC died; cleaning up Oct 18 21:41:17 dhcp47-74 kernel: usb 3-4: device descriptor read/8, error -110 Oct 18 21:41:17 dhcp47-74 kernel: usb 3-4: device descriptor read/8, error -22 Oct 18 21:41:17 dhcp47-74 kernel: hub 3-0:1.0: cannot disable port 4 (err = -19) Basically what is happening is in xhci_stop_endpoint_command_watchdog() the xhci->lock is grabbed with just spin_lock. What lockdep deduces is that if an interrupt occurred while in this function it would deadlock with xhci_irq because that function also grabs the xhci->lock. Fixing it is trivial by using spin_lock_irqsave instead. This should be queued to stable kernels as far back as 2.6.33. Signed-off-by: Don Zickus <dzickus@redhat.com> Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Cc: stable@kernel.org
2011-10-21 11:52:14 +08:00
spin_unlock_irqrestore(&xhci->lock, flags);
xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
"xHCI host controller is dead.");
USB: xhci: Add watchdog timer for URB cancellation. In order to giveback a canceled URB, we must ensure that the xHCI hardware will not access the buffer in an URB. We can't modify the buffer pointers on endpoint rings without issuing and waiting for a stop endpoint command. Since URBs can be canceled in interrupt context, we can't wait on that command. The old code trusted that the host controller would respond to the command, and would giveback the URBs in the event handler. If the hardware never responds to the stop endpoint command, the URBs will never be completed, and we might hang the USB subsystem. Implement a watchdog timer that is spawned whenever a stop endpoint command is queued. If a stop endpoint command event is found on the event ring during an interrupt, we need to stop the watchdog timer with del_timer(). Since del_timer() can fail if the timer is running and waiting on the xHCI lock, we need a way to signal to the timer that everything is fine and it should exit. If we simply clear EP_HALT_PENDING, a new stop endpoint command could sneak in and set it before the watchdog timer can grab the lock. Instead we use a combination of the EP_HALT_PENDING flag and a counter for the number of pending stop endpoint commands (xhci_virt_ep->stop_cmds_pending). If we need to cancel the watchdog timer and del_timer() succeeds, we decrement the number of pending stop endpoint commands. If del_timer() fails, we leave the number of pending stop endpoint commands alone. In either case, we clear the EP_HALT_PENDING flag. The timer will decrement the number of pending stop endpoint commands once it obtains the lock. If the timer is the tail end of the last stop endpoint command (xhci_virt_ep->stop_cmds_pending == 0), and the endpoint's command is still pending (EP_HALT_PENDING is set), we assume the host is dying. The watchdog timer will set XHCI_STATE_DYING, try to halt the xHCI host, and give back all pending URBs. Various other places in the driver need to check whether the xHCI host is dying. If the interrupt handler ever notices, it should immediately stop processing events. The URB enqueue function should also return -ESHUTDOWN. The URB dequeue function should simply return the value of usb_hcd_check_unlink_urb() and the watchdog timer will take care of giving the URB back. When a device is disconnected, the xHCI hardware structures should be freed without issuing a disable slot command (since the hardware probably won't respond to it anyway). The debugging polling loop should stop polling if the host is dying. When a device is disconnected, any pending watchdog timers are killed with del_timer_sync(). It must be synchronous so that the watchdog timer doesn't attempt to access the freed endpoint structures. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-10-28 01:57:01 +08:00
}
static void update_ring_for_set_deq_completion(struct xhci_hcd *xhci,
struct xhci_virt_device *dev,
struct xhci_ring *ep_ring,
unsigned int ep_index)
{
union xhci_trb *dequeue_temp;
int num_trbs_free_temp;
bool revert = false;
num_trbs_free_temp = ep_ring->num_trbs_free;
dequeue_temp = ep_ring->dequeue;
xhci: Fix hang on back-to-back Set TR Deq Ptr commands. The Microsoft LifeChat 3000 USB headset was causing a very reproducible hang whenever it was plugged in. At first, I thought the host controller was producing bad transfer events, because the log was filled with errors like: xhci_hcd 0000:00:14.0: ERROR Transfer event TRB DMA ptr not part of current TD However, it turned out to be an xHCI driver bug in the ring expansion patches. The bug is triggered When there are two ring segments, and a TD that ends just before a link TRB, like so: ______________ _____________ | | ---> | setup TRB B | ______________ | _____________ | | | | data TRB B | ______________ | _____________ | setup TRB A | <-- deq | | data TRB B | ______________ | _____________ | data TRB A | | | | <-- enq, deq'' ______________ | _____________ | status TRB A | | | | ______________ | _____________ | link TRB |--------------- | link TRB | _____________ <--- deq' _____________ TD A (the first control transfer) stalls on the data phase. That halts the ring. The xHCI driver moves the hardware dequeue pointer to the first TRB after the stalled transfer, which happens to be the link TRB. Once the Set TR dequeue pointer command completes, the function update_ring_for_set_deq_completion runs. That function is supposed to update the xHCI driver's dequeue pointer to match the internal hardware dequeue pointer. On the first call this would work fine, and the software dequeue pointer would move to deq'. However, if the transfer immediately after that stalled (TD B in this case), another Set TR Dequeue command would be issued. That would move the hardware dequeue pointer to deq''. Once that command completed, update_ring_for_set_deq_completion would run again. The original code would unconditionally increment the software dequeue pointer, which moved the pointer off the ring segment into la-la-land. The while loop would happy increment the dequeue pointer (possibly wrapping it) until it matched the hardware pointer value. The while loop would also access all the memory in between the first ring segment and the second ring segment to determine if it was a link TRB. This could cause general protection faults, although it was unlikely because the ring segments came from a DMA pool, and would often have consecutive memory addresses. If nothing in that space looked like a link TRB, the deq_seg pointer for the ring would remain on the first segment. Thus, the deq_seg and the software dequeue pointer would get out of sync. When the next transfer event came in after the stalled transfer, the xHCI driver code would attempt to convert the software dequeue pointer into a DMA address in order to compare the DMA address for the completed transfer. Since the deq_seg and the dequeue pointer were out of sync, xhci_trb_virt_to_dma would return NULL. The transfer event would get ignored, the transfer would eventually timeout, and we would mistakenly convert the finished transfer to no-op TRBs. Some kernel driver (maybe xHCI?) would then get stuck in an infinite loop in interrupt context, and the whole machine would hang. This patch should be backported to kernels as old as 3.4, that contain the commit b008df60c6369ba0290fa7daa177375407a12e07 "xHCI: count free TRBs on transfer ring" Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Cc: Andiry Xu <andiry.xu@amd.com> Cc: stable@vger.kernel.org
2012-06-22 07:28:30 +08:00
/* If we get two back-to-back stalls, and the first stalled transfer
* ends just before a link TRB, the dequeue pointer will be left on
* the link TRB by the code in the while loop. So we have to update
* the dequeue pointer one segment further, or we'll jump off
* the segment into la-la-land.
*/
if (trb_is_link(ep_ring->dequeue)) {
xhci: Fix hang on back-to-back Set TR Deq Ptr commands. The Microsoft LifeChat 3000 USB headset was causing a very reproducible hang whenever it was plugged in. At first, I thought the host controller was producing bad transfer events, because the log was filled with errors like: xhci_hcd 0000:00:14.0: ERROR Transfer event TRB DMA ptr not part of current TD However, it turned out to be an xHCI driver bug in the ring expansion patches. The bug is triggered When there are two ring segments, and a TD that ends just before a link TRB, like so: ______________ _____________ | | ---> | setup TRB B | ______________ | _____________ | | | | data TRB B | ______________ | _____________ | setup TRB A | <-- deq | | data TRB B | ______________ | _____________ | data TRB A | | | | <-- enq, deq'' ______________ | _____________ | status TRB A | | | | ______________ | _____________ | link TRB |--------------- | link TRB | _____________ <--- deq' _____________ TD A (the first control transfer) stalls on the data phase. That halts the ring. The xHCI driver moves the hardware dequeue pointer to the first TRB after the stalled transfer, which happens to be the link TRB. Once the Set TR dequeue pointer command completes, the function update_ring_for_set_deq_completion runs. That function is supposed to update the xHCI driver's dequeue pointer to match the internal hardware dequeue pointer. On the first call this would work fine, and the software dequeue pointer would move to deq'. However, if the transfer immediately after that stalled (TD B in this case), another Set TR Dequeue command would be issued. That would move the hardware dequeue pointer to deq''. Once that command completed, update_ring_for_set_deq_completion would run again. The original code would unconditionally increment the software dequeue pointer, which moved the pointer off the ring segment into la-la-land. The while loop would happy increment the dequeue pointer (possibly wrapping it) until it matched the hardware pointer value. The while loop would also access all the memory in between the first ring segment and the second ring segment to determine if it was a link TRB. This could cause general protection faults, although it was unlikely because the ring segments came from a DMA pool, and would often have consecutive memory addresses. If nothing in that space looked like a link TRB, the deq_seg pointer for the ring would remain on the first segment. Thus, the deq_seg and the software dequeue pointer would get out of sync. When the next transfer event came in after the stalled transfer, the xHCI driver code would attempt to convert the software dequeue pointer into a DMA address in order to compare the DMA address for the completed transfer. Since the deq_seg and the dequeue pointer were out of sync, xhci_trb_virt_to_dma would return NULL. The transfer event would get ignored, the transfer would eventually timeout, and we would mistakenly convert the finished transfer to no-op TRBs. Some kernel driver (maybe xHCI?) would then get stuck in an infinite loop in interrupt context, and the whole machine would hang. This patch should be backported to kernels as old as 3.4, that contain the commit b008df60c6369ba0290fa7daa177375407a12e07 "xHCI: count free TRBs on transfer ring" Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Cc: Andiry Xu <andiry.xu@amd.com> Cc: stable@vger.kernel.org
2012-06-22 07:28:30 +08:00
ep_ring->deq_seg = ep_ring->deq_seg->next;
ep_ring->dequeue = ep_ring->deq_seg->trbs;
}
while (ep_ring->dequeue != dev->eps[ep_index].queued_deq_ptr) {
/* We have more usable TRBs */
ep_ring->num_trbs_free++;
ep_ring->dequeue++;
if (trb_is_link(ep_ring->dequeue)) {
if (ep_ring->dequeue ==
dev->eps[ep_index].queued_deq_ptr)
break;
ep_ring->deq_seg = ep_ring->deq_seg->next;
ep_ring->dequeue = ep_ring->deq_seg->trbs;
}
if (ep_ring->dequeue == dequeue_temp) {
revert = true;
break;
}
}
if (revert) {
xhci_dbg(xhci, "Unable to find new dequeue pointer\n");
ep_ring->num_trbs_free = num_trbs_free_temp;
}
}
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
/*
* When we get a completion for a Set Transfer Ring Dequeue Pointer command,
* we need to clear the set deq pending flag in the endpoint ring state, so that
* the TD queueing code can ring the doorbell again. We also need to ring the
* endpoint doorbell to restart the ring, but only if there aren't more
* cancellations pending.
*/
static void xhci_handle_cmd_set_deq(struct xhci_hcd *xhci, int slot_id,
union xhci_trb *trb, u32 cmd_comp_code)
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
{
unsigned int ep_index;
USB: xhci: Correct assumptions about number of rings per endpoint. Much of the xHCI driver code assumes that endpoints only have one ring. Now an endpoint can have one ring per enabled stream ID, so correct that assumption. Use functions that translate the stream_id field in the URB or the DMA address of a TRB into the correct stream ring. Correct the polling loop to print out all enabled stream rings. Make the URB cancellation routine find the correct stream ring if the URB has stream_id set. Make sure the URB enqueueing routine does the same. Also correct the code that handles stalled/halted endpoints. Check that commands and registers that can take stream IDs handle them properly. That includes ringing an endpoint doorbell, resetting a stalled/halted endpoint, and setting a transfer ring dequeue pointer (since that command can set the dequeue pointer in a stream context or an endpoint context). Correct the transfer event handler to translate a TRB DMA address into the stream ring it was enqueued to. Make the code to allocate and prepare TD structures adds the TD to the right td_list for the stream ring. Make sure the code to give the first TRB in a TD to the hardware manipulates the correct stream ring. When an endpoint stalls, store the stream ID of the stream ring that stalled in the xhci_virt_ep structure. Use that instead of the stream ID in the URB, since an URB may be re-used after it is given back after a non-control endpoint stall. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-03 06:34:43 +08:00
unsigned int stream_id;
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
struct xhci_ring *ep_ring;
struct xhci_virt_device *dev;
struct xhci_virt_ep *ep;
struct xhci_ep_ctx *ep_ctx;
struct xhci_slot_ctx *slot_ctx;
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
ep_index = TRB_TO_EP_INDEX(le32_to_cpu(trb->generic.field[3]));
stream_id = TRB_TO_STREAM_ID(le32_to_cpu(trb->generic.field[2]));
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
dev = xhci->devs[slot_id];
ep = &dev->eps[ep_index];
USB: xhci: Correct assumptions about number of rings per endpoint. Much of the xHCI driver code assumes that endpoints only have one ring. Now an endpoint can have one ring per enabled stream ID, so correct that assumption. Use functions that translate the stream_id field in the URB or the DMA address of a TRB into the correct stream ring. Correct the polling loop to print out all enabled stream rings. Make the URB cancellation routine find the correct stream ring if the URB has stream_id set. Make sure the URB enqueueing routine does the same. Also correct the code that handles stalled/halted endpoints. Check that commands and registers that can take stream IDs handle them properly. That includes ringing an endpoint doorbell, resetting a stalled/halted endpoint, and setting a transfer ring dequeue pointer (since that command can set the dequeue pointer in a stream context or an endpoint context). Correct the transfer event handler to translate a TRB DMA address into the stream ring it was enqueued to. Make the code to allocate and prepare TD structures adds the TD to the right td_list for the stream ring. Make sure the code to give the first TRB in a TD to the hardware manipulates the correct stream ring. When an endpoint stalls, store the stream ID of the stream ring that stalled in the xhci_virt_ep structure. Use that instead of the stream ID in the URB, since an URB may be re-used after it is given back after a non-control endpoint stall. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-03 06:34:43 +08:00
ep_ring = xhci_stream_id_to_ring(dev, ep_index, stream_id);
if (!ep_ring) {
xhci_warn(xhci, "WARN Set TR deq ptr command for freed stream ID %u\n",
USB: xhci: Correct assumptions about number of rings per endpoint. Much of the xHCI driver code assumes that endpoints only have one ring. Now an endpoint can have one ring per enabled stream ID, so correct that assumption. Use functions that translate the stream_id field in the URB or the DMA address of a TRB into the correct stream ring. Correct the polling loop to print out all enabled stream rings. Make the URB cancellation routine find the correct stream ring if the URB has stream_id set. Make sure the URB enqueueing routine does the same. Also correct the code that handles stalled/halted endpoints. Check that commands and registers that can take stream IDs handle them properly. That includes ringing an endpoint doorbell, resetting a stalled/halted endpoint, and setting a transfer ring dequeue pointer (since that command can set the dequeue pointer in a stream context or an endpoint context). Correct the transfer event handler to translate a TRB DMA address into the stream ring it was enqueued to. Make the code to allocate and prepare TD structures adds the TD to the right td_list for the stream ring. Make sure the code to give the first TRB in a TD to the hardware manipulates the correct stream ring. When an endpoint stalls, store the stream ID of the stream ring that stalled in the xhci_virt_ep structure. Use that instead of the stream ID in the URB, since an URB may be re-used after it is given back after a non-control endpoint stall. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-03 06:34:43 +08:00
stream_id);
/* XXX: Harmless??? */
goto cleanup;
USB: xhci: Correct assumptions about number of rings per endpoint. Much of the xHCI driver code assumes that endpoints only have one ring. Now an endpoint can have one ring per enabled stream ID, so correct that assumption. Use functions that translate the stream_id field in the URB or the DMA address of a TRB into the correct stream ring. Correct the polling loop to print out all enabled stream rings. Make the URB cancellation routine find the correct stream ring if the URB has stream_id set. Make sure the URB enqueueing routine does the same. Also correct the code that handles stalled/halted endpoints. Check that commands and registers that can take stream IDs handle them properly. That includes ringing an endpoint doorbell, resetting a stalled/halted endpoint, and setting a transfer ring dequeue pointer (since that command can set the dequeue pointer in a stream context or an endpoint context). Correct the transfer event handler to translate a TRB DMA address into the stream ring it was enqueued to. Make the code to allocate and prepare TD structures adds the TD to the right td_list for the stream ring. Make sure the code to give the first TRB in a TD to the hardware manipulates the correct stream ring. When an endpoint stalls, store the stream ID of the stream ring that stalled in the xhci_virt_ep structure. Use that instead of the stream ID in the URB, since an URB may be re-used after it is given back after a non-control endpoint stall. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-03 06:34:43 +08:00
}
ep_ctx = xhci_get_ep_ctx(xhci, dev->out_ctx, ep_index);
slot_ctx = xhci_get_slot_ctx(xhci, dev->out_ctx);
trace_xhci_handle_cmd_set_deq(slot_ctx);
trace_xhci_handle_cmd_set_deq_ep(ep_ctx);
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
if (cmd_comp_code != COMP_SUCCESS) {
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
unsigned int ep_state;
unsigned int slot_state;
switch (cmd_comp_code) {
case COMP_TRB_ERROR:
xhci_warn(xhci, "WARN Set TR Deq Ptr cmd invalid because of stream ID configuration\n");
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
break;
case COMP_CONTEXT_STATE_ERROR:
xhci_warn(xhci, "WARN Set TR Deq Ptr cmd failed due to incorrect slot or ep state.\n");
ep_state = GET_EP_CTX_STATE(ep_ctx);
slot_state = le32_to_cpu(slot_ctx->dev_state);
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
slot_state = GET_SLOT_STATE(slot_state);
xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
"Slot state = %u, EP state = %u",
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
slot_state, ep_state);
break;
case COMP_SLOT_NOT_ENABLED_ERROR:
xhci_warn(xhci, "WARN Set TR Deq Ptr cmd failed because slot %u was not enabled.\n",
slot_id);
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
break;
default:
xhci_warn(xhci, "WARN Set TR Deq Ptr cmd with unknown completion code of %u.\n",
cmd_comp_code);
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
break;
}
/* OK what do we do now? The endpoint state is hosed, and we
* should never get to this point if the synchronization between
* queueing, and endpoint state are correct. This might happen
* if the device gets disconnected after we've finished
* cancelling URBs, which might not be an error...
*/
} else {
u64 deq;
/* 4.6.10 deq ptr is written to the stream ctx for streams */
if (ep->ep_state & EP_HAS_STREAMS) {
struct xhci_stream_ctx *ctx =
&ep->stream_info->stream_ctx_array[stream_id];
deq = le64_to_cpu(ctx->stream_ring) & SCTX_DEQ_MASK;
} else {
deq = le64_to_cpu(ep_ctx->deq) & ~EP_CTX_CYCLE_MASK;
}
xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
"Successful Set TR Deq Ptr cmd, deq = @%08llx", deq);
if (xhci_trb_virt_to_dma(ep->queued_deq_seg,
ep->queued_deq_ptr) == deq) {
xhci: Update internal dequeue pointers after stalls. When an endpoint stalls, the xHCI driver must move the endpoint ring's dequeue pointer past the stalled transfer. To do that, the driver issues a Set TR Dequeue Pointer command, which will complete some time later. Takashi was having issues with USB 1.1 audio devices that stalled, and his analysis of the code was that the old code would not update the xHCI driver's ring dequeue pointer after the command completes. However, the dequeue pointer is set in xhci_find_new_dequeue_state(), just before the set command is issued to the hardware. Setting the dequeue pointer before the Set TR Dequeue Pointer command completes is a dangerous thing to do, since the xHCI hardware can fail the command. Instead, store the new dequeue pointer in the xhci_virt_ep structure, and update the ring's dequeue pointer when the Set TR dequeue pointer command completes. While we're at it, make sure we can't queue another Set TR Dequeue Command while the first one is still being processed. This just won't work with the internal xHCI state code. I'm still not sure if this is the right thing to do, since we might have a case where a driver queues multiple URBs to a control ring, one of the URBs Stalls, and then the driver tries to cancel the second URB. There may be a race condition there where the xHCI driver might try to issue multiple Set TR Dequeue Pointer commands, but I would have to think very hard about how the Stop Endpoint and cancellation code works. Keep the fix simple until when/if we run into that case. This patch should be queued to kernels all the way back to 2.6.31. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Tested-by: Takashi Iwai <tiwai@suse.de> Cc: stable@kernel.org
2011-02-24 07:46:42 +08:00
/* Update the ring's dequeue segment and dequeue pointer
* to reflect the new position.
*/
update_ring_for_set_deq_completion(xhci, dev,
ep_ring, ep_index);
xhci: Update internal dequeue pointers after stalls. When an endpoint stalls, the xHCI driver must move the endpoint ring's dequeue pointer past the stalled transfer. To do that, the driver issues a Set TR Dequeue Pointer command, which will complete some time later. Takashi was having issues with USB 1.1 audio devices that stalled, and his analysis of the code was that the old code would not update the xHCI driver's ring dequeue pointer after the command completes. However, the dequeue pointer is set in xhci_find_new_dequeue_state(), just before the set command is issued to the hardware. Setting the dequeue pointer before the Set TR Dequeue Pointer command completes is a dangerous thing to do, since the xHCI hardware can fail the command. Instead, store the new dequeue pointer in the xhci_virt_ep structure, and update the ring's dequeue pointer when the Set TR dequeue pointer command completes. While we're at it, make sure we can't queue another Set TR Dequeue Command while the first one is still being processed. This just won't work with the internal xHCI state code. I'm still not sure if this is the right thing to do, since we might have a case where a driver queues multiple URBs to a control ring, one of the URBs Stalls, and then the driver tries to cancel the second URB. There may be a race condition there where the xHCI driver might try to issue multiple Set TR Dequeue Pointer commands, but I would have to think very hard about how the Stop Endpoint and cancellation code works. Keep the fix simple until when/if we run into that case. This patch should be queued to kernels all the way back to 2.6.31. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Tested-by: Takashi Iwai <tiwai@suse.de> Cc: stable@kernel.org
2011-02-24 07:46:42 +08:00
} else {
xhci_warn(xhci, "Mismatch between completed Set TR Deq Ptr command & xHCI internal state.\n");
xhci: Update internal dequeue pointers after stalls. When an endpoint stalls, the xHCI driver must move the endpoint ring's dequeue pointer past the stalled transfer. To do that, the driver issues a Set TR Dequeue Pointer command, which will complete some time later. Takashi was having issues with USB 1.1 audio devices that stalled, and his analysis of the code was that the old code would not update the xHCI driver's ring dequeue pointer after the command completes. However, the dequeue pointer is set in xhci_find_new_dequeue_state(), just before the set command is issued to the hardware. Setting the dequeue pointer before the Set TR Dequeue Pointer command completes is a dangerous thing to do, since the xHCI hardware can fail the command. Instead, store the new dequeue pointer in the xhci_virt_ep structure, and update the ring's dequeue pointer when the Set TR dequeue pointer command completes. While we're at it, make sure we can't queue another Set TR Dequeue Command while the first one is still being processed. This just won't work with the internal xHCI state code. I'm still not sure if this is the right thing to do, since we might have a case where a driver queues multiple URBs to a control ring, one of the URBs Stalls, and then the driver tries to cancel the second URB. There may be a race condition there where the xHCI driver might try to issue multiple Set TR Dequeue Pointer commands, but I would have to think very hard about how the Stop Endpoint and cancellation code works. Keep the fix simple until when/if we run into that case. This patch should be queued to kernels all the way back to 2.6.31. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Tested-by: Takashi Iwai <tiwai@suse.de> Cc: stable@kernel.org
2011-02-24 07:46:42 +08:00
xhci_warn(xhci, "ep deq seg = %p, deq ptr = %p\n",
ep->queued_deq_seg, ep->queued_deq_ptr);
xhci: Update internal dequeue pointers after stalls. When an endpoint stalls, the xHCI driver must move the endpoint ring's dequeue pointer past the stalled transfer. To do that, the driver issues a Set TR Dequeue Pointer command, which will complete some time later. Takashi was having issues with USB 1.1 audio devices that stalled, and his analysis of the code was that the old code would not update the xHCI driver's ring dequeue pointer after the command completes. However, the dequeue pointer is set in xhci_find_new_dequeue_state(), just before the set command is issued to the hardware. Setting the dequeue pointer before the Set TR Dequeue Pointer command completes is a dangerous thing to do, since the xHCI hardware can fail the command. Instead, store the new dequeue pointer in the xhci_virt_ep structure, and update the ring's dequeue pointer when the Set TR dequeue pointer command completes. While we're at it, make sure we can't queue another Set TR Dequeue Command while the first one is still being processed. This just won't work with the internal xHCI state code. I'm still not sure if this is the right thing to do, since we might have a case where a driver queues multiple URBs to a control ring, one of the URBs Stalls, and then the driver tries to cancel the second URB. There may be a race condition there where the xHCI driver might try to issue multiple Set TR Dequeue Pointer commands, but I would have to think very hard about how the Stop Endpoint and cancellation code works. Keep the fix simple until when/if we run into that case. This patch should be queued to kernels all the way back to 2.6.31. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Tested-by: Takashi Iwai <tiwai@suse.de> Cc: stable@kernel.org
2011-02-24 07:46:42 +08:00
}
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
}
cleanup:
dev->eps[ep_index].ep_state &= ~SET_DEQ_PENDING;
xhci: Update internal dequeue pointers after stalls. When an endpoint stalls, the xHCI driver must move the endpoint ring's dequeue pointer past the stalled transfer. To do that, the driver issues a Set TR Dequeue Pointer command, which will complete some time later. Takashi was having issues with USB 1.1 audio devices that stalled, and his analysis of the code was that the old code would not update the xHCI driver's ring dequeue pointer after the command completes. However, the dequeue pointer is set in xhci_find_new_dequeue_state(), just before the set command is issued to the hardware. Setting the dequeue pointer before the Set TR Dequeue Pointer command completes is a dangerous thing to do, since the xHCI hardware can fail the command. Instead, store the new dequeue pointer in the xhci_virt_ep structure, and update the ring's dequeue pointer when the Set TR dequeue pointer command completes. While we're at it, make sure we can't queue another Set TR Dequeue Command while the first one is still being processed. This just won't work with the internal xHCI state code. I'm still not sure if this is the right thing to do, since we might have a case where a driver queues multiple URBs to a control ring, one of the URBs Stalls, and then the driver tries to cancel the second URB. There may be a race condition there where the xHCI driver might try to issue multiple Set TR Dequeue Pointer commands, but I would have to think very hard about how the Stop Endpoint and cancellation code works. Keep the fix simple until when/if we run into that case. This patch should be queued to kernels all the way back to 2.6.31. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Tested-by: Takashi Iwai <tiwai@suse.de> Cc: stable@kernel.org
2011-02-24 07:46:42 +08:00
dev->eps[ep_index].queued_deq_seg = NULL;
dev->eps[ep_index].queued_deq_ptr = NULL;
USB: xhci: Correct assumptions about number of rings per endpoint. Much of the xHCI driver code assumes that endpoints only have one ring. Now an endpoint can have one ring per enabled stream ID, so correct that assumption. Use functions that translate the stream_id field in the URB or the DMA address of a TRB into the correct stream ring. Correct the polling loop to print out all enabled stream rings. Make the URB cancellation routine find the correct stream ring if the URB has stream_id set. Make sure the URB enqueueing routine does the same. Also correct the code that handles stalled/halted endpoints. Check that commands and registers that can take stream IDs handle them properly. That includes ringing an endpoint doorbell, resetting a stalled/halted endpoint, and setting a transfer ring dequeue pointer (since that command can set the dequeue pointer in a stream context or an endpoint context). Correct the transfer event handler to translate a TRB DMA address into the stream ring it was enqueued to. Make the code to allocate and prepare TD structures adds the TD to the right td_list for the stream ring. Make sure the code to give the first TRB in a TD to the hardware manipulates the correct stream ring. When an endpoint stalls, store the stream ID of the stream ring that stalled in the xhci_virt_ep structure. Use that instead of the stream ID in the URB, since an URB may be re-used after it is given back after a non-control endpoint stall. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-03 06:34:43 +08:00
/* Restart any rings with pending URBs */
ring_doorbell_for_active_rings(xhci, slot_id, ep_index);
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
}
static void xhci_handle_cmd_reset_ep(struct xhci_hcd *xhci, int slot_id,
union xhci_trb *trb, u32 cmd_comp_code)
{
struct xhci_virt_device *vdev;
struct xhci_ep_ctx *ep_ctx;
unsigned int ep_index;
ep_index = TRB_TO_EP_INDEX(le32_to_cpu(trb->generic.field[3]));
vdev = xhci->devs[slot_id];
ep_ctx = xhci_get_ep_ctx(xhci, vdev->out_ctx, ep_index);
trace_xhci_handle_cmd_reset_ep(ep_ctx);
/* This command will only fail if the endpoint wasn't halted,
* but we don't care.
*/
xhci_dbg_trace(xhci, trace_xhci_dbg_reset_ep,
"Ignoring reset ep completion code of %u", cmd_comp_code);
/* HW with the reset endpoint quirk needs to have a configure endpoint
* command complete before the endpoint can be used. Queue that here
* because the HW can't handle two commands being queued in a row.
*/
if (xhci->quirks & XHCI_RESET_EP_QUIRK) {
struct xhci_command *command;
command = xhci_alloc_command(xhci, false, GFP_ATOMIC);
if (!command)
return;
xhci_dbg_trace(xhci, trace_xhci_dbg_quirks,
"Queueing configure endpoint command");
xhci_queue_configure_endpoint(xhci, command,
xhci->devs[slot_id]->in_ctx->dma, slot_id,
false);
xhci_ring_cmd_db(xhci);
} else {
/* Clear our internal halted state */
xhci->devs[slot_id]->eps[ep_index].ep_state &= ~EP_HALTED;
}
/* if this was a soft reset, then restart */
if ((le32_to_cpu(trb->generic.field[3])) & TRB_TSP)
ring_doorbell_for_active_rings(xhci, slot_id, ep_index);
}
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
static void xhci_handle_cmd_enable_slot(struct xhci_hcd *xhci, int slot_id,
struct xhci_command *command, u32 cmd_comp_code)
{
if (cmd_comp_code == COMP_SUCCESS)
command->slot_id = slot_id;
else
command->slot_id = 0;
}
static void xhci_handle_cmd_disable_slot(struct xhci_hcd *xhci, int slot_id)
{
struct xhci_virt_device *virt_dev;
struct xhci_slot_ctx *slot_ctx;
virt_dev = xhci->devs[slot_id];
if (!virt_dev)
return;
slot_ctx = xhci_get_slot_ctx(xhci, virt_dev->out_ctx);
trace_xhci_handle_cmd_disable_slot(slot_ctx);
if (xhci->quirks & XHCI_EP_LIMIT_QUIRK)
/* Delete default control endpoint resources */
xhci_free_device_endpoint_resources(xhci, virt_dev, true);
xhci_free_virt_device(xhci, slot_id);
}
static void xhci_handle_cmd_config_ep(struct xhci_hcd *xhci, int slot_id,
struct xhci_event_cmd *event, u32 cmd_comp_code)
{
struct xhci_virt_device *virt_dev;
struct xhci_input_control_ctx *ctrl_ctx;
struct xhci_ep_ctx *ep_ctx;
unsigned int ep_index;
unsigned int ep_state;
u32 add_flags, drop_flags;
/*
* Configure endpoint commands can come from the USB core
* configuration or alt setting changes, or because the HW
* needed an extra configure endpoint command after a reset
* endpoint command or streams were being configured.
* If the command was for a halted endpoint, the xHCI driver
* is not waiting on the configure endpoint command.
*/
virt_dev = xhci->devs[slot_id];
ctrl_ctx = xhci_get_input_control_ctx(virt_dev->in_ctx);
if (!ctrl_ctx) {
xhci_warn(xhci, "Could not get input context, bad type.\n");
return;
}
add_flags = le32_to_cpu(ctrl_ctx->add_flags);
drop_flags = le32_to_cpu(ctrl_ctx->drop_flags);
/* Input ctx add_flags are the endpoint index plus one */
ep_index = xhci_last_valid_endpoint(add_flags) - 1;
ep_ctx = xhci_get_ep_ctx(xhci, virt_dev->out_ctx, ep_index);
trace_xhci_handle_cmd_config_ep(ep_ctx);
/* A usb_set_interface() call directly after clearing a halted
* condition may race on this quirky hardware. Not worth
* worrying about, since this is prototype hardware. Not sure
* if this will work for streams, but streams support was
* untested on this prototype.
*/
if (xhci->quirks & XHCI_RESET_EP_QUIRK &&
ep_index != (unsigned int) -1 &&
add_flags - SLOT_FLAG == drop_flags) {
ep_state = virt_dev->eps[ep_index].ep_state;
if (!(ep_state & EP_HALTED))
return;
xhci_dbg_trace(xhci, trace_xhci_dbg_quirks,
"Completed config ep cmd - "
"last ep index = %d, state = %d",
ep_index, ep_state);
/* Clear internal halted state and restart ring(s) */
virt_dev->eps[ep_index].ep_state &= ~EP_HALTED;
ring_doorbell_for_active_rings(xhci, slot_id, ep_index);
return;
}
return;
}
static void xhci_handle_cmd_addr_dev(struct xhci_hcd *xhci, int slot_id)
{
struct xhci_virt_device *vdev;
struct xhci_slot_ctx *slot_ctx;
vdev = xhci->devs[slot_id];
slot_ctx = xhci_get_slot_ctx(xhci, vdev->out_ctx);
trace_xhci_handle_cmd_addr_dev(slot_ctx);
}
static void xhci_handle_cmd_reset_dev(struct xhci_hcd *xhci, int slot_id,
struct xhci_event_cmd *event)
{
struct xhci_virt_device *vdev;
struct xhci_slot_ctx *slot_ctx;
vdev = xhci->devs[slot_id];
slot_ctx = xhci_get_slot_ctx(xhci, vdev->out_ctx);
trace_xhci_handle_cmd_reset_dev(slot_ctx);
xhci_dbg(xhci, "Completed reset device command.\n");
if (!xhci->devs[slot_id])
xhci_warn(xhci, "Reset device command completion "
"for disabled slot %u\n", slot_id);
}
static void xhci_handle_cmd_nec_get_fw(struct xhci_hcd *xhci,
struct xhci_event_cmd *event)
{
if (!(xhci->quirks & XHCI_NEC_HOST)) {
xhci_warn(xhci, "WARN NEC_GET_FW command on non-NEC host\n");
return;
}
xhci_dbg_trace(xhci, trace_xhci_dbg_quirks,
"NEC firmware version %2x.%02x",
NEC_FW_MAJOR(le32_to_cpu(event->status)),
NEC_FW_MINOR(le32_to_cpu(event->status)));
}
static void xhci_complete_del_and_free_cmd(struct xhci_command *cmd, u32 status)
{
list_del(&cmd->cmd_list);
if (cmd->completion) {
cmd->status = status;
complete(cmd->completion);
} else {
kfree(cmd);
}
}
void xhci_cleanup_command_queue(struct xhci_hcd *xhci)
{
struct xhci_command *cur_cmd, *tmp_cmd;
xhci->current_cmd = NULL;
list_for_each_entry_safe(cur_cmd, tmp_cmd, &xhci->cmd_list, cmd_list)
xhci_complete_del_and_free_cmd(cur_cmd, COMP_COMMAND_ABORTED);
}
void xhci_handle_command_timeout(struct work_struct *work)
xhci: rework command timeout and cancellation, Use one timer to control command timeout. start/kick the timer every time a command is completed and a new command is waiting, or a new command is added to a empty list. If the timer runs out, then tag the current command as "aborted", and start the xhci command abortion process. Previously each function that submitted a command had its own timer. If that command timed out, a new command structure for the command was created and it was put on a cancel_cmd_list list, then a pci write to abort the command ring was issued. when the ring was aborted, it checked if the current command was the one to be canceled, later when the ring was stopped the driver got ownership of the TRBs in the command ring, compared then to the TRBs in the cancel_cmd_list, and turned them into No-ops. Now, instead, at timeout we tag the status of the command in the command queue to be aborted, and start the ring abortion. Ring abortion stops the command ring and gives control of the commands to us. All the aborted commands are now turned into No-ops. If the ring is already stopped when the command times outs its not possible to start the ring abortion, in this case the command is turnd to No-op right away. All these changes allows us to remove the entire cancel_cmd_list code. The functions waiting for a command to finish no longer have their own timeouts. They will wait either until the command completes normally, or until the whole command abortion is done. Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-05-09 00:26:03 +08:00
{
struct xhci_hcd *xhci;
unsigned long flags;
u64 hw_ring_state;
xhci = container_of(to_delayed_work(work), struct xhci_hcd, cmd_timer);
xhci: rework command timeout and cancellation, Use one timer to control command timeout. start/kick the timer every time a command is completed and a new command is waiting, or a new command is added to a empty list. If the timer runs out, then tag the current command as "aborted", and start the xhci command abortion process. Previously each function that submitted a command had its own timer. If that command timed out, a new command structure for the command was created and it was put on a cancel_cmd_list list, then a pci write to abort the command ring was issued. when the ring was aborted, it checked if the current command was the one to be canceled, later when the ring was stopped the driver got ownership of the TRBs in the command ring, compared then to the TRBs in the cancel_cmd_list, and turned them into No-ops. Now, instead, at timeout we tag the status of the command in the command queue to be aborted, and start the ring abortion. Ring abortion stops the command ring and gives control of the commands to us. All the aborted commands are now turned into No-ops. If the ring is already stopped when the command times outs its not possible to start the ring abortion, in this case the command is turnd to No-op right away. All these changes allows us to remove the entire cancel_cmd_list code. The functions waiting for a command to finish no longer have their own timeouts. They will wait either until the command completes normally, or until the whole command abortion is done. Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-05-09 00:26:03 +08:00
spin_lock_irqsave(&xhci->lock, flags);
/*
* If timeout work is pending, or current_cmd is NULL, it means we
* raced with command completion. Command is handled so just return.
