[RESEND Patch v10 05/23] perf/x86: Use x86_perf_regs in NMI handlers

Support for sampling additional register state in NMI context
(e.g. vector registers and SSP) requires an x86-specific register
container. The generic pt_regs structure cannot represent all of
the required x86 register data, so switch x86 NMI handlers to
x86_perf_regs.

pt_regs is still passed to x86_pmu_handle_irq(), so there is no
functional change to existing handling.

AMD IBS NMI handling does not use x86_pmu_handle_irq(), so this
conversion does not apply to IBS. IBS support for extended register
sampling can be added separately in follow-up patches.

Co-developed-by: Kan Liang <[email protected]>
Signed-off-by: Kan Liang <[email protected]>
Signed-off-by: Dapeng Mi <[email protected]>
---
 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 75358a297222..3368270c0ad1 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1800,9 +1800,11 @@ 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;
@@ -1826,7 +1828,8 @@ 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 5f50a3ee08f5..3f4dd3f50f56 100644
--- a/arch/x86/xen/pmu.c
+++ b/arch/x86/xen/pmu.c
@@ -456,12 +456,14 @@ 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__);
@@ -472,7 +474,8 @@ 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