* [PATCH 1/6] drm/i915/execlists: Move RPCS setup to context pin
2019-01-15 14:47 [PATCH 0/6] Add uAPI to support ICL VME hardware for new media-driver Joonas Lahtinen
@ 2019-01-15 14:47 ` Joonas Lahtinen
2019-01-15 14:47 ` [PATCH 2/6] drm/i915: Record the sseu configuration per-context & engine Joonas Lahtinen
` (6 subsequent siblings)
7 siblings, 0 replies; 17+ messages in thread
From: Joonas Lahtinen @ 2019-01-15 14:47 UTC (permalink / raw)
To: Intel graphics driver community testing & development
Cc: Jani Nikula, Takashi Iwai, Timo Aaltonen, Carl Zhang, Stephane Marchesin
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Configuring RPCS in context image just before pin is sufficient and will
come extra handy in one of the following patches.
v2:
* Split image setup a bit differently. (Chris Wilson)
v3:
* Update context image after reset as well - otherwise the application
of pinned default state clears the RPCS.
v4:
* Use local variable throughout the function. (Chris Wilson)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Suggested-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
drivers/gpu/drm/i915/intel_lrc.c | 45 ++++++++++++++++++++------------
1 file changed, 28 insertions(+), 17 deletions(-)
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 608458b92db3..24328745a0ea 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1169,6 +1169,24 @@ static int __context_pin(struct i915_gem_context *ctx, struct i915_vma *vma)
return i915_vma_pin(vma, 0, 0, flags);
}
+static u32 make_rpcs(struct drm_i915_private *dev_priv);
+
+static void
+__execlists_update_reg_state(struct intel_engine_cs *engine,
+ struct intel_context *ce)
+{
+ u32 *regs = ce->lrc_reg_state;
+ struct intel_ring *ring = ce->ring;
+
+ regs[CTX_RING_BUFFER_START + 1] = i915_ggtt_offset(ring->vma);
+ regs[CTX_RING_HEAD + 1] = ring->head;
+ regs[CTX_RING_TAIL + 1] = ring->tail;
+
+ /* RPCS */
+ if (engine->class == RENDER_CLASS)
+ regs[CTX_R_PWR_CLK_STATE + 1] = make_rpcs(engine->i915);
+}
+
static struct intel_context *
__execlists_context_pin(struct intel_engine_cs *engine,
struct i915_gem_context *ctx,
@@ -1207,10 +1225,8 @@ __execlists_context_pin(struct intel_engine_cs *engine,
GEM_BUG_ON(!intel_ring_offset_valid(ce->ring, ce->ring->head));
ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE;
- ce->lrc_reg_state[CTX_RING_BUFFER_START+1] =
- i915_ggtt_offset(ce->ring->vma);
- ce->lrc_reg_state[CTX_RING_HEAD + 1] = ce->ring->head;
- ce->lrc_reg_state[CTX_RING_TAIL + 1] = ce->ring->tail;
+
+ __execlists_update_reg_state(engine, ce);
ce->state->obj->pin_global++;
i915_gem_context_get(ctx);
@@ -1834,14 +1850,14 @@ static void execlists_reset(struct intel_engine_cs *engine,
engine->pinned_default_state + LRC_STATE_PN * PAGE_SIZE,
engine->context_size - PAGE_SIZE);
}
- execlists_init_reg_state(regs,
- request->gem_context, engine, request->ring);
/* Move the RING_HEAD onto the breadcrumb, past the hanging batch */
- regs[CTX_RING_BUFFER_START + 1] = i915_ggtt_offset(request->ring->vma);
-
request->ring->head = intel_ring_wrap(request->ring, request->postfix);
- regs[CTX_RING_HEAD + 1] = request->ring->head;
+
+ execlists_init_reg_state(regs, request->gem_context, engine,
+ request->ring);
+
+ __execlists_update_reg_state(engine, request->hw_context);
intel_ring_update_space(request->ring);
@@ -2530,8 +2546,7 @@ static void execlists_init_reg_state(u32 *regs,
if (rcs) {
regs[CTX_LRI_HEADER_2] = MI_LOAD_REGISTER_IMM(1);
- CTX_REG(regs, CTX_R_PWR_CLK_STATE, GEN8_R_PWR_CLK_STATE,
- make_rpcs(dev_priv));
+ CTX_REG(regs, CTX_R_PWR_CLK_STATE, GEN8_R_PWR_CLK_STATE, 0);
i915_oa_init_reg_state(engine, ctx, regs);
}
@@ -2692,12 +2707,8 @@ void intel_lr_context_resume(struct drm_i915_private *i915)
intel_ring_reset(ce->ring, 0);
- if (ce->pin_count) { /* otherwise done in context_pin */
- u32 *regs = ce->lrc_reg_state;
-
- regs[CTX_RING_HEAD + 1] = ce->ring->head;
- regs[CTX_RING_TAIL + 1] = ce->ring->tail;
- }
+ if (ce->pin_count) /* otherwise done in context_pin */
+ __execlists_update_reg_state(engine, ce);
}
}
}
--
2.17.2
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH 2/6] drm/i915: Record the sseu configuration per-context & engine
2019-01-15 14:47 [PATCH 0/6] Add uAPI to support ICL VME hardware for new media-driver Joonas Lahtinen
2019-01-15 14:47 ` [PATCH 1/6] drm/i915/execlists: Move RPCS setup to context pin Joonas Lahtinen
@ 2019-01-15 14:47 ` Joonas Lahtinen
2019-01-15 14:47 ` [PATCH 3/6] drm/i915/perf: lock powergating configuration to default when active Joonas Lahtinen
` (5 subsequent siblings)
7 siblings, 0 replies; 17+ messages in thread
From: Joonas Lahtinen @ 2019-01-15 14:47 UTC (permalink / raw)
To: Intel graphics driver community testing & development
Cc: Jani Nikula, Takashi Iwai, Timo Aaltonen, Carl Zhang, Stephane Marchesin
From: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
We want to expose the ability to reconfigure the slices, subslice and
eu per context and per engine. To facilitate that, store the current
configuration on the context for each engine, which is initially set
to the device default upon creation.
v2: record sseu configuration per context & engine (Chris)
v3: introduce the i915_gem_context_sseu to store powergating
programming, sseu_dev_info has grown quite a bit (Lionel)
v4: rename i915_gem_sseu into intel_sseu (Chris)
use to_intel_context() (Chris)
v5: More to_intel_context() (Tvrtko)
Switch intel_sseu from union to struct (Tvrtko)
Move context default sseu in existing loop (Chris)
v6: s/intel_sseu_from_device_sseu/intel_device_default_sseu/ (Tvrtko)
Tvrtko Ursulin:
v7:
* Pass intel_sseu by pointer instead of value to make_rpcs.
* Rebase for make_rpcs changes.
v8:
* Rebase for RPCS edit on pin.
v9:
* Rebase for context image setup changes.
v10:
* Rename dev_priv to i915. (Chris Wilson)
v11:
* Rebase.
v12:
* Rebase for IS_GEN changes.
v13:
* Rebase for RUNTIME_INFO.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
drivers/gpu/drm/i915/i915_drv.h | 14 +++++++++++
drivers/gpu/drm/i915/i915_gem_context.c | 2 ++
drivers/gpu/drm/i915/i915_gem_context.h | 4 ++++
drivers/gpu/drm/i915/i915_request.h | 10 ++++++++
drivers/gpu/drm/i915/intel_lrc.c | 31 +++++++++++++------------
5 files changed, 46 insertions(+), 15 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 956c1c86f90d..d9120b70d9b4 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3331,6 +3331,20 @@ mkwrite_device_info(struct drm_i915_private *dev_priv)
return (struct intel_device_info *)INTEL_INFO(dev_priv);
}
+static inline struct intel_sseu
+intel_device_default_sseu(struct drm_i915_private *i915)
+{
+ const struct sseu_dev_info *sseu = &RUNTIME_INFO(i915)->sseu;
+ struct intel_sseu value = {
+ .slice_mask = sseu->slice_mask,
+ .subslice_mask = sseu->subslice_mask[0],
+ .min_eus_per_subslice = sseu->max_eus_per_subslice,
+ .max_eus_per_subslice = sseu->max_eus_per_subslice,
+ };
+
+ return value;
+}
+
/* modesetting */
extern void intel_modeset_init_hw(struct drm_device *dev);
extern int intel_modeset_init(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 5933adbe3d99..a182045e3808 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -342,6 +342,8 @@ __create_hw_context(struct drm_i915_private *dev_priv,
struct intel_context *ce = &ctx->__engine[n];
ce->gem_context = ctx;
+ /* Use the whole device by default */
+ ce->sseu = intel_device_default_sseu(dev_priv);
}
INIT_RADIX_TREE(&ctx->handles_vma, GFP_KERNEL);
diff --git a/drivers/gpu/drm/i915/i915_gem_context.h b/drivers/gpu/drm/i915/i915_gem_context.h
index f6d870b1f73e..ef04e422cf9a 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.h
+++ b/drivers/gpu/drm/i915/i915_gem_context.h
@@ -31,6 +31,7 @@
#include "i915_gem.h"
#include "i915_scheduler.h"
+#include "intel_device_info.h"
struct pid;
@@ -171,6 +172,9 @@ struct i915_gem_context {
int pin_count;
const struct intel_context_ops *ops;
+
+ /** sseu: Control eu/slice partitioning */
+ struct intel_sseu sseu;
} __engine[I915_NUM_ENGINES];
/** ring_size: size for allocating the per-engine ring buffer */
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index d014b0605445..907bd8f11aeb 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -38,6 +38,16 @@ struct drm_i915_gem_object;
struct i915_request;
struct i915_timeline;
+/*
+ * Powergating configuration for a particular (context,engine).
+ */
+struct intel_sseu {
+ u8 slice_mask;
+ u8 subslice_mask;
+ u8 min_eus_per_subslice;
+ u8 max_eus_per_subslice;
+};
+
struct intel_wait {
struct rb_node node;
struct task_struct *tsk;
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 24328745a0ea..31bf84b22e61 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1169,7 +1169,8 @@ static int __context_pin(struct i915_gem_context *ctx, struct i915_vma *vma)
return i915_vma_pin(vma, 0, 0, flags);
}
-static u32 make_rpcs(struct drm_i915_private *dev_priv);
+static u32
+make_rpcs(struct drm_i915_private *i915, struct intel_sseu *ctx_sseu);
static void
__execlists_update_reg_state(struct intel_engine_cs *engine,
@@ -1184,7 +1185,8 @@ __execlists_update_reg_state(struct intel_engine_cs *engine,
/* RPCS */
if (engine->class == RENDER_CLASS)
- regs[CTX_R_PWR_CLK_STATE + 1] = make_rpcs(engine->i915);
+ regs[CTX_R_PWR_CLK_STATE + 1] = make_rpcs(engine->i915,
+ &ce->sseu);
}
static struct intel_context *
@@ -2322,18 +2324,19 @@ int logical_xcs_ring_init(struct intel_engine_cs *engine)
}
static u32
-make_rpcs(struct drm_i915_private *dev_priv)
+make_rpcs(struct drm_i915_private *i915, struct intel_sseu *ctx_sseu)
{
- bool subslice_pg = RUNTIME_INFO(dev_priv)->sseu.has_subslice_pg;
- u8 slices = hweight8(RUNTIME_INFO(dev_priv)->sseu.slice_mask);
- u8 subslices = hweight8(RUNTIME_INFO(dev_priv)->sseu.subslice_mask[0]);
+ const struct sseu_dev_info *sseu = &RUNTIME_INFO(i915)->sseu;
+ bool subslice_pg = sseu->has_subslice_pg;
+ u8 slices = hweight8(ctx_sseu->slice_mask);
+ u8 subslices = hweight8(ctx_sseu->subslice_mask);
u32 rpcs = 0;
/*
* No explicit RPCS request is needed to ensure full
* slice/subslice/EU enablement prior to Gen9.
*/
- if (INTEL_GEN(dev_priv) < 9)
+ if (INTEL_GEN(i915) < 9)
return 0;
/*
@@ -2361,7 +2364,7 @@ make_rpcs(struct drm_i915_private *dev_priv)
* subslices are enabled, or a count between one and four on the first
* slice.
*/
- if (IS_GEN(dev_priv, 11) && slices == 1 && subslices >= 4) {
+ if (IS_GEN(i915, 11) && slices == 1 && subslices >= 4) {
GEM_BUG_ON(subslices & 1);
subslice_pg = false;
@@ -2374,10 +2377,10 @@ make_rpcs(struct drm_i915_private *dev_priv)
* must make an explicit request through RPCS for full
* enablement.
*/
- if (RUNTIME_INFO(dev_priv)->sseu.has_slice_pg) {
+ if (sseu->has_slice_pg) {
u32 mask, val = slices;
- if (INTEL_GEN(dev_priv) >= 11) {
+ if (INTEL_GEN(i915) >= 11) {
mask = GEN11_RPCS_S_CNT_MASK;
val <<= GEN11_RPCS_S_CNT_SHIFT;
} else {
@@ -2402,18 +2405,16 @@ make_rpcs(struct drm_i915_private *dev_priv)
rpcs |= GEN8_RPCS_ENABLE | GEN8_RPCS_SS_CNT_ENABLE | val;
}
- if (RUNTIME_INFO(dev_priv)->sseu.has_eu_pg) {
+ if (sseu->has_eu_pg) {
u32 val;
- val = RUNTIME_INFO(dev_priv)->sseu.eu_per_subslice <<
- GEN8_RPCS_EU_MIN_SHIFT;
+ val = ctx_sseu->min_eus_per_subslice << GEN8_RPCS_EU_MIN_SHIFT;
GEM_BUG_ON(val & ~GEN8_RPCS_EU_MIN_MASK);
val &= GEN8_RPCS_EU_MIN_MASK;
rpcs |= val;
- val = RUNTIME_INFO(dev_priv)->sseu.eu_per_subslice <<
- GEN8_RPCS_EU_MAX_SHIFT;
+ val = ctx_sseu->max_eus_per_subslice << GEN8_RPCS_EU_MAX_SHIFT;
GEM_BUG_ON(val & ~GEN8_RPCS_EU_MAX_MASK);
val &= GEN8_RPCS_EU_MAX_MASK;
--
2.17.2
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH 3/6] drm/i915/perf: lock powergating configuration to default when active
2019-01-15 14:47 [PATCH 0/6] Add uAPI to support ICL VME hardware for new media-driver Joonas Lahtinen
2019-01-15 14:47 ` [PATCH 1/6] drm/i915/execlists: Move RPCS setup to context pin Joonas Lahtinen
2019-01-15 14:47 ` [PATCH 2/6] drm/i915: Record the sseu configuration per-context & engine Joonas Lahtinen
@ 2019-01-15 14:47 ` Joonas Lahtinen
2019-01-15 14:47 ` [PATCH 4/6] drm/i915: Add timeline barrier support Joonas Lahtinen
` (4 subsequent siblings)
7 siblings, 0 replies; 17+ messages in thread
From: Joonas Lahtinen @ 2019-01-15 14:47 UTC (permalink / raw)
To: Intel graphics driver community testing & development
Cc: Jani Nikula, Takashi Iwai, Timo Aaltonen, Carl Zhang, Stephane Marchesin
From: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
If some of the contexts submitting workloads to the GPU have been
configured to shutdown slices/subslices, we might loose the NOA
configurations written in the NOA muxes.
One possible solution to this problem is to reprogram the NOA muxes
when we switch to a new context. We initially tried this in the
workaround batchbuffer but some concerns where raised about the cost
of reprogramming at every context switch. This solution is also not
without consequences from the userspace point of view. Reprogramming
of the muxes can only happen once the powergating configuration has
changed (which happens after context switch). This means for a window
of time during the recording, counters recorded by the OA unit might
be invalid. This requires userspace dealing with OA reports to discard
the invalid values.
Minimizing the reprogramming could be implemented by tracking of the
last programmed configuration somewhere in GGTT and use MI_PREDICATE
to discard some of the programming commands, but the command streamer
would still have to parse all the MI_LRI instructions in the
workaround batchbuffer.
Another solution, which this change implements, is to simply disregard
the user requested configuration for the period of time when i915/perf
is active.
On most platforms there are no issues with this apart from a performance
penality for some media workloads that benefit from running on a partially
powergated GPU. We already prevent RC6 from affecting the programming so
it doesn't sound completely unreasonable to hold on powergating for the
same reason.
On Icelake however there would a functional problem if the slices not-
containing the VME block were left enabled with a running media workload
which explicitly disabled them. To avoid a GPU hang in this case, on
Icelake we lock the enablement to only slices which contain VME blocks.
Downside is that it means degraded GPU performance when OA is active but
there is no known alternative solution for this.
v2: Leave RPCS programming in intel_lrc.c (Lionel)
v3: Update for s/union intel_sseu/struct intel_sseu/ (Lionel)
More to_intel_context() (Tvrtko)
s/dev_priv/i915/ (Tvrtko)
Tvrtko Ursulin:
v4:
* Rebase for make_rpcs changes.
v5:
* Apply OA restriction from make_rpcs directly.
v6:
* Rebase for context image setup changes.
v7:
* Move stream assignment before metric enable.
v8-9:
* Rebase.
v10:
* Squashed with ICL support patch.
Bspec: 21140
Co-Developed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> # v9
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
drivers/gpu/drm/i915/i915_perf.c | 13 ++++++---
drivers/gpu/drm/i915/intel_lrc.c | 46 ++++++++++++++++++++++++--------
drivers/gpu/drm/i915/intel_lrc.h | 2 ++
3 files changed, 46 insertions(+), 15 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index faff6cf1aaa1..07170e49ecb3 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1677,6 +1677,11 @@ static void gen8_update_reg_state_unlocked(struct i915_gem_context *ctx,
CTX_REG(reg_state, state_offset, flex_regs[i], value);
}
+
+ CTX_REG(reg_state, CTX_R_PWR_CLK_STATE, GEN8_R_PWR_CLK_STATE,
+ gen8_make_rpcs(dev_priv,
+ &to_intel_context(ctx,
+ dev_priv->engine[RCS])->sseu));
}
/*
@@ -2098,21 +2103,21 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
if (ret)
goto err_lock;
+ stream->ops = &i915_oa_stream_ops;
+ dev_priv->perf.oa.exclusive_stream = stream;
+
ret = dev_priv->perf.oa.ops.enable_metric_set(stream);
if (ret) {
DRM_DEBUG("Unable to enable metric set\n");
goto err_enable;
}
- stream->ops = &i915_oa_stream_ops;
-
- dev_priv->perf.oa.exclusive_stream = stream;
-
mutex_unlock(&dev_priv->drm.struct_mutex);
return 0;
err_enable:
+ dev_priv->perf.oa.exclusive_stream = NULL;
dev_priv->perf.oa.ops.disable_metric_set(dev_priv);
mutex_unlock(&dev_priv->drm.struct_mutex);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 31bf84b22e61..f32be56ec503 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1169,9 +1169,6 @@ static int __context_pin(struct i915_gem_context *ctx, struct i915_vma *vma)
return i915_vma_pin(vma, 0, 0, flags);
}
-static u32
-make_rpcs(struct drm_i915_private *i915, struct intel_sseu *ctx_sseu);
-
static void
__execlists_update_reg_state(struct intel_engine_cs *engine,
struct intel_context *ce)
@@ -1185,8 +1182,8 @@ __execlists_update_reg_state(struct intel_engine_cs *engine,
/* RPCS */
if (engine->class == RENDER_CLASS)
- regs[CTX_R_PWR_CLK_STATE + 1] = make_rpcs(engine->i915,
- &ce->sseu);
+ regs[CTX_R_PWR_CLK_STATE + 1] = gen8_make_rpcs(engine->i915,
+ &ce->sseu);
}
static struct intel_context *
@@ -2323,13 +2320,12 @@ int logical_xcs_ring_init(struct intel_engine_cs *engine)
return logical_ring_init(engine);
}
-static u32
-make_rpcs(struct drm_i915_private *i915, struct intel_sseu *ctx_sseu)
+u32 gen8_make_rpcs(struct drm_i915_private *i915, struct intel_sseu *req_sseu)
{
const struct sseu_dev_info *sseu = &RUNTIME_INFO(i915)->sseu;
bool subslice_pg = sseu->has_subslice_pg;
- u8 slices = hweight8(ctx_sseu->slice_mask);
- u8 subslices = hweight8(ctx_sseu->subslice_mask);
+ struct intel_sseu ctx_sseu;
+ u8 slices, subslices;
u32 rpcs = 0;
/*
@@ -2339,6 +2335,34 @@ make_rpcs(struct drm_i915_private *i915, struct intel_sseu *ctx_sseu)
if (INTEL_GEN(i915) < 9)
return 0;
+ /*
+ * If i915/perf is active, we want a stable powergating configuration
+ * on the system.
+ *
+ * We could choose full enablement, but on ICL we know there are use
+ * cases which disable slices for functional, apart for performance
+ * reasons. So in this case we select a known stable subset.
