From 1bfffa106ec25f9dfe384b15323a77f5ed8524a0 Mon Sep 17 00:00:00 2001
From: Mikko Perttunen <mperttunen@nvidia.com>
Date: Fri, 8 Jul 2022 18:18:02 +0300
Subject: gpu: host1x: Generalize host1x_cdma_push_wide()
Git-commit: 8c92243d9e68a93dd282fa2151b67b5c0e31e957
Patch-mainline: v6.0-rc1
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225 jsc#PED-2849

host1x_cdma_push_wide() had the assumptions that the last parameter word
was a NOP opcode, and that NOP opcodes could be used in all situations.

Neither are true with the new job opcode sequence, so adjust the
function to not have these assumptions, and instead place an early
RESTART opcode when necessary to jump back to the beginning of the
pushbuffer.

Signed-off-by: Mikko Perttunen <mperttunen@nvidia.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
 drivers/gpu/host1x/cdma.c | 24 +++++++++---------------
 1 file changed, 9 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/host1x/cdma.c b/drivers/gpu/host1x/cdma.c
index bb1f3c746be4..103fda055394 100644
--- a/drivers/gpu/host1x/cdma.c
+++ b/drivers/gpu/host1x/cdma.c
@@ -615,8 +615,8 @@ void host1x_cdma_push_wide(struct host1x_cdma *cdma, u32 op1, u32 op2,
 	struct host1x_channel *channel = cdma_to_channel(cdma);
 	struct host1x *host1x = cdma_to_host1x(cdma);
 	struct push_buffer *pb = &cdma->push_buffer;
-	unsigned int needed = 2, extra = 0, i;
 	unsigned int space = cdma->slots_free;
+	unsigned int needed = 2, extra = 0;
 
 	if (host1x_debug_trace_cmdbuf)
 		trace_host1x_cdma_push_wide(dev_name(channel->dev), op1, op2,
@@ -634,20 +634,14 @@ void host1x_cdma_push_wide(struct host1x_cdma *cdma, u32 op1, u32 op2,
 	cdma->slots_free = space - needed;
 	cdma->slots_used += needed;
 
-	/*
-	 * Note that we rely on the fact that this is only used to submit wide
-	 * gather opcodes, which consist of 3 words, and they are padded with
-	 * a NOP to avoid having to deal with fractional slots (a slot always
-	 * represents 2 words). The fourth opcode passed to this function will
-	 * therefore always be a NOP.
-	 *
-	 * This works around a slight ambiguity when it comes to opcodes. For
-	 * all current host1x incarnations the NOP opcode uses the exact same
-	 * encoding (0x20000000), so we could hard-code the value here, but a
-	 * new incarnation may change it and break that assumption.
-	 */
-	for (i = 0; i < extra; i++)
-		host1x_pushbuffer_push(pb, op4, op4);
+	if (extra > 0) {
+		/*
+		 * If there isn't enough space at the tail of the pushbuffer,
+		 * insert a RESTART(0) here to go back to the beginning.
+		 * The code above adjusted the indexes appropriately.
+		 */
+		host1x_pushbuffer_push(pb, (0x5 << 28), 0xdead0000);
+	}
 
 	host1x_pushbuffer_push(pb, op1, op2);
 	host1x_pushbuffer_push(pb, op3, op4);
-- 
2.38.1