[openeuler:OLK-6.6 1609/1609] drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_topology.c:1922:5: warning: stack frame size (2200) exceeds limit (2048) in 'kfd_topology_add_device' - Kernel

10 Dec 2024


      Hi xiajingze,
FYI, the error/warning still remains.
tree:   https://gitee.com/openeuler/kernel.git OLK-6.6
head:   db988390007bce595dba0dfd782c610578e26d2d
commit: 241ad43fe7e9c24d5ba4cdd1ec22e731cdd22d14 [1609/1609] Compiler: Add clang's PGO support for kernel.
config: x86_64-allyesconfig (https://download.01.org/0day-ci/archive/20241210/202412101126.LSCSnI7W-lkp@i...)
compiler: clang version 19.1.3 (https://github.com/llvm/llvm-project ab51eccf88f5321e7c60591c5546b254b6afab99)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20241210/202412101126.LSCSnI7W-lkp@i...)
If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot lkp@intel.com
| Closes: https://lore.kernel.org/oe-kbuild-all/202412101126.LSCSnI7W-lkp@intel.com/
All warnings (new ones prefixed by >>):
In file included from drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_topology.c:26:
   In file included from include/linux/pci.h:1666:
   In file included from include/linux/dmapool.h:14:
   In file included from include/linux/scatterlist.h:8:
   In file included from include/linux/mm.h:2235:
   include/linux/vmstat.h:508:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
     508 |         return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~ ^
     509 |                            item];
         |                            ~~~~
   include/linux/vmstat.h:515:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
     515 |         return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~ ^
     516 |                            NR_VM_NUMA_EVENT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~~
   include/linux/vmstat.h:522:36: warning: arithmetic between different enumeration types ('enum node_stat_item' and 'enum lru_list') [-Wenum-enum-conversion]
     522 |         return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_"
         |                               ~~~~~~~~~~~ ^ ~~~
   include/linux/vmstat.h:527:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
     527 |         return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~ ^
     528 |                            NR_VM_NUMA_EVENT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~~
   include/linux/vmstat.h:536:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
     536 |         return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~ ^
     537 |                            NR_VM_NUMA_EVENT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~~
...
...
drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_topology.c:1922:5: warning: stack frame size (2200) exceeds limit (2048) in 'kfd_topology_add_device' [-Wframe-larger-than]
1922 | int kfd_topology_add_device(struct kfd_node *gpu)
         |     ^
   6 warnings generated.
--
   In file included from drivers/gpu/drm/amd/amdgpu/../display/dc/dml/calcs/dcn_calc_auto.c:26:
   In file included from drivers/gpu/drm/amd/amdgpu/../display/dc/dm_services.h:35:
   In file included from drivers/gpu/drm/amd/amdgpu/../display/dc/dm_services_types.h:29:
   In file included from drivers/gpu/drm/amd/amdgpu/../display/dc/os_types.h:31:
   In file included from include/linux/kgdb.h:19:
   In file included from include/linux/kprobes.h:28:
   In file included from include/linux/ftrace.h:13:
   In file included from include/linux/kallsyms.h:13:
   In file included from include/linux/mm.h:2235:
   include/linux/vmstat.h:508:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
     508 |         return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~ ^
     509 |                            item];
         |                            ~~~~
   include/linux/vmstat.h:515:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
     515 |         return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~ ^
     516 |                            NR_VM_NUMA_EVENT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~~
   include/linux/vmstat.h:522:36: warning: arithmetic between different enumeration types ('enum node_stat_item' and 'enum lru_list') [-Wenum-enum-conversion]
     522 |         return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_"
         |                               ~~~~~~~~~~~ ^ ~~~
   include/linux/vmstat.h:527:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
     527 |         return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~ ^
     528 |                            NR_VM_NUMA_EVENT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~~
   include/linux/vmstat.h:536:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
     536 |         return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~ ^
     537 |                            NR_VM_NUMA_EVENT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~~
...
