From b2f73922d119686323f14fbbe46587f863852328 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 30 Sep 2015 15:59:17 +0200 Subject: fs/proc, core/debug: Don't expose absolute kernel addresses via wchan So the /proc/PID/stat 'wchan' field (the 30th field, which contains the absolute kernel address of the kernel function a task is blocked in) leaks absolute kernel addresses to unprivileged user-space: seq_put_decimal_ull(m, ' ', wchan); The absolute address might also leak via /proc/PID/wchan as well, if KALLSYMS is turned off or if the symbol lookup fails for some reason: static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { unsigned long wchan; char symname[KSYM_NAME_LEN]; wchan = get_wchan(task); if (lookup_symbol_name(wchan, symname) < 0) { if (!ptrace_may_access(task, PTRACE_MODE_READ)) return 0; seq_printf(m, "%lu", wchan); } else { seq_printf(m, "%s", symname); } return 0; } This isn't ideal, because for example it trivially leaks the KASLR offset to any local attacker: fomalhaut:~> printf "%016lx\n" $(cat /proc/$$/stat | cut -d' ' -f35) ffffffff8123b380 Most real-life uses of wchan are symbolic: ps -eo pid:10,tid:10,wchan:30,comm and procps uses /proc/PID/wchan, not the absolute address in /proc/PID/stat: triton:~/tip> strace -f ps -eo pid:10,tid:10,wchan:30,comm 2>&1 | grep wchan | tail -1 open("/proc/30833/wchan", O_RDONLY) = 6 There's one compatibility quirk here: procps relies on whether the absolute value is non-zero - and we can provide that functionality by outputing "0" or "1" depending on whether the task is blocked (whether there's a wchan address). These days there appears to be very little legitimate reason user-space would be interested in the absolute address. The absolute address is mostly historic: from the days when we didn't have kallsyms and user-space procps had to do the decoding itself via the System.map. So this patch sets all numeric output to "0" or "1" and keeps only symbolic output, in /proc/PID/wchan. ( The absolute sleep address can generally still be profiled via perf, by tasks with sufficient privileges. ) Reviewed-by: Thomas Gleixner Acked-by: Kees Cook Acked-by: Linus Torvalds Cc: Cc: Al Viro Cc: Alexander Potapenko Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Denys Vlasenko Cc: Dmitry Vyukov Cc: Kostya Serebryany Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Peter Zijlstra Cc: Sasha Levin Cc: kasan-dev Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/r/20150930135917.GA3285@gmail.com Signed-off-by: Ingo Molnar --- fs/proc/array.c | 16 ++++++++++++++-- fs/proc/base.c | 9 +++------ 2 files changed, 17 insertions(+), 8 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/array.c b/fs/proc/array.c index f60f0121e331..eed2050db9be 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -375,7 +375,7 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task, int whole) { - unsigned long vsize, eip, esp, wchan = ~0UL; + unsigned long vsize, eip, esp, wchan = 0; int priority, nice; int tty_pgrp = -1, tty_nr = 0; sigset_t sigign, sigcatch; @@ -507,7 +507,19 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, seq_put_decimal_ull(m, ' ', task->blocked.sig[0] & 0x7fffffffUL); seq_put_decimal_ull(m, ' ', sigign.sig[0] & 0x7fffffffUL); seq_put_decimal_ull(m, ' ', sigcatch.sig[0] & 0x7fffffffUL); - seq_put_decimal_ull(m, ' ', wchan); + + /* + * We used to output the absolute kernel address, but that's an + * information leak - so instead we show a 0/1 flag here, to signal + * to user-space whether there's a wchan field in /proc/PID/wchan. + * + * This works with older implementations of procps as well. + */ + if (wchan) + seq_puts(m, " 1"); + else + seq_puts(m, " 0"); + seq_put_decimal_ull(m, ' ', 0); seq_put_decimal_ull(m, ' ', 0); seq_put_decimal_ll(m, ' ', task->exit_signal); diff --git a/fs/proc/base.c b/fs/proc/base.c index b25eee4cead5..29595af32866 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -430,13 +430,10 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns, wchan = get_wchan(task); - if (lookup_symbol_name(wchan, symname) < 0) { - if (!ptrace_may_access(task, PTRACE_MODE_READ)) - return 0; - seq_printf(m, "%lu", wchan); - } else { + if (wchan && ptrace_may_access(task, PTRACE_MODE_READ) && !lookup_symbol_name(wchan, symname)) seq_printf(m, "%s", symname); - } + else + seq_putc(m, '0'); return 0; } -- cgit