+ */
+ if (!i915->perf.oa.exclusive_stream) {
+ ctx_sseu = *req_sseu;
+ } else {
+ ctx_sseu = intel_device_default_sseu(i915);
+
+ if (IS_GEN(i915, 11)) {
+ /*
+ * We only need subslice count so it doesn't matter
+ * which ones we select - just turn off low bits in the
+ * amount of half of all available subslices per slice.
+ */
+ ctx_sseu.subslice_mask =
+ ~(~0 << (hweight8(ctx_sseu.subslice_mask) / 2));
+ ctx_sseu.slice_mask = 0x1;
+ }
+ }
+
+ slices = hweight8(ctx_sseu.slice_mask);
+ subslices = hweight8(ctx_sseu.subslice_mask);
+
/*
* Since the SScount bitfield in GEN8_R_PWR_CLK_STATE is only three bits
* wide and Icelake has up to eight subslices, specfial programming is
@@ -2408,13 +2432,13 @@ make_rpcs(struct drm_i915_private *i915, struct intel_sseu *ctx_sseu)
if (sseu->has_eu_pg) {
u32 val;
- val = ctx_sseu->min_eus_per_subslice << GEN8_RPCS_EU_MIN_SHIFT;
+ val = ctx_sseu.min_eus_per_subslice << GEN8_RPCS_EU_MIN_SHIFT;
GEM_BUG_ON(val & ~GEN8_RPCS_EU_MIN_MASK);
val &= GEN8_RPCS_EU_MIN_MASK;
rpcs |= val;
- val = ctx_sseu->max_eus_per_subslice << GEN8_RPCS_EU_MAX_SHIFT;
+ val = ctx_sseu.max_eus_per_subslice << GEN8_RPCS_EU_MAX_SHIFT;
GEM_BUG_ON(val & ~GEN8_RPCS_EU_MAX_MASK);
val &= GEN8_RPCS_EU_MAX_MASK;
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index f5a5502ecf70..a4e28cc55fda 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -104,4 +104,6 @@ void intel_lr_context_resume(struct drm_i915_private *dev_priv);
void intel_execlists_set_default_submission(struct intel_engine_cs *engine);
+u32 gen8_make_rpcs(struct drm_i915_private *i915, struct intel_sseu *ctx_sseu);
+
#endif /* _INTEL_LRC_H_ */
--
2.17.2
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH 4/6] drm/i915: Add timeline barrier support
2019-01-15 14:47 [PATCH 0/6] Add uAPI to support ICL VME hardware for new media-driver Joonas Lahtinen
` (2 preceding siblings ...)
2019-01-15 14:47 ` [PATCH 3/6] drm/i915/perf: lock powergating configuration to default when active Joonas Lahtinen
@ 2019-01-15 14:47 ` Joonas Lahtinen
2019-01-15 14:47 ` [PATCH 5/6] drm/i915: Expose RPCS (SSEU) configuration to userspace (Gen11 only) Joonas Lahtinen
` (3 subsequent siblings)
7 siblings, 0 replies; 17+ messages in thread
From: Joonas Lahtinen @ 2019-01-15 14:47 UTC (permalink / raw)
To: Intel graphics driver community testing & development
Cc: Jani Nikula, Takashi Iwai, Timo Aaltonen, Carl Zhang, Stephane Marchesin
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Timeline barrier allows serialization between different timelines.
After calling i915_timeline_set_barrier with a request, all following
submissions on this timeline will be set up as depending on this request,
or barrier. Once the barrier has been completed it automatically gets
cleared and things continue as normal.
This facility will be used by the upcoming context SSEU code.
v2:
* Assert barrier has been retired on timeline_fini. (Chris Wilson)
* Fix mock_timeline.
v3:
* Improved comment language. (Chris Wilson)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Suggested-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
---
drivers/gpu/drm/i915/i915_request.c | 13 +++++++++
drivers/gpu/drm/i915/i915_timeline.c | 3 +++
drivers/gpu/drm/i915/i915_timeline.h | 27 +++++++++++++++++++
.../gpu/drm/i915/selftests/mock_timeline.c | 2 ++
4 files changed, 45 insertions(+)
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index d1355154886a..496217305a00 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -509,6 +509,15 @@ i915_request_alloc_slow(struct intel_context *ce)
return kmem_cache_alloc(ce->gem_context->i915->requests, GFP_KERNEL);
}
+static int add_timeline_barrier(struct i915_request *rq)
+{
+ struct i915_request *barrier =
+ i915_gem_active_raw(&rq->timeline->barrier,
+ &rq->i915->drm.struct_mutex);
+
+ return barrier ? i915_request_await_dma_fence(rq, &barrier->fence) : 0;
+}
+
/**
* i915_request_alloc - allocate a request structure
*
@@ -652,6 +661,10 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
*/
rq->head = rq->ring->emit;
+ ret = add_timeline_barrier(rq);
+ if (ret)
+ goto err_unwind;
+
ret = engine->request_alloc(rq);
if (ret)
goto err_unwind;
diff --git a/drivers/gpu/drm/i915/i915_timeline.c b/drivers/gpu/drm/i915/i915_timeline.c
index 4667cc08c416..5a87c5bd5154 100644
--- a/drivers/gpu/drm/i915/i915_timeline.c
+++ b/drivers/gpu/drm/i915/i915_timeline.c
@@ -37,6 +37,8 @@ void i915_timeline_init(struct drm_i915_private *i915,
INIT_LIST_HEAD(&timeline->requests);
i915_syncmap_init(&timeline->sync);
+
+ init_request_active(&timeline->barrier, NULL);
}
/**
@@ -69,6 +71,7 @@ void i915_timelines_park(struct drm_i915_private *i915)
void i915_timeline_fini(struct i915_timeline *timeline)
{
GEM_BUG_ON(!list_empty(&timeline->requests));
+ GEM_BUG_ON(i915_gem_active_isset(&timeline->barrier));
i915_syncmap_free(&timeline->sync);
diff --git a/drivers/gpu/drm/i915/i915_timeline.h b/drivers/gpu/drm/i915/i915_timeline.h
index 38c1e15e927a..af6c05333d76 100644
--- a/drivers/gpu/drm/i915/i915_timeline.h
+++ b/drivers/gpu/drm/i915/i915_timeline.h
@@ -64,6 +64,16 @@ struct i915_timeline {
*/
struct i915_syncmap *sync;
+ /**
+ * Barrier provides the ability to serialize ordering between different
+ * timelines.
+ *
+ * Users can call i915_timeline_set_barrier which will make all
+ * subsequent submissions to this timeline be executed only after the
+ * barrier has been completed.
+ */
+ struct i915_gem_active barrier;
+
struct list_head link;
const char *name;
@@ -136,4 +146,21 @@ static inline bool i915_timeline_sync_is_later(struct i915_timeline *tl,
void i915_timelines_park(struct drm_i915_private *i915);
+/**
+ * i915_timeline_set_barrier - orders submission between different timelines
+ * @timeline: timeline to set the barrier on
+ * @rq: request after which new submissions can proceed
+ *
+ * Sets the passed in request as the serialization point for all subsequent
+ * submissions on @timeline. Subsequent requests will not be submitted to GPU
+ * until the barrier has been completed.
+ */
+static inline void
+i915_timeline_set_barrier(struct i915_timeline *timeline,
+ struct i915_request *rq)
+{
+ GEM_BUG_ON(timeline->fence_context == rq->timeline->fence_context);
+ i915_gem_active_set(&timeline->barrier, rq);
+}
+
#endif
diff --git a/drivers/gpu/drm/i915/selftests/mock_timeline.c b/drivers/gpu/drm/i915/selftests/mock_timeline.c
index dcf3b16f5a07..a718b64c988e 100644
--- a/drivers/gpu/drm/i915/selftests/mock_timeline.c
+++ b/drivers/gpu/drm/i915/selftests/mock_timeline.c
@@ -19,6 +19,8 @@ void mock_timeline_init(struct i915_timeline *timeline, u64 context)
i915_syncmap_init(&timeline->sync);
+ init_request_active(&timeline->barrier, NULL);
+
INIT_LIST_HEAD(&timeline->link);
}
--
2.17.2
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH 5/6] drm/i915: Expose RPCS (SSEU) configuration to userspace (Gen11 only)
2019-01-15 14:47 [PATCH 0/6] Add uAPI to support ICL VME hardware for new media-driver Joonas Lahtinen
` (3 preceding siblings ...)
2019-01-15 14:47 ` [PATCH 4/6] drm/i915: Add timeline barrier support Joonas Lahtinen
@ 2019-01-15 14:47 ` Joonas Lahtinen
2019-01-21 12:56 ` Timo Aaltonen
2019-01-21 21:33 ` Takashi Iwai
2019-01-15 14:47 ` [PATCH 6/6] drm/i915/selftests: Context SSEU reconfiguration tests Joonas Lahtinen
` (2 subsequent siblings)
7 siblings, 2 replies; 17+ messages in thread
From: Joonas Lahtinen @ 2019-01-15 14:47 UTC (permalink / raw)
To: Intel graphics driver community testing & development
Cc: Jani Nikula, Takashi Iwai, Timo Aaltonen, Carl Zhang, Stephane Marchesin
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
We want to allow userspace to reconfigure the subslice configuration on a
per context basis.
This is required for the functional requirement of shutting down non-VME
enabled sub-slices on Gen11 parts.
To do so, we expose a context parameter to allow adjustment of the RPCS
register stored within the context image (and currently not accessible via
LRI).
If the context is adjusted before first use or whilst idle, the adjustment
is for "free"; otherwise if the context is active we queue a request to do
so (using the kernel context), following all other activity by that
context, which is also marked as barrier for all following submission
against the same context.
Since the overhead of device re-configuration during context switching can
be significant, especially in multi-context workloads, we limit this new
uAPI to only support the Gen11 VME use case. In this use case either the
device is fully enabled, and exactly one slice and half of the subslices
are enabled.
Example usage:
struct drm_i915_gem_context_param_sseu sseu = { };
struct drm_i915_gem_context_param arg =
{ .param = I915_CONTEXT_PARAM_SSEU,
.ctx_id = gem_context_create(fd),
.size = sizeof(sseu),
.value = to_user_pointer(&sseu)
};
/* Query device defaults. */
gem_context_get_param(fd, &arg);
/* Set VME configuration on a 1x6x8 part. */
sseu.slice_mask = 0x1;
sseu.subslice_mask = 0xe0;
gem_context_set_param(fd, &arg);
v2: Fix offset of CTX_R_PWR_CLK_STATE in intel_lr_context_set_sseu() (Lionel)
v3: Add ability to program this per engine (Chris)
v4: Move most get_sseu() into i915_gem_context.c (Lionel)
v5: Validate sseu configuration against the device's capabilities (Lionel)
v6: Change context powergating settings through MI_SDM on kernel context (Chris)
v7: Synchronize the requests following a powergating setting change using a global
dependency (Chris)
Iterate timelines through dev_priv.gt.active_rings (Tvrtko)
Disable RPCS configuration setting for non capable users (Lionel/Tvrtko)
v8: s/union intel_sseu/struct intel_sseu/ (Lionel)
s/dev_priv/i915/ (Tvrtko)
Change uapi class/instance fields to u16 (Tvrtko)
Bump mask fields to 64bits (Lionel)
Don't return EPERM when dynamic sseu is disabled (Tvrtko)
v9: Import context image into kernel context's ppgtt only when
reconfiguring powergated slice/subslices (Chris)
Use aliasing ppgtt when needed (Michel)
Tvrtko Ursulin:
v10:
* Update for upstream changes.
* Request submit needs a RPM reference.
* Reject on !FULL_PPGTT for simplicity.
* Pull out get/set param to helpers for readability and less indent.
* Use i915_request_await_dma_fence in add_global_barrier to skip waits
on the same timeline and avoid GEM_BUG_ON.
* No need to explicitly assign a NULL pointer to engine in legacy mode.
* No need to move gen8_make_rpcs up.
* Factored out global barrier as prep patch.
* Allow to only CAP_SYS_ADMIN if !Gen11.
v11:
* Remove engine vfunc in favour of local helper. (Chris Wilson)
* Stop retiring requests before updates since it is not needed
(Chris Wilson)
* Implement direct CPU update path for idle contexts. (Chris Wilson)
* Left side dependency needs only be on the same context timeline.
(Chris Wilson)
* It is sufficient to order the timeline. (Chris Wilson)
* Reject !RCS configuration attempts with -ENODEV for now.
v12:
* Rebase for make_rpcs.
v13:
* Centralize SSEU normalization to make_rpcs.
* Type width checking (uAPI <-> implementation).
* Gen11 restrictions uAPI checks.
* Gen11 subslice count differences handling.
Chris Wilson:
* args->size handling fixes.
* Update context image from GGTT.
* Postpone context image update to pinning.
* Use i915_gem_active_raw instead of last_request_on_engine.
v14:
* Add activity tracker on intel_context to fix the lifetime issues
and simplify the code. (Chris Wilson)
v15:
* Fix context pin leak if no space in ring by simplifying the
context pinning sequence.
v16:
* Rebase for context get/set param locking changes.
* Just -ENODEV on !Gen11. (Joonas)
v17:
* Fix one Gen11 subslice enablement rule.
* Handle error from i915_sw_fence_await_sw_fence_gfp. (Chris Wilson)
v18:
* Update commit message. (Joonas)
* Restrict uAPI to VME use case. (Joonas)
v19:
* Rebase.
v20:
* Rebase for ce->active_tracker.
v21:
* Rebase for IS_GEN changes.
v22:
* Reserve uAPI for flags straight away. (Chris Wilson)
v23:
* Rebase for RUNTIME_INFO.
v24:
* Added some headline docs for the uapi usage. (Joonas/Chris)
v25:
* Renamed class/instance to engine_class/engine_instance to avoid clash
with C++ keyword. (Tony Ye)
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=100899
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107634
Issue: https://github.com/intel/media-driver/issues/267
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Zhipeng Gong <zhipeng.gong@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Tony Ye <tony.ye@intel.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> # v21
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
drivers/gpu/drm/i915/i915_gem_context.c | 341 +++++++++++++++++++++++-
drivers/gpu/drm/i915/i915_gem_context.h | 6 +
drivers/gpu/drm/i915/intel_lrc.c | 4 +-
include/uapi/drm/i915_drm.h | 64 +++++
4 files changed, 412 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index a182045e3808..f65d3e9089b6 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -89,6 +89,7 @@
#include <drm/i915_drm.h>
#include "i915_drv.h"
#include "i915_trace.h"
+#include "intel_lrc_reg.h"
#include "intel_workarounds.h"
#define ALL_L3_SLICES(dev) (1 << NUM_L3_SLICES(dev)) - 1
@@ -321,6 +322,15 @@ static u32 default_desc_template(const struct drm_i915_private *i915,
return desc;
}
+static void intel_context_retire(struct i915_gem_active *active,
+ struct i915_request *rq)
+{
+ struct intel_context *ce =
+ container_of(active, typeof(*ce), active_tracker);
+
+ intel_context_unpin(ce);
+}
+
static struct i915_gem_context *
__create_hw_context(struct drm_i915_private *dev_priv,
struct drm_i915_file_private *file_priv)
@@ -344,6 +354,8 @@ __create_hw_context(struct drm_i915_private *dev_priv,
ce->gem_context = ctx;
/* Use the whole device by default */
ce->sseu = intel_device_default_sseu(dev_priv);
+
+ init_request_active(&ce->active_tracker, intel_context_retire);
}
INIT_RADIX_TREE(&ctx->handles_vma, GFP_KERNEL);
@@ -841,6 +853,56 @@ int i915_gem_context_destroy_ioctl(struct drm_device *dev, void *data,
return 0;
}
+static int get_sseu(struct i915_gem_context *ctx,
+ struct drm_i915_gem_context_param *args)
+{
+ struct drm_i915_gem_context_param_sseu user_sseu;
+ struct intel_engine_cs *engine;
+ struct intel_context *ce;
+ int ret;
+
+ if (args->size == 0)
+ goto out;
+ else if (args->size < sizeof(user_sseu))
+ return -EINVAL;
+
+ if (copy_from_user(&user_sseu, u64_to_user_ptr(args->value),
+ sizeof(user_sseu)))
+ return -EFAULT;
+
+ if (user_sseu.flags || user_sseu.rsvd)
+ return -EINVAL;
+
+ engine = intel_engine_lookup_user(ctx->i915,
+ user_sseu.engine_class,
+ user_sseu.engine_instance);
+ if (!engine)
+ return -EINVAL;
+
+ /* Only use for mutex here is to serialize get_param and set_param. */
+ ret = mutex_lock_interruptible(&ctx->i915->drm.struct_mutex);
+ if (ret)
+ return ret;
+
+ ce = to_intel_context(ctx, engine);
+
+ user_sseu.slice_mask = ce->sseu.slice_mask;
+ user_sseu.subslice_mask = ce->sseu.subslice_mask;
+ user_sseu.min_eus_per_subslice = ce->sseu.min_eus_per_subslice;
+ user_sseu.max_eus_per_subslice = ce->sseu.max_eus_per_subslice;
+
+ mutex_unlock(&ctx->i915->drm.struct_mutex);
+
+ if (copy_to_user(u64_to_user_ptr(args->value), &user_sseu,
+ sizeof(user_sseu)))
+ return -EFAULT;
+
+out:
+ args->size = sizeof(user_sseu);
+
+ return 0;
+}
+
int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
struct drm_file *file)
{
@@ -853,15 +915,17 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
if (!ctx)
return -ENOENT;
- args->size = 0;
switch (args->param) {
case I915_CONTEXT_PARAM_BAN_PERIOD:
ret = -EINVAL;
break;
case I915_CONTEXT_PARAM_NO_ZEROMAP:
+ args->size = 0;
args->value = test_bit(UCONTEXT_NO_ZEROMAP, &ctx->user_flags);
break;
case I915_CONTEXT_PARAM_GTT_SIZE:
+ args->size = 0;
+
if (ctx->ppgtt)
args->value = ctx->ppgtt->vm.total;
else if (to_i915(dev)->mm.aliasing_ppgtt)
@@ -870,14 +934,20 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
args->value = to_i915(dev)->ggtt.vm.total;
break;
case I915_CONTEXT_PARAM_NO_ERROR_CAPTURE:
+ args->size = 0;
args->value = i915_gem_context_no_error_capture(ctx);
break;
case I915_CONTEXT_PARAM_BANNABLE:
+ args->size = 0;
args->value = i915_gem_context_is_bannable(ctx);
break;
case I915_CONTEXT_PARAM_PRIORITY:
+ args->size = 0;
args->value = ctx->sched.priority >> I915_USER_PRIORITY_SHIFT;
break;
+ case I915_CONTEXT_PARAM_SSEU:
+ ret = get_sseu(ctx, args);
+ break;
default:
ret = -EINVAL;
break;
@@ -887,6 +957,271 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
return ret;
}
+static int gen8_emit_rpcs_config(struct i915_request *rq,
+ struct intel_context *ce,
+ struct intel_sseu sseu)
+{
+ u64 offset;
+ u32 *cs;
+
+ cs = intel_ring_begin(rq, 4);
+ if (IS_ERR(cs))
+ return PTR_ERR(cs);
+
+ offset = ce->state->node.start +
+ LRC_STATE_PN * PAGE_SIZE +
+ (CTX_R_PWR_CLK_STATE + 1) * 4;
+
+ *cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
+ *cs++ = lower_32_bits(offset);
+ *cs++ = upper_32_bits(offset);
+ *cs++ = gen8_make_rpcs(rq->i915, &sseu);
+
+ intel_ring_advance(rq, cs);
+
+ return 0;
+}
+
+static int
+gen8_modify_rpcs_gpu(struct intel_context *ce,
+ struct intel_engine_cs *engine,
+ struct intel_sseu sseu)
+{
+ struct drm_i915_private *i915 = engine->i915;
+ struct i915_request *rq, *prev;
+ int ret;
+
+ GEM_BUG_ON(!ce->pin_count);
+
+ lockdep_assert_held(&i915->drm.struct_mutex);
+
+ /* Submitting requests etc needs the hw awake. */
+ intel_runtime_pm_get(i915);
+
+ rq = i915_request_alloc(engine, i915->kernel_context);
+ if (IS_ERR(rq)) {
+ ret = PTR_ERR(rq);
+ goto out_put;
+ }
+
+ /* Queue this switch after all other activity by this context. */
+ prev = i915_gem_active_raw(&ce->ring->timeline->last_request,
+ &i915->drm.struct_mutex);
+ if (prev && !i915_request_completed(prev)) {
+ ret = i915_sw_fence_await_sw_fence_gfp(&rq->submit,
+ &prev->submit,
+ I915_FENCE_GFP);
+ if (ret < 0)
+ goto out_add;
+ }
+
+ ret = gen8_emit_rpcs_config(rq, ce, sseu);
+ if (ret)
+ goto out_add;
+
+ /* Order all following requests to be after. */
+ i915_timeline_set_barrier(ce->ring->timeline, rq);
+
+ /*
+ * Guarantee context image and the timeline remains pinned until the
+ * modifying request is retired by setting the ce activity tracker.
+ *
+ * But we only need to take one pin on the account of it. Or in other
+ * words transfer the pinned ce object to tracked active request.
+ */
+ if (!i915_gem_active_isset(&ce->active_tracker))
+ __intel_context_pin(ce);
+ i915_gem_active_set(&ce->active_tracker, rq);
+
+out_add:
+ i915_request_add(rq);
+out_put:
+ intel_runtime_pm_put(i915);
+
+ return ret;
+}
+
+static int
+i915_gem_context_reconfigure_sseu(struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine,
+ struct intel_sseu sseu)
+{
+ struct intel_context *ce = to_intel_context(ctx, engine);
+ int ret;
+
+ GEM_BUG_ON(INTEL_GEN(ctx->i915) < 8);
+ GEM_BUG_ON(engine->id != RCS);
+
+ ret = mutex_lock_interruptible(&ctx->i915->drm.struct_mutex);
+ if (ret)
+ return ret;
+
+ /* Nothing to do if unmodified. */
+ if (!memcmp(&ce->sseu, &sseu, sizeof(sseu)))
+ goto out;
+
+ /*
+ * If context is not idle we have to submit an ordered request to modify
+ * its context image via the kernel context. Pristine and idle contexts
+ * will be configured on pinning.
+ */
+ if (ce->pin_count)
+ ret = gen8_modify_rpcs_gpu(ce, engine, sseu);
+
+ if (!ret)
+ ce->sseu = sseu;
+
+out:
+ mutex_unlock(&ctx->i915->drm.struct_mutex);
+
+ return ret;
+}
+
+static int
+user_to_context_sseu(struct drm_i915_private *i915,
+ const struct drm_i915_gem_context_param_sseu *user,
+ struct intel_sseu *context)
+{
+ const struct sseu_dev_info *device = &RUNTIME_INFO(i915)->sseu;
+
+ /* No zeros in any field. */
+ if (!user->slice_mask || !user->subslice_mask ||
+ !user->min_eus_per_subslice || !user->max_eus_per_subslice)
+ return -EINVAL;
+
+ /* Max > min. */
+ if (user->max_eus_per_subslice < user->min_eus_per_subslice)
+ return -EINVAL;
+
+ /* Check validity against hardware. */
+ if (user->slice_mask & ~device->slice_mask)
+ return -EINVAL;
+
+ if (user->subslice_mask & ~device->subslice_mask[0])
+ return -EINVAL;
+
+ if (user->max_eus_per_subslice > device->max_eus_per_subslice)
+ return -EINVAL;
+
+ /*
+ * Some future proofing on the types since the uAPI is wider than the
+ * current internal implementation.
+ */
+ if (WARN_ON((fls(user->slice_mask) >
+ sizeof(context->slice_mask) * BITS_PER_BYTE) ||
+ (fls(user->subslice_mask) >
+ sizeof(context->subslice_mask) * BITS_PER_BYTE) ||
+ overflows_type(user->min_eus_per_subslice,
+ context->min_eus_per_subslice) ||
+ overflows_type(user->max_eus_per_subslice,
+ context->max_eus_per_subslice)))
+ return -EINVAL;
+
+ context->slice_mask = user->slice_mask;
+ context->subslice_mask = user->subslice_mask;
+ context->min_eus_per_subslice = user->min_eus_per_subslice;
+ context->max_eus_per_subslice = user->max_eus_per_subslice;
+
+ /* Part specific restrictions. */
+ if (IS_GEN(i915, 11)) {
+ unsigned int hw_s = hweight8(device->slice_mask);
+ unsigned int hw_ss_per_s = hweight8(device->subslice_mask[0]);
+ unsigned int req_s = hweight8(context->slice_mask);
+ unsigned int req_ss = hweight8(context->subslice_mask);
+
+ /*
+ * Only full subslice enablement is possible if more than one
+ * slice is turned on.
+ */
+ if (req_s > 1 && req_ss != hw_ss_per_s)
+ return -EINVAL;
+
+ /*
+ * If more than four (SScount bitfield limit) subslices are
+ * requested then the number has to be even.
+ */
+ if (req_ss > 4 && (req_ss & 1))
+ return -EINVAL;
+
+ /*
+ * If only one slice is enabled and subslice count is below the
+ * device full enablement, it must be at most half of the all
+ * available subslices.
+ */
+ if (req_s == 1 && req_ss < hw_ss_per_s &&
+ req_ss > (hw_ss_per_s / 2))
+ return -EINVAL;
+
+ /* ABI restriction - VME use case only. */
+
+ /* All slices or one slice only. */
+ if (req_s != 1 && req_s != hw_s)
+ return -EINVAL;
+
+ /*
+ * Half subslices or full enablement only when one slice is
+ * enabled.
+ */
+ if (req_s == 1 &&
+ (req_ss != hw_ss_per_s && req_ss != (hw_ss_per_s / 2)))
+ return -EINVAL;
+
+ /* No EU configuration changes. */
+ if ((user->min_eus_per_subslice !=
+ device->max_eus_per_subslice) ||
+ (user->max_eus_per_subslice !=
+ device->max_eus_per_subslice))
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int set_sseu(struct i915_gem_context *ctx,
+ struct drm_i915_gem_context_param *args)
+{
+ struct drm_i915_private *i915 = ctx->i915;
+ struct drm_i915_gem_context_param_sseu user_sseu;
+ struct intel_engine_cs *engine;
+ struct intel_sseu sseu;
+ int ret;
+
+ if (args->size < sizeof(user_sseu))
+ return -EINVAL;
+
+ if (!IS_GEN(i915, 11))
+ return -ENODEV;
+
+ if (copy_from_user(&user_sseu, u64_to_user_ptr(args->value),
+ sizeof(user_sseu)))
+ return -EFAULT;
+
+ if (user_sseu.flags || user_sseu.rsvd)
+ return -EINVAL;
+
+ engine = intel_engine_lookup_user(i915,
+ user_sseu.engine_class,
+ user_sseu.engine_instance);
+ if (!engine)
+ return -EINVAL;
+
+ /* Only render engine supports RPCS configuration. */
+ if (engine->class != RENDER_CLASS)
+ return -ENODEV;
+
+ ret = user_to_context_sseu(i915, &user_sseu, &sseu);
+ if (ret)
+ return ret;
+
+ ret = i915_gem_context_reconfigure_sseu(ctx, engine, sseu);
+ if (ret)
+ return ret;
+
+ args->size = sizeof(user_sseu);
+
+ return 0;
+}
+
int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data,
struct drm_file *file)
{
@@ -949,7 +1284,9 @@ int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data,
I915_USER_PRIORITY(priority);
}
break;
-
+ case I915_CONTEXT_PARAM_SSEU:
+ ret = set_sseu(ctx, args);
+ break;
default:
ret = -EINVAL;
break;
diff --git a/drivers/gpu/drm/i915/i915_gem_context.h b/drivers/gpu/drm/i915/i915_gem_context.h
index ef04e422cf9a..2ded4b8c9b9f 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.h
+++ b/drivers/gpu/drm/i915/i915_gem_context.h
@@ -171,6 +171,12 @@ struct i915_gem_context {
u64 lrc_desc;
int pin_count;
+ /**
+ * active_tracker: Active tracker for the external rq activity
+ * on this intel_context object.
+ */
+ struct i915_gem_active active_tracker;
+
const struct intel_context_ops *ops;
/** sseu: Control eu/slice partitioning */
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index f32be56ec503..c75115132dee 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -2388,7 +2388,9 @@ u32 gen8_make_rpcs(struct drm_i915_private *i915, struct intel_sseu *req_sseu)
* subslices are enabled, or a count between one and four on the first
* slice.
*/
- if (IS_GEN(i915, 11) && slices == 1 && subslices >= 4) {
+ if (IS_GEN(i915, 11) &&
+ slices == 1 &&
+ subslices > min_t(u8, 4, hweight8(sseu->subslice_mask[0]) / 2)) {
GEM_BUG_ON(subslices & 1);
subslice_pg = false;
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 298b2e197744..397810fa2d33 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -1486,9 +1486,73 @@ struct drm_i915_gem_context_param {
#define I915_CONTEXT_MAX_USER_PRIORITY 1023 /* inclusive */
#define I915_CONTEXT_DEFAULT_PRIORITY 0
#define I915_CONTEXT_MIN_USER_PRIORITY -1023 /* inclusive */
+ /*
+ * When using the following param, value should be a pointer to
+ * drm_i915_gem_context_param_sseu.
+ */
+#define I915_CONTEXT_PARAM_SSEU 0x7
__u64 value;
};
+/**
+ * Context SSEU programming
+ *
+ * It may be necessary for either functional or performance reason to configure
+ * a context to run with a reduced number of SSEU (where SSEU stands for Slice/
+ * Sub-slice/EU).
+ *
+ * This is done by configuring SSEU configuration using the below
+ * @struct drm_i915_gem_context_param_sseu for every supported engine which
+ * userspace intends to use.
+ *
+ * Not all GPUs or engines support this functionality in which case an error
+ * code -ENODEV will be returned.
+ *
+ * Also, flexibility of possible SSEU configuration permutations varies between
+ * GPU generations and software imposed limitations. Requesting such a
+ * combination will return an error code of -EINVAL.
+ *
+ * NOTE: When perf/OA is active the context's SSEU configuration is ignored in
+ * favour of a single global setting.
+ */
+struct drm_i915_gem_context_param_sseu {
+ /*
+ * Engine class & instance to be configured or queried.
+ */
+ __u16 engine_class;
+ __u16 engine_instance;
+
+ /*
+ * Unused for now. Must be cleared to zero.
+ */
+ __u32 flags;
+
+ /*
+ * Mask of slices to enable for the context. Valid values are a subset
+ * of the bitmask value returned for I915_PARAM_SLICE_MASK.
+ */
+ __u64 slice_mask;
+
+ /*
+ * Mask of subslices to enable for the context. Valid values are a
+ * subset of the bitmask value return by I915_PARAM_SUBSLICE_MASK.
+ */
+ __u64 subslice_mask;
+
+ /*
+ * Minimum/Maximum number of EUs to enable per subslice for the
+ * context. min_eus_per_subslice must be inferior or equal to
+ * max_eus_per_subslice.
+ */
+ __u16 min_eus_per_subslice;
+ __u16 max_eus_per_subslice;
+
+ /*
+ * Unused for now. Must be cleared to zero.
+ */
+ __u32 rsvd;
+};
+
enum drm_i915_oa_format {
I915_OA_FORMAT_A13 = 1, /* HSW only */
I915_OA_FORMAT_A29, /* HSW only */
--
2.17.2
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 17+ messages in thread* Re: [PATCH 5/6] drm/i915: Expose RPCS (SSEU) configuration to userspace (Gen11 only)
2019-01-15 14:47 ` [PATCH 5/6] drm/i915: Expose RPCS (SSEU) configuration to userspace (Gen11 only) Joonas Lahtinen
@ 2019-01-21 12:56 ` Timo Aaltonen
2019-01-21 21:33 ` Takashi Iwai
1 sibling, 0 replies; 17+ messages in thread
From: Timo Aaltonen @ 2019-01-21 12:56 UTC (permalink / raw)
To: Joonas Lahtinen,
Intel graphics driver community testing & development
Cc: Jani Nikula, Takashi Iwai, Carl Zhang, Stephane Marchesin
On 15.1.2019 16.47, Joonas Lahtinen wrote:
> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
>
> We want to allow userspace to reconfigure the subslice configuration on a
> per context basis.
>
> This is required for the functional requirement of shutting down non-VME
> enabled sub-slices on Gen11 parts.
>
> To do so, we expose a context parameter to allow adjustment of the RPCS
> register stored within the context image (and currently not accessible via
> LRI).
>
> If the context is adjusted before first use or whilst idle, the adjustment
> is for "free"; otherwise if the context is active we queue a request to do
> so (using the kernel context), following all other activity by that
> context, which is also marked as barrier for all following submission
> against the same context.
>
> Since the overhead of device re-configuration during context switching can
> be significant, especially in multi-context workloads, we limit this new
> uAPI to only support the Gen11 VME use case. In this use case either the
> device is fully enabled, and exactly one slice and half of the subslices
> are enabled.
>
> Example usage:
>
> struct drm_i915_gem_context_param_sseu sseu = { };
> struct drm_i915_gem_context_param arg =
> { .param = I915_CONTEXT_PARAM_SSEU,
> .ctx_id = gem_context_create(fd),
> .size = sizeof(sseu),
> .value = to_user_pointer(&sseu)
> };
>
> /* Query device defaults. */
> gem_context_get_param(fd, &arg);
>
> /* Set VME configuration on a 1x6x8 part. */
> sseu.slice_mask = 0x1;
> sseu.subslice_mask = 0xe0;
> gem_context_set_param(fd, &arg);
>
> v2: Fix offset of CTX_R_PWR_CLK_STATE in intel_lr_context_set_sseu() (Lionel)
>
> v3: Add ability to program this per engine (Chris)
>
> v4: Move most get_sseu() into i915_gem_context.c (Lionel)
>
> v5: Validate sseu configuration against the device's capabilities (Lionel)
>
> v6: Change context powergating settings through MI_SDM on kernel context (Chris)
>
> v7: Synchronize the requests following a powergating setting change using a global
> dependency (Chris)
> Iterate timelines through dev_priv.gt.active_rings (Tvrtko)
> Disable RPCS configuration setting for non capable users (Lionel/Tvrtko)
>
> v8: s/union intel_sseu/struct intel_sseu/ (Lionel)
> s/dev_priv/i915/ (Tvrtko)
> Change uapi class/instance fields to u16 (Tvrtko)
> Bump mask fields to 64bits (Lionel)
> Don't return EPERM when dynamic sseu is disabled (Tvrtko)
>
> v9: Import context image into kernel context's ppgtt only when
> reconfiguring powergated slice/subslices (Chris)
> Use aliasing ppgtt when needed (Michel)
>
> Tvrtko Ursulin:
>
> v10:
> * Update for upstream changes.
> * Request submit needs a RPM reference.
> * Reject on !FULL_PPGTT for simplicity.
> * Pull out get/set param to helpers for readability and less indent.
> * Use i915_request_await_dma_fence in add_global_barrier to skip waits
> on the same timeline and avoid GEM_BUG_ON.
> * No need to explicitly assign a NULL pointer to engine in legacy mode.
> * No need to move gen8_make_rpcs up.
> * Factored out global barrier as prep patch.
> * Allow to only CAP_SYS_ADMIN if !Gen11.
>
> v11:
> * Remove engine vfunc in favour of local helper. (Chris Wilson)
> * Stop retiring requests before updates since it is not needed
> (Chris Wilson)
> * Implement direct CPU update path for idle contexts. (Chris Wilson)
> * Left side dependency needs only be on the same context timeline.
> (Chris Wilson)
> * It is sufficient to order the timeline. (Chris Wilson)
> * Reject !RCS configuration attempts with -ENODEV for now.
>
> v12:
> * Rebase for make_rpcs.
>
> v13:
> * Centralize SSEU normalization to make_rpcs.
> * Type width checking (uAPI <-> implementation).
> * Gen11 restrictions uAPI checks.
> * Gen11 subslice count differences handling.
> Chris Wilson:
> * args->size handling fixes.
> * Update context image from GGTT.
> * Postpone context image update to pinning.
> * Use i915_gem_active_raw instead of last_request_on_engine.
>
> v14:
> * Add activity tracker on intel_context to fix the lifetime issues
> and simplify the code. (Chris Wilson)
>
> v15:
> * Fix context pin leak if no space in ring by simplifying the
> context pinning sequence.
>
> v16:
> * Rebase for context get/set param locking changes.
> * Just -ENODEV on !Gen11. (Joonas)
>
> v17:
> * Fix one Gen11 subslice enablement rule.
> * Handle error from i915_sw_fence_await_sw_fence_gfp. (Chris Wilson)
>
> v18:
> * Update commit message. (Joonas)
> * Restrict uAPI to VME use case. (Joonas)
>
> v19:
> * Rebase.
>
> v20:
> * Rebase for ce->active_tracker.
>
> v21:
> * Rebase for IS_GEN changes.
>
> v22:
> * Reserve uAPI for flags straight away. (Chris Wilson)
>
> v23:
> * Rebase for RUNTIME_INFO.
>
> v24:
> * Added some headline docs for the uapi usage. (Joonas/Chris)
>
> v25:
> * Renamed class/instance to engine_class/engine_instance to avoid clash
> with C++ keyword. (Tony Ye)
>
> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=100899
> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107634
> Issue: https://github.com/intel/media-driver/issues/267
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com>
> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
> Cc: Zhipeng Gong <zhipeng.gong@intel.com>
> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
> Cc: Tony Ye <tony.ye@intel.com>
> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> # v21
> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Hi, we're targeting the new media driver to be included in the next
Ubuntu release (19.04), so
Acked-by: Timo Aaltonen <timo.aaltonen@canonical.com>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 17+ messages in thread* Re: [PATCH 5/6] drm/i915: Expose RPCS (SSEU) configuration to userspace (Gen11 only)
2019-01-15 14:47 ` [PATCH 5/6] drm/i915: Expose RPCS (SSEU) configuration to userspace (Gen11 only) Joonas Lahtinen
2019-01-21 12:56 ` Timo Aaltonen
@ 2019-01-21 21:33 ` Takashi Iwai
1 sibling, 0 replies; 17+ messages in thread
From: Takashi Iwai @ 2019-01-21 21:33 UTC (permalink / raw)
To: Joonas Lahtinen
Cc: Jani Nikula, Takashi Iwai,
Intel graphics driver community testing & development,
Timo Aaltonen, Carl Zhang, Stephane Marchesin
On Tue, 15 Jan 2019 15:47:32 +0100,
Joonas Lahtinen wrote:
>
> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
>
> We want to allow userspace to reconfigure the subslice configuration on a
> per context basis.
>
> This is required for the functional requirement of shutting down non-VME
> enabled sub-slices on Gen11 parts.
>
> To do so, we expose a context parameter to allow adjustment of the RPCS
> register stored within the context image (and currently not accessible via
> LRI).
>
> If the context is adjusted before first use or whilst idle, the adjustment
> is for "free"; otherwise if the context is active we queue a request to do
> so (using the kernel context), following all other activity by that
> context, which is also marked as barrier for all following submission
> against the same context.
>
> Since the overhead of device re-configuration during context switching can
> be significant, especially in multi-context workloads, we limit this new
> uAPI to only support the Gen11 VME use case. In this use case either the
> device is fully enabled, and exactly one slice and half of the subslices
> are enabled.
>
> Example usage:
>
> struct drm_i915_gem_context_param_sseu sseu = { };
> struct drm_i915_gem_context_param arg =
> { .param = I915_CONTEXT_PARAM_SSEU,
> .ctx_id = gem_context_create(fd),
> .size = sizeof(sseu),
> .value = to_user_pointer(&sseu)
> };
>
> /* Query device defaults. */
> gem_context_get_param(fd, &arg);
>
> /* Set VME configuration on a 1x6x8 part. */
> sseu.slice_mask = 0x1;
> sseu.subslice_mask = 0xe0;
> gem_context_set_param(fd, &arg);
>
> v2: Fix offset of CTX_R_PWR_CLK_STATE in intel_lr_context_set_sseu() (Lionel)
>
> v3: Add ability to program this per engine (Chris)
>
> v4: Move most get_sseu() into i915_gem_context.c (Lionel)
>
> v5: Validate sseu configuration against the device's capabilities (Lionel)
>
> v6: Change context powergating settings through MI_SDM on kernel context (Chris)
>
> v7: Synchronize the requests following a powergating setting change using a global
> dependency (Chris)
> Iterate timelines through dev_priv.gt.active_rings (Tvrtko)
> Disable RPCS configuration setting for non capable users (Lionel/Tvrtko)
>
> v8: s/union intel_sseu/struct intel_sseu/ (Lionel)
> s/dev_priv/i915/ (Tvrtko)
> Change uapi class/instance fields to u16 (Tvrtko)
> Bump mask fields to 64bits (Lionel)
> Don't return EPERM when dynamic sseu is disabled (Tvrtko)
>
> v9: Import context image into kernel context's ppgtt only when
> reconfiguring powergated slice/subslices (Chris)
> Use aliasing ppgtt when needed (Michel)
>
> Tvrtko Ursulin:
>
> v10:
> * Update for upstream changes.
> * Request submit needs a RPM reference.
> * Reject on !FULL_PPGTT for simplicity.
> * Pull out get/set param to helpers for readability and less indent.
> * Use i915_request_await_dma_fence in add_global_barrier to skip waits
> on the same timeline and avoid GEM_BUG_ON.
> * No need to explicitly assign a NULL pointer to engine in legacy mode.
> * No need to move gen8_make_rpcs up.
> * Factored out global barrier as prep patch.
> * Allow to only CAP_SYS_ADMIN if !Gen11.
>
> v11:
> * Remove engine vfunc in favour of local helper. (Chris Wilson)
> * Stop retiring requests before updates since it is not needed
> (Chris Wilson)
> * Implement direct CPU update path for idle contexts. (Chris Wilson)
> * Left side dependency needs only be on the same context timeline.
> (Chris Wilson)
> * It is sufficient to order the timeline. (Chris Wilson)
> * Reject !RCS configuration attempts with -ENODEV for now.
>
> v12:
> * Rebase for make_rpcs.
>
> v13:
> * Centralize SSEU normalization to make_rpcs.
> * Type width checking (uAPI <-> implementation).
> * Gen11 restrictions uAPI checks.
> * Gen11 subslice count differences handling.
> Chris Wilson:
> * args->size handling fixes.
> * Update context image from GGTT.
> * Postpone context image update to pinning.
> * Use i915_gem_active_raw instead of last_request_on_engine.
>
> v14:
> * Add activity tracker on intel_context to fix the lifetime issues
> and simplify the code. (Chris Wilson)
>
> v15:
> * Fix context pin leak if no space in ring by simplifying the
> context pinning sequence.
>
> v16:
> * Rebase for context get/set param locking changes.
> * Just -ENODEV on !Gen11. (Joonas)
>
> v17:
> * Fix one Gen11 subslice enablement rule.
> * Handle error from i915_sw_fence_await_sw_fence_gfp. (Chris Wilson)
>
> v18:
> * Update commit message. (Joonas)
> * Restrict uAPI to VME use case. (Joonas)
>
> v19:
> * Rebase.
>
> v20:
> * Rebase for ce->active_tracker.
>
> v21:
> * Rebase for IS_GEN changes.
>
> v22:
> * Reserve uAPI for flags straight away. (Chris Wilson)
>
> v23:
> * Rebase for RUNTIME_INFO.
>
> v24:
> * Added some headline docs for the uapi usage. (Joonas/Chris)
>
> v25:
> * Renamed class/instance to engine_class/engine_instance to avoid clash
> with C++ keyword. (Tony Ye)
>
> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=100899
> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107634
> Issue: https://github.com/intel/media-driver/issues/267
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com>
> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
> Cc: Zhipeng Gong <zhipeng.gong@intel.com>
> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
> Cc: Tony Ye <tony.ye@intel.com>
> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> # v21
> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
The change looks good to me.
Feel free to take my ack
Acked-by: Takashi Iwai <tiwai@suse.de>
thanks,
Takashi
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 17+ messages in thread
* [PATCH 6/6] drm/i915/selftests: Context SSEU reconfiguration tests
2019-01-15 14:47 [PATCH 0/6] Add uAPI to support ICL VME hardware for new media-driver Joonas Lahtinen
` (4 preceding siblings ...)
2019-01-15 14:47 ` [PATCH 5/6] drm/i915: Expose RPCS (SSEU) configuration to userspace (Gen11 only) Joonas Lahtinen
@ 2019-01-15 14:47 ` Joonas Lahtinen
2019-01-15 15:57 ` ✗ Fi.CI.BAT: failure for Add uAPI to support ICL VME hardware for new media-driver Patchwork
2019-02-04 8:57 ` [PATCH 0/6] " Joonas Lahtinen
7 siblings, 0 replies; 17+ messages in thread
From: Joonas Lahtinen @ 2019-01-15 14:47 UTC (permalink / raw)
To: Intel graphics driver community testing & development
Cc: Jani Nikula, Takashi Iwai, Timo Aaltonen, Carl Zhang, Stephane Marchesin
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Exercise the context image reconfiguration logic for idle and busy
contexts, with the resets thrown into the mix as well.
Free from the uAPI restrictions this test runs on all Gen9+ platforms
with slice power gating.
v2:
* Rename some helpers for clarity.
* Include subtest names in error logs.
* Remove unnecessary function export.
v3:
* Rebase for RUNTIME_INFO.
v4:
* Fix incomplete unexport from v2. (Chris Wilson)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
drivers/gpu/drm/i915/i915_gem_context.c | 31 +-
.../gpu/drm/i915/selftests/i915_gem_context.c | 481 ++++++++++++++++++
2 files changed, 502 insertions(+), 10 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index f65d3e9089b6..0444cfa96cf5 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -1042,23 +1042,19 @@ gen8_modify_rpcs_gpu(struct intel_context *ce,
}
static int
-i915_gem_context_reconfigure_sseu(struct i915_gem_context *ctx,
- struct intel_engine_cs *engine,
- struct intel_sseu sseu)
+__i915_gem_context_reconfigure_sseu(struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine,
+ struct intel_sseu sseu)
{
struct intel_context *ce = to_intel_context(ctx, engine);
- int ret;
+ int ret = 0;
GEM_BUG_ON(INTEL_GEN(ctx->i915) < 8);
GEM_BUG_ON(engine->id != RCS);
- ret = mutex_lock_interruptible(&ctx->i915->drm.struct_mutex);
- if (ret)
- return ret;
-
/* Nothing to do if unmodified. */
if (!memcmp(&ce->sseu, &sseu, sizeof(sseu)))
- goto out;
+ return 0;
/*
* If context is not idle we have to submit an ordered request to modify
@@ -1071,7 +1067,22 @@ i915_gem_context_reconfigure_sseu(struct i915_gem_context *ctx,
if (!ret)
ce->sseu = sseu;
-out:
+ return ret;
+}
+
+static int
+i915_gem_context_reconfigure_sseu(struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine,
+ struct intel_sseu sseu)
+{
+ int ret;
+
+ ret = mutex_lock_interruptible(&ctx->i915->drm.struct_mutex);
+ if (ret)
+ return ret;
+
+ ret = __i915_gem_context_reconfigure_sseu(ctx, engine, sseu);
+
mutex_unlock(&ctx->i915->drm.struct_mutex);
return ret;
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index 4cba50679607..91ceacd81de6 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -27,6 +27,8 @@
#include "../i915_selftest.h"
#include "i915_random.h"
#include "igt_flush_test.h"
+#include "igt_reset.h"
+#include "igt_spinner.h"
#include "mock_drm.h"
#include "mock_gem_device.h"
@@ -653,6 +655,484 @@ static int igt_ctx_exec(void *arg)
return err;
}
+static struct i915_vma *rpcs_query_batch(struct i915_vma *vma)
+{
+ struct drm_i915_gem_object *obj;
+ u32 *cmd;
+ int err;
+
+ if (INTEL_GEN(vma->vm->i915) < 8)
+ return ERR_PTR(-EINVAL);
+
+ obj = i915_gem_object_create_internal(vma->vm->i915, PAGE_SIZE);
+ if (IS_ERR(obj))
+ return ERR_CAST(obj);
+
+ cmd = i915_gem_object_pin_map(obj, I915_MAP_WB);
+ if (IS_ERR(cmd)) {
+ err = PTR_ERR(cmd);
+ goto err;
+ }
+
+ *cmd++ = MI_STORE_REGISTER_MEM_GEN8;
+ *cmd++ = i915_mmio_reg_offset(GEN8_R_PWR_CLK_STATE);
+ *cmd++ = lower_32_bits(vma->node.start);
+ *cmd++ = upper_32_bits(vma->node.start);
+ *cmd = MI_BATCH_BUFFER_END;
+
+ i915_gem_object_unpin_map(obj);
+
+ err = i915_gem_object_set_to_gtt_domain(obj, false);
+ if (err)
+ goto err;
+
+ vma = i915_vma_instance(obj, vma->vm, NULL);
+ if (IS_ERR(vma)) {
+ err = PTR_ERR(vma);
+ goto err;
+ }
+
+ err = i915_vma_pin(vma, 0, 0, PIN_USER);
+ if (err)
+ goto err;
+
+ return vma;
+
+err:
+ i915_gem_object_put(obj);
+ return ERR_PTR(err);
+}
+
+static int
+emit_rpcs_query(struct drm_i915_gem_object *obj,
+ struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine,
+ struct i915_request **rq_out)
+{
+ struct i915_address_space *vm;
+ struct i915_request *rq;
+ struct i915_vma *batch;
+ struct i915_vma *vma;
+ int err;
+
+ GEM_BUG_ON(!ctx->ppgtt);
+ GEM_BUG_ON(!intel_engine_can_store_dword(engine));
+
+ vm = &ctx->ppgtt->vm;
+
+ vma = i915_vma_instance(obj, vm, NULL);
+ if (IS_ERR(vma))
+ return PTR_ERR(vma);
+
+ err = i915_gem_object_set_to_gtt_domain(obj, false);
+ if (err)
+ return err;
+
+ err = i915_vma_pin(vma, 0, 0, PIN_HIGH | PIN_USER);
+ if (err)
+ return err;
+
+ batch = rpcs_query_batch(vma);
+ if (IS_ERR(batch)) {
+ err = PTR_ERR(batch);
+ goto err_vma;
+ }
+
+ rq = i915_request_alloc(engine, ctx);
+ if (IS_ERR(rq)) {
+ err = PTR_ERR(rq);
+ goto err_batch;
+ }
+
+ err = engine->emit_bb_start(rq, batch->node.start, batch->node.size, 0);
+ if (err)
+ goto err_request;
+
+ err = i915_vma_move_to_active(batch, rq, 0);
+ if (err)
+ goto skip_request;
+
+ err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+ if (err)
+ goto skip_request;
+
+ i915_gem_object_set_active_reference(batch->obj);
+ i915_vma_unpin(batch);
+ i915_vma_close(batch);
+
+ i915_vma_unpin(vma);
+
+ *rq_out = i915_request_get(rq);
+
+ i915_request_add(rq);
+
+ return 0;
+
+skip_request:
+ i915_request_skip(rq, err);
+err_request:
+ i915_request_add(rq);
+err_batch:
+ i915_vma_unpin(batch);
+err_vma:
+ i915_vma_unpin(vma);
+
+ return err;
+}
+
+#define TEST_IDLE (1 << 0)
+#define TEST_BUSY (1 << 1)
+#define TEST_RESET (1 << 2)
+
+static int
+__sseu_prepare(struct drm_i915_private *i915,
+ const char *name,
+ unsigned int flags,
+ struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine,
+ struct igt_spinner **spin_out)
+{
+ int ret = 0;
+
+ if (flags & (TEST_BUSY | TEST_RESET)) {
+ struct igt_spinner *spin;
+ struct i915_request *rq;
+
+ spin = kzalloc(sizeof(*spin), GFP_KERNEL);
+ if (!spin) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ ret = igt_spinner_init(spin, i915);
+ if (ret)
+ return ret;
+
+ rq = igt_spinner_create_request(spin, ctx, engine, MI_NOOP);
+ if (IS_ERR(rq)) {
+ ret = PTR_ERR(rq);
+ igt_spinner_fini(spin);
+ kfree(spin);
+ goto out;
+ }
+
+ i915_request_add(rq);
+
+ if (!igt_wait_for_spinner(spin, rq)) {
+ pr_err("%s: Spinner failed to start!\n", name);
+ igt_spinner_end(spin);
+ igt_spinner_fini(spin);
+ kfree(spin);
+ ret = -ETIMEDOUT;
+ goto out;
+ }
+
+ *spin_out = spin;
+ }
+
+out:
+ return ret;
+}
+
+static int
+__read_slice_count(struct drm_i915_private *i915,
+ struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine,
+ struct drm_i915_gem_object *obj,
+ struct igt_spinner *spin,
+ u32 *rpcs)
+{
+ struct i915_request *rq = NULL;
+ u32 s_mask, s_shift;
+ unsigned int cnt;
+ u32 *buf, val;
+ long ret;
+
+ ret = emit_rpcs_query(obj, ctx, engine, &rq);
+ if (ret)
+ return ret;
+
+ if (spin)
+ igt_spinner_end(spin);
+
+ ret = i915_request_wait(rq, I915_WAIT_LOCKED, MAX_SCHEDULE_TIMEOUT);
+ if (ret <= 0)
+ return ret < 0 ? ret : -ETIME;
+
+ i915_request_put(rq);
+
+ buf = i915_gem_object_pin_map(obj, I915_MAP_WB);
+ if (IS_ERR(buf)) {
+ ret = PTR_ERR(buf);
+ return ret;
+ }
+
+ if (INTEL_GEN(i915) >= 11) {
+ s_mask = GEN11_RPCS_S_CNT_MASK;
+ s_shift = GEN11_RPCS_S_CNT_SHIFT;
+ } else {
+ s_mask = GEN8_RPCS_S_CNT_MASK;
+ s_shift = GEN8_RPCS_S_CNT_SHIFT;
+ }
+
+ val = *buf;
+ cnt = (val & s_mask) >> s_shift;
+ *rpcs = val;
+
+ i915_gem_object_unpin_map(obj);
+
+ return cnt;
+}
+
+static void __err_rpcs(u32 rpcs, unsigned int slices)
+{
+ pr_info("RPCS=0x%x; %u%sx%u%s\n",
+ rpcs, slices,
+ (rpcs & GEN8_RPCS_S_CNT_ENABLE) ? "*" : "",
+ (rpcs & GEN8_RPCS_SS_CNT_MASK) >> GEN8_RPCS_SS_CNT_SHIFT,
+ (rpcs & GEN8_RPCS_SS_CNT_ENABLE) ? "*" : "");
+}
+
+static int
+__sseu_finish(struct drm_i915_private *i915,
+ const char *name,
+ unsigned int flags,
+ struct i915_gem_context *ctx,
+ struct i915_gem_context *kctx,
+ struct intel_engine_cs *engine,
+ struct drm_i915_gem_object *obj,
+ unsigned int expected,
+ struct igt_spinner *spin)
+{
+ unsigned int slices =
+ hweight32(intel_device_default_sseu(i915).slice_mask);
+ u32 rpcs = 0;
+ int ret = 0;
+
+ if (flags & TEST_RESET) {
+ ret = i915_reset_engine(engine, "sseu");
+ if (ret)
+ goto out;
+ }
+
+ ret = __read_slice_count(i915, ctx, engine, obj,
+ flags & TEST_RESET ? NULL : spin, &rpcs);
+ if (ret < 0) {
+ goto out;
+ } else if (ret != expected) {
+ pr_err("%s: Context slice count %d is not %u!\n",
+ name, ret, expected);
+ __err_rpcs(rpcs, ret);
+ ret = -EINVAL;
+ goto out;
+ } else {
+ ret = 0;
+ }
+
+ ret = __read_slice_count(i915, kctx, engine, obj, NULL, &rpcs);
+ if (ret < 0) {
+ goto out;
+ } else if (ret != slices) {
+ pr_err("%s: Kernel context slice count %d is not %u!\n",
+ name, ret, slices);
+ __err_rpcs(rpcs, ret);
+ ret = -EINVAL;
+ goto out;
+ } else {
+ ret = 0;
+ }
+
+out:
+ if (spin)
+ igt_spinner_end(spin);
+
+ if (flags & TEST_IDLE) {
+ ret = i915_gem_wait_for_idle(i915,
+ I915_WAIT_LOCKED,
+ MAX_SCHEDULE_TIMEOUT);
+ if (ret)
+ return ret;
+
+ ret = __read_slice_count(i915, ctx, engine, obj, NULL, &rpcs);
+ if (ret < 0) {
+ return ret;
+ } else if (ret != expected) {
+ pr_err("%s: Context slice count %d is not %u after idle!\n",
+ name, ret, expected);
+ __err_rpcs(rpcs, ret);
+ return -EINVAL;
+ } else {
+ ret = 0;
+ }
+ }
+
+ return ret;
+
+}
+
+static int
+__sseu_test(struct drm_i915_private *i915,
+ const char *name,
+ unsigned int flags,
+ struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine,
+ struct drm_i915_gem_object *obj,
+ struct intel_sseu sseu)
+{
+ struct igt_spinner *spin = NULL;
+ struct i915_gem_context *kctx;
+ int ret;
+
+ kctx = kernel_context(i915);
+ if (IS_ERR(kctx))
+ return PTR_ERR(kctx);
+
+ ret = __sseu_prepare(i915, name, flags, ctx, engine, &spin);
+ if (ret)
+ goto out;
+
+ ret = __i915_gem_context_reconfigure_sseu(ctx, engine, sseu);
+ if (ret)
+ goto out;
+
+ ret = __sseu_finish(i915, name, flags, ctx, kctx, engine, obj,
+ hweight32(sseu.slice_mask), spin);
+
+out:
+ if (spin) {
+ igt_spinner_end(spin);
+ igt_spinner_fini(spin);
+ kfree(spin);
+ }
+
+ kernel_context_close(kctx);
+
+ return ret;
+}
+
+static int
+__igt_ctx_sseu(struct drm_i915_private *i915,
+ const char *name,
+ unsigned int flags)
+{
+ struct intel_sseu default_sseu = intel_device_default_sseu(i915);
+ struct intel_engine_cs *engine = i915->engine[RCS];
+ struct drm_i915_gem_object *obj;
+ struct i915_gem_context *ctx;
+ struct intel_sseu pg_sseu;
+ struct drm_file *file;
+ int ret;
+
+ if (INTEL_GEN(i915) < 9)
+ return 0;
+
+ if (!RUNTIME_INFO(i915)->sseu.has_slice_pg)
+ return 0;
+
+ if (hweight32(default_sseu.slice_mask) < 2)
+ return 0;
+
+ /*
+ * Gen11 VME friendly power-gated configuration with half enabled
+ * sub-slices.
+ */
+ pg_sseu = default_sseu;
+ pg_sseu.slice_mask = 1;
+ pg_sseu.subslice_mask =
+ ~(~0 << (hweight32(default_sseu.subslice_mask) / 2));
+
+ pr_info("SSEU subtest '%s', flags=%x, def_slices=%u, pg_slices=%u\n",
+ name, flags, hweight32(default_sseu.slice_mask),
+ hweight32(pg_sseu.slice_mask));
+
+ file = mock_file(i915);
+ if (IS_ERR(file))
+ return PTR_ERR(file);
+
+ if (flags & TEST_RESET)
+ igt_global_reset_lock(i915);
+
+ mutex_lock(&i915->drm.struct_mutex);
+
+ ctx = i915_gem_create_context(i915, file->driver_priv);
+ if (IS_ERR(ctx)) {
+ ret = PTR_ERR(ctx);
+ goto out_unlock;
+ }
+
+ obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
+ if (IS_ERR(obj)) {
+ ret = PTR_ERR(obj);
+ goto out_unlock;
+ }
+
+ intel_runtime_pm_get(i915);
+
+ /* First set the default mask. */
+ ret = __sseu_test(i915, name, flags, ctx, engine, obj, default_sseu);
+ if (ret)
+ goto out_fail;
+
+ /* Then set a power-gated configuration. */
+ ret = __sseu_test(i915, name, flags, ctx, engine, obj, pg_sseu);
+ if (ret)
+ goto out_fail;
+
+ /* Back to defaults. */
+ ret = __sseu_test(i915, name, flags, ctx, engine, obj, default_sseu);
+ if (ret)
+ goto out_fail;
+
+ /* One last power-gated configuration for the road. */
+ ret = __sseu_test(i915, name, flags, ctx, engine, obj, pg_sseu);
+ if (ret)
+ goto out_fail;
+
+out_fail:
+ if (igt_flush_test(i915, I915_WAIT_LOCKED))
+ ret = -EIO;
+
+ i915_gem_object_put(obj);
+
+ intel_runtime_pm_put(i915);
+
+out_unlock:
+ mutex_unlock(&i915->drm.struct_mutex);
+
+ if (flags & TEST_RESET)
+ igt_global_reset_unlock(i915);
+
+ mock_file_free(i915, file);
+
+ if (ret)
+ pr_err("%s: Failed with %d!\n", name, ret);
+
+ return ret;
+}
+
+static int igt_ctx_sseu(void *arg)
+{
+ struct {
+ const char *name;
+ unsigned int flags;
+ } *phase, phases[] = {
+ { .name = "basic", .flags = 0 },
+ { .name = "idle", .flags = TEST_IDLE },
+ { .name = "busy", .flags = TEST_BUSY },
+ { .name = "busy-reset", .flags = TEST_BUSY | TEST_RESET },
+ { .name = "busy-idle", .flags = TEST_BUSY | TEST_IDLE },
+ { .name = "reset-idle", .flags = TEST_RESET | TEST_IDLE },
+ };
+ unsigned int i;
+ int ret = 0;
+
+ for (i = 0, phase = phases; ret == 0 && i < ARRAY_SIZE(phases);
+ i++, phase++)
+ ret = __igt_ctx_sseu(arg, phase->name, phase->flags);
+
+ return ret;
+}
+
static int igt_ctx_readonly(void *arg)
{
struct drm_i915_private *i915 = arg;
@@ -1239,6 +1719,7 @@ int i915_gem_context_live_selftests(struct drm_i915_private *dev_priv)
SUBTEST(live_nop_switch),
SUBTEST(igt_ctx_exec),
SUBTEST(igt_ctx_readonly),
+ SUBTEST(igt_ctx_sseu),
SUBTEST(igt_vm_isolation),
};
--
2.17.2
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 17+ messages in thread* ✗ Fi.CI.BAT: failure for Add uAPI to support ICL VME hardware for new media-driver
2019-01-15 14:47 [PATCH 0/6] Add uAPI to support ICL VME hardware for new media-driver Joonas Lahtinen
` (5 preceding siblings ...)
