Daniel Borkmann says:
====================
pull-request: bpf-next 2019-10-27
The following pull-request contains BPF updates for your *net-next* tree.
We've added 52 non-merge commits during the last 11 day(s) which contain
a total of 65 files changed, 2604 insertions(+), 1100 deletions(-).
The main changes are:
1) Revolutionize BPF tracing by using in-kernel BTF to type check BPF
assembly code. The work here teaches BPF verifier to recognize
kfree_skb()'s first argument as 'struct sk_buff *' in tracepoints
such that verifier allows direct use of bpf_skb_event_output() helper
used in tc BPF et al (w/o probing memory access) that dumps skb data
into perf ring buffer. Also add direct loads to probe memory in order
to speed up/replace bpf_probe_read() calls, from Alexei Starovoitov.
2) Big batch of changes to improve libbpf and BPF kselftests. Besides
others: generalization of libbpf's CO-RE relocation support to now
also include field existence relocations, revamp the BPF kselftest
Makefile to add test runner concept allowing to exercise various
ways to build BPF programs, and teach bpf_object__open() and friends
to automatically derive BPF program type/expected attach type from
section names to ease their use, from Andrii Nakryiko.
3) Fix deadlock in stackmap's build-id lookup on rq_lock(), from Song Liu.
4) Allow to read BTF as raw data from bpftool. Most notable use case
is to dump /sys/kernel/btf/vmlinux through this, from Jiri Olsa.
5) Use bpf_redirect_map() helper in libbpf's AF_XDP helper prog which
manages to improve "rx_drop" performance by ~4%., from Björn Töpel.
6) Fix to restore the flow dissector after reattach BPF test and also
fix error handling in bpf_helper_defs.h generation, from Jakub Sitnicki.
7) Improve verifier's BTF ctx access for use outside of raw_tp, from
Martin KaFai Lau.
8) Improve documentation for AF_XDP with new sections and to reflect
latest features, from Magnus Karlsson.
9) Add back 'version' section parsing to libbpf for old kernels, from
John Fastabend.
10) Fix strncat bounds error in libbpf's libbpf_prog_type_by_name(),
from KP Singh.
11) Turn on -mattr=+alu32 in LLVM by default for BPF kselftests in order
to improve insn coverage for built BPF progs, from Yonghong Song.
12) Misc minor cleanups and fixes, from various others.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
In commit 43e74c0267 ("bpf_xdp_redirect_map: Perform map lookup in
eBPF helper") the bpf_redirect_map() helper learned to do map lookup,
which means that the explicit lookup in the XDP program for AF_XDP is
not needed for post-5.3 kernels.
This commit adds the implicit map lookup with default action, which
improves the performance for the "rx_drop" [1] scenario with ~4%.
For pre-5.3 kernels, the bpf_redirect_map() returns XDP_ABORTED, and a
fallback path for backward compatibility is entered, where explicit
lookup is still performed. This means a slight regression for older
kernels (an additional bpf_redirect_map() call), but I consider that a
fair punishment for users not upgrading their kernels. ;-)
v1->v2: Backward compatibility (Toke) [2]
v2->v3: Avoid masking/zero-extension by using JMP32 [3]
[1] # xdpsock -i eth0 -z -r
[2] https://lore.kernel.org/bpf/87pnirb3dc.fsf@toke.dk/
[3] https://lore.kernel.org/bpf/87v9sip0i8.fsf@toke.dk/
Suggested-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/bpf/20191022072206.6318-1-bjorn.topel@gmail.com
For kernel logging macros, pr_warning() is completely removed and
replaced by pr_warn(). By using pr_warn() in tools/lib/bpf/ for
symmetry to kernel logging macros, we could eventually drop the
use of pr_warning() in the whole kernel tree.
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20191021055532.185245-1-wangkefeng.wang@huawei.com
'struct xdp_umem_reg' has 4 bytes of padding at the end that makes
valgrind complain about passing uninitialized stack memory to the
syscall:
Syscall param socketcall.setsockopt() points to uninitialised byte(s)
at 0x4E7AB7E: setsockopt (in /usr/lib64/libc-2.29.so)
by 0x4BDE035: xsk_umem__create@@LIBBPF_0.0.4 (xsk.c:172)
Uninitialised value was created by a stack allocation
at 0x4BDDEBA: xsk_umem__create@@LIBBPF_0.0.4 (xsk.c:140)
Padding bytes appeared after introducing of a new 'flags' field.
memset() is required to clear them.
Fixes: 10d30e3017 ("libbpf: add flags to umem config")
Signed-off-by: Ilya Maximets <i.maximets@ovn.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20191009164929.17242-1-i.maximets@ovn.org
bcc uses libbpf repo as a submodule. It brings in libbpf source
code and builds everything together to produce shared libraries.
With latest libbpf, I got the following errors:
/bin/ld: libbcc_bpf.so.0.10.0: version node not found for symbol xsk_umem__create@LIBBPF_0.0.2
/bin/ld: failed to set dynamic section sizes: Bad value
collect2: error: ld returned 1 exit status
make[2]: *** [src/cc/libbcc_bpf.so.0.10.0] Error 1
In xsk.c, we have
asm(".symver xsk_umem__create_v0_0_2, xsk_umem__create@LIBBPF_0.0.2");
asm(".symver xsk_umem__create_v0_0_4, xsk_umem__create@@LIBBPF_0.0.4");
The linker thinks the built is for LIBBPF but cannot find proper version
LIBBPF_0.0.2/4, so emit errors.
I also confirmed that using libbpf.a to produce a shared library also
has issues:
-bash-4.4$ cat t.c
extern void *xsk_umem__create;
void * test() { return xsk_umem__create; }
-bash-4.4$ gcc -c -fPIC t.c
-bash-4.4$ gcc -shared t.o libbpf.a -o t.so
/bin/ld: t.so: version node not found for symbol xsk_umem__create@LIBBPF_0.0.2
/bin/ld: failed to set dynamic section sizes: Bad value
collect2: error: ld returned 1 exit status
-bash-4.4$
Symbol versioning does happens in commonly used libraries, e.g., elfutils
and glibc. For static libraries, for a versioned symbol, the old definitions
will be ignored, and the symbol will be an alias to the latest definition.
For example, glibc sched_setaffinity is versioned.
-bash-4.4$ readelf -s /usr/lib64/libc.so.6 | grep sched_setaffinity
756: 000000000013d3d0 13 FUNC GLOBAL DEFAULT 13 sched_setaffinity@GLIBC_2.3.3
757: 00000000000e2e70 455 FUNC GLOBAL DEFAULT 13 sched_setaffinity@@GLIBC_2.3.4
1800: 0000000000000000 0 FILE LOCAL DEFAULT ABS sched_setaffinity.c
4228: 00000000000e2e70 455 FUNC LOCAL DEFAULT 13 __sched_setaffinity_new
4648: 000000000013d3d0 13 FUNC LOCAL DEFAULT 13 __sched_setaffinity_old
7338: 000000000013d3d0 13 FUNC GLOBAL DEFAULT 13 sched_setaffinity@GLIBC_2
7380: 00000000000e2e70 455 FUNC GLOBAL DEFAULT 13 sched_setaffinity@@GLIBC_
-bash-4.4$
For static library, the definition of sched_setaffinity aliases to the new definition.
-bash-4.4$ readelf -s /usr/lib64/libc.a | grep sched_setaffinity
File: /usr/lib64/libc.a(sched_setaffinity.o)
8: 0000000000000000 455 FUNC GLOBAL DEFAULT 1 __sched_setaffinity_new
12: 0000000000000000 455 FUNC WEAK DEFAULT 1 sched_setaffinity
For both elfutils and glibc, additional macros are used to control different handling
of symbol versioning w.r.t static and shared libraries.
For elfutils, the macro is SYMBOL_VERSIONING
(https://sourceware.org/git/?p=elfutils.git;a=blob;f=lib/eu-config.h).
For glibc, the macro is SHARED
(https://sourceware.org/git/?p=glibc.git;a=blob;f=include/shlib-compat.h;hb=refs/heads/master)
This patch used SHARED as the macro name. After this patch, the libbpf.a has
-bash-4.4$ readelf -s libbpf.a | grep xsk_umem__create
372: 0000000000017145 1190 FUNC GLOBAL DEFAULT 1 xsk_umem__create_v0_0_4
405: 0000000000017145 1190 FUNC GLOBAL DEFAULT 1 xsk_umem__create
499: 00000000000175eb 103 FUNC GLOBAL DEFAULT 1 xsk_umem__create_v0_0_2
-bash-4.4$
No versioned symbols for xsk_umem__create.
The libbpf.a can be used to build a shared library succesfully.
-bash-4.4$ cat t.c
extern void *xsk_umem__create;
void * test() { return xsk_umem__create; }
-bash-4.4$ gcc -c -fPIC t.c
-bash-4.4$ gcc -shared t.o libbpf.a -o t.so
-bash-4.4$
Fixes: 10d30e3017 ("libbpf: add flags to umem config")
Cc: Kevin Laatz <kevin.laatz@intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andrii Nakryiko <andriin@fb.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
The xsk_socket__create() function fails and returns an error if it cannot
get the XDP_OPTIONS through getsockopt(). However, support for XDP_OPTIONS
was not added until kernel 5.3, so this means that creating XSK sockets
always fails on older kernels.
Since the option is just used to set the zero-copy flag in the xsk struct,
and that flag is not really used for anything yet, just remove the
getsockopt() call until a proper use for it is introduced.
Suggested-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
This patch adds a 'flags' field to the umem_config and umem_reg structs.
This will allow for more options to be added for configuring umems.
The first use for the flags field is to add a flag for unaligned chunks
mode. These flags can either be user-provided or filled with a default.
Since we change the size of the xsk_umem_config struct, we need to version
the ABI. This patch includes the ABI versioning for xsk_umem__create. The
Makefile was also updated to handle multiple function versions in
check-abi.
Signed-off-by: Kevin Laatz <kevin.laatz@intel.com>
Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Drop __NR_mmap2 fork in flavor of LFS, that is _FILE_OFFSET_BITS=64
(glibc & bionic) / LARGEFILE64_SOURCE (for musl) decision. It allows
mmap() to use 64bit offset that is passed to mmap2 syscall. As result
pgoff is not truncated and no need to use direct access to mmap2 for
32 bits systems.
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
This commit adds support for the new need_wakeup flag in AF_XDP. The
xsk_socket__create function is updated to handle this and a new
function is introduced called xsk_ring_prod__needs_wakeup(). This
function can be used by the application to check if Rx and/or Tx
processing needs to be explicitly woken up.
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Despite a proper NULL-termination after strncpy(..., ..., IFNAMSIZ - 1),
GCC8 still complains about *expected* string truncation:
xsk.c:330:2: error: 'strncpy' output may be truncated copying 15 bytes
from a string of length 15 [-Werror=stringop-truncation]
strncpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ - 1);
This patch gets rid of the issue altogether by using memcpy instead.
There is no performance regression, as strncpy will still copy and fill
all of the bytes anyway.
v1->v2:
- rebase against bpf tree.
Cc: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
'channels.max_combined' initialized only on ioctl success and
errno is only valid on ioctl failure.
The code doesn't produce any runtime issues, but makes memory
sanitizers angry:
Conditional jump or move depends on uninitialised value(s)
at 0x55C056F: xsk_get_max_queues (xsk.c:336)
by 0x55C05B2: xsk_create_bpf_maps (xsk.c:354)
by 0x55C089F: xsk_setup_xdp_prog (xsk.c:447)
by 0x55C0E57: xsk_socket__create (xsk.c:601)
Uninitialised value was created by a stack allocation
at 0x55C04CD: xsk_get_max_queues (xsk.c:318)
Additionally fixed warning on uninitialized bytes in ioctl arguments:
Syscall param ioctl(SIOCETHTOOL) points to uninitialised byte(s)
at 0x648D45B: ioctl (in /usr/lib64/libc-2.28.so)
by 0x55C0546: xsk_get_max_queues (xsk.c:330)
by 0x55C05B2: xsk_create_bpf_maps (xsk.c:354)
by 0x55C089F: xsk_setup_xdp_prog (xsk.c:447)
by 0x55C0E57: xsk_socket__create (xsk.c:601)
Address 0x1ffefff378 is on thread 1's stack
in frame #1, created by xsk_get_max_queues (xsk.c:318)
Uninitialised value was created by a stack allocation
at 0x55C04CD: xsk_get_max_queues (xsk.c:318)
CC: Magnus Karlsson <magnus.karlsson@intel.com>
Fixes: 1cad078842 ("libbpf: add support for using AF_XDP sockets")
Signed-off-by: Ilya Maximets <i.maximets@samsung.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Similar issue was fixed in cdfc7f888c ("libbpf: fix GCC8 warning for
strncpy") already. This one was missed. Fixing now.
Cc: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
GCC8 started emitting warning about using strncpy with number of bytes
exactly equal destination size, which is generally unsafe, as can lead
to non-zero terminated string being copied. Use IFNAMSIZ - 1 as number
of bytes to ensure name is always zero-terminated.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Cc: Magnus Karlsson <magnus.karlsson@intel.com>
Acked-by: Yonghong Song <yhs@fb.com>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Query XDP_OPTIONS in libbpf to determine if the zero-copy mode is active
or not.
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Use the recent change to XSKMAP bpf_map_lookup_elem() to test if
there is a xsk present in the map instead of duplicating the work
with qidconf.
Fix things so callers using XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD
bypass any internal bpf maps, so xsk_socket__{create|delete} works
properly.
Clean up error handling path.
Signed-off-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Acked-by: Song Liu <songliubraving@fb.com>
Tested-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
libbpf_util.h header was recently exposed as public as a dependency of
xsk.h. In addition to memory barriers, it contained logging helpers,
which are not supposed to be exposed. This patch moves those into
libbpf_internal.h, which is kept as an internal header.
Cc: Stanislav Fomichev <sdf@google.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Fixes: 7080da8909 ("libbpf: add libbpf_util.h to header install.")
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
The patches with fixes tags added a cast-to-void in the places when
the return value of a function was ignored.
This is not common practice in the kernel, and is therefore removed in
this patch.
Reported-by: Daniel Borkmann <daniel@iogearbox.net>
Fixes: 5750902a6e ("libbpf: proper XSKMAP cleanup")
Fixes: 0e6741f092 ("libbpf: fix invalid munmap call")
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
The bpf_map_update_elem() function, when used on an XSKMAP, will fail
if not a valid AF_XDP socket is passed as value. Therefore, this is
function cannot be used to clear the XSKMAP. Instead, the
bpf_map_delete_elem() function should be used for that.
This patch also simplifies the code by breaking up
xsk_update_bpf_maps() into three smaller functions.
Reported-by: William Tu <u9012063@gmail.com>
Fixes: 1cad078842 ("libbpf: add support for using AF_XDP sockets")
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Tested-by: William Tu <u9012063@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
When unmapping the AF_XDP memory regions used for the rings, an
invalid address was passed to the munmap() calls. Instead of passing
the beginning of the memory region, the descriptor region was passed
to munmap.
When the userspace application tried to tear down an AF_XDP socket,
the operation failed and the application would still have a reference
to socket it wished to get rid of.
Reported-by: William Tu <u9012063@gmail.com>
Fixes: 1cad078842 ("libbpf: add support for using AF_XDP sockets")
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Tested-by: William Tu <u9012063@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
In commit da11b41758 ("libbpf: teach libbpf about log_level bit 2"),
the BPF_LOG_BUF_SIZE was increased to 16M. The XDP socket part of
libbpf allocated the log_buf on the stack, but for the new 16M buffer
size this is not going to work. Change the code so it uses a 16K buffer
instead.
Fixes: da11b41758 ("libbpf: teach libbpf about log_level bit 2")
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
In xsk_socket__create(), the libbpf_flags field was not checked for
setting currently unused/unknown flags. This patch fixes that by
returning -EINVAL if the user has set any flag that is not in use at
this point in time.
Fixes: 1cad078842 ("libbpf: add support for using AF_XDP sockets")
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Reviewed-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
This commit adds AF_XDP support to libbpf. The main reason for this is
to facilitate writing applications that use AF_XDP by offering
higher-level APIs that hide many of the details of the AF_XDP
uapi. This is in the same vein as libbpf facilitates XDP adoption by
offering easy-to-use higher level interfaces of XDP
functionality. Hopefully this will facilitate adoption of AF_XDP, make
applications using it simpler and smaller, and finally also make it
possible for applications to benefit from optimizations in the AF_XDP
user space access code. Previously, people just copied and pasted the
code from the sample application into their application, which is not
desirable.
The interface is composed of two parts:
* Low-level access interface to the four rings and the packet
* High-level control plane interface for creating and setting
up umems and af_xdp sockets as well as a simple XDP program.
Tested-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
