Skip to contentSkip to conversation

x86/xen: add xen hypercall preemption

RFC Superseded Luis R. Rodriguez 6 participants 31 messages Jan 23, 2015 – Jan 27, 2015

Subsystems (7)
Arm (32-bit) x86 KVM Tracing +3 more subsystems

v4 of 5 Superseded Latest is v5 →

lore
Share & tools
lore
#0 lore raw

v4 cover x86/xen: add xen hypercall preemption

From: "Luis R. Rodriguez" <[email protected]>

This v4 addresses some of the cleanups recommended and adds tracing option for when we do actually preempt a hypercall. I kept the NOKPROBE_SYMBOL() for now but did remove the 'notrace' stuff.

This goes out as RFC still as I have not been able to test 32-bit. Can anyone test that or at least confirm that the 32-bit point we do the upcall is definitely not on the IRQ stack?

Luis R. Rodriguez (2):
x86/xen: add xen_is_preemptible_hypercall() x86/xen: allow privcmd hypercalls to be preempted

 arch/arm/include/asm/xen/hypercall.h |  5 +++++
 arch/x86/include/asm/xen/hypercall.h | 20 ++++++++++++++++++++
 arch/x86/kernel/entry_32.S           |  2 ++
 arch/x86/kernel/entry_64.S           |  2 ++
 arch/x86/xen/enlighten.c             |  7 +++++++
 arch/x86/xen/xen-head.S              | 18 +++++++++++++++++-
 drivers/xen/events/events_base.c     | 23 +++++++++++++++++++++++
 include/trace/events/xen.h           |  9 +++++++++
 include/xen/events.h                 |  1 +
 9 files changed, 86 insertions(+), 1 deletion(-)
Signature · 1 line
2.1.1
#1 lore raw

RFC v4 1/2 x86/xen: add xen_is_preemptible_hypercall()

From: "Luis R. Rodriguez" <[email protected]>

On kernels with voluntary or no preemption we can run into situations where a hypercall issued through userspace will linger around as it addresses sub-operatiosn in kernel context (multicalls). Such operations can trigger soft lockup detection.

We want to address a way to let the kernel voluntarily preempt such calls even on non preempt kernels, to address this we first need to distinguish which hypercalls fall under this category. This implements xen_is_preemptible_hypercall() which lets us do just that by adding a secondary hypercall page, calls made via the new page may be preempted.

Andrew had originally submitted a version of this work [0].

[0] http://lists.xen.org/archives/html/xen-devel/2014-02/msg01056.html

Based on original work by: Andrew Cooper <[email protected]>

Cc Andy Lutomirski <[email protected]>
Cc Borislav Petkov <[email protected]>
Cc David Vrabel <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc "H. Peter Anvin" <[email protected]>
Cc Steven Rostedt <[email protected]>
Cc Masami Hiramatsu <[email protected]>
Cc Jan Beulich <[email protected]>
---
 arch/arm/include/asm/xen/hypercall.h |  5 +++++
 arch/x86/include/asm/xen/hypercall.h | 20 ++++++++++++++++++++
 arch/x86/xen/enlighten.c             |  7 +++++++
 arch/x86/xen/xen-head.S              | 18 +++++++++++++++++-
 4 files changed, 49 insertions(+), 1 deletion(-)
arch/arm/include/asm/xen/hypercall.h +5 -0
index 712b50e..4fc8395 100644
@@ -74,4 +74,9 @@ MULTI_mmu_update(struct multicall_entry *mcl, struct mmu_update *req,
 	BUG();
 }
 
+static inline bool xen_is_preemptible_hypercall(struct pt_regs *regs)
+{
+	return false;
+}
+
 #endif /* _ASM_ARM_XEN_HYPERCALL_H */
arch/x86/include/asm/xen/hypercall.h +20 -0
index ca08a27..221008e 100644
@@ -84,6 +84,22 @@
 
 extern struct { char _entry[32]; } hypercall_page[];
 
+#ifndef CONFIG_PREEMPT
+extern struct { char _entry[32]; } preemptible_hypercall_page[];
+
+static inline bool xen_is_preemptible_hypercall(struct pt_regs *regs)
+{
+	return !user_mode_vm(regs) &&
+		regs->ip >= (unsigned long)preemptible_hypercall_page &&
+		regs->ip < (unsigned long)preemptible_hypercall_page + PAGE_SIZE;
+}
+#else
+static inline bool xen_is_preemptible_hypercall(struct pt_regs *regs)
+{
+	return false;
+}
+#endif
+
 #define __HYPERCALL		"call hypercall_page+%c[offset]"
 #define __HYPERCALL_ENTRY(x)						\
 	[offset] "i" (__HYPERVISOR_##x * sizeof(hypercall_page[0]))
@@ -215,7 +231,11 @@ privcmd_call(unsigned call,
 
 	asm volatile("call *%[call]"
 		     : __HYPERCALL_5PARAM
+#ifndef CONFIG_PREEMPT
+		     : [call] "a" (&preemptible_hypercall_page[call])
+#else
 		     : [call] "a" (&hypercall_page[call])
+#endif
 		     : __HYPERCALL_CLOBBER5);
 
 	return (long)__res;
arch/x86/xen/enlighten.c +7 -0
index 6bf3a13..9c01b48 100644
@@ -84,6 +84,9 @@
 #include "multicalls.h"
 
 EXPORT_SYMBOL_GPL(hypercall_page);
+#ifndef CONFIG_PREEMPT
+EXPORT_SYMBOL_GPL(preemptible_hypercall_page);
+#endif
 
 /*
  * Pointer to the xen_vcpu_info structure or
@@ -1531,6 +1534,10 @@ asmlinkage __visible void __init xen_start_kernel(void)
 #endif
 	xen_setup_machphys_mapping();
 
+#ifndef CONFIG_PREEMPT
+	copy_page(preemptible_hypercall_page, hypercall_page);
+#endif
+
 	/* Install Xen paravirt ops */
 	pv_info = xen_info;
 	pv_init_ops = xen_init_ops;
arch/x86/xen/xen-head.S +17 -1
index 674b2225..6e6a9517 100644
@@ -85,9 +85,18 @@ ENTRY(xen_pvh_early_cpu_init)
 .pushsection .text
 	.balign PAGE_SIZE
 ENTRY(hypercall_page)
+
+#ifdef CONFIG_PREEMPT
+#  define PREEMPT_HYPERCALL_ENTRY(x)
+#else
+#  define PREEMPT_HYPERCALL_ENTRY(x) \
+       .global xen_hypercall_##x ## _p ASM_NL \
+       .set preemptible_xen_hypercall_##x, xen_hypercall_##x + PAGE_SIZE ASM_NL
+#endif
 #define NEXT_HYPERCALL(x) \
 	ENTRY(xen_hypercall_##x) \
-	.skip 32
+	.skip 32 ASM_NL \
+	PREEMPT_HYPERCALL_ENTRY(x)
 
 NEXT_HYPERCALL(set_trap_table)
 NEXT_HYPERCALL(mmu_update)
@@ -138,6 +147,13 @@ NEXT_HYPERCALL(arch_4)
 NEXT_HYPERCALL(arch_5)
 NEXT_HYPERCALL(arch_6)
 	.balign PAGE_SIZE
+
+#ifndef CONFIG_PREEMPT
+ENTRY(preemptible_hypercall_page)
+	.skip PAGE_SIZE
+#endif /* CONFIG_PREEMPT */
+
+#undef NEXT_HYPERCALL
 .popsection
 
 	ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS,       .asciz "linux")
Signature · 1 line
2.1.1
#2 lore raw

Re: [RFC v4 1/2] x86/xen: add xen_is_preemptible_hypercall()

Quoted 7 lines · Luis R. Rodriguez

From: "Luis R. Rodriguez" <[email protected]>

On kernels with voluntary or no preemption we can run into situations where a hypercall issued through userspace will linger around as it addresses sub-operatiosn in kernel context (multicalls). Such operations can trigger soft lockup detection.

Looks reasonable.

--Andy

#3 lore raw

Re: [RFC v4 1/2] x86/xen: add xen_is_preemptible_hypercall()

Quoted 11 lines · Andy Lutomirski
Quoted 7 lines · Luis R. Rodriguez

From: "Luis R. Rodriguez" <[email protected]>

On kernels with voluntary or no preemption we can run into situations where a hypercall issued through userspace will linger around as it addresses sub-operatiosn in kernel context (multicalls). Such operations can trigger soft lockup detection.

Looks reasonable.

I'll add a reviewed-by...

LUis

#4 lore raw

Re: [RFC v4 1/2] x86/xen: add xen_is_preemptible_hypercall()

In reply to Andy Lutomirski
Quoted 11 lines · Andy Lutomirski
Quoted 7 lines · Luis R. Rodriguez

From: "Luis R. Rodriguez" <[email protected]>

On kernels with voluntary or no preemption we can run into situations where a hypercall issued through userspace will linger around as it addresses sub-operatiosn in kernel context (multicalls). Such operations can trigger soft lockup detection.

Looks reasonable.

I'll add a reviewed-by...

LUis

#5 lore raw

Re: [RFC v4 1/2] x86/xen: add xen_is_preemptible_hypercall()

In reply to Luis R. Rodriguez
Quoted 7 lines · Luis R. Rodriguez

From: "Luis R. Rodriguez" <[email protected]>

On kernels with voluntary or no preemption we can run into situations where a hypercall issued through userspace will linger around as it addresses sub-operatiosn in kernel context (multicalls). Such operations can trigger soft lockup detection.

Looks reasonable.

--Andy

#6 lore raw

Re: [Xen-devel] [RFC v4 1/2] x86/xen: add xen_is_preemptible_hypercall()

In reply to Luis R. Rodriguez
Quoted 14 lines · Luis R. Rodriguez

From: "Luis R. Rodriguez" <[email protected]>

On kernels with voluntary or no preemption we can run into situations where a hypercall issued through userspace will linger around as it addresses sub-operatiosn in kernel context (multicalls). Such operations can trigger soft lockup detection.

We want to address a way to let the kernel voluntarily preempt such calls even on non preempt kernels, to address this we first need to distinguish which hypercalls fall under this category. This implements xen_is_preemptible_hypercall() which lets us do just that by adding a secondary hypercall page, calls made via the new page may be preempted.

[...]

Quoted 4 lines
arch/x86/include/asm/xen/hypercall.h +0 -0
@@ -84,6 +84,22 @@
 

arch/x86/include/asm/xen/hypercall.h line 94

Quoted 10 lines
arch/x86/include/asm/xen/hypercall.h +8 -0
 extern struct { char _entry[32]; } hypercall_page[];
 
+#ifndef CONFIG_PREEMPT
+extern struct { char _entry[32]; } preemptible_hypercall_page[];
+
+static inline bool xen_is_preemptible_hypercall(struct pt_regs *regs)
+{
+	return !user_mode_vm(regs) &&
+		regs->ip >= (unsigned long)preemptible_hypercall_page &&
+		regs->ip < (unsigned long)preemptible_hypercall_page + PAGE_SIZE;

I think you can optimize this to:

    return (regs->ip >> PAGE_SHIFT) == preemptible_hypercall_pfn
	&& !user_mode_vm(regs);

David

#7 lore raw

Re: [Xen-devel] [RFC v4 1/2] x86/xen: add xen_is_preemptible_hypercall()

Quoted 33 lines · David Vrabel
Quoted 14 lines · Luis R. Rodriguez

From: "Luis R. Rodriguez" <[email protected]>

On kernels with voluntary or no preemption we can run into situations where a hypercall issued through userspace will linger around as it addresses sub-operatiosn in kernel context (multicalls). Such operations can trigger soft lockup detection.

We want to address a way to let the kernel voluntarily preempt such calls even on non preempt kernels, to address this we first need to distinguish which hypercalls fall under this category. This implements xen_is_preemptible_hypercall() which lets us do just that by adding a secondary hypercall page, calls made via the new page may be preempted.

[...]

Quoted 4 lines
arch/x86/include/asm/xen/hypercall.h +0 -0
@@ -84,6 +84,22 @@
 

arch/x86/include/asm/xen/hypercall.h line 94

Quoted 10 lines
arch/x86/include/asm/xen/hypercall.h +8 -0
 extern struct { char _entry[32]; } hypercall_page[];
 
+#ifndef CONFIG_PREEMPT
+extern struct { char _entry[32]; } preemptible_hypercall_page[];
+
+static inline bool xen_is_preemptible_hypercall(struct pt_regs *regs)
+{
+	return !user_mode_vm(regs) &&
+		regs->ip >= (unsigned long)preemptible_hypercall_page &&
+		regs->ip < (unsigned long)preemptible_hypercall_page + PAGE_SIZE;

I think you can optimize this to:

Quoted 1 line
    return (regs->ip >> PAGE_SHIFT) == preemptible_hypercall_pfn

I take it you meant preemptible_hypercall_page ?

Quoted 1 line
	&& !user_mode_vm(regs);

If so I don't see how this can work as an identical replacement. Consider a PAGE_SIZE is 16, so PAGE_SHIFT would be 4, and lets say we are checking for byte 2 which should be in the page:

; 0b0010 >>4

	0

Can you elaborate more on this, or can we perhaps leave such optimization as an evolution to avoid regressions if you are not 100% certain?

Luis

#8 lore raw

Re: [RFC v4 1/2] x86/xen: add xen_is_preemptible_hypercall()

In reply to David Vrabel
Quoted 33 lines · David Vrabel
Quoted 14 lines · Luis R. Rodriguez

From: "Luis R. Rodriguez" <[email protected]>

On kernels with voluntary or no preemption we can run into situations where a hypercall issued through userspace will linger around as it addresses sub-operatiosn in kernel context (multicalls). Such operations can trigger soft lockup detection.

We want to address a way to let the kernel voluntarily preempt such calls even on non preempt kernels, to address this we first need to distinguish which hypercalls fall under this category. This implements xen_is_preemptible_hypercall() which lets us do just that by adding a secondary hypercall page, calls made via the new page may be preempted.

[...]

Quoted 4 lines
arch/x86/include/asm/xen/hypercall.h +0 -0
@@ -84,6 +84,22 @@
 

arch/x86/include/asm/xen/hypercall.h line 94

Quoted 10 lines
arch/x86/include/asm/xen/hypercall.h +8 -0
 extern struct { char _entry[32]; } hypercall_page[];
 
+#ifndef CONFIG_PREEMPT
+extern struct { char _entry[32]; } preemptible_hypercall_page[];
+
+static inline bool xen_is_preemptible_hypercall(struct pt_regs *regs)
+{
+	return !user_mode_vm(regs) &&
+		regs->ip >= (unsigned long)preemptible_hypercall_page &&
+		regs->ip < (unsigned long)preemptible_hypercall_page + PAGE_SIZE;

I think you can optimize this to:

Quoted 1 line
    return (regs->ip >> PAGE_SHIFT) == preemptible_hypercall_pfn

I take it you meant preemptible_hypercall_page ?

Quoted 1 line
	&& !user_mode_vm(regs);

If so I don't see how this can work as an identical replacement. Consider a PAGE_SIZE is 16, so PAGE_SHIFT would be 4, and lets say we are checking for byte 2 which should be in the page:

; 0b0010 >>4

	0

Can you elaborate more on this, or can we perhaps leave such optimization as an evolution to avoid regressions if you are not 100% certain?

