diff options
Diffstat (limited to 'tools')
496 files changed, 35887 insertions, 10233 deletions
diff --git a/tools/arch/arc/include/uapi/asm/unistd.h b/tools/arch/arc/include/uapi/asm/unistd.h new file mode 100644 index 000000000000..5eafa1115162 --- /dev/null +++ b/tools/arch/arc/include/uapi/asm/unistd.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/******** no-legacy-syscalls-ABI *******/ + +/* + * Non-typical guard macro to enable inclusion twice in ARCH sys.c + * That is how the Generic syscall wrapper generator works + */ +#if !defined(_UAPI_ASM_ARC_UNISTD_H) || defined(__SYSCALL) +#define _UAPI_ASM_ARC_UNISTD_H + +#define __ARCH_WANT_RENAMEAT +#define __ARCH_WANT_STAT64 +#define __ARCH_WANT_SET_GET_RLIMIT +#define __ARCH_WANT_SYS_EXECVE +#define __ARCH_WANT_SYS_CLONE +#define __ARCH_WANT_SYS_VFORK +#define __ARCH_WANT_SYS_FORK +#define __ARCH_WANT_TIME32_SYSCALLS + +#define sys_mmap2 sys_mmap_pgoff + +#include <asm-generic/unistd.h> + +#define NR_syscalls __NR_syscalls + +/* Generic syscall (fs/filesystems.c - lost in asm-generic/unistd.h */ +#define __NR_sysfs (__NR_arch_specific_syscall + 3) + +/* ARC specific syscall */ +#define __NR_cacheflush (__NR_arch_specific_syscall + 0) +#define __NR_arc_settls (__NR_arch_specific_syscall + 1) +#define __NR_arc_gettls (__NR_arch_specific_syscall + 2) +#define __NR_arc_usr_cmpxchg (__NR_arch_specific_syscall + 4) + +__SYSCALL(__NR_cacheflush, sys_cacheflush) +__SYSCALL(__NR_arc_settls, sys_arc_settls) +__SYSCALL(__NR_arc_gettls, sys_arc_gettls) +__SYSCALL(__NR_arc_usr_cmpxchg, sys_arc_usr_cmpxchg) +__SYSCALL(__NR_sysfs, sys_sysfs) + +#undef __SYSCALL + +#endif diff --git a/tools/arch/arm64/include/asm/barrier.h b/tools/arch/arm64/include/asm/barrier.h index 378c051fa177..3b9b41331c4f 100644 --- a/tools/arch/arm64/include/asm/barrier.h +++ b/tools/arch/arm64/include/asm/barrier.h @@ -14,6 +14,16 @@ #define wmb() asm volatile("dmb ishst" ::: "memory") #define rmb() asm volatile("dmb ishld" ::: "memory") +/* + * Kernel uses dmb variants on arm64 for smp_*() barriers. Pretty much the same + * implementation as above mb()/wmb()/rmb(), though for the latter kernel uses + * dsb. In any case, should above mb()/wmb()/rmb() change, make sure the below + * smp_*() don't. + */ +#define smp_mb() asm volatile("dmb ish" ::: "memory") +#define smp_wmb() asm volatile("dmb ishst" ::: "memory") +#define smp_rmb() asm volatile("dmb ishld" ::: "memory") + #define smp_store_release(p, v) \ do { \ union { typeof(*p) __val; char __c[1]; } __u = \ diff --git a/tools/arch/csky/include/uapi/asm/perf_regs.h b/tools/arch/csky/include/uapi/asm/perf_regs.h new file mode 100644 index 000000000000..ee323d818592 --- /dev/null +++ b/tools/arch/csky/include/uapi/asm/perf_regs.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +// Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. + +#ifndef _ASM_CSKY_PERF_REGS_H +#define _ASM_CSKY_PERF_REGS_H + +/* Index of struct pt_regs */ +enum perf_event_csky_regs { + PERF_REG_CSKY_TLS, + PERF_REG_CSKY_LR, + PERF_REG_CSKY_PC, + PERF_REG_CSKY_SR, + PERF_REG_CSKY_SP, + PERF_REG_CSKY_ORIG_A0, + PERF_REG_CSKY_A0, + PERF_REG_CSKY_A1, + PERF_REG_CSKY_A2, + PERF_REG_CSKY_A3, + PERF_REG_CSKY_REGS0, + PERF_REG_CSKY_REGS1, + PERF_REG_CSKY_REGS2, + PERF_REG_CSKY_REGS3, + PERF_REG_CSKY_REGS4, + PERF_REG_CSKY_REGS5, + PERF_REG_CSKY_REGS6, + PERF_REG_CSKY_REGS7, + PERF_REG_CSKY_REGS8, + PERF_REG_CSKY_REGS9, +#if defined(__CSKYABIV2__) + PERF_REG_CSKY_EXREGS0, + PERF_REG_CSKY_EXREGS1, + PERF_REG_CSKY_EXREGS2, + PERF_REG_CSKY_EXREGS3, + PERF_REG_CSKY_EXREGS4, + PERF_REG_CSKY_EXREGS5, + PERF_REG_CSKY_EXREGS6, + PERF_REG_CSKY_EXREGS7, + PERF_REG_CSKY_EXREGS8, + PERF_REG_CSKY_EXREGS9, + PERF_REG_CSKY_EXREGS10, + PERF_REG_CSKY_EXREGS11, + PERF_REG_CSKY_EXREGS12, + PERF_REG_CSKY_EXREGS13, + PERF_REG_CSKY_EXREGS14, + PERF_REG_CSKY_HI, + PERF_REG_CSKY_LO, + PERF_REG_CSKY_DCSR, +#endif + PERF_REG_CSKY_MAX, +}; +#endif /* _ASM_CSKY_PERF_REGS_H */ diff --git a/tools/arch/hexagon/include/uapi/asm/unistd.h b/tools/arch/hexagon/include/uapi/asm/unistd.h new file mode 100644 index 000000000000..432c4db1b623 --- /dev/null +++ b/tools/arch/hexagon/include/uapi/asm/unistd.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Syscall support for Hexagon + * + * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +/* + * The kernel pulls this unistd.h in three different ways: + * 1. the "normal" way which gets all the __NR defines + * 2. with __SYSCALL defined to produce function declarations + * 3. with __SYSCALL defined to produce syscall table initialization + * See also: syscalltab.c + */ + +#define sys_mmap2 sys_mmap_pgoff +#define __ARCH_WANT_RENAMEAT +#define __ARCH_WANT_STAT64 +#define __ARCH_WANT_SET_GET_RLIMIT +#define __ARCH_WANT_SYS_EXECVE +#define __ARCH_WANT_SYS_CLONE +#define __ARCH_WANT_SYS_VFORK +#define __ARCH_WANT_SYS_FORK +#define __ARCH_WANT_TIME32_SYSCALLS + +#include <asm-generic/unistd.h> diff --git a/tools/arch/riscv/include/uapi/asm/unistd.h b/tools/arch/riscv/include/uapi/asm/unistd.h new file mode 100644 index 000000000000..0e2eeeb1fd27 --- /dev/null +++ b/tools/arch/riscv/include/uapi/asm/unistd.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright (C) 2018 David Abdurachmanov <david.abdurachmanov@gmail.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifdef __LP64__ +#define __ARCH_WANT_NEW_STAT +#define __ARCH_WANT_SET_GET_RLIMIT +#endif /* __LP64__ */ + +#include <asm-generic/unistd.h> + +/* + * Allows the instruction cache to be flushed from userspace. Despite RISC-V + * having a direct 'fence.i' instruction available to userspace (which we + * can't trap!), that's not actually viable when running on Linux because the + * kernel might schedule a process on another hart. There is no way for + * userspace to handle this without invoking the kernel (as it doesn't know the + * thread->hart mappings), so we've defined a RISC-V specific system call to + * flush the instruction cache. + * + * __NR_riscv_flush_icache is defined to flush the instruction cache over an + * address range, with the flush applying to either all threads or just the + * caller. We don't currently do anything with the address range, that's just + * in there for forwards compatibility. + */ +#ifndef __NR_riscv_flush_icache +#define __NR_riscv_flush_icache (__NR_arch_specific_syscall + 15) +#endif +__SYSCALL(__NR_riscv_flush_icache, sys_riscv_flush_icache) diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h index 16511d97e8dc..09652eabe769 100644 --- a/tools/arch/s390/include/uapi/asm/kvm.h +++ b/tools/arch/s390/include/uapi/asm/kvm.h @@ -152,7 +152,8 @@ struct kvm_s390_vm_cpu_subfunc { __u8 pcc[16]; /* with MSA4 */ __u8 ppno[16]; /* with MSA5 */ __u8 kma[16]; /* with MSA8 */ - __u8 reserved[1808]; + __u8 kdsa[16]; /* with MSA9 */ + __u8 reserved[1792]; }; /* kvm attributes for crypto */ diff --git a/tools/arch/x86/include/asm/barrier.h b/tools/arch/x86/include/asm/barrier.h index 58919868473c..0adf295dd5b6 100644 --- a/tools/arch/x86/include/asm/barrier.h +++ b/tools/arch/x86/include/asm/barrier.h @@ -21,9 +21,12 @@ #define rmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory") #define wmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory") #elif defined(__x86_64__) -#define mb() asm volatile("mfence":::"memory") -#define rmb() asm volatile("lfence":::"memory") +#define mb() asm volatile("mfence" ::: "memory") +#define rmb() asm volatile("lfence" ::: "memory") #define wmb() asm volatile("sfence" ::: "memory") +#define smp_rmb() barrier() +#define smp_wmb() barrier() +#define smp_mb() asm volatile("lock; addl $0,-132(%%rsp)" ::: "memory", "cc") #endif #if defined(__x86_64__) diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index dabfcf7c3941..7a0e64ccd6ff 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -381,6 +381,7 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) #define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) #define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2) +#define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3) #define KVM_STATE_NESTED_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_RUN_PENDING 0x00000002 diff --git a/tools/arch/x86/include/uapi/asm/perf_regs.h b/tools/arch/x86/include/uapi/asm/perf_regs.h index f3329cabce5c..ac67bbea10ca 100644 --- a/tools/arch/x86/include/uapi/asm/perf_regs.h +++ b/tools/arch/x86/include/uapi/asm/perf_regs.h @@ -27,8 +27,29 @@ enum perf_event_x86_regs { PERF_REG_X86_R13, PERF_REG_X86_R14, PERF_REG_X86_R15, - + /* These are the limits for the GPRs. */ PERF_REG_X86_32_MAX = PERF_REG_X86_GS + 1, PERF_REG_X86_64_MAX = PERF_REG_X86_R15 + 1, + + /* These all need two bits set because they are 128bit */ + PERF_REG_X86_XMM0 = 32, + PERF_REG_X86_XMM1 = 34, + PERF_REG_X86_XMM2 = 36, + PERF_REG_X86_XMM3 = 38, + PERF_REG_X86_XMM4 = 40, + PERF_REG_X86_XMM5 = 42, + PERF_REG_X86_XMM6 = 44, + PERF_REG_X86_XMM7 = 46, + PERF_REG_X86_XMM8 = 48, + PERF_REG_X86_XMM9 = 50, + PERF_REG_X86_XMM10 = 52, + PERF_REG_X86_XMM11 = 54, + PERF_REG_X86_XMM12 = 56, + PERF_REG_X86_XMM13 = 58, + PERF_REG_X86_XMM14 = 60, + PERF_REG_X86_XMM15 = 62, + + /* These include both GPRs and XMMX registers */ + PERF_REG_X86_XMM_MAX = PERF_REG_X86_XMM15 + 2, }; #endif /* _ASM_X86_PERF_REGS_H */ diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h index f0b0c90dd398..d213ec5c3766 100644 --- a/tools/arch/x86/include/uapi/asm/vmx.h +++ b/tools/arch/x86/include/uapi/asm/vmx.h @@ -146,6 +146,7 @@ #define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1 #define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2 +#define VMX_ABORT_VMCS_CORRUPTED 3 #define VMX_ABORT_LOAD_HOST_MSR_FAIL 4 #endif /* _UAPIVMX_H */ diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index 3b24dc05251c..9d05572370ed 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -257,6 +257,7 @@ ENTRY(__memcpy_mcsafe) /* Copy successful. Return zero */ .L_done_memcpy_trap: xorl %eax, %eax +.L_done: ret ENDPROC(__memcpy_mcsafe) EXPORT_SYMBOL_GPL(__memcpy_mcsafe) @@ -273,7 +274,7 @@ EXPORT_SYMBOL_GPL(__memcpy_mcsafe) addl %edx, %ecx .E_trailing_bytes: mov %ecx, %eax - ret + jmp .L_done /* * For write fault handling, given the destination is unaligned, diff --git a/tools/bpf/bpftool/.gitignore b/tools/bpf/bpftool/.gitignore index 67167e44b726..8248b8dd89d4 100644 --- a/tools/bpf/bpftool/.gitignore +++ b/tools/bpf/bpftool/.gitignore @@ -1,5 +1,5 @@ *.d -bpftool +/bpftool bpftool*.8 bpf-helpers.* FEATURE-DUMP.bpftool diff --git a/tools/bpf/bpftool/Documentation/bpftool-btf.rst b/tools/bpf/bpftool/Documentation/bpftool-btf.rst new file mode 100644 index 000000000000..2dbc1413fabd --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-btf.rst @@ -0,0 +1,222 @@ +================ +bpftool-btf +================ +------------------------------------------------------------------------------- +tool for inspection of BTF data +------------------------------------------------------------------------------- + +:Manual section: 8 + +SYNOPSIS +======== + + **bpftool** [*OPTIONS*] **btf** *COMMAND* + + *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] } + + *COMMANDS* := { **dump** | **help** } + +BTF COMMANDS +============= + +| **bpftool** **btf dump** *BTF_SRC* +| **bpftool** **btf help** +| +| *BTF_SRC* := { **id** *BTF_ID* | **prog** *PROG* | **map** *MAP* [{**key** | **value** | **kv** | **all**}] | **file** *FILE* } +| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } +| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } + +DESCRIPTION +=========== + **bpftool btf dump** *BTF_SRC* + Dump BTF entries from a given *BTF_SRC*. + + When **id** is specified, BTF object with that ID will be + loaded and all its BTF types emitted. + + When **map** is provided, it's expected that map has + associated BTF object with BTF types describing key and + value. It's possible to select whether to dump only BTF + type(s) associated with key (**key**), value (**value**), + both key and value (**kv**), or all BTF types present in + associated BTF object (**all**). If not specified, **kv** + is assumed. + + When **prog** is provided, it's expected that program has + associated BTF object with BTF types. + + When specifying *FILE*, an ELF file is expected, containing + .BTF section with well-defined BTF binary format data, + typically produced by clang or pahole. + + **bpftool btf help** + Print short help message. + +OPTIONS +======= + -h, --help + Print short generic help message (similar to **bpftool help**). + + -V, --version + Print version number (similar to **bpftool version**). + + -j, --json + Generate JSON output. For commands that cannot produce JSON, this + option has no effect. + + -p, --pretty + Generate human-readable JSON output. Implies **-j**. + +EXAMPLES +======== +**# bpftool btf dump id 1226** +:: + + [1] PTR '(anon)' type_id=2 + [2] STRUCT 'dummy_tracepoint_args' size=16 vlen=2 + 'pad' type_id=3 bits_offset=0 + 'sock' type_id=4 bits_offset=64 + [3] INT 'long long unsigned int' size=8 bits_offset=0 nr_bits=64 encoding=(none) + [4] PTR '(anon)' type_id=5 + [5] FWD 'sock' fwd_kind=union + +This gives an example of default output for all supported BTF kinds. + +**$ cat prog.c** +:: + + struct fwd_struct; + + enum my_enum { + VAL1 = 3, + VAL2 = 7, + }; + + typedef struct my_struct my_struct_t; + + struct my_struct { + const unsigned int const_int_field; + int bitfield_field: 4; + char arr_field[16]; + const struct fwd_struct *restrict fwd_field; + enum my_enum enum_field; + volatile my_struct_t *typedef_ptr_field; + }; + + union my_union { + int a; + struct my_struct b; + }; + + struct my_struct struct_global_var __attribute__((section("data_sec"))) = { + .bitfield_field = 3, + .enum_field = VAL1, + }; + int global_var __attribute__((section("data_sec"))) = 7; + + __attribute__((noinline)) + int my_func(union my_union *arg1, int arg2) + { + static int static_var __attribute__((section("data_sec"))) = 123; + static_var++; + return static_var; + } + +**$ bpftool btf dump file prog.o** +:: + + [1] PTR '(anon)' type_id=2 + [2] UNION 'my_union' size=48 vlen=2 + 'a' type_id=3 bits_offset=0 + 'b' type_id=4 bits_offset=0 + [3] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED + [4] STRUCT 'my_struct' size=48 vlen=6 + 'const_int_field' type_id=5 bits_offset=0 + 'bitfield_field' type_id=3 bits_offset=32 bitfield_size=4 + 'arr_field' type_id=8 bits_offset=40 + 'fwd_field' type_id=10 bits_offset=192 + 'enum_field' type_id=14 bits_offset=256 + 'typedef_ptr_field' type_id=15 bits_offset=320 + [5] CONST '(anon)' type_id=6 + [6] INT 'unsigned int' size=4 bits_offset=0 nr_bits=32 encoding=(none) + [7] INT 'char' size=1 bits_offset=0 nr_bits=8 encoding=SIGNED + [8] ARRAY '(anon)' type_id=7 index_type_id=9 nr_elems=16 + [9] INT '__ARRAY_SIZE_TYPE__' size=4 bits_offset=0 nr_bits=32 encoding=(none) + [10] RESTRICT '(anon)' type_id=11 + [11] PTR '(anon)' type_id=12 + [12] CONST '(anon)' type_id=13 + [13] FWD 'fwd_struct' fwd_kind=union + [14] ENUM 'my_enum' size=4 vlen=2 + 'VAL1' val=3 + 'VAL2' val=7 + [15] PTR '(anon)' type_id=16 + [16] VOLATILE '(anon)' type_id=17 + [17] TYPEDEF 'my_struct_t' type_id=4 + [18] FUNC_PROTO '(anon)' ret_type_id=3 vlen=2 + 'arg1' type_id=1 + 'arg2' type_id=3 + [19] FUNC 'my_func' type_id=18 + [20] VAR 'struct_global_var' type_id=4, linkage=global-alloc + [21] VAR 'global_var' type_id=3, linkage=global-alloc + [22] VAR 'my_func.static_var' type_id=3, linkage=static + [23] DATASEC 'data_sec' size=0 vlen=3 + type_id=20 offset=0 size=48 + type_id=21 offset=0 size=4 + type_id=22 offset=52 size=4 + +The following commands print BTF types associated with specified map's key, +value, both key and value, and all BTF types, respectively. By default, both +key and value types will be printed. + +**# bpftool btf dump map id 123 key** + +:: + + [39] TYPEDEF 'u32' type_id=37 + +**# bpftool btf dump map id 123 value** + +:: + + [86] PTR '(anon)' type_id=87 + +**# bpftool btf dump map id 123 kv** + +:: + + [39] TYPEDEF 'u32' type_id=37 + [86] PTR '(anon)' type_id=87 + +**# bpftool btf dump map id 123 all** + +:: + + [1] PTR '(anon)' type_id=0 + . + . + . + [2866] ARRAY '(anon)' type_id=52 index_type_id=51 nr_elems=4 + +All the standard ways to specify map or program are supported: + +**# bpftool btf dump map id 123** + +**# bpftool btf dump map pinned /sys/fs/bpf/map_name** + +**# bpftool btf dump prog id 456** + +**# bpftool btf dump prog tag b88e0a09b1d9759d** + +**# bpftool btf dump prog pinned /sys/fs/bpf/prog_name** + +SEE ALSO +======== + **bpf**\ (2), + **bpf-helpers**\ (7), + **bpftool**\ (8), + **bpftool-map**\ (8), + **bpftool-prog**\ (8), + **bpftool-cgroup**\ (8), + **bpftool-feature**\ (8), + **bpftool-net**\ (8), + **bpftool-perf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst index 9bb9ace54ba8..ac26876389c2 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst @@ -29,7 +29,7 @@ CGROUP COMMANDS | *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } | *ATTACH_TYPE* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** | | **bind4** | **bind6** | **post_bind4** | **post_bind6** | **connect4** | **connect6** | -| **sendmsg4** | **sendmsg6** } +| **sendmsg4** | **sendmsg6** | **sysctl** } | *ATTACH_FLAGS* := { **multi** | **override** } DESCRIPTION @@ -85,7 +85,8 @@ DESCRIPTION **sendmsg4** call to sendto(2), sendmsg(2), sendmmsg(2) for an unconnected udp4 socket (since 4.18); **sendmsg6** call to sendto(2), sendmsg(2), sendmmsg(2) for an - unconnected udp6 socket (since 4.18). + unconnected udp6 socket (since 4.18); + **sysctl** sysctl access (since 5.2). **bpftool cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG* Detach *PROG* from the cgroup *CGROUP* and attach type @@ -99,7 +100,7 @@ OPTIONS -h, --help Print short generic help message (similar to **bpftool help**). - -v, --version + -V, --version Print version number (similar to **bpftool version**). -j, --json @@ -144,4 +145,5 @@ SEE ALSO **bpftool-map**\ (8), **bpftool-feature**\ (8), **bpftool-net**\ (8), - **bpftool-perf**\ (8) + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-feature.rst b/tools/bpf/bpftool/Documentation/bpftool-feature.rst index 82de03dd8f52..14180e887082 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-feature.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-feature.rst @@ -63,7 +63,7 @@ OPTIONS -h, --help Print short generic help message (similar to **bpftool help**). - -v, --version + -V, --version Print version number (similar to **bpftool version**). -j, --json @@ -82,4 +82,5 @@ SEE ALSO **bpftool-map**\ (8), **bpftool-cgroup**\ (8), **bpftool-net**\ (8), - **bpftool-perf**\ (8) + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 5c984ffc9f01..13ef27b39f20 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -135,7 +135,7 @@ OPTIONS -h, --help Print short generic help message (similar to **bpftool help**). - -v, --version + -V, --version Print version number (similar to **bpftool version**). -j, --json @@ -258,4 +258,5 @@ SEE ALSO **bpftool-cgroup**\ (8), **bpftool-feature**\ (8), **bpftool-net**\ (8), - **bpftool-perf**\ (8) + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst index 779dab3650ee..934580850f42 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-net.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst @@ -55,7 +55,7 @@ OPTIONS -h, --help Print short generic help message (similar to **bpftool help**). - -v, --version + -V, --version Print version number (similar to **bpftool version**). -j, --json @@ -143,4 +143,5 @@ SEE ALSO **bpftool-map**\ (8), **bpftool-cgroup**\ (8), **bpftool-feature**\ (8), - **bpftool-perf**\ (8) + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-perf.rst b/tools/bpf/bpftool/Documentation/bpftool-perf.rst index bca5590a80d0..0c7576523a21 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-perf.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-perf.rst @@ -43,7 +43,7 @@ OPTIONS -h, --help Print short generic help message (similar to **bpftool help**). - -v, --version + -V, --version Print version number (similar to **bpftool version**). -j, --json @@ -85,4 +85,5 @@ SEE ALSO **bpftool-map**\ (8), **bpftool-cgroup**\ (8), **bpftool-feature**\ (8), - **bpftool-net**\ (8) + **bpftool-net**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 9386bd6e0396..e8118544d118 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -25,7 +25,7 @@ PROG COMMANDS | **bpftool** **prog dump xlated** *PROG* [{**file** *FILE* | **opcodes** | **visual** | **linum**}] | **bpftool** **prog dump jited** *PROG* [{**file** *FILE* | **opcodes** | **linum**}] | **bpftool** **prog pin** *PROG* *FILE* -| **bpftool** **prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] +| **bpftool** **prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] [**pinmaps** *MAP_DIR*] | **bpftool** **prog attach** *PROG* *ATTACH_TYPE* [*MAP*] | **bpftool** **prog detach** *PROG* *ATTACH_TYPE* [*MAP*] | **bpftool** **prog tracelog** @@ -39,7 +39,8 @@ PROG COMMANDS | **cgroup/sock** | **cgroup/dev** | **lwt_in** | **lwt_out** | **lwt_xmit** | | **lwt_seg6local** | **sockops** | **sk_skb** | **sk_msg** | **lirc_mode2** | | **cgroup/bind4** | **cgroup/bind6** | **cgroup/post_bind4** | **cgroup/post_bind6** | -| **cgroup/connect4** | **cgroup/connect6** | **cgroup/sendmsg4** | **cgroup/sendmsg6** +| **cgroup/connect4** | **cgroup/connect6** | **cgroup/sendmsg4** | **cgroup/sendmsg6** | +| **cgroup/sysctl** | } | *ATTACH_TYPE* := { | **msg_verdict** | **stream_verdict** | **stream_parser** | **flow_dissector** @@ -56,6 +57,14 @@ DESCRIPTION Output will start with program ID followed by program type and zero or more named attributes (depending on kernel version). + Since Linux 5.1 the kernel can collect statistics on BPF + programs (such as the total time spent running the program, + and the number of times it was run). If available, bpftool + shows such statistics. However, the kernel does not collect + them by defaults, as it slightly impacts performance on each + program run. Activation or deactivation of the feature is + performed via the **kernel.bpf_stats_enabled** sysctl knob. + **bpftool prog dump xlated** *PROG* [{ **file** *FILE* | **opcodes** | **visual** | **linum** }] Dump eBPF instructions of the program from the kernel. By default, eBPF will be disassembled and printed to standard @@ -144,7 +153,7 @@ OPTIONS -h, --help Print short generic help message (similar to **bpftool help**). - -v, --version + -V, --version Print version number (similar to **bpftool version**). -j, --json @@ -262,4 +271,5 @@ SEE ALSO **bpftool-cgroup**\ (8), **bpftool-feature**\ (8), **bpftool-net**\ (8), - **bpftool-perf**\ (8) + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst index 4f2188845dd8..3e562d7fd56f 100644 --- a/tools/bpf/bpftool/Documentation/bpftool.rst +++ b/tools/bpf/bpftool/Documentation/bpftool.rst @@ -49,7 +49,7 @@ OPTIONS -h, --help Print short help message (similar to **bpftool help**). - -v, --version + -V, --version Print version number (similar to **bpftool version**). -j, --json @@ -76,4 +76,5 @@ SEE ALSO **bpftool-cgroup**\ (8), **bpftool-feature**\ (8), **bpftool-net**\ (8), - **bpftool-perf**\ (8) + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index b803827d01e8..50e402a5a9c8 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -217,6 +217,7 @@ _bpftool() done cur=${words[cword]} prev=${words[cword - 1]} + pprev=${words[cword - 2]} local object=${words[1]} command=${words[2]} @@ -272,17 +273,17 @@ _bpftool() "$cur" ) ) return 0 ;; - *) - _bpftool_once_attr 'file' - if _bpftool_search_list 'xlated'; then - COMPREPLY+=( $( compgen -W 'opcodes visual linum' -- \ - "$cur" ) ) - else - COMPREPLY+=( $( compgen -W 'opcodes linum' -- \ - "$cur" ) ) - fi - return 0 - ;; + *) + _bpftool_once_attr 'file' + if _bpftool_search_list 'xlated'; then + COMPREPLY+=( $( compgen -W 'opcodes visual linum' -- \ + "$cur" ) ) + else + COMPREPLY+=( $( compgen -W 'opcodes linum' -- \ + "$cur" ) ) + fi + return 0 + ;; esac ;; pin) @@ -370,7 +371,8 @@ _bpftool() lirc_mode2 cgroup/bind4 cgroup/bind6 \ cgroup/connect4 cgroup/connect6 \ cgroup/sendmsg4 cgroup/sendmsg6 \ - cgroup/post_bind4 cgroup/post_bind6" -- \ + cgroup/post_bind4 cgroup/post_bind6 \ + cgroup/sysctl" -- \ "$cur" ) ) return 0 ;; @@ -606,6 +608,51 @@ _bpftool() ;; esac ;; + btf) + local PROG_TYPE='id pinned tag' + local MAP_TYPE='id pinned' + case $command in + dump) + case $prev in + $command) + COMPREPLY+=( $( compgen -W "id map prog file" -- \ + "$cur" ) ) + return 0 + ;; + prog) + COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) ) + return 0 + ;; + map) + COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) + return 0 + ;; + id) + case $pprev in + prog) + _bpftool_get_prog_ids + ;; + map) + _bpftool_get_map_ids + ;; + esac + return 0 + ;; + *) + if [[ $cword == 6 ]] && [[ ${words[3]} == "map" ]]; then + COMPREPLY+=( $( compgen -W 'key value kv all' -- \ + "$cur" ) ) + fi + return 0 + ;; + esac + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'dump help' -- "$cur" ) ) + ;; + esac + ;; cgroup) case $command in show|list) @@ -619,7 +666,7 @@ _bpftool() attach|detach) local ATTACH_TYPES='ingress egress sock_create sock_ops \ device bind4 bind6 post_bind4 post_bind6 connect4 \ - connect6 sendmsg4 sendmsg6' + connect6 sendmsg4 sendmsg6 sysctl' local ATTACH_FLAGS='multi override' local PROG_TYPE='id pinned tag' case $prev in @@ -629,7 +676,7 @@ _bpftool() ;; ingress|egress|sock_create|sock_ops|device|bind4|bind6|\ post_bind4|post_bind6|connect4|connect6|sendmsg4|\ - sendmsg6) + sendmsg6|sysctl) COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \ "$cur" ) ) return 0 diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c new file mode 100644 index 000000000000..7317438ecd9e --- /dev/null +++ b/tools/bpf/bpftool/btf.c @@ -0,0 +1,586 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2019 Facebook */ + +#include <errno.h> +#include <fcntl.h> +#include <linux/err.h> +#include <stdbool.h> +#include <stdio.h> +#include <string.h> +#include <unistd.h> +#include <gelf.h> +#include <bpf.h> +#include <linux/btf.h> + +#include "btf.h" +#include "json_writer.h" +#include "main.h" + +static const char * const btf_kind_str[NR_BTF_KINDS] = { + [BTF_KIND_UNKN] = "UNKNOWN", + [BTF_KIND_INT] = "INT", + [BTF_KIND_PTR] = "PTR", + [BTF_KIND_ARRAY] = "ARRAY", + [BTF_KIND_STRUCT] = "STRUCT", + [BTF_KIND_UNION] = "UNION", + [BTF_KIND_ENUM] = "ENUM", + [BTF_KIND_FWD] = "FWD", + [BTF_KIND_TYPEDEF] = "TYPEDEF", + [BTF_KIND_VOLATILE] = "VOLATILE", + [BTF_KIND_CONST] = "CONST", + [BTF_KIND_RESTRICT] = "RESTRICT", + [BTF_KIND_FUNC] = "FUNC", + [BTF_KIND_FUNC_PROTO] = "FUNC_PROTO", + [BTF_KIND_VAR] = "VAR", + [BTF_KIND_DATASEC] = "DATASEC", +}; + +static const char *btf_int_enc_str(__u8 encoding) +{ + switch (encoding) { + case 0: + return "(none)"; + case BTF_INT_SIGNED: + return "SIGNED"; + case BTF_INT_CHAR: + return "CHAR"; + case BTF_INT_BOOL: + return "BOOL"; + default: + return "UNKN"; + } +} + +static const char *btf_var_linkage_str(__u32 linkage) +{ + switch (linkage) { + case BTF_VAR_STATIC: + return "static"; + case BTF_VAR_GLOBAL_ALLOCATED: + return "global-alloc"; + default: + return "(unknown)"; + } +} + +static const char *btf_str(const struct btf *btf, __u32 off) +{ + if (!off) + return "(anon)"; + return btf__name_by_offset(btf, off) ? : "(invalid)"; +} + +static int dump_btf_type(const struct btf *btf, __u32 id, + const struct btf_type *t) +{ + json_writer_t *w = json_wtr; + int kind, safe_kind; + + kind = BTF_INFO_KIND(t->info); + safe_kind = kind <= BTF_KIND_MAX ? kind : BTF_KIND_UNKN; + + if (json_output) { + jsonw_start_object(w); + jsonw_uint_field(w, "id", id); + jsonw_string_field(w, "kind", btf_kind_str[safe_kind]); + jsonw_string_field(w, "name", btf_str(btf, t->name_off)); + } else { + printf("[%u] %s '%s'", id, btf_kind_str[safe_kind], + btf_str(btf, t->name_off)); + } + + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_INT: { + __u32 v = *(__u32 *)(t + 1); + const char *enc; + + enc = btf_int_enc_str(BTF_INT_ENCODING(v)); + + if (json_output) { + jsonw_uint_field(w, "size", t->size); + jsonw_uint_field(w, "bits_offset", BTF_INT_OFFSET(v)); + jsonw_uint_field(w, "nr_bits", BTF_INT_BITS(v)); + jsonw_string_field(w, "encoding", enc); + } else { + printf(" size=%u bits_offset=%u nr_bits=%u encoding=%s", + t->size, BTF_INT_OFFSET(v), BTF_INT_BITS(v), + enc); + } + break; + } + case BTF_KIND_PTR: + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_TYPEDEF: + if (json_output) + jsonw_uint_field(w, "type_id", t->type); + else + printf(" type_id=%u", t->type); + break; + case BTF_KIND_ARRAY: { + const struct btf_array *arr = (const void *)(t + 1); + + if (json_output) { + jsonw_uint_field(w, "type_id", arr->type); + jsonw_uint_field(w, "index_type_id", arr->index_type); + jsonw_uint_field(w, "nr_elems", arr->nelems); + } else { + printf(" type_id=%u index_type_id=%u nr_elems=%u", + arr->type, arr->index_type, arr->nelems); + } + break; + } + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + const struct btf_member *m = (const void *)(t + 1); + __u16 vlen = BTF_INFO_VLEN(t->info); + int i; + + if (json_output) { + jsonw_uint_field(w, "size", t->size); + jsonw_uint_field(w, "vlen", vlen); + jsonw_name(w, "members"); + jsonw_start_array(w); + } else { + printf(" size=%u vlen=%u", t->size, vlen); + } + for (i = 0; i < vlen; i++, m++) { + const char *name = btf_str(btf, m->name_off); + __u32 bit_off, bit_sz; + + if (BTF_INFO_KFLAG(t->info)) { + bit_off = BTF_MEMBER_BIT_OFFSET(m->offset); + bit_sz = BTF_MEMBER_BITFIELD_SIZE(m->offset); + } else { + bit_off = m->offset; + bit_sz = 0; + } + + if (json_output) { + jsonw_start_object(w); + jsonw_string_field(w, "name", name); + jsonw_uint_field(w, "type_id", m->type); + jsonw_uint_field(w, "bits_offset", bit_off); + if (bit_sz) { + jsonw_uint_field(w, "bitfield_size", + bit_sz); + } + jsonw_end_object(w); + } else { + printf("\n\t'%s' type_id=%u bits_offset=%u", + name, m->type, bit_off); + if (bit_sz) + printf(" bitfield_size=%u", bit_sz); + } + } + if (json_output) + jsonw_end_array(w); + break; + } + case BTF_KIND_ENUM: { + const struct btf_enum *v = (const void *)(t + 1); + __u16 vlen = BTF_INFO_VLEN(t->info); + int i; + + if (json_output) { + jsonw_uint_field(w, "size", t->size); + jsonw_uint_field(w, "vlen", vlen); + jsonw_name(w, "values"); + jsonw_start_array(w); + } else { + printf(" size=%u vlen=%u", t->size, vlen); + } + for (i = 0; i < vlen; i++, v++) { + const char *name = btf_str(btf, v->name_off); + + if (json_output) { + jsonw_start_object(w); + jsonw_string_field(w, "name", name); + jsonw_uint_field(w, "val", v->val); + jsonw_end_object(w); + } else { + printf("\n\t'%s' val=%u", name, v->val); + } + } + if (json_output) + jsonw_end_array(w); + break; + } + case BTF_KIND_FWD: { + const char *fwd_kind = BTF_INFO_KFLAG(t->info) ? "union" + : "struct"; + + if (json_output) + jsonw_string_field(w, "fwd_kind", fwd_kind); + else + printf(" fwd_kind=%s", fwd_kind); + break; + } + case BTF_KIND_FUNC: + if (json_output) + jsonw_uint_field(w, "type_id", t->type); + else + printf(" type_id=%u", t->type); + break; + case BTF_KIND_FUNC_PROTO: { + const struct btf_param *p = (const void *)(t + 1); + __u16 vlen = BTF_INFO_VLEN(t->info); + int i; + + if (json_output) { + jsonw_uint_field(w, "ret_type_id", t->type); + jsonw_uint_field(w, "vlen", vlen); + jsonw_name(w, "params"); + jsonw_start_array(w); + } else { + printf(" ret_type_id=%u vlen=%u", t->type, vlen); + } + for (i = 0; i < vlen; i++, p++) { + const char *name = btf_str(btf, p->name_off); + + if (json_output) { + jsonw_start_object(w); + jsonw_string_field(w, "name", name); + jsonw_uint_field(w, "type_id", p->type); + jsonw_end_object(w); + } else { + printf("\n\t'%s' type_id=%u", name, p->type); + } + } + if (json_output) + jsonw_end_array(w); + break; + } + case BTF_KIND_VAR: { + const struct btf_var *v = (const void *)(t + 1); + const char *linkage; + + linkage = btf_var_linkage_str(v->linkage); + + if (json_output) { + jsonw_uint_field(w, "type_id", t->type); + jsonw_string_field(w, "linkage", linkage); + } else { + printf(" type_id=%u, linkage=%s", t->type, linkage); + } + break; + } + case BTF_KIND_DATASEC: { + const struct btf_var_secinfo *v = (const void *)(t+1); + __u16 vlen = BTF_INFO_VLEN(t->info); + int i; + + if (json_output) { + jsonw_uint_field(w, "size", t->size); + jsonw_uint_field(w, "vlen", vlen); + jsonw_name(w, "vars"); + jsonw_start_array(w); + } else { + printf(" size=%u vlen=%u", t->size, vlen); + } + for (i = 0; i < vlen; i++, v++) { + if (json_output) { + jsonw_start_object(w); + jsonw_uint_field(w, "type_id", v->type); + jsonw_uint_field(w, "offset", v->offset); + jsonw_uint_field(w, "size", v->size); + jsonw_end_object(w); + } else { + printf("\n\ttype_id=%u offset=%u size=%u", + v->type, v->offset, v->size); + } + } + if (json_output) + jsonw_end_array(w); + break; + } + default: + break; + } + + if (json_output) + jsonw_end_object(json_wtr); + else + printf("\n"); + + return 0; +} + +static int dump_btf_raw(const struct btf *btf, + __u32 *root_type_ids, int root_type_cnt) +{ + const struct btf_type *t; + int i; + + if (json_output) { + jsonw_start_object(json_wtr); + jsonw_name(json_wtr, "types"); + jsonw_start_array(json_wtr); + } + + if (root_type_cnt) { + for (i = 0; i < root_type_cnt; i++) { + t = btf__type_by_id(btf, root_type_ids[i]); + dump_btf_type(btf, root_type_ids[i], t); + } + } else { + int cnt = btf__get_nr_types(btf); + + for (i = 1; i <= cnt; i++) { + t = btf__type_by_id(btf, i); + dump_btf_type(btf, i, t); + } + } + + if (json_output) { + jsonw_end_array(json_wtr); + jsonw_end_object(json_wtr); + } + return 0; +} + +static bool check_btf_endianness(GElf_Ehdr *ehdr) +{ + static unsigned int const endian = 1; + + switch (ehdr->e_ident[EI_DATA]) { + case ELFDATA2LSB: + return *(unsigned char const *)&endian == 1; + case ELFDATA2MSB: + return *(unsigned char const *)&endian == 0; + default: + return 0; + } +} + +static int btf_load_from_elf(const char *path, struct btf **btf) +{ + int err = -1, fd = -1, idx = 0; + Elf_Data *btf_data = NULL; + Elf_Scn *scn = NULL; + Elf *elf = NULL; + GElf_Ehdr ehdr; + + if (elf_version(EV_CURRENT) == EV_NONE) { + p_err("failed to init libelf for %s", path); + return -1; + } + + fd = open(path, O_RDONLY); + if (fd < 0) { + p_err("failed to open %s: %s", path, strerror(errno)); + return -1; + } + + elf = elf_begin(fd, ELF_C_READ, NULL); + if (!elf) { + p_err("failed to open %s as ELF file", path); + goto done; + } + if (!gelf_getehdr(elf, &ehdr)) { + p_err("failed to get EHDR from %s", path); + goto done; + } + if (!check_btf_endianness(&ehdr)) { + p_err("non-native ELF endianness is not supported"); + goto done; + } + if (!elf_rawdata(elf_getscn(elf, ehdr.e_shstrndx), NULL)) { + p_err("failed to get e_shstrndx from %s\n", path); + goto done; + } + + while ((scn = elf_nextscn(elf, scn)) != NULL) { + GElf_Shdr sh; + char *name; + + idx++; + if (gelf_getshdr(scn, &sh) != &sh) { + p_err("failed to get section(%d) header from %s", + idx, path); + goto done; + } + name = elf_strptr(elf, ehdr.e_shstrndx, sh.sh_name); + if (!name) { + p_err("failed to get section(%d) name from %s", + idx, path); + goto done; + } + if (strcmp(name, BTF_ELF_SEC) == 0) { + btf_data = elf_getdata(scn, 0); + if (!btf_data) { + p_err("failed to get section(%d, %s) data from %s", + idx, name, path); + goto done; + } + break; + } + } + + if (!btf_data) { + p_err("%s ELF section not found in %s", BTF_ELF_SEC, path); + goto done; + } + + *btf = btf__new(btf_data->d_buf, btf_data->d_size); + if (IS_ERR(*btf)) { + err = PTR_ERR(*btf); + *btf = NULL; + p_err("failed to load BTF data from %s: %s", + path, strerror(err)); + goto done; + } + + err = 0; +done: + if (err) { + if (*btf) { + btf__free(*btf); + *btf = NULL; + } + } + if (elf) + elf_end(elf); + close(fd); + return err; +} + +static int do_dump(int argc, char **argv) +{ + struct btf *btf = NULL; + __u32 root_type_ids[2]; + int root_type_cnt = 0; + __u32 btf_id = -1; + const char *src; + int fd = -1; + int err; + + if (!REQ_ARGS(2)) { + usage(); + return -1; + } + src = GET_ARG(); + + if (is_prefix(src, "map")) { + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + + if (!REQ_ARGS(2)) { + usage(); + return -1; + } + + fd = map_parse_fd_and_info(&argc, &argv, &info, &len); + if (fd < 0) + return -1; + + btf_id = info.btf_id; + if (argc && is_prefix(*argv, "key")) { + root_type_ids[root_type_cnt++] = info.btf_key_type_id; + NEXT_ARG(); + } else if (argc && is_prefix(*argv, "value")) { + root_type_ids[root_type_cnt++] = info.btf_value_type_id; + NEXT_ARG(); + } else if (argc && is_prefix(*argv, "all")) { + NEXT_ARG(); + } else if (argc && is_prefix(*argv, "kv")) { + root_type_ids[root_type_cnt++] = info.btf_key_type_id; + root_type_ids[root_type_cnt++] = info.btf_value_type_id; + NEXT_ARG(); + } else { + root_type_ids[root_type_cnt++] = info.btf_key_type_id; + root_type_ids[root_type_cnt++] = info.btf_value_type_id; + } + } else if (is_prefix(src, "prog")) { + struct bpf_prog_info info = {}; + __u32 len = sizeof(info); + + if (!REQ_ARGS(2)) { + usage(); + return -1; + } + + fd = prog_parse_fd(&argc, &argv); + if (fd < 0) + return -1; + + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err) { + p_err("can't get prog info: %s", strerror(errno)); + goto done; + } + + btf_id = info.btf_id; + } else if (is_prefix(src, "id")) { + char *endptr; + + btf_id = strtoul(*argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as ID", **argv); + return -1; + } + NEXT_ARG(); + } else if (is_prefix(src, "file")) { + err = btf_load_from_elf(*argv, &btf); + if (err) + goto done; + NEXT_ARG(); + } else { + err = -1; + p_err("unrecognized BTF source specifier: '%s'", src); + goto done; + } + + if (!btf) { + err = btf__get_from_id(btf_id, &btf); + if (err) { + p_err("get btf by id (%u): %s", btf_id, strerror(err)); + goto done; + } + if (!btf) { + err = ENOENT; + p_err("can't find btf with ID (%u)", btf_id); + goto done; + } + } + + dump_btf_raw(btf, root_type_ids, root_type_cnt); + +done: + close(fd); + btf__free(btf); + return err; +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %s btf dump BTF_SRC\n" + " %s btf help\n" + "\n" + " BTF_SRC := { id BTF_ID | prog PROG | map MAP [{key | value | kv | all}] | file FILE }\n" + " " HELP_SPEC_MAP "\n" + " " HELP_SPEC_PROGRAM "\n" + " " HELP_SPEC_OPTIONS "\n" + "", + bin_name, bin_name); + + return 0; +} + +static const struct cmd cmds[] = { + { "help", do_help }, + { "dump", do_dump }, + { 0 } +}; + +int do_btf(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c index e63bce0755eb..8cafb9b31467 100644 --- a/tools/bpf/bpftool/btf_dumper.c +++ b/tools/bpf/bpftool/btf_dumper.c @@ -309,6 +309,48 @@ static int btf_dumper_struct(const struct btf_dumper *d, __u32 type_id, return ret; } +static int btf_dumper_var(const struct btf_dumper *d, __u32 type_id, + __u8 bit_offset, const void *data) +{ + const struct btf_type *t = btf__type_by_id(d->btf, type_id); + int ret; + + jsonw_start_object(d->jw); + jsonw_name(d->jw, btf__name_by_offset(d->btf, t->name_off)); + ret = btf_dumper_do_type(d, t->type, bit_offset, data); + jsonw_end_object(d->jw); + + return ret; +} + +static int btf_dumper_datasec(const struct btf_dumper *d, __u32 type_id, + const void *data) +{ + struct btf_var_secinfo *vsi; + const struct btf_type *t; + int ret = 0, i, vlen; + + t = btf__type_by_id(d->btf, type_id); + if (!t) + return -EINVAL; + + vlen = BTF_INFO_VLEN(t->info); + vsi = (struct btf_var_secinfo *)(t + 1); + + jsonw_start_object(d->jw); + jsonw_name(d->jw, btf__name_by_offset(d->btf, t->name_off)); + jsonw_start_array(d->jw); + for (i = 0; i < vlen; i++) { + ret = btf_dumper_do_type(d, vsi[i].type, 0, data + vsi[i].offset); + if (ret) + break; + } + jsonw_end_array(d->jw); + jsonw_end_object(d->jw); + + return ret; +} + static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id, __u8 bit_offset, const void *data) { @@ -341,6 +383,10 @@ static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id, case BTF_KIND_CONST: case BTF_KIND_RESTRICT: return btf_dumper_modifier(d, type_id, bit_offset, data); + case BTF_KIND_VAR: + return btf_dumper_var(d, type_id, bit_offset, data); + case BTF_KIND_DATASEC: + return btf_dumper_datasec(d, type_id, data); default: jsonw_printf(d->jw, "(unsupported-kind"); return -EINVAL; @@ -377,6 +423,7 @@ static int __btf_dumper_type_only(const struct btf *btf, __u32 type_id, { const struct btf_type *proto_type; const struct btf_array *array; + const struct btf_var *var; const struct btf_type *t; if (!type_id) { @@ -440,6 +487,18 @@ static int __btf_dumper_type_only(const struct btf *btf, __u32 type_id, if (pos == -1) return -1; break; + case BTF_KIND_VAR: + var = (struct btf_var *)(t + 1); + if (var->linkage == BTF_VAR_STATIC) + BTF_PRINT_ARG("static "); + BTF_PRINT_TYPE(t->type); + BTF_PRINT_ARG(" %s", + btf__name_by_offset(btf, t->name_off)); + break; + case BTF_KIND_DATASEC: + BTF_PRINT_ARG("section (\"%s\") ", + btf__name_by_offset(btf, t->name_off)); + break; case BTF_KIND_UNKN: default: return -1; diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index 4b5c8da2a7c0..7e22f115c8c1 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -25,7 +25,7 @@ " ATTACH_TYPE := { ingress | egress | sock_create |\n" \ " sock_ops | device | bind4 | bind6 |\n" \ " post_bind4 | post_bind6 | connect4 |\n" \ - " connect6 | sendmsg4 | sendmsg6 }" + " connect6 | sendmsg4 | sendmsg6 | sysctl }" static const char * const attach_type_strings[] = { [BPF_CGROUP_INET_INGRESS] = "ingress", @@ -41,6 +41,7 @@ static const char * const attach_type_strings[] = { [BPF_CGROUP_INET6_POST_BIND] = "post_bind6", [BPF_CGROUP_UDP4_SENDMSG] = "sendmsg4", [BPF_CGROUP_UDP6_SENDMSG] = "sendmsg6", + [BPF_CGROUP_SYSCTL] = "sysctl", [__MAX_BPF_ATTACH_TYPE] = NULL, }; @@ -248,6 +249,13 @@ static int do_show_tree_fn(const char *fpath, const struct stat *sb, for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) show_attached_bpf_progs(cgroup_fd, type, ftw->level); + if (errno == EINVAL) + /* Last attach type does not support query. + * Do not report an error for this, especially because batch + * mode would stop processing commands. + */ + errno = 0; + if (json_output) { jsonw_end_array(json_wtr); jsonw_end_object(json_wtr); diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index a9d5e9e6a732..1ac1fc520e6a 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -56,7 +56,7 @@ static int do_help(int argc, char **argv) " %s batch file FILE\n" " %s version\n" "\n" - " OBJECT := { prog | map | cgroup | perf | net | feature }\n" + " OBJECT := { prog | map | cgroup | perf | net | feature | btf }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, bin_name, bin_name); @@ -188,6 +188,7 @@ static const struct cmd cmds[] = { { "perf", do_perf }, { "net", do_net }, { "feature", do_feature }, + { "btf", do_btf }, { "version", do_version }, { 0 } }; diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index d7dd84d3c660..3d63feb7f852 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -73,6 +73,7 @@ static const char * const prog_type_name[] = { [BPF_PROG_TYPE_LIRC_MODE2] = "lirc_mode2", [BPF_PROG_TYPE_SK_REUSEPORT] = "sk_reuseport", [BPF_PROG_TYPE_FLOW_DISSECTOR] = "flow_dissector", + [BPF_PROG_TYPE_CGROUP_SYSCTL] = "cgroup_sysctl", }; extern const char * const map_type_name[]; @@ -149,6 +150,7 @@ int do_perf(int argc, char **arg); int do_net(int argc, char **arg); int do_tracelog(int argc, char **arg); int do_feature(int argc, char **argv); +int do_btf(int argc, char **argv); int parse_u32_arg(int *argc, char ***argv, __u32 *val, const char *what); int prog_parse_fd(int *argc, char ***argv); diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index e0c650d91784..3ec82904ccec 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -46,6 +46,7 @@ const char * const map_type_name[] = { [BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE] = "percpu_cgroup_storage", [BPF_MAP_TYPE_QUEUE] = "queue", [BPF_MAP_TYPE_STACK] = "stack", + [BPF_MAP_TYPE_SK_STORAGE] = "sk_storage", }; const size_t map_type_name_size = ARRAY_SIZE(map_type_name); @@ -153,11 +154,13 @@ static int do_dump_btf(const struct btf_dumper *d, /* start of key-value pair */ jsonw_start_object(d->jw); - jsonw_name(d->jw, "key"); + if (map_info->btf_key_type_id) { + jsonw_name(d->jw, "key"); - ret = btf_dumper_type(d, map_info->btf_key_type_id, key); - if (ret) - goto err_end_obj; + ret = btf_dumper_type(d, map_info->btf_key_type_id, key); + if (ret) + goto err_end_obj; + } if (!map_is_per_cpu(map_info->type)) { jsonw_name(d->jw, "value"); @@ -259,20 +262,20 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key, } static void print_entry_error(struct bpf_map_info *info, unsigned char *key, - const char *value) + const char *error_msg) { - int value_size = strlen(value); + int msg_size = strlen(error_msg); bool single_line, break_names; - break_names = info->key_size > 16 || value_size > 16; - single_line = info->key_size + value_size <= 24 && !break_names; + break_names = info->key_size > 16 || msg_size > 16; + single_line = info->key_size + msg_size <= 24 && !break_names; printf("key:%c", break_names ? '\n' : ' '); fprint_hex(stdout, key, info->key_size, " "); printf(single_line ? " " : "\n"); - printf("value:%c%s", break_names ? '\n' : ' ', value); + printf("value:%c%s", break_names ? '\n' : ' ', error_msg); printf("\n"); } @@ -296,11 +299,7 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, if (info->value_size) { printf("value:%c", break_names ? '\n' : ' '); - if (value) - fprint_hex(stdout, value, info->value_size, - " "); - else - printf("<no entry>"); + fprint_hex(stdout, value, info->value_size, " "); } printf("\n"); @@ -319,11 +318,8 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, for (i = 0; i < n; i++) { printf("value (CPU %02d):%c", i, info->value_size > 16 ? '\n' : ' '); - if (value) - fprint_hex(stdout, value + i * step, - info->value_size, " "); - else - printf("<no entry>"); + fprint_hex(stdout, value + i * step, + info->value_size, " "); printf("\n"); } } @@ -536,6 +532,9 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) } close(fd); + if (info->btf_id) + jsonw_int_field(json_wtr, "btf_id", info->btf_id); + if (!hash_empty(map_table.table)) { struct pinned_obj *obj; @@ -602,15 +601,19 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) } close(fd); - printf("\n"); if (!hash_empty(map_table.table)) { struct pinned_obj *obj; hash_for_each_possible(map_table.table, obj, hash, info->id) { if (obj->id == info->id) - printf("\tpinned %s\n", obj->path); + printf("\n\tpinned %s", obj->path); } } + + if (info->btf_id) + printf("\n\tbtf_id %d", info->btf_id); + + printf("\n"); return 0; } @@ -720,11 +723,16 @@ static int dump_map_elem(int fd, void *key, void *value, jsonw_string_field(json_wtr, "error", strerror(lookup_errno)); jsonw_end_object(json_wtr); } else { - if (errno == ENOENT) - print_entry_plain(map_info, key, NULL); - else - print_entry_error(map_info, key, - strerror(lookup_errno)); + const char *msg = NULL; + + if (lookup_errno == ENOENT) + msg = "<no entry>"; + else if (lookup_errno == ENOSPC && + map_info->type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) + msg = "<cannot read>"; + + print_entry_error(map_info, key, + msg ? : strerror(lookup_errno)); } return 0; @@ -778,6 +786,10 @@ static int do_dump(int argc, char **argv) } } + if (info.type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY && + info.value_size != 8) + p_info("Warning: cannot read values from %s map with value_size != 8", + map_type_name[info.type]); while (true) { err = bpf_map_get_next_key(fd, prev_key, key); if (err) { @@ -1151,6 +1163,9 @@ static int do_create(int argc, char **argv) return -1; } NEXT_ARG(); + } else { + p_err("unknown arg %s", *argv); + return -1; } } diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c index db0e7de49d49..67e99c56bc88 100644 --- a/tools/bpf/bpftool/net.c +++ b/tools/bpf/bpftool/net.c @@ -3,6 +3,7 @@ #define _GNU_SOURCE #include <errno.h> +#include <fcntl.h> #include <stdlib.h> #include <string.h> #include <unistd.h> @@ -12,6 +13,8 @@ #include <linux/rtnetlink.h> #include <linux/tc_act/tc_bpf.h> #include <sys/socket.h> +#include <sys/stat.h> +#include <sys/types.h> #include <bpf.h> #include <nlattr.h> @@ -48,6 +51,10 @@ struct bpf_filter_t { int ifindex; }; +struct bpf_attach_info { + __u32 flow_dissector_id; +}; + static int dump_link_nlmsg(void *cookie, void *msg, struct nlattr **tb) { struct bpf_netdev_t *netinfo = cookie; @@ -180,8 +187,45 @@ out: return 0; } +static int query_flow_dissector(struct bpf_attach_info *attach_info) +{ + __u32 attach_flags; + __u32 prog_ids[1]; + __u32 prog_cnt; + int err; + int fd; + + fd = open("/proc/self/ns/net", O_RDONLY); + if (fd < 0) { + p_err("can't open /proc/self/ns/net: %d", + strerror(errno)); + return -1; + } + prog_cnt = ARRAY_SIZE(prog_ids); + err = bpf_prog_query(fd, BPF_FLOW_DISSECTOR, 0, + &attach_flags, prog_ids, &prog_cnt); + close(fd); + if (err) { + if (errno == EINVAL) { + /* Older kernel's don't support querying + * flow dissector programs. + */ + errno = 0; + return 0; + } + p_err("can't query prog: %s", strerror(errno)); + return -1; + } + + if (prog_cnt == 1) + attach_info->flow_dissector_id = prog_ids[0]; + + return 0; +} + static int do_show(int argc, char **argv) { + struct bpf_attach_info attach_info = {}; int i, sock, ret, filter_idx = -1; struct bpf_netdev_t dev_array; unsigned int nl_pid; @@ -199,6 +243,10 @@ static int do_show(int argc, char **argv) usage(); } + ret = query_flow_dissector(&attach_info); + if (ret) + return -1; + sock = libbpf_netlink_open(&nl_pid); if (sock < 0) { fprintf(stderr, "failed to open netlink sock\n"); @@ -227,6 +275,12 @@ static int do_show(int argc, char **argv) } NET_END_ARRAY("\n"); } + + NET_START_ARRAY("flow_dissector", "%s:\n"); + if (attach_info.flow_dissector_id > 0) + NET_DUMP_UINT("id", "id %u", attach_info.flow_dissector_id); + NET_END_ARRAY("\n"); + NET_END_OBJECT; if (json_output) jsonw_end_array(json_wtr); diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index d2be5a06c339..26336bad0442 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -249,6 +249,9 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) if (info->nr_map_ids) show_prog_maps(fd, info->nr_map_ids); + if (info->btf_id) + jsonw_int_field(json_wtr, "btf_id", info->btf_id); + if (!hash_empty(prog_table.table)) { struct pinned_obj *obj; @@ -319,6 +322,9 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd) } } + if (info->btf_id) + printf("\n\tbtf_id %d", info->btf_id); + printf("\n"); } @@ -873,6 +879,8 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) } } + set_max_rlimit(); + obj = __bpf_object__open_xattr(&attr, bpf_flags); if (IS_ERR_OR_NULL(obj)) { p_err("failed to open object file"); @@ -952,8 +960,6 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) goto err_close_obj; } - set_max_rlimit(); - err = bpf_object__load(obj); if (err) { p_err("failed to load object file"); @@ -1054,7 +1060,7 @@ static int do_help(int argc, char **argv) " tracepoint | raw_tracepoint | xdp | perf_event | cgroup/skb |\n" " cgroup/sock | cgroup/dev | lwt_in | lwt_out | lwt_xmit |\n" " lwt_seg6local | sockops | sk_skb | sk_msg | lirc_mode2 |\n" - " sk_reuseport | flow_dissector |\n" + " sk_reuseport | flow_dissector | cgroup/sysctl |\n" " cgroup/bind4 | cgroup/bind6 | cgroup/post_bind4 |\n" " cgroup/post_bind6 | cgroup/connect4 | cgroup/connect6 |\n" " cgroup/sendmsg4 | cgroup/sendmsg6 }\n" diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c index 7073dbe1ff27..0bb17bf88b18 100644 --- a/tools/bpf/bpftool/xlated_dumper.c +++ b/tools/bpf/bpftool/xlated_dumper.c @@ -195,6 +195,9 @@ static const char *print_imm(void *private_data, if (insn->src_reg == BPF_PSEUDO_MAP_FD) snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), "map[id:%u]", insn->imm); + else if (insn->src_reg == BPF_PSEUDO_MAP_VALUE) + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "map[id:%u][0]+%u", insn->imm, (insn + 1)->imm); else snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), "0x%llx", (unsigned long long)full_imm); diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 8d3864b061f3..361207387b1b 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -67,6 +67,7 @@ FEATURE_TESTS_BASIC := \ sdt \ setns \ libaio \ + libzstd \ disassembler-four-args # FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list @@ -120,6 +121,7 @@ FEATURE_DISPLAY ?= \ get_cpuid \ bpf \ libaio \ + libzstd \ disassembler-four-args # Set FEATURE_CHECK_(C|LD)FLAGS-all for all FEATURE_TESTS features. diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 7ceb4441b627..4b8244ee65ce 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -62,7 +62,8 @@ FILES= \ test-clang.bin \ test-llvm.bin \ test-llvm-version.bin \ - test-libaio.bin + test-libaio.bin \ + test-libzstd.bin FILES := $(addprefix $(OUTPUT),$(FILES)) @@ -301,6 +302,9 @@ $(OUTPUT)test-clang.bin: $(OUTPUT)test-libaio.bin: $(BUILD) -lrt +$(OUTPUT)test-libzstd.bin: + $(BUILD) -lzstd + ############################### clean: diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c index 7853e6d91090..a59c53705093 100644 --- a/tools/build/feature/test-all.c +++ b/tools/build/feature/test-all.c @@ -182,6 +182,10 @@ # include "test-disassembler-four-args.c" #undef main +#define main main_test_zstd +# include "test-libzstd.c" +#undef main + int main(int argc, char *argv[]) { main_test_libpython(); @@ -224,6 +228,7 @@ int main(int argc, char *argv[]) main_test_libaio(); main_test_reallocarray(); main_test_disassembler_four_args(); + main_test_libzstd(); return 0; } diff --git a/tools/build/feature/test-libzstd.c b/tools/build/feature/test-libzstd.c new file mode 100644 index 000000000000..55268c01b84d --- /dev/null +++ b/tools/build/feature/test-libzstd.c @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <zstd.h> + +int main(void) +{ + ZSTD_CStream *cstream; + + cstream = ZSTD_createCStream(); + ZSTD_freeCStream(cstream); + + return 0; +} diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h index a1a959ba24ff..b0e35eec6499 100644 --- a/tools/include/linux/coresight-pmu.h +++ b/tools/include/linux/coresight-pmu.h @@ -12,11 +12,13 @@ /* ETMv3.5/PTM's ETMCR config bit */ #define ETM_OPT_CYCACC 12 +#define ETM_OPT_CTXTID 14 #define ETM_OPT_TS 28 #define ETM_OPT_RETSTK 29 /* ETMv4 CONFIGR programming bits for the ETM OPTs */ #define ETM4_CFG_BIT_CYCACC 4 +#define ETM4_CFG_BIT_CTXTID 6 #define ETM4_CFG_BIT_TS 11 #define ETM4_CFG_BIT_RETSTK 12 diff --git a/tools/include/linux/filter.h b/tools/include/linux/filter.h index cce0b02c0e28..ca28b6ab8db7 100644 --- a/tools/include/linux/filter.h +++ b/tools/include/linux/filter.h @@ -278,10 +278,29 @@ .off = 0, \ .imm = ((__u64) (IMM)) >> 32 }) +#define BPF_LD_IMM64_RAW_FULL(DST, SRC, OFF1, OFF2, IMM1, IMM2) \ + ((struct bpf_insn) { \ + .code = BPF_LD | BPF_DW | BPF_IMM, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF1, \ + .imm = IMM1 }), \ + ((struct bpf_insn) { \ + .code = 0, /* zero is reserved opcode */ \ + .dst_reg = 0, \ + .src_reg = 0, \ + .off = OFF2, \ + .imm = IMM2 }) + /* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */ #define BPF_LD_MAP_FD(DST, MAP_FD) \ - BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD) + BPF_LD_IMM64_RAW_FULL(DST, BPF_PSEUDO_MAP_FD, 0, 0, \ + MAP_FD, 0) + +#define BPF_LD_MAP_VALUE(DST, MAP_FD, VALUE_OFF) \ + BPF_LD_IMM64_RAW_FULL(DST, BPF_PSEUDO_MAP_VALUE, 0, 0, \ + MAP_FD, VALUE_OFF) /* Relative call */ diff --git a/tools/include/nolibc/nolibc.h b/tools/include/nolibc/nolibc.h index 1708e9f9f8aa..2551e9b71167 100644 --- a/tools/include/nolibc/nolibc.h +++ b/tools/include/nolibc/nolibc.h @@ -1243,6 +1243,200 @@ struct sys_stat_struct { long st_pad4[14]; }; +#elif defined(__riscv) + +#if __riscv_xlen == 64 +#define PTRLOG "3" +#define SZREG "8" +#elif __riscv_xlen == 32 +#define PTRLOG "2" +#define SZREG "4" +#endif + +/* Syscalls for RISCV : + * - stack is 16-byte aligned + * - syscall number is passed in a7 + * - arguments are in a0, a1, a2, a3, a4, a5 + * - the system call is performed by calling ecall + * - syscall return comes in a0 + * - the arguments are cast to long and assigned into the target + * registers which are then simply passed as registers to the asm code, + * so that we don't have to experience issues with register constraints. + */ + +#define my_syscall0(num) \ +({ \ + register long _num asm("a7") = (num); \ + register long _arg1 asm("a0"); \ + \ + asm volatile ( \ + "ecall\n\t" \ + : "=r"(_arg1) \ + : "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall1(num, arg1) \ +({ \ + register long _num asm("a7") = (num); \ + register long _arg1 asm("a0") = (long)(arg1); \ + \ + asm volatile ( \ + "ecall\n" \ + : "+r"(_arg1) \ + : "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + register long _num asm("a7") = (num); \ + register long _arg1 asm("a0") = (long)(arg1); \ + register long _arg2 asm("a1") = (long)(arg2); \ + \ + asm volatile ( \ + "ecall\n" \ + : "+r"(_arg1) \ + : "r"(_arg2), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + register long _num asm("a7") = (num); \ + register long _arg1 asm("a0") = (long)(arg1); \ + register long _arg2 asm("a1") = (long)(arg2); \ + register long _arg3 asm("a2") = (long)(arg3); \ + \ + asm volatile ( \ + "ecall\n\t" \ + : "+r"(_arg1) \ + : "r"(_arg2), "r"(_arg3), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall4(num, arg1, arg2, arg3, arg4) \ +({ \ + register long _num asm("a7") = (num); \ + register long _arg1 asm("a0") = (long)(arg1); \ + register long _arg2 asm("a1") = (long)(arg2); \ + register long _arg3 asm("a2") = (long)(arg3); \ + register long _arg4 asm("a3") = (long)(arg4); \ + \ + asm volatile ( \ + "ecall\n" \ + : "+r"(_arg1) \ + : "r"(_arg2), "r"(_arg3), "r"(_arg4), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + register long _num asm("a7") = (num); \ + register long _arg1 asm("a0") = (long)(arg1); \ + register long _arg2 asm("a1") = (long)(arg2); \ + register long _arg3 asm("a2") = (long)(arg3); \ + register long _arg4 asm("a3") = (long)(arg4); \ + register long _arg5 asm("a4") = (long)(arg5); \ + \ + asm volatile ( \ + "ecall\n" \ + : "+r"(_arg1) \ + : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ +({ \ + register long _num asm("a7") = (num); \ + register long _arg1 asm("a0") = (long)(arg1); \ + register long _arg2 asm("a1") = (long)(arg2); \ + register long _arg3 asm("a2") = (long)(arg3); \ + register long _arg4 asm("a3") = (long)(arg4); \ + register long _arg5 asm("a4") = (long)(arg5); \ + register long _arg6 asm("a5") = (long)(arg6); \ + \ + asm volatile ( \ + "ecall\n" \ + : "+r"(_arg1) \ + : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), "r"(_arg6), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +/* startup code */ +asm(".section .text\n" + ".global _start\n" + "_start:\n" + ".option push\n" + ".option norelax\n" + "lla gp, __global_pointer$\n" + ".option pop\n" + "ld a0, 0(sp)\n" // argc (a0) was in the stack + "add a1, sp, "SZREG"\n" // argv (a1) = sp + "slli a2, a0, "PTRLOG"\n" // envp (a2) = SZREG*argc ... + "add a2, a2, "SZREG"\n" // + SZREG (skip null) + "add a2,a2,a1\n" // + argv + "andi sp,a1,-16\n" // sp must be 16-byte aligned + "call main\n" // main() returns the status code, we'll exit with it. + "andi a0, a0, 0xff\n" // limit exit code to 8 bits + "li a7, 93\n" // NR_exit == 93 + "ecall\n" + ""); + +/* fcntl / open */ +#define O_RDONLY 0 +#define O_WRONLY 1 +#define O_RDWR 2 +#define O_CREAT 0x100 +#define O_EXCL 0x200 +#define O_NOCTTY 0x400 +#define O_TRUNC 0x1000 +#define O_APPEND 0x2000 +#define O_NONBLOCK 0x4000 +#define O_DIRECTORY 0x200000 + +struct sys_stat_struct { + unsigned long st_dev; /* Device. */ + unsigned long st_ino; /* File serial number. */ + unsigned int st_mode; /* File mode. */ + unsigned int st_nlink; /* Link count. */ + unsigned int st_uid; /* User ID of the file's owner. */ + unsigned int st_gid; /* Group ID of the file's group. */ + unsigned long st_rdev; /* Device number, if device. */ + unsigned long __pad1; + long st_size; /* Size of file, in bytes. */ + int st_blksize; /* Optimal block size for I/O. */ + int __pad2; + long st_blocks; /* Number 512-byte blocks allocated. */ + long st_atime; /* Time of last access. */ + unsigned long st_atime_nsec; + long st_mtime; /* Time of last modification. */ + unsigned long st_mtime_nsec; + long st_ctime; /* Time of last status change. */ + unsigned long st_ctime_nsec; + unsigned int __unused4; + unsigned int __unused5; +}; + #endif diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 929c8e537a14..63e0cf66f01a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -105,6 +105,7 @@ enum bpf_cmd { BPF_BTF_GET_FD_BY_ID, BPF_TASK_FD_QUERY, BPF_MAP_LOOKUP_AND_DELETE_ELEM, + BPF_MAP_FREEZE, }; enum bpf_map_type { @@ -132,6 +133,7 @@ enum bpf_map_type { BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, BPF_MAP_TYPE_QUEUE, BPF_MAP_TYPE_STACK, + BPF_MAP_TYPE_SK_STORAGE, }; /* Note that tracing related programs such as @@ -166,6 +168,8 @@ enum bpf_prog_type { BPF_PROG_TYPE_LIRC_MODE2, BPF_PROG_TYPE_SK_REUSEPORT, BPF_PROG_TYPE_FLOW_DISSECTOR, + BPF_PROG_TYPE_CGROUP_SYSCTL, + BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, }; enum bpf_attach_type { @@ -187,6 +191,7 @@ enum bpf_attach_type { BPF_CGROUP_UDP6_SENDMSG, BPF_LIRC_MODE2, BPF_FLOW_DISSECTOR, + BPF_CGROUP_SYSCTL, __MAX_BPF_ATTACH_TYPE }; @@ -255,8 +260,19 @@ enum bpf_attach_type { */ #define BPF_F_ANY_ALIGNMENT (1U << 1) -/* when bpf_ldimm64->src_reg == BPF_PSEUDO_MAP_FD, bpf_ldimm64->imm == fd */ +/* When BPF ldimm64's insn[0].src_reg != 0 then this can have + * two extensions: + * + * insn[0].src_reg: BPF_PSEUDO_MAP_FD BPF_PSEUDO_MAP_VALUE + * insn[0].imm: map fd map fd + * insn[1].imm: 0 offset into value + * insn[0].off: 0 0 + * insn[1].off: 0 0 + * ldimm64 rewrite: address of map address of map[0]+offset + * verifier type: CONST_PTR_TO_MAP PTR_TO_MAP_VALUE + */ #define BPF_PSEUDO_MAP_FD 1 +#define BPF_PSEUDO_MAP_VALUE 2 /* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative * offset to another bpf function @@ -283,7 +299,7 @@ enum bpf_attach_type { #define BPF_OBJ_NAME_LEN 16U -/* Flags for accessing BPF object */ +/* Flags for accessing BPF object from syscall side. */ #define BPF_F_RDONLY (1U << 3) #define BPF_F_WRONLY (1U << 4) @@ -293,6 +309,10 @@ enum bpf_attach_type { /* Zero-initialize hash function seed. This should only be used for testing. */ #define BPF_F_ZERO_SEED (1U << 6) +/* Flags for accessing BPF object from program side. */ +#define BPF_F_RDONLY_PROG (1U << 7) +#define BPF_F_WRONLY_PROG (1U << 8) + /* flags for BPF_PROG_QUERY */ #define BPF_F_QUERY_EFFECTIVE (1U << 0) @@ -396,6 +416,13 @@ union bpf_attr { __aligned_u64 data_out; __u32 repeat; __u32 duration; + __u32 ctx_size_in; /* input: len of ctx_in */ + __u32 ctx_size_out; /* input/output: len of ctx_out + * returns ENOSPC if ctx_out + * is too small. + */ + __aligned_u64 ctx_in; + __aligned_u64 ctx_out; } test; struct { /* anonymous struct used by BPF_*_GET_*_ID */ @@ -602,7 +629,7 @@ union bpf_attr { * **BPF_F_INVALIDATE_HASH** (set *skb*\ **->hash**, *skb*\ * **->swhash** and *skb*\ **->l4hash** to 0). * - * A call to this helper is susceptible to change the underlaying + * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers * previously done by the verifier are invalidated and must be * performed again, if the helper is used in combination with @@ -627,7 +654,7 @@ union bpf_attr { * flexibility and can handle sizes larger than 2 or 4 for the * checksum to update. * - * A call to this helper is susceptible to change the underlaying + * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers * previously done by the verifier are invalidated and must be * performed again, if the helper is used in combination with @@ -659,7 +686,7 @@ union bpf_attr { * flexibility and can handle sizes larger than 2 or 4 for the * checksum to update. * - * A call to this helper is susceptible to change the underlaying + * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers * previously done by the verifier are invalidated and must be * performed again, if the helper is used in combination with @@ -714,7 +741,7 @@ union bpf_attr { * efficient, but it is handled through an action code where the * redirection happens only after the eBPF program has returned. * - * A call to this helper is susceptible to change the underlaying + * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers * previously done by the verifier are invalidated and must be * performed again, if the helper is used in combination with @@ -779,7 +806,7 @@ union bpf_attr { * **ETH_P_8021Q** and **ETH_P_8021AD**, it is considered to * be **ETH_P_8021Q**. * - * A call to this helper is susceptible to change the underlaying + * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers * previously done by the verifier are invalidated and must be * performed again, if the helper is used in combination with @@ -791,7 +818,7 @@ union bpf_attr { * Description * Pop a VLAN header from the packet associated to *skb*. * - * A call to this helper is susceptible to change the underlaying + * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers * previously done by the verifier are invalidated and must be * performed again, if the helper is used in combination with @@ -1141,7 +1168,7 @@ union bpf_attr { * All values for *flags* are reserved for future usage, and must * be left at zero. * - * A call to this helper is susceptible to change the underlaying + * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers * previously done by the verifier are invalidated and must be * performed again, if the helper is used in combination with @@ -1254,7 +1281,7 @@ union bpf_attr { * implicitly linearizes, unclones and drops offloads from the * *skb*. * - * A call to this helper is susceptible to change the underlaying + * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers * previously done by the verifier are invalidated and must be * performed again, if the helper is used in combination with @@ -1290,7 +1317,7 @@ union bpf_attr { * **bpf_skb_pull_data()** to effectively unclone the *skb* from * the very beginning in case it is indeed cloned. * - * A call to this helper is susceptible to change the underlaying + * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers * previously done by the verifier are invalidated and must be * performed again, if the helper is used in combination with @@ -1342,7 +1369,7 @@ union bpf_attr { * All values for *flags* are reserved for future usage, and must * be left at zero. * - * A call to this helper is susceptible to change the underlaying + * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers * previously done by the verifier are invalidated and must be * performed again, if the helper is used in combination with @@ -1357,7 +1384,7 @@ union bpf_attr { * can be used to prepare the packet for pushing or popping * headers. * - * A call to this helper is susceptible to change the underlaying + * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers * previously done by the verifier are invalidated and must be * performed again, if the helper is used in combination with @@ -1478,15 +1505,33 @@ union bpf_attr { * Grow or shrink the room for data in the packet associated to * *skb* by *len_diff*, and according to the selected *mode*. * - * There is a single supported mode at this time: + * There are two supported modes at this time: + * + * * **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer + * (room space is added or removed below the layer 2 header). * * * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer * (room space is added or removed below the layer 3 header). * - * All values for *flags* are reserved for future usage, and must - * be left at zero. + * The following flags are supported at this time: + * + * * **BPF_F_ADJ_ROOM_FIXED_GSO**: Do not adjust gso_size. + * Adjusting mss in this way is not allowed for datagrams. + * + * * **BPF_F_ADJ_ROOM_ENCAP_L3_IPV4**, + * **BPF_F_ADJ_ROOM_ENCAP_L3_IPV6**: + * Any new space is reserved to hold a tunnel header. + * Configure skb offsets and other fields accordingly. + * + * * **BPF_F_ADJ_ROOM_ENCAP_L4_GRE**, + * **BPF_F_ADJ_ROOM_ENCAP_L4_UDP**: + * Use with ENCAP_L3 flags to further specify the tunnel type. + * + * * **BPF_F_ADJ_ROOM_ENCAP_L2**\ (*len*): + * Use with ENCAP_L3/L4 flags to further specify the tunnel + * type; *len* is the length of the inner MAC header. * - * A call to this helper is susceptible to change the underlaying + * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers * previously done by the verifier are invalidated and must be * performed again, if the helper is used in combination with @@ -1565,7 +1610,7 @@ union bpf_attr { * more flexibility as the user is free to store whatever meta * data they need. * - * A call to this helper is susceptible to change the underlaying + * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers * previously done by the verifier are invalidated and must be * performed again, if the helper is used in combination with @@ -1694,12 +1739,19 @@ union bpf_attr { * error if an eBPF program tries to set a callback that is not * supported in the current kernel. * - * The supported callback values that *argval* can combine are: + * *argval* is a flag array which can combine these flags: * * * **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out) * * **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission) * * **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change) * + * Therefore, this function can be used to clear a callback flag by + * setting the appropriate bit to zero. e.g. to disable the RTO + * callback: + * + * **bpf_sock_ops_cb_flags_set(bpf_sock,** + * **bpf_sock->bpf_sock_ops_cb_flags & ~BPF_SOCK_OPS_RTO_CB_FLAG)** + * * Here are some examples of where one could call such eBPF * program: * @@ -1800,7 +1852,7 @@ union bpf_attr { * copied if necessary (i.e. if data was not linear and if start * and end pointers do not point to the same chunk). * - * A call to this helper is susceptible to change the underlaying + * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers * previously done by the verifier are invalidated and must be * performed again, if the helper is used in combination with @@ -1834,7 +1886,7 @@ union bpf_attr { * only possible to shrink the packet as of this writing, * therefore *delta* must be a negative integer. * - * A call to this helper is susceptible to change the underlaying + * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers * previously done by the verifier are invalidated and must be * performed again, if the helper is used in combination with @@ -2009,18 +2061,18 @@ union bpf_attr { * **BPF_LWT_ENCAP_IP** * IP encapsulation (GRE/GUE/IPIP/etc). The outer header * must be IPv4 or IPv6, followed by zero or more - * additional headers, up to LWT_BPF_MAX_HEADROOM total - * bytes in all prepended headers. Please note that - * if skb_is_gso(skb) is true, no more than two headers - * can be prepended, and the inner header, if present, - * should be either GRE or UDP/GUE. - * - * BPF_LWT_ENCAP_SEG6*** types can be called by bpf programs of - * type BPF_PROG_TYPE_LWT_IN; BPF_LWT_ENCAP_IP type can be called - * by bpf programs of types BPF_PROG_TYPE_LWT_IN and - * BPF_PROG_TYPE_LWT_XMIT. - * - * A call to this helper is susceptible to change the underlaying + * additional headers, up to **LWT_BPF_MAX_HEADROOM** + * total bytes in all prepended headers. Please note that + * if **skb_is_gso**\ (*skb*) is true, no more than two + * headers can be prepended, and the inner header, if + * present, should be either GRE or UDP/GUE. + * + * **BPF_LWT_ENCAP_SEG6**\ \* types can be called by BPF programs + * of type **BPF_PROG_TYPE_LWT_IN**; **BPF_LWT_ENCAP_IP** type can + * be called by bpf programs of types **BPF_PROG_TYPE_LWT_IN** and + * **BPF_PROG_TYPE_LWT_XMIT**. + * + * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers * previously done by the verifier are invalidated and must be * performed again, if the helper is used in combination with @@ -2035,7 +2087,7 @@ union bpf_attr { * inside the outermost IPv6 Segment Routing Header can be * modified through this helper. * - * A call to this helper is susceptible to change the underlaying + * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers * previously done by the verifier are invalidated and must be * performed again, if the helper is used in combination with @@ -2051,7 +2103,7 @@ union bpf_attr { * after the segments are accepted. *delta* can be as well * positive (growing) as negative (shrinking). * - * A call to this helper is susceptible to change the underlaying + * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers * previously done by the verifier are invalidated and must be * performed again, if the helper is used in combination with @@ -2074,13 +2126,13 @@ union bpf_attr { * Type of *param*: **int**. * **SEG6_LOCAL_ACTION_END_B6** * End.B6 action: Endpoint bound to an SRv6 policy. - * Type of param: **struct ipv6_sr_hdr**. + * Type of *param*: **struct ipv6_sr_hdr**. * **SEG6_LOCAL_ACTION_END_B6_ENCAP** * End.B6.Encap action: Endpoint bound to an SRv6 * encapsulation policy. - * Type of param: **struct ipv6_sr_hdr**. + * Type of *param*: **struct ipv6_sr_hdr**. * - * A call to this helper is susceptible to change the underlaying + * A call to this helper is susceptible to change the underlying * packet buffer. Therefore, at load time, all checks on pointers * previously done by the verifier are invalidated and must be * performed again, if the helper is used in combination with @@ -2233,7 +2285,8 @@ union bpf_attr { * Return * Pointer to **struct bpf_sock**, or **NULL** in case of failure. * For sockets with reuseport option, the **struct bpf_sock** - * result is from **reuse->socks**\ [] using the hash of the tuple. + * result is from *reuse*\ **->socks**\ [] using the hash of the + * tuple. * * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) * Description @@ -2269,7 +2322,8 @@ union bpf_attr { * Return * Pointer to **struct bpf_sock**, or **NULL** in case of failure. * For sockets with reuseport option, the **struct bpf_sock** - * result is from **reuse->socks**\ [] using the hash of the tuple. + * result is from *reuse*\ **->socks**\ [] using the hash of the + * tuple. * * int bpf_sk_release(struct bpf_sock *sock) * Description @@ -2431,6 +2485,193 @@ union bpf_attr { * Return * A **struct bpf_sock** pointer on success, or **NULL** in * case of failure. + * + * struct bpf_sock *bpf_skc_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) + * Description + * Look for TCP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-**NULL**, released via **bpf_sk_release**\ (). + * + * This function is identical to **bpf_sk_lookup_tcp**\ (), except + * that it also returns timewait or request sockets. Use + * **bpf_sk_fullsock**\ () or **bpf_tcp_sock**\ () to access the + * full structure. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to **struct bpf_sock**, or **NULL** in case of failure. + * For sockets with reuseport option, the **struct bpf_sock** + * result is from *reuse*\ **->socks**\ [] using the hash of the + * tuple. + * + * int bpf_tcp_check_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) + * Description + * Check whether *iph* and *th* contain a valid SYN cookie ACK for + * the listening socket in *sk*. + * + * *iph* points to the start of the IPv4 or IPv6 header, while + * *iph_len* contains **sizeof**\ (**struct iphdr**) or + * **sizeof**\ (**struct ip6hdr**). + * + * *th* points to the start of the TCP header, while *th_len* + * contains **sizeof**\ (**struct tcphdr**). + * + * Return + * 0 if *iph* and *th* are a valid SYN cookie ACK, or a negative + * error otherwise. + * + * int bpf_sysctl_get_name(struct bpf_sysctl *ctx, char *buf, size_t buf_len, u64 flags) + * Description + * Get name of sysctl in /proc/sys/ and copy it into provided by + * program buffer *buf* of size *buf_len*. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * + * If *flags* is zero, full name (e.g. "net/ipv4/tcp_mem") is + * copied. Use **BPF_F_SYSCTL_BASE_NAME** flag to copy base name + * only (e.g. "tcp_mem"). + * Return + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + * + * int bpf_sysctl_get_current_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len) + * Description + * Get current value of sysctl as it is presented in /proc/sys + * (incl. newline, etc), and copy it as a string into provided + * by program buffer *buf* of size *buf_len*. + * + * The whole value is copied, no matter what file position user + * space issued e.g. sys_read at. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * Return + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + * + * **-EINVAL** if current value was unavailable, e.g. because + * sysctl is uninitialized and read returns -EIO for it. + * + * int bpf_sysctl_get_new_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len) + * Description + * Get new value being written by user space to sysctl (before + * the actual write happens) and copy it as a string into + * provided by program buffer *buf* of size *buf_len*. + * + * User space may write new value at file position > 0. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * Return + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + * + * **-EINVAL** if sysctl is being read. + * + * int bpf_sysctl_set_new_value(struct bpf_sysctl *ctx, const char *buf, size_t buf_len) + * Description + * Override new value being written by user space to sysctl with + * value provided by program in buffer *buf* of size *buf_len*. + * + * *buf* should contain a string in same form as provided by user + * space on sysctl write. + * + * User space may write new value at file position > 0. To override + * the whole sysctl value file position should be set to zero. + * Return + * 0 on success. + * + * **-E2BIG** if the *buf_len* is too big. + * + * **-EINVAL** if sysctl is being read. + * + * int bpf_strtol(const char *buf, size_t buf_len, u64 flags, long *res) + * Description + * Convert the initial part of the string from buffer *buf* of + * size *buf_len* to a long integer according to the given base + * and save the result in *res*. + * + * The string may begin with an arbitrary amount of white space + * (as determined by **isspace**\ (3)) followed by a single + * optional '**-**' sign. + * + * Five least significant bits of *flags* encode base, other bits + * are currently unused. + * + * Base must be either 8, 10, 16 or 0 to detect it automatically + * similar to user space **strtol**\ (3). + * Return + * Number of characters consumed on success. Must be positive but + * no more than *buf_len*. + * + * **-EINVAL** if no valid digits were found or unsupported base + * was provided. + * + * **-ERANGE** if resulting value was out of range. + * + * int bpf_strtoul(const char *buf, size_t buf_len, u64 flags, unsigned long *res) + * Description + * Convert the initial part of the string from buffer *buf* of + * size *buf_len* to an unsigned long integer according to the + * given base and save the result in *res*. + * + * The string may begin with an arbitrary amount of white space + * (as determined by **isspace**\ (3)). + * + * Five least significant bits of *flags* encode base, other bits + * are currently unused. + * + * Base must be either 8, 10, 16 or 0 to detect it automatically + * similar to user space **strtoul**\ (3). + * Return + * Number of characters consumed on success. Must be positive but + * no more than *buf_len*. + * + * **-EINVAL** if no valid digits were found or unsupported base + * was provided. + * + * **-ERANGE** if resulting value was out of range. + * + * void *bpf_sk_storage_get(struct bpf_map *map, struct bpf_sock *sk, void *value, u64 flags) + * Description + * Get a bpf-local-storage from a *sk*. + * + * Logically, it could be thought of getting the value from + * a *map* with *sk* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem**\ (*map*, **&**\ *sk*) except this + * helper enforces the key must be a full socket and the map must + * be a **BPF_MAP_TYPE_SK_STORAGE** also. + * + * Underneath, the value is stored locally at *sk* instead of + * the *map*. The *map* is used as the bpf-local-storage + * "type". The bpf-local-storage "type" (i.e. the *map*) is + * searched against all bpf-local-storages residing at *sk*. + * + * An optional *flags* (**BPF_SK_STORAGE_GET_F_CREATE**) can be + * used such that a new bpf-local-storage will be + * created if one does not exist. *value* can be used + * together with **BPF_SK_STORAGE_GET_F_CREATE** to specify + * the initial value of a bpf-local-storage. If *value* is + * **NULL**, the new bpf-local-storage will be zero initialized. + * Return + * A bpf-local-storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf-local-storage. + * + * int bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk) + * Description + * Delete a bpf-local-storage from a *sk*. + * Return + * 0 on success. + * + * **-ENOENT** if the bpf-local-storage cannot be found. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2531,7 +2772,17 @@ union bpf_attr { FN(sk_fullsock), \ FN(tcp_sock), \ FN(skb_ecn_set_ce), \ - FN(get_listener_sock), + FN(get_listener_sock), \ + FN(skc_lookup_tcp), \ + FN(tcp_check_syncookie), \ + FN(sysctl_get_name), \ + FN(sysctl_get_current_value), \ + FN(sysctl_get_new_value), \ + FN(sysctl_set_new_value), \ + FN(strtol), \ + FN(strtoul), \ + FN(sk_storage_get), \ + FN(sk_storage_delete), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -2590,9 +2841,30 @@ enum bpf_func_id { /* Current network namespace */ #define BPF_F_CURRENT_NETNS (-1L) +/* BPF_FUNC_skb_adjust_room flags. */ +#define BPF_F_ADJ_ROOM_FIXED_GSO (1ULL << 0) + +#define BPF_ADJ_ROOM_ENCAP_L2_MASK 0xff +#define BPF_ADJ_ROOM_ENCAP_L2_SHIFT 56 + +#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 (1ULL << 1) +#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 (1ULL << 2) +#define BPF_F_ADJ_ROOM_ENCAP_L4_GRE (1ULL << 3) +#define BPF_F_ADJ_ROOM_ENCAP_L4_UDP (1ULL << 4) +#define BPF_F_ADJ_ROOM_ENCAP_L2(len) (((__u64)len & \ + BPF_ADJ_ROOM_ENCAP_L2_MASK) \ + << BPF_ADJ_ROOM_ENCAP_L2_SHIFT) + +/* BPF_FUNC_sysctl_get_name flags. */ +#define BPF_F_SYSCTL_BASE_NAME (1ULL << 0) + +/* BPF_FUNC_sk_storage_get flags */ +#define BPF_SK_STORAGE_GET_F_CREATE (1ULL << 0) + /* Mode for BPF_FUNC_skb_adjust_room helper. */ enum bpf_adj_room_mode { BPF_ADJ_ROOM_NET, + BPF_ADJ_ROOM_MAC, }; /* Mode for BPF_FUNC_skb_load_bytes_relative helper. */ @@ -3218,4 +3490,14 @@ struct bpf_line_info { struct bpf_spin_lock { __u32 val; }; + +struct bpf_sysctl { + __u32 write; /* Sysctl is being read (= 0) or written (= 1). + * Allows 1,2,4-byte read, but no write. + */ + __u32 file_pos; /* Sysctl file position to read from, write to. + * Allows 1,2,4-byte read an 4-byte write. + */ +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h index 7b7475ef2f17..63ae4a39e58b 100644 --- a/tools/include/uapi/linux/btf.h +++ b/tools/include/uapi/linux/btf.h @@ -39,11 +39,11 @@ struct btf_type { * struct, union and fwd */ __u32 info; - /* "size" is used by INT, ENUM, STRUCT and UNION. + /* "size" is used by INT, ENUM, STRUCT, UNION and DATASEC. * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, - * FUNC and FUNC_PROTO. + * FUNC, FUNC_PROTO and VAR. * "type" is a type_id referring to another type. */ union { @@ -70,8 +70,10 @@ struct btf_type { #define BTF_KIND_RESTRICT 11 /* Restrict */ #define BTF_KIND_FUNC 12 /* Function */ #define BTF_KIND_FUNC_PROTO 13 /* Function Proto */ -#define BTF_KIND_MAX 13 -#define NR_BTF_KINDS 14 +#define BTF_KIND_VAR 14 /* Variable */ +#define BTF_KIND_DATASEC 15 /* Section */ +#define BTF_KIND_MAX BTF_KIND_DATASEC +#define NR_BTF_KINDS (BTF_KIND_MAX + 1) /* For some specific BTF_KIND, "struct btf_type" is immediately * followed by extra data. @@ -81,7 +83,7 @@ struct btf_type { * is the 32 bits arrangement: */ #define BTF_INT_ENCODING(VAL) (((VAL) & 0x0f000000) >> 24) -#define BTF_INT_OFFSET(VAL) (((VAL & 0x00ff0000)) >> 16) +#define BTF_INT_OFFSET(VAL) (((VAL) & 0x00ff0000) >> 16) #define BTF_INT_BITS(VAL) ((VAL) & 0x000000ff) /* Attributes stored in the BTF_INT_ENCODING */ @@ -138,4 +140,26 @@ struct btf_param { __u32 type; }; +enum { + BTF_VAR_STATIC = 0, + BTF_VAR_GLOBAL_ALLOCATED, +}; + +/* BTF_KIND_VAR is followed by a single "struct btf_var" to describe + * additional information related to the variable such as its linkage. + */ +struct btf_var { + __u32 linkage; +}; + +/* BTF_KIND_DATASEC is followed by multiple "struct btf_var_secinfo" + * to describe all BTF_KIND_VAR types it contains along with it's + * in-section offset as well as size. + */ +struct btf_var_secinfo { + __u32 type; + __u32 offset; + __u32 size; +}; + #endif /* _UAPI__LINUX_BTF_H__ */ diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore index 4db74758c674..d9e9dec04605 100644 --- a/tools/lib/bpf/.gitignore +++ b/tools/lib/bpf/.gitignore @@ -1,3 +1,5 @@ libbpf_version.h +libbpf.pc FEATURE-DUMP.libbpf test_libbpf +libbpf.so.* diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 8e7c56e9590f..f91639bf5650 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -3,7 +3,7 @@ BPF_VERSION = 0 BPF_PATCHLEVEL = 0 -BPF_EXTRAVERSION = 2 +BPF_EXTRAVERSION = 3 MAKEFLAGS += --no-print-directory @@ -90,6 +90,7 @@ LIBBPF_VERSION = $(BPF_VERSION).$(BPF_PATCHLEVEL).$(BPF_EXTRAVERSION) LIB_TARGET = libbpf.a libbpf.so.$(LIBBPF_VERSION) LIB_FILE = libbpf.a libbpf.so* +PC_FILE = libbpf.pc # Set compile option CFLAGS ifdef EXTRA_CFLAGS @@ -134,13 +135,14 @@ VERSION_SCRIPT := libbpf.map LIB_TARGET := $(addprefix $(OUTPUT),$(LIB_TARGET)) LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE)) +PC_FILE := $(addprefix $(OUTPUT),$(PC_FILE)) GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN) | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {s++} END{print s}') VERSIONED_SYM_COUNT = $(shell readelf -s --wide $(OUTPUT)libbpf.so | \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l) -CMD_TARGETS = $(LIB_TARGET) +CMD_TARGETS = $(LIB_TARGET) $(PC_FILE) CXX_TEST_TARGET = $(OUTPUT)test_libbpf @@ -187,6 +189,12 @@ $(OUTPUT)libbpf.a: $(BPF_IN) $(OUTPUT)test_libbpf: test_libbpf.cpp $(OUTPUT)libbpf.a $(QUIET_LINK)$(CXX) $(INCLUDES) $^ -lelf -o $@ +$(OUTPUT)libbpf.pc: + $(QUIET_GEN)sed -e "s|@PREFIX@|$(prefix)|" \ + -e "s|@LIBDIR@|$(libdir_SQ)|" \ + -e "s|@VERSION@|$(LIBBPF_VERSION)|" \ + < libbpf.pc.template > $@ + check: check_abi check_abi: $(OUTPUT)libbpf.so @@ -222,9 +230,14 @@ install_headers: $(call do_install,bpf.h,$(prefix)/include/bpf,644); \ $(call do_install,libbpf.h,$(prefix)/include/bpf,644); \ $(call do_install,btf.h,$(prefix)/include/bpf,644); \ + $(call do_install,libbpf_util.h,$(prefix)/include/bpf,644); \ $(call do_install,xsk.h,$(prefix)/include/bpf,644); -install: install_lib +install_pkgconfig: $(PC_FILE) + $(call QUIET_INSTALL, $(PC_FILE)) \ + $(call do_install,$(PC_FILE),$(libdir_SQ)/pkgconfig,644) + +install: install_lib install_pkgconfig ### Cleaning rules @@ -234,7 +247,7 @@ config-clean: clean: $(call QUIET_CLEAN, libbpf) $(RM) $(TARGETS) $(CXX_TEST_TARGET) \ - *.o *~ *.a *.so *.so.$(VERSION) .*.d .*.cmd LIBBPF-CFLAGS + *.o *~ *.a *.so *.so.$(VERSION) .*.d .*.cmd *.pc LIBBPF-CFLAGS $(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 9cd015574e83..c4a48086dc9a 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -46,6 +46,8 @@ # define __NR_bpf 349 # elif defined(__s390__) # define __NR_bpf 351 +# elif defined(__arc__) +# define __NR_bpf 280 # else # error __NR_bpf not defined. libbpf does not support your arch. # endif @@ -79,7 +81,6 @@ static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size) int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr) { - __u32 name_len = create_attr->name ? strlen(create_attr->name) : 0; union bpf_attr attr; memset(&attr, '\0', sizeof(attr)); @@ -89,8 +90,9 @@ int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr) attr.value_size = create_attr->value_size; attr.max_entries = create_attr->max_entries; attr.map_flags = create_attr->map_flags; - memcpy(attr.map_name, create_attr->name, - min(name_len, BPF_OBJ_NAME_LEN - 1)); + if (create_attr->name) + memcpy(attr.map_name, create_attr->name, + min(strlen(create_attr->name), BPF_OBJ_NAME_LEN - 1)); attr.numa_node = create_attr->numa_node; attr.btf_fd = create_attr->btf_fd; attr.btf_key_type_id = create_attr->btf_key_type_id; @@ -155,7 +157,6 @@ int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name, int key_size, int inner_map_fd, int max_entries, __u32 map_flags, int node) { - __u32 name_len = name ? strlen(name) : 0; union bpf_attr attr; memset(&attr, '\0', sizeof(attr)); @@ -166,7 +167,9 @@ int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name, attr.inner_map_fd = inner_map_fd; attr.max_entries = max_entries; attr.map_flags = map_flags; - memcpy(attr.map_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1)); + if (name) + memcpy(attr.map_name, name, + min(strlen(name), BPF_OBJ_NAME_LEN - 1)); if (node >= 0) { attr.map_flags |= BPF_F_NUMA_NODE; @@ -216,18 +219,15 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, void *finfo = NULL, *linfo = NULL; union bpf_attr attr; __u32 log_level; - __u32 name_len; int fd; if (!load_attr || !log_buf != !log_buf_sz) return -EINVAL; log_level = load_attr->log_level; - if (log_level > 2 || (log_level && !log_buf)) + if (log_level > (4 | 2 | 1) || (log_level && !log_buf)) return -EINVAL; - name_len = load_attr->name ? strlen(load_attr->name) : 0; - memset(&attr, 0, sizeof(attr)); attr.prog_type = load_attr->prog_type; attr.expected_attach_type = load_attr->expected_attach_type; @@ -253,8 +253,9 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, attr.line_info_rec_size = load_attr->line_info_rec_size; attr.line_info_cnt = load_attr->line_info_cnt; attr.line_info = ptr_to_u64(load_attr->line_info); - memcpy(attr.prog_name, load_attr->name, - min(name_len, BPF_OBJ_NAME_LEN - 1)); + if (load_attr->name) + memcpy(attr.prog_name, load_attr->name, + min(strlen(load_attr->name), BPF_OBJ_NAME_LEN - 1)); fd = sys_bpf_prog_load(&attr, sizeof(attr)); if (fd >= 0) @@ -429,6 +430,16 @@ int bpf_map_get_next_key(int fd, const void *key, void *next_key) return sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr)); } +int bpf_map_freeze(int fd) +{ + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.map_fd = fd; + + return sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr)); +} + int bpf_obj_pin(int fd, const char *pathname) { union bpf_attr attr; @@ -545,10 +556,15 @@ int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr) attr.test.data_out = ptr_to_u64(test_attr->data_out); attr.test.data_size_in = test_attr->data_size_in; attr.test.data_size_out = test_attr->data_size_out; + attr.test.ctx_in = ptr_to_u64(test_attr->ctx_in); + attr.test.ctx_out = ptr_to_u64(test_attr->ctx_out); + attr.test.ctx_size_in = test_attr->ctx_size_in; + attr.test.ctx_size_out = test_attr->ctx_size_out; attr.test.repeat = test_attr->repeat; ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr)); test_attr->data_size_out = attr.test.data_size_out; + test_attr->ctx_size_out = attr.test.ctx_size_out; test_attr->retval = attr.test.retval; test_attr->duration = attr.test.duration; return ret; diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 6ffdd79bea89..9593fec75652 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -26,6 +26,7 @@ #include <linux/bpf.h> #include <stdbool.h> #include <stddef.h> +#include <stdint.h> #ifdef __cplusplus extern "C" { @@ -92,7 +93,7 @@ struct bpf_load_program_attr { #define MAPS_RELAX_COMPAT 0x01 /* Recommend log buffer size */ -#define BPF_LOG_BUF_SIZE (256 * 1024) +#define BPF_LOG_BUF_SIZE (UINT32_MAX >> 8) /* verifier maximum in kernels <= 5.1 */ LIBBPF_API int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, char *log_buf, size_t log_buf_sz); @@ -117,6 +118,7 @@ LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value); LIBBPF_API int bpf_map_delete_elem(int fd, const void *key); LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key); +LIBBPF_API int bpf_map_freeze(int fd); LIBBPF_API int bpf_obj_pin(int fd, const char *pathname); LIBBPF_API int bpf_obj_get(const char *pathname); LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd, @@ -135,6 +137,11 @@ struct bpf_prog_test_run_attr { * out: length of data_out */ __u32 retval; /* out: return code of the BPF program */ __u32 duration; /* out: average per repetition in ns */ + const void *ctx_in; /* optional */ + __u32 ctx_size_in; + void *ctx_out; /* optional */ + __u32 ctx_size_out; /* in: max length of ctx_out + * out: length of cxt_out */ }; LIBBPF_API int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr); diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index cf119c9b6f27..03348c4d6bd4 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -11,7 +11,7 @@ #include "btf.h" #include "bpf.h" #include "libbpf.h" -#include "libbpf_util.h" +#include "libbpf_internal.h" #define max(a, b) ((a) > (b) ? (a) : (b)) #define min(a, b) ((a) < (b) ? (a) : (b)) @@ -24,6 +24,8 @@ ((k) == BTF_KIND_CONST) || \ ((k) == BTF_KIND_RESTRICT)) +#define IS_VAR(k) ((k) == BTF_KIND_VAR) + static struct btf_type btf_void; struct btf { @@ -212,6 +214,10 @@ static int btf_type_size(struct btf_type *t) return base_size + vlen * sizeof(struct btf_member); case BTF_KIND_FUNC_PROTO: return base_size + vlen * sizeof(struct btf_param); + case BTF_KIND_VAR: + return base_size + sizeof(struct btf_var); + case BTF_KIND_DATASEC: + return base_size + vlen * sizeof(struct btf_var_secinfo); default: pr_debug("Unsupported BTF_KIND:%u\n", BTF_INFO_KIND(t->info)); return -EINVAL; @@ -283,6 +289,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) case BTF_KIND_STRUCT: case BTF_KIND_UNION: case BTF_KIND_ENUM: + case BTF_KIND_DATASEC: size = t->size; goto done; case BTF_KIND_PTR: @@ -292,6 +299,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) case BTF_KIND_VOLATILE: case BTF_KIND_CONST: case BTF_KIND_RESTRICT: + case BTF_KIND_VAR: type_id = t->type; break; case BTF_KIND_ARRAY: @@ -326,7 +334,8 @@ int btf__resolve_type(const struct btf *btf, __u32 type_id) t = btf__type_by_id(btf, type_id); while (depth < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t) && - IS_MODIFIER(BTF_INFO_KIND(t->info))) { + (IS_MODIFIER(BTF_INFO_KIND(t->info)) || + IS_VAR(BTF_INFO_KIND(t->info)))) { type_id = t->type; t = btf__type_by_id(btf, type_id); depth++; @@ -408,6 +417,92 @@ done: return btf; } +static int compare_vsi_off(const void *_a, const void *_b) +{ + const struct btf_var_secinfo *a = _a; + const struct btf_var_secinfo *b = _b; + + return a->offset - b->offset; +} + +static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, + struct btf_type *t) +{ + __u32 size = 0, off = 0, i, vars = BTF_INFO_VLEN(t->info); + const char *name = btf__name_by_offset(btf, t->name_off); + const struct btf_type *t_var; + struct btf_var_secinfo *vsi; + struct btf_var *var; + int ret; + + if (!name) { + pr_debug("No name found in string section for DATASEC kind.\n"); + return -ENOENT; + } + + ret = bpf_object__section_size(obj, name, &size); + if (ret || !size || (t->size && t->size != size)) { + pr_debug("Invalid size for section %s: %u bytes\n", name, size); + return -ENOENT; + } + + t->size = size; + + for (i = 0, vsi = (struct btf_var_secinfo *)(t + 1); + i < vars; i++, vsi++) { + t_var = btf__type_by_id(btf, vsi->type); + var = (struct btf_var *)(t_var + 1); + + if (BTF_INFO_KIND(t_var->info) != BTF_KIND_VAR) { + pr_debug("Non-VAR type seen in section %s\n", name); + return -EINVAL; + } + + if (var->linkage == BTF_VAR_STATIC) + continue; + + name = btf__name_by_offset(btf, t_var->name_off); + if (!name) { + pr_debug("No name found in string section for VAR kind\n"); + return -ENOENT; + } + + ret = bpf_object__variable_offset(obj, name, &off); + if (ret) { + pr_debug("No offset found in symbol table for VAR %s\n", name); + return -ENOENT; + } + + vsi->offset = off; + } + + qsort(t + 1, vars, sizeof(*vsi), compare_vsi_off); + return 0; +} + +int btf__finalize_data(struct bpf_object *obj, struct btf *btf) +{ + int err = 0; + __u32 i; + + for (i = 1; i <= btf->nr_types; i++) { + struct btf_type *t = btf->types[i]; + + /* Loader needs to fix up some of the things compiler + * couldn't get its hands on while emitting BTF. This + * is section size and global variable offset. We use + * the info from the ELF itself for this purpose. + */ + if (BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC) { + err = btf_fixup_datasec(obj, btf, t); + if (err) + break; + } + } + + return err; +} + int btf__load(struct btf *btf) { __u32 log_buf_size = BPF_LOG_BUF_SIZE; @@ -1259,8 +1354,16 @@ static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext, } /* special BTF "void" type is made canonical immediately */ d->map[0] = 0; - for (i = 1; i <= btf->nr_types; i++) - d->map[i] = BTF_UNPROCESSED_ID; + for (i = 1; i <= btf->nr_types; i++) { + struct btf_type *t = d->btf->types[i]; + __u16 kind = BTF_INFO_KIND(t->info); + + /* VAR and DATASEC are never deduped and are self-canonical */ + if (kind == BTF_KIND_VAR || kind == BTF_KIND_DATASEC) + d->map[i] = i; + else + d->map[i] = BTF_UNPROCESSED_ID; + } d->hypot_map = malloc(sizeof(__u32) * (1 + btf->nr_types)); if (!d->hypot_map) { @@ -1851,6 +1954,8 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) case BTF_KIND_UNION: case BTF_KIND_FUNC: case BTF_KIND_FUNC_PROTO: + case BTF_KIND_VAR: + case BTF_KIND_DATASEC: return 0; case BTF_KIND_INT: @@ -2604,6 +2709,7 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) case BTF_KIND_PTR: case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: + case BTF_KIND_VAR: r = btf_dedup_remap_type_id(d, t->type); if (r < 0) return r; @@ -2658,6 +2764,20 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) break; } + case BTF_KIND_DATASEC: { + struct btf_var_secinfo *var = (struct btf_var_secinfo *)(t + 1); + __u16 vlen = BTF_INFO_VLEN(t->info); + + for (i = 0; i < vlen; i++) { + r = btf_dedup_remap_type_id(d, var->type); + if (r < 0) + return r; + var->type = r; + var++; + } + break; + } + default: return -EINVAL; } diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 28a1e1e59861..c7b399e81fce 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -21,6 +21,8 @@ struct btf; struct btf_ext; struct btf_type; +struct bpf_object; + /* * The .BTF.ext ELF section layout defined as * struct btf_ext_header @@ -57,6 +59,7 @@ struct btf_ext_header { LIBBPF_API void btf__free(struct btf *btf); LIBBPF_API struct btf *btf__new(__u8 *data, __u32 size); +LIBBPF_API int btf__finalize_data(struct bpf_object *obj, struct btf *btf); LIBBPF_API int btf__load(struct btf *btf); LIBBPF_API __s32 btf__find_by_name(const struct btf *btf, const char *type_name); diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 11c25d9ea431..197b574406b3 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -7,6 +7,7 @@ * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com> * Copyright (C) 2015 Huawei Inc. * Copyright (C) 2017 Nicira, Inc. + * Copyright (C) 2019 Isovalent, Inc. */ #ifndef _GNU_SOURCE @@ -42,7 +43,7 @@ #include "bpf.h" #include "btf.h" #include "str_error.h" -#include "libbpf_util.h" +#include "libbpf_internal.h" #ifndef EM_BPF #define EM_BPF 247 @@ -52,6 +53,11 @@ #define BPF_FS_MAGIC 0xcafe4a11 #endif +/* vsprintf() in __base_pr() uses nonliteral format string. It may break + * compilation if user enables corresponding warning. Disable it explicitly. + */ +#pragma GCC diagnostic ignored "-Wformat-nonliteral" + #define __printf(a, b) __attribute__((format(printf, a, b))) static int __base_pr(enum libbpf_print_level level, const char *format, @@ -120,6 +126,12 @@ static inline __u64 ptr_to_u64(const void *ptr) struct bpf_capabilities { /* v4.14: kernel support for program & map names. */ __u32 name:1; + /* v5.2: kernel support for global data sections. */ + __u32 global_data:1; + /* BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO support */ + __u32 btf_func:1; + /* BTF_KIND_VAR and BTF_KIND_DATASEC support */ + __u32 btf_datasec:1; }; /* @@ -144,6 +156,7 @@ struct bpf_program { enum { RELO_LD64, RELO_CALL, + RELO_DATA, } type; int insn_idx; union { @@ -152,6 +165,7 @@ struct bpf_program { }; } *reloc_desc; int nr_reloc; + int log_level; struct { int nr; @@ -176,6 +190,19 @@ struct bpf_program { __u32 line_info_cnt; }; +enum libbpf_map_type { + LIBBPF_MAP_UNSPEC, + LIBBPF_MAP_DATA, + LIBBPF_MAP_BSS, + LIBBPF_MAP_RODATA, +}; + +static const char * const libbpf_type_to_btf_name[] = { + [LIBBPF_MAP_DATA] = ".data", + [LIBBPF_MAP_BSS] = ".bss", + [LIBBPF_MAP_RODATA] = ".rodata", +}; + struct bpf_map { int fd; char *name; @@ -187,11 +214,18 @@ struct bpf_map { __u32 btf_value_type_id; void *priv; bpf_map_clear_priv_t clear_priv; + enum libbpf_map_type libbpf_type; +}; + +struct bpf_secdata { + void *rodata; + void *data; }; static LIST_HEAD(bpf_objects_list); struct bpf_object { + char name[BPF_OBJ_NAME_LEN]; char license[64]; __u32 kern_version; @@ -199,6 +233,7 @@ struct bpf_object { size_t nr_programs; struct bpf_map *maps; size_t nr_maps; + struct bpf_secdata sections; bool loaded; bool has_pseudo_calls; @@ -214,6 +249,9 @@ struct bpf_object { Elf *elf; GElf_Ehdr ehdr; Elf_Data *symbols; + Elf_Data *data; + Elf_Data *rodata; + Elf_Data *bss; size_t strtabidx; struct { GElf_Shdr shdr; @@ -222,6 +260,9 @@ struct bpf_object { int nr_reloc; int maps_shndx; int text_shndx; + int data_shndx; + int rodata_shndx; + int bss_shndx; } efile; /* * All loaded bpf_object is linked in a list, which is @@ -443,6 +484,7 @@ static struct bpf_object *bpf_object__new(const char *path, size_t obj_buf_sz) { struct bpf_object *obj; + char *end; obj = calloc(1, sizeof(struct bpf_object) + strlen(path) + 1); if (!obj) { @@ -451,8 +493,14 @@ static struct bpf_object *bpf_object__new(const char *path, } strcpy(obj->path, path); - obj->efile.fd = -1; + /* Using basename() GNU version which doesn't modify arg. */ + strncpy(obj->name, basename((void *)path), + sizeof(obj->name) - 1); + end = strchr(obj->name, '.'); + if (end) + *end = 0; + obj->efile.fd = -1; /* * Caller of this function should also calls * bpf_object__elf_finish() after data collection to return @@ -462,6 +510,9 @@ static struct bpf_object *bpf_object__new(const char *path, obj->efile.obj_buf = obj_buf; obj->efile.obj_buf_sz = obj_buf_sz; obj->efile.maps_shndx = -1; + obj->efile.data_shndx = -1; + obj->efile.rodata_shndx = -1; + obj->efile.bss_shndx = -1; obj->loaded = false; @@ -480,6 +531,9 @@ static void bpf_object__elf_finish(struct bpf_object *obj) obj->efile.elf = NULL; } obj->efile.symbols = NULL; + obj->efile.data = NULL; + obj->efile.rodata = NULL; + obj->efile.bss = NULL; zfree(&obj->efile.reloc); obj->efile.nr_reloc = 0; @@ -621,27 +675,182 @@ static bool bpf_map_type__is_map_in_map(enum bpf_map_type type) return false; } +static int bpf_object_search_section_size(const struct bpf_object *obj, + const char *name, size_t *d_size) +{ + const GElf_Ehdr *ep = &obj->efile.ehdr; + Elf *elf = obj->efile.elf; + Elf_Scn *scn = NULL; + int idx = 0; + + while ((scn = elf_nextscn(elf, scn)) != NULL) { + const char *sec_name; + Elf_Data *data; + GElf_Shdr sh; + + idx++; + if (gelf_getshdr(scn, &sh) != &sh) { + pr_warning("failed to get section(%d) header from %s\n", + idx, obj->path); + return -EIO; + } + + sec_name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name); + if (!sec_name) { + pr_warning("failed to get section(%d) name from %s\n", + idx, obj->path); + return -EIO; + } + + if (strcmp(name, sec_name)) + continue; + + data = elf_getdata(scn, 0); + if (!data) { + pr_warning("failed to get section(%d) data from %s(%s)\n", + idx, name, obj->path); + return -EIO; + } + + *d_size = data->d_size; + return 0; + } + + return -ENOENT; +} + +int bpf_object__section_size(const struct bpf_object *obj, const char *name, + __u32 *size) +{ + int ret = -ENOENT; + size_t d_size; + + *size = 0; + if (!name) { + return -EINVAL; + } else if (!strcmp(name, ".data")) { + if (obj->efile.data) + *size = obj->efile.data->d_size; + } else if (!strcmp(name, ".bss")) { + if (obj->efile.bss) + *size = obj->efile.bss->d_size; + } else if (!strcmp(name, ".rodata")) { + if (obj->efile.rodata) + *size = obj->efile.rodata->d_size; + } else { + ret = bpf_object_search_section_size(obj, name, &d_size); + if (!ret) + *size = d_size; + } + + return *size ? 0 : ret; +} + +int bpf_object__variable_offset(const struct bpf_object *obj, const char *name, + __u32 *off) +{ + Elf_Data *symbols = obj->efile.symbols; + const char *sname; + size_t si; + + if (!name || !off) + return -EINVAL; + + for (si = 0; si < symbols->d_size / sizeof(GElf_Sym); si++) { + GElf_Sym sym; + + if (!gelf_getsym(symbols, si, &sym)) + continue; + if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL || + GELF_ST_TYPE(sym.st_info) != STT_OBJECT) + continue; + + sname = elf_strptr(obj->efile.elf, obj->efile.strtabidx, + sym.st_name); + if (!sname) { + pr_warning("failed to get sym name string for var %s\n", + name); + return -EIO; + } + if (strcmp(name, sname) == 0) { + *off = sym.st_value; + return 0; + } + } + + return -ENOENT; +} + +static bool bpf_object__has_maps(const struct bpf_object *obj) +{ + return obj->efile.maps_shndx >= 0 || + obj->efile.data_shndx >= 0 || + obj->efile.rodata_shndx >= 0 || + obj->efile.bss_shndx >= 0; +} + +static int +bpf_object__init_internal_map(struct bpf_object *obj, struct bpf_map *map, + enum libbpf_map_type type, Elf_Data *data, + void **data_buff) +{ + struct bpf_map_def *def = &map->def; + char map_name[BPF_OBJ_NAME_LEN]; + + map->libbpf_type = type; + map->offset = ~(typeof(map->offset))0; + snprintf(map_name, sizeof(map_name), "%.8s%.7s", obj->name, + libbpf_type_to_btf_name[type]); + map->name = strdup(map_name); + if (!map->name) { + pr_warning("failed to alloc map name\n"); + return -ENOMEM; + } + + def->type = BPF_MAP_TYPE_ARRAY; + def->key_size = sizeof(int); + def->value_size = data->d_size; + def->max_entries = 1; + def->map_flags = type == LIBBPF_MAP_RODATA ? + BPF_F_RDONLY_PROG : 0; + if (data_buff) { + *data_buff = malloc(data->d_size); + if (!*data_buff) { + zfree(&map->name); + pr_warning("failed to alloc map content buffer\n"); + return -ENOMEM; + } + memcpy(*data_buff, data->d_buf, data->d_size); + } + + pr_debug("map %td is \"%s\"\n", map - obj->maps, map->name); + return 0; +} + static int bpf_object__init_maps(struct bpf_object *obj, int flags) { + int i, map_idx, map_def_sz = 0, nr_syms, nr_maps = 0, nr_maps_glob = 0; bool strict = !(flags & MAPS_RELAX_COMPAT); - int i, map_idx, map_def_sz, nr_maps = 0; - Elf_Scn *scn; - Elf_Data *data = NULL; Elf_Data *symbols = obj->efile.symbols; + Elf_Data *data = NULL; + int ret = 0; - if (obj->efile.maps_shndx < 0) - return -EINVAL; if (!symbols) return -EINVAL; + nr_syms = symbols->d_size / sizeof(GElf_Sym); - scn = elf_getscn(obj->efile.elf, obj->efile.maps_shndx); - if (scn) - data = elf_getdata(scn, NULL); - if (!scn || !data) { - pr_warning("failed to get Elf_Data from map section %d\n", - obj->efile.maps_shndx); - return -EINVAL; + if (obj->efile.maps_shndx >= 0) { + Elf_Scn *scn = elf_getscn(obj->efile.elf, + obj->efile.maps_shndx); + + if (scn) + data = elf_getdata(scn, NULL); + if (!scn || !data) { + pr_warning("failed to get Elf_Data from map section %d\n", + obj->efile.maps_shndx); + return -EINVAL; + } } /* @@ -651,7 +860,16 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) * * TODO: Detect array of map and report error. */ - for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) { + if (obj->caps.global_data) { + if (obj->efile.data_shndx >= 0) + nr_maps_glob++; + if (obj->efile.rodata_shndx >= 0) + nr_maps_glob++; + if (obj->efile.bss_shndx >= 0) + nr_maps_glob++; + } + + for (i = 0; data && i < nr_syms; i++) { GElf_Sym sym; if (!gelf_getsym(symbols, i, &sym)) @@ -661,22 +879,24 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) nr_maps++; } - /* Alloc obj->maps and fill nr_maps. */ - pr_debug("maps in %s: %d maps in %zd bytes\n", obj->path, - nr_maps, data->d_size); - - if (!nr_maps) + if (!nr_maps && !nr_maps_glob) return 0; /* Assume equally sized map definitions */ - map_def_sz = data->d_size / nr_maps; - if (!data->d_size || (data->d_size % nr_maps) != 0) { - pr_warning("unable to determine map definition size " - "section %s, %d maps in %zd bytes\n", - obj->path, nr_maps, data->d_size); - return -EINVAL; + if (data) { + pr_debug("maps in %s: %d maps in %zd bytes\n", obj->path, + nr_maps, data->d_size); + + map_def_sz = data->d_size / nr_maps; + if (!data->d_size || (data->d_size % nr_maps) != 0) { + pr_warning("unable to determine map definition size " + "section %s, %d maps in %zd bytes\n", + obj->path, nr_maps, data->d_size); + return -EINVAL; + } } + nr_maps += nr_maps_glob; obj->maps = calloc(nr_maps, sizeof(obj->maps[0])); if (!obj->maps) { pr_warning("alloc maps for object failed\n"); @@ -697,7 +917,7 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) /* * Fill obj->maps using data in "maps" section. */ - for (i = 0, map_idx = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) { + for (i = 0, map_idx = 0; data && i < nr_syms; i++) { GElf_Sym sym; const char *map_name; struct bpf_map_def *def; @@ -710,6 +930,8 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) map_name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, sym.st_name); + + obj->maps[map_idx].libbpf_type = LIBBPF_MAP_UNSPEC; obj->maps[map_idx].offset = sym.st_value; if (sym.st_value + map_def_sz > data->d_size) { pr_warning("corrupted maps section in %s: last map \"%s\" too small\n", @@ -758,8 +980,31 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) map_idx++; } - qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), compare_bpf_map); - return 0; + if (!obj->caps.global_data) + goto finalize; + + /* + * Populate rest of obj->maps with libbpf internal maps. + */ + if (obj->efile.data_shndx >= 0) + ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++], + LIBBPF_MAP_DATA, + obj->efile.data, + &obj->sections.data); + if (!ret && obj->efile.rodata_shndx >= 0) + ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++], + LIBBPF_MAP_RODATA, + obj->efile.rodata, + &obj->sections.rodata); + if (!ret && obj->efile.bss_shndx >= 0) + ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++], + LIBBPF_MAP_BSS, + obj->efile.bss, NULL); +finalize: + if (!ret) + qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), + compare_bpf_map); + return ret; } static bool section_have_execinstr(struct bpf_object *obj, int idx) @@ -780,11 +1025,80 @@ static bool section_have_execinstr(struct bpf_object *obj, int idx) return false; } +static void bpf_object__sanitize_btf(struct bpf_object *obj) +{ + bool has_datasec = obj->caps.btf_datasec; + bool has_func = obj->caps.btf_func; + struct btf *btf = obj->btf; + struct btf_type *t; + int i, j, vlen; + __u16 kind; + + if (!obj->btf || (has_func && has_datasec)) + return; + + for (i = 1; i <= btf__get_nr_types(btf); i++) { + t = (struct btf_type *)btf__type_by_id(btf, i); + kind = BTF_INFO_KIND(t->info); + + if (!has_datasec && kind == BTF_KIND_VAR) { + /* replace VAR with INT */ + t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0); + t->size = sizeof(int); + *(int *)(t+1) = BTF_INT_ENC(0, 0, 32); + } else if (!has_datasec && kind == BTF_KIND_DATASEC) { + /* replace DATASEC with STRUCT */ + struct btf_var_secinfo *v = (void *)(t + 1); + struct btf_member *m = (void *)(t + 1); + struct btf_type *vt; + char *name; + + name = (char *)btf__name_by_offset(btf, t->name_off); + while (*name) { + if (*name == '.') + *name = '_'; + name++; + } + + vlen = BTF_INFO_VLEN(t->info); + t->info = BTF_INFO_ENC(BTF_KIND_STRUCT, 0, vlen); + for (j = 0; j < vlen; j++, v++, m++) { + /* order of field assignments is important */ + m->offset = v->offset * 8; + m->type = v->type; + /* preserve variable name as member name */ + vt = (void *)btf__type_by_id(btf, v->type); + m->name_off = vt->name_off; + } + } else if (!has_func && kind == BTF_KIND_FUNC_PROTO) { + /* replace FUNC_PROTO with ENUM */ + vlen = BTF_INFO_VLEN(t->info); + t->info = BTF_INFO_ENC(BTF_KIND_ENUM, 0, vlen); + t->size = sizeof(__u32); /* kernel enforced */ + } else if (!has_func && kind == BTF_KIND_FUNC) { + /* replace FUNC with TYPEDEF */ + t->info = BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0); + } + } +} + +static void bpf_object__sanitize_btf_ext(struct bpf_object *obj) +{ + if (!obj->btf_ext) + return; + + if (!obj->caps.btf_func) { + btf_ext__free(obj->btf_ext); + obj->btf_ext = NULL; + } +} + static int bpf_object__elf_collect(struct bpf_object *obj, int flags) { Elf *elf = obj->efile.elf; GElf_Ehdr *ep = &obj->efile.ehdr; Elf_Data *btf_ext_data = NULL; + Elf_Data *btf_data = NULL; Elf_Scn *scn = NULL; int idx = 0, err = 0; @@ -828,32 +1142,18 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) (int)sh.sh_link, (unsigned long)sh.sh_flags, (int)sh.sh_type); - if (strcmp(name, "license") == 0) + if (strcmp(name, "license") == 0) { err = bpf_object__init_license(obj, data->d_buf, data->d_size); - else if (strcmp(name, "version") == 0) + } else if (strcmp(name, "version") == 0) { err = bpf_object__init_kversion(obj, data->d_buf, data->d_size); - else if (strcmp(name, "maps") == 0) + } else if (strcmp(name, "maps") == 0) { obj->efile.maps_shndx = idx; - else if (strcmp(name, BTF_ELF_SEC) == 0) { - obj->btf = btf__new(data->d_buf, data->d_size); - if (IS_ERR(obj->btf)) { - pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n", - BTF_ELF_SEC, PTR_ERR(obj->btf)); - obj->btf = NULL; - continue; - } - err = btf__load(obj->btf); - if (err) { - pr_warning("Error loading %s into kernel: %d. Ignored and continue.\n", - BTF_ELF_SEC, err); - btf__free(obj->btf); - obj->btf = NULL; - err = 0; - } + } else if (strcmp(name, BTF_ELF_SEC) == 0) { + btf_data = data; } else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) { btf_ext_data = data; } else if (sh.sh_type == SHT_SYMTAB) { @@ -865,20 +1165,28 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) obj->efile.symbols = data; obj->efile.strtabidx = sh.sh_link; } - } else if ((sh.sh_type == SHT_PROGBITS) && - (sh.sh_flags & SHF_EXECINSTR) && - (data->d_size > 0)) { - if (strcmp(name, ".text") == 0) - obj->efile.text_shndx = idx; - err = bpf_object__add_program(obj, data->d_buf, - data->d_size, name, idx); - if (err) { - char errmsg[STRERR_BUFSIZE]; - char *cp = libbpf_strerror_r(-err, errmsg, - sizeof(errmsg)); - - pr_warning("failed to alloc program %s (%s): %s", - name, obj->path, cp); + } else if (sh.sh_type == SHT_PROGBITS && data->d_size > 0) { + if (sh.sh_flags & SHF_EXECINSTR) { + if (strcmp(name, ".text") == 0) + obj->efile.text_shndx = idx; + err = bpf_object__add_program(obj, data->d_buf, + data->d_size, name, idx); + if (err) { + char errmsg[STRERR_BUFSIZE]; + char *cp = libbpf_strerror_r(-err, errmsg, + sizeof(errmsg)); + + pr_warning("failed to alloc program %s (%s): %s", + name, obj->path, cp); + } + } else if (strcmp(name, ".data") == 0) { + obj->efile.data = data; + obj->efile.data_shndx = idx; + } else if (strcmp(name, ".rodata") == 0) { + obj->efile.rodata = data; + obj->efile.rodata_shndx = idx; + } else { + pr_debug("skip section(%d) %s\n", idx, name); } } else if (sh.sh_type == SHT_REL) { void *reloc = obj->efile.reloc; @@ -906,6 +1214,9 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) obj->efile.reloc[n].shdr = sh; obj->efile.reloc[n].data = data; } + } else if (sh.sh_type == SHT_NOBITS && strcmp(name, ".bss") == 0) { + obj->efile.bss = data; + obj->efile.bss_shndx = idx; } else { pr_debug("skip section(%d) %s\n", idx, name); } @@ -917,6 +1228,27 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) pr_warning("Corrupted ELF file: index of strtab invalid\n"); return LIBBPF_ERRNO__FORMAT; } + if (btf_data) { + obj->btf = btf__new(btf_data->d_buf, btf_data->d_size); + if (IS_ERR(obj->btf)) { + pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n", + BTF_ELF_SEC, PTR_ERR(obj->btf)); + obj->btf = NULL; + } else { + err = btf__finalize_data(obj, obj->btf); + if (!err) { + bpf_object__sanitize_btf(obj); + err = btf__load(obj->btf); + } + if (err) { + pr_warning("Error finalizing and loading %s into kernel: %d. Ignored and continue.\n", + BTF_ELF_SEC, err); + btf__free(obj->btf); + obj->btf = NULL; + err = 0; + } + } + } if (btf_ext_data) { if (!obj->btf) { pr_debug("Ignore ELF section %s because its depending ELF section %s is not found.\n", @@ -929,10 +1261,12 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) BTF_EXT_ELF_SEC, PTR_ERR(obj->btf_ext)); obj->btf_ext = NULL; + } else { + bpf_object__sanitize_btf_ext(obj); } } } - if (obj->efile.maps_shndx >= 0) { + if (bpf_object__has_maps(obj)) { err = bpf_object__init_maps(obj, flags); if (err) goto out; @@ -968,13 +1302,46 @@ bpf_object__find_program_by_title(struct bpf_object *obj, const char *title) return NULL; } +static bool bpf_object__shndx_is_data(const struct bpf_object *obj, + int shndx) +{ + return shndx == obj->efile.data_shndx || + shndx == obj->efile.bss_shndx || + shndx == obj->efile.rodata_shndx; +} + +static bool bpf_object__shndx_is_maps(const struct bpf_object *obj, + int shndx) +{ + return shndx == obj->efile.maps_shndx; +} + +static bool bpf_object__relo_in_known_section(const struct bpf_object *obj, + int shndx) +{ + return shndx == obj->efile.text_shndx || + bpf_object__shndx_is_maps(obj, shndx) || + bpf_object__shndx_is_data(obj, shndx); +} + +static enum libbpf_map_type +bpf_object__section_to_libbpf_map_type(const struct bpf_object *obj, int shndx) +{ + if (shndx == obj->efile.data_shndx) + return LIBBPF_MAP_DATA; + else if (shndx == obj->efile.bss_shndx) + return LIBBPF_MAP_BSS; + else if (shndx == obj->efile.rodata_shndx) + return LIBBPF_MAP_RODATA; + else + return LIBBPF_MAP_UNSPEC; +} + static int bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, Elf_Data *data, struct bpf_object *obj) { Elf_Data *symbols = obj->efile.symbols; - int text_shndx = obj->efile.text_shndx; - int maps_shndx = obj->efile.maps_shndx; struct bpf_map *maps = obj->maps; size_t nr_maps = obj->nr_maps; int i, nrels; @@ -994,7 +1361,10 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, GElf_Sym sym; GElf_Rel rel; unsigned int insn_idx; + unsigned int shdr_idx; struct bpf_insn *insns = prog->insns; + enum libbpf_map_type type; + const char *name; size_t map_idx; if (!gelf_getrel(data, i, &rel)) { @@ -1009,13 +1379,18 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, GELF_R_SYM(rel.r_info)); return -LIBBPF_ERRNO__FORMAT; } - pr_debug("relo for %lld value %lld name %d\n", + + name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, + sym.st_name) ? : "<?>"; + + pr_debug("relo for %lld value %lld name %d (\'%s\')\n", (long long) (rel.r_info >> 32), - (long long) sym.st_value, sym.st_name); + (long long) sym.st_value, sym.st_name, name); - if (sym.st_shndx != maps_shndx && sym.st_shndx != text_shndx) { - pr_warning("Program '%s' contains non-map related relo data pointing to section %u\n", - prog->section_name, sym.st_shndx); + shdr_idx = sym.st_shndx; + if (!bpf_object__relo_in_known_section(obj, shdr_idx)) { + pr_warning("Program '%s' contains unrecognized relo data pointing to section %u\n", + prog->section_name, shdr_idx); return -LIBBPF_ERRNO__RELOC; } @@ -1040,24 +1415,45 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, return -LIBBPF_ERRNO__RELOC; } - /* TODO: 'maps' is sorted. We can use bsearch to make it faster. */ - for (map_idx = 0; map_idx < nr_maps; map_idx++) { - if (maps[map_idx].offset == sym.st_value) { - pr_debug("relocation: find map %zd (%s) for insn %u\n", - map_idx, maps[map_idx].name, insn_idx); - break; + if (bpf_object__shndx_is_maps(obj, shdr_idx) || + bpf_object__shndx_is_data(obj, shdr_idx)) { + type = bpf_object__section_to_libbpf_map_type(obj, shdr_idx); + if (type != LIBBPF_MAP_UNSPEC) { + if (GELF_ST_BIND(sym.st_info) == STB_GLOBAL) { + pr_warning("bpf: relocation: not yet supported relo for non-static global \'%s\' variable found in insns[%d].code 0x%x\n", + name, insn_idx, insns[insn_idx].code); + return -LIBBPF_ERRNO__RELOC; + } + if (!obj->caps.global_data) { + pr_warning("bpf: relocation: kernel does not support global \'%s\' variable access in insns[%d]\n", + name, insn_idx); + return -LIBBPF_ERRNO__RELOC; + } } - } - if (map_idx >= nr_maps) { - pr_warning("bpf relocation: map_idx %d large than %d\n", - (int)map_idx, (int)nr_maps - 1); - return -LIBBPF_ERRNO__RELOC; - } + for (map_idx = 0; map_idx < nr_maps; map_idx++) { + if (maps[map_idx].libbpf_type != type) + continue; + if (type != LIBBPF_MAP_UNSPEC || + (type == LIBBPF_MAP_UNSPEC && + maps[map_idx].offset == sym.st_value)) { + pr_debug("relocation: find map %zd (%s) for insn %u\n", + map_idx, maps[map_idx].name, insn_idx); + break; + } + } - prog->reloc_desc[i].type = RELO_LD64; - prog->reloc_desc[i].insn_idx = insn_idx; - prog->reloc_desc[i].map_idx = map_idx; + if (map_idx >= nr_maps) { + pr_warning("bpf relocation: map_idx %d large than %d\n", + (int)map_idx, (int)nr_maps - 1); + return -LIBBPF_ERRNO__RELOC; + } + + prog->reloc_desc[i].type = type != LIBBPF_MAP_UNSPEC ? + RELO_DATA : RELO_LD64; + prog->reloc_desc[i].insn_idx = insn_idx; + prog->reloc_desc[i].map_idx = map_idx; + } } return 0; } @@ -1065,18 +1461,27 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf) { struct bpf_map_def *def = &map->def; - __u32 key_type_id, value_type_id; + __u32 key_type_id = 0, value_type_id = 0; int ret; - ret = btf__get_map_kv_tids(btf, map->name, def->key_size, - def->value_size, &key_type_id, - &value_type_id); - if (ret) + if (!bpf_map__is_internal(map)) { + ret = btf__get_map_kv_tids(btf, map->name, def->key_size, + def->value_size, &key_type_id, + &value_type_id); + } else { + /* + * LLVM annotates global data differently in BTF, that is, + * only as '.data', '.bss' or '.rodata'. + */ + ret = btf__find_by_name(btf, + libbpf_type_to_btf_name[map->libbpf_type]); + } + if (ret < 0) return ret; map->btf_key_type_id = key_type_id; - map->btf_value_type_id = value_type_id; - + map->btf_value_type_id = bpf_map__is_internal(map) ? + ret : value_type_id; return 0; } @@ -1182,9 +1587,146 @@ bpf_object__probe_name(struct bpf_object *obj) } static int +bpf_object__probe_global_data(struct bpf_object *obj) +{ + struct bpf_load_program_attr prg_attr; + struct bpf_create_map_attr map_attr; + char *cp, errmsg[STRERR_BUFSIZE]; + struct bpf_insn insns[] = { + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int ret, map; + + memset(&map_attr, 0, sizeof(map_attr)); + map_attr.map_type = BPF_MAP_TYPE_ARRAY; + map_attr.key_size = sizeof(int); + map_attr.value_size = 32; + map_attr.max_entries = 1; + + map = bpf_create_map_xattr(&map_attr); + if (map < 0) { + cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + pr_warning("Error in %s():%s(%d). Couldn't create simple array map.\n", + __func__, cp, errno); + return -errno; + } + + insns[0].imm = map; + + memset(&prg_attr, 0, sizeof(prg_attr)); + prg_attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + prg_attr.insns = insns; + prg_attr.insns_cnt = ARRAY_SIZE(insns); + prg_attr.license = "GPL"; + + ret = bpf_load_program_xattr(&prg_attr, NULL, 0); + if (ret >= 0) { + obj->caps.global_data = 1; + close(ret); + } + + close(map); + return 0; +} + +static int bpf_object__probe_btf_func(struct bpf_object *obj) +{ + const char strs[] = "\0int\0x\0a"; + /* void x(int a) {} */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* FUNC_PROTO */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0), + BTF_PARAM_ENC(7, 1), + /* FUNC x */ /* [3] */ + BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), 2), + }; + int res; + + res = libbpf__probe_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs)); + if (res < 0) + return res; + if (res > 0) + obj->caps.btf_func = 1; + return 0; +} + +static int bpf_object__probe_btf_datasec(struct bpf_object *obj) +{ + const char strs[] = "\0x\0.data"; + /* static int a; */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* VAR x */ /* [2] */ + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), + BTF_VAR_STATIC, + /* DATASEC val */ /* [3] */ + BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), + BTF_VAR_SECINFO_ENC(2, 0, 4), + }; + int res; + + res = libbpf__probe_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs)); + if (res < 0) + return res; + if (res > 0) + obj->caps.btf_datasec = 1; + return 0; +} + +static int bpf_object__probe_caps(struct bpf_object *obj) { - return bpf_object__probe_name(obj); + int (*probe_fn[])(struct bpf_object *obj) = { + bpf_object__probe_name, + bpf_object__probe_global_data, + bpf_object__probe_btf_func, + bpf_object__probe_btf_datasec, + }; + int i, ret; + + for (i = 0; i < ARRAY_SIZE(probe_fn); i++) { + ret = probe_fn[i](obj); + if (ret < 0) + pr_debug("Probe #%d failed with %d.\n", i, ret); + } + + return 0; +} + +static int +bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + int err, zero = 0; + __u8 *data; + + /* Nothing to do here since kernel already zero-initializes .bss map. */ + if (map->libbpf_type == LIBBPF_MAP_BSS) + return 0; + + data = map->libbpf_type == LIBBPF_MAP_DATA ? + obj->sections.data : obj->sections.rodata; + + err = bpf_map_update_elem(map->fd, &zero, data, 0); + /* Freeze .rodata map as read-only from syscall side. */ + if (!err && map->libbpf_type == LIBBPF_MAP_RODATA) { + err = bpf_map_freeze(map->fd); + if (err) { + cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + pr_warning("Error freezing map(%s) as read-only: %s\n", + map->name, cp); + err = 0; + } + } + return err; } static int @@ -1244,6 +1786,7 @@ bpf_object__create_maps(struct bpf_object *obj) size_t j; err = *pfd; +err_out: cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); pr_warning("failed to create map (name: '%s'): %s\n", map->name, cp); @@ -1251,6 +1794,15 @@ bpf_object__create_maps(struct bpf_object *obj) zclose(obj->maps[j].fd); return err; } + + if (bpf_map__is_internal(map)) { + err = bpf_object__populate_internal_map(obj, map); + if (err < 0) { + zclose(*pfd); + goto err_out; + } + } + pr_debug("create map %s: fd=%d\n", map->name, *pfd); } @@ -1405,21 +1957,29 @@ bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj) return 0; for (i = 0; i < prog->nr_reloc; i++) { - if (prog->reloc_desc[i].type == RELO_LD64) { + if (prog->reloc_desc[i].type == RELO_LD64 || + prog->reloc_desc[i].type == RELO_DATA) { + bool relo_data = prog->reloc_desc[i].type == RELO_DATA; struct bpf_insn *insns = prog->insns; int insn_idx, map_idx; insn_idx = prog->reloc_desc[i].insn_idx; map_idx = prog->reloc_desc[i].map_idx; - if (insn_idx >= (int)prog->insns_cnt) { + if (insn_idx + 1 >= (int)prog->insns_cnt) { pr_warning("relocation out of range: '%s'\n", prog->section_name); return -LIBBPF_ERRNO__RELOC; } - insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD; + + if (!relo_data) { + insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD; + } else { + insns[insn_idx].src_reg = BPF_PSEUDO_MAP_VALUE; + insns[insn_idx + 1].imm = insns[insn_idx].imm; + } insns[insn_idx].imm = obj->maps[map_idx].fd; - } else { + } else if (prog->reloc_desc[i].type == RELO_CALL) { err = bpf_program__reloc_text(prog, obj, &prog->reloc_desc[i]); if (err) @@ -1494,6 +2054,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, { struct bpf_load_program_attr load_attr; char *cp, errmsg[STRERR_BUFSIZE]; + int log_buf_size = BPF_LOG_BUF_SIZE; char *log_buf; int ret; @@ -1514,21 +2075,30 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, load_attr.line_info = prog->line_info; load_attr.line_info_rec_size = prog->line_info_rec_size; load_attr.line_info_cnt = prog->line_info_cnt; + load_attr.log_level = prog->log_level; if (!load_attr.insns || !load_attr.insns_cnt) return -EINVAL; - log_buf = malloc(BPF_LOG_BUF_SIZE); +retry_load: + log_buf = malloc(log_buf_size); if (!log_buf) pr_warning("Alloc log buffer for bpf loader error, continue without log\n"); - ret = bpf_load_program_xattr(&load_attr, log_buf, BPF_LOG_BUF_SIZE); + ret = bpf_load_program_xattr(&load_attr, log_buf, log_buf_size); if (ret >= 0) { + if (load_attr.log_level) + pr_debug("verifier log:\n%s", log_buf); *pfd = ret; ret = 0; goto out; } + if (errno == ENOSPC) { + log_buf_size <<= 1; + free(log_buf); + goto retry_load; + } ret = -LIBBPF_ERRNO__LOAD; cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); pr_warning("load bpf program failed: %s\n", cp); @@ -1693,7 +2263,9 @@ static bool bpf_prog_type__needs_kver(enum bpf_prog_type type) case BPF_PROG_TYPE_UNSPEC: case BPF_PROG_TYPE_TRACEPOINT: case BPF_PROG_TYPE_RAW_TRACEPOINT: + case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: case BPF_PROG_TYPE_PERF_EVENT: + case BPF_PROG_TYPE_CGROUP_SYSCTL: return false; case BPF_PROG_TYPE_KPROBE: default: @@ -1729,6 +2301,7 @@ __bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz, CHECK_ERR(bpf_object__elf_init(obj), err, out); CHECK_ERR(bpf_object__check_endianness(obj), err, out); + CHECK_ERR(bpf_object__probe_caps(obj), err, out); CHECK_ERR(bpf_object__elf_collect(obj, flags), err, out); CHECK_ERR(bpf_object__collect_reloc(obj), err, out); CHECK_ERR(bpf_object__validate(obj, needs_kver), err, out); @@ -1822,7 +2395,6 @@ int bpf_object__load(struct bpf_object *obj) obj->loaded = true; - CHECK_ERR(bpf_object__probe_caps(obj), err, out); CHECK_ERR(bpf_object__create_maps(obj), err, out); CHECK_ERR(bpf_object__relocate(obj), err, out); CHECK_ERR(bpf_object__load_progs(obj), err, out); @@ -2303,6 +2875,9 @@ void bpf_object__close(struct bpf_object *obj) obj->maps[i].priv = NULL; obj->maps[i].clear_priv = NULL; } + + zfree(&obj->sections.rodata); + zfree(&obj->sections.data); zfree(&obj->maps); obj->nr_maps = 0; @@ -2631,6 +3206,8 @@ static const struct { BPF_CGROUP_UDP4_SENDMSG), BPF_EAPROG_SEC("cgroup/sendmsg6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_SENDMSG), + BPF_EAPROG_SEC("cgroup/sysctl", BPF_PROG_TYPE_CGROUP_SYSCTL, + BPF_CGROUP_SYSCTL), }; #undef BPF_PROG_SEC_IMPL @@ -2780,6 +3357,11 @@ bool bpf_map__is_offload_neutral(struct bpf_map *map) return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY; } +bool bpf_map__is_internal(struct bpf_map *map) +{ + return map->libbpf_type != LIBBPF_MAP_UNSPEC; +} + void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex) { map->map_ifindex = ifindex; @@ -2938,6 +3520,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, bpf_program__set_expected_attach_type(prog, expected_attach_type); + prog->log_level = attr->log_level; if (!first_prog) first_prog = prog; } diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index c70785cc8ef5..c5ff00515ce7 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -75,6 +75,10 @@ struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr, LIBBPF_API struct bpf_object *bpf_object__open_buffer(void *obj_buf, size_t obj_buf_sz, const char *name); +int bpf_object__section_size(const struct bpf_object *obj, const char *name, + __u32 *size); +int bpf_object__variable_offset(const struct bpf_object *obj, const char *name, + __u32 *off); LIBBPF_API int bpf_object__pin_maps(struct bpf_object *obj, const char *path); LIBBPF_API int bpf_object__unpin_maps(struct bpf_object *obj, const char *path); @@ -301,6 +305,7 @@ LIBBPF_API void *bpf_map__priv(struct bpf_map *map); LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd); LIBBPF_API int bpf_map__resize(struct bpf_map *map, __u32 max_entries); LIBBPF_API bool bpf_map__is_offload_neutral(struct bpf_map *map); +LIBBPF_API bool bpf_map__is_internal(struct bpf_map *map); LIBBPF_API void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex); LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path); LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path); @@ -314,6 +319,7 @@ struct bpf_prog_load_attr { enum bpf_prog_type prog_type; enum bpf_attach_type expected_attach_type; int ifindex; + int log_level; }; LIBBPF_API int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index f3ce50500cf2..673001787cba 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -157,3 +157,10 @@ LIBBPF_0.0.2 { bpf_program__bpil_addr_to_offs; bpf_program__bpil_offs_to_addr; } LIBBPF_0.0.1; + +LIBBPF_0.0.3 { + global: + bpf_map__is_internal; + bpf_map_freeze; + btf__finalize_data; +} LIBBPF_0.0.2; diff --git a/tools/lib/bpf/libbpf.pc.template b/tools/lib/bpf/libbpf.pc.template new file mode 100644 index 000000000000..ac17fcef2108 --- /dev/null +++ b/tools/lib/bpf/libbpf.pc.template @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +prefix=@PREFIX@ +libdir=@LIBDIR@ +includedir=${prefix}/include + +Name: libbpf +Description: BPF library +Version: @VERSION@ +Libs: -L${libdir} -lbpf +Requires.private: libelf +Cflags: -I${includedir} diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h new file mode 100644 index 000000000000..f3025b4d90e1 --- /dev/null +++ b/tools/lib/bpf/libbpf_internal.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +/* + * Internal libbpf helpers. + * + * Copyright (c) 2019 Facebook + */ + +#ifndef __LIBBPF_LIBBPF_INTERNAL_H +#define __LIBBPF_LIBBPF_INTERNAL_H + +#define BTF_INFO_ENC(kind, kind_flag, vlen) \ + ((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN)) +#define BTF_TYPE_ENC(name, info, size_or_type) (name), (info), (size_or_type) +#define BTF_INT_ENC(encoding, bits_offset, nr_bits) \ + ((encoding) << 24 | (bits_offset) << 16 | (nr_bits)) +#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \ + BTF_INT_ENC(encoding, bits_offset, bits) +#define BTF_MEMBER_ENC(name, type, bits_offset) (name), (type), (bits_offset) +#define BTF_PARAM_ENC(name, type) (name), (type) +#define BTF_VAR_SECINFO_ENC(type, offset, size) (type), (offset), (size) + +extern void libbpf_print(enum libbpf_print_level level, + const char *format, ...) + __attribute__((format(printf, 2, 3))); + +#define __pr(level, fmt, ...) \ +do { \ + libbpf_print(level, "libbpf: " fmt, ##__VA_ARGS__); \ +} while (0) + +#define pr_warning(fmt, ...) __pr(LIBBPF_WARN, fmt, ##__VA_ARGS__) +#define pr_info(fmt, ...) __pr(LIBBPF_INFO, fmt, ##__VA_ARGS__) +#define pr_debug(fmt, ...) __pr(LIBBPF_DEBUG, fmt, ##__VA_ARGS__) + +int libbpf__probe_raw_btf(const char *raw_types, size_t types_len, + const char *str_sec, size_t str_len); + +#endif /* __LIBBPF_LIBBPF_INTERNAL_H */ diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index 8c3a1c04dcb2..5e2aa83f637a 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -9,11 +9,13 @@ #include <net/if.h> #include <sys/utsname.h> +#include <linux/btf.h> #include <linux/filter.h> #include <linux/kernel.h> #include "bpf.h" #include "libbpf.h" +#include "libbpf_internal.h" static bool grep(const char *buffer, const char *pattern) { @@ -93,10 +95,12 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_SK_MSG: 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: default: break; } @@ -129,11 +133,73 @@ bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex) return errno != EINVAL && errno != EOPNOTSUPP; } +int libbpf__probe_raw_btf(const char *raw_types, size_t types_len, + const char *str_sec, size_t str_len) +{ + struct btf_header hdr = { + .magic = BTF_MAGIC, + .version = BTF_VERSION, + .hdr_len = sizeof(struct btf_header), + .type_len = types_len, + .str_off = types_len, + .str_len = str_len, + }; + int btf_fd, btf_len; + __u8 *raw_btf; + + btf_len = hdr.hdr_len + hdr.type_len + hdr.str_len; + raw_btf = malloc(btf_len); + if (!raw_btf) + return -ENOMEM; + + memcpy(raw_btf, &hdr, sizeof(hdr)); + memcpy(raw_btf + hdr.hdr_len, raw_types, hdr.type_len); + memcpy(raw_btf + hdr.hdr_len + hdr.type_len, str_sec, hdr.str_len); + + btf_fd = bpf_load_btf(raw_btf, btf_len, NULL, 0, false); + if (btf_fd < 0) { + free(raw_btf); + return 0; + } + + close(btf_fd); + free(raw_btf); + return 1; +} + +static int load_sk_storage_btf(void) +{ + const char strs[] = "\0bpf_spin_lock\0val\0cnt\0l"; + /* struct bpf_spin_lock { + * int val; + * }; + * struct val { + * int cnt; + * struct bpf_spin_lock l; + * }; + */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* struct bpf_spin_lock */ /* [2] */ + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), 4), + BTF_MEMBER_ENC(15, 1, 0), /* int val; */ + /* struct val */ /* [3] */ + BTF_TYPE_ENC(15, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8), + BTF_MEMBER_ENC(19, 1, 0), /* int cnt; */ + BTF_MEMBER_ENC(23, 2, 32),/* struct bpf_spin_lock l; */ + }; + + return libbpf__probe_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs)); +} + bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) { int key_size, value_size, max_entries, map_flags; + __u32 btf_key_type_id = 0, btf_value_type_id = 0; struct bpf_create_map_attr attr = {}; - int fd = -1, fd_inner; + int fd = -1, btf_fd = -1, fd_inner; key_size = sizeof(__u32); value_size = sizeof(__u32); @@ -159,6 +225,16 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) case BPF_MAP_TYPE_STACK: key_size = 0; break; + case BPF_MAP_TYPE_SK_STORAGE: + btf_key_type_id = 1; + btf_value_type_id = 3; + value_size = 8; + max_entries = 0; + map_flags = BPF_F_NO_PREALLOC; + btf_fd = load_sk_storage_btf(); + if (btf_fd < 0) + return false; + break; case BPF_MAP_TYPE_UNSPEC: case BPF_MAP_TYPE_HASH: case BPF_MAP_TYPE_ARRAY: @@ -204,11 +280,18 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) attr.max_entries = max_entries; attr.map_flags = map_flags; attr.map_ifindex = ifindex; + if (btf_fd >= 0) { + attr.btf_fd = btf_fd; + attr.btf_key_type_id = btf_key_type_id; + attr.btf_value_type_id = btf_value_type_id; + } fd = bpf_create_map_xattr(&attr); } if (fd >= 0) close(fd); + if (btf_fd >= 0) + close(btf_fd); return fd >= 0; } diff --git a/tools/lib/bpf/libbpf_util.h b/tools/lib/bpf/libbpf_util.h index 81ecda0cb9c9..59c779c5790c 100644 --- a/tools/lib/bpf/libbpf_util.h +++ b/tools/lib/bpf/libbpf_util.h @@ -10,18 +10,35 @@ extern "C" { #endif -extern void libbpf_print(enum libbpf_print_level level, - const char *format, ...) - __attribute__((format(printf, 2, 3))); - -#define __pr(level, fmt, ...) \ -do { \ - libbpf_print(level, "libbpf: " fmt, ##__VA_ARGS__); \ -} while (0) - -#define pr_warning(fmt, ...) __pr(LIBBPF_WARN, fmt, ##__VA_ARGS__) -#define pr_info(fmt, ...) __pr(LIBBPF_INFO, fmt, ##__VA_ARGS__) -#define pr_debug(fmt, ...) __pr(LIBBPF_DEBUG, fmt, ##__VA_ARGS__) +/* Use these barrier functions instead of smp_[rw]mb() when they are + * used in a libbpf header file. That way they can be built into the + * application that uses libbpf. + */ +#if defined(__i386__) || defined(__x86_64__) +# define libbpf_smp_rmb() asm volatile("" : : : "memory") +# define libbpf_smp_wmb() asm volatile("" : : : "memory") +# define libbpf_smp_mb() \ + asm volatile("lock; addl $0,-4(%%rsp)" : : : "memory", "cc") +/* Hinders stores to be observed before older loads. */ +# define libbpf_smp_rwmb() asm volatile("" : : : "memory") +#elif defined(__aarch64__) +# define libbpf_smp_rmb() asm volatile("dmb ishld" : : : "memory") +# define libbpf_smp_wmb() asm volatile("dmb ishst" : : : "memory") +# define libbpf_smp_mb() asm volatile("dmb ish" : : : "memory") +# define libbpf_smp_rwmb() libbpf_smp_mb() +#elif defined(__arm__) +/* These are only valid for armv7 and above */ +# define libbpf_smp_rmb() asm volatile("dmb ish" : : : "memory") +# define libbpf_smp_wmb() asm volatile("dmb ishst" : : : "memory") +# define libbpf_smp_mb() asm volatile("dmb ish" : : : "memory") +# define libbpf_smp_rwmb() libbpf_smp_mb() +#else +/* Architecture missing native barrier functions. */ +# define libbpf_smp_rmb() __sync_synchronize() +# define libbpf_smp_wmb() __sync_synchronize() +# define libbpf_smp_mb() __sync_synchronize() +# define libbpf_smp_rwmb() __sync_synchronize() +#endif #ifdef __cplusplus } /* extern "C" */ diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index 8d0078b65486..38667b62f1fe 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -29,7 +29,7 @@ #include "bpf.h" #include "libbpf.h" -#include "libbpf_util.h" +#include "libbpf_internal.h" #include "xsk.h" #ifndef SOL_XDP @@ -248,8 +248,7 @@ int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area, __u64 size, return 0; out_mmap: - munmap(umem->fill, - off.fr.desc + umem->config.fill_size * sizeof(__u64)); + munmap(map, off.fr.desc + umem->config.fill_size * sizeof(__u64)); out_socket: close(umem->fd); out_umem_alloc: @@ -259,7 +258,8 @@ out_umem_alloc: static int xsk_load_xdp_prog(struct xsk_socket *xsk) { - char bpf_log_buf[BPF_LOG_BUF_SIZE]; + static const int log_buf_size = 16 * 1024; + char log_buf[log_buf_size]; int err, prog_fd; /* This is the C-program: @@ -308,10 +308,10 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk) size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); prog_fd = bpf_load_program(BPF_PROG_TYPE_XDP, prog, insns_cnt, - "LGPL-2.1 or BSD-2-Clause", 0, bpf_log_buf, - BPF_LOG_BUF_SIZE); + "LGPL-2.1 or BSD-2-Clause", 0, log_buf, + log_buf_size); if (prog_fd < 0) { - pr_warning("BPF log buffer:\n%s", bpf_log_buf); + pr_warning("BPF log buffer:\n%s", log_buf); return prog_fd; } @@ -387,21 +387,17 @@ static void xsk_delete_bpf_maps(struct xsk_socket *xsk) { close(xsk->qidconf_map_fd); close(xsk->xsks_map_fd); + xsk->qidconf_map_fd = -1; + xsk->xsks_map_fd = -1; } -static int xsk_update_bpf_maps(struct xsk_socket *xsk, int qidconf_value, - int xsks_value) +static int xsk_lookup_bpf_maps(struct xsk_socket *xsk) { - bool qidconf_map_updated = false, xsks_map_updated = false; + __u32 i, *map_ids, num_maps, prog_len = sizeof(struct bpf_prog_info); + __u32 map_len = sizeof(struct bpf_map_info); struct bpf_prog_info prog_info = {}; - __u32 prog_len = sizeof(prog_info); struct bpf_map_info map_info; - __u32 map_len = sizeof(map_info); - __u32 *map_ids; - int reset_value = 0; - __u32 num_maps; - unsigned int i; - int err; + int fd, err; err = bpf_obj_get_info_by_fd(xsk->prog_fd, &prog_info, &prog_len); if (err) @@ -422,66 +418,71 @@ static int xsk_update_bpf_maps(struct xsk_socket *xsk, int qidconf_value, goto out_map_ids; for (i = 0; i < prog_info.nr_map_ids; i++) { - int fd; + if (xsk->qidconf_map_fd != -1 && xsk->xsks_map_fd != -1) + break; fd = bpf_map_get_fd_by_id(map_ids[i]); - if (fd < 0) { - err = -errno; - goto out_maps; - } + if (fd < 0) + continue; err = bpf_obj_get_info_by_fd(fd, &map_info, &map_len); - if (err) - goto out_maps; + if (err) { + close(fd); + continue; + } if (!strcmp(map_info.name, "qidconf_map")) { - err = bpf_map_update_elem(fd, &xsk->queue_id, - &qidconf_value, 0); - if (err) - goto out_maps; - qidconf_map_updated = true; xsk->qidconf_map_fd = fd; - } else if (!strcmp(map_info.name, "xsks_map")) { - err = bpf_map_update_elem(fd, &xsk->queue_id, - &xsks_value, 0); - if (err) - goto out_maps; - xsks_map_updated = true; + continue; + } + + if (!strcmp(map_info.name, "xsks_map")) { xsk->xsks_map_fd = fd; + continue; } - if (qidconf_map_updated && xsks_map_updated) - break; + close(fd); } - if (!(qidconf_map_updated && xsks_map_updated)) { + err = 0; + if (xsk->qidconf_map_fd < 0 || xsk->xsks_map_fd < 0) { err = -ENOENT; - goto out_maps; + xsk_delete_bpf_maps(xsk); } - err = 0; - goto out_success; - -out_maps: - if (qidconf_map_updated) - (void)bpf_map_update_elem(xsk->qidconf_map_fd, &xsk->queue_id, - &reset_value, 0); - if (xsks_map_updated) - (void)bpf_map_update_elem(xsk->xsks_map_fd, &xsk->queue_id, - &reset_value, 0); -out_success: - if (qidconf_map_updated) - close(xsk->qidconf_map_fd); - if (xsks_map_updated) - close(xsk->xsks_map_fd); out_map_ids: free(map_ids); return err; } +static void xsk_clear_bpf_maps(struct xsk_socket *xsk) +{ + int qid = false; + + bpf_map_update_elem(xsk->qidconf_map_fd, &xsk->queue_id, &qid, 0); + bpf_map_delete_elem(xsk->xsks_map_fd, &xsk->queue_id); +} + +static int xsk_set_bpf_maps(struct xsk_socket *xsk) +{ + int qid = true, fd = xsk->fd, err; + + err = bpf_map_update_elem(xsk->qidconf_map_fd, &xsk->queue_id, &qid, 0); + if (err) + goto out; + + err = bpf_map_update_elem(xsk->xsks_map_fd, &xsk->queue_id, &fd, 0); + if (err) + goto out; + + return 0; +out: + xsk_clear_bpf_maps(xsk); + return err; +} + static int xsk_setup_xdp_prog(struct xsk_socket *xsk) { - bool prog_attached = false; __u32 prog_id = 0; int err; @@ -491,7 +492,6 @@ static int xsk_setup_xdp_prog(struct xsk_socket *xsk) return err; if (!prog_id) { - prog_attached = true; err = xsk_create_bpf_maps(xsk); if (err) return err; @@ -501,20 +501,21 @@ static int xsk_setup_xdp_prog(struct xsk_socket *xsk) goto out_maps; } else { xsk->prog_fd = bpf_prog_get_fd_by_id(prog_id); + err = xsk_lookup_bpf_maps(xsk); + if (err) + goto out_load; } - err = xsk_update_bpf_maps(xsk, true, xsk->fd); + err = xsk_set_bpf_maps(xsk); if (err) goto out_load; return 0; out_load: - if (prog_attached) - close(xsk->prog_fd); + close(xsk->prog_fd); out_maps: - if (prog_attached) - xsk_delete_bpf_maps(xsk); + xsk_delete_bpf_maps(xsk); return err; } @@ -523,11 +524,11 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, struct xsk_ring_cons *rx, struct xsk_ring_prod *tx, const struct xsk_socket_config *usr_config) { + void *rx_map = NULL, *tx_map = NULL; struct sockaddr_xdp sxdp = {}; struct xdp_mmap_offsets off; struct xsk_socket *xsk; socklen_t optlen; - void *map; int err; if (!umem || !xsk_ptr || !rx || !tx) @@ -593,40 +594,40 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, } if (rx) { - map = xsk_mmap(NULL, off.rx.desc + - xsk->config.rx_size * sizeof(struct xdp_desc), - PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_POPULATE, - xsk->fd, XDP_PGOFF_RX_RING); - if (map == MAP_FAILED) { + rx_map = xsk_mmap(NULL, off.rx.desc + + xsk->config.rx_size * sizeof(struct xdp_desc), + PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_POPULATE, + xsk->fd, XDP_PGOFF_RX_RING); + if (rx_map == MAP_FAILED) { err = -errno; goto out_socket; } rx->mask = xsk->config.rx_size - 1; rx->size = xsk->config.rx_size; - rx->producer = map + off.rx.producer; - rx->consumer = map + off.rx.consumer; - rx->ring = map + off.rx.desc; + rx->producer = rx_map + off.rx.producer; + rx->consumer = rx_map + off.rx.consumer; + rx->ring = rx_map + off.rx.desc; } xsk->rx = rx; if (tx) { - map = xsk_mmap(NULL, off.tx.desc + - xsk->config.tx_size * sizeof(struct xdp_desc), - PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_POPULATE, - xsk->fd, XDP_PGOFF_TX_RING); - if (map == MAP_FAILED) { + tx_map = xsk_mmap(NULL, off.tx.desc + + xsk->config.tx_size * sizeof(struct xdp_desc), + PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_POPULATE, + xsk->fd, XDP_PGOFF_TX_RING); + if (tx_map == MAP_FAILED) { err = -errno; goto out_mmap_rx; } tx->mask = xsk->config.tx_size - 1; tx->size = xsk->config.tx_size; - tx->producer = map + off.tx.producer; - tx->consumer = map + off.tx.consumer; - tx->ring = map + off.tx.desc; + tx->producer = tx_map + off.tx.producer; + tx->consumer = tx_map + off.tx.consumer; + tx->ring = tx_map + off.tx.desc; tx->cached_cons = xsk->config.tx_size; } xsk->tx = tx; @@ -642,6 +643,9 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, goto out_mmap_tx; } + xsk->qidconf_map_fd = -1; + xsk->xsks_map_fd = -1; + if (!(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) { err = xsk_setup_xdp_prog(xsk); if (err) @@ -653,13 +657,11 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, out_mmap_tx: if (tx) - munmap(xsk->tx, - off.tx.desc + + munmap(tx_map, off.tx.desc + xsk->config.tx_size * sizeof(struct xdp_desc)); out_mmap_rx: if (rx) - munmap(xsk->rx, - off.rx.desc + + munmap(rx_map, off.rx.desc + xsk->config.rx_size * sizeof(struct xdp_desc)); out_socket: if (--umem->refcount) @@ -684,9 +686,9 @@ int xsk_umem__delete(struct xsk_umem *umem) optlen = sizeof(off); err = getsockopt(umem->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen); if (!err) { - munmap(umem->fill->ring, + munmap(umem->fill->ring - off.fr.desc, off.fr.desc + umem->config.fill_size * sizeof(__u64)); - munmap(umem->comp->ring, + munmap(umem->comp->ring - off.cr.desc, off.cr.desc + umem->config.comp_size * sizeof(__u64)); } @@ -698,6 +700,7 @@ int xsk_umem__delete(struct xsk_umem *umem) void xsk_socket__delete(struct xsk_socket *xsk) { + size_t desc_sz = sizeof(struct xdp_desc); struct xdp_mmap_offsets off; socklen_t optlen; int err; @@ -705,19 +708,21 @@ void xsk_socket__delete(struct xsk_socket *xsk) if (!xsk) return; - (void)xsk_update_bpf_maps(xsk, 0, 0); + xsk_clear_bpf_maps(xsk); + xsk_delete_bpf_maps(xsk); optlen = sizeof(off); err = getsockopt(xsk->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen); if (!err) { - if (xsk->rx) - munmap(xsk->rx->ring, - off.rx.desc + - xsk->config.rx_size * sizeof(struct xdp_desc)); - if (xsk->tx) - munmap(xsk->tx->ring, - off.tx.desc + - xsk->config.tx_size * sizeof(struct xdp_desc)); + if (xsk->rx) { + munmap(xsk->rx->ring - off.rx.desc, + off.rx.desc + xsk->config.rx_size * desc_sz); + } + if (xsk->tx) { + munmap(xsk->tx->ring - off.tx.desc, + off.tx.desc + xsk->config.tx_size * desc_sz); + } + } xsk->umem->refcount--; diff --git a/tools/lib/bpf/xsk.h b/tools/lib/bpf/xsk.h index a497f00e2962..82ea71a0f3ec 100644 --- a/tools/lib/bpf/xsk.h +++ b/tools/lib/bpf/xsk.h @@ -16,6 +16,7 @@ #include <linux/if_xdp.h> #include "libbpf.h" +#include "libbpf_util.h" #ifdef __cplusplus extern "C" { @@ -36,6 +37,10 @@ struct name { \ DEFINE_XSK_RING(xsk_ring_prod); DEFINE_XSK_RING(xsk_ring_cons); +/* For a detailed explanation on the memory barriers associated with the + * ring, please take a look at net/xdp/xsk_queue.h. + */ + struct xsk_umem; struct xsk_socket; @@ -105,7 +110,7 @@ static inline __u32 xsk_cons_nb_avail(struct xsk_ring_cons *r, __u32 nb) static inline size_t xsk_ring_prod__reserve(struct xsk_ring_prod *prod, size_t nb, __u32 *idx) { - if (unlikely(xsk_prod_nb_free(prod, nb) < nb)) + if (xsk_prod_nb_free(prod, nb) < nb) return 0; *idx = prod->cached_prod; @@ -116,10 +121,10 @@ static inline size_t xsk_ring_prod__reserve(struct xsk_ring_prod *prod, static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, size_t nb) { - /* Make sure everything has been written to the ring before signalling - * this to the kernel. + /* Make sure everything has been written to the ring before indicating + * this to the kernel by writing the producer pointer. */ - smp_wmb(); + libbpf_smp_wmb(); *prod->producer += nb; } @@ -129,11 +134,11 @@ static inline size_t xsk_ring_cons__peek(struct xsk_ring_cons *cons, { size_t entries = xsk_cons_nb_avail(cons, nb); - if (likely(entries > 0)) { + if (entries > 0) { /* Make sure we do not speculatively read the data before * we have received the packet buffers from the ring. */ - smp_rmb(); + libbpf_smp_rmb(); *idx = cons->cached_cons; cons->cached_cons += entries; @@ -144,6 +149,11 @@ static inline size_t xsk_ring_cons__peek(struct xsk_ring_cons *cons, static inline void xsk_ring_cons__release(struct xsk_ring_cons *cons, size_t nb) { + /* Make sure data has been read before indicating we are done + * with the entries by updating the consumer pointer. + */ + libbpf_smp_rwmb(); + *cons->consumer += nb; } diff --git a/tools/lib/traceevent/Documentation/Makefile b/tools/lib/traceevent/Documentation/Makefile new file mode 100644 index 000000000000..aa72ab96c3c1 --- /dev/null +++ b/tools/lib/traceevent/Documentation/Makefile @@ -0,0 +1,207 @@ +include ../../../scripts/Makefile.include +include ../../../scripts/utilities.mak + +# This Makefile and manpage XSL files were taken from tools/perf/Documentation +# and modified for libtraceevent. + +MAN3_TXT= \ + $(wildcard libtraceevent-*.txt) \ + libtraceevent.txt + +MAN_TXT = $(MAN3_TXT) +_MAN_XML=$(patsubst %.txt,%.xml,$(MAN_TXT)) +_MAN_HTML=$(patsubst %.txt,%.html,$(MAN_TXT)) +_DOC_MAN3=$(patsubst %.txt,%.3,$(MAN3_TXT)) + +MAN_XML=$(addprefix $(OUTPUT),$(_MAN_XML)) +MAN_HTML=$(addprefix $(OUTPUT),$(_MAN_HTML)) +DOC_MAN3=$(addprefix $(OUTPUT),$(_DOC_MAN3)) + +# Make the path relative to DESTDIR, not prefix +ifndef DESTDIR +prefix?=$(HOME) +endif +bindir?=$(prefix)/bin +htmldir?=$(prefix)/share/doc/libtraceevent-doc +pdfdir?=$(prefix)/share/doc/libtraceevent-doc +mandir?=$(prefix)/share/man +man3dir=$(mandir)/man3 + +ASCIIDOC=asciidoc +ASCIIDOC_EXTRA = --unsafe -f asciidoc.conf +ASCIIDOC_HTML = xhtml11 +MANPAGE_XSL = manpage-normal.xsl +XMLTO_EXTRA = +INSTALL?=install +RM ?= rm -f + +ifdef USE_ASCIIDOCTOR +ASCIIDOC = asciidoctor +ASCIIDOC_EXTRA = -a compat-mode +ASCIIDOC_EXTRA += -I. -rasciidoctor-extensions +ASCIIDOC_EXTRA += -a mansource="libtraceevent" -a manmanual="libtraceevent Manual" +ASCIIDOC_HTML = xhtml5 +endif + +XMLTO=xmlto + +_tmp_tool_path := $(call get-executable,$(ASCIIDOC)) +ifeq ($(_tmp_tool_path),) + missing_tools = $(ASCIIDOC) +endif + +ifndef USE_ASCIIDOCTOR +_tmp_tool_path := $(call get-executable,$(XMLTO)) +ifeq ($(_tmp_tool_path),) + missing_tools += $(XMLTO) +endif +endif + +# +# For asciidoc ... +# -7.1.2, no extra settings are needed. +# 8.0-, set ASCIIDOC8. +# + +# +# For docbook-xsl ... +# -1.68.1, set ASCIIDOC_NO_ROFF? (based on changelog from 1.73.0) +# 1.69.0, no extra settings are needed? +# 1.69.1-1.71.0, set DOCBOOK_SUPPRESS_SP? +# 1.71.1, no extra settings are needed? +# 1.72.0, set DOCBOOK_XSL_172. +# 1.73.0-, set ASCIIDOC_NO_ROFF +# + +# +# If you had been using DOCBOOK_XSL_172 in an attempt to get rid +# of 'the ".ft C" problem' in your generated manpages, and you +# instead ended up with weird characters around callouts, try +# using ASCIIDOC_NO_ROFF instead (it works fine with ASCIIDOC8). +# + +ifdef ASCIIDOC8 +ASCIIDOC_EXTRA += -a asciidoc7compatible +endif +ifdef DOCBOOK_XSL_172 +ASCIIDOC_EXTRA += -a libtraceevent-asciidoc-no-roff +MANPAGE_XSL = manpage-1.72.xsl +else + ifdef ASCIIDOC_NO_ROFF + # docbook-xsl after 1.72 needs the regular XSL, but will not + # pass-thru raw roff codes from asciidoc.conf, so turn them off. + ASCIIDOC_EXTRA += -a libtraceevent-asciidoc-no-roff + endif +endif +ifdef MAN_BOLD_LITERAL +XMLTO_EXTRA += -m manpage-bold-literal.xsl +endif +ifdef DOCBOOK_SUPPRESS_SP +XMLTO_EXTRA += -m manpage-suppress-sp.xsl +endif + +SHELL_PATH ?= $(SHELL) +# Shell quote; +SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH)) + +DESTDIR ?= +DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))' + +export DESTDIR DESTDIR_SQ + +# +# Please note that there is a minor bug in asciidoc. +# The version after 6.0.3 _will_ include the patch found here: +# http://marc.theaimsgroup.com/?l=libtraceevent&m=111558757202243&w=2 +# +# Until that version is released you may have to apply the patch +# yourself - yes, all 6 characters of it! +# +QUIET_SUBDIR0 = +$(MAKE) -C # space to separate -C and subdir +QUIET_SUBDIR1 = + +ifneq ($(findstring $(MAKEFLAGS),w),w) +PRINT_DIR = --no-print-directory +else # "make -w" +NO_SUBDIR = : +endif + +ifneq ($(findstring $(MAKEFLAGS),s),s) +ifneq ($(V),1) + QUIET_ASCIIDOC = @echo ' ASCIIDOC '$@; + QUIET_XMLTO = @echo ' XMLTO '$@; + QUIET_SUBDIR0 = +@subdir= + QUIET_SUBDIR1 = ;$(NO_SUBDIR) \ + echo ' SUBDIR ' $$subdir; \ + $(MAKE) $(PRINT_DIR) -C $$subdir + export V +endif +endif + +all: html man + +man: man3 +man3: $(DOC_MAN3) + +html: $(MAN_HTML) + +$(MAN_HTML) $(DOC_MAN3): asciidoc.conf + +install: install-man + +check-man-tools: +ifdef missing_tools + $(error "You need to install $(missing_tools) for man pages") +endif + +do-install-man: man + $(call QUIET_INSTALL, Documentation-man) \ + $(INSTALL) -d -m 755 $(DESTDIR)$(man3dir); \ + $(INSTALL) -m 644 $(DOC_MAN3) $(DESTDIR)$(man3dir); + +install-man: check-man-tools man do-install-man + +uninstall: uninstall-man + +uninstall-man: + $(call QUIET_UNINST, Documentation-man) \ + $(Q)$(RM) $(addprefix $(DESTDIR)$(man3dir)/,$(DOC_MAN3)) + + +ifdef missing_tools + DO_INSTALL_MAN = $(warning Please install $(missing_tools) to have the man pages installed) +else + DO_INSTALL_MAN = do-install-man +endif + +CLEAN_FILES = \ + $(MAN_XML) $(addsuffix +,$(MAN_XML)) \ + $(MAN_HTML) $(addsuffix +,$(MAN_HTML)) \ + $(DOC_MAN3) *.3 + +clean: + $(call QUIET_CLEAN, Documentation) $(RM) $(CLEAN_FILES) + +ifdef USE_ASCIIDOCTOR +$(OUTPUT)%.3 : $(OUTPUT)%.txt + $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \ + $(ASCIIDOC) -b manpage -d manpage \ + $(ASCIIDOC_EXTRA) -alibtraceevent_version=$(EVENT_PARSE_VERSION) -o $@+ $< && \ + mv $@+ $@ +endif + +$(OUTPUT)%.3 : $(OUTPUT)%.xml + $(QUIET_XMLTO)$(RM) $@ && \ + $(XMLTO) -o $(OUTPUT). -m $(MANPAGE_XSL) $(XMLTO_EXTRA) man $< + +$(OUTPUT)%.xml : %.txt + $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \ + $(ASCIIDOC) -b docbook -d manpage \ + $(ASCIIDOC_EXTRA) -alibtraceevent_version=$(EVENT_PARSE_VERSION) -o $@+ $< && \ + mv $@+ $@ + +$(MAN_HTML): $(OUTPUT)%.html : %.txt + $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \ + $(ASCIIDOC) -b $(ASCIIDOC_HTML) -d manpage \ + $(ASCIIDOC_EXTRA) -aperf_version=$(EVENT_PARSE_VERSION) -o $@+ $< && \ + mv $@+ $@ diff --git a/tools/lib/traceevent/Documentation/asciidoc.conf b/tools/lib/traceevent/Documentation/asciidoc.conf new file mode 100644 index 000000000000..07595717f06e --- /dev/null +++ b/tools/lib/traceevent/Documentation/asciidoc.conf @@ -0,0 +1,120 @@ +## linktep: macro +# +# Usage: linktep:command[manpage-section] +# +# Note, {0} is the manpage section, while {target} is the command. +# +# Show TEP link as: <command>(<section>); if section is defined, else just show +# the command. + +[macros] +(?su)[\\]?(?P<name>linktep):(?P<target>\S*?)\[(?P<attrlist>.*?)\]= + +[attributes] +asterisk=* +plus=+ +caret=^ +startsb=[ +endsb=] +tilde=~ + +ifdef::backend-docbook[] +[linktep-inlinemacro] +{0%{target}} +{0#<citerefentry>} +{0#<refentrytitle>{target}</refentrytitle><manvolnum>{0}</manvolnum>} +{0#</citerefentry>} +endif::backend-docbook[] + +ifdef::backend-docbook[] +ifndef::tep-asciidoc-no-roff[] +# "unbreak" docbook-xsl v1.68 for manpages. v1.69 works with or without this. +# v1.72 breaks with this because it replaces dots not in roff requests. +[listingblock] +<example><title>{title}</title> +<literallayout> +ifdef::doctype-manpage[] + .ft C +endif::doctype-manpage[] +| +ifdef::doctype-manpage[] + .ft +endif::doctype-manpage[] +</literallayout> +{title#}</example> +endif::tep-asciidoc-no-roff[] + +ifdef::tep-asciidoc-no-roff[] +ifdef::doctype-manpage[] +# The following two small workarounds insert a simple paragraph after screen +[listingblock] +<example><title>{title}</title> +<literallayout> +| +</literallayout><simpara></simpara> +{title#}</example> + +[verseblock] +<formalpara{id? id="{id}"}><title>{title}</title><para> +{title%}<literallayout{id? id="{id}"}> +{title#}<literallayout> +| +</literallayout> +{title#}</para></formalpara> +{title%}<simpara></simpara> +endif::doctype-manpage[] +endif::tep-asciidoc-no-roff[] +endif::backend-docbook[] + +ifdef::doctype-manpage[] +ifdef::backend-docbook[] +[header] +template::[header-declarations] +<refentry> +<refmeta> +<refentrytitle>{mantitle}</refentrytitle> +<manvolnum>{manvolnum}</manvolnum> +<refmiscinfo class="source">libtraceevent</refmiscinfo> +<refmiscinfo class="version">{libtraceevent_version}</refmiscinfo> +<refmiscinfo class="manual">libtraceevent Manual</refmiscinfo> +</refmeta> +<refnamediv> + <refname>{manname1}</refname> + <refname>{manname2}</refname> + <refname>{manname3}</refname> + <refname>{manname4}</refname> + <refname>{manname5}</refname> + <refname>{manname6}</refname> + <refname>{manname7}</refname> + <refname>{manname8}</refname> + <refname>{manname9}</refname> + <refname>{manname10}</refname> + <refname>{manname11}</refname> + <refname>{manname12}</refname> + <refname>{manname13}</refname> + <refname>{manname14}</refname> + <refname>{manname15}</refname> + <refname>{manname16}</refname> + <refname>{manname17}</refname> + <refname>{manname18}</refname> + <refname>{manname19}</refname> + <refname>{manname20}</refname> + <refname>{manname21}</refname> + <refname>{manname22}</refname> + <refname>{manname23}</refname> + <refname>{manname24}</refname> + <refname>{manname25}</refname> + <refname>{manname26}</refname> + <refname>{manname27}</refname> + <refname>{manname28}</refname> + <refname>{manname29}</refname> + <refname>{manname30}</refname> + <refpurpose>{manpurpose}</refpurpose> +</refnamediv> +endif::backend-docbook[] +endif::doctype-manpage[] + +ifdef::backend-xhtml11[] +[linktep-inlinemacro] +<a href="{target}.html">{target}{0?({0})}</a> +endif::backend-xhtml11[] diff --git a/tools/lib/traceevent/Documentation/libtraceevent-commands.txt b/tools/lib/traceevent/Documentation/libtraceevent-commands.txt new file mode 100644 index 000000000000..bec552001f8e --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-commands.txt @@ -0,0 +1,153 @@ +libtraceevent(3) +================ + +NAME +---- +tep_register_comm, tep_override_comm, tep_pid_is_registered, +tep_data_comm_from_pid, tep_data_pid_from_comm, tep_cmdline_pid - +Manage pid to process name mappings. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +int *tep_register_comm*(struct tep_handle pass:[*]_tep_, const char pass:[*]_comm_, int _pid_); +int *tep_override_comm*(struct tep_handle pass:[*]_tep_, const char pass:[*]_comm_, int _pid_); +bool *tep_is_pid_registered*(struct tep_handle pass:[*]_tep_, int _pid_); +const char pass:[*]*tep_data_comm_from_pid*(struct tep_handle pass:[*]_pevent_, int _pid_); +struct cmdline pass:[*]*tep_data_pid_from_comm*(struct tep_handle pass:[*]_pevent_, const char pass:[*]_comm_, struct cmdline pass:[*]_next_); +int *tep_cmdline_pid*(struct tep_handle pass:[*]_pevent_, struct cmdline pass:[*]_cmdline_); +-- + +DESCRIPTION +----------- +These functions can be used to handle the mapping between pid and process name. +The library builds a cache of these mappings, which is used to display the name +of the process, instead of its pid. This information can be retrieved from +tracefs/saved_cmdlines file. + +The _tep_register_comm()_ function registers a _pid_ / process name mapping. +If a command with the same _pid_ is already registered, an error is returned. +The _pid_ argument is the process ID, the _comm_ argument is the process name, +_tep_ is the event context. The _comm_ is duplicated internally. + +The _tep_override_comm()_ function registers a _pid_ / process name mapping. +If a process with the same pid is already registered, the process name string is +udapted with the new one. The _pid_ argument is the process ID, the _comm_ +argument is the process name, _tep_ is the event context. The _comm_ is +duplicated internally. + +The _tep_is_pid_registered()_ function checks if a pid has a process name +mapping registered. The _pid_ argument is the process ID, _tep_ is the event +context. + +The _tep_data_comm_from_pid()_ function returns the process name for a given +pid. The _pid_ argument is the process ID, _tep_ is the event context. +The returned string should not be freed, but will be freed when the _tep_ +handler is closed. + +The _tep_data_pid_from_comm()_ function returns a pid for a given process name. +The _comm_ argument is the process name, _tep_ is the event context. +The argument _next_ is the cmdline structure to search for the next pid. +As there may be more than one pid for a given process, the result of this call +can be passed back into a recurring call in the _next_ parameter, to search for +the next pid. If _next_ is NULL, it will return the first pid associated with +the _comm_. The function performs a linear search, so it may be slow. + +The _tep_cmdline_pid()_ function returns the pid associated with a given +_cmdline_. The _tep_ argument is the event context. + +RETURN VALUE +------------ +_tep_register_comm()_ function returns 0 on success. In case of an error -1 is +returned and errno is set to indicate the cause of the problem: ENOMEM, if there +is not enough memory to duplicate the _comm_ or EEXIST if a mapping for this +_pid_ is already registered. + +_tep_override_comm()_ function returns 0 on success. In case of an error -1 is +returned and errno is set to indicate the cause of the problem: ENOMEM, if there +is not enough memory to duplicate the _comm_. + +_tep_is_pid_registered()_ function returns true if the _pid_ has a process name +mapped to it, false otherwise. + +_tep_data_comm_from_pid()_ function returns the process name as string, or the +string "<...>" if there is no mapping for the given pid. + +_tep_data_pid_from_comm()_ function returns a pointer to a struct cmdline, that +holds a pid for a given process, or NULL if none is found. This result can be +passed back into a recurring call as the _next_ parameter of the function. + +_tep_cmdline_pid()_ functions returns the pid for the give cmdline. If _cmdline_ + is NULL, then -1 is returned. + +EXAMPLE +------- +The following example registers pid for command "ls", in context of event _tep_ +and performs various searches for pid / process name mappings: +[source,c] +-- +#include <event-parse.h> +... +int ret; +int ls_pid = 1021; +struct tep_handle *tep = tep_alloc(); +... + ret = tep_register_comm(tep, "ls", ls_pid); + if (ret != 0 && errno == EEXIST) + ret = tep_override_comm(tep, "ls", ls_pid); + if (ret != 0) { + /* Failed to register pid / command mapping */ + } +... + if (tep_is_pid_registered(tep, ls_pid) == 0) { + /* Command mapping for ls_pid is not registered */ + } +... + const char *comm = tep_data_comm_from_pid(tep, ls_pid); + if (comm) { + /* Found process name for ls_pid */ + } +... + int pid; + struct cmdline *cmd = tep_data_pid_from_comm(tep, "ls", NULL); + while (cmd) { + pid = tep_cmdline_pid(tep, cmd); + /* Found pid for process "ls" */ + cmd = tep_data_pid_from_comm(tep, "ls", cmd); + } +-- +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-cpus.txt b/tools/lib/traceevent/Documentation/libtraceevent-cpus.txt new file mode 100644 index 000000000000..5ad70e43b752 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-cpus.txt @@ -0,0 +1,77 @@ +libtraceevent(3) +================ + +NAME +---- +tep_get_cpus, tep_set_cpus - Get / set the number of CPUs, which have a tracing +buffer representing it. Note, the buffer may be empty. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +int *tep_get_cpus*(struct tep_handle pass:[*]_tep_); +void *tep_set_cpus*(struct tep_handle pass:[*]_tep_, int _cpus_); +-- + +DESCRIPTION +----------- +The _tep_get_cpus()_ function gets the number of CPUs, which have a tracing +buffer representing it. The _tep_ argument is trace event parser context. + +The _tep_set_cpus()_ function sets the number of CPUs, which have a tracing +buffer representing it. The _tep_ argument is trace event parser context. +The _cpu_ argument is the number of CPUs with tracing data. + +RETURN VALUE +------------ +The _tep_get_cpus()_ functions returns the number of CPUs, which have tracing +data recorded. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... + tep_set_cpus(tep, 5); +... + printf("We have tracing data for %d CPUs", tep_get_cpus(tep)); +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-endian_read.txt b/tools/lib/traceevent/Documentation/libtraceevent-endian_read.txt new file mode 100644 index 000000000000..e64851b6e189 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-endian_read.txt @@ -0,0 +1,78 @@ +libtraceevent(3) +================ + +NAME +---- +tep_read_number - Reads a number from raw data. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +unsigned long long *tep_read_number*(struct tep_handle pass:[*]_tep_, const void pass:[*]_ptr_, int _size_); +-- + +DESCRIPTION +----------- +The _tep_read_number()_ function reads an integer from raw data, taking into +account the endianness of the raw data and the current host. The _tep_ argument +is the trace event parser context. The _ptr_ is a pointer to the raw data, where +the integer is, and the _size_ is the size of the integer. + +RETURN VALUE +------------ +The _tep_read_number()_ function returns the integer in the byte order of +the current host. In case of an error, 0 is returned. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +void process_record(struct tep_record *record) +{ + int offset = 24; + int data = tep_read_number(tep, record->data + offset, 4); + + /* Read the 4 bytes at the offset 24 of data as an integer */ +} +... +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-event_find.txt b/tools/lib/traceevent/Documentation/libtraceevent-event_find.txt new file mode 100644 index 000000000000..7bc062c9f76f --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-event_find.txt @@ -0,0 +1,103 @@ +libtraceevent(3) +================ + +NAME +---- +tep_find_event,tep_find_event_by_name,tep_find_event_by_record - +Find events by given key. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +struct tep_event pass:[*]*tep_find_event*(struct tep_handle pass:[*]_tep_, int _id_); +struct tep_event pass:[*]*tep_find_event_by_name*(struct tep_handle pass:[*]_tep_, const char pass:[*]_sys_, const char pass:[*]_name_); +struct tep_event pass:[*]*tep_find_event_by_record*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_record_); +-- + +DESCRIPTION +----------- +This set of functions can be used to search for an event, based on a given +criteria. All functions require a pointer to a _tep_, trace event parser +context. + +The _tep_find_event()_ function searches for an event by given event _id_. The +event ID is assigned dynamically and can be viewed in event's format file, +"ID" field. + +The tep_find_event_by_name()_ function searches for an event by given +event _name_, under the system _sys_. If the _sys_ is NULL (not specified), +the first event with _name_ is returned. + +The tep_find_event_by_record()_ function searches for an event from a given +_record_. + +RETURN VALUE +------------ +All these functions return a pointer to the found event, or NULL if there is no +such event. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +struct tep_event *event; + +event = tep_find_event(tep, 1857); +if (event == NULL) { + /* There is no event with ID 1857 */ +} + +event = tep_find_event_by_name(tep, "kvm", "kvm_exit"); +if (event == NULL) { + /* There is no kvm_exit event, from kvm system */ +} + +void event_from_record(struct tep_record *record) +{ + struct tep_event *event = tep_find_event_by_record(tep, record); + if (event == NULL) { + /* There is no event from given record */ + } +} +... +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-event_get.txt b/tools/lib/traceevent/Documentation/libtraceevent-event_get.txt new file mode 100644 index 000000000000..6525092fc417 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-event_get.txt @@ -0,0 +1,99 @@ +libtraceevent(3) +================ + +NAME +---- +tep_get_event, tep_get_first_event, tep_get_events_count - Access events. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +struct tep_event pass:[*]*tep_get_event*(struct tep_handle pass:[*]_tep_, int _index_); +struct tep_event pass:[*]*tep_get_first_event*(struct tep_handle pass:[*]_tep_); +int *tep_get_events_count*(struct tep_handle pass:[*]_tep_); +-- + +DESCRIPTION +----------- +The _tep_get_event()_ function returns a pointer to event at the given _index_. +The _tep_ argument is trace event parser context, the _index_ is the index of +the requested event. + +The _tep_get_first_event()_ function returns a pointer to the first event. +As events are stored in an array, this function returns the pointer to the +beginning of the array. The _tep_ argument is trace event parser context. + +The _tep_get_events_count()_ function returns the number of the events +in the array. The _tep_ argument is trace event parser context. + +RETURN VALUE +------------ +The _tep_get_event()_ returns a pointer to the event located at _index_. +NULL is returned in case of error, in case there are no events or _index_ is +out of range. + +The _tep_get_first_event()_ returns a pointer to the first event. NULL is +returned in case of error, or in case there are no events. + +The _tep_get_events_count()_ returns the number of the events. 0 is +returned in case of error, or in case there are no events. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +int i,count = tep_get_events_count(tep); +struct tep_event *event, *events = tep_get_first_event(tep); + +if (events == NULL) { + /* There are no events */ +} else { + for (i = 0; i < count; i++) { + event = (events+i); + /* process events[i] */ + } + + /* Get the last event */ + event = tep_get_event(tep, count-1); +} +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-event_list.txt b/tools/lib/traceevent/Documentation/libtraceevent-event_list.txt new file mode 100644 index 000000000000..fba350e5a4cb --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-event_list.txt @@ -0,0 +1,122 @@ +libtraceevent(3) +================ + +NAME +---- +tep_list_events, tep_list_events_copy - +Get list of events, sorted by given criteria. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +enum *tep_event_sort_type* { + _TEP_EVENT_SORT_ID_, + _TEP_EVENT_SORT_NAME_, + _TEP_EVENT_SORT_SYSTEM_, +}; + +struct tep_event pass:[*]pass:[*]*tep_list_events*(struct tep_handle pass:[*]_tep_, enum tep_event_sort_type _sort_type_); +struct tep_event pass:[*]pass:[*]*tep_list_events_copy*(struct tep_handle pass:[*]_tep_, enum tep_event_sort_type _sort_type_); +-- + +DESCRIPTION +----------- +The _tep_list_events()_ function returns an array of pointers to the events, +sorted by the _sort_type_ criteria. The last element of the array is NULL. +The returned memory must not be freed, it is managed by the library. +The function is not thread safe. The _tep_ argument is trace event parser +context. The _sort_type_ argument is the required sort criteria: +[verse] +-- + _TEP_EVENT_SORT_ID_ - sort by the event ID. + _TEP_EVENT_SORT_NAME_ - sort by the event (name, system, id) triplet. + _TEP_EVENT_SORT_SYSTEM_ - sort by the event (system, name, id) triplet. +-- + +The _tep_list_events_copy()_ is a thread safe version of _tep_list_events()_. +It has the same behavior, but the returned array is allocated internally and +must be freed by the caller. Note that the content of the array must not be +freed (see the EXAMPLE below). + +RETURN VALUE +------------ +The _tep_list_events()_ function returns an array of pointers to events. +In case of an error, NULL is returned. The returned array must not be freed, +it is managed by the library. + +The _tep_list_events_copy()_ function returns an array of pointers to events. +In case of an error, NULL is returned. The returned array must be freed by +the caller. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +int i; +struct tep_event_format **events; + +i=0; +events = tep_list_events(tep, TEP_EVENT_SORT_ID); +if (events == NULL) { + /* Failed to get the events, sorted by ID */ +} else { + while(events[i]) { + /* walk through the list of the events, sorted by ID */ + i++; + } +} + +i=0; +events = tep_list_events_copy(tep, TEP_EVENT_SORT_NAME); +if (events == NULL) { + /* Failed to get the events, sorted by name */ +} else { + while(events[i]) { + /* walk through the list of the events, sorted by name */ + i++; + } + free(events); +} + +... +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-field_find.txt b/tools/lib/traceevent/Documentation/libtraceevent-field_find.txt new file mode 100644 index 000000000000..0896af5b9eff --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-field_find.txt @@ -0,0 +1,118 @@ +libtraceevent(3) +================ + +NAME +---- +tep_find_common_field, tep_find_field, tep_find_any_field - +Search for a field in an event. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +struct tep_format_field pass:[*]*tep_find_common_field*(struct tep_event pass:[*]_event_, const char pass:[*]_name_); +struct tep_format_field pass:[*]*tep_find_field*(struct tep_event_ormat pass:[*]_event_, const char pass:[*]_name_); +struct tep_format_field pass:[*]*tep_find_any_field*(struct tep_event pass:[*]_event_, const char pass:[*]_name_); +-- + +DESCRIPTION +----------- +These functions search for a field with given name in an event. The field +returned can be used to find the field content from within a data record. + +The _tep_find_common_field()_ function searches for a common field with _name_ +in the _event_. + +The _tep_find_field()_ function searches for an event specific field with +_name_ in the _event_. + +The _tep_find_any_field()_ function searches for any field with _name_ in the +_event_. + +RETURN VALUE +------------ +The _tep_find_common_field(), _tep_find_field()_ and _tep_find_any_field()_ +functions return a pointer to the found field, or NULL in case there is no field +with the requested name. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +void get_htimer_info(struct tep_handle *tep, struct tep_record *record) +{ + struct tep_format_field *field; + struct tep_event *event; + long long softexpires; + int mode; + int pid; + + event = tep_find_event_by_name(tep, "timer", "hrtimer_start"); + + field = tep_find_common_field(event, "common_pid"); + if (field == NULL) { + /* Cannot find "common_pid" field in the event */ + } else { + /* Get pid from the data record */ + pid = tep_read_number(tep, record->data + field->offset, + field->size); + } + + field = tep_find_field(event, "softexpires"); + if (field == NULL) { + /* Cannot find "softexpires" event specific field in the event */ + } else { + /* Get softexpires parameter from the data record */ + softexpires = tep_read_number(tep, record->data + field->offset, + field->size); + } + + field = tep_find_any_field(event, "mode"); + if (field == NULL) { + /* Cannot find "mode" field in the event */ + } else + { + /* Get mode parameter from the data record */ + mode = tep_read_number(tep, record->data + field->offset, + field->size); + } +} +... +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-field_get_val.txt b/tools/lib/traceevent/Documentation/libtraceevent-field_get_val.txt new file mode 100644 index 000000000000..6324f0d48aeb --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-field_get_val.txt @@ -0,0 +1,122 @@ +libtraceevent(3) +================ + +NAME +---- +tep_get_any_field_val, tep_get_common_field_val, tep_get_field_val, +tep_get_field_raw - Get value of a field. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* +*#include <trace-seq.h>* + +int *tep_get_any_field_val*(struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, unsigned long long pass:[*]_val_, int _err_); +int *tep_get_common_field_val*(struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, unsigned long long pass:[*]_val_, int _err_); +int *tep_get_field_val*(struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, unsigned long long pass:[*]_val_, int _err_); +void pass:[*]*tep_get_field_raw*(struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, int pass:[*]_len_, int _err_); +-- + +DESCRIPTION +----------- +These functions can be used to find a field and retrieve its value. + +The _tep_get_any_field_val()_ function searches in the _record_ for a field +with _name_, part of the _event_. If the field is found, its value is stored in +_val_. If there is an error and _err_ is not zero, then an error string is +written into _s_. + +The _tep_get_common_field_val()_ function does the same as +_tep_get_any_field_val()_, but searches only in the common fields. This works +for any event as all events include the common fields. + +The _tep_get_field_val()_ function does the same as _tep_get_any_field_val()_, +but searches only in the event specific fields. + +The _tep_get_field_raw()_ function searches in the _record_ for a field with +_name_, part of the _event_. If the field is found, a pointer to where the field +exists in the record's raw data is returned. The size of the data is stored in +_len_. If there is an error and _err_ is not zero, then an error string is +written into _s_. + +RETURN VALUE +------------ +The _tep_get_any_field_val()_, _tep_get_common_field_val()_ and +_tep_get_field_val()_ functions return 0 on success, or -1 in case of an error. + +The _tep_get_field_raw()_ function returns a pointer to field's raw data, and +places the length of this data in _len_. In case of an error NULL is returned. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +#include <trace-seq.h> +... +struct tep_handle *tep = tep_alloc(); +... +struct tep_event *event = tep_find_event_by_name(tep, "kvm", "kvm_exit"); +... +void process_record(struct tep_record *record) +{ + int len; + char *comm; + struct tep_event_format *event; + unsigned long long val; + + event = tep_find_event_by_record(pevent, record); + if (event != NULL) { + if (tep_get_common_field_val(NULL, event, "common_type", + record, &val, 0) == 0) { + /* Got the value of common type field */ + } + if (tep_get_field_val(NULL, event, "pid", record, &val, 0) == 0) { + /* Got the value of pid specific field */ + } + comm = tep_get_field_raw(NULL, event, "comm", record, &len, 0); + if (comm != NULL) { + /* Got a pointer to the comm event specific field */ + } + } +} +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*trace-seq.h* + Header file to include in order to have access to trace sequences + related APIs. Trace sequences are used to allow a function to call + several other functions to create a string of data to use. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-field_print.txt b/tools/lib/traceevent/Documentation/libtraceevent-field_print.txt new file mode 100644 index 000000000000..9a9df98ac44d --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-field_print.txt @@ -0,0 +1,126 @@ +libtraceevent(3) +================ + +NAME +---- +tep_print_field, tep_print_fields, tep_print_num_field, tep_print_func_field - +Print the field content. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* +*#include <trace-seq.h>* + +void *tep_print_field*(struct trace_seq pass:[*]_s_, void pass:[*]_data_, struct tep_format_field pass:[*]_field_); +void *tep_print_fields*(struct trace_seq pass:[*]_s_, void pass:[*]_data_, int _size_, struct tep_event pass:[*]_event_); +int *tep_print_num_field*(struct trace_seq pass:[*]_s_, const char pass:[*]_fmt_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, int _err_); +int *tep_print_func_field*(struct trace_seq pass:[*]_s_, const char pass:[*]_fmt_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, int _err_); +-- + +DESCRIPTION +----------- +These functions print recorded field's data, according to the field's type. + +The _tep_print_field()_ function extracts from the recorded raw _data_ value of +the _field_ and prints it into _s_, according to the field type. + +The _tep_print_fields()_ prints each field name followed by the record's field +value according to the field's type: +[verse] +-- +"field1_name=field1_value field2_name=field2_value ..." +-- +It iterates all fields of the _event_, and calls _tep_print_field()_ for each of +them. + +The _tep_print_num_field()_ function prints a numeric field with given format +string. A search is performed in the _event_ for a field with _name_. If such +field is found, its value is extracted from the _record_ and is printed in the +_s_, according to the given format string _fmt_. If the argument _err_ is +non-zero, and an error occures - it is printed in the _s_. + +The _tep_print_func_field()_ function prints a function field with given format +string. A search is performed in the _event_ for a field with _name_. If such +field is found, its value is extracted from the _record_. The value is assumed +to be a function address, and a search is perform to find the name of this +function. The function name (if found) and its address are printed in the _s_, +according to the given format string _fmt_. If the argument _err_ is non-zero, +and an error occures - it is printed in _s_. + +RETURN VALUE +------------ +The _tep_print_num_field()_ and _tep_print_func_field()_ functions return 1 +on success, -1 in case of an error or 0 if the print buffer _s_ is full. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +#include <trace-seq.h> +... +struct tep_handle *tep = tep_alloc(); +... +struct trace_seq seq; +trace_seq_init(&seq); +struct tep_event *event = tep_find_event_by_name(tep, "timer", "hrtimer_start"); +... +void process_record(struct tep_record *record) +{ + struct tep_format_field *field_pid = tep_find_common_field(event, "common_pid"); + + trace_seq_reset(&seq); + + /* Print the value of "common_pid" */ + tep_print_field(&seq, record->data, field_pid); + + /* Print all fields of the "hrtimer_start" event */ + tep_print_fields(&seq, record->data, record->size, event); + + /* Print the value of "expires" field with custom format string */ + tep_print_num_field(&seq, " timer expires in %llu ", event, "expires", record, 0); + + /* Print the address and the name of "function" field with custom format string */ + tep_print_func_field(&seq, " timer function is %s ", event, "function", record, 0); + } + ... +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*trace-seq.h* + Header file to include in order to have access to trace sequences related APIs. + Trace sequences are used to allow a function to call several other functions + to create a string of data to use. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-field_read.txt b/tools/lib/traceevent/Documentation/libtraceevent-field_read.txt new file mode 100644 index 000000000000..64e9e25d3fd9 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-field_read.txt @@ -0,0 +1,81 @@ +libtraceevent(3) +================ + +NAME +---- +tep_read_number_field - Reads a number from raw data. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +int *tep_read_number_field*(struct tep_format_field pass:[*]_field_, const void pass:[*]_data_, unsigned long long pass:[*]_value_); +-- + +DESCRIPTION +----------- +The _tep_read_number_field()_ function reads the value of the _field_ from the +raw _data_ and stores it in the _value_. The function sets the _value_ according +to the endianness of the raw data and the current machine and stores it in +_value_. + +RETURN VALUE +------------ +The _tep_read_number_field()_ function retunrs 0 in case of success, or -1 in +case of an error. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +struct tep_event *event = tep_find_event_by_name(tep, "timer", "hrtimer_start"); +... +void process_record(struct tep_record *record) +{ + unsigned long long pid; + struct tep_format_field *field_pid = tep_find_common_field(event, "common_pid"); + + if (tep_read_number_field(field_pid, record->data, &pid) != 0) { + /* Failed to get "common_pid" value */ + } +} +... +-- +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-fields.txt b/tools/lib/traceevent/Documentation/libtraceevent-fields.txt new file mode 100644 index 000000000000..1ccb531d5114 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-fields.txt @@ -0,0 +1,105 @@ +libtraceevent(3) +================ + +NAME +---- +tep_event_common_fields, tep_event_fields - Get a list of fields for an event. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +struct tep_format_field pass:[*]pass:[*]*tep_event_common_fields*(struct tep_event pass:[*]_event_); +struct tep_format_field pass:[*]pass:[*]*tep_event_fields*(struct tep_event pass:[*]_event_); +-- + +DESCRIPTION +----------- +The _tep_event_common_fields()_ function returns an array of pointers to common +fields for the _event_. The array is allocated in the function and must be freed +by free(). The last element of the array is NULL. + +The _tep_event_fields()_ function returns an array of pointers to event specific +fields for the _event_. The array is allocated in the function and must be freed +by free(). The last element of the array is NULL. + +RETURN VALUE +------------ +Both _tep_event_common_fields()_ and _tep_event_fields()_ functions return +an array of pointers to tep_format_field structures in case of success, or +NULL in case of an error. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +int i; +struct tep_format_field **fields; +struct tep_event *event = tep_find_event_by_name(tep, "kvm", "kvm_exit"); +if (event != NULL) { + fields = tep_event_common_fields(event); + if (fields != NULL) { + i = 0; + while (fields[i]) { + /* + walk through the list of the common fields + of the kvm_exit event + */ + i++; + } + free(fields); + } + fields = tep_event_fields(event); + if (fields != NULL) { + i = 0; + while (fields[i]) { + /* + walk through the list of the event specific + fields of the kvm_exit event + */ + i++; + } + free(fields); + } +} +... +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-file_endian.txt b/tools/lib/traceevent/Documentation/libtraceevent-file_endian.txt new file mode 100644 index 000000000000..f401ad311047 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-file_endian.txt @@ -0,0 +1,91 @@ +libtraceevent(3) +================ + +NAME +---- +tep_is_file_bigendian, tep_set_file_bigendian - Get / set the endianness of the +raw data being accessed by the tep handler. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +enum *tep_endian* { + TEP_LITTLE_ENDIAN = 0, + TEP_BIG_ENDIAN +}; + +bool *tep_is_file_bigendian*(struct tep_handle pass:[*]_tep_); +void *tep_set_file_bigendian*(struct tep_handle pass:[*]_tep_, enum tep_endian _endian_); + +-- +DESCRIPTION +----------- +The _tep_is_file_bigendian()_ function gets the endianness of the raw data, +being accessed by the tep handler. The _tep_ argument is trace event parser +context. + +The _tep_set_file_bigendian()_ function sets the endianness of raw data being +accessed by the tep handler. The _tep_ argument is trace event parser context. +[verse] +-- +The _endian_ argument is the endianness: + _TEP_LITTLE_ENDIAN_ - the raw data is in little endian format, + _TEP_BIG_ENDIAN_ - the raw data is in big endian format. +-- +RETURN VALUE +------------ +The _tep_is_file_bigendian()_ function returns true if the data is in bigendian +format, false otherwise. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... + tep_set_file_bigendian(tep, TEP_LITTLE_ENDIAN); +... + if (tep_is_file_bigendian(tep)) { + /* The raw data is in big endian */ + } else { + /* The raw data is in little endian */ + } +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-filter.txt b/tools/lib/traceevent/Documentation/libtraceevent-filter.txt new file mode 100644 index 000000000000..4a9962d8cb59 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-filter.txt @@ -0,0 +1,209 @@ +libtraceevent(3) +================ + +NAME +---- +tep_filter_alloc, tep_filter_free, tep_filter_reset, tep_filter_make_string, +tep_filter_copy, tep_filter_compare, tep_filter_match, tep_event_filtered, +tep_filter_remove_event, tep_filter_strerror, tep_filter_add_filter_str - +Event filter related APIs. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +struct tep_event_filter pass:[*]*tep_filter_alloc*(struct tep_handle pass:[*]_tep_); +void *tep_filter_free*(struct tep_event_filter pass:[*]_filter_); +void *tep_filter_reset*(struct tep_event_filter pass:[*]_filter_); +enum tep_errno *tep_filter_add_filter_str*(struct tep_event_filter pass:[*]_filter_, const char pass:[*]_filter_str_); +int *tep_event_filtered*(struct tep_event_filter pass:[*]_filter_, int _event_id_); +int *tep_filter_remove_event*(struct tep_event_filter pass:[*]_filter_, int _event_id_); +enum tep_errno *tep_filter_match*(struct tep_event_filter pass:[*]_filter_, struct tep_record pass:[*]_record_); +int *tep_filter_copy*(struct tep_event_filter pass:[*]_dest_, struct tep_event_filter pass:[*]_source_); +int *tep_filter_compare*(struct tep_event_filter pass:[*]_filter1_, struct tep_event_filter pass:[*]_filter2_); +char pass:[*]*tep_filter_make_string*(struct tep_event_filter pass:[*]_filter_, int _event_id_); +int *tep_filter_strerror*(struct tep_event_filter pass:[*]_filter_, enum tep_errno _err_, char pass:[*]buf, size_t _buflen_); +-- + +DESCRIPTION +----------- +Filters can be attached to traced events. They can be used to filter out various +events when outputting them. Each event can be filtered based on its parameters, +described in the event's format file. This set of functions can be used to +create, delete, modify and attach event filters. + +The _tep_filter_alloc()_ function creates a new event filter. The _tep_ argument +is the trace event parser context. + +The _tep_filter_free()_ function frees an event filter and all resources that it +had used. + +The _tep_filter_reset()_ function removes all rules from an event filter and +resets it. + +The _tep_filter_add_filter_str()_ function adds a new rule to the _filter_. The +_filter_str_ argument is the filter string, that contains the rule. + +The _tep_event_filtered()_ function checks if the event with _event_id_ has +_filter_. + +The _tep_filter_remove_event()_ function removes a _filter_ for an event with +_event_id_. + +The _tep_filter_match()_ function tests if a _record_ matches given _filter_. + +The _tep_filter_copy()_ function copies a _source_ filter into a _dest_ filter. + +The _tep_filter_compare()_ function compares two filers - _filter1_ and _filter2_. + +The _tep_filter_make_string()_ function constructs a string, displaying +the _filter_ contents for given _event_id_. + +The _tep_filter_strerror()_ function copies the _filter_ error buffer into the +given _buf_ with the size _buflen_. If the error buffer is empty, in the _buf_ +is copied a string, describing the error _err_. + +RETURN VALUE +------------ +The _tep_filter_alloc()_ function returns a pointer to the newly created event +filter, or NULL in case of an error. + +The _tep_filter_add_filter_str()_ function returns 0 if the rule was +successfully added or a negative error code. Use _tep_filter_strerror()_ to see +actual error message in case of an error. + +The _tep_event_filtered()_ function returns 1 if the filter is found for given +event, or 0 otherwise. + +The _tep_filter_remove_event()_ function returns 1 if the vent was removed, or +0 if the event was not found. + +The _tep_filter_match()_ function returns _tep_errno_, according to the result: +[verse] +-- +_pass:[TEP_ERRNO__FILTER_MATCH]_ - filter found for event, the record matches. +_pass:[TEP_ERRNO__FILTER_MISS]_ - filter found for event, the record does not match. +_pass:[TEP_ERRNO__FILTER_NOT_FOUND]_ - no filter found for record's event. +_pass:[TEP_ERRNO__NO_FILTER]_ - no rules in the filter. +-- +or any other _tep_errno_, if an error occurred during the test. + +The _tep_filter_copy()_ function returns 0 on success or -1 if not all rules + were copied. + +The _tep_filter_compare()_ function returns 1 if the two filters hold the same +content, or 0 if they do not. + +The _tep_filter_make_string()_ function returns a string, which must be freed +with free(), or NULL in case of an error. + +The _tep_filter_strerror()_ function returns 0 if message was filled +successfully, or -1 in case of an error. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +char errstr[200]; +int ret; + +struct tep_event_filter *filter = tep_filter_alloc(tep); +struct tep_event_filter *filter1 = tep_filter_alloc(tep); +ret = tep_filter_add_filter_str(filter, "sched/sched_wakeup:target_cpu==1"); +if(ret < 0) { + tep_filter_strerror(filter, ret, errstr, sizeof(errstr)); + /* Failed to add a new rule to the filter, the error string is in errstr */ +} +if (tep_filter_copy(filter1, filter) != 0) { + /* Failed to copy filter in filter1 */ +} +... +if (tep_filter_compare(filter, filter1) != 1) { + /* Both filters are different */ +} +... +void process_record(struct tep_handle *tep, struct tep_record *record) +{ + struct tep_event *event; + char *fstring; + + event = tep_find_event_by_record(tep, record); + + if (tep_event_filtered(filter, event->id) == 1) { + /* The event has filter */ + fstring = tep_filter_make_string(filter, event->id); + if (fstring != NULL) { + /* The filter for the event is in fstring */ + free(fstring); + } + } + + switch (tep_filter_match(filter, record)) { + case TEP_ERRNO__FILTER_MATCH: + /* The filter matches the record */ + break; + case TEP_ERRNO__FILTER_MISS: + /* The filter does not match the record */ + break; + case TEP_ERRNO__FILTER_NOT_FOUND: + /* No filter found for record's event */ + break; + case TEP_ERRNO__NO_FILTER: + /* There are no rules in the filter */ + break + default: + /* An error occurred during the test */ + break; + } + + if (tep_filter_remove_event(filter, event->id) == 1) { + /* The event was removed from the filter */ + } +} + +... +tep_filter_reset(filter); +... +tep_filter_free(filter); +tep_filter_free(filter1); +... +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-func_apis.txt b/tools/lib/traceevent/Documentation/libtraceevent-func_apis.txt new file mode 100644 index 000000000000..38bfea30a5f6 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-func_apis.txt @@ -0,0 +1,183 @@ +libtraceevent(3) +================ + +NAME +---- +tep_find_function, tep_find_function_address, tep_set_function_resolver, +tep_reset_function_resolver, tep_register_function, tep_register_print_string - +function related tep APIs + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +typedef char pass:[*](*tep_func_resolver_t*)(void pass:[*]_priv_, unsigned long long pass:[*]_addrp_, char pass:[**]_modp_); +int *tep_set_function_resolver*(struct tep_handle pass:[*]_tep_, tep_func_resolver_t pass:[*]_func_, void pass:[*]_priv_); +void *tep_reset_function_resolver*(struct tep_handle pass:[*]_tep_); +const char pass:[*]*tep_find_function*(struct tep_handle pass:[*]_tep_, unsigned long long _addr_); +unsigned long long *tep_find_function_address*(struct tep_handle pass:[*]_tep_, unsigned long long _addr_); +int *tep_register_function*(struct tep_handle pass:[*]_tep_, char pass:[*]_name_, unsigned long long _addr_, char pass:[*]_mod_); +int *tep_register_print_string*(struct tep_handle pass:[*]_tep_, const char pass:[*]_fmt_, unsigned long long _addr_); +-- + +DESCRIPTION +----------- +Some tools may have already a way to resolve the kernel functions. These APIs +allow them to keep using it instead of duplicating all the entries inside. + +The _tep_func_resolver_t_ type is the prototype of the alternative kernel +functions resolver. This function receives a pointer to its custom context +(set with the _tep_set_function_resolver()_ call ) and the address of a kernel +function, which has to be resolved. In case of success, it should return +the name of the function and its module (if any) in _modp_. + +The _tep_set_function_resolver()_ function registers _func_ as an alternative +kernel functions resolver. The _tep_ argument is trace event parser context. +The _priv_ argument is a custom context of the _func_ function. The function +resolver is used by the APIs _tep_find_function()_, +_tep_find_function_address()_, and _tep_print_func_field()_ to resolve +a function address to a function name. + +The _tep_reset_function_resolver()_ function resets the kernel functions +resolver to the default function. The _tep_ argument is trace event parser +context. + + +These APIs can be used to find function name and start address, by given +address. The given address does not have to be exact, it will select +the function that would contain it. + +The _tep_find_function()_ function returns the function name, which contains the +given address _addr_. The _tep_ argument is the trace event parser context. + +The _tep_find_function_address()_ function returns the function start address, +by given address _addr_. The _addr_ does not have to be exact, it will select +the function that would contain it. The _tep_ argument is the trace event +parser context. + +The _tep_register_function()_ function registers a function name mapped to an +address and (optional) module. This mapping is used in case the function tracer +or events have "%pF" or "%pS" parameter in its format string. It is common to +pass in the kallsyms function names with their corresponding addresses with this +function. The _tep_ argument is the trace event parser context. The _name_ is +the name of the function, the string is copied internally. The _addr_ is +the start address of the function. The _mod_ is the kernel module +the function may be in (NULL for none). + +The _tep_register_print_string()_ function registers a string by the address +it was stored in the kernel. Some strings internal to the kernel with static +address are passed to certain events. The "%s" in the event's format field +which has an address needs to know what string would be at that address. The +tep_register_print_string() supplies the parsing with the mapping between kernel +addresses and those strings. The _tep_ argument is the trace event parser +context. The _fmt_ is the string to register, it is copied internally. +The _addr_ is the address the string was located at. + + +RETURN VALUE +------------ +The _tep_set_function_resolver()_ function returns 0 in case of success, or -1 +in case of an error. + +The _tep_find_function()_ function returns the function name, or NULL in case +it cannot be found. + +The _tep_find_function_address()_ function returns the function start address, +or 0 in case it cannot be found. + +The _tep_register_function()_ function returns 0 in case of success. In case of +an error -1 is returned, and errno is set to the appropriate error number. + +The _tep_register_print_string()_ function returns 0 in case of success. In case +of an error -1 is returned, and errno is set to the appropriate error number. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +char *my_resolve_kernel_addr(void *context, + unsigned long long *addrp, char **modp) +{ + struct db *function_database = context; + struct symbol *sym = sql_lookup(function_database, *addrp); + + if (!sym) + return NULL; + + *modp = sym->module_name; + return sym->name; +} + +void show_function( unsigned long long addr) +{ + unsigned long long fstart; + const char *fname; + + if (tep_set_function_resolver(tep, my_resolve_kernel_addr, + function_database) != 0) { + /* failed to register my_resolve_kernel_addr */ + } + + /* These APIs use my_resolve_kernel_addr() to resolve the addr */ + fname = tep_find_function(tep, addr); + fstart = tep_find_function_address(tep, addr); + + /* + addr is in function named fname, starting at fstart address, + at offset (addr - fstart) + */ + + tep_reset_function_resolver(tep); + +} +... + if (tep_register_function(tep, "kvm_exit", + (unsigned long long) 0x12345678, "kvm") != 0) { + /* Failed to register kvm_exit address mapping */ + } +... + if (tep_register_print_string(tep, "print string", + (unsigned long long) 0x87654321, NULL) != 0) { + /* Failed to register "print string" address mapping */ + } +... +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-func_find.txt b/tools/lib/traceevent/Documentation/libtraceevent-func_find.txt new file mode 100644 index 000000000000..04840e244445 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-func_find.txt @@ -0,0 +1,88 @@ +libtraceevent(3) +================ + +NAME +---- +tep_find_function,tep_find_function_address - Find function name / start address. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +const char pass:[*]*tep_find_function*(struct tep_handle pass:[*]_tep_, unsigned long long _addr_); +unsigned long long *tep_find_function_address*(struct tep_handle pass:[*]_tep_, unsigned long long _addr_); +-- + +DESCRIPTION +----------- +These functions can be used to find function name and start address, by given +address. The given address does not have to be exact, it will select the function +that would contain it. + +The _tep_find_function()_ function returns the function name, which contains the +given address _addr_. The _tep_ argument is the trace event parser context. + +The _tep_find_function_address()_ function returns the function start address, +by given address _addr_. The _addr_ does not have to be exact, it will select the +function that would contain it. The _tep_ argument is the trace event parser context. + +RETURN VALUE +------------ +The _tep_find_function()_ function returns the function name, or NULL in case +it cannot be found. + +The _tep_find_function_address()_ function returns the function start address, +or 0 in case it cannot be found. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +void show_function( unsigned long long addr) +{ + const char *fname = tep_find_function(tep, addr); + unsigned long long fstart = tep_find_function_address(tep, addr); + + /* addr is in function named fname, starting at fstart address, at offset (addr - fstart) */ +} +... +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-handle.txt b/tools/lib/traceevent/Documentation/libtraceevent-handle.txt new file mode 100644 index 000000000000..8d568316847d --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-handle.txt @@ -0,0 +1,101 @@ +libtraceevent(3) +================ + +NAME +---- +tep_alloc, tep_free,tep_ref, tep_unref,tep_ref_get - Create, destroy, manage +references of trace event parser context. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +struct tep_handle pass:[*]*tep_alloc*(void); +void *tep_free*(struct tep_handle pass:[*]_tep_); +void *tep_ref*(struct tep_handle pass:[*]_tep_); +void *tep_unref*(struct tep_handle pass:[*]_tep_); +int *tep_ref_get*(struct tep_handle pass:[*]_tep_); +-- + +DESCRIPTION +----------- +These are the main functions to create and destroy tep_handle - the main +structure, representing the trace event parser context. This context is used as +the input parameter of most library APIs. + +The _tep_alloc()_ function allocates and initializes the tep context. + +The _tep_free()_ function will decrement the reference of the _tep_ handler. +When there is no more references, then it will free the handler, as well +as clean up all its resources that it had used. The argument _tep_ is +the pointer to the trace event parser context. + +The _tep_ref()_ function adds a reference to the _tep_ handler. + +The _tep_unref()_ function removes a reference from the _tep_ handler. When +the last reference is removed, the _tep_ is destroyed, and all resources that +it had used are cleaned up. + +The _tep_ref_get()_ functions gets the current references of the _tep_ handler. + +RETURN VALUE +------------ +_tep_alloc()_ returns a pointer to a newly created tep_handle structure. +NULL is returned in case there is not enough free memory to allocate it. + +_tep_ref_get()_ returns the current references of _tep_. +If _tep_ is NULL, 0 is returned. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> + +... +struct tep_handle *tep = tep_alloc(); +... +int ref = tep_ref_get(tep); +tep_ref(tep); +if ( (ref+1) != tep_ref_get(tep)) { + /* Something wrong happened, the counter is not incremented by 1 */ +} +tep_unref(tep); +... +tep_free(tep); +... +-- +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-header_page.txt b/tools/lib/traceevent/Documentation/libtraceevent-header_page.txt new file mode 100644 index 000000000000..615d117dc39f --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-header_page.txt @@ -0,0 +1,102 @@ +libtraceevent(3) +================ + +NAME +---- +tep_get_header_page_size, tep_get_header_timestamp_size, tep_is_old_format - +Get the data stored in the header page, in kernel context. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +int *tep_get_header_page_size*(struct tep_handle pass:[*]_tep_); +int *tep_get_header_timestamp_size*(struct tep_handle pass:[*]_tep_); +bool *tep_is_old_format*(struct tep_handle pass:[*]_tep_); +-- +DESCRIPTION +----------- +These functions retrieve information from kernel context, stored in tracefs +events/header_page. Old kernels do not have header page info, so default values +from user space context are used. + +The _tep_get_header_page_size()_ function returns the size of a long integer, +in kernel context. The _tep_ argument is trace event parser context. +This information is retrieved from tracefs events/header_page, "commit" field. + +The _tep_get_header_timestamp_size()_ function returns the size of timestamps, +in kernel context. The _tep_ argument is trace event parser context. This +information is retrieved from tracefs events/header_page, "timestamp" field. + +The _tep_is_old_format()_ function returns true if the kernel predates +the addition of events/header_page, otherwise it returns false. + +RETURN VALUE +------------ +The _tep_get_header_page_size()_ function returns the size of a long integer, +in bytes. + +The _tep_get_header_timestamp_size()_ function returns the size of timestamps, +in bytes. + +The _tep_is_old_format()_ function returns true, if an old kernel is used to +generate the tracing data, which has no event/header_page. If the kernel is new, +or _tep_ is NULL, false is returned. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... + int longsize; + int timesize; + bool old; + + longsize = tep_get_header_page_size(tep); + timesize = tep_get_header_timestamp_size(tep); + old = tep_is_old_format(tep); + + printf ("%s kernel is used to generate the tracing data.\n", + old?"Old":"New"); + printf("The size of a long integer is %d bytes.\n", longsize); + printf("The timestamps size is %d bytes.\n", timesize); +... +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-host_endian.txt b/tools/lib/traceevent/Documentation/libtraceevent-host_endian.txt new file mode 100644 index 000000000000..d5d375eb8d1e --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-host_endian.txt @@ -0,0 +1,104 @@ +libtraceevent(3) +================ + +NAME +---- +tep_is_bigendian, tep_is_local_bigendian, tep_set_local_bigendian - Get / set +the endianness of the local machine. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +enum *tep_endian* { + TEP_LITTLE_ENDIAN = 0, + TEP_BIG_ENDIAN +}; + +int *tep_is_bigendian*(void); +bool *tep_is_local_bigendian*(struct tep_handle pass:[*]_tep_); +void *tep_set_local_bigendian*(struct tep_handle pass:[*]_tep_, enum tep_endian _endian_); +-- + +DESCRIPTION +----------- + +The _tep_is_bigendian()_ gets the endianness of the machine, executing +the function. + +The _tep_is_local_bigendian()_ function gets the endianness of the local +machine, saved in the _tep_ handler. The _tep_ argument is the trace event +parser context. This API is a bit faster than _tep_is_bigendian()_, as it +returns cached endianness of the local machine instead of checking it each time. + +The _tep_set_local_bigendian()_ function sets the endianness of the local +machine in the _tep_ handler. The _tep_ argument is trace event parser context. +The _endian_ argument is the endianness: +[verse] +-- + _TEP_LITTLE_ENDIAN_ - the machine is little endian, + _TEP_BIG_ENDIAN_ - the machine is big endian. +-- + +RETURN VALUE +------------ +The _tep_is_bigendian()_ function returns non zero if the endianness of the +machine, executing the code, is big endian and zero otherwise. + +The _tep_is_local_bigendian()_ function returns true, if the endianness of the +local machine, saved in the _tep_ handler, is big endian, or false otherwise. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... + if (tep_is_bigendian()) + tep_set_local_bigendian(tep, TEP_BIG_ENDIAN); + else + tep_set_local_bigendian(tep, TEP_LITTLE_ENDIAN); +... + if (tep_is_local_bigendian(tep)) + printf("This machine you are running on is bigendian\n"); + else + printf("This machine you are running on is little endian\n"); + +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-long_size.txt b/tools/lib/traceevent/Documentation/libtraceevent-long_size.txt new file mode 100644 index 000000000000..01d78ea2519a --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-long_size.txt @@ -0,0 +1,78 @@ +libtraceevent(3) +================ + +NAME +---- +tep_get_long_size, tep_set_long_size - Get / set the size of a long integer on +the machine, where the trace is generated, in bytes + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +int *tep_get_long_size*(strucqt tep_handle pass:[*]_tep_); +void *tep_set_long_size*(struct tep_handle pass:[*]_tep_, int _long_size_); +-- + +DESCRIPTION +----------- +The _tep_get_long_size()_ function returns the size of a long integer on the machine, +where the trace is generated. The _tep_ argument is trace event parser context. + +The _tep_set_long_size()_ function sets the size of a long integer on the machine, +where the trace is generated. The _tep_ argument is trace event parser context. +The _long_size_ is the size of a long integer, in bytes. + +RETURN VALUE +------------ +The _tep_get_long_size()_ function returns the size of a long integer on the machine, +where the trace is generated, in bytes. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +tep_set_long_size(tep, 4); +... +int long_size = tep_get_long_size(tep); +... +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-page_size.txt b/tools/lib/traceevent/Documentation/libtraceevent-page_size.txt new file mode 100644 index 000000000000..452c0cfa1822 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-page_size.txt @@ -0,0 +1,82 @@ +libtraceevent(3) +================ + +NAME +---- +tep_get_page_size, tep_set_page_size - Get / set the size of a memory page on +the machine, where the trace is generated + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +int *tep_get_page_size*(struct tep_handle pass:[*]_tep_); +void *tep_set_page_size*(struct tep_handle pass:[*]_tep_, int _page_size_); +-- + +DESCRIPTION +----------- +The _tep_get_page_size()_ function returns the size of a memory page on +the machine, where the trace is generated. The _tep_ argument is trace +event parser context. + +The _tep_set_page_size()_ function stores in the _tep_ context the size of a +memory page on the machine, where the trace is generated. +The _tep_ argument is trace event parser context. +The _page_size_ argument is the size of a memory page, in bytes. + +RETURN VALUE +------------ +The _tep_get_page_size()_ function returns size of the memory page, in bytes. + +EXAMPLE +------- +[source,c] +-- +#include <unistd.h> +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... + int page_size = getpagesize(); + + tep_set_page_size(tep, page_size); + + printf("The page size for this machine is %d\n", tep_get_page_size(tep)); + +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-parse_event.txt b/tools/lib/traceevent/Documentation/libtraceevent-parse_event.txt new file mode 100644 index 000000000000..f248114ca1ff --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-parse_event.txt @@ -0,0 +1,90 @@ +libtraceevent(3) +================ + +NAME +---- +tep_parse_event, tep_parse_format - Parse the event format information + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +enum tep_errno *tep_parse_event*(struct tep_handle pass:[*]_tep_, const char pass:[*]_buf_, unsigned long _size_, const char pass:[*]_sys_); +enum tep_errno *tep_parse_format*(struct tep_handle pass:[*]_tep_, struct tep_event pass:[*]pass:[*]_eventp_, const char pass:[*]_buf_, unsigned long _size_, const char pass:[*]_sys_); +-- + +DESCRIPTION +----------- +The _tep_parse_event()_ function parses the event format and creates an event +structure to quickly parse raw data for a given event. The _tep_ argument is +the trace event parser context. The created event structure is stored in the +_tep_ context. The _buf_ argument is a buffer with _size_, where the event +format data is. The event format data can be taken from +tracefs/events/.../.../format files. The _sys_ argument is the system of +the event. + +The _tep_parse_format()_ function does the same as _tep_parse_event()_. The only +difference is in the extra _eventp_ argument, where the newly created event +structure is returned. + +RETURN VALUE +------------ +Both _tep_parse_event()_ and _tep_parse_format()_ functions return 0 on success, +or TEP_ERRNO__... in case of an error. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +char *buf; +int size; +struct tep_event *event = NULL; +buf = read_file("/sys/kernel/tracing/events/ftrace/print/format", &size); +if (tep_parse_event(tep, buf, size, "ftrace") != 0) { + /* Failed to parse the ftrace print format */ +} + +if (tep_parse_format(tep, &event, buf, size, "ftrace") != 0) { + /* Failed to parse the ftrace print format */ +} +... +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-parse_head.txt b/tools/lib/traceevent/Documentation/libtraceevent-parse_head.txt new file mode 100644 index 000000000000..c90f16c7d8e6 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-parse_head.txt @@ -0,0 +1,82 @@ +libtraceevent(3) +================ + +NAME +---- +tep_parse_header_page - Parses the data stored in the header page. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +int *tep_parse_header_page*(struct tep_handle pass:[*]_tep_, char pass:[*]_buf_, unsigned long _size_, int _long_size_); +-- + +DESCRIPTION +----------- +The _tep_parse_header_page()_ function parses the header page data from _buf_, +and initializes the _tep_, trace event parser context, with it. The buffer +_buf_ is with _size_, and is supposed to be copied from +tracefs/events/header_page. + +Some old kernels do not have header page info, in this case the +_tep_parse_header_page()_ function can be called with _size_ equal to 0. The +_tep_ context is initialized with default values. The _long_size_ can be used in +this use case, to set the size of a long integer to be used. + +RETURN VALUE +------------ +The _tep_parse_header_page()_ function returns 0 in case of success, or -1 +in case of an error. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +char *buf; +int size; +buf = read_file("/sys/kernel/tracing/events/header_page", &size); +if (tep_parse_header_page(tep, buf, size, sizeof(unsigned long)) != 0) { + /* Failed to parse the header page */ +} +... +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-record_parse.txt b/tools/lib/traceevent/Documentation/libtraceevent-record_parse.txt new file mode 100644 index 000000000000..e9a69116c78b --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-record_parse.txt @@ -0,0 +1,137 @@ +libtraceevent(3) +================ + +NAME +---- +tep_data_type, tep_data_pid,tep_data_preempt_count, tep_data_flags - +Extract common fields from a record. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +enum *trace_flag_type* { + _TRACE_FLAG_IRQS_OFF_, + _TRACE_FLAG_IRQS_NOSUPPORT_, + _TRACE_FLAG_NEED_RESCHED_, + _TRACE_FLAG_HARDIRQ_, + _TRACE_FLAG_SOFTIRQ_, +}; + +int *tep_data_type*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_rec_); +int *tep_data_pid*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_rec_); +int *tep_data_preempt_count*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_rec_); +int *tep_data_flags*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_rec_); +-- + +DESCRIPTION +----------- +This set of functions can be used to extract common fields from a record. + +The _tep_data_type()_ function gets the event id from the record _rec_. +It reads the "common_type" field. The _tep_ argument is the trace event parser +context. + +The _tep_data_pid()_ function gets the process id from the record _rec_. +It reads the "common_pid" field. The _tep_ argument is the trace event parser +context. + +The _tep_data_preempt_count()_ function gets the preemption count from the +record _rec_. It reads the "common_preempt_count" field. The _tep_ argument is +the trace event parser context. + +The _tep_data_flags()_ function gets the latency flags from the record _rec_. +It reads the "common_flags" field. The _tep_ argument is the trace event parser +context. Supported latency flags are: +[verse] +-- + _TRACE_FLAG_IRQS_OFF_, Interrupts are disabled. + _TRACE_FLAG_IRQS_NOSUPPORT_, Reading IRQ flag is not supported by the architecture. + _TRACE_FLAG_NEED_RESCHED_, Task needs rescheduling. + _TRACE_FLAG_HARDIRQ_, Hard IRQ is running. + _TRACE_FLAG_SOFTIRQ_, Soft IRQ is running. +-- + +RETURN VALUE +------------ +The _tep_data_type()_ function returns an integer, representing the event id. + +The _tep_data_pid()_ function returns an integer, representing the process id + +The _tep_data_preempt_count()_ function returns an integer, representing the +preemption count. + +The _tep_data_flags()_ function returns an integer, representing the latency +flags. Look at the _trace_flag_type_ enum for supported flags. + +All these functions in case of an error return a negative integer. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +void process_record(struct tep_record *record) +{ + int data; + + data = tep_data_type(tep, record); + if (data >= 0) { + /* Got the ID of the event */ + } + + data = tep_data_pid(tep, record); + if (data >= 0) { + /* Got the process ID */ + } + + data = tep_data_preempt_count(tep, record); + if (data >= 0) { + /* Got the preemption count */ + } + + data = tep_data_flags(tep, record); + if (data >= 0) { + /* Got the latency flags */ + } +} +... +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-reg_event_handler.txt b/tools/lib/traceevent/Documentation/libtraceevent-reg_event_handler.txt new file mode 100644 index 000000000000..53d37d72a1c1 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-reg_event_handler.txt @@ -0,0 +1,156 @@ +libtraceevent(3) +================ + +NAME +---- +tep_register_event_handler, tep_unregister_event_handler - Register / +unregisters a callback function to parse an event information. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +enum *tep_reg_handler* { + _TEP_REGISTER_SUCCESS_, + _TEP_REGISTER_SUCCESS_OVERWRITE_, +}; + +int *tep_register_event_handler*(struct tep_handle pass:[*]_tep_, int _id_, const char pass:[*]_sys_name_, const char pass:[*]_event_name_, tep_event_handler_func _func_, void pass:[*]_context_); +int *tep_unregister_event_handler*(struct tep_handle pass:[*]tep, int id, const char pass:[*]sys_name, const char pass:[*]event_name, tep_event_handler_func func, void pass:[*]_context_); + +typedef int (*pass:[*]tep_event_handler_func*)(struct trace_seq pass:[*]s, struct tep_record pass:[*]record, struct tep_event pass:[*]event, void pass:[*]context); +-- + +DESCRIPTION +----------- +The _tep_register_event_handler()_ function registers a handler function, +which is going to be called to parse the information for a given event. +The _tep_ argument is the trace event parser context. The _id_ argument is +the id of the event. The _sys_name_ argument is the name of the system, +the event belongs to. The _event_name_ argument is the name of the event. +If _id_ is >= 0, it is used to find the event, otherwise _sys_name_ and +_event_name_ are used. The _func_ is a pointer to the function, which is going +to be called to parse the event information. The _context_ argument is a pointer +to the context data, which will be passed to the _func_. If a handler function +for the same event is already registered, it will be overridden with the new +one. This mechanism allows a developer to override the parsing of a given event. +If for some reason the default print format is not sufficient, the developer +can register a function for an event to be used to parse the data instead. + +The _tep_unregister_event_handler()_ function unregisters the handler function, +previously registered with _tep_register_event_handler()_. The _tep_ argument +is the trace event parser context. The _id_, _sys_name_, _event_name_, _func_, +and _context_ are the same arguments, as when the callback function _func_ was +registered. + +The _tep_event_handler_func_ is the type of the custom event handler +function. The _s_ argument is the trace sequence, it can be used to create a +custom string, describing the event. A _record_ to get the event from is passed +as input parameter and also the _event_ - the handle to the record's event. The +_context_ is custom context, set when the custom event handler is registered. + +RETURN VALUE +------------ +The _tep_register_event_handler()_ function returns _TEP_REGISTER_SUCCESS_ +if the new handler is registered successfully or +_TEP_REGISTER_SUCCESS_OVERWRITE_ if an existing handler is overwritten. +If there is not enough memory to complete the registration, +TEP_ERRNO__MEM_ALLOC_FAILED is returned. + +The _tep_unregister_event_handler()_ function returns 0 if _func_ was removed +successful or, -1 if the event was not found. + +The _tep_event_handler_func_ should return -1 in case of an error, +or 0 otherwise. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +#include <trace-seq.h> +... +struct tep_handle *tep = tep_alloc(); +... +int timer_expire_handler(struct trace_seq *s, struct tep_record *record, + struct tep_event *event, void *context) +{ + trace_seq_printf(s, "hrtimer="); + + if (tep_print_num_field(s, "0x%llx", event, "timer", record, 0) == -1) + tep_print_num_field(s, "0x%llx", event, "hrtimer", record, 1); + + trace_seq_printf(s, " now="); + + tep_print_num_field(s, "%llu", event, "now", record, 1); + + tep_print_func_field(s, " function=%s", event, "function", record, 0); + + return 0; +} +... + int ret; + + ret = tep_register_event_handler(tep, -1, "timer", "hrtimer_expire_entry", + timer_expire_handler, NULL); + if (ret < 0) { + char buf[32]; + + tep_strerror(tep, ret, buf, 32) + printf("Failed to register handler for hrtimer_expire_entry: %s\n", buf); + } else { + switch (ret) { + case TEP_REGISTER_SUCCESS: + printf ("Registered handler for hrtimer_expire_entry\n"); + break; + case TEP_REGISTER_SUCCESS_OVERWRITE: + printf ("Overwrote handler for hrtimer_expire_entry\n"); + break; + } + } +... + ret = tep_unregister_event_handler(tep, -1, "timer", "hrtimer_expire_entry", + timer_expire_handler, NULL); + if ( ret ) + printf ("Failed to unregister handler for hrtimer_expire_entry\n"); + +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*trace-seq.h* + Header file to include in order to have access to trace sequences + related APIs. Trace sequences are used to allow a function to call + several other functions to create a string of data to use. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-reg_print_func.txt b/tools/lib/traceevent/Documentation/libtraceevent-reg_print_func.txt new file mode 100644 index 000000000000..708dce91ebd8 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-reg_print_func.txt @@ -0,0 +1,155 @@ +libtraceevent(3) +================ + +NAME +---- +tep_register_print_function,tep_unregister_print_function - +Registers / Unregisters a helper function. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +enum *tep_func_arg_type* { + TEP_FUNC_ARG_VOID, + TEP_FUNC_ARG_INT, + TEP_FUNC_ARG_LONG, + TEP_FUNC_ARG_STRING, + TEP_FUNC_ARG_PTR, + TEP_FUNC_ARG_MAX_TYPES +}; + +typedef unsigned long long (*pass:[*]tep_func_handler*)(struct trace_seq pass:[*]s, unsigned long long pass:[*]args); + +int *tep_register_print_function*(struct tep_handle pass:[*]_tep_, tep_func_handler _func_, enum tep_func_arg_type _ret_type_, char pass:[*]_name_, _..._); +int *tep_unregister_print_function*(struct tep_handle pass:[*]_tep_, tep_func_handler _func_, char pass:[*]_name_); +-- + +DESCRIPTION +----------- +Some events may have helper functions in the print format arguments. +This allows a plugin to dynamically create a way to process one of +these functions. + +The _tep_register_print_function()_ registers such helper function. The _tep_ +argument is the trace event parser context. The _func_ argument is a pointer +to the helper function. The _ret_type_ argument is the return type of the +helper function, value from the _tep_func_arg_type_ enum. The _name_ is the name +of the helper function, as seen in the print format arguments. The _..._ is a +variable list of _tep_func_arg_type_ enums, the _func_ function arguments. +This list must end with _TEP_FUNC_ARG_VOID_. See 'EXAMPLE' section. + +The _tep_unregister_print_function()_ unregisters a helper function, previously +registered with _tep_register_print_function()_. The _tep_ argument is the +trace event parser context. The _func_ and _name_ arguments are the same, used +when the helper function was registered. + +The _tep_func_handler_ is the type of the helper function. The _s_ argument is +the trace sequence, it can be used to create a custom string. +The _args_ is a list of arguments, defined when the helper function was +registered. + +RETURN VALUE +------------ +The _tep_register_print_function()_ function returns 0 in case of success. +In case of an error, TEP_ERRNO_... code is returned. + +The _tep_unregister_print_function()_ returns 0 in case of success, or -1 in +case of an error. + +EXAMPLE +------- +Some events have internal functions calls, that appear in the print format +output. For example "tracefs/events/i915/g4x_wm/format" has: +[source,c] +-- +print fmt: "pipe %c, frame=%u, scanline=%u, wm %d/%d/%d, sr %s/%d/%d/%d, hpll %s/%d/%d/%d, fbc %s", + ((REC->pipe) + 'A'), REC->frame, REC->scanline, REC->primary, + REC->sprite, REC->cursor, yesno(REC->cxsr), REC->sr_plane, + REC->sr_cursor, REC->sr_fbc, yesno(REC->hpll), REC->hpll_plane, + REC->hpll_cursor, REC->hpll_fbc, yesno(REC->fbc) +-- +Notice the call to function _yesno()_ in the print arguments. In the kernel +context, this function has the following implementation: +[source,c] +-- +static const char *yesno(int x) +{ + static const char *yes = "yes"; + static const char *no = "no"; + + return x ? yes : no; +} +-- +The user space event parser has no idea how to handle this _yesno()_ function. +The _tep_register_print_function()_ API can be used to register a user space +helper function, mapped to the kernel's _yesno()_: +[source,c] +-- +#include <event-parse.h> +#include <trace-seq.h> +... +struct tep_handle *tep = tep_alloc(); +... +static const char *yes_no_helper(int x) +{ + return x ? "yes" : "no"; +} +... + if ( tep_register_print_function(tep, + yes_no_helper, + TEP_FUNC_ARG_STRING, + "yesno", + TEP_FUNC_ARG_INT, + TEP_FUNC_ARG_VOID) != 0) { + /* Failed to register yes_no_helper function */ + } + +/* + Now, when the event parser encounters this yesno() function, it will know + how to handle it. +*/ +... + if (tep_unregister_print_function(tep, yes_no_helper, "yesno") != 0) { + /* Failed to unregister yes_no_helper function */ + } +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*trace-seq.h* + Header file to include in order to have access to trace sequences + related APIs. Trace sequences are used to allow a function to call + several other functions to create a string of data to use. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-set_flag.txt b/tools/lib/traceevent/Documentation/libtraceevent-set_flag.txt new file mode 100644 index 000000000000..b0599780b9a6 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-set_flag.txt @@ -0,0 +1,104 @@ +libtraceevent(3) +================ + +NAME +---- +tep_set_flag, tep_clear_flag, tep_test_flag - +Manage flags of trace event parser context. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +enum *tep_flag* { + _TEP_NSEC_OUTPUT_, + _TEP_DISABLE_SYS_PLUGINS_, + _TEP_DISABLE_PLUGINS_ +}; +void *tep_set_flag*(struct tep_handle pass:[*]_tep_, enum tep_flag _flag_); +void *tep_clear_flag*(struct tep_handle pass:[*]_tep_, enum tep_flag _flag_); +bool *tep_test_flag*(struct tep_handle pass:[*]_tep_, enum tep_flag _flag_); +-- + +DESCRIPTION +----------- +Trace event parser context flags are defined in *enum tep_flag*: +[verse] +-- +_TEP_NSEC_OUTPUT_ - print event's timestamp in nano seconds, instead of micro seconds. +_TEP_DISABLE_SYS_PLUGINS_ - disable plugins, located in system's plugin + directory. This directory is defined at library compile + time, and usually depends on library installation + prefix: (install_preffix)/lib/traceevent/plugins +_TEP_DISABLE_PLUGINS_ - disable all library plugins: + - in system's plugin directory + - in directory, defined by the environment variable _TRACEEVENT_PLUGIN_DIR_ + - in user's home directory, _~/.traceevent/plugins_ +-- +Note: plugin related flags must me set before calling _tep_load_plugins()_ API. + +The _tep_set_flag()_ function sets _flag_ to _tep_ context. + +The _tep_clear_flag()_ function clears _flag_ from _tep_ context. + +The _tep_test_flag()_ function tests if _flag_ is set to _tep_ context. + +RETURN VALUE +------------ +_tep_test_flag()_ function returns true if _flag_ is set, false otherwise. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +/* Print timestamps in nanoseconds */ +tep_set_flag(tep, TEP_NSEC_OUTPUT); +... +if (tep_test_flag(tep, TEP_NSEC_OUTPUT)) { + /* print timestamps in nanoseconds */ +} else { + /* print timestamps in microseconds */ +} +... +/* Print timestamps in microseconds */ +tep_clear_flag(tep, TEP_NSEC_OUTPUT); +... +-- +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-strerror.txt b/tools/lib/traceevent/Documentation/libtraceevent-strerror.txt new file mode 100644 index 000000000000..ee4062a00c9f --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-strerror.txt @@ -0,0 +1,85 @@ +libtraceevent(3) +================ + +NAME +---- +tep_strerror - Returns a string describing regular errno and tep error number. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +int *tep_strerror*(struct tep_handle pass:[*]_tep_, enum tep_errno _errnum_, char pass:[*]_buf_, size_t _buflen_); + +-- +DESCRIPTION +----------- +The _tep_strerror()_ function converts tep error number into a human +readable string. +The _tep_ argument is trace event parser context. The _errnum_ is a regular +errno, defined in errno.h, or a tep error number. The string, describing this +error number is copied in the _buf_ argument. The _buflen_ argument is +the size of the _buf_. + +It as a thread safe wrapper around strerror_r(). The library function has two +different behaviors - POSIX and GNU specific. The _tep_strerror()_ API always +behaves as the POSIX version - the error string is copied in the user supplied +buffer. + +RETURN VALUE +------------ +The _tep_strerror()_ function returns 0, if a valid _errnum_ is passed and the +string is copied into _buf_. If _errnum_ is not a valid error number, +-1 is returned and _buf_ is not modified. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +char buf[32]; +char *pool = calloc(1, 128); +if (tep == NULL) { + tep_strerror(tep, TEP_ERRNO__MEM_ALLOC_FAILED, buf, 32); + printf ("The pool is not initialized, %s", buf); +} +... +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-tseq.txt b/tools/lib/traceevent/Documentation/libtraceevent-tseq.txt new file mode 100644 index 000000000000..8ac6aa174e12 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-tseq.txt @@ -0,0 +1,158 @@ +libtraceevent(3) +================ + +NAME +---- +trace_seq_init, trace_seq_destroy, trace_seq_reset, trace_seq_terminate, +trace_seq_putc, trace_seq_puts, trace_seq_printf, trace_seq_vprintf, +trace_seq_do_fprintf, trace_seq_do_printf - +Initialize / destroy a trace sequence. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* +*#include <trace-seq.h>* + +void *trace_seq_init*(struct trace_seq pass:[*]_s_); +void *trace_seq_destroy*(struct trace_seq pass:[*]_s_); +void *trace_seq_reset*(struct trace_seq pass:[*]_s_); +void *trace_seq_terminate*(struct trace_seq pass:[*]_s_); +int *trace_seq_putc*(struct trace_seq pass:[*]_s_, unsigned char _c_); +int *trace_seq_puts*(struct trace_seq pass:[*]_s_, const char pass:[*]_str_); +int *trace_seq_printf*(struct trace_seq pass:[*]_s_, const char pass:[*]_fmt_, _..._); +int *trace_seq_vprintf*(struct trace_seq pass:[*]_s_, const char pass:[*]_fmt_, va_list _args_); +int *trace_seq_do_printf*(struct trace_seq pass:[*]_s_); +int *trace_seq_do_fprintf*(struct trace_seq pass:[*]_s_, FILE pass:[*]_fp_); +-- + +DESCRIPTION +----------- +Trace sequences are used to allow a function to call several other functions +to create a string of data to use. + +The _trace_seq_init()_ function initializes the trace sequence _s_. + +The _trace_seq_destroy()_ function destroys the trace sequence _s_ and frees +all its resources that it had used. + +The _trace_seq_reset()_ function re-initializes the trace sequence _s_. All +characters already written in _s_ will be deleted. + +The _trace_seq_terminate()_ function terminates the trace sequence _s_. It puts +the null character pass:['\0'] at the end of the buffer. + +The _trace_seq_putc()_ function puts a single character _c_ in the trace +sequence _s_. + +The _trace_seq_puts()_ function puts a NULL terminated string _str_ in the +trace sequence _s_. + +The _trace_seq_printf()_ function puts a formated string _fmt _with +variable arguments _..._ in the trace sequence _s_. + +The _trace_seq_vprintf()_ function puts a formated string _fmt _with +list of arguments _args_ in the trace sequence _s_. + +The _trace_seq_do_printf()_ function prints the buffer of trace sequence _s_ to +the standard output stdout. + +The _trace_seq_do_fprintf()_ function prints the buffer of trace sequence _s_ +to the given file _fp_. + +RETURN VALUE +------------ +Both _trace_seq_putc()_ and _trace_seq_puts()_ functions return the number of +characters put in the trace sequence, or 0 in case of an error + +Both _trace_seq_printf()_ and _trace_seq_vprintf()_ functions return 0 if the +trace oversizes the buffer's free space, the number of characters printed, or +a negative value in case of an error. + +Both _trace_seq_do_printf()_ and _trace_seq_do_fprintf()_ functions return the +number of printed characters, or -1 in case of an error. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +#include <trace-seq.h> +... +struct trace_seq seq; +trace_seq_init(&seq); +... +void foo_seq_print(struct trace_seq *tseq, char *format, ...) +{ + va_list ap; + va_start(ap, format); + if (trace_seq_vprintf(tseq, format, ap) <= 0) { + /* Failed to print in the trace sequence */ + } + va_end(ap); +} + +trace_seq_reset(&seq); + +char *str = " MAN page example"; +if (trace_seq_puts(&seq, str) != strlen(str)) { + /* Failed to put str in the trace sequence */ +} +if (trace_seq_putc(&seq, ':') != 1) { + /* Failed to put ':' in the trace sequence */ +} +if (trace_seq_printf(&seq, " trace sequence: %d", 1) <= 0) { + /* Failed to print in the trace sequence */ +} +foo_seq_print( &seq, " %d\n", 2); + +trace_seq_terminate(&seq); +... + +if (trace_seq_do_printf(&seq) < 0 ) { + /* Failed to print the sequence buffer to the standard output */ +} +FILE *fp = fopen("trace.txt", "w"); +if (trace_seq_do_fprintf(&seq, fp) < 0 ) [ + /* Failed to print the sequence buffer to the trace.txt file */ +} + +trace_seq_destroy(&seq); +... +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*trace-seq.h* + Header file to include in order to have access to trace sequences related APIs. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent.txt b/tools/lib/traceevent/Documentation/libtraceevent.txt new file mode 100644 index 000000000000..fbd977b47de1 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent.txt @@ -0,0 +1,203 @@ +libtraceevent(3) +================ + +NAME +---- +libtraceevent - Linux kernel trace event library + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +Management of tep handler data structure and access of its members: + struct tep_handle pass:[*]*tep_alloc*(void); + void *tep_free*(struct tep_handle pass:[*]_tep_); + void *tep_ref*(struct tep_handle pass:[*]_tep_); + void *tep_unref*(struct tep_handle pass:[*]_tep_); + int *tep_ref_get*(struct tep_handle pass:[*]_tep_); + void *tep_set_flag*(struct tep_handle pass:[*]_tep_, enum tep_flag _flag_); + void *tep_clear_flag*(struct tep_handle pass:[*]_tep_, enum tep_flag _flag_); + bool *tep_test_flag*(struct tep_handle pass:[*]_tep_, enum tep_flag _flags_); + int *tep_get_cpus*(struct tep_handle pass:[*]_tep_); + void *tep_set_cpus*(struct tep_handle pass:[*]_tep_, int _cpus_); + int *tep_get_long_size*(strucqt tep_handle pass:[*]_tep_); + void *tep_set_long_size*(struct tep_handle pass:[*]_tep_, int _long_size_); + int *tep_get_page_size*(struct tep_handle pass:[*]_tep_); + void *tep_set_page_size*(struct tep_handle pass:[*]_tep_, int _page_size_); + bool *tep_is_latency_format*(struct tep_handle pass:[*]_tep_); + void *tep_set_latency_format*(struct tep_handle pass:[*]_tep_, int _lat_); + int *tep_get_header_page_size*(struct tep_handle pass:[*]_tep_); + int *tep_get_header_timestamp_size*(struct tep_handle pass:[*]_tep_); + bool *tep_is_old_format*(struct tep_handle pass:[*]_tep_); + int *tep_strerror*(struct tep_handle pass:[*]_tep_, enum tep_errno _errnum_, char pass:[*]_buf_, size_t _buflen_); + +Register / unregister APIs: + int *tep_register_trace_clock*(struct tep_handle pass:[*]_tep_, const char pass:[*]_trace_clock_); + int *tep_register_function*(struct tep_handle pass:[*]_tep_, char pass:[*]_name_, unsigned long long _addr_, char pass:[*]_mod_); + int *tep_register_event_handler*(struct tep_handle pass:[*]_tep_, int _id_, const char pass:[*]_sys_name_, const char pass:[*]_event_name_, tep_event_handler_func _func_, void pass:[*]_context_); + int *tep_unregister_event_handler*(struct tep_handle pass:[*]tep, int id, const char pass:[*]sys_name, const char pass:[*]event_name, tep_event_handler_func func, void pass:[*]_context_); + int *tep_register_print_string*(struct tep_handle pass:[*]_tep_, const char pass:[*]_fmt_, unsigned long long _addr_); + int *tep_register_print_function*(struct tep_handle pass:[*]_tep_, tep_func_handler _func_, enum tep_func_arg_type _ret_type_, char pass:[*]_name_, _..._); + int *tep_unregister_print_function*(struct tep_handle pass:[*]_tep_, tep_func_handler _func_, char pass:[*]_name_); + +Plugins management: + struct tep_plugin_list pass:[*]*tep_load_plugins*(struct tep_handle pass:[*]_tep_); + void *tep_unload_plugins*(struct tep_plugin_list pass:[*]_plugin_list_, struct tep_handle pass:[*]_tep_); + char pass:[*]pass:[*]*tep_plugin_list_options*(void); + void *tep_plugin_free_options_list*(char pass:[*]pass:[*]_list_); + int *tep_plugin_add_options*(const char pass:[*]_name_, struct tep_plugin_option pass:[*]_options_); + void *tep_plugin_remove_options*(struct tep_plugin_option pass:[*]_options_); + void *tep_print_plugins*(struct trace_seq pass:[*]_s_, const char pass:[*]_prefix_, const char pass:[*]_suffix_, const struct tep_plugin_list pass:[*]_list_); + +Event related APIs: + struct tep_event pass:[*]*tep_get_event*(struct tep_handle pass:[*]_tep_, int _index_); + struct tep_event pass:[*]*tep_get_first_event*(struct tep_handle pass:[*]_tep_); + int *tep_get_events_count*(struct tep_handle pass:[*]_tep_); + struct tep_event pass:[*]pass:[*]*tep_list_events*(struct tep_handle pass:[*]_tep_, enum tep_event_sort_type _sort_type_); + struct tep_event pass:[*]pass:[*]*tep_list_events_copy*(struct tep_handle pass:[*]_tep_, enum tep_event_sort_type _sort_type_); + +Event printing: + void *tep_print_event*(struct tep_handle pass:[*]_tep_, struct trace_seq pass:[*]_s_, struct tep_record pass:[*]_record_, bool _use_trace_clock_); + void *tep_print_event_data*(struct tep_handle pass:[*]_tep_, struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, struct tep_record pass:[*]_record_); + void *tep_event_info*(struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, struct tep_record pass:[*]_record_); + void *tep_print_event_task*(struct tep_handle pass:[*]_tep_, struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, struct tep_record pass:[*]_record_); + void *tep_print_event_time*(struct tep_handle pass:[*]_tep_, struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, struct tep_record pass:[*]record, bool _use_trace_clock_); + void *tep_set_print_raw*(struct tep_handle pass:[*]_tep_, int _print_raw_); + +Event finding: + struct tep_event pass:[*]*tep_find_event*(struct tep_handle pass:[*]_tep_, int _id_); + struct tep_event pass:[*]*tep_find_event_by_name*(struct tep_handle pass:[*]_tep_, const char pass:[*]_sys_, const char pass:[*]_name_); + struct tep_event pass:[*]*tep_find_event_by_record*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_record_); + +Parsing of event files: + int *tep_parse_header_page*(struct tep_handle pass:[*]_tep_, char pass:[*]_buf_, unsigned long _size_, int _long_size_); + enum tep_errno *tep_parse_event*(struct tep_handle pass:[*]_tep_, const char pass:[*]_buf_, unsigned long _size_, const char pass:[*]_sys_); + enum tep_errno *tep_parse_format*(struct tep_handle pass:[*]_tep_, struct tep_event pass:[*]pass:[*]_eventp_, const char pass:[*]_buf_, unsigned long _size_, const char pass:[*]_sys_); + +APIs related to fields from event's format files: + struct tep_format_field pass:[*]pass:[*]*tep_event_common_fields*(struct tep_event pass:[*]_event_); + struct tep_format_field pass:[*]pass:[*]*tep_event_fields*(struct tep_event pass:[*]_event_); + void pass:[*]*tep_get_field_raw*(struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, int pass:[*]_len_, int _err_); + int *tep_get_field_val*(struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, unsigned long long pass:[*]_val_, int _err_); + int *tep_get_common_field_val*(struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, unsigned long long pass:[*]_val_, int _err_); + int *tep_get_any_field_val*(struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, unsigned long long pass:[*]_val_, int _err_); + int *tep_read_number_field*(struct tep_format_field pass:[*]_field_, const void pass:[*]_data_, unsigned long long pass:[*]_value_); + +Event fields printing: + void *tep_print_field*(struct trace_seq pass:[*]_s_, void pass:[*]_data_, struct tep_format_field pass:[*]_field_); + void *tep_print_fields*(struct trace_seq pass:[*]_s_, void pass:[*]_data_, int _size_, struct tep_event pass:[*]_event_); + int *tep_print_num_field*(struct trace_seq pass:[*]_s_, const char pass:[*]_fmt_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, int _err_); + int *tep_print_func_field*(struct trace_seq pass:[*]_s_, const char pass:[*]_fmt_, struct tep_event pass:[*]_event_, const char pass:[*]_name_, struct tep_record pass:[*]_record_, int _err_); + +Event fields finding: + struct tep_format_field pass:[*]*tep_find_common_field*(struct tep_event pass:[*]_event_, const char pass:[*]_name_); + struct tep_format_field pass:[*]*tep_find_field*(struct tep_event_ormat pass:[*]_event_, const char pass:[*]_name_); + struct tep_format_field pass:[*]*tep_find_any_field*(struct tep_event pass:[*]_event_, const char pass:[*]_name_); + +Functions resolver: + int *tep_set_function_resolver*(struct tep_handle pass:[*]_tep_, tep_func_resolver_t pass:[*]_func_, void pass:[*]_priv_); + void *tep_reset_function_resolver*(struct tep_handle pass:[*]_tep_); + const char pass:[*]*tep_find_function*(struct tep_handle pass:[*]_tep_, unsigned long long _addr_); + unsigned long long *tep_find_function_address*(struct tep_handle pass:[*]_tep_, unsigned long long _addr_); + +Filter management: + struct tep_event_filter pass:[*]*tep_filter_alloc*(struct tep_handle pass:[*]_tep_); + enum tep_errno *tep_filter_add_filter_str*(struct tep_event_filter pass:[*]_filter_, const char pass:[*]_filter_str_); + enum tep_errno *tep_filter_match*(struct tep_event_filter pass:[*]_filter_, struct tep_record pass:[*]_record_); + int *tep_filter_strerror*(struct tep_event_filter pass:[*]_filter_, enum tep_errno _err_, char pass:[*]buf, size_t _buflen_); + int *tep_event_filtered*(struct tep_event_filter pass:[*]_filter_, int _event_id_); + void *tep_filter_reset*(struct tep_event_filter pass:[*]_filter_); + void *tep_filter_free*(struct tep_event_filter pass:[*]_filter_); + char pass:[*]*tep_filter_make_string*(struct tep_event_filter pass:[*]_filter_, int _event_id_); + int *tep_filter_remove_event*(struct tep_event_filter pass:[*]_filter_, int _event_id_); + int *tep_filter_copy*(struct tep_event_filter pass:[*]_dest_, struct tep_event_filter pass:[*]_source_); + int *tep_filter_compare*(struct tep_event_filter pass:[*]_filter1_, struct tep_event_filter pass:[*]_filter2_); + +Parsing various data from the records: + void *tep_data_latency_format*(struct tep_handle pass:[*]_tep_, struct trace_seq pass:[*]_s_, struct tep_record pass:[*]_record_); + int *tep_data_type*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_rec_); + int *tep_data_pid*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_rec_); + int *tep_data_preempt_count*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_rec_); + int *tep_data_flags*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_rec_); + +Command and task related APIs: + const char pass:[*]*tep_data_comm_from_pid*(struct tep_handle pass:[*]_tep_, int _pid_); + struct cmdline pass:[*]*tep_data_pid_from_comm*(struct tep_handle pass:[*]_tep_, const char pass:[*]_comm_, struct cmdline pass:[*]_next_); + int *tep_register_comm*(struct tep_handle pass:[*]_tep_, const char pass:[*]_comm_, int _pid_); + int *tep_override_comm*(struct tep_handle pass:[*]_tep_, const char pass:[*]_comm_, int _pid_); + bool *tep_is_pid_registered*(struct tep_handle pass:[*]_tep_, int _pid_); + int *tep_cmdline_pid*(struct tep_handle pass:[*]_tep_, struct cmdline pass:[*]_cmdline_); + +Endian related APIs: + int *tep_is_bigendian*(void); + unsigned long long *tep_read_number*(struct tep_handle pass:[*]_tep_, const void pass:[*]_ptr_, int _size_); + bool *tep_is_file_bigendian*(struct tep_handle pass:[*]_tep_); + void *tep_set_file_bigendian*(struct tep_handle pass:[*]_tep_, enum tep_endian _endian_); + bool *tep_is_local_bigendian*(struct tep_handle pass:[*]_tep_); + void *tep_set_local_bigendian*(struct tep_handle pass:[*]_tep_, enum tep_endian _endian_); + +Trace sequences: +*#include <trace-seq.h>* + void *trace_seq_init*(struct trace_seq pass:[*]_s_); + void *trace_seq_reset*(struct trace_seq pass:[*]_s_); + void *trace_seq_destroy*(struct trace_seq pass:[*]_s_); + int *trace_seq_printf*(struct trace_seq pass:[*]_s_, const char pass:[*]_fmt_, ...); + int *trace_seq_vprintf*(struct trace_seq pass:[*]_s_, const char pass:[*]_fmt_, va_list _args_); + int *trace_seq_puts*(struct trace_seq pass:[*]_s_, const char pass:[*]_str_); + int *trace_seq_putc*(struct trace_seq pass:[*]_s_, unsigned char _c_); + void *trace_seq_terminate*(struct trace_seq pass:[*]_s_); + int *trace_seq_do_fprintf*(struct trace_seq pass:[*]_s_, FILE pass:[*]_fp_); + int *trace_seq_do_printf*(struct trace_seq pass:[*]_s_); +-- + +DESCRIPTION +----------- +The libtraceevent(3) library provides APIs to access kernel tracepoint events, +located in the tracefs file system under the events directory. + +ENVIRONMENT +----------- +[verse] +-- +TRACEEVENT_PLUGIN_DIR + Additional plugin directory. All shared object files, located in this directory will be loaded as traceevent plugins. +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*trace-seq.h* + Header file to include in order to have access to trace sequences related APIs. + Trace sequences are used to allow a function to call several other functions + to create a string of data to use. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/manpage-1.72.xsl b/tools/lib/traceevent/Documentation/manpage-1.72.xsl new file mode 100644 index 000000000000..b4d315cb8c47 --- /dev/null +++ b/tools/lib/traceevent/Documentation/manpage-1.72.xsl @@ -0,0 +1,14 @@ +<!-- manpage-1.72.xsl: + special settings for manpages rendered from asciidoc+docbook + handles peculiarities in docbook-xsl 1.72.0 --> +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + version="1.0"> + +<xsl:import href="manpage-base.xsl"/> + +<!-- these are the special values for the roff control characters + needed for docbook-xsl 1.72.0 --> +<xsl:param name="git.docbook.backslash">▓</xsl:param> +<xsl:param name="git.docbook.dot" >⌂</xsl:param> + +</xsl:stylesheet> diff --git a/tools/lib/traceevent/Documentation/manpage-base.xsl b/tools/lib/traceevent/Documentation/manpage-base.xsl new file mode 100644 index 000000000000..a264fa616093 --- /dev/null +++ b/tools/lib/traceevent/Documentation/manpage-base.xsl @@ -0,0 +1,35 @@ +<!-- manpage-base.xsl: + special formatting for manpages rendered from asciidoc+docbook --> +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + version="1.0"> + +<!-- these params silence some output from xmlto --> +<xsl:param name="man.output.quietly" select="1"/> +<xsl:param name="refentry.meta.get.quietly" select="1"/> + +<!-- convert asciidoc callouts to man page format; + git.docbook.backslash and git.docbook.dot params + must be supplied by another XSL file or other means --> +<xsl:template match="co"> + <xsl:value-of select="concat( + $git.docbook.backslash,'fB(', + substring-after(@id,'-'),')', + $git.docbook.backslash,'fR')"/> +</xsl:template> +<xsl:template match="calloutlist"> + <xsl:value-of select="$git.docbook.dot"/> + <xsl:text>sp </xsl:text> + <xsl:apply-templates/> + <xsl:text> </xsl:text> +</xsl:template> +<xsl:template match="callout"> + <xsl:value-of select="concat( + $git.docbook.backslash,'fB', + substring-after(@arearefs,'-'), + '. ',$git.docbook.backslash,'fR')"/> + <xsl:apply-templates/> + <xsl:value-of select="$git.docbook.dot"/> + <xsl:text>br </xsl:text> +</xsl:template> + +</xsl:stylesheet> diff --git a/tools/lib/traceevent/Documentation/manpage-bold-literal.xsl b/tools/lib/traceevent/Documentation/manpage-bold-literal.xsl new file mode 100644 index 000000000000..608eb5df6281 --- /dev/null +++ b/tools/lib/traceevent/Documentation/manpage-bold-literal.xsl @@ -0,0 +1,17 @@ +<!-- manpage-bold-literal.xsl: + special formatting for manpages rendered from asciidoc+docbook --> +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + version="1.0"> + +<!-- render literal text as bold (instead of plain or monospace); + this makes literal text easier to distinguish in manpages + viewed on a tty --> +<xsl:template match="literal"> + <xsl:value-of select="$git.docbook.backslash"/> + <xsl:text>fB</xsl:text> + <xsl:apply-templates/> + <xsl:value-of select="$git.docbook.backslash"/> + <xsl:text>fR</xsl:text> +</xsl:template> + +</xsl:stylesheet> diff --git a/tools/lib/traceevent/Documentation/manpage-normal.xsl b/tools/lib/traceevent/Documentation/manpage-normal.xsl new file mode 100644 index 000000000000..a48f5b11f3dc --- /dev/null +++ b/tools/lib/traceevent/Documentation/manpage-normal.xsl @@ -0,0 +1,13 @@ +<!-- manpage-normal.xsl: + special settings for manpages rendered from asciidoc+docbook + handles anything we want to keep away from docbook-xsl 1.72.0 --> +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + version="1.0"> + +<xsl:import href="manpage-base.xsl"/> + +<!-- these are the normal values for the roff control characters --> +<xsl:param name="git.docbook.backslash">\</xsl:param> +<xsl:param name="git.docbook.dot" >.</xsl:param> + +</xsl:stylesheet> diff --git a/tools/lib/traceevent/Documentation/manpage-suppress-sp.xsl b/tools/lib/traceevent/Documentation/manpage-suppress-sp.xsl new file mode 100644 index 000000000000..a63c7632a87d --- /dev/null +++ b/tools/lib/traceevent/Documentation/manpage-suppress-sp.xsl @@ -0,0 +1,21 @@ +<!-- manpage-suppress-sp.xsl: + special settings for manpages rendered from asciidoc+docbook + handles erroneous, inline .sp in manpage output of some + versions of docbook-xsl --> +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + version="1.0"> + +<!-- attempt to work around spurious .sp at the tail of the line + that some versions of docbook stylesheets seem to add --> +<xsl:template match="simpara"> + <xsl:variable name="content"> + <xsl:apply-templates/> + </xsl:variable> + <xsl:value-of select="normalize-space($content)"/> + <xsl:if test="not(ancestor::authorblurb) and + not(ancestor::personblurb)"> + <xsl:text> </xsl:text> + </xsl:if> +</xsl:template> + +</xsl:stylesheet> diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile index 941761d9923d..3292c290654f 100644 --- a/tools/lib/traceevent/Makefile +++ b/tools/lib/traceevent/Makefile @@ -50,9 +50,13 @@ man_dir = $(prefix)/share/man man_dir_SQ = '$(subst ','\'',$(man_dir))' pkgconfig_dir ?= $(word 1,$(shell $(PKG_CONFIG) \ --variable pc_path pkg-config | tr ":" " ")) +includedir_relative = traceevent +includedir = $(prefix)/include/$(includedir_relative) +includedir_SQ = '$(subst ','\'',$(includedir))' export man_dir man_dir_SQ INSTALL export DESTDIR DESTDIR_SQ +export EVENT_PARSE_VERSION set_plugin_dir := 1 @@ -279,6 +283,8 @@ define do_install_pkgconfig_file cp -f ${PKG_CONFIG_FILE}.template ${PKG_CONFIG_FILE}; \ sed -i "s|INSTALL_PREFIX|${1}|g" ${PKG_CONFIG_FILE}; \ sed -i "s|LIB_VERSION|${EVENT_PARSE_VERSION}|g" ${PKG_CONFIG_FILE}; \ + sed -i "s|LIB_DIR|${libdir}|g" ${PKG_CONFIG_FILE}; \ + sed -i "s|HEADER_DIR|$(includedir)|g" ${PKG_CONFIG_FILE}; \ $(call do_install,$(PKG_CONFIG_FILE),$(pkgconfig_dir),644); \ else \ (echo Failed to locate pkg-config directory) 1>&2; \ @@ -300,10 +306,10 @@ install_pkgconfig: install_headers: $(call QUIET_INSTALL, headers) \ - $(call do_install,event-parse.h,$(prefix)/include/traceevent,644); \ - $(call do_install,event-utils.h,$(prefix)/include/traceevent,644); \ - $(call do_install,trace-seq.h,$(prefix)/include/traceevent,644); \ - $(call do_install,kbuffer.h,$(prefix)/include/traceevent,644) + $(call do_install,event-parse.h,$(DESTDIR)$(includedir_SQ),644); \ + $(call do_install,event-utils.h,$(DESTDIR)$(includedir_SQ),644); \ + $(call do_install,trace-seq.h,$(DESTDIR)$(includedir_SQ),644); \ + $(call do_install,kbuffer.h,$(DESTDIR)$(includedir_SQ),644) install: install_lib @@ -313,6 +319,38 @@ clean: $(RM) TRACEEVENT-CFLAGS tags TAGS; \ $(RM) $(PKG_CONFIG_FILE) +PHONY += doc +doc: + $(call descend,Documentation) + +PHONY += doc-clean +doc-clean: + $(call descend,Documentation,clean) + +PHONY += doc-install +doc-install: + $(call descend,Documentation,install) + +PHONY += doc-uninstall +doc-uninstall: + $(call descend,Documentation,uninstall) + +PHONY += help +help: + @echo 'Possible targets:' + @echo'' + @echo ' all - default, compile the library and the'\ + 'plugins' + @echo ' plugins - compile the plugins' + @echo ' install - install the library, the plugins,'\ + 'the header and pkgconfig files' + @echo ' clean - clean the library and the plugins object files' + @echo ' doc - compile the documentation files - man'\ + 'and html pages, in the Documentation directory' + @echo ' doc-clean - clean the documentation files' + @echo ' doc-install - install the man pages' + @echo ' doc-uninstall - uninstall the man pages' + @echo'' PHONY += force plugins force: diff --git a/tools/lib/traceevent/event-parse-api.c b/tools/lib/traceevent/event-parse-api.c index d463761a58f4..988587840c80 100644 --- a/tools/lib/traceevent/event-parse-api.c +++ b/tools/lib/traceevent/event-parse-api.c @@ -9,6 +9,22 @@ #include "event-utils.h" /** + * tep_get_event - returns the event with the given index + * @tep: a handle to the tep_handle + * @index: index of the requested event, in the range 0 .. nr_events + * + * This returns pointer to the element of the events array with the given index + * If @tep is NULL, or @index is not in the range 0 .. nr_events, NULL is returned. + */ +struct tep_event *tep_get_event(struct tep_handle *tep, int index) +{ + if (tep && tep->events && index < tep->nr_events) + return tep->events[index]; + + return NULL; +} + +/** * tep_get_first_event - returns the first event in the events array * @tep: a handle to the tep_handle * @@ -17,10 +33,7 @@ */ struct tep_event *tep_get_first_event(struct tep_handle *tep) { - if (tep && tep->events) - return tep->events[0]; - - return NULL; + return tep_get_event(tep, 0); } /** @@ -32,7 +45,7 @@ struct tep_event *tep_get_first_event(struct tep_handle *tep) */ int tep_get_events_count(struct tep_handle *tep) { - if(tep) + if (tep) return tep->nr_events; return 0; } @@ -43,19 +56,47 @@ int tep_get_events_count(struct tep_handle *tep) * @flag: flag, or combination of flags to be set * can be any combination from enum tep_flag * - * This sets a flag or mbination of flags from enum tep_flag - */ + * This sets a flag or combination of flags from enum tep_flag + */ void tep_set_flag(struct tep_handle *tep, int flag) { - if(tep) + if (tep) tep->flags |= flag; } -unsigned short tep_data2host2(struct tep_handle *pevent, unsigned short data) +/** + * tep_clear_flag - clear event parser flag + * @tep: a handle to the tep_handle + * @flag: flag to be cleared + * + * This clears a tep flag + */ +void tep_clear_flag(struct tep_handle *tep, enum tep_flag flag) +{ + if (tep) + tep->flags &= ~flag; +} + +/** + * tep_test_flag - check the state of event parser flag + * @tep: a handle to the tep_handle + * @flag: flag to be checked + * + * This returns the state of the requested tep flag. + * Returns: true if the flag is set, false otherwise. + */ +bool tep_test_flag(struct tep_handle *tep, enum tep_flag flag) +{ + if (tep) + return tep->flags & flag; + return false; +} + +unsigned short tep_data2host2(struct tep_handle *tep, unsigned short data) { unsigned short swap; - if (!pevent || pevent->host_bigendian == pevent->file_bigendian) + if (!tep || tep->host_bigendian == tep->file_bigendian) return data; swap = ((data & 0xffULL) << 8) | @@ -64,11 +105,11 @@ unsigned short tep_data2host2(struct tep_handle *pevent, unsigned short data) return swap; } -unsigned int tep_data2host4(struct tep_handle *pevent, unsigned int data) +unsigned int tep_data2host4(struct tep_handle *tep, unsigned int data) { unsigned int swap; - if (!pevent || pevent->host_bigendian == pevent->file_bigendian) + if (!tep || tep->host_bigendian == tep->file_bigendian) return data; swap = ((data & 0xffULL) << 24) | @@ -80,11 +121,11 @@ unsigned int tep_data2host4(struct tep_handle *pevent, unsigned int data) } unsigned long long -tep_data2host8(struct tep_handle *pevent, unsigned long long data) +tep_data2host8(struct tep_handle *tep, unsigned long long data) { unsigned long long swap; - if (!pevent || pevent->host_bigendian == pevent->file_bigendian) + if (!tep || tep->host_bigendian == tep->file_bigendian) return data; swap = ((data & 0xffULL) << 56) | @@ -101,175 +142,232 @@ tep_data2host8(struct tep_handle *pevent, unsigned long long data) /** * tep_get_header_page_size - get size of the header page - * @pevent: a handle to the tep_handle + * @tep: a handle to the tep_handle * * This returns size of the header page - * If @pevent is NULL, 0 is returned. + * If @tep is NULL, 0 is returned. + */ +int tep_get_header_page_size(struct tep_handle *tep) +{ + if (tep) + return tep->header_page_size_size; + return 0; +} + +/** + * tep_get_header_timestamp_size - get size of the timestamp in the header page + * @tep: a handle to the tep_handle + * + * This returns size of the timestamp in the header page + * If @tep is NULL, 0 is returned. */ -int tep_get_header_page_size(struct tep_handle *pevent) +int tep_get_header_timestamp_size(struct tep_handle *tep) { - if(pevent) - return pevent->header_page_size_size; + if (tep) + return tep->header_page_ts_size; return 0; } /** * tep_get_cpus - get the number of CPUs - * @pevent: a handle to the tep_handle + * @tep: a handle to the tep_handle * * This returns the number of CPUs - * If @pevent is NULL, 0 is returned. + * If @tep is NULL, 0 is returned. */ -int tep_get_cpus(struct tep_handle *pevent) +int tep_get_cpus(struct tep_handle *tep) { - if(pevent) - return pevent->cpus; + if (tep) + return tep->cpus; return 0; } /** * tep_set_cpus - set the number of CPUs - * @pevent: a handle to the tep_handle + * @tep: a handle to the tep_handle * * This sets the number of CPUs */ -void tep_set_cpus(struct tep_handle *pevent, int cpus) +void tep_set_cpus(struct tep_handle *tep, int cpus) { - if(pevent) - pevent->cpus = cpus; + if (tep) + tep->cpus = cpus; } /** - * tep_get_long_size - get the size of a long integer on the current machine - * @pevent: a handle to the tep_handle + * tep_get_long_size - get the size of a long integer on the traced machine + * @tep: a handle to the tep_handle * - * This returns the size of a long integer on the current machine - * If @pevent is NULL, 0 is returned. + * This returns the size of a long integer on the traced machine + * If @tep is NULL, 0 is returned. */ -int tep_get_long_size(struct tep_handle *pevent) +int tep_get_long_size(struct tep_handle *tep) { - if(pevent) - return pevent->long_size; + if (tep) + return tep->long_size; return 0; } /** - * tep_set_long_size - set the size of a long integer on the current machine - * @pevent: a handle to the tep_handle + * tep_set_long_size - set the size of a long integer on the traced machine + * @tep: a handle to the tep_handle * @size: size, in bytes, of a long integer * - * This sets the size of a long integer on the current machine + * This sets the size of a long integer on the traced machine */ -void tep_set_long_size(struct tep_handle *pevent, int long_size) +void tep_set_long_size(struct tep_handle *tep, int long_size) { - if(pevent) - pevent->long_size = long_size; + if (tep) + tep->long_size = long_size; } /** - * tep_get_page_size - get the size of a memory page on the current machine - * @pevent: a handle to the tep_handle + * tep_get_page_size - get the size of a memory page on the traced machine + * @tep: a handle to the tep_handle * - * This returns the size of a memory page on the current machine - * If @pevent is NULL, 0 is returned. + * This returns the size of a memory page on the traced machine + * If @tep is NULL, 0 is returned. */ -int tep_get_page_size(struct tep_handle *pevent) +int tep_get_page_size(struct tep_handle *tep) { - if(pevent) - return pevent->page_size; + if (tep) + return tep->page_size; return 0; } /** - * tep_set_page_size - set the size of a memory page on the current machine - * @pevent: a handle to the tep_handle + * tep_set_page_size - set the size of a memory page on the traced machine + * @tep: a handle to the tep_handle * @_page_size: size of a memory page, in bytes * - * This sets the size of a memory page on the current machine + * This sets the size of a memory page on the traced machine */ -void tep_set_page_size(struct tep_handle *pevent, int _page_size) +void tep_set_page_size(struct tep_handle *tep, int _page_size) { - if(pevent) - pevent->page_size = _page_size; + if (tep) + tep->page_size = _page_size; } /** - * tep_file_bigendian - get if the file is in big endian order - * @pevent: a handle to the tep_handle + * tep_is_file_bigendian - return the endian of the file + * @tep: a handle to the tep_handle * - * This returns if the file is in big endian order - * If @pevent is NULL, 0 is returned. + * This returns true if the file is in big endian order + * If @tep is NULL, false is returned. */ -int tep_file_bigendian(struct tep_handle *pevent) +bool tep_is_file_bigendian(struct tep_handle *tep) { - if(pevent) - return pevent->file_bigendian; - return 0; + if (tep) + return (tep->file_bigendian == TEP_BIG_ENDIAN); + return false; } /** * tep_set_file_bigendian - set if the file is in big endian order - * @pevent: a handle to the tep_handle + * @tep: a handle to the tep_handle * @endian: non zero, if the file is in big endian order * * This sets if the file is in big endian order */ -void tep_set_file_bigendian(struct tep_handle *pevent, enum tep_endian endian) +void tep_set_file_bigendian(struct tep_handle *tep, enum tep_endian endian) { - if(pevent) - pevent->file_bigendian = endian; + if (tep) + tep->file_bigendian = endian; } /** - * tep_is_host_bigendian - get if the order of the current host is big endian - * @pevent: a handle to the tep_handle + * tep_is_local_bigendian - return the endian of the saved local machine + * @tep: a handle to the tep_handle * - * This gets if the order of the current host is big endian - * If @pevent is NULL, 0 is returned. + * This returns true if the saved local machine in @tep is big endian. + * If @tep is NULL, false is returned. */ -int tep_is_host_bigendian(struct tep_handle *pevent) +bool tep_is_local_bigendian(struct tep_handle *tep) { - if(pevent) - return pevent->host_bigendian; + if (tep) + return (tep->host_bigendian == TEP_BIG_ENDIAN); return 0; } /** - * tep_set_host_bigendian - set the order of the local host - * @pevent: a handle to the tep_handle + * tep_set_local_bigendian - set the stored local machine endian order + * @tep: a handle to the tep_handle * @endian: non zero, if the local host has big endian order * - * This sets the order of the local host + * This sets the endian order for the local machine. */ -void tep_set_host_bigendian(struct tep_handle *pevent, enum tep_endian endian) +void tep_set_local_bigendian(struct tep_handle *tep, enum tep_endian endian) { - if(pevent) - pevent->host_bigendian = endian; + if (tep) + tep->host_bigendian = endian; } /** * tep_is_latency_format - get if the latency output format is configured - * @pevent: a handle to the tep_handle + * @tep: a handle to the tep_handle * - * This gets if the latency output format is configured - * If @pevent is NULL, 0 is returned. + * This returns true if the latency output format is configured + * If @tep is NULL, false is returned. */ -int tep_is_latency_format(struct tep_handle *pevent) +bool tep_is_latency_format(struct tep_handle *tep) { - if(pevent) - return pevent->latency_format; - return 0; + if (tep) + return (tep->latency_format); + return false; } /** * tep_set_latency_format - set the latency output format - * @pevent: a handle to the tep_handle + * @tep: a handle to the tep_handle * @lat: non zero for latency output format * * This sets the latency output format */ -void tep_set_latency_format(struct tep_handle *pevent, int lat) +void tep_set_latency_format(struct tep_handle *tep, int lat) +{ + if (tep) + tep->latency_format = lat; +} + +/** + * tep_is_old_format - get if an old kernel is used + * @tep: a handle to the tep_handle + * + * This returns true, if an old kernel is used to generate the tracing events or + * false if a new kernel is used. Old kernels did not have header page info. + * If @tep is NULL, false is returned. + */ +bool tep_is_old_format(struct tep_handle *tep) +{ + if (tep) + return tep->old_format; + return false; +} + +/** + * tep_set_print_raw - set a flag to force print in raw format + * @tep: a handle to the tep_handle + * @print_raw: the new value of the print_raw flag + * + * This sets a flag to force print in raw format + */ +void tep_set_print_raw(struct tep_handle *tep, int print_raw) +{ + if (tep) + tep->print_raw = print_raw; +} + +/** + * tep_set_test_filters - set a flag to test a filter string + * @tep: a handle to the tep_handle + * @test_filters: the new value of the test_filters flag + * + * This sets a flag to test a filter string. If this flag is set, when + * tep_filter_add_filter_str() API as called,it will print the filter string + * instead of adding it. + */ +void tep_set_test_filters(struct tep_handle *tep, int test_filters) { - if(pevent) - pevent->latency_format = lat; + if (tep) + tep->test_filters = test_filters; } diff --git a/tools/lib/traceevent/event-parse-local.h b/tools/lib/traceevent/event-parse-local.h index 35833ee32d6c..09aa142f7fdd 100644 --- a/tools/lib/traceevent/event-parse-local.h +++ b/tools/lib/traceevent/event-parse-local.h @@ -92,8 +92,8 @@ struct tep_handle { void tep_free_event(struct tep_event *event); void tep_free_format_field(struct tep_format_field *field); -unsigned short tep_data2host2(struct tep_handle *pevent, unsigned short data); -unsigned int tep_data2host4(struct tep_handle *pevent, unsigned int data); -unsigned long long tep_data2host8(struct tep_handle *pevent, unsigned long long data); +unsigned short tep_data2host2(struct tep_handle *tep, unsigned short data); +unsigned int tep_data2host4(struct tep_handle *tep, unsigned int data); +unsigned long long tep_data2host8(struct tep_handle *tep, unsigned long long data); #endif /* _PARSE_EVENTS_INT_H */ diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 981c6ce2da2c..b36b536a9fcb 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -148,14 +148,14 @@ struct cmdline_list { int pid; }; -static int cmdline_init(struct tep_handle *pevent) +static int cmdline_init(struct tep_handle *tep) { - struct cmdline_list *cmdlist = pevent->cmdlist; + struct cmdline_list *cmdlist = tep->cmdlist; struct cmdline_list *item; struct tep_cmdline *cmdlines; int i; - cmdlines = malloc(sizeof(*cmdlines) * pevent->cmdline_count); + cmdlines = malloc(sizeof(*cmdlines) * tep->cmdline_count); if (!cmdlines) return -1; @@ -169,15 +169,15 @@ static int cmdline_init(struct tep_handle *pevent) free(item); } - qsort(cmdlines, pevent->cmdline_count, sizeof(*cmdlines), cmdline_cmp); + qsort(cmdlines, tep->cmdline_count, sizeof(*cmdlines), cmdline_cmp); - pevent->cmdlines = cmdlines; - pevent->cmdlist = NULL; + tep->cmdlines = cmdlines; + tep->cmdlist = NULL; return 0; } -static const char *find_cmdline(struct tep_handle *pevent, int pid) +static const char *find_cmdline(struct tep_handle *tep, int pid) { const struct tep_cmdline *comm; struct tep_cmdline key; @@ -185,13 +185,13 @@ static const char *find_cmdline(struct tep_handle *pevent, int pid) if (!pid) return "<idle>"; - if (!pevent->cmdlines && cmdline_init(pevent)) + if (!tep->cmdlines && cmdline_init(tep)) return "<not enough memory for cmdlines!>"; key.pid = pid; - comm = bsearch(&key, pevent->cmdlines, pevent->cmdline_count, - sizeof(*pevent->cmdlines), cmdline_cmp); + comm = bsearch(&key, tep->cmdlines, tep->cmdline_count, + sizeof(*tep->cmdlines), cmdline_cmp); if (comm) return comm->comm; @@ -199,32 +199,32 @@ static const char *find_cmdline(struct tep_handle *pevent, int pid) } /** - * tep_pid_is_registered - return if a pid has a cmdline registered - * @pevent: handle for the pevent + * tep_is_pid_registered - return if a pid has a cmdline registered + * @tep: a handle to the trace event parser context * @pid: The pid to check if it has a cmdline registered with. * - * Returns 1 if the pid has a cmdline mapped to it - * 0 otherwise. + * Returns true if the pid has a cmdline mapped to it + * false otherwise. */ -int tep_pid_is_registered(struct tep_handle *pevent, int pid) +bool tep_is_pid_registered(struct tep_handle *tep, int pid) { const struct tep_cmdline *comm; struct tep_cmdline key; if (!pid) - return 1; + return true; - if (!pevent->cmdlines && cmdline_init(pevent)) - return 0; + if (!tep->cmdlines && cmdline_init(tep)) + return false; key.pid = pid; - comm = bsearch(&key, pevent->cmdlines, pevent->cmdline_count, - sizeof(*pevent->cmdlines), cmdline_cmp); + comm = bsearch(&key, tep->cmdlines, tep->cmdline_count, + sizeof(*tep->cmdlines), cmdline_cmp); if (comm) - return 1; - return 0; + return true; + return false; } /* @@ -232,10 +232,10 @@ int tep_pid_is_registered(struct tep_handle *pevent, int pid) * we must add this pid. This is much slower than when cmdlines * are added before the array is initialized. */ -static int add_new_comm(struct tep_handle *pevent, +static int add_new_comm(struct tep_handle *tep, const char *comm, int pid, bool override) { - struct tep_cmdline *cmdlines = pevent->cmdlines; + struct tep_cmdline *cmdlines = tep->cmdlines; struct tep_cmdline *cmdline; struct tep_cmdline key; char *new_comm; @@ -246,8 +246,8 @@ static int add_new_comm(struct tep_handle *pevent, /* avoid duplicates */ key.pid = pid; - cmdline = bsearch(&key, pevent->cmdlines, pevent->cmdline_count, - sizeof(*pevent->cmdlines), cmdline_cmp); + cmdline = bsearch(&key, tep->cmdlines, tep->cmdline_count, + sizeof(*tep->cmdlines), cmdline_cmp); if (cmdline) { if (!override) { errno = EEXIST; @@ -264,37 +264,37 @@ static int add_new_comm(struct tep_handle *pevent, return 0; } - cmdlines = realloc(cmdlines, sizeof(*cmdlines) * (pevent->cmdline_count + 1)); + cmdlines = realloc(cmdlines, sizeof(*cmdlines) * (tep->cmdline_count + 1)); if (!cmdlines) { errno = ENOMEM; return -1; } - cmdlines[pevent->cmdline_count].comm = strdup(comm); - if (!cmdlines[pevent->cmdline_count].comm) { + cmdlines[tep->cmdline_count].comm = strdup(comm); + if (!cmdlines[tep->cmdline_count].comm) { free(cmdlines); errno = ENOMEM; return -1; } - cmdlines[pevent->cmdline_count].pid = pid; + cmdlines[tep->cmdline_count].pid = pid; - if (cmdlines[pevent->cmdline_count].comm) - pevent->cmdline_count++; + if (cmdlines[tep->cmdline_count].comm) + tep->cmdline_count++; - qsort(cmdlines, pevent->cmdline_count, sizeof(*cmdlines), cmdline_cmp); - pevent->cmdlines = cmdlines; + qsort(cmdlines, tep->cmdline_count, sizeof(*cmdlines), cmdline_cmp); + tep->cmdlines = cmdlines; return 0; } -static int _tep_register_comm(struct tep_handle *pevent, +static int _tep_register_comm(struct tep_handle *tep, const char *comm, int pid, bool override) { struct cmdline_list *item; - if (pevent->cmdlines) - return add_new_comm(pevent, comm, pid, override); + if (tep->cmdlines) + return add_new_comm(tep, comm, pid, override); item = malloc(sizeof(*item)); if (!item) @@ -309,17 +309,17 @@ static int _tep_register_comm(struct tep_handle *pevent, return -1; } item->pid = pid; - item->next = pevent->cmdlist; + item->next = tep->cmdlist; - pevent->cmdlist = item; - pevent->cmdline_count++; + tep->cmdlist = item; + tep->cmdline_count++; return 0; } /** * tep_register_comm - register a pid / comm mapping - * @pevent: handle for the pevent + * @tep: a handle to the trace event parser context * @comm: the command line to register * @pid: the pid to map the command line to * @@ -327,14 +327,14 @@ static int _tep_register_comm(struct tep_handle *pevent, * a given pid. The comm is duplicated. If a command with the same pid * already exist, -1 is returned and errno is set to EEXIST */ -int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid) +int tep_register_comm(struct tep_handle *tep, const char *comm, int pid) { - return _tep_register_comm(pevent, comm, pid, false); + return _tep_register_comm(tep, comm, pid, false); } /** * tep_override_comm - register a pid / comm mapping - * @pevent: handle for the pevent + * @tep: a handle to the trace event parser context * @comm: the command line to register * @pid: the pid to map the command line to * @@ -342,19 +342,19 @@ int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid) * a given pid. The comm is duplicated. If a command with the same pid * already exist, the command string is udapted with the new one */ -int tep_override_comm(struct tep_handle *pevent, const char *comm, int pid) +int tep_override_comm(struct tep_handle *tep, const char *comm, int pid) { - if (!pevent->cmdlines && cmdline_init(pevent)) { + if (!tep->cmdlines && cmdline_init(tep)) { errno = ENOMEM; return -1; } - return _tep_register_comm(pevent, comm, pid, true); + return _tep_register_comm(tep, comm, pid, true); } -int tep_register_trace_clock(struct tep_handle *pevent, const char *trace_clock) +int tep_register_trace_clock(struct tep_handle *tep, const char *trace_clock) { - pevent->trace_clock = strdup(trace_clock); - if (!pevent->trace_clock) { + tep->trace_clock = strdup(trace_clock); + if (!tep->trace_clock) { errno = ENOMEM; return -1; } @@ -408,18 +408,18 @@ static int func_bcmp(const void *a, const void *b) return 1; } -static int func_map_init(struct tep_handle *pevent) +static int func_map_init(struct tep_handle *tep) { struct func_list *funclist; struct func_list *item; struct func_map *func_map; int i; - func_map = malloc(sizeof(*func_map) * (pevent->func_count + 1)); + func_map = malloc(sizeof(*func_map) * (tep->func_count + 1)); if (!func_map) return -1; - funclist = pevent->funclist; + funclist = tep->funclist; i = 0; while (funclist) { @@ -432,34 +432,34 @@ static int func_map_init(struct tep_handle *pevent) free(item); } - qsort(func_map, pevent->func_count, sizeof(*func_map), func_cmp); + qsort(func_map, tep->func_count, sizeof(*func_map), func_cmp); /* * Add a special record at the end. */ - func_map[pevent->func_count].func = NULL; - func_map[pevent->func_count].addr = 0; - func_map[pevent->func_count].mod = NULL; + func_map[tep->func_count].func = NULL; + func_map[tep->func_count].addr = 0; + func_map[tep->func_count].mod = NULL; - pevent->func_map = func_map; - pevent->funclist = NULL; + tep->func_map = func_map; + tep->funclist = NULL; return 0; } static struct func_map * -__find_func(struct tep_handle *pevent, unsigned long long addr) +__find_func(struct tep_handle *tep, unsigned long long addr) { struct func_map *func; struct func_map key; - if (!pevent->func_map) - func_map_init(pevent); + if (!tep->func_map) + func_map_init(tep); key.addr = addr; - func = bsearch(&key, pevent->func_map, pevent->func_count, - sizeof(*pevent->func_map), func_bcmp); + func = bsearch(&key, tep->func_map, tep->func_count, + sizeof(*tep->func_map), func_bcmp); return func; } @@ -472,15 +472,14 @@ struct func_resolver { /** * tep_set_function_resolver - set an alternative function resolver - * @pevent: handle for the pevent + * @tep: a handle to the trace event parser context * @resolver: function to be used * @priv: resolver function private state. * * Some tools may have already a way to resolve kernel functions, allow them to - * keep using it instead of duplicating all the entries inside - * pevent->funclist. + * keep using it instead of duplicating all the entries inside tep->funclist. */ -int tep_set_function_resolver(struct tep_handle *pevent, +int tep_set_function_resolver(struct tep_handle *tep, tep_func_resolver_t *func, void *priv) { struct func_resolver *resolver = malloc(sizeof(*resolver)); @@ -491,38 +490,38 @@ int tep_set_function_resolver(struct tep_handle *pevent, resolver->func = func; resolver->priv = priv; - free(pevent->func_resolver); - pevent->func_resolver = resolver; + free(tep->func_resolver); + tep->func_resolver = resolver; return 0; } /** * tep_reset_function_resolver - reset alternative function resolver - * @pevent: handle for the pevent + * @tep: a handle to the trace event parser context * * Stop using whatever alternative resolver was set, use the default * one instead. */ -void tep_reset_function_resolver(struct tep_handle *pevent) +void tep_reset_function_resolver(struct tep_handle *tep) { - free(pevent->func_resolver); - pevent->func_resolver = NULL; + free(tep->func_resolver); + tep->func_resolver = NULL; } static struct func_map * -find_func(struct tep_handle *pevent, unsigned long long addr) +find_func(struct tep_handle *tep, unsigned long long addr) { struct func_map *map; - if (!pevent->func_resolver) - return __find_func(pevent, addr); + if (!tep->func_resolver) + return __find_func(tep, addr); - map = &pevent->func_resolver->map; + map = &tep->func_resolver->map; map->mod = NULL; map->addr = addr; - map->func = pevent->func_resolver->func(pevent->func_resolver->priv, - &map->addr, &map->mod); + map->func = tep->func_resolver->func(tep->func_resolver->priv, + &map->addr, &map->mod); if (map->func == NULL) return NULL; @@ -531,18 +530,18 @@ find_func(struct tep_handle *pevent, unsigned long long addr) /** * tep_find_function - find a function by a given address - * @pevent: handle for the pevent + * @tep: a handle to the trace event parser context * @addr: the address to find the function with * * Returns a pointer to the function stored that has the given * address. Note, the address does not have to be exact, it * will select the function that would contain the address. */ -const char *tep_find_function(struct tep_handle *pevent, unsigned long long addr) +const char *tep_find_function(struct tep_handle *tep, unsigned long long addr) { struct func_map *map; - map = find_func(pevent, addr); + map = find_func(tep, addr); if (!map) return NULL; @@ -551,7 +550,7 @@ const char *tep_find_function(struct tep_handle *pevent, unsigned long long addr /** * tep_find_function_address - find a function address by a given address - * @pevent: handle for the pevent + * @tep: a handle to the trace event parser context * @addr: the address to find the function with * * Returns the address the function starts at. This can be used in @@ -559,11 +558,11 @@ const char *tep_find_function(struct tep_handle *pevent, unsigned long long addr * name and the function offset. */ unsigned long long -tep_find_function_address(struct tep_handle *pevent, unsigned long long addr) +tep_find_function_address(struct tep_handle *tep, unsigned long long addr) { struct func_map *map; - map = find_func(pevent, addr); + map = find_func(tep, addr); if (!map) return 0; @@ -572,7 +571,7 @@ tep_find_function_address(struct tep_handle *pevent, unsigned long long addr) /** * tep_register_function - register a function with a given address - * @pevent: handle for the pevent + * @tep: a handle to the trace event parser context * @function: the function name to register * @addr: the address the function starts at * @mod: the kernel module the function may be in (NULL for none) @@ -580,7 +579,7 @@ tep_find_function_address(struct tep_handle *pevent, unsigned long long addr) * This registers a function name with an address and module. * The @func passed in is duplicated. */ -int tep_register_function(struct tep_handle *pevent, char *func, +int tep_register_function(struct tep_handle *tep, char *func, unsigned long long addr, char *mod) { struct func_list *item = malloc(sizeof(*item)); @@ -588,7 +587,7 @@ int tep_register_function(struct tep_handle *pevent, char *func, if (!item) return -1; - item->next = pevent->funclist; + item->next = tep->funclist; item->func = strdup(func); if (!item->func) goto out_free; @@ -601,8 +600,8 @@ int tep_register_function(struct tep_handle *pevent, char *func, item->mod = NULL; item->addr = addr; - pevent->funclist = item; - pevent->func_count++; + tep->funclist = item; + tep->func_count++; return 0; @@ -617,23 +616,23 @@ out_free: /** * tep_print_funcs - print out the stored functions - * @pevent: handle for the pevent + * @tep: a handle to the trace event parser context * * This prints out the stored functions. */ -void tep_print_funcs(struct tep_handle *pevent) +void tep_print_funcs(struct tep_handle *tep) { int i; - if (!pevent->func_map) - func_map_init(pevent); + if (!tep->func_map) + func_map_init(tep); - for (i = 0; i < (int)pevent->func_count; i++) { + for (i = 0; i < (int)tep->func_count; i++) { printf("%016llx %s", - pevent->func_map[i].addr, - pevent->func_map[i].func); - if (pevent->func_map[i].mod) - printf(" [%s]\n", pevent->func_map[i].mod); + tep->func_map[i].addr, + tep->func_map[i].func); + if (tep->func_map[i].mod) + printf(" [%s]\n", tep->func_map[i].mod); else printf("\n"); } @@ -663,18 +662,18 @@ static int printk_cmp(const void *a, const void *b) return 0; } -static int printk_map_init(struct tep_handle *pevent) +static int printk_map_init(struct tep_handle *tep) { struct printk_list *printklist; struct printk_list *item; struct printk_map *printk_map; int i; - printk_map = malloc(sizeof(*printk_map) * (pevent->printk_count + 1)); + printk_map = malloc(sizeof(*printk_map) * (tep->printk_count + 1)); if (!printk_map) return -1; - printklist = pevent->printklist; + printklist = tep->printklist; i = 0; while (printklist) { @@ -686,41 +685,41 @@ static int printk_map_init(struct tep_handle *pevent) free(item); } - qsort(printk_map, pevent->printk_count, sizeof(*printk_map), printk_cmp); + qsort(printk_map, tep->printk_count, sizeof(*printk_map), printk_cmp); - pevent->printk_map = printk_map; - pevent->printklist = NULL; + tep->printk_map = printk_map; + tep->printklist = NULL; return 0; } static struct printk_map * -find_printk(struct tep_handle *pevent, unsigned long long addr) +find_printk(struct tep_handle *tep, unsigned long long addr) { struct printk_map *printk; struct printk_map key; - if (!pevent->printk_map && printk_map_init(pevent)) + if (!tep->printk_map && printk_map_init(tep)) return NULL; key.addr = addr; - printk = bsearch(&key, pevent->printk_map, pevent->printk_count, - sizeof(*pevent->printk_map), printk_cmp); + printk = bsearch(&key, tep->printk_map, tep->printk_count, + sizeof(*tep->printk_map), printk_cmp); return printk; } /** * tep_register_print_string - register a string by its address - * @pevent: handle for the pevent + * @tep: a handle to the trace event parser context * @fmt: the string format to register * @addr: the address the string was located at * * This registers a string by the address it was stored in the kernel. * The @fmt passed in is duplicated. */ -int tep_register_print_string(struct tep_handle *pevent, const char *fmt, +int tep_register_print_string(struct tep_handle *tep, const char *fmt, unsigned long long addr) { struct printk_list *item = malloc(sizeof(*item)); @@ -729,7 +728,7 @@ int tep_register_print_string(struct tep_handle *pevent, const char *fmt, if (!item) return -1; - item->next = pevent->printklist; + item->next = tep->printklist; item->addr = addr; /* Strip off quotes and '\n' from the end */ @@ -747,8 +746,8 @@ int tep_register_print_string(struct tep_handle *pevent, const char *fmt, if (strcmp(p, "\\n") == 0) *p = 0; - pevent->printklist = item; - pevent->printk_count++; + tep->printklist = item; + tep->printk_count++; return 0; @@ -760,21 +759,21 @@ out_free: /** * tep_print_printk - print out the stored strings - * @pevent: handle for the pevent + * @tep: a handle to the trace event parser context * * This prints the string formats that were stored. */ -void tep_print_printk(struct tep_handle *pevent) +void tep_print_printk(struct tep_handle *tep) { int i; - if (!pevent->printk_map) - printk_map_init(pevent); + if (!tep->printk_map) + printk_map_init(tep); - for (i = 0; i < (int)pevent->printk_count; i++) { + for (i = 0; i < (int)tep->printk_count; i++) { printf("%016llx %s\n", - pevent->printk_map[i].addr, - pevent->printk_map[i].printk); + tep->printk_map[i].addr, + tep->printk_map[i].printk); } } @@ -783,29 +782,29 @@ static struct tep_event *alloc_event(void) return calloc(1, sizeof(struct tep_event)); } -static int add_event(struct tep_handle *pevent, struct tep_event *event) +static int add_event(struct tep_handle *tep, struct tep_event *event) { int i; - struct tep_event **events = realloc(pevent->events, sizeof(event) * - (pevent->nr_events + 1)); + struct tep_event **events = realloc(tep->events, sizeof(event) * + (tep->nr_events + 1)); if (!events) return -1; - pevent->events = events; + tep->events = events; - for (i = 0; i < pevent->nr_events; i++) { - if (pevent->events[i]->id > event->id) + for (i = 0; i < tep->nr_events; i++) { + if (tep->events[i]->id > event->id) break; } - if (i < pevent->nr_events) - memmove(&pevent->events[i + 1], - &pevent->events[i], - sizeof(event) * (pevent->nr_events - i)); + if (i < tep->nr_events) + memmove(&tep->events[i + 1], + &tep->events[i], + sizeof(event) * (tep->nr_events - i)); - pevent->events[i] = event; - pevent->nr_events++; + tep->events[i] = event; + tep->nr_events++; - event->pevent = pevent; + event->tep = tep; return 0; } @@ -1184,7 +1183,7 @@ static enum tep_event_type read_token(char **tok) } /** - * tep_read_token - access to utilities to use the pevent parser + * tep_read_token - access to utilities to use the tep parser * @tok: The token to return * * This will parse tokens from the string given by @@ -1657,8 +1656,8 @@ static int event_read_fields(struct tep_event *event, struct tep_format_field ** else if (field->flags & TEP_FIELD_IS_STRING) field->elementsize = 1; else if (field->flags & TEP_FIELD_IS_LONG) - field->elementsize = event->pevent ? - event->pevent->long_size : + field->elementsize = event->tep ? + event->tep->long_size : sizeof(long); } else field->elementsize = field->size; @@ -2942,14 +2941,14 @@ process_bitmask(struct tep_event *event __maybe_unused, struct tep_print_arg *ar } static struct tep_function_handler * -find_func_handler(struct tep_handle *pevent, char *func_name) +find_func_handler(struct tep_handle *tep, char *func_name) { struct tep_function_handler *func; - if (!pevent) + if (!tep) return NULL; - for (func = pevent->func_handlers; func; func = func->next) { + for (func = tep->func_handlers; func; func = func->next) { if (strcmp(func->name, func_name) == 0) break; } @@ -2957,12 +2956,12 @@ find_func_handler(struct tep_handle *pevent, char *func_name) return func; } -static void remove_func_handler(struct tep_handle *pevent, char *func_name) +static void remove_func_handler(struct tep_handle *tep, char *func_name) { struct tep_function_handler *func; struct tep_function_handler **next; - next = &pevent->func_handlers; + next = &tep->func_handlers; while ((func = *next)) { if (strcmp(func->name, func_name) == 0) { *next = func->next; @@ -3076,7 +3075,7 @@ process_function(struct tep_event *event, struct tep_print_arg *arg, return process_dynamic_array_len(event, arg, tok); } - func = find_func_handler(event->pevent, token); + func = find_func_handler(event->tep, token); if (func) { free_token(token); return process_func_handler(event, func, arg, tok); @@ -3357,14 +3356,14 @@ tep_find_any_field(struct tep_event *event, const char *name) /** * tep_read_number - read a number from data - * @pevent: handle for the pevent + * @tep: a handle to the trace event parser context * @ptr: the raw data * @size: the size of the data that holds the number * * Returns the number (converted to host) from the * raw data. */ -unsigned long long tep_read_number(struct tep_handle *pevent, +unsigned long long tep_read_number(struct tep_handle *tep, const void *ptr, int size) { unsigned long long val; @@ -3373,12 +3372,12 @@ unsigned long long tep_read_number(struct tep_handle *pevent, case 1: return *(unsigned char *)ptr; case 2: - return tep_data2host2(pevent, *(unsigned short *)ptr); + return tep_data2host2(tep, *(unsigned short *)ptr); case 4: - return tep_data2host4(pevent, *(unsigned int *)ptr); + return tep_data2host4(tep, *(unsigned int *)ptr); case 8: memcpy(&val, (ptr), sizeof(unsigned long long)); - return tep_data2host8(pevent, val); + return tep_data2host8(tep, val); default: /* BUG! */ return 0; @@ -3406,7 +3405,7 @@ int tep_read_number_field(struct tep_format_field *field, const void *data, case 2: case 4: case 8: - *value = tep_read_number(field->event->pevent, + *value = tep_read_number(field->event->tep, data + field->offset, field->size); return 0; default: @@ -3414,7 +3413,7 @@ int tep_read_number_field(struct tep_format_field *field, const void *data, } } -static int get_common_info(struct tep_handle *pevent, +static int get_common_info(struct tep_handle *tep, const char *type, int *offset, int *size) { struct tep_event *event; @@ -3424,12 +3423,12 @@ static int get_common_info(struct tep_handle *pevent, * All events should have the same common elements. * Pick any event to find where the type is; */ - if (!pevent->events) { + if (!tep->events) { do_warning("no event_list!"); return -1; } - event = pevent->events[0]; + event = tep->events[0]; field = tep_find_common_field(event, type); if (!field) return -1; @@ -3440,58 +3439,58 @@ static int get_common_info(struct tep_handle *pevent, return 0; } -static int __parse_common(struct tep_handle *pevent, void *data, +static int __parse_common(struct tep_handle *tep, void *data, int *size, int *offset, const char *name) { int ret; if (!*size) { - ret = get_common_info(pevent, name, offset, size); + ret = get_common_info(tep, name, offset, size); if (ret < 0) return ret; } - return tep_read_number(pevent, data + *offset, *size); + return tep_read_number(tep, data + *offset, *size); } -static int trace_parse_common_type(struct tep_handle *pevent, void *data) +static int trace_parse_common_type(struct tep_handle *tep, void *data) { - return __parse_common(pevent, data, - &pevent->type_size, &pevent->type_offset, + return __parse_common(tep, data, + &tep->type_size, &tep->type_offset, "common_type"); } -static int parse_common_pid(struct tep_handle *pevent, void *data) +static int parse_common_pid(struct tep_handle *tep, void *data) { - return __parse_common(pevent, data, - &pevent->pid_size, &pevent->pid_offset, + return __parse_common(tep, data, + &tep->pid_size, &tep->pid_offset, "common_pid"); } -static int parse_common_pc(struct tep_handle *pevent, void *data) +static int parse_common_pc(struct tep_handle *tep, void *data) { - return __parse_common(pevent, data, - &pevent->pc_size, &pevent->pc_offset, + return __parse_common(tep, data, + &tep->pc_size, &tep->pc_offset, "common_preempt_count"); } -static int parse_common_flags(struct tep_handle *pevent, void *data) +static int parse_common_flags(struct tep_handle *tep, void *data) { - return __parse_common(pevent, data, - &pevent->flags_size, &pevent->flags_offset, + return __parse_common(tep, data, + &tep->flags_size, &tep->flags_offset, "common_flags"); } -static int parse_common_lock_depth(struct tep_handle *pevent, void *data) +static int parse_common_lock_depth(struct tep_handle *tep, void *data) { - return __parse_common(pevent, data, - &pevent->ld_size, &pevent->ld_offset, + return __parse_common(tep, data, + &tep->ld_size, &tep->ld_offset, "common_lock_depth"); } -static int parse_common_migrate_disable(struct tep_handle *pevent, void *data) +static int parse_common_migrate_disable(struct tep_handle *tep, void *data) { - return __parse_common(pevent, data, - &pevent->ld_size, &pevent->ld_offset, + return __parse_common(tep, data, + &tep->ld_size, &tep->ld_offset, "common_migrate_disable"); } @@ -3499,28 +3498,28 @@ static int events_id_cmp(const void *a, const void *b); /** * tep_find_event - find an event by given id - * @pevent: a handle to the pevent + * @tep: a handle to the trace event parser context * @id: the id of the event * * Returns an event that has a given @id. */ -struct tep_event *tep_find_event(struct tep_handle *pevent, int id) +struct tep_event *tep_find_event(struct tep_handle *tep, int id) { struct tep_event **eventptr; struct tep_event key; struct tep_event *pkey = &key; /* Check cache first */ - if (pevent->last_event && pevent->last_event->id == id) - return pevent->last_event; + if (tep->last_event && tep->last_event->id == id) + return tep->last_event; key.id = id; - eventptr = bsearch(&pkey, pevent->events, pevent->nr_events, - sizeof(*pevent->events), events_id_cmp); + eventptr = bsearch(&pkey, tep->events, tep->nr_events, + sizeof(*tep->events), events_id_cmp); if (eventptr) { - pevent->last_event = *eventptr; + tep->last_event = *eventptr; return *eventptr; } @@ -3529,7 +3528,7 @@ struct tep_event *tep_find_event(struct tep_handle *pevent, int id) /** * tep_find_event_by_name - find an event by given name - * @pevent: a handle to the pevent + * @tep: a handle to the trace event parser context * @sys: the system name to search for * @name: the name of the event to search for * @@ -3537,19 +3536,19 @@ struct tep_event *tep_find_event(struct tep_handle *pevent, int id) * @sys. If @sys is NULL the first event with @name is returned. */ struct tep_event * -tep_find_event_by_name(struct tep_handle *pevent, +tep_find_event_by_name(struct tep_handle *tep, const char *sys, const char *name) { struct tep_event *event = NULL; int i; - if (pevent->last_event && - strcmp(pevent->last_event->name, name) == 0 && - (!sys || strcmp(pevent->last_event->system, sys) == 0)) - return pevent->last_event; + if (tep->last_event && + strcmp(tep->last_event->name, name) == 0 && + (!sys || strcmp(tep->last_event->system, sys) == 0)) + return tep->last_event; - for (i = 0; i < pevent->nr_events; i++) { - event = pevent->events[i]; + for (i = 0; i < tep->nr_events; i++) { + event = tep->events[i]; if (strcmp(event->name, name) == 0) { if (!sys) break; @@ -3557,17 +3556,17 @@ tep_find_event_by_name(struct tep_handle *pevent, break; } } - if (i == pevent->nr_events) + if (i == tep->nr_events) event = NULL; - pevent->last_event = event; + tep->last_event = event; return event; } static unsigned long long eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg *arg) { - struct tep_handle *pevent = event->pevent; + struct tep_handle *tep = event->tep; unsigned long long val = 0; unsigned long long left, right; struct tep_print_arg *typearg = NULL; @@ -3589,7 +3588,7 @@ eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg } /* must be a number */ - val = tep_read_number(pevent, data + arg->field.field->offset, + val = tep_read_number(tep, data + arg->field.field->offset, arg->field.field->size); break; case TEP_PRINT_FLAGS: @@ -3629,11 +3628,11 @@ eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg } /* Default to long size */ - field_size = pevent->long_size; + field_size = tep->long_size; switch (larg->type) { case TEP_PRINT_DYNAMIC_ARRAY: - offset = tep_read_number(pevent, + offset = tep_read_number(tep, data + larg->dynarray.field->offset, larg->dynarray.field->size); if (larg->dynarray.field->elementsize) @@ -3662,7 +3661,7 @@ eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg default: goto default_op; /* oops, all bets off */ } - val = tep_read_number(pevent, + val = tep_read_number(tep, data + offset, field_size); if (typearg) val = eval_type(val, typearg, 1); @@ -3763,7 +3762,7 @@ eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg } break; case TEP_PRINT_DYNAMIC_ARRAY_LEN: - offset = tep_read_number(pevent, + offset = tep_read_number(tep, data + arg->dynarray.field->offset, arg->dynarray.field->size); /* @@ -3775,7 +3774,7 @@ eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg break; case TEP_PRINT_DYNAMIC_ARRAY: /* Without [], we pass the address to the dynamic data */ - offset = tep_read_number(pevent, + offset = tep_read_number(tep, data + arg->dynarray.field->offset, arg->dynarray.field->size); /* @@ -3850,7 +3849,7 @@ static void print_str_to_seq(struct trace_seq *s, const char *format, trace_seq_printf(s, format, str); } -static void print_bitmask_to_seq(struct tep_handle *pevent, +static void print_bitmask_to_seq(struct tep_handle *tep, struct trace_seq *s, const char *format, int len_arg, const void *data, int size) { @@ -3882,7 +3881,7 @@ static void print_bitmask_to_seq(struct tep_handle *pevent, * In the kernel, this is an array of long words, thus * endianness is very important. */ - if (pevent->file_bigendian) + if (tep->file_bigendian) index = size - (len + 1); else index = len; @@ -3908,7 +3907,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, struct tep_event *event, const char *format, int len_arg, struct tep_print_arg *arg) { - struct tep_handle *pevent = event->pevent; + struct tep_handle *tep = event->tep; struct tep_print_flag_sym *flag; struct tep_format_field *field; struct printk_map *printk; @@ -3945,7 +3944,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, * is a pointer. */ if (!(field->flags & TEP_FIELD_IS_ARRAY) && - field->size == pevent->long_size) { + field->size == tep->long_size) { /* Handle heterogeneous recording and processing * architectures @@ -3960,12 +3959,12 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, * on 32-bit devices: * In this case, 64 bits must be read. */ - addr = (pevent->long_size == 8) ? + addr = (tep->long_size == 8) ? *(unsigned long long *)(data + field->offset) : (unsigned long long)*(unsigned int *)(data + field->offset); /* Check if it matches a print format */ - printk = find_printk(pevent, addr); + printk = find_printk(tep, addr); if (printk) trace_seq_puts(s, printk->printk); else @@ -4022,7 +4021,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, case TEP_PRINT_HEX_STR: if (arg->hex.field->type == TEP_PRINT_DYNAMIC_ARRAY) { unsigned long offset; - offset = tep_read_number(pevent, + offset = tep_read_number(tep, data + arg->hex.field->dynarray.field->offset, arg->hex.field->dynarray.field->size); hex = data + (offset & 0xffff); @@ -4053,7 +4052,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, unsigned long offset; struct tep_format_field *field = arg->int_array.field->dynarray.field; - offset = tep_read_number(pevent, + offset = tep_read_number(tep, data + field->offset, field->size); num = data + (offset & 0xffff); @@ -4104,7 +4103,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, f = tep_find_any_field(event, arg->string.string); arg->string.offset = f->offset; } - str_offset = tep_data2host4(pevent, *(unsigned int *)(data + arg->string.offset)); + str_offset = tep_data2host4(tep, *(unsigned int *)(data + arg->string.offset)); str_offset &= 0xffff; print_str_to_seq(s, format, len_arg, ((char *)data) + str_offset); break; @@ -4122,10 +4121,10 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, f = tep_find_any_field(event, arg->bitmask.bitmask); arg->bitmask.offset = f->offset; } - bitmask_offset = tep_data2host4(pevent, *(unsigned int *)(data + arg->bitmask.offset)); + bitmask_offset = tep_data2host4(tep, *(unsigned int *)(data + arg->bitmask.offset)); bitmask_size = bitmask_offset >> 16; bitmask_offset &= 0xffff; - print_bitmask_to_seq(pevent, s, format, len_arg, + print_bitmask_to_seq(tep, s, format, len_arg, data + bitmask_offset, bitmask_size); break; } @@ -4257,7 +4256,7 @@ static void free_args(struct tep_print_arg *args) static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, struct tep_event *event) { - struct tep_handle *pevent = event->pevent; + struct tep_handle *tep = event->tep; struct tep_format_field *field, *ip_field; struct tep_print_arg *args, *arg, **next; unsigned long long ip, val; @@ -4265,8 +4264,8 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s void *bptr; int vsize = 0; - field = pevent->bprint_buf_field; - ip_field = pevent->bprint_ip_field; + field = tep->bprint_buf_field; + ip_field = tep->bprint_ip_field; if (!field) { field = tep_find_field(event, "buf"); @@ -4279,11 +4278,11 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s do_warning_event(event, "can't find ip field for binary printk"); return NULL; } - pevent->bprint_buf_field = field; - pevent->bprint_ip_field = ip_field; + tep->bprint_buf_field = field; + tep->bprint_ip_field = ip_field; } - ip = tep_read_number(pevent, data + ip_field->offset, ip_field->size); + ip = tep_read_number(tep, data + ip_field->offset, ip_field->size); /* * The first arg is the IP pointer. @@ -4338,6 +4337,7 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s case 'S': case 'f': case 'F': + case 'x': break; default: /* @@ -4360,7 +4360,7 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s vsize = 4; break; case 1: - vsize = pevent->long_size; + vsize = tep->long_size; break; case 2: vsize = 8; @@ -4377,7 +4377,7 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s /* the pointers are always 4 bytes aligned */ bptr = (void *)(((unsigned long)bptr + 3) & ~3); - val = tep_read_number(pevent, bptr, vsize); + val = tep_read_number(tep, bptr, vsize); bptr += vsize; arg = alloc_arg(); if (!arg) { @@ -4434,13 +4434,13 @@ static char * get_bprint_format(void *data, int size __maybe_unused, struct tep_event *event) { - struct tep_handle *pevent = event->pevent; + struct tep_handle *tep = event->tep; unsigned long long addr; struct tep_format_field *field; struct printk_map *printk; char *format; - field = pevent->bprint_fmt_field; + field = tep->bprint_fmt_field; if (!field) { field = tep_find_field(event, "fmt"); @@ -4448,12 +4448,12 @@ get_bprint_format(void *data, int size __maybe_unused, do_warning_event(event, "can't find format field for binary printk"); return NULL; } - pevent->bprint_fmt_field = field; + tep->bprint_fmt_field = field; } - addr = tep_read_number(pevent, data + field->offset, field->size); + addr = tep_read_number(tep, data + field->offset, field->size); - printk = find_printk(pevent, addr); + printk = find_printk(tep, addr); if (!printk) { if (asprintf(&format, "%%pf: (NO FORMAT FOUND at %llx)\n", addr) < 0) return NULL; @@ -4835,13 +4835,13 @@ void tep_print_field(struct trace_seq *s, void *data, { unsigned long long val; unsigned int offset, len, i; - struct tep_handle *pevent = field->event->pevent; + struct tep_handle *tep = field->event->tep; if (field->flags & TEP_FIELD_IS_ARRAY) { offset = field->offset; len = field->size; if (field->flags & TEP_FIELD_IS_DYNAMIC) { - val = tep_read_number(pevent, data + offset, len); + val = tep_read_number(tep, data + offset, len); offset = val; len = offset >> 16; offset &= 0xffff; @@ -4861,7 +4861,7 @@ void tep_print_field(struct trace_seq *s, void *data, field->flags &= ~TEP_FIELD_IS_STRING; } } else { - val = tep_read_number(pevent, data + field->offset, + val = tep_read_number(tep, data + field->offset, field->size); if (field->flags & TEP_FIELD_IS_POINTER) { trace_seq_printf(s, "0x%llx", val); @@ -4910,7 +4910,7 @@ void tep_print_fields(struct trace_seq *s, void *data, static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_event *event) { - struct tep_handle *pevent = event->pevent; + struct tep_handle *tep = event->tep; struct tep_print_fmt *print_fmt = &event->print_fmt; struct tep_print_arg *arg = print_fmt->args; struct tep_print_arg *args = NULL; @@ -5002,7 +5002,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_e case '-': goto cont_process; case 'p': - if (pevent->long_size == 4) + if (tep->long_size == 4) ls = 1; else ls = 2; @@ -5063,7 +5063,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_e arg = arg->next; if (show_func) { - func = find_func(pevent, val); + func = find_func(tep, val); if (func) { trace_seq_puts(s, func->func); if (show_func == 'F') @@ -5073,7 +5073,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_e break; } } - if (pevent->long_size == 8 && ls == 1 && + if (tep->long_size == 8 && ls == 1 && sizeof(long) != 8) { char *p; @@ -5171,8 +5171,8 @@ out_failed: } /** - * tep_data_lat_fmt - parse the data for the latency format - * @pevent: a handle to the pevent + * tep_data_latency_format - parse the data for the latency format + * @tep: a handle to the trace event parser context * @s: the trace_seq to write to * @record: the record to read from * @@ -5180,8 +5180,8 @@ out_failed: * need rescheduling, in hard/soft interrupt, preempt count * and lock depth) and places it into the trace_seq. */ -void tep_data_lat_fmt(struct tep_handle *pevent, - struct trace_seq *s, struct tep_record *record) +void tep_data_latency_format(struct tep_handle *tep, + struct trace_seq *s, struct tep_record *record) { static int check_lock_depth = 1; static int check_migrate_disable = 1; @@ -5195,13 +5195,13 @@ void tep_data_lat_fmt(struct tep_handle *pevent, int softirq; void *data = record->data; - lat_flags = parse_common_flags(pevent, data); - pc = parse_common_pc(pevent, data); + lat_flags = parse_common_flags(tep, data); + pc = parse_common_pc(tep, data); /* lock_depth may not always exist */ if (lock_depth_exists) - lock_depth = parse_common_lock_depth(pevent, data); + lock_depth = parse_common_lock_depth(tep, data); else if (check_lock_depth) { - lock_depth = parse_common_lock_depth(pevent, data); + lock_depth = parse_common_lock_depth(tep, data); if (lock_depth < 0) check_lock_depth = 0; else @@ -5210,9 +5210,9 @@ void tep_data_lat_fmt(struct tep_handle *pevent, /* migrate_disable may not always exist */ if (migrate_disable_exists) - migrate_disable = parse_common_migrate_disable(pevent, data); + migrate_disable = parse_common_migrate_disable(tep, data); else if (check_migrate_disable) { - migrate_disable = parse_common_migrate_disable(pevent, data); + migrate_disable = parse_common_migrate_disable(tep, data); if (migrate_disable < 0) check_migrate_disable = 0; else @@ -5255,79 +5255,79 @@ void tep_data_lat_fmt(struct tep_handle *pevent, /** * tep_data_type - parse out the given event type - * @pevent: a handle to the pevent + * @tep: a handle to the trace event parser context * @rec: the record to read from * * This returns the event id from the @rec. */ -int tep_data_type(struct tep_handle *pevent, struct tep_record *rec) +int tep_data_type(struct tep_handle *tep, struct tep_record *rec) { - return trace_parse_common_type(pevent, rec->data); + return trace_parse_common_type(tep, rec->data); } /** * tep_data_pid - parse the PID from record - * @pevent: a handle to the pevent + * @tep: a handle to the trace event parser context * @rec: the record to parse * * This returns the PID from a record. */ -int tep_data_pid(struct tep_handle *pevent, struct tep_record *rec) +int tep_data_pid(struct tep_handle *tep, struct tep_record *rec) { - return parse_common_pid(pevent, rec->data); + return parse_common_pid(tep, rec->data); } /** * tep_data_preempt_count - parse the preempt count from the record - * @pevent: a handle to the pevent + * @tep: a handle to the trace event parser context * @rec: the record to parse * * This returns the preempt count from a record. */ -int tep_data_preempt_count(struct tep_handle *pevent, struct tep_record *rec) +int tep_data_preempt_count(struct tep_handle *tep, struct tep_record *rec) { - return parse_common_pc(pevent, rec->data); + return parse_common_pc(tep, rec->data); } /** * tep_data_flags - parse the latency flags from the record - * @pevent: a handle to the pevent + * @tep: a handle to the trace event parser context * @rec: the record to parse * * This returns the latency flags from a record. * * Use trace_flag_type enum for the flags (see event-parse.h). */ -int tep_data_flags(struct tep_handle *pevent, struct tep_record *rec) +int tep_data_flags(struct tep_handle *tep, struct tep_record *rec) { - return parse_common_flags(pevent, rec->data); + return parse_common_flags(tep, rec->data); } /** * tep_data_comm_from_pid - return the command line from PID - * @pevent: a handle to the pevent + * @tep: a handle to the trace event parser context * @pid: the PID of the task to search for * * This returns a pointer to the command line that has the given * @pid. */ -const char *tep_data_comm_from_pid(struct tep_handle *pevent, int pid) +const char *tep_data_comm_from_pid(struct tep_handle *tep, int pid) { const char *comm; - comm = find_cmdline(pevent, pid); + comm = find_cmdline(tep, pid); return comm; } static struct tep_cmdline * -pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct tep_cmdline *next) +pid_from_cmdlist(struct tep_handle *tep, const char *comm, struct tep_cmdline *next) { struct cmdline_list *cmdlist = (struct cmdline_list *)next; if (cmdlist) cmdlist = cmdlist->next; else - cmdlist = pevent->cmdlist; + cmdlist = tep->cmdlist; while (cmdlist && strcmp(cmdlist->comm, comm) != 0) cmdlist = cmdlist->next; @@ -5337,7 +5337,7 @@ pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct tep_cmdline /** * tep_data_pid_from_comm - return the pid from a given comm - * @pevent: a handle to the pevent + * @tep: a handle to the trace event parser context * @comm: the cmdline to find the pid from * @next: the cmdline structure to find the next comm * @@ -5348,7 +5348,7 @@ pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct tep_cmdline * next pid. * Also, it does a linear search, so it may be slow. */ -struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm, +struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *tep, const char *comm, struct tep_cmdline *next) { struct tep_cmdline *cmdline; @@ -5357,25 +5357,25 @@ struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char * If the cmdlines have not been converted yet, then use * the list. */ - if (!pevent->cmdlines) - return pid_from_cmdlist(pevent, comm, next); + if (!tep->cmdlines) + return pid_from_cmdlist(tep, comm, next); if (next) { /* * The next pointer could have been still from * a previous call before cmdlines were created */ - if (next < pevent->cmdlines || - next >= pevent->cmdlines + pevent->cmdline_count) + if (next < tep->cmdlines || + next >= tep->cmdlines + tep->cmdline_count) next = NULL; else cmdline = next++; } if (!next) - cmdline = pevent->cmdlines; + cmdline = tep->cmdlines; - while (cmdline < pevent->cmdlines + pevent->cmdline_count) { + while (cmdline < tep->cmdlines + tep->cmdline_count) { if (strcmp(cmdline->comm, comm) == 0) return cmdline; cmdline++; @@ -5385,12 +5385,13 @@ struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char /** * tep_cmdline_pid - return the pid associated to a given cmdline + * @tep: a handle to the trace event parser context * @cmdline: The cmdline structure to get the pid from * * Returns the pid for a give cmdline. If @cmdline is NULL, then * -1 is returned. */ -int tep_cmdline_pid(struct tep_handle *pevent, struct tep_cmdline *cmdline) +int tep_cmdline_pid(struct tep_handle *tep, struct tep_cmdline *cmdline) { struct cmdline_list *cmdlist = (struct cmdline_list *)cmdline; @@ -5401,9 +5402,9 @@ int tep_cmdline_pid(struct tep_handle *pevent, struct tep_cmdline *cmdline) * If cmdlines have not been created yet, or cmdline is * not part of the array, then treat it as a cmdlist instead. */ - if (!pevent->cmdlines || - cmdline < pevent->cmdlines || - cmdline >= pevent->cmdlines + pevent->cmdline_count) + if (!tep->cmdlines || + cmdline < tep->cmdlines || + cmdline >= tep->cmdlines + tep->cmdline_count) return cmdlist->pid; return cmdline->pid; @@ -5423,7 +5424,7 @@ void tep_event_info(struct trace_seq *s, struct tep_event *event, { int print_pretty = 1; - if (event->pevent->print_raw || (event->flags & TEP_EVENT_FL_PRINTRAW)) + if (event->tep->print_raw || (event->flags & TEP_EVENT_FL_PRINTRAW)) tep_print_fields(s, record->data, record->size, event); else { @@ -5444,7 +5445,8 @@ static bool is_timestamp_in_us(char *trace_clock, bool use_trace_clock) return true; if (!strcmp(trace_clock, "local") || !strcmp(trace_clock, "global") - || !strcmp(trace_clock, "uptime") || !strcmp(trace_clock, "perf")) + || !strcmp(trace_clock, "uptime") || !strcmp(trace_clock, "perf") + || !strncmp(trace_clock, "mono", 4)) return true; /* trace_clock is setting in tsc or counter mode */ @@ -5453,14 +5455,14 @@ static bool is_timestamp_in_us(char *trace_clock, bool use_trace_clock) /** * tep_find_event_by_record - return the event from a given record - * @pevent: a handle to the pevent + * @tep: a handle to the trace event parser context * @record: The record to get the event from * * Returns the associated event for a given record, or NULL if non is * is found. */ struct tep_event * -tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record) +tep_find_event_by_record(struct tep_handle *tep, struct tep_record *record) { int type; @@ -5469,21 +5471,21 @@ tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record) return NULL; } - type = trace_parse_common_type(pevent, record->data); + type = trace_parse_common_type(tep, record->data); - return tep_find_event(pevent, type); + return tep_find_event(tep, type); } /** * tep_print_event_task - Write the event task comm, pid and CPU - * @pevent: a handle to the pevent + * @tep: a handle to the trace event parser context * @s: the trace_seq to write to * @event: the handle to the record's event * @record: The record to get the event from * * Writes the tasks comm, pid and CPU to @s. */ -void tep_print_event_task(struct tep_handle *pevent, struct trace_seq *s, +void tep_print_event_task(struct tep_handle *tep, struct trace_seq *s, struct tep_event *event, struct tep_record *record) { @@ -5491,27 +5493,26 @@ void tep_print_event_task(struct tep_handle *pevent, struct trace_seq *s, const char *comm; int pid; - pid = parse_common_pid(pevent, data); - comm = find_cmdline(pevent, pid); + pid = parse_common_pid(tep, data); + comm = find_cmdline(tep, pid); - if (pevent->latency_format) { - trace_seq_printf(s, "%8.8s-%-5d %3d", - comm, pid, record->cpu); - } else + if (tep->latency_format) + trace_seq_printf(s, "%8.8s-%-5d %3d", comm, pid, record->cpu); + else trace_seq_printf(s, "%16s-%-5d [%03d]", comm, pid, record->cpu); } /** * tep_print_event_time - Write the event timestamp - * @pevent: a handle to the pevent + * @tep: a handle to the trace event parser context * @s: the trace_seq to write to * @event: the handle to the record's event * @record: The record to get the event from - * @use_trace_clock: Set to parse according to the @pevent->trace_clock + * @use_trace_clock: Set to parse according to the @tep->trace_clock * * Writes the timestamp of the record into @s. */ -void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s, +void tep_print_event_time(struct tep_handle *tep, struct trace_seq *s, struct tep_event *event, struct tep_record *record, bool use_trace_clock) @@ -5522,19 +5523,18 @@ void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s, int p; bool use_usec_format; - use_usec_format = is_timestamp_in_us(pevent->trace_clock, - use_trace_clock); + use_usec_format = is_timestamp_in_us(tep->trace_clock, use_trace_clock); if (use_usec_format) { secs = record->ts / NSEC_PER_SEC; nsecs = record->ts - secs * NSEC_PER_SEC; } - if (pevent->latency_format) { - tep_data_lat_fmt(pevent, s, record); + if (tep->latency_format) { + tep_data_latency_format(tep, s, record); } if (use_usec_format) { - if (pevent->flags & TEP_NSEC_OUTPUT) { + if (tep->flags & TEP_NSEC_OUTPUT) { usecs = nsecs; p = 9; } else { @@ -5554,14 +5554,14 @@ void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s, /** * tep_print_event_data - Write the event data section - * @pevent: a handle to the pevent + * @tep: a handle to the trace event parser context * @s: the trace_seq to write to * @event: the handle to the record's event * @record: The record to get the event from * * Writes the parsing of the record's data to @s. */ -void tep_print_event_data(struct tep_handle *pevent, struct trace_seq *s, +void tep_print_event_data(struct tep_handle *tep, struct trace_seq *s, struct tep_event *event, struct tep_record *record) { @@ -5578,15 +5578,15 @@ void tep_print_event_data(struct tep_handle *pevent, struct trace_seq *s, tep_event_info(s, event, record); } -void tep_print_event(struct tep_handle *pevent, struct trace_seq *s, +void tep_print_event(struct tep_handle *tep, struct trace_seq *s, struct tep_record *record, bool use_trace_clock) { struct tep_event *event; - event = tep_find_event_by_record(pevent, record); + event = tep_find_event_by_record(tep, record); if (!event) { int i; - int type = trace_parse_common_type(pevent, record->data); + int type = trace_parse_common_type(tep, record->data); do_warning("ug! no event found for type %d", type); trace_seq_printf(s, "[UNKNOWN TYPE %d]", type); @@ -5596,9 +5596,9 @@ void tep_print_event(struct tep_handle *pevent, struct trace_seq *s, return; } - tep_print_event_task(pevent, s, event, record); - tep_print_event_time(pevent, s, event, record, use_trace_clock); - tep_print_event_data(pevent, s, event, record); + tep_print_event_task(tep, s, event, record); + tep_print_event_time(tep, s, event, record, use_trace_clock); + tep_print_event_data(tep, s, event, record); } static int events_id_cmp(const void *a, const void *b) @@ -5649,32 +5649,26 @@ static int events_system_cmp(const void *a, const void *b) return events_id_cmp(a, b); } -struct tep_event **tep_list_events(struct tep_handle *pevent, enum tep_event_sort_type sort_type) +static struct tep_event **list_events_copy(struct tep_handle *tep) { struct tep_event **events; - int (*sort)(const void *a, const void *b); - - events = pevent->sort_events; - - if (events && pevent->last_type == sort_type) - return events; - if (!events) { - events = malloc(sizeof(*events) * (pevent->nr_events + 1)); - if (!events) - return NULL; + if (!tep) + return NULL; - memcpy(events, pevent->events, sizeof(*events) * pevent->nr_events); - events[pevent->nr_events] = NULL; + events = malloc(sizeof(*events) * (tep->nr_events + 1)); + if (!events) + return NULL; - pevent->sort_events = events; + memcpy(events, tep->events, sizeof(*events) * tep->nr_events); + events[tep->nr_events] = NULL; + return events; +} - /* the internal events are sorted by id */ - if (sort_type == TEP_EVENT_SORT_ID) { - pevent->last_type = sort_type; - return events; - } - } +static void list_events_sort(struct tep_event **events, int nr_events, + enum tep_event_sort_type sort_type) +{ + int (*sort)(const void *a, const void *b); switch (sort_type) { case TEP_EVENT_SORT_ID: @@ -5687,11 +5681,82 @@ struct tep_event **tep_list_events(struct tep_handle *pevent, enum tep_event_sor sort = events_system_cmp; break; default: + sort = NULL; + } + + if (sort) + qsort(events, nr_events, sizeof(*events), sort); +} + +/** + * tep_list_events - Get events, sorted by given criteria. + * @tep: a handle to the tep context + * @sort_type: desired sort order of the events in the array + * + * Returns an array of pointers to all events, sorted by the given + * @sort_type criteria. The last element of the array is NULL. The returned + * memory must not be freed, it is managed by the library. + * The function is not thread safe. + */ +struct tep_event **tep_list_events(struct tep_handle *tep, + enum tep_event_sort_type sort_type) +{ + struct tep_event **events; + + if (!tep) + return NULL; + + events = tep->sort_events; + if (events && tep->last_type == sort_type) return events; + + if (!events) { + events = list_events_copy(tep); + if (!events) + return NULL; + + tep->sort_events = events; + + /* the internal events are sorted by id */ + if (sort_type == TEP_EVENT_SORT_ID) { + tep->last_type = sort_type; + return events; + } } - qsort(events, pevent->nr_events, sizeof(*events), sort); - pevent->last_type = sort_type; + list_events_sort(events, tep->nr_events, sort_type); + tep->last_type = sort_type; + + return events; +} + + +/** + * tep_list_events_copy - Thread safe version of tep_list_events() + * @tep: a handle to the tep context + * @sort_type: desired sort order of the events in the array + * + * Returns an array of pointers to all events, sorted by the given + * @sort_type criteria. The last element of the array is NULL. The returned + * array is newly allocated inside the function and must be freed by the caller + */ +struct tep_event **tep_list_events_copy(struct tep_handle *tep, + enum tep_event_sort_type sort_type) +{ + struct tep_event **events; + + if (!tep) + return NULL; + + events = list_events_copy(tep); + if (!events) + return NULL; + + /* the internal events are sorted by id */ + if (sort_type == TEP_EVENT_SORT_ID) + return events; + + list_events_sort(events, tep->nr_events, sort_type); return events; } @@ -5950,7 +6015,7 @@ static void parse_header_field(const char *field, /** * tep_parse_header_page - parse the data stored in the header page - * @pevent: the handle to the pevent + * @tep: a handle to the trace event parser context * @buf: the buffer storing the header page format string * @size: the size of @buf * @long_size: the long size to use if there is no header @@ -5960,7 +6025,7 @@ static void parse_header_field(const char *field, * * /sys/kernel/debug/tracing/events/header_page */ -int tep_parse_header_page(struct tep_handle *pevent, char *buf, unsigned long size, +int tep_parse_header_page(struct tep_handle *tep, char *buf, unsigned long size, int long_size) { int ignore; @@ -5970,22 +6035,22 @@ int tep_parse_header_page(struct tep_handle *pevent, char *buf, unsigned long si * Old kernels did not have header page info. * Sorry but we just use what we find here in user space. */ - pevent->header_page_ts_size = sizeof(long long); - pevent->header_page_size_size = long_size; - pevent->header_page_data_offset = sizeof(long long) + long_size; - pevent->old_format = 1; + tep->header_page_ts_size = sizeof(long long); + tep->header_page_size_size = long_size; + tep->header_page_data_offset = sizeof(long long) + long_size; + tep->old_format = 1; return -1; } init_input_buf(buf, size); - parse_header_field("timestamp", &pevent->header_page_ts_offset, - &pevent->header_page_ts_size, 1); - parse_header_field("commit", &pevent->header_page_size_offset, - &pevent->header_page_size_size, 1); - parse_header_field("overwrite", &pevent->header_page_overwrite, + parse_header_field("timestamp", &tep->header_page_ts_offset, + &tep->header_page_ts_size, 1); + parse_header_field("commit", &tep->header_page_size_offset, + &tep->header_page_size_size, 1); + parse_header_field("overwrite", &tep->header_page_overwrite, &ignore, 0); - parse_header_field("data", &pevent->header_page_data_offset, - &pevent->header_page_data_size, 1); + parse_header_field("data", &tep->header_page_data_offset, + &tep->header_page_data_size, 1); return 0; } @@ -6013,11 +6078,11 @@ static void free_handler(struct event_handler *handle) free(handle); } -static int find_event_handle(struct tep_handle *pevent, struct tep_event *event) +static int find_event_handle(struct tep_handle *tep, struct tep_event *event) { struct event_handler *handle, **next; - for (next = &pevent->handlers; *next; + for (next = &tep->handlers; *next; next = &(*next)->next) { handle = *next; if (event_matches(event, handle->id, @@ -6055,7 +6120,7 @@ static int find_event_handle(struct tep_handle *pevent, struct tep_event *event) * /sys/kernel/debug/tracing/events/.../.../format */ enum tep_errno __tep_parse_format(struct tep_event **eventp, - struct tep_handle *pevent, const char *buf, + struct tep_handle *tep, const char *buf, unsigned long size, const char *sys) { struct tep_event *event; @@ -6097,8 +6162,8 @@ enum tep_errno __tep_parse_format(struct tep_event **eventp, goto event_alloc_failed; } - /* Add pevent to event so that it can be referenced */ - event->pevent = pevent; + /* Add tep to event so that it can be referenced */ + event->tep = tep; ret = event_read_format(event); if (ret < 0) { @@ -6110,7 +6175,7 @@ enum tep_errno __tep_parse_format(struct tep_event **eventp, * If the event has an override, don't print warnings if the event * print format fails to parse. */ - if (pevent && find_event_handle(pevent, event)) + if (tep && find_event_handle(tep, event)) show_warning = 0; ret = event_read_print(event); @@ -6162,18 +6227,18 @@ enum tep_errno __tep_parse_format(struct tep_event **eventp, } static enum tep_errno -__parse_event(struct tep_handle *pevent, +__parse_event(struct tep_handle *tep, struct tep_event **eventp, const char *buf, unsigned long size, const char *sys) { - int ret = __tep_parse_format(eventp, pevent, buf, size, sys); + int ret = __tep_parse_format(eventp, tep, buf, size, sys); struct tep_event *event = *eventp; if (event == NULL) return ret; - if (pevent && add_event(pevent, event)) { + if (tep && add_event(tep, event)) { ret = TEP_ERRNO__MEM_ALLOC_FAILED; goto event_add_failed; } @@ -6191,7 +6256,7 @@ event_add_failed: /** * tep_parse_format - parse the event format - * @pevent: the handle to the pevent + * @tep: a handle to the trace event parser context * @eventp: returned format * @buf: the buffer storing the event format string * @size: the size of @buf @@ -6204,17 +6269,17 @@ event_add_failed: * * /sys/kernel/debug/tracing/events/.../.../format */ -enum tep_errno tep_parse_format(struct tep_handle *pevent, +enum tep_errno tep_parse_format(struct tep_handle *tep, struct tep_event **eventp, const char *buf, unsigned long size, const char *sys) { - return __parse_event(pevent, eventp, buf, size, sys); + return __parse_event(tep, eventp, buf, size, sys); } /** * tep_parse_event - parse the event format - * @pevent: the handle to the pevent + * @tep: a handle to the trace event parser context * @buf: the buffer storing the event format string * @size: the size of @buf * @sys: the system the event belongs to @@ -6226,11 +6291,11 @@ enum tep_errno tep_parse_format(struct tep_handle *pevent, * * /sys/kernel/debug/tracing/events/.../.../format */ -enum tep_errno tep_parse_event(struct tep_handle *pevent, const char *buf, +enum tep_errno tep_parse_event(struct tep_handle *tep, const char *buf, unsigned long size, const char *sys) { struct tep_event *event = NULL; - return __parse_event(pevent, &event, buf, size, sys); + return __parse_event(tep, &event, buf, size, sys); } int get_field_val(struct trace_seq *s, struct tep_format_field *field, @@ -6292,8 +6357,8 @@ void *tep_get_field_raw(struct trace_seq *s, struct tep_event *event, offset = field->offset; if (field->flags & TEP_FIELD_IS_DYNAMIC) { - offset = tep_read_number(event->pevent, - data + offset, field->size); + offset = tep_read_number(event->tep, + data + offset, field->size); *len = offset >> 16; offset &= 0xffff; } else @@ -6386,7 +6451,8 @@ int tep_get_any_field_val(struct trace_seq *s, struct tep_event *event, * @record: The record with the field name. * @err: print default error if failed. * - * Returns: 0 on success, -1 field not found, or 1 if buffer is full. + * Returns positive value on success, negative in case of an error, + * or 0 if buffer is full. */ int tep_print_num_field(struct trace_seq *s, const char *fmt, struct tep_event *event, const char *name, @@ -6418,14 +6484,15 @@ int tep_print_num_field(struct trace_seq *s, const char *fmt, * @record: The record with the field name. * @err: print default error if failed. * - * Returns: 0 on success, -1 field not found, or 1 if buffer is full. + * Returns positive value on success, negative in case of an error, + * or 0 if buffer is full. */ int tep_print_func_field(struct trace_seq *s, const char *fmt, struct tep_event *event, const char *name, struct tep_record *record, int err) { struct tep_format_field *field = tep_find_field(event, name); - struct tep_handle *pevent = event->pevent; + struct tep_handle *tep = event->tep; unsigned long long val; struct func_map *func; char tmp[128]; @@ -6436,7 +6503,7 @@ int tep_print_func_field(struct trace_seq *s, const char *fmt, if (tep_read_number_field(field, record->data, &val)) goto failed; - func = find_func(pevent, val); + func = find_func(tep, val); if (func) snprintf(tmp, 128, "%s/0x%llx", func->func, func->addr - val); @@ -6468,7 +6535,7 @@ static void free_func_handle(struct tep_function_handler *func) /** * tep_register_print_function - register a helper function - * @pevent: the handle to the pevent + * @tep: a handle to the trace event parser context * @func: the function to process the helper function * @ret_type: the return type of the helper function * @name: the name of the helper function @@ -6481,7 +6548,7 @@ static void free_func_handle(struct tep_function_handler *func) * The @parameters is a variable list of tep_func_arg_type enums that * must end with TEP_FUNC_ARG_VOID. */ -int tep_register_print_function(struct tep_handle *pevent, +int tep_register_print_function(struct tep_handle *tep, tep_func_handler func, enum tep_func_arg_type ret_type, char *name, ...) @@ -6493,7 +6560,7 @@ int tep_register_print_function(struct tep_handle *pevent, va_list ap; int ret; - func_handle = find_func_handler(pevent, name); + func_handle = find_func_handler(tep, name); if (func_handle) { /* * This is most like caused by the users own @@ -6501,7 +6568,7 @@ int tep_register_print_function(struct tep_handle *pevent, * system defaults. */ pr_stat("override of function helper '%s'", name); - remove_func_handler(pevent, name); + remove_func_handler(tep, name); } func_handle = calloc(1, sizeof(*func_handle)); @@ -6548,8 +6615,8 @@ int tep_register_print_function(struct tep_handle *pevent, } va_end(ap); - func_handle->next = pevent->func_handlers; - pevent->func_handlers = func_handle; + func_handle->next = tep->func_handlers; + tep->func_handlers = func_handle; return 0; out_free: @@ -6560,7 +6627,7 @@ int tep_register_print_function(struct tep_handle *pevent, /** * tep_unregister_print_function - unregister a helper function - * @pevent: the handle to the pevent + * @tep: a handle to the trace event parser context * @func: the function to process the helper function * @name: the name of the helper function * @@ -6568,20 +6635,20 @@ int tep_register_print_function(struct tep_handle *pevent, * * Returns 0 if the handler was removed successully, -1 otherwise. */ -int tep_unregister_print_function(struct tep_handle *pevent, +int tep_unregister_print_function(struct tep_handle *tep, tep_func_handler func, char *name) { struct tep_function_handler *func_handle; - func_handle = find_func_handler(pevent, name); + func_handle = find_func_handler(tep, name); if (func_handle && func_handle->func == func) { - remove_func_handler(pevent, name); + remove_func_handler(tep, name); return 0; } return -1; } -static struct tep_event *search_event(struct tep_handle *pevent, int id, +static struct tep_event *search_event(struct tep_handle *tep, int id, const char *sys_name, const char *event_name) { @@ -6589,7 +6656,7 @@ static struct tep_event *search_event(struct tep_handle *pevent, int id, if (id >= 0) { /* search by id */ - event = tep_find_event(pevent, id); + event = tep_find_event(tep, id); if (!event) return NULL; if (event_name && (strcmp(event_name, event->name) != 0)) @@ -6597,7 +6664,7 @@ static struct tep_event *search_event(struct tep_handle *pevent, int id, if (sys_name && (strcmp(sys_name, event->system) != 0)) return NULL; } else { - event = tep_find_event_by_name(pevent, sys_name, event_name); + event = tep_find_event_by_name(tep, sys_name, event_name); if (!event) return NULL; } @@ -6606,7 +6673,7 @@ static struct tep_event *search_event(struct tep_handle *pevent, int id, /** * tep_register_event_handler - register a way to parse an event - * @pevent: the handle to the pevent + * @tep: a handle to the trace event parser context * @id: the id of the event to register * @sys_name: the system name the event belongs to * @event_name: the name of the event @@ -6627,14 +6694,14 @@ static struct tep_event *search_event(struct tep_handle *pevent, int id, * negative TEP_ERRNO_... in case of an error * */ -int tep_register_event_handler(struct tep_handle *pevent, int id, +int tep_register_event_handler(struct tep_handle *tep, int id, const char *sys_name, const char *event_name, tep_event_handler_func func, void *context) { struct tep_event *event; struct event_handler *handle; - event = search_event(pevent, id, sys_name, event_name); + event = search_event(tep, id, sys_name, event_name); if (event == NULL) goto not_found; @@ -6669,8 +6736,8 @@ int tep_register_event_handler(struct tep_handle *pevent, int id, } handle->func = func; - handle->next = pevent->handlers; - pevent->handlers = handle; + handle->next = tep->handlers; + tep->handlers = handle; handle->context = context; return TEP_REGISTER_SUCCESS; @@ -6697,7 +6764,7 @@ static int handle_matches(struct event_handler *handler, int id, /** * tep_unregister_event_handler - unregister an existing event handler - * @pevent: the handle to the pevent + * @tep: a handle to the trace event parser context * @id: the id of the event to unregister * @sys_name: the system name the handler belongs to * @event_name: the name of the event handler @@ -6711,7 +6778,7 @@ static int handle_matches(struct event_handler *handler, int id, * * Returns 0 if handler was removed successfully, -1 if event was not found. */ -int tep_unregister_event_handler(struct tep_handle *pevent, int id, +int tep_unregister_event_handler(struct tep_handle *tep, int id, const char *sys_name, const char *event_name, tep_event_handler_func func, void *context) { @@ -6719,7 +6786,7 @@ int tep_unregister_event_handler(struct tep_handle *pevent, int id, struct event_handler *handle; struct event_handler **next; - event = search_event(pevent, id, sys_name, event_name); + event = search_event(tep, id, sys_name, event_name); if (event == NULL) goto not_found; @@ -6733,7 +6800,7 @@ int tep_unregister_event_handler(struct tep_handle *pevent, int id, } not_found: - for (next = &pevent->handlers; *next; next = &(*next)->next) { + for (next = &tep->handlers; *next; next = &(*next)->next) { handle = *next; if (handle_matches(handle, id, sys_name, event_name, func, context)) @@ -6750,23 +6817,23 @@ not_found: } /** - * tep_alloc - create a pevent handle + * tep_alloc - create a tep handle */ struct tep_handle *tep_alloc(void) { - struct tep_handle *pevent = calloc(1, sizeof(*pevent)); + struct tep_handle *tep = calloc(1, sizeof(*tep)); - if (pevent) { - pevent->ref_count = 1; - pevent->host_bigendian = tep_host_bigendian(); + if (tep) { + tep->ref_count = 1; + tep->host_bigendian = tep_is_bigendian(); } - return pevent; + return tep; } -void tep_ref(struct tep_handle *pevent) +void tep_ref(struct tep_handle *tep) { - pevent->ref_count++; + tep->ref_count++; } int tep_get_ref(struct tep_handle *tep) @@ -6816,10 +6883,10 @@ void tep_free_event(struct tep_event *event) } /** - * tep_free - free a pevent handle - * @pevent: the pevent handle to free + * tep_free - free a tep handle + * @tep: the tep handle to free */ -void tep_free(struct tep_handle *pevent) +void tep_free(struct tep_handle *tep) { struct cmdline_list *cmdlist, *cmdnext; struct func_list *funclist, *funcnext; @@ -6828,21 +6895,21 @@ void tep_free(struct tep_handle *pevent) struct event_handler *handle; int i; - if (!pevent) + if (!tep) return; - cmdlist = pevent->cmdlist; - funclist = pevent->funclist; - printklist = pevent->printklist; + cmdlist = tep->cmdlist; + funclist = tep->funclist; + printklist = tep->printklist; - pevent->ref_count--; - if (pevent->ref_count) + tep->ref_count--; + if (tep->ref_count) return; - if (pevent->cmdlines) { - for (i = 0; i < pevent->cmdline_count; i++) - free(pevent->cmdlines[i].comm); - free(pevent->cmdlines); + if (tep->cmdlines) { + for (i = 0; i < tep->cmdline_count; i++) + free(tep->cmdlines[i].comm); + free(tep->cmdlines); } while (cmdlist) { @@ -6852,12 +6919,12 @@ void tep_free(struct tep_handle *pevent) cmdlist = cmdnext; } - if (pevent->func_map) { - for (i = 0; i < (int)pevent->func_count; i++) { - free(pevent->func_map[i].func); - free(pevent->func_map[i].mod); + if (tep->func_map) { + for (i = 0; i < (int)tep->func_count; i++) { + free(tep->func_map[i].func); + free(tep->func_map[i].mod); } - free(pevent->func_map); + free(tep->func_map); } while (funclist) { @@ -6868,16 +6935,16 @@ void tep_free(struct tep_handle *pevent) funclist = funcnext; } - while (pevent->func_handlers) { - func_handler = pevent->func_handlers; - pevent->func_handlers = func_handler->next; + while (tep->func_handlers) { + func_handler = tep->func_handlers; + tep->func_handlers = func_handler->next; free_func_handle(func_handler); } - if (pevent->printk_map) { - for (i = 0; i < (int)pevent->printk_count; i++) - free(pevent->printk_map[i].printk); - free(pevent->printk_map); + if (tep->printk_map) { + for (i = 0; i < (int)tep->printk_count; i++) + free(tep->printk_map[i].printk); + free(tep->printk_map); } while (printklist) { @@ -6887,24 +6954,24 @@ void tep_free(struct tep_handle *pevent) printklist = printknext; } - for (i = 0; i < pevent->nr_events; i++) - tep_free_event(pevent->events[i]); + for (i = 0; i < tep->nr_events; i++) + tep_free_event(tep->events[i]); - while (pevent->handlers) { - handle = pevent->handlers; - pevent->handlers = handle->next; + while (tep->handlers) { + handle = tep->handlers; + tep->handlers = handle->next; free_handler(handle); } - free(pevent->trace_clock); - free(pevent->events); - free(pevent->sort_events); - free(pevent->func_resolver); + free(tep->trace_clock); + free(tep->events); + free(tep->sort_events); + free(tep->func_resolver); - free(pevent); + free(tep); } -void tep_unref(struct tep_handle *pevent) +void tep_unref(struct tep_handle *tep) { - tep_free(pevent); + tep_free(tep); } diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h index aec48f2aea8a..642f68ab5fb2 100644 --- a/tools/lib/traceevent/event-parse.h +++ b/tools/lib/traceevent/event-parse.h @@ -64,8 +64,8 @@ typedef int (*tep_event_handler_func)(struct trace_seq *s, struct tep_event *event, void *context); -typedef int (*tep_plugin_load_func)(struct tep_handle *pevent); -typedef int (*tep_plugin_unload_func)(struct tep_handle *pevent); +typedef int (*tep_plugin_load_func)(struct tep_handle *tep); +typedef int (*tep_plugin_unload_func)(struct tep_handle *tep); struct tep_plugin_option { struct tep_plugin_option *next; @@ -85,12 +85,12 @@ struct tep_plugin_option { * TEP_PLUGIN_LOADER: (required) * The function name to initialized the plugin. * - * int TEP_PLUGIN_LOADER(struct tep_handle *pevent) + * int TEP_PLUGIN_LOADER(struct tep_handle *tep) * * TEP_PLUGIN_UNLOADER: (optional) * The function called just before unloading * - * int TEP_PLUGIN_UNLOADER(struct tep_handle *pevent) + * int TEP_PLUGIN_UNLOADER(struct tep_handle *tep) * * TEP_PLUGIN_OPTIONS: (optional) * Plugin options that can be set before loading @@ -278,7 +278,7 @@ struct tep_print_fmt { }; struct tep_event { - struct tep_handle *pevent; + struct tep_handle *tep; char *name; int id; int flags; @@ -393,9 +393,9 @@ struct tep_plugin_list; #define INVALID_PLUGIN_LIST_OPTION ((char **)((unsigned long)-1)) -struct tep_plugin_list *tep_load_plugins(struct tep_handle *pevent); +struct tep_plugin_list *tep_load_plugins(struct tep_handle *tep); void tep_unload_plugins(struct tep_plugin_list *plugin_list, - struct tep_handle *pevent); + struct tep_handle *tep); char **tep_plugin_list_options(void); void tep_plugin_free_options_list(char **list); int tep_plugin_add_options(const char *name, @@ -409,8 +409,10 @@ void tep_print_plugins(struct trace_seq *s, typedef char *(tep_func_resolver_t)(void *priv, unsigned long long *addrp, char **modp); void tep_set_flag(struct tep_handle *tep, int flag); +void tep_clear_flag(struct tep_handle *tep, enum tep_flag flag); +bool tep_test_flag(struct tep_handle *tep, enum tep_flag flags); -static inline int tep_host_bigendian(void) +static inline int tep_is_bigendian(void) { unsigned char str[] = { 0x1, 0x2, 0x3, 0x4 }; unsigned int val; @@ -428,37 +430,37 @@ enum trace_flag_type { TRACE_FLAG_SOFTIRQ = 0x10, }; -int tep_set_function_resolver(struct tep_handle *pevent, +int tep_set_function_resolver(struct tep_handle *tep, tep_func_resolver_t *func, void *priv); -void tep_reset_function_resolver(struct tep_handle *pevent); -int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid); -int tep_override_comm(struct tep_handle *pevent, const char *comm, int pid); -int tep_register_trace_clock(struct tep_handle *pevent, const char *trace_clock); -int tep_register_function(struct tep_handle *pevent, char *name, +void tep_reset_function_resolver(struct tep_handle *tep); +int tep_register_comm(struct tep_handle *tep, const char *comm, int pid); +int tep_override_comm(struct tep_handle *tep, const char *comm, int pid); +int tep_register_trace_clock(struct tep_handle *tep, const char *trace_clock); +int tep_register_function(struct tep_handle *tep, char *name, unsigned long long addr, char *mod); -int tep_register_print_string(struct tep_handle *pevent, const char *fmt, +int tep_register_print_string(struct tep_handle *tep, const char *fmt, unsigned long long addr); -int tep_pid_is_registered(struct tep_handle *pevent, int pid); +bool tep_is_pid_registered(struct tep_handle *tep, int pid); -void tep_print_event_task(struct tep_handle *pevent, struct trace_seq *s, +void tep_print_event_task(struct tep_handle *tep, struct trace_seq *s, struct tep_event *event, struct tep_record *record); -void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s, +void tep_print_event_time(struct tep_handle *tep, struct trace_seq *s, struct tep_event *event, struct tep_record *record, bool use_trace_clock); -void tep_print_event_data(struct tep_handle *pevent, struct trace_seq *s, +void tep_print_event_data(struct tep_handle *tep, struct trace_seq *s, struct tep_event *event, struct tep_record *record); -void tep_print_event(struct tep_handle *pevent, struct trace_seq *s, +void tep_print_event(struct tep_handle *tep, struct trace_seq *s, struct tep_record *record, bool use_trace_clock); -int tep_parse_header_page(struct tep_handle *pevent, char *buf, unsigned long size, +int tep_parse_header_page(struct tep_handle *tep, char *buf, unsigned long size, int long_size); -enum tep_errno tep_parse_event(struct tep_handle *pevent, const char *buf, +enum tep_errno tep_parse_event(struct tep_handle *tep, const char *buf, unsigned long size, const char *sys); -enum tep_errno tep_parse_format(struct tep_handle *pevent, +enum tep_errno tep_parse_format(struct tep_handle *tep, struct tep_event **eventp, const char *buf, unsigned long size, const char *sys); @@ -490,50 +492,50 @@ enum tep_reg_handler { TEP_REGISTER_SUCCESS_OVERWRITE, }; -int tep_register_event_handler(struct tep_handle *pevent, int id, +int tep_register_event_handler(struct tep_handle *tep, int id, const char *sys_name, const char *event_name, tep_event_handler_func func, void *context); -int tep_unregister_event_handler(struct tep_handle *pevent, int id, +int tep_unregister_event_handler(struct tep_handle *tep, int id, const char *sys_name, const char *event_name, tep_event_handler_func func, void *context); -int tep_register_print_function(struct tep_handle *pevent, +int tep_register_print_function(struct tep_handle *tep, tep_func_handler func, enum tep_func_arg_type ret_type, char *name, ...); -int tep_unregister_print_function(struct tep_handle *pevent, +int tep_unregister_print_function(struct tep_handle *tep, tep_func_handler func, char *name); struct tep_format_field *tep_find_common_field(struct tep_event *event, const char *name); struct tep_format_field *tep_find_field(struct tep_event *event, const char *name); struct tep_format_field *tep_find_any_field(struct tep_event *event, const char *name); -const char *tep_find_function(struct tep_handle *pevent, unsigned long long addr); +const char *tep_find_function(struct tep_handle *tep, unsigned long long addr); unsigned long long -tep_find_function_address(struct tep_handle *pevent, unsigned long long addr); -unsigned long long tep_read_number(struct tep_handle *pevent, const void *ptr, int size); +tep_find_function_address(struct tep_handle *tep, unsigned long long addr); +unsigned long long tep_read_number(struct tep_handle *tep, const void *ptr, int size); int tep_read_number_field(struct tep_format_field *field, const void *data, unsigned long long *value); struct tep_event *tep_get_first_event(struct tep_handle *tep); int tep_get_events_count(struct tep_handle *tep); -struct tep_event *tep_find_event(struct tep_handle *pevent, int id); +struct tep_event *tep_find_event(struct tep_handle *tep, int id); struct tep_event * -tep_find_event_by_name(struct tep_handle *pevent, const char *sys, const char *name); +tep_find_event_by_name(struct tep_handle *tep, const char *sys, const char *name); struct tep_event * -tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record); - -void tep_data_lat_fmt(struct tep_handle *pevent, - struct trace_seq *s, struct tep_record *record); -int tep_data_type(struct tep_handle *pevent, struct tep_record *rec); -int tep_data_pid(struct tep_handle *pevent, struct tep_record *rec); -int tep_data_preempt_count(struct tep_handle *pevent, struct tep_record *rec); -int tep_data_flags(struct tep_handle *pevent, struct tep_record *rec); -const char *tep_data_comm_from_pid(struct tep_handle *pevent, int pid); +tep_find_event_by_record(struct tep_handle *tep, struct tep_record *record); + +void tep_data_latency_format(struct tep_handle *tep, + struct trace_seq *s, struct tep_record *record); +int tep_data_type(struct tep_handle *tep, struct tep_record *rec); +int tep_data_pid(struct tep_handle *tep, struct tep_record *rec); +int tep_data_preempt_count(struct tep_handle *tep, struct tep_record *rec); +int tep_data_flags(struct tep_handle *tep, struct tep_record *rec); +const char *tep_data_comm_from_pid(struct tep_handle *tep, int pid); struct tep_cmdline; -struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm, +struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *tep, const char *comm, struct tep_cmdline *next); -int tep_cmdline_pid(struct tep_handle *pevent, struct tep_cmdline *cmdline); +int tep_cmdline_pid(struct tep_handle *tep, struct tep_cmdline *cmdline); void tep_print_field(struct trace_seq *s, void *data, struct tep_format_field *field); @@ -541,10 +543,12 @@ void tep_print_fields(struct trace_seq *s, void *data, int size __maybe_unused, struct tep_event *event); void tep_event_info(struct trace_seq *s, struct tep_event *event, struct tep_record *record); -int tep_strerror(struct tep_handle *pevent, enum tep_errno errnum, +int tep_strerror(struct tep_handle *tep, enum tep_errno errnum, char *buf, size_t buflen); -struct tep_event **tep_list_events(struct tep_handle *pevent, enum tep_event_sort_type); +struct tep_event **tep_list_events(struct tep_handle *tep, enum tep_event_sort_type); +struct tep_event **tep_list_events_copy(struct tep_handle *tep, + enum tep_event_sort_type); struct tep_format_field **tep_event_common_fields(struct tep_event *event); struct tep_format_field **tep_event_fields(struct tep_event *event); @@ -552,24 +556,28 @@ enum tep_endian { TEP_LITTLE_ENDIAN = 0, TEP_BIG_ENDIAN }; -int tep_get_cpus(struct tep_handle *pevent); -void tep_set_cpus(struct tep_handle *pevent, int cpus); -int tep_get_long_size(struct tep_handle *pevent); -void tep_set_long_size(struct tep_handle *pevent, int long_size); -int tep_get_page_size(struct tep_handle *pevent); -void tep_set_page_size(struct tep_handle *pevent, int _page_size); -int tep_file_bigendian(struct tep_handle *pevent); -void tep_set_file_bigendian(struct tep_handle *pevent, enum tep_endian endian); -int tep_is_host_bigendian(struct tep_handle *pevent); -void tep_set_host_bigendian(struct tep_handle *pevent, enum tep_endian endian); -int tep_is_latency_format(struct tep_handle *pevent); -void tep_set_latency_format(struct tep_handle *pevent, int lat); -int tep_get_header_page_size(struct tep_handle *pevent); +int tep_get_cpus(struct tep_handle *tep); +void tep_set_cpus(struct tep_handle *tep, int cpus); +int tep_get_long_size(struct tep_handle *tep); +void tep_set_long_size(struct tep_handle *tep, int long_size); +int tep_get_page_size(struct tep_handle *tep); +void tep_set_page_size(struct tep_handle *tep, int _page_size); +bool tep_is_file_bigendian(struct tep_handle *tep); +void tep_set_file_bigendian(struct tep_handle *tep, enum tep_endian endian); +bool tep_is_local_bigendian(struct tep_handle *tep); +void tep_set_local_bigendian(struct tep_handle *tep, enum tep_endian endian); +bool tep_is_latency_format(struct tep_handle *tep); +void tep_set_latency_format(struct tep_handle *tep, int lat); +int tep_get_header_page_size(struct tep_handle *tep); +int tep_get_header_timestamp_size(struct tep_handle *tep); +bool tep_is_old_format(struct tep_handle *tep); +void tep_set_print_raw(struct tep_handle *tep, int print_raw); +void tep_set_test_filters(struct tep_handle *tep, int test_filters); struct tep_handle *tep_alloc(void); -void tep_free(struct tep_handle *pevent); -void tep_ref(struct tep_handle *pevent); -void tep_unref(struct tep_handle *pevent); +void tep_free(struct tep_handle *tep); +void tep_ref(struct tep_handle *tep); +void tep_unref(struct tep_handle *tep); int tep_get_ref(struct tep_handle *tep); /* access to the internal parser */ @@ -581,8 +589,8 @@ const char *tep_get_input_buf(void); unsigned long long tep_get_input_buf_ptr(void); /* for debugging */ -void tep_print_funcs(struct tep_handle *pevent); -void tep_print_printk(struct tep_handle *pevent); +void tep_print_funcs(struct tep_handle *tep); +void tep_print_printk(struct tep_handle *tep); /* ----------------------- filtering ----------------------- */ @@ -709,13 +717,13 @@ struct tep_filter_type { #define TEP_FILTER_ERROR_BUFSZ 1024 struct tep_event_filter { - struct tep_handle *pevent; + struct tep_handle *tep; int filters; struct tep_filter_type *event_filters; char error_buffer[TEP_FILTER_ERROR_BUFSZ]; }; -struct tep_event_filter *tep_filter_alloc(struct tep_handle *pevent); +struct tep_event_filter *tep_filter_alloc(struct tep_handle *tep); /* for backward compatibility */ #define FILTER_NONE TEP_ERRNO__NO_FILTER @@ -723,12 +731,6 @@ struct tep_event_filter *tep_filter_alloc(struct tep_handle *pevent); #define FILTER_MISS TEP_ERRNO__FILTER_MISS #define FILTER_MATCH TEP_ERRNO__FILTER_MATCH -enum tep_filter_trivial_type { - TEP_FILTER_TRIVIAL_FALSE, - TEP_FILTER_TRIVIAL_TRUE, - TEP_FILTER_TRIVIAL_BOTH, -}; - enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter, const char *filter_str); @@ -743,9 +745,6 @@ int tep_event_filtered(struct tep_event_filter *filter, void tep_filter_reset(struct tep_event_filter *filter); -int tep_filter_clear_trivial(struct tep_event_filter *filter, - enum tep_filter_trivial_type type); - void tep_filter_free(struct tep_event_filter *filter); char *tep_filter_make_string(struct tep_event_filter *filter, int event_id); @@ -753,15 +752,8 @@ char *tep_filter_make_string(struct tep_event_filter *filter, int event_id); int tep_filter_remove_event(struct tep_event_filter *filter, int event_id); -int tep_filter_event_has_trivial(struct tep_event_filter *filter, - int event_id, - enum tep_filter_trivial_type type); - int tep_filter_copy(struct tep_event_filter *dest, struct tep_event_filter *source); -int tep_update_trivial(struct tep_event_filter *dest, struct tep_event_filter *source, - enum tep_filter_trivial_type type); - int tep_filter_compare(struct tep_event_filter *filter1, struct tep_event_filter *filter2); #endif /* _PARSE_EVENTS_H */ diff --git a/tools/lib/traceevent/event-plugin.c b/tools/lib/traceevent/event-plugin.c index e74f16c88398..8ca28de9337a 100644 --- a/tools/lib/traceevent/event-plugin.c +++ b/tools/lib/traceevent/event-plugin.c @@ -269,7 +269,7 @@ void tep_print_plugins(struct trace_seq *s, } static void -load_plugin(struct tep_handle *pevent, const char *path, +load_plugin(struct tep_handle *tep, const char *path, const char *file, void *data) { struct tep_plugin_list **plugin_list = data; @@ -316,7 +316,7 @@ load_plugin(struct tep_handle *pevent, const char *path, *plugin_list = list; pr_stat("registering plugin: %s", plugin); - func(pevent); + func(tep); return; out_free: @@ -324,9 +324,9 @@ load_plugin(struct tep_handle *pevent, const char *path, } static void -load_plugins_dir(struct tep_handle *pevent, const char *suffix, +load_plugins_dir(struct tep_handle *tep, const char *suffix, const char *path, - void (*load_plugin)(struct tep_handle *pevent, + void (*load_plugin)(struct tep_handle *tep, const char *path, const char *name, void *data), @@ -359,15 +359,15 @@ load_plugins_dir(struct tep_handle *pevent, const char *suffix, if (strcmp(name + (strlen(name) - strlen(suffix)), suffix) != 0) continue; - load_plugin(pevent, path, name, data); + load_plugin(tep, path, name, data); } closedir(dir); } static void -load_plugins(struct tep_handle *pevent, const char *suffix, - void (*load_plugin)(struct tep_handle *pevent, +load_plugins(struct tep_handle *tep, const char *suffix, + void (*load_plugin)(struct tep_handle *tep, const char *path, const char *name, void *data), @@ -378,7 +378,7 @@ load_plugins(struct tep_handle *pevent, const char *suffix, char *envdir; int ret; - if (pevent->flags & TEP_DISABLE_PLUGINS) + if (tep->flags & TEP_DISABLE_PLUGINS) return; /* @@ -386,8 +386,8 @@ load_plugins(struct tep_handle *pevent, const char *suffix, * check that first. */ #ifdef PLUGIN_DIR - if (!(pevent->flags & TEP_DISABLE_SYS_PLUGINS)) - load_plugins_dir(pevent, suffix, PLUGIN_DIR, + if (!(tep->flags & TEP_DISABLE_SYS_PLUGINS)) + load_plugins_dir(tep, suffix, PLUGIN_DIR, load_plugin, data); #endif @@ -397,7 +397,7 @@ load_plugins(struct tep_handle *pevent, const char *suffix, */ envdir = getenv("TRACEEVENT_PLUGIN_DIR"); if (envdir) - load_plugins_dir(pevent, suffix, envdir, load_plugin, data); + load_plugins_dir(tep, suffix, envdir, load_plugin, data); /* * Now let the home directory override the environment @@ -413,22 +413,22 @@ load_plugins(struct tep_handle *pevent, const char *suffix, return; } - load_plugins_dir(pevent, suffix, path, load_plugin, data); + load_plugins_dir(tep, suffix, path, load_plugin, data); free(path); } struct tep_plugin_list* -tep_load_plugins(struct tep_handle *pevent) +tep_load_plugins(struct tep_handle *tep) { struct tep_plugin_list *list = NULL; - load_plugins(pevent, ".so", load_plugin, &list); + load_plugins(tep, ".so", load_plugin, &list); return list; } void -tep_unload_plugins(struct tep_plugin_list *plugin_list, struct tep_handle *pevent) +tep_unload_plugins(struct tep_plugin_list *plugin_list, struct tep_handle *tep) { tep_plugin_unload_func func; struct tep_plugin_list *list; @@ -438,7 +438,7 @@ tep_unload_plugins(struct tep_plugin_list *plugin_list, struct tep_handle *peven plugin_list = list->next; func = dlsym(list->handle, TEP_PLUGIN_UNLOADER_NAME); if (func) - func(pevent); + func(tep); dlclose(list->handle); free(list->name); free(list); diff --git a/tools/lib/traceevent/kbuffer-parse.c b/tools/lib/traceevent/kbuffer-parse.c index af2a1f3b7424..b887e7437d67 100644 --- a/tools/lib/traceevent/kbuffer-parse.c +++ b/tools/lib/traceevent/kbuffer-parse.c @@ -727,3 +727,52 @@ int kbuffer_start_of_data(struct kbuffer *kbuf) { return kbuf->start; } + +/** + * kbuffer_raw_get - get raw buffer info + * @kbuf: The kbuffer + * @subbuf: Start of mapped subbuffer + * @info: Info descriptor to fill in + * + * For debugging. This can return internals of the ring buffer. + * Expects to have info->next set to what it will read. + * The type, length and timestamp delta will be filled in, and + * @info->next will be updated to the next element. + * The @subbuf is used to know if the info is passed the end of + * data and NULL will be returned if it is. + */ +struct kbuffer_raw_info * +kbuffer_raw_get(struct kbuffer *kbuf, void *subbuf, struct kbuffer_raw_info *info) +{ + unsigned long long flags; + unsigned long long delta; + unsigned int type_len; + unsigned int size; + int start; + int length; + void *ptr = info->next; + + if (!kbuf || !subbuf) + return NULL; + + if (kbuf->flags & KBUFFER_FL_LONG_8) + start = 16; + else + start = 12; + + flags = read_long(kbuf, subbuf + 8); + size = (unsigned int)flags & COMMIT_MASK; + + if (ptr < subbuf || ptr >= subbuf + start + size) + return NULL; + + type_len = translate_data(kbuf, ptr, &ptr, &delta, &length); + + info->next = ptr + length; + + info->type = type_len; + info->delta = delta; + info->length = length; + + return info; +} diff --git a/tools/lib/traceevent/kbuffer.h b/tools/lib/traceevent/kbuffer.h index 03dce757553f..ed4d697fc137 100644 --- a/tools/lib/traceevent/kbuffer.h +++ b/tools/lib/traceevent/kbuffer.h @@ -65,4 +65,17 @@ int kbuffer_subbuffer_size(struct kbuffer *kbuf); void kbuffer_set_old_format(struct kbuffer *kbuf); int kbuffer_start_of_data(struct kbuffer *kbuf); +/* Debugging */ + +struct kbuffer_raw_info { + int type; + int length; + unsigned long long delta; + void *next; +}; + +/* Read raw data */ +struct kbuffer_raw_info *kbuffer_raw_get(struct kbuffer *kbuf, void *subbuf, + struct kbuffer_raw_info *info); + #endif /* _K_BUFFER_H */ diff --git a/tools/lib/traceevent/libtraceevent.pc.template b/tools/lib/traceevent/libtraceevent.pc.template index 42e4d6cb6b9e..86384fcd57f1 100644 --- a/tools/lib/traceevent/libtraceevent.pc.template +++ b/tools/lib/traceevent/libtraceevent.pc.template @@ -1,6 +1,6 @@ prefix=INSTALL_PREFIX -libdir=${prefix}/lib64 -includedir=${prefix}/include/traceevent +libdir=LIB_DIR +includedir=HEADER_DIR Name: libtraceevent URL: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c index cb5ce66dab6e..552592d153fb 100644 --- a/tools/lib/traceevent/parse-filter.c +++ b/tools/lib/traceevent/parse-filter.c @@ -154,7 +154,7 @@ add_filter_type(struct tep_event_filter *filter, int id) filter_type = &filter->event_filters[i]; filter_type->event_id = id; - filter_type->event = tep_find_event(filter->pevent, id); + filter_type->event = tep_find_event(filter->tep, id); filter_type->filter = NULL; filter->filters++; @@ -164,9 +164,9 @@ add_filter_type(struct tep_event_filter *filter, int id) /** * tep_filter_alloc - create a new event filter - * @pevent: The pevent that this filter is associated with + * @tep: The tep that this filter is associated with */ -struct tep_event_filter *tep_filter_alloc(struct tep_handle *pevent) +struct tep_event_filter *tep_filter_alloc(struct tep_handle *tep) { struct tep_event_filter *filter; @@ -175,8 +175,8 @@ struct tep_event_filter *tep_filter_alloc(struct tep_handle *pevent) return NULL; memset(filter, 0, sizeof(*filter)); - filter->pevent = pevent; - tep_ref(pevent); + filter->tep = tep; + tep_ref(tep); return filter; } @@ -256,7 +256,7 @@ static int event_match(struct tep_event *event, } static enum tep_errno -find_event(struct tep_handle *pevent, struct event_list **events, +find_event(struct tep_handle *tep, struct event_list **events, char *sys_name, char *event_name) { struct tep_event *event; @@ -299,8 +299,8 @@ find_event(struct tep_handle *pevent, struct event_list **events, } } - for (i = 0; i < pevent->nr_events; i++) { - event = pevent->events[i]; + for (i = 0; i < tep->nr_events; i++) { + event = tep->events[i]; if (event_match(event, sys_name ? &sreg : NULL, &ereg)) { match = 1; if (add_event(events, event) < 0) { @@ -1257,7 +1257,7 @@ static void filter_init_error_buf(struct tep_event_filter *filter) enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter, const char *filter_str) { - struct tep_handle *pevent = filter->pevent; + struct tep_handle *tep = filter->tep; struct event_list *event; struct event_list *events = NULL; const char *filter_start; @@ -1313,7 +1313,7 @@ enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter, } /* Find this event */ - ret = find_event(pevent, &events, strim(sys_name), strim(event_name)); + ret = find_event(tep, &events, strim(sys_name), strim(event_name)); if (ret < 0) { free_events(events); free(this_event); @@ -1334,7 +1334,7 @@ enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter, if (ret < 0) rtn = ret; - if (ret >= 0 && pevent->test_filters) { + if (ret >= 0 && tep->test_filters) { char *test; test = tep_filter_make_string(filter, event->event->id); if (test) { @@ -1346,9 +1346,6 @@ enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter, free_events(events); - if (rtn >= 0 && pevent->test_filters) - exit(0); - return rtn; } @@ -1380,7 +1377,7 @@ int tep_filter_strerror(struct tep_event_filter *filter, enum tep_errno err, return 0; } - return tep_strerror(filter->pevent, err, buf, buflen); + return tep_strerror(filter->tep, err, buf, buflen); } /** @@ -1443,7 +1440,7 @@ void tep_filter_reset(struct tep_event_filter *filter) void tep_filter_free(struct tep_event_filter *filter) { - tep_unref(filter->pevent); + tep_unref(filter->tep); tep_filter_reset(filter); @@ -1462,10 +1459,10 @@ static int copy_filter_type(struct tep_event_filter *filter, const char *name; char *str; - /* Can't assume that the pevent's are the same */ + /* Can't assume that the tep's are the same */ sys = filter_type->event->system; name = filter_type->event->name; - event = tep_find_event_by_name(filter->pevent, sys, name); + event = tep_find_event_by_name(filter->tep, sys, name); if (!event) return -1; @@ -1522,167 +1519,6 @@ int tep_filter_copy(struct tep_event_filter *dest, struct tep_event_filter *sour return ret; } - -/** - * tep_update_trivial - update the trivial filters with the given filter - * @dest - the filter to update - * @source - the filter as the source of the update - * @type - the type of trivial filter to update. - * - * Scan dest for trivial events matching @type to replace with the source. - * - * Returns 0 on success and -1 if there was a problem updating, but - * events may have still been updated on error. - */ -int tep_update_trivial(struct tep_event_filter *dest, struct tep_event_filter *source, - enum tep_filter_trivial_type type) -{ - struct tep_handle *src_pevent; - struct tep_handle *dest_pevent; - struct tep_event *event; - struct tep_filter_type *filter_type; - struct tep_filter_arg *arg; - char *str; - int i; - - src_pevent = source->pevent; - dest_pevent = dest->pevent; - - /* Do nothing if either of the filters has nothing to filter */ - if (!dest->filters || !source->filters) - return 0; - - for (i = 0; i < dest->filters; i++) { - filter_type = &dest->event_filters[i]; - arg = filter_type->filter; - if (arg->type != TEP_FILTER_ARG_BOOLEAN) - continue; - if ((arg->boolean.value && type == TEP_FILTER_TRIVIAL_FALSE) || - (!arg->boolean.value && type == TEP_FILTER_TRIVIAL_TRUE)) - continue; - - event = filter_type->event; - - if (src_pevent != dest_pevent) { - /* do a look up */ - event = tep_find_event_by_name(src_pevent, - event->system, - event->name); - if (!event) - return -1; - } - - str = tep_filter_make_string(source, event->id); - if (!str) - continue; - - /* Don't bother if the filter is trivial too */ - if (strcmp(str, "TRUE") != 0 && strcmp(str, "FALSE") != 0) - filter_event(dest, event, str, NULL); - free(str); - } - return 0; -} - -/** - * tep_filter_clear_trivial - clear TRUE and FALSE filters - * @filter: the filter to remove trivial filters from - * @type: remove only true, false, or both - * - * Removes filters that only contain a TRUE or FALES boolean arg. - * - * Returns 0 on success and -1 if there was a problem. - */ -int tep_filter_clear_trivial(struct tep_event_filter *filter, - enum tep_filter_trivial_type type) -{ - struct tep_filter_type *filter_type; - int count = 0; - int *ids = NULL; - int i; - - if (!filter->filters) - return 0; - - /* - * Two steps, first get all ids with trivial filters. - * then remove those ids. - */ - for (i = 0; i < filter->filters; i++) { - int *new_ids; - - filter_type = &filter->event_filters[i]; - if (filter_type->filter->type != TEP_FILTER_ARG_BOOLEAN) - continue; - switch (type) { - case TEP_FILTER_TRIVIAL_FALSE: - if (filter_type->filter->boolean.value) - continue; - break; - case TEP_FILTER_TRIVIAL_TRUE: - if (!filter_type->filter->boolean.value) - continue; - default: - break; - } - - new_ids = realloc(ids, sizeof(*ids) * (count + 1)); - if (!new_ids) { - free(ids); - return -1; - } - - ids = new_ids; - ids[count++] = filter_type->event_id; - } - - if (!count) - return 0; - - for (i = 0; i < count; i++) - tep_filter_remove_event(filter, ids[i]); - - free(ids); - return 0; -} - -/** - * tep_filter_event_has_trivial - return true event contains trivial filter - * @filter: the filter with the information - * @event_id: the id of the event to test - * @type: trivial type to test for (TRUE, FALSE, EITHER) - * - * Returns 1 if the event contains a matching trivial type - * otherwise 0. - */ -int tep_filter_event_has_trivial(struct tep_event_filter *filter, - int event_id, - enum tep_filter_trivial_type type) -{ - struct tep_filter_type *filter_type; - - if (!filter->filters) - return 0; - - filter_type = find_filter_type(filter, event_id); - - if (!filter_type) - return 0; - - if (filter_type->filter->type != TEP_FILTER_ARG_BOOLEAN) - return 0; - - switch (type) { - case TEP_FILTER_TRIVIAL_FALSE: - return !filter_type->filter->boolean.value; - - case TEP_FILTER_TRIVIAL_TRUE: - return filter_type->filter->boolean.value; - default: - return 1; - } -} - static int test_filter(struct tep_event *event, struct tep_filter_arg *arg, struct tep_record *record, enum tep_errno *err); @@ -1692,8 +1528,8 @@ get_comm(struct tep_event *event, struct tep_record *record) const char *comm; int pid; - pid = tep_data_pid(event->pevent, record); - comm = tep_data_comm_from_pid(event->pevent, pid); + pid = tep_data_pid(event->tep, record); + comm = tep_data_comm_from_pid(event->tep, pid); return comm; } @@ -1861,7 +1697,7 @@ static int test_num(struct tep_event *event, struct tep_filter_arg *arg, static const char *get_field_str(struct tep_filter_arg *arg, struct tep_record *record) { struct tep_event *event; - struct tep_handle *pevent; + struct tep_handle *tep; unsigned long long addr; const char *val = NULL; unsigned int size; @@ -1891,12 +1727,12 @@ static const char *get_field_str(struct tep_filter_arg *arg, struct tep_record * } else { event = arg->str.field->event; - pevent = event->pevent; + tep = event->tep; addr = get_value(event, arg->str.field, record); if (arg->str.field->flags & (TEP_FIELD_IS_POINTER | TEP_FIELD_IS_LONG)) /* convert to a kernel symbol */ - val = tep_find_function(pevent, addr); + val = tep_find_function(tep, addr); if (val == NULL) { /* just use the hex of the string name */ @@ -2036,7 +1872,7 @@ int tep_event_filtered(struct tep_event_filter *filter, int event_id) enum tep_errno tep_filter_match(struct tep_event_filter *filter, struct tep_record *record) { - struct tep_handle *pevent = filter->pevent; + struct tep_handle *tep = filter->tep; struct tep_filter_type *filter_type; int event_id; int ret; @@ -2047,7 +1883,7 @@ enum tep_errno tep_filter_match(struct tep_event_filter *filter, if (!filter->filters) return TEP_ERRNO__NO_FILTER; - event_id = tep_data_type(pevent, record); + event_id = tep_data_type(tep, record); filter_type = find_filter_type(filter, event_id); if (!filter_type) @@ -2409,14 +2245,6 @@ int tep_filter_compare(struct tep_event_filter *filter1, struct tep_event_filter break; if (filter_type1->filter->type != filter_type2->filter->type) break; - switch (filter_type1->filter->type) { - case TEP_FILTER_TRIVIAL_FALSE: - case TEP_FILTER_TRIVIAL_TRUE: - /* trivial types just need the type compared */ - continue; - default: - break; - } /* The best way to compare complex filters is with strings */ str1 = arg_to_str(filter1, filter_type1->filter); str2 = arg_to_str(filter2, filter_type2->filter); diff --git a/tools/lib/traceevent/parse-utils.c b/tools/lib/traceevent/parse-utils.c index 77e4ec6402dd..e99867111387 100644 --- a/tools/lib/traceevent/parse-utils.c +++ b/tools/lib/traceevent/parse-utils.c @@ -14,7 +14,7 @@ void __vwarning(const char *fmt, va_list ap) { if (errno) - perror("trace-cmd"); + perror("libtraceevent"); errno = 0; fprintf(stderr, " "); diff --git a/tools/lib/traceevent/plugin_cfg80211.c b/tools/lib/traceevent/plugin_cfg80211.c index a51b366f47da..3d43b56a6c98 100644 --- a/tools/lib/traceevent/plugin_cfg80211.c +++ b/tools/lib/traceevent/plugin_cfg80211.c @@ -25,9 +25,9 @@ process___le16_to_cpup(struct trace_seq *s, unsigned long long *args) return val ? (long long) le16toh(*val) : 0; } -int TEP_PLUGIN_LOADER(struct tep_handle *pevent) +int TEP_PLUGIN_LOADER(struct tep_handle *tep) { - tep_register_print_function(pevent, + tep_register_print_function(tep, process___le16_to_cpup, TEP_FUNC_ARG_INT, "__le16_to_cpup", @@ -36,8 +36,8 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent) return 0; } -void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent) +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) { - tep_unregister_print_function(pevent, process___le16_to_cpup, + tep_unregister_print_function(tep, process___le16_to_cpup, "__le16_to_cpup"); } diff --git a/tools/lib/traceevent/plugin_function.c b/tools/lib/traceevent/plugin_function.c index a73eca34a8f9..7770fcb78e0f 100644 --- a/tools/lib/traceevent/plugin_function.c +++ b/tools/lib/traceevent/plugin_function.c @@ -126,7 +126,7 @@ static int add_and_get_index(const char *parent, const char *child, int cpu) static int function_handler(struct trace_seq *s, struct tep_record *record, struct tep_event *event, void *context) { - struct tep_handle *pevent = event->pevent; + struct tep_handle *tep = event->tep; unsigned long long function; unsigned long long pfunction; const char *func; @@ -136,12 +136,12 @@ static int function_handler(struct trace_seq *s, struct tep_record *record, if (tep_get_field_val(s, event, "ip", record, &function, 1)) return trace_seq_putc(s, '!'); - func = tep_find_function(pevent, function); + func = tep_find_function(tep, function); if (tep_get_field_val(s, event, "parent_ip", record, &pfunction, 1)) return trace_seq_putc(s, '!'); - parent = tep_find_function(pevent, pfunction); + parent = tep_find_function(tep, pfunction); if (parent && ftrace_indent->set) index = add_and_get_index(parent, func, record->cpu); @@ -164,9 +164,9 @@ static int function_handler(struct trace_seq *s, struct tep_record *record, return 0; } -int TEP_PLUGIN_LOADER(struct tep_handle *pevent) +int TEP_PLUGIN_LOADER(struct tep_handle *tep) { - tep_register_event_handler(pevent, -1, "ftrace", "function", + tep_register_event_handler(tep, -1, "ftrace", "function", function_handler, NULL); tep_plugin_add_options("ftrace", plugin_options); @@ -174,11 +174,11 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent) return 0; } -void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent) +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) { int i, x; - tep_unregister_event_handler(pevent, -1, "ftrace", "function", + tep_unregister_event_handler(tep, -1, "ftrace", "function", function_handler, NULL); for (i = 0; i <= cpus; i++) { diff --git a/tools/lib/traceevent/plugin_hrtimer.c b/tools/lib/traceevent/plugin_hrtimer.c index 5db5e401275f..bb434e0ed03a 100644 --- a/tools/lib/traceevent/plugin_hrtimer.c +++ b/tools/lib/traceevent/plugin_hrtimer.c @@ -67,23 +67,23 @@ static int timer_start_handler(struct trace_seq *s, return 0; } -int TEP_PLUGIN_LOADER(struct tep_handle *pevent) +int TEP_PLUGIN_LOADER(struct tep_handle *tep) { - tep_register_event_handler(pevent, -1, + tep_register_event_handler(tep, -1, "timer", "hrtimer_expire_entry", timer_expire_handler, NULL); - tep_register_event_handler(pevent, -1, "timer", "hrtimer_start", + tep_register_event_handler(tep, -1, "timer", "hrtimer_start", timer_start_handler, NULL); return 0; } -void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent) +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) { - tep_unregister_event_handler(pevent, -1, + tep_unregister_event_handler(tep, -1, "timer", "hrtimer_expire_entry", timer_expire_handler, NULL); - tep_unregister_event_handler(pevent, -1, "timer", "hrtimer_start", + tep_unregister_event_handler(tep, -1, "timer", "hrtimer_start", timer_start_handler, NULL); } diff --git a/tools/lib/traceevent/plugin_jbd2.c b/tools/lib/traceevent/plugin_jbd2.c index a5e34135dd6a..04fc125f38cb 100644 --- a/tools/lib/traceevent/plugin_jbd2.c +++ b/tools/lib/traceevent/plugin_jbd2.c @@ -48,16 +48,16 @@ process_jiffies_to_msecs(struct trace_seq *s, unsigned long long *args) return jiffies; } -int TEP_PLUGIN_LOADER(struct tep_handle *pevent) +int TEP_PLUGIN_LOADER(struct tep_handle *tep) { - tep_register_print_function(pevent, + tep_register_print_function(tep, process_jbd2_dev_to_name, TEP_FUNC_ARG_STRING, "jbd2_dev_to_name", TEP_FUNC_ARG_INT, TEP_FUNC_ARG_VOID); - tep_register_print_function(pevent, + tep_register_print_function(tep, process_jiffies_to_msecs, TEP_FUNC_ARG_LONG, "jiffies_to_msecs", @@ -66,11 +66,11 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent) return 0; } -void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent) +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) { - tep_unregister_print_function(pevent, process_jbd2_dev_to_name, + tep_unregister_print_function(tep, process_jbd2_dev_to_name, "jbd2_dev_to_name"); - tep_unregister_print_function(pevent, process_jiffies_to_msecs, + tep_unregister_print_function(tep, process_jiffies_to_msecs, "jiffies_to_msecs"); } diff --git a/tools/lib/traceevent/plugin_kmem.c b/tools/lib/traceevent/plugin_kmem.c index 0e3c601f9ed1..edaec5d962c3 100644 --- a/tools/lib/traceevent/plugin_kmem.c +++ b/tools/lib/traceevent/plugin_kmem.c @@ -39,57 +39,57 @@ static int call_site_handler(struct trace_seq *s, struct tep_record *record, if (tep_read_number_field(field, data, &val)) return 1; - func = tep_find_function(event->pevent, val); + func = tep_find_function(event->tep, val); if (!func) return 1; - addr = tep_find_function_address(event->pevent, val); + addr = tep_find_function_address(event->tep, val); trace_seq_printf(s, "(%s+0x%x) ", func, (int)(val - addr)); return 1; } -int TEP_PLUGIN_LOADER(struct tep_handle *pevent) +int TEP_PLUGIN_LOADER(struct tep_handle *tep) { - tep_register_event_handler(pevent, -1, "kmem", "kfree", + tep_register_event_handler(tep, -1, "kmem", "kfree", call_site_handler, NULL); - tep_register_event_handler(pevent, -1, "kmem", "kmalloc", + tep_register_event_handler(tep, -1, "kmem", "kmalloc", call_site_handler, NULL); - tep_register_event_handler(pevent, -1, "kmem", "kmalloc_node", + tep_register_event_handler(tep, -1, "kmem", "kmalloc_node", call_site_handler, NULL); - tep_register_event_handler(pevent, -1, "kmem", "kmem_cache_alloc", + tep_register_event_handler(tep, -1, "kmem", "kmem_cache_alloc", call_site_handler, NULL); - tep_register_event_handler(pevent, -1, "kmem", + tep_register_event_handler(tep, -1, "kmem", "kmem_cache_alloc_node", call_site_handler, NULL); - tep_register_event_handler(pevent, -1, "kmem", "kmem_cache_free", + tep_register_event_handler(tep, -1, "kmem", "kmem_cache_free", call_site_handler, NULL); return 0; } -void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent) +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) { - tep_unregister_event_handler(pevent, -1, "kmem", "kfree", + tep_unregister_event_handler(tep, -1, "kmem", "kfree", call_site_handler, NULL); - tep_unregister_event_handler(pevent, -1, "kmem", "kmalloc", + tep_unregister_event_handler(tep, -1, "kmem", "kmalloc", call_site_handler, NULL); - tep_unregister_event_handler(pevent, -1, "kmem", "kmalloc_node", + tep_unregister_event_handler(tep, -1, "kmem", "kmalloc_node", call_site_handler, NULL); - tep_unregister_event_handler(pevent, -1, "kmem", "kmem_cache_alloc", + tep_unregister_event_handler(tep, -1, "kmem", "kmem_cache_alloc", call_site_handler, NULL); - tep_unregister_event_handler(pevent, -1, "kmem", + tep_unregister_event_handler(tep, -1, "kmem", "kmem_cache_alloc_node", call_site_handler, NULL); - tep_unregister_event_handler(pevent, -1, "kmem", "kmem_cache_free", + tep_unregister_event_handler(tep, -1, "kmem", "kmem_cache_free", call_site_handler, NULL); } diff --git a/tools/lib/traceevent/plugin_kvm.c b/tools/lib/traceevent/plugin_kvm.c index 64b9c25a1fd3..c8e623065a7e 100644 --- a/tools/lib/traceevent/plugin_kvm.c +++ b/tools/lib/traceevent/plugin_kvm.c @@ -389,8 +389,8 @@ static int kvm_mmu_print_role(struct trace_seq *s, struct tep_record *record, * We can only use the structure if file is of the same * endianness. */ - if (tep_file_bigendian(event->pevent) == - tep_is_host_bigendian(event->pevent)) { + if (tep_is_file_bigendian(event->tep) == + tep_is_local_bigendian(event->tep)) { trace_seq_printf(s, "%u q%u%s %s%s %spae %snxe %swp%s%s%s", role.level, @@ -445,40 +445,40 @@ process_is_writable_pte(struct trace_seq *s, unsigned long long *args) return pte & PT_WRITABLE_MASK; } -int TEP_PLUGIN_LOADER(struct tep_handle *pevent) +int TEP_PLUGIN_LOADER(struct tep_handle *tep) { init_disassembler(); - tep_register_event_handler(pevent, -1, "kvm", "kvm_exit", + tep_register_event_handler(tep, -1, "kvm", "kvm_exit", kvm_exit_handler, NULL); - tep_register_event_handler(pevent, -1, "kvm", "kvm_emulate_insn", + tep_register_event_handler(tep, -1, "kvm", "kvm_emulate_insn", kvm_emulate_insn_handler, NULL); - tep_register_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit", + tep_register_event_handler(tep, -1, "kvm", "kvm_nested_vmexit", kvm_nested_vmexit_handler, NULL); - tep_register_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit_inject", + tep_register_event_handler(tep, -1, "kvm", "kvm_nested_vmexit_inject", kvm_nested_vmexit_inject_handler, NULL); - tep_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_get_page", + tep_register_event_handler(tep, -1, "kvmmmu", "kvm_mmu_get_page", kvm_mmu_get_page_handler, NULL); - tep_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_sync_page", + tep_register_event_handler(tep, -1, "kvmmmu", "kvm_mmu_sync_page", kvm_mmu_print_role, NULL); - tep_register_event_handler(pevent, -1, + tep_register_event_handler(tep, -1, "kvmmmu", "kvm_mmu_unsync_page", kvm_mmu_print_role, NULL); - tep_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_zap_page", + tep_register_event_handler(tep, -1, "kvmmmu", "kvm_mmu_zap_page", kvm_mmu_print_role, NULL); - tep_register_event_handler(pevent, -1, "kvmmmu", + tep_register_event_handler(tep, -1, "kvmmmu", "kvm_mmu_prepare_zap_page", kvm_mmu_print_role, NULL); - tep_register_print_function(pevent, + tep_register_print_function(tep, process_is_writable_pte, TEP_FUNC_ARG_INT, "is_writable_pte", @@ -487,37 +487,37 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent) return 0; } -void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent) +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) { - tep_unregister_event_handler(pevent, -1, "kvm", "kvm_exit", + tep_unregister_event_handler(tep, -1, "kvm", "kvm_exit", kvm_exit_handler, NULL); - tep_unregister_event_handler(pevent, -1, "kvm", "kvm_emulate_insn", + tep_unregister_event_handler(tep, -1, "kvm", "kvm_emulate_insn", kvm_emulate_insn_handler, NULL); - tep_unregister_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit", + tep_unregister_event_handler(tep, -1, "kvm", "kvm_nested_vmexit", kvm_nested_vmexit_handler, NULL); - tep_unregister_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit_inject", + tep_unregister_event_handler(tep, -1, "kvm", "kvm_nested_vmexit_inject", kvm_nested_vmexit_inject_handler, NULL); - tep_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_get_page", + tep_unregister_event_handler(tep, -1, "kvmmmu", "kvm_mmu_get_page", kvm_mmu_get_page_handler, NULL); - tep_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_sync_page", + tep_unregister_event_handler(tep, -1, "kvmmmu", "kvm_mmu_sync_page", kvm_mmu_print_role, NULL); - tep_unregister_event_handler(pevent, -1, + tep_unregister_event_handler(tep, -1, "kvmmmu", "kvm_mmu_unsync_page", kvm_mmu_print_role, NULL); - tep_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_zap_page", + tep_unregister_event_handler(tep, -1, "kvmmmu", "kvm_mmu_zap_page", kvm_mmu_print_role, NULL); - tep_unregister_event_handler(pevent, -1, "kvmmmu", + tep_unregister_event_handler(tep, -1, "kvmmmu", "kvm_mmu_prepare_zap_page", kvm_mmu_print_role, NULL); - tep_unregister_print_function(pevent, process_is_writable_pte, + tep_unregister_print_function(tep, process_is_writable_pte, "is_writable_pte"); } diff --git a/tools/lib/traceevent/plugin_mac80211.c b/tools/lib/traceevent/plugin_mac80211.c index e38b9477aad2..884303c26b5c 100644 --- a/tools/lib/traceevent/plugin_mac80211.c +++ b/tools/lib/traceevent/plugin_mac80211.c @@ -87,17 +87,17 @@ static int drv_bss_info_changed(struct trace_seq *s, return 0; } -int TEP_PLUGIN_LOADER(struct tep_handle *pevent) +int TEP_PLUGIN_LOADER(struct tep_handle *tep) { - tep_register_event_handler(pevent, -1, "mac80211", + tep_register_event_handler(tep, -1, "mac80211", "drv_bss_info_changed", drv_bss_info_changed, NULL); return 0; } -void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent) +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) { - tep_unregister_event_handler(pevent, -1, "mac80211", + tep_unregister_event_handler(tep, -1, "mac80211", "drv_bss_info_changed", drv_bss_info_changed, NULL); } diff --git a/tools/lib/traceevent/plugin_sched_switch.c b/tools/lib/traceevent/plugin_sched_switch.c index 834c9e378ff8..957389a0ff7a 100644 --- a/tools/lib/traceevent/plugin_sched_switch.c +++ b/tools/lib/traceevent/plugin_sched_switch.c @@ -62,7 +62,7 @@ static void write_and_save_comm(struct tep_format_field *field, comm = &s->buffer[len]; /* Help out the comm to ids. This will handle dups */ - tep_register_comm(field->event->pevent, comm, pid); + tep_register_comm(field->event->tep, comm, pid); } static int sched_wakeup_handler(struct trace_seq *s, @@ -135,27 +135,27 @@ static int sched_switch_handler(struct trace_seq *s, return 0; } -int TEP_PLUGIN_LOADER(struct tep_handle *pevent) +int TEP_PLUGIN_LOADER(struct tep_handle *tep) { - tep_register_event_handler(pevent, -1, "sched", "sched_switch", + tep_register_event_handler(tep, -1, "sched", "sched_switch", sched_switch_handler, NULL); - tep_register_event_handler(pevent, -1, "sched", "sched_wakeup", + tep_register_event_handler(tep, -1, "sched", "sched_wakeup", sched_wakeup_handler, NULL); - tep_register_event_handler(pevent, -1, "sched", "sched_wakeup_new", + tep_register_event_handler(tep, -1, "sched", "sched_wakeup_new", sched_wakeup_handler, NULL); return 0; } -void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent) +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) { - tep_unregister_event_handler(pevent, -1, "sched", "sched_switch", + tep_unregister_event_handler(tep, -1, "sched", "sched_switch", sched_switch_handler, NULL); - tep_unregister_event_handler(pevent, -1, "sched", "sched_wakeup", + tep_unregister_event_handler(tep, -1, "sched", "sched_wakeup", sched_wakeup_handler, NULL); - tep_unregister_event_handler(pevent, -1, "sched", "sched_wakeup_new", + tep_unregister_event_handler(tep, -1, "sched", "sched_wakeup_new", sched_wakeup_handler, NULL); } diff --git a/tools/lib/traceevent/plugin_scsi.c b/tools/lib/traceevent/plugin_scsi.c index 4eba25cc1431..5d0387a4b65a 100644 --- a/tools/lib/traceevent/plugin_scsi.c +++ b/tools/lib/traceevent/plugin_scsi.c @@ -414,9 +414,9 @@ unsigned long long process_scsi_trace_parse_cdb(struct trace_seq *s, return 0; } -int TEP_PLUGIN_LOADER(struct tep_handle *pevent) +int TEP_PLUGIN_LOADER(struct tep_handle *tep) { - tep_register_print_function(pevent, + tep_register_print_function(tep, process_scsi_trace_parse_cdb, TEP_FUNC_ARG_STRING, "scsi_trace_parse_cdb", @@ -427,8 +427,8 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent) return 0; } -void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent) +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) { - tep_unregister_print_function(pevent, process_scsi_trace_parse_cdb, + tep_unregister_print_function(tep, process_scsi_trace_parse_cdb, "scsi_trace_parse_cdb"); } diff --git a/tools/lib/traceevent/plugin_xen.c b/tools/lib/traceevent/plugin_xen.c index bc0496e4c296..993b208d0323 100644 --- a/tools/lib/traceevent/plugin_xen.c +++ b/tools/lib/traceevent/plugin_xen.c @@ -120,9 +120,9 @@ unsigned long long process_xen_hypercall_name(struct trace_seq *s, return 0; } -int TEP_PLUGIN_LOADER(struct tep_handle *pevent) +int TEP_PLUGIN_LOADER(struct tep_handle *tep) { - tep_register_print_function(pevent, + tep_register_print_function(tep, process_xen_hypercall_name, TEP_FUNC_ARG_STRING, "xen_hypercall_name", @@ -131,8 +131,8 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent) return 0; } -void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent) +void TEP_PLUGIN_UNLOADER(struct tep_handle *tep) { - tep_unregister_print_function(pevent, process_xen_hypercall_name, + tep_unregister_print_function(tep, process_xen_hypercall_name, "xen_hypercall_name"); } diff --git a/tools/memory-model/Documentation/explanation.txt b/tools/memory-model/Documentation/explanation.txt index 35bff92cc773..68caa9a976d0 100644 --- a/tools/memory-model/Documentation/explanation.txt +++ b/tools/memory-model/Documentation/explanation.txt @@ -27,7 +27,7 @@ Explanation of the Linux-Kernel Memory Consistency Model 19. AND THEN THERE WAS ALPHA 20. THE HAPPENS-BEFORE RELATION: hb 21. THE PROPAGATES-BEFORE RELATION: pb - 22. RCU RELATIONS: rcu-link, gp, rscs, rcu-fence, and rb + 22. RCU RELATIONS: rcu-link, rcu-gp, rcu-rscsi, rcu-fence, and rb 23. LOCKING 24. ODDS AND ENDS @@ -1430,8 +1430,8 @@ they execute means that it cannot have cycles. This requirement is the content of the LKMM's "propagation" axiom. -RCU RELATIONS: rcu-link, gp, rscs, rcu-fence, and rb ----------------------------------------------------- +RCU RELATIONS: rcu-link, rcu-gp, rcu-rscsi, rcu-fence, and rb +------------------------------------------------------------- RCU (Read-Copy-Update) is a powerful synchronization mechanism. It rests on two concepts: grace periods and read-side critical sections. @@ -1446,17 +1446,19 @@ As far as memory models are concerned, RCU's main feature is its Grace-Period Guarantee, which states that a critical section can never span a full grace period. In more detail, the Guarantee says: - If a critical section starts before a grace period then it - must end before the grace period does. In addition, every - store that propagates to the critical section's CPU before the - end of the critical section must propagate to every CPU before - the end of the grace period. + For any critical section C and any grace period G, at least + one of the following statements must hold: - If a critical section ends after a grace period ends then it - must start after the grace period does. In addition, every - store that propagates to the grace period's CPU before the - start of the grace period must propagate to every CPU before - the start of the critical section. +(1) C ends before G does, and in addition, every store that + propagates to C's CPU before the end of C must propagate to + every CPU before G ends. + +(2) G starts before C does, and in addition, every store that + propagates to G's CPU before the start of G must propagate + to every CPU before C starts. + +In particular, it is not possible for a critical section to both start +before and end after a grace period. Here is a simple example of RCU in action: @@ -1483,10 +1485,11 @@ The Grace Period Guarantee tells us that when this code runs, it will never end with r1 = 1 and r2 = 0. The reasoning is as follows. r1 = 1 means that P0's store to x propagated to P1 before P1 called synchronize_rcu(), so P0's critical section must have started before -P1's grace period. On the other hand, r2 = 0 means that P0's store to -y, which occurs before the end of the critical section, did not -propagate to P1 before the end of the grace period, violating the -Guarantee. +P1's grace period, contrary to part (2) of the Guarantee. On the +other hand, r2 = 0 means that P0's store to y, which occurs before the +end of the critical section, did not propagate to P1 before the end of +the grace period, contrary to part (1). Together the results violate +the Guarantee. In the kernel's implementations of RCU, the requirements for stores to propagate to every CPU are fulfilled by placing strong fences at @@ -1504,11 +1507,11 @@ before" or "ends after" a grace period? Some aspects of the meaning are pretty obvious, as in the example above, but the details aren't entirely clear. The LKMM formalizes this notion by means of the rcu-link relation. rcu-link encompasses a very general notion of -"before": Among other things, X ->rcu-link Z includes cases where X -happens-before or is equal to some event Y which is equal to or comes -before Z in the coherence order. When Y = Z this says that X ->rfe Z -implies X ->rcu-link Z. In addition, when Y = X it says that X ->fr Z -and X ->co Z each imply X ->rcu-link Z. +"before": If E and F are RCU fence events (i.e., rcu_read_lock(), +rcu_read_unlock(), or synchronize_rcu()) then among other things, +E ->rcu-link F includes cases where E is po-before some memory-access +event X, F is po-after some memory-access event Y, and we have any of +X ->rfe Y, X ->co Y, or X ->fr Y. The formal definition of the rcu-link relation is more than a little obscure, and we won't give it here. It is closely related to the pb @@ -1516,171 +1519,173 @@ relation, and the details don't matter unless you want to comb through a somewhat lengthy formal proof. Pretty much all you need to know about rcu-link is the information in the preceding paragraph. -The LKMM also defines the gp and rscs relations. They bring grace -periods and read-side critical sections into the picture, in the +The LKMM also defines the rcu-gp and rcu-rscsi relations. They bring +grace periods and read-side critical sections into the picture, in the following way: - E ->gp F means there is a synchronize_rcu() fence event S such - that E ->po S and either S ->po F or S = F. In simple terms, - there is a grace period po-between E and F. + E ->rcu-gp F means that E and F are in fact the same event, + and that event is a synchronize_rcu() fence (i.e., a grace + period). - E ->rscs F means there is a critical section delimited by an - rcu_read_lock() fence L and an rcu_read_unlock() fence U, such - that E ->po U and either L ->po F or L = F. You can think of - this as saying that E and F are in the same critical section - (in fact, it also allows E to be po-before the start of the - critical section and F to be po-after the end). + E ->rcu-rscsi F means that E and F are the rcu_read_unlock() + and rcu_read_lock() fence events delimiting some read-side + critical section. (The 'i' at the end of the name emphasizes + that this relation is "inverted": It links the end of the + critical section to the start.) If we think of the rcu-link relation as standing for an extended -"before", then X ->gp Y ->rcu-link Z says that X executes before a -grace period which ends before Z executes. (In fact it covers more -than this, because it also includes cases where X executes before a -grace period and some store propagates to Z's CPU before Z executes -but doesn't propagate to some other CPU until after the grace period -ends.) Similarly, X ->rscs Y ->rcu-link Z says that X is part of (or -before the start of) a critical section which starts before Z -executes. - -The LKMM goes on to define the rcu-fence relation as a sequence of gp -and rscs links separated by rcu-link links, in which the number of gp -links is >= the number of rscs links. For example: +"before", then X ->rcu-gp Y ->rcu-link Z roughly says that X is a +grace period which ends before Z begins. (In fact it covers more than +this, because it also includes cases where some store propagates to +Z's CPU before Z begins but doesn't propagate to some other CPU until +after X ends.) Similarly, X ->rcu-rscsi Y ->rcu-link Z says that X is +the end of a critical section which starts before Z begins. + +The LKMM goes on to define the rcu-fence relation as a sequence of +rcu-gp and rcu-rscsi links separated by rcu-link links, in which the +number of rcu-gp links is >= the number of rcu-rscsi links. For +example: - X ->gp Y ->rcu-link Z ->rscs T ->rcu-link U ->gp V + X ->rcu-gp Y ->rcu-link Z ->rcu-rscsi T ->rcu-link U ->rcu-gp V would imply that X ->rcu-fence V, because this sequence contains two -gp links and only one rscs link. (It also implies that X ->rcu-fence T -and Z ->rcu-fence V.) On the other hand: +rcu-gp links and one rcu-rscsi link. (It also implies that +X ->rcu-fence T and Z ->rcu-fence V.) On the other hand: - X ->rscs Y ->rcu-link Z ->rscs T ->rcu-link U ->gp V + X ->rcu-rscsi Y ->rcu-link Z ->rcu-rscsi T ->rcu-link U ->rcu-gp V does not imply X ->rcu-fence V, because the sequence contains only -one gp link but two rscs links. +one rcu-gp link but two rcu-rscsi links. The rcu-fence relation is important because the Grace Period Guarantee means that rcu-fence acts kind of like a strong fence. In particular, -if W is a write and we have W ->rcu-fence Z, the Guarantee says that W -will propagate to every CPU before Z executes. +E ->rcu-fence F implies not only that E begins before F ends, but also +that any write po-before E will propagate to every CPU before any +instruction po-after F can execute. (However, it does not imply that +E must execute before F; in fact, each synchronize_rcu() fence event +is linked to itself by rcu-fence as a degenerate case.) To prove this in full generality requires some intellectual effort. We'll consider just a very simple case: - W ->gp X ->rcu-link Y ->rscs Z. + G ->rcu-gp W ->rcu-link Z ->rcu-rscsi F. -This formula means that there is a grace period G and a critical -section C such that: +This formula means that G and W are the same event (a grace period), +and there are events X, Y and a read-side critical section C such that: - 1. W is po-before G; + 1. G = W is po-before or equal to X; - 2. X is equal to or po-after G; + 2. X comes "before" Y in some sense (including rfe, co and fr); - 3. X comes "before" Y in some sense; + 2. Y is po-before Z; - 4. Y is po-before the end of C; + 4. Z is the rcu_read_unlock() event marking the end of C; - 5. Z is equal to or po-after the start of C. + 5. F is the rcu_read_lock() event marking the start of C. -From 2 - 4 we deduce that the grace period G ends before the critical -section C. Then the second part of the Grace Period Guarantee says -not only that G starts before C does, but also that W (which executes -on G's CPU before G starts) must propagate to every CPU before C -starts. In particular, W propagates to every CPU before Z executes -(or finishes executing, in the case where Z is equal to the -rcu_read_lock() fence event which starts C.) This sort of reasoning -can be expanded to handle all the situations covered by rcu-fence. +From 1 - 4 we deduce that the grace period G ends before the critical +section C. Then part (2) of the Grace Period Guarantee says not only +that G starts before C does, but also that any write which executes on +G's CPU before G starts must propagate to every CPU before C starts. +In particular, the write propagates to every CPU before F finishes +executing and hence before any instruction po-after F can execute. +This sort of reasoning can be extended to handle all the situations +covered by rcu-fence. Finally, the LKMM defines the RCU-before (rb) relation in terms of rcu-fence. This is done in essentially the same way as the pb relation was defined in terms of strong-fence. We will omit the -details; the end result is that E ->rb F implies E must execute before -F, just as E ->pb F does (and for much the same reasons). +details; the end result is that E ->rb F implies E must execute +before F, just as E ->pb F does (and for much the same reasons). Putting this all together, the LKMM expresses the Grace Period Guarantee by requiring that the rb relation does not contain a cycle. -Equivalently, this "rcu" axiom requires that there are no events E and -F with E ->rcu-link F ->rcu-fence E. Or to put it a third way, the -axiom requires that there are no cycles consisting of gp and rscs -alternating with rcu-link, where the number of gp links is >= the -number of rscs links. +Equivalently, this "rcu" axiom requires that there are no events E +and F with E ->rcu-link F ->rcu-fence E. Or to put it a third way, +the axiom requires that there are no cycles consisting of rcu-gp and +rcu-rscsi alternating with rcu-link, where the number of rcu-gp links +is >= the number of rcu-rscsi links. Justifying the axiom isn't easy, but it is in fact a valid formalization of the Grace Period Guarantee. We won't attempt to go through the detailed argument, but the following analysis gives a -taste of what is involved. Suppose we have a violation of the first -part of the Guarantee: A critical section starts before a grace -period, and some store propagates to the critical section's CPU before -the end of the critical section but doesn't propagate to some other -CPU until after the end of the grace period. +taste of what is involved. Suppose both parts of the Guarantee are +violated: A critical section starts before a grace period, and some +store propagates to the critical section's CPU before the end of the +critical section but doesn't propagate to some other CPU until after +the end of the grace period. Putting symbols to these ideas, let L and U be the rcu_read_lock() and rcu_read_unlock() fence events delimiting the critical section in question, and let S be the synchronize_rcu() fence event for the grace period. Saying that the critical section starts before S means there -are events E and F where E is po-after L (which marks the start of the -critical section), E is "before" F in the sense of the rcu-link -relation, and F is po-before the grace period S: +are events Q and R where Q is po-after L (which marks the start of the +critical section), Q is "before" R in the sense used by the rcu-link +relation, and R is po-before the grace period S. Thus we have: - L ->po E ->rcu-link F ->po S. + L ->rcu-link S. -Let W be the store mentioned above, let Z come before the end of the +Let W be the store mentioned above, let Y come before the end of the critical section and witness that W propagates to the critical -section's CPU by reading from W, and let Y on some arbitrary CPU be a -witness that W has not propagated to that CPU, where Y happens after +section's CPU by reading from W, and let Z on some arbitrary CPU be a +witness that W has not propagated to that CPU, where Z happens after some event X which is po-after S. Symbolically, this amounts to: - S ->po X ->hb* Y ->fr W ->rf Z ->po U. + S ->po X ->hb* Z ->fr W ->rf Y ->po U. -The fr link from Y to W indicates that W has not propagated to Y's CPU -at the time that Y executes. From this, it can be shown (see the -discussion of the rcu-link relation earlier) that X and Z are related -by rcu-link, yielding: +The fr link from Z to W indicates that W has not propagated to Z's CPU +at the time that Z executes. From this, it can be shown (see the +discussion of the rcu-link relation earlier) that S and U are related +by rcu-link: - S ->po X ->rcu-link Z ->po U. + S ->rcu-link U. -The formulas say that S is po-between F and X, hence F ->gp X. They -also say that Z comes before the end of the critical section and E -comes after its start, hence Z ->rscs E. From all this we obtain: +Since S is a grace period we have S ->rcu-gp S, and since L and U are +the start and end of the critical section C we have U ->rcu-rscsi L. +From this we obtain: - F ->gp X ->rcu-link Z ->rscs E ->rcu-link F, + S ->rcu-gp S ->rcu-link U ->rcu-rscsi L ->rcu-link S, a forbidden cycle. Thus the "rcu" axiom rules out this violation of the Grace Period Guarantee. For something a little more down-to-earth, let's see how the axiom works out in practice. Consider the RCU code example from above, this -time with statement labels added to the memory access instructions: +time with statement labels added: int x, y; P0() { - rcu_read_lock(); - W: WRITE_ONCE(x, 1); - X: WRITE_ONCE(y, 1); - rcu_read_unlock(); + L: rcu_read_lock(); + X: WRITE_ONCE(x, 1); + Y: WRITE_ONCE(y, 1); + U: rcu_read_unlock(); } P1() { int r1, r2; - Y: r1 = READ_ONCE(x); - synchronize_rcu(); - Z: r2 = READ_ONCE(y); + Z: r1 = READ_ONCE(x); + S: synchronize_rcu(); + W: r2 = READ_ONCE(y); } -If r2 = 0 at the end then P0's store at X overwrites the value that -P1's load at Z reads from, so we have Z ->fre X and thus Z ->rcu-link X. -In addition, there is a synchronize_rcu() between Y and Z, so therefore -we have Y ->gp Z. +If r2 = 0 at the end then P0's store at Y overwrites the value that +P1's load at W reads from, so we have W ->fre Y. Since S ->po W and +also Y ->po U, we get S ->rcu-link U. In addition, S ->rcu-gp S +because S is a grace period. -If r1 = 1 at the end then P1's load at Y reads from P0's store at W, -so we have W ->rcu-link Y. In addition, W and X are in the same critical -section, so therefore we have X ->rscs W. +If r1 = 1 at the end then P1's load at Z reads from P0's store at X, +so we have X ->rfe Z. Together with L ->po X and Z ->po S, this +yields L ->rcu-link S. And since L and U are the start and end of a +critical section, we have U ->rcu-rscsi L. -Then X ->rscs W ->rcu-link Y ->gp Z ->rcu-link X is a forbidden cycle, -violating the "rcu" axiom. Hence the outcome is not allowed by the -LKMM, as we would expect. +Then U ->rcu-rscsi L ->rcu-link S ->rcu-gp S ->rcu-link U is a +forbidden cycle, violating the "rcu" axiom. Hence the outcome is not +allowed by the LKMM, as we would expect. For contrast, let's see what can happen in a more complicated example: @@ -1690,51 +1695,52 @@ For contrast, let's see what can happen in a more complicated example: { int r0; - rcu_read_lock(); - W: r0 = READ_ONCE(x); - X: WRITE_ONCE(y, 1); - rcu_read_unlock(); + L0: rcu_read_lock(); + r0 = READ_ONCE(x); + WRITE_ONCE(y, 1); + U0: rcu_read_unlock(); } P1() { int r1; - Y: r1 = READ_ONCE(y); - synchronize_rcu(); - Z: WRITE_ONCE(z, 1); + r1 = READ_ONCE(y); + S1: synchronize_rcu(); + WRITE_ONCE(z, 1); } P2() { int r2; - rcu_read_lock(); - U: r2 = READ_ONCE(z); - V: WRITE_ONCE(x, 1); - rcu_read_unlock(); + L2: rcu_read_lock(); + r2 = READ_ONCE(z); + WRITE_ONCE(x, 1); + U2: rcu_read_unlock(); } If r0 = r1 = r2 = 1 at the end, then similar reasoning to before shows -that W ->rscs X ->rcu-link Y ->gp Z ->rcu-link U ->rscs V ->rcu-link W. -However this cycle is not |