perf fixes

index aa62437d1aa1..98b0f0729527 100644
@@ -1708,6 +1708,120 @@ static __initconst const u64 glm_hw_cache_extra_regs
 	},
 };
 
+static __initconst const u64 glp_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(L1D)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x81d0,	/* MEM_UOPS_RETIRED.ALL_LOADS */
+			[C(RESULT_MISS)]	= 0x0,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= 0x82d0,	/* MEM_UOPS_RETIRED.ALL_STORES */
+			[C(RESULT_MISS)]	= 0x0,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= 0x0,
+			[C(RESULT_MISS)]	= 0x0,
+		},
+	},
+	[C(L1I)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x0380,	/* ICACHE.ACCESSES */
+			[C(RESULT_MISS)]	= 0x0280,	/* ICACHE.MISSES */
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= -1,
+			[C(RESULT_MISS)]	= -1,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= 0x0,
+			[C(RESULT_MISS)]	= 0x0,
+		},
+	},
+	[C(LL)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x1b7,	/* OFFCORE_RESPONSE */
+			[C(RESULT_MISS)]	= 0x1b7,	/* OFFCORE_RESPONSE */
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= 0x1b7,	/* OFFCORE_RESPONSE */
+			[C(RESULT_MISS)]	= 0x1b7,	/* OFFCORE_RESPONSE */
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= 0x0,
+			[C(RESULT_MISS)]	= 0x0,
+		},
+	},
+	[C(DTLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x81d0,	/* MEM_UOPS_RETIRED.ALL_LOADS */
+			[C(RESULT_MISS)]	= 0xe08,	/* DTLB_LOAD_MISSES.WALK_COMPLETED */
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= 0x82d0,	/* MEM_UOPS_RETIRED.ALL_STORES */
+			[C(RESULT_MISS)]	= 0xe49,	/* DTLB_STORE_MISSES.WALK_COMPLETED */
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= 0x0,
+			[C(RESULT_MISS)]	= 0x0,
+		},
+	},
+	[C(ITLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x00c0,	/* INST_RETIRED.ANY_P */
+			[C(RESULT_MISS)]	= 0x0481,	/* ITLB.MISS */
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= -1,
+			[C(RESULT_MISS)]	= -1,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= -1,
+			[C(RESULT_MISS)]	= -1,
+		},
+	},
+	[C(BPU)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x00c4,	/* BR_INST_RETIRED.ALL_BRANCHES */
+			[C(RESULT_MISS)]	= 0x00c5,	/* BR_MISP_RETIRED.ALL_BRANCHES */
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= -1,
+			[C(RESULT_MISS)]	= -1,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= -1,
+			[C(RESULT_MISS)]	= -1,
+		},
+	},
+};
+
+static __initconst const u64 glp_hw_cache_extra_regs
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(LL)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= GLM_DEMAND_READ|
+						  GLM_LLC_ACCESS,
+			[C(RESULT_MISS)]	= GLM_DEMAND_READ|
+						  GLM_LLC_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= GLM_DEMAND_WRITE|
+						  GLM_LLC_ACCESS,
+			[C(RESULT_MISS)]	= GLM_DEMAND_WRITE|
+						  GLM_LLC_MISS,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= 0x0,
+			[C(RESULT_MISS)]	= 0x0,
+		},
+	},
+};
+
 #define KNL_OT_L2_HITE		BIT_ULL(19) /* Other Tile L2 Hit */
 #define KNL_OT_L2_HITF		BIT_ULL(20) /* Other Tile L2 Hit */
 #define KNL_MCDRAM_LOCAL	BIT_ULL(21)

@@ -3016,6 +3130,9 @@ static int hsw_hw_config(struct perf_event *event)
 	return 0;
 }
 
+static struct event_constraint counter0_constraint =
+			INTEL_ALL_EVENT_CONSTRAINT(0, 0x1);
+
 static struct event_constraint counter2_constraint =
 			EVENT_CONSTRAINT(0, 0x4, 0);
 

@@ -3037,6 +3154,21 @@ hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 	return c;
 }
 
+static struct event_constraint *
+glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
+			  struct perf_event *event)
+{
+	struct event_constraint *c;
+
+	/* :ppp means to do reduced skid PEBS which is PMC0 only. */
+	if (event->attr.precise_ip == 3)
+		return &counter0_constraint;
+
+	c = intel_get_event_constraints(cpuc, idx, event);
+
+	return c;
+}
+
 /*
  * Broadwell:
  *

@@ -3265,10 +3397,8 @@ static void intel_pmu_cpu_dying(int cpu)
 static void intel_pmu_sched_task(struct perf_event_context *ctx,
 				 bool sched_in)
 {
-	if (x86_pmu.pebs_active)
-		intel_pmu_pebs_sched_task(ctx, sched_in);
-	if (x86_pmu.lbr_nr)
-		intel_pmu_lbr_sched_task(ctx, sched_in);
+	intel_pmu_pebs_sched_task(ctx, sched_in);
+	intel_pmu_lbr_sched_task(ctx, sched_in);
 }
 
 PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");

@@ -3838,6 +3968,32 @@ __init int intel_pmu_init(void)
 		pr_cont("Goldmont events, ");
 		break;
 
+	case INTEL_FAM6_ATOM_GEMINI_LAKE:
+		memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
+		       sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, glp_hw_cache_extra_regs,
+		       sizeof(hw_cache_extra_regs));
+
+		intel_pmu_lbr_init_skl();
+
+		x86_pmu.event_constraints = intel_slm_event_constraints;
+		x86_pmu.pebs_constraints = intel_glp_pebs_event_constraints;
+		x86_pmu.extra_regs = intel_glm_extra_regs;
+		/*
+		 * It's recommended to use CPU_CLK_UNHALTED.CORE_P + NPEBS
+		 * for precise cycles.
+		 */
+		x86_pmu.pebs_aliases = NULL;
+		x86_pmu.pebs_prec_dist = true;
+		x86_pmu.lbr_pt_coexist = true;
+		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+		x86_pmu.get_event_constraints = glp_get_event_constraints;
+		x86_pmu.cpu_events = glm_events_attrs;
+		/* Goldmont Plus has 4-wide pipeline */
+		event_attr_td_total_slots_scale_glm.event_str = "4";
+		pr_cont("Goldmont plus events, ");
+		break;
+
 	case INTEL_FAM6_WESTMERE:
 	case INTEL_FAM6_WESTMERE_EP:
 	case INTEL_FAM6_WESTMERE_EX:

index 238ae3248ba5..4cf100ff2a37 100644
@@ -40,16 +40,16 @@
  * Model specific counters:
  *	MSR_CORE_C1_RES: CORE C1 Residency Counter
  *			 perf code: 0x00
- *			 Available model: SLM,AMT
+ *			 Available model: SLM,AMT,GLM
  *			 Scope: Core (each processor core has a MSR)
  *	MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
  *			       perf code: 0x01
- *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL
+ *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,GLM
  *			       Scope: Core
  *	MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW
- *						SKL,KNL
+ *						SKL,KNL,GLM
  *			       Scope: Core
  *	MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
  *			       perf code: 0x03

@@ -57,16 +57,17 @@
  *			       Scope: Core
  *	MSR_PKG_C2_RESIDENCY:  Package C2 Residency Counter.
  *			       perf code: 0x00
- *			       Available model: SNB,IVB,HSW,BDW,SKL,KNL
+ *			       Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM
  *			       Scope: Package (physical package)
  *	MSR_PKG_C3_RESIDENCY:  Package C3 Residency Counter.
  *			       perf code: 0x01
  *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL
+ *						GLM
  *			       Scope: Package (physical package)
  *	MSR_PKG_C6_RESIDENCY:  Package C6 Residency Counter.
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW
- *						SKL,KNL
+ *						SKL,KNL,GLM
  *			       Scope: Package (physical package)
  *	MSR_PKG_C7_RESIDENCY:  Package C7 Residency Counter.
  *			       perf code: 0x03

@@ -82,7 +83,7 @@
  *			       Scope: Package (physical package)
  *	MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
  *			       perf code: 0x06
- *			       Available model: HSW ULT only
+ *			       Available model: HSW ULT, GLM
  *			       Scope: Package (physical package)
  *
  */

