From: Like Xu like.xu@linux.intel.com
mainline inclusion from mainline-v5.9-rc1 commit e1ad1ac2deb8f90af9f12ff316989dd5675dec11 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I47H3V CVE: NA
--------------------------------
commit e1ad1ac2deb8f90af9f12ff316989dd5675dec11 upstream Backport summary: backport to kernel 4.19.57 for ICX perf topdown support
When a guest wants to use the LBR registers, its hypervisor creates a guest LBR event and let host perf schedules it. The LBR records msrs are accessible to the guest when its guest LBR event is scheduled on by the perf subsystem.
Before scheduling this event out, we should avoid host changes on IA32_DEBUGCTLMSR or LBR_SELECT. Otherwise, some unexpected branch operations may interfere with guest behavior, pollute LBR records, and even cause host branches leakage. In addition, the read operation on host is also avoidable.
To ensure that guest LBR records are not lost during the context switch, the guest LBR event would enable the callstack mode which could save/restore guest unread LBR records with the help of intel_pmu_lbr_sched_task() naturally.
However, the guest LBR_SELECT may changes for its own use and the host LBR event doesn't save/restore it. To ensure that we doesn't lost the guest LBR_SELECT value when the guest LBR event is running, the vlbr_constraint is bound up with a new constraint flag PERF_X86_EVENT_LBR_SELECT.
Signed-off-by: Like Xu like.xu@linux.intel.com Signed-off-by: Wei Wang wei.w.wang@intel.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/20200514083054.62538-6-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/intel/core.c | 4 ++++ arch/x86/events/intel/lbr.c | 31 ++++++++++++++++++++++++++----- arch/x86/events/perf_event.h | 3 +++ 3 files changed, 33 insertions(+), 5 deletions(-)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index ec4373143d16..28359c6d9039 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2167,6 +2167,8 @@ static void intel_pmu_disable_event(struct perf_event *event) } else if (idx == INTEL_PMC_IDX_FIXED_BTS) { intel_pmu_disable_bts(); intel_pmu_drain_bts_buffer(); + } else if (idx == INTEL_PMC_IDX_FIXED_VLBR) { + intel_clear_masks(event, idx); }
/* @@ -2249,6 +2251,8 @@ static void intel_pmu_enable_event(struct perf_event *event) if (!__this_cpu_read(cpu_hw_events.enabled)) return; intel_pmu_enable_bts(hwc->config); + } else if (idx == INTEL_PMC_IDX_FIXED_VLBR) { + intel_set_masks(event, idx); } }
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index eea75f1fc245..a3dc3b5bc78d 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -383,6 +383,9 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
wrmsrl(x86_pmu.lbr_tos, tos); task_ctx->lbr_stack_state = LBR_NONE; + + if (cpuc->lbr_select) + wrmsrl(MSR_LBR_SELECT, task_ctx->lbr_sel); }
static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx) @@ -415,6 +418,9 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
cpuc->last_task_ctx = task_ctx; cpuc->last_log_id = ++task_ctx->log_id; + + if (cpuc->lbr_select) + rdmsrl(MSR_LBR_SELECT, task_ctx->lbr_sel); }
void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in) @@ -462,6 +468,9 @@ void intel_pmu_lbr_add(struct perf_event *event) if (!x86_pmu.lbr_nr) return;
+ if (event->hw.flags & PERF_X86_EVENT_LBR_SELECT) + cpuc->lbr_select = 1; + cpuc->br_sel = event->hw.branch_reg.reg;
if (branch_user_callstack(cpuc->br_sel) && event->ctx->task_ctx_data) { @@ -509,6 +518,9 @@ void intel_pmu_lbr_del(struct perf_event *event) task_ctx->lbr_callstack_users--; }
+ if (event->hw.flags & PERF_X86_EVENT_LBR_SELECT) + cpuc->lbr_select = 0; + if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0) cpuc->lbr_pebs_users--; cpuc->lbr_users--; @@ -517,11 +529,19 @@ void intel_pmu_lbr_del(struct perf_event *event) perf_sched_cb_dec(event->ctx->pmu); }
+static inline bool vlbr_exclude_host(void) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + return test_bit(INTEL_PMC_IDX_FIXED_VLBR, + (unsigned long *)&cpuc->intel_ctrl_guest_mask); +} + void intel_pmu_lbr_enable_all(bool pmi) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
- if (cpuc->lbr_users) + if (cpuc->lbr_users && !vlbr_exclude_host()) __intel_pmu_lbr_enable(pmi); }
@@ -529,7 +549,7 @@ void intel_pmu_lbr_disable_all(void) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
- if (cpuc->lbr_users) + if (cpuc->lbr_users && !vlbr_exclude_host()) __intel_pmu_lbr_disable(); }
@@ -669,7 +689,8 @@ void intel_pmu_lbr_read(void) * This could be smarter and actually check the event, * but this simple approach seems to work for now. */ - if (!cpuc->lbr_users || cpuc->lbr_users == cpuc->lbr_pebs_users) + if (!cpuc->lbr_users || vlbr_exclude_host() || + cpuc->lbr_users == cpuc->lbr_pebs_users) return;
if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32) @@ -1332,5 +1353,5 @@ int x86_perf_get_lbr(struct x86_pmu_lbr *lbr) 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)); + __EVENT_CONSTRAINT(INTEL_FIXED_VLBR_EVENT, (1ULL << INTEL_PMC_IDX_FIXED_VLBR), + FIXED_EVENT_FLAGS, 1, 0, PERF_X86_EVENT_LBR_SELECT); diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 639a8a6ba05c..697a776b839b 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -78,6 +78,7 @@ static inline bool constraint_match(struct event_constraint *c, u64 ecode) #define PERF_X86_EVENT_AUTO_RELOAD 0x0400 /* use PEBS auto-reload */ #define PERF_X86_EVENT_LARGE_PEBS 0x0800 /* use large PEBS */ #define PERF_X86_EVENT_PAIR 0x1000 /* Large Increment per Cycle */ +#define PERF_X86_EVENT_LBR_SELECT 0x2000 /* Save/Restore MSR_LBR_SELECT */
struct amd_nb { @@ -231,6 +232,7 @@ struct cpu_hw_events { u64 br_sel; struct x86_perf_task_context *last_task_ctx; int last_log_id; + int lbr_select;
/* * Intel host/guest exclude bits @@ -703,6 +705,7 @@ struct x86_perf_task_context { u64 lbr_from[MAX_LBR_ENTRIES]; u64 lbr_to[MAX_LBR_ENTRIES]; u64 lbr_info[MAX_LBR_ENTRIES]; + u64 lbr_sel; int tos; int valid_lbrs; int lbr_callstack_users;