| 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
| ||
|
Message-ID: <20191009132639.GF2359@hirez.programming.kicks-ass.net>
Date: Wed, 9 Oct 2019 15:26:39 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: Masami Hiramatsu <mhiramat@...nel.org>
Cc: linux-kernel@...r.kernel.org, x86@...nel.org,
Nadav Amit <nadav.amit@...il.com>,
Andy Lutomirski <luto@...nel.org>,
Dave Hansen <dave.hansen@...ux.intel.com>,
Song Liu <songliubraving@...com>,
Steven Rostedt <rostedt@...dmis.org>,
Daniel Bristot de Oliveira <bristot@...hat.com>,
paulmck@...nel.org
Subject: Re: x86/kprobes bug? (was: [PATCH 1/3] x86/alternatives: Teach
text_poke_bp() to emulate instructions)
On Wed, Oct 09, 2019 at 03:07:54PM +0200, Peter Zijlstra wrote:
> So from what I can tell of kernel/kprobes.c, what it does is something like:
>
> ARM: (__arm_kprobe)
> text_poke(INT3)
> /* guarantees nothing, INT3 will become visible at some point, maybe */
>
> (kprobe_optimizer)
> if (opt) {
> /* guarantees the bytes after INT3 are unused */
> syncrhonize_rcu_tasks();
> text_poke_bp(JMP32);
> /* implies IPI-sync, kprobe really is enabled */
> }
>
>
> DISARM: (__unregister_kprobe_top)
> if (opt) {
> text_poke_bp(INT3 + tail);
> /* implies IPI-sync, so tail is guaranteed visible */
> }
> text_poke(old);
>
>
> FREE: (__unregister_kprobe_bottom)
> /* guarantees 'old' is visible and the kprobe really is unused, maybe */
> synchronize_rcu();
> free();
>
>
> Now the problem is that I don't think the synchronize_rcu() at free
> implies enough to guarantee 'old' really is visible on all CPUs.
> Similarly, I don't think synchronize_rcu_tasks() is sufficient on the
> ARM side either. It only provides the guarantee -provided- the INT3 is
> actually visible. If it is not, all bets are off.
>
> I'd feel much better if we switch arch_arm_kprobe() over to using
> text_poke_bp(). Or at the very least add the on_each_cpu(do_sync_core)
> to it.
>
> Hmm?
So I suppose I'm suggesting we do something like the below on top of
what I already have here:
git://git.kernel.org/pub/scm/linux/kernel/git/peterz/queue.git x86/ftrace
All it needs are a few comments ;-) Also note how this nicely gets rid
of the one text_poke_bp(.emulate) user, so we can go and remove that as
well.
---
arch/x86/include/asm/text-patching.h | 1 +
arch/x86/kernel/alternative.c | 11 ++++++++---
arch/x86/kernel/kprobes/core.c | 1 +
arch/x86/kernel/kprobes/opt.c | 12 ++++--------
4 files changed, 14 insertions(+), 11 deletions(-)
diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index d553175212b3..d3269558e5b5 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -42,6 +42,7 @@ extern void text_poke_early(void *addr, const void *opcode, size_t len);
* an inconsistent instruction while you patch.
*/
extern void *text_poke(void *addr, const void *opcode, size_t len);
+extern void text_poke_sync(void);
extern void *text_poke_kgdb(void *addr, const void *opcode, size_t len);
extern int poke_int3_handler(struct pt_regs *regs);
extern void text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate);
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 34a08bc68e9a..9e81ab542190 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -936,6 +936,11 @@ static void do_sync_core(void *info)
sync_core();
}
+void text_poke_sync(void)
+{
+ on_each_cpu(do_sync_core, NULL, 1);
+}
+
struct text_poke_loc {
s32 rel_addr; /* addr := _stext + rel_addr */
s32 rel32;
@@ -1089,7 +1094,7 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
for (i = 0; i < nr_entries; i++)
text_poke(text_poke_addr(&tp[i]), &int3, sizeof(int3));
- on_each_cpu(do_sync_core, NULL, 1);
+ text_poke_sync();
/*
* Second step: update all but the first byte of the patched range.
@@ -1111,7 +1116,7 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
* not necessary and we'd be safe even without it. But
* better safe than sorry (plus there's not only Intel).
*/
- on_each_cpu(do_sync_core, NULL, 1);
+ text_poke_sync();
}
/*
@@ -1127,7 +1132,7 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
}
if (do_sync)
- on_each_cpu(do_sync_core, NULL, 1);
+ text_poke_sync();
/*
* sync_core() implies an smp_mb() and orders this store against
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 7e4a8a1c9d9a..8ae5170207b2 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -503,6 +503,7 @@ void arch_arm_kprobe(struct kprobe *p)
void arch_disarm_kprobe(struct kprobe *p)
{
text_poke(p->addr, &p->opcode, 1);
+ text_poke_sync();
}
void arch_remove_kprobe(struct kprobe *p)
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 36d7249f2145..30a2646cfc8a 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -446,14 +446,10 @@ void arch_optimize_kprobes(struct list_head *oplist)
/* Replace a relative jump with a breakpoint (int3). */
void arch_unoptimize_kprobe(struct optimized_kprobe *op)
{
- u8 insn_buff[JMP32_INSN_SIZE];
-
- /* Set int3 to first byte for kprobes */
- insn_buff[0] = INT3_INSN_OPCODE;
- memcpy(insn_buff + 1, op->optinsn.copied_insn, DISP32_SIZE);
-
- text_poke_bp(op->kp.addr, insn_buff, JMP32_INSN_SIZE,
- text_gen_insn(JMP32_INSN_OPCODE, op->kp.addr, op->optinsn.insn));
+ arch_arm_kprobe(&op->kp);
+ text_poke(op->kp.addr + INT3_INSN_SIZE,
+ op->optinsn.copied_insn, DISP32_SIZE);
+ text_poke_sync();
}
/*
Powered by blists - more mailing lists