summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2021-12-31 14:35:40 +0000
committerDavid S. Miller <davem@davemloft.net>2021-12-31 14:35:40 +0000
commite63a02348958cd7cc8c8401c94de57ad97b5d06c (patch)
treed3f07960e158be75c3002c13d3dc2c142a65fbb7
parentce2b6eb409ad40607193641c3ec18c3457e1f57c (diff)
parent9e6b19a66d9b6b94395478fe79c5a3ccba181ad3 (diff)
downloadlinux-e63a02348958cd7cc8c8401c94de57ad97b5d06c.tar.gz
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Alexei Starovoitov says: ==================== pull-request: bpf-next 2021-12-30 The following pull-request contains BPF updates for your *net-next* tree. We've added 72 non-merge commits during the last 20 day(s) which contain a total of 223 files changed, 3510 insertions(+), 1591 deletions(-). The main changes are: 1) Automatic setrlimit in libbpf when bpf is memcg's in the kernel, from Andrii. 2) Beautify and de-verbose verifier logs, from Christy. 3) Composable verifier types, from Hao. 4) bpf_strncmp helper, from Hou. 5) bpf.h header dependency cleanup, from Jakub. 6) get_func_[arg|ret|arg_cnt] helpers, from Jiri. 7) Sleepable local storage, from KP. 8) Extend kfunc with PTR_TO_CTX, PTR_TO_MEM argument support, from Kumar. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
-rw-r--r--Documentation/bpf/classic_vs_extended.rst376
-rw-r--r--Documentation/bpf/index.rst1
-rw-r--r--Documentation/bpf/instruction-set.rst514
-rw-r--r--arch/s390/mm/hugetlbpage.c1
-rw-r--r--arch/x86/net/bpf_jit_comp.c55
-rw-r--r--drivers/bluetooth/btqca.c1
-rw-r--r--drivers/infiniband/core/cache.c1
-rw-r--r--drivers/infiniband/hw/irdma/ctrl.c2
-rw-r--r--drivers/infiniband/hw/irdma/uda.c2
-rw-r--r--drivers/infiniband/hw/mlx5/doorbell.c1
-rw-r--r--drivers/infiniband/hw/mlx5/qp.c1
-rw-r--r--drivers/net/amt.c1
-rw-r--r--drivers/net/appletalk/ipddp.c1
-rw-r--r--drivers/net/bonding/bond_main.c1
-rw-r--r--drivers/net/can/usb/peak_usb/pcan_usb.c1
-rw-r--r--drivers/net/dsa/microchip/ksz8795.c1
-rw-r--r--drivers/net/dsa/xrs700x/xrs700x.c1
-rw-r--r--drivers/net/ethernet/amazon/ena/ena_netdev.c2
-rw-r--r--drivers/net/ethernet/amazon/ena/ena_netdev.h1
-rw-r--r--drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c1
-rw-r--r--drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c2
-rw-r--r--drivers/net/ethernet/cavium/thunder/nicvf_main.c2
-rw-r--r--drivers/net/ethernet/cavium/thunder/nicvf_queues.c1
-rw-r--r--drivers/net/ethernet/freescale/dpaa/dpaa_eth.c2
-rw-r--r--drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c2
-rw-r--r--drivers/net/ethernet/freescale/enetc/enetc.c2
-rw-r--r--drivers/net/ethernet/huawei/hinic/hinic_tx.c1
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_txrx.c2
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_xsk.c2
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_xsk.h1
-rw-r--r--drivers/net/ethernet/intel/ice/ice_devlink.c2
-rw-r--r--drivers/net/ethernet/intel/ice/ice_txrx.c2
-rw-r--r--drivers/net/ethernet/intel/ice/ice_txrx_lib.c2
-rw-r--r--drivers/net/ethernet/intel/ice/ice_xsk.c2
-rw-r--r--drivers/net/ethernet/intel/igb/igb_main.c2
-rw-r--r--drivers/net/ethernet/intel/igc/igc_main.c2
-rw-r--r--drivers/net/ethernet/intel/igc/igc_xdp.c1
-rw-r--r--drivers/net/ethernet/intel/ixgbe/ixgbe_main.c2
-rw-r--r--drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h2
-rw-r--r--drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c2
-rw-r--r--drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c2
-rw-r--r--drivers/net/ethernet/marvell/mvneta.c2
-rw-r--r--drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c2
-rw-r--r--drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c2
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/en_netdev.c1
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/en_rx.c2
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en/qos.c1
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c2
-rw-r--r--drivers/net/ethernet/microsoft/mana/mana_bpf.c2
-rw-r--r--drivers/net/ethernet/microsoft/mana/mana_en.c2
-rw-r--r--drivers/net/ethernet/netronome/nfp/nfp_net_common.c2
-rw-r--r--drivers/net/ethernet/qlogic/qede/qede_fp.c2
-rw-r--r--drivers/net/ethernet/sfc/efx.c1
-rw-r--r--drivers/net/ethernet/sfc/efx_channels.c1
-rw-r--r--drivers/net/ethernet/sfc/efx_common.c1
-rw-r--r--drivers/net/ethernet/sfc/rx.c2
-rw-r--r--drivers/net/ethernet/socionext/netsec.c2
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/stmmac.h1
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/stmmac_main.c2
-rw-r--r--drivers/net/ethernet/ti/cpsw_priv.c2
-rw-r--r--drivers/net/ethernet/ti/cpsw_priv.h2
-rw-r--r--drivers/net/hamradio/hdlcdrv.c1
-rw-r--r--drivers/net/hamradio/scc.c1
-rw-r--r--drivers/net/hyperv/netvsc_bpf.c2
-rw-r--r--drivers/net/loopback.c1
-rw-r--r--drivers/net/tun.c2
-rw-r--r--drivers/net/veth.c4
-rw-r--r--drivers/net/virtio_net.c4
-rw-r--r--drivers/net/vrf.c1
-rw-r--r--drivers/net/xen-netfront.c2
-rw-r--r--fs/nfs/dir.c1
-rw-r--r--fs/nfs/fs_context.c1
-rw-r--r--fs/select.c1
-rw-r--r--include/linux/bpf-cgroup-defs.h70
-rw-r--r--include/linux/bpf-cgroup.h57
-rw-r--r--include/linux/bpf-netns.h8
-rw-r--r--include/linux/bpf.h107
-rw-r--r--include/linux/bpf_local_storage.h6
-rw-r--r--include/linux/bpf_verifier.h27
-rw-r--r--include/linux/cgroup-defs.h2
-rw-r--r--include/linux/dsa/loop.h1
-rw-r--r--include/linux/filter.h2
-rw-r--r--include/linux/perf_event.h1
-rw-r--r--include/net/ip6_fib.h1
-rw-r--r--include/net/ipv6.h2
-rw-r--r--include/net/netns/bpf.h9
-rw-r--r--include/net/route.h1
-rw-r--r--include/net/sock.h2
-rw-r--r--include/net/xdp_priv.h1
-rw-r--r--include/net/xdp_sock.h1
-rw-r--r--include/uapi/linux/bpf.h39
-rw-r--r--kernel/bpf/bloom_filter.c6
-rw-r--r--kernel/bpf/bpf_inode_storage.c6
-rw-r--r--kernel/bpf/bpf_local_storage.c50
-rw-r--r--kernel/bpf/bpf_task_storage.c6
-rw-r--r--kernel/bpf/btf.c124
-rw-r--r--kernel/bpf/cgroup.c2
-rw-r--r--kernel/bpf/cpumap.c4
-rw-r--r--kernel/bpf/devmap.c4
-rw-r--r--kernel/bpf/helpers.c29
-rw-r--r--kernel/bpf/local_storage.c3
-rw-r--r--kernel/bpf/lpm_trie.c2
-rw-r--r--kernel/bpf/map_iter.c4
-rw-r--r--kernel/bpf/net_namespace.c1
-rw-r--r--kernel/bpf/reuseport_array.c6
-rw-r--r--kernel/bpf/ringbuf.c2
-rw-r--r--kernel/bpf/syscall.c3
-rw-r--r--kernel/bpf/trampoline.c8
-rw-r--r--kernel/bpf/verifier.c696
-rw-r--r--kernel/cgroup/cgroup.c1
-rw-r--r--kernel/sysctl.c1
-rw-r--r--kernel/trace/bpf_trace.c81
-rw-r--r--kernel/trace/trace_kprobe.c1
-rw-r--r--kernel/trace/trace_uprobe.c1
-rw-r--r--net/bluetooth/bnep/sock.c1
-rw-r--r--net/bluetooth/eir.h2
-rw-r--r--net/bluetooth/hidp/sock.c1
-rw-r--r--net/bluetooth/l2cap_sock.c1
-rw-r--r--net/bridge/br_ioctl.c1
-rw-r--r--net/caif/caif_socket.c1
-rw-r--r--net/core/bpf_sk_storage.c10
-rw-r--r--net/core/dev.c2
-rw-r--r--net/core/devlink.c1
-rw-r--r--net/core/filter.c72
-rw-r--r--net/core/flow_dissector.c1
-rw-r--r--net/core/lwt_bpf.c1
-rw-r--r--net/core/sock_diag.c1
-rw-r--r--net/core/sock_map.c2
-rw-r--r--net/core/sysctl_net_core.c1
-rw-r--r--net/decnet/dn_nsp_in.c1
-rw-r--r--net/dsa/dsa_priv.h1
-rw-r--r--net/ethtool/ioctl.c1
-rw-r--r--net/ipv4/nexthop.c1
-rw-r--r--net/ipv4/udp.c1
-rw-r--r--net/ipv6/ip6_fib.c1
-rw-r--r--net/ipv6/seg6_local.c1
-rw-r--r--net/ipv6/udp.c1
-rw-r--r--net/iucv/af_iucv.c1
-rw-r--r--net/kcm/kcmsock.c1
-rw-r--r--net/netfilter/nfnetlink_hook.c1
-rw-r--r--net/netfilter/nft_reject_netdev.c1
-rw-r--r--net/netlink/af_netlink.c2
-rw-r--r--net/packet/af_packet.c1
-rw-r--r--net/rose/rose_in.c1
-rw-r--r--net/sched/sch_frag.c1
-rw-r--r--net/smc/smc_ib.c2
-rw-r--r--net/smc/smc_ism.c1
-rw-r--r--net/socket.c1
-rw-r--r--net/unix/af_unix.c1
-rw-r--r--net/vmw_vsock/af_vsock.c1
-rw-r--r--net/xdp/xskmap.c1
-rw-r--r--net/xfrm/xfrm_state.c1
-rw-r--r--net/xfrm/xfrm_user.c1
-rw-r--r--samples/bpf/hbm.c11
-rw-r--r--samples/bpf/xdp_fwd_user.c12
-rw-r--r--security/device_cgroup.c1
-rw-r--r--tools/bpf/bpftool/Makefile13
-rw-r--r--tools/bpf/bpftool/feature.c26
-rw-r--r--tools/bpf/bpftool/main.c2
-rw-r--r--tools/bpf/resolve_btfids/Makefile1
-rw-r--r--tools/bpf/runqslower/Makefile4
-rw-r--r--tools/include/uapi/linux/bpf.h39
-rw-r--r--tools/lib/bpf/Makefile3
-rw-r--r--tools/lib/bpf/bpf.c85
-rw-r--r--tools/lib/bpf/bpf.h2
-rw-r--r--tools/lib/bpf/bpf_tracing.h431
-rw-r--r--tools/lib/bpf/btf.h6
-rw-r--r--tools/lib/bpf/btf_dump.c4
-rw-r--r--tools/lib/bpf/gen_loader.c11
-rw-r--r--tools/lib/bpf/libbpf.c85
-rw-r--r--tools/lib/bpf/libbpf.h77
-rw-r--r--tools/lib/bpf/libbpf.map4
-rw-r--r--tools/lib/bpf/libbpf_internal.h60
-rw-r--r--tools/lib/bpf/libbpf_legacy.h12
-rw-r--r--tools/lib/bpf/libbpf_probes.c251
-rw-r--r--tools/lib/bpf/relo_core.c20
-rw-r--r--tools/lib/bpf/xsk.c9
-rw-r--r--tools/perf/builtin-trace.c13
-rw-r--r--tools/scripts/Makefile.include13
-rw-r--r--tools/testing/selftests/bpf/Makefile12
-rw-r--r--tools/testing/selftests/bpf/bench.c24
-rw-r--r--tools/testing/selftests/bpf/bench.h9
-rw-r--r--tools/testing/selftests/bpf/benchs/bench_count.c2
-rw-r--r--tools/testing/selftests/bpf/benchs/bench_rename.c16
-rw-r--r--tools/testing/selftests/bpf/benchs/bench_ringbufs.c14
-rw-r--r--tools/testing/selftests/bpf/benchs/bench_strncmp.c161
-rw-r--r--tools/testing/selftests/bpf/benchs/bench_trigger.c24
-rwxr-xr-xtools/testing/selftests/bpf/benchs/run_bench_strncmp.sh12
-rw-r--r--tools/testing/selftests/bpf/config2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/align.c191
-rw-r--r--tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c7
-rw-r--r--tools/testing/selftests/bpf/prog_tests/btf.c1
-rw-r--r--tools/testing/selftests/bpf/prog_tests/connect_force_port.c18
-rw-r--r--tools/testing/selftests/bpf/prog_tests/core_reloc.c79
-rw-r--r--tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c17
-rw-r--r--tools/testing/selftests/bpf/prog_tests/get_func_args_test.c44
-rw-r--r--tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/ksyms_btf.c14
-rw-r--r--tools/testing/selftests/bpf/prog_tests/libbpf_probes.c124
-rw-r--r--tools/testing/selftests/bpf/prog_tests/select_reuseport.c1
-rw-r--r--tools/testing/selftests/bpf/prog_tests/sk_lookup.c1
-rw-r--r--tools/testing/selftests/bpf/prog_tests/sock_fields.c1
-rw-r--r--tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c15
-rw-r--r--tools/testing/selftests/bpf/prog_tests/stacktrace_map.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/test_local_storage.c20
-rw-r--r--tools/testing/selftests/bpf/prog_tests/test_overhead.c20
-rw-r--r--tools/testing/selftests/bpf/prog_tests/test_strncmp.c167
-rw-r--r--tools/testing/selftests/bpf/prog_tests/trampoline_count.c6
-rw-r--r--tools/testing/selftests/bpf/progs/get_func_args_test.c123
-rw-r--r--tools/testing/selftests/bpf/progs/local_storage.c24
-rw-r--r--tools/testing/selftests/bpf/progs/strncmp_bench.c50
-rw-r--r--tools/testing/selftests/bpf/progs/strncmp_test.c54
-rw-r--r--tools/testing/selftests/bpf/progs/test_ksyms_btf_write_check.c29
-rw-r--r--tools/testing/selftests/bpf/test_cpp.cpp9
-rw-r--r--tools/testing/selftests/bpf/test_maps.c1
-rw-r--r--tools/testing/selftests/bpf/test_progs.c2
-rw-r--r--tools/testing/selftests/bpf/test_verifier.c18
-rw-r--r--tools/testing/selftests/bpf/verifier/btf_ctx_access.c12
-rwxr-xr-xtools/testing/selftests/bpf/vmtest.sh2
221 files changed, 3506 insertions, 1591 deletions
diff --git a/Documentation/bpf/classic_vs_extended.rst b/Documentation/bpf/classic_vs_extended.rst
new file mode 100644
index 000000000000..2f81a81f5267
--- /dev/null
+++ b/Documentation/bpf/classic_vs_extended.rst
@@ -0,0 +1,376 @@
+
+===================
+Classic BPF vs eBPF
+===================
+
+eBPF is designed to be JITed with one to one mapping, which can also open up
+the possibility for GCC/LLVM compilers to generate optimized eBPF code through
+an eBPF backend that performs almost as fast as natively compiled code.
+
+Some core changes of the eBPF format from classic BPF:
+
+- Number of registers increase from 2 to 10:
+
+ The old format had two registers A and X, and a hidden frame pointer. The
+ new layout extends this to be 10 internal registers and a read-only frame
+ pointer. Since 64-bit CPUs are passing arguments to functions via registers
+ the number of args from eBPF program to in-kernel function is restricted
+ to 5 and one register is used to accept return value from an in-kernel
+ function. Natively, x86_64 passes first 6 arguments in registers, aarch64/
+ sparcv9/mips64 have 7 - 8 registers for arguments; x86_64 has 6 callee saved
+ registers, and aarch64/sparcv9/mips64 have 11 or more callee saved registers.
+
+ Thus, all eBPF registers map one to one to HW registers on x86_64, aarch64,
+ etc, and eBPF calling convention maps directly to ABIs used by the kernel on
+ 64-bit architectures.
+
+ On 32-bit architectures JIT may map programs that use only 32-bit arithmetic
+ and may let more complex programs to be interpreted.
+
+ R0 - R5 are scratch registers and eBPF program needs spill/fill them if
+ necessary across calls. Note that there is only one eBPF program (== one
+ eBPF main routine) and it cannot call other eBPF functions, it can only
+ call predefined in-kernel functions, though.
+
+- Register width increases from 32-bit to 64-bit:
+
+ Still, the semantics of the original 32-bit ALU operations are preserved
+ via 32-bit subregisters. All eBPF registers are 64-bit with 32-bit lower
+ subregisters that zero-extend into 64-bit if they are being written to.
+ That behavior maps directly to x86_64 and arm64 subregister definition, but
+ makes other JITs more difficult.
+
+ 32-bit architectures run 64-bit eBPF programs via interpreter.
+ Their JITs may convert BPF programs that only use 32-bit subregisters into
+ native instruction set and let the rest being interpreted.
+
+ Operation is 64-bit, because on 64-bit architectures, pointers are also
+ 64-bit wide, and we want to pass 64-bit values in/out of kernel functions,
+ so 32-bit eBPF registers would otherwise require to define register-pair
+ ABI, thus, there won't be able to use a direct eBPF register to HW register
+ mapping and JIT would need to do combine/split/move operations for every
+ register in and out of the function, which is complex, bug prone and slow.
+ Another reason is the use of atomic 64-bit counters.
+
+- Conditional jt/jf targets replaced with jt/fall-through:
+
+ While the original design has constructs such as ``if (cond) jump_true;
+ else jump_false;``, they are being replaced into alternative constructs like
+ ``if (cond) jump_true; /* else fall-through */``.
+
+- Introduces bpf_call insn and register passing convention for zero overhead
+ calls from/to other kernel functions:
+
+ Before an in-kernel function call, the eBPF program needs to
+ place function arguments into R1 to R5 registers to satisfy calling
+ convention, then the interpreter will take them from registers and pass
+ to in-kernel function. If R1 - R5 registers are mapped to CPU registers
+ that are used for argument passing on given architecture, the JIT compiler
+ doesn't need to emit extra moves. Function arguments will be in the correct
+ registers and BPF_CALL instruction will be JITed as single 'call' HW
+ instruction. This calling convention was picked to cover common call
+ situations without performance penalty.
+
+ After an in-kernel function call, R1 - R5 are reset to unreadable and R0 has
+ a return value of the function. Since R6 - R9 are callee saved, their state
+ is preserved across the call.
+
+ For example, consider three C functions::
+
+ u64 f1() { return (*_f2)(1); }
+ u64 f2(u64 a) { return f3(a + 1, a); }
+ u64 f3(u64 a, u64 b) { return a - b; }
+
+ GCC can compile f1, f3 into x86_64::
+
+ f1:
+ movl $1, %edi
+ movq _f2(%rip), %rax
+ jmp *%rax
+ f3:
+ movq %rdi, %rax
+ subq %rsi, %rax
+ ret
+
+ Function f2 in eBPF may look like::
+
+ f2:
+ bpf_mov R2, R1
+ bpf_add R1, 1
+ bpf_call f3
+ bpf_exit
+
+ If f2 is JITed and the pointer stored to ``_f2``. The calls f1 -> f2 -> f3 and
+ returns will be seamless. Without JIT, __bpf_prog_run() interpreter needs to
+ be used to call into f2.
+
+ For practical reasons all eBPF programs have only one argument 'ctx' which is
+ already placed into R1 (e.g. on __bpf_prog_run() startup) and the programs
+ can call kernel functions with up to 5 arguments. Calls with 6 or more arguments
+ are currently not supported, but these restrictions can be lifted if necessary
+ in the future.
+
+ On 64-bit architectures all register map to HW registers one to one. For
+ example, x86_64 JIT compiler can map them as ...
+
+ ::
+
+ R0 - rax
+ R1 - rdi
+ R2 - rsi
+ R3 - rdx
+ R4 - rcx
+ R5 - r8
+ R6 - rbx
+ R7 - r13
+ R8 - r14
+ R9 - r15
+ R10 - rbp
+
+ ... since x86_64 ABI mandates rdi, rsi, rdx, rcx, r8, r9 for argument passing
+ and rbx, r12 - r15 are callee saved.
+
+ Then the following eBPF pseudo-program::
+
+ bpf_mov R6, R1 /* save ctx */
+ bpf_mov R2, 2
+ bpf_mov R3, 3
+ bpf_mov R4, 4
+ bpf_mov R5, 5
+ bpf_call foo
+ bpf_mov R7, R0 /* save foo() return value */
+ bpf_mov R1, R6 /* restore ctx for next call */
+ bpf_mov R2, 6
+ bpf_mov R3, 7
+ bpf_mov R4, 8
+ bpf_mov R5, 9
+ bpf_call bar
+ bpf_add R0, R7
+ bpf_exit
+
+ After JIT to x86_64 may look like::
+
+ push %rbp
+ mov %rsp,%rbp
+ sub $0x228,%rsp
+ mov %rbx,-0x228(%rbp)
+ mov %r13,-0x220(%rbp)
+ mov %rdi,%rbx
+ mov $0x2,%esi
+ mov $0x3,%edx
+ mov $0x4,%ecx
+ mov $0x5,%r8d
+ callq foo
+ mov %rax,%r13
+ mov %rbx,%rdi
+ mov $0x6,%esi
+ mov $0x7,%edx
+ mov $0x8,%ecx
+ mov $0x9,%r8d
+ callq bar
+ add %r13,%rax
+ mov -0x228(%rbp),%rbx
+ mov -0x220(%rbp),%r13
+ leaveq
+ retq
+
+ Which is in this example equivalent in C to::
+
+ u64 bpf_filter(u64 ctx)
+ {
+ return foo(ctx, 2, 3, 4, 5) + bar(ctx, 6, 7, 8, 9);
+ }
+
+ In-kernel functions foo() and bar() with prototype: u64 (*)(u64 arg1, u64
+ arg2, u64 arg3, u64 arg4, u64 arg5); will receive arguments in proper
+ registers and place their return value into ``%rax`` which is R0 in eBPF.
+ Prologue and epilogue are emitted by JIT and are implicit in the
+ interpreter. R0-R5 are scratch registers, so eBPF program needs to preserve
+ them across the calls as defined by calling convention.
+
+ For example the following program is invalid::
+
+ bpf_mov R1, 1
+ bpf_call foo
+ bpf_mov R0, R1
+ bpf_exit
+
+ After the call the registers R1-R5 contain junk values and cannot be read.
+ An in-kernel verifier.rst is used to validate eBPF programs.
+
+Also in the new design, eBPF is limited to 4096 insns, which means that any
+program will terminate quickly and will only call a fixed number of kernel
+functions. Original BPF and eBPF are two operand instructions,
+which helps to do one-to-one mapping between eBPF insn and x86 insn during JIT.
+
+The input context pointer for invoking the interpreter function is generic,
+its content is defined by a specific use case. For seccomp register R1 points
+to seccomp_data, for converted BPF filters R1 points to a skb.
+
+A program, that is translated internally consists of the following elements::
+
+ op:16, jt:8, jf:8, k:32 ==> op:8, dst_reg:4, src_reg:4, off:16, imm:32
+
+So far 87 eBPF instructions were implemented. 8-bit 'op' opcode field
+has room for new instructions. Some of them may use 16/24/32 byte encoding. New
+instructions must be multiple of 8 bytes to preserve backward compatibility.
+
+eBPF is a general purpose RISC instruction set. Not every register and
+every instruction are used during translation from original BPF to eBPF.
+For example, socket filters are not using ``exclusive add`` instruction, but
+tracing filters may do to maintain counters of events, for example. Register R9
+is not used by socket filters either, but more complex filters may be running
+out of registers and would have to resort to spill/fill to stack.
+
+eBPF can be used as a generic assembler for last step performance
+optimizations, socket filters and seccomp are using it as assembler. Tracing
+filters may use it as assembler to generate code from kernel. In kernel usage
+may not be bounded by security considerations, since generated eBPF code
+may be optimizing internal code path and not being exposed to the user space.
+Safety of eBPF can come from the verifier.rst. In such use cases as
+described, it may be used as safe instruction set.
+
+Just like the original BPF, eBPF runs within a controlled environment,
+is deterministic and the kernel can easily prove that. The safety of the program
+can be determined in two steps: first step does depth-first-search to disallow
+loops and other CFG validation; second step starts from the first insn and
+descends all possible paths. It simulates execution of every insn and observes
+the state change of registers and stack.
+
+opcode encoding
+===============
+
+eBPF is reusing most of the opcode encoding from classic to simplify conversion
+of classic BPF to eBPF.
+
+For arithmetic and jump instructions the 8-bit 'code' field is divided into three
+parts::
+
+ +----------------+--------+--------------------+
+ | 4 bits | 1 bit | 3 bits |
+ | operation code | source | instruction class |
+ +----------------+--------+--------------------+
+ (MSB) (LSB)
+
+Three LSB bits store instruction class which is one of:
+
+ =================== ===============
+ Classic BPF classes eBPF classes
+ =================== ===============
+ BPF_LD 0x00 BPF_LD 0x00
+ BPF_LDX 0x01 BPF_LDX 0x01
+ BPF_ST 0x02 BPF_ST 0x02
+ BPF_STX 0x03 BPF_STX 0x03
+ BPF_ALU 0x04 BPF_ALU 0x04
+ BPF_JMP 0x05 BPF_JMP 0x05
+ BPF_RET 0x06 BPF_JMP32 0x06
+ BPF_MISC 0x07 BPF_ALU64 0x07
+ =================== ===============
+
+The 4th bit encodes the source operand ...
+
+ ::
+
+ BPF_K 0x00
+ BPF_X 0x08
+
+ * in classic BPF, this means::
+
+ BPF_SRC(code) == BPF_X - use register X as source operand
+ BPF_SRC(code) == BPF_K - use 32-bit immediate as source operand
+
+ * in eBPF, this means::
+
+ BPF_SRC(code) == BPF_X - use 'src_reg' register as source operand
+ BPF_SRC(code) == BPF_K - use 32-bit immediate as source operand
+
+... and four MSB bits store operation code.
+
+If BPF_CLASS(code) == BPF_ALU or BPF_ALU64 [ in eBPF ], BPF_OP(code) is one of::
+
+ BPF_ADD 0x00
+ BPF_SUB 0x10
+ BPF_MUL 0x20
+ BPF_DIV 0x30
+ BPF_OR 0x40
+ BPF_AND 0x50
+ BPF_LSH 0x60
+ BPF_RSH 0x70
+ BPF_NEG 0x80
+ BPF_MOD 0x90
+ BPF_XOR 0xa0
+ BPF_MOV 0xb0 /* eBPF only: mov reg to reg */
+ BPF_ARSH 0xc0 /* eBPF only: sign extending shift right */
+ BPF_END 0xd0 /* eBPF only: endianness conversion */
+
+If BPF_CLASS(code) == BPF_JMP or BPF_JMP32 [ in eBPF ], BPF_OP(code) is one of::
+
+ BPF_JA 0x00 /* BPF_JMP only */
+ BPF_JEQ 0x10
+ BPF_JGT 0x20
+ BPF_JGE 0x30
+ BPF_JSET 0x40
+ BPF_JNE 0x50 /* eBPF only: jump != */
+ BPF_JSGT 0x60 /* eBPF only: signed '>' */
+ BPF_JSGE 0x70 /* eBPF only: signed '>=' */
+ BPF_CALL 0x80 /* eBPF BPF_JMP only: function call */
+ BPF_EXIT 0x90 /* eBPF BPF_JMP only: function return */
+ BPF_JLT 0xa0 /* eBPF only: unsigned '<' */
+ BPF_JLE 0xb0 /* eBPF only: unsigned '<=' */
+ BPF_JSLT 0xc0 /* eBPF only: signed '<' */
+ BPF_JSLE 0xd0 /* eBPF only: signed '<=' */
+
+So BPF_ADD | BPF_X | BPF_ALU means 32-bit addition in both classic BPF
+and eBPF. There are only two registers in classic BPF, so it means A += X.
+In eBPF it means dst_reg = (u32) dst_reg + (u32) src_reg; similarly,
+BPF_XOR | BPF_K | BPF_ALU means A ^= imm32 in classic BPF and analogous
+src_reg = (u32) src_reg ^ (u32) imm32 in eBPF.
+
+Classic BPF is using BPF_MISC class to represent A = X and X = A moves.
+eBPF is using BPF_MOV | BPF_X | BPF_ALU code instead. Since there are no
+BPF_MISC operations in eBPF, the class 7 is used as BPF_ALU64 to mean
+exactly the same operations as BPF_ALU, but with 64-bit wide operands
+instead. So BPF_ADD | BPF_X | BPF_ALU64 means 64-bit addition, i.e.:
+dst_reg = dst_reg + src_reg
+
+Classic BPF wastes the whole BPF_RET class to represent a single ``ret``
+operation. Classic BPF_RET | BPF_K means copy imm32 into return register
+and perform function exit. eBPF is modeled to match CPU, so BPF_JMP | BPF_EXIT
+in eBPF means function exit only. The eBPF program needs to store return
+value into register R0 before doing a BPF_EXIT. Class 6 in eBPF is used as
+BPF_JMP32 to mean exactly the same operations as BPF_JMP, but with 32-bit wide
+operands for the comparisons instead.
+
+For load and store instructions the 8-bit 'code' field is divided as::
+
+ +--------+--------+-------------------+
+ | 3 bits | 2 bits | 3 bits |
+ | mode | size | instruction class |
+ +--------+--------+-------------------+
+ (MSB) (LSB)
+
+Size modifier is one of ...
+
+::
+
+ BPF_W 0x00 /* word */
+ BPF_H 0x08 /* half word */
+ BPF_B 0x10 /* byte */
+ BPF_DW 0x18 /* eBPF only, double word */
+
+... which encodes size of load/store operation::
+
+ B - 1 byte
+ H - 2 byte
+ W - 4 byte
+ DW - 8 byte (eBPF only)
+
+Mode modifier is one of::
+
+ BPF_IMM 0x00 /* used for 32-bit mov in classic BPF and 64-bit in eBPF */
+ BPF_ABS 0x20
+ BPF_IND 0x40
+ BPF_MEM 0x60
+ BPF_LEN 0x80 /* classic BPF only, reserved in eBPF */
+ BPF_MSH 0xa0 /* classic BPF only, reserved in eBPF */
+ BPF_ATOMIC 0xc0 /* eBPF only, atomic operations */
diff --git a/Documentation/bpf/index.rst b/Documentation/bpf/index.rst
index 91ba5a62026b..ef5c996547ec 100644
--- a/Documentation/bpf/index.rst
+++ b/Documentation/bpf/index.rst
@@ -21,6 +21,7 @@ that goes into great technical depth about the BPF Architecture.
helpers
programs
maps
+ classic_vs_extended.rst
bpf_licensing
test_debug
other
diff --git a/Documentation/bpf/instruction-set.rst b/Documentation/bpf/instruction-set.rst
index fa7cba59031e..1af51143ff9f 100644
--- a/Documentation/bpf/instruction-set.rst
+++ b/Documentation/bpf/instruction-set.rst
@@ -3,296 +3,68 @@
eBPF Instruction Set
====================
-eBPF is designed to be JITed with one to one mapping, which can also open up
-the possibility for GCC/LLVM compilers to generate optimized eBPF code through
-an eBPF backend that performs almost as fast as natively compiled code.
-
-Some core changes of the eBPF format from classic BPF:
-
-- Number of registers increase from 2 to 10:
-
- The old format had two registers A and X, and a hidden frame pointer. The
- new layout extends this to be 10 internal registers and a read-only frame
- pointer. Since 64-bit CPUs are passing arguments to functions via registers
- the number of args from eBPF program to in-kernel function is restricted
- to 5 and one register is used to accept return value from an in-kernel
- function. Natively, x86_64 passes first 6 arguments in registers, aarch64/
- sparcv9/mips64 have 7 - 8 registers for arguments; x86_64 has 6 callee saved
- registers, and aarch64/sparcv9/mips64 have 11 or more callee saved registers.
-
- Therefore, eBPF calling convention is defined as:
-
- * R0 - return value from in-kernel function, and exit value for eBPF program
- * R1 - R5 - arguments from eBPF program to in-kernel function
- * R6 - R9 - callee saved registers that in-kernel function will preserve
- * R10 - read-only frame pointer to access stack
-
- Thus, all eBPF registers map one to one to HW registers on x86_64, aarch64,
- etc, and eBPF calling convention maps directly to ABIs used by the kernel on
- 64-bit architectures.
-
- On 32-bit architectures JIT may map programs that use only 32-bit arithmetic
- and may let more complex programs to be interpreted.
-
- R0 - R5 are scratch registers and eBPF program needs spill/fill them if
- necessary across calls. Note that there is only one eBPF program (== one
- eBPF main routine) and it cannot call other eBPF functions, it can only
- call predefined in-kernel functions, though.
-
-- Register width increases from 32-bit to 64-bit:
-
- Still, the semantics of the original 32-bit ALU operations are preserved
- via 32-bit subregisters. All eBPF registers are 64-bit with 32-bit lower
- subregisters that zero-extend into 64-bit if they are being written to.
- That behavior maps directly to x86_64 and arm64 subregister definition, but
- makes other JITs more difficult.
-
- 32-bit architectures run 64-bit eBPF programs via interpreter.
- Their JITs may convert BPF programs that only use 32-bit subregisters into
- native instruction set and let the rest being interpreted.
-
- Operation is 64-bit, because on 64-bit architectures, pointers are also
- 64-bit wide, and we want to pass 64-bit values in/out of kernel functions,
- so 32-bit eBPF registers would otherwise require to define register-pair
- ABI, thus, there won't be able to use a direct eBPF register to HW register
- mapping and JIT would need to do combine/split/move operations for every
- register in and out of the function, which is complex, bug prone and slow.
- Another reason is the use of atomic 64-bit counters.
-
-- Conditional jt/jf targets replaced with jt/fall-through:
-
- While the original design has constructs such as ``if (cond) jump_true;
- else jump_false;``, they are being replaced into alternative constructs like
- ``if (cond) jump_true; /* else fall-through */``.
-
-- Introduces bpf_call insn and register passing convention for zero overhead
- calls from/to other kernel functions:
-
- Before an in-kernel function call, the eBPF program needs to
- place function arguments into R1 to R5 registers to satisfy calling
- convention, then the interpreter will take them from registers and pass
- to in-kernel function. If R1 - R5 registers are mapped to CPU registers
- that are used for argument passing on given architecture, the JIT compiler
- doesn't need to emit extra moves. Function arguments will be in the correct
- registers and BPF_CALL instruction will be JITed as single 'call' HW
- instruction. This calling convention was picked to cover common call
- situations without performance penalty.
-
- After an in-kernel function call, R1 - R5 are reset to unreadable and R0 has
- a return value of the function. Since R6 - R9 are callee saved, their state
- is preserved across the call.
-
- For example, consider three C functions::
-
- u64 f1() { return (*_f2)(1); }
- u64 f2(u64 a) { return f3(a + 1, a); }
- u64 f3(u64 a, u64 b) { return a - b; }
-
- GCC can compile f1, f3 into x86_64::
-
- f1:
- movl $1, %edi
- movq _f2(%rip), %rax
- jmp *%rax
- f3:
- movq %rdi, %rax
- subq %rsi, %rax
- ret
-
- Function f2 in eBPF may look like::
-
- f2:
- bpf_mov R2, R1
- bpf_add R1, 1
- bpf_call f3
- bpf_exit
-
- If f2 is JITed and the pointer stored to ``_f2``. The calls f1 -> f2 -> f3 and
- returns will be seamless. Without JIT, __bpf_prog_run() interpreter needs to
- be used to call into f2.
-
- For practical reasons all eBPF programs have only one argument 'ctx' which is
- already placed into R1 (e.g. on __bpf_prog_run() startup) and the programs
- can call kernel functions with up to 5 arguments. Calls with 6 or more arguments
- are currently not supported, but these restrictions can be lifted if necessary
- in the future.
-
- On 64-bit architectures all register map to HW registers one to one. For
- example, x86_64 JIT compiler can map them as ...
-
- ::
-
- R0 - rax
- R1 - rdi
- R2 - rsi
- R3 - rdx
- R4 - rcx
- R5 - r8
- R6 - rbx
- R7 - r13
- R8 - r14
- R9 - r15
- R10 - rbp
-
- ... since x86_64 ABI mandates rdi, rsi, rdx, rcx, r8, r9 for argument passing
- and rbx, r12 - r15 are callee saved.
-
- Then the following eBPF pseudo-program::
-
- bpf_mov R6, R1 /* save ctx */
- bpf_mov R2, 2
- bpf_mov R3, 3
- bpf_mov R4, 4
- bpf_mov R5, 5
- bpf_call foo
- bpf_mov R7, R0 /* save foo() return value */
- bpf_mov R1, R6 /* restore ctx for next call */
- bpf_mov R2, 6
- bpf_mov R3, 7
- bpf_mov R4, 8
- bpf_mov R5, 9
- bpf_call bar
- bpf_add R0, R7
- bpf_exit
-
- After JIT to x86_64 may look like::
-
- push %rbp
- mov %rsp,%rbp
- sub $0x228,%rsp
- mov %rbx,-0x228(%rbp)
- mov %r13,-0x220(%rbp)
- mov %rdi,%rbx
- mov $0x2,%esi
- mov $0x3,%edx
- mov $0x4,%ecx
- mov $0x5,%r8d
- callq foo
- mov %rax,%r13
- mov %rbx,%rdi
- mov $0x6,%esi
- mov $0x7,%edx
- mov $0x8,%ecx
- mov $0x9,%r8d
- callq bar
- add %r13,%rax
- mov -0x228(%rbp),%rbx
- mov -0x220(%rbp),%r13
- leaveq
- retq
-
- Which is in this example equivalent in C to::
-
- u64 bpf_filter(u64 ctx)
- {
- return foo(ctx, 2, 3, 4, 5) + bar(ctx, 6, 7, 8, 9);
- }
-
- In-kernel functions foo() and bar() with prototype: u64 (*)(u64 arg1, u64
- arg2, u64 arg3, u64 arg4, u64 arg5); will receive arguments in proper
- registers and place their return value into ``%rax`` which is R0 in eBPF.
- Prologue and epilogue are emitted by JIT and are implicit in the
- interpreter. R0-R5 are scratch registers, so eBPF program needs to preserve
- them across the calls as defined by calling convention.
-
- For example the following program is invalid::
-
- bpf_mov R1, 1
- bpf_call foo
- bpf_mov R0, R1
- bpf_exit
-
- After the call the registers R1-R5 contain junk values and cannot be read.
- An in-kernel `eBPF verifier`_ is used to validate eBPF programs.
-
-Also in the new design, eBPF is limited to 4096 insns, which means that any
-program will terminate quickly and will only call a fixed number of kernel
-functions. Original BPF and eBPF are two operand instructions,
-which helps to do one-to-one mapping between eBPF insn and x86 insn during JIT.
-
-The input context pointer for invoking the interpreter function is generic,
-its content is defined by a specific use case. For seccomp register R1 points
-to seccomp_data, for converted BPF filters R1 points to a skb.
-
-A program, that is translated internally consists of the following elements::
-
- op:16, jt:8, jf:8, k:32 ==> op:8, dst_reg:4, src_reg:4, off:16, imm:32
-
-So far 87 eBPF instructions were implemented. 8-bit 'op' opcode field
-has room for new instructions. Some of them may use 16/24/32 byte encoding. New
-instructions must be multiple of 8 bytes to preserve backward compatibility.
-
-eBPF is a general purpose RISC instruction set. Not every register and
-every instruction are used during translation from original BPF to eBPF.
-For example, socket filters are not using ``exclusive add`` instruction, but
-tracing filters may do to maintain counters of events, for example. Register R9
-is not used by socket filters either, but more complex filters may be running
-out of registers and would have to resort to spill/fill to stack.
-
-eBPF can be used as a generic assembler for last step performance
-optimizations, socket filters and seccomp are using it as assembler. Tracing
-filters may use it as assembler to generate code from kernel. In kernel usage
-may not be bounded by security considerations, since generated eBPF code
-may be optimizing internal code path and not being exposed to the user space.
-Safety of eBPF can come from the `eBPF verifier`_. In such use cases as
-described, it may be used as safe instruction set.
-
-Just like the original BPF, eBPF runs within a controlled environment,
-is deterministic and the kernel can easily prove that. The safety of the program
-can be determined in two steps: first step does depth-first-search to disallow
-loops and other CFG validation; second step starts from the first insn and
-descends all possible paths. It simulates execution of every insn and observes
-the state change of registers and stack.
-
-eBPF opcode encoding
-====================
+Registers and calling convention
+================================
+
+eBPF has 10 general purpose registers and a read-only frame pointer register,
+all of which are 64-bits wide.
-eBPF is reusing most of the opcode encoding from classic to simplify conversion
-of classic BPF to eBPF. For arithmetic and jump instructions the 8-bit 'code'
-field is divided into three parts::
+The eBPF calling convention is defined as:
- +----------------+--------+--------------------+
- | 4 bits | 1 bit | 3 bits |
- | operation code | source | instruction class |
- +----------------+--------+--------------------+
- (MSB) (LSB)
+ * R0: return value from function calls, and exit value for eBPF programs
+ * R1 - R5: arguments for function calls
+ * R6 - R9: callee saved registers that function calls will preserve
+ * R10: read-only frame pointer to access stack
-Three LSB bits store instruction class which is one of:
+R0 - R5 are scratch registers and eBPF programs needs to spill/fill them if
+necessary across calls.
- =================== ===============
- Classic BPF classes eBPF classes
- =================== ===============
- BPF_LD 0x00 BPF_LD 0x00
- BPF_LDX 0x01 BPF_LDX 0x01
- BPF_ST 0x02 BPF_ST 0x02
- BPF_STX 0x03 BPF_STX 0x03
- BPF_ALU 0x04 BPF_ALU 0x04
- BPF_JMP 0x05 BPF_JMP 0x05
- BPF_RET 0x06 BPF_JMP32 0x06
- BPF_MISC 0x07 BPF_ALU64 0x07
- =================== ===============
+Instruction classes
+===================
-When BPF_CLASS(code) == BPF_ALU or BPF_JMP, 4th bit encodes source operand ...
+The three LSB bits of the 'opcode' field store the instruction class:
- ::
+ ========= =====
+ class value
+ ========= =====
+ BPF_LD 0x00
+ BPF_LDX 0x01
+ BPF_ST 0x02
+ BPF_STX 0x03
+ BPF_ALU 0x04
+ BPF_JMP 0x05
+ BPF_JMP32 0x06
+ BPF_ALU64 0x07
+ ========= =====
- BPF_K 0x00
- BPF_X 0x08
+Arithmetic and jump instructions
+================================
- * in classic BPF, this means::
+For arithmetic and jump instructions (BPF_ALU, BPF_ALU64, BPF_JMP and
+BPF_JMP32), the 8-bit 'opcode' field is divided into three parts:
- BPF_SRC(code) == BPF_X - use register X as source operand
- BPF_SRC(code) == BPF_K - use 32-bit immediate as source operand
+ ============== ====== =================
+ 4 bits (MSB) 1 bit 3 bits (LSB)
+ ============== ====== =================
+ operation code source instruction class
+ ============== ====== =================
- * in eBPF, this means::
+The 4th bit encodes the source operand:
- BPF_SRC(code) == BPF_X - use 'src_reg' register as source operand
- BPF_SRC(code) == BPF_K - use 32-bit immediate as source operand
+ ====== ===== ========================================
+ source value description
+ ====== ===== ========================================
+ BPF_K 0x00 use 32-bit immediate as source operand
+ BPF_X 0x08 use 'src_reg' register as source operand
+ ====== ===== ========================================
-... and four MSB bits store operation code.
+The four MSB bits store the operation code.
-If BPF_CLASS(code) == BPF_ALU or BPF_ALU64 [ in eBPF ], BPF_OP(code) is one of::
+For class BPF_ALU or BPF_ALU64:
+ ======== ===== =========================
+ code value description
+ ======== ===== =========================
BPF_ADD 0x00
BPF_SUB 0x10
BPF_MUL 0x20
@@ -304,116 +76,105 @@ If BPF_CLASS(code) == BPF_ALU or BPF_ALU64 [ in eBPF ], BPF_OP(code) is one of::
BPF_NEG 0x80
BPF_MOD 0x90
BPF_XOR 0xa0
- BPF_MOV 0xb0 /* eBPF only: mov reg to reg */
- BPF_ARSH 0xc0 /* eBPF only: sign extending shift right */
- BPF_END 0xd0 /* eBPF only: endianness conversion */
+ BPF_MOV 0xb0 mov reg to reg
+ BPF_ARSH 0xc0 sign extending shift right
+ BPF_END 0xd0 endianness conversion
+ ======== ===== =========================
-If BPF_CLASS(code) == BPF_JMP or BPF_JMP32 [ in eBPF ], BPF_OP(code) is one of::
+For class BPF_JMP or BPF_JMP32:
- BPF_JA 0x00 /* BPF_JMP only */
+ ======== ===== =========================
+ code value description
+ ======== ===== =========================
+ BPF_JA 0x00 BPF_JMP only
BPF_JEQ 0x10
BPF_JGT 0x20
BPF_JGE 0x30
BPF_JSET 0x40
- BPF_JNE 0x50 /* eBPF only: jump != */
- BPF_JSGT 0x60 /* eBPF only: signed '>' */
- BPF_JSGE 0x70 /* eBPF only: signed '>=' */
- BPF_CALL 0x80 /* eBPF BPF_JMP only: function call */
- BPF_EXIT 0x90 /* eBPF BPF_JMP only: function return */
- BPF_JLT 0xa0 /* eBPF only: unsigned '<' */
- BPF_JLE 0xb0 /* eBPF only: unsigned '<=' */
- BPF_JSLT 0xc0 /* eBPF only: signed '<' */
- BPF_JSLE 0xd0 /* eBPF only: signed '<=' */
-
-So BPF_ADD | BPF_X | BPF_ALU means 32-bit addition in both classic BPF
-and eBPF. There are only two registers in classic BPF, so it means A += X.
-In eBPF it means dst_reg = (u32) dst_reg + (u32) src_reg; similarly,
-BPF_XOR | BPF_K | BPF_ALU means A ^= imm32 in classic BPF and analogous
-src_reg = (u32) src_reg ^ (u32) imm32 in eBPF.
-
-Classic BPF is using BPF_MISC class to represent A = X and X = A moves.
-eBPF is using BPF_MOV | BPF_X | BPF_ALU code instead. Since there are no
-BPF_MISC operations in eBPF, the class 7 is used as BPF_ALU64 to mean
-exactly the same operations as BPF_ALU, but with 64-bit wide operands
-instead. So BPF_ADD | BPF_X | BPF_ALU64 means 64-bit addition, i.e.:
-dst_reg = dst_reg + src_reg
-
-Classic BPF wastes the whole BPF_RET class to represent a single ``ret``
-operation. Classic BPF_RET | BPF_K means copy imm32 into return register
-and perform function exit. eBPF is modeled to match CPU, so BPF_JMP | BPF_EXIT
-in eBPF means function exit only. The eBPF program needs to store return
-value into register R0 before doing a BPF_EXIT. Class 6 in eBPF is used as
-BPF_JMP32 to mean exactly the same operations as BPF_JMP, but with 32-bit wide
-operands for the comparisons instead.
+ BPF_JNE 0x50 jump '!='
+ BPF_JSGT 0x60 signed '>'
+ BPF_JSGE 0x70 signed '>='
+ BPF_CALL 0x80 function call
+ BPF_EXIT 0x90 function return
+ BPF_JLT 0xa0 unsigned '<'
+ BPF_JLE 0xb0 unsigned '<='
+ BPF_JSLT 0xc0 signed '<'
+ BPF_JSLE 0xd0 signed '<='
+ ======== ===== =========================
-For load and store instructions the 8-bit 'code' field is divided as::
+So BPF_ADD | BPF_X | BPF_ALU means::
- +--------+--------+-------------------+
- | 3 bits | 2 bits | 3 bits |
- | mode | size | instruction class |
- +--------+--------+-------------------+
- (MSB) (LSB)
+ dst_reg = (u32) dst_reg + (u32) src_reg;
-Size modifier is one of ...
+Similarly, BPF_XOR | BPF_K | BPF_ALU means::
-::
+ src_reg = (u32) src_reg ^ (u32) imm32
- BPF_W 0x00 /* word */
- BPF_H 0x08 /* half word */
- BPF_B 0x10 /* byte */
- BPF_DW 0x18 /* eBPF only, double word */
+eBPF is using BPF_MOV | BPF_X | BPF_ALU to represent A = B moves. BPF_ALU64
+is used to mean exactly the same operations as BPF_ALU, but with 64-bit wide
+operands instead. So BPF_ADD | BPF_X | BPF_ALU64 means 64-bit addition, i.e.::
-... which encodes size of load/store operation::
+ dst_reg = dst_reg + src_reg
- B - 1 byte
- H - 2 byte
- W - 4 byte
- DW - 8 byte (eBPF only)
+BPF_JMP | BPF_EXIT means function exit only. The eBPF program needs to store
+the return value into register R0 before doing a BPF_EXIT. Class 6 is used as
+BPF_JMP32 to mean exactly the same operations as BPF_JMP, but with 32-bit wide
+operands for the comparisons instead.
