drm/amdgpu: Enable SA software trap.

Enables support for software trap for MES >= 4.
Adapted from implementation from Jay Cornwall.

v2: Add IP version check in conditions.
v3: Remove debugger code changes.
Signed-off-by: NJay Cornwall <Jay.Cornwall@amd.com>
Signed-off-by: NDavid Belanger <david.belanger@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Acked-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/mes_v11_0.c

@@ -185,7 +185,11 @@ static int mes_v11_0_add_hw_queue(struct amdgpu_mes *mes,
 	mes_add_queue_pkt.trap_handler_addr = input->tba_addr;
 	mes_add_queue_pkt.tma_addr = input->tma_addr;
 	mes_add_queue_pkt.is_kfd_process = input->is_kfd_process;
-	mes_add_queue_pkt.trap_en = 1;
+
+	if (!(((adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 4) &&
+		  (adev->ip_versions[GC_HWIP][0] >= IP_VERSION(11, 0, 0)) &&
+		  (adev->ip_versions[GC_HWIP][0] <= IP_VERSION(11, 0, 3))))
+		mes_add_queue_pkt.trap_en = 1;
 
 	return mes_v11_0_submit_pkt_and_poll_completion(mes,
 			&mes_add_queue_pkt, sizeof(mes_add_queue_pkt),

drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm

@@ -43,12 +43,14 @@
 #define HAVE_XNACK (ASIC_FAMILY < CHIP_SIENNA_CICHLID)
 #define HAVE_SENDMSG_RTN (ASIC_FAMILY >= CHIP_PLUM_BONITO)
 #define HAVE_BUFFER_LDS_LOAD (ASIC_FAMILY < CHIP_PLUM_BONITO)
+#define SW_SA_TRAP (ASIC_FAMILY >= CHIP_PLUM_BONITO)
 
 var SINGLE_STEP_MISSED_WORKAROUND		= 1	//workaround for lost MODE.DEBUG_EN exception when SAVECTX raised
 
 var SQ_WAVE_STATUS_SPI_PRIO_MASK		= 0x00000006
 var SQ_WAVE_STATUS_HALT_MASK			= 0x2000
 var SQ_WAVE_STATUS_ECC_ERR_MASK			= 0x20000
+var SQ_WAVE_STATUS_TRAP_EN_SHIFT		= 6
 
 var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT		= 12
 var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SIZE		= 9
@@ -183,6 +185,13 @@ L_SKIP_RESTORE:
 
 	s_getreg_b32	s_save_trapsts, hwreg(HW_REG_TRAPSTS)
 
+#if SW_SA_TRAP
+	// If ttmp1[31] is set then trap may occur early.
+	// Spin wait until SAVECTX exception is raised.
+	s_bitcmp1_b32	s_save_pc_hi, 31
+	s_cbranch_scc1  L_CHECK_SAVE
+#endif
+
 	s_and_b32       ttmp2, s_save_status, SQ_WAVE_STATUS_HALT_MASK
 	s_cbranch_scc0	L_NOT_HALTED
 
@@ -1061,8 +1070,20 @@ L_RESTORE_HWREG:
 	s_and_b32	s_restore_pc_hi, s_restore_pc_hi, 0x0000ffff		//pc[47:32] //Do it here in order not to affect STATUS
 	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
+
+#if SW_SA_TRAP
+	// If traps are enabled then return to the shader with PRIV=0.
+	// Otherwise retain PRIV=1 for subsequent context save requests.
+	s_getreg_b32	s_restore_tmp, hwreg(HW_REG_STATUS)
+	s_bitcmp1_b32	s_restore_tmp, SQ_WAVE_STATUS_TRAP_EN_SHIFT
+	s_cbranch_scc1	L_RETURN_WITHOUT_PRIV
+
 	s_setreg_b32	hwreg(HW_REG_STATUS), s_restore_status			// SCC is included, which is changed by previous salu
+	s_setpc_b64	[s_restore_pc_lo, s_restore_pc_hi]
+L_RETURN_WITHOUT_PRIV:
+#endif
 
+	s_setreg_b32	hwreg(HW_REG_STATUS), s_restore_status			// SCC is included, which is changed by previous salu
 	s_rfe_b64	s_restore_pc_lo						//Return to the main shader program and resume execution
 
 L_END_PGM: