AMD-GFX Archive on lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH] drm/amdkfd: Trap handler support for expert scheduling mode
@ 2025-11-10 16:48 Jay Cornwall
  2025-11-14 14:27 ` Lancelot SIX
  0 siblings, 1 reply; 2+ messages in thread
From: Jay Cornwall @ 2025-11-10 16:48 UTC (permalink / raw)
  To: amd-gfx; +Cc: Jay Cornwall, Lancelot Six

The trap handler may be entered with dependency checking disabled.
Wait for dependency counters and save/restore scheduling mode.

Signed-off-by: Jay Cornwall <jay.cornwall@amd.com>
Cc: Lancelot Six <lancelot.six@amd.com>
---
 .../gpu/drm/amd/amdkfd/cwsr_trap_handler.h    | 853 +++++++++---------
 .../amd/amdkfd/cwsr_trap_handler_gfx12.asm    |  31 +
 2 files changed, 461 insertions(+), 423 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
index 0320163b6e74..a12f703bda8b 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
@@ -3644,14 +3644,18 @@ static const uint32_t cwsr_trap_gfx9_4_3_hex[] = {
 };
 
 static const uint32_t cwsr_trap_gfx12_hex[] = {
-	0xbfa00001, 0xbfa002a2,
-	0xb0804009, 0xb8f8f804,
+	0xbfa00001, 0xbfa002ad,
+	0xb0804009, 0xb8eef81a,
+	0xbf880000, 0xb980081a,
+	0x00000000, 0xb8f8f804,
+	0x9177ff77, 0x0c000000,
+	0x846e9a6e, 0x8c776e77,
 	0x9178ff78, 0x00008c00,
 	0xb8fbf811, 0x8b6eff78,
 	0x00004000, 0xbfa10008,
 	0x8b6eff7b, 0x00000080,
 	0xbfa20018, 0x8b6ea07b,
-	0xbfa20042, 0xbf830010,
+	0xbfa20045, 0xbf830010,
 	0xb8fbf811, 0xbfa0fffb,
 	0x8b6eff7b, 0x00000bd0,
 	0xbfa20010, 0xb8eef812,
@@ -3662,7 +3666,7 @@ static const uint32_t cwsr_trap_gfx12_hex[] = {
 	0xf0000000, 0xbfa20005,
 	0x8b6fff6f, 0x00000200,
 	0xbfa20002, 0x8b6ea07b,
-	0xbfa2002c, 0xbefa4d82,
+	0xbfa2002f, 0xbefa4d82,
 	0xbf8a0000, 0x84fa887a,
 	0xbf0d8f7b, 0xbfa10002,
 	0x8c7bff7b, 0xffff0000,
@@ -3683,97 +3687,43 @@ static const uint32_t cwsr_trap_gfx12_hex[] = {
 	0x806c846c, 0x826d806d,
 	0x8b6dff6d, 0x0000ffff,
 	0x8bfe7e7e, 0x8bea6a6a,
-	0x85788978, 0xb9783244,
-	0xbe804a6c, 0xb8faf802,
-	0xbf0d987a, 0xbfa10001,
-	0xbfb00000, 0x8b6dff6d,
-	0x0000ffff, 0xbefa0080,
-	0xb97a0151, 0xbeee007e,
-	0xbeef007f, 0xbefe0180,
-	0xbefe4d84, 0xbf8a0000,
-	0x8b7aff7f, 0x04000000,
-	0x847a857a, 0x8c6d7a6d,
-	0xbefa007e, 0x8b7bff7f,
-	0x0000ffff, 0xbefe00c1,
-	0xbeff00c1, 0xee0a407a,
-	0x000c0000, 0x00000000,
-	0x7e000280, 0xbefe007a,
-	0xbeff007b, 0xb8fb0742,
-	0x847b997b, 0xb8fa3b05,
-	0x807a817a, 0xbf0d997b,
-	0xbfa20002, 0x847a897a,
-	0xbfa00001, 0x847a8a7a,
-	0xb8fb1e06, 0x847b8a7b,
-	0x807a7b7a, 0x8b7bff7f,
-	0x0000ffff, 0x807aff7a,
-	0x00000200, 0x807a7e7a,
-	0x827b807b, 0xd7610000,
-	0x00010870, 0xd7610000,
-	0x00010a71, 0xd7610000,
-	0x00010c72, 0xd7610000,
-	0x00010e73, 0xd7610000,
-	0x00011074, 0xd7610000,
-	0x00011275, 0xd7610000,
-	0x00011476, 0xd7610000,
-	0x00011677, 0xd7610000,
-	0x00011a79, 0xd7610000,
-	0x00011c7e, 0xd7610000,
-	0x00011e7f, 0xd8500000,
-	0x00000000, 0xd8500000,
-	0x00000000, 0xd8500000,
-	0x00000000, 0xd8500000,
-	0x00000000, 0xd8500000,
-	0x00000000, 0xd8500000,
-	0x00000000, 0xd8500000,
-	0x00000000, 0xd8500000,
-	0x00000000, 0xbefe00ff,
-	0x00003fff, 0xbeff0080,
+	0x85788978, 0x936eff77,
+	0x0002001a, 0xb96e081a,
+	0xb9783244, 0xbe804a6c,
+	0xb8faf802, 0xbf0d987a,
+	0xbfa10001, 0xbfb00000,
+	0x8b6dff6d, 0x0000ffff,
+	0xbefa0080, 0xb97a0151,
+	0xbeee007e, 0xbeef007f,
+	0xbefe0180, 0xbefe4d84,
+	0xbf8a0000, 0x8b7aff7f,
+	0x04000000, 0x847a857a,
+	0x8c6d7a6d, 0xbefa007e,
+	0x8b7bff7f, 0x0000ffff,
+	0xbefe00c1, 0xbeff00c1,
 	0xee0a407a, 0x000c0000,
-	0x00004000, 0xd760007a,
-	0x00011d00, 0xd760007b,
-	0x00011f00, 0xbefe007a,
-	0xbeff007b, 0xbef4007e,
-	0x8b75ff7f, 0x0000ffff,
-	0x8c75ff75, 0x00040000,
-	0xbef60080, 0xbef700ff,
-	0x10807fac, 0xbef1007d,
-	0xbef00080, 0xb8f30742,
-	0x84739973, 0xbefe00c1,
-	0x857d9973, 0x8b7d817d,
-	0xbf06817d, 0xbfa20002,
-	0xbeff0080, 0xbfa00002,
-	0xbeff00c1, 0xbfa0000c,
-	0xbef600ff, 0x01000000,
-	0xc4068070, 0x008ce801,
-	0x00008000, 0xc4068070,
-	0x008ce802, 0x00010000,
-	0xc4068070, 0x008ce803,
-	0x00018000, 0xbfa0000b,
-	0xbef600ff, 0x01000000,
-	0xc4068070, 0x008ce801,
-	0x00010000, 0xc4068070,
-	0x008ce802, 0x00020000,
-	0xc4068070, 0x008ce803,
-	0x00030000, 0xb8f03b05,
-	0x80708170, 0xbf0d9973,
-	0xbfa20002, 0x84708970,
-	0xbfa00001, 0x84708a70,
-	0xb8fa1e06, 0x847a8a7a,
-	0x80707a70, 0x8070ff70,
-	0x00000200, 0xbef600ff,
-	0x01000000, 0x7e000280,
-	0x7e020280, 0x7e040280,
-	0xbe804ec2, 0xbf94fffe,
-	0xb8faf804, 0x8b7a847a,
-	0x91788478, 0x8c787a78,
-	0x917aff6d, 0x80000000,
-	0xd7610002, 0x00010071,
-	0xd7610002, 0x0001026c,
-	0xd7610002, 0x0001047a,
-	0xd7610002, 0x0001066e,
-	0xd7610002, 0x0001086f,
-	0xd7610002, 0x00010a78,
-	0xd7610002, 0x00010e7b,
+	0x00000000, 0x7e000280,
+	0xbefe007a, 0xbeff007b,
+	0xb8fb0742, 0x847b997b,
+	0xb8fa3b05, 0x807a817a,
+	0xbf0d997b, 0xbfa20002,
+	0x847a897a, 0xbfa00001,
+	0x847a8a7a, 0xb8fb1e06,
+	0x847b8a7b, 0x807a7b7a,
+	0x8b7bff7f, 0x0000ffff,
+	0x807aff7a, 0x00000200,
+	0x807a7e7a, 0x827b807b,
+	0xd7610000, 0x00010870,
+	0xd7610000, 0x00010a71,
+	0xd7610000, 0x00010c72,
+	0xd7610000, 0x00010e73,
+	0xd7610000, 0x00011074,
+	0xd7610000, 0x00011275,
+	0xd7610000, 0x00011476,
+	0xd7610000, 0x00011677,
+	0xd7610000, 0x00011a79,
+	0xd7610000, 0x00011c7e,
+	0xd7610000, 0x00011e7f,
 	0xd8500000, 0x00000000,
 	0xd8500000, 0x00000000,
 	0xd8500000, 0x00000000,
@@ -3782,113 +3732,54 @@ static const uint32_t cwsr_trap_gfx12_hex[] = {
 	0xd8500000, 0x00000000,
 	0xd8500000, 0x00000000,
 	0xd8500000, 0x00000000,
-	0xb8faf811, 0xd7610002,
-	0x00010c7a, 0xb8faf801,
-	0xd7610002, 0x0001107a,
-	0xb8faf814, 0xd7610002,
-	0x0001127a, 0xb8faf815,
-	0xd7610002, 0x0001147a,
-	0xb8faf812, 0xd7610002,
-	0x0001167a, 0xb8faf813,
-	0xd7610002, 0x0001187a,
-	0xb8faf802, 0xd7610002,
-	0x00011a7a, 0xbefa50c1,
-	0xbfc70000, 0xd7610002,
-	0x00011c7a, 0xd8500000,
-	0x00000000, 0xd8500000,
-	0x00000000, 0xd8500000,
-	0x00000000, 0xd8500000,
-	0x00000000, 0xd8500000,
-	0x00000000, 0xd8500000,
-	0x00000000, 0xd8500000,
-	0x00000000, 0xd8500000,
-	0x00000000, 0xbefe00ff,
-	0x0000ffff, 0xbeff0080,
+	0xbefe00ff, 0x00003fff,
+	0xbeff0080, 0xee0a407a,
+	0x000c0000, 0x00004000,
+	0xd760007a, 0x00011d00,
+	0xd760007b, 0x00011f00,
+	0xbefe007a, 0xbeff007b,
+	0xbef4007e, 0x8b75ff7f,
+	0x0000ffff, 0x8c75ff75,
+	0x00040000, 0xbef60080,
+	0xbef700ff, 0x10807fac,
+	0xbef1007d, 0xbef00080,
+	0xb8f30742, 0x84739973,
+	0xbefe00c1, 0x857d9973,
+	0x8b7d817d, 0xbf06817d,
+	0xbfa20002, 0xbeff0080,
+	0xbfa00002, 0xbeff00c1,
+	0xbfa0000c, 0xbef600ff,
+	0x01000000, 0xc4068070,
+	0x008ce801, 0x00008000,
 	0xc4068070, 0x008ce802,
-	0x00000000, 0xbefe00c1,
+	0x00010000, 0xc4068070,
+	0x008ce803, 0x00018000,
+	0xbfa0000b, 0xbef600ff,
+	0x01000000, 0xc4068070,
+	0x008ce801, 0x00010000,
+	0xc4068070, 0x008ce802,
+	0x00020000, 0xc4068070,
+	0x008ce803, 0x00030000,
 	0xb8f03b05, 0x80708170,
 	0xbf0d9973, 0xbfa20002,
 	0x84708970, 0xbfa00001,
 	0x84708a70, 0xb8fa1e06,
 	0x847a8a7a, 0x80707a70,
+	0x8070ff70, 0x00000200,
 	0xbef600ff, 0x01000000,
-	0xbef90080, 0xbefd0080,
-	0xbf800000, 0xbe804100,
-	0xbe824102, 0xbe844104,
-	0xbe864106, 0xbe884108,
-	0xbe8a410a, 0xbe8c410c,
-	0xbe8e410e, 0xbf068079,
-	0xbfa10032, 0xd7610002,
-	0x00010000, 0xd7610002,
-	0x00010201, 0xd7610002,
-	0x00010402, 0xd7610002,
-	0x00010603, 0xd7610002,
-	0x00010804, 0xd7610002,
-	0x00010a05, 0xd7610002,
-	0x00010c06, 0xd7610002,
-	0x00010e07, 0xd7610002,
-	0x00011008, 0xd7610002,
-	0x00011209, 0xd7610002,
-	0x0001140a, 0xd7610002,
-	0x0001160b, 0xd7610002,
-	0x0001180c, 0xd7610002,
-	0x00011a0d, 0xd7610002,
-	0x00011c0e, 0xd7610002,
-	0x00011e0f, 0xd8500000,
-	0x00000000, 0xd8500000,
-	0x00000000, 0xd8500000,
-	0x00000000, 0xd8500000,
-	0x00000000, 0xd8500000,
-	0x00000000, 0xd8500000,
-	0x00000000, 0xd8500000,
-	0x00000000, 0xd8500000,
-	0x00000000, 0x80799079,
-	0xbfa00038, 0xd7610002,
-	0x00012000, 0xd7610002,
-	0x00012201, 0xd7610002,
-	0x00012402, 0xd7610002,
-	0x00012603, 0xd7610002,
-	0x00012804, 0xd7610002,
-	0x00012a05, 0xd7610002,
-	0x00012c06, 0xd7610002,
-	0x00012e07, 0xd7610002,
-	0x00013008, 0xd7610002,
-	0x00013209, 0xd7610002,
-	0x0001340a, 0xd7610002,
-	0x0001360b, 0xd7610002,
-	0x0001380c, 0xd7610002,
-	0x00013a0d, 0xd7610002,
-	0x00013c0e, 0xd7610002,
-	0x00013e0f, 0xd8500000,
-	0x00000000, 0xd8500000,
-	0x00000000, 0xd8500000,
-	0x00000000, 0xd8500000,
-	0x00000000, 0xd8500000,
-	0x00000000, 0xd8500000,
-	0x00000000, 0xd8500000,
-	0x00000000, 0xd8500000,
-	0x00000000, 0x80799079,
-	0xc4068070, 0x008ce802,
-	0x00000000, 0x8070ff70,
-	0x00000080, 0xbef90080,
-	0x7e040280, 0x807d907d,
-	0xbf0aff7d, 0x00000060,
-	0xbfa2ff88, 0xbe804100,
-	0xbe824102, 0xbe844104,
