gpu: host1x: Support 40-bit addressing

Tegra186 and later support 40 bits of address space. Additional
registers need to be programmed to store the full 40 bits of push
buffer addresses.

Since command stream gathers can also reside in buffers in a 40-bit
address space, a new variant of the GATHER opcode is also introduced.
It takes two parameters: the first parameter contains the lower 32
bits of the address and the second parameter contains bits 32 to 39.

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

1 files changed, 26 insertions, 4 deletions

diff --git a/drivers/gpu/host1x/hw/channel_hw.c b/drivers/gpu/host1x/hw/channel_hw.c
index 3067af4452cd..27101c04a827 100644
--- a/drivers/gpu/host1x/hw/channel_hw.c
+++ b/drivers/gpu/host1x/hw/channel_hw.c
@@ -61,15 +61,37 @@ static void trace_write_gather(struct host1x_cdma *cdma, struct host1x_bo *bo,
 static void submit_gathers(struct host1x_job *job)
 {
 	struct host1x_cdma *cdma = &job->channel->cdma;
+#if HOST1X_HW < 6
+	struct device *dev = job->channel->dev;
+#endif
 	unsigned int i;
 
 	for (i = 0; i < job->num_gathers; i++) {
 		struct host1x_job_gather *g = &job->gathers[i];
-		u32 op1 = host1x_opcode_gather(g->words);
-		u32 op2 = g->base + g->offset;
+		dma_addr_t addr = g->base + g->offset;
+		u32 op2, op3;
+
+		op2 = lower_32_bits(addr);
+		op3 = upper_32_bits(addr);
+
+		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;
 
-		trace_write_gather(cdma, g->bo, g->offset, op1 & 0xffff);
-		host1x_cdma_push(cdma, op1, op2);
+			host1x_cdma_push_wide(cdma, op1, op2, op3, op4);
+#else
+			dev_err(dev, "invalid gather for push buffer %pad\n",
+				&addr);
+			continue;
+#endif
+		} else {
+			u32 op1 = host1x_opcode_gather(g->words);
+
+			host1x_cdma_push(cdma, op1, op2);
+		}
 	}
 }