kernel/bpf/cgroup.c | 68 +++++++++++++++++++++++++++++++++++++++------ 1 file changed, 60 insertions(+), 8 deletions(-)
Syzbot found a Use After Free bug in compute_effective_progs().
The reproducer creates a number of BPF links, and causes a fault
injected alloc to fail, while calling bpf_link_detach on them.
Link detach triggers the link to be freed by bpf_link_free(),
which calls __cgroup_bpf_detach() and update_effective_progs().
If the memory allocation in this function fails, the function restores
the pointer to the bpf_cgroup_link on the cgroup list, but the memory
gets freed just after it returns. After this, every subsequent call to
update_effective_progs() causes this already deallocated pointer to be
dereferenced in prog_list_length(), and triggers KASAN UAF error.
To fix this issue don't preserve the pointer to the prog or link in the
list, but remove it and replace it with a dummy prog without shrinking
the table. The subsequent call to __cgroup_bpf_detach() or
__cgroup_bpf_detach() will correct it.
Cc: "Alexei Starovoitov" <ast@kernel.org>
Cc: "Daniel Borkmann" <daniel@iogearbox.net>
Cc: "Andrii Nakryiko" <andrii@kernel.org>
Cc: "Martin KaFai Lau" <kafai@fb.com>
Cc: "Song Liu" <songliubraving@fb.com>
Cc: "Yonghong Song" <yhs@fb.com>
Cc: "John Fastabend" <john.fastabend@gmail.com>
Cc: "KP Singh" <kpsingh@kernel.org>
Cc: <netdev@vger.kernel.org>
Cc: <bpf@vger.kernel.org>
Cc: <stable@vger.kernel.org>
Cc: <linux-kernel@vger.kernel.org>
Link: https://syzkaller.appspot.com/bug?id=8ebf179a95c2a2670f7cf1ba62429ec044369db4
Fixes: af6eea57437a ("bpf: Implement bpf_link-based cgroup BPF program attachment")
Reported-by: <syzbot+f264bffdfbd5614f3bb2@syzkaller.appspotmail.com>
Signed-off-by: Tadeusz Struk <tadeusz.struk@linaro.org>
---
v2: Add a fall back path that removes a prog from the effective progs
table in case detach fails to allocate memory in compute_effective_progs().
v3: Implement the fallback in a separate function purge_effective_progs
v4: Changed purge_effective_progs() to manipulate the array in a similar way
how replace_effective_prog() does it.
---
kernel/bpf/cgroup.c | 68 +++++++++++++++++++++++++++++++++++++++------
1 file changed, 60 insertions(+), 8 deletions(-)
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 128028efda64..6f1a6160c99e 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -681,6 +681,60 @@ static struct bpf_prog_list *find_detach_entry(struct list_head *progs,
return ERR_PTR(-ENOENT);
}
+/**
+ * purge_effective_progs() - After compute_effective_progs fails to alloc new
+ * cgrp->bpf.inactive table we can recover by
+ * recomputing the array in place.
+ *
+ * @cgrp: The cgroup which descendants to travers
+ * @prog: A program to detach or NULL
+ * @link: A link to detach or NULL
+ * @atype: Type of detach operation
+ */
+static void purge_effective_progs(struct cgroup *cgrp, struct bpf_prog *prog,
+ struct bpf_cgroup_link *link,
+ enum cgroup_bpf_attach_type atype)
+{
+ struct cgroup_subsys_state *css;
+ struct bpf_prog_array *progs;
+ struct bpf_prog_list *pl;
+ struct list_head *head;
+ struct cgroup *cg;
+ int pos;
+
+ /* recompute effective prog array in place */
+ css_for_each_descendant_pre(css, &cgrp->self) {
+ struct cgroup *desc = container_of(css, struct cgroup, self);
+
+ if (percpu_ref_is_zero(&desc->bpf.refcnt))
+ continue;
+
+ /* find position of link or prog in effective progs array */
+ for (pos = 0, cg = desc; cg; cg = cgroup_parent(cg)) {
+ if (pos && !(cg->bpf.flags[atype] & BPF_F_ALLOW_MULTI))
+ continue;
+
+ head = &cg->bpf.progs[atype];
+ list_for_each_entry(pl, head, node) {
+ if (!prog_list_prog(pl))
+ continue;
+ if (pl->prog == prog && pl->link == link)
+ goto found;
+ pos++;
+ }
+ }
+found:
+ BUG_ON(!cg);
+ progs = rcu_dereference_protected(
+ desc->bpf.effective[atype],
+ lockdep_is_held(&cgroup_mutex));
+
+ /* Remove the program from the array */
+ WARN_ONCE(bpf_prog_array_delete_safe_at(progs, pos),
+ "Failed to purge a prog from array at index %d", pos);
+ }
+}
+
/**
* __cgroup_bpf_detach() - Detach the program or link from a cgroup, and
* propagate the change to descendants
@@ -723,8 +777,12 @@ static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
pl->link = NULL;
err = update_effective_progs(cgrp, atype);
- if (err)
- goto cleanup;
+ if (err) {
+ /* If update affective array failed replace the prog with a dummy prog*/
+ pl->prog = old_prog;
+ pl->link = link;
+ purge_effective_progs(cgrp, old_prog, link, atype);
+ }
/* now can actually delete it from this cgroup list */
list_del(&pl->node);
@@ -736,12 +794,6 @@ static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
bpf_prog_put(old_prog);
static_branch_dec(&cgroup_bpf_enabled_key[atype]);
return 0;
-
-cleanup:
- /* restore back prog or link */
- pl->prog = old_prog;
- pl->link = link;
- return err;
}
static int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
--
2.36.1On 5/17/22 11:04, Tadeusz Struk wrote:
> Syzbot found a Use After Free bug in compute_effective_progs().
> The reproducer creates a number of BPF links, and causes a fault
> injected alloc to fail, while calling bpf_link_detach on them.
> Link detach triggers the link to be freed by bpf_link_free(),
> which calls __cgroup_bpf_detach() and update_effective_progs().
> If the memory allocation in this function fails, the function restores
> the pointer to the bpf_cgroup_link on the cgroup list, but the memory
> gets freed just after it returns. After this, every subsequent call to
> update_effective_progs() causes this already deallocated pointer to be
> dereferenced in prog_list_length(), and triggers KASAN UAF error.
>
> To fix this issue don't preserve the pointer to the prog or link in the
> list, but remove it and replace it with a dummy prog without shrinking
> the table. The subsequent call to __cgroup_bpf_detach() or
> __cgroup_bpf_detach() will correct it.
>
> Cc: "Alexei Starovoitov" <ast@kernel.org>
> Cc: "Daniel Borkmann" <daniel@iogearbox.net>
> Cc: "Andrii Nakryiko" <andrii@kernel.org>
> Cc: "Martin KaFai Lau" <kafai@fb.com>
> Cc: "Song Liu" <songliubraving@fb.com>
> Cc: "Yonghong Song" <yhs@fb.com>
> Cc: "John Fastabend" <john.fastabend@gmail.com>
> Cc: "KP Singh" <kpsingh@kernel.org>
> Cc: <netdev@vger.kernel.org>
> Cc: <bpf@vger.kernel.org>
> Cc: <stable@vger.kernel.org>
> Cc: <linux-kernel@vger.kernel.org>
>
> Link: https://syzkaller.appspot.com/bug?id=8ebf179a95c2a2670f7cf1ba62429ec044369db4
> Fixes: af6eea57437a ("bpf: Implement bpf_link-based cgroup BPF program attachment")
> Reported-by: <syzbot+f264bffdfbd5614f3bb2@syzkaller.appspotmail.com>
> Signed-off-by: Tadeusz Struk <tadeusz.struk@linaro.org>
> ---
> v2: Add a fall back path that removes a prog from the effective progs
> table in case detach fails to allocate memory in compute_effective_progs().
>
> v3: Implement the fallback in a separate function purge_effective_progs
>
> v4: Changed purge_effective_progs() to manipulate the array in a similar way
> how replace_effective_prog() does it.
> ---
> kernel/bpf/cgroup.c | 68 +++++++++++++++++++++++++++++++++++++++------
> 1 file changed, 60 insertions(+), 8 deletions(-)
>
> diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
> index 128028efda64..6f1a6160c99e 100644
> --- a/kernel/bpf/cgroup.c
> +++ b/kernel/bpf/cgroup.c
> @@ -681,6 +681,60 @@ static struct bpf_prog_list *find_detach_entry(struct list_head *progs,
> return ERR_PTR(-ENOENT);
> }
>
> +/**
> + * purge_effective_progs() - After compute_effective_progs fails to alloc new
> + * cgrp->bpf.inactive table we can recover by
> + * recomputing the array in place.
> + *
> + * @cgrp: The cgroup which descendants to travers
> + * @prog: A program to detach or NULL
> + * @link: A link to detach or NULL
> + * @atype: Type of detach operation
> + */
> +static void purge_effective_progs(struct cgroup *cgrp, struct bpf_prog *prog,
> + struct bpf_cgroup_link *link,
> + enum cgroup_bpf_attach_type atype)
> +{
> + struct cgroup_subsys_state *css;
> + struct bpf_prog_array *progs;
> + struct bpf_prog_list *pl;
> + struct list_head *head;
> + struct cgroup *cg;
> + int pos;
> +
> + /* recompute effective prog array in place */
> + css_for_each_descendant_pre(css, &cgrp->self) {
> + struct cgroup *desc = container_of(css, struct cgroup, self);
> +
> + if (percpu_ref_is_zero(&desc->bpf.refcnt))
> + continue;
> +
> + /* find position of link or prog in effective progs array */
> + for (pos = 0, cg = desc; cg; cg = cgroup_parent(cg)) {
> + if (pos && !(cg->bpf.flags[atype] & BPF_F_ALLOW_MULTI))
> + continue;
> +
> + head = &cg->bpf.progs[atype];
> + list_for_each_entry(pl, head, node) {
> + if (!prog_list_prog(pl))
> + continue;
> + if (pl->prog == prog && pl->link == link)
> + goto found;
> + pos++;
> + }
> + }
> +found:
> + BUG_ON(!cg);
> + progs = rcu_dereference_protected(
> + desc->bpf.effective[atype],
> + lockdep_is_held(&cgroup_mutex));
> +
> + /* Remove the program from the array */
> + WARN_ONCE(bpf_prog_array_delete_safe_at(progs, pos),
> + "Failed to purge a prog from array at index %d", pos);
> + }
> +}
> +
> /**
> * __cgroup_bpf_detach() - Detach the program or link from a cgroup, and
> * propagate the change to descendants
> @@ -723,8 +777,12 @@ static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
> pl->link = NULL;
>
> err = update_effective_progs(cgrp, atype);
> - if (err)
> - goto cleanup;
> + if (err) {
> + /* If update affective array failed replace the prog with a dummy prog*/
> + pl->prog = old_prog;
> + pl->link = link;
> + purge_effective_progs(cgrp, old_prog, link, atype);
> + }
>
> /* now can actually delete it from this cgroup list */
> list_del(&pl->node);
> @@ -736,12 +794,6 @@ static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
> bpf_prog_put(old_prog);
> static_branch_dec(&cgroup_bpf_enabled_key[atype]);
> return 0;
> -
> -cleanup:
> - /* restore back prog or link */
> - pl->prog = old_prog;
> - pl->link = link;
> - return err;
> }
>
> static int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
Hi Andrii,
Do you have any more feedback? Does it look better to you now?
--
Thanks,
Tadeusz
On Mon, May 23, 2022 at 2:36 PM Tadeusz Struk <tadeusz.struk@linaro.org> wrote:
>
> On 5/17/22 11:04, Tadeusz Struk wrote:
> > Syzbot found a Use After Free bug in compute_effective_progs().
> > The reproducer creates a number of BPF links, and causes a fault
> > injected alloc to fail, while calling bpf_link_detach on them.
> > Link detach triggers the link to be freed by bpf_link_free(),
> > which calls __cgroup_bpf_detach() and update_effective_progs().
> > If the memory allocation in this function fails, the function restores
> > the pointer to the bpf_cgroup_link on the cgroup list, but the memory
> > gets freed just after it returns. After this, every subsequent call to
> > update_effective_progs() causes this already deallocated pointer to be
> > dereferenced in prog_list_length(), and triggers KASAN UAF error.
> >
> > To fix this issue don't preserve the pointer to the prog or link in the
> > list, but remove it and replace it with a dummy prog without shrinking
> > the table. The subsequent call to __cgroup_bpf_detach() or
> > __cgroup_bpf_detach() will correct it.
> >
> > Cc: "Alexei Starovoitov" <ast@kernel.org>
> > Cc: "Daniel Borkmann" <daniel@iogearbox.net>
> > Cc: "Andrii Nakryiko" <andrii@kernel.org>
> > Cc: "Martin KaFai Lau" <kafai@fb.com>
> > Cc: "Song Liu" <songliubraving@fb.com>
> > Cc: "Yonghong Song" <yhs@fb.com>
> > Cc: "John Fastabend" <john.fastabend@gmail.com>
> > Cc: "KP Singh" <kpsingh@kernel.org>
> > Cc: <netdev@vger.kernel.org>
> > Cc: <bpf@vger.kernel.org>
> > Cc: <stable@vger.kernel.org>
> > Cc: <linux-kernel@vger.kernel.org>
> >
> > Link: https://syzkaller.appspot.com/bug?id=8ebf179a95c2a2670f7cf1ba62429ec044369db4
> > Fixes: af6eea57437a ("bpf: Implement bpf_link-based cgroup BPF program attachment")
> > Reported-by: <syzbot+f264bffdfbd5614f3bb2@syzkaller.appspotmail.com>
> > Signed-off-by: Tadeusz Struk <tadeusz.struk@linaro.org>
> > ---
> > v2: Add a fall back path that removes a prog from the effective progs
> > table in case detach fails to allocate memory in compute_effective_progs().
> >
> > v3: Implement the fallback in a separate function purge_effective_progs
> >
> > v4: Changed purge_effective_progs() to manipulate the array in a similar way
> > how replace_effective_prog() does it.
> > ---
> > kernel/bpf/cgroup.c | 68 +++++++++++++++++++++++++++++++++++++++------
> > 1 file changed, 60 insertions(+), 8 deletions(-)
> >
> > diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
> > index 128028efda64..6f1a6160c99e 100644
> > --- a/kernel/bpf/cgroup.c
> > +++ b/kernel/bpf/cgroup.c
> > @@ -681,6 +681,60 @@ static struct bpf_prog_list *find_detach_entry(struct list_head *progs,
> > return ERR_PTR(-ENOENT);
> > }
> >
> > +/**
> > + * purge_effective_progs() - After compute_effective_progs fails to alloc new
> > + * cgrp->bpf.inactive table we can recover by
> > + * recomputing the array in place.
> > + *
> > + * @cgrp: The cgroup which descendants to travers
> > + * @prog: A program to detach or NULL
> > + * @link: A link to detach or NULL
> > + * @atype: Type of detach operation
> > + */
> > +static void purge_effective_progs(struct cgroup *cgrp, struct bpf_prog *prog,
> > + struct bpf_cgroup_link *link,
> > + enum cgroup_bpf_attach_type atype)
> > +{
> > + struct cgroup_subsys_state *css;
> > + struct bpf_prog_array *progs;
> > + struct bpf_prog_list *pl;
> > + struct list_head *head;
> > + struct cgroup *cg;
> > + int pos;
> > +
> > + /* recompute effective prog array in place */
> > + css_for_each_descendant_pre(css, &cgrp->self) {
> > + struct cgroup *desc = container_of(css, struct cgroup, self);
> > +
> > + if (percpu_ref_is_zero(&desc->bpf.refcnt))
> > + continue;
> > +
> > + /* find position of link or prog in effective progs array */
> > + for (pos = 0, cg = desc; cg; cg = cgroup_parent(cg)) {
> > + if (pos && !(cg->bpf.flags[atype] & BPF_F_ALLOW_MULTI))
> > + continue;
> > +
> > + head = &cg->bpf.progs[atype];
> > + list_for_each_entry(pl, head, node) {
> > + if (!prog_list_prog(pl))
> > + continue;
> > + if (pl->prog == prog && pl->link == link)
> > + goto found;
> > + pos++;
> > + }
> > + }
> > +found:
> > + BUG_ON(!cg);
> > + progs = rcu_dereference_protected(
> > + desc->bpf.effective[atype],
> > + lockdep_is_held(&cgroup_mutex));
> > +
> > + /* Remove the program from the array */
> > + WARN_ONCE(bpf_prog_array_delete_safe_at(progs, pos),
> > + "Failed to purge a prog from array at index %d", pos);
> > + }
> > +}
> > +
> > /**
> > * __cgroup_bpf_detach() - Detach the program or link from a cgroup, and
> > * propagate the change to descendants
> > @@ -723,8 +777,12 @@ static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
> > pl->link = NULL;
> >
> > err = update_effective_progs(cgrp, atype);
> > - if (err)
> > - goto cleanup;
> > + if (err) {
> > + /* If update affective array failed replace the prog with a dummy prog*/
> > + pl->prog = old_prog;
> > + pl->link = link;
> > + purge_effective_progs(cgrp, old_prog, link, atype);
> > + }
> >
> > /* now can actually delete it from this cgroup list */
> > list_del(&pl->node);
> > @@ -736,12 +794,6 @@ static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
> > bpf_prog_put(old_prog);
> > static_branch_dec(&cgroup_bpf_enabled_key[atype]);
> > return 0;
> > -
> > -cleanup:
> > - /* restore back prog or link */
> > - pl->prog = old_prog;
> > - pl->link = link;
> > - return err;
> > }
> >
> > static int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
>
> Hi Andrii,
> Do you have any more feedback? Does it look better to you now?
Hi, this is on my TODO list, but I need a bit more focused time to
think all this through and I haven't managed to get it in last week.
I'm worried about the percpu_ref_is_zero(&desc->bpf.refcnt) portion
and whether it can cause some skew in the calculated array index, I
need to look at this a bit more in depth. Sorry for the delay.
> --
> Thanks,
> Tadeusz
Hi Andrii, On 5/23/22 15:47, Andrii Nakryiko wrote: >> Hi Andrii, >> Do you have any more feedback? Does it look better to you now? > Hi, this is on my TODO list, but I need a bit more focused time to > think all this through and I haven't managed to get it in last week. > I'm worried about the percpu_ref_is_zero(&desc->bpf.refcnt) portion > and whether it can cause some skew in the calculated array index, I > need to look at this a bit more in depth. Sorry for the delay. Did you get a chance to look at this yet? -- Thanks, Tadeusz
On Thu, Jun 2, 2022 at 7:37 AM Tadeusz Struk <tadeusz.struk@linaro.org> wrote:
>
> Hi Andrii,
> On 5/23/22 15:47, Andrii Nakryiko wrote:
> >> Hi Andrii,
> >> Do you have any more feedback? Does it look better to you now?
> > Hi, this is on my TODO list, but I need a bit more focused time to
> > think all this through and I haven't managed to get it in last week.
> > I'm worried about the percpu_ref_is_zero(&desc->bpf.refcnt) portion
> > and whether it can cause some skew in the calculated array index, I
> > need to look at this a bit more in depth. Sorry for the delay.
>
> Did you get a chance to look at this yet?
>
Hm.. I've applied it two days ago, but for some reason there was no
notification from the bot. It's now c89c79fda9b6 ("bpf: Fix KASAN
use-after-free Read in compute_effective_progs").
> --
> Thanks,
> Tadeusz
On 6/2/22 09:11, Andrii Nakryiko wrote:
>> Did you get a chance to look at this yet?
>>
> Hm.. I've applied it two days ago, but for some reason there was no
> notification from the bot. It's now c89c79fda9b6 ("bpf: Fix KASAN
> use-after-free Read in compute_effective_progs").
Great! Thank you.
--
Thanks,
Tadeusz
On 6/2/22 09:25, Tadeusz Struk wrote:
> On 6/2/22 09:11, Andrii Nakryiko wrote:
>>> Did you get a chance to look at this yet?
>>>
>> Hm.. I've applied it two days ago, but for some reason there was no
>> notification from the bot. It's now c89c79fda9b6 ("bpf: Fix KASAN
>> use-after-free Read in compute_effective_progs").
FYI. Just requested a test on bpf-next and it passed fine.
https://groups.google.com/g/syzkaller-android-bugs/c/nr6mD4vhRA4
--
Thanks,
Tadeusz
On 5/23/22 15:47, Andrii Nakryiko wrote: >> Hi Andrii, >> Do you have any more feedback? Does it look better to you now? > Hi, this is on my TODO list, but I need a bit more focused time to > think all this through and I haven't managed to get it in last week. > I'm worried about the percpu_ref_is_zero(&desc->bpf.refcnt) portion > and whether it can cause some skew in the calculated array index, I > need to look at this a bit more in depth. Sorry for the delay. That's fine. take your time and let me know if there is anything else to change/improve. FWIW I tested it extensively with the syzbot repro and the issue doesn't trigger anymore. -- Thanks, Tadeusz
© 2016 - 2026 Red Hat, Inc.