| 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: Tue, 29 Sep 2015 15:39:07 +0100
From: Robert Bragg <robert@...bynine.org>
To: intel-gfx@...ts.freedesktop.org
Cc: Daniel Vetter <daniel.vetter@...el.com>,
Chris Wilson <chris@...is-wilson.co.uk>,
Sourab Gupta <sourab.gupta@...el.com>,
Zhenyu Wang <zhenyuw@...ux.intel.com>,
Jani Nikula <jani.nikula@...ux.intel.com>,
David Airlie <airlied@...ux.ie>,
Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...nel.org>,
Kan Liang <kan.liang@...el.com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Zheng Yan <zheng.z.yan@...el.com>,
Mark Rutland <mark.rutland@....com>,
Matt Fleming <matt.fleming@...el.com>,
dri-devel@...ts.freedesktop.org, linux-kernel@...r.kernel.org,
linux-api@...r.kernel.org
Subject: [RFC 4/6] drm/i915: Add i915 perf event for Haswell OA unit
Gen graphics hardware can be set up to periodically write snapshots of
performance counters into a circular buffer via its Observation
Architecture and this patch exposes that capability to userspace via the
i915 perf interface.
Cc: Chris Wilson <chris@...is-wilson.co.uk>
Signed-off-by: Robert Bragg <robert@...bynine.org>
Signed-off-by: Zhenyu Wang <zhenyuw@...ux.intel.com>
---
drivers/gpu/drm/i915/i915_drv.h | 57 +++
drivers/gpu/drm/i915/i915_gem_context.c | 23 +-
drivers/gpu/drm/i915/i915_perf.c | 697 +++++++++++++++++++++++++++++++-
drivers/gpu/drm/i915/i915_reg.h | 338 ++++++++++++++++
include/uapi/drm/i915_drm.h | 63 +++
5 files changed, 1171 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 0cb36d9..d6db816 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1694,6 +1694,11 @@ struct i915_execbuffer_params {
struct drm_i915_gem_request *request;
};
+struct i915_oa_format {
+ u32 format;
+ int size;
+};
+
struct i915_oa_reg {
u32 addr;
u32 value;
@@ -1760,6 +1765,20 @@ struct i915_perf_event {
void (*destroy)(struct i915_perf_event *event);
};
+struct i915_oa_ops {
+ void (*init_oa_buffer)(struct drm_i915_private *dev_priv);
+ void (*enable_metric_set)(struct drm_i915_private *dev_priv);
+ void (*disable_metric_set)(struct drm_i915_private *dev_priv);
+ void (*oa_enable)(struct drm_i915_private *dev_priv);
+ void (*oa_disable)(struct drm_i915_private *dev_priv);
+ void (*update_oacontrol)(struct drm_i915_private *dev_priv);
+ void (*update_specific_hw_ctx_id)(struct drm_i915_private *dev_priv,
+ u32 ctx_id);
+ void (*read)(struct i915_perf_event *event,
+ struct i915_perf_read_state *read_state);
+ bool (*oa_buffer_is_empty)(struct drm_i915_private *dev_priv);
+};
+
struct drm_i915_private {
struct drm_device *dev;
struct kmem_cache *objects;
@@ -1996,7 +2015,43 @@ struct drm_i915_private {
struct {
bool initialized;
+
struct mutex lock;
+
+ struct ctl_table_header *sysctl_header;
+
+ struct {
+ struct i915_perf_event *exclusive_event;
+
+ u32 specific_ctx_id;
+
+ struct hrtimer poll_check_timer;
+ wait_queue_head_t poll_wq;
+
+ bool periodic;
+ u32 period_exponent;
+
+ u32 metrics_set;
+
+ const struct i915_oa_reg *mux_regs;
+ int mux_regs_len;
+ const struct i915_oa_reg *b_counter_regs;
+ int b_counter_regs_len;
+
+ struct {
+ struct drm_i915_gem_object *obj;
+ u32 gtt_offset;
+ u8 *addr;
+ u32 head;
+ u32 tail;
+ int format;
+ int format_size;
+ } oa_buffer;
+
+ struct i915_oa_ops ops;
+ const struct i915_oa_format *oa_formats;
+ } oa;
+
struct list_head events;
} perf;
@@ -3204,6 +3259,8 @@ int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data,
int i915_perf_open_ioctl(struct drm_device *dev, void *data,
struct drm_file *file);
+void i915_oa_context_pin_notify(struct drm_i915_private *dev_priv,
+ struct intel_context *context);
/* i915_gem_evict.c */
int __must_check i915_gem_evict_something(struct drm_device *dev,
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 8e893b3..3c4419c 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -133,6 +133,23 @@ static int get_context_size(struct drm_device *dev)
return ret;
}
+static int i915_gem_context_pin_state(struct drm_device *dev,
+ struct intel_context *ctx)
+{
+ int ret;
+
+ BUG_ON(!mutex_is_locked(&dev->struct_mutex));
+
+ ret = i915_gem_obj_ggtt_pin(ctx->legacy_hw_ctx.rcs_state,
+ get_context_alignment(dev), 0);
+ if (ret)
+ return ret;
+
+ i915_oa_context_pin_notify(dev->dev_private, ctx);
+
+ return 0;
+}
+
void i915_gem_context_free(struct kref *ctx_ref)
{
struct intel_context *ctx = container_of(ctx_ref, typeof(*ctx), ref);
@@ -258,8 +275,7 @@ i915_gem_create_context(struct drm_device *dev,
* be available. To avoid this we always pin the default
* context.
