From: Michael J. Ruhl <michael.j.ruhl(a)intel.com>
commit b4a4957d3d1c328b733fce783b7264996f866ad2 upstream.
rvt_destroy_qp() cannot complete until all in process packets have
been released from the underlying hardware. If a link down event
occurs, an application can hang with a kernel stack similar to:
cat /proc/<app PID>/stack
quiesce_qp+0x178/0x250 [hfi1]
rvt_reset_qp+0x23d/0x400 [rdmavt]
rvt_destroy_qp+0x69/0x210 [rdmavt]
ib_destroy_qp+0xba/0x1c0 [ib_core]
nvme_rdma_destroy_queue_ib+0x46/0x80 [nvme_rdma]
nvme_rdma_free_queue+0x3c/0xd0 [nvme_rdma]
nvme_rdma_destroy_io_queues+0x88/0xd0 [nvme_rdma]
nvme_rdma_error_recovery_work+0x52/0xf0 [nvme_rdma]
process_one_work+0x17a/0x440
worker_thread+0x126/0x3c0
kthread+0xcf/0xe0
ret_from_fork+0x58/0x90
0xffffffffffffffff
quiesce_qp() waits until all outstanding packets have been freed.
This wait should be momentary. During a link down event, the cleanup
handling does not ensure that all packets caught by the link down are
flushed properly.
This is caused by the fact that the freeze path and the link down
event is handled the same. This is not correct. The freeze path
waits until the HFI is unfrozen and then restarts PIO. A link down
is not a freeze event. The link down path cannot restart the PIO
until link is restored. If the PIO path is restarted before the link
comes up, the application (QP) using the PIO path will hang (until
link is restored).
Fix by separating the linkdown path from the freeze path and use the
link down path for link down events.
Close a race condition sc_disable() by acquiring both the progress
and release locks.
Close a race condition in sc_stop() by moving the setting of the flag
bits under the alloc lock.
Fixes: 7724105686e7 ("IB/hfi1: add driver files")
Cc: <stable(a)vger.kernel.org> # 4.14.x
Reviewed-by: Mike Marciniszyn <mike.marciniszyn(a)intel.com>
Signed-off-by: Michael J. Ruhl <michael.j.ruhl(a)intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro(a)intel.com>
---
drivers/infiniband/hw/hfi1/chip.c | 7 +++++-
drivers/infiniband/hw/hfi1/pio.c | 42 ++++++++++++++++++++++++++++++-------
drivers/infiniband/hw/hfi1/pio.h | 2 ++
3 files changed, 42 insertions(+), 9 deletions(-)
diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index 33cf173..f9faacc 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -6722,6 +6722,7 @@ void start_freeze_handling(struct hfi1_pportdata *ppd, int flags)
struct hfi1_devdata *dd = ppd->dd;
struct send_context *sc;
int i;
+ int sc_flags;
if (flags & FREEZE_SELF)
write_csr(dd, CCE_CTRL, CCE_CTRL_SPC_FREEZE_SMASK);
@@ -6732,11 +6733,13 @@ void start_freeze_handling(struct hfi1_pportdata *ppd, int flags)
/* notify all SDMA engines that they are going into a freeze */
sdma_freeze_notify(dd, !!(flags & FREEZE_LINK_DOWN));
+ sc_flags = SCF_FROZEN | SCF_HALTED | (flags & FREEZE_LINK_DOWN ?
+ SCF_LINK_DOWN : 0);
/* do halt pre-handling on all enabled send contexts */
for (i = 0; i < dd->num_send_contexts; i++) {
sc = dd->send_contexts[i].sc;
if (sc && (sc->flags & SCF_ENABLED))
- sc_stop(sc, SCF_FROZEN | SCF_HALTED);
+ sc_stop(sc, sc_flags);
}
/* Send context are frozen. Notify user space */
@@ -10646,6 +10649,8 @@ int set_link_state(struct hfi1_pportdata *ppd, u32 state)
add_rcvctrl(dd, RCV_CTRL_RCV_PORT_ENABLE_SMASK);
handle_linkup_change(dd, 1);
+ pio_kernel_linkup(dd);
+
ppd->host_link_state = HLS_UP_INIT;
break;
case HLS_UP_ARMED:
diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c
index a95ac62..44a8940 100644
--- a/drivers/infiniband/hw/hfi1/pio.c
+++ b/drivers/infiniband/hw/hfi1/pio.c
@@ -937,20 +937,18 @@ void sc_free(struct send_context *sc)
void sc_disable(struct send_context *sc)
{
u64 reg;
- unsigned long flags;
struct pio_buf *pbuf;
if (!sc)
return;
/* do all steps, even if already disabled */
- spin_lock_irqsave(&sc->alloc_lock, flags);
+ spin_lock_irq(&sc->alloc_lock);
reg = read_kctxt_csr(sc->dd, sc->hw_context, SC(CTRL));
reg &= ~SC(CTRL_CTXT_ENABLE_SMASK);
sc->flags &= ~SCF_ENABLED;
sc_wait_for_packet_egress(sc, 1);
write_kctxt_csr(sc->dd, sc->hw_context, SC(CTRL), reg);
- spin_unlock_irqrestore(&sc->alloc_lock, flags);
/*
* Flush any waiters. Once the context is disabled,
@@ -960,7 +958,7 @@ void sc_disable(struct send_context *sc)
* proceed with the flush.
*/
udelay(1);
- spin_lock_irqsave(&sc->release_lock, flags);
+ spin_lock(&sc->release_lock);
if (sc->sr) { /* this context has a shadow ring */
while (sc->sr_tail != sc->sr_head) {
pbuf = &sc->sr[sc->sr_tail].pbuf;
@@ -971,7 +969,8 @@ void sc_disable(struct send_context *sc)
sc->sr_tail = 0;
}
}
- spin_unlock_irqrestore(&sc->release_lock, flags);
+ spin_unlock(&sc->release_lock);
+ spin_unlock_irq(&sc->alloc_lock);
}
/* return SendEgressCtxtStatus.PacketOccupancy */
@@ -1194,11 +1193,39 @@ void pio_kernel_unfreeze(struct hfi1_devdata *dd)
sc = dd->send_contexts[i].sc;
if (!sc || !(sc->flags & SCF_FROZEN) || sc->type == SC_USER)
continue;
+ if (sc->flags & SCF_LINK_DOWN)
+ continue;
sc_enable(sc); /* will clear the sc frozen flag */
}
}
+/**
+ * pio_kernel_linkup() - Re-enable send contexts after linkup event
+ * @dd: valid devive data
+ *
+ * When the link goes down, the freeze path is taken. However, a link down
+ * event is different from a freeze because if the send context is re-enabled
+ * whowever is sending data will start sending data again, which will hang
+ * any QP that is sending data.
+ *
+ * The freeze path now looks at the type of event that occurs and takes this
+ * path for link down event.
+ */
+void pio_kernel_linkup(struct hfi1_devdata *dd)
+{
+ struct send_context *sc;
+ int i;
+
+ for (i = 0; i < dd->num_send_contexts; i++) {
+ sc = dd->send_contexts[i].sc;
+ if (!sc || !(sc->flags & SCF_LINK_DOWN) || sc->type == SC_USER)
+ continue;
+
+ sc_enable(sc); /* will clear the sc link down flag */
+ }
+}
+
/*
* Wait for the SendPioInitCtxt.PioInitInProgress bit to clear.
* Returns:
@@ -1398,11 +1425,10 @@ void sc_stop(struct send_context *sc, int flag)
{
unsigned long flags;
- /* mark the context */
- sc->flags |= flag;
-
/* stop buffer allocations */
spin_lock_irqsave(&sc->alloc_lock, flags);
+ /* mark the context */
+ sc->flags |= flag;
sc->flags &= ~SCF_ENABLED;
spin_unlock_irqrestore(&sc->alloc_lock, flags);
wake_up(&sc->halt_wait);
diff --git a/drivers/infiniband/hw/hfi1/pio.h b/drivers/infiniband/hw/hfi1/pio.h
index 99ca5ed..c7c4e6e 100644
--- a/drivers/infiniband/hw/hfi1/pio.h
+++ b/drivers/infiniband/hw/hfi1/pio.h
@@ -145,6 +145,7 @@ struct send_context {
#define SCF_IN_FREE 0x02
#define SCF_HALTED 0x04
#define SCF_FROZEN 0x08
+#define SCF_LINK_DOWN 0x10
struct send_context_info {
struct send_context *sc; /* allocated working context */
@@ -312,6 +313,7 @@ struct pio_buf *sc_buffer_alloc(struct send_context *sc, u32 dw_len,
void pio_reset_all(struct hfi1_devdata *dd);
void pio_freeze(struct hfi1_devdata *dd);
void pio_kernel_unfreeze(struct hfi1_devdata *dd);
+void pio_kernel_linkup(struct hfi1_devdata *dd);
/* global PIO send control operations */
#define PSC_GLOBAL_ENABLE 0
Hello,
We were trying to build 4.14 kernel with GCC 8, but perf failed to
compile. The upstream tree seems to have necessary commits to support
GCC 8, but they were not ported to 4.14 branch. With backporting the
following commits we were able to restore perf compilation and compile
a working 4.14 kernel with GCC 8.2:
6810158d526e483868e519befff407b91e76b3db: perf annotate: Use asprintf
when formatting objdump command
b7a313d84e853049062011d78cb04b6decd12f5c: perf tools: Fix python
extension build for gcc 8
77f18153c080855e1c3fb520ca31a4e61530121d: perf tools: Fix snprint
warnings for gcc 8
06c3f2aa9fc68e7f3fe3d83e7569d2a2801d9f99: perf utils: Move
is_directory() to path.h
Propose to apply the above commits to 4.14 to be able to compile it
with GCC 8 (mostly to properly support CONFIG_RETPOLINE)
Commit 6810158d526e483868e519befff407b91e76b3db might need adjustment
to cleanly apply on 4.14 branch.
Regards,
Ignat
-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA512
Hi Greg,
Pleae pull commits for Linux 3.18 .
I've sent a review request for all commits over a week ago and all
comments were addressed.
Thanks,
Sasha
=====
The following changes since commit 0d63979c1bc9c85578be4c589768a13dc0a7c5eb:
Linux 3.18.124 (2018-10-13 09:09:32 +0200)
are available in the Git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/sashal/linux-stable.git tags/for-greg-3.18-16102018
for you to fetch changes up to 8103cbfd1edd20d4de51defa9d6914e33b043f91:
powerpc/tm: Avoid possible userspace r1 corruption on reclaim (2018-10-15 18:02:23 -0400)
- ----------------------------------------------------------------
for-greg-3.18-16102018
- ----------------------------------------------------------------
James Cowgill (1):
RISC-V: include linux/ftrace.h in asm-prototypes.h
Jozef Balga (1):
media: af9035: prevent buffer overflow on write
Michael Neuling (2):
powerpc/tm: Fix userspace r13 corruption
powerpc/tm: Avoid possible userspace r1 corruption on reclaim
arch/powerpc/kernel/tm.S | 20 +++++++++++++++++---
arch/riscv/include/asm/asm-prototypes.h | 7 +++++++
drivers/media/usb/dvb-usb-v2/af9035.c | 6 ++++--
3 files changed, 28 insertions(+), 5 deletions(-)
create mode 100644 arch/riscv/include/asm/asm-prototypes.h
-----BEGIN PGP SIGNATURE-----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=j/HW
-----END PGP SIGNATURE-----
-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA512
Hi Greg,
Pleae pull commits for Linux 4.4 .
I've sent a review request for all commits over a week ago and all
comments were addressed.
Thanks,
Sasha
=====
The following changes since commit b001adea66f0e0a7803adfbf9128a2d7969daa4e:
Linux 4.4.161 (2018-10-13 09:11:36 +0200)
are available in the Git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/sashal/linux-stable.git tags/for-greg-4.4-16102018
for you to fetch changes up to 0d850290d80e46758e82d87904cec458113f923e:
powerpc/tm: Avoid possible userspace r1 corruption on reclaim (2018-10-15 18:02:16 -0400)
- ----------------------------------------------------------------
for-greg-4.4-16102018
- ----------------------------------------------------------------
Andreas Schwab (1):
Input: atakbd - fix Atari keymap
James Cowgill (1):
RISC-V: include linux/ftrace.h in asm-prototypes.h
Jozef Balga (1):
media: af9035: prevent buffer overflow on write
Keerthy (1):
clocksource/drivers/ti-32k: Add CLOCK_SOURCE_SUSPEND_NONSTOP flag for non-am43 SoCs
Michael Neuling (2):
powerpc/tm: Fix userspace r13 corruption
powerpc/tm: Avoid possible userspace r1 corruption on reclaim
Michael Schmitz (1):
Input: atakbd - fix Atari CapsLock behaviour
Nathan Chancellor (1):
net/mlx4: Use cpumask_available for eq->affinity_mask
arch/powerpc/kernel/tm.S | 20 +++++++--
arch/riscv/include/asm/asm-prototypes.h | 7 ++++
drivers/clocksource/timer-ti-32k.c | 3 ++
drivers/input/keyboard/atakbd.c | 74 +++++++++++++--------------------
drivers/media/usb/dvb-usb-v2/af9035.c | 6 ++-
drivers/net/ethernet/mellanox/mlx4/eq.c | 3 +-
6 files changed, 61 insertions(+), 52 deletions(-)
create mode 100644 arch/riscv/include/asm/asm-prototypes.h
-----BEGIN PGP SIGNATURE-----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=uvan
-----END PGP SIGNATURE-----
