summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
diff options
context:
space:
mode:
authorDave Airlie <airlied@redhat.com>2024-04-30 14:20:31 +1000
committerDave Airlie <airlied@redhat.com>2024-04-30 14:40:43 +1000
commit68b89e23c2282877b0d411e07a3ef90490d6fe30 (patch)
treeb9be4b583185edfdb72255819ae8c3680166fb67 /drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
parentb84bc948528e6474ba48596144e9c17466a98448 (diff)
parent4d3421e04c5dc38baf15224c051256204f223c15 (diff)
downloadlinux-68b89e23c2282877b0d411e07a3ef90490d6fe30.tar.gz
linux-68b89e23c2282877b0d411e07a3ef90490d6fe30.tar.bz2
linux-68b89e23c2282877b0d411e07a3ef90490d6fe30.zip
Merge tag 'drm-intel-gt-next-2024-04-26' of https://anongit.freedesktop.org/git/drm/drm-intel into drm-next
UAPI Changes: - drm/i915/guc: Use context hints for GT frequency Allow user to provide a low latency context hint. When set, KMD sends a hint to GuC which results in special handling for this context. SLPC will ramp the GT frequency aggressively every time it switches to this context. The down freq threshold will also be lower so GuC will ramp down the GT freq for this context more slowly. We also disable waitboost for this context as that will interfere with the strategy. We need to enable the use of SLPC Compute strategy during init, but it will apply only to contexts that set this bit during context creation. Userland can check whether this feature is supported using a new param- I915_PARAM_HAS_CONTEXT_FREQ_HINT. This flag is true for all guc submission enabled platforms as they use SLPC for frequency management. The Mesa usage model for this flag is here - https://gitlab.freedesktop.org/sushmave/mesa/-/commits/compute_hint - drm/i915/gt: Enable only one CCS for compute workload Enable only one CCS engine by default with all the compute sices allocated to it. While generating the list of UABI engines to be exposed to the user, exclude any additional CCS engines beyond the first instance *** NOTE: This W/A will make all DG2 SKUs appear like single CCS SKUs by default to mitigate a hardware bug. All the EUs will still remain usable, and all the userspace drivers have been confirmed to be able to dynamically detect the change in number of CCS engines and adjust. For the smaller percent of applications that get perf benefit from letting the userspace driver dispatch across all 4 CCS engines we will be introducing a sysfs control as a later patch to choose 4 CCS each with 25% EUs (or 50% if 2 CCS). NOTE: A regression has been reported at https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/10895 However Andi has been triaging the issue and we're closing in a fix to the gap in the W/A implementation: https://lists.freedesktop.org/archives/intel-gfx/2024-April/348747.html Driver Changes: - Add new and fix to existing workarounds: Wa_14018575942 (MTL), Wa_16019325821 (Gen12.70), Wa_14019159160 (MTL), Wa_16015675438, Wa_14020495402 (Gen12.70) (Tejas, John, Lucas) - Fix UAF on destroy against retire race and remove two earlier partial fixes (Janusz) - Limit the reserved VM space to only the platforms that need it (Andi) - Reset queue_priority_hint on parking for execlist platforms (Chris) - Fix gt reset with GuC submission is disabled (Nirmoy) - Correct capture of EIR register on hang (John) - Remove usage of the deprecated ida_simple_xx() API - Refactor confusing __intel_gt_reset() (Nirmoy) - Fix the fix for GuC reset lock confusion (John) - Simplify/extend platform check for Wa_14018913170 (John) - Replace dev_priv with i915 (Andi) - Add and use gt_to_guc() wrapper (Andi) - Remove bogus null check (Rodrigo, Dan) . Selftest improvements (Janusz, Nirmoy, Daniele) Signed-off-by: Dave Airlie <airlied@redhat.com> From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/ZitVBTvZmityDi7D@jlahtine-mobl.ger.corp.intel.com
Diffstat (limited to 'drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c')
-rw-r--r--drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c22
1 files changed, 2 insertions, 20 deletions
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index d3a771afb083..42619fc05de4 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -255,7 +255,6 @@ struct i915_execbuffer {
struct intel_context *context; /* logical state for the request */
struct i915_gem_context *gem_context; /** caller's context */
intel_wakeref_t wakeref;
- intel_wakeref_t wakeref_gt0;
/** our requests to build */
struct i915_request *requests[MAX_ENGINE_INSTANCE + 1];
@@ -2457,7 +2456,7 @@ static int eb_submit(struct i915_execbuffer *eb)
* The engine index is returned.
*/
static unsigned int
-gen8_dispatch_bsd_engine(struct drm_i915_private *dev_priv,
+gen8_dispatch_bsd_engine(struct drm_i915_private *i915,
struct drm_file *file)
{
struct drm_i915_file_private *file_priv = file->driver_priv;
@@ -2465,7 +2464,7 @@ gen8_dispatch_bsd_engine(struct drm_i915_private *dev_priv,
/* Check whether the file_priv has already selected one ring. */
if ((int)file_priv->bsd_engine < 0)
file_priv->bsd_engine =
- get_random_u32_below(dev_priv->engine_uabi_class_count[I915_ENGINE_CLASS_VIDEO]);
+ get_random_u32_below(i915->engine_uabi_class_count[I915_ENGINE_CLASS_VIDEO]);
return file_priv->bsd_engine;
}
@@ -2686,7 +2685,6 @@ static int
eb_select_engine(struct i915_execbuffer *eb)
{
struct intel_context *ce, *child;
- struct intel_gt *gt;
unsigned int idx;
int err;
@@ -2710,17 +2708,10 @@ eb_select_engine(struct i915_execbuffer *eb)
}
}
eb->num_batches = ce->parallel.number_children + 1;
- gt = ce->engine->gt;
for_each_child(ce, child)
intel_context_get(child);
eb->wakeref = intel_gt_pm_get(ce->engine->gt);
- /*
- * Keep GT0 active on MTL so that i915_vma_parked() doesn't
- * free VMAs while execbuf ioctl is validating VMAs.
- */
- if (gt->info.id)
- eb->wakeref_gt0 = intel_gt_pm_get(to_gt(gt->i915));
if (!test_bit(CONTEXT_ALLOC_BIT, &ce->flags)) {
err = intel_context_alloc_state(ce);
@@ -2759,9 +2750,6 @@ eb_select_engine(struct i915_execbuffer *eb)
return err;
err:
- if (gt->info.id)
- intel_gt_pm_put(to_gt(gt->i915), eb->wakeref_gt0);
-
intel_gt_pm_put(ce->engine->gt, eb->wakeref);
for_each_child(ce, child)
intel_context_put(child);
@@ -2775,12 +2763,6 @@ eb_put_engine(struct i915_execbuffer *eb)
struct intel_context *child;
i915_vm_put(eb->context->vm);
- /*
- * This works in conjunction with eb_select_engine() to prevent
- * i915_vma_parked() from interfering while execbuf validates vmas.
- */
- if (eb->gt->info.id)
- intel_gt_pm_put(to_gt(eb->gt->i915), eb->wakeref_gt0);
intel_gt_pm_put(eb->context->engine->gt, eb->wakeref);
for_each_child(eb->context, child)
intel_context_put(child);