From fa722f0d9820a84952a3cbaccb888c31f9bfca2a Mon Sep 17 00:00:00 2001 From: Jay Cornwall Date: Tue, 2 Apr 2019 11:43:30 -0500 Subject: [PATCH] drm/amdkfd: Preserve ttmp[4:5] instead of ttmp[14:15] ttmp[4:5] is initialized by the SPI with SPI_GDBG_TRAP_DATA* values. These values are more useful to the debugger than ttmp[14:15], which carries dispatch_scratch_base*. There are too few registers to preserve both. Signed-off-by: Jay Cornwall Reviewed-by: Felix Kuehling Signed-off-by: Felix Kuehling Signed-off-by: Alex Deucher --- .../gpu/drm/amd/amdkfd/cwsr_trap_handler.h | 466 +++++++++--------- .../drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm | 45 +- 2 files changed, 253 insertions(+), 258 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h index eed845b4e9a7..e413d4a71fa3 100644 --- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h +++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h @@ -274,12 +274,12 @@ static const uint32_t cwsr_trap_gfx8_hex[] = { static const uint32_t cwsr_trap_gfx9_hex[] = { - 0xbf820001, 0xbf820161, + 0xbf820001, 0xbf82015e, 0xb8f8f802, 0x89788678, - 0xb8f1f803, 0x866eff71, + 0xb8fbf803, 0x866eff7b, 0x00000400, 0xbf85003b, - 0x866eff71, 0x00000800, - 0xbf850003, 0x866eff71, + 0x866eff7b, 0x00000800, + 0xbf850003, 0x866eff7b, 0x00000100, 0xbf84000c, 0x866eff78, 0x00002000, 0xbf840005, 0xbf8e0010, @@ -292,13 +292,13 @@ static const uint32_t cwsr_trap_gfx9_hex[] = { 0x8977ff77, 0xfc000000, 0x87776f77, 0x896eff6e, 0x001f8000, 0xb96ef807, - 0xb8f0f812, 0xb8f1f813, - 0x8ef08870, 0xc0071bb8, + 0xb8faf812, 0xb8fbf813, + 0x8efa887a, 0xc0071bbd, 0x00000000, 0xbf8cc07f, - 0xc0071c38, 0x00000008, + 0xc0071ebd, 0x00000008, 0xbf8cc07f, 0x86ee6e6e, 0xbf840001, 0xbe801d6e, - 0xb8f1f803, 0x8671ff71, + 0xb8fbf803, 0x867bff7b, 0x000001ff, 0xbf850002, 0x806c846c, 0x826d806d, 0x866dff6d, 0x0000ffff, @@ -308,258 +308,256 @@ static const uint32_t cwsr_trap_gfx9_hex[] = { 0x8f6e8378, 0xb96ee0c2, 0xbf800002, 0xb9780002, 0xbe801f6c, 0x866dff6d, - 0x0000ffff, 0xbef00080, - 0xb9700283, 0xb8f02407, - 0x8e709b70, 0x876d706d, - 0xb8f003c7, 0x8e709a70, - 0x876d706d, 0xb8f0f807, - 0x8670ff70, 0x00007fff, - 0xb970f807, 0xbeee007e, + 0x0000ffff, 0xbefa0080, + 0xb97a0283, 0xb8fa2407, + 0x8e7a9b7a, 0x876d7a6d, + 0xb8fa03c7, 0x8e7a9a7a, + 0x876d7a6d, 0xb8faf807, + 0x867aff7a, 0x00007fff, + 0xb97af807, 0xbeee007e, 0xbeef007f, 0xbefe0180, - 0xbf900004, 0x87708478, - 0xb970f802, 0xbf8e0002, - 0xbf88fffe, 0xb8f02a05, + 0xbf900004, 0x877a8478, + 0xb97af802, 0xbf8e0002, + 0xbf88fffe, 0xb8fa2a05, + 0x807a817a, 0x8e7a8a7a, + 0xb8fb1605, 0x807b817b, + 0x8e7b867b, 0x807a7b7a, + 0x807a7e7a, 0x827b807f, + 0x867bff7b, 0x0000ffff, + 0xc04b1c3d, 0x00000050, + 0xbf8cc07f, 0xc04b1d3d, + 0x00000060, 0xbf8cc07f, + 0xc0431e7d, 0x00000074, + 0xbf8cc07f, 0xbef4007e, + 0x8675ff7f, 0x0000ffff, + 0x8775ff75, 0x00040000, + 0xbef60080, 0xbef700ff, + 0x00807fac, 0x867aff7f, + 0x08000000, 0x8f7a837a, + 0x87777a77, 0x867aff7f, + 0x70000000, 0x8f7a817a, + 0x87777a77, 0xbef1007c, + 0xbef00080, 0xb8f02a05, 0x80708170, 0x8e708a70, - 0xb8f11605, 0x80718171, - 0x8e718671, 0x80707170, - 0x80707e70, 0x8271807f, - 0x8671ff71, 0x0000ffff, - 0xc0471cb8, 0x00000040, - 0xbf8cc07f, 0xc04b1d38, - 0x00000048, 0xbf8cc07f, - 0xc0431e78, 0x00000058, - 0xbf8cc07f, 0xc0471eb8, - 0x0000005c, 0xbf8cc07f, - 0xbef4007e, 0x8675ff7f, - 0x0000ffff, 0x8775ff75, - 0x00040000, 0xbef60080, - 0xbef700ff, 0x00807fac, - 0x8670ff7f, 0x08000000, - 0x8f708370, 0x87777077, - 0x8670ff7f, 0x70000000, - 0x8f708170, 0x87777077, - 0xbefb007c, 0xbefa0080, - 0xb8fa2a05, 0x807a817a, - 0x8e7a8a7a, 0xb8f01605, - 0x80708170, 0x8e708670, - 0x807a707a, 0xbef60084, - 0xbef600ff, 0x01000000, - 0xbefe007c, 0xbefc007a, - 0xc0611efa, 0x0000007c, - 0xbf8cc07f, 0x807a847a, - 0xbefc007e, 0xbefe007c, - 0xbefc007a, 0xc0611b3a, + 0xb8fa1605, 0x807a817a, + 0x8e7a867a, 0x80707a70, + 0xbef60084, 0xbef600ff, + 0x01000000, 0xbefe007c, + 0xbefc0070, 0xc0611c7a, 0x0000007c, 0xbf8cc07f, - 0x807a847a, 0xbefc007e, - 0xbefe007c, 0xbefc007a, - 0xc0611b7a, 0x0000007c, - 0xbf8cc07f, 0x807a847a, + 0x80708470, 0xbefc007e, + 0xbefe007c, 0xbefc0070, + 0xc0611b3a, 0x0000007c, + 0xbf8cc07f, 0x80708470, 0xbefc007e, 0xbefe007c, - 0xbefc007a, 0xc0611bba, + 0xbefc0070, 0xc0611b7a, 0x0000007c, 0xbf8cc07f, - 0x807a847a, 0xbefc007e, - 0xbefe007c, 0xbefc007a, - 0xc0611bfa, 0x0000007c, - 0xbf8cc07f, 0x807a847a, + 0x80708470, 0xbefc007e, + 0xbefe007c, 0xbefc0070, + 0xc0611bba, 0x0000007c, + 0xbf8cc07f, 0x80708470, 0xbefc007e, 0xbefe007c, - 0xbefc007a, 0xc0611e3a, + 0xbefc0070, 0xc0611bfa, 0x0000007c, 0xbf8cc07f, - 0x807a847a, 0xbefc007e, - 0xb8f1f803, 0xbefe007c, - 0xbefc007a, 0xc0611c7a, - 0x0000007c, 0xbf8cc07f, - 0x807a847a, 0xbefc007e, - 0xbefe007c, 0xbefc007a, - 0xc0611a3a, 0x0000007c, - 0xbf8cc07f, 0x807a847a, + 0x80708470, 0xbefc007e, + 0xbefe007c, 0xbefc0070, + 0xc0611e3a, 0x0000007c, + 0xbf8cc07f, 0x80708470, + 0xbefc007e, 0xb8fbf803, + 0xbefe007c, 0xbefc0070, + 0xc0611efa, 0x0000007c, + 0xbf8cc07f, 0x80708470, 0xbefc007e, 0xbefe007c, - 0xbefc007a, 0xc0611a7a, - 0x0000007c, 0xbf8cc07f, - 0x807a847a, 0xbefc007e, - 0xb8fbf801, 0xbefe007c, - 0xbefc007a, 0xc0611efa, + 0xbefc0070, 0xc0611a3a, 0x0000007c, 0xbf8cc07f, - 0x807a847a, 0xbefc007e, - 0x8670ff7f, 0x04000000, - 0xbeef0080, 0x876f6f70, - 0xb8fa2a05, 0x807a817a, - 0x8e7a8a7a, 0xb8f11605, - 0x80718171, 0x8e718471, - 0x8e768271, 0xbef600ff, - 0x01000000, 0xbef20174, - 0x80747a74, 0x82758075, - 0xbefc0080, 0xbf800000, - 0xbe802b00, 0xbe822b02, - 0xbe842b04, 0xbe862b06, - 0xbe882b08, 0xbe8a2b0a, - 0xbe8c2b0c, 0xbe8e2b0e, - 0xc06b003a, 0x00000000, - 0xbf8cc07f, 0xc06b013a, - 0x00000010, 0xbf8cc07f, - 0xc06b023a, 0x00000020, - 0xbf8cc07f, 0xc06b033a, - 0x00000030, 0xbf8cc07f, - 0x8074c074, 0x82758075, - 0x807c907c, 0xbf0a717c, - 0xbf85ffe7, 0xbef40172, - 0xbefa0080, 0xbefe00c1, - 0xbeff00c1, 0xbee80080, - 0xbee90080, 0xbef600ff, - 0x01000000, 0xe0724000, - 0x7a1d0000, 0xe0724100, - 0x7a1d0100, 0xe0724200, - 0x7a1d0200, 0xe0724300, - 0x7a1d0300, 0xbefe00c1, - 0xbeff00c1, 0xb8f14306, - 0x8671c171, 0xbf84002c, - 0xbf8a0000, 0x8670ff6f, - 0x04000000, 0xbf840028, - 0x8e718671, 0x8e718271, - 0xbef60071, 0xb8fa2a05, - 0x807a817a, 0x8e7a8a7a, - 0xb8f01605, 0x80708170, - 0x8e708670, 0x807a707a, - 0x807aff7a, 0x00000080, + 0x80708470, 0xbefc007e, + 0xbefe007c, 0xbefc0070, + 0xc0611a7a, 0x0000007c, + 0xbf8cc07f, 0x80708470, + 0xbefc007e, 0xb8f1f801, + 0xbefe007c, 0xbefc0070, + 0xc0611c7a, 0x0000007c, + 0xbf8cc07f, 0x80708470, + 0xbefc007e, 0x867aff7f, + 0x04000000, 0xbeef0080, + 0x876f6f7a, 0xb8f02a05, + 0x80708170, 0x8e708a70, + 0xb8fb1605, 0x807b817b, + 0x8e7b847b, 0x8e76827b, 0xbef600ff, 0x01000000, - 0xbefc0080, 0xd28c0002, - 0x000100c1, 0xd28d0003, - 0x000204c1, 0xd1060002, - 0x00011103, 0x7e0602ff, - 0x00000200, 0xbefc00ff, - 0x00010000, 0xbe800077, - 0x8677ff77, 0xff7fffff, - 0x8777ff77, 0x00058000, - 0xd8ec0000, 0x00000002, - 0xbf8cc07f, 0xe0765000, - 0x7a1d0002, 0x68040702, - 0xd0c9006a, 0x0000e302, - 0xbf87fff7, 0xbef70000, - 0xbefa00ff, 0x00000400, + 0xbef20174, 0x80747074, + 0x82758075, 0xbefc0080, + 0xbf800000, 0xbe802b00, + 0xbe822b02, 0xbe842b04, + 0xbe862b06, 0xbe882b08, + 0xbe8a2b0a, 0xbe8c2b0c, + 0xbe8e2b0e, 0xc06b003a, + 0x00000000, 0xbf8cc07f, + 0xc06b013a, 0x00000010, + 0xbf8cc07f, 0xc06b023a, + 0x00000020, 0xbf8cc07f, + 0xc06b033a, 0x00000030, + 0xbf8cc07f, 0x8074c074, + 