Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel os linux

drm/amdgpu/acp: Make PM domain really work

Devices created by mfd_add_hotplug_devices() don't really increase the
index of its name, so get_mfd_cell_dev() cannot find any device, hence a
NULL dev is passed to pm_genpd_add_device():
[ 56.974926] (NULL device *): amdgpu: device acp_audio_dma.0.auto added to pm domain
[ 56.974933] (NULL device *): amdgpu: Failed to add dev to genpd
[ 56.974941] [drm:amdgpu_device_ip_init [amdgpu]] *ERROR* hw_init of IP block <acp_ip> failed -22
[ 56.975810] amdgpu 0000:00:01.0: amdgpu: amdgpu_device_ip_init failed
[ 56.975839] amdgpu 0000:00:01.0: amdgpu: Fatal error during GPU init
[ 56.977136] ------------[ cut here ]------------
[ 56.977143] kernel BUG at mm/slub.c:4206!
[ 56.977158] invalid opcode: 0000 [#1] SMP NOPTI
[ 56.977167] CPU: 1 PID: 1648 Comm: modprobe Not tainted 5.12.0-051200rc8-generic #202104182230
[ 56.977175] Hardware name: To Be Filled By O.E.M. To Be Filled By O.E.M./FM2A68M-HD+, BIOS P5.20 02/13/2019
[ 56.977180] RIP: 0010:kfree+0x3bf/0x410
[ 56.977195] Code: 89 e7 48 d3 e2 f7 da e8 5f 0d 02 00 80 e7 02 75 3e 44 89 ee 4c 89 e7 e8 ef 5f fd ff e9 fa fe ff ff 49 8b 44 24 08 a8 01 75 b7 <0f> 0b 4c 8b 4d b0 48 8b 4d a8 48 89 da 4c 89 e6 41 b8 01 00 00 00
[ 56.977202] RSP: 0018:ffffa48640ff79f0 EFLAGS: 00010246
[ 56.977210] RAX: 0000000000000000 RBX: ffff9286127d5608 RCX: 0000000000000000
[ 56.977215] RDX: 0000000000000000 RSI: ffffffffc099d0fb RDI: ffff9286127d5608
[ 56.977220] RBP: ffffa48640ff7a48 R08: 0000000000000001 R09: 0000000000000001
[ 56.977224] R10: 0000000000000000 R11: ffff9286087d8458 R12: fffff3ae0449f540
[ 56.977229] R13: 0000000000000000 R14: dead000000000122 R15: dead000000000100
[ 56.977234] FS: 00007f9de5929540(0000) GS:ffff928612e80000(0000) knlGS:0000000000000000
[ 56.977240] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 56.977245] CR2: 00007f697dd97160 CR3: 00000001110f0000 CR4: 00000000001506e0
[ 56.977251] Call Trace:
[ 56.977261] amdgpu_dm_encoder_destroy+0x1b/0x30 [amdgpu]
[ 56.978056] drm_mode_config_cleanup+0x4f/0x2e0 [drm]
[ 56.978147] ? kfree+0x3dd/0x410
[ 56.978157] ? drm_managed_release+0xc8/0x100 [drm]
[ 56.978232] drm_mode_config_init_release+0xe/0x10 [drm]
[ 56.978311] drm_managed_release+0x9d/0x100 [drm]
[ 56.978388] devm_drm_dev_init_release+0x4d/0x70 [drm]
[ 56.978450] devm_action_release+0x15/0x20
[ 56.978459] release_nodes+0x77/0xc0
[ 56.978469] devres_release_all+0x3f/0x50
[ 56.978477] really_probe+0x245/0x460
[ 56.978485] driver_probe_device+0xe9/0x160
[ 56.978492] device_driver_attach+0xab/0xb0
[ 56.978499] __driver_attach+0x8f/0x150
[ 56.978506] ? device_driver_attach+0xb0/0xb0
[ 56.978513] bus_for_each_dev+0x7e/0xc0
[ 56.978521] driver_attach+0x1e/0x20
[ 56.978528] bus_add_driver+0x135/0x1f0
[ 56.978534] driver_register+0x91/0xf0
[ 56.978540] __pci_register_driver+0x54/0x60
[ 56.978549] amdgpu_init+0x77/0x1000 [amdgpu]
[ 56.979246] ? 0xffffffffc0dbc000
[ 56.979254] do_one_initcall+0x48/0x1d0
[ 56.979265] ? kmem_cache_alloc_trace+0x120/0x230
[ 56.979274] ? do_init_module+0x28/0x280
[ 56.979282] do_init_module+0x62/0x280
[ 56.979288] load_module+0x71c/0x7a0
[ 56.979296] __do_sys_finit_module+0xc2/0x120
[ 56.979305] __x64_sys_finit_module+0x1a/0x20
[ 56.979311] do_syscall_64+0x38/0x90
[ 56.979319] entry_SYSCALL_64_after_hwframe+0x44/0xae
[ 56.979328] RIP: 0033:0x7f9de54f989d
[ 56.979335] Code: 00 c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d c3 f5 0c 00 f7 d8 64 89 01 48
[ 56.979342] RSP: 002b:00007ffe3c395a28 EFLAGS: 00000246 ORIG_RAX: 0000000000000139
[ 56.979350] RAX: ffffffffffffffda RBX: 0000560df3ef4330 RCX: 00007f9de54f989d
[ 56.979355] RDX: 0000000000000000 RSI: 0000560df3a07358 RDI: 000000000000000f
[ 56.979360] RBP: 0000000000040000 R08: 0000000000000000 R09: 0000000000000000
[ 56.979365] R10: 000000000000000f R11: 0000000000000246 R12: 0000560df3a07358
[ 56.979369] R13: 0000000000000000 R14: 0000560df3ef4460 R15: 0000560df3ef4330
[ 56.979377] Modules linked in: amdgpu(+) iommu_v2 gpu_sched drm_ttm_helper ttm drm_kms_helper cec rc_core i2c_algo_bit fb_sys_fops syscopyarea sysfillrect sysimgblt nft_counter xt_tcpudp ipt_REJECT nf_reject_ipv4 xt_conntrack iptable_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 iptable_mangle iptable_raw iptable_security ip_set nf_tables libcrc32c nfnetlink ip6_tables iptable_filter bpfilter input_leds binfmt_misc edac_mce_amd kvm_amd ccp kvm snd_hda_codec_realtek snd_hda_codec_generic crct10dif_pclmul snd_hda_codec_hdmi ledtrig_audio ghash_clmulni_intel aesni_intel snd_hda_intel snd_intel_dspcfg snd_seq_midi crypto_simd snd_intel_sdw_acpi cryptd snd_hda_codec snd_seq_midi_event snd_rawmidi snd_hda_core snd_hwdep snd_seq fam15h_power k10temp snd_pcm snd_seq_device snd_timer snd mac_hid soundcore sch_fq_codel nct6775 hwmon_vid drm ip_tables x_tables autofs4 dm_mirror dm_region_hash dm_log hid_generic usbhid hid uas usb_storage r8169 crc32_pclmul realtek ahci xhci_pci i2c_piix4
[ 56.979521] xhci_pci_renesas libahci video
[ 56.979541] ---[ end trace cb8f6a346f18da7b ]---

Instead of finding MFD hotplugged device by its name, simply iterate
over the child devices to avoid the issue.

Squash in unused variable removal (Alex)

BugLink: https://bugs.launchpad.net/bugs/1920674
Fixes: 25030321ba28 ("drm/amd: add pm domain for ACP IP sub blocks")
Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

authored by

Kai-Heng Feng and committed by
Alex Deucher
aff89028 222e0a71

+26 -28
+26 -28
drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
··· 160 160 return 0; 161 161 } 162 162 163 - static struct device *get_mfd_cell_dev(const char *device_name, int r) 163 + static int acp_genpd_add_device(struct device *dev, void *data) 164 164 { 165 - char auto_dev_name[25]; 166 - struct device *dev; 165 + struct generic_pm_domain *gpd = data; 166 + int ret; 167 167 168 - snprintf(auto_dev_name, sizeof(auto_dev_name), 169 - "%s.%d.auto", device_name, r); 170 - dev = bus_find_device_by_name(&platform_bus_type, NULL, auto_dev_name); 171 - dev_info(dev, "device %s added to pm domain\n", auto_dev_name); 168 + ret = pm_genpd_add_device(gpd, dev); 169 + if (ret) 170 + dev_err(dev, "Failed to add dev to genpd %d\n", ret); 172 171 173 - return dev; 172 + return ret; 173 + } 174 + 175 + static int acp_genpd_remove_device(struct device *dev, void *data) 176 + { 177 + int ret; 178 + 179 + ret = pm_genpd_remove_device(dev); 180 + if (ret) 181 + dev_err(dev, "Failed to remove dev from genpd %d\n", ret); 182 + 183 + /* Continue to remove */ 184 + return 0; 174 185 } 175 186 176 187 /** ··· 192 181 */ 193 182 static int acp_hw_init(void *handle) 194 183 { 195 - int r, i; 184 + int r; 196 185 uint64_t acp_base; 197 186 u32 val = 0; 198 187 u32 count = 0; 199 - struct device *dev; 200 188 struct i2s_platform_data *i2s_pdata = NULL; 201 189 202 190 struct amdgpu_device *adev = (struct amdgpu_device *)handle; ··· 351 341 if (r) 352 342 goto failure; 353 343 354 - for (i = 0; i < ACP_DEVS ; i++) { 355 - dev = get_mfd_cell_dev(adev->acp.acp_cell[i].name, i); 356 - r = pm_genpd_add_device(&adev->acp.acp_genpd->gpd, dev); 357 - if (r) { 358 - dev_err(dev, "Failed to add dev to genpd\n"); 359 - goto failure; 360 - } 361 - } 362 - 344 + r = device_for_each_child(adev->acp.parent, &adev->acp.acp_genpd->gpd, 345 + acp_genpd_add_device); 346 + if (r) 347 + goto failure; 363 348 364 349 /* Assert Soft reset of ACP */ 365 350 val = cgs_read_register(adev->acp.cgs_device, mmACP_SOFT_RESET); ··· 415 410 */ 416 411 static int acp_hw_fini(void *handle) 417 412 { 418 - int i, ret; 419 413 u32 val = 0; 420 414 u32 count = 0; 421 - struct device *dev; 422 415 struct amdgpu_device *adev = (struct amdgpu_device *)handle; 423 416 424 417 /* return early if no ACP */ ··· 461 458 udelay(100); 462 459 } 463 460 464 - for (i = 0; i < ACP_DEVS ; i++) { 465 - dev = get_mfd_cell_dev(adev->acp.acp_cell[i].name, i); 466 - ret = pm_genpd_remove_device(dev); 467 - /* If removal fails, dont giveup and try rest */ 468 - if (ret) 469 - dev_err(dev, "remove dev from genpd failed\n"); 470 - } 461 + device_for_each_child(adev->acp.parent, NULL, 462 + acp_genpd_remove_device); 471 463 472 464 mfd_remove_devices(adev->acp.parent); 473 465 kfree(adev->acp.acp_res);