aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/i915/gt/intel_workarounds.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/i915/gt/intel_workarounds.c')
-rw-r--r--drivers/gpu/drm/i915/gt/intel_workarounds.c138
1 files changed, 107 insertions, 31 deletions
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 4e292d4bf7b9..887e0dc701f7 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -116,17 +116,17 @@ static void _wa_add(struct i915_wa_list *wal, const struct i915_wa *wa)
} else {
wa_ = &wal->list[mid];
- if ((wa->mask & ~wa_->mask) == 0) {
- DRM_ERROR("Discarding overwritten w/a for reg %04x (mask: %08x, value: %08x)\n",
+ if ((wa->clr | wa_->clr) && !(wa->clr & ~wa_->clr)) {
+ DRM_ERROR("Discarding overwritten w/a for reg %04x (clear: %08x, set: %08x)\n",
i915_mmio_reg_offset(wa_->reg),
- wa_->mask, wa_->val);
+ wa_->clr, wa_->set);
- wa_->val &= ~wa->mask;
+ wa_->set &= ~wa->clr;
}
wal->wa_count++;
- wa_->val |= wa->val;
- wa_->mask |= wa->mask;
+ wa_->set |= wa->set;
+ wa_->clr |= wa->clr;
wa_->read |= wa->read;
return;
}
@@ -147,13 +147,13 @@ static void _wa_add(struct i915_wa_list *wal, const struct i915_wa *wa)
}
}
-static void wa_add(struct i915_wa_list *wal, i915_reg_t reg, u32 mask,
- u32 val, u32 read_mask)
+static void wa_add(struct i915_wa_list *wal, i915_reg_t reg,
+ u32 clear, u32 set, u32 read_mask)
{
struct i915_wa wa = {
.reg = reg,
- .mask = mask,
- .val = val,
+ .clr = clear,
+ .set = set,
.read = read_mask,
};
@@ -161,38 +161,43 @@ static void wa_add(struct i915_wa_list *wal, i915_reg_t reg, u32 mask,
}
static void
-wa_write_masked_or(struct i915_wa_list *wal, i915_reg_t reg, u32 mask,
- u32 val)
+wa_write_masked_or(struct i915_wa_list *wal, i915_reg_t reg, u32 clear, u32 set)
{
- wa_add(wal, reg, mask, val, mask);
+ wa_add(wal, reg, clear, set, clear);
}
static void
-wa_masked_en(struct i915_wa_list *wal, i915_reg_t reg, u32 val)
+wa_write(struct i915_wa_list *wal, i915_reg_t reg, u32 set)
+{
+ wa_write_masked_or(wal, reg, ~0, set);
+}
+
+static void
+wa_write_or(struct i915_wa_list *wal, i915_reg_t reg, u32 set)
{
- wa_write_masked_or(wal, reg, val, _MASKED_BIT_ENABLE(val));
+ wa_write_masked_or(wal, reg, set, set);
}
static void
-wa_write(struct i915_wa_list *wal, i915_reg_t reg, u32 val)
+wa_masked_en(struct i915_wa_list *wal, i915_reg_t reg, u32 val)
{
- wa_write_masked_or(wal, reg, ~0, val);
+ wa_add(wal, reg, 0, _MASKED_BIT_ENABLE(val), val);
}
static void
-wa_write_or(struct i915_wa_list *wal, i915_reg_t reg, u32 val)
+wa_masked_dis(struct i915_wa_list *wal, i915_reg_t reg, u32 val)
{
- wa_write_masked_or(wal, reg, val, val);
+ wa_add(wal, reg, 0, _MASKED_BIT_DISABLE(val), val);
}
#define WA_SET_BIT_MASKED(addr, mask) \
- wa_write_masked_or(wal, (addr), (mask), _MASKED_BIT_ENABLE(mask))
+ wa_masked_en(wal, (addr), (mask))
#define WA_CLR_BIT_MASKED(addr, mask) \
- wa_write_masked_or(wal, (addr), (mask), _MASKED_BIT_DISABLE(mask))
+ wa_masked_dis(wal, (addr), (mask))
#define WA_SET_FIELD_MASKED(addr, mask, value) \
- wa_write_masked_or(wal, (addr), (mask), _MASKED_FIELD((mask), (value)))
+ wa_write_masked_or(wal, (addr), 0, _MASKED_FIELD((mask), (value)))
static void gen8_ctx_workarounds_init(struct intel_engine_cs *engine,
struct i915_wa_list *wal)
@@ -662,7 +667,7 @@ int intel_engine_emit_ctx_wa(struct i915_request *rq)
*cs++ = MI_LOAD_REGISTER_IMM(wal->count);
for (i = 0, wa = wal->list; i < wal->count; i++, wa++) {
*cs++ = i915_mmio_reg_offset(wa->reg);
- *cs++ = wa->val;
+ *cs++ = wa->set;
}
*cs++ = MI_NOOP;
@@ -827,7 +832,7 @@ wa_init_mcr(struct drm_i915_private *i915, struct i915_wa_list *wal)
DRM_WARN("No common index found between subslice mask %x and L3 bank mask %x!\n",
intel_sseu_get_subslices(sseu, slice), l3_en);
subslice = fls(l3_en);
- WARN_ON(!subslice);
+ drm_WARN_ON(&i915->drm, !subslice);
}
subslice--;
@@ -991,11 +996,10 @@ wal_get_fw_for_rmw(struct intel_uncore *uncore, const struct i915_wa_list *wal)
static bool
wa_verify(const struct i915_wa *wa, u32 cur, const char *name, const char *from)
{
- if ((cur ^ wa->val) & wa->read) {
- DRM_ERROR("%s workaround lost on %s! (%x=%x/%x, expected %x, mask=%x)\n",
+ if ((cur ^ wa->set) & wa->read) {
+ DRM_ERROR("%s workaround lost on %s! (%x=%x/%x, expected %x)\n",
name, from, i915_mmio_reg_offset(wa->reg),
- cur, cur & wa->read,
- wa->val, wa->mask);
+ cur, cur & wa->read, wa->set);
return false;
}
@@ -1020,7 +1024,10 @@ wa_list_apply(struct intel_uncore *uncore, const struct i915_wa_list *wal)
intel_uncore_forcewake_get__locked(uncore, fw);
for (i = 0, wa = wal->list; i < wal->count; i++, wa++) {
- intel_uncore_rmw_fw(uncore, wa->reg, wa->mask, wa->val);
+ if (wa->clr)
+ intel_uncore_rmw_fw(uncore, wa->reg, wa->clr, wa->set);
+ else
+ intel_uncore_write_fw(uncore, wa->reg, wa->set);
if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
wa_verify(wa,
intel_uncore_read_fw(uncore, wa->reg),
@@ -1254,6 +1261,9 @@ static void tgl_whitelist_build(struct intel_engine_cs *engine)
whitelist_reg_ext(w, PS_INVOCATION_COUNT,
RING_FORCE_TO_NONPRIV_ACCESS_RD |
RING_FORCE_TO_NONPRIV_RANGE_4);
+
+ /* Wa_1808121037:tgl */
+ whitelist_reg(w, GEN7_COMMON_SLICE_CHICKEN1);
break;
default:
break;
@@ -1345,6 +1355,16 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
wa_write_or(wal,
GEN7_SARCHKMD,
GEN7_DISABLE_SAMPLER_PREFETCH);
+
+ /* Wa_1407928979:tgl */
+ wa_write_or(wal,
+ GEN7_FF_THREAD_MODE,
+ GEN12_FF_TESSELATION_DOP_GATE_DISABLE);
+
+ /* Wa_1606931601:tgl */
+ wa_masked_en(wal,
+ GEN7_ROW_CHICKEN2,
+ GEN12_DISABLE_EARLY_READ);
}
if (IS_GEN(i915, 11)) {
@@ -1457,6 +1477,52 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
GEN8_L3SQCREG4,
GEN8_LQSC_FLUSH_COHERENT_LINES);
}
+
+ if (IS_GEN(i915, 7))
+ /* WaBCSVCSTlbInvalidationMode:ivb,vlv,hsw */
+ wa_masked_en(wal,
+ GFX_MODE_GEN7,
+ GFX_TLB_INVALIDATE_EXPLICIT | GFX_REPLAY_MODE);
+
+ if (IS_GEN_RANGE(i915, 6, 7))
+ /*
+ * We need to disable the AsyncFlip performance optimisations in
+ * order to use MI_WAIT_FOR_EVENT within the CS. It should
+ * already be programmed to '1' on all products.
+ *
+ * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv
+ */
+ wa_masked_en(wal,
+ MI_MODE,
+ ASYNC_FLIP_PERF_DISABLE);
+
+ if (IS_GEN(i915, 6)) {
+ /*
+ * Required for the hardware to program scanline values for
+ * waiting
+ * WaEnableFlushTlbInvalidationMode:snb
+ */
+ wa_masked_en(wal,
+ GFX_MODE,
+ GFX_TLB_INVALIDATE_EXPLICIT);
+
+ /*
+ * From the Sandybridge PRM, volume 1 part 3, page 24:
+ * "If this bit is set, STCunit will have LRA as replacement
+ * policy. [...] This bit must be reset. LRA replacement
+ * policy is not supported."
+ */
+ wa_masked_dis(wal,
+ CACHE_MODE_0,
+ CM0_STC_EVICT_DISABLE_LRA_SNB);
+ }
+
+ if (IS_GEN_RANGE(i915, 4, 6))
+ /* WaTimedSingleVertexDispatch:cl,bw,ctg,elk,ilk,snb */
+ wa_add(wal, MI_MODE,
+ 0, _MASKED_BIT_ENABLE(VS_TIMER_DISPATCH),
+ /* XXX bit doesn't stick on Broadwater */
+ IS_I965G(i915) ? 0 : VS_TIMER_DISPATCH);
}
static void
@@ -1475,7 +1541,7 @@ xcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
static void
engine_init_workarounds(struct intel_engine_cs *engine, struct i915_wa_list *wal)
{
- if (I915_SELFTEST_ONLY(INTEL_GEN(engine->i915) < 8))
+ if (I915_SELFTEST_ONLY(INTEL_GEN(engine->i915) < 4))
return;
if (engine->class == RENDER_CLASS)
@@ -1488,7 +1554,7 @@ void intel_engine_init_workarounds(struct intel_engine_cs *engine)
{
struct i915_wa_list *wal = &engine->wa_list;
- if (INTEL_GEN(engine->i915) < 8)
+ if (INTEL_GEN(engine->i915) < 4)
return;
wa_init_start(wal, "engine", engine->name);
@@ -1612,6 +1678,16 @@ static int engine_wa_list_verify(struct intel_context *ce,
goto err_vma;
}
+ i915_vma_lock(vma);
+ err = i915_request_await_object(rq, vma->obj, true);
+ if (err == 0)
+ err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+ i915_vma_unlock(vma);
+ if (err) {
+ i915_request_add(rq);
+ goto err_vma;
+ }
+
err = wa_list_srm(rq, wal, vma);
if (err)
goto err_vma;
Powered by cgit, Gruvboxed by Blaster4385.