[PATCH] drm/xe/migrate: make MI_TLB_INVALIDATE conditional

[Matthew Auld]

When clearing VRAM we should be able to skip invalidating the TLBs if we
are only using the identity map to access VRAM (which is the common
case), since no modifications are made to PTEs on the fly. Also since we
use huge 1G entries within the identity map, there should be a pretty
decent chance that the next packet(s) (if also clears) can avoid a tree
walk if we don't shoot down the TLBs, like if we have to process a long
stream of clears.

Signed-off-by: Matthew Auld <matthew.auld at intel.com>
Cc: Himal Prasad Ghimiray <himal.prasad.ghimiray at intel.com>
Cc: Thomas Hellström <thomas.hellstrom at linux.intel.com>
Cc: Matthew Brost <matthew.brost at intel.com>
---
 drivers/gpu/drm/xe/xe_migrate.c  | 18 +++++++++++-------
 drivers/gpu/drm/xe/xe_ring_ops.c | 10 +++++-----
 2 files changed, 16 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 8f8e9fdfb2a8..a76363740a12 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -896,7 +896,7 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m,
 			goto err;
 		}
 
-		xe_sched_job_add_migrate_flush(job, flush_flags);
+		xe_sched_job_add_migrate_flush(job, flush_flags | MI_INVALIDATE_TLB);
 		if (!fence) {
 			err = xe_sched_job_add_deps(job, src_bo->ttm.base.resv,
 						    DMA_RESV_USAGE_BOOKKEEP);
@@ -1119,11 +1119,13 @@ struct dma_fence *xe_migrate_clear(struct xe_migrate *m,
 
 		size -= clear_L0;
 		/* Preemption is enabled again by the ring ops. */
-		if (clear_vram && xe_migrate_allow_identity(clear_L0, &src_it))
+		if (clear_vram && xe_migrate_allow_identity(clear_L0, &src_it)) {
 			xe_res_next(&src_it, clear_L0);
-		else
-			emit_pte(m, bb, clear_L0_pt, clear_vram, clear_only_system_ccs,
-				 &src_it, clear_L0, dst);
+		} else {
+			emit_pte(m, bb, clear_L0_pt, clear_vram,
+				 clear_only_system_ccs, &src_it, clear_L0, dst);
+			flush_flags |= MI_INVALIDATE_TLB;
+		}
 
 		bb->cs[bb->len++] = MI_BATCH_BUFFER_END;
 		update_idx = bb->len;
@@ -1134,7 +1136,7 @@ struct dma_fence *xe_migrate_clear(struct xe_migrate *m,
 		if (xe_migrate_needs_ccs_emit(xe)) {
 			emit_copy_ccs(gt, bb, clear_L0_ofs, true,
 				      m->cleared_mem_ofs, false, clear_L0);
-			flush_flags = MI_FLUSH_DW_CCS;
+			flush_flags |= MI_FLUSH_DW_CCS;
 		}
 
 		job = xe_bb_create_migration_job(m->q, bb,
@@ -1469,6 +1471,8 @@ __xe_migrate_update_pgtables(struct xe_migrate *m,
 		goto err_sa;
 	}
 
+	xe_sched_job_add_migrate_flush(job, MI_INVALIDATE_TLB);
+
 	if (ops->pre_commit) {
 		pt_update->job = job;
 		err = ops->pre_commit(pt_update);
@@ -1667,7 +1671,7 @@ static struct dma_fence *xe_migrate_vram(struct xe_migrate *m,
 		goto err;
 	}
 
-	xe_sched_job_add_migrate_flush(job, 0);
+	xe_sched_job_add_migrate_flush(job, MI_INVALIDATE_TLB);
 
 	mutex_lock(&m->job_mutex);
 	xe_sched_job_arm(job);
diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
index bc1689db4cd7..b5548e0769f4 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops.c
+++ b/drivers/gpu/drm/xe/xe_ring_ops.c
@@ -110,10 +110,10 @@ static int emit_bb_start(u64 batch_addr, u32 ppgtt_flag, u32 *dw, int i)
 	return i;
 }
 
-static int emit_flush_invalidate(u32 *dw, int i)
+static int emit_flush_invalidate(u32 *dw, int i, u32 flush_flags)
 {
-	dw[i++] = MI_FLUSH_DW | 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 |
+		MI_FLUSH_DW_STORE_INDEX | (flush_flags & MI_INVALIDATE_TLB) ?: 0;
 	dw[i++] = LRC_PPHWSP_FLUSH_INVAL_SCRATCH_ADDR;
 	dw[i++] = 0;
 	dw[i++] = 0;
@@ -411,13 +411,13 @@ static void emit_migration_job_gen12(struct xe_sched_job *job,
 	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(dw, i);
+		i = emit_flush_invalidate(dw, i, job->migrate_flush_flags);
 		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 |
+	dw[i++] = MI_FLUSH_DW | 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;
-- 
2.49.0