Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf: Fix loss of notification with multi-event
  perf, x86: Force IBS LVT offset assignment for family 10h
  perf, x86: Disable PEBS on SandyBridge chips
  trace_events_filter: Use rcu_assign_pointer() when setting ftrace_event_call->filter
  perf session: Fix crash with invalid CPU list
  perf python: Fix undefined symbol problem
  perf/x86: Enable raw event access to Intel offcore events
  perf: Don't use -ENOSPC for out of PMU resources
  perf: Do not set task_ctx pointer in cpuctx if there are no events in the context
  perf/x86: Fix PEBS instruction unwind
  oprofile, x86: Fix crash when unloading module (nmi timer mode)
  oprofile: Fix crash when unloading module (hr timer mode)

8 files changed, 50 insertions, 32 deletions

diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index c475379199b1..8e9c98edc068 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -353,15 +353,15 @@ validate_group(struct perf_event *event)
 	fake_pmu.used_mask = fake_used_mask;
 
 	if (!validate_event(&fake_pmu, leader))
-		return -ENOSPC;
+		return -EINVAL;
 
 	list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
 		if (!validate_event(&fake_pmu, sibling))
-			return -ENOSPC;
+			return -EINVAL;
 	}
 
 	if (!validate_event(&fake_pmu, event))
-		return -ENOSPC;
+		return -EINVAL;
 
 	return 0;
 }
diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c
index 4f2971bcf8e5..315fc0b250f8 100644
--- a/arch/mips/kernel/perf_event_mipsxx.c
+++ b/arch/mips/kernel/perf_event_mipsxx.c
@@ -623,7 +623,7 @@ static int mipspmu_event_init(struct perf_event *event)
 	if (!atomic_inc_not_zero(&active_events)) {
 		if (atomic_read(&active_events) > MIPS_MAX_HWEVENTS) {
 			atomic_dec(&active_events);
-			return -ENOSPC;
+			return -EINVAL;
 		}
 
 		mutex_lock(&pmu_reserve_mutex);
@@ -732,15 +732,15 @@ static int validate_group(struct perf_event *event)
 	memset(&fake_cpuc, 0, sizeof(fake_cpuc));
 
 	if (!validate_event(&fake_cpuc, leader))
-		return -ENOSPC;
+		return -EINVAL;
 
 	list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
 		if (!validate_event(&fake_cpuc, sibling))
-			return -ENOSPC;
+			return -EINVAL;
 	}
 
 	if (!validate_event(&fake_cpuc, event))
-		return -ENOSPC;
+		return -EINVAL;
 
 	return 0;
 }
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 640891014b2a..2bda212a0010 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -312,12 +312,8 @@ int x86_setup_perfctr(struct perf_event *event)
 			return -EOPNOTSUPP;
 	}
 
-	/*
-	 * Do not allow config1 (extended registers) to propagate,
-	 * there's no sane user-space generalization yet:
-	 */
 	if (attr->type == PERF_TYPE_RAW)
-		return 0;
+		return x86_pmu_extra_regs(event->attr.config, event);
 
 	if (attr->type == PERF_TYPE_HW_CACHE)
 		return set_ext_hw_attr(hwc, event);
@@ -588,7 +584,7 @@ done:
 				x86_pmu.put_event_constraints(cpuc, cpuc->event_list[i]);
 		}
 	}
-	return num ? -ENOSPC : 0;
+	return num ? -EINVAL : 0;
 }
 
 /*
@@ -607,7 +603,7 @@ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader,
 
 	if (is_x86_event(leader)) {
 		if (n >= max_count)
-			return -ENOSPC;
+			return -EINVAL;
 		cpuc->event_list[n] = leader;
 		n++;
 	}
@@ -620,7 +616,7 @@ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader,
 			continue;
 
 		if (n >= max_count)
-			return -ENOSPC;
+			return -EINVAL;
 
 		cpuc->event_list[n] = event;
 		n++;
@@ -1316,7 +1312,7 @@ static int validate_event(struct perf_event *event)
 	c = x86_pmu.get_event_constraints(fake_cpuc, event);
 
 	if (!c || !c->weight)
-		ret = -ENOSPC;
+		ret = -EINVAL;
 
 	if (x86_pmu.put_event_constraints)
 		x86_pmu.put_event_constraints(fake_cpuc, event);
@@ -1341,7 +1337,7 @@ static int validate_group(struct perf_event *event)
 {
 	struct perf_event *leader = event->group_leader;
 	struct cpu_hw_events *fake_cpuc;
-	int ret = -ENOSPC, n;
+	int ret = -EINVAL, n;
 
 	fake_cpuc = allocate_fake_cpuc();
 	if (IS_ERR(fake_cpuc))
diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
index ab6343d21825..3b8a2d30d14e 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -199,8 +199,7 @@ static int force_ibs_eilvt_setup(void)
 		goto out;
 	}
 
-	pr_err(FW_BUG "using offset %d for IBS interrupts\n", offset);
-	pr_err(FW_BUG "workaround enabled for IBS LVT offset\n");
+	pr_info("IBS: LVT offset %d assigned\n", offset);
 
 	return 0;
 out:
@@ -265,19 +264,23 @@ perf_ibs_cpu_notifier(struct notifier_block *self, unsigned long action, void *h
 static __init int amd_ibs_init(void)
 {
 	u32 caps;
-	int ret;
+	int ret = -EINVAL;
 
 	caps = __get_ibs_caps();
 	if (!caps)
 		return -ENODEV;	/* ibs not supported by the cpu */
 
-	if (!ibs_eilvt_valid()) {
-		ret = force_ibs_eilvt_setup();
-		if (ret) {
-			pr_err("Failed to setup IBS, %d\n", ret);
-			return ret;
-		}
-	}
+	/*
+	 * Force LVT offset assignment for family 10h: The offsets are
+	 * not assigned by the BIOS for this family, so the OS is
+	 * responsible for doing it. If the OS assignment fails, fall
+	 * back to BIOS settings and try to setup this.
+	 */
+	if (boot_cpu_data.x86 == 0x10)
+		force_ibs_eilvt_setup();
+
+	if (!ibs_eilvt_valid())
+		goto out;
 
 	get_online_cpus();
 	ibs_caps = caps;
@@ -287,7 +290,11 @@ static __init int amd_ibs_init(void)
 	smp_call_function(setup_APIC_ibs, NULL, 1);
 	put_online_cpus();
 
-	return perf_event_ibs_init();
+	ret = perf_event_ibs_init();
+out:
+	if (ret)
+		pr_err("Failed to setup IBS, %d\n", ret);
+	return ret;
 }
 
 /* Since we need the pci subsystem to init ibs we can't do this earlier: */
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 2be5ebe99872..8d601b18bf9f 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1545,6 +1545,13 @@ static void intel_clovertown_quirks(void)
 	x86_pmu.pebs_constraints = NULL;
 }
 
+static void intel_sandybridge_quirks(void)
+{
+	printk(KERN_WARNING "PEBS disabled due to CPU errata.\n");
+	x86_pmu.pebs = 0;
+	x86_pmu.pebs_constraints = NULL;
+}
+
 __init int intel_pmu_init(void)
 {
 	union cpuid10_edx edx;
@@ -1694,6 +1701,7 @@ __init int intel_pmu_init(void)
 		break;
 
 	case 42: /* SandyBridge */
+		x86_pmu.quirks = intel_sandybridge_quirks;
 	case 45: /* SandyBridge, "Romely-EP" */
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index c0d238f49db8..73da6b64f5b7 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -493,6 +493,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
 	unsigned long from = cpuc->lbr_entries[0].from;
 	unsigned long old_to, to = cpuc->lbr_entries[0].to;
 	unsigned long ip = regs->ip;
+	int is_64bit = 0;
 
 	/*
 	 * We don't need to fixup if the PEBS assist is fault like
@@ -544,7 +545,10 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
 		} else
 			kaddr = (void *)to;
 
-		kernel_insn_init(&insn, kaddr);
+#ifdef CONFIG_X86_64
+		is_64bit = kernel_ip(to) || !test_thread_flag(TIF_IA32);
+#endif
+		insn_init(&insn, kaddr, is_64bit);
 		insn_get_length(&insn);
 		to += insn.length;
 	} while (to < ip);
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 492bf1358a7c..ef484d9d0a25 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -1268,7 +1268,7 @@ reserve:
 	}
 
 done:
-	return num ? -ENOSPC : 0;
+	return num ? -EINVAL : 0;
 }
 
 static __initconst const struct x86_pmu p4_pmu = {
diff --git a/arch/x86/oprofile/init.c b/arch/x86/oprofile/init.c
index cdfe4c54deca..f148cf652678 100644
--- a/arch/x86/oprofile/init.c
+++ b/arch/x86/oprofile/init.c
@@ -21,6 +21,7 @@ extern int op_nmi_timer_init(struct oprofile_operations *ops);
 extern void op_nmi_exit(void);
 extern void x86_backtrace(struct pt_regs * const regs, unsigned int depth);
 
+static int nmi_timer;
 
 int __init oprofile_arch_init(struct oprofile_operations *ops)
 {
@@ -31,8 +32,9 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 #ifdef CONFIG_X86_LOCAL_APIC
 	ret = op_nmi_init(ops);
 #endif
+	nmi_timer = (ret != 0);
 #ifdef CONFIG_X86_IO_APIC
-	if (ret < 0)
+	if (nmi_timer)
 		ret = op_nmi_timer_init(ops);
 #endif
 	ops->backtrace = x86_backtrace;
@@ -44,6 +46,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 void oprofile_arch_exit(void)
 {
 #ifdef CONFIG_X86_LOCAL_APIC
-	op_nmi_exit();
+	if (!nmi_timer)
+		op_nmi_exit();
 #endif
 }