0x82758075, 0x807c907c, + 0xbf0a7b7c, 0xbf85ffe7, + 0xbef40172, 0xbef00080, 0xbefe00c1, 0xbeff00c1, - 0xb8f12a05, 0x80718171, - 0x8e718271, 0x8e768871, + 0xbee80080, 0xbee90080, 0xbef600ff, 0x01000000, - 0xbefc0084, 0xbf0a717c, - 0xbf840015, 0xbf11017c, - 0x8071ff71, 0x00001000, - 0x7e000300, 0x7e020301, - 0x7e040302, 0x7e060303, - 0xe0724000, 0x7a1d0000, - 0xe0724100, 0x7a1d0100, - 0xe0724200, 0x7a1d0200, - 0xe0724300, 0x7a1d0300, - 0x807c847c, 0x807aff7a, - 0x00000400, 0xbf0a717c, - 0xbf85ffef, 0xbf9c0000, - 0xbf8200dc, 0xbef4007e, - 0x8675ff7f, 0x0000ffff, - 0x8775ff75, 0x00040000, - 0xbef60080, 0xbef700ff, - 0x00807fac, 0x866eff7f, - 0x08000000, 0x8f6e836e, - 0x87776e77, 0x866eff7f, - 0x70000000, 0x8f6e816e, - 0x87776e77, 0x866eff7f, - 0x04000000, 0xbf84001e, + 0xe0724000, 0x701d0000, + 0xe0724100, 0x701d0100, + 0xe0724200, 0x701d0200, + 0xe0724300, 0x701d0300, 0xbefe00c1, 0xbeff00c1, - 0xb8ef4306, 0x866fc16f, - 0xbf840019, 0x8e6f866f, - 0x8e6f826f, 0xbef6006f, - 0xb8f82a05, 0x80788178, - 0x8e788a78, 0xb8ee1605, - 0x806e816e, 0x8e6e866e, - 0x80786e78, 0x8078ff78, + 0xb8fb4306, 0x867bc17b, + 0xbf84002c, 0xbf8a0000, + 0x867aff6f, 0x04000000, + 0xbf840028, 0x8e7b867b, + 0x8e7b827b, 0xbef6007b, + 0xb8f02a05, 0x80708170, + 0x8e708a70, 0xb8fa1605, + 0x807a817a, 0x8e7a867a, + 0x80707a70, 0x8070ff70, 0x00000080, 0xbef600ff, 0x01000000, 0xbefc0080, - 0xe0510000, 0x781d0000, - 0xe0510100, 0x781d0000, - 0x807cff7c, 0x00000200, - 0x8078ff78, 0x00000200, - 0xbf0a6f7c, 0xbf85fff6, - 0xbef80080, 0xbefe00c1, - 0xbeff00c1, 0xb8ef2a05, - 0x806f816f, 0x8e6f826f, - 0x8e76886f, 0xbef600ff, - 0x01000000, 0xbeee0078, - 0x8078ff78, 0x00000400, - 0xbefc0084, 0xbf11087c, - 0x806fff6f, 0x00008000, - 0xe0524000, 0x781d0000, - 0xe0524100, 0x781d0100, - 0xe0524200, 0x781d0200, - 0xe0524300, 0x781d0300, - 0xbf8c0f70, 0x7e000300, + 0xd28c0002, 0x000100c1, + 0xd28d0003, 0x000204c1, + 0xd1060002, 0x00011103, + 0x7e0602ff, 0x00000200, + 0xbefc00ff, 0x00010000, + 0xbe800077, 0x8677ff77, + 0xff7fffff, 0x8777ff77, + 0x00058000, 0xd8ec0000, + 0x00000002, 0xbf8cc07f, + 0xe0765000, 0x701d0002, + 0x68040702, 0xd0c9006a, + 0x0000f702, 0xbf87fff7, + 0xbef70000, 0xbef000ff, + 0x00000400, 0xbefe00c1, + 0xbeff00c1, 0xb8fb2a05, + 0x807b817b, 0x8e7b827b, + 0x8e76887b, 0xbef600ff, + 0x01000000, 0xbefc0084, + 0xbf0a7b7c, 0xbf840015, + 0xbf11017c, 0x807bff7b, + 0x00001000, 0x7e000300, 0x7e020301, 0x7e040302, - 0x7e060303, 0x807c847c, - 0x8078ff78, 0x00000400, - 