Commit ef50fa9b authored by Chris Wilson's avatar Chris Wilson Committed by Joonas Lahtinen

drm/i915/gt: Move hsw GT workarounds from init_clock_gating to workarounds

Rescue the GT workarounds from being buried inside init_clock_gating so
that we remember to apply them after a GT reset, and that they are
included in our verification that the workarounds are applied.

v2: Leave HSW_SCRATCH to set an explicit value, not or in our disable
bit.

Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/2011Signed-off-by: default avatarChris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: default avatarMika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: stable@vger.kernel.org
Link: https://patchwork.freedesktop.org/patch/msgid/20200611093015.11370-1-chris@chris-wilson.co.uk
(cherry picked from commit f93ec5fb)
Signed-off-by: default avatarJoonas Lahtinen <joonas.lahtinen@linux.intel.com>
parent 898e4e57
......@@ -178,6 +178,12 @@ wa_write_or(struct i915_wa_list *wal, i915_reg_t reg, u32 set)
wa_write_masked_or(wal, reg, set, set);
}
static void
wa_write_clr(struct i915_wa_list *wal, i915_reg_t reg, u32 clr)
{
wa_write_masked_or(wal, reg, clr, 0);
}
static void
wa_masked_en(struct i915_wa_list *wal, i915_reg_t reg, u32 val)
{
......@@ -686,6 +692,46 @@ int intel_engine_emit_ctx_wa(struct i915_request *rq)
return 0;
}
static void
hsw_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
{
/* L3 caching of data atomics doesn't work -- disable it. */
wa_write(wal, HSW_SCRATCH1, HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE);
wa_add(wal,
HSW_ROW_CHICKEN3, 0,
_MASKED_BIT_ENABLE(HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE),
0 /* XXX does this reg exist? */);
/* WaVSRefCountFullforceMissDisable:hsw */
wa_write_clr(wal, GEN7_FF_THREAD_MODE, GEN7_FF_VS_REF_CNT_FFME);
wa_masked_dis(wal,
CACHE_MODE_0_GEN7,
/* WaDisable_RenderCache_OperationalFlush:hsw */
RC_OP_FLUSH_ENABLE |
/* enable HiZ Raw Stall Optimization */
HIZ_RAW_STALL_OPT_DISABLE);
/* WaDisable4x2SubspanOptimization:hsw */
wa_masked_en(wal, CACHE_MODE_1, PIXEL_SUBSPAN_COLLECT_OPT_DISABLE);
/*
* BSpec recommends 8x4 when MSAA is used,
* however in practice 16x4 seems fastest.
*
* Note that PS/WM thread counts depend on the WIZ hashing
* disable bit, which we don't touch here, but it's good
* to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
*/
wa_add(wal, GEN7_GT_MODE, 0,
_MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4),
GEN6_WIZ_HASHING_16x4);
/* WaSampleCChickenBitEnable:hsw */
wa_masked_en(wal, HALF_SLICE_CHICKEN3, HSW_SAMPLE_C_PERFORMANCE);
}
static void
gen9_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
{
......@@ -963,6 +1009,8 @@ gt_init_workarounds(struct drm_i915_private *i915, struct i915_wa_list *wal)
bxt_gt_workarounds_init(i915, wal);
else if (IS_SKYLAKE(i915))
skl_gt_workarounds_init(i915, wal);
else if (IS_HASWELL(i915))
hsw_gt_workarounds_init(i915, wal);
else if (INTEL_GEN(i915) <= 8)
return;
else
......
......@@ -7230,46 +7230,11 @@ static void bdw_init_clock_gating(struct drm_i915_private *dev_priv)
static void hsw_init_clock_gating(struct drm_i915_private *dev_priv)
{
/* L3 caching of data atomics doesn't work -- disable it. */
I915_WRITE(HSW_SCRATCH1, HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE);
I915_WRITE(HSW_ROW_CHICKEN3,
_MASKED_BIT_ENABLE(HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE));
/* This is required by WaCatErrorRejectionIssue:hsw */
I915_WRITE(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG,
I915_READ(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |
GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB);
/* WaVSRefCountFullforceMissDisable:hsw */
I915_WRITE(GEN7_FF_THREAD_MODE,
I915_READ(GEN7_FF_THREAD_MODE) & ~GEN7_FF_VS_REF_CNT_FFME);
/* WaDisable_RenderCache_OperationalFlush:hsw */
I915_WRITE(CACHE_MODE_0_GEN7, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
/* enable HiZ Raw Stall Optimization */
I915_WRITE(CACHE_MODE_0_GEN7,
_MASKED_BIT_DISABLE(HIZ_RAW_STALL_OPT_DISABLE));
/* WaDisable4x2SubspanOptimization:hsw */
I915_WRITE(CACHE_MODE_1,
_MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_DISABLE));
/*
* BSpec recommends 8x4 when MSAA is used,
* however in practice 16x4 seems fastest.
*
* Note that PS/WM thread counts depend on the WIZ hashing
* disable bit, which we don't touch here, but it's good
* to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
*/
I915_WRITE(GEN7_GT_MODE,
_MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4));
/* WaSampleCChickenBitEnable:hsw */
I915_WRITE(HALF_SLICE_CHICKEN3,
_MASKED_BIT_ENABLE(HSW_SAMPLE_C_PERFORMANCE));
/* WaSwitchSolVfFArbitrationPriority:hsw */
I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment