[Patch v8 06/23] perf/x86: Use x86_perf_regs in the x86 nmi handlers

[Dapeng Mi]

More and more regs will be supported in the overflow, e.g., more vector
registers, SSP, etc. The generic pt_regs struct cannot store all of
them. Use a X86 specific x86_perf_regs instead.

The struct pt_regs *regs is still passed to x86_pmu_handle_irq(). There
is no functional change for the existing code.

AMD IBS's NMI handler doesn't utilize the static call
x86_pmu_handle_irq(). The x86_perf_regs struct doesn't apply to the AMD
IBS. It can be added separately later when AMD IBS supports more regs.

Co-developed-by: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
Signed-off-by: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
Signed-off-by: Dapeng Mi <dapeng1.mi@xxxxxxxxxxxxxxx>
---

V8: Use x86_perf_regs for xen_pmu_irq_handler() as well.

 arch/x86/events/core.c | 5 ++++-
 arch/x86/xen/pmu.c     | 5 ++++-
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 17e122e27e0b..17c8f44ee43b 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1788,9 +1788,11 @@ void perf_put_guest_lvtpc(void)
 EXPORT_SYMBOL_FOR_KVM(perf_put_guest_lvtpc);
 #endif /* CONFIG_PERF_GUEST_MEDIATED_PMU */
 
+static DEFINE_PER_CPU(struct x86_perf_regs, x86_intr_regs);
 static int
 perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs)
 {
+	struct x86_perf_regs *x86_regs = this_cpu_ptr(&x86_intr_regs);
 	u64 start_clock;
 	u64 finish_clock;
 	int ret;
@@ -1814,7 +1816,8 @@ perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs)
 		return NMI_DONE;
 
 	start_clock = sched_clock();
-	ret = static_call(x86_pmu_handle_irq)(regs);
+	x86_regs->regs = *regs;
+	ret = static_call(x86_pmu_handle_irq)(&x86_regs->regs);
 	finish_clock = sched_clock();
 
 	perf_sample_event_took(finish_clock - start_clock);
diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c
index 8f89ce0b67e3..de3d7d391a5e 100644
--- a/arch/x86/xen/pmu.c
+++ b/arch/x86/xen/pmu.c
@@ -455,12 +455,14 @@ static void xen_convert_regs(const struct xen_pmu_regs *xen_regs,
 	}
 }
 
+static DEFINE_PER_CPU(struct x86_perf_regs, x86_xen_intr_regs);
 irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id)
 {
 	int err, ret = IRQ_NONE;
 	struct pt_regs regs = {0};
 	const struct xen_pmu_data *xenpmu_data = get_xenpmu_data();
 	uint8_t xenpmu_flags = get_xenpmu_flags();
+	struct x86_perf_regs *x86_regs = this_cpu_ptr(&x86_xen_intr_regs);
 
 	if (!xenpmu_data) {
 		pr_warn_once("%s: pmudata not initialized\n", __func__);
@@ -471,7 +473,8 @@ irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id)
 		xenpmu_flags | XENPMU_IRQ_PROCESSING;
 	xen_convert_regs(&xenpmu_data->pmu.r.regs, &regs,
 			 xenpmu_data->pmu.pmu_flags);
-	if (x86_pmu.handle_irq(&regs))
+	x86_regs->regs = regs;
+	if (x86_pmu.handle_irq(&x86_regs->regs))
 		ret = IRQ_HANDLED;
 
 	/* Write out cached context to HW */
-- 
2.34.1