* [PATCH v7 bpf-next 05/14] bpf: extend bpf_prog_array to store pointers to the cgroup storage
From: Roman Gushchin @ 2018-08-02 21:27 UTC (permalink / raw)
To: netdev
Cc: linux-kernel, kernel-team, Roman Gushchin, Alexei Starovoitov,
Daniel Borkmann
In-Reply-To: <20180802212730.18579-1-guro@fb.com>
This patch converts bpf_prog_array from an array of prog pointers
to the array of struct bpf_prog_array_item elements.
This allows to save a cgroup storage pointer for each bpf program
efficiently attached to a cgroup.
Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
---
drivers/media/rc/bpf-lirc.c | 10 +++---
include/linux/bpf.h | 19 ++++++++----
kernel/bpf/cgroup.c | 21 +++++++------
kernel/bpf/core.c | 76 +++++++++++++++++++++++----------------------
4 files changed, 70 insertions(+), 56 deletions(-)
diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c
index fcfab6635f9c..8c26df9b96c1 100644
--- a/drivers/media/rc/bpf-lirc.c
+++ b/drivers/media/rc/bpf-lirc.c
@@ -195,14 +195,16 @@ void lirc_bpf_run(struct rc_dev *rcdev, u32 sample)
*/
void lirc_bpf_free(struct rc_dev *rcdev)
{
- struct bpf_prog **progs;
+ struct bpf_prog_array_item *item;
if (!rcdev->raw->progs)
return;
- progs = rcu_dereference(rcdev->raw->progs)->progs;
- while (*progs)
- bpf_prog_put(*progs++);
+ item = rcu_dereference(rcdev->raw->progs)->items;
+ while (item->prog) {
+ bpf_prog_put(item->prog);
+ item++;
+ }
bpf_prog_array_free(rcdev->raw->progs);
}
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 9d1e4727495e..16be67888c30 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -349,9 +349,14 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
* The 'struct bpf_prog_array *' should only be replaced with xchg()
* since other cpus are walking the array of pointers in parallel.
*/
+struct bpf_prog_array_item {
+ struct bpf_prog *prog;
+ struct bpf_cgroup_storage *cgroup_storage;
+};
+
struct bpf_prog_array {
struct rcu_head rcu;
- struct bpf_prog *progs[0];
+ struct bpf_prog_array_item items[0];
};
struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags);
@@ -372,7 +377,8 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
#define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null) \
({ \
- struct bpf_prog **_prog, *__prog; \
+ struct bpf_prog_array_item *_item; \
+ struct bpf_prog *_prog; \
struct bpf_prog_array *_array; \
u32 _ret = 1; \
preempt_disable(); \
@@ -380,10 +386,11 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
_array = rcu_dereference(array); \
if (unlikely(check_non_null && !_array))\
goto _out; \
- _prog = _array->progs; \
- while ((__prog = READ_ONCE(*_prog))) { \
- _ret &= func(__prog, ctx); \
- _prog++; \
+ _item = &_array->items[0]; \
+ while ((_prog = READ_ONCE(_item->prog))) { \
+ bpf_cgroup_storage_set(_item->cgroup_storage); \
+ _ret &= func(_prog, ctx); \
+ _item++; \
} \
_out: \
rcu_read_unlock(); \
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 935274c86bfe..ddfa6cc13e57 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -117,15 +117,18 @@ static int compute_effective_progs(struct cgroup *cgrp,
cnt = 0;
p = cgrp;
do {
- if (cnt == 0 || (p->bpf.flags[type] & BPF_F_ALLOW_MULTI))
- list_for_each_entry(pl,
- &p->bpf.progs[type], node) {
- if (!pl->prog)
- continue;
- progs->progs[cnt++] = pl->prog;
- }
- p = cgroup_parent(p);
- } while (p);
+ if (cnt > 0 && !(p->bpf.flags[type] & BPF_F_ALLOW_MULTI))
+ continue;
+
+ list_for_each_entry(pl, &p->bpf.progs[type], node) {
+ if (!pl->prog)
+ continue;
+
+ progs->items[cnt].prog = pl->prog;
+ progs->items[cnt].cgroup_storage = pl->storage;
+ cnt++;
+ }
+ } while ((p = cgroup_parent(p)));
rcu_assign_pointer(*array, progs);
return 0;
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 253aa8e79c7b..9abcf25ebf9f 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1542,7 +1542,8 @@ struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags)
{
if (prog_cnt)
return kzalloc(sizeof(struct bpf_prog_array) +
- sizeof(struct bpf_prog *) * (prog_cnt + 1),
+ sizeof(struct bpf_prog_array_item) *
+ (prog_cnt + 1),
flags);
return &empty_prog_array.hdr;
@@ -1556,43 +1557,45 @@ void bpf_prog_array_free(struct bpf_prog_array __rcu *progs)
kfree_rcu(progs, rcu);
}
-int bpf_prog_array_length(struct bpf_prog_array __rcu *progs)
+int bpf_prog_array_length(struct bpf_prog_array __rcu *array)
{
- struct bpf_prog **prog;
+ struct bpf_prog_array_item *item;
u32 cnt = 0;
rcu_read_lock();
- prog = rcu_dereference(progs)->progs;
- for (; *prog; prog++)
- if (*prog != &dummy_bpf_prog.prog)
+ item = rcu_dereference(array)->items;
+ for (; item->prog; item++)
+ if (item->prog != &dummy_bpf_prog.prog)
cnt++;
rcu_read_unlock();
return cnt;
}
-static bool bpf_prog_array_copy_core(struct bpf_prog **prog,
+
+static bool bpf_prog_array_copy_core(struct bpf_prog_array __rcu *array,
u32 *prog_ids,
u32 request_cnt)
{
+ struct bpf_prog_array_item *item;
int i = 0;
- for (; *prog; prog++) {
- if (*prog == &dummy_bpf_prog.prog)
+ item = rcu_dereference(array)->items;
+ for (; item->prog; item++) {
+ if (item->prog == &dummy_bpf_prog.prog)
continue;
- prog_ids[i] = (*prog)->aux->id;
+ prog_ids[i] = item->prog->aux->id;
if (++i == request_cnt) {
- prog++;
+ item++;
break;
}
}
- return !!(*prog);
+ return !!(item->prog);
}
-int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
+int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *array,
__u32 __user *prog_ids, u32 cnt)
{
- struct bpf_prog **prog;
unsigned long err = 0;
bool nospc;
u32 *ids;
@@ -1611,8 +1614,7 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
if (!ids)
return -ENOMEM;
rcu_read_lock();
- prog = rcu_dereference(progs)->progs;
- nospc = bpf_prog_array_copy_core(prog, ids, cnt);
+ nospc = bpf_prog_array_copy_core(array, ids, cnt);
rcu_read_unlock();
err = copy_to_user(prog_ids, ids, cnt * sizeof(u32));
kfree(ids);
@@ -1623,14 +1625,14 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
return 0;
}
-void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *progs,
+void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *array,
struct bpf_prog *old_prog)
{
- struct bpf_prog **prog = progs->progs;
+ struct bpf_prog_array_item *item = array->items;
- for (; *prog; prog++)
- if (*prog == old_prog) {
- WRITE_ONCE(*prog, &dummy_bpf_prog.prog);
+ for (; item->prog; item++)
+ if (item->prog == old_prog) {
+ WRITE_ONCE(item->prog, &dummy_bpf_prog.prog);
break;
}
}
@@ -1641,7 +1643,7 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
struct bpf_prog_array **new_array)
{
int new_prog_cnt, carry_prog_cnt = 0;
- struct bpf_prog **existing_prog;
+ struct bpf_prog_array_item *existing;
struct bpf_prog_array *array;
bool found_exclude = false;
int new_prog_idx = 0;
@@ -1650,15 +1652,15 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
* the new array.
*/
if (old_array) {
- existing_prog = old_array->progs;
- for (; *existing_prog; existing_prog++) {
- if (*existing_prog == exclude_prog) {
+ existing = old_array->items;
+ for (; existing->prog; existing++) {
+ if (existing->prog == exclude_prog) {
found_exclude = true;
continue;
}
- if (*existing_prog != &dummy_bpf_prog.prog)
+ if (existing->prog != &dummy_bpf_prog.prog)
carry_prog_cnt++;
- if (*existing_prog == include_prog)
+ if (existing->prog == include_prog)
return -EEXIST;
}
}
@@ -1684,15 +1686,17 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
/* Fill in the new prog array */
if (carry_prog_cnt) {
- existing_prog = old_array->progs;
- for (; *existing_prog; existing_prog++)
- if (*existing_prog != exclude_prog &&
- *existing_prog != &dummy_bpf_prog.prog)
- array->progs[new_prog_idx++] = *existing_prog;
+ existing = old_array->items;
+ for (; existing->prog; existing++)
+ if (existing->prog != exclude_prog &&
+ existing->prog != &dummy_bpf_prog.prog) {
+ array->items[new_prog_idx++].prog =
+ existing->prog;
+ }
}
if (include_prog)
- array->progs[new_prog_idx++] = include_prog;
- array->progs[new_prog_idx] = NULL;
+ array->items[new_prog_idx++].prog = include_prog;
+ array->items[new_prog_idx].prog = NULL;
*new_array = array;
return 0;
}
@@ -1701,7 +1705,6 @@ int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array,
u32 *prog_ids, u32 request_cnt,
u32 *prog_cnt)
{
- struct bpf_prog **prog;
u32 cnt = 0;
if (array)
@@ -1714,8 +1717,7 @@ int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array,
return 0;
/* this function is called under trace/bpf_trace.c: bpf_event_mutex */
- prog = rcu_dereference_check(array, 1)->progs;
- return bpf_prog_array_copy_core(prog, prog_ids, request_cnt) ? -ENOSPC
+ return bpf_prog_array_copy_core(array, prog_ids, request_cnt) ? -ENOSPC
: 0;
}
--
2.14.4
^ permalink raw reply related
* Re: [net-next, v6, 6/7] net-sysfs: Add interface for Rx queue(s) map per Tx queue
From: Michael S. Tsirkin @ 2018-08-02 21:08 UTC (permalink / raw)
To: Nambiar, Amritha
Cc: Andrei Vagin, netdev, davem, alexander.h.duyck,
willemdebruijn.kernel, sridhar.samudrala, alexander.duyck,
edumazet, hannes, tom, tom, jasowang, gaowanlong, virtualization,
rostedt
In-Reply-To: <c3fbd7f6-054b-a9a3-ea21-4169b26a0a41@intel.com>
On Thu, Aug 02, 2018 at 02:04:12PM -0700, Nambiar, Amritha wrote:
> On 8/1/2018 5:11 PM, Andrei Vagin wrote:
> > On Tue, Jul 10, 2018 at 07:28:49PM -0700, Nambiar, Amritha wrote:
> >> With this patch series, I introduced static_key for XPS maps
> >> (xps_needed), so static_key_slow_inc() is used to switch branches. The
> >> definition of static_key_slow_inc() has cpus_read_lock in place. In the
> >> virtio_net driver, XPS queues are initialized after setting the
> >> queue:cpu affinity in virtnet_set_affinity() which is already protected
> >> within cpus_read_lock. Hence, the warning here trying to acquire
> >> cpus_read_lock when it is already held.
> >>
> >> A quick fix for this would be to just extract netif_set_xps_queue() out
> >> of the lock by simply wrapping it with another put/get_online_cpus
> >> (unlock right before and hold lock right after).
> >
> > virtnet_set_affinity() is called from virtnet_cpu_online(), which is
> > called under cpus_read_lock too.
> >
> > It looks like now we can't call netif_set_xps_queue() from cpu hotplug
> > callbacks.
> >
> > I can suggest a very straightforward fix for this problem. The patch is
> > attached.
> >
>
> Thanks for looking into this. I was thinking of fixing this in the
> virtio_net driver by moving the XPS initialization (and have a new
> get_affinity utility) in the ndo_open (so it is together with other tx
> preparation) instead of probe. Your patch solves this in general for
> setting up cpu hotplug callbacks which is under cpus_read_lock.
I like this too. Could you repost in a standard way
(inline, with your signoff etc) so we can ack this for
net-next?
> >> But this may not a
> >> clean solution. It'd help if I can get suggestions on what would be a
> >> clean option to fix this without extensively changing the code in
> >> virtio_net. Is it mandatory to protect the affinitization with
> >> read_lock? I don't see similar lock in other drivers while setting the
> >> affinity. I understand this warning should go away, but isn't it safe to
> >> have multiple readers.
> >>
> >>> On Fri, Jun 29, 2018 at 09:27:07PM -0700, Amritha Nambiar wrote:
^ permalink raw reply
* Re: [net-next, v6, 6/7] net-sysfs: Add interface for Rx queue(s) map per Tx queue
From: Nambiar, Amritha @ 2018-08-02 21:04 UTC (permalink / raw)
To: Andrei Vagin
Cc: netdev, davem, alexander.h.duyck, willemdebruijn.kernel,
sridhar.samudrala, alexander.duyck, edumazet, hannes, tom, tom,
jasowang, gaowanlong, Michael S. Tsirkin, virtualization, rostedt
In-Reply-To: <20180802001157.GA29171@outlook.office365.com>
On 8/1/2018 5:11 PM, Andrei Vagin wrote:
> On Tue, Jul 10, 2018 at 07:28:49PM -0700, Nambiar, Amritha wrote:
>> With this patch series, I introduced static_key for XPS maps
>> (xps_needed), so static_key_slow_inc() is used to switch branches. The
>> definition of static_key_slow_inc() has cpus_read_lock in place. In the
>> virtio_net driver, XPS queues are initialized after setting the
>> queue:cpu affinity in virtnet_set_affinity() which is already protected
>> within cpus_read_lock. Hence, the warning here trying to acquire
>> cpus_read_lock when it is already held.
>>
>> A quick fix for this would be to just extract netif_set_xps_queue() out
>> of the lock by simply wrapping it with another put/get_online_cpus
>> (unlock right before and hold lock right after).
>
> virtnet_set_affinity() is called from virtnet_cpu_online(), which is
> called under cpus_read_lock too.
>
> It looks like now we can't call netif_set_xps_queue() from cpu hotplug
> callbacks.
>
> I can suggest a very straightforward fix for this problem. The patch is
> attached.
>
Thanks for looking into this. I was thinking of fixing this in the
virtio_net driver by moving the XPS initialization (and have a new
get_affinity utility) in the ndo_open (so it is together with other tx
preparation) instead of probe. Your patch solves this in general for
setting up cpu hotplug callbacks which is under cpus_read_lock.
>> But this may not a
>> clean solution. It'd help if I can get suggestions on what would be a
>> clean option to fix this without extensively changing the code in
>> virtio_net. Is it mandatory to protect the affinitization with
>> read_lock? I don't see similar lock in other drivers while setting the
>> affinity. I understand this warning should go away, but isn't it safe to
>> have multiple readers.
