Re: [Intel-xe] [PATCH 05/21] drm/xe/oa: Add/remove config ioctl's

[Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>]

On Tue, Sep 19, 2023 at 09:10:33AM -0700, Ashutosh Dixit wrote:
>OA configurations consist of a set of event and counter select registers.
>The add_config ioctl 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.
>
>Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>

I think the plan was to do away with the differentiation of flex/mux/b 
even from the implementation, otherwise this lgtm,

Umesh
>---
> drivers/gpu/drm/xe/xe_device.c |   4 +
> drivers/gpu/drm/xe/xe_oa.c     | 379 ++++++++++++++++++++++++++++++++-
> drivers/gpu/drm/xe/xe_oa.h     |   5 +
> 3 files changed, 387 insertions(+), 1 deletion(-)
>
>diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
>index 2c3dac6340f04..aacca14e52b11 100644
>--- a/drivers/gpu/drm/xe/xe_device.c
>+++ b/drivers/gpu/drm/xe/xe_device.c
>@@ -114,6 +114,10 @@ static const struct drm_ioctl_desc xe_ioctls[] = {
> 	DRM_IOCTL_DEF_DRV(XE_WAIT_USER_FENCE, xe_wait_user_fence_ioctl,
> 			  DRM_RENDER_ALLOW),
> 	DRM_IOCTL_DEF_DRV(XE_VM_MADVISE, xe_vm_madvise_ioctl, DRM_RENDER_ALLOW),
>+
>+	DRM_IOCTL_DEF_DRV(XE_OA_ADD_CONFIG, xe_oa_add_config_ioctl, DRM_RENDER_ALLOW),
>+	DRM_IOCTL_DEF_DRV(XE_OA_REMOVE_CONFIG, xe_oa_remove_config_ioctl, DRM_RENDER_ALLOW),
>+
> };
>
> static const struct file_operations xe_driver_fops = {
>diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c
>index fae067e73c027..1963bc6fad10e 100644
>--- a/drivers/gpu/drm/xe/xe_oa.c
>+++ b/drivers/gpu/drm/xe/xe_oa.c
>@@ -12,8 +12,8 @@
> #include <drm/drm_drv.h>
>
> #include "regs/xe_oa_regs.h"
>-#include "xe_gt.h"
> #include "xe_device.h"
>+#include "xe_gt.h"
> #include "xe_oa.h"
>
> static u32 xe_oa_stream_paranoid = true;
>@@ -33,6 +33,376 @@ static const struct xe_oa_format oa_formats[] = {
>
> static struct ctl_table_header *sysctl_header;
>
>+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->flex_regs);
>+	kfree(oa_config->b_counter_regs);
>+	kfree(oa_config->mux_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 },	/* GEN12_OAG_OA_PESS */
>+	{ .start = 0xd900, .end = 0xd91c },	/* GEN12_OAG_OASTARTTRIG[1-8] */
>+	{ .start = 0xd920, .end = 0xd93c },	/* GEN12_OAG_OAREPORTTRIG1[1-8] */
>+	{ .start = 0xd940, .end = 0xd97c },	/* GEN12_OAG_CEC[0-7][0-1] */
>+	{ .start = 0xdc00, .end = 0xdc3c },	/* GEN12_OAG_SCEC[0-7][0-1] */
>+	{ .start = 0xdc40, .end = 0xdc40 },	/* GEN12_OAG_SPCTR_CNF */
>+	{ .start = 0xdc44, .end = 0xdc44 },	/* GEN12_OAA_DBG_REG */
>+	{}
>+};
>+
>+static const struct xe_mmio_range mtl_oam_b_counters[] = {
>+	{ .start = 0x393000, .end = 0x39301c },	/* GEN12_OAM_STARTTRIG1[1-8] */
>+	{ .start = 0x393020, .end = 0x39303c },	/* GEN12_OAM_REPORTTRIG1[1-8] */
>+	{ .start = 0x393040, .end = 0x39307c },	/* GEN12_OAM_CEC[0-7][0-1] */
>+	{ .start = 0x393200, .end = 0x39323C },	/* MPES[0-7] */
>+	{}
>+};
>+
>+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);
>+}
>+
>+/*
>+ * Ref: 14010536224:
>+ * 0x20cc is repurposed on MTL, so use a separate array for MTL.
>+ */
>+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 bool xe_oa_is_valid_mux_addr(struct xe_oa *oa, u32 addr)
>+{
>+	if (oa->xe->info.platform == XE_METEORLAKE)
>+		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 u32 mask_reg_value(u32 reg, u32 val)
>+{
>+	/*
>+	 * HALF_SLICE_CHICKEN2 is programmed with a the WaDisableSTUnitPowerOptimization
>+	 * workaround. Make sure the value programmed by userspace doesn't change this.
>+	 */
>+	if (REG_EQUAL_MCR(reg, HALF_SLICE_CHICKEN2))
>+		val = val & ~_MASKED_BIT_ENABLE(GEN8_ST_PO_DISABLE);
>+
>+	/*
>+	 * WAIT_FOR_RC6_EXIT has only one bit fullfilling the function indicated by its
>+	 * name and a bunch of selection fields used by OA configs.
>+	 */
>+	if (REG_EQUAL(reg, WAIT_FOR_RC6_EXIT))
>+		val = val & ~_MASKED_BIT_ENABLE(HSW_WAIT_FOR_RC6_EXIT_ENABLE);
>+
>+	return val;
>+}
>+
>+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;
>+
>+	if (!n_regs || WARN_ON(!is_valid))
>+		return NULL;
>+
>+	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 = mask_reg_value(addr, 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 *arg = data;
>+	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_oa_stream_paranoid && !perfmon_capable()) {
>+		drm_dbg(&oa->xe->drm, "Insufficient privileges to add xe OA config\n");
>+		return -EACCES;
>+	}
>+
>+	if ((!arg->mux_regs_ptr || !arg->n_mux_regs) &&
>+	    (!arg->boolean_regs_ptr || !arg->n_boolean_regs) &&
>+	    (!arg->flex_regs_ptr || !arg->n_flex_regs)) {
>+		drm_dbg(&oa->xe->drm, "No OA registers given\n");
>+		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->mux_regs_len = arg->n_mux_regs;
>+	regs = xe_oa_alloc_regs(oa, xe_oa_is_valid_mux_addr,
>+				u64_to_user_ptr(arg->mux_regs_ptr),
>+				arg->n_mux_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->mux_regs = regs;
>+
>+	oa_config->b_counter_regs_len = arg->n_boolean_regs;
>+	regs = xe_oa_alloc_regs(oa, xe_oa_is_valid_b_counter_addr,
>+				u64_to_user_ptr(arg->boolean_regs_ptr),
>+				arg->n_boolean_regs);
>+	if (IS_ERR(regs)) {
>+		drm_dbg(&oa->xe->drm, "Failed to create OA config for b_counter_regs\n");
>+		err = PTR_ERR(regs);
>+		goto reg_err;
>+	}
>+	oa_config->b_counter_regs = regs;
>+
>+	oa_config->flex_regs_len = arg->n_flex_regs;
>+	regs = xe_oa_alloc_regs(oa, xe_oa_is_valid_flex_addr,
>+				u64_to_user_ptr(arg->flex_regs_ptr),
>+				arg->n_flex_regs);
>+	if (IS_ERR(regs)) {
>+		drm_dbg(&oa->xe->drm, "Failed to create OA config for flex_regs\n");
>+		err = PTR_ERR(regs);
>+		goto reg_err;
>+	}
>+	oa_config->flex_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;
>+	}
>+
>+	/* Config id 0 is invalid, id 1 for kernel stored test config. */
>+	oa_config->id = idr_alloc(&oa->metrics_idr, oa_config, 2, 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 = data;
>+	int ret;
>+
>+	if (!oa->xe) {
>+		drm_dbg(&oa->xe->drm, "xe oa interface not available for this system\n");
>+		return -ENODEV;
>+	}
>+
>+	if (xe_oa_stream_paranoid && !perfmon_capable()) {
>+		drm_dbg(&oa->xe->drm, "Insufficient privileges to remove xe OA config\n");
>+		return -EACCES;
>+	}
>+
>+	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;
>@@ -258,6 +628,12 @@ int xe_oa_init(struct xe_device *xe)
> 	return 0;
> }
>
>+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;
>@@ -270,6 +646,7 @@ void xe_oa_fini(struct xe_device *xe)
> 	for_each_gt(gt, xe, i)
> 		kfree(gt->oa.group);
>
>+	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 ba4ba80fd34cb..79f77f445deb0 100644
>--- a/drivers/gpu/drm/xe/xe_oa.h
>+++ b/drivers/gpu/drm/xe/xe_oa.h
>@@ -12,7 +12,12 @@ 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_ioctl_version(struct xe_device *xe);
> int xe_oa_sysctl_register(void);
> void xe_oa_sysctl_unregister(void);
>
>+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
>-- 
>2.41.0
>