lkml.org 
[lkml]   [2012]   [Sep]   [12]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[ 65/85] powerpc: Make sure IPI handlers see data written by IPI senders
Date
From: Greg KH <gregkh@linuxfoundation.org>

3.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Paul Mackerras <paulus@samba.org>

commit 9fb1b36ca1234e64a5d1cc573175303395e3354d upstream.

We have been observing hangs, both of KVM guest vcpu tasks and more
generally, where a process that is woken doesn't properly wake up and
continue to run, but instead sticks in TASK_WAKING state. This
happens because the update of rq->wake_list in ttwu_queue_remote()
is not ordered with the update of ipi_message in
smp_muxed_ipi_message_pass(), and the reading of rq->wake_list in
scheduler_ipi() is not ordered with the reading of ipi_message in
smp_ipi_demux(). Thus it is possible for the IPI receiver not to see
the updated rq->wake_list and therefore conclude that there is nothing
for it to do.

In order to make sure that anything done before smp_send_reschedule()
is ordered before anything done in the resulting call to scheduler_ipi(),
this adds barriers in smp_muxed_message_pass() and smp_ipi_demux().
The barrier in smp_muxed_message_pass() is a full barrier to ensure that
there is a full ordering between the smp_send_reschedule() caller and
scheduler_ipi(). In smp_ipi_demux(), we use xchg() rather than
xchg_local() because xchg() includes release and acquire barriers.
Using xchg() rather than xchg_local() makes sense given that
ipi_message is not just accessed locally.

This moves the barrier between setting the message and calling the
cause_ipi() function into the individual cause_ipi implementations.
Most of them -- those that used outb, out_8 or similar -- already had
a full barrier because out_8 etc. include a sync before the MMIO
store. This adds an explicit barrier in the two remaining cases.

These changes made no measurable difference to the speed of IPIs as
measured using a simple ping-pong latency test across two CPUs on
different cores of a POWER7 machine.

The analysis of the reason why processes were not waking up properly
is due to Milton Miller.

Reported-by: Milton Miller <miltonm@bga.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

---
arch/powerpc/kernel/dbell.c | 2 ++
arch/powerpc/kernel/smp.c | 11 +++++++++--
arch/powerpc/sysdev/xics/icp-hv.c | 6 +++++-
3 files changed, 16 insertions(+), 3 deletions(-)

--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -28,6 +28,8 @@ void doorbell_setup_this_cpu(void)

void doorbell_cause_ipi(int cpu, unsigned long data)
{
+ /* Order previous accesses vs. msgsnd, which is treated as a store */
+ mb();
ppc_msgsnd(PPC_DBELL, 0, data);
}

--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -215,8 +215,15 @@ void smp_muxed_ipi_message_pass(int cpu,
struct cpu_messages *info = &per_cpu(ipi_message, cpu);
char *message = (char *)&info->messages;

+ /*
+ * Order previous accesses before accesses in the IPI handler.
+ */
+ smp_mb();
message[msg] = 1;
- mb();
+ /*
+ * cause_ipi functions are required to include a full barrier
+ * before doing whatever causes the IPI.
+ */
smp_ops->cause_ipi(cpu, info->data);
}

@@ -228,7 +235,7 @@ irqreturn_t smp_ipi_demux(void)
mb(); /* order any irq clear */

do {
- all = xchg_local(&info->messages, 0);
+ all = xchg(&info->messages, 0);

#ifdef __BIG_ENDIAN
if (all & (1 << (24 - 8 * PPC_MSG_CALL_FUNCTION)))
--- a/arch/powerpc/sysdev/xics/icp-hv.c
+++ b/arch/powerpc/sysdev/xics/icp-hv.c
@@ -65,7 +65,11 @@ static inline void icp_hv_set_xirr(unsig
static inline void icp_hv_set_qirr(int n_cpu , u8 value)
{
int hw_cpu = get_hard_smp_processor_id(n_cpu);
- long rc = plpar_hcall_norets(H_IPI, hw_cpu, value);
+ long rc;
+
+ /* Make sure all previous accesses are ordered before IPI sending */
+ mb();
+ rc = plpar_hcall_norets(H_IPI, hw_cpu, value);
if (rc != H_SUCCESS) {
pr_err("%s: bad return code qirr cpu=%d hw_cpu=%d mfrr=0x%x "
"returned %ld\n", __func__, n_cpu, hw_cpu, value, rc);



\
 
 \ /
  Last update: 2012-09-13 05:01    [W:0.273 / U:0.040 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site