>>
>>> On Fri, Jun 29, 2018 at 09:27:07PM -0700, Amritha Nambiar wrote:
^ permalink raw reply
* [PATCH bpf-next] selftests/bpf: fix a typo in map in map test
From: Roman Gushchin @ 2018-08-02 22:47 UTC (permalink / raw)
To: netdev
Cc: linux-kernel, kernel-team, Roman Gushchin, Martin KaFai Lau,
Arthur Fabre, Daniel Borkmann, Alexei Starovoitov
Commit fbeb1603bf4e ("bpf: verifier: MOV64 don't mark dst reg unbounded")
revealed a typo in commit fb30d4b71214 ("bpf: Add tests for map-in-map"):
BPF_MOV64_REG(BPF_REG_0, 0) was used instead of
BPF_MOV64_IMM(BPF_REG_0, 0).
I've noticed the problem by running bpf kselftests.
Fixes: fb30d4b71214 ("bpf: Add tests for map-in-map")
Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Arthur Fabre <afabre@cloudflare.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Alexei Starovoitov <ast@kernel.org>
---
tools/testing/selftests/bpf/test_verifier.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 4b5e03c25204..ac281ee771dd 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -7113,7 +7113,7 @@ static struct bpf_test tests[] = {
BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
BPF_FUNC_map_lookup_elem),
- BPF_MOV64_REG(BPF_REG_0, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
.fixup_map_in_map = { 3 },
@@ -7136,7 +7136,7 @@ static struct bpf_test tests[] = {
BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
BPF_FUNC_map_lookup_elem),
- BPF_MOV64_REG(BPF_REG_0, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
.fixup_map_in_map = { 3 },
@@ -7158,7 +7158,7 @@ static struct bpf_test tests[] = {
BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
BPF_FUNC_map_lookup_elem),
- BPF_MOV64_REG(BPF_REG_0, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
.fixup_map_in_map = { 3 },
--
2.14.4
^ permalink raw reply related
* [RFC bpf-next v2 3/3] docs: Split filter.txt into separate documents.
From: Tobin C. Harding @ 2018-08-02 22:31 UTC (permalink / raw)
To: Daniel Borkmann, Alexei Starovoitov
Cc: Tobin C. Harding, Jonathan Corbet, David S. Miller, linux-doc,
netdev, linux-kernel
In-Reply-To: <20180802223100.26236-1-me@tobin.cc>
In preparation for conversion of Documentation/networking/filter.txt it
was noticed that the document contains a lot of information. The
document may be more accessible if it was split up. Some parts pertain
to everyone, let's put these bits in core-api/. The more hard core bits
about eBPF internals could be put with the other BPF docs in
Documentation/bpf/. There is a small bit of information on testing and
miscellaneous matters that are useful for everyone (everyone does
testing, right) so lets keep that info at the bottom of both new
documents. (This includes the original authors.)
Split Documentation/networking/filter.txt into
Documentation/bpf/eBPF.rst and Documentation/core-api/bpf.rst
Signed-off-by: Tobin C. Harding <me@tobin.cc>
---
.../{networking/filter.txt => bpf/eBPF.rst} | 590 +----------------
Documentation/core-api/bpf.rst | 599 ++++++++++++++++++
2 files changed, 612 insertions(+), 577 deletions(-)
rename Documentation/{networking/filter.txt => bpf/eBPF.rst} (63%)
create mode 100644 Documentation/core-api/bpf.rst
diff --git a/Documentation/networking/filter.txt b/Documentation/bpf/eBPF.rst
similarity index 63%
rename from Documentation/networking/filter.txt
rename to Documentation/bpf/eBPF.rst
index d12721e997f8..1695c7c7185d 100644
--- a/Documentation/networking/filter.txt
+++ b/Documentation/bpf/eBPF.rst
@@ -1,582 +1,18 @@
-Linux Socket Filtering aka Berkeley Packet Filter (BPF)
-=======================================================
-
-Introduction
-------------
-
-Linux Socket Filtering (LSF) is derived from the Berkeley Packet Filter.
-Though there are some distinct differences between the BSD and Linux
-kernel filtering, but when we speak of BPF or LSF in Linux context, we
-mean the very same mechanism of filtering in the Linux kernel.
-
-BPF allows a user-space program to attach a filter onto any socket and
-allow or disallow certain types of data to come through the socket. LSF
-follows exactly the same filter code structure as BSD's BPF, so referring
-to the BSD bpf.4 manpage is very helpful in creating filters.
-
-On Linux, BPF is much simpler than on BSD. One does not have to worry
-about devices or anything like that. You simply create your filter code,
-send it to the kernel via the SO_ATTACH_FILTER option and if your filter
-code passes the kernel check on it, you then immediately begin filtering
-data on that socket.
-
-You can also detach filters from your socket via the SO_DETACH_FILTER
-option. This will probably not be used much since when you close a socket
-that has a filter on it the filter is automagically removed. The other
-less common case may be adding a different filter on the same socket where
-you had another filter that is still running: the kernel takes care of
-removing the old one and placing your new one in its place, assuming your
-filter has passed the checks, otherwise if it fails the old filter will
-remain on that socket.
-
-SO_LOCK_FILTER option allows locking of the filter attached to a socket.
-Once set, a filter cannot be removed or changed. This allows one process to
-setup a socket, attach a filter, lock it then drop privileges and be
-assured that the filter will be kept until the socket is closed.
-
-The biggest user of this construct might be libpcap. Issuing a high-level
-filter command like `tcpdump -i em1 port 22` passes through the libpcap
-internal compiler that generates a structure that can eventually be loaded
-via SO_ATTACH_FILTER to the kernel. `tcpdump -i em1 port 22 -ddd`
-displays what is being placed into this structure.
-
-Although we were only speaking about sockets here, BPF in Linux is used
-in many more places. There's xt_bpf for netfilter, cls_bpf in the kernel
-qdisc layer, SECCOMP-BPF (SECure COMPuting [1]), and lots of other places
-such as team driver, PTP code, etc where BPF is being used.
-
- [1] Documentation/userspace-api/seccomp_filter.rst
-
-Original BPF paper:
-
-Steven McCanne and Van Jacobson. 1993. The BSD packet filter: a new
-architecture for user-level packet capture. In Proceedings of the
-USENIX Winter 1993 Conference Proceedings on USENIX Winter 1993
-Conference Proceedings (USENIX'93). USENIX Association, Berkeley,
-CA, USA, 2-2. [http://www.tcpdump.org/papers/bpf-usenix93.pdf]
-
-Structure
----------
-
-User space applications include <linux/filter.h> which contains the
-following relevant structures:
-
-struct sock_filter { /* Filter block */
- __u16 code; /* Actual filter code */
- __u8 jt; /* Jump true */
- __u8 jf; /* Jump false */
- __u32 k; /* Generic multiuse field */
-};
-
-Such a structure is assembled as an array of 4-tuples, that contains
-a code, jt, jf and k value. jt and jf are jump offsets and k a generic
-value to be used for a provided code.
-
-struct sock_fprog { /* Required for SO_ATTACH_FILTER. */
- unsigned short len; /* Number of filter blocks */
- struct sock_filter __user *filter;
-};
-
-For socket filtering, a pointer to this structure (as shown in
-follow-up example) is being passed to the kernel through setsockopt(2).
-
-Example
--------
-
-#include <sys/socket.h>
-#include <sys/types.h>
-#include <arpa/inet.h>
-#include <linux/if_ether.h>
-/* ... */
-
-/* From the example above: tcpdump -i em1 port 22 -dd */
-struct sock_filter code[] = {
- { 0x28, 0, 0, 0x0000000c },
- { 0x15, 0, 8, 0x000086dd },
- { 0x30, 0, 0, 0x00000014 },
- { 0x15, 2, 0, 0x00000084 },
- { 0x15, 1, 0, 0x00000006 },
- { 0x15, 0, 17, 0x00000011 },
- { 0x28, 0, 0, 0x00000036 },
- { 0x15, 14, 0, 0x00000016 },
- { 0x28, 0, 0, 0x00000038 },
- { 0x15, 12, 13, 0x00000016 },
- { 0x15, 0, 12, 0x00000800 },
- { 0x30, 0, 0, 0x00000017 },
- { 0x15, 2, 0, 0x00000084 },
- { 0x15, 1, 0, 0x00000006 },
- { 0x15, 0, 8, 0x00000011 },
- { 0x28, 0, 0, 0x00000014 },
- { 0x45, 6, 0, 0x00001fff },
- { 0xb1, 0, 0, 0x0000000e },
- { 0x48, 0, 0, 0x0000000e },
- { 0x15, 2, 0, 0x00000016 },
- { 0x48, 0, 0, 0x00000010 },
- { 0x15, 0, 1, 0x00000016 },
- { 0x06, 0, 0, 0x0000ffff },
- { 0x06, 0, 0, 0x00000000 },
-};
-
-struct sock_fprog bpf = {
- .len = ARRAY_SIZE(code),
- .filter = code,
-};
-
-sock = socket(PF_PACKET, SOCK_RAW, htons(ETH_P_ALL));
-if (sock < 0)
- /* ... bail out ... */
-
-ret = setsockopt(sock, SOL_SOCKET, SO_ATTACH_FILTER, &bpf, sizeof(bpf));
-if (ret < 0)
- /* ... bail out ... */
-
-/* ... */
-close(sock);
-
-The above example code attaches a socket filter for a PF_PACKET socket
-in order to let all IPv4/IPv6 packets with port 22 pass. The rest will
-be dropped for this socket.
-
-The setsockopt(2) call to SO_DETACH_FILTER doesn't need any arguments
-and SO_LOCK_FILTER for preventing the filter to be detached, takes an
-integer value with 0 or 1.
-
-Note that socket filters are not restricted to PF_PACKET sockets only,
-but can also be used on other socket families.
-
-Summary of system calls:
-
- * setsockopt(sockfd, SOL_SOCKET, SO_ATTACH_FILTER, &val, sizeof(val));
- * setsockopt(sockfd, SOL_SOCKET, SO_DETACH_FILTER, &val, sizeof(val));
- * setsockopt(sockfd, SOL_SOCKET, SO_LOCK_FILTER, &val, sizeof(val));
-
-Normally, most use cases for socket filtering on packet sockets will be
-covered by libpcap in high-level syntax, so as an application developer
-you should stick to that. libpcap wraps its own layer around all that.
-
-Unless i) using/linking to libpcap is not an option, ii) the required BPF
-filters use Linux extensions that are not supported by libpcap's compiler,
-iii) a filter might be more complex and not cleanly implementable with
-libpcap's compiler, or iv) particular filter codes should be optimized
-differently than libpcap's internal compiler does; then in such cases
-writing such a filter "by hand" can be of an alternative. For example,
-xt_bpf and cls_bpf users might have requirements that could result in
-more complex filter code, or one that cannot be expressed with libpcap
-(e.g. different return codes for various code paths). Moreover, BPF JIT
-implementors may wish to manually write test cases and thus need low-level
-access to BPF code as well.
-
-BPF engine and instruction set
-------------------------------
-
-Under tools/bpf/ there's a small helper tool called bpf_asm which can
-be used to write low-level filters for example scenarios mentioned in the
-previous section. Asm-like syntax mentioned here has been implemented in
-bpf_asm and will be used for further explanations (instead of dealing with
-less readable opcodes directly, principles are the same). The syntax is
-closely modelled after Steven McCanne's and Van Jacobson's BPF paper.
-
-The BPF architecture consists of the following basic elements:
-
- Element Description
-
- A 32 bit wide accumulator
- X 32 bit wide X register
- M[] 16 x 32 bit wide misc registers aka "scratch memory
- store", addressable from 0 to 15
-
-A program, that is translated by bpf_asm into "opcodes" is an array that
-consists of the following elements (as already mentioned):
-
- op:16, jt:8, jf:8, k:32
-
-The element op is a 16 bit wide opcode that has a particular instruction
-encoded. jt and jf are two 8 bit wide jump targets, one for condition
-"jump if true", the other one "jump if false". Eventually, element k
-contains a miscellaneous argument that can be interpreted in different
-ways depending on the given instruction in op.
-
-The instruction set consists of load, store, branch, alu, miscellaneous
-and return instructions that are also represented in bpf_asm syntax. This
-table lists all bpf_asm instructions available resp. what their underlying
-opcodes as defined in linux/filter.h stand for:
-
- Instruction Addressing mode Description
-
- ld 1, 2, 3, 4, 10 Load word into A
- ldi 4 Load word into A
- ldh 1, 2 Load half-word into A
- ldb 1, 2 Load byte into A
- ldx 3, 4, 5, 10 Load word into X
- ldxi 4 Load word into X
- ldxb 5 Load byte into X
-
- st 3 Store A into M[]
- stx 3 Store X into M[]
-
- jmp 6 Jump to label
- ja 6 Jump to label
- jeq 7, 8 Jump on A == k
- jneq 8 Jump on A != k
- jne 8 Jump on A != k
- jlt 8 Jump on A < k
- jle 8 Jump on A <= k
- jgt 7, 8 Jump on A > k
- jge 7, 8 Jump on A >= k
- jset 7, 8 Jump on A & k
-
- add 0, 4 A + <x>
- sub 0, 4 A - <x>
- mul 0, 4 A * <x>
- div 0, 4 A / <x>
- mod 0, 4 A % <x>
- neg !A
- and 0, 4 A & <x>
- or 0, 4 A | <x>
- xor 0, 4 A ^ <x>
- lsh 0, 4 A << <x>
- rsh 0, 4 A >> <x>
-
- tax Copy A into X
- txa Copy X into A
-
- ret 4, 9 Return
-
-The next table shows addressing formats from the 2nd column:
-
- Addressing mode Syntax Description
-
- 0 x/%x Register X
- 1 [k] BHW at byte offset k in the packet
- 2 [x + k] BHW at the offset X + k in the packet
- 3 M[k] Word at offset k in M[]
- 4 #k Literal value stored in k
- 5 4*([k]&0xf) Lower nibble * 4 at byte offset k in the packet
- 6 L Jump label L
- 7 #k,Lt,Lf Jump to Lt if true, otherwise jump to Lf
- 8 #k,Lt Jump to Lt if predicate is true
- 9 a/%a Accumulator A
- 10 extension BPF extension
-
-The Linux kernel also has a couple of BPF extensions that are used along
-with the class of load instructions by "overloading" the k argument with
-a negative offset + a particular extension offset. The result of such BPF
-extensions are loaded into A.
-
-Possible BPF extensions are shown in the following table:
-
- Extension Description
-
- len skb->len
- proto skb->protocol
- type skb->pkt_type
- poff Payload start offset
- ifidx skb->dev->ifindex
- nla Netlink attribute of type X with offset A
- nlan Nested Netlink attribute of type X with offset A
- mark skb->mark
- queue skb->queue_mapping
- hatype skb->dev->type
- rxhash skb->hash
- cpu raw_smp_processor_id()
- vlan_tci skb_vlan_tag_get(skb)
- vlan_avail skb_vlan_tag_present(skb)
- vlan_tpid skb->vlan_proto
- rand prandom_u32()
-
-These extensions can also be prefixed with '#'.
