[PATCH v5][RESEND] perf, x86: Fix multi-segment problem of perf_event_intel_uncore

[Taku Izumi]

In multi-segment system, uncore devices may belong to buses whose segment
number is other than 0.

  ....
  0000:ff:10.5 System peripheral: Intel Corporation Xeon E5 v3/Core i7 Scratchpad & Semaphore Registers (rev 03)
  ...
  0001:7f:10.5 System peripheral: Intel Corporation Xeon E5 v3/Core i7 Scratchpad & Semaphore Registers (rev 03)
  ...
  0001:bf:10.5 System peripheral: Intel Corporation Xeon E5 v3/Core i7 Scratchpad & Semaphore Registers (rev 03)
  ...
  0001:ff:10.5 System peripheral: Intel Corporation Xeon E5 v3/Core i7 Scratchpad & Semaphore Registers (rev 03
  ...

In that case, relation of bus number and physical id may be broken
because "uncore_pcibus_to_physid" doesn't take account of PCI segment.
For example, bus 0000:ff and 0001:ff uses the same entry of
"uncore_pcibus_to_physid" array.

This patch fixes ths problem by introducing segment-aware pci2phy_map instead.

 v4 -> v5:
   - Add initializaton code of pci2phy_map when newly alloced at __find_pci2phy_map()

 v3 -> v4:
   - avoid GFP_ATOMIC allocation at __find_pci2phy_map()
   - Add missing pci_dev_put at snb_pci2phy_map_init()
   - Add missing raw_spin_unlock at snbep_pci2phy_map_init()

Signed-off-by: Taku Izumi <izumi.taku@xxxxxxxxxxxxxx>
---
 arch/x86/kernel/cpu/perf_event_intel_uncore.c      | 61 ++++++++++++++++++++--
 arch/x86/kernel/cpu/perf_event_intel_uncore.h      | 12 ++++-
 arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c  | 16 ++++--
 .../x86/kernel/cpu/perf_event_intel_uncore_snbep.c | 32 +++++++++---
 4 files changed, 106 insertions(+), 15 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 560e525..61215a6 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -7,7 +7,8 @@ struct intel_uncore_type **uncore_pci_uncores = empty_uncore;
 static bool pcidrv_registered;
 struct pci_driver *uncore_pci_driver;
 /* pci bus to socket mapping */
-int uncore_pcibus_to_physid[256] = { [0 ... 255] = -1, };
+DEFINE_RAW_SPINLOCK(pci2phy_map_lock);
+struct list_head pci2phy_map_head = LIST_HEAD_INIT(pci2phy_map_head);
 struct pci_dev *uncore_extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX];
 
 static DEFINE_RAW_SPINLOCK(uncore_box_lock);
@@ -20,6 +21,59 @@ static struct event_constraint uncore_constraint_fixed =
 struct event_constraint uncore_constraint_empty =
 	EVENT_CONSTRAINT(0, 0, 0);
 
+int uncore_pcibus_to_physid(struct pci_bus *bus)
+{
+	struct pci2phy_map *map;
+	int phys_id = -1;
+
+	raw_spin_lock(&pci2phy_map_lock);
+	list_for_each_entry(map, &pci2phy_map_head, list) {
+		if (map->segment == pci_domain_nr(bus)) {
+			phys_id = map->pbus_to_physid[bus->number];
+			break;
+		}
+	}
+	raw_spin_unlock(&pci2phy_map_lock);
+
+	return phys_id;
+}
+
+struct pci2phy_map *__find_pci2phy_map(int segment)
+{
+	struct pci2phy_map *map, *alloc = NULL;
+	int i;
+
+	lockdep_assert_held(&pci2phy_map_lock);
+
+lookup:
+	list_for_each_entry(map, &pci2phy_map_head, list) {
+		if (map->segment == segment)
+			goto end;
+	}
+
+	if (!alloc) {
+		raw_spin_unlock(&pci2phy_map_lock);
+		alloc = kmalloc(sizeof(struct pci2phy_map), GFP_KERNEL);
+		raw_spin_lock(&pci2phy_map_lock);
+
+		if (!alloc)
+			return NULL;
+
+		goto lookup;
+	}
+
+	map = alloc;
+	alloc = NULL;
+	map->segment = segment;
+	for (i = 0; i < 256; i++)
+		map->pbus_to_physid[i] = -1;
+	list_add_tail(&map->list, &pci2phy_map_head);
+
+end:
+	kfree(alloc);
+	return map;
+}
+
 ssize_t uncore_event_show(struct kobject *kobj,
 			  struct kobj_attribute *attr, char *buf)
 {
@@ -809,7 +863,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
 	int phys_id;
 	bool first_box = false;
 
-	phys_id = uncore_pcibus_to_physid[pdev->bus->number];
+	phys_id = uncore_pcibus_to_physid(pdev->bus);
 	if (phys_id < 0)
 		return -ENODEV;
 
@@ -856,9 +910,10 @@ static void uncore_pci_remove(struct pci_dev *pdev)
 {
 	struct intel_uncore_box *box = pci_get_drvdata(pdev);
 	struct intel_uncore_pmu *pmu;
-	int i, cpu, phys_id = uncore_pcibus_to_physid[pdev->bus->number];
+	int i, cpu, phys_id;
 	bool last_box = false;
 
+	phys_id = uncore_pcibus_to_physid(pdev->bus);
 	box = pci_get_drvdata(pdev);
 	if (!box) {
 		for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) {
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 72c54c2..2f0a4a9 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -117,6 +117,15 @@ struct uncore_event_desc {
 	const char *config;
 };
 
+struct pci2phy_map {
+	struct list_head list;
+	int segment;
+	int pbus_to_physid[256];
+};
+
+int uncore_pcibus_to_physid(struct pci_bus *bus);
+struct pci2phy_map *__find_pci2phy_map(int segment);
+
 ssize_t uncore_event_show(struct kobject *kobj,
 			  struct kobj_attribute *attr, char *buf);
 
@@ -317,7 +326,8 @@ u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx);
 extern struct intel_uncore_type **uncore_msr_uncores;
 extern struct intel_uncore_type **uncore_pci_uncores;
 extern struct pci_driver *uncore_pci_driver;
-extern int uncore_pcibus_to_physid[256];
+extern raw_spinlock_t pci2phy_map_lock;
+extern struct list_head pci2phy_map_head;
 extern struct pci_dev *uncore_extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX];
 extern struct event_constraint uncore_constraint_empty;
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
index f78574b..8452561 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
@@ -420,15 +420,25 @@ static void snb_uncore_imc_event_del(struct perf_event *event, int flags)
 static int snb_pci2phy_map_init(int devid)
 {
 	struct pci_dev *dev = NULL;
-	int bus;
+	struct pci2phy_map *map;
+	int bus, segment;
 
 	dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, dev);
 	if (!dev)
 		return -ENOTTY;
 
 	bus = dev->bus->number;
-
-	uncore_pcibus_to_physid[bus] = 0;
+	segment = pci_domain_nr(dev->bus);
+
+	raw_spin_lock(&pci2phy_map_lock);
+	map = __find_pci2phy_map(segment);
+	if (!map) {
+		raw_spin_unlock(&pci2phy_map_lock);
+		pci_dev_put(dev);
+		return -ENOMEM;
+	}
+	map->pbus_to_physid[bus] = 0;
+	raw_spin_unlock(&pci2phy_map_lock);
 
 	pci_dev_put(dev);
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
index 694510a8..97a2ac9 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
@@ -1087,7 +1087,8 @@ static struct pci_driver snbep_uncore_pci_driver = {
 static int snbep_pci2phy_map_init(int devid)
 {
 	struct pci_dev *ubox_dev = NULL;
-	int i, bus, nodeid;
+	int i, bus, nodeid, segment;
+	struct pci2phy_map *map;
 	int err = 0;
 	u32 config = 0;
 
@@ -1106,16 +1107,27 @@ static int snbep_pci2phy_map_init(int devid)
 		err = pci_read_config_dword(ubox_dev, 0x54, &config);
 		if (err)
 			break;
+
+		segment = pci_domain_nr(ubox_dev->bus);
+		raw_spin_lock(&pci2phy_map_lock);
+		map = __find_pci2phy_map(segment);
+		if (!map) {
+			raw_spin_unlock(&pci2phy_map_lock);
+			err = -ENOMEM;
+			break;
+		}
+
 		/*
 		 * every three bits in the Node ID mapping register maps
 		 * to a particular node.
 		 */
 		for (i = 0; i < 8; i++) {
 			if (nodeid == ((config >> (3 * i)) & 0x7)) {
-				uncore_pcibus_to_physid[bus] = i;
+				map->pbus_to_physid[bus] = i;
 				break;
 			}
 		}
+		raw_spin_unlock(&pci2phy_map_lock);
 	}
 
 	if (!err) {
@@ -1123,13 +1135,17 @@ static int snbep_pci2phy_map_init(int devid)
 		 * For PCI bus with no UBOX device, find the next bus
 		 * that has UBOX device and use its mapping.
 		 */
-		i = -1;
-		for (bus = 255; bus >= 0; bus--) {
-			if (uncore_pcibus_to_physid[bus] >= 0)
-				i = uncore_pcibus_to_physid[bus];
-			else
-				uncore_pcibus_to_physid[bus] = i;
+		raw_spin_lock(&pci2phy_map_lock);
+		list_for_each_entry(map, &pci2phy_map_head, list) {
+			i = -1;
+			for (bus = 255; bus >= 0; bus--) {
+				if (map->pbus_to_physid[bus] >= 0)
+					i = map->pbus_to_physid[bus];
+				else
+					map->pbus_to_physid[bus] = i;
+			}
 		}
+		raw_spin_unlock(&pci2phy_map_lock);
 	}
 
 	pci_dev_put(ubox_dev);
-- 
1.8.3.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/