[PATCH v2] amdkfd: pass debug exceptions to second-level trap handler

[Deucher, Alexander]

[AMD Official Use Only - General]

Acked-by: Alex Deucher <alexander.deucher at amd.com>
________________________________
From: amd-gfx <amd-gfx-bounces at lists.freedesktop.org> on behalf of Laurent Morichetti <laurent.morichetti at amd.com>
Sent: Thursday, February 1, 2024 4:33 PM
To: amd-gfx at lists.freedesktop.org <amd-gfx at lists.freedesktop.org>
Cc: jay.cornwall.six at amd.com <jay.cornwall.six at amd.com>; Morichetti, Laurent <Laurent.Morichetti at amd.com>; Six, Lancelot <Lancelot.Six at amd.com>; Cornwall, Jay <Jay.Cornwall at amd.com>
Subject: [PATCH v2] amdkfd: pass debug exceptions to second-level trap handler

Call the 2nd level trap handler if the cwsr handler is entered with any
one of wave_start, wave_end, or trap_after_inst exceptions.

Signed-off-by: Laurent Morichetti <laurent.morichetti at amd.com>
Tested-by: Lancelot Six <lancelot.six at amd.com>
Reviewed-by: Jay Cornwall <jay.cornwall at amd.com>
---
 drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h  |  2 +-
 .../drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm  | 17 ++++++++++++++++-
 2 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
index d1caaf0e6a7c..2e9b64edb8d2 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
@@ -2518,7 +2518,7 @@ static const uint32_t cwsr_trap_gfx11_hex[] = {
         0x8b6eff7b, 0x00000400,
         0xbfa20045, 0xbf830010,
         0xb8fbf803, 0xbfa0fffa,
-       0x8b6eff7b, 0x00000900,
+       0x8b6eff7b, 0x00160900,
         0xbfa20015, 0x8b6eff7b,
         0x000071ff, 0xbfa10008,
         0x8b6fff7b, 0x00007080,
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
index 71b3dc0c7363..7568ff3af978 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
@@ -81,6 +81,11 @@ var SQ_WAVE_TRAPSTS_POST_SAVECTX_SHIFT               = 11
 var SQ_WAVE_TRAPSTS_POST_SAVECTX_SIZE           = 21
 var SQ_WAVE_TRAPSTS_ILLEGAL_INST_MASK           = 0x800
 var SQ_WAVE_TRAPSTS_EXCP_HI_MASK                = 0x7000
+#if ASIC_FAMILY >= CHIP_PLUM_BONITO
+var SQ_WAVE_TRAPSTS_WAVE_START_MASK            = 0x20000
+var SQ_WAVE_TRAPSTS_WAVE_END_MASK              = 0x40000
+var SQ_WAVE_TRAPSTS_TRAP_AFTER_INST_MASK       = 0x100000
+#endif

 var SQ_WAVE_MODE_EXCP_EN_SHIFT                  = 12
 var SQ_WAVE_MODE_EXCP_EN_ADDR_WATCH_SHIFT       = 19
@@ -92,6 +97,16 @@ var SQ_WAVE_IB_STS_RCNT_FIRST_REPLAY_MASK    = 0x003F8000

 var SQ_WAVE_MODE_DEBUG_EN_MASK                  = 0x800

+#if ASIC_FAMILY < CHIP_PLUM_BONITO
+var S_TRAPSTS_NON_MASKABLE_EXCP_MASK           = SQ_WAVE_TRAPSTS_MEM_VIOL_MASK|SQ_WAVE_TRAPSTS_ILLEGAL_INST_MASK
+#else
+var S_TRAPSTS_NON_MASKABLE_EXCP_MASK           = SQ_WAVE_TRAPSTS_MEM_VIOL_MASK         |\
+                                                 SQ_WAVE_TRAPSTS_ILLEGAL_INST_MASK      |\
+                                                 SQ_WAVE_TRAPSTS_WAVE_START_MASK        |\
+                                                 SQ_WAVE_TRAPSTS_WAVE_END_MASK          |\
+                                                 SQ_WAVE_TRAPSTS_TRAP_AFTER_INST_MASK
+#endif
+
 // bits [31:24] unused by SPI debug data
 var TTMP11_SAVE_REPLAY_W64H_SHIFT               = 31
 var TTMP11_SAVE_REPLAY_W64H_MASK                = 0x80000000
@@ -224,7 +239,7 @@ L_NOT_HALTED:
         // Check non-maskable exceptions. memory_violation, illegal_instruction
         // and xnack_error exceptions always cause the wave to enter the trap
         // handler.
-       s_and_b32       ttmp2, s_save_trapsts, SQ_WAVE_TRAPSTS_MEM_VIOL_MASK|SQ_WAVE_TRAPSTS_ILLEGAL_INST_MASK
+       s_and_b32       ttmp2, s_save_trapsts, S_TRAPSTS_NON_MASKABLE_EXCP_MASK
         s_cbranch_scc1  L_FETCH_2ND_TRAP

         // Check for maskable exceptions in trapsts.excp and trapsts.excp_hi.

base-commit: c4b562a17829454713e45219fa754be1bfda9004
--
2.25.1

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.freedesktop.org/archives/amd-gfx/attachments/20240206/172681ea/attachment-0001.htm>