mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-25 20:35:17 +07:00
6d757753ce
Currently module unloading is broken in nouveau due to a rather annoying race condition resulting from nouveau_backlight.c having gone a bit stale over time: [ 1960.791143] ================================================================== [ 1960.791394] BUG: KASAN: use-after-free in nouveau_backlight_exit+0x112/0x150 [nouveau] [ 1960.791460] Read of size 4 at addr ffff88075accf350 by task zsh/11185 [ 1960.791521] [ 1960.791545] CPU: 7 PID: 11185 Comm: zsh Kdump: loaded Tainted: G O 4.18.0Lyude-Test+ #4 [ 1960.791580] Hardware name: LENOVO 20EQS64N0B/20EQS64N0B, BIOS N1EET79W (1.52 ) 07/13/2018 [ 1960.791628] Call Trace: [ 1960.791680] dump_stack+0xa4/0xfd [ 1960.791721] print_address_description+0x71/0x239 [ 1960.791833] ? nouveau_backlight_exit+0x112/0x150 [nouveau] [ 1960.791877] kasan_report.cold.6+0x242/0x2fe [ 1960.791919] __asan_report_load4_noabort+0x19/0x20 [ 1960.792012] nouveau_backlight_exit+0x112/0x150 [nouveau] [ 1960.792081] nouveau_display_destroy+0x76/0x150 [nouveau] [ 1960.792150] nouveau_drm_device_fini+0xb7/0x190 [nouveau] [ 1960.792265] nouveau_drm_device_remove+0x14b/0x1d0 [nouveau] [ 1960.792347] ? nouveau_cli_work_queue+0x2e0/0x2e0 [nouveau] [ 1960.792378] ? trace_hardirqs_on_caller+0x38b/0x570 [ 1960.792406] ? trace_hardirqs_on+0xd/0x10 [ 1960.792472] nouveau_drm_remove+0x37/0x50 [nouveau] [ 1960.792502] pci_device_remove+0x112/0x2d0 [ 1960.792530] ? pcibios_free_irq+0x10/0x10 [ 1960.792558] ? kasan_check_write+0x14/0x20 [ 1960.792587] device_release_driver_internal+0x35c/0x650 [ 1960.792617] device_release_driver+0x12/0x20 [ 1960.792643] pci_stop_bus_device+0x172/0x1e0 [ 1960.792671] pci_stop_and_remove_bus_device_locked+0x1a/0x30 [ 1960.792715] remove_store+0xcb/0xe0 [ 1960.792753] ? sriov_numvfs_store+0x2e0/0x2e0 [ 1960.792779] ? __lock_is_held+0xb5/0x140 [ 1960.792808] ? component_add+0x530/0x530 [ 1960.792834] dev_attr_store+0x3f/0x70 [ 1960.792859] ? sysfs_file_ops+0x11d/0x170 [ 1960.792885] sysfs_kf_write+0x104/0x150 [ 1960.792915] ? sysfs_file_ops+0x170/0x170 [ 1960.792940] kernfs_fop_write+0x24f/0x400 [ 1960.792978] ? __lock_acquire+0x6ea/0x47f0 [ 1960.793021] __vfs_write+0xeb/0x760 [ 1960.793048] ? kernel_read+0x130/0x130 [ 1960.793076] ? __lock_is_held+0xb5/0x140 [ 1960.793107] ? rcu_read_lock_sched_held+0xdd/0x110 [ 1960.793135] ? rcu_sync_lockdep_assert+0x78/0xb0 [ 1960.793162] ? __sb_start_write+0x183/0x220 [ 1960.793189] vfs_write+0x14d/0x4a0 [ 1960.793229] ksys_write+0xd2/0x1b0 [ 1960.793255] ? __ia32_sys_read+0xb0/0xb0 [ 1960.793298] ? fput+0x1d/0x120 [ 1960.793324] ? filp_close+0xf3/0x130 [ 1960.793349] ? entry_SYSCALL_64_after_hwframe+0x59/0xbe [ 1960.793380] __x64_sys_write+0x73/0xb0 [ 1960.793407] do_syscall_64+0xaa/0x400 [ 1960.793433] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 1960.793460] RIP: 0033:0x7f59df433164 [ 1960.793486] Code: 89 02 48 c7 c0 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 8d 05 81 38 2d 00 8b 00 85 c0 75 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 41 54 49 89 d4 55 48 89 f5 53 [ 1960.793541] RSP: 002b:00007ffd70ee2fb8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 1960.793576] RAX: ffffffffffffffda RBX: 0000000000000002 RCX: 00007f59df433164 [ 1960.793620] RDX: 0000000000000002 RSI: 00005578088640c0 RDI: 0000000000000001 [ 1960.793665] RBP: 00005578088640c0 R08: 00007f59df7038c0 R09: 00007f59e0995b80 [ 1960.793696] R10: 000000000000000a R11: 0000000000000246 R12: 00007f59df702760 [ 1960.793730] R13: 0000000000000002 R14: 00007f59df6fd760 R15: 0000000000000002 [ 1960.793768] [ 1960.793790] Allocated by task 11167: [ 1960.793816] save_stack+0x43/0xd0 [ 1960.793841] kasan_kmalloc+0xc4/0xe0 [ 1960.793880] kasan_slab_alloc+0x11/0x20 [ 1960.793905] kmem_cache_alloc+0xd7/0x270 [ 1960.793944] getname_flags+0xbd/0x520 [ 1960.793969] user_path_at_empty+0x23/0x50 [ 1960.793994] do_faccessat+0x1fc/0x5d0 [ 1960.794018] __x64_sys_access+0x59/0x80 [ 1960.794043] do_syscall_64+0xaa/0x400 [ 1960.794067] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 1960.794093] [ 1960.794127] Freed by task 11167: [ 1960.794152] save_stack+0x43/0xd0 [ 1960.794190] __kasan_slab_free+0x139/0x190 [ 1960.794215] kasan_slab_free+0xe/0x10 [ 1960.794239] kmem_cache_free+0xcb/0x2c0 [ 1960.794264] putname+0xad/0xe0 [ 1960.794287] filename_lookup.part.59+0x1f1/0x360 [ 1960.794313] user_path_at_empty+0x3e/0x50 [ 1960.794338] do_faccessat+0x1fc/0x5d0 [ 1960.794362] __x64_sys_access+0x59/0x80 [ 1960.794393] do_syscall_64+0xaa/0x400 [ 1960.794421] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 1960.794461] [ 1960.794483] The buggy address belongs to the object at ffff88075acceac0 [ 1960.794483] which belongs to the cache names_cache of size 4096 [ 1960.794540] The buggy address is located 2192 bytes inside of [ 1960.794540] 4096-byte region [ffff88075acceac0, ffff88075accfac0) [ 1960.794581] The buggy address belongs to the page: [ 1960.794609] page:ffffea001d6b3200 count:1 mapcount:0 mapping:ffff880778e4b1c0 index:0x0 compound_mapcount: 0 [ 1960.794651] flags: 0x8000000000008100(slab|head) [ 1960.794679] raw: 8000000000008100 ffffea001d39e808 ffffea001d39ea08 ffff880778e4b1c0 [ 1960.794739] raw: 0000000000000000 0000000000070007 00000001ffffffff 0000000000000000 [ 1960.794785] page dumped because: kasan: bad access detected [ 1960.794813] [ 1960.794834] Memory state around the buggy address: [ 1960.794861] ffff88075accf200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 1960.794894] ffff88075accf280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 1960.794925] >ffff88075accf300: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 1960.794956] ^ [ 1960.794985] ffff88075accf380: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 1960.795017] ffff88075accf400: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 1960.795061] ================================================================== [ 1960.795106] Disabling lock debugging due to kernel taint [ 1960.795131] ------------[ cut here ]------------ [ 1960.795148] ida_remove called for id=1802201963 which is not allocated. [ 1960.795193] WARNING: CPU: 7 PID: 11185 at lib/idr.c:521 ida_remove+0x184/0x210 [ 1960.795213] Modules linked in: nouveau(O) mxm_wmi ttm i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops drm joydev vfat fat intel_rapl x86_pkg_temp_thermal coretemp crc32_pclmul iTCO_wdt psmouse wmi_bmof mei_me tpm_tis mei tpm_tis_core tpm i2c_i801 thinkpad_acpi pcc_cpufreq crc32c_intel serio_raw xhci_pci xhci_hcd wmi video i2c_dev i2c_core [ 1960.795305] CPU: 7 PID: 11185 Comm: zsh Kdump: loaded Tainted: G B O 4.18.0Lyude-Test+ #4 [ 1960.795330] Hardware name: LENOVO 20EQS64N0B/20EQS64N0B, BIOS N1EET79W (1.52 ) 07/13/2018 [ 1960.795352] RIP: 0010:ida_remove+0x184/0x210 [ 1960.795370] Code: 4c 89 f7 e8 ae c8 00 00 eb 22 41 83 c4 02 4c 89 e8 41 83 fc 3f 0f 86 64 ff ff ff 44 89 fe 48 c7 c7 20 94 1e 83 e8 54 ed 81 fe <0f> 0b 48 b8 00 00 00 00 00 fc ff df 48 01 c3 c7 03 00 00 00 00 c7 [ 1960.795402] RSP: 0018:ffff88074d4df7b8 EFLAGS: 00010082 [ 1960.795421] RAX: 0000000000000000 RBX: 1ffff100e9a9befa RCX: ffffffff81479975 [ 1960.795440] RDX: 0000000000000000 RSI: 0000000000000008 RDI: ffff88077c1de690 [ 1960.795460] RBP: ffff88074d4df878 R08: ffffed00ef83bcd3 R09: ffffed00ef83bcd2 [ 1960.795479] R10: ffffed00ef83bcd2 R11: ffff88077c1de697 R12: 000000000000036b [ 1960.795498] R13: 0000000000000202 R14: ffffffffa0aa7fa0 R15: 000000006b6b6b6b [ 1960.795518] FS: 00007f59e0995b80(0000) GS:ffff88077c1c0000(0000) knlGS:0000000000000000 [ 1960.795553] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1960.795571] CR2: 00007f59e09a2010 CR3: 00000004a1a70005 CR4: 00000000003606e0 [ 1960.795596] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 1960.795629] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 1960.795649] Call Trace: [ 1960.795667] ? ida_destroy+0x1d0/0x1d0 [ 1960.795686] ? kasan_check_write+0x14/0x20 [ 1960.795704] ? do_raw_spin_lock+0xc2/0x1c0 [ 1960.795724] ida_simple_remove+0x26/0x40 [ 1960.795794] nouveau_backlight_exit+0x9d/0x150 [nouveau] [ 1960.795867] nouveau_display_destroy+0x76/0x150 [nouveau] [ 1960.795930] nouveau_drm_device_fini+0xb7/0x190 [nouveau] [ 1960.795989] nouveau_drm_device_remove+0x14b/0x1d0 [nouveau] [ 1960.796047] ? nouveau_cli_work_queue+0x2e0/0x2e0 [nouveau] [ 1960.796067] ? trace_hardirqs_on_caller+0x38b/0x570 [ 1960.796089] ? trace_hardirqs_on+0xd/0x10 [ 1960.796146] nouveau_drm_remove+0x37/0x50 [nouveau] [ 1960.796167] pci_device_remove+0x112/0x2d0 [ 1960.796186] ? pcibios_free_irq+0x10/0x10 [ 1960.796218] ? kasan_check_write+0x14/0x20 [ 1960.796237] device_release_driver_internal+0x35c/0x650 [ 1960.796257] device_release_driver+0x12/0x20 [ 1960.796289] pci_stop_bus_device+0x172/0x1e0 [ 1960.796308] pci_stop_and_remove_bus_device_locked+0x1a/0x30 [ 1960.796328] remove_store+0xcb/0xe0 [ 1960.796345] ? sriov_numvfs_store+0x2e0/0x2e0 [ 1960.796364] ? __lock_is_held+0xb5/0x140 [ 1960.796383] ? component_add+0x530/0x530 [ 1960.796401] dev_attr_store+0x3f/0x70 [ 1960.796419] ? sysfs_file_ops+0x11d/0x170 [ 1960.796436] sysfs_kf_write+0x104/0x150 [ 1960.796454] ? sysfs_file_ops+0x170/0x170 [ 1960.796471] kernfs_fop_write+0x24f/0x400 [ 1960.796488] ? __lock_acquire+0x6ea/0x47f0 [ 1960.796520] __vfs_write+0xeb/0x760 [ 1960.796538] ? kernel_read+0x130/0x130 [ 1960.796556] ? __lock_is_held+0xb5/0x140 [ 1960.796590] ? rcu_read_lock_sched_held+0xdd/0x110 [ 1960.796608] ? rcu_sync_lockdep_assert+0x78/0xb0 [ 1960.796626] ? __sb_start_write+0x183/0x220 [ 1960.796648] vfs_write+0x14d/0x4a0 [ 1960.796666] ksys_write+0xd2/0x1b0 [ 1960.796684] ? __ia32_sys_read+0xb0/0xb0 [ 1960.796701] ? fput+0x1d/0x120 [ 1960.796732] ? filp_close+0xf3/0x130 [ 1960.796749] ? entry_SYSCALL_64_after_hwframe+0x59/0xbe [ 1960.796768] __x64_sys_write+0x73/0xb0 [ 1960.796800] do_syscall_64+0xaa/0x400 [ 1960.796818] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 1960.796836] RIP: 0033:0x7f59df433164 [ 1960.796854] Code: 89 02 48 c7 c0 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 8d 05 81 38 2d 00 8b 00 85 c0 75 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 41 54 49 89 d4 55 48 89 f5 53 [ 1960.796884] RSP: 002b:00007ffd70ee2fb8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 1960.796906] RAX: ffffffffffffffda RBX: 0000000000000002 RCX: 00007f59df433164 [ 1960.796926] RDX: 0000000000000002 RSI: 00005578088640c0 RDI: 0000000000000001 [ 1960.796946] RBP: 00005578088640c0 R08: 00007f59df7038c0 R09: 00007f59e0995b80 [ 1960.796966] R10: 000000000000000a R11: 0000000000000246 R12: 00007f59df702760 [ 1960.796985] R13: 0000000000000002 R14: 00007f59df6fd760 R15: 0000000000000002 [ 1960.797008] irq event stamp: 509990 [ 1960.797026] hardirqs last enabled at (509989): [<ffffffff8119ff78>] flush_work+0x4b8/0x6d0 [ 1960.797063] hardirqs last disabled at (509990): [<ffffffff8297c395>] _raw_spin_lock_irqsave+0x25/0x60 [ 1960.797085] softirqs last enabled at (509744): [<ffffffff82c005ad>] __do_softirq+0x5ad/0x8c0 [ 1960.797121] softirqs last disabled at (509735): [<ffffffff8115aa15>] irq_exit+0x1a5/0x1e0 [ 1960.797142] ---[ end trace fb1342325f1846b8 ]--- While I haven't actually gone into the details of what's causing this to happen (maybe the kernel removes the backlight device in the device core before we get to it?), it doesn't really matter anyway because the way nouveau handles backlights has long since been deprecated. According to the documentation on the drm_connector->late_register() hook, the ->late_register() hook should be used for adding extra connector-related devices. Vice versa, the ->early_unregister() hook is meant to be used for removing those devices. So: gut nouveau_drm->bl_list and nouveau_drm->backlight, and replace them with per-connector backlight structures. Additionally, move backlight registration/teardown into the ->late_register() and ->early_unregister() hooks so that DRM can give us a chance to remove the backlight before the connector is even removed. This appears to fix the problem once and for all. Changes since v2: - Use NV_INFO_ONCE for printing GMUX information, since otherwise this will end up printing that message for as many times as we have connectors Signed-off-by: Lyude Paul <lyude@redhat.com> Reviewed-by: Karol Herbst <kherbst@redhat.com> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
92 lines
2.9 KiB
C
92 lines
2.9 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef __NOUVEAU_DISPLAY_H__
|
|
#define __NOUVEAU_DISPLAY_H__
|
|
#include "nouveau_drv.h"
|
|
#include <nvif/disp.h>
|
|
|
|
struct nouveau_framebuffer {
|
|
struct drm_framebuffer base;
|
|
struct nouveau_bo *nvbo;
|
|
struct nouveau_vma *vma;
|
|
u32 r_handle;
|
|
u32 r_format;
|
|
u32 r_pitch;
|
|
struct nvif_object h_base[4];
|
|
struct nvif_object h_core;
|
|
};
|
|
|
|
static inline struct nouveau_framebuffer *
|
|
nouveau_framebuffer(struct drm_framebuffer *fb)
|
|
{
|
|
return container_of(fb, struct nouveau_framebuffer, base);
|
|
}
|
|
|
|
int nouveau_framebuffer_new(struct drm_device *,
|
|
const struct drm_mode_fb_cmd2 *,
|
|
struct nouveau_bo *, struct nouveau_framebuffer **);
|
|
|
|
struct nouveau_page_flip_state {
|
|
struct list_head head;
|
|
struct drm_pending_vblank_event *event;
|
|
struct drm_crtc *crtc;
|
|
int bpp, pitch;
|
|
u64 offset;
|
|
};
|
|
|
|
struct nouveau_display {
|
|
void *priv;
|
|
void (*dtor)(struct drm_device *);
|
|
int (*init)(struct drm_device *);
|
|
void (*fini)(struct drm_device *);
|
|
|
|
struct nvif_disp disp;
|
|
|
|
struct drm_property *dithering_mode;
|
|
struct drm_property *dithering_depth;
|
|
struct drm_property *underscan_property;
|
|
struct drm_property *underscan_hborder_property;
|
|
struct drm_property *underscan_vborder_property;
|
|
/* not really hue and saturation: */
|
|
struct drm_property *vibrant_hue_property;
|
|
struct drm_property *color_vibrance_property;
|
|
|
|
struct drm_atomic_state *suspend;
|
|
};
|
|
|
|
static inline struct nouveau_display *
|
|
nouveau_display(struct drm_device *dev)
|
|
{
|
|
return nouveau_drm(dev)->display;
|
|
}
|
|
|
|
int nouveau_display_create(struct drm_device *dev);
|
|
void nouveau_display_destroy(struct drm_device *dev);
|
|
int nouveau_display_init(struct drm_device *dev);
|
|
void nouveau_display_fini(struct drm_device *dev, bool suspend, bool runtime);
|
|
int nouveau_display_suspend(struct drm_device *dev, bool runtime);
|
|
void nouveau_display_resume(struct drm_device *dev, bool runtime);
|
|
int nouveau_display_vblank_enable(struct drm_device *, unsigned int);
|
|
void nouveau_display_vblank_disable(struct drm_device *, unsigned int);
|
|
bool nouveau_display_scanoutpos(struct drm_device *, unsigned int,
|
|
bool, int *, int *, ktime_t *,
|
|
ktime_t *, const struct drm_display_mode *);
|
|
|
|
int nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb,
|
|
struct drm_pending_vblank_event *event,
|
|
uint32_t page_flip_flags,
|
|
struct drm_modeset_acquire_ctx *ctx);
|
|
int nouveau_finish_page_flip(struct nouveau_channel *,
|
|
struct nouveau_page_flip_state *);
|
|
|
|
int nouveau_display_dumb_create(struct drm_file *, struct drm_device *,
|
|
struct drm_mode_create_dumb *args);
|
|
int nouveau_display_dumb_map_offset(struct drm_file *, struct drm_device *,
|
|
u32 handle, u64 *offset);
|
|
|
|
void nouveau_hdmi_mode_set(struct drm_encoder *, struct drm_display_mode *);
|
|
|
|
struct drm_framebuffer *
|
|
nouveau_user_framebuffer_create(struct drm_device *, struct drm_file *,
|
|
const struct drm_mode_fb_cmd2 *);
|
|
#endif
|