1 files changed, 101 insertions, 122 deletions

diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index fce74062d981..463dc7a5a6c3 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1,4 +1,7 @@
+#include <linux/module.h>
+
 #include <asm/cpu_device_id.h>
+#include <asm/intel-family.h>
 #include "uncore.h"
 
 static struct intel_uncore_type *empty_uncore[] = { NULL, };
@@ -882,7 +885,7 @@ uncore_types_init(struct intel_uncore_type **types, bool setid)
 static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct intel_uncore_type *type;
-	struct intel_uncore_pmu *pmu;
+	struct intel_uncore_pmu *pmu = NULL;
 	struct intel_uncore_box *box;
 	int phys_id, pkg, ret;
 
@@ -903,20 +906,37 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
 	}
 
 	type = uncore_pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)];
+
 	/*
-	 * for performance monitoring unit with multiple boxes,
-	 * each box has a different function id.
-	 */
-	pmu = &type->pmus[UNCORE_PCI_DEV_IDX(id->driver_data)];
-	/* Knights Landing uses a common PCI device ID for multiple instances of
-	 * an uncore PMU device type. There is only one entry per device type in
-	 * the knl_uncore_pci_ids table inspite of multiple devices present for
-	 * some device types. Hence PCI device idx would be 0 for all devices.
-	 * So increment pmu pointer to point to an unused array element.
+	 * Some platforms, e.g.  Knights Landing, use a common PCI device ID
+	 * for multiple instances of an uncore PMU device type. We should check
+	 * PCI slot and func to indicate the uncore box.
 	 */
-	if (boot_cpu_data.x86_model == 87) {
-		while (pmu->func_id >= 0)
-			pmu++;
+	if (id->driver_data & ~0xffff) {
+		struct pci_driver *pci_drv = pdev->driver;
+		const struct pci_device_id *ids = pci_drv->id_table;
+		unsigned int devfn;
+
+		while (ids && ids->vendor) {
+			if ((ids->vendor == pdev->vendor) &&
+			    (ids->device == pdev->device)) {
+				devfn = PCI_DEVFN(UNCORE_PCI_DEV_DEV(ids->driver_data),
+						  UNCORE_PCI_DEV_FUNC(ids->driver_data));
+				if (devfn == pdev->devfn) {
+					pmu = &type->pmus[UNCORE_PCI_DEV_IDX(ids->driver_data)];
+					break;
+				}
+			}
+			ids++;
+		}
+		if (pmu == NULL)
+			return -ENODEV;
+	} else {
+		/*
+		 * for performance monitoring unit with multiple boxes,
+		 * each box has a different function id.
+		 */
+		pmu = &type->pmus[UNCORE_PCI_DEV_IDX(id->driver_data)];
 	}
 
 	if (WARN_ON_ONCE(pmu->boxes[pkg] != NULL))
@@ -956,7 +976,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
 
 static void uncore_pci_remove(struct pci_dev *pdev)
 {
-	struct intel_uncore_box *box = pci_get_drvdata(pdev);
+	struct intel_uncore_box *box;
 	struct intel_uncore_pmu *pmu;
 	int i, phys_id, pkg;
 
@@ -1034,7 +1054,7 @@ static void uncore_pci_exit(void)
 	}
 }
 
-static void uncore_cpu_dying(int cpu)
+static int uncore_cpu_dying(unsigned int cpu)
 {
 	struct intel_uncore_type *type, **types = uncore_msr_uncores;
 	struct intel_uncore_pmu *pmu;
@@ -1051,16 +1071,19 @@ static void uncore_cpu_dying(int cpu)
 				uncore_box_exit(box);
 		}
 	}
+	return 0;
 }
 
-static void uncore_cpu_starting(int cpu, bool init)
+static int first_init;
+
+static int uncore_cpu_starting(unsigned int cpu)
 {
 	struct intel_uncore_type *type, **types = uncore_msr_uncores;
 	struct intel_uncore_pmu *pmu;
 	struct intel_uncore_box *box;
 	int i, pkg, ncpus = 1;
 
-	if (init) {
+	if (first_init) {
 		/*
 		 * On init we get the number of online cpus in the package
 		 * and set refcount for all of them.
@@ -1081,9 +1104,11 @@ static void uncore_cpu_starting(int cpu, bool init)
 				uncore_box_init(box);
 		}
 	}
+
+	return 0;
 }
 
-static int uncore_cpu_prepare(int cpu)
+static int uncore_cpu_prepare(unsigned int cpu)
 {
 	struct intel_uncore_type *type, **types = uncore_msr_uncores;
 	struct intel_uncore_pmu *pmu;
@@ -1146,13 +1171,13 @@ static void uncore_change_context(struct intel_uncore_type **uncores,
 		uncore_change_type_ctx(*uncores, old_cpu, new_cpu);
 }
 
-static void uncore_event_exit_cpu(int cpu)
+static int uncore_event_cpu_offline(unsigned int cpu)
 {
 	int target;
 
 	/* Check if exiting cpu is used for collecting uncore events */
 	if (!cpumask_test_and_clear_cpu(cpu, &uncore_cpu_mask))
-		return;
+		return 0;
 
 	/* Find a new cpu to collect uncore events */
 	target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
@@ -1165,9 +1190,10 @@ static void uncore_event_exit_cpu(int cpu)
 
 	uncore_change_context(uncore_msr_uncores, cpu, target);
 	uncore_change_context(uncore_pci_uncores, cpu, target);
+	return 0;
 }
 
-static void uncore_event_init_cpu(int cpu)
+static int uncore_event_cpu_online(unsigned int cpu)
 {
 	int target;
 
@@ -1177,50 +1203,15 @@ static void uncore_event_init_cpu(int cpu)
 	 */
 	target = cpumask_any_and(&uncore_cpu_mask, topology_core_cpumask(cpu));
 	if (target < nr_cpu_ids)
-		return;
+		return 0;
 
 	cpumask_set_cpu(cpu, &uncore_cpu_mask);
 
 	uncore_change_context(uncore_msr_uncores, -1, cpu);
 	uncore_change_context(uncore_pci_uncores, -1, cpu);
+	return 0;
 }
 
-static int uncore_cpu_notifier(struct notifier_block *self,
-			       unsigned long action, void *hcpu)
-{
-	unsigned int cpu = (long)hcpu;
-
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_UP_PREPARE:
-		return notifier_from_errno(uncore_cpu_prepare(cpu));
-
-	case CPU_STARTING:
-		uncore_cpu_starting(cpu, false);
-	case CPU_DOWN_FAILED:
-		uncore_event_init_cpu(cpu);
-		break;
-
-	case CPU_UP_CANCELED:
-	case CPU_DYING:
-		uncore_cpu_dying(cpu);
-		break;
-
-	case CPU_DOWN_PREPARE:
-		uncore_event_exit_cpu(cpu);
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block uncore_cpu_nb = {
-	.notifier_call	= uncore_cpu_notifier,
-	/*
-	 * to migrate uncore events, our notifier should be executed
-	 * before perf core's notifier.
-	 */
-	.priority	= CPU_PRI_PERF + 1,
-};
-
 static int __init type_pmu_register(struct intel_uncore_type *type)
 {
 	int i, ret;
@@ -1264,41 +1255,6 @@ err:
 	return ret;
 }
 
-static void __init uncore_cpu_setup(void *dummy)
-{
-	uncore_cpu_starting(smp_processor_id(), true);
-}
-
-/* Lazy to avoid allocation of a few bytes for the normal case */
-static __initdata DECLARE_BITMAP(packages, MAX_LOCAL_APIC);
-
-static int __init uncore_cpumask_init(bool msr)
-{
-	unsigned int cpu;
-
-	for_each_online_cpu(cpu) {
-		unsigned int pkg = topology_logical_package_id(cpu);
-		int ret;
-
-		if (test_and_set_bit(pkg, packages))
-			continue;
-		/*
-		 * The first online cpu of each package allocates and takes
-		 * the refcounts for all other online cpus in that package.
-		 * If msrs are not enabled no allocation is required.
-		 */
-		if (msr) {
-			ret = uncore_cpu_prepare(cpu);
-			if (ret)
-				return ret;
-		}
-		uncore_event_init_cpu(cpu);
-		smp_call_function_single(cpu, uncore_cpu_setup, NULL, 1);
-	}
-	__register_cpu_notifier(&uncore_cpu_nb);
-	return 0;
-}
-
 #define X86_UNCORE_MODEL_MATCH(model, init)	\
 	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&init }
 
@@ -1361,30 +1317,32 @@ static const struct intel_uncore_init_fun knl_uncore_init __initconst = {
 };
 
 static const struct intel_uncore_init_fun skl_uncore_init __initconst = {
+	.cpu_init = skl_uncore_cpu_init,
 	.pci_init = skl_uncore_pci_init,
 };
 
 static const struct x86_cpu_id intel_uncore_match[] __initconst = {
-	X86_UNCORE_MODEL_MATCH(26, nhm_uncore_init),	/* Nehalem */
-	X86_UNCORE_MODEL_MATCH(30, nhm_uncore_init),
-	X86_UNCORE_MODEL_MATCH(37, nhm_uncore_init),	/* Westmere */
-	X86_UNCORE_MODEL_MATCH(44, nhm_uncore_init),
-	X86_UNCORE_MODEL_MATCH(42, snb_uncore_init),	/* Sandy Bridge */
-	X86_UNCORE_MODEL_MATCH(58, ivb_uncore_init),	/* Ivy Bridge */
-	X86_UNCORE_MODEL_MATCH(60, hsw_uncore_init),	/* Haswell */
-	X86_UNCORE_MODEL_MATCH(69, hsw_uncore_init),	/* Haswell Celeron */
-	X86_UNCORE_MODEL_MATCH(70, hsw_uncore_init),	/* Haswell */
-	X86_UNCORE_MODEL_MATCH(61, bdw_uncore_init),	/* Broadwell */
-	X86_UNCORE_MODEL_MATCH(71, bdw_uncore_init),	/* Broadwell */
-	X86_UNCORE_MODEL_MATCH(45, snbep_uncore_init),	/* Sandy Bridge-EP */
-	X86_UNCORE_MODEL_MATCH(46, nhmex_uncore_init),	/* Nehalem-EX */
-	X86_UNCORE_MODEL_MATCH(47, nhmex_uncore_init),	/* Westmere-EX aka. Xeon E7 */
-	X86_UNCORE_MODEL_MATCH(62, ivbep_uncore_init),	/* Ivy Bridge-EP */
-	X86_UNCORE_MODEL_MATCH(63, hswep_uncore_init),	/* Haswell-EP */
-	X86_UNCORE_MODEL_MATCH(79, bdx_uncore_init),	/* BDX-EP */
-	X86_UNCORE_MODEL_MATCH(86, bdx_uncore_init),	/* BDX-DE */
-	X86_UNCORE_MODEL_MATCH(87, knl_uncore_init),	/* Knights Landing */
-	X86_UNCORE_MODEL_MATCH(94, skl_uncore_init),	/* SkyLake */
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM_EP,	  nhm_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM,	  nhm_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_WESTMERE,	  nhm_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_WESTMERE_EP,	  nhm_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE,	  snb_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE,	  ivb_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_CORE,	  hsw_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_ULT,	  hsw_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_GT3E,	  hsw_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_CORE, bdw_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_GT3E, bdw_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE_X,  snbep_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM_EX,	  nhmex_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_WESTMERE_EX,	  nhmex_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X,	  ivbep_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_X,	  hswep_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_X,	  bdx_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, bdx_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL,	  knl_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP,skl_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, skl_uncore_init),
 	{},
 };
 
@@ -1420,11 +1378,33 @@ static int __init intel_uncore_init(void)
 	if (cret && pret)
 		return -ENODEV;
 
-	cpu_notifier_register_begin();
-	ret = uncore_cpumask_init(!cret);
-	if (ret)
-		goto err;
-	cpu_notifier_register_done();
+	/*
+	 * Install callbacks. Core will call them for each online cpu.
+	 *
+	 * The first online cpu of each package allocates and takes
+	 * the refcounts for all other online cpus in that package.
+	 * If msrs are not enabled no allocation is required and
+	 * uncore_cpu_prepare() is not called for each online cpu.
+	 */
+	if (!cret) {
+	       ret = cpuhp_setup_state(CPUHP_PERF_X86_UNCORE_PREP,
+					"PERF_X86_UNCORE_PREP",
+					uncore_cpu_prepare, NULL);
+		if (ret)
+			goto err;
+	} else {
+		cpuhp_setup_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP,
+					  "PERF_X86_UNCORE_PREP",
+					  uncore_cpu_prepare, NULL);
+	}
+	first_init = 1;
+	cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_STARTING,
+			  "AP_PERF_X86_UNCORE_STARTING",
+			  uncore_cpu_starting, uncore_cpu_dying);
+	first_init = 0;
+	cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE,
+			  "AP_PERF_X86_UNCORE_ONLINE",
+			  uncore_event_cpu_online, uncore_event_cpu_offline);
 	return 0;
 
 err:
@@ -1432,17 +1412,16 @@ err:
 	on_each_cpu_mask(&uncore_cpu_mask, uncore_exit_boxes, NULL, 1);
 	uncore_types_exit(uncore_msr_uncores);
 	uncore_pci_exit();
-	cpu_notifier_register_done();
 	return ret;
 }
 module_init(intel_uncore_init);
 
 static void __exit intel_uncore_exit(void)
 {
-	cpu_notifier_register_begin();
-	__unregister_cpu_notifier(&uncore_cpu_nb);
+	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_UNCORE_ONLINE);
+	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_UNCORE_STARTING);
+	cpuhp_remove_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP);
 	uncore_types_exit(uncore_msr_uncores);
 	uncore_pci_exit();
-	cpu_notifier_register_done();
 }
 module_exit(intel_uncore_exit);