@@ -504,6 +505,17 @@ static const struct cstate_model knl_cstates __initconst = {
 };
 
 
+static const struct cstate_model glm_cstates __initconst = {
+	.core_events		= BIT(PERF_CSTATE_CORE_C1_RES) |
+				  BIT(PERF_CSTATE_CORE_C3_RES) |
+				  BIT(PERF_CSTATE_CORE_C6_RES),
+
+	.pkg_events		= BIT(PERF_CSTATE_PKG_C2_RES) |
+				  BIT(PERF_CSTATE_PKG_C3_RES) |
+				  BIT(PERF_CSTATE_PKG_C6_RES) |
+				  BIT(PERF_CSTATE_PKG_C10_RES),
+};
+
 
 #define X86_CSTATES_MODEL(model, states)				\
 	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long) &(states) }

@@ -546,6 +558,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 
 	X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates),
+
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT, glm_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);

index c6d23ffe422d..a322fed5f8ed 100644
@@ -606,12 +606,6 @@ static inline void intel_pmu_drain_pebs_buffer(void)
 	x86_pmu.drain_pebs(&regs);
 }
 
-void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in)
-{
-	if (!sched_in)
-		intel_pmu_drain_pebs_buffer();
-}
-
 /*
  * PEBS
  */

@@ -651,6 +645,12 @@ struct event_constraint intel_glm_pebs_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
+struct event_constraint intel_glp_pebs_event_constraints[] = {
+	/* Allow all events as PEBS with no flags */
+	INTEL_ALL_EVENT_CONSTRAINT(0, 0xf),
+	EVENT_CONSTRAINT_END
+};
+
 struct event_constraint intel_nehalem_pebs_event_constraints[] = {
 	INTEL_PLD_CONSTRAINT(0x100b, 0xf),      /* MEM_INST_RETIRED.* */
 	INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf),    /* MEM_UNCORE_RETIRED.* */

@@ -816,6 +816,14 @@ static inline bool pebs_needs_sched_cb(struct cpu_hw_events *cpuc)
 	return cpuc->n_pebs && (cpuc->n_pebs == cpuc->n_large_pebs);
 }
 
+void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	if (!sched_in && pebs_needs_sched_cb(cpuc))
+		intel_pmu_drain_pebs_buffer();
+}
+
 static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
 {
 	struct debug_store *ds = cpuc->ds;

@@ -889,6 +897,8 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
 		ds->pebs_event_reset[hwc->idx] =
 			(u64)(-hwc->sample_period) & x86_pmu.cntval_mask;
+	} else {
+		ds->pebs_event_reset[hwc->idx] = 0;
 	}
 }
 

index eb261656a320..955457a30197 100644
@@ -380,8 +380,12 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 
 void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
 {
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct x86_perf_task_context *task_ctx;
 
+	if (!cpuc->lbr_users)
+		return;
+
 	/*
 	 * If LBR callstack feature is enabled and the stack was saved when
 	 * the task was scheduled out, restore the stack. Otherwise flush

index 53728eea1bed..476aec3a4cab 100644
@@ -879,6 +879,8 @@ extern struct event_constraint intel_slm_pebs_event_constraints[];
 
 extern struct event_constraint intel_glm_pebs_event_constraints[];
 
+extern struct event_constraint intel_glp_pebs_event_constraints[];
+
 extern struct event_constraint intel_nehalem_pebs_event_constraints[];
 
 extern struct event_constraint intel_westmere_pebs_event_constraints[];

index 4d2c32f98482..c17c0881fd36 100644
@@ -1452,6 +1452,13 @@ static enum event_type_t get_event_type(struct perf_event *event)
 
 	lockdep_assert_held(&ctx->lock);
 
+	/*
+	 * It's 'group type', really, because if our group leader is
+	 * pinned, so are we.
+	 */
+	if (event->group_leader != event)
+		event = event->group_leader;
+
 	event_type = event->attr.pinned ? EVENT_PINNED : EVENT_FLEXIBLE;
 	if (!ctx->task)
 		event_type |= EVENT_CPU;

