From ecd435143eb03611e25694141bf59d1c04ad5b9e Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 30 Nov 2023 10:52:24 -0800 Subject: libbpf: add bpf_token_create() API Add low-level wrapper API for BPF_TOKEN_CREATE command in bpf() syscall. Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20231130185229.2688956-13-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- tools/lib/bpf/bpf.c | 17 +++++++++++++++++ tools/lib/bpf/bpf.h | 24 ++++++++++++++++++++++++ tools/lib/bpf/libbpf.map | 1 + 3 files changed, 42 insertions(+) (limited to 'tools/lib') diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 9dc9625651dc..d4019928a864 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -1287,3 +1287,20 @@ int bpf_prog_bind_map(int prog_fd, int map_fd, ret = sys_bpf(BPF_PROG_BIND_MAP, &attr, attr_sz); return libbpf_err_errno(ret); } + +int bpf_token_create(int bpffs_fd, struct bpf_token_create_opts *opts) +{ + const size_t attr_sz = offsetofend(union bpf_attr, token_create); + union bpf_attr attr; + int fd; + + if (!OPTS_VALID(opts, bpf_token_create_opts)) + return libbpf_err(-EINVAL); + + memset(&attr, 0, attr_sz); + attr.token_create.bpffs_fd = bpffs_fd; + attr.token_create.flags = OPTS_GET(opts, flags, 0); + + fd = sys_bpf_fd(BPF_TOKEN_CREATE, &attr, attr_sz); + return libbpf_err_errno(fd); +} diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index d0f53772bdc0..e49254c9f68f 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -640,6 +640,30 @@ struct bpf_test_run_opts { LIBBPF_API int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts); +struct bpf_token_create_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + __u32 flags; + size_t :0; +}; +#define bpf_token_create_opts__last_field flags + +/** + * @brief **bpf_token_create()** creates a new instance of BPF token derived + * from specified BPF FS mount point. + * + * BPF token created with this API can be passed to bpf() syscall for + * commands like BPF_PROG_LOAD, BPF_MAP_CREATE, etc. + * + * @param bpffs_fd FD for BPF FS instance from which to derive a BPF token + * instance. + * @param opts optional BPF token creation options, can be NULL + * + * @return BPF token FD > 0, on success; negative error code, otherwise (errno + * is also set to the error code) + */ +LIBBPF_API int bpf_token_create(int bpffs_fd, + struct bpf_token_create_opts *opts); + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 91c5aef7dae7..df7657b65c47 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -401,6 +401,7 @@ LIBBPF_1.3.0 { bpf_program__attach_netkit; bpf_program__attach_tcx; bpf_program__attach_uprobe_multi; + bpf_token_create; ring__avail_data_size; ring__consume; ring__consumer_pos; -- cgit v1.2.3 From 37891cea6699200fb83eae464ebe1c0f73040474 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 30 Nov 2023 10:52:25 -0800 Subject: libbpf: add BPF token support to bpf_map_create() API Add ability to provide token_fd for BPF_MAP_CREATE command through bpf_map_create() API. Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20231130185229.2688956-14-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- tools/lib/bpf/bpf.c | 4 +++- tools/lib/bpf/bpf.h | 5 ++++- 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'tools/lib') diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index d4019928a864..1653b64b7015 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -169,7 +169,7 @@ int bpf_map_create(enum bpf_map_type map_type, __u32 max_entries, const struct bpf_map_create_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, map_extra); + const size_t attr_sz = offsetofend(union bpf_attr, map_token_fd); union bpf_attr attr; int fd; @@ -198,6 +198,8 @@ int bpf_map_create(enum bpf_map_type map_type, attr.numa_node = OPTS_GET(opts, numa_node, 0); attr.map_ifindex = OPTS_GET(opts, map_ifindex, 0); + attr.map_token_fd = OPTS_GET(opts, token_fd, 0); + fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, attr_sz); return libbpf_err_errno(fd); } diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index e49254c9f68f..ae2136f596b4 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -51,8 +51,11 @@ struct bpf_map_create_opts { __u32 numa_node; __u32 map_ifindex; + + __u32 token_fd; + size_t :0; }; -#define bpf_map_create_opts__last_field map_ifindex +#define bpf_map_create_opts__last_field token_fd LIBBPF_API int bpf_map_create(enum bpf_map_type map_type, const char *map_name, -- cgit v1.2.3 From 1a8df7fa00aac35aff9ef1941c5334b3a01d09e4 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 30 Nov 2023 10:52:26 -0800 Subject: libbpf: add BPF token support to bpf_btf_load() API Allow user to specify token_fd for bpf_btf_load() API that wraps kernel's BPF_BTF_LOAD command. This allows loading BTF from unprivileged process as long as it has BPF token allowing BPF_BTF_LOAD command, which can be created and delegated by privileged process. Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20231130185229.2688956-15-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- tools/lib/bpf/bpf.c | 4 +++- tools/lib/bpf/bpf.h | 3 ++- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'tools/lib') diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 1653b64b7015..544ae2376b6b 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -1184,7 +1184,7 @@ int bpf_raw_tracepoint_open(const char *name, int prog_fd) int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, btf_log_true_size); + const size_t attr_sz = offsetofend(union bpf_attr, btf_token_fd); union bpf_attr attr; char *log_buf; size_t log_size; @@ -1209,6 +1209,8 @@ int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts attr.btf = ptr_to_u64(btf_data); attr.btf_size = btf_size; + attr.btf_token_fd = OPTS_GET(opts, token_fd, 0); + /* log_level == 0 and log_buf != NULL means "try loading without * log_buf, but retry with log_buf and log_level=1 on error", which is * consistent across low-level and high-level BTF and program loading diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index ae2136f596b4..4b0f25e97b0d 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -133,9 +133,10 @@ struct bpf_btf_load_opts { * If kernel doesn't support this feature, log_size is left unchanged. */ __u32 log_true_size; + __u32 token_fd; size_t :0; }; -#define bpf_btf_load_opts__last_field log_true_size +#define bpf_btf_load_opts__last_field token_fd LIBBPF_API int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts *opts); -- cgit v1.2.3 From 1571740a9ba036f26cc5211a86021199987219e8 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 30 Nov 2023 10:52:27 -0800 Subject: libbpf: add BPF token support to bpf_prog_load() API Wire through token_fd into bpf_prog_load(). Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20231130185229.2688956-16-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- tools/lib/bpf/bpf.c | 3 ++- tools/lib/bpf/bpf.h | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'tools/lib') diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 544ae2376b6b..f4e1da3c6d5f 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -234,7 +234,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, size_t insn_cnt, struct bpf_prog_load_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, log_true_size); + const size_t attr_sz = offsetofend(union bpf_attr, prog_token_fd); void *finfo = NULL, *linfo = NULL; const char *func_info, *line_info; __u32 log_size, log_level, attach_prog_fd, attach_btf_obj_fd; @@ -263,6 +263,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type, attr.prog_flags = OPTS_GET(opts, prog_flags, 0); attr.prog_ifindex = OPTS_GET(opts, prog_ifindex, 0); attr.kern_version = OPTS_GET(opts, kern_version, 0); + attr.prog_token_fd = OPTS_GET(opts, token_fd, 0); if (prog_name && kernel_supports(NULL, FEAT_PROG_NAME)) libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name)); diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 4b0f25e97b0d..991b86bfe7e4 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -105,9 +105,10 @@ struct bpf_prog_load_opts { * If kernel doesn't support this feature, log_size is left unchanged. */ __u32 log_true_size; + __u32 token_fd; size_t :0; }; -#define bpf_prog_load_opts__last_field log_true_size +#define bpf_prog_load_opts__last_field token_fd LIBBPF_API int bpf_prog_load(enum bpf_prog_type prog_type, const char *prog_name, const char *license, -- cgit v1.2.3 From 8b7b0e5fe47de90ba6c350f9abece589fb637f79 Mon Sep 17 00:00:00 2001 From: David Vernet Date: Fri, 8 Dec 2023 00:17:03 -0600 Subject: bpf: Load vmlinux btf for any struct_ops map In libbpf, when determining whether we need to load vmlinux btf, we're currently (among other things) checking whether there is any struct_ops program present in the object. This works for most realistic struct_ops maps, as a struct_ops map is of course typically composed of one or more struct_ops programs. However, that technically need not be the case. A struct_ops interface could be defined which allows a map to be specified which one or more non-prog fields, and which provides default behavior if no struct_ops progs is actually provided otherwise. For sched_ext, for example, you technically only need to specify the name of the scheduler in the struct_ops map, with the core scheduler logic providing default behavior if no prog is actually specified. If we were to define and try to load such a struct_ops map, we would crash in libbpf when initializing it as obj->btf_vmlinux will be NULL: Reading symbols from minimal... (gdb) r Starting program: minimal_example [Thread debugging using libthread_db enabled] Using host libthread_db library "/usr/lib/libthread_db.so.1". Program received signal SIGSEGV, Segmentation fault. 0x000055555558308c in btf__type_cnt (btf=0x0) at btf.c:612 612 return btf->start_id + btf->nr_types; (gdb) bt type_name=0x5555555d99e3 "sched_ext_ops", kind=4) at btf.c:914 kind=4) at btf.c:942 type=0x7fffffffe558, type_id=0x7fffffffe548, ... data_member=0x7fffffffe568) at libbpf.c:948 kern_btf=0x0) at libbpf.c:1017 at libbpf.c:8059 So as to account for such bare-bones struct_ops maps, let's update obj_needs_vmlinux_btf() to also iterate over an obj's maps and check whether any of them are struct_ops maps. Signed-off-by: David Vernet Signed-off-by: Andrii Nakryiko Reviewed-by: Alan Maguire Link: https://lore.kernel.org/bpf/20231208061704.400463-1-void@manifault.com --- tools/lib/bpf/libbpf.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'tools/lib') diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index ea9b8158c20d..ac54ebc0629f 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -3054,9 +3054,15 @@ static bool prog_needs_vmlinux_btf(struct bpf_program *prog) return false; } +static bool map_needs_vmlinux_btf(struct bpf_map *map) +{ + return bpf_map__is_struct_ops(map); +} + static bool obj_needs_vmlinux_btf(const struct bpf_object *obj) { struct bpf_program *prog; + struct bpf_map *map; int i; /* CO-RE relocations need kernel BTF, only when btf_custom_path @@ -3081,6 +3087,11 @@ static bool obj_needs_vmlinux_btf(const struct bpf_object *obj) return true; } + bpf_object__for_each_map(map, obj) { + if (map_needs_vmlinux_btf(map)) + return true; + } + return false; } -- cgit v1.2.3 From 32fa058398624166dd04ff4af49cfef69c94abbc Mon Sep 17 00:00:00 2001 From: Sergei Trofimovich Date: Fri, 8 Dec 2023 21:51:00 +0000 Subject: libbpf: Add pr_warn() for EINVAL cases in linker_sanity_check_elf Before the change on `i686-linux` `systemd` build failed as: $ bpftool gen object src/core/bpf/socket_bind/socket-bind.bpf.o src/core/bpf/socket_bind/socket-bind.bpf.unstripped.o Error: failed to link 'src/core/bpf/socket_bind/socket-bind.bpf.unstripped.o': Invalid argument (22) After the change it fails as: $ bpftool gen object src/core/bpf/socket_bind/socket-bind.bpf.o src/core/bpf/socket_bind/socket-bind.bpf.unstripped.o libbpf: ELF section #9 has inconsistent alignment addr=8 != d=4 in src/core/bpf/socket_bind/socket-bind.bpf.unstripped.o Error: failed to link 'src/core/bpf/socket_bind/socket-bind.bpf.unstripped.o': Invalid argument (22) Now it's slightly easier to figure out what is wrong with an ELF file. Signed-off-by: Sergei Trofimovich Signed-off-by: Andrii Nakryiko Acked-by: Eduard Zingerman Link: https://lore.kernel.org/bpf/20231208215100.435876-1-slyich@gmail.com --- tools/lib/bpf/linker.c | 24 ++++++++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-) (limited to 'tools/lib') diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index 5ced96d99f8c..52a2901e8bd0 100644 --- a/tools/lib/bpf/linker.c +++ b/tools/lib/bpf/linker.c @@ -719,13 +719,25 @@ static int linker_sanity_check_elf(struct src_obj *obj) return -EINVAL; } - if (sec->shdr->sh_addralign && !is_pow_of_2(sec->shdr->sh_addralign)) + if (sec->shdr->sh_addralign && !is_pow_of_2(sec->shdr->sh_addralign)) { + pr_warn("ELF section #%zu alignment %llu is non pow-of-2 alignment in %s\n", + sec->sec_idx, (long long unsigned)sec->shdr->sh_addralign, + obj->filename); return -EINVAL; - if (sec->shdr->sh_addralign != sec->data->d_align) + } + if (sec->shdr->sh_addralign != sec->data->d_align) { + pr_warn("ELF section #%zu has inconsistent alignment addr=%llu != d=%llu in %s\n", + sec->sec_idx, (long long unsigned)sec->shdr->sh_addralign, + (long long unsigned)sec->data->d_align, obj->filename); return -EINVAL; + } - if (sec->shdr->sh_size != sec->data->d_size) + if (sec->shdr->sh_size != sec->data->d_size) { + pr_warn("ELF section #%zu has inconsistent section size sh=%llu != d=%llu in %s\n", + sec->sec_idx, (long long unsigned)sec->shdr->sh_size, + (long long unsigned)sec->data->d_size, obj->filename); return -EINVAL; + } switch (sec->shdr->sh_type) { case SHT_SYMTAB: @@ -737,8 +749,12 @@ static int linker_sanity_check_elf(struct src_obj *obj) break; case SHT_PROGBITS: if (sec->shdr->sh_flags & SHF_EXECINSTR) { - if (sec->shdr->sh_size % sizeof(struct bpf_insn) != 0) + if (sec->shdr->sh_size % sizeof(struct bpf_insn) != 0) { + pr_warn("ELF section #%zu has unexpected size alignment %llu in %s\n", + sec->sec_idx, (long long unsigned)sec->shdr->sh_size, + obj->filename); return -EINVAL; + } } break; case SHT_NOBITS: -- cgit v1.2.3 From 2f70803532e9b7f14897d17f8944d431755661a7 Mon Sep 17 00:00:00 2001 From: Daniel Xu Date: Mon, 11 Dec 2023 13:20:07 -0700 Subject: libbpf: Add BPF_CORE_WRITE_BITFIELD() macro === Motivation === Similar to reading from CO-RE bitfields, we need a CO-RE aware bitfield writing wrapper to make the verifier happy. Two alternatives to this approach are: 1. Use the upcoming `preserve_static_offset` [0] attribute to disable CO-RE on specific structs. 2. Use broader byte-sized writes to write to bitfields. (1) is a bit hard to use. It requires specific and not-very-obvious annotations to bpftool generated vmlinux.h. It's also not generally available in released LLVM versions yet. (2) makes the code quite hard to read and write. And especially if BPF_CORE_READ_BITFIELD() is already being used, it makes more sense to to have an inverse helper for writing. === Implementation details === Since the logic is a bit non-obvious, I thought it would be helpful to explain exactly what's going on. To start, it helps by explaining what LSHIFT_U64 (lshift) and RSHIFT_U64 (rshift) is designed to mean. Consider the core of the BPF_CORE_READ_BITFIELD() algorithm: val <<= __CORE_RELO(s, field, LSHIFT_U64); val = val >> __CORE_RELO(s, field, RSHIFT_U64); Basically what happens is we lshift to clear the non-relevant (blank) higher order bits. Then we rshift to bring the relevant bits (bitfield) down to LSB position (while also clearing blank lower order bits). To illustrate: Start: ........XXX...... Lshift: XXX......00000000 Rshift: 00000000000000XXX where `.` means blank bit, `0` means 0 bit, and `X` means bitfield bit. After the two operations, the bitfield is ready to be interpreted as a regular integer. Next, we want to build an alternative (but more helpful) mental model on lshift and rshift. That is, to consider: * rshift as the total number of blank bits in the u64 * lshift as number of blank bits left of the bitfield in the u64 Take a moment to consider why that is true by consulting the above diagram. With this insight, we can now define the following relationship: bitfield _ | | 0.....00XXX0...00 | | | | |______| | | lshift | | |____| (rshift - lshift) That is, we know the number of higher order blank bits is just lshift. And the number of lower order blank bits is (rshift - lshift). Finally, we can examine the core of the write side algorithm: mask = (~0ULL << rshift) >> lshift; // 1 val = (val & ~mask) | ((nval << rpad) & mask); // 2 1. Compute a mask where the set bits are the bitfield bits. The first left shift zeros out exactly the number of blank bits, leaving a bitfield sized set of 1s. The subsequent right shift inserts the correct amount of higher order blank bits. 2. On the left of the `|`, mask out the bitfield bits. This creates 0s where the new bitfield bits will go. On the right of the `|`, bring nval into the correct bit position and mask out any bits that fall outside of the bitfield. Finally, by bor'ing the two halves, we get the final set of bits to write back. [0]: https://reviews.llvm.org/D133361 Co-developed-by: Eduard Zingerman Signed-off-by: Eduard Zingerman Co-developed-by: Jonathan Lemon Signed-off-by: Jonathan Lemon Acked-by: Andrii Nakryiko Signed-off-by: Daniel Xu Link: https://lore.kernel.org/r/4d3dd215a4fd57d980733886f9c11a45e1a9adf3.1702325874.git.dxu@dxuuu.xyz Signed-off-by: Martin KaFai Lau --- tools/lib/bpf/bpf_core_read.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'tools/lib') diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h index 1ac57bb7ac55..7325a12692a3 100644 --- a/tools/lib/bpf/bpf_core_read.h +++ b/tools/lib/bpf/bpf_core_read.h @@ -111,6 +111,38 @@ enum bpf_enum_value_kind { val; \ }) +/* + * Write to a bitfield, identified by s->field. + * This is the inverse of BPF_CORE_WRITE_BITFIELD(). + */ +#define BPF_CORE_WRITE_BITFIELD(s, field, new_val) ({ \ + void *p = (void *)s + __CORE_RELO(s, field, BYTE_OFFSET); \ + unsigned int byte_size = __CORE_RELO(s, field, BYTE_SIZE); \ + unsigned int lshift = __CORE_RELO(s, field, LSHIFT_U64); \ + unsigned int rshift = __CORE_RELO(s, field, RSHIFT_U64); \ + unsigned long long mask, val, nval = new_val; \ + unsigned int rpad = rshift - lshift; \ + \ + asm volatile("" : "+r"(p)); \ + \ + switch (byte_size) { \ + case 1: val = *(unsigned char *)p; break; \ + case 2: val = *(unsigned short *)p; break; \ + case 4: val = *(unsigned int *)p; break; \ + case 8: val = *(unsigned long long *)p; break; \ + } \ + \ + mask = (~0ULL << rshift) >> lshift; \ + val = (val & ~mask) | ((nval << rpad) & mask); \ + \ + switch (byte_size) { \ + case 1: *(unsigned char *)p = val; break; \ + case 2: *(unsigned short *)p = val; break; \ + case 4: *(unsigned int *)p = val; break; \ + case 8: *(unsigned long long *)p = val; break; \ + } \ +}) + #define ___bpf_field_ref1(field) (field) #define ___bpf_field_ref2(type, field) (((typeof(type) *)0)->field) #define ___bpf_field_ref(args...) \ -- cgit v1.2.3 From c6c5be3eee975ae640966844db66d404c1de79b1 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Wed, 13 Dec 2023 11:08:34 -0800 Subject: libbpf: split feature detectors definitions from cached results Split a list of supported feature detectors with their corresponding callbacks from actual cached supported/missing values. This will allow to have more flexible per-token or per-object feature detectors in subsequent refactorings. Acked-by: John Fastabend Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20231213190842.3844987-3-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- tools/lib/bpf/libbpf.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) (limited to 'tools/lib') diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index ac54ebc0629f..d2828a26b011 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -4999,12 +4999,17 @@ enum kern_feature_result { FEAT_MISSING = 2, }; +struct kern_feature_cache { + enum kern_feature_result res[__FEAT_CNT]; +}; + typedef int (*feature_probe_fn)(void); +static struct kern_feature_cache feature_cache; + static struct kern_feature_desc { const char *desc; feature_probe_fn probe; - enum kern_feature_result res; } feature_probes[__FEAT_CNT] = { [FEAT_PROG_NAME] = { "BPF program name", probe_kern_prog_name, @@ -5072,6 +5077,7 @@ static struct kern_feature_desc { bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id) { struct kern_feature_desc *feat = &feature_probes[feat_id]; + struct kern_feature_cache *cache = &feature_cache; int ret; if (obj && obj->gen_loader) @@ -5080,19 +5086,19 @@ bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id) */ return true; - if (READ_ONCE(feat->res) == FEAT_UNKNOWN) { + if (READ_ONCE(cache->res[feat_id]) == FEAT_UNKNOWN) { ret = feat->probe(); if (ret > 0) { - WRITE_ONCE(feat->res, FEAT_SUPPORTED); + WRITE_ONCE(cache->res[feat_id], FEAT_SUPPORTED); } else if (ret == 0) { - WRITE_ONCE(feat->res, FEAT_MISSING); + WRITE_ONCE(cache->res[feat_id], FEAT_MISSING); } else { pr_warn("Detection of kernel %s support failed: %d\n", feat->desc, ret); - WRITE_ONCE(feat->res, FEAT_MISSING); + WRITE_ONCE(cache->res[feat_id], FEAT_MISSING); } } - return READ_ONCE(feat->res) == FEAT_SUPPORTED; + return READ_ONCE(cache->res[feat_id]) == FEAT_SUPPORTED; } static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd) -- cgit v1.2.3 From 29c302a2e265a356434b005155990a9e766db75d Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Wed, 13 Dec 2023 11:08:35 -0800 Subject: libbpf: further decouple feature checking logic from bpf_object Add feat_supported() helper that accepts feature cache instead of bpf_object. This allows low-level code in bpf.c to not know or care about higher-level concept of bpf_object, yet it will be able to utilize custom feature checking in cases where BPF token might influence the outcome. Acked-by: John Fastabend Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20231213190842.3844987-4-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- tools/lib/bpf/bpf.c | 6 +++--- tools/lib/bpf/libbpf.c | 22 +++++++++++++++------- tools/lib/bpf/libbpf_internal.h | 5 ++++- 3 files changed, 22 insertions(+), 11 deletions(-) (limited to 'tools/lib') diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index f4e1da3c6d5f..120855ac6859 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -146,7 +146,7 @@ int bump_rlimit_memlock(void) struct rlimit rlim; /* if kernel supports memcg-based accounting, skip bumping RLIMIT_MEMLOCK */ - if (memlock_bumped || kernel_supports(NULL, FEAT_MEMCG_ACCOUNT)) + if (memlock_bumped || feat_supported(NULL, FEAT_MEMCG_ACCOUNT)) return 0; memlock_bumped = true; @@ -181,7 +181,7 @@ int bpf_map_create(enum bpf_map_type map_type, return libbpf_err(-EINVAL); attr.map_type = map_type; - if (map_name && kernel_supports(NULL, FEAT_PROG_NAME)) + if (map_name && feat_supported(NULL, FEAT_PROG_NAME)) libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name)); attr.key_size = key_size; attr.value_size = value_size; @@ -265,7 +265,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type, attr.kern_version = OPTS_GET(opts, kern_version, 0); attr.prog_token_fd = OPTS_GET(opts, token_fd, 0); - if (prog_name && kernel_supports(NULL, FEAT_PROG_NAME)) + if (prog_name && feat_supported(NULL, FEAT_PROG_NAME)) libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name)); attr.license = ptr_to_u64(license); diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index d2828a26b011..2b7962120730 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -5074,17 +5074,14 @@ static struct kern_feature_desc { }, }; -bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id) +bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_id) { struct kern_feature_desc *feat = &feature_probes[feat_id]; - struct kern_feature_cache *cache = &feature_cache; int ret; - if (obj && obj->gen_loader) - /* To generate loader program assume the latest kernel - * to avoid doing extra prog_load, map_create syscalls. - */ - return true; + /* assume global feature cache, unless custom one is provided */ + if (!cache) + cache = &feature_cache; if (READ_ONCE(cache->res[feat_id]) == FEAT_UNKNOWN) { ret = feat->probe(); @@ -5101,6 +5098,17 @@ bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id) return READ_ONCE(cache->res[feat_id]) == FEAT_SUPPORTED; } +bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id) +{ + if (obj && obj->gen_loader) + /* To generate loader program assume the latest kernel + * to avoid doing extra prog_load, map_create syscalls. + */ + return true; + + return feat_supported(NULL, feat_id); +} + static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd) { struct bpf_map_info map_info; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index b5d334754e5d..754a432335e4 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -360,8 +360,11 @@ enum kern_feature_id { __FEAT_CNT, }; -int probe_memcg_account(void); +struct kern_feature_cache; +bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_id); bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id); + +int probe_memcg_account(void); int bump_rlimit_memlock(void); int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz); -- cgit v1.2.3 From ab8fc393b27cd2d6dd1ced1ba2358ddcd123fc15 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Wed, 13 Dec 2023 11:08:36 -0800 Subject: libbpf: move feature detection code into its own file It's quite a lot of well isolated code, so it seems like a good candidate to move it out of libbpf.c to reduce its size. Acked-by: John Fastabend Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20231213190842.3844987-5-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- tools/lib/bpf/Build | 2 +- tools/lib/bpf/elf.c | 2 - tools/lib/bpf/features.c | 463 ++++++++++++++++++++++++++++++++++++++++ tools/lib/bpf/libbpf.c | 463 +--------------------------------------- tools/lib/bpf/libbpf_internal.h | 12 +- tools/lib/bpf/str_error.h | 3 + 6 files changed, 479 insertions(+), 466 deletions(-) create mode 100644 tools/lib/bpf/features.c (limited to 'tools/lib') diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build index 2d0c282c8588..b6619199a706 100644 --- a/tools/lib/bpf/Build +++ b/tools/lib/bpf/Build @@ -1,4 +1,4 @@ libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \ netlink.o bpf_prog_linfo.o libbpf_probes.o hashmap.o \ btf_dump.o ringbuf.o strset.o linker.o gen_loader.o relo_core.o \ - usdt.o zip.o elf.o + usdt.o zip.o elf.o features.o diff --git a/tools/lib/bpf/elf.c b/tools/lib/bpf/elf.c index b02faec748a5..c92e02394159 100644 --- a/tools/lib/bpf/elf.c +++ b/tools/lib/bpf/elf.c @@ -11,8 +11,6 @@ #include "libbpf_internal.h" #include "str_error.h" -#define STRERR_BUFSIZE 128 - /* A SHT_GNU_versym section holds 16-bit words. This bit is set if * the symbol is hidden and can only be seen when referenced using an * explicit version number. This is a GNU extension. diff --git a/tools/lib/bpf/features.c b/tools/lib/bpf/features.c new file mode 100644 index 000000000000..338fd0dcd3bd --- /dev/null +++ b/tools/lib/bpf/features.c @@ -0,0 +1,463 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ +#include +#include +#include "bpf.h" +#include "libbpf.h" +#include "libbpf_common.h" +#include "libbpf_internal.h" +#include "str_error.h" + +static inline __u64 ptr_to_u64(const void *ptr) +{ + return (__u64)(unsigned long)ptr; +} + +static int probe_fd(int fd) +{ + if (fd >= 0) + close(fd); + return fd >= 0; +} + +static int probe_kern_prog_name(void) +{ + const size_t attr_sz = offsetofend(union bpf_attr, prog_name); + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + union bpf_attr attr; + int ret; + + memset(&attr, 0, attr_sz); + attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + attr.license = ptr_to_u64("GPL"); + attr.insns = ptr_to_u64(insns); + attr.insn_cnt = (__u32)ARRAY_SIZE(insns); + libbpf_strlcpy(attr.prog_name, "libbpf_nametest", sizeof(attr.prog_name)); + + /* make sure loading with name works */ + ret = sys_bpf_prog_load(&attr, attr_sz, PROG_LOAD_ATTEMPTS); + return probe_fd(ret); +} + +static int probe_kern_global_data(void) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + struct bpf_insn insns[] = { + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int ret, map, insn_cnt = ARRAY_SIZE(insns); + + map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_global", sizeof(int), 32, 1, NULL); + if (map < 0) { + ret = -errno; + cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); + pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", + __func__, cp, -ret); + return ret; + } + + insns[0].imm = map; + + ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL); + close(map); + return probe_fd(ret); +} + +static int probe_kern_btf(void) +{ + static const char strs[] = "\0int"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + +static int probe_kern_btf_func(void) +{ + static const char strs[] = "\0int\0x\0a"; + /* void x(int a) {} */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* FUNC_PROTO */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0), + BTF_PARAM_ENC(7, 1), + /* FUNC x */ /* [3] */ + BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), 2), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + +static int probe_kern_btf_func_global(void) +{ + static const char strs[] = "\0int\0x\0a"; + /* static void x(int a) {} */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* FUNC_PROTO */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0), + BTF_PARAM_ENC(7, 1), + /* FUNC x BTF_FUNC_GLOBAL */ /* [3] */ + BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 2), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + +static int probe_kern_btf_datasec(void) +{ + static const char strs[] = "\0x\0.data"; + /* static int a; */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* VAR x */ /* [2] */ + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), + BTF_VAR_STATIC, + /* DATASEC val */ /* [3] */ + BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), + BTF_VAR_SECINFO_ENC(2, 0, 4), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + +static int probe_kern_btf_float(void) +{ + static const char strs[] = "\0float"; + __u32 types[] = { + /* float */ + BTF_TYPE_FLOAT_ENC(1, 4), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + +static int probe_kern_btf_decl_tag(void) +{ + static const char strs[] = "\0tag"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* VAR x */ /* [2] */ + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), + BTF_VAR_STATIC, + /* attr */ + BTF_TYPE_DECL_TAG_ENC(1, 2, -1), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + +static int probe_kern_btf_type_tag(void) +{ + static const char strs[] = "\0tag"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* attr */ + BTF_TYPE_TYPE_TAG_ENC(1, 1), /* [2] */ + /* ptr */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2), /* [3] */ + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + +static int probe_kern_array_mmap(void) +{ + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_MMAPABLE); + int fd; + + fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_mmap", sizeof(int), sizeof(int), 1, &opts); + return probe_fd(fd); +} + +static int probe_kern_exp_attach_type(void) +{ + LIBBPF_OPTS(bpf_prog_load_opts, opts, .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE); + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int fd, insn_cnt = ARRAY_SIZE(insns); + + /* use any valid combination of program type and (optional) + * non-zero expected attach type (i.e., not a BPF_CGROUP_INET_INGRESS) + * to see if kernel supports expected_attach_type field for + * BPF_PROG_LOAD command + */ + fd = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", insns, insn_cnt, &opts); + return probe_fd(fd); +} + +static int probe_kern_probe_read_kernel(void) +{ + struct bpf_insn insns[] = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), /* r1 = r10 (fp) */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), /* r1 += -8 */ + BPF_MOV64_IMM(BPF_REG_2, 8), /* r2 = 8 */ + BPF_MOV64_IMM(BPF_REG_3, 0), /* r3 = 0 */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_probe_read_kernel), + BPF_EXIT_INSN(), + }; + int fd, insn_cnt = ARRAY_SIZE(insns); + + fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, NULL); + return probe_fd(fd); +} + +static int probe_prog_bind_map(void) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int ret, map, prog, insn_cnt = ARRAY_SIZE(insns); + + map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_det_bind", sizeof(int), 32, 1, NULL); + if (map < 0) { + ret = -errno; + cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); + pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", + __func__, cp, -ret); + return ret; + } + + prog = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL); + if (prog < 0) { + close(map); + return 0; + } + + ret = bpf_prog_bind_map(prog, map, NULL); + + close(map); + close(prog); + + return ret >= 0; +} + +static int probe_module_btf(void) +{ + static const char strs[] = "\0int"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), + }; + struct bpf_btf_info info; + __u32 len = sizeof(info); + char name[16]; + int fd, err; + + fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs)); + if (fd < 0) + return 0; /* BTF not supported at all */ + + memset(&info, 0, sizeof(info)); + info.name = ptr_to_u64(name); + info.name_len = sizeof(name); + + /* check that BPF_OBJ_GET_INFO_BY_FD supports specifying name pointer; + * kernel's module BTF support coincides with support for + * name/name_len fields in struct bpf_btf_info. + */ + err = bpf_btf_get_info_by_fd(fd, &info, &len); + close(fd); + return !err; +} + +static int probe_perf_link(void) +{ + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int prog_fd, link_fd, err; + + prog_fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", + insns, ARRAY_SIZE(insns), NULL); + if (prog_fd < 0) + return -errno; + + /* use invalid perf_event FD to get EBADF, if link is supported; + * otherwise EINVAL should be returned + */ + link_fd = bpf_link_create(prog_fd, -1, BPF_PERF_EVENT, NULL); + err = -errno; /* close() can clobber errno */ + + if (link_fd >= 0) + close(link_fd); + close(prog_fd); + + return link_fd < 0 && err == -EBADF; +} + +static int probe_uprobe_multi_link(void) +{ + LIBBPF_OPTS(bpf_prog_load_opts, load_opts, + .expected_attach_type = BPF_TRACE_UPROBE_MULTI, + ); + LIBBPF_OPTS(bpf_link_create_opts, link_opts); + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int prog_fd, link_fd, err; + unsigned long offset = 0; + + prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL", + insns, ARRAY_SIZE(insns), &load_opts); + if (prog_fd < 0) + return -errno; + + /* Creating uprobe in '/' binary should fail with -EBADF. */ + link_opts.uprobe_multi.path = "/"; + link_opts.uprobe_multi.offsets = &offset; + link_opts.uprobe_multi.cnt = 1; + + link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts); + err = -errno; /* close() can clobber errno */ + + if (link_fd >= 0) + close(link_fd); + close(prog_fd); + + return link_fd < 0 && err == -EBADF; +} + +static int probe_kern_bpf_cookie(void) +{ + struct bpf_insn insns[] = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_attach_cookie), + BPF_EXIT_INSN(), + }; + int ret, insn_cnt = ARRAY_SIZE(insns); + + ret = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL", insns, insn_cnt, NULL); + return probe_fd(ret); +} + +static int probe_kern_btf_enum64(void) +{ + static const char strs[] = "\0enum64"; + __u32 types[] = { + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 0), 8), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + +typedef int (*feature_probe_fn)(void); + +static struct kern_feature_cache feature_cache; + +static struct kern_feature_desc { + const char *desc; + feature_probe_fn probe; +} feature_probes[__FEAT_CNT] = { + [FEAT_PROG_NAME] = { + "BPF program name", probe_kern_prog_name, + }, + [FEAT_GLOBAL_DATA] = { + "global variables", probe_kern_global_data, + }, + [FEAT_BTF] = { + "minimal BTF", probe_kern_btf, + }, + [FEAT_BTF_FUNC] = { + "BTF functions", probe_kern_btf_func, + }, + [FEAT_BTF_GLOBAL_FUNC] = { + "BTF global function", probe_kern_btf_func_global, + }, + [FEAT_BTF_DATASEC] = { + "BTF data section and variable", probe_kern_btf_datasec, + }, + [FEAT_ARRAY_MMAP] = { + "ARRAY map