CVE-2024-50098

En el kernel de Linux, se ha resuelto la siguiente vulnerabilidad: scsi: ufs: core: Establecer SDEV_OFFLINE cuando se apaga UFS. Hay un historial de interbloqueo si se realiza el reinicio al comienzo del arranque. SDEV_QUIESCE se estableció para todos los scsi_devices de LU por el apagado de UFS, y en ese momento el controlador de audio estaba esperando a blk_mq_submit_bio() sosteniendo un mutex_lock mientras leía el binario fw. Después de eso, ocurrió un problema de interbloqueo mientras el apagado del controlador de audio estaba esperando mutex_unlock de blk_mq_submit_bio(). Para resolver esto, establezca SDEV_OFFLINE para todas las LU excepto WLUN, de modo que cualquier E/S que se caiga después de un apagado de UFS devuelva un error. [ 31.907781]I[0: swapper/0: 0] 1 130705007 1651079834 11289729804 0 D( 2) 3 ffffff882e208000 * init [apagado_dispositivo] [ 31.907793]I[0: swapper/0: 0] Mutex: 0xffffff8849a2b8b0: owner[0xffffff882e28cb00 kworker/6:0 :49] [ 31.907806]I[0: swapper/0: 0] Rastreo de llamadas: [ 31.907810]I[0: swapper/0: 0] __switch_to+0x174/0x338 [ 31.907819]I[0: intercambiador/0: 0] __schedule+0x5ec/0x9cc [ 31.907826]I[0: intercambiador/0: 0] schedule+0x7c/0xe8 [ 31.907834]I[0: intercambiador/0: 0] schedule_preempt_disabled+0x24/0x40 [ 31.907842]I[0: intercambiador/0: 0] __mutex_lock+0x408/0xdac [ 31.907849]I[0: intercambiador/0: 0] __mutex_lock_slowpath+0x14/0x24 [ 31.907858]I[0: intercambiador/0: 0] mutex_lock+0x40/0xec [ 31.907866]I[0: intercambiador/0: 0] device_shutdown+0x108/0x280 [ 31.907875]I[0: intercambiador/0: 0] kernel_restart+0x4c/0x11c [ 31.907883]I[0: intercambiador/0: 0] __arm64_sys_reboot+0x15c/0x280 [ 31.907890]I[0: intercambiador/0: 0] invoke_syscall+0x70/0x158 [ 31.907899]I[0: intercambiador/0: 0] el0_svc_common+0xb4/0xf4 [ 31.907909]I[0: intercambiador/0: 0] do_el0_svc+0x2c/0xb0 [ 31.907918]I[0: intercambiador/0: 0] el0_svc+0x34/0xe0 [ 31.907928]I[0: intercambiador/0: 0] el0t_64_sync_handler+0x68/0xb4 [ 31.907937]I[0: intercambiador/0: 0] el0t_64_sync+0x1a0/0x1a4 [ 31.908774]I[0: intercambiador/0: 0] 49 0 11960702 11236868007 0 D( 2) 6 ffffff882e28cb00 * kworker/6:0 [__bio_queue_enter] [ 31.908783]I[0: swapper/0: 0] Rastreo de llamadas: [ 31.908788]I[0: swapper/0: 0] __switch_to+0x174/0x338 [ 31.908796]I[0: swapper/0: 0] __schedule+0x5ec/0x9cc [ 31.908803]I[0: swapper/0: 0] schedule+0x7c/0xe8 [ 31.908811]I[0: swapper/0: 0] __bio_queue_enter+0xb8/0x178 [ 31.908818]I[0: swapper/0: 0] blk_mq_submit_bio+0x194/0x67c [ 31.908827]I[0: intercambiador/0: 0] __submit_bio+0xb8/0x19c

In the Linux kernel, the following vulnerability has been resolved: scsi: ufs: core: Set SDEV_OFFLINE when UFS is shut down There is a history of deadlock if reboot is performed at the beginning of booting. SDEV_QUIESCE was set for all LU's scsi_devices by UFS shutdown, and at that time the audio driver was waiting on blk_mq_submit_bio() holding a mutex_lock while reading the fw binary. After that, a deadlock issue occurred while audio driver shutdown was waiting for mutex_unlock of blk_mq_submit_bio(). To solve this, set SDEV_OFFLINE for all LUs except WLUN, so that any I/O that comes down after a UFS shutdown will return an error. [ 31.907781]I[0: swapper/0: 0] 1 130705007 1651079834 11289729804 0 D( 2) 3 ffffff882e208000 * init [device_shutdown] [ 31.907793]I[0: swapper/0: 0] Mutex: 0xffffff8849a2b8b0: owner[0xffffff882e28cb00 kworker/6:0 :49] [ 31.907806]I[0: swapper/0: 0] Call trace: [ 31.907810]I[0: swapper/0: 0] __switch_to+0x174/0x338 [ 31.907819]I[0: swapper/0: 0] __schedule+0x5ec/0x9cc [ 31.907826]I[0: swapper/0: 0] schedule+0x7c/0xe8 [ 31.907834]I[0: swapper/0: 0] schedule_preempt_disabled+0x24/0x40 [ 31.907842]I[0: swapper/0: 0] __mutex_lock+0x408/0xdac [ 31.907849]I[0: swapper/0: 0] __mutex_lock_slowpath+0x14/0x24 [ 31.907858]I[0: swapper/0: 0] mutex_lock+0x40/0xec [ 31.907866]I[0: swapper/0: 0] device_shutdown+0x108/0x280 [ 31.907875]I[0: swapper/0: 0] kernel_restart+0x4c/0x11c [ 31.907883]I[0: swapper/0: 0] __arm64_sys_reboot+0x15c/0x280 [ 31.907890]I[0: swapper/0: 0] invoke_syscall+0x70/0x158 [ 31.907899]I[0: swapper/0: 0] el0_svc_common+0xb4/0xf4 [ 31.907909]I[0: swapper/0: 0] do_el0_svc+0x2c/0xb0 [ 31.907918]I[0: swapper/0: 0] el0_svc+0x34/0xe0 [ 31.907928]I[0: swapper/0: 0] el0t_64_sync_handler+0x68/0xb4 [ 31.907937]I[0: swapper/0: 0] el0t_64_sync+0x1a0/0x1a4 [ 31.908774]I[0: swapper/0: 0] 49 0 11960702 11236868007 0 D( 2) 6 ffffff882e28cb00 * kworker/6:0 [__bio_queue_enter] [ 31.908783]I[0: swapper/0: 0] Call trace: [ 31.908788]I[0: swapper/0: 0] __switch_to+0x174/0x338 [ 31.908796]I[0: swapper/0: 0] __schedule+0x5ec/0x9cc [ 31.908803]I[0: swapper/0: 0] schedule+0x7c/0xe8 [ 31.908811]I[0: swapper/0: 0] __bio_queue_enter+0xb8/0x178 [ 31.908818]I[0: swapper/0: 0] blk_mq_submit_bio+0x194/0x67c [ 31.908827]I[0: swapper/0: 0] __submit_bio+0xb8/0x19c