-Examples for low-level BPF:
-
-** ARP packets:
-
- ldh [12]
- jne #0x806, drop
- ret #-1
- drop: ret #0
-
-** IPv4 TCP packets:
-
- ldh [12]
- jne #0x800, drop
- ldb [23]
- jneq #6, drop
- ret #-1
- drop: ret #0
-
-** (Accelerated) VLAN w/ id 10:
-
- ld vlan_tci
- jneq #10, drop
- ret #-1
- drop: ret #0
-
-** icmp random packet sampling, 1 in 4
- ldh [12]
- jne #0x800, drop
- ldb [23]
- jneq #1, drop
- # get a random uint32 number
- ld rand
- mod #4
- jneq #1, drop
- ret #-1
- drop: ret #0
-
-** SECCOMP filter example:
-
- ld [4] /* offsetof(struct seccomp_data, arch) */
- jne #0xc000003e, bad /* AUDIT_ARCH_X86_64 */
- ld [0] /* offsetof(struct seccomp_data, nr) */
- jeq #15, good /* __NR_rt_sigreturn */
- jeq #231, good /* __NR_exit_group */
- jeq #60, good /* __NR_exit */
- jeq #0, good /* __NR_read */
- jeq #1, good /* __NR_write */
- jeq #5, good /* __NR_fstat */
- jeq #9, good /* __NR_mmap */
- jeq #14, good /* __NR_rt_sigprocmask */
- jeq #13, good /* __NR_rt_sigaction */
- jeq #35, good /* __NR_nanosleep */
- bad: ret #0 /* SECCOMP_RET_KILL_THREAD */
- good: ret #0x7fff0000 /* SECCOMP_RET_ALLOW */
-
-The above example code can be placed into a file (here called "foo"), and
-then be passed to the bpf_asm tool for generating opcodes, output that xt_bpf
-and cls_bpf understands and can directly be loaded with. Example with above
-ARP code:
-
-$ ./bpf_asm foo
-4,40 0 0 12,21 0 1 2054,6 0 0 4294967295,6 0 0 0,
-
-In copy and paste C-like output:
-
-$ ./bpf_asm -c foo
-{ 0x28, 0, 0, 0x0000000c },
-{ 0x15, 0, 1, 0x00000806 },
-{ 0x06, 0, 0, 0xffffffff },
-{ 0x06, 0, 0, 0000000000 },
-
-In particular, as usage with xt_bpf or cls_bpf can result in more complex BPF
-filters that might not be obvious at first, it's good to test filters before
-attaching to a live system. For that purpose, there's a small tool called
-bpf_dbg under tools/bpf/ in the kernel source directory. This debugger allows
-for testing BPF filters against given pcap files, single stepping through the
-BPF code on the pcap's packets and to do BPF machine register dumps.
-
-Starting bpf_dbg is trivial and just requires issuing:
-
-# ./bpf_dbg
-
-In case input and output do not equal stdin/stdout, bpf_dbg takes an
-alternative stdin source as a first argument, and an alternative stdout
-sink as a second one, e.g. `./bpf_dbg test_in.txt test_out.txt`.
-
-Other than that, a particular libreadline configuration can be set via
-file "~/.bpf_dbg_init" and the command history is stored in the file
-"~/.bpf_dbg_history".
-
-Interaction in bpf_dbg happens through a shell that also has auto-completion
-support (follow-up example commands starting with '>' denote bpf_dbg shell).
-The usual workflow would be to ...
-
-> load bpf 6,40 0 0 12,21 0 3 2048,48 0 0 23,21 0 1 1,6 0 0 65535,6 0 0 0
- Loads a BPF filter from standard output of bpf_asm, or transformed via
- e.g. `tcpdump -iem1 -ddd port 22 | tr '\n' ','`. Note that for JIT
- debugging (next section), this command creates a temporary socket and
- loads the BPF code into the kernel. Thus, this will also be useful for
- JIT developers.
-
-> load pcap foo.pcap
- Loads standard tcpdump pcap file.
-
-> run [<n>]
-bpf passes:1 fails:9
- Runs through all packets from a pcap to account how many passes and fails
- the filter will generate. A limit of packets to traverse can be given.
-
-> disassemble
-l0: ldh [12]
-l1: jeq #0x800, l2, l5
-l2: ldb [23]
-l3: jeq #0x1, l4, l5
-l4: ret #0xffff
-l5: ret #0
- Prints out BPF code disassembly.
-
-> dump
-/* { op, jt, jf, k }, */
-{ 0x28, 0, 0, 0x0000000c },
-{ 0x15, 0, 3, 0x00000800 },
-{ 0x30, 0, 0, 0x00000017 },
-{ 0x15, 0, 1, 0x00000001 },
-{ 0x06, 0, 0, 0x0000ffff },
-{ 0x06, 0, 0, 0000000000 },
- Prints out C-style BPF code dump.
-
-> breakpoint 0
-breakpoint at: l0: ldh [12]
-> breakpoint 1
-breakpoint at: l1: jeq #0x800, l2, l5
- ...
- Sets breakpoints at particular BPF instructions. Issuing a `run` command
- will walk through the pcap file continuing from the current packet and
- break when a breakpoint is being hit (another `run` will continue from
- the currently active breakpoint executing next instructions):
-
- > run
- -- register dump --
- pc: [0] <-- program counter
- code: [40] jt[0] jf[0] k[12] <-- plain BPF code of current instruction
- curr: l0: ldh [12] <-- disassembly of current instruction
- A: [00000000][0] <-- content of A (hex, decimal)
- X: [00000000][0] <-- content of X (hex, decimal)
- M[0,15]: [00000000][0] <-- folded content of M (hex, decimal)
- -- packet dump -- <-- Current packet from pcap (hex)
- len: 42
- 0: 00 19 cb 55 55 a4 00 14 a4 43 78 69 08 06 00 01
- 16: 08 00 06 04 00 01 00 14 a4 43 78 69 0a 3b 01 26
- 32: 00 00 00 00 00 00 0a 3b 01 01
- (breakpoint)
- >
-
-> breakpoint
-breakpoints: 0 1
- Prints currently set breakpoints.
-
-> step [-<n>, +<n>]
- Performs single stepping through the BPF program from the current pc
- offset. Thus, on each step invocation, above register dump is issued.
- This can go forwards and backwards in time, a plain `step` will break
- on the next BPF instruction, thus +1. (No `run` needs to be issued here.)
-
-> select <n>
- Selects a given packet from the pcap file to continue from. Thus, on
- the next `run` or `step`, the BPF program is being evaluated against
- the user pre-selected packet. Numbering starts just as in Wireshark
- with index 1.
-
-> quit
-#
- Exits bpf_dbg.
-
-JIT compiler
-------------
-
-The Linux kernel has a built-in BPF JIT compiler for x86_64, SPARC, PowerPC,
-ARM, ARM64, MIPS and s390 which can be enabled through CONFIG_BPF_JIT. The JIT
-compiler is transparently invoked for each attached filter from user space
-or for internal kernel users if it has been previously enabled by root:
-
- echo 1 > /proc/sys/net/core/bpf_jit_enable
-
-For JIT developers, doing audits etc, each compile run can output the generated
-opcode image into the kernel log via:
-
- echo 2 > /proc/sys/net/core/bpf_jit_enable
-
-Example output from dmesg:
-
-[ 3389.935842] flen=6 proglen=70 pass=3 image=ffffffffa0069c8f
-[ 3389.935847] JIT code: 00000000: 55 48 89 e5 48 83 ec 60 48 89 5d f8 44 8b 4f 68
-[ 3389.935849] JIT code: 00000010: 44 2b 4f 6c 4c 8b 87 d8 00 00 00 be 0c 00 00 00
-[ 3389.935850] JIT code: 00000020: e8 1d 94 ff e0 3d 00 08 00 00 75 16 be 17 00 00
-[ 3389.935851] JIT code: 00000030: 00 e8 28 94 ff e0 83 f8 01 75 07 b8 ff ff 00 00
-[ 3389.935852] JIT code: 00000040: eb 02 31 c0 c9 c3
-
-When CONFIG_BPF_JIT_ALWAYS_ON is enabled, bpf_jit_enable is permanently set to 1 and
-setting any other value than that will return in failure. This is even the case for
-setting bpf_jit_enable to 2, since dumping the final JIT image into the kernel log
-is discouraged and introspection through bpftool (under tools/bpf/bpftool/) is the
-generally recommended approach instead.
-
-In the kernel source tree under tools/bpf/, there's bpf_jit_disasm for
-generating disassembly out of the kernel log's hexdump:
-
-# ./bpf_jit_disasm
-70 bytes emitted from JIT compiler (pass:3, flen:6)
-ffffffffa0069c8f + <x>:
- 0: push %rbp
- 1: mov %rsp,%rbp
- 4: sub $0x60,%rsp
- 8: mov %rbx,-0x8(%rbp)
- c: mov 0x68(%rdi),%r9d
- 10: sub 0x6c(%rdi),%r9d
- 14: mov 0xd8(%rdi),%r8
- 1b: mov $0xc,%esi
- 20: callq 0xffffffffe0ff9442
- 25: cmp $0x800,%eax
- 2a: jne 0x0000000000000042
- 2c: mov $0x17,%esi
- 31: callq 0xffffffffe0ff945e
- 36: cmp $0x1,%eax
- 39: jne 0x0000000000000042
- 3b: mov $0xffff,%eax
- 40: jmp 0x0000000000000044
- 42: xor %eax,%eax
- 44: leaveq
- 45: retq
-
-Issuing option `-o` will "annotate" opcodes to resulting assembler
-instructions, which can be very useful for JIT developers:
-
-# ./bpf_jit_disasm -o
-70 bytes emitted from JIT compiler (pass:3, flen:6)
-ffffffffa0069c8f + <x>:
- 0: push %rbp
- 55
- 1: mov %rsp,%rbp
- 48 89 e5
- 4: sub $0x60,%rsp
- 48 83 ec 60
- 8: mov %rbx,-0x8(%rbp)
- 48 89 5d f8
- c: mov 0x68(%rdi),%r9d
- 44 8b 4f 68
- 10: sub 0x6c(%rdi),%r9d
- 44 2b 4f 6c
- 14: mov 0xd8(%rdi),%r8
- 4c 8b 87 d8 00 00 00
- 1b: mov $0xc,%esi
- be 0c 00 00 00
- 20: callq 0xffffffffe0ff9442
- e8 1d 94 ff e0
- 25: cmp $0x800,%eax
- 3d 00 08 00 00
- 2a: jne 0x0000000000000042
- 75 16
- 2c: mov $0x17,%esi
- be 17 00 00 00
- 31: callq 0xffffffffe0ff945e
- e8 28 94 ff e0
- 36: cmp $0x1,%eax
- 83 f8 01
- 39: jne 0x0000000000000042
- 75 07
- 3b: mov $0xffff,%eax
- b8 ff ff 00 00
- 40: jmp 0x0000000000000044
- eb 02
- 42: xor %eax,%eax
- 31 c0
- 44: leaveq
- c9
- 45: retq
- c3
-
-For BPF JIT developers, bpf_jit_disasm, bpf_asm and bpf_dbg provides a useful
-toolchain for developing and testing the kernel's JIT compiler.
-
+.. SPDX-License-Identifier: GPL-2.0+
BPF kernel internals
--------------------
-Internally, for the kernel interpreter, a different instruction set
-format with similar underlying principles from BPF described in previous
-paragraphs is being used. However, the instruction set format is modelled
-closer to the underlying architecture to mimic native instruction sets, so
-that better performance can be achieved (more details later). This new
-ISA is called 'eBPF' or 'internal BPF' interchangeably. (Note: eBPF which
-originates from [e]xtended BPF is not the same as BPF extensions! While
-eBPF is an ISA, BPF extensions date back to classic BPF's 'overloading'
-of BPF_LD | BPF_{B,H,W} | BPF_ABS instruction.)
+
+This document follows on from Documentation/core-api/bpf.rst
+
+Internally, for the kernel interpreter, a different instruction set format
+with similar underlying principles from BPF described in the document
+linked to above is being used. However, the instruction set format is
+modelled closer to the underlying architecture to mimic native instruction
+sets, so that better performance can be achieved (more details later). This
+new ISA is called 'eBPF' or 'internal BPF' interchangeably. (Note: eBPF
+which originates from [e]xtended BPF is not the same as BPF extensions!
+While eBPF is an ISA, BPF extensions date back to classic BPF's
+'overloading' of BPF_LD | BPF_{B,H,W} | BPF_ABS instruction.)
It is designed to be JITed with one to one mapping, which can also open up
the possibility for GCC/LLVM compilers to generate optimized eBPF code through
diff --git a/Documentation/core-api/bpf.rst b/Documentation/core-api/bpf.rst
new file mode 100644
index 000000000000..f6635bd8ebd6
--- /dev/null
+++ b/Documentation/core-api/bpf.rst
@@ -0,0 +1,599 @@
+.. SPDX-License-Identifier: GPL-2.0+
+Linux Socket Filtering aka Berkeley Packet Filter (BPF)
+=======================================================
+
+Introduction
+------------
+
+Linux Socket Filtering (LSF) is derived from the Berkeley Packet Filter.
+Though there are some distinct differences between the BSD and Linux
+kernel filtering, but when we speak of BPF or LSF in Linux context, we
+mean the very same mechanism of filtering in the Linux kernel.
+
+BPF allows a user-space program to attach a filter onto any socket and
+allow or disallow certain types of data to come through the socket. LSF
+follows exactly the same filter code structure as BSD's BPF, so referring
+to the BSD bpf.4 manpage is very helpful in creating filters.
+
+On Linux, BPF is much simpler than on BSD. One does not have to worry
+about devices or anything like that. You simply create your filter code,
+send it to the kernel via the SO_ATTACH_FILTER option and if your filter
+code passes the kernel check on it, you then immediately begin filtering
+data on that socket.
+
+You can also detach filters from your socket via the SO_DETACH_FILTER
+option. This will probably not be used much since when you close a socket
+that has a filter on it the filter is automagically removed. The other
+less common case may be adding a different filter on the same socket where
+you had another filter that is still running: the kernel takes care of
+removing the old one and placing your new one in its place, assuming your
+filter has passed the checks, otherwise if it fails the old filter will
+remain on that socket.
+
+SO_LOCK_FILTER option allows locking of the filter attached to a socket.
+Once set, a filter cannot be removed or changed. This allows one process to
+setup a socket, attach a filter, lock it then drop privileges and be
+assured that the filter will be kept until the socket is closed.
+
+The biggest user of this construct might be libpcap. Issuing a high-level
+filter command like `tcpdump -i em1 port 22` passes through the libpcap
+internal compiler that generates a structure that can eventually be loaded
+via SO_ATTACH_FILTER to the kernel. `tcpdump -i em1 port 22 -ddd`
+displays what is being placed into this structure.
+
+Although we were only speaking about sockets here, BPF in Linux is used
+in many more places. There's xt_bpf for netfilter, cls_bpf in the kernel
+qdisc layer, SECCOMP-BPF (SECure COMPuting [1]), and lots of other places
+such as team driver, PTP code, etc where BPF is being used.
+
+ [1] Documentation/userspace-api/seccomp_filter.rst
+
+Original BPF paper:
+
+Steven McCanne and Van Jacobson. 1993. The BSD packet filter: a new
+architecture for user-level packet capture. In Proceedings of the
+USENIX Winter 1993 Conference Proceedings on USENIX Winter 1993
+Conference Proceedings (USENIX'93). USENIX Association, Berkeley,
+CA, USA, 2-2. [http://www.tcpdump.org/papers/bpf-usenix93.pdf]
+
+Structure
+---------
+
+User space applications include <linux/filter.h> which contains the
+following relevant structures:
+
+struct sock_filter { /* Filter block */
+ __u16 code; /* Actual filter code */
+ __u8 jt; /* Jump true */
+ __u8 jf; /* Jump false */
+ __u32 k; /* Generic multiuse field */
+};
+
+Such a structure is assembled as an array of 4-tuples, that contains
+a code, jt, jf and k value. jt and jf are jump offsets and k a generic
+value to be used for a provided code.
+
+struct sock_fprog { /* Required for SO_ATTACH_FILTER. */
+ unsigned short len; /* Number of filter blocks */
+ struct sock_filter __user *filter;
+};
+
+For socket filtering, a pointer to this structure (as shown in
+follow-up example) is being passed to the kernel through setsockopt(2).
+
+Example
+-------
+
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <arpa/inet.h>
+#include <linux/if_ether.h>
+/* ... */
+
+/* From the example above: tcpdump -i em1 port 22 -dd */
+struct sock_filter code[] = {
+ { 0x28, 0, 0, 0x0000000c },
+ { 0x15, 0, 8, 0x000086dd },
+ { 0x30, 0, 0, 0x00000014 },
+ { 0x15, 2, 0, 0x00000084 },
+ { 0x15, 1, 0, 0x00000006 },
+ { 0x15, 0, 17, 0x00000011 },
+ { 0x28, 0, 0, 0x00000036 },
+ { 0x15, 14, 0, 0x00000016 },
+ { 0x28, 0, 0, 0x00000038 },
+ { 0x15, 12, 13, 0x00000016 },
+ { 0x15, 0, 12, 0x00000800 },
+ { 0x30, 0, 0, 0x00000017 },
+ { 0x15, 2, 0, 0x00000084 },
+ { 0x15, 1, 0, 0x00000006 },
+ { 0x15, 0, 8, 0x00000011 },
+ { 0x28, 0, 0, 0x00000014 },
+ { 0x45, 6, 0, 0x00001fff },
+ { 0xb1, 0, 0, 0x0000000e },
+ { 0x48, 0, 0, 0x0000000e },
+ { 0x15, 2, 0, 0x00000016 },
+ { 0x48, 0, 0, 0x00000010 },
+ { 0x15, 0, 1, 0x00000016 },
+ { 0x06, 0, 0, 0x0000ffff },
+ { 0x06, 0, 0, 0x00000000 },
+};
+
+struct sock_fprog bpf = {
+ .len = ARRAY_SIZE(code),
+ .filter = code,
+};
+
+sock = socket(PF_PACKET, SOCK_RAW, htons(ETH_P_ALL));
+if (sock < 0)
+ /* ... bail out ... */
+
+ret = setsockopt(sock, SOL_SOCKET, SO_ATTACH_FILTER, &bpf, sizeof(bpf));
+if (ret < 0)
+ /* ... bail out ... */
+
+/* ... */
+close(sock);
+
+The above example code attaches a socket filter for a PF_PACKET socket
+in order to let all IPv4/IPv6 packets with port 22 pass. The rest will
+be dropped for this socket.
+
+The setsockopt(2) call to SO_DETACH_FILTER doesn't need any arguments
+and SO_LOCK_FILTER for preventing the filter to be detached, takes an
+integer value with 0 or 1.
+
+Note that socket filters are not restricted to PF_PACKET sockets only,
+but can also be used on other socket families.
+
+Summary of system calls:
+
+ * setsockopt(sockfd, SOL_SOCKET, SO_ATTACH_FILTER, &val, sizeof(val));
+ * setsockopt(sockfd, SOL_SOCKET, SO_DETACH_FILTER, &val, sizeof(val));
+ * setsockopt(sockfd, SOL_SOCKET, SO_LOCK_FILTER, &val, sizeof(val));
+
+Normally, most use cases for socket filtering on packet sockets will be
+covered by libpcap in high-level syntax, so as an application developer
+you should stick to that. libpcap wraps its own layer around all that.
+
+Unless i) using/linking to libpcap is not an option, ii) the required BPF
+filters use Linux extensions that are not supported by libpcap's compiler,
+iii) a filter might be more complex and not cleanly implementable with
+libpcap's compiler, or iv) particular filter codes should be optimized
+differently than libpcap's internal compiler does; then in such cases
+writing such a filter "by hand" can be of an alternative. For example,
+xt_bpf and cls_bpf users might have requirements that could result in
+more complex filter code, or one that cannot be expressed with libpcap
+(e.g. different return codes for various code paths). Moreover, BPF JIT
+implementors may wish to manually write test cases and thus need low-level
+access to BPF code as well.
+
+BPF engine and instruction set
+------------------------------
+
+Under tools/bpf/ there's a small helper tool called bpf_asm which can
+be used to write low-level filters for example scenarios mentioned in the
+previous section. Asm-like syntax mentioned here has been implemented in
+bpf_asm and will be used for further explanations (instead of dealing with
+less readable opcodes directly, principles are the same). The syntax is
+closely modelled after Steven McCanne's and Van Jacobson's BPF paper.
+
+The BPF architecture consists of the following basic elements:
+
+ Element Description
+
+ A 32 bit wide accumulator
+ X 32 bit wide X register
+ M[] 16 x 32 bit wide misc registers aka "scratch memory
+ store", addressable from 0 to 15
+
+A program, that is translated by bpf_asm into "opcodes" is an array that
+consists of the following elements (as already mentioned):
+
+ op:16, jt:8, jf:8, k:32
+
+The element op is a 16 bit wide opcode that has a particular instruction
+encoded. jt and jf are two 8 bit wide jump targets, one for condition
+"jump if true", the other one "jump if false". Eventually, element k
+contains a miscellaneous argument that can be interpreted in different
+ways depending on the given instruction in op.
+
+The instruction set consists of load, store, branch, alu, miscellaneous
+and return instructions that are also represented in bpf_asm syntax. This
+table lists all bpf_asm instructions available resp. what their underlying
+opcodes as defined in linux/filter.h stand for:
+
+ Instruction Addressing mode Description
+
+ ld 1, 2, 3, 4, 10 Load word into A
+ ldi 4 Load word into A
+ ldh 1, 2 Load half-word into A
+ ldb 1, 2 Load byte into A
+ ldx 3, 4, 5, 10 Load word into X
+ ldxi 4 Load word into X
+ ldxb 5 Load byte into X
+
+ st 3 Store A into M[]
+ stx 3 Store X into M[]
+
+ jmp 6 Jump to label
+ ja 6 Jump to label
+ jeq 7, 8 Jump on A == k
+ jneq 8 Jump on A != k
+ jne 8 Jump on A != k
+ jlt 8 Jump on A < k
+ jle 8 Jump on A <= k
+ jgt 7, 8 Jump on A > k
+ jge 7, 8 Jump on A >= k
+ jset 7, 8 Jump on A & k
+
+ add 0, 4 A + <x>
+ sub 0, 4 A - <x>
+ mul 0, 4 A * <x>
+ div 0, 4 A / <x>
+ mod 0, 4 A % <x>
+ neg !A
+ and 0, 4 A & <x>
+ or 0, 4 A | <x>
+ xor 0, 4 A ^ <x>
+ lsh 0, 4 A << <x>
+ rsh 0, 4 A >> <x>
+
+ tax Copy A into X
+ txa Copy X into A
+
+ ret 4, 9 Return
+
+The next table shows addressing formats from the 2nd column:
+
+ Addressing mode Syntax Description
+
+ 0 x/%x Register X
+ 1 [k] BHW at byte offset k in the packet
+ 2 [x + k] BHW at the offset X + k in the packet
+ 3 M[k] Word at offset k in M[]
+ 4 #k Literal value stored in k
+ 5 4*([k]&0xf) Lower nibble * 4 at byte offset k in the packet
+ 6 L Jump label L
+ 7 #k,Lt,Lf Jump to Lt if true, otherwise jump to Lf
+ 8 #k,Lt Jump to Lt if predicate is true
+ 9 a/%a Accumulator A
+ 10 extension BPF extension
+
+The Linux kernel also has a couple of BPF extensions that are used along
+with the class of load instructions by "overloading" the k argument with
+a negative offset + a particular extension offset. The result of such BPF
+extensions are loaded into A.
+
+Possible BPF extensions are shown in the following table:
+
+ Extension Description
+
+ len skb->len
+ proto skb->protocol
+ type skb->pkt_type
+ poff Payload start offset
+ ifidx skb->dev->ifindex
+ nla Netlink attribute of type X with offset A
+ nlan Nested Netlink attribute of type X with offset A
+ mark skb->mark
+ queue skb->queue_mapping
+ hatype skb->dev->type
+ rxhash skb->hash
+ cpu raw_smp_processor_id()
+ vlan_tci skb_vlan_tag_get(skb)
+ vlan_avail skb_vlan_tag_present(skb)
+ vlan_tpid skb->vlan_proto
+ rand prandom_u32()
+
+These extensions can also be prefixed with '#'.
+Examples for low-level BPF:
+
+** ARP packets:
+
+ ldh [12]
+ jne #0x806, drop
+ ret #-1
+ drop: ret #0
+
+** IPv4 TCP packets:
+
+ ldh [12]
+ jne #0x800, drop
+ ldb [23]
+ jneq #6, drop
+ ret #-1
+ drop: ret #0
+
+** (Accelerated) VLAN w/ id 10:
+
+ ld vlan_tci
+ jneq #10, drop
+ ret #-1
+ drop: ret #0
+
+** icmp random packet sampling, 1 in 4
+ ldh [12]
+ jne #0x800, drop
+ ldb [23]
+ jneq #1, drop
+ # get a random uint32 number
+ ld rand
+ mod #4
+ jneq #1, drop
+ ret #-1
+ drop: ret #0
+
+** SECCOMP filter example:
+
+ ld [4] /* offsetof(struct seccomp_data, arch) */
+ jne #0xc000003e, bad /* AUDIT_ARCH_X86_64 */
+ ld [0] /* offsetof(struct seccomp_data, nr) */
+ jeq #15, good /* __NR_rt_sigreturn */
+ jeq #231, good /* __NR_exit_group */
+ jeq #60, good /* __NR_exit */
+ jeq #0, good /* __NR_read */
+ jeq #1, good /* __NR_write */
+ jeq #5, good /* __NR_fstat */
+ jeq #9, good /* __NR_mmap */
+ jeq #14, good /* __NR_rt_sigprocmask */
+ jeq #13, good /* __NR_rt_sigaction */
+ jeq #35, good /* __NR_nanosleep */
+ bad: ret #0 /* SECCOMP_RET_KILL_THREAD */
+ good: ret #0x7fff0000 /* SECCOMP_RET_ALLOW */
+
+The above example code can be placed into a file (here called "foo"), and
+then be passed to the bpf_asm tool for generating opcodes, output that xt_bpf
+and cls_bpf understands and can directly be loaded with. Example with above
+ARP code:
+
+$ ./bpf_asm foo
+4,40 0 0 12,21 0 1 2054,6 0 0 4294967295,6 0 0 0,
+
+In copy and paste C-like output:
+
+$ ./bpf_asm -c foo
+{ 0x28, 0, 0, 0x0000000c },
+{ 0x15, 0, 1, 0x00000806 },
+{ 0x06, 0, 0, 0xffffffff },
+{ 0x06, 0, 0, 0000000000 },
+
+In particular, as usage with xt_bpf or cls_bpf can result in more complex BPF
+filters that might not be obvious at first, it's good to test filters before
+attaching to a live system. For that purpose, there's a small tool called
+bpf_dbg under tools/bpf/ in the kernel source directory. This debugger allows
+for testing BPF filters against given pcap files, single stepping through the
+BPF code on the pcap's packets and to do BPF machine register dumps.
+
+Starting bpf_dbg is trivial and just requires issuing:
+
+# ./bpf_dbg
+
+In case input and output do not equal stdin/stdout, bpf_dbg takes an
+alternative stdin source as a first argument, and an alternative stdout
+sink as a second one, e.g. `./bpf_dbg test_in.txt test_out.txt`.
+
+Other than that, a particular libreadline configuration can be set via
+file "~/.bpf_dbg_init" and the command history is stored in the file
+"~/.bpf_dbg_history".
+
+Interaction in bpf_dbg happens through a shell that also has auto-completion
+support (follow-up example commands starting with '>' denote bpf_dbg shell).
+The usual workflow would be to ...
+
+> load bpf 6,40 0 0 12,21 0 3 2048,48 0 0 23,21 0 1 1,6 0 0 65535,6 0 0 0
+ Loads a BPF filter from standard output of bpf_asm, or transformed via
+ e.g. `tcpdump -iem1 -ddd port 22 | tr '\n' ','`. Note that for JIT
+ debugging (next section), this command creates a temporary socket and
+ loads the BPF code into the kernel. Thus, this will also be useful for
+ JIT developers.
+
+> load pcap foo.pcap
+ Loads standard tcpdump pcap file.
+
+> run [<n>]
+bpf passes:1 fails:9
+ Runs through all packets from a pcap to account how many passes and fails
+ the filter will generate. A limit of packets to traverse can be given.
+
+> disassemble
+l0: ldh [12]
+l1: jeq #0x800, l2, l5
+l2: ldb [23]
+l3: jeq #0x1, l4, l5
+l4: ret #0xffff
+l5: ret #0
+ Prints out BPF code disassembly.
+
+> dump
+/* { op, jt, jf, k }, */
+{ 0x28, 0, 0, 0x0000000c },
+{ 0x15, 0, 3, 0x00000800 },
+{ 0x30, 0, 0, 0x00000017 },
+{ 0x15, 0, 1, 0x00000001 },
+{ 0x06, 0, 0, 0x0000ffff },
+{ 0x06, 0, 0, 0000000000 },
+ Prints out C-style BPF code dump.
+
+> breakpoint 0
+breakpoint at: l0: ldh [12]
+> breakpoint 1
+breakpoint at: l1: jeq #0x800, l2, l5
+ ...
+ Sets breakpoints at particular BPF instructions. Issuing a `run` command
+ will walk through the pcap file continuing from the current packet and
+ break when a breakpoint is being hit (another `run` will continue from
+ the currently active breakpoint executing next instructions):
+
+ > run
+ -- register dump --
+ pc: [0] <-- program counter
+ code: [40] jt[0] jf[0] k[12] <-- plain BPF code of current instruction
+ curr: l0: ldh [12] <-- disassembly of current instruction
+ A: [00000000][0] <-- content of A (hex, decimal)
+ X: [00000000][0] <-- content of X (hex, decimal)
+ M[0,15]: [00000000][0] <-- folded content of M (hex, decimal)
+ -- packet dump -- <-- Current packet from pcap (hex)
+ len: 42
+ 0: 00 19 cb 55 55 a4 00 14 a4 43 78 69 08 06 00 01
+ 16: 08 00 06 04 00 01 00 14 a4 43 78 69 0a 3b 01 26
+ 32: 00 00 00 00 00 00 0a 3b 01 01
+ (breakpoint)
+ >
+
+> breakpoint
+breakpoints: 0 1
+ Prints currently set breakpoints.
+
+> step [-<n>, +<n>]
+ Performs single stepping through the BPF program from the current pc
+ offset. Thus, on each step invocation, above register dump is issued.
+ This can go forwards and backwards in time, a plain `step` will break
+ on the next BPF instruction, thus +1. (No `run` needs to be issued here.)
+
+> select <n>
+ Selects a given packet from the pcap file to continue from. Thus, on
+ the next `run` or `step`, the BPF program is being evaluated against
+ the user pre-selected packet. Numbering starts just as in Wireshark
+ with index 1.
+
+> quit
+#
+ Exits bpf_dbg.
+
+JIT compiler
+------------
+
+The Linux kernel has a built-in BPF JIT compiler for x86_64, SPARC, PowerPC,
+ARM, ARM64, MIPS and s390 which can be enabled through CONFIG_BPF_JIT. The JIT
+compiler is transparently invoked for each attached filter from user space
+or for internal kernel users if it has been previously enabled by root:
+
+ echo 1 > /proc/sys/net/core/bpf_jit_enable
+
+For JIT developers, doing audits etc, each compile run can output the generated
+opcode image into the kernel log via:
+
+ echo 2 > /proc/sys/net/core/bpf_jit_enable
+
+Example output from dmesg:
+
+[ 3389.935842] flen=6 proglen=70 pass=3 image=ffffffffa0069c8f
+[ 3389.935847] JIT code: 00000000: 55 48 89 e5 48 83 ec 60 48 89 5d f8 44 8b 4f 68
+[ 3389.935849] JIT code: 00000010: 44 2b 4f 6c 4c 8b 87 d8 00 00 00 be 0c 00 00 00
+[ 3389.935850] JIT code: 00000020: e8 1d 94 ff e0 3d 00 08 00 00 75 16 be 17 00 00
+[ 3389.935851] JIT code: 00000030: 00 e8 28 94 ff e0 83 f8 01 75 07 b8 ff ff 00 00
+[ 3389.935852] JIT code: 00000040: eb 02 31 c0 c9 c3
+
+When CONFIG_BPF_JIT_ALWAYS_ON is enabled, bpf_jit_enable is permanently set to 1 and
+setting any other value than that will return in failure. This is even the case for
+setting bpf_jit_enable to 2, since dumping the final JIT image into the kernel log
+is discouraged and introspection through bpftool (under tools/bpf/bpftool/) is the
+generally recommended approach instead.
+
+In the kernel source tree under tools/bpf/, there's bpf_jit_disasm for
+generating disassembly out of the kernel log's hexdump:
+
+# ./bpf_jit_disasm
+70 bytes emitted from JIT compiler (pass:3, flen:6)
+ffffffffa0069c8f + <x>:
+ 0: push %rbp
+ 1: mov %rsp,%rbp
+ 4: sub $0x60,%rsp
+ 8: mov %rbx,-0x8(%rbp)
+ c: mov 0x68(%rdi),%r9d
+ 10: sub 0x6c(%rdi),%r9d
+ 14: mov 0xd8(%rdi),%r8
+ 1b: mov $0xc,%esi
+ 20: callq 0xffffffffe0ff9442
+ 25: cmp $0x800,%eax
+ 2a: jne 0x0000000000000042
+ 2c: mov $0x17,%esi
+ 31: callq 0xffffffffe0ff945e
+ 36: cmp $0x1,%eax
+ 39: jne 0x0000000000000042
+ 3b: mov $0xffff,%eax
+ 40: jmp 0x0000000000000044
+ 42: xor %eax,%eax
+ 44: leaveq
+ 45: retq
+
+Issuing option `-o` will "annotate" opcodes to resulting assembler
+instructions, which can be very useful for JIT developers:
+
+# ./bpf_jit_disasm -o
+70 bytes emitted from JIT compiler (pass:3, flen:6)
+ffffffffa0069c8f + <x>:
+ 0: push %rbp
+ 55
+ 1: mov %rsp,%rbp
+ 48 89 e5
+ 4: sub $0x60,%rsp
+ 48 83 ec 60
+ 8: mov %rbx,-0x8(%rbp)
+ 48 89 5d f8
+ c: mov 0x68(%rdi),%r9d
+ 44 8b 4f 68
+ 10: sub 0x6c(%rdi),%r9d
+ 44 2b 4f 6c
+ 14: mov 0xd8(%rdi),%r8
+ 4c 8b 87 d8 00 00 00
+ 1b: mov $0xc,%esi
+ be 0c 00 00 00
+ 20: callq 0xffffffffe0ff9442
+ e8 1d 94 ff e0
+ 25: cmp $0x800,%eax
+ 3d 00 08 00 00
+ 2a: jne 0x0000000000000042
+ 75 16
+ 2c: mov $0x17,%esi
+ be 17 00 00 00
+ 31: callq 0xffffffffe0ff945e
+ e8 28 94 ff e0
+ 36: cmp $0x1,%eax
+ 83 f8 01
+ 39: jne 0x0000000000000042
+ 75 07
+ 3b: mov $0xffff,%eax
+ b8 ff ff 00 00
+ 40: jmp 0x0000000000000044
+ eb 02
+ 42: xor %eax,%eax
+ 31 c0
+ 44: leaveq
+ c9
+ 45: retq
+ c3
+
+For BPF JIT developers, bpf_jit_disasm, bpf_asm and bpf_dbg provides a useful
+toolchain for developing and testing the kernel's JIT compiler.
+
+Testing
+-------
+
+Next to the BPF toolchain, the kernel also ships a test module that contains
+various test cases for classic and internal BPF that can be executed against
+the BPF interpreter and JIT compiler. It can be found in lib/test_bpf.c and
+enabled via Kconfig:
+
+ CONFIG_TEST_BPF=m
+
+After the module has been built and installed, the test suite can be executed
+via insmod or modprobe against 'test_bpf' module. Results of the test cases
+including timings in nsec can be found in the kernel log (dmesg).
+
+Misc
+----
+
+Also trinity, the Linux syscall fuzzer, has built-in support for BPF and
+SECCOMP-BPF kernel fuzzing.
+
+Written by
+----------
+
+The document was written in the hope that it is found useful and in order
+to give potential BPF hackers or security auditors a better overview of
+the underlying architecture.
+
+Jay Schulist <jschlst@samba.org>
+Daniel Borkmann <daniel@iogearbox.net>
+Alexei Starovoitov <ast@kernel.org>
--
2.17.1
^ permalink raw reply related
* [RFC bpf-next v2 2/3] docs: net: Use lowercase 'k' for kernel
From: Tobin C. Harding @ 2018-08-02 22:30 UTC (permalink / raw)
To: Daniel Borkmann, Alexei Starovoitov
Cc: Tobin C. Harding, Jonathan Corbet, David S. Miller, linux-doc,
netdev, linux-kernel
In-Reply-To: <20180802223100.26236-1-me@tobin.cc>
The whole document uses a lowercase 'k' for 'kernel' except in one
instance. The kernel community also favours a lowercase 'k'.
Use lowercase 'k' for kernel instead of uppercase 'K'.
Signed-off-by: Tobin C. Harding <me@tobin.cc>
---
Documentation/networking/filter.txt | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt
index 1fe4adf9c4c6..d12721e997f8 100644
--- a/Documentation/networking/filter.txt
+++ b/Documentation/networking/filter.txt
@@ -6,7 +6,7 @@ Introduction
Linux Socket Filtering (LSF) is derived from the Berkeley Packet Filter.
Though there are some distinct differences between the BSD and Linux
-Kernel filtering, but when we speak of BPF or LSF in Linux context, we
+kernel filtering, but when we speak of BPF or LSF in Linux context, we
mean the very same mechanism of filtering in the Linux kernel.
BPF allows a user-space program to attach a filter onto any socket and
--
2.17.1
^ permalink raw reply related
* [RFC bpf-next v2 1/3] docs: net: Fix various minor typos
From: Tobin C. Harding @ 2018-08-02 22:30 UTC (permalink / raw)
To: Daniel Borkmann, Alexei Starovoitov
Cc: Tobin C. Harding, Jonathan Corbet, David S. Miller, linux-doc,
netdev, linux-kernel
In-Reply-To: <20180802223100.26236-1-me@tobin.cc>
Document contains a few minor typos and grammatical issues. We should
however try to keep the current flavour of the document.
Fix typos and grammar if fix is _really_ an improvement.
Signed-off-by: Tobin C. Harding <me@tobin.cc>
---
Documentation/networking/filter.txt | 66 +++++++++++++++--------------
1 file changed, 35 insertions(+), 31 deletions(-)
diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt
index e6b4ebb2b243..1fe4adf9c4c6 100644
--- a/Documentation/networking/filter.txt
+++ b/Documentation/networking/filter.txt
@@ -29,8 +29,8 @@ removing the old one and placing your new one in its place, assuming your
filter has passed the checks, otherwise if it fails the old filter will
remain on that socket.
-SO_LOCK_FILTER option allows to lock the filter attached to a socket. Once
-set, a filter cannot be removed or changed. This allows one process to
+SO_LOCK_FILTER option allows locking of the filter attached to a socket.
+Once set, a filter cannot be removed or changed. This allows one process to
setup a socket, attach a filter, lock it then drop privileges and be
assured that the filter will be kept until the socket is closed.
@@ -463,7 +463,7 @@ JIT compiler
------------
The Linux kernel has a built-in BPF JIT compiler for x86_64, SPARC, PowerPC,
-ARM, ARM64, MIPS and s390 and can be enabled through CONFIG_BPF_JIT. The JIT
+ARM, ARM64, MIPS and s390 which can be enabled through CONFIG_BPF_JIT. The JIT
compiler is transparently invoked for each attached filter from user space
or for internal kernel users if it has been previously enabled by root:
@@ -572,7 +572,7 @@ Internally, for the kernel interpreter, a different instruction set
format with similar underlying principles from BPF described in previous
paragraphs is being used. However, the instruction set format is modelled
closer to the underlying architecture to mimic native instruction sets, so
-that a better performance can be achieved (more details later). This new
+that better performance can be achieved (more details later). This new
ISA is called 'eBPF' or 'internal BPF' interchangeably. (Note: eBPF which
originates from [e]xtended BPF is not the same as BPF extensions! While
eBPF is an ISA, BPF extensions date back to classic BPF's 'overloading'
@@ -647,12 +647,12 @@ Some core changes of the new internal format:
32-bit architectures run 64-bit internal BPF programs via interpreter.
Their JITs may convert BPF programs that only use 32-bit subregisters into
- native instruction set and let the rest being interpreted.
+ native instruction set and let the rest be interpreted.
- Operation is 64-bit, because on 64-bit architectures, pointers are also
- 64-bit wide, and we want to pass 64-bit values in/out of kernel functions,
- so 32-bit eBPF registers would otherwise require to define register-pair
- ABI, thus, there won't be able to use a direct eBPF register to HW register
+ Operation is 64-bit since on 64-bit architectures pointers are also
+ 64-bit wide and we want to pass 64-bit values in/out of kernel functions.
+ 32-bit eBPF registers would otherwise require us to define a register-pair
+ ABI, thus we would not be able to use a direct eBPF register to HW register
mapping and JIT would need to do combine/split/move operations for every
register in and out of the function, which is complex, bug prone and slow.
Another reason is the use of atomic 64-bit counters.
@@ -677,7 +677,7 @@ Some core changes of the new internal format:
situations without performance penalty.
After an in-kernel function call, R1 - R5 are reset to unreadable and R0 has
- a return value of the function. Since R6 - R9 are callee saved, their state
+ the return value of the function. Since R6 - R9 are callee saved, their state
is preserved across the call.
For example, consider three C functions:
@@ -715,7 +715,7 @@ Some core changes of the new internal format:
are currently not supported, but these restrictions can be lifted if necessary
in the future.
- On 64-bit architectures all register map to HW registers one to one. For
+ On 64-bit architectures all registers map to HW registers one to one. For
example, x86_64 JIT compiler can map them as ...
R0 - rax
@@ -814,9 +814,10 @@ A program, that is translated internally consists of the following elements:
op:16, jt:8, jf:8, k:32 ==> op:8, dst_reg:4, src_reg:4, off:16, imm:32
-So far 87 internal BPF instructions were implemented. 8-bit 'op' opcode field
-has room for new instructions. Some of them may use 16/24/32 byte encoding. New
-instructions must be multiple of 8 bytes to preserve backward compatibility.
+So far 87 internal BPF instructions have been implemented. 8-bit 'op' opcode
+field has room for new instructions. Some of them may use 16/24/32 byte
+encoding. New instructions must be a multiple of 8 bytes to preserve backward
+compatibility.
Internal BPF is a general purpose RISC instruction set. Not every register and
every instruction are used during translation from original BPF to new format.
@@ -827,11 +828,11 @@ out of registers and would have to resort to spill/fill to stack.
Internal BPF can used as generic assembler for last step performance
optimizations, socket filters and seccomp are using it as assembler. Tracing
-filters may use it as assembler to generate code from kernel. In kernel usage
+filters may use it as assembler to generate code from kernel. In-kernel usage
may not be bounded by security considerations, since generated internal BPF code
-may be optimizing internal code path and not being exposed to the user space.
-Safety of internal BPF can come from a verifier (TBD). In such use cases as
-described, it may be used as safe instruction set.
+may use an optimised internal code path and may not be being exposed to user
+space. Safety of internal BPF can come from a verifier (TBD). In such use cases
+as described, it may be used as safe as the instruction set.
Just like the original BPF, the new format runs within a controlled environment,
is deterministic and the kernel can easily prove that. The safety of the program
@@ -927,7 +928,7 @@ Classic BPF is using BPF_MISC class to represent A = X and X = A moves.
eBPF is using BPF_MOV | BPF_X | BPF_ALU code instead. Since there are no
BPF_MISC operations in eBPF, the class 7 is used as BPF_ALU64 to mean
exactly the same operations as BPF_ALU, but with 64-bit wide operands
-instead. So BPF_ADD | BPF_X | BPF_ALU64 means 64-bit addition, i.e.:
+instead. So BPF_ADD | BPF_X | BPF_ALU64 means 64-bit addition i.e.
dst_reg = dst_reg + src_reg
Classic BPF wastes the whole BPF_RET class to represent a single 'ret'
@@ -1005,9 +1006,10 @@ BPF_XADD | BPF_DW | BPF_STX: lock xadd *(u64 *)(dst_reg + off16) += src_reg
Where size is one of: BPF_B or BPF_H or BPF_W or BPF_DW. Note that 1 and
2 byte atomic increments are not supported.
-eBPF has one 16-byte instruction: BPF_LD | BPF_DW | BPF_IMM which consists
-of two consecutive 'struct bpf_insn' 8-byte blocks and interpreted as single
+eBPF has one 16-byte instruction: BPF_LD | BPF_DW | BPF_IMM which consists of
+two consecutive 'struct bpf_insn' 8-byte blocks and is interpreted as single
instruction that loads 64-bit immediate value into a dst_reg.
+
Classic BPF has similar instruction: BPF_LD | BPF_W | BPF_IMM which loads
32-bit immediate value into a register.
@@ -1016,8 +1018,8 @@ eBPF verifier
The safety of the eBPF program is determined in two steps.
First step does DAG check to disallow loops and other CFG validation.
-In particular it will detect programs that have unreachable instructions.
-(though classic BPF checker allows them)
+In particular it will detect programs that have unreachable instructions
+(though classic BPF checker allows them).
Second step starts from the first insn and descends all possible paths.
It simulates execution of every insn and observes the state change of
@@ -1078,7 +1080,9 @@ Classic BPF verifier does similar check with M[0-15] memory slots.
For example:
bpf_ld R0 = *(u32 *)(R10 - 4)
bpf_exit
-is invalid program.
+
+is an invalid program.
+
Though R10 is correct read-only register and has type PTR_TO_STACK
and R10 - 4 is within stack bounds, there were no stores into that location.
@@ -1089,13 +1093,13 @@ Allowed function calls are customized with bpf_verifier_ops->get_func_proto()
The eBPF verifier will check that registers match argument constraints.
After the call register R0 will be set to return type of the function.
-Function calls is a main mechanism to extend functionality of eBPF programs.
-Socket filters may let programs to call one set of functions, whereas tracing
-filters may allow completely different set.
+Function calls is an important mechanism to extend functionality of eBPF
+programs. Socket filters may let programs call one set of functions,
+whereas tracing filters may allow a completely different set.
-If a function made accessible to eBPF program, it needs to be thought through
-from safety point of view. The verifier will guarantee that the function is
-called with valid arguments.
+If a function is made accessible to eBPF program, it needs to be thought
+through from a safety point of view. The verifier will guarantee that the
+function is called with valid arguments.
seccomp vs socket filters have different security restrictions for classic BPF.
Seccomp solves this by two stage verifier: classic BPF verifier is followed
@@ -1167,7 +1171,7 @@ checked and found to be non-NULL, all copies can become PTR_TO_MAP_VALUEs.
As well as range-checking, the tracked information is also used for enforcing
alignment of pointer accesses. For instance, on most systems the packet pointer
is 2 bytes after a 4-byte alignment. If a program adds 14 bytes to that to jump
-over the Ethernet header, then reads IHL and addes (IHL * 4), the resulting
+over the Ethernet header, then reads IHL and adds (IHL * 4), the resulting
pointer will have a variable offset known to be 4n+2 for some n, so adding the 2
bytes (NET_IP_ALIGN) gives a 4-byte alignment and so word-sized accesses through
that pointer are safe.
--
2.17.1
^ permalink raw reply related
* [RFC bpf-next v2 0/3] docs: Convert filter.txt to RST
From: Tobin C. Harding @ 2018-08-02 22:30 UTC (permalink / raw)
To: Daniel Borkmann, Alexei Starovoitov
Cc: Tobin C. Harding, Jonathan Corbet, David S. Miller, linux-doc,
netdev, linux-kernel
Hi,
v2 new and improved (with the actual files committed).
This is a documentation RFC for two reasons
1. The content is heavy and I don't fully understand it all, original
authors are you ok with the document being split up like this?
2. I'm only the conversion monkey, I'd like someone with a bigger view
of kernel docs in general to ok this please.
This RFC came out of this patch set
[PATCH bpf-next 00/13] docs: Convert BPF filter.txt to RST
As such the first two patches are the only ones I could salvage from
that set. Stating the obvious the mappings are:
Patch 1 was [PATCH bpf-next 12/13] docs: net: Fix various minor typos
Patch 2 was [PATCH bpf-next 09/13] docs: net: Use lowercase 'k' for kernel
Patch 3 is the splitting of filter.txt into bpf/eBPF.rst and
core-api/bpf.rst
Again, stating the obvious, if this RFC is ok I'll redo all the other
patches from the original set on top of this.
thanks,
Tobin.
v2:
- Actually add the files to the commit
- Check the _whole_ patch before sending
- Use checkpatch like we are supposed to
- Add licences
Tobin C. Harding (3):
docs: net: Fix various minor typos
docs: net: Use lowercase 'k' for kernel
docs: Split filter.txt into separate documents.
.../{networking/filter.txt => bpf/eBPF.rst} | 648 ++----------------
Documentation/core-api/bpf.rst | 599 ++++++++++++++++
2 files changed, 643 insertions(+), 604 deletions(-)
rename Documentation/{networking/filter.txt => bpf/eBPF.rst} (60%)
create mode 100644 Documentation/core-api/bpf.rst
--
2.17.1
^ permalink raw reply
* Re: [PATCH] inet/connection_sock: prefer _THIS_IP_ to current_text_addr
From: Nick Desaulniers @ 2018-08-02 22:29 UTC (permalink / raw)
To: David S. Miller; +Cc: Nathan Chancellor, netdev, LKML, Greg KH
In-Reply-To: <20180802.151740.166085629835691260.davem@davemloft.net>
On Thu, Aug 2, 2018 at 3:17 PM David Miller <davem@davemloft.net> wrote:
>
> From: Nick Desaulniers <ndesaulniers@google.com>
> Date: Thu, 2 Aug 2018 15:10:00 -0700
>
> > On Thu, Aug 2, 2018 at 2:42 PM David Miller <davem@davemloft.net> wrote:
> >>
> >> From: Nick Desaulniers <ndesaulniers@google.com>
> >> Date: Wed, 1 Aug 2018 14:57:59 -0700
> >>
> >> > As part of the effort to reduce the code duplication between _THIS_IP_
> >> > and current_text_addr(), let's consolidate callers of
> >> > current_text_addr() to use _THIS_IP_.
> >> >
> >> > Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
> >>
> >> I'll ACk this for now:
> >>
> >> Acked-by: David S. Miller <davem@davemloft.net>
> >
> > Thank you David. Should you take it into the net tree, can you please add:
> >
> > Cc: stable@vger.kernel.org # 4.17, 4.14, 4.9, 4.4
> >
> > to the commit message? This will help us as Nathan stated previously
> > in this thread.
>
> Why in the world is this a stable candidate? It doesn't fix a bug.
>
> My understanding is that you are trying to do a consolidation of code
> and clean things up so that only one interface is used.
>
> That means it should, at best, go to the net-next tree.
>
> Thank you.
+ gkh
We're trying to provide backports for all clang related bugs and
warnings to the stable trees back through 4.4.
--
Thanks,
~Nick Desaulniers
^ permalink raw reply
* Re: [PATCH] inet/connection_sock: prefer _THIS_IP_ to current_text_addr
From: David Miller @ 2018-08-02 22:17 UTC (permalink / raw)
To: ndesaulniers; +Cc: natechancellor, netdev, linux-kernel
In-Reply-To: <CAKwvOdnp7R094sbsyKi921ZVB8BD+d-8L37mcPv0UjMMF4QqDg@mail.gmail.com>
From: Nick Desaulniers <ndesaulniers@google.com>
Date: Thu, 2 Aug 2018 15:10:00 -0700
> On Thu, Aug 2, 2018 at 2:42 PM David Miller <davem@davemloft.net> wrote:
>>
>> From: Nick Desaulniers <ndesaulniers@google.com>
>> Date: Wed, 1 Aug 2018 14:57:59 -0700
>>
>> > As part of the effort to reduce the code duplication between _THIS_IP_
>> > and current_text_addr(), let's consolidate callers of
>> > current_text_addr() to use _THIS_IP_.
>> >
>> > Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
>>
>> I'll ACk this for now:
>>
>> Acked-by: David S. Miller <davem@davemloft.net>
>
> Thank you David. Should you take it into the net tree, can you please add:
>
> Cc: stable@vger.kernel.org # 4.17, 4.14, 4.9, 4.4
>
> to the commit message? This will help us as Nathan stated previously
> in this thread.
Why in the world is this a stable candidate? It doesn't fix a bug.
My understanding is that you are trying to do a consolidation of code
and clean things up so that only one interface is used.
That means it should, at best, go to the net-next tree.
Thank you.
^ permalink raw reply
* Re: [PATCH] inet/connection_sock: prefer _THIS_IP_ to current_text_addr
From: Nick Desaulniers @ 2018-08-02 22:10 UTC (permalink / raw)
To: David S. Miller; +Cc: Nathan Chancellor, netdev, LKML
In-Reply-To: <20180802.144234.41564686794492805.davem@davemloft.net>
On Thu, Aug 2, 2018 at 2:42 PM David Miller <davem@davemloft.net> wrote:
>
> From: Nick Desaulniers <ndesaulniers@google.com>
> Date: Wed, 1 Aug 2018 14:57:59 -0700
>
> > As part of the effort to reduce the code duplication between _THIS_IP_
> > and current_text_addr(), let's consolidate callers of
> > current_text_addr() to use _THIS_IP_.
> >
> > Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
>
> I'll ACk this for now:
>
> Acked-by: David S. Miller <davem@davemloft.net>
Thank you David. Should you take it into the net tree, can you please add:
Cc: stable@vger.kernel.org # 4.17, 4.14, 4.9, 4.4
to the commit message? This will help us as Nathan stated previously
in this thread.
--
Thanks,
~Nick Desaulniers
^ permalink raw reply
* Re: [pull request][net-next 00/10] Mellanox, mlx5 and devlink updates 2018-07-31
From: Petr Machata @ 2018-08-02 20:10 UTC (permalink / raw)
To: David Miller
Cc: jakub.kicinski, saeedm, netdev, jiri, alexander.duyck, helgaas
In-Reply-To: <20180802.110415.1933161188196080420.davem@davemloft.net>
David Miller <davem@davemloft.net> writes:
> From: Jakub Kicinski <jakub.kicinski@netronome.com>
> Date: Thu, 2 Aug 2018 10:11:12 -0700
>
>> On Thu, 02 Aug 2018 11:29:12 +0300, Petr Machata wrote:
>>> Could you please clarify your remark?
>>
>> Oh, I think David meant the patches I was objecting to a while ago,
>> which were doing buffer configuration via the DCB API.
>
> Exactly.
Ah, OK then.
Thanks,
Petr
^ permalink raw reply
* Re: [PATCH net-next] xen-netback: use true and false for boolean values
From: David Miller @ 2018-08-02 21:43 UTC (permalink / raw)
To: gustavo; +Cc: wei.liu2, paul.durrant, xen-devel, netdev, linux-kernel
In-Reply-To: <20180802003101.GA19256@embeddedor.com>
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 1 Aug 2018 19:31:01 -0500
> Return statements in functions returning bool should use true or false
> instead of an integer value.
>
> This issue was detected with the help of Coccinelle.
>
> Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Applied.
^ permalink raw reply
* Re: [PATCH] inet/connection_sock: prefer _THIS_IP_ to current_text_addr
From: David Miller @ 2018-08-02 21:42 UTC (permalink / raw)
To: ndesaulniers; +Cc: natechancellor, netdev, linux-kernel
In-Reply-To: <20180801215759.103758-1-ndesaulniers@google.com>
From: Nick Desaulniers <ndesaulniers@google.com>
Date: Wed, 1 Aug 2018 14:57:59 -0700
> As part of the effort to reduce the code duplication between _THIS_IP_
> and current_text_addr(), let's consolidate callers of
> current_text_addr() to use _THIS_IP_.
>
> Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
I'll ACk this for now:
Acked-by: David S. Miller <davem@davemloft.net>
^ permalink raw reply
* Re: [PATCH] drivers: net: lmc: fix case value for target abort error
From: David Miller @ 2018-08-02 21:42 UTC (permalink / raw)
To: colin.king; +Cc: gomonovych, netdev, kernel-janitors, linux-kernel
In-Reply-To: <20180801172241.1974-1-colin.king@canonical.com>
From: Colin King <colin.king@canonical.com>
Date: Wed, 1 Aug 2018 18:22:41 +0100
> From: Colin Ian King <colin.king@canonical.com>
>
> Current value for a target abort error is 0x010, however, this value
> should in fact be 0x002. As it stands, the range of error is 0..7 so
> it is currently never being detected. This bug has been in the driver
> since the early 2.6.12 days (or before).
>
> Detected by CoverityScan, CID#744290 ("Logically dead code")
>
> Signed-off-by: Colin Ian King <colin.king@canonical.com>
Applied, thanks Colin.
^ permalink raw reply
* Re: [PATCH] net: hns: remove redundant variables 'max_frm' and 'tmp_mac_key'
From: David Miller @ 2018-08-02 21:40 UTC (permalink / raw)
To: yuehaibing
Cc: yisen.zhuang, salil.mehta, lipeng321, linux-kernel, netdev,
shenjian15, joe, keescook, wangxi11
In-Reply-To: <20180801101647.16968-1-yuehaibing@huawei.com>
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 1 Aug 2018 18:16:47 +0800
> Variables 'max_frm' and 'tmp_mac_key' are being assigned,
> but are never used,hence they are redundant and can be removed.
>
> fix fllowing warning:
>
> drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c:461:6: warning: variable 'max_frm' set but not used [-Wunused-but-set-variable]
> drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c:1685:31: warning: variable 'tmp_mac_key' set but not used [-Wunused-but-set-variable]
> drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c:1855:41: warning: variable 'tmp_mac_key' set but not used [-Wunused-but-set-variable]
>
> Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Applied, thank you.
^ permalink raw reply
* Re: [PATCH v4 0/8] Add clock config and pm support to bcm iProc mdio mux
From: David Miller @ 2018-08-02 21:39 UTC (permalink / raw)
To: arun.parameswaran
Cc: f.fainelli, andrew, robh+dt, mark.rutland, rjui, sbranden,
catalin.marinas, will.deacon, netdev, devicetree,
linux-arm-kernel, linux-kernel, bcm-kernel-feedback-list
In-Reply-To: <1533171233-14557-1-git-send-email-arun.parameswaran@broadcom.com>
From: Arun Parameswaran <arun.parameswaran@broadcom.com>
Date: Wed, 1 Aug 2018 17:53:45 -0700
> The patchset extends the Broadcom iProc mdio mux to add support for
> suspend/resume and the ability to configure the internal clock
> divider. The patchset also sets the scan control register to
> disable external master access.
...
Series applied to net-next, thank you.
^ permalink raw reply
* Re: [PATCH v1 1/3] random: Make crng state queryable
From: Theodore Y. Ts'o @ 2018-08-02 21:35 UTC (permalink / raw)
To: Jason A. Donenfeld; +Cc: linux-kernel, netdev, davem
In-Reply-To: <20180731191102.2434-2-Jason@zx2c4.com>
On Tue, Jul 31, 2018 at 09:11:00PM +0200, Jason A. Donenfeld wrote:
> It is very useful to be able to know whether or not get_random_bytes_wait
> / wait_for_random_bytes is going to block or not, or whether plain
> get_random_bytes is going to return good randomness or bad randomness.
>
> The particular use case is for mitigating certain attacks in WireGuard.
> A handshake packet arrives and is queued up. Elsewhere a worker thread
> takes items from the queue and processes them. In replying to these
> items, it needs to use some random data, and it has to be good random
> data. If we simply block until we can have good randomness, then it's
> possible for an attacker to fill the queue up with packets waiting to be
> processed. Upon realizing the queue is full, WireGuard will detect that
> it's under a denial of service attack, and behave accordingly. A better
> approach is just to drop incoming handshake packets if the crng is not
> yet initialized.
>
> This patch, therefore, makes that information directly accessible.
>
> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Applied to the random.git tree.
- Ted
^ permalink raw reply
* [PATCH v7 bpf-next 14/14] samples/bpf: extend test_cgrp2_attach2 test to use cgroup storage
From: Roman Gushchin @ 2018-08-02 21:27 UTC (permalink / raw)
To: netdev
Cc: linux-kernel, kernel-team, Roman Gushchin, Alexei Starovoitov,
Daniel Borkmann
In-Reply-To: <20180802212730.18579-1-guro@fb.com>
The test_cgrp2_attach test covers bpf cgroup attachment code well,
so let's re-use it for testing allocation/releasing of cgroup storage.
The extension is pretty straightforward: the bpf program will use
the cgroup storage to save the number of transmitted bytes.
Expected output:
$ ./test_cgrp2_attach2
Attached DROP prog. This ping in cgroup /foo should fail...
ping: sendmsg: Operation not permitted
Attached DROP prog. This ping in cgroup /foo/bar should fail...
ping: sendmsg: Operation not permitted
Attached PASS prog. This ping in cgroup /foo/bar should pass...
Detached PASS from /foo/bar while DROP is attached to /foo.
This ping in cgroup /foo/bar should fail...
ping: sendmsg: Operation not permitted
Attached PASS from /foo/bar and detached DROP from /foo.
This ping in cgroup /foo/bar should pass...
### override:PASS
### multi:PASS
Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
---
samples/bpf/test_cgrp2_attach2.c | 21 ++++++++++++++++++++-
1 file changed, 20 insertions(+), 1 deletion(-)
diff --git a/samples/bpf/test_cgrp2_attach2.c b/samples/bpf/test_cgrp2_attach2.c
index b453e6a161be..180f9d813bca 100644
--- a/samples/bpf/test_cgrp2_attach2.c
+++ b/samples/bpf/test_cgrp2_attach2.c
@@ -8,7 +8,8 @@
* information. The number of invocations of the program, which maps
* to the number of packets received, is stored to key 0. Key 1 is
* incremented on each iteration by the number of bytes stored in
- * the skb.
+ * the skb. The program also stores the number of received bytes
+ * in the cgroup storage.
*
* - Attaches the new program to a cgroup using BPF_PROG_ATTACH
*
@@ -21,12 +22,15 @@
#include <stdio.h>
#include <stdlib.h>
#include <assert.h>
+#include <sys/resource.h>
+#include <sys/time.h>
#include <unistd.h>
#include <linux/bpf.h>
#include <bpf/bpf.h>
#include "bpf_insn.h"
+#include "bpf_rlimit.h"
#include "cgroup_helpers.h"
#define FOO "/foo"
@@ -205,6 +209,8 @@ static int map_fd = -1;
static int prog_load_cnt(int verdict, int val)
{
+ int cgroup_storage_fd;
+
if (map_fd < 0)
map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0);
if (map_fd < 0) {
@@ -212,6 +218,13 @@ static int prog_load_cnt(int verdict, int val)
return -1;
}
+ cgroup_storage_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE,
+ sizeof(struct bpf_cgroup_storage_key), 8, 0, 0);
+ if (cgroup_storage_fd < 0) {
+ printf("failed to create map '%s'\n", strerror(errno));
+ return -1;
+ }
+
struct bpf_insn prog[] = {
BPF_MOV32_IMM(BPF_REG_0, 0),
BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */
@@ -222,6 +235,11 @@ static int prog_load_cnt(int verdict, int val)
BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
BPF_MOV64_IMM(BPF_REG_1, val), /* r1 = 1 */
BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */
+ BPF_LD_MAP_FD(BPF_REG_1, cgroup_storage_fd),
+ BPF_MOV64_IMM(BPF_REG_2, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage),
+ BPF_MOV64_IMM(BPF_REG_1, val),
+ BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_W, BPF_REG_0, BPF_REG_1, 0, 0),
BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */
BPF_EXIT_INSN(),
};
@@ -237,6 +255,7 @@ static int prog_load_cnt(int verdict, int val)
printf("Output from verifier:\n%s\n-------\n", bpf_log_buf);
return 0;
}
+ close(cgroup_storage_fd);
return ret;
}
--
2.14.4
^ permalink raw reply related
* [PATCH v7 bpf-next 13/14] selftests/bpf: add a cgroup storage test
From: Roman Gushchin @ 2018-08-02 21:27 UTC (permalink / raw)
To: netdev
Cc: linux-kernel, kernel-team, Roman Gushchin, Alexei Starovoitov,
Daniel Borkmann
In-Reply-To: <20180802212730.18579-1-guro@fb.com>
Implement a test to cover the cgroup storage functionality.
The test implements a bpf program which drops every second packet
by using the cgroup storage as a persistent storage.
The test also use the userspace API to check the data
in the cgroup storage, alter it, and check that the loaded
and attached bpf program sees the update.
Expected output:
$ ./test_cgroup_storage
test_cgroup_storage:PASS
Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
---
tools/testing/selftests/bpf/Makefile | 3 +-
tools/testing/selftests/bpf/test_cgroup_storage.c | 130 ++++++++++++++++++++++
2 files changed, 132 insertions(+), 1 deletion(-)
create mode 100644 tools/testing/selftests/bpf/test_cgroup_storage.c
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 1b28277998e2..ad241ddba350 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -23,7 +23,7 @@ $(TEST_CUSTOM_PROGS): $(OUTPUT)/%: %.c
TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
test_sock test_btf test_sockmap test_lirc_mode2_user get_cgroup_id_user \
- test_socket_cookie
+ test_socket_cookie test_cgroup_storage
TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \
@@ -66,6 +66,7 @@ $(OUTPUT)/test_sockmap: cgroup_helpers.c
$(OUTPUT)/test_tcpbpf_user: cgroup_helpers.c
$(OUTPUT)/test_progs: trace_helpers.c
$(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c
+$(OUTPUT)/test_cgroup_storage: cgroup_helpers.c
.PHONY: force
diff --git a/tools/testing/selftests/bpf/test_cgroup_storage.c b/tools/testing/selftests/bpf/test_cgroup_storage.c
new file mode 100644
index 000000000000..dc83fb2d3f27
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_cgroup_storage.c
@@ -0,0 +1,130 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <assert.h>
+#include <bpf/bpf.h>
+#include <linux/filter.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+#include "cgroup_helpers.h"
+
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
+#define TEST_CGROUP "/test-bpf-cgroup-storage-buf/"
+
+int main(int argc, char **argv)
+{
+ struct bpf_insn prog[] = {
+ BPF_LD_MAP_FD(BPF_REG_1, 0), /* map fd */
+ BPF_MOV64_IMM(BPF_REG_2, 0), /* flags, not used */
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_get_local_storage),
+ BPF_MOV64_IMM(BPF_REG_1, 1),
+ BPF_STX_XADD(BPF_DW, BPF_REG_0, BPF_REG_1, 0),
+ BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x1),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+ BPF_EXIT_INSN(),
+ };
+ size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
+ int error = EXIT_FAILURE;
+ int map_fd, prog_fd, cgroup_fd;
+ struct bpf_cgroup_storage_key key;
+ unsigned long long value;
+
+ map_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE, sizeof(key),
+ sizeof(value), 0, 0);
+ if (map_fd < 0) {
+ printf("Failed to create map: %s\n", strerror(errno));
+ goto out;
+ }
+
+ prog[0].imm = map_fd;
+ prog_fd = bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB,
+ prog, insns_cnt, "GPL", 0,
+ bpf_log_buf, BPF_LOG_BUF_SIZE);
+ if (prog_fd < 0) {
+ printf("Failed to load bpf program: %s\n", bpf_log_buf);
+ goto out;
+ }
+
+ if (setup_cgroup_environment()) {
+ printf("Failed to setup cgroup environment\n");
+ goto err;
+ }
+
+ /* Create a cgroup, get fd, and join it */
+ cgroup_fd = create_and_get_cgroup(TEST_CGROUP);
+ if (!cgroup_fd) {
+ printf("Failed to create test cgroup\n");
+ goto err;
+ }
+
+ if (join_cgroup(TEST_CGROUP)) {
+ printf("Failed to join cgroup\n");
+ goto err;
+ }
+
+ /* Attach the bpf program */
+ if (bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0)) {
+ printf("Failed to attach bpf program\n");
+ goto err;
+ }
+
+ if (bpf_map_get_next_key(map_fd, NULL, &key)) {
+ printf("Failed to get the first key in cgroup storage\n");
+ goto err;
+ }
+
+ if (bpf_map_lookup_elem(map_fd, &key, &value)) {
+ printf("Failed to lookup cgroup storage\n");
+ goto err;
+ }
+
+ /* Every second packet should be dropped */
+ assert(system("ping localhost -c 1 -W 1 -q > /dev/null") == 0);
+ assert(system("ping localhost -c 1 -W 1 -q > /dev/null"));
+ assert(system("ping localhost -c 1 -W 1 -q > /dev/null") == 0);
+
+ /* Check the counter in the cgroup local storage */
+ if (bpf_map_lookup_elem(map_fd, &key, &value)) {
+ printf("Failed to lookup cgroup storage\n");
+ goto err;
+ }
+
+ if (value != 3) {
+ printf("Unexpected data in the cgroup storage: %llu\n", value);
+ goto err;
+ }
+
+ /* Bump the counter in the cgroup local storage */
+ value++;
+ if (bpf_map_update_elem(map_fd, &key, &value, 0)) {
+ printf("Failed to update the data in the cgroup storage\n");
+ goto err;
+ }
+
+ /* Every second packet should be dropped */
+ assert(system("ping localhost -c 1 -W 1 -q > /dev/null") == 0);
+ assert(system("ping localhost -c 1 -W 1 -q > /dev/null"));
+ assert(system("ping localhost -c 1 -W 1 -q > /dev/null") == 0);
+
+ /* Check the final value of the counter in the cgroup local storage */
+ if (bpf_map_lookup_elem(map_fd, &key, &value)) {
+ printf("Failed to lookup the cgroup storage\n");
+ goto err;
+ }
+
+ if (value != 7) {
+ printf("Unexpected data in the cgroup storage: %llu\n", value);
+ goto err;
+ }
+
+ error = 0;
+ printf("test_cgroup_storage:PASS\n");
+
+err:
+ cleanup_cgroup_environment();
+
+out:
+ return error;
+}
--
2.14.4
^ permalink raw reply related
* [PATCH v7 bpf-next 12/14] selftests/bpf: add verifier cgroup storage tests
From: Roman Gushchin @ 2018-08-02 21:27 UTC (permalink / raw)
To: netdev
Cc: linux-kernel, kernel-team, Roman Gushchin, Alexei Starovoitov,
Daniel Borkmann
In-Reply-To: <20180802212730.18579-1-guro@fb.com>
Add the following verifier tests to cover the cgroup storage
functionality:
1) valid access to the cgroup storage
2) invalid access: use regular hashmap instead of cgroup storage map
3) invalid access: use invalid map fd
4) invalid access: try access memory after the cgroup storage
5) invalid access: try access memory before the cgroup storage
6) invalid access: call get_local_storage() with non-zero flags
For tests 2)-6) check returned error strings.
Expected output:
$ ./test_verifier
#0/u add+sub+mul OK
#0/p add+sub+mul OK
#1/u DIV32 by 0, zero check 1 OK
...
#280/p valid cgroup storage access OK
#281/p invalid cgroup storage access 1 OK
#282/p invalid cgroup storage access 2 OK
#283/p invalid per-cgroup storage access 3 OK
#284/p invalid cgroup storage access 4 OK
#285/p invalid cgroup storage access 5 OK
...
#649/p pass modified ctx pointer to helper, 2 OK
#650/p pass modified ctx pointer to helper, 3 OK
Summary: 901 PASSED, 0 SKIPPED, 0 FAILED
Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
---
tools/testing/selftests/bpf/bpf_helpers.h | 2 +
tools/testing/selftests/bpf/test_verifier.c | 140 +++++++++++++++++++++++++++-
2 files changed, 141 insertions(+), 1 deletion(-)
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 19a424483f6e..cb9fcfbc9307 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -135,6 +135,8 @@ static int (*bpf_rc_keydown)(void *ctx, unsigned int protocol,
(void *) BPF_FUNC_rc_keydown;
static unsigned long long (*bpf_get_current_cgroup_id)(void) =
(void *) BPF_FUNC_get_current_cgroup_id;
+static void *(*bpf_get_local_storage)(void *map, unsigned long long flags) =
+ (void *) BPF_FUNC_get_local_storage;
/* llvm builtin functions that eBPF C program may use to
* emit BPF_LD_ABS and BPF_LD_IND instructions
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index c582afba9d1f..4b5e03c25204 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -50,7 +50,7 @@
#define MAX_INSNS BPF_MAXINSNS
#define MAX_FIXUPS 8
-#define MAX_NR_MAPS 7
+#define MAX_NR_MAPS 8
#define POINTER_VALUE 0xcafe4all
#define TEST_DATA_LEN 64
@@ -70,6 +70,7 @@ struct bpf_test {
int fixup_prog1[MAX_FIXUPS];
int fixup_prog2[MAX_FIXUPS];
int fixup_map_in_map[MAX_FIXUPS];
+ int fixup_cgroup_storage[MAX_FIXUPS];
const char *errstr;
const char *errstr_unpriv;
uint32_t retval;
@@ -4630,6 +4631,121 @@ static struct bpf_test tests[] = {
.result = REJECT,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
+ {
+ "valid cgroup storage access",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_2, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_get_local_storage),
+ BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_cgroup_storage = { 1 },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+ },
+ {
+ "invalid cgroup storage access 1",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_2, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_get_local_storage),
+ BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map1 = { 1 },
+ .result = REJECT,
+ .errstr = "cannot pass map_type 1 into func bpf_get_local_storage",
+ .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+ },
+ {
+ "invalid cgroup storage access 2",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_2, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 1),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_get_local_storage),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .result = REJECT,
+ .errstr = "fd 1 is not pointing to valid bpf_map",
+ .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+ },
+ {
+ "invalid per-cgroup storage access 3",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_2, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_get_local_storage),
+ BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 256),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_cgroup_storage = { 1 },
+ .result = REJECT,
+ .errstr = "invalid access to map value, value_size=64 off=256 size=4",
+ .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+ },
+ {
+ "invalid cgroup storage access 4",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_2, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_get_local_storage),
+ BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, -2),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_cgroup_storage = { 1 },
+ .result = REJECT,
+ .errstr = "invalid access to map value, value_size=64 off=-2 size=4",
+ .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+ },
+ {
+ "invalid cgroup storage access 5",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_2, 7),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_get_local_storage),
+ BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_cgroup_storage = { 1 },
+ .result = REJECT,
+ .errstr = "get_local_storage() doesn't support non-zero flags",
+ .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+ },
+ {
+ "invalid cgroup storage access 6",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_1),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_get_local_storage),
+ BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_cgroup_storage = { 1 },
+ .result = REJECT,
+ .errstr = "get_local_storage() doesn't support non-zero flags",
+ .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+ },
{
"multiple registers share map_lookup_elem result",
.insns = {
@@ -12462,6 +12578,19 @@ static int create_map_in_map(void)
return outer_map_fd;
}
+static int create_cgroup_storage(void)
+{
+ int fd;
+
+ fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE,
+ sizeof(struct bpf_cgroup_storage_key),
+ TEST_DATA_LEN, 0, 0);
+ if (fd < 0)
+ printf("Failed to create array '%s'!\n", strerror(errno));
+
+ return fd;
+}
+
static char bpf_vlog[UINT_MAX >> 8];
static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
@@ -12474,6 +12603,7 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
int *fixup_prog1 = test->fixup_prog1;
int *fixup_prog2 = test->fixup_prog2;
int *fixup_map_in_map = test->fixup_map_in_map;
+ int *fixup_cgroup_storage = test->fixup_cgroup_storage;
if (test->fill_helper)
test->fill_helper(test);
@@ -12541,6 +12671,14 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
fixup_map_in_map++;
} while (*fixup_map_in_map);
}
+
+ if (*fixup_cgroup_storage) {
+ map_fds[7] = create_cgroup_storage();
+ do {
+ prog[*fixup_cgroup_storage].imm = map_fds[7];
+ fixup_cgroup_storage++;
+ } while (*fixup_cgroup_storage);
+ }
}
static void do_test_single(struct bpf_test *test, bool unpriv,
--
2.14.4
^ permalink raw reply related
* [PATCH v7 bpf-next 09/14] bpf: sync bpf.h to tools/
From: Roman Gushchin @ 2018-08-02 21:27 UTC (permalink / raw)
To: netdev
Cc: linux-kernel, kernel-team, Roman Gushchin, Alexei Starovoitov,
Daniel Borkmann
In-Reply-To: <20180802212730.18579-1-guro@fb.com>
Sync cgroup storage related changes:
1) new BPF_MAP_TYPE_CGROUP_STORAGE map type
2) struct bpf_cgroup_sotrage_key definition
3) get_local_storage() helper
Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
---
tools/include/uapi/linux/bpf.h | 27 ++++++++++++++++++++++++++-
1 file changed, 26 insertions(+), 1 deletion(-)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 0ebaaf7f3568..dd5758dc35d3 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -75,6 +75,11 @@ struct bpf_lpm_trie_key {
__u8 data[0]; /* Arbitrary size */
};
+struct bpf_cgroup_storage_key {
+ __u64 cgroup_inode_id; /* cgroup inode id */
+ __u32 attach_type; /* program attach type */
+};
+
/* BPF syscall commands, see bpf(2) man-page for details. */
enum bpf_cmd {
BPF_MAP_CREATE,
@@ -120,6 +125,7 @@ enum bpf_map_type {
BPF_MAP_TYPE_CPUMAP,
BPF_MAP_TYPE_XSKMAP,
BPF_MAP_TYPE_SOCKHASH,
+ BPF_MAP_TYPE_CGROUP_STORAGE,
};
enum bpf_prog_type {
@@ -2089,6 +2095,24 @@ union bpf_attr {
* Return
* A 64-bit integer containing the current cgroup id based
* on the cgroup within which the current task is running.
+ *
+ * void* get_local_storage(void *map, u64 flags)
+ * Description
+ * Get the pointer to the local storage area.
+ * The type and the size of the local storage is defined
+ * by the *map* argument.
+ * The *flags* meaning is specific for each map type,
+ * and has to be 0 for cgroup local storage.
+ *
+ * Depending on the bpf program type, a local storage area
+ * can be shared between multiple instances of the bpf program,
+ * running simultaneously.
+ *
+ * A user should care about the synchronization by himself.
+ * For example, by using the BPF_STX_XADD instruction to alter
+ * the shared data.
+ * Return
+ * Pointer to the local storage area.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -2171,7 +2195,8 @@ union bpf_attr {
FN(rc_repeat), \
FN(rc_keydown), \
FN(skb_cgroup_id), \
- FN(get_current_cgroup_id),
+ FN(get_current_cgroup_id), \
+ FN(get_local_storage),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
--
2.14.4
^ permalink raw reply related
* [PATCH v7 bpf-next 08/14] bpf: introduce the bpf_get_local_storage() helper function
From: Roman Gushchin @ 2018-08-02 21:27 UTC (permalink / raw)
To: netdev
Cc: linux-kernel, kernel-team, Roman Gushchin, Alexei Starovoitov,
Daniel Borkmann
In-Reply-To: <20180802212730.18579-1-guro@fb.com>
The bpf_get_local_storage() helper function is used
to get a pointer to the bpf local storage from a bpf program.
It takes a pointer to a storage map and flags as arguments.
Right now it accepts only cgroup storage maps, and flags
argument has to be 0. Further it can be extended to support
other types of local storage: e.g. thread local storage etc.
Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
---
include/linux/bpf.h | 2 ++
include/uapi/linux/bpf.h | 21 ++++++++++++++++++++-
kernel/bpf/cgroup.c | 2 ++
kernel/bpf/core.c | 1 +
kernel/bpf/helpers.c | 20 ++++++++++++++++++++
kernel/bpf/verifier.c | 18 ++++++++++++++++++
net/core/filter.c | 23 ++++++++++++++++++++++-
7 files changed, 85 insertions(+), 2 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index ca4ac2a39def..cd8790d2c6ed 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -788,6 +788,8 @@ extern const struct bpf_func_proto bpf_sock_map_update_proto;
extern const struct bpf_func_proto bpf_sock_hash_update_proto;
extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto;
+extern const struct bpf_func_proto bpf_get_local_storage_proto;
+
/* Shared helpers among cBPF and eBPF. */
void bpf_user_rnd_init_once(void);
u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index b10118ee5afe..dd5758dc35d3 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2095,6 +2095,24 @@ union bpf_attr {
* Return
* A 64-bit integer containing the current cgroup id based
* on the cgroup within which the current task is running.
+ *
+ * void* get_local_storage(void *map, u64 flags)
+ * Description
+ * Get the pointer to the local storage area.
+ * The type and the size of the local storage is defined
+ * by the *map* argument.
+ * The *flags* meaning is specific for each map type,
+ * and has to be 0 for cgroup local storage.
+ *
+ * Depending on the bpf program type, a local storage area
+ * can be shared between multiple instances of the bpf program,
+ * running simultaneously.
+ *
+ * A user should care about the synchronization by himself.
+ * For example, by using the BPF_STX_XADD instruction to alter
+ * the shared data.
+ * Return
+ * Pointer to the local storage area.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -2177,7 +2195,8 @@ union bpf_attr {
FN(rc_repeat), \
FN(rc_keydown), \
FN(skb_cgroup_id), \
- FN(get_current_cgroup_id),
+ FN(get_current_cgroup_id), \
+ FN(get_local_storage),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index ddfa6cc13e57..0a4fe5a7dc91 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -684,6 +684,8 @@ cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_map_delete_elem_proto;
case BPF_FUNC_get_current_uid_gid:
return &bpf_get_current_uid_gid_proto;
+ case BPF_FUNC_get_local_storage:
+ return &bpf_get_local_storage_proto;
case BPF_FUNC_trace_printk:
if (capable(CAP_SYS_ADMIN))
return bpf_get_trace_printk_proto();
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 9abcf25ebf9f..4d09e610777f 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1795,6 +1795,7 @@ const struct bpf_func_proto bpf_get_current_comm_proto __weak;
const struct bpf_func_proto bpf_sock_map_update_proto __weak;
const struct bpf_func_proto bpf_sock_hash_update_proto __weak;
const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak;
+const struct bpf_func_proto bpf_get_local_storage_proto __weak;
const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
{
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 73065e2d23c2..1991466b8327 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -193,4 +193,24 @@ const struct bpf_func_proto bpf_get_current_cgroup_id_proto = {
.gpl_only = false,
.ret_type = RET_INTEGER,
};
+
+DECLARE_PER_CPU(void*, bpf_cgroup_storage);
+
+BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags)
+{
+ /* map and flags arguments are not used now,
+ * but provide an ability to extend the API
+ * for other types of local storages.
+ * verifier checks that their values are correct.
+ */
+ return (unsigned long) this_cpu_read(bpf_cgroup_storage);
+}
+
+const struct bpf_func_proto bpf_get_local_storage_proto = {
+ .func = bpf_get_local_storage,
+ .gpl_only = false,
+ .ret_type = RET_PTR_TO_MAP_VALUE,
+ .arg1_type = ARG_CONST_MAP_PTR,
+ .arg2_type = ARG_ANYTHING,
+};
#endif
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 1ede16c8bb40..587468a9c37d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2127,6 +2127,10 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
func_id != BPF_FUNC_current_task_under_cgroup)
goto error;
break;
+ case BPF_MAP_TYPE_CGROUP_STORAGE:
+ if (func_id != BPF_FUNC_get_local_storage)
+ goto error;
+ break;
/* devmap returns a pointer to a live net_device ifindex that we cannot
* allow to be modified from bpf side. So do not allow lookup elements
* for now.
@@ -2209,6 +2213,10 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
if (map->map_type != BPF_MAP_TYPE_SOCKHASH)
goto error;
break;
+ case BPF_FUNC_get_local_storage:
+ if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE)
+ goto error;
+ break;
default:
break;
}
@@ -2533,6 +2541,16 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
}
regs = cur_regs(env);
+
+ /* check that flags argument in get_local_storage(map, flags) is 0,
+ * this is required because get_local_storage() can't return an error.
+ */
+ if (func_id == BPF_FUNC_get_local_storage &&
+ !register_is_null(®s[BPF_REG_2])) {
+ verbose(env, "get_local_storage() doesn't support non-zero flags\n");
+ return -EINVAL;
+ }
+
/* reset caller saved regs */
for (i = 0; i < CALLER_SAVED_REGS; i++) {
mark_reg_not_init(env, regs, caller_saved[i]);
diff --git a/net/core/filter.c b/net/core/filter.c
index 9bb9a4488e25..9f73aae2f089 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4820,6 +4820,8 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
*/
case BPF_FUNC_get_current_uid_gid:
return &bpf_get_current_uid_gid_proto;
+ case BPF_FUNC_get_local_storage:
+ return &bpf_get_local_storage_proto;
default:
return bpf_base_func_proto(func_id);
}
@@ -4844,6 +4846,8 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
}
case BPF_FUNC_get_socket_cookie:
return &bpf_get_socket_cookie_sock_addr_proto;
+ case BPF_FUNC_get_local_storage:
+ return &bpf_get_local_storage_proto;
default:
return bpf_base_func_proto(func_id);
}
@@ -4866,6 +4870,17 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
}
}
+static const struct bpf_func_proto *
+cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+ switch (func_id) {
+ case BPF_FUNC_get_local_storage:
+ return &bpf_get_local_storage_proto;
+ default:
+ return sk_filter_func_proto(func_id, prog);
+ }
+}
+
static const struct bpf_func_proto *
tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
@@ -4988,6 +5003,8 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_sock_hash_update_proto;
case BPF_FUNC_get_socket_cookie:
return &bpf_get_socket_cookie_sock_ops_proto;
+ case BPF_FUNC_get_local_storage:
+ return &bpf_get_local_storage_proto;
default:
return bpf_base_func_proto(func_id);
}
@@ -5007,6 +5024,8 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_msg_cork_bytes_proto;
case BPF_FUNC_msg_pull_data:
return &bpf_msg_pull_data_proto;
+ case BPF_FUNC_get_local_storage:
+ return &bpf_get_local_storage_proto;
default:
return bpf_base_func_proto(func_id);
}
@@ -5034,6 +5053,8 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_sk_redirect_map_proto;
case BPF_FUNC_sk_redirect_hash:
return &bpf_sk_redirect_hash_proto;
+ case BPF_FUNC_get_local_storage:
+ return &bpf_get_local_storage_proto;
default:
return bpf_base_func_proto(func_id);
}
@@ -6838,7 +6859,7 @@ const struct bpf_prog_ops xdp_prog_ops = {
};
const struct bpf_verifier_ops cg_skb_verifier_ops = {
- .get_func_proto = sk_filter_func_proto,
+ .get_func_proto = cg_skb_func_proto,
.is_valid_access = sk_filter_is_valid_access,
.convert_ctx_access = bpf_convert_ctx_access,
};
--
2.14.4
^ permalink raw reply related
* [PATCH v7 bpf-next 07/14] bpf: don't allow create maps of cgroup local storages
From: Roman Gushchin @ 2018-08-02 21:27 UTC (permalink / raw)
To: netdev
Cc: linux-kernel, kernel-team, Roman Gushchin, Alexei Starovoitov,
Daniel Borkmann
In-Reply-To: <20180802212730.18579-1-guro@fb.com>
As there is one-to-one relation between a bpf program
and cgroup local storage map, there is no sense in
creating a map of cgroup local storage maps.
Forbid it explicitly to avoid possible side effects.
Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
---
kernel/bpf/map_in_map.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c
index 1da574612bea..3bfbf4464416 100644
--- a/kernel/bpf/map_in_map.c
+++ b/kernel/bpf/map_in_map.c
@@ -23,7 +23,8 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
* is a runtime binding. Doing static check alone
* in the verifier is not enough.
*/
- if (inner_map->map_type == BPF_MAP_TYPE_PROG_ARRAY) {
+ if (inner_map->map_type == BPF_MAP_TYPE_PROG_ARRAY ||
+ inner_map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE) {
fdput(f);
return ERR_PTR(-ENOTSUPP);
}
--
2.14.4
^ permalink raw reply related
* [PATCH v7 bpf-next 06/14] bpf/verifier: introduce BPF_PTR_TO_MAP_VALUE
From: Roman Gushchin @ 2018-08-02 21:27 UTC (permalink / raw)
To: netdev
Cc: linux-kernel, kernel-team, Roman Gushchin, Alexei Starovoitov,
Daniel Borkmann
In-Reply-To: <20180802212730.18579-1-guro@fb.com>
BPF_MAP_TYPE_CGROUP_STORAGE maps are special in a way
that the access from the bpf program side is lookup-free.
That means the result is guaranteed to be a valid
pointer to the cgroup storage; no NULL-check is required.
This patch introduces BPF_PTR_TO_MAP_VALUE return type,
which is required to cause the verifier accept programs,
which are not checking the map value pointer for being NULL.
Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
---
include/linux/bpf.h | 1 +
kernel/bpf/verifier.c | 8 ++++++--
2 files changed, 7 insertions(+), 2 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 16be67888c30..ca4ac2a39def 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -155,6 +155,7 @@ enum bpf_arg_type {
enum bpf_return_type {
RET_INTEGER, /* function returns integer */
RET_VOID, /* function doesn't return anything */
+ RET_PTR_TO_MAP_VALUE, /* returns a pointer to map elem value */
RET_PTR_TO_MAP_VALUE_OR_NULL, /* returns a pointer to map elem value or NULL */
};
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 7e75434a9e54..1ede16c8bb40 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2545,8 +2545,12 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
mark_reg_unknown(env, regs, BPF_REG_0);
} else if (fn->ret_type == RET_VOID) {
regs[BPF_REG_0].type = NOT_INIT;
- } else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL) {
- regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
+ } else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL ||
+ fn->ret_type == RET_PTR_TO_MAP_VALUE) {
+ if (fn->ret_type == RET_PTR_TO_MAP_VALUE)
+ regs[BPF_REG_0].type = PTR_TO_MAP_VALUE;
+ else
+ regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
/* There is no offset yet applied, variable or fixed */
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].off = 0;
--
2.14.4
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox