gpu: host1x: Program context stream ID on submission

Add code to do stream ID switching at the beginning of a job. The
stream ID is switched to the stream ID specified by the context
passed in the job structure.

Before switching the stream ID, an OP_DONE wait is done on the
channel's engine to ensure that there is no residual ongoing
work that might do DMA using the new stream ID.

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

3 files changed, 68 insertions, 4 deletions

diff --git a/drivers/gpu/host1x/hw/channel_hw.c b/drivers/gpu/host1x/hw/channel_hw.c
index 6b40e9af1e88..f84caf06621a 100644
--- a/drivers/gpu/host1x/hw/channel_hw.c
+++ b/drivers/gpu/host1x/hw/channel_hw.c
@@ -180,6 +180,45 @@ static void host1x_enable_gather_filter(struct host1x_channel *ch)
 #endif
 }
 
+static void host1x_channel_program_engine_streamid(struct host1x_job *job)
+{
+#if HOST1X_HW >= 6
+	u32 fence;
+
+	if (!job->memory_context)
+		return;
+
+	fence = host1x_syncpt_incr_max(job->syncpt, 1);
+
+	/* First, increment a syncpoint on OP_DONE condition.. */
+
+	host1x_cdma_push(&job->channel->cdma,
+		host1x_opcode_nonincr(HOST1X_UCLASS_INCR_SYNCPT, 1),
+		HOST1X_UCLASS_INCR_SYNCPT_INDX_F(job->syncpt->id) |
+			HOST1X_UCLASS_INCR_SYNCPT_COND_F(1));
+
+	/* Wait for syncpoint to increment */
+
+	host1x_cdma_push(&job->channel->cdma,
+		host1x_opcode_setclass(HOST1X_CLASS_HOST1X,
+			host1x_uclass_wait_syncpt_r(), 1),
+		host1x_class_host_wait_syncpt(job->syncpt->id, fence));
+
+	/*
+	 * Now that we know the engine is idle, return to class and
+	 * change stream ID.
+	 */
+
+	host1x_cdma_push(&job->channel->cdma,
+		host1x_opcode_setclass(job->class, 0, 0),
+		HOST1X_OPCODE_NOP);
+
+	host1x_cdma_push(&job->channel->cdma,
+		host1x_opcode_setpayload(job->memory_context->stream_id),
+		host1x_opcode_setstreamid(job->engine_streamid_offset / 4));
+#endif
+}
+
 static int channel_submit(struct host1x_job *job)
 {
 	struct host1x_channel *ch = job->channel;
@@ -236,18 +275,23 @@ static int channel_submit(struct host1x_job *job)
 	if (sp->base)
 		synchronize_syncpt_base(job);
 
-	syncval = host1x_syncpt_incr_max(sp, user_syncpt_incrs);
-
 	host1x_hw_syncpt_assign_to_channel(host, sp, ch);
 
-	job->syncpt_end = syncval;
-
 	/* add a setclass for modules that require it */
 	if (job->class)
 		host1x_cdma_push(&ch->cdma,
 				 host1x_opcode_setclass(job->class, 0, 0),
 				 HOST1X_OPCODE_NOP);
 
+	/*
+	 * Ensure engine DMA is idle and set new stream ID. May increment
+	 * syncpt max.
+	 */
+	host1x_channel_program_engine_streamid(job);
+
+	syncval = host1x_syncpt_incr_max(sp, user_syncpt_incrs);
+	job->syncpt_end = syncval;
+
 	submit_gathers(job, syncval - user_syncpt_incrs);
 
 	/* end CDMA submit & stash pinned hMems into sync queue */
diff --git a/drivers/gpu/host1x/hw/host1x06_hardware.h b/drivers/gpu/host1x/hw/host1x06_hardware.h
index 01a142a09800..5d515745eee7 100644
--- a/drivers/gpu/host1x/hw/host1x06_hardware.h
+++ b/drivers/gpu/host1x/hw/host1x06_hardware.h
@@ -127,6 +127,16 @@ static inline u32 host1x_opcode_gather_incr(unsigned offset, unsigned count)
 	return (6 << 28) | (offset << 16) | BIT(15) | BIT(14) | count;
 }
 
+static inline u32 host1x_opcode_setstreamid(unsigned streamid)
+{
+	return (7 << 28) | streamid;
+}
+
+static inline u32 host1x_opcode_setpayload(unsigned payload)
+{
+	return (9 << 28) | payload;
+}
+
 static inline u32 host1x_opcode_gather_wide(unsigned count)
 {
 	return (12 << 28) | count;
diff --git a/drivers/gpu/host1x/hw/host1x07_hardware.h b/drivers/gpu/host1x/hw/host1x07_hardware.h
index e6582172ebfd..82c0cc9bb0b5 100644
--- a/drivers/gpu/host1x/hw/host1x07_hardware.h
+++ b/drivers/gpu/host1x/hw/host1x07_hardware.h
@@ -127,6 +127,16 @@ static inline u32 host1x_opcode_gather_incr(unsigned offset, unsigned count)
 	return (6 << 28) | (offset << 16) | BIT(15) | BIT(14) | count;
 }
 
+static inline u32 host1x_opcode_setstreamid(unsigned streamid)
+{
+	return (7 << 28) | streamid;
+}
+
+static inline u32 host1x_opcode_setpayload(unsigned payload)
+{
+	return (9 << 28) | payload;
+}
+
 static inline u32 host1x_opcode_gather_wide(unsigned count)
 {
 	return (12 << 28) | count;