[Intel-gfx] [PATCH 04/11] drm/i915: Add EU stride runtime parameter
Stuart Summers
stuart.summers at intel.com
Thu Aug 22 18:32:06 UTC 2019
Add a new SSEU runtime parameter, eu_stride, which is
used to mirror the userspace concept of a range of EUs
per subslice.
This patch simply adds the parameter and updates usage
in the QUERY_TOPOLOGY_INFO handler.
v2: Add GEM_BUG_ON to make sure eu_stride is valid
Signed-off-by: Stuart Summers <stuart.summers at intel.com>
Reviewed-by: Chris Wilson <chris at chris-wilson.co.uk>
---
drivers/gpu/drm/i915/gt/intel_sseu.c | 2 ++
drivers/gpu/drm/i915/gt/intel_sseu.h | 3 +++
drivers/gpu/drm/i915/i915_query.c | 5 ++---
drivers/gpu/drm/i915/intel_device_info.c | 9 ++++-----
4 files changed, 11 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.c b/drivers/gpu/drm/i915/gt/intel_sseu.c
index edf39ae132c3..d52686a1afdc 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.c
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.c
@@ -17,6 +17,8 @@ void intel_sseu_set_info(struct sseu_dev_info *sseu, u8 max_slices,
sseu->ss_stride = GEN_SSEU_STRIDE(sseu->max_subslices);
GEM_BUG_ON(sseu->ss_stride > GEN_MAX_SUBSLICE_STRIDE);
+ sseu->eu_stride = GEN_SSEU_STRIDE(sseu->max_eus_per_subslice);
+ GEM_BUG_ON(sseu->eu_stride > GEN_MAX_EU_STRIDE);
}
unsigned int
diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.h b/drivers/gpu/drm/i915/gt/intel_sseu.h
index 8b8b562ff773..7f2355ce963d 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.h
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.h
@@ -16,6 +16,8 @@ struct drm_i915_private;
#define GEN_MAX_SUBSLICES (8) /* ICL upper bound */
#define GEN_SSEU_STRIDE(max_entries) DIV_ROUND_UP(max_entries, BITS_PER_BYTE)
#define GEN_MAX_SUBSLICE_STRIDE GEN_SSEU_STRIDE(GEN_MAX_SUBSLICES)
+#define GEN_MAX_EUS (10) /* HSW upper bound */
+#define GEN_MAX_EU_STRIDE GEN_SSEU_STRIDE(GEN_MAX_EUS)
struct sseu_dev_info {
u8 slice_mask;
@@ -35,6 +37,7 @@ struct sseu_dev_info {
u8 max_eus_per_subslice;
u8 ss_stride;
+ u8 eu_stride;
/* We don't have more than 8 eus per subslice at the moment and as we
* store eus enabled using bits, no need to multiply by eus per
diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
index d8e25dcf5f0b..abac5042da2b 100644
--- a/drivers/gpu/drm/i915/i915_query.c
+++ b/drivers/gpu/drm/i915/i915_query.c
@@ -37,7 +37,6 @@ static int query_topology_info(struct drm_i915_private *dev_priv,
const struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
struct drm_i915_query_topology_info topo;
u32 slice_length, subslice_length, eu_length, total_length;
- u8 eu_stride = GEN_SSEU_STRIDE(sseu->max_eus_per_subslice);
int ret;
if (query_item->flags != 0)
@@ -50,7 +49,7 @@ static int query_topology_info(struct drm_i915_private *dev_priv,
slice_length = sizeof(sseu->slice_mask);
subslice_length = sseu->max_slices * sseu->ss_stride;
- eu_length = sseu->max_slices * sseu->max_subslices * eu_stride;
+ eu_length = sseu->max_slices * sseu->max_subslices * sseu->eu_stride;
total_length = sizeof(topo) + slice_length + subslice_length +
eu_length;
@@ -70,7 +69,7 @@ static int query_topology_info(struct drm_i915_private *dev_priv,
topo.subslice_offset = slice_length;
topo.subslice_stride = sseu->ss_stride;
topo.eu_offset = slice_length + subslice_length;
- topo.eu_stride = eu_stride;
+ topo.eu_stride = sseu->eu_stride;
if (__copy_to_user(u64_to_user_ptr(query_item->data_ptr),
&topo, sizeof(topo)))
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index 77d7bbaa49f3..b1a79ed408eb 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -118,10 +118,9 @@ void intel_device_info_dump_runtime(const struct intel_runtime_info *info,
static int sseu_eu_idx(const struct sseu_dev_info *sseu, int slice,
int subslice)
{
- int subslice_stride = GEN_SSEU_STRIDE(sseu->max_eus_per_subslice);
- int slice_stride = sseu->max_subslices * subslice_stride;
+ int slice_stride = sseu->max_subslices * sseu->eu_stride;
- return slice * slice_stride + subslice * subslice_stride;
+ return slice * slice_stride + subslice * sseu->eu_stride;
}
static u16 sseu_get_eus(const struct sseu_dev_info *sseu, int slice,
@@ -130,7 +129,7 @@ static u16 sseu_get_eus(const struct sseu_dev_info *sseu, int slice,
int i, offset = sseu_eu_idx(sseu, slice, subslice);
u16 eu_mask = 0;
- for (i = 0; i < GEN_SSEU_STRIDE(sseu->max_eus_per_subslice); i++) {
+ for (i = 0; i < sseu->eu_stride; i++) {
eu_mask |= ((u16)sseu->eu_mask[offset + i]) <<
(i * BITS_PER_BYTE);
}
@@ -143,7 +142,7 @@ static void sseu_set_eus(struct sseu_dev_info *sseu, int slice, int subslice,
{
int i, offset = sseu_eu_idx(sseu, slice, subslice);
- for (i = 0; i < GEN_SSEU_STRIDE(sseu->max_eus_per_subslice); i++) {
+ for (i = 0; i < sseu->eu_stride; i++) {
sseu->eu_mask[offset + i] =
(eu_mask >> (BITS_PER_BYTE * i)) & 0xff;
}
--
2.22.0
More information about the Intel-gfx
mailing list