Linux kernel stable tree (mirror) https://git.radix-linux.su/kernel/linux.git/atom?h=v6.11.8 2024-11-01T01:02:28+00:00 2024-11-01T01:02:28+00:00 Srinivasan Shanmugam srinivasan.shanmugam@amd.com 2024-10-08T13:31:48+00:00 urn:sha1:f000e1df85de492c09f08dbabde51b36c33beec4 [ Upstream commit e7457532cb7167516263150ceae86f36d6ef9683 ] This patch addresses a double unlock issue in the amdgpu_mes_add_ring function. The mutex was being unlocked twice under certain error conditions, which could lead to undefined behavior. The fix ensures that the mutex is unlocked only once before jumping to the clean_up_memory label. The unlock operation is moved to just before the goto statement within the conditional block that checks the return value of amdgpu_ring_init. This prevents the second unlock attempt after the clean_up_memory label, which is no longer necessary as the mutex is already unlocked by this point in the code flow. This change resolves the potential double unlock and maintains the correct mutex handling throughout the function. Fixes below: Commit d0c423b64765 ("drm/amdgpu/mes: use ring for kernel queue submission"), leads to the following Smatch static checker warning: drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c:1240 amdgpu_mes_add_ring() warn: double unlock '&adev->mes.mutex_hidden' (orig line 1213) drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c 1143 int amdgpu_mes_add_ring(struct amdgpu_device *adev, int gang_id, 1144 int queue_type, int idx, 1145 struct amdgpu_mes_ctx_data *ctx_data, 1146 struct amdgpu_ring **out) 1147 { 1148 struct amdgpu_ring *ring; 1149 struct amdgpu_mes_gang *gang; 1150 struct amdgpu_mes_queue_properties qprops = {0}; 1151 int r, queue_id, pasid; 1152 1153 /* 1154 * Avoid taking any other locks under MES lock to avoid circular 1155 * lock dependencies. 1156 */ 1157 amdgpu_mes_lock(&adev->mes); 1158 gang = idr_find(&adev->mes.gang_id_idr, gang_id); 1159 if (!gang) { 1160 DRM_ERROR("gang id %d doesn't exist\n", gang_id); 1161 amdgpu_mes_unlock(&adev->mes); 1162 return -EINVAL; 1163 } 1164 pasid = gang->process->pasid; 1165 1166 ring = kzalloc(sizeof(struct amdgpu_ring), GFP_KERNEL); 1167 if (!ring) { 1168 amdgpu_mes_unlock(&adev->mes); 1169 return -ENOMEM; 1170 } 1171 1172 ring->ring_obj = NULL; 1173 ring->use_doorbell = true; 1174 ring->is_mes_queue = true; 1175 ring->mes_ctx = ctx_data; 1176 ring->idx = idx; 1177 ring->no_scheduler = true; 1178 1179 if (queue_type == AMDGPU_RING_TYPE_COMPUTE) { 1180 int offset = offsetof(struct amdgpu_mes_ctx_meta_data, 1181 compute[ring->idx].mec_hpd); 1182 ring->eop_gpu_addr = 1183 amdgpu_mes_ctx_get_offs_gpu_addr(ring, offset); 1184 } 1185 1186 switch (queue_type) { 1187 case AMDGPU_RING_TYPE_GFX: 1188 ring->funcs = adev->gfx.gfx_ring[0].funcs; 1189 ring->me = adev->gfx.gfx_ring[0].me; 1190 ring->pipe = adev->gfx.gfx_ring[0].pipe; 1191 break; 1192 case AMDGPU_RING_TYPE_COMPUTE: 1193 ring->funcs = adev->gfx.compute_ring[0].funcs; 1194 ring->me = adev->gfx.compute_ring[0].me; 1195 ring->pipe = adev->gfx.compute_ring[0].pipe; 1196 break; 1197 case AMDGPU_RING_TYPE_SDMA: 