gen8_ggtt_invalidate() is only needed for limited set of platforms where GGTT is mapped as WC otherwise this can cause unwanted side-effects on XE_HP platforms where GFX_FLSH_CNTL_GEN6 is not valid.
v2: Add a func to detect wc ggtt detection (Ville)
Fixes: d2eae8e98d59 ("drm/i915/dg2: Drop force_probe requirement") Cc: Rodrigo Vivi rodrigo.vivi@intel.com Cc: Tvrtko Ursulin tvrtko.ursulin@linux.intel.com Cc: Joonas Lahtinen joonas.lahtinen@linux.intel.com Cc: Jani Nikula jani.nikula@linux.intel.com Cc: Jonathan Cavitt jonathan.cavitt@intel.com Cc: John Harrison john.c.harrison@intel.com Cc: Andi Shyti andi.shyti@linux.intel.com Cc: Ville Syrjälä ville.syrjala@linux.intel.com Cc: stable@vger.kernel.org # v6.2+ Suggested-by: Matt Roper matthew.d.roper@intel.com Signed-off-by: Nirmoy Das nirmoy.das@intel.com Acked-by: Andi Shyti andi.shyti@linux.intel.com --- drivers/gpu/drm/i915/gt/intel_ggtt.c | 35 +++++++++++++++++++--------- 1 file changed, 24 insertions(+), 11 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c index 4d7d88b92632..401667f83f96 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c @@ -195,6 +195,21 @@ void gen6_ggtt_invalidate(struct i915_ggtt *ggtt) spin_unlock_irq(&uncore->lock); }
+static bool needs_wc_ggtt_mapping(struct drm_i915_private *i915) +{ + /* + * On BXT+/ICL+ writes larger than 64 bit to the GTT pagetable range + * will be dropped. For WC mappings in general we have 64 byte burst + * writes when the WC buffer is flushed, so we can't use it, but have to + * resort to an uncached mapping. The WC issue is easily caught by the + * readback check when writing GTT PTE entries. + */ + if (!IS_GEN9_LP(i915) && GRAPHICS_VER(i915) < 11) + return true; + + return false; +} + static void gen8_ggtt_invalidate(struct i915_ggtt *ggtt) { struct intel_uncore *uncore = ggtt->vm.gt->uncore; @@ -202,8 +217,12 @@ static void gen8_ggtt_invalidate(struct i915_ggtt *ggtt) /* * Note that as an uncached mmio write, this will flush the * WCB of the writes into the GGTT before it triggers the invalidate. + * + * Only perform this when GGTT is mapped as WC, see ggtt_probe_common(). */ - intel_uncore_write_fw(uncore, GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN); + if (needs_wc_ggtt_mapping(ggtt->vm.i915)) + intel_uncore_write_fw(uncore, GFX_FLSH_CNTL_GEN6, + GFX_FLSH_CNTL_EN); }
static void guc_ggtt_invalidate(struct i915_ggtt *ggtt) @@ -1126,17 +1145,11 @@ static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size) GEM_WARN_ON(pci_resource_len(pdev, GEN4_GTTMMADR_BAR) != gen6_gttmmadr_size(i915)); phys_addr = pci_resource_start(pdev, GEN4_GTTMMADR_BAR) + gen6_gttadr_offset(i915);
- /* - * On BXT+/ICL+ writes larger than 64 bit to the GTT pagetable range - * will be dropped. For WC mappings in general we have 64 byte burst - * writes when the WC buffer is flushed, so we can't use it, but have to - * resort to an uncached mapping. The WC issue is easily caught by the - * readback check when writing GTT PTE entries. - */ - if (IS_GEN9_LP(i915) || GRAPHICS_VER(i915) >= 11) - ggtt->gsm = ioremap(phys_addr, size); - else + if (needs_wc_ggtt_mapping(i915)) ggtt->gsm = ioremap_wc(phys_addr, size); + else + ggtt->gsm = ioremap(phys_addr, size); + if (!ggtt->gsm) { drm_err(&i915->drm, "Failed to map the ggtt page table\n"); return -ENOMEM;