From c5cae661d6cf808b6984762f763261adf35f3eb7 Mon Sep 17 00:00:00 2001 From: Ian Campbell Date: Thu, 17 Dec 2009 13:57:09 +0000 Subject: xen: fix hang on suspend. In 65f63384 "xen: improve error handling in do_suspend" I said: - xs_suspend()/xs_resume() and dpm_suspend_noirq()/dpm_resume_noirq() were not nested in the obvious way. and changed the ordering of the calls as so: BEFORE AFTER xs_suspend dpm_suspend_noirq dpm_suspend_noirq xs_suspend *SUSPEND* *SUSPEND* dpm_resume_noirq dpm_resume_noirq xs_resume xs_resume Clearly this is not an improvement and I was talking rubbish. In particular the new ordering is susceptible to a hang if a xenstore write is in progress at the point at which the suspend kicks in. When the suspend process calls xs_suspend it tries to take the request_mutex but if a write is in progress it could be looping in xenbus_xs.c:read_reply() waiting for something to arrive on &xs_state.reply_list while holding the request_mutex (taken in the caller of read_reply). However if we have done dpm_suspend_noirq before xs_suspend then we won't get any more xenstore interrupts and process_msg() will never be woken up to add anything to the reply_list. Fix this by calling xs_suspend before dpm_suspend_noirq. If dpm_suspend_noirq fails then make sure we go through the xs_suspend_cancel() code path. Signed-off-by: Ian Campbell Acked-by: Jeremy Fitzhardinge Cc: Stable Kernel --- drivers/xen/manage.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'drivers/xen') diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c index c499793..5d42d55 100644 --- a/drivers/xen/manage.c +++ b/drivers/xen/manage.c @@ -102,15 +102,15 @@ static void do_suspend(void) goto out_thaw; } + printk(KERN_DEBUG "suspending xenstore...\n"); + xs_suspend(); + err = dpm_suspend_noirq(PMSG_SUSPEND); if (err) { printk(KERN_ERR "dpm_suspend_noirq failed: %d\n", err); goto out_resume; } - printk(KERN_DEBUG "suspending xenstore...\n"); - xs_suspend(); - err = stop_machine(xen_suspend, &cancelled, cpumask_of(0)); dpm_resume_noirq(PMSG_RESUME); @@ -120,13 +120,13 @@ static void do_suspend(void) cancelled = 1; } +out_resume: if (!cancelled) { xen_arch_resume(); xs_resume(); } else xs_suspend_cancel(); -out_resume: dpm_resume_end(PMSG_RESUME); /* Make sure timer events get retriggered on all CPUs */ -- cgit v1.1