-	0xbe864106, 0xbe884108,
-	0xbe8a410a, 0xd7610002,
-	0x00010000, 0xd7610002,
-	0x00010201, 0xd7610002,
-	0x00010402, 0xd7610002,
-	0x00010603, 0xd7610002,
-	0x00010804, 0xd7610002,
-	0x00010a05, 0xd7610002,
-	0x00010c06, 0xd7610002,
-	0x00010e07, 0xd7610002,
-	0x00011008, 0xd7610002,
-	0x00011209, 0xd7610002,
-	0x0001140a, 0xd7610002,
-	0x0001160b, 0xd8500000,
+	0x7e000280, 0x7e020280,
+	0x7e040280, 0xbe804ec2,
+	0xbf94fffe, 0xb8faf804,
+	0x8b7a847a, 0x91788478,
+	0x8c787a78, 0x917aff6d,
+	0x80000000, 0xd7610002,
+	0x00010071, 0xd7610002,
+	0x0001026c, 0xd7610002,
+	0x0001047a, 0xd7610002,
+	0x0001066e, 0xd7610002,
+	0x0001086f, 0xd7610002,
+	0x00010a78, 0xd7610002,
+	0x00010e7b, 0xd8500000,
 	0x00000000, 0xd8500000,
 	0x00000000, 0xd8500000,
 	0x00000000, 0xd8500000,
@@ -3896,273 +3787,389 @@ static const uint32_t cwsr_trap_gfx12_hex[] = {
 	0x00000000, 0xd8500000,
 	0x00000000, 0xd8500000,
 	0x00000000, 0xd8500000,
-	0x00000000, 0xc4068070,
+	0x00000000, 0xb8faf811,
+	0xd7610002, 0x00010c7a,
+	0xb8faf801, 0xd7610002,
+	0x0001107a, 0xb8faf814,
+	0xd7610002, 0x0001127a,
+	0xb8faf815, 0xd7610002,
+	0x0001147a, 0xb8faf812,
+	0xd7610002, 0x0001167a,
+	0xb8faf813, 0xd7610002,
+	0x0001187a, 0xb8faf802,
+	0xd7610002, 0x00011a7a,
+	0xbefa50c1, 0xbfc70000,
+	0xd7610002, 0x00011c7a,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xbefe00ff, 0x0000ffff,
+	0xbeff0080, 0xc4068070,
+	0x008ce802, 0x00000000,
+	0xbefe00c1, 0xb8f03b05,
+	0x80708170, 0xbf0d9973,
+	0xbfa20002, 0x84708970,
+	0xbfa00001, 0x84708a70,
+	0xb8fa1e06, 0x847a8a7a,
+	0x80707a70, 0xbef600ff,
+	0x01000000, 0xbef90080,
+	0xbefd0080, 0xbf800000,
+	0xbe804100, 0xbe824102,
+	0xbe844104, 0xbe864106,
+	0xbe884108, 0xbe8a410a,
+	0xbe8c410c, 0xbe8e410e,
+	0xbf068079, 0xbfa10032,
+	0xd7610002, 0x00010000,
+	0xd7610002, 0x00010201,
+	0xd7610002, 0x00010402,
+	0xd7610002, 0x00010603,
+	0xd7610002, 0x00010804,
+	0xd7610002, 0x00010a05,
+	0xd7610002, 0x00010c06,
+	0xd7610002, 0x00010e07,
+	0xd7610002, 0x00011008,
+	0xd7610002, 0x00011209,
+	0xd7610002, 0x0001140a,
+	0xd7610002, 0x0001160b,
+	0xd7610002, 0x0001180c,
+	0xd7610002, 0x00011a0d,
+	0xd7610002, 0x00011c0e,
+	0xd7610002, 0x00011e0f,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0x80799079, 0xbfa00038,
+	0xd7610002, 0x00012000,
+	0xd7610002, 0x00012201,
+	0xd7610002, 0x00012402,
+	0xd7610002, 0x00012603,
+	0xd7610002, 0x00012804,
+	0xd7610002, 0x00012a05,
+	0xd7610002, 0x00012c06,
+	0xd7610002, 0x00012e07,
+	0xd7610002, 0x00013008,
+	0xd7610002, 0x00013209,
+	0xd7610002, 0x0001340a,
+	0xd7610002, 0x0001360b,
+	0xd7610002, 0x0001380c,
+	0xd7610002, 0x00013a0d,
+	0xd7610002, 0x00013c0e,
+	0xd7610002, 0x00013e0f,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0x80799079, 0xc4068070,
 	0x008ce802, 0x00000000,
-	0xbefe00c1, 0x857d9973,
-	0x8b7d817d, 0xbf06817d,
-	0xbfa20002, 0xbeff0080,
-	0xbfa00001, 0xbeff00c1,
-	0xb8fb4306, 0x8b7bc17b,
-	0xbfa10044, 0x8b7aff6d,
-	0x80000000, 0xbfa10041,
-	0x847b897b, 0xbef6007b,
-	0xb8f03b05, 0x80708170,
-	0xbf0d9973, 0xbfa20002,
-	0x84708970, 0xbfa00001,
-	0x84708a70, 0xb8fa1e06,
-	0x847a8a7a, 0x80707a70,
-	0x8070ff70, 0x00000200,
 	0x8070ff70, 0x00000080,
-	0xbef600ff, 0x01000000,
-	0xd71f0000, 0x000100c1,
-	0xd7200000, 0x000200c1,
-	0x16000084, 0x857d9973,
-	0x8b7d817d, 0xbf06817d,
-	0xbefd0080, 0xbfa20013,
-	0xbe8300ff, 0x00000080,
-	0xbf800000, 0xbf800000,
-	0xbf800000, 0xd8d80000,
-	0x01000000, 0xbf8a0000,
-	0xc4068070, 0x008ce801,
-	0x00000000, 0x807d037d,
-	0x80700370, 0xd5250000,
-	0x0001ff00, 0x00000080,
-	0xbf0a7b7d, 0xbfa2fff3,
-	0xbfa00012, 0xbe8300ff,
-	0x00000100, 0xbf800000,
+	0xbef90080, 0x7e040280,
+	0x807d907d, 0xbf0aff7d,
+	0x00000060, 0xbfa2ff88,
+	0xbe804100, 0xbe824102,
+	0xbe844104, 0xbe864106,
+	0xbe884108, 0xbe8a410a,
+	0xd7610002, 0x00010000,
+	0xd7610002, 0x00010201,
+	0xd7610002, 0x00010402,
+	0xd7610002, 0x00010603,
+	0xd7610002, 0x00010804,
+	0xd7610002, 0x00010a05,
+	0xd7610002, 0x00010c06,
+	0xd7610002, 0x00010e07,
+	0xd7610002, 0x00011008,
+	0xd7610002, 0x00011209,
+	0xd7610002, 0x0001140a,
+	0xd7610002, 0x0001160b,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xd8500000, 0x00000000,
+	0xc4068070, 0x008ce802,
+	0x00000000, 0xbefe00c1,
+	0x857d9973, 0x8b7d817d,
+	0xbf06817d, 0xbfa20002,
+	0xbeff0080, 0xbfa00001,
+	0xbeff00c1, 0xb8fb4306,
+	0x8b7bc17b, 0xbfa10044,
+	0x8b7aff6d, 0x80000000,
+	0xbfa10041, 0x847b897b,
+	0xbef6007b, 0xb8f03b05,
+	0x80708170, 0xbf0d9973,
+	0xbfa20002, 0x84708970,
+	0xbfa00001, 0x84708a70,
+	0xb8fa1e06, 0x847a8a7a,
+	0x80707a70, 0x8070ff70,
+	0x00000200, 0x8070ff70,
+	0x00000080, 0xbef600ff,
+	0x01000000, 0xd71f0000,
+	0x000100c1, 0xd7200000,
+	0x000200c1, 0x16000084,
+	0x857d9973, 0x8b7d817d,
+	0xbf06817d, 0xbefd0080,
+	0xbfa20013, 0xbe8300ff,
+	0x00000080, 0xbf800000,
 	0xbf800000, 0xbf800000,
 	0xd8d80000, 0x01000000,
 	0xbf8a0000, 0xc4068070,
 	0x008ce801, 0x00000000,
 	0x807d037d, 0x80700370,
 	0xd5250000, 0x0001ff00,
-	0x00000100, 0xbf0a7b7d,
-	0xbfa2fff3, 0xbefe00c1,
-	0x857d9973, 0x8b7d817d,
-	0xbf06817d, 0xbfa20004,
-	0xbef000ff, 0x00000200,
-	0xbeff0080, 0xbfa00003,
-	0xbef000ff, 0x00000400,
-	0xbeff00c1, 0xb8fb3b05,
-	0x807b817b, 0x847b827b,
-	0x857d9973, 0x8b7d817d,
-	0xbf06817d, 0xbfa2001b,
-	0xbef600ff, 0x01000000,
-	0xbefd0084, 0xbf0a7b7d,
-	0xbfa10040, 0x7e008700,
-	0x7e028701, 0x7e048702,
-	0x7e068703, 0xc4068070,
-	0x008ce800, 0x00000000,
+	0x00000080, 0xbf0a7b7d,
+	0xbfa2fff3, 0xbfa00012,
+	0xbe8300ff, 0x00000100,
+	0xbf800000, 0xbf800000,
+	0xbf800000, 0xd8d80000,
+	0x01000000, 0xbf8a0000,
 	0xc4068070, 0x008ce801,
-	0x00008000, 0xc4068070,
-	0x008ce802, 0x00010000,
-	0xc4068070, 0x008ce803,
-	0x00018000, 0x807d847d,
-	0x8070ff70, 0x00000200,
-	0xbf0a7b7d, 0xbfa2ffeb,
-	0xbfa0002a, 0xbef600ff,
+	0x00000000, 0x807d037d,
+	0x80700370, 0xd5250000,
+	0x0001ff00, 0x00000100,
+	0xbf0a7b7d, 0xbfa2fff3,
+	0xbefe00c1, 0x857d9973,
+	0x8b7d817d, 0xbf06817d,
+	0xbfa20004, 0xbef000ff,
+	0x00000200, 0xbeff0080,
+	0xbfa00003, 0xbef000ff,
+	0x00000400, 0xbeff00c1,
+	0xb8fb3b05, 0x807b817b,
+	0x847b827b, 0x857d9973,
+	0x8b7d817d, 0xbf06817d,
+	0xbfa2001b, 0xbef600ff,
 	0x01000000, 0xbefd0084,
-	0xbf0a7b7d, 0xbfa10015,
+	0xbf0a7b7d, 0xbfa10040,
 	0x7e008700, 0x7e028701,
 	0x7e048702, 0x7e068703,
 	0xc4068070, 0x008ce800,
 	0x00000000, 0xc4068070,
-	0x008ce801, 0x00010000,
+	0x008ce801, 0x00008000,
 	0xc4068070, 0x008ce802,
-	0x00020000, 0xc4068070,
-	0x008ce803, 0x00030000,
+	0x00010000, 0xc4068070,
+	0x008ce803, 0x00018000,
 	0x807d847d, 0x8070ff70,
-	0x00000400, 0xbf0a7b7d,
-	0xbfa2ffeb, 0xb8fb1e06,
-	0x8b7bc17b, 0xbfa1000d,
-	0x847b837b, 0x807b7d7b,
-	0xbefe00c1, 0xbeff0080,
-	0x7e008700, 0xc4068070,
-	0x008ce800, 0x00000000,
-	0x807d817d, 0x8070ff70,
-	0x00000080, 0xbf0a7b7d,
-	0xbfa2fff7, 0xbfa0016e,
-	0xbef4007e, 0x8b75ff7f,
-	0x0000ffff, 0x8c75ff75,
-	0x00040000, 0xbef60080,
-	0xbef700ff, 0x10807fac,
-	0xbef1007f, 0xb8f20742,
-	0x84729972, 0x8b6eff7f,
-	0x04000000, 0xbfa1003b,
-	0xbefe00c1, 0x857d9972,
-	0x8b7d817d, 0xbf06817d,
-	0xbfa20002, 0xbeff0080,
-	0xbfa00001, 0xbeff00c1,
-	0xb8ef4306, 0x8b6fc16f,
-	0xbfa10030, 0x846f896f,
-	0xbef6006f, 0xb8f83b05,
-	0x80788178, 0xbf0d9972,
-	0xbfa20002, 0x84788978,
-	0xbfa00001, 0x84788a78,
-	0xb8ee1e06, 0x846e8a6e,
-	0x80786e78, 0x8078ff78,
-	0x00000200, 0x8078ff78,
-	0x00000080, 0xbef600ff,
-	0x01000000, 0x857d9972,
-	0x8b7d817d, 0xbf06817d,
-	0xbefd0080, 0xbfa2000d,
-	0xc4050078, 0x0080e800,
-	0x00000000, 0xbf8a0000,
-	0xdac00000, 0x00000000,
-	0x807dff7d, 0x00000080,
-	0x8078ff78, 0x00000080,
-	0xbf0a6f7d, 0xbfa2fff4,
-	0xbfa0000c, 0xc4050078,
-	0x0080e800, 0x00000000,
-	0xbf8a0000, 0xdac00000,
-	0x00000000, 0x807dff7d,
-	0x00000100, 0x8078ff78,
-	0x00000100, 0xbf0a6f7d,
-	0xbfa2fff4, 0xbef80080,
-	0xbefe00c1, 0x857d9972,
-	0x8b7d817d, 0xbf06817d,
-	0xbfa20002, 0xbeff0080,
-	0xbfa00001, 0xbeff00c1,
-	0xb8ef3b05, 0x806f816f,
-	0x846f826f, 0x857d9972,
-	0x8b7d817d, 0xbf06817d,
-	0xbfa2002c, 0xbef600ff,
-	0x01000000, 0xbeee0078,
-	0x8078ff78, 0x00000200,
-	0xbefd0084, 0xbf0a6f7d,
-	0xbfa10061, 0xc4050078,
-	0x008ce800, 0x00000000,
-	0xc4050078, 0x008ce801,
-	0x00008000, 0xc4050078,
-	0x008ce802, 0x00010000,
-	0xc4050078, 0x008ce803,
-	0x00018000, 0xbf8a0000,
-	0x7e008500, 0x7e028501,
-	0x7e048502, 0x7e068503,
-	0x807d847d, 0x8078ff78,
-	0x00000200, 0xbf0a6f7d,
-	0xbfa2ffea, 0xc405006e,
-	0x008ce800, 0x00000000,
-	0xc405006e, 0x008ce801,
-	0x00008000, 0xc405006e,
-	0x008ce802, 0x00010000,
-	0xc405006e, 0x008ce803,
-	0x00018000, 0xbf8a0000,
-	0xbfa0003d, 0xbef600ff,
-	0x01000000, 0xbeee0078,
-	0x8078ff78, 0x00000400,
-	0xbefd0084, 0xbf0a6f7d,
-	0xbfa10016, 0xc4050078,
-	0x008ce800, 0x00000000,