0xbf0a6f7c, 0xbf85ffee, - 0xbf9c0000, 0xe0524000, - 0x6e1d0000, 0xe0524100, - 0x6e1d0100, 0xe0524200, - 0x6e1d0200, 0xe0524300, - 0x6e1d0300, 0xb8f82a05, + 0x7e060303, 0xe0724000, + 0x701d0000, 0xe0724100, + 0x701d0100, 0xe0724200, + 0x701d0200, 0xe0724300, + 0x701d0300, 0x807c847c, + 0x8070ff70, 0x00000400, + 0xbf0a7b7c, 0xbf85ffef, + 0xbf9c0000, 0xbf8200da, + 0xbef4007e, 0x8675ff7f, + 0x0000ffff, 0x8775ff75, + 0x00040000, 0xbef60080, + 0xbef700ff, 0x00807fac, + 0x866eff7f, 0x08000000, + 0x8f6e836e, 0x87776e77, + 0x866eff7f, 0x70000000, + 0x8f6e816e, 0x87776e77, + 0x866eff7f, 0x04000000, + 0xbf84001e, 0xbefe00c1, + 0xbeff00c1, 0xb8ef4306, + 0x866fc16f, 0xbf840019, + 0x8e6f866f, 0x8e6f826f, + 0xbef6006f, 0xb8f82a05, 0x80788178, 0x8e788a78, 0xb8ee1605, 0x806e816e, 0x8e6e866e, 0x80786e78, - 0x80f8c078, 0xb8ef1605, - 0x806f816f, 0x8e6f846f, - 0x8e76826f, 0xbef600ff, - 0x01000000, 0xbefc006f, - 0xc031003a, 0x00000078, - 0x80f8c078, 0xbf8cc07f, - 0x80fc907c, 0xbf800000, - 0xbe802d00, 0xbe822d02, - 0xbe842d04, 0xbe862d06, - 0xbe882d08, 0xbe8a2d0a, - 0xbe8c2d0c, 0xbe8e2d0e, - 0xbf06807c, 0xbf84fff0, + 0x8078ff78, 0x00000080, + 0xbef600ff, 0x01000000, + 0xbefc0080, 0xe0510000, + 0x781d0000, 0xe0510100, + 0x781d0000, 0x807cff7c, + 0x00000200, 0x8078ff78, + 0x00000200, 0xbf0a6f7c, + 0xbf85fff6, 0xbef80080, + 0xbefe00c1, 0xbeff00c1, + 0xb8ef2a05, 0x806f816f, + 0x8e6f826f, 0x8e76886f, + 0xbef600ff, 0x01000000, + 0xbeee0078, 0x8078ff78, + 0x00000400, 0xbefc0084, + 0xbf11087c, 0x806fff6f, + 0x00008000, 0xe0524000, + 0x781d0000, 0xe0524100, + 0x781d0100, 0xe0524200, + 0x781d0200, 0xe0524300, + 0x781d0300, 0xbf8c0f70, + 0x7e000300, 0x7e020301, + 0x7e040302, 0x7e060303, + 0x807c847c, 0x8078ff78, + 0x00000400, 0xbf0a6f7c, + 0xbf85ffee, 0xbf9c0000, + 0xe0524000, 0x6e1d0000, + 0xe0524100, 0x6e1d0100, + 0xe0524200, 0x6e1d0200, + 0xe0524300, 0x6e1d0300, 0xb8f82a05, 0x80788178, 0x8e788a78, 0xb8ee1605, 0x806e816e, 0x8e6e866e, - 0x80786e78, 0xbef60084, + 0x80786e78, 0x80f8c078, + 0xb8ef1605, 0x806f816f, + 0x8e6f846f, 0x8e76826f, 0xbef600ff, 0x01000000, - 0xc0211bfa, 0x00000078, - 0x80788478, 0xc0211b3a, + 0xbefc006f, 0xc031003a, + 0x00000078, 0x80f8c078, + 0xbf8cc07f, 0x80fc907c, + 0xbf800000, 0xbe802d00, + 0xbe822d02, 0xbe842d04, + 0xbe862d06, 0xbe882d08, + 0xbe8a2d0a, 0xbe8c2d0c, + 0xbe8e2d0e, 0xbf06807c, + 0xbf84fff0, 0xb8f82a05, + 0x80788178, 0x8e788a78, + 0xb8ee1605, 0x806e816e, + 0x8e6e866e, 0x80786e78, + 0xbef60084, 