| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Fri, 14 Jun 2024 06:46:29 -0700
From: kan.liang@...ux.intel.com
To: peterz@...radead.org,
mingo@...nel.org,
linux-kernel@...r.kernel.org
Cc: acme@...nel.org,
namhyung@...nel.org,
irogers@...gle.com,
eranian@...gle.com,
ak@...ux.intel.com,
yunying.sun@...el.com,
tim.c.chen@...ux.intel.com,
Kan Liang <kan.liang@...ux.intel.com>
Subject: [PATCH V2 6/8] perf/x86/uncore: Apply the unit control RB tree to PCI uncore units
From: Kan Liang <kan.liang@...ux.intel.com>
The unit control RB tree has the unit control and unit ID information
for all the PCI units. Use them to replace the box_ctls/pci_offsets to
get an accurate unit control address for PCI uncore units.
The UPI/M3UPI units in the discovery table are ignored. Please see the
commit 65248a9a9ee1 ("perf/x86/uncore: Add a quirk for UPI on SPR").
Manually allocate a unit control RB tree for UPI/M3UPI.
Add cleanup_extra_boxes to release such manual allocation.
Tested-by: Yunying Sun <yunying.sun@...el.com>
Signed-off-by: Kan Liang <kan.liang@...ux.intel.com>
---
arch/x86/events/intel/uncore.c | 53 +++++++++++-----------
arch/x86/events/intel/uncore.h | 4 ++
arch/x86/events/intel/uncore_discovery.c | 26 ++++++++---
arch/x86/events/intel/uncore_discovery.h | 2 +
arch/x86/events/intel/uncore_snbep.c | 57 ++++++++++++++++++------
5 files changed, 94 insertions(+), 48 deletions(-)
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index f48c7049d2ed..79449c5b9256 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -969,6 +969,9 @@ static void uncore_type_exit(struct intel_uncore_type *type)
if (type->cleanup_mapping)
type->cleanup_mapping(type);
+ if (type->cleanup_extra_boxes)
+ type->cleanup_extra_boxes(type);
+
if (pmu) {
for (i = 0; i < type->num_boxes; i++, pmu++) {
uncore_pmu_unregister(pmu);
@@ -1084,22 +1087,19 @@ static struct intel_uncore_pmu *
uncore_pci_find_dev_pmu_from_types(struct pci_dev *pdev)
{
struct intel_uncore_type **types = uncore_pci_uncores;
+ struct intel_uncore_discovery_unit *unit;
struct intel_uncore_type *type;
- u64 box_ctl;
- int i, die;
+ struct rb_node *node;
for (; *types; types++) {
type = *types;
- for (die = 0; die < __uncore_max_dies; die++) {
- for (i = 0; i < type->num_boxes; i++) {
- if (!type->box_ctls[die])
- continue;
- box_ctl = type->box_ctls[die] + type->pci_offsets[i];
- if (pdev->devfn == UNCORE_DISCOVERY_PCI_DEVFN(box_ctl) &&
- pdev->bus->number == UNCORE_DISCOVERY_PCI_BUS(box_ctl) &&
- pci_domain_nr(pdev->bus) == UNCORE_DISCOVERY_PCI_DOMAIN(box_ctl))
- return &type->pmus[i];
- }
+
+ for (node = rb_first(type->boxes); node; node = rb_next(node)) {
+ unit = rb_entry(node, struct intel_uncore_discovery_unit, node);
+ if (pdev->devfn == UNCORE_DISCOVERY_PCI_DEVFN(unit->addr) &&
+ pdev->bus->number == UNCORE_DISCOVERY_PCI_BUS(unit->addr) &&
+ pci_domain_nr(pdev->bus) == UNCORE_DISCOVERY_PCI_DOMAIN(unit->addr))
+ return &type->pmus[unit->pmu_idx];
}
}
@@ -1375,28 +1375,25 @@ static struct notifier_block uncore_pci_notifier = {
static void uncore_pci_pmus_register(void)
{
struct intel_uncore_type **types = uncore_pci_uncores;
+ struct intel_uncore_discovery_unit *unit;
struct intel_uncore_type *type;
struct intel_uncore_pmu *pmu;
+ struct rb_node *node;
struct pci_dev *pdev;
- u64 box_ctl;
- int i, die;
for (; *types; types++) {
type = *types;
- for (die = 0; die < __uncore_max_dies; die++) {
- for (i = 0; i < type->num_boxes; i++) {
- if (!type->box_ctls[die])
- continue;
- box_ctl = type->box_ctls[die] + type->pci_offsets[i];
- pdev = pci_get_domain_bus_and_slot(UNCORE_DISCOVERY_PCI_DOMAIN(box_ctl),
- UNCORE_DISCOVERY_PCI_BUS(box_ctl),
- UNCORE_DISCOVERY_PCI_DEVFN(box_ctl));
- if (!pdev)
- continue;
- pmu = &type->pmus[i];
-
- uncore_pci_pmu_register(pdev, type, pmu, die);
- }
+
+ for (node = rb_first(type->boxes); node; node = rb_next(node)) {
+ unit = rb_entry(node, struct intel_uncore_discovery_unit, node);
+ pdev = pci_get_domain_bus_and_slot(UNCORE_DISCOVERY_PCI_DOMAIN(unit->addr),
+ UNCORE_DISCOVERY_PCI_BUS(unit->addr),
+ UNCORE_DISCOVERY_PCI_DEVFN(unit->addr));
+
+ if (!pdev)
+ continue;
+ pmu = &type->pmus[unit->pmu_idx];
+ uncore_pci_pmu_register(pdev, type, pmu, unit->die);
}
}
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index 0a49e304fe40..05c429c8cb93 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -99,6 +99,10 @@ struct intel_uncore_type {
int (*get_topology)(struct intel_uncore_type *type);
void (*set_mapping)(struct intel_uncore_type *type);
void (*cleanup_mapping)(struct intel_uncore_type *type);
+ /*
+ * Optional callbacks for extra uncore units cleanup
+ */
+ void (*cleanup_extra_boxes)(struct intel_uncore_type *type);
};
#define pmu_group attr_groups[0]
diff --git a/arch/x86/events/intel/uncore_discovery.c b/arch/x86/events/intel/uncore_discovery.c
index 076ec1efe9cc..866493fda47c 100644
--- a/arch/x86/events/intel/uncore_discovery.c
+++ b/arch/x86/events/intel/uncore_discovery.c
@@ -215,8 +215,8 @@ uncore_find_unit(struct rb_root *root, unsigned int id)
return NULL;
}
-static void uncore_find_add_unit(struct intel_uncore_discovery_unit *node,
- struct rb_root *root, u16 *num_units)
+void uncore_find_add_unit(struct intel_uncore_discovery_unit *node,
+ struct rb_root *root, u16 *num_units)
{
struct intel_uncore_discovery_unit *unit = uncore_find_unit(root, node->id);
@@ -560,7 +560,7 @@ bool intel_generic_uncore_assign_hw_event(struct perf_event *event,
if (!box->pmu->type->boxes)
return false;
- if (box->pci_dev || box->io_addr) {
+ if (box->io_addr) {
hwc->config_base = uncore_pci_event_ctl(box, hwc->idx);
hwc->event_base = uncore_pci_perf_ctr(box, hwc->idx);
return true;
@@ -570,16 +570,28 @@ bool intel_generic_uncore_assign_hw_event(struct perf_event *event,
if (!box_ctl)
return false;
+ if (box->pci_dev) {
+ box_ctl = UNCORE_DISCOVERY_PCI_BOX_CTRL(box_ctl);
+ hwc->config_base = box_ctl + uncore_pci_event_ctl(box, hwc->idx);
+ hwc->event_base = box_ctl + uncore_pci_perf_ctr(box, hwc->idx);
+ return true;
+ }
+
hwc->config_base = box_ctl + box->pmu->type->event_ctl + hwc->idx;
hwc->event_base = box_ctl + box->pmu->type->perf_ctr + hwc->idx;
return true;
}
+static inline int intel_pci_uncore_box_ctl(struct intel_uncore_box *box)
+{
+ return UNCORE_DISCOVERY_PCI_BOX_CTRL(intel_generic_uncore_box_ctl(box));
+}
+
void intel_generic_uncore_pci_init_box(struct intel_uncore_box *box)
{
struct pci_dev *pdev = box->pci_dev;
- int box_ctl = uncore_pci_box_ctl(box);
+ int box_ctl = intel_pci_uncore_box_ctl(box);
__set_bit(UNCORE_BOX_FLAG_CTL_OFFS8, &box->flags);
pci_write_config_dword(pdev, box_ctl, GENERIC_PMON_BOX_CTL_INT);
@@ -588,7 +600,7 @@ void intel_generic_uncore_pci_init_box(struct intel_uncore_box *box)
void intel_generic_uncore_pci_disable_box(struct intel_uncore_box *box)
{
struct pci_dev *pdev = box->pci_dev;
- int box_ctl = uncore_pci_box_ctl(box);
+ int box_ctl = intel_pci_uncore_box_ctl(box);
pci_write_config_dword(pdev, box_ctl, GENERIC_PMON_BOX_CTL_FRZ);
}
@@ -596,7 +608,7 @@ void intel_generic_uncore_pci_disable_box(struct intel_uncore_box *box)
void intel_generic_uncore_pci_enable_box(struct intel_uncore_box *box)
{
struct pci_dev *pdev = box->pci_dev;
- int box_ctl = uncore_pci_box_ctl(box);
+ int box_ctl = intel_pci_uncore_box_ctl(box);
pci_write_config_dword(pdev, box_ctl, 0);
}
@@ -748,6 +760,8 @@ static bool uncore_update_uncore_type(enum uncore_access_type type_id,
uncore->box_ctl = (unsigned int)UNCORE_DISCOVERY_PCI_BOX_CTRL(type->box_ctrl);
uncore->box_ctls = type->box_ctrl_die;
uncore->pci_offsets = type->box_offset;
+ uncore->boxes = &type->units;
+ uncore->num_boxes = type->num_units;
break;
case UNCORE_ACCESS_MMIO:
uncore->ops = &generic_uncore_mmio_ops;
diff --git a/arch/x86/events/intel/uncore_discovery.h b/arch/x86/events/intel/uncore_discovery.h
index 4a7a7c819d6f..0acf9b681f3b 100644
--- a/arch/x86/events/intel/uncore_discovery.h
+++ b/arch/x86/events/intel/uncore_discovery.h
@@ -171,3 +171,5 @@ int intel_uncore_find_discovery_unit_id(struct rb_root *units, int die,
unsigned int pmu_idx);
bool intel_generic_uncore_assign_hw_event(struct perf_event *event,
struct intel_uncore_box *box);
+void uncore_find_add_unit(struct intel_uncore_discovery_unit *node,
+ struct rb_root *root, u16 *num_units);
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index c42b170886d2..fbafc6ea198f 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -6198,6 +6198,24 @@ static u64 spr_upi_pci_offsets[SPR_UNCORE_UPI_NUM_BOXES] = {
0, 0x8000, 0x10000, 0x18000
};
+static void spr_extra_boxes_cleanup(struct intel_uncore_type *type)
+{
+ struct intel_uncore_discovery_unit *pos;
+ struct rb_node *node;
+
+ if (!type->boxes)
+ return;
+
+ while (!RB_EMPTY_ROOT(type->boxes)) {
+ node = rb_first(type->boxes);
+ pos = rb_entry(node, struct intel_uncore_discovery_unit, node);
+ rb_erase(node, type->boxes);
+ kfree(pos);
+ }
+ kfree(type->boxes);
+ type->boxes = NULL;
+}
+
static struct intel_uncore_type spr_uncore_upi = {
.event_mask = SNBEP_PMON_RAW_EVENT_MASK,
.event_mask_ext = SPR_RAW_EVENT_MASK_EXT,
@@ -6212,10 +6230,11 @@ static struct intel_uncore_type spr_uncore_upi = {
.num_counters = 4,
.num_boxes = SPR_UNCORE_UPI_NUM_BOXES,
.perf_ctr_bits = 48,
- .perf_ctr = ICX_UPI_PCI_PMON_CTR0,
- .event_ctl = ICX_UPI_PCI_PMON_CTL0,
+ .perf_ctr = ICX_UPI_PCI_PMON_CTR0 - ICX_UPI_PCI_PMON_BOX_CTL,
+ .event_ctl = ICX_UPI_PCI_PMON_CTL0 - ICX_UPI_PCI_PMON_BOX_CTL,
.box_ctl = ICX_UPI_PCI_PMON_BOX_CTL,
.pci_offsets = spr_upi_pci_offsets,
+ .cleanup_extra_boxes = spr_extra_boxes_cleanup,
};
static struct intel_uncore_type spr_uncore_m3upi = {
@@ -6225,11 +6244,12 @@ static struct intel_uncore_type spr_uncore_m3upi = {
.num_counters = 4,
.num_boxes = SPR_UNCORE_UPI_NUM_BOXES,
.perf_ctr_bits = 48,
- .perf_ctr = ICX_M3UPI_PCI_PMON_CTR0,
- .event_ctl = ICX_M3UPI_PCI_PMON_CTL0,
+ .perf_ctr = ICX_M3UPI_PCI_PMON_CTR0 - ICX_M3UPI_PCI_PMON_BOX_CTL,
+ .event_ctl = ICX_M3UPI_PCI_PMON_CTL0 - ICX_M3UPI_PCI_PMON_BOX_CTL,
.box_ctl = ICX_M3UPI_PCI_PMON_BOX_CTL,
.pci_offsets = spr_upi_pci_offsets,
.constraints = icx_uncore_m3upi_constraints,
+ .cleanup_extra_boxes = spr_extra_boxes_cleanup,
};
enum perf_uncore_spr_iio_freerunning_type_id {
@@ -6516,10 +6536,11 @@ void spr_uncore_cpu_init(void)
static void spr_update_device_location(int type_id)
{
+ struct intel_uncore_discovery_unit *unit;
struct intel_uncore_type *type;
struct pci_dev *dev = NULL;
+ struct rb_root *root;
u32 device, devfn;
- u64 *ctls;
int die;
if (type_id == UNCORE_SPR_UPI) {
@@ -6533,27 +6554,35 @@ static void spr_update_device_location(int type_id)
} else
return;
- ctls = kcalloc(__uncore_max_dies, sizeof(u64), GFP_KERNEL);
- if (!ctls) {
+ root = kzalloc(sizeof(struct rb_root), GFP_KERNEL);
+ if (!root) {
type->num_boxes = 0;
return;
}
+ *root = RB_ROOT;
while ((dev = pci_get_device(PCI_VENDOR_ID_INTEL, device, dev)) != NULL) {
- if (devfn != dev->devfn)
- continue;
die = uncore_device_to_die(dev);
if (die < 0)
continue;
- ctls[die] = pci_domain_nr(dev->bus) << UNCORE_DISCOVERY_PCI_DOMAIN_OFFSET |
- dev->bus->number << UNCORE_DISCOVERY_PCI_BUS_OFFSET |
- devfn << UNCORE_DISCOVERY_PCI_DEVFN_OFFSET |
- type->box_ctl;
+ unit = kzalloc(sizeof(*unit), GFP_KERNEL);
+ if (!unit)
+ continue;
+ unit->die = die;
+ unit->id = PCI_SLOT(dev->devfn) - PCI_SLOT(devfn);
+ unit->addr = pci_domain_nr(dev->bus) << UNCORE_DISCOVERY_PCI_DOMAIN_OFFSET |
+ dev->bus->number << UNCORE_DISCOVERY_PCI_BUS_OFFSET |
+ devfn << UNCORE_DISCOVERY_PCI_DEVFN_OFFSET |
+ type->box_ctl;
+
+ unit->pmu_idx = unit->id;
+
+ uncore_find_add_unit(unit, root, NULL);
}
- type->box_ctls = ctls;
+ type->boxes = root;
}
int spr_uncore_pci_init(void)
--
2.35.1
Powered by blists - more mailing lists