From: Like Xu like.xu@linux.intel.com
mainline inclusion from mainline-v5.9-rc1 commit 097e4311cda952dfb047f2a49d35aa5de500d474 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I47H3V CVE: NA
--------------------------------
commit 097e4311cda952dfb047f2a49d35aa5de500d474 upstream Backport summary: backport to kernel 4.19.57 for ICX perf topdown support
The hypervisor may request the perf subsystem to schedule a time window to directly access the LBR records msrs for its own use. Normally, it would create a guest LBR event with callstack mode enabled, which is scheduled along with other ordinary LBR events on the host but in an exclusive way.
To avoid wasting a counter for the guest LBR event, the perf tracks its hw->idx via INTEL_PMC_IDX_FIXED_VLBR and assigns it with a fake VLBR counter with the help of new vlbr_constraint. As with the BTS event, there is actually no hardware counter assigned for the guest LBR event.
Signed-off-by: Like Xu like.xu@linux.intel.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/20200514083054.62538-5-like.xu@linux.intel.com Signed-off-by: Yunying Sun yunying.sun@intel.com Signed-off-by: Jackie Liu liuyun01@kylinos.cn Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Reviewed-by: Wei Li liwei391@huawei.com Reviewed-by: Xie XiuQi xiexiuqi@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- arch/x86/events/core.c | 1 + arch/x86/events/intel/core.c | 18 ++++++++++++++++++ arch/x86/events/intel/lbr.c | 4 ++++ arch/x86/events/perf_event.h | 1 + arch/x86/include/asm/perf_event.h | 22 +++++++++++++++++++++- 5 files changed, 45 insertions(+), 1 deletion(-)
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 25a1b9953c1d9..b4b3ecc9bbbaa 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1063,6 +1063,7 @@ static inline void x86_assign_hw_event(struct perf_event *event,
switch (hwc->idx) { case INTEL_PMC_IDX_FIXED_BTS: + case INTEL_PMC_IDX_FIXED_VLBR: hwc->config_base = 0; hwc->event_base = 0; break; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index e5ef223a60931..ec4373143d164 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2494,6 +2494,20 @@ intel_bts_constraints(struct perf_event *event) return NULL; }
+/* + * Note: matches a fake event, like Fixed2. + */ +static struct event_constraint * +intel_vlbr_constraints(struct perf_event *event) +{ + struct event_constraint *c = &vlbr_constraint; + + if (unlikely(constraint_match(c, event->hw.config))) + return c; + + return NULL; +} + static int intel_alt_er(int idx, u64 config) { int alt_idx = idx; @@ -2684,6 +2698,10 @@ __intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx, { struct event_constraint *c;
+ c = intel_vlbr_constraints(event); + if (c) + return c; + c = intel_bts_constraints(event); if (c) return c; diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 15aa2fbdd60ec..eea75f1fc245d 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -1330,3 +1330,7 @@ int x86_perf_get_lbr(struct x86_pmu_lbr *lbr) return 0; } EXPORT_SYMBOL_GPL(x86_perf_get_lbr); + +struct event_constraint vlbr_constraint = + FIXED_EVENT_CONSTRAINT(INTEL_FIXED_VLBR_EVENT, + (INTEL_PMC_IDX_FIXED_VLBR - INTEL_PMC_IDX_FIXED)); diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 1394966d8b516..485f4d4d5c28a 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -967,6 +967,7 @@ void release_ds_buffers(void); void reserve_ds_buffers(void);
extern struct event_constraint bts_constraint; +extern struct event_constraint vlbr_constraint;
void intel_pmu_enable_bts(u64 config);
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index b0174e83ddda7..c4729277d31d7 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -181,9 +181,29 @@ struct x86_pmu_capability { #define GLOBAL_STATUS_UNC_OVF BIT_ULL(61) #define GLOBAL_STATUS_ASIF BIT_ULL(60) #define GLOBAL_STATUS_COUNTERS_FROZEN BIT_ULL(59) -#define GLOBAL_STATUS_LBRS_FROZEN BIT_ULL(58) +#define GLOBAL_STATUS_LBRS_FROZEN_BIT 58 +#define GLOBAL_STATUS_LBRS_FROZEN BIT_ULL(GLOBAL_STATUS_LBRS_FROZEN_BIT) #define GLOBAL_STATUS_TRACE_TOPAPMI BIT_ULL(55)
+/* + * We model guest LBR event tracing as another fixed-mode PMC like BTS. + * + * We choose bit 58 because it's used to indicate LBR stack frozen state + * for architectural perfmon v4, also we unconditionally mask that bit in + * the handle_pmi_common(), so it'll never be set in the overflow handling. + * + * With this fake counter assigned, the guest LBR event user (such as KVM), + * can program the LBR registers on its own, and we don't actually do anything + * with then in the host context. + */ +#define INTEL_PMC_IDX_FIXED_VLBR (GLOBAL_STATUS_LBRS_FROZEN_BIT) + +/* + * Pseudo-encoding the guest LBR event as event=0x00,umask=0x1b, + * since it would claim bit 58 which is effectively Fixed26. + */ +#define INTEL_FIXED_VLBR_EVENT 0x1b00 + /* * Adaptive PEBS v4 */