2019-01-15 14:47 ` [PATCH 6/6] drm/i915/selftests: Context SSEU reconfiguration tests Joonas Lahtinen
@ 2019-01-15 15:57 ` Patchwork
2019-02-04 8:57 ` [PATCH 0/6] " Joonas Lahtinen
7 siblings, 0 replies; 17+ messages in thread
From: Patchwork @ 2019-01-15 15:57 UTC (permalink / raw)
To: Joonas Lahtinen; +Cc: intel-gfx
== Series Details ==
Series: Add uAPI to support ICL VME hardware for new media-driver
URL : https://patchwork.freedesktop.org/series/55249/
State : failure
== Summary ==
CALL scripts/checksyscalls.sh
DESCEND objtool
CHK include/generated/compile.h
CC [M] drivers/gpu/drm/i915/i915_gem_context.o
drivers/gpu/drm/i915/i915_gem_context.c: In function ‘gen8_modify_rpcs_gpu’:
drivers/gpu/drm/i915/i915_gem_context.c:1039:2: error: too few arguments to function ‘intel_runtime_pm_put’
intel_runtime_pm_put(i915);
^~~~~~~~~~~~~~~~~~~~
In file included from drivers/gpu/drm/i915/i915_trace.h:10:0,
from drivers/gpu/drm/i915/i915_drv.h:2577,
from drivers/gpu/drm/i915/i915_gem_context.c:90:
drivers/gpu/drm/i915/intel_drv.h:2208:6: note: declared here
void intel_runtime_pm_put(struct drm_i915_private *i915, intel_wakeref_t wref);
^~~~~~~~~~~~~~~~~~~~
In file included from drivers/gpu/drm/i915/i915_gem_context.c:1377:0:
drivers/gpu/drm/i915/selftests/i915_gem_context.c: In function ‘__igt_ctx_sseu’:
drivers/gpu/drm/i915/selftests/i915_gem_context.c:1097:2: error: too few arguments to function ‘intel_runtime_pm_put’
intel_runtime_pm_put(i915);
^~~~~~~~~~~~~~~~~~~~
In file included from drivers/gpu/drm/i915/i915_trace.h:10:0,
from drivers/gpu/drm/i915/i915_drv.h:2577,
from drivers/gpu/drm/i915/i915_gem_context.c:90:
drivers/gpu/drm/i915/intel_drv.h:2208:6: note: declared here
void intel_runtime_pm_put(struct drm_i915_private *i915, intel_wakeref_t wref);
^~~~~~~~~~~~~~~~~~~~
scripts/Makefile.build:276: recipe for target 'drivers/gpu/drm/i915/i915_gem_context.o' failed
make[4]: *** [drivers/gpu/drm/i915/i915_gem_context.o] Error 1
scripts/Makefile.build:492: recipe for target 'drivers/gpu/drm/i915' failed
make[3]: *** [drivers/gpu/drm/i915] Error 2
scripts/Makefile.build:492: recipe for target 'drivers/gpu/drm' failed
make[2]: *** [drivers/gpu/drm] Error 2
scripts/Makefile.build:492: recipe for target 'drivers/gpu' failed
make[1]: *** [drivers/gpu] Error 2
Makefile:1042: recipe for target 'drivers' failed
make: *** [drivers] Error 2
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 17+ messages in thread* Re: [PATCH 0/6] Add uAPI to support ICL VME hardware for new media-driver
2019-01-15 14:47 [PATCH 0/6] Add uAPI to support ICL VME hardware for new media-driver Joonas Lahtinen
` (6 preceding siblings ...)
2019-01-15 15:57 ` ✗ Fi.CI.BAT: failure for Add uAPI to support ICL VME hardware for new media-driver Patchwork
@ 2019-02-04 8:57 ` Joonas Lahtinen
2019-02-04 9:07 ` Daniel Vetter
7 siblings, 1 reply; 17+ messages in thread
From: Joonas Lahtinen @ 2019-02-04 8:57 UTC (permalink / raw)
To: Intel graphics driver community testing & development
Cc: Jani Nikula, Timo Aaltonen, dri-devel, Carl Zhang, Rodrigo Vivi,
Dave Airlie
Quoting Joonas Lahtinen (2019-01-15 16:47:27)
> Hi all,
>
> I would like to have some Acked-by's from you, the distro media
> folks Cc'd here, to document your intent to start using Intel's
> new media driver[1]. So if you recognize yourself (or are otherwise
> interested), please read on.
>
> TL;DR Distro folks, please give your Acked-by on patch [5/6]
A gentle reminder, I'm still looking to hear back from Stephane
and Dave.
We'd like to have this included in the final 5.1 drm-intel-next
pull request this week.
If there are no further comments by Wed, I will conclude that we
have reached a silent agreement, and merge this to give enough
time for Rodrigo to send the PR.
Regards, Joonas
> I believe most are already aware of the situation that Intel
> is moving to the new codebase for libva backend to support new Intel
> integrated graphics devices. The existing intel-libva-driver will
> be continue to be be supported for pre-Icelake platforms (<Gen11).
> Icelake and further platforms will only be supported from the
> new codebase.
>
> There's the complication that some Icelake features of the new
> driver will require new kernel uAPIs to work... But the new driver
> has not yet been well-established in the community from perspective
> of fulfilling [2]. This is very much due to the demand being low
> as Icelake is not widely available yet. So it's bit of a chicken
> and egg problem as we have a new platform *and* a new codebase for
> it simultaneously.
>
> Ahead of that community adoption, to ensure that Icelake has good
> kernel support from day one, we'd like to merge kernel support for
> the parts that have functional effect (this series). This is to
> avoid the scenario where end users have to update their distro
> kernels, like happened with Skylake.
>
> So if I could get Acked-by's from distro folks on the patch [5/6] that
> adds the new uAPI. That would document their intent to become an active
> user of the media-driver[1]. If that happens in the next week or two,
> it would mean that Icelake hardware features would be supported in
> kernel version 5.1 fully from kernel driver point of view.
>
> The new uAPI is needed to make VME feature functionally work
> on Icelake. It's pretty much a simple enable/disable switch for
> hardware configuration that only includes hardware slices compatible
> with the VME workload. So it's currently limited to the required on/off
> choice to keep things straightforward. The uAPI can be extended in the
> future for possible performance gains for more fine-grained control.
>
> VME is shared function to handle motion estimation. One intended
> usercase is in Hierarchical Motion Estimation (HME) media kernel. It
> provides a bigger search range with reduced cost for the search. HME
> should improve the encode quality with scenarios where the video has
> a lot of motion in it. Carl (Cc'd) can provide more details if needed.
>
> The respective IGT tests are reviewed and can be found at:
>
> https://patchwork.freedesktop.org/series/49190/
>
> The userspace changes are reviewed and rebased here:
>
> https://github.com/intel/media-driver/pull/271
> https://github.com/intel/media-driver/pull/463
>
> Best Regards, Joonas Lahtinen
>
> Cc: dri-devel@lists.freedesktop.org
> Cc: Timo Aaltonen <timo.aaltonen@canonical.com>
> Cc: Takashi Iwai <tiwai@suse.de>
> Cc: Stephane Marchesin <stephane.marchesin@gmail.com>
> Cc: Dave Airlie <airlied@redhat.com>
> Cc: Daniel Vetter <daniel@ffwll.ch>
>
> PS. This series might result in some CI failures reported as it adds new uAPI
> and Patchwork / CI synchronization of tests and kernel is currently WIP.
>
> [1] https://github.com/intel/media-driver
> [2] https://01.org/linuxgraphics/gfx-docs/drm/gpu/drm-uapi.html#open-source-userspace-requirements
>
> Lionel Landwerlin (2):
> drm/i915: Record the sseu configuration per-context & engine
> drm/i915/perf: lock powergating configuration to default when active
>
> Tvrtko Ursulin (4):
> drm/i915/execlists: Move RPCS setup to context pin
> drm/i915: Add timeline barrier support
> drm/i915: Expose RPCS (SSEU) configuration to userspace (Gen11 only)
> drm/i915/selftests: Context SSEU reconfiguration tests
>
> drivers/gpu/drm/i915/i915_drv.h | 14 +
> drivers/gpu/drm/i915/i915_gem_context.c | 354 ++++++++++++-
> drivers/gpu/drm/i915/i915_gem_context.h | 10 +
> drivers/gpu/drm/i915/i915_perf.c | 13 +-
> drivers/gpu/drm/i915/i915_request.c | 13 +
> drivers/gpu/drm/i915/i915_request.h | 10 +
> drivers/gpu/drm/i915/i915_timeline.c | 3 +
> drivers/gpu/drm/i915/i915_timeline.h | 27 +
> drivers/gpu/drm/i915/intel_lrc.c | 100 ++--
> drivers/gpu/drm/i915/intel_lrc.h | 2 +
> .../gpu/drm/i915/selftests/i915_gem_context.c | 481 ++++++++++++++++++
> .../gpu/drm/i915/selftests/mock_timeline.c | 2 +
> include/uapi/drm/i915_drm.h | 64 +++
> 13 files changed, 1056 insertions(+), 37 deletions(-)
>
> --
> 2.17.2
>
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel
^ permalink raw reply [flat|nested] 17+ messages in thread* Re: [PATCH 0/6] Add uAPI to support ICL VME hardware for new media-driver
2019-02-04 8:57 ` [PATCH 0/6] " Joonas Lahtinen
@ 2019-02-04 9:07 ` Daniel Vetter
2019-02-05 4:16 ` Stéphane Marchesin
0 siblings, 1 reply; 17+ messages in thread
From: Daniel Vetter @ 2019-02-04 9:07 UTC (permalink / raw)
To: Joonas Lahtinen
Cc: Jani Nikula, Takashi Iwai,
Intel graphics driver community testing & development,
Timo Aaltonen, dri-devel, Carl Zhang, Stephane Marchesin,
Dave Airlie
On Mon, Feb 04, 2019 at 10:57:24AM +0200, Joonas Lahtinen wrote:
> Quoting Joonas Lahtinen (2019-01-15 16:47:27)
> > Hi all,
> >
> > I would like to have some Acked-by's from you, the distro media
> > folks Cc'd here, to document your intent to start using Intel's
> > new media driver[1]. So if you recognize yourself (or are otherwise
> > interested), please read on.
> >
> > TL;DR Distro folks, please give your Acked-by on patch [5/6]
>
> A gentle reminder, I'm still looking to hear back from Stephane
> and Dave.
>
> We'd like to have this included in the final 5.1 drm-intel-next
> pull request this week.
>
> If there are no further comments by Wed, I will conclude that we
> have reached a silent agreement, and merge this to give enough
> time for Rodrigo to send the PR.
Maybe should add that ubunut/suse folks seem ok. Also, it's for libva, in
the past that's been very far down the list of contentious topics. Mostly
positive meh seems plenty good enough feedback I think.
-Daniel
>
> Regards, Joonas
>
> > I believe most are already aware of the situation that Intel
> > is moving to the new codebase for libva backend to support new Intel
> > integrated graphics devices. The existing intel-libva-driver will
> > be continue to be be supported for pre-Icelake platforms (<Gen11).
> > Icelake and further platforms will only be supported from the
> > new codebase.
> >
> > There's the complication that some Icelake features of the new
> > driver will require new kernel uAPIs to work... But the new driver
> > has not yet been well-established in the community from perspective
> > of fulfilling [2]. This is very much due to the demand being low
> > as Icelake is not widely available yet. So it's bit of a chicken
> > and egg problem as we have a new platform *and* a new codebase for
> > it simultaneously.
> >
> > Ahead of that community adoption, to ensure that Icelake has good
> > kernel support from day one, we'd like to merge kernel support for
> > the parts that have functional effect (this series). This is to
> > avoid the scenario where end users have to update their distro
> > kernels, like happened with Skylake.
> >
> > So if I could get Acked-by's from distro folks on the patch [5/6] that
> > adds the new uAPI. That would document their intent to become an active
> > user of the media-driver[1]. If that happens in the next week or two,
> > it would mean that Icelake hardware features would be supported in
> > kernel version 5.1 fully from kernel driver point of view.
> >
> > The new uAPI is needed to make VME feature functionally work
> > on Icelake. It's pretty much a simple enable/disable switch for
> > hardware configuration that only includes hardware slices compatible
> > with the VME workload. So it's currently limited to the required on/off
> > choice to keep things straightforward. The uAPI can be extended in the
> > future for possible performance gains for more fine-grained control.
> >
> > VME is shared function to handle motion estimation. One intended
> > usercase is in Hierarchical Motion Estimation (HME) media kernel. It
> > provides a bigger search range with reduced cost for the search. HME
> > should improve the encode quality with scenarios where the video has
> > a lot of motion in it. Carl (Cc'd) can provide more details if needed.
> >
> > The respective IGT tests are reviewed and can be found at:
> >
> > https://patchwork.freedesktop.org/series/49190/
> >
> > The userspace changes are reviewed and rebased here:
> >
> > https://github.com/intel/media-driver/pull/271
> > https://github.com/intel/media-driver/pull/463
> >
> > Best Regards, Joonas Lahtinen
> >
> > Cc: dri-devel@lists.freedesktop.org
> > Cc: Timo Aaltonen <timo.aaltonen@canonical.com>
> > Cc: Takashi Iwai <tiwai@suse.de>
> > Cc: Stephane Marchesin <stephane.marchesin@gmail.com>
> > Cc: Dave Airlie <airlied@redhat.com>
> > Cc: Daniel Vetter <daniel@ffwll.ch>
> >
> > PS. This series might result in some CI failures reported as it adds new uAPI
> > and Patchwork / CI synchronization of tests and kernel is currently WIP.
> >
> > [1] https://github.com/intel/media-driver
> > [2] https://01.org/linuxgraphics/gfx-docs/drm/gpu/drm-uapi.html#open-source-userspace-requirements
> >
> > Lionel Landwerlin (2):
> > drm/i915: Record the sseu configuration per-context & engine
> > drm/i915/perf: lock powergating configuration to default when active
> >
> > Tvrtko Ursulin (4):
> > drm/i915/execlists: Move RPCS setup to context pin
> > drm/i915: Add timeline barrier support
> > drm/i915: Expose RPCS (SSEU) configuration to userspace (Gen11 only)
> > drm/i915/selftests: Context SSEU reconfiguration tests
> >
> > drivers/gpu/drm/i915/i915_drv.h | 14 +
> > drivers/gpu/drm/i915/i915_gem_context.c | 354 ++++++++++++-
> > drivers/gpu/drm/i915/i915_gem_context.h | 10 +
> > drivers/gpu/drm/i915/i915_perf.c | 13 +-
> > drivers/gpu/drm/i915/i915_request.c | 13 +
> > drivers/gpu/drm/i915/i915_request.h | 10 +
> > drivers/gpu/drm/i915/i915_timeline.c | 3 +
> > drivers/gpu/drm/i915/i915_timeline.h | 27 +
> > drivers/gpu/drm/i915/intel_lrc.c | 100 ++--
> > drivers/gpu/drm/i915/intel_lrc.h | 2 +
> > .../gpu/drm/i915/selftests/i915_gem_context.c | 481 ++++++++++++++++++
> > .../gpu/drm/i915/selftests/mock_timeline.c | 2 +
> > include/uapi/drm/i915_drm.h | 64 +++
> > 13 files changed, 1056 insertions(+), 37 deletions(-)
> >
> > --
> > 2.17.2
> >
--
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 17+ messages in thread
* Re: [PATCH 0/6] Add uAPI to support ICL VME hardware for new media-driver
2019-02-04 9:07 ` Daniel Vetter
@ 2019-02-05 4:16 ` Stéphane Marchesin
2019-02-05 9:49 ` Joonas Lahtinen
0 siblings, 1 reply; 17+ messages in thread
From: Stéphane Marchesin @ 2019-02-05 4:16 UTC (permalink / raw)
To: Daniel Vetter
Cc: Intel graphics driver community testing & development,
Timo Aaltonen, dri-devel, Carl Zhang, Jani Nikula, Rodrigo Vivi,
Dave Airlie
On Mon, Feb 4, 2019 at 1:07 AM Daniel Vetter <daniel@ffwll.ch> wrote:
>
> On Mon, Feb 04, 2019 at 10:57:24AM +0200, Joonas Lahtinen wrote:
> > Quoting Joonas Lahtinen (2019-01-15 16:47:27)
> > > Hi all,
> > >
> > > I would like to have some Acked-by's from you, the distro media
> > > folks Cc'd here, to document your intent to start using Intel's
> > > new media driver[1]. So if you recognize yourself (or are otherwise
> > > interested), please read on.
> > >
> > > TL;DR Distro folks, please give your Acked-by on patch [5/6]
> >
> > A gentle reminder, I'm still looking to hear back from Stephane
> > and Dave.
> >
> > We'd like to have this included in the final 5.1 drm-intel-next
> > pull request this week.
> >
> > If there are no further comments by Wed, I will conclude that we
> > have reached a silent agreement, and merge this to give enough
> > time for Rodrigo to send the PR.
>
> Maybe should add that ubunut/suse folks seem ok. Also, it's for libva, in
> the past that's been very far down the list of contentious topics. Mostly
> positive meh seems plenty good enough feedback I think.
FWIW I think the API changes are fine. Sure it feels a bit odd at
first, but there's no better alternative that I can see either.
Acked-by: Stéphane Marchesin <marcheu@chromium.org>
> -Daniel
>
> >
> > Regards, Joonas
> >
> > > I believe most are already aware of the situation that Intel
> > > is moving to the new codebase for libva backend to support new Intel
> > > integrated graphics devices. The existing intel-libva-driver will
> > > be continue to be be supported for pre-Icelake platforms (<Gen11).
> > > Icelake and further platforms will only be supported from the
> > > new codebase.
> > >
> > > There's the complication that some Icelake features of the new
> > > driver will require new kernel uAPIs to work... But the new driver
> > > has not yet been well-established in the community from perspective
> > > of fulfilling [2]. This is very much due to the demand being low
> > > as Icelake is not widely available yet. So it's bit of a chicken
> > > and egg problem as we have a new platform *and* a new codebase for
> > > it simultaneously.
> > >
> > > Ahead of that community adoption, to ensure that Icelake has good
> > > kernel support from day one, we'd like to merge kernel support for
> > > the parts that have functional effect (this series). This is to
> > > avoid the scenario where end users have to update their distro
> > > kernels, like happened with Skylake.
> > >
> > > So if I could get Acked-by's from distro folks on the patch [5/6] that
> > > adds the new uAPI. That would document their intent to become an active
> > > user of the media-driver[1]. If that happens in the next week or two,
> > > it would mean that Icelake hardware features would be supported in
> > > kernel version 5.1 fully from kernel driver point of view.
> > >
> > > The new uAPI is needed to make VME feature functionally work
> > > on Icelake. It's pretty much a simple enable/disable switch for
> > > hardware configuration that only includes hardware slices compatible
> > > with the VME workload. So it's currently limited to the required on/off
> > > choice to keep things straightforward. The uAPI can be extended in the
> > > future for possible performance gains for more fine-grained control.
> > >
> > > VME is shared function to handle motion estimation. One intended
> > > usercase is in Hierarchical Motion Estimation (HME) media kernel. It
> > > provides a bigger search range with reduced cost for the search. HME
> > > should improve the encode quality with scenarios where the video has
> > > a lot of motion in it. Carl (Cc'd) can provide more details if needed.
> > >
> > > The respective IGT tests are reviewed and can be found at:
> > >
> > > https://patchwork.freedesktop.org/series/49190/
> > >
> > > The userspace changes are reviewed and rebased here:
> > >
> > > https://github.com/intel/media-driver/pull/271
> > > https://github.com/intel/media-driver/pull/463
> > >
> > > Best Regards, Joonas Lahtinen
> > >
> > > Cc: dri-devel@lists.freedesktop.org
> > > Cc: Timo Aaltonen <timo.aaltonen@canonical.com>
> > > Cc: Takashi Iwai <tiwai@suse.de>
> > > Cc: Stephane Marchesin <stephane.marchesin@gmail.com>
> > > Cc: Dave Airlie <airlied@redhat.com>
> > > Cc: Daniel Vetter <daniel@ffwll.ch>
> > >
> > > PS. This series might result in some CI failures reported as it adds new uAPI
> > > and Patchwork / CI synchronization of tests and kernel is currently WIP.
> > >
> > > [1] https://github.com/intel/media-driver
> > > [2] https://01.org/linuxgraphics/gfx-docs/drm/gpu/drm-uapi.html#open-source-userspace-requirements
> > >
> > > Lionel Landwerlin (2):
> > > drm/i915: Record the sseu configuration per-context & engine
> > > drm/i915/perf: lock powergating configuration to default when active
> > >
> > > Tvrtko Ursulin (4):
> > > drm/i915/execlists: Move RPCS setup to context pin
> > > drm/i915: Add timeline barrier support
> > > drm/i915: Expose RPCS (SSEU) configuration to userspace (Gen11 only)
> > > drm/i915/selftests: Context SSEU reconfiguration tests
> > >
> > > drivers/gpu/drm/i915/i915_drv.h | 14 +
> > > drivers/gpu/drm/i915/i915_gem_context.c | 354 ++++++++++++-
> > > drivers/gpu/drm/i915/i915_gem_context.h | 10 +
> > > drivers/gpu/drm/i915/i915_perf.c | 13 +-
> > > drivers/gpu/drm/i915/i915_request.c | 13 +
> > > drivers/gpu/drm/i915/i915_request.h | 10 +
> > > drivers/gpu/drm/i915/i915_timeline.c | 3 +
> > > drivers/gpu/drm/i915/i915_timeline.h | 27 +
> > > drivers/gpu/drm/i915/intel_lrc.c | 100 ++--
> > > drivers/gpu/drm/i915/intel_lrc.h | 2 +
> > > .../gpu/drm/i915/selftests/i915_gem_context.c | 481 ++++++++++++++++++
> > > .../gpu/drm/i915/selftests/mock_timeline.c | 2 +
> > > include/uapi/drm/i915_drm.h | 64 +++
> > > 13 files changed, 1056 insertions(+), 37 deletions(-)
> > >
> > > --
> > > 2.17.2
> > >
>
> --
> Daniel Vetter
> Software Engineer, Intel Corporation
> http://blog.ffwll.ch
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel
^ permalink raw reply [flat|nested] 17+ messages in thread
* Re: [PATCH 0/6] Add uAPI to support ICL VME hardware for new media-driver
2019-02-05 4:16 ` Stéphane Marchesin
@ 2019-02-05 9:49 ` Joonas Lahtinen
0 siblings, 0 replies; 17+ messages in thread
From: Joonas Lahtinen @ 2019-02-05 9:49 UTC (permalink / raw)
To: Stéphane Marchesin, Daniel Vetter
Cc: Intel graphics driver community testing & development,
Timo Aaltonen, dri-devel, Carl Zhang, Jani Nikula, Rodrigo Vivi,
Dave Airlie
Quoting Stéphane Marchesin (2019-02-05 06:16:48)
> On Mon, Feb 4, 2019 at 1:07 AM Daniel Vetter <daniel@ffwll.ch> wrote:
> >
> > On Mon, Feb 04, 2019 at 10:57:24AM +0200, Joonas Lahtinen wrote:
> > > Quoting Joonas Lahtinen (2019-01-15 16:47:27)
> > > > Hi all,
> > > >
> > > > I would like to have some Acked-by's from you, the distro media
> > > > folks Cc'd here, to document your intent to start using Intel's
> > > > new media driver[1]. So if you recognize yourself (or are otherwise
> > > > interested), please read on.
> > > >
> > > > TL;DR Distro folks, please give your Acked-by on patch [5/6]
> > >
> > > A gentle reminder, I'm still looking to hear back from Stephane
> > > and Dave.
> > >
> > > We'd like to have this included in the final 5.1 drm-intel-next
> > > pull request this week.
> > >
> > > If there are no further comments by Wed, I will conclude that we
> > > have reached a silent agreement, and merge this to give enough
> > > time for Rodrigo to send the PR.
> >
> > Maybe should add that ubunut/suse folks seem ok. Also, it's for libva, in
> > the past that's been very far down the list of contentious topics. Mostly
> > positive meh seems plenty good enough feedback I think.
>
> FWIW I think the API changes are fine. Sure it feels a bit odd at
> first, but there's no better alternative that I can see either.
>
> Acked-by: Stéphane Marchesin <marcheu@chromium.org>
>
Dave commented on IRC that he's fine with us proceeding to merge
with these Acks in place.
Thank you all for looking into the matter, this will now find its
way into Kernel version 5.1.
Regards, Joonas
>
> > -Daniel
> >
> > >
> > > Regards, Joonas
> > >
> > > > I believe most are already aware of the situation that Intel
> > > > is moving to the new codebase for libva backend to support new Intel
> > > > integrated graphics devices. The existing intel-libva-driver will
> > > > be continue to be be supported for pre-Icelake platforms (<Gen11).
> > > > Icelake and further platforms will only be supported from the
> > > > new codebase.
> > > >
> > > > There's the complication that some Icelake features of the new
> > > > driver will require new kernel uAPIs to work... But the new driver
> > > > has not yet been well-established in the community from perspective
> > > > of fulfilling [2]. This is very much due to the demand being low
> > > > as Icelake is not widely available yet. So it's bit of a chicken
> > > > and egg problem as we have a new platform *and* a new codebase for
> > > > it simultaneously.
> > > >
> > > > Ahead of that community adoption, to ensure that Icelake has good
> > > > kernel support from day one, we'd like to merge kernel support for
> > > > the parts that have functional effect (this series). This is to
> > > > avoid the scenario where end users have to update their distro
> > > > kernels, like happened with Skylake.
> > > >
> > > > So if I could get Acked-by's from distro folks on the patch [5/6] that
> > > > adds the new uAPI. That would document their intent to become an active
> > > > user of the media-driver[1]. If that happens in the next week or two,
> > > > it would mean that Icelake hardware features would be supported in
> > > > kernel version 5.1 fully from kernel driver point of view.
> > > >
> > > > The new uAPI is needed to make VME feature functionally work
> > > > on Icelake. It's pretty much a simple enable/disable switch for
> > > > hardware configuration that only includes hardware slices compatible
> > > > with the VME workload. So it's currently limited to the required on/off
> > > > choice to keep things straightforward. The uAPI can be extended in the
> > > > future for possible performance gains for more fine-grained control.
> > > >
> > > > VME is shared function to handle motion estimation. One intended
> > > > usercase is in Hierarchical Motion Estimation (HME) media kernel. It
> > > > provides a bigger search range with reduced cost for the search. HME
> > > > should improve the encode quality with scenarios where the video has
> > > > a lot of motion in it. Carl (Cc'd) can provide more details if needed.
> > > >
> > > > The respective IGT tests are reviewed and can be found at:
> > > >
> > > > https://patchwork.freedesktop.org/series/49190/
> > > >
> > > > The userspace changes are reviewed and rebased here:
> > > >
> > > > https://github.com/intel/media-driver/pull/271
> > > > https://github.com/intel/media-driver/pull/463
> > > >
> > > > Best Regards, Joonas Lahtinen
> > > >
> > > > Cc: dri-devel@lists.freedesktop.org
> > > > Cc: Timo Aaltonen <timo.aaltonen@canonical.com>
> > > > Cc: Takashi Iwai <tiwai@suse.de>
> > > > Cc: Stephane Marchesin <stephane.marchesin@gmail.com>
> > > > Cc: Dave Airlie <airlied@redhat.com>
> > > > Cc: Daniel Vetter <daniel@ffwll.ch>
> > > >
> > > > PS. This series might result in some CI failures reported as it adds new uAPI
> > > > and Patchwork / CI synchronization of tests and kernel is currently WIP.
> > > >
> > > > [1] https://github.com/intel/media-driver
> > > > [2] https://01.org/linuxgraphics/gfx-docs/drm/gpu/drm-uapi.html#open-source-userspace-requirements
> > > >
> > > > Lionel Landwerlin (2):
> > > > drm/i915: Record the sseu configuration per-context & engine
> > > > drm/i915/perf: lock powergating configuration to default when active
> > > >
> > > > Tvrtko Ursulin (4):
> > > > drm/i915/execlists: Move RPCS setup to context pin
> > > > drm/i915: Add timeline barrier support
> > > > drm/i915: Expose RPCS (SSEU) configuration to userspace (Gen11 only)
> > > > drm/i915/selftests: Context SSEU reconfiguration tests
> > > >
> > > > drivers/gpu/drm/i915/i915_drv.h | 14 +
> > > > drivers/gpu/drm/i915/i915_gem_context.c | 354 ++++++++++++-
> > > > drivers/gpu/drm/i915/i915_gem_context.h | 10 +
> > > > drivers/gpu/drm/i915/i915_perf.c | 13 +-
> > > > drivers/gpu/drm/i915/i915_request.c | 13 +
> > > > drivers/gpu/drm/i915/i915_request.h | 10 +
> > > > drivers/gpu/drm/i915/i915_timeline.c | 3 +
> > > > drivers/gpu/drm/i915/i915_timeline.h | 27 +
> > > > drivers/gpu/drm/i915/intel_lrc.c | 100 ++--
> > > > drivers/gpu/drm/i915/intel_lrc.h | 2 +
> > > > .../gpu/drm/i915/selftests/i915_gem_context.c | 481 ++++++++++++++++++
> > > > .../gpu/drm/i915/selftests/mock_timeline.c | 2 +
> > > > include/uapi/drm/i915_drm.h | 64 +++
> > > > 13 files changed, 1056 insertions(+), 37 deletions(-)
> > > >
> > > > --
> > > > 2.17.2
> > > >
> >
> > --
> > Daniel Vetter
> > Software Engineer, Intel Corporation
> > http://blog.ffwll.ch
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel
^ permalink raw reply [flat|nested] 17+ messages in thread
* [PATCH 6/6] drm/i915/selftests: Context SSEU reconfiguration tests
2019-01-24 11:41 [PATCH 0/6] Per context dynamic (sub)slice power-gating Tvrtko Ursulin
@ 2019-01-24 11:42 ` Tvrtko Ursulin
0 siblings, 0 replies; 17+ messages in thread
From: Tvrtko Ursulin @ 2019-01-24 11:42 UTC (permalink / raw)
To: Intel-gfx
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Exercise the context image reconfiguration logic for idle and busy
contexts, with the resets thrown into the mix as well.
Free from the uAPI restrictions this test runs on all Gen9+ platforms
with slice power gating.
v2:
* Rename some helpers for clarity.
* Include subtest names in error logs.
* Remove unnecessary function export.
v3:
* Rebase for RUNTIME_INFO.
v4:
* Fix incomplete unexport from v2. (Chris Wilson)
v5:
* Rebased for runtime pm api changes.
v6:
* Rebased for i915_reset.c.
v7:
* Tidy checkpatch warnings.
* Consolidate error checking and logging a bit.
* Skip idle test phase if something failed before it.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> # v6
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> # v6
---
drivers/gpu/drm/i915/i915_gem_context.c | 31 +-
.../gpu/drm/i915/selftests/i915_gem_context.c | 472 ++++++++++++++++++
2 files changed, 493 insertions(+), 10 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 92ebbcde3ded..508e131e4434 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -1049,23 +1049,19 @@ gen8_modify_rpcs_gpu(struct intel_context *ce,
}
static int
-i915_gem_context_reconfigure_sseu(struct i915_gem_context *ctx,
- struct intel_engine_cs *engine,
- struct intel_sseu sseu)
+__i915_gem_context_reconfigure_sseu(struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine,
+ struct intel_sseu sseu)
{
struct intel_context *ce = to_intel_context(ctx, engine);
- int ret;
+ int ret = 0;
GEM_BUG_ON(INTEL_GEN(ctx->i915) < 8);
GEM_BUG_ON(engine->id != RCS);
- ret = mutex_lock_interruptible(&ctx->i915->drm.struct_mutex);
- if (ret)
- return ret;
-
/* Nothing to do if unmodified. */
if (!memcmp(&ce->sseu, &sseu, sizeof(sseu)))
- goto out;
+ return 0;
/*
* If context is not idle we have to submit an ordered request to modify
@@ -1078,7 +1074,22 @@ i915_gem_context_reconfigure_sseu(struct i915_gem_context *ctx,
if (!ret)
ce->sseu = sseu;
-out:
+ return ret;
+}
+
+static int
+i915_gem_context_reconfigure_sseu(struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine,
+ struct intel_sseu sseu)
+{
+ int ret;
+
+ ret = mutex_lock_interruptible(&ctx->i915->drm.struct_mutex);
+ if (ret)
+ return ret;
+
+ ret = __i915_gem_context_reconfigure_sseu(ctx, engine, sseu);
+
mutex_unlock(&ctx->i915->drm.struct_mutex);
return ret;
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index e2c1f0bc2abe..f028be2492b8 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -24,10 +24,13 @@
#include <linux/prime_numbers.h>
+#include "../i915_reset.h"
#include "../i915_selftest.h"
#include "i915_random.h"
#include "igt_flush_test.h"
#include "igt_live_test.h"
+#include "igt_reset.h"
+#include "igt_spinner.h"
#include "mock_drm.h"
#include "mock_gem_device.h"
@@ -576,6 +579,474 @@ static int igt_ctx_exec(void *arg)
return err;
}
+static struct i915_vma *rpcs_query_batch(struct i915_vma *vma)
+{
+ struct drm_i915_gem_object *obj;
+ u32 *cmd;
+ int err;
+
+ if (INTEL_GEN(vma->vm->i915) < 8)
+ return ERR_PTR(-EINVAL);
+
+ obj = i915_gem_object_create_internal(vma->vm->i915, PAGE_SIZE);
+ if (IS_ERR(obj))
+ return ERR_CAST(obj);
+
+ cmd = i915_gem_object_pin_map(obj, I915_MAP_WB);
+ if (IS_ERR(cmd)) {
+ err = PTR_ERR(cmd);
+ goto err;
+ }
+
+ *cmd++ = MI_STORE_REGISTER_MEM_GEN8;
+ *cmd++ = i915_mmio_reg_offset(GEN8_R_PWR_CLK_STATE);
+ *cmd++ = lower_32_bits(vma->node.start);
+ *cmd++ = upper_32_bits(vma->node.start);
+ *cmd = MI_BATCH_BUFFER_END;
+
+ i915_gem_object_unpin_map(obj);
+
+ err = i915_gem_object_set_to_gtt_domain(obj, false);
+ if (err)
+ goto err;
+
+ vma = i915_vma_instance(obj, vma->vm, NULL);
+ if (IS_ERR(vma)) {
+ err = PTR_ERR(vma);
+ goto err;
+ }
+
+ err = i915_vma_pin(vma, 0, 0, PIN_USER);
+ if (err)
+ goto err;
+
+ return vma;
+
+err:
+ i915_gem_object_put(obj);
+ return ERR_PTR(err);
+}
+
+static int
+emit_rpcs_query(struct drm_i915_gem_object *obj,
+ struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine,
+ struct i915_request **rq_out)
+{
+ struct i915_address_space *vm;
+ struct i915_request *rq;
+ struct i915_vma *batch;
+ struct i915_vma *vma;
+ int err;
+
+ GEM_BUG_ON(!ctx->ppgtt);
+ GEM_BUG_ON(!intel_engine_can_store_dword(engine));
+
+ vm = &ctx->ppgtt->vm;
+
+ vma = i915_vma_instance(obj, vm, NULL);
+ if (IS_ERR(vma))
+ return PTR_ERR(vma);
+
+ err = i915_gem_object_set_to_gtt_domain(obj, false);
+ if (err)
+ return err;
+
+ err = i915_vma_pin(vma, 0, 0, PIN_HIGH | PIN_USER);
+ if (err)
+ return err;
+
+ batch = rpcs_query_batch(vma);
+ if (IS_ERR(batch)) {
+ err = PTR_ERR(batch);
+ goto err_vma;
+ }
+
+ rq = i915_request_alloc(engine, ctx);
+ if (IS_ERR(rq)) {
+ err = PTR_ERR(rq);
+ goto err_batch;
+ }
+
+ err = engine->emit_bb_start(rq, batch->node.start, batch->node.size, 0);
+ if (err)
+ goto err_request;
+
+ err = i915_vma_move_to_active(batch, rq, 0);
+ if (err)
+ goto skip_request;
+
+ err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+ if (err)
+ goto skip_request;
+
+ i915_gem_object_set_active_reference(batch->obj);
+ i915_vma_unpin(batch);
+ i915_vma_close(batch);
+
+ i915_vma_unpin(vma);
+
+ *rq_out = i915_request_get(rq);
+
+ i915_request_add(rq);
+
+ return 0;
+
+skip_request:
+ i915_request_skip(rq, err);
+err_request:
+ i915_request_add(rq);
+err_batch:
+ i915_vma_unpin(batch);
+err_vma:
+ i915_vma_unpin(vma);
+
+ return err;
+}
+
+#define TEST_IDLE BIT(0)
+#define TEST_BUSY BIT(1)
+#define TEST_RESET BIT(2)
+
+static int
+__sseu_prepare(struct drm_i915_private *i915,
+ const char *name,
+ unsigned int flags,
+ struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine,
+ struct igt_spinner **spin_out)
+{
+ int ret = 0;
+
+ if (flags & (TEST_BUSY | TEST_RESET)) {
+ struct igt_spinner *spin;
+ struct i915_request *rq;
+
+ spin = kzalloc(sizeof(*spin), GFP_KERNEL);
+ if (!spin) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ ret = igt_spinner_init(spin, i915);
+ if (ret)
+ return ret;
+
+ rq = igt_spinner_create_request(spin, ctx, engine, MI_NOOP);
+ if (IS_ERR(rq)) {
+ ret = PTR_ERR(rq);
+ igt_spinner_fini(spin);
+ kfree(spin);
+ goto out;
+ }
+
+ i915_request_add(rq);
+
+ if (!igt_wait_for_spinner(spin, rq)) {
+ pr_err("%s: Spinner failed to start!\n", name);
+ igt_spinner_end(spin);
+ igt_spinner_fini(spin);
+ kfree(spin);
+ ret = -ETIMEDOUT;
+ goto out;
+ }
+
+ *spin_out = spin;
+ }
+
+out:
+ return ret;
+}
+
+static int
+__read_slice_count(struct drm_i915_private *i915,
+ struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine,
+ struct drm_i915_gem_object *obj,
+ struct igt_spinner *spin,
+ u32 *rpcs)
+{
+ struct i915_request *rq = NULL;
+ u32 s_mask, s_shift;
+ unsigned int cnt;
+ u32 *buf, val;
+ long ret;
+
+ ret = emit_rpcs_query(obj, ctx, engine, &rq);
+ if (ret)
+ return ret;
+
+ if (spin)
+ igt_spinner_end(spin);
+
+ ret = i915_request_wait(rq, I915_WAIT_LOCKED, MAX_SCHEDULE_TIMEOUT);
+ if (ret <= 0)
+ return ret < 0 ? ret : -ETIME;
+
+ i915_request_put(rq);
+
+ buf = i915_gem_object_pin_map(obj, I915_MAP_WB);
+ if (IS_ERR(buf)) {
+ ret = PTR_ERR(buf);
+ return ret;
+ }
+
+ if (INTEL_GEN(i915) >= 11) {
+ s_mask = GEN11_RPCS_S_CNT_MASK;
+ s_shift = GEN11_RPCS_S_CNT_SHIFT;
+ } else {
+ s_mask = GEN8_RPCS_S_CNT_MASK;
+ s_shift = GEN8_RPCS_S_CNT_SHIFT;
+ }
+
+ val = *buf;
+ cnt = (val & s_mask) >> s_shift;
+ *rpcs = val;
+
+ i915_gem_object_unpin_map(obj);
+
+ return cnt;
+}
+
+static int
+__check_rpcs(const char *name, u32 rpcs, int slices, unsigned int expected,
+ const char *prefix, const char *suffix)
+{
+ if (slices == expected)
+ return 0;
+
+ if (slices < 0) {
+ pr_err("%s: %s read slice count failed with %d%s\n",
+ name, prefix, slices, suffix);
+ return slices;
+ }
+
+ pr_err("%s: %s slice count %d is not %u%s\n",
+ name, prefix, slices, expected, suffix);
+
+ pr_info("RPCS=0x%x; %u%sx%u%s\n",
+ rpcs, slices,
+ (rpcs & GEN8_RPCS_S_CNT_ENABLE) ? "*" : "",
+ (rpcs & GEN8_RPCS_SS_CNT_MASK) >> GEN8_RPCS_SS_CNT_SHIFT,
+ (rpcs & GEN8_RPCS_SS_CNT_ENABLE) ? "*" : "");
+
+ return -EINVAL;
+}
+
+static int
+__sseu_finish(struct drm_i915_private *i915,
+ const char *name,
+ unsigned int flags,
+ struct i915_gem_context *ctx,
+ struct i915_gem_context *kctx,
+ struct intel_engine_cs *engine,
+ struct drm_i915_gem_object *obj,
+ unsigned int expected,
+ struct igt_spinner *spin)
+{
+ unsigned int slices =
+ hweight32(intel_device_default_sseu(i915).slice_mask);
+ u32 rpcs = 0;
+ int ret = 0;
+
+ if (flags & TEST_RESET) {
+ ret = i915_reset_engine(engine, "sseu");
+ if (ret)
+ goto out;
+ }
+
+ ret = __read_slice_count(i915, ctx, engine, obj,
+ flags & TEST_RESET ? NULL : spin, &rpcs);
+ ret = __check_rpcs(name, rpcs, ret, expected, "Context", "!");
+ if (ret)
+ goto out;
+
+ ret = __read_slice_count(i915, kctx, engine, obj, NULL, &rpcs);
+ ret = __check_rpcs(name, rpcs, ret, slices, "Kernel context", "!");
+
+out:
+ if (spin)
+ igt_spinner_end(spin);
+
+ if ((flags & TEST_IDLE) && ret == 0) {
+ ret = i915_gem_wait_for_idle(i915,
+ I915_WAIT_LOCKED,
+ MAX_SCHEDULE_TIMEOUT);
+ if (ret)
+ return ret;
+
+ ret = __read_slice_count(i915, ctx, engine, obj, NULL, &rpcs);
+ ret = __check_rpcs(name, rpcs, ret, expected,
+ "Context", " after idle!");
+ }
+
+ return ret;
+}
+
+static int
+__sseu_test(struct drm_i915_private *i915,
+ const char *name,
+ unsigned int flags,
+ struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine,
+ struct drm_i915_gem_object *obj,
+ struct intel_sseu sseu)
+{
+ struct igt_spinner *spin = NULL;
+ struct i915_gem_context *kctx;
+ int ret;
+
+ kctx = kernel_context(i915);
+ if (IS_ERR(kctx))
+ return PTR_ERR(kctx);
+
+ ret = __sseu_prepare(i915, name, flags, ctx, engine, &spin);
+ if (ret)
+ goto out;
+
+ ret = __i915_gem_context_reconfigure_sseu(ctx, engine, sseu);
+ if (ret)
+ goto out;
+
+ ret = __sseu_finish(i915, name, flags, ctx, kctx, engine, obj,
+ hweight32(sseu.slice_mask), spin);
+
+out:
+ if (spin) {
+ igt_spinner_end(spin);
+ igt_spinner_fini(spin);
+ kfree(spin);
+ }
+
+ kernel_context_close(kctx);
+
+ return ret;
+}
+
+static int
+__igt_ctx_sseu(struct drm_i915_private *i915,
+ const char *name,
+ unsigned int flags)
+{
+ struct intel_sseu default_sseu = intel_device_default_sseu(i915);
+ struct intel_engine_cs *engine = i915->engine[RCS];
+ struct drm_i915_gem_object *obj;
+ struct i915_gem_context *ctx;
+ struct intel_sseu pg_sseu;
+ intel_wakeref_t wakeref;
+ struct drm_file *file;
+ int ret;
+
+ if (INTEL_GEN(i915) < 9)
+ return 0;
+
+ if (!RUNTIME_INFO(i915)->sseu.has_slice_pg)
+ return 0;
+
+ if (hweight32(default_sseu.slice_mask) < 2)
+ return 0;
+
+ /*
+ * Gen11 VME friendly power-gated configuration with half enabled
+ * sub-slices.
+ */
+ pg_sseu = default_sseu;
+ pg_sseu.slice_mask = 1;
+ pg_sseu.subslice_mask =
+ ~(~0 << (hweight32(default_sseu.subslice_mask) / 2));
+
+ pr_info("SSEU subtest '%s', flags=%x, def_slices=%u, pg_slices=%u\n",
+ name, flags, hweight32(default_sseu.slice_mask),
+ hweight32(pg_sseu.slice_mask));
+
+ file = mock_file(i915);
+ if (IS_ERR(file))
+ return PTR_ERR(file);
+
+ if (flags & TEST_RESET)
+ igt_global_reset_lock(i915);
+
+ mutex_lock(&i915->drm.struct_mutex);
+
+ ctx = i915_gem_create_context(i915, file->driver_priv);
+ if (IS_ERR(ctx)) {
+ ret = PTR_ERR(ctx);
+ goto out_unlock;
+ }
+
+ obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
+ if (IS_ERR(obj)) {
+ ret = PTR_ERR(obj);
+ goto out_unlock;
+ }
+
+ wakeref = intel_runtime_pm_get(i915);
+
+ /* First set the default mask. */
+ ret = __sseu_test(i915, name, flags, ctx, engine, obj, default_sseu);
+ if (ret)
+ goto out_fail;
+
+ /* Then set a power-gated configuration. */
+ ret = __sseu_test(i915, name, flags, ctx, engine, obj, pg_sseu);
+ if (ret)
+ goto out_fail;
+
+ /* Back to defaults. */
+ ret = __sseu_test(i915, name, flags, ctx, engine, obj, default_sseu);
+ if (ret)
+ goto out_fail;
+
+ /* One last power-gated configuration for the road. */
+ ret = __sseu_test(i915, name, flags, ctx, engine, obj, pg_sseu);
+ if (ret)
+ goto out_fail;
+
+out_fail:
+ if (igt_flush_test(i915, I915_WAIT_LOCKED))
+ ret = -EIO;
+
+ i915_gem_object_put(obj);
+
+ intel_runtime_pm_put(i915, wakeref);
+
+out_unlock:
+ mutex_unlock(&i915->drm.struct_mutex);
+
+ if (flags & TEST_RESET)
+ igt_global_reset_unlock(i915);
+
+ mock_file_free(i915, file);
+
+ if (ret)
+ pr_err("%s: Failed with %d!\n", name, ret);
+
+ return ret;
+}
+
+static int igt_ctx_sseu(void *arg)
+{
+ struct {
+ const char *name;
+ unsigned int flags;
+ } *phase, phases[] = {
+ { .name = "basic", .flags = 0 },
+ { .name = "idle", .flags = TEST_IDLE },
+ { .name = "busy", .flags = TEST_BUSY },
+ { .name = "busy-reset", .flags = TEST_BUSY | TEST_RESET },
+ { .name = "busy-idle", .flags = TEST_BUSY | TEST_IDLE },
+ { .name = "reset-idle", .flags = TEST_RESET | TEST_IDLE },
+ };
+ unsigned int i;
+ int ret = 0;
+
+ for (i = 0, phase = phases; ret == 0 && i < ARRAY_SIZE(phases);
+ i++, phase++)
+ ret = __igt_ctx_sseu(arg, phase->name, phase->flags);
+
+ return ret;
+}
+
static int igt_ctx_readonly(void *arg)
{
struct drm_i915_private *i915 = arg;
@@ -1162,6 +1633,7 @@ int i915_gem_context_live_selftests(struct drm_i915_private *dev_priv)
SUBTEST(live_nop_switch),
SUBTEST(igt_ctx_exec),
SUBTEST(igt_ctx_readonly),
+ SUBTEST(igt_ctx_sseu),
SUBTEST(igt_vm_isolation),
};
--
2.19.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 17+ messages in thread
* [PATCH 6/6] drm/i915/selftests: Context SSEU reconfiguration tests
2019-01-14 13:57 [PATCH 0/6] Per context dynamic (sub)slice power-gating Tvrtko Ursulin
@ 2019-01-14 13:57 ` Tvrtko Ursulin
0 siblings, 0 replies; 17+ messages in thread
From: Tvrtko Ursulin @ 2019-01-14 13:57 UTC (permalink / raw)
To: Intel-gfx
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Exercise the context image reconfiguration logic for idle and busy
contexts, with the resets thrown into the mix as well.
Free from the uAPI restrictions this test runs on all Gen9+ platforms
with slice power gating.
v2:
* Rename some helpers for clarity.
* Include subtest names in error logs.
* Remove unnecessary function export.
v3:
* Rebase for RUNTIME_INFO.
v4:
* Fix incomplete unexport from v2. (Chris Wilson)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
drivers/gpu/drm/i915/i915_gem_context.c | 31 +-
.../gpu/drm/i915/selftests/i915_gem_context.c | 481 ++++++++++++++++++
2 files changed, 502 insertions(+), 10 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index f65d3e9089b6..0444cfa96cf5 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -1042,23 +1042,19 @@ gen8_modify_rpcs_gpu(struct intel_context *ce,
}
static int
-i915_gem_context_reconfigure_sseu(struct i915_gem_context *ctx,
- struct intel_engine_cs *engine,
- struct intel_sseu sseu)
+__i915_gem_context_reconfigure_sseu(struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine,
+ struct intel_sseu sseu)
{
struct intel_context *ce = to_intel_context(ctx, engine);
- int ret;
+ int ret = 0;
GEM_BUG_ON(INTEL_GEN(ctx->i915) < 8);
GEM_BUG_ON(engine->id != RCS);
- ret = mutex_lock_interruptible(&ctx->i915->drm.struct_mutex);
- if (ret)
- return ret;
-
/* Nothing to do if unmodified. */
if (!memcmp(&ce->sseu, &sseu, sizeof(sseu)))
- goto out;
+ return 0;
/*
* If context is not idle we have to submit an ordered request to modify
@@ -1071,7 +1067,22 @@ i915_gem_context_reconfigure_sseu(struct i915_gem_context *ctx,
if (!ret)
ce->sseu = sseu;
-out:
+ return ret;
+}
+
+static int
+i915_gem_context_reconfigure_sseu(struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine,
+ struct intel_sseu sseu)
+{
+ int ret;
+
+ ret = mutex_lock_interruptible(&ctx->i915->drm.struct_mutex);
+ if (ret)
+ return ret;
+
+ ret = __i915_gem_context_reconfigure_sseu(ctx, engine, sseu);
+
mutex_unlock(&ctx->i915->drm.struct_mutex);
return ret;
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index d00cdf3c2939..c940381e2c66 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -27,6 +27,8 @@
#include "../i915_selftest.h"
#include "i915_random.h"
#include "igt_flush_test.h"
+#include "igt_reset.h"
+#include "igt_spinner.h"
#include "mock_drm.h"
#include "mock_gem_device.h"
@@ -650,6 +652,484 @@ static int igt_ctx_exec(void *arg)
return err;
}
+static struct i915_vma *rpcs_query_batch(struct i915_vma *vma)
+{
+ struct drm_i915_gem_object *obj;
+ u32 *cmd;
+ int err;
+
+ if (INTEL_GEN(vma->vm->i915) < 8)
+ return ERR_PTR(-EINVAL);
+
+ obj = i915_gem_object_create_internal(vma->vm->i915, PAGE_SIZE);
+ if (IS_ERR(obj))
+ return ERR_CAST(obj);
+
+ cmd = i915_gem_object_pin_map(obj, I915_MAP_WB);
+ if (IS_ERR(cmd)) {
+ err = PTR_ERR(cmd);
+ goto err;
+ }
+
+ *cmd++ = MI_STORE_REGISTER_MEM_GEN8;
+ *cmd++ = i915_mmio_reg_offset(GEN8_R_PWR_CLK_STATE);
+ *cmd++ = lower_32_bits(vma->node.start);
+ *cmd++ = upper_32_bits(vma->node.start);
+ *cmd = MI_BATCH_BUFFER_END;
+
+ i915_gem_object_unpin_map(obj);
+
+ err = i915_gem_object_set_to_gtt_domain(obj, false);
+ if (err)
+ goto err;
+
+ vma = i915_vma_instance(obj, vma->vm, NULL);
+ if (IS_ERR(vma)) {
+ err = PTR_ERR(vma);
+ goto err;
+ }
+
+ err = i915_vma_pin(vma, 0, 0, PIN_USER);
+ if (err)
+ goto err;
+
+ return vma;
+
+err:
+ i915_gem_object_put(obj);
+ return ERR_PTR(err);
+}
+
+static int
+emit_rpcs_query(struct drm_i915_gem_object *obj,
+ struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine,
+ struct i915_request **rq_out)
+{
+ struct i915_address_space *vm;
+ struct i915_request *rq;
+ struct i915_vma *batch;
+ struct i915_vma *vma;
+ int err;
+
+ GEM_BUG_ON(!ctx->ppgtt);
+ GEM_BUG_ON(!intel_engine_can_store_dword(engine));
+
+ vm = &ctx->ppgtt->vm;
+
+ vma = i915_vma_instance(obj, vm, NULL);
+ if (IS_ERR(vma))
+ return PTR_ERR(vma);
+
+ err = i915_gem_object_set_to_gtt_domain(obj, false);
+ if (err)
+ return err;
+
+ err = i915_vma_pin(vma, 0, 0, PIN_HIGH | PIN_USER);
+ if (err)
+ return err;
+
+ batch = rpcs_query_batch(vma);
+ if (IS_ERR(batch)) {
+ err = PTR_ERR(batch);
+ goto err_vma;
+ }
+
+ rq = i915_request_alloc(engine, ctx);
+ if (IS_ERR(rq)) {
+ err = PTR_ERR(rq);
+ goto err_batch;
+ }
+
+ err = engine->emit_bb_start(rq, batch->node.start, batch->node.size, 0);
+ if (err)
+ goto err_request;
+
+ err = i915_vma_move_to_active(batch, rq, 0);
+ if (err)
+ goto skip_request;
+
+ err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+ if (err)
+ goto skip_request;
+
+ i915_gem_object_set_active_reference(batch->obj);
+ i915_vma_unpin(batch);
+ i915_vma_close(batch);
+
+ i915_vma_unpin(vma);
+
+ *rq_out = i915_request_get(rq);
+
+ i915_request_add(rq);
+
+ return 0;
+
+skip_request:
+ i915_request_skip(rq, err);
+err_request:
+ i915_request_add(rq);
+err_batch:
+ i915_vma_unpin(batch);
+err_vma:
+ i915_vma_unpin(vma);
+
+ return err;
+}
+
+#define TEST_IDLE (1 << 0)
+#define TEST_BUSY (1 << 1)
+#define TEST_RESET (1 << 2)
+
+static int
+__sseu_prepare(struct drm_i915_private *i915,
+ const char *name,
+ unsigned int flags,
+ struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine,
+ struct igt_spinner **spin_out)
+{
+ int ret = 0;
+
+ if (flags & (TEST_BUSY | TEST_RESET)) {
+ struct igt_spinner *spin;
+ struct i915_request *rq;
+
+ spin = kzalloc(sizeof(*spin), GFP_KERNEL);
+ if (!spin) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ ret = igt_spinner_init(spin, i915);
+ if (ret)
+ return ret;
+
+ rq = igt_spinner_create_request(spin, ctx, engine, MI_NOOP);
+ if (IS_ERR(rq)) {
+ ret = PTR_ERR(rq);
+ igt_spinner_fini(spin);
+ kfree(spin);
+ goto out;
+ }
+
+ i915_request_add(rq);
+
+ if (!igt_wait_for_spinner(spin, rq)) {
+ pr_err("%s: Spinner failed to start!\n", name);
+ igt_spinner_end(spin);
+ igt_spinner_fini(spin);
+ kfree(spin);
+ ret = -ETIMEDOUT;
+ goto out;
+ }
+
+ *spin_out = spin;
+ }
+
+out:
+ return ret;
+}
+
+static int
+__read_slice_count(struct drm_i915_private *i915,
+ struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine,
+ struct drm_i915_gem_object *obj,
+ struct igt_spinner *spin,
+ u32 *rpcs)
+{
+ struct i915_request *rq = NULL;
+ u32 s_mask, s_shift;
+ unsigned int cnt;
+ u32 *buf, val;
+ long ret;
+
+ ret = emit_rpcs_query(obj, ctx, engine, &rq);
+ if (ret)
+ return ret;
+
+ if (spin)
+ igt_spinner_end(spin);
+
+ ret = i915_request_wait(rq, I915_WAIT_LOCKED, MAX_SCHEDULE_TIMEOUT);
+ if (ret <= 0)
+ return ret < 0 ? ret : -ETIME;
+
+ i915_request_put(rq);
+
+ buf = i915_gem_object_pin_map(obj, I915_MAP_WB);
+ if (IS_ERR(buf)) {
+ ret = PTR_ERR(buf);
+ return ret;
+ }
+
+ if (INTEL_GEN(i915) >= 11) {
+ s_mask = GEN11_RPCS_S_CNT_MASK;
+ s_shift = GEN11_RPCS_S_CNT_SHIFT;
+ } else {
+ s_mask = GEN8_RPCS_S_CNT_MASK;
+ s_shift = GEN8_RPCS_S_CNT_SHIFT;
+ }
+
+ val = *buf;
+ cnt = (val & s_mask) >> s_shift;
+ *rpcs = val;
+
+ i915_gem_object_unpin_map(obj);
+
+ return cnt;
+}
+
+static void __err_rpcs(u32 rpcs, unsigned int slices)
+{
+ pr_info("RPCS=0x%x; %u%sx%u%s\n",
+ rpcs, slices,
+ (rpcs & GEN8_RPCS_S_CNT_ENABLE) ? "*" : "",
+ (rpcs & GEN8_RPCS_SS_CNT_MASK) >> GEN8_RPCS_SS_CNT_SHIFT,
+ (rpcs & GEN8_RPCS_SS_CNT_ENABLE) ? "*" : "");
+}
+
+static int
+__sseu_finish(struct drm_i915_private *i915,
+ const char *name,
+ unsigned int flags,
+ struct i915_gem_context *ctx,
+ struct i915_gem_context *kctx,
+ struct intel_engine_cs *engine,
+ struct drm_i915_gem_object *obj,
+ unsigned int expected,
+ struct igt_spinner *spin)
+{
+ unsigned int slices =
+ hweight32(intel_device_default_sseu(i915).slice_mask);
+ u32 rpcs = 0;
+ int ret = 0;
+
+ if (flags & TEST_RESET) {
+ ret = i915_reset_engine(engine, "sseu");
+ if (ret)
+ goto out;
+ }
+
+ ret = __read_slice_count(i915, ctx, engine, obj,
+ flags & TEST_RESET ? NULL : spin, &rpcs);
+ if (ret < 0) {
+ goto out;
+ } else if (ret != expected) {
+ pr_err("%s: Context slice count %d is not %u!\n",
+ name, ret, expected);
+ __err_rpcs(rpcs, ret);
+ ret = -EINVAL;
+ goto out;
+ } else {
+ ret = 0;
+ }
+
+ ret = __read_slice_count(i915, kctx, engine, obj, NULL, &rpcs);
+ if (ret < 0) {
+ goto out;
+ } else if (ret != slices) {
+ pr_err("%s: Kernel context slice count %d is not %u!\n",
+ name, ret, slices);
+ __err_rpcs(rpcs, ret);
+ ret = -EINVAL;
+ goto out;
+ } else {
+ ret = 0;
+ }
+
+out:
+ if (spin)
+ igt_spinner_end(spin);
+
+ if (flags & TEST_IDLE) {
+ ret = i915_gem_wait_for_idle(i915,
+ I915_WAIT_LOCKED,
+ MAX_SCHEDULE_TIMEOUT);
+ if (ret)
+ return ret;
+
+ ret = __read_slice_count(i915, ctx, engine, obj, NULL, &rpcs);
+ if (ret < 0) {
+ return ret;
+ } else if (ret != expected) {
+ pr_err("%s: Context slice count %d is not %u after idle!\n",
+ name, ret, expected);
+ __err_rpcs(rpcs, ret);
+ return -EINVAL;
+ } else {
+ ret = 0;
+ }
+ }
+
+ return ret;
+
+}
+
+static int
+__sseu_test(struct drm_i915_private *i915,
+ const char *name,
+ unsigned int flags,
+ struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine,
+ struct drm_i915_gem_object *obj,
+ struct intel_sseu sseu)
+{
+ struct igt_spinner *spin = NULL;
+ struct i915_gem_context *kctx;
+ int ret;
+
+ kctx = kernel_context(i915);
+ if (IS_ERR(kctx))
+ return PTR_ERR(kctx);
+
+ ret = __sseu_prepare(i915, name, flags, ctx, engine, &spin);
+ if (ret)
+ goto out;
+
+ ret = __i915_gem_context_reconfigure_sseu(ctx, engine, sseu);
+ if (ret)
+ goto out;
+
+ ret = __sseu_finish(i915, name, flags, ctx, kctx, engine, obj,
+ hweight32(sseu.slice_mask), spin);
+
+out:
+ if (spin) {
+ igt_spinner_end(spin);
+ igt_spinner_fini(spin);
+ kfree(spin);
+ }
+
+ kernel_context_close(kctx);
+
+ return ret;
+}
+
+static int
+__igt_ctx_sseu(struct drm_i915_private *i915,
+ const char *name,
+ unsigned int flags)
+{
+ struct intel_sseu default_sseu = intel_device_default_sseu(i915);
+ struct intel_engine_cs *engine = i915->engine[RCS];
+ struct drm_i915_gem_object *obj;
+ struct i915_gem_context *ctx;
+ struct intel_sseu pg_sseu;
+ struct drm_file *file;
+ int ret;
+
+ if (INTEL_GEN(i915) < 9)
+ return 0;
+
+ if (!RUNTIME_INFO(i915)->sseu.has_slice_pg)
+ return 0;
+
+ if (hweight32(default_sseu.slice_mask) < 2)
+ return 0;
+
+ /*
+ * Gen11 VME friendly power-gated configuration with half enabled
+ * sub-slices.
+ */
+ pg_sseu = default_sseu;
+ pg_sseu.slice_mask = 1;
+ pg_sseu.subslice_mask =
+ ~(~0 << (hweight32(default_sseu.subslice_mask) / 2));
+
+ pr_info("SSEU subtest '%s', flags=%x, def_slices=%u, pg_slices=%u\n",
+ name, flags, hweight32(default_sseu.slice_mask),
+ hweight32(pg_sseu.slice_mask));
+
+ file = mock_file(i915);
+ if (IS_ERR(file))
+ return PTR_ERR(file);
+
+ if (flags & TEST_RESET)
+ igt_global_reset_lock(i915);
+
+ mutex_lock(&i915->drm.struct_mutex);
+
+ ctx = i915_gem_create_context(i915, file->driver_priv);
+ if (IS_ERR(ctx)) {
+ ret = PTR_ERR(ctx);
+ goto out_unlock;
+ }
+
+ obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
+ if (IS_ERR(obj)) {
+ ret = PTR_ERR(obj);
+ goto out_unlock;
+ }
+
+ intel_runtime_pm_get(i915);
+
+ /* First set the default mask. */
+ ret = __sseu_test(i915, name, flags, ctx, engine, obj, default_sseu);
+ if (ret)
+ goto out_fail;
+
+ /* Then set a power-gated configuration. */
+ ret = __sseu_test(i915, name, flags, ctx, engine, obj, pg_sseu);
+ if (ret)
+ goto out_fail;
+
+ /* Back to defaults. */
+ ret = __sseu_test(i915, name, flags, ctx, engine, obj, default_sseu);
+ if (ret)
+ goto out_fail;
+
+ /* One last power-gated configuration for the road. */
+ ret = __sseu_test(i915, name, flags, ctx, engine, obj, pg_sseu);
+ if (ret)
+ goto out_fail;
+
+out_fail:
+ if (igt_flush_test(i915, I915_WAIT_LOCKED))
+ ret = -EIO;
+
+ i915_gem_object_put(obj);
+
+ intel_runtime_pm_put(i915);
+
+out_unlock:
+ mutex_unlock(&i915->drm.struct_mutex);
+
+ if (flags & TEST_RESET)
+ igt_global_reset_unlock(i915);
+
+ mock_file_free(i915, file);
+
+ if (ret)
+ pr_err("%s: Failed with %d!\n", name, ret);
+
+ return ret;
+}
+
+static int igt_ctx_sseu(void *arg)
+{
+ struct {
+ const char *name;
+ unsigned int flags;
+ } *phase, phases[] = {
+ { .name = "basic", .flags = 0 },
+ { .name = "idle", .flags = TEST_IDLE },
+ { .name = "busy", .flags = TEST_BUSY },
+ { .name = "busy-reset", .flags = TEST_BUSY | TEST_RESET },
+ { .name = "busy-idle", .flags = TEST_BUSY | TEST_IDLE },
+ { .name = "reset-idle", .flags = TEST_RESET | TEST_IDLE },
+ };
+ unsigned int i;
+ int ret = 0;
+
+ for (i = 0, phase = phases; ret == 0 && i < ARRAY_SIZE(phases);
+ i++, phase++)
+ ret = __igt_ctx_sseu(arg, phase->name, phase->flags);
+
+ return ret;
+}
+
static int igt_ctx_readonly(void *arg)
{
struct drm_i915_private *i915 = arg;
@@ -1232,6 +1712,7 @@ int i915_gem_context_live_selftests(struct drm_i915_private *dev_priv)
SUBTEST(live_nop_switch),
SUBTEST(igt_ctx_exec),
SUBTEST(igt_ctx_readonly),
+ SUBTEST(igt_ctx_sseu),
SUBTEST(igt_vm_isolation),
};
--
2.19.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 17+ messages in thread
* [PATCH 6/6] drm/i915/selftests: Context SSEU reconfiguration tests
2019-01-08 15:12 [PATCH 0/6] Per context dynamic (sub)slice power-gating Tvrtko Ursulin
@ 2019-01-08 15:12 ` Tvrtko Ursulin
0 siblings, 0 replies; 17+ messages in thread
From: Tvrtko Ursulin @ 2019-01-08 15:12 UTC (permalink / raw)
To: Intel-gfx
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Exercise the context image reconfiguration logic for idle and busy
contexts, with the resets thrown into the mix as well.
Free from the uAPI restrictions this test runs on all Gen9+ platforms
with slice power gating.
v2:
* Rename some helpers for clarity.
* Include subtest names in error logs.
* Remove unnecessary function export.
v3:
* Rebase for RUNTIME_INFO.
v4:
* Fix incomplete unexport from v2. (Chris Wilson)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
drivers/gpu/drm/i915/i915_gem_context.c | 31 +-
.../gpu/drm/i915/selftests/i915_gem_context.c | 481 ++++++++++++++++++
2 files changed, 502 insertions(+), 10 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 1ab7d6980c36..c395141e26b5 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -1043,23 +1043,19 @@ gen8_modify_rpcs_gpu(struct intel_context *ce,
}
static int
-i915_gem_context_reconfigure_sseu(struct i915_gem_context *ctx,
- struct intel_engine_cs *engine,
- struct intel_sseu sseu)
+__i915_gem_context_reconfigure_sseu(struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine,
+ struct intel_sseu sseu)
{
struct intel_context *ce = to_intel_context(ctx, engine);
- int ret;
+ int ret = 0;
GEM_BUG_ON(INTEL_GEN(ctx->i915) < 8);
GEM_BUG_ON(engine->id != RCS);
- ret = mutex_lock_interruptible(&ctx->i915->drm.struct_mutex);
- if (ret)
- return ret;
-
/* Nothing to do if unmodified. */
if (!memcmp(&ce->sseu, &sseu, sizeof(sseu)))
- goto out;
+ return 0;
/*
* If context is not idle we have to submit an ordered request to modify
@@ -1072,7 +1068,22 @@ i915_gem_context_reconfigure_sseu(struct i915_gem_context *ctx,
if (!ret)
ce->sseu = sseu;
-out:
+ return ret;
+}
+
+static int
+i915_gem_context_reconfigure_sseu(struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine,
+ struct intel_sseu sseu)
+{
+ int ret;
+
+ ret = mutex_lock_interruptible(&ctx->i915->drm.struct_mutex);
+ if (ret)
+ return ret;
+
+ ret = __i915_gem_context_reconfigure_sseu(ctx, engine, sseu);
+
mutex_unlock(&ctx->i915->drm.struct_mutex);
return ret;
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index d00cdf3c2939..c940381e2c66 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -27,6 +27,8 @@
#include "../i915_selftest.h"
#include "i915_random.h"
#include "igt_flush_test.h"
+#include "igt_reset.h"
+#include "igt_spinner.h"
#include "mock_drm.h"
#include "mock_gem_device.h"
@@ -650,6 +652,484 @@ static int igt_ctx_exec(void *arg)
return err;
}
+static struct i915_vma *rpcs_query_batch(struct i915_vma *vma)
+{
+ struct drm_i915_gem_object *obj;
+ u32 *cmd;
+ int err;
+
+ if (INTEL_GEN(vma->vm->i915) < 8)
+ return ERR_PTR(-EINVAL);
+
+ obj = i915_gem_object_create_internal(vma->vm->i915, PAGE_SIZE);
+ if (IS_ERR(obj))
+ return ERR_CAST(obj);
+
+ cmd = i915_gem_object_pin_map(obj, I915_MAP_WB);
+ if (IS_ERR(cmd)) {
+ err = PTR_ERR(cmd);
+ goto err;
+ }
+
+ *cmd++ = MI_STORE_REGISTER_MEM_GEN8;
+ *cmd++ = i915_mmio_reg_offset(GEN8_R_PWR_CLK_STATE);
+ *cmd++ = lower_32_bits(vma->node.start);
+ *cmd++ = upper_32_bits(vma->node.start);
+ *cmd = MI_BATCH_BUFFER_END;
+
+ i915_gem_object_unpin_map(obj);
+
+ err = i915_gem_object_set_to_gtt_domain(obj, false);
+ if (err)
+ goto err;
+
+ vma = i915_vma_instance(obj, vma->vm, NULL);
+ if (IS_ERR(vma)) {
+ err = PTR_ERR(vma);
+ goto err;
+ }
+
+ err = i915_vma_pin(vma, 0, 0, PIN_USER);
+ if (err)
+ goto err;
+
+ return vma;
+
+err:
+ i915_gem_object_put(obj);
+ return ERR_PTR(err);
+}
+
+static int
+emit_rpcs_query(struct drm_i915_gem_object *obj,
+ struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine,
+ struct i915_request **rq_out)
+{
+ struct i915_address_space *vm;
+ struct i915_request *rq;
+ struct i915_vma *batch;
+ struct i915_vma *vma;
+ int err;
+
+ GEM_BUG_ON(!ctx->ppgtt);
+ GEM_BUG_ON(!intel_engine_can_store_dword(engine));
+
+ vm = &ctx->ppgtt->vm;
+
+ vma = i915_vma_instance(obj, vm, NULL);
+ if (IS_ERR(vma))
+ return PTR_ERR(vma);
+
+ err = i915_gem_object_set_to_gtt_domain(obj, false);
+ if (err)
+ return err;
+
+ err = i915_vma_pin(vma, 0, 0, PIN_HIGH | PIN_USER);
+ if (err)
+ return err;
+
+ batch = rpcs_query_batch(vma);
+ if (IS_ERR(batch)) {
+ err = PTR_ERR(batch);
+ goto err_vma;
+ }
+
+ rq = i915_request_alloc(engine, ctx);
+ if (IS_ERR(rq)) {
+ err = PTR_ERR(rq);
+ goto err_batch;
+ }
+
+ err = engine->emit_bb_start(rq, batch->node.start, batch->node.size, 0);
+ if (err)
+ goto err_request;
+
+ err = i915_vma_move_to_active(batch, rq, 0);
+ if (err)
+ goto skip_request;
+
+ err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+ if (err)
+ goto skip_request;
+
+ i915_gem_object_set_active_reference(batch->obj);
+ i915_vma_unpin(batch);
+ i915_vma_close(batch);
+
+ i915_vma_unpin(vma);
+
+ *rq_out = i915_request_get(rq);
+
+ i915_request_add(rq);
+
+ return 0;
+
+skip_request:
+ i915_request_skip(rq, err);
+err_request:
+ i915_request_add(rq);
+err_batch:
+ i915_vma_unpin(batch);
+err_vma:
+ i915_vma_unpin(vma);
+
+ return err;
+}
+
+#define TEST_IDLE (1 << 0)
+#define TEST_BUSY (1 << 1)
+#define TEST_RESET (1 << 2)
+
+static int
+__sseu_prepare(struct drm_i915_private *i915,
+ const char *name,
+ unsigned int flags,
+ struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine,
+ struct igt_spinner **spin_out)
+{
+ int ret = 0;
+
+ if (flags & (TEST_BUSY | TEST_RESET)) {
+ struct igt_spinner *spin;
+ struct i915_request *rq;
+
+ spin = kzalloc(sizeof(*spin), GFP_KERNEL);
+ if (!spin) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ ret = igt_spinner_init(spin, i915);
+ if (ret)
+ return ret;
+
+ rq = igt_spinner_create_request(spin, ctx, engine, MI_NOOP);
+ if (IS_ERR(rq)) {
+ ret = PTR_ERR(rq);
+ igt_spinner_fini(spin);
+ kfree(spin);
+ goto out;
+ }
+
+ i915_request_add(rq);
+
+ if (!igt_wait_for_spinner(spin, rq)) {
+ pr_err("%s: Spinner failed to start!\n", name);
+ igt_spinner_end(spin);
+ igt_spinner_fini(spin);
+ kfree(spin);
+ ret = -ETIMEDOUT;
+ goto out;
+ }
+
+ *spin_out = spin;
+ }
+
+out:
+ return ret;
+}
+
+static int
+__read_slice_count(struct drm_i915_private *i915,
+ struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine,
+ struct drm_i915_gem_object *obj,
+ struct igt_spinner *spin,
+ u32 *rpcs)
+{
+ struct i915_request *rq = NULL;
+ u32 s_mask, s_shift;
+ unsigned int cnt;
+ u32 *buf, val;
+ long ret;
+
+ ret = emit_rpcs_query(obj, ctx, engine, &rq);
+ if (ret)
+ return ret;
+
+ if (spin)
+ igt_spinner_end(spin);
+
+ ret = i915_request_wait(rq, I915_WAIT_LOCKED, MAX_SCHEDULE_TIMEOUT);
+ if (ret <= 0)
+ return ret < 0 ? ret : -ETIME;
+
+ i915_request_put(rq);
+
+ buf = i915_gem_object_pin_map(obj, I915_MAP_WB);
+ if (IS_ERR(buf)) {
+ ret = PTR_ERR(buf);
+ return ret;
+ }
+
+ if (INTEL_GEN(i915) >= 11) {
+ s_mask = GEN11_RPCS_S_CNT_MASK;
+ s_shift = GEN11_RPCS_S_CNT_SHIFT;
+ } else {
+ s_mask = GEN8_RPCS_S_CNT_MASK;
+ s_shift = GEN8_RPCS_S_CNT_SHIFT;
+ }
+
+ val = *buf;
+ cnt = (val & s_mask) >> s_shift;
+ *rpcs = val;
+
+ i915_gem_object_unpin_map(obj);
+
+ return cnt;
+}
+
+static void __err_rpcs(u32 rpcs, unsigned int slices)
+{
+ pr_info("RPCS=0x%x; %u%sx%u%s\n",
+ rpcs, slices,
+ (rpcs & GEN8_RPCS_S_CNT_ENABLE) ? "*" : "",
+ (rpcs & GEN8_RPCS_SS_CNT_MASK) >> GEN8_RPCS_SS_CNT_SHIFT,
+ (rpcs & GEN8_RPCS_SS_CNT_ENABLE) ? "*" : "");
+}
+
+static int
+__sseu_finish(struct drm_i915_private *i915,
+ const char *name,
+ unsigned int flags,
+ struct i915_gem_context *ctx,
+ struct i915_gem_context *kctx,
+ struct intel_engine_cs *engine,
+ struct drm_i915_gem_object *obj,
+ unsigned int expected,
+ struct igt_spinner *spin)
+{
+ unsigned int slices =
+ hweight32(intel_device_default_sseu(i915).slice_mask);
+ u32 rpcs = 0;
+ int ret = 0;
+
+ if (flags & TEST_RESET) {
+ ret = i915_reset_engine(engine, "sseu");
+ if (ret)
+ goto out;
+ }
+
+ ret = __read_slice_count(i915, ctx, engine, obj,
+ flags & TEST_RESET ? NULL : spin, &rpcs);
+ if (ret < 0) {
+ goto out;
+ } else if (ret != expected) {
+ pr_err("%s: Context slice count %d is not %u!\n",
+ name, ret, expected);
+ __err_rpcs(rpcs, ret);
+ ret = -EINVAL;
+ goto out;
+ } else {
+ ret = 0;
+ }
+
+ ret = __read_slice_count(i915, kctx, engine, obj, NULL, &rpcs);
+ if (ret < 0) {
+ goto out;
+ } else if (ret != slices) {
+ pr_err("%s: Kernel context slice count %d is not %u!\n",
+ name, ret, slices);
+ __err_rpcs(rpcs, ret);
+ ret = -EINVAL;
+ goto out;
+ } else {
+ ret = 0;
+ }
+
+out:
+ if (spin)
+ igt_spinner_end(spin);
+
+ if (flags & TEST_IDLE) {
+ ret = i915_gem_wait_for_idle(i915,
+ I915_WAIT_LOCKED,
+ MAX_SCHEDULE_TIMEOUT);
+ if (ret)
+ return ret;
+
+ ret = __read_slice_count(i915, ctx, engine, obj, NULL, &rpcs);
+ if (ret < 0) {
+ return ret;
+ } else if (ret != expected) {
+ pr_err("%s: Context slice count %d is not %u after idle!\n",
+ name, ret, expected);
+ __err_rpcs(rpcs, ret);
+ return -EINVAL;
+ } else {
+ ret = 0;
+ }
+ }
+
+ return ret;
+
+}
+
+static int
+__sseu_test(struct drm_i915_private *i915,
+ const char *name,
+ unsigned int flags,
+ struct i915_gem_context *ctx,
+ struct intel_engine_cs *engine,
+ struct drm_i915_gem_object *obj,
+ struct intel_sseu sseu)
+{
+ struct igt_spinner *spin = NULL;
+ struct i915_gem_context *kctx;
+ int ret;
+
+ kctx = kernel_context(i915);
+ if (IS_ERR(kctx))
+ return PTR_ERR(kctx);
+
+ ret = __sseu_prepare(i915, name, flags, ctx, engine, &spin);
+ if (ret)
+ goto out;
+
+ ret = __i915_gem_context_reconfigure_sseu(ctx, engine, sseu);
+ if (ret)
+ goto out;
+
+ ret = __sseu_finish(i915, name, flags, ctx, kctx, engine, obj,
+ hweight32(sseu.slice_mask), spin);
+
+out:
+ if (spin) {
+ igt_spinner_end(spin);
+ igt_spinner_fini(spin);
+ kfree(spin);
+ }
+
+ kernel_context_close(kctx);
+
+ return ret;
+}
+
+static int
+__igt_ctx_sseu(struct drm_i915_private *i915,
+ const char *name,
+ unsigned int flags)
+{
+ struct intel_sseu default_sseu = intel_device_default_sseu(i915);
+ struct intel_engine_cs *engine = i915->engine[RCS];
+ struct drm_i915_gem_object *obj;
+ struct i915_gem_context *ctx;
+ struct intel_sseu pg_sseu;
+ struct drm_file *file;
+ int ret;
+
+ if (INTEL_GEN(i915) < 9)
+ return 0;
+
+ if (!RUNTIME_INFO(i915)->sseu.has_slice_pg)
+ return 0;
+
+ if (hweight32(default_sseu.slice_mask) < 2)
+ return 0;
+
+ /*
+ * Gen11 VME friendly power-gated configuration with half enabled
+ * sub-slices.
+ */
+ pg_sseu = default_sseu;
+ pg_sseu.slice_mask = 1;
+ pg_sseu.subslice_mask =
+ ~(~0 << (hweight32(default_sseu.subslice_mask) / 2));
+
+ pr_info("SSEU subtest '%s', flags=%x, def_slices=%u, pg_slices=%u\n",
+ name, flags, hweight32(default_sseu.slice_mask),
+ hweight32(pg_sseu.slice_mask));
+
+ file = mock_file(i915);
+ if (IS_ERR(file))
+ return PTR_ERR(file);
+
+ if (flags & TEST_RESET)
+ igt_global_reset_lock(i915);
+
+ mutex_lock(&i915->drm.struct_mutex);
+
+ ctx = i915_gem_create_context(i915, file->driver_priv);
+ if (IS_ERR(ctx)) {
+ ret = PTR_ERR(ctx);
+ goto out_unlock;
+ }
+
+ obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
+ if (IS_ERR(obj)) {
+ ret = PTR_ERR(obj);
+ goto out_unlock;
+ }
+
+ intel_runtime_pm_get(i915);
+
+ /* First set the default mask. */
+ ret = __sseu_test(i915, name, flags, ctx, engine, obj, default_sseu);
+ if (ret)
+ goto out_fail;
+
+ /* Then set a power-gated configuration. */
+ ret = __sseu_test(i915, name, flags, ctx, engine, obj, pg_sseu);
+ if (ret)
+ goto out_fail;
+
+ /* Back to defaults. */
+ ret = __sseu_test(i915, name, flags, ctx, engine, obj, default_sseu);
+ if (ret)
+ goto out_fail;
+
+ /* One last power-gated configuration for the road. */
+ ret = __sseu_test(i915, name, flags, ctx, engine, obj, pg_sseu);
+ if (ret)
+ goto out_fail;
+
+out_fail:
+ if (igt_flush_test(i915, I915_WAIT_LOCKED))
+ ret = -EIO;
+
+ i915_gem_object_put(obj);
+
+ intel_runtime_pm_put(i915);
+
+out_unlock:
+ mutex_unlock(&i915->drm.struct_mutex);
+
+ if (flags & TEST_RESET)
+ igt_global_reset_unlock(i915);
+
+ mock_file_free(i915, file);
+
+ if (ret)
+ pr_err("%s: Failed with %d!\n", name, ret);
+
+ return ret;
+}
+
+static int igt_ctx_sseu(void *arg)
+{
+ struct {
+ const char *name;
+ unsigned int flags;
+ } *phase, phases[] = {
+ { .name = "basic", .flags = 0 },
+ { .name = "idle", .flags = TEST_IDLE },
+ { .name = "busy", .flags = TEST_BUSY },
+ { .name = "busy-reset", .flags = TEST_BUSY | TEST_RESET },
+ { .name = "busy-idle", .flags = TEST_BUSY | TEST_IDLE },
+ { .name = "reset-idle", .flags = TEST_RESET | TEST_IDLE },
+ };
+ unsigned int i;
+ int ret = 0;
+
+ for (i = 0, phase = phases; ret == 0 && i < ARRAY_SIZE(phases);
+ i++, phase++)
+ ret = __igt_ctx_sseu(arg, phase->name, phase->flags);
+
+ return ret;
+}
+
static int igt_ctx_readonly(void *arg)
{
struct drm_i915_private *i915 = arg;
@@ -1232,6 +1712,7 @@ int i915_gem_context_live_selftests(struct drm_i915_private *dev_priv)
SUBTEST(live_nop_switch),
SUBTEST(igt_ctx_exec),
SUBTEST(igt_ctx_readonly),
+ SUBTEST(igt_ctx_sseu),
SUBTEST(igt_vm_isolation),
};
--
2.19.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 17+ messages in thread