[Xen-devel] [RFC v4 2/2] x86/xen: allow privcmd hypercalls to be preempted

["Luis R. Rodriguez" <mcgrof@xxxxxxxxxxxxxxxx>]

From: "Luis R. Rodriguez" <mcgrof@xxxxxxxx>

Xen has support for splitting heavy work work into a series
of hypercalls, called multicalls, and preempting them through
what Xen calls continuation [0]. Despite this though without
CONFIG_PREEMPT preemption won't happen, without preemption
a system can become pretty useless on heavy handed hypercalls.
Such is the case for example when creating a > 50 GiB HVM guest,
we can get softlockups [1] with:.

kernel: [  802.084335] BUG: soft lockup - CPU#1 stuck for 22s! [xend:31351]

The softlock up triggers on the TASK_UNINTERRUPTIBLE hanger check
(default 120 seconds), on the Xen side in this particular case
this happens when the following Xen hypervisor code is used:

xc_domain_set_pod_target() -->
  do_memory_op() -->
    arch_memory_op() -->
      p2m_pod_set_mem_target()
        -- long delay (real or emulated) --

This happens on arch_memory_op() on the XENMEM_set_pod_target memory
op even though arch_memory_op() can handle continuation via
hypercall_create_continuation() for example.

Machines over 50 GiB of memory are on high demand and hard to come
by so to help replicate this sort of issue long delays on select
hypercalls have been emulated in order to be able to test this on
smaller machines [2].

On one hand this issue can be considered as expected given that
CONFIG_PREEMPT=n is used however we have forced voluntary preemption
precedent practices in the kernel even for CONFIG_PREEMPT=n through
the usage of cond_resched() sprinkled in many places. To address
this issue with Xen hypercalls though we need to find a way to aid
to the schedular in the middle of hypercalls. We are motivated to
address this issue on CONFIG_PREEMPT=n as otherwise the system becomes
rather unresponsive for long periods of time; in the worst case, at least
only currently by emulating long delays on select io disk bound
hypercalls, this can lead to filesystem corruption if the delay happens
for example on SCHEDOP_remote_shutdown (when we call 'xl <domain> shutdown').

We can address this problem by trying to check if we should schedule
on the xen timer in the middle of a hypercall on the return from the
timer interrupt. We want to be careful to not always force voluntary
preemption though so to do this we only selectively enable preemption
on very specific xen hypercalls.

This enables hypercall preemption by selectively forcing checks for
voluntary preempting only on ioctl initiated private hypercalls
where we know some folks have run into reported issues [1].

This also adds a trace event to be able to review when xen hypercalls
are preemtped, right now we just tell you when it happens and which
CPU got preempted.

ergon:~ # echo 1 > 
/sys/kernel/debug/tracing/events/xen/xen_hypercall_preemption/trigger
ergon:~ # cat /sys/kernel/debug/tracing/trace_pipe
...
 qemu-system-i38-2114  [000] ....   491.038440: xen_hypercall_preemption: on 
CPU 0
 qemu-system-i38-2114  [003] ....   518.138592: xen_hypercall_preemption: on 
CPU 3
...

[0] 
http://xenbits.xen.org/gitweb/?p=xen.git;a=commitdiff;h=42217cbc5b3e84b8c145d8cfb62dd5de0134b9e8;hp=3a0b9c57d5c9e82c55dd967c84dd06cb43c49ee9
[1] https://bugzilla.novell.com/show_bug.cgi?id=861093
[2] http://ftp.suse.com/pub/people/mcgrof/xen/emulate-long-xen-hypercalls.patch

Based on original work by: David Vrabel <david.vrabel@xxxxxxxxxx>
Suggested-by: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxx>
Cc: David Vrabel <david.vrabel@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: x86@xxxxxxxxxx
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@xxxxxxxxxxx>
Cc: Jan Beulich <JBeulich@xxxxxxxx>
Cc: linux-kernel@xxxxxxxxxxxxxxx
Signed-off-by: Luis R. Rodriguez <mcgrof@xxxxxxxx>
---
 arch/x86/kernel/entry_32.S       |  2 ++
 arch/x86/kernel/entry_64.S       |  2 ++
 drivers/xen/events/events_base.c | 23 +++++++++++++++++++++++
 include/trace/events/xen.h       |  9 +++++++++
 include/xen/events.h             |  1 +
 5 files changed, 37 insertions(+)

diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 000d419..b4b1f42 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -982,6 +982,8 @@ ENTRY(xen_hypervisor_callback)
 ENTRY(xen_do_upcall)
 1:     mov %esp, %eax
        call xen_evtchn_do_upcall
+       movl %esp,%eax
+       call xen_end_upcall
        jmp  ret_from_intr
        CFI_ENDPROC
 ENDPROC(xen_hypervisor_callback)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 9ebaf63..ee28733 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1198,6 +1198,8 @@ ENTRY(xen_do_hypervisor_callback)   # 
do_hypervisor_callback(struct *pt_regs)
        popq %rsp
        CFI_DEF_CFA_REGISTER rsp
        decl PER_CPU_VAR(irq_count)
+       movq %rsp, %rdi  /* pass pt_regs as first argument */
+       call xen_end_upcall
        jmp  error_exit
        CFI_ENDPROC
 END(xen_do_hypervisor_callback)
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index b4bca2d..8126642 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -32,6 +32,10 @@
 #include <linux/slab.h>
 #include <linux/irqnr.h>
 #include <linux/pci.h>
+#include <linux/sched.h>
+#include <linux/kprobes.h>
+
+#include <trace/events/xen.h>
 
 #ifdef CONFIG_X86
 #include <asm/desc.h>
@@ -1243,6 +1247,25 @@ void xen_evtchn_do_upcall(struct pt_regs *regs)
        set_irq_regs(old_regs);
 }
 
+/*
+ * CONFIG_PREEMPT=n kernels can end up triggering the softlock
+ * TASK_UNINTERRUPTIBLE hanger check (default 120 seconds)
+ * when certain multicalls are used [0] on large systems, in
+ * that case we need a way to voluntarily preempt. This is
+ * only an issue on CONFIG_PREEMPT=n kernels.
+ *
+ * [0] https://bugzilla.novell.com/show_bug.cgi?id=861093
+ */
+void xen_end_upcall(struct pt_regs *regs)
+{
+       if (xen_is_preemptible_hypercall(regs)) {
+               int cpuid = smp_processor_id();
+               if (_cond_resched())
+                       trace_xen_hypercall_preemption(cpuid);
+       }
+}
+NOKPROBE_SYMBOL(xen_end_upcall);
+
 void xen_hvm_evtchn_do_upcall(void)
 {
        __xen_evtchn_do_upcall();
diff --git a/include/trace/events/xen.h b/include/trace/events/xen.h
index d06b6da..77e333b 100644
--- a/include/trace/events/xen.h
+++ b/include/trace/events/xen.h
@@ -509,6 +509,15 @@ TRACE_EVENT(xen_cpu_set_ldt,
                      __entry->addr, __entry->entries)
        );
 
+TRACE_EVENT(xen_hypercall_preemption,
+           TP_PROTO(int cpu_id),
+           TP_ARGS(cpu_id),
+           TP_STRUCT__entry(
+                   __field(int, cpuid)
+                   ),
+           TP_fast_assign(__entry->cpuid = cpu_id),
+           TP_printk("on CPU %d", __entry->cpuid)
+       );
 
 #endif /*  _TRACE_XEN_H */
 
diff --git a/include/xen/events.h b/include/xen/events.h
index 5321cd9..f08df87 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -95,6 +95,7 @@ void xen_hvm_callback_vector(void);
 extern int xen_have_vector_callback;
 int xen_set_callback_via(uint64_t via);
 void xen_evtchn_do_upcall(struct pt_regs *regs);
+void xen_end_upcall(struct pt_regs *regs);
 void xen_hvm_evtchn_do_upcall(void);
 
 /* Bind a pirq for a physical interrupt to an irq. */
-- 
2.1.1


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel