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.c89
1 files changed, 65 insertions, 24 deletions
diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
index 5b2b37b59813..9f327f27c072 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops.c
+++ b/drivers/gpu/drm/xe/xe_ring_ops.c
@@ -7,9 +7,9 @@
#include <generated/xe_wa_oob.h>
+#include "instructions/xe_gpu_commands.h"
#include "instructions/xe_mi_commands.h"
#include "regs/xe_engine_regs.h"
-#include "regs/xe_gpu_commands.h"
#include "regs/xe_gt_regs.h"
#include "regs/xe_lrc_layout.h"
#include "xe_exec_queue_types.h"
@@ -17,6 +17,7 @@
#include "xe_lrc.h"
#include "xe_macros.h"
#include "xe_sched_job.h"
+#include "xe_sriov.h"
#include "xe_vm_types.h"
#include "xe_vm.h"
#include "xe_wa.h"
@@ -79,6 +80,16 @@ static int emit_store_imm_ggtt(u32 addr, u32 value, u32 *dw, int i)
return i;
}
+static int emit_flush_dw(u32 *dw, int i)
+{
+ dw[i++] = MI_FLUSH_DW | MI_FLUSH_IMM_DW;
+ dw[i++] = 0;
+ dw[i++] = 0;
+ dw[i++] = 0;
+
+ return i;
+}
+
static int emit_flush_imm_ggtt(u32 addr, u32 value, bool invalidate_tlb,
u32 *dw, int i)
{
@@ -210,7 +221,23 @@ 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++] = 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) */
@@ -221,6 +248,8 @@ static void __emit_job_gen12_simple(struct xe_sched_job *job, struct xe_lrc *lrc
u32 ppgtt_flag = get_ppgtt_flag(job);
struct xe_gt *gt = job->q->gt;
+ 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),
@@ -233,10 +262,12 @@ static void __emit_job_gen12_simple(struct xe_sched_job *job, struct xe_lrc *lrc
i = emit_bb_start(batch_addr, ppgtt_flag, dw, i);
- if (job->user_fence.used)
+ if (job->user_fence.used) {
+ i = emit_flush_dw(dw, i);
i = emit_store_imm_ppgtt_posted(job->user_fence.addr,
job->user_fence.value,
dw, i);
+ }
i = emit_flush_imm_ggtt(xe_lrc_seqno_ggtt_addr(lrc), seqno, false, dw, i);
@@ -270,6 +301,8 @@ 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;
+ i = emit_copy_timestamp(lrc, dw, i);
+
dw[i++] = preparser_disable(true);
/* hsdes: 1809175790 */
@@ -292,10 +325,12 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc,
i = emit_bb_start(batch_addr, ppgtt_flag, dw, i);
- if (job->user_fence.used)
+ if (job->user_fence.used) {
+ i = emit_flush_dw(dw, i);
i = emit_store_imm_ppgtt_posted(job->user_fence.addr,
job->user_fence.value,
dw, i);
+ }
i = emit_flush_imm_ggtt(xe_lrc_seqno_ggtt_addr(lrc), seqno, false, dw, i);
@@ -317,6 +352,8 @@ 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;
+ i = emit_copy_timestamp(lrc, dw, i);
+
dw[i++] = preparser_disable(true);
if (lacks_render)
mask_flags = PIPE_CONTROL_3D_ARCH_FLAGS;
@@ -360,19 +397,23 @@ static void emit_migration_job_gen12(struct xe_sched_job *job,
{
u32 dw[MAX_JOB_SIZE_DW], i = 0;
+ i = emit_copy_timestamp(lrc, dw, i);
+
i = emit_store_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc),
seqno, dw, i);
dw[i++] = MI_ARB_ON_OFF | MI_ARB_DISABLE; /* Enabled again below */
- i = emit_bb_start(job->batch_addr[0], BIT(8), dw, i);
+ i = emit_bb_start(job->ptrs[0].batch_addr, BIT(8), dw, i);
- /* 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);
+ 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);
+ }
- i = emit_bb_start(job->batch_addr[1], BIT(8), dw, i);
+ 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;
@@ -393,9 +434,9 @@ static void emit_job_gen12_gsc(struct xe_sched_job *job)
xe_gt_assert(gt, job->q->width <= 1); /* no parallel submission for GSCCS */
- __emit_job_gen12_simple(job, job->q->lrc,
- job->batch_addr[0],
- xe_sched_job_seqno(job));
+ __emit_job_gen12_simple(job, job->q->lrc[0],
+ job->ptrs[0].batch_addr,
+ xe_sched_job_lrc_seqno(job));
}
static void emit_job_gen12_copy(struct xe_sched_job *job)
@@ -403,15 +444,15 @@ static void emit_job_gen12_copy(struct xe_sched_job *job)
int i;
if (xe_sched_job_is_migration(job->q)) {
- emit_migration_job_gen12(job, job->q->lrc,
- xe_sched_job_seqno(job));
+ emit_migration_job_gen12(job, job->q->lrc[0],
+ xe_sched_job_lrc_seqno(job));
return;
}
for (i = 0; i < job->q->width; ++i)
- __emit_job_gen12_simple(job, job->q->lrc + i,
- job->batch_addr[i],
- xe_sched_job_seqno(job));
+ __emit_job_gen12_simple(job, job->q->lrc[i],
+ job->ptrs[i].batch_addr,
+ xe_sched_job_lrc_seqno(job));
}
static void emit_job_gen12_video(struct xe_sched_job *job)
@@ -420,9 +461,9 @@ static void emit_job_gen12_video(struct xe_sched_job *job)
/* FIXME: Not doing parallel handshake for now */
for (i = 0; i < job->q->width; ++i)
- __emit_job_gen12_video(job, job->q->lrc + i,
- job->batch_addr[i],
- xe_sched_job_seqno(job));
+ __emit_job_gen12_video(job, job->q->lrc[i],
+ job->ptrs[i].batch_addr,
+ xe_sched_job_lrc_seqno(job));
}
static void emit_job_gen12_render_compute(struct xe_sched_job *job)
@@ -430,9 +471,9 @@ static void emit_job_gen12_render_compute(struct xe_sched_job *job)
int i;
for (i = 0; i < job->q->width; ++i)
- __emit_job_gen12_render_compute(job, job->q->lrc + i,
- job->batch_addr[i],
- xe_sched_job_seqno(job));
+ __emit_job_gen12_render_compute(job, job->q->lrc[i],
+ job->ptrs[i].batch_addr,
+ xe_sched_job_lrc_seqno(job));
}
static const struct xe_ring_ops ring_ops_gen12_gsc = {
generated by cgit (git 2.34.1) at 2025-03-22 08:58:59 +0000