-Mode modifier is one of::
- BPF_IMM 0x00 /* used for 32-bit mov in classic BPF and 64-bit in eBPF */
- BPF_ABS 0x20
- BPF_IND 0x40
- BPF_MEM 0x60
- BPF_LEN 0x80 /* classic BPF only, reserved in eBPF */
- BPF_MSH 0xa0 /* classic BPF only, reserved in eBPF */
- BPF_ATOMIC 0xc0 /* eBPF only, atomic operations */
+Load and store instructions
+===========================
-eBPF has two non-generic instructions: (BPF_ABS | <size> | BPF_LD) and
-(BPF_IND | <size> | BPF_LD) which are used to access packet data.
+For load and store instructions (BPF_LD, BPF_LDX, BPF_ST and BPF_STX), the
+8-bit 'opcode' field is divided as:
-They had to be carried over from classic to have strong performance of
-socket filters running in eBPF interpreter. These instructions can only
-be used when interpreter context is a pointer to ``struct sk_buff`` and
-have seven implicit operands. Register R6 is an implicit input that must
-contain pointer to sk_buff. Register R0 is an implicit output which contains
-the data fetched from the packet. Registers R1-R5 are scratch registers
-and must not be used to store the data across BPF_ABS | BPF_LD or
-BPF_IND | BPF_LD instructions.
+ ============ ====== =================
+ 3 bits (MSB) 2 bits 3 bits (LSB)
+ ============ ====== =================
+ mode size instruction class
+ ============ ====== =================
-These instructions have implicit program exit condition as well. When
-eBPF program is trying to access the data beyond the packet boundary,
-the interpreter will abort the execution of the program. JIT compilers
-therefore must preserve this property. src_reg and imm32 fields are
-explicit inputs to these instructions.
+The size modifier is one of:
+
+ ============= ===== =====================
+ size modifier value description
+ ============= ===== =====================
+ BPF_W 0x00 word (4 bytes)
+ BPF_H 0x08 half word (2 bytes)
+ BPF_B 0x10 byte
+ BPF_DW 0x18 double word (8 bytes)
+ ============= ===== =====================
+
+The mode modifier is one of:
+
+ ============= ===== =====================
+ mode modifier value description
+ ============= ===== =====================
+ BPF_IMM 0x00 used for 64-bit mov
+ BPF_ABS 0x20
+ BPF_IND 0x40
+ BPF_MEM 0x60
+ BPF_ATOMIC 0xc0 atomic operations
+ ============= ===== =====================
-For example::
+BPF_MEM | <size> | BPF_STX means::
- BPF_IND | BPF_W | BPF_LD means:
+ *(size *) (dst_reg + off) = src_reg
- R0 = ntohl(*(u32 *) (((struct sk_buff *) R6)->data + src_reg + imm32))
- and R1 - R5 were scratched.
+BPF_MEM | <size> | BPF_ST means::
-Unlike classic BPF instruction set, eBPF has generic load/store operations::
+ *(size *) (dst_reg + off) = imm32
- BPF_MEM | <size> | BPF_STX: *(size *) (dst_reg + off) = src_reg
- BPF_MEM | <size> | BPF_ST: *(size *) (dst_reg + off) = imm32
- BPF_MEM | <size> | BPF_LDX: dst_reg = *(size *) (src_reg + off)
+BPF_MEM | <size> | BPF_LDX means::
+
+ dst_reg = *(size *) (src_reg + off)
Where size is one of: BPF_B or BPF_H or BPF_W or BPF_DW.
-It also includes atomic operations, which use the immediate field for extra
+Atomic operations
+-----------------
+
+eBPF includes atomic operations, which use the immediate field for extra
encoding::
.imm = BPF_ADD, .code = BPF_ATOMIC | BPF_W | BPF_STX: lock xadd *(u32 *)(dst_reg + off16) += src_reg
@@ -457,11 +218,36 @@ You may encounter ``BPF_XADD`` - this is a legacy name for ``BPF_ATOMIC``,
referring to the exclusive-add operation encoded when the immediate field is
zero.
+16-byte instructions
+--------------------
+
eBPF has one 16-byte instruction: ``BPF_LD | BPF_DW | BPF_IMM`` which consists
of two consecutive ``struct bpf_insn`` 8-byte blocks and interpreted as single
instruction that loads 64-bit immediate value into a dst_reg.
-Classic BPF has similar instruction: ``BPF_LD | BPF_W | BPF_IMM`` which loads
-32-bit immediate value into a register.
-.. Links:
-.. _eBPF verifier: verifiers.rst
+Packet access instructions
+--------------------------
+
+eBPF has two non-generic instructions: (BPF_ABS | <size> | BPF_LD) and
+(BPF_IND | <size> | BPF_LD) which are used to access packet data.
+
+They had to be carried over from classic BPF to have strong performance of
+socket filters running in eBPF interpreter. These instructions can only
+be used when interpreter context is a pointer to ``struct sk_buff`` and
+have seven implicit operands. Register R6 is an implicit input that must
+contain pointer to sk_buff. Register R0 is an implicit output which contains
+the data fetched from the packet. Registers R1-R5 are scratch registers
+and must not be used to store the data across BPF_ABS | BPF_LD or
+BPF_IND | BPF_LD instructions.
+
+These instructions have implicit program exit condition as well. When
+eBPF program is trying to access the data beyond the packet boundary,
+the interpreter will abort the execution of the program. JIT compilers
+therefore must preserve this property. src_reg and imm32 fields are
+explicit inputs to these instructions.
+
+For example, BPF_IND | BPF_W | BPF_LD means::
+
+ R0 = ntohl(*(u32 *) (((struct sk_buff *) R6)->data + src_reg + imm32))
+
+and R1 - R5 are clobbered.
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index da36d13ffc16..082793d497ec 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -9,6 +9,7 @@
#define KMSG_COMPONENT "hugetlb"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+#include <asm/pgalloc.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/mman.h>
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index c1205414de10..ce1f86f245c9 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1976,7 +1976,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
void *orig_call)
{
int ret, i, nr_args = m->nr_args;
- int stack_size = nr_args * 8;
+ int regs_off, ip_off, args_off, stack_size = nr_args * 8;
struct bpf_tramp_progs *fentry = &tprogs[BPF_TRAMP_FENTRY];
struct bpf_tramp_progs *fexit = &tprogs[BPF_TRAMP_FEXIT];
struct bpf_tramp_progs *fmod_ret = &tprogs[BPF_TRAMP_MODIFY_RETURN];
@@ -1991,14 +1991,39 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
if (!is_valid_bpf_tramp_flags(flags))
return -EINVAL;
+ /* Generated trampoline stack layout:
+ *
+ * RBP + 8 [ return address ]
+ * RBP + 0 [ RBP ]
+ *
+ * RBP - 8 [ return value ] BPF_TRAMP_F_CALL_ORIG or
+ * BPF_TRAMP_F_RET_FENTRY_RET flags
+ *
+ * [ reg_argN ] always
+ * [ ... ]
+ * RBP - regs_off [ reg_arg1 ] program's ctx pointer
+ *
+ * RBP - args_off [ args count ] always
+ *
+ * RBP - ip_off [ traced function ] BPF_TRAMP_F_IP_ARG flag
+ */
+
/* room for return value of orig_call or fentry prog */
save_ret = flags & (BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_RET_FENTRY_RET);
if (save_ret)
stack_size += 8;
+ regs_off = stack_size;
+
+ /* args count */
+ stack_size += 8;
+ args_off = stack_size;
+
if (flags & BPF_TRAMP_F_IP_ARG)
stack_size += 8; /* room for IP address argument */
+ ip_off = stack_size;
+
if (flags & BPF_TRAMP_F_SKIP_FRAME)
/* skip patched call instruction and point orig_call to actual
* body of the kernel function.
@@ -2012,23 +2037,25 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
EMIT4(0x48, 0x83, 0xEC, stack_size); /* sub rsp, stack_size */
EMIT1(0x53); /* push rbx */
+ /* Store number of arguments of the traced function:
+ * mov rax, nr_args
+ * mov QWORD PTR [rbp - args_off], rax
+ */
+ emit_mov_imm64(&prog, BPF_REG_0, 0, (u32) nr_args);
+ emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -args_off);
+
if (flags & BPF_TRAMP_F_IP_ARG) {
/* Store IP address of the traced function:
* mov rax, QWORD PTR [rbp + 8]
* sub rax, X86_PATCH_SIZE
- * mov QWORD PTR [rbp - stack_size], rax
+ * mov QWORD PTR [rbp - ip_off], rax
*/
emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, 8);
EMIT4(0x48, 0x83, 0xe8, X86_PATCH_SIZE);
- emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -stack_size);
-
- /* Continue with stack_size for regs storage, stack will
- * be correctly restored with 'leave' instruction.
- */
- stack_size -= 8;
+ emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -ip_off);
}
- save_regs(m, &prog, nr_args, stack_size);
+ save_regs(m, &prog, nr_args, regs_off);
if (flags & BPF_TRAMP_F_CALL_ORIG) {
/* arg1: mov rdi, im */
@@ -2040,7 +2067,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
}
if (fentry->nr_progs)
- if (invoke_bpf(m, &prog, fentry, stack_size,
+ if (invoke_bpf(m, &prog, fentry, regs_off,
flags & BPF_TRAMP_F_RET_FENTRY_RET))
return -EINVAL;
@@ -2050,7 +2077,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
if (!branches)
return -ENOMEM;
- if (invoke_bpf_mod_ret(m, &prog, fmod_ret, stack_size,
+ if (invoke_bpf_mod_ret(m, &prog, fmod_ret, regs_off,
branches)) {
ret = -EINVAL;
goto cleanup;
@@ -2058,7 +2085,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
}
if (flags & BPF_TRAMP_F_CALL_ORIG) {
- restore_regs(m, &prog, nr_args, stack_size);
+ restore_regs(m, &prog, nr_args, regs_off);
/* call original function */
if (emit_call(&prog, orig_call, prog)) {
@@ -2088,13 +2115,13 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
}
if (fexit->nr_progs)
- if (invoke_bpf(m, &prog, fexit, stack_size, false)) {
+ if (invoke_bpf(m, &prog, fexit, regs_off, false)) {
ret = -EINVAL;
goto cleanup;
}
if (flags & BPF_TRAMP_F_RESTORE_REGS)
- restore_regs(m, &prog, nr_args, stack_size);
+ restore_regs(m, &prog, nr_args, regs_off);
/* This needs to be done regardless. If there were fmod_ret programs,
* the return value is only updated on the stack and still needs to be
diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c
index be04d74037d2..f7bf311d7910 100644
--- a/drivers/bluetooth/btqca.c
+++ b/drivers/bluetooth/btqca.c
@@ -6,6 +6,7 @@
*/
#include <linux/module.h>
#include <linux/firmware.h>
+#include <linux/vmalloc.h>
#include <net/bluetooth/bluetooth.h>
#include <net/bluetooth/hci_core.h>
diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c
index 0c98dd3dee67..b79f816a7203 100644
--- a/drivers/infiniband/core/cache.c
+++ b/drivers/infiniband/core/cache.c
@@ -33,6 +33,7 @@
* SOFTWARE.
*/
+#include <linux/if_vlan.h>
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/slab.h>
diff --git a/drivers/infiniband/hw/irdma/ctrl.c b/drivers/infiniband/hw/irdma/ctrl.c
index 7264f8c2f7d5..3141a9c85de5 100644
--- a/drivers/infiniband/hw/irdma/ctrl.c
+++ b/drivers/infiniband/hw/irdma/ctrl.c
@@ -1,5 +1,7 @@
// SPDX-License-Identifier: GPL-2.0 or Linux-OpenIB
/* Copyright (c) 2015 - 2021 Intel Corporation */
+#include <linux/etherdevice.h>
+
#include "osdep.h"
#include "status.h"
#include "hmc.h"
diff --git a/drivers/infiniband/hw/irdma/uda.c b/drivers/infiniband/hw/irdma/uda.c
index f5b1b6150cdc..7a9988ddbd01 100644
--- a/drivers/infiniband/hw/irdma/uda.c
+++ b/drivers/infiniband/hw/irdma/uda.c
@@ -1,5 +1,7 @@
// SPDX-License-Identifier: GPL-2.0 or Linux-OpenIB
/* Copyright (c) 2016 - 2021 Intel Corporation */
+#include <linux/etherdevice.h>
+
#include "osdep.h"
#include "status.h"
#include "hmc.h"
diff --git a/drivers/infiniband/hw/mlx5/doorbell.c b/drivers/infiniband/hw/mlx5/doorbell.c
index 6398e2f48579..e32111117a5e 100644
--- a/drivers/infiniband/hw/mlx5/doorbell.c
+++ b/drivers/infiniband/hw/mlx5/doorbell.c
@@ -32,6 +32,7 @@
#include <linux/kref.h>
#include <linux/slab.h>
+#include <linux/sched/mm.h>
#include <rdma/ib_umem.h>
#include "mlx5_ib.h"
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index e5abbcfc1d57..29475cf8c7c3 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -30,6 +30,7 @@
* SOFTWARE.
*/
+#include <linux/etherdevice.h>
#include <linux/module.h>
#include <rdma/ib_umem.h>
#include <rdma/ib_cache.h>
diff --git a/drivers/net/amt.c b/drivers/net/amt.c
index b732ee9a50ef..a1c7a8acd9c8 100644
--- a/drivers/net/amt.c
+++ b/drivers/net/amt.c
@@ -11,6 +11,7 @@
#include <linux/net.h>
#include <linux/igmp.h>
#include <linux/workqueue.h>
+#include <net/sch_generic.h>
#include <net/net_namespace.h>
#include <net/ip.h>
#include <net/udp.h>
diff --git a/drivers/net/appletalk/ipddp.c b/drivers/net/appletalk/ipddp.c
index 5566daefbff4..d558535390f9 100644
--- a/drivers/net/appletalk/ipddp.c
+++ b/drivers/net/appletalk/ipddp.c
@@ -23,6 +23,7 @@
* of the GNU General Public License, incorporated herein by reference.
*/
+#include <linux/compat.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/init.h>
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 1bb8fa9fd3aa..07fc603c2fa7 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -35,6 +35,7 @@
#include <linux/module.h>
#include <linux/types.h>
#include <linux/fcntl.h>
+#include <linux/filter.h>
#include <linux/interrupt.h>
#include <linux/ptrace.h>
#include <linux/ioport.h>
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c
index 876218752766..ac6772fe9746 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb.c
@@ -8,6 +8,7 @@
*
* Many thanks to Klaus Hitschler <klaus.hitschler@gmx.de>
*/
+#include <asm/unaligned.h>
#include <linux/netdevice.h>
#include <linux/usb.h>
#include <linux/module.h>
diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c
index 013e9c02be71..991b9c6b6ce7 100644
--- a/drivers/net/dsa/microchip/ksz8795.c
+++ b/drivers/net/dsa/microchip/ksz8795.c
@@ -10,6 +10,7 @@
#include <linux/delay.h>
#include <linux/export.h>
#include <linux/gpio.h>
+#include <linux/if_vlan.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/platform_data/microchip-ksz.h>
diff --git a/drivers/net/dsa/xrs700x/xrs700x.c b/drivers/net/dsa/xrs700x/xrs700x.c
index 35fa19ddaf19..0730352cdd57 100644
--- a/drivers/net/dsa/xrs700x/xrs700x.c
+++ b/drivers/net/dsa/xrs700x/xrs700x.c
@@ -5,6 +5,7 @@
*/
#include <net/dsa.h>
+#include <linux/etherdevice.h>
#include <linux/if_bridge.h>
#include <linux/of_device.h>
#include <linux/netdev_features.h>
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 7d5d885d85d5..3b46f1df5609 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -434,7 +434,7 @@ static int ena_xdp_execute(struct ena_ring *rx_ring, struct xdp_buff *xdp)
xdp_stat = &rx_ring->rx_stats.xdp_pass;
break;
default:
- bpf_warn_invalid_xdp_action(verdict);
+ bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, verdict);
xdp_stat = &rx_ring->rx_stats.xdp_invalid;
}
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index 0c39fc2fa345..9391c7101fba 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -14,6 +14,7 @@
#include <linux/interrupt.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
+#include <uapi/linux/bpf.h>
#include "ena_com.h"
#include "ena_eth_com.h"
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index 951c4c569a9b..4da31b1b84f9 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -9,6 +9,7 @@
#include <linux/pci.h>
#include <linux/netdevice.h>
+#include <linux/vmalloc.h>
#include <net/devlink.h>
#include "bnxt_hsi.h"
#include "bnxt.h"
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index c8083df5e0ab..52fad0fdeacf 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -195,7 +195,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
*event |= BNXT_REDIRECT_EVENT;
break;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(bp->dev, xdp_prog, act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(bp->dev, xdp_prog, act);
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 63191692f624..a04aa206fddc 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -590,7 +590,7 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog,
nicvf_xdp_sq_append_pkt(nic, sq, (u64)xdp.data, dma_addr, len);
return true;
default:
- bpf_warn_invalid_xdp_action(action);
+ bpf_warn_invalid_xdp_action(nic->netdev, prog, action);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(nic->netdev, prog, action);
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index 50bbe79fb93d..4367edbdd579 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -10,6 +10,7 @@
#include <linux/iommu.h>
#include <net/ip.h>
#include <net/tso.h>
+#include <uapi/linux/bpf.h>
#include "nic_reg.h"
#include "nic.h"
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index d6871437d951..c78883c3a2c8 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -2623,7 +2623,7 @@ static u32 dpaa_run_xdp(struct dpaa_priv *priv, struct qm_fd *fd, void *vaddr,
}
break;
default:
- bpf_warn_invalid_xdp_action(xdp_act);
+ bpf_warn_invalid_xdp_action(priv->net_dev, xdp_prog, xdp_act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(priv->net_dev, xdp_prog, xdp_act);
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 8e643567abce..d21ba70ef4a3 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -374,7 +374,7 @@ static u32 dpaa2_eth_run_xdp(struct dpaa2_eth_priv *priv,
dpaa2_eth_xdp_enqueue(priv, ch, fd, vaddr, rx_fq->flowid);
break;
default:
- bpf_warn_invalid_xdp_action(xdp_act);
+ bpf_warn_invalid_xdp_action(priv->net_dev, xdp_prog, xdp_act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(priv->net_dev, xdp_prog, xdp_act);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 504e12554079..eacb41f86bdb 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -1547,7 +1547,7 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
switch (xdp_act) {
default:
- bpf_warn_invalid_xdp_action(xdp_act);
+ bpf_warn_invalid_xdp_action(rx_ring->ndev, prog, xdp_act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(rx_ring->ndev, prog, xdp_act);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
index a984a7a6dd2e..8d59babbf476 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
@@ -4,6 +4,7 @@
* Copyright(c) 2017 Huawei Technologies Co., Ltd
*/
+#include <linux/if_vlan.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/u64_stats_sync.h>
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 9e3991caa5c9..66cc79500c10 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2322,7 +2322,7 @@ static int i40e_run_xdp(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
result = I40E_XDP_REDIR;
break;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, act);
fallthrough;
case XDP_ABORTED:
out_failure:
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index ea06e957393e..945b1bb9c6f4 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -176,7 +176,7 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
goto out_failure;
break;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, act);
fallthrough;
case XDP_ABORTED:
out_failure:
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
index ea88f4597a07..bb962987f300 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
@@ -22,7 +22,6 @@
struct i40e_vsi;
struct xsk_buff_pool;
-struct zero_copy_allocator;
int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair);
int i40e_queue_pair_enable(struct i40e_vsi *vsi, int queue_pair);
diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c
index 5aa18219920b..a230edb38466 100644
--- a/drivers/net/ethernet/intel/ice/ice_devlink.c
+++ b/drivers/net/ethernet/intel/ice/ice_devlink.c
@@ -1,6 +1,8 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2020, Intel Corporation. */
+#include <linux/vmalloc.h>
+
#include "ice.h"
#include "ice_lib.h"
#include "ice_devlink.h"
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 486fc5509d13..3e38695f1c9d 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -576,7 +576,7 @@ ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
goto out_failure;
return ICE_XDP_REDIR;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, act);
fallthrough;
case XDP_ABORTED:
out_failure:
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index 1dd7e84f41f8..9520b140bdbf 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -1,6 +1,8 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2019, Intel Corporation. */
+#include <linux/filter.h>
+
#include "ice_txrx_lib.h"
#include "ice_eswitch.h"
#include "ice_lib.h"
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index c895351b25e0..2388837d6d6c 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -481,7 +481,7 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
goto out_failure;
break;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, act);
fallthrough;
case XDP_ABORTED:
out_failure:
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 4603ae35fcab..38ba92022cd4 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -8500,7 +8500,7 @@ static struct sk_buff *igb_run_xdp(struct igb_adapter *adapter,
result = IGB_XDP_REDIR;
break;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(adapter->netdev, xdp_prog, act);
fallthrough;
case XDP_ABORTED:
out_failure:
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 453ef9f17162..2f17f36e94fd 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2241,7 +2241,7 @@ static int __igc_xdp_run_prog(struct igc_adapter *adapter,
return IGC_XDP_REDIRECT;
break;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(adapter->netdev, prog, act);
fallthrough;
case XDP_ABORTED:
out_failure:
diff --git a/drivers/net/ethernet/intel/igc/igc_xdp.c b/drivers/net/ethernet/intel/igc/igc_xdp.c
index a8cf5374be47..aeeb34e64610 100644
--- a/drivers/net/ethernet/intel/igc/igc_xdp.c
+++ b/drivers/net/ethernet/intel/igc/igc_xdp.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2020, Intel Corporation. */
+#include <linux/if_vlan.h>
#include <net/xdp_sock_drv.h>
#include "igc.h"
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 15095ac868d5..c6ff656b2476 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2235,7 +2235,7 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,
result = IXGBE_XDP_REDIR;
break;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, act);
fallthrough;
case XDP_ABORTED:
out_failure:
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h
index a82533f21d36..bba3feaf3318 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h
@@ -35,8 +35,6 @@ int ixgbe_xsk_pool_setup(struct ixgbe_adapter *adapter,
struct xsk_buff_pool *pool,
u16 qid);
-void ixgbe_zca_free(struct zero_copy_allocator *alloc, unsigned long handle);
-
bool ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 cleaned_count);
int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector,
struct ixgbe_ring *rx_ring,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
index db2bc58dfcfd..b3fd8e5cd85b 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -131,7 +131,7 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter,
goto out_failure;
break;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, act);
fallthrough;
case XDP_ABORTED:
out_failure:
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index ea73fb3026bc..0015fcf1df2b 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -1070,7 +1070,7 @@ static struct sk_buff *ixgbevf_run_xdp(struct ixgbevf_adapter *adapter,
goto out_failure;
break;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, act);
fallthrough;
case XDP_ABORTED:
out_failure:
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index e4c328f61188..83c8908f0cc7 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -2240,7 +2240,7 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
mvneta_xdp_put_buff(pp, rxq, xdp, sinfo, sync);
break;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(pp->dev, prog, act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(pp->dev, prog, act);
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 339ae274021e..7cdbf8b8bbf6 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -3823,7 +3823,7 @@ mvpp2_run_xdp(struct mvpp2_port *port, struct bpf_prog *prog,
}
break;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(port->dev, prog, act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(port->dev, prog, act);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
index 0cc6353254bf..7c4068c5d1ac 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
@@ -1198,7 +1198,7 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
put_page(page);
break;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(pfvf->netdev, prog, act);
break;
case XDP_ABORTED:
trace_xdp_exception(pfvf->netdev, prog, act);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index ad1e4caf48bf..c61dc7ae0c05 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -33,6 +33,7 @@
#include <linux/bpf.h>
#include <linux/etherdevice.h>
+#include <linux/filter.h>
#include <linux/tcp.h>
#include <linux/if_vlan.h>
#include <linux/delay.h>
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 650e6a1844ae..8cfc649f226b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -812,7 +812,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
trace_xdp_exception(dev, xdp_prog, act);
goto xdp_drop_no_cnt; /* Drop on xmit failure */
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(dev, xdp_prog, act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(dev, xdp_prog, act);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
index 50977f01a050..00449df98a5e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
/* Copyright (c) 2020, Mellanox Technologies inc. All rights reserved. */
+#include <net/sch_generic.h>
#include "en.h"
#include "params.h"
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 2f0df5cc1a2d..338d65e2c9ce 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -151,7 +151,7 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
rq->stats->xdp_redirect++;
return true;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(rq->netdev, prog, act);
fallthrough;
case XDP_ABORTED:
xdp_abort:
diff --git a/drivers/net/ethernet/microsoft/mana/mana_bpf.c b/drivers/net/ethernet/microsoft/mana/mana_bpf.c
index 1bc8ff388341..1d2f948b5c00 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_bpf.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_bpf.c
@@ -60,7 +60,7 @@ u32 mana_run_xdp(struct net_device *ndev, struct mana_rxq *rxq,
break;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(ndev, prog, act);
}
out:
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index d37d35885579..498d0f999275 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -1,6 +1,8 @@
// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
/* Copyright (c) 2021, Microsoft Corporation. */
+#include <uapi/linux/bpf.h>
+
#include <linux/inetdevice.h>
#include <linux/etherdevice.h>
#include <linux/ethtool.h>
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 6e38da4ad554..79257ec41987 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1944,7 +1944,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
xdp_prog, act);
continue;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(dp->netdev, xdp_prog, act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(dp->netdev, xdp_prog, act);
diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c
index 5ea9cb4311a1..b242000a77fd 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_fp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c
@@ -1153,7 +1153,7 @@ static bool qede_rx_xdp(struct qede_dev *edev,
qede_rx_bd_ring_consume(rxq);
break;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(edev->ndev, prog, act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(edev->ndev, prog, act);
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index a8c252e2b252..302dc835ac3d 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -5,6 +5,7 @@
* Copyright 2005-2013 Solarflare Communications Inc.
*/
+#include <linux/filter.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/netdevice.h>
diff --git a/drivers/net/ethernet/sfc/efx_channels.c b/drivers/net/ethernet/sfc/efx_channels.c
index 3dbea028b325..b015d1f2e204 100644
--- a/drivers/net/ethernet/sfc/efx_channels.c
+++ b/drivers/net/ethernet/sfc/efx_channels.c
@@ -10,6 +10,7 @@
#include "net_driver.h"
#include <linux/module.h>
+#include <linux/filter.h>
#include "efx_channels.h"
#include "efx.h"
#include "efx_common.h"
diff --git a/drivers/net/ethernet/sfc/efx_common.c b/drivers/net/ethernet/sfc/efx_common.c
index f187631b2c5c..af37c990217e 100644
--- a/drivers/net/ethernet/sfc/efx_common.c
+++ b/drivers/net/ethernet/sfc/efx_common.c
@@ -9,6 +9,7 @@
*/
#include "net_driver.h"
+#include <linux/filter.h>
#include <linux/module.h>
#include <linux/netdevice.h>
#include <net/gre.h>
diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index 606750938b89..2375cef577e4 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -338,7 +338,7 @@ static bool efx_do_xdp(struct efx_nic *efx, struct efx_channel *channel,
break;
default:
- bpf_warn_invalid_xdp_action(xdp_act);
+ bpf_warn_invalid_xdp_action(efx->net_dev, xdp_prog, xdp_act);
efx_free_rx_buffers(rx_queue, rx_buf, 1);
channel->n_rx_xdp_bad_drops++;
trace_xdp_exception(efx->net_dev, xdp_prog, xdp_act);
diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index 2e6bd65f6f43..556bd353dd42 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -933,7 +933,7 @@ static u32 netsec_run_xdp(struct netsec_priv *priv, struct bpf_prog *prog,
}
break;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(priv->ndev, prog, act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(priv->ndev, prog, act);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index aca3c3f0f0ad..40b5ed94cb54 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -22,6 +22,7 @@
#include <linux/net_tstamp.h>
#include <linux/reset.h>
#include <net/page_pool.h>
+#include <uapi/linux/bpf.h>
struct stmmac_resources {
void __iomem *addr;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index fd50e5783e8f..63ff2dad8c85 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -4723,7 +4723,7 @@ static int __stmmac_xdp_run_prog(struct stmmac_priv *priv,
res = STMMAC_XDP_REDIRECT;
break;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(priv->dev, prog, act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(priv->dev, prog, act);
diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c
index 8624a044776f..3537502e5e8b 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.c
+++ b/drivers/net/ethernet/ti/cpsw_priv.c
@@ -1362,7 +1362,7 @@ int cpsw_run_xdp(struct cpsw_priv *priv, int ch, struct xdp_buff *xdp,
xdp_do_flush_map();
break;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(ndev, prog, act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(ndev, prog, act);
diff --git a/drivers/net/ethernet/ti/cpsw_priv.h b/drivers/net/ethernet/ti/cpsw_priv.h
index f33c882eb70e..74555970730c 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.h
+++ b/drivers/net/ethernet/ti/cpsw_priv.h
@@ -6,6 +6,8 @@
#ifndef DRIVERS_NET_ETHERNET_TI_CPSW_PRIV_H_
#define DRIVERS_NET_ETHERNET_TI_CPSW_PRIV_H_
+#include <uapi/linux/bpf.h>
+
#include "davinci_cpdma.h"
#define CPSW_DEBUG (NETIF_MSG_HW | NETIF_MSG_WOL | \
diff --git a/drivers/net/hamradio/hdlcdrv.c b/drivers/net/hamradio/hdlcdrv.c
index b0edb91bb10a..8297411e87ea 100644
--- a/drivers/net/hamradio/hdlcdrv.c
+++ b/drivers/net/hamradio/hdlcdrv.c
@@ -30,6 +30,7 @@
/*****************************************************************************/
#include <linux/capability.h>
+#include <linux/compat.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/net.h>
diff --git a/drivers/net/hamradio/scc.c b/drivers/net/hamradio/scc.c
index 3d59dac063ac..f90830d3dfa6 100644
--- a/drivers/net/hamradio/scc.c
+++ b/drivers/net/hamradio/scc.c
@@ -148,6 +148,7 @@
/* ----------------------------------------------------------------------- */
+#include <linux/compat.h>
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/signal.h>
diff --git a/drivers/net/hyperv/netvsc_bpf.c b/drivers/net/hyperv/netvsc_bpf.c
index aa877da113f8..7856905414eb 100644
--- a/drivers/net/hyperv/netvsc_bpf.c
+++ b/drivers/net/hyperv/netvsc_bpf.c
@@ -68,7 +68,7 @@ u32 netvsc_run_xdp(struct net_device *ndev, struct netvsc_channel *nvchan,
break;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(ndev, prog, act);
}
out:
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index a1c77cc00416..ed0edf5884ef 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -44,6 +44,7 @@
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/ethtool.h>
+#include <net/sch_generic.h>
#include <net/sock.h>
#include <net/checksum.h>
#include <linux/if_ether.h> /* For the statistics structure. */
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 45a67e72a02c..fed85447701a 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1602,7 +1602,7 @@ static int tun_xdp_act(struct tun_struct *tun, struct bpf_prog *xdp_prog,
case XDP_PASS:
break;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(tun->dev, xdp_prog, act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(tun->dev, xdp_prog, act);
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index a4be530b3a1b..d21dd25f429e 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -644,7 +644,7 @@ static struct xdp_frame *veth_xdp_rcv_one(struct veth_rq *rq,
rcu_read_unlock();
goto xdp_xmit;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(rq->dev, xdp_prog, act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(rq->dev, xdp_prog, act);
@@ -794,7 +794,7 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq,
rcu_read_unlock();
goto xdp_xmit;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(rq->dev, xdp_prog, act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(rq->dev, xdp_prog, act);
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 87f8c896238f..569eecfbc2cd 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -812,7 +812,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
rcu_read_unlock();
goto xdp_xmit;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(vi->dev, xdp_prog, act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(vi->dev, xdp_prog, act);
@@ -1022,7 +1022,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
rcu_read_unlock();
goto xdp_xmit;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(vi->dev, xdp_prog, act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(vi->dev, xdp_prog, act);
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index b4c64226b7ca..e0b1ab99a359 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -34,6 +34,7 @@
#include <net/addrconf.h>
#include <net/l3mdev.h>
#include <net/fib_rules.h>
+#include <net/sch_generic.h>
#include <net/netns/generic.h>
#include <net/netfilter/nf_conntrack.h>
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index d514d96027a6..8b18246ad999 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -948,7 +948,7 @@ static u32 xennet_run_xdp(struct netfront_queue *queue, struct page *pdata,
break;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(queue->info->netdev, prog, act);
}
return act;
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 731d31015b6a..347793626f19 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -18,6 +18,7 @@
* 6 Jun 1999 Cache readdir lookups in the page cache. -DaveM
*/
+#include <linux/compat.h>
#include <linux/module.h>
#include <linux/time.h>
#include <linux/errno.h>
diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c
index 0d444a90f513..ea17fa1f31ec 100644
--- a/fs/nfs/fs_context.c
+++ b/fs/nfs/fs_context.c
@@ -10,6 +10,7 @@
* Split from fs/nfs/super.c by David Howells <dhowells@redhat.com>
*/
+#include <linux/compat.h>
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/fs_context.h>
diff --git a/fs/select.c b/fs/select.c
index 945896d0ac9e..02cd8cb5e69f 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -15,6 +15,7 @@
* of fds to overcome nfds < 16390 descriptors limit (Tigran Aivazian).
*/
+#include <linux/compat.h>
#include <linux/kernel.h>
#include <linux/sched/signal.h>
#include <linux/sched/rt.h>
diff --git a/include/linux/bpf-cgroup-defs.h b/include/linux/bpf-cgroup-defs.h
new file mode 100644
index 000000000000..695d1224a71b
--- /dev/null
+++ b/include/linux/bpf-cgroup-defs.h
@@ -0,0 +1,70 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BPF_CGROUP_DEFS_H
+#define _BPF_CGROUP_DEFS_H
+
+#ifdef CONFIG_CGROUP_BPF
+
+#include <linux/list.h>
+#include <linux/percpu-refcount.h>
+#include <linux/workqueue.h>
+
+struct bpf_prog_array;
+
+enum cgroup_bpf_attach_type {
+ CGROUP_BPF_ATTACH_TYPE_INVALID = -1,
+ CGROUP_INET_INGRESS = 0,
+ CGROUP_INET_EGRESS,
+ CGROUP_INET_SOCK_CREATE,
+ CGROUP_SOCK_OPS,
+ CGROUP_DEVICE,
+ CGROUP_INET4_BIND,
+ CGROUP_INET6_BIND,
+ CGROUP_INET4_CONNECT,
+ CGROUP_INET6_CONNECT,
+ CGROUP_INET4_POST_BIND,
+ CGROUP_INET6_POST_BIND,
+ CGROUP_UDP4_SENDMSG,
+ CGROUP_UDP6_SENDMSG,
+ CGROUP_SYSCTL,
+ CGROUP_UDP4_RECVMSG,
+ CGROUP_UDP6_RECVMSG,
+ CGROUP_GETSOCKOPT,
+ CGROUP_SETSOCKOPT,
+ CGROUP_INET4_GETPEERNAME,
+ CGROUP_INET6_GETPEERNAME,
+ CGROUP_INET4_GETSOCKNAME,
+ CGROUP_INET6_GETSOCKNAME,
+ CGROUP_INET_SOCK_RELEASE,
+ MAX_CGROUP_BPF_ATTACH_TYPE
+};
+
+struct cgroup_bpf {
+ /* array of effective progs in this cgroup */
+ struct bpf_prog_array __rcu *effective[MAX_CGROUP_BPF_ATTACH_TYPE];
+
+ /* attached progs to this cgroup and attach flags
+ * when flags == 0 or BPF_F_ALLOW_OVERRIDE the progs list will
+ * have either zero or one element
+ * when BPF_F_ALLOW_MULTI the list can have up to BPF_CGROUP_MAX_PROGS
+ */
+ struct list_head progs[MAX_CGROUP_BPF_ATTACH_TYPE];
+ u32 flags[MAX_CGROUP_BPF_ATTACH_TYPE];
+
+ /* list of cgroup shared storages */
+ struct list_head storages;
+
+ /* temp storage for effective prog array used by prog_attach/detach */
+ struct bpf_prog_array *inactive;
+
+ /* reference counter used to detach bpf programs after cgroup removal */
+ struct percpu_ref refcnt;
+
+ /* cgroup_bpf is released using a work queue */
+ struct work_struct release_work;
+};
+
+#else /* CONFIG_CGROUP_BPF */
+struct cgroup_bpf {};
+#endif /* CONFIG_CGROUP_BPF */
+
+#endif
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 11820a430d6c..b525d8cdc25b 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -3,10 +3,10 @@
#define _BPF_CGROUP_H
#include <linux/bpf.h>
+#include <linux/bpf-cgroup-defs.h>
#include <linux/errno.h>
#include <linux/jump_label.h>
#include <linux/percpu.h>
-#include <linux/percpu-refcount.h>
#include <linux/rbtree.h>
#include <uapi/linux/bpf.h>
@@ -23,33 +23,6 @@ struct ctl_table_header;
struct task_struct;
#ifdef CONFIG_CGROUP_BPF
-enum cgroup_bpf_attach_type {
- CGROUP_BPF_ATTACH_TYPE_INVALID = -1,
- CGROUP_INET_INGRESS = 0,
- CGROUP_INET_EGRESS,
- CGROUP_INET_SOCK_CREATE,
- CGROUP_SOCK_OPS,
- CGROUP_DEVICE,
- CGROUP_INET4_BIND,
- CGROUP_INET6_BIND,
- CGROUP_INET4_CONNECT,
- CGROUP_INET6_CONNECT,
- CGROUP_INET4_POST_BIND,
- CGROUP_INET6_POST_BIND,
- CGROUP_UDP4_SENDMSG,
- CGROUP_UDP6_SENDMSG,
- CGROUP_SYSCTL,
- CGROUP_UDP4_RECVMSG,
- CGROUP_UDP6_RECVMSG,
- CGROUP_GETSOCKOPT,
- CGROUP_SETSOCKOPT,
- CGROUP_INET4_GETPEERNAME,
- CGROUP_INET6_GETPEERNAME,
- CGROUP_INET4_GETSOCKNAME,
- CGROUP_INET6_GETSOCKNAME,
- CGROUP_INET_SOCK_RELEASE,
- MAX_CGROUP_BPF_ATTACH_TYPE
-};
#define CGROUP_ATYPE(type) \
case BPF_##type: return type
@@ -127,33 +100,6 @@ struct bpf_prog_list {
struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE];
};
-struct bpf_prog_array;
-
-struct cgroup_bpf {
- /* array of effective progs in this cgroup */
- struct bpf_prog_array __rcu *effective[MAX_CGROUP_BPF_ATTACH_TYPE];
-
- /* attached progs to this cgroup and attach flags
- * when flags == 0 or BPF_F_ALLOW_OVERRIDE the progs list will
- * have either zero or one element
- * when BPF_F_ALLOW_MULTI the list can have up to BPF_CGROUP_MAX_PROGS
- */
- struct list_head progs[MAX_CGROUP_BPF_ATTACH_TYPE];
- u32 flags[MAX_CGROUP_BPF_ATTACH_TYPE];
-
- /* list of cgroup shared storages */
- struct list_head storages;
-
- /* temp storage for effective prog array used by prog_attach/detach */
- struct bpf_prog_array *inactive;
-
- /* reference counter used to detach bpf programs after cgroup removal */
- struct percpu_ref refcnt;
-
- /* cgroup_bpf is released using a work queue */
- struct work_struct release_work;
-};
-
int cgroup_bpf_inherit(struct cgroup *cgrp);
void cgroup_bpf_offline(struct cgroup *cgrp);
@@ -451,7 +397,6 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr,
union bpf_attr __user *uattr);
#else
-struct cgroup_bpf {};
static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; }
static inline void cgroup_bpf_offline(struct cgroup *cgrp) {}
diff --git a/include/linux/bpf-netns.h b/include/linux/bpf-netns.h
index 722f799c1a2e..413cfa5e4b07 100644
--- a/include/linux/bpf-netns.h
+++ b/include/linux/bpf-netns.h
@@ -3,15 +3,9 @@
#define _BPF_NETNS_H
#include <linux/mutex.h>
+#include <net/netns/bpf.h>
#include <uapi/linux/bpf.h>
-enum netns_bpf_attach_type {
- NETNS_BPF_INVALID = -1,
- NETNS_BPF_FLOW_DISSECTOR = 0,
- NETNS_BPF_SK_LOOKUP,
- MAX_NETNS_BPF_ATTACH_TYPE
-};
-
static inline enum netns_bpf_attach_type
to_netns_bpf_attach_type(enum bpf_attach_type attach_type)
{
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 0ceb54c6342f..26753139d5b4 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -297,6 +297,34 @@ bool bpf_map_meta_equal(const struct bpf_map *meta0,
extern const struct bpf_map_ops bpf_map_offload_ops;
+/* bpf_type_flag contains a set of flags that are applicable to the values of
+ * arg_type, ret_type and reg_type. For example, a pointer value may be null,
+ * or a memory is read-only. We classify types into two categories: base types
+ * and extended types. Extended types are base types combined with a type flag.
+ *
+ * Currently there are no more than 32 base types in arg_type, ret_type and
+ * reg_types.
+ */
+#define BPF_BASE_TYPE_BITS 8
+
+enum bpf_type_flag {
+ /* PTR may be NULL. */
+ PTR_MAYBE_NULL = BIT(0 + BPF_BASE_TYPE_BITS),
+
+ /* MEM is read-only. When applied on bpf_arg, it indicates the arg is
+ * compatible with both mutable and immutable memory.
+ */
+ MEM_RDONLY = BIT(1 + BPF_BASE_TYPE_BITS),
+
+ __BPF_TYPE_LAST_FLAG = MEM_RDONLY,
+};
+
+/* Max number of base types. */
+#define BPF_BASE_TYPE_LIMIT (1UL << BPF_BASE_TYPE_BITS)
+
+/* Max number of all types. */
+#define BPF_TYPE_LIMIT (__BPF_TYPE_LAST_FLAG | (__BPF_TYPE_LAST_FLAG - 1))
+
/* function argument constraints */
enum bpf_arg_type {
ARG_DONTCARE = 0, /* unused argument in helper function */
@@ -308,13 +336,11 @@ enum bpf_arg_type {
ARG_PTR_TO_MAP_KEY, /* pointer to stack used as map key */
ARG_PTR_TO_MAP_VALUE, /* pointer to stack used as map value */
ARG_PTR_TO_UNINIT_MAP_VALUE, /* pointer to valid memory used to store a map value */
- ARG_PTR_TO_MAP_VALUE_OR_NULL, /* pointer to stack used as map value or NULL */
/* the following constraints used to prototype bpf_memcmp() and other
* functions that access data on eBPF program stack
*/
ARG_PTR_TO_MEM, /* pointer to valid memory (stack, packet, map value) */
- ARG_PTR_TO_MEM_OR_NULL, /* pointer to valid memory or NULL */
ARG_PTR_TO_UNINIT_MEM, /* pointer to memory does not need to be initialized,
* helper function must fill all bytes or clear
* them in error case.
@@ -324,42 +350,65 @@ enum bpf_arg_type {
ARG_CONST_SIZE_OR_ZERO, /* number of bytes accessed from memory or 0 */
ARG_PTR_TO_CTX, /* pointer to context */
- ARG_PTR_TO_CTX_OR_NULL, /* pointer to context or NULL */
ARG_ANYTHING, /* any (initialized) argument is ok */
ARG_PTR_TO_SPIN_LOCK, /* pointer to bpf_spin_lock */
ARG_PTR_TO_SOCK_COMMON, /* pointer to sock_common */
ARG_PTR_TO_INT, /* pointer to int */
ARG_PTR_TO_LONG, /* pointer to long */
ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */
- ARG_PTR_TO_SOCKET_OR_NULL, /* pointer to bpf_sock (fullsock) or NULL */
ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */
ARG_PTR_TO_ALLOC_MEM, /* pointer to dynamically allocated memory */
- ARG_PTR_TO_ALLOC_MEM_OR_NULL, /* pointer to dynamically allocated memory or NULL */
ARG_CONST_ALLOC_SIZE_OR_ZERO, /* number of allocated bytes requested */
ARG_PTR_TO_BTF_ID_SOCK_COMMON, /* pointer to in-kernel sock_common or bpf-mirrored bpf_sock */
ARG_PTR_TO_PERCPU_BTF_ID, /* pointer to in-kernel percpu type */
ARG_PTR_TO_FUNC, /* pointer to a bpf program function */
- ARG_PTR_TO_STACK_OR_NULL, /* pointer to stack or NULL */
+ ARG_PTR_TO_STACK, /* pointer to stack */
ARG_PTR_TO_CONST_STR, /* pointer to a null terminated read-only string */
ARG_PTR_TO_TIMER, /* pointer to bpf_timer */
__BPF_ARG_TYPE_MAX,
+
+ /* Extended arg_types. */
+ ARG_PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_MAP_VALUE,
+ ARG_PTR_TO_MEM_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_MEM,
+ ARG_PTR_TO_CTX_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_CTX,
+ ARG_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET,
+ ARG_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_ALLOC_MEM,
+ ARG_PTR_TO_STACK_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_STACK,
+
+ /* This must be the last entry. Its purpose is to ensure the enum is
+ * wide enough to hold the higher bits reserved for bpf_type_flag.
+ */
+ __BPF_ARG_TYPE_LIMIT = BPF_TYPE_LIMIT,
};
+static_assert(__BPF_ARG_TYPE_MAX <= BPF_BASE_TYPE_LIMIT);
/* type of values returned from helper functions */
enum bpf_return_type {
RET_INTEGER, /* function returns integer */
RET_VOID, /* function doesn't return anything */
RET_PTR_TO_MAP_VALUE, /* returns a pointer to map elem value */
- RET_PTR_TO_MAP_VALUE_OR_NULL, /* returns a pointer to map elem value or NULL */
- RET_PTR_TO_SOCKET_OR_NULL, /* returns a pointer to a socket or NULL */
- RET_PTR_TO_TCP_SOCK_OR_NULL, /* returns a pointer to a tcp_sock or NULL */
- RET_PTR_TO_SOCK_COMMON_OR_NULL, /* returns a pointer to a sock_common or NULL */
- RET_PTR_TO_ALLOC_MEM_OR_NULL, /* returns a pointer to dynamically allocated memory or NULL */
- RET_PTR_TO_BTF_ID_OR_NULL, /* returns a pointer to a btf_id or NULL */
- RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL, /* returns a pointer to a valid memory or a btf_id or NULL */
+ RET_PTR_TO_SOCKET, /* returns a pointer to a socket */
+ RET_PTR_TO_TCP_SOCK, /* returns a pointer to a tcp_sock */
+ RET_PTR_TO_SOCK_COMMON, /* returns a pointer to a sock_common */
+ RET_PTR_TO_ALLOC_MEM, /* returns a pointer to dynamically allocated memory */
RET_PTR_TO_MEM_OR_BTF_ID, /* returns a pointer to a valid memory or a btf_id */
RET_PTR_TO_BTF_ID, /* returns a pointer to a btf_id */
+ __BPF_RET_TYPE_MAX,
+
+ /* Extended ret_types. */
+ RET_PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_MAP_VALUE,
+ RET_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCKET,
+ RET_PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_TCP_SOCK,
+ RET_PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCK_COMMON,
+ RET_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_ALLOC_MEM,
+ RET_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_BTF_ID,
+
+ /* This must be the last entry. Its purpose is to ensure the enum is
+ * wide enough to hold the higher bits reserved for bpf_type_flag.
+ */
+ __BPF_RET_TYPE_LIMIT = BPF_TYPE_LIMIT,
};
+static_assert(__BPF_RET_TYPE_MAX <= BPF_BASE_TYPE_LIMIT);
/* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs
* to in-kernel helper functions and for adjusting imm32 field in BPF_CALL
@@ -421,18 +470,15 @@ enum bpf_reg_type {
PTR_TO_CTX, /* reg points to bpf_context */
CONST_PTR_TO_MAP, /* reg points to struct bpf_map */
PTR_TO_MAP_VALUE, /* reg points to map element value */
- PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */
+ PTR_TO_MAP_KEY, /* reg points to a map element key */
PTR_TO_STACK, /* reg == frame_pointer + offset */
PTR_TO_PACKET_META, /* skb->data - meta_len */
PTR_TO_PACKET, /* reg points to skb->data */
PTR_TO_PACKET_END, /* skb->data + headlen */
PTR_TO_FLOW_KEYS, /* reg points to bpf_flow_keys */
PTR_TO_SOCKET, /* reg points to struct bpf_sock */
- PTR_TO_SOCKET_OR_NULL, /* reg points to struct bpf_sock or NULL */
PTR_TO_SOCK_COMMON, /* reg points to sock_common */
- PTR_TO_SOCK_COMMON_OR_NULL, /* reg points to sock_common or NULL */
PTR_TO_TCP_SOCK, /* reg points to struct tcp_sock */
- PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */
PTR_TO_TP_BUFFER, /* reg points to a writable raw tp's buffer */
PTR_TO_XDP_SOCK, /* reg points to struct xdp_sock */
/* PTR_TO_BTF_ID points to a kernel struct that does not need
@@ -450,18 +496,25 @@ enum bpf_reg_type {
* been checked for null. Used primarily to inform the verifier
* an explicit null check is required for this struct.