...
drivers/gpu/drm/amd/amdgpu/../display/dc/dml/calcs/dcn_calc_auto.c:121:6: warning: stack frame size (2568) exceeds limit (2048) in 'mode_support_and_system_configuration' [-Wframe-larger-than]
121 | void mode_support_and_system_configuration(struct dcn_bw_internal_vars *v)
         |      ^
   6 warnings generated.
vim +/kfd_topology_add_device +1922 drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_topology.c
d230f1bfe7a197 Jonathan Kim 8dc1db3172ae2f Mukul Joshi f701acb6a4ed0a Felix Kuehling f701acb6a4ed0a Felix Kuehling f701acb6a4ed0a Felix Kuehling f701acb6a4ed0a Felix Kuehling f701acb6a4ed0a Felix Kuehling f701acb6a4ed0a Felix Kuehling f701acb6a4ed0a Felix Kuehling f701acb6a4ed0a Felix Kuehling f701acb6a4ed0a Felix Kuehling 400a39f1ec43d2 James Zhu 400a39f1ec43d2 James Zhu 400a39f1ec43d2 James Zhu 400a39f1ec43d2 James Zhu 400a39f1ec43d2 James Zhu 400a39f1ec43d2 James Zhu f701acb6a4ed0a Felix Kuehling 400a39f1ec43d2 James Zhu f701acb6a4ed0a Felix Kuehling f701acb6a4ed0a Felix Kuehling f701acb6a4ed0a Felix Kuehling f701acb6a4ed0a Felix Kuehling f701acb6a4ed0a Felix Kuehling f701acb6a4ed0a Felix Kuehling f701acb6a4ed0a Felix Kuehling f701acb6a4ed0a Felix Kuehling f701acb6a4ed0a Felix Kuehling f701acb6a4ed0a Felix Kuehling f701acb6a4ed0a Felix Kuehling c0cc999f3c32e6 Ma Jun f701acb6a4ed0a Felix Kuehling f701acb6a4ed0a Felix Kuehling 5b5c4e40a37e85 Evgeny Pinchuk 5b5c4e40a37e85 Evgeny Pinchuk 5b5c4e40a37e85 Evgeny Pinchuk 3a87177eb14113 Harish 0f28cca87e9afc Ramesh Errabolu 0f28cca87e9afc Ramesh Errabolu 3a87177eb14113 Harish 3a87177eb14113 Harish 3a87177eb14113 Harish 3a87177eb14113 Harish 3a87177eb14113 Harish 3a87177eb14113 Harish 3a87177eb14113 Harish 3a87177eb14113 Harish 574c4183ef7511 Graham Sider c181159a5b1e1e Yong Zhao b7675b7bbc3c4c Graham Sider b7675b7bbc3c4c Graham Sider b7675b7bbc3c4c Graham Sider b7675b7bbc3c4c Graham Sider b7675b7bbc3c4c Graham Sider b7675b7bbc3c4c Graham Sider c181159a5b1e1e Yong Zhao 3a87177eb14113 Harish 3a87177eb14113 Harish 3a87177eb14113 Harish 8dc1db3172ae2f Mukul Joshi 8dc1db3172ae2f Mukul Joshi d69a3b762dc4c9 Mukul Joshi d69a3b762dc4c9 Mukul Joshi c6d1ec4134edc1 Joseph Greathouse 02274fc0f67259 Graham Sider c6d1ec4134edc1 Joseph Greathouse 92085240ef9c0e Jonathan Kim d69a3b762dc4c9 Mukul Joshi 92085240ef9c0e Jonathan Kim 92085240ef9c0e Jonathan Kim 92085240ef9c0e Jonathan Kim d69a3b762dc4c9 Mukul Joshi 3a87177eb14113 Harish 574c4183ef7511 Graham Sider 3a87177eb14113 Harish 3a87177eb14113 Harish a476c0c645535c Philip Yang a476c0c645535c Philip Yang a476c0c645535c Philip Yang a476c0c645535c Philip Yang 7c9b717196b1af Oak Zeng 8dc1db3172ae2f Mukul Joshi 3a87177eb14113 Harish 8dc1db3172ae2f Mukul Joshi ee2f17f4d02b14 Amber Lin 14568cf6583e9d Oak Zeng ee2f17f4d02b14 Amber Lin bb71c74db3c554 Huang Rui 8dc1db3172ae2f Mukul Joshi 8dc1db3172ae2f Mukul Joshi 29633d0e204df1 Joseph Greathouse 29e764621bbcd4 Oak Zeng 02274fc0f67259 Graham Sider e6945304187dea Yong Zhao 0c1690e38b5e68 Shaoyun Liu 3a87177eb14113 Harish 3a87177eb14113 Harish 3a87177eb14113 Harish 7eb0502ac0538e Graham Sider 3a87177eb14113 Harish 3a87177eb14113 Harish 3a87177eb14113 Harish 3a87177eb14113 Harish 3a87177eb14113 Harish 3a87177eb14113 Harish 3a87177eb14113 Harish 3a87177eb14113 Harish 3a87177eb14113 Harish 3a87177eb14113 Harish 3a87177eb14113 Harish 846a44d7e918a4 Gang Ba ed81cd6e0e9f37 Kent Russell 42aa8793d795f1 Felix Kuehling 3a87177eb14113 Harish 3a87177eb14113 Harish 3a87177eb14113 Harish 3a87177eb14113 Harish e4804a39ba5f72 Graham Sider d230f1bfe7a197 Jonathan Kim 3a87177eb14113 Harish 7eb0502ac0538e Graham Sider d230f1bfe7a197 Jonathan Kim d230f1bfe7a197 Jonathan Kim 7639a8c420f04c Ben Goz 7639a8c420f04c Ben Goz 1ae99eab34f90c Oak Zeng 1ae99eab34f90c Oak Zeng 1ae99eab34f90c Oak Zeng 1ae99eab34f90c Oak Zeng 1ae99eab34f90c Oak Zeng 1ae99eab34f90c Oak Zeng 3a87177eb14113 Harish 3a87177eb14113 Harish 3a87177eb14113 Harish 70f372bffcc84c Philip Cox 3a87177eb14113 Harish 7eb0502ac0538e Graham Sider 3a87177eb14113 Harish 3a87177eb14113 Harish 70f372bffcc84c Philip Cox 70f372bffcc84c Philip Cox 3a87177eb14113 Harish 5436ab94cd9460 Stanley.Yang 0dee45a25a63f7 Eric Huang 56c5977eae8799 Graham Sider 0dee45a25a63f7 Eric Huang 56c5977eae8799 Graham Sider 56c5977eae8799 Graham Sider 0dee45a25a63f7 Eric Huang 0dee45a25a63f7 Eric Huang 046e674b961594 Graham Sider 56c5977eae8799 Graham Sider 0dee45a25a63f7 Eric Huang 0dee45a25a63f7 Eric Huang 610dab118ff501 Philip Yang 4c166eb95decf0 Philip Yang 4c166eb95decf0 Philip Yang 03d400e7605e3d Alex Sierra 03d400e7605e3d Alex Sierra 03d400e7605e3d Alex Sierra 03d400e7605e3d Alex Sierra 3a87177eb14113 Harish 3a87177eb14113 Harish 5b5c4e40a37e85 Evgeny Pinchuk f701acb6a4ed0a Felix Kuehling 7d4f8db4a1448e Dan Carpenter 5b5c4e40a37e85 Evgeny Pinchuk 5b5c4e40a37e85 Evgeny Pinchuk

2022-03-25  1921 2022-09-14 @1922  int kfd_topology_add_device(struct kfd_node *gpu) 2022-11-16  1923  { 2022-11-16  1924  	uint32_t gpu_id; 2022-11-16  1925  	struct kfd_topology_device *dev; 2022-11-16  1926  	struct kfd_cu_info cu_info; 2022-11-16  1927  	int res = 0; 2022-11-16  1928  	int i; 2022-11-16  1929  	const char *asic_name = amdgpu_asic_name[gpu->adev->asic_type]; 2022-11-16  1930 2022-11-16  1931  	gpu_id = kfd_generate_gpu_id(gpu); 2023-08-09  1932  	if (gpu->xcp && !gpu->xcp->ddev) { 2023-08-09  1933  		dev_warn(gpu->adev->dev, 2023-08-09  1934  		"Won't add GPU (ID: 0x%x) to topology since it has no drm node assigned.", 2023-08-09  1935  		gpu_id); 2023-08-09  1936  		return 0; 2023-08-09  1937  	} else { 2022-11-16  1938  		pr_debug("Adding new GPU (ID: 0x%x) to topology\n", gpu_id); 2023-08-09  1939  	} 2022-11-16  1940 2022-11-16  1941  	/* Check to see if this gpu device exists in the topology_device_list. 2022-11-16  1942  	 * If so, assign the gpu to that device, 2022-11-16  1943  	 * else create a Virtual CRAT for this gpu device and then parse that 2022-11-16  1944  	 * CRAT to create a new topology device. Once created assign the gpu to 2022-11-16  1945  	 * that topology device 2022-11-16  1946  	 */ 2022-11-16  1947  	down_write(&topology_lock); 2022-11-16  1948  	dev = kfd_assign_gpu(gpu); 2022-11-16  1949  	if (!dev) 2022-11-16  1950  		res = kfd_topology_add_device_locked(gpu, gpu_id, &dev); 2022-11-02  1951  	up_write(&topology_lock); 2022-11-16  1952  	if (res) 2022-11-16  1953  		return res; 2014-07-16  1954 2014-07-16  1955  	dev->gpu_id = gpu_id; 2014-07-16  1956  	gpu->id = gpu_id; Kasiviswanathan 2017-12-08  1957 2022-05-26  1958  	kfd_dev_create_p2p_links(); 2022-05-26  1959 Kasiviswanathan 2017-12-08  1960  	/* TODO: Move the following lines to function Kasiviswanathan 2017-12-08  1961  	 *	kfd_add_non_crat_information Kasiviswanathan 2017-12-08  1962  	 */ Kasiviswanathan 2017-12-08  1963 Kasiviswanathan 2017-12-08  1964  	/* Fill-in additional information that is not available in CRAT but Kasiviswanathan 2017-12-08  1965  	 * needed for the topology Kasiviswanathan 2017-12-08  1966  	 */ Kasiviswanathan 2017-12-08  1967 2021-10-19  1968  	amdgpu_amdkfd_get_cu_info(dev->gpu->adev, &cu_info); 2019-08-01  1969 2021-11-11  1970  	for (i = 0; i < KFD_TOPOLOGY_PUBLIC_NAME_SIZE-1; i++) { 2021-11-11  1971  		dev->node_props.name[i] = __tolower(asic_name[i]); 2021-11-11  1972  		if (asic_name[i] == '\0') 2021-11-11  1973  			break; 2021-11-11  1974  	} 2021-11-11  1975  	dev->node_props.name[i] = '\0'; 2019-08-01  1976 Kasiviswanathan 2017-12-08  1977  	dev->node_props.simd_arrays_per_engine = Kasiviswanathan 2017-12-08  1978  		cu_info.num_shader_arrays_per_engine; Kasiviswanathan 2017-12-08  1979 2022-09-14  1980  	dev->node_props.gfx_target_version = 2022-09-14  1981  				gpu->kfd->device_info.gfx_target_version; 2022-05-09  1982  	dev->node_props.vendor_id = gpu->adev->pdev->vendor; 2022-05-09  1983  	dev->node_props.device_id = gpu->adev->pdev->device; 2020-04-16  1984  	dev->node_props.capability |= 2021-11-05  1985  		((dev->gpu->adev->rev_id << HSA_CAP_ASIC_REVISION_SHIFT) & 2020-04-16  1986  			HSA_CAP_ASIC_REVISION_MASK); 2022-05-03  1987 2022-05-09  1988  	dev->node_props.location_id = pci_dev_id(gpu->adev->pdev); 2022-05-03  1989  	if (KFD_GC_VERSION(dev->gpu->kfd) == IP_VERSION(9, 4, 3)) 2022-05-03  1990  		dev->node_props.location_id |= dev->gpu->node_id; 2022-05-03  1991 2022-05-09  1992  	dev->node_props.domain = pci_domain_nr(gpu->adev->pdev->bus); Kasiviswanathan 2017-12-08  1993  	dev->node_props.max_engine_clk_fcompute = 2021-10-19  1994  		amdgpu_amdkfd_get_max_engine_clock_in_mhz(dev->gpu->adev); Kasiviswanathan 2017-12-08  1995  	dev->node_props.max_engine_clk_ccompute = Kasiviswanathan 2017-12-08  1996  		cpufreq_quick_get_max(0) / 1000; 2023-02-23  1997 2023-02-23  1998  	if (gpu->xcp) 2023-02-23  1999  		dev->node_props.drm_render_minor = gpu->xcp->ddev->render->index; 2023-02-23  2000  	else 2018-03-15  2001  		dev->node_props.drm_render_minor = 2022-09-14  2002  				gpu->kfd->shared_resources.drm_render_minor; Kasiviswanathan 2017-12-08  2003 2022-09-14  2004  	dev->node_props.hive_id = gpu->kfd->hive_id; 2021-11-18  2005  	dev->node_props.num_sdma_engines = kfd_get_num_sdma_engines(gpu); 2019-02-08  2006  	dev->node_props.num_sdma_xgmi_engines = 2021-11-18  2007  					kfd_get_num_xgmi_sdma_engines(gpu); 2019-12-16  2008  	dev->node_props.num_sdma_queues_per_engine = 2022-09-14  2009  				gpu->kfd->device_info.num_sdma_queues_per_engine - 2022-09-14  2010  				gpu->kfd->device_info.num_reserved_sdma_queues_per_engine; 2020-01-15  2011  	dev->node_props.num_gws = (dev->gpu->gws && 2019-05-03  2012  		dev->gpu->dqm->sched_policy != KFD_SCHED_POLICY_NO_HWS) ? 2021-11-05  2013  		dev->gpu->adev->gds.gws_size : 0; 2020-01-30  2014  	dev->node_props.num_cp_queues = get_cp_queues_num(dev->gpu->dqm); 2018-07-06  2015 Kasiviswanathan 2017-12-08  2016  	kfd_fill_mem_clk_max_info(dev); Kasiviswanathan 2017-12-08  2017  	kfd_fill_iolink_non_crat_info(dev); Kasiviswanathan 2017-12-08  2018 2021-11-10  2019  	switch (dev->gpu->adev->asic_type) { Kasiviswanathan 2017-12-08  2020  	case CHIP_KAVERI: Kasiviswanathan 2017-12-08  2021  	case CHIP_HAWAII: Kasiviswanathan 2017-12-08  2022  	case CHIP_TONGA: Kasiviswanathan 2017-12-08  2023  		dev->node_props.capability |= ((HSA_CAP_DOORBELL_TYPE_PRE_1_0 << Kasiviswanathan 2017-12-08  2024  			HSA_CAP_DOORBELL_TYPE_TOTALBITS_SHIFT) & Kasiviswanathan 2017-12-08  2025  			HSA_CAP_DOORBELL_TYPE_TOTALBITS_MASK); Kasiviswanathan 2017-12-08  2026  		break; Kasiviswanathan 2017-12-08  2027  	case CHIP_CARRIZO: Kasiviswanathan 2017-12-08  2028  	case CHIP_FIJI: Kasiviswanathan 2017-12-08  2029  	case CHIP_POLARIS10: Kasiviswanathan 2017-12-08  2030  	case CHIP_POLARIS11: 2018-09-05  2031  	case CHIP_POLARIS12: 2019-03-21  2032  	case CHIP_VEGAM: 2017-12-08  2033  		pr_debug("Adding doorbell packet type capability\n"); Kasiviswanathan 2017-12-08  2034  		dev->node_props.capability |= ((HSA_CAP_DOORBELL_TYPE_1_0 << Kasiviswanathan 2017-12-08  2035  			HSA_CAP_DOORBELL_TYPE_TOTALBITS_SHIFT) & Kasiviswanathan 2017-12-08  2036  			HSA_CAP_DOORBELL_TYPE_TOTALBITS_MASK); Kasiviswanathan 2017-12-08  2037  		break; 2021-10-28  2038  	default: 2022-03-25  2039  		if (KFD_GC_VERSION(dev->gpu) < IP_VERSION(9, 0, 1)) Kasiviswanathan 2017-12-08  