-	0xc4050078, 0x008ce801,
-	0x00010000, 0xc4050078,
-	0x008ce802, 0x00020000,
-	0xc4050078, 0x008ce803,
-	0x00030000, 0xbf8a0000,
-	0x7e008500, 0x7e028501,
-	0x7e048502, 0x7e068503,
-	0x807d847d, 0x8078ff78,
-	0x00000400, 0xbf0a6f7d,
-	0xbfa2ffea, 0xb8ef1e06,
-	0x8b6fc16f, 0xbfa1000f,
-	0x846f836f, 0x806f7d6f,
-	0xbefe00c1, 0xbeff0080,
-	0xc4050078, 0x008ce800,
-	0x00000000, 0xbf8a0000,
-	0x7e008500, 0x807d817d,
-	0x8078ff78, 0x00000080,
-	0xbf0a6f7d, 0xbfa2fff6,
-	0xbeff00c1, 0xc405006e,
+	0x00000200, 0xbf0a7b7d,
+	0xbfa2ffeb, 0xbfa0002a,
+	0xbef600ff, 0x01000000,
+	0xbefd0084, 0xbf0a7b7d,
+	0xbfa10015, 0x7e008700,
+	0x7e028701, 0x7e048702,
+	0x7e068703, 0xc4068070,
 	0x008ce800, 0x00000000,
-	0xc405006e, 0x008ce801,
-	0x00010000, 0xc405006e,
+	0xc4068070, 0x008ce801,
+	0x00010000, 0xc4068070,
 	0x008ce802, 0x00020000,
-	0xc405006e, 0x008ce803,
-	0x00030000, 0xbf8a0000,
+	0xc4068070, 0x008ce803,
+	0x00030000, 0x807d847d,
+	0x8070ff70, 0x00000400,
+	0xbf0a7b7d, 0xbfa2ffeb,
+	0xb8fb1e06, 0x8b7bc17b,
+	0xbfa1000d, 0x847b837b,
+	0x807b7d7b, 0xbefe00c1,
+	0xbeff0080, 0x7e008700,
+	0xc4068070, 0x008ce800,
+	0x00000000, 0x807d817d,
+	0x8070ff70, 0x00000080,
+	0xbf0a7b7d, 0xbfa2fff7,
+	0xbfa00171, 0xbef4007e,
+	0x8b75ff7f, 0x0000ffff,
+	0x8c75ff75, 0x00040000,
+	0xbef60080, 0xbef700ff,
+	0x10807fac, 0xbef1007f,
+	0xb8f20742, 0x84729972,
+	0x8b6eff7f, 0x04000000,
+	0xbfa1003b, 0xbefe00c1,
+	0x857d9972, 0x8b7d817d,
+	0xbf06817d, 0xbfa20002,
+	0xbeff0080, 0xbfa00001,
+	0xbeff00c1, 0xb8ef4306,
+	0x8b6fc16f, 0xbfa10030,
+	0x846f896f, 0xbef6006f,
 	0xb8f83b05, 0x80788178,
 	0xbf0d9972, 0xbfa20002,
 	0x84788978, 0xbfa00001,
 	0x84788a78, 0xb8ee1e06,
 	0x846e8a6e, 0x80786e78,
 	0x8078ff78, 0x00000200,
-	0x80f8ff78, 0x00000050,
+	0x8078ff78, 0x00000080,
 	0xbef600ff, 0x01000000,
-	0xbefd00ff, 0x0000006c,
-	0x80f89078, 0xf462403a,
-	0xf0000000, 0xbf8a0000,
-	0x80fd847d, 0xbf800000,
-	0xbe804300, 0xbe824302,
-	0x80f8a078, 0xf462603a,
-	0xf0000000, 0xbf8a0000,
-	0x80fd887d, 0xbf800000,
-	0xbe804300, 0xbe824302,
-	0xbe844304, 0xbe864306,
-	0x80f8c078, 0xf462803a,
-	0xf0000000, 0xbf8a0000,
-	0x80fd907d, 0xbf800000,
-	0xbe804300, 0xbe824302,
-	0xbe844304, 0xbe864306,
-	0xbe884308, 0xbe8a430a,
-	0xbe8c430c, 0xbe8e430e,
-	0xbf06807d, 0xbfa1fff0,
-	0xb980f801, 0x00000000,
-	0xb8f83b05, 0x80788178,
-	0xbf0d9972, 0xbfa20002,
-	0x84788978, 0xbfa00001,
-	0x84788a78, 0xb8ee1e06,
-	0x846e8a6e, 0x80786e78,
+	0x857d9972, 0x8b7d817d,
+	0xbf06817d, 0xbefd0080,
+	0xbfa2000d, 0xc4050078,
+	0x0080e800, 0x00000000,
+	0xbf8a0000, 0xdac00000,
+	0x00000000, 0x807dff7d,
+	0x00000080, 0x8078ff78,
+	0x00000080, 0xbf0a6f7d,
+	0xbfa2fff4, 0xbfa0000c,
+	0xc4050078, 0x0080e800,
+	0x00000000, 0xbf8a0000,
+	0xdac00000, 0x00000000,
+	0x807dff7d, 0x00000100,
+	0x8078ff78, 0x00000100,
+	0xbf0a6f7d, 0xbfa2fff4,
+	0xbef80080, 0xbefe00c1,
+	0x857d9972, 0x8b7d817d,
+	0xbf06817d, 0xbfa20002,
+	0xbeff0080, 0xbfa00001,
+	0xbeff00c1, 0xb8ef3b05,
+	0x806f816f, 0x846f826f,
+	0x857d9972, 0x8b7d817d,
+	0xbf06817d, 0xbfa2002c,
+	0xbef600ff, 0x01000000,
+	0xbeee0078, 0x8078ff78,
+	0x00000200, 0xbefd0084,
+	0xbf0a6f7d, 0xbfa10061,
+	0xc4050078, 0x008ce800,
+	0x00000000, 0xc4050078,
+	0x008ce801, 0x00008000,
+	0xc4050078, 0x008ce802,
+	0x00010000, 0xc4050078,
+	0x008ce803, 0x00018000,
+	0xbf8a0000, 0x7e008500,
+	0x7e028501, 0x7e048502,
+	0x7e068503, 0x807d847d,
 	0x8078ff78, 0x00000200,
+	0xbf0a6f7d, 0xbfa2ffea,
+	0xc405006e, 0x008ce800,
+	0x00000000, 0xc405006e,
+	0x008ce801, 0x00008000,
+	0xc405006e, 0x008ce802,
+	0x00010000, 0xc405006e,
+	0x008ce803, 0x00018000,
+	0xbf8a0000, 0xbfa0003d,
 	0xbef600ff, 0x01000000,
-	0xbeff0071, 0xf4621bfa,
+	0xbeee0078, 0x8078ff78,
+	0x00000400, 0xbefd0084,
+	0xbf0a6f7d, 0xbfa10016,
+	0xc4050078, 0x008ce800,
+	0x00000000, 0xc4050078,
+	0x008ce801, 0x00010000,
+	0xc4050078, 0x008ce802,
+	0x00020000, 0xc4050078,
+	0x008ce803, 0x00030000,
+	0xbf8a0000, 0x7e008500,
+	0x7e028501, 0x7e048502,
+	0x7e068503, 0x807d847d,
+	0x8078ff78, 0x00000400,
+	0xbf0a6f7d, 0xbfa2ffea,
+	0xb8ef1e06, 0x8b6fc16f,
+	0xbfa1000f, 0x846f836f,
+	0x806f7d6f, 0xbefe00c1,
+	0xbeff0080, 0xc4050078,
+	0x008ce800, 0x00000000,
+	0xbf8a0000, 0x7e008500,
+	0x807d817d, 0x8078ff78,
+	0x00000080, 0xbf0a6f7d,
+	0xbfa2fff6, 0xbeff00c1,
+	0xc405006e, 0x008ce800,
+	0x00000000, 0xc405006e,
+	0x008ce801, 0x00010000,
+	0xc405006e, 0x008ce802,
+	0x00020000, 0xc405006e,
+	0x008ce803, 0x00030000,
+	0xbf8a0000, 0xb8f83b05,
+	0x80788178, 0xbf0d9972,
+	0xbfa20002, 0x84788978,
+	0xbfa00001, 0x84788a78,
+	0xb8ee1e06, 0x846e8a6e,
+	0x80786e78, 0x8078ff78,
+	0x00000200, 0x80f8ff78,
+	0x00000050, 0xbef600ff,
+	0x01000000, 0xbefd00ff,
+	0x0000006c, 0x80f89078,
+	0xf462403a, 0xf0000000,
+	0xbf8a0000, 0x80fd847d,
+	0xbf800000, 0xbe804300,
+	0xbe824302, 0x80f8a078,
+	0xf462603a, 0xf0000000,
+	0xbf8a0000, 0x80fd887d,
+	0xbf800000, 0xbe804300,
+	0xbe824302, 0xbe844304,
+	0xbe864306, 0x80f8c078,
+	0xf462803a, 0xf0000000,
+	0xbf8a0000, 0x80fd907d,
+	0xbf800000, 0xbe804300,
+	0xbe824302, 0xbe844304,
+	0xbe864306, 0xbe884308,
+	0xbe8a430a, 0xbe8c430c,
+	0xbe8e430e, 0xbf06807d,
+	0xbfa1fff0, 0xb980f801,
+	0x00000000, 0xb8f83b05,
+	0x80788178, 0xbf0d9972,
+	0xbfa20002, 0x84788978,
+	0xbfa00001, 0x84788a78,
+	0xb8ee1e06, 0x846e8a6e,
+	0x80786e78, 0x8078ff78,
+	0x00000200, 0xbef600ff,
+	0x01000000, 0xbeff0071,
+	0xf4621bfa, 0xf0000000,
+	0x80788478, 0xf4621b3a,
 	0xf0000000, 0x80788478,
-	0xf4621b3a, 0xf0000000,
-	0x80788478, 0xf4621b7a,
+	0xf4621b7a, 0xf0000000,
+	0x80788478, 0xf4621c3a,
 	0xf0000000, 0x80788478,
-	0xf4621c3a, 0xf0000000,
-	0x80788478, 0xf4621c7a,
+	0xf4621c7a, 0xf0000000,
+	0x80788478, 0xf4621eba,
 	0xf0000000, 0x80788478,
-	0xf4621eba, 0xf0000000,
-	0x80788478, 0xf4621efa,
+	0xf4621efa, 0xf0000000,
+	0x80788478, 0xf4621e7a,
 	0xf0000000, 0x80788478,
-	0xf4621e7a, 0xf0000000,
-	0x80788478, 0xf4621cfa,
+	0xf4621cfa, 0xf0000000,
+	0x80788478, 0xf4621bba,
 	0xf0000000, 0x80788478,
+	0xbf8a0000, 0xb96ef814,
 	0xf4621bba, 0xf0000000,
 	0x80788478, 0xbf8a0000,
-	0xb96ef814, 0xf4621bba,
+	0xb96ef815, 0xf4621bba,
 	0xf0000000, 0x80788478,
-	0xbf8a0000, 0xb96ef815,
+	0xbf8a0000, 0xb96ef812,
 	0xf4621bba, 0xf0000000,
 	0x80788478, 0xbf8a0000,
-	0xb96ef812, 0xf4621bba,
+	0xb96ef813, 0x8b6eff7f,
+	0x04000000, 0xbfa1000d,
+	0x80788478, 0xf4621bba,
 	0xf0000000, 0x80788478,
-	0xbf8a0000, 0xb96ef813,
-	0x8b6eff7f, 0x04000000,
-	0xbfa1000d, 0x80788478,
-	0xf4621bba, 0xf0000000,
-	0x80788478, 0xbf8a0000,
-	0xbf0d806e, 0xbfa10006,
-	0x856e906e, 0x8b6e6e6e,
-	0xbfa10003, 0xbe804ec1,
-	0x816ec16e, 0xbfa0fffb,
-	0xbefd006f, 0xbefe0070,
-	0xbeff0071, 0xb97b2011,
-	0x857b867b, 0xb97b0191,
-	0x857b827b, 0xb97bba11,
-	0xb973f801, 0xb8ee3b05,
-	0x806e816e, 0xbf0d9972,
-	0xbfa20002, 0x846e896e,
-	0xbfa00001, 0x846e8a6e,
-	0xb8ef1e06, 0x846f8a6f,
-	0x806e6f6e, 0x806eff6e,
-	0x00000200, 0x806e746e,
-	0x826f8075, 0x8b6fff6f,
-	0x0000ffff, 0xf4605c37,
-	0xf8000050, 0xf4605d37,
-	0xf8000060, 0xf4601e77,
-	0xf8000074, 0xbf8a0000,
-	0x8b6dff6d, 0x0000ffff,
-	0x8bfe7e7e, 0x8bea6a6a,
+	0xbf8a0000, 0xbf0d806e,
+	0xbfa10006, 0x856e906e,
+	0x8b6e6e6e, 0xbfa10003,
+	0xbe804ec1, 0x816ec16e,
+	0xbfa0fffb, 0xbefd006f,
+	0xbefe0070, 0xbeff0071,
+	0xb97b2011, 0x857b867b,
+	0xb97b0191, 0x857b827b,
+	0xb97bba11, 0xb973f801,
+	0xb8ee3b05, 0x806e816e,
+	0xbf0d9972, 0xbfa20002,
+	0x846e896e, 0xbfa00001,
+	0x846e8a6e, 0xb8ef1e06,
+	0x846f8a6f, 0x806e6f6e,
+	0x806eff6e, 0x00000200,
+	0x806e746e, 0x826f8075,
+	0x8b6fff6f, 0x0000ffff,
+	0xf4605c37, 0xf8000050,
+	0xf4605d37, 0xf8000060,
+	0xf4601e77, 0xf8000074,
+	0xbf8a0000, 0x8b6dff6d,
+	0x0000ffff, 0x8bfe7e7e,
+	0x8bea6a6a, 0x936eff77,
+	0x0002001a, 0xb96e081a,
 	0xb97af804, 0xbe804ec2,
 	0xbf94fffe, 0xbe804a6c,
 	0xbe804ec2, 0xbf94fffe,
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 5a1a1b1f897f..f756d3b73281 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx12.asm
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx12.asm
@@ -78,9 +78,16 @@ var SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_2_SHIFT	= SQ_WAVE_EXCP_FLAG_PRIV_ILLEGAL
 var SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_2_SIZE	= SQ_WAVE_EXCP_FLAG_PRIV_HOST_TRAP_SHIFT - SQ_WAVE_EXCP_FLAG_PRIV_ILLEGAL_INST_SHIFT
 var SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_3_SHIFT	= SQ_WAVE_EXCP_FLAG_PRIV_WAVE_START_SHIFT
 var SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_3_SIZE	= 32 - SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_3_SHIFT
+
+var SQ_WAVE_SCHED_MODE_DEP_MODE_SHIFT		= 0
+var SQ_WAVE_SCHED_MODE_DEP_MODE_SIZE		= 2
+
 var BARRIER_STATE_SIGNAL_OFFSET			= 16
 var BARRIER_STATE_VALID_OFFSET			= 0
 
+var TTMP11_SCHED_MODE_SHIFT			= 26
+var TTMP11_SCHED_MODE_SIZE			= 2
+var TTMP11_SCHED_MODE_MASK			= 0xC000000
 var TTMP11_DEBUG_TRAP_ENABLED_SHIFT		= 23
 var TTMP11_DEBUG_TRAP_ENABLED_MASK		= 0x800000
 
@@ -160,8 +167,19 @@ L_JUMP_TO_RESTORE:
 	s_branch	L_RESTORE
 
 L_SKIP_RESTORE:
+	// Assume most relaxed scheduling mode is set. Save and revert to normal mode.
+	s_getreg_b32	ttmp2, hwreg(HW_REG_WAVE_SCHED_MODE)
+	s_wait_alu	0
+	s_setreg_imm32_b32	hwreg(HW_REG_WAVE_SCHED_MODE, \
+		SQ_WAVE_SCHED_MODE_DEP_MODE_SHIFT, SQ_WAVE_SCHED_MODE_DEP_MODE_SIZE), 0
+
 	s_getreg_b32	s_save_state_priv, hwreg(HW_REG_WAVE_STATE_PRIV)	//save STATUS since we will change SCC
 
+	// Save SCHED_MODE[1:0] into ttmp11[27:26].
+	s_andn2_b32	ttmp11, ttmp11, TTMP11_SCHED_MODE_MASK
+	s_lshl_b32	ttmp2, ttmp2, TTMP11_SCHED_MODE_SHIFT
+	s_or_b32	ttmp11, ttmp11, ttmp2
+
 	// Clear SPI_PRIO: do not save with elevated priority.
 	// Clear ECC_ERR: prevents SQC store and triggers FATAL_HALT if setreg'd.
 	s_andn2_b32	s_save_state_priv, s_save_state_priv, SQ_WAVE_STATE_PRIV_ALWAYS_CLEAR_MASK
@@ -287,6 +305,10 @@ L_EXIT_TRAP:
 	// STATE_PRIV.BARRIER_COMPLETE may have changed since we read it.
 	// Only restore fields which the trap handler changes.
 	s_lshr_b32	s_save_state_priv, s_save_state_priv, SQ_WAVE_STATE_PRIV_SCC_SHIFT
+
+	// Assume relaxed scheduling mode after this point.
+	restore_sched_mode(ttmp2)
+
 	s_setreg_b32	hwreg(HW_REG_WAVE_STATE_PRIV, SQ_WAVE_STATE_PRIV_SCC_SHIFT, \
 		SQ_WAVE_STATE_PRIV_POISON_ERR_SHIFT - SQ_WAVE_STATE_PRIV_SCC_SHIFT + 1), s_save_state_priv
 
@@ -1043,6 +1065,9 @@ L_SKIP_BARRIER_RESTORE:
 	s_and_b64	exec, exec, exec					// Restore STATUS.EXECZ, not writable by s_setreg_b32
 	s_and_b64	vcc, vcc, vcc						// Restore STATUS.VCCZ, not writable by s_setreg_b32
 
+	// Assume relaxed scheduling mode after this point.
+	restore_sched_mode(s_restore_tmp)
+
 	s_setreg_b32	hwreg(HW_REG_WAVE_STATE_PRIV), s_restore_state_priv	// SCC is included, which is changed by previous salu
 
 	// Make barrier and LDS state visible to all waves in the group.
@@ -1134,3 +1159,9 @@ function valu_sgpr_hazard
 	end
 #endif
 end
+
+function restore_sched_mode(s_tmp)
+	s_bfe_u32	s_tmp, ttmp11, (TTMP11_SCHED_MODE_SHIFT | (TTMP11_SCHED_MODE_SIZE << 0x10))
+	s_setreg_b32	hwreg(HW_REG_WAVE_SCHED_MODE, SQ_WAVE_SCHED_MODE_DEP_MODE_SHIFT, \
+		 SQ_WAVE_SCHED_MODE_DEP_MODE_SIZE), s_tmp
+end
-- 
2.34.1


^ permalink raw reply related	[flat|nested] 2+ messages in thread

* Re: [PATCH] drm/amdkfd: Trap handler support for expert scheduling mode
  2025-11-10 16:48 [PATCH] drm/amdkfd: Trap handler support for expert scheduling mode Jay Cornwall
@ 2025-11-14 14:27 ` Lancelot SIX
  0 siblings, 0 replies; 2+ messages in thread
From: Lancelot SIX @ 2025-11-14 14:27 UTC (permalink / raw)
  To: Jay Cornwall, amd-gfx



On 10/11/2025 16:48, Jay Cornwall wrote:
> The trap handler may be entered with dependency checking disabled.
> Wait for dependency counters and save/restore scheduling mode.
> 
> Signed-off-by: Jay Cornwall <jay.cornwall@amd.com>
> Cc: Lancelot Six <lancelot.six@amd.com>

Hi,

Should the 2nd level trap handler be modified to also do restore of 
SCHED_MODE?  It seems it does.

I think I somehow assumed that on entry to the 2nd level trap handler, 
those ttmp11 bits should be guaranteed 0, but I can't really see 
anything that would provide such guarantee.

So if we were to use a "new" 2nd level trap handler that did the restore 
from an old 1st level trap handler, could we end-up restoring arbitrary 
data from ttmp11[26:27]?

If I read it is "right", only ttmp1 high bits (27:16) provide such 
guarantee.  If so, should we copy those bits to ttmp1 before jumping to 
the 2nd level trap handler?

Best,
Lancelot.

> ---
>   .../gpu/drm/amd/amdkfd/cwsr_trap_handler.h    | 853 +++++++++---------
>   .../amd/amdkfd/cwsr_trap_handler_gfx12.asm    |  31 +
>   2 files changed, 461 insertions(+), 423 deletions(-)
> 
> diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
> index 0320163b6e74..a12f703bda8b 100644
> --- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
> +++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
> @@ -3644,14 +3644,18 @@ static const uint32_t cwsr_trap_gfx9_4_3_hex[] = {
>   };
>   
>   static const uint32_t cwsr_trap_gfx12_hex[] = {
> -	0xbfa00001, 0xbfa002a2,
> -	0xb0804009, 0xb8f8f804,
> +	0xbfa00001, 0xbfa002ad,
> +	0xb0804009, 0xb8eef81a,
> +	0xbf880000, 0xb980081a,
> +	0x00000000, 0xb8f8f804,
> +	0x9177ff77, 0x0c000000,
> +	0x846e9a6e, 0x8c776e77,
>   	0x9178ff78, 0x00008c00,
>   	0xb8fbf811, 0x8b6eff78,
>   	0x00004000, 0xbfa10008,
>   	0x8b6eff7b, 0x00000080,
>   	0xbfa20018, 0x8b6ea07b,
> -	0xbfa20042, 0xbf830010,
> +	0xbfa20045, 0xbf830010,
>   	0xb8fbf811, 0xbfa0fffb,
>   	0x8b6eff7b, 0x00000bd0,
>   	0xbfa20010, 0xb8eef812,
> @@ -3662,7 +3666,7 @@ static const uint32_t cwsr_trap_gfx12_hex[] = {
>   	0xf0000000, 0xbfa20005,
>   	0x8b6fff6f, 0x00000200,
>   	0xbfa20002, 0x8b6ea07b,
> -	0xbfa2002c, 0xbefa4d82,
> +	0xbfa2002f, 0xbefa4d82,
>   	0xbf8a0000, 0x84fa887a,
>   	0xbf0d8f7b, 0xbfa10002,
>   	0x8c7bff7b, 0xffff0000,
> @@ -3683,97 +3687,43 @@ static const uint32_t cwsr_trap_gfx12_hex[] = {
>   	0x806c846c, 0x826d806d,
>   	0x8b6dff6d, 0x0000ffff,
>   	0x8bfe7e7e, 0x8bea6a6a,
> -	0x85788978, 0xb9783244,
> -	0xbe804a6c, 0xb8faf802,
> -	0xbf0d987a, 0xbfa10001,
> -	0xbfb00000, 0x8b6dff6d,
> -	0x0000ffff, 0xbefa0080,
> -	0xb97a0151, 0xbeee007e,
> -	0xbeef007f, 0xbefe0180,
> -	0xbefe4d84, 0xbf8a0000,
> -	0x8b7aff7f, 0x04000000,
> -	0x847a857a, 0x8c6d7a6d,
> -	0xbefa007e, 0x8b7bff7f,
> -	0x0000ffff, 0xbefe00c1,
> -	0xbeff00c1, 0xee0a407a,
> -	0x000c0000, 0x00000000,
> -	0x7e000280, 0xbefe007a,
> -	0xbeff007b, 0xb8fb0742,
> -	0x847b997b, 0xb8fa3b05,
> -	0x807a817a, 0xbf0d997b,
> -	0xbfa20002, 0x847a897a,
> -	0xbfa00001, 0x847a8a7a,
> -	0xb8fb1e06, 0x847b8a7b,
> -	0x807a7b7a, 0x8b7bff7f,
> -	0x0000ffff, 0x807aff7a,
> -	0x00000200, 0x807a7e7a,
> -	0x827b807b, 0xd7610000,
> -	0x00010870, 0xd7610000,
> -	0x00010a71, 0xd7610000,
> -	0x00010c72, 0xd7610000,
> -	0x00010e73, 0xd7610000,
> -	0x00011074, 0xd7610000,
> -	0x00011275, 0xd7610000,
> -	0x00011476, 0xd7610000,
> -	0x00011677, 0xd7610000,
> -	0x00011a79, 0xd7610000,
> -	0x00011c7e, 0xd7610000,
> -	0x00011e7f, 0xd8500000,
> -	0x00000000, 0xd8500000,
> -	0x00000000, 0xd8500000,
> -	0x00000000, 0xd8500000,
> -	0x00000000, 0xd8500000,
> -	0x00000000, 0xd8500000,
> -	0x00000000, 0xd8500000,
> -	0x00000000, 0xd8500000,
> -	0x00000000, 0xbefe00ff,
> -	0x00003fff, 0xbeff0080,
> +	0x85788978, 0x936eff77,
> +	0x0002001a, 0xb96e081a,
> +	0xb9783244, 0xbe804a6c,
> +	0xb8faf802, 0xbf0d987a,
> +	0xbfa10001, 0xbfb00000,
> +	0x8b6dff6d, 0x0000ffff,
> +	0xbefa0080, 0xb97a0151,
> +	0xbeee007e, 0xbeef007f,
> +	0xbefe0180, 0xbefe4d84,
> +	0xbf8a0000, 0x8b7aff7f,
> +	0x04000000, 0x847a857a,
> +	0x8c6d7a6d, 0xbefa007e,
> +	0x8b7bff7f, 0x0000ffff,
> +	0xbefe00c1, 0xbeff00c1,
>   	0xee0a407a, 0x000c0000,
> -	0x00004000, 0xd760007a,
> -	0x00011d00, 0xd760007b,
> -	0x00011f00, 0xbefe007a,
> -	0xbeff007b, 0xbef4007e,
> -	0x8b75ff7f, 0x0000ffff,
> -	0x8c75ff75, 0x00040000,
> -	0xbef60080, 0xbef700ff,
> -	0x10807fac, 0xbef1007d,
> -	0xbef00080, 0xb8f30742,
> -	0x84739973, 0xbefe00c1,
> -	0x857d9973, 0x8b7d817d,
> -	0xbf06817d, 0xbfa20002,
> -	0xbeff0080, 0xbfa00002,
> -	0xbeff00c1, 0xbfa0000c,
> -	0xbef600ff, 0x01000000,
> -	0xc4068070, 0x008ce801,
> -	0x00008000, 0xc4068070,
> -	0x008ce802, 0x00010000,
> -	0xc4068070, 0x008ce803,
> -	0x00018000, 0xbfa0000b,
> -	0xbef600ff, 0x01000000,
> -	0xc4068070, 0x008ce801,
> -	0x00010000, 0xc4068070,
> -	0x008ce802, 0x00020000,
> -	0xc4068070, 0x008ce803,
> -	0x00030000, 0xb8f03b05,
> -	0x80708170, 0xbf0d9973,
> -	0xbfa20002, 0x84708970,
> -	0xbfa00001, 0x84708a70,
> -	0xb8fa1e06, 0x847a8a7a,
> -	0x80707a70, 0x8070ff70,
> -	0x00000200, 0xbef600ff,
> -	0x01000000, 0x7e000280,
> -	0x7e020280, 0x7e040280,
> -	0xbe804ec2, 0xbf94fffe,
> -	0xb8faf804, 0x8b7a847a,
> -	0x91788478, 0x8c787a78,
> -	0x917aff6d, 0x80000000,
> -	0xd7610002, 0x00010071,
> -	0xd7610002, 0x0001026c,
> -	0xd7610002, 0x0001047a,
> -	0xd7610002, 0x0001066e,
> -	0xd7610002, 0x0001086f,
> -	0xd7610002, 0x00010a78,
> -	0xd7610002, 0x00010e7b,
> +	0x00000000, 0x7e000280,
> +	0xbefe007a, 0xbeff007b,
> +	0xb8fb0742, 0x847b997b,
> +	0xb8fa3b05, 0x807a817a,
> +	0xbf0d997b, 0xbfa20002,
> +	0x847a897a, 0xbfa00001,
> +	0x847a8a7a, 0xb8fb1e06,
> +	0x847b8a7b, 0x807a7b7a,
> +	0x8b7bff7f, 0x0000ffff,
> +	0x807aff7a, 0x00000200,
> +	0x807a7e7a, 0x827b807b,
> +	0xd7610000, 0x00010870,
> +	0xd7610000, 0x00010a71,
> +	0xd7610000, 0x00010c72,
> +	0xd7610000, 0x00010e73,
> +	0xd7610000, 0x00011074,
> +	0xd7610000, 0x00011275,
> +	0xd7610000, 0x00011476,
> +	0xd7610000, 0x00011677,
> +	0xd7610000, 0x00011a79,
> +	0xd7610000, 0x00011c7e,
> +	0xd7610000, 0x00011e7f,
>   	0xd8500000, 0x00000000,
>   	0xd8500000, 0x00000000,
>   	0xd8500000, 0x00000000,
> @@ -3782,113 +3732,54 @@ static const uint32_t cwsr_trap_gfx12_hex[] = {
>   	0xd8500000, 0x00000000,
>   	0xd8500000, 0x00000000,
>   	0xd8500000, 0x00000000,
> -	0xb8faf811, 0xd7610002,
> -	0x00010c7a, 0xb8faf801,
> -	0xd7610002, 0x0001107a,
> -	0xb8faf814, 0xd7610002,
> -	0x0001127a, 0xb8faf815,
> -	0xd7610002, 0x0001147a,
> -	0xb8faf812, 0xd7610002,
> -	0x0001167a, 0xb8faf813,
> -	0xd7610002, 0x0001187a,
> -	0xb8faf802, 0xd7610002,
> -	0x00011a7a, 0xbefa50c1,
> -	0xbfc70000, 0xd7610002,
> -	0x00011c7a, 0xd8500000,
> -	0x00000000, 0xd8500000,
> -	0x00000000, 0xd8500000,
> -	0x00000000, 0xd8500000,
> -	0x00000000, 0xd8500000,
> -	0x00000000, 0xd8500000,
> -	0x00000000, 0xd8500000,
> -	0x00000000, 0xd8500000,
> -	0x00000000, 0xbefe00ff,
> -	0x0000ffff, 0xbeff0080,
> +	0xbefe00ff, 0x00003fff,
> +	0xbeff0080, 0xee0a407a,
> +	0x000c0000, 0x00004000,
> +	0xd760007a, 0x00011d00,
> +	0xd760007b, 0x00011f00,
> +	0xbefe007a, 0xbeff007b,
> +	0xbef4007e, 0x8b75ff7f,
> +	0x0000ffff, 0x8c75ff75,
> +	0x00040000, 0xbef60080,
> +	0xbef700ff, 0x10807fac,
> +	0xbef1007d, 0xbef00080,
> +	0xb8f30742, 0x84739973,
> +	0xbefe00c1, 0x857d9973,
> +	0x8b7d817d, 0xbf06817d,
> +	0xbfa20002, 0xbeff0080,
> +	0xbfa00002, 0xbeff00c1,
> +	0xbfa0000c, 0xbef600ff,
> +	0x01000000, 0xc4068070,
> +	0x008ce801, 0x00008000,
>   	0xc4068070, 0x008ce802,
> -	0x00000000, 0xbefe00c1,
> +	0x00010000, 0xc4068070,
> +	0x008ce803, 0x00018000,
> +	0xbfa0000b, 0xbef600ff,
> +	0x01000000, 0xc4068070,
> +	0x008ce801, 0x00010000,
> +	0xc4068070, 0x008ce802,
> +	0x00020000, 0xc4068070,
> +	0x008ce803, 0x00030000,
>   	0xb8f03b05, 0x80708170,
>   	0xbf0d9973, 0xbfa20002,
>   	0x84708970, 0xbfa00001,
>   	0x84708a70, 0xb8fa1e06,
>   	0x847a8a7a, 0x80707a70,
> +	0x8070ff70, 0x00000200,
>   	0xbef600ff, 0x01000000,
> -	0xbef90080, 0xbefd0080,
> -	0xbf800000, 0xbe804100,
> -	0xbe824102, 0xbe844104,
> -	0xbe864106, 0xbe884108,
> -	0xbe8a410a, 0xbe8c410c,
> -	0xbe8e410e, 0xbf068079,
> -	0xbfa10032, 0xd7610002,
> -	0x00010000, 0xd7610002,
> -	0x00010201, 0xd7610002,
> -	0x00010402, 0xd7610002,
> -	0x00010603, 0xd7610002,
> -	0x00010804, 0xd7610002,
> -	0x00010a05, 0xd7610002,
> -	0x00010c06, 0xd7610002,
> -	0x00010e07, 0xd7610002,
> -	0x00011008, 0xd7610002,
> -	0x00011209, 0xd7610002,
> -	0x0001140a, 0xd7610002,
> -	0x0001160b, 0xd7610002,
> -	0x0001180c, 0xd7610002,
> -	0x00011a0d, 0xd7610002,
> -	0x00011c0e, 0xd7610002,
> -	0x00011e0f, 0xd8500000,
> -	0x00000000, 0xd8500000,
> -	0x00000000, 0xd8500000,
> -	0x00000000, 0xd8500000,
> -	0x00000000, 0xd8500000,
> -	0x00000000, 0xd8500000,
> -	0x00000000, 0xd8500000,
> -	0x00000000, 0xd8500000,
> -	0x00000000, 0x80799079,
> -	0xbfa00038, 0xd7610002,
> -	0x00012000, 0xd7610002,
> -	0x00012201, 0xd7610002,
> -	0x00012402, 0xd7610002,
> -	0x00012603, 0xd7610002,
> -	0x00012804, 0xd7610002,
> -	0x00012a05, 0xd7610002,
> -	0x00012c06, 0xd7610002,
> -	0x00012e07, 0xd7610002,
> -	0x00013008, 0xd7610002,
> -	0x00013209, 0xd7610002,
> -	0x0001340a, 0xd7610002,
> -	0x0001360b, 0xd7610002,
> -	0x0001380c, 0xd7610002,
> -	0x00013a0d, 0xd7610002,
> -	0x00013c0e, 0xd7610002,
> -	0x00013e0f, 0xd8500000,
> -	0x00000000, 0xd8500000,
> -	0x00000000, 0xd8500000,
> -	0x00000000, 0xd8500000,
> -	0x00000000, 0xd8500000,
> -	0x00000000, 0xd8500000,
> -	0x00000000, 0xd8500000,
> -	0x00000000, 0xd8500000,
> -	0x00000000, 0x80799079,
> -	0xc4068070, 0x008ce802,
> -	0x00000000, 0x8070ff70,
> -	0x00000080, 0xbef90080,
> -	0x7e040280, 0x807d907d,
> -	0xbf0aff7d, 0x00000060,
> -	0xbfa2ff88, 0xbe804100,
> -	0xbe824102, 0xbe844104,
> -	0xbe864106, 0xbe884108,
> -	0xbe8a410a, 0xd7610002,
> -	0x00010000, 0xd7610002,
> -	0x00010201, 0xd7610002,
> -	0x00010402, 0xd7610002,
> -	0x00010603, 0xd7610002,
> -	0x00010804, 0xd7610002,
> -	0x00010a05, 0xd7610002,
> -	0x00010c06, 0xd7610002,
> -	0x00010e07, 0xd7610002,
> -	0x00011008, 0xd7610002,
> -	0x00011209, 0xd7610002,
> -	0x0001140a, 0xd7610002,
> -	0x0001160b, 0xd8500000,
> +	0x7e000280, 0x7e020280,
> +	0x7e040280, 0xbe804ec2,
> +	0xbf94fffe, 0xb8faf804,
> +	0x8b7a847a, 0x91788478,
> +	0x8c787a78, 0x917aff6d,
> +	0x80000000, 0xd7610002,
> +	0x00010071, 0xd7610002,
> +	0x0001026c, 0xd7610002,
> +	0x0001047a, 0xd7610002,
> +	0x0001066e, 0xd7610002,
> +	0x0001086f, 0xd7610002,
> +	0x00010a78, 0xd7610002,
> +	0x00010e7b, 0xd8500000,
>   	0x00000000, 0xd8500000,
>   	0x00000000, 0xd8500000,
>   	0x00000000, 0xd8500000,
> @@ -3896,273 +3787,389 @@ static const uint32_t cwsr_trap_gfx12_hex[] = {
>   	0x00000000, 0xd8500000,
>   	0x00000000, 0xd8500000,
>   	0x00000000, 0xd8500000,
> -	0x00000000, 0xc4068070,
> +	0x00000000, 0xb8faf811,
> +	0xd7610002, 0x00010c7a,
> +	0xb8faf801, 0xd7610002,
> +	0x0001107a, 0xb8faf814,
> +	0xd7610002, 0x0001127a,
> +	0xb8faf815, 0xd7610002,
> +	0x0001147a, 0xb8faf812,
> +	0xd7610002, 0x0001167a,
> +	0xb8faf813, 0xd7610002,
> +	0x0001187a, 0xb8faf802,
> +	0xd7610002, 0x00011a7a,
> +	0xbefa50c1, 0xbfc70000,
> +	0xd7610002, 0x00011c7a,
> +	0xd8500000, 0x00000000,
> +	0xd8500000, 0x00000000,
> +	0xd8500000, 0x00000000,
> +	0xd8500000, 0x00000000,
> +	0xd8500000, 0x00000000,
> +	0xd8500000, 0x00000000,
> +	0xd8500000, 0x00000000,
> +	0xd8500000, 0x00000000,
> +	0xbefe00ff, 0x0000ffff,
> +	0xbeff0080, 0xc4068070,
> +	0x008ce802, 0x00000000,
> +	0xbefe00c1, 0xb8f03b05,
> +	0x80708170, 0xbf0d9973,
> +	0xbfa20002, 0x84708970,
> +	0xbfa00001, 0x84708a70,
> +	0xb8fa1e06, 0x847a8a7a,
> +	0x80707a70, 0xbef600ff,
> +	0x01000000, 0xbef90080,
> +	0xbefd0080, 0xbf800000,
> +	0xbe804100, 0xbe824102,
> +	0xbe844104, 0xbe864106,
> +	0xbe884108, 0xbe8a410a,
> +	0xbe8c410c, 0xbe8e410e,
> +	0xbf068079, 0xbfa10032,
> +	0xd7610002, 0x00010000,
> +	0xd7610002, 0x00010201,
> +	0xd7610002, 0x00010402,
> +	0xd7610002, 0x00010603,
> +	0xd7610002, 0x00010804,
> +	0xd7610002, 0x00010a05,
> +	0xd7610002, 0x00010c06,
> +	0xd7610002, 0x00010e07,
> +	0xd7610002, 0x00011008,
> +	0xd7610002, 0x00011209,
> +	0xd7610002, 0x0001140a,
> +	0xd7610002, 0x0001160b,
> +	0xd7610002, 0x0001180c,
> +	0xd7610002, 0x00011a0d,
> +	0xd7610002, 0x00011c0e,
> +	0xd7610002, 0x00011e0f,
> +	0xd8500000, 0x00000000,
> +	0xd8500000, 0x00000000,
> +	0xd8500000, 0x00000000,
> +	0xd8500000, 0x00000000,
> +	0xd8500000, 0x00000000,
> +	0xd8500000, 0x00000000,
> +	0xd8500000, 0x00000000,
> +	0xd8500000, 0x00000000,
> +	0x80799079, 0xbfa00038,
> +	0xd7610002, 0x00012000,
> +	0xd7610002, 0x00012201,
> +	0xd7610002, 0x00012402,
> +	0xd7610002, 0x00012603,
> +	0xd7610002, 0x00012804,
> +	0xd7610002, 0x00012a05,
> +	0xd7610002, 0x00012c06,
> +	0xd7610002, 0x00012e07,
> +	0xd7610002, 0x00013008,
> +	0xd7610002, 0x00013209,
> +	0xd7610002, 0x0001340a,
> +	0xd7610002, 0x0001360b,
> +	0xd7610002, 0x0001380c,
> +	0xd7610002, 0x00013a0d,
> +	0xd7610002, 0x00013c0e,
> +	0xd7610002, 0x00013e0f,
> +	0xd8500000, 0x00000000,
> +	0xd8500000, 0x00000000,
> +	0xd8500000, 0x00000000,
> +	0xd8500000, 0x00000000,
> +	0xd8500000, 0x00000000,
> +	0xd8500000, 0x00000000,
> +	0xd8500000, 0x00000000,
> +	0xd8500000, 0x00000000,
> +	0x80799079, 0xc4068070,
>   	0x008ce802, 0x00000000,
> -	0xbefe00c1, 0x857d9973,
> -	0x8b7d817d, 0xbf06817d,
> -	0xbfa20002, 0xbeff0080,
> -	0xbfa00001, 0xbeff00c1,
> -	0xb8fb4306, 0x8b7bc17b,
> -	0xbfa10044, 0x8b7aff6d,
> -	0x80000000, 0xbfa10041,
> -	0x847b897b, 0xbef6007b,
> -	0xb8f03b05, 0x80708170,
> -	0xbf0d9973, 0xbfa20002,
> -	0x84708970, 0xbfa00001,
> -	0x84708a70, 0xb8fa1e06,
> -	0x847a8a7a, 0x80707a70,
> -	0x8070ff70, 0x00000200,
>   	0x8070ff70, 0x00000080,
> -	0xbef600ff, 0x01000000,
> -	0xd71f0000, 0x000100c1,
> -	0xd7200000, 0x000200c1,
> -	0x16000084, 0x857d9973,
> -	0x8b7d817d, 0xbf06817d,
> -	0xbefd0080, 0xbfa20013,
> -	0xbe8300ff, 0x00000080,
> -	0xbf800000, 0xbf800000,
> -	0xbf800000, 0xd8d80000,
> -	0x01000000, 0xbf8a0000,
> -	0xc4068070, 0x008ce801,
> -	0x00000000, 0x807d037d,
> -	0x80700370, 0xd5250000,
> -	0x0001ff00, 0x00000080,
> -	0xbf0a7b7d, 0xbfa2fff3,
> -	0xbfa00012, 0xbe8300ff,
> -	0x00000100, 0xbf800000,
> +	0xbef90080, 0x7e040280,
> +	0x807d907d, 0xbf0aff7d,
> +	0x00000060, 0xbfa2ff88,
> +	0xbe804100, 0xbe824102,
> +	0xbe844104, 0xbe864106,
> +	0xbe884108, 0xbe8a410a,
> +	0xd7610002, 0x00010000,
> +	0xd7610002, 0x00010201,
> +	0xd7610002, 0x00010402,
> +	0xd7610002, 0x00010603,
> +	0xd7610002, 0x00010804,
> +	0xd7610002, 0x00010a05,
> +	0xd7610002, 0x00010c06,
> +	0xd7610002, 0x00010e07,
> +	0xd7610002, 0x00011008,
> +	0xd7610002, 0x00011209,
> +	0xd7610002, 0x0001140a,
> +	0xd7610002, 0x0001160b,
> +	0xd8500000, 0x00000000,
> +	0xd8500000, 0x00000000,
> +	0xd8500000, 0x00000000,
> +	0xd8500000, 0x00000000,
> +	0xd8500000, 0x00000000,
> +	0xd8500000, 0x00000000,
> +	0xd8500000, 0x00000000,
> +	0xd8500000, 0x00000000,
> +	0xc4068070, 0x008ce802,
> +	0x00000000, 0xbefe00c1,
> +	0x857d9973, 0x8b7d817d,
> +	0xbf06817d, 0xbfa20002,
> +	0xbeff0080, 0xbfa00001,
> +	0xbeff00c1, 0xb8fb4306,
> +	0x8b7bc17b, 0xbfa10044,
> +	0x8b7aff6d, 0x80000000,
> +	0xbfa10041, 0x847b897b,
> +	0xbef6007b, 0xb8f03b05,
> +	0x80708170, 0xbf0d9973,
> +	0xbfa20002, 0x84708970,
> +	0xbfa00001, 0x84708a70,
> +	0xb8fa1e06, 0x847a8a7a,
> +	0x80707a70, 0x8070ff70,
> +	0x00000200, 0x8070ff70,
> +	0x00000080, 0xbef600ff,
> +	0x01000000, 0xd71f0000,
> +	0x000100c1, 0xd7200000,
> +	0x000200c1, 0x16000084,
> +	0x857d9973, 0x8b7d817d,
> +	0xbf06817d, 0xbefd0080,
> +	0xbfa20013, 0xbe8300ff,
> +	0x00000080, 0xbf800000,
>   	0xbf800000, 0xbf800000,
>   	0xd8d80000, 0x01000000,
>   	0xbf8a0000, 0xc4068070,
>   	0x008ce801, 0x00000000,
>   	0x807d037d, 0x80700370,
>   	0xd5250000, 0x0001ff00,
> -	0x00000100, 0xbf0a7b7d,
> -	0xbfa2fff3, 0xbefe00c1,
> -	0x857d9973, 0x8b7d817d,
> -	0xbf06817d, 0xbfa20004,
> -	0xbef000ff, 0x00000200,
> -	0xbeff0080, 0xbfa00003,
> -	0xbef000ff, 0x00000400,
> -	0xbeff00c1, 0xb8fb3b05,
> -	0x807b817b, 0x847b827b,
> -	0x857d9973, 0x8b7d817d,
> -	0xbf06817d, 0xbfa2001b,
> -	0xbef600ff, 0x01000000,
> -	0xbefd0084, 0xbf0a7b7d,
> -	0xbfa10040, 0x7e008700,
> -	0x7e028701, 0x7e048702,
> -	0x7e068703, 0xc4068070,
> -	0x008ce800, 0x00000000,
> +	0x00000080, 0xbf0a7b7d,
> +	0xbfa2fff3, 0xbfa00012,
> +	0xbe8300ff, 0x00000100,
> +	0xbf800000, 0xbf800000,
> +	0xbf800000, 0xd8d80000,
> +	0x01000000, 0xbf8a0000,
>   	0xc4068070, 0x008ce801,
> -	0x00008000, 0xc4068070,
> -	0x008ce802, 0x00010000,
> -	0xc4068070, 0x008ce803,
> -	0x00018000, 0x807d847d,
> -	0x8070ff70, 0x00000200,
> -	0xbf0a7b7d, 0xbfa2ffeb,
> -	0xbfa0002a, 0xbef600ff,
> +	0x00000000, 0x807d037d,
> +	0x80700370, 0xd5250000,
> +	0x0001ff00, 0x00000100,
> +	0xbf0a7b7d, 0xbfa2fff3,
> +	0xbefe00c1, 0x857d9973,
> +	0x8b7d817d, 0xbf06817d,
> +	0xbfa20004, 0xbef000ff,
> +	0x00000200, 0xbeff0080,
> +	0xbfa00003, 0xbef000ff,
> +	0x00000400, 0xbeff00c1,
> +	0xb8fb3b05, 0x807b817b,
> +	0x847b827b, 0x857d9973,
> +	0x8b7d817d, 0xbf06817d,
> +	0xbfa2001b, 0xbef600ff,
>   	0x01000000, 0xbefd0084,
> -	0xbf0a7b7d, 0xbfa10015,
> +	0xbf0a7b7d, 0xbfa10040,
>   	0x7e008700, 0x7e028701,
>   	0x7e048702, 0x7e068703,
>   	0xc4068070, 0x008ce800,
>   	0x00000000, 0xc4068070,
> -	0x008ce801, 0x00010000,
> +	0x008ce801, 0x00008000,
>   	0xc4068070, 0x008ce802,
> -	0x00020000, 0xc4068070,
> -	0x008ce803, 0x00030000,
> +	0x00010000, 0xc4068070,
> +	0x008ce803, 0x00018000,
>   	0x807d847d, 0x8070ff70,
> -	0x00000400, 0xbf0a7b7d,
> -	0xbfa2ffeb, 0xb8fb1e06,
> -	0x8b7bc17b, 0xbfa1000d,
> -	0x847b837b, 0x807b7d7b,
> -	0xbefe00c1, 0xbeff0080,
> -	0x7e008700, 0xc4068070,
> -	0x008ce800, 0x00000000,
> -	0x807d817d, 0x8070ff70,
> -	0x00000080, 0xbf0a7b7d,
> -	0xbfa2fff7, 0xbfa0016e,
> -	0xbef4007e, 0x8b75ff7f,
> -	0x0000ffff, 0x8c75ff75,
> -	0x00040000, 0xbef60080,
> -	0xbef700ff, 0x10807fac,
> -	0xbef1007f, 0xb8f20742,
> -	0x84729972, 0x8b6eff7f,
> -	0x04000000, 0xbfa1003b,
> -	0xbefe00c1, 0x857d9972,
> -	0x8b7d817d, 0xbf06817d,
> -	0xbfa20002, 0xbeff0080,
> -	0xbfa00001, 0xbeff00c1,
> -	0xb8ef4306, 0x8b6fc16f,
> -	0xbfa10030, 0x846f896f,
> -	0xbef6006f, 0xb8f83b05,
> -	0x80788178, 0xbf0d9972,
> -	0xbfa20002, 0x84788978,
> -	0xbfa00001, 0x84788a78,
> -	0xb8ee1e06, 0x846e8a6e,
> -	0x80786e78, 0x8078ff78,
> -	0x00000200, 0x8078ff78,
> -	0x00000080, 0xbef600ff,
> -	0x01000000, 0x857d9972,
> -	0x8b7d817d, 0xbf06817d,
> -	0xbefd0080, 0xbfa2000d,
> -	0xc4050078, 0x0080e800,
> -	0x00000000, 0xbf8a0000,
> -	0xdac00000, 0x00000000,
> -	0x807dff7d, 0x00000080,
> -	0x8078ff78, 0x00000080,
> -	0xbf0a6f7d, 0xbfa2fff4,
> -	0xbfa0000c, 0xc4050078,
> -	0x0080e800, 0x00000000,
> -	0xbf8a0000, 0xdac00000,
> -	0x00000000, 0x807dff7d,
> -	0x00000100, 0x8078ff78,
> -	0x00000100, 0xbf0a6f7d,
> -	0xbfa2fff4, 0xbef80080,
> -	0xbefe00c1, 0x857d9972,
> -	0x8b7d817d, 0xbf06817d,
> -	0xbfa20002, 0xbeff0080,
> -	0xbfa00001, 0xbeff00c1,
> -	0xb8ef3b05, 0x806f816f,
> -	0x846f826f, 0x857d9972,
> -	0x8b7d817d, 0xbf06817d,
> -	0xbfa2002c, 0xbef600ff,
> -	0x01000000, 0xbeee0078,
> -	0x8078ff78, 0x00000200,
> -	0xbefd0084, 0xbf0a6f7d,
> -	0xbfa10061, 0xc4050078,
> -	0x008ce800, 0x00000000,
> -	0xc4050078, 0x008ce801,
> -	0x00008000, 0xc4050078,
> -	0x008ce802, 0x00010000,
> -	0xc4050078, 0x008ce803,
> -	0x00018000, 0xbf8a0000,
> -	0x7e008500, 0x7e028501,
> -	0x7e048502, 0x7e068503,
> -	0x807d847d, 0x8078ff78,
> -	0x00000200, 0xbf0a6f7d,
> -	0xbfa2ffea, 0xc405006e,
> -	0x008ce800, 0x00000000,
> -	0xc405006e, 0x008ce801,
> -	0x00008000, 0xc405006e,
> -	0x008ce802, 0x00010000,
> -	0xc405006e, 0x008ce803,
> -	0x00018000, 0xbf8a0000,
> -	0xbfa0003d, 0xbef600ff,
> -	0x01000000, 0xbeee0078,
> -	0x8078ff78, 0x00000400,
> -	0xbefd0084, 0xbf0a6f7d,
> -	0xbfa10016, 0xc4050078,
> -	0x008ce800, 0x00000000,
> -	0xc4050078, 0x008ce801,
> -	0x00010000, 0xc4050078,
> -	0x008ce802, 0x00020000,
> -	0xc4050078, 0x008ce803,
> -	0x00030000, 0xbf8a0000,
> -	0x7e008500, 0x7e028501,
> -	0x7e048502, 0x7e068503,
> -	0x807d847d, 0x8078ff78,
> -	0x00000400, 0xbf0a6f7d,
> -	0xbfa2ffea, 0xb8ef1e06,
> -	0x8b6fc16f, 0xbfa1000f,
> -	0x846f836f, 0x806f7d6f,
> -	0xbefe00c1, 0xbeff0080,
> -	0xc4050078, 0x008ce800,
> -	0x00000000, 0xbf8a0000,
> -	0x7e008500, 0x807d817d,
> -	0x8078ff78, 0x00000080,
> -	0xbf0a6f7d, 0xbfa2fff6,
> -	0xbeff00c1, 0xc405006e,
> +	0x00000200, 0xbf0a7b7d,
> +	0xbfa2ffeb, 0xbfa0002a,
> +	0xbef600ff, 0x01000000,
> +	0xbefd0084, 0xbf0a7b7d,
> +	0xbfa10015, 0x7e008700,
> +	0x7e028701, 0x7e048702,
> +	0x7e068703, 0xc4068070,
>   	0x008ce800, 0x00000000,
> -	0xc405006e, 0x008ce801,
> -	0x00010000, 0xc405006e,
> +	0xc4068070, 0x008ce801,
> +	0x00010000, 0xc4068070,
>   	0x008ce802, 0x00020000,
> -	0xc405006e, 0x008ce803,
> -	0x00030000, 0xbf8a0000,
> +	0xc4068070, 0x008ce803,
> +	0x00030000, 0x807d847d,
> +	0x8070ff70, 0x00000400,
> +	0xbf0a7b7d, 0xbfa2ffeb,
> +	0xb8fb1e06, 0x8b7bc17b,
> +	0xbfa1000d, 0x847b837b,
> +	0x807b7d7b, 0xbefe00c1,
> +	0xbeff0080, 0x7e008700,
> +	0xc4068070, 0x008ce800,
> +	0x00000000, 0x807d817d,
> +	0x8070ff70, 0x00000080,
> +	0xbf0a7b7d, 0xbfa2fff7,
> +	0xbfa00171, 0xbef4007e,
> +	0x8b75ff7f, 0x0000ffff,
> +	0x8c75ff75, 0x00040000,
> +	0xbef60080, 0xbef700ff,
> +	0x10807fac, 0xbef1007f,
> +	0xb8f20742, 0x84729972,
> +	0x8b6eff7f, 0x04000000,
> +	0xbfa1003b, 0xbefe00c1,
> +	0x857d9972, 0x8b7d817d,
> +	0xbf06817d, 0xbfa20002,
> +	0xbeff0080, 0xbfa00001,
> +	0xbeff00c1, 0xb8ef4306,
> +	0x8b6fc16f, 0xbfa10030,
> +	0x846f896f, 0xbef6006f,
>   	0xb8f83b05, 0x80788178,
>   	0xbf0d9972, 0xbfa20002,
>   	0x84788978, 0xbfa00001,
>   	0x84788a78, 0xb8ee1e06,
>   	0x846e8a6e, 0x80786e78,
>   	0x8078ff78, 0x00000200,
> -	0x80f8ff78, 0x00000050,
> +	0x8078ff78, 0x00000080,
>   	0xbef600ff, 0x01000000,
> -	0xbefd00ff, 0x0000006c,
> -	0x80f89078, 0xf462403a,
> -	0xf0000000, 0xbf8a0000,
> -	0x80fd847d, 0xbf800000,
> -	0xbe804300, 0xbe824302,
> -	0x80f8a078, 0xf462603a,
> -	0xf0000000, 0xbf8a0000,
> -	0x80fd887d, 0xbf800000,
> -	0xbe804300, 0xbe824302,
> -	0xbe844304, 0xbe864306,
> -	0x80f8c078, 0xf462803a,
> -	0xf0000000, 0xbf8a0000,
> -	0x80fd907d, 0xbf800000,
> -	0xbe804300, 0xbe824302,
> -	0xbe844304, 0xbe864306,
> -	0xbe884308, 0xbe8a430a,
> -	0xbe8c430c, 0xbe8e430e,
> -	0xbf06807d, 0xbfa1fff0,
> -	0xb980f801, 0x00000000,
> -	0xb8f83b05, 0x80788178,
> -	0xbf0d9972, 0xbfa20002,
> -	0x84788978, 0xbfa00001,
> -	0x84788a78, 0xb8ee1e06,
> -	0x846e8a6e, 0x80786e78,
> +	0x857d9972, 0x8b7d817d,
> +	0xbf06817d, 0xbefd0080,
> +	0xbfa2000d, 0xc4050078,
> +	0x0080e800, 0x00000000,
> +	0xbf8a0000, 0xdac00000,
> +	0x00000000, 0x807dff7d,
> +	0x00000080, 0x8078ff78,
> +	0x00000080, 0xbf0a6f7d,
> +	0xbfa2fff4, 0xbfa0000c,
> +	0xc4050078, 0x0080e800,
> +	0x00000000, 0xbf8a0000,
> +	0xdac00000, 0x00000000,
> +	0x807dff7d, 0x00000100,
> +	0x8078ff78, 0x00000100,
> +	0xbf0a6f7d, 0xbfa2fff4,
> +	0xbef80080, 0xbefe00c1,
> +	0x857d9972, 0x8b7d817d,
> +	0xbf06817d, 0xbfa20002,
> +	0xbeff0080, 0xbfa00001,
> +	0xbeff00c1, 0xb8ef3b05,
> +	0x806f816f, 0x846f826f,
> +	0x857d9972, 0x8b7d817d,
> +	0xbf06817d, 0xbfa2002c,
> +	0xbef600ff, 0x01000000,
> +	0xbeee0078, 0x8078ff78,
> +	0x00000200, 0xbefd0084,
> +	0xbf0a6f7d, 0xbfa10061,
> +	0xc4050078, 0x008ce800,
> +	0x00000000, 0xc4050078,
> +	0x008ce801, 0x00008000,
> +	0xc4050078, 0x008ce802,
> +	0x00010000, 0xc4050078,
> +	0x008ce803, 0x00018000,
> +	0xbf8a0000, 0x7e008500,
> +	0x7e028501, 0x7e048502,
> +	0x7e068503, 0x807d847d,
>   	0x8078ff78, 0x00000200,
> +	0xbf0a6f7d, 0xbfa2ffea,
> +	0xc405006e, 0x008ce800,
> +	0x00000000, 0xc405006e,
> +	0x008ce801, 0x00008000,
> +	0xc405006e, 0x008ce802,
> +	0x00010000, 0xc405006e,
> +	0x008ce803, 0x00018000,
> +	0xbf8a0000, 0xbfa0003d,
>   	0xbef600ff, 0x01000000,
> -	0xbeff0071, 0xf4621bfa,
> +	0xbeee0078, 0x8078ff78,
> +	0x00000400, 0xbefd0084,
> +	0xbf0a6f7d, 0xbfa10016,
> +	0xc4050078, 0x008ce800,
> +	0x00000000, 0xc4050078,
> +	0x008ce801, 0x00010000,
> +	0xc4050078, 0x008ce802,
> +	0x00020000, 0xc4050078,
> +	0x008ce803, 0x00030000,
> +	0xbf8a0000, 0x7e008500,
> +	0x7e028501, 0x7e048502,
> +	0x7e068503, 0x807d847d,
> +	0x8078ff78, 0x00000400,
> +	0xbf0a6f7d, 0xbfa2ffea,
> +	0xb8ef1e06, 0x8b6fc16f,
> +	0xbfa1000f, 0x846f836f,
> +	0x806f7d6f, 0xbefe00c1,
> +	0xbeff0080, 0xc4050078,
> +	0x008ce800, 0x00000000,
> +	0xbf8a0000, 0x7e008500,
> +	0x807d817d, 0x8078ff78,
> +	0x00000080, 0xbf0a6f7d,
> +	0xbfa2fff6, 0xbeff00c1,
> +	0xc405006e, 0x008ce800,
> +	0x00000000, 0xc405006e,
> +	0x008ce801, 0x00010000,
> +	0xc405006e, 0x008ce802,
> +	0x00020000, 0xc405006e,
> +	0x008ce803, 0x00030000,
> +	0xbf8a0000, 0xb8f83b05,
> +	0x80788178, 0xbf0d9972,
> +	0xbfa20002, 0x84788978,
> +	0xbfa00001, 0x84788a78,
> +	0xb8ee1e06, 0x846e8a6e,
> +	0x80786e78, 0x8078ff78,
> +	0x00000200, 0x80f8ff78,
> +	0x00000050, 0xbef600ff,
> +	0x01000000, 0xbefd00ff,
> +	0x0000006c, 0x80f89078,
> +	0xf462403a, 0xf0000000,
> +	0xbf8a0000, 0x80fd847d,
> +	0xbf800000, 0xbe804300,
> +	0xbe824302, 0x80f8a078,
> +	0xf462603a, 0xf0000000,
> +	0xbf8a0000, 0x80fd887d,
> +	0xbf800000, 0xbe804300,
> +	0xbe824302, 0xbe844304,
> +	0xbe864306, 0x80f8c078,
> +	0xf462803a, 0xf0000000,
> +	0xbf8a0000, 0x80fd907d,
> +	0xbf800000, 0xbe804300,
> +	0xbe824302, 0xbe844304,
> +	0xbe864306, 0xbe884308,
> +	0xbe8a430a, 0xbe8c430c,
> +	0xbe8e430e, 0xbf06807d,
> +	0xbfa1fff0, 0xb980f801,
> +	0x00000000, 0xb8f83b05,
> +	0x80788178, 0xbf0d9972,
> +	0xbfa20002, 0x84788978,
> +	0xbfa00001, 0x84788a78,
> +	0xb8ee1e06, 0x846e8a6e,
> +	0x80786e78, 0x8078ff78,
> +	0x00000200, 0xbef600ff,
> +	0x01000000, 0xbeff0071,
> +	0xf4621bfa, 0xf0000000,
> +	0x80788478, 0xf4621b3a,
>   	0xf0000000, 0x80788478,
> -	0xf4621b3a, 0xf0000000,
> -	0x80788478, 0xf4621b7a,
> +	0xf4621b7a, 0xf0000000,
> +	0x80788478, 0xf4621c3a,
>   	0xf0000000, 0x80788478,
> -	0xf4621c3a, 0xf0000000,
> -	0x80788478, 0xf4621c7a,
> +	0xf4621c7a, 0xf0000000,
> +	0x80788478, 0xf4621eba,
>   	0xf0000000, 0x80788478,
> -	0xf4621eba, 0xf0000000,
> -	0x80788478, 0xf4621efa,
> +	0xf4621efa, 0xf0000000,
> +	0x80788478, 0xf4621e7a,
>   	0xf0000000, 0x80788478,
> -	0xf4621e7a, 0xf0000000,
> -	0x80788478, 0xf4621cfa,
> +	0xf4621cfa, 0xf0000000,
> +	0x80788478, 0xf4621bba,
>   	0xf0000000, 0x80788478,
> +	0xbf8a0000, 0xb96ef814,
>   	0xf4621bba, 0xf0000000,
>   	0x80788478, 0xbf8a0000,
> -	0xb96ef814, 0xf4621bba,
> +	0xb96ef815, 0xf4621bba,
>   	0xf0000000, 0x80788478,
> -	0xbf8a0000, 0xb96ef815,
> +	0xbf8a0000, 0xb96ef812,
>   	0xf4621bba, 0xf0000000,
>   	0x80788478, 0xbf8a0000,
> -	0xb96ef812, 0xf4621bba,
> +	0xb96ef813, 0x8b6eff7f,
> +	0x04000000, 0xbfa1000d,
> +	0x80788478, 0xf4621bba,
>   	0xf0000000, 0x80788478,
> -	0xbf8a0000, 0xb96ef813,
> -	0x8b6eff7f, 0x04000000,
> -	0xbfa1000d, 0x80788478,
> -	0xf4621bba, 0xf0000000,
> -	0x80788478, 0xbf8a0000,
> -	0xbf0d806e, 0xbfa10006,
> -	0x856e906e, 0x8b6e6e6e,
> -	0xbfa10003, 0xbe804ec1,
> -	0x816ec16e, 0xbfa0fffb,
> -	0xbefd006f, 0xbefe0070,
> -	0xbeff0071, 0xb97b2011,
> -	0x857b867b, 0xb97b0191,
> -	0x857b827b, 0xb97bba11,
> -	0xb973f801, 0xb8ee3b05,
> -	0x806e816e, 0xbf0d9972,
> -	0xbfa20002, 0x846e896e,
> -	0xbfa00001, 0x846e8a6e,
> -	0xb8ef1e06, 0x846f8a6f,
> -	0x806e6f6e, 0x806eff6e,
> -	0x00000200, 0x806e746e,
> -	0x826f8075, 0x8b6fff6f,
> -	0x0000ffff, 0xf4605c37,
> -	0xf8000050, 0xf4605d37,
> -	0xf8000060, 0xf4601e77,
> -	0xf8000074, 0xbf8a0000,
> -	0x8b6dff6d, 0x0000ffff,
> -	0x8bfe7e7e, 0x8bea6a6a,
> +	0xbf8a0000, 0xbf0d806e,
> +	0xbfa10006, 0x856e906e,
> +	0x8b6e6e6e, 0xbfa10003,
> +	0xbe804ec1, 0x816ec16e,
> +	0xbfa0fffb, 0xbefd006f,
> +	0xbefe0070, 0xbeff0071,
> +	0xb97b2011, 0x857b867b,
> +	0xb97b0191, 0x857b827b,
> +	0xb97bba11, 0xb973f801,
> +	0xb8ee3b05, 0x806e816e,
> +	0xbf0d9972, 0xbfa20002,
> +	0x846e896e, 0xbfa00001,
> +	0x846e8a6e, 0xb8ef1e06,
> +	0x846f8a6f, 0x806e6f6e,
> +	0x806eff6e, 0x00000200,
> +	0x806e746e, 0x826f8075,
> +	0x8b6fff6f, 0x0000ffff,
> +	0xf4605c37, 0xf8000050,
> +	0xf4605d37, 0xf8000060,
> +	0xf4601e77, 0xf8000074,
> +	0xbf8a0000, 0x8b6dff6d,
> +	0x0000ffff, 0x8bfe7e7e,
> +	0x8bea6a6a, 0x936eff77,
> +	0x0002001a, 0xb96e081a,
>   	0xb97af804, 0xbe804ec2,
>   	0xbf94fffe, 0xbe804a6c,
>   	0xbe804ec2, 0xbf94fffe,
> 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 5a1a1b1f897f..f756d3b73281 100644
> --- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx12.asm
> +++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx12.asm
> @@ -78,9 +78,16 @@ var SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_2_SHIFT	= SQ_WAVE_EXCP_FLAG_PRIV_ILLEGAL
>   var SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_2_SIZE	= SQ_WAVE_EXCP_FLAG_PRIV_HOST_TRAP_SHIFT - SQ_WAVE_EXCP_FLAG_PRIV_ILLEGAL_INST_SHIFT
>   var SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_3_SHIFT	= SQ_WAVE_EXCP_FLAG_PRIV_WAVE_START_SHIFT
>   var SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_3_SIZE	= 32 - SQ_WAVE_EXCP_FLAG_PRIV_RESTORE_PART_3_SHIFT
> +
> +var SQ_WAVE_SCHED_MODE_DEP_MODE_SHIFT		= 0
> +var SQ_WAVE_SCHED_MODE_DEP_MODE_SIZE		= 2
> +
>   var BARRIER_STATE_SIGNAL_OFFSET			= 16
>   var BARRIER_STATE_VALID_OFFSET			= 0
>   
> +var TTMP11_SCHED_MODE_SHIFT			= 26
> +var TTMP11_SCHED_MODE_SIZE			= 2
> +var TTMP11_SCHED_MODE_MASK			= 0xC000000
>   var TTMP11_DEBUG_TRAP_ENABLED_SHIFT		= 23
>   var TTMP11_DEBUG_TRAP_ENABLED_MASK		= 0x800000
>   
> @@ -160,8 +167,19 @@ L_JUMP_TO_RESTORE:
>   	s_branch	L_RESTORE
>   
>   L_SKIP_RESTORE:
> +	// Assume most relaxed scheduling mode is set. Save and revert to normal mode.
> +	s_getreg_b32	ttmp2, hwreg(HW_REG_WAVE_SCHED_MODE)
> +	s_wait_alu	0
> +	s_setreg_imm32_b32	hwreg(HW_REG_WAVE_SCHED_MODE, \
> +		SQ_WAVE_SCHED_MODE_DEP_MODE_SHIFT, SQ_WAVE_SCHED_MODE_DEP_MODE_SIZE), 0
> +
>   	s_getreg_b32	s_save_state_priv, hwreg(HW_REG_WAVE_STATE_PRIV)	//save STATUS since we will change SCC
>   
> +	// Save SCHED_MODE[1:0] into ttmp11[27:26].
> +	s_andn2_b32	ttmp11, ttmp11, TTMP11_SCHED_MODE_MASK
> +	s_lshl_b32	ttmp2, ttmp2, TTMP11_SCHED_MODE_SHIFT
> +	s_or_b32	ttmp11, ttmp11, ttmp2
> +
>   	// Clear SPI_PRIO: do not save with elevated priority.
>   	// Clear ECC_ERR: prevents SQC store and triggers FATAL_HALT if setreg'd.
>   	s_andn2_b32	s_save_state_priv, s_save_state_priv, SQ_WAVE_STATE_PRIV_ALWAYS_CLEAR_MASK
> @@ -287,6 +305,10 @@ L_EXIT_TRAP:
>   	// STATE_PRIV.BARRIER_COMPLETE may have changed since we read it.
>   	// Only restore fields which the trap handler changes.
>   	s_lshr_b32	s_save_state_priv, s_save_state_priv, SQ_WAVE_STATE_PRIV_SCC_SHIFT
> +
> +	// Assume relaxed scheduling mode after this point.
> +	restore_sched_mode(ttmp2)
> +
>   	s_setreg_b32	hwreg(HW_REG_WAVE_STATE_PRIV, SQ_WAVE_STATE_PRIV_SCC_SHIFT, \
>   		SQ_WAVE_STATE_PRIV_POISON_ERR_SHIFT - SQ_WAVE_STATE_PRIV_SCC_SHIFT + 1), s_save_state_priv
>   
> @@ -1043,6 +1065,9 @@ L_SKIP_BARRIER_RESTORE:
>   	s_and_b64	exec, exec, exec					// Restore STATUS.EXECZ, not writable by s_setreg_b32
>   	s_and_b64	vcc, vcc, vcc						// Restore STATUS.VCCZ, not writable by s_setreg_b32
>   
> +	// Assume relaxed scheduling mode after this point.
> +	restore_sched_mode(s_restore_tmp)
> +
>   	s_setreg_b32	hwreg(HW_REG_WAVE_STATE_PRIV), s_restore_state_priv	// SCC is included, which is changed by previous salu
>   
>   	// Make barrier and LDS state visible to all waves in the group.
> @@ -1134,3 +1159,9 @@ function valu_sgpr_hazard
>   	end
>   #endif
>   end
> +
> +function restore_sched_mode(s_tmp)
> +	s_bfe_u32	s_tmp, ttmp11, (TTMP11_SCHED_MODE_SHIFT | (TTMP11_SCHED_MODE_SIZE << 0x10))
> +	s_setreg_b32	hwreg(HW_REG_WAVE_SCHED_MODE, SQ_WAVE_SCHED_MODE_DEP_MODE_SHIFT, \
> +		 SQ_WAVE_SCHED_MODE_DEP_MODE_SIZE), s_tmp
> +end


^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2025-11-14 14:27 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2025-11-10 16:48 [PATCH] drm/amdkfd: Trap handler support for expert scheduling mode Jay Cornwall
2025-11-14 14:27 ` Lancelot SIX

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox