freedreno: Document CP_INDIRECT_BUFFER_CHAIN

This will let us use batch chaining instead of growing batches on a5xx
and a6xx.

Reviewed-by: Rob Clark <robdclark@gmail.com>
Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3537>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3537>

diff --git a/src/freedreno/registers/adreno_pm4.xml b/src/freedreno/registers/adreno_pm4.xml
index 48f77f6..78847fb 100644 (file)
--- a/src/freedreno/registers/adreno_pm4.xml
+++ b/src/freedreno/registers/adreno_pm4.xml
@@ -157,6 +157,12 @@ xsi:schemaLocation="http://nouveau.freedesktop.org/ rules-ng.xsd">
        <value name="CP_PREEMPT_ENABLE" value="0x1c"/>
        <value name="CP_PREEMPT_TOKEN" value="0x1e"/>
        <value name="CP_INDIRECT_BUFFER" value="0x3f"/>
+       <doc>
+               Takes the same arguments as CP_INDIRECT_BUFFER, but jumps to
+               another buffer at the same level. Must be at the end of IB, and
+               doesn't work with draw state IB's.
+       </doc>
+       <value name="CP_INDIRECT_BUFFER_CHAIN" value="0x57" variants="A5XX-"/>
        <doc>indirect buffer dispatch.  same as IB, but init is pipelined</doc>
        <value name="CP_INDIRECT_BUFFER_PFD" value="0x37"/>
        <doc>wait for the IDLE state of the engine</doc>