gpu: host1x: Add support for syncpoint waits in CDMA pushbuffer

Add support for inserting syncpoint waits in the CDMA pushbuffer.
These waits need to be done in HOST1X class, while gather submitted
by the application execute in engine class.

Support is added by converting the gather list of job into a command
list that can include both gathers and waits. When the job is
submitted, these commands are pushed as the appropriate opcodes
on the CDMA pushbuffer.

Also supported are waits relative to the start of the job,
which are useful for jobs doing multiple things with an engine
that doesn't natively support pipelining.

While at it, use 32-bit waits on chips that support them.

Signed-off-by: Mikko Perttunen <mperttunen@nvidia.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>

1 files changed, 65 insertions, 20 deletions

diff --git a/drivers/gpu/host1x/hw/channel_hw.c b/drivers/gpu/host1x/hw/channel_hw.c
index bf21512e5078..1999780a7203 100644
--- a/drivers/gpu/host1x/hw/channel_hw.c
+++ b/drivers/gpu/host1x/hw/channel_hw.c
@@ -47,39 +47,84 @@ static void trace_write_gather(struct host1x_cdma *cdma, struct host1x_bo *bo,
 	}
 }
 
-static void submit_gathers(struct host1x_job *job)
+static void submit_wait(struct host1x_cdma *cdma, u32 id, u32 threshold,
+			u32 next_class)
+{
+#if HOST1X_HW >= 2
+	host1x_cdma_push_wide(cdma,
+		host1x_opcode_setclass(
+			HOST1X_CLASS_HOST1X,
+			HOST1X_UCLASS_LOAD_SYNCPT_PAYLOAD_32,
+			/* WAIT_SYNCPT_32 is at SYNCPT_PAYLOAD_32+2 */
+			BIT(0) | BIT(2)
+		),
+		threshold,
+		id,
+		host1x_opcode_setclass(next_class, 0, 0)
+	);
+#else
+	/* TODO add waitchk or use waitbases or other mitigation */
+	host1x_cdma_push(cdma,
+		host1x_opcode_setclass(
+			HOST1X_CLASS_HOST1X,
+			host1x_uclass_wait_syncpt_r(),
+			BIT(0)
+		),
+		host1x_class_host_wait_syncpt(id, threshold)
+	);
+	host1x_cdma_push(cdma,
+		host1x_opcode_setclass(next_class, 0, 0),
+		HOST1X_OPCODE_NOP
+	);
+#endif
+}
+
+static void submit_gathers(struct host1x_job *job, u32 job_syncpt_base)
 {
 	struct host1x_cdma *cdma = &job->channel->cdma;
 #if HOST1X_HW < 6
 	struct device *dev = job->channel->dev;
 #endif
 	unsigned int i;
+	u32 threshold;
 
-	for (i = 0; i < job->num_gathers; i++) {
-		struct host1x_job_gather *g = &job->gathers[i];
-		dma_addr_t addr = g->base + g->offset;
-		u32 op2, op3;
+	for (i = 0; i < job->num_cmds; i++) {
+		struct host1x_job_cmd *cmd = &job->cmds[i];
 
-		op2 = lower_32_bits(addr);
-		op3 = upper_32_bits(addr);
+		if (cmd->is_wait) {
+			if (cmd->wait.relative)
+				threshold = job_syncpt_base + cmd->wait.threshold;
+			else
+				threshold = cmd->wait.threshold;
 
-		trace_write_gather(cdma, g->bo, g->offset, g->words);
+			submit_wait(cdma, cmd->wait.id, threshold, cmd->wait.next_class);
+		} else {
+			struct host1x_job_gather *g = &cmd->gather;
+
+			dma_addr_t addr = g->base + g->offset;
+			u32 op2, op3;
+
+			op2 = lower_32_bits(addr);
+			op3 = upper_32_bits(addr);
 
-		if (op3 != 0) {
+			trace_write_gather(cdma, g->bo, g->offset, g->words);
+
+			if (op3 != 0) {
 #if HOST1X_HW >= 6
-			u32 op1 = host1x_opcode_gather_wide(g->words);
-			u32 op4 = HOST1X_OPCODE_NOP;
+				u32 op1 = host1x_opcode_gather_wide(g->words);
+				u32 op4 = HOST1X_OPCODE_NOP;
 
-			host1x_cdma_push_wide(cdma, op1, op2, op3, op4);
+				host1x_cdma_push_wide(cdma, op1, op2, op3, op4);
 #else
-			dev_err(dev, "invalid gather for push buffer %pad\n",
-				&addr);
-			continue;
+				dev_err(dev, "invalid gather for push buffer %pad\n",
+					&addr);
+				continue;
 #endif
-		} else {
-			u32 op1 = host1x_opcode_gather(g->words);
+			} else {
+				u32 op1 = host1x_opcode_gather(g->words);
 
-			host1x_cdma_push(cdma, op1, op2);
+				host1x_cdma_push(cdma, op1, op2);
+			}
 		}
 	}
 }
@@ -126,7 +171,7 @@ static int channel_submit(struct host1x_job *job)
 	struct host1x *host = dev_get_drvdata(ch->dev->parent);
 
 	trace_host1x_channel_submit(dev_name(ch->dev),
-				    job->num_gathers, job->num_relocs,
+				    job->num_cmds, job->num_relocs,
 				    job->syncpt->id, job->syncpt_incrs);
 
 	/* before error checks, return current max */
@@ -181,7 +226,7 @@ static int channel_submit(struct host1x_job *job)
 				 host1x_opcode_setclass(job->class, 0, 0),
 				 HOST1X_OPCODE_NOP);
 
-	submit_gathers(job);
+	submit_gathers(job, syncval - user_syncpt_incrs);
 
 	/* end CDMA submit & stash pinned hMems into sync queue */
 	host1x_cdma_end(&ch->cdma, job);