drm/amdkfd: Preserve wave state after instruction fetch MEM_VIOL

If instruction fetch fails the wave cannot be halted and returned to
the shader without raising MEM_VIOL again. Currently the wave is
terminated if this occurs, but this loses information about the cause
of the fault. The debugger would prefer the faulting wave state to be
context-saved.

Poll inside the trap handler until TRAPSTS.SAVECTX indicates context
save is ready. Exit the poll loop and complete the remainder of the
exception handler, then return to the shader. The next instruction
fetch will be from the trap handler and not the faulting PC. Context
save will then deschedule the wave and save its state.

Signed-off-by: Jay Cornwall <Jay.Cornwall@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
index ec9a9a99f8080dd015d96209aa50d6ce9e7083e5..097da0dd3b04b04c1506ac25cf19f300c62e8346 100644 (file)
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
@@ -274,15 +274,17 @@ static const uint32_t cwsr_trap_gfx8_hex[] = {
 
 
 static const uint32_t cwsr_trap_gfx9_hex[] = {
-       0xbf820001, 0xbf82015d,
+       0xbf820001, 0xbf820161,
        0xb8f8f802, 0x89788678,
        0xb8f1f803, 0x866eff71,
-       0x00000400, 0xbf850037,
+       0x00000400, 0xbf85003b,
        0x866eff71, 0x00000800,
        0xbf850003, 0x866eff71,
-       0x00000100, 0xbf840008,
+       0x00000100, 0xbf84000c,
        0x866eff78, 0x00002000,
-       0xbf840001, 0xbf810000,
+       0xbf840005, 0xbf8e0010,
+       0xb8eef803, 0x866eff6e,
+       0x00000400, 0xbf84fffb,
        0x8778ff78, 0x00002000,
        0x80ec886c, 0x82ed806d,
        0xb8eef807, 0x866fff6e,

diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
index 0bb9c577b3a2c8b7a93e2b9dc330fdff1b32f5ea..6a010c9e55deb15832a5b45f4064fc5bb5ff1cf3 100644 (file)
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
@@ -266,10 +266,16 @@ if (!EMU_RUN_HACK)
 
 L_HALT_WAVE:
     // If STATUS.HALT is set then this fault must come from SQC instruction fetch.
-    // We cannot prevent further faults so just terminate the wavefront.
+    // We cannot prevent further faults. Spin wait until context saved.
     s_and_b32       ttmp2, s_save_status, SQ_WAVE_STATUS_HALT_MASK
     s_cbranch_scc0  L_NOT_ALREADY_HALTED
-    s_endpgm
+
+L_WAIT_CTX_SAVE:
+    s_sleep         0x10
+    s_getreg_b32    ttmp2, hwreg(HW_REG_TRAPSTS)
+    s_and_b32       ttmp2, ttmp2, SQ_WAVE_TRAPSTS_SAVECTX_MASK
+    s_cbranch_scc0  L_WAIT_CTX_SAVE
+
 L_NOT_ALREADY_HALTED:
     s_or_b32        s_save_status, s_save_status, SQ_WAVE_STATUS_HALT_MASK