*/
- PTR_TO_BTF_ID_OR_NULL,
PTR_TO_MEM, /* reg points to valid memory region */
- PTR_TO_MEM_OR_NULL, /* reg points to valid memory region or NULL */
- PTR_TO_RDONLY_BUF, /* reg points to a readonly buffer */
- PTR_TO_RDONLY_BUF_OR_NULL, /* reg points to a readonly buffer or NULL */
- PTR_TO_RDWR_BUF, /* reg points to a read/write buffer */
- PTR_TO_RDWR_BUF_OR_NULL, /* reg points to a read/write buffer or NULL */
+ PTR_TO_BUF, /* reg points to a read/write buffer */
PTR_TO_PERCPU_BTF_ID, /* reg points to a percpu kernel variable */
PTR_TO_FUNC, /* reg points to a bpf program function */
- PTR_TO_MAP_KEY, /* reg points to a map element key */
__BPF_REG_TYPE_MAX,
+
+ /* Extended reg_types. */
+ PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | PTR_TO_MAP_VALUE,
+ PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | PTR_TO_SOCKET,
+ PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | PTR_TO_SOCK_COMMON,
+ PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | PTR_TO_TCP_SOCK,
+ PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | PTR_TO_BTF_ID,
+
+ /* This must be the last entry. Its purpose is to ensure the enum is
+ * wide enough to hold the higher bits reserved for bpf_type_flag.
+ */
+ __BPF_REG_TYPE_LIMIT = BPF_TYPE_LIMIT,
};
+static_assert(__BPF_REG_TYPE_MAX <= BPF_BASE_TYPE_LIMIT);
/* The information passed from prog-specific *_is_valid_access
* back to the verifier.
@@ -777,6 +830,7 @@ void bpf_ksym_add(struct bpf_ksym *ksym);
void bpf_ksym_del(struct bpf_ksym *ksym);
int bpf_jit_charge_modmem(u32 pages);
void bpf_jit_uncharge_modmem(u32 pages);
+bool bpf_prog_has_trampoline(const struct bpf_prog *prog);
#else
static inline int bpf_trampoline_link_prog(struct bpf_prog *prog,
struct bpf_trampoline *tr)
@@ -805,6 +859,10 @@ static inline bool is_bpf_image_address(unsigned long address)
{
return false;
}
+static inline bool bpf_prog_has_trampoline(const struct bpf_prog *prog)
+{
+ return false;
+}
#endif
struct bpf_func_info_aux {
@@ -2163,6 +2221,7 @@ extern const struct bpf_func_proto bpf_sk_getsockopt_proto;
extern const struct bpf_func_proto bpf_kallsyms_lookup_name_proto;
extern const struct bpf_func_proto bpf_find_vma_proto;
extern const struct bpf_func_proto bpf_loop_proto;
+extern const struct bpf_func_proto bpf_strncmp_proto;
const struct bpf_func_proto *tracing_prog_func_proto(
enum bpf_func_id func_id, const struct bpf_prog *prog);
diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h
index 24496bc28e7b..37b3906af8b1 100644
--- a/include/linux/bpf_local_storage.h
+++ b/include/linux/bpf_local_storage.h
@@ -8,6 +8,7 @@
#define _BPF_LOCAL_STORAGE_H
#include <linux/bpf.h>
+#include <linux/filter.h>
#include <linux/rculist.h>
#include <linux/list.h>
#include <linux/hash.h>
@@ -16,6 +17,9 @@
#define BPF_LOCAL_STORAGE_CACHE_SIZE 16
+#define bpf_rcu_lock_held() \
+ (rcu_read_lock_held() || rcu_read_lock_trace_held() || \
+ rcu_read_lock_bh_held())
struct bpf_local_storage_map_bucket {
struct hlist_head list;
raw_spinlock_t lock;
@@ -161,4 +165,6 @@ struct bpf_local_storage_data *
bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
void *value, u64 map_flags);
+void bpf_local_storage_free_rcu(struct rcu_head *rcu);
+
#endif /* _BPF_LOCAL_STORAGE_H */
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 182b16a91084..143401d4c9d9 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -18,6 +18,8 @@
* that converting umax_value to int cannot overflow.
*/
#define BPF_MAX_VAR_SIZ (1 << 29)
+/* size of type_str_buf in bpf_verifier. */
+#define TYPE_STR_BUF_LEN 64
/* Liveness marks, used for registers and spilled-regs (in stack slots).
* Read marks propagate upwards until they find a write mark; they record that
@@ -388,6 +390,8 @@ static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log)
#define BPF_LOG_LEVEL (BPF_LOG_LEVEL1 | BPF_LOG_LEVEL2)
#define BPF_LOG_MASK (BPF_LOG_LEVEL | BPF_LOG_STATS)
#define BPF_LOG_KERNEL (BPF_LOG_MASK + 1) /* kernel internal flag */
+#define BPF_LOG_MIN_ALIGNMENT 8U
+#define BPF_LOG_ALIGNMENT 40U
static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log)
{
@@ -474,6 +478,16 @@ struct bpf_verifier_env {
/* longest register parentage chain walked for liveness marking */
u32 longest_mark_read_walk;
bpfptr_t fd_array;
+
+ /* bit mask to keep track of whether a register has been accessed
+ * since the last time the function state was printed
+ */
+ u32 scratched_regs;
+ /* Same as scratched_regs but for stack slots */
+ u64 scratched_stack_slots;
+ u32 prev_log_len, prev_insn_print_len;
+ /* buffer used in reg_type_str() to generate reg_type string */
+ char type_str_buf[TYPE_STR_BUF_LEN];
};
__printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log,
@@ -536,5 +550,18 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
struct bpf_attach_target_info *tgt_info);
void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab);
+#define BPF_BASE_TYPE_MASK GENMASK(BPF_BASE_TYPE_BITS - 1, 0)
+
+/* extract base type from bpf_{arg, return, reg}_type. */
+static inline u32 base_type(u32 type)
+{
+ return type & BPF_BASE_TYPE_MASK;
+}
+
+/* extract flags from an extended type. See bpf_type_flag in bpf.h. */
+static inline u32 type_flag(u32 type)
+{
+ return type & ~BPF_BASE_TYPE_MASK;
+}
#endif /* _LINUX_BPF_VERIFIER_H */
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index db2e147e069f..411684c80cf3 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -19,7 +19,7 @@
#include <linux/percpu-rwsem.h>
#include <linux/u64_stats_sync.h>
#include <linux/workqueue.h>
-#include <linux/bpf-cgroup.h>
+#include <linux/bpf-cgroup-defs.h>
#include <linux/psi_types.h>
#ifdef CONFIG_CGROUPS
diff --git a/include/linux/dsa/loop.h b/include/linux/dsa/loop.h
index 5a3470bcc8a7..b8fef35591aa 100644
--- a/include/linux/dsa/loop.h
+++ b/include/linux/dsa/loop.h
@@ -2,6 +2,7 @@
#ifndef DSA_LOOP_H
#define DSA_LOOP_H
+#include <linux/if_vlan.h>
#include <linux/types.h>
#include <linux/ethtool.h>
#include <net/dsa.h>
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 68c6b5c208e7..60eec80fa1d4 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1027,7 +1027,7 @@ void xdp_do_flush(void);
*/
#define xdp_do_flush_map xdp_do_flush
-void bpf_warn_invalid_xdp_action(u32 act);
+void bpf_warn_invalid_xdp_action(struct net_device *dev, struct bpf_prog *prog, u32 act);
#ifdef CONFIG_INET
struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 0dcfd265beed..4a021149eaf0 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -611,6 +611,7 @@ struct swevent_hlist {
#define PERF_ATTACH_SCHED_CB 0x20
#define PERF_ATTACH_CHILD 0x40
+struct bpf_prog;
struct perf_cgroup;
struct perf_buffer;
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 83b8070d1cc9..a9a4ccc0cdb5 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -20,6 +20,7 @@
#include <net/inetpeer.h>
#include <net/fib_notifier.h>
#include <linux/indirect_call_wrapper.h>
+#include <uapi/linux/bpf.h>
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
#define FIB6_TABLE_HASHSZ 256
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 53ac7707ca70..3afcb128e064 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -21,6 +21,8 @@
#include <net/snmp.h>
#include <net/netns/hash.h>
+struct ip_tunnel_info;
+
#define SIN6_LEN_RFC2133 24
#define IPV6_MAXPLEN 65535
diff --git a/include/net/netns/bpf.h b/include/net/netns/bpf.h
index 0ca6a1b87185..2c01a278d1eb 100644
--- a/include/net/netns/bpf.h
+++ b/include/net/netns/bpf.h
@@ -6,11 +6,18 @@
#ifndef __NETNS_BPF_H__
#define __NETNS_BPF_H__
-#include <linux/bpf-netns.h>
+#include <linux/list.h>
struct bpf_prog;
struct bpf_prog_array;
+enum netns_bpf_attach_type {
+ NETNS_BPF_INVALID = -1,
+ NETNS_BPF_FLOW_DISSECTOR = 0,
+ NETNS_BPF_SK_LOOKUP,
+ MAX_NETNS_BPF_ATTACH_TYPE
+};
+
struct netns_bpf {
/* Array of programs to run compiled from progs or links */
struct bpf_prog_array __rcu *run_array[MAX_NETNS_BPF_ATTACH_TYPE];
diff --git a/include/net/route.h b/include/net/route.h
index 2e6c0e153e3a..4c858dcf1aa8 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -43,6 +43,7 @@
#define RT_CONN_FLAGS(sk) (RT_TOS(inet_sk(sk)->tos) | sock_flag(sk, SOCK_LOCALROUTE))
#define RT_CONN_FLAGS_TOS(sk,tos) (RT_TOS(tos) | sock_flag(sk, SOCK_LOCALROUTE))
+struct ip_tunnel_info;
struct fib_nh;
struct fib_info;
struct uncached_list;
diff --git a/include/net/sock.h b/include/net/sock.h
index 44cc25f0bae7..7b4b4237e6e0 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -56,7 +56,6 @@
#include <linux/wait.h>
#include <linux/cgroup-defs.h>
#include <linux/rbtree.h>
-#include <linux/filter.h>
#include <linux/rculist_nulls.h>
#include <linux/poll.h>
#include <linux/sockptr.h>
@@ -249,6 +248,7 @@ struct sock_common {
};
struct bpf_local_storage;
+struct sk_filter;
/**
* struct sock - network layer representation of sockets
diff --git a/include/net/xdp_priv.h b/include/net/xdp_priv.h
index a9d5b7603b89..a2d58b1a12e1 100644
--- a/include/net/xdp_priv.h
+++ b/include/net/xdp_priv.h
@@ -10,7 +10,6 @@ struct xdp_mem_allocator {
union {
void *allocator;
struct page_pool *page_pool;
- struct zero_copy_allocator *zc_alloc;
};
struct rhash_head node;
struct rcu_head rcu;
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index fff069d2ed1b..3057e1a4a11c 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -6,6 +6,7 @@
#ifndef _LINUX_XDP_SOCK_H
#define _LINUX_XDP_SOCK_H
+#include <linux/bpf.h>
#include <linux/workqueue.h>
#include <linux/if_xdp.h>
#include <linux/mutex.h>
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index c26871263f1f..b0383d371b9a 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4983,6 +4983,41 @@ union bpf_attr {
* Return
* The number of loops performed, **-EINVAL** for invalid **flags**,
* **-E2BIG** if **nr_loops** exceeds the maximum number of loops.
+ *
+ * long bpf_strncmp(const char *s1, u32 s1_sz, const char *s2)
+ * Description
+ * Do strncmp() between **s1** and **s2**. **s1** doesn't need
+ * to be null-terminated and **s1_sz** is the maximum storage
+ * size of **s1**. **s2** must be a read-only string.
+ * Return
+ * An integer less than, equal to, or greater than zero
+ * if the first **s1_sz** bytes of **s1** is found to be
+ * less than, to match, or be greater than **s2**.
+ *
+ * long bpf_get_func_arg(void *ctx, u32 n, u64 *value)
+ * Description
+ * Get **n**-th argument (zero based) of the traced function (for tracing programs)
+ * returned in **value**.
+ *
+ * Return
+ * 0 on success.
+ * **-EINVAL** if n >= arguments count of traced function.
+ *
+ * long bpf_get_func_ret(void *ctx, u64 *value)
+ * Description
+ * Get return value of the traced function (for tracing programs)
+ * in **value**.
+ *
+ * Return
+ * 0 on success.
+ * **-EOPNOTSUPP** for tracing programs other than BPF_TRACE_FEXIT or BPF_MODIFY_RETURN.
+ *
+ * long bpf_get_func_arg_cnt(void *ctx)
+ * Description
+ * Get number of arguments of the traced function (for tracing programs).
+ *
+ * Return
+ * The number of arguments of the traced function.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -5167,6 +5202,10 @@ union bpf_attr {
FN(kallsyms_lookup_name), \
FN(find_vma), \
FN(loop), \
+ FN(strncmp), \
+ FN(get_func_arg), \
+ FN(get_func_ret), \
+ FN(get_func_arg_cnt), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c
index 277a05e9c984..b141a1346f72 100644
--- a/kernel/bpf/bloom_filter.c
+++ b/kernel/bpf/bloom_filter.c
@@ -82,6 +82,11 @@ static int bloom_map_delete_elem(struct bpf_map *map, void *value)
return -EOPNOTSUPP;
}
+static int bloom_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+ return -EOPNOTSUPP;
+}
+
static struct bpf_map *bloom_map_alloc(union bpf_attr *attr)
{
u32 bitset_bytes, bitset_mask, nr_hash_funcs, nr_bits;
@@ -192,6 +197,7 @@ const struct bpf_map_ops bloom_filter_map_ops = {
.map_meta_equal = bpf_map_meta_equal,
.map_alloc = bloom_map_alloc,
.map_free = bloom_map_free,
+ .map_get_next_key = bloom_map_get_next_key,
.map_push_elem = bloom_map_push_elem,
.map_peek_elem = bloom_map_peek_elem,
.map_pop_elem = bloom_map_pop_elem,
diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c
index 96ceed0e0fb5..e29d9e3d853e 100644
--- a/kernel/bpf/bpf_inode_storage.c
+++ b/kernel/bpf/bpf_inode_storage.c
@@ -17,6 +17,7 @@
#include <linux/bpf_lsm.h>
#include <linux/btf_ids.h>
#include <linux/fdtable.h>
+#include <linux/rcupdate_trace.h>
DEFINE_BPF_STORAGE_CACHE(inode_cache);
@@ -44,7 +45,8 @@ static struct bpf_local_storage_data *inode_storage_lookup(struct inode *inode,
if (!bsb)
return NULL;
- inode_storage = rcu_dereference(bsb->storage);
+ inode_storage =
+ rcu_dereference_check(bsb->storage, bpf_rcu_lock_held());
if (!inode_storage)
return NULL;
@@ -172,6 +174,7 @@ BPF_CALL_4(bpf_inode_storage_get, struct bpf_map *, map, struct inode *, inode,
{
struct bpf_local_storage_data *sdata;
+ WARN_ON_ONCE(!bpf_rcu_lock_held());
if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE))
return (unsigned long)NULL;
@@ -204,6 +207,7 @@ BPF_CALL_4(bpf_inode_storage_get, struct bpf_map *, map, struct inode *, inode,
BPF_CALL_2(bpf_inode_storage_delete,
struct bpf_map *, map, struct inode *, inode)
{
+ WARN_ON_ONCE(!bpf_rcu_lock_held());
if (!inode)
return -EINVAL;
diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index b305270b7a4b..71de2a89869c 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -11,6 +11,9 @@
#include <net/sock.h>
#include <uapi/linux/sock_diag.h>
#include <uapi/linux/btf.h>
+#include <linux/rcupdate.h>
+#include <linux/rcupdate_trace.h>
+#include <linux/rcupdate_wait.h>
#define BPF_LOCAL_STORAGE_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_CLONE)
@@ -81,6 +84,22 @@ bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner,
return NULL;
}
+void bpf_local_storage_free_rcu(struct rcu_head *rcu)
+{
+ struct bpf_local_storage *local_storage;
+
+ local_storage = container_of(rcu, struct bpf_local_storage, rcu);
+ kfree_rcu(local_storage, rcu);
+}
+
+static void bpf_selem_free_rcu(struct rcu_head *rcu)
+{
+ struct bpf_local_storage_elem *selem;
+
+ selem = container_of(rcu, struct bpf_local_storage_elem, rcu);
+ kfree_rcu(selem, rcu);
+}
+
/* local_storage->lock must be held and selem->local_storage == local_storage.
* The caller must ensure selem->smap is still valid to be
* dereferenced for its smap->elem_size and smap->cache_idx.
@@ -93,7 +112,7 @@ bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
bool free_local_storage;
void *owner;
- smap = rcu_dereference(SDATA(selem)->smap);
+ smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held());
owner = local_storage->owner;
/* All uncharging on the owner must be done first.
@@ -118,12 +137,12 @@ bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
*
* Although the unlock will be done under
* rcu_read_lock(), it is more intutivie to
- * read if kfree_rcu(local_storage, rcu) is done
+ * read if the freeing of the storage is done
* after the raw_spin_unlock_bh(&local_storage->lock).
*
* Hence, a "bool free_local_storage" is returned
- * to the caller which then calls the kfree_rcu()
- * after unlock.
+ * to the caller which then calls then frees the storage after
+ * all the RCU grace periods have expired.
*/
}
hlist_del_init_rcu(&selem->snode);
@@ -131,8 +150,7 @@ bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
SDATA(selem))
RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL);
- kfree_rcu(selem, rcu);
-
+ call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_rcu);
return free_local_storage;
}
@@ -146,7 +164,8 @@ static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem)
/* selem has already been unlinked from sk */
return;
- local_storage = rcu_dereference(selem->local_storage);
+ local_storage = rcu_dereference_check(selem->local_storage,
+ bpf_rcu_lock_held());
raw_spin_lock_irqsave(&local_storage->lock, flags);
if (likely(selem_linked_to_storage(selem)))
free_local_storage = bpf_selem_unlink_storage_nolock(
@@ -154,7 +173,8 @@ static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem)
raw_spin_unlock_irqrestore(&local_storage->lock, flags);
if (free_local_storage)
- kfree_rcu(local_storage, rcu);
+ call_rcu_tasks_trace(&local_storage->rcu,
+ bpf_local_storage_free_rcu);
}
void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage,
@@ -174,7 +194,7 @@ void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem)
/* selem has already be unlinked from smap */
return;
- smap = rcu_dereference(SDATA(selem)->smap);
+ smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held());
b = select_bucket(smap, selem);
raw_spin_lock_irqsave(&b->lock, flags);
if (likely(selem_linked_to_map(selem)))
@@ -213,12 +233,14 @@ bpf_local_storage_lookup(struct bpf_local_storage *local_storage,
struct bpf_local_storage_elem *selem;
/* Fast path (cache hit) */
- sdata = rcu_dereference(local_storage->cache[smap->cache_idx]);
+ sdata = rcu_dereference_check(local_storage->cache[smap->cache_idx],
+ bpf_rcu_lock_held());
if (sdata && rcu_access_pointer(sdata->smap) == smap)
return sdata;
/* Slow path (cache miss) */
- hlist_for_each_entry_rcu(selem, &local_storage->list, snode)
+ hlist_for_each_entry_rcu(selem, &local_storage->list, snode,
+ rcu_read_lock_trace_held())
if (rcu_access_pointer(SDATA(selem)->smap) == smap)
break;
@@ -306,7 +328,8 @@ int bpf_local_storage_alloc(void *owner,
* bucket->list, first_selem can be freed immediately
* (instead of kfree_rcu) because
* bpf_local_storage_map_free() does a
- * synchronize_rcu() before walking the bucket->list.
+ * synchronize_rcu_mult (waiting for both sleepable and
+ * normal programs) before walking the bucket->list.
* Hence, no one is accessing selem from the
* bucket->list under rcu_read_lock().
*/
@@ -342,7 +365,8 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
!map_value_has_spin_lock(&smap->map)))
return ERR_PTR(-EINVAL);
- local_storage = rcu_dereference(*owner_storage(smap, owner));
+ local_storage = rcu_dereference_check(*owner_storage(smap, owner),
+ bpf_rcu_lock_held());
if (!local_storage || hlist_empty(&local_storage->list)) {
/* Very first elem for the owner */
err = check_flags(NULL, map_flags);
diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c
index bb69aea1a777..5da7bed0f5f6 100644
--- a/kernel/bpf/bpf_task_storage.c
+++ b/kernel/bpf/bpf_task_storage.c
@@ -17,6 +17,7 @@
#include <uapi/linux/btf.h>
#include <linux/btf_ids.h>
#include <linux/fdtable.h>
+#include <linux/rcupdate_trace.h>
DEFINE_BPF_STORAGE_CACHE(task_cache);
@@ -59,7 +60,8 @@ task_storage_lookup(struct task_struct *task, struct bpf_map *map,
struct bpf_local_storage *task_storage;
struct bpf_local_storage_map *smap;
- task_storage = rcu_dereference(task->bpf_storage);
+ task_storage =
+ rcu_dereference_check(task->bpf_storage, bpf_rcu_lock_held());
if (!task_storage)
return NULL;
@@ -229,6 +231,7 @@ BPF_CALL_4(bpf_task_storage_get, struct bpf_map *, map, struct task_struct *,
{
struct bpf_local_storage_data *sdata;
+ WARN_ON_ONCE(!bpf_rcu_lock_held());
if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE))
return (unsigned long)NULL;
@@ -260,6 +263,7 @@ BPF_CALL_2(bpf_task_storage_delete, struct bpf_map *, map, struct task_struct *,
{
int ret;
+ WARN_ON_ONCE(!bpf_rcu_lock_held());
if (!task)
return -EINVAL;
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 8b00c6e4d6fb..33bb8ae4a804 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -4826,7 +4826,7 @@ struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog)
return prog->aux->attach_btf;
}
-static bool is_string_ptr(struct btf *btf, const struct btf_type *t)
+static bool is_int_ptr(struct btf *btf, const struct btf_type *t)
{
/* t comes in already as a pointer */
t = btf_type_by_id(btf, t->type);
@@ -4835,8 +4835,7 @@ static bool is_string_ptr(struct btf *btf, const struct btf_type *t)
if (BTF_INFO_KIND(t->info) == BTF_KIND_CONST)
t = btf_type_by_id(btf, t->type);
- /* char, signed char, unsigned char */
- return btf_type_is_int(t) && t->size == 1;
+ return btf_type_is_int(t);
}
bool btf_ctx_access(int off, int size, enum bpf_access_type type,
@@ -4941,10 +4940,12 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
/* check for PTR_TO_RDONLY_BUF_OR_NULL or PTR_TO_RDWR_BUF_OR_NULL */
for (i = 0; i < prog->aux->ctx_arg_info_size; i++) {
const struct bpf_ctx_arg_aux *ctx_arg_info = &prog->aux->ctx_arg_info[i];
+ u32 type, flag;
- if (ctx_arg_info->offset == off &&
- (ctx_arg_info->reg_type == PTR_TO_RDONLY_BUF_OR_NULL ||
- ctx_arg_info->reg_type == PTR_TO_RDWR_BUF_OR_NULL)) {
+ type = base_type(ctx_arg_info->reg_type);
+ flag = type_flag(ctx_arg_info->reg_type);
+ if (ctx_arg_info->offset == off && type == PTR_TO_BUF &&
+ (flag & PTR_MAYBE_NULL)) {
info->reg_type = ctx_arg_info->reg_type;
return true;
}
@@ -4957,7 +4958,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
*/
return true;
- if (is_string_ptr(btf, t))
+ if (is_int_ptr(btf, t))
return true;
/* this is a pointer to another type */
@@ -5575,12 +5576,53 @@ static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = {
#endif
};
+/* Returns true if struct is composed of scalars, 4 levels of nesting allowed */
+static bool __btf_type_is_scalar_struct(struct bpf_verifier_log *log,
+ const struct btf *btf,
+ const struct btf_type *t, int rec)
+{
+ const struct btf_type *member_type;
+ const struct btf_member *member;
+ u32 i;
+
+ if (!btf_type_is_struct(t))
+ return false;
+
+ for_each_member(i, t, member) {
+ const struct btf_array *array;
+
+ member_type = btf_type_skip_modifiers(btf, member->type, NULL);
+ if (btf_type_is_struct(member_type)) {
+ if (rec >= 3) {
+ bpf_log(log, "max struct nesting depth exceeded\n");
+ return false;
+ }
+ if (!__btf_type_is_scalar_struct(log, btf, member_type, rec + 1))
+ return false;
+ continue;
+ }
+ if (btf_type_is_array(member_type)) {
+ array = btf_type_array(member_type);
+ if (!array->nelems)
+ return false;
+ member_type = btf_type_skip_modifiers(btf, array->type, NULL);
+ if (!btf_type_is_scalar(member_type))
+ return false;
+ continue;
+ }
+ if (!btf_type_is_scalar(member_type))
+ return false;
+ }
+ return true;
+}
+
static int btf_check_func_arg_match(struct bpf_verifier_env *env,
const struct btf *btf, u32 func_id,
struct bpf_reg_state *regs,
bool ptr_to_mem_ok)
{
struct bpf_verifier_log *log = &env->log;
+ bool is_kfunc = btf_is_kernel(btf);
const char *func_name, *ref_tname;
const struct btf_type *t, *ref_t;
const struct btf_param *args;
@@ -5633,7 +5675,20 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
ref_t = btf_type_skip_modifiers(btf, t->type, &ref_id);
ref_tname = btf_name_by_offset(btf, ref_t->name_off);
- if (btf_is_kernel(btf)) {
+ if (btf_get_prog_ctx_type(log, btf, t,
+ env->prog->type, i)) {
+ /* If function expects ctx type in BTF check that caller
+ * is passing PTR_TO_CTX.
+ */
+ if (reg->type != PTR_TO_CTX) {
+ bpf_log(log,
+ "arg#%d expected pointer to ctx, but got %s\n",
+ i, btf_type_str(t));
+ return -EINVAL;
+ }
+ if (check_ctx_reg(env, reg, regno))
+ return -EINVAL;
+ } else if (is_kfunc && (reg->type == PTR_TO_BTF_ID || reg2btf_ids[reg->type])) {
const struct btf_type *reg_ref_t;
const struct btf *reg_btf;
const char *reg_ref_tname;
@@ -5649,14 +5704,9 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
if (reg->type == PTR_TO_BTF_ID) {
reg_btf = reg->btf;
reg_ref_id = reg->btf_id;
- } else if (reg2btf_ids[reg->type]) {
+ } else {
reg_btf = btf_vmlinux;
reg_ref_id = *reg2btf_ids[reg->type];
- } else {
- bpf_log(log, "kernel function %s args#%d expected pointer to %s %s but R%d is not a pointer to btf_id\n",
- func_name, i,
- btf_type_str(ref_t), ref_tname, regno);
- return -EINVAL;
}
reg_ref_t = btf_type_skip_modifiers(reg_btf, reg_ref_id,
@@ -5672,23 +5722,24 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
reg_ref_tname);
return -EINVAL;
}
- } else if (btf_get_prog_ctx_type(log, btf, t,
- env->prog->type, i)) {
- /* If function expects ctx type in BTF check that caller
- * is passing PTR_TO_CTX.
- */
- if (reg->type != PTR_TO_CTX) {
- bpf_log(log,
- "arg#%d expected pointer to ctx, but got %s\n",
- i, btf_type_str(t));
- return -EINVAL;
- }
- if (check_ctx_reg(env, reg, regno))
- return -EINVAL;
} else if (ptr_to_mem_ok) {
const struct btf_type *resolve_ret;
u32 type_size;
+ if (is_kfunc) {
+ /* Permit pointer to mem, but only when argument
+ * type is pointer to scalar, or struct composed
+ * (recursively) of scalars.
+ */
+ if (!btf_type_is_scalar(ref_t) &&
+ !__btf_type_is_scalar_struct(log, btf, ref_t, 0)) {
+ bpf_log(log,
+ "arg#%d pointer type %s %s must point to scalar or struct with scalar\n",
+ i, btf_type_str(ref_t), ref_tname);
+ return -EINVAL;
+ }
+ }
+
resolve_ret = btf_resolve_size(btf, ref_t, &type_size);
if (IS_ERR(resolve_ret)) {
bpf_log(log,
@@ -5701,6 +5752,8 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
if (check_mem_reg(env, reg, regno, type_size))
return -EINVAL;
} else {
+ bpf_log(log, "reg type unsupported for arg#%d %sfunction %s#%d\n", i,
+ is_kfunc ? "kernel " : "", func_name, func_id);
return -EINVAL;
}
}
@@ -5750,7 +5803,7 @@ int btf_check_kfunc_arg_match(struct bpf_verifier_env *env,
const struct btf *btf, u32 func_id,
struct bpf_reg_state *regs)
{
- return btf_check_func_arg_match(env, btf, func_id, regs, false);
+ return btf_check_func_arg_match(env, btf, func_id, regs, true);
}
/* Convert BTF of a function into bpf_reg_state if possible
@@ -5858,7 +5911,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
return -EINVAL;
}
- reg->type = PTR_TO_MEM_OR_NULL;
+ reg->type = PTR_TO_MEM | PTR_MAYBE_NULL;
reg->id = ++env->id_gen;
continue;
@@ -6352,7 +6405,7 @@ const struct bpf_func_proto bpf_btf_find_by_name_kind_proto = {
.func = bpf_btf_find_by_name_kind,
.gpl_only = false,
.ret_type = RET_INTEGER,
- .arg1_type = ARG_PTR_TO_MEM,
+ .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg2_type = ARG_CONST_SIZE,
.arg3_type = ARG_ANYTHING,
.arg4_type = ARG_ANYTHING,
@@ -6534,12 +6587,11 @@ static struct bpf_cand_cache *populate_cand_cache(struct bpf_cand_cache *cands,
bpf_free_cands_from_cache(*cc);
*cc = NULL;
}
- new_cands = kmalloc(sizeof_cands(cands->cnt), GFP_KERNEL);
+ new_cands = kmemdup(cands, sizeof_cands(cands->cnt), GFP_KERNEL);
if (!new_cands) {
bpf_free_cands(cands);
return ERR_PTR(-ENOMEM);
}
- memcpy(new_cands, cands, sizeof_cands(cands->cnt));
/* strdup the name, since it will stay in cache.
* the cands->name points to strings in prog's BTF and the prog can be unloaded.
*/
@@ -6657,7 +6709,7 @@ bpf_core_find_cands(struct bpf_core_ctx *ctx, u32 local_type_id)
main_btf = bpf_get_btf_vmlinux();
if (IS_ERR(main_btf))
- return (void *)main_btf;
+ return ERR_CAST(main_btf);
local_type = btf_type_by_id(local_btf, local_type_id);
if (!local_type)
@@ -6684,14 +6736,14 @@ bpf_core_find_cands(struct bpf_core_ctx *ctx, u32 local_type_id)
/* Attempt to find target candidates in vmlinux BTF first */
cands = bpf_core_add_cands(cands, main_btf, 1);
if (IS_ERR(cands))
- return cands;
+ return ERR_CAST(cands);
/* cands is a pointer to kmalloced memory here if cands->cnt > 0 */
/* populate cache even when cands->cnt == 0 */
cc = populate_cand_cache(cands, vmlinux_cand_cache, VMLINUX_CAND_CACHE_SIZE);
if (IS_ERR(cc))
- return cc;
+ return ERR_CAST(cc);
/* if vmlinux BTF has any candidate, don't go for module BTFs */
if (cc->cnt)
@@ -6717,7 +6769,7 @@ check_modules:
cands = bpf_core_add_cands(cands, mod_btf, btf_nr_types(main_btf));
if (IS_ERR(cands)) {
btf_put(mod_btf);
- return cands;
+ return ERR_CAST(cands);
}
spin_lock_bh(&btf_idr_lock);
btf_put(mod_btf);
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 43eb3501721b..514b4681a90a 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1789,7 +1789,7 @@ static const struct bpf_func_proto bpf_sysctl_set_new_value_proto = {
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE,
};
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 585b2b77ccc4..0421061d95f1 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -195,7 +195,7 @@ static void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu,
}
return;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(NULL, rcpu->prog, act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(skb->dev, rcpu->prog, act);
@@ -254,7 +254,7 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
}
break;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(NULL, rcpu->prog, act);
fallthrough;
case XDP_DROP:
xdp_return_frame(xdpf);
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index f02d04540c0c..6feea293ff10 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -348,7 +348,7 @@ static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog,
frames[nframes++] = xdpf;
break;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(NULL, xdp_prog, act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(dev, xdp_prog, act);
@@ -507,7 +507,7 @@ static u32 dev_map_bpf_prog_run_skb(struct sk_buff *skb, struct bpf_dtab_netdev
__skb_push(skb, skb->mac_len);
break;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(NULL, dst->xdp_prog, act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(dst->dev, dst->xdp_prog, act);
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 19fecfeaa9c2..01cfdf40c838 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -2,6 +2,7 @@
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
*/
#include <linux/bpf.h>
+#include <linux/bpf-cgroup.h>
#include <linux/rcupdate.h>
#include <linux/random.h>
#include <linux/smp.h>
@@ -530,7 +531,7 @@ const struct bpf_func_proto bpf_strtol_proto = {
.func = bpf_strtol,
.gpl_only = false,
.ret_type = RET_INTEGER,
- .arg1_type = ARG_PTR_TO_MEM,
+ .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg2_type = ARG_CONST_SIZE,
.arg3_type = ARG_ANYTHING,
.arg4_type = ARG_PTR_TO_LONG,
@@ -558,13 +559,27 @@ const struct bpf_func_proto bpf_strtoul_proto = {
.func = bpf_strtoul,
.gpl_only = false,
.ret_type = RET_INTEGER,
- .arg1_type = ARG_PTR_TO_MEM,
+ .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg2_type = ARG_CONST_SIZE,
.arg3_type = ARG_ANYTHING,
.arg4_type = ARG_PTR_TO_LONG,
};
#endif
+BPF_CALL_3(bpf_strncmp, const char *, s1, u32, s1_sz, const char *, s2)
+{
+ return strncmp(s1, s2, s1_sz);
+}
+
+const struct bpf_func_proto bpf_strncmp_proto = {
+ .func = bpf_strncmp,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_CONST_SIZE,
+ .arg3_type = ARG_PTR_TO_CONST_STR,
+};
+
BPF_CALL_4(bpf_get_ns_current_pid_tgid, u64, dev, u64, ino,
struct bpf_pidns_info *, nsdata, u32, size)
{
@@ -630,7 +645,7 @@ const struct bpf_func_proto bpf_event_output_data_proto = {
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_CONST_MAP_PTR,
.arg3_type = ARG_ANYTHING,
- .arg4_type = ARG_PTR_TO_MEM,
+ .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg5_type = ARG_CONST_SIZE_OR_ZERO,
};
@@ -667,7 +682,7 @@ BPF_CALL_2(bpf_per_cpu_ptr, const void *, ptr, u32, cpu)
const struct bpf_func_proto bpf_per_cpu_ptr_proto = {
.func = bpf_per_cpu_ptr,
.gpl_only = false,
- .ret_type = RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL,
+ .ret_type = RET_PTR_TO_MEM_OR_BTF_ID | PTR_MAYBE_NULL | MEM_RDONLY,
.arg1_type = ARG_PTR_TO_PERCPU_BTF_ID,
.arg2_type = ARG_ANYTHING,
};
@@ -680,7 +695,7 @@ BPF_CALL_1(bpf_this_cpu_ptr, const void *, percpu_ptr)
const struct bpf_func_proto bpf_this_cpu_ptr_proto = {
.func = bpf_this_cpu_ptr,
.gpl_only = false,
- .ret_type = RET_PTR_TO_MEM_OR_BTF_ID,
+ .ret_type = RET_PTR_TO_MEM_OR_BTF_ID | MEM_RDONLY,
.arg1_type = ARG_PTR_TO_PERCPU_BTF_ID,
};
@@ -1011,7 +1026,7 @@ const struct bpf_func_proto bpf_snprintf_proto = {
.arg1_type = ARG_PTR_TO_MEM_OR_NULL,
.arg2_type = ARG_CONST_SIZE_OR_ZERO,
.arg3_type = ARG_PTR_TO_CONST_STR,
- .arg4_type = ARG_PTR_TO_MEM_OR_NULL,
+ .arg4_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY,
.arg5_type = ARG_CONST_SIZE_OR_ZERO,
};
@@ -1378,6 +1393,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
return &bpf_for_each_map_elem_proto;
case BPF_FUNC_loop:
return &bpf_loop_proto;
+ case BPF_FUNC_strncmp:
+ return &bpf_strncmp_proto;
default:
break;
}
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index 035e9e3a7132..23f7f9d08a62 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -163,8 +163,7 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *key,
return 0;
}
- new = bpf_map_kmalloc_node(map, sizeof(struct bpf_storage_buffer) +
- map->value_size,
+ new = bpf_map_kmalloc_node(map, struct_size(new, data, map->value_size),
__GFP_ZERO | GFP_ATOMIC | __GFP_NOWARN,
map->numa_node);
if (!new)
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 423549d2c52e..5763cc7ac4f1 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -412,7 +412,7 @@ static int trie_update_elem(struct bpf_map *map,
rcu_assign_pointer(im_node->child[1], node);
}
- /* Finally, assign the intermediate node to the determined spot */
+ /* Finally, assign the intermediate node to the determined slot */
rcu_assign_pointer(*slot, im_node);
out:
diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c
index 6a9542af4212..b0fa190b0979 100644
--- a/kernel/bpf/map_iter.c
+++ b/kernel/bpf/map_iter.c
@@ -174,9 +174,9 @@ static const struct bpf_iter_reg bpf_map_elem_reg_info = {
.ctx_arg_info_size = 2,
.ctx_arg_info = {
{ offsetof(struct bpf_iter__bpf_map_elem, key),
- PTR_TO_RDONLY_BUF_OR_NULL },
+ PTR_TO_BUF | PTR_MAYBE_NULL | MEM_RDONLY },
{ offsetof(struct bpf_iter__bpf_map_elem, value),
- PTR_TO_RDWR_BUF_OR_NULL },
+ PTR_TO_BUF | PTR_MAYBE_NULL },
},
};
diff --git a/kernel/bpf/net_namespace.c b/kernel/bpf/net_namespace.c
index 542f275bf252..868cc2c43899 100644
--- a/kernel/bpf/net_namespace.c
+++ b/kernel/bpf/net_namespace.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
+#include <linux/bpf-netns.h>
#include <linux/filter.h>
#include <net/net_namespace.h>
diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c
index 93a55391791a..556a769b5b80 100644
--- a/kernel/bpf/reuseport_array.c
+++ b/kernel/bpf/reuseport_array.c
@@ -152,16 +152,12 @@ static struct bpf_map *reuseport_array_alloc(union bpf_attr *attr)
{
int numa_node = bpf_map_attr_numa_node(attr);
struct reuseport_array *array;
- u64 array_size;
if (!bpf_capable())
return ERR_PTR(-EPERM);
- array_size = sizeof(*array);
- array_size += (u64)attr->max_entries * sizeof(struct sock *);
-
/* allocate all map elements and zero-initialize them */
- array = bpf_map_area_alloc(array_size, numa_node);
+ array = bpf_map_area_alloc(struct_size(array, ptrs, attr->max_entries), numa_node);
if (!array)
return ERR_PTR(-ENOMEM);
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index 9e0c10c6892a..638d7fd7b375 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -444,7 +444,7 @@ const struct bpf_func_proto bpf_ringbuf_output_proto = {
.func = bpf_ringbuf_output,
.ret_type = RET_INTEGER,
.arg1_type = ARG_CONST_MAP_PTR,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE_OR_ZERO,
.arg4_type = ARG_ANYTHING,
};
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index ddd81d543203..fa4505f9b611 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2,6 +2,7 @@
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
*/
#include <linux/bpf.h>
+#include <linux/bpf-cgroup.h>
#include <linux/bpf_trace.h>
#include <linux/bpf_lirc.h>
#include <linux/bpf_verifier.h>
@@ -4772,7 +4773,7 @@ static const struct bpf_func_proto bpf_sys_bpf_proto = {
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_ANYTHING,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE,
};
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index e98de5e73ba5..4b6974a195c1 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -27,6 +27,14 @@ static struct hlist_head trampoline_table[TRAMPOLINE_TABLE_SIZE];
/* serializes access to trampoline_table */
static DEFINE_MUTEX(trampoline_mutex);
+bool bpf_prog_has_trampoline(const struct bpf_prog *prog)
+{
+ enum bpf_attach_type eatype = prog->expected_attach_type;
+
+ return eatype == BPF_TRACE_FENTRY || eatype == BPF_TRACE_FEXIT ||
+ eatype == BPF_MODIFY_RETURN;
+}
+
void *bpf_jit_alloc_exec_page(void)
{
void *image;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index cd79bb12d076..b70c66c6db3b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4,6 +4,7 @@
* Copyright (c) 2018 Covalent IO, Inc. http://covalent.io
*/
#include <uapi/linux/btf.h>
+#include <linux/bpf-cgroup.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/slab.h>
@@ -441,18 +442,6 @@ static bool reg_type_not_null(enum bpf_reg_type type)
type == PTR_TO_SOCK_COMMON;
}
-static bool reg_type_may_be_null(enum bpf_reg_type type)
-{
- return type == PTR_TO_MAP_VALUE_OR_NULL ||
- type == PTR_TO_SOCKET_OR_NULL ||
- type == PTR_TO_SOCK_COMMON_OR_NULL ||
- type == PTR_TO_TCP_SOCK_OR_NULL ||
- type == PTR_TO_BTF_ID_OR_NULL ||
- type == PTR_TO_MEM_OR_NULL ||
- type == PTR_TO_RDONLY_BUF_OR_NULL ||
- type == PTR_TO_RDWR_BUF_OR_NULL;
-}
-
static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg)
{
return reg->type == PTR_TO_MAP_VALUE &&
@@ -461,12 +450,14 @@ static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg)
static bool reg_type_may_be_refcounted_or_null(enum bpf_reg_type type)
{
- return type == PTR_TO_SOCKET ||
- type == PTR_TO_SOCKET_OR_NULL ||
- type == PTR_TO_TCP_SOCK ||
- type == PTR_TO_TCP_SOCK_OR_NULL ||
- type == PTR_TO_MEM ||
- type == PTR_TO_MEM_OR_NULL;
+ return base_type(type) == PTR_TO_SOCKET ||
+ base_type(type) == PTR_TO_TCP_SOCK ||
+ base_type(type) == PTR_TO_MEM;
+}
+
+static bool type_is_rdonly_mem(u32 type)
+{
+ return type & MEM_RDONLY;
}
static bool arg_type_may_be_refcounted(enum bpf_arg_type type)
@@ -474,14 +465,9 @@ static bool arg_type_may_be_refcounted(enum bpf_arg_type type)
return type == ARG_PTR_TO_SOCK_COMMON;
}
-static bool arg_type_may_be_null(enum bpf_arg_type type)
+static bool type_may_be_null(u32 type)
{
- return type == ARG_PTR_TO_MAP_VALUE_OR_NULL ||
- type == ARG_PTR_TO_MEM_OR_NULL ||
- type == ARG_PTR_TO_CTX_OR_NULL ||
- type == ARG_PTR_TO_SOCKET_OR_NULL ||
- type == ARG_PTR_TO_ALLOC_MEM_OR_NULL ||
- type == ARG_PTR_TO_STACK_OR_NULL;
+ return type & PTR_MAYBE_NULL;
}
/* Determine whether the function releases some resources allocated by another
@@ -541,39 +527,54 @@ static bool is_cmpxchg_insn(const struct bpf_insn *insn)
insn->imm == BPF_CMPXCHG;
}
-/* string representation of 'enum bpf_reg_type' */
-static const char * const reg_type_str[] = {
- [NOT_INIT] = "?",
- [SCALAR_VALUE] = "inv",
- [PTR_TO_CTX] = "ctx",
- [CONST_PTR_TO_MAP] = "map_ptr",
- [PTR_TO_MAP_VALUE] = "map_value",
- [PTR_TO_MAP_VALUE_OR_NULL] = "map_value_or_null",
- [PTR_TO_STACK] = "fp",
- [PTR_TO_PACKET] = "pkt",
- [PTR_TO_PACKET_META] = "pkt_meta",
- [PTR_TO_PACKET_END] = "pkt_end",
- [PTR_TO_FLOW_KEYS] = "flow_keys",
- [PTR_TO_SOCKET] = "sock",
- [PTR_TO_SOCKET_OR_NULL] = "sock_or_null",
- [PTR_TO_SOCK_COMMON] = "sock_common",
- [PTR_TO_SOCK_COMMON_OR_NULL] = "sock_common_or_null",
- [PTR_TO_TCP_SOCK] = "tcp_sock",
- [PTR_TO_TCP_SOCK_OR_NULL] = "tcp_sock_or_null",
- [PTR_TO_TP_BUFFER] = "tp_buffer",
- [PTR_TO_XDP_SOCK] = "xdp_sock",
- [PTR_TO_BTF_ID] = "ptr_",
- [PTR_TO_BTF_ID_OR_NULL] = "ptr_or_null_",
- [PTR_TO_PERCPU_BTF_ID] = "percpu_ptr_",
- [PTR_TO_MEM] = "mem",
- [PTR_TO_MEM_OR_NULL] = "mem_or_null",
- [PTR_TO_RDONLY_BUF] = "rdonly_buf",
- [PTR_TO_RDONLY_BUF_OR_NULL] = "rdonly_buf_or_null",
- [PTR_TO_RDWR_BUF] = "rdwr_buf",
- [PTR_TO_RDWR_BUF_OR_NULL] = "rdwr_buf_or_null",
- [PTR_TO_FUNC] = "func",
- [PTR_TO_MAP_KEY] = "map_key",
-};
+/* string representation of 'enum bpf_reg_type'
+ *
+ * Note that reg_type_str() can not appear more than once in a single verbose()
+ * statement.
+ */
+static const char *reg_type_str(struct bpf_verifier_env *env,
+ enum bpf_reg_type type)
+{
+ char postfix[16] = {0}, prefix[16] = {0};
+ static const char * const str[] = {
+ [NOT_INIT] = "?",
+ [SCALAR_VALUE] = "inv",
+ [PTR_TO_CTX] = "ctx",
+ [CONST_PTR_TO_MAP] = "map_ptr",
+ [PTR_TO_MAP_VALUE] = "map_value",
+ [PTR_TO_STACK] = "fp",
+ [PTR_TO_PACKET] = "pkt",
+ [PTR_TO_PACKET_META] = "pkt_meta",
+ [PTR_TO_PACKET_END] = "pkt_end",
+ [PTR_TO_FLOW_KEYS] = "flow_keys",
+ [PTR_TO_SOCKET] = "sock",
+ [PTR_TO_SOCK_COMMON] = "sock_common",
+ [PTR_TO_TCP_SOCK] = "tcp_sock",
+ [PTR_TO_TP_BUFFER] = "tp_buffer",
+ [PTR_TO_XDP_SOCK] = "xdp_sock",
+ [PTR_TO_BTF_ID] = "ptr_",
+ [PTR_TO_PERCPU_BTF_ID] = "percpu_ptr_",
+ [PTR_TO_MEM] = "mem",
+ [PTR_TO_BUF] = "buf",
+ [PTR_TO_FUNC] = "func",
+ [PTR_TO_MAP_KEY] = "map_key",
+ };
+
+ if (type & PTR_MAYBE_NULL) {
+ if (base_type(type) == PTR_TO_BTF_ID ||
+ base_type(type) == PTR_TO_PERCPU_BTF_ID)
+ strncpy(postfix, "or_null_", 16);
+ else
+ strncpy(postfix, "_or_null", 16);
+ }
+
+ if (type & MEM_RDONLY)
+ strncpy(prefix, "rdonly_", 16);
+
+ snprintf(env->type_str_buf, TYPE_STR_BUF_LEN, "%s%s%s",
+ prefix, str[base_type(type)], postfix);
+ return env->type_str_buf;
+}
static char slot_type_char[] = {
[STACK_INVALID] = '?',
@@ -608,6 +609,44 @@ static const char *kernel_type_name(const struct btf* btf, u32 id)
return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off);
}
+static void mark_reg_scratched(struct bpf_verifier_env *env, u32 regno)
+{
+ env->scratched_regs |= 1U << regno;
+}
+
+static void mark_stack_slot_scratched(struct bpf_verifier_env *env, u32 spi)
+{
+ env->scratched_stack_slots |= 1UL << spi;
+}
+
+static bool reg_scratched(const struct bpf_verifier_env *env, u32 regno)
+{
+ return (env->scratched_regs >> regno) & 1;
+}
+
+static bool stack_slot_scratched(const struct bpf_verifier_env *env, u64 regno)
+{
+ return (env->scratched_stack_slots >> regno) & 1;
+}
+
+static bool verifier_state_scratched(const struct bpf_verifier_env *env)
+{
+ return env->scratched_regs || env->scratched_stack_slots;
+}
+
+static void mark_verifier_state_clean(struct bpf_verifier_env *env)
+{
+ env->scratched_regs = 0U;
+ env->scratched_stack_slots = 0UL;
+}
+
+/* Used for printing the entire verifier state. */
+static void mark_verifier_state_scratched(struct bpf_verifier_env *env)
+{
+ env->scratched_regs = ~0U;
+ env->scratched_stack_slots = ~0UL;
+}
+
/* The reg state of a pointer or a bounded scalar was saved when
* it was spilled to the stack.
*/
@@ -623,7 +662,8 @@ static void scrub_spilled_slot(u8 *stype)
}
static void print_verifier_state(struct bpf_verifier_env *env,
- const struct bpf_func_state *state)
+ const struct bpf_func_state *state,
+ bool print_all)
{
const struct bpf_reg_state *reg;
enum bpf_reg_type t;
@@ -636,9 +676,11 @@ static void print_verifier_state(struct bpf_verifier_env *env,
t = reg->type;
if (t == NOT_INIT)
continue;
+ if (!print_all && !reg_scratched(env, i))
+ continue;
verbose(env, " R%d", i);
print_liveness(env, reg->live);
- verbose(env, "=%s", reg_type_str[t]);
+ verbose(env, "=%s", reg_type_str(env, t));
if (t == SCALAR_VALUE && reg->precise)
verbose(env, "P");
if ((t == SCALAR_VALUE || t == PTR_TO_STACK) &&
@@ -646,9 +688,8 @@ static void print_verifier_state(struct bpf_verifier_env *env,
/* reg->off should be 0 for SCALAR_VALUE */
verbose(env, "%lld", reg->var_off.value + reg->off);
} else {
- if (t == PTR_TO_BTF_ID ||
- t == PTR_TO_BTF_ID_OR_NULL ||
- t == PTR_TO_PERCPU_BTF_ID)
+ if (base_type(t) == PTR_TO_BTF_ID ||
+ base_type(t) == PTR_TO_PERCPU_BTF_ID)
verbose(env, "%s", kernel_type_name(reg->btf, reg->btf_id));
verbose(env, "(id=%d", reg->id);
if (reg_type_may_be_refcounted_or_null(t))
@@ -657,10 +698,9 @@ static void print_verifier_state(struct bpf_verifier_env *env,
verbose(env, ",off=%d", reg->off);
if (type_is_pkt_pointer(t))
verbose(env, ",r=%d", reg->range);
- else if (t == CONST_PTR_TO_MAP ||
- t == PTR_TO_MAP_KEY ||
- t == PTR_TO_MAP_VALUE ||
- t == PTR_TO_MAP_VALUE_OR_NULL)
+ else if (base_type(t) == CONST_PTR_TO_MAP ||
+ base_type(t) == PTR_TO_MAP_KEY ||
+ base_type(t) == PTR_TO_MAP_VALUE)
verbose(env, ",ks=%d,vs=%d",
reg->map_ptr->key_size,
reg->map_ptr->value_size);
@@ -725,12 +765,14 @@ static void print_verifier_state(struct bpf_verifier_env *env,
types_buf[BPF_REG_SIZE] = 0;
if (!valid)
continue;
+ if (!print_all && !stack_slot_scratched(env, i))
+ continue;
verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
print_liveness(env, state->stack[i].spilled_ptr.live);
if (is_spilled_reg(&state->stack[i])) {
reg = &state->stack[i].spilled_ptr;
t = reg->type;
- verbose(env, "=%s", reg_type_str[t]);
+ verbose(env, "=%s", reg_type_str(env, t));
if (t == SCALAR_VALUE && reg->precise)
verbose(env, "P");
if (t == SCALAR_VALUE && tnum_is_const(reg->var_off))
@@ -750,6 +792,26 @@ static void print_verifier_state(struct bpf_verifier_env *env,
if (state->in_async_callback_fn)
verbose(env, " async_cb");
verbose(env, "\n");
+ mark_verifier_state_clean(env);
+}
+
+static inline u32 vlog_alignment(u32 pos)
+{
+ return round_up(max(pos + BPF_LOG_MIN_ALIGNMENT / 2, BPF_LOG_ALIGNMENT),
+ BPF_LOG_MIN_ALIGNMENT) - pos - 1;
+}
+
+static void print_insn_state(struct bpf_verifier_env *env,
+ const struct bpf_func_state *state)
+{
+ if (env->prev_log_len && env->prev_log_len == env->log.len_used) {
+ /* remove new line character */
+ bpf_vlog_reset(&env->log, env->prev_log_len - 1);
+ verbose(env, "%*c;", vlog_alignment(env->prev_insn_print_len), ' ');
+ } else {
+ verbose(env, "%d:", env->insn_idx);
+ }
+ print_verifier_state(env, state, false);
}
/* copy array src of length n * size bytes to dst. dst is reallocated if it's too
@@ -1143,8 +1205,7 @@ static void mark_reg_known_zero(struct bpf_verifier_env *env,
static void mark_ptr_not_null_reg(struct bpf_reg_state *reg)
{
- switch (reg->type) {
- case PTR_TO_MAP_VALUE_OR_NULL: {
+ if (base_type(reg->type) == PTR_TO_MAP_VALUE) {
const struct bpf_map *map = reg->map_ptr;
if (map->inner_map_meta) {
@@ -1163,32 +1224,10 @@ static void mark_ptr_not_null_reg(struct bpf_reg_state *reg)
} else {
reg->type = PTR_TO_MAP_VALUE;
}
- break;
- }
- case PTR_TO_SOCKET_OR_NULL:
- reg->type = PTR_TO_SOCKET;
- break;
- case PTR_TO_SOCK_COMMON_OR_NULL:
- reg->type = PTR_TO_SOCK_COMMON;
- break;
- case PTR_TO_TCP_SOCK_OR_NULL:
- reg->type = PTR_TO_TCP_SOCK;
- break;
- case PTR_TO_BTF_ID_OR_NULL:
- reg->type = PTR_TO_BTF_ID;
- break;
- case PTR_TO_MEM_OR_NULL:
- reg->type = PTR_TO_MEM;
- break;
- case PTR_TO_RDONLY_BUF_OR_NULL:
- reg->type = PTR_TO_RDONLY_BUF;
- break;
- case PTR_TO_RDWR_BUF_OR_NULL:
- reg->type = PTR_TO_RDWR_BUF;
- break;
- default:
- WARN_ONCE(1, "unknown nullable register type");
+ return;
}
+
+ reg->type &= ~PTR_MAYBE_NULL;
}
static bool reg_is_pkt_pointer(const struct bpf_reg_state *reg)
@@ -1546,6 +1585,7 @@ static void init_func_state(struct bpf_verifier_env *env,
state->frameno = frameno;
state->subprogno = subprogno;
init_reg_state(env, state);
+ mark_verifier_state_scratched(env);
}
/* Similar to push_stack(), but for async callbacks */
@@ -2049,7 +2089,7 @@ static int mark_reg_read(struct bpf_verifier_env *env,
break;
if (parent->live & REG_LIVE_DONE) {
verbose(env, "verifier BUG type %s var_off %lld off %d\n",
- reg_type_str[parent->type],
+ reg_type_str(env, parent->type),
parent->var_off.value, parent->off);
return -EFAULT;
}
@@ -2233,6 +2273,8 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
return -EINVAL;
}
+ mark_reg_scratched(env, regno);
+
reg = &regs[regno];
rw64 = is_reg64(env, insn, regno, reg, t);
if (t == SRC_OP) {
@@ -2337,7 +2379,7 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
if (insn->code == 0)
return 0;
- if (env->log.level & BPF_LOG_LEVEL) {
+ if (env->log.level & BPF_LOG_LEVEL2) {
verbose(env, "regs=%x stack=%llx before ", *reg_mask, *stack_mask);
verbose(env, "%d: ", idx);
print_bpf_insn(&cbs, insn, env->allow_ptr_leaks);
@@ -2591,7 +2633,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno,
DECLARE_BITMAP(mask, 64);
u32 history = st->jmp_history_cnt;
- if (env->log.level & BPF_LOG_LEVEL)
+ if (env->log.level & BPF_LOG_LEVEL2)
verbose(env, "last_idx %d first_idx %d\n", last_idx, first_idx);
for (i = last_idx;;) {
if (skip_first) {
@@ -2678,11 +2720,11 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno,
new_marks = true;
reg->precise = true;
}
- if (env->log.level & BPF_LOG_LEVEL) {
- print_verifier_state(env, func);
- verbose(env, "parent %s regs=%x stack=%llx marks\n",
+ if (env->log.level & BPF_LOG_LEVEL2) {
+ verbose(env, "parent %s regs=%x stack=%llx marks:",
new_marks ? "didn't have" : "already had",
reg_mask, stack_mask);
+ print_verifier_state(env, func, true);
}
if (!reg_mask && !stack_mask)
@@ -2708,9 +2750,8 @@ static int mark_chain_precision_stack(struct bpf_verifier_env *env, int spi)
static bool is_spillable_regtype(enum bpf_reg_type type)
{
- switch (type) {
+ switch (base_type(type)) {
case PTR_TO_MAP_VALUE:
- case PTR_TO_MAP_VALUE_OR_NULL:
case PTR_TO_STACK:
case PTR_TO_CTX:
case PTR_TO_PACKET:
@@ -2719,21 +2760,13 @@ static bool is_spillable_regtype(enum bpf_reg_type type)
case PTR_TO_FLOW_KEYS:
case CONST_PTR_TO_MAP:
case PTR_TO_SOCKET:
- case PTR_TO_SOCKET_OR_NULL:
case PTR_TO_SOCK_COMMON:
- case PTR_TO_SOCK_COMMON_OR_NULL:
case PTR_TO_TCP_SOCK:
- case PTR_TO_TCP_SOCK_OR_NULL:
case PTR_TO_XDP_SOCK:
case PTR_TO_BTF_ID:
- case PTR_TO_BTF_ID_OR_NULL:
- case PTR_TO_RDONLY_BUF:
- case PTR_TO_RDONLY_BUF_OR_NULL:
- case PTR_TO_RDWR_BUF:
- case PTR_TO_RDWR_BUF_OR_NULL:
+ case PTR_TO_BUF:
case PTR_TO_PERCPU_BTF_ID:
case PTR_TO_MEM:
- case PTR_TO_MEM_OR_NULL:
case PTR_TO_FUNC:
case PTR_TO_MAP_KEY:
return true;
@@ -2838,6 +2871,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
env->insn_aux_data[insn_idx].sanitize_stack_spill = true;
}
+ mark_stack_slot_scratched(env, spi);
if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) &&
!register_is_null(reg) && env->bpf_capable) {
if (dst_reg != BPF_REG_FP) {
@@ -2959,6 +2993,7 @@ static int check_stack_write_var_off(struct bpf_verifier_env *env,
slot = -i - 1;
spi = slot / BPF_REG_SIZE;
stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE];
+ mark_stack_slot_scratched(env, spi);
if (!env->allow_ptr_leaks
&& *stype != NOT_INIT
@@ -3375,11 +3410,8 @@ static int check_mem_region_access(struct bpf_verifier_env *env, u32 regno,
/* We may have adjusted the register pointing to memory region, so we
* need to try adding each of min_value and max_value to off
* to make sure our theoretical access will be safe.
- */
- if (env->log.level & BPF_LOG_LEVEL)
- print_verifier_state(env, state);
-
- /* The minimum value is only important with signed
+ *
+ * The minimum value is only important with signed
* comparisons where we can't assume the floor of a
* value is 0. If we are using signed variables for our
* index'es we need to make sure that whatever we use
@@ -3574,7 +3606,7 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off,
*/
*reg_type = info.reg_type;
- if (*reg_type == PTR_TO_BTF_ID || *reg_type == PTR_TO_BTF_ID_OR_NULL) {
+ if (base_type(*reg_type) == PTR_TO_BTF_ID) {
*btf = info.btf;
*btf_id = info.btf_id;
} else {
@@ -3642,7 +3674,7 @@ static int check_sock_access(struct bpf_verifier_env *env, int insn_idx,
}
verbose(env, "R%d invalid %s access off=%d size=%d\n",
- regno, reg_type_str[reg->type], off, size);
+ regno, reg_type_str(env, reg->type), off, size);
return -EACCES;
}
@@ -4369,15 +4401,30 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
mark_reg_unknown(env, regs, value_regno);
}
}
- } else if (reg->type == PTR_TO_MEM) {
+ } else if (base_type(reg->type) == PTR_TO_MEM) {
+ bool rdonly_mem = type_is_rdonly_mem(reg->type);
+
+ if (type_may_be_null(reg->type)) {
+ verbose(env, "R%d invalid mem access '%s'\n", regno,
+ reg_type_str(env, reg->type));
+ return -EACCES;
+ }
+
+ if (t == BPF_WRITE && rdonly_mem) {
+ verbose(env, "R%d cannot write into %s\n",
+ regno, reg_type_str(env, reg->type));
+ return -EACCES;
+ }
+
if (t == BPF_WRITE && value_regno >= 0 &&
is_pointer_value(env, value_regno)) {
verbose(env, "R%d leaks addr into mem\n", value_regno);
return -EACCES;
}
+
err = check_mem_region_access(env, regno, off, size,
reg->mem_size, false);
- if (!err && t == BPF_READ && value_regno >= 0)
+ if (!err && value_regno >= 0 && (t == BPF_READ || rdonly_mem))
mark_reg_unknown(env, regs, value_regno);
} else if (reg->type == PTR_TO_CTX) {
enum bpf_reg_type reg_type = SCALAR_VALUE;
@@ -4407,7 +4454,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
} else {
mark_reg_known_zero(env, regs,
value_regno);
- if (reg_type_may_be_null(reg_type))
+ if (type_may_be_null(reg_type))
regs[value_regno].id = ++env->id_gen;
/* A load of ctx field could have different
* actual load size with the one encoded in the
@@ -4415,8 +4462,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
* a sub-register.
*/
regs[value_regno].subreg_def = DEF_NOT_SUBREG;
- if (reg_type == PTR_TO_BTF_ID ||
- reg_type == PTR_TO_BTF_ID_OR_NULL) {
+ if (base_type(reg_type) == PTR_TO_BTF_ID) {
regs[value_regno].btf = btf;
regs[value_regno].btf_id = btf_id;
}
@@ -4469,7 +4515,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
} else if (type_is_sk_pointer(reg->type)) {
if (t == BPF_WRITE) {
verbose(env, "R%d cannot write into %s\n",
- regno, reg_type_str[reg->type]);
+ regno, reg_type_str(env, reg->type));
return -EACCES;
}
err = check_sock_access(env, insn_idx, regno, off, size, t);
@@ -4485,26 +4531,32 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
} else if (reg->type == CONST_PTR_TO_MAP) {
err = check_ptr_to_map_access(env, regs, regno, off, size, t,
value_regno);
- } else if (reg->type == PTR_TO_RDONLY_BUF) {
- if (t == BPF_WRITE) {
- verbose(env, "R%d cannot write into %s\n",
- regno, reg_type_str[reg->type]);
- return -EACCES;
+ } else if (base_type(reg->type) == PTR_TO_BUF) {
+ bool rdonly_mem = type_is_rdonly_mem(reg->type);
+ const char *buf_info;
+ u32 *max_access;
+
+ if (rdonly_mem) {
+ if (t == BPF_WRITE) {
+ verbose(env, "R%d cannot write into %s\n",
+ regno, reg_type_str(env, reg->type));
+ return -EACCES;
+ }
+ buf_info = "rdonly";
+ max_access = &env->prog->aux->max_rdonly_access;
+ } else {
+ buf_info = "rdwr";
+ max_access = &env->prog->aux->max_rdwr_access;
}
+
err = check_buffer_access(env, reg, regno, off, size, false,
- "rdonly",
- &env->prog->aux->max_rdonly_access);
- if (!err && value_regno >= 0)
- mark_reg_unknown(env, regs, value_regno);
- } else if (reg->type == PTR_TO_RDWR_BUF) {
- err = check_buffer_access(env, reg, regno, off, size, false,
- "rdwr",
- &env->prog->aux->max_rdwr_access);
- if (!err && t == BPF_READ && value_regno >= 0)
+ buf_info, max_access);
+
+ if (!err && value_regno >= 0 && (rdonly_mem || t == BPF_READ))
mark_reg_unknown(env, regs, value_regno);
} else {
verbose(env, "R%d invalid mem access '%s'\n", regno,
- reg_type_str[reg->type]);
+ reg_type_str(env, reg->type));
return -EACCES;
}
@@ -4578,7 +4630,7 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
is_sk_reg(env, insn->dst_reg)) {
verbose(env, "BPF_ATOMIC stores into R%d %s is not allowed\n",
insn->dst_reg,
- reg_type_str[reg_state(env, insn->dst_reg)->type]);
+ reg_type_str(env, reg_state(env, insn->dst_reg)->type));
return -EACCES;
}
@@ -4761,8 +4813,10 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
struct bpf_call_arg_meta *meta)
{
struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
+ const char *buf_info;
+ u32 *max_access;
- switch (reg->type) {
+ switch (base_type(reg->type)) {
case PTR_TO_PACKET:
case PTR_TO_PACKET_META:
return check_packet_access(env, regno, reg->off, access_size,
@@ -4781,18 +4835,20 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
return check_mem_region_access(env, regno, reg->off,
access_size, reg->mem_size,
zero_size_allowed);
- case PTR_TO_RDONLY_BUF:
- if (meta && meta->raw_mode)
- return -EACCES;
- return check_buffer_access(env, reg, regno, reg->off,
- access_size, zero_size_allowed,
- "rdonly",
- &env->prog->aux->max_rdonly_access);
- case PTR_TO_RDWR_BUF:
+ case PTR_TO_BUF:
+ if (type_is_rdonly_mem(reg->type)) {
+ if (meta && meta->raw_mode)
+ return -EACCES;
+
+ buf_info = "rdonly";
+ max_access = &env->prog->aux->max_rdonly_access;
+ } else {
+ buf_info = "rdwr";
+ max_access = &env->prog->aux->max_rdwr_access;
+ }
return check_buffer_access(env, reg, regno, reg->off,
access_size, zero_size_allowed,
- "rdwr",
- &env->prog->aux->max_rdwr_access);
+ buf_info, max_access);
case PTR_TO_STACK:
return check_stack_range_initialized(
env,
@@ -4804,9 +4860,9 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
register_is_null(reg))
return 0;
- verbose(env, "R%d type=%s expected=%s\n", regno,
- reg_type_str[reg->type],
- reg_type_str[PTR_TO_STACK]);
+ verbose(env, "R%d type=%s ", regno,
+ reg_type_str(env, reg->type));
+ verbose(env, "expected=%s\n", reg_type_str(env, PTR_TO_STACK));
return -EACCES;
}
}
@@ -4817,7 +4873,7 @@ int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
if (register_is_null(reg))
return 0;
- if (reg_type_may_be_null(reg->type)) {
+ if (type_may_be_null(reg->type)) {
/* Assuming that the register contains a value check if the memory
* access is safe. Temporarily save and restore the register's state as
* the conversion shouldn't be visible to a caller.
@@ -4965,9 +5021,8 @@ static int process_timer_func(struct bpf_verifier_env *env, int regno,
static bool arg_type_is_mem_ptr(enum bpf_arg_type type)
{
- return type == ARG_PTR_TO_MEM ||
- type == ARG_PTR_TO_MEM_OR_NULL ||
- type == ARG_PTR_TO_UNINIT_MEM;
+ return base_type(type) == ARG_PTR_TO_MEM ||
+ base_type(type) == ARG_PTR_TO_UNINIT_MEM;
}
static bool arg_type_is_mem_size(enum bpf_arg_type type)
@@ -5072,8 +5127,7 @@ static const struct bpf_reg_types mem_types = {
PTR_TO_MAP_KEY,
PTR_TO_MAP_VALUE,
PTR_TO_MEM,
- PTR_TO_RDONLY_BUF,
- PTR_TO_RDWR_BUF,
+ PTR_TO_BUF,
},
};
@@ -5104,31 +5158,26 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
[ARG_PTR_TO_MAP_KEY] = &map_key_value_types,
[ARG_PTR_TO_MAP_VALUE] = &map_key_value_types,
[ARG_PTR_TO_UNINIT_MAP_VALUE] = &map_key_value_types,
- [ARG_PTR_TO_MAP_VALUE_OR_NULL] = &map_key_value_types,
[ARG_CONST_SIZE] = &scalar_types,
[ARG_CONST_SIZE_OR_ZERO] = &scalar_types,
[ARG_CONST_ALLOC_SIZE_OR_ZERO] = &scalar_types,
[ARG_CONST_MAP_PTR] = &const_map_ptr_types,
[ARG_PTR_TO_CTX] = &context_types,
- [ARG_PTR_TO_CTX_OR_NULL] = &context_types,
[ARG_PTR_TO_SOCK_COMMON] = &sock_types,
#ifdef CONFIG_NET
[ARG_PTR_TO_BTF_ID_SOCK_COMMON] = &btf_id_sock_common_types,
#endif
[ARG_PTR_TO_SOCKET] = &fullsock_types,
- [ARG_PTR_TO_SOCKET_OR_NULL] = &fullsock_types,
[ARG_PTR_TO_BTF_ID] = &btf_ptr_types,
[ARG_PTR_TO_SPIN_LOCK] = &spin_lock_types,
[ARG_PTR_TO_MEM] = &mem_types,
- [ARG_PTR_TO_MEM_OR_NULL] = &mem_types,
[ARG_PTR_TO_UNINIT_MEM] = &mem_types,
[ARG_PTR_TO_ALLOC_MEM] = &alloc_mem_types,
- [ARG_PTR_TO_ALLOC_MEM_OR_NULL] = &alloc_mem_types,
[ARG_PTR_TO_INT] = &int_ptr_types,
[ARG_PTR_TO_LONG] = &int_ptr_types,
[ARG_PTR_TO_PERCPU_BTF_ID] = &percpu_btf_ptr_types,
[ARG_PTR_TO_FUNC] = &func_ptr_types,
- [ARG_PTR_TO_STACK_OR_NULL] = &stack_ptr_types,
+ [ARG_PTR_TO_STACK] = &stack_ptr_types,
[ARG_PTR_TO_CONST_STR] = &const_str_ptr_types,
[ARG_PTR_TO_TIMER] = &timer_types,
};
@@ -5142,12 +5191,27 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
const struct bpf_reg_types *compatible;
int i, j;
- compatible = compatible_reg_types[arg_type];
+ compatible = compatible_reg_types[base_type(arg_type)];
if (!compatible) {
verbose(env, "verifier internal error: unsupported arg type %d\n", arg_type);
return -EFAULT;
}
+ /* ARG_PTR_TO_MEM + RDONLY is compatible with PTR_TO_MEM and PTR_TO_MEM + RDONLY,
+ * but ARG_PTR_TO_MEM is compatible only with PTR_TO_MEM and NOT with PTR_TO_MEM + RDONLY
+ *
+ * Same for MAYBE_NULL:
+ *
+ * ARG_PTR_TO_MEM + MAYBE_NULL is compatible with PTR_TO_MEM and PTR_TO_MEM + MAYBE_NULL,
+ * but ARG_PTR_TO_MEM is compatible only with PTR_TO_MEM but NOT with PTR_TO_MEM + MAYBE_NULL
+ *
+ * Therefore we fold these flags depending on the arg_type before comparison.
+ */
+ if (arg_type & MEM_RDONLY)
+ type &= ~MEM_RDONLY;
+ if (arg_type & PTR_MAYBE_NULL)
+ type &= ~PTR_MAYBE_NULL;
+
for (i = 0; i < ARRAY_SIZE(compatible->types); i++) {
expected = compatible->types[i];
if (expected == NOT_INIT)
@@ -5157,14 +5221,14 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
goto found;
}
- verbose(env, "R%d type=%s expected=", regno, reg_type_str[type]);
+ verbose(env, "R%d type=%s expected=", regno, reg_type_str(env, reg->type));
for (j = 0; j + 1 < i; j++)
- verbose(env, "%s, ", reg_type_str[compatible->types[j]]);
- verbose(env, "%s\n", reg_type_str[compatible->types[j]]);
+ verbose(env, "%s, ", reg_type_str(env, compatible->types[j]));
+ verbose(env, "%s\n", reg_type_str(env, compatible->types[j]));
return -EACCES;
found:
- if (type == PTR_TO_BTF_ID) {
+ if (reg->type == PTR_TO_BTF_ID) {
if (!arg_btf_id) {
if (!compatible->btf_id) {
verbose(env, "verifier internal error: missing arg compatible BTF ID\n");
@@ -5223,15 +5287,14 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
return -EACCES;
}
- if (arg_type == ARG_PTR_TO_MAP_VALUE ||
- arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE ||
- arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL) {
+ if (base_type(arg_type) == ARG_PTR_TO_MAP_VALUE ||
+ base_type(arg_type) == ARG_PTR_TO_UNINIT_MAP_VALUE) {
err = resolve_map_arg_type(env, meta, &arg_type);
if (err)
return err;
}
- if (register_is_null(reg) && arg_type_may_be_null(arg_type))
+ if (register_is_null(reg) && type_may_be_null(arg_type))
/* A NULL register has a SCALAR_VALUE type, so skip
* type checking.
*/
@@ -5300,10 +5363,11 @@ skip_type_check:
err = check_helper_mem_access(env, regno,
meta->map_ptr->key_size, false,
NULL);
- } else if (arg_type == ARG_PTR_TO_MAP_VALUE ||
- (arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL &&
- !register_is_null(reg)) ||
- arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) {
+ } else if (base_type(arg_type) == ARG_PTR_TO_MAP_VALUE ||
+ base_type(arg_type) == ARG_PTR_TO_UNINIT_MAP_VALUE) {
+ if (type_may_be_null(arg_type) && register_is_null(reg))
+ return 0;
+
/* bpf_map_xxx(..., map_ptr, ..., value) call:
* check [value, value + map->value_size) validity
*/
@@ -6025,9 +6089,9 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn
if (env->log.level & BPF_LOG_LEVEL) {
verbose(env, "caller:\n");
- print_verifier_state(env, caller);
+ print_verifier_state(env, caller, true);
verbose(env, "callee:\n");
- print_verifier_state(env, callee);
+ print_verifier_state(env, callee, true);
}
return 0;
}
@@ -6242,9 +6306,9 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
*insn_idx = callee->callsite + 1;
if (env->log.level & BPF_LOG_LEVEL) {
verbose(env, "returning from callee:\n");
- print_verifier_state(env, callee);
+ print_verifier_state(env, callee, true);
verbose(env, "to caller at %d:\n", *insn_idx);
- print_verifier_state(env, caller);
+ print_verifier_state(env, caller, true);
}
/* clear everything in the callee */
free_func_state(callee);
@@ -6410,13 +6474,11 @@ static int check_bpf_snprintf_call(struct bpf_verifier_env *env,
static int check_get_func_ip(struct bpf_verifier_env *env)
{
- enum bpf_attach_type eatype = env->prog->expected_attach_type;
enum bpf_prog_type type = resolve_prog_type(env->prog);
int func_id = BPF_FUNC_get_func_ip;
if (type == BPF_PROG_TYPE_TRACING) {
- if (eatype != BPF_TRACE_FENTRY && eatype != BPF_TRACE_FEXIT &&
- eatype != BPF_MODIFY_RETURN) {
+ if (!bpf_prog_has_trampoline(env->prog)) {
verbose(env, "func %s#%d supported only for fentry/fexit/fmod_ret programs\n",
func_id_name(func_id), func_id);
return -ENOTSUPP;
@@ -6435,6 +6497,8 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
int *insn_idx_p)
{
const struct bpf_func_proto *fn = NULL;
+ enum bpf_return_type ret_type;
+ enum bpf_type_flag ret_flag;
struct bpf_reg_state *regs;
struct bpf_call_arg_meta meta;
int insn_idx = *insn_idx_p;
@@ -6574,13 +6638,14 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG;
/* update return register (already marked as written above) */
- if (fn->ret_type == RET_INTEGER) {
+ ret_type = fn->ret_type;
+ ret_flag = type_flag(fn->ret_type);
+ if (ret_type == RET_INTEGER) {
/* sets type to SCALAR_VALUE */
mark_reg_unknown(env, regs, BPF_REG_0);
- } else if (fn->ret_type == RET_VOID) {
+ } else if (ret_type == RET_VOID) {
regs[BPF_REG_0].type = NOT_INIT;
- } else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL ||
- fn->ret_type == RET_PTR_TO_MAP_VALUE) {
+ } else if (base_type(ret_type) == RET_PTR_TO_MAP_VALUE) {
/* There is no offset yet applied, variable or fixed */
mark_reg_known_zero(env, regs, BPF_REG_0);
/* remember map_ptr, so that check_map_access()
@@ -6594,28 +6659,25 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
}
regs[BPF_REG_0].map_ptr = meta.map_ptr;
regs[BPF_REG_0].map_uid = meta.map_uid;
- if (fn->ret_type == RET_PTR_TO_MAP_VALUE) {
- regs[BPF_REG_0].type = PTR_TO_MAP_VALUE;
- if (map_value_has_spin_lock(meta.map_ptr))
- regs[BPF_REG_0].id = ++env->id_gen;
- } else {
- regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
+ regs[BPF_REG_0].type = PTR_TO_MAP_VALUE | ret_flag;
+ if (!type_may_be_null(ret_type) &&
+ map_value_has_spin_lock(meta.map_ptr)) {
+ regs[BPF_REG_0].id = ++env->id_gen;
}
- } else if (fn->ret_type == RET_PTR_TO_SOCKET_OR_NULL) {
+ } else if (base_type(ret_type) == RET_PTR_TO_SOCKET) {
mark_reg_known_zero(env, regs, BPF_REG_0);
- regs[BPF_REG_0].type = PTR_TO_SOCKET_OR_NULL;
- } else if (fn->ret_type == RET_PTR_TO_SOCK_COMMON_OR_NULL) {
+ regs[BPF_REG_0].type = PTR_TO_SOCKET | ret_flag;
+ } else if (base_type(ret_type) == RET_PTR_TO_SOCK_COMMON) {
mark_reg_known_zero(env, regs, BPF_REG_0);
- regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON_OR_NULL;
- } else if (fn->ret_type == RET_PTR_TO_TCP_SOCK_OR_NULL) {
+ regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON | ret_flag;
+ } else if (base_type(ret_type) == RET_PTR_TO_TCP_SOCK) {
mark_reg_known_zero(env, regs, BPF_REG_0);
- regs[BPF_REG_0].type = PTR_TO_TCP_SOCK_OR_NULL;
- } else if (fn->ret_type == RET_PTR_TO_ALLOC_MEM_OR_NULL) {
+ regs[BPF_REG_0].type = PTR_TO_TCP_SOCK | ret_flag;
+ } else if (base_type(ret_type) == RET_PTR_TO_ALLOC_MEM) {
mark_reg_known_zero(env, regs, BPF_REG_0);
- regs[BPF_REG_0].type = PTR_TO_MEM_OR_NULL;
+ regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag;
regs[BPF_REG_0].mem_size = meta.mem_size;
- } else if (fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL ||
- fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID) {
+ } else if (base_type(ret_type) == RET_PTR_TO_MEM_OR_BTF_ID) {
const struct btf_type *t;
mark_reg_known_zero(env, regs, BPF_REG_0);
@@ -6633,29 +6695,30 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
tname, PTR_ERR(ret));
return -EINVAL;
}
- regs[BPF_REG_0].type =
- fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID ?
- PTR_TO_MEM : PTR_TO_MEM_OR_NULL;
+ regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag;
regs[BPF_REG_0].mem_size = tsize;
} else {
- regs[BPF_REG_0].type =
- fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID ?
- PTR_TO_BTF_ID : PTR_TO_BTF_ID_OR_NULL;
+ /* MEM_RDONLY may be carried from ret_flag, but it
+ * doesn't apply on PTR_TO_BTF_ID. Fold it, otherwise
+ * it will confuse the check of PTR_TO_BTF_ID in
+ * check_mem_access().
+ */
+ ret_flag &= ~MEM_RDONLY;
+
+ regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag;
regs[BPF_REG_0].btf = meta.ret_btf;
regs[BPF_REG_0].btf_id = meta.ret_btf_id;
}
- } else if (fn->ret_type == RET_PTR_TO_BTF_ID_OR_NULL ||
- fn->ret_type == RET_PTR_TO_BTF_ID) {
+ } else if (base_type(ret_type) == RET_PTR_TO_BTF_ID) {
int ret_btf_id;
mark_reg_known_zero(env, regs, BPF_REG_0);
- regs[BPF_REG_0].type = fn->ret_type == RET_PTR_TO_BTF_ID ?
- PTR_TO_BTF_ID :
- PTR_TO_BTF_ID_OR_NULL;
+ regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag;
ret_btf_id = *fn->ret_btf_id;
if (ret_btf_id == 0) {
- verbose(env, "invalid return type %d of func %s#%d\n",
- fn->ret_type, func_id_name(func_id), func_id);
+ verbose(env, "invalid return type %u of func %s#%d\n",
+ base_type(ret_type), func_id_name(func_id),
+ func_id);
return -EINVAL;
}
/* current BPF helper definitions are only coming from
@@ -6664,12 +6727,12 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
regs[BPF_REG_0].btf = btf_vmlinux;
regs[BPF_REG_0].btf_id = ret_btf_id;
} else {
- verbose(env, "unknown return type %d of func %s#%d\n",
- fn->ret_type, func_id_name(func_id), func_id);
+ verbose(env, "unknown return type %u of func %s#%d\n",
+ base_type(ret_type), func_id_name(func_id), func_id);
return -EINVAL;
}
- if (reg_type_may_be_null(regs[BPF_REG_0].type))
+ if (type_may_be_null(regs[BPF_REG_0].type))
regs[BPF_REG_0].id = ++env->id_gen;
if (is_ptr_cast_function(func_id)) {
@@ -6878,25 +6941,25 @@ static bool check_reg_sane_offset(struct bpf_verifier_env *env,
if (known && (val >= BPF_MAX_VAR_OFF || val <= -BPF_MAX_VAR_OFF)) {
verbose(env, "math between %s pointer and %lld is not allowed\n",
- reg_type_str[type], val);
+ reg_type_str(env, type), val);
return false;
}
if (reg->off >= BPF_MAX_VAR_OFF || reg->off <= -BPF_MAX_VAR_OFF) {
verbose(env, "%s pointer offset %d is not allowed\n",
- reg_type_str[type], reg->off);
+ reg_type_str(env, type), reg->off);
return false;
}
if (smin == S64_MIN) {
verbose(env, "math between %s pointer and register with unbounded min value is not allowed\n",
- reg_type_str[type]);
+ reg_type_str(env, type));
return false;
}
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]);
+ smin, reg_type_str(env, type));
return false;
}
@@ -7273,11 +7336,13 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
return -EACCES;
}
- switch (ptr_reg->type) {
- case PTR_TO_MAP_VALUE_OR_NULL:
+ if (ptr_reg->type & PTR_MAYBE_NULL) {
verbose(env, "R%d pointer arithmetic on %s prohibited, null-check it first\n",
- dst, reg_type_str[ptr_reg->type]);
+ dst, reg_type_str(env, ptr_reg->type));
return -EACCES;
+ }
+
+ switch (base_type(ptr_reg->type)) {
case CONST_PTR_TO_MAP:
/* smin_val represents the known value */
if (known && smin_val == 0 && opcode == BPF_ADD)
@@ -7285,14 +7350,11 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
fallthrough;
case PTR_TO_PACKET_END:
case PTR_TO_SOCKET:
- case PTR_TO_SOCKET_OR_NULL:
case PTR_TO_SOCK_COMMON:
- case PTR_TO_SOCK_COMMON_OR_NULL:
case PTR_TO_TCP_SOCK:
- case PTR_TO_TCP_SOCK_OR_NULL:
case PTR_TO_XDP_SOCK:
verbose(env, "R%d pointer arithmetic on %s prohibited\n",
- dst, reg_type_str[ptr_reg->type]);
+ dst, reg_type_str(env, ptr_reg->type));
return -EACCES;
default:
break;
@@ -8265,12 +8327,12 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
/* Got here implies adding two SCALAR_VALUEs */
if (WARN_ON_ONCE(ptr_reg)) {
- print_verifier_state(env, state);
+ print_verifier_state(env, state, true);
verbose(env, "verifier internal error: unexpected ptr_reg\n");
return -EINVAL;
}
if (WARN_ON(!src_reg)) {
- print_verifier_state(env, state);
+ print_verifier_state(env, state, true);
verbose(env, "verifier internal error: no src_reg\n");
return -EINVAL;
}
@@ -9015,7 +9077,7 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state,
struct bpf_reg_state *reg, u32 id,
bool is_null)
{
- if (reg_type_may_be_null(reg->type) && reg->id == id &&
+ if (type_may_be_null(reg->type) && reg->id == id &&
!WARN_ON_ONCE(!reg->id)) {
/* Old offset (both fixed and variable parts) should
* have been known-zero, because we don't allow pointer
@@ -9393,7 +9455,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
*/
if (!is_jmp32 && BPF_SRC(insn->code) == BPF_K &&
insn->imm == 0 && (opcode == BPF_JEQ || opcode == BPF_JNE) &&
- reg_type_may_be_null(dst_reg->type)) {
+ type_may_be_null(dst_reg->type)) {
/* Mark all identical registers in each branch as either
* safe or unknown depending R == 0 or R != 0 conditional.
*/
@@ -9409,7 +9471,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
return -EACCES;
}
if (env->log.level & BPF_LOG_LEVEL)
- print_verifier_state(env, this_branch->frame[this_branch->curframe]);
+ print_insn_state(env, this_branch->frame[this_branch->curframe]);
return 0;
}
@@ -9448,7 +9510,7 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
mark_reg_known_zero(env, regs, insn->dst_reg);
dst_reg->type = aux->btf_var.reg_type;
- switch (dst_reg->type) {
+ switch (base_type(dst_reg->type)) {
case PTR_TO_MEM:
dst_reg->mem_size = aux->btf_var.mem_size;
break;
@@ -9647,7 +9709,7 @@ static int check_return_code(struct bpf_verifier_env *env)
/* enforce return zero from async callbacks like timer */
if (reg->type != SCALAR_VALUE) {
verbose(env, "In async callback the register R0 is not a known value (%s)\n",
- reg_type_str[reg->type]);
+ reg_type_str(env, reg->type));
return -EINVAL;
}
@@ -9661,7 +9723,7 @@ static int check_return_code(struct bpf_verifier_env *env)
if (is_subprog) {
if (reg->type != SCALAR_VALUE) {
verbose(env, "At subprogram exit the register R0 is not a scalar value (%s)\n",
- reg_type_str[reg->type]);
+ reg_type_str(env, reg->type));
return -EINVAL;
}
return 0;
@@ -9725,7 +9787,7 @@ static int check_return_code(struct bpf_verifier_env *env)
if (reg->type != SCALAR_VALUE) {
verbose(env, "At program exit the register R0 is not a known value (%s)\n",
- reg_type_str[reg->type]);
+ reg_type_str(env, reg->type));
return -EINVAL;
}
@@ -10582,7 +10644,7 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
return true;
if (rcur->type == NOT_INIT)
return false;
- switch (rold->type) {
+ switch (base_type(rold->type)) {
case SCALAR_VALUE:
if (env->explore_alu_limits)
return false;
@@ -10604,6 +10666,22 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
}
case PTR_TO_MAP_KEY:
case PTR_TO_MAP_VALUE:
+ /* a PTR_TO_MAP_VALUE could be safe to use as a
+ * PTR_TO_MAP_VALUE_OR_NULL into the same map.
+ * However, if the old PTR_TO_MAP_VALUE_OR_NULL then got NULL-
+ * checked, doing so could have affected others with the same
+ * id, and we can't check for that because we lost the id when
+ * we converted to a PTR_TO_MAP_VALUE.
+ */
+ if (type_may_be_null(rold->type)) {
+ if (!type_may_be_null(rcur->type))
+ return false;
+ if (memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)))
+ return false;
+ /* Check our ids match any regs they're supposed to */
+ return check_ids(rold->id, rcur->id, idmap);
+ }
+
/* If the new min/max/var_off satisfy the old ones and
* everything else matches, we are OK.
* 'id' is not compared, since it's only used for maps with
@@ -10615,20 +10693,6 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 &&
range_within(rold, rcur) &&
tnum_in(rold->var_off, rcur->var_off);
- case PTR_TO_MAP_VALUE_OR_NULL:
- /* a PTR_TO_MAP_VALUE could be safe to use as a
- * PTR_TO_MAP_VALUE_OR_NULL into the same map.
- * However, if the old PTR_TO_MAP_VALUE_OR_NULL then got NULL-
- * checked, doing so could have affected others with the same
- * id, and we can't check for that because we lost the id when
- * we converted to a PTR_TO_MAP_VALUE.
- */
- if (rcur->type != PTR_TO_MAP_VALUE_OR_NULL)
- return false;
- if (memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)))
- return false;
- /* Check our ids match any regs they're supposed to */
- return check_ids(rold->id, rcur->id, idmap);
case PTR_TO_PACKET_META:
case PTR_TO_PACKET:
if (rcur->type != rold->type)
@@ -10657,11 +10721,8 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
case PTR_TO_PACKET_END:
case PTR_TO_FLOW_KEYS:
case PTR_TO_SOCKET:
- case PTR_TO_SOCKET_OR_NULL:
case PTR_TO_SOCK_COMMON:
- case PTR_TO_SOCK_COMMON_OR_NULL:
case PTR_TO_TCP_SOCK:
- case PTR_TO_TCP_SOCK_OR_NULL:
case PTR_TO_XDP_SOCK:
/* Only valid matches are exact, which memcmp() above
* would have accepted
@@ -11187,17 +11248,13 @@ next:
/* Return true if it's OK to have the same insn return a different type. */
static bool reg_type_mismatch_ok(enum bpf_reg_type type)
{
- switch (type) {
+ switch (base_type(type)) {
case PTR_TO_CTX:
case PTR_TO_SOCKET:
- case PTR_TO_SOCKET_OR_NULL:
case PTR_TO_SOCK_COMMON:
- case PTR_TO_SOCK_COMMON_OR_NULL:
case PTR_TO_TCP_SOCK:
- case PTR_TO_TCP_SOCK_OR_NULL:
case PTR_TO_XDP_SOCK:
case PTR_TO_BTF_ID:
- case PTR_TO_BTF_ID_OR_NULL:
return false;
default:
return true;
@@ -11277,16 +11334,12 @@ static int do_check(struct bpf_verifier_env *env)
if (need_resched())
cond_resched();
- if (env->log.level & BPF_LOG_LEVEL2 ||
- (env->log.level & BPF_LOG_LEVEL && do_print_state)) {
- if (env->log.level & BPF_LOG_LEVEL2)
- verbose(env, "%d:", env->insn_idx);
- else
- verbose(env, "\nfrom %d to %d%s:",
- env->prev_insn_idx, env->insn_idx,
- env->cur_state->speculative ?
- " (speculative execution)" : "");
- print_verifier_state(env, state->frame[state->curframe]);
+ if (env->log.level & BPF_LOG_LEVEL2 && do_print_state) {
+ verbose(env, "\nfrom %d to %d%s:",
+ env->prev_insn_idx, env->insn_idx,
+ env->cur_state->speculative ?
+ " (speculative execution)" : "");
+ print_verifier_state(env, state->frame[state->curframe], true);
do_print_state = false;
}
@@ -11297,9 +11350,15 @@ static int do_check(struct bpf_verifier_env *env)
.private_data = env,
};
+ if (verifier_state_scratched(env))
+ print_insn_state(env, state->frame[state->curframe]);
+
verbose_linfo(env, env->insn_idx, "; ");
+ env->prev_log_len = env->log.len_used;
verbose(env, "%d: ", env->insn_idx);
print_bpf_insn(&cbs, insn, env->allow_ptr_leaks);
+ env->prev_insn_print_len = env->log.len_used - env->prev_log_len;
+ env->prev_log_len = env->log.len_used;
}
if (bpf_prog_is_dev_bound(env->prog->aux)) {
@@ -11421,7 +11480,7 @@ static int do_check(struct bpf_verifier_env *env)
if (is_ctx_reg(env, insn->dst_reg)) {
verbose(env, "BPF_ST stores into R%d %s is not allowed\n",
insn->dst_reg,
- reg_type_str[reg_state(env, insn->dst_reg)->type]);
+ reg_type_str(env, reg_state(env, insn->dst_reg)->type));
return -EACCES;
}
@@ -11508,6 +11567,7 @@ static int do_check(struct bpf_verifier_env *env)
if (err)
return err;
process_bpf_exit:
+ mark_verifier_state_scratched(env);
update_branch_counts(env, env->cur_state);
err = pop_stack(env, &prev_insn_idx,
&env->insn_idx, pop_log);
@@ -11673,7 +11733,7 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env,
err = -EINVAL;
goto err_put;
}
- aux->btf_var.reg_type = PTR_TO_MEM;
+ aux->btf_var.reg_type = PTR_TO_MEM | MEM_RDONLY;
aux->btf_var.mem_size = tsize;
} else {
aux->btf_var.reg_type = PTR_TO_BTF_ID;
@@ -11833,6 +11893,9 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
}
break;
case BPF_MAP_TYPE_RINGBUF:
+ case BPF_MAP_TYPE_INODE_STORAGE:
+ case BPF_MAP_TYPE_SK_STORAGE:
+ case BPF_MAP_TYPE_TASK_STORAGE:
break;
default:
verbose(env,
@@ -13016,6 +13079,7 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env,
static int do_misc_fixups(struct bpf_verifier_env *env)
{
struct bpf_prog *prog = env->prog;
+ enum bpf_attach_type eatype = prog->expected_attach_type;
bool expect_blinding = bpf_jit_blinding_enabled(prog);
enum bpf_prog_type prog_type = resolve_prog_type(prog);
struct bpf_insn *insn = prog->insnsi;
@@ -13386,11 +13450,79 @@ patch_map_ops_generic:
continue;
}
+ /* Implement bpf_get_func_arg inline. */
+ if (prog_type == BPF_PROG_TYPE_TRACING &&
+ insn->imm == BPF_FUNC_get_func_arg) {
+ /* Load nr_args from ctx - 8 */
+ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8);
+ insn_buf[1] = BPF_JMP32_REG(BPF_JGE, BPF_REG_2, BPF_REG_0, 6);
+ insn_buf[2] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 3);
+ insn_buf[3] = BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_1);
+ insn_buf[4] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 0);
+ insn_buf[5] = BPF_STX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0);
+ insn_buf[6] = BPF_MOV64_IMM(BPF_REG_0, 0);
+ insn_buf[7] = BPF_JMP_A(1);
+ insn_buf[8] = BPF_MOV64_IMM(BPF_REG_0, -EINVAL);
+ cnt = 9;
+
+ new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+ env->prog = prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ continue;
+ }
+
+ /* Implement bpf_get_func_ret inline. */
+ if (prog_type == BPF_PROG_TYPE_TRACING &&
+ insn->imm == BPF_FUNC_get_func_ret) {
+ if (eatype == BPF_TRACE_FEXIT ||
+ eatype == BPF_MODIFY_RETURN) {
+ /* Load nr_args from ctx - 8 */
+ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8);
+ insn_buf[1] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_0, 3);
+ insn_buf[2] = BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1);
+ insn_buf[3] = BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0);
+ insn_buf[4] = BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_3, 0);
+ insn_buf[5] = BPF_MOV64_IMM(BPF_REG_0, 0);
+ cnt = 6;
+ } else {
+ insn_buf[0] = BPF_MOV64_IMM(BPF_REG_0, -EOPNOTSUPP);
+ cnt = 1;
+ }
+
+ new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+ env->prog = prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ continue;
+ }
+
+ /* Implement get_func_arg_cnt inline. */
+ if (prog_type == BPF_PROG_TYPE_TRACING &&
+ insn->imm == BPF_FUNC_get_func_arg_cnt) {
+ /* Load nr_args from ctx - 8 */
+ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8);
+
+ new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, 1);
+ if (!new_prog)
+ return -ENOMEM;
+
+ env->prog = prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ continue;
+ }
+
/* Implement bpf_get_func_ip inline. */
if (prog_type == BPF_PROG_TYPE_TRACING &&
insn->imm == BPF_FUNC_get_func_ip) {
- /* Load IP address from ctx - 8 */
- insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8);
+ /* Load IP address from ctx - 16 */
+ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -16);
new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, 1);
if (!new_prog)
@@ -13504,7 +13636,7 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog)
mark_reg_known_zero(env, regs, i);
else if (regs[i].type == SCALAR_VALUE)
mark_reg_unknown(env, regs, i);
- else if (regs[i].type == PTR_TO_MEM_OR_NULL) {
+ else if (base_type(regs[i].type) == PTR_TO_MEM) {
const u32 mem_size = regs[i].mem_size;
mark_reg_known_zero(env, regs, i);
@@ -14099,6 +14231,8 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr)
}
}
+ mark_verifier_state_clean(env);
+
if (IS_ERR(btf_vmlinux)) {
/* Either gcc or pahole or kernel are broken. */
verbose(env, "in-kernel BTF is malformed\n");
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 919194de39c8..cd4c23f7e3df 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -30,6 +30,7 @@
#include "cgroup-internal.h"
+#include <linux/bpf-cgroup.h>
#include <linux/cred.h>
#include <linux/errno.h>
#include <linux/init_task.h>
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 083be6af29d7..d7ed1dffa426 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -33,6 +33,7 @@
#include <linux/security.h>
#include <linux/ctype.h>
#include <linux/kmemleak.h>
+#include <linux/filter.h>
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/kernel.h>
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 623dd0684429..21aa30644219 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -345,7 +345,7 @@ static const struct bpf_func_proto bpf_probe_write_user_proto = {
.gpl_only = true,
.ret_type = RET_INTEGER,
.arg1_type = ARG_ANYTHING,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE,
};
@@ -394,7 +394,7 @@ static const struct bpf_func_proto bpf_trace_printk_proto = {
.func = bpf_trace_printk,
.gpl_only = true,
.ret_type = RET_INTEGER,
- .arg1_type = ARG_PTR_TO_MEM,
+ .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg2_type = ARG_CONST_SIZE,
};
@@ -450,9 +450,9 @@ static const struct bpf_func_proto bpf_trace_vprintk_proto = {
.func = bpf_trace_vprintk,
.gpl_only = true,
.ret_type = RET_INTEGER,
- .arg1_type = ARG_PTR_TO_MEM,
+ .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg2_type = ARG_CONST_SIZE,
- .arg3_type = ARG_PTR_TO_MEM_OR_NULL,
+ .arg3_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY,
.arg4_type = ARG_CONST_SIZE_OR_ZERO,
};
@@ -492,9 +492,9 @@ static const struct bpf_func_proto bpf_seq_printf_proto = {
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_BTF_ID,
.arg1_btf_id = &btf_seq_file_ids[0],
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE,
- .arg4_type = ARG_PTR_TO_MEM_OR_NULL,
+ .arg4_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY,
.arg5_type = ARG_CONST_SIZE_OR_ZERO,
};
@@ -509,7 +509,7 @@ static const struct bpf_func_proto bpf_seq_write_proto = {
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_BTF_ID,
.arg1_btf_id = &btf_seq_file_ids[0],
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE_OR_ZERO,
};
@@ -533,7 +533,7 @@ static const struct bpf_func_proto bpf_seq_printf_btf_proto = {
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_BTF_ID,
.arg1_btf_id = &btf_seq_file_ids[0],
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE_OR_ZERO,
.arg4_type = ARG_ANYTHING,
};
@@ -694,7 +694,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto = {
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_CONST_MAP_PTR,
.arg3_type = ARG_ANYTHING,
- .arg4_type = ARG_PTR_TO_MEM,
+ .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg5_type = ARG_CONST_SIZE_OR_ZERO,
};
@@ -1004,7 +1004,7 @@ const struct bpf_func_proto bpf_snprintf_btf_proto = {
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_MEM,
.arg2_type = ARG_CONST_SIZE,
- .arg3_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg4_type = ARG_CONST_SIZE,
.arg5_type = ARG_ANYTHING,
};
@@ -1012,7 +1012,7 @@ const struct bpf_func_proto bpf_snprintf_btf_proto = {
BPF_CALL_1(bpf_get_func_ip_tracing, void *, ctx)
{
/* This helper call is inlined by verifier. */
- return ((u64 *)ctx)[-1];
+ return ((u64 *)ctx)[-2];
}
static const struct bpf_func_proto bpf_get_func_ip_proto_tracing = {
@@ -1091,6 +1091,53 @@ static const struct bpf_func_proto bpf_get_branch_snapshot_proto = {
.arg2_type = ARG_CONST_SIZE_OR_ZERO,
};
+BPF_CALL_3(get_func_arg, void *, ctx, u32, n, u64 *, value)
+{
+ /* This helper call is inlined by verifier. */
+ u64 nr_args = ((u64 *)ctx)[-1];
+
+ if ((u64) n >= nr_args)
+ return -EINVAL;
+ *value = ((u64 *)ctx)[n];
+ return 0;
+}
+
+static const struct bpf_func_proto bpf_get_func_arg_proto = {
+ .func = get_func_arg,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_PTR_TO_LONG,
+};
+
+BPF_CALL_2(get_func_ret, void *, ctx, u64 *, value)
+{
+ /* This helper call is inlined by verifier. */
+ u64 nr_args = ((u64 *)ctx)[-1];
+
+ *value = ((u64 *)ctx)[nr_args];
+ return 0;
+}
+
+static const struct bpf_func_proto bpf_get_func_ret_proto = {
+ .func = get_func_ret,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_LONG,
+};
+
+BPF_CALL_1(get_func_arg_cnt, void *, ctx)
+{
+ /* This helper call is inlined by verifier. */
+ return ((u64 *)ctx)[-1];
+}
+
+static const struct bpf_func_proto bpf_get_func_arg_cnt_proto = {
+ .func = get_func_arg_cnt,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+};
+
static const struct bpf_func_proto *
bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
@@ -1287,7 +1334,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_tp = {
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_CONST_MAP_PTR,
.arg3_type = ARG_ANYTHING,
- .arg4_type = ARG_PTR_TO_MEM,
+ .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg5_type = ARG_CONST_SIZE_OR_ZERO,
};
@@ -1509,7 +1556,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = {
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_CONST_MAP_PTR,
.arg3_type = ARG_ANYTHING,
- .arg4_type = ARG_PTR_TO_MEM,
+ .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg5_type = ARG_CONST_SIZE_OR_ZERO,
};
@@ -1563,7 +1610,7 @@ static const struct bpf_func_proto bpf_get_stack_proto_raw_tp = {
.gpl_only = true,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE_OR_ZERO,
.arg4_type = ARG_ANYTHING,
};
@@ -1629,6 +1676,12 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
NULL;
case BPF_FUNC_d_path:
return &bpf_d_path_proto;
+ case BPF_FUNC_get_func_arg:
+ return bpf_prog_has_trampoline(prog) ? &bpf_get_func_arg_proto : NULL;
+ case BPF_FUNC_get_func_ret:
+ return bpf_prog_has_trampoline(prog) ? &bpf_get_func_ret_proto : NULL;
+ case BPF_FUNC_get_func_arg_cnt:
+ return bpf_prog_has_trampoline(prog) ? &bpf_get_func_arg_cnt_proto : NULL;
default:
fn = raw_tp_prog_func_proto(func_id, prog);
if (!fn && prog->expected_attach_type == BPF_TRACE_ITER)
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 33272a7b6912..4e1257f50aa3 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -7,6 +7,7 @@
*/
#define pr_fmt(fmt) "trace_kprobe: " fmt
+#include <linux/bpf-cgroup.h>
#include <linux/security.h>
#include <linux/module.h>
#include <linux/uaccess.h>
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index f5f0039d31e5..4f35514a48f3 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -7,6 +7,7 @@
*/
#define pr_fmt(fmt) "trace_uprobe: " fmt
+#include <linux/bpf-cgroup.h>
#include <linux/security.h>
#include <linux/ctype.h>
#include <linux/module.h>
diff --git a/net/bluetooth/bnep/sock.c b/net/bluetooth/bnep/sock.c
index d515571b2afb..57d509d77cb4 100644
--- a/net/bluetooth/bnep/sock.c
+++ b/net/bluetooth/bnep/sock.c
@@ -24,6 +24,7 @@
SOFTWARE IS DISCLAIMED.
*/
+#include <linux/compat.h>
#include <linux/export.h>
#include <linux/file.h>
diff --git a/net/bluetooth/eir.h b/net/bluetooth/eir.h
index 724662f8f8b1..05e2e917fc25 100644
--- a/net/bluetooth/eir.h
+++ b/net/bluetooth/eir.h
@@ -5,6 +5,8 @@
* Copyright (C) 2021 Intel Corporation
*/
+#include <asm/unaligned.h>
+
void eir_create(struct hci_dev *hdev, u8 *data);
u8 eir_create_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr);
diff --git a/net/bluetooth/hidp/sock.c b/net/bluetooth/hidp/sock.c
index 595fb3c9d6c3..369ed92dac99 100644
--- a/net/bluetooth/hidp/sock.c
+++ b/net/bluetooth/hidp/sock.c
@@ -20,6 +20,7 @@
SOFTWARE IS DISCLAIMED.
*/
+#include <linux/compat.h>
#include <linux/export.h>
#include <linux/file.h>
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 251017c69ab7..188e4d4813b0 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -29,6 +29,7 @@
#include <linux/module.h>
#include <linux/export.h>
+#include <linux/filter.h>
#include <linux/sched/signal.h>
#include <net/bluetooth/bluetooth.h>
diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c
index 5f3c1cf7f6ad..f213ed108361 100644
--- a/net/bridge/br_ioctl.c
+++ b/net/bridge/br_ioctl.c
@@ -8,6 +8,7 @@
*/
#include <linux/capability.h>
+#include <linux/compat.h>
#include <linux/kernel.h>
#include <linux/if_bridge.h>
#include <linux/netdevice.h>
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index e12fd3cad619..2b8892d502f7 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -6,6 +6,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ":%s(): " fmt, __func__
+#include <linux/filter.h>
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/module.h>
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index 68d2cbf8331a..d9c37fd10809 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -13,6 +13,7 @@
#include <net/sock.h>
#include <uapi/linux/sock_diag.h>
#include <uapi/linux/btf.h>
+#include <linux/rcupdate_trace.h>
DEFINE_BPF_STORAGE_CACHE(sk_cache);
@@ -22,7 +23,8 @@ bpf_sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit)
struct bpf_local_storage *sk_storage;
struct bpf_local_storage_map *smap;
- sk_storage = rcu_dereference(sk->sk_bpf_storage);
+ sk_storage =
+ rcu_dereference_check(sk->sk_bpf_storage, bpf_rcu_lock_held());
if (!sk_storage)
return NULL;
@@ -258,6 +260,7 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk,
{
struct bpf_local_storage_data *sdata;
+ WARN_ON_ONCE(!bpf_rcu_lock_held());
if (!sk || !sk_fullsock(sk) || flags > BPF_SK_STORAGE_GET_F_CREATE)
return (unsigned long)NULL;
@@ -288,6 +291,7 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk,
BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk)
{
+ WARN_ON_ONCE(!bpf_rcu_lock_held());
if (!sk || !sk_fullsock(sk))
return -EINVAL;
@@ -416,6 +420,7 @@ static bool bpf_sk_storage_tracing_allowed(const struct bpf_prog *prog)
BPF_CALL_4(bpf_sk_storage_get_tracing, struct bpf_map *, map, struct sock *, sk,
void *, value, u64, flags)
{
+ WARN_ON_ONCE(!bpf_rcu_lock_held());
if (in_hardirq() || in_nmi())
return (unsigned long)NULL;
@@ -425,6 +430,7 @@ BPF_CALL_4(bpf_sk_storage_get_tracing, struct bpf_map *, map, struct sock *, sk,
BPF_CALL_2(bpf_sk_storage_delete_tracing, struct bpf_map *, map,
struct sock *, sk)
{
+ WARN_ON_ONCE(!bpf_rcu_lock_held());
if (in_hardirq() || in_nmi())
return -EPERM;
@@ -929,7 +935,7 @@ static struct bpf_iter_reg bpf_sk_storage_map_reg_info = {
{ offsetof(struct bpf_iter__bpf_sk_storage_map, sk),
PTR_TO_BTF_ID_OR_NULL },
{ offsetof(struct bpf_iter__bpf_sk_storage_map, value),
- PTR_TO_RDWR_BUF_OR_NULL },
+ PTR_TO_BUF | PTR_MAYBE_NULL },
},
.seq_info = &iter_seq_info,
};
diff --git a/net/core/dev.c b/net/core/dev.c
index 644b9c8be3a8..6c8b226b5f2f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4712,7 +4712,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
case XDP_PASS:
break;
default:
- bpf_warn_invalid_xdp_action(act);
+ bpf_warn_invalid_xdp_action(skb->dev, xdp_prog, act);
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(skb->dev, xdp_prog, act);
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 6366ce324dce..fcd9f6d85cf1 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -7,6 +7,7 @@
* Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
*/
+#include <linux/etherdevice.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/types.h>
diff --git a/net/core/filter.c b/net/core/filter.c
index e4cc3aff5bf7..606ab5a98a1a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1712,7 +1712,7 @@ static const struct bpf_func_proto bpf_skb_store_bytes_proto = {
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
- .arg3_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg4_type = ARG_CONST_SIZE,
.arg5_type = ARG_ANYTHING,
};
@@ -2017,9 +2017,9 @@ static const struct bpf_func_proto bpf_csum_diff_proto = {
.gpl_only = false,
.pkt_access = true,
.ret_type = RET_INTEGER,
- .arg1_type = ARG_PTR_TO_MEM_OR_NULL,
+ .arg1_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY,
.arg2_type = ARG_CONST_SIZE_OR_ZERO,
- .arg3_type = ARG_PTR_TO_MEM_OR_NULL,
+ .arg3_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY,
.arg4_type = ARG_CONST_SIZE_OR_ZERO,
.arg5_type = ARG_ANYTHING,
};
@@ -2540,7 +2540,7 @@ static const struct bpf_func_proto bpf_redirect_neigh_proto = {
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_ANYTHING,
- .arg2_type = ARG_PTR_TO_MEM_OR_NULL,
+ .arg2_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE_OR_ZERO,
.arg4_type = ARG_ANYTHING,
};
@@ -4173,7 +4173,7 @@ static const struct bpf_func_proto bpf_skb_event_output_proto = {
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_CONST_MAP_PTR,
.arg3_type = ARG_ANYTHING,
- .arg4_type = ARG_PTR_TO_MEM,
+ .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg5_type = ARG_CONST_SIZE_OR_ZERO,
};
@@ -4187,7 +4187,7 @@ const struct bpf_func_proto bpf_skb_output_proto = {
.arg1_btf_id = &bpf_skb_output_btf_ids[0],
.arg2_type = ARG_CONST_MAP_PTR,
.arg3_type = ARG_ANYTHING,
- .arg4_type = ARG_PTR_TO_MEM,
+ .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg5_type = ARG_CONST_SIZE_OR_ZERO,
};
@@ -4370,7 +4370,7 @@ static const struct bpf_func_proto bpf_skb_set_tunnel_key_proto = {
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE,
.arg4_type = ARG_ANYTHING,
};
@@ -4396,7 +4396,7 @@ static const struct bpf_func_proto bpf_skb_set_tunnel_opt_proto = {
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE,
};
@@ -4566,7 +4566,7 @@ static const struct bpf_func_proto bpf_xdp_event_output_proto = {
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_CONST_MAP_PTR,
.arg3_type = ARG_ANYTHING,
- .arg4_type = ARG_PTR_TO_MEM,
+ .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg5_type = ARG_CONST_SIZE_OR_ZERO,
};
@@ -4580,7 +4580,7 @@ const struct bpf_func_proto bpf_xdp_output_proto = {
.arg1_btf_id = &bpf_xdp_output_btf_ids[0],
.arg2_type = ARG_CONST_MAP_PTR,
.arg3_type = ARG_ANYTHING,
- .arg4_type = ARG_PTR_TO_MEM,
+ .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg5_type = ARG_CONST_SIZE_OR_ZERO,
};
@@ -5066,7 +5066,7 @@ const struct bpf_func_proto bpf_sk_setsockopt_proto = {
.arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON,
.arg2_type = ARG_ANYTHING,
.arg3_type = ARG_ANYTHING,
- .arg4_type = ARG_PTR_TO_MEM,
+ .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg5_type = ARG_CONST_SIZE,
};
@@ -5100,7 +5100,7 @@ static const struct bpf_func_proto bpf_sock_addr_setsockopt_proto = {
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
.arg3_type = ARG_ANYTHING,
- .arg4_type = ARG_PTR_TO_MEM,
+ .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg5_type = ARG_CONST_SIZE,
};
@@ -5134,7 +5134,7 @@ static const struct bpf_func_proto bpf_sock_ops_setsockopt_proto = {
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
.arg3_type = ARG_ANYTHING,
- .arg4_type = ARG_PTR_TO_MEM,
+ .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg5_type = ARG_CONST_SIZE,
};
@@ -5309,7 +5309,7 @@ static const struct bpf_func_proto bpf_bind_proto = {
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE,
};
@@ -5897,7 +5897,7 @@ static const struct bpf_func_proto bpf_lwt_in_push_encap_proto = {
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
- .arg3_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg4_type = ARG_CONST_SIZE
};
@@ -5907,7 +5907,7 @@ static const struct bpf_func_proto bpf_lwt_xmit_push_encap_proto = {
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
- .arg3_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg4_type = ARG_CONST_SIZE
};
@@ -5950,7 +5950,7 @@ static const struct bpf_func_proto bpf_lwt_seg6_store_bytes_proto = {
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
- .arg3_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg4_type = ARG_CONST_SIZE
};
@@ -6038,7 +6038,7 @@ static const struct bpf_func_proto bpf_lwt_seg6_action_proto = {
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
- .arg3_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg4_type = ARG_CONST_SIZE
};
@@ -6263,7 +6263,7 @@ static const struct bpf_func_proto bpf_skc_lookup_tcp_proto = {
.pkt_access = true,
.ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL,
.arg1_type = ARG_PTR_TO_CTX,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE,
.arg4_type = ARG_ANYTHING,
.arg5_type = ARG_ANYTHING,
@@ -6282,7 +6282,7 @@ static const struct bpf_func_proto bpf_sk_lookup_tcp_proto = {
.pkt_access = true,
.ret_type = RET_PTR_TO_SOCKET_OR_NULL,
.arg1_type = ARG_PTR_TO_CTX,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE,
.arg4_type = ARG_ANYTHING,
.arg5_type = ARG_ANYTHING,
@@ -6301,7 +6301,7 @@ static const struct bpf_func_proto bpf_sk_lookup_udp_proto = {
.pkt_access = true,
.ret_type = RET_PTR_TO_SOCKET_OR_NULL,
.arg1_type = ARG_PTR_TO_CTX,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE,
.arg4_type = ARG_ANYTHING,
.arg5_type = ARG_ANYTHING,
@@ -6338,7 +6338,7 @@ static const struct bpf_func_proto bpf_xdp_sk_lookup_udp_proto = {
.pkt_access = true,
.ret_type = RET_PTR_TO_SOCKET_OR_NULL,
.arg1_type = ARG_PTR_TO_CTX,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE,
.arg4_type = ARG_ANYTHING,
.arg5_type = ARG_ANYTHING,
@@ -6361,7 +6361,7 @@ static const struct bpf_func_proto bpf_xdp_skc_lookup_tcp_proto = {
.pkt_access = true,
.ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL,
.arg1_type = ARG_PTR_TO_CTX,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE,
.arg4_type = ARG_ANYTHING,
.arg5_type = ARG_ANYTHING,
@@ -6384,7 +6384,7 @@ static const struct bpf_func_proto bpf_xdp_sk_lookup_tcp_proto = {
.pkt_access = true,
.ret_type = RET_PTR_TO_SOCKET_OR_NULL,
.arg1_type = ARG_PTR_TO_CTX,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE,
.arg4_type = ARG_ANYTHING,
.arg5_type = ARG_ANYTHING,
@@ -6403,7 +6403,7 @@ static const struct bpf_func_proto bpf_sock_addr_skc_lookup_tcp_proto = {
.gpl_only = false,
.ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL,
.arg1_type = ARG_PTR_TO_CTX,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE,
.arg4_type = ARG_ANYTHING,
.arg5_type = ARG_ANYTHING,
@@ -6422,7 +6422,7 @@ static const struct bpf_func_proto bpf_sock_addr_sk_lookup_tcp_proto = {
.gpl_only = false,
.ret_type = RET_PTR_TO_SOCKET_OR_NULL,
.arg1_type = ARG_PTR_TO_CTX,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE,
.arg4_type = ARG_ANYTHING,
.arg5_type = ARG_ANYTHING,
@@ -6441,7 +6441,7 @@ static const struct bpf_func_proto bpf_sock_addr_sk_lookup_udp_proto = {
.gpl_only = false,
.ret_type = RET_PTR_TO_SOCKET_OR_NULL,
.arg1_type = ARG_PTR_TO_CTX,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE,
.arg4_type = ARG_ANYTHING,
.arg5_type = ARG_ANYTHING,
@@ -6754,9 +6754,9 @@ static const struct bpf_func_proto bpf_tcp_check_syncookie_proto = {
.pkt_access = true,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE,
- .arg4_type = ARG_PTR_TO_MEM,
+ .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg5_type = ARG_CONST_SIZE,
};
@@ -6823,9 +6823,9 @@ static const struct bpf_func_proto bpf_tcp_gen_syncookie_proto = {
.pkt_access = true,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE,
- .arg4_type = ARG_PTR_TO_MEM,
+ .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg5_type = ARG_CONST_SIZE,
};
@@ -7054,7 +7054,7 @@ static const struct bpf_func_proto bpf_sock_ops_store_hdr_opt_proto = {
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg3_type = ARG_CONST_SIZE,
.arg4_type = ARG_ANYTHING,
};
@@ -8180,13 +8180,13 @@ static bool xdp_is_valid_access(int off, int size,
return __is_valid_xdp_access(off, size);
}
-void bpf_warn_invalid_xdp_action(u32 act)
+void bpf_warn_invalid_xdp_action(struct net_device *dev, struct bpf_prog *prog, u32 act)
{
const u32 act_max = XDP_REDIRECT;
- WARN_ONCE(1, "%s XDP return value %u, expect packet loss!\n",
- act > act_max ? "Illegal" : "Driver unsupported",
- act);
+ pr_warn_once("%s XDP return value %u on prog %s (id %d) dev %s, expect packet loss!\n",
+ act > act_max ? "Illegal" : "Driver unsupported",
+ act, prog->aux->name, prog->aux->id, dev ? dev->name : "N/A");
}
EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action);
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index fe9b5063cb73..15833e1d6ea1 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -5,6 +5,7 @@
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/if_vlan.h>
+#include <linux/filter.h>
#include <net/dsa.h>
#include <net/dst_metadata.h>
#include <net/ip.h>
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index 2f7940bcf715..349480ef68a5 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -2,6 +2,7 @@
/* Copyright (c) 2016 Thomas Graf <tgraf@tgraf.ch>
*/
+#include <linux/filter.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/skbuff.h>
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index c9c45b935f99..f7cf74cdd3db 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -1,5 +1,6 @@
/* License: GPL */
+#include <linux/filter.h>
#include <linux/mutex.h>
#include <linux/socket.h>
#include <linux/skbuff.h>
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 4ca4b11f4e5f..9618ab6d7cc9 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -1564,7 +1564,7 @@ static struct bpf_iter_reg sock_map_iter_reg = {
.ctx_arg_info_size = 2,
.ctx_arg_info = {
{ offsetof(struct bpf_iter__sockmap, key),
- PTR_TO_RDONLY_BUF_OR_NULL },
+ PTR_TO_BUF | PTR_MAYBE_NULL | MEM_RDONLY },
{ offsetof(struct bpf_iter__sockmap, sk),
PTR_TO_BTF_ID_OR_NULL },
},
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 5f88526ad61c..7b4d485aac7a 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -6,6 +6,7 @@
* Added /proc/sys/net/core directory entry (empty =) ). [MS]
*/
+#include <linux/filter.h>
#include <linux/mm.h>
#include <linux/sysctl.h>
#include <linux/module.h>
diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c
index 7ab788f41a3f..c59be5b04479 100644
--- a/net/decnet/dn_nsp_in.c
+++ b/net/decnet/dn_nsp_in.c
@@ -38,6 +38,7 @@
*******************************************************************************/
#include <linux/errno.h>
+#include <linux/filter.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/in.h>
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index edfaae7b5967..b5ae21f172a8 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -8,6 +8,7 @@
#define __DSA_PRIV_H
#include <linux/if_bridge.h>
+#include <linux/if_vlan.h>
#include <linux/phy.h>
#include <linux/netdevice.h>
#include <linux/netpoll.h>
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 9a113d893521..b2cdba1b4aae 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -8,6 +8,7 @@
*/
#include <linux/compat.h>
+#include <linux/etherdevice.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/capability.h>
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 1319d093cdda..eeafeccebb8d 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -8,6 +8,7 @@
#include <linux/nexthop.h>
#include <linux/rtnetlink.h>
#include <linux/slab.h>
+#include <linux/vmalloc.h>
#include <net/arp.h>
#include <net/ipv6_stubs.h>
#include <net/lwtunnel.h>
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 4a486ea1333f..7b18a6f42f18 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -74,6 +74,7 @@
#define pr_fmt(fmt) "UDP: " fmt
+#include <linux/bpf-cgroup.h>
#include <linux/uaccess.h>
#include <asm/ioctls.h>
#include <linux/memblock.h>
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 0371d2c14145..463c37dea449 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -15,6 +15,7 @@
#define pr_fmt(fmt) "IPv6: " fmt
+#include <linux/bpf.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/net.h>
diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index 2dc40b3f373e..a5eea182149d 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -7,6 +7,7 @@
* eBPF support: Mathieu Xhonneux <m.xhonneux@gmail.com>
*/
+#include <linux/filter.h>
#include <linux/types.h>
#include <linux/skbuff.h>
#include <linux/net.h>
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index aa5d86bbfb53..1accc06abc54 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -17,6 +17,7 @@
* YOSHIFUJI Hideaki @USAGI: convert /proc/net/udp6 to seq_file.
*/
+#include <linux/bpf-cgroup.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 49ecbe8d176a..a1760add5bf1 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -13,6 +13,7 @@
#define KMSG_COMPONENT "af_iucv"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+#include <linux/filter.h>
#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/types.h>
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 11a715d76a4f..71899e5a5a11 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -9,6 +9,7 @@
#include <linux/errno.h>
#include <linux/errqueue.h>
#include <linux/file.h>
+#include <linux/filter.h>
#include <linux/in.h>
#include <linux/kernel.h>
#include <linux/module.h>
diff --git a/net/netfilter/nfnetlink_hook.c b/net/netfilter/nfnetlink_hook.c
index d5c719c9e36c..71e29adac48b 100644
--- a/net/netfilter/nfnetlink_hook.c
+++ b/net/netfilter/nfnetlink_hook.c
@@ -6,6 +6,7 @@
*/
#include <linux/module.h>
+#include <linux/kallsyms.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/skbuff.h>
diff --git a/net/netfilter/nft_reject_netdev.c b/net/netfilter/nft_reject_netdev.c
index d89f68754f42..61cd8c4ac385 100644
--- a/net/netfilter/nft_reject_netdev.c
+++ b/net/netfilter/nft_reject_netdev.c
@@ -4,6 +4,7 @@
* Copyright (c) 2020 Jose M. Guisado <guigom@riseup.net>
*/
+#include <linux/etherdevice.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/module.h>
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 4be2d97ff93e..7b344035bfe3 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -20,8 +20,10 @@
#include <linux/module.h>
+#include <linux/bpf.h>
#include <linux/capability.h>
#include <linux/kernel.h>
+#include <linux/filter.h>
#include <linux/init.h>
#include <linux/signal.h>
#include <linux/sched.h>
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 59c265b8ac26..9bbe7282efb6 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -49,6 +49,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/ethtool.h>
+#include <linux/filter.h>
#include <linux/types.h>
#include <linux/mm.h>
#include <linux/capability.h>
diff --git a/net/rose/rose_in.c b/net/rose/rose_in.c
index 6af786d66b03..4d67f36dce1b 100644
--- a/net/rose/rose_in.c
+++ b/net/rose/rose_in.c
@@ -9,6 +9,7 @@
* diagrams as the code is not obvious and probably very easy to break.
*/
#include <linux/errno.h>
+#include <linux/filter.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/in.h>
diff --git a/net/sched/sch_frag.c b/net/sched/sch_frag.c
index 5ded4c8672a6..a9bd0a235890 100644
--- a/net/sched/sch_frag.c
+++ b/net/sched/sch_frag.c
@@ -1,4 +1,5 @@
// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+#include <linux/if_vlan.h>
#include <net/netlink.h>
#include <net/sch_generic.h>
#include <net/pkt_sched.h>
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index fe5d5399c4e8..a3e2d3b89568 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -12,6 +12,8 @@
* Author(s): Ursula Braun <ubraun@linux.vnet.ibm.com>
*/
+#include <linux/etherdevice.h>
+#include <linux/if_vlan.h>
#include <linux/random.h>
#include <linux/workqueue.h>
#include <linux/scatterlist.h>
diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c
index fd28cc498b98..a2084ecdb97e 100644
--- a/net/smc/smc_ism.c
+++ b/net/smc/smc_ism.c
@@ -6,6 +6,7 @@
* Copyright IBM Corp. 2018
*/
+#include <linux/if_vlan.h>
#include <linux/spinlock.h>
#include <linux/mutex.h>
#include <linux/slab.h>
diff --git a/net/socket.c b/net/socket.c
index 6b2a898055ca..4b8bb20d5e9a 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -52,6 +52,7 @@
* Based upon Swansea University Computer Society NET3.039
*/
+#include <linux/bpf-cgroup.h>
#include <linux/ethtool.h>
#include <linux/mm.h>
#include <linux/socket.h>
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 4d6e33bbd446..c19569819866 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -89,6 +89,7 @@
#include <linux/socket.h>
#include <linux/un.h>
#include <linux/fcntl.h>
+#include <linux/filter.h>
#include <linux/termios.h>
#include <linux/sockios.h>
#include <linux/net.h>
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index ed0df839c38c..3235261f138d 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -85,6 +85,7 @@
* TCP_LISTEN - listening
*/
+#include <linux/compat.h>
#include <linux/types.h>
#include <linux/bitops.h>
#include <linux/cred.h>
diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c
index 2e48d0e094d9..65b53fb3de13 100644
--- a/net/xdp/xskmap.c
+++ b/net/xdp/xskmap.c
@@ -4,6 +4,7 @@
*/
#include <linux/bpf.h>
+#include <linux/filter.h>
#include <linux/capability.h>
#include <net/xdp_sock.h>
#include <linux/slab.h>
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index a2f4001221d1..0407272a990c 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -14,6 +14,7 @@
*
*/
+#include <linux/compat.h>
#include <linux/workqueue.h>
#include <net/xfrm.h>
#include <linux/pfkeyv2.h>
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 7c36cc1f3d79..e3e26f4da6c2 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -11,6 +11,7 @@
*
*/
+#include <linux/compat.h>
#include <linux/crypto.h>
#include <linux/module.h>
#include <linux/kernel.h>
diff --git a/samples/bpf/hbm.c b/samples/bpf/hbm.c
index b0c18efe7928..1fe5bcafb3bc 100644
--- a/samples/bpf/hbm.c
+++ b/samples/bpf/hbm.c
@@ -120,6 +120,9 @@ static void do_error(char *msg, bool errno_flag)
static int prog_load(char *prog)
{
+ struct bpf_program *pos;
+ const char *sec_name;
+
obj = bpf_object__open_file(prog, NULL);
if (libbpf_get_error(obj)) {
printf("ERROR: opening BPF object file failed\n");
@@ -132,7 +135,13 @@ static int prog_load(char *prog)
goto err;
}
- bpf_prog = bpf_object__find_program_by_title(obj, "cgroup_skb/egress");
+ bpf_object__for_each_program(pos, obj) {
+ sec_name = bpf_program__section_name(pos);
+ if (sec_name && !strcmp(sec_name, "cgroup_skb/egress")) {
+ bpf_prog = pos;
+ break;
+ }
+ }
if (!bpf_prog) {
printf("ERROR: finding a prog in obj file failed\n");
goto err;
diff --git a/samples/bpf/xdp_fwd_user.c b/samples/bpf/xdp_fwd_user.c
index 00061261a8da..4ad896782f77 100644
--- a/samples/bpf/xdp_fwd_user.c
+++ b/samples/bpf/xdp_fwd_user.c
@@ -79,7 +79,9 @@ int main(int argc, char **argv)
.prog_type = BPF_PROG_TYPE_XDP,
};
const char *prog_name = "xdp_fwd";
- struct bpf_program *prog;
+ struct bpf_program *prog = NULL;
+ struct bpf_program *pos;
+ const char *sec_name;
int prog_fd, map_fd = -1;
char filename[PATH_MAX];
struct bpf_object *obj;
@@ -134,7 +136,13 @@ int main(int argc, char **argv)
return 1;
}
- prog = bpf_object__find_program_by_title(obj, prog_name);
+ bpf_object__for_each_program(pos, obj) {
+ sec_name = bpf_program__section_name(pos);
+ if (sec_name && !strcmp(sec_name, prog_name)) {
+ prog = pos;
+ break;
+ }
+ }
prog_fd = bpf_program__fd(prog);
if (prog_fd < 0) {
printf("program not found: %s\n", strerror(prog_fd));
diff --git a/security/device_cgroup.c b/security/device_cgroup.c
index 04375df52fc9..842889f3dcb7 100644
--- a/security/device_cgroup.c
+++ b/security/device_cgroup.c
@@ -5,6 +5,7 @@
* Copyright 2007 IBM Corp
*/
+#include <linux/bpf-cgroup.h>
#include <linux/device_cgroup.h>
#include <linux/cgroup.h>
#include <linux/ctype.h>
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 42eb8eee3d89..83369f55df61 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -57,7 +57,7 @@ $(LIBBPF_INTERNAL_HDRS): $(LIBBPF_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_HDRS_
$(LIBBPF_BOOTSTRAP): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_BOOTSTRAP_OUTPUT)
$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_BOOTSTRAP_OUTPUT) \
DESTDIR=$(LIBBPF_BOOTSTRAP_DESTDIR) prefix= \
- ARCH= CC=$(HOSTCC) LD=$(HOSTLD) $@ install_headers
+ ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) $@ install_headers
$(LIBBPF_BOOTSTRAP_INTERNAL_HDRS): $(LIBBPF_BOOTSTRAP_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_BOOTSTRAP_HDRS_DIR)
$(call QUIET_INSTALL, $@)
@@ -152,6 +152,9 @@ CFLAGS += -DHAVE_LIBBFD_SUPPORT
SRCS += $(BFD_SRCS)
endif
+HOST_CFLAGS = $(subst -I$(LIBBPF_INCLUDE),-I$(LIBBPF_BOOTSTRAP_INCLUDE),\
+ $(subst $(CLANG_CROSS_FLAGS),,$(CFLAGS)))
+
BPFTOOL_BOOTSTRAP := $(BOOTSTRAP_OUTPUT)bpftool
BOOTSTRAP_OBJS = $(addprefix $(BOOTSTRAP_OUTPUT),main.o common.o json_writer.o gen.o btf.o xlated_dumper.o btf_dumper.o disasm.o)
@@ -202,7 +205,7 @@ endif
CFLAGS += $(if $(BUILD_BPF_SKELS),,-DBPFTOOL_WITHOUT_SKELETONS)
$(BOOTSTRAP_OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c
- $(QUIET_CC)$(HOSTCC) $(CFLAGS) -c -MMD $< -o $@
+ $(QUIET_CC)$(HOSTCC) $(HOST_CFLAGS) -c -MMD $< -o $@
$(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c
$(QUIET_CC)$(CC) $(CFLAGS) -c -MMD $< -o $@
@@ -213,15 +216,13 @@ ifneq ($(feature-zlib), 1)
endif
$(BPFTOOL_BOOTSTRAP): $(BOOTSTRAP_OBJS) $(LIBBPF_BOOTSTRAP)
- $(QUIET_LINK)$(HOSTCC) $(CFLAGS) $(LDFLAGS) $(BOOTSTRAP_OBJS) $(LIBS_BOOTSTRAP) -o $@
+ $(QUIET_LINK)$(HOSTCC) $(HOST_CFLAGS) $(LDFLAGS) $(BOOTSTRAP_OBJS) $(LIBS_BOOTSTRAP) -o $@
$(OUTPUT)bpftool: $(OBJS) $(LIBBPF)
$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(OBJS) $(LIBS) -o $@
$(BOOTSTRAP_OUTPUT)%.o: %.c $(LIBBPF_BOOTSTRAP_INTERNAL_HDRS) | $(BOOTSTRAP_OUTPUT)
- $(QUIET_CC)$(HOSTCC) \
- $(subst -I$(LIBBPF_INCLUDE),-I$(LIBBPF_BOOTSTRAP_INCLUDE),$(CFLAGS)) \
- -c -MMD $< -o $@
+ $(QUIET_CC)$(HOSTCC) $(HOST_CFLAGS) -c -MMD $< -o $@
$(OUTPUT)%.o: %.c
$(QUIET_CC)$(CC) $(CFLAGS) -c -MMD $< -o $@
diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c
index 5397077d0d9e..6719b9282eca 100644
--- a/tools/bpf/bpftool/feature.c
+++ b/tools/bpf/bpftool/feature.c
@@ -642,12 +642,32 @@ probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type,
printf("\n");
}
-static void
-probe_large_insn_limit(const char *define_prefix, __u32 ifindex)
+/*
+ * Probe for availability of kernel commit (5.3):
+ *
+ * c04c0d2b968a ("bpf: increase complexity limit and maximum program size")
+ */
+static void probe_large_insn_limit(const char *define_prefix, __u32 ifindex)
{
+ LIBBPF_OPTS(bpf_prog_load_opts, opts,
+ .prog_ifindex = ifindex,
+ );
+ struct bpf_insn insns[BPF_MAXINSNS + 1];
bool res;
+ int i, fd;
+
+ for (i = 0; i < BPF_MAXINSNS; i++)
+ insns[i] = BPF_MOV64_IMM(BPF_REG_0, 1);
+ insns[BPF_MAXINSNS] = BPF_EXIT_INSN();
+
+ errno = 0;
+ fd = bpf_prog_load(BPF_PROG_TYPE_SCHED_CLS, NULL, "GPL",
+ insns, ARRAY_SIZE(insns), &opts);
+ res = fd >= 0 || (errno != E2BIG && errno != EINVAL);
+
+ if (fd >= 0)
+ close(fd);
- res = bpf_probe_large_insn_limit(ifindex);
print_bool_feature("have_large_insn_limit",
"Large program size limit",
"LARGE_INSN_LIMIT",
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 8b71500e7cb2..020e91a542d5 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -408,6 +408,8 @@ int main(int argc, char **argv)
bool version_requested = false;
int opt, ret;
+ setlinebuf(stdout);
+
last_do_help = do_help;
pretty_output = false;
json_output = false;
diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile
index 751643f860b2..9ddeca947635 100644
--- a/tools/bpf/resolve_btfids/Makefile
+++ b/tools/bpf/resolve_btfids/Makefile
@@ -19,6 +19,7 @@ CC = $(HOSTCC)
LD = $(HOSTLD)
ARCH = $(HOSTARCH)
RM ?= rm
+CROSS_COMPILE =
OUTPUT ?= $(srctree)/tools/bpf/resolve_btfids/
diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile
index 8791d0e2762b..da6de16a3dfb 100644
--- a/tools/bpf/runqslower/Makefile
+++ b/tools/bpf/runqslower/Makefile
@@ -12,7 +12,7 @@ BPFOBJ := $(BPFOBJ_OUTPUT)libbpf.a
BPF_DESTDIR := $(BPFOBJ_OUTPUT)
BPF_INCLUDE := $(BPF_DESTDIR)/include
INCLUDES := -I$(OUTPUT) -I$(BPF_INCLUDE) -I$(abspath ../../include/uapi)
-CFLAGS := -g -Wall
+CFLAGS := -g -Wall $(CLANG_CROSS_FLAGS)
# Try to detect best kernel BTF source
KERNEL_REL := $(shell uname -r)
@@ -88,4 +88,4 @@ $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(BPFOBJ_OU
$(DEFAULT_BPFTOOL): $(BPFOBJ) | $(BPFTOOL_OUTPUT)
$(Q)$(MAKE) $(submake_extras) -C ../bpftool OUTPUT=$(BPFTOOL_OUTPUT) \
- CC=$(HOSTCC) LD=$(HOSTLD)
+ ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index c26871263f1f..b0383d371b9a 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4983,6 +4983,41 @@ union bpf_attr {
* Return
* The number of loops performed, **-EINVAL** for invalid **flags**,
* **-E2BIG** if **nr_loops** exceeds the maximum number of loops.
+ *
+ * long bpf_strncmp(const char *s1, u32 s1_sz, const char *s2)
+ * Description
+ * Do strncmp() between **s1** and **s2**. **s1** doesn't need
+ * to be null-terminated and **s1_sz** is the maximum storage
+ * size of **s1**. **s2** must be a read-only string.
+ * Return
+ * An integer less than, equal to, or greater than zero
+ * if the first **s1_sz** bytes of **s1** is found to be
+ * less than, to match, or be greater than **s2**.
+ *
+ * long bpf_get_func_arg(void *ctx, u32 n, u64 *value)
+ * Description
+ * Get **n**-th argument (zero based) of the traced function (for tracing programs)
+ * returned in **value**.
+ *
+ * Return
+ * 0 on success.
+ * **-EINVAL** if n >= arguments count of traced function.
+ *
+ * long bpf_get_func_ret(void *ctx, u64 *value)
+ * Description
+ * Get return value of the traced function (for tracing programs)
+ * in **value**.
+ *
+ * Return
+ * 0 on success.
+ * **-EOPNOTSUPP** for tracing programs other than BPF_TRACE_FEXIT or BPF_MODIFY_RETURN.
+ *
+ * long bpf_get_func_arg_cnt(void *ctx)
+ * Description
+ * Get number of arguments of the traced function (for tracing programs).
+ *
+ * Return
+ * The number of arguments of the traced function.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -5167,6 +5202,10 @@ union bpf_attr {
FN(kallsyms_lookup_name), \
FN(find_vma), \
FN(loop), \
+ FN(strncmp), \
+ FN(get_func_arg), \
+ FN(get_func_ret), \
+ FN(get_func_arg_cnt), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 5f7086fae31c..f947b61b2107 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -90,6 +90,7 @@ override CFLAGS += -Werror -Wall
override CFLAGS += $(INCLUDES)
override CFLAGS += -fvisibility=hidden
override CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
+override CFLAGS += $(CLANG_CROSS_FLAGS)
# flags specific for shared library
SHLIB_FLAGS := -DSHARED -fPIC
@@ -162,7 +163,7 @@ $(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h
$(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION)
$(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN_SHARED) $(VERSION_SCRIPT)
- $(QUIET_LINK)$(CC) $(LDFLAGS) \
+ $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) \
--shared -Wl,-soname,libbpf.so.$(LIBBPF_MAJOR_VERSION) \
-Wl,--version-script=$(VERSION_SCRIPT) $< -lelf -lz -o $@
@ln -sf $(@F) $(OUTPUT)libbpf.so
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 6b2407e12060..9b64eed2b003 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -28,7 +28,9 @@
#include <asm/unistd.h>
#include <errno.h>
#include <linux/bpf.h>
+#include <linux/filter.h>
#include <limits.h>
+#include <sys/resource.h>
#include "bpf.h"
#include "libbpf.h"
#include "libbpf_internal.h"
@@ -94,6 +96,77 @@ static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int
return fd;
}
+/* Probe whether kernel switched from memlock-based (RLIMIT_MEMLOCK) to
+ * memcg-based memory accounting for BPF maps and progs. This was done in [0].
+ * We use the support for bpf_ktime_get_coarse_ns() helper, which was added in
+ * the same 5.11 Linux release ([1]), to detect memcg-based accounting for BPF.
+ *
+ * [0] https://lore.kernel.org/bpf/20201201215900.3569844-1-guro@fb.com/
+ * [1] d05512618056 ("bpf: Add bpf_ktime_get_coarse_ns helper")
+ */
+int probe_memcg_account(void)
+{
+ const size_t prog_load_attr_sz = offsetofend(union bpf_attr, attach_btf_obj_fd);
+ struct bpf_insn insns[] = {
+ BPF_EMIT_CALL(BPF_FUNC_ktime_get_coarse_ns),
+ BPF_EXIT_INSN(),
+ };
+ size_t insn_cnt = sizeof(insns) / sizeof(insns[0]);
+ union bpf_attr attr;
+ int prog_fd;
+
+ /* attempt loading freplace trying to use custom BTF */
+ memset(&attr, 0, prog_load_attr_sz);
+ attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
+ attr.insns = ptr_to_u64(insns);
+ attr.insn_cnt = insn_cnt;
+ attr.license = ptr_to_u64("GPL");
+
+ prog_fd = sys_bpf_fd(BPF_PROG_LOAD, &attr, prog_load_attr_sz);
+ if (prog_fd >= 0) {
+ close(prog_fd);
+ return 1;
+ }
+ return 0;
+}
+
+static bool memlock_bumped;
+static rlim_t memlock_rlim = RLIM_INFINITY;
+
+int libbpf_set_memlock_rlim(size_t memlock_bytes)
+{
+ if (memlock_bumped)
+ return libbpf_err(-EBUSY);
+
+ memlock_rlim = memlock_bytes;
+ return 0;
+}
+
+int bump_rlimit_memlock(void)
+{
+ struct rlimit rlim;
+
+ /* this the default in libbpf 1.0, but for now user has to opt-in explicitly */
+ if (!(libbpf_mode & LIBBPF_STRICT_AUTO_RLIMIT_MEMLOCK))
+ return 0;
+
+ /* if kernel supports memcg-based accounting, skip bumping RLIMIT_MEMLOCK */
+ if (memlock_bumped || kernel_supports(NULL, FEAT_MEMCG_ACCOUNT))
+ return 0;
+
+ memlock_bumped = true;
+
+ /* zero memlock_rlim_max disables auto-bumping RLIMIT_MEMLOCK */
+ if (memlock_rlim == 0)
+ return 0;
+
+ rlim.rlim_cur = rlim.rlim_max = memlock_rlim;
+ if (setrlimit(RLIMIT_MEMLOCK, &rlim))
+ return -errno;
+
+ return 0;
+}
+
int bpf_map_create(enum bpf_map_type map_type,
const char *map_name,
__u32 key_size,
@@ -105,6 +178,8 @@ int bpf_map_create(enum bpf_map_type map_type,
union bpf_attr attr;
int fd;
+ bump_rlimit_memlock();
+
memset(&attr, 0, attr_sz);
if (!OPTS_VALID(opts, bpf_map_create_opts))
@@ -112,7 +187,7 @@ int bpf_map_create(enum bpf_map_type map_type,
attr.map_type = map_type;
if (map_name)
- strncat(attr.map_name, map_name, sizeof(attr.map_name) - 1);
+ libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name));
attr.key_size = key_size;
attr.value_size = value_size;
attr.max_entries = max_entries;
@@ -251,6 +326,8 @@ int bpf_prog_load_v0_6_0(enum bpf_prog_type prog_type,
union bpf_attr attr;
char *log_buf;
+ bump_rlimit_memlock();
+
if (!OPTS_VALID(opts, bpf_prog_load_opts))
return libbpf_err(-EINVAL);
@@ -271,7 +348,7 @@ int bpf_prog_load_v0_6_0(enum bpf_prog_type prog_type,
attr.kern_version = OPTS_GET(opts, kern_version, 0);
if (prog_name)
- strncat(attr.prog_name, prog_name, sizeof(attr.prog_name) - 1);
+ libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name));
attr.license = ptr_to_u64(license);
if (insn_cnt > UINT_MAX)
@@ -456,6 +533,8 @@ int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
union bpf_attr attr;
int fd;
+ bump_rlimit_memlock();
+
memset(&attr, 0, sizeof(attr));
attr.prog_type = type;
attr.insn_cnt = (__u32)insns_cnt;
@@ -1056,6 +1135,8 @@ int bpf_btf_load(const void *btf_data, size_t btf_size, const struct bpf_btf_loa
__u32 log_level;
int fd;
+ bump_rlimit_memlock();
+
memset(&attr, 0, attr_sz);
if (!OPTS_VALID(opts, bpf_btf_load_opts))
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 94e553a0ff9d..00619f64a040 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -35,6 +35,8 @@
extern "C" {
#endif
+int libbpf_set_memlock_rlim(size_t memlock_bytes);
+
struct bpf_map_create_opts {
size_t sz; /* size of this struct for forward/backward compatibility */
diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h
index db05a5937105..90f56b0f585f 100644
--- a/tools/lib/bpf/bpf_tracing.h
+++ b/tools/lib/bpf/bpf_tracing.h
@@ -66,277 +66,204 @@
#if defined(__KERNEL__) || defined(__VMLINUX_H__)
-#define PT_REGS_PARM1(x) ((x)->di)
-#define PT_REGS_PARM2(x) ((x)->si)
-#define PT_REGS_PARM3(x) ((x)->dx)
-#define PT_REGS_PARM4(x) ((x)->cx)
-#define PT_REGS_PARM5(x) ((x)->r8)
-#define PT_REGS_RET(x) ((x)->sp)
-#define PT_REGS_FP(x) ((x)->bp)
-#define PT_REGS_RC(x) ((x)->ax)
-#define PT_REGS_SP(x) ((x)->sp)
-#define PT_REGS_IP(x) ((x)->ip)
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), di)
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), si)
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), dx)
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), cx)
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), r8)
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), sp)
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), bp)
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), ax)
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), sp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), ip)
+#define __PT_PARM1_REG di
+#define __PT_PARM2_REG si
+#define __PT_PARM3_REG dx
+#define __PT_PARM4_REG cx
+#define __PT_PARM5_REG r8
+#define __PT_RET_REG sp
+#define __PT_FP_REG bp
+#define __PT_RC_REG ax
+#define __PT_SP_REG sp
+#define __PT_IP_REG ip
#else
#ifdef __i386__
-/* i386 kernel is built with -mregparm=3 */
-#define PT_REGS_PARM1(x) ((x)->eax)
-#define PT_REGS_PARM2(x) ((x)->edx)
-#define PT_REGS_PARM3(x) ((x)->ecx)
-#define PT_REGS_PARM4(x) 0
-#define PT_REGS_PARM5(x) 0
-#define PT_REGS_RET(x) ((x)->esp)
-#define PT_REGS_FP(x) ((x)->ebp)
-#define PT_REGS_RC(x) ((x)->eax)
-#define PT_REGS_SP(x) ((x)->esp)
-#define PT_REGS_IP(x) ((x)->eip)
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), eax)
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), edx)
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), ecx)
-#define PT_REGS_PARM4_CORE(x) 0
-#define PT_REGS_PARM5_CORE(x) 0
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), esp)
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), ebp)
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), eax)
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), esp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), eip)
-
-#else
-#define PT_REGS_PARM1(x) ((x)->rdi)
-#define PT_REGS_PARM2(x) ((x)->rsi)
-#define PT_REGS_PARM3(x) ((x)->rdx)
-#define PT_REGS_PARM4(x) ((x)->rcx)
-#define PT_REGS_PARM5(x) ((x)->r8)
-#define PT_REGS_RET(x) ((x)->rsp)
-#define PT_REGS_FP(x) ((x)->rbp)
-#define PT_REGS_RC(x) ((x)->rax)
-#define PT_REGS_SP(x) ((x)->rsp)
-#define PT_REGS_IP(x) ((x)->rip)
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), rdi)
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), rsi)
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), rdx)
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), rcx)
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), r8)
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), rsp)
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), rbp)
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), rax)
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), rsp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), rip)
-
-#endif
-#endif
+#define __PT_PARM1_REG eax
+#define __PT_PARM2_REG edx
+#define __PT_PARM3_REG ecx
+/* i386 kernel is built with -mregparm=3 */
+#define __PT_PARM4_REG __unsupported__
+#define __PT_PARM5_REG __unsupported__
+#define __PT_RET_REG esp
+#define __PT_FP_REG ebp
+#define __PT_RC_REG eax
+#define __PT_SP_REG esp
+#define __PT_IP_REG eip
+
+#else /* __i386__ */
+
+#define __PT_PARM1_REG rdi
+#define __PT_PARM2_REG rsi
+#define __PT_PARM3_REG rdx
+#define __PT_PARM4_REG rcx
+#define __PT_PARM5_REG r8
+#define __PT_RET_REG rsp
+#define __PT_FP_REG rbp
+#define __PT_RC_REG rax
+#define __PT_SP_REG rsp
+#define __PT_IP_REG rip
+
+#endif /* __i386__ */
+
+#endif /* __KERNEL__ || __VMLINUX_H__ */
#elif defined(bpf_target_s390)
/* s390 provides user_pt_regs instead of struct pt_regs to userspace */
-struct pt_regs;
-#define PT_REGS_S390 const volatile user_pt_regs
-#define PT_REGS_PARM1(x) (((PT_REGS_S390 *)(x))->gprs[2])
-#define PT_REGS_PARM2(x) (((PT_REGS_S390 *)(x))->gprs[3])
-#define PT_REGS_PARM3(x) (((PT_REGS_S390 *)(x))->gprs[4])
-#define PT_REGS_PARM4(x) (((PT_REGS_S390 *)(x))->gprs[5])
-#define PT_REGS_PARM5(x) (((PT_REGS_S390 *)(x))->gprs[6])
-#define PT_REGS_RET(x) (((PT_REGS_S390 *)(x))->gprs[14])
-/* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_FP(x) (((PT_REGS_S390 *)(x))->gprs[11])
-#define PT_REGS_RC(x) (((PT_REGS_S390 *)(x))->gprs[2])
-#define PT_REGS_SP(x) (((PT_REGS_S390 *)(x))->gprs[15])
-#define PT_REGS_IP(x) (((PT_REGS_S390 *)(x))->psw.addr)
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[2])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[3])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[4])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[5])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[6])
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[14])
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[11])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[2])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[15])
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), psw.addr)
+#define __PT_REGS_CAST(x) ((const user_pt_regs *)(x))
+#define __PT_PARM1_REG gprs[2]
+#define __PT_PARM2_REG gprs[3]
+#define __PT_PARM3_REG gprs[4]
+#define __PT_PARM4_REG gprs[5]
+#define __PT_PARM5_REG gprs[6]
+#define __PT_RET_REG grps[14]
+#define __PT_FP_REG gprs[11] /* Works only with CONFIG_FRAME_POINTER */
+#define __PT_RC_REG gprs[2]
+#define __PT_SP_REG gprs[15]
+#define __PT_IP_REG psw.addr
#elif defined(bpf_target_arm)
-#define PT_REGS_PARM1(x) ((x)->uregs[0])
-#define PT_REGS_PARM2(x) ((x)->uregs[1])
-#define PT_REGS_PARM3(x) ((x)->uregs[2])
-#define PT_REGS_PARM4(x) ((x)->uregs[3])
-#define PT_REGS_PARM5(x) ((x)->uregs[4])
-#define PT_REGS_RET(x) ((x)->uregs[14])
-#define PT_REGS_FP(x) ((x)->uregs[11]) /* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_RC(x) ((x)->uregs[0])
-#define PT_REGS_SP(x) ((x)->uregs[13])
-#define PT_REGS_IP(x) ((x)->uregs[12])
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), uregs[0])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), uregs[1])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), uregs[2])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), uregs[3])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), uregs[4])
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), uregs[14])
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), uregs[11])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), uregs[0])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), uregs[13])
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), uregs[12])
+#define __PT_PARM1_REG uregs[0]
+#define __PT_PARM2_REG uregs[1]
+#define __PT_PARM3_REG uregs[2]
+#define __PT_PARM4_REG uregs[3]
+#define __PT_PARM5_REG uregs[4]
+#define __PT_RET_REG uregs[14]
+#define __PT_FP_REG uregs[11] /* Works only with CONFIG_FRAME_POINTER */
+#define __PT_RC_REG uregs[0]
+#define __PT_SP_REG uregs[13]
+#define __PT_IP_REG uregs[12]
#elif defined(bpf_target_arm64)
/* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */
-struct pt_regs;
-#define PT_REGS_ARM64 const volatile struct user_pt_regs
-#define PT_REGS_PARM1(x) (((PT_REGS_ARM64 *)(x))->regs[0])
-#define PT_REGS_PARM2(x) (((PT_REGS_ARM64 *)(x))->regs[1])
-#define PT_REGS_PARM3(x) (((PT_REGS_ARM64 *)(x))->regs[2])
-#define PT_REGS_PARM4(x) (((PT_REGS_ARM64 *)(x))->regs[3])
-#define PT_REGS_PARM5(x) (((PT_REGS_ARM64 *)(x))->regs[4])
-#define PT_REGS_RET(x) (((PT_REGS_ARM64 *)(x))->regs[30])
-/* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_FP(x) (((PT_REGS_ARM64 *)(x))->regs[29])
-#define PT_REGS_RC(x) (((PT_REGS_ARM64 *)(x))->regs[0])
-#define PT_REGS_SP(x) (((PT_REGS_ARM64 *)(x))->sp)
-#define PT_REGS_IP(x) (((PT_REGS_ARM64 *)(x))->pc)
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[0])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[1])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[2])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[3])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[4])
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[30])
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[29])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[0])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), sp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), pc)
+#define __PT_REGS_CAST(x) ((const struct user_pt_regs *)(x))
+#define __PT_PARM1_REG regs[0]
+#define __PT_PARM2_REG regs[1]
+#define __PT_PARM3_REG regs[2]
+#define __PT_PARM4_REG regs[3]
+#define __PT_PARM5_REG regs[4]
+#define __PT_RET_REG regs[30]
+#define __PT_FP_REG regs[29] /* Works only with CONFIG_FRAME_POINTER */
+#define __PT_RC_REG regs[0]
+#define __PT_SP_REG sp
+#define __PT_IP_REG pc
#elif defined(bpf_target_mips)
-#define PT_REGS_PARM1(x) ((x)->regs[4])
-#define PT_REGS_PARM2(x) ((x)->regs[5])
-#define PT_REGS_PARM3(x) ((x)->regs[6])
-#define PT_REGS_PARM4(x) ((x)->regs[7])
-#define PT_REGS_PARM5(x) ((x)->regs[8])
-#define PT_REGS_RET(x) ((x)->regs[31])
-#define PT_REGS_FP(x) ((x)->regs[30]) /* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_RC(x) ((x)->regs[2])
-#define PT_REGS_SP(x) ((x)->regs[29])
-#define PT_REGS_IP(x) ((x)->cp0_epc)
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), regs[4])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), regs[5])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), regs[6])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), regs[7])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), regs[8])
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), regs[31])
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), regs[30])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), regs[2])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), regs[29])
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), cp0_epc)
+#define __PT_PARM1_REG regs[4]
+#define __PT_PARM2_REG regs[5]
+#define __PT_PARM3_REG regs[6]
+#define __PT_PARM4_REG regs[7]
+#define __PT_PARM5_REG regs[8]
+#define __PT_RET_REG regs[31]
+#define __PT_FP_REG regs[30] /* Works only with CONFIG_FRAME_POINTER */
+#define __PT_RC_REG regs[2]
+#define __PT_SP_REG regs[29]
+#define __PT_IP_REG cp0_epc
#elif defined(bpf_target_powerpc)
-#define PT_REGS_PARM1(x) ((x)->gpr[3])
-#define PT_REGS_PARM2(x) ((x)->gpr[4])
-#define PT_REGS_PARM3(x) ((x)->gpr[5])
-#define PT_REGS_PARM4(x) ((x)->gpr[6])
-#define PT_REGS_PARM5(x) ((x)->gpr[7])
-#define PT_REGS_RC(x) ((x)->gpr[3])
-#define PT_REGS_SP(x) ((x)->sp)
-#define PT_REGS_IP(x) ((x)->nip)
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), gpr[3])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), gpr[4])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), gpr[5])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), gpr[6])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), gpr[7])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), gpr[3])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), sp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), nip)
+#define __PT_PARM1_REG gpr[3]
+#define __PT_PARM2_REG gpr[4]
+#define __PT_PARM3_REG gpr[5]
+#define __PT_PARM4_REG gpr[6]
+#define __PT_PARM5_REG gpr[7]
+#define __PT_RET_REG regs[31]
+#define __PT_FP_REG __unsupported__
+#define __PT_RC_REG gpr[3]
+#define __PT_SP_REG sp
+#define __PT_IP_REG nip
#elif defined(bpf_target_sparc)
-#define PT_REGS_PARM1(x) ((x)->u_regs[UREG_I0])
-#define PT_REGS_PARM2(x) ((x)->u_regs[UREG_I1])
-#define PT_REGS_PARM3(x) ((x)->u_regs[UREG_I2])
-#define PT_REGS_PARM4(x) ((x)->u_regs[UREG_I3])
-#define PT_REGS_PARM5(x) ((x)->u_regs[UREG_I4])
-#define PT_REGS_RET(x) ((x)->u_regs[UREG_I7])
-#define PT_REGS_RC(x) ((x)->u_regs[UREG_I0])
-#define PT_REGS_SP(x) ((x)->u_regs[UREG_FP])
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I0])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I1])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I2])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I3])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I4])
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I7])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I0])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), u_regs[UREG_FP])
-
+#define __PT_PARM1_REG u_regs[UREG_I0]
+#define __PT_PARM2_REG u_regs[UREG_I1]
+#define __PT_PARM3_REG u_regs[UREG_I2]
+#define __PT_PARM4_REG u_regs[UREG_I3]
+#define __PT_PARM5_REG u_regs[UREG_I4]
+#define __PT_RET_REG u_regs[UREG_I7]
+#define __PT_FP_REG __unsupported__
+#define __PT_RC_REG u_regs[UREG_I0]
+#define __PT_SP_REG u_regs[UREG_FP]
/* Should this also be a bpf_target check for the sparc case? */
#if defined(__arch64__)
-#define PT_REGS_IP(x) ((x)->tpc)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), tpc)
+#define __PT_IP_REG tpc
#else
-#define PT_REGS_IP(x) ((x)->pc)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), pc)
+#define __PT_IP_REG pc
#endif
#elif defined(bpf_target_riscv)
+#define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x))
+#define __PT_PARM1_REG a0
+#define __PT_PARM2_REG a1
+#define __PT_PARM3_REG a2
+#define __PT_PARM4_REG a3
+#define __PT_PARM5_REG a4
+#define __PT_RET_REG ra
+#define __PT_FP_REG fp
+#define __PT_RC_REG a5
+#define __PT_SP_REG sp
+#define __PT_IP_REG epc
+
+#endif
+
+#if defined(bpf_target_defined)
+
struct pt_regs;
-#define PT_REGS_RV const volatile struct user_regs_struct
-#define PT_REGS_PARM1(x) (((PT_REGS_RV *)(x))->a0)
-#define PT_REGS_PARM2(x) (((PT_REGS_RV *)(x))->a1)
-#define PT_REGS_PARM3(x) (((PT_REGS_RV *)(x))->a2)
-#define PT_REGS_PARM4(x) (((PT_REGS_RV *)(x))->a3)
-#define PT_REGS_PARM5(x) (((PT_REGS_RV *)(x))->a4)
-#define PT_REGS_RET(x) (((PT_REGS_RV *)(x))->ra)
-#define PT_REGS_FP(x) (((PT_REGS_RV *)(x))->s5)
-#define PT_REGS_RC(x) (((PT_REGS_RV *)(x))->a5)
-#define PT_REGS_SP(x) (((PT_REGS_RV *)(x))->sp)
-#define PT_REGS_IP(x) (((PT_REGS_RV *)(x))->epc)
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a0)
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a1)
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a2)
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a3)
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a4)
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), ra)
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), fp)
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a5)
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), sp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), epc)
+/* allow some architecutres to override `struct pt_regs` */
+#ifndef __PT_REGS_CAST
+#define __PT_REGS_CAST(x) (x)
#endif
+#define PT_REGS_PARM1(x) (__PT_REGS_CAST(x)->__PT_PARM1_REG)
+#define PT_REGS_PARM2(x) (__PT_REGS_CAST(x)->__PT_PARM2_REG)
+#define PT_REGS_PARM3(x) (__PT_REGS_CAST(x)->__PT_PARM3_REG)
+#define PT_REGS_PARM4(x) (__PT_REGS_CAST(x)->__PT_PARM4_REG)
+#define PT_REGS_PARM5(x) (__PT_REGS_CAST(x)->__PT_PARM5_REG)
+#define PT_REGS_RET(x) (__PT_REGS_CAST(x)->__PT_RET_REG)
+#define PT_REGS_FP(x) (__PT_REGS_CAST(x)->__PT_FP_REG)
+#define PT_REGS_RC(x) (__PT_REGS_CAST(x)->__PT_RC_REG)
+#define PT_REGS_SP(x) (__PT_REGS_CAST(x)->__PT_SP_REG)
+#define PT_REGS_IP(x) (__PT_REGS_CAST(x)->__PT_IP_REG)
+
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM1_REG)
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM2_REG)
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM3_REG)
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM4_REG)
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM5_REG)
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_RET_REG)
+#define PT_REGS_FP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_FP_REG)
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_RC_REG)
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_SP_REG)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_IP_REG)
+
#if defined(bpf_target_powerpc)
+
#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = (ctx)->link; })
#define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP
+
#elif defined(bpf_target_sparc)
+
#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = PT_REGS_RET(ctx); })
#define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP
-#elif defined(bpf_target_defined)
+
+#else
+
#define BPF_KPROBE_READ_RET_IP(ip, ctx) \
({ bpf_probe_read_kernel(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); })
#define BPF_KRETPROBE_READ_RET_IP(ip, ctx) \
- ({ bpf_probe_read_kernel(&(ip), sizeof(ip), \
- (void *)(PT_REGS_FP(ctx) + sizeof(ip))); })
+ ({ bpf_probe_read_kernel(&(ip), sizeof(ip), (void *)(PT_REGS_FP(ctx) + sizeof(ip))); })
+
#endif
-#if !defined(bpf_target_defined)
+#else /* defined(bpf_target_defined) */
#define PT_REGS_PARM1(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
#define PT_REGS_PARM2(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
@@ -363,7 +290,7 @@ struct pt_regs;
#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
#define BPF_KRETPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
-#endif /* !defined(bpf_target_defined) */
+#endif /* defined(bpf_target_defined) */
#ifndef ___bpf_concat
#define ___bpf_concat(a, b) a ## b
@@ -375,25 +302,23 @@ struct pt_regs;
#define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N
#endif
#ifndef ___bpf_narg
-#define ___bpf_narg(...) \
- ___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
+#define ___bpf_narg(...) ___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
#endif
-#define ___bpf_ctx_cast0() ctx
-#define ___bpf_ctx_cast1(x) ___bpf_ctx_cast0(), (void *)ctx[0]
-#define ___bpf_ctx_cast2(x, args...) ___bpf_ctx_cast1(args), (void *)ctx[1]
-#define ___bpf_ctx_cast3(x, args...) ___bpf_ctx_cast2(args), (void *)ctx[2]
-#define ___bpf_ctx_cast4(x, args...) ___bpf_ctx_cast3(args), (void *)ctx[3]
-#define ___bpf_ctx_cast5(x, args...) ___bpf_ctx_cast4(args), (void *)ctx[4]
-#define ___bpf_ctx_cast6(x, args...) ___bpf_ctx_cast5(args), (void *)ctx[5]
-#define ___bpf_ctx_cast7(x, args...) ___bpf_ctx_cast6(args), (void *)ctx[6]
-#define ___bpf_ctx_cast8(x, args...) ___bpf_ctx_cast7(args), (void *)ctx[7]
-#define ___bpf_ctx_cast9(x, args...) ___bpf_ctx_cast8(args), (void *)ctx[8]
+#define ___bpf_ctx_cast0() ctx
+#define ___bpf_ctx_cast1(x) ___bpf_ctx_cast0(), (void *)ctx[0]
+#define ___bpf_ctx_cast2(x, args...) ___bpf_ctx_cast1(args), (void *)ctx[1]
+#define ___bpf_ctx_cast3(x, args...) ___bpf_ctx_cast2(args), (void *)ctx[2]
+#define ___bpf_ctx_cast4(x, args...) ___bpf_ctx_cast3(args), (void *)ctx[3]
+#define ___bpf_ctx_cast5(x, args...) ___bpf_ctx_cast4(args), (void *)ctx[4]
+#define ___bpf_ctx_cast6(x, args...) ___bpf_ctx_cast5(args), (void *)ctx[5]
+#define ___bpf_ctx_cast7(x, args...) ___bpf_ctx_cast6(args), (void *)ctx[6]
+#define ___bpf_ctx_cast8(x, args...) ___bpf_ctx_cast7(args), (void *)ctx[7]
+#define ___bpf_ctx_cast9(x, args...) ___bpf_ctx_cast8(args), (void *)ctx[8]
#define ___bpf_ctx_cast10(x, args...) ___bpf_ctx_cast9(args), (void *)ctx[9]
#define ___bpf_ctx_cast11(x, args...) ___bpf_ctx_cast10(args), (void *)ctx[10]
#define ___bpf_ctx_cast12(x, args...) ___bpf_ctx_cast11(args), (void *)ctx[11]
-#define ___bpf_ctx_cast(args...) \
- ___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args)
+#define ___bpf_ctx_cast(args...) ___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args)
/*
* BPF_PROG is a convenience wrapper for generic tp_btf/fentry/fexit and
@@ -426,19 +351,13 @@ ____##name(unsigned long long *ctx, ##args)
struct pt_regs;
-#define ___bpf_kprobe_args0() ctx
-#define ___bpf_kprobe_args1(x) \
- ___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx)
-#define ___bpf_kprobe_args2(x, args...) \
- ___bpf_kprobe_args1(args), (void *)PT_REGS_PARM2(ctx)
-#define ___bpf_kprobe_args3(x, args...) \
- ___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx)
-#define ___bpf_kprobe_args4(x, args...) \
- ___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx)
-#define ___bpf_kprobe_args5(x, args...) \
- ___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx)
-#define ___bpf_kprobe_args(args...) \
- ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args)
+#define ___bpf_kprobe_args0() ctx
+#define ___bpf_kprobe_args1(x) ___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx)
+#define ___bpf_kprobe_args2(x, args...) ___bpf_kprobe_args1(args), (void *)PT_REGS_PARM2(ctx)
+#define ___bpf_kprobe_args3(x, args...) ___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx)
+#define ___bpf_kprobe_args4(x, args...) ___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx)
+#define ___bpf_kprobe_args5(x, args...) ___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx)
+#define ___bpf_kprobe_args(args...) ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args)
/*
* BPF_KPROBE serves the same purpose for kprobes as BPF_PROG for
@@ -464,11 +383,9 @@ typeof(name(0)) name(struct pt_regs *ctx) \
static __attribute__((always_inline)) typeof(name(0)) \
____##name(struct pt_regs *ctx, ##args)
-#define ___bpf_kretprobe_args0() ctx
-#define ___bpf_kretprobe_args1(x) \
- ___bpf_kretprobe_args0(), (void *)PT_REGS_RC(ctx)
-#define ___bpf_kretprobe_args(args...) \
- ___bpf_apply(___bpf_kretprobe_args, ___bpf_narg(args))(args)
+#define ___bpf_kretprobe_args0() ctx
+#define ___bpf_kretprobe_args1(x) ___bpf_kretprobe_args0(), (void *)PT_REGS_RC(ctx)
+#define ___bpf_kretprobe_args(args...) ___bpf_apply(___bpf_kretprobe_args, ___bpf_narg(args))(args)
/*
* BPF_KRETPROBE is similar to BPF_KPROBE, except, it only provides optional
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 742a2bf71c5e..061839f04525 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -313,12 +313,18 @@ LIBBPF_API struct btf_dump *btf_dump__new_deprecated(const struct btf *btf,
*
* The rest works just like in case of ___libbpf_override() usage with symbol
* versioning.
+ *
+ * C++ compilers don't support __builtin_types_compatible_p(), so at least
+ * don't screw up compilation for them and let C++ users pick btf_dump__new
+ * vs btf_dump__new_deprecated explicitly.
*/
+#ifndef __cplusplus
#define btf_dump__new(a1, a2, a3, a4) __builtin_choose_expr( \
__builtin_types_compatible_p(typeof(a4), btf_dump_printf_fn_t) || \
__builtin_types_compatible_p(typeof(a4), void(void *, const char *, va_list)), \
btf_dump__new_deprecated((void *)a1, (void *)a2, (void *)a3, (void *)a4), \
btf_dump__new((void *)a1, (void *)a2, (void *)a3, (void *)a4))
+#endif
LIBBPF_API void btf_dump__free(struct btf_dump *d);
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index f06a1d343c92..b9a3260c83cb 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -2321,8 +2321,8 @@ int btf_dump__dump_type_data(struct btf_dump *d, __u32 id,
if (!opts->indent_str)
d->typed_dump->indent_str[0] = '\t';
else
- strncat(d->typed_dump->indent_str, opts->indent_str,
- sizeof(d->typed_dump->indent_str) - 1);
+ libbpf_strlcpy(d->typed_dump->indent_str, opts->indent_str,
+ sizeof(d->typed_dump->indent_str));
d->typed_dump->compact = OPTS_GET(opts, compact, false);
d->typed_dump->skip_names = OPTS_GET(opts, skip_names, false);
diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c
index 8ed02e89c9a9..8ecef1088ba2 100644
--- a/tools/lib/bpf/gen_loader.c
+++ b/tools/lib/bpf/gen_loader.c
@@ -371,8 +371,9 @@ int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps)
{
int i;
- if (nr_progs != gen->nr_progs || nr_maps != gen->nr_maps) {
- pr_warn("progs/maps mismatch\n");
+ if (nr_progs < gen->nr_progs || nr_maps != gen->nr_maps) {
+ pr_warn("nr_progs %d/%d nr_maps %d/%d mismatch\n",
+ nr_progs, gen->nr_progs, nr_maps, gen->nr_maps);
gen->error = -EFAULT;
return gen->error;
}
@@ -462,8 +463,7 @@ void bpf_gen__map_create(struct bpf_gen *gen,
attr.map_flags = map_attr->map_flags;
attr.map_extra = map_attr->map_extra;
if (map_name)
- memcpy(attr.map_name, map_name,
- min((unsigned)strlen(map_name), BPF_OBJ_NAME_LEN - 1));
+ libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name));
attr.numa_node = map_attr->numa_node;
attr.map_ifindex = map_attr->map_ifindex;
attr.max_entries = max_entries;
@@ -969,8 +969,7 @@ void bpf_gen__prog_load(struct bpf_gen *gen,
core_relos = add_data(gen, gen->core_relos,
attr.core_relo_cnt * attr.core_relo_rec_size);
- memcpy(attr.prog_name, prog_name,
- min((unsigned)strlen(prog_name), BPF_OBJ_NAME_LEN - 1));
+ libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name));
prog_load_attr = add_data(gen, &attr, attr_size);
/* populate union bpf_attr with a pointer to license */
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 902f1ad5b7e6..9cb99d1e2385 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -187,42 +187,6 @@ const char *libbpf_version_string(void)
#undef __S
}
-enum kern_feature_id {
- /* v4.14: kernel support for program & map names. */
- FEAT_PROG_NAME,
- /* v5.2: kernel support for global data sections. */
- FEAT_GLOBAL_DATA,
- /* BTF support */
- FEAT_BTF,
- /* BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO support */
- FEAT_BTF_FUNC,
- /* BTF_KIND_VAR and BTF_KIND_DATASEC support */
- FEAT_BTF_DATASEC,
- /* BTF_FUNC_GLOBAL is supported */
- FEAT_BTF_GLOBAL_FUNC,
- /* BPF_F_MMAPABLE is supported for arrays */
- FEAT_ARRAY_MMAP,
- /* kernel support for expected_attach_type in BPF_PROG_LOAD */
- FEAT_EXP_ATTACH_TYPE,
- /* bpf_probe_read_{kernel,user}[_str] helpers */
- FEAT_PROBE_READ_KERN,
- /* BPF_PROG_BIND_MAP is supported */
- FEAT_PROG_BIND_MAP,
- /* Kernel support for module BTFs */
- FEAT_MODULE_BTF,
- /* BTF_KIND_FLOAT support */
- FEAT_BTF_FLOAT,
- /* BPF perf link support */
- FEAT_PERF_LINK,
- /* BTF_KIND_DECL_TAG support */
- FEAT_BTF_DECL_TAG,
- /* BTF_KIND_TYPE_TAG support */
- FEAT_BTF_TYPE_TAG,
- __FEAT_CNT,
-};
-
-static bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id);
-
enum reloc_type {
RELO_LD64,
RELO_CALL,
@@ -831,11 +795,36 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data,
return 0;
}
-static __u32 get_kernel_version(void)
+__u32 get_kernel_version(void)
{
+ /* On Ubuntu LINUX_VERSION_CODE doesn't correspond to info.release,
+ * but Ubuntu provides /proc/version_signature file, as described at
+ * https://ubuntu.com/kernel, with an example contents below, which we
+ * can use to get a proper LINUX_VERSION_CODE.
+ *
+ * Ubuntu 5.4.0-12.15-generic 5.4.8
+ *
+ * In the above, 5.4.8 is what kernel is actually expecting, while
+ * uname() call will return 5.4.0 in info.release.
+ */
+ const char *ubuntu_kver_file = "/proc/version_signature";
__u32 major, minor, patch;
struct utsname info;
+ if (access(ubuntu_kver_file, R_OK) == 0) {
+ FILE *f;
+
+ f = fopen(ubuntu_kver_file, "r");
+ if (f) {
+ if (fscanf(f, "%*s %*s %d.%d.%d\n", &major, &minor, &patch) == 3) {
+ fclose(f);
+ return KERNEL_VERSION(major, minor, patch);
+ }
+ fclose(f);
+ }
+ /* something went wrong, fall back to uname() approach */
+ }
+
uname(&info);
if (sscanf(info.release, "%u.%u.%u", &major, &minor, &patch) != 3)
return 0;
@@ -1201,12 +1190,10 @@ static struct bpf_object *bpf_object__new(const char *path,
strcpy(obj->path, path);
if (obj_name) {
- strncpy(obj->name, obj_name, sizeof(obj->name) - 1);
- obj->name[sizeof(obj->name) - 1] = 0;
+ libbpf_strlcpy(obj->name, obj_name, sizeof(obj->name));
} else {
/* Using basename() GNU version which doesn't modify arg. */
- strncpy(obj->name, basename((void *)path),
- sizeof(obj->name) - 1);
+ libbpf_strlcpy(obj->name, basename((void *)path), sizeof(obj->name));
end = strchr(obj->name, '.');
if (end)
*end = 0;
@@ -1358,7 +1345,10 @@ static int bpf_object__check_endianness(struct bpf_object *obj)
static int
bpf_object__init_license(struct bpf_object *obj, void *data, size_t size)
{
- memcpy(obj->license, data, min(size, sizeof(obj->license) - 1));
+ /* libbpf_strlcpy() only copies first N - 1 bytes, so size + 1 won't
+ * go over allowed ELF data section buffer
+ */
+ libbpf_strlcpy(obj->license, data, min(size + 1, sizeof(obj->license)));
pr_debug("license of %s is %s\n", obj->path, obj->license);
return 0;
}
@@ -4354,6 +4344,10 @@ bpf_object__probe_loading(struct bpf_object *obj)
if (obj->gen_loader)
return 0;
+ ret = bump_rlimit_memlock();
+ if (ret)
+ pr_warn("Failed to bump RLIMIT_MEMLOCK (err = %d), you might need to do it explicitly!\n", ret);
+
/* make sure basic loading works */
ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL);
if (ret < 0)
@@ -4720,14 +4714,17 @@ static struct kern_feature_desc {
[FEAT_BTF_TYPE_TAG] = {
"BTF_KIND_TYPE_TAG support", probe_kern_btf_type_tag,
},
+ [FEAT_MEMCG_ACCOUNT] = {
+ "memcg-based memory accounting", probe_memcg_account,
+ },
};
-static bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id)
+bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id)
{
struct kern_feature_desc *feat = &feature_probes[feat_id];
int ret;
- if (obj->gen_loader)
+ if (obj && obj->gen_loader)
/* To generate loader program assume the latest kernel
* to avoid doing extra prog_load, map_create syscalls.
*/
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index a8b894dae633..85dfef88b3d2 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -227,6 +227,7 @@ struct btf;
LIBBPF_API struct btf *bpf_object__btf(const struct bpf_object *obj);
LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj);
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__find_program_by_name() instead")
LIBBPF_API struct bpf_program *
bpf_object__find_program_by_title(const struct bpf_object *obj,
const char *title);
@@ -339,7 +340,31 @@ LIBBPF_DEPRECATED_SINCE(0, 7, "multi-instance bpf_program support is deprecated"
LIBBPF_API int bpf_program__unpin_instance(struct bpf_program *prog,
const char *path,
int instance);
+
+/**
+ * @brief **bpf_program__pin()** pins the BPF program to a file
+ * in the BPF FS specified by a path. This increments the programs
+ * reference count, allowing it to stay loaded after the process
+ * which loaded it has exited.
+ *
+ * @param prog BPF program to pin, must already be loaded
+ * @param path file path in a BPF file system
+ * @return 0, on success; negative error code, otherwise
+ */
LIBBPF_API int bpf_program__pin(struct bpf_program *prog, const char *path);
+
+/**
+ * @brief **bpf_program__unpin()** unpins the BPF program from a file
+ * in the BPFFS specified by a path. This decrements the programs
+ * reference count.
+ *
+ * The file pinning the BPF program can also be unlinked by a different
+ * process in which case this function will return an error.
+ *
+ * @param prog BPF program to unpin
+ * @param path file path to the pin in a BPF file system
+ * @return 0, on success; negative error code, otherwise
+ */
LIBBPF_API int bpf_program__unpin(struct bpf_program *prog, const char *path);
LIBBPF_API void bpf_program__unload(struct bpf_program *prog);
@@ -1027,13 +1052,57 @@ bpf_prog_linfo__lfind(const struct bpf_prog_linfo *prog_linfo,
* user, causing subsequent probes to fail. In this case, the caller may want
* to adjust that limit with setrlimit().
*/
-LIBBPF_API bool bpf_probe_prog_type(enum bpf_prog_type prog_type,
- __u32 ifindex);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use libbpf_probe_bpf_prog_type() instead")
+LIBBPF_API bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use libbpf_probe_bpf_map_type() instead")
LIBBPF_API bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex);
-LIBBPF_API bool bpf_probe_helper(enum bpf_func_id id,
- enum bpf_prog_type prog_type, __u32 ifindex);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use libbpf_probe_bpf_helper() instead")
+LIBBPF_API bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type, __u32 ifindex);
+LIBBPF_DEPRECATED_SINCE(0, 8, "implement your own or use bpftool for feature detection")
LIBBPF_API bool bpf_probe_large_insn_limit(__u32 ifindex);
+/**
+ * @brief **libbpf_probe_bpf_prog_type()** detects if host kernel supports
+ * BPF programs of a given type.
+ * @param prog_type BPF program type to detect kernel support for
+ * @param opts reserved for future extensibility, should be NULL
+ * @return 1, if given program type is supported; 0, if given program type is
+ * not supported; negative error code if feature detection failed or can't be
+ * performed
+ *
+ * Make sure the process has required set of CAP_* permissions (or runs as
+ * root) when performing feature checking.
+ */
+LIBBPF_API int libbpf_probe_bpf_prog_type(enum bpf_prog_type prog_type, const void *opts);
+/**
+ * @brief **libbpf_probe_bpf_map_type()** detects if host kernel supports
+ * BPF maps of a given type.
+ * @param map_type BPF map type to detect kernel support for
+ * @param opts reserved for future extensibility, should be NULL
+ * @return 1, if given map type is supported; 0, if given map type is
+ * not supported; negative error code if feature detection failed or can't be
+ * performed
+ *
+ * Make sure the process has required set of CAP_* permissions (or runs as
+ * root) when performing feature checking.
+ */
+LIBBPF_API int libbpf_probe_bpf_map_type(enum bpf_map_type map_type, const void *opts);
+/**
+ * @brief **libbpf_probe_bpf_helper()** detects if host kernel supports the
+ * use of a given BPF helper from specified BPF program type.
+ * @param prog_type BPF program type used to check the support of BPF helper
+ * @param helper_id BPF helper ID (enum bpf_func_id) to check support for
+ * @param opts reserved for future extensibility, should be NULL
+ * @return 1, if given combination of program type and helper is supported; 0,
+ * if the combination is not supported; negative error code if feature
+ * detection for provided input arguments failed or can't be performed
+ *
+ * Make sure the process has required set of CAP_* permissions (or runs as
+ * root) when performing feature checking.
+ */
+LIBBPF_API int libbpf_probe_bpf_helper(enum bpf_prog_type prog_type,
+ enum bpf_func_id helper_id, const void *opts);
+
/*
* Get bpf_prog_info in continuous memory
*
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 4d483af7dba6..529783967793 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -427,4 +427,8 @@ LIBBPF_0.7.0 {
bpf_program__log_level;
bpf_program__set_log_buf;
bpf_program__set_log_level;
+ libbpf_probe_bpf_helper;
+ libbpf_probe_bpf_map_type;
+ libbpf_probe_bpf_prog_type;
+ libbpf_set_memlock_rlim_max;
};
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 355c41019aed..1565679eb432 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -169,6 +169,27 @@ static inline void *libbpf_reallocarray(void *ptr, size_t nmemb, size_t size)
return realloc(ptr, total);
}
+/* Copy up to sz - 1 bytes from zero-terminated src string and ensure that dst
+ * is zero-terminated string no matter what (unless sz == 0, in which case
+ * it's a no-op). It's conceptually close to FreeBSD's strlcpy(), but differs
+ * in what is returned. Given this is internal helper, it's trivial to extend
+ * this, when necessary. Use this instead of strncpy inside libbpf source code.
+ */
+static inline void libbpf_strlcpy(char *dst, const char *src, size_t sz)
+{
+ size_t i;
+
+ if (sz == 0)
+ return;
+
+ sz--;
+ for (i = 0; i < sz && src[i]; i++)
+ dst[i] = src[i];
+ dst[i] = '\0';
+}
+
+__u32 get_kernel_version(void);
+
struct btf;
struct btf_type;
@@ -272,6 +293,45 @@ static inline bool libbpf_validate_opts(const char *opts,
(opts)->sz - __off); \
})
+enum kern_feature_id {
+ /* v4.14: kernel support for program & map names. */
+ FEAT_PROG_NAME,
+ /* v5.2: kernel support for global data sections. */
+ FEAT_GLOBAL_DATA,
+ /* BTF support */
+ FEAT_BTF,
+ /* BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO support */
+ FEAT_BTF_FUNC,
+ /* BTF_KIND_VAR and BTF_KIND_DATASEC support */
+ FEAT_BTF_DATASEC,
+ /* BTF_FUNC_GLOBAL is supported */
+ FEAT_BTF_GLOBAL_FUNC,
+ /* BPF_F_MMAPABLE is supported for arrays */
+ FEAT_ARRAY_MMAP,
+ /* kernel support for expected_attach_type in BPF_PROG_LOAD */
+ FEAT_EXP_ATTACH_TYPE,
+ /* bpf_probe_read_{kernel,user}[_str] helpers */
+ FEAT_PROBE_READ_KERN,
+ /* BPF_PROG_BIND_MAP is supported */
+ FEAT_PROG_BIND_MAP,
+ /* Kernel support for module BTFs */
+ FEAT_MODULE_BTF,
+ /* BTF_KIND_FLOAT support */
+ FEAT_BTF_FLOAT,
+ /* BPF perf link support */
+ FEAT_PERF_LINK,
+ /* BTF_KIND_DECL_TAG support */
+ FEAT_BTF_DECL_TAG,
+ /* BTF_KIND_TYPE_TAG support */
+ FEAT_BTF_TYPE_TAG,
+ /* memcg-based accounting for BPF maps and progs */
+ FEAT_MEMCG_ACCOUNT,
+ __FEAT_CNT,
+};
+
+int probe_memcg_account(void);
+bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id);
+int bump_rlimit_memlock(void);
int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz);
int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz);
diff --git a/tools/lib/bpf/libbpf_legacy.h b/tools/lib/bpf/libbpf_legacy.h
index bb03c568af7b..79131f761a27 100644
--- a/tools/lib/bpf/libbpf_legacy.h
+++ b/tools/lib/bpf/libbpf_legacy.h
@@ -45,7 +45,6 @@ enum libbpf_strict_mode {
* (positive) error code.
*/
LIBBPF_STRICT_DIRECT_ERRS = 0x02,
-
/*
* Enforce strict BPF program section (SEC()) names.
* E.g., while prefiously SEC("xdp_whatever") or SEC("perf_event_blah") were
@@ -63,6 +62,17 @@ enum libbpf_strict_mode {
* Clients can maintain it on their own if it is valuable for them.
*/
LIBBPF_STRICT_NO_OBJECT_LIST = 0x08,
+ /*
+ * Automatically bump RLIMIT_MEMLOCK using setrlimit() before the
+ * first BPF program or map creation operation. This is done only if
+ * kernel is too old to support memcg-based memory accounting for BPF
+ * subsystem. By default, RLIMIT_MEMLOCK limit is set to RLIM_INFINITY,
+ * but it can be overriden with libbpf_set_memlock_rlim_max() API.
+ * Note that libbpf_set_memlock_rlim_max() needs to be called before
+ * the very first bpf_prog_load(), bpf_map_create() or bpf_object__load()
+ * operation.
+ */
+ LIBBPF_STRICT_AUTO_RLIMIT_MEMLOCK = 0x10,
__LIBBPF_STRICT_LAST,
};
diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c
index 4bdec69523a7..97b06cede56f 100644
--- a/tools/lib/bpf/libbpf_probes.c
+++ b/tools/lib/bpf/libbpf_probes.c
@@ -48,28 +48,20 @@ static int get_vendor_id(int ifindex)
return strtol(buf, NULL, 0);
}
-static int get_kernel_version(void)
+static int probe_prog_load(enum bpf_prog_type prog_type,
+ const struct bpf_insn *insns, size_t insns_cnt,
+ char *log_buf, size_t log_buf_sz,
+ __u32 ifindex)
{
- int version, subversion, patchlevel;
- struct utsname utsn;
-
- /* Return 0 on failure, and attempt to probe with empty kversion */
- if (uname(&utsn))
- return 0;
-
- if (sscanf(utsn.release, "%d.%d.%d",
- &version, &subversion, &patchlevel) != 3)
- return 0;
-
- return (version << 16) + (subversion << 8) + patchlevel;
-}
-
-static void
-probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
- size_t insns_cnt, char *buf, size_t buf_len, __u32 ifindex)
-{
- LIBBPF_OPTS(bpf_prog_load_opts, opts);
- int fd;
+ LIBBPF_OPTS(bpf_prog_load_opts, opts,
+ .log_buf = log_buf,
+ .log_size = log_buf_sz,
+ .log_level = log_buf ? 1 : 0,
+ .prog_ifindex = ifindex,
+ );
+ int fd, err, exp_err = 0;
+ const char *exp_msg = NULL;
+ char buf[4096];
switch (prog_type) {
case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
@@ -84,6 +76,38 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
case BPF_PROG_TYPE_KPROBE:
opts.kern_version = get_kernel_version();
break;
+ case BPF_PROG_TYPE_LIRC_MODE2:
+ opts.expected_attach_type = BPF_LIRC_MODE2;
+ break;
+ case BPF_PROG_TYPE_TRACING:
+ case BPF_PROG_TYPE_LSM:
+ opts.log_buf = buf;
+ opts.log_size = sizeof(buf);
+ opts.log_level = 1;
+ if (prog_type == BPF_PROG_TYPE_TRACING)
+ opts.expected_attach_type = BPF_TRACE_FENTRY;
+ else
+ opts.expected_attach_type = BPF_MODIFY_RETURN;
+ opts.attach_btf_id = 1;
+
+ exp_err = -EINVAL;
+ exp_msg = "attach_btf_id 1 is not a function";
+ break;
+ case BPF_PROG_TYPE_EXT:
+ opts.log_buf = buf;
+ opts.log_size = sizeof(buf);
+ opts.log_level = 1;
+ opts.attach_btf_id = 1;
+
+ exp_err = -EINVAL;
+ exp_msg = "Cannot replace kernel functions";
+ break;
+ case BPF_PROG_TYPE_SYSCALL:
+ opts.prog_flags = BPF_F_SLEEPABLE;
+ break;
+ case BPF_PROG_TYPE_STRUCT_OPS:
+ exp_err = -524; /* -ENOTSUPP */
+ break;
case BPF_PROG_TYPE_UNSPEC:
case BPF_PROG_TYPE_SOCKET_FILTER:
case BPF_PROG_TYPE_SCHED_CLS:
@@ -103,25 +127,42 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
case BPF_PROG_TYPE_RAW_TRACEPOINT:
case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
case BPF_PROG_TYPE_LWT_SEG6LOCAL:
- case BPF_PROG_TYPE_LIRC_MODE2:
case BPF_PROG_TYPE_SK_REUSEPORT:
case BPF_PROG_TYPE_FLOW_DISSECTOR:
case BPF_PROG_TYPE_CGROUP_SYSCTL:
- case BPF_PROG_TYPE_TRACING:
- case BPF_PROG_TYPE_STRUCT_OPS:
- case BPF_PROG_TYPE_EXT:
- case BPF_PROG_TYPE_LSM:
- default:
break;
+ default:
+ return -EOPNOTSUPP;
}
- opts.prog_ifindex = ifindex;
- opts.log_buf = buf;
- opts.log_size = buf_len;
-
- fd = bpf_prog_load(prog_type, NULL, "GPL", insns, insns_cnt, NULL);
+ fd = bpf_prog_load(prog_type, NULL, "GPL", insns, insns_cnt, &opts);
+ err = -errno;
if (fd >= 0)
close(fd);
+ if (exp_err) {
+ if (fd >= 0 || err != exp_err)
+ return 0;
+ if (exp_msg && !strstr(buf, exp_msg))
+ return 0;
+ return 1;
+ }
+ return fd >= 0 ? 1 : 0;
+}
+
+int libbpf_probe_bpf_prog_type(enum bpf_prog_type prog_type, const void *opts)
+{
+ struct bpf_insn insns[] = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN()
+ };
+ const size_t insn_cnt = ARRAY_SIZE(insns);
+ int ret;
+
+ if (opts)
+ return libbpf_err(-EINVAL);
+
+ ret = probe_prog_load(prog_type, insns, insn_cnt, NULL, 0, 0);
+ return libbpf_err(ret);
}
bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex)
@@ -131,12 +172,16 @@ bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex)
BPF_EXIT_INSN()
};
+ /* prefer libbpf_probe_bpf_prog_type() unless offload is requested */
+ if (ifindex == 0)
+ return libbpf_probe_bpf_prog_type(prog_type, NULL) == 1;
+
if (ifindex && prog_type == BPF_PROG_TYPE_SCHED_CLS)
/* nfp returns -EINVAL on exit(0) with TC offload */
insns[0].imm = 2;
errno = 0;
- probe_load(prog_type, insns, ARRAY_SIZE(insns), NULL, 0, ifindex);
+ probe_prog_load(prog_type, insns, ARRAY_SIZE(insns), NULL, 0, ifindex);
return errno != EINVAL && errno != EOPNOTSUPP;
}
@@ -197,16 +242,18 @@ static int load_local_storage_btf(void)
strs, sizeof(strs));
}
-bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
+static int probe_map_create(enum bpf_map_type map_type, __u32 ifindex)
{
- int key_size, value_size, max_entries, map_flags;
+ LIBBPF_OPTS(bpf_map_create_opts, opts);
+ int key_size, value_size, max_entries;
__u32 btf_key_type_id = 0, btf_value_type_id = 0;
- int fd = -1, btf_fd = -1, fd_inner;
+ int fd = -1, btf_fd = -1, fd_inner = -1, exp_err = 0, err;
+
+ opts.map_ifindex = ifindex;
key_size = sizeof(__u32);
value_size = sizeof(__u32);
max_entries = 1;
- map_flags = 0;
switch (map_type) {
case BPF_MAP_TYPE_STACK_TRACE:
@@ -215,7 +262,7 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
case BPF_MAP_TYPE_LPM_TRIE:
key_size = sizeof(__u64);
value_size = sizeof(__u64);
- map_flags = BPF_F_NO_PREALLOC;
+ opts.map_flags = BPF_F_NO_PREALLOC;
break;
case BPF_MAP_TYPE_CGROUP_STORAGE:
case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE:
@@ -234,17 +281,25 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
btf_value_type_id = 3;
value_size = 8;
max_entries = 0;
- map_flags = BPF_F_NO_PREALLOC;
+ opts.map_flags = BPF_F_NO_PREALLOC;
btf_fd = load_local_storage_btf();
if (btf_fd < 0)
- return false;
+ return btf_fd;
break;
case BPF_MAP_TYPE_RINGBUF:
key_size = 0;
value_size = 0;
max_entries = 4096;
break;
- case BPF_MAP_TYPE_UNSPEC:
+ case BPF_MAP_TYPE_STRUCT_OPS:
+ /* we'll get -ENOTSUPP for invalid BTF type ID for struct_ops */
+ opts.btf_vmlinux_value_type_id = 1;
+ exp_err = -524; /* -ENOTSUPP */
+ break;
+ case BPF_MAP_TYPE_BLOOM_FILTER:
+ key_size = 0;
+ max_entries = 1;
+ break;
case BPF_MAP_TYPE_HASH:
case BPF_MAP_TYPE_ARRAY:
case BPF_MAP_TYPE_PROG_ARRAY:
@@ -263,49 +318,114 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
case BPF_MAP_TYPE_XSKMAP:
case BPF_MAP_TYPE_SOCKHASH:
case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY:
- case BPF_MAP_TYPE_STRUCT_OPS:
- default:
break;
+ case BPF_MAP_TYPE_UNSPEC:
+ default:
+ return -EOPNOTSUPP;
}
if (map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
- LIBBPF_OPTS(bpf_map_create_opts, opts);
-
/* TODO: probe for device, once libbpf has a function to create
* map-in-map for offload
*/
if (ifindex)
- return false;
+ goto cleanup;
fd_inner = bpf_map_create(BPF_MAP_TYPE_HASH, NULL,
sizeof(__u32), sizeof(__u32), 1, NULL);
if (fd_inner < 0)
- return false;
+ goto cleanup;
opts.inner_map_fd = fd_inner;
- fd = bpf_map_create(map_type, NULL, sizeof(__u32), sizeof(__u32), 1, &opts);
- close(fd_inner);
- } else {
- LIBBPF_OPTS(bpf_map_create_opts, opts);
-
- /* Note: No other restriction on map type probes for offload */
- opts.map_flags = map_flags;
- opts.map_ifindex = ifindex;
- if (btf_fd >= 0) {
- opts.btf_fd = btf_fd;
- opts.btf_key_type_id = btf_key_type_id;
- opts.btf_value_type_id = btf_value_type_id;
- }
+ }
- fd = bpf_map_create(map_type, NULL, key_size, value_size, max_entries, &opts);
+ if (btf_fd >= 0) {
+ opts.btf_fd = btf_fd;
+ opts.btf_key_type_id = btf_key_type_id;
+ opts.btf_value_type_id = btf_value_type_id;
}
+
+ fd = bpf_map_create(map_type, NULL, key_size, value_size, max_entries, &opts);
+ err = -errno;
+
+cleanup:
if (fd >= 0)
close(fd);
+ if (fd_inner >= 0)
+ close(fd_inner);
if (btf_fd >= 0)
close(btf_fd);
- return fd >= 0;
+ if (exp_err)
+ return fd < 0 && err == exp_err ? 1 : 0;
+ else
+ return fd >= 0 ? 1 : 0;
+}
+
+int libbpf_probe_bpf_map_type(enum bpf_map_type map_type, const void *opts)
+{
+ int ret;
+
+ if (opts)
+ return libbpf_err(-EINVAL);
+
+ ret = probe_map_create(map_type, 0);
+ return libbpf_err(ret);
+}
+
+bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
+{
+ return probe_map_create(map_type, ifindex) == 1;
+}
+
+int libbpf_probe_bpf_helper(enum bpf_prog_type prog_type, enum bpf_func_id helper_id,
+ const void *opts)
+{
+ struct bpf_insn insns[] = {
+ BPF_EMIT_CALL((__u32)helper_id),
+ BPF_EXIT_INSN(),
+ };
+ const size_t insn_cnt = ARRAY_SIZE(insns);
+ char buf[4096];
+ int ret;
+
+ if (opts)
+ return libbpf_err(-EINVAL);
+
+ /* we can't successfully load all prog types to check for BPF helper
+ * support, so bail out with -EOPNOTSUPP error
+ */
+ switch (prog_type) {
+ case BPF_PROG_TYPE_TRACING:
+ case BPF_PROG_TYPE_EXT:
+ case BPF_PROG_TYPE_LSM:
+ case BPF_PROG_TYPE_STRUCT_OPS:
+ return -EOPNOTSUPP;
+ default:
+ break;
+ }
+
+ buf[0] = '\0';
+ ret = probe_prog_load(prog_type, insns, insn_cnt, buf, sizeof(buf), 0);
+ if (ret < 0)
+ return libbpf_err(ret);
+
+ /* If BPF verifier doesn't recognize BPF helper ID (enum bpf_func_id)
+ * at all, it will emit something like "invalid func unknown#181".
+ * If BPF verifier recognizes BPF helper but it's not supported for
+ * given BPF program type, it will emit "unknown func bpf_sys_bpf#166".
+ * In both cases, provided combination of BPF program type and BPF
+ * helper is not supported by the kernel.
+ * In all other cases, probe_prog_load() above will either succeed (e.g.,
+ * because BPF helper happens to accept no input arguments or it
+ * accepts one input argument and initial PTR_TO_CTX is fine for
+ * that), or we'll get some more specific BPF verifier error about
+ * some unsatisfied conditions.
+ */
+ if (ret == 0 && (strstr(buf, "invalid func ") || strstr(buf, "unknown func ")))
+ return 0;
+ return 1; /* assume supported */
}
bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type,
@@ -318,8 +438,7 @@ bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type,
char buf[4096] = {};
bool res;
- probe_load(prog_type, insns, ARRAY_SIZE(insns), buf, sizeof(buf),
- ifindex);
+ probe_prog_load(prog_type, insns, ARRAY_SIZE(insns), buf, sizeof(buf), ifindex);
res = !grep(buf, "invalid func ") && !grep(buf, "unknown func ");
if (ifindex) {
@@ -351,8 +470,8 @@ bool bpf_probe_large_insn_limit(__u32 ifindex)
insns[BPF_MAXINSNS] = BPF_EXIT_INSN();
errno = 0;
- probe_load(BPF_PROG_TYPE_SCHED_CLS, insns, ARRAY_SIZE(insns), NULL, 0,
- ifindex);
+ probe_prog_load(BPF_PROG_TYPE_SCHED_CLS, insns, ARRAY_SIZE(insns), NULL, 0,
+ ifindex);
return errno != E2BIG && errno != EINVAL;
}
diff --git a/tools/lib/bpf/relo_core.c b/tools/lib/bpf/relo_core.c
index 32464f0ab4b1..910865e29edc 100644
--- a/tools/lib/bpf/relo_core.c
+++ b/tools/lib/bpf/relo_core.c
@@ -709,10 +709,14 @@ static int bpf_core_calc_field_relo(const char *prog_name,
static int bpf_core_calc_type_relo(const struct bpf_core_relo *relo,
const struct bpf_core_spec *spec,
- __u32 *val)
+ __u32 *val, bool *validate)
{
__s64 sz;
+ /* by default, always check expected value in bpf_insn */
+ if (validate)
+ *validate = true;
+
/* type-based relos return zero when target type is not found */
if (!spec) {
*val = 0;
@@ -722,6 +726,11 @@ static int bpf_core_calc_type_relo(const struct bpf_core_relo *relo,
switch (relo->kind) {
case BPF_CORE_TYPE_ID_TARGET:
*val = spec->root_type_id;
+ /* type ID, embedded in bpf_insn, might change during linking,
+ * so enforcing it is pointless
+ */
+ if (validate)
+ *validate = false;
break;
case BPF_CORE_TYPE_EXISTS:
*val = 1;
@@ -861,8 +870,8 @@ static int bpf_core_calc_relo(const char *prog_name,
res->fail_memsz_adjust = true;
}
} else if (core_relo_is_type_based(relo->kind)) {
- err = bpf_core_calc_type_relo(relo, local_spec, &res->orig_val);
- err = err ?: bpf_core_calc_type_relo(relo, targ_spec, &res->new_val);
+ err = bpf_core_calc_type_relo(relo, local_spec, &res->orig_val, &res->validate);
+ err = err ?: bpf_core_calc_type_relo(relo, targ_spec, &res->new_val, NULL);
} else if (core_relo_is_enumval_based(relo->kind)) {
err = bpf_core_calc_enumval_relo(relo, local_spec, &res->orig_val);
err = err ?: bpf_core_calc_enumval_relo(relo, targ_spec, &res->new_val);
@@ -1213,7 +1222,9 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
/* TYPE_ID_LOCAL relo is special and doesn't need candidate search */
if (relo->kind == BPF_CORE_TYPE_ID_LOCAL) {
- targ_res.validate = true;
+ /* bpf_insn's imm value could get out of sync during linking */
+ memset(&targ_res, 0, sizeof(targ_res));
+ targ_res.validate = false;
targ_res.poison = false;
targ_res.orig_val = local_spec->root_type_id;
targ_res.new_val = local_spec->root_type_id;
@@ -1227,7 +1238,6 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
return -EOPNOTSUPP;
}
-
for (i = 0, j = 0; i < cands->len; i++) {
err = bpf_core_spec_match(local_spec, cands->cands[i].btf,
cands->cands[i].id, cand_spec);
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index e8d94c6dd3bc..edafe56664f3 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -548,8 +548,7 @@ static int xsk_get_max_queues(struct xsk_socket *xsk)
return -errno;
ifr.ifr_data = (void *)&channels;
- memcpy(ifr.ifr_name, ctx->ifname, IFNAMSIZ - 1);
- ifr.ifr_name[IFNAMSIZ - 1] = '\0';
+ libbpf_strlcpy(ifr.ifr_name, ctx->ifname, IFNAMSIZ);
err = ioctl(fd, SIOCETHTOOL, &ifr);
if (err && errno != EOPNOTSUPP) {
ret = -errno;
@@ -768,8 +767,7 @@ static int xsk_create_xsk_struct(int ifindex, struct xsk_socket *xsk)
}
ctx->ifindex = ifindex;
- memcpy(ctx->ifname, ifname, IFNAMSIZ -1);
- ctx->ifname[IFNAMSIZ - 1] = 0;
+ libbpf_strlcpy(ctx->ifname, ifname, IFNAMSIZ);
xsk->ctx = ctx;
xsk->ctx->has_bpf_link = xsk_probe_bpf_link();
@@ -951,8 +949,7 @@ static struct xsk_ctx *xsk_create_ctx(struct xsk_socket *xsk,
ctx->refcount = 1;
ctx->umem = umem;
ctx->queue_id = queue_id;
- memcpy(ctx->ifname, ifname, IFNAMSIZ - 1);
- ctx->ifname[IFNAMSIZ - 1] = '\0';
+ libbpf_strlcpy(ctx->ifname, ifname, IFNAMSIZ);
ctx->fill = fill;
ctx->comp = comp;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 0b52e08e558e..97121fb45842 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -3257,10 +3257,21 @@ static void trace__set_bpf_map_syscalls(struct trace *trace)
static struct bpf_program *trace__find_bpf_program_by_title(struct trace *trace, const char *name)
{
+ struct bpf_program *pos, *prog = NULL;
+ const char *sec_name;
+
if (trace->bpf_obj == NULL)
return NULL;
- return bpf_object__find_program_by_title(trace->bpf_obj, name);
+ bpf_object__for_each_program(pos, trace->bpf_obj) {
+ sec_name = bpf_program__section_name(pos);
+ if (sec_name && !strcmp(sec_name, name)) {
+ prog = pos;
+ break;
+ }
+ }
+
+ return prog;
}
static struct bpf_program *trace__find_syscall_bpf_prog(struct trace *trace, struct syscall *sc,
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index 071312f5eb92..b0be5f40a3f1 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -87,7 +87,18 @@ LLVM_STRIP ?= llvm-strip
ifeq ($(CC_NO_CLANG), 1)
EXTRA_WARNINGS += -Wstrict-aliasing=3
-endif
+
+else ifneq ($(CROSS_COMPILE),)
+CLANG_CROSS_FLAGS := --target=$(notdir $(CROSS_COMPILE:%-=%))
+GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)gcc))
+ifneq ($(GCC_TOOLCHAIN_DIR),)
+CLANG_CROSS_FLAGS += --prefix=$(GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE))
+CLANG_CROSS_FLAGS += --sysroot=$(shell $(CROSS_COMPILE)gcc -print-sysroot)
+CLANG_CROSS_FLAGS += --gcc-toolchain=$(realpath $(GCC_TOOLCHAIN_DIR)/..)
+endif # GCC_TOOLCHAIN_DIR
+CFLAGS += $(CLANG_CROSS_FLAGS)
+AFLAGS += $(CLANG_CROSS_FLAGS)
+endif # CROSS_COMPILE
# Hack to avoid type-punned warnings on old systems such as RHEL5:
# We should be changing CFLAGS and checking gcc version, but this
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index a795bca4c8ec..42ffc24e9e71 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -170,7 +170,7 @@ $(OUTPUT)/%:%.c
$(OUTPUT)/urandom_read: urandom_read.c
$(call msg,BINARY,,$@)
- $(Q)$(CC) $(LDFLAGS) $< $(LDLIBS) -Wl,--build-id=sha1 -o $@
+ $(Q)$(CC) $(CFLAGS) $(LDFLAGS) $< $(LDLIBS) -Wl,--build-id=sha1 -o $@
$(OUTPUT)/bpf_testmod.ko: $(VMLINUX_BTF) $(wildcard bpf_testmod/Makefile bpf_testmod/*.[ch])
$(call msg,MOD,,$@)
@@ -217,7 +217,7 @@ BPFTOOL ?= $(DEFAULT_BPFTOOL)
$(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \
$(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/bpftool
$(Q)$(MAKE) $(submake_extras) -C $(BPFTOOLDIR) \
- CC=$(HOSTCC) LD=$(HOSTLD) \
+ ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) \
EXTRA_CFLAGS='-g -O0' \
OUTPUT=$(HOST_BUILD_DIR)/bpftool/ \
LIBBPF_OUTPUT=$(HOST_BUILD_DIR)/libbpf/ \
@@ -248,7 +248,7 @@ $(HOST_BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \
$(APIDIR)/linux/bpf.h \
| $(HOST_BUILD_DIR)/libbpf
$(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) \
- EXTRA_CFLAGS='-g -O0' \
+ EXTRA_CFLAGS='-g -O0' ARCH= CROSS_COMPILE= \
OUTPUT=$(HOST_BUILD_DIR)/libbpf/ CC=$(HOSTCC) LD=$(HOSTLD) \
DESTDIR=$(HOST_SCRATCH_DIR)/ prefix= all install_headers
endif
@@ -537,6 +537,7 @@ $(OUTPUT)/bench_ringbufs.o: $(OUTPUT)/ringbuf_bench.skel.h \
$(OUTPUT)/perfbuf_bench.skel.h
$(OUTPUT)/bench_bloom_filter_map.o: $(OUTPUT)/bloom_filter_bench.skel.h
$(OUTPUT)/bench_bpf_loop.o: $(OUTPUT)/bpf_loop_bench.skel.h
+$(OUTPUT)/bench_strncmp.o: $(OUTPUT)/strncmp_bench.skel.h
$(OUTPUT)/bench.o: bench.h testing_helpers.h $(BPFOBJ)
$(OUTPUT)/bench: LDLIBS += -lm
$(OUTPUT)/bench: $(OUTPUT)/bench.o \
@@ -547,9 +548,10 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o \
$(OUTPUT)/bench_trigger.o \
$(OUTPUT)/bench_ringbufs.o \
$(OUTPUT)/bench_bloom_filter_map.o \
- $(OUTPUT)/bench_bpf_loop.o
+ $(OUTPUT)/bench_bpf_loop.o \
+ $(OUTPUT)/bench_strncmp.o
$(call msg,BINARY,,$@)
- $(Q)$(CC) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@
+ $(Q)$(CC) $(CFLAGS) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@
EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) $(HOST_SCRATCH_DIR) \
prog_tests/tests.h map_tests/tests.h verifier/tests.h \
diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c
index 3d6082b97a56..f973320e6dbf 100644
--- a/tools/testing/selftests/bpf/bench.c
+++ b/tools/testing/selftests/bpf/bench.c
@@ -29,26 +29,10 @@ static int libbpf_print_fn(enum libbpf_print_level level,
return vfprintf(stderr, format, args);
}
-static int bump_memlock_rlimit(void)
+void setup_libbpf(void)
{
- struct rlimit rlim_new = {
- .rlim_cur = RLIM_INFINITY,
- .rlim_max = RLIM_INFINITY,
- };
-
- return setrlimit(RLIMIT_MEMLOCK, &rlim_new);
-}
-
-void setup_libbpf()
-{
- int err;
-
libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
libbpf_set_print(libbpf_print_fn);
-
- err = bump_memlock_rlimit();
- if (err)
- fprintf(stderr, "failed to increase RLIMIT_MEMLOCK: %d", err);
}
void false_hits_report_progress(int iter, struct bench_res *res, long delta_ns)
@@ -205,11 +189,13 @@ static const struct argp_option opts[] = {
extern struct argp bench_ringbufs_argp;
extern struct argp bench_bloom_map_argp;
extern struct argp bench_bpf_loop_argp;
+extern struct argp bench_strncmp_argp;
static const struct argp_child bench_parsers[] = {
{ &bench_ringbufs_argp, 0, "Ring buffers benchmark", 0 },
{ &bench_bloom_map_argp, 0, "Bloom filter map benchmark", 0 },
{ &bench_bpf_loop_argp, 0, "bpf_loop helper benchmark", 0 },
+ { &bench_strncmp_argp, 0, "bpf_strncmp helper benchmark", 0 },
{},
};
@@ -409,6 +395,8 @@ extern const struct bench bench_bloom_false_positive;
extern const struct bench bench_hashmap_without_bloom;
extern const struct bench bench_hashmap_with_bloom;
extern const struct bench bench_bpf_loop;
+extern const struct bench bench_strncmp_no_helper;
+extern const struct bench bench_strncmp_helper;
static const struct bench *benchs[] = {
&bench_count_global,
@@ -441,6 +429,8 @@ static const struct bench *benchs[] = {
&bench_hashmap_without_bloom,
&bench_hashmap_with_bloom,
&bench_bpf_loop,
+ &bench_strncmp_no_helper,
+ &bench_strncmp_helper,
};
static void setup_benchmark()
diff --git a/tools/testing/selftests/bpf/bench.h b/tools/testing/selftests/bpf/bench.h
index 50785503756b..fb3e213df3dc 100644
--- a/tools/testing/selftests/bpf/bench.h
+++ b/tools/testing/selftests/bpf/bench.h
@@ -38,8 +38,8 @@ struct bench_res {
struct bench {
const char *name;
- void (*validate)();
- void (*setup)();
+ void (*validate)(void);
+ void (*setup)(void);
void *(*producer_thread)(void *ctx);
void *(*consumer_thread)(void *ctx);
void (*measure)(struct bench_res* res);
@@ -54,7 +54,7 @@ struct counter {
extern struct env env;
extern const struct bench *bench;
-void setup_libbpf();
+void setup_libbpf(void);
void hits_drops_report_progress(int iter, struct bench_res *res, long delta_ns);
void hits_drops_report_final(struct bench_res res[], int res_cnt);
void false_hits_report_progress(int iter, struct bench_res *res, long delta_ns);
@@ -62,7 +62,8 @@ void false_hits_report_final(struct bench_res res[], int res_cnt);
void ops_report_progress(int iter, struct bench_res *res, long delta_ns);
void ops_report_final(struct bench_res res[], int res_cnt);
-static inline __u64 get_time_ns() {
+static inline __u64 get_time_ns(void)
+{
struct timespec t;
clock_gettime(CLOCK_MONOTONIC, &t);
diff --git a/tools/testing/selftests/bpf/benchs/bench_count.c b/tools/testing/selftests/bpf/benchs/bench_count.c
index befba7a82643..078972ce208e 100644
--- a/tools/testing/selftests/bpf/benchs/bench_count.c
+++ b/tools/testing/selftests/bpf/benchs/bench_count.c
@@ -36,7 +36,7 @@ static struct count_local_ctx {
struct counter *hits;
} count_local_ctx;
-static void count_local_setup()
+static void count_local_setup(void)
{
struct count_local_ctx *ctx = &count_local_ctx;
diff --git a/tools/testing/selftests/bpf/benchs/bench_rename.c b/tools/testing/selftests/bpf/benchs/bench_rename.c
index c7ec114eca56..3c203b6d6a6e 100644
--- a/tools/testing/selftests/bpf/benchs/bench_rename.c
+++ b/tools/testing/selftests/bpf/benchs/bench_rename.c
@@ -11,7 +11,7 @@ static struct ctx {
int fd;
} ctx;
-static void validate()
+static void validate(void)
{
if (env.producer_cnt != 1) {
fprintf(stderr, "benchmark doesn't support multi-producer!\n");
@@ -43,7 +43,7 @@ static void measure(struct bench_res *res)
res->hits = atomic_swap(&ctx.hits.value, 0);
}
-static void setup_ctx()
+static void setup_ctx(void)
{
setup_libbpf();
@@ -71,36 +71,36 @@ static void attach_bpf(struct bpf_program *prog)
}
}
-static void setup_base()
+static void setup_base(void)
{
setup_ctx();
}
-static void setup_kprobe()
+static void setup_kprobe(void)
{
setup_ctx();
attach_bpf(ctx.skel->progs.prog1);
}
-static void setup_kretprobe()
+static void setup_kretprobe(void)
{
setup_ctx();
attach_bpf(ctx.skel->progs.prog2);
}
-static void setup_rawtp()
+static void setup_rawtp(void)
{
setup_ctx();
attach_bpf(ctx.skel->progs.prog3);
}
-static void setup_fentry()
+static void setup_fentry(void)
{
setup_ctx();
attach_bpf(ctx.skel->progs.prog4);
}
-static void setup_fexit()
+static void setup_fexit(void)
{
setup_ctx();
attach_bpf(ctx.skel->progs.prog5);
diff --git a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
index 52d4a2f91dbd..da8593b3494a 100644
--- a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
+++ b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
@@ -88,12 +88,12 @@ const struct argp bench_ringbufs_argp = {
static struct counter buf_hits;
-static inline void bufs_trigger_batch()
+static inline void bufs_trigger_batch(void)
{
(void)syscall(__NR_getpgid);
}
-static void bufs_validate()
+static void bufs_validate(void)
{
if (env.consumer_cnt != 1) {
fprintf(stderr, "rb-libbpf benchmark doesn't support multi-consumer!\n");
@@ -132,7 +132,7 @@ static void ringbuf_libbpf_measure(struct bench_res *res)
res->drops = atomic_swap(&ctx->skel->bss->dropped, 0);
}
-static struct ringbuf_bench *ringbuf_setup_skeleton()
+static struct ringbuf_bench *ringbuf_setup_skeleton(void)
{
struct ringbuf_bench *skel;
@@ -167,7 +167,7 @@ static int buf_process_sample(void *ctx, void *data, size_t len)
return 0;
}
-static void ringbuf_libbpf_setup()
+static void ringbuf_libbpf_setup(void)
{
struct ringbuf_libbpf_ctx *ctx = &ringbuf_libbpf_ctx;
struct bpf_link *link;
@@ -223,7 +223,7 @@ static void ringbuf_custom_measure(struct bench_res *res)
res->drops = atomic_swap(&ctx->skel->bss->dropped, 0);
}
-static void ringbuf_custom_setup()
+static void ringbuf_custom_setup(void)
{
struct ringbuf_custom_ctx *ctx = &ringbuf_custom_ctx;
const size_t page_size = getpagesize();
@@ -352,7 +352,7 @@ static void perfbuf_measure(struct bench_res *res)
res->drops = atomic_swap(&ctx->skel->bss->dropped, 0);
}
-static struct perfbuf_bench *perfbuf_setup_skeleton()
+static struct perfbuf_bench *perfbuf_setup_skeleton(void)
{
struct perfbuf_bench *skel;
@@ -390,7 +390,7 @@ perfbuf_process_sample_raw(void *input_ctx, int cpu,
return LIBBPF_PERF_EVENT_CONT;
}
-static void perfbuf_libbpf_setup()
+static void perfbuf_libbpf_setup(void)
{
struct perfbuf_libbpf_ctx *ctx = &perfbuf_libbpf_ctx;
struct perf_event_attr attr;
diff --git a/tools/testing/selftests/bpf/benchs/bench_strncmp.c b/tools/testing/selftests/bpf/benchs/bench_strncmp.c
new file mode 100644
index 000000000000..494b591c0289
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/bench_strncmp.c
@@ -0,0 +1,161 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021. Huawei Technologies Co., Ltd */
+#include <argp.h>
+#include "bench.h"
+#include "strncmp_bench.skel.h"
+
+static struct strncmp_ctx {
+ struct strncmp_bench *skel;
+} ctx;
+
+static struct strncmp_args {
+ u32 cmp_str_len;
+} args = {
+ .cmp_str_len = 32,
+};
+
+enum {
+ ARG_CMP_STR_LEN = 5000,
+};
+
+static const struct argp_option opts[] = {
+ { "cmp-str-len", ARG_CMP_STR_LEN, "CMP_STR_LEN", 0,
+ "Set the length of compared string" },
+ {},
+};
+
+static error_t strncmp_parse_arg(int key, char *arg, struct argp_state *state)
+{
+ switch (key) {
+ case ARG_CMP_STR_LEN:
+ args.cmp_str_len = strtoul(arg, NULL, 10);
+ if (!args.cmp_str_len ||
+ args.cmp_str_len >= sizeof(ctx.skel->bss->str)) {
+ fprintf(stderr, "Invalid cmp str len (limit %zu)\n",
+ sizeof(ctx.skel->bss->str));
+ argp_usage(state);
+ }
+ break;
+ default:
+ return ARGP_ERR_UNKNOWN;
+ }
+
+ return 0;
+}
+
+const struct argp bench_strncmp_argp = {
+ .options = opts,
+ .parser = strncmp_parse_arg,
+};
+
+static void strncmp_validate(void)
+{
+ if (env.consumer_cnt != 1) {
+ fprintf(stderr, "strncmp benchmark doesn't support multi-consumer!\n");
+ exit(1);
+ }
+}
+
+static void strncmp_setup(void)
+{
+ int err;
+ char *target;
+ size_t i, sz;
+
+ sz = sizeof(ctx.skel->rodata->target);
+ if (!sz || sz < sizeof(ctx.skel->bss->str)) {
+ fprintf(stderr, "invalid string size (target %zu, src %zu)\n",
+ sz, sizeof(ctx.skel->bss->str));
+ exit(1);
+ }
+
+ setup_libbpf();
+
+ ctx.skel = strncmp_bench__open();
+ if (!ctx.skel) {
+ fprintf(stderr, "failed to open skeleton\n");
+ exit(1);
+ }
+
+ srandom(time(NULL));
+ target = ctx.skel->rodata->target;
+ for (i = 0; i < sz - 1; i++)
+ target[i] = '1' + random() % 9;
+ target[sz - 1] = '\0';
+
+ ctx.skel->rodata->cmp_str_len = args.cmp_str_len;
+
+ memcpy(ctx.skel->bss->str, target, args.cmp_str_len);
+ ctx.skel->bss->str[args.cmp_str_len] = '\0';
+ /* Make bss->str < rodata->target */
+ ctx.skel->bss->str[args.cmp_str_len - 1] -= 1;
+
+ err = strncmp_bench__load(ctx.skel);
+ if (err) {
+ fprintf(stderr, "failed to load skeleton\n");
+ strncmp_bench__destroy(ctx.skel);
+ exit(1);
+ }
+}
+
+static void strncmp_attach_prog(struct bpf_program *prog)
+{
+ struct bpf_link *link;
+
+ link = bpf_program__attach(prog);
+ if (!link) {
+ fprintf(stderr, "failed to attach program!\n");
+ exit(1);
+ }
+}
+
+static void strncmp_no_helper_setup(void)
+{
+ strncmp_setup();
+ strncmp_attach_prog(ctx.skel->progs.strncmp_no_helper);
+}
+
+static void strncmp_helper_setup(void)
+{
+ strncmp_setup();
+ strncmp_attach_prog(ctx.skel->progs.strncmp_helper);
+}
+
+static void *strncmp_producer(void *ctx)
+{
+ while (true)
+ (void)syscall(__NR_getpgid);
+ return NULL;
+}
+
+static void *strncmp_consumer(void *ctx)
+{
+ return NULL;
+}
+
+static void strncmp_measure(struct bench_res *res)
+{
+ res->hits = atomic_swap(&ctx.skel->bss->hits, 0);
+}
+
+const struct bench bench_strncmp_no_helper = {
+ .name = "strncmp-no-helper",
+ .validate = strncmp_validate,
+ .setup = strncmp_no_helper_setup,
+ .producer_thread = strncmp_producer,
+ .consumer_thread = strncmp_consumer,
+ .measure = strncmp_measure,
+ .report_progress = hits_drops_report_progress,
+ .report_final = hits_drops_report_final,
+};
+
+const struct bench bench_strncmp_helper = {
+ .name = "strncmp-helper",
+ .validate = strncmp_validate,
+ .setup = strncmp_helper_setup,
+ .producer_thread = strncmp_producer,
+ .consumer_thread = strncmp_consumer,
+ .measure = strncmp_measure,
+ .report_progress = hits_drops_report_progress,
+ .report_final = hits_drops_report_final,
+};
diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c
index 049a5ad56f65..7f957c55a3ca 100644
--- a/tools/testing/selftests/bpf/benchs/bench_trigger.c
+++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c
@@ -11,7 +11,7 @@ static struct trigger_ctx {
static struct counter base_hits;
-static void trigger_validate()
+static void trigger_validate(void)
{
if (env.consumer_cnt != 1) {
fprintf(stderr, "benchmark doesn't support multi-consumer!\n");
@@ -45,7 +45,7 @@ static void trigger_measure(struct bench_res *res)
res->hits = atomic_swap(&ctx.skel->bss->hits, 0);
}
-static void setup_ctx()
+static void setup_ctx(void)
{
setup_libbpf();
@@ -67,37 +67,37 @@ static void attach_bpf(struct bpf_program *prog)
}
}
-static void trigger_tp_setup()
+static void trigger_tp_setup(void)
{
setup_ctx();
attach_bpf(ctx.skel->progs.bench_trigger_tp);
}
-static void trigger_rawtp_setup()
+static void trigger_rawtp_setup(void)
{
setup_ctx();
attach_bpf(ctx.skel->progs.bench_trigger_raw_tp);
}
-static void trigger_kprobe_setup()
+static void trigger_kprobe_setup(void)
{
setup_ctx();
attach_bpf(ctx.skel->progs.bench_trigger_kprobe);
}
-static void trigger_fentry_setup()
+static void trigger_fentry_setup(void)
{
setup_ctx();
attach_bpf(ctx.skel->progs.bench_trigger_fentry);
}
-static void trigger_fentry_sleep_setup()
+static void trigger_fentry_sleep_setup(void)
{
setup_ctx();
attach_bpf(ctx.skel->progs.bench_trigger_fentry_sleep);
}
-static void trigger_fmodret_setup()
+static void trigger_fmodret_setup(void)
{
setup_ctx();
attach_bpf(ctx.skel->progs.bench_trigger_fmodret);
@@ -183,22 +183,22 @@ static void usetup(bool use_retprobe, bool use_nop)
ctx.skel->links.bench_trigger_uprobe = link;
}
-static void uprobe_setup_with_nop()
+static void uprobe_setup_with_nop(void)
{
usetup(false, true);
}
-static void uretprobe_setup_with_nop()
+static void uretprobe_setup_with_nop(void)
{
usetup(true, true);
}
-static void uprobe_setup_without_nop()
+static void uprobe_setup_without_nop(void)
{
usetup(false, false);
}
-static void uretprobe_setup_without_nop()
+static void uretprobe_setup_without_nop(void)
{
usetup(true, false);
}
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_strncmp.sh b/tools/testing/selftests/bpf/benchs/run_bench_strncmp.sh
new file mode 100755
index 000000000000..142697284b45
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/run_bench_strncmp.sh
@@ -0,0 +1,12 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source ./benchs/run_common.sh
+
+set -eufo pipefail
+
+for s in 1 8 64 512 2048 4095; do
+ for b in no-helper helper; do
+ summarize ${b}-${s} "$($RUN_BENCH --cmp-str-len=$s strncmp-${b})"
+ done
+done
diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 5192305159ec..f6287132fa89 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -38,7 +38,9 @@ CONFIG_IPV6_SIT=m
CONFIG_BPF_JIT=y
CONFIG_BPF_LSM=y
CONFIG_SECURITY=y
+CONFIG_RC_CORE=y
CONFIG_LIRC=y
+CONFIG_BPF_LIRC_MODE2=y
CONFIG_IMA=y
CONFIG_SECURITYFS=y
CONFIG_IMA_WRITE_POLICY=y
diff --git a/tools/testing/selftests/bpf/prog_tests/align.c b/tools/testing/selftests/bpf/prog_tests/align.c
index 837f67c6bfda..0ee29e11eaee 100644
--- a/tools/testing/selftests/bpf/prog_tests/align.c
+++ b/tools/testing/selftests/bpf/prog_tests/align.c
@@ -39,13 +39,13 @@ static struct bpf_align_test tests[] = {
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.matches = {
- {1, "R1=ctx(id=0,off=0,imm=0)"},
- {1, "R10=fp0"},
- {1, "R3_w=inv2"},
- {2, "R3_w=inv4"},
- {3, "R3_w=inv8"},
- {4, "R3_w=inv16"},
- {5, "R3_w=inv32"},
+ {0, "R1=ctx(id=0,off=0,imm=0)"},
+ {0, "R10=fp0"},
+ {0, "R3_w=inv2"},
+ {1, "R3_w=inv4"},
+ {2, "R3_w=inv8"},
+ {3, "R3_w=inv16"},
+ {4, "R3_w=inv32"},
},
},
{
@@ -67,19 +67,19 @@ static struct bpf_align_test tests[] = {
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.matches = {
- {1, "R1=ctx(id=0,off=0,imm=0)"},
- {1, "R10=fp0"},
- {1, "R3_w=inv1"},
- {2, "R3_w=inv2"},
- {3, "R3_w=inv4"},
- {4, "R3_w=inv8"},
- {5, "R3_w=inv16"},
- {6, "R3_w=inv1"},
- {7, "R4_w=inv32"},
- {8, "R4_w=inv16"},
- {9, "R4_w=inv8"},
- {10, "R4_w=inv4"},
- {11, "R4_w=inv2"},
+ {0, "R1=ctx(id=0,off=0,imm=0)"},
+ {0, "R10=fp0"},
+ {0, "R3_w=inv1"},
+ {1, "R3_w=inv2"},
+ {2, "R3_w=inv4"},
+ {3, "R3_w=inv8"},
+ {4, "R3_w=inv16"},
+ {5, "R3_w=inv1"},
+ {6, "R4_w=inv32"},
+ {7, "R4_w=inv16"},
+ {8, "R4_w=inv8"},
+ {9, "R4_w=inv4"},
+ {10, "R4_w=inv2"},
},
},
{
@@ -96,14 +96,14 @@ static struct bpf_align_test tests[] = {
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.matches = {
- {1, "R1=ctx(id=0,off=0,imm=0)"},
- {1, "R10=fp0"},
- {1, "R3_w=inv4"},
- {2, "R3_w=inv8"},
- {3, "R3_w=inv10"},
- {4, "R4_w=inv8"},
- {5, "R4_w=inv12"},
- {6, "R4_w=inv14"},
+ {0, "R1=ctx(id=0,off=0,imm=0)"},
+ {0, "R10=fp0"},
+ {0, "R3_w=inv4"},
+ {1, "R3_w=inv8"},
+ {2, "R3_w=inv10"},
+ {3, "R4_w=inv8"},
+ {4, "R4_w=inv12"},
+ {5, "R4_w=inv14"},
},
},
{
@@ -118,12 +118,12 @@ static struct bpf_align_test tests[] = {
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.matches = {
- {1, "R1=ctx(id=0,off=0,imm=0)"},
- {1, "R10=fp0"},
+ {0, "R1=ctx(id=0,off=0,imm=0)"},
+ {0, "R10=fp0"},
+ {0, "R3_w=inv7"},
{1, "R3_w=inv7"},
- {2, "R3_w=inv7"},
- {3, "R3_w=inv14"},
- {4, "R3_w=inv56"},
+ {2, "R3_w=inv14"},
+ {3, "R3_w=inv56"},
},
},
@@ -161,19 +161,19 @@ static struct bpf_align_test tests[] = {
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.matches = {
- {7, "R0_w=pkt(id=0,off=8,r=8,imm=0)"},
- {7, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
- {8, "R3_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"},
- {9, "R3_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
- {10, "R3_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"},
- {11, "R3_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"},
- {18, "R3=pkt_end(id=0,off=0,imm=0)"},
- {18, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
- {19, "R4_w=inv(id=0,umax_value=8160,var_off=(0x0; 0x1fe0))"},
- {20, "R4_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"},
- {21, "R4_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"},
- {22, "R4_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
- {23, "R4_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"},
+ {6, "R0_w=pkt(id=0,off=8,r=8,imm=0)"},
+ {6, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+ {7, "R3_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"},
+ {8, "R3_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+ {9, "R3_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"},
+ {10, "R3_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"},
+ {12, "R3_w=pkt_end(id=0,off=0,imm=0)"},
+ {17, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+ {18, "R4_w=inv(id=0,umax_value=8160,var_off=(0x0; 0x1fe0))"},
+ {19, "R4_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"},
+ {20, "R4_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"},
+ {21, "R4_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+ {22, "R4_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"},
},
},
{
@@ -194,16 +194,16 @@ static struct bpf_align_test tests[] = {
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.matches = {
- {7, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
- {8, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"},
- {9, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
- {10, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"},
- {11, "R4_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"},
- {12, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"},
- {13, "R4_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
- {14, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"},
- {15, "R4_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"},
- {16, "R4_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"},
+ {6, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+ {7, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"},
+ {8, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+ {9, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"},
+ {10, "R4_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"},
+ {11, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"},
+ {12, "R4_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+ {13, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"},
+ {14, "R4_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"},
+ {15, "R4_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"},
},
},
{
@@ -234,14 +234,14 @@ static struct bpf_align_test tests[] = {
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.matches = {
- {4, "R5_w=pkt(id=0,off=0,r=0,imm=0)"},
- {5, "R5_w=pkt(id=0,off=14,r=0,imm=0)"},
- {6, "R4_w=pkt(id=0,off=14,r=0,imm=0)"},
- {10, "R2=pkt(id=0,off=0,r=18,imm=0)"},
+ {2, "R5_w=pkt(id=0,off=0,r=0,imm=0)"},
+ {4, "R5_w=pkt(id=0,off=14,r=0,imm=0)"},
+ {5, "R4_w=pkt(id=0,off=14,r=0,imm=0)"},
+ {9, "R2=pkt(id=0,off=0,r=18,imm=0)"},
{10, "R5=pkt(id=0,off=14,r=18,imm=0)"},
{10, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+ {13, "R4_w=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"},
{14, "R4_w=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"},
- {15, "R4_w=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"},
},
},
{
@@ -296,8 +296,8 @@ static struct bpf_align_test tests[] = {
/* Calculated offset in R6 has unknown value, but known
* alignment of 4.
*/
- {8, "R2_w=pkt(id=0,off=0,r=8,imm=0)"},
- {8, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+ {6, "R2_w=pkt(id=0,off=0,r=8,imm=0)"},
+ {7, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
/* Offset is added to packet pointer R5, resulting in
* known fixed offset, and variable offset from R6.
*/
@@ -313,11 +313,11 @@ static struct bpf_align_test tests[] = {
/* Variable offset is added to R5 packet pointer,
* resulting in auxiliary alignment of 4.
*/
- {18, "R5_w=pkt(id=2,off=0,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+ {17, "R5_w=pkt(id=2,off=0,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
/* Constant offset is added to R5, resulting in
* reg->off of 14.
*/
- {19, "R5_w=pkt(id=2,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+ {18, "R5_w=pkt(id=2,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
/* At the time the word size load is performed from R5,
* its total fixed offset is NET_IP_ALIGN + reg->off
* (14) which is 16. Then the variable offset is 4-byte
@@ -329,18 +329,18 @@ static struct bpf_align_test tests[] = {
/* Constant offset is added to R5 packet pointer,
* resulting in reg->off value of 14.
*/
- {26, "R5_w=pkt(id=0,off=14,r=8"},
+ {25, "R5_w=pkt(id=0,off=14,r=8"},
/* Variable offset is added to R5, resulting in a
* variable offset of (4n).
*/
- {27, "R5_w=pkt(id=3,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+ {26, "R5_w=pkt(id=3,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
/* Constant is added to R5 again, setting reg->off to 18. */
- {28, "R5_w=pkt(id=3,off=18,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+ {27, "R5_w=pkt(id=3,off=18,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
/* And once more we add a variable; resulting var_off
* is still (4n), fixed offset is not changed.
* Also, we create a new reg->id.
*/
- {29, "R5_w=pkt(id=4,off=18,r=0,umax_value=2040,var_off=(0x0; 0x7fc)"},
+ {28, "R5_w=pkt(id=4,off=18,r=0,umax_value=2040,var_off=(0x0; 0x7fc)"},
/* At the time the word size load is performed from R5,
* its total fixed offset is NET_IP_ALIGN + reg->off (18)
* which is 20. Then the variable offset is (4n), so
@@ -386,13 +386,13 @@ static struct bpf_align_test tests[] = {
/* Calculated offset in R6 has unknown value, but known
* alignment of 4.
*/
- {8, "R2_w=pkt(id=0,off=0,r=8,imm=0)"},
- {8, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+ {6, "R2_w=pkt(id=0,off=0,r=8,imm=0)"},
+ {7, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
/* Adding 14 makes R6 be (4n+2) */
- {9, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
+ {8, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
/* Packet pointer has (4n+2) offset */
{11, "R5_w=pkt(id=1,off=0,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc)"},
- {13, "R4=pkt(id=1,off=4,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc)"},
+ {12, "R4=pkt(id=1,off=4,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc)"},
/* At the time the word size load is performed from R5,
* its total fixed offset is NET_IP_ALIGN + reg->off (0)
* which is 2. Then the variable offset is (4n+2), so
@@ -403,12 +403,12 @@ static struct bpf_align_test tests[] = {
/* Newly read value in R6 was shifted left by 2, so has
* known alignment of 4.
*/
- {18, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+ {17, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
/* Added (4n) to packet pointer's (4n+2) var_off, giving
* another (4n+2).
*/
{19, "R5_w=pkt(id=2,off=0,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"},
- {21, "R4=pkt(id=2,off=4,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"},
+ {20, "R4=pkt(id=2,off=4,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"},
/* At the time the word size load is performed from R5,
* its total fixed offset is NET_IP_ALIGN + reg->off (0)
* which is 2. Then the variable offset is (4n+2), so
@@ -448,18 +448,18 @@ static struct bpf_align_test tests[] = {
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.result = REJECT,
.matches = {
- {4, "R5_w=pkt_end(id=0,off=0,imm=0)"},
+ {3, "R5_w=pkt_end(id=0,off=0,imm=0)"},
/* (ptr - ptr) << 2 == unknown, (4n) */
- {6, "R5_w=inv(id=0,smax_value=9223372036854775804,umax_value=18446744073709551612,var_off=(0x0; 0xfffffffffffffffc)"},
+ {5, "R5_w=inv(id=0,smax_value=9223372036854775804,umax_value=18446744073709551612,var_off=(0x0; 0xfffffffffffffffc)"},
/* (4n) + 14 == (4n+2). We blow our bounds, because
* the add could overflow.
*/
- {7, "R5_w=inv(id=0,smin_value=-9223372036854775806,smax_value=9223372036854775806,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"},
+ {6, "R5_w=inv(id=0,smin_value=-9223372036854775806,smax_value=9223372036854775806,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"},
/* Checked s>=0 */
{9, "R5=inv(id=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"},
/* packet pointer + nonnegative (4n+2) */
{11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"},
- {13, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"},
+ {12, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"},
/* NET_IP_ALIGN + (4n+2) == (4n), alignment is fine.
* We checked the bounds, but it might have been able
* to overflow if the packet pointer started in the
@@ -502,14 +502,14 @@ static struct bpf_align_test tests[] = {
/* Calculated offset in R6 has unknown value, but known
* alignment of 4.
*/
- {7, "R2_w=pkt(id=0,off=0,r=8,imm=0)"},
- {9, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+ {6, "R2_w=pkt(id=0,off=0,r=8,imm=0)"},
+ {8, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
/* Adding 14 makes R6 be (4n+2) */
- {10, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
+ {9, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
/* New unknown value in R7 is (4n) */
- {11, "R7_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+ {10, "R7_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
/* Subtracting it from R6 blows our unsigned bounds */
- {12, "R6=inv(id=0,smin_value=-1006,smax_value=1034,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"},
+ {11, "R6=inv(id=0,smin_value=-1006,smax_value=1034,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"},
/* Checked s>= 0 */
{14, "R6=inv(id=0,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc))"},
/* At the time the word size load is performed from R5,
@@ -556,14 +556,14 @@ static struct bpf_align_test tests[] = {
/* Calculated offset in R6 has unknown value, but known
* alignment of 4.
*/
- {7, "R2_w=pkt(id=0,off=0,r=8,imm=0)"},
- {10, "R6_w=inv(id=0,umax_value=60,var_off=(0x0; 0x3c))"},
+ {6, "R2_w=pkt(id=0,off=0,r=8,imm=0)"},
+ {9, "R6_w=inv(id=0,umax_value=60,var_off=(0x0; 0x3c))"},
/* Adding 14 makes R6 be (4n+2) */
- {11, "R6_w=inv(id=0,umin_value=14,umax_value=74,var_off=(0x2; 0x7c))"},
+ {10, "R6_w=inv(id=0,umin_value=14,umax_value=74,var_off=(0x2; 0x7c))"},
/* Subtracting from packet pointer overflows ubounds */
{13, "R5_w=pkt(id=2,off=0,r=8,umin_value=18446744073709551542,umax_value=18446744073709551602,var_off=(0xffffffffffffff82; 0x7c)"},
/* New unknown value in R7 is (4n), >= 76 */
- {15, "R7_w=inv(id=0,umin_value=76,umax_value=1096,var_off=(0x0; 0x7fc))"},
+ {14, "R7_w=inv(id=0,umin_value=76,umax_value=1096,var_off=(0x0; 0x7fc))"},
/* Adding it to packet pointer gives nice bounds again */
{16, "R5_w=pkt(id=3,off=0,r=0,umin_value=2,umax_value=1082,var_off=(0x2; 0xfffffffc)"},
/* At the time the word size load is performed from R5,
@@ -625,12 +625,15 @@ static int do_test_single(struct bpf_align_test *test)
line_ptr = strtok(bpf_vlog_copy, "\n");
for (i = 0; i < MAX_MATCHES; i++) {
struct bpf_reg_match m = test->matches[i];
+ int tmp;
if (!m.match)
break;
while (line_ptr) {
cur_line = -1;
sscanf(line_ptr, "%u: ", &cur_line);
+ if (cur_line == -1)
+ sscanf(line_ptr, "from %u to %u: ", &tmp, &cur_line);
if (cur_line == m.line)
break;
line_ptr = strtok(NULL, "\n");
@@ -642,7 +645,19 @@ static int do_test_single(struct bpf_align_test *test)
printf("%s", bpf_vlog);
break;
}
+ /* Check the next line as well in case the previous line
+ * did not have a corresponding bpf insn. Example:
+ * func#0 @0
+ * 0: R1=ctx(id=0,off=0,imm=0) R10=fp0
+ * 0: (b7) r3 = 2 ; R3_w=inv2
+ */
if (!strstr(line_ptr, m.match)) {
+ cur_line = -1;
+ line_ptr = strtok(NULL, "\n");
+ sscanf(line_ptr, "%u: ", &cur_line);
+ }
+ if (cur_line != m.line || !line_ptr ||
+ !strstr(line_ptr, m.match)) {
printf("Failed to find match %u: %s\n",
m.line, m.match);
ret = 1;
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
index 0a6c5f00abd4..dbe56fa8582d 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
@@ -65,8 +65,8 @@ void serial_test_bpf_obj_id(void)
if (CHECK_FAIL(err))
goto done;
- prog = bpf_object__find_program_by_title(objs[i],
- "raw_tp/sys_enter");
+ prog = bpf_object__find_program_by_name(objs[i],
+ "test_obj_id");
if (CHECK_FAIL(!prog))
goto done;
links[i] = bpf_program__attach(prog);
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
index 8daca0ac909f..8f7a1cef7d87 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -217,7 +217,7 @@ static bool found;
static int libbpf_debug_print(enum libbpf_print_level level,
const char *format, va_list args)
{
- const char *log_buf;
+ const char *prog_name, *log_buf;
if (level != LIBBPF_WARN ||
!strstr(format, "-- BEGIN PROG LOAD LOG --")) {
@@ -225,15 +225,14 @@ static int libbpf_debug_print(enum libbpf_print_level level,
return 0;
}
- /* skip prog_name */
- va_arg(args, char *);
+ prog_name = va_arg(args, char *);
log_buf = va_arg(args, char *);
if (!log_buf)
goto out;
if (err_str && strstr(log_buf, err_str) != NULL)
found = true;
out:
- printf(format, log_buf);
+ printf(format, prog_name, log_buf);
return 0;
}
diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index 01b776a7beeb..8ba53acf9eb4 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -22,7 +22,6 @@
#include <bpf/libbpf.h>
#include <bpf/btf.h>
-#include "bpf_rlimit.h"
#include "bpf_util.h"
#include "../test_btf.h"
#include "test_progs.h"
diff --git a/tools/testing/selftests/bpf/prog_tests/connect_force_port.c b/tools/testing/selftests/bpf/prog_tests/connect_force_port.c
index ca574e1e30e6..9c4325f4aef2 100644
--- a/tools/testing/selftests/bpf/prog_tests/connect_force_port.c
+++ b/tools/testing/selftests/bpf/prog_tests/connect_force_port.c
@@ -67,9 +67,9 @@ static int run_test(int cgroup_fd, int server_fd, int family, int type)
goto close_bpf_object;
}
- prog = bpf_object__find_program_by_title(obj, v4 ?
- "cgroup/connect4" :
- "cgroup/connect6");
+ prog = bpf_object__find_program_by_name(obj, v4 ?
+ "connect4" :
+ "connect6");
if (CHECK(!prog, "find_prog", "connect prog not found\n")) {
err = -EIO;
goto close_bpf_object;
@@ -83,9 +83,9 @@ static int run_test(int cgroup_fd, int server_fd, int family, int type)
goto close_bpf_object;
}
- prog = bpf_object__find_program_by_title(obj, v4 ?
- "cgroup/getpeername4" :
- "cgroup/getpeername6");
+ prog = bpf_object__find_program_by_name(obj, v4 ?
+ "getpeername4" :
+ "getpeername6");
if (CHECK(!prog, "find_prog", "getpeername prog not found\n")) {
err = -EIO;
goto close_bpf_object;
@@ -99,9 +99,9 @@ static int run_test(int cgroup_fd, int server_fd, int family, int type)
goto close_bpf_object;
}
- prog = bpf_object__find_program_by_title(obj, v4 ?
- "cgroup/getsockname4" :
- "cgroup/getsockname6");
+ prog = bpf_object__find_program_by_name(obj, v4 ?
+ "getsockname4" :
+ "getsockname6");
if (CHECK(!prog, "find_prog", "getsockname prog not found\n")) {
err = -EIO;
goto close_bpf_object;
diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index 44a9868c70ea..b8bdd1c3efca 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -10,7 +10,7 @@ static int duration = 0;
#define STRUCT_TO_CHAR_PTR(struct_name) (const char *)&(struct struct_name)
-#define MODULES_CASE(name, sec_name, tp_name) { \
+#define MODULES_CASE(name, pg_name, tp_name) { \
.case_name = name, \
.bpf_obj_file = "test_core_reloc_module.o", \
.btf_src_file = NULL, /* find in kernel module BTFs */ \
@@ -28,7 +28,7 @@ static int duration = 0;
.comm_len = sizeof("test_progs"), \
}, \
.output_len = sizeof(struct core_reloc_module_output), \
- .prog_sec_name = sec_name, \
+ .prog_name = pg_name, \
.raw_tp_name = tp_name, \
.trigger = __trigger_module_test_read, \
.needs_testmod = true, \
@@ -43,7 +43,9 @@ static int duration = 0;
#define FLAVORS_CASE_COMMON(name) \
.case_name = #name, \
.bpf_obj_file = "test_core_reloc_flavors.o", \
- .btf_src_file = "btf__core_reloc_" #name ".o" \
+ .btf_src_file = "btf__core_reloc_" #name ".o", \
+ .raw_tp_name = "sys_enter", \
+ .prog_name = "test_core_flavors" \
#define FLAVORS_CASE(name) { \
FLAVORS_CASE_COMMON(name), \
@@ -66,7 +68,9 @@ static int duration = 0;
#define NESTING_CASE_COMMON(name) \
.case_name = #name, \
.bpf_obj_file = "test_core_reloc_nesting.o", \
- .btf_src_file = "btf__core_reloc_" #name ".o"
+ .btf_src_file = "btf__core_reloc_" #name ".o", \
+ .raw_tp_name = "sys_enter", \
+ .prog_name = "test_core_nesting" \
#define NESTING_CASE(name) { \
NESTING_CASE_COMMON(name), \
@@ -91,7 +95,9 @@ static int duration = 0;
#define ARRAYS_CASE_COMMON(name) \
.case_name = #name, \
.bpf_obj_file = "test_core_reloc_arrays.o", \
- .btf_src_file = "btf__core_reloc_" #name ".o"
+ .btf_src_file = "btf__core_reloc_" #name ".o", \
+ .raw_tp_name = "sys_enter", \
+ .prog_name = "test_core_arrays" \
#define ARRAYS_CASE(name) { \
ARRAYS_CASE_COMMON(name), \
@@ -123,7 +129,9 @@ static int duration = 0;
#define PRIMITIVES_CASE_COMMON(name) \
.case_name = #name, \
.bpf_obj_file = "test_core_reloc_primitives.o", \
- .btf_src_file = "btf__core_reloc_" #name ".o"
+ .btf_src_file = "btf__core_reloc_" #name ".o", \
+ .raw_tp_name = "sys_enter", \
+ .prog_name = "test_core_primitives" \
#define PRIMITIVES_CASE(name) { \
PRIMITIVES_CASE_COMMON(name), \
@@ -158,6 +166,8 @@ static int duration = 0;
.e = 5, .f = 6, .g = 7, .h = 8, \
}, \
.output_len = sizeof(struct core_reloc_mods_output), \
+ .raw_tp_name = "sys_enter", \
+ .prog_name = "test_core_mods", \
}
#define PTR_AS_ARR_CASE(name) { \
@@ -174,6 +184,8 @@ static int duration = 0;
.a = 3, \
}, \
.output_len = sizeof(struct core_reloc_ptr_as_arr), \
+ .raw_tp_name = "sys_enter", \
+ .prog_name = "test_core_ptr_as_arr", \
}
#define INTS_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) { \
@@ -190,7 +202,9 @@ static int duration = 0;
#define INTS_CASE_COMMON(name) \
.case_name = #name, \
.bpf_obj_file = "test_core_reloc_ints.o", \
- .btf_src_file = "btf__core_reloc_" #name ".o"
+ .btf_src_file = "btf__core_reloc_" #name ".o", \
+ .raw_tp_name = "sys_enter", \
+ .prog_name = "test_core_ints"
#define INTS_CASE(name) { \
INTS_CASE_COMMON(name), \
@@ -208,7 +222,9 @@ static int duration = 0;
#define FIELD_EXISTS_CASE_COMMON(name) \
.case_name = #name, \
.bpf_obj_file = "test_core_reloc_existence.o", \
- .btf_src_file = "btf__core_reloc_" #name ".o" \
+ .btf_src_file = "btf__core_reloc_" #name ".o", \
+ .raw_tp_name = "sys_enter", \
+ .prog_name = "test_core_existence"
#define BITFIELDS_CASE_COMMON(objfile, test_name_prefix, name) \
.case_name = test_name_prefix#name, \
@@ -223,6 +239,8 @@ static int duration = 0;
.output = STRUCT_TO_CHAR_PTR(core_reloc_bitfields_output) \
__VA_ARGS__, \
.output_len = sizeof(struct core_reloc_bitfields_output), \
+ .raw_tp_name = "sys_enter", \
+ .prog_name = "test_core_bitfields", \
}, { \
BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_direct.o", \
"direct:", name), \
@@ -231,7 +249,7 @@ static int duration = 0;
.output = STRUCT_TO_CHAR_PTR(core_reloc_bitfields_output) \
__VA_ARGS__, \
.output_len = sizeof(struct core_reloc_bitfields_output), \
- .prog_sec_name = "tp_btf/sys_enter", \
+ .prog_name = "test_core_bitfields_direct", \
}
@@ -239,17 +257,21 @@ static int duration = 0;
BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_probed.o", \
"probed:", name), \
.fails = true, \
+ .raw_tp_name = "sys_enter", \
+ .prog_name = "test_core_bitfields", \
}, { \
BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_direct.o", \
"direct:", name), \
- .prog_sec_name = "tp_btf/sys_enter", \
.fails = true, \
+ .prog_name = "test_core_bitfields_direct", \
}
#define SIZE_CASE_COMMON(name) \
.case_name = #name, \
.bpf_obj_file = "test_core_reloc_size.o", \
- .btf_src_file = "btf__core_reloc_" #name ".o"
+ .btf_src_file = "btf__core_reloc_" #name ".o", \
+ .raw_tp_name = "sys_enter", \
+ .prog_name = "test_core_size"
#define SIZE_OUTPUT_DATA(type) \
STRUCT_TO_CHAR_PTR(core_reloc_size_output) { \
@@ -277,8 +299,10 @@ static int duration = 0;
#define TYPE_BASED_CASE_COMMON(name) \
.case_name = #name, \
- .bpf_obj_file = "test_core_reloc_type_based.o", \
- .btf_src_file = "btf__core_reloc_" #name ".o" \
+ .bpf_obj_file = "test_core_reloc_type_based.o", \
+ .btf_src_file = "btf__core_reloc_" #name ".o", \
+ .raw_tp_name = "sys_enter", \
+ .prog_name = "test_core_type_based"
#define TYPE_BASED_CASE(name, ...) { \
TYPE_BASED_CASE_COMMON(name), \
@@ -295,7 +319,9 @@ static int duration = 0;
#define TYPE_ID_CASE_COMMON(name) \
.case_name = #name, \
.bpf_obj_file = "test_core_reloc_type_id.o", \
- .btf_src_file = "btf__core_reloc_" #name ".o" \
+ .btf_src_file = "btf__core_reloc_" #name ".o", \
+ .raw_tp_name = "sys_enter", \
+ .prog_name = "test_core_type_id"
#define TYPE_ID_CASE(name, setup_fn) { \
TYPE_ID_CASE_COMMON(name), \
@@ -312,7 +338,9 @@ static int duration = 0;
#define ENUMVAL_CASE_COMMON(name) \
.case_name = #name, \
.bpf_obj_file = "test_core_reloc_enumval.o", \
- .btf_src_file = "btf__core_reloc_" #name ".o" \
+ .btf_src_file = "btf__core_reloc_" #name ".o", \
+ .raw_tp_name = "sys_enter", \
+ .prog_name = "test_core_enumval"
#define ENUMVAL_CASE(name, ...) { \
ENUMVAL_CASE_COMMON(name), \
@@ -342,7 +370,7 @@ struct core_reloc_test_case {
bool fails;
bool needs_testmod;
bool relaxed_core_relocs;
- const char *prog_sec_name;
+ const char *prog_name;
const char *raw_tp_name;
setup_test_fn setup;
trigger_test_fn trigger;
@@ -497,11 +525,13 @@ static struct core_reloc_test_case test_cases[] = {
.comm_len = sizeof("test_progs"),
},
.output_len = sizeof(struct core_reloc_kernel_output),
+ .raw_tp_name = "sys_enter",
+ .prog_name = "test_core_kernel",
},
/* validate we can find kernel module BTF types for relocs/attach */
- MODULES_CASE("module_probed", "raw_tp/bpf_testmod_test_read", "bpf_testmod_test_read"),
- MODULES_CASE("module_direct", "tp_btf/bpf_testmod_test_read", NULL),
+ MODULES_CASE("module_probed", "test_core_module_probed", "bpf_testmod_test_read"),
+ MODULES_CASE("module_direct", "test_core_module_direct", NULL),
/* validate BPF program can use multiple flavors to match against
* single target BTF type
@@ -580,6 +610,8 @@ static struct core_reloc_test_case test_cases[] = {
.c = 0, /* BUG in clang, should be 3 */
},
.output_len = sizeof(struct core_reloc_misc_output),
+ .raw_tp_name = "sys_enter",
+ .prog_name = "test_core_misc",
},
/* validate field existence checks */
@@ -848,14 +880,9 @@ void test_core_reloc(void)
if (!ASSERT_OK_PTR(obj, "obj_open"))
goto cleanup;
- probe_name = "raw_tracepoint/sys_enter";
- tp_name = "sys_enter";
- if (test_case->prog_sec_name) {
- probe_name = test_case->prog_sec_name;
- tp_name = test_case->raw_tp_name; /* NULL for tp_btf */
- }
-
- prog = bpf_object__find_program_by_title(obj, probe_name);
+ probe_name = test_case->prog_name;
+ tp_name = test_case->raw_tp_name; /* NULL for tp_btf */
+ prog = bpf_object__find_program_by_name(obj, probe_name);
if (CHECK(!prog, "find_probe",
"prog '%s' not found\n", probe_name))
goto cleanup;
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
index fdd603ebda28..c52f99f6a909 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
@@ -101,6 +101,8 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
for (i = 0; i < prog_cnt; i++) {
struct bpf_link_info link_info;
+ struct bpf_program *pos;
+ const char *pos_sec_name;
char *tgt_name;
__s32 btf_id;
@@ -109,7 +111,14 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
goto close_prog;
btf_id = btf__find_by_name_kind(btf, tgt_name + 1, BTF_KIND_FUNC);
- prog[i] = bpf_object__find_program_by_title(obj, prog_name[i]);
+ prog[i] = NULL;
+ bpf_object__for_each_program(pos, obj) {
+ pos_sec_name = bpf_program__section_name(pos);
+ if (pos_sec_name && !strcmp(pos_sec_name, prog_name[i])) {
+ prog[i] = pos;
+ break;
+ }
+ }
if (!ASSERT_OK_PTR(prog[i], prog_name[i]))
goto close_prog;
@@ -211,8 +220,8 @@ static void test_func_replace_verify(void)
static int test_second_attach(struct bpf_object *obj)
{
- const char *prog_name = "freplace/get_constant";
- const char *tgt_name = prog_name + 9; /* cut off freplace/ */
+ const char *prog_name = "security_new_get_constant";
+ const char *tgt_name = "get_constant";
const char *tgt_obj_file = "./test_pkt_access.o";
struct bpf_program *prog = NULL;
struct bpf_object *tgt_obj;
@@ -220,7 +229,7 @@ static int test_second_attach(struct bpf_object *obj)
struct bpf_link *link;
int err = 0, tgt_fd;
- prog = bpf_object__find_program_by_title(obj, prog_name);
+ prog = bpf_object__find_program_by_name(obj, prog_name);
if (CHECK(!prog, "find_prog", "prog %s not found\n", prog_name))
return -ENOENT;
diff --git a/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c b/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c
new file mode 100644
index 000000000000..85c427119fe9
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include "get_func_args_test.skel.h"
+
+void test_get_func_args_test(void)
+{
+ struct get_func_args_test *skel = NULL;
+ __u32 duration = 0, retval;
+ int err, prog_fd;
+
+ skel = get_func_args_test__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "get_func_args_test__open_and_load"))
+ return;
+
+ err = get_func_args_test__attach(skel);
+ if (!ASSERT_OK(err, "get_func_args_test__attach"))
+ goto cleanup;
+
+ /* This runs bpf_fentry_test* functions and triggers
+ * fentry/fexit programs.
+ */
+ prog_fd = bpf_program__fd(skel->progs.test1);
+ err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
+ NULL, NULL, &retval, &duration);
+ ASSERT_OK(err, "test_run");
+ ASSERT_EQ(retval, 0, "test_run");
+
+ /* This runs bpf_modify_return_test function and triggers
+ * fmod_ret_test and fexit_test programs.
+ */
+ prog_fd = bpf_program__fd(skel->progs.fmod_ret_test);
+ err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
+ NULL, NULL, &retval, &duration);
+ ASSERT_OK(err, "test_run");
+ ASSERT_EQ(retval, 1234, "test_run");
+
+ ASSERT_EQ(skel->bss->test1_result, 1, "test1_result");
+ ASSERT_EQ(skel->bss->test2_result, 1, "test2_result");
+ ASSERT_EQ(skel->bss->test3_result, 1, "test3_result");
+ ASSERT_EQ(skel->bss->test4_result, 1, "test4_result");
+
+cleanup:
+ get_func_args_test__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c
index 977ab433a946..e834a01de16a 100644
--- a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c
+++ b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c
@@ -89,7 +89,7 @@ void test_get_stack_raw_tp(void)
{
const char *file = "./test_get_stack_rawtp.o";
const char *file_err = "./test_get_stack_rawtp_err.o";
- const char *prog_name = "raw_tracepoint/sys_enter";
+ const char *prog_name = "bpf_prog1";
int i, err, prog_fd, exp_cnt = MAX_CNT_RAWTP;
struct perf_buffer *pb = NULL;
struct bpf_link *link = NULL;
@@ -107,7 +107,7 @@ void test_get_stack_raw_tp(void)
if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno))
return;
- prog = bpf_object__find_program_by_title(obj, prog_name);
+ prog = bpf_object__find_program_by_name(obj, prog_name);
if (CHECK(!prog, "find_probe", "prog '%s' not found\n", prog_name))
goto close_prog;
diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c b/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c
index 79f6bd1e50d6..f6933b06daf8 100644
--- a/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c
@@ -8,6 +8,7 @@
#include "test_ksyms_btf_null_check.skel.h"
#include "test_ksyms_weak.skel.h"
#include "test_ksyms_weak.lskel.h"
+#include "test_ksyms_btf_write_check.skel.h"
static int duration;
@@ -137,6 +138,16 @@ cleanup:
test_ksyms_weak_lskel__destroy(skel);
}
+static void test_write_check(void)
+{
+ struct test_ksyms_btf_write_check *skel;
+
+ skel = test_ksyms_btf_write_check__open_and_load();
+ ASSERT_ERR_PTR(skel, "unexpected load of a prog writing to ksym memory\n");
+
+ test_ksyms_btf_write_check__destroy(skel);
+}
+
void test_ksyms_btf(void)
{
int percpu_datasec;
@@ -167,4 +178,7 @@ void test_ksyms_btf(void)
if (test__start_subtest("weak_ksyms_lskel"))
test_weak_syms_lskel();
+
+ if (test__start_subtest("write_check"))
+ test_write_check();
}
diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c
new file mode 100644
index 000000000000..9f766ddd946a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c
@@ -0,0 +1,124 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2021 Facebook */
+
+#include <test_progs.h>
+#include <bpf/btf.h>
+
+void test_libbpf_probe_prog_types(void)
+{
+ struct btf *btf;
+ const struct btf_type *t;
+ const struct btf_enum *e;
+ int i, n, id;
+
+ btf = btf__parse("/sys/kernel/btf/vmlinux", NULL);
+ if (!ASSERT_OK_PTR(btf, "btf_parse"))
+ return;
+
+ /* find enum bpf_prog_type and enumerate each value */
+ id = btf__find_by_name_kind(btf, "bpf_prog_type", BTF_KIND_ENUM);
+ if (!ASSERT_GT(id, 0, "bpf_prog_type_id"))
+ goto cleanup;
+ t = btf__type_by_id(btf, id);
+ if (!ASSERT_OK_PTR(t, "bpf_prog_type_enum"))
+ goto cleanup;
+
+ for (e = btf_enum(t), i = 0, n = btf_vlen(t); i < n; e++, i++) {
+ const char *prog_type_name = btf__str_by_offset(btf, e->name_off);
+ enum bpf_prog_type prog_type = (enum bpf_prog_type)e->val;
+ int res;
+
+ if (prog_type == BPF_PROG_TYPE_UNSPEC)
+ continue;
+
+ if (!test__start_subtest(prog_type_name))
+ continue;
+
+ res = libbpf_probe_bpf_prog_type(prog_type, NULL);
+ ASSERT_EQ(res, 1, prog_type_name);
+ }
+
+cleanup:
+ btf__free(btf);
+}
+
+void test_libbpf_probe_map_types(void)
+{
+ struct btf *btf;
+ const struct btf_type *t;
+ const struct btf_enum *e;
+ int i, n, id;
+
+ btf = btf__parse("/sys/kernel/btf/vmlinux", NULL);
+ if (!ASSERT_OK_PTR(btf, "btf_parse"))
+ return;
+
+ /* find enum bpf_map_type and enumerate each value */
+ id = btf__find_by_name_kind(btf, "bpf_map_type", BTF_KIND_ENUM);
+ if (!ASSERT_GT(id, 0, "bpf_map_type_id"))
+ goto cleanup;
+ t = btf__type_by_id(btf, id);
+ if (!ASSERT_OK_PTR(t, "bpf_map_type_enum"))
+ goto cleanup;
+
+ for (e = btf_enum(t), i = 0, n = btf_vlen(t); i < n; e++, i++) {
+ const char *map_type_name = btf__str_by_offset(btf, e->name_off);
+ enum bpf_map_type map_type = (enum bpf_map_type)e->val;
+ int res;
+
+ if (map_type == BPF_MAP_TYPE_UNSPEC)
+ continue;
+
+ if (!test__start_subtest(map_type_name))
+ continue;
+
+ res = libbpf_probe_bpf_map_type(map_type, NULL);
+ ASSERT_EQ(res, 1, map_type_name);
+ }
+
+cleanup:
+ btf__free(btf);
+}
+
+void test_libbpf_probe_helpers(void)
+{
+#define CASE(prog, helper, supp) { \
+ .prog_type_name = "BPF_PROG_TYPE_" # prog, \
+ .helper_name = "bpf_" # helper, \
+ .prog_type = BPF_PROG_TYPE_ ## prog, \
+ .helper_id = BPF_FUNC_ ## helper, \
+ .supported = supp, \
+}
+ const struct case_def {
+ const char *prog_type_name;
+ const char *helper_name;
+ enum bpf_prog_type prog_type;
+ enum bpf_func_id helper_id;
+ bool supported;
+ } cases[] = {
+ CASE(KPROBE, unspec, false),
+ CASE(KPROBE, map_lookup_elem, true),
+ CASE(KPROBE, loop, true),
+
+ CASE(KPROBE, ktime_get_coarse_ns, false),
+ CASE(SOCKET_FILTER, ktime_get_coarse_ns, true),
+
+ CASE(KPROBE, sys_bpf, false),
+ CASE(SYSCALL, sys_bpf, true),
+ };
+ size_t case_cnt = ARRAY_SIZE(cases), i;
+ char buf[128];
+
+ for (i = 0; i < case_cnt; i++) {
+ const struct case_def *d = &cases[i];
+ int res;
+
+ snprintf(buf, sizeof(buf), "%s+%s", d->prog_type_name, d->helper_name);
+
+ if (!test__start_subtest(buf))
+ continue;
+
+ res = libbpf_probe_bpf_helper(d->prog_type, d->helper_id, NULL);
+ ASSERT_EQ(res, d->supported, buf);
+ }
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
index 980ac0f2c0bb..1cbd8cd64044 100644
--- a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
+++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
@@ -18,7 +18,6 @@
#include <netinet/in.h>
#include <bpf/bpf.h>
#include <bpf/libbpf.h>
-#include "bpf_rlimit.h"
#include "bpf_util.h"
#include "test_progs.h"
diff --git a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
index 57846cc7ce36..597d0467a926 100644
--- a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
+++ b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
@@ -30,7 +30,6 @@
#include <bpf/bpf.h>
#include "test_progs.h"
-#include "bpf_rlimit.h"
#include "bpf_util.h"
#include "cgroup_helpers.h"
#include "network_helpers.h"
diff --git a/tools/testing/selftests/bpf/prog_tests/sock_fields.c b/tools/testing/selftests/bpf/prog_tests/sock_fields.c
index fae40db4d81f..9fc040eaa482 100644
--- a/tools/testing/selftests/bpf/prog_tests/sock_fields.c
+++ b/tools/testing/selftests/bpf/prog_tests/sock_fields.c
@@ -15,7 +15,6 @@
#include "network_helpers.h"
#include "cgroup_helpers.h"
#include "test_progs.h"
-#include "bpf_rlimit.h"
#include "test_sock_fields.skel.h"
enum bpf_linum_array_idx {
diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c
index 6a953f4adfdc..8ed78a9383ba 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c
@@ -136,7 +136,8 @@ static int start_server(void)
return fd;
}
-static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title)
+static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title,
+ const char *prog_name)
{
enum bpf_attach_type attach_type;
enum bpf_prog_type prog_type;
@@ -145,20 +146,20 @@ static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title)
err = libbpf_prog_type_by_name(title, &prog_type, &attach_type);
if (err) {
- log_err("Failed to deduct types for %s BPF program", title);
+ log_err("Failed to deduct types for %s BPF program", prog_name);
return -1;
}
- prog = bpf_object__find_program_by_title(obj, title);
+ prog = bpf_object__find_program_by_name(obj, prog_name);
if (!prog) {
- log_err("Failed to find %s BPF program", title);
+ log_err("Failed to find %s BPF program", prog_name);
return -1;
}
err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd,
attach_type, 0);
if (err) {
- log_err("Failed to attach %s BPF program", title);
+ log_err("Failed to attach %s BPF program", prog_name);
return -1;
}
@@ -181,11 +182,11 @@ static void run_test(int cgroup_fd)
if (!ASSERT_OK(err, "obj_load"))
goto close_bpf_object;
- err = prog_attach(obj, cgroup_fd, "cgroup/getsockopt");
+ err = prog_attach(obj, cgroup_fd, "cgroup/getsockopt", "_getsockopt");
if (CHECK_FAIL(err))
goto close_bpf_object;
- err = prog_attach(obj, cgroup_fd, "cgroup/setsockopt");
+ err = prog_attach(obj, cgroup_fd, "cgroup/setsockopt", "_setsockopt");
if (CHECK_FAIL(err))
goto close_bpf_object;
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c
index 337493d74ec5..313f0a66232e 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c
@@ -4,7 +4,7 @@
void test_stacktrace_map(void)
{
int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd;
- const char *prog_name = "tracepoint/sched/sched_switch";
+ const char *prog_name = "oncpu";
int err, prog_fd, stack_trace_len;
const char *file = "./test_stacktrace_map.o";
__u32 key, val, duration = 0;
@@ -16,7 +16,7 @@ void test_stacktrace_map(void)
if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno))
return;
- prog = bpf_object__find_program_by_title(obj, prog_name);
+ prog = bpf_object__find_program_by_name(obj, prog_name);
if (CHECK(!prog, "find_prog", "prog '%s' not found\n", prog_name))
goto close_prog;
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c
index 063a14a2060d..1cb8dd36bd8f 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c
@@ -3,7 +3,7 @@
void test_stacktrace_map_raw_tp(void)
{
- const char *prog_name = "tracepoint/sched/sched_switch";
+ const char *prog_name = "oncpu";
int control_map_fd, stackid_hmap_fd, stackmap_fd;
const char *file = "./test_stacktrace_map.o";
__u32 key, val, duration = 0;
@@ -16,7 +16,7 @@ void test_stacktrace_map_raw_tp(void)
if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno))
return;
- prog = bpf_object__find_program_by_title(obj, prog_name);
+ prog = bpf_object__find_program_by_name(obj, prog_name);
if (CHECK(!prog, "find_prog", "prog '%s' not found\n", prog_name))
goto close_prog;
diff --git a/tools/testing/selftests/bpf/prog_tests/test_local_storage.c b/tools/testing/selftests/bpf/prog_tests/test_local_storage.c
index d2c16eaae367..26ac26a88026 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_local_storage.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_local_storage.c
@@ -28,10 +28,6 @@ static unsigned int duration;
struct storage {
void *inode;
unsigned int value;
- /* Lock ensures that spin locked versions of local stoage operations
- * also work, most operations in this tests are still single threaded
- */
- struct bpf_spin_lock lock;
};
/* Fork and exec the provided rm binary and return the exit code of the
@@ -66,27 +62,24 @@ static int run_self_unlink(int *monitored_pid, const char *rm_path)
static bool check_syscall_operations(int map_fd, int obj_fd)
{
- struct storage val = { .value = TEST_STORAGE_VALUE, .lock = { 0 } },
- lookup_val = { .value = 0, .lock = { 0 } };
+ struct storage val = { .value = TEST_STORAGE_VALUE },
+ lookup_val = { .value = 0 };
int err;
/* Looking up an existing element should fail initially */
- err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val,
- BPF_F_LOCK);
+ err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val, 0);
if (CHECK(!err || errno != ENOENT, "bpf_map_lookup_elem",
"err:%d errno:%d\n", err, errno))
return false;
/* Create a new element */
- err = bpf_map_update_elem(map_fd, &obj_fd, &val,
- BPF_NOEXIST | BPF_F_LOCK);
+ err = bpf_map_update_elem(map_fd, &obj_fd, &val, BPF_NOEXIST);
if (CHECK(err < 0, "bpf_map_update_elem", "err:%d errno:%d\n", err,
errno))
return false;
/* Lookup the newly created element */
- err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val,
- BPF_F_LOCK);
+ err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val, 0);
if (CHECK(err < 0, "bpf_map_lookup_elem", "err:%d errno:%d", err,
errno))
return false;
@@ -102,8 +95,7 @@ static bool check_syscall_operations(int map_fd, int obj_fd)
return false;
/* The lookup should fail, now that the element has been deleted */
- err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val,
- BPF_F_LOCK);
+ err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val, 0);
if (CHECK(!err || errno != ENOENT, "bpf_map_lookup_elem",
"err:%d errno:%d\n", err, errno))
return false;
diff --git a/tools/testing/selftests/bpf/prog_tests/test_overhead.c b/tools/testing/selftests/bpf/prog_tests/test_overhead.c
index 123c68c1917d..05acb376f74d 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_overhead.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_overhead.c
@@ -56,11 +56,11 @@ static void setaffinity(void)
void test_test_overhead(void)
{
- const char *kprobe_name = "kprobe/__set_task_comm";
- const char *kretprobe_name = "kretprobe/__set_task_comm";
- const char *raw_tp_name = "raw_tp/task_rename";
- const char *fentry_name = "fentry/__set_task_comm";
- const char *fexit_name = "fexit/__set_task_comm";
+ const char *kprobe_name = "prog1";
+ const char *kretprobe_name = "prog2";
+ const char *raw_tp_name = "prog3";
+ const char *fentry_name = "prog4";
+ const char *fexit_name = "prog5";
const char *kprobe_func = "__set_task_comm";
struct bpf_program *kprobe_prog, *kretprobe_prog, *raw_tp_prog;
struct bpf_program *fentry_prog, *fexit_prog;
@@ -76,23 +76,23 @@ void test_test_overhead(void)
if (!ASSERT_OK_PTR(obj, "obj_open_file"))
return;
- kprobe_prog = bpf_object__find_program_by_title(obj, kprobe_name);
+ kprobe_prog = bpf_object__find_program_by_name(obj, kprobe_name);
if (CHECK(!kprobe_prog, "find_probe",
"prog '%s' not found\n", kprobe_name))
goto cleanup;
- kretprobe_prog = bpf_object__find_program_by_title(obj, kretprobe_name);
+ kretprobe_prog = bpf_object__find_program_by_name(obj, kretprobe_name);
if (CHECK(!kretprobe_prog, "find_probe",
"prog '%s' not found\n", kretprobe_name))
goto cleanup;
- raw_tp_prog = bpf_object__find_program_by_title(obj, raw_tp_name);
+ raw_tp_prog = bpf_object__find_program_by_name(obj, raw_tp_name);
if (CHECK(!raw_tp_prog, "find_probe",
"prog '%s' not found\n", raw_tp_name))
goto cleanup;
- fentry_prog = bpf_object__find_program_by_title(obj, fentry_name);
+ fentry_prog = bpf_object__find_program_by_name(obj, fentry_name);
if (CHECK(!fentry_prog, "find_probe",
"prog '%s' not found\n", fentry_name))
goto cleanup;
- fexit_prog = bpf_object__find_program_by_title(obj, fexit_name);
+ fexit_prog = bpf_object__find_program_by_name(obj, fexit_name);
if (CHECK(!fexit_prog, "find_probe",
"prog '%s' not found\n", fexit_name))
goto cleanup;
diff --git a/tools/testing/selftests/bpf/prog_tests/test_strncmp.c b/tools/testing/selftests/bpf/prog_tests/test_strncmp.c
new file mode 100644
index 000000000000..b57a3009465f
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_strncmp.c
@@ -0,0 +1,167 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021. Huawei Technologies Co., Ltd */
+#include <test_progs.h>
+#include "strncmp_test.skel.h"
+
+static int trigger_strncmp(const struct strncmp_test *skel)
+{
+ int cmp;
+
+ usleep(1);
+
+ cmp = skel->bss->cmp_ret;
+ if (cmp > 0)
+ return 1;
+ if (cmp < 0)
+ return -1;
+ return 0;
+}
+
+/*
+ * Compare str and target after making str[i] != target[i].
+ * When exp is -1, make str[i] < target[i] and delta = -1.
+ */
+static void strncmp_full_str_cmp(struct strncmp_test *skel, const char *name,
+ int exp)
+{
+ size_t nr = sizeof(skel->bss->str);
+ char *str = skel->bss->str;
+ int delta = exp;
+ int got;
+ size_t i;
+
+ memcpy(str, skel->rodata->target, nr);
+ for (i = 0; i < nr - 1; i++) {
+ str[i] += delta;
+
+ got = trigger_strncmp(skel);
+ ASSERT_EQ(got, exp, name);
+
+ str[i] -= delta;
+ }
+}
+
+static void test_strncmp_ret(void)
+{
+ struct strncmp_test *skel;
+ struct bpf_program *prog;
+ int err, got;
+
+ skel = strncmp_test__open();
+ if (!ASSERT_OK_PTR(skel, "strncmp_test open"))
+ return;
+
+ bpf_object__for_each_program(prog, skel->obj)
+ bpf_program__set_autoload(prog, false);
+
+ bpf_program__set_autoload(skel->progs.do_strncmp, true);
+
+ err = strncmp_test__load(skel);
+ if (!ASSERT_EQ(err, 0, "strncmp_test load"))
+ goto out;
+
+ err = strncmp_test__attach(skel);
+ if (!ASSERT_EQ(err, 0, "strncmp_test attach"))
+ goto out;
+
+ skel->bss->target_pid = getpid();
+
+ /* Empty str */
+ skel->bss->str[0] = '\0';
+ got = trigger_strncmp(skel);
+ ASSERT_EQ(got, -1, "strncmp: empty str");
+
+ /* Same string */
+ memcpy(skel->bss->str, skel->rodata->target, sizeof(skel->bss->str));
+ got = trigger_strncmp(skel);
+ ASSERT_EQ(got, 0, "strncmp: same str");
+
+ /* Not-null-termainted string */
+ memcpy(skel->bss->str, skel->rodata->target, sizeof(skel->bss->str));
+ skel->bss->str[sizeof(skel->bss->str) - 1] = 'A';
+ got = trigger_strncmp(skel);
+ ASSERT_EQ(got, 1, "strncmp: not-null-term str");
+
+ strncmp_full_str_cmp(skel, "strncmp: less than", -1);
+ strncmp_full_str_cmp(skel, "strncmp: greater than", 1);
+out:
+ strncmp_test__destroy(skel);
+}
+
+static void test_strncmp_bad_not_const_str_size(void)
+{
+ struct strncmp_test *skel;
+ struct bpf_program *prog;
+ int err;
+
+ skel = strncmp_test__open();
+ if (!ASSERT_OK_PTR(skel, "strncmp_test open"))
+ return;
+
+ bpf_object__for_each_program(prog, skel->obj)
+ bpf_program__set_autoload(prog, false);
+
+ bpf_program__set_autoload(skel->progs.strncmp_bad_not_const_str_size,
+ true);
+
+ err = strncmp_test__load(skel);
+ ASSERT_ERR(err, "strncmp_test load bad_not_const_str_size");
+
+ strncmp_test__destroy(skel);
+}
+
+static void test_strncmp_bad_writable_target(void)
+{
+ struct strncmp_test *skel;
+ struct bpf_program *prog;
+ int err;
+
+ skel = strncmp_test__open();
+ if (!ASSERT_OK_PTR(skel, "strncmp_test open"))
+ return;
+
+ bpf_object__for_each_program(prog, skel->obj)
+ bpf_program__set_autoload(prog, false);
+
+ bpf_program__set_autoload(skel->progs.strncmp_bad_writable_target,
+ true);
+
+ err = strncmp_test__load(skel);
+ ASSERT_ERR(err, "strncmp_test load bad_writable_target");
+
+ strncmp_test__destroy(skel);
+}
+
+static void test_strncmp_bad_not_null_term_target(void)
+{
+ struct strncmp_test *skel;
+ struct bpf_program *prog;
+ int err;
+
+ skel = strncmp_test__open();
+ if (!ASSERT_OK_PTR(skel, "strncmp_test open"))
+ return;
+
+ bpf_object__for_each_program(prog, skel->obj)
+ bpf_program__set_autoload(prog, false);
+
+ bpf_program__set_autoload(skel->progs.strncmp_bad_not_null_term_target,
+ true);
+
+ err = strncmp_test__load(skel);
+ ASSERT_ERR(err, "strncmp_test load bad_not_null_term_target");
+
+ strncmp_test__destroy(skel);
+}
+
+void test_test_strncmp(void)
+{
+ if (test__start_subtest("strncmp_ret"))
+ test_strncmp_ret();
+ if (test__start_subtest("strncmp_bad_not_const_str_size"))
+ test_strncmp_bad_not_const_str_size();
+ if (test__start_subtest("strncmp_bad_writable_target"))
+ test_strncmp_bad_writable_target();
+ if (test__start_subtest("strncmp_bad_not_null_term_target"))
+ test_strncmp_bad_not_null_term_target();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
index fc146671b20a..9c795ee52b7b 100644
--- a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
+++ b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
@@ -35,7 +35,7 @@ static struct bpf_link *load(struct bpf_object *obj, const char *name)
struct bpf_program *prog;
int duration = 0;
- prog = bpf_object__find_program_by_title(obj, name);
+ prog = bpf_object__find_program_by_name(obj, name);
if (CHECK(!prog, "find_probe", "prog '%s' not found\n", name))
return ERR_PTR(-EINVAL);
return bpf_program__attach_trace(prog);
@@ -44,8 +44,8 @@ static struct bpf_link *load(struct bpf_object *obj, const char *name)
/* TODO: use different target function to run in concurrent mode */
void serial_test_trampoline_count(void)
{
- const char *fentry_name = "fentry/__set_task_comm";
- const char *fexit_name = "fexit/__set_task_comm";
+ const char *fentry_name = "prog1";
+ const char *fexit_name = "prog2";
const char *object = "test_trampoline_count.o";
struct inst inst[MAX_TRAMP_PROGS] = {};
int err, i = 0, duration = 0;
diff --git a/tools/testing/selftests/bpf/progs/get_func_args_test.c b/tools/testing/selftests/bpf/progs/get_func_args_test.c
new file mode 100644
index 000000000000..e0f34a55e697
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/get_func_args_test.c
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <errno.h>
+
+char _license[] SEC("license") = "GPL";
+
+__u64 test1_result = 0;
+SEC("fentry/bpf_fentry_test1")
+int BPF_PROG(test1)
+{
+ __u64 cnt = bpf_get_func_arg_cnt(ctx);
+ __u64 a = 0, z = 0, ret = 0;
+ __s64 err;
+
+ test1_result = cnt == 1;
+
+ /* valid arguments */
+ err = bpf_get_func_arg(ctx, 0, &a);
+
+ /* We need to cast access to traced function argument values with
+ * proper type cast, because trampoline uses type specific instruction
+ * to save it, like for 'int a' with 32-bit mov like:
+ *
+ * mov %edi,-0x8(%rbp)
+ *
+ * so the upper 4 bytes are not zeroed.
+ */
+ test1_result &= err == 0 && ((int) a == 1);
+
+ /* not valid argument */
+ err = bpf_get_func_arg(ctx, 1, &z);
+ test1_result &= err == -EINVAL;
+
+ /* return value fails in fentry */
+ err = bpf_get_func_ret(ctx, &ret);
+ test1_result &= err == -EOPNOTSUPP;
+ return 0;
+}
+
+__u64 test2_result = 0;
+SEC("fexit/bpf_fentry_test2")
+int BPF_PROG(test2)
+{
+ __u64 cnt = bpf_get_func_arg_cnt(ctx);
+ __u64 a = 0, b = 0, z = 0, ret = 0;
+ __s64 err;
+
+ test2_result = cnt == 2;
+
+ /* valid arguments */
+ err = bpf_get_func_arg(ctx, 0, &a);
+ test2_result &= err == 0 && (int) a == 2;
+
+ err = bpf_get_func_arg(ctx, 1, &b);
+ test2_result &= err == 0 && b == 3;
+
+ /* not valid argument */
+ err = bpf_get_func_arg(ctx, 2, &z);
+ test2_result &= err == -EINVAL;
+
+ /* return value */
+ err = bpf_get_func_ret(ctx, &ret);
+ test2_result &= err == 0 && ret == 5;
+ return 0;
+}
+
+__u64 test3_result = 0;
+SEC("fmod_ret/bpf_modify_return_test")
+int BPF_PROG(fmod_ret_test, int _a, int *_b, int _ret)
+{
+ __u64 cnt = bpf_get_func_arg_cnt(ctx);
+ __u64 a = 0, b = 0, z = 0, ret = 0;
+ __s64 err;
+
+ test3_result = cnt == 2;
+
+ /* valid arguments */
+ err = bpf_get_func_arg(ctx, 0, &a);
+ test3_result &= err == 0 && ((int) a == 1);
+
+ err = bpf_get_func_arg(ctx, 1, &b);
+ test3_result &= err == 0 && ((int *) b == _b);
+
+ /* not valid argument */
+ err = bpf_get_func_arg(ctx, 2, &z);
+ test3_result &= err == -EINVAL;
+
+ /* return value */
+ err = bpf_get_func_ret(ctx, &ret);
+ test3_result &= err == 0 && ret == 0;
+
+ /* change return value, it's checked in fexit_test program */
+ return 1234;
+}
+
+__u64 test4_result = 0;
+SEC("fexit/bpf_modify_return_test")
+int BPF_PROG(fexit_test, int _a, int *_b, int _ret)
+{
+ __u64 cnt = bpf_get_func_arg_cnt(ctx);
+ __u64 a = 0, b = 0, z = 0, ret = 0;
+ __s64 err;
+
+ test4_result = cnt == 2;
+
+ /* valid arguments */
+ err = bpf_get_func_arg(ctx, 0, &a);
+ test4_result &= err == 0 && ((int) a == 1);
+
+ err = bpf_get_func_arg(ctx, 1, &b);
+ test4_result &= err == 0 && ((int *) b == _b);
+
+ /* not valid argument */
+ err = bpf_get_func_arg(ctx, 2, &z);
+ test4_result &= err == -EINVAL;
+
+ /* return value */
+ err = bpf_get_func_ret(ctx, &ret);
+ test4_result &= err == 0 && ret == 1234;
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/local_storage.c b/tools/testing/selftests/bpf/progs/local_storage.c
index 95868bc7ada9..9b1f9b75d5c2 100644
--- a/tools/testing/selftests/bpf/progs/local_storage.c
+++ b/tools/testing/selftests/bpf/progs/local_storage.c
@@ -20,7 +20,6 @@ int sk_storage_result = -1;
struct local_storage {
struct inode *exec_inode;
__u32 value;
- struct bpf_spin_lock lock;
};
struct {
@@ -58,9 +57,7 @@ int BPF_PROG(unlink_hook, struct inode *dir, struct dentry *victim)
bpf_get_current_task_btf(), 0, 0);
if (storage) {
/* Don't let an executable delete itself */
- bpf_spin_lock(&storage->lock);
is_self_unlink = storage->exec_inode == victim->d_inode;
- bpf_spin_unlock(&storage->lock);
if (is_self_unlink)
return -EPERM;
}
@@ -68,7 +65,7 @@ int BPF_PROG(unlink_hook, struct inode *dir, struct dentry *victim)
return 0;
}
-SEC("lsm/inode_rename")
+SEC("lsm.s/inode_rename")
int BPF_PROG(inode_rename, struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
@@ -89,10 +86,8 @@ int BPF_PROG(inode_rename, struct inode *old_dir, struct dentry *old_dentry,
if (!storage)
return 0;
- bpf_spin_lock(&storage->lock);
if (storage->value != DUMMY_STORAGE_VALUE)
inode_storage_result = -1;
- bpf_spin_unlock(&storage->lock);
err = bpf_inode_storage_delete(&inode_storage_map, old_dentry->d_inode);
if (!err)
@@ -101,7 +96,7 @@ int BPF_PROG(inode_rename, struct inode *old_dir, struct dentry *old_dentry,
return 0;
}
-SEC("lsm/socket_bind")
+SEC("lsm.s/socket_bind")
int BPF_PROG(socket_bind, struct socket *sock, struct sockaddr *address,
int addrlen)
{
@@ -117,10 +112,8 @@ int BPF_PROG(socket_bind, struct socket *sock, struct sockaddr *address,
if (!storage)
return 0;
- bpf_spin_lock(&storage->lock);
if (storage->value != DUMMY_STORAGE_VALUE)
sk_storage_result = -1;
- bpf_spin_unlock(&storage->lock);
err = bpf_sk_storage_delete(&sk_storage_map, sock->sk);
if (!err)
@@ -129,7 +122,7 @@ int BPF_PROG(socket_bind, struct socket *sock, struct sockaddr *address,
return 0;
}
-SEC("lsm/socket_post_create")
+SEC("lsm.s/socket_post_create")
int BPF_PROG(socket_post_create, struct socket *sock, int family, int type,
int protocol, int kern)
{
@@ -144,9 +137,7 @@ int BPF_PROG(socket_post_create, struct socket *sock, int family, int type,
if (!storage)
return 0;
- bpf_spin_lock(&storage->lock);
storage->value = DUMMY_STORAGE_VALUE;
- bpf_spin_unlock(&storage->lock);
return 0;
}
@@ -154,7 +145,7 @@ int BPF_PROG(socket_post_create, struct socket *sock, int family, int type,
/* This uses the local storage to remember the inode of the binary that a
* process was originally executing.
*/
-SEC("lsm/bprm_committed_creds")
+SEC("lsm.s/bprm_committed_creds")
void BPF_PROG(exec, struct linux_binprm *bprm)
{
__u32 pid = bpf_get_current_pid_tgid() >> 32;
@@ -166,18 +157,13 @@ void BPF_PROG(exec, struct linux_binprm *bprm)
storage = bpf_task_storage_get(&task_storage_map,
bpf_get_current_task_btf(), 0,
BPF_LOCAL_STORAGE_GET_F_CREATE);
- if (storage) {
- bpf_spin_lock(&storage->lock);
+ if (storage)
storage->exec_inode = bprm->file->f_inode;
- bpf_spin_unlock(&storage->lock);
- }
storage = bpf_inode_storage_get(&inode_storage_map, bprm->file->f_inode,
0, BPF_LOCAL_STORAGE_GET_F_CREATE);
if (!storage)
return;
- bpf_spin_lock(&storage->lock);
storage->value = DUMMY_STORAGE_VALUE;
- bpf_spin_unlock(&storage->lock);
}
diff --git a/tools/testing/selftests/bpf/progs/strncmp_bench.c b/tools/testing/selftests/bpf/progs/strncmp_bench.c
new file mode 100644
index 000000000000..18373a7df76e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/strncmp_bench.c
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021. Huawei Technologies Co., Ltd */
+#include <linux/types.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#define STRNCMP_STR_SZ 4096
+
+/* Will be updated by benchmark before program loading */
+const volatile unsigned int cmp_str_len = 1;
+const char target[STRNCMP_STR_SZ];
+
+long hits = 0;
+char str[STRNCMP_STR_SZ];
+
+char _license[] SEC("license") = "GPL";
+
+static __always_inline int local_strncmp(const char *s1, unsigned int sz,
+ const char *s2)
+{
+ int ret = 0;
+ unsigned int i;
+
+ for (i = 0; i < sz; i++) {
+ /* E.g. 0xff > 0x31 */
+ ret = (unsigned char)s1[i] - (unsigned char)s2[i];
+ if (ret || !s1[i])
+ break;
+ }
+
+ return ret;
+}
+
+SEC("tp/syscalls/sys_enter_getpgid")
+int strncmp_no_helper(void *ctx)
+{
+ if (local_strncmp(str, cmp_str_len + 1, target) < 0)
+ __sync_add_and_fetch(&hits, 1);
+ return 0;
+}
+
+SEC("tp/syscalls/sys_enter_getpgid")
+int strncmp_helper(void *ctx)
+{
+ if (bpf_strncmp(str, cmp_str_len + 1, target) < 0)
+ __sync_add_and_fetch(&hits, 1);
+ return 0;
+}
+
diff --git a/tools/testing/selftests/bpf/progs/strncmp_test.c b/tools/testing/selftests/bpf/progs/strncmp_test.c
new file mode 100644
index 000000000000..900d930d48a8
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/strncmp_test.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021. Huawei Technologies Co., Ltd */
+#include <stdbool.h>
+#include <linux/types.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#define STRNCMP_STR_SZ 8
+
+const char target[STRNCMP_STR_SZ] = "EEEEEEE";
+char str[STRNCMP_STR_SZ];
+int cmp_ret = 0;
+int target_pid = 0;
+
+const char no_str_target[STRNCMP_STR_SZ] = "12345678";
+char writable_target[STRNCMP_STR_SZ];
+unsigned int no_const_str_size = STRNCMP_STR_SZ;
+
+char _license[] SEC("license") = "GPL";
+
+SEC("tp/syscalls/sys_enter_nanosleep")
+int do_strncmp(void *ctx)
+{
+ if ((bpf_get_current_pid_tgid() >> 32) != target_pid)
+ return 0;
+
+ cmp_ret = bpf_strncmp(str, STRNCMP_STR_SZ, target);
+ return 0;
+}
+
+SEC("tp/syscalls/sys_enter_nanosleep")
+int strncmp_bad_not_const_str_size(void *ctx)
+{
+ /* The value of string size is not const, so will fail */
+ cmp_ret = bpf_strncmp(str, no_const_str_size, target);
+ return 0;
+}
+
+SEC("tp/syscalls/sys_enter_nanosleep")
+int strncmp_bad_writable_target(void *ctx)
+{
+ /* Compared target is not read-only, so will fail */
+ cmp_ret = bpf_strncmp(str, STRNCMP_STR_SZ, writable_target);
+ return 0;
+}
+
+SEC("tp/syscalls/sys_enter_nanosleep")
+int strncmp_bad_not_null_term_target(void *ctx)
+{
+ /* Compared target is not null-terminated, so will fail */
+ cmp_ret = bpf_strncmp(str, STRNCMP_STR_SZ, no_str_target);
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_ksyms_btf_write_check.c b/tools/testing/selftests/bpf/progs/test_ksyms_btf_write_check.c
new file mode 100644
index 000000000000..2180c41cd890
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_ksyms_btf_write_check.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Google */
+
+#include "vmlinux.h"
+
+#include <bpf/bpf_helpers.h>
+
+extern const int bpf_prog_active __ksym; /* int type global var. */
+
+SEC("raw_tp/sys_enter")
+int handler(const void *ctx)
+{
+ int *active;
+ __u32 cpu;
+
+ cpu = bpf_get_smp_processor_id();
+ active = (int *)bpf_per_cpu_ptr(&bpf_prog_active, cpu);
+ if (active) {
+ /* Kernel memory obtained from bpf_{per,this}_cpu_ptr
+ * is read-only, should _not_ pass verification.
+ */
+ /* WRITE_ONCE */
+ *(volatile int *)active = -1;
+ }
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_cpp.cpp b/tools/testing/selftests/bpf/test_cpp.cpp
index a8d2e9a87fbf..e00201de2890 100644
--- a/tools/testing/selftests/bpf/test_cpp.cpp
+++ b/tools/testing/selftests/bpf/test_cpp.cpp
@@ -7,9 +7,15 @@
/* do nothing, just make sure we can link successfully */
+static void dump_printf(void *ctx, const char *fmt, va_list args)
+{
+}
+
int main(int argc, char *argv[])
{
+ struct btf_dump_opts opts = { };
struct test_core_extern *skel;
+ struct btf *btf;
/* libbpf.h */
libbpf_set_print(NULL);
@@ -18,7 +24,8 @@ int main(int argc, char *argv[])
bpf_prog_get_fd_by_id(0);
/* btf.h */
- btf__new(NULL, 0);
+ btf = btf__new(NULL, 0);
+ btf_dump__new(btf, dump_printf, nullptr, &opts);
/* BPF skeleton */
skel = test_core_extern__open_and_load();
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index f4cd658bbe00..50f7e74ca0b9 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -23,7 +23,6 @@
#include <bpf/libbpf.h>
#include "bpf_util.h"
-#include "bpf_rlimit.h"
#include "test_maps.h"
#include "testing_helpers.h"
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 296928948bb9..2ecb73a65206 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -4,7 +4,6 @@
#define _GNU_SOURCE
#include "test_progs.h"
#include "cgroup_helpers.h"
-#include "bpf_rlimit.h"
#include <argp.h>
#include <pthread.h>
#include <sched.h>
@@ -1342,7 +1341,6 @@ int main(int argc, char **argv)
/* Use libbpf 1.0 API mode */
libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
-
libbpf_set_print(libbpf_print_fn);
srand(time(NULL));
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 4f1fe8af10a4..76cd903117af 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -41,7 +41,6 @@
# define CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS 1
# endif
#endif
-#include "bpf_rlimit.h"
#include "bpf_rand.h"
#include "bpf_util.h"
#include "test_btf.h"
@@ -701,22 +700,18 @@ static int create_sk_storage_map(void)
static int create_map_timer(void)
{
- struct bpf_create_map_attr attr = {
- .name = "test_map",
- .map_type = BPF_MAP_TYPE_ARRAY,
- .key_size = 4,
- .value_size = 16,
- .max_entries = 1,
+ LIBBPF_OPTS(bpf_map_create_opts, opts,
.btf_key_type_id = 1,
.btf_value_type_id = 5,
- };
+ );
int fd, btf_fd;
btf_fd = load_btf();
if (btf_fd < 0)
return -1;
- attr.btf_fd = btf_fd;
- fd = bpf_create_map_xattr(&attr);
+
+ opts.btf_fd = btf_fd;
+ fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "test_map", 4, 16, 1, &opts);
if (fd < 0)
printf("Failed to create map with timer\n");
return fd;
@@ -1399,6 +1394,9 @@ int main(int argc, char **argv)
return EXIT_FAILURE;
}
+ /* Use libbpf 1.0 API mode */
+ libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
+
bpf_semi_rand_init();
return do_test(unpriv, from, to);
}
diff --git a/tools/testing/selftests/bpf/verifier/btf_ctx_access.c b/tools/testing/selftests/bpf/verifier/btf_ctx_access.c
new file mode 100644
index 000000000000..6340db6b46dc
--- /dev/null
+++ b/tools/testing/selftests/bpf/verifier/btf_ctx_access.c
@@ -0,0 +1,12 @@
+{
+ "btf_ctx_access accept",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 8), /* load 2nd argument value (int pointer) */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_TRACING,
+ .expected_attach_type = BPF_TRACE_FENTRY,
+ .kfunc = "bpf_modify_return_test",
+},
diff --git a/tools/testing/selftests/bpf/vmtest.sh b/tools/testing/selftests/bpf/vmtest.sh
index 5e43c79ddc6e..b3afd43549fa 100755
--- a/tools/testing/selftests/bpf/vmtest.sh
+++ b/tools/testing/selftests/bpf/vmtest.sh
@@ -32,7 +32,7 @@ ROOTFS_IMAGE="root.img"
OUTPUT_DIR="$HOME/.bpf_selftests"
KCONFIG_URL="https://raw.githubusercontent.com/libbpf/libbpf/master/travis-ci/vmtest/configs/config-latest.${ARCH}"
KCONFIG_API_URL="https://api.github.com/repos/libbpf/libbpf/contents/travis-ci/vmtest/configs/config-latest.${ARCH}"
-INDEX_URL="https://raw.githubusercontent.com/libbpf/libbpf/master/travis-ci/vmtest/configs/INDEX"
+INDEX_URL="https://raw.githubusercontent.com/libbpf/ci/master/INDEX"
NUM_COMPILE_JOBS="$(nproc)"
LOG_FILE_BASE="$(date +"bpf_selftests.%Y-%m-%d_%H-%M-%S")"
LOG_FILE="${LOG_FILE_BASE}.log"