drm/i915/xehp: Loop over all gslices for INSTDONE processing

We no longer have traditional slices on Xe_HP platforms, but the
INSTDONE registers are replicated according to gslice representation
which is similar.  We can mostly re-use the existing instdone code with
just a few modifications:

 * Create an alternate instdone loop macro that will iterate over the
   flat DSS space, but still provide the gslice/dss steering values for
   compatibility with the legacy code.

 * We should allocate INSTDONE storage space according to the maximum
   number of gslices rather than the maximum number of legacy slices to
   ensure we have enough storage space to hold all of the values.  XeHP
   design has 8 gslices, whereas older platforms never had more than 3
   slices.

Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210805163647.801064-3-matthew.d.roper@intel.com

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 0d9105a31d84ecc205aa976a1ee580a8b27c25cd..58ed67894b3db580762d6c7094d0593537432f9c 100644 (file)
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1163,16 +1163,16 @@ void intel_engine_get_instdone(const struct intel_engine_cs *engine,
        u32 mmio_base = engine->mmio_base;
        int slice;
        int subslice;
+       int iter;
 
        memset(instdone, 0, sizeof(*instdone));
 
-       switch (GRAPHICS_VER(i915)) {
-       default:
+       if (GRAPHICS_VER(i915) >= 8) {
                instdone->instdone =
                        intel_uncore_read(uncore, RING_INSTDONE(mmio_base));
 
                if (engine->id != RCS0)
-                       break;
+                       return;
 
                instdone->slice_common =
                        intel_uncore_read(uncore, GEN7_SC_INSTDONE);
@@ -1182,21 +1182,32 @@ void intel_engine_get_instdone(const struct intel_engine_cs *engine,
                        instdone->slice_common_extra[1] =
                                intel_uncore_read(uncore, GEN12_SC_INSTDONE_EXTRA2);
                }
-               for_each_instdone_slice_subslice(i915, sseu, slice, subslice) {
-                       instdone->sampler[slice][subslice] =
-                               read_subslice_reg(engine, slice, subslice,
-                                                 GEN7_SAMPLER_INSTDONE);
-                       instdone->row[slice][subslice] =
-                               read_subslice_reg(engine, slice, subslice,
-                                                 GEN7_ROW_INSTDONE);
+
+               if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) {
+                       for_each_instdone_gslice_dss_xehp(i915, sseu, iter, slice, subslice) {
+                               instdone->sampler[slice][subslice] =
+                                       read_subslice_reg(engine, slice, subslice,
+                                                         GEN7_SAMPLER_INSTDONE);
+                               instdone->row[slice][subslice] =
+                                       read_subslice_reg(engine, slice, subslice,
+                                                         GEN7_ROW_INSTDONE);
+                       }
+               } else {
+                       for_each_instdone_slice_subslice(i915, sseu, slice, subslice) {
+                               instdone->sampler[slice][subslice] =
+                                       read_subslice_reg(engine, slice, subslice,
+                                                         GEN7_SAMPLER_INSTDONE);
+                               instdone->row[slice][subslice] =
+                                       read_subslice_reg(engine, slice, subslice,
+                                                         GEN7_ROW_INSTDONE);
+                       }
                }
-               break;
-       case 7:
+       } else if (GRAPHICS_VER(i915) >= 7) {
                instdone->instdone =
                        intel_uncore_read(uncore, RING_INSTDONE(mmio_base));
 
                if (engine->id != RCS0)
-                       break;
+                       return;
 
                instdone->slice_common =
                        intel_uncore_read(uncore, GEN7_SC_INSTDONE);
@@ -1204,22 +1215,15 @@ void intel_engine_get_instdone(const struct intel_engine_cs *engine,
                        intel_uncore_read(uncore, GEN7_SAMPLER_INSTDONE);
                instdone->row[0][0] =
                        intel_uncore_read(uncore, GEN7_ROW_INSTDONE);
-
-               break;
-       case 6:
-       case 5:
-       case 4:
+       } else if (GRAPHICS_VER(i915) >= 4) {
                instdone->instdone =
                        intel_uncore_read(uncore, RING_INSTDONE(mmio_base));
                if (engine->id == RCS0)
                        /* HACK: Using the wrong struct member */
                        instdone->slice_common =
                                intel_uncore_read(uncore, GEN4_INSTDONE1);
-               break;
-       case 3:
-       case 2:
+       } else {
                instdone->instdone = intel_uncore_read(uncore, GEN2_INSTDONE);
-               break;
        }
 }
 

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index ed91bcff20eb598b122422e402c3f18117708152..0b4846b01626e51183166b28d374d3f0c7e8451c 100644 (file)
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -67,8 +67,8 @@ struct intel_instdone {
        /* The following exist only in the RCS engine */
        u32 slice_common;
        u32 slice_common_extra[2];
-       u32 sampler[I915_MAX_SLICES][I915_MAX_SUBSLICES];
-       u32 row[I915_MAX_SLICES][I915_MAX_SUBSLICES];
+       u32 sampler[GEN_MAX_GSLICES][I915_MAX_SUBSLICES];
+       u32 row[GEN_MAX_GSLICES][I915_MAX_SUBSLICES];
 };
 
 /*
@@ -578,4 +578,12 @@ intel_engine_has_relative_mmio(const struct intel_engine_cs * const engine)
                for_each_if((instdone_has_slice(dev_priv_, sseu_, slice_)) && \
                            (instdone_has_subslice(dev_priv_, sseu_, slice_, \
                                                    subslice_)))
+
+#define for_each_instdone_gslice_dss_xehp(dev_priv_, sseu_, iter_, gslice_, dss_) \
+       for ((iter_) = 0, (gslice_) = 0, (dss_) = 0; \
+            (iter_) < GEN_MAX_SUBSLICES; \
+            (iter_)++, (gslice_) = (iter_) / GEN_DSS_PER_GSLICE, \
+            (dss_) = (iter_) % GEN_DSS_PER_GSLICE) \
+               for_each_if(intel_sseu_has_subslice((sseu_), 0, (iter_)))
+
 #endif /* __INTEL_ENGINE_TYPES_H__ */

diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.h b/drivers/gpu/drm/i915/gt/intel_sseu.h
index 22fef98887c0334a69a1d67fc160855e71e4286b..0270acdcc157676f58cb8c0c3988e71d176ea747 100644 (file)
--- a/drivers/gpu/drm/i915/gt/intel_sseu.h
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.h
@@ -26,6 +26,9 @@ struct drm_printer;
 #define GEN_DSS_PER_CSLICE     8
 #define GEN_DSS_PER_MSLICE     8
 
+#define GEN_MAX_GSLICES                (GEN_MAX_SUBSLICES / GEN_DSS_PER_GSLICE)
+#define GEN_MAX_CSLICES                (GEN_MAX_SUBSLICES / GEN_DSS_PER_CSLICE)
+
 struct sseu_dev_info {
        u8 slice_mask;
        u8 subslice_mask[GEN_MAX_SLICES * GEN_MAX_SUBSLICE_STRIDE];
@@ -78,6 +81,10 @@ intel_sseu_has_subslice(const struct sseu_dev_info *sseu, int slice,
        u8 mask;
        int ss_idx = subslice / BITS_PER_BYTE;
 
+       if (slice >= sseu->max_slices ||
+           subslice >= sseu->max_subslices)
+               return false;
+
        GEM_BUG_ON(ss_idx >= sseu->ss_stride);
 
        mask = sseu->subslice_mask[slice * sseu->ss_stride + ss_idx];

diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 0f08bcfbe9641559d3184f6e66e7c460d0563420..8230bc3ac8a99a3b8de39c5762495217a173bc9b 100644 (file)
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -444,15 +444,29 @@ static void error_print_instdone(struct drm_i915_error_state_buf *m,
        if (GRAPHICS_VER(m->i915) <= 6)
                return;
 
-       for_each_instdone_slice_subslice(m->i915, sseu, slice, subslice)
-               err_printf(m, "  SAMPLER_INSTDONE[%d][%d]: 0x%08x\n",
-                          slice, subslice,
-                          ee->instdone.sampler[slice][subslice]);
-
-       for_each_instdone_slice_subslice(m->i915, sseu, slice, subslice)
-               err_printf(m, "  ROW_INSTDONE[%d][%d]: 0x%08x\n",
-                          slice, subslice,
-                          ee->instdone.row[slice][subslice]);
+       if (GRAPHICS_VER_FULL(m->i915) >= IP_VER(12, 50)) {
+               int iter;
+
+               for_each_instdone_gslice_dss_xehp(m->i915, sseu, iter, slice, subslice)
+                       err_printf(m, "  SAMPLER_INSTDONE[%d][%d]: 0x%08x\n",
+                                  slice, subslice,
+                                  ee->instdone.sampler[slice][subslice]);
+
+               for_each_instdone_gslice_dss_xehp(m->i915, sseu, iter, slice, subslice)
+                       err_printf(m, "  ROW_INSTDONE[%d][%d]: 0x%08x\n",
+                                  slice, subslice,
+                                  ee->instdone.row[slice][subslice]);
+       } else {
+               for_each_instdone_slice_subslice(m->i915, sseu, slice, subslice)
+                       err_printf(m, "  SAMPLER_INSTDONE[%d][%d]: 0x%08x\n",
+                                  slice, subslice,
+                                  ee->instdone.sampler[slice][subslice]);
+
+               for_each_instdone_slice_subslice(m->i915, sseu, slice, subslice)
+                       err_printf(m, "  ROW_INSTDONE[%d][%d]: 0x%08x\n",
+                                  slice, subslice,
+                                  ee->instdone.row[slice][subslice]);
+       }
 
        if (GRAPHICS_VER(m->i915) < 12)
                return;