UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity
OpenCloudOS-Kernel/drivers/gpu/drm/i915/intel_workarounds.c

1266 lines
35 KiB
C
Raw Blame History

/*
* SPDX-License-Identifier: MIT
*
* Copyright © 2014-2018 Intel Corporation
*/
#include "i915_drv.h"
#include "intel_workarounds.h"
/**
* DOC: Hardware workarounds
*
* This file is intended as a central place to implement most [1]_ of the
* required workarounds for hardware to work as originally intended. They fall
* in five basic categories depending on how/when they are applied:
*
* - Workarounds that touch registers that are saved/restored to/from the HW
* context image. The list is emitted (via Load Register Immediate commands)
* everytime a new context is created.
* - GT workarounds. The list of these WAs is applied whenever these registers
* revert to default values (on GPU reset, suspend/resume [2]_, etc..).
* - Display workarounds. The list is applied during display clock-gating
* initialization.
* - Workarounds that whitelist a privileged register, so that UMDs can manage
* them directly. This is just a special case of a MMMIO workaround (as we
* write the list of these to/be-whitelisted registers to some special HW
* registers).
* - Workaround batchbuffers, that get executed automatically by the hardware
* on every HW context restore.
*
* .. [1] Please notice that there are other WAs that, due to their nature,
* cannot be applied from a central place. Those are peppered around the rest
* of the code, as needed.
*
* .. [2] Technically, some registers are powercontext saved & restored, so they
* survive a suspend/resume. In practice, writing them again is not too
* costly and simplifies things. We can revisit this in the future.
*
* Layout
* ~~~~~~
*
* Keep things in this file ordered by WA type, as per the above (context, GT,
* display, register whitelist, batchbuffer). Then, inside each type, keep the
* following order:
*
* - Infrastructure functions and macros
* - WAs per platform in standard gen/chrono order
* - Public functions to init or apply the given workaround type.
*/
static void wa_init_start(struct i915_wa_list *wal, const char *name)
{
wal->name = name;
}
#define WA_LIST_CHUNK (1 << 4)
static void wa_init_finish(struct i915_wa_list *wal)
{
/* Trim unused entries. */
if (!IS_ALIGNED(wal->count, WA_LIST_CHUNK)) {
struct i915_wa *list = kmemdup(wal->list,
wal->count * sizeof(*list),
GFP_KERNEL);
if (list) {
kfree(wal->list);
wal->list = list;
}
}
if (!wal->count)
return;
DRM_DEBUG_DRIVER("Initialized %u %s workarounds\n",
wal->wa_count, wal->name);
}
static void _wa_add(struct i915_wa_list *wal, const struct i915_wa *wa)
{
unsigned int addr = i915_mmio_reg_offset(wa->reg);
unsigned int start = 0, end = wal->count;
const unsigned int grow = WA_LIST_CHUNK;
struct i915_wa *wa_;
GEM_BUG_ON(!is_power_of_2(grow));
if (IS_ALIGNED(wal->count, grow)) { /* Either uninitialized or full. */
struct i915_wa *list;
list = kmalloc_array(ALIGN(wal->count + 1, grow), sizeof(*wa),
GFP_KERNEL);
if (!list) {
DRM_ERROR("No space for workaround init!\n");
return;
}
if (wal->list)
memcpy(list, wal->list, sizeof(*wa) * wal->count);
wal->list = list;
}
while (start < end) {
unsigned int mid = start + (end - start) / 2;
if (i915_mmio_reg_offset(wal->list[mid].reg) < addr) {
start = mid + 1;
} else if (i915_mmio_reg_offset(wal->list[mid].reg) > addr) {
end = mid;
} 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",
i915_mmio_reg_offset(wa_->reg),
wa_->mask, wa_->val);
wa_->val &= ~wa->mask;
}
wal->wa_count++;
wa_->val |= wa->val;
wa_->mask |= wa->mask;
return;
}
}
wal->wa_count++;
wa_ = &wal->list[wal->count++];
*wa_ = *wa;
while (wa_-- > wal->list) {
GEM_BUG_ON(i915_mmio_reg_offset(wa_[0].reg) ==
i915_mmio_reg_offset(wa_[1].reg));
if (i915_mmio_reg_offset(wa_[1].reg) >
i915_mmio_reg_offset(wa_[0].reg))
break;
swap(wa_[1], wa_[0]);
}
}
static void
wa_write_masked_or(struct i915_wa_list *wal, i915_reg_t reg, u32 mask,
u32 val)
{
struct i915_wa wa = {
.reg = reg,
.mask = mask,
.val = val
};
_wa_add(wal, &wa);
}
static void
wa_masked_en(struct i915_wa_list *wal, i915_reg_t reg, u32 val)
{
wa_write_masked_or(wal, reg, val, _MASKED_BIT_ENABLE(val));
}
static void
wa_write(struct i915_wa_list *wal, i915_reg_t reg, u32 val)
{
wa_write_masked_or(wal, reg, ~0, val);
}
static void
wa_write_or(struct i915_wa_list *wal, i915_reg_t reg, u32 val)
{
wa_write_masked_or(wal, reg, val, val);
}
#define WA_SET_BIT_MASKED(addr, mask) \
wa_write_masked_or(wal, (addr), (mask), _MASKED_BIT_ENABLE(mask))
#define WA_CLR_BIT_MASKED(addr, mask) \
wa_write_masked_or(wal, (addr), (mask), _MASKED_BIT_DISABLE(mask))
#define WA_SET_FIELD_MASKED(addr, mask, value) \
wa_write_masked_or(wal, (addr), (mask), _MASKED_FIELD((mask), (value)))
static void gen8_ctx_workarounds_init(struct intel_engine_cs *engine)
{
struct i915_wa_list *wal = &engine->ctx_wa_list;
WA_SET_BIT_MASKED(INSTPM, INSTPM_FORCE_ORDERING);
/* WaDisableAsyncFlipPerfMode:bdw,chv */
WA_SET_BIT_MASKED(MI_MODE, ASYNC_FLIP_PERF_DISABLE);
/* WaDisablePartialInstShootdown:bdw,chv */
WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE);
/* Use Force Non-Coherent whenever executing a 3D context. This is a
* workaround for for a possible hang in the unlikely event a TLB
* invalidation occurs during a PSD flush.
*/
/* WaForceEnableNonCoherent:bdw,chv */
/* WaHdcDisableFetchWhenMasked:bdw,chv */
WA_SET_BIT_MASKED(HDC_CHICKEN0,
HDC_DONOT_FETCH_MEM_WHEN_MASKED |
HDC_FORCE_NON_COHERENT);
/* From the Haswell PRM, Command Reference: Registers, CACHE_MODE_0:
* "The Hierarchical Z RAW Stall Optimization allows non-overlapping
* polygons in the same 8x4 pixel/sample area to be processed without
* stalling waiting for the earlier ones to write to Hierarchical Z
* buffer."
*
* This optimization is off by default for BDW and CHV; turn it on.
*/
WA_CLR_BIT_MASKED(CACHE_MODE_0_GEN7, HIZ_RAW_STALL_OPT_DISABLE);
/* Wa4x4STCOptimizationDisable:bdw,chv */
WA_SET_BIT_MASKED(CACHE_MODE_1, GEN8_4x4_STC_OPTIMIZATION_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_SET_FIELD_MASKED(GEN7_GT_MODE,
GEN6_WIZ_HASHING_MASK,
GEN6_WIZ_HASHING_16x4);
}
static void bdw_ctx_workarounds_init(struct intel_engine_cs *engine)
{
struct drm_i915_private *i915 = engine->i915;
struct i915_wa_list *wal = &engine->ctx_wa_list;
gen8_ctx_workarounds_init(engine);
/* WaDisableThreadStallDopClockGating:bdw (pre-production) */
WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, STALL_DOP_GATING_DISABLE);
/* WaDisableDopClockGating:bdw
*
* Also see the related UCGTCL1 write in broadwell_init_clock_gating()
* to disable EUTC clock gating.
*/
WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2,
DOP_CLOCK_GATING_DISABLE);
WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3,
GEN8_SAMPLER_POWER_BYPASS_DIS);
WA_SET_BIT_MASKED(HDC_CHICKEN0,
/* WaForceContextSaveRestoreNonCoherent:bdw */
HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT |
/* WaDisableFenceDestinationToSLM:bdw (pre-prod) */
(IS_BDW_GT3(i915) ? HDC_FENCE_DEST_SLM_DISABLE : 0));
}
static void chv_ctx_workarounds_init(struct intel_engine_cs *engine)
{
struct i915_wa_list *wal = &engine->ctx_wa_list;
gen8_ctx_workarounds_init(engine);
/* WaDisableThreadStallDopClockGating:chv */
WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, STALL_DOP_GATING_DISABLE);
/* Improve HiZ throughput on CHV. */
WA_SET_BIT_MASKED(HIZ_CHICKEN, CHV_HZ_8X8_MODE_IN_1X);
}
static void gen9_ctx_workarounds_init(struct intel_engine_cs *engine)
{
struct drm_i915_private *i915 = engine->i915;
struct i915_wa_list *wal = &engine->ctx_wa_list;
if (HAS_LLC(i915)) {
/* WaCompressedResourceSamplerPbeMediaNewHashMode:skl,kbl
*
* Must match Display Engine. See
* WaCompressedResourceDisplayNewHashMode.
*/
WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
GEN9_PBE_COMPRESSED_HASH_SELECTION);
WA_SET_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN7,
GEN9_SAMPLER_HASH_COMPRESSED_READ_ADDR);
}
/* WaClearFlowControlGpgpuContextSave:skl,bxt,kbl,glk,cfl */
/* WaDisablePartialInstShootdown:skl,bxt,kbl,glk,cfl */
WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
FLOW_CONTROL_ENABLE |
PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE);
/* Syncing dependencies between camera and graphics:skl,bxt,kbl */
if (!IS_COFFEELAKE(i915))
WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3,
GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC);
/* WaEnableYV12BugFixInHalfSliceChicken7:skl,bxt,kbl,glk,cfl */
/* WaEnableSamplerGPGPUPreemptionSupport:skl,bxt,kbl,cfl */
WA_SET_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN7,
GEN9_ENABLE_YV12_BUGFIX |
GEN9_ENABLE_GPGPU_PREEMPTION);
/* Wa4x4STCOptimizationDisable:skl,bxt,kbl,glk,cfl */
/* WaDisablePartialResolveInVc:skl,bxt,kbl,cfl */
WA_SET_BIT_MASKED(CACHE_MODE_1,
GEN8_4x4_STC_OPTIMIZATION_DISABLE |
GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE);
/* WaCcsTlbPrefetchDisable:skl,bxt,kbl,glk,cfl */
WA_CLR_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN5,
GEN9_CCS_TLB_PREFETCH_ENABLE);
/* WaForceContextSaveRestoreNonCoherent:skl,bxt,kbl,cfl */
WA_SET_BIT_MASKED(HDC_CHICKEN0,
HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT |
HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE);
/* WaForceEnableNonCoherent and WaDisableHDCInvalidation are
* both tied to WaForceContextSaveRestoreNonCoherent
* in some hsds for skl. We keep the tie for all gen9. The
* documentation is a bit hazy and so we want to get common behaviour,
* even though there is no clear evidence we would need both on kbl/bxt.
* This area has been source of system hangs so we play it safe
* and mimic the skl regardless of what bspec says.
*
* Use Force Non-Coherent whenever executing a 3D context. This
* is a workaround for a possible hang in the unlikely event
* a TLB invalidation occurs during a PSD flush.
*/
/* WaForceEnableNonCoherent:skl,bxt,kbl,cfl */
WA_SET_BIT_MASKED(HDC_CHICKEN0,
HDC_FORCE_NON_COHERENT);
/* WaDisableSamplerPowerBypassForSOPingPong:skl,bxt,kbl,cfl */
if (IS_SKYLAKE(i915) || IS_KABYLAKE(i915) || IS_COFFEELAKE(i915))
WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3,
GEN8_SAMPLER_POWER_BYPASS_DIS);
/* WaDisableSTUnitPowerOptimization:skl,bxt,kbl,glk,cfl */
WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN2, GEN8_ST_PO_DISABLE);
/*
* Supporting preemption with fine-granularity requires changes in the
* batch buffer programming. Since we can't break old userspace, we
* need to set our default preemption level to safe value. Userspace is
* still able to use more fine-grained preemption levels, since in
* WaEnablePreemptionGranularityControlByUMD we're whitelisting the
* per-ctx register. As such, WaDisable{3D,GPGPU}MidCmdPreemption are
* not real HW workarounds, but merely a way to start using preemption
* while maintaining old contract with userspace.
*/
/* WaDisable3DMidCmdPreemption:skl,bxt,glk,cfl,[cnl] */
WA_CLR_BIT_MASKED(GEN8_CS_CHICKEN1, GEN9_PREEMPT_3D_OBJECT_LEVEL);
/* WaDisableGPGPUMidCmdPreemption:skl,bxt,blk,cfl,[cnl] */
WA_SET_FIELD_MASKED(GEN8_CS_CHICKEN1,
GEN9_PREEMPT_GPGPU_LEVEL_MASK,
GEN9_PREEMPT_GPGPU_COMMAND_LEVEL);
/* WaClearHIZ_WM_CHICKEN3:bxt,glk */
if (IS_GEN9_LP(i915))
WA_SET_BIT_MASKED(GEN9_WM_CHICKEN3, GEN9_FACTOR_IN_CLR_VAL_HIZ);
}
static void skl_tune_iz_hashing(struct intel_engine_cs *engine)
{
struct drm_i915_private *i915 = engine->i915;
struct i915_wa_list *wal = &engine->ctx_wa_list;
u8 vals[3] = { 0, 0, 0 };
unsigned int i;
for (i = 0; i < 3; i++) {
u8 ss;
/*
* Only consider slices where one, and only one, subslice has 7
* EUs
*/
if (!is_power_of_2(RUNTIME_INFO(i915)->sseu.subslice_7eu[i]))
continue;
/*
* subslice_7eu[i] != 0 (because of the check above) and
* ss_max == 4 (maximum number of subslices possible per slice)
*
* -> 0 <= ss <= 3;
*/
ss = ffs(RUNTIME_INFO(i915)->sseu.subslice_7eu[i]) - 1;
vals[i] = 3 - ss;
}
if (vals[0] == 0 && vals[1] == 0 && vals[2] == 0)
return;
/* Tune IZ hashing. See intel_device_info_runtime_init() */
WA_SET_FIELD_MASKED(GEN7_GT_MODE,
GEN9_IZ_HASHING_MASK(2) |
GEN9_IZ_HASHING_MASK(1) |
GEN9_IZ_HASHING_MASK(0),
GEN9_IZ_HASHING(2, vals[2]) |
GEN9_IZ_HASHING(1, vals[1]) |
GEN9_IZ_HASHING(0, vals[0]));
}
static void skl_ctx_workarounds_init(struct intel_engine_cs *engine)
{
gen9_ctx_workarounds_init(engine);
skl_tune_iz_hashing(engine);
}
static void bxt_ctx_workarounds_init(struct intel_engine_cs *engine)
{
struct i915_wa_list *wal = &engine->ctx_wa_list;
gen9_ctx_workarounds_init(engine);
/* WaDisableThreadStallDopClockGating:bxt */
WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
STALL_DOP_GATING_DISABLE);
/* WaToEnableHwFixForPushConstHWBug:bxt */
WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
}
static void kbl_ctx_workarounds_init(struct intel_engine_cs *engine)
{
struct drm_i915_private *i915 = engine->i915;
struct i915_wa_list *wal = &engine->ctx_wa_list;
gen9_ctx_workarounds_init(engine);
/* WaToEnableHwFixForPushConstHWBug:kbl */
if (IS_KBL_REVID(i915, KBL_REVID_C0, REVID_FOREVER))
WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
/* WaDisableSbeCacheDispatchPortSharing:kbl */
WA_SET_BIT_MASKED(GEN7_HALF_SLICE_CHICKEN1,
GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE);
}
static void glk_ctx_workarounds_init(struct intel_engine_cs *engine)
{
struct i915_wa_list *wal = &engine->ctx_wa_list;
gen9_ctx_workarounds_init(engine);
/* WaToEnableHwFixForPushConstHWBug:glk */
WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
}
static void cfl_ctx_workarounds_init(struct intel_engine_cs *engine)
{
struct i915_wa_list *wal = &engine->ctx_wa_list;
gen9_ctx_workarounds_init(engine);
/* WaToEnableHwFixForPushConstHWBug:cfl */
WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
/* WaDisableSbeCacheDispatchPortSharing:cfl */
WA_SET_BIT_MASKED(GEN7_HALF_SLICE_CHICKEN1,
GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE);
}
static void cnl_ctx_workarounds_init(struct intel_engine_cs *engine)
{
struct drm_i915_private *i915 = engine->i915;
struct i915_wa_list *wal = &engine->ctx_wa_list;
/* WaForceContextSaveRestoreNonCoherent:cnl */
WA_SET_BIT_MASKED(CNL_HDC_CHICKEN0,
HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT);
/* WaThrottleEUPerfToAvoidTDBackPressure:cnl(pre-prod) */
if (IS_CNL_REVID(i915, CNL_REVID_B0, CNL_REVID_B0))
WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, THROTTLE_12_5);
/* WaDisableReplayBufferBankArbitrationOptimization:cnl */
WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
/* WaDisableEnhancedSBEVertexCaching:cnl (pre-prod) */
if (IS_CNL_REVID(i915, 0, CNL_REVID_B0))
WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE);
/* WaPushConstantDereferenceHoldDisable:cnl */
WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2, PUSH_CONSTANT_DEREF_DISABLE);
/* FtrEnableFastAnisoL1BankingFix:cnl */
WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3, CNL_FAST_ANISO_L1_BANKING_FIX);
/* WaDisable3DMidCmdPreemption:cnl */
WA_CLR_BIT_MASKED(GEN8_CS_CHICKEN1, GEN9_PREEMPT_3D_OBJECT_LEVEL);
/* WaDisableGPGPUMidCmdPreemption:cnl */
WA_SET_FIELD_MASKED(GEN8_CS_CHICKEN1,
GEN9_PREEMPT_GPGPU_LEVEL_MASK,
GEN9_PREEMPT_GPGPU_COMMAND_LEVEL);
/* WaDisableEarlyEOT:cnl */
WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, DISABLE_EARLY_EOT);
}
static void icl_ctx_workarounds_init(struct intel_engine_cs *engine)
{
struct drm_i915_private *i915 = engine->i915;
struct i915_wa_list *wal = &engine->ctx_wa_list;
/* WaDisableBankHangMode:icl */
wa_write(wal,
GEN8_L3CNTLREG,
intel_uncore_read(engine->uncore, GEN8_L3CNTLREG) |
GEN8_ERRDETBCTRL);
/* Wa_1604370585:icl (pre-prod)
* Formerly known as WaPushConstantDereferenceHoldDisable
*/
if (IS_ICL_REVID(i915, ICL_REVID_A0, ICL_REVID_B0))
WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2,
PUSH_CONSTANT_DEREF_DISABLE);
/* WaForceEnableNonCoherent:icl
* This is not the same workaround as in early Gen9 platforms, where
* lacking this could cause system hangs, but coherency performance
* overhead is high and only a few compute workloads really need it
* (the register is whitelisted in hardware now, so UMDs can opt in
* for coherency if they have a good reason).
*/
WA_SET_BIT_MASKED(ICL_HDC_MODE, HDC_FORCE_NON_COHERENT);
/* Wa_2006611047:icl (pre-prod)
* Formerly known as WaDisableImprovedTdlClkGating
*/
if (IS_ICL_REVID(i915, ICL_REVID_A0, ICL_REVID_A0))
WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2,
GEN11_TDL_CLOCK_GATING_FIX_DISABLE);
/* Wa_2006665173:icl (pre-prod) */
if (IS_ICL_REVID(i915, ICL_REVID_A0, ICL_REVID_A0))
WA_SET_BIT_MASKED(GEN11_COMMON_SLICE_CHICKEN3,
GEN11_BLEND_EMB_FIX_DISABLE_IN_RCC);
/* WaEnableFloatBlendOptimization:icl */
wa_write_masked_or(wal,
GEN10_CACHE_MODE_SS,
0, /* write-only, so skip validation */
_MASKED_BIT_ENABLE(FLOAT_BLEND_OPTIMIZATION_ENABLE));
/* WaDisableGPGPUMidThreadPreemption:icl */
WA_SET_FIELD_MASKED(GEN8_CS_CHICKEN1,
GEN9_PREEMPT_GPGPU_LEVEL_MASK,
GEN9_PREEMPT_GPGPU_THREAD_GROUP_LEVEL);
}
void intel_engine_init_ctx_wa(struct intel_engine_cs *engine)
{
struct drm_i915_private *i915 = engine->i915;
struct i915_wa_list *wal = &engine->ctx_wa_list;
wa_init_start(wal, "context");
if (IS_GEN(i915, 11))
icl_ctx_workarounds_init(engine);
else if (IS_CANNONLAKE(i915))
cnl_ctx_workarounds_init(engine);
else if (IS_COFFEELAKE(i915))
cfl_ctx_workarounds_init(engine);
else if (IS_GEMINILAKE(i915))
glk_ctx_workarounds_init(engine);
else if (IS_KABYLAKE(i915))
kbl_ctx_workarounds_init(engine);
else if (IS_BROXTON(i915))
bxt_ctx_workarounds_init(engine);
else if (IS_SKYLAKE(i915))
skl_ctx_workarounds_init(engine);
else if (IS_CHERRYVIEW(i915))
chv_ctx_workarounds_init(engine);
else if (IS_BROADWELL(i915))
bdw_ctx_workarounds_init(engine);
else if (INTEL_GEN(i915) < 8)
return;
else
MISSING_CASE(INTEL_GEN(i915));
wa_init_finish(wal);
}
int intel_engine_emit_ctx_wa(struct i915_request *rq)
{
struct i915_wa_list *wal = &rq->engine->ctx_wa_list;
struct i915_wa *wa;
unsigned int i;
u32 *cs;
int ret;
if (wal->count == 0)
return 0;
ret = rq->engine->emit_flush(rq, EMIT_BARRIER);
if (ret)
return ret;
cs = intel_ring_begin(rq, (wal->count * 2 + 2));
if (IS_ERR(cs))
return PTR_ERR(cs);
*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++ = MI_NOOP;
intel_ring_advance(rq, cs);
ret = rq->engine->emit_flush(rq, EMIT_BARRIER);
if (ret)
return ret;
return 0;
}
static void
gen9_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
{
/* WaDisableKillLogic:bxt,skl,kbl */
if (!IS_COFFEELAKE(i915))
wa_write_or(wal,
GAM_ECOCHK,
ECOCHK_DIS_TLB);
if (HAS_LLC(i915)) {
/* WaCompressedResourceSamplerPbeMediaNewHashMode:skl,kbl
*
* Must match Display Engine. See
* WaCompressedResourceDisplayNewHashMode.
*/
wa_write_or(wal,
MMCD_MISC_CTRL,
MMCD_PCLA | MMCD_HOTSPOT_EN);
}
/* WaDisableHDCInvalidation:skl,bxt,kbl,cfl */
wa_write_or(wal,
GAM_ECOCHK,
BDW_DISABLE_HDC_INVALIDATION);
}
static void
skl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
{
gen9_gt_workarounds_init(i915, wal);
/* WaDisableGafsUnitClkGating:skl */
wa_write_or(wal,
GEN7_UCGCTL4,
GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE);
/* WaInPlaceDecompressionHang:skl */
if (IS_SKL_REVID(i915, SKL_REVID_H0, REVID_FOREVER))
wa_write_or(wal,
GEN9_GAMT_ECO_REG_RW_IA,
GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS);
}
static void
bxt_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
{
gen9_gt_workarounds_init(i915, wal);
/* WaInPlaceDecompressionHang:bxt */
wa_write_or(wal,
GEN9_GAMT_ECO_REG_RW_IA,
GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS);
}
static void
kbl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
{
gen9_gt_workarounds_init(i915, wal);
/* WaDisableDynamicCreditSharing:kbl */
if (IS_KBL_REVID(i915, 0, KBL_REVID_B0))
wa_write_or(wal,
GAMT_CHKN_BIT_REG,
GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING);
/* WaDisableGafsUnitClkGating:kbl */
wa_write_or(wal,
GEN7_UCGCTL4,
GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE);
/* WaInPlaceDecompressionHang:kbl */
wa_write_or(wal,
GEN9_GAMT_ECO_REG_RW_IA,
GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS);
}
static void
glk_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
{
gen9_gt_workarounds_init(i915, wal);
}
static void
cfl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
{
gen9_gt_workarounds_init(i915, wal);
/* WaDisableGafsUnitClkGating:cfl */
wa_write_or(wal,
GEN7_UCGCTL4,
GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE);
/* WaInPlaceDecompressionHang:cfl */
wa_write_or(wal,
GEN9_GAMT_ECO_REG_RW_IA,
GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS);
}
static void
wa_init_mcr(struct drm_i915_private *i915, struct i915_wa_list *wal)
{
const struct sseu_dev_info *sseu = &RUNTIME_INFO(i915)->sseu;
u32 mcr_slice_subslice_mask;
/*
* WaProgramMgsrForL3BankSpecificMmioReads: cnl,icl
* L3Banks could be fused off in single slice scenario. If that is
* the case, we might need to program MCR select to a valid L3Bank
* by default, to make sure we correctly read certain registers
* later on (in the range 0xB100 - 0xB3FF).
* This might be incompatible with
* WaProgramMgsrForCorrectSliceSpecificMmioReads.
* Fortunately, this should not happen in production hardware, so
* we only assert that this is the case (instead of implementing
* something more complex that requires checking the range of every
* MMIO read).
*/
if (INTEL_GEN(i915) >= 10 &&
is_power_of_2(sseu->slice_mask)) {
/*
* read FUSE3 for enabled L3 Bank IDs, if L3 Bank matches
* enabled subslice, no need to redirect MCR packet
*/
u32 slice = fls(sseu->slice_mask);
u32 fuse3 =
intel_uncore_read(&i915->uncore, GEN10_MIRROR_FUSE3);
u8 ss_mask = sseu->subslice_mask[slice];
u8 enabled_mask = (ss_mask | ss_mask >>
GEN10_L3BANK_PAIR_COUNT) & GEN10_L3BANK_MASK;
u8 disabled_mask = fuse3 & GEN10_L3BANK_MASK;
/*
* Production silicon should have matched L3Bank and
* subslice enabled
*/
WARN_ON((enabled_mask & disabled_mask) != enabled_mask);
}
if (INTEL_GEN(i915) >= 11)
mcr_slice_subslice_mask = GEN11_MCR_SLICE_MASK |
GEN11_MCR_SUBSLICE_MASK;
else
mcr_slice_subslice_mask = GEN8_MCR_SLICE_MASK |
GEN8_MCR_SUBSLICE_MASK;
/*
* WaProgramMgsrForCorrectSliceSpecificMmioReads:cnl,icl
* Before any MMIO read into slice/subslice specific registers, MCR
* packet control register needs to be programmed to point to any
* enabled s/ss pair. Otherwise, incorrect values will be returned.
* This means each subsequent MMIO read will be forwarded to an
* specific s/ss combination, but this is OK since these registers
* are consistent across s/ss in almost all cases. In the rare
* occasions, such as INSTDONE, where this value is dependent
* on s/ss combo, the read should be done with read_subslice_reg.
*/
wa_write_masked_or(wal,
GEN8_MCR_SELECTOR,
mcr_slice_subslice_mask,
intel_calculate_mcr_s_ss_select(i915));
}
static void
cnl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
{
wa_init_mcr(i915, wal);
/* WaDisableI2mCycleOnWRPort:cnl (pre-prod) */
if (IS_CNL_REVID(i915, CNL_REVID_B0, CNL_REVID_B0))
wa_write_or(wal,
GAMT_CHKN_BIT_REG,
GAMT_CHKN_DISABLE_I2M_CYCLE_ON_WR_PORT);
/* WaInPlaceDecompressionHang:cnl */
wa_write_or(wal,
GEN9_GAMT_ECO_REG_RW_IA,
GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS);
}
static void
icl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
{
wa_init_mcr(i915, wal);
/* WaInPlaceDecompressionHang:icl */
wa_write_or(wal,
GEN9_GAMT_ECO_REG_RW_IA,
GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS);
/* WaModifyGamTlbPartitioning:icl */
wa_write_masked_or(wal,
GEN11_GACB_PERF_CTRL,
GEN11_HASH_CTRL_MASK,
GEN11_HASH_CTRL_BIT0 | GEN11_HASH_CTRL_BIT4);
/* Wa_1405766107:icl
* Formerly known as WaCL2SFHalfMaxAlloc
*/
wa_write_or(wal,
GEN11_LSN_UNSLCVC,
GEN11_LSN_UNSLCVC_GAFS_HALF_SF_MAXALLOC |
GEN11_LSN_UNSLCVC_GAFS_HALF_CL2_MAXALLOC);
/* Wa_220166154:icl
* Formerly known as WaDisCtxReload
*/
wa_write_or(wal,
GEN8_GAMW_ECO_DEV_RW_IA,
GAMW_ECO_DEV_CTX_RELOAD_DISABLE);
/* Wa_1405779004:icl (pre-prod) */
if (IS_ICL_REVID(i915, ICL_REVID_A0, ICL_REVID_A0))
wa_write_or(wal,
SLICE_UNIT_LEVEL_CLKGATE,
MSCUNIT_CLKGATE_DIS);
/* Wa_1406680159:icl */
wa_write_or(wal,
SUBSLICE_UNIT_LEVEL_CLKGATE,
GWUNIT_CLKGATE_DIS);
/* Wa_1406838659:icl (pre-prod) */
if (IS_ICL_REVID(i915, ICL_REVID_A0, ICL_REVID_B0))
wa_write_or(wal,
INF_UNIT_LEVEL_CLKGATE,
CGPSF_CLKGATE_DIS);
/* Wa_1406463099:icl
* Formerly known as WaGamTlbPendError
*/
wa_write_or(wal,
GAMT_CHKN_BIT_REG,
GAMT_CHKN_DISABLE_L3_COH_PIPE);
}
static void
gt_init_workarounds(struct drm_i915_private *i915, struct i915_wa_list *wal)
{
if (IS_GEN(i915, 11))
icl_gt_workarounds_init(i915, wal);
else if (IS_CANNONLAKE(i915))
cnl_gt_workarounds_init(i915, wal);
else if (IS_COFFEELAKE(i915))
cfl_gt_workarounds_init(i915, wal);
else if (IS_GEMINILAKE(i915))
glk_gt_workarounds_init(i915, wal);
else if (IS_KABYLAKE(i915))
kbl_gt_workarounds_init(i915, wal);
else if (IS_BROXTON(i915))
bxt_gt_workarounds_init(i915, wal);
else if (IS_SKYLAKE(i915))
skl_gt_workarounds_init(i915, wal);
else if (INTEL_GEN(i915) <= 8)
return;
else
MISSING_CASE(INTEL_GEN(i915));
}
void intel_gt_init_workarounds(struct drm_i915_private *i915)
{
struct i915_wa_list *wal = &i915->gt_wa_list;
wa_init_start(wal, "GT");
gt_init_workarounds(i915, wal);
wa_init_finish(wal);
}
static enum forcewake_domains
wal_get_fw_for_rmw(struct intel_uncore *uncore, const struct i915_wa_list *wal)
{
enum forcewake_domains fw = 0;
struct i915_wa *wa;
unsigned int i;
for (i = 0, wa = wal->list; i < wal->count; i++, wa++)
fw |= intel_uncore_forcewake_for_reg(uncore,
wa->reg,
FW_REG_READ |
FW_REG_WRITE);
return fw;
}
static void
wa_list_apply(struct intel_uncore *uncore, const struct i915_wa_list *wal)
{
enum forcewake_domains fw;
unsigned long flags;
struct i915_wa *wa;
unsigned int i;
if (!wal->count)
return;
fw = wal_get_fw_for_rmw(uncore, wal);
spin_lock_irqsave(&uncore->lock, flags);
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);
}
intel_uncore_forcewake_put__locked(uncore, fw);
spin_unlock_irqrestore(&uncore->lock, flags);
}
void intel_gt_apply_workarounds(struct drm_i915_private *i915)
{
wa_list_apply(&i915->uncore, &i915->gt_wa_list);
}
static bool
wa_verify(const struct i915_wa *wa, u32 cur, const char *name, const char *from)
{
if ((cur ^ wa->val) & wa->mask) {
DRM_ERROR("%s workaround lost on %s! (%x=%x/%x, expected %x, mask=%x)\n",
name, from, i915_mmio_reg_offset(wa->reg), cur,
cur & wa->mask, wa->val, wa->mask);
return false;
}
return true;
}
static bool wa_list_verify(struct intel_uncore *uncore,
const struct i915_wa_list *wal,
const char *from)
{
struct i915_wa *wa;
unsigned int i;
bool ok = true;
for (i = 0, wa = wal->list; i < wal->count; i++, wa++)
ok &= wa_verify(wa,
intel_uncore_read(uncore, wa->reg),
wal->name, from);
return ok;
}
bool intel_gt_verify_workarounds(struct drm_i915_private *i915,
const char *from)
{
return wa_list_verify(&i915->uncore, &i915->gt_wa_list, from);
}
static void
whitelist_reg(struct i915_wa_list *wal, i915_reg_t reg)
{
struct i915_wa wa = {
.reg = reg
};
if (GEM_DEBUG_WARN_ON(wal->count >= RING_MAX_NONPRIV_SLOTS))
return;
_wa_add(wal, &wa);
}
static void gen9_whitelist_build(struct i915_wa_list *w)
{
/* WaVFEStateAfterPipeControlwithMediaStateClear:skl,bxt,glk,cfl */
whitelist_reg(w, GEN9_CTX_PREEMPT_REG);
/* WaEnablePreemptionGranularityControlByUMD:skl,bxt,kbl,cfl,[cnl] */
whitelist_reg(w, GEN8_CS_CHICKEN1);
/* WaAllowUMDToModifyHDCChicken1:skl,bxt,kbl,glk,cfl */
whitelist_reg(w, GEN8_HDC_CHICKEN1);
}
static void skl_whitelist_build(struct i915_wa_list *w)
{
gen9_whitelist_build(w);
/* WaDisableLSQCROPERFforOCL:skl */
whitelist_reg(w, GEN8_L3SQCREG4);
}
static void bxt_whitelist_build(struct i915_wa_list *w)
{
gen9_whitelist_build(w);
}
static void kbl_whitelist_build(struct i915_wa_list *w)
{
gen9_whitelist_build(w);
/* WaDisableLSQCROPERFforOCL:kbl */
whitelist_reg(w, GEN8_L3SQCREG4);
}
static void glk_whitelist_build(struct i915_wa_list *w)
{
gen9_whitelist_build(w);
/* WA #0862: Userspace has to set "Barrier Mode" to avoid hangs. */
whitelist_reg(w, GEN9_SLICE_COMMON_ECO_CHICKEN1);
}
static void cfl_whitelist_build(struct i915_wa_list *w)
{
gen9_whitelist_build(w);
}
static void cnl_whitelist_build(struct i915_wa_list *w)
{
/* WaEnablePreemptionGranularityControlByUMD:cnl */
whitelist_reg(w, GEN8_CS_CHICKEN1);
}
static void icl_whitelist_build(struct i915_wa_list *w)
{
/* WaAllowUMDToModifyHalfSliceChicken7:icl */
whitelist_reg(w, GEN9_HALF_SLICE_CHICKEN7);
/* WaAllowUMDToModifySamplerMode:icl */
whitelist_reg(w, GEN10_SAMPLER_MODE);
/* WaEnableStateCacheRedirectToCS:icl */
whitelist_reg(w, GEN9_SLICE_COMMON_ECO_CHICKEN1);
}
void intel_engine_init_whitelist(struct intel_engine_cs *engine)
{
struct drm_i915_private *i915 = engine->i915;
struct i915_wa_list *w = &engine->whitelist;
GEM_BUG_ON(engine->id != RCS0);
wa_init_start(w, "whitelist");
if (IS_GEN(i915, 11))
icl_whitelist_build(w);
else if (IS_CANNONLAKE(i915))
cnl_whitelist_build(w);
else if (IS_COFFEELAKE(i915))
cfl_whitelist_build(w);
else if (IS_GEMINILAKE(i915))
glk_whitelist_build(w);
else if (IS_KABYLAKE(i915))
kbl_whitelist_build(w);
else if (IS_BROXTON(i915))
bxt_whitelist_build(w);
else if (IS_SKYLAKE(i915))
skl_whitelist_build(w);
else if (INTEL_GEN(i915) <= 8)
return;
else
MISSING_CASE(INTEL_GEN(i915));
wa_init_finish(w);
}
void intel_engine_apply_whitelist(struct intel_engine_cs *engine)
{
const struct i915_wa_list *wal = &engine->whitelist;
struct intel_uncore *uncore = engine->uncore;
const u32 base = engine->mmio_base;
struct i915_wa *wa;
unsigned int i;
if (!wal->count)
return;
for (i = 0, wa = wal->list; i < wal->count; i++, wa++)
intel_uncore_write(uncore,
RING_FORCE_TO_NONPRIV(base, i),
i915_mmio_reg_offset(wa->reg));
/* And clear the rest just in case of garbage */
for (; i < RING_MAX_NONPRIV_SLOTS; i++)
intel_uncore_write(uncore,
RING_FORCE_TO_NONPRIV(base, i),
i915_mmio_reg_offset(RING_NOPID(base)));
}
static void
rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
{
struct drm_i915_private *i915 = engine->i915;
if (IS_GEN(i915, 11)) {
/* This is not an Wa. Enable for better image quality */
wa_masked_en(wal,
_3D_CHICKEN3,
_3D_CHICKEN3_AA_LINE_QUALITY_FIX_ENABLE);
/* WaPipelineFlushCoherentLines:icl */
wa_write_or(wal,
GEN8_L3SQCREG4,
GEN8_LQSC_FLUSH_COHERENT_LINES);
/*
* Wa_1405543622:icl
* Formerly known as WaGAPZPriorityScheme
*/
wa_write_or(wal,
GEN8_GARBCNTL,
GEN11_ARBITRATION_PRIO_ORDER_MASK);
/*
* Wa_1604223664:icl
* Formerly known as WaL3BankAddressHashing
*/
wa_write_masked_or(wal,
GEN8_GARBCNTL,
GEN11_HASH_CTRL_EXCL_MASK,
GEN11_HASH_CTRL_EXCL_BIT0);
wa_write_masked_or(wal,
GEN11_GLBLINVL,
GEN11_BANK_HASH_ADDR_EXCL_MASK,
GEN11_BANK_HASH_ADDR_EXCL_BIT0);
/*
* Wa_1405733216:icl
* Formerly known as WaDisableCleanEvicts
*/
wa_write_or(wal,
GEN8_L3SQCREG4,
GEN11_LQSC_CLEAN_EVICT_DISABLE);
/* WaForwardProgressSoftReset:icl */
wa_write_or(wal,
GEN10_SCRATCH_LNCF2,
PMFLUSHDONE_LNICRSDROP |
PMFLUSH_GAPL3UNBLOCK |
PMFLUSHDONE_LNEBLK);
/* Wa_1406609255:icl (pre-prod) */
if (IS_ICL_REVID(i915, ICL_REVID_A0, ICL_REVID_B0))
wa_write_or(wal,
GEN7_SARCHKMD,
GEN7_DISABLE_DEMAND_PREFETCH |
GEN7_DISABLE_SAMPLER_PREFETCH);
}
if (IS_GEN_RANGE(i915, 9, 11)) {
/* FtrPerCtxtPreemptionGranularityControl:skl,bxt,kbl,cfl,cnl,icl */
wa_masked_en(wal,
GEN7_FF_SLICE_CS_CHICKEN1,
GEN9_FFSC_PERCTX_PREEMPT_CTRL);
}
if (IS_SKYLAKE(i915) || IS_KABYLAKE(i915) || IS_COFFEELAKE(i915)) {
/* WaEnableGapsTsvCreditFix:skl,kbl,cfl */
wa_write_or(wal,
GEN8_GARBCNTL,
GEN9_GAPS_TSV_CREDIT_DISABLE);
}
if (IS_BROXTON(i915)) {
/* WaDisablePooledEuLoadBalancingFix:bxt */
wa_masked_en(wal,
FF_SLICE_CS_CHICKEN2,
GEN9_POOLED_EU_LOAD_BALANCING_FIX_DISABLE);
}
if (IS_GEN(i915, 9)) {
/* WaContextSwitchWithConcurrentTLBInvalidate:skl,bxt,kbl,glk,cfl */
wa_masked_en(wal,
GEN9_CSFE_CHICKEN1_RCS,
GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE);
/* WaEnableLbsSlaRetryTimerDecrement:skl,bxt,kbl,glk,cfl */
wa_write_or(wal,
BDW_SCRATCH1,
GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE);
/* WaProgramL3SqcReg1DefaultForPerf:bxt,glk */
if (IS_GEN9_LP(i915))
wa_write_masked_or(wal,
GEN8_L3SQCREG1,
L3_PRIO_CREDITS_MASK,
L3_GENERAL_PRIO_CREDITS(62) |
L3_HIGH_PRIO_CREDITS(2));
/* WaOCLCoherentLineFlush:skl,bxt,kbl,cfl */
wa_write_or(wal,
GEN8_L3SQCREG4,
GEN8_LQSC_FLUSH_COHERENT_LINES);
}
}
static void
xcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
{
struct drm_i915_private *i915 = engine->i915;
/* WaKBLVECSSemaphoreWaitPoll:kbl */
if (IS_KBL_REVID(i915, KBL_REVID_A0, KBL_REVID_E0)) {
wa_write(wal,
RING_SEMA_WAIT_POLL(engine->mmio_base),
1);
}
}
static void
engine_init_workarounds(struct intel_engine_cs *engine, struct i915_wa_list *wal)
{
if (I915_SELFTEST_ONLY(INTEL_GEN(engine->i915) < 8))
return;
if (engine->id == RCS0)
rcs_engine_wa_init(engine, wal);
else
xcs_engine_wa_init(engine, wal);
}
void intel_engine_init_workarounds(struct intel_engine_cs *engine)
{
struct i915_wa_list *wal = &engine->wa_list;
if (GEM_WARN_ON(INTEL_GEN(engine->i915) < 8))
return;
wa_init_start(wal, engine->name);
engine_init_workarounds(engine, wal);
wa_init_finish(wal);
}
void intel_engine_apply_workarounds(struct intel_engine_cs *engine)
{
wa_list_apply(engine->uncore, &engine->wa_list);
}
#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
#include "selftests/intel_workarounds.c"
#endif
Reference in New Issue View Git Blame Copy Permalink