1198 ring->funcs = adev->sdma.instance[0].ring.funcs; 1199 break; 1200 default: 1201 BUG(); 1202 } 1203 1204 r = amdgpu_ring_init(adev, ring, 1024, NULL, 0, 1205 AMDGPU_RING_PRIO_DEFAULT, NULL); 1206 if (r) 1207 goto clean_up_memory; 1208 1209 amdgpu_mes_ring_to_queue_props(adev, ring, &qprops); 1210 1211 dma_fence_wait(gang->process->vm->last_update, false); 1212 dma_fence_wait(ctx_data->meta_data_va->last_pt_update, false); 1213 amdgpu_mes_unlock(&adev->mes); ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 1214 1215 r = amdgpu_mes_add_hw_queue(adev, gang_id, &qprops, &queue_id); 1216 if (r) 1217 goto clean_up_ring; ^^^^^^^^^^^^^^^^^^ 1218 1219 ring->hw_queue_id = queue_id; 1220 ring->doorbell_index = qprops.doorbell_off; 1221 1222 if (queue_type == AMDGPU_RING_TYPE_GFX) 1223 sprintf(ring->name, "gfx_%d.%d.%d", pasid, gang_id, queue_id); 1224 else if (queue_type == AMDGPU_RING_TYPE_COMPUTE) 1225 sprintf(ring->name, "compute_%d.%d.%d", pasid, gang_id, 1226 queue_id); 1227 else if (queue_type == AMDGPU_RING_TYPE_SDMA) 1228 sprintf(ring->name, "sdma_%d.%d.%d", pasid, gang_id, 1229 queue_id); 1230 else 1231 BUG(); 1232 1233 *out = ring; 1234 return 0; 1235 1236 clean_up_ring: 1237 amdgpu_ring_fini(ring); 1238 clean_up_memory: 1239 kfree(ring); --> 1240 amdgpu_mes_unlock(&adev->mes); ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 1241 return r; 1242 } Fixes: d0c423b64765 ("drm/amdgpu/mes: use ring for kernel queue submission") Cc: Christian König <christian.koenig@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Cc: Hawking Zhang <Hawking.Zhang@amd.com> Suggested-by: Jack Xiao <Jack.Xiao@amd.com> Reported by: Dan Carpenter <dan.carpenter@linaro.org> Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com> Reviewed-by: Jack Xiao <Jack.Xiao@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> (cherry picked from commit bfaf1883605fd0c0dbabacd67ed49708470d5ea4) Signed-off-by: Sasha Levin <sashal@kernel.org> 2024-08-13T17:17:36+00:00 Jack Xiao Jack.Xiao@amd.com 2024-08-07T06:49:30+00:00 urn:sha1:7254027e1e6edbff54f5930a5f13f14ac6f1694c Configure two pipes with different hardware resources. Signed-off-by: Jack Xiao <Jack.Xiao@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> (cherry picked from commit ea5d6db17a8e3635ad91e8c53faa1fdc9570fbbb) 2024-08-13T17:17:36+00:00 Jack Xiao Jack.Xiao@amd.com 2024-08-07T05:19:59+00:00 urn:sha1:a13d91bf3c1910212e45a69d04ad40d99878f8da Enable unified mes firmware to load on pipe0 and pipe1. Signed-off-by: Jack Xiao <Jack.Xiao@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> (cherry picked from commit e69c2dd7534f3fcabf7bb801db2a7ac71e7e5da6) 2024-08-13T17:04:48+00:00 Jack Xiao Jack.Xiao@amd.com 2024-08-07T03:53:35+00:00 urn:sha1:2029b3d7e1358bcca30f74978543ba35b4bbc43d Add multiple mes ring instances in mes structure to support multiple mes pipes. Signed-off-by: Jack Xiao <Jack.Xiao@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> (cherry picked from commit c7d4355648ffa02a1551495b05c71ea6c884d29c) 2024-07-27T22:10:12+00:00 Michael Chen michael.chen@amd.com 2024-07-23T21:45:23+00:00 urn:sha1:9038e25c80558d48ce33d6d8c168666164dc72e9 MES firmware requires larger log buffer for gfx12. Allocate proper buffer respectively for gfx11 and gfx12. Signed-off-by: Michael Chen <michael.chen@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> (cherry picked from commit 739d0f3e1f36738d4cd84166784a8f7a58d69612) 2024-06-19T16:50:24+00:00 Alex Deucher alexander.deucher@amd.com 2024-06-03T20:59:22+00:00 urn:sha1:19797687e64b961f7c5aac9cf60951561aec038e No longer used so remove it. Reviewed-by: Mukul Joshi <mukul.joshi@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 2024-06-19T16:46:39+00:00 Mukul Joshi mukul.joshi@amd.com 2024-06-14T21:07:58+00:00 urn:sha1:4d14a7405424cfd0d0b72df30d0e4698805746de This reverts commit 3612702852acbded39233b1600c8d9f47e40139f. This is causing a BUG message during suspend. [ 61.603542] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:283 [ 61.603550] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 2028, name: kworker/u64:14 [ 61.603553] preempt_count: 1, expected: 0 [ 61.603555] RCU nest depth: 0, expected: 0 [ 61.603557] Preemption disabled at: [ 61.603559] [<ffffffffc08a3261>] amdgpu_gfx_disable_kgq+0x61/0x160 [amdgpu] [ 61.603789] CPU: 9 PID: 2028 Comm: kworker/u64:14 Tainted: G W 6.8.0+ #7 [ 61.603795] Workqueue: events_unbound async_run_entry_fn [ 61.603801] Call Trace: [ 61.603803] <TASK> [ 61.603806] dump_stack_lvl+0x37/0x50 [ 61.603811] ? amdgpu_gfx_disable_kgq+0x61/0x160 [amdgpu] [ 61.604007] dump_stack+0x10/0x20 [ 61.604010] __might_resched+0x16f/0x1d0 [ 61.604016] __might_sleep+0x43/0x70 [ 61.604020] mutex_lock+0x1f/0x60 [ 61.604024] amdgpu_mes_unmap_legacy_queue+0x6d/0x100 [amdgpu] [ 61.604226] gfx11_kiq_unmap_queues+0x3dc/0x430 [amdgpu] [ 61.604422] ? srso_alias_return_thunk+0x5/0xfbef5 [ 61.604429] amdgpu_gfx_disable_kgq+0x122/0x160 [amdgpu] [ 61.604621] gfx_v11_0_hw_fini+0xda/0x100 [amdgpu] [ 61.604814] gfx_v11_0_suspend+0xe/0x20 [amdgpu] [ 61.605008] amdgpu_device_ip_suspend_phase2+0x135/0x1d0 [amdgpu] [ 61.605175] amdgpu_device_suspend+0xec/0x180 [amdgpu] Signed-off-by: Mukul Joshi <mukul.joshi@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 2024-06-14T20:17:11+00:00 Yang Wang kevinyang.wang@amd.com 2024-05-30T14:51:03+00:00 urn:sha1:bf349b036d57950e9822b1d11ba12b8e28fa42d1 v1: refine mes firmware loading v2: use dev_info instead of DRM_INFO Signed-off-by: Yang Wang <kevinyang.wang@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 2024-06-14T20:17:11+00:00 Mukul Joshi mukul.joshi@amd.com 2024-06-05T22:48:55+00:00 urn:sha1:3612702852acbded39233b1600c8d9f47e40139f Add missing locking at a few places when calling MES APIs to ensure exclusive access to MES queue. Signed-off-by: Mukul Joshi <mukul.joshi@amd.com> Reviewed-by: Kent Russell <kent.russell@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 2024-05-02T20:18:13+00:00 Jack Xiao Jack.Xiao@amd.com 2024-03-01T08:51:40+00:00 urn:sha1:15ddc4e6931b747b5d241a4e61dbd4d4b95c8360 Add the unified mes firmware loading support. Signed-off-by: Jack Xiao <Jack.Xiao@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>