summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/xe/xe_ring_ops.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/xe/xe_ring_ops.c')
-rw-r--r--drivers/gpu/drm/xe/xe_ring_ops.c102
1 files changed, 59 insertions, 43 deletions
diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
index 0be4f489d3e1..ac0c6dcffe15 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops.c
+++ b/drivers/gpu/drm/xe/xe_ring_ops.c
@@ -90,11 +90,10 @@ static int emit_flush_dw(u32 *dw, int i)
return i;
}
-static int emit_flush_imm_ggtt(u32 addr, u32 value, bool invalidate_tlb,
- u32 *dw, int i)
+static int emit_flush_imm_ggtt(u32 addr, u32 value, u32 flags, u32 *dw, int i)
{
dw[i++] = MI_FLUSH_DW | MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_IMM_DW |
- (invalidate_tlb ? MI_INVALIDATE_TLB : 0);
+ flags;
dw[i++] = addr | MI_FLUSH_DW_USE_GTT;
dw[i++] = 0;
dw[i++] = value;
@@ -111,16 +110,14 @@ static int emit_bb_start(u64 batch_addr, u32 ppgtt_flag, u32 *dw, int i)
return i;
}
-static int emit_flush_invalidate(u32 flag, u32 *dw, int i)
+static int emit_flush_invalidate(u32 addr, u32 val, u32 flush_flags, u32 *dw, int i)
{
- dw[i] = MI_FLUSH_DW;
- dw[i] |= flag;
- dw[i++] |= MI_INVALIDATE_TLB | MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_IMM_DW |
- MI_FLUSH_DW_STORE_INDEX;
+ dw[i++] = MI_FLUSH_DW | MI_FLUSH_DW_OP_STOREDW |
+ MI_FLUSH_IMM_DW | (flush_flags & MI_INVALIDATE_TLB) ?: 0;
- dw[i++] = LRC_PPHWSP_SCRATCH_ADDR | MI_FLUSH_DW_USE_GTT;
+ dw[i++] = addr | MI_FLUSH_DW_USE_GTT;
dw[i++] = 0;
- dw[i++] = ~0U;
+ dw[i++] = val;
return i;
}
@@ -141,7 +138,8 @@ emit_pipe_control(u32 *dw, int i, u32 bit_group_0, u32 bit_group_1, u32 offset,
static int emit_pipe_invalidate(u32 mask_flags, bool invalidate_tlb, u32 *dw,
int i)
{
- u32 flags = PIPE_CONTROL_CS_STALL |
+ u32 flags0 = 0;
+ u32 flags1 = PIPE_CONTROL_CS_STALL |
PIPE_CONTROL_COMMAND_CACHE_INVALIDATE |
PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE |
PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE |
@@ -152,11 +150,15 @@ static int emit_pipe_invalidate(u32 mask_flags, bool invalidate_tlb, u32 *dw,
PIPE_CONTROL_STORE_DATA_INDEX;
if (invalidate_tlb)
- flags |= PIPE_CONTROL_TLB_INVALIDATE;
+ flags1 |= PIPE_CONTROL_TLB_INVALIDATE;
+
+ flags1 &= ~mask_flags;
- flags &= ~mask_flags;
+ if (flags1 & PIPE_CONTROL_VF_CACHE_INVALIDATE)
+ flags0 |= PIPE_CONTROL0_L3_READ_ONLY_CACHE_INVALIDATE;
- return emit_pipe_control(dw, i, 0, flags, LRC_PPHWSP_SCRATCH_ADDR, 0);
+ return emit_pipe_control(dw, i, flags0, flags1,
+ LRC_PPHWSP_FLUSH_INVAL_SCRATCH_ADDR, 0);
}
static int emit_store_imm_ppgtt_posted(u64 addr, u64 value,
@@ -177,6 +179,10 @@ static int emit_render_cache_flush(struct xe_sched_job *job, u32 *dw, int i)
bool lacks_render = !(gt->info.engine_mask & XE_HW_ENGINE_RCS_MASK);
u32 flags;
+ if (XE_GT_WA(gt, 14016712196))
+ i = emit_pipe_control(dw, i, 0, PIPE_CONTROL_DEPTH_CACHE_FLUSH,
+ LRC_PPHWSP_FLUSH_INVAL_SCRATCH_ADDR, 0);
+
flags = (PIPE_CONTROL_CS_STALL |
PIPE_CONTROL_TILE_CACHE_FLUSH |
PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
@@ -184,7 +190,7 @@ static int emit_render_cache_flush(struct xe_sched_job *job, u32 *dw, int i)
PIPE_CONTROL_DC_FLUSH_ENABLE |
PIPE_CONTROL_FLUSH_ENABLE);
