Commit 8c92243d authored by Mikko Perttunen's avatar Mikko Perttunen Committed by Thierry Reding

gpu: host1x: Generalize host1x_cdma_push_wide()

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: default avatarMikko Perttunen <mperttunen@nvidia.com>
Signed-off-by: default avatarThierry Reding <treding@nvidia.com>
parent 5b7239c1
...@@ -615,8 +615,8 @@ void host1x_cdma_push_wide(struct host1x_cdma *cdma, u32 op1, u32 op2, ...@@ -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_channel *channel = cdma_to_channel(cdma);
struct host1x *host1x = cdma_to_host1x(cdma); struct host1x *host1x = cdma_to_host1x(cdma);
struct push_buffer *pb = &cdma->push_buffer; struct push_buffer *pb = &cdma->push_buffer;
unsigned int needed = 2, extra = 0, i;
unsigned int space = cdma->slots_free; unsigned int space = cdma->slots_free;
unsigned int needed = 2, extra = 0;
if (host1x_debug_trace_cmdbuf) if (host1x_debug_trace_cmdbuf)
trace_host1x_cdma_push_wide(dev_name(channel->dev), op1, op2, 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, ...@@ -634,20 +634,14 @@ void host1x_cdma_push_wide(struct host1x_cdma *cdma, u32 op1, u32 op2,
cdma->slots_free = space - needed; cdma->slots_free = space - needed;
cdma->slots_used += needed; cdma->slots_used += needed;
/* if (extra > 0) {
* 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 * If there isn't enough space at the tail of the pushbuffer,
* a NOP to avoid having to deal with fractional slots (a slot always * insert a RESTART(0) here to go back to the beginning.
* represents 2 words). The fourth opcode passed to this function will * The code above adjusted the indexes appropriately.
* therefore always be a NOP. */
* host1x_pushbuffer_push(pb, (0x5 << 28), 0xdead0000);
* 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);
host1x_pushbuffer_push(pb, op1, op2); host1x_pushbuffer_push(pb, op1, op2);
host1x_pushbuffer_push(pb, op3, op4); host1x_pushbuffer_push(pb, op3, op4);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment