linux-kernel - Re: [PATCH] modules: lockdep: Suppress suspicious RCU usage warning

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-Id: <20191206102129.abe60bfefb78048d4ab1d3cc@kernel.org>
Date:   Fri, 6 Dec 2019 10:21:29 +0900
From:   Masami Hiramatsu <mhiramat@...nel.org>
To:     Jessica Yu <jeyu@...nel.org>
Cc:     Joel Fernandes <joel@...lfernandes.org>,
        Ingo Molnar <mingo@...nel.org>,
        Anders Roxell <anders.roxell@...aro.org>, paulmck@...nel.org,
        "Naveen N . Rao" <naveen.n.rao@...ux.ibm.com>,
        Anil S Keshavamurthy <anil.s.keshavamurthy@...el.com>,
        David Miller <davem@...emloft.net>,
        Linux Kernel Mailing List <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] modules: lockdep: Suppress suspicious RCU usage warning

On Thu, 5 Dec 2019 20:17:59 +0100
Jessica Yu <jeyu@...nel.org> wrote:

> +++ Masami Hiramatsu [03/12/19 15:14 +0900]:
> >While running kprobe module test, find_module_all() caused
> >a suspicious RCU usage warning.
> >
> >-----
> > =============================
> > WARNING: suspicious RCU usage
> > 5.4.0-next-20191202+ #63 Not tainted
> > -----------------------------
> > kernel/module.c:619 RCU-list traversed in non-reader section!!
> >
> > other info that might help us debug this:
> >
> >
> > rcu_scheduler_active = 2, debug_locks = 1
> > 1 lock held by rmmod/642:
> >  #0: ffffffff8227da80 (module_mutex){+.+.}, at: __x64_sys_delete_module+0x9a/0x230
> >
> > stack backtrace:
> > CPU: 0 PID: 642 Comm: rmmod Not tainted 5.4.0-next-20191202+ #63
> > Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014
> > Call Trace:
> >  dump_stack+0x71/0xa0
> >  find_module_all+0xc1/0xd0
> >  __x64_sys_delete_module+0xac/0x230
> >  ? do_syscall_64+0x12/0x1f0
> >  do_syscall_64+0x50/0x1f0
> >  entry_SYSCALL_64_after_hwframe+0x49/0xbe
> > RIP: 0033:0x4b6d49
> >-----
> >
> >This is because list_for_each_entry_rcu(modules) is called
> >without rcu_read_lock(). This is safe because the module_mutex
> >is locked.
> >
> >Pass lockdep_is_held(&module_lock) to the list_for_each_entry_rcu()
> 
> s/module_lock/module_mutex/, but you don't have to respin the patch
> just for this.

Oops.

> 
> >to suppress this warning, This also fixes similar issue in
> >mod_find() and each_symbol_section().
> >
> >Signed-off-by: Masami Hiramatsu <mhiramat@...nel.org>
> 
> Thanks Masami! This looks good. I'll queue this up shortly after the
> merge window.

Thank you for merging :)


> 
> Jessica
> 
> >---
> > kernel/module.c |    9 ++++++---
> > 1 file changed, 6 insertions(+), 3 deletions(-)
> >
> >diff --git a/kernel/module.c b/kernel/module.c
> >index cb6250be6ee9..38e5c6a7451b 100644
> >--- a/kernel/module.c
> >+++ b/kernel/module.c
> >@@ -214,7 +214,8 @@ static struct module *mod_find(unsigned long addr)
> > {
> > 	struct module *mod;
> >
> >-	list_for_each_entry_rcu(mod, &modules, list) {
> >+	list_for_each_entry_rcu(mod, &modules, list,
> >+				lockdep_is_held(&module_mutex)) {
> > 		if (within_module(addr, mod))
> > 			return mod;
> > 	}
> >@@ -448,7 +449,8 @@ bool each_symbol_section(bool (*fn)(const struct symsearch *arr,
> > 	if (each_symbol_in_section(arr, ARRAY_SIZE(arr), NULL, fn, data))
> > 		return true;
> >
> >-	list_for_each_entry_rcu(mod, &modules, list) {
> >+	list_for_each_entry_rcu(mod, &modules, list,
> >+				lockdep_is_held(&module_mutex)) {
> > 		struct symsearch arr[] = {
> > 			{ mod->syms, mod->syms + mod->num_syms, mod->crcs,
> > 			  NOT_GPL_ONLY, false },
> >@@ -616,7 +618,8 @@ static struct module *find_module_all(const char *name, size_t len,
> >
> > 	module_assert_mutex_or_preempt();
> >
> >-	list_for_each_entry_rcu(mod, &modules, list) {
> >+	list_for_each_entry_rcu(mod, &modules, list,
> >+				lockdep_is_held(&module_mutex)) {
> > 		if (!even_unformed && mod->state == MODULE_STATE_UNFORMED)
> > 			continue;
> > 		if (strlen(mod->name) == len && !memcmp(mod->name, name, len))
> >


-- 
Masami Hiramatsu <mhiramat@...nel.org>