Re: [PATCH] drm/sched: fix null-ptr-deref in init entity
Am 15.03.24 um 15:12 schrieb Alex Deucher: On Fri, Mar 15, 2024 at 10:12 AM Christian König wrote: Am 15.03.24 um 03:39 schrieb [email protected]: From: Vitaly Prosyak The bug can be triggered by sending an amdgpu_cs_wait_ioctl to the AMDGPU DRM driver on any ASICs with valid context. The bug was reported by Joonkyo Jung . For example the following code: static void Syzkaller2(int fd) { union drm_amdgpu_ctx arg1; union drm_amdgpu_wait_cs arg2; arg1.in.op = AMDGPU_CTX_OP_ALLOC_CTX; ret = drmIoctl(fd, 0x140106442 /* amdgpu_ctx_ioctl */, &arg1); arg2.in.handle = 0x0; arg2.in.timeout = 0x2; arg2.in.ip_type = AMD_IP_VPE /* 0x9 */; arg2->in.ip_instance = 0x0; arg2.in.ring = 0x0; arg2.in.ctx_id = arg1.out.alloc.ctx_id; drmIoctl(fd, 0xc0206449 /* AMDGPU_WAIT_CS * /, &arg2); } The ioctl AMDGPU_WAIT_CS without previously submitted job could be assumed that the error should be returned, but the following commit 1decbf6bb0b4dc56c9da6c5e57b994ebfc2be3aa modified the logic and allowed to have sched_rq equal to NULL. As a result when there is no job the ioctl AMDGPU_WAIT_CS returns success. The change fixes null-ptr-deref in init entity and the stack below demonstrates the error condition: [ +0.07] BUG: kernel NULL pointer dereference, address: 0028 [ +0.007086] #PF: supervisor read access in kernel mode [ +0.005234] #PF: error_code(0x) - not-present page [ +0.005232] PGD 0 P4D 0 [ +0.002501] Oops: [#1] PREEMPT SMP KASAN NOPTI [ +0.005034] CPU: 10 PID: 9229 Comm: amd_basic Tainted: GB WL 6.7.0+ #4 [ +0.007797] Hardware name: ASUS System Product Name/ROG STRIX B550-F GAMING (WI-FI), BIOS 1401 12/03/2020 [ +0.009798] RIP: 0010:drm_sched_entity_init+0x2d3/0x420 [gpu_sched] [ +0.006426] Code: 80 00 00 00 00 00 00 00 e8 1a 81 82 e0 49 89 9c 24 c0 00 00 00 4c 89 ef e8 4a 80 82 e0 49 8b 5d 00 48 8d 7b 28 e8 3d 80 82 e0 <48> 83 7b 28 00 0f 84 28 01 00 00 4d 8d ac 24 98 00 00 00 49 8d 5c [ +0.019094] RSP: 0018:c90014c1fa40 EFLAGS: 00010282 [ +0.005237] RAX: 0001 RBX: RCX: 8113f3fa [ +0.007326] RDX: fbfff0a7889d RSI: 0008 RDI: 853c44e0 [ +0.007264] RBP: c90014c1fa80 R08: 0001 R09: fbfff0a7889c [ +0.007266] R10: 853c44e7 R11: 0001 R12: 8881a719b010 [ +0.007263] R13: 88810d412748 R14: 0002 R15: [ +0.007264] FS: 77045540() GS:8883cc90() knlGS: [ +0.008236] CS: 0010 DS: ES: CR0: 80050033 [ +0.005851] CR2: 0028 CR3: 00011912e000 CR4: 00350ef0 [ +0.007175] Call Trace: [ +0.002561] [ +0.002141] ? show_regs+0x6a/0x80 [ +0.003473] ? __die+0x25/0x70 [ +0.003124] ? page_fault_oops+0x214/0x720 [ +0.004179] ? preempt_count_sub+0x18/0xc0 [ +0.004093] ? __pfx_page_fault_oops+0x10/0x10 [ +0.004590] ? srso_return_thunk+0x5/0x5f [ +0.004000] ? vprintk_default+0x1d/0x30 [ +0.004063] ? srso_return_thunk+0x5/0x5f [ +0.004087] ? vprintk+0x5c/0x90 [ +0.003296] ? drm_sched_entity_init+0x2d3/0x420 [gpu_sched] [ +0.005807] ? srso_return_thunk+0x5/0x5f [ +0.004090] ? _printk+0xb3/0xe0 [ +0.003293] ? __pfx__printk+0x10/0x10 [ +0.003735] ? asm_sysvec_apic_timer_interrupt+0x1b/0x20 [ +0.005482] ? do_user_addr_fault+0x345/0x770 [ +0.004361] ? exc_page_fault+0x64/0xf0 [ +0.003972] ? asm_exc_page_fault+0x27/0x30 [ +0.004271] ? add_taint+0x2a/0xa0 [ +0.003476] ? drm_sched_entity_init+0x2d3/0x420 [gpu_sched] [ +0.005812] amdgpu_ctx_get_entity+0x3f9/0x770 [amdgpu] [ +0.009530] ? finish_task_switch.isra.0+0x129/0x470 [ +0.005068] ? __pfx_amdgpu_ctx_get_entity+0x10/0x10 [amdgpu] [ +0.010063] ? __kasan_check_write+0x14/0x20 [ +0.004356] ? srso_return_thunk+0x5/0x5f [ +0.004001] ? mutex_unlock+0x81/0xd0 [ +0.003802] ? srso_return_thunk+0x5/0x5f [ +0.004096] amdgpu_cs_wait_ioctl+0xf6/0x270 [amdgpu] [ +0.009355] ? __pfx_amdgpu_cs_wait_ioctl+0x10/0x10 [amdgpu] [ +0.009981] ? srso_return_thunk+0x5/0x5f [ +0.004089] ? srso_return_thunk+0x5/0x5f [ +0.004090] ? __srcu_read_lock+0x20/0x50 [ +0.004096] drm_ioctl_kernel+0x140/0x1f0 [drm] [ +0.005080] ? __pfx_amdgpu_cs_wait_ioctl+0x10/0x10 [amdgpu] [ +0.009974] ? __pfx_drm_ioctl_kernel+0x10/0x10 [drm] [ +0.005618] ? srso_return_thunk+0x5/0x5f [ +0.004088] ? __kasan_check_write+0x14/0x20 [ +0.004357] drm_ioctl+0x3da/0x730 [drm] [ +0.004461] ? __pfx_amdgpu_cs_wait_ioctl+0x10/0x10 [amdgpu] [ +0.009979] ? __pfx_drm_ioctl+0x10/0x10 [drm] [ +0.004993] ? srso_return_thunk+0x5/0x5f [ +0.004090] ? __kasan_check_write+0x14/0x20 [ +0.004356] ? srso_return_thunk+0x5/0x5f [ +0.004090] ? _raw_spin_lock_irqsave+0x99/0x100 [ +0.004712] ? __pfx__raw_spin_lock_irqsave+0x10/0x10 [ +0.005063] ? __pfx_arch_do_signal_or_restart+0x10/0x10 [ +0.005477]
Re: [PATCH] drm/sched: fix null-ptr-deref in init entity
On Fri, Mar 15, 2024 at 10:12 AM Christian König wrote: > > Am 15.03.24 um 03:39 schrieb [email protected]: > > From: Vitaly Prosyak > > > > The bug can be triggered by sending an amdgpu_cs_wait_ioctl > > to the AMDGPU DRM driver on any ASICs with valid context. > > The bug was reported by Joonkyo Jung . > > For example the following code: > > > > static void Syzkaller2(int fd) > > { > > union drm_amdgpu_ctx arg1; > > union drm_amdgpu_wait_cs arg2; > > > > arg1.in.op = AMDGPU_CTX_OP_ALLOC_CTX; > > ret = drmIoctl(fd, 0x140106442 /* amdgpu_ctx_ioctl */, &arg1); > > > > arg2.in.handle = 0x0; > > arg2.in.timeout = 0x2; > > arg2.in.ip_type = AMD_IP_VPE /* 0x9 */; > > arg2->in.ip_instance = 0x0; > > arg2.in.ring = 0x0; > > arg2.in.ctx_id = arg1.out.alloc.ctx_id; > > > > drmIoctl(fd, 0xc0206449 /* AMDGPU_WAIT_CS * /, &arg2); > > } > > > > The ioctl AMDGPU_WAIT_CS without previously submitted job could be assumed > > that > > the error should be returned, but the following commit > > 1decbf6bb0b4dc56c9da6c5e57b994ebfc2be3aa > > modified the logic and allowed to have sched_rq equal to NULL. > > > > As a result when there is no job the ioctl AMDGPU_WAIT_CS returns success. > > The change fixes null-ptr-deref in init entity and the stack below > > demonstrates > > the error condition: > > > > [ +0.07] BUG: kernel NULL pointer dereference, address: > > 0028 > > [ +0.007086] #PF: supervisor read access in kernel mode > > [ +0.005234] #PF: error_code(0x) - not-present page > > [ +0.005232] PGD 0 P4D 0 > > [ +0.002501] Oops: [#1] PREEMPT SMP KASAN NOPTI > > [ +0.005034] CPU: 10 PID: 9229 Comm: amd_basic Tainted: GB WL > > 6.7.0+ #4 > > [ +0.007797] Hardware name: ASUS System Product Name/ROG STRIX B550-F > > GAMING (WI-FI), BIOS 1401 12/03/2020 > > [ +0.009798] RIP: 0010:drm_sched_entity_init+0x2d3/0x420 [gpu_sched] > > [ +0.006426] Code: 80 00 00 00 00 00 00 00 e8 1a 81 82 e0 49 89 9c 24 c0 > > 00 00 00 4c 89 ef e8 4a 80 82 e0 49 8b 5d 00 48 8d 7b 28 e8 3d 80 82 e0 > > <48> 83 7b 28 00 0f 84 28 01 00 00 4d 8d ac 24 98 00 00 00 49 8d 5c > > [ +0.019094] RSP: 0018:c90014c1fa40 EFLAGS: 00010282 > > [ +0.005237] RAX: 0001 RBX: RCX: > > 8113f3fa > > [ +0.007326] RDX: fbfff0a7889d RSI: 0008 RDI: > > 853c44e0 > > [ +0.007264] RBP: c90014c1fa80 R08: 0001 R09: > > fbfff0a7889c > > [ +0.007266] R10: 853c44e7 R11: 0001 R12: > > 8881a719b010 > > [ +0.007263] R13: 88810d412748 R14: 0002 R15: > > > > [ +0.007264] FS: 77045540() GS:8883cc90() > > knlGS: > > [ +0.008236] CS: 0010 DS: ES: CR0: 80050033 > > [ +0.005851] CR2: 0028 CR3: 00011912e000 CR4: > > 00350ef0 > > [ +0.007175] Call Trace: > > [ +0.002561] > > [ +0.002141] ? show_regs+0x6a/0x80 > > [ +0.003473] ? __die+0x25/0x70 > > [ +0.003124] ? page_fault_oops+0x214/0x720 > > [ +0.004179] ? preempt_count_sub+0x18/0xc0 > > [ +0.004093] ? __pfx_page_fault_oops+0x10/0x10 > > [ +0.004590] ? srso_return_thunk+0x5/0x5f > > [ +0.004000] ? vprintk_default+0x1d/0x30 > > [ +0.004063] ? srso_return_thunk+0x5/0x5f > > [ +0.004087] ? vprintk+0x5c/0x90 > > [ +0.003296] ? drm_sched_entity_init+0x2d3/0x420 [gpu_sched] > > [ +0.005807] ? srso_return_thunk+0x5/0x5f > > [ +0.004090] ? _printk+0xb3/0xe0 > > [ +0.003293] ? __pfx__printk+0x10/0x10 > > [ +0.003735] ? asm_sysvec_apic_timer_interrupt+0x1b/0x20 > > [ +0.005482] ? do_user_addr_fault+0x345/0x770 > > [ +0.004361] ? exc_page_fault+0x64/0xf0 > > [ +0.003972] ? asm_exc_page_fault+0x27/0x30 > > [ +0.004271] ? add_taint+0x2a/0xa0 > > [ +0.003476] ? drm_sched_entity_init+0x2d3/0x420 [gpu_sched] > > [ +0.005812] amdgpu_ctx_get_entity+0x3f9/0x770 [amdgpu] > > [ +0.009530] ? finish_task_switch.isra.0+0x129/0x470 > > [ +0.005068] ? __pfx_amdgpu_ctx_get_entity+0x10/0x10 [amdgpu] > > [ +0.010063] ? __kasan_check_write+0x14/0x20 > > [ +0.004356] ? srso_return_thunk+0x5/0x5f > > [ +0.004001] ? mutex_unlock+0x81/0xd0 > > [ +0.003802] ? srso_return_thunk+0x5/0x5f > > [ +0.004096] amdgpu_cs_wait_ioctl+0xf6/0x270 [amdgpu] > > [ +0.009355] ? __pfx_amdgpu_cs_wait_ioctl+0x10/0x10 [amdgpu] > > [ +0.009981] ? srso_return_thunk+0x5/0x5f > > [ +0.004089] ? srso_return_thunk+0x5/0x5f > > [ +0.004090] ? __srcu_read_lock+0x20/0x50 > > [ +0.004096] drm_ioctl_kernel+0x140/0x1f0 [drm] > > [ +0.005080] ? __pfx_amdgpu_cs_wait_ioctl+0x10/0x10 [amdgpu] > > [ +0.009974] ? __pfx_drm_ioctl_kernel+0x10/0x10 [drm] > > [ +0.005618] ? srso_return_thunk+0x5/0x5f > > [ +0.004088] ? __kasan_check_write+0x14/0x20 > > [ +0.004357] drm_ioctl+0x3da/0x730 [drm] > > [ +0.004461] ? __pfx_amdgpu_cs_wait_ioctl+0x10/0x10 [amdgp
Re: [PATCH] drm/sched: fix null-ptr-deref in init entity
Am 15.03.24 um 03:39 schrieb [email protected]: From: Vitaly Prosyak The bug can be triggered by sending an amdgpu_cs_wait_ioctl to the AMDGPU DRM driver on any ASICs with valid context. The bug was reported by Joonkyo Jung . For example the following code: static void Syzkaller2(int fd) { union drm_amdgpu_ctx arg1; union drm_amdgpu_wait_cs arg2; arg1.in.op = AMDGPU_CTX_OP_ALLOC_CTX; ret = drmIoctl(fd, 0x140106442 /* amdgpu_ctx_ioctl */, &arg1); arg2.in.handle = 0x0; arg2.in.timeout = 0x2; arg2.in.ip_type = AMD_IP_VPE /* 0x9 */; arg2->in.ip_instance = 0x0; arg2.in.ring = 0x0; arg2.in.ctx_id = arg1.out.alloc.ctx_id; drmIoctl(fd, 0xc0206449 /* AMDGPU_WAIT_CS * /, &arg2); } The ioctl AMDGPU_WAIT_CS without previously submitted job could be assumed that the error should be returned, but the following commit 1decbf6bb0b4dc56c9da6c5e57b994ebfc2be3aa modified the logic and allowed to have sched_rq equal to NULL. As a result when there is no job the ioctl AMDGPU_WAIT_CS returns success. The change fixes null-ptr-deref in init entity and the stack below demonstrates the error condition: [ +0.07] BUG: kernel NULL pointer dereference, address: 0028 [ +0.007086] #PF: supervisor read access in kernel mode [ +0.005234] #PF: error_code(0x) - not-present page [ +0.005232] PGD 0 P4D 0 [ +0.002501] Oops: [#1] PREEMPT SMP KASAN NOPTI [ +0.005034] CPU: 10 PID: 9229 Comm: amd_basic Tainted: GB WL 6.7.0+ #4 [ +0.007797] Hardware name: ASUS System Product Name/ROG STRIX B550-F GAMING (WI-FI), BIOS 1401 12/03/2020 [ +0.009798] RIP: 0010:drm_sched_entity_init+0x2d3/0x420 [gpu_sched] [ +0.006426] Code: 80 00 00 00 00 00 00 00 e8 1a 81 82 e0 49 89 9c 24 c0 00 00 00 4c 89 ef e8 4a 80 82 e0 49 8b 5d 00 48 8d 7b 28 e8 3d 80 82 e0 <48> 83 7b 28 00 0f 84 28 01 00 00 4d 8d ac 24 98 00 00 00 49 8d 5c [ +0.019094] RSP: 0018:c90014c1fa40 EFLAGS: 00010282 [ +0.005237] RAX: 0001 RBX: RCX: 8113f3fa [ +0.007326] RDX: fbfff0a7889d RSI: 0008 RDI: 853c44e0 [ +0.007264] RBP: c90014c1fa80 R08: 0001 R09: fbfff0a7889c [ +0.007266] R10: 853c44e7 R11: 0001 R12: 8881a719b010 [ +0.007263] R13: 88810d412748 R14: 0002 R15: [ +0.007264] FS: 77045540() GS:8883cc90() knlGS: [ +0.008236] CS: 0010 DS: ES: CR0: 80050033 [ +0.005851] CR2: 0028 CR3: 00011912e000 CR4: 00350ef0 [ +0.007175] Call Trace: [ +0.002561] [ +0.002141] ? show_regs+0x6a/0x80 [ +0.003473] ? __die+0x25/0x70 [ +0.003124] ? page_fault_oops+0x214/0x720 [ +0.004179] ? preempt_count_sub+0x18/0xc0 [ +0.004093] ? __pfx_page_fault_oops+0x10/0x10 [ +0.004590] ? srso_return_thunk+0x5/0x5f [ +0.004000] ? vprintk_default+0x1d/0x30 [ +0.004063] ? srso_return_thunk+0x5/0x5f [ +0.004087] ? vprintk+0x5c/0x90 [ +0.003296] ? drm_sched_entity_init+0x2d3/0x420 [gpu_sched] [ +0.005807] ? srso_return_thunk+0x5/0x5f [ +0.004090] ? _printk+0xb3/0xe0 [ +0.003293] ? __pfx__printk+0x10/0x10 [ +0.003735] ? asm_sysvec_apic_timer_interrupt+0x1b/0x20 [ +0.005482] ? do_user_addr_fault+0x345/0x770 [ +0.004361] ? exc_page_fault+0x64/0xf0 [ +0.003972] ? asm_exc_page_fault+0x27/0x30 [ +0.004271] ? add_taint+0x2a/0xa0 [ +0.003476] ? drm_sched_entity_init+0x2d3/0x420 [gpu_sched] [ +0.005812] amdgpu_ctx_get_entity+0x3f9/0x770 [amdgpu] [ +0.009530] ? finish_task_switch.isra.0+0x129/0x470 [ +0.005068] ? __pfx_amdgpu_ctx_get_entity+0x10/0x10 [amdgpu] [ +0.010063] ? __kasan_check_write+0x14/0x20 [ +0.004356] ? srso_return_thunk+0x5/0x5f [ +0.004001] ? mutex_unlock+0x81/0xd0 [ +0.003802] ? srso_return_thunk+0x5/0x5f [ +0.004096] amdgpu_cs_wait_ioctl+0xf6/0x270 [amdgpu] [ +0.009355] ? __pfx_amdgpu_cs_wait_ioctl+0x10/0x10 [amdgpu] [ +0.009981] ? srso_return_thunk+0x5/0x5f [ +0.004089] ? srso_return_thunk+0x5/0x5f [ +0.004090] ? __srcu_read_lock+0x20/0x50 [ +0.004096] drm_ioctl_kernel+0x140/0x1f0 [drm] [ +0.005080] ? __pfx_amdgpu_cs_wait_ioctl+0x10/0x10 [amdgpu] [ +0.009974] ? __pfx_drm_ioctl_kernel+0x10/0x10 [drm] [ +0.005618] ? srso_return_thunk+0x5/0x5f [ +0.004088] ? __kasan_check_write+0x14/0x20 [ +0.004357] drm_ioctl+0x3da/0x730 [drm] [ +0.004461] ? __pfx_amdgpu_cs_wait_ioctl+0x10/0x10 [amdgpu] [ +0.009979] ? __pfx_drm_ioctl+0x10/0x10 [drm] [ +0.004993] ? srso_return_thunk+0x5/0x5f [ +0.004090] ? __kasan_check_write+0x14/0x20 [ +0.004356] ? srso_return_thunk+0x5/0x5f [ +0.004090] ? _raw_spin_lock_irqsave+0x99/0x100 [ +0.004712] ? __pfx__raw_spin_lock_irqsave+0x10/0x10 [ +0.005063] ? __pfx_arch_do_signal_or_restart+0x10/0x10 [ +0.005477] ? srso_return_thunk+0x5/0x5f [ +0.004000] ? preempt_count_sub+0x18/0xc0 [ +0.004237] ? srs