*/
- ret = i915_gem_obj_ggtt_pin(ctx->legacy_hw_ctx.rcs_state,
- get_context_alignment(dev), 0);
+ ret = i915_gem_context_pin_state(dev, ctx);
if (ret) {
DRM_DEBUG_DRIVER("Couldn't pin %d\n", ret);
goto err_destroy;
@@ -634,8 +650,7 @@ static int do_switch(struct drm_i915_gem_request *req)
/* Trying to pin first makes error handling easier. */
if (ring == &dev_priv->ring[RCS]) {
- ret = i915_gem_obj_ggtt_pin(to->legacy_hw_ctx.rcs_state,
- get_context_alignment(ring->dev), 0);
+ ret = i915_gem_context_pin_state(ring->dev, to);
if (ret)
return ret;
}
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 477e3e6..bc1c4d1 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -26,6 +26,31 @@
#include <linux/sizes.h>
#include "i915_drv.h"
+#include "intel_ringbuffer.h"
+#include "intel_lrc.h"
+#include "i915_oa_hsw.h"
+
+/* Must be a power of two */
+#define OA_BUFFER_SIZE SZ_16M
+#define OA_TAKEN(tail, head) ((tail - head) & (OA_BUFFER_SIZE - 1))
+
+/* frequency for forwarding samples from OA to perf buffer */
+#define POLL_FREQUENCY 200
+#define POLL_PERIOD max_t(u64, 10000, NSEC_PER_SEC / POLL_FREQUENCY)
+
+#define OA_EXPONENT_MAX 0x3f
+
+static struct i915_oa_format hsw_oa_formats[I915_OA_FORMAT_MAX] = {
+ [I915_OA_FORMAT_A13] = { 0, 64 },
+ [I915_OA_FORMAT_A29] = { 1, 128 },
+ [I915_OA_FORMAT_A13_B8_C8] = { 2, 128 },
+ /* A29_B8_C8 Disallowed as 192 bytes doesn't factor into buffer size */
+ [I915_OA_FORMAT_B4_C8] = { 4, 64 },
+ [I915_OA_FORMAT_A45_B8_C8] = { 5, 256 },
+ [I915_OA_FORMAT_B4_C8_A16] = { 6, 128 },
+ [I915_OA_FORMAT_C4_B8] = { 7, 64 },
+};
+
/**
* i915_perf_copy_attr() - copy specific event attributes from userspace
@@ -107,6 +132,634 @@ err_size:
goto out;
}
+
+static bool gen7_oa_buffer_is_empty(struct drm_i915_private *dev_priv)
+{
+ u32 oastatus2 = I915_READ(GEN7_OASTATUS2);
+ u32 oastatus1 = I915_READ(GEN7_OASTATUS1);
+ u32 head = oastatus2 & GEN7_OASTATUS2_HEAD_MASK;
+ u32 tail = oastatus1 & GEN7_OASTATUS1_TAIL_MASK;
+
+ return OA_TAKEN(tail, head) == 0;
+}
+
+static bool append_oa_status(struct i915_perf_event *event,
+ struct i915_perf_read_state *read_state,
+ enum drm_i915_perf_record_type type)
+{
+ struct drm_i915_perf_event_header header = { type, 0, sizeof(header) };
+
+ if ((read_state->count - read_state->read) < header.size)
+ return false;
+
+ copy_to_user(read_state->buf, &header, sizeof(header));
+
+ read_state->buf += sizeof(header);
+ read_state->read += header.size;
+
+ return true;
+}
+
+static bool append_oa_sample(struct i915_perf_event *event,
+ struct i915_perf_read_state *read_state,
+ const u8 *report)
+{
+ struct drm_i915_private *dev_priv = event->dev_priv;
+ int report_size = dev_priv->perf.oa.oa_buffer.format_size;
+ struct drm_i915_perf_event_header header;
+ u32 sample_flags = event->sample_flags;
+ u32 dummy_ctx_id = 0;
+ u32 dummy_timestamp = 0;
+
+ header.type = DRM_I915_PERF_RECORD_SAMPLE;
+ header.misc = 0;
+ header.size = sizeof(header);
+
+
+ /* XXX: could pre-compute this when opening the event... */
+
+ if (sample_flags & I915_PERF_SAMPLE_CTXID)
+ header.size += 4;
+
+ if (sample_flags & I915_PERF_SAMPLE_TIMESTAMP)
+ header.size += 4;
+
+ if (sample_flags & I915_PERF_SAMPLE_OA_REPORT)
+ header.size += report_size;
+
+
+ if ((read_state->count - read_state->read) < header.size)
+ return false;
+
+
+ copy_to_user(read_state->buf, &header, sizeof(header));
+ read_state->buf += sizeof(header);
+
+ if (sample_flags & I915_PERF_SAMPLE_CTXID) {
+#warning "fixme: extract context ID from OA reports"
+ copy_to_user(read_state->buf, &dummy_ctx_id, 4);
+ read_state->buf += 4;
+ }
+
+ if (sample_flags & I915_PERF_SAMPLE_TIMESTAMP) {
+#warning "fixme: extract timestamp from OA reports"
+ copy_to_user(read_state->buf, &dummy_timestamp, 4);
+ read_state->buf += 4;
+ }
+
+ if (sample_flags & I915_PERF_SAMPLE_OA_REPORT) {
+ copy_to_user(read_state->buf, report, report_size);
+ read_state->buf += report_size;
+ }
+
+
+ read_state->read += header.size;
+
+ return true;
+}
+
+static u32 gen7_append_oa_reports(struct i915_perf_event *event,
+ struct i915_perf_read_state *read_state,
+ u32 head,
+ u32 tail)
+{
+ struct drm_i915_private *dev_priv = event->dev_priv;
+ int report_size = dev_priv->perf.oa.oa_buffer.format_size;
+ u8 *oa_buf_base = dev_priv->perf.oa.oa_buffer.addr;
+ u32 mask = (OA_BUFFER_SIZE - 1);
+ u8 *report;
+ u32 taken;
+
+ head -= dev_priv->perf.oa.oa_buffer.gtt_offset;
+ tail -= dev_priv->perf.oa.oa_buffer.gtt_offset;
+
+ /* Note: the gpu doesn't wrap the tail according to the OA buffer size
+ * so when we need to make sure our head/tail values are in-bounds we
+ * use the above mask.
+ */
+
+ while ((taken = OA_TAKEN(tail, head))) {
+ /* The tail increases in 64 byte increments, not in
+ * format_size steps. */
+ if (taken < report_size)
+ break;
+
+ report = oa_buf_base + (head & mask);
+
+ if (dev_priv->perf.oa.exclusive_event->enabled) {
+ if (!append_oa_sample(event, read_state, report))
+ break;
+ }
+
+ /* If append_oa_sample() returns false we shouldn't progress
+ * head so we update it afterwards... */
+ head += report_size;
+ }
+
+ return dev_priv->perf.oa.oa_buffer.gtt_offset + head;
+}
+
+static void gen7_oa_read(struct i915_perf_event *event,
+ struct i915_perf_read_state *read_state)
+{
+ struct drm_i915_private *dev_priv = event->dev_priv;
+ u32 oastatus2;
+ u32 oastatus1;
+ u32 head;
+ u32 tail;
+
+ WARN_ON(!dev_priv->perf.oa.oa_buffer.addr);
+
+ oastatus2 = I915_READ(GEN7_OASTATUS2);
+ oastatus1 = I915_READ(GEN7_OASTATUS1);
+
+ head = oastatus2 & GEN7_OASTATUS2_HEAD_MASK;
+ tail = oastatus1 & GEN7_OASTATUS1_TAIL_MASK;
+
+ if (unlikely(oastatus1 & (GEN7_OASTATUS1_OABUFFER_OVERFLOW |
+ GEN7_OASTATUS1_REPORT_LOST))) {
+
+ if (oastatus1 & GEN7_OASTATUS1_OABUFFER_OVERFLOW) {
+ if (append_oa_status(event, read_state,
+ DRM_I915_PERF_RECORD_OA_BUFFER_OVERFLOW))
+ oastatus1 &= ~GEN7_OASTATUS1_OABUFFER_OVERFLOW;
+ }
+
+ if (oastatus1 & GEN7_OASTATUS1_REPORT_LOST) {
+ if (append_oa_status(event, read_state,
+ DRM_I915_PERF_RECORD_OA_REPORT_LOST))
+ oastatus1 &= ~GEN7_OASTATUS1_REPORT_LOST;
+ }
+
+ I915_WRITE(GEN7_OASTATUS1, oastatus1);
+ }
+
+ head = gen7_append_oa_reports(event, read_state, head, tail);
+
+ I915_WRITE(GEN7_OASTATUS2, (head & GEN7_OASTATUS2_HEAD_MASK) |
+ OA_MEM_SELECT_GGTT);
+}
+
+static bool i915_oa_can_read(struct i915_perf_event *event)
+{
+ struct drm_i915_private *dev_priv = event->dev_priv;
+
+ return !dev_priv->perf.oa.ops.oa_buffer_is_empty(dev_priv);
+}
+
+static int i915_oa_wait_unlocked(struct i915_perf_event *event)
+{
+ struct drm_i915_private *dev_priv = event->dev_priv;
+
+ /* Note: the oa_buffer_is_empty() condition is ok to run unlocked as it
+ * just performs mmio reads of the OA buffer head + tail pointers and
+ * it's assumed we're handling some operation that implies the event
+ * can't be destroyed until completion (such as a read()) that ensures
+ * the device + OA buffer can't disappear
+ */
+ return wait_event_interruptible(dev_priv->perf.oa.poll_wq,
+ !dev_priv->perf.oa.ops.oa_buffer_is_empty(dev_priv));
+}
+
+static void i915_oa_poll_wait(struct i915_perf_event *event,
+ struct file *file,
+ poll_table *wait)
+{
+ struct drm_i915_private *dev_priv = event->dev_priv;
+
+ poll_wait(file, &dev_priv->perf.oa.poll_wq, wait);
+}
+
+static void i915_oa_read(struct i915_perf_event *event,
+ struct i915_perf_read_state *read_state)
+{
+ struct drm_i915_private *dev_priv = event->dev_priv;
+
+ dev_priv->perf.oa.ops.read(event, read_state);
+}
+
+static void
+free_oa_buffer(struct drm_i915_private *i915)
+{
+ mutex_lock(&i915->dev->struct_mutex);
+
+ vunmap(i915->perf.oa.oa_buffer.addr);
+ i915_gem_object_ggtt_unpin(i915->perf.oa.oa_buffer.obj);
+ drm_gem_object_unreference(&i915->perf.oa.oa_buffer.obj->base);
+
+ i915->perf.oa.oa_buffer.obj = NULL;
+ i915->perf.oa.oa_buffer.gtt_offset = 0;
+ i915->perf.oa.oa_buffer.addr = NULL;
+
+ mutex_unlock(&i915->dev->struct_mutex);
+}
+
+static void i915_oa_event_destroy(struct i915_perf_event *event)
+{
+ struct drm_i915_private *dev_priv = event->dev_priv;
+
+ BUG_ON(event != dev_priv->perf.oa.exclusive_event);
+
+ dev_priv->perf.oa.ops.disable_metric_set(dev_priv);
+
+ free_oa_buffer(dev_priv);
+
+ intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
+ intel_runtime_pm_put(dev_priv);
+
+ dev_priv->perf.oa.exclusive_event = NULL;
+}
+
+static void *vmap_oa_buffer(struct drm_i915_gem_object *obj)
+{
+ int i;
+ void *addr = NULL;
+ struct sg_page_iter sg_iter;
+ struct page **pages;
+
+ pages = drm_malloc_ab(obj->base.size >> PAGE_SHIFT, sizeof(*pages));
+ if (pages == NULL) {
+ DRM_DEBUG_DRIVER("Failed to get space for pages\n");
+ goto finish;
+ }
+
+ i = 0;
+ for_each_sg_page(obj->pages->sgl, &sg_iter, obj->pages->nents, 0) {
+ pages[i] = sg_page_iter_page(&sg_iter);
+ i++;
+ }
+
+ addr = vmap(pages, i, 0, PAGE_KERNEL);
+ if (addr == NULL) {
+ DRM_DEBUG_DRIVER("Failed to vmap pages\n");
+ goto finish;
+ }
+
+finish:
+ if (pages)
+ drm_free_large(pages);
+ return addr;
+}
+
+static void gen7_init_oa_buffer(struct drm_i915_private *dev_priv)
+{
+ /* Pre-DevBDW: OABUFFER must be set with counters off,
+ * before OASTATUS1, but after OASTATUS2 */
+ I915_WRITE(GEN7_OASTATUS2, dev_priv->perf.oa.oa_buffer.gtt_offset |
+ OA_MEM_SELECT_GGTT); /* head */
+ I915_WRITE(GEN7_OABUFFER, dev_priv->perf.oa.oa_buffer.gtt_offset);
+ I915_WRITE(GEN7_OASTATUS1, dev_priv->perf.oa.oa_buffer.gtt_offset |
+ OABUFFER_SIZE_16M); /* tail */
+}
+
+static int alloc_oa_buffer(struct drm_i915_private *dev_priv)
+{
+ struct drm_i915_gem_object *bo;
+ int ret;
+
+ BUG_ON(dev_priv->perf.oa.oa_buffer.obj);
+
+ ret = i915_mutex_lock_interruptible(dev_priv->dev);
+ if (ret)
+ return ret;
+
+ bo = i915_gem_alloc_object(dev_priv->dev, OA_BUFFER_SIZE);
+ if (bo == NULL) {
+ DRM_ERROR("Failed to allocate OA buffer\n");
+ ret = -ENOMEM;
+ goto unlock;
+ }
+ dev_priv->perf.oa.oa_buffer.obj = bo;
+
+ ret = i915_gem_object_set_cache_level(bo, I915_CACHE_LLC);
+ if (ret)
+ goto err_unref;
+
+ /* PreHSW required 512K alignment, HSW requires 16M */
+ ret = i915_gem_obj_ggtt_pin(bo, SZ_16M, 0);
+ if (ret)
+ goto err_unref;
+
+ dev_priv->perf.oa.oa_buffer.gtt_offset = i915_gem_obj_ggtt_offset(bo);
+ dev_priv->perf.oa.oa_buffer.addr = vmap_oa_buffer(bo);
+
+ dev_priv->perf.oa.ops.init_oa_buffer(dev_priv);
+
+ DRM_DEBUG_DRIVER("OA Buffer initialized, gtt offset = 0x%x, vaddr = %p",
+ dev_priv->perf.oa.oa_buffer.gtt_offset,
+ dev_priv->perf.oa.oa_buffer.addr);
+
+ goto unlock;
+
+err_unref:
+ drm_gem_object_unreference(&bo->base);
+
+unlock:
+ mutex_unlock(&dev_priv->dev->struct_mutex);
+ return ret;
+}
+
+static void config_oa_regs(struct drm_i915_private *dev_priv,
+ const struct i915_oa_reg *regs,
+ int n_regs)
+{
+ int i;
+
+ for (i = 0; i < n_regs; i++) {
+ const struct i915_oa_reg *reg = regs + i;
+
+ I915_WRITE(reg->addr, reg->value);
+ }
+}
+
+static void hsw_enable_metric_set(struct drm_i915_private *dev_priv)
+{
+ dev_priv->perf.oa.mux_regs = NULL;
+ dev_priv->perf.oa.mux_regs_len = 0;
+ dev_priv->perf.oa.b_counter_regs = NULL;
+ dev_priv->perf.oa.b_counter_regs_len = 0;
+
+ I915_WRITE(GDT_CHICKEN_BITS, GT_NOA_ENABLE);
+
+ /* PRM:
+ *
+ * OA unit is using “crclk” for its functionality. When trunk
+ * level clock gating takes place, OA clock would be gated,
+ * unable to count the events from non-render clock domain.
+ * Render clock gating must be disabled when OA is enabled to
+ * count the events from non-render domain. Unit level clock
+ * gating for RCS should also be disabled.
+ */
+ I915_WRITE(GEN7_MISCCPCTL, (I915_READ(GEN7_MISCCPCTL) &
+ ~GEN7_DOP_CLOCK_GATE_ENABLE));
+ I915_WRITE(GEN6_UCGCTL1, (I915_READ(GEN6_UCGCTL1) |
+ GEN6_CSUNIT_CLOCK_GATE_DISABLE));
+
+ switch (dev_priv->perf.oa.metrics_set) {
+ case I915_OA_METRICS_SET_3D:
+ config_oa_regs(dev_priv, i915_oa_3d_mux_config_hsw,
+ i915_oa_3d_mux_config_hsw_len);
+ config_oa_regs(dev_priv, i915_oa_3d_b_counter_config_hsw,
+ i915_oa_3d_b_counter_config_hsw_len);
+ break;
+ default:
+ BUG();
+ }
+}
+
+static void hsw_disable_metric_set(struct drm_i915_private *dev_priv)
+{
+ I915_WRITE(GEN6_UCGCTL1, (I915_READ(GEN6_UCGCTL1) &
+ ~GEN6_CSUNIT_CLOCK_GATE_DISABLE));
+ I915_WRITE(GEN7_MISCCPCTL, (I915_READ(GEN7_MISCCPCTL) |
+ GEN7_DOP_CLOCK_GATE_ENABLE));
+
+ I915_WRITE(GDT_CHICKEN_BITS, (I915_READ(GDT_CHICKEN_BITS) &
+ ~GT_NOA_ENABLE));
+}
+
+static void gen7_update_oacontrol(struct drm_i915_private *dev_priv)
+{
+ if (dev_priv->perf.oa.exclusive_event->enabled) {
+ unsigned long ctx_id = 0;
+ bool pinning_ok = false;
+
+ if (dev_priv->perf.oa.exclusive_event->ctx &&
+ dev_priv->perf.oa.specific_ctx_id) {
+ ctx_id = dev_priv->perf.oa.specific_ctx_id;
+ pinning_ok = true;
+ }
+
+ if (dev_priv->perf.oa.exclusive_event->ctx == NULL ||
+ pinning_ok) {
+ bool periodic = dev_priv->perf.oa.periodic;
+ u32 period_exponent = dev_priv->perf.oa.period_exponent;
+ u32 report_format = dev_priv->perf.oa.oa_buffer.format;
+
+ I915_WRITE(GEN7_OACONTROL,
+ (ctx_id & GEN7_OACONTROL_CTX_MASK) |
+ (period_exponent <<
+ GEN7_OACONTROL_TIMER_PERIOD_SHIFT) |
+ (periodic ?
+ GEN7_OACONTROL_TIMER_ENABLE : 0) |
+ (report_format <<
+ GEN7_OACONTROL_FORMAT_SHIFT) |
+ (ctx_id ?
+ GEN7_OACONTROL_PER_CTX_ENABLE : 0) |
+ GEN7_OACONTROL_ENABLE);
+ return;
+ }
+ }
+
+ I915_WRITE(GEN7_OACONTROL, 0);
+}
+
+static void gen7_oa_enable(struct drm_i915_private *dev_priv)
+{
+ u32 oastatus1, tail;
+
+ gen7_update_oacontrol(dev_priv);
+
+ /* Reset the head ptr so we don't forward reports from before now. */
+ oastatus1 = I915_READ(GEN7_OASTATUS1);
+ tail = oastatus1 & GEN7_OASTATUS1_TAIL_MASK;
+ I915_WRITE(GEN7_OASTATUS2, (tail & GEN7_OASTATUS2_HEAD_MASK) |
+ OA_MEM_SELECT_GGTT);
+}
+
+static void i915_oa_event_enable(struct i915_perf_event *event)
+{
+ struct drm_i915_private *dev_priv = event->dev_priv;
+
+ dev_priv->perf.oa.ops.oa_enable(dev_priv);
+
+ if (dev_priv->perf.oa.periodic)
+ hrtimer_start(&dev_priv->perf.oa.poll_check_timer,
+ ns_to_ktime(POLL_PERIOD),
+ HRTIMER_MODE_REL_PINNED);
+}
+
+static void gen7_oa_disable(struct drm_i915_private *dev_priv)
+{
+ I915_WRITE(GEN7_OACONTROL, 0);
+}
+
+static void i915_oa_event_disable(struct i915_perf_event *event)
+{
+ struct drm_i915_private *dev_priv = event->dev_priv;
+
+ dev_priv->perf.oa.ops.oa_disable(dev_priv);
+
+ if (dev_priv->perf.oa.periodic)
+ hrtimer_cancel(&dev_priv->perf.oa.poll_check_timer);
+}
+
+static int i915_oa_event_init(struct i915_perf_event *event,
+ struct drm_i915_perf_open_param *param)
+{
+ struct drm_i915_private *dev_priv = event->dev_priv;
+ struct drm_i915_perf_oa_attr oa_attr;
+ u32 known_flags = 0;
+ int format_size;
+ int ret;
+
+ BUG_ON(param->type != I915_PERF_OA_EVENT);
+
+ if (!dev_priv->perf.oa.ops.init_oa_buffer) {
+ DRM_ERROR("OA unit not supported\n");
+ return -ENODEV;
+ }
+
+ /* To avoid the complexity of having to accurately filter
+ * counter reports and marshal to the appropriate client
+ * we currently only allow exclusive access */
+ if (dev_priv->perf.oa.exclusive_event) {
+ DRM_ERROR("OA unit already in use\n");
+ return -EBUSY;
+ }
+
+ ret = i915_perf_copy_attr(to_user_ptr(param->attr),
+ &oa_attr,
+ I915_OA_ATTR_SIZE_VER0,
+ sizeof(oa_attr));
+ if (ret)
+ return ret;
+
+ known_flags = I915_OA_FLAG_PERIODIC;
+ if (oa_attr.flags & ~known_flags) {
+ DRM_ERROR("Unknown drm_i915_perf_oa_attr flag\n");
+ return -EINVAL;
+ }
+
+ if (oa_attr.oa_format >= I915_OA_FORMAT_MAX) {
+ DRM_ERROR("Invalid OA report format\n");
+ return -EINVAL;
+ }
+
+ format_size = dev_priv->perf.oa.oa_formats[oa_attr.oa_format].size;
+ if (!format_size) {
+ DRM_ERROR("Invalid OA report format\n");
+ return -EINVAL;
+ }
+
+ dev_priv->perf.oa.oa_buffer.format_size = format_size;
+
+ dev_priv->perf.oa.oa_buffer.format =
+ dev_priv->perf.oa.oa_formats[oa_attr.oa_format].format;
+
+ if (IS_HASWELL(dev_priv->dev)) {
+ if (oa_attr.metrics_set <= 0 ||
+ oa_attr.metrics_set > I915_OA_METRICS_SET_MAX) {
+ DRM_ERROR("Metric set not available\n");
+ return -EINVAL;
+ }
+ } else {
+ BUG(); /* checked above */
+ return -ENODEV;
+ }
+
+ dev_priv->perf.oa.metrics_set = oa_attr.metrics_set;
+
+ dev_priv->perf.oa.periodic = !!(oa_attr.flags & I915_OA_FLAG_PERIODIC);
+
+ /* NB: The exponent represents a period as follows:
+ *
+ * 80ns * 2^(period_exponent + 1)
+ */
+ if (dev_priv->perf.oa.periodic) {
+ u64 period_exponent = oa_attr.oa_timer_exponent;
+
+ if (period_exponent > OA_EXPONENT_MAX)
+ return -EINVAL;
+
+ /* Theoretically we can program the OA unit to sample every
+ * 160ns but don't allow that by default unless root...
+ *
+ * Referring to perf's kernel.perf_event_max_sample_rate for
+ * a precedent (100000 by default); with an OA exponent of
+ * 6 we get a period of 10.240 microseconds -just under
+ * 100000Hz
+ */
+ if (period_exponent < 6 && !capable(CAP_SYS_ADMIN)) {
+ DRM_ERROR("Sampling period too high without root privileges\n");
+ return -EACCES;
+ }
+
+ dev_priv->perf.oa.period_exponent = period_exponent;
+ } else if (oa_attr.oa_timer_exponent) {
+ DRM_ERROR("Sampling exponent specified without requesting periodic sampling");
+ return -EINVAL;
+ }
+
+ ret = alloc_oa_buffer(dev_priv);
+ if (ret)
+ return ret;
+
+ dev_priv->perf.oa.exclusive_event = event;
+
+ /* PRM - observability performance counters:
+ *
+ * OACONTROL, performance counter enable, note:
+ *
+ * "When this bit is set, in order to have coherent counts,
+ * RC6 power state and trunk clock gating must be disabled.
+ * This can be achieved by programming MMIO registers as
+ * 0xA094=0 and 0xA090[31]=1"
+ *
+ * In our case we are expected that taking pm + FORCEWAKE
+ * references will effectively disable RC6.
+ */
+ intel_runtime_pm_get(dev_priv);
+ intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
+
+ dev_priv->perf.oa.ops.enable_metric_set(dev_priv);
+
+ event->destroy = i915_oa_event_destroy;
+ event->enable = i915_oa_event_enable;
+ event->disable = i915_oa_event_disable;
+ event->can_read = i915_oa_can_read;
+ event->wait_unlocked = i915_oa_wait_unlocked;
+ event->poll_wait = i915_oa_poll_wait;
+ event->read = i915_oa_read;
+
+ return 0;
+}
+
+static void gen7_update_specific_hw_ctx_id(struct drm_i915_private *dev_priv,
+ u32 ctx_id)
+{
+ dev_priv->perf.oa.specific_ctx_id = ctx_id;
+ gen7_update_oacontrol(dev_priv);
+}
+
+static void i915_oa_context_pin_notify_locked(struct drm_i915_private *dev_priv,
+ struct intel_context *context)
+{
+ if (i915.enable_execlists ||
+ dev_priv->perf.oa.ops.update_specific_hw_ctx_id == NULL)
+ return;
+
+ if (dev_priv->perf.oa.exclusive_event &&
+ dev_priv->perf.oa.exclusive_event->ctx == context) {
+ struct drm_i915_gem_object *obj =
+ context->legacy_hw_ctx.rcs_state;
+ u32 ctx_id = i915_gem_obj_ggtt_offset(obj);
+
+ dev_priv->perf.oa.ops.update_specific_hw_ctx_id(dev_priv, ctx_id);
+ }
+}
+
+void i915_oa_context_pin_notify(struct drm_i915_private *dev_priv,
+ struct intel_context *context)
+{
+ if (!dev_priv->perf.initialized)
+ return;
+
+ mutex_lock(&dev_priv->perf.lock);
+ i915_oa_context_pin_notify_locked(dev_priv, context);
+ mutex_unlock(&dev_priv->perf.lock);
+}
+
static ssize_t i915_perf_read_locked(struct i915_perf_event *event,
struct file *file,
char __user *buf,
@@ -152,6 +805,20 @@ static ssize_t i915_perf_read(struct file *file,
return ret;
}
+static enum hrtimer_restart poll_check_timer_cb(struct hrtimer *hrtimer)
+{
+ struct drm_i915_private *dev_priv =
+ container_of(hrtimer, typeof(*dev_priv),
+ perf.oa.poll_check_timer);
+
+ if (!dev_priv->perf.oa.ops.oa_buffer_is_empty(dev_priv))
+ wake_up(&dev_priv->perf.oa.poll_wq);
+
+ hrtimer_forward_now(hrtimer, ns_to_ktime(POLL_PERIOD));
+
+ return HRTIMER_RESTART;
+}
+
static unsigned int i915_perf_poll_locked(struct i915_perf_event *event,
struct file *file,
poll_table *wait)
@@ -366,7 +1033,11 @@ int i915_perf_open_ioctl_locked(struct drm_device *dev, void *data,
event->ctx = specific_ctx;
switch (param->type) {
- /* TODO: Init according to specific type */
+ case I915_PERF_OA_EVENT:
+ ret = i915_oa_event_init(event, param);
+ if (ret)
+ goto err_alloc;
+ break;
default:
DRM_ERROR("Unknown perf event type\n");
ret = -EINVAL;
@@ -429,7 +1100,27 @@ void i915_perf_init(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = to_i915(dev);
- /* Currently no global event state to initialize */
+ if (!IS_HASWELL(dev))
+ return;
+
+ hrtimer_init(&dev_priv->perf.oa.poll_check_timer,
+ CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ dev_priv->perf.oa.poll_check_timer.function = poll_check_timer_cb;
+ init_waitqueue_head(&dev_priv->perf.oa.poll_wq);
+
+ INIT_LIST_HEAD(&dev_priv->perf.events);
+ mutex_init(&dev_priv->perf.lock);
+
+ dev_priv->perf.oa.ops.init_oa_buffer = gen7_init_oa_buffer;
+ dev_priv->perf.oa.ops.enable_metric_set = hsw_enable_metric_set;
+ dev_priv->perf.oa.ops.disable_metric_set = hsw_disable_metric_set;
+ dev_priv->perf.oa.ops.oa_enable = gen7_oa_enable;
+ dev_priv->perf.oa.ops.oa_disable = gen7_oa_disable;
+ dev_priv->perf.oa.ops.update_specific_hw_ctx_id = gen7_update_specific_hw_ctx_id;
+ dev_priv->perf.oa.ops.read = gen7_oa_read;
+ dev_priv->perf.oa.ops.oa_buffer_is_empty = gen7_oa_buffer_is_empty;
+
+ dev_priv->perf.oa.oa_formats = hsw_oa_formats;
dev_priv->perf.initialized = true;
}
@@ -441,7 +1132,7 @@ void i915_perf_fini(struct drm_device *dev)
if (!dev_priv->perf.initialized)
return;
- /* Currently nothing to clean up */
+ dev_priv->perf.oa.ops.init_oa_buffer = NULL;
dev_priv->perf.initialized = false;
}
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 2e488e8..0736358 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -537,6 +537,343 @@
#define GEN7_3DPRIM_BASE_VERTEX 0x2440
#define GEN7_OACONTROL 0x2360
+#define GEN7_OACONTROL_CTX_MASK 0xFFFFF000
+#define GEN7_OACONTROL_TIMER_PERIOD_MASK 0x3F
+#define GEN7_OACONTROL_TIMER_PERIOD_SHIFT 6
+#define GEN7_OACONTROL_TIMER_ENABLE (1<<5)
+#define GEN7_OACONTROL_FORMAT_A13 (0<<2)
+#define GEN7_OACONTROL_FORMAT_A29 (1<<2)
+#define GEN7_OACONTROL_FORMAT_A13_B8_C8 (2<<2)
+#define GEN7_OACONTROL_FORMAT_A29_B8_C8 (3<<2)
+#define GEN7_OACONTROL_FORMAT_B4_C8 (4<<2)
+#define GEN7_OACONTROL_FORMAT_A45_B8_C8 (5<<2)
+#define GEN7_OACONTROL_FORMAT_B4_C8_A16 (6<<2)
+#define GEN7_OACONTROL_FORMAT_C4_B8 (7<<2)
+#define GEN7_OACONTROL_FORMAT_SHIFT 2
+#define GEN7_OACONTROL_PER_CTX_ENABLE (1<<1)
+#define GEN7_OACONTROL_ENABLE (1<<0)
+
+#define GEN8_OACTXID 0x2364
+
+#define GEN8_OACONTROL 0x2B00
+#define GEN8_OA_REPORT_FORMAT_A12 (0<<2)
+#define GEN8_OA_REPORT_FORMAT_A12_B8_C8 (2<<2)
+#define GEN8_OA_REPORT_FORMAT_A36_B8_C8 (5<<2)
+#define GEN8_OA_REPORT_FORMAT_C4_B8 (7<<2)
+#define GEN8_OA_REPORT_FORMAT_SHIFT 2
+#define GEN8_OA_SPECIFIC_CONTEXT_ENABLE (1<<1)
+#define GEN8_OA_COUNTER_ENABLE (1<<0)
+
+#define GEN8_OACTXCONTROL 0x2360
+#define GEN8_OA_TIMER_PERIOD_MASK 0x3F
+#define GEN8_OA_TIMER_PERIOD_SHIFT 2
+#define GEN8_OA_TIMER_ENABLE (1<<1)
+#define GEN8_OA_COUNTER_RESUME (1<<0)
+
+#define GEN7_OABUFFER 0x23B0 /* R/W */
+#define GEN7_OABUFFER_OVERRUN_DISABLE (1<<3)
+#define GEN7_OABUFFER_EDGE_TRIGGER (1<<2)
+#define GEN7_OABUFFER_STOP_RESUME_ENABLE (1<<1)
+#define GEN7_OABUFFER_RESUME (1<<0)
+
+#define GEN8_OABUFFER 0x2b14
+
+#define GEN7_OASTATUS1 0x2364
+#define GEN7_OASTATUS1_TAIL_MASK 0xffffffc0
+#define GEN7_OASTATUS1_COUNTER_OVERFLOW (1<<2)
+#define GEN7_OASTATUS1_OABUFFER_OVERFLOW (1<<1)
+#define GEN7_OASTATUS1_REPORT_LOST (1<<0)
+
+#define GEN7_OASTATUS2 0x2368
+#define GEN7_OASTATUS2_HEAD_MASK 0xffffffc0
+
+#define GEN8_OASTATUS 0x2b08
+#define GEN8_OASTATUS_OVERRUN_STATUS (1<<3)
+#define GEN8_OASTATUS_COUNTER_OVERFLOW (1<<2)
+#define GEN8_OASTATUS_OABUFFER_OVERFLOW (1<<1)
+#define GEN8_OASTATUS_REPORT_LOST (1<<0)
+
+#define GEN8_OAHEADPTR 0x2B0C
+#define GEN8_OATAILPTR 0x2B10
+
+#define OABUFFER_SIZE_128K (0<<3)
+#define OABUFFER_SIZE_256K (1<<3)
+#define OABUFFER_SIZE_512K (2<<3)
+#define OABUFFER_SIZE_1M (3<<3)
+#define OABUFFER_SIZE_2M (4<<3)
+#define OABUFFER_SIZE_4M (5<<3)
+#define OABUFFER_SIZE_8M (6<<3)
+#define OABUFFER_SIZE_16M (7<<3)
+
+#define OA_MEM_SELECT_GGTT (1<<0)
+
+#define EU_PERF_CNTL0 0xe458
+
+#define GDT_CHICKEN_BITS 0x9840
+#define GT_NOA_ENABLE 0x00000080
+
+/*
+ * OA Boolean state
+ */
+
+#define OAREPORTTRIG1 0x2740
+#define OAREPORTTRIG1_THRESHOLD_MASK 0xffff
+#define OAREPORTTRIG1_EDGE_LEVEL_TRIGER_SELECT_MASK 0xffff0000 /* 0=level */
+
+#define OAREPORTTRIG2 0x2744
+#define OAREPORTTRIG2_INVERT_A_0 (1<<0)
+#define OAREPORTTRIG2_INVERT_A_1 (1<<1)
+#define OAREPORTTRIG2_INVERT_A_2 (1<<2)
+#define OAREPORTTRIG2_INVERT_A_3 (1<<3)
+#define OAREPORTTRIG2_INVERT_A_4 (1<<4)
+#define OAREPORTTRIG2_INVERT_A_5 (1<<5)
+#define OAREPORTTRIG2_INVERT_A_6 (1<<6)
+#define OAREPORTTRIG2_INVERT_A_7 (1<<7)
+#define OAREPORTTRIG2_INVERT_A_8 (1<<8)
+#define OAREPORTTRIG2_INVERT_A_9 (1<<9)
+#define OAREPORTTRIG2_INVERT_A_10 (1<<10)
+#define OAREPORTTRIG2_INVERT_A_11 (1<<11)
+#define OAREPORTTRIG2_INVERT_A_12 (1<<12)
+#define OAREPORTTRIG2_INVERT_A_13 (1<<13)
+#define OAREPORTTRIG2_INVERT_A_14 (1<<14)
+#define OAREPORTTRIG2_INVERT_A_15 (1<<15)
+#define OAREPORTTRIG2_INVERT_B_0 (1<<16)
+#define OAREPORTTRIG2_INVERT_B_1 (1<<17)
+#define OAREPORTTRIG2_INVERT_B_2 (1<<18)
+#define OAREPORTTRIG2_INVERT_B_3 (1<<19)
+#define OAREPORTTRIG2_INVERT_C_0 (1<<20)
+#define OAREPORTTRIG2_INVERT_C_1 (1<<21)
+#define OAREPORTTRIG2_INVERT_D_0 (1<<22)
+#define OAREPORTTRIG2_THRESHOLD_ENABLE (1<<23)
+#define OAREPORTTRIG2_REPORT_TRIGGER_ENABLE (1<<31)
+
+#define OAREPORTTRIG3 0x2748
+#define OAREPORTTRIG3_NOA_SELECT_MASK 0xf
+#define OAREPORTTRIG3_NOA_SELECT_8_SHIFT 0
+#define OAREPORTTRIG3_NOA_SELECT_9_SHIFT 4
+#define OAREPORTTRIG3_NOA_SELECT_10_SHIFT 8
+#define OAREPORTTRIG3_NOA_SELECT_11_SHIFT 12
+#define OAREPORTTRIG3_NOA_SELECT_12_SHIFT 16
+#define OAREPORTTRIG3_NOA_SELECT_13_SHIFT 20
+#define OAREPORTTRIG3_NOA_SELECT_14_SHIFT 24
+#define OAREPORTTRIG3_NOA_SELECT_15_SHIFT 28
+
+#define OAREPORTTRIG4 0x274c
+#define OAREPORTTRIG4_NOA_SELECT_MASK 0xf
+#define OAREPORTTRIG4_NOA_SELECT_0_SHIFT 0
+#define OAREPORTTRIG4_NOA_SELECT_1_SHIFT 4
+#define OAREPORTTRIG4_NOA_SELECT_2_SHIFT 8
+#define OAREPORTTRIG4_NOA_SELECT_3_SHIFT 12
+#define OAREPORTTRIG4_NOA_SELECT_4_SHIFT 16
+#define OAREPORTTRIG4_NOA_SELECT_5_SHIFT 20
+#define OAREPORTTRIG4_NOA_SELECT_6_SHIFT 24
+#define OAREPORTTRIG4_NOA_SELECT_7_SHIFT 28
+
+#define OAREPORTTRIG5 0x2750
+#define OAREPORTTRIG5_THRESHOLD_MASK 0xffff
+#define OAREPORTTRIG5_EDGE_LEVEL_TRIGER_SELECT_MASK 0xffff0000 /* 0=level */
+
+#define OAREPORTTRIG6 0x2754
+#define OAREPORTTRIG6_INVERT_A_0 (1<<0)
+#define OAREPORTTRIG6_INVERT_A_1 (1<<1)
+#define OAREPORTTRIG6_INVERT_A_2 (1<<2)
+#define OAREPORTTRIG6_INVERT_A_3 (1<<3)
+#define OAREPORTTRIG6_INVERT_A_4 (1<<4)
+#define OAREPORTTRIG6_INVERT_A_5 (1<<5)
+#define OAREPORTTRIG6_INVERT_A_6 (1<<6)
+#define OAREPORTTRIG6_INVERT_A_7 (1<<7)
+#define OAREPORTTRIG6_INVERT_A_8 (1<<8)
+#define OAREPORTTRIG6_INVERT_A_9 (1<<9)
+#define OAREPORTTRIG6_INVERT_A_10 (1<<10)
+#define OAREPORTTRIG6_INVERT_A_11 (1<<11)
+#define OAREPORTTRIG6_INVERT_A_12 (1<<12)
+#define OAREPORTTRIG6_INVERT_A_13 (1<<13)
+#define OAREPORTTRIG6_INVERT_A_14 (1<<14)
+#define OAREPORTTRIG6_INVERT_A_15 (1<<15)
+#define OAREPORTTRIG6_INVERT_B_0 (1<<16)
+#define OAREPORTTRIG6_INVERT_B_1 (1<<17)
+#define OAREPORTTRIG6_INVERT_B_2 (1<<18)
+#define OAREPORTTRIG6_INVERT_B_3 (1<<19)
+#define OAREPORTTRIG6_INVERT_C_0 (1<<20)
+#define OAREPORTTRIG6_INVERT_C_1 (1<<21)
+#define OAREPORTTRIG6_INVERT_D_0 (1<<22)
+#define OAREPORTTRIG6_THRESHOLD_ENABLE (1<<23)
+#define OAREPORTTRIG6_REPORT_TRIGGER_ENABLE (1<<31)
+
+#define OAREPORTTRIG7 0x2758
+#define OAREPORTTRIG7_NOA_SELECT_MASK 0xf
+#define OAREPORTTRIG7_NOA_SELECT_8_SHIFT 0
+#define OAREPORTTRIG7_NOA_SELECT_9_SHIFT 4
+#define OAREPORTTRIG7_NOA_SELECT_10_SHIFT 8
+#define OAREPORTTRIG7_NOA_SELECT_11_SHIFT 12
+#define OAREPORTTRIG7_NOA_SELECT_12_SHIFT 16
+#define OAREPORTTRIG7_NOA_SELECT_13_SHIFT 20
+#define OAREPORTTRIG7_NOA_SELECT_14_SHIFT 24
+#define OAREPORTTRIG7_NOA_SELECT_15_SHIFT 28
+
+#define OAREPORTTRIG8 0x275c
+#define OAREPORTTRIG8_NOA_SELECT_MASK 0xf
+#define OAREPORTTRIG8_NOA_SELECT_0_SHIFT 0
+#define OAREPORTTRIG8_NOA_SELECT_1_SHIFT 4
+#define OAREPORTTRIG8_NOA_SELECT_2_SHIFT 8
+#define OAREPORTTRIG8_NOA_SELECT_3_SHIFT 12
+#define OAREPORTTRIG8_NOA_SELECT_4_SHIFT 16
+#define OAREPORTTRIG8_NOA_SELECT_5_SHIFT 20
+#define OAREPORTTRIG8_NOA_SELECT_6_SHIFT 24
+#define OAREPORTTRIG8_NOA_SELECT_7_SHIFT 28
+
+#define OASTARTTRIG1 0x2710
+#define OASTARTTRIG1_THRESHOLD_COUNT_MASK_MBZ 0xffff0000
+#define OASTARTTRIG1_THRESHOLD_MASK 0xffff
+
+#define OASTARTTRIG2 0x2714
+#define OASTARTTRIG2_INVERT_A_0 (1<<0)
+#define OASTARTTRIG2_INVERT_A_1 (1<<1)
+#define OASTARTTRIG2_INVERT_A_2 (1<<2)
+#define OASTARTTRIG2_INVERT_A_3 (1<<3)
+#define OASTARTTRIG2_INVERT_A_4 (1<<4)
+#define OASTARTTRIG2_INVERT_A_5 (1<<5)
+#define OASTARTTRIG2_INVERT_A_6 (1<<6)
+#define OASTARTTRIG2_INVERT_A_7 (1<<7)
+#define OASTARTTRIG2_INVERT_A_8 (1<<8)
+#define OASTARTTRIG2_INVERT_A_9 (1<<9)
+#define OASTARTTRIG2_INVERT_A_10 (1<<10)
+#define OASTARTTRIG2_INVERT_A_11 (1<<11)
+#define OASTARTTRIG2_INVERT_A_12 (1<<12)
+#define OASTARTTRIG2_INVERT_A_13 (1<<13)
+#define OASTARTTRIG2_INVERT_A_14 (1<<14)
+#define OASTARTTRIG2_INVERT_A_15 (1<<15)
+#define OASTARTTRIG2_INVERT_B_0 (1<<16)
+#define OASTARTTRIG2_INVERT_B_1 (1<<17)
+#define OASTARTTRIG2_INVERT_B_2 (1<<18)
+#define OASTARTTRIG2_INVERT_B_3 (1<<19)
+#define OASTARTTRIG2_INVERT_C_0 (1<<20)
+#define OASTARTTRIG2_INVERT_C_1 (1<<21)
+#define OASTARTTRIG2_INVERT_D_0 (1<<22)
+#define OASTARTTRIG2_THRESHOLD_ENABLE (1<<23)
+#define OASTARTTRIG2_START_TRIG_FLAG_MBZ (1<<24)
+#define OASTARTTRIG2_EVENT_SELECT_0 (1<<28)
+#define OASTARTTRIG2_EVENT_SELECT_1 (1<<29)
+#define OASTARTTRIG2_EVENT_SELECT_2 (1<<30)
+#define OASTARTTRIG2_EVENT_SELECT_3 (1<<31)
+
+#define OASTARTTRIG3 0x2718
+#define OASTARTTRIG3_NOA_SELECT_MASK 0xf
+#define OASTARTTRIG3_NOA_SELECT_8_SHIFT 0
+#define OASTARTTRIG3_NOA_SELECT_9_SHIFT 4
+#define OASTARTTRIG3_NOA_SELECT_10_SHIFT 8
+#define OASTARTTRIG3_NOA_SELECT_11_SHIFT 12
+#define OASTARTTRIG3_NOA_SELECT_12_SHIFT 16
+#define OASTARTTRIG3_NOA_SELECT_13_SHIFT 20
+#define OASTARTTRIG3_NOA_SELECT_14_SHIFT 24
+#define OASTARTTRIG3_NOA_SELECT_15_SHIFT 28
+
+#define OASTARTTRIG4 0x271c
+#define OASTARTTRIG4_NOA_SELECT_MASK 0xf
+#define OASTARTTRIG4_NOA_SELECT_0_SHIFT 0
+#define OASTARTTRIG4_NOA_SELECT_1_SHIFT 4
+#define OASTARTTRIG4_NOA_SELECT_2_SHIFT 8
+#define OASTARTTRIG4_NOA_SELECT_3_SHIFT 12
+#define OASTARTTRIG4_NOA_SELECT_4_SHIFT 16
+#define OASTARTTRIG4_NOA_SELECT_5_SHIFT 20
+#define OASTARTTRIG4_NOA_SELECT_6_SHIFT 24
+#define OASTARTTRIG4_NOA_SELECT_7_SHIFT 28
+
+#define OASTARTTRIG5 0x2720
+#define OASTARTTRIG5_THRESHOLD_COUNT_MASK_MBZ 0xffff0000
+#define OASTARTTRIG5_THRESHOLD_MASK 0xffff
+
+#define OASTARTTRIG6 0x2724
+#define OASTARTTRIG6_INVERT_A_0 (1<<0)
+#define OASTARTTRIG6_INVERT_A_1 (1<<1)
+#define OASTARTTRIG6_INVERT_A_2 (1<<2)
+#define OASTARTTRIG6_INVERT_A_3 (1<<3)
+#define OASTARTTRIG6_INVERT_A_4 (1<<4)
+#define OASTARTTRIG6_INVERT_A_5 (1<<5)
+#define OASTARTTRIG6_INVERT_A_6 (1<<6)
+#define OASTARTTRIG6_INVERT_A_7 (1<<7)
+#define OASTARTTRIG6_INVERT_A_8 (1<<8)
+#define OASTARTTRIG6_INVERT_A_9 (1<<9)
+#define OASTARTTRIG6_INVERT_A_10 (1<<10)
+#define OASTARTTRIG6_INVERT_A_11 (1<<11)
+#define OASTARTTRIG6_INVERT_A_12 (1<<12)
+#define OASTARTTRIG6_INVERT_A_13 (1<<13)
+#define OASTARTTRIG6_INVERT_A_14 (1<<14)
+#define OASTARTTRIG6_INVERT_A_15 (1<<15)
+#define OASTARTTRIG6_INVERT_B_0 (1<<16)
+#define OASTARTTRIG6_INVERT_B_1 (1<<17)
+#define OASTARTTRIG6_INVERT_B_2 (1<<18)
+#define OASTARTTRIG6_INVERT_B_3 (1<<19)
+#define OASTARTTRIG6_INVERT_C_0 (1<<20)
+#define OASTARTTRIG6_INVERT_C_1 (1<<21)
+#define OASTARTTRIG6_INVERT_D_0 (1<<22)
+#define OASTARTTRIG6_THRESHOLD_ENABLE (1<<23)
+#define OASTARTTRIG6_START_TRIG_FLAG_MBZ (1<<24)
+#define OASTARTTRIG6_EVENT_SELECT_4 (1<<28)
+#define OASTARTTRIG6_EVENT_SELECT_5 (1<<29)
+#define OASTARTTRIG6_EVENT_SELECT_6 (1<<30)
+#define OASTARTTRIG6_EVENT_SELECT_7 (1<<31)
+
+#define OASTARTTRIG7 0x2728
+#define OASTARTTRIG7_NOA_SELECT_MASK 0xf
+#define OASTARTTRIG7_NOA_SELECT_8_SHIFT 0
+#define OASTARTTRIG7_NOA_SELECT_9_SHIFT 4
+#define OASTARTTRIG7_NOA_SELECT_10_SHIFT 8
+#define OASTARTTRIG7_NOA_SELECT_11_SHIFT 12
+#define OASTARTTRIG7_NOA_SELECT_12_SHIFT 16
+#define OASTARTTRIG7_NOA_SELECT_13_SHIFT 20
+#define OASTARTTRIG7_NOA_SELECT_14_SHIFT 24
+#define OASTARTTRIG7_NOA_SELECT_15_SHIFT 28
+
+#define OASTARTTRIG8 0x272c
+#define OASTARTTRIG8_NOA_SELECT_MASK 0xf
+#define OASTARTTRIG8_NOA_SELECT_0_SHIFT 0
+#define OASTARTTRIG8_NOA_SELECT_1_SHIFT 4
+#define OASTARTTRIG8_NOA_SELECT_2_SHIFT 8
+#define OASTARTTRIG8_NOA_SELECT_3_SHIFT 12
+#define OASTARTTRIG8_NOA_SELECT_4_SHIFT 16
+#define OASTARTTRIG8_NOA_SELECT_5_SHIFT 20
+#define OASTARTTRIG8_NOA_SELECT_6_SHIFT 24
+#define OASTARTTRIG8_NOA_SELECT_7_SHIFT 28
+
+/* CECX_0 */
+#define OACEC_COMPARE_LESS_OR_EQUAL 6
+#define OACEC_COMPARE_NOT_EQUAL 5
+#define OACEC_COMPARE_LESS_THAN 4
+#define OACEC_COMPARE_GREATER_OR_EQUAL 3
+#define OACEC_COMPARE_EQUAL 2
+#define OACEC_COMPARE_GREATER_THAN 1
+#define OACEC_COMPARE_ANY_EQUAL 0
+
+#define OACEC_COMPARE_VALUE_MASK 0xffff
+#define OACEC_COMPARE_VALUE_SHIFT 3
+
+#define OACEC_SELECT_NOA (0<<19)
+#define OACEC_SELECT_PREV (1<<19)
+#define OACEC_SELECT_BOOLEAN (2<<19)
+
+/* CECX_1 */
+#define OACEC_MASK_MASK 0xffff
+#define OACEC_CONSIDERATIONS_MASK 0xffff
+#define OACEC_CONSIDERATIONS_SHIFT 16
+
+#define OACEC0_0 0x2770
+#define OACEC0_1 0x2774
+#define OACEC1_0 0x2778
+#define OACEC1_1 0x277c
+#define OACEC2_0 0x2780
+#define OACEC2_1 0x2784
+#define OACEC3_0 0x2788
+#define OACEC3_1 0x278c
+#define OACEC4_0 0x2790
+#define OACEC4_1 0x2794
+#define OACEC5_0 0x2798
+#define OACEC5_1 0x279c
+#define OACEC6_0 0x27a0
+#define OACEC6_1 0x27a4
+#define OACEC7_0 0x27a8
+#define OACEC7_1 0x27ac
+
#define _GEN7_PIPEA_DE_LOAD_SL 0x70068
#define _GEN7_PIPEB_DE_LOAD_SL 0x71068
@@ -6668,6 +7005,7 @@ enum skl_disp_power_wells {
# define GEN6_RCCUNIT_CLOCK_GATE_DISABLE (1 << 11)
#define GEN6_UCGCTL3 0x9408
+# define GEN6_OACSUNIT_CLOCK_GATE_DISABLE (1 << 20)
#define GEN7_UCGCTL4 0x940c
#define GEN7_L3BANK2X_CLOCK_GATE_DISABLE (1<<25)
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index a84f71f..af5dfd4 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -58,6 +58,29 @@
#define I915_ERROR_UEVENT "ERROR"
#define I915_RESET_UEVENT "RESET"
+/*
+ * perf events configuration exposed by i915 through
+ * /sys/bus/event_sources/drivers/i915_oa
+ */
+
+enum drm_i915_oa_format {
+ I915_OA_FORMAT_A13 = 0,
+ I915_OA_FORMAT_A29 = 1,
+ I915_OA_FORMAT_A13_B8_C8 = 2,
+ I915_OA_FORMAT_B4_C8 = 4,
+ I915_OA_FORMAT_A45_B8_C8 = 5,
+ I915_OA_FORMAT_B4_C8_A16 = 6,
+ I915_OA_FORMAT_C4_B8 = 7,
+
+ I915_OA_FORMAT_MAX /* non-ABI */
+};
+
+enum drm_i915_oa_set {
+ I915_OA_METRICS_SET_3D = 1,
+
+ I915_OA_METRICS_SET_MAX /* non-ABI */
+};
+
/* Each region is a minimum of 16k, and there are at most 255 of them.
*/
#define I915_NR_TEX_REGIONS 255 /* table size 2k - maximum due to use
@@ -1132,9 +1155,35 @@ struct drm_i915_gem_context_param {
};
enum drm_i915_perf_event_type {
+ I915_PERF_OA_EVENT = 1,
+
I915_PERF_EVENT_TYPE_MAX /* non-ABI */
};
+
+#define I915_OA_FLAG_PERIODIC (1<<0)
+
+struct drm_i915_perf_oa_attr {
+ __u32 size;
+
+ __u32 flags;
+
+ __u32 metrics_set;
+ __u32 oa_format;
+ __u32 oa_timer_exponent;
+};
+
+/* Note: same versioning scheme as struct perf_event_attr
+ *
+ * Userspace specified size defines ABI version and kernel
+ * zero extends to size of latest version. If userspace
+ * gives a larger structure than the kernel expects then
+ * kernel asserts that all unknown fields are zero.
+ */
+#define I915_OA_ATTR_SIZE_VER0 20 /* sizeof first published struct */
+
+
+
#define I915_PERF_FLAG_FD_CLOEXEC (1<<0)
#define I915_PERF_FLAG_FD_NONBLOCK (1<<1)
#define I915_PERF_FLAG_SINGLE_CONTEXT (1<<2)
@@ -1188,6 +1237,20 @@ enum drm_i915_perf_record_type {
*/
DRM_I915_PERF_RECORD_SAMPLE = 1,
+ /*
+ * Indicates that one or more OA reports was not written
+ * by the hardware.
+ */
+ DRM_I915_PERF_RECORD_OA_REPORT_LOST = 2,
+
+ /*
+ * Indicates that the internal circular buffer that Gen
+ * graphics writes OA reports into has filled, which may
+ * either mean that old reports could be overwritten or
+ * subsequent reports lost until the buffer is cleared.
+ */
+ DRM_I915_PERF_RECORD_OA_BUFFER_OVERFLOW = 3,
+
DRM_I915_PERF_RECORD_MAX /* non-ABI */
};
--
2.5.2
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists