CVE-2024-50147

In the Linux kernel, the following vulnerability has been resolved:<br /> <br /> net/mlx5: Fix command bitmask initialization<br /> <br /> Command bitmask have a dedicated bit for MANAGE_PAGES command, this bit<br /> isn&amp;#39;t Initialize during command bitmask Initialization, only during<br /> MANAGE_PAGES.<br /> <br /> In addition, mlx5_cmd_trigger_completions() is trying to trigger<br /> completion for MANAGE_PAGES command as well.<br /> <br /> Hence, in case health error occurred before any MANAGE_PAGES command<br /> have been invoke (for example, during mlx5_enable_hca()),<br /> mlx5_cmd_trigger_completions() will try to trigger completion for<br /> MANAGE_PAGES command, which will result in null-ptr-deref error.[1]<br /> <br /> Fix it by Initialize command bitmask correctly.<br /> <br /> While at it, re-write the code for better understanding.<br /> <br /> [1]<br /> BUG: KASAN: null-ptr-deref in mlx5_cmd_trigger_completions+0x1db/0x600 [mlx5_core]<br /> Write of size 4 at addr 0000000000000214 by task kworker/u96:2/12078<br /> CPU: 10 PID: 12078 Comm: kworker/u96:2 Not tainted 6.9.0-rc2_for_upstream_debug_2024_04_07_19_01 #1<br /> Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014<br /> Workqueue: mlx5_health0000:08:00.0 mlx5_fw_fatal_reporter_err_work [mlx5_core]<br /> Call Trace:<br /> <br /> dump_stack_lvl+0x7e/0xc0<br /> kasan_report+0xb9/0xf0<br /> kasan_check_range+0xec/0x190<br /> mlx5_cmd_trigger_completions+0x1db/0x600 [mlx5_core]<br /> mlx5_cmd_flush+0x94/0x240 [mlx5_core]<br /> enter_error_state+0x6c/0xd0 [mlx5_core]<br /> mlx5_fw_fatal_reporter_err_work+0xf3/0x480 [mlx5_core]<br /> process_one_work+0x787/0x1490<br /> ? lockdep_hardirqs_on_prepare+0x400/0x400<br /> ? pwq_dec_nr_in_flight+0xda0/0xda0<br /> ? assign_work+0x168/0x240<br /> worker_thread+0x586/0xd30<br /> ? rescuer_thread+0xae0/0xae0<br /> kthread+0x2df/0x3b0<br /> ? kthread_complete_and_exit+0x20/0x20<br /> ret_from_fork+0x2d/0x70<br /> ? kthread_complete_and_exit+0x20/0x20<br /> ret_from_fork_asm+0x11/0x20<br />