mmap()", probe_kern_array_mmap, + }, + [FEAT_EXP_ATTACH_TYPE] = { + "BPF_PROG_LOAD expected_attach_type attribute", + probe_kern_exp_attach_type, + }, + [FEAT_PROBE_READ_KERN] = { + "bpf_probe_read_kernel() helper", probe_kern_probe_read_kernel, + }, + [FEAT_PROG_BIND_MAP] = { + "BPF_PROG_BIND_MAP support", probe_prog_bind_map, + }, + [FEAT_MODULE_BTF] = { + "module BTF support", probe_module_btf, + }, + [FEAT_BTF_FLOAT] = { + "BTF_KIND_FLOAT support", probe_kern_btf_float, + }, + [FEAT_PERF_LINK] = { + "BPF perf link support", probe_perf_link, + }, + [FEAT_BTF_DECL_TAG] = { + "BTF_KIND_DECL_TAG support", probe_kern_btf_decl_tag, + }, + [FEAT_BTF_TYPE_TAG] = { + "BTF_KIND_TYPE_TAG support", probe_kern_btf_type_tag, + }, + [FEAT_MEMCG_ACCOUNT] = { + "memcg-based memory accounting", probe_memcg_account, + }, + [FEAT_BPF_COOKIE] = { + "BPF cookie support", probe_kern_bpf_cookie, + }, + [FEAT_BTF_ENUM64] = { + "BTF_KIND_ENUM64 support", probe_kern_btf_enum64, + }, + [FEAT_SYSCALL_WRAPPER] = { + "Kernel using syscall wrapper", probe_kern_syscall_wrapper, + }, + [FEAT_UPROBE_MULTI_LINK] = { + "BPF multi-uprobe link support", probe_uprobe_multi_link, + }, +}; + +bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_id) +{ + struct kern_feature_desc *feat = &feature_probes[feat_id]; + int ret; + + /* assume global feature cache, unless custom one is provided */ + if (!cache) + cache = &feature_cache; + + if (READ_ONCE(cache->res[feat_id]) == FEAT_UNKNOWN) { + ret = feat->probe(); + if (ret > 0) { + WRITE_ONCE(cache->res[feat_id], FEAT_SUPPORTED); + } else if (ret == 0) { + WRITE_ONCE(cache->res[feat_id], FEAT_MISSING); + } else { + pr_warn("Detection of kernel %s support failed: %d\n", feat->desc, ret); + WRITE_ONCE(cache->res[feat_id], FEAT_MISSING); + } + } + + return READ_ONCE(cache->res[feat_id]) == FEAT_SUPPORTED; +} diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 2b7962120730..4e6f8d225caa 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -4637,467 +4637,6 @@ bpf_object__probe_loading(struct bpf_object *obj) return 0; } -static int probe_fd(int fd) -{ - if (fd >= 0) - close(fd); - return fd >= 0; -} - -static int probe_kern_prog_name(void) -{ - const size_t attr_sz = offsetofend(union bpf_attr, prog_name); - struct bpf_insn insns[] = { - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - union bpf_attr attr; - int ret; - - memset(&attr, 0, attr_sz); - attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; - attr.license = ptr_to_u64("GPL"); - attr.insns = ptr_to_u64(insns); - attr.insn_cnt = (__u32)ARRAY_SIZE(insns); - libbpf_strlcpy(attr.prog_name, "libbpf_nametest", sizeof(attr.prog_name)); - - /* make sure loading with name works */ - ret = sys_bpf_prog_load(&attr, attr_sz, PROG_LOAD_ATTEMPTS); - return probe_fd(ret); -} - -static int probe_kern_global_data(void) -{ - char *cp, errmsg[STRERR_BUFSIZE]; - struct bpf_insn insns[] = { - BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16), - BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42), - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - int ret, map, insn_cnt = ARRAY_SIZE(insns); - - map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_global", sizeof(int), 32, 1, NULL); - if (map < 0) { - ret = -errno; - cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); - pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", - __func__, cp, -ret); - return ret; - } - - insns[0].imm = map; - - ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL); - close(map); - return probe_fd(ret); -} - -static int probe_kern_btf(void) -{ - static const char strs[] = "\0int"; - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_btf_func(void) -{ - static const char strs[] = "\0int\0x\0a"; - /* void x(int a) {} */ - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ - /* FUNC_PROTO */ /* [2] */ - BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0), - BTF_PARAM_ENC(7, 1), - /* FUNC x */ /* [3] */ - BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), 2), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_btf_func_global(void) -{ - static const char strs[] = "\0int\0x\0a"; - /* static void x(int a) {} */ - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ - /* FUNC_PROTO */ /* [2] */ - BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0), - BTF_PARAM_ENC(7, 1), - /* FUNC x BTF_FUNC_GLOBAL */ /* [3] */ - BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 2), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_btf_datasec(void) -{ - static const char strs[] = "\0x\0.data"; - /* static int a; */ - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ - /* VAR x */ /* [2] */ - BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), - BTF_VAR_STATIC, - /* DATASEC val */ /* [3] */ - BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), - BTF_VAR_SECINFO_ENC(2, 0, 4), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_btf_float(void) -{ - static const char strs[] = "\0float"; - __u32 types[] = { - /* float */ - BTF_TYPE_FLOAT_ENC(1, 4), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_btf_decl_tag(void) -{ - static const char strs[] = "\0tag"; - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ - /* VAR x */ /* [2] */ - BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), - BTF_VAR_STATIC, - /* attr */ - BTF_TYPE_DECL_TAG_ENC(1, 2, -1), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_btf_type_tag(void) -{ - static const char strs[] = "\0tag"; - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ - /* attr */ - BTF_TYPE_TYPE_TAG_ENC(1, 1), /* [2] */ - /* ptr */ - BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2), /* [3] */ - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_array_mmap(void) -{ - LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_MMAPABLE); - int fd; - - fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_mmap", sizeof(int), sizeof(int), 1, &opts); - return probe_fd(fd); -} - -static int probe_kern_exp_attach_type(void) -{ - LIBBPF_OPTS(bpf_prog_load_opts, opts, .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE); - struct bpf_insn insns[] = { - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - int fd, insn_cnt = ARRAY_SIZE(insns); - - /* use any valid combination of program type and (optional) - * non-zero expected attach type (i.e., not a BPF_CGROUP_INET_INGRESS) - * to see if kernel supports expected_attach_type field for - * BPF_PROG_LOAD command - */ - fd = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", insns, insn_cnt, &opts); - return probe_fd(fd); -} - -static int probe_kern_probe_read_kernel(void) -{ - struct bpf_insn insns[] = { - BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), /* r1 = r10 (fp) */ - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), /* r1 += -8 */ - BPF_MOV64_IMM(BPF_REG_2, 8), /* r2 = 8 */ - BPF_MOV64_IMM(BPF_REG_3, 0), /* r3 = 0 */ - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_probe_read_kernel), - BPF_EXIT_INSN(), - }; - int fd, insn_cnt = ARRAY_SIZE(insns); - - fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, NULL); - return probe_fd(fd); -} - -static int probe_prog_bind_map(void) -{ - char *cp, errmsg[STRERR_BUFSIZE]; - struct bpf_insn insns[] = { - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - int ret, map, prog, insn_cnt = ARRAY_SIZE(insns); - - map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_det_bind", sizeof(int), 32, 1, NULL); - if (map < 0) { - ret = -errno; - cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); - pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", - __func__, cp, -ret); - return ret; - } - - prog = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL); - if (prog < 0) { - close(map); - return 0; - } - - ret = bpf_prog_bind_map(prog, map, NULL); - - close(map); - close(prog); - - return ret >= 0; -} - -static int probe_module_btf(void) -{ - static const char strs[] = "\0int"; - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), - }; - struct bpf_btf_info info; - __u32 len = sizeof(info); - char name[16]; - int fd, err; - - fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs)); - if (fd < 0) - return 0; /* BTF not supported at all */ - - memset(&info, 0, sizeof(info)); - info.name = ptr_to_u64(name); - info.name_len = sizeof(name); - - /* check that BPF_OBJ_GET_INFO_BY_FD supports specifying name pointer; - * kernel's module BTF support coincides with support for - * name/name_len fields in struct bpf_btf_info. - */ - err = bpf_btf_get_info_by_fd(fd, &info, &len); - close(fd); - return !err; -} - -static int probe_perf_link(void) -{ - struct bpf_insn insns[] = { - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - int prog_fd, link_fd, err; - - prog_fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", - insns, ARRAY_SIZE(insns), NULL); - if (prog_fd < 0) - return -errno; - - /* use invalid perf_event FD to get EBADF, if link is supported; - * otherwise EINVAL should be returned - */ - link_fd = bpf_link_create(prog_fd, -1, BPF_PERF_EVENT, NULL); - err = -errno; /* close() can clobber errno */ - - if (link_fd >= 0) - close(link_fd); - close(prog_fd); - - return link_fd < 0 && err == -EBADF; -} - -static int probe_uprobe_multi_link(void) -{ - LIBBPF_OPTS(bpf_prog_load_opts, load_opts, - .expected_attach_type = BPF_TRACE_UPROBE_MULTI, - ); - LIBBPF_OPTS(bpf_link_create_opts, link_opts); - struct bpf_insn insns[] = { - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - int prog_fd, link_fd, err; - unsigned long offset = 0; - - prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL", - insns, ARRAY_SIZE(insns), &load_opts); - if (prog_fd < 0) - return -errno; - - /* Creating uprobe in '/' binary should fail with -EBADF. */ - link_opts.uprobe_multi.path = "/"; - link_opts.uprobe_multi.offsets = &offset; - link_opts.uprobe_multi.cnt = 1; - - link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts); - err = -errno; /* close() can clobber errno */ - - if (link_fd >= 0) - close(link_fd); - close(prog_fd); - - return link_fd < 0 && err == -EBADF; -} - -static int probe_kern_bpf_cookie(void) -{ - struct bpf_insn insns[] = { - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_attach_cookie), - BPF_EXIT_INSN(), - }; - int ret, insn_cnt = ARRAY_SIZE(insns); - - ret = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL", insns, insn_cnt, NULL); - return probe_fd(ret); -} - -static int probe_kern_btf_enum64(void) -{ - static const char strs[] = "\0enum64"; - __u32 types[] = { - BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 0), 8), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_syscall_wrapper(void); - -enum kern_feature_result { - FEAT_UNKNOWN = 0, - FEAT_SUPPORTED = 1, - FEAT_MISSING = 2, -}; - -struct kern_feature_cache { - enum kern_feature_result res[__FEAT_CNT]; -}; - -typedef int (*feature_probe_fn)(void); - -static struct kern_feature_cache feature_cache; - -static struct kern_feature_desc { - const char *desc; - feature_probe_fn probe; -} feature_probes[__FEAT_CNT] = { - [FEAT_PROG_NAME] = { - "BPF program name", probe_kern_prog_name, - }, - [FEAT_GLOBAL_DATA] = { - "global variables", probe_kern_global_data, - }, - [FEAT_BTF] = { - "minimal BTF", probe_kern_btf, - }, - [FEAT_BTF_FUNC] = { - "BTF functions", probe_kern_btf_func, - }, - [FEAT_BTF_GLOBAL_FUNC] = { - "BTF global function", probe_kern_btf_func_global, - }, - [FEAT_BTF_DATASEC] = { - "BTF data section and variable", probe_kern_btf_datasec, - }, - [FEAT_ARRAY_MMAP] = { - "ARRAY map mmap()", probe_kern_array_mmap, - }, - [FEAT_EXP_ATTACH_TYPE] = { - "BPF_PROG_LOAD expected_attach_type attribute", - probe_kern_exp_attach_type, - }, - [FEAT_PROBE_READ_KERN] = { - "bpf_probe_read_kernel() helper", probe_kern_probe_read_kernel, - }, - [FEAT_PROG_BIND_MAP] = { - "BPF_PROG_BIND_MAP support", probe_prog_bind_map, - }, - [FEAT_MODULE_BTF] = { - "module BTF support", probe_module_btf, - }, - [FEAT_BTF_FLOAT] = { - "BTF_KIND_FLOAT support", probe_kern_btf_float, - }, - [FEAT_PERF_LINK] = { - "BPF perf link support", probe_perf_link, - }, - [FEAT_BTF_DECL_TAG] = { - "BTF_KIND_DECL_TAG support", probe_kern_btf_decl_tag, - }, - [FEAT_BTF_TYPE_TAG] = { - "BTF_KIND_TYPE_TAG support", probe_kern_btf_type_tag, - }, - [FEAT_MEMCG_ACCOUNT] = { - "memcg-based memory accounting", probe_memcg_account, - }, - [FEAT_BPF_COOKIE] = { - "BPF cookie support", probe_kern_bpf_cookie, - }, - [FEAT_BTF_ENUM64] = { - "BTF_KIND_ENUM64 support", probe_kern_btf_enum64, - }, - [FEAT_SYSCALL_WRAPPER] = { - "Kernel using syscall wrapper", probe_kern_syscall_wrapper, - }, - [FEAT_UPROBE_MULTI_LINK] = { - "BPF multi-uprobe link support", probe_uprobe_multi_link, - }, -}; - -bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_id) -{ - struct kern_feature_desc *feat = &feature_probes[feat_id]; - int ret; - - /* assume global feature cache, unless custom one is provided */ - if (!cache) - cache = &feature_cache; - - if (READ_ONCE(cache->res[feat_id]) == FEAT_UNKNOWN) { - ret = feat->probe(); - if (ret > 0) { - WRITE_ONCE(cache->res[feat_id], FEAT_SUPPORTED); - } else if (ret == 0) { - WRITE_ONCE(cache->res[feat_id], FEAT_MISSING); - } else { - pr_warn("Detection of kernel %s support failed: %d\n", feat->desc, ret); - WRITE_ONCE(cache->res[feat_id], FEAT_MISSING); - } - } - - return READ_ONCE(cache->res[feat_id]) == FEAT_SUPPORTED; -} - bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id) { if (obj && obj->gen_loader) @@ -10626,7 +10165,7 @@ static const char *arch_specific_syscall_pfx(void) #endif } -static int probe_kern_syscall_wrapper(void) +int probe_kern_syscall_wrapper(void) { char syscall_name[64]; const char *ksys_pfx; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 754a432335e4..db4a499c0ec5 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -360,10 +360,20 @@ enum kern_feature_id { __FEAT_CNT, }; -struct kern_feature_cache; +enum kern_feature_result { + FEAT_UNKNOWN = 0, + FEAT_SUPPORTED = 1, + FEAT_MISSING = 2, +}; + +struct kern_feature_cache { + enum kern_feature_result res[__FEAT_CNT]; +}; + bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_id); bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id); +int probe_kern_syscall_wrapper(void); int probe_memcg_account(void); int bump_rlimit_memlock(void); diff --git a/tools/lib/bpf/str_error.h b/tools/lib/bpf/str_error.h index a139334d57b6..626d7ffb03d6 100644 --- a/tools/lib/bpf/str_error.h +++ b/tools/lib/bpf/str_error.h @@ -2,5 +2,8 @@ #ifndef __LIBBPF_STR_ERROR_H #define __LIBBPF_STR_ERROR_H +#define STRERR_BUFSIZE 128 + char *libbpf_strerror_r(int err, char *dst, int len); + #endif /* __LIBBPF_STR_ERROR_H */ -- cgit v1.2.3 From a75bb6a16518d4a224f24116633f3f9d5787f6d1 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Wed, 13 Dec 2023 11:08:37 -0800 Subject: libbpf: wire up token_fd into feature probing logic Adjust feature probing callbacks to take into account optional token_fd. In unprivileged contexts, some feature detectors would fail to detect kernel support just because BPF program, BPF map, or BTF object can't be loaded due to privileged nature of those operations. So when BPF object is loaded with BPF token, this token should be used for feature probing. This patch is setting support for this scenario, but we don't yet pass non-zero token FD. This will be added in the next patch. We also switched BPF cookie detector from using kprobe program to tracepoint one, as tracepoint is somewhat less dangerous BPF program type and has higher likelihood of being allowed through BPF token in the future. This change has no effect on detection behavior. Acked-by: John Fastabend Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20231213190842.3844987-6-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- tools/lib/bpf/bpf.c | 3 +- tools/lib/bpf/features.c | 91 ++++++++++++++++++++++++----------------- tools/lib/bpf/libbpf.c | 2 +- tools/lib/bpf/libbpf_internal.h | 8 ++-- tools/lib/bpf/libbpf_probes.c | 8 ++-- 5 files changed, 66 insertions(+), 46 deletions(-) (limited to 'tools/lib') diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 120855ac6859..0ad8e532b3cf 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -103,7 +103,7 @@ int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts) * [0] https://lore.kernel.org/bpf/20201201215900.3569844-1-guro@fb.com/ * [1] d05512618056 ("bpf: Add bpf_ktime_get_coarse_ns helper") */ -int probe_memcg_account(void) +int probe_memcg_account(int token_fd) { const size_t attr_sz = offsetofend(union bpf_attr, attach_btf_obj_fd); struct bpf_insn insns[] = { @@ -120,6 +120,7 @@ int probe_memcg_account(void) attr.insns = ptr_to_u64(insns); attr.insn_cnt = insn_cnt; attr.license = ptr_to_u64("GPL"); + attr.prog_token_fd = token_fd; prog_fd = sys_bpf_fd(BPF_PROG_LOAD, &attr, attr_sz); if (prog_fd >= 0) { diff --git a/tools/lib/bpf/features.c b/tools/lib/bpf/features.c index 338fd0dcd3bd..ce98a334be21 100644 --- a/tools/lib/bpf/features.c +++ b/tools/lib/bpf/features.c @@ -20,7 +20,7 @@ static int probe_fd(int fd) return fd >= 0; } -static int probe_kern_prog_name(void) +static int probe_kern_prog_name(int token_fd) { const size_t attr_sz = offsetofend(union bpf_attr, prog_name); struct bpf_insn insns[] = { @@ -35,6 +35,7 @@ static int probe_kern_prog_name(void) attr.license = ptr_to_u64("GPL"); attr.insns = ptr_to_u64(insns); attr.insn_cnt = (__u32)ARRAY_SIZE(insns); + attr.prog_token_fd = token_fd; libbpf_strlcpy(attr.prog_name, "libbpf_nametest", sizeof(attr.prog_name)); /* make sure loading with name works */ @@ -42,7 +43,7 @@ static int probe_kern_prog_name(void) return probe_fd(ret); } -static int probe_kern_global_data(void) +static int probe_kern_global_data(int token_fd) { char *cp, errmsg[STRERR_BUFSIZE]; struct bpf_insn insns[] = { @@ -51,9 +52,11 @@ static int probe_kern_global_data(void) BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }; + LIBBPF_OPTS(bpf_map_create_opts, map_opts, .token_fd = token_fd); + LIBBPF_OPTS(bpf_prog_load_opts, prog_opts, .token_fd = token_fd); int ret, map, insn_cnt = ARRAY_SIZE(insns); - map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_global", sizeof(int), 32, 1, NULL); + map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_global", sizeof(int), 32, 1, &map_opts); if (map < 0) { ret = -errno; cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); @@ -64,12 +67,12 @@ static int probe_kern_global_data(void) insns[0].imm = map; - ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL); + ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &prog_opts); close(map); return probe_fd(ret); } -static int probe_kern_btf(void) +static int probe_kern_btf(int token_fd) { static const char strs[] = "\0int"; __u32 types[] = { @@ -78,10 +81,10 @@ static int probe_kern_btf(void) }; return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); + strs, sizeof(strs), token_fd)); } -static int probe_kern_btf_func(void) +static int probe_kern_btf_func(int token_fd) { static const char strs[] = "\0int\0x\0a"; /* void x(int a) {} */ @@ -96,10 +99,10 @@ static int probe_kern_btf_func(void) }; return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); + strs, sizeof(strs), token_fd)); } -static int probe_kern_btf_func_global(void) +static int probe_kern_btf_func_global(int token_fd) { static const char strs[] = "\0int\0x\0a"; /* static void x(int a) {} */ @@ -114,10 +117,10 @@ static int probe_kern_btf_func_global(void) }; return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); + strs, sizeof(strs), token_fd)); } -static int probe_kern_btf_datasec(void) +static int probe_kern_btf_datasec(int token_fd) { static const char strs[] = "\0x\0.data"; /* static int a; */ @@ -133,10 +136,10 @@ static int probe_kern_btf_datasec(void) }; return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); + strs, sizeof(strs), token_fd)); } -static int probe_kern_btf_float(void) +static int probe_kern_btf_float(int token_fd) { static const char strs[] = "\0float"; __u32 types[] = { @@ -145,10 +148,10 @@ static int probe_kern_btf_float(void) }; return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); + strs, sizeof(strs), token_fd)); } -static int probe_kern_btf_decl_tag(void) +static int probe_kern_btf_decl_tag(int token_fd) { static const char strs[] = "\0tag"; __u32 types[] = { @@ -162,10 +165,10 @@ static int probe_kern_btf_decl_tag(void) }; return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); + strs, sizeof(strs), token_fd)); } -static int probe_kern_btf_type_tag(void) +static int probe_kern_btf_type_tag(int token_fd) { static const char strs[] = "\0tag"; __u32 types[] = { @@ -178,21 +181,27 @@ static int probe_kern_btf_type_tag(void) }; return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); + strs, sizeof(strs), token_fd)); } -static int probe_kern_array_mmap(void) +static int probe_kern_array_mmap(int token_fd) { - LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_MMAPABLE); + LIBBPF_OPTS(bpf_map_create_opts, opts, + .map_flags = BPF_F_MMAPABLE, + .token_fd = token_fd, + ); int fd; fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_mmap", sizeof(int), sizeof(int), 1, &opts); return probe_fd(fd); } -static int probe_kern_exp_attach_type(void) +static int probe_kern_exp_attach_type(int token_fd) { - LIBBPF_OPTS(bpf_prog_load_opts, opts, .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE); + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE, + .token_fd = token_fd, + ); struct bpf_insn insns[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), @@ -208,8 +217,9 @@ static int probe_kern_exp_attach_type(void) return probe_fd(fd); } -static int probe_kern_probe_read_kernel(void) +static int probe_kern_probe_read_kernel(int token_fd) { + LIBBPF_OPTS(bpf_prog_load_opts, opts, .token_fd = token_fd); struct bpf_insn insns[] = { BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), /* r1 = r10 (fp) */ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), /* r1 +=