From 3f8f7b4ef6d97ba0015e675fd46c329869712e7e Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 1 Sep 2021 13:21:34 -0500 Subject: signal: Remove the bogus sigkill_pending in ptrace_stop commit 7d613f9f72ec8f90ddefcae038fdae5adb8404b3 upstream. The existence of sigkill_pending is a little silly as it is functionally a duplicate of fatal_signal_pending that is used in exactly one place. Checking for pending fatal signals and returning early in ptrace_stop is actively harmful. It casues the ptrace_stop called by ptrace_signal to return early before setting current->exit_code. Later when ptrace_signal reads the signal number from current->exit_code is undefined, making it unpredictable what will happen. Instead rely on the fact that schedule will not sleep if there is a pending signal that can awaken a task. Removing the explict sigkill_pending test fixes fixes ptrace_signal when ptrace_stop does not stop because current->exit_code is always set to to signr. Cc: stable@vger.kernel.org Fixes: 3d749b9e676b ("ptrace: simplify ptrace_stop()->sigkill_pending() path") Fixes: 1a669c2f16d4 ("Add arch_ptrace_stop") Link: https://lkml.kernel.org/r/87pmsyx29t.fsf@disp2133 Reviewed-by: Kees Cook Signed-off-by: "Eric W. Biederman" Signed-off-by: Greg Kroah-Hartman --- kernel/signal.c | 17 ++--------------- 1 file changed, 2 insertions(+), 15 deletions(-) (limited to 'kernel') diff --git a/kernel/signal.c b/kernel/signal.c index 6aa9ca45ebb1..a699055ebfe8 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1823,16 +1823,6 @@ static inline int may_ptrace_stop(void) return 1; } -/* - * Return non-zero if there is a SIGKILL that should be waking us up. - * Called with the siglock held. - */ -static int sigkill_pending(struct task_struct *tsk) -{ - return sigismember(&tsk->pending.signal, SIGKILL) || - sigismember(&tsk->signal->shared_pending.signal, SIGKILL); -} - /* * This must be called with current->sighand->siglock held. * @@ -1858,15 +1848,10 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info) * calling arch_ptrace_stop, so we must release it now. * To preserve proper semantics, we must do this before * any signal bookkeeping like checking group_stop_count. - * Meanwhile, a SIGKILL could come in before we retake the - * siglock. That must prevent us from sleeping in TASK_TRACED. - * So after regaining the lock, we must check for SIGKILL. */ spin_unlock_irq(¤t->sighand->siglock); arch_ptrace_stop(exit_code, info); spin_lock_irq(¤t->sighand->siglock); - if (sigkill_pending(current)) - return; } /* @@ -1875,6 +1860,8 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info) * Also, transition to TRACED and updates to ->jobctl should be * atomic with respect to siglock and should be done after the arch * hook as siglock is released and regrabbed across it. + * schedule() will not sleep if there is a pending signal that + * can awaken the task. */ set_current_state(TASK_TRACED); -- cgit v1.2.3 From e245b6ccaafb3c544b5b73133b254af44a53bc39 Mon Sep 17 00:00:00 2001 From: Ye Bin Date: Wed, 13 Oct 2021 20:19:14 +0800 Subject: PM: hibernate: Get block device exclusively in swsusp_check() [ Upstream commit 39fbef4b0f77f9c89c8f014749ca533643a37c9f ] The following kernel crash can be triggered: [ 89.266592] ------------[ cut here ]------------ [ 89.267427] kernel BUG at fs/buffer.c:3020! [ 89.268264] invalid opcode: 0000 [#1] SMP KASAN PTI [ 89.269116] CPU: 7 PID: 1750 Comm: kmmpd-loop0 Not tainted 5.10.0-862.14.0.6.x86_64-08610-gc932cda3cef4-dirty #20 [ 89.273169] RIP: 0010:submit_bh_wbc.isra.0+0x538/0x6d0 [ 89.277157] RSP: 0018:ffff888105ddfd08 EFLAGS: 00010246 [ 89.278093] RAX: 0000000000000005 RBX: ffff888124231498 RCX: ffffffffb2772612 [ 89.279332] RDX: 1ffff11024846293 RSI: 0000000000000008 RDI: ffff888124231498 [ 89.280591] RBP: ffff8881248cc000 R08: 0000000000000001 R09: ffffed1024846294 [ 89.281851] R10: ffff88812423149f R11: ffffed1024846293 R12: 0000000000003800 [ 89.283095] R13: 0000000000000001 R14: 0000000000000000 R15: ffff8881161f7000 [ 89.284342] FS: 0000000000000000(0000) GS:ffff88839b5c0000(0000) knlGS:0000000000000000 [ 89.285711] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 89.286701] CR2: 00007f166ebc01a0 CR3: 0000000435c0e000 CR4: 00000000000006e0 [ 89.287919] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 89.289138] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 89.290368] Call Trace: [ 89.290842] write_mmp_block+0x2ca/0x510 [ 89.292218] kmmpd+0x433/0x9a0 [ 89.294902] kthread+0x2dd/0x3e0 [ 89.296268] ret_from_fork+0x22/0x30 [ 89.296906] Modules linked in: by running the following commands: 1. mkfs.ext4 -O mmp /dev/sda -b 1024 2. mount /dev/sda /home/test 3. echo "/dev/sda" > /sys/power/resume That happens because swsusp_check() calls set_blocksize() on the target partition which confuses the file system: Thread1 Thread2 mount /dev/sda /home/test get s_mmp_bh --> has mapped flag start kmmpd thread echo "/dev/sda" > /sys/power/resume resume_store software_resume swsusp_check set_blocksize truncate_inode_pages_range truncate_cleanup_page block_invalidatepage discard_buffer --> clean mapped flag write_mmp_block submit_bh submit_bh_wbc BUG_ON(!buffer_mapped(bh)) To address this issue, modify swsusp_check() to open the target block device with exclusive access. Signed-off-by: Ye Bin [ rjw: Subject and changelog edits ] Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- kernel/power/swap.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 160e1006640d..a7630e7b22a5 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -1519,9 +1519,10 @@ end: int swsusp_check(void) { int error; + void *holder; hib_resume_bdev = blkdev_get_by_dev(swsusp_resume_device, - FMODE_READ, NULL); + FMODE_READ | FMODE_EXCL, &holder); if (!IS_ERR(hib_resume_bdev)) { set_blocksize(hib_resume_bdev, PAGE_SIZE); clear_page(swsusp_header); @@ -1541,7 +1542,7 @@ int swsusp_check(void) put: if (error) - blkdev_put(hib_resume_bdev, FMODE_READ); + blkdev_put(hib_resume_bdev, FMODE_READ | FMODE_EXCL); else pr_debug("PM: Image signature found, resuming\n"); } else { -- cgit v1.2.3 From 26efb10b1e2224af9b40f2a6917fbb53e4bd1387 Mon Sep 17 00:00:00 2001 From: Vincent Donnefort Date: Thu, 4 Nov 2021 17:51:20 +0000 Subject: sched/core: Mitigate race cpus_share_cache()/update_top_cache_domain() [ Upstream commit 42dc938a590c96eeb429e1830123fef2366d9c80 ] Nothing protects the access to the per_cpu variable sd_llc_id. When testing the same CPU (i.e. this_cpu == that_cpu), a race condition exists with update_top_cache_domain(). One scenario being: CPU1 CPU2 ================================================================== per_cpu(sd_llc_id, CPUX) => 0 partition_sched_domains_locked() detach_destroy_domains() cpus_share_cache(CPUX, CPUX) update_top_cache_domain(CPUX) per_cpu(sd_llc_id, CPUX) => 0 per_cpu(sd_llc_id, CPUX) = CPUX per_cpu(sd_llc_id, CPUX) => CPUX return false ttwu_queue_cond() wouldn't catch smp_processor_id() == cpu and the result is a warning triggered from ttwu_queue_wakelist(). Avoid a such race in cpus_share_cache() by always returning true when this_cpu == that_cpu. Fixes: 518cd6234178 ("sched: Only queue remote wakeups when crossing cache boundaries") Reported-by: Jing-Ting Wu Signed-off-by: Vincent Donnefort Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Valentin Schneider Reviewed-by: Vincent Guittot Link: https://lore.kernel.org/r/20211104175120.857087-1-vincent.donnefort@arm.com Signed-off-by: Sasha Levin --- kernel/sched/core.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 4a0a754f24c8..69c6c740da11 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1885,6 +1885,9 @@ out: bool cpus_share_cache(int this_cpu, int that_cpu) { + if (this_cpu == that_cpu) + return true; + return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu); } #endif /* CONFIG_SMP */ -- cgit v1.2.3