From 7d4df2dad312f270d62fecb0e5c8b086c6d7dcfc Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Mon, 29 Jul 2024 04:21:58 +0200 Subject: kcov: properly check for softirq context When collecting coverage from softirqs, KCOV uses in_serving_softirq() to check whether the code is running in the softirq context. Unfortunately, in_serving_softirq() is > 0 even when the code is running in the hardirq or NMI context for hardirqs and NMIs that happened during a softirq. As a result, if a softirq handler contains a remote coverage collection section and a hardirq with another remote coverage collection section happens during handling the softirq, KCOV incorrectly detects a nested softirq coverate collection section and prints a WARNING, as reported by syzbot. This issue was exposed by commit a7f3813e589f ("usb: gadget: dummy_hcd: Switch to hrtimer transfer scheduler"), which switched dummy_hcd to using hrtimer and made the timer's callback be executed in the hardirq context. Change the related checks in KCOV to account for this behavior of in_serving_softirq() and make KCOV ignore remote coverage collection sections in the hardirq and NMI contexts. This prevents the WARNING printed by syzbot but does not fix the inability of KCOV to collect coverage from the __usb_hcd_giveback_urb when dummy_hcd is in use (caused by a7f3813e589f); a separate patch is required for that. Link: https://lkml.kernel.org/r/20240729022158.92059-1-andrey.konovalov@linux.dev Fixes: 5ff3b30ab57d ("kcov: collect coverage from interrupts") Signed-off-by: Andrey Konovalov Reported-by: syzbot+2388cdaeb6b10f0c13ac@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=2388cdaeb6b10f0c13ac Acked-by: Marco Elver Cc: Alan Stern Cc: Aleksandr Nogikh Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Greg Kroah-Hartman Cc: Marcello Sylvester Bauer Cc: Signed-off-by: Andrew Morton --- kernel/kcov.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/kcov.c b/kernel/kcov.c index f0a69d402066..274b6b7c718d 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -161,6 +161,15 @@ static void kcov_remote_area_put(struct kcov_remote_area *area, kmsan_unpoison_memory(&area->list, sizeof(area->list)); } +/* + * Unlike in_serving_softirq(), this function returns false when called during + * a hardirq or an NMI that happened in the softirq context. + */ +static inline bool in_softirq_really(void) +{ + return in_serving_softirq() && !in_hardirq() && !in_nmi(); +} + static notrace bool check_kcov_mode(enum kcov_mode needed_mode, struct task_struct *t) { unsigned int mode; @@ -170,7 +179,7 @@ static notrace bool check_kcov_mode(enum kcov_mode needed_mode, struct task_stru * so we ignore code executed in interrupts, unless we are in a remote * coverage collection section in a softirq. */ - if (!in_task() && !(in_serving_softirq() && t->kcov_softirq)) + if (!in_task() && !(in_softirq_really() && t->kcov_softirq)) return false; mode = READ_ONCE(t->kcov_mode); /* @@ -849,7 +858,7 @@ void kcov_remote_start(u64 handle) if (WARN_ON(!kcov_check_handle(handle, true, true, true))) return; - if (!in_task() && !in_serving_softirq()) + if (!in_task() && !in_softirq_really()) return; local_lock_irqsave(&kcov_percpu_data.lock, flags); @@ -991,7 +1000,7 @@ void kcov_remote_stop(void) int sequence; unsigned long flags; - if (!in_task() && !in_serving_softirq()) + if (!in_task() && !in_softirq_really()) return; local_lock_irqsave(&kcov_percpu_data.lock, flags); -- cgit v1.2.3 From 6d45e1c948a8b7ed6ceddb14319af69424db730c Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Tue, 6 Aug 2024 13:46:47 -0400 Subject: padata: Fix possible divide-by-0 panic in padata_mt_helper() We are hit with a not easily reproducible divide-by-0 panic in padata.c at bootup time. [ 10.017908] Oops: divide error: 0000 1 PREEMPT SMP NOPTI [ 10.017908] CPU: 26 PID: 2627 Comm: kworker/u1666:1 Not tainted 6.10.0-15.el10.x86_64 #1 [ 10.017908] Hardware name: Lenovo ThinkSystem SR950 [7X12CTO1WW]/[7X12CTO1WW], BIOS [PSE140J-2.30] 07/20/2021 [ 10.017908] Workqueue: events_unbound padata_mt_helper [ 10.017908] RIP: 0010:padata_mt_helper+0x39/0xb0 : [ 10.017963] Call Trace: [ 10.017968] [ 10.018004] ? padata_mt_helper+0x39/0xb0 [ 10.018084] process_one_work+0x174/0x330 [ 10.018093] worker_thread+0x266/0x3a0 [ 10.018111] kthread+0xcf/0x100 [ 10.018124] ret_from_fork+0x31/0x50 [ 10.018138] ret_from_fork_asm+0x1a/0x30 [ 10.018147] Looking at the padata_mt_helper() function, the only way a divide-by-0 panic can happen is when ps->chunk_size is 0. The way that chunk_size is initialized in padata_do_multithreaded(), chunk_size can be 0 when the min_chunk in the passed-in padata_mt_job structure is 0. Fix this divide-by-0 panic by making sure that chunk_size will be at least 1 no matter what the input parameters are. Link: https://lkml.kernel.org/r/20240806174647.1050398-1-longman@redhat.com Fixes: 004ed42638f4 ("padata: add basic support for multithreaded jobs") Signed-off-by: Waiman Long Cc: Daniel Jordan Cc: Steffen Klassert Cc: Waiman Long Cc: Signed-off-by: Andrew Morton --- kernel/padata.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'kernel') diff --git a/kernel/padata.c b/kernel/padata.c index 53f4bc912712..0fa6c2895460 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -517,6 +517,13 @@ void __init padata_do_multithreaded(struct padata_mt_job *job) ps.chunk_size = max(ps.chunk_size, job->min_chunk); ps.chunk_size = roundup(ps.chunk_size, job->align); + /* + * chunk_size can be 0 if the caller sets min_chunk to 0. So force it + * to at least 1 to prevent divide-by-0 panic in padata_mt_helper().` + */ + if (!ps.chunk_size) + ps.chunk_size = 1U; + list_for_each_entry(pw, &works, pw_list) if (job->numa_aware) { int old_node = atomic_read(&last_used_nid); -- cgit v1.2.3