2040  			WARN(1, "Unexpected ASIC family %u", 2021-11-10  2041  			     dev->gpu->adev->asic_type); 2022-03-25  2042  		else 2022-03-25  2043  			kfd_topology_set_capabilities(dev); 2015-06-07  2044  	} 2015-06-07  2045 2019-06-10  2046  	/* 2019-06-10  2047  	 * Overwrite ATS capability according to needs_iommu_device to fix 2019-06-10  2048  	 * potential missing corresponding bit in CRAT of BIOS. 2019-06-10  2049  	 */ 2019-06-10  2050  	dev->node_props.capability &= ~HSA_CAP_ATS_PRESENT; 2019-06-10  2051 Kasiviswanathan 2017-12-08  2052  	/* Fix errors in CZ CRAT. Kasiviswanathan 2017-12-08  2053  	 * simd_count: Carrizo CRAT reports wrong simd_count, probably Kasiviswanathan 2017-12-08  2054  	 *		because it doesn't consider masked out CUs 2017-12-08  2055  	 * max_waves_per_simd: Carrizo reports wrong max_waves_per_simd Kasiviswanathan 2017-12-08  2056  	 */ 2021-11-10  2057  	if (dev->gpu->adev->asic_type == CHIP_CARRIZO) { Kasiviswanathan 2017-12-08  2058  		dev->node_props.simd_count = Kasiviswanathan 2017-12-08  2059  			cu_info.simd_per_cu * cu_info.cu_active_number; 2017-12-08  2060  		dev->node_props.max_waves_per_simd = 10; 2017-12-08  2061  	} Kasiviswanathan 2017-12-08  2062 2020-08-17  2063  	/* kfd only concerns sram ecc on GFX and HBM ecc on UMC */ 2019-01-11  2064  	dev->node_props.capability |= 2021-10-19  2065  		((dev->gpu->adev->ras_enabled & BIT(AMDGPU_RAS_BLOCK__GFX)) != 0) ? 2019-01-11  2066  		HSA_CAP_SRAM_EDCSUPPORTED : 0; 2021-10-19  2067  	dev->node_props.capability |= 2021-10-19  2068  		((dev->gpu->adev->ras_enabled & BIT(AMDGPU_RAS_BLOCK__UMC)) != 0) ? 2019-01-11  2069  		HSA_CAP_MEM_EDCSUPPORTED : 0; 2019-01-11  2070 2021-11-09  2071  	if (KFD_GC_VERSION(dev->gpu) != IP_VERSION(9, 0, 1)) 2021-10-19  2072  		dev->node_props.capability |= (dev->gpu->adev->ras_enabled != 0) ? 2019-01-11  2073  			HSA_CAP_RASEVENTNOTIFY : 0; 2019-01-11  2074 2023-03-31  2075  	if (KFD_IS_SVM_API_SUPPORTED(dev->gpu->adev)) 2020-12-09  2076  		dev->node_props.capability |= HSA_CAP_SVMAPI_SUPPORTED; 2020-12-09  2077 2023-06-15  2078  	if (dev->gpu->adev->gmc.is_app_apu || 2023-06-15  2079  		dev->gpu->adev->gmc.xgmi.connected_to_cpu) 2023-06-15  2080  		dev->node_props.capability |= HSA_CAP_FLAGS_COHERENTHOSTACCESS; 2023-06-15  2081 Kasiviswanathan 2017-12-08  2082  	kfd_debug_print_topology(); Kasiviswanathan 2017-12-08  2083 2014-07-16  2084  	kfd_notify_gpu_change(gpu_id, 1); 2022-11-16  2085 2022-11-25  2086  	return 0; 2014-07-16  2087  } 2014-07-16  2088
:::::: The code at line 1922 was first introduced by commit
:::::: 8dc1db3172ae2f17ae71e33b608a33411ce8a1aa drm/amdkfd: Introduce kfd_node struct (v5)
:::::: TO: Mukul Joshi mukul.joshi@amd.com
:::::: CC: Alex Deucher alexander.deucher@amd.com
-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki