diff options
Diffstat (limited to 'tools/testing/selftests/bpf/progs')
50 files changed, 2948 insertions, 254 deletions
diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c index 81ad9a0b29d0..849f42e548b5 100644 --- a/tools/testing/selftests/bpf/progs/bpf_flow.c +++ b/tools/testing/selftests/bpf/progs/bpf_flow.c @@ -57,17 +57,25 @@ struct frag_hdr { __be32 identification; }; -struct bpf_map_def SEC("maps") jmp_table = { +struct { + __u32 type; + __u32 max_entries; + __u32 key_size; + __u32 value_size; +} jmp_table SEC(".maps") = { .type = BPF_MAP_TYPE_PROG_ARRAY, + .max_entries = 8, .key_size = sizeof(__u32), .value_size = sizeof(__u32), - .max_entries = 8 }; -struct bpf_map_def SEC("maps") last_dissection = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct bpf_flow_keys *value; +} last_dissection SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct bpf_flow_keys), .max_entries = 1, }; diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c new file mode 100644 index 000000000000..8f44767a75fa --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c @@ -0,0 +1,92 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * BTF-to-C dumper tests for bitfield. + * + * Copyright (c) 2019 Facebook + */ +#include <stdbool.h> + +/* ----- START-EXPECTED-OUTPUT ----- */ +/* + *struct bitfields_only_mixed_types { + * int a: 3; + * long int b: 2; + * _Bool c: 1; + * enum { + * A = 0, + * B = 1, + * } d: 1; + * short e: 5; + * int: 20; + * unsigned int f: 30; + *}; + * + */ +/* ------ END-EXPECTED-OUTPUT ------ */ + +struct bitfields_only_mixed_types { + int a: 3; + long int b: 2; + bool c: 1; /* it's really a _Bool type */ + enum { + A, /* A = 0, dumper is very explicit */ + B, /* B = 1, same */ + } d: 1; + short e: 5; + /* 20-bit padding here */ + unsigned f: 30; /* this gets aligned on 4-byte boundary */ +}; + +/* ----- START-EXPECTED-OUTPUT ----- */ +/* + *struct bitfield_mixed_with_others { + * char: 4; + * int a: 4; + * short b; + * long int c; + * long int d: 8; + * int e; + * int f; + *}; + * + */ +/* ------ END-EXPECTED-OUTPUT ------ */ +struct bitfield_mixed_with_others { + long: 4; /* char is enough as a backing field */ + int a: 4; + /* 8-bit implicit padding */ + short b; /* combined with previous bitfield */ + /* 4 more bytes of implicit padding */ + long c; + long d: 8; + /* 24 bits implicit padding */ + int e; /* combined with previous bitfield */ + int f; + /* 4 bytes of padding */ +}; + +/* ----- START-EXPECTED-OUTPUT ----- */ +/* + *struct bitfield_flushed { + * int a: 4; + * long: 60; + * long int b: 16; + *}; + * + */ +/* ------ END-EXPECTED-OUTPUT ------ */ +struct bitfield_flushed { + int a: 4; + long: 0; /* flush until next natural alignment boundary */ + long b: 16; +}; + +int f(struct { + struct bitfields_only_mixed_types _1; + struct bitfield_mixed_with_others _2; + struct bitfield_flushed _3; +} *_) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_multidim.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_multidim.c new file mode 100644 index 000000000000..ba97165bdb28 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_multidim.c @@ -0,0 +1,35 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * BTF-to-C dumper test for multi-dimensional array output. + * + * Copyright (c) 2019 Facebook + */ +/* ----- START-EXPECTED-OUTPUT ----- */ +typedef int arr_t[2]; + +typedef int multiarr_t[3][4][5]; + +typedef int *ptr_arr_t[6]; + +typedef int *ptr_multiarr_t[7][8][9][10]; + +typedef int * (*fn_ptr_arr_t[11])(); + +typedef int * (*fn_ptr_multiarr_t[12][13])(); + +struct root_struct { + arr_t _1; + multiarr_t _2; + ptr_arr_t _3; + ptr_multiarr_t _4; + fn_ptr_arr_t _5; + fn_ptr_multiarr_t _6; +}; + +/* ------ END-EXPECTED-OUTPUT ------ */ + +int f(struct root_struct *s) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_namespacing.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_namespacing.c new file mode 100644 index 000000000000..92a4ad428710 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_namespacing.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * BTF-to-C dumper test validating no name versioning happens between + * independent C namespaces (struct/union/enum vs typedef/enum values). + * + * Copyright (c) 2019 Facebook + */ +/* ----- START-EXPECTED-OUTPUT ----- */ +struct S { + int S; + int U; +}; + +typedef struct S S; + +union U { + int S; + int U; +}; + +typedef union U U; + +enum E { + V = 0, +}; + +typedef enum E E; + +struct A {}; + +union B {}; + +enum C { + A = 1, + B = 2, + C = 3, +}; + +struct X {}; + +union Y {}; + +enum Z; + +typedef int X; + +typedef int Y; + +typedef int Z; + +/*------ END-EXPECTED-OUTPUT ------ */ + +int f(struct { + struct S _1; + S _2; + union U _3; + U _4; + enum E _5; + E _6; + struct A a; + union B b; + enum C c; + struct X x; + union Y y; + enum Z *z; + X xx; + Y yy; + Z zz; +} *_) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_ordering.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_ordering.c new file mode 100644 index 000000000000..7c95702ee4cb --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_ordering.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * BTF-to-C dumper test for topological sorting of dependent structs. + * + * Copyright (c) 2019 Facebook + */ +/* ----- START-EXPECTED-OUTPUT ----- */ +struct s1 {}; + +struct s3; + +struct s4; + +struct s2 { + struct s2 *s2; + struct s3 *s3; + struct s4 *s4; +}; + +struct s3 { + struct s1 s1; + struct s2 s2; +}; + +struct s4 { + struct s1 s1; + struct s3 s3; +}; + +struct list_head { + struct list_head *next; + struct list_head *prev; +}; + +struct hlist_node { + struct hlist_node *next; + struct hlist_node **pprev; +}; + +struct hlist_head { + struct hlist_node *first; +}; + +struct callback_head { + struct callback_head *next; + void (*func)(struct callback_head *); +}; + +struct root_struct { + struct s4 s4; + struct list_head l; + struct hlist_node n; + struct hlist_head h; + struct callback_head cb; +}; + +/*------ END-EXPECTED-OUTPUT ------ */ + +int f(struct root_struct *root) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c new file mode 100644 index 000000000000..1cef3bec1dc7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c @@ -0,0 +1,75 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * BTF-to-C dumper tests for struct packing determination. + * + * Copyright (c) 2019 Facebook + */ +/* ----- START-EXPECTED-OUTPUT ----- */ +struct packed_trailing_space { + int a; + short b; +} __attribute__((packed)); + +struct non_packed_trailing_space { + int a; + short b; +}; + +struct packed_fields { + short a; + int b; +} __attribute__((packed)); + +struct non_packed_fields { + short a; + int b; +}; + +struct nested_packed { + char: 4; + int a: 4; + long int b; + struct { + char c; + int d; + } __attribute__((packed)) e; +} __attribute__((packed)); + +union union_is_never_packed { + int a: 4; + char b; + char c: 1; +}; + +union union_does_not_need_packing { + struct { + long int a; + int b; + } __attribute__((packed)); + int c; +}; + +union jump_code_union { + char code[5]; + struct { + char jump; + int offset; + } __attribute__((packed)); +}; + +/*------ END-EXPECTED-OUTPUT ------ */ + +int f(struct { + struct packed_trailing_space _1; + struct non_packed_trailing_space _2; + struct packed_fields _3; + struct non_packed_fields _4; + struct nested_packed _5; + union union_is_never_packed _6; + union union_does_not_need_packing _7; + union jump_code_union _8; +} *_) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c new file mode 100644 index 000000000000..3a62119c7498 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c @@ -0,0 +1,111 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * BTF-to-C dumper tests for implicit and explicit padding between fields and + * at the end of a struct. + * + * Copyright (c) 2019 Facebook + */ +/* ----- START-EXPECTED-OUTPUT ----- */ +struct padded_implicitly { + int a; + long int b; + char c; +}; + +/* ------ END-EXPECTED-OUTPUT ------ */ + +/* ----- START-EXPECTED-OUTPUT ----- */ +/* + *struct padded_explicitly { + * int a; + * int: 32; + * int b; + *}; + * + */ +/* ------ END-EXPECTED-OUTPUT ------ */ + +struct padded_explicitly { + int a; + int: 1; /* algo will explicitly pad with full 32 bits here */ + int b; +}; + +/* ----- START-EXPECTED-OUTPUT ----- */ +/* + *struct padded_a_lot { + * int a; + * long: 32; + * long: 64; + * long: 64; + * int b; + *}; + * + */ +/* ------ END-EXPECTED-OUTPUT ------ */ + +struct padded_a_lot { + int a; + /* 32 bit of implicit padding here, which algo will make explicit */ + long: 64; + long: 64; + int b; +}; + +/* ----- START-EXPECTED-OUTPUT ----- */ +/* + *struct padded_cache_line { + * int a; + * long: 32; + * long: 64; + * long: 64; + * long: 64; + * int b; + *}; + * + */ +/* ------ END-EXPECTED-OUTPUT ------ */ + +struct padded_cache_line { + int a; + int b __attribute__((aligned(32))); +}; + +/* ----- START-EXPECTED-OUTPUT ----- */ +/* + *struct zone_padding { + * char x[0]; + *}; + * + *struct zone { + * int a; + * short b; + * short: 16; + * struct zone_padding __pad__; + *}; + * + */ +/* ------ END-EXPECTED-OUTPUT ------ */ + +struct zone_padding { + char x[0]; +} __attribute__((__aligned__(8))); + +struct zone { + int a; + short b; + short: 16; + struct zone_padding __pad__; +}; + +int f(struct { + struct padded_implicitly _1; + struct padded_explicitly _2; + struct padded_a_lot _3; + struct padded_cache_line _4; + struct zone _5; +} *_) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c new file mode 100644 index 000000000000..d4a02fe44a12 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c @@ -0,0 +1,229 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * BTF-to-C dumper test for majority of C syntax quirks. + * + * Copyright (c) 2019 Facebook + */ +/* ----- START-EXPECTED-OUTPUT ----- */ +enum e1 { + A = 0, + B = 1, +}; + +enum e2 { + C = 100, + D = -100, + E = 0, +}; + +typedef enum e2 e2_t; + +typedef enum { + F = 0, + G = 1, + H = 2, +} e3_t; + +typedef int int_t; + +typedef volatile const int * volatile const crazy_ptr_t; + +typedef int *****we_need_to_go_deeper_ptr_t; + +typedef volatile const we_need_to_go_deeper_ptr_t * restrict * volatile * const * restrict volatile * restrict const * volatile const * restrict volatile const how_about_this_ptr_t; + +typedef int *ptr_arr_t[10]; + +typedef void (*fn_ptr1_t)(int); + +typedef void (*printf_fn_t)(const char *, ...); + +/* ------ END-EXPECTED-OUTPUT ------ */ +/* + * While previous function pointers are pretty trivial (C-syntax-level + * trivial), the following are deciphered here for future generations: + * + * - `fn_ptr2_t`: function, taking anonymous struct as a first arg and pointer + * to a function, that takes int and returns int, as a second arg; returning + * a pointer to a const pointer to a char. Equivalent to: + * typedef struct { int a; } s_t; + * typedef int (*fn_t)(int); + * typedef char * const * (*fn_ptr2_t)(s_t, fn_t); + * + * - `fn_complext_t`: pointer to a function returning struct and accepting + * union and struct. All structs and enum are anonymous and defined inline. + * + * - `signal_t: pointer to a function accepting a pointer to a function as an + * argument and returning pointer to a function as a result. Sane equivalent: + * typedef void (*signal_handler_t)(int); + * typedef signal_handler_t (*signal_ptr_t)(int, signal_handler_t); + * + * - fn_ptr_arr1_t: array of pointers to a function accepting pointer to + * a pointer to an int and returning pointer to a char. Easy. + * + * - fn_ptr_arr2_t: array of const pointers to a function taking no arguments + * and returning a const pointer to a function, that takes pointer to a + * `int -> char *` function and returns pointer to a char. Equivalent: + * typedef char * (*fn_input_t)(int); + * typedef char * (*fn_output_outer_t)(fn_input_t); + * typedef const fn_output_outer_t (* fn_output_inner_t)(); + * typedef const fn_output_inner_t fn_ptr_arr2_t[5]; + */ +/* ----- START-EXPECTED-OUTPUT ----- */ +typedef char * const * (*fn_ptr2_t)(struct { + int a; +}, int (*)(int)); + +typedef struct { + int a; + void (*b)(int, struct { + int c; + }, union { + char d; + int e[5]; + }); +} (*fn_complex_t)(union { + void *f; + char g[16]; +}, struct { + int h; +}); + +typedef void (* (*signal_t)(int, void (*)(int)))(int); + +typedef char * (*fn_ptr_arr1_t[10])(int **); + +typedef char * (* const (* const fn_ptr_arr2_t[5])())(char * (*)(int)); + +struct struct_w_typedefs { + int_t a; + crazy_ptr_t b; + we_need_to_go_deeper_ptr_t c; + how_about_this_ptr_t d; + ptr_arr_t e; + fn_ptr1_t f; + printf_fn_t g; + fn_ptr2_t h; + fn_complex_t i; + signal_t j; + fn_ptr_arr1_t k; + fn_ptr_arr2_t l; +}; + +typedef struct { + int x; + int y; + int z; +} anon_struct_t; + +struct struct_fwd; + +typedef struct struct_fwd struct_fwd_t; + +typedef struct struct_fwd *struct_fwd_ptr_t; + +union union_fwd; + +typedef union union_fwd union_fwd_t; + +typedef union union_fwd *union_fwd_ptr_t; + +struct struct_empty {}; + +struct struct_simple { + int a; + char b; + const int_t *p; + struct struct_empty s; + enum e2 e; + enum { + ANON_VAL1 = 1, + ANON_VAL2 = 2, + } f; + int arr1[13]; + enum e2 arr2[5]; +}; + +union union_empty {}; + +union union_simple { + void *ptr; + int num; + int_t num2; + union union_empty u; +}; + +struct struct_in_struct { + struct struct_simple simple; + union union_simple also_simple; + struct { + int a; + } not_so_hard_as_well; + union { + int b; + int c; + } anon_union_is_good; + struct { + int d; + int e; + }; + union { + int f; + int g; + }; +}; + +struct struct_with_embedded_stuff { + int a; + struct { + int b; + struct { + struct struct_with_embedded_stuff *c; + const char *d; + } e; + union { + volatile long int f; + void * restrict g; + }; + }; + union { + const int_t *h; + void (*i)(char, int, void *); + } j; + enum { + K = 100, + L = 200, + } m; + char n[16]; + struct { + char o; + int p; + void (*q)(int); + } r[5]; + struct struct_in_struct s[10]; + int t[11]; +}; + +struct root_struct { + enum e1 _1; + enum e2 _2; + e2_t _2_1; + e3_t _2_2; + struct struct_w_typedefs _3; + anon_struct_t _7; + struct struct_fwd *_8; + struct_fwd_t *_9; + struct_fwd_ptr_t _10; + union union_fwd *_11; + union_fwd_t *_12; + union_fwd_ptr_t _13; + struct struct_with_embedded_stuff _14; +}; + +/* ------ END-EXPECTED-OUTPUT ------ */ + +int f(struct root_struct *s) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/loop1.c b/tools/testing/selftests/bpf/progs/loop1.c new file mode 100644 index 000000000000..dea395af9ea9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/loop1.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/sched.h> +#include <linux/ptrace.h> +#include <stdint.h> +#include <stddef.h> +#include <stdbool.h> +#include <linux/bpf.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +SEC("raw_tracepoint/kfree_skb") +int nested_loops(volatile struct pt_regs* ctx) +{ + int i, j, sum = 0, m; + + for (j = 0; j < 300; j++) + for (i = 0; i < j; i++) { + if (j & 1) + m = ctx->rax; + else + m = j; + sum += i * m; + } + + return sum; +} diff --git a/tools/testing/selftests/bpf/progs/loop2.c b/tools/testing/selftests/bpf/progs/loop2.c new file mode 100644 index 000000000000..0637bd8e8bcf --- /dev/null +++ b/tools/testing/selftests/bpf/progs/loop2.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/sched.h> +#include <linux/ptrace.h> +#include <stdint.h> +#include <stddef.h> +#include <stdbool.h> +#include <linux/bpf.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +SEC("raw_tracepoint/consume_skb") +int while_true(volatile struct pt_regs* ctx) +{ + int i = 0; + + while (true) { + if (ctx->rax & 1) + i += 3; + else + i += 7; + if (i > 40) + break; + } + + return i; +} diff --git a/tools/testing/selftests/bpf/progs/loop3.c b/tools/testing/selftests/bpf/progs/loop3.c new file mode 100644 index 000000000000..30a0f6cba080 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/loop3.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/sched.h> +#include <linux/ptrace.h> +#include <stdint.h> +#include <stddef.h> +#include <stdbool.h> +#include <linux/bpf.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +SEC("raw_tracepoint/consume_skb") +int while_true(volatile struct pt_regs* ctx) +{ + __u64 i = 0, sum = 0; + do { + i++; + sum += ctx->rax; + } while (i < 0x100000000ULL); + return sum; +} diff --git a/tools/testing/selftests/bpf/progs/netcnt_prog.c b/tools/testing/selftests/bpf/progs/netcnt_prog.c index 9f741e69cebe..a25c82a5b7c8 100644 --- a/tools/testing/selftests/bpf/progs/netcnt_prog.c +++ b/tools/testing/selftests/bpf/progs/netcnt_prog.c @@ -10,24 +10,22 @@ #define REFRESH_TIME_NS 100000000 #define NS_PER_SEC 1000000000 -struct bpf_map_def SEC("maps") percpu_netcnt = { +struct { + __u32 type; + struct bpf_cgroup_storage_key *key; + struct percpu_net_cnt *value; +} percpu_netcnt SEC(".maps") = { .type = BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, - .key_size = sizeof(struct bpf_cgroup_storage_key), - .value_size = sizeof(struct percpu_net_cnt), }; -BPF_ANNOTATE_KV_PAIR(percpu_netcnt, struct bpf_cgroup_storage_key, - struct percpu_net_cnt); - -struct bpf_map_def SEC("maps") netcnt = { +struct { + __u32 type; + struct bpf_cgroup_storage_key *key; + struct net_cnt *value; +} netcnt SEC(".maps") = { .type = BPF_MAP_TYPE_CGROUP_STORAGE, - .key_size = sizeof(struct bpf_cgroup_storage_key), - .value_size = sizeof(struct net_cnt), }; -BPF_ANNOTATE_KV_PAIR(netcnt, struct bpf_cgroup_storage_key, - struct net_cnt); - SEC("cgroup/skb") int bpf_nextcnt(struct __sk_buff *skb) { diff --git a/tools/testing/selftests/bpf/progs/pyperf.h b/tools/testing/selftests/bpf/progs/pyperf.h new file mode 100644 index 000000000000..6b0781391be5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/pyperf.h @@ -0,0 +1,272 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/sched.h> +#include <linux/ptrace.h> +#include <stdint.h> +#include <stddef.h> +#include <stdbool.h> +#include <linux/bpf.h> +#include "bpf_helpers.h" + +#define FUNCTION_NAME_LEN 64 +#define FILE_NAME_LEN 128 +#define TASK_COMM_LEN 16 + +typedef struct { + int PyThreadState_frame; + int PyThreadState_thread; + int PyFrameObject_back; + int PyFrameObject_code; + int PyFrameObject_lineno; + int PyCodeObject_filename; + int PyCodeObject_name; + int String_data; + int String_size; +} OffsetConfig; + +typedef struct { + uintptr_t current_state_addr; + uintptr_t tls_key_addr; + OffsetConfig offsets; + bool use_tls; +} PidData; + +typedef struct { + uint32_t success; +} Stats; + +typedef struct { + char name[FUNCTION_NAME_LEN]; + char file[FILE_NAME_LEN]; +} Symbol; + +typedef struct { + uint32_t pid; + uint32_t tid; + char comm[TASK_COMM_LEN]; + int32_t kernel_stack_id; + int32_t user_stack_id; + bool thread_current; + bool pthread_match; + bool stack_complete; + int16_t stack_len; + int32_t stack[STACK_MAX_LEN]; + + int has_meta; + int metadata; + char dummy_safeguard; +} Event; + + +struct bpf_elf_map { + __u32 type; + __u32 size_key; + __u32 size_value; + __u32 max_elem; + __u32 flags; +}; + +typedef int pid_t; + +typedef struct { + void* f_back; // PyFrameObject.f_back, previous frame + void* f_code; // PyFrameObject.f_code, pointer to PyCodeObject + void* co_filename; // PyCodeObject.co_filename + void* co_name; // PyCodeObject.co_name +} FrameData; + +static inline __attribute__((__always_inline__)) void* +get_thread_state(void* tls_base, PidData* pidData) +{ + void* thread_state; + int key; + + bpf_probe_read(&key, sizeof(key), (void*)(long)pidData->tls_key_addr); + bpf_probe_read(&thread_state, sizeof(thread_state), + tls_base + 0x310 + key * 0x10 + 0x08); + return thread_state; +} + +static inline __attribute__((__always_inline__)) bool +get_frame_data(void* frame_ptr, PidData* pidData, FrameData* frame, Symbol* symbol) +{ + // read data from PyFrameObject + bpf_probe_read(&frame->f_back, + sizeof(frame->f_back), + frame_ptr + pidData->offsets.PyFrameObject_back); + bpf_probe_read(&frame->f_code, + sizeof(frame->f_code), + frame_ptr + pidData->offsets.PyFrameObject_code); + + // read data from PyCodeObject + if (!frame->f_code) + return false; + bpf_probe_read(&frame->co_filename, + sizeof(frame->co_filename), + frame->f_code + pidData->offsets.PyCodeObject_filename); + bpf_probe_read(&frame->co_name, + sizeof(frame->co_name), + frame->f_code + pidData->offsets.PyCodeObject_name); + // read actual names into symbol + if (frame->co_filename) + bpf_probe_read_str(&symbol->file, + sizeof(symbol->file), + frame->co_filename + pidData->offsets.String_data); + if (frame->co_name) + bpf_probe_read_str(&symbol->name, + sizeof(symbol->name), + frame->co_name + pidData->offsets.String_data); + return true; +} + +struct bpf_elf_map SEC("maps") pidmap = { + .type = BPF_MAP_TYPE_HASH, + .size_key = sizeof(int), + .size_value = sizeof(PidData), + .max_elem = 1, +}; + +struct bpf_elf_map SEC("maps") eventmap = { + .type = BPF_MAP_TYPE_HASH, + .size_key = sizeof(int), + .size_value = sizeof(Event), + .max_elem = 1, +}; + +struct bpf_elf_map SEC("maps") symbolmap = { + .type = BPF_MAP_TYPE_HASH, + .size_key = sizeof(Symbol), + .size_value = sizeof(int), + .max_elem = 1, +}; + +struct bpf_elf_map SEC("maps") statsmap = { + .type = BPF_MAP_TYPE_ARRAY, + .size_key = sizeof(Stats), + .size_value = sizeof(int), + .max_elem = 1, +}; + +struct bpf_elf_map SEC("maps") perfmap = { + .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, + .size_key = sizeof(int), + .size_value = sizeof(int), + .max_elem = 32, +}; + +struct bpf_elf_map SEC("maps") stackmap = { + .type = BPF_MAP_TYPE_STACK_TRACE, + .size_key = sizeof(int), + .size_value = sizeof(long long) * 127, + .max_elem = 1000, +}; + +static inline __attribute__((__always_inline__)) int __on_event(struct pt_regs *ctx) +{ + uint64_t pid_tgid = bpf_get_current_pid_tgid(); + pid_t pid = (pid_t)(pid_tgid >> 32); + PidData* pidData = bpf_map_lookup_elem(&pidmap, &pid); + if (!pidData) + return 0; + + int zero = 0; + Event* event = bpf_map_lookup_elem(&eventmap, &zero); + if (!event) + return 0; + + event->pid = pid; + + event->tid = (pid_t)pid_tgid; + bpf_get_current_comm(&event->comm, sizeof(event->comm)); + + event->user_stack_id = bpf_get_stackid(ctx, &stackmap, BPF_F_USER_STACK); + event->kernel_stack_id = bpf_get_stackid(ctx, &stackmap, 0); + + void* thread_state_current = (void*)0; + bpf_probe_read(&thread_state_current, + sizeof(thread_state_current), + (void*)(long)pidData->current_state_addr); + + struct task_struct* task = (struct task_struct*)bpf_get_current_task(); + void* tls_base = (void*)task; + + void* thread_state = pidData->use_tls ? get_thread_state(tls_base, pidData) + : thread_state_current; + event->thread_current = thread_state == thread_state_current; + + if (pidData->use_tls) { + uint64_t pthread_created; + uint64_t pthread_self; + bpf_probe_read(&pthread_self, sizeof(pthread_self), tls_base + 0x10); + + bpf_probe_read(&pthread_created, + sizeof(pthread_created), + thread_state + pidData->offsets.PyThreadState_thread); + event->pthread_match = pthread_created == pthread_self; + } else { + event->pthread_match = 1; + } + + if (event->pthread_match || !pidData->use_tls) { + void* frame_ptr; + FrameData frame; + Symbol sym = {}; + int cur_cpu = bpf_get_smp_processor_id(); + + bpf_probe_read(&frame_ptr, + sizeof(frame_ptr), + thread_state + pidData->offsets.PyThreadState_frame); + + int32_t* symbol_counter = bpf_map_lookup_elem(&symbolmap, &sym); + if (symbol_counter == NULL) + return 0; +#ifdef NO_UNROLL +#pragma clang loop unroll(disable) +#else +#pragma clang loop unroll(full) +#endif + /* Unwind python stack */ + for (int i = 0; i < STACK_MAX_LEN; ++i) { + if (frame_ptr && get_frame_data(frame_ptr, pidData, &frame, &sym)) { + int32_t new_symbol_id = *symbol_counter * 64 + cur_cpu; + int32_t *symbol_id = bpf_map_lookup_elem(&symbolmap, &sym); + if (!symbol_id) { + bpf_map_update_elem(&symbolmap, &sym, &zero, 0); + symbol_id = bpf_map_lookup_elem(&symbolmap, &sym); + if (!symbol_id) + return 0; + } + if (*symbol_id == new_symbol_id) + (*symbol_counter)++; + event->stack[i] = *symbol_id; + event->stack_len = i + 1; + frame_ptr = frame.f_back; + } + } + event->stack_complete = frame_ptr == NULL; + } else { + event->stack_complete = 1; + } + + Stats* stats = bpf_map_lookup_elem(&statsmap, &zero); + if (stats) + stats->success++; + + event->has_meta = 0; + bpf_perf_event_output(ctx, &perfmap, 0, event, offsetof(Event, metadata)); + return 0; +} + +SEC("raw_tracepoint/kfree_skb") +int on_event(struct pt_regs* ctx) +{ + int i, ret = 0; + ret |= __on_event(ctx); + ret |= __on_event(ctx); + ret |= __on_event(ctx); + ret |= __on_event(ctx); + ret |= __on_event(ctx); + return ret; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/pyperf100.c b/tools/testing/selftests/bpf/progs/pyperf100.c new file mode 100644 index 000000000000..29786325db54 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/pyperf100.c @@ -0,0 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#define STACK_MAX_LEN 100 +#include "pyperf.h" diff --git a/tools/testing/selftests/bpf/progs/pyperf180.c b/tools/testing/selftests/bpf/progs/pyperf180.c new file mode 100644 index 000000000000..c39f559d3100 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/pyperf180.c @@ -0,0 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#define STACK_MAX_LEN 180 +#include "pyperf.h" diff --git a/tools/testing/selftests/bpf/progs/pyperf50.c b/tools/testing/selftests/bpf/progs/pyperf50.c new file mode 100644 index 000000000000..ef7ce340a292 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/pyperf50.c @@ -0,0 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#define STACK_MAX_LEN 50 +#include "pyperf.h" diff --git a/tools/testing/selftests/bpf/progs/pyperf600.c b/tools/testing/selftests/bpf/progs/pyperf600.c new file mode 100644 index 000000000000..cb49b89e37cd --- /dev/null +++ b/tools/testing/selftests/bpf/progs/pyperf600.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#define STACK_MAX_LEN 600 +/* clang will not unroll the loop 600 times. + * Instead it will unroll it to the amount it deemed + * appropriate, but the loop will still execute 600 times. + * Total program size is around 90k insns + */ +#include "pyperf.h" diff --git a/tools/testing/selftests/bpf/progs/pyperf600_nounroll.c b/tools/testing/selftests/bpf/progs/pyperf600_nounroll.c new file mode 100644 index 000000000000..6beff7502f4d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/pyperf600_nounroll.c @@ -0,0 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#define STACK_MAX_LEN 600 +#define NO_UNROLL +/* clang will not unroll at all. + * Total program size is around 2k insns + */ +#include "pyperf.h" diff --git a/tools/testing/selftests/bpf/progs/socket_cookie_prog.c b/tools/testing/selftests/bpf/progs/socket_cookie_prog.c index 9ff8ac4b0bf6..6aabb681fb9a 100644 --- a/tools/testing/selftests/bpf/progs/socket_cookie_prog.c +++ b/tools/testing/selftests/bpf/progs/socket_cookie_prog.c @@ -7,25 +7,36 @@ #include "bpf_helpers.h" #include "bpf_endian.h" -struct bpf_map_def SEC("maps") socket_cookies = { - .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(__u64), - .value_size = sizeof(__u32), - .max_entries = 1 << 8, +struct socket_cookie { + __u64 cookie_key; + __u32 cookie_value; +}; + +struct { + __u32 type; + __u32 map_flags; + int *key; + struct socket_cookie *value; +} socket_cookies SEC(".maps") = { + .type = BPF_MAP_TYPE_SK_STORAGE, + .map_flags = BPF_F_NO_PREALLOC, }; SEC("cgroup/connect6") int set_cookie(struct bpf_sock_addr *ctx) { - __u32 cookie_value = 0xFF; - __u64 cookie_key; + struct socket_cookie *p; if (ctx->family != AF_INET6 || ctx->user_family != AF_INET6) return 1; - cookie_key = bpf_get_socket_cookie(ctx); - if (bpf_map_update_elem(&socket_cookies, &cookie_key, &cookie_value, 0)) - return 0; + p = bpf_sk_storage_get(&socket_cookies, ctx->sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + if (!p) + return 1; + + p->cookie_value = 0xFF; + p->cookie_key = bpf_get_socket_cookie(ctx); return 1; } @@ -33,9 +44,8 @@ int set_cookie(struct bpf_sock_addr *ctx) SEC("sockops") int update_cookie(struct bpf_sock_ops *ctx) { - __u32 new_cookie_value; - __u32 *cookie_value; - __u64 cookie_key; + struct bpf_sock *sk; + struct socket_cookie *p; if (ctx->family != AF_INET6) return 1; @@ -43,14 +53,17 @@ int update_cookie(struct bpf_sock_ops *ctx) if (ctx->op != BPF_SOCK_OPS_TCP_CONNECT_CB) return 1; - cookie_key = bpf_get_socket_cookie(ctx); + if (!ctx->sk) + return 1; + + p = bpf_sk_storage_get(&socket_cookies, ctx->sk, 0, 0); + if (!p) + return 1; - cookie_value = bpf_map_lookup_elem(&socket_cookies, &cookie_key); - if (!cookie_value) + if (p->cookie_key != bpf_get_socket_cookie(ctx)) return 1; - new_cookie_value = (ctx->local_port << 8) | *cookie_value; - bpf_map_update_elem(&socket_cookies, &cookie_key, &new_cookie_value, 0); + p->cookie_value = (ctx->local_port << 8) | p->cookie_value; return 1; } diff --git a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c index 0f92858f6226..9390e0244259 100644 --- a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c @@ -1,17 +1,9 @@ #include <linux/bpf.h> #include "bpf_helpers.h" -#include "bpf_util.h" #include "bpf_endian.h" int _version SEC("version") = 1; -#define bpf_printk(fmt, ...) \ -({ \ - char ____fmt[] = fmt; \ - bpf_trace_printk(____fmt, sizeof(____fmt), \ - ##__VA_ARGS__); \ -}) - SEC("sk_skb1") int bpf_prog1(struct __sk_buff *skb) { diff --git a/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c b/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c index 12a7b5c82ed6..e80484d98a1a 100644 --- a/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c @@ -1,17 +1,10 @@ #include <linux/bpf.h> + #include "bpf_helpers.h" -#include "bpf_util.h" #include "bpf_endian.h" int _version SEC("version") = 1; -#define bpf_printk(fmt, ...) \ -({ \ - char ____fmt[] = fmt; \ - bpf_trace_printk(____fmt, sizeof(____fmt), \ - ##__VA_ARGS__); \ -}) - SEC("sk_msg1") int bpf_prog1(struct sk_msg_md *msg) { diff --git a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c index 2ce7634a4012..d85c874ef25e 100644 --- a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c @@ -1,17 +1,9 @@ #include <linux/bpf.h> #include "bpf_helpers.h" -#include "bpf_util.h" #include "bpf_endian.h" int _version SEC("version") = 1; -#define bpf_printk(fmt, ...) \ -({ \ - char ____fmt[] = fmt; \ - bpf_trace_printk(____fmt, sizeof(____fmt), \ - ##__VA_ARGS__); \ -}) - struct bpf_map_def SEC("maps") sock_map_rx = { .type = BPF_MAP_TYPE_SOCKMAP, .key_size = sizeof(int), diff --git a/tools/testing/selftests/bpf/progs/strobemeta.c b/tools/testing/selftests/bpf/progs/strobemeta.c new file mode 100644 index 000000000000..d3df3d86f092 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/strobemeta.c @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +// Copyright (c) 2019 Facebook + +#define STROBE_MAX_INTS 2 +#define STROBE_MAX_STRS 25 +#define STROBE_MAX_MAPS 100 +#define STROBE_MAX_MAP_ENTRIES 20 +/* full unroll by llvm #undef NO_UNROLL */ +#include "strobemeta.h" + diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h new file mode 100644 index 000000000000..1ff73f60a3e4 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/strobemeta.h @@ -0,0 +1,528 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <stdint.h> +#include <stddef.h> +#include <stdbool.h> +#include <linux/bpf.h> +#include <linux/ptrace.h> +#include <linux/sched.h> +#include <linux/types.h> +#include "bpf_helpers.h" + +typedef uint32_t pid_t; +struct task_struct {}; + +#define TASK_COMM_LEN 16 +#define PERF_MAX_STACK_DEPTH 127 + +#define STROBE_TYPE_INVALID 0 +#define STROBE_TYPE_INT 1 +#define STROBE_TYPE_STR 2 +#define STROBE_TYPE_MAP 3 + +#define STACK_TABLE_EPOCH_SHIFT 20 +#define STROBE_MAX_STR_LEN 1 +#define STROBE_MAX_CFGS 32 +#define STROBE_MAX_PAYLOAD \ + (STROBE_MAX_STRS * STROBE_MAX_STR_LEN + \ + STROBE_MAX_MAPS * (1 + STROBE_MAX_MAP_ENTRIES * 2) * STROBE_MAX_STR_LEN) + +struct strobe_value_header { + /* + * meaning depends on type: + * 1. int: 0, if value not set, 1 otherwise + * 2. str: 1 always, whether value is set or not is determined by ptr + * 3. map: 1 always, pointer points to additional struct with number + * of entries (up to STROBE_MAX_MAP_ENTRIES) + */ + uint16_t len; + /* + * _reserved might be used for some future fields/flags, but we always + * want to keep strobe_value_header to be 8 bytes, so BPF can read 16 + * bytes in one go and get both header and value + */ + uint8_t _reserved[6]; +}; + +/* + * strobe_value_generic is used from BPF probe only, but needs to be a union + * of strobe_value_int/strobe_value_str/strobe_value_map + */ +struct strobe_value_generic { + struct strobe_value_header header; + union { + int64_t val; + void *ptr; + }; +}; + +struct strobe_value_int { + struct strobe_value_header header; + int64_t value; +}; + +struct strobe_value_str { + struct strobe_value_header header; + const char* value; +}; + +struct strobe_value_map { + struct strobe_value_header header; + const struct strobe_map_raw* value; +}; + +struct strobe_map_entry { + const char* key; + const char* val; +}; + +/* + * Map of C-string key/value pairs with fixed maximum capacity. Each map has + * corresponding int64 ID, which application can use (or ignore) in whatever + * way appropriate. Map is "write-only", there is no way to get data out of + * map. Map is intended to be used to provide metadata for profilers and is + * not to be used for internal in-app communication. All methods are + * thread-safe. + */ +struct strobe_map_raw { + /* + * general purpose unique ID that's up to application to decide + * whether and how to use; for request metadata use case id is unique + * request ID that's used to match metadata with stack traces on + * Strobelight backend side + */ + int64_t id; + /* number of used entries in map */ + int64_t cnt; + /* + * having volatile doesn't change anything on BPF side, but clang + * emits warnings for passing `volatile const char *` into + * bpf_probe_read_str that expects just `const char *` + */ + const char* tag; + /* + * key/value entries, each consisting of 2 pointers to key and value + * C strings + */ + struct strobe_map_entry entries[STROBE_MAX_MAP_ENTRIES]; +}; + +/* Following values define supported values of TLS mode */ +#define TLS_NOT_SET -1 +#define TLS_LOCAL_EXEC 0 +#define TLS_IMM_EXEC 1 +#define TLS_GENERAL_DYN 2 + +/* + * structure that universally represents TLS location (both for static + * executables and shared libraries) + */ +struct strobe_value_loc { + /* + * tls_mode defines what TLS mode was used for particular metavariable: + * - -1 (TLS_NOT_SET) - no metavariable; + * - 0 (TLS_LOCAL_EXEC) - Local Executable mode; + * - 1 (TLS_IMM_EXEC) - Immediate Executable mode; + * - 2 (TLS_GENERAL_DYN) - General Dynamic mode; + * Local Dynamic mode is not yet supported, because never seen in + * practice. Mode defines how offset field is interpreted. See + * calc_location() in below for details. + */ + int64_t tls_mode; + /* + * TLS_LOCAL_EXEC: offset from thread pointer (fs:0 for x86-64, + * tpidr_el0 for aarch64). + * TLS_IMM_EXEC: absolute address of GOT entry containing offset + * from thread pointer; + * TLS_GENERAL_DYN: absolute addres of double GOT entry + * containing tls_index_t struct; + */ + int64_t offset; +}; + +struct strobemeta_cfg { + int64_t req_meta_idx; + struct strobe_value_loc int_locs[STROBE_MAX_INTS]; + struct strobe_value_loc str_locs[STROBE_MAX_STRS]; + struct strobe_value_loc map_locs[STROBE_MAX_MAPS]; +}; + +struct strobe_map_descr { + uint64_t id; + int16_t tag_len; + /* + * cnt <0 - map value isn't set; + * 0 - map has id set, but no key/value entries + */ + int16_t cnt; + /* + * both key_lens[i] and val_lens[i] should be >0 for present key/value + * entry + */ + uint16_t key_lens[STROBE_MAX_MAP_ENTRIES]; + uint16_t val_lens[STROBE_MAX_MAP_ENTRIES]; +}; + +struct strobemeta_payload { + /* req_id has valid request ID, if req_meta_valid == 1 */ + int64_t req_id; + uint8_t req_meta_valid; + /* + * mask has Nth bit set to 1, if Nth metavar was present and + * successfully read + */ + uint64_t int_vals_set_mask; + int64_t int_vals[STROBE_MAX_INTS]; + /* len is >0 for present values */ + uint16_t str_lens[STROBE_MAX_STRS]; + /* if map_descrs[i].cnt == -1, metavar is not present/set */ + struct strobe_map_descr map_descrs[STROBE_MAX_MAPS]; + /* + * payload has compactly packed values of str and map variables in the + * form: strval1\0strval2\0map1key1\0map1val1\0map2key1\0map2val1\0 + * (and so on); str_lens[i], key_lens[i] and val_lens[i] determines + * value length + */ + char payload[STROBE_MAX_PAYLOAD]; +}; + +struct strobelight_bpf_sample { + uint64_t ktime; + char comm[TASK_COMM_LEN]; + pid_t pid; + int user_stack_id; + int kernel_stack_id; + int has_meta; + struct strobemeta_payload metadata; + /* + * makes it possible to pass (<real payload size> + 1) as data size to + * perf_submit() to avoid perf_submit's paranoia about passing zero as + * size, as it deduces that <real payload size> might be + * **theoretically** zero + */ + char dummy_safeguard; +}; + +struct bpf_map_def SEC("maps") samples = { + .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 32, +}; + +struct bpf_map_def SEC("maps") stacks_0 = { + .type = BPF_MAP_TYPE_STACK_TRACE, + .key_size = sizeof(uint32_t), + .value_size = sizeof(uint64_t) * PERF_MAX_STACK_DEPTH, + .max_entries = 16, +}; + +struct bpf_map_def SEC("maps") stacks_1 = { + .type = BPF_MAP_TYPE_STACK_TRACE, + .key_size = sizeof(uint32_t), + .value_size = sizeof(uint64_t) * PERF_MAX_STACK_DEPTH, + .max_entries = 16, +}; + +struct bpf_map_def SEC("maps") sample_heap = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(uint32_t), + .value_size = sizeof(struct strobelight_bpf_sample), + .max_entries = 1, +}; + +struct bpf_map_def SEC("maps") strobemeta_cfgs = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(pid_t), + .value_size = sizeof(struct strobemeta_cfg), + .max_entries = STROBE_MAX_CFGS, +}; + +/* Type for the dtv. */ +/* https://github.com/lattera/glibc/blob/master/nptl/sysdeps/x86_64/tls.h#L34 */ +typedef union dtv { + size_t counter; + struct { + void* val; + bool is_static; + } pointer; +} dtv_t; + +/* Partial definition for tcbhead_t */ +/* https://github.com/bminor/glibc/blob/master/sysdeps/x86_64/nptl/tls.h#L42 */ +struct tcbhead { + void* tcb; + dtv_t* dtv; +}; + +/* + * TLS module/offset information for shared library case. + * For x86-64, this is mapped onto two entries in GOT. + * For aarch64, this is pointed to by second GOT entry. + */ +struct tls_index { + uint64_t module; + uint64_t offset; +}; + +static inline __attribute__((always_inline)) +void *calc_location(struct strobe_value_loc *loc, void *tls_base) +{ + /* + * tls_mode value is: + * - -1 (TLS_NOT_SET), if no metavar is present; + * - 0 (TLS_LOCAL_EXEC), if metavar uses Local Executable mode of TLS + * (offset from fs:0 for x86-64 or tpidr_el0 for aarch64); + * - 1 (TLS_IMM_EXEC), if metavar uses Immediate Executable mode of TLS; + * - 2 (TLS_GENERAL_DYN), if metavar uses General Dynamic mode of TLS; + * This schema allows to use something like: + * (tls_mode + 1) * (tls_base + offset) + * to get NULL for "no metavar" location, or correct pointer for local + * executable mode without doing extra ifs. + */ + if (loc->tls_mode <= TLS_LOCAL_EXEC) { + /* static executable is simple, we just have offset from + * tls_base */ + void *addr = tls_base + loc->offset; + /* multiply by (tls_mode + 1) to get NULL, if we have no + * metavar in this slot */ + return (void *)((loc->tls_mode + 1) * (int64_t)addr); + } + /* + * Other modes are more complicated, we need to jump through few hoops. + * + * For immediate executable mode (currently supported only for aarch64): + * - loc->offset is pointing to a GOT entry containing fixed offset + * relative to tls_base; + * + * For general dynamic mode: + * - loc->offset is pointing to a beginning of double GOT entries; + * - (for aarch64 only) second entry points to tls_index_t struct; + * - (for x86-64 only) two GOT entries are already tls_index_t; + * - tls_index_t->module is used to find start of TLS section in + * which variable resides; + * - tls_index_t->offset provides offset within that TLS section, + * pointing to value of variable. + */ + struct tls_index tls_index; + dtv_t *dtv; + void *tls_ptr; + + bpf_probe_read(&tls_index, sizeof(struct tls_index), + (void *)loc->offset); + /* valid module index is always positive */ + if (tls_index.module > 0) { + /* dtv = ((struct tcbhead *)tls_base)->dtv[tls_index.module] */ + bpf_probe_read(&dtv, sizeof(dtv), + &((struct tcbhead *)tls_base)->dtv); + dtv += tls_index.module; + } else { + dtv = NULL; + } + bpf_probe_read(&tls_ptr, sizeof(void *), dtv); + /* if pointer has (void *)-1 value, then TLS wasn't initialized yet */ + return tls_ptr && tls_ptr != (void *)-1 + ? tls_ptr + tls_index.offset + : NULL; +} + +static inline __attribute__((always_inline)) +void read_int_var(struct strobemeta_cfg *cfg, size_t idx, void *tls_base, + struct strobe_value_generic *value, + struct strobemeta_payload *data) +{ + void *location = calc_location(&cfg->int_locs[idx], tls_base); + if (!location) + return; + + bpf_probe_read(value, sizeof(struct strobe_value_generic), location); + data->int_vals[idx] = value->val; + if (value->header.len) + data->int_vals_set_mask |= (1 << idx); +} + +static inline __attribute__((always_inline)) +uint64_t read_str_var(struct strobemeta_cfg* cfg, size_t idx, void *tls_base, + struct strobe_value_generic *value, + struct strobemeta_payload *data, void *payload) +{ + void *location; + uint32_t len; + + data->str_lens[idx] = 0; + location = calc_location(&cfg->str_locs[idx], tls_base); + if (!location) + return 0; + + bpf_probe_read(value, sizeof(struct strobe_value_generic), location); + len = bpf_probe_read_str(payload, STROBE_MAX_STR_LEN, value->ptr); + /* + * if bpf_probe_read_str returns error (<0), due to casting to + * unsinged int, it will become big number, so next check is + * sufficient to check for errors AND prove to BPF verifier, that + * bpf_probe_read_str won't return anything bigger than + * STROBE_MAX_STR_LEN + */ + if (len > STROBE_MAX_STR_LEN) + return 0; + + data->str_lens[idx] = len; + return len; +} + +static inline __attribute__((always_inline)) +void *read_map_var(struct strobemeta_cfg *cfg, size_t idx, void *tls_base, + struct strobe_value_generic *value, + struct strobemeta_payload* data, void *payload) +{ + struct strobe_map_descr* descr = &data->map_descrs[idx]; + struct strobe_map_raw map; + void *location; + uint32_t len; + int i; + + descr->tag_len = 0; /* presume no tag is set */ + descr->cnt = -1; /* presume no value is set */ + + location = calc_location(&cfg->map_locs[idx], tls_base); + if (!location) + return payload; + + bpf_probe_read(value, sizeof(struct strobe_value_generic), location); + if (bpf_probe_read(&map, sizeof(struct strobe_map_raw), value->ptr)) + return payload; + + descr->id = map.id; + descr->cnt = map.cnt; + if (cfg->req_meta_idx == idx) { + data->req_id = map.id; + data->req_meta_valid = 1; + } + + len = bpf_probe_read_str(payload, STROBE_MAX_STR_LEN, map.tag); + if (len <= STROBE_MAX_STR_LEN) { + descr->tag_len = len; + payload += len; + } + +#ifdef NO_UNROLL +#pragma clang loop unroll(disable) +#else +#pragma unroll +#endif + for (int i = 0; i < STROBE_MAX_MAP_ENTRIES && i < map.cnt; ++i) { + descr->key_lens[i] = 0; + len = bpf_probe_read_str(payload, STROBE_MAX_STR_LEN, + map.entries[i].key); + if (len <= STROBE_MAX_STR_LEN) { + descr->key_lens[i] = len; + payload += len; + } + descr->val_lens[i] = 0; + len = bpf_probe_read_str(payload, STROBE_MAX_STR_LEN, + map.entries[i].val); + if (len <= STROBE_MAX_STR_LEN) { + descr->val_lens[i] = len; + payload += len; + } + } + + return payload; +} + +/* + * read_strobe_meta returns NULL, if no metadata was read; otherwise returns + * pointer to *right after* payload ends + */ +static inline __attribute__((always_inline)) +void *read_strobe_meta(struct task_struct* task, + struct strobemeta_payload* data) { + pid_t pid = bpf_get_current_pid_tgid() >> 32; + struct strobe_value_generic value = {0}; + struct strobemeta_cfg *cfg; + void *tls_base, *payload; + + cfg = bpf_map_lookup_elem(&strobemeta_cfgs, &pid); + if (!cfg) + return NULL; + + data->int_vals_set_mask = 0; + data->req_meta_valid = 0; + payload = data->payload; + /* + * we don't have struct task_struct definition, it should be: + * tls_base = (void *)task->thread.fsbase; + */ + tls_base = (void *)task; + +#ifdef NO_UNROLL +#pragma clang loop unroll(disable) +#else +#pragma unroll +#endif + for (int i = 0; i < STROBE_MAX_INTS; ++i) { + read_int_var(cfg, i, tls_base, &value, data); + } +#ifdef NO_UNROLL +#pragma clang loop unroll(disable) +#else +#pragma unroll +#endif + for (int i = 0; i < STROBE_MAX_STRS; ++i) { + payload += read_str_var(cfg, i, tls_base, &value, data, payload); + } +#ifdef NO_UNROLL +#pragma clang loop unroll(disable) +#else +#pragma unroll +#endif + for (int i = 0; i < STROBE_MAX_MAPS; ++i) { + payload = read_map_var(cfg, i, tls_base, &value, data, payload); + } + /* + * return pointer right after end of payload, so it's possible to + * calculate exact amount of useful data that needs to be sent + */ + return payload; +} + +SEC("raw_tracepoint/kfree_skb") +int on_event(struct pt_regs *ctx) { + pid_t pid = bpf_get_current_pid_tgid() >> 32; + struct strobelight_bpf_sample* sample; + struct task_struct *task; + uint32_t zero = 0; + uint64_t ktime_ns; + void *sample_end; + + sample = bpf_map_lookup_elem(&sample_heap, &zero); + if (!sample) + return 0; /* this will never happen */ + + sample->pid = pid; + bpf_get_current_comm(&sample->comm, TASK_COMM_LEN); + ktime_ns = bpf_ktime_get_ns(); + sample->ktime = ktime_ns; + + task = (struct task_struct *)bpf_get_current_task(); + sample_end = read_strobe_meta(task, &sample->metadata); + sample->has_meta = sample_end != NULL; + sample_end = sample_end ? : &sample->metadata; + + if ((ktime_ns >> STACK_TABLE_EPOCH_SHIFT) & 1) { + sample->kernel_stack_id = bpf_get_stackid(ctx, &stacks_1, 0); + sample->user_stack_id = bpf_get_stackid(ctx, &stacks_1, BPF_F_USER_STACK); + } else { + sample->kernel_stack_id = bpf_get_stackid(ctx, &stacks_0, 0); + sample->user_stack_id = bpf_get_stackid(ctx, &stacks_0, BPF_F_USER_STACK); + } + + uint64_t sample_size = sample_end - (void *)sample; + /* should always be true */ + if (sample_size < sizeof(struct strobelight_bpf_sample)) + bpf_perf_event_output(ctx, &samples, 0, sample, 1 + sample_size); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/strobemeta_nounroll1.c b/tools/testing/selftests/bpf/progs/strobemeta_nounroll1.c new file mode 100644 index 000000000000..f0a1669e11d6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/strobemeta_nounroll1.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +// Copyright (c) 2019 Facebook + +#define STROBE_MAX_INTS 2 +#define STROBE_MAX_STRS 25 +#define STROBE_MAX_MAPS 13 +#define STROBE_MAX_MAP_ENTRIES 20 +#define NO_UNROLL +#include "strobemeta.h" diff --git a/tools/testing/selftests/bpf/progs/strobemeta_nounroll2.c b/tools/testing/selftests/bpf/progs/strobemeta_nounroll2.c new file mode 100644 index 000000000000..4291a7d642e7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/strobemeta_nounroll2.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +// Copyright (c) 2019 Facebook + +#define STROBE_MAX_INTS 2 +#define STROBE_MAX_STRS 25 +#define STROBE_MAX_MAPS 30 +#define STROBE_MAX_MAP_ENTRIES 20 +#define NO_UNROLL +#include "strobemeta.h" diff --git a/tools/testing/selftests/bpf/progs/test_btf_newkv.c b/tools/testing/selftests/bpf/progs/test_btf_newkv.c new file mode 100644 index 000000000000..28c16bb583b6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_btf_newkv.c @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018 Facebook */ +#include <linux/bpf.h> +#include "bpf_helpers.h" + +int _version SEC("version") = 1; + +struct ipv_counts { + unsigned int v4; + unsigned int v6; +}; + +/* just to validate we can handle maps in multiple sections */ +struct bpf_map_def SEC("maps") btf_map_legacy = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(long long), + .max_entries = 4, +}; + +BPF_ANNOTATE_KV_PAIR(btf_map_legacy, int, struct ipv_counts); + +struct { + int *key; + struct ipv_counts *value; + unsigned int type; + unsigned int max_entries; +} btf_map SEC(".maps") = { + .type = BPF_MAP_TYPE_ARRAY, + .max_entries = 4, +}; + +struct dummy_tracepoint_args { + unsigned long long pad; + struct sock *sock; +}; + +__attribute__((noinline)) +static int test_long_fname_2(struct dummy_tracepoint_args *arg) +{ + struct ipv_counts *counts; + int key = 0; + + if (!arg->sock) + return 0; + + counts = bpf_map_lookup_elem(&btf_map, &key); + if (!counts) + return 0; + + counts->v6++; + + /* just verify we can reference both maps */ + counts = bpf_map_lookup_elem(&btf_map_legacy, &key); + if (!counts) + return 0; + + return 0; +} + +__attribute__((noinline)) +static int test_long_fname_1(struct dummy_tracepoint_args *arg) +{ + return test_long_fname_2(arg); +} + +SEC("dummy_tracepoint") +int _dummy_tracepoint(struct dummy_tracepoint_args *arg) +{ + return test_long_fname_1(arg); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c index f6d9f238e00a..aaa6ec250e15 100644 --- a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c +++ b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c @@ -15,17 +15,25 @@ struct stack_trace_t { struct bpf_stack_build_id user_stack_buildid[MAX_STACK_RAWTP]; }; -struct bpf_map_def SEC("maps") perfmap = { +struct { + __u32 type; + __u32 max_entries; + __u32 key_size; + __u32 value_size; +} perfmap SEC(".maps") = { .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, + .max_entries = 2, .key_size = sizeof(int), .value_size = sizeof(__u32), - .max_entries = 2, }; -struct bpf_map_def SEC("maps") stackdata_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct stack_trace_t *value; +} stackdata_map SEC(".maps") = { .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct stack_trace_t), .max_entries = 1, }; @@ -47,10 +55,13 @@ struct bpf_map_def SEC("maps") stackdata_map = { * issue and avoid complicated C programming massaging. * This is an acceptable workaround since there is one entry here. */ -struct bpf_map_def SEC("maps") rawdata_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u64 (*value)[2 * MAX_STACK_RAWTP]; +} rawdata_map SEC(".maps") = { .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(__u32), - .value_size = MAX_STACK_RAWTP * sizeof(__u64) * 2, .max_entries = 1, }; diff --git a/tools/testing/selftests/bpf/progs/test_global_data.c b/tools/testing/selftests/bpf/progs/test_global_data.c index 5ab14e941980..866cc7ddbe43 100644 --- a/tools/testing/selftests/bpf/progs/test_global_data.c +++ b/tools/testing/selftests/bpf/progs/test_global_data.c @@ -7,17 +7,23 @@ #include "bpf_helpers.h" -struct bpf_map_def SEC("maps") result_number = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u64 *value; +} result_number SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u64), .max_entries = 11, }; -struct bpf_map_def SEC("maps") result_string = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + const char (*value)[32]; +} result_string SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = 32, .max_entries = 5, }; @@ -27,10 +33,13 @@ struct foo { __u64 c; }; -struct bpf_map_def SEC("maps") result_struct = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct foo *value; +} result_struct SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct foo), .max_entries = 5, }; diff --git a/tools/testing/selftests/bpf/progs/test_l4lb.c b/tools/testing/selftests/bpf/progs/test_l4lb.c index 1e10c9590991..848cbb90f581 100644 --- a/tools/testing/selftests/bpf/progs/test_l4lb.c +++ b/tools/testing/selftests/bpf/progs/test_l4lb.c @@ -169,38 +169,53 @@ struct eth_hdr { unsigned short eth_proto; }; -struct bpf_map_def SEC("maps") vip_map = { +struct { + __u32 type; + __u32 max_entries; + struct vip *key; + struct vip_meta *value; +} vip_map SEC(".maps") = { .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(struct vip), - .value_size = sizeof(struct vip_meta), .max_entries = MAX_VIPS, }; -struct bpf_map_def SEC("maps") ch_rings = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} ch_rings SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = CH_RINGS_SIZE, }; -struct bpf_map_def SEC("maps") reals = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct real_definition *value; +} reals SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct real_definition), .max_entries = MAX_REALS, }; -struct bpf_map_def SEC("maps") stats = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct vip_stats *value; +} stats SEC(".maps") = { .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct vip_stats), .max_entries = MAX_VIPS, }; -struct bpf_map_def SEC("maps") ctl_array = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct ctl_value *value; +} ctl_array SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct ctl_value), .max_entries = CTL_MAP_SIZE, }; diff --git a/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c index ba44a14e6dc4..c63ecf3ca573 100644 --- a/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c +++ b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c @@ -165,38 +165,53 @@ struct eth_hdr { unsigned short eth_proto; }; -struct bpf_map_def SEC("maps") vip_map = { +struct { + __u32 type; + __u32 max_entries; + struct vip *key; + struct vip_meta *value; +} vip_map SEC(".maps") = { .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(struct vip), - .value_size = sizeof(struct vip_meta), .max_entries = MAX_VIPS, }; -struct bpf_map_def SEC("maps") ch_rings = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} ch_rings SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = CH_RINGS_SIZE, }; -struct bpf_map_def SEC("maps") reals = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct real_definition *value; +} reals SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct real_definition), .max_entries = MAX_REALS, }; -struct bpf_map_def SEC("maps") stats = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct vip_stats *value; +} stats SEC(".maps") = { .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct vip_stats), .max_entries = MAX_VIPS, }; -struct bpf_map_def SEC("maps") ctl_array = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct ctl_value *value; +} ctl_array SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct ctl_value), .max_entries = CTL_MAP_SIZE, }; diff --git a/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c index 0575751bc1bc..7c7cb3177463 100644 --- a/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c +++ b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c @@ -6,13 +6,6 @@ #include "bpf_helpers.h" #include "bpf_endian.h" -#define bpf_printk(fmt, ...) \ -({ \ - char ____fmt[] = fmt; \ - bpf_trace_printk(____fmt, sizeof(____fmt), \ - ##__VA_ARGS__); \ -}) - /* Packet parsing state machine helpers. */ #define cursor_advance(_cursor, _len) \ ({ void *_tmp = _cursor; _cursor += _len; _tmp; }) diff --git a/tools/testing/selftests/bpf/progs/test_map_lock.c b/tools/testing/selftests/bpf/progs/test_map_lock.c index af8cc68ed2f9..40d9c2853393 100644 --- a/tools/testing/selftests/bpf/progs/test_map_lock.c +++ b/tools/testing/selftests/bpf/progs/test_map_lock.c @@ -11,29 +11,31 @@ struct hmap_elem { int var[VAR_NUM]; }; -struct bpf_map_def SEC("maps") hash_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct hmap_elem *value; +} hash_map SEC(".maps") = { .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(int), - .value_size = sizeof(struct hmap_elem), .max_entries = 1, }; -BPF_ANNOTATE_KV_PAIR(hash_map, int, struct hmap_elem); - struct array_elem { struct bpf_spin_lock lock; int var[VAR_NUM]; }; -struct bpf_map_def SEC("maps") array_map = { +struct { + __u32 type; + __u32 max_entries; + int *key; + struct array_elem *value; +} array_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(struct array_elem), .max_entries = 1, }; -BPF_ANNOTATE_KV_PAIR(array_map, int, struct array_elem); - SEC("map_lock_demo") int bpf_map_lock_test(struct __sk_buff *skb) { diff --git a/tools/testing/selftests/bpf/progs/test_seg6_loop.c b/tools/testing/selftests/bpf/progs/test_seg6_loop.c new file mode 100644 index 000000000000..463964d79f73 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_seg6_loop.c @@ -0,0 +1,261 @@ +#include <stddef.h> +#include <inttypes.h> +#include <errno.h> +#include <linux/seg6_local.h> +#include <linux/bpf.h> +#include "bpf_helpers.h" +#include "bpf_endian.h" + +/* Packet parsing state machine helpers. */ +#define cursor_advance(_cursor, _len) \ + ({ void *_tmp = _cursor; _cursor += _len; _tmp; }) + +#define SR6_FLAG_ALERT (1 << 4) + +#define htonll(x) ((bpf_htonl(1)) == 1 ? (x) : ((uint64_t)bpf_htonl((x) & \ + 0xFFFFFFFF) << 32) | bpf_htonl((x) >> 32)) +#define ntohll(x) ((bpf_ntohl(1)) == 1 ? (x) : ((uint64_t)bpf_ntohl((x) & \ + 0xFFFFFFFF) << 32) | bpf_ntohl((x) >> 32)) +#define BPF_PACKET_HEADER __attribute__((packed)) + +struct ip6_t { + unsigned int ver:4; + unsigned int priority:8; + unsigned int flow_label:20; + unsigned short payload_len; + unsigned char next_header; + unsigned char hop_limit; + unsigned long long src_hi; + unsigned long long src_lo; + unsigned long long dst_hi; + unsigned long long dst_lo; +} BPF_PACKET_HEADER; + +struct ip6_addr_t { + unsigned long long hi; + unsigned long long lo; +} BPF_PACKET_HEADER; + +struct ip6_srh_t { + unsigned char nexthdr; + unsigned char hdrlen; + unsigned char type; + unsigned char segments_left; + unsigned char first_segment; + unsigned char flags; + unsigned short tag; + + struct ip6_addr_t segments[0]; +} BPF_PACKET_HEADER; + +struct sr6_tlv_t { + unsigned char type; + unsigned char len; + unsigned char value[0]; +} BPF_PACKET_HEADER; + +static __attribute__((always_inline)) struct ip6_srh_t *get_srh(struct __sk_buff *skb) +{ + void *cursor, *data_end; + struct ip6_srh_t *srh; + struct ip6_t *ip; + uint8_t *ipver; + + data_end = (void *)(long)skb->data_end; + cursor = (void *)(long)skb->data; + ipver = (uint8_t *)cursor; + + if ((void *)ipver + sizeof(*ipver) > data_end) + return NULL; + + if ((*ipver >> 4) != 6) + return NULL; + + ip = cursor_advance(cursor, sizeof(*ip)); + if ((void *)ip + sizeof(*ip) > data_end) + return NULL; + + if (ip->next_header != 43) + return NULL; + + srh = cursor_advance(cursor, sizeof(*srh)); + if ((void *)srh + sizeof(*srh) > data_end) + return NULL; + + if (srh->type != 4) + return NULL; + + return srh; +} + +static __attribute__((always_inline)) +int update_tlv_pad(struct __sk_buff *skb, uint32_t new_pad, + uint32_t old_pad, uint32_t pad_off) +{ + int err; + + if (new_pad != old_pad) { + err = bpf_lwt_seg6_adjust_srh(skb, pad_off, + (int) new_pad - (int) old_pad); + if (err) + return err; + } + + if (new_pad > 0) { + char pad_tlv_buf[16] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0}; + struct sr6_tlv_t *pad_tlv = (struct sr6_tlv_t *) pad_tlv_buf; + + pad_tlv->type = SR6_TLV_PADDING; + pad_tlv->len = new_pad - 2; + + err = bpf_lwt_seg6_store_bytes(skb, pad_off, + (void *)pad_tlv_buf, new_pad); + if (err) + return err; + } + + return 0; +} + +static __attribute__((always_inline)) +int is_valid_tlv_boundary(struct __sk_buff *skb, struct ip6_srh_t *srh, + uint32_t *tlv_off, uint32_t *pad_size, + uint32_t *pad_off) +{ + uint32_t srh_off, cur_off; + int offset_valid = 0; + int err; + + srh_off = (char *)srh - (char *)(long)skb->data; + // cur_off = end of segments, start of possible TLVs + cur_off = srh_off + sizeof(*srh) + + sizeof(struct ip6_addr_t) * (srh->first_segment + 1); + + *pad_off = 0; + + // we can only go as far as ~10 TLVs due to the BPF max stack size + #pragma clang loop unroll(disable) + for (int i = 0; i < 100; i++) { + struct sr6_tlv_t tlv; + + if (cur_off == *tlv_off) + offset_valid = 1; + + if (cur_off >= srh_off + ((srh->hdrlen + 1) << 3)) + break; + + err = bpf_skb_load_bytes(skb, cur_off, &tlv, sizeof(tlv)); + if (err) + return err; + + if (tlv.type == SR6_TLV_PADDING) { + *pad_size = tlv.len + sizeof(tlv); + *pad_off = cur_off; + + if (*tlv_off == srh_off) { + *tlv_off = cur_off; + offset_valid = 1; + } + break; + + } else if (tlv.type == SR6_TLV_HMAC) { + break; + } + + cur_off += sizeof(tlv) + tlv.len; + } // we reached the padding or HMAC TLVs, or the end of the SRH + + if (*pad_off == 0) + *pad_off = cur_off; + + if (*tlv_off == -1) + *tlv_off = cur_off; + else if (!offset_valid) + return -EINVAL; + + return 0; +} + +static __attribute__((always_inline)) +int add_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh, uint32_t tlv_off, + struct sr6_tlv_t *itlv, uint8_t tlv_size) +{ + uint32_t srh_off = (char *)srh - (char *)(long)skb->data; + uint8_t len_remaining, new_pad; + uint32_t pad_off = 0; + uint32_t pad_size = 0; + uint32_t partial_srh_len; + int err; + + if (tlv_off != -1) + tlv_off += srh_off; + + if (itlv->type == SR6_TLV_PADDING || itlv->type == SR6_TLV_HMAC) + return -EINVAL; + + err = is_valid_tlv_boundary(skb, srh, &tlv_off, &pad_size, &pad_off); + if (err) + return err; + + err = bpf_lwt_seg6_adjust_srh(skb, tlv_off, sizeof(*itlv) + itlv->len); + if (err) + return err; + + err = bpf_lwt_seg6_store_bytes(skb, tlv_off, (void *)itlv, tlv_size); + if (err) + return err; + + // the following can't be moved inside update_tlv_pad because the + // bpf verifier has some issues with it + pad_off += sizeof(*itlv) + itlv->len; + partial_srh_len = pad_off - srh_off; + len_remaining = partial_srh_len % 8; + new_pad = 8 - len_remaining; + + if (new_pad == 1) // cannot pad for 1 byte only + new_pad = 9; + else if (new_pad == 8) + new_pad = 0; + + return update_tlv_pad(skb, new_pad, pad_size, pad_off); +} + +// Add an Egress TLV fc00::4, add the flag A, +// and apply End.X action to fc42::1 +SEC("lwt_seg6local") +int __add_egr_x(struct __sk_buff *skb) +{ + unsigned long long hi = 0xfc42000000000000; + unsigned long long lo = 0x1; + struct ip6_srh_t *srh = get_srh(skb); + uint8_t new_flags = SR6_FLAG_ALERT; + struct ip6_addr_t addr; + int err, offset; + + if (srh == NULL) + return BPF_DROP; + + uint8_t tlv[20] = {2, 18, 0, 0, 0xfd, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, + 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x4}; + + err = add_tlv(skb, srh, (srh->hdrlen+1) << 3, + (struct sr6_tlv_t *)&tlv, 20); + if (err) + return BPF_DROP; + + offset = sizeof(struct ip6_t) + offsetof(struct ip6_srh_t, flags); + err = bpf_lwt_seg6_store_bytes(skb, offset, + (void *)&new_flags, sizeof(new_flags)); + if (err) + return BPF_DROP; + + addr.lo = htonll(lo); + addr.hi = htonll(hi); + err = bpf_lwt_seg6_action(skb, SEG6_LOCAL_ACTION_END_X, + (void *)&addr, sizeof(addr)); + if (err) + return BPF_DROP; + return BPF_REDIRECT; +} +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c index 5b54ec637ada..435a9527733e 100644 --- a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c +++ b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c @@ -21,38 +21,55 @@ int _version SEC("version") = 1; #define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER) #endif -struct bpf_map_def SEC("maps") outer_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 key_size; + __u32 value_size; +} outer_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY_OF_MAPS, + .max_entries = 1, .key_size = sizeof(__u32), .value_size = sizeof(__u32), - .max_entries = 1, }; -struct bpf_map_def SEC("maps") result_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} result_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = NR_RESULTS, }; -struct bpf_map_def SEC("maps") tmp_index_ovr_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + int *value; +} tmp_index_ovr_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(int), .max_entries = 1, }; -struct bpf_map_def SEC("maps") linum_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} linum_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = 1, }; -struct bpf_map_def SEC("maps") data_check_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct data_check *value; +} data_check_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct data_check), .max_entries = 1, }; diff --git a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c new file mode 100644 index 000000000000..6ac68be5d68b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/bpf.h> +#include <linux/version.h> +#include "bpf_helpers.h" + +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u64 *value; +} info_map SEC(".maps") = { + .type = BPF_MAP_TYPE_ARRAY, + .max_entries = 1, +}; + +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u64 *value; +} status_map SEC(".maps") = { + .type = BPF_MAP_TYPE_ARRAY, + .max_entries = 1, +}; + +SEC("send_signal_demo") +int bpf_send_signal_test(void *ctx) +{ + __u64 *info_val, *status_val; + __u32 key = 0, pid, sig; + int ret; + + status_val = bpf_map_lookup_elem(&status_map, &key); + if (!status_val || *status_val != 0) + return 0; + + info_val = bpf_map_lookup_elem(&info_map, &key); + if (!info_val || *info_val == 0) + return 0; + + sig = *info_val >> 32; + pid = *info_val & 0xffffFFFF; + + if ((bpf_get_current_pid_tgid() >> 32) == pid) { + ret = bpf_send_signal(sig); + if (ret == 0) + *status_val = 1; + } + + return 0; +} +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c index 1c39e4ccb7f1..c3d383d650cb 100644 --- a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c +++ b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c @@ -27,31 +27,43 @@ enum bpf_linum_array_idx { __NR_BPF_LINUM_ARRAY_IDX, }; -struct bpf_map_def SEC("maps") addr_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct sockaddr_in6 *value; +} addr_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct sockaddr_in6), .max_entries = __NR_BPF_ADDR_ARRAY_IDX, }; -struct bpf_map_def SEC("maps") sock_result_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct bpf_sock *value; +} sock_result_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct bpf_sock), .max_entries = __NR_BPF_RESULT_ARRAY_IDX, }; -struct bpf_map_def SEC("maps") tcp_sock_result_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct bpf_tcp_sock *value; +} tcp_sock_result_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct bpf_tcp_sock), .max_entries = __NR_BPF_RESULT_ARRAY_IDX, }; -struct bpf_map_def SEC("maps") linum_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} linum_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = __NR_BPF_LINUM_ARRAY_IDX, }; @@ -60,26 +72,26 @@ struct bpf_spinlock_cnt { __u32 cnt; }; -struct bpf_map_def SEC("maps") sk_pkt_out_cnt = { +struct { + __u32 type; + __u32 map_flags; + int *key; + struct bpf_spinlock_cnt *value; +} sk_pkt_out_cnt SEC(".maps") = { .type = BPF_MAP_TYPE_SK_STORAGE, - .key_size = sizeof(int), - .value_size = sizeof(struct bpf_spinlock_cnt), - .max_entries = 0, .map_flags = BPF_F_NO_PREALLOC, }; -BPF_ANNOTATE_KV_PAIR(sk_pkt_out_cnt, int, struct bpf_spinlock_cnt); - -struct bpf_map_def SEC("maps") sk_pkt_out_cnt10 = { +struct { + __u32 type; + __u32 map_flags; + int *key; + struct bpf_spinlock_cnt *value; +} sk_pkt_out_cnt10 SEC(".maps") = { .type = BPF_MAP_TYPE_SK_STORAGE, - .key_size = sizeof(int), - .value_size = sizeof(struct bpf_spinlock_cnt), - .max_entries = 0, .map_flags = BPF_F_NO_PREALLOC, }; -BPF_ANNOTATE_KV_PAIR(sk_pkt_out_cnt10, int, struct bpf_spinlock_cnt); - static bool is_loopback6(__u32 *a6) { return !a6[0] && !a6[1] && !a6[2] && a6[3] == bpf_htonl(1); diff --git a/tools/testing/selftests/bpf/progs/test_spin_lock.c b/tools/testing/selftests/bpf/progs/test_spin_lock.c index 40f904312090..0a77ae36d981 100644 --- a/tools/testing/selftests/bpf/progs/test_spin_lock.c +++ b/tools/testing/selftests/bpf/progs/test_spin_lock.c @@ -10,30 +10,29 @@ struct hmap_elem { int test_padding; }; -struct bpf_map_def SEC("maps") hmap = { +struct { + __u32 type; + __u32 max_entries; + int *key; + struct hmap_elem *value; +} hmap SEC(".maps") = { .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(int), - .value_size = sizeof(struct hmap_elem), .max_entries = 1, }; -BPF_ANNOTATE_KV_PAIR(hmap, int, struct hmap_elem); - - struct cls_elem { struct bpf_spin_lock lock; volatile int cnt; }; -struct bpf_map_def SEC("maps") cls_map = { +struct { + __u32 type; + struct bpf_cgroup_storage_key *key; + struct cls_elem *value; +} cls_map SEC(".maps") = { .type = BPF_MAP_TYPE_CGROUP_STORAGE, - .key_size = sizeof(struct bpf_cgroup_storage_key), - .value_size = sizeof(struct cls_elem), }; -BPF_ANNOTATE_KV_PAIR(cls_map, struct bpf_cgroup_storage_key, - struct cls_elem); - struct bpf_vqueue { struct bpf_spin_lock lock; /* 4 byte hole */ @@ -42,14 +41,16 @@ struct bpf_vqueue { unsigned int rate; }; -struct bpf_map_def SEC("maps") vqueue = { +struct { + __u32 type; + __u32 max_entries; + int *key; + struct bpf_vqueue *value; +} vqueue SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(struct bpf_vqueue), .max_entries = 1, }; -BPF_ANNOTATE_KV_PAIR(vqueue, int, struct bpf_vqueue); #define CREDIT_PER_NS(delta, rate) (((delta) * rate) >> 20) SEC("spin_lock_demo") diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c index d86c281e957f..fcf2280bb60c 100644 --- a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c +++ b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c @@ -8,34 +8,50 @@ #define PERF_MAX_STACK_DEPTH 127 #endif -struct bpf_map_def SEC("maps") control_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} control_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = 1, }; -struct bpf_map_def SEC("maps") stackid_hmap = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} stackid_hmap SEC(".maps") = { .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = 16384, }; -struct bpf_map_def SEC("maps") stackmap = { +typedef struct bpf_stack_build_id stack_trace_t[PERF_MAX_STACK_DEPTH]; + +struct { + __u32 type; + __u32 max_entries; + __u32 map_flags; + __u32 key_size; + __u32 value_size; +} stackmap SEC(".maps") = { .type = BPF_MAP_TYPE_STACK_TRACE, - .key_size = sizeof(__u32), - .value_size = sizeof(struct bpf_stack_build_id) - * PERF_MAX_STACK_DEPTH, .max_entries = 128, .map_flags = BPF_F_STACK_BUILD_ID, + .key_size = sizeof(__u32), + .value_size = sizeof(stack_trace_t), }; -struct bpf_map_def SEC("maps") stack_amap = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + /* there seems to be a bug in kernel not handling typedef properly */ + struct bpf_stack_build_id (*value)[PERF_MAX_STACK_DEPTH]; +} stack_amap SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct bpf_stack_build_id) - * PERF_MAX_STACK_DEPTH, .max_entries = 128, }; diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c index af111af7ca1a..7ad09adbf648 100644 --- a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c +++ b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c @@ -8,31 +8,47 @@ #define PERF_MAX_STACK_DEPTH 127 #endif -struct bpf_map_def SEC("maps") control_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} control_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = 1, }; -struct bpf_map_def SEC("maps") stackid_hmap = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} stackid_hmap SEC(".maps") = { .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = 16384, }; -struct bpf_map_def SEC("maps") stackmap = { +typedef __u64 stack_trace_t[PERF_MAX_STACK_DEPTH]; + +struct { + __u32 type; + __u32 max_entries; + __u32 key_size; + __u32 value_size; +} stackmap SEC(".maps") = { .type = BPF_MAP_TYPE_STACK_TRACE, - .key_size = sizeof(__u32), - .value_size = sizeof(__u64) * PERF_MAX_STACK_DEPTH, .max_entries = 16384, + .key_size = sizeof(__u32), + .value_size = sizeof(stack_trace_t), }; -struct bpf_map_def SEC("maps") stack_amap = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u64 (*value)[PERF_MAX_STACK_DEPTH]; +} stack_amap SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u64) * PERF_MAX_STACK_DEPTH, .max_entries = 16384, }; diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c b/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c new file mode 100644 index 000000000000..608a06871572 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <stdint.h> +#include <string.h> + +#include <linux/stddef.h> +#include <linux/bpf.h> + +#include "bpf_helpers.h" + +#ifndef ARRAY_SIZE +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +/* tcp_mem sysctl has only 3 ints, but this test is doing TCP_MEM_LOOPS */ +#define TCP_MEM_LOOPS 28 /* because 30 doesn't fit into 512 bytes of stack */ +#define MAX_ULONG_STR_LEN 7 +#define MAX_VALUE_STR_LEN (TCP_MEM_LOOPS * MAX_ULONG_STR_LEN) + +static __always_inline int is_tcp_mem(struct bpf_sysctl *ctx) +{ + volatile char tcp_mem_name[] = "net/ipv4/tcp_mem/very_very_very_very_long_pointless_string"; + unsigned char i; + char name[64]; + int ret; + + memset(name, 0, sizeof(name)); + ret = bpf_sysctl_get_name(ctx, name, sizeof(name), 0); + if (ret < 0 || ret != sizeof(tcp_mem_name) - 1) + return 0; + +#pragma clang loop unroll(disable) + for (i = 0; i < sizeof(tcp_mem_name); ++i) + if (name[i] != tcp_mem_name[i]) + return 0; + + return 1; +} + +SEC("cgroup/sysctl") +int sysctl_tcp_mem(struct bpf_sysctl *ctx) +{ + unsigned long tcp_mem[TCP_MEM_LOOPS] = {}; + char value[MAX_VALUE_STR_LEN]; + unsigned char i, off = 0; + int ret; + + if (ctx->write) + return 0; + + if (!is_tcp_mem(ctx)) + return 0; + + ret = bpf_sysctl_get_current_value(ctx, value, MAX_VALUE_STR_LEN); + if (ret < 0 || ret >= MAX_VALUE_STR_LEN) + return 0; + +#pragma clang loop unroll(disable) + for (i = 0; i < ARRAY_SIZE(tcp_mem); ++i) { + ret = bpf_strtoul(value + off, MAX_ULONG_STR_LEN, 0, + tcp_mem + i); + if (ret <= 0 || ret > MAX_ULONG_STR_LEN) + return 0; + off += ret & MAX_ULONG_STR_LEN; + } + + return tcp_mem[0] < tcp_mem[1] && tcp_mem[1] < tcp_mem[2]; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c b/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c new file mode 100644 index 000000000000..cb201cbe11e7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <stdint.h> +#include <string.h> + +#include <linux/stddef.h> +#include <linux/bpf.h> + +#include "bpf_helpers.h" + +#ifndef ARRAY_SIZE +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +/* tcp_mem sysctl has only 3 ints, but this test is doing TCP_MEM_LOOPS */ +#define TCP_MEM_LOOPS 20 /* because 30 doesn't fit into 512 bytes of stack */ +#define MAX_ULONG_STR_LEN 7 +#define MAX_VALUE_STR_LEN (TCP_MEM_LOOPS * MAX_ULONG_STR_LEN) + +static __attribute__((noinline)) int is_tcp_mem(struct bpf_sysctl *ctx) +{ + volatile char tcp_mem_name[] = "net/ipv4/tcp_mem/very_very_very_very_long_pointless_string_to_stress_byte_loop"; + unsigned char i; + char name[64]; + int ret; + + memset(name, 0, sizeof(name)); + ret = bpf_sysctl_get_name(ctx, name, sizeof(name), 0); + if (ret < 0 || ret != sizeof(tcp_mem_name) - 1) + return 0; + +#pragma clang loop unroll(disable) + for (i = 0; i < sizeof(tcp_mem_name); ++i) + if (name[i] != tcp_mem_name[i]) + return 0; + + return 1; +} + + +SEC("cgroup/sysctl") +int sysctl_tcp_mem(struct bpf_sysctl *ctx) +{ + unsigned long tcp_mem[TCP_MEM_LOOPS] = {}; + char value[MAX_VALUE_STR_LEN]; + unsigned char i, off = 0; + int ret; + + if (ctx->write) + return 0; + + if (!is_tcp_mem(ctx)) + return 0; + + ret = bpf_sysctl_get_current_value(ctx, value, MAX_VALUE_STR_LEN); + if (ret < 0 || ret >= MAX_VALUE_STR_LEN) + return 0; + +#pragma clang loop unroll(disable) + for (i = 0; i < ARRAY_SIZE(tcp_mem); ++i) { + ret = bpf_strtoul(value + off, MAX_ULONG_STR_LEN, 0, + tcp_mem + i); + if (ret <= 0 || ret > MAX_ULONG_STR_LEN) + return 0; + off += ret & MAX_ULONG_STR_LEN; + } + + return tcp_mem[0] < tcp_mem[1] && tcp_mem[1] < tcp_mem[2]; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c index a295cad805d7..5cbbff416998 100644 --- a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c +++ b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c @@ -8,7 +8,6 @@ #include <linux/bpf.h> #include "bpf_helpers.h" -#include "bpf_util.h" /* Max supported length of a string with unsigned long in base 10 (pow2 - 1). */ #define MAX_ULONG_STR_LEN 0xF @@ -16,6 +15,10 @@ /* Max supported length of sysctl value string (pow2). */ #define MAX_VALUE_STR_LEN 0x40 +#ifndef ARRAY_SIZE +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + static __always_inline int is_tcp_mem(struct bpf_sysctl *ctx) { char tcp_mem_name[] = "net/ipv4/tcp_mem"; diff --git a/tools/testing/selftests/bpf/progs/test_tcp_estats.c b/tools/testing/selftests/bpf/progs/test_tcp_estats.c index bee3bbecc0c4..df98f7e32832 100644 --- a/tools/testing/selftests/bpf/progs/test_tcp_estats.c +++ b/tools/testing/selftests/bpf/progs/test_tcp_estats.c @@ -148,10 +148,13 @@ struct tcp_estats_basic_event { struct tcp_estats_conn_id conn_id; }; -struct bpf_map_def SEC("maps") ev_record_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct tcp_estats_basic_event *value; +} ev_record_map SEC(".maps") = { .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(__u32), - .value_size = sizeof(struct tcp_estats_basic_event), .max_entries = 1024, }; diff --git a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c index c7c3240e0dd4..38e10c9fd996 100644 --- a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c @@ -14,17 +14,23 @@ #include "bpf_endian.h" #include "test_tcpbpf.h" -struct bpf_map_def SEC("maps") global_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct tcpbpf_globals *value; +} global_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct tcpbpf_globals), .max_entries = 4, }; -struct bpf_map_def SEC("maps") sockopt_results = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + int *value; +} sockopt_results SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(int), .max_entries = 2, }; diff --git a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c index ec6db6e64c41..d073d37d4e27 100644 --- a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c @@ -14,18 +14,26 @@ #include "bpf_endian.h" #include "test_tcpnotify.h" -struct bpf_map_def SEC("maps") global_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct tcpnotify_globals *value; +} global_map SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct tcpnotify_globals), .max_entries = 4, }; -struct bpf_map_def SEC("maps") perf_event_map = { +struct { + __u32 type; + __u32 max_entries; + __u32 key_size; + __u32 value_size; +} perf_event_map SEC(".maps") = { .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, + .max_entries = 2, .key_size = sizeof(int), .value_size = sizeof(__u32), - .max_entries = 2, }; int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_xdp.c b/tools/testing/selftests/bpf/progs/test_xdp.c index 5e7df8bb5b5d..ec3d2c1c8cf9 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp.c +++ b/tools/testing/selftests/bpf/progs/test_xdp.c @@ -22,17 +22,23 @@ int _version SEC("version") = 1; -struct bpf_map_def SEC("maps") rxcnt = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u64 *value; +} rxcnt SEC(".maps") = { .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u64), .max_entries = 256, }; -struct bpf_map_def SEC("maps") vip2tnl = { +struct { + __u32 type; + __u32 max_entries; + struct vip *key; + struct iptnl_info *value; +} vip2tnl SEC(".maps") = { .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(struct vip), - .value_size = sizeof(struct iptnl_info), .max_entries = MAX_IPTNL_ENTRIES, }; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_loop.c b/tools/testing/selftests/bpf/progs/test_xdp_loop.c new file mode 100644 index 000000000000..7fa4677df22e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_loop.c @@ -0,0 +1,231 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <stddef.h> +#include <string.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/in.h> +#include <linux/udp.h> +#include <linux/tcp.h> +#include <linux/pkt_cls.h> +#include <sys/socket.h> +#include "bpf_helpers.h" +#include "bpf_endian.h" +#include "test_iptunnel_common.h" + +int _version SEC("version") = 1; + +struct bpf_map_def SEC("maps") rxcnt = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(__u64), + .max_entries = 256, +}; + +struct bpf_map_def SEC("maps") vip2tnl = { + .type = BPF_MAP_TYPE_HASH, + .key_size = sizeof(struct vip), + .value_size = sizeof(struct iptnl_info), + .max_entries = MAX_IPTNL_ENTRIES, +}; + +static __always_inline void count_tx(__u32 protocol) +{ + __u64 *rxcnt_count; + + rxcnt_count = bpf_map_lookup_elem(&rxcnt, &protocol); + if (rxcnt_count) + *rxcnt_count += 1; +} + +static __always_inline int get_dport(void *trans_data, void *data_end, + __u8 protocol) +{ + struct tcphdr *th; + struct udphdr *uh; + + switch (protocol) { + case IPPROTO_TCP: + th = (struct tcphdr *)trans_data; + if (th + 1 > data_end) + return -1; + return th->dest; + case IPPROTO_UDP: + uh = (struct udphdr *)trans_data; + if (uh + 1 > data_end) + return -1; + return uh->dest; + default: + return 0; + } +} + +static __always_inline void set_ethhdr(struct ethhdr *new_eth, + const struct ethhdr *old_eth, + const struct iptnl_info *tnl, + __be16 h_proto) +{ + memcpy(new_eth->h_source, old_eth->h_dest, sizeof(new_eth->h_source)); + memcpy(new_eth->h_dest, tnl->dmac, sizeof(new_eth->h_dest)); + new_eth->h_proto = h_proto; +} + +static __always_inline int handle_ipv4(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct iptnl_info *tnl; + struct ethhdr *new_eth; + struct ethhdr *old_eth; + struct iphdr *iph = data + sizeof(struct ethhdr); + __u16 *next_iph; + __u16 payload_len; + struct vip vip = {}; + int dport; + __u32 csum = 0; + int i; + + if (iph + 1 > data_end) + return XDP_DROP; + + dport = get_dport(iph + 1, data_end, iph->protocol); + if (dport == -1) + return XDP_DROP; + + vip.protocol = iph->protocol; + vip.family = AF_INET; + vip.daddr.v4 = iph->daddr; + vip.dport = dport; + payload_len = bpf_ntohs(iph->tot_len); + + tnl = bpf_map_lookup_elem(&vip2tnl, &vip); + /* It only does v4-in-v4 */ + if (!tnl || tnl->family != AF_INET) + return XDP_PASS; + + if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct iphdr))) + return XDP_DROP; + + data = (void *)(long)xdp->data; + data_end = (void *)(long)xdp->data_end; + + new_eth = data; + iph = data + sizeof(*new_eth); + old_eth = data + sizeof(*iph); + + if (new_eth + 1 > data_end || + old_eth + 1 > data_end || + iph + 1 > data_end) + return XDP_DROP; + + set_ethhdr(new_eth, old_eth, tnl, bpf_htons(ETH_P_IP)); + + iph->version = 4; + iph->ihl = sizeof(*iph) >> 2; + iph->frag_off = 0; + iph->protocol = IPPROTO_IPIP; + iph->check = 0; + iph->tos = 0; + iph->tot_len = bpf_htons(payload_len + sizeof(*iph)); + iph->daddr = tnl->daddr.v4; + iph->saddr = tnl->saddr.v4; + iph->ttl = 8; + + next_iph = (__u16 *)iph; +#pragma clang loop unroll(disable) + for (i = 0; i < sizeof(*iph) >> 1; i++) + csum += *next_iph++; + + iph->check = ~((csum & 0xffff) + (csum >> 16)); + + count_tx(vip.protocol); + + return XDP_TX; +} + +static __always_inline int handle_ipv6(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct iptnl_info *tnl; + struct ethhdr *new_eth; + struct ethhdr *old_eth; + struct ipv6hdr *ip6h = data + sizeof(struct ethhdr); + __u16 payload_len; + struct vip vip = {}; + int dport; + + if (ip6h + 1 > data_end) + return XDP_DROP; + + dport = get_dport(ip6h + 1, data_end, ip6h->nexthdr); + if (dport == -1) + return XDP_DROP; + + vip.protocol = ip6h->nexthdr; + vip.family = AF_INET6; + memcpy(vip.daddr.v6, ip6h->daddr.s6_addr32, sizeof(vip.daddr)); + vip.dport = dport; + payload_len = ip6h->payload_len; + + tnl = bpf_map_lookup_elem(&vip2tnl, &vip); + /* It only does v6-in-v6 */ + if (!tnl || tnl->family != AF_INET6) + return XDP_PASS; + + if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct ipv6hdr))) + return XDP_DROP; + + data = (void *)(long)xdp->data; + data_end = (void *)(long)xdp->data_end; + + new_eth = data; + ip6h = data + sizeof(*new_eth); + old_eth = data + sizeof(*ip6h); + + if (new_eth + 1 > data_end || old_eth + 1 > data_end || + ip6h + 1 > data_end) + return XDP_DROP; + + set_ethhdr(new_eth, old_eth, tnl, bpf_htons(ETH_P_IPV6)); + + ip6h->version = 6; + ip6h->priority = 0; + memset(ip6h->flow_lbl, 0, sizeof(ip6h->flow_lbl)); + ip6h->payload_len = bpf_htons(bpf_ntohs(payload_len) + sizeof(*ip6h)); + ip6h->nexthdr = IPPROTO_IPV6; + ip6h->hop_limit = 8; + memcpy(ip6h->saddr.s6_addr32, tnl->saddr.v6, sizeof(tnl->saddr.v6)); + memcpy(ip6h->daddr.s6_addr32, tnl->daddr.v6, sizeof(tnl->daddr.v6)); + + count_tx(vip.protocol); + + return XDP_TX; +} + +SEC("xdp_tx_iptunnel") +int _xdp_tx_iptunnel(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct ethhdr *eth = data; + __u16 h_proto; + + if (eth + 1 > data_end) + return XDP_DROP; + + h_proto = eth->h_proto; + + if (h_proto == bpf_htons(ETH_P_IP)) + return handle_ipv4(xdp); + else if (h_proto == bpf_htons(ETH_P_IPV6)) + + return handle_ipv6(xdp); + else + return XDP_DROP; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c index 5e4aac74f9d0..d2eddb5553d1 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c @@ -15,13 +15,6 @@ #include <linux/udp.h> #include "bpf_helpers.h" -#define bpf_printk(fmt, ...) \ -({ \ - char ____fmt[] = fmt; \ - bpf_trace_printk(____fmt, sizeof(____fmt), \ - ##__VA_ARGS__); \ -}) - static __u32 rol32(__u32 word, unsigned int shift) { return (word << shift) | (word >> ((-shift) & 31)); @@ -170,52 +163,66 @@ struct lb_stats { __u64 v1; }; -struct bpf_map_def __attribute__ ((section("maps"), used)) vip_map = { +struct { + __u32 type; + __u32 max_entries; + struct vip_definition *key; + struct vip_meta *value; +} vip_map SEC(".maps") = { .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(struct vip_definition), - .value_size = sizeof(struct vip_meta), .max_entries = 512, - .map_flags = 0, }; -struct bpf_map_def __attribute__ ((section("maps"), used)) lru_cache = { +struct { + __u32 type; + __u32 max_entries; + __u32 map_flags; + struct flow_key *key; + struct real_pos_lru *value; +} lru_cache SEC(".maps") = { .type = BPF_MAP_TYPE_LRU_HASH, - .key_size = sizeof(struct flow_key), - .value_size = sizeof(struct real_pos_lru), .max_entries = 300, .map_flags = 1U << 1, }; -struct bpf_map_def __attribute__ ((section("maps"), used)) ch_rings = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + __u32 *value; +} ch_rings SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), .max_entries = 12 * 655, - .map_flags = 0, }; -struct bpf_map_def __attribute__ ((section("maps"), used)) reals = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct real_definition *value; +} reals SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct real_definition), .max_entries = 40, - .map_flags = 0, }; -struct bpf_map_def __attribute__ ((section("maps"), used)) stats = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct lb_stats *value; +} stats SEC(".maps") = { .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct lb_stats), .max_entries = 515, - .map_flags = 0, }; -struct bpf_map_def __attribute__ ((section("maps"), used)) ctl_array = { +struct { + __u32 type; + __u32 max_entries; + __u32 *key; + struct ctl_value *value; +} ctl_array SEC(".maps") = { .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct ctl_value), .max_entries = 16, - .map_flags = 0, }; struct eth_hdr { diff --git a/tools/testing/selftests/bpf/progs/xdping_kern.c b/tools/testing/selftests/bpf/progs/xdping_kern.c new file mode 100644 index 000000000000..87393e7c667c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/xdping_kern.c @@ -0,0 +1,184 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019, Oracle and/or its affiliates. All rights reserved. */ + +#define KBUILD_MODNAME "foo" +#include <stddef.h> +#include <string.h> +#include <linux/bpf.h> +#include <linux/icmp.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/if_vlan.h> +#include <linux/ip.h> + +#include "bpf_helpers.h" +#include "bpf_endian.h" + +#include "xdping.h" + +struct bpf_map_def SEC("maps") ping_map = { + .type = BPF_MAP_TYPE_HASH, + .key_size = sizeof(__u32), + .value_size = sizeof(struct pinginfo), + .max_entries = 256, +}; + +static __always_inline void swap_src_dst_mac(void *data) +{ + unsigned short *p = data; + unsigned short dst[3]; + + dst[0] = p[0]; + dst[1] = p[1]; + dst[2] = p[2]; + p[0] = p[3]; + p[1] = p[4]; + p[2] = p[5]; + p[3] = dst[0]; + p[4] = dst[1]; + p[5] = dst[2]; +} + +static __always_inline __u16 csum_fold_helper(__wsum sum) +{ + sum = (sum & 0xffff) + (sum >> 16); + return ~((sum & 0xffff) + (sum >> 16)); +} + +static __always_inline __u16 ipv4_csum(void *data_start, int data_size) +{ + __wsum sum; + + sum = bpf_csum_diff(0, 0, data_start, data_size, 0); + return csum_fold_helper(sum); +} + +#define ICMP_ECHO_LEN 64 + +static __always_inline int icmp_check(struct xdp_md *ctx, int type) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ethhdr *eth = data; + struct icmphdr *icmph; + struct iphdr *iph; + + if (data + sizeof(*eth) + sizeof(*iph) + ICMP_ECHO_LEN > data_end) + return XDP_PASS; + + if (eth->h_proto != bpf_htons(ETH_P_IP)) + return XDP_PASS; + + iph = data + sizeof(*eth); + + if (iph->protocol != IPPROTO_ICMP) + return XDP_PASS; + + if (bpf_ntohs(iph->tot_len) - sizeof(*iph) != ICMP_ECHO_LEN) + return XDP_PASS; + + icmph = data + sizeof(*eth) + sizeof(*iph); + + if (icmph->type != type) + return XDP_PASS; + + return XDP_TX; +} + +SEC("xdpclient") +int xdping_client(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct pinginfo *pinginfo = NULL; + struct ethhdr *eth = data; + struct icmphdr *icmph; + struct iphdr *iph; + __u64 recvtime; + __be32 raddr; + __be16 seq; + int ret; + __u8 i; + + ret = icmp_check(ctx, ICMP_ECHOREPLY); + + if (ret != XDP_TX) + return ret; + + iph = data + sizeof(*eth); + icmph = data + sizeof(*eth) + sizeof(*iph); + raddr = iph->saddr; + + /* Record time reply received. */ + recvtime = bpf_ktime_get_ns(); + pinginfo = bpf_map_lookup_elem(&ping_map, &raddr); + if (!pinginfo || pinginfo->seq != icmph->un.echo.sequence) + return XDP_PASS; + + if (pinginfo->start) { +#pragma clang loop unroll(full) + for (i = 0; i < XDPING_MAX_COUNT; i++) { + if (pinginfo->times[i] == 0) + break; + } + /* verifier is fussy here... */ + if (i < XDPING_MAX_COUNT) { + pinginfo->times[i] = recvtime - + pinginfo->start; + pinginfo->start = 0; + i++; + } + /* No more space for values? */ + if (i == pinginfo->count || i == XDPING_MAX_COUNT) + return XDP_PASS; + } + + /* Now convert reply back into echo request. */ + swap_src_dst_mac(data); + iph->saddr = iph->daddr; + iph->daddr = raddr; + icmph->type = ICMP_ECHO; + seq = bpf_htons(bpf_ntohs(icmph->un.echo.sequence) + 1); + icmph->un.echo.sequence = seq; + icmph->checksum = 0; + icmph->checksum = ipv4_csum(icmph, ICMP_ECHO_LEN); + + pinginfo->seq = seq; + pinginfo->start = bpf_ktime_get_ns(); + + return XDP_TX; +} + +SEC("xdpserver") +int xdping_server(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ethhdr *eth = data; + struct icmphdr *icmph; + struct iphdr *iph; + __be32 raddr; + int ret; + + ret = icmp_check(ctx, ICMP_ECHO); + + if (ret != XDP_TX) + return ret; + + iph = data + sizeof(*eth); + icmph = data + sizeof(*eth) + sizeof(*iph); + raddr = iph->saddr; + + /* Now convert request into echo reply. */ + swap_src_dst_mac(data); + iph->saddr = iph->daddr; + iph->daddr = raddr; + icmph->type = ICMP_ECHOREPLY; + icmph->checksum = 0; + icmph->checksum = ipv4_csum(icmph, ICMP_ECHO_LEN); + + return XDP_TX; +} + +char _license[] SEC("license") = "GPL"; |