linux-kernel - Re: [PATCH] stacktrace: fix spaces and annoying extra newlines

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 for Android: free password hash cracker in your pocket

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

Date:   Tue, 7 Feb 2017 15:23:00 -0800
From:   Linus Torvalds <torvalds@...ux-foundation.org>
To:     Omar Sandoval <osandov@...ndov.com>
Cc:     Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
        kernel-team <kernel-team@...com>, Ingo Molnar <mingo@...nel.org>,
        Peter Zijlstra <peterz@...radead.org>,
        Thomas Gleixner <tglx@...utronix.de>
Subject: Re: [PATCH] stacktrace: fix spaces and annoying extra newlines

Hmm.

Looks ok, except I think we migth want to go even further:

On Tue, Feb 7, 2017 at 2:44 PM, Omar Sandoval <osandov@...ndov.com> wrote:
>
> Since KERN_CONT became meaningful again, lockdep stack traces have
> looked like this:

[ removed really ugly trace ]

> This is what it should look like:
>
> [    6.650322] -> #1 (B){+.+...}:
> [    6.651053]        [<ffffffff810d8873>] lock_acquire+0xc3/0x210
> [    6.652000]        [<ffffffff816f6414>] mutex_lock_nested+0x74/0x6d0
> [    6.652664]        [<ffffffffa01b43c3>] init_btrfs_fs+0x21/0x196 [btrfs]
> [    6.653288]        [<ffffffff81000472>] do_one_initcall+0x52/0x1b0
> [    6.653858]        [<ffffffff811a3ae6>] do_init_module+0x5f/0x209
> [    6.654426]        [<ffffffff81122f3d>] load_module+0x218d/0x2b80
> [    6.654992]        [<ffffffff81123bdb>] SyS_finit_module+0xeb/0x120
> [    6.655591]        [<ffffffff816fd241>] entry_SYSCALL_64_fastpath+0x1f/0xc2

That's still pretty ugly.

Actually, let's just remove those hex numbers too, which buy you nothing at all.

> -               printk("%*c", 1 + spaces, ' ');
> -               print_ip_sym(trace->entries[i]);
> +               ip = (void *)trace->entries[i];
> +               printk("%*c[<%p>] %pS\n", 1 + spaces, ' ', ip, ip);

So how does it look if we make that just be

        printk("%*c%pS\n", 1 + spaces, ' ', (void *)trace->entries[i]);

which also avoids the extra variable because the thing is only used
once anyway. We've removed the hex numbers from other printouts, and
they really are completely useless with modules and kernel randomized
addresses.

Would you mind testing such a thing and re-submitting?

               Linus