0xbef600ff, + 0x01000000, 0xc0211bfa, 0x00000078, 0x80788478, - 0xc0211b7a, 0x00000078, - 0x80788478, 0xc0211eba, + 0xc0211b3a, 0x00000078, + 0x80788478, 0xc0211b7a, 0x00000078, 0x80788478, - 0xc0211efa, 0x00000078, - 0x80788478, 0xc0211c3a, + 0xc0211c3a, 0x00000078, + 0x80788478, 0xc0211c7a, 0x00000078, 0x80788478, - 0xc0211c7a, 0x00000078, - 0x80788478, 0xc0211a3a, + 0xc0211eba, 0x00000078, + 0x80788478, 0xc0211efa, 0x00000078, 0x80788478, - 0xc0211a7a, 0x00000078, - 0x80788478, 0xc0211cfa, + 0xc0211a3a, 0x00000078, + 0x80788478, 0xc0211a7a, 0x00000078, 0x80788478, - 0xbf8cc07f, 0xbefc006f, - 0xbefe007a, 0xbeff007b, - 0x866f71ff, 0x000003ff, - 0xb96f4803, 0x866f71ff, - 0xfffff800, 0x8f6f8b6f, - 0xb96fa2c3, 0xb973f801, - 0xb8ee2a05, 0x806e816e, - 0x8e6e8a6e, 0xb8ef1605, - 0x806f816f, 0x8e6f866f, - 0x806e6f6e, 0x806e746e, - 0x826f8075, 0x866fff6f, - 0x0000ffff, 0xc0071cb7, - 0x00000040, 0xc00b1d37, - 0x00000048, 0xc0031e77, - 0x00000058, 0xc0071eb7, - 0x0000005c, 0xbf8cc07f, - 0x866fff6d, 0xf8000000, - 0x8f6f9b6f, 0x8e6f906f, - 0xbeee0080, 0x876e6f6e, - 0x866fff6d, 0x04000000, - 0x8f6f9a6f, 0x8e6f8f6f, - 0x876e6f6e, 0x866fff70, - 0x00800000, 0x8f6f976f, - 0xb96ef807, 0x866dff6d, - 0x0000ffff, 0x86fe7e7e, - 0x86ea6a6a, 0x8f6e8370, - 0xb96ee0c2, 0xbf800002, - 0xb9700002, 0xbf8a0000, - 0x95806f6c, 0xbf810000, + 0xc0211cfa, 0x00000078, + 0x80788478, 0xbf8cc07f, + 0xbefc006f, 0xbefe0070, + 0xbeff0071, 0x866f7bff, + 0x000003ff, 0xb96f4803, + 0x866f7bff, 0xfffff800, + 0x8f6f8b6f, 0xb96fa2c3, + 0xb973f801, 0xb8ee2a05, + 0x806e816e, 0x8e6e8a6e, + 0xb8ef1605, 0x806f816f, + 0x8e6f866f, 0x806e6f6e, + 0x806e746e, 0x826f8075, + 0x866fff6f, 0x0000ffff, + 0xc00b1c37, 0x00000050, + 0xc00b1d37, 0x00000060, + 0xc0031e77, 0x00000074, + 0xbf8cc07f, 0x866fff6d, + 0xf8000000, 0x8f6f9b6f, + 0x8e6f906f, 0xbeee0080, + 0x876e6f6e, 0x866fff6d, + 0x04000000, 0x8f6f9a6f, + 0x8e6f8f6f, 0x876e6f6e, + 0x866fff7a, 0x00800000, + 0x8f6f976f, 0xb96ef807, + 0x866dff6d, 0x0000ffff, + 0x86fe7e7e, 0x86ea6a6a, + 0x8f6e837a, 0xb96ee0c2, + 0xbf800002, 0xb97a0002, + 0xbf8a0000, 0x95806f6c, + 0xbf810000, 0x00000000, }; diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm index e1ac34517642..6bae2e022c6e 100644 --- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm +++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm @@ -162,8 +162,8 @@ var s_save_pc_lo = ttmp0 //{TTMP1, TTMP0} = {3'h0,pc_rewind[3:0], HT[0],tra var s_save_pc_hi = ttmp1 var s_save_exec_lo = ttmp2 var s_save_exec_hi = ttmp3 -var s_save_tmp = ttmp4 -var s_save_trapsts = ttmp5 //not really used until the end of the SAVE routine +var s_save_tmp = ttmp14 +var s_save_trapsts = ttmp15 //not really used until the end of the SAVE routine var s_save_xnack_mask_lo = ttmp6 var s_save_xnack_mask_hi = ttmp7 var s_save_buf_rsrc0 = ttmp8 @@ -171,9 +171,9 @@ var s_save_buf_rsrc1 = ttmp9 var s_save_buf_rsrc2 = ttmp10 var s_save_buf_rsrc3 = ttmp11 var s_save_status = ttmp12 -var s_save_mem_offset = ttmp14 +var s_save_mem_offset = ttmp4 var s_save_alloc_size = s_save_trapsts //conflict -var s_save_m0 = ttmp15 +var s_save_m0 = ttmp5 var s_save_ttmps_lo = s_save_tmp //no conflict var s_save_ttmps_hi = s_save_trapsts //no conflict @@ -207,10 +207,10 @@ var s_restore_mode = ttmp7 var s_restore_pc_lo = ttmp0 var s_restore_pc_hi = ttmp1 -var s_restore_exec_lo = ttmp14 -var s_restore_exec_hi = ttmp15 -var s_restore_status = ttmp4 -var s_restore_trapsts = ttmp5 +var s_restore_exec_lo = ttmp4 +var s_restore_exec_hi = ttmp5 +var s_restore_status = ttmp14 +var s_restore_trapsts = ttmp15 var s_restore_xnack_mask_lo = xnack_mask_lo var s_restore_xnack_mask_hi = xnack_mask_hi var s_restore_buf_rsrc0 = ttmp8 @@ -299,12 +299,12 @@ L_FETCH_2ND_TRAP: // Read second-level TBA/TMA from first-level TMA and jump if available. // ttmp[2:5] and ttmp12 can be used (others hold SPI-initialized debug data) // ttmp12 holds SQ_WAVE_STATUS - s_getreg_b32 ttmp4, hwreg(HW_REG_SQ_SHADER_TMA_LO) - s_getreg_b32 ttmp5, hwreg(HW_REG_SQ_SHADER_TMA_HI) - s_lshl_b64 [ttmp4, ttmp5], [ttmp4, ttmp5], 0x8 - s_load_dwordx2 [ttmp2, ttmp3], [ttmp4, ttmp5], 0x0 glc:1 // second-level TBA + s_getreg_b32 ttmp14, hwreg(HW_REG_SQ_SHADER_TMA_LO) + s_getreg_b32 ttmp15, hwreg(HW_REG_SQ_SHADER_TMA_HI) + s_lshl_b64 [ttmp14, ttmp15], [ttmp14, ttmp15], 0x8 + s_load_dwordx2 [ttmp2, ttmp3], [ttmp14, ttmp15], 0x0 glc:1 // second-level TBA s_waitcnt lgkmcnt(0) - s_load_dwordx2 [ttmp4, ttmp5], [ttmp4, ttmp5], 0x8 glc:1 // second-level TMA + s_load_dwordx2 [ttmp14, ttmp15], [ttmp14, ttmp15], 0x8 glc:1 // second-level TMA s_waitcnt lgkmcnt(0) s_and_b64 [ttmp2, ttmp3], [ttmp2, ttmp3], [ttmp2, ttmp3] s_cbranch_scc0 L_NO_NEXT_TRAP // second-level trap handler not been set @@ -411,7 +411,7 @@ end else end - // Save trap temporaries 6-11, 13-15 initialized by SPI debug dispatch logic + // Save trap temporaries 4-11, 13 initialized by SPI debug dispatch logic // ttmp SR memory offset : size(VGPR)+size(SGPR)+0x40 get_vgpr_size_bytes(s_save_ttmps_lo) get_sgpr_size_bytes(s_save_ttmps_hi) @@ -419,13 +419,11 @@ end s_add_u32 s_save_ttmps_lo, s_save_ttmps_lo, s_save_spi_init_lo s_addc_u32 s_save_ttmps_hi, s_save_spi_init_hi, 0x0 s_and_b32 s_save_ttmps_hi, s_save_ttmps_hi, 0xFFFF - s_store_dwordx2 [ttmp6, ttmp7], [s_save_ttmps_lo, s_save_ttmps_hi], 0x40 glc:1 + s_store_dwordx4 [ttmp4, ttmp5, ttmp6, ttmp7], [s_save_ttmps_lo, s_save_ttmps_hi], 0x50 glc:1 ack_sqc_store_workaround() - s_store_dwordx4 [ttmp8, ttmp9, ttmp10, ttmp11], [s_save_ttmps_lo, s_save_ttmps_hi], 0x48 glc:1 + s_store_dwordx4 [ttmp8, ttmp9, ttmp10, ttmp11], [s_save_ttmps_lo, s_save_ttmps_hi], 0x60 glc:1 ack_sqc_store_workaround() - s_store_dword ttmp13, [s_save_ttmps_lo, s_save_ttmps_hi], 0x58 glc:1 - ack_sqc_store_workaround() - s_store_dwordx2 [ttmp14, ttmp15], [s_save_ttmps_lo, s_save_ttmps_hi], 0x5C glc:1 + s_store_dword ttmp13, [s_save_ttmps_lo, s_save_ttmps_hi], 0x74 glc:1 ack_sqc_store_workaround() /* setup Resource Contants */ @@ -1099,7 +1097,7 @@ end //s_setreg_b32 hwreg(HW_REG_TRAPSTS), s_restore_trapsts //don't overwrite SAVECTX bit as it may be set through external SAVECTX during restore s_setreg_b32 hwreg(HW_REG_MODE), s_restore_mode - // Restore trap temporaries 6-11, 13-15 initialized by SPI debug dispatch logic + // Restore trap temporaries 4-11, 13 initialized by SPI debug dispatch logic // ttmp SR memory offset : size(VGPR)+size(SGPR)+0x40 get_vgpr_size_bytes(s_restore_ttmps_lo) get_sgpr_size_bytes(s_restore_ttmps_hi) @@ -1107,10 +1105,9 @@ end s_add_u32 s_restore_ttmps_lo, s_restore_ttmps_lo, s_restore_buf_rsrc0 s_addc_u32 s_restore_ttmps_hi, s_restore_buf_rsrc1, 0x0 s_and_b32 s_restore_ttmps_hi, s_restore_ttmps_hi, 0xFFFF - s_load_dwordx2 [ttmp6, ttmp7], [s_restore_ttmps_lo, s_restore_ttmps_hi], 0x40 glc:1 - s_load_dwordx4 [ttmp8, ttmp9, ttmp10, ttmp11], [s_restore_ttmps_lo, s_restore_ttmps_hi], 0x48 glc:1 - s_load_dword ttmp13, [s_restore_ttmps_lo, s_restore_ttmps_hi], 0x58 glc:1 - s_load_dwordx2 [ttmp14, ttmp15], [s_restore_ttmps_lo, s_restore_ttmps_hi], 0x5C glc:1 + s_load_dwordx4 [ttmp4, ttmp5, ttmp6, ttmp7], [s_restore_ttmps_lo, s_restore_ttmps_hi], 0x50 glc:1 + s_load_dwordx4 [ttmp8, ttmp9, ttmp10, ttmp11], [s_restore_ttmps_lo, s_restore_ttmps_hi], 0x60 glc:1 + s_load_dword ttmp13, [s_restore_ttmps_lo, s_restore_ttmps_hi], 0x74 glc:1 s_waitcnt lgkmcnt(0) //reuse s_restore_m0 as a temp register -- 2.30.2