x86/kprobes: Fix KRETPROBES when CONFIG_KRETPROBE_ON_RETHOOK is set
PATCH 1/1 x86/kprobes: Fix KRETPROBES when CONFIG_KRETPROBE_ON_RETHOOK is set
[PATCH bpf] x86/kprobes: Fix KRETPROBES when CONFIG_KRETPROBE_ON_RETHOOK is set
The recent kernel change "kprobes: Use rethook for kretprobe if possible", introduced a potential NULL pointer dereference bug in the KRETPROBE mechanism. The official Kprobes documentation defines that "Any or all handlers can be NULL". Unfortunately, there is a missing return handler verification to fulfill these requirements and can result in a NULL pointer dereference bug.
This patch adds such verification in kretprobe_rethook_handler() function.
--- kernel/kprobes.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
kernel/kprobes.c +1 -1
@@ -2126,7 +2126,7 @@ static void kretprobe_rethook_handler(struct rethook_node *rh, void *data,struct kprobe_ctlblk *kcb;/* The data must NOT be null. This means rethook data structure is broken. */ -if (WARN_ON_ONCE (!data)) +if (WARN_ON_ONCE (!data) || !rp->handler)return ;__this_cpu_write (current_kprobe, &rp->kp);
Signature · 2 lines
pi3 (pi3ki31ny) - pi3 (at) itsec pl http://pi3.com.pl
Daniel Borkmann
maintainerQuoted 9 lines · Adam Zabrocki
[PATCH bpf] x86/kprobes: Fix KRETPROBES when
CONFIG_KRETPROBE_ON_RETHOOKis setThe recent kernel change "kprobes: Use rethook for kretprobe if possible", introduced a potential NULL pointer dereference bug in the KRETPROBE mechanism. The official Kprobes documentation defines that "Any or all handlers can be NULL". Unfortunately, there is a missing return handler verification to fulfill these requirements and can result in a NULL pointer dereference bug.
Quoted 5 lines
This patch adds such verification in
kretprobe_rethook_handler()function.Fixes 73f9b911faa7 ("kprobes: Use rethook for kretprobe if possible")Signed-off-by Adam Zabrocki <[email protected]>Acked-by Masami Hiramatsu <[email protected]>
I don't mind if this fix gets routed via bpf tree if all parties are okay with it (Masami? Steven?). Just noting that there is currently no specific dependency in bpf tree for it, but if it's easier to route this way, happy to take it.
Quoted 10 lines
--- kernel/kprobes.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)kernel/kprobes.c +0
-0
kernel/kprobes.c static void kretprobe_rethook_handler(struct rethook_node *rh, void *data, · line 2132
Quoted 8 lines
kernel/kprobes.c +1
-1@@ -2126,7 +2126,7 @@ static void kretprobe_rethook_handler(struct rethook_node *rh, void *data,struct kprobe_ctlblk *kcb;/* The data must NOT be null. This means rethook data structure is broken. */ -if (WARN_ON_ONCE (!data)) +if (WARN_ON_ONCE (!data) || !rp->handler)return ;__this_cpu_write (current_kprobe, &rp->kp);
Thanks,
Daniel
Masami Hiramatsu
maintainerQuoted 12 lines · On Mon, 25 Apr 2022 16:42:12 +0200 Daniel Borkmann <[email protected]> wrote:
Quoted 11 lines · Adam Zabrocki
[PATCH bpf] x86/kprobes: Fix KRETPROBES when
CONFIG_KRETPROBE_ON_RETHOOKis setThe recent kernel change "kprobes: Use rethook for kretprobe if possible", introduced a potential NULL pointer dereference bug in the KRETPROBE mechanism. The official Kprobes documentation defines that "Any or all handlers can be NULL". Unfortunately, there is a missing return handler verification to fulfill these requirements and can result in a NULL pointer dereference bug.
This patch adds such verification in
kretprobe_rethook_handler()function.
Quoted 7 lines
Quoted 3 lines
Fixes 73f9b911faa7 ("kprobes: Use rethook for kretprobe if possible")Signed-off-by Adam Zabrocki <[email protected]>Acked-by Masami Hiramatsu <[email protected]>I don't mind if this fix gets routed via bpf tree if all parties are okay with it (Masami? Steven?). Just noting that there is currently no specific dependency in bpf tree for it, but if it's easier to route this way, happy to take it.
Yeah, I and Steve talked about it and he suggested this to be merged via BPF tree since the original commit came from the BPF tree.
Thank you,
Quoted 22 lines
Quoted 11 lines
--- kernel/kprobes.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)kernel/kprobes.c +0
-0kernel/kprobes.c static void kretprobe_rethook_handler(struct rethook_node *rh, void *data, · line 2132
Quoted 8 lines
kernel/kprobes.c +1
-1@@ -2126,7 +2126,7 @@ static void kretprobe_rethook_handler(struct rethook_node *rh, void *data,struct kprobe_ctlblk *kcb;/* The data must NOT be null. This means rethook data structure is broken. */ -if (WARN_ON_ONCE (!data)) +if (WARN_ON_ONCE (!data) || !rp->handler)return ;__this_cpu_write (current_kprobe, &rp->kp);Thanks,
Daniel
Signature · 1 line
Masami Hiramatsu <[email protected]>
Daniel Borkmann
maintainerQuoted 18 lines · Masami Hiramatsu
Quoted 16 lines · On Mon, 25 Apr 2022 16:42:12 +0200 Daniel Borkmann <[email protected]> wrote:
Quoted 14 lines · Adam Zabrocki
[PATCH bpf] x86/kprobes: Fix KRETPROBES when
CONFIG_KRETPROBE_ON_RETHOOKis setThe recent kernel change "kprobes: Use rethook for kretprobe if possible", introduced a potential NULL pointer dereference bug in the KRETPROBE mechanism. The official Kprobes documentation defines that "Any or all handlers can be NULL". Unfortunately, there is a missing return handler verification to fulfill these requirements and can result in a NULL pointer dereference bug.
This patch adds such verification in
kretprobe_rethook_handler()function.Fixes 73f9b911faa7 ("kprobes: Use rethook for kretprobe if possible")Signed-off-by Adam Zabrocki <[email protected]>Acked-by Masami Hiramatsu <[email protected]>
Quoted 6 lines
Quoted 3 lines
I don't mind if this fix gets routed via bpf tree if all parties are okay with it (Masami? Steven?). Just noting that there is currently no specific dependency in bpf tree for it, but if it's easier to route this way, happy to take it.
Yeah, I and Steve talked about it and he suggested this to be merged via BPF tree since the original commit came from the BPF tree.
Okay, I just applied it to bpf tree then.
Thanks everyone,
Daniel