/proc/net/tcp{4,6} uses jiffies for various computations.
Let us add bpf_jiffies64() helper to tracing program
so bpf_iter and other programs can use it.
Change-Id: I18cb1e7ecea12b3ffdc597fe6b97a5d2c8137e1e
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200623230808.3988073-1-yhs@fb.com
bpf_free_used_maps() or close(map_fd) will trigger map_free callback.
bpf_free_used_maps() is called after bpf prog is no longer executing:
bpf_prog_put->call_rcu->bpf_prog_free->bpf_free_used_maps.
Hence there is no need to call synchronize_rcu() to protect map elements.
Note that hash_of_maps and array_of_maps update/delete inner maps via
sys_bpf() that calls maybe_wait_bpf_programs() and synchronize_rcu().
Change-Id: Iac22753fc71080d3cee7931f11f8ab8a30fe96c0
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Paul E. McKenney <paulmck@kernel.org>
Link: https://lore.kernel.org/bpf/20200630043343.53195-2-alexei.starovoitov@gmail.com
Add two tests for PTR_TO_BTF_ID vs. null ptr comparison,
one for PTR_TO_BTF_ID in the ctx structure and the
other for PTR_TO_BTF_ID after one level pointer chasing.
In both cases, the test ensures condition is not
removed.
For example, for this test
struct bpf_fentry_test_t {
struct bpf_fentry_test_t *a;
};
int BPF_PROG(test7, struct bpf_fentry_test_t *arg)
{
if (arg == 0)
test7_result = 1;
return 0;
}
Before the previous verifier change, we have xlated codes:
int test7(long long unsigned int * ctx):
; int BPF_PROG(test7, struct bpf_fentry_test_t *arg)
0: (79) r1 = *(u64 *)(r1 +0)
; int BPF_PROG(test7, struct bpf_fentry_test_t *arg)
1: (b4) w0 = 0
2: (95) exit
After the previous verifier change, we have:
int test7(long long unsigned int * ctx):
; int BPF_PROG(test7, struct bpf_fentry_test_t *arg)
0: (79) r1 = *(u64 *)(r1 +0)
; if (arg == 0)
1: (55) if r1 != 0x0 goto pc+4
; test7_result = 1;
2: (18) r1 = map[id:6][0]+48
4: (b7) r2 = 1
5: (7b) *(u64 *)(r1 +0) = r2
; int BPF_PROG(test7, struct bpf_fentry_test_t *arg)
6: (b4) w0 = 0
7: (95) exit
Change-Id: I4bfad59a173ce4e838c6f6f494e85c0a1e8d0431
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200630171241.2523875-1-yhs@fb.com
Wenbo reported an issue in [1] where a checking of null
pointer is evaluated as always false. In this particular
case, the program type is tp_btf and the pointer to
compare is a PTR_TO_BTF_ID.
The current verifier considers PTR_TO_BTF_ID always
reprents a non-null pointer, hence all PTR_TO_BTF_ID compares
to 0 will be evaluated as always not-equal, which resulted
in the branch elimination.
For example,
struct bpf_fentry_test_t {
struct bpf_fentry_test_t *a;
};
int BPF_PROG(test7, struct bpf_fentry_test_t *arg)
{
if (arg == 0)
test7_result = 1;
return 0;
}
int BPF_PROG(test8, struct bpf_fentry_test_t *arg)
{
if (arg->a == 0)
test8_result = 1;
return 0;
}
In above bpf programs, both branch arg == 0 and arg->a == 0
are removed. This may not be what developer expected.
The bug is introduced by Commit cac616db39c2 ("bpf: Verifier
track null pointer branch_taken with JNE and JEQ"),
where PTR_TO_BTF_ID is considered to be non-null when evaluting
pointer vs. scalar comparison. This may be added
considering we have PTR_TO_BTF_ID_OR_NULL in the verifier
as well.
PTR_TO_BTF_ID_OR_NULL is added to explicitly requires
a non-NULL testing in selective cases. The current generic
pointer tracing framework in verifier always
assigns PTR_TO_BTF_ID so users does not need to
check NULL pointer at every pointer level like a->b->c->d.
We may not want to assign every PTR_TO_BTF_ID as
PTR_TO_BTF_ID_OR_NULL as this will require a null test
before pointer dereference which may cause inconvenience
for developers. But we could avoid branch elimination
to preserve original code intention.
This patch simply removed PTR_TO_BTD_ID from reg_type_not_null()
in verifier, which prevented the above branches from being eliminated.
[1]: https://lore.kernel.org/bpf/79dbb7c0-449d-83eb-5f4f-7af0cc269168@fb.com/T/
Fixes: cac616db39c2 ("bpf: Verifier track null pointer branch_taken with JNE and JEQ")
Reported-by: Wenbo Zhang <ethercflow@gmail.com>
Change-Id: Ifdd05e48cd123b397afeece6ee584d3834e20333
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200630171240.2523722-1-yhs@fb.com
Iterating over BPF links attached to network namespace in pre_exit hook is
not safe, even if there is just one. Once link gets auto-detached, that is
its back-pointer to net object is set to NULL, the link can be released and
freed without waiting on netns_bpf_mutex, effectively causing the list
element we are operating on to be freed.
This leads to use-after-free when trying to access the next element on the
list, as reported by KASAN. Bug can be triggered by destroying a network
namespace, while also releasing a link attached to this network namespace.
| ==================================================================
| BUG: KASAN: use-after-free in netns_bpf_pernet_pre_exit+0xd9/0x130
| Read of size 8 at addr ffff888119e0d778 by task kworker/u8:2/177
|
| CPU: 3 PID: 177 Comm: kworker/u8:2 Not tainted 5.8.0-rc1-00197-ga0c04c9d1008-dirty #776
| Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ?-20190727_073836-buildvm-ppc64le-16.ppc.fedoraproject.org-3.fc31 04/01/2014
| Workqueue: netns cleanup_net
| Call Trace:
| dump_stack+0x9e/0xe0
| print_address_description.constprop.0+0x3a/0x60
| ? netns_bpf_pernet_pre_exit+0xd9/0x130
| kasan_report.cold+0x1f/0x40
| ? netns_bpf_pernet_pre_exit+0xd9/0x130
| netns_bpf_pernet_pre_exit+0xd9/0x130
| cleanup_net+0x30b/0x5b0
| ? unregister_pernet_device+0x50/0x50
| ? rcu_read_lock_bh_held+0xb0/0xb0
| ? _raw_spin_unlock_irq+0x24/0x50
| process_one_work+0x4d1/0xa10
| ? lock_release+0x3e0/0x3e0
| ? pwq_dec_nr_in_flight+0x110/0x110
| ? rwlock_bug.part.0+0x60/0x60
| worker_thread+0x7a/0x5c0
| ? process_one_work+0xa10/0xa10
| kthread+0x1e3/0x240
| ? kthread_create_on_node+0xd0/0xd0
| ret_from_fork+0x1f/0x30
|
| Allocated by task 280:
| save_stack+0x1b/0x40
| __kasan_kmalloc.constprop.0+0xc2/0xd0
| netns_bpf_link_create+0xfe/0x650
| __do_sys_bpf+0x153a/0x2a50
| do_syscall_64+0x59/0x300
| entry_SYSCALL_64_after_hwframe+0x44/0xa9
|
| Freed by task 198:
| save_stack+0x1b/0x40
| __kasan_slab_free+0x12f/0x180
| kfree+0xed/0x350
| process_one_work+0x4d1/0xa10
| worker_thread+0x7a/0x5c0
| kthread+0x1e3/0x240
| ret_from_fork+0x1f/0x30
|
| The buggy address belongs to the object at ffff888119e0d700
| which belongs to the cache kmalloc-192 of size 192
| The buggy address is located 120 bytes inside of
| 192-byte region [ffff888119e0d700, ffff888119e0d7c0)
| The buggy address belongs to the page:
| page:ffffea0004678340 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0
| flags: 0x2fffe0000000200(slab)
| raw: 02fffe0000000200 ffffea00045ba8c0 0000000600000006 ffff88811a80ea80
| raw: 0000000000000000 0000000000100010 00000001ffffffff 0000000000000000
| page dumped because: kasan: bad access detected
|
| Memory state around the buggy address:
| ffff888119e0d600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
| ffff888119e0d680: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
| >ffff888119e0d700: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
| ^
| ffff888119e0d780: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
| ffff888119e0d800: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
| ==================================================================
Remove the "fast-path" for releasing a link that got auto-detached by a
dying network namespace to fix it. This way as long as link is on the list
and netns_bpf mutex is held, we have a guarantee that link memory can be
accessed.
An alternative way to fix this issue would be to safely iterate over the
list of links and ensure there is no access to link object after detaching
it. But, at the moment, optimizing synchronization overhead on link release
without a workload in mind seems like an overkill.
Fixes: ab53cad90eb1 ("bpf, netns: Keep a list of attached bpf_link's")
Change-Id: Ib1f668d2fba2b3d16806608548e3335a9274a866
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20200630164541.1329993-1-jakub@cloudflare.com
Using BPF_PROG_DETACH on a flow dissector program supports neither
attach_flags nor attach_bpf_fd. Yet no value is enforced for them.
Enforce that attach_flags are zero, and require the current program
to be passed via attach_bpf_fd. This allows us to remove the check
for CAP_SYS_ADMIN, since userspace can now no longer remove
arbitrary flow dissector programs.
Fixes: b27f7bb590ba ("flow_dissector: Move out netns_bpf prog callbacks")
Change-Id: I2eaf851ab883dc315c642bf6ea26f529a178e5d3
Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200629095630.7933-3-lmb@cloudflare.com
Using BPF_PROG_ATTACH on a flow dissector program supports neither
target_fd, attach_flags or replace_bpf_fd but accepts any value.
Enforce that all of them are zero. This is fine for replace_bpf_fd
since its presence is indicated by BPF_F_REPLACE. It's more
problematic for target_fd, since zero is a valid fd. Should we
want to use the flag later on we'd have to add an exception for
fd 0. The alternative is to force a value like -1. This requires
more changes to tests. There is also precedent for using 0,
since bpf_iter uses this for target_fd as well.
Fixes: b27f7bb590ba ("flow_dissector: Move out netns_bpf prog callbacks")
Change-Id: Ic950b6164e2ad5405669794b069376a98521a67f
Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200629095630.7933-2-lmb@cloudflare.com
To support multi-prog link-based attachments for new netns attach types, we
need to keep track of more than one bpf_link per attach type. Hence,
convert net->bpf.links into a list, that currently can be either empty or
have just one item.
Instead of reusing bpf_prog_list from bpf-cgroup, we link together
bpf_netns_link's themselves. This makes list management simpler as we don't
have to allocate, initialize, and later release list elements. We can do
this because multi-prog attachment will be available only for bpf_link, and
we don't need to build a list of programs attached directly and indirectly
via links.
No functional changes intended.
Change-Id: I64d0c6fe7c9fa3a50b81071345bb7e9458df1aff
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200625141357.910330-4-jakub@cloudflare.com
Prepare for having multi-prog attachments for new netns attach types by
storing programs to run in a bpf_prog_array, which is well suited for
iterating over programs and running them in sequence.
After this change bpf(PROG_QUERY) may block to allocate memory in
bpf_prog_array_copy_to_user() for collected program IDs. This forces a
change in how we protect access to the attached program in the query
callback. Because bpf_prog_array_copy_to_user() can sleep, we switch from
an RCU read lock to holding a mutex that serializes updaters.
Because we allow only one BPF flow_dissector program to be attached to
netns at all times, the bpf_prog_array pointed by net->bpf.run_array is
always either detached (null) or one element long.
No functional changes intended.
Change-Id: I9c35fccef7fc323a73f49ba3066b60baa7d1fb03
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200625141357.910330-3-jakub@cloudflare.com
Prepare for using bpf_prog_array to store attached programs by moving out
code that updates the attached program out of flow dissector.
Managing bpf_prog_array is more involved than updating a single bpf_prog
pointer. This will let us do it all from one place, bpf/net_namespace.c, in
the subsequent patch.
No functional change intended.
Change-Id: I3e347b0401b328c2bf355c6559c4fe43ee5cd19d
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200625141357.910330-2-jakub@cloudflare.com
BPF ringbuf assumes the size to be a multiple of page size and the power of
2 value. The latter is important to avoid division while calculating position
inside the ring buffer and using (N-1) mask instead. This patch fixes omission
to enforce power-of-2 size rule.
Fixes: 457f44363a88 ("bpf: Implement BPF ring buffer and verifier support for it")
Change-Id: Ic4b87200d91936c3302ab0687f6b187bac7ce60b
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20200630061500.1804799-1-andriin@fb.com
To ensure btf_ctx_access() is safe the verifier checks that the BTF
arg type is an int, enum, or pointer. When the function does the
BTF arg lookup it uses the calculation 'arg = off / 8' using the
fact that registers are 8B. This requires that the first arg is
in the first reg, the second in the second, and so on. However,
for __int128 the arg will consume two registers by default LLVM
implementation. So this will cause the arg layout assumed by the
'arg = off / 8' calculation to be incorrect.
Because __int128 is uncommon this patch applies the easiest fix and
will force int types to be sizeof(u64) or smaller so that they will
fit in a single register.
v2: remove unneeded parens per Andrii's feedback
Fixes: 9e15db66136a1 ("bpf: Implement accurate raw_tp context access via BTF")
Change-Id: Iaa7a6fbaf8d4746c80bf4217bf518aba9e1a83b3
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/159303723962.11287.13309537171132420717.stgit@john-Precision-5820-Tower
The helper is used in tracing programs to cast a socket
pointer to a udp6_sock pointer.
The return value could be NULL if the casting is illegal.
Change-Id: If6ef5992dcf07b5b8171c8221078d0f96fdce956
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Cc: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/bpf/20200623230815.3988481-1-yhs@fb.com
Three more helpers are added to cast a sock_common pointer to
an tcp_sock, tcp_timewait_sock or a tcp_request_sock for
tracing programs.
Change-Id: I43e998912a1e786d8f96e01e9a331554832d29be
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200623230811.3988277-1-yhs@fb.com
The helper is used in tracing programs to cast a socket
pointer to a tcp6_sock pointer.
The return value could be NULL if the casting is illegal.
A new helper return type RET_PTR_TO_BTF_ID_OR_NULL is added
so the verifier is able to deduce proper return types for the helper.
Different from the previous BTF_ID based helpers,
the bpf_skc_to_tcp6_sock() argument can be several possible
btf_ids. More specifically, all possible socket data structures
with sock_common appearing in the first in the memory layout.
This patch only added socket types related to tcp and udp.
All possible argument btf_id and return value btf_id
for helper bpf_skc_to_tcp6_sock() are pre-calculcated and
cached. In the future, it is even possible to precompute
these btf_id's at kernel build time.
Change-Id: I42addc1779489c7e2ba1de30a59e009b1ba21f80
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200623230809.3988195-1-yhs@fb.com
This patch adds support of SO_KEEPALIVE flag and TCP related options
to bpf_setsockopt() routine. This is helpful if we want to enable or tune
TCP keepalive for applications which don't do it in the userspace code.
v3:
- update kernel-doc in uapi (Nikita Vetoshkin <nekto0n@yandex-team.ru>)
v4:
- update kernel-doc in tools too (Alexei Starovoitov)
- add test to selftests (Alexei Starovoitov)
Change-Id: Ie16bf737964360c59ab9a8d796343863b3883b59
Signed-off-by: Dmitry Yakunin <zeil@yandex-team.ru>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200620153052.9439-3-zeil@yandex-team.ru
Add a helper to directly set the TCP_KEEP_IDLE sockopt from kernel
space without going through a fake uaccess.
Change-Id: I57286ea8efb618476bac4d8d74f16e01b17e12aa
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is preparation for usage in bpf_setsockopt.
Change-Id: I13c4392ffff4c19f40bdf36b22f6bf0ed760de2a
Signed-off-by: Dmitry Yakunin <zeil@yandex-team.ru>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200620153052.9439-1-zeil@yandex-team.ru
When producing the bpf-helpers.7 man page from the documentation from
the BPF user space header file, rst2man complains:
<stdin>:2636: (ERROR/3) Unexpected indentation.
<stdin>:2640: (WARNING/2) Block quote ends without a blank line; unexpected unindent.
Let's fix formatting for the relevant chunk (item list in
bpf_ringbuf_query()'s description), and for a couple other functions.
Change-Id: Ia04fa1e276aceb34405de9be8e57ed7946675c3b
Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200623153935.6215-1-quentin@isovalent.com
This is a fix for a regression in commit 2c78ee898d8f ("bpf: Implement CAP_BPF").
Before the above commit it was possible to load network bpf programs
with just the CAP_SYS_ADMIN privilege.
The Android bpfloader happens to run in such a configuration (it has
SYS_ADMIN but not NET_ADMIN) and creates maps and loads bpf programs
for later use by Android's netd (which has NET_ADMIN but not SYS_ADMIN).
Fixes: 2c78ee898d8f ("bpf: Implement CAP_BPF")
Reported-by: John Stultz <john.stultz@linaro.org>
Change-Id: I14b6ebf1244d7fe5c8d2296f19bd71f2b638e4a7
Signed-off-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: John Stultz <john.stultz@linaro.org>
Link: https://lore.kernel.org/bpf/20200620212616.93894-1-zenczykowski@gmail.com
Currently, if a bpf program has more than one subprograms, each program will be
jitted separately. For programs with bpf-to-bpf calls the
prog->aux->num_exentries is not setup properly. For example, with
bpf_iter_netlink.c modified to force one function to be not inlined and with
CONFIG_BPF_JIT_ALWAYS_ON the following error is seen:
$ ./test_progs -n 3/3
...
libbpf: failed to load program 'iter/netlink'
libbpf: failed to load object 'bpf_iter_netlink'
libbpf: failed to load BPF skeleton 'bpf_iter_netlink': -4007
test_netlink:FAIL:bpf_iter_netlink__open_and_load skeleton open_and_load failed
#3/3 netlink:FAIL
The dmesg shows the following errors:
ex gen bug
which is triggered by the following code in arch/x86/net/bpf_jit_comp.c:
if (excnt >= bpf_prog->aux->num_exentries) {
pr_err("ex gen bug\n");
return -EFAULT;
}
This patch fixes the issue by computing proper num_exentries for each
subprogram before calling JIT.
Change-Id: If0291fa2e4b6609d4ee507398e9d8203342c4e08
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Switch most of BPF helper definitions from returning int to long. These
definitions are coming from comments in BPF UAPI header and are used to
generate bpf_helper_defs.h (under libbpf) to be later included and used from
BPF programs.
In actual in-kernel implementation, all the helpers are defined as returning
u64, but due to some historical reasons, most of them are actually defined as
returning int in UAPI (usually, to return 0 on success, and negative value on
error).
This actually causes Clang to quite often generate sub-optimal code, because
compiler believes that return value is 32-bit, and in a lot of cases has to be
up-converted (usually with a pair of 32-bit bit shifts) to 64-bit values,
before they can be used further in BPF code.
Besides just "polluting" the code, these 32-bit shifts quite often cause
problems for cases in which return value matters. This is especially the case
for the family of bpf_probe_read_str() functions. There are few other similar
helpers (e.g., bpf_read_branch_records()), in which return value is used by
BPF program logic to record variable-length data and process it. For such
cases, BPF program logic carefully manages offsets within some array or map to
read variable-length data. For such uses, it's crucial for BPF verifier to
track possible range of register values to prove that all the accesses happen
within given memory bounds. Those extraneous zero-extending bit shifts,
inserted by Clang (and quite often interleaved with other code, which makes
the issues even more challenging and sometimes requires employing extra
per-variable compiler barriers), throws off verifier logic and makes it mark
registers as having unknown variable offset. We'll study this pattern a bit
later below.
Another common pattern is to check return of BPF helper for non-zero state to
detect error conditions and attempt alternative actions in such case. Even in
this simple and straightforward case, this 32-bit vs BPF's native 64-bit mode
quite often leads to sub-optimal and unnecessary extra code. We'll look at
this pattern as well.
Clang's BPF target supports two modes of code generation: ALU32, in which it
is capable of using lower 32-bit parts of registers, and no-ALU32, in which
only full 64-bit registers are being used. ALU32 mode somewhat mitigates the
above described problems, but not in all cases.
This patch switches all the cases in which BPF helpers return 0 or negative
error from returning int to returning long. It is shown below that such change
in definition leads to equivalent or better code. No-ALU32 mode benefits more,
but ALU32 mode doesn't degrade or still gets improved code generation.
Another class of cases switched from int to long are bpf_probe_read_str()-like
helpers, which encode successful case as non-negative values, while still
returning negative value for errors.
In all of such cases, correctness is preserved due to two's complement
encoding of negative values and the fact that all helpers return values with
32-bit absolute value. Two's complement ensures that for negative values
higher 32 bits are all ones and when truncated, leave valid negative 32-bit
value with the same value. Non-negative values have upper 32 bits set to zero
and similarly preserve value when high 32 bits are truncated. This means that
just casting to int/u32 is correct and efficient (and in ALU32 mode doesn't
require any extra shifts).
To minimize the chances of regressions, two code patterns were investigated,
as mentioned above. For both patterns, BPF assembly was analyzed in
ALU32/NO-ALU32 compiler modes, both with current 32-bit int return type and
new 64-bit long return type.
Case 1. Variable-length data reading and concatenation. This is quite
ubiquitous pattern in tracing/monitoring applications, reading data like
process's environment variables, file path, etc. In such case, many pieces of
string-like variable-length data are read into a single big buffer, and at the
end of the process, only a part of array containing actual data is sent to
user-space for further processing. This case is tested in test_varlen.c
selftest (in the next patch). Code flow is roughly as follows:
void *payload = &sample->payload;
u64 len;
len = bpf_probe_read_kernel_str(payload, MAX_SZ1, &source_data1);
if (len <= MAX_SZ1) {
payload += len;
sample->len1 = len;
}
len = bpf_probe_read_kernel_str(payload, MAX_SZ2, &source_data2);
if (len <= MAX_SZ2) {
payload += len;
sample->len2 = len;
}
/* and so on */
sample->total_len = payload - &sample->payload;
/* send over, e.g., perf buffer */
There could be two variations with slightly different code generated: when len
is 64-bit integer and when it is 32-bit integer. Both variations were analysed.
BPF assembly instructions between two successive invocations of
bpf_probe_read_kernel_str() were used to check code regressions. Results are
below, followed by short analysis. Left side is using helpers with int return
type, the right one is after the switch to long.
ALU32 + INT ALU32 + LONG
=========== ============
64-BIT (13 insns): 64-BIT (10 insns):
------------------------------------ ------------------------------------
17: call 115 17: call 115
18: if w0 > 256 goto +9 <LBB0_4> 18: if r0 > 256 goto +6 <LBB0_4>
19: w1 = w0 19: r1 = 0 ll
20: r1 <<= 32 21: *(u64 *)(r1 + 0) = r0
21: r1 s>>= 32 22: r6 = 0 ll
22: r2 = 0 ll 24: r6 += r0
24: *(u64 *)(r2 + 0) = r1 00000000000000c8 <LBB0_4>:
25: r6 = 0 ll 25: r1 = r6
27: r6 += r1 26: w2 = 256
00000000000000e0 <LBB0_4>: 27: r3 = 0 ll
28: r1 = r6 29: call 115
29: w2 = 256
30: r3 = 0 ll
32: call 115
32-BIT (11 insns): 32-BIT (12 insns):
------------------------------------ ------------------------------------
17: call 115 17: call 115
18: if w0 > 256 goto +7 <LBB1_4> 18: if w0 > 256 goto +8 <LBB1_4>
19: r1 = 0 ll 19: r1 = 0 ll
21: *(u32 *)(r1 + 0) = r0 21: *(u32 *)(r1 + 0) = r0
22: w1 = w0 22: r0 <<= 32
23: r6 = 0 ll 23: r0 >>= 32
25: r6 += r1 24: r6 = 0 ll
00000000000000d0 <LBB1_4>: 26: r6 += r0
26: r1 = r6 00000000000000d8 <LBB1_4>:
27: w2 = 256 27: r1 = r6
28: r3 = 0 ll 28: w2 = 256
30: call 115 29: r3 = 0 ll
31: call 115
In ALU32 mode, the variant using 64-bit length variable clearly wins and
avoids unnecessary zero-extension bit shifts. In practice, this is even more
important and good, because BPF code won't need to do extra checks to "prove"
that payload/len are within good bounds.
32-bit len is one instruction longer. Clang decided to do 64-to-32 casting
with two bit shifts, instead of equivalent `w1 = w0` assignment. The former
uses extra register. The latter might potentially lose some range information,
but not for 32-bit value. So in this case, verifier infers that r0 is [0, 256]
after check at 18:, and shifting 32 bits left/right keeps that range intact.
We should probably look into Clang's logic and see why it chooses bitshifts
over sub-register assignments for this.
NO-ALU32 + INT NO-ALU32 + LONG
============== ===============
64-BIT (14 insns): 64-BIT (10 insns):
------------------------------------ ------------------------------------
17: call 115 17: call 115
18: r0 <<= 32 18: if r0 > 256 goto +6 <LBB0_4>
19: r1 = r0 19: r1 = 0 ll
20: r1 >>= 32 21: *(u64 *)(r1 + 0) = r0
21: if r1 > 256 goto +7 <LBB0_4> 22: r6 = 0 ll
22: r0 s>>= 32 24: r6 += r0
23: r1 = 0 ll 00000000000000c8 <LBB0_4>:
25: *(u64 *)(r1 + 0) = r0 25: r1 = r6
26: r6 = 0 ll 26: r2 = 256
28: r6 += r0 27: r3 = 0 ll
00000000000000e8 <LBB0_4>: 29: call 115
29: r1 = r6
30: r2 = 256
31: r3 = 0 ll
33: call 115
32-BIT (13 insns): 32-BIT (13 insns):
------------------------------------ ------------------------------------
17: call 115 17: call 115
18: r1 = r0 18: r1 = r0
19: r1 <<= 32 19: r1 <<= 32
20: r1 >>= 32 20: r1 >>= 32
21: if r1 > 256 goto +6 <LBB1_4> 21: if r1 > 256 goto +6 <LBB1_4>
22: r2 = 0 ll 22: r2 = 0 ll
24: *(u32 *)(r2 + 0) = r0 24: *(u32 *)(r2 + 0) = r0
25: r6 = 0 ll 25: r6 = 0 ll
27: r6 += r1 27: r6 += r1
00000000000000e0 <LBB1_4>: 00000000000000e0 <LBB1_4>:
28: r1 = r6 28: r1 = r6
29: r2 = 256 29: r2 = 256
30: r3 = 0 ll 30: r3 = 0 ll
32: call 115 32: call 115
In NO-ALU32 mode, for the case of 64-bit len variable, Clang generates much
superior code, as expected, eliminating unnecessary bit shifts. For 32-bit
len, code is identical.
So overall, only ALU-32 32-bit len case is more-or-less equivalent and the
difference stems from internal Clang decision, rather than compiler lacking
enough information about types.
Case 2. Let's look at the simpler case of checking return result of BPF helper
for errors. The code is very simple:
long bla;
if (bpf_probe_read_kenerl(&bla, sizeof(bla), 0))
return 1;
else
return 0;
ALU32 + CHECK (9 insns) ALU32 + CHECK (9 insns)
==================================== ====================================
0: r1 = r10 0: r1 = r10
1: r1 += -8 1: r1 += -8
2: w2 = 8 2: w2 = 8
3: r3 = 0 3: r3 = 0
4: call 113 4: call 113
5: w1 = w0 5: r1 = r0
6: w0 = 1 6: w0 = 1
7: if w1 != 0 goto +1 <LBB2_2> 7: if r1 != 0 goto +1 <LBB2_2>
8: w0 = 0 8: w0 = 0
0000000000000048 <LBB2_2>: 0000000000000048 <LBB2_2>:
9: exit 9: exit
Almost identical code, the only difference is the use of full register
assignment (r1 = r0) vs half-registers (w1 = w0) in instruction #5. On 32-bit
architectures, new BPF assembly might be slightly less optimal, in theory. But
one can argue that's not a big issue, given that use of full registers is
still prevalent (e.g., for parameter passing).
NO-ALU32 + CHECK (11 insns) NO-ALU32 + CHECK (9 insns)
==================================== ====================================
0: r1 = r10 0: r1 = r10
1: r1 += -8 1: r1 += -8
2: r2 = 8 2: r2 = 8
3: r3 = 0 3: r3 = 0
4: call 113 4: call 113
5: r1 = r0 5: r1 = r0
6: r1 <<= 32 6: r0 = 1
7: r1 >>= 32 7: if r1 != 0 goto +1 <LBB2_2>
8: r0 = 1 8: r0 = 0
9: if r1 != 0 goto +1 <LBB2_2> 0000000000000048 <LBB2_2>:
10: r0 = 0 9: exit
0000000000000058 <LBB2_2>:
11: exit
NO-ALU32 is a clear improvement, getting rid of unnecessary zero-extension bit
shifts.
Change-Id: Ie4ba541847b25df0d89042e74ee18c7b3d99d091
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20200623032224.4020118-1-andriin@fb.com
Set map_btf_name and map_btf_id for all map types so that map fields can
be accessed by bpf programs.
Change-Id: Iaac3e281d0372951555e9e694fc5eeb4d2062d99
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/a825f808f22af52b018dbe82f1c7d29dab5fc978.1592600985.git.rdna@fb.com
There are multiple use-cases when it's convenient to have access to bpf
map fields, both `struct bpf_map` and map type specific struct-s such as
`struct bpf_array`, `struct bpf_htab`, etc.
For example while working with sock arrays it can be necessary to
calculate the key based on map->max_entries (some_hash % max_entries).
Currently this is solved by communicating max_entries via "out-of-band"
channel, e.g. via additional map with known key to get info about target
map. That works, but is not very convenient and error-prone while
working with many maps.
In other cases necessary data is dynamic (i.e. unknown at loading time)
and it's impossible to get it at all. For example while working with a
hash table it can be convenient to know how much capacity is already
used (bpf_htab.count.counter for BPF_F_NO_PREALLOC case).
At the same time kernel knows this info and can provide it to bpf
program.
Fill this gap by adding support to access bpf map fields from bpf
program for both `struct bpf_map` and map type specific fields.
Support is implemented via btf_struct_access() so that a user can define
their own `struct bpf_map` or map type specific struct in their program
with only necessary fields and preserve_access_index attribute, cast a
map to this struct and use a field.
For example:
struct bpf_map {
__u32 max_entries;
} __attribute__((preserve_access_index));
struct bpf_array {
struct bpf_map map;
__u32 elem_size;
} __attribute__((preserve_access_index));
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
__uint(max_entries, 4);
__type(key, __u32);
__type(value, __u32);
} m_array SEC(".maps");
SEC("cgroup_skb/egress")
int cg_skb(void *ctx)
{
struct bpf_array *array = (struct bpf_array *)&m_array;
struct bpf_map *map = (struct bpf_map *)&m_array;
/* .. use map->max_entries or array->map.max_entries .. */
}
Similarly to other btf_struct_access() use-cases (e.g. struct tcp_sock
in net/ipv4/bpf_tcp_ca.c) the patch allows access to any fields of
corresponding struct. Only reading from map fields is supported.
For btf_struct_access() to work there should be a way to know btf id of
a struct that corresponds to a map type. To get btf id there should be a
way to get a stringified name of map-specific struct, such as
"bpf_array", "bpf_htab", etc for a map type. Two new fields are added to
`struct bpf_map_ops` to handle it:
* .map_btf_name keeps a btf name of a struct returned by map_alloc();
* .map_btf_id is used to cache btf id of that struct.
To make btf ids calculation cheaper they're calculated once while
preparing btf_vmlinux and cached same way as it's done for btf_id field
of `struct bpf_func_proto`
While calculating btf ids, struct names are NOT checked for collision.
Collisions will be checked as a part of the work to prepare btf ids used
in verifier in compile time that should land soon. The only known
collision for `struct bpf_htab` (kernel/bpf/hashtab.c vs
net/core/sock_map.c) was fixed earlier.
Both new fields .map_btf_name and .map_btf_id must be set for a map type
for the feature to work. If neither is set for a map type, verifier will
return ENOTSUPP on a try to access map_ptr of corresponding type. If
just one of them set, it's verifier misconfiguration.
Only `struct bpf_array` for BPF_MAP_TYPE_ARRAY and `struct bpf_htab` for
BPF_MAP_TYPE_HASH are supported by this patch. Other map types will be
supported separately.
The feature is available only for CONFIG_DEBUG_INFO_BTF=y and gated by
perfmon_capable() so that unpriv programs won't have access to bpf map
fields.
Change-Id: Ibd44c4fe4f296e0488dff536e1ec56e90d542f56
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/6479686a0cd1e9067993df57b4c3eef0e276fec9.1592600985.git.rdna@fb.com
btf_parse_vmlinux() implements manual search for struct bpf_ctx_convert
since at the time of implementing btf_find_by_name_kind() was not
available.
Later btf_find_by_name_kind() was introduced in 27ae7997a661 ("bpf:
Introduce BPF_PROG_TYPE_STRUCT_OPS"). It provides similar search
functionality and can be leveraged in btf_parse_vmlinux(). Do it.
Change-Id: I8696dbabe6b28ced7c0b72683a349da2849b349b
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/6e12d5c3e8a3d552925913ef73a695dd1bb27800.1592600985.git.rdna@fb.com
From an email thread on how to try to fix up the current Android boot
issues...
Change-Id: If4a4ef96acc09708727451fb79233b3cc1f18482
Signed-off-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
When do experiments with llvm (disabling instcombine and
simplifyCFG), I hit the following error with test_seg6_loop.o.
; R1=pkt(id=0,off=0,r=48,imm=0), R7=pkt(id=0,off=40,r=48,imm=0)
w2 = w7
; R2_w=inv(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff))
w2 -= w1
R2 32-bit pointer arithmetic prohibited
The corresponding source code is:
uint32_t srh_off
// srh and skb->data are all packet pointers
srh_off = (char *)srh - (char *)(long)skb->data;
The verifier does not support 32-bit pointer/scalar arithmetic.
Without my llvm change, the code looks like
; R3=pkt(id=0,off=40,r=48,imm=0), R8=pkt(id=0,off=0,r=48,imm=0)
w3 -= w8
; R3_w=inv(id=0)
This is explicitly allowed in verifier if both registers are
pointers and the opcode is BPF_SUB.
To fix this problem, I changed the verifier to allow
32-bit pointer/scaler BPF_SUB operations.
At the source level, the issue could be workarounded with
inline asm or changing "uint32_t srh_off" to "uint64_t srh_off".
But I feel that verifier change might be the right thing to do.
Change-Id: I945bd3ed2a2f4ce3189002d810873e055ed5bb84
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20200618234631.3321118-1-yhs@fb.com
Fix definition of bpf_ringbuf_output() in UAPI header comments, which is used
to generate libbpf's bpf_helper_defs.h header. Return value is a number (error
code), not a pointer.
Fixes: 457f44363a88 ("bpf: Implement BPF ring buffer and verifier support for it")
Change-Id: I160f1c2da80e8fb1d338c028e780242401345c53
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20200615214926.3638836-1-andriin@fb.com
BPF_PROBE_MEM is kernel-internal implmementation details. When dumping BPF
instructions to user-space, it needs to be replaced back with BPF_MEM mode.
Fixes: 2a02759ef5f8 ("bpf: Add support for BTF pointers to interpreter")
Change-Id: I0fb4571b71113e03d132aea0e24061d1dbdd1be3
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200613002115.1632142-1-andriin@fb.com
V2:
- Defer changing BPF-syscall to start at file-descriptor 1
- Use {} to zero initialise struct.
The recent commit fbee97feed9b ("bpf: Add support to attach bpf program to a
devmap entry"), introduced ability to attach (and run) a separate XDP
bpf_prog for each devmap entry. A bpf_prog is added via a file-descriptor.
As zero were a valid FD, not using the feature requires using value minus-1.
The UAPI is extended via tail-extending struct bpf_devmap_val and using
map->value_size to determine the feature set.
This will break older userspace applications not using the bpf_prog feature.
Consider an old userspace app that is compiled against newer kernel
uapi/bpf.h, it will not know that it need to initialise the member
bpf_prog.fd to minus-1. Thus, users will be forced to update source code to
get program running on newer kernels.
This patch remove the minus-1 checks, and have zero mean feature isn't used.
Followup patches either for kernel or libbpf should handle and avoid
returning file-descriptor zero in the first place.
Fixes: fbee97feed9b ("bpf: Add support to attach bpf program to a devmap entry")
Change-Id: I2dcd38cc6b266a202070a703a08c80bdd76e4c25
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/159170950687.2102545.7235914718298050113.stgit@firesoul
When using BPF_PROG_ATTACH to attach a program to a cgroup in
BPF_F_ALLOW_MULTI mode, it is not possible to replace a program
with itself. This is because the check for duplicate programs
doesn't take the replacement program into account.
Replacing a program with itself might seem weird, but it has
some uses: first, it allows resetting the associated cgroup storage.
Second, it makes the API consistent with the non-ALLOW_MULTI usage,
where it is possible to replace a program with itself. Third, it
aligns BPF_PROG_ATTACH with bpf_link, where replacing itself is
also supported.
Sice this code has been refactored a few times this change will
only apply to v5.7 and later. Adjustments could be made to
commit 1020c1f24a94 ("bpf: Simplify __cgroup_bpf_attach") and
commit d7bf2c10af ("bpf: allocate cgroup storage entries on attaching bpf programs")
as well as commit 324bda9e6c ("bpf: multi program support for cgroup+bpf")
Fixes: af6eea57437a ("bpf: Implement bpf_link-based cgroup BPF program attachment")
Change-Id: Iab6473295791bd02cc785628a20164d2be573412
Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200608162202.94002-1-lmb@cloudflare.com
This is a new context that does not handle metadata at the moment, so
mark data_meta invalid.
Fixes: fbee97feed9b ("bpf: Add support to attach bpf program to a devmap entry")
Change-Id: If50703e1fea700017cf9f8114638c18f9dd6fea6
Signed-off-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200608151723.9539-1-dsahern@kernel.org
The seg6_validate_srh() is used to validate SRH for three cases:
case1: SRH of data-plane SRv6 packets to be processed by the Linux kernel.
Case2: SRH of the netlink message received from user-space (iproute2)
Case3: SRH injected into packets through setsockopt
In case1, the SRH can be encoded in the Reduced way (i.e., first SID is
carried in DA only and not represented as SID in the SRH) and the
seg6_validate_srh() now handles this case correctly.
In case2 and case3, the SRH shouldn’t be encoded in the Reduced way
otherwise we lose the first segment (i.e., the first hop).
The current implementation of the seg6_validate_srh() allow SRH of case2
and case3 to be encoded in the Reduced way. This leads a slab-out-of-bounds
problem.
This patch verifies SRH of case1, case2 and case3. Allowing case1 to be
reduced while preventing SRH of case2 and case3 from being reduced .
Reported-by: syzbot+e8c028b62439eac42073@syzkaller.appspotmail.com
Reported-by: YueHaibing <yuehaibing@huawei.com>
Fixes: 0cb7498f234e ("seg6: fix SRH processing to comply with RFC8754")
Change-Id: I2917c075b16c8887f80f74f380e2f26b12d1c19c
Signed-off-by: Ahmed Abdelsalam <ahabdels@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The Segment Routing Header (SRH) which defines the SRv6 dataplane is defined
in RFC8754.
RFC8754 (section 4.1) defines the SR source node behavior which encapsulates
packets into an outer IPv6 header and SRH. The SR source node encodes the
full list of Segments that defines the packet path in the SRH. Then, the
first segment from list of Segments is copied into the Destination address
of the outer IPv6 header and the packet is sent to the first hop in its path
towards the destination.
If the Segment list has only one segment, the SR source node can omit the SRH
as he only segment is added in the destination address.
RFC8754 (section 4.1.1) defines the Reduced SRH, when a source does not
require the entire SID list to be preserved in the SRH. A reduced SRH does
not contain the first segment of the related SR Policy (the first segment is
the one already in the DA of the IPv6 header), and the Last Entry field is
set to n-2, where n is the number of elements in the SR Policy.
RFC8754 (section 4.3.1.1) defines the SRH processing and the logic to
validate the SRH (S09, S10, S11) which works for both reduced and
non-reduced behaviors.
This patch updates seg6_validate_srh() to validate the SRH as per RFC8754.
Change-Id: I55505e57085e8ac01e7c58a5578749222ee01d8c
Signed-off-by: Ahmed Abdelsalam <ahabdels@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This code returns success if the "info_aux" allocation fails but it
should return -ENOMEM.
Fixes: 8c1b6e69dcc1 ("bpf: Compare BTF types of functions arguments with actual types")
Change-Id: Ibb33775fe1f6e7baaac2742b6ac428b8b1a95d84
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20200604085436.GA943001@mwanda
A recent commit added new variables only used if CONFIG_NETDEVICES is
set. A simple fix would be to only declare these variables if the same
condition is valid but Alexei suggested an even simpler solution:
since CONFIG_NETDEVICES doesn't change anything in .h I think the
best is to remove #ifdef CONFIG_NETDEVICES from net/core/filter.c
and rely on sock_bindtoindex() returning ENOPROTOOPT in the extreme
case of oddly configured kernels.
Fixes: 70c58997c1e8 ("bpf: Allow SO_BINDTODEVICE opt in bpf_setsockopt")
Suggested-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Change-Id: I5b714b9d8bb20a37fbad6e17da36f7917e594ae4
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20200603190347.2310320-1-matthieu.baerts@tessares.net
... rather than open-coding it, and badly, at that.
Acked-by: Alexei Starovoitov <ast@kernel.org>
Change-Id: Iae2b2dde82b3d2b129316fd20c82b19dd87c9331
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Add a bpf_csum_level() helper which BPF programs can use in combination
with bpf_skb_adjust_room() when they pass in BPF_F_ADJ_ROOM_NO_CSUM_RESET
flag to the latter to avoid falling back to CHECKSUM_NONE.
The bpf_csum_level() allows to adjust CHECKSUM_UNNECESSARY skb->csum_levels
via BPF_CSUM_LEVEL_{INC,DEC} which calls __skb_{incr,decr}_checksum_unnecessary()
on the skb. The helper also allows a BPF_CSUM_LEVEL_RESET which sets the skb's
csum to CHECKSUM_NONE as well as a BPF_CSUM_LEVEL_QUERY to just return the
current level. Without this helper, there is no way to otherwise adjust the
skb->csum_level. I did not add an extra dummy flags as there is plenty of free
bitspace in level argument itself iff ever needed in future.
Change-Id: I1ea8152f8c1bf173e493c19fe4ec7f4dbbf4448c
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Alan Maguire <alan.maguire@oracle.com>
Acked-by: Lorenz Bauer <lmb@cloudflare.com>
Link: https://lore.kernel.org/bpf/279ae3717cb3d03c0ffeb511493c93c450a01e1a.1591108731.git.daniel@iogearbox.net
Lorenz recently reported:
In our TC classifier cls_redirect [0], we use the following sequence of
helper calls to decapsulate a GUE (basically IP + UDP + custom header)
encapsulated packet:
bpf_skb_adjust_room(skb, -encap_len, BPF_ADJ_ROOM_MAC, BPF_F_ADJ_ROOM_FIXED_GSO)
bpf_redirect(skb->ifindex, BPF_F_INGRESS)
It seems like some checksums of the inner headers are not validated in
this case. For example, a TCP SYN packet with invalid TCP checksum is
still accepted by the network stack and elicits a SYN ACK. [...]
That is, we receive the following packet from the driver:
| ETH | IP | UDP | GUE | IP | TCP |
skb->ip_summed == CHECKSUM_UNNECESSARY
ip_summed is CHECKSUM_UNNECESSARY because our NICs do rx checksum offloading.
On this packet we run skb_adjust_room_mac(-encap_len), and get the following:
| ETH | IP | TCP |
skb->ip_summed == CHECKSUM_UNNECESSARY
Note that ip_summed is still CHECKSUM_UNNECESSARY. After bpf_redirect()'ing
into the ingress, we end up in tcp_v4_rcv(). There, skb_checksum_init() is
turned into a no-op due to CHECKSUM_UNNECESSARY.
The bpf_skb_adjust_room() helper is not aware of protocol specifics. Internally,
it handles the CHECKSUM_COMPLETE case via skb_postpull_rcsum(), but that does
not cover CHECKSUM_UNNECESSARY. In this case skb->csum_level of the original
skb prior to bpf_skb_adjust_room() call was 0, that is, covering UDP. Right now
there is no way to adjust the skb->csum_level. NICs that have checksum offload
disabled (CHECKSUM_NONE) or that support CHECKSUM_COMPLETE are not affected.
Use a safe default for CHECKSUM_UNNECESSARY by resetting to CHECKSUM_NONE and
add a flag to the helper called BPF_F_ADJ_ROOM_NO_CSUM_RESET that allows users
from opting out. Opting out is useful for the case where we don't remove/add
full protocol headers, or for the case where a user wants to adjust the csum
level manually e.g. through bpf_csum_level() helper that is added in subsequent
patch.
The bpf_skb_proto_{4_to_6,6_to_4}() for NAT64/46 translation from the BPF
bpf_skb_change_proto() helper uses bpf_skb_net_hdr_{push,pop}() pair internally
as well but doesn't change layers, only transitions between v4 to v6 and vice
versa, therefore no adoption is required there.
[0] https://lore.kernel.org/bpf/20200424185556.7358-1-lmb@cloudflare.com/
Fixes: 2be7e212d5 ("bpf: add bpf_skb_adjust_room helper")
Reported-by: Lorenz Bauer <lmb@cloudflare.com>
Reported-by: Alan Maguire <alan.maguire@oracle.com>
Change-Id: I205f68f5949ddfc3bd74e3a8b9c8ab64b9f7689c
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Alan Maguire <alan.maguire@oracle.com>
Link: https://lore.kernel.org/bpf/CACAyw9-uU_52esMd1JjuA80fRPHJv5vsSg8GnfW3t_qDU4aVKQ@mail.gmail.com/
Link: https://lore.kernel.org/bpf/11a90472e7cce83e76ddbfce81fdfce7bfc68808.1591108731.git.daniel@iogearbox.net
Failure to update a bpf_link because it has been auto-detached by a dying
cgroup currently results in EINVAL error, even though the arguments passed
to bpf() syscall are not wrong.
bpf_links attaching to netns in this case will return ENOLINK, which
carries the message that the link is no longer attached to anything.
Change cgroup bpf_links to do the same to keep the uAPI errors consistent.
Fixes: 0c991ebc8c69 ("bpf: Implement bpf_prog replacement for an active bpf_cgroup_link")
Suggested-by: Lorenz Bauer <lmb@cloudflare.com>
Change-Id: Ie72f54528e345f6f715965575a34cee3fd79d764
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200531082846.2117903-6-jakub@cloudflare.com
Extend bpf() syscall subcommands that operate on bpf_link, that is
LINK_CREATE, LINK_UPDATE, OBJ_GET_INFO, to accept attach types tied to
network namespaces (only flow dissector at the moment).
Link-based and prog-based attachment can be used interchangeably, but only
one can exist at a time. Attempts to attach a link when a prog is already
attached directly, and the other way around, will be met with -EEXIST.
Attempts to detach a program when link exists result in -EINVAL.
Attachment of multiple links of same attach type to one netns is not
supported with the intention to lift the restriction when a use-case
presents itself. Because of that link create returns -E2BIG when trying to
create another netns link, when one already exists.
Link-based attachments to netns don't keep a netns alive by holding a ref
to it. Instead links get auto-detached from netns when the latter is being
destroyed, using a pernet pre_exit callback.
When auto-detached, link lives in defunct state as long there are open FDs
for it. -ENOLINK is returned if a user tries to update a defunct link.
Because bpf_link to netns doesn't hold a ref to struct net, special care is
taken when releasing, updating, or filling link info. The netns might be
getting torn down when any of these link operations are in progress. That
is why auto-detach and update/release/fill_info are synchronized by the
same mutex. Also, link ops have to always check if auto-detach has not
happened yet and if netns is still alive (refcnt > 0).
Change-Id: I5d37351067b49c8fd029f236150c82dec7d29c4f
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200531082846.2117903-5-jakub@cloudflare.com
Move functions to manage BPF programs attached to netns that are not
specific to flow dissector to a dedicated module named
bpf/net_namespace.c.
The set of functions will grow with the addition of bpf_link support for
netns attached programs. This patch prepares ground by creating a place
for it.
This is a code move with no functional changes intended.
Change-Id: I3186a38b1ca22a16a518adc899668bfaaa455f76
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200531082846.2117903-4-jakub@cloudflare.com
The ICMP flow dissector currently parses only the Type and Code fields.
Some ICMP packets (echo, timestamp) have a 16 bit Identifier field which
is used to correlate packets.
Add such field in flow_dissector_key_icmp and replace skb_flow_get_be16()
with a more complex function which populate this field.
Change-Id: Ie0f0ceb22519e41ff2709a2211e94b5eb2105011
Signed-off-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Documents two piece of code which can't be understood at a glance.
Change-Id: Iab8a179a9feb1f85b0063cf26ed041d0d52eed1c
Signed-off-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
FLOW_DISSECTOR_KEY_ICMP is checked for every packet, not only ICMP ones.
Even if the test overhead is probably negligible, move the
ICMP dissector code under the big 'switch(ip_proto)' so it gets called
only for ICMP packets.
Change-Id: I10db391f01b0d045039f70083f0eb0cba131ad5c
Signed-off-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In order to:
(1) attach more than one BPF program type to netns, or
(2) support attaching BPF programs to netns with bpf_link, or
(3) support multi-prog attach points for netns
we will need to keep more state per netns than a single pointer like we
have now for BPF flow dissector program.
Prepare for the above by extracting netns_bpf that is part of struct net,
for storing all state related to BPF programs attached to netns.
Turn flow dissector callbacks for querying/attaching/detaching a program
into generic ones that operate on netns_bpf. Next patch will move the
generic callbacks into their own module.
This is similar to how it is organized for cgroup with cgroup_bpf.
Change-Id: Ie800e295efc026516ddba972baf74179c8377fd5
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Cc: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/bpf/20200531082846.2117903-3-jakub@cloudflare.com
Split out the part of attach callback that happens with attach/detach lock
acquired. This structures the prog attach callback in a way that opens up
doors for moving the locking out of flow_dissector and into generic
callbacks for attaching/detaching progs to netns in subsequent patches.
Change-Id: Id39eb2c51ac5a91709a5905e2603259e9a44a86f
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/bpf/20200531082846.2117903-2-jakub@cloudflare.com
It is currently not possible to detach the flow dissector program and
attach a new one in an atomic fashion, that is with a single syscall.
Attempts to do so will be met with EEXIST error.
This makes updates to flow dissector program hard. Traffic steering that
relies on BPF-powered flow dissection gets disrupted while old program has
been already detached but the new one has not been attached yet.
There is also a window of opportunity to attach a flow dissector to a
non-root namespace while updating the root flow dissector, thus blocking
the update.
Lastly, the behavior is inconsistent with cgroup BPF programs, which can be
replaced with a single bpf(BPF_PROG_ATTACH, ...) syscall without any
restrictions.
Allow attaching a new flow dissector program when another one is already
present with a restriction that it can't be the same program.
Change-Id: Ibc2f5b7c561cae3793087d39d5a782dbe1862df9
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20191011082946.22695-2-jakub@cloudflare.com
