GSP Shared Memory

From 3dbrew
Revision as of 20:34, 30 January 2013 by Yellows8 (talk | contribs) (→‎Commands)
Jump to navigation Jump to search

This page describes the GX commands which can be written to GSP shared memory. After writing the command data to GSP shared memory, TriggerCmdReqQueue must be used to trigger GSP processing for the command.

Command Buffer Header

Index Byte Description
0 Command Index, must be <=15
1 Must not be value 0
2 Must not be value 1
3 Bit0 must not be set

The command buffer is located at sharedmem + 0x800 + threadindex*0x200.

Command Header

Index Byte Description
0 Command ID
2-1 ?
3 When non-zero GSP module may check flags for the specified cmdID, command handling is aborted when the flags are set.

The command is located at cmdbuf + 0x20 + cmdindex*0x20, the size of each command is 0x20-bytes. The command parameters are located at command+4. Addresses specified in parameters are application vaddrs, these are usually located in either the application GSP heap or VRAM.

Commands

GX Command 0

Index Word Description
0 u8 CommandID is 0x00
1 Source address
2 Destination address
3 Size

This command is normally used to DMA data from the application GSP heap to VRAM.

GX Command 1

Index Word Description
0 u8 CommandID is 0x01
1 Buffer address
2 Buffer size
3 Flag, bit0 is written to GSP module state
6-4 Unused
7 When non-zero, call svcFlushProcessDataCache() with the specified buffer

This command converts the specified address to a physical address, then writes the physical address and size to the GPU registers at 0x1EF018E0.

GX Command 2

Index Word Description
0 u8 CommandID is 0x02

GX Command 3

Index Word Description
0 u8 CommandID is 0x03

GX Command 4

Index Word Description
0 u8 CommandID is 0x04

GX Command 5

Index Word Description
0 u8 CommandID is 0x05
1 Buf0 address
2 Buf0 size
3 Buf1 address
4 Buf1 size
5 Buf2 address
6 Buf2 size

The application buffer addresses specified in the parameters are used with svcFlushProcessDataCache. The input buf0 size must not be zero. When buf1 size is zero, svcFlushProcessDataCache() for buf1 and buf2 are skipped. When buf2 size is zero, svcFlushProcessDataCache() for buf2 is skipped.