dev-amdgpu: Support multiple CPs and MMIO AddrRanges

Currently gem5 assumes that there is only one command processor (CP)
which contains the PM4 packet processor. Some GPU devices have multiple
CPs which the driver tests individually during POST if they are used or
not. Therefore, these additional CPs need to be supported.

This commit allows for multiple PM4 packet processors which represent
multiple CPs. Each of these processors will have its own independent
MMIO address range. To more easily support ranges, the MMIO addresses
now use AddrRange to index a PM4 packet processor instead of the
hard-coded constexpr MMIO start and size pairs.

By default only one PM4 packet processor is created, meaning the
functionality of the simulation is unchanged for devices currently
supported in gem5.

Change-Id: I977f4fd3a169ef4a78671a4fb58c8ea0e19bf52c

src/dev/amdgpu/AMDGPU.py

@@ -95,7 +95,7 @@ class AMDGPUDevice(PciDevice):
     # The config script should not create a new cp here but rather assign the
     # same cp that is assigned to the Shader SimObject.
     cp = Param.GPUCommandProcessor(NULL, "Command Processor")
-    pm4_pkt_proc = Param.PM4PacketProcessor("PM4 Packet Processor")
+    pm4_pkt_procs = VectorParam.PM4PacketProcessor("PM4 Packet Processor")
     memory_manager = Param.AMDGPUMemoryManager("GPU Memory Manager")
     memories = VectorParam.AbstractMemory([], "All memories in the device")
     device_ih = Param.AMDGPUInterruptHandler("GPU Interrupt handler")
@@ -118,6 +118,10 @@ class PM4PacketProcessor(DmaVirtDevice):
     cxx_header = "dev/amdgpu/pm4_packet_processor.hh"
     cxx_class = "gem5::PM4PacketProcessor"
 
+    # Default to 0 as the common case is one PM4 packet processor
+    ip_id = Param.Int(0, "Instance ID of this PM4 processor")
+    mmio_range = Param.AddrRange("Range of MMIO addresses")
+
 
 class AMDGPUMemoryManager(ClockedObject):
     type = "AMDGPUMemoryManager"