Add a basic sandbox tool to launch a command which is only allowed to access in a read only or read-write way a whitelist of file hierarchies. Add to the bpf_load library the ability to handle a BPF program subtype. Signed-off-by: Mickaël Salaün <mic@xxxxxxxxxxx> Cc: Alexei Starovoitov <ast@xxxxxxxxxx> Cc: Andy Lutomirski <luto@xxxxxxxxxxxxxx> Cc: Daniel Borkmann <daniel@xxxxxxxxxxxxx> Cc: David S. Miller <davem@xxxxxxxxxxxxx> Cc: James Morris <james.l.morris@xxxxxxxxxx> Cc: Kees Cook <keescook@xxxxxxxxxxxx> Cc: Serge E. Hallyn <serge@xxxxxxxxxx> --- Changes since v7: * rewrite the example using an inode map * add to bpf_load the ability to handle subtypes per program type Changes since v6: * check return value of load_and_attach() * allow to write on pipes * rename BPF_PROG_TYPE_LANDLOCK to BPF_PROG_TYPE_LANDLOCK_RULE * rename Landlock version to ABI to better reflect its purpose * use const variable (suggested by Kees Cook) * remove useless definitions (suggested by Kees Cook) * add detailed explanations (suggested by Kees Cook) Changes since v5: * cosmetic fixes * rebase Changes since v4: * write Landlock rule in C and compiled it with LLVM * remove cgroup handling * remove path handling: only handle a read-only environment * remove errno return codes Changes since v3: * remove seccomp and origin field: completely free from seccomp programs * handle more FS-related hooks * handle inode hooks and directory traversal * add faked but consistent view thanks to ENOENT * add /lib64 in the example * fix spelling * rename some types and definitions (e.g. SECCOMP_ADD_LANDLOCK_RULE) Changes since v2: * use BPF_PROG_ATTACH for cgroup handling --- samples/bpf/Makefile | 4 + samples/bpf/bpf_load.c | 82 ++++++++++++++++++++- samples/bpf/bpf_load.h | 7 ++ samples/bpf/landlock1.h | 14 ++++ samples/bpf/landlock1_kern.c | 171 +++++++++++++++++++++++++++++++++++++++++++ samples/bpf/landlock1_user.c | 164 +++++++++++++++++++++++++++++++++++++++++ 6 files changed, 439 insertions(+), 3 deletions(-) create mode 100644 samples/bpf/landlock1.h create mode 100644 samples/bpf/landlock1_kern.c create mode 100644 samples/bpf/landlock1_user.c diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index ec3fc8d88e87..015b1375daa5 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -43,6 +43,7 @@ hostprogs-y += xdp_redirect_cpu hostprogs-y += xdp_monitor hostprogs-y += xdp_rxq_info hostprogs-y += syscall_tp +hostprogs-y += landlock1 # Libbpf dependencies LIBBPF := ../../tools/lib/bpf/bpf.o ../../tools/lib/bpf/nlattr.o @@ -93,6 +94,7 @@ xdp_redirect_cpu-objs := bpf_load.o $(LIBBPF) xdp_redirect_cpu_user.o xdp_monitor-objs := bpf_load.o $(LIBBPF) xdp_monitor_user.o xdp_rxq_info-objs := bpf_load.o $(LIBBPF) xdp_rxq_info_user.o syscall_tp-objs := bpf_load.o $(LIBBPF) syscall_tp_user.o +landlock1-objs := bpf_load.o $(LIBBPF) landlock1_user.o # Tell kbuild to always build the programs always := $(hostprogs-y) @@ -144,6 +146,7 @@ always += xdp_monitor_kern.o always += xdp_rxq_info_kern.o always += xdp2skb_meta_kern.o always += syscall_tp_kern.o +always += landlock1_kern.o HOSTCFLAGS += -I$(objtree)/usr/include HOSTCFLAGS += -I$(srctree)/tools/lib/ @@ -188,6 +191,7 @@ HOSTLOADLIBES_xdp_redirect_cpu += -lelf HOSTLOADLIBES_xdp_monitor += -lelf HOSTLOADLIBES_xdp_rxq_info += -lelf HOSTLOADLIBES_syscall_tp += -lelf +HOSTLOADLIBES_landlock1 += -lelf # Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline: # make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c index 5bb37db6054b..f7c91093b2f5 100644 --- a/samples/bpf/bpf_load.c +++ b/samples/bpf/bpf_load.c @@ -12,6 +12,7 @@ #include <stdlib.h> #include <linux/bpf.h> #include <linux/filter.h> +#include <linux/landlock.h> #include <linux/perf_event.h> #include <linux/netlink.h> #include <linux/rtnetlink.h> @@ -43,6 +44,9 @@ int prog_array_fd = -1; struct bpf_map_data map_data[MAX_MAPS]; int map_data_count = 0; +struct bpf_subtype_data subtype_data[MAX_PROGS]; +int subtype_data_count = 0; + static int populate_prog_array(const char *event, int prog_fd) { int ind = atoi(event), err; @@ -67,12 +71,14 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size) bool is_cgroup_sk = strncmp(event, "cgroup/sock", 11) == 0; bool is_sockops = strncmp(event, "sockops", 7) == 0; bool is_sk_skb = strncmp(event, "sk_skb", 6) == 0; + bool is_landlock = strncmp(event, "landlock", 8) == 0; size_t insns_cnt = size / sizeof(struct bpf_insn); enum bpf_prog_type prog_type; char buf[256]; int fd, efd, err, id; struct perf_event_attr attr = {}; union bpf_prog_subtype *st = NULL; + struct bpf_subtype_data *sd = NULL; attr.type = PERF_TYPE_TRACEPOINT; attr.sample_type = PERF_SAMPLE_RAW; @@ -97,6 +103,50 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size) prog_type = BPF_PROG_TYPE_SOCK_OPS; } else if (is_sk_skb) { prog_type = BPF_PROG_TYPE_SK_SKB; + } else if (is_landlock) { + int i, prog_id; + const char *event_id = (event + 8); + + if (!isdigit(*event_id)) { + printf("invalid prog number\n"); + return -1; + } + prog_id = atoi(event_id); + for (i = 0; i < subtype_data_count; i++) { + if (subtype_data[i].name && strcmp(event, + subtype_data[i].name) == 0) { + /* save the prog_id for a next program */ + sd = &subtype_data[i]; + sd->prog_id = prog_id; + st = &sd->subtype; + free(sd->name); + sd->name = NULL; + break; + } + } + if (!st) { + printf("missing subtype\n"); + return -1; + } + /* automatic conversion of program pointer to FD */ + if (st->landlock_hook.options & LANDLOCK_OPTION_PREVIOUS) { + int previous = -1; + + /* assume the previous program is already loaded */ + for (i = 0; i < subtype_data_count; i++) { + if (subtype_data[i].prog_id == + st->landlock_hook.previous) { + previous = subtype_data[i].prog_fd; + break; + } + } + if (previous == -1) { + printf("could not find the previous program\n"); + return -1; + } + st->landlock_hook.previous = previous; + } + prog_type = BPF_PROG_TYPE_LANDLOCK_HOOK; } else { printf("Unknown event '%s'\n", event); return -1; @@ -108,10 +158,13 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size) printf("bpf_load_program() err=%d\n%s", errno, bpf_log_buf); return -1; } + if (sd) + sd->prog_fd = fd; prog_fd[prog_cnt++] = fd; - if (is_xdp || is_perf_event || is_cgroup_skb || is_cgroup_sk) + if (is_xdp || is_perf_event || is_cgroup_skb || is_cgroup_sk || + is_landlock) return 0; if (is_socket || is_sockops || is_sk_skb) { @@ -515,6 +568,29 @@ static int do_load_bpf_file(const char *path, fixup_map_cb fixup_map) data_maps = data; for (j = 0; j < MAX_MAPS; j++) map_data[j].fd = -1; + } else if (strncmp(shname, "subtype", 7) == 0) { + processed_sec[i] = true; + if (*(shname + 7) != '/') { + printf("invalid name of subtype section"); + return 1; + } + if (data->d_size != sizeof(union bpf_prog_subtype)) { + printf("invalid size of subtype section: %zd\n", + data->d_size); + printf("ref: %zd\n", + sizeof(union bpf_prog_subtype)); + return 1; + } + if (subtype_data_count >= MAX_PROGS) { + printf("too many subtype sections"); + return 1; + } + memcpy(&subtype_data[subtype_data_count].subtype, + data->d_buf, + sizeof(union bpf_prog_subtype)); + subtype_data[subtype_data_count].name = + strdup((shname + 8)); + subtype_data_count++; } else if (shdr.sh_type == SHT_SYMTAB) { strtabidx = shdr.sh_link; symbols = data; @@ -575,7 +651,6 @@ static int do_load_bpf_file(const char *path, fixup_map_cb fixup_map) /* load programs */ for (i = 1; i < ehdr.e_shnum; i++) { - if (processed_sec[i]) continue; @@ -590,7 +665,8 @@ static int do_load_bpf_file(const char *path, fixup_map_cb fixup_map) memcmp(shname, "socket", 6) == 0 || memcmp(shname, "cgroup/", 7) == 0 || memcmp(shname, "sockops", 7) == 0 || - memcmp(shname, "sk_skb", 6) == 0) { + memcmp(shname, "sk_skb", 6) == 0 || + memcmp(shname, "landlock", 8) == 0) { ret = load_and_attach(shname, data->d_buf, data->d_size); if (ret != 0) diff --git a/samples/bpf/bpf_load.h b/samples/bpf/bpf_load.h index 453c200b389b..b5abe793e271 100644 --- a/samples/bpf/bpf_load.h +++ b/samples/bpf/bpf_load.h @@ -24,6 +24,13 @@ struct bpf_map_data { struct bpf_map_def def; }; +struct bpf_subtype_data { + char *name; + int prog_id; + int prog_fd; + union bpf_prog_subtype subtype; +}; + typedef void (*fixup_map_cb)(struct bpf_map_data *map, int idx); extern int prog_fd[MAX_PROGS]; diff --git a/samples/bpf/landlock1.h b/samples/bpf/landlock1.h new file mode 100644 index 000000000000..6d0538816088 --- /dev/null +++ b/samples/bpf/landlock1.h @@ -0,0 +1,14 @@ +/* + * Landlock sample 1 - common header + * + * Copyright © 2018 Mickaël Salaün <mic@xxxxxxxxxxx> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2, as + * published by the Free Software Foundation. + */ + +#define MAP_MARK_READ (1ULL << 63) +#define MAP_MARK_WRITE (1ULL << 62) +#define COOKIE_VALUE_FREEZED (1ULL << 61) +#define _MAP_MARK_MASK (MAP_MARK_READ | MAP_MARK_WRITE | COOKIE_VALUE_FREEZED) diff --git a/samples/bpf/landlock1_kern.c b/samples/bpf/landlock1_kern.c new file mode 100644 index 000000000000..113243677ddd --- /dev/null +++ b/samples/bpf/landlock1_kern.c @@ -0,0 +1,171 @@ +/* + * Landlock sample 1 - whitelist of read only or read-write file hierarchy + * + * Copyright © 2017-2018 Mickaël Salaün <mic@xxxxxxxxxxx> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2, as + * published by the Free Software Foundation. + */ + +/* + * This file contains a function that will be compiled to eBPF bytecode thanks + * to LLVM/Clang. + * + * Each SEC() means that the following function or variable will be part of a + * custom ELF section. This sections are then processed by the userspace part + * (see landlock1_user.c) to extract eBPF bytecode and take into account + * variables describing the eBPF program subtype or its license. + */ + +#include <uapi/linux/bpf.h> +#include <uapi/linux/landlock.h> + +#include "bpf_helpers.h" +#include "landlock1.h" /* MAP_MARK_* */ + +SEC("maps") +struct bpf_map_def inode_map = { + .type = BPF_MAP_TYPE_INODE, + .key_size = sizeof(u32), + .value_size = sizeof(u64), + .max_entries = 20, +}; + +SEC("subtype/landlock1") +static union bpf_prog_subtype _subtype1 = { + .landlock_hook = { + .type = LANDLOCK_HOOK_FS_WALK, + } +}; + +static __always_inline __u64 update_cookie(__u64 cookie, __u8 lookup, + void *inode, void *chain, bool freeze) +{ + __u64 map_allow = 0; + + if (cookie == 0) { + cookie = bpf_inode_get_tag(inode, chain); + if (cookie) + return cookie; + /* only look for the first match in the map, ignore nested + * paths in this example */ + map_allow = bpf_inode_map_lookup(&inode_map, inode); + if (map_allow) + cookie = 1 | map_allow; + } else { + if (cookie & COOKIE_VALUE_FREEZED) + return cookie; + map_allow = cookie & _MAP_MARK_MASK; + cookie &= ~_MAP_MARK_MASK; + switch (lookup) { + case LANDLOCK_CTX_FS_WALK_INODE_LOOKUP_DOTDOT: + cookie--; + break; + case LANDLOCK_CTX_FS_WALK_INODE_LOOKUP_DOT: + break; + default: + /* ignore _MAP_MARK_MASK overflow in this example */ + cookie++; + break; + } + if (cookie >= 1) + cookie |= map_allow; + } + /* do not modify the cookie for each fs_pick */ + if (freeze && cookie) + cookie |= COOKIE_VALUE_FREEZED; + return cookie; +} + +/* + * The function fs_walk() is a simple Landlock program enforced on a set of + * processes. This program will be run for each walk through a file path. + * + * The argument ctx contains the context of the program when it is run, which + * enable to evaluate the file path. This context can change for each run of + * the program. + */ +SEC("landlock1") +int fs_walk(struct landlock_ctx_fs_walk *ctx) +{ + ctx->cookie = update_cookie(ctx->cookie, ctx->inode_lookup, + (void *)ctx->inode, (void *)ctx->chain, false); + return LANDLOCK_RET_ALLOW; +} + +SEC("subtype/landlock2") +static union bpf_prog_subtype _subtype2 = { + .landlock_hook = { + .type = LANDLOCK_HOOK_FS_PICK, + .options = LANDLOCK_OPTION_PREVIOUS, + .previous = 1, /* landlock1 */ + .triggers = LANDLOCK_TRIGGER_FS_PICK_CHDIR | + LANDLOCK_TRIGGER_FS_PICK_GETATTR | + LANDLOCK_TRIGGER_FS_PICK_READDIR | + LANDLOCK_TRIGGER_FS_PICK_TRANSFER | + LANDLOCK_TRIGGER_FS_PICK_OPEN, + } +}; + +SEC("landlock2") +int fs_pick_ro(struct landlock_ctx_fs_pick *ctx) +{ + ctx->cookie = update_cookie(ctx->cookie, ctx->inode_lookup, + (void *)ctx->inode, (void *)ctx->chain, true); + if (ctx->cookie & MAP_MARK_READ) + return LANDLOCK_RET_ALLOW; + return LANDLOCK_RET_DENY; +} + +SEC("subtype/landlock3") +static union bpf_prog_subtype _subtype3 = { + .landlock_hook = { + .type = LANDLOCK_HOOK_FS_PICK, + .options = LANDLOCK_OPTION_PREVIOUS, + .previous = 2, /* landlock2 */ + .triggers = LANDLOCK_TRIGGER_FS_PICK_APPEND | + LANDLOCK_TRIGGER_FS_PICK_CREATE | + LANDLOCK_TRIGGER_FS_PICK_LINK | + LANDLOCK_TRIGGER_FS_PICK_LINKTO | + LANDLOCK_TRIGGER_FS_PICK_LOCK | + LANDLOCK_TRIGGER_FS_PICK_MOUNTON | + LANDLOCK_TRIGGER_FS_PICK_RENAME | + LANDLOCK_TRIGGER_FS_PICK_RENAMETO | + LANDLOCK_TRIGGER_FS_PICK_RMDIR | + LANDLOCK_TRIGGER_FS_PICK_SETATTR | + LANDLOCK_TRIGGER_FS_PICK_UNLINK | + LANDLOCK_TRIGGER_FS_PICK_WRITE, + } +}; + +SEC("landlock3") +int fs_pick_rw(struct landlock_ctx_fs_pick *ctx) +{ + ctx->cookie = update_cookie(ctx->cookie, ctx->inode_lookup, + (void *)ctx->inode, (void *)ctx->chain, true); + if (ctx->cookie & MAP_MARK_WRITE) + return LANDLOCK_RET_ALLOW; + return LANDLOCK_RET_DENY; +} + +SEC("subtype/landlock4") +static union bpf_prog_subtype _subtype4 = { + .landlock_hook = { + .type = LANDLOCK_HOOK_FS_GET, + .options = LANDLOCK_OPTION_PREVIOUS, + .previous = 3, /* landlock3 */ + } +}; + +SEC("landlock4") +int fs_get(struct landlock_ctx_fs_get *ctx) +{ + /* save the cookie in the tag for relative path lookup */ + bpf_landlock_set_tag((void *)ctx->tag_object, (void *)ctx->chain, + ctx->cookie & ~COOKIE_VALUE_FREEZED); + return LANDLOCK_RET_ALLOW; +} + +SEC("license") +static const char _license[] = "GPL"; diff --git a/samples/bpf/landlock1_user.c b/samples/bpf/landlock1_user.c new file mode 100644 index 000000000000..e46e0ca182cd --- /dev/null +++ b/samples/bpf/landlock1_user.c @@ -0,0 +1,164 @@ +/* + * Landlock sample 1 - partial read-only filesystem + * + * Copyright © 2017-2018 Mickaël Salaün <mic@xxxxxxxxxxx> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2, as + * published by the Free Software Foundation. + */ + +#include "bpf_load.h" +#include "landlock1.h" /* MAP_MARK_* */ +#include "libbpf.h" + +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> /* open() */ +#include <linux/bpf.h> +#include <linux/filter.h> +#include <linux/landlock.h> +#include <linux/prctl.h> +#include <linux/seccomp.h> +#include <stddef.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/prctl.h> +#include <sys/syscall.h> +#include <unistd.h> + +#ifndef seccomp +static int seccomp(unsigned int op, unsigned int flags, void *args) +{ + errno = 0; + return syscall(__NR_seccomp, op, flags, args); +} +#endif + +static int apply_sandbox(int prog_fd) +{ + int ret = 0; + + /* set up the test sandbox */ + if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) { + perror("prctl(no_new_priv)"); + return 1; + } + if (seccomp(SECCOMP_PREPEND_LANDLOCK_PROG, 0, &prog_fd)) { + perror("seccomp(set_hook)"); + ret = 1; + } + close(prog_fd); + + return ret; +} + +#define ENV_FS_PATH_RO_NAME "LL_PATH_RO" +#define ENV_FS_PATH_RW_NAME "LL_PATH_RW" +#define ENV_PATH_TOKEN ":" + +static int parse_path(char *env_path, const char ***path_list) +{ + int i, path_nb = 0; + + if (env_path) { + path_nb++; + for (i = 0; env_path[i]; i++) { + if (env_path[i] == ENV_PATH_TOKEN[0]) + path_nb++; + } + } + *path_list = malloc(path_nb * sizeof(**path_list)); + for (i = 0; i < path_nb; i++) + (*path_list)[i] = strsep(&env_path, ENV_PATH_TOKEN); + + return path_nb; +} + +static int populate_map(const char *env_var, unsigned long long value, + int map_fd) +{ + int path_nb, ref_fd, i; + char *env_path_name; + const char **path_list = NULL; + + env_path_name = getenv(env_var); + if (!env_path_name) + return 0; + env_path_name = strdup(env_path_name); + path_nb = parse_path(env_path_name, &path_list); + + for (i = 0; i < path_nb; i++) { + ref_fd = open(path_list[i], O_RDONLY | O_CLOEXEC); + if (ref_fd < 0) { + fprintf(stderr, "Failed to open \"%s\": %s\n", + path_list[i], + strerror(errno)); + return 1; + } + if (bpf_map_update_elem(map_fd, &ref_fd, &value, BPF_ANY)) { + fprintf(stderr, "Failed to update the map with" + " \"%s\": %s\n", path_list[i], + strerror(errno)); + return 1; + } + close(ref_fd); + } + free(env_path_name); + return 0; +} + +int main(int argc, char * const argv[], char * const *envp) +{ + char filename[256]; + char *cmd_path; + char * const *cmd_argv; + int ll_prog; + + if (argc < 2) { + fprintf(stderr, "usage: %s <cmd> [args]...\n\n", argv[0]); + fprintf(stderr, "Launch a command in a restricted environment.\n"); + fprintf(stderr, "Environment variables containing paths, each separated by a colon:\n"); + fprintf(stderr, "* %s: whitelist of allowed files and directories to be read\n", + ENV_FS_PATH_RO_NAME); + fprintf(stderr, "* %s: whitelist of allowed files and directories to be modified\n", + ENV_FS_PATH_RW_NAME); + fprintf(stderr, "\nexample:\n" + "%s=\"/bin:/lib:/lib64:/usr:${HOME}\" " + "%s=\"/tmp:/dev/urandom:/dev/random:/dev/null\" " + "%s /bin/sh -i\n", + ENV_FS_PATH_RO_NAME, ENV_FS_PATH_RW_NAME, argv[0]); + return 1; + } + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + if (load_bpf_file(filename)) { + printf("%s", bpf_log_buf); + return 1; + } + ll_prog = prog_fd[3]; /* fs_get */ + if (!ll_prog) { + if (errno) + printf("load_bpf_file: %s\n", strerror(errno)); + else + printf("load_bpf_file: Error\n"); + return 1; + } + + if (populate_map(ENV_FS_PATH_RO_NAME, MAP_MARK_READ, map_fd[0])) + return 1; + if (populate_map(ENV_FS_PATH_RW_NAME, MAP_MARK_READ | MAP_MARK_WRITE, + map_fd[0])) + return 1; + close(map_fd[0]); + + fprintf(stderr, "Launching a new sandboxed process\n"); + if (apply_sandbox(ll_prog)) + return 1; + cmd_path = argv[1]; + cmd_argv = argv + 1; + execve(cmd_path, cmd_argv, envp); + perror("Failed to call execve"); + return 1; +} -- 2.16.2 -- To unsubscribe from this list: send the line "unsubscribe linux-api" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html