Luis

#9 lore raw

Re: [RFC v4 1/2] x86/xen: add xen_is_preemptible_hypercall()

In reply to Luis R. Rodriguez
Quoted 14 lines · Luis R. Rodriguez

From: "Luis R. Rodriguez" <[email protected]>

On kernels with voluntary or no preemption we can run into situations where a hypercall issued through userspace will linger around as it addresses sub-operatiosn in kernel context (multicalls). Such operations can trigger soft lockup detection.

We want to address a way to let the kernel voluntarily preempt such calls even on non preempt kernels, to address this we first need to distinguish which hypercalls fall under this category. This implements xen_is_preemptible_hypercall() which lets us do just that by adding a secondary hypercall page, calls made via the new page may be preempted.

[...]

Quoted 4 lines
arch/x86/include/asm/xen/hypercall.h +0 -0
@@ -84,6 +84,22 @@
 

arch/x86/include/asm/xen/hypercall.h line 94

Quoted 10 lines
arch/x86/include/asm/xen/hypercall.h +8 -0
 extern struct { char _entry[32]; } hypercall_page[];
 
+#ifndef CONFIG_PREEMPT
+extern struct { char _entry[32]; } preemptible_hypercall_page[];
+
+static inline bool xen_is_preemptible_hypercall(struct pt_regs *regs)
+{
+	return !user_mode_vm(regs) &&
+		regs->ip >= (unsigned long)preemptible_hypercall_page &&
+		regs->ip < (unsigned long)preemptible_hypercall_page + PAGE_SIZE;

I think you can optimize this to:

    return (regs->ip >> PAGE_SHIFT) == preemptible_hypercall_pfn
	&& !user_mode_vm(regs);

David

#10 lore raw

RFC v4 1/2 x86/xen: add xen_is_preemptible_hypercall()

In reply to Luis R. Rodriguez

From: "Luis R. Rodriguez" <[email protected]>

On kernels with voluntary or no preemption we can run into situations where a hypercall issued through userspace will linger around as it addresses sub-operatiosn in kernel context (multicalls). Such operations can trigger soft lockup detection.

We want to address a way to let the kernel voluntarily preempt such calls even on non preempt kernels, to address this we first need to distinguish which hypercalls fall under this category. This implements xen_is_preemptible_hypercall() which lets us do just that by adding a secondary hypercall page, calls made via the new page may be preempted.

Andrew had originally submitted a version of this work [0].

[0] http://lists.xen.org/archives/html/xen-devel/2014-02/msg01056.html

Based on original work by: Andrew Cooper <[email protected]>

Cc Andy Lutomirski <[email protected]>
Cc Borislav Petkov <[email protected]>
Cc David Vrabel <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc "H. Peter Anvin" <[email protected]>
Cc Steven Rostedt <[email protected]>
Cc Masami Hiramatsu <[email protected]>
Cc Jan Beulich <[email protected]>
---
 arch/arm/include/asm/xen/hypercall.h |  5 +++++
 arch/x86/include/asm/xen/hypercall.h | 20 ++++++++++++++++++++
 arch/x86/xen/enlighten.c             |  7 +++++++
 arch/x86/xen/xen-head.S              | 18 +++++++++++++++++-
 4 files changed, 49 insertions(+), 1 deletion(-)
arch/arm/include/asm/xen/hypercall.h +5 -0
index 712b50e..4fc8395 100644
@@ -74,4 +74,9 @@ MULTI_mmu_update(struct multicall_entry *mcl, struct mmu_update *req,
 	BUG();
 }
 
+static inline bool xen_is_preemptible_hypercall(struct pt_regs *regs)
+{
+	return false;
+}
+
 #endif /* _ASM_ARM_XEN_HYPERCALL_H */
arch/x86/include/asm/xen/hypercall.h +20 -0
index ca08a27..221008e 100644
@@ -84,6 +84,22 @@
 
 extern struct { char _entry[32]; } hypercall_page[];
 
+#ifndef CONFIG_PREEMPT
+extern struct { char _entry[32]; } preemptible_hypercall_page[];
+
+static inline bool xen_is_preemptible_hypercall(struct pt_regs *regs)
+{
+	return !user_mode_vm(regs) &&
+		regs->ip >= (unsigned long)preemptible_hypercall_page &&
+		regs->ip < (unsigned long)preemptible_hypercall_page + PAGE_SIZE;
+}
+#else
+static inline bool xen_is_preemptible_hypercall(struct pt_regs *regs)
+{
+	return false;
+}
+#endif
+
 #define __HYPERCALL		"call hypercall_page+%c[offset]"
 #define __HYPERCALL_ENTRY(x)						\
 	[offset] "i" (__HYPERVISOR_##x * sizeof(hypercall_page[0]))
@@ -215,7 +231,11 @@ privcmd_call(unsigned call,
 
 	asm volatile("call *%[call]"
 		     : __HYPERCALL_5PARAM
+#ifndef CONFIG_PREEMPT
+		     : [call] "a" (&preemptible_hypercall_page[call])
+#else
 		     : [call] "a" (&hypercall_page[call])
+#endif
 		     : __HYPERCALL_CLOBBER5);
 
 	return (long)__res;
arch/x86/xen/enlighten.c +7 -0
index 6bf3a13..9c01b48 100644
@@ -84,6 +84,9 @@
 #include "multicalls.h"
 
 EXPORT_SYMBOL_GPL(hypercall_page);
+#ifndef CONFIG_PREEMPT
+EXPORT_SYMBOL_GPL(preemptible_hypercall_page);
+#endif
 
 /*
  * Pointer to the xen_vcpu_info structure or
@@ -1531,6 +1534,10 @@ asmlinkage __visible void __init xen_start_kernel(void)
 #endif
 	xen_setup_machphys_mapping();
 
+#ifndef CONFIG_PREEMPT
+	copy_page(preemptible_hypercall_page, hypercall_page);
+#endif
+
 	/* Install Xen paravirt ops */
 	pv_info = xen_info;
 	pv_init_ops = xen_init_ops;
arch/x86/xen/xen-head.S +17 -1
index 674b2225..6e6a9517 100644
@@ -85,9 +85,18 @@ ENTRY(xen_pvh_early_cpu_init)
 .pushsection .text
 	.balign PAGE_SIZE
 ENTRY(hypercall_page)
+
+#ifdef CONFIG_PREEMPT
+#  define PREEMPT_HYPERCALL_ENTRY(x)
+#else
+#  define PREEMPT_HYPERCALL_ENTRY(x) \
+       .global xen_hypercall_##x ## _p ASM_NL \
+       .set preemptible_xen_hypercall_##x, xen_hypercall_##x + PAGE_SIZE ASM_NL
+#endif
 #define NEXT_HYPERCALL(x) \
 	ENTRY(xen_hypercall_##x) \
-	.skip 32
+	.skip 32 ASM_NL \
+	PREEMPT_HYPERCALL_ENTRY(x)
 
 NEXT_HYPERCALL(set_trap_table)
 NEXT_HYPERCALL(mmu_update)
@@ -138,6 +147,13 @@ NEXT_HYPERCALL(arch_4)
 NEXT_HYPERCALL(arch_5)
 NEXT_HYPERCALL(arch_6)
 	.balign PAGE_SIZE
+
+#ifndef CONFIG_PREEMPT
+ENTRY(preemptible_hypercall_page)
+	.skip PAGE_SIZE
+#endif /* CONFIG_PREEMPT */
+
+#undef NEXT_HYPERCALL
 .popsection
 
 	ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS,       .asciz "linux")
Signature · 1 line
2.1.1
#11 lore raw

RFC v4 2/2 x86/xen: allow privcmd hypercalls to be preempted

In reply to Luis R. Rodriguez

From: "Luis R. Rodriguez" <[email protected]>

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 <[email protected]>

Cc Andy Lutomirski <[email protected]>
Cc Borislav Petkov <[email protected]>
Cc David Vrabel <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc "H. Peter Anvin" <[email protected]>
Cc Steven Rostedt <[email protected]>
Cc Masami Hiramatsu <[email protected]>
Cc Jan Beulich <[email protected]>
---
 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(+)
arch/x86/kernel/entry_32.S +2 -0
index 000d419..b4b1f42 100644
@@ -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)
arch/x86/kernel/entry_64.S +2 -0
index 9ebaf63..ee28733 100644
@@ -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)
drivers/xen/events/events_base.c +23 -0
index b4bca2d..8126642 100644
@@ -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();
include/trace/events/xen.h +9 -0
index d06b6da..77e333b 100644
@@ -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 */
 
include/xen/events.h +1 -0
index 5321cd9..f08df87 100644
@@ -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. */
Signature · 1 line
2.1.1
Reviewed-by on v4 2/2
#12 lore raw

Re: [RFC v4 2/2] x86/xen: allow privcmd hypercalls to be preempted

Quoted 82 lines · Luis R. Rodriguez

From: "Luis R. Rodriguez" <[email protected]>

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 <[email protected]>

Cc Andy Lutomirski <[email protected]>
Cc Borislav Petkov <[email protected]>
Cc David Vrabel <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc "H. Peter Anvin" <[email protected]>
Cc Steven Rostedt <[email protected]>
Cc Masami Hiramatsu <[email protected]>
Cc Jan Beulich <[email protected]>
Quoted 8 lines
---
 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(+)
Quoted 6 lines
drivers/xen/events/events_base.c +5 -0
+/*
+ * 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

drivers/xen/events/events_base.c void xen_evtchn_do_upcall(struct pt_regs *regs) · line 1264

Quoted 10 lines
drivers/xen/events/events_base.c +10 -0
+ * 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);

If you want to speed this up a bit, I think you could move the smp_processor_id() into the TP_fast_assign. But don't tracepoints report the cpu number even without any action?

maintainer
#13 lore raw

Re: [RFC v4 2/2] x86/xen: allow privcmd hypercalls to be preempted

Quoted 12 lines · On Thu, 22 Jan 2015 17:40:27 -0800 Andy Lutomirski <[email protected]> wrote:
Quoted 12 lines
drivers/xen/events/events_base.c +11 -0
+/*
+ * 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)
+{
Quoted 8 lines

drivers/xen/events/events_base.c void xen_evtchn_do_upcall(struct pt_regs *regs) · line 1264

Quoted 4 lines
drivers/xen/events/events_base.c +4 -0
+       if (xen_is_preemptible_hypercall(regs)) {
+               int cpuid = smp_processor_id();
+               if (_cond_resched())
+                       trace_xen_hypercall_preemption(cpuid);

If you want to speed this up a bit, I think you could move the smp_processor_id() into the TP_fast_assign. But don't tracepoints report the cpu number even without any action?

Yes, but if you scheduled here, the tracepoint could happen on a different CPU. Thus, cpuid will not equal smp_processor_id().

-- Steve

maintainer
#14 lore raw

Re: [RFC v4 2/2] x86/xen: allow privcmd hypercalls to be preempted

In reply to Andy Lutomirski
Quoted 12 lines · On Thu, 22 Jan 2015 17:40:27 -0800 Andy Lutomirski <[email protected]> wrote:
Quoted 12 lines
drivers/xen/events/events_base.c +11 -0
+/*
+ * 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)
+{
Quoted 8 lines

drivers/xen/events/events_base.c void xen_evtchn_do_upcall(struct pt_regs *regs) · line 1264

Quoted 4 lines
drivers/xen/events/events_base.c +4 -0
+       if (xen_is_preemptible_hypercall(regs)) {
+               int cpuid = smp_processor_id();
+               if (_cond_resched())
+                       trace_xen_hypercall_preemption(cpuid);

If you want to speed this up a bit, I think you could move the smp_processor_id() into the TP_fast_assign. But don't tracepoints report the cpu number even without any action?

Yes, but if you scheduled here, the tracepoint could happen on a different CPU. Thus, cpuid will not equal smp_processor_id().

-- Steve

Reviewed-by on v4 2/2
#15 lore raw

Re: [RFC v4 2/2] x86/xen: allow privcmd hypercalls to be preempted

In reply to Luis R. Rodriguez
Quoted 82 lines · Luis R. Rodriguez

From: "Luis R. Rodriguez" <[email protected]>

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 <[email protected]>

Cc Andy Lutomirski <[email protected]>
Cc Borislav Petkov <[email protected]>
Cc David Vrabel <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc "H. Peter Anvin" <[email protected]>
Cc Steven Rostedt <[email protected]>
Cc Masami Hiramatsu <[email protected]>
Cc Jan Beulich <[email protected]>
Quoted 8 lines
---
 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(+)
Quoted 6 lines
drivers/xen/events/events_base.c +5 -0
+/*
+ * 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

drivers/xen/events/events_base.c void xen_evtchn_do_upcall(struct pt_regs *regs) · line 1264

Quoted 10 lines
drivers/xen/events/events_base.c +10 -0
+ * 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);

If you want to speed this up a bit, I think you could move the smp_processor_id() into the TP_fast_assign. But don't tracepoints report the cpu number even without any action?

#16 lore raw

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

In reply to Luis R. Rodriguez
Quoted 48 lines · Luis R. Rodriguez

From: "Luis R. Rodriguez" <[email protected]>

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.

[...]

drivers/xen/events/events_base.c void xen_evtchn_do_upcall(struct pt_regs *regs) · line 1255

Quoted 10 lines
drivers/xen/events/events_base.c +6 -0
@@ -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.

Rewrite this comment as;

* Some hypercalls issued by the toolstack can take many 10s of
* seconds. Allow tasks running hypercalls via the privcmd driver to be
* voluntarily preempted even if full kernel preemption is disabled.

drivers/xen/events/events_base.c void xen_evtchn_do_upcall(struct pt_regs *regs) · line 1257

Quoted 1 line
drivers/xen/events/events_base.c +1 -0
+ * [0] https://bugzilla.novell.com/show_bug.cgi?id=861093

This link isn't accessible so I don't think it should be included here.

drivers/xen/events/events_base.c void xen_evtchn_do_upcall(struct pt_regs *regs) · line 1264

Quoted 7 lines
drivers/xen/events/events_base.c +7 -0
+ */
+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);

I don't think a tracepoint here is useful.

drivers/xen/events/events_base.c void xen_evtchn_do_upcall(struct pt_regs *regs) · line 1267

Quoted 3 lines
drivers/xen/events/events_base.c +3 -0
+	}
+}
+NOKPROBE_SYMBOL(xen_end_upcall);

Do we need this is this function is no longer notrace?

David

#17 lore raw

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

Quoted 63 lines · David Vrabel
Quoted 48 lines · Luis R. Rodriguez

From: "Luis R. Rodriguez" <[email protected]>

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.

[...]

drivers/xen/events/events_base.c void xen_evtchn_do_upcall(struct pt_regs *regs) · line 1255

Quoted 10 lines
drivers/xen/events/events_base.c +6 -0
@@ -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.

Rewrite this comment as;

Quoted 1 line

* Some hypercalls issued by the toolstack can take many 10s of

Its not just hypercalls though, this is all about the interactions with multicalls no?

Quoted 6 lines

* seconds. Allow tasks running hypercalls via the privcmd driver to be
* voluntarily preempted even if full kernel preemption is disabled.

drivers/xen/events/events_base.c void xen_evtchn_do_upcall(struct pt_regs *regs) · line 1257

Quoted 1 line
drivers/xen/events/events_base.c +1 -0
+ * [0] https://bugzilla.novell.com/show_bug.cgi?id=861093

This link isn't accessible so I don't think it should be included here.

OK.

Luis

#18 lore raw

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

Quoted 16 lines
Quoted 1 line
Quoted 1 line · On 23.01.15 at 19:58, <[email protected]> wrote:
Quoted 14 lines · David Vrabel

drivers/xen/events/events_base.c void xen_evtchn_do_upcall(struct pt_regs *regs) · line 1255

Quoted 10 lines · Luis R. Rodriguez
drivers/xen/events/events_base.c +6 -0
@@ -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.

Rewrite this comment as;

Quoted 4 lines
Quoted 1 line

* Some hypercalls issued by the toolstack can take many 10s of

Its not just hypercalls though, this is all about the interactions with multicalls no?

multicalls are just a special case of hypercalls.

Jan

#19 lore raw

Re: [RFC v4 2/2] x86/xen: allow privcmd hypercalls to be preempted

In reply to Luis R. Rodriguez
Quoted 16 lines
Quoted 1 line
Quoted 1 line · On 23.01.15 at 19:58, <[email protected]> wrote:
Quoted 14 lines · David Vrabel

drivers/xen/events/events_base.c void xen_evtchn_do_upcall(struct pt_regs *regs) · line 1255

Quoted 10 lines · Luis R. Rodriguez
drivers/xen/events/events_base.c +6 -0
@@ -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.

Rewrite this comment as;

Quoted 4 lines
Quoted 1 line

* Some hypercalls issued by the toolstack can take many 10s of

Its not just hypercalls though, this is all about the interactions with multicalls no?

multicalls are just a special case of hypercalls.

Jan

#20 lore raw

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

In reply to Luis R. Rodriguez
Quoted 3 lines · Luis R. Rodriguez

Its not just hypercalls though, this is all about the interactions with multicalls no?

No. This applies to any preemptible hypercall and the toolstack doesn't use multicalls for most of its work.

David

#21 lore raw

Re: [RFC v4 2/2] x86/xen: allow privcmd hypercalls to be preempted

In reply to Luis R. Rodriguez
Quoted 3 lines · Luis R. Rodriguez

Its not just hypercalls though, this is all about the interactions with multicalls no?

No. This applies to any preemptible hypercall and the toolstack doesn't use multicalls for most of its work.

David

#22 lore raw

Re: [RFC v4 2/2] x86/xen: allow privcmd hypercalls to be preempted

In reply to David Vrabel
Quoted 63 lines · David Vrabel
Quoted 48 lines · Luis R. Rodriguez

From: "Luis R. Rodriguez" <[email protected]>

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.

[...]

drivers/xen/events/events_base.c void xen_evtchn_do_upcall(struct pt_regs *regs) · line 1255

Quoted 10 lines
drivers/xen/events/events_base.c +6 -0
@@ -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.

Rewrite this comment as;

Quoted 1 line

* Some hypercalls issued by the toolstack can take many 10s of

Its not just hypercalls though, this is all about the interactions with multicalls no?

Quoted 6 lines

* seconds. Allow tasks running hypercalls via the privcmd driver to be
* voluntarily preempted even if full kernel preemption is disabled.

drivers/xen/events/events_base.c void xen_evtchn_do_upcall(struct pt_regs *regs) · line 1257

Quoted 1 line
drivers/xen/events/events_base.c +1 -0
+ * [0] https://bugzilla.novell.com/show_bug.cgi?id=861093

This link isn't accessible so I don't think it should be included here.

OK.

Luis

#23 lore raw

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

In reply to David Vrabel
Quoted 9 lines · David Vrabel

drivers/xen/events/events_base.c void xen_evtchn_do_upcall(struct pt_regs *regs) · line 1264

Quoted 7 lines

+ */

drivers/xen/events/events_base.c +6 -0
+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);

I don't think a tracepoint here is useful.

OK.. I'll remove.

Quoted 5 lines

drivers/xen/events/events_base.c void xen_evtchn_do_upcall(struct pt_regs *regs) · line 1267

Quoted 3 lines
drivers/xen/events/events_base.c +3 -0
+	}
+}
+NOKPROBE_SYMBOL(xen_end_upcall);

Do we need this is this function is no longer notrace?

Stephen and Andy were going down some corner case rabbit hole and it seemed to me that the conclusion was not settled so to be safe I kept it. I'll let them decide. I did remove the notrace junk.

Luis

#24 lore raw

Re: [RFC v4 2/2] x86/xen: allow privcmd hypercalls to be preempted

In reply to David Vrabel
Quoted 9 lines · David Vrabel

drivers/xen/events/events_base.c void xen_evtchn_do_upcall(struct pt_regs *regs) · line 1264

Quoted 7 lines

+ */

drivers/xen/events/events_base.c +6 -0
+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);

I don't think a tracepoint here is useful.

OK.. I'll remove.

Quoted 5 lines

drivers/xen/events/events_base.c void xen_evtchn_do_upcall(struct pt_regs *regs) · line 1267

Quoted 3 lines
drivers/xen/events/events_base.c +3 -0
+	}
+}
+NOKPROBE_SYMBOL(xen_end_upcall);

Do we need this is this function is no longer notrace?

Stephen and Andy were going down some corner case rabbit hole and it seemed to me that the conclusion was not settled so to be safe I kept it. I'll let them decide. I did remove the notrace junk.

Luis

#25 lore raw

Re: [RFC v4 2/2] x86/xen: allow privcmd hypercalls to be preempted

In reply to Luis R. Rodriguez
Quoted 48 lines · Luis R. Rodriguez

From: "Luis R. Rodriguez" <[email protected]>

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.

[...]

drivers/xen/events/events_base.c void xen_evtchn_do_upcall(struct pt_regs *regs) · line 1255

Quoted 10 lines
drivers/xen/events/events_base.c +6 -0
@@ -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.

Rewrite this comment as;

* Some hypercalls issued by the toolstack can take many 10s of
* seconds. Allow tasks running hypercalls via the privcmd driver to be
* voluntarily preempted even if full kernel preemption is disabled.

drivers/xen/events/events_base.c void xen_evtchn_do_upcall(struct pt_regs *regs) · line 1257

Quoted 1 line
drivers/xen/events/events_base.c +1 -0
+ * [0] https://bugzilla.novell.com/show_bug.cgi?id=861093

This link isn't accessible so I don't think it should be included here.

drivers/xen/events/events_base.c void xen_evtchn_do_upcall(struct pt_regs *regs) · line 1264

Quoted 7 lines
drivers/xen/events/events_base.c +7 -0
+ */
+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);

I don't think a tracepoint here is useful.

drivers/xen/events/events_base.c void xen_evtchn_do_upcall(struct pt_regs *regs) · line 1267

Quoted 3 lines
drivers/xen/events/events_base.c +3 -0
+	}
+}
+NOKPROBE_SYMBOL(xen_end_upcall);

Do we need this is this function is no longer notrace?

David

#26 lore raw

RFC v4 2/2 x86/xen: allow privcmd hypercalls to be preempted

In reply to Luis R. Rodriguez

From: "Luis R. Rodriguez" <[email protected]>

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 <[email protected]>

Cc Andy Lutomirski <[email protected]>
Cc Borislav Petkov <[email protected]>
Cc David Vrabel <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc "H. Peter Anvin" <[email protected]>
Cc Steven Rostedt <[email protected]>
Cc Masami Hiramatsu <[email protected]>
Cc Jan Beulich <[email protected]>
---
 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(+)
arch/x86/kernel/entry_32.S +2 -0
index 000d419..b4b1f42 100644
@@ -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)
arch/x86/kernel/entry_64.S +2 -0
index 9ebaf63..ee28733 100644
@@ -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)
drivers/xen/events/events_base.c +23 -0
index b4bca2d..8126642 100644
@@ -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();
include/trace/events/xen.h +9 -0
index d06b6da..77e333b 100644
@@ -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 */
 
include/xen/events.h +1 -0
index 5321cd9..f08df87 100644
@@ -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. */
Signature · 1 line
2.1.1
#27 lore raw
In reply to Luis R. Rodriguez
Quoted 10 lines · Luis R. Rodriguez

From: "Luis R. Rodriguez" <[email protected]>

This v4 addresses some of the cleanups recommended and adds tracing option for when we do actually preempt a hypercall. I kept the NOKPROBE_SYMBOL() for now but did remove the 'notrace' stuff.

This goes out as RFC still as I have not been able to test 32-bit. Can anyone test that or at least confirm that the 32-bit point we do the upcall is definitely not on the IRQ stack?

You can omit fixing this for 32-bit guests (provided you note as such in the commit message).

David

#28 lore raw
Quoted 8 lines · David Vrabel
Quoted 7 lines · Luis R. Rodriguez

From: "Luis R. Rodriguez" <[email protected]>

This v4 addresses some of the cleanups recommended and adds tracing option for when we do actually preempt a hypercall. I kept the NOKPROBE_SYMBOL() for now but did remove the 'notrace' stuff.

Quoted 6 lines
Quoted 3 lines

This goes out as RFC still as I have not been able to test 32-bit. Can anyone test that or at least confirm that the 32-bit point we do the upcall is definitely not on the IRQ stack?

You can omit fixing this for 32-bit guests (provided you note as such in the commit message).

I'll be happy to do that.

Luis

#29 lore raw
In reply to David Vrabel
Quoted 8 lines · David Vrabel
Quoted 7 lines · Luis R. Rodriguez

From: "Luis R. Rodriguez" <[email protected]>

This v4 addresses some of the cleanups recommended and adds tracing option for when we do actually preempt a hypercall. I kept the NOKPROBE_SYMBOL() for now but did remove the 'notrace' stuff.

Quoted 6 lines
Quoted 3 lines

This goes out as RFC still as I have not been able to test 32-bit. Can anyone test that or at least confirm that the 32-bit point we do the upcall is definitely not on the IRQ stack?

You can omit fixing this for 32-bit guests (provided you note as such in the commit message).

I'll be happy to do that.

Luis

#30 lore raw
In reply to Luis R. Rodriguez
Quoted 10 lines · Luis R. Rodriguez

From: "Luis R. Rodriguez" <[email protected]>

This v4 addresses some of the cleanups recommended and adds tracing option for when we do actually preempt a hypercall. I kept the NOKPROBE_SYMBOL() for now but did remove the 'notrace' stuff.

This goes out as RFC still as I have not been able to test 32-bit. Can anyone test that or at least confirm that the 32-bit point we do the upcall is definitely not on the IRQ stack?

You can omit fixing this for 32-bit guests (provided you note as such in the commit message).

David