aboutsummaryrefslogtreecommitdiff
path: root/tools/testing/selftests/bpf
AgeCommit message (Collapse)AuthorFilesLines
2020-06-24selftests/bpf: Add tcp/udp iterator programs to selftestsYonghong Song1-0/+68
Added tcp{4,6} and udp{4,6} bpf programs into test_progs selftest so that they at least can load successfully. $ ./test_progs -n 3 ... #3/7 tcp4:OK #3/8 tcp6:OK #3/9 udp4:OK #3/10 udp6:OK ... #3 bpf_iter:OK Summary: 1/16 PASSED, 0 SKIPPED, 0 FAILED Signed-off-by: Yonghong Song <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Acked-by: Andrii Nakryiko <[email protected]> Acked-by: Martin KaFai Lau <[email protected]> Link: https://lore.kernel.org/bpf/[email protected]
2020-06-24selftests/bpf: Implement sample udp/udp6 bpf_iter programsYonghong Song3-0/+166
On my VM, I got identical results between /proc/net/udp[6] and the udp{4,6} bpf iterator. For udp6: $ cat /sys/fs/bpf/p1 sl local_address remote_address st tx_queue rx_queue tr tm->when retrnsmt uid timeout inode ref pointer drops 1405: 000080FE00000000FF7CC4D0D9EFE4FE:0222 00000000000000000000000000000000:0000 07 00000000:00000000 00:00000000 00000000 193 0 19183 2 0000000029eab111 0 $ cat /proc/net/udp6 sl local_address remote_address st tx_queue rx_queue tr tm->when retrnsmt uid timeout inode ref pointer drops 1405: 000080FE00000000FF7CC4D0D9EFE4FE:0222 00000000000000000000000000000000:0000 07 00000000:00000000 00:00000000 00000000 193 0 19183 2 0000000029eab111 0 For udp4: $ cat /sys/fs/bpf/p4 sl local_address rem_address st tx_queue rx_queue tr tm->when retrnsmt uid timeout inode ref pointer drops 2007: 00000000:1F90 00000000:0000 07 00000000:00000000 00:00000000 00000000 0 0 72540 2 000000004ede477a 0 $ cat /proc/net/udp sl local_address rem_address st tx_queue rx_queue tr tm->when retrnsmt uid timeout inode ref pointer drops 2007: 00000000:1F90 00000000:0000 07 00000000:00000000 00:00000000 00000000 0 0 72540 2 000000004ede477a 0 Signed-off-by: Yonghong Song <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Acked-by: Andrii Nakryiko <[email protected]> Acked-by: Martin KaFai Lau <[email protected]> Link: https://lore.kernel.org/bpf/[email protected]
2020-06-24selftests/bpf: Implement sample tcp/tcp6 bpf_iter programsYonghong Song3-0/+499
In my VM, I got identical result compared to /proc/net/{tcp,tcp6}. For tcp6: $ cat /proc/net/tcp6 sl local_address remote_address st tx_queue rx_queue tr tm->when retrnsmt uid timeout inode 0: 00000000000000000000000000000000:0016 00000000000000000000000000000000:0000 0A 00000000:00000000 00:00000001 00000000 0 0 17955 1 000000003eb3102e 100 0 0 10 0 $ cat /sys/fs/bpf/p1 sl local_address remote_address st tx_queue rx_queue tr tm->when retrnsmt uid timeout inode 0: 00000000000000000000000000000000:0016 00000000000000000000000000000000:0000 0A 00000000:00000000 00:00000000 00000000 0 0 17955 1 000000003eb3102e 100 0 0 10 0 For tcp: $ cat /proc/net/tcp sl local_address rem_address st tx_queue rx_queue tr tm->when retrnsmt uid timeout inode 0: 00000000:0016 00000000:0000 0A 00000000:00000000 00:00000000 00000000 0 0 2666 1 000000007152e43f 100 0 0 10 0 $ cat /sys/fs/bpf/p2 sl local_address remote_address st tx_queue rx_queue tr tm->when retrnsmt uid timeout inode 1: 00000000:0016 00000000:0000 0A 00000000:00000000 00:00000000 00000000 0 0 2666 1 000000007152e43f 100 0 0 10 0 Signed-off-by: Yonghong Song <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Acked-by: Andrii Nakryiko <[email protected]> Acked-by: Martin KaFai Lau <[email protected]> Link: https://lore.kernel.org/bpf/[email protected]
2020-06-24selftests/bpf: Add more common macros to bpf_tracing_net.hYonghong Song1-0/+35
These newly added macros will be used in subsequent bpf iterator tcp{4,6} and udp{4,6} programs. Signed-off-by: Yonghong Song <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Acked-by: Andrii Nakryiko <[email protected]> Acked-by: Martin KaFai Lau <[email protected]> Link: https://lore.kernel.org/bpf/[email protected]
2020-06-24selftests/bpf: Refactor some net macros to bpf_tracing_net.hYonghong Song3-9/+18
Refactor bpf_iter_ipv6_route.c and bpf_iter_netlink.c so net macros, originally from various include/linux header files, are moved to a new header file bpf_tracing_net.h. The goal is to improve reuse so networking tracing programs do not need to copy these macros every time they use them. Signed-off-by: Yonghong Song <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Acked-by: Andrii Nakryiko <[email protected]> Acked-by: Martin KaFai Lau <[email protected]> Link: https://lore.kernel.org/bpf/[email protected]
2020-06-24selftests/bpf: Move newer bpf_iter_* type redefining to a new header fileYonghong Song9-136/+57
Commit b9f4c01f3e0b ("selftest/bpf: Make bpf_iter selftest compilable against old vmlinux.h") and Commit dda18a5c0b75 ("selftests/bpf: Convert bpf_iter_test_kern{3, 4}.c to define own bpf_iter_meta") redefined newly introduced types in bpf programs so the bpf program can still compile properly with old kernels although loading may fail. Since this patch set introduced new types and the same workaround is needed, so let us move the workaround to a separate header file so they do not clutter bpf programs. Signed-off-by: Yonghong Song <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Acked-by: Andrii Nakryiko <[email protected]> Acked-by: Martin KaFai Lau <[email protected]> Link: https://lore.kernel.org/bpf/[email protected]
2020-06-24bpf: Add SO_KEEPALIVE and related options to bpf_setsockoptDmitry Yakunin1-0/+27
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 <[email protected]>) v4: - update kernel-doc in tools too (Alexei Starovoitov) - add test to selftests (Alexei Starovoitov) Signed-off-by: Dmitry Yakunin <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Acked-by: Martin KaFai Lau <[email protected]> Link: https://lore.kernel.org/bpf/[email protected]
2020-06-24selftests/bpf: Workaround for get_stack_rawtp test.Alexei Starovoitov1-1/+2
./test_progs-no_alu32 -t get_stack_raw_tp fails due to: 52: (85) call bpf_get_stack#67 53: (bf) r8 = r0 54: (bf) r1 = r8 55: (67) r1 <<= 32 56: (c7) r1 s>>= 32 ; if (usize < 0) 57: (c5) if r1 s< 0x0 goto pc+26 R0=inv(id=0,smax_value=800) R1_w=inv(id=0,umax_value=800,var_off=(0x0; 0x3ff)) R6=ctx(id=0,off=0,imm=0) R7=map_value(id=0,off=0,ks=4,vs=1600,imm=0) R8_w=inv(id=0,smax_value=800) R9=inv800 ; ksize = bpf_get_stack(ctx, raw_data + usize, max_len - usize, 0); 58: (1f) r9 -= r8 ; ksize = bpf_get_stack(ctx, raw_data + usize, max_len - usize, 0); 59: (bf) r2 = r7 60: (0f) r2 += r1 regs=1 stack=0 before 52: (85) call bpf_get_stack#67 ; ksize = bpf_get_stack(ctx, raw_data + usize, max_len - usize, 0); 61: (bf) r1 = r6 62: (bf) r3 = r9 63: (b7) r4 = 0 64: (85) call bpf_get_stack#67 R0=inv(id=0,smax_value=800) R1_w=ctx(id=0,off=0,imm=0) R2_w=map_value(id=0,off=0,ks=4,vs=1600,umax_value=800,var_off=(0x0; 0x3ff),s32_max_value=1023,u32_max_value=1023) R3_w=inv(id=0,umax_value=9223372036854776608) R3 unbounded memory access, use 'var &= const' or 'if (var < const)' In the C code: usize = bpf_get_stack(ctx, raw_data, max_len, BPF_F_USER_STACK); if (usize < 0) return 0; ksize = bpf_get_stack(ctx, raw_data + usize, max_len - usize, 0); if (ksize < 0) return 0; We used to have problem with pointer arith in R2. Now it's a problem with two integers in R3. 'if (usize < 0)' is comparing R1 and makes it [0,800], but R8 stays [-inf,800]. Both registers represent the same 'usize' variable. Then R9 -= R8 is doing 800 - [-inf, 800] so the result of "max_len - usize" looks unbounded to the verifier while it's obvious in C code that "max_len - usize" should be [0, 800]. To workaround the problem convert ksize and usize variables from int to long. Signed-off-by: Alexei Starovoitov <[email protected]>
2020-06-23libbpf: Fix CO-RE relocs against .text sectionAndrii Nakryiko1-1/+1
bpf_object__find_program_by_title(), used by CO-RE relocation code, doesn't return .text "BPF program", if it is a function storage for sub-programs. Because of that, any CO-RE relocation in helper non-inlined functions will fail. Fix this by searching for .text-corresponding BPF program manually. Adjust one of bpf_iter selftest to exhibit this pattern. Fixes: ddc7c3042614 ("libbpf: implement BPF CO-RE offset relocation algorithm") Reported-by: Yonghong Song <[email protected]> Signed-off-by: Andrii Nakryiko <[email protected]> Signed-off-by: Yonghong Song <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Acked-by: Yonghong Song <[email protected]> Link: https://lore.kernel.org/bpf/[email protected]
2020-06-24selftests/bpf: Add variable-length data concat pattern less than testJohn Fastabend2-4/+78
Extend original variable-length tests with a case to catch a common existing pattern of testing for < 0 for errors. Note because verifier also tracks upper bounds and we know it can not be greater than MAX_LEN here we can skip upper bound check. In ALU64 enabled compilation converting from long->int return types in probe helpers results in extra instruction pattern, <<= 32, s >>= 32. The trade-off is the non-ALU64 case works. If you really care about every extra insn (XDP case?) then you probably should be using original int type. In addition adding a sext insn to bpf might help the verifier in the general case to avoid these types of tricks. Signed-off-by: John Fastabend <[email protected]> Signed-off-by: Andrii Nakryiko <[email protected]> Signed-off-by: Daniel Borkmann <[email protected]> Link: https://lore.kernel.org/bpf/[email protected]
2020-06-24selftests/bpf: Add variable-length data concatenation pattern testAndrii Nakryiko2-0/+152
Add selftest that validates variable-length data reading and concatentation with one big shared data array. This is a common pattern in production use for monitoring and tracing applications, that potentially can read a lot of data, but overall read much less. Such pattern allows to determine precisely what amount of data needs to be sent over perfbuf/ringbuf and maximize efficiency. Signed-off-by: Andrii Nakryiko <[email protected]> Signed-off-by: Daniel Borkmann <[email protected]> Link: https://lore.kernel.org/bpf/[email protected]
2020-06-22selftests/bpf: Add __ksym extern selftestAndrii Nakryiko2-0/+103
Validate libbpf is able to handle weak and strong kernel symbol externs in BPF code correctly. Signed-off-by: Andrii Nakryiko <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Reviewed-by: Hao Luo <[email protected]> Link: https://lore.kernel.org/bpf/[email protected]
2020-06-22selftests/bpf: Test access to bpf map pointerAndrey Ignatov3-0/+780
Add selftests to test access to map pointers from bpf program for all map types except struct_ops (that one would need additional work). verifier test focuses mostly on scenarios that must be rejected. prog_tests test focuses on accessing multiple fields both scalar and a nested struct from bpf program and verifies that those fields have expected values. Signed-off-by: Andrey Ignatov <[email protected]> Signed-off-by: Daniel Borkmann <[email protected]> Acked-by: John Fastabend <[email protected]> Acked-by: Martin KaFai Lau <[email protected]> Link: https://lore.kernel.org/bpf/139a6a17f8016491e39347849b951525335c6eb4.1592600985.git.rdna@fb.com
2020-06-22bpf: Support access to bpf map fieldsAndrey Ignatov1-1/+1
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. Signed-off-by: Andrey Ignatov <[email protected]> Signed-off-by: Daniel Borkmann <[email protected]> Acked-by: John Fastabend <[email protected]> Acked-by: Martin KaFai Lau <[email protected]> Link: https://lore.kernel.org/bpf/6479686a0cd1e9067993df57b4c3eef0e276fec9.1592600985.git.rdna@fb.com
2020-06-19tools/bpf: Add verifier tests for 32bit pointer/scalar arithmeticYonghong Song1-0/+38
Added two test_verifier subtests for 32bit pointer/scalar arithmetic with BPF_SUB operator. They are passing verifier now. Signed-off-by: Yonghong Song <[email protected]> Signed-off-by: Daniel Borkmann <[email protected]> Link: https://lore.kernel.org/bpf/[email protected]
2020-06-17selftests/bpf: Make sure optvals > PAGE_SIZE are bypassedStanislav Fomichev2-9/+91
We are relying on the fact, that we can pass > sizeof(int) optvals to the SOL_IP+IP_FREEBIND option (the kernel will take first 4 bytes). In the BPF program we check that we can only touch PAGE_SIZE bytes, but the real optlen is PAGE_SIZE * 2. In both cases, we override it to some predefined value and trim the optlen. Also, let's modify exiting IP_TOS usecase to test optlen=0 case where BPF program just bypasses the data as is. Signed-off-by: Stanislav Fomichev <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Link: https://lore.kernel.org/bpf/[email protected]
2020-06-12libbpf: Support pre-initializing .bss global variablesAndrii Nakryiko2-9/+55
Remove invalid assumption in libbpf that .bss map doesn't have to be updated in kernel. With addition of skeleton and memory-mapped initialization image, .bss doesn't have to be all zeroes when BPF map is created, because user-code might have initialized those variables from user-space. Fixes: eba9c5f498a1 ("libbpf: Refactor global data map initialization") Signed-off-by: Andrii Nakryiko <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Link: https://lore.kernel.org/bpf/[email protected]
2020-06-11selftests/bpf: Add cgroup_skb/egress test for load_bytes_relativeYiFei Zhu2-0/+119
When cgroup_skb/egress triggers the MAC header is not set. Added a test that asserts reading MAC header is a -EFAULT but NET header succeeds. The test result from within the eBPF program is stored in an 1-element array map that the userspace then reads and asserts on. Another assertion is added that reading from a large offset, past the end of packet, returns -EFAULT. Signed-off-by: YiFei Zhu <[email protected]> Signed-off-by: Daniel Borkmann <[email protected]> Reviewed-by: Stanislav Fomichev <[email protected]> Link: https://lore.kernel.org/bpf/9028ccbea4385a620e69c0a104f469ffd655c01e.1591812755.git.zhuyifei@google.com
2020-06-09bpf: Selftests and tools use struct bpf_devmap_val from uapiJesper Dangaard Brouer3-11/+2
Sync tools uapi bpf.h header file and update selftests that use struct bpf_devmap_val. Signed-off-by: Jesper Dangaard Brouer <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Link: https://lore.kernel.org/bpf/159170951195.2102545.1833108712124273987.stgit@firesoul
2020-06-09bpf: cgroup: Allow multi-attach program to replace itselfLorenz Bauer1-0/+7
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 d7bf2c10af05 ("bpf: allocate cgroup storage entries on attaching bpf programs") as well as commit 324bda9e6c5a ("bpf: multi program support for cgroup+bpf") Fixes: af6eea57437a ("bpf: Implement bpf_link-based cgroup BPF program attachment") Signed-off-by: Lorenz Bauer <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Link: https://lore.kernel.org/bpf/[email protected]
2020-06-08selftests/bpf: Fix ringbuf selftest sample counting undeterminismAndrii Nakryiko1-7/+35
Fix test race, in which background poll can get either 5 or 6 samples, depending on timing of notification. Prevent this by open-coding sample triggering and forcing notification for the very last sample only. Also switch to using atomic increments and exchanges for more obviously reliable counting and checking. Additionally, check expected processed sample counters for single-threaded use cases as well. Fixes: 9a5f25ad30e5 ("selftests/bpf: Fix sample_cnt shared between two threads") Signed-off-by: Andrii Nakryiko <[email protected]> Signed-off-by: Daniel Borkmann <[email protected]> Link: https://lore.kernel.org/bpf/[email protected]
2020-06-02selftests/bpf: Add a default $(CXX) valueIlya Leoshkevich1-0/+2
When using make kselftest TARGETS=bpf, tools/bpf is built with MAKEFLAGS=rR, which causes $(CXX) to be undefined, which in turn causes the build to fail with CXX test_cpp /bin/sh: 2: g: not found Fix by adding a default $(CXX) value, like tools/build/feature/Makefile already does. Signed-off-by: Ilya Leoshkevich <[email protected]> Signed-off-by: Daniel Borkmann <[email protected]> Link: https://lore.kernel.org/bpf/[email protected]
2020-06-02bpf, selftests: Use bpf_probe_read_kernelIlya Leoshkevich4-48/+48
Since commit 0ebeea8ca8a4 ("bpf: Restrict bpf_probe_read{, str}() only to archs where they work") 44 verifier tests fail on s390 due to not having bpf_probe_read anymore. Fix by using bpf_probe_read_kernel. Signed-off-by: Ilya Leoshkevich <[email protected]> Signed-off-by: Daniel Borkmann <[email protected]> Link: https://lore.kernel.org/bpf/[email protected]
2020-06-02selftests/bpf: Fix verifier testAlexei Starovoitov1-1/+1
Adjust verifier test due to addition of new field. Fixes: c3c16f2ea6d2 ("bpf: Add rx_queue_mapping to bpf_sock") Signed-off-by: Alexei Starovoitov <[email protected]>
2020-06-02selftests/bpf: Fix sample_cnt shared between two threadsAndrii Nakryiko1-1/+1
Make sample_cnt volatile to fix possible selftests failure due to compiler optimization preventing latest sample_cnt value to be visible to main thread. sample_cnt is incremented in background thread, which is then joined into main thread. So in terms of visibility sample_cnt update is ok. But because it's not volatile, compiler might make optimizations that would prevent main thread to see latest updated value. Fix this by marking global variable volatile. Fixes: cb1c9ddd5525 ("selftests/bpf: Add BPF ringbuf selftests") Signed-off-by: Andrii Nakryiko <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Acked-by: Song Liu <[email protected]> Link: https://lore.kernel.org/bpf/[email protected]
2020-06-02bpf, selftests: Adapt cls_redirect to call csum_level helperDaniel Borkmann1-3/+6
Adapt bpf_skb_adjust_room() to pass in BPF_F_ADJ_ROOM_NO_CSUM_RESET flag and use the new bpf_csum_level() helper to inc/dec the checksum level by one after the encap/decap. Signed-off-by: Daniel Borkmann <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Reviewed-by: Lorenz Bauer <[email protected]> Link: https://lore.kernel.org/bpf/e7458f10e3f3d795307cbc5ad870112671d9c6f7.1591108731.git.daniel@iogearbox.net
2020-06-01selftests/bpf: Extend test_flow_dissector to cover link creationJakub Sitnicki1-33/+82
Extend the existing flow_dissector test case to run tests once using direct prog attachments, and then for the second time using indirect attachment via link. The intention is to exercises the newly added high-level API for attaching programs to network namespace with links (bpf_program__attach_netns). Signed-off-by: Jakub Sitnicki <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Link: https://lore.kernel.org/bpf/[email protected]
2020-06-01selftests/bpf: Convert test_flow_dissector to use BPF skeletonJakub Sitnicki2-15/+55
Switch flow dissector test setup from custom BPF object loader to BPF skeleton to save boilerplate and prepare for testing higher-level API for attaching flow dissector with bpf_link. To avoid depending on program order in the BPF object when populating the flow dissector PROG_ARRAY map, change the program section names to contain the program index into the map. This follows the example set by tailcall tests. Signed-off-by: Jakub Sitnicki <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Link: https://lore.kernel.org/bpf/[email protected]
2020-06-01selftests/bpf, flow_dissector: Close TAP device FD after the testJakub Sitnicki1-0/+1
test_flow_dissector leaves a TAP device after it's finished, potentially interfering with other tests that will run after it. Fix it by closing the TAP descriptor on cleanup. Fixes: 0905beec9f52 ("selftests/bpf: run flow dissector tests in skb-less mode") Signed-off-by: Jakub Sitnicki <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Link: https://lore.kernel.org/bpf/[email protected]
2020-06-01selftests/bpf: Add tests for attaching bpf_link to netnsJakub Sitnicki1-37/+551
Extend the existing test case for flow dissector attaching to cover: - link creation, - link updates, - link info querying, - mixing links with direct prog attachment. Signed-off-by: Jakub Sitnicki <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Link: https://lore.kernel.org/bpf/[email protected]
2020-06-01selftests/bpf: Add test for SO_BINDTODEVICE opt of bpf_setsockoptFerenc Fejes1-0/+33
This test intended to verify if SO_BINDTODEVICE option works in bpf_setsockopt. Because we already in the SOL_SOCKET level in this connect bpf prog its safe to verify the sanity in the beginning of the connect_v4_prog by calling the bind_to_device test helper. The testing environment already created by the test_sock_addr.sh script so this test assume that two netdevices already existing in the system: veth pair with names test_sock_addr1 and test_sock_addr2. The test will try to bind the socket to those devices first. Then the test assume there are no netdevice with "nonexistent_dev" name so the bpf_setsockopt will give use ENODEV error. At the end the test remove the device binding from the socket by binding it to an empty name. Signed-off-by: Ferenc Fejes <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Link: https://lore.kernel.org/bpf/3f055b8e45c65639c5c73d0b4b6c589e60b86f15.1590871065.git.fejes@inf.elte.hu
2020-06-01bpf, selftests: Add test for ktls with skb bpf ingress policyJohn Fastabend2-22/+187
This adds a test for bpf ingress policy. To ensure data writes happen as expected with extra TLS headers we run these tests with data verification enabled by default. This will test receive packets have "PASS" stamped into the front of the payload. Signed-off-by: John Fastabend <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Link: https://lore.kernel.org/bpf/159079363965.5745.3390806911628980210.stgit@john-Precision-5820-Tower Signed-off-by: Alexei Starovoitov <[email protected]>
2020-06-01selftest: Add tests for XDP programs in devmap entriesDavid Ahern3-0/+163
Add tests to verify ability to add an XDP program to a entry in a DEVMAP. Add negative tests to show DEVMAP programs can not be attached to devices as a normal XDP program, and accesses to egress_ifindex require BPF_XDP_DEVMAP attach type. Signed-off-by: David Ahern <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Acked-by: Toke Høiland-Jørgensen <[email protected]> Link: https://lore.kernel.org/bpf/[email protected] Signed-off-by: Alexei Starovoitov <[email protected]>
2020-06-01bpf: Add BPF ringbuf and perf buffer benchmarksAndrii Nakryiko6-1/+754
Extend bench framework with ability to have benchmark-provided child argument parser for custom benchmark-specific parameters. This makes bench generic code modular and independent from any specific benchmark. Also implement a set of benchmarks for new BPF ring buffer and existing perf buffer. 4 benchmarks were implemented: 2 variations for each of BPF ringbuf and perfbuf:, - rb-libbpf utilizes stock libbpf ring_buffer manager for reading data; - rb-custom implements custom ring buffer setup and reading code, to eliminate overheads inherent in generic libbpf code due to callback functions and the need to update consumer position after each consumed record, instead of batching updates (due to pessimistic assumption that user callback might take long time and thus could unnecessarily hold ring buffer space for too long); - pb-libbpf uses stock libbpf perf_buffer code with all the default settings, though uses higher-performance raw event callback to minimize unnecessary overhead; - pb-custom implements its own custom consumer code to minimize any possible overhead of generic libbpf implementation and indirect function calls. All of the test support default, no data notification skipped, mode, as well as sampled mode (with --rb-sampled flag), which allows to trigger epoll notification less frequently and reduce overhead. As will be shown, this mode is especially critical for perf buffer, which suffers from high overhead of wakeups in kernel. Otherwise, all benchamrks implement similar way to generate a batch of records by using fentry/sys_getpgid BPF program, which pushes a bunch of records in a tight loop and records number of successful and dropped samples. Each record is a small 8-byte integer, to minimize the effect of memory copying with bpf_perf_event_output() and bpf_ringbuf_output(). Benchmarks that have only one producer implement optional back-to-back mode, in which record production and consumption is alternating on the same CPU. This is the highest-throughput happy case, showing ultimate performance achievable with either BPF ringbuf or perfbuf. All the below scenarios are implemented in a script in benchs/run_bench_ringbufs.sh. Tests were performed on 28-core/56-thread Intel Xeon CPU E5-2680 v4 @ 2.40GHz CPU. Single-producer, parallel producer ================================== rb-libbpf 12.054 ± 0.320M/s (drops 0.000 ± 0.000M/s) rb-custom 8.158 ± 0.118M/s (drops 0.001 ± 0.003M/s) pb-libbpf 0.931 ± 0.007M/s (drops 0.000 ± 0.000M/s) pb-custom 0.965 ± 0.003M/s (drops 0.000 ± 0.000M/s) Single-producer, parallel producer, sampled notification ======================================================== rb-libbpf 11.563 ± 0.067M/s (drops 0.000 ± 0.000M/s) rb-custom 15.895 ± 0.076M/s (drops 0.000 ± 0.000M/s) pb-libbpf 9.889 ± 0.032M/s (drops 0.000 ± 0.000M/s) pb-custom 9.866 ± 0.028M/s (drops 0.000 ± 0.000M/s) Single producer on one CPU, consumer on another one, both running at full speed. Curiously, rb-libbpf has higher throughput than objectively faster (due to more lightweight consumer code path) rb-custom. It appears that faster consumer causes kernel to send notifications more frequently, because consumer appears to be caught up more frequently. Performance of perfbuf suffers from default "no sampling" policy and huge overhead that causes. In sampled mode, rb-custom is winning very significantly eliminating too frequent in-kernel wakeups, the gain appears to be more than 2x. Perf buffer achieves even more impressive wins, compared to stock perfbuf settings, with 10x improvements in throughput with 1:500 sampling rate. The trade-off is that with sampling, application might not get next X events until X+1st arrives, which is not always acceptable. With steady influx of events, though, this shouldn't be a problem. Overall, single-producer performance of ring buffers seems to be better no matter the sampled/non-sampled modes, but it especially beats ring buffer without sampling due to its adaptive notification approach. Single-producer, back-to-back mode ================================== rb-libbpf 15.507 ± 0.247M/s (drops 0.000 ± 0.000M/s) rb-libbpf-sampled 14.692 ± 0.195M/s (drops 0.000 ± 0.000M/s) rb-custom 21.449 ± 0.157M/s (drops 0.000 ± 0.000M/s) rb-custom-sampled 20.024 ± 0.386M/s (drops 0.000 ± 0.000M/s) pb-libbpf 1.601 ± 0.015M/s (drops 0.000 ± 0.000M/s) pb-libbpf-sampled 8.545 ± 0.064M/s (drops 0.000 ± 0.000M/s) pb-custom 1.607 ± 0.022M/s (drops 0.000 ± 0.000M/s) pb-custom-sampled 8.988 ± 0.144M/s (drops 0.000 ± 0.000M/s) Here we test a back-to-back mode, which is arguably best-case scenario both for BPF ringbuf and perfbuf, because there is no contention and for ringbuf also no excessive notification, because consumer appears to be behind after the first record. For ringbuf, custom consumer code clearly wins with 21.5 vs 16 million records per second exchanged between producer and consumer. Sampled mode actually hurts a bit due to slightly slower producer logic (it needs to fetch amount of data available to decide whether to skip or force notification). Perfbuf with wakeup sampling gets 5.5x throughput increase, compared to no-sampling version. There also doesn't seem to be noticeable overhead from generic libbpf handling code. Perfbuf back-to-back, effect of sample rate =========================================== pb-sampled-1 1.035 ± 0.012M/s (drops 0.000 ± 0.000M/s) pb-sampled-5 3.476 ± 0.087M/s (drops 0.000 ± 0.000M/s) pb-sampled-10 5.094 ± 0.136M/s (drops 0.000 ± 0.000M/s) pb-sampled-25 7.118 ± 0.153M/s (drops 0.000 ± 0.000M/s) pb-sampled-50 8.169 ± 0.156M/s (drops 0.000 ± 0.000M/s) pb-sampled-100 8.887 ± 0.136M/s (drops 0.000 ± 0.000M/s) pb-sampled-250 9.180 ± 0.209M/s (drops 0.000 ± 0.000M/s) pb-sampled-500 9.353 ± 0.281M/s (drops 0.000 ± 0.000M/s) pb-sampled-1000 9.411 ± 0.217M/s (drops 0.000 ± 0.000M/s) pb-sampled-2000 9.464 ± 0.167M/s (drops 0.000 ± 0.000M/s) pb-sampled-3000 9.575 ± 0.273M/s (drops 0.000 ± 0.000M/s) This benchmark shows the effect of event sampling for perfbuf. Back-to-back mode for highest throughput. Just doing every 5th record notification gives 3.5x speed up. 250-500 appears to be the point of diminishing return, with almost 9x speed up. Most benchmarks use 500 as the default sampling for pb-raw and pb-custom. Ringbuf back-to-back, effect of sample rate =========================================== rb-sampled-1 1.106 ± 0.010M/s (drops 0.000 ± 0.000M/s) rb-sampled-5 4.746 ± 0.149M/s (drops 0.000 ± 0.000M/s) rb-sampled-10 7.706 ± 0.164M/s (drops 0.000 ± 0.000M/s) rb-sampled-25 12.893 ± 0.273M/s (drops 0.000 ± 0.000M/s) rb-sampled-50 15.961 ± 0.361M/s (drops 0.000 ± 0.000M/s) rb-sampled-100 18.203 ± 0.445M/s (drops 0.000 ± 0.000M/s) rb-sampled-250 19.962 ± 0.786M/s (drops 0.000 ± 0.000M/s) rb-sampled-500 20.881 ± 0.551M/s (drops 0.000 ± 0.000M/s) rb-sampled-1000 21.317 ± 0.532M/s (drops 0.000 ± 0.000M/s) rb-sampled-2000 21.331 ± 0.535M/s (drops 0.000 ± 0.000M/s) rb-sampled-3000 21.688 ± 0.392M/s (drops 0.000 ± 0.000M/s) Similar benchmark for ring buffer also shows a great advantage (in terms of throughput) of skipping notifications. Skipping every 5th one gives 4x boost. Also similar to perfbuf case, 250-500 seems to be the point of diminishing returns, giving roughly 20x better results. Keep in mind, for this test, notifications are controlled manually with BPF_RB_NO_WAKEUP and BPF_RB_FORCE_WAKEUP. As can be seen from previous benchmarks, adaptive notifications based on consumer's positions provides same (or even slightly better due to simpler load generator on BPF side) benefits in favorable back-to-back scenario. Over zealous and fast consumer, which is almost always caught up, will make thoughput numbers smaller. That's the case when manual notification control might prove to be extremely beneficial. Ringbuf back-to-back, reserve+commit vs output ============================================== reserve 22.819 ± 0.503M/s (drops 0.000 ± 0.000M/s) output 18.906 ± 0.433M/s (drops 0.000 ± 0.000M/s) Ringbuf sampled, reserve+commit vs output ========================================= reserve-sampled 15.350 ± 0.132M/s (drops 0.000 ± 0.000M/s) output-sampled 14.195 ± 0.144M/s (drops 0.000 ± 0.000M/s) BPF ringbuf supports two sets of APIs with various usability and performance tradeoffs: bpf_ringbuf_reserve()+bpf_ringbuf_commit() vs bpf_ringbuf_output(). This benchmark clearly shows superiority of reserve+commit approach, despite using a small 8-byte record size. Single-producer, consumer/producer competing on the same CPU, low batch count ============================================================================= rb-libbpf 3.045 ± 0.020M/s (drops 3.536 ± 0.148M/s) rb-custom 3.055 ± 0.022M/s (drops 3.893 ± 0.066M/s) pb-libbpf 1.393 ± 0.024M/s (drops 0.000 ± 0.000M/s) pb-custom 1.407 ± 0.016M/s (drops 0.000 ± 0.000M/s) This benchmark shows one of the worst-case scenarios, in which producer and consumer do not coordinate *and* fight for the same CPU. No batch count and sampling settings were able to eliminate drops for ringbuffer, producer is just too fast for consumer to keep up. But ringbuf and perfbuf still able to pass through quite a lot of messages, which is more than enough for a lot of applications. Ringbuf, multi-producer contention ================================== rb-libbpf nr_prod 1 10.916 ± 0.399M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 2 4.931 ± 0.030M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 3 4.880 ± 0.006M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 4 3.926 ± 0.004M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 8 4.011 ± 0.004M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 12 3.967 ± 0.016M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 16 2.604 ± 0.030M/s (drops 0.001 ± 0.002M/s) rb-libbpf nr_prod 20 2.233 ± 0.003M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 24 2.085 ± 0.015M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 28 2.055 ± 0.004M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 32 1.962 ± 0.004M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 36 2.089 ± 0.005M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 40 2.118 ± 0.006M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 44 2.105 ± 0.004M/s (drops 0.000 ± 0.000M/s) rb-libbpf nr_prod 48 2.120 ± 0.058M/s (drops 0.000 ± 0.001M/s) rb-libbpf nr_prod 52 2.074 ± 0.024M/s (drops 0.007 ± 0.014M/s) Ringbuf uses a very short-duration spinlock during reservation phase, to check few invariants, increment producer count and set record header. This is the biggest point of contention for ringbuf implementation. This benchmark evaluates the effect of multiple competing writers on overall throughput of a single shared ringbuffer. Overall throughput drops almost 2x when going from single to two highly-contended producers, gradually dropping with additional competing producers. Performance drop stabilizes at around 20 producers and hovers around 2mln even with 50+ fighting producers, which is a 5x drop compared to non-contended case. Good kernel implementation in kernel helps maintain decent performance here. Note, that in the intended real-world scenarios, it's not expected to get even close to such a high levels of contention. But if contention will become a problem, there is always an option of sharding few ring buffers across a set of CPUs. Signed-off-by: Andrii Nakryiko <[email protected]> Signed-off-by: Daniel Borkmann <[email protected]> Link: https://lore.kernel.org/bpf/[email protected] Signed-off-by: Alexei Starovoitov <[email protected]>
2020-06-01selftests/bpf: Add BPF ringbuf selftestsAndrii Nakryiko4-0/+468
Both singleton BPF ringbuf and BPF ringbuf with map-in-map use cases are tested. Also reserve+submit/discards and output variants of API are validated. Signed-off-by: Andrii Nakryiko <[email protected]> Signed-off-by: Daniel Borkmann <[email protected]> Link: https://lore.kernel.org/bpf/[email protected] Signed-off-by: Alexei Starovoitov <[email protected]>
2020-06-01bpf: Implement BPF ring buffer and verifier support for itAndrii Nakryiko8-18/+18
This commit adds a new MPSC ring buffer implementation into BPF ecosystem, which allows multiple CPUs to submit data to a single shared ring buffer. On the consumption side, only single consumer is assumed. Motivation ---------- There are two distinctive motivators for this work, which are not satisfied by existing perf buffer, which prompted creation of a new ring buffer implementation. - more efficient memory utilization by sharing ring buffer across CPUs; - preserving ordering of events that happen sequentially in time, even across multiple CPUs (e.g., fork/exec/exit events for a task). These two problems are independent, but perf buffer fails to satisfy both. Both are a result of a choice to have per-CPU perf ring buffer. Both can be also solved by having an MPSC implementation of ring buffer. The ordering problem could technically be solved for perf buffer with some in-kernel counting, but given the first one requires an MPSC buffer, the same solution would solve the second problem automatically. Semantics and APIs ------------------ Single ring buffer is presented to BPF programs as an instance of BPF map of type BPF_MAP_TYPE_RINGBUF. Two other alternatives considered, but ultimately rejected. One way would be to, similar to BPF_MAP_TYPE_PERF_EVENT_ARRAY, make BPF_MAP_TYPE_RINGBUF could represent an array of ring buffers, but not enforce "same CPU only" rule. This would be more familiar interface compatible with existing perf buffer use in BPF, but would fail if application needed more advanced logic to lookup ring buffer by arbitrary key. HASH_OF_MAPS addresses this with current approach. Additionally, given the performance of BPF ringbuf, many use cases would just opt into a simple single ring buffer shared among all CPUs, for which current approach would be an overkill. Another approach could introduce a new concept, alongside BPF map, to represent generic "container" object, which doesn't necessarily have key/value interface with lookup/update/delete operations. This approach would add a lot of extra infrastructure that has to be built for observability and verifier support. It would also add another concept that BPF developers would have to familiarize themselves with, new syntax in libbpf, etc. But then would really provide no additional benefits over the approach of using a map. BPF_MAP_TYPE_RINGBUF doesn't support lookup/update/delete operations, but so doesn't few other map types (e.g., queue and stack; array doesn't support delete, etc). The approach chosen has an advantage of re-using existing BPF map infrastructure (introspection APIs in kernel, libbpf support, etc), being familiar concept (no need to teach users a new type of object in BPF program), and utilizing existing tooling (bpftool). For common scenario of using a single ring buffer for all CPUs, it's as simple and straightforward, as would be with a dedicated "container" object. On the other hand, by being a map, it can be combined with ARRAY_OF_MAPS and HASH_OF_MAPS map-in-maps to implement a wide variety of topologies, from one ring buffer for each CPU (e.g., as a replacement for perf buffer use cases), to a complicated application hashing/sharding of ring buffers (e.g., having a small pool of ring buffers with hashed task's tgid being a look up key to preserve order, but reduce contention). Key and value sizes are enforced to be zero. max_entries is used to specify the size of ring buffer and has to be a power of 2 value. There are a bunch of similarities between perf buffer (BPF_MAP_TYPE_PERF_EVENT_ARRAY) and new BPF ring buffer semantics: - variable-length records; - if there is no more space left in ring buffer, reservation fails, no blocking; - memory-mappable data area for user-space applications for ease of consumption and high performance; - epoll notifications for new incoming data; - but still the ability to do busy polling for new data to achieve the lowest latency, if necessary. BPF ringbuf provides two sets of APIs to BPF programs: - bpf_ringbuf_output() allows to *copy* data from one place to a ring buffer, similarly to bpf_perf_event_output(); - bpf_ringbuf_reserve()/bpf_ringbuf_commit()/bpf_ringbuf_discard() APIs split the whole process into two steps. First, a fixed amount of space is reserved. If successful, a pointer to a data inside ring buffer data area is returned, which BPF programs can use similarly to a data inside array/hash maps. Once ready, this piece of memory is either committed or discarded. Discard is similar to commit, but makes consumer ignore the record. bpf_ringbuf_output() has disadvantage of incurring extra memory copy, because record has to be prepared in some other place first. But it allows to submit records of the length that's not known to verifier beforehand. It also closely matches bpf_perf_event_output(), so will simplify migration significantly. bpf_ringbuf_reserve() avoids the extra copy of memory by providing a memory pointer directly to ring buffer memory. In a lot of cases records are larger than BPF stack space allows, so many programs have use extra per-CPU array as a temporary heap for preparing sample. bpf_ringbuf_reserve() avoid this needs completely. But in exchange, it only allows a known constant size of memory to be reserved, such that verifier can verify that BPF program can't access memory outside its reserved record space. bpf_ringbuf_output(), while slightly slower due to extra memory copy, covers some use cases that are not suitable for bpf_ringbuf_reserve(). The difference between commit and discard is very small. Discard just marks a record as discarded, and such records are supposed to be ignored by consumer code. Discard is useful for some advanced use-cases, such as ensuring all-or-nothing multi-record submission, or emulating temporary malloc()/free() within single BPF program invocation. Each reserved record is tracked by verifier through existing reference-tracking logic, similar to socket ref-tracking. It is thus impossible to reserve a record, but forget to submit (or discard) it. bpf_ringbuf_query() helper allows to query various properties of ring buffer. Currently 4 are supported: - BPF_RB_AVAIL_DATA returns amount of unconsumed data in ring buffer; - BPF_RB_RING_SIZE returns the size of ring buffer; - BPF_RB_CONS_POS/BPF_RB_PROD_POS returns current logical possition of consumer/producer, respectively. Returned values are momentarily snapshots of ring buffer state and could be off by the time helper returns, so this should be used only for debugging/reporting reasons or for implementing various heuristics, that take into account highly-changeable nature of some of those characteristics. One such heuristic might involve more fine-grained control over poll/epoll notifications about new data availability in ring buffer. Together with BPF_RB_NO_WAKEUP/BPF_RB_FORCE_WAKEUP flags for output/commit/discard helpers, it allows BPF program a high degree of control and, e.g., more efficient batched notifications. Default self-balancing strategy, though, should be adequate for most applications and will work reliable and efficiently already. Design and implementation ------------------------- This reserve/commit schema allows a natural way for multiple producers, either on different CPUs or even on the same CPU/in the same BPF program, to reserve independent records and work with them without blocking other producers. This means that if BPF program was interruped by another BPF program sharing the same ring buffer, they will both get a record reserved (provided there is enough space left) and can work with it and submit it independently. This applies to NMI context as well, except that due to using a spinlock during reservation, in NMI context, bpf_ringbuf_reserve() might fail to get a lock, in which case reservation will fail even if ring buffer is not full. The ring buffer itself internally is implemented as a power-of-2 sized circular buffer, with two logical and ever-increasing counters (which might wrap around on 32-bit architectures, that's not a problem): - consumer counter shows up to which logical position consumer consumed the data; - producer counter denotes amount of data reserved by all producers. Each time a record is reserved, producer that "owns" the record will successfully advance producer counter. At that point, data is still not yet ready to be consumed, though. Each record has 8 byte header, which contains the length of reserved record, as well as two extra bits: busy bit to denote that record is still being worked on, and discard bit, which might be set at commit time if record is discarded. In the latter case, consumer is supposed to skip the record and move on to the next one. Record header also encodes record's relative offset from the beginning of ring buffer data area (in pages). This allows bpf_ringbuf_commit()/bpf_ringbuf_discard() to accept only the pointer to the record itself, without requiring also the pointer to ring buffer itself. Ring buffer memory location will be restored from record metadata header. This significantly simplifies verifier, as well as improving API usability. Producer counter increments are serialized under spinlock, so there is a strict ordering between reservations. Commits, on the other hand, are completely lockless and independent. All records become available to consumer in the order of reservations, but only after all previous records where already committed. It is thus possible for slow producers to temporarily hold off submitted records, that were reserved later. Reservation/commit/consumer protocol is verified by litmus tests in Documentation/litmus-test/bpf-rb. One interesting implementation bit, that significantly simplifies (and thus speeds up as well) implementation of both producers and consumers is how data area is mapped twice contiguously back-to-back in the virtual memory. This allows to not take any special measures for samples that have to wrap around at the end of the circular buffer data area, because the next page after the last data page would be first data page again, and thus the sample will still appear completely contiguous in virtual memory. See comment and a simple ASCII diagram showing this visually in bpf_ringbuf_area_alloc(). Another feature that distinguishes BPF ringbuf from perf ring buffer is a self-pacing notifications of new data being availability. bpf_ringbuf_commit() implementation will send a notification of new record being available after commit only if consumer has already caught up right up to the record being committed. If not, consumer still has to catch up and thus will see new data anyways without needing an extra poll notification. Benchmarks (see tools/testing/selftests/bpf/benchs/bench_ringbuf.c) show that this allows to achieve a very high throughput without having to resort to tricks like "notify only every Nth sample", which are necessary with perf buffer. For extreme cases, when BPF program wants more manual control of notifications, commit/discard/output helpers accept BPF_RB_NO_WAKEUP and BPF_RB_FORCE_WAKEUP flags, which give full control over notifications of data availability, but require extra caution and diligence in using this API. Comparison to alternatives -------------------------- Before considering implementing BPF ring buffer from scratch existing alternatives in kernel were evaluated, but didn't seem to meet the needs. They largely fell into few categores: - per-CPU buffers (perf, ftrace, etc), which don't satisfy two motivations outlined above (ordering and memory consumption); - linked list-based implementations; while some were multi-producer designs, consuming these from user-space would be very complicated and most probably not performant; memory-mapping contiguous piece of memory is simpler and more performant for user-space consumers; - io_uring is SPSC, but also requires fixed-sized elements. Naively turning SPSC queue into MPSC w/ lock would have subpar performance compared to locked reserve + lockless commit, as with BPF ring buffer. Fixed sized elements would be too limiting for BPF programs, given existing BPF programs heavily rely on variable-sized perf buffer already; - specialized implementations (like a new printk ring buffer, [0]) with lots of printk-specific limitations and implications, that didn't seem to fit well for intended use with BPF programs. [0] https://lwn.net/Articles/779550/ Signed-off-by: Andrii Nakryiko <[email protected]> Signed-off-by: Daniel Borkmann <[email protected]> Link: https://lore.kernel.org/bpf/[email protected] Signed-off-by: Alexei Starovoitov <[email protected]>
2020-06-01selftests/bpf: Add tests for write-only stacks/queuesAnton Protopopov1-1/+39
For write-only stacks and queues bpf_map_update_elem should be allowed, but bpf_map_lookup_elem and bpf_map_lookup_and_delete_elem should fail with EPERM. Signed-off-by: Anton Protopopov <[email protected]> Signed-off-by: Daniel Borkmann <[email protected]> Link: https://lore.kernel.org/bpf/[email protected] Signed-off-by: Alexei Starovoitov <[email protected]>
2020-06-01selftests/bpf: Cleanup comments in test_mapsAnton Protopopov1-3/+3
Make comments inside the test_map_rdonly and test_map_wronly tests consistent with logic. Signed-off-by: Anton Protopopov <[email protected]> Signed-off-by: Daniel Borkmann <[email protected]> Link: https://lore.kernel.org/bpf/[email protected] Signed-off-by: Alexei Starovoitov <[email protected]>
2020-06-01selftests/bpf: Cleanup some file descriptors in test_mapsAnton Protopopov1-0/+4
The test_map_rdonly and test_map_wronly tests should close file descriptors which they open. Signed-off-by: Anton Protopopov <[email protected]> Signed-off-by: Daniel Borkmann <[email protected]> Link: https://lore.kernel.org/bpf/[email protected] Signed-off-by: Alexei Starovoitov <[email protected]>
2020-06-01selftests/bpf: Fix a typo in test_mapsAnton Protopopov1-1/+1
Trivial fix to a typo in the test_map_wronly test: "read" -> "write" Signed-off-by: Anton Protopopov <[email protected]> Signed-off-by: Daniel Borkmann <[email protected]> Link: https://lore.kernel.org/bpf/[email protected] Signed-off-by: Alexei Starovoitov <[email protected]>
2020-06-01bpf, selftests: Test probe_* helpers from SCHED_CLSJohn Fastabend2-0/+58
Lets test using probe* in SCHED_CLS network programs as well just to be sure these keep working. Its cheap to add the extra test and provides a second context to test outside of sk_msg after we generalized probe* helpers to all networking types. Signed-off-by: John Fastabend <[email protected]> Signed-off-by: Daniel Borkmann <[email protected]> Acked-by: Yonghong Song <[email protected]> Acked-by: Andrii Nakryiko <[email protected]> Link: https://lore.kernel.org/bpf/159033911685.12355.15951980509828906214.stgit@john-Precision-5820-Tower Signed-off-by: Alexei Starovoitov <[email protected]>
2020-06-01bpf, selftests: Add sk_msg helpers load and attach testJohn Fastabend2-0/+82
The test itself is not particularly useful but it encodes a common pattern we have. Namely do a sk storage lookup then depending on data here decide if we need to do more work or alternatively allow packet to PASS. Then if we need to do more work consult task_struct for more information about the running task. Finally based on this additional information drop or pass the data. In this case the suspicious check is not so realisitic but it encodes the general pattern and uses the helpers so we test the workflow. This is a load test to ensure verifier correctly handles this case. Signed-off-by: John Fastabend <[email protected]> Signed-off-by: Daniel Borkmann <[email protected]> Acked-by: Andrii Nakryiko <[email protected]> Link: https://lore.kernel.org/bpf/159033909665.12355.6166415847337547879.stgit@john-Precision-5820-Tower Signed-off-by: Alexei Starovoitov <[email protected]>
2020-05-31Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/netDavid S. Miller1-14/+32
xdp_umem.c had overlapping changes between the 64-bit math fix for the calculation of npgs and the removal of the zerocopy memory type which got rid of the chunk_size_nohdr member. The mlx5 Kconfig conflict is a case where we just take the net-next copy of the Kconfig entry dependency as it takes on the ESWITCH dependency by one level of indirection which is what the 'net' conflicting change is trying to ensure. Signed-off-by: David S. Miller <[email protected]>
2020-05-29bpf, selftests: Add a verifier test for assigning 32bit reg states to 64bit onesJohn Fastabend1-0/+22
Added a verifier test for assigning 32bit reg states to 64bit where 32bit reg holds a constant value of 0. Without previous kernel verifier.c fix, the test in this patch will fail. Signed-off-by: Yonghong Song <[email protected]> Signed-off-by: John Fastabend <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Link: https://lore.kernel.org/bpf/159077335867.6014.2075350327073125374.stgit@john-Precision-5820-Tower
2020-05-29bpf, selftests: Verifier bounds tests need to be updatedJohn Fastabend1-14/+10
After previous fix for zero extension test_verifier tests #65 and #66 now fail. Before the fix we can see the alu32 mov op at insn 10 10: R0_w=map_value(id=0,off=0,ks=8,vs=8,imm=0) R1_w=invP(id=0, smin_value=4294967168,smax_value=4294967423, umin_value=4294967168,umax_value=4294967423, var_off=(0x0; 0x1ffffffff), s32_min_value=-2147483648,s32_max_value=2147483647, u32_min_value=0,u32_max_value=-1) R10=fp0 fp-8_w=mmmmmmmm 10: (bc) w1 = w1 11: R0_w=map_value(id=0,off=0,ks=8,vs=8,imm=0) R1_w=invP(id=0, smin_value=0,smax_value=2147483647, umin_value=0,umax_value=4294967295, var_off=(0x0; 0xffffffff), s32_min_value=-2147483648,s32_max_value=2147483647, u32_min_value=0,u32_max_value=-1) R10=fp0 fp-8_w=mmmmmmmm After the fix at insn 10 because we have 's32_min_value < 0' the following step 11 now has 'smax_value=U32_MAX' where before we pulled the s32_max_value bound into the smax_value as seen above in 11 with smax_value=2147483647. 10: R0_w=map_value(id=0,off=0,ks=8,vs=8,imm=0) R1_w=inv(id=0, smin_value=4294967168,smax_value=4294967423, umin_value=4294967168,umax_value=4294967423, var_off=(0x0; 0x1ffffffff), s32_min_value=-2147483648, s32_max_value=2147483647, u32_min_value=0,u32_max_value=-1) R10=fp0 fp-8_w=mmmmmmmm 10: (bc) w1 = w1 11: R0_w=map_value(id=0,off=0,ks=8,vs=8,imm=0) R1_w=inv(id=0, smin_value=0,smax_value=4294967295, umin_value=0,umax_value=4294967295, var_off=(0x0; 0xffffffff), s32_min_value=-2147483648, s32_max_value=2147483647, u32_min_value=0, u32_max_value=-1) R10=fp0 fp-8_w=mmmmmmmm The fall out of this is by the time we get to the failing instruction at step 14 where previously we had the following: 14: R0_w=map_value(id=0,off=0,ks=8,vs=8,imm=0) R1_w=inv(id=0, smin_value=72057594021150720,smax_value=72057594029539328, umin_value=72057594021150720,umax_value=72057594029539328, var_off=(0xffffffff000000; 0xffffff), s32_min_value=-16777216,s32_max_value=-1, u32_min_value=-16777216,u32_max_value=-1) R10=fp0 fp-8_w=mmmmmmmm 14: (0f) r0 += r1 We now have, 14: R0_w=map_value(id=0,off=0,ks=8,vs=8,imm=0) R1_w=inv(id=0, smin_value=0,smax_value=72057594037927935, umin_value=0,umax_value=72057594037927935, var_off=(0x0; 0xffffffffffffff), s32_min_value=-2147483648,s32_max_value=2147483647, u32_min_value=0,u32_max_value=-1) R10=fp0 fp-8_w=mmmmmmmm 14: (0f) r0 += r1 In the original step 14 'smin_value=72057594021150720' this trips the logic in the verifier function check_reg_sane_offset(), if (smin >= BPF_MAX_VAR_OFF || smin <= -BPF_MAX_VAR_OFF) { verbose(env, "value %lld makes %s pointer be out of bounds\n", smin, reg_type_str[type]); return false; } Specifically, the 'smin <= -BPF_MAX_VAR_OFF' check. But with the fix at step 14 we have bounds 'smin_value=0' so the above check is not tripped because BPF_MAX_VAR_OFF=1<<29. We have a smin_value=0 here because at step 10 the smaller smin_value=0 means the subtractions at steps 11 and 12 bring the smin_value negative. 11: (17) r1 -= 2147483584 12: (17) r1 -= 2147483584 13: (77) r1 >>= 8 Then the shift clears the top bit and smin_value is set to 0. Note we still have the smax_value in the fixed code so any reads will fail. An alternative would be to have reg_sane_check() do both smin and smax value tests. To fix the test we can omit the 'r1 >>=8' at line 13. This will change the err string, but keeps the intention of the test as suggseted by the title, "check after truncation of boundary-crossing range". If the verifier logic changes a different value is likely to be thrown in the error or the error will no longer be thrown forcing this test to be examined. With this change we see the new state at step 13. 13: R0_w=map_value(id=0,off=0,ks=8,vs=8,imm=0) R1_w=invP(id=0, smin_value=-4294967168,smax_value=127, umin_value=0,umax_value=18446744073709551615, s32_min_value=-2147483648,s32_max_value=2147483647, u32_min_value=0,u32_max_value=-1) R10=fp0 fp-8_w=mmmmmmmm Giving the expected out of bounds error, "value -4294967168 makes map_value pointer be out of bounds" However, for unpriv case we see a different error now because of the mixed signed bounds pointer arithmatic. This seems OK so I've only added the unpriv_errstr for this. Another optino may have been to do addition on r1 instead of subtraction but I favor the approach above slightly. Signed-off-by: John Fastabend <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Acked-by: Yonghong Song <[email protected]> Link: https://lore.kernel.org/bpf/159077333942.6014.14004320043595756079.stgit@john-Precision-5820-Tower
2020-05-24Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/netDavid S. Miller2-1/+20
The MSCC bug fix in 'net' had to be slightly adjusted because the register accesses are done slightly differently in net-next. Signed-off-by: David S. Miller <[email protected]>
2020-05-23selftests/bpf: CONFIG_LIRC required for test_lirc_mode2.shAlan Maguire1-0/+1
test_lirc_mode2.sh assumes presence of /sys/class/rc/rc0/lirc*/uevent which will not be present unless CONFIG_LIRC=y Fixes: 6bdd533cee9a ("bpf: add selftest for lirc_mode2 type program") Signed-off-by: Alan Maguire <[email protected]> Signed-off-by: Daniel Borkmann <[email protected]> Link: https://lore.kernel.org/bpf/[email protected]
2020-05-23selftests/bpf: CONFIG_IPV6_SEG6_BPF required for test_seg6_loop.oAlan Maguire1-0/+1
test_seg6_loop.o uses the helper bpf_lwt_seg6_adjust_srh(); it will not be present if CONFIG_IPV6_SEG6_BPF is not specified. Fixes: b061017f8b4d ("selftests/bpf: add realistic loop tests") Signed-off-by: Alan Maguire <[email protected]> Signed-off-by: Daniel Borkmann <[email protected]> Link: https://lore.kernel.org/bpf/[email protected]
2020-05-23selftests/bpf: Add general instructions for test executionAlan Maguire1-0/+2
Getting a clean BPF selftests run involves ensuring latest trunk LLVM/clang are used, pahole is recent (>=1.16) and config matches the specified config file as closely as possible. Add to bpf_devel_QA.rst and point tools/testing/selftests/bpf/README.rst to it. Signed-off-by: Alan Maguire <[email protected]> Signed-off-by: Daniel Borkmann <[email protected]> Acked-by: Andrii Nakryiko <[email protected]> Link: https://lore.kernel.org/bpf/[email protected]
2020-05-21bpf: Selftests, add printk to test_sk_lookup_kern to encode null ptr checkJohn Fastabend1-0/+1
Adding a printk to test_sk_lookup_kern created the reported failure where a pointer type is checked twice for NULL. Lets add it to the progs test test_sk_lookup_kern.c so we test the case from C all the way into the verifier. We already have printk's in selftests so seems OK to add another one. Signed-off-by: John Fastabend <[email protected]> Signed-off-by: Alexei Starovoitov <[email protected]> Acked-by: Andrii Nakryiko <[email protected]> Link: https://lore.kernel.org/bpf/159009170603.6313.1715279795045285176.stgit@john-Precision-5820-Tower