- if (XE_WA(gt, 1409600907))
+ if (XE_GT_WA(gt, 1409600907))
flags |= PIPE_CONTROL_DEPTH_STALL;
if (lacks_render)
@@ -200,7 +206,7 @@ static int emit_pipe_control_to_ring_end(struct xe_hw_engine *hwe, u32 *dw, int
if (hwe->class != XE_ENGINE_CLASS_RENDER)
return i;
- if (XE_WA(hwe->gt, 16020292621))
+ if (XE_GT_WA(hwe->gt, 16020292621))
i = emit_pipe_control(dw, i, 0, PIPE_CONTROL_LRI_POST_SYNC,
RING_NOPID(hwe->mmio_base).addr, 0);
@@ -221,36 +227,38 @@ static int emit_pipe_imm_ggtt(u32 addr, u32 value, bool stall_only, u32 *dw,
static u32 get_ppgtt_flag(struct xe_sched_job *job)
{
- return job->q->vm ? BIT(8) : 0;
+ if (job->q->vm && !job->ggtt)
+ return BIT(8);
+
+ return 0;
}
static int emit_copy_timestamp(struct xe_lrc *lrc, u32 *dw, int i)
{
- dw[i++] = MI_COPY_MEM_MEM | MI_COPY_MEM_MEM_SRC_GGTT |
- MI_COPY_MEM_MEM_DST_GGTT;
+ dw[i++] = MI_STORE_REGISTER_MEM | MI_SRM_USE_GGTT | MI_SRM_ADD_CS_OFFSET;
+ dw[i++] = RING_CTX_TIMESTAMP(0).addr;
dw[i++] = xe_lrc_ctx_job_timestamp_ggtt_addr(lrc);
dw[i++] = 0;
- dw[i++] = xe_lrc_ctx_timestamp_ggtt_addr(lrc);
- dw[i++] = 0;
- dw[i++] = MI_NOOP;
return i;
}
/* for engines that don't require any special HW handling (no EUs, no aux inval, etc) */
static void __emit_job_gen12_simple(struct xe_sched_job *job, struct xe_lrc *lrc,
- u64 batch_addr, u32 seqno)
+ u64 batch_addr, u32 *head, u32 seqno)
{
u32 dw[MAX_JOB_SIZE_DW], i = 0;
u32 ppgtt_flag = get_ppgtt_flag(job);
struct xe_gt *gt = job->q->gt;
+ *head = lrc->ring.tail;
+
i = emit_copy_timestamp(lrc, dw, i);
if (job->ring_ops_flush_tlb) {
dw[i++] = preparser_disable(true);
i = emit_flush_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc),
- seqno, true, dw, i);
+ seqno, MI_INVALIDATE_TLB, dw, i);
dw[i++] = preparser_disable(false);
} else {
i = emit_store_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc),
@@ -266,7 +274,7 @@ static void __emit_job_gen12_simple(struct xe_sched_job *job, struct xe_lrc *lrc
dw, i);
}
- i = emit_flush_imm_ggtt(xe_lrc_seqno_ggtt_addr(lrc), seqno, false, dw, i);
+ i = emit_flush_imm_ggtt(xe_lrc_seqno_ggtt_addr(lrc), seqno, 0, dw, i);
i = emit_user_interrupt(dw, i);
@@ -290,7 +298,7 @@ static bool has_aux_ccs(struct xe_device *xe)
}
static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc,
- u64 batch_addr, u32 seqno)
+ u64 batch_addr, u32 *head, u32 seqno)
{
u32 dw[MAX_JOB_SIZE_DW], i = 0;
u32 ppgtt_flag = get_ppgtt_flag(job);
@@ -298,6 +306,8 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc,
struct xe_device *xe = gt_to_xe(gt);
bool decode = job->q->class == XE_ENGINE_CLASS_VIDEO_DECODE;
+ *head = lrc->ring.tail;
+
i = emit_copy_timestamp(lrc, dw, i);
dw[i++] = preparser_disable(true);
@@ -312,7 +322,7 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc,
if (job->ring_ops_flush_tlb)
i = emit_flush_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc),
- seqno, true, dw, i);
+ seqno, MI_INVALIDATE_TLB, dw, i);
dw[i++] = preparser_disable(false);
@@ -329,7 +339,7 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc,
dw, i);
}
- i = emit_flush_imm_ggtt(xe_lrc_seqno_ggtt_addr(lrc), seqno, false, dw, i);
+ i = emit_flush_imm_ggtt(xe_lrc_seqno_ggtt_addr(lrc), seqno, 0, dw, i);
i = emit_user_interrupt(dw, i);
@@ -340,7 +350,8 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc,
static void __emit_job_gen12_render_compute(struct xe_sched_job *job,
struct xe_lrc *lrc,
- u64 batch_addr, u32 seqno)
+ u64 batch_addr, u32 *head,
+ u32 seqno)
{
u32 dw[MAX_JOB_SIZE_DW], i = 0;
u32 ppgtt_flag = get_ppgtt_flag(job);
@@ -349,6 +360,8 @@ static void __emit_job_gen12_render_compute(struct xe_sched_job *job,
bool lacks_render = !(gt->info.engine_mask & XE_HW_ENGINE_RCS_MASK);
u32 mask_flags = 0;
+ *head = lrc->ring.tail;
+
i = emit_copy_timestamp(lrc, dw, i);
dw[i++] = preparser_disable(true);
@@ -390,33 +403,31 @@ static void __emit_job_gen12_render_compute(struct xe_sched_job *job,
}
static void emit_migration_job_gen12(struct xe_sched_job *job,
- struct xe_lrc *lrc, u32 seqno)
+ struct xe_lrc *lrc, u32 *head,
+ u32 seqno)
{
+ u32 saddr = xe_lrc_start_seqno_ggtt_addr(lrc);
u32 dw[MAX_JOB_SIZE_DW], i = 0;
+ *head = lrc->ring.tail;
+
i = emit_copy_timestamp(lrc, dw, i);
- i = emit_store_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc),
- seqno, dw, i);
+ i = emit_store_imm_ggtt(saddr, seqno, dw, i);
dw[i++] = MI_ARB_ON_OFF | MI_ARB_DISABLE; /* Enabled again below */
i = emit_bb_start(job->ptrs[0].batch_addr, BIT(8), dw, i);
- if (!IS_SRIOV_VF(gt_to_xe(job->q->gt))) {
- /* XXX: Do we need this? Leaving for now. */
- dw[i++] = preparser_disable(true);
- i = emit_flush_invalidate(0, dw, i);
- dw[i++] = preparser_disable(false);
- }
+ dw[i++] = preparser_disable(true);
+ i = emit_flush_invalidate(saddr, seqno, job->migrate_flush_flags, dw, i);
+ dw[i++] = preparser_disable(false);
i = emit_bb_start(job->ptrs[1].batch_addr, BIT(8), dw, i);
- dw[i++] = MI_FLUSH_DW | MI_INVALIDATE_TLB | job->migrate_flush_flags |
- MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_IMM_DW;
- dw[i++] = xe_lrc_seqno_ggtt_addr(lrc) | MI_FLUSH_DW_USE_GTT;
- dw[i++] = 0;
- dw[i++] = seqno; /* value */
+ i = emit_flush_imm_ggtt(xe_lrc_seqno_ggtt_addr(lrc), seqno,
+ job->migrate_flush_flags,
+ dw, i);
i = emit_user_interrupt(dw, i);
@@ -433,6 +444,7 @@ static void emit_job_gen12_gsc(struct xe_sched_job *job)
__emit_job_gen12_simple(job, job->q->lrc[0],
job->ptrs[0].batch_addr,
+ &job->ptrs[0].head,
xe_sched_job_lrc_seqno(job));
}
@@ -442,6 +454,7 @@ static void emit_job_gen12_copy(struct xe_sched_job *job)
if (xe_sched_job_is_migration(job->q)) {
emit_migration_job_gen12(job, job->q->lrc[0],
+ &job->ptrs[0].head,
xe_sched_job_lrc_seqno(job));
return;
}
@@ -449,6 +462,7 @@ static void emit_job_gen12_copy(struct xe_sched_job *job)
for (i = 0; i < job->q->width; ++i)
__emit_job_gen12_simple(job, job->q->lrc[i],
job->ptrs[i].batch_addr,
+ &job->ptrs[i].head,
xe_sched_job_lrc_seqno(job));
}
@@ -460,6 +474,7 @@ static void emit_job_gen12_video(struct xe_sched_job *job)
for (i = 0; i < job->q->width; ++i)
__emit_job_gen12_video(job, job->q->lrc[i],
job->ptrs[i].batch_addr,
+ &job->ptrs[i].head,
xe_sched_job_lrc_seqno(job));
}
@@ -470,6 +485,7 @@ static void emit_job_gen12_render_compute(struct xe_sched_job *job)
for (i = 0; i < job->q->width; ++i)
__emit_job_gen12_render_compute(job, job->q->lrc[i],
job->ptrs[i].batch_addr,
+ &job->ptrs[i].head,
xe_sched_job_lrc_seqno(job));
}
generated by cgit (git 2.34.1) at 2025-12-25 09:50:35 +0000