@@ -4365,7 +4372,9 @@ EXPORT_SYMBOL_GPL(perf_event_read_value);
 static int __perf_read_group_add(struct perf_event *leader,
 					u64 read_format, u64 *values)
 {
+	struct perf_event_context *ctx = leader->ctx;
 	struct perf_event *sub;
+	unsigned long flags;
 	int n = 1; /* skip @nr */
 	int ret;
 

@@ -4395,12 +4404,15 @@ static int __perf_read_group_add(struct perf_event *leader,
 	if (read_format & PERF_FORMAT_ID)
 		values[n++] = primary_event_id(leader);
 
+	raw_spin_lock_irqsave(&ctx->lock, flags);
+
 	list_for_each_entry(sub, &leader->sibling_list, group_entry) {
 		values[n++] += perf_event_count(sub);
 		if (read_format & PERF_FORMAT_ID)
 			values[n++] = primary_event_id(sub);
 	}
 
+	raw_spin_unlock_irqrestore(&ctx->lock, flags);
 	return 0;
 }
 

@@ -7308,21 +7320,6 @@ int perf_event_account_interrupt(struct perf_event *event)
 	return __perf_event_account_interrupt(event, 1);
 }
 
-static bool sample_is_allowed(struct perf_event *event, struct pt_regs *regs)
-{
-	/*
-	 * Due to interrupt latency (AKA "skid"), we may enter the
-	 * kernel before taking an overflow, even if the PMU is only
-	 * counting user events.
-	 * To avoid leaking information to userspace, we must always
-	 * reject kernel samples when exclude_kernel is set.
-	 */
-	if (event->attr.exclude_kernel && !user_mode(regs))
-		return false;
-
-	return true;
-}
-
 /*
  * Generic event overflow handling, sampling.
  */

@@ -7344,12 +7341,6 @@ static int __perf_event_overflow(struct perf_event *event,
 	ret = __perf_event_account_interrupt(event, throttle);
 
 	/*
-	 * For security, drop the skid kernel samples if necessary.
-	 */
-	if (!sample_is_allowed(event, regs))
-		return ret;
-
-	/*
 	 * XXX event_limit might not quite work as expected on inherited
 	 * events
 	 */

index a4d3762cd825..83874b0e266c 100644
@@ -704,7 +704,7 @@ static void __ui_browser__line_arrow_down(struct ui_browser *browser,
 		ui_browser__gotorc(browser, row, column + 1);
 		SLsmg_draw_hline(2);
 
-		if (row++ == 0)
+		if (++row == 0)
 			goto out;
 	} else
 		row = 0;

index 87b431886670..413f74df08de 100644
@@ -273,7 +273,7 @@ struct perf_evsel *perf_evsel__new_cycles(void)
 	struct perf_event_attr attr = {
 		.type	= PERF_TYPE_HARDWARE,
 		.config	= PERF_COUNT_HW_CPU_CYCLES,
-		.exclude_kernel	= 1,
+		.exclude_kernel	= geteuid() != 0,
 	};
 	struct perf_evsel *evsel;
 

@@ -298,8 +298,10 @@ struct perf_evsel *perf_evsel__new_cycles(void)
 		goto out;
 
 	/* use asprintf() because free(evsel) assumes name is allocated */
-	if (asprintf(&evsel->name, "cycles%.*s",
-		     attr.precise_ip ? attr.precise_ip + 1 : 0, ":ppp") < 0)
+	if (asprintf(&evsel->name, "cycles%s%s%.*s",
+		     (attr.precise_ip || attr.exclude_kernel) ? ":" : "",
+		     attr.exclude_kernel ? "u" : "",
+		     attr.precise_ip ? attr.precise_ip + 1 : 0, "ppp") < 0)
 		goto error_free;
 out:
 	return evsel;

index 5de2b86b9880..2e9eb6aa3ce2 100644
@@ -2209,7 +2209,7 @@ int machine__get_kernel_start(struct machine *machine)
 	machine->kernel_start = 1ULL << 63;
 	if (map) {
 		err = map__load(map);
-		if (map->start)
+		if (!err)
 			machine->kernel_start = map->start;
 	}
 	return err;