[PATCH 4/4] drm/amdkfd: gfx12.1 add no-op prefetch on trap entry

Alex Deucher <[email protected]>
Newsgroups org.freedesktop.lists.amd-gfx
Message-ID <[email protected]>
From: Jay Cornwall <[email protected]>

VMEM instructions may hang after trap exit. Issue a no-op
prefetch to reset wave VMEM state.

v2: squash in preserve SCC on trap entry

Signed-off-by: Jay Cornwall <[email protected]>
Cc: Joseph Greathouse <[email protected]>
Cc: Michael Chen <[email protected]>
Cc: Lancelot Six <[email protected]>
Cc: Vladimir Indic <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
---
 .../gpu/drm/amd/amdkfd/cwsr_trap_handler.h    | 1266 +++++++++--------
 .../amd/amdkfd/cwsr_trap_handler_gfx12.asm    |   35 +-
 2 files changed, 672 insertions(+), 629 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
index b28b57f145579..8cf3527dc1564 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
@@ -3645,9 +3645,9 @@ static const uint32_t cwsr_trap_gfx9_4_3_hex[] = {
 
 static const uint32_t cwsr_trap_gfx12_hex[] = {
 	0xbfa00001, 0xbfa00255,
-	0xb0804009, 0xb8eef81a,
-	0xbf880000, 0xb980081a,
-	0x00000000, 0xb8f8f804,
+	0xb0804009, 0xb8f8f804,
+	0xb8eef81a, 0xbf880000,
+	0xb980081a, 0x00000000,
 	0x9177ff77, 0x0c000000,
 	0x846e9a6e, 0x8c776e77,
 	0x9178ff78, 0x00008c00,
@@ -4601,444 +4601,466 @@ static const uint32_t cwsr_trap_gfx9_5_0_hex[] = {
 };
 
 static const uint32_t cwsr_trap_gfx12_1_0_hex[] = {
-	0xbfa00001, 0xbfa003da,
+	0xbfa00001, 0xbfa003f1,
 	0xb0804009, 0xb8f8f804,
-	0x9178ff78, 0x00008c00,
-	0xb8fbf811, 0xbf0c877b,
-	0xbfa20002, 0x916dff6d,
-	0xf0000000, 0xbf0d857b,
-	0xbfa10006, 0x917bff7b,
-	0x00000480, 0xb98001d1,
-	0x00000000, 0xb9800291,
-	0x00000000, 0x8b6eff78,
-	0x00004000, 0xbfa10008,
-	0x8b6eff7b, 0x00000480,
-	0xbfa20018, 0x8b6ea07b,
-	0xbfa200ea, 0xbf830010,
-	0xb8fbf811, 0xbfa0fffb,
-	0x8b6eff7b, 0x00000bd0,
-	0xbfa20010, 0xb8eef812,
-	0x8b6f8f7b, 0xbfa10002,
-	0x8c6eff6e, 0x00000080,
-	0xb8eff813, 0x8b6e6e6f,
-	0xbfa20008, 0x8b6eff6d,
-	0xf0000000, 0xbfa20005,
-	0x8b6fff6f, 0x00000200,
-	0xbfa20002, 0x8b6ea07b,
-	0xbfa200d4, 0x9177ff77,
-	0x007fc000, 0xb8fa04a1,
-	0x847a967a, 0x8c777a77,
-	0xb8fa0421, 0x847a957a,
-	0x8c777a77, 0xb8fa3021,
-	0x847a8e7a, 0x8c777a77,
-	0xb980f821, 0x00000000,
-	0xbeef007b, 0xbefa4d82,
-	0xbf8a0000, 0x84fa887a,
-	0xbf0d987b, 0xbfa10002,
-	0x8c7bff7b, 0xfe000000,
-	0xf4601bbd, 0xf8000010,
-	0xbf8a0000, 0x846e976e,
-	0x9177ff77, 0x03800000,
-	0x8c776e77, 0x8b6eff6f,
-	0x00000480, 0xbfa1000c,
-	0xbf0d8e78, 0xbfa20002,
-	0xbf0d9877, 0xbfa20002,
+	0xb8faf811, 0xbf0d887a,
+	0xbfa10008, 0xb9800211,
+	0x00000000, 0xbeee0180,
+	0x7e020280, 0xee17406e,
+	0x00040000, 0x00000001,
+	0xbe804a6c, 0xbefa007e,
+	0xbefe0081, 0xd760007b,
+	0x00010101, 0xbeee0180,
+	0x7e020280, 0xee17406e,
+	0x00040000, 0x00000001,
+	0xd7610001, 0x0001007b,
+	0xbefe007a, 0x9178ff78,
+	0x00008c00, 0xb8fbf811,
+	0xbf0c877b, 0xbfa20002,
+	0x916dff6d, 0xf0000000,
+	0xbf0d857b, 0xbfa10006,
+	0x917bff7b, 0x00000480,
 	0xb98001d1, 0x00000000,
-	0xbf0d8e78, 0xbfa20002,
-	0xbf0d9977, 0xbfa20002,
 	0xb9800291, 0x00000000,
-	0xf4603bbd, 0xf8000000,
-	0xbf8a0000, 0xf4603ebd,
-	0xf8000008, 0xbf8a0000,
-	0x8bee6e6e, 0xbfa10001,
-	0xbe80486e, 0x8b6eff6d,
-	0xf0000000, 0xbfa20009,
-	0xb8eef811, 0x8b6eff6e,
-	0x00000080, 0xbfa20007,
-	0x8c78ff78, 0x00004000,
-	0x80ec886c, 0x82ed806d,
-	0xbfa00002, 0x806c846c,
-	0x826d806d, 0x8b6dff6d,
-	0x01ffffff, 0xb8fbf811,
-	0xbf0d847b, 0xbfa20081,
-	0xf4003eb6, 0xf8000000,
-	0xbfc70000, 0xf4003bb6,
-	0xf8000008, 0x8b76ff7a,
-	0x80000000, 0xbfa20027,
-	0x9376ff7a, 0x00060019,
-	0x81f9a376, 0xbf0b8179,
-	0xbfa2006e, 0x81f9ac76,
-	0xbf0b8179, 0xbfa20068,
-	0x81f9b776, 0xbf0b8179,
-	0xbfa20065, 0x8b76ff7a,
-	0x000001ff, 0xbf06ff76,
-	0x000000fe, 0xbfa20063,
-	0xbf06ff76, 0x000000ff,
-	0xbfa2005d, 0xbf06ff76,
-	0x000000fa, 0xbfa2005a,
-	0x81f9ff76, 0x000000e9,
-	0xbf0b8179, 0xbfa20056,
-	0x8b76ff7b, 0xffff0000,
-	0xbf06ff76, 0xbf860000,
-	0xbfa1005a, 0x9376ff7b,
-	0x0002000e, 0x8b79ff7b,
-	0x00003f00, 0x85798679,
-	0x8c767976, 0xb9763b01,
-	0xbfa00052, 0x8b76ff7a,
-	0xfc000000, 0xbf06ff76,
-	0xd4000000, 0xbfa20019,
-	0xbf06ff76, 0xc8000000,
-	0xbfa2002d, 0x8b76ff7a,
-	0xff000000, 0xbf06ff76,
-	0xcf000000, 0xbfa2003f,
-	0x8b79ff7a, 0xffff0000,
-	0xbf06ff79, 0xcc330000,
-	0xbfa2003d, 0xbf06ff79,
-	0xcc880000, 0xbfa2003a,
-	0xbf06ff79, 0xcc350000,
-	0xbfa2003a, 0xbf06ff79,
-	0xcc3a0000, 0xbfa20037,
-	0xbf06ff76, 0xcc000000,
-	0xbfa10034, 0x8b76ff7b,
-	0x000001ff, 0xbf06ff76,
-	0x000000ff, 0xbfa20029,
-	0xbf06ff76, 0x000000fa,
-	0xbfa20026, 0x81f6ff76,
-	0x000000e9, 0xbf0b8176,
-	0xbfa20022, 0x8b76ff7b,
-	0x0003fe00, 0xbf06ff76,
-	0x0001fe00, 0xbfa2001d,
-	0x8b76ff7b, 0x07fc0000,
-	0xbf06ff76, 0x03fc0000,
-	0xbfa20018, 0xbfa00014,
-	0x9376ff7a, 0x00040016,
-	0x81f68176, 0xbf0b8176,
-	0xbfa20012, 0x9376ff7a,
-	0x00050011, 0x81f68176,
-	0xbf0b8176, 0xbfa2000d,
+	0x8b6eff78, 0x00004000,
+	0xbfa10008, 0x8b6eff7b,
+	0x00000480, 0xbfa20018,
+	0x8b6ea07b, 0xbfa200ea,
+	0xbf830010, 0xb8fbf811,
+	0xbfa0fffb, 0x8b6eff7b,
+	0x00000bd0, 0xbfa20010,
+	0xb8eef812, 0x8b6f8f7b,
+	0xbfa10002, 0x8c6eff6e,
+	0x00000080, 0xb8eff813,
+	0x8b6e6e6f, 0xbfa20008,
+	0x8b6eff6d, 0xf0000000,
+	0xbfa20005, 0x8b6fff6f,
+	0x00000200, 0xbfa20002,
+	0x8b6ea07b, 0xbfa200d4,
+	0x9177ff77, 0x007fc000,
+	0xb8fa04a1, 0x847a967a,
+	0x8c777a77, 0xb8fa0421,
+	0x847a957a, 0x8c777a77,
+	0xb8fa3021, 0x847a8e7a,
+	0x8c777a77, 0xb980f821,
+	0x00000000, 0xbeef007b,
+	0xbefa4d82, 0xbf8a0000,
+	0x84fa887a, 0xbf0d987b,
+	0xbfa10002, 0x8c7bff7b,
+	0xfe000000, 0xf4601bbd,
+	0xf8000010, 0xbf8a0000,
+	0x846e976e, 0x9177ff77,
+	0x03800000, 0x8c776e77,
+	0x8b6eff6f, 0x00000480,
+	0xbfa1000c, 0xbf0d8e78,
+	0xbfa20002, 0xbf0d9877,
+	0xbfa20002, 0xb98001d1,
+	0x00000000, 0xbf0d8e78,
+	0xbfa20002, 0xbf0d9977,
+	0xbfa20002, 0xb9800291,
+	0x00000000, 0xf4603bbd,
+	0xf8000000, 0xbf8a0000,
+	0xf4603ebd, 0xf8000008,
+	0xbf8a0000, 0x8bee6e6e,
+	0xbfa10001, 0xbe80486e,
+	0x8b6eff6d, 0xf0000000,
+	0xbfa20009, 0xb8eef811,
+	0x8b6eff6e, 0x00000080,
+	0xbfa20007, 0x8c78ff78,
+	0x00004000, 0x80ec886c,
+	0x82ed806d, 0xbfa00002,
+	0x806c846c, 0x826d806d,
+	0x8b6dff6d, 0x01ffffff,
+	0xb8fbf811, 0xbf0d847b,
+	0xbfa20081, 0xf4003eb6,
+	0xf8000000, 0xbfc70000,
+	0xf4003bb6, 0xf8000008,
+	0x8b76ff7a, 0x80000000,
+	0xbfa20027, 0x9376ff7a,
+	0x00060019, 0x81f9a376,
+	0xbf0b8179, 0xbfa2006e,
+	0x81f9ac76, 0xbf0b8179,
+	0xbfa20068, 0x81f9b776,
+	0xbf0b8179, 0xbfa20065,
 	0x8b76ff7a, 0x000001ff,
+	0xbf06ff76, 0x000000fe,
+	0xbfa20063, 0xbf06ff76,
+	0x000000ff, 0xbfa2005d,
+	0xbf06ff76, 0x000000fa,
+	0xbfa2005a, 0x81f9ff76,
+	0x000000e9, 0xbf0b8179,
+	0xbfa20056, 0x8b76ff7b,
+	0xffff0000, 0xbf06ff76,
+	0xbf860000, 0xbfa1005a,
+	0x9376ff7b, 0x0002000e,
+	0x8b79ff7b, 0x00003f00,
+	0x85798679, 0x8c767976,
+	0xb9763b01, 0xbfa00052,
+	0x8b76ff7a, 0xfc000000,
+	0xbf06ff76, 0xd4000000,
+	0xbfa20019, 0xbf06ff76,
+	0xc8000000, 0xbfa2002d,
+	0x8b76ff7a, 0xff000000,
+	0xbf06ff76, 0xcf000000,
+	0xbfa2003f, 0x8b79ff7a,
+	0xffff0000, 0xbf06ff79,
+	0xcc330000, 0xbfa2003d,
+	0xbf06ff79, 0xcc880000,
+	0xbfa2003a, 0xbf06ff79,
+	0xcc350000, 0xbfa2003a,
+	0xbf06ff79, 0xcc3a0000,
+	0xbfa20037, 0xbf06ff76,
+	0xcc000000, 0xbfa10034,
+	0x8b76ff7b, 0x000001ff,
 	0xbf06ff76, 0x000000ff,
-	0xbfa20008, 0x8b76ff7b,
-	0x000001ff, 0xbf06ff76,
-	0x000000ff, 0xbfa20003,
-	0xbfc70000, 0xbefb006e,
-	0xbfa0ffa7, 0xbfc70000,
-	0xbefb006f, 0xbfa0ffa4,
-	0x80ec886c, 0x82ed806d,
-	0xbfa0fff7, 0xbfc70000,
-	0x857a9677, 0xb97a04a1,
-	0x857a9577, 0xb97a0421,
-	0x857a8e77, 0xb97a3021,
-	0x8bfe7e7e, 0x8bea6a6a,
-	0x85788978, 0xb9783244,
-	0xbe804a6c, 0xb8faf802,
-	0xbf0d987a, 0xbfa10001,
-	0xbfb00000, 0x8b6dff6d,
-	0x01ffffff, 0xbefa0080,
-	0xb97a0151, 0x9177ff77,
-	0x007fc000, 0xb8fa04a1,
-	0x847a967a, 0x8c777a77,
-	0xb8fa0421, 0x847a957a,
-	0x8c777a77, 0xb8fa3021,
-	0x847a8e7a, 0x8c777a77,
-	0xb980f821, 0x00000000,
-	0xbf0d847b, 0xbfa20081,
-	0xf4003eb6, 0xf8000000,
-	0xbfc70000, 0xf4003bb6,
-	0xf8000008, 0x8b76ff7a,
-	0x80000000, 0xbfa20027,
-	0x9376ff7a, 0x00060019,
-	0x81f9a376, 0xbf0b8179,
-	0xbfa2006e, 0x81f9ac76,
-	0xbf0b8179, 0xbfa20068,
-	0x81f9b776, 0xbf0b8179,
-	0xbfa20065, 0x8b76ff7a,
+	0xbfa20029, 0xbf06ff76,
+	0x000000fa, 0xbfa20026,
+	0x81f6ff76, 0x000000e9,
+	0xbf0b8176, 0xbfa20022,
+	0x8b76ff7b, 0x0003fe00,
+	0xbf06ff76, 0x0001fe00,
+	0xbfa2001d, 0x8b76ff7b,
+	0x07fc0000, 0xbf06ff76,
+	0x03fc0000, 0xbfa20018,
+	0xbfa00014, 0x9376ff7a,
+	0x00040016, 0x81f68176,
+	0xbf0b8176, 0xbfa20012,
+	0x9376ff7a, 0x00050011,
+	0x81f68176, 0xbf0b8176,
+	0xbfa2000d, 0x8b76ff7a,
 	0x000001ff, 0xbf06ff76,
-	0x000000fe, 0xbfa20063,
+	0x000000ff, 0xbfa20008,
+	0x8b76ff7b, 0x000001ff,
 	0xbf06ff76, 0x000000ff,
-	0xbfa2005d, 0xbf06ff76,
-	0x000000fa, 0xbfa2005a,
-	0x81f9ff76, 0x000000e9,
-	0xbf0b8179, 0xbfa20056,
-	0x8b76ff7b, 0xffff0000,
-	0xbf06ff76, 0xbf860000,
-	0xbfa1005a, 0x9376ff7b,
-	0x0002000e, 0x8b79ff7b,
-	0x00003f00, 0x85798679,
-	0x8c767976, 0xb9763b01,
-	0xbfa00052, 0x8b76ff7a,
-	0xfc000000, 0xbf06ff76,
-	0xd4000000, 0xbfa20019,
-	0xbf06ff76, 0xc8000000,
-	0xbfa2002d, 0x8b76ff7a,
-	0xff000000, 0xbf06ff76,
-	0xcf000000, 0xbfa2003f,
-	0x8b79ff7a, 0xffff0000,
-	0xbf06ff79, 0xcc330000,
-	0xbfa2003d, 0xbf06ff79,
-	0xcc880000, 0xbfa2003a,
-	0xbf06ff79, 0xcc350000,
-	0xbfa2003a, 0xbf06ff79,
-	0xcc3a0000, 0xbfa20037,
-	0xbf06ff76, 0xcc000000,
-	0xbfa10034, 0x8b76ff7b,
-	0x000001ff, 0xbf06ff76,
-	0x000000ff, 0xbfa20029,
-	0xbf06ff76, 0x000000fa,
-	0xbfa20026, 0x81f6ff76,
-	0x000000e9, 0xbf0b8176,
-	0xbfa20022, 0x8b76ff7b,
-	0x0003fe00, 0xbf06ff76,
-	0x0001fe00, 0xbfa2001d,
-	0x8b76ff7b, 0x07fc0000,
-	0xbf06ff76, 0x03fc0000,
-	0xbfa20018, 0xbfa00014,
-	0x9376ff7a, 0x00040016,
-	0x81f68176, 0xbf0b8176,
-	0xbfa20012, 0x9376ff7a,
-	0x00050011, 0x81f68176,
-	0xbf0b8176, 0xbfa2000d,
+	0xbfa20003, 0xbfc70000,
+	0xbefb006e, 0xbfa0ffa7,
+	0xbfc70000, 0xbefb006f,
+	0xbfa0ffa4, 0x80ec886c,
+	0x82ed806d, 0xbfa0fff7,
+	0xbfc70000, 0x857a9677,
+	0xb97a04a1, 0x857a9577,
+	0xb97a0421, 0x857a8e77,
+	0xb97a3021, 0x8bfe7e7e,
+	0x8bea6a6a, 0x85788978,
+	0xb9783244, 0xbe804a6c,
+	0xb8faf802, 0xbf0d987a,
+	0xbfa10001, 0xbfb00000,
+	0x8b6dff6d, 0x01ffffff,
+	0xbefa0080, 0xb97a0151,
+	0x9177ff77, 0x007fc000,
+	0xb8fa04a1, 0x847a967a,
+	0x8c777a77, 0xb8fa0421,
+	0x847a957a, 0x8c777a77,
+	0xb8fa3021, 0x847a8e7a,
+	0x8c777a77, 0xb980f821,
+	0x00000000, 0xbf0d847b,
+	0xbfa20081, 0xf4003eb6,
+	0xf8000000, 0xbfc70000,
+	0xf4003bb6, 0xf8000008,
+	0x8b76ff7a, 0x80000000,
+	0xbfa20027, 0x9376ff7a,
+	0x00060019, 0x81f9a376,
+	0xbf0b8179, 0xbfa2006e,
+	0x81f9ac76, 0xbf0b8179,
+	0xbfa20068, 0x81f9b776,
+	0xbf0b8179, 0xbfa20065,
 	0x8b76ff7a, 0x000001ff,
+	0xbf06ff76, 0x000000fe,
+	0xbfa20063, 0xbf06ff76,
+	0x000000ff, 0xbfa2005d,
+	0xbf06ff76, 0x000000fa,
+	0xbfa2005a, 0x81f9ff76,
+	0x000000e9, 0xbf0b8179,
+	0xbfa20056, 0x8b76ff7b,
+	0xffff0000, 0xbf06ff76,
+	0xbf860000, 0xbfa1005a,
+	0x9376ff7b, 0x0002000e,
+	0x8b79ff7b, 0x00003f00,
+	0x85798679, 0x8c767976,
+	0xb9763b01, 0xbfa00052,
+	0x8b76ff7a, 0xfc000000,
+	0xbf06ff76, 0xd4000000,
+	0xbfa20019, 0xbf06ff76,
+	0xc8000000, 0xbfa2002d,
+	0x8b76ff7a, 0xff000000,
+	0xbf06ff76, 0xcf000000,
+	0xbfa2003f, 0x8b79ff7a,
+	0xffff0000, 0xbf06ff79,
+	0xcc330000, 0xbfa2003d,
+	0xbf06ff79, 0xcc880000,
+	0xbfa2003a, 0xbf06ff79,
+	0xcc350000, 0xbfa2003a,
+	0xbf06ff79, 0xcc3a0000,
+	0xbfa20037, 0xbf06ff76,
+	0xcc000000, 0xbfa10034,
+	0x8b76ff7b, 0x000001ff,
 	0xbf06ff76, 0x000000ff,
-	0xbfa20008, 0x8b76ff7b,
+	0xbfa20029, 0xbf06ff76,
+	0x000000fa, 0xbfa20026,
+	0x81f6ff76, 0x000000e9,
+	0xbf0b8176, 0xbfa20022,
+	0x8b76ff7b, 0x0003fe00,
+	0xbf06ff76, 0x0001fe00,
+	0xbfa2001d, 0x8b76ff7b,
+	0x07fc0000, 0xbf06ff76,
+	0x03fc0000, 0xbfa20018,
+	0xbfa00014, 0x9376ff7a,
+	0x00040016, 0x81f68176,
+	0xbf0b8176, 0xbfa20012,
+	0x9376ff7a, 0x00050011,
+	0x81f68176, 0xbf0b8176,
+	0xbfa2000d, 0x8b76ff7a,
 	0x000001ff, 0xbf06ff76,
-	0x000000ff, 0xbfa20003,
-	0xbfc70000, 0xbefb006e,
-	0xbfa0ffa7, 0xbfc70000,
-	0xbefb006f, 0xbfa0ffa4,
-	0x80ec886c, 0x82ed806d,
-	0xbfa0fff7, 0xbfc70000,
-	0xbeee007e, 0xbeef007f,
-	0xbefe0180, 0xbefe4d84,
-	0xbf8a0000, 0x8b7aff7f,
-	0x04000000, 0x847a857a,
-	0x8c6d7a6d, 0xb8eff822,
-	0xb980f822, 0x00000000,
-	0xb8fa2b01, 0x847a997a,
-	0x8c6d7a6d, 0xbefa0080,
-	0xb97a2b01, 0xbefa007e,
+	0x000000ff, 0xbfa20008,
+	0x8b76ff7b, 0x000001ff,
+	0xbf06ff76, 0x000000ff,
+	0xbfa20003, 0xbfc70000,
+	0xbefb006e, 0xbfa0ffa7,
+	0xbfc70000, 0xbefb006f,
+	0xbfa0ffa4, 0x80ec886c,
+	0x82ed806d, 0xbfa0fff7,
+	0xbfc70000, 0xbeee007e,
+	0xbeef007f, 0xbefe0180,
+	0xbefe4d84, 0xbf8a0000,
+	0x8b7aff7f, 0x04000000,
+	0x847a857a, 0x8c6d7a6d,
+	0xb8eff822, 0xb980f822,
+	0x00000000, 0xb8fa2b01,
+	0x847a997a, 0x8c6d7a6d,
+	0xbefa0080, 0xb97a2b01,
+	0xbefa007e, 0x8b7bff7f,
+	0x01ffffff, 0xbefe00c1,
+	0xbeff00c1, 0xee0a407a,
+	0x000c0000, 0x00000000,
+	0x7e000280, 0xbefe007a,
+	0xbeff007b, 0xb8fb0742,
+	0x847b997b, 0xb8fa3b05,
+	0x807a817a, 0xbf0d997b,
+	0xbfa20002, 0x847a897a,
+	0xbfa00001, 0x847a8a7a,
 	0x8b7bff7f, 0x01ffffff,
-	0xbefe00c1, 0xbeff00c1,
-	0xee0a407a, 0x000c0000,
-	0x00000000, 0x7e000280,
+	0x807aff7a, 0x000001c0,
+	0x807a7e7a, 0x827b807b,
+	0xd7610000, 0x00010870,
+	0xd7610000, 0x00010a71,
+	0xd7610000, 0x00010c72,
+	0xd7610000, 0x00010e73,
+	0xd7610000, 0x00011074,
+	0xd7610000, 0x00011275,
+	0xd7610000, 0x00011476,
+	0xd7610000, 0x00011677,
+	0xd7610000, 0x00011a79,
+	0xd7610000, 0x00011c7e,
+	0xd7610000, 0x00011e7f,
+	0xbefe00ff, 0x00003fff,
+	0xbeff0080, 0xee0a407a,
+	0x000c0000, 0x00000000,
+	0xd760007a, 0x00011d00,
+	0xd760007b, 0x00011f00,
 	0xbefe007a, 0xbeff007b,
-	0xb8fb0742, 0x847b997b,
-	0xb8fa3b05, 0x807a817a,
-	0xbf0d997b, 0xbfa20002,
-	0x847a897a, 0xbfa00001,
-	0x847a8a7a, 0x8b7bff7f,
-	0x01ffffff, 0x807aff7a,
-	0x000001c0, 0x807a7e7a,
-	0x827b807b, 0xd7610000,
-	0x00010870, 0xd7610000,
-	0x00010a71, 0xd7610000,
-	0x00010c72, 0xd7610000,
-	0x00010e73, 0xd7610000,
-	0x00011074, 0xd7610000,
-	0x00011275, 0xd7610000,
-	0x00011476, 0xd7610000,
-	0x00011677, 0xd7610000,
-	0x00011a79, 0xd7610000,
-	0x00011c7e, 0xd7610000,
-	0x00011e7f, 0xbefe00ff,
-	0x00003fff, 0xbeff0080,
-	0xee0a407a, 0x000c0000,
-	0x00000000, 0xd760007a,
-	0x00011d00, 0xd760007b,
-	0x00011f00, 0xbefe007a,
-	0xbeff007b, 0xbef4007e,
-	0x8b75ff7f, 0x01ffffff,
-	0xbef1007d, 0xb8f30742,
-	0x84739973, 0xbefe00c1,
-	0x857d9973, 0x8b7d817d,
-	0xbf06817d, 0xbfa20002,
-	0xbeff0080, 0xbfa00002,
-	0xbeff00c1, 0xbfa0000a,
-	0xee0a4074, 0x008c0000,
-	0x00008000, 0xee0a4074,
-	0x010c0000, 0x00010000,
-	0xee0a4074, 0x018c0000,
-	0x00018000, 0xbfa00009,
-	0xee0a4074, 0x008c0000,
+	0xbef4007e, 0x8b75ff7f,
+	0x01ffffff, 0xbef1007d,
+	0xb8f30742, 0x84739973,
+	0xbefe00c1, 0x857d9973,
+	0x8b7d817d, 0xbf06817d,
+	0xbfa20002, 0xbeff0080,
+	0xbfa00002, 0xbeff00c1,
+	0xbfa0000a, 0xee0a4074,
+	0x008c0000, 0x00008000,
+	0xee0a4074, 0x010c0000,
 	0x00010000, 0xee0a4074,
-	0x010c0000, 0x00020000,
-	0xee0a4074, 0x018c0000,
-	0x00030000, 0xb8f03b05,
-	0x80708170, 0xbf0d9973,
-	0xbfa20002, 0x84708970,
-	0xbfa00001, 0x84708a70,
-	0x8070ff70, 0x00000200,
-	0x7e000280, 0x7e020280,
-	0x7e040280, 0xbefd0080,
-	0xd7610002, 0x0000fa71,
-	0x807d817d, 0xb8faf802,
-	0xbf0c8b7a, 0xbfa20003,
-	0xbe804fc2, 0xbf94fffe,
-	0xbfa10001, 0xbe804ec4,
-	0xbf94fffc, 0xbefa4c88,
-	0xbfc70000, 0xbf0c807a,
-	0xbfa20006, 0x9371ff7a,
-	0x00070004, 0x937aff7a,
-	0x00070010, 0xbf06717a,
-	0xbfa2fff6, 0xb8faf804,
-	0x8b7aff7a, 0x0001000c,
-	0x9178ff78, 0x0001000c,
-	0x8c787a78, 0xd7610002,
-	0x0000fa6c, 0x807d817d,
-	0x8b7aff6d, 0x01ffffff,
-	0xd7610002, 0x0000fa7a,
-	0x807d817d, 0xd7610002,
-	0x0000fa6e, 0x807d817d,
-	0xbefa0080, 0xd7610002,
+	0x018c0000, 0x00018000,
+	0xbfa00009, 0xee0a4074,
+	0x008c0000, 0x00010000,
+	0xee0a4074, 0x010c0000,
+	0x00020000, 0xee0a4074,
+	0x018c0000, 0x00030000,
+	0xb8f03b05, 0x80708170,
+	0xbf0d9973, 0xbfa20002,
+	0x84708970, 0xbfa00001,
+	0x84708a70, 0x8070ff70,
+	0x00000200, 0x7e000280,
+	0x7e020280, 0x7e040280,
+	0xbefd0080, 0xd7610002,
+	0x0000fa71, 0x807d817d,
+	0xb8faf802, 0xbf0c8b7a,
+	0xbfa20003, 0xbe804fc2,
+	0xbf94fffe, 0xbfa10001,
+	0xbe804ec4, 0xbf94fffc,
+	0xbefa4c88, 0xbfc70000,
+	0xbf0c807a, 0xbfa20006,
+	0x9371ff7a, 0x00070004,
+	0x937aff7a, 0x00070010,
+	0xbf06717a, 0xbfa2fff6,
+	0xb8faf804, 0x8b7aff7a,
+	0x0001000c, 0x9178ff78,
+	0x0001000c, 0x8c787a78,
+	0xd7610002, 0x0000fa6c,
+	0x807d817d, 0x8b7aff6d,
+	0x01ffffff, 0xd7610002,
 	0x0000fa7a, 0x807d817d,
-	0xd7610002, 0x0000fa78,
-	0x807d817d, 0xb8faf811,
+	0xd7610002, 0x0000fa6e,
+	0x807d817d, 0xbefa0080,
 	0xd7610002, 0x0000fa7a,
 	0x807d817d, 0xd7610002,
-	0x0000fa6f, 0x807d817d,
-	0xb8f1f801, 0x937aff6d,
-	0x00060019, 0x847a8c7a,
-	0x8c717a71, 0xd7610002,
-	0x0000fa71, 0x807d817d,
-	0xb8f1f814, 0xd7610002,
-	0x0000fa71, 0x807d817d,
-	0xb8f1f815, 0xd7610002,
-	0x0000fa71, 0x807d817d,
-	0xb8f1f812, 0xd7610002,
-	0x0000fa71, 0x807d817d,
-	0xb8f1f813, 0xd7610002,
-	0x0000fa71, 0x807d817d,
-	0xb8faf802, 0xd7610002,
+	0x0000fa78, 0x807d817d,
+	0xb8faf811, 0xd7610002,
 	0x0000fa7a, 0x807d817d,
-	0xbefa50c1, 0xbfc70000,
+	0xd7610002, 0x0000fa6f,
+	0x807d817d, 0xb8f1f801,
+	0x937aff6d, 0x00060019,
+	0x847a8c7a, 0x8c717a71,
+	0xd7610002, 0x0000fa71,
+	0x807d817d, 0xb8f1f814,
+	0xd7610002, 0x0000fa71,
+	0x807d817d, 0xb8f1f815,
+	0xd7610002, 0x0000fa71,
+	0x807d817d, 0xb8f1f812,
+	0xd7610002, 0x0000fa71,
+	0x807d817d, 0xb8f1f813,
+	0xd7610002, 0x0000fa71,
+	0x807d817d, 0xb8faf802,
 	0xd7610002, 0x0000fa7a,
-	0x807d817d, 0xbefa4c88,
+	0x807d817d, 0xbefa50c1,
 	0xbfc70000, 0xd7610002,
 	0x0000fa7a, 0x807d817d,
-	0xb8faf81a, 0xd7610002,
-	0x0000fa7a, 0x807d817d,
-	0xbefe00c1, 0xbeff0080,
-	0x80767074, 0x82778075,
+	0xbefa4c88, 0xbfc70000,
+	0xd7610002, 0x0000fa7a,
+	0x807d817d, 0xb8faf81a,
+	0xd7610002, 0x0000fa7a,
+	0x807d817d, 0xbefe00c1,
+	0xbeff0080, 0x80767074,
+	0x82778075, 0xee0a4076,
+	0x010c0000, 0x00000000,
+	0xbefe00c1, 0x7e040280,
+	0xbefa5081, 0xbfc70000,
+	0xd7610002, 0x0001007a,
+	0xbefa5082, 0xbfc70000,
+	0xd7610002, 0x0001027a,
+	0xbefa5083, 0xbfc70000,
+	0xd7610002, 0x0001047a,
+	0xbefa5084, 0xbfc70000,
+	0xd7610002, 0x0001067a,
+	0xbefa5085, 0xbfc70000,
+	0xd7610002, 0x0001087a,
+	0xbefa5086, 0xbfc70000,
+	0xd7610002, 0x00010a7a,
+	0xbefa5087, 0xbfc70000,
+	0xd7610002, 0x00010c7a,
+	0xbefa5088, 0xbfc70000,
+	0xd7610002, 0x00010e7a,
+	0xbefa5089, 0xbfc70000,
+	0xd7610002, 0x0001107a,
+	0xbefa508a, 0xbfc70000,
+	0xd7610002, 0x0001127a,
+	0xbefa508b, 0xbfc70000,
+	0xd7610002, 0x0001147a,
+	0xbefa508c, 0xbfc70000,
+	0xd7610002, 0x0001167a,
+	0xbefa508d, 0xbfc70000,
+	0xd7610002, 0x0001187a,
+	0xbefa508e, 0xbfc70000,
+	0xd7610002, 0x00011a7a,
+	0xbefa508f, 0xbfc70000,
+	0xd7610002, 0x00011c7a,
+	0xbefa5090, 0xbfc70000,
+	0xd7610002, 0x00011e7a,
 	0xee0a4076, 0x010c0000,
-	0x00000000, 0xbefe00c1,
-	0x7e040280, 0xbefa5081,
-	0xbfc70000, 0xd7610002,
-	0x0001007a, 0xbefa5082,
-	0xbfc70000, 0xd7610002,
-	0x0001027a, 0xbefa5083,
-	0xbfc70000, 0xd7610002,
-	0x0001047a, 0xbefa5084,
-	0xbfc70000, 0xd7610002,
-	0x0001067a, 0xbefa5085,
-	0xbfc70000, 0xd7610002,
-	0x0001087a, 0xbefa5086,
-	0xbfc70000, 0xd7610002,
-	0x00010a7a, 0xbefa5087,
-	0xbfc70000, 0xd7610002,
-	0x00010c7a, 0xbefa5088,
-	0xbfc70000, 0xd7610002,
-	0x00010e7a, 0xbefa5089,
-	0xbfc70000, 0xd7610002,
-	0x0001107a, 0xbefa508a,
-	0xbfc70000, 0xd7610002,
-	0x0001127a, 0xbefa508b,
-	0xbfc70000, 0xd7610002,
-	0x0001147a, 0xbefa508c,
