Re: [PATCH 00/15] perf: KVM: Fix, optimize, and clean up callbacks

From: Like Xu
Date: Fri Aug 27 2021 - 04:04:04 EST

On 27/8/2021 3:44 pm, Peter Zijlstra wrote:
On Fri, Aug 27, 2021 at 02:52:25PM +0800, Like Xu wrote:

On 27/8/2021 8:57 am, Sean Christopherson wrote:
This started out as a small series[1] to fix a KVM bug related to Intel PT
interrupt handling and snowballed horribly.

The main problem being addressed is that the perf_guest_cbs are shared by
all CPUs, can be nullified by KVM during module unload, and are not
protected against concurrent access from NMI context.

Shouldn't this be a generic issue of the static_call() usage ?

At the beginning, we set up the static entry assuming perf_guest_cbs != NULL:

if (perf_guest_cbs && perf_guest_cbs->handle_intel_pt_intr) {

and then we unset the perf_guest_cbs and do the static function call like this:

static int handle_pmi_common(struct pt_regs *regs, u64 status)
if (!static_call(x86_guest_handle_intel_pt_intr)())

You just have to make sure all static_call() invocations that started
before unreg are finished before continuing with the unload.
synchronize_rcu() can help with that.

Do you mean something like that:

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 64e310ff4f3a..e7d310af7509 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8465,6 +8465,7 @@ void kvm_arch_exit(void)
+ synchronize_rcu();

if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e466fc8176e1..63ae56c5d133 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6508,6 +6508,7 @@ EXPORT_SYMBOL_GPL(perf_register_guest_info_callbacks);
int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs)
perf_guest_cbs = NULL;
+ arch_perf_update_guest_cbs();
return 0;

This is module unload 101. Nothing specific to static_call().