*/
if (!xhci->current_cmd || delayed_work_pending(&xhci->cmd_timer)) {
spin_unlock_irqrestore(&xhci->lock, flags);
return;
xhci: rework command timeout and cancellation, Use one timer to control command timeout. start/kick the timer every time a command is completed and a new command is waiting, or a new command is added to a empty list. If the timer runs out, then tag the current command as "aborted", and start the xhci command abortion process. Previously each function that submitted a command had its own timer. If that command timed out, a new command structure for the command was created and it was put on a cancel_cmd_list list, then a pci write to abort the command ring was issued. when the ring was aborted, it checked if the current command was the one to be canceled, later when the ring was stopped the driver got ownership of the TRBs in the command ring, compared then to the TRBs in the cancel_cmd_list, and turned them into No-ops. Now, instead, at timeout we tag the status of the command in the command queue to be aborted, and start the ring abortion. Ring abortion stops the command ring and gives control of the commands to us. All the aborted commands are now turned into No-ops. If the ring is already stopped when the command times outs its not possible to start the ring abortion, in this case the command is turnd to No-op right away. All these changes allows us to remove the entire cancel_cmd_list code. The functions waiting for a command to finish no longer have their own timeouts. They will wait either until the command completes normally, or until the whole command abortion is done. Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-05-09 00:26:03 +08:00
}
/* mark this command to be cancelled */
xhci->current_cmd->status = COMP_COMMAND_ABORTED;
xhci: rework command timeout and cancellation, Use one timer to control command timeout. start/kick the timer every time a command is completed and a new command is waiting, or a new command is added to a empty list. If the timer runs out, then tag the current command as "aborted", and start the xhci command abortion process. Previously each function that submitted a command had its own timer. If that command timed out, a new command structure for the command was created and it was put on a cancel_cmd_list list, then a pci write to abort the command ring was issued. when the ring was aborted, it checked if the current command was the one to be canceled, later when the ring was stopped the driver got ownership of the TRBs in the command ring, compared then to the TRBs in the cancel_cmd_list, and turned them into No-ops. Now, instead, at timeout we tag the status of the command in the command queue to be aborted, and start the ring abortion. Ring abortion stops the command ring and gives control of the commands to us. All the aborted commands are now turned into No-ops. If the ring is already stopped when the command times outs its not possible to start the ring abortion, in this case the command is turnd to No-op right away. All these changes allows us to remove the entire cancel_cmd_list code. The functions waiting for a command to finish no longer have their own timeouts. They will wait either until the command completes normally, or until the whole command abortion is done. Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-05-09 00:26:03 +08:00
/* Make sure command ring is running before aborting it */
hw_ring_state = xhci_read_64(xhci, &xhci->op_regs->cmd_ring);
if (hw_ring_state == ~(u64)0) {
xhci_hc_died(xhci);
goto time_out_completed;
}
xhci: rework command timeout and cancellation, Use one timer to control command timeout. start/kick the timer every time a command is completed and a new command is waiting, or a new command is added to a empty list. If the timer runs out, then tag the current command as "aborted", and start the xhci command abortion process. Previously each function that submitted a command had its own timer. If that command timed out, a new command structure for the command was created and it was put on a cancel_cmd_list list, then a pci write to abort the command ring was issued. when the ring was aborted, it checked if the current command was the one to be canceled, later when the ring was stopped the driver got ownership of the TRBs in the command ring, compared then to the TRBs in the cancel_cmd_list, and turned them into No-ops. Now, instead, at timeout we tag the status of the command in the command queue to be aborted, and start the ring abortion. Ring abortion stops the command ring and gives control of the commands to us. All the aborted commands are now turned into No-ops. If the ring is already stopped when the command times outs its not possible to start the ring abortion, in this case the command is turnd to No-op right away. All these changes allows us to remove the entire cancel_cmd_list code. The functions waiting for a command to finish no longer have their own timeouts. They will wait either until the command completes normally, or until the whole command abortion is done. Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-05-09 00:26:03 +08:00
if ((xhci->cmd_ring_state & CMD_RING_STATE_RUNNING) &&
(hw_ring_state & CMD_RING_RUNNING)) {
/* Prevent new doorbell, and start command abort */
xhci->cmd_ring_state = CMD_RING_STATE_ABORTED;
xhci: rework command timeout and cancellation, Use one timer to control command timeout. start/kick the timer every time a command is completed and a new command is waiting, or a new command is added to a empty list. If the timer runs out, then tag the current command as "aborted", and start the xhci command abortion process. Previously each function that submitted a command had its own timer. If that command timed out, a new command structure for the command was created and it was put on a cancel_cmd_list list, then a pci write to abort the command ring was issued. when the ring was aborted, it checked if the current command was the one to be canceled, later when the ring was stopped the driver got ownership of the TRBs in the command ring, compared then to the TRBs in the cancel_cmd_list, and turned them into No-ops. Now, instead, at timeout we tag the status of the command in the command queue to be aborted, and start the ring abortion. Ring abortion stops the command ring and gives control of the commands to us. All the aborted commands are now turned into No-ops. If the ring is already stopped when the command times outs its not possible to start the ring abortion, in this case the command is turnd to No-op right away. All these changes allows us to remove the entire cancel_cmd_list code. The functions waiting for a command to finish no longer have their own timeouts. They will wait either until the command completes normally, or until the whole command abortion is done. Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-05-09 00:26:03 +08:00
xhci_dbg(xhci, "Command timeout\n");
xhci_abort_cmd_ring(xhci, flags);
goto time_out_completed;
xhci: rework command timeout and cancellation, Use one timer to control command timeout. start/kick the timer every time a command is completed and a new command is waiting, or a new command is added to a empty list. If the timer runs out, then tag the current command as "aborted", and start the xhci command abortion process. Previously each function that submitted a command had its own timer. If that command timed out, a new command structure for the command was created and it was put on a cancel_cmd_list list, then a pci write to abort the command ring was issued. when the ring was aborted, it checked if the current command was the one to be canceled, later when the ring was stopped the driver got ownership of the TRBs in the command ring, compared then to the TRBs in the cancel_cmd_list, and turned them into No-ops. Now, instead, at timeout we tag the status of the command in the command queue to be aborted, and start the ring abortion. Ring abortion stops the command ring and gives control of the commands to us. All the aborted commands are now turned into No-ops. If the ring is already stopped when the command times outs its not possible to start the ring abortion, in this case the command is turnd to No-op right away. All these changes allows us to remove the entire cancel_cmd_list code. The functions waiting for a command to finish no longer have their own timeouts. They will wait either until the command completes normally, or until the whole command abortion is done. Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-05-09 00:26:03 +08:00
}
/* host removed. Bail out */
if (xhci->xhc_state & XHCI_STATE_REMOVING) {
xhci_dbg(xhci, "host removed, ring start fail?\n");
xhci_cleanup_command_queue(xhci);
goto time_out_completed;
}
xhci: rework command timeout and cancellation, Use one timer to control command timeout. start/kick the timer every time a command is completed and a new command is waiting, or a new command is added to a empty list. If the timer runs out, then tag the current command as "aborted", and start the xhci command abortion process. Previously each function that submitted a command had its own timer. If that command timed out, a new command structure for the command was created and it was put on a cancel_cmd_list list, then a pci write to abort the command ring was issued. when the ring was aborted, it checked if the current command was the one to be canceled, later when the ring was stopped the driver got ownership of the TRBs in the command ring, compared then to the TRBs in the cancel_cmd_list, and turned them into No-ops. Now, instead, at timeout we tag the status of the command in the command queue to be aborted, and start the ring abortion. Ring abortion stops the command ring and gives control of the commands to us. All the aborted commands are now turned into No-ops. If the ring is already stopped when the command times outs its not possible to start the ring abortion, in this case the command is turnd to No-op right away. All these changes allows us to remove the entire cancel_cmd_list code. The functions waiting for a command to finish no longer have their own timeouts. They will wait either until the command completes normally, or until the whole command abortion is done. Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-05-09 00:26:03 +08:00
/* command timeout on stopped ring, ring can't be aborted */
xhci_dbg(xhci, "Command timeout on stopped ring\n");
xhci_handle_stopped_cmd_ring(xhci, xhci->current_cmd);
time_out_completed:
xhci: rework command timeout and cancellation, Use one timer to control command timeout. start/kick the timer every time a command is completed and a new command is waiting, or a new command is added to a empty list. If the timer runs out, then tag the current command as "aborted", and start the xhci command abortion process. Previously each function that submitted a command had its own timer. If that command timed out, a new command structure for the command was created and it was put on a cancel_cmd_list list, then a pci write to abort the command ring was issued. when the ring was aborted, it checked if the current command was the one to be canceled, later when the ring was stopped the driver got ownership of the TRBs in the command ring, compared then to the TRBs in the cancel_cmd_list, and turned them into No-ops. Now, instead, at timeout we tag the status of the command in the command queue to be aborted, and start the ring abortion. Ring abortion stops the command ring and gives control of the commands to us. All the aborted commands are now turned into No-ops. If the ring is already stopped when the command times outs its not possible to start the ring abortion, in this case the command is turnd to No-op right away. All these changes allows us to remove the entire cancel_cmd_list code. The functions waiting for a command to finish no longer have their own timeouts. They will wait either until the command completes normally, or until the whole command abortion is done. Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-05-09 00:26:03 +08:00
spin_unlock_irqrestore(&xhci->lock, flags);
return;
}
static void handle_cmd_completion(struct xhci_hcd *xhci,
struct xhci_event_cmd *event)
{
int slot_id = TRB_TO_SLOT_ID(le32_to_cpu(event->flags));
u64 cmd_dma;
dma_addr_t cmd_dequeue_dma;
u32 cmd_comp_code;
union xhci_trb *cmd_trb;
struct xhci_command *cmd;
u32 cmd_type;
cmd_dma = le64_to_cpu(event->cmd_trb);
cmd_trb = xhci->cmd_ring->dequeue;
trace_xhci_handle_command(xhci->cmd_ring, &cmd_trb->generic);
cmd_dequeue_dma = xhci_trb_virt_to_dma(xhci->cmd_ring->deq_seg,
cmd_trb);
/*
* Check whether the completion event is for our internal kept
* command.
*/
if (!cmd_dequeue_dma || cmd_dma != (u64)cmd_dequeue_dma) {
xhci_warn(xhci,
"ERROR mismatched command completion event\n");
return;
}
cmd = list_first_entry(&xhci->cmd_list, struct xhci_command, cmd_list);
cancel_delayed_work(&xhci->cmd_timer);
xhci: rework command timeout and cancellation, Use one timer to control command timeout. start/kick the timer every time a command is completed and a new command is waiting, or a new command is added to a empty list. If the timer runs out, then tag the current command as "aborted", and start the xhci command abortion process. Previously each function that submitted a command had its own timer. If that command timed out, a new command structure for the command was created and it was put on a cancel_cmd_list list, then a pci write to abort the command ring was issued. when the ring was aborted, it checked if the current command was the one to be canceled, later when the ring was stopped the driver got ownership of the TRBs in the command ring, compared then to the TRBs in the cancel_cmd_list, and turned them into No-ops. Now, instead, at timeout we tag the status of the command in the command queue to be aborted, and start the ring abortion. Ring abortion stops the command ring and gives control of the commands to us. All the aborted commands are now turned into No-ops. If the ring is already stopped when the command times outs its not possible to start the ring abortion, in this case the command is turnd to No-op right away. All these changes allows us to remove the entire cancel_cmd_list code. The functions waiting for a command to finish no longer have their own timeouts. They will wait either until the command completes normally, or until the whole command abortion is done. Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-05-09 00:26:03 +08:00
cmd_comp_code = GET_COMP_CODE(le32_to_cpu(event->status));
xhci: rework command timeout and cancellation, Use one timer to control command timeout. start/kick the timer every time a command is completed and a new command is waiting, or a new command is added to a empty list. If the timer runs out, then tag the current command as "aborted", and start the xhci command abortion process. Previously each function that submitted a command had its own timer. If that command timed out, a new command structure for the command was created and it was put on a cancel_cmd_list list, then a pci write to abort the command ring was issued. when the ring was aborted, it checked if the current command was the one to be canceled, later when the ring was stopped the driver got ownership of the TRBs in the command ring, compared then to the TRBs in the cancel_cmd_list, and turned them into No-ops. Now, instead, at timeout we tag the status of the command in the command queue to be aborted, and start the ring abortion. Ring abortion stops the command ring and gives control of the commands to us. All the aborted commands are now turned into No-ops. If the ring is already stopped when the command times outs its not possible to start the ring abortion, in this case the command is turnd to No-op right away. All these changes allows us to remove the entire cancel_cmd_list code. The functions waiting for a command to finish no longer have their own timeouts. They will wait either until the command completes normally, or until the whole command abortion is done. Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-05-09 00:26:03 +08:00
/* If CMD ring stopped we own the trbs between enqueue and dequeue */
if (cmd_comp_code == COMP_COMMAND_RING_STOPPED) {
complete_all(&xhci->cmd_ring_stop_completion);
xhci: rework command timeout and cancellation, Use one timer to control command timeout. start/kick the timer every time a command is completed and a new command is waiting, or a new command is added to a empty list. If the timer runs out, then tag the current command as "aborted", and start the xhci command abortion process. Previously each function that submitted a command had its own timer. If that command timed out, a new command structure for the command was created and it was put on a cancel_cmd_list list, then a pci write to abort the command ring was issued. when the ring was aborted, it checked if the current command was the one to be canceled, later when the ring was stopped the driver got ownership of the TRBs in the command ring, compared then to the TRBs in the cancel_cmd_list, and turned them into No-ops. Now, instead, at timeout we tag the status of the command in the command queue to be aborted, and start the ring abortion. Ring abortion stops the command ring and gives control of the commands to us. All the aborted commands are now turned into No-ops. If the ring is already stopped when the command times outs its not possible to start the ring abortion, in this case the command is turnd to No-op right away. All these changes allows us to remove the entire cancel_cmd_list code. The functions waiting for a command to finish no longer have their own timeouts. They will wait either until the command completes normally, or until the whole command abortion is done. Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-05-09 00:26:03 +08:00
return;
}
if (cmd->command_trb != xhci->cmd_ring->dequeue) {
xhci_err(xhci,
"Command completion event does not match command\n");
return;
}
xhci: rework command timeout and cancellation, Use one timer to control command timeout. start/kick the timer every time a command is completed and a new command is waiting, or a new command is added to a empty list. If the timer runs out, then tag the current command as "aborted", and start the xhci command abortion process. Previously each function that submitted a command had its own timer. If that command timed out, a new command structure for the command was created and it was put on a cancel_cmd_list list, then a pci write to abort the command ring was issued. when the ring was aborted, it checked if the current command was the one to be canceled, later when the ring was stopped the driver got ownership of the TRBs in the command ring, compared then to the TRBs in the cancel_cmd_list, and turned them into No-ops. Now, instead, at timeout we tag the status of the command in the command queue to be aborted, and start the ring abortion. Ring abortion stops the command ring and gives control of the commands to us. All the aborted commands are now turned into No-ops. If the ring is already stopped when the command times outs its not possible to start the ring abortion, in this case the command is turnd to No-op right away. All these changes allows us to remove the entire cancel_cmd_list code. The functions waiting for a command to finish no longer have their own timeouts. They will wait either until the command completes normally, or until the whole command abortion is done. Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-05-09 00:26:03 +08:00
/*
* Host aborted the command ring, check if the current command was
* supposed to be aborted, otherwise continue normally.
* The command ring is stopped now, but the xHC will issue a Command
* Ring Stopped event which will cause us to restart it.
*/
if (cmd_comp_code == COMP_COMMAND_ABORTED) {
xhci: rework command timeout and cancellation, Use one timer to control command timeout. start/kick the timer every time a command is completed and a new command is waiting, or a new command is added to a empty list. If the timer runs out, then tag the current command as "aborted", and start the xhci command abortion process. Previously each function that submitted a command had its own timer. If that command timed out, a new command structure for the command was created and it was put on a cancel_cmd_list list, then a pci write to abort the command ring was issued. when the ring was aborted, it checked if the current command was the one to be canceled, later when the ring was stopped the driver got ownership of the TRBs in the command ring, compared then to the TRBs in the cancel_cmd_list, and turned them into No-ops. Now, instead, at timeout we tag the status of the command in the command queue to be aborted, and start the ring abortion. Ring abortion stops the command ring and gives control of the commands to us. All the aborted commands are now turned into No-ops. If the ring is already stopped when the command times outs its not possible to start the ring abortion, in this case the command is turnd to No-op right away. All these changes allows us to remove the entire cancel_cmd_list code. The functions waiting for a command to finish no longer have their own timeouts. They will wait either until the command completes normally, or until the whole command abortion is done. Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-05-09 00:26:03 +08:00
xhci->cmd_ring_state = CMD_RING_STATE_STOPPED;
if (cmd->status == COMP_COMMAND_ABORTED) {
if (xhci->current_cmd == cmd)
xhci->current_cmd = NULL;
xhci: rework command timeout and cancellation, Use one timer to control command timeout. start/kick the timer every time a command is completed and a new command is waiting, or a new command is added to a empty list. If the timer runs out, then tag the current command as "aborted", and start the xhci command abortion process. Previously each function that submitted a command had its own timer. If that command timed out, a new command structure for the command was created and it was put on a cancel_cmd_list list, then a pci write to abort the command ring was issued. when the ring was aborted, it checked if the current command was the one to be canceled, later when the ring was stopped the driver got ownership of the TRBs in the command ring, compared then to the TRBs in the cancel_cmd_list, and turned them into No-ops. Now, instead, at timeout we tag the status of the command in the command queue to be aborted, and start the ring abortion. Ring abortion stops the command ring and gives control of the commands to us. All the aborted commands are now turned into No-ops. If the ring is already stopped when the command times outs its not possible to start the ring abortion, in this case the command is turnd to No-op right away. All these changes allows us to remove the entire cancel_cmd_list code. The functions waiting for a command to finish no longer have their own timeouts. They will wait either until the command completes normally, or until the whole command abortion is done. Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-05-09 00:26:03 +08:00
goto event_handled;
}
}
cmd_type = TRB_FIELD_TO_TYPE(le32_to_cpu(cmd_trb->generic.field[3]));
switch (cmd_type) {
case TRB_ENABLE_SLOT:
xhci_handle_cmd_enable_slot(xhci, slot_id, cmd, cmd_comp_code);
break;
case TRB_DISABLE_SLOT:
xhci_handle_cmd_disable_slot(xhci, slot_id);
break;
case TRB_CONFIG_EP:
if (!cmd->completion)
xhci_handle_cmd_config_ep(xhci, slot_id, event,
cmd_comp_code);
USB: xhci: Bandwidth allocation support Since the xHCI host controller hardware (xHC) has an internal schedule, it needs a better representation of what devices are consuming bandwidth on the bus. Each device is represented by a device context, with data about the device, endpoints, and pointers to each endpoint ring. We need to update the endpoint information for a device context before a new configuration or alternate interface setting is selected. We setup an input device context with modified endpoint information and newly allocated endpoint rings, and then submit a Configure Endpoint Command to the hardware. The host controller can reject the new configuration if it exceeds the bus bandwidth, or the host controller doesn't have enough internal resources for the configuration. If the command fails, we still have the older device context with the previous configuration. If the command succeeds, we free the old endpoint rings. The root hub isn't a real device, so always say yes to any bandwidth changes for it. The USB core will enable, disable, and then enable endpoint 0 several times during the initialization sequence. The device will always have an endpoint ring for endpoint 0 and bandwidth allocated for that, unless the device is disconnected or gets a SetAddress 0 request. So we don't pay attention for when xhci_check_bandwidth() is called for a re-add of endpoint 0. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-28 10:58:38 +08:00
break;
case TRB_EVAL_CONTEXT:
break;
case TRB_ADDR_DEV:
xhci_handle_cmd_addr_dev(xhci, slot_id);
break;
case TRB_STOP_RING:
WARN_ON(slot_id != TRB_TO_SLOT_ID(
le32_to_cpu(cmd_trb->generic.field[3])));
if (!cmd->completion)
xhci_handle_cmd_stop_ep(xhci, slot_id, cmd_trb, event);
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
break;
case TRB_SET_DEQ:
WARN_ON(slot_id != TRB_TO_SLOT_ID(
le32_to_cpu(cmd_trb->generic.field[3])));
xhci_handle_cmd_set_deq(xhci, slot_id, cmd_trb, cmd_comp_code);
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
break;
case TRB_CMD_NOOP:
xhci: rework command timeout and cancellation, Use one timer to control command timeout. start/kick the timer every time a command is completed and a new command is waiting, or a new command is added to a empty list. If the timer runs out, then tag the current command as "aborted", and start the xhci command abortion process. Previously each function that submitted a command had its own timer. If that command timed out, a new command structure for the command was created and it was put on a cancel_cmd_list list, then a pci write to abort the command ring was issued. when the ring was aborted, it checked if the current command was the one to be canceled, later when the ring was stopped the driver got ownership of the TRBs in the command ring, compared then to the TRBs in the cancel_cmd_list, and turned them into No-ops. Now, instead, at timeout we tag the status of the command in the command queue to be aborted, and start the ring abortion. Ring abortion stops the command ring and gives control of the commands to us. All the aborted commands are now turned into No-ops. If the ring is already stopped when the command times outs its not possible to start the ring abortion, in this case the command is turnd to No-op right away. All these changes allows us to remove the entire cancel_cmd_list code. The functions waiting for a command to finish no longer have their own timeouts. They will wait either until the command completes normally, or until the whole command abortion is done. Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-05-09 00:26:03 +08:00
/* Is this an aborted command turned to NO-OP? */
if (cmd->status == COMP_COMMAND_RING_STOPPED)
cmd_comp_code = COMP_COMMAND_RING_STOPPED;
break;
case TRB_RESET_EP:
WARN_ON(slot_id != TRB_TO_SLOT_ID(
le32_to_cpu(cmd_trb->generic.field[3])));
xhci_handle_cmd_reset_ep(xhci, slot_id, cmd_trb, cmd_comp_code);
break;
case TRB_RESET_DEV:
/* SLOT_ID field in reset device cmd completion event TRB is 0.
* Use the SLOT_ID from the command TRB instead (xhci 4.6.11)
*/
slot_id = TRB_TO_SLOT_ID(
le32_to_cpu(cmd_trb->generic.field[3]));
xhci_handle_cmd_reset_dev(xhci, slot_id, event);
break;
case TRB_NEC_GET_FW:
xhci_handle_cmd_nec_get_fw(xhci, event);
break;
default:
/* Skip over unknown commands on the event ring */
xhci_info(xhci, "INFO unknown command type %d\n", cmd_type);
break;
}
xhci: rework command timeout and cancellation, Use one timer to control command timeout. start/kick the timer every time a command is completed and a new command is waiting, or a new command is added to a empty list. If the timer runs out, then tag the current command as "aborted", and start the xhci command abortion process. Previously each function that submitted a command had its own timer. If that command timed out, a new command structure for the command was created and it was put on a cancel_cmd_list list, then a pci write to abort the command ring was issued. when the ring was aborted, it checked if the current command was the one to be canceled, later when the ring was stopped the driver got ownership of the TRBs in the command ring, compared then to the TRBs in the cancel_cmd_list, and turned them into No-ops. Now, instead, at timeout we tag the status of the command in the command queue to be aborted, and start the ring abortion. Ring abortion stops the command ring and gives control of the commands to us. All the aborted commands are now turned into No-ops. If the ring is already stopped when the command times outs its not possible to start the ring abortion, in this case the command is turnd to No-op right away. All these changes allows us to remove the entire cancel_cmd_list code. The functions waiting for a command to finish no longer have their own timeouts. They will wait either until the command completes normally, or until the whole command abortion is done. Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-05-09 00:26:03 +08:00
/* restart timer if this wasn't the last command */
if (!list_is_singular(&xhci->cmd_list)) {
xhci->current_cmd = list_first_entry(&cmd->cmd_list,
struct xhci_command, cmd_list);
xhci_mod_cmd_timer(xhci, XHCI_CMD_DEFAULT_TIMEOUT);
} else if (xhci->current_cmd == cmd) {
xhci->current_cmd = NULL;
xhci: rework command timeout and cancellation, Use one timer to control command timeout. start/kick the timer every time a command is completed and a new command is waiting, or a new command is added to a empty list. If the timer runs out, then tag the current command as "aborted", and start the xhci command abortion process. Previously each function that submitted a command had its own timer. If that command timed out, a new command structure for the command was created and it was put on a cancel_cmd_list list, then a pci write to abort the command ring was issued. when the ring was aborted, it checked if the current command was the one to be canceled, later when the ring was stopped the driver got ownership of the TRBs in the command ring, compared then to the TRBs in the cancel_cmd_list, and turned them into No-ops. Now, instead, at timeout we tag the status of the command in the command queue to be aborted, and start the ring abortion. Ring abortion stops the command ring and gives control of the commands to us. All the aborted commands are now turned into No-ops. If the ring is already stopped when the command times outs its not possible to start the ring abortion, in this case the command is turnd to No-op right away. All these changes allows us to remove the entire cancel_cmd_list code. The functions waiting for a command to finish no longer have their own timeouts. They will wait either until the command completes normally, or until the whole command abortion is done. Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-05-09 00:26:03 +08:00
}
event_handled:
xhci_complete_del_and_free_cmd(cmd, cmd_comp_code);
inc_deq(xhci, xhci->cmd_ring);
}
static void handle_vendor_event(struct xhci_hcd *xhci,
union xhci_trb *event)
{
u32 trb_type;
trb_type = TRB_FIELD_TO_TYPE(le32_to_cpu(event->generic.field[3]));
xhci_dbg(xhci, "Vendor specific event TRB type = %u\n", trb_type);
if (trb_type == TRB_NEC_CMD_COMP && (xhci->quirks & XHCI_NEC_HOST))
handle_cmd_completion(xhci, &event->event_cmd);
}
static void handle_device_notification(struct xhci_hcd *xhci,
union xhci_trb *event)
{
u32 slot_id;
USB/xHCI: Support device-initiated USB 3.0 resume. USB 3.0 hubs don't have a port suspend change bit (that bit is now reserved). Instead, when a host-initiated resume finishes, the hub sets the port link state change bit. When a USB 3.0 device initiates remote wakeup, the parent hubs with their upstream links in U3 will pass the LFPS up the chain. The first hub that has an upstream link in U0 (which may be the roothub) will reflect that LFPS back down the path to the device. However, the parent hubs in the resumed path will not set their link state change bit. Instead, the device that initiated the resume has to send an asynchronous "Function Wake" Device Notification up to the host controller. Therefore, we need a way to notify the USB core of a device resume without going through the normal hub URB completion method. First, make the xHCI roothub act like an external USB 3.0 hub and not pass up the port link state change bit when a device-initiated resume finishes. Introduce a new xHCI bit field, port_remote_wakeup, so that we can tell the difference between a port coming out of the U3Exit state (host-initiated resume) and the RExit state (ending state of device-initiated resume). Since the USB core can't tell whether a port on a hub has resumed by looking at the Hub Status buffer, we need to introduce a bitfield, wakeup_bits, that indicates which ports have resumed. When the xHCI driver notices a port finishing a device-initiated resume, we call into a new USB core function, usb_wakeup_notification(), that will set the right bit in wakeup_bits, and kick khubd for that hub. We also call usb_wakeup_notification() when the Function Wake Device Notification is received by the xHCI driver. This covers the case where the link between the roothub and the first-tier hub is in U0, and the hub reflects the resume signaling back to the device without giving any indication it has done so until the device sends the Function Wake notification. Change the code in khubd that handles the remote wakeup to look at the state the USB core thinks the device is in, and handle the remote wakeup if the port's wakeup bit is set. This patch only takes care of the case where the device is attached directly to the roothub, or the USB 3.0 hub that is attached to the root hub is the device sending the Function Wake Device Notification (e.g. because a new USB device was attached). The other cases will be covered in a second patch. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
2011-11-15 10:00:01 +08:00
struct usb_device *udev;
slot_id = TRB_TO_SLOT_ID(le32_to_cpu(event->generic.field[3]));
USB/xHCI: Support device-initiated USB 3.0 resume. USB 3.0 hubs don't have a port suspend change bit (that bit is now reserved). Instead, when a host-initiated resume finishes, the hub sets the port link state change bit. When a USB 3.0 device initiates remote wakeup, the parent hubs with their upstream links in U3 will pass the LFPS up the chain. The first hub that has an upstream link in U0 (which may be the roothub) will reflect that LFPS back down the path to the device. However, the parent hubs in the resumed path will not set their link state change bit. Instead, the device that initiated the resume has to send an asynchronous "Function Wake" Device Notification up to the host controller. Therefore, we need a way to notify the USB core of a device resume without going through the normal hub URB completion method. First, make the xHCI roothub act like an external USB 3.0 hub and not pass up the port link state change bit when a device-initiated resume finishes. Introduce a new xHCI bit field, port_remote_wakeup, so that we can tell the difference between a port coming out of the U3Exit state (host-initiated resume) and the RExit state (ending state of device-initiated resume). Since the USB core can't tell whether a port on a hub has resumed by looking at the Hub Status buffer, we need to introduce a bitfield, wakeup_bits, that indicates which ports have resumed. When the xHCI driver notices a port finishing a device-initiated resume, we call into a new USB core function, usb_wakeup_notification(), that will set the right bit in wakeup_bits, and kick khubd for that hub. We also call usb_wakeup_notification() when the Function Wake Device Notification is received by the xHCI driver. This covers the case where the link between the roothub and the first-tier hub is in U0, and the hub reflects the resume signaling back to the device without giving any indication it has done so until the device sends the Function Wake notification. Change the code in khubd that handles the remote wakeup to look at the state the USB core thinks the device is in, and handle the remote wakeup if the port's wakeup bit is set. This patch only takes care of the case where the device is attached directly to the roothub, or the USB 3.0 hub that is attached to the root hub is the device sending the Function Wake Device Notification (e.g. because a new USB device was attached). The other cases will be covered in a second patch. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
2011-11-15 10:00:01 +08:00
if (!xhci->devs[slot_id]) {
xhci_warn(xhci, "Device Notification event for "
"unused slot %u\n", slot_id);
USB/xHCI: Support device-initiated USB 3.0 resume. USB 3.0 hubs don't have a port suspend change bit (that bit is now reserved). Instead, when a host-initiated resume finishes, the hub sets the port link state change bit. When a USB 3.0 device initiates remote wakeup, the parent hubs with their upstream links in U3 will pass the LFPS up the chain. The first hub that has an upstream link in U0 (which may be the roothub) will reflect that LFPS back down the path to the device. However, the parent hubs in the resumed path will not set their link state change bit. Instead, the device that initiated the resume has to send an asynchronous "Function Wake" Device Notification up to the host controller. Therefore, we need a way to notify the USB core of a device resume without going through the normal hub URB completion method. First, make the xHCI roothub act like an external USB 3.0 hub and not pass up the port link state change bit when a device-initiated resume finishes. Introduce a new xHCI bit field, port_remote_wakeup, so that we can tell the difference between a port coming out of the U3Exit state (host-initiated resume) and the RExit state (ending state of device-initiated resume). Since the USB core can't tell whether a port on a hub has resumed by looking at the Hub Status buffer, we need to introduce a bitfield, wakeup_bits, that indicates which ports have resumed. When the xHCI driver notices a port finishing a device-initiated resume, we call into a new USB core function, usb_wakeup_notification(), that will set the right bit in wakeup_bits, and kick khubd for that hub. We also call usb_wakeup_notification() when the Function Wake Device Notification is received by the xHCI driver. This covers the case where the link between the roothub and the first-tier hub is in U0, and the hub reflects the resume signaling back to the device without giving any indication it has done so until the device sends the Function Wake notification. Change the code in khubd that handles the remote wakeup to look at the state the USB core thinks the device is in, and handle the remote wakeup if the port's wakeup bit is set. This patch only takes care of the case where the device is attached directly to the roothub, or the USB 3.0 hub that is attached to the root hub is the device sending the Function Wake Device Notification (e.g. because a new USB device was attached). The other cases will be covered in a second patch. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
2011-11-15 10:00:01 +08:00
return;
}
xhci_dbg(xhci, "Device Wake Notification event for slot ID %u\n",
slot_id);
udev = xhci->devs[slot_id]->udev;
if (udev && udev->parent)
usb_wakeup_notification(udev->parent, udev->portnum);
}
/*
* Quirk hanlder for errata seen on Cavium ThunderX2 processor XHCI
* Controller.
* As per ThunderX2errata-129 USB 2 device may come up as USB 1
* If a connection to a USB 1 device is followed by another connection
* to a USB 2 device.
*
* Reset the PHY after the USB device is disconnected if device speed
* is less than HCD_USB3.
* Retry the reset sequence max of 4 times checking the PLL lock status.
*
*/
static void xhci_cavium_reset_phy_quirk(struct xhci_hcd *xhci)
{
struct usb_hcd *hcd = xhci_to_hcd(xhci);
u32 pll_lock_check;
u32 retry_count = 4;
do {
/* Assert PHY reset */
writel(0x6F, hcd->regs + 0x1048);
udelay(10);
/* De-assert the PHY reset */
writel(0x7F, hcd->regs + 0x1048);
udelay(200);
pll_lock_check = readl(hcd->regs + 0x1070);
} while (!(pll_lock_check & 0x1) && --retry_count);
}
static void handle_port_status(struct xhci_hcd *xhci,
union xhci_trb *event)
{
xhci: Register second xHCI roothub. This patch changes the xHCI driver to allocate two roothubs. This touches the driver initialization and shutdown paths, roothub emulation code, and port status change event handlers. This is a rather large patch, but it can't be broken up, or it would break git-bisect. Make the xHCI driver register its own PCI probe function. This will call the USB core to create the USB 2.0 roothub, and then create the USB 3.0 roothub. This gets the code for registering a shared roothub out of the USB core, and allows other HCDs later to decide if and how many shared roothubs they want to allocate. Make sure the xHCI's reset method marks the xHCI host controller's primary roothub as the USB 2.0 roothub. This ensures that the high speed bus will be processed first when the PCI device is resumed, and any USB 3.0 devices that have migrated over to high speed will migrate back after being reset. This ensures that USB persist works with these odd devices. The reset method will also mark the xHCI USB2 roothub as having an integrated TT. Like EHCI host controllers with a "rate matching hub" the xHCI USB 2.0 roothub doesn't have an OHCI or UHCI companion controller. It doesn't really have a TT, but we'll lie and say it has an integrated TT. We need to do this because the USB core will reject LS/FS devices under a HS hub without a TT. Other details: ------------- The roothub emulation code is changed to return the correct number of ports for the two roothubs. For the USB 3.0 roothub, it only reports the USB 3.0 ports. For the USB 2.0 roothub, it reports all the LS/FS/HS ports. The code to disable a port now checks the speed of the roothub, and refuses to disable SuperSpeed ports under the USB 3.0 roothub. The code for initializing a new device context must be changed to set the proper roothub port number. Since we've split the xHCI host into two roothubs, we can't just use the port number in the ancestor hub. Instead, we loop through the array of hardware port status register speeds and find the Nth port with a similar speed. The port status change event handler is updated to figure out whether the port that reported the change is a USB 3.0 port, or a non-SuperSpeed port. Once it figures out the port speed, it kicks the proper roothub. The function to find a slot ID based on the port index is updated to take into account that the two roothubs will have over-lapping port indexes. It checks that the virtual device with a matching port index is the same speed as the passed in roothub. There's also changes to the driver initialization and shutdown paths: 1. Make sure that the xhci_hcd pointer is shared across the two usb_hcd structures. The xhci_hcd pointer is allocated and the registers are mapped in when xhci_pci_setup() is called with the primary HCD. When xhci_pci_setup() is called with the non-primary HCD, the xhci_hcd pointer is stored. 2. Make sure to set the sg_tablesize for both usb_hcd structures. Set the PCI DMA mask for the non-primary HCD to allow for 64-bit or 32-bit DMA. (The PCI DMA mask is set from the primary HCD further down in the xhci_pci_setup() function.) 3. Ensure that the host controller doesn't start kicking khubd in response to port status changes before both usb_hcd structures are registered. xhci_run() only starts the xHC running once it has been called with the non-primary roothub. Similarly, the xhci_stop() function only halts the host controller when it is called with the non-primary HCD. Then on the second call, it resets and cleans up the MSI-X irqs. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
2010-12-17 03:21:10 +08:00
struct usb_hcd *hcd;
u32 port_id;
u32 portsc, cmd_reg;
int max_ports;
int slot_id;
unsigned int hcd_portnum;
struct xhci_bus_state *bus_state;
bool bogus_port_status = false;
struct xhci_port *port;
/* Port status change events always have a successful completion code */
if (GET_COMP_CODE(le32_to_cpu(event->generic.field[2])) != COMP_SUCCESS)
xhci_warn(xhci,
"WARN: xHC returned failed port status event\n");
port_id = GET_PORT_ID(le32_to_cpu(event->generic.field[0]));
max_ports = HCS_MAX_PORTS(xhci->hcs_params1);
if ((port_id <= 0) || (port_id > max_ports)) {
xhci_warn(xhci, "Port change event with invalid port ID %d\n",
port_id);
inc_deq(xhci, xhci->event_ring);
return;
}
port = &xhci->hw_ports[port_id - 1];
if (!port || !port->rhub || port->hcd_portnum == DUPLICATE_ENTRY) {
xhci_warn(xhci, "Port change event, no port for port ID %u\n",
port_id);
bogus_port_status = true;
xhci: Register second xHCI roothub. This patch changes the xHCI driver to allocate two roothubs. This touches the driver initialization and shutdown paths, roothub emulation code, and port status change event handlers. This is a rather large patch, but it can't be broken up, or it would break git-bisect. Make the xHCI driver register its own PCI probe function. This will call the USB core to create the USB 2.0 roothub, and then create the USB 3.0 roothub. This gets the code for registering a shared roothub out of the USB core, and allows other HCDs later to decide if and how many shared roothubs they want to allocate. Make sure the xHCI's reset method marks the xHCI host controller's primary roothub as the USB 2.0 roothub. This ensures that the high speed bus will be processed first when the PCI device is resumed, and any USB 3.0 devices that have migrated over to high speed will migrate back after being reset. This ensures that USB persist works with these odd devices. The reset method will also mark the xHCI USB2 roothub as having an integrated TT. Like EHCI host controllers with a "rate matching hub" the xHCI USB 2.0 roothub doesn't have an OHCI or UHCI companion controller. It doesn't really have a TT, but we'll lie and say it has an integrated TT. We need to do this because the USB core will reject LS/FS devices under a HS hub without a TT. Other details: ------------- The roothub emulation code is changed to return the correct number of ports for the two roothubs. For the USB 3.0 roothub, it only reports the USB 3.0 ports. For the USB 2.0 roothub, it reports all the LS/FS/HS ports. The code to disable a port now checks the speed of the roothub, and refuses to disable SuperSpeed ports under the USB 3.0 roothub. The code for initializing a new device context must be changed to set the proper roothub port number. Since we've split the xHCI host into two roothubs, we can't just use the port number in the ancestor hub. Instead, we loop through the array of hardware port status register speeds and find the Nth port with a similar speed. The port status change event handler is updated to figure out whether the port that reported the change is a USB 3.0 port, or a non-SuperSpeed port. Once it figures out the port speed, it kicks the proper roothub. The function to find a slot ID based on the port index is updated to take into account that the two roothubs will have over-lapping port indexes. It checks that the virtual device with a matching port index is the same speed as the passed in roothub. There's also changes to the driver initialization and shutdown paths: 1. Make sure that the xhci_hcd pointer is shared across the two usb_hcd structures. The xhci_hcd pointer is allocated and the registers are mapped in when xhci_pci_setup() is called with the primary HCD. When xhci_pci_setup() is called with the non-primary HCD, the xhci_hcd pointer is stored. 2. Make sure to set the sg_tablesize for both usb_hcd structures. Set the PCI DMA mask for the non-primary HCD to allow for 64-bit or 32-bit DMA. (The PCI DMA mask is set from the primary HCD further down in the xhci_pci_setup() function.) 3. Ensure that the host controller doesn't start kicking khubd in response to port status changes before both usb_hcd structures are registered. xhci_run() only starts the xHC running once it has been called with the non-primary roothub. Similarly, the xhci_stop() function only halts the host controller when it is called with the non-primary HCD. Then on the second call, it resets and cleans up the MSI-X irqs. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
2010-12-17 03:21:10 +08:00
goto cleanup;
}
/* We might get interrupts after shared_hcd is removed */
if (port->rhub == &xhci->usb3_rhub && xhci->shared_hcd == NULL) {
xhci_dbg(xhci, "ignore port event for removed USB3 hcd\n");
bogus_port_status = true;
goto cleanup;
}
hcd = port->rhub->hcd;
bus_state = &port->rhub->bus_state;
hcd_portnum = port->hcd_portnum;
portsc = readl(port->addr);
xhci_dbg(xhci, "Port change event, %d-%d, id %d, portsc: 0x%x\n",
hcd->self.busnum, hcd_portnum + 1, port_id, portsc);
trace_xhci_handle_port_status(hcd_portnum, portsc);
if (hcd->state == HC_STATE_SUSPENDED) {
xhci_dbg(xhci, "resume root hub\n");
usb_hcd_resume_root_hub(hcd);
}
if (hcd->speed >= HCD_USB3 &&
(portsc & PORT_PLS_MASK) == XDEV_INACTIVE) {
slot_id = xhci_find_slot_id_by_port(hcd, xhci, hcd_portnum + 1);
if (slot_id && xhci->devs[slot_id])
xhci->devs[slot_id]->flags |= VDEV_PORT_ERROR;
}
if ((portsc & PORT_PLC) && (portsc & PORT_PLS_MASK) == XDEV_RESUME) {
xhci_dbg(xhci, "port resume event for port %d\n", port_id);
cmd_reg = readl(&xhci->op_regs->command);
if (!(cmd_reg & CMD_RUN)) {
xhci_warn(xhci, "xHC is not running.\n");
goto cleanup;
}
if (DEV_SUPERSPEED_ANY(portsc)) {
xhci_dbg(xhci, "remote wake SS port %d\n", port_id);
USB/xHCI: Support device-initiated USB 3.0 resume. USB 3.0 hubs don't have a port suspend change bit (that bit is now reserved). Instead, when a host-initiated resume finishes, the hub sets the port link state change bit. When a USB 3.0 device initiates remote wakeup, the parent hubs with their upstream links in U3 will pass the LFPS up the chain. The first hub that has an upstream link in U0 (which may be the roothub) will reflect that LFPS back down the path to the device. However, the parent hubs in the resumed path will not set their link state change bit. Instead, the device that initiated the resume has to send an asynchronous "Function Wake" Device Notification up to the host controller. Therefore, we need a way to notify the USB core of a device resume without going through the normal hub URB completion method. First, make the xHCI roothub act like an external USB 3.0 hub and not pass up the port link state change bit when a device-initiated resume finishes. Introduce a new xHCI bit field, port_remote_wakeup, so that we can tell the difference between a port coming out of the U3Exit state (host-initiated resume) and the RExit state (ending state of device-initiated resume). Since the USB core can't tell whether a port on a hub has resumed by looking at the Hub Status buffer, we need to introduce a bitfield, wakeup_bits, that indicates which ports have resumed. When the xHCI driver notices a port finishing a device-initiated resume, we call into a new USB core function, usb_wakeup_notification(), that will set the right bit in wakeup_bits, and kick khubd for that hub. We also call usb_wakeup_notification() when the Function Wake Device Notification is received by the xHCI driver. This covers the case where the link between the roothub and the first-tier hub is in U0, and the hub reflects the resume signaling back to the device without giving any indication it has done so until the device sends the Function Wake notification. Change the code in khubd that handles the remote wakeup to look at the state the USB core thinks the device is in, and handle the remote wakeup if the port's wakeup bit is set. This patch only takes care of the case where the device is attached directly to the roothub, or the USB 3.0 hub that is attached to the root hub is the device sending the Function Wake Device Notification (e.g. because a new USB device was attached). The other cases will be covered in a second patch. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
2011-11-15 10:00:01 +08:00
/* Set a flag to say the port signaled remote wakeup,
* so we can tell the difference between the end of
* device and host initiated resume.
*/
bus_state->port_remote_wakeup |= 1 << hcd_portnum;
xhci_test_and_clear_bit(xhci, port, PORT_PLC);
xhci: fix USB3 device initiated resume race with roothub autosuspend A race in xhci USB3 remote wake handling may force device back to suspend after it initiated resume siganaling, causing a missed resume event or warm reset of device. When a USB3 link completes resume signaling and goes to enabled (UO) state a interrupt is issued and the interrupt handler will clear the bus_state->port_remote_wakeup resume flag, allowing bus suspend. If the USB3 roothub thread just finished reading port status before the interrupt, finding ports still in suspended (U3) state, but hasn't yet started suspending the hub, then the xhci interrupt handler will clear the flag that prevented roothub suspend and allow bus to suspend, forcing all port links back to suspended (U3) state. Example case: usb_runtime_suspend() # because all ports still show suspended U3 usb_suspend_both() hub_suspend(); # successful as hub->wakeup_bits not set yet ==> INTERRUPT xhci_irq() handle_port_status() clear bus_state->port_remote_wakeup usb_wakeup_notification() sets hub->wakeup_bits; kick_hub_wq() <== END INTERRUPT hcd_bus_suspend() xhci_bus_suspend() # success as port_remote_wakeup bits cleared Fix this by increasing roothub usage count during port resume to prevent roothub autosuspend, and by making sure bus_state->port_remote_wakeup flag is only cleared after resume completion is visible, i.e. after xhci roothub returned U0 or other non-U3 link state link on a get port status request. Issue rootcaused by Chiasheng Lee Cc: <stable@vger.kernel.org> Cc: Lee, Hou-hsun <hou-hsun.lee@intel.com> Reported-by: Lee, Chiasheng <chiasheng.lee@intel.com> Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Link: https://lore.kernel.org/r/20191211142007.8847-3-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-12-11 22:20:03 +08:00
usb_hcd_start_port_resume(&hcd->self, hcd_portnum);
xhci_set_link_state(xhci, port, XDEV_U0);
/* Need to wait until the next link state change
* indicates the device is actually in U0.
*/
bogus_port_status = true;
goto cleanup;
} else if (!test_bit(hcd_portnum, &bus_state->resuming_ports)) {
xhci_dbg(xhci, "resume HS port %d\n", port_id);
bus_state->resume_done[hcd_portnum] = jiffies +
msecs_to_jiffies(USB_RESUME_TIMEOUT);
set_bit(hcd_portnum, &bus_state->resuming_ports);
usb: xhci: reduce device initiated resume time variance. This patch will improve the variable auto-resume latency of an usb-port. The attempt to sync the start of root hub polling with resume time signaling finish was ruined by a later request to start immediate root hub polling. When xhci gets a port status change event interrupt due to PORT_PLC (port link state transition), linux Host controller driver drives the resume signalling on the bus for the amount of time defined by USB_REUME_TIMEOUT(40ms) macro. This 40ms delay for resume signalling is in acceptable limit, but it get worse when xhci goes for polling mode in order to detect other events on its ports and modify rh_timer timer with a variable time out of 1ms to (HZ/4)ms. drivers/usb/core/hcd.c line 799 mod_timer (&hcd->rh_timer, (jiffies/(HZ/4) + 1) * (HZ/4)). Due to above variable timeout usb auto-resume latency varies from 40ms to ~300ms. Log Snippet: ~128ms latency [ 53.112049] hub 1-0:1.0: state 7 ports 12 chg 0000 evt 0000 [ 53.229200] hub 1-0:1.0: state 7 ports 12 chg 0000 evt 0004 [ 53.240177] usb 1-2: usb wakeup-resume [ 53.240195] usb 1-2: finish resume [ 53.240357] usb usb1-port2: resume, status 0 ----------------------------------------------------------------- ~300ms latency [ 59.946620] hub 1-0:1.0: state 7 ports 12 chg 0000 evt 0000 [ 59.979341] hub 1-0:1.0: state 7 ports 12 chg 0000 evt 0000 [ 60.229342] hub 1-0:1.0: state 7 ports 12 chg 0000 evt 0004 [ 60.251321] usb 1-2: usb wakeup-resume [ 60.251335] usb 1-2: finish resume [ 60.251539] usb usb1-port2: resume, status 0 This variable resume latency can be optimized, as in case of PORT_PLC change event rh_timer has already been modified with USB_RESUME_TIMEOUT (40ms) delay,leaving the rest to GetPortStatus and started polling for root hub status (invoking usb_hcd_poll_rh_status). We can avoid polling as we have already modified rh_timer with delay of 40ms. This patch set the HCD_FLAG_POLL_RH to hcd->flags after modification of rh_timer, and avoids polling of root hub status. so rh_timer can fire after 40ms and usb device auto-resuem latency will be around 40ms. [topic and first two senctences of commit message changed -Mathias] Signed-off-by: Anshuman Gupta <anshuman.gupta@intel.com> Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-10-05 16:21:46 +08:00
/* Do the rest in GetPortStatus after resume time delay.
* Avoid polling roothub status before that so that a
* usb device auto-resume latency around ~40ms.
*/
set_bit(HCD_FLAG_POLL_RH, &hcd->flags);
mod_timer(&hcd->rh_timer,
bus_state->resume_done[hcd_portnum]);
usb_hcd_start_port_resume(&hcd->self, hcd_portnum);
usb: xhci: reduce device initiated resume time variance. This patch will improve the variable auto-resume latency of an usb-port. The attempt to sync the start of root hub polling with resume time signaling finish was ruined by a later request to start immediate root hub polling. When xhci gets a port status change event interrupt due to PORT_PLC (port link state transition), linux Host controller driver drives the resume signalling on the bus for the amount of time defined by USB_REUME_TIMEOUT(40ms) macro. This 40ms delay for resume signalling is in acceptable limit, but it get worse when xhci goes for polling mode in order to detect other events on its ports and modify rh_timer timer with a variable time out of 1ms to (HZ/4)ms. drivers/usb/core/hcd.c line 799 mod_timer (&hcd->rh_timer, (jiffies/(HZ/4) + 1) * (HZ/4)). Due to above variable timeout usb auto-resume latency varies from 40ms to ~300ms. Log Snippet: ~128ms latency [ 53.112049] hub 1-0:1.0: state 7 ports 12 chg 0000 evt 0000 [ 53.229200] hub 1-0:1.0: state 7 ports 12 chg 0000 evt 0004 [ 53.240177] usb 1-2: usb wakeup-resume [ 53.240195] usb 1-2: finish resume [ 53.240357] usb usb1-port2: resume, status 0 ----------------------------------------------------------------- ~300ms latency [ 59.946620] hub 1-0:1.0: state 7 ports 12 chg 0000 evt 0000 [ 59.979341] hub 1-0:1.0: state 7 ports 12 chg 0000 evt 0000 [ 60.229342] hub 1-0:1.0: state 7 ports 12 chg 0000 evt 0004 [ 60.251321] usb 1-2: usb wakeup-resume [ 60.251335] usb 1-2: finish resume [ 60.251539] usb usb1-port2: resume, status 0 This variable resume latency can be optimized, as in case of PORT_PLC change event rh_timer has already been modified with USB_RESUME_TIMEOUT (40ms) delay,leaving the rest to GetPortStatus and started polling for root hub status (invoking usb_hcd_poll_rh_status). We can avoid polling as we have already modified rh_timer with delay of 40ms. This patch set the HCD_FLAG_POLL_RH to hcd->flags after modification of rh_timer, and avoids polling of root hub status. so rh_timer can fire after 40ms and usb device auto-resuem latency will be around 40ms. [topic and first two senctences of commit message changed -Mathias] Signed-off-by: Anshuman Gupta <anshuman.gupta@intel.com> Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-10-05 16:21:46 +08:00
bogus_port_status = true;
}
}
if ((portsc & PORT_PLC) &&
DEV_SUPERSPEED_ANY(portsc) &&
((portsc & PORT_PLS_MASK) == XDEV_U0 ||
(portsc & PORT_PLS_MASK) == XDEV_U1 ||
(portsc & PORT_PLS_MASK) == XDEV_U2)) {
xhci_dbg(xhci, "resume SS port %d finished\n", port_id);
/* We've just brought the device into U0/1/2 through either the
USB/xHCI: Support device-initiated USB 3.0 resume. USB 3.0 hubs don't have a port suspend change bit (that bit is now reserved). Instead, when a host-initiated resume finishes, the hub sets the port link state change bit. When a USB 3.0 device initiates remote wakeup, the parent hubs with their upstream links in U3 will pass the LFPS up the chain. The first hub that has an upstream link in U0 (which may be the roothub) will reflect that LFPS back down the path to the device. However, the parent hubs in the resumed path will not set their link state change bit. Instead, the device that initiated the resume has to send an asynchronous "Function Wake" Device Notification up to the host controller. Therefore, we need a way to notify the USB core of a device resume without going through the normal hub URB completion method. First, make the xHCI roothub act like an external USB 3.0 hub and not pass up the port link state change bit when a device-initiated resume finishes. Introduce a new xHCI bit field, port_remote_wakeup, so that we can tell the difference between a port coming out of the U3Exit state (host-initiated resume) and the RExit state (ending state of device-initiated resume). Since the USB core can't tell whether a port on a hub has resumed by looking at the Hub Status buffer, we need to introduce a bitfield, wakeup_bits, that indicates which ports have resumed. When the xHCI driver notices a port finishing a device-initiated resume, we call into a new USB core function, usb_wakeup_notification(), that will set the right bit in wakeup_bits, and kick khubd for that hub. We also call usb_wakeup_notification() when the Function Wake Device Notification is received by the xHCI driver. This covers the case where the link between the roothub and the first-tier hub is in U0, and the hub reflects the resume signaling back to the device without giving any indication it has done so until the device sends the Function Wake notification. Change the code in khubd that handles the remote wakeup to look at the state the USB core thinks the device is in, and handle the remote wakeup if the port's wakeup bit is set. This patch only takes care of the case where the device is attached directly to the roothub, or the USB 3.0 hub that is attached to the root hub is the device sending the Function Wake Device Notification (e.g. because a new USB device was attached). The other cases will be covered in a second patch. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
2011-11-15 10:00:01 +08:00
* Resume state after a device remote wakeup, or through the
* U3Exit state after a host-initiated resume. If it's a device
* initiated remote wake, don't pass up the link state change,
* so the roothub behavior is consistent with external
* USB 3.0 hub behavior.
*/
slot_id = xhci_find_slot_id_by_port(hcd, xhci, hcd_portnum + 1);
if (slot_id && xhci->devs[slot_id])
xhci_ring_device(xhci, slot_id);
if (bus_state->port_remote_wakeup & (1 << hcd_portnum)) {
xhci_test_and_clear_bit(xhci, port, PORT_PLC);
USB/xHCI: Support device-initiated USB 3.0 resume. USB 3.0 hubs don't have a port suspend change bit (that bit is now reserved). Instead, when a host-initiated resume finishes, the hub sets the port link state change bit. When a USB 3.0 device initiates remote wakeup, the parent hubs with their upstream links in U3 will pass the LFPS up the chain. The first hub that has an upstream link in U0 (which may be the roothub) will reflect that LFPS back down the path to the device. However, the parent hubs in the resumed path will not set their link state change bit. Instead, the device that initiated the resume has to send an asynchronous "Function Wake" Device Notification up to the host controller. Therefore, we need a way to notify the USB core of a device resume without going through the normal hub URB completion method. First, make the xHCI roothub act like an external USB 3.0 hub and not pass up the port link state change bit when a device-initiated resume finishes. Introduce a new xHCI bit field, port_remote_wakeup, so that we can tell the difference between a port coming out of the U3Exit state (host-initiated resume) and the RExit state (ending state of device-initiated resume). Since the USB core can't tell whether a port on a hub has resumed by looking at the Hub Status buffer, we need to introduce a bitfield, wakeup_bits, that indicates which ports have resumed. When the xHCI driver notices a port finishing a device-initiated resume, we call into a new USB core function, usb_wakeup_notification(), that will set the right bit in wakeup_bits, and kick khubd for that hub. We also call usb_wakeup_notification() when the Function Wake Device Notification is received by the xHCI driver. This covers the case where the link between the roothub and the first-tier hub is in U0, and the hub reflects the resume signaling back to the device without giving any indication it has done so until the device sends the Function Wake notification. Change the code in khubd that handles the remote wakeup to look at the state the USB core thinks the device is in, and handle the remote wakeup if the port's wakeup bit is set. This patch only takes care of the case where the device is attached directly to the roothub, or the USB 3.0 hub that is attached to the root hub is the device sending the Function Wake Device Notification (e.g. because a new USB device was attached). The other cases will be covered in a second patch. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
2011-11-15 10:00:01 +08:00
usb_wakeup_notification(hcd->self.root_hub,
hcd_portnum + 1);
USB/xHCI: Support device-initiated USB 3.0 resume. USB 3.0 hubs don't have a port suspend change bit (that bit is now reserved). Instead, when a host-initiated resume finishes, the hub sets the port link state change bit. When a USB 3.0 device initiates remote wakeup, the parent hubs with their upstream links in U3 will pass the LFPS up the chain. The first hub that has an upstream link in U0 (which may be the roothub) will reflect that LFPS back down the path to the device. However, the parent hubs in the resumed path will not set their link state change bit. Instead, the device that initiated the resume has to send an asynchronous "Function Wake" Device Notification up to the host controller. Therefore, we need a way to notify the USB core of a device resume without going through the normal hub URB completion method. First, make the xHCI roothub act like an external USB 3.0 hub and not pass up the port link state change bit when a device-initiated resume finishes. Introduce a new xHCI bit field, port_remote_wakeup, so that we can tell the difference between a port coming out of the U3Exit state (host-initiated resume) and the RExit state (ending state of device-initiated resume). Since the USB core can't tell whether a port on a hub has resumed by looking at the Hub Status buffer, we need to introduce a bitfield, wakeup_bits, that indicates which ports have resumed. When the xHCI driver notices a port finishing a device-initiated resume, we call into a new USB core function, usb_wakeup_notification(), that will set the right bit in wakeup_bits, and kick khubd for that hub. We also call usb_wakeup_notification() when the Function Wake Device Notification is received by the xHCI driver. This covers the case where the link between the roothub and the first-tier hub is in U0, and the hub reflects the resume signaling back to the device without giving any indication it has done so until the device sends the Function Wake notification. Change the code in khubd that handles the remote wakeup to look at the state the USB core thinks the device is in, and handle the remote wakeup if the port's wakeup bit is set. This patch only takes care of the case where the device is attached directly to the roothub, or the USB 3.0 hub that is attached to the root hub is the device sending the Function Wake Device Notification (e.g. because a new USB device was attached). The other cases will be covered in a second patch. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
2011-11-15 10:00:01 +08:00
bogus_port_status = true;
goto cleanup;
}
}
usb: Fix xHCI host issues on remote wakeup. When a device signals remote wakeup on a roothub, and the suspend change bit is set, the host controller driver must not give control back to the USB core until the port goes back into the active state. EHCI accomplishes this by waiting in the get port status function until the PORT_RESUME bit is cleared: /* stop resume signaling */ temp &= ~(PORT_RWC_BITS | PORT_SUSPEND | PORT_RESUME); ehci_writel(ehci, temp, status_reg); clear_bit(wIndex, &ehci->resuming_ports); retval = ehci_handshake(ehci, status_reg, PORT_RESUME, 0, 2000 /* 2msec */); Similarly, the xHCI host should wait until the port goes into U0, before passing control up to the USB core. When the port transitions from the RExit state to U0, the xHCI driver will get a port status change event. We need to wait for that event before passing control up to the USB core. After the port transitions to the active state, the USB core should time a recovery interval before it talks to the device. The length of that recovery interval is TRSMRCY, 10 ms, mentioned in the USB 2.0 spec, section 7.1.7.7. The previous xHCI code (which did not wait for the port to go into U0) would cause the USB core to violate that recovery interval. This bug caused numerous USB device disconnects on remote wakeup under ChromeOS and a Lynx Point LP xHCI host that takes up to 20 ms to move from RExit to U0. ChromeOS is very aggressive about power savings, and sets the autosuspend_delay to 100 ms, and disables USB persist. I attempted to replicate this bug with Ubuntu 12.04, but could not. I used Ubuntu 12.04 on the same platform, with the same BIOS that the bug was triggered on ChromeOS with. I also changed the USB sysfs settings as described above, but still could not reproduce the bug under Ubuntu. It may be that ChromeOS userspace triggers this bug through additional settings. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
2013-08-20 23:12:12 +08:00
/*
* Check to see if xhci-hub.c is waiting on RExit to U0 transition (or
* RExit to a disconnect state). If so, let the the driver know it's
* out of the RExit state.
*/
if (!DEV_SUPERSPEED_ANY(portsc) && hcd->speed < HCD_USB3 &&
test_and_clear_bit(hcd_portnum,
usb: Fix xHCI host issues on remote wakeup. When a device signals remote wakeup on a roothub, and the suspend change bit is set, the host controller driver must not give control back to the USB core until the port goes back into the active state. EHCI accomplishes this by waiting in the get port status function until the PORT_RESUME bit is cleared: /* stop resume signaling */ temp &= ~(PORT_RWC_BITS | PORT_SUSPEND | PORT_RESUME); ehci_writel(ehci, temp, status_reg); clear_bit(wIndex, &ehci->resuming_ports); retval = ehci_handshake(ehci, status_reg, PORT_RESUME, 0, 2000 /* 2msec */); Similarly, the xHCI host should wait until the port goes into U0, before passing control up to the USB core. When the port transitions from the RExit state to U0, the xHCI driver will get a port status change event. We need to wait for that event before passing control up to the USB core. After the port transitions to the active state, the USB core should time a recovery interval before it talks to the device. The length of that recovery interval is TRSMRCY, 10 ms, mentioned in the USB 2.0 spec, section 7.1.7.7. The previous xHCI code (which did not wait for the port to go into U0) would cause the USB core to violate that recovery interval. This bug caused numerous USB device disconnects on remote wakeup under ChromeOS and a Lynx Point LP xHCI host that takes up to 20 ms to move from RExit to U0. ChromeOS is very aggressive about power savings, and sets the autosuspend_delay to 100 ms, and disables USB persist. I attempted to replicate this bug with Ubuntu 12.04, but could not. I used Ubuntu 12.04 on the same platform, with the same BIOS that the bug was triggered on ChromeOS with. I also changed the USB sysfs settings as described above, but still could not reproduce the bug under Ubuntu. It may be that ChromeOS userspace triggers this bug through additional settings. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
2013-08-20 23:12:12 +08:00
&bus_state->rexit_ports)) {
complete(&bus_state->rexit_done[hcd_portnum]);
usb: Fix xHCI host issues on remote wakeup. When a device signals remote wakeup on a roothub, and the suspend change bit is set, the host controller driver must not give control back to the USB core until the port goes back into the active state. EHCI accomplishes this by waiting in the get port status function until the PORT_RESUME bit is cleared: /* stop resume signaling */ temp &= ~(PORT_RWC_BITS | PORT_SUSPEND | PORT_RESUME); ehci_writel(ehci, temp, status_reg); clear_bit(wIndex, &ehci->resuming_ports); retval = ehci_handshake(ehci, status_reg, PORT_RESUME, 0, 2000 /* 2msec */); Similarly, the xHCI host should wait until the port goes into U0, before passing control up to the USB core. When the port transitions from the RExit state to U0, the xHCI driver will get a port status change event. We need to wait for that event before passing control up to the USB core. After the port transitions to the active state, the USB core should time a recovery interval before it talks to the device. The length of that recovery interval is TRSMRCY, 10 ms, mentioned in the USB 2.0 spec, section 7.1.7.7. The previous xHCI code (which did not wait for the port to go into U0) would cause the USB core to violate that recovery interval. This bug caused numerous USB device disconnects on remote wakeup under ChromeOS and a Lynx Point LP xHCI host that takes up to 20 ms to move from RExit to U0. ChromeOS is very aggressive about power savings, and sets the autosuspend_delay to 100 ms, and disables USB persist. I attempted to replicate this bug with Ubuntu 12.04, but could not. I used Ubuntu 12.04 on the same platform, with the same BIOS that the bug was triggered on ChromeOS with. I also changed the USB sysfs settings as described above, but still could not reproduce the bug under Ubuntu. It may be that ChromeOS userspace triggers this bug through additional settings. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
2013-08-20 23:12:12 +08:00
bogus_port_status = true;
goto cleanup;
}
if (hcd->speed < HCD_USB3) {
xhci_test_and_clear_bit(xhci, port, PORT_PLC);
if ((xhci->quirks & XHCI_RESET_PLL_ON_DISCONNECT) &&
(portsc & PORT_CSC) && !(portsc & PORT_CONNECT))
xhci_cavium_reset_phy_quirk(xhci);
}
cleanup:
/* Update event ring dequeue pointer before dropping the lock */
inc_deq(xhci, xhci->event_ring);
/* Don't make the USB core poll the roothub if we got a bad port status
* change event. Besides, at that point we can't tell which roothub
* (USB 2.0 or USB 3.0) to kick.
*/
if (bogus_port_status)
return;
xhci: Avoid "dead ports", add roothub port polling. The USB core hub thread (khubd) is designed with external USB hubs in mind. It expects that if a port status change bit is set, the hub will continue to send a notification through the hub status data transfer. Basically, it expects hub notifications to be level-triggered. The xHCI host controller is designed to be edge-triggered on the logical 'OR' of all the port status change bits. When all port status change bits are clear, and a new change bit is set, the xHC will generate a Port Status Change Event. If another change bit is set in the same port status register before the first bit is cleared, it will not send another event. This means that the hub code may lose port status changes because of race conditions between clearing change bits. The user sees this as a "dead port" that doesn't react to device connects. The fix is to turn on port polling whenever a new change bit is set. Once the USB core issues a hub status request that shows that no change bits are set in any USB ports, turn off port polling. We can't allow the USB core to poll the roothub for port events during host suspend because if the PCI host is in D3cold, the port registers will be all f's. Instead, stop the port polling timer, and unconditionally restart it when the host resumes. If there are no port change bits set after the resume, the first call to hub_status_data will disable polling. This patch should be backported to stable kernels with the first xHCI support, 2.6.31 and newer, that include the commit 0f2a79300a1471cf92ab43af165ea13555c8b0a5 "USB: xhci: Root hub support." There will be merge conflicts because the check for HC_STATE_SUSPENDED was moved into xhci_suspend in 3.8. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Acked-by: Alan Stern <stern@rowland.harvard.edu> Cc: stable@vger.kernel.org
2012-11-28 04:30:23 +08:00
/*
* xHCI port-status-change events occur when the "or" of all the
* status-change bits in the portsc register changes from 0 to 1.
* New status changes won't cause an event if any other change
* bits are still set. When an event occurs, switch over to
* polling to avoid losing status changes.
*/
xhci_dbg(xhci, "%s: starting port polling.\n", __func__);
set_bit(HCD_FLAG_POLL_RH, &hcd->flags);
spin_unlock(&xhci->lock);
/* Pass this up to the core */
xhci: Register second xHCI roothub. This patch changes the xHCI driver to allocate two roothubs. This touches the driver initialization and shutdown paths, roothub emulation code, and port status change event handlers. This is a rather large patch, but it can't be broken up, or it would break git-bisect. Make the xHCI driver register its own PCI probe function. This will call the USB core to create the USB 2.0 roothub, and then create the USB 3.0 roothub. This gets the code for registering a shared roothub out of the USB core, and allows other HCDs later to decide if and how many shared roothubs they want to allocate. Make sure the xHCI's reset method marks the xHCI host controller's primary roothub as the USB 2.0 roothub. This ensures that the high speed bus will be processed first when the PCI device is resumed, and any USB 3.0 devices that have migrated over to high speed will migrate back after being reset. This ensures that USB persist works with these odd devices. The reset method will also mark the xHCI USB2 roothub as having an integrated TT. Like EHCI host controllers with a "rate matching hub" the xHCI USB 2.0 roothub doesn't have an OHCI or UHCI companion controller. It doesn't really have a TT, but we'll lie and say it has an integrated TT. We need to do this because the USB core will reject LS/FS devices under a HS hub without a TT. Other details: ------------- The roothub emulation code is changed to return the correct number of ports for the two roothubs. For the USB 3.0 roothub, it only reports the USB 3.0 ports. For the USB 2.0 roothub, it reports all the LS/FS/HS ports. The code to disable a port now checks the speed of the roothub, and refuses to disable SuperSpeed ports under the USB 3.0 roothub. The code for initializing a new device context must be changed to set the proper roothub port number. Since we've split the xHCI host into two roothubs, we can't just use the port number in the ancestor hub. Instead, we loop through the array of hardware port status register speeds and find the Nth port with a similar speed. The port status change event handler is updated to figure out whether the port that reported the change is a USB 3.0 port, or a non-SuperSpeed port. Once it figures out the port speed, it kicks the proper roothub. The function to find a slot ID based on the port index is updated to take into account that the two roothubs will have over-lapping port indexes. It checks that the virtual device with a matching port index is the same speed as the passed in roothub. There's also changes to the driver initialization and shutdown paths: 1. Make sure that the xhci_hcd pointer is shared across the two usb_hcd structures. The xhci_hcd pointer is allocated and the registers are mapped in when xhci_pci_setup() is called with the primary HCD. When xhci_pci_setup() is called with the non-primary HCD, the xhci_hcd pointer is stored. 2. Make sure to set the sg_tablesize for both usb_hcd structures. Set the PCI DMA mask for the non-primary HCD to allow for 64-bit or 32-bit DMA. (The PCI DMA mask is set from the primary HCD further down in the xhci_pci_setup() function.) 3. Ensure that the host controller doesn't start kicking khubd in response to port status changes before both usb_hcd structures are registered. xhci_run() only starts the xHC running once it has been called with the non-primary roothub. Similarly, the xhci_stop() function only halts the host controller when it is called with the non-primary HCD. Then on the second call, it resets and cleans up the MSI-X irqs. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
2010-12-17 03:21:10 +08:00
usb_hcd_poll_rh_status(hcd);
spin_lock(&xhci->lock);
}
/*
* This TD is defined by the TRBs starting at start_trb in start_seg and ending
* at end_trb, which may be in another segment. If the suspect DMA address is a
* TRB in this TD, this function returns that TRB's segment. Otherwise it
* returns 0.
*/
struct xhci_segment *trb_in_td(struct xhci_hcd *xhci,
struct xhci_segment *start_seg,
union xhci_trb *start_trb,
union xhci_trb *end_trb,
dma_addr_t suspect_dma,
bool debug)
{
dma_addr_t start_dma;
dma_addr_t end_seg_dma;
dma_addr_t end_trb_dma;
struct xhci_segment *cur_seg;
start_dma = xhci_trb_virt_to_dma(start_seg, start_trb);
cur_seg = start_seg;
do {
if (start_dma == 0)
USB: clean up some host controller sparse warnings Fix usb sparse warnings: drivers/usb/host/isp1362-hcd.c:2220:50: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:43:24: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:49:24: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:161:24: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:198:16: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:319:31: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:1231:33: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-pci.c:177:23: warning: non-ANSI function declaration of function 'xhci_register_pci' drivers/usb/host/xhci-pci.c:182:26: warning: non-ANSI function declaration of function 'xhci_unregister_pci' drivers/usb/host/xhci-ring.c:342:32: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:525:34: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:1009:32: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:1031:32: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:1041:16: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:1096:30: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:1100:27: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:224:27: warning: symbol 'xhci_alloc_container_ctx' was not declared. Should it be static? drivers/usb/host/xhci-mem.c:242:6: warning: symbol 'xhci_free_container_ctx' was not declared. Should it be static? Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Lothar Wassmann <LW@KARO-electronics.de> Signed-off By: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-19 23:53:50 +08:00
return NULL;
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
/* We may get an event for a Link TRB in the middle of a TD */
end_seg_dma = xhci_trb_virt_to_dma(cur_seg,
&cur_seg->trbs[TRBS_PER_SEGMENT - 1]);
/* If the end TRB isn't in this segment, this is set to 0 */
end_trb_dma = xhci_trb_virt_to_dma(cur_seg, end_trb);
if (debug)
xhci_warn(xhci,
"Looking for event-dma %016llx trb-start %016llx trb-end %016llx seg-start %016llx seg-end %016llx\n",
(unsigned long long)suspect_dma,
(unsigned long long)start_dma,
(unsigned long long)end_trb_dma,
(unsigned long long)cur_seg->dma,
(unsigned long long)end_seg_dma);
if (end_trb_dma > 0) {
/* The end TRB is in this segment, so suspect should be here */
if (start_dma <= end_trb_dma) {
if (suspect_dma >= start_dma && suspect_dma <= end_trb_dma)
return cur_seg;
} else {
/* Case for one segment with
* a TD wrapped around to the top
*/
if ((suspect_dma >= start_dma &&
suspect_dma <= end_seg_dma) ||
(suspect_dma >= cur_seg->dma &&
suspect_dma <= end_trb_dma))
return cur_seg;
}
USB: clean up some host controller sparse warnings Fix usb sparse warnings: drivers/usb/host/isp1362-hcd.c:2220:50: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:43:24: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:49:24: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:161:24: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:198:16: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:319:31: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:1231:33: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-pci.c:177:23: warning: non-ANSI function declaration of function 'xhci_register_pci' drivers/usb/host/xhci-pci.c:182:26: warning: non-ANSI function declaration of function 'xhci_unregister_pci' drivers/usb/host/xhci-ring.c:342:32: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:525:34: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:1009:32: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:1031:32: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:1041:16: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:1096:30: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:1100:27: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:224:27: warning: symbol 'xhci_alloc_container_ctx' was not declared. Should it be static? drivers/usb/host/xhci-mem.c:242:6: warning: symbol 'xhci_free_container_ctx' was not declared. Should it be static? Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Lothar Wassmann <LW@KARO-electronics.de> Signed-off By: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-19 23:53:50 +08:00
return NULL;
} else {
/* Might still be somewhere in this segment */
if (suspect_dma >= start_dma && suspect_dma <= end_seg_dma)
return cur_seg;
}
cur_seg = cur_seg->next;
start_dma = xhci_trb_virt_to_dma(cur_seg, &cur_seg->trbs[0]);
} while (cur_seg != start_seg);
USB: clean up some host controller sparse warnings Fix usb sparse warnings: drivers/usb/host/isp1362-hcd.c:2220:50: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:43:24: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:49:24: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:161:24: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:198:16: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:319:31: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:1231:33: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-pci.c:177:23: warning: non-ANSI function declaration of function 'xhci_register_pci' drivers/usb/host/xhci-pci.c:182:26: warning: non-ANSI function declaration of function 'xhci_unregister_pci' drivers/usb/host/xhci-ring.c:342:32: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:525:34: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:1009:32: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:1031:32: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:1041:16: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:1096:30: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:1100:27: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:224:27: warning: symbol 'xhci_alloc_container_ctx' was not declared. Should it be static? drivers/usb/host/xhci-mem.c:242:6: warning: symbol 'xhci_free_container_ctx' was not declared. Should it be static? Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Lothar Wassmann <LW@KARO-electronics.de> Signed-off By: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-19 23:53:50 +08:00
return NULL;
}
static void xhci_clear_hub_tt_buffer(struct xhci_hcd *xhci, struct xhci_td *td,
struct xhci_virt_ep *ep)
{
/*
* As part of low/full-speed endpoint-halt processing
* we must clear the TT buffer (USB 2.0 specification 11.17.5).
*/
if (td->urb->dev->tt && !usb_pipeint(td->urb->pipe) &&
(td->urb->dev->tt->hub != xhci_to_hcd(xhci)->self.root_hub) &&
!(ep->ep_state & EP_CLEARING_TT)) {
ep->ep_state |= EP_CLEARING_TT;
td->urb->ep->hcpriv = td->urb->dev;
if (usb_hub_clear_tt_buffer(td->urb))
ep->ep_state &= ~EP_CLEARING_TT;
}
}
static void xhci_cleanup_halted_endpoint(struct xhci_hcd *xhci,
unsigned int slot_id, unsigned int ep_index,
unsigned int stream_id, struct xhci_td *td,
enum xhci_ep_reset_type reset_type)
{
struct xhci_virt_ep *ep = &xhci->devs[slot_id]->eps[ep_index];
struct xhci_command *command;
/*
* Avoid resetting endpoint if link is inactive. Can cause host hang.
* Device will be reset soon to recover the link so don't do anything
*/
if (xhci->devs[slot_id]->flags & VDEV_PORT_ERROR)
return;
command = xhci_alloc_command(xhci, false, GFP_ATOMIC);
if (!command)
return;
ep->ep_state |= EP_HALTED;
xhci_queue_reset_ep(xhci, command, slot_id, ep_index, reset_type);
if (reset_type == EP_HARD_RESET) {
ep->ep_state |= EP_HARD_CLEAR_TOGGLE;
xhci_cleanup_stalled_ring(xhci, ep_index, stream_id, td);
xhci_clear_hub_tt_buffer(xhci, td, ep);
}
xhci_ring_cmd_db(xhci);
}
/* Check if an error has halted the endpoint ring. The class driver will
* cleanup the halt for a non-default control endpoint if we indicate a stall.
* However, a babble and other errors also halt the endpoint ring, and the class
* driver won't clear the halt in that case, so we need to issue a Set Transfer
* Ring Dequeue Pointer command manually.
*/
static int xhci_requires_manual_halt_cleanup(struct xhci_hcd *xhci,
struct xhci_ep_ctx *ep_ctx,
unsigned int trb_comp_code)
{
/* TRB completion codes that may require a manual halt cleanup */
if (trb_comp_code == COMP_USB_TRANSACTION_ERROR ||
trb_comp_code == COMP_BABBLE_DETECTED_ERROR ||
trb_comp_code == COMP_SPLIT_TRANSACTION_ERROR)
/* The 0.95 spec says a babbling control endpoint
* is not halted. The 0.96 spec says it is. Some HW
* claims to be 0.95 compliant, but it halts the control
* endpoint anyway. Check if a babble halted the
* endpoint.
*/
if (GET_EP_CTX_STATE(ep_ctx) == EP_STATE_HALTED)
return 1;
return 0;
}
int xhci_is_vendor_info_code(struct xhci_hcd *xhci, unsigned int trb_comp_code)
{
if (trb_comp_code >= 224 && trb_comp_code <= 255) {
/* Vendor defined "informational" completion code,
* treat as not-an-error.
*/
xhci_dbg(xhci, "Vendor defined info completion code %u\n",
trb_comp_code);
xhci_dbg(xhci, "Treating code as success.\n");
return 1;
}
return 0;
}
static int xhci_td_cleanup(struct xhci_hcd *xhci, struct xhci_td *td,
struct xhci_ring *ep_ring, int *status)
{
struct urb *urb = NULL;
/* Clean up the endpoint's TD list */
urb = td->urb;
/* if a bounce buffer was used to align this td then unmap it */
xhci_unmap_td_bounce_buffer(xhci, ep_ring, td);
/* Do one last check of the actual transfer length.
* If the host controller said we transferred more data than the buffer
* length, urb->actual_length will be a very big number (since it's
* unsigned). Play it safe and say we didn't transfer anything.
*/
if (urb->actual_length > urb->transfer_buffer_length) {
xhci_warn(xhci, "URB req %u and actual %u transfer length mismatch\n",
urb->transfer_buffer_length, urb->actual_length);
urb->actual_length = 0;
*status = 0;
}
list_del_init(&td->td_list);
/* Was this TD slated to be cancelled but completed anyway? */
if (!list_empty(&td->cancelled_td_list))
list_del_init(&td->cancelled_td_list);
inc_td_cnt(urb);
/* Giveback the urb when all the tds are completed */
if (last_td_in_urb(td)) {
if ((urb->actual_length != urb->transfer_buffer_length &&
(urb->transfer_flags & URB_SHORT_NOT_OK)) ||
(*status != 0 && !usb_endpoint_xfer_isoc(&urb->ep->desc)))
xhci_dbg(xhci, "Giveback URB %p, len = %d, expected = %d, status = %d\n",
urb, urb->actual_length,
urb->transfer_buffer_length, *status);
/* set isoc urb status to 0 just as EHCI, UHCI, and OHCI */
if (usb_pipetype(urb->pipe) == PIPE_ISOCHRONOUS)
*status = 0;
xhci_giveback_urb_in_irq(xhci, td, *status);
}
return 0;
}
static int finish_td(struct xhci_hcd *xhci, struct xhci_td *td,
struct xhci_transfer_event *event,
struct xhci_virt_ep *ep, int *status)
{
struct xhci_virt_device *xdev;
struct xhci_ep_ctx *ep_ctx;
struct xhci_ring *ep_ring;
unsigned int slot_id;
u32 trb_comp_code;
int ep_index;
slot_id = TRB_TO_SLOT_ID(le32_to_cpu(event->flags));
xdev = xhci->devs[slot_id];
ep_index = TRB_TO_EP_ID(le32_to_cpu(event->flags)) - 1;
ep_ring = xhci_dma_to_transfer_ring(ep, le64_to_cpu(event->buffer));
ep_ctx = xhci_get_ep_ctx(xhci, xdev->out_ctx, ep_index);
trb_comp_code = GET_COMP_CODE(le32_to_cpu(event->transfer_len));
if (trb_comp_code == COMP_STOPPED_LENGTH_INVALID ||
trb_comp_code == COMP_STOPPED ||
trb_comp_code == COMP_STOPPED_SHORT_PACKET) {
/* The Endpoint Stop Command completion will take care of any
* stopped TDs. A stopped TD may be restarted, so don't update
* the ring dequeue pointer or take this TD off any lists yet.
*/
return 0;
}
if (trb_comp_code == COMP_STALL_ERROR ||
xhci_requires_manual_halt_cleanup(xhci, ep_ctx,
trb_comp_code)) {
/* Issue a reset endpoint command to clear the host side
* halt, followed by a set dequeue command to move the
* dequeue pointer past the TD.
* The class driver clears the device side halt later.
*/
xhci_cleanup_halted_endpoint(xhci, slot_id, ep_index,
ep_ring->stream_id, td, EP_HARD_RESET);
} else {
/* Update ring dequeue pointer */
while (ep_ring->dequeue != td->last_trb)
inc_deq(xhci, ep_ring);
inc_deq(xhci, ep_ring);
}
return xhci_td_cleanup(xhci, td, ep_ring, status);
}
/* sum trb lengths from ring dequeue up to stop_trb, _excluding_ stop_trb */
static int sum_trb_lengths(struct xhci_hcd *xhci, struct xhci_ring *ring,
union xhci_trb *stop_trb)
{
u32 sum;
union xhci_trb *trb = ring->dequeue;
struct xhci_segment *seg = ring->deq_seg;
for (sum = 0; trb != stop_trb; next_trb(xhci, ring, &seg, &trb)) {
if (!trb_is_noop(trb) && !trb_is_link(trb))
sum += TRB_LEN(le32_to_cpu(trb->generic.field[2]));
}
return sum;
}
/*
* Process control tds, update urb status and actual_length.
*/
static int process_ctrl_td(struct xhci_hcd *xhci, struct xhci_td *td,
union xhci_trb *ep_trb, struct xhci_transfer_event *event,
struct xhci_virt_ep *ep, int *status)
{
struct xhci_virt_device *xdev;
unsigned int slot_id;
int ep_index;
struct xhci_ep_ctx *ep_ctx;
u32 trb_comp_code;
u32 remaining, requested;
u32 trb_type;
trb_type = TRB_FIELD_TO_TYPE(le32_to_cpu(ep_trb->generic.field[3]));
slot_id = TRB_TO_SLOT_ID(le32_to_cpu(event->flags));
xdev = xhci->devs[slot_id];
ep_index = TRB_TO_EP_ID(le32_to_cpu(event->flags)) - 1;
ep_ctx = xhci_get_ep_ctx(xhci, xdev->out_ctx, ep_index);
trb_comp_code = GET_COMP_CODE(le32_to_cpu(event->transfer_len));
requested = td->urb->transfer_buffer_length;
remaining = EVENT_TRB_LEN(le32_to_cpu(event->transfer_len));
switch (trb_comp_code) {
case COMP_SUCCESS:
if (trb_type != TRB_STATUS) {
xhci_warn(xhci, "WARN: Success on ctrl %s TRB without IOC set?\n",
(trb_type == TRB_DATA) ? "data" : "setup");
*status = -ESHUTDOWN;
break;
}
*status = 0;
break;
case COMP_SHORT_PACKET:
*status = 0;
break;
case COMP_STOPPED_SHORT_PACKET:
if (trb_type == TRB_DATA || trb_type == TRB_NORMAL)
td->urb->actual_length = remaining;
else
xhci_warn(xhci, "WARN: Stopped Short Packet on ctrl setup or status TRB\n");
goto finish_td;
case COMP_STOPPED:
switch (trb_type) {
case TRB_SETUP:
td->urb->actual_length = 0;
goto finish_td;
case TRB_DATA:
case TRB_NORMAL:
td->urb->actual_length = requested - remaining;
goto finish_td;
case TRB_STATUS:
td->urb->actual_length = requested;
goto finish_td;
default:
xhci_warn(xhci, "WARN: unexpected TRB Type %d\n",
trb_type);
goto finish_td;
}
case COMP_STOPPED_LENGTH_INVALID:
goto finish_td;
default:
if (!xhci_requires_manual_halt_cleanup(xhci,
ep_ctx, trb_comp_code))
break;
xhci_dbg(xhci, "TRB error %u, halted endpoint index = %u\n",
trb_comp_code, ep_index);
/* else fall through */
case COMP_STALL_ERROR:
/* Did we transfer part of the data (middle) phase? */
if (trb_type == TRB_DATA || trb_type == TRB_NORMAL)
td->urb->actual_length = requested - remaining;
else if (!td->urb_length_set)
td->urb->actual_length = 0;
goto finish_td;
}
/* stopped at setup stage, no data transferred */
if (trb_type == TRB_SETUP)
goto finish_td;
/*
* if on data stage then update the actual_length of the URB and flag it
* as set, so it won't be overwritten in the event for the last TRB.
*/
if (trb_type == TRB_DATA ||
trb_type == TRB_NORMAL) {
td->urb_length_set = true;
td->urb->actual_length = requested - remaining;
xhci_dbg(xhci, "Waiting for status stage event\n");
return 0;
}
/* at status stage */
if (!td->urb_length_set)
td->urb->actual_length = requested;
finish_td:
return finish_td(xhci, td, event, ep, status);
}
/*
* Process isochronous tds, update urb packet status and actual_length.
*/
static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td,
union xhci_trb *ep_trb, struct xhci_transfer_event *event,
struct xhci_virt_ep *ep, int *status)
{
struct xhci_ring *ep_ring;
struct urb_priv *urb_priv;
int idx;
struct usb_iso_packet_descriptor *frame;
u32 trb_comp_code;
bool sum_trbs_for_length = false;
u32 remaining, requested, ep_trb_len;
int short_framestatus;
ep_ring = xhci_dma_to_transfer_ring(ep, le64_to_cpu(event->buffer));
trb_comp_code = GET_COMP_CODE(le32_to_cpu(event->transfer_len));
urb_priv = td->urb->hcpriv;
idx = urb_priv->num_tds_done;
frame = &td->urb->iso_frame_desc[idx];
requested = frame->length;
remaining = EVENT_TRB_LEN(le32_to_cpu(event->transfer_len));
ep_trb_len = TRB_LEN(le32_to_cpu(ep_trb->generic.field[2]));
short_framestatus = td->urb->transfer_flags & URB_SHORT_NOT_OK ?
-EREMOTEIO : 0;
/* handle completion code */
switch (trb_comp_code) {
case COMP_SUCCESS:
if (remaining) {
frame->status = short_framestatus;
if (xhci->quirks & XHCI_TRUST_TX_LENGTH)
sum_trbs_for_length = true;
xhci: Add new short TX quirk for Fresco Logic host. Sergio reported that when he recorded audio from a USB headset mic plugged into the USB 3.0 port on his ASUS N53SV-DH72, the audio sounded "robotic". When plugged into the USB 2.0 port under EHCI on the same laptop, the audio sounded fine. The device is: Bus 002 Device 004: ID 046d:0a0c Logitech, Inc. Clear Chat Comfort USB Headset The problem was tracked down to the Fresco Logic xHCI host controller not correctly reporting short transfers on isochronous IN endpoints. The driver would submit a 96 byte transfer, the device would only send 88 or 90 bytes, and the xHCI host would report the transfer had a "successful" completion code, with an untransferred buffer length of 8 or 6 bytes. The successful completion code and non-zero untransferred length is a contradiction. The xHCI host is supposed to only mark a transfer as successful if all the bytes are transferred. Otherwise, the transfer should be marked with a short packet completion code. Without the EHCI bus trace, we wouldn't know whether the xHCI driver should trust the completion code or the untransferred length. With it, we know to trust the untransferred length. Add a new xHCI quirk for the Fresco Logic host controller. If a transfer is reported as successful, but the untransferred length is non-zero, print a warning. For the Fresco Logic host, change the completion code to COMP_SHORT_TX and process the transfer like a short transfer. This should be backported to stable kernels that contain the commit f5182b4155b9d686c5540a6822486400e34ddd98 "xhci: Disable MSI for some Fresco Logic hosts." That commit was marked for stable kernels as old as 2.6.36. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Reported-by: Sergio Correia <lists@uece.net> Tested-by: Sergio Correia <lists@uece.net> Cc: stable@vger.kernel.org Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
2012-05-09 00:22:49 +08:00
break;
}
frame->status = 0;
break;
case COMP_SHORT_PACKET:
frame->status = short_framestatus;
sum_trbs_for_length = true;
break;
case COMP_BANDWIDTH_OVERRUN_ERROR:
frame->status = -ECOMM;
break;
case COMP_ISOCH_BUFFER_OVERRUN:
case COMP_BABBLE_DETECTED_ERROR:
frame->status = -EOVERFLOW;
break;
case COMP_INCOMPATIBLE_DEVICE_ERROR:
case COMP_STALL_ERROR:
frame->status = -EPROTO;
break;
case COMP_USB_TRANSACTION_ERROR:
frame->status = -EPROTO;
if (ep_trb != td->last_trb)
return 0;
break;
case COMP_STOPPED:
sum_trbs_for_length = true;
break;
case COMP_STOPPED_SHORT_PACKET:
/* field normally containing residue now contains tranferred */
frame->status = short_framestatus;
requested = remaining;
break;
case COMP_STOPPED_LENGTH_INVALID:
requested = 0;
remaining = 0;
break;
default:
sum_trbs_for_length = true;
frame->status = -1;
break;
}
if (sum_trbs_for_length)
frame->actual_length = sum_trb_lengths(xhci, ep_ring, ep_trb) +
ep_trb_len - remaining;
else
frame->actual_length = requested;
td->urb->actual_length += frame->actual_length;
return finish_td(xhci, td, event, ep, status);
}
static int skip_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td,
struct xhci_transfer_event *event,
struct xhci_virt_ep *ep, int *status)
{
struct xhci_ring *ep_ring;
struct urb_priv *urb_priv;
struct usb_iso_packet_descriptor *frame;
int idx;
ep_ring = xhci_dma_to_transfer_ring(ep, le64_to_cpu(event->buffer));
urb_priv = td->urb->hcpriv;
idx = urb_priv->num_tds_done;
frame = &td->urb->iso_frame_desc[idx];
xhci: Always set urb->status to zero for isoc endpoints. When the xHCI driver encounters a Missed Service Interval event for an isochronous endpoint ring, it means the host controller skipped over one or more isochronous TDs. For TD that is skipped, skip_isoc_td() is called. This sets the frame descriptor status to -EXDEV, and also sets the value stored in the int pointed to by status to -EXDEV. If the isochronous TD happens to be the last TD in an URB, handle_tx_event() will use the status variable to give back the URB to the USB core. That means drivers will see urb->status as -EXDEV. It turns out that EHCI, UHCI, and OHCI always set urb->status to zero for an isochronous urb, regardless of what the frame status is. See itd_complete() in ehci-sched.c: } else { /* URB was too late */ desc->status = -EXDEV; } } /* handle completion now? */ if (likely ((urb_index + 1) != urb->number_of_packets)) goto done; /* ASSERT: it's really the last itd for this urb list_for_each_entry (itd, &stream->td_list, itd_list) BUG_ON (itd->urb == urb); */ /* give urb back to the driver; completion often (re)submits */ dev = urb->dev; ehci_urb_done(ehci, urb, 0); ehci_urb_done() completes the URB with the status of the third argument, which is always zero in this case. It turns out that many USB webcam drivers, such as uvcvideo, cannot handle urb->status set to a non-zero value. They will not resubmit their isochronous URBs in that case, and userspace will see a frozen video. Change the xHCI driver to be consistent with the EHCI and UHCI driver, and always set urb->status to 0 for isochronous URBs. This patch should be backported to kernels as old as 2.6.36 Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Cc: "Xu, Andiry" <Andiry.Xu@amd.com> Cc: stable@kernel.org
2011-06-16 10:57:46 +08:00
/* The transfer is partly done. */
frame->status = -EXDEV;
/* calc actual length */
frame->actual_length = 0;
/* Update ring dequeue pointer */
while (ep_ring->dequeue != td->last_trb)
inc_deq(xhci, ep_ring);
inc_deq(xhci, ep_ring);
return xhci_td_cleanup(xhci, td, ep_ring, status);
}
/*
* Process bulk and interrupt tds, update urb status and actual_length.
*/
static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_td *td,
union xhci_trb *ep_trb, struct xhci_transfer_event *event,
struct xhci_virt_ep *ep, int *status)
{
struct xhci_slot_ctx *slot_ctx;
struct xhci_ring *ep_ring;
u32 trb_comp_code;
u32 remaining, requested, ep_trb_len;
unsigned int slot_id;
int ep_index;
slot_id = TRB_TO_SLOT_ID(le32_to_cpu(event->flags));
slot_ctx = xhci_get_slot_ctx(xhci, xhci->devs[slot_id]->out_ctx);
ep_index = TRB_TO_EP_ID(le32_to_cpu(event->flags)) - 1;
ep_ring = xhci_dma_to_transfer_ring(ep, le64_to_cpu(event->buffer));
trb_comp_code = GET_COMP_CODE(le32_to_cpu(event->transfer_len));
remaining = EVENT_TRB_LEN(le32_to_cpu(event->transfer_len));
ep_trb_len = TRB_LEN(le32_to_cpu(ep_trb->generic.field[2]));
requested = td->urb->transfer_buffer_length;
switch (trb_comp_code) {
case COMP_SUCCESS:
ep_ring->err_count = 0;
/* handle success with untransferred data as short packet */
if (ep_trb != td->last_trb || remaining) {
xhci_warn(xhci, "WARN Successful completion on short TX\n");
xhci_dbg(xhci, "ep %#x - asked for %d bytes, %d bytes untransferred\n",
td->urb->ep->desc.bEndpointAddress,
requested, remaining);
}
*status = 0;
break;
case COMP_SHORT_PACKET:
xhci_dbg(xhci, "ep %#x - asked for %d bytes, %d bytes untransferred\n",
td->urb->ep->desc.bEndpointAddress,
requested, remaining);
*status = 0;
break;
case COMP_STOPPED_SHORT_PACKET:
td->urb->actual_length = remaining;
goto finish_td;
case COMP_STOPPED_LENGTH_INVALID:
/* stopped on ep trb with invalid length, exclude it */
ep_trb_len = 0;
remaining = 0;
break;
case COMP_USB_TRANSACTION_ERROR:
if ((ep_ring->err_count++ > MAX_SOFT_RETRY) ||
le32_to_cpu(slot_ctx->tt_info) & TT_SLOT)
break;
*status = 0;
xhci_cleanup_halted_endpoint(xhci, slot_id, ep_index,
ep_ring->stream_id, td, EP_SOFT_RESET);
return 0;
default:
/* do nothing */
break;
}
if (ep_trb == td->last_trb)
td->urb->actual_length = requested - remaining;
else
td->urb->actual_length =
sum_trb_lengths(xhci, ep_ring, ep_trb) +
ep_trb_len - remaining;
finish_td:
if (remaining > requested) {
xhci_warn(xhci, "bad transfer trb length %d in event trb\n",
remaining);
td->urb->actual_length = 0;
}
return finish_td(xhci, td, event, ep, status);
}
/*
* If this function returns an error condition, it means it got a Transfer
* event with a corrupted Slot ID, Endpoint ID, or TRB DMA address.
* At this point, the host controller is probably hosed and should be reset.
*/
static int handle_tx_event(struct xhci_hcd *xhci,
struct xhci_transfer_event *event)
{
struct xhci_virt_device *xdev;
struct xhci_virt_ep *ep;
struct xhci_ring *ep_ring;
unsigned int slot_id;
int ep_index;
USB: clean up some host controller sparse warnings Fix usb sparse warnings: drivers/usb/host/isp1362-hcd.c:2220:50: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:43:24: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:49:24: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:161:24: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:198:16: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:319:31: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:1231:33: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-pci.c:177:23: warning: non-ANSI function declaration of function 'xhci_register_pci' drivers/usb/host/xhci-pci.c:182:26: warning: non-ANSI function declaration of function 'xhci_unregister_pci' drivers/usb/host/xhci-ring.c:342:32: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:525:34: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:1009:32: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:1031:32: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:1041:16: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:1096:30: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-ring.c:1100:27: warning: Using plain integer as NULL pointer drivers/usb/host/xhci-mem.c:224:27: warning: symbol 'xhci_alloc_container_ctx' was not declared. Should it be static? drivers/usb/host/xhci-mem.c:242:6: warning: symbol 'xhci_free_container_ctx' was not declared. Should it be static? Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Lothar Wassmann <LW@KARO-electronics.de> Signed-off By: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-19 23:53:50 +08:00
struct xhci_td *td = NULL;
dma_addr_t ep_trb_dma;
struct xhci_segment *ep_seg;
union xhci_trb *ep_trb;
int status = -EINPROGRESS;
struct xhci_ep_ctx *ep_ctx;
USB: xHCI: prevent infinite loop when processing MSE event When a xHC host is unable to handle isochronous transfer in the interval, it reports a Missed Service Error event and skips some tds. Currently xhci driver handles MSE event in the following ways: 1. When encounter a MSE event, set ep->skip flag, update event ring dequeue pointer and return. 2. When encounter the next event on this ep, the driver will run the do-while loop, fetch td from ep's td_list to find the td corresponding to this event. All tds missed are marked as short transfer(-EXDEV). The do-while loop will end in two ways: 1. If the td pointed by the event trb is found; 2. If the ep ring's td_list is empty. However, if a buggy HW reports some unpredicted event (for example, an overrun event following a MSE event while the ep ring is actually not empty), the driver will never find the td, and it will loop until the td_list is empty. Unfortunately, the spinlock is dropped when give back a urb in the do-while loop. During the spinlock released period, the class driver may still submit urbs and add tds to the td_list. This may cause disaster, since the td_list will never be empty and the loop never ends, and the system hangs. To fix this, count the number of TDs on the ep ring before skipping TDs, and quit the loop when skipped that number of tds. This guarantees the do-while loop will end after certain number of cycles, and driver will not be trapped in an infinite loop. Signed-off-by: Andiry Xu <andiry.xu@amd.com> Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-09-20 07:05:12 +08:00
struct list_head *tmp;
u32 trb_comp_code;
USB: xHCI: prevent infinite loop when processing MSE event When a xHC host is unable to handle isochronous transfer in the interval, it reports a Missed Service Error event and skips some tds. Currently xhci driver handles MSE event in the following ways: 1. When encounter a MSE event, set ep->skip flag, update event ring dequeue pointer and return. 2. When encounter the next event on this ep, the driver will run the do-while loop, fetch td from ep's td_list to find the td corresponding to this event. All tds missed are marked as short transfer(-EXDEV). The do-while loop will end in two ways: 1. If the td pointed by the event trb is found; 2. If the ep ring's td_list is empty. However, if a buggy HW reports some unpredicted event (for example, an overrun event following a MSE event while the ep ring is actually not empty), the driver will never find the td, and it will loop until the td_list is empty. Unfortunately, the spinlock is dropped when give back a urb in the do-while loop. During the spinlock released period, the class driver may still submit urbs and add tds to the td_list. This may cause disaster, since the td_list will never be empty and the loop never ends, and the system hangs. To fix this, count the number of TDs on the ep ring before skipping TDs, and quit the loop when skipped that number of tds. This guarantees the do-while loop will end after certain number of cycles, and driver will not be trapped in an infinite loop. Signed-off-by: Andiry Xu <andiry.xu@amd.com> Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-09-20 07:05:12 +08:00
int td_num = 0;
bool handling_skipped_tds = false;
slot_id = TRB_TO_SLOT_ID(le32_to_cpu(event->flags));
ep_index = TRB_TO_EP_ID(le32_to_cpu(event->flags)) - 1;
trb_comp_code = GET_COMP_CODE(le32_to_cpu(event->transfer_len));
ep_trb_dma = le64_to_cpu(event->buffer);
xdev = xhci->devs[slot_id];
if (!xdev) {
xhci_err(xhci, "ERROR Transfer event pointed to bad slot %u\n",
slot_id);
goto err_out;
}
ep = &xdev->eps[ep_index];
ep_ring = xhci_dma_to_transfer_ring(ep, ep_trb_dma);
ep_ctx = xhci_get_ep_ctx(xhci, xdev->out_ctx, ep_index);
if (GET_EP_CTX_STATE(ep_ctx) == EP_STATE_DISABLED) {
xhci_err(xhci,
"ERROR Transfer event for disabled endpoint slot %u ep %u\n",
slot_id, ep_index);
goto err_out;
}
/* Some transfer events don't always point to a trb, see xhci 4.17.4 */
if (!ep_ring) {
switch (trb_comp_code) {
case COMP_STALL_ERROR:
case COMP_USB_TRANSACTION_ERROR:
case COMP_INVALID_STREAM_TYPE_ERROR:
case COMP_INVALID_STREAM_ID_ERROR:
xhci_cleanup_halted_endpoint(xhci, slot_id, ep_index, 0,
NULL, EP_SOFT_RESET);
goto cleanup;
case COMP_RING_UNDERRUN:
case COMP_RING_OVERRUN:
case COMP_STOPPED_LENGTH_INVALID:
goto cleanup;
default:
xhci_err(xhci, "ERROR Transfer event for unknown stream ring slot %u ep %u\n",
slot_id, ep_index);
goto err_out;
}
}
USB: xHCI: prevent infinite loop when processing MSE event When a xHC host is unable to handle isochronous transfer in the interval, it reports a Missed Service Error event and skips some tds. Currently xhci driver handles MSE event in the following ways: 1. When encounter a MSE event, set ep->skip flag, update event ring dequeue pointer and return. 2. When encounter the next event on this ep, the driver will run the do-while loop, fetch td from ep's td_list to find the td corresponding to this event. All tds missed are marked as short transfer(-EXDEV). The do-while loop will end in two ways: 1. If the td pointed by the event trb is found; 2. If the ep ring's td_list is empty. However, if a buggy HW reports some unpredicted event (for example, an overrun event following a MSE event while the ep ring is actually not empty), the driver will never find the td, and it will loop until the td_list is empty. Unfortunately, the spinlock is dropped when give back a urb in the do-while loop. During the spinlock released period, the class driver may still submit urbs and add tds to the td_list. This may cause disaster, since the td_list will never be empty and the loop never ends, and the system hangs. To fix this, count the number of TDs on the ep ring before skipping TDs, and quit the loop when skipped that number of tds. This guarantees the do-while loop will end after certain number of cycles, and driver will not be trapped in an infinite loop. Signed-off-by: Andiry Xu <andiry.xu@amd.com> Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-09-20 07:05:12 +08:00
/* Count current td numbers if ep->skip is set */
if (ep->skip) {
list_for_each(tmp, &ep_ring->td_list)
td_num++;
}
/* Look for common error cases */
switch (trb_comp_code) {
/* Skip codes that require special handling depending on
* transfer type
*/
case COMP_SUCCESS:
if (EVENT_TRB_LEN(le32_to_cpu(event->transfer_len)) == 0)
xhci: Add new short TX quirk for Fresco Logic host. Sergio reported that when he recorded audio from a USB headset mic plugged into the USB 3.0 port on his ASUS N53SV-DH72, the audio sounded "robotic". When plugged into the USB 2.0 port under EHCI on the same laptop, the audio sounded fine. The device is: Bus 002 Device 004: ID 046d:0a0c Logitech, Inc. Clear Chat Comfort USB Headset The problem was tracked down to the Fresco Logic xHCI host controller not correctly reporting short transfers on isochronous IN endpoints. The driver would submit a 96 byte transfer, the device would only send 88 or 90 bytes, and the xHCI host would report the transfer had a "successful" completion code, with an untransferred buffer length of 8 or 6 bytes. The successful completion code and non-zero untransferred length is a contradiction. The xHCI host is supposed to only mark a transfer as successful if all the bytes are transferred. Otherwise, the transfer should be marked with a short packet completion code. Without the EHCI bus trace, we wouldn't know whether the xHCI driver should trust the completion code or the untransferred length. With it, we know to trust the untransferred length. Add a new xHCI quirk for the Fresco Logic host controller. If a transfer is reported as successful, but the untransferred length is non-zero, print a warning. For the Fresco Logic host, change the completion code to COMP_SHORT_TX and process the transfer like a short transfer. This should be backported to stable kernels that contain the commit f5182b4155b9d686c5540a6822486400e34ddd98 "xhci: Disable MSI for some Fresco Logic hosts." That commit was marked for stable kernels as old as 2.6.36. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Reported-by: Sergio Correia <lists@uece.net> Tested-by: Sergio Correia <lists@uece.net> Cc: stable@vger.kernel.org Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
2012-05-09 00:22:49 +08:00
break;
if (xhci->quirks & XHCI_TRUST_TX_LENGTH ||
ep_ring->last_td_was_short)
trb_comp_code = COMP_SHORT_PACKET;
xhci: Add new short TX quirk for Fresco Logic host. Sergio reported that when he recorded audio from a USB headset mic plugged into the USB 3.0 port on his ASUS N53SV-DH72, the audio sounded "robotic". When plugged into the USB 2.0 port under EHCI on the same laptop, the audio sounded fine. The device is: Bus 002 Device 004: ID 046d:0a0c Logitech, Inc. Clear Chat Comfort USB Headset The problem was tracked down to the Fresco Logic xHCI host controller not correctly reporting short transfers on isochronous IN endpoints. The driver would submit a 96 byte transfer, the device would only send 88 or 90 bytes, and the xHCI host would report the transfer had a "successful" completion code, with an untransferred buffer length of 8 or 6 bytes. The successful completion code and non-zero untransferred length is a contradiction. The xHCI host is supposed to only mark a transfer as successful if all the bytes are transferred. Otherwise, the transfer should be marked with a short packet completion code. Without the EHCI bus trace, we wouldn't know whether the xHCI driver should trust the completion code or the untransferred length. With it, we know to trust the untransferred length. Add a new xHCI quirk for the Fresco Logic host controller. If a transfer is reported as successful, but the untransferred length is non-zero, print a warning. For the Fresco Logic host, change the completion code to COMP_SHORT_TX and process the transfer like a short transfer. This should be backported to stable kernels that contain the commit f5182b4155b9d686c5540a6822486400e34ddd98 "xhci: Disable MSI for some Fresco Logic hosts." That commit was marked for stable kernels as old as 2.6.36. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Reported-by: Sergio Correia <lists@uece.net> Tested-by: Sergio Correia <lists@uece.net> Cc: stable@vger.kernel.org Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
2012-05-09 00:22:49 +08:00
else
xhci_warn_ratelimited(xhci,
"WARN Successful completion on short TX for slot %u ep %u: needs XHCI_TRUST_TX_LENGTH quirk?\n",
slot_id, ep_index);
case COMP_SHORT_PACKET:
break;
/* Completion codes for endpoint stopped state */
case COMP_STOPPED:
xhci_dbg(xhci, "Stopped on Transfer TRB for slot %u ep %u\n",
slot_id, ep_index);
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
break;
case COMP_STOPPED_LENGTH_INVALID:
xhci_dbg(xhci,
"Stopped on No-op or Link TRB for slot %u ep %u\n",
slot_id, ep_index);
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
break;
case COMP_STOPPED_SHORT_PACKET:
xhci_dbg(xhci,
"Stopped with short packet transfer detected for slot %u ep %u\n",
slot_id, ep_index);
break;
/* Completion codes for endpoint halted state */
case COMP_STALL_ERROR:
xhci_dbg(xhci, "Stalled endpoint for slot %u ep %u\n", slot_id,
ep_index);
ep->ep_state |= EP_HALTED;
status = -EPIPE;
break;
case COMP_SPLIT_TRANSACTION_ERROR:
xhci_dbg(xhci, "Split transaction error for slot %u ep %u\n",
slot_id, ep_index);
status = -EPROTO;
break;
case COMP_USB_TRANSACTION_ERROR:
xhci_dbg(xhci, "Transfer error for slot %u ep %u on endpoint\n",
slot_id, ep_index);
status = -EPROTO;
break;
case COMP_BABBLE_DETECTED_ERROR:
xhci_dbg(xhci, "Babble error for slot %u ep %u on endpoint\n",
slot_id, ep_index);
status = -EOVERFLOW;
break;
/* Completion codes for endpoint error state */
case COMP_TRB_ERROR:
xhci_warn(xhci,
"WARN: TRB error for slot %u ep %u on endpoint\n",
slot_id, ep_index);
status = -EILSEQ;
break;
/* completion codes not indicating endpoint state change */
case COMP_DATA_BUFFER_ERROR:
xhci_warn(xhci,
"WARN: HC couldn't access mem fast enough for slot %u ep %u\n",
slot_id, ep_index);
status = -ENOSR;
break;
case COMP_BANDWIDTH_OVERRUN_ERROR:
xhci_warn(xhci,
"WARN: bandwidth overrun event for slot %u ep %u on endpoint\n",
slot_id, ep_index);
break;
case COMP_ISOCH_BUFFER_OVERRUN:
xhci_warn(xhci,
"WARN: buffer overrun event for slot %u ep %u on endpoint",
slot_id, ep_index);
break;
case COMP_RING_UNDERRUN:
/*
* When the Isoch ring is empty, the xHC will generate
* a Ring Overrun Event for IN Isoch endpoint or Ring
* Underrun Event for OUT Isoch endpoint.
*/
xhci_dbg(xhci, "underrun event on endpoint\n");
if (!list_empty(&ep_ring->td_list))
xhci_dbg(xhci, "Underrun Event for slot %d ep %d "
"still with TDs queued?\n",
TRB_TO_SLOT_ID(le32_to_cpu(event->flags)),
ep_index);
goto cleanup;
case COMP_RING_OVERRUN:
xhci_dbg(xhci, "overrun event on endpoint\n");
if (!list_empty(&ep_ring->td_list))
xhci_dbg(xhci, "Overrun Event for slot %d ep %d "
"still with TDs queued?\n",
TRB_TO_SLOT_ID(le32_to_cpu(event->flags)),
ep_index);
goto cleanup;
case COMP_MISSED_SERVICE_ERROR:
/*
* When encounter missed service error, one or more isoc tds
* may be missed by xHC.
* Set skip flag of the ep_ring; Complete the missed tds as
* short transfer when process the ep_ring next time.
*/
ep->skip = true;
xhci_dbg(xhci,
"Miss service interval error for slot %u ep %u, set skip flag\n",
slot_id, ep_index);
goto cleanup;
case COMP_NO_PING_RESPONSE_ERROR:
ep->skip = true;
xhci_dbg(xhci,
"No Ping response error for slot %u ep %u, Skip one Isoc TD\n",
slot_id, ep_index);
goto cleanup;
case COMP_INCOMPATIBLE_DEVICE_ERROR:
/* needs disable slot command to recover */
xhci_warn(xhci,
"WARN: detect an incompatible device for slot %u ep %u",
slot_id, ep_index);
status = -EPROTO;
break;
default:
if (xhci_is_vendor_info_code(xhci, trb_comp_code)) {
status = 0;
break;
}
xhci_warn(xhci,
"ERROR Unknown event condition %u for slot %u ep %u , HC probably busted\n",
trb_comp_code, slot_id, ep_index);
goto cleanup;
}
do {
/* This TRB should be in the TD at the head of this ring's
* TD list.
*/
if (list_empty(&ep_ring->td_list)) {
/*
* Don't print wanings if it's due to a stopped endpoint
* generating an extra completion event if the device
* was suspended. Or, a event for the last TRB of a
* short TD we already got a short event for.
* The short TD is already removed from the TD list.
*/
if (!(trb_comp_code == COMP_STOPPED ||
trb_comp_code == COMP_STOPPED_LENGTH_INVALID ||
ep_ring->last_td_was_short)) {
xhci_warn(xhci, "WARN Event TRB for slot %d ep %d with no TDs queued?\n",
TRB_TO_SLOT_ID(le32_to_cpu(event->flags)),
ep_index);
}
if (ep->skip) {
ep->skip = false;
xhci_dbg(xhci, "td_list is empty while skip flag set. Clear skip flag for slot %u ep %u.\n",
slot_id, ep_index);
}
goto cleanup;
}
USB: xHCI: prevent infinite loop when processing MSE event When a xHC host is unable to handle isochronous transfer in the interval, it reports a Missed Service Error event and skips some tds. Currently xhci driver handles MSE event in the following ways: 1. When encounter a MSE event, set ep->skip flag, update event ring dequeue pointer and return. 2. When encounter the next event on this ep, the driver will run the do-while loop, fetch td from ep's td_list to find the td corresponding to this event. All tds missed are marked as short transfer(-EXDEV). The do-while loop will end in two ways: 1. If the td pointed by the event trb is found; 2. If the ep ring's td_list is empty. However, if a buggy HW reports some unpredicted event (for example, an overrun event following a MSE event while the ep ring is actually not empty), the driver will never find the td, and it will loop until the td_list is empty. Unfortunately, the spinlock is dropped when give back a urb in the do-while loop. During the spinlock released period, the class driver may still submit urbs and add tds to the td_list. This may cause disaster, since the td_list will never be empty and the loop never ends, and the system hangs. To fix this, count the number of TDs on the ep ring before skipping TDs, and quit the loop when skipped that number of tds. This guarantees the do-while loop will end after certain number of cycles, and driver will not be trapped in an infinite loop. Signed-off-by: Andiry Xu <andiry.xu@amd.com> Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-09-20 07:05:12 +08:00
/* We've skipped all the TDs on the ep ring when ep->skip set */
if (ep->skip && td_num == 0) {
ep->skip = false;
xhci_dbg(xhci, "All tds on the ep_ring skipped. Clear skip flag for slot %u ep %u.\n",
slot_id, ep_index);
USB: xHCI: prevent infinite loop when processing MSE event When a xHC host is unable to handle isochronous transfer in the interval, it reports a Missed Service Error event and skips some tds. Currently xhci driver handles MSE event in the following ways: 1. When encounter a MSE event, set ep->skip flag, update event ring dequeue pointer and return. 2. When encounter the next event on this ep, the driver will run the do-while loop, fetch td from ep's td_list to find the td corresponding to this event. All tds missed are marked as short transfer(-EXDEV). The do-while loop will end in two ways: 1. If the td pointed by the event trb is found; 2. If the ep ring's td_list is empty. However, if a buggy HW reports some unpredicted event (for example, an overrun event following a MSE event while the ep ring is actually not empty), the driver will never find the td, and it will loop until the td_list is empty. Unfortunately, the spinlock is dropped when give back a urb in the do-while loop. During the spinlock released period, the class driver may still submit urbs and add tds to the td_list. This may cause disaster, since the td_list will never be empty and the loop never ends, and the system hangs. To fix this, count the number of TDs on the ep ring before skipping TDs, and quit the loop when skipped that number of tds. This guarantees the do-while loop will end after certain number of cycles, and driver will not be trapped in an infinite loop. Signed-off-by: Andiry Xu <andiry.xu@amd.com> Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-09-20 07:05:12 +08:00
goto cleanup;
}
td = list_first_entry(&ep_ring->td_list, struct xhci_td,
td_list);
USB: xHCI: prevent infinite loop when processing MSE event When a xHC host is unable to handle isochronous transfer in the interval, it reports a Missed Service Error event and skips some tds. Currently xhci driver handles MSE event in the following ways: 1. When encounter a MSE event, set ep->skip flag, update event ring dequeue pointer and return. 2. When encounter the next event on this ep, the driver will run the do-while loop, fetch td from ep's td_list to find the td corresponding to this event. All tds missed are marked as short transfer(-EXDEV). The do-while loop will end in two ways: 1. If the td pointed by the event trb is found; 2. If the ep ring's td_list is empty. However, if a buggy HW reports some unpredicted event (for example, an overrun event following a MSE event while the ep ring is actually not empty), the driver will never find the td, and it will loop until the td_list is empty. Unfortunately, the spinlock is dropped when give back a urb in the do-while loop. During the spinlock released period, the class driver may still submit urbs and add tds to the td_list. This may cause disaster, since the td_list will never be empty and the loop never ends, and the system hangs. To fix this, count the number of TDs on the ep ring before skipping TDs, and quit the loop when skipped that number of tds. This guarantees the do-while loop will end after certain number of cycles, and driver will not be trapped in an infinite loop. Signed-off-by: Andiry Xu <andiry.xu@amd.com> Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-09-20 07:05:12 +08:00
if (ep->skip)
td_num--;
/* Is this a TRB in the currently executing TD? */
ep_seg = trb_in_td(xhci, ep_ring->deq_seg, ep_ring->dequeue,
td->last_trb, ep_trb_dma, false);
/*
* Skip the Force Stopped Event. The event_trb(event_dma) of FSE
* is not in the current TD pointed by ep_ring->dequeue because
* that the hardware dequeue pointer still at the previous TRB
* of the current TD. The previous TRB maybe a Link TD or the
* last TRB of the previous TD. The command completion handle
* will take care the rest.
*/
if (!ep_seg && (trb_comp_code == COMP_STOPPED ||
trb_comp_code == COMP_STOPPED_LENGTH_INVALID)) {
goto cleanup;
}
if (!ep_seg) {
if (!ep->skip ||
!usb_endpoint_xfer_isoc(&td->urb->ep->desc)) {
/* Some host controllers give a spurious
* successful event after a short transfer.
* Ignore it.
*/
if ((xhci->quirks & XHCI_SPURIOUS_SUCCESS) &&
ep_ring->last_td_was_short) {
ep_ring->last_td_was_short = false;
goto cleanup;
}
/* HC is busted, give up! */
xhci_err(xhci,
"ERROR Transfer event TRB DMA ptr not "
"part of current TD ep_index %d "
"comp_code %u\n", ep_index,
trb_comp_code);
trb_in_td(xhci, ep_ring->deq_seg,
ep_ring->dequeue, td->last_trb,
ep_trb_dma, true);
return -ESHUTDOWN;
}
skip_isoc_td(xhci, td, event, ep, &status);
goto cleanup;
}
if (trb_comp_code == COMP_SHORT_PACKET)
ep_ring->last_td_was_short = true;
else
ep_ring->last_td_was_short = false;
if (ep->skip) {
xhci_dbg(xhci,
"Found td. Clear skip flag for slot %u ep %u.\n",
slot_id, ep_index);
ep->skip = false;
}
USB: xhci: Handle URB cancel, complete and resubmit race. In the old code, there was a race condition between the stop endpoint command and the URB submission process. When the stop endpoint command is handled by the event handler, the endpoint ring is assumed to be stopped. When a stop endpoint command is queued, URB submissions are to not ring the doorbell. The old code would check the number of pending URBs to be canceled, and would not ring the doorbell if it was non-zero. However, the following race condition could occur with the old code: 1. Cancel an URB, add it to the list of URBs to be canceled, queue the stop endpoint command, and increment ep->cancels_pending to 1. 2. The URB finishes on the HW, and an event is enqueued to the event ring (at the same time as 1). 3. The stop endpoint command finishes, and the endpoint is halted. An event is queued to the event ring. 4. The event handler sees the finished URB, notices it was to be canceled, decrements ep->cancels_pending to 0, and removes it from the to be canceled list. 5. The event handler drops the lock and gives back the URB. The completion handler requeues the URB (or a different driver enqueues a new URB). This causes the endpoint's doorbell to be rung, since ep->cancels_pending == 0. The endpoint is now running. 6. A second URB is canceled, and it's added to the canceled list. Since ep->cancels_pending == 0, a new stop endpoint command is queued, and ep->cancels_pending is incremented to 1. 7. The event handler then sees the completed stop endpoint command. The handler assumes the endpoint is stopped, but it isn't. It attempts to move the dequeue pointer or change TDs to cancel the second URB, while the hardware is actively accessing the endpoint ring. To eliminate this race condition, a new endpoint state bit is introduced, EP_HALT_PENDING. When this bit is set, a stop endpoint command has been queued, and the command handler has not begun to process the URB cancellation list yet. The endpoint doorbell should not be rung when this is set. Set this when a stop endpoint command is queued, clear it when the handler for that command runs, and check if it's set before ringing a doorbell. ep->cancels_pending is eliminated, because it is no longer used. Make sure to ring the doorbell for an endpoint when the stop endpoint command handler runs, even if the canceled URB list is empty. All canceled URBs could have completed and new URBs could have been enqueued without the doorbell being rung before the command was handled. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-10-28 01:55:52 +08:00
ep_trb = &ep_seg->trbs[(ep_trb_dma - ep_seg->dma) /
sizeof(*ep_trb)];
trace_xhci_handle_transfer(ep_ring,
(struct xhci_generic_trb *) ep_trb);
/*
* No-op TRB could trigger interrupts in a case where
* a URB was killed and a STALL_ERROR happens right
* after the endpoint ring stopped. Reset the halted
* endpoint. Otherwise, the endpoint remains stalled
* indefinitely.
*/
if (trb_is_noop(ep_trb)) {
if (trb_comp_code == COMP_STALL_ERROR ||
xhci_requires_manual_halt_cleanup(xhci, ep_ctx,
trb_comp_code))
xhci_cleanup_halted_endpoint(xhci, slot_id,
ep_index,
ep_ring->stream_id,
td, EP_HARD_RESET);
goto cleanup;
}
/* update the urb's actual_length and give back to the core */
if (usb_endpoint_xfer_control(&td->urb->ep->desc))
process_ctrl_td(xhci, td, ep_trb, event, ep, &status);
else if (usb_endpoint_xfer_isoc(&td->urb->ep->desc))
process_isoc_td(xhci, td, ep_trb, event, ep, &status);
else
process_bulk_intr_td(xhci, td, ep_trb, event, ep,
&status);
cleanup:
handling_skipped_tds = ep->skip &&
trb_comp_code != COMP_MISSED_SERVICE_ERROR &&
trb_comp_code != COMP_NO_PING_RESPONSE_ERROR;
/*
* Do not update event ring dequeue pointer if we're in a loop
* processing missed tds.
*/
if (!handling_skipped_tds)
inc_deq(xhci, xhci->event_ring);
/*
* If ep->skip is set, it means there are missed tds on the
* endpoint ring need to take care of.
* Process them as short transfer until reach the td pointed by
* the event.
*/
} while (handling_skipped_tds);
return 0;
err_out:
xhci_err(xhci, "@%016llx %08x %08x %08x %08x\n",
(unsigned long long) xhci_trb_virt_to_dma(
xhci->event_ring->deq_seg,
xhci->event_ring->dequeue),
lower_32_bits(le64_to_cpu(event->buffer)),
upper_32_bits(le64_to_cpu(event->buffer)),
le32_to_cpu(event->transfer_len),
le32_to_cpu(event->flags));
return -ENODEV;
}
/*
* This function handles all OS-owned events on the event ring. It may drop
* xhci->lock between event processing (e.g. to pass up port status changes).
* Returns >0 for "possibly more events to process" (caller should call again),
* otherwise 0 if done. In future, <0 returns should indicate error code.
*/
static int xhci_handle_event(struct xhci_hcd *xhci)
{
union xhci_trb *event;
int update_ptrs = 1;
int ret;
/* Event ring hasn't been allocated yet. */
if (!xhci->event_ring || !xhci->event_ring->dequeue) {
xhci_err(xhci, "ERROR event ring not ready\n");
return -ENOMEM;
}
event = xhci->event_ring->dequeue;
/* Does the HC or OS own the TRB? */
if ((le32_to_cpu(event->event_cmd.flags) & TRB_CYCLE) !=
xhci->event_ring->cycle_state)
return 0;
trace_xhci_handle_event(xhci->event_ring, &event->generic);
/*
* Barrier between reading the TRB_CYCLE (valid) flag above and any
* speculative reads of the event's flags/data below.
*/
rmb();
/* FIXME: Handle more event types. */
switch (le32_to_cpu(event->event_cmd.flags) & TRB_TYPE_BITMASK) {
case TRB_TYPE(TRB_COMPLETION):
handle_cmd_completion(xhci, &event->event_cmd);
break;
case TRB_TYPE(TRB_PORT_STATUS):
handle_port_status(xhci, event);
update_ptrs = 0;
break;
case TRB_TYPE(TRB_TRANSFER):
ret = handle_tx_event(xhci, &event->trans_event);
if (ret >= 0)
update_ptrs = 0;
break;
case TRB_TYPE(TRB_DEV_NOTE):
handle_device_notification(xhci, event);
break;
default:
if ((le32_to_cpu(event->event_cmd.flags) & TRB_TYPE_BITMASK) >=
TRB_TYPE(48))
handle_vendor_event(xhci, event);
else
xhci_warn(xhci, "ERROR unknown event type %d\n",
TRB_FIELD_TO_TYPE(
le32_to_cpu(event->event_cmd.flags)));
}
USB: xhci: Add watchdog timer for URB cancellation. In order to giveback a canceled URB, we must ensure that the xHCI hardware will not access the buffer in an URB. We can't modify the buffer pointers on endpoint rings without issuing and waiting for a stop endpoint command. Since URBs can be canceled in interrupt context, we can't wait on that command. The old code trusted that the host controller would respond to the command, and would giveback the URBs in the event handler. If the hardware never responds to the stop endpoint command, the URBs will never be completed, and we might hang the USB subsystem. Implement a watchdog timer that is spawned whenever a stop endpoint command is queued. If a stop endpoint command event is found on the event ring during an interrupt, we need to stop the watchdog timer with del_timer(). Since del_timer() can fail if the timer is running and waiting on the xHCI lock, we need a way to signal to the timer that everything is fine and it should exit. If we simply clear EP_HALT_PENDING, a new stop endpoint command could sneak in and set it before the watchdog timer can grab the lock. Instead we use a combination of the EP_HALT_PENDING flag and a counter for the number of pending stop endpoint commands (xhci_virt_ep->stop_cmds_pending). If we need to cancel the watchdog timer and del_timer() succeeds, we decrement the number of pending stop endpoint commands. If del_timer() fails, we leave the number of pending stop endpoint commands alone. In either case, we clear the EP_HALT_PENDING flag. The timer will decrement the number of pending stop endpoint commands once it obtains the lock. If the timer is the tail end of the last stop endpoint command (xhci_virt_ep->stop_cmds_pending == 0), and the endpoint's command is still pending (EP_HALT_PENDING is set), we assume the host is dying. The watchdog timer will set XHCI_STATE_DYING, try to halt the xHCI host, and give back all pending URBs. Various other places in the driver need to check whether the xHCI host is dying. If the interrupt handler ever notices, it should immediately stop processing events. The URB enqueue function should also return -ESHUTDOWN. The URB dequeue function should simply return the value of usb_hcd_check_unlink_urb() and the watchdog timer will take care of giving the URB back. When a device is disconnected, the xHCI hardware structures should be freed without issuing a disable slot command (since the hardware probably won't respond to it anyway). The debugging polling loop should stop polling if the host is dying. When a device is disconnected, any pending watchdog timers are killed with del_timer_sync(). It must be synchronous so that the watchdog timer doesn't attempt to access the freed endpoint structures. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-10-28 01:57:01 +08:00
/* Any of the above functions may drop and re-acquire the lock, so check
* to make sure a watchdog timer didn't mark the host as non-responsive.
*/
if (xhci->xhc_state & XHCI_STATE_DYING) {
xhci_dbg(xhci, "xHCI host dying, returning from "
"event handler.\n");
return 0;
USB: xhci: Add watchdog timer for URB cancellation. In order to giveback a canceled URB, we must ensure that the xHCI hardware will not access the buffer in an URB. We can't modify the buffer pointers on endpoint rings without issuing and waiting for a stop endpoint command. Since URBs can be canceled in interrupt context, we can't wait on that command. The old code trusted that the host controller would respond to the command, and would giveback the URBs in the event handler. If the hardware never responds to the stop endpoint command, the URBs will never be completed, and we might hang the USB subsystem. Implement a watchdog timer that is spawned whenever a stop endpoint command is queued. If a stop endpoint command event is found on the event ring during an interrupt, we need to stop the watchdog timer with del_timer(). Since del_timer() can fail if the timer is running and waiting on the xHCI lock, we need a way to signal to the timer that everything is fine and it should exit. If we simply clear EP_HALT_PENDING, a new stop endpoint command could sneak in and set it before the watchdog timer can grab the lock. Instead we use a combination of the EP_HALT_PENDING flag and a counter for the number of pending stop endpoint commands (xhci_virt_ep->stop_cmds_pending). If we need to cancel the watchdog timer and del_timer() succeeds, we decrement the number of pending stop endpoint commands. If del_timer() fails, we leave the number of pending stop endpoint commands alone. In either case, we clear the EP_HALT_PENDING flag. The timer will decrement the number of pending stop endpoint commands once it obtains the lock. If the timer is the tail end of the last stop endpoint command (xhci_virt_ep->stop_cmds_pending == 0), and the endpoint's command is still pending (EP_HALT_PENDING is set), we assume the host is dying. The watchdog timer will set XHCI_STATE_DYING, try to halt the xHCI host, and give back all pending URBs. Various other places in the driver need to check whether the xHCI host is dying. If the interrupt handler ever notices, it should immediately stop processing events. The URB enqueue function should also return -ESHUTDOWN. The URB dequeue function should simply return the value of usb_hcd_check_unlink_urb() and the watchdog timer will take care of giving the URB back. When a device is disconnected, the xHCI hardware structures should be freed without issuing a disable slot command (since the hardware probably won't respond to it anyway). The debugging polling loop should stop polling if the host is dying. When a device is disconnected, any pending watchdog timers are killed with del_timer_sync(). It must be synchronous so that the watchdog timer doesn't attempt to access the freed endpoint structures. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-10-28 01:57:01 +08:00
}
if (update_ptrs)
/* Update SW event ring dequeue pointer */
inc_deq(xhci, xhci->event_ring);
/* Are there more items on the event ring? Caller will call us again to
* check.
*/
return 1;
}
/*
* Update Event Ring Dequeue Pointer:
* - When all events have finished
* - To avoid "Event Ring Full Error" condition
*/
static void xhci_update_erst_dequeue(struct xhci_hcd *xhci,
union xhci_trb *event_ring_deq)
{
u64 temp_64;
dma_addr_t deq;
temp_64 = xhci_read_64(xhci, &xhci->ir_set->erst_dequeue);
/* If necessary, update the HW's version of the event ring deq ptr. */
if (event_ring_deq != xhci->event_ring->dequeue) {
deq = xhci_trb_virt_to_dma(xhci->event_ring->deq_seg,
xhci->event_ring->dequeue);
if (deq == 0)
xhci_warn(xhci, "WARN something wrong with SW event ring dequeue ptr\n");
/*
* Per 4.9.4, Software writes to the ERDP register shall
* always advance the Event Ring Dequeue Pointer value.
*/
if ((temp_64 & (u64) ~ERST_PTR_MASK) ==
((u64) deq & (u64) ~ERST_PTR_MASK))
return;
/* Update HC event ring dequeue pointer */
temp_64 &= ERST_PTR_MASK;
temp_64 |= ((u64) deq & (u64) ~ERST_PTR_MASK);
}
/* Clear the event handler busy flag (RW1C) */
temp_64 |= ERST_EHB;
xhci_write_64(xhci, temp_64, &xhci->ir_set->erst_dequeue);
}
/*
* xHCI spec says we can get an interrupt, and if the HC has an error condition,
* we might get bad data out of the event ring. Section 4.10.2.7 has a list of
* indicators of an event TRB error, but we check the status *first* to be safe.
*/
irqreturn_t xhci_irq(struct usb_hcd *hcd)
{
struct xhci_hcd *xhci = hcd_to_xhci(hcd);
union xhci_trb *event_ring_deq;
irqreturn_t ret = IRQ_NONE;
USB: xhci: fix lock-inversion problem With threaded interrupts, bottom-half handlers are called with interrupts enabled. Therefore they can't safely use spin_lock(); they have to use spin_lock_irqsave(). Lockdep warns about a violation occurring in xhci_irq(): ========================================================= [ INFO: possible irq lock inversion dependency detected ] 4.11.0-rc8-dbg+ #1 Not tainted --------------------------------------------------------- swapper/7/0 just changed the state of lock: (&(&ehci->lock)->rlock){-.-...}, at: [<ffffffffa0130a69>] ehci_hrtimer_func+0x29/0xc0 [ehci_hcd] but this lock took another, HARDIRQ-unsafe lock in the past: (hcd_urb_list_lock){+.....} and interrupts could create inverse lock ordering between them. other info that might help us debug this: Possible interrupt unsafe locking scenario: CPU0 CPU1 ---- ---- lock(hcd_urb_list_lock); local_irq_disable(); lock(&(&ehci->lock)->rlock); lock(hcd_urb_list_lock); <Interrupt> lock(&(&ehci->lock)->rlock); *** DEADLOCK *** no locks held by swapper/7/0. the shortest dependencies between 2nd lock and 1st lock: -> (hcd_urb_list_lock){+.....} ops: 252 { HARDIRQ-ON-W at: __lock_acquire+0x602/0x1280 lock_acquire+0xd5/0x1c0 _raw_spin_lock+0x2f/0x40 usb_hcd_unlink_urb_from_ep+0x1b/0x60 [usbcore] xhci_giveback_urb_in_irq.isra.45+0x70/0x1b0 [xhci_hcd] finish_td.constprop.60+0x1d8/0x2e0 [xhci_hcd] xhci_irq+0xdd6/0x1fa0 [xhci_hcd] usb_hcd_irq+0x26/0x40 [usbcore] irq_forced_thread_fn+0x2f/0x70 irq_thread+0x149/0x1d0 kthread+0x113/0x150 ret_from_fork+0x2e/0x40 This patch fixes the problem. Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Reported-and-tested-by: Bart Van Assche <bart.vanassche@sandisk.com> CC: <stable@vger.kernel.org> Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-05-17 23:32:03 +08:00
unsigned long flags;
u64 temp_64;
u32 status;
int event_loop = 0;
USB: xhci: fix lock-inversion problem With threaded interrupts, bottom-half handlers are called with interrupts enabled. Therefore they can't safely use spin_lock(); they have to use spin_lock_irqsave(). Lockdep warns about a violation occurring in xhci_irq(): ========================================================= [ INFO: possible irq lock inversion dependency detected ] 4.11.0-rc8-dbg+ #1 Not tainted --------------------------------------------------------- swapper/7/0 just changed the state of lock: (&(&ehci->lock)->rlock){-.-...}, at: [<ffffffffa0130a69>] ehci_hrtimer_func+0x29/0xc0 [ehci_hcd] but this lock took another, HARDIRQ-unsafe lock in the past: (hcd_urb_list_lock){+.....} and interrupts could create inverse lock ordering between them. other info that might help us debug this: Possible interrupt unsafe locking scenario: CPU0 CPU1 ---- ---- lock(hcd_urb_list_lock); local_irq_disable(); lock(&(&ehci->lock)->rlock); lock(hcd_urb_list_lock); <Interrupt> lock(&(&ehci->lock)->rlock); *** DEADLOCK *** no locks held by swapper/7/0. the shortest dependencies between 2nd lock and 1st lock: -> (hcd_urb_list_lock){+.....} ops: 252 { HARDIRQ-ON-W at: __lock_acquire+0x602/0x1280 lock_acquire+0xd5/0x1c0 _raw_spin_lock+0x2f/0x40 usb_hcd_unlink_urb_from_ep+0x1b/0x60 [usbcore] xhci_giveback_urb_in_irq.isra.45+0x70/0x1b0 [xhci_hcd] finish_td.constprop.60+0x1d8/0x2e0 [xhci_hcd] xhci_irq+0xdd6/0x1fa0 [xhci_hcd] usb_hcd_irq+0x26/0x40 [usbcore] irq_forced_thread_fn+0x2f/0x70 irq_thread+0x149/0x1d0 kthread+0x113/0x150 ret_from_fork+0x2e/0x40 This patch fixes the problem. Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Reported-and-tested-by: Bart Van Assche <bart.vanassche@sandisk.com> CC: <stable@vger.kernel.org> Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-05-17 23:32:03 +08:00
spin_lock_irqsave(&xhci->lock, flags);
/* Check if the xHC generated the interrupt, or the irq is shared */
status = readl(&xhci->op_regs->status);
if (status == ~(u32)0) {
xhci_hc_died(xhci);
ret = IRQ_HANDLED;
goto out;
}
if (!(status & STS_EINT))
goto out;
if (status & STS_FATAL) {
xhci_warn(xhci, "WARNING: Host System Error\n");
xhci_halt(xhci);
ret = IRQ_HANDLED;
goto out;
}
/*
* Clear the op reg interrupt status first,
* so we can receive interrupts from other MSI-X interrupters.
* Write 1 to clear the interrupt status.
*/
status |= STS_EINT;
writel(status, &xhci->op_regs->status);
if (!hcd->msi_enabled) {
u32 irq_pending;
irq_pending = readl(&xhci->ir_set->irq_pending);
irq_pending |= IMAN_IP;
writel(irq_pending, &xhci->ir_set->irq_pending);
}
xhci: Cleanup only when releasing primary hcd Under stress occasions some TI devices might not return early when reading the status register during the quirk invocation of xhci_irq made by usb_hcd_pci_remove. This means that instead of returning, we end up handling this interruption in the middle of a shutdown. Since xhci->event_ring has already been freed in xhci_mem_cleanup, we end up accessing freed memory, causing the Oops below. commit 8c24d6d7b09d ("usb: xhci: stop everything on the first call to xhci_stop") is the one that changed the instant in which we clean up the event queue when stopping a device. Before, we didn't call xhci_mem_cleanup at the first time xhci_stop is executed (for the shared HCD), instead, we only did it after the invocation for the primary HCD, much later at the removal path. The code flow for this oops looks like this: xhci_pci_remove() usb_remove_hcd(xhci->shared) xhci_stop(xhci->shared) xhci_halt() xhci_mem_cleanup(xhci); // Free the event_queue usb_hcd_pci_remove(primary) xhci_irq() // Access the event_queue if STS_EINT is set. Crash. xhci_stop() xhci_halt() // return early The fix modifies xhci_stop to only cleanup the xhci data when releasing the primary HCD. This way, we still have the event_queue configured when invoking xhci_irq. We still halt the device on the first call to xhci_stop, though. I could reproduce this issue several times on the mainline kernel by doing a bind-unbind stress test with a specific storage gadget attached. I also ran the same test over-night with my patch applied and didn't observe the issue anymore. [ 113.334124] Unable to handle kernel paging request for data at address 0x00000028 [ 113.335514] Faulting instruction address: 0xd00000000d4f767c [ 113.336839] Oops: Kernel access of bad area, sig: 11 [#1] [ 113.338214] SMP NR_CPUS=1024 NUMA PowerNV [c000000efe47ba90] c000000000720850 usb_hcd_irq+0x50/0x80 [c000000efe47bac0] c00000000073d328 usb_hcd_pci_remove+0x68/0x1f0 [c000000efe47bb00] d00000000daf0128 xhci_pci_remove+0x78/0xb0 [xhci_pci] [c000000efe47bb30] c00000000055cf70 pci_device_remove+0x70/0x110 [c000000efe47bb70] c00000000061c6bc __device_release_driver+0xbc/0x190 [c000000efe47bba0] c00000000061c7d0 device_release_driver+0x40/0x70 [c000000efe47bbd0] c000000000619510 unbind_store+0x120/0x150 [c000000efe47bc20] c0000000006183c4 drv_attr_store+0x64/0xa0 [c000000efe47bc60] c00000000039f1d0 sysfs_kf_write+0x80/0xb0 [c000000efe47bca0] c00000000039e14c kernfs_fop_write+0x18c/0x1f0 [c000000efe47bcf0] c0000000002e962c __vfs_write+0x6c/0x190 [c000000efe47bd90] c0000000002eab40 vfs_write+0xc0/0x200 [c000000efe47bde0] c0000000002ec85c SyS_write+0x6c/0x110 [c000000efe47be30] c000000000009260 system_call+0x38/0x108 Signed-off-by: Gabriel Krisman Bertazi <krisman@linux.vnet.ibm.com> Cc: Roger Quadros <rogerq@ti.com> Cc: joel@jms.id.au Cc: stable@vger.kernel.org Reviewed-by: Roger Quadros <rogerq@ti.com> Cc: <stable@vger.kernel.org> #v4.3+ Tested-by: Joel Stanley <joel@jms.id.au> Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-06-01 23:09:07 +08:00
if (xhci->xhc_state & XHCI_STATE_DYING ||
xhci->xhc_state & XHCI_STATE_HALTED) {
xhci_dbg(xhci, "xHCI dying, ignoring interrupt. "
"Shouldn't IRQs be disabled?\n");
/* Clear the event handler busy flag (RW1C);
* the event ring should be empty.
*/
temp_64 = xhci_read_64(xhci, &xhci->ir_set->erst_dequeue);
xhci_write_64(xhci, temp_64 | ERST_EHB,
&xhci->ir_set->erst_dequeue);
ret = IRQ_HANDLED;
goto out;
}
event_ring_deq = xhci->event_ring->dequeue;
/* FIXME this should be a delayed service routine
* that clears the EHB.
*/
while (xhci_handle_event(xhci) > 0) {
if (event_loop++ < TRBS_PER_SEGMENT / 2)
continue;
xhci_update_erst_dequeue(xhci, event_ring_deq);
event_loop = 0;
}
xhci_update_erst_dequeue(xhci, event_ring_deq);
ret = IRQ_HANDLED;
out:
USB: xhci: fix lock-inversion problem With threaded interrupts, bottom-half handlers are called with interrupts enabled. Therefore they can't safely use spin_lock(); they have to use spin_lock_irqsave(). Lockdep warns about a violation occurring in xhci_irq(): ========================================================= [ INFO: possible irq lock inversion dependency detected ] 4.11.0-rc8-dbg+ #1 Not tainted --------------------------------------------------------- swapper/7/0 just changed the state of lock: (&(&ehci->lock)->rlock){-.-...}, at: [<ffffffffa0130a69>] ehci_hrtimer_func+0x29/0xc0 [ehci_hcd] but this lock took another, HARDIRQ-unsafe lock in the past: (hcd_urb_list_lock){+.....} and interrupts could create inverse lock ordering between them. other info that might help us debug this: Possible interrupt unsafe locking scenario: CPU0 CPU1 ---- ---- lock(hcd_urb_list_lock); local_irq_disable(); lock(&(&ehci->lock)->rlock); lock(hcd_urb_list_lock); <Interrupt> lock(&(&ehci->lock)->rlock); *** DEADLOCK *** no locks held by swapper/7/0. the shortest dependencies between 2nd lock and 1st lock: -> (hcd_urb_list_lock){+.....} ops: 252 { HARDIRQ-ON-W at: __lock_acquire+0x602/0x1280 lock_acquire+0xd5/0x1c0 _raw_spin_lock+0x2f/0x40 usb_hcd_unlink_urb_from_ep+0x1b/0x60 [usbcore] xhci_giveback_urb_in_irq.isra.45+0x70/0x1b0 [xhci_hcd] finish_td.constprop.60+0x1d8/0x2e0 [xhci_hcd] xhci_irq+0xdd6/0x1fa0 [xhci_hcd] usb_hcd_irq+0x26/0x40 [usbcore] irq_forced_thread_fn+0x2f/0x70 irq_thread+0x149/0x1d0 kthread+0x113/0x150 ret_from_fork+0x2e/0x40 This patch fixes the problem. Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Reported-and-tested-by: Bart Van Assche <bart.vanassche@sandisk.com> CC: <stable@vger.kernel.org> Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-05-17 23:32:03 +08:00
spin_unlock_irqrestore(&xhci->lock, flags);
return ret;
}
irqreturn_t xhci_msi_irq(int irq, void *hcd)
{
return xhci_irq(hcd);
}
/**** Endpoint Ring Operations ****/
/*
* Generic function for queueing a TRB on a ring.
* The caller must have checked to make sure there's room on the ring.
USB: xHCI: Fix bug in link TRB activation change. Commit 6c12db90f19727c76990e7f4801c67a148b30111 introduced a bug for control transfers. The patch was supposed to change when the link TRBs at the end of each ring segment were given to the hardware. If a transfer descriptor (TD) ended just before the link TRB, the code wouldn't give back the link TRB to the hardware; instead it would be given back in prepare_ring() just before the next TD was enqueued at the top of the ring. Unfortunately, the code relied on checking the chain bit of the TRB to determine whether the TD ended just before the link TRB. It assumed that the ring enqueuing code would call prepare_ring() before enqueuing the next TD. However, control transfers are made of multiple TDs, and prepare_ring() is only called once before enqueuing two or three TDs. If the first or second TD of the control transfer ended just before the link TRB, then the code in inc_enq() would not move the enqueue pointer past the link TRB, and the link TRB would get overwritten. This would cause the xHCI driver to start writing to memory past the ring segment, and eventually the system would crash or hang. The fix is to add a flag to inc_enq() that says whether the caller will enqueue more TDs before calling prepare_ring(). If the chain bit is cleared (meaning this is the last TRB in a TD), and the caller will not enqueue more TDs, then we defer giving back the link TRB. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Cc: stable <stable@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-06-11 03:25:28 +08:00
*
* @more_trbs_coming: Will you enqueue more TRBs before calling
* prepare_transfer()?
*/
static void queue_trb(struct xhci_hcd *xhci, struct xhci_ring *ring,
bool more_trbs_coming,
u32 field1, u32 field2, u32 field3, u32 field4)
{
struct xhci_generic_trb *trb;
trb = &ring->enqueue->generic;
trb->field[0] = cpu_to_le32(field1);
trb->field[1] = cpu_to_le32(field2);
trb->field[2] = cpu_to_le32(field3);
trb->field[3] = cpu_to_le32(field4);
trace_xhci_queue_trb(ring, trb);
inc_enq(xhci, ring, more_trbs_coming);
}
/*
* Does various checks on the endpoint ring, and makes it ready to queue num_trbs.
* FIXME allocate segments if the ring is full.
*/
static int prepare_ring(struct xhci_hcd *xhci, struct xhci_ring *ep_ring,
u32 ep_state, unsigned int num_trbs, gfp_t mem_flags)
{
unsigned int num_trbs_needed;
/* Make sure the endpoint has been added to xHC schedule */
switch (ep_state) {
case EP_STATE_DISABLED:
/*
* USB core changed config/interfaces without notifying us,
* or hardware is reporting the wrong state.
*/
xhci_warn(xhci, "WARN urb submitted to disabled ep\n");
return -ENOENT;
case EP_STATE_ERROR:
xhci_warn(xhci, "WARN waiting for error on ep to be cleared\n");
/* FIXME event handling code for error needs to clear it */
/* XXX not sure if this should be -ENOENT or not */
return -EINVAL;
case EP_STATE_HALTED:
xhci_dbg(xhci, "WARN halted endpoint, queueing URB anyway.\n");
case EP_STATE_STOPPED:
case EP_STATE_RUNNING:
break;
default:
xhci_err(xhci, "ERROR unknown endpoint state for ep\n");
/*
* FIXME issue Configure Endpoint command to try to get the HC
* back into a known state.
*/
return -EINVAL;
}
while (1) {
if (room_on_ring(xhci, ep_ring, num_trbs))
break;
if (ep_ring == xhci->cmd_ring) {
xhci_err(xhci, "Do not support expand command ring\n");
return -ENOMEM;
}
xhci_dbg_trace(xhci, trace_xhci_dbg_ring_expansion,
"ERROR no room on ep ring, try ring expansion");
num_trbs_needed = num_trbs - ep_ring->num_trbs_free;
if (xhci_ring_expansion(xhci, ep_ring, num_trbs_needed,
mem_flags)) {
xhci_err(xhci, "Ring expansion failed\n");
return -ENOMEM;
}
}
while (trb_is_link(ep_ring->enqueue)) {
/* If we're not dealing with 0.95 hardware or isoc rings
* on AMD 0.96 host, clear the chain bit.
*/
if (!xhci_link_trb_quirk(xhci) &&
!(ep_ring->type == TYPE_ISOC &&
(xhci->quirks & XHCI_AMD_0x96_HOST)))
ep_ring->enqueue->link.control &=
cpu_to_le32(~TRB_CHAIN);
else
ep_ring->enqueue->link.control |=
cpu_to_le32(TRB_CHAIN);
wmb();
ep_ring->enqueue->link.control ^= cpu_to_le32(TRB_CYCLE);
/* Toggle the cycle bit after the last ring segment. */
if (link_trb_toggles_cycle(ep_ring->enqueue))
ep_ring->cycle_state ^= 1;
ep_ring->enq_seg = ep_ring->enq_seg->next;
ep_ring->enqueue = ep_ring->enq_seg->trbs;
}
return 0;
}
static int prepare_transfer(struct xhci_hcd *xhci,
struct xhci_virt_device *xdev,
unsigned int ep_index,
USB: xhci: Correct assumptions about number of rings per endpoint. Much of the xHCI driver code assumes that endpoints only have one ring. Now an endpoint can have one ring per enabled stream ID, so correct that assumption. Use functions that translate the stream_id field in the URB or the DMA address of a TRB into the correct stream ring. Correct the polling loop to print out all enabled stream rings. Make the URB cancellation routine find the correct stream ring if the URB has stream_id set. Make sure the URB enqueueing routine does the same. Also correct the code that handles stalled/halted endpoints. Check that commands and registers that can take stream IDs handle them properly. That includes ringing an endpoint doorbell, resetting a stalled/halted endpoint, and setting a transfer ring dequeue pointer (since that command can set the dequeue pointer in a stream context or an endpoint context). Correct the transfer event handler to translate a TRB DMA address into the stream ring it was enqueued to. Make the code to allocate and prepare TD structures adds the TD to the right td_list for the stream ring. Make sure the code to give the first TRB in a TD to the hardware manipulates the correct stream ring. When an endpoint stalls, store the stream ID of the stream ring that stalled in the xhci_virt_ep structure. Use that instead of the stream ID in the URB, since an URB may be re-used after it is given back after a non-control endpoint stall. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-03 06:34:43 +08:00
unsigned int stream_id,
unsigned int num_trbs,
struct urb *urb,
unsigned int td_index,
gfp_t mem_flags)
{
int ret;
struct urb_priv *urb_priv;
struct xhci_td *td;
USB: xhci: Correct assumptions about number of rings per endpoint. Much of the xHCI driver code assumes that endpoints only have one ring. Now an endpoint can have one ring per enabled stream ID, so correct that assumption. Use functions that translate the stream_id field in the URB or the DMA address of a TRB into the correct stream ring. Correct the polling loop to print out all enabled stream rings. Make the URB cancellation routine find the correct stream ring if the URB has stream_id set. Make sure the URB enqueueing routine does the same. Also correct the code that handles stalled/halted endpoints. Check that commands and registers that can take stream IDs handle them properly. That includes ringing an endpoint doorbell, resetting a stalled/halted endpoint, and setting a transfer ring dequeue pointer (since that command can set the dequeue pointer in a stream context or an endpoint context). Correct the transfer event handler to translate a TRB DMA address into the stream ring it was enqueued to. Make the code to allocate and prepare TD structures adds the TD to the right td_list for the stream ring. Make sure the code to give the first TRB in a TD to the hardware manipulates the correct stream ring. When an endpoint stalls, store the stream ID of the stream ring that stalled in the xhci_virt_ep structure. Use that instead of the stream ID in the URB, since an URB may be re-used after it is given back after a non-control endpoint stall. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-03 06:34:43 +08:00
struct xhci_ring *ep_ring;
struct xhci_ep_ctx *ep_ctx = xhci_get_ep_ctx(xhci, xdev->out_ctx, ep_index);
USB: xhci: Correct assumptions about number of rings per endpoint. Much of the xHCI driver code assumes that endpoints only have one ring. Now an endpoint can have one ring per enabled stream ID, so correct that assumption. Use functions that translate the stream_id field in the URB or the DMA address of a TRB into the correct stream ring. Correct the polling loop to print out all enabled stream rings. Make the URB cancellation routine find the correct stream ring if the URB has stream_id set. Make sure the URB enqueueing routine does the same. Also correct the code that handles stalled/halted endpoints. Check that commands and registers that can take stream IDs handle them properly. That includes ringing an endpoint doorbell, resetting a stalled/halted endpoint, and setting a transfer ring dequeue pointer (since that command can set the dequeue pointer in a stream context or an endpoint context). Correct the transfer event handler to translate a TRB DMA address into the stream ring it was enqueued to. Make the code to allocate and prepare TD structures adds the TD to the right td_list for the stream ring. Make sure the code to give the first TRB in a TD to the hardware manipulates the correct stream ring. When an endpoint stalls, store the stream ID of the stream ring that stalled in the xhci_virt_ep structure. Use that instead of the stream ID in the URB, since an URB may be re-used after it is given back after a non-control endpoint stall. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-03 06:34:43 +08:00
ep_ring = xhci_stream_id_to_ring(xdev, ep_index, stream_id);
if (!ep_ring) {
xhci_dbg(xhci, "Can't prepare ring for bad stream ID %u\n",
stream_id);
return -EINVAL;
}
ret = prepare_ring(xhci, ep_ring, GET_EP_CTX_STATE(ep_ctx),
num_trbs, mem_flags);
if (ret)
return ret;
urb_priv = urb->hcpriv;
td = &urb_priv->td[td_index];
INIT_LIST_HEAD(&td->td_list);
INIT_LIST_HEAD(&td->cancelled_td_list);
if (td_index == 0) {
ret = usb_hcd_link_urb_to_ep(bus_to_hcd(urb->dev->bus), urb);
xhci: Fix memory leak during failed enqueue. When the isochronous transfer support was introduced, and the xHCI driver switched to using urb->hcpriv to store an "urb_priv" pointer, a couple of memory leaks were introduced into the URB enqueue function in its error handling paths. xhci_urb_enqueue allocates urb_priv, but it doesn't free it if changing the control endpoint's max packet size fails or the bulk endpoint is in the middle of allocating or deallocating streams. xhci_urb_enqueue also doesn't free urb_priv if any of the four endpoint types' enqueue functions fail. Instead, it expects those functions to free urb_priv if an error occurs. However, the bulk, control, and interrupt enqueue functions do not free urb_priv if the endpoint ring is NULL. It will, however, get freed if prepare_transfer() fails in those enqueue functions. Several of the error paths in the isochronous endpoint enqueue function also fail to free it. xhci_queue_isoc_tx_prepare() doesn't free urb_priv if prepare_ring() indicates there is not enough room for all the isochronous TDs in this URB. If individual isochronous TDs fail to be queued (perhaps due to an endpoint state change), urb_priv is also leaked. This argues that the freeing of urb_priv should be done in the function that allocated it, xhci_urb_enqueue. This patch looks rather ugly, but refactoring the code will have to wait because this patch needs to be backported to stable kernels. This patch should be backported to kernels as old as 2.6.36. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Cc: Andiry Xu <andiry.xu@amd.com> Cc: stable@kernel.org
2011-07-23 05:34:34 +08:00
if (unlikely(ret))
return ret;
}
td->urb = urb;
/* Add this TD to the tail of the endpoint ring's TD list */
list_add_tail(&td->td_list, &ep_ring->td_list);
td->start_seg = ep_ring->enq_seg;
td->first_trb = ep_ring->enqueue;
return 0;
}
unsigned int count_trbs(u64 addr, u64 len)
{
unsigned int num_trbs;
num_trbs = DIV_ROUND_UP(len + (addr & (TRB_MAX_BUFF_SIZE - 1)),
TRB_MAX_BUFF_SIZE);
if (num_trbs == 0)
num_trbs++;
return num_trbs;
}
static inline unsigned int count_trbs_needed(struct urb *urb)
{
return count_trbs(urb->transfer_dma, urb->transfer_buffer_length);
}
static unsigned int count_sg_trbs_needed(struct urb *urb)
{
struct scatterlist *sg;
unsigned int i, len, full_len, num_trbs = 0;
full_len = urb->transfer_buffer_length;
for_each_sg(urb->sg, sg, urb->num_mapped_sgs, i) {
len = sg_dma_len(sg);
num_trbs += count_trbs(sg_dma_address(sg), len);
len = min_t(unsigned int, len, full_len);
full_len -= len;
if (full_len == 0)
break;
}
return num_trbs;
}
static unsigned int count_isoc_trbs_needed(struct urb *urb, int i)
{
u64 addr, len;
addr = (u64) (urb->transfer_dma + urb->iso_frame_desc[i].offset);
len = urb->iso_frame_desc[i].length;
return count_trbs(addr, len);
}
static void check_trb_math(struct urb *urb, int running_total)
{
if (unlikely(running_total != urb->transfer_buffer_length))
dev_err(&urb->dev->dev, "%s - ep %#x - Miscalculated tx length, "
"queued %#x (%d), asked for %#x (%d)\n",
__func__,
urb->ep->desc.bEndpointAddress,
running_total, running_total,
urb->transfer_buffer_length,
urb->transfer_buffer_length);
}
static void giveback_first_trb(struct xhci_hcd *xhci, int slot_id,
USB: xhci: Correct assumptions about number of rings per endpoint. Much of the xHCI driver code assumes that endpoints only have one ring. Now an endpoint can have one ring per enabled stream ID, so correct that assumption. Use functions that translate the stream_id field in the URB or the DMA address of a TRB into the correct stream ring. Correct the polling loop to print out all enabled stream rings. Make the URB cancellation routine find the correct stream ring if the URB has stream_id set. Make sure the URB enqueueing routine does the same. Also correct the code that handles stalled/halted endpoints. Check that commands and registers that can take stream IDs handle them properly. That includes ringing an endpoint doorbell, resetting a stalled/halted endpoint, and setting a transfer ring dequeue pointer (since that command can set the dequeue pointer in a stream context or an endpoint context). Correct the transfer event handler to translate a TRB DMA address into the stream ring it was enqueued to. Make the code to allocate and prepare TD structures adds the TD to the right td_list for the stream ring. Make sure the code to give the first TRB in a TD to the hardware manipulates the correct stream ring. When an endpoint stalls, store the stream ID of the stream ring that stalled in the xhci_virt_ep structure. Use that instead of the stream ID in the URB, since an URB may be re-used after it is given back after a non-control endpoint stall. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-03 06:34:43 +08:00
unsigned int ep_index, unsigned int stream_id, int start_cycle,
struct xhci_generic_trb *start_trb)
{
/*
* Pass all the TRBs to the hardware at once and make sure this write
* isn't reordered.
*/
wmb();
if (start_cycle)
start_trb->field[3] |= cpu_to_le32(start_cycle);
else
start_trb->field[3] &= cpu_to_le32(~TRB_CYCLE);
xhci_ring_ep_doorbell(xhci, slot_id, ep_index, stream_id);
}
static void check_interval(struct xhci_hcd *xhci, struct urb *urb,
struct xhci_ep_ctx *ep_ctx)
{
int xhci_interval;
int ep_interval;
xhci_interval = EP_INTERVAL_TO_UFRAMES(le32_to_cpu(ep_ctx->ep_info));
ep_interval = urb->interval;
/* Convert to microframes */
if (urb->dev->speed == USB_SPEED_LOW ||
urb->dev->speed == USB_SPEED_FULL)
ep_interval *= 8;
/* FIXME change this to a warning and a suggestion to use the new API
* to set the polling interval (once the API is added).
*/
if (xhci_interval != ep_interval) {
dev_dbg_ratelimited(&urb->dev->dev,
"Driver uses different interval (%d microframe%s) than xHCI (%d microframe%s)\n",
ep_interval, ep_interval == 1 ? "" : "s",
xhci_interval, xhci_interval == 1 ? "" : "s");
urb->interval = xhci_interval;
/* Convert back to frames for LS/FS devices */
if (urb->dev->speed == USB_SPEED_LOW ||
urb->dev->speed == USB_SPEED_FULL)
urb->interval /= 8;
}
}
/*
* xHCI uses normal TRBs for both bulk and interrupt. When the interrupt
* endpoint is to be serviced, the xHC will consume (at most) one TD. A TD
* (comprised of sg list entries) can take several service intervals to
* transmit.
*/
int xhci_queue_intr_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
struct urb *urb, int slot_id, unsigned int ep_index)
{
struct xhci_ep_ctx *ep_ctx;
ep_ctx = xhci_get_ep_ctx(xhci, xhci->devs[slot_id]->out_ctx, ep_index);
check_interval(xhci, urb, ep_ctx);
return xhci_queue_bulk_tx(xhci, mem_flags, urb, slot_id, ep_index);
}
/*
xHCI: Fix TD Size calculation on 1.0 hosts. The xHCI 1.0 specification made a change to the TD Size field in TRBs. The value is now the number of packets that remain to be sent in the TD, not including this TRB. The TD Size value for the last TRB in a TD must always be zero. The xHCI function xhci_v1_0_td_remainder() attempts to calculate this, but it gets it wrong. First, it erroneously reuses the old xhci_td_remainder function, which will right shift the value by 10. The xHCI 1.0 spec as of June 2011 says nothing about right shifting by 10. Second, it does not set the TD size for the last TRB in a TD to zero. Third, it uses roundup instead of DIV_ROUND_UP. The total packet count is supposed to be the total number of bytes in this TD, divided by the max packet size, rounded up. DIV_ROUND_UP is the right function to use in that case. With the old code, a TD on an endpoint with max packet size 1024 would be set up like so: TRB 1, TRB length = 600 bytes, TD size = 0 TRB 1, TRB length = 200 bytes, TD size = 0 TRB 1, TRB length = 100 bytes, TD size = 0 With the new code, the TD would be set up like this: TRB 1, TRB length = 600 bytes, TD size = 1 TRB 1, TRB length = 200 bytes, TD size = 1 TRB 1, TRB length = 100 bytes, TD size = 0 This commit should be backported to kernels as old as 3.0, that contain the commit 4da6e6f247a2601ab9f1e63424e4d944ed4124f3 "xhci 1.0: Update TD size field format." Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Reported-by: Chintan Mehta <chintan.mehta@sibridgetech.com> Reported-by: Shimmer Huang <shimmering.h@gmail.com> Tested-by: Bhavik Kothari <bhavik.kothari@sibridgetech.com> Tested-by: Shimmer Huang <shimmering.h@gmail.com> Cc: stable@vger.kernel.org
2012-10-26 06:56:40 +08:00
* For xHCI 1.0 host controllers, TD size is the number of max packet sized
* packets remaining in the TD (*not* including this TRB).
*
* Total TD packet count = total_packet_count =
xHCI: Fix TD Size calculation on 1.0 hosts. The xHCI 1.0 specification made a change to the TD Size field in TRBs. The value is now the number of packets that remain to be sent in the TD, not including this TRB. The TD Size value for the last TRB in a TD must always be zero. The xHCI function xhci_v1_0_td_remainder() attempts to calculate this, but it gets it wrong. First, it erroneously reuses the old xhci_td_remainder function, which will right shift the value by 10. The xHCI 1.0 spec as of June 2011 says nothing about right shifting by 10. Second, it does not set the TD size for the last TRB in a TD to zero. Third, it uses roundup instead of DIV_ROUND_UP. The total packet count is supposed to be the total number of bytes in this TD, divided by the max packet size, rounded up. DIV_ROUND_UP is the right function to use in that case. With the old code, a TD on an endpoint with max packet size 1024 would be set up like so: TRB 1, TRB length = 600 bytes, TD size = 0 TRB 1, TRB length = 200 bytes, TD size = 0 TRB 1, TRB length = 100 bytes, TD size = 0 With the new code, the TD would be set up like this: TRB 1, TRB length = 600 bytes, TD size = 1 TRB 1, TRB length = 200 bytes, TD size = 1 TRB 1, TRB length = 100 bytes, TD size = 0 This commit should be backported to kernels as old as 3.0, that contain the commit 4da6e6f247a2601ab9f1e63424e4d944ed4124f3 "xhci 1.0: Update TD size field format." Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Reported-by: Chintan Mehta <chintan.mehta@sibridgetech.com> Reported-by: Shimmer Huang <shimmering.h@gmail.com> Tested-by: Bhavik Kothari <bhavik.kothari@sibridgetech.com> Tested-by: Shimmer Huang <shimmering.h@gmail.com> Cc: stable@vger.kernel.org
2012-10-26 06:56:40 +08:00
* DIV_ROUND_UP(TD size in bytes / wMaxPacketSize)
*
* Packets transferred up to and including this TRB = packets_transferred =
* rounddown(total bytes transferred including this TRB / wMaxPacketSize)
*
* TD size = total_packet_count - packets_transferred
*
* For xHCI 0.96 and older, TD size field should be the remaining bytes
* including this TRB, right shifted by 10
*
* For all hosts it must fit in bits 21:17, so it can't be bigger than 31.
* This is taken care of in the TRB_TD_SIZE() macro
*
xHCI: Fix TD Size calculation on 1.0 hosts. The xHCI 1.0 specification made a change to the TD Size field in TRBs. The value is now the number of packets that remain to be sent in the TD, not including this TRB. The TD Size value for the last TRB in a TD must always be zero. The xHCI function xhci_v1_0_td_remainder() attempts to calculate this, but it gets it wrong. First, it erroneously reuses the old xhci_td_remainder function, which will right shift the value by 10. The xHCI 1.0 spec as of June 2011 says nothing about right shifting by 10. Second, it does not set the TD size for the last TRB in a TD to zero. Third, it uses roundup instead of DIV_ROUND_UP. The total packet count is supposed to be the total number of bytes in this TD, divided by the max packet size, rounded up. DIV_ROUND_UP is the right function to use in that case. With the old code, a TD on an endpoint with max packet size 1024 would be set up like so: TRB 1, TRB length = 600 bytes, TD size = 0 TRB 1, TRB length = 200 bytes, TD size = 0 TRB 1, TRB length = 100 bytes, TD size = 0 With the new code, the TD would be set up like this: TRB 1, TRB length = 600 bytes, TD size = 1 TRB 1, TRB length = 200 bytes, TD size = 1 TRB 1, TRB length = 100 bytes, TD size = 0 This commit should be backported to kernels as old as 3.0, that contain the commit 4da6e6f247a2601ab9f1e63424e4d944ed4124f3 "xhci 1.0: Update TD size field format." Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Reported-by: Chintan Mehta <chintan.mehta@sibridgetech.com> Reported-by: Shimmer Huang <shimmering.h@gmail.com> Tested-by: Bhavik Kothari <bhavik.kothari@sibridgetech.com> Tested-by: Shimmer Huang <shimmering.h@gmail.com> Cc: stable@vger.kernel.org
2012-10-26 06:56:40 +08:00
* The last TRB in a TD must have the TD size set to zero.
*/
static u32 xhci_td_remainder(struct xhci_hcd *xhci, int transferred,
int trb_buff_len, unsigned int td_total_len,
struct urb *urb, bool more_trbs_coming)
{
u32 maxp, total_packet_count;
/* MTK xHCI 0.96 contains some features from 1.0 */
if (xhci->hci_version < 0x100 && !(xhci->quirks & XHCI_MTK_HOST))
return ((td_total_len - transferred) >> 10);
/* One TRB with a zero-length data packet. */
if (!more_trbs_coming || (transferred == 0 && trb_buff_len == 0) ||
trb_buff_len == td_total_len)
return 0;
/* for MTK xHCI 0.96, TD size include this TRB, but not in 1.x */
if ((xhci->quirks & XHCI_MTK_HOST) && (xhci->hci_version < 0x100))
trb_buff_len = 0;
maxp = usb_endpoint_maxp(&urb->ep->desc);
total_packet_count = DIV_ROUND_UP(td_total_len, maxp);
/* Queueing functions don't count the current TRB into transferred */
return (total_packet_count - ((transferred + trb_buff_len) / maxp));
}
static int xhci_align_td(struct xhci_hcd *xhci, struct urb *urb, u32 enqd_len,
u32 *trb_buff_len, struct xhci_segment *seg)
{
struct device *dev = xhci_to_hcd(xhci)->self.controller;
unsigned int unalign;
unsigned int max_pkt;
u32 new_buff_len;
size_t len;
max_pkt = usb_endpoint_maxp(&urb->ep->desc);
unalign = (enqd_len + *trb_buff_len) % max_pkt;
/* we got lucky, last normal TRB data on segment is packet aligned */
if (unalign == 0)
return 0;
xhci_dbg(xhci, "Unaligned %d bytes, buff len %d\n",
unalign, *trb_buff_len);
/* is the last nornal TRB alignable by splitting it */
if (*trb_buff_len > unalign) {
*trb_buff_len -= unalign;
xhci_dbg(xhci, "split align, new buff len %d\n", *trb_buff_len);
return 0;
}
/*
* We want enqd_len + trb_buff_len to sum up to a number aligned to
* number which is divisible by the endpoint's wMaxPacketSize. IOW:
* (size of currently enqueued TRBs + remainder) % wMaxPacketSize == 0.
*/
new_buff_len = max_pkt - (enqd_len % max_pkt);
if (new_buff_len > (urb->transfer_buffer_length - enqd_len))
new_buff_len = (urb->transfer_buffer_length - enqd_len);
/* create a max max_pkt sized bounce buffer pointed to by last trb */
if (usb_urb_dir_out(urb)) {
len = sg_pcopy_to_buffer(urb->sg, urb->num_sgs,
seg->bounce_buf, new_buff_len, enqd_len);
if (len != new_buff_len)
xhci_warn(xhci,
"WARN Wrong bounce buffer write length: %zu != %d\n",
len, new_buff_len);
seg->bounce_dma = dma_map_single(dev, seg->bounce_buf,
max_pkt, DMA_TO_DEVICE);
} else {
seg->bounce_dma = dma_map_single(dev, seg->bounce_buf,
max_pkt, DMA_FROM_DEVICE);
}
if (dma_mapping_error(dev, seg->bounce_dma)) {
/* try without aligning. Some host controllers survive */
xhci_warn(xhci, "Failed mapping bounce buffer, not aligning\n");
return 0;
}
*trb_buff_len = new_buff_len;
seg->bounce_len = new_buff_len;
seg->bounce_offs = enqd_len;
xhci_dbg(xhci, "Bounce align, new buff len %d\n", *trb_buff_len);
return 1;
}
/* This is very similar to what ehci-q.c qtd_fill() does */
int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
struct urb *urb, int slot_id, unsigned int ep_index)
{
struct xhci_ring *ring;
struct urb_priv *urb_priv;
struct xhci_td *td;
struct xhci_generic_trb *start_trb;
struct scatterlist *sg = NULL;
bool more_trbs_coming = true;
bool need_zero_pkt = false;
bool first_trb = true;
unsigned int num_trbs;
unsigned int start_cycle, num_sgs = 0;
unsigned int enqd_len, block_len, trb_buff_len, full_len;
int sent_len, ret;
u32 field, length_field, remainder;
u64 addr, send_addr;
ring = xhci_urb_to_transfer_ring(xhci, urb);
if (!ring)
USB: xhci: Correct assumptions about number of rings per endpoint. Much of the xHCI driver code assumes that endpoints only have one ring. Now an endpoint can have one ring per enabled stream ID, so correct that assumption. Use functions that translate the stream_id field in the URB or the DMA address of a TRB into the correct stream ring. Correct the polling loop to print out all enabled stream rings. Make the URB cancellation routine find the correct stream ring if the URB has stream_id set. Make sure the URB enqueueing routine does the same. Also correct the code that handles stalled/halted endpoints. Check that commands and registers that can take stream IDs handle them properly. That includes ringing an endpoint doorbell, resetting a stalled/halted endpoint, and setting a transfer ring dequeue pointer (since that command can set the dequeue pointer in a stream context or an endpoint context). Correct the transfer event handler to translate a TRB DMA address into the stream ring it was enqueued to. Make the code to allocate and prepare TD structures adds the TD to the right td_list for the stream ring. Make sure the code to give the first TRB in a TD to the hardware manipulates the correct stream ring. When an endpoint stalls, store the stream ID of the stream ring that stalled in the xhci_virt_ep structure. Use that instead of the stream ID in the URB, since an URB may be re-used after it is given back after a non-control endpoint stall. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-03 06:34:43 +08:00
return -EINVAL;
full_len = urb->transfer_buffer_length;
/* If we have scatter/gather list, we use it. */
if (urb->num_sgs) {
num_sgs = urb->num_mapped_sgs;
sg = urb->sg;
addr = (u64) sg_dma_address(sg);
block_len = sg_dma_len(sg);
num_trbs = count_sg_trbs_needed(urb);
} else {
num_trbs = count_trbs_needed(urb);
addr = (u64) urb->transfer_dma;
block_len = full_len;
}
ret = prepare_transfer(xhci, xhci->devs[slot_id],
USB: xhci: Correct assumptions about number of rings per endpoint. Much of the xHCI driver code assumes that endpoints only have one ring. Now an endpoint can have one ring per enabled stream ID, so correct that assumption. Use functions that translate the stream_id field in the URB or the DMA address of a TRB into the correct stream ring. Correct the polling loop to print out all enabled stream rings. Make the URB cancellation routine find the correct stream ring if the URB has stream_id set. Make sure the URB enqueueing routine does the same. Also correct the code that handles stalled/halted endpoints. Check that commands and registers that can take stream IDs handle them properly. That includes ringing an endpoint doorbell, resetting a stalled/halted endpoint, and setting a transfer ring dequeue pointer (since that command can set the dequeue pointer in a stream context or an endpoint context). Correct the transfer event handler to translate a TRB DMA address into the stream ring it was enqueued to. Make the code to allocate and prepare TD structures adds the TD to the right td_list for the stream ring. Make sure the code to give the first TRB in a TD to the hardware manipulates the correct stream ring. When an endpoint stalls, store the stream ID of the stream ring that stalled in the xhci_virt_ep structure. Use that instead of the stream ID in the URB, since an URB may be re-used after it is given back after a non-control endpoint stall. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-03 06:34:43 +08:00
ep_index, urb->stream_id,
num_trbs, urb, 0, mem_flags);
if (unlikely(ret < 0))
return ret;
urb_priv = urb->hcpriv;
/* Deal with URB_ZERO_PACKET - need one more td/trb */
if (urb->transfer_flags & URB_ZERO_PACKET && urb_priv->num_tds > 1)
need_zero_pkt = true;
td = &urb_priv->td[0];
/*
* Don't give the first TRB to the hardware (by toggling the cycle bit)
* until we've finished creating all the other TRBs. The ring's cycle
* state may change as we enqueue the other TRBs, so save it too.
*/
start_trb = &ring->enqueue->generic;
start_cycle = ring->cycle_state;
send_addr = addr;
/* Queue the TRBs, even if they are zero-length */
for (enqd_len = 0; first_trb || enqd_len < full_len;
enqd_len += trb_buff_len) {
field = TRB_TYPE(TRB_NORMAL);
/* TRB buffer should not cross 64KB boundaries */
trb_buff_len = TRB_BUFF_LEN_UP_TO_BOUNDARY(addr);
trb_buff_len = min_t(unsigned int, trb_buff_len, block_len);
if (enqd_len + trb_buff_len > full_len)
trb_buff_len = full_len - enqd_len;
/* Don't change the cycle bit of the first TRB until later */
if (first_trb) {
first_trb = false;
if (start_cycle == 0)
field |= TRB_CYCLE;
} else
field |= ring->cycle_state;
/* Chain all the TRBs together; clear the chain bit in the last
* TRB to indicate it's the last TRB in the chain.
*/
if (enqd_len + trb_buff_len < full_len) {
field |= TRB_CHAIN;
if (trb_is_link(ring->enqueue + 1)) {
if (xhci_align_td(xhci, urb, enqd_len,
&trb_buff_len,
ring->enq_seg)) {
send_addr = ring->enq_seg->bounce_dma;
/* assuming TD won't span 2 segs */
td->bounce_seg = ring->enq_seg;
}
}
}
if (enqd_len + trb_buff_len >= full_len) {
field &= ~TRB_CHAIN;
field |= TRB_IOC;
more_trbs_coming = false;
td->last_trb = ring->enqueue;
if (xhci_urb_suitable_for_idt(urb)) {
memcpy(&send_addr, urb->transfer_buffer,
trb_buff_len);
le64_to_cpus(&send_addr);
field |= TRB_IDT;
}
}
/* Only set interrupt on short packet for IN endpoints */
if (usb_urb_dir_in(urb))
field |= TRB_ISP;
/* Set the TRB length, TD size, and interrupter fields. */
remainder = xhci_td_remainder(xhci, enqd_len, trb_buff_len,
full_len, urb, more_trbs_coming);
length_field = TRB_LEN(trb_buff_len) |
TRB_TD_SIZE(remainder) |
TRB_INTR_TARGET(0);
queue_trb(xhci, ring, more_trbs_coming | need_zero_pkt,
lower_32_bits(send_addr),
upper_32_bits(send_addr),
length_field,
field);
addr += trb_buff_len;
sent_len = trb_buff_len;
while (sg && sent_len >= block_len) {
/* New sg entry */
--num_sgs;
sent_len -= block_len;
if (num_sgs != 0) {
sg = sg_next(sg);
block_len = sg_dma_len(sg);
addr = (u64) sg_dma_address(sg);
addr += sent_len;
}
}
block_len -= sent_len;
send_addr = addr;
}
if (need_zero_pkt) {
ret = prepare_transfer(xhci, xhci->devs[slot_id],
ep_index, urb->stream_id,
1, urb, 1, mem_flags);
urb_priv->td[1].last_trb = ring->enqueue;
field = TRB_TYPE(TRB_NORMAL) | ring->cycle_state | TRB_IOC;
queue_trb(xhci, ring, 0, 0, 0, TRB_INTR_TARGET(0), field);
}
check_trb_math(urb, enqd_len);
USB: xhci: Correct assumptions about number of rings per endpoint. Much of the xHCI driver code assumes that endpoints only have one ring. Now an endpoint can have one ring per enabled stream ID, so correct that assumption. Use functions that translate the stream_id field in the URB or the DMA address of a TRB into the correct stream ring. Correct the polling loop to print out all enabled stream rings. Make the URB cancellation routine find the correct stream ring if the URB has stream_id set. Make sure the URB enqueueing routine does the same. Also correct the code that handles stalled/halted endpoints. Check that commands and registers that can take stream IDs handle them properly. That includes ringing an endpoint doorbell, resetting a stalled/halted endpoint, and setting a transfer ring dequeue pointer (since that command can set the dequeue pointer in a stream context or an endpoint context). Correct the transfer event handler to translate a TRB DMA address into the stream ring it was enqueued to. Make the code to allocate and prepare TD structures adds the TD to the right td_list for the stream ring. Make sure the code to give the first TRB in a TD to the hardware manipulates the correct stream ring. When an endpoint stalls, store the stream ID of the stream ring that stalled in the xhci_virt_ep structure. Use that instead of the stream ID in the URB, since an URB may be re-used after it is given back after a non-control endpoint stall. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-03 06:34:43 +08:00
giveback_first_trb(xhci, slot_id, ep_index, urb->stream_id,
start_cycle, start_trb);
return 0;
}
/* Caller must have locked xhci->lock */
int xhci_queue_ctrl_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
struct urb *urb, int slot_id, unsigned int ep_index)
{
struct xhci_ring *ep_ring;
int num_trbs;
int ret;
struct usb_ctrlrequest *setup;
struct xhci_generic_trb *start_trb;
int start_cycle;
u32 field;
struct urb_priv *urb_priv;
struct xhci_td *td;
USB: xhci: Correct assumptions about number of rings per endpoint. Much of the xHCI driver code assumes that endpoints only have one ring. Now an endpoint can have one ring per enabled stream ID, so correct that assumption. Use functions that translate the stream_id field in the URB or the DMA address of a TRB into the correct stream ring. Correct the polling loop to print out all enabled stream rings. Make the URB cancellation routine find the correct stream ring if the URB has stream_id set. Make sure the URB enqueueing routine does the same. Also correct the code that handles stalled/halted endpoints. Check that commands and registers that can take stream IDs handle them properly. That includes ringing an endpoint doorbell, resetting a stalled/halted endpoint, and setting a transfer ring dequeue pointer (since that command can set the dequeue pointer in a stream context or an endpoint context). Correct the transfer event handler to translate a TRB DMA address into the stream ring it was enqueued to. Make the code to allocate and prepare TD structures adds the TD to the right td_list for the stream ring. Make sure the code to give the first TRB in a TD to the hardware manipulates the correct stream ring. When an endpoint stalls, store the stream ID of the stream ring that stalled in the xhci_virt_ep structure. Use that instead of the stream ID in the URB, since an URB may be re-used after it is given back after a non-control endpoint stall. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-03 06:34:43 +08:00
ep_ring = xhci_urb_to_transfer_ring(xhci, urb);
if (!ep_ring)
return -EINVAL;
/*
* Need to copy setup packet into setup TRB, so we can't use the setup
* DMA address.
*/
if (!urb->setup_packet)
return -EINVAL;
/* 1 TRB for setup, 1 for status */
num_trbs = 2;
/*
* Don't need to check if we need additional event data and normal TRBs,
* since data in control transfers will never get bigger than 16MB
* XXX: can we get a buffer that crosses 64KB boundaries?
*/
if (urb->transfer_buffer_length > 0)
num_trbs++;
USB: xhci: Correct assumptions about number of rings per endpoint. Much of the xHCI driver code assumes that endpoints only have one ring. Now an endpoint can have one ring per enabled stream ID, so correct that assumption. Use functions that translate the stream_id field in the URB or the DMA address of a TRB into the correct stream ring. Correct the polling loop to print out all enabled stream rings. Make the URB cancellation routine find the correct stream ring if the URB has stream_id set. Make sure the URB enqueueing routine does the same. Also correct the code that handles stalled/halted endpoints. Check that commands and registers that can take stream IDs handle them properly. That includes ringing an endpoint doorbell, resetting a stalled/halted endpoint, and setting a transfer ring dequeue pointer (since that command can set the dequeue pointer in a stream context or an endpoint context). Correct the transfer event handler to translate a TRB DMA address into the stream ring it was enqueued to. Make the code to allocate and prepare TD structures adds the TD to the right td_list for the stream ring. Make sure the code to give the first TRB in a TD to the hardware manipulates the correct stream ring. When an endpoint stalls, store the stream ID of the stream ring that stalled in the xhci_virt_ep structure. Use that instead of the stream ID in the URB, since an URB may be re-used after it is given back after a non-control endpoint stall. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-03 06:34:43 +08:00
ret = prepare_transfer(xhci, xhci->devs[slot_id],
ep_index, urb->stream_id,
num_trbs, urb, 0, mem_flags);
if (ret < 0)
return ret;
urb_priv = urb->hcpriv;
td = &urb_priv->td[0];
/*
* Don't give the first TRB to the hardware (by toggling the cycle bit)
* until we've finished creating all the other TRBs. The ring's cycle
* state may change as we enqueue the other TRBs, so save it too.
*/
start_trb = &ep_ring->enqueue->generic;
start_cycle = ep_ring->cycle_state;
/* Queue setup TRB - see section 6.4.1.2.1 */
/* FIXME better way to translate setup_packet into two u32 fields? */
setup = (struct usb_ctrlrequest *) urb->setup_packet;
field = 0;
field |= TRB_IDT | TRB_TYPE(TRB_SETUP);
if (start_cycle == 0)
field |= 0x1;
/* xHCI 1.0/1.1 6.4.1.2.1: Transfer Type field */
if ((xhci->hci_version >= 0x100) || (xhci->quirks & XHCI_MTK_HOST)) {
if (urb->transfer_buffer_length > 0) {
if (setup->bRequestType & USB_DIR_IN)
field |= TRB_TX_TYPE(TRB_DATA_IN);
else
field |= TRB_TX_TYPE(TRB_DATA_OUT);
}
}
queue_trb(xhci, ep_ring, true,
setup->bRequestType | setup->bRequest << 8 | le16_to_cpu(setup->wValue) << 16,
le16_to_cpu(setup->wIndex) | le16_to_cpu(setup->wLength) << 16,
TRB_LEN(8) | TRB_INTR_TARGET(0),
/* Immediate data in pointer */
field);
/* If there's data, queue data TRBs */
/* Only set interrupt on short packet for IN endpoints */
if (usb_urb_dir_in(urb))
field = TRB_ISP | TRB_TYPE(TRB_DATA);
else
field = TRB_TYPE(TRB_DATA);
if (urb->transfer_buffer_length > 0) {
u32 length_field, remainder;
u64 addr;
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;
}
remainder = xhci_td_remainder(xhci, 0,
urb->transfer_buffer_length,
urb->transfer_buffer_length,
urb, 1);
length_field = TRB_LEN(urb->transfer_buffer_length) |
TRB_TD_SIZE(remainder) |
TRB_INTR_TARGET(0);
if (setup->bRequestType & USB_DIR_IN)
field |= TRB_DIR_IN;
queue_trb(xhci, ep_ring, true,
lower_32_bits(addr),
upper_32_bits(addr),
length_field,
field | ep_ring->cycle_state);
}
/* Save the DMA address of the last TRB in the TD */
td->last_trb = ep_ring->enqueue;
/* Queue status TRB - see Table 7 and sections 4.11.2.2 and 6.4.1.2.3 */
/* If the device sent data, the status stage is an OUT transfer */
if (urb->transfer_buffer_length > 0 && setup->bRequestType & USB_DIR_IN)
field = 0;
else
field = TRB_DIR_IN;
queue_trb(xhci, ep_ring, false,
0,
0,
TRB_INTR_TARGET(0),
/* Event on completion */
field | TRB_IOC | TRB_TYPE(TRB_STATUS) | ep_ring->cycle_state);
USB: xhci: Correct assumptions about number of rings per endpoint. Much of the xHCI driver code assumes that endpoints only have one ring. Now an endpoint can have one ring per enabled stream ID, so correct that assumption. Use functions that translate the stream_id field in the URB or the DMA address of a TRB into the correct stream ring. Correct the polling loop to print out all enabled stream rings. Make the URB cancellation routine find the correct stream ring if the URB has stream_id set. Make sure the URB enqueueing routine does the same. Also correct the code that handles stalled/halted endpoints. Check that commands and registers that can take stream IDs handle them properly. That includes ringing an endpoint doorbell, resetting a stalled/halted endpoint, and setting a transfer ring dequeue pointer (since that command can set the dequeue pointer in a stream context or an endpoint context). Correct the transfer event handler to translate a TRB DMA address into the stream ring it was enqueued to. Make the code to allocate and prepare TD structures adds the TD to the right td_list for the stream ring. Make sure the code to give the first TRB in a TD to the hardware manipulates the correct stream ring. When an endpoint stalls, store the stream ID of the stream ring that stalled in the xhci_virt_ep structure. Use that instead of the stream ID in the URB, since an URB may be re-used after it is given back after a non-control endpoint stall. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-04-03 06:34:43 +08:00
giveback_first_trb(xhci, slot_id, ep_index, 0,
start_cycle, start_trb);
return 0;
}
/*
* The transfer burst count field of the isochronous TRB defines the number of
* bursts that are required to move all packets in this TD. Only SuperSpeed
* devices can burst up to bMaxBurst number of packets per service interval.
* This field is zero based, meaning a value of zero in the field means one
* burst. Basically, for everything but SuperSpeed devices, this field will be
* zero. Only xHCI 1.0 host controllers support this field.
*/
static unsigned int xhci_get_burst_count(struct xhci_hcd *xhci,
struct urb *urb, unsigned int total_packet_count)
{
unsigned int max_burst;
if (xhci->hci_version < 0x100 || urb->dev->speed < USB_SPEED_SUPER)
return 0;
max_burst = urb->ep->ss_ep_comp.bMaxBurst;
return DIV_ROUND_UP(total_packet_count, max_burst + 1) - 1;
}
/*
* Returns the number of packets in the last "burst" of packets. This field is
* valid for all speeds of devices. USB 2.0 devices can only do one "burst", so
* the last burst packet count is equal to the total number of packets in the
* TD. SuperSpeed endpoints can have up to 3 bursts. All but the last burst
* must contain (bMaxBurst + 1) number of packets, but the last burst can
* contain 1 to (bMaxBurst + 1) packets.
*/
static unsigned int xhci_get_last_burst_packet_count(struct xhci_hcd *xhci,
struct urb *urb, unsigned int total_packet_count)
{
unsigned int max_burst;
unsigned int residue;
if (xhci->hci_version < 0x100)
return 0;
if (urb->dev->speed >= USB_SPEED_SUPER) {
/* bMaxBurst is zero based: 0 means 1 packet per burst */
max_burst = urb->ep->ss_ep_comp.bMaxBurst;
residue = total_packet_count % (max_burst + 1);
/* If residue is zero, the last burst contains (max_burst + 1)
* number of packets, but the TLBPC field is zero-based.
*/
if (residue == 0)
return max_burst;
return residue - 1;
}
if (total_packet_count == 0)
return 0;
return total_packet_count - 1;
}
/*
* Calculates Frame ID field of the isochronous TRB identifies the
* target frame that the Interval associated with this Isochronous
* Transfer Descriptor will start on. Refer to 4.11.2.5 in 1.1 spec.
*
* Returns actual frame id on success, negative value on error.
*/
static int xhci_get_isoc_frame_id(struct xhci_hcd *xhci,
struct urb *urb, int index)
{
int start_frame, ist, ret = 0;
int start_frame_id, end_frame_id, current_frame_id;
if (urb->dev->speed == USB_SPEED_LOW ||
urb->dev->speed == USB_SPEED_FULL)
start_frame = urb->start_frame + index * urb->interval;
else
start_frame = (urb->start_frame + index * urb->interval) >> 3;
/* Isochronous Scheduling Threshold (IST, bits 0~3 in HCSPARAMS2):
*
* If bit [3] of IST is cleared to '0', software can add a TRB no
* later than IST[2:0] Microframes before that TRB is scheduled to
* be executed.
* If bit [3] of IST is set to '1', software can add a TRB no later
* than IST[2:0] Frames before that TRB is scheduled to be executed.
*/
ist = HCS_IST(xhci->hcs_params2) & 0x7;
if (HCS_IST(xhci->hcs_params2) & (1 << 3))
ist <<= 3;
/* Software shall not schedule an Isoch TD with a Frame ID value that
* is less than the Start Frame ID or greater than the End Frame ID,
* where:
*
* End Frame ID = (Current MFINDEX register value + 895 ms.) MOD 2048
* Start Frame ID = (Current MFINDEX register value + IST + 1) MOD 2048
*
* Both the End Frame ID and Start Frame ID values are calculated
* in microframes. When software determines the valid Frame ID value;
* The End Frame ID value should be rounded down to the nearest Frame
* boundary, and the Start Frame ID value should be rounded up to the
* nearest Frame boundary.
*/
current_frame_id = readl(&xhci->run_regs->microframe_index);
start_frame_id = roundup(current_frame_id + ist + 1, 8);
end_frame_id = rounddown(current_frame_id + 895 * 8, 8);
start_frame &= 0x7ff;
start_frame_id = (start_frame_id >> 3) & 0x7ff;
end_frame_id = (end_frame_id >> 3) & 0x7ff;
xhci_dbg(xhci, "%s: index %d, reg 0x%x start_frame_id 0x%x, end_frame_id 0x%x, start_frame 0x%x\n",
__func__, index, readl(&xhci->run_regs->microframe_index),
start_frame_id, end_frame_id, start_frame);
if (start_frame_id < end_frame_id) {
if (start_frame > end_frame_id ||
start_frame < start_frame_id)
ret = -EINVAL;
} else if (start_frame_id > end_frame_id) {
if ((start_frame > end_frame_id &&
start_frame < start_frame_id))
ret = -EINVAL;
} else {
ret = -EINVAL;
}
if (index == 0) {
if (ret == -EINVAL || start_frame == start_frame_id) {
start_frame = start_frame_id + 1;
if (urb->dev->speed == USB_SPEED_LOW ||
urb->dev->speed == USB_SPEED_FULL)
urb->start_frame = start_frame;
else
urb->start_frame = start_frame << 3;
ret = 0;
}
}
if (ret) {
xhci_warn(xhci, "Frame ID %d (reg %d, index %d) beyond range (%d, %d)\n",
start_frame, current_frame_id, index,
start_frame_id, end_frame_id);
xhci_warn(xhci, "Ignore frame ID field, use SIA bit instead\n");
return ret;
}
return start_frame;
}
/* This is for isoc transfer */
static int xhci_queue_isoc_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
struct urb *urb, int slot_id, unsigned int ep_index)
{
struct xhci_ring *ep_ring;
struct urb_priv *urb_priv;
struct xhci_td *td;
int num_tds, trbs_per_td;
struct xhci_generic_trb *start_trb;
bool first_trb;
int start_cycle;
u32 field, length_field;
int running_total, trb_buff_len, td_len, td_remain_len, ret;
u64 start_addr, addr;
int i, j;
bool more_trbs_coming;
struct xhci_virt_ep *xep;
int frame_id;
xep = &xhci->devs[slot_id]->eps[ep_index];
ep_ring = xhci->devs[slot_id]->eps[ep_index].ring;
num_tds = urb->number_of_packets;
if (num_tds < 1) {
xhci_dbg(xhci, "Isoc URB with zero packets?\n");
return -EINVAL;
}
start_addr = (u64) urb->transfer_dma;
start_trb = &ep_ring->enqueue->generic;
start_cycle = ep_ring->cycle_state;
xhci: Fix failed enqueue in the middle of isoch TD. When an isochronous transfer is enqueued, xhci_queue_isoc_tx_prepare() will ensure that there is enough room on the transfer rings for all of the isochronous TDs for that URB. However, when xhci_queue_isoc_tx() is enqueueing individual isoc TDs, the prepare_transfer() function can fail if the endpoint state has changed to disabled, error, or some other unknown state. With the current code, if Nth TD (not the first TD) fails, the ring is left in a sorry state. The partially enqueued TDs are left on the ring, and the first TRB of the TD is not given back to the hardware. The enqueue pointer is left on the TRB after the last successfully enqueued TD. This means the ring is basically useless. Any new transfers will be enqueued after the failed TDs, which the hardware will never read because the cycle bit indicates it does not own them. The ring will fill up with untransferred TDs, and the endpoint will be basically unusable. The untransferred TDs will also remain on the TD list. Since the td_list is a FIFO, this basically means the ring handler will be waiting on TDs that will never be completed (or worse, dereference memory that doesn't exist any more). Change the code to clean up the isochronous ring after a failed transfer. If the first TD failed, simply return and allow the xhci_urb_enqueue function to free the urb_priv. If the Nth TD failed, first remove the TDs from the td_list. Then convert the TRBs that were enqueued into No-op TRBs. Make sure to flip the cycle bit on all enqueued TRBs (including any link TRBs in the middle or between TDs), but leave the cycle bit of the first TRB (which will show software-owned) intact. Then move the ring enqueue pointer back to the first TRB and make sure to change the xhci_ring's cycle state to what is appropriate for that ring segment. This ensures that the No-op TRBs will be overwritten by subsequent TDs, and the hardware will not start executing random TRBs because the cycle bit was left as hardware-owned. This bug is unlikely to be hit, but it was something I noticed while tracking down the watchdog timer issue. I verified that the fix works by injecting some errors on the 250th isochronous URB queued, although I could not verify that the ring is in the correct state because uvcvideo refused to talk to the device after the first usb_submit_urb() failed. Ring debugging shows that the ring looks correct, however. This patch should be backported to kernels as old as 2.6.36. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Cc: Andiry Xu <andiry.xu@amd.com> Cc: stable@kernel.org
2011-07-30 03:44:32 +08:00
urb_priv = urb->hcpriv;
/* Queue the TRBs for each TD, even if they are zero-length */
for (i = 0; i < num_tds; i++) {
unsigned int total_pkt_count, max_pkt;
unsigned int burst_count, last_burst_pkt_count;
u32 sia_frame_id;
first_trb = true;
running_total = 0;
addr = start_addr + urb->iso_frame_desc[i].offset;
td_len = urb->iso_frame_desc[i].length;
td_remain_len = td_len;
max_pkt = usb_endpoint_maxp(&urb->ep->desc);
total_pkt_count = DIV_ROUND_UP(td_len, max_pkt);
/* A zero-length transfer still involves at least one packet. */
if (total_pkt_count == 0)
total_pkt_count++;
burst_count = xhci_get_burst_count(xhci, urb, total_pkt_count);
last_burst_pkt_count = xhci_get_last_burst_packet_count(xhci,
urb, total_pkt_count);
trbs_per_td = count_isoc_trbs_needed(urb, i);
ret = prepare_transfer(xhci, xhci->devs[slot_id], ep_index,
urb->stream_id, trbs_per_td, urb, i, mem_flags);
xhci: Fix failed enqueue in the middle of isoch TD. When an isochronous transfer is enqueued, xhci_queue_isoc_tx_prepare() will ensure that there is enough room on the transfer rings for all of the isochronous TDs for that URB. However, when xhci_queue_isoc_tx() is enqueueing individual isoc TDs, the prepare_transfer() function can fail if the endpoint state has changed to disabled, error, or some other unknown state. With the current code, if Nth TD (not the first TD) fails, the ring is left in a sorry state. The partially enqueued TDs are left on the ring, and the first TRB of the TD is not given back to the hardware. The enqueue pointer is left on the TRB after the last successfully enqueued TD. This means the ring is basically useless. Any new transfers will be enqueued after the failed TDs, which the hardware will never read because the cycle bit indicates it does not own them. The ring will fill up with untransferred TDs, and the endpoint will be basically unusable. The untransferred TDs will also remain on the TD list. Since the td_list is a FIFO, this basically means the ring handler will be waiting on TDs that will never be completed (or worse, dereference memory that doesn't exist any more). Change the code to clean up the isochronous ring after a failed transfer. If the first TD failed, simply return and allow the xhci_urb_enqueue function to free the urb_priv. If the Nth TD failed, first remove the TDs from the td_list. Then convert the TRBs that were enqueued into No-op TRBs. Make sure to flip the cycle bit on all enqueued TRBs (including any link TRBs in the middle or between TDs), but leave the cycle bit of the first TRB (which will show software-owned) intact. Then move the ring enqueue pointer back to the first TRB and make sure to change the xhci_ring's cycle state to what is appropriate for that ring segment. This ensures that the No-op TRBs will be overwritten by subsequent TDs, and the hardware will not start executing random TRBs because the cycle bit was left as hardware-owned. This bug is unlikely to be hit, but it was something I noticed while tracking down the watchdog timer issue. I verified that the fix works by injecting some errors on the 250th isochronous URB queued, although I could not verify that the ring is in the correct state because uvcvideo refused to talk to the device after the first usb_submit_urb() failed. Ring debugging shows that the ring looks correct, however. This patch should be backported to kernels as old as 2.6.36. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Cc: Andiry Xu <andiry.xu@amd.com> Cc: stable@kernel.org
2011-07-30 03:44:32 +08:00
if (ret < 0) {
if (i == 0)
return ret;
goto cleanup;
}
td = &urb_priv->td[i];
/* use SIA as default, if frame id is used overwrite it */
sia_frame_id = TRB_SIA;
if (!(urb->transfer_flags & URB_ISO_ASAP) &&
HCC_CFC(xhci->hcc_params)) {
frame_id = xhci_get_isoc_frame_id(xhci, urb, i);
if (frame_id >= 0)
sia_frame_id = TRB_FRAME_ID(frame_id);
}
/*
* Set isoc specific data for the first TRB in a TD.
* Prevent HW from getting the TRBs by keeping the cycle state
* inverted in the first TDs isoc TRB.
*/
field = TRB_TYPE(TRB_ISOC) |
TRB_TLBPC(last_burst_pkt_count) |
sia_frame_id |
(i ? ep_ring->cycle_state : !start_cycle);
/* xhci 1.1 with ETE uses TD_Size field for TBC, old is Rsvdz */
if (!xep->use_extended_tbc)
field |= TRB_TBC(burst_count);
/* fill the rest of the TRB fields, and remaining normal TRBs */
for (j = 0; j < trbs_per_td; j++) {
u32 remainder = 0;
/* only first TRB is isoc, overwrite otherwise */
if (!first_trb)
field = TRB_TYPE(TRB_NORMAL) |
ep_ring->cycle_state;
/* Only set interrupt on short packet for IN EPs */
if (usb_urb_dir_in(urb))
field |= TRB_ISP;
/* Set the chain bit for all except the last TRB */
if (j < trbs_per_td - 1) {
more_trbs_coming = true;
field |= TRB_CHAIN;
} else {
more_trbs_coming = false;
td->last_trb = ep_ring->enqueue;
field |= TRB_IOC;
/* set BEI, except for the last TD */
if (xhci->hci_version >= 0x100 &&
!(xhci->quirks & XHCI_AVOID_BEI) &&
i < num_tds - 1)
field |= TRB_BEI;
}
/* Calculate TRB length */
trb_buff_len = TRB_BUFF_LEN_UP_TO_BOUNDARY(addr);
if (trb_buff_len > td_remain_len)
trb_buff_len = td_remain_len;
/* Set the TRB length, TD size, & interrupter fields. */
remainder = xhci_td_remainder(xhci, running_total,
trb_buff_len, td_len,
urb, more_trbs_coming);
length_field = TRB_LEN(trb_buff_len) |
TRB_INTR_TARGET(0);
/* xhci 1.1 with ETE uses TD Size field for TBC */
if (first_trb && xep->use_extended_tbc)
length_field |= TRB_TD_SIZE_TBC(burst_count);
else
length_field |= TRB_TD_SIZE(remainder);
first_trb = false;
queue_trb(xhci, ep_ring, more_trbs_coming,
lower_32_bits(addr),
upper_32_bits(addr),
length_field,
field);
running_total += trb_buff_len;
addr += trb_buff_len;
td_remain_len -= trb_buff_len;
}
/* Check TD length */
if (running_total != td_len) {
xhci_err(xhci, "ISOC TD length unmatch\n");
ret = -EINVAL;
goto cleanup;
}
}
/* store the next frame id */
if (HCC_CFC(xhci->hcc_params))
xep->next_frame_id = urb->start_frame + num_tds * urb->interval;
if (xhci_to_hcd(xhci)->self.bandwidth_isoc_reqs == 0) {
if (xhci->quirks & XHCI_AMD_PLL_FIX)
usb_amd_quirk_pll_disable();
}
xhci_to_hcd(xhci)->self.bandwidth_isoc_reqs++;
giveback_first_trb(xhci, slot_id, ep_index, urb->stream_id,
start_cycle, start_trb);
return 0;
xhci: Fix failed enqueue in the middle of isoch TD. When an isochronous transfer is enqueued, xhci_queue_isoc_tx_prepare() will ensure that there is enough room on the transfer rings for all of the isochronous TDs for that URB. However, when xhci_queue_isoc_tx() is enqueueing individual isoc TDs, the prepare_transfer() function can fail if the endpoint state has changed to disabled, error, or some other unknown state. With the current code, if Nth TD (not the first TD) fails, the ring is left in a sorry state. The partially enqueued TDs are left on the ring, and the first TRB of the TD is not given back to the hardware. The enqueue pointer is left on the TRB after the last successfully enqueued TD. This means the ring is basically useless. Any new transfers will be enqueued after the failed TDs, which the hardware will never read because the cycle bit indicates it does not own them. The ring will fill up with untransferred TDs, and the endpoint will be basically unusable. The untransferred TDs will also remain on the TD list. Since the td_list is a FIFO, this basically means the ring handler will be waiting on TDs that will never be completed (or worse, dereference memory that doesn't exist any more). Change the code to clean up the isochronous ring after a failed transfer. If the first TD failed, simply return and allow the xhci_urb_enqueue function to free the urb_priv. If the Nth TD failed, first remove the TDs from the td_list. Then convert the TRBs that were enqueued into No-op TRBs. Make sure to flip the cycle bit on all enqueued TRBs (including any link TRBs in the middle or between TDs), but leave the cycle bit of the first TRB (which will show software-owned) intact. Then move the ring enqueue pointer back to the first TRB and make sure to change the xhci_ring's cycle state to what is appropriate for that ring segment. This ensures that the No-op TRBs will be overwritten by subsequent TDs, and the hardware will not start executing random TRBs because the cycle bit was left as hardware-owned. This bug is unlikely to be hit, but it was something I noticed while tracking down the watchdog timer issue. I verified that the fix works by injecting some errors on the 250th isochronous URB queued, although I could not verify that the ring is in the correct state because uvcvideo refused to talk to the device after the first usb_submit_urb() failed. Ring debugging shows that the ring looks correct, however. This patch should be backported to kernels as old as 2.6.36. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Cc: Andiry Xu <andiry.xu@amd.com> Cc: stable@kernel.org
2011-07-30 03:44:32 +08:00
cleanup:
/* Clean up a partially enqueued isoc transfer. */
for (i--; i >= 0; i--)
list_del_init(&urb_priv->td[i].td_list);
xhci: Fix failed enqueue in the middle of isoch TD. When an isochronous transfer is enqueued, xhci_queue_isoc_tx_prepare() will ensure that there is enough room on the transfer rings for all of the isochronous TDs for that URB. However, when xhci_queue_isoc_tx() is enqueueing individual isoc TDs, the prepare_transfer() function can fail if the endpoint state has changed to disabled, error, or some other unknown state. With the current code, if Nth TD (not the first TD) fails, the ring is left in a sorry state. The partially enqueued TDs are left on the ring, and the first TRB of the TD is not given back to the hardware. The enqueue pointer is left on the TRB after the last successfully enqueued TD. This means the ring is basically useless. Any new transfers will be enqueued after the failed TDs, which the hardware will never read because the cycle bit indicates it does not own them. The ring will fill up with untransferred TDs, and the endpoint will be basically unusable. The untransferred TDs will also remain on the TD list. Since the td_list is a FIFO, this basically means the ring handler will be waiting on TDs that will never be completed (or worse, dereference memory that doesn't exist any more). Change the code to clean up the isochronous ring after a failed transfer. If the first TD failed, simply return and allow the xhci_urb_enqueue function to free the urb_priv. If the Nth TD failed, first remove the TDs from the td_list. Then convert the TRBs that were enqueued into No-op TRBs. Make sure to flip the cycle bit on all enqueued TRBs (including any link TRBs in the middle or between TDs), but leave the cycle bit of the first TRB (which will show software-owned) intact. Then move the ring enqueue pointer back to the first TRB and make sure to change the xhci_ring's cycle state to what is appropriate for that ring segment. This ensures that the No-op TRBs will be overwritten by subsequent TDs, and the hardware will not start executing random TRBs because the cycle bit was left as hardware-owned. This bug is unlikely to be hit, but it was something I noticed while tracking down the watchdog timer issue. I verified that the fix works by injecting some errors on the 250th isochronous URB queued, although I could not verify that the ring is in the correct state because uvcvideo refused to talk to the device after the first usb_submit_urb() failed. Ring debugging shows that the ring looks correct, however. This patch should be backported to kernels as old as 2.6.36. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Cc: Andiry Xu <andiry.xu@amd.com> Cc: stable@kernel.org
2011-07-30 03:44:32 +08:00
/* Use the first TD as a temporary variable to turn the TDs we've queued
* into No-ops with a software-owned cycle bit. That way the hardware
* won't accidentally start executing bogus TDs when we partially
* overwrite them. td->first_trb and td->start_seg are already set.
*/
urb_priv->td[0].last_trb = ep_ring->enqueue;
xhci: Fix failed enqueue in the middle of isoch TD. When an isochronous transfer is enqueued, xhci_queue_isoc_tx_prepare() will ensure that there is enough room on the transfer rings for all of the isochronous TDs for that URB. However, when xhci_queue_isoc_tx() is enqueueing individual isoc TDs, the prepare_transfer() function can fail if the endpoint state has changed to disabled, error, or some other unknown state. With the current code, if Nth TD (not the first TD) fails, the ring is left in a sorry state. The partially enqueued TDs are left on the ring, and the first TRB of the TD is not given back to the hardware. The enqueue pointer is left on the TRB after the last successfully enqueued TD. This means the ring is basically useless. Any new transfers will be enqueued after the failed TDs, which the hardware will never read because the cycle bit indicates it does not own them. The ring will fill up with untransferred TDs, and the endpoint will be basically unusable. The untransferred TDs will also remain on the TD list. Since the td_list is a FIFO, this basically means the ring handler will be waiting on TDs that will never be completed (or worse, dereference memory that doesn't exist any more). Change the code to clean up the isochronous ring after a failed transfer. If the first TD failed, simply return and allow the xhci_urb_enqueue function to free the urb_priv. If the Nth TD failed, first remove the TDs from the td_list. Then convert the TRBs that were enqueued into No-op TRBs. Make sure to flip the cycle bit on all enqueued TRBs (including any link TRBs in the middle or between TDs), but leave the cycle bit of the first TRB (which will show software-owned) intact. Then move the ring enqueue pointer back to the first TRB and make sure to change the xhci_ring's cycle state to what is appropriate for that ring segment. This ensures that the No-op TRBs will be overwritten by subsequent TDs, and the hardware will not start executing random TRBs because the cycle bit was left as hardware-owned. This bug is unlikely to be hit, but it was something I noticed while tracking down the watchdog timer issue. I verified that the fix works by injecting some errors on the 250th isochronous URB queued, although I could not verify that the ring is in the correct state because uvcvideo refused to talk to the device after the first usb_submit_urb() failed. Ring debugging shows that the ring looks correct, however. This patch should be backported to kernels as old as 2.6.36. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Cc: Andiry Xu <andiry.xu@amd.com> Cc: stable@kernel.org
2011-07-30 03:44:32 +08:00
/* Every TRB except the first & last will have its cycle bit flipped. */
td_to_noop(xhci, ep_ring, &urb_priv->td[0], true);
xhci: Fix failed enqueue in the middle of isoch TD. When an isochronous transfer is enqueued, xhci_queue_isoc_tx_prepare() will ensure that there is enough room on the transfer rings for all of the isochronous TDs for that URB. However, when xhci_queue_isoc_tx() is enqueueing individual isoc TDs, the prepare_transfer() function can fail if the endpoint state has changed to disabled, error, or some other unknown state. With the current code, if Nth TD (not the first TD) fails, the ring is left in a sorry state. The partially enqueued TDs are left on the ring, and the first TRB of the TD is not given back to the hardware. The enqueue pointer is left on the TRB after the last successfully enqueued TD. This means the ring is basically useless. Any new transfers will be enqueued after the failed TDs, which the hardware will never read because the cycle bit indicates it does not own them. The ring will fill up with untransferred TDs, and the endpoint will be basically unusable. The untransferred TDs will also remain on the TD list. Since the td_list is a FIFO, this basically means the ring handler will be waiting on TDs that will never be completed (or worse, dereference memory that doesn't exist any more). Change the code to clean up the isochronous ring after a failed transfer. If the first TD failed, simply return and allow the xhci_urb_enqueue function to free the urb_priv. If the Nth TD failed, first remove the TDs from the td_list. Then convert the TRBs that were enqueued into No-op TRBs. Make sure to flip the cycle bit on all enqueued TRBs (including any link TRBs in the middle or between TDs), but leave the cycle bit of the first TRB (which will show software-owned) intact. Then move the ring enqueue pointer back to the first TRB and make sure to change the xhci_ring's cycle state to what is appropriate for that ring segment. This ensures that the No-op TRBs will be overwritten by subsequent TDs, and the hardware will not start executing random TRBs because the cycle bit was left as hardware-owned. This bug is unlikely to be hit, but it was something I noticed while tracking down the watchdog timer issue. I verified that the fix works by injecting some errors on the 250th isochronous URB queued, although I could not verify that the ring is in the correct state because uvcvideo refused to talk to the device after the first usb_submit_urb() failed. Ring debugging shows that the ring looks correct, however. This patch should be backported to kernels as old as 2.6.36. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Cc: Andiry Xu <andiry.xu@amd.com> Cc: stable@kernel.org
2011-07-30 03:44:32 +08:00
/* Reset the ring enqueue back to the first TRB and its cycle bit. */
ep_ring->enqueue = urb_priv->td[0].first_trb;
ep_ring->enq_seg = urb_priv->td[0].start_seg;
xhci: Fix failed enqueue in the middle of isoch TD. When an isochronous transfer is enqueued, xhci_queue_isoc_tx_prepare() will ensure that there is enough room on the transfer rings for all of the isochronous TDs for that URB. However, when xhci_queue_isoc_tx() is enqueueing individual isoc TDs, the prepare_transfer() function can fail if the endpoint state has changed to disabled, error, or some other unknown state. With the current code, if Nth TD (not the first TD) fails, the ring is left in a sorry state. The partially enqueued TDs are left on the ring, and the first TRB of the TD is not given back to the hardware. The enqueue pointer is left on the TRB after the last successfully enqueued TD. This means the ring is basically useless. Any new transfers will be enqueued after the failed TDs, which the hardware will never read because the cycle bit indicates it does not own them. The ring will fill up with untransferred TDs, and the endpoint will be basically unusable. The untransferred TDs will also remain on the TD list. Since the td_list is a FIFO, this basically means the ring handler will be waiting on TDs that will never be completed (or worse, dereference memory that doesn't exist any more). Change the code to clean up the isochronous ring after a failed transfer. If the first TD failed, simply return and allow the xhci_urb_enqueue function to free the urb_priv. If the Nth TD failed, first remove the TDs from the td_list. Then convert the TRBs that were enqueued into No-op TRBs. Make sure to flip the cycle bit on all enqueued TRBs (including any link TRBs in the middle or between TDs), but leave the cycle bit of the first TRB (which will show software-owned) intact. Then move the ring enqueue pointer back to the first TRB and make sure to change the xhci_ring's cycle state to what is appropriate for that ring segment. This ensures that the No-op TRBs will be overwritten by subsequent TDs, and the hardware will not start executing random TRBs because the cycle bit was left as hardware-owned. This bug is unlikely to be hit, but it was something I noticed while tracking down the watchdog timer issue. I verified that the fix works by injecting some errors on the 250th isochronous URB queued, although I could not verify that the ring is in the correct state because uvcvideo refused to talk to the device after the first usb_submit_urb() failed. Ring debugging shows that the ring looks correct, however. This patch should be backported to kernels as old as 2.6.36. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Cc: Andiry Xu <andiry.xu@amd.com> Cc: stable@kernel.org
2011-07-30 03:44:32 +08:00
ep_ring->cycle_state = start_cycle;
ep_ring->num_trbs_free = ep_ring->num_trbs_free_temp;
xhci: Fix failed enqueue in the middle of isoch TD. When an isochronous transfer is enqueued, xhci_queue_isoc_tx_prepare() will ensure that there is enough room on the transfer rings for all of the isochronous TDs for that URB. However, when xhci_queue_isoc_tx() is enqueueing individual isoc TDs, the prepare_transfer() function can fail if the endpoint state has changed to disabled, error, or some other unknown state. With the current code, if Nth TD (not the first TD) fails, the ring is left in a sorry state. The partially enqueued TDs are left on the ring, and the first TRB of the TD is not given back to the hardware. The enqueue pointer is left on the TRB after the last successfully enqueued TD. This means the ring is basically useless. Any new transfers will be enqueued after the failed TDs, which the hardware will never read because the cycle bit indicates it does not own them. The ring will fill up with untransferred TDs, and the endpoint will be basically unusable. The untransferred TDs will also remain on the TD list. Since the td_list is a FIFO, this basically means the ring handler will be waiting on TDs that will never be completed (or worse, dereference memory that doesn't exist any more). Change the code to clean up the isochronous ring after a failed transfer. If the first TD failed, simply return and allow the xhci_urb_enqueue function to free the urb_priv. If the Nth TD failed, first remove the TDs from the td_list. Then convert the TRBs that were enqueued into No-op TRBs. Make sure to flip the cycle bit on all enqueued TRBs (including any link TRBs in the middle or between TDs), but leave the cycle bit of the first TRB (which will show software-owned) intact. Then move the ring enqueue pointer back to the first TRB and make sure to change the xhci_ring's cycle state to what is appropriate for that ring segment. This ensures that the No-op TRBs will be overwritten by subsequent TDs, and the hardware will not start executing random TRBs because the cycle bit was left as hardware-owned. This bug is unlikely to be hit, but it was something I noticed while tracking down the watchdog timer issue. I verified that the fix works by injecting some errors on the 250th isochronous URB queued, although I could not verify that the ring is in the correct state because uvcvideo refused to talk to the device after the first usb_submit_urb() failed. Ring debugging shows that the ring looks correct, however. This patch should be backported to kernels as old as 2.6.36. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Cc: Andiry Xu <andiry.xu@amd.com> Cc: stable@kernel.org
2011-07-30 03:44:32 +08:00
usb_hcd_unlink_urb_from_ep(bus_to_hcd(urb->dev->bus), urb);
return ret;
}
/*
* Check transfer ring to guarantee there is enough room for the urb.
* Update ISO URB start_frame and interval.
* Update interval as xhci_queue_intr_tx does. Use xhci frame_index to
* update urb->start_frame if URB_ISO_ASAP is set in transfer_flags or
* Contiguous Frame ID is not supported by HC.
*/
int xhci_queue_isoc_tx_prepare(struct xhci_hcd *xhci, gfp_t mem_flags,
struct urb *urb, int slot_id, unsigned int ep_index)
{
struct xhci_virt_device *xdev;
struct xhci_ring *ep_ring;
struct xhci_ep_ctx *ep_ctx;
int start_frame;
int num_tds, num_trbs, i;
int ret;
struct xhci_virt_ep *xep;
int ist;
xdev = xhci->devs[slot_id];
xep = &xhci->devs[slot_id]->eps[ep_index];
ep_ring = xdev->eps[ep_index].ring;
ep_ctx = xhci_get_ep_ctx(xhci, xdev->out_ctx, ep_index);
num_trbs = 0;
num_tds = urb->number_of_packets;
for (i = 0; i < num_tds; i++)
num_trbs += count_isoc_trbs_needed(urb, i);
/* Check the ring to guarantee there is enough room for the whole urb.
* Do not insert any td of the urb to the ring if the check failed.
*/
ret = prepare_ring(xhci, ep_ring, GET_EP_CTX_STATE(ep_ctx),
num_trbs, mem_flags);
if (ret)
return ret;
/*
* Check interval value. This should be done before we start to
* calculate the start frame value.
*/
check_interval(xhci, urb, ep_ctx);
/* Calculate the start frame and put it in urb->start_frame. */
if (HCC_CFC(xhci->hcc_params) && !list_empty(&ep_ring->td_list)) {
if (GET_EP_CTX_STATE(ep_ctx) == EP_STATE_RUNNING) {
urb->start_frame = xep->next_frame_id;
goto skip_start_over;
}
}
start_frame = readl(&xhci->run_regs->microframe_index);
start_frame &= 0x3fff;
/*
* Round up to the next frame and consider the time before trb really
* gets scheduled by hardare.
*/
ist = HCS_IST(xhci->hcs_params2) & 0x7;
if (HCS_IST(xhci->hcs_params2) & (1 << 3))
ist <<= 3;
start_frame += ist + XHCI_CFC_DELAY;
start_frame = roundup(start_frame, 8);
/*
* Round up to the next ESIT (Endpoint Service Interval Time) if ESIT
* is greate than 8 microframes.
*/
if (urb->dev->speed == USB_SPEED_LOW ||
urb->dev->speed == USB_SPEED_FULL) {
start_frame = roundup(start_frame, urb->interval << 3);
urb->start_frame = start_frame >> 3;
} else {
start_frame = roundup(start_frame, urb->interval);
urb->start_frame = start_frame;
}
skip_start_over:
ep_ring->num_trbs_free_temp = ep_ring->num_trbs_free;
return xhci_queue_isoc_tx(xhci, mem_flags, urb, slot_id, ep_index);
}
/**** Command Ring Operations ****/
/* Generic function for queueing a command TRB on the command ring.
* Check to make sure there's room on the command ring for one command TRB.
* Also check that there's room reserved for commands that must not fail.
* If this is a command that must not fail, meaning command_must_succeed = TRUE,
* then only check for the number of reserved spots.
* Don't decrement xhci->cmd_ring_reserved_trbs after we've queued the TRB
* because the command event handler may want to resubmit a failed command.
*/
static int queue_command(struct xhci_hcd *xhci, struct xhci_command *cmd,
u32 field1, u32 field2,
u32 field3, u32 field4, bool command_must_succeed)
{
int reserved_trbs = xhci->cmd_ring_reserved_trbs;
int ret;
usb: xhci: fix xhci locking up during hcd remove The problem seems to be that if a new device is detected while we have already removed the shared HCD, then many of the xhci operations (e.g. xhci_alloc_dev(), xhci_setup_device()) hang as command never completes. I don't think XHCI can operate without the shared HCD as we've already called xhci_halt() in xhci_only_stop_hcd() when shared HCD goes away. We need to prevent new commands from being queued not only when HCD is dying but also when HCD is halted. The following lockup was detected while testing the otg state machine. [ 178.199951] xhci-hcd xhci-hcd.0.auto: xHCI Host Controller [ 178.205799] xhci-hcd xhci-hcd.0.auto: new USB bus registered, assigned bus number 1 [ 178.214458] xhci-hcd xhci-hcd.0.auto: hcc params 0x0220f04c hci version 0x100 quirks 0x00010010 [ 178.223619] xhci-hcd xhci-hcd.0.auto: irq 400, io mem 0x48890000 [ 178.230677] usb usb1: New USB device found, idVendor=1d6b, idProduct=0002 [ 178.237796] usb usb1: New USB device strings: Mfr=3, Product=2, SerialNumber=1 [ 178.245358] usb usb1: Product: xHCI Host Controller [ 178.250483] usb usb1: Manufacturer: Linux 4.0.0-rc1-00024-g6111320 xhci-hcd [ 178.257783] usb usb1: SerialNumber: xhci-hcd.0.auto [ 178.267014] hub 1-0:1.0: USB hub found [ 178.272108] hub 1-0:1.0: 1 port detected [ 178.278371] xhci-hcd xhci-hcd.0.auto: xHCI Host Controller [ 178.284171] xhci-hcd xhci-hcd.0.auto: new USB bus registered, assigned bus number 2 [ 178.294038] usb usb2: New USB device found, idVendor=1d6b, idProduct=0003 [ 178.301183] usb usb2: New USB device strings: Mfr=3, Product=2, SerialNumber=1 [ 178.308776] usb usb2: Product: xHCI Host Controller [ 178.313902] usb usb2: Manufacturer: Linux 4.0.0-rc1-00024-g6111320 xhci-hcd [ 178.321222] usb usb2: SerialNumber: xhci-hcd.0.auto [ 178.329061] hub 2-0:1.0: USB hub found [ 178.333126] hub 2-0:1.0: 1 port detected [ 178.567585] dwc3 48890000.usb: usb_otg_start_host 0 [ 178.572707] xhci-hcd xhci-hcd.0.auto: remove, state 4 [ 178.578064] usb usb2: USB disconnect, device number 1 [ 178.586565] xhci-hcd xhci-hcd.0.auto: USB bus 2 deregistered [ 178.592585] xhci-hcd xhci-hcd.0.auto: remove, state 1 [ 178.597924] usb usb1: USB disconnect, device number 1 [ 178.603248] usb 1-1: new high-speed USB device number 2 using xhci-hcd [ 190.597337] INFO: task kworker/u4:0:6 blocked for more than 10 seconds. [ 190.604273] Not tainted 4.0.0-rc1-00024-g6111320 #1058 [ 190.610228] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 190.618443] kworker/u4:0 D c05c0ac0 0 6 2 0x00000000 [ 190.625120] Workqueue: usb_otg usb_otg_work [ 190.629533] [<c05c0ac0>] (__schedule) from [<c05c10ac>] (schedule+0x34/0x98) [ 190.636915] [<c05c10ac>] (schedule) from [<c05c1318>] (schedule_preempt_disabled+0xc/0x10) [ 190.645591] [<c05c1318>] (schedule_preempt_disabled) from [<c05c23d0>] (mutex_lock_nested+0x1ac/0x3fc) [ 190.655353] [<c05c23d0>] (mutex_lock_nested) from [<c046cf8c>] (usb_disconnect+0x3c/0x208) [ 190.664043] [<c046cf8c>] (usb_disconnect) from [<c0470cf0>] (_usb_remove_hcd+0x98/0x1d8) [ 190.672535] [<c0470cf0>] (_usb_remove_hcd) from [<c0485da8>] (usb_otg_start_host+0x50/0xf4) [ 190.681299] [<c0485da8>] (usb_otg_start_host) from [<c04849a4>] (otg_set_protocol+0x5c/0xd0) [ 190.690153] [<c04849a4>] (otg_set_protocol) from [<c0484b88>] (otg_set_state+0x170/0xbfc) [ 190.698735] [<c0484b88>] (otg_set_state) from [<c0485740>] (otg_statemachine+0x12c/0x470) [ 190.707326] [<c0485740>] (otg_statemachine) from [<c0053c84>] (process_one_work+0x1b4/0x4a0) [ 190.716162] [<c0053c84>] (process_one_work) from [<c00540f8>] (worker_thread+0x154/0x44c) [ 190.724742] [<c00540f8>] (worker_thread) from [<c0058f88>] (kthread+0xd4/0xf0) [ 190.732328] [<c0058f88>] (kthread) from [<c000e810>] (ret_from_fork+0x14/0x24) [ 190.739898] 5 locks held by kworker/u4:0/6: [ 190.744274] #0: ("%s""usb_otg"){.+.+.+}, at: [<c0053bf4>] process_one_work+0x124/0x4a0 [ 190.752799] #1: ((&otgd->work)){+.+.+.}, at: [<c0053bf4>] process_one_work+0x124/0x4a0 [ 190.761326] #2: (&otgd->fsm.lock){+.+.+.}, at: [<c048562c>] otg_statemachine+0x18/0x470 [ 190.769934] #3: (usb_bus_list_lock){+.+.+.}, at: [<c0470ce8>] _usb_remove_hcd+0x90/0x1d8 [ 190.778635] #4: (&dev->mutex){......}, at: [<c046cf8c>] usb_disconnect+0x3c/0x208 [ 190.786700] INFO: task kworker/1:0:14 blocked for more than 10 seconds. [ 190.793633] Not tainted 4.0.0-rc1-00024-g6111320 #1058 [ 190.799567] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 190.807783] kworker/1:0 D c05c0ac0 0 14 2 0x00000000 [ 190.814457] Workqueue: usb_hub_wq hub_event [ 190.818866] [<c05c0ac0>] (__schedule) from [<c05c10ac>] (schedule+0x34/0x98) [ 190.826252] [<c05c10ac>] (schedule) from [<c05c4e40>] (schedule_timeout+0x13c/0x1ec) [ 190.834377] [<c05c4e40>] (schedule_timeout) from [<c05c19f0>] (wait_for_common+0xbc/0x150) [ 190.843062] [<c05c19f0>] (wait_for_common) from [<bf068a3c>] (xhci_setup_device+0x164/0x5cc [xhci_hcd]) [ 190.852986] [<bf068a3c>] (xhci_setup_device [xhci_hcd]) from [<c046b7f4>] (hub_port_init+0x3f4/0xb10) [ 190.862667] [<c046b7f4>] (hub_port_init) from [<c046eb64>] (hub_event+0x704/0x1018) [ 190.870704] [<c046eb64>] (hub_event) from [<c0053c84>] (process_one_work+0x1b4/0x4a0) [ 190.878919] [<c0053c84>] (process_one_work) from [<c00540f8>] (worker_thread+0x154/0x44c) [ 190.887503] [<c00540f8>] (worker_thread) from [<c0058f88>] (kthread+0xd4/0xf0) [ 190.895076] [<c0058f88>] (kthread) from [<c000e810>] (ret_from_fork+0x14/0x24) [ 190.902650] 5 locks held by kworker/1:0/14: [ 190.907023] #0: ("usb_hub_wq"){.+.+.+}, at: [<c0053bf4>] process_one_work+0x124/0x4a0 [ 190.915454] #1: ((&hub->events)){+.+.+.}, at: [<c0053bf4>] process_one_work+0x124/0x4a0 [ 190.924070] #2: (&dev->mutex){......}, at: [<c046e490>] hub_event+0x30/0x1018 [ 190.931768] #3: (&port_dev->status_lock){+.+.+.}, at: [<c046eb50>] hub_event+0x6f0/0x1018 [ 190.940558] #4: (&bus->usb_address0_mutex){+.+.+.}, at: [<c046b458>] hub_port_init+0x58/0xb10 Signed-off-by: Roger Quadros <rogerq@ti.com> Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2015-05-29 22:01:49 +08:00
if ((xhci->xhc_state & XHCI_STATE_DYING) ||
(xhci->xhc_state & XHCI_STATE_HALTED)) {
usb: xhci: fix xhci locking up during hcd remove The problem seems to be that if a new device is detected while we have already removed the shared HCD, then many of the xhci operations (e.g. xhci_alloc_dev(), xhci_setup_device()) hang as command never completes. I don't think XHCI can operate without the shared HCD as we've already called xhci_halt() in xhci_only_stop_hcd() when shared HCD goes away. We need to prevent new commands from being queued not only when HCD is dying but also when HCD is halted. The following lockup was detected while testing the otg state machine. [ 178.199951] xhci-hcd xhci-hcd.0.auto: xHCI Host Controller [ 178.205799] xhci-hcd xhci-hcd.0.auto: new USB bus registered, assigned bus number 1 [ 178.214458] xhci-hcd xhci-hcd.0.auto: hcc params 0x0220f04c hci version 0x100 quirks 0x00010010 [ 178.223619] xhci-hcd xhci-hcd.0.auto: irq 400, io mem 0x48890000 [ 178.230677] usb usb1: New USB device found, idVendor=1d6b, idProduct=0002 [ 178.237796] usb usb1: New USB device strings: Mfr=3, Product=2, SerialNumber=1 [ 178.245358] usb usb1: Product: xHCI Host Controller [ 178.250483] usb usb1: Manufacturer: Linux 4.0.0-rc1-00024-g6111320 xhci-hcd [ 178.257783] usb usb1: SerialNumber: xhci-hcd.0.auto [ 178.267014] hub 1-0:1.0: USB hub found [ 178.272108] hub 1-0:1.0: 1 port detected [ 178.278371] xhci-hcd xhci-hcd.0.auto: xHCI Host Controller [ 178.284171] xhci-hcd xhci-hcd.0.auto: new USB bus registered, assigned bus number 2 [ 178.294038] usb usb2: New USB device found, idVendor=1d6b, idProduct=0003 [ 178.301183] usb usb2: New USB device strings: Mfr=3, Product=2, SerialNumber=1 [ 178.308776] usb usb2: Product: xHCI Host Controller [ 178.313902] usb usb2: Manufacturer: Linux 4.0.0-rc1-00024-g6111320 xhci-hcd [ 178.321222] usb usb2: SerialNumber: xhci-hcd.0.auto [ 178.329061] hub 2-0:1.0: USB hub found [ 178.333126] hub 2-0:1.0: 1 port detected [ 178.567585] dwc3 48890000.usb: usb_otg_start_host 0 [ 178.572707] xhci-hcd xhci-hcd.0.auto: remove, state 4 [ 178.578064] usb usb2: USB disconnect, device number 1 [ 178.586565] xhci-hcd xhci-hcd.0.auto: USB bus 2 deregistered [ 178.592585] xhci-hcd xhci-hcd.0.auto: remove, state 1 [ 178.597924] usb usb1: USB disconnect, device number 1 [ 178.603248] usb 1-1: new high-speed USB device number 2 using xhci-hcd [ 190.597337] INFO: task kworker/u4:0:6 blocked for more than 10 seconds. [ 190.604273] Not tainted 4.0.0-rc1-00024-g6111320 #1058 [ 190.610228] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 190.618443] kworker/u4:0 D c05c0ac0 0 6 2 0x00000000 [ 190.625120] Workqueue: usb_otg usb_otg_work [ 190.629533] [<c05c0ac0>] (__schedule) from [<c05c10ac>] (schedule+0x34/0x98) [ 190.636915] [<c05c10ac>] (schedule) from [<c05c1318>] (schedule_preempt_disabled+0xc/0x10) [ 190.645591] [<c05c1318>] (schedule_preempt_disabled) from [<c05c23d0>] (mutex_lock_nested+0x1ac/0x3fc) [ 190.655353] [<c05c23d0>] (mutex_lock_nested) from [<c046cf8c>] (usb_disconnect+0x3c/0x208) [ 190.664043] [<c046cf8c>] (usb_disconnect) from [<c0470cf0>] (_usb_remove_hcd+0x98/0x1d8) [ 190.672535] [<c0470cf0>] (_usb_remove_hcd) from [<c0485da8>] (usb_otg_start_host+0x50/0xf4) [ 190.681299] [<c0485da8>] (usb_otg_start_host) from [<c04849a4>] (otg_set_protocol+0x5c/0xd0) [ 190.690153] [<c04849a4>] (otg_set_protocol) from [<c0484b88>] (otg_set_state+0x170/0xbfc) [ 190.698735] [<c0484b88>] (otg_set_state) from [<c0485740>] (otg_statemachine+0x12c/0x470) [ 190.707326] [<c0485740>] (otg_statemachine) from [<c0053c84>] (process_one_work+0x1b4/0x4a0) [ 190.716162] [<c0053c84>] (process_one_work) from [<c00540f8>] (worker_thread+0x154/0x44c) [ 190.724742] [<c00540f8>] (worker_thread) from [<c0058f88>] (kthread+0xd4/0xf0) [ 190.732328] [<c0058f88>] (kthread) from [<c000e810>] (ret_from_fork+0x14/0x24) [ 190.739898] 5 locks held by kworker/u4:0/6: [ 190.744274] #0: ("%s""usb_otg"){.+.+.+}, at: [<c0053bf4>] process_one_work+0x124/0x4a0 [ 190.752799] #1: ((&otgd->work)){+.+.+.}, at: [<c0053bf4>] process_one_work+0x124/0x4a0 [ 190.761326] #2: (&otgd->fsm.lock){+.+.+.}, at: [<c048562c>] otg_statemachine+0x18/0x470 [ 190.769934] #3: (usb_bus_list_lock){+.+.+.}, at: [<c0470ce8>] _usb_remove_hcd+0x90/0x1d8 [ 190.778635] #4: (&dev->mutex){......}, at: [<c046cf8c>] usb_disconnect+0x3c/0x208 [ 190.786700] INFO: task kworker/1:0:14 blocked for more than 10 seconds. [ 190.793633] Not tainted 4.0.0-rc1-00024-g6111320 #1058 [ 190.799567] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 190.807783] kworker/1:0 D c05c0ac0 0 14 2 0x00000000 [ 190.814457] Workqueue: usb_hub_wq hub_event [ 190.818866] [<c05c0ac0>] (__schedule) from [<c05c10ac>] (schedule+0x34/0x98) [ 190.826252] [<c05c10ac>] (schedule) from [<c05c4e40>] (schedule_timeout+0x13c/0x1ec) [ 190.834377] [<c05c4e40>] (schedule_timeout) from [<c05c19f0>] (wait_for_common+0xbc/0x150) [ 190.843062] [<c05c19f0>] (wait_for_common) from [<bf068a3c>] (xhci_setup_device+0x164/0x5cc [xhci_hcd]) [ 190.852986] [<bf068a3c>] (xhci_setup_device [xhci_hcd]) from [<c046b7f4>] (hub_port_init+0x3f4/0xb10) [ 190.862667] [<c046b7f4>] (hub_port_init) from [<c046eb64>] (hub_event+0x704/0x1018) [ 190.870704] [<c046eb64>] (hub_event) from [<c0053c84>] (process_one_work+0x1b4/0x4a0) [ 190.878919] [<c0053c84>] (process_one_work) from [<c00540f8>] (worker_thread+0x154/0x44c) [ 190.887503] [<c00540f8>] (worker_thread) from [<c0058f88>] (kthread+0xd4/0xf0) [ 190.895076] [<c0058f88>] (kthread) from [<c000e810>] (ret_from_fork+0x14/0x24) [ 190.902650] 5 locks held by kworker/1:0/14: [ 190.907023] #0: ("usb_hub_wq"){.+.+.+}, at: [<c0053bf4>] process_one_work+0x124/0x4a0 [ 190.915454] #1: ((&hub->events)){+.+.+.}, at: [<c0053bf4>] process_one_work+0x124/0x4a0 [ 190.924070] #2: (&dev->mutex){......}, at: [<c046e490>] hub_event+0x30/0x1018 [ 190.931768] #3: (&port_dev->status_lock){+.+.+.}, at: [<c046eb50>] hub_event+0x6f0/0x1018 [ 190.940558] #4: (&bus->usb_address0_mutex){+.+.+.}, at: [<c046b458>] hub_port_init+0x58/0xb10 Signed-off-by: Roger Quadros <rogerq@ti.com> Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2015-05-29 22:01:49 +08:00
xhci_dbg(xhci, "xHCI dying or halted, can't queue_command\n");
return -ESHUTDOWN;
usb: xhci: fix xhci locking up during hcd remove The problem seems to be that if a new device is detected while we have already removed the shared HCD, then many of the xhci operations (e.g. xhci_alloc_dev(), xhci_setup_device()) hang as command never completes. I don't think XHCI can operate without the shared HCD as we've already called xhci_halt() in xhci_only_stop_hcd() when shared HCD goes away. We need to prevent new commands from being queued not only when HCD is dying but also when HCD is halted. The following lockup was detected while testing the otg state machine. [ 178.199951] xhci-hcd xhci-hcd.0.auto: xHCI Host Controller [ 178.205799] xhci-hcd xhci-hcd.0.auto: new USB bus registered, assigned bus number 1 [ 178.214458] xhci-hcd xhci-hcd.0.auto: hcc params 0x0220f04c hci version 0x100 quirks 0x00010010 [ 178.223619] xhci-hcd xhci-hcd.0.auto: irq 400, io mem 0x48890000 [ 178.230677] usb usb1: New USB device found, idVendor=1d6b, idProduct=0002 [ 178.237796] usb usb1: New USB device strings: Mfr=3, Product=2, SerialNumber=1 [ 178.245358] usb usb1: Product: xHCI Host Controller [ 178.250483] usb usb1: Manufacturer: Linux 4.0.0-rc1-00024-g6111320 xhci-hcd [ 178.257783] usb usb1: SerialNumber: xhci-hcd.0.auto [ 178.267014] hub 1-0:1.0: USB hub found [ 178.272108] hub 1-0:1.0: 1 port detected [ 178.278371] xhci-hcd xhci-hcd.0.auto: xHCI Host Controller [ 178.284171] xhci-hcd xhci-hcd.0.auto: new USB bus registered, assigned bus number 2 [ 178.294038] usb usb2: New USB device found, idVendor=1d6b, idProduct=0003 [ 178.301183] usb usb2: New USB device strings: Mfr=3, Product=2, SerialNumber=1 [ 178.308776] usb usb2: Product: xHCI Host Controller [ 178.313902] usb usb2: Manufacturer: Linux 4.0.0-rc1-00024-g6111320 xhci-hcd [ 178.321222] usb usb2: SerialNumber: xhci-hcd.0.auto [ 178.329061] hub 2-0:1.0: USB hub found [ 178.333126] hub 2-0:1.0: 1 port detected [ 178.567585] dwc3 48890000.usb: usb_otg_start_host 0 [ 178.572707] xhci-hcd xhci-hcd.0.auto: remove, state 4 [ 178.578064] usb usb2: USB disconnect, device number 1 [ 178.586565] xhci-hcd xhci-hcd.0.auto: USB bus 2 deregistered [ 178.592585] xhci-hcd xhci-hcd.0.auto: remove, state 1 [ 178.597924] usb usb1: USB disconnect, device number 1 [ 178.603248] usb 1-1: new high-speed USB device number 2 using xhci-hcd [ 190.597337] INFO: task kworker/u4:0:6 blocked for more than 10 seconds. [ 190.604273] Not tainted 4.0.0-rc1-00024-g6111320 #1058 [ 190.610228] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 190.618443] kworker/u4:0 D c05c0ac0 0 6 2 0x00000000 [ 190.625120] Workqueue: usb_otg usb_otg_work [ 190.629533] [<c05c0ac0>] (__schedule) from [<c05c10ac>] (schedule+0x34/0x98) [ 190.636915] [<c05c10ac>] (schedule) from [<c05c1318>] (schedule_preempt_disabled+0xc/0x10) [ 190.645591] [<c05c1318>] (schedule_preempt_disabled) from [<c05c23d0>] (mutex_lock_nested+0x1ac/0x3fc) [ 190.655353] [<c05c23d0>] (mutex_lock_nested) from [<c046cf8c>] (usb_disconnect+0x3c/0x208) [ 190.664043] [<c046cf8c>] (usb_disconnect) from [<c0470cf0>] (_usb_remove_hcd+0x98/0x1d8) [ 190.672535] [<c0470cf0>] (_usb_remove_hcd) from [<c0485da8>] (usb_otg_start_host+0x50/0xf4) [ 190.681299] [<c0485da8>] (usb_otg_start_host) from [<c04849a4>] (otg_set_protocol+0x5c/0xd0) [ 190.690153] [<c04849a4>] (otg_set_protocol) from [<c0484b88>] (otg_set_state+0x170/0xbfc) [ 190.698735] [<c0484b88>] (otg_set_state) from [<c0485740>] (otg_statemachine+0x12c/0x470) [ 190.707326] [<c0485740>] (otg_statemachine) from [<c0053c84>] (process_one_work+0x1b4/0x4a0) [ 190.716162] [<c0053c84>] (process_one_work) from [<c00540f8>] (worker_thread+0x154/0x44c) [ 190.724742] [<c00540f8>] (worker_thread) from [<c0058f88>] (kthread+0xd4/0xf0) [ 190.732328] [<c0058f88>] (kthread) from [<c000e810>] (ret_from_fork+0x14/0x24) [ 190.739898] 5 locks held by kworker/u4:0/6: [ 190.744274] #0: ("%s""usb_otg"){.+.+.+}, at: [<c0053bf4>] process_one_work+0x124/0x4a0 [ 190.752799] #1: ((&otgd->work)){+.+.+.}, at: [<c0053bf4>] process_one_work+0x124/0x4a0 [ 190.761326] #2: (&otgd->fsm.lock){+.+.+.}, at: [<c048562c>] otg_statemachine+0x18/0x470 [ 190.769934] #3: (usb_bus_list_lock){+.+.+.}, at: [<c0470ce8>] _usb_remove_hcd+0x90/0x1d8 [ 190.778635] #4: (&dev->mutex){......}, at: [<c046cf8c>] usb_disconnect+0x3c/0x208 [ 190.786700] INFO: task kworker/1:0:14 blocked for more than 10 seconds. [ 190.793633] Not tainted 4.0.0-rc1-00024-g6111320 #1058 [ 190.799567] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 190.807783] kworker/1:0 D c05c0ac0 0 14 2 0x00000000 [ 190.814457] Workqueue: usb_hub_wq hub_event [ 190.818866] [<c05c0ac0>] (__schedule) from [<c05c10ac>] (schedule+0x34/0x98) [ 190.826252] [<c05c10ac>] (schedule) from [<c05c4e40>] (schedule_timeout+0x13c/0x1ec) [ 190.834377] [<c05c4e40>] (schedule_timeout) from [<c05c19f0>] (wait_for_common+0xbc/0x150) [ 190.843062] [<c05c19f0>] (wait_for_common) from [<bf068a3c>] (xhci_setup_device+0x164/0x5cc [xhci_hcd]) [ 190.852986] [<bf068a3c>] (xhci_setup_device [xhci_hcd]) from [<c046b7f4>] (hub_port_init+0x3f4/0xb10) [ 190.862667] [<c046b7f4>] (hub_port_init) from [<c046eb64>] (hub_event+0x704/0x1018) [ 190.870704] [<c046eb64>] (hub_event) from [<c0053c84>] (process_one_work+0x1b4/0x4a0) [ 190.878919] [<c0053c84>] (process_one_work) from [<c00540f8>] (worker_thread+0x154/0x44c) [ 190.887503] [<c00540f8>] (worker_thread) from [<c0058f88>] (kthread+0xd4/0xf0) [ 190.895076] [<c0058f88>] (kthread) from [<c000e810>] (ret_from_fork+0x14/0x24) [ 190.902650] 5 locks held by kworker/1:0/14: [ 190.907023] #0: ("usb_hub_wq"){.+.+.+}, at: [<c0053bf4>] process_one_work+0x124/0x4a0 [ 190.915454] #1: ((&hub->events)){+.+.+.}, at: [<c0053bf4>] process_one_work+0x124/0x4a0 [ 190.924070] #2: (&dev->mutex){......}, at: [<c046e490>] hub_event+0x30/0x1018 [ 190.931768] #3: (&port_dev->status_lock){+.+.+.}, at: [<c046eb50>] hub_event+0x6f0/0x1018 [ 190.940558] #4: (&bus->usb_address0_mutex){+.+.+.}, at: [<c046b458>] hub_port_init+0x58/0xb10 Signed-off-by: Roger Quadros <rogerq@ti.com> Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2015-05-29 22:01:49 +08:00
}
if (!command_must_succeed)
reserved_trbs++;
ret = prepare_ring(xhci, xhci->cmd_ring, EP_STATE_RUNNING,
reserved_trbs, GFP_ATOMIC);
if (ret < 0) {
xhci_err(xhci, "ERR: No room for command on command ring\n");
if (command_must_succeed)
xhci_err(xhci, "ERR: Reserved TRB counting for "
"unfailable commands failed.\n");
return ret;
}
cmd->command_trb = xhci->cmd_ring->enqueue;
xhci: rework command timeout and cancellation, Use one timer to control command timeout. start/kick the timer every time a command is completed and a new command is waiting, or a new command is added to a empty list. If the timer runs out, then tag the current command as "aborted", and start the xhci command abortion process. Previously each function that submitted a command had its own timer. If that command timed out, a new command structure for the command was created and it was put on a cancel_cmd_list list, then a pci write to abort the command ring was issued. when the ring was aborted, it checked if the current command was the one to be canceled, later when the ring was stopped the driver got ownership of the TRBs in the command ring, compared then to the TRBs in the cancel_cmd_list, and turned them into No-ops. Now, instead, at timeout we tag the status of the command in the command queue to be aborted, and start the ring abortion. Ring abortion stops the command ring and gives control of the commands to us. All the aborted commands are now turned into No-ops. If the ring is already stopped when the command times outs its not possible to start the ring abortion, in this case the command is turnd to No-op right away. All these changes allows us to remove the entire cancel_cmd_list code. The functions waiting for a command to finish no longer have their own timeouts. They will wait either until the command completes normally, or until the whole command abortion is done. Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-05-09 00:26:03 +08:00
/* if there are no other commands queued we start the timeout timer */
if (list_empty(&xhci->cmd_list)) {
xhci: rework command timeout and cancellation, Use one timer to control command timeout. start/kick the timer every time a command is completed and a new command is waiting, or a new command is added to a empty list. If the timer runs out, then tag the current command as "aborted", and start the xhci command abortion process. Previously each function that submitted a command had its own timer. If that command timed out, a new command structure for the command was created and it was put on a cancel_cmd_list list, then a pci write to abort the command ring was issued. when the ring was aborted, it checked if the current command was the one to be canceled, later when the ring was stopped the driver got ownership of the TRBs in the command ring, compared then to the TRBs in the cancel_cmd_list, and turned them into No-ops. Now, instead, at timeout we tag the status of the command in the command queue to be aborted, and start the ring abortion. Ring abortion stops the command ring and gives control of the commands to us. All the aborted commands are now turned into No-ops. If the ring is already stopped when the command times outs its not possible to start the ring abortion, in this case the command is turnd to No-op right away. All these changes allows us to remove the entire cancel_cmd_list code. The functions waiting for a command to finish no longer have their own timeouts. They will wait either until the command completes normally, or until the whole command abortion is done. Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-05-09 00:26:03 +08:00
xhci->current_cmd = cmd;
xhci_mod_cmd_timer(xhci, XHCI_CMD_DEFAULT_TIMEOUT);
xhci: rework command timeout and cancellation, Use one timer to control command timeout. start/kick the timer every time a command is completed and a new command is waiting, or a new command is added to a empty list. If the timer runs out, then tag the current command as "aborted", and start the xhci command abortion process. Previously each function that submitted a command had its own timer. If that command timed out, a new command structure for the command was created and it was put on a cancel_cmd_list list, then a pci write to abort the command ring was issued. when the ring was aborted, it checked if the current command was the one to be canceled, later when the ring was stopped the driver got ownership of the TRBs in the command ring, compared then to the TRBs in the cancel_cmd_list, and turned them into No-ops. Now, instead, at timeout we tag the status of the command in the command queue to be aborted, and start the ring abortion. Ring abortion stops the command ring and gives control of the commands to us. All the aborted commands are now turned into No-ops. If the ring is already stopped when the command times outs its not possible to start the ring abortion, in this case the command is turnd to No-op right away. All these changes allows us to remove the entire cancel_cmd_list code. The functions waiting for a command to finish no longer have their own timeouts. They will wait either until the command completes normally, or until the whole command abortion is done. Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-05-09 00:26:03 +08:00
}
list_add_tail(&cmd->cmd_list, &xhci->cmd_list);
queue_trb(xhci, xhci->cmd_ring, false, field1, field2, field3,
field4 | xhci->cmd_ring->cycle_state);
return 0;
}
/* Queue a slot enable or disable request on the command ring */
int xhci_queue_slot_control(struct xhci_hcd *xhci, struct xhci_command *cmd,
u32 trb_type, u32 slot_id)
{
return queue_command(xhci, cmd, 0, 0, 0,
TRB_TYPE(trb_type) | SLOT_ID_FOR_TRB(slot_id), false);
}
/* Queue an address device command TRB */
int xhci_queue_address_device(struct xhci_hcd *xhci, struct xhci_command *cmd,
dma_addr_t in_ctx_ptr, u32 slot_id, enum xhci_setup_dev setup)
{
return queue_command(xhci, cmd, lower_32_bits(in_ctx_ptr),
upper_32_bits(in_ctx_ptr), 0,
usb: xhci: change enumeration scheme to 'new scheme' by default Change the default enumeration scheme for xhci attached non-SuperSpeed devices from: Reset SetAddress [xhci address-device BSR = 0] GetDescriptor(8) GetDescriptor(18) ...to: Reset [xhci address-device BSR = 1] GetDescriptor(64) Reset SetAddress [xhci address-device BSR = 0] GetDescriptor(18) ...as some devices misbehave when encountering a SetAddress command prior to GetDescriptor. There are known legacy devices that require this scheme, but testing has found at least one USB3 device that fails enumeration when presented with this ordering. For now, follow the ehci case and enable 'new scheme' by default for non-SuperSpeed devices. To support this enumeration scheme on xhci the AddressDevice operation needs to be performed twice. The first instance of the command enables the HC's device and slot context info for the device, but omits sending the device a SetAddress command (BSR == block set address request). Then, after GetDescriptor completes, follow up with the full AddressDevice+SetAddress operation. As mentioned before, this ordering of events with USB3 devices causes an extra state transition to be exposed to xhci. Previously USB3 devices would transition directly from 'enabled' to 'addressed' and never need to underrun responses to 'get descriptor'. We do see the 64-byte descriptor fetch the correct data, but the following 18-byte descriptor read after the reset gets: bLength = 0 bDescriptorType = 0 bcdUSB = 0 bDeviceClass = 0 bDeviceSubClass = 0 bDeviceProtocol = 0 bMaxPacketSize0 = 9 instead of: bLength = 12 bDescriptorType = 1 bcdUSB = 300 bDeviceClass = 0 bDeviceSubClass = 0 bDeviceProtocol = 0 bMaxPacketSize0 = 9 which results in the discovery process looping until falling back to 'old scheme' enumeration. Acked-by: Alan Stern <stern@rowland.harvard.edu> Reported-by: David Moore <david.moore@gmail.com> Suggested-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
2013-12-06 09:07:27 +08:00
TRB_TYPE(TRB_ADDR_DEV) | SLOT_ID_FOR_TRB(slot_id)
| (setup == SETUP_CONTEXT_ONLY ? TRB_BSR : 0), false);
}
int xhci_queue_vendor_command(struct xhci_hcd *xhci, struct xhci_command *cmd,
u32 field1, u32 field2, u32 field3, u32 field4)
{
return queue_command(xhci, cmd, field1, field2, field3, field4, false);
}
/* Queue a reset device command TRB */
int xhci_queue_reset_device(struct xhci_hcd *xhci, struct xhci_command *cmd,
u32 slot_id)
{
return queue_command(xhci, cmd, 0, 0, 0,
TRB_TYPE(TRB_RESET_DEV) | SLOT_ID_FOR_TRB(slot_id),
false);
}
USB: xhci: Bandwidth allocation support Since the xHCI host controller hardware (xHC) has an internal schedule, it needs a better representation of what devices are consuming bandwidth on the bus. Each device is represented by a device context, with data about the device, endpoints, and pointers to each endpoint ring. We need to update the endpoint information for a device context before a new configuration or alternate interface setting is selected. We setup an input device context with modified endpoint information and newly allocated endpoint rings, and then submit a Configure Endpoint Command to the hardware. The host controller can reject the new configuration if it exceeds the bus bandwidth, or the host controller doesn't have enough internal resources for the configuration. If the command fails, we still have the older device context with the previous configuration. If the command succeeds, we free the old endpoint rings. The root hub isn't a real device, so always say yes to any bandwidth changes for it. The USB core will enable, disable, and then enable endpoint 0 several times during the initialization sequence. The device will always have an endpoint ring for endpoint 0 and bandwidth allocated for that, unless the device is disconnected or gets a SetAddress 0 request. So we don't pay attention for when xhci_check_bandwidth() is called for a re-add of endpoint 0. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-28 10:58:38 +08:00
/* Queue a configure endpoint command TRB */
int xhci_queue_configure_endpoint(struct xhci_hcd *xhci,
struct xhci_command *cmd, dma_addr_t in_ctx_ptr,
u32 slot_id, bool command_must_succeed)
USB: xhci: Bandwidth allocation support Since the xHCI host controller hardware (xHC) has an internal schedule, it needs a better representation of what devices are consuming bandwidth on the bus. Each device is represented by a device context, with data about the device, endpoints, and pointers to each endpoint ring. We need to update the endpoint information for a device context before a new configuration or alternate interface setting is selected. We setup an input device context with modified endpoint information and newly allocated endpoint rings, and then submit a Configure Endpoint Command to the hardware. The host controller can reject the new configuration if it exceeds the bus bandwidth, or the host controller doesn't have enough internal resources for the configuration. If the command fails, we still have the older device context with the previous configuration. If the command succeeds, we free the old endpoint rings. The root hub isn't a real device, so always say yes to any bandwidth changes for it. The USB core will enable, disable, and then enable endpoint 0 several times during the initialization sequence. The device will always have an endpoint ring for endpoint 0 and bandwidth allocated for that, unless the device is disconnected or gets a SetAddress 0 request. So we don't pay attention for when xhci_check_bandwidth() is called for a re-add of endpoint 0. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-28 10:58:38 +08:00
{
return queue_command(xhci, cmd, lower_32_bits(in_ctx_ptr),
upper_32_bits(in_ctx_ptr), 0,
TRB_TYPE(TRB_CONFIG_EP) | SLOT_ID_FOR_TRB(slot_id),
command_must_succeed);
USB: xhci: Bandwidth allocation support Since the xHCI host controller hardware (xHC) has an internal schedule, it needs a better representation of what devices are consuming bandwidth on the bus. Each device is represented by a device context, with data about the device, endpoints, and pointers to each endpoint ring. We need to update the endpoint information for a device context before a new configuration or alternate interface setting is selected. We setup an input device context with modified endpoint information and newly allocated endpoint rings, and then submit a Configure Endpoint Command to the hardware. The host controller can reject the new configuration if it exceeds the bus bandwidth, or the host controller doesn't have enough internal resources for the configuration. If the command fails, we still have the older device context with the previous configuration. If the command succeeds, we free the old endpoint rings. The root hub isn't a real device, so always say yes to any bandwidth changes for it. The USB core will enable, disable, and then enable endpoint 0 several times during the initialization sequence. The device will always have an endpoint ring for endpoint 0 and bandwidth allocated for that, unless the device is disconnected or gets a SetAddress 0 request. So we don't pay attention for when xhci_check_bandwidth() is called for a re-add of endpoint 0. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-28 10:58:38 +08:00
}
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
/* Queue an evaluate context command TRB */
int xhci_queue_evaluate_context(struct xhci_hcd *xhci, struct xhci_command *cmd,
dma_addr_t in_ctx_ptr, u32 slot_id, bool command_must_succeed)
{
return queue_command(xhci, cmd, lower_32_bits(in_ctx_ptr),
upper_32_bits(in_ctx_ptr), 0,
TRB_TYPE(TRB_EVAL_CONTEXT) | SLOT_ID_FOR_TRB(slot_id),
command_must_succeed);
}
/*
* Suspend is set to indicate "Stop Endpoint Command" is being issued to stop
* activity on an endpoint that is about to be suspended.
*/
int xhci_queue_stop_endpoint(struct xhci_hcd *xhci, struct xhci_command *cmd,
int slot_id, unsigned int ep_index, int suspend)
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
{
u32 trb_slot_id = SLOT_ID_FOR_TRB(slot_id);
u32 trb_ep_index = EP_ID_FOR_TRB(ep_index);
u32 type = TRB_TYPE(TRB_STOP_RING);
u32 trb_suspend = SUSPEND_PORT_FOR_TRB(suspend);
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
return queue_command(xhci, cmd, 0, 0, 0,
trb_slot_id | trb_ep_index | type | trb_suspend, false);
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
}
/* Set Transfer Ring Dequeue Pointer command */
void xhci_queue_new_dequeue_state(struct xhci_hcd *xhci,
unsigned int slot_id, unsigned int ep_index,
struct xhci_dequeue_state *deq_state)
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
{
dma_addr_t addr;
u32 trb_slot_id = SLOT_ID_FOR_TRB(slot_id);
u32 trb_ep_index = EP_ID_FOR_TRB(ep_index);
u32 trb_stream_id = STREAM_ID_FOR_TRB(deq_state->stream_id);
u32 trb_sct = 0;
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
u32 type = TRB_TYPE(TRB_SET_DEQ);
xhci: Update internal dequeue pointers after stalls. When an endpoint stalls, the xHCI driver must move the endpoint ring's dequeue pointer past the stalled transfer. To do that, the driver issues a Set TR Dequeue Pointer command, which will complete some time later. Takashi was having issues with USB 1.1 audio devices that stalled, and his analysis of the code was that the old code would not update the xHCI driver's ring dequeue pointer after the command completes. However, the dequeue pointer is set in xhci_find_new_dequeue_state(), just before the set command is issued to the hardware. Setting the dequeue pointer before the Set TR Dequeue Pointer command completes is a dangerous thing to do, since the xHCI hardware can fail the command. Instead, store the new dequeue pointer in the xhci_virt_ep structure, and update the ring's dequeue pointer when the Set TR dequeue pointer command completes. While we're at it, make sure we can't queue another Set TR Dequeue Command while the first one is still being processed. This just won't work with the internal xHCI state code. I'm still not sure if this is the right thing to do, since we might have a case where a driver queues multiple URBs to a control ring, one of the URBs Stalls, and then the driver tries to cancel the second URB. There may be a race condition there where the xHCI driver might try to issue multiple Set TR Dequeue Pointer commands, but I would have to think very hard about how the Stop Endpoint and cancellation code works. Keep the fix simple until when/if we run into that case. This patch should be queued to kernels all the way back to 2.6.31. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Tested-by: Takashi Iwai <tiwai@suse.de> Cc: stable@kernel.org
2011-02-24 07:46:42 +08:00
struct xhci_virt_ep *ep;
struct xhci_command *cmd;
int ret;
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
"Set TR Deq Ptr cmd, new deq seg = %p (0x%llx dma), new deq ptr = %p (0x%llx dma), new cycle = %u",
deq_state->new_deq_seg,
(unsigned long long)deq_state->new_deq_seg->dma,
deq_state->new_deq_ptr,
(unsigned long long)xhci_trb_virt_to_dma(
deq_state->new_deq_seg, deq_state->new_deq_ptr),
deq_state->new_cycle_state);
addr = xhci_trb_virt_to_dma(deq_state->new_deq_seg,
deq_state->new_deq_ptr);
if (addr == 0) {
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
xhci_warn(xhci, "WARN Cannot submit Set TR Deq Ptr\n");
xhci_warn(xhci, "WARN deq seg = %p, deq pt = %p\n",
deq_state->new_deq_seg, deq_state->new_deq_ptr);
return;
}
xhci: Update internal dequeue pointers after stalls. When an endpoint stalls, the xHCI driver must move the endpoint ring's dequeue pointer past the stalled transfer. To do that, the driver issues a Set TR Dequeue Pointer command, which will complete some time later. Takashi was having issues with USB 1.1 audio devices that stalled, and his analysis of the code was that the old code would not update the xHCI driver's ring dequeue pointer after the command completes. However, the dequeue pointer is set in xhci_find_new_dequeue_state(), just before the set command is issued to the hardware. Setting the dequeue pointer before the Set TR Dequeue Pointer command completes is a dangerous thing to do, since the xHCI hardware can fail the command. Instead, store the new dequeue pointer in the xhci_virt_ep structure, and update the ring's dequeue pointer when the Set TR dequeue pointer command completes. While we're at it, make sure we can't queue another Set TR Dequeue Command while the first one is still being processed. This just won't work with the internal xHCI state code. I'm still not sure if this is the right thing to do, since we might have a case where a driver queues multiple URBs to a control ring, one of the URBs Stalls, and then the driver tries to cancel the second URB. There may be a race condition there where the xHCI driver might try to issue multiple Set TR Dequeue Pointer commands, but I would have to think very hard about how the Stop Endpoint and cancellation code works. Keep the fix simple until when/if we run into that case. This patch should be queued to kernels all the way back to 2.6.31. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Tested-by: Takashi Iwai <tiwai@suse.de> Cc: stable@kernel.org
2011-02-24 07:46:42 +08:00
ep = &xhci->devs[slot_id]->eps[ep_index];
if ((ep->ep_state & SET_DEQ_PENDING)) {
xhci_warn(xhci, "WARN Cannot submit Set TR Deq Ptr\n");
xhci_warn(xhci, "A Set TR Deq Ptr command is pending.\n");
return;
xhci: Update internal dequeue pointers after stalls. When an endpoint stalls, the xHCI driver must move the endpoint ring's dequeue pointer past the stalled transfer. To do that, the driver issues a Set TR Dequeue Pointer command, which will complete some time later. Takashi was having issues with USB 1.1 audio devices that stalled, and his analysis of the code was that the old code would not update the xHCI driver's ring dequeue pointer after the command completes. However, the dequeue pointer is set in xhci_find_new_dequeue_state(), just before the set command is issued to the hardware. Setting the dequeue pointer before the Set TR Dequeue Pointer command completes is a dangerous thing to do, since the xHCI hardware can fail the command. Instead, store the new dequeue pointer in the xhci_virt_ep structure, and update the ring's dequeue pointer when the Set TR dequeue pointer command completes. While we're at it, make sure we can't queue another Set TR Dequeue Command while the first one is still being processed. This just won't work with the internal xHCI state code. I'm still not sure if this is the right thing to do, since we might have a case where a driver queues multiple URBs to a control ring, one of the URBs Stalls, and then the driver tries to cancel the second URB. There may be a race condition there where the xHCI driver might try to issue multiple Set TR Dequeue Pointer commands, but I would have to think very hard about how the Stop Endpoint and cancellation code works. Keep the fix simple until when/if we run into that case. This patch should be queued to kernels all the way back to 2.6.31. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Tested-by: Takashi Iwai <tiwai@suse.de> Cc: stable@kernel.org
2011-02-24 07:46:42 +08:00
}
/* This function gets called from contexts where it cannot sleep */
cmd = xhci_alloc_command(xhci, false, GFP_ATOMIC);
if (!cmd)
return;
ep->queued_deq_seg = deq_state->new_deq_seg;
ep->queued_deq_ptr = deq_state->new_deq_ptr;
if (deq_state->stream_id)
trb_sct = SCT_FOR_TRB(SCT_PRI_TR);
ret = queue_command(xhci, cmd,
lower_32_bits(addr) | trb_sct | deq_state->new_cycle_state,
upper_32_bits(addr), trb_stream_id,
trb_slot_id | trb_ep_index | type, false);
if (ret < 0) {
xhci_free_command(xhci, cmd);
return;
}
/* Stop the TD queueing code from ringing the doorbell until
* this command completes. The HC won't set the dequeue pointer
* if the ring is running, and ringing the doorbell starts the
* ring running.
*/
ep->ep_state |= SET_DEQ_PENDING;
USB: xhci: URB cancellation support. Add URB cancellation support to the xHCI host controller driver. This currently supports cancellation for endpoints that do not have streams enabled. An URB is represented by a number of Transaction Request Buffers (TRBs), that are chained together to make one (or more) Transaction Descriptors (TDs) on an endpoint ring. The ring is comprised of contiguous segments, linked together with Link TRBs (which may or may not be chained into a TD). To cancel an URB, we must stop the endpoint ring, make the hardware skip over the TDs in the URB (either by turning them into No-op TDs, or by moving the hardware's ring dequeue pointer past the last TRB in the last TD), and then restart the ring. There are times when we must drop the xHCI lock during this process, like when we need to complete cancelled URBs. We must ensure that additional URBs can be marked as cancelled, and that new URBs can be enqueued (since the URB completion handlers can do either). The new endpoint ring variables cancels_pending and state (which can only be modified while holding the xHCI lock) ensure that future cancellation and enqueueing do not interrupt any pending cancellation code. To facilitate cancellation, we must keep track of the starting ring segment, first TRB, and last TRB for each URB. We also need to keep track of the list of TDs that have been marked as cancelled, separate from the list of TDs that are queued for this endpoint. The new variables and cancellation list are stored in the xhci_td structure. Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 10:02:31 +08:00
}
int xhci_queue_reset_ep(struct xhci_hcd *xhci, struct xhci_command *cmd,
int slot_id, unsigned int ep_index,
enum xhci_ep_reset_type reset_type)
{
u32 trb_slot_id = SLOT_ID_FOR_TRB(slot_id);
u32 trb_ep_index = EP_ID_FOR_TRB(ep_index);
u32 type = TRB_TYPE(TRB_RESET_EP);
if (reset_type == EP_SOFT_RESET)
type |= TRB_TSP;
return queue_command(xhci, cmd, 0, 0, 0,
trb_slot_id | trb_ep_index | type, false);
}