-	0xbfc70000, 0xd7610002,
-	0x0001167a, 0xbefa508d,
-	0xbfc70000, 0xd7610002,
-	0x0001187a, 0xbefa508e,
-	0xbfc70000, 0xd7610002,
-	0x00011a7a, 0xbefa508f,
-	0xbfc70000, 0xd7610002,
-	0x00011c7a, 0xbefa5090,
-	0xbfc70000, 0xd7610002,
-	0x00011e7a, 0xee0a4076,
-	0x010c0000, 0x00008000,
-	0xb8f03b05, 0x80708170,
-	0xbf0d9973, 0xbfa20002,
-	0x84708970, 0xbfa00001,
-	0x84708a70, 0xbef90080,
-	0xbefd0080, 0xbf800000,
-	0xbe804100, 0xbe824102,
-	0xbe844104, 0xbe864106,
-	0xbe884108, 0xbe8a410a,
-	0xbe8c410c, 0xbe8e410e,
-	0xd7610002, 0x0000f200,
-	0x80798179, 0xd7610002,
-	0x0000f201, 0x80798179,
-	0xd7610002, 0x0000f202,
+	0x00008000, 0xb8f03b05,
+	0x80708170, 0xbf0d9973,
+	0xbfa20002, 0x84708970,
+	0xbfa00001, 0x84708a70,
+	0xbef90080, 0xbefd0080,
+	0xbf800000, 0xbe804100,
+	0xbe824102, 0xbe844104,
+	0xbe864106, 0xbe884108,
+	0xbe8a410a, 0xbe8c410c,
+	0xbe8e410e, 0xd7610002,
+	0x0000f200, 0x80798179,
+	0xd7610002, 0x0000f201,
 	0x80798179, 0xd7610002,
-	0x0000f203, 0x80798179,
-	0xd7610002, 0x0000f204,
+	0x0000f202, 0x80798179,
+	0xd7610002, 0x0000f203,
 	0x80798179, 0xd7610002,
-	0x0000f205, 0x80798179,
-	0xd7610002, 0x0000f206,
+	0x0000f204, 0x80798179,
+	0xd7610002, 0x0000f205,
 	0x80798179, 0xd7610002,
-	0x0000f207, 0x80798179,
-	0xd7610002, 0x0000f208,
+	0x0000f206, 0x80798179,
+	0xd7610002, 0x0000f207,
 	0x80798179, 0xd7610002,
-	0x0000f209, 0x80798179,
-	0xd7610002, 0x0000f20a,
+	0x0000f208, 0x80798179,
+	0xd7610002, 0x0000f209,
 	0x80798179, 0xd7610002,
-	0x0000f20b, 0x80798179,
-	0xd7610002, 0x0000f20c,
+	0x0000f20a, 0x80798179,
+	0xd7610002, 0x0000f20b,
 	0x80798179, 0xd7610002,
-	0x0000f20d, 0x80798179,
-	0xd7610002, 0x0000f20e,
+	0x0000f20c, 0x80798179,
+	0xd7610002, 0x0000f20d,
 	0x80798179, 0xd7610002,
-	0x0000f20f, 0x80798179,
-	0xbf06a079, 0xbfa10009,
-	0x80767074, 0x82778075,
-	0xee0a4076, 0x010c0000,
-	0x00000000, 0x8070ff70,
-	0x00000080, 0xbef90080,
-	0x7e040280, 0x807d907d,
-	0xbf0aff7d, 0x00000060,
-	0xbfa2ffb9, 0xbe804100,
-	0xbe824102, 0xbe844104,
-	0xbe864106, 0xbe884108,
-	0xbe8a410a, 0xd7610002,
-	0x0000f200, 0x80798179,
-	0xd7610002, 0x0000f201,
+	0x0000f20e, 0x80798179,
+	0xd7610002, 0x0000f20f,
+	0x80798179, 0xbf06a079,
+	0xbfa10009, 0x80767074,
+	0x82778075, 0xee0a4076,
+	0x010c0000, 0x00000000,
+	0x8070ff70, 0x00000080,
+	0xbef90080, 0x7e040280,
+	0x807d907d, 0xbf0aff7d,
+	0x00000060, 0xbfa2ffb9,
+	0xbe804100, 0xbe824102,
+	0xbe844104, 0xbe864106,
+	0xbe884108, 0xbe8a410a,
+	0xd7610002, 0x0000f200,
 	0x80798179, 0xd7610002,
-	0x0000f202, 0x80798179,
-	0xd7610002, 0x0000f203,
+	0x0000f201, 0x80798179,
+	0xd7610002, 0x0000f202,
 	0x80798179, 0xd7610002,
-	0x0000f204, 0x80798179,
-	0xd7610002, 0x0000f205,
+	0x0000f203, 0x80798179,
+	0xd7610002, 0x0000f204,
 	0x80798179, 0xd7610002,
-	0x0000f206, 0x80798179,
-	0xd7610002, 0x0000f207,
+	0x0000f205, 0x80798179,
+	0xd7610002, 0x0000f206,
 	0x80798179, 0xd7610002,
-	0x0000f208, 0x80798179,
-	0xd7610002, 0x0000f209,
+	0x0000f207, 0x80798179,
+	0xd7610002, 0x0000f208,
 	0x80798179, 0xd7610002,
-	0x0000f20a, 0x80798179,
-	0xd7610002, 0x0000f20b,
-	0x80798179, 0xbefe00ff,
-	0x0000ffff, 0x80767074,
+	0x0000f209, 0x80798179,
+	0xd7610002, 0x0000f20a,
+	0x80798179, 0xd7610002,
+	0x0000f20b, 0x80798179,
+	0xbefe00ff, 0x0000ffff,
+	0x80767074, 0x82778075,
+	0xee0a4076, 0x010c0000,
+	0x00000000, 0xbefe00c1,
+	0x857d9973, 0x8b7d817d,
+	0xbf06817d, 0xbfa20002,
+	0xbeff0080, 0xbfa00001,
+	0xbeff00c1, 0xb8fb4306,
+	0x8b7bc17b, 0xbfa10042,
+	0x8b7aff6d, 0x80000000,
+	0xbfa1003f, 0x847b8a7b,
+	0xb8f03b05, 0x80708170,
+	0xbf0d9973, 0xbfa20002,
+	0x84708970, 0xbfa00001,
+	0x84708a70, 0x8070ff70,
+	0x00000200, 0x8070ff70,
+	0x00000200, 0xd71f0000,
+	0x000100c1, 0xd7200000,
+	0x000200c1, 0x16000084,
+	0x857d9973, 0x8b7d817d,
+	0xbf06817d, 0xbefd0080,
+	0xbfa20015, 0xbe8300ff,
+	0x00000080, 0xbf800000,
+	0xbf800000, 0xbf800000,
+	0xd8d80000, 0x01000000,
+	0xbf8a0000, 0x80767074,
 	0x82778075, 0xee0a4076,
-	0x010c0000, 0x00000000,
-	0xbefe00c1, 0x857d9973,
-	0x8b7d817d, 0xbf06817d,
-	0xbfa20002, 0xbeff0080,
-	0xbfa00001, 0xbeff00c1,
-	0xb8fb4306, 0x8b7bc17b,
-	0xbfa10042, 0x8b7aff6d,
-	0x80000000, 0xbfa1003f,
-	0x847b8a7b, 0xb8f03b05,
-	0x80708170, 0xbf0d9973,
-	0xbfa20002, 0x84708970,
-	0xbfa00001, 0x84708a70,
-	0x8070ff70, 0x00000200,
-	0x8070ff70, 0x00000200,
-	0xd71f0000, 0x000100c1,
-	0xd7200000, 0x000200c1,
-	0x16000084, 0x857d9973,
-	0x8b7d817d, 0xbf06817d,
-	0xbefd0080, 0xbfa20015,
-	0xbe8300ff, 0x00000080,
+	0x008c0000, 0x00000000,
+	0x807d037d, 0x80700370,
+	0xd5250000, 0x0001ff00,
+	0x00000080, 0xbf0a7b7d,
+	0xbfa2fff1, 0xbfa00014,
+	0xbe8300ff, 0x00000100,
 	0xbf800000, 0xbf800000,
 	0xbf800000, 0xd8d80000,
 	0x01000000, 0xbf8a0000,
@@ -5046,254 +5068,244 @@ static const uint32_t cwsr_trap_gfx12_1_0_hex[] = {
 	0xee0a4076, 0x008c0000,
 	0x00000000, 0x807d037d,
 	0x80700370, 0xd5250000,
-	0x0001ff00, 0x00000080,
+	0x0001ff00, 0x00000100,
 	0xbf0a7b7d, 0xbfa2fff1,
-	0xbfa00014, 0xbe8300ff,
-	0x00000100, 0xbf800000,
-	0xbf800000, 0xbf800000,
-	0xd8d80000, 0x01000000,
-	0xbf8a0000, 0x80767074,
-	0x82778075, 0xee0a4076,
-	0x008c0000, 0x00000000,
-	0x807d037d, 0x80700370,
-	0xd5250000, 0x0001ff00,
-	0x00000100, 0xbf0a7b7d,
-	0xbfa2fff1, 0xbefe00c1,
-	0x857d9973, 0x8b7d817d,
-	0xbf06817d, 0xbfa20004,
-	0xbef000ff, 0x00000200,
-	0xbeff0080, 0xbfa00003,
-	0xbef000ff, 0x00000400,
-	0xbeff00c1, 0xb8fb3b05,
-	0x807b817b, 0x847b827b,
-	0x857d9973, 0x8b7d817d,
-	0xbf06817d, 0xbfa2001b,
+	0xbefe00c1, 0x857d9973,
+	0x8b7d817d, 0xbf06817d,
+	0xbfa20004, 0xbef000ff,
+	0x00000200, 0xbeff0080,
+	0xbfa00003, 0xbef000ff,
+	0x00000400, 0xbeff00c1,
+	0xb8fb3b05, 0x807b817b,
+	0x847b827b, 0x857d9973,
+	0x8b7d817d, 0xbf06817d,
+	0xbfa2001b, 0xbefd0084,
+	0xbf0a7b7d, 0xbfa10032,
+	0x7e008700, 0x7e028701,
+	0x7e048702, 0x7e068703,
+	0x80767074, 0x82778075,
+	0xee0a4076, 0x000c0000,
+	0x00000000, 0xee0a4076,
+	0x008c0000, 0x00008000,
+	0xee0a4076, 0x010c0000,
+	0x00010000, 0xee0a4076,
+	0x018c0000, 0x00018000,
+	0x807d847d, 0x8070ff70,
+	0x00000200, 0xbf0a7b7d,
+	0xbfa2ffe9, 0xbfa0001a,
 	0xbefd0084, 0xbf0a7b7d,
-	0xbfa10032, 0x7e008700,
+	0xbfa10017, 0x7e008700,
 	0x7e028701, 0x7e048702,
 	0x7e068703, 0x80767074,
 	0x82778075, 0xee0a4076,
 	0x000c0000, 0x00000000,
 	0xee0a4076, 0x008c0000,
-	0x00008000, 0xee0a4076,
-	0x010c0000, 0x00010000,
+	0x00010000, 0xee0a4076,
+	0x010c0000, 0x00020000,
 	0xee0a4076, 0x018c0000,
-	0x00018000, 0x807d847d,
-	0x8070ff70, 0x00000200,
+	0x00030000, 0x807d847d,
+	0x8070ff70, 0x00000400,
 	0xbf0a7b7d, 0xbfa2ffe9,
-	0xbfa0001a, 0xbefd0084,
-	0xbf0a7b7d, 0xbfa10017,
-	0x7e008700, 0x7e028701,
-	0x7e048702, 0x7e068703,
-	0x80767074, 0x82778075,
-	0xee0a4076, 0x000c0000,
-	0x00000000, 0xee0a4076,
-	0x008c0000, 0x00010000,
-	0xee0a4076, 0x010c0000,
-	0x00020000, 0xee0a4076,
-	0x018c0000, 0x00030000,
-	0x807d847d, 0x8070ff70,
-	0x00000400, 0xbf0a7b7d,
-	0xbfa2ffe9, 0xbfa00184,
-	0xbef4007e, 0x8b75ff7f,
-	0x01ffffff, 0xbef1007f,
-	0xb8f20742, 0x84729972,
-	0x8b6eff7f, 0x04000000,
-	0xbfa10044, 0xbefe00c1,
-	0x857d9972, 0x8b7d817d,
-	0xbf06817d, 0xbfa20002,
-	0xbeff0080, 0xbfa00001,
-	0xbeff00c1, 0xb8ef4306,
-	0x8b6fc16f, 0xbfa10039,
-	0x846f8a6f, 0xb8f83b05,
-	0x80788178, 0xbf0d9972,
-	0xbfa20002, 0x84788978,
-	0xbfa00001, 0x84788a78,
-	0x8078ff78, 0x00000200,
-	0x8078ff78, 0x00000200,
-	0x857d9972, 0x8b7d817d,
-	0xbf06817d, 0xbefd0080,
-	0xd71f0001, 0x000100c1,
-	0xd7200001, 0x000202c1,
-	0x30020282, 0xbfa20012,
-	0x80767874, 0x82778075,
-	0xee0a0076, 0x000c0000,
-	0x00000000, 0xbf8a0000,
-	0xd8340000, 0x00000001,
-	0xd5250001, 0x0001ff01,
-	0x00000080, 0x807dff7d,
-	0x00000080, 0x8078ff78,
-	0x00000080, 0xbf0a6f7d,
-	0xbfa2ffef, 0xbfa00011,
-	0x80767874, 0x82778075,
-	0xee0a0076, 0x000c0000,
-	0x00000000, 0xbf8a0000,
-	0xd8340000, 0x00000001,
-	0xd5250001, 0x0001ff01,
-	0x00000100, 0x807dff7d,
-	0x00000100, 0x8078ff78,
-	0x00000100, 0xbf0a6f7d,
-	0xbfa2ffef, 0xbef80080,
+	0xbfa00184, 0xbef4007e,
+	0x8b75ff7f, 0x01ffffff,
+	0xbef1007f, 0xb8f20742,
+	0x84729972, 0x8b6eff7f,
+	0x04000000, 0xbfa10044,
 	0xbefe00c1, 0x857d9972,
 	0x8b7d817d, 0xbf06817d,
 	0xbfa20002, 0xbeff0080,
 	0xbfa00001, 0xbeff00c1,
-	0xb8ef3b05, 0x806f816f,
-	0x846f826f, 0x857d9972,
+	0xb8ef4306, 0x8b6fc16f,
+	0xbfa10039, 0x846f8a6f,
+	0xb8f83b05, 0x80788178,
+	0xbf0d9972, 0xbfa20002,
+	0x84788978, 0xbfa00001,
+	0x84788a78, 0x8078ff78,
+	0x00000200, 0x8078ff78,
+	0x00000200, 0x857d9972,
 	0x8b7d817d, 0xbf06817d,
-	0xbfa2002c, 0xbeee0078,
-	0x8078ff78, 0x00000200,
-	0xbefd0084, 0x80767874,
-	0x82778075, 0xee0a0076,
-	0x000c0000, 0x00000000,
-	0xee0a0076, 0x000c0001,
-	0x00008000, 0xee0a0076,
-	0x000c0002, 0x00010000,
-	0xee0a0076, 0x000c0003,
-	0x00018000, 0xbf8a0000,
-	0x7e008500, 0x7e028501,
-	0x7e048502, 0x7e068503,
-	0x807d847d, 0x8078ff78,
-	0x00000200, 0xbf0a6f7d,
-	0xbfa2ffe8, 0x80766e74,
+	0xbefd0080, 0xd71f0001,
+	0x000100c1, 0xd7200001,
+	0x000202c1, 0x30020282,
+	0xbfa20012, 0x80767874,
 	0x82778075, 0xee0a0076,
 	0x000c0000, 0x00000000,
-	0xee0a0076, 0x000c0001,
-	0x00008000, 0xee0a0076,
-	0x000c0002, 0x00010000,
-	0xee0a0076, 0x000c0003,
-	0x00018000, 0xbf8a0000,
-	0xbfa0002d, 0xbeee0078,
-	0x8078ff78, 0x00000400,
-	0xbefd0084, 0xbf0a6f7d,
-	0xbfa10018, 0x80767874,
+	0xbf8a0000, 0xd8340000,
+	0x00000001, 0xd5250001,
+	0x0001ff01, 0x00000080,
+	0x807dff7d, 0x00000080,
+	0x8078ff78, 0x00000080,
+	0xbf0a6f7d, 0xbfa2ffef,
+	0xbfa00011, 0x80767874,
 	0x82778075, 0xee0a0076,
 	0x000c0000, 0x00000000,
-	0xee0a0076, 0x000c0001,
+	0xbf8a0000, 0xd8340000,
+	0x00000001, 0xd5250001,
+	0x0001ff01, 0x00000100,
+	0x807dff7d, 0x00000100,
+	0x8078ff78, 0x00000100,
+	0xbf0a6f7d, 0xbfa2ffef,
+	0xbef80080, 0xbefe00c1,
+	0x857d9972, 0x8b7d817d,
+	0xbf06817d, 0xbfa20002,
+	0xbeff0080, 0xbfa00001,
+	0xbeff00c1, 0xb8ef3b05,
+	0x806f816f, 0x846f826f,
+	0x857d9972, 0x8b7d817d,
+	0xbf06817d, 0xbfa2002c,
+	0xbeee0078, 0x8078ff78,
+	0x00000200, 0xbefd0084,
+	0x80767874, 0x82778075,
+	0xee0a0076, 0x000c0000,
+	0x00000000, 0xee0a0076,
+	0x000c0001, 0x00008000,
+	0xee0a0076, 0x000c0002,
 	0x00010000, 0xee0a0076,
-	0x000c0002, 0x00020000,
-	0xee0a0076, 0x000c0003,
-	0x00030000, 0xbf8a0000,
-	0x7e008500, 0x7e028501,
-	0x7e048502, 0x7e068503,
-	0x807d847d, 0x8078ff78,
-	0x00000400, 0xbf0a6f7d,
-	0xbfa2ffe8, 0x80766e74,
-	0x82778075, 0xee0a0076,
-	0x000c0000, 0x00000000,
-	0xee0a0076, 0x000c0001,
+	0x000c0003, 0x00018000,
+	0xbf8a0000, 0x7e008500,
+	0x7e028501, 0x7e048502,
+	0x7e068503, 0x807d847d,
+	0x8078ff78, 0x00000200,
+	0xbf0a6f7d, 0xbfa2ffe8,
+	0x80766e74, 0x82778075,
+	0xee0a0076, 0x000c0000,
+	0x00000000, 0xee0a0076,
+	0x000c0001, 0x00008000,
+	0xee0a0076, 0x000c0002,
 	0x00010000, 0xee0a0076,
-	0x000c0002, 0x00020000,
-	0xee0a0076, 0x000c0003,
-	0x00030000, 0xbf8a0000,
-	0xb8f83b05, 0x80788178,
-	0xbf0d9972, 0xbfa20002,
-	0x84788978, 0xbfa00001,
-	0x84788a78, 0x8078ff78,
-	0x00000200, 0x80f8ff78,
-	0x00000060, 0x80767874,
-	0x82778075, 0xbefd00ff,
-	0x0000006c, 0xf460403b,
-	0xf8000000, 0xbf8a0000,
-	0x80fd847d, 0xbf800000,
-	0xbe804300, 0xbe824302,
-	0x80f6a076, 0x82f78077,
-	0xf460603b, 0xf8000000,
-	0xbf8a0000, 0x80fd887d,
+	0x000c0003, 0x00018000,
+	0xbf8a0000, 0xbfa0002d,
+	0xbeee0078, 0x8078ff78,
+	0x00000400, 0xbefd0084,
+	0xbf0a6f7d, 0xbfa10018,
+	0x80767874, 0x82778075,
+	0xee0a0076, 0x000c0000,
+	0x00000000, 0xee0a0076,
+	0x000c0001, 0x00010000,
+	0xee0a0076, 0x000c0002,
+	0x00020000, 0xee0a0076,
+	0x000c0003, 0x00030000,
+	0xbf8a0000, 0x7e008500,
+	0x7e028501, 0x7e048502,
+	0x7e068503, 0x807d847d,
+	0x8078ff78, 0x00000400,
+	0xbf0a6f7d, 0xbfa2ffe8,
+	0x80766e74, 0x82778075,
+	0xee0a0076, 0x000c0000,
+	0x00000000, 0xee0a0076,
+	0x000c0001, 0x00010000,
+	0xee0a0076, 0x000c0002,
+	0x00020000, 0xee0a0076,
+	0x000c0003, 0x00030000,
+	0xbf8a0000, 0xb8f83b05,
+	0x80788178, 0xbf0d9972,
+	0xbfa20002, 0x84788978,
+	0xbfa00001, 0x84788a78,
+	0x8078ff78, 0x00000200,
+	0x80f8ff78, 0x00000060,
+	0x80767874, 0x82778075,
+	0xbefd00ff, 0x0000006c,
+	0xf460403b, 0xf8000000,
+	0xbf8a0000, 0x80fd847d,
 	0xbf800000, 0xbe804300,
-	0xbe824302, 0xbe844304,
-	0xbe864306, 0x80f6c076,
-	0x82f78077, 0xf460803b,
+	0xbe824302, 0x80f6a076,
+	0x82f78077, 0xf460603b,
 	0xf8000000, 0xbf8a0000,
-	0x80fd907d, 0xbf800000,
+	0x80fd887d, 0xbf800000,
 	0xbe804300, 0xbe824302,
 	0xbe844304, 0xbe864306,
-	0xbe884308, 0xbe8a430a,
-	0xbe8c430c, 0xbe8e430e,
-	0xbf06807d, 0xbfa1ffef,
-	0xb980f801, 0x00000000,
-	0xb8f83b05, 0x80788178,
-	0xbf0d9972, 0xbfa20002,
-	0x84788978, 0xbfa00001,
-	0x84788a78, 0x8078ff78,
-	0x00000200, 0x80767874,
-	0x82778075, 0xbeff0071,
-	0xf4601bfb, 0xf8000000,
-	0xf4601b3b, 0xf8000004,
-	0xf4601b7b, 0xf8000008,
-	0xf4601c3b, 0xf800000c,
-	0xf4601c7b, 0xf8000010,
-	0xf4601ebb, 0xf8000014,
-	0xf4601efb, 0xf8000018,
-	0xf4601e7b, 0xf800001c,
-	0xf4601cfb, 0xf8000020,
-	0xf4601bbb, 0xf8000024,
-	0xbf8a0000, 0xb96ef814,
-	0xf4601bbb, 0xf8000028,
-	0xbf8a0000, 0xb96ef815,
-	0xf4601bbb, 0xf800002c,
-	0xbf8a0000, 0xb96ef812,
-	0xf4601bbb, 0xf8000030,
-	0xbf8a0000, 0xb96ef813,
-	0x8b6eff7f, 0x04000000,
-	0xbfa10022, 0xf4601bbb,
-	0xf8000038, 0xbf8a0000,
-	0xbf0d806e, 0xbfa1001d,
-	0x856e906e, 0x8b6e6e6e,
-	0xbfa10003, 0xbe804ec1,
-	0x816ec16e, 0xbfa0fffb,
-	0xbef800ff, 0x00000080,
-	0xbefd0081, 0xf4601bbb,
-	0xf0000000, 0xbfc70000,
-	0x80788478, 0x937eff6e,
-	0x00070004, 0x847e907e,
-	0x8c7d7e7d, 0xbe80517d,
-	0x917dff7d, 0x007f0000,
-	0x856e906e, 0x8b6e6e6e,
-	0xbfa10003, 0xbe804e7d,
-	0x816ec16e, 0xbfa0fffb,
-	0x807d817d, 0xbf08907d,
-	0xbfa1ffec, 0xf4601bbb,
-	0xf800003c, 0xbfc70000,
-	0xbf0d806e, 0xbfa1000c,
-	0xbf0d9a7f, 0xbfa10002,
-	0xbf068180, 0xbe804fc4,
-	0xbf94fffc, 0xbfa10006,
-	0x856e906e, 0x8b6e6e6e,
-	0xbfa10003, 0xbe804ec3,
-	0x816ec16e, 0xbfa0fffb,
-	0xf4601bbb, 0xf8000040,
-	0xbfc70000, 0xb96ef81a,
-	0xbefd006f, 0xbefe0070,
-	0xbeff0071, 0xb979f822,
-	0xb97b2011, 0x857b867b,
-	0xb97b0191, 0x857b827b,
-	0xb97bba11, 0xb973f801,
-	0xb8ee3b05, 0x806e816e,
-	0xbf0d9972, 0xbfa20002,
-	0x846e896e, 0xbfa00001,
-	0x846e8a6e, 0x806eff6e,
-	0x000001c0, 0x806e746e,
-	0x826f8075, 0xf4605c37,
-	0xf8000010, 0xf4605d37,
-	0xf8000020, 0xf4601e77,
-	0xf8000034, 0xbf8a0000,
-	0x856e9677, 0xb96e04a1,
-	0x856e9577, 0xb96e0421,
-	0x856e8e77, 0xb96e3021,
-	0x8b6dff6d, 0x01ffffff,
-	0x8bfe7e7e, 0x8bea6a6a,
-	0xb97af804, 0xb8eef802,
-	0xbf0c8b6e, 0xbfa20003,
-	0xbe804fc2, 0xbf94fffe,
-	0xbfa10001, 0xbe804ec4,
-	0xbf94fffc, 0x857a897a,
-	0xb97a0244, 0xbe804a6c,
+	0x80f6c076, 0x82f78077,
+	0xf460803b, 0xf8000000,
+	0xbf8a0000, 0x80fd907d,
+	0xbf800000, 0xbe804300,
+	0xbe824302, 0xbe844304,
+	0xbe864306, 0xbe884308,
+	0xbe8a430a, 0xbe8c430c,
+	0xbe8e430e, 0xbf06807d,
+	0xbfa1ffef, 0xb980f801,
+	0x00000000, 0xb8f83b05,
+	0x80788178, 0xbf0d9972,
+	0xbfa20002, 0x84788978,
+	0xbfa00001, 0x84788a78,
+	0x8078ff78, 0x00000200,
+	0x80767874, 0x82778075,
+	0xbeff0071, 0xf4601bfb,
+	0xf8000000, 0xf4601b3b,
+	0xf8000004, 0xf4601b7b,
+	0xf8000008, 0xf4601c3b,
+	0xf800000c, 0xf4601c7b,
+	0xf8000010, 0xf4601ebb,
+	0xf8000014, 0xf4601efb,
+	0xf8000018, 0xf4601e7b,
+	0xf800001c, 0xf4601cfb,
+	0xf8000020, 0xf4601bbb,
+	0xf8000024, 0xbf8a0000,
+	0xb96ef814, 0xf4601bbb,
+	0xf8000028, 0xbf8a0000,
+	0xb96ef815, 0xf4601bbb,
+	0xf800002c, 0xbf8a0000,
+	0xb96ef812, 0xf4601bbb,
+	0xf8000030, 0xbf8a0000,
+	0xb96ef813, 0x8b6eff7f,
+	0x04000000, 0xbfa10022,
+	0xf4601bbb, 0xf8000038,
+	0xbf8a0000, 0xbf0d806e,
+	0xbfa1001d, 0x856e906e,
+	0x8b6e6e6e, 0xbfa10003,
+	0xbe804ec1, 0x816ec16e,
+	0xbfa0fffb, 0xbef800ff,
+	0x00000080, 0xbefd0081,
+	0xf4601bbb, 0xf0000000,
+	0xbfc70000, 0x80788478,
+	0x937eff6e, 0x00070004,
+	0x847e907e, 0x8c7d7e7d,
+	0xbe80517d, 0x917dff7d,
+	0x007f0000, 0x856e906e,
+	0x8b6e6e6e, 0xbfa10003,
+	0xbe804e7d, 0x816ec16e,
+	0xbfa0fffb, 0x807d817d,
+	0xbf08907d, 0xbfa1ffec,
+	0xf4601bbb, 0xf800003c,
+	0xbfc70000, 0xbf0d806e,
+	0xbfa1000c, 0xbf0d9a7f,
+	0xbfa10002, 0xbf068180,
+	0xbe804fc4, 0xbf94fffc,
+	0xbfa10006, 0x856e906e,
+	0x8b6e6e6e, 0xbfa10003,
+	0xbe804ec3, 0x816ec16e,
+	0xbfa0fffb, 0xf4601bbb,
+	0xf8000040, 0xbfc70000,
+	0xb96ef81a, 0xbefd006f,
+	0xbefe0070, 0xbeff0071,
+	0xb979f822, 0xb97b2011,
+	0x857b867b, 0xb97b0191,
+	0x857b827b, 0xb97bba11,
+	0xb973f801, 0xb8ee3b05,
+	0x806e816e, 0xbf0d9972,
+	0xbfa20002, 0x846e896e,
+	0xbfa00001, 0x846e8a6e,
+	0x806eff6e, 0x000001c0,
+	0x806e746e, 0x826f8075,
+	0xf4605c37, 0xf8000010,
+	0xf4605d37, 0xf8000020,
+	0xf4601e77, 0xf8000034,
+	0xbf8a0000, 0x856e9677,
+	0xb96e04a1, 0x856e9577,
+	0xb96e0421, 0x856e8e77,
+	0xb96e3021, 0x8b6dff6d,
+	0x01ffffff, 0x8bfe7e7e,
+	0x8bea6a6a, 0xb97af804,
 	0xb8eef802, 0xbf0c8b6e,
 	0xbfa20003, 0xbe804fc2,
 	0xbf94fffe, 0xbfa10001,
 	0xbe804ec4, 0xbf94fffc,
-	0xbfb10000, 0xbf9f0000,
+	0x857a897a, 0xb97a0244,
+	0xbe804a6c, 0xb8eef802,
+	0xbf0c8b6e, 0xbfa20003,
+	0xbe804fc2, 0xbf94fffe,
+	0xbfa10001, 0xbe804ec4,
+	0xbf94fffc, 0xbfb10000,
 	0xbf9f0000, 0xbf9f0000,
 	0xbf9f0000, 0xbf9f0000,
+	0xbf9f0000, 0x00000000,
 };
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx12.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx12.asm
index 07de21918444c..233ed8b6d122c 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx12.asm
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx12.asm
@@ -44,11 +44,16 @@
 #define HAVE_HT_TRAP_ID_WA (ASIC_FAMILY >= CHIP_GFX12)
 #define WAVE32_ONLY (ASIC_FAMILY == CHIP_GC_12_0_3)
 #define SAVE_TTMPS_IN_SGPR_BLOCK (ASIC_FAMILY >= CHIP_GC_12_0_3)
+#define VMEM_ON_TRAP_ENTRY_WA (ASIC_FAMILY == CHIP_GC_12_0_3)
 
 #if HAVE_XNACK && !WAVE32_ONLY
 # error
 #endif
 
+#if VMEM_ON_TRAP_ENTRY_WA && RELAXED_SCHEDULING_IN_TRAP
+# error
+#endif
+
 #define ADDRESS_HI32_NUM_BITS ((HAVE_57BIT_ADDRESS ? 57 : 48) - 32)
 #define ADDRESS_HI32_MASK ((1 << ADDRESS_HI32_NUM_BITS) - 1)
 
@@ -238,6 +243,34 @@ L_JUMP_TO_RESTORE:
 	s_branch	L_RESTORE
 
 L_SKIP_RESTORE:
+	s_getreg_b32	s_save_state_priv, hwreg(HW_REG_WAVE_STATE_PRIV)	//save STATUS since we will change SCC
+
+#if VMEM_ON_TRAP_ENTRY_WA
+	s_getreg_b32	ttmp14, hwreg(HW_REG_WAVE_EXCP_FLAG_PRIV)
+	s_bitcmp1_b32	ttmp14, SQ_WAVE_EXCP_FLAG_PRIV_WAVE_START_SHIFT
+	s_cbranch_scc0	L_NOT_WAVE_START
+
+	s_setreg_imm32_b32	hwreg(HW_REG_WAVE_EXCP_FLAG_PRIV, SQ_WAVE_EXCP_FLAG_PRIV_WAVE_START_SHIFT, 1), 0
+
+	s_mov_b64	[ttmp2, ttmp3], 0
+	v_mov_b32	v1, 0
+	global_prefetch_b8	v1, [ttmp2, ttmp3] scope:SCOPE_SE th:TH_LOAD_RT
+
+	s_rfe_b64	[ttmp0, ttmp1]
+
+L_NOT_WAVE_START:
+	s_mov_b32	ttmp14, exec_lo
+	s_mov_b32	exec_lo, 1
+	v_readlane_b32	ttmp15, v1, 0
+
+	s_mov_b64	[ttmp2, ttmp3], 0
+	v_mov_b32	v1, 0
+	global_prefetch_b8	v1, [ttmp2, ttmp3] scope:SCOPE_SE th:TH_LOAD_RT
+
+	v_writelane_b32	v1, ttmp15, 0
+	s_mov_b32	exec_lo, ttmp14
+#endif
+
 #if RELAXED_SCHEDULING_IN_TRAP
 	// Assume most relaxed scheduling mode is set. Save and revert to normal mode.
 	s_getreg_b32	ttmp2, hwreg(HW_REG_WAVE_SCHED_MODE)
@@ -246,8 +279,6 @@ L_SKIP_RESTORE:
 		SQ_WAVE_SCHED_MODE_DEP_MODE_SHIFT, SQ_WAVE_SCHED_MODE_DEP_MODE_SIZE), 0
 #endif
 
-	s_getreg_b32	s_save_state_priv, hwreg(HW_REG_WAVE_STATE_PRIV)	//save STATUS since we will change SCC
-
 #if RELAXED_SCHEDULING_IN_TRAP
 	// Save SCHED_MODE[1:0] into ttmp11[27:26].
 	s_andn2_b32	ttmp11, ttmp11, TTMP11_SCHED_MODE_MASK
-- 
2.55.0
lmpx.com only provides a reader for public news (NNTP) servers. It is not affiliated with the servers or forums shown here and is not responsible for the content of articles, which is written by their respective authors.