[PATCH 05/16] drm/xe/oa/uapi: Add/remove OA config perf ops
Ashutosh Dixit
ashutosh.dixit at intel.com
Sat Jan 20 02:00:15 UTC 2024
Introduce add/remove config perf ops for OA. OA configurations consist of a
set of event/counter select register address/value pairs. The add_config
perf op validates and stores such configurations and also exposes them in
the metrics sysfs. These configurations will be programmed to OA unit HW
when an OA stream using a configuration is opened. The OA stream can also
switch to other stored configurations.
v2: Start config id's from 1 and other minor review comments (Umesh)
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa at intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit at intel.com>
---
drivers/gpu/drm/xe/xe_device.c | 4 +
drivers/gpu/drm/xe/xe_oa.c | 405 +++++++++++++++++++++++++++++++
drivers/gpu/drm/xe/xe_oa.h | 8 +
drivers/gpu/drm/xe/xe_oa_types.h | 10 +
drivers/gpu/drm/xe/xe_perf.c | 16 ++
include/uapi/drm/xe_drm.h | 25 ++
6 files changed, 468 insertions(+)
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 1c3f3545b5335..46e781983125e 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -549,6 +549,8 @@ int xe_device_probe(struct xe_device *xe)
xe_display_register(xe);
+ xe_oa_register(xe);
+
xe_debugfs_register(xe);
xe_hwmon_register(xe);
@@ -593,6 +595,8 @@ void xe_device_remove(struct xe_device *xe)
struct xe_gt *gt;
u8 id;
+ xe_oa_unregister(xe);
+
xe_device_remove_display(xe);
xe_display_fini(xe);
diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c
index 35a55ad8270f3..73dfe325fc258 100644
--- a/drivers/gpu/drm/xe/xe_oa.c
+++ b/drivers/gpu/drm/xe/xe_oa.c
@@ -10,9 +10,32 @@
#include "xe_gt.h"
#include "xe_mmio.h"
#include "xe_oa.h"
+#include "xe_perf.h"
#define XE_OA_UNIT_INVALID U32_MAX
+struct xe_oa_reg {
+ struct xe_reg addr;
+ u32 value;
+};
+
+struct xe_oa_config {
+ struct xe_oa *oa;
+
+ char uuid[UUID_STRING_LEN + 1];
+ int id;
+
+ const struct xe_oa_reg *regs;
+ u32 regs_len;
+
+ struct attribute_group sysfs_metric;
+ struct attribute *attrs[2];
+ struct kobj_attribute sysfs_metric_id;
+
+ struct kref ref;
+ struct rcu_head rcu;
+};
+
#define DRM_FMT(x) DRM_XE_OA_FMT_TYPE_##x
static const struct xe_oa_format oa_formats[] = {
@@ -37,6 +60,376 @@ static const struct xe_oa_format oa_formats[] = {
[XE_OA_FORMAT_PEC36u64_G1_4_G2_32] = { 4, 320, DRM_FMT(PEC), HDR_64_BIT, 1, 0 },
};
+static void xe_oa_config_release(struct kref *ref)
+{
+ struct xe_oa_config *oa_config =
+ container_of(ref, typeof(*oa_config), ref);
+
+ kfree(oa_config->regs);
+
+ kfree_rcu(oa_config, rcu);
+}
+
+static void xe_oa_config_put(struct xe_oa_config *oa_config)
+{
+ if (!oa_config)
+ return;
+
+ kref_put(&oa_config->ref, xe_oa_config_release);
+}
+
+static bool xe_oa_is_valid_flex_addr(struct xe_oa *oa, u32 addr)
+{
+ static const struct xe_reg flex_eu_regs[] = {
+ EU_PERF_CNTL0,
+ EU_PERF_CNTL1,
+ EU_PERF_CNTL2,
+ EU_PERF_CNTL3,
+ EU_PERF_CNTL4,
+ EU_PERF_CNTL5,
+ EU_PERF_CNTL6,
+ };
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(flex_eu_regs); i++) {
+ if (flex_eu_regs[i].addr == addr)
+ return true;
+ }
+ return false;
+}
+
+static bool xe_oa_reg_in_range_table(u32 addr, const struct xe_mmio_range *table)
+{
+ while (table->start && table->end) {
+ if (addr >= table->start && addr <= table->end)
+ return true;
+
+ table++;
+ }
+
+ return false;
+}
+
+static const struct xe_mmio_range xehp_oa_b_counters[] = {
+ { .start = 0xdc48, .end = 0xdc48 }, /* OAA_ENABLE_REG */
+ { .start = 0xdd00, .end = 0xdd48 }, /* OAG_LCE0_0 - OAA_LENABLE_REG */
+ {}
+};
+
+static const struct xe_mmio_range gen12_oa_b_counters[] = {
+ { .start = 0x2b2c, .end = 0x2b2c }, /* OAG_OA_PESS */
+ { .start = 0xd900, .end = 0xd91c }, /* OAG_OASTARTTRIG[1-8] */
+ { .start = 0xd920, .end = 0xd93c }, /* OAG_OAREPORTTRIG1[1-8] */
+ { .start = 0xd940, .end = 0xd97c }, /* OAG_CEC[0-7][0-1] */
+ { .start = 0xdc00, .end = 0xdc3c }, /* OAG_SCEC[0-7][0-1] */
+ { .start = 0xdc40, .end = 0xdc40 }, /* OAG_SPCTR_CNF */
+ { .start = 0xdc44, .end = 0xdc44 }, /* OAA_DBG_REG */
+ {}
+};
+
+static const struct xe_mmio_range mtl_oam_b_counters[] = {
+ { .start = 0x393000, .end = 0x39301c }, /* OAM_STARTTRIG1[1-8] */
+ { .start = 0x393020, .end = 0x39303c }, /* OAM_REPORTTRIG1[1-8] */
+ { .start = 0x393040, .end = 0x39307c }, /* OAM_CEC[0-7][0-1] */
+ { .start = 0x393200, .end = 0x39323C }, /* MPES[0-7] */
+ {}
+};
+
+static const struct xe_mmio_range xe2_oa_b_counters[] = {
+ { .start = 0x393200, .end = 0x39323C }, /* MPES_0_MPES_SAG - MPES_7_UPPER_MPES_SAG */
+ { .start = 0x394200, .end = 0x39423C }, /* MPES_0_MPES_SCMI0 - MPES_7_UPPER_MPES_SCMI0 */
+ { .start = 0x394A00, .end = 0x394A3C }, /* MPES_0_MPES_SCMI1 - MPES_7_UPPER_MPES_SCMI1 */
+ {},
+};
+
+static bool xe_oa_is_valid_b_counter_addr(struct xe_oa *oa, u32 addr)
+{
+ return xe_oa_reg_in_range_table(addr, xehp_oa_b_counters) ||
+ xe_oa_reg_in_range_table(addr, gen12_oa_b_counters) ||
+ xe_oa_reg_in_range_table(addr, mtl_oam_b_counters) ||
+ (GRAPHICS_VER(oa->xe) >= 20 &&
+ xe_oa_reg_in_range_table(addr, xe2_oa_b_counters));
+}
+
+static const struct xe_mmio_range mtl_oa_mux_regs[] = {
+ { .start = 0x0d00, .end = 0x0d04 }, /* RPM_CONFIG[0-1] */
+ { .start = 0x0d0c, .end = 0x0d2c }, /* NOA_CONFIG[0-8] */
+ { .start = 0x9840, .end = 0x9840 }, /* GDT_CHICKEN_BITS */
+ { .start = 0x9884, .end = 0x9888 }, /* NOA_WRITE */
+ { .start = 0x38d100, .end = 0x38d114}, /* VISACTL */
+ {}
+};
+
+static const struct xe_mmio_range gen12_oa_mux_regs[] = {
+ { .start = 0x0d00, .end = 0x0d04 }, /* RPM_CONFIG[0-1] */
+ { .start = 0x0d0c, .end = 0x0d2c }, /* NOA_CONFIG[0-8] */
+ { .start = 0x9840, .end = 0x9840 }, /* GDT_CHICKEN_BITS */
+ { .start = 0x9884, .end = 0x9888 }, /* NOA_WRITE */
+ { .start = 0x20cc, .end = 0x20cc }, /* WAIT_FOR_RC6_EXIT */
+ {}
+};
+
+static const struct xe_mmio_range xe2_oa_mux_regs[] = {
+ { .start = 0x13000, .end = 0x137FC }, /* PES_0_PESL0 - PES_63_UPPER_PESL3 */
+ {},
+};
+
+static bool xe_oa_is_valid_mux_addr(struct xe_oa *oa, u32 addr)
+{
+ if (GRAPHICS_VER(oa->xe) >= 20)
+ return xe_oa_reg_in_range_table(addr, xe2_oa_mux_regs);
+ else if (GRAPHICS_VERx100(oa->xe) >= 1270)
+ return xe_oa_reg_in_range_table(addr, mtl_oa_mux_regs);
+ else
+ return xe_oa_reg_in_range_table(addr, gen12_oa_mux_regs);
+}
+
+static bool xe_oa_is_valid_config_reg_addr(struct xe_oa *oa, u32 addr)
+{
+ return xe_oa_is_valid_flex_addr(oa, addr) ||
+ xe_oa_is_valid_b_counter_addr(oa, addr) ||
+ xe_oa_is_valid_mux_addr(oa, addr);
+}
+
+static struct xe_oa_reg *
+xe_oa_alloc_regs(struct xe_oa *oa, bool (*is_valid)(struct xe_oa *oa, u32 addr),
+ u32 __user *regs, u32 n_regs)
+{
+ struct xe_oa_reg *oa_regs;
+ int err;
+ u32 i;
+
+ oa_regs = kmalloc_array(n_regs, sizeof(*oa_regs), GFP_KERNEL);
+ if (!oa_regs)
+ return ERR_PTR(-ENOMEM);
+
+ for (i = 0; i < n_regs; i++) {
+ u32 addr, value;
+
+ err = get_user(addr, regs);
+ if (err)
+ goto addr_err;
+
+ if (!is_valid(oa, addr)) {
+ drm_dbg(&oa->xe->drm, "Invalid oa_reg address: %X\n", addr);
+ err = -EINVAL;
+ goto addr_err;
+ }
+
+ err = get_user(value, regs + 1);
+ if (err)
+ goto addr_err;
+
+ oa_regs[i].addr = XE_REG(addr);
+ oa_regs[i].value = value;
+
+ regs += 2;
+ }
+
+ return oa_regs;
+
+addr_err:
+ kfree(oa_regs);
+ return ERR_PTR(err);
+}
+
+static ssize_t show_dynamic_id(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
+{
+ struct xe_oa_config *oa_config =
+ container_of(attr, typeof(*oa_config), sysfs_metric_id);
+
+ return sprintf(buf, "%d\n", oa_config->id);
+}
+
+static int create_dynamic_oa_sysfs_entry(struct xe_oa *oa,
+ struct xe_oa_config *oa_config)
+{
+ sysfs_attr_init(&oa_config->sysfs_metric_id.attr);
+ oa_config->sysfs_metric_id.attr.name = "id";
+ oa_config->sysfs_metric_id.attr.mode = 0444;
+ oa_config->sysfs_metric_id.show = show_dynamic_id;
+ oa_config->sysfs_metric_id.store = NULL;
+
+ oa_config->attrs[0] = &oa_config->sysfs_metric_id.attr;
+ oa_config->attrs[1] = NULL;
+
+ oa_config->sysfs_metric.name = oa_config->uuid;
+ oa_config->sysfs_metric.attrs = oa_config->attrs;
+
+ return sysfs_create_group(oa->metrics_kobj, &oa_config->sysfs_metric);
+}
+
+int xe_oa_add_config_ioctl(struct drm_device *dev, void *data,
+ struct drm_file *file)
+{
+ struct xe_oa *oa = &to_xe_device(dev)->oa;
+ struct drm_xe_oa_config param;
+ struct drm_xe_oa_config *arg = ¶m;
+ struct xe_oa_config *oa_config, *tmp;
+ struct xe_oa_reg *regs;
+ int err, id;
+
+ if (!oa->xe) {
+ drm_dbg(&oa->xe->drm, "xe oa interface not available for this system\n");
+ return -ENODEV;
+ }
+
+ if (xe_perf_stream_paranoid && !perfmon_capable()) {
+ drm_dbg(&oa->xe->drm, "Insufficient privileges to add xe OA config\n");
+ return -EACCES;
+ }
+
+ err = __copy_from_user(¶m, data, sizeof(param));
+ if (XE_IOCTL_DBG(oa->xe, err))
+ return -EFAULT;
+
+ if (XE_IOCTL_DBG(oa->xe, arg->extensions) ||
+ XE_IOCTL_DBG(oa->xe, !arg->regs_ptr) ||
+ XE_IOCTL_DBG(oa->xe, !arg->n_regs))
+ return -EINVAL;
+
+ oa_config = kzalloc(sizeof(*oa_config), GFP_KERNEL);
+ if (!oa_config)
+ return -ENOMEM;
+
+ oa_config->oa = oa;
+ kref_init(&oa_config->ref);
+
+ if (!uuid_is_valid(arg->uuid)) {
+ drm_dbg(&oa->xe->drm, "Invalid uuid format for OA config\n");
+ err = -EINVAL;
+ goto reg_err;
+ }
+
+ /* Last character in oa_config->uuid will be 0 because oa_config is kzalloc */
+ memcpy(oa_config->uuid, arg->uuid, sizeof(arg->uuid));
+
+ oa_config->regs_len = arg->n_regs;
+ regs = xe_oa_alloc_regs(oa, xe_oa_is_valid_config_reg_addr,
+ u64_to_user_ptr(arg->regs_ptr),
+ arg->n_regs);
+ if (IS_ERR(regs)) {
+ drm_dbg(&oa->xe->drm, "Failed to create OA config for mux_regs\n");
+ err = PTR_ERR(regs);
+ goto reg_err;
+ }
+ oa_config->regs = regs;
+
+ err = mutex_lock_interruptible(&oa->metrics_lock);
+ if (err)
+ goto reg_err;
+
+ /* We shouldn't have too many configs, so this iteration shouldn't be too costly */
+ idr_for_each_entry(&oa->metrics_idr, tmp, id) {
+ if (!strcmp(tmp->uuid, oa_config->uuid)) {
+ drm_dbg(&oa->xe->drm, "OA config already exists with this uuid\n");
+ err = -EADDRINUSE;
+ goto sysfs_err;
+ }
+ }
+
+ err = create_dynamic_oa_sysfs_entry(oa, oa_config);
+ if (err) {
+ drm_dbg(&oa->xe->drm, "Failed to create sysfs entry for OA config\n");
+ goto sysfs_err;
+ }
+
+ oa_config->id = idr_alloc(&oa->metrics_idr, oa_config, 1, 0, GFP_KERNEL);
+ if (oa_config->id < 0) {
+ drm_dbg(&oa->xe->drm, "Failed to create sysfs entry for OA config\n");
+ err = oa_config->id;
+ goto sysfs_err;
+ }
+
+ mutex_unlock(&oa->metrics_lock);
+
+ drm_dbg(&oa->xe->drm, "Added config %s id=%i\n", oa_config->uuid, oa_config->id);
+
+ return oa_config->id;
+
+sysfs_err:
+ mutex_unlock(&oa->metrics_lock);
+reg_err:
+ xe_oa_config_put(oa_config);
+ drm_dbg(&oa->xe->drm, "Failed to add new OA config\n");
+ return err;
+}
+
+int xe_oa_remove_config_ioctl(struct drm_device *dev, void *data,
+ struct drm_file *file)
+{
+ struct xe_oa *oa = &to_xe_device(dev)->oa;
+ struct xe_oa_config *oa_config;
+ u64 arg, *ptr = data;
+ int ret;
+
+ if (!oa->xe) {
+ drm_dbg(&oa->xe->drm, "xe oa interface not available for this system\n");
+ return -ENODEV;
+ }
+
+ if (xe_perf_stream_paranoid && !perfmon_capable()) {
+ drm_dbg(&oa->xe->drm, "Insufficient privileges to remove xe OA config\n");
+ return -EACCES;
+ }
+
+ ret = get_user(arg, ptr);
+ if (XE_IOCTL_DBG(oa->xe, ret))
+ return ret;
+
+ ret = mutex_lock_interruptible(&oa->metrics_lock);
+ if (ret)
+ return ret;
+
+ oa_config = idr_find(&oa->metrics_idr, arg);
+ if (!oa_config) {
+ drm_dbg(&oa->xe->drm, "Failed to remove unknown OA config\n");
+ ret = -ENOENT;
+ goto err_unlock;
+ }
+
+ WARN_ON(arg != oa_config->id);
+
+ sysfs_remove_group(oa->metrics_kobj, &oa_config->sysfs_metric);
+ idr_remove(&oa->metrics_idr, arg);
+
+ mutex_unlock(&oa->metrics_lock);
+
+ drm_dbg(&oa->xe->drm, "Removed config %s id=%i\n", oa_config->uuid, oa_config->id);
+
+ xe_oa_config_put(oa_config);
+
+ return 0;
+
+err_unlock:
+ mutex_unlock(&oa->metrics_lock);
+ return ret;
+}
+
+void xe_oa_register(struct xe_device *xe)
+{
+ struct xe_oa *oa = &xe->oa;
+
+ if (!oa->xe)
+ return;
+
+ oa->metrics_kobj = kobject_create_and_add("metrics",
+ &xe->drm.primary->kdev->kobj);
+}
+
+void xe_oa_unregister(struct xe_device *xe)
+{
+ struct xe_oa *oa = &xe->oa;
+
+ if (!oa->metrics_kobj)
+ return;
+
+ kobject_put(oa->metrics_kobj);
+ oa->metrics_kobj = NULL;
+}
+
static u32 num_oa_units_per_gt(struct xe_gt *gt)
{
return 1;
@@ -244,6 +637,9 @@ int xe_oa_init(struct xe_device *xe)
for_each_gt(gt, xe, i)
mutex_init(>->oa.gt_lock);
+ mutex_init(&oa->metrics_lock);
+ idr_init_base(&oa->metrics_idr, 1);
+
ret = xe_oa_init_oa_units(oa);
if (ret) {
drm_err(&xe->drm, "OA initialization failed %d\n", ret);
@@ -257,6 +653,12 @@ int xe_oa_init(struct xe_device *xe)
return ret;
}
+static int destroy_config(int id, void *p, void *data)
+{
+ xe_oa_config_put(p);
+ return 0;
+}
+
void xe_oa_fini(struct xe_device *xe)
{
struct xe_oa *oa = &xe->oa;
@@ -269,5 +671,8 @@ void xe_oa_fini(struct xe_device *xe)
for_each_gt(gt, xe, i)
kfree(gt->oa.oa_unit);
+ idr_for_each(&oa->metrics_idr, destroy_config, oa);
+ idr_destroy(&oa->metrics_idr);
+
oa->xe = NULL;
}
diff --git a/drivers/gpu/drm/xe/xe_oa.h b/drivers/gpu/drm/xe/xe_oa.h
index a2f301e2be57b..4a4e3b2b70fcd 100644
--- a/drivers/gpu/drm/xe/xe_oa.h
+++ b/drivers/gpu/drm/xe/xe_oa.h
@@ -8,9 +8,17 @@
#include "xe_oa_types.h"
+struct drm_device;
+struct drm_file;
struct xe_device;
int xe_oa_init(struct xe_device *xe);
void xe_oa_fini(struct xe_device *xe);
+void xe_oa_register(struct xe_device *xe);
+void xe_oa_unregister(struct xe_device *xe);
+int xe_oa_add_config_ioctl(struct drm_device *dev, void *data,
+ struct drm_file *file);
+int xe_oa_remove_config_ioctl(struct drm_device *dev, void *data,
+ struct drm_file *file);
#endif
diff --git a/drivers/gpu/drm/xe/xe_oa_types.h b/drivers/gpu/drm/xe/xe_oa_types.h
index bb9a579d4529a..594e38c6328d2 100644
--- a/drivers/gpu/drm/xe/xe_oa_types.h
+++ b/drivers/gpu/drm/xe/xe_oa_types.h
@@ -6,6 +6,7 @@
#ifndef _XE_OA_TYPES_H_
#define _XE_OA_TYPES_H__
+#include <linux/idr.h>
#include <linux/math.h>
#include <linux/types.h>
#include <linux/mutex.h>
@@ -120,6 +121,15 @@ struct xe_oa {
/** @xe: back pointer to xe device */
struct xe_device *xe;
+ /** @metrics_kobj: kobj for metrics sysfs */
+ struct kobject *metrics_kobj;
+
+ /** @metrics_lock: lock protecting add/remove configs */
+ struct mutex metrics_lock;
+
+ /** @metrics_idr: List of dynamic configurations (struct xe_oa_config) */
+ struct idr metrics_idr;
+
/** @oa_formats: tracks all OA formats across platforms */
const struct xe_oa_format *oa_formats;
diff --git a/drivers/gpu/drm/xe/xe_perf.c b/drivers/gpu/drm/xe/xe_perf.c
index 37538e98dcc04..2aee4c7989486 100644
--- a/drivers/gpu/drm/xe/xe_perf.c
+++ b/drivers/gpu/drm/xe/xe_perf.c
@@ -6,11 +6,25 @@
#include <linux/errno.h>
#include <linux/sysctl.h>
+#include "xe_oa.h"
#include "xe_perf.h"
u32 xe_perf_stream_paranoid = true;
static struct ctl_table_header *sysctl_header;
+static int xe_oa_ioctl(struct drm_device *dev, struct drm_xe_perf_param *arg,
+ struct drm_file *file)
+{
+ switch (arg->perf_op) {
+ case DRM_XE_PERF_OP_ADD_CONFIG:
+ return xe_oa_add_config_ioctl(dev, (void *)arg->param, file);
+ case DRM_XE_PERF_OP_REMOVE_CONFIG:
+ return xe_oa_remove_config_ioctl(dev, (void *)arg->param, file);
+ default:
+ return -EINVAL;
+ }
+}
+
int xe_perf_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
{
struct drm_xe_perf_param *arg = data;
@@ -19,6 +33,8 @@ int xe_perf_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
return -EINVAL;
switch (arg->perf_type) {
+ case DRM_XE_PERF_TYPE_OA:
+ return xe_oa_ioctl(dev, arg, file);
default:
return -EINVAL;
}
diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
index 5c7529c35b907..e295d0b82c022 100644
--- a/include/uapi/drm/xe_drm.h
+++ b/include/uapi/drm/xe_drm.h
@@ -1346,6 +1346,7 @@ struct drm_xe_wait_user_fence {
* enum drm_xe_perf_type - Perf stream types
*/
enum drm_xe_perf_type {
+ DRM_XE_PERF_TYPE_OA,
DRM_XE_PERF_TYPE_MAX,
};
@@ -1414,6 +1415,30 @@ enum drm_xe_oa_format_type {
DRM_XE_OA_FMT_TYPE_PEC,
};
+/**
+ * struct drm_xe_oa_config - OA metric configuration
+ *
+ * Multiple OA configs can be added using @DRM_XE_PERF_OP_ADD_CONFIG. A
+ * particular config can be specified when opening an OA stream using
+ * @DRM_XE_OA_PROPERTY_OA_METRIC_SET property.
+ */
+struct drm_xe_oa_config {
+ /** @extensions: Pointer to the first extension struct, if any */
+ __u64 extensions;
+
+ /** * @uuid: String formatted like "%\08x-%\04x-%\04x-%\04x-%\012x" */
+ char uuid[36];
+
+ /** @n_regs: Number of regs in @regs_ptr */
+ __u32 n_regs;
+
+ /**
+ * @regs_ptr: Pointer to (register address, value) pairs for OA config
+ * registers. Expected length of buffer is: (2 * sizeof(u32) * @n_regs).
+ */
+ __u64 regs_ptr;
+};
+
#if defined(__cplusplus)
}
#endif
--
2.41.0
More information about the Intel-xe
mailing list