From 7c05e7f3e74e7e550534d524e04d7e6f78d6fa24 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Fri, 5 Jan 2024 18:48:17 +0800 Subject: bpf: Support inlining bpf_kptr_xchg() helper The motivation of inlining bpf_kptr_xchg() comes from the performance profiling of bpf memory allocator benchmark. The benchmark uses bpf_kptr_xchg() to stash the allocated objects and to pop the stashed objects for free. After inling bpf_kptr_xchg(), the performance for object free on 8-CPUs VM increases about 2%~10%. The inline also has downside: both the kasan and kcsan checks on the pointer will be unavailable. bpf_kptr_xchg() can be inlined by converting the calling of bpf_kptr_xchg() into an atomic_xchg() instruction. But the conversion depends on two conditions: 1) JIT backend supports atomic_xchg() on pointer-sized word 2) For the specific arch, the implementation of xchg is the same as atomic_xchg() on pointer-sized words. It seems most 64-bit JIT backends satisfies these two conditions. But as a precaution, defining a weak function bpf_jit_supports_ptr_xchg() to state whether such conversion is safe and only supporting inline for 64-bit host. For x86-64, it supports BPF_XCHG atomic operation and both xchg() and atomic_xchg() use arch_xchg() to implement the exchange, so enabling the inline of bpf_kptr_xchg() on x86-64 first. Reviewed-by: Eduard Zingerman Signed-off-by: Hou Tao Link: https://lore.kernel.org/r/20240105104819.3916743-2-houtao@huaweicloud.com Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 68fb6c8142fe..35f067fd3840 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -955,6 +955,7 @@ bool bpf_jit_supports_subprog_tailcalls(void); bool bpf_jit_supports_kfunc_call(void); bool bpf_jit_supports_far_kfunc_call(void); bool bpf_jit_supports_exceptions(void); +bool bpf_jit_supports_ptr_xchg(void); void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie); bool bpf_helper_changes_pkt_data(void *func); -- cgit v1.2.3 From 522bb2c1f82b12eb7befaae815d1d959b8e6bba2 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 4 Jan 2024 16:09:05 -0800 Subject: bpf: support multiple tags per argument Add ability to iterate multiple decl_tag types pointed to the same function argument. Use this to support multiple __arg_xxx tags per global subprog argument. We leave btf_find_decl_tag_value() intact, but change its implementation to use a new btf_find_next_decl_tag() which can be straightforwardly used to find next BTF type ID of a matching btf_decl_tag type. btf_prepare_func_args() is switched from btf_find_decl_tag_value() to btf_find_next_decl_tag() to gain multiple tags per argument support. Signed-off-by: Andrii Nakryiko Acked-by: Eduard Zingerman Link: https://lore.kernel.org/r/20240105000909.2818934-5-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 ++ kernel/bpf/btf.c | 64 ++++++++++++++++++++++++++++++++++------------------- 2 files changed, 43 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e30100597d0a..377857b232c6 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2472,6 +2472,8 @@ int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *pr struct btf *btf, const struct btf_type *t); const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt, int comp_idx, const char *tag_key); +int btf_find_next_decl_tag(const struct btf *btf, const struct btf_type *pt, + int comp_idx, const char *tag_key, int last_id); struct bpf_prog *bpf_prog_by_id(u32 id); struct bpf_link *bpf_link_by_id(u32 id); diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 1636b574a63d..4f532b303a27 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3310,30 +3310,48 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t, return BTF_FIELD_FOUND; } -const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt, - int comp_idx, const char *tag_key) +int btf_find_next_decl_tag(const struct btf *btf, const struct btf_type *pt, + int comp_idx, const char *tag_key, int last_id) { - const char *value = NULL; - int i; + int len = strlen(tag_key); + int i, n; - for (i = 1; i < btf_nr_types(btf); i++) { + for (i = last_id + 1, n = btf_nr_types(btf); i < n; i++) { const struct btf_type *t = btf_type_by_id(btf, i); - int len = strlen(tag_key); if (!btf_type_is_decl_tag(t)) continue; - if (pt != btf_type_by_id(btf, t->type) || - btf_type_decl_tag(t)->component_idx != comp_idx) + if (pt != btf_type_by_id(btf, t->type)) + continue; + if (btf_type_decl_tag(t)->component_idx != comp_idx) continue; if (strncmp(__btf_name_by_offset(btf, t->name_off), tag_key, len)) continue; - /* Prevent duplicate entries for same type */ - if (value) - return ERR_PTR(-EEXIST); - value = __btf_name_by_offset(btf, t->name_off) + len; + return i; } - if (!value) - return ERR_PTR(-ENOENT); + return -ENOENT; +} + +const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt, + int comp_idx, const char *tag_key) +{ + const char *value = NULL; + const struct btf_type *t; + int len, id; + + id = btf_find_next_decl_tag(btf, pt, comp_idx, tag_key, 0); + if (id < 0) + return ERR_PTR(id); + + t = btf_type_by_id(btf, id); + len = strlen(tag_key); + value = __btf_name_by_offset(btf, t->name_off) + len; + + /* Prevent duplicate entries for same type */ + id = btf_find_next_decl_tag(btf, pt, comp_idx, tag_key, id); + if (id >= 0) + return ERR_PTR(-EEXIST); + return value; } @@ -7032,20 +7050,16 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog) * Only PTR_TO_CTX and SCALAR are supported atm. */ for (i = 0; i < nargs; i++) { - const char *tag; u32 tags = 0; + int id = 0; - tag = btf_find_decl_tag_value(btf, fn_t, i, "arg:"); - if (IS_ERR(tag) && PTR_ERR(tag) == -ENOENT) { - tag = NULL; - } else if (IS_ERR(tag)) { - bpf_log(log, "arg#%d type's tag fetching failure: %ld\n", i, PTR_ERR(tag)); - return PTR_ERR(tag); - } /* 'arg:' decl_tag takes precedence over derivation of * register type from BTF type itself */ - if (tag) { + while ((id = btf_find_next_decl_tag(btf, fn_t, i, "arg:", id)) > 0) { + const struct btf_type *tag_t = btf_type_by_id(btf, id); + const char *tag = __btf_name_by_offset(btf, tag_t->name_off) + 4; + /* disallow arg tags in static subprogs */ if (!is_global) { bpf_log(log, "arg#%d type tag is not supported in static functions\n", i); @@ -7061,6 +7075,10 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog) return -EOPNOTSUPP; } } + if (id != -ENOENT) { + bpf_log(log, "arg#%d type tag fetching failure: %d\n", i, id); + return id; + } t = btf_type_by_id(btf, args[i].type); while (btf_type_is_modifier(t)) -- cgit v1.2.3 From 32f55dd4add4df1a5bc8febc1fafd3086290dbf6 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Mon, 8 Jan 2024 22:51:58 +0200 Subject: bpf: Make bpf_for_each_spilled_reg consider narrow spills Adjust the check in bpf_get_spilled_reg to take into account spilled registers narrower than 64 bits. That allows find_equal_scalars to properly adjust the range of all spilled registers that have the same ID. Before this change, it was possible for a register and a spilled register to have the same IDs but different ranges if the spill was narrower than 64 bits and a range check was performed on the register. Signed-off-by: Maxim Mikityanskiy Acked-by: Eduard Zingerman Link: https://lore.kernel.org/r/20240108205209.838365-5-maxtram95@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index d07d857ca67f..e11baecbde68 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -453,7 +453,7 @@ struct bpf_verifier_state { #define bpf_get_spilled_reg(slot, frame, mask) \ (((slot < frame->allocated_stack / BPF_REG_SIZE) && \ - ((1 << frame->stack[slot].slot_type[0]) & (mask))) \ + ((1 << frame->stack[slot].slot_type[BPF_REG_SIZE - 1]) & (mask))) \ ? &frame->stack[slot].spilled_ptr : NULL) /* Iterate over 'frame', setting 'reg' to either NULL or a spilled register. */ -- cgit v1.2.3 From 3b1f89e747cd4b24244f2798a35d28815b744303 Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Fri, 19 Jan 2024 14:49:52 -0800 Subject: bpf: refactory struct_ops type initialization to a function. Move the majority of the code to bpf_struct_ops_init_one(), which can then be utilized for the initialization of newly registered dynamically allocated struct_ops types in the following patches. Signed-off-by: Kui-Feng Lee Link: https://lore.kernel.org/r/20240119225005.668602-2-thinker.li@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/btf.h | 1 + kernel/bpf/bpf_struct_ops.c | 157 +++++++++++++++++++++++--------------------- kernel/bpf/btf.c | 5 ++ 3 files changed, 89 insertions(+), 74 deletions(-) (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index cf5c6ff48981..932af1680bb5 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -137,6 +137,7 @@ struct btf_struct_metas { extern const struct file_operations btf_fops; +const char *btf_get_name(const struct btf *btf); void btf_get(struct btf *btf); void btf_put(struct btf *btf); int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr, u32 uattr_sz); diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 02068bd0e4d9..96cba76f4ac3 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -110,102 +110,111 @@ const struct bpf_prog_ops bpf_struct_ops_prog_ops = { static const struct btf_type *module_type; -void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) +static void bpf_struct_ops_init_one(struct bpf_struct_ops *st_ops, + struct btf *btf, + struct bpf_verifier_log *log) { - s32 type_id, value_id, module_id; const struct btf_member *member; - struct bpf_struct_ops *st_ops; const struct btf_type *t; + s32 type_id, value_id; char value_name[128]; const char *mname; - u32 i, j; + int i; - /* Ensure BTF type is emitted for "struct bpf_struct_ops_##_name" */ -#define BPF_STRUCT_OPS_TYPE(_name) BTF_TYPE_EMIT(struct bpf_struct_ops_##_name); -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE + if (strlen(st_ops->name) + VALUE_PREFIX_LEN >= + sizeof(value_name)) { + pr_warn("struct_ops name %s is too long\n", + st_ops->name); + return; + } + sprintf(value_name, "%s%s", VALUE_PREFIX, st_ops->name); - module_id = btf_find_by_name_kind(btf, "module", BTF_KIND_STRUCT); - if (module_id < 0) { - pr_warn("Cannot find struct module in btf_vmlinux\n"); + value_id = btf_find_by_name_kind(btf, value_name, + BTF_KIND_STRUCT); + if (value_id < 0) { + pr_warn("Cannot find struct %s in %s\n", + value_name, btf_get_name(btf)); return; } - module_type = btf_type_by_id(btf, module_id); - for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - st_ops = bpf_struct_ops[i]; + type_id = btf_find_by_name_kind(btf, st_ops->name, + BTF_KIND_STRUCT); + if (type_id < 0) { + pr_warn("Cannot find struct %s in %s\n", + st_ops->name, btf_get_name(btf)); + return; + } + t = btf_type_by_id(btf, type_id); + if (btf_type_vlen(t) > BPF_STRUCT_OPS_MAX_NR_MEMBERS) { + pr_warn("Cannot support #%u members in struct %s\n", + btf_type_vlen(t), st_ops->name); + return; + } - if (strlen(st_ops->name) + VALUE_PREFIX_LEN >= - sizeof(value_name)) { - pr_warn("struct_ops name %s is too long\n", + for_each_member(i, t, member) { + const struct btf_type *func_proto; + + mname = btf_name_by_offset(btf, member->name_off); + if (!*mname) { + pr_warn("anon member in struct %s is not supported\n", st_ops->name); - continue; + break; } - sprintf(value_name, "%s%s", VALUE_PREFIX, st_ops->name); - value_id = btf_find_by_name_kind(btf, value_name, - BTF_KIND_STRUCT); - if (value_id < 0) { - pr_warn("Cannot find struct %s in btf_vmlinux\n", - value_name); - continue; + if (__btf_member_bitfield_size(t, member)) { + pr_warn("bit field member %s in struct %s is not supported\n", + mname, st_ops->name); + break; } - type_id = btf_find_by_name_kind(btf, st_ops->name, - BTF_KIND_STRUCT); - if (type_id < 0) { - pr_warn("Cannot find struct %s in btf_vmlinux\n", - st_ops->name); - continue; - } - t = btf_type_by_id(btf, type_id); - if (btf_type_vlen(t) > BPF_STRUCT_OPS_MAX_NR_MEMBERS) { - pr_warn("Cannot support #%u members in struct %s\n", - btf_type_vlen(t), st_ops->name); - continue; + func_proto = btf_type_resolve_func_ptr(btf, + member->type, + NULL); + if (func_proto && + btf_distill_func_proto(log, btf, + func_proto, mname, + &st_ops->func_models[i])) { + pr_warn("Error in parsing func ptr %s in struct %s\n", + mname, st_ops->name); + break; } + } - for_each_member(j, t, member) { - const struct btf_type *func_proto; + if (i == btf_type_vlen(t)) { + if (st_ops->init(btf)) { + pr_warn("Error in init bpf_struct_ops %s\n", + st_ops->name); + } else { + st_ops->type_id = type_id; + st_ops->type = t; + st_ops->value_id = value_id; + st_ops->value_type = btf_type_by_id(btf, + value_id); + } + } +} - mname = btf_name_by_offset(btf, member->name_off); - if (!*mname) { - pr_warn("anon member in struct %s is not supported\n", - st_ops->name); - break; - } +void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) +{ + struct bpf_struct_ops *st_ops; + s32 module_id; + u32 i; - if (__btf_member_bitfield_size(t, member)) { - pr_warn("bit field member %s in struct %s is not supported\n", - mname, st_ops->name); - break; - } + /* Ensure BTF type is emitted for "struct bpf_struct_ops_##_name" */ +#define BPF_STRUCT_OPS_TYPE(_name) BTF_TYPE_EMIT(struct bpf_struct_ops_##_name); +#include "bpf_struct_ops_types.h" +#undef BPF_STRUCT_OPS_TYPE - func_proto = btf_type_resolve_func_ptr(btf, - member->type, - NULL); - if (func_proto && - btf_distill_func_proto(log, btf, - func_proto, mname, - &st_ops->func_models[j])) { - pr_warn("Error in parsing func ptr %s in struct %s\n", - mname, st_ops->name); - break; - } - } + module_id = btf_find_by_name_kind(btf, "module", BTF_KIND_STRUCT); + if (module_id < 0) { + pr_warn("Cannot find struct module in %s\n", btf_get_name(btf)); + return; + } + module_type = btf_type_by_id(btf, module_id); - if (j == btf_type_vlen(t)) { - if (st_ops->init(btf)) { - pr_warn("Error in init bpf_struct_ops %s\n", - st_ops->name); - } else { - st_ops->type_id = type_id; - st_ops->type = t; - st_ops->value_id = value_id; - st_ops->value_type = btf_type_by_id(btf, - value_id); - } - } + for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { + st_ops = bpf_struct_ops[i]; + bpf_struct_ops_init_one(st_ops, btf, log); } } diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 4f532b303a27..f8735a2ec5d4 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -1707,6 +1707,11 @@ static void btf_free_rcu(struct rcu_head *rcu) btf_free(btf); } +const char *btf_get_name(const struct btf *btf) +{ + return btf->name; +} + void btf_get(struct btf *btf) { refcount_inc(&btf->refcnt); -- cgit v1.2.3 From 4c5763ed996a61b51d721d0968d0df957826ea49 Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Fri, 19 Jan 2024 14:49:54 -0800 Subject: bpf, net: introduce bpf_struct_ops_desc. Move some of members of bpf_struct_ops to bpf_struct_ops_desc. type_id is unavailabe in bpf_struct_ops anymore. Modules should get it from the btf received by kmod's init function. Cc: netdev@vger.kernel.org Signed-off-by: Kui-Feng Lee Link: https://lore.kernel.org/r/20240119225005.668602-4-thinker.li@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf.h | 15 +++++--- kernel/bpf/bpf_struct_ops.c | 80 ++++++++++++++++++++++-------------------- kernel/bpf/verifier.c | 8 +++-- net/bpf/bpf_dummy_struct_ops.c | 11 +++++- net/ipv4/bpf_tcp_ca.c | 8 ++++- 5 files changed, 73 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 377857b232c6..7fc95e7babab 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1673,18 +1673,23 @@ struct bpf_struct_ops { void (*unreg)(void *kdata); int (*update)(void *kdata, void *old_kdata); int (*validate)(void *kdata); - const struct btf_type *type; - const struct btf_type *value_type; + void *cfi_stubs; const char *name; struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS]; +}; + +struct bpf_struct_ops_desc { + struct bpf_struct_ops *st_ops; + + const struct btf_type *type; + const struct btf_type *value_type; u32 type_id; u32 value_id; - void *cfi_stubs; }; #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) #define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA)) -const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id); +const struct bpf_struct_ops_desc *bpf_struct_ops_find(u32 type_id); void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log); bool bpf_struct_ops_get(const void *kdata); void bpf_struct_ops_put(const void *kdata); @@ -1728,7 +1733,7 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); #endif #else -static inline const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id) +static inline const struct bpf_struct_ops_desc *bpf_struct_ops_find(u32 type_id) { return NULL; } diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 5b3ebcb435d0..9774f7824e8b 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -32,7 +32,7 @@ struct bpf_struct_ops_value { struct bpf_struct_ops_map { struct bpf_map map; struct rcu_head rcu; - const struct bpf_struct_ops *st_ops; + const struct bpf_struct_ops_desc *st_ops_desc; /* protect map_update */ struct mutex lock; /* link has all the bpf_links that is populated @@ -92,9 +92,9 @@ enum { __NR_BPF_STRUCT_OPS_TYPE, }; -static struct bpf_struct_ops * const bpf_struct_ops[] = { +static struct bpf_struct_ops_desc bpf_struct_ops[] = { #define BPF_STRUCT_OPS_TYPE(_name) \ - [BPF_STRUCT_OPS_TYPE_##_name] = &bpf_##_name, + [BPF_STRUCT_OPS_TYPE_##_name] = { .st_ops = &bpf_##_name }, #include "bpf_struct_ops_types.h" #undef BPF_STRUCT_OPS_TYPE }; @@ -115,10 +115,11 @@ enum { IDX_MODULE_ID, }; -static void bpf_struct_ops_init_one(struct bpf_struct_ops *st_ops, - struct btf *btf, - struct bpf_verifier_log *log) +static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, + struct btf *btf, + struct bpf_verifier_log *log) { + struct bpf_struct_ops *st_ops = st_ops_desc->st_ops; const struct btf_member *member; const struct btf_type *t; s32 type_id, value_id; @@ -190,18 +191,18 @@ static void bpf_struct_ops_init_one(struct bpf_struct_ops *st_ops, pr_warn("Error in init bpf_struct_ops %s\n", st_ops->name); } else { - st_ops->type_id = type_id; - st_ops->type = t; - st_ops->value_id = value_id; - st_ops->value_type = btf_type_by_id(btf, - value_id); + st_ops_desc->type_id = type_id; + st_ops_desc->type = t; + st_ops_desc->value_id = value_id; + st_ops_desc->value_type = btf_type_by_id(btf, + value_id); } } } void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) { - struct bpf_struct_ops *st_ops; + struct bpf_struct_ops_desc *st_ops_desc; u32 i; /* Ensure BTF type is emitted for "struct bpf_struct_ops_##_name" */ @@ -210,14 +211,14 @@ void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) #undef BPF_STRUCT_OPS_TYPE for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - st_ops = bpf_struct_ops[i]; - bpf_struct_ops_init_one(st_ops, btf, log); + st_ops_desc = &bpf_struct_ops[i]; + bpf_struct_ops_desc_init(st_ops_desc, btf, log); } } extern struct btf *btf_vmlinux; -static const struct bpf_struct_ops * +static const struct bpf_struct_ops_desc * bpf_struct_ops_find_value(u32 value_id) { unsigned int i; @@ -226,14 +227,14 @@ bpf_struct_ops_find_value(u32 value_id) return NULL; for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - if (bpf_struct_ops[i]->value_id == value_id) - return bpf_struct_ops[i]; + if (bpf_struct_ops[i].value_id == value_id) + return &bpf_struct_ops[i]; } return NULL; } -const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id) +const struct bpf_struct_ops_desc *bpf_struct_ops_find(u32 type_id) { unsigned int i; @@ -241,8 +242,8 @@ const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id) return NULL; for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - if (bpf_struct_ops[i]->type_id == type_id) - return bpf_struct_ops[i]; + if (bpf_struct_ops[i].type_id == type_id) + return &bpf_struct_ops[i]; } return NULL; @@ -302,7 +303,7 @@ static void *bpf_struct_ops_map_lookup_elem(struct bpf_map *map, void *key) static void bpf_struct_ops_map_put_progs(struct bpf_struct_ops_map *st_map) { - const struct btf_type *t = st_map->st_ops->type; + const struct btf_type *t = st_map->st_ops_desc->type; u32 i; for (i = 0; i < btf_type_vlen(t); i++) { @@ -382,11 +383,12 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, void *value, u64 flags) { struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; - const struct bpf_struct_ops *st_ops = st_map->st_ops; + const struct bpf_struct_ops_desc *st_ops_desc = st_map->st_ops_desc; + const struct bpf_struct_ops *st_ops = st_ops_desc->st_ops; struct bpf_struct_ops_value *uvalue, *kvalue; const struct btf_type *module_type; const struct btf_member *member; - const struct btf_type *t = st_ops->type; + const struct btf_type *t = st_ops_desc->type; struct bpf_tramp_links *tlinks; void *udata, *kdata; int prog_fd, err; @@ -399,7 +401,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, if (*(u32 *)key != 0) return -E2BIG; - err = check_zero_holes(st_ops->value_type, value); + err = check_zero_holes(st_ops_desc->value_type, value); if (err) return err; @@ -492,7 +494,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, } if (prog->type != BPF_PROG_TYPE_STRUCT_OPS || - prog->aux->attach_btf_id != st_ops->type_id || + prog->aux->attach_btf_id != st_ops_desc->type_id || prog->expected_attach_type != i) { bpf_prog_put(prog); err = -EINVAL; @@ -588,7 +590,7 @@ static long bpf_struct_ops_map_delete_elem(struct bpf_map *map, void *key) BPF_STRUCT_OPS_STATE_TOBEFREE); switch (prev_state) { case BPF_STRUCT_OPS_STATE_INUSE: - st_map->st_ops->unreg(&st_map->kvalue.data); + st_map->st_ops_desc->st_ops->unreg(&st_map->kvalue.data); bpf_map_put(map); return 0; case BPF_STRUCT_OPS_STATE_TOBEFREE: @@ -669,22 +671,22 @@ static int bpf_struct_ops_map_alloc_check(union bpf_attr *attr) static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) { - const struct bpf_struct_ops *st_ops; + const struct bpf_struct_ops_desc *st_ops_desc; size_t st_map_size; struct bpf_struct_ops_map *st_map; const struct btf_type *t, *vt; struct bpf_map *map; int ret; - st_ops = bpf_struct_ops_find_value(attr->btf_vmlinux_value_type_id); - if (!st_ops) + st_ops_desc = bpf_struct_ops_find_value(attr->btf_vmlinux_value_type_id); + if (!st_ops_desc) return ERR_PTR(-ENOTSUPP); - vt = st_ops->value_type; + vt = st_ops_desc->value_type; if (attr->value_size != vt->size) return ERR_PTR(-EINVAL); - t = st_ops->type; + t = st_ops_desc->type; st_map_size = sizeof(*st_map) + /* kvalue stores the @@ -696,7 +698,7 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) if (!st_map) return ERR_PTR(-ENOMEM); - st_map->st_ops = st_ops; + st_map->st_ops_desc = st_ops_desc; map = &st_map->map; ret = bpf_jit_charge_modmem(PAGE_SIZE); @@ -733,8 +735,8 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) static u64 bpf_struct_ops_map_mem_usage(const struct bpf_map *map) { struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; - const struct bpf_struct_ops *st_ops = st_map->st_ops; - const struct btf_type *vt = st_ops->value_type; + const struct bpf_struct_ops_desc *st_ops_desc = st_map->st_ops_desc; + const struct btf_type *vt = st_ops_desc->value_type; u64 usage; usage = sizeof(*st_map) + @@ -808,7 +810,7 @@ static void bpf_struct_ops_map_link_dealloc(struct bpf_link *link) /* st_link->map can be NULL if * bpf_struct_ops_link_create() fails to register. */ - st_map->st_ops->unreg(&st_map->kvalue.data); + st_map->st_ops_desc->st_ops->unreg(&st_map->kvalue.data); bpf_map_put(&st_map->map); } kfree(st_link); @@ -855,7 +857,7 @@ static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map if (!bpf_struct_ops_valid_to_reg(new_map)) return -EINVAL; - if (!st_map->st_ops->update) + if (!st_map->st_ops_desc->st_ops->update) return -EOPNOTSUPP; mutex_lock(&update_mutex); @@ -868,12 +870,12 @@ static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map old_st_map = container_of(old_map, struct bpf_struct_ops_map, map); /* The new and old struct_ops must be the same type. */ - if (st_map->st_ops != old_st_map->st_ops) { + if (st_map->st_ops_desc != old_st_map->st_ops_desc) { err = -EINVAL; goto err_out; } - err = st_map->st_ops->update(st_map->kvalue.data, old_st_map->kvalue.data); + err = st_map->st_ops_desc->st_ops->update(st_map->kvalue.data, old_st_map->kvalue.data); if (err) goto err_out; @@ -924,7 +926,7 @@ int bpf_struct_ops_link_create(union bpf_attr *attr) if (err) goto err_out; - err = st_map->st_ops->reg(st_map->kvalue.data); + err = st_map->st_ops_desc->st_ops->reg(st_map->kvalue.data); if (err) { bpf_link_cleanup(&link_primer); link = NULL; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 9e9cc132dd02..e279491118b7 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -20285,6 +20285,7 @@ static void print_verification_stats(struct bpf_verifier_env *env) static int check_struct_ops_btf_id(struct bpf_verifier_env *env) { const struct btf_type *t, *func_proto; + const struct bpf_struct_ops_desc *st_ops_desc; const struct bpf_struct_ops *st_ops; const struct btf_member *member; struct bpf_prog *prog = env->prog; @@ -20297,14 +20298,15 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) } btf_id = prog->aux->attach_btf_id; - st_ops = bpf_struct_ops_find(btf_id); - if (!st_ops) { + st_ops_desc = bpf_struct_ops_find(btf_id); + if (!st_ops_desc) { verbose(env, "attach_btf_id %u is not a supported struct\n", btf_id); return -ENOTSUPP; } + st_ops = st_ops_desc->st_ops; - t = st_ops->type; + t = st_ops_desc->type; member_idx = prog->expected_attach_type; if (member_idx >= btf_type_vlen(t)) { verbose(env, "attach to invalid member idx %u of struct %s\n", diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c index 8906f7bdf4a9..ba2c58dba2da 100644 --- a/net/bpf/bpf_dummy_struct_ops.c +++ b/net/bpf/bpf_dummy_struct_ops.c @@ -22,6 +22,8 @@ struct bpf_dummy_ops_test_args { struct bpf_dummy_ops_state state; }; +static struct btf *bpf_dummy_ops_btf; + static struct bpf_dummy_ops_test_args * dummy_ops_init_args(const union bpf_attr *kattr, unsigned int nr) { @@ -90,9 +92,15 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, void *image = NULL; unsigned int op_idx; int prog_ret; + s32 type_id; int err; - if (prog->aux->attach_btf_id != st_ops->type_id) + type_id = btf_find_by_name_kind(bpf_dummy_ops_btf, + bpf_bpf_dummy_ops.name, + BTF_KIND_STRUCT); + if (type_id < 0) + return -EINVAL; + if (prog->aux->attach_btf_id != type_id) return -EOPNOTSUPP; func_proto = prog->aux->attach_func_proto; @@ -148,6 +156,7 @@ out: static int bpf_dummy_init(struct btf *btf) { + bpf_dummy_ops_btf = btf; return 0; } diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index ae8b15e6896f..dffd8828079b 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -20,6 +20,7 @@ static u32 unsupported_ops[] = { static const struct btf_type *tcp_sock_type; static u32 tcp_sock_id, sock_id; +static const struct btf_type *tcp_congestion_ops_type; static int bpf_tcp_ca_init(struct btf *btf) { @@ -36,6 +37,11 @@ static int bpf_tcp_ca_init(struct btf *btf) tcp_sock_id = type_id; tcp_sock_type = btf_type_by_id(btf, tcp_sock_id); + type_id = btf_find_by_name_kind(btf, "tcp_congestion_ops", BTF_KIND_STRUCT); + if (type_id < 0) + return -EINVAL; + tcp_congestion_ops_type = btf_type_by_id(btf, type_id); + return 0; } @@ -149,7 +155,7 @@ static u32 prog_ops_moff(const struct bpf_prog *prog) u32 midx; midx = prog->expected_attach_type; - t = bpf_tcp_congestion_ops.type; + t = tcp_congestion_ops_type; m = &btf_type_member(t)[midx]; return __btf_member_bit_offset(t, m) / 8; -- cgit v1.2.3 From 1338b93346587a2a6ac79bbcf55ef5b357745573 Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Fri, 19 Jan 2024 14:49:57 -0800 Subject: bpf: pass btf object id in bpf_map_info. Include btf object id (btf_obj_id) in bpf_map_info so that tools (ex: bpftools struct_ops dump) know the correct btf from the kernel to look up type information of struct_ops types. Since struct_ops types can be defined and registered in a module. The type information of a struct_ops type are defined in the btf of the module defining it. The userspace tools need to know which btf is for the module defining a struct_ops type. Signed-off-by: Kui-Feng Lee Link: https://lore.kernel.org/r/20240119225005.668602-7-thinker.li@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf.h | 4 ++++ include/uapi/linux/bpf.h | 2 +- kernel/bpf/bpf_struct_ops.c | 7 +++++++ kernel/bpf/syscall.c | 2 ++ tools/include/uapi/linux/bpf.h | 2 +- 5 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7fc95e7babab..29fcae9fa8ed 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1732,6 +1732,7 @@ struct bpf_dummy_ops { int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); #endif +void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map); #else static inline const struct bpf_struct_ops_desc *bpf_struct_ops_find(u32 type_id) { @@ -1759,6 +1760,9 @@ static inline int bpf_struct_ops_link_create(union bpf_attr *attr) { return -EOPNOTSUPP; } +static inline void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map) +{ +} #endif diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 287d05732668..a380047c86af 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6487,7 +6487,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; - __u32 :32; /* alignment pad */ + __u32 btf_vmlinux_id; __u64 map_extra; } __attribute__((aligned(8))); diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 5ddcca4c4fba..5e98af4fc2e2 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -947,3 +947,10 @@ err_out: kfree(link); return err; } + +void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map) +{ + struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; + + info->btf_vmlinux_id = btf_obj_id(st_map->btf); +} diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 13193aaafb64..55b458429705 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -4691,6 +4691,8 @@ static int bpf_map_get_info_by_fd(struct file *file, info.btf_value_type_id = map->btf_value_type_id; } info.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; + if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) + bpf_map_struct_ops_info_fill(&info, map); if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_info_fill(&info, map); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 287d05732668..a380047c86af 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -6487,7 +6487,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; - __u32 :32; /* alignment pad */ + __u32 btf_vmlinux_id; __u64 map_extra; } __attribute__((aligned(8))); -- cgit v1.2.3 From 689423db3bda2244c24db8a64de4cdb37be1de41 Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Fri, 19 Jan 2024 14:49:58 -0800 Subject: bpf: lookup struct_ops types from a given module BTF. This is a preparation for searching for struct_ops types from a specified module. BTF is always btf_vmlinux now. This patch passes a pointer of BTF to bpf_struct_ops_find_value() and bpf_struct_ops_find(). Once the new registration API of struct_ops types is used, other BTFs besides btf_vmlinux can also be passed to them. Signed-off-by: Kui-Feng Lee Link: https://lore.kernel.org/r/20240119225005.668602-8-thinker.li@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf.h | 4 ++-- kernel/bpf/bpf_struct_ops.c | 11 ++++++----- kernel/bpf/verifier.c | 2 +- 3 files changed, 9 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 29fcae9fa8ed..86ff8911d7ee 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1689,7 +1689,7 @@ struct bpf_struct_ops_desc { #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) #define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA)) -const struct bpf_struct_ops_desc *bpf_struct_ops_find(u32 type_id); +const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf *btf, u32 type_id); void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log); bool bpf_struct_ops_get(const void *kdata); void bpf_struct_ops_put(const void *kdata); @@ -1734,7 +1734,7 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, #endif void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map); #else -static inline const struct bpf_struct_ops_desc *bpf_struct_ops_find(u32 type_id) +static inline const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf *btf, u32 type_id) { return NULL; } diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 5e98af4fc2e2..7505f515aac3 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -221,11 +221,11 @@ void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) extern struct btf *btf_vmlinux; static const struct bpf_struct_ops_desc * -bpf_struct_ops_find_value(u32 value_id) +bpf_struct_ops_find_value(struct btf *btf, u32 value_id) { unsigned int i; - if (!value_id || !btf_vmlinux) + if (!value_id || !btf) return NULL; for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { @@ -236,11 +236,12 @@ bpf_struct_ops_find_value(u32 value_id) return NULL; } -const struct bpf_struct_ops_desc *bpf_struct_ops_find(u32 type_id) +const struct bpf_struct_ops_desc * +bpf_struct_ops_find(struct btf *btf, u32 type_id) { unsigned int i; - if (!type_id || !btf_vmlinux) + if (!type_id || !btf) return NULL; for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { @@ -682,7 +683,7 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) struct bpf_map *map; int ret; - st_ops_desc = bpf_struct_ops_find_value(attr->btf_vmlinux_value_type_id); + st_ops_desc = bpf_struct_ops_find_value(btf_vmlinux, attr->btf_vmlinux_value_type_id); if (!st_ops_desc) return ERR_PTR(-ENOTSUPP); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e279491118b7..2a0fd2ccdb11 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -20298,7 +20298,7 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) } btf_id = prog->aux->attach_btf_id; - st_ops_desc = bpf_struct_ops_find(btf_id); + st_ops_desc = bpf_struct_ops_find(btf_vmlinux, btf_id); if (!st_ops_desc) { verbose(env, "attach_btf_id %u is not a supported struct\n", btf_id); -- cgit v1.2.3 From e3f87fdfed7b770dd7066b02262b12747881e76d Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Fri, 19 Jan 2024 14:50:00 -0800 Subject: bpf: hold module refcnt in bpf_struct_ops map creation and prog verification. To ensure that a module remains accessible whenever a struct_ops object of a struct_ops type provided by the module is still in use. struct bpf_struct_ops_map doesn't hold a refcnt to btf anymore since a module will hold a refcnt to it's btf already. But, struct_ops programs are different. They hold their associated btf, not the module since they need only btf to assure their types (signatures). However, verifier holds the refcnt of the associated module of a struct_ops type temporarily when verify a struct_ops prog. Verifier needs the help from the verifier operators (struct bpf_verifier_ops) provided by the owner module to verify data access of a prog, provide information, and generate code. This patch also add a count of links (links_cnt) to bpf_struct_ops_map. It avoids bpf_struct_ops_map_put_progs() from accessing btf after calling module_put() in bpf_struct_ops_map_free(). Signed-off-by: Kui-Feng Lee Link: https://lore.kernel.org/r/20240119225005.668602-10-thinker.li@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf.h | 1 + include/linux/bpf_verifier.h | 1 + kernel/bpf/bpf_struct_ops.c | 29 +++++++++++++++++++++++------ kernel/bpf/verifier.c | 11 +++++++++++ 4 files changed, 36 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 86ff8911d7ee..a5b425893d38 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1674,6 +1674,7 @@ struct bpf_struct_ops { int (*update)(void *kdata, void *old_kdata); int (*validate)(void *kdata); void *cfi_stubs; + struct module *owner; const char *name; struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS]; }; diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index e11baecbde68..7f5816482a10 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -662,6 +662,7 @@ struct bpf_verifier_env { u32 prev_insn_idx; struct bpf_prog *prog; /* eBPF program being verified */ const struct bpf_verifier_ops *ops; + struct module *attach_btf_mod; /* The owner module of prog->aux->attach_btf */ struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */ int stack_size; /* number of states to be processed */ bool strict_alignment; /* perform strict pointer alignment checks */ diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 3b8d689ece5d..02216a8d9265 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -40,6 +40,7 @@ struct bpf_struct_ops_map { * (in kvalue.data). */ struct bpf_link **links; + u32 links_cnt; /* image is a page that has all the trampolines * that stores the func args before calling the bpf_prog. * A PAGE_SIZE "image" is enough to store all trampoline for @@ -306,10 +307,9 @@ static void *bpf_struct_ops_map_lookup_elem(struct bpf_map *map, void *key) static void bpf_struct_ops_map_put_progs(struct bpf_struct_ops_map *st_map) { - const struct btf_type *t = st_map->st_ops_desc->type; u32 i; - for (i = 0; i < btf_type_vlen(t); i++) { + for (i = 0; i < st_map->links_cnt; i++) { if (st_map->links[i]) { bpf_link_put(st_map->links[i]); st_map->links[i] = NULL; @@ -641,12 +641,20 @@ static void __bpf_struct_ops_map_free(struct bpf_map *map) bpf_jit_uncharge_modmem(PAGE_SIZE); } bpf_map_area_free(st_map->uvalue); - btf_put(st_map->btf); bpf_map_area_free(st_map); } static void bpf_struct_ops_map_free(struct bpf_map *map) { + struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; + + /* st_ops->owner was acquired during map_alloc to implicitly holds + * the btf's refcnt. The acquire was only done when btf_is_module() + * st_map->btf cannot be NULL here. + */ + if (btf_is_module(st_map->btf)) + module_put(st_map->st_ops_desc->st_ops->owner); + /* The struct_ops's function may switch to another struct_ops. * * For example, bpf_tcp_cc_x->init() may switch to @@ -682,6 +690,7 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) size_t st_map_size; struct bpf_struct_ops_map *st_map; const struct btf_type *t, *vt; + struct module *mod = NULL; struct bpf_map *map; struct btf *btf; int ret; @@ -695,11 +704,18 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) btf_put(btf); return ERR_PTR(-EINVAL); } + + mod = btf_try_get_module(btf); + /* mod holds a refcnt to btf. We don't need an extra refcnt + * here. + */ + btf_put(btf); + if (!mod) + return ERR_PTR(-EINVAL); } else { btf = bpf_get_btf_vmlinux(); if (IS_ERR(btf)) return ERR_CAST(btf); - btf_get(btf); } st_ops_desc = bpf_struct_ops_find_value(btf, attr->btf_vmlinux_value_type_id); @@ -746,8 +762,9 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) goto errout_free; } st_map->uvalue = bpf_map_area_alloc(vt->size, NUMA_NO_NODE); + st_map->links_cnt = btf_type_vlen(t); st_map->links = - bpf_map_area_alloc(btf_type_vlen(t) * sizeof(struct bpf_links *), + bpf_map_area_alloc(st_map->links_cnt * sizeof(struct bpf_links *), NUMA_NO_NODE); if (!st_map->uvalue || !st_map->links) { ret = -ENOMEM; @@ -763,7 +780,7 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) errout_free: __bpf_struct_ops_map_free(map); errout: - btf_put(btf); + module_put(mod); return ERR_PTR(ret); } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6081512deb79..f31868ba0c2d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -20299,6 +20299,15 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) } btf = prog->aux->attach_btf ?: bpf_get_btf_vmlinux(); + if (btf_is_module(btf)) { + /* Make sure st_ops is valid through the lifetime of env */ + env->attach_btf_mod = btf_try_get_module(btf); + if (!env->attach_btf_mod) { + verbose(env, "struct_ops module %s is not found\n", + btf_get_name(btf)); + return -ENOTSUPP; + } + } btf_id = prog->aux->attach_btf_id; st_ops_desc = bpf_struct_ops_find(btf, btf_id); @@ -21024,6 +21033,8 @@ err_release_maps: env->prog->expected_attach_type = 0; *prog = env->prog; + + module_put(env->attach_btf_mod); err_unlock: if (!is_priv) mutex_unlock(&bpf_verifier_lock); -- cgit v1.2.3 From 612d087d4ba54cef47946e22e5dabad762dd7ed5 Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Fri, 19 Jan 2024 14:50:01 -0800 Subject: bpf: validate value_type A value_type should consist of three components: refcnt, state, and data. refcnt and state has been move to struct bpf_struct_ops_common_value to make it easier to check the value type. Signed-off-by: Kui-Feng Lee Link: https://lore.kernel.org/r/20240119225005.668602-11-thinker.li@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf.h | 12 ++++++ kernel/bpf/bpf_struct_ops.c | 93 +++++++++++++++++++++++++++++---------------- 2 files changed, 72 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a5b425893d38..7c178170f93f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1688,6 +1688,18 @@ struct bpf_struct_ops_desc { u32 value_id; }; +enum bpf_struct_ops_state { + BPF_STRUCT_OPS_STATE_INIT, + BPF_STRUCT_OPS_STATE_INUSE, + BPF_STRUCT_OPS_STATE_TOBEFREE, + BPF_STRUCT_OPS_STATE_READY, +}; + +struct bpf_struct_ops_common_value { + refcount_t refcnt; + enum bpf_struct_ops_state state; +}; + #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) #define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA)) const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf *btf, u32 type_id); diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 02216a8d9265..30ab34fab0f8 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -13,19 +13,8 @@ #include #include -enum bpf_struct_ops_state { - BPF_STRUCT_OPS_STATE_INIT, - BPF_STRUCT_OPS_STATE_INUSE, - BPF_STRUCT_OPS_STATE_TOBEFREE, - BPF_STRUCT_OPS_STATE_READY, -}; - -#define BPF_STRUCT_OPS_COMMON_VALUE \ - refcount_t refcnt; \ - enum bpf_struct_ops_state state - struct bpf_struct_ops_value { - BPF_STRUCT_OPS_COMMON_VALUE; + struct bpf_struct_ops_common_value common; char data[] ____cacheline_aligned_in_smp; }; @@ -81,8 +70,8 @@ static DEFINE_MUTEX(update_mutex); #define BPF_STRUCT_OPS_TYPE(_name) \ extern struct bpf_struct_ops bpf_##_name; \ \ -struct bpf_struct_ops_##_name { \ - BPF_STRUCT_OPS_COMMON_VALUE; \ +struct bpf_struct_ops_##_name { \ + struct bpf_struct_ops_common_value common; \ struct _name data ____cacheline_aligned_in_smp; \ }; #include "bpf_struct_ops_types.h" @@ -113,11 +102,49 @@ const struct bpf_prog_ops bpf_struct_ops_prog_ops = { BTF_ID_LIST(st_ops_ids) BTF_ID(struct, module) +BTF_ID(struct, bpf_struct_ops_common_value) enum { IDX_MODULE_ID, + IDX_ST_OPS_COMMON_VALUE_ID, }; +extern struct btf *btf_vmlinux; + +static bool is_valid_value_type(struct btf *btf, s32 value_id, + const struct btf_type *type, + const char *value_name) +{ + const struct btf_type *common_value_type; + const struct btf_member *member; + const struct btf_type *vt, *mt; + + vt = btf_type_by_id(btf, value_id); + if (btf_vlen(vt) != 2) { + pr_warn("The number of %s's members should be 2, but we get %d\n", + value_name, btf_vlen(vt)); + return false; + } + member = btf_type_member(vt); + mt = btf_type_by_id(btf, member->type); + common_value_type = btf_type_by_id(btf_vmlinux, + st_ops_ids[IDX_ST_OPS_COMMON_VALUE_ID]); + if (mt != common_value_type) { + pr_warn("The first member of %s should be bpf_struct_ops_common_value\n", + value_name); + return false; + } + member++; + mt = btf_type_by_id(btf, member->type); + if (mt != type) { + pr_warn("The second member of %s should be %s\n", + value_name, btf_name_by_offset(btf, type->name_off)); + return false; + } + + return true; +} + static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, struct btf *btf, struct bpf_verifier_log *log) @@ -138,14 +165,6 @@ static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, } sprintf(value_name, "%s%s", VALUE_PREFIX, st_ops->name); - value_id = btf_find_by_name_kind(btf, value_name, - BTF_KIND_STRUCT); - if (value_id < 0) { - pr_warn("Cannot find struct %s in %s\n", - value_name, btf_get_name(btf)); - return; - } - type_id = btf_find_by_name_kind(btf, st_ops->name, BTF_KIND_STRUCT); if (type_id < 0) { @@ -160,6 +179,16 @@ static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, return; } + value_id = btf_find_by_name_kind(btf, value_name, + BTF_KIND_STRUCT); + if (value_id < 0) { + pr_warn("Cannot find struct %s in %s\n", + value_name, btf_get_name(btf)); + return; + } + if (!is_valid_value_type(btf, value_id, t, value_name)) + return; + for_each_member(i, t, member) { const struct btf_type *func_proto; @@ -219,8 +248,6 @@ void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) } } -extern struct btf *btf_vmlinux; - static const struct bpf_struct_ops_desc * bpf_struct_ops_find_value(struct btf *btf, u32 value_id) { @@ -276,7 +303,7 @@ int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, kvalue = &st_map->kvalue; /* Pair with smp_store_release() during map_update */ - state = smp_load_acquire(&kvalue->state); + state = smp_load_acquire(&kvalue->common.state); if (state == BPF_STRUCT_OPS_STATE_INIT) { memset(value, 0, map->value_size); return 0; @@ -287,7 +314,7 @@ int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, */ uvalue = value; memcpy(uvalue, st_map->uvalue, map->value_size); - uvalue->state = state; + uvalue->common.state = state; /* This value offers the user space a general estimate of how * many sockets are still utilizing this struct_ops for TCP @@ -295,7 +322,7 @@ int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, * should sufficiently meet our present goals. */ refcnt = atomic64_read(&map->refcnt) - atomic64_read(&map->usercnt); - refcount_set(&uvalue->refcnt, max_t(s64, refcnt, 0)); + refcount_set(&uvalue->common.refcnt, max_t(s64, refcnt, 0)); return 0; } @@ -413,7 +440,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, if (err) return err; - if (uvalue->state || refcount_read(&uvalue->refcnt)) + if (uvalue->common.state || refcount_read(&uvalue->common.refcnt)) return -EINVAL; tlinks = kcalloc(BPF_TRAMP_MAX, sizeof(*tlinks), GFP_KERNEL); @@ -425,7 +452,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, mutex_lock(&st_map->lock); - if (kvalue->state != BPF_STRUCT_OPS_STATE_INIT) { + if (kvalue->common.state != BPF_STRUCT_OPS_STATE_INIT) { err = -EBUSY; goto unlock; } @@ -540,7 +567,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, * * Pair with smp_load_acquire() during lookup_elem(). */ - smp_store_release(&kvalue->state, BPF_STRUCT_OPS_STATE_READY); + smp_store_release(&kvalue->common.state, BPF_STRUCT_OPS_STATE_READY); goto unlock; } @@ -558,7 +585,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, * It ensures the above udata updates (e.g. prog->aux->id) * can be seen once BPF_STRUCT_OPS_STATE_INUSE is set. */ - smp_store_release(&kvalue->state, BPF_STRUCT_OPS_STATE_INUSE); + smp_store_release(&kvalue->common.state, BPF_STRUCT_OPS_STATE_INUSE); goto unlock; } @@ -588,7 +615,7 @@ static long bpf_struct_ops_map_delete_elem(struct bpf_map *map, void *key) if (st_map->map.map_flags & BPF_F_LINK) return -EOPNOTSUPP; - prev_state = cmpxchg(&st_map->kvalue.state, + prev_state = cmpxchg(&st_map->kvalue.common.state, BPF_STRUCT_OPS_STATE_INUSE, BPF_STRUCT_OPS_STATE_TOBEFREE); switch (prev_state) { @@ -848,7 +875,7 @@ static bool bpf_struct_ops_valid_to_reg(struct bpf_map *map) return map->map_type == BPF_MAP_TYPE_STRUCT_OPS && map->map_flags & BPF_F_LINK && /* Pair with smp_store_release() during map_update */ - smp_load_acquire(&st_map->kvalue.state) == BPF_STRUCT_OPS_STATE_READY; + smp_load_acquire(&st_map->kvalue.common.state) == BPF_STRUCT_OPS_STATE_READY; } static void bpf_struct_ops_map_link_dealloc(struct bpf_link *link) -- cgit v1.2.3 From f6be98d19985411ca1f3d53413d94d5b7f41c200 Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Fri, 19 Jan 2024 14:50:02 -0800 Subject: bpf, net: switch to dynamic registration Replace the static list of struct_ops types with per-btf struct_ops_tab to enable dynamic registration. Both bpf_dummy_ops and bpf_tcp_ca now utilize the registration function instead of being listed in bpf_struct_ops_types.h. Cc: netdev@vger.kernel.org Signed-off-by: Kui-Feng Lee Link: https://lore.kernel.org/r/20240119225005.668602-12-thinker.li@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf.h | 27 ++++++---- include/linux/btf.h | 12 +++++ kernel/bpf/bpf_struct_ops.c | 100 +++++--------------------------------- kernel/bpf/bpf_struct_ops_types.h | 12 ----- kernel/bpf/btf.c | 86 ++++++++++++++++++++++++++++++-- net/bpf/bpf_dummy_struct_ops.c | 11 ++++- net/ipv4/bpf_tcp_ca.c | 12 +++-- 7 files changed, 142 insertions(+), 118 deletions(-) delete mode 100644 kernel/bpf/bpf_struct_ops_types.h (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7c178170f93f..75b7f9b19c6a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1701,9 +1701,20 @@ struct bpf_struct_ops_common_value { }; #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) +/* This macro helps developer to register a struct_ops type and generate + * type information correctly. Developers should use this macro to register + * a struct_ops type instead of calling __register_bpf_struct_ops() directly. + */ +#define register_bpf_struct_ops(st_ops, type) \ + ({ \ + struct bpf_struct_ops_##type { \ + struct bpf_struct_ops_common_value common; \ + struct type data ____cacheline_aligned_in_smp; \ + }; \ + BTF_TYPE_EMIT(struct bpf_struct_ops_##type); \ + __register_bpf_struct_ops(st_ops); \ + }) #define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA)) -const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf *btf, u32 type_id); -void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log); bool bpf_struct_ops_get(const void *kdata); void bpf_struct_ops_put(const void *kdata); int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, @@ -1745,16 +1756,12 @@ struct bpf_dummy_ops { int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); #endif +int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, + struct btf *btf, + struct bpf_verifier_log *log); void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map); #else -static inline const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf *btf, u32 type_id) -{ - return NULL; -} -static inline void bpf_struct_ops_init(struct btf *btf, - struct bpf_verifier_log *log) -{ -} +#define register_bpf_struct_ops(st_ops, type) ({ (void *)(st_ops); 0; }) static inline bool bpf_try_module_get(const void *data, struct module *owner) { return try_module_get(owner); diff --git a/include/linux/btf.h b/include/linux/btf.h index 932af1680bb5..1ee8977b8c95 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -497,6 +497,18 @@ static inline void *btf_id_set8_contains(const struct btf_id_set8 *set, u32 id) struct bpf_verifier_log; +#if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) +struct bpf_struct_ops; +int __register_bpf_struct_ops(struct bpf_struct_ops *st_ops); +const struct bpf_struct_ops_desc *bpf_struct_ops_find_value(struct btf *btf, u32 value_id); +const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf *btf, u32 type_id); +#else +static inline const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf *btf, u32 type_id) +{ + return NULL; +} +#endif + #ifdef CONFIG_BPF_SYSCALL const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); const char *btf_name_by_offset(const struct btf *btf, u32 offset); diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 30ab34fab0f8..defc052e4622 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -62,35 +62,6 @@ static DEFINE_MUTEX(update_mutex); #define VALUE_PREFIX "bpf_struct_ops_" #define VALUE_PREFIX_LEN (sizeof(VALUE_PREFIX) - 1) -/* bpf_struct_ops_##_name (e.g. bpf_struct_ops_tcp_congestion_ops) is - * the map's value exposed to the userspace and its btf-type-id is - * stored at the map->btf_vmlinux_value_type_id. - * - */ -#define BPF_STRUCT_OPS_TYPE(_name) \ -extern struct bpf_struct_ops bpf_##_name; \ - \ -struct bpf_struct_ops_##_name { \ - struct bpf_struct_ops_common_value common; \ - struct _name data ____cacheline_aligned_in_smp; \ -}; -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE - -enum { -#define BPF_STRUCT_OPS_TYPE(_name) BPF_STRUCT_OPS_TYPE_##_name, -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE - __NR_BPF_STRUCT_OPS_TYPE, -}; - -static struct bpf_struct_ops_desc bpf_struct_ops[] = { -#define BPF_STRUCT_OPS_TYPE(_name) \ - [BPF_STRUCT_OPS_TYPE_##_name] = { .st_ops = &bpf_##_name }, -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE -}; - const struct bpf_verifier_ops bpf_struct_ops_verifier_ops = { }; @@ -145,9 +116,9 @@ static bool is_valid_value_type(struct btf *btf, s32 value_id, return true; } -static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, - struct btf *btf, - struct bpf_verifier_log *log) +int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, + struct btf *btf, + struct bpf_verifier_log *log) { struct bpf_struct_ops *st_ops = st_ops_desc->st_ops; const struct btf_member *member; @@ -161,7 +132,7 @@ static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, sizeof(value_name)) { pr_warn("struct_ops name %s is too long\n", st_ops->name); - return; + return -EINVAL; } sprintf(value_name, "%s%s", VALUE_PREFIX, st_ops->name); @@ -170,13 +141,13 @@ static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, if (type_id < 0) { pr_warn("Cannot find struct %s in %s\n", st_ops->name, btf_get_name(btf)); - return; + return -EINVAL; } t = btf_type_by_id(btf, type_id); if (btf_type_vlen(t) > BPF_STRUCT_OPS_MAX_NR_MEMBERS) { pr_warn("Cannot support #%u members in struct %s\n", btf_type_vlen(t), st_ops->name); - return; + return -EINVAL; } value_id = btf_find_by_name_kind(btf, value_name, @@ -184,10 +155,10 @@ static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, if (value_id < 0) { pr_warn("Cannot find struct %s in %s\n", value_name, btf_get_name(btf)); - return; + return -EINVAL; } if (!is_valid_value_type(btf, value_id, t, value_name)) - return; + return -EINVAL; for_each_member(i, t, member) { const struct btf_type *func_proto; @@ -196,13 +167,13 @@ static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, if (!*mname) { pr_warn("anon member in struct %s is not supported\n", st_ops->name); - break; + return -EOPNOTSUPP; } if (__btf_member_bitfield_size(t, member)) { pr_warn("bit field member %s in struct %s is not supported\n", mname, st_ops->name); - break; + return -EOPNOTSUPP; } func_proto = btf_type_resolve_func_ptr(btf, @@ -214,7 +185,7 @@ static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, &st_ops->func_models[i])) { pr_warn("Error in parsing func ptr %s in struct %s\n", mname, st_ops->name); - break; + return -EINVAL; } } @@ -222,6 +193,7 @@ static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, if (st_ops->init(btf)) { pr_warn("Error in init bpf_struct_ops %s\n", st_ops->name); + return -EINVAL; } else { st_ops_desc->type_id = type_id; st_ops_desc->type = t; @@ -230,54 +202,8 @@ static void bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, value_id); } } -} -void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) -{ - struct bpf_struct_ops_desc *st_ops_desc; - u32 i; - - /* Ensure BTF type is emitted for "struct bpf_struct_ops_##_name" */ -#define BPF_STRUCT_OPS_TYPE(_name) BTF_TYPE_EMIT(struct bpf_struct_ops_##_name); -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE - - for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - st_ops_desc = &bpf_struct_ops[i]; - bpf_struct_ops_desc_init(st_ops_desc, btf, log); - } -} - -static const struct bpf_struct_ops_desc * -bpf_struct_ops_find_value(struct btf *btf, u32 value_id) -{ - unsigned int i; - - if (!value_id || !btf) - return NULL; - - for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - if (bpf_struct_ops[i].value_id == value_id) - return &bpf_struct_ops[i]; - } - - return NULL; -} - -const struct bpf_struct_ops_desc * -bpf_struct_ops_find(struct btf *btf, u32 type_id) -{ - unsigned int i; - - if (!type_id || !btf) - return NULL; - - for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - if (bpf_struct_ops[i].type_id == type_id) - return &bpf_struct_ops[i]; - } - - return NULL; + return 0; } static int bpf_struct_ops_map_get_next_key(struct bpf_map *map, void *key, diff --git a/kernel/bpf/bpf_struct_ops_types.h b/kernel/bpf/bpf_struct_ops_types.h deleted file mode 100644 index 5678a9ddf817..000000000000 --- a/kernel/bpf/bpf_struct_ops_types.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* internal file - do not include directly */ - -#ifdef CONFIG_BPF_JIT -#ifdef CONFIG_NET -BPF_STRUCT_OPS_TYPE(bpf_dummy_ops) -#endif -#ifdef CONFIG_INET -#include -BPF_STRUCT_OPS_TYPE(tcp_congestion_ops) -#endif -#endif diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 2e5e6ec5d965..5c3e526a2dec 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -5972,8 +5973,6 @@ struct btf *btf_parse_vmlinux(void) /* btf_parse_vmlinux() runs under bpf_verifier_lock */ bpf_ctx_convert.t = btf_type_by_id(btf, bpf_ctx_convert_btf_id[0]); - bpf_struct_ops_init(btf, log); - refcount_set(&btf->refcnt, 1); err = btf_alloc_id(btf); @@ -8706,11 +8705,13 @@ bool btf_type_ids_nocast_alias(struct bpf_verifier_log *log, return !strncmp(reg_name, arg_name, cmp_len); } +#ifdef CONFIG_BPF_JIT static int -btf_add_struct_ops(struct btf *btf, struct bpf_struct_ops *st_ops) +btf_add_struct_ops(struct btf *btf, struct bpf_struct_ops *st_ops, + struct bpf_verifier_log *log) { struct btf_struct_ops_tab *tab, *new_tab; - int i; + int i, err; tab = btf->struct_ops_tab; if (!tab) { @@ -8740,7 +8741,84 @@ btf_add_struct_ops(struct btf *btf, struct bpf_struct_ops *st_ops) tab->ops[btf->struct_ops_tab->cnt].st_ops = st_ops; + err = bpf_struct_ops_desc_init(&tab->ops[btf->struct_ops_tab->cnt], btf, log); + if (err) + return err; + btf->struct_ops_tab->cnt++; return 0; } + +const struct bpf_struct_ops_desc * +bpf_struct_ops_find_value(struct btf *btf, u32 value_id) +{ + const struct bpf_struct_ops_desc *st_ops_list; + unsigned int i; + u32 cnt; + + if (!value_id) + return NULL; + if (!btf->struct_ops_tab) + return NULL; + + cnt = btf->struct_ops_tab->cnt; + st_ops_list = btf->struct_ops_tab->ops; + for (i = 0; i < cnt; i++) { + if (st_ops_list[i].value_id == value_id) + return &st_ops_list[i]; + } + + return NULL; +} + +const struct bpf_struct_ops_desc * +bpf_struct_ops_find(struct btf *btf, u32 type_id) +{ + const struct bpf_struct_ops_desc *st_ops_list; + unsigned int i; + u32 cnt; + + if (!type_id) + return NULL; + if (!btf->struct_ops_tab) + return NULL; + + cnt = btf->struct_ops_tab->cnt; + st_ops_list = btf->struct_ops_tab->ops; + for (i = 0; i < cnt; i++) { + if (st_ops_list[i].type_id == type_id) + return &st_ops_list[i]; + } + + return NULL; +} + +int __register_bpf_struct_ops(struct bpf_struct_ops *st_ops) +{ + struct bpf_verifier_log *log; + struct btf *btf; + int err = 0; + + btf = btf_get_module_btf(st_ops->owner); + if (!btf) + return -EINVAL; + + log = kzalloc(sizeof(*log), GFP_KERNEL | __GFP_NOWARN); + if (!log) { + err = -ENOMEM; + goto errout; + } + + log->level = BPF_LOG_KERNEL; + + err = btf_add_struct_ops(btf, st_ops, log); + +errout: + kfree(log); + btf_put(btf); + + return err; +} +EXPORT_SYMBOL_GPL(__register_bpf_struct_ops); +#endif diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c index ba2c58dba2da..02de71719aed 100644 --- a/net/bpf/bpf_dummy_struct_ops.c +++ b/net/bpf/bpf_dummy_struct_ops.c @@ -7,7 +7,7 @@ #include #include -extern struct bpf_struct_ops bpf_bpf_dummy_ops; +static struct bpf_struct_ops bpf_bpf_dummy_ops; /* A common type for test_N with return value in bpf_dummy_ops */ typedef int (*dummy_ops_test_ret_fn)(struct bpf_dummy_ops_state *state, ...); @@ -256,7 +256,7 @@ static struct bpf_dummy_ops __bpf_bpf_dummy_ops = { .test_sleepable = bpf_dummy_test_sleepable, }; -struct bpf_struct_ops bpf_bpf_dummy_ops = { +static struct bpf_struct_ops bpf_bpf_dummy_ops = { .verifier_ops = &bpf_dummy_verifier_ops, .init = bpf_dummy_init, .check_member = bpf_dummy_ops_check_member, @@ -265,4 +265,11 @@ struct bpf_struct_ops bpf_bpf_dummy_ops = { .unreg = bpf_dummy_unreg, .name = "bpf_dummy_ops", .cfi_stubs = &__bpf_bpf_dummy_ops, + .owner = THIS_MODULE, }; + +static int __init bpf_dummy_struct_ops_init(void) +{ + return register_bpf_struct_ops(&bpf_bpf_dummy_ops, bpf_dummy_ops); +} +late_initcall(bpf_dummy_struct_ops_init); diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index dffd8828079b..8e7716256d3c 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -12,7 +12,7 @@ #include /* "extern" is to avoid sparse warning. It is only used in bpf_struct_ops.c. */ -extern struct bpf_struct_ops bpf_tcp_congestion_ops; +static struct bpf_struct_ops bpf_tcp_congestion_ops; static u32 unsupported_ops[] = { offsetof(struct tcp_congestion_ops, get_info), @@ -345,7 +345,7 @@ static struct tcp_congestion_ops __bpf_ops_tcp_congestion_ops = { .release = __bpf_tcp_ca_release, }; -struct bpf_struct_ops bpf_tcp_congestion_ops = { +static struct bpf_struct_ops bpf_tcp_congestion_ops = { .verifier_ops = &bpf_tcp_ca_verifier_ops, .reg = bpf_tcp_ca_reg, .unreg = bpf_tcp_ca_unreg, @@ -356,10 +356,16 @@ struct bpf_struct_ops bpf_tcp_congestion_ops = { .validate = bpf_tcp_ca_validate, .name = "tcp_congestion_ops", .cfi_stubs = &__bpf_ops_tcp_congestion_ops, + .owner = THIS_MODULE, }; static int __init bpf_tcp_ca_kfunc_init(void) { - return register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_tcp_ca_kfunc_set); + int ret; + + ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_tcp_ca_kfunc_set); + ret = ret ?: register_bpf_struct_ops(&bpf_tcp_congestion_ops, tcp_congestion_ops); + + return ret; } late_initcall(bpf_tcp_ca_kfunc_init); -- cgit v1.2.3 From 6fe01d3cbb924a72493eb3f4722dfcfd1c194234 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 23 Jan 2024 18:20:59 -0800 Subject: bpf: Add BPF token delegation mount options to BPF FS Add few new mount options to BPF FS that allow to specify that a given BPF FS instance allows creation of BPF token (added in the next patch), and what sort of operations are allowed under BPF token. As such, we get 4 new mount options, each is a bit mask - `delegate_cmds` allow to specify which bpf() syscall commands are allowed with BPF token derived from this BPF FS instance; - if BPF_MAP_CREATE command is allowed, `delegate_maps` specifies a set of allowable BPF map types that could be created with BPF token; - if BPF_PROG_LOAD command is allowed, `delegate_progs` specifies a set of allowable BPF program types that could be loaded with BPF token; - if BPF_PROG_LOAD command is allowed, `delegate_attachs` specifies a set of allowable BPF program attach types that could be loaded with BPF token; delegate_progs and delegate_attachs are meant to be used together, as full BPF program type is, in general, determined through both program type and program attach type. Currently, these mount options accept the following forms of values: - a special value "any", that enables all possible values of a given bit set; - numeric value (decimal or hexadecimal, determined by kernel automatically) that specifies a bit mask value directly; - all the values for a given mount option are combined, if specified multiple times. E.g., `mount -t bpf nodev /path/to/mount -o delegate_maps=0x1 -o delegate_maps=0x2` will result in a combined 0x3 mask. Ideally, more convenient (for humans) symbolic form derived from corresponding UAPI enums would be accepted (e.g., `-o delegate_progs=kprobe|tracepoint`) and I intend to implement this, but it requires a bunch of UAPI header churn, so I postponed it until this feature lands upstream or at least there is a definite consensus that this feature is acceptable and is going to make it, just to minimize amount of wasted effort and not increase amount of non-essential code to be reviewed. Attentive reader will notice that BPF FS is now marked as FS_USERNS_MOUNT, which theoretically makes it mountable inside non-init user namespace as long as the process has sufficient *namespaced* capabilities within that user namespace. But in reality we still restrict BPF FS to be mountable only by processes with CAP_SYS_ADMIN *in init userns* (extra check in bpf_fill_super()). FS_USERNS_MOUNT is added to allow creating BPF FS context object (i.e., fsopen("bpf")) from inside unprivileged process inside non-init userns, to capture that userns as the owning userns. It will still be required to pass this context object back to privileged process to instantiate and mount it. This manipulation is important, because capturing non-init userns as the owning userns of BPF FS instance (super block) allows to use that userns to constraint BPF token to that userns later on (see next patch). So creating BPF FS with delegation inside unprivileged userns will restrict derived BPF token objects to only "work" inside that intended userns, making it scoped to a intended "container". Also, setting these delegation options requires capable(CAP_SYS_ADMIN), so unprivileged process cannot set this up without involvement of a privileged process. There is a set of selftests at the end of the patch set that simulates this sequence of steps and validates that everything works as intended. But careful review is requested to make sure there are no missed gaps in the implementation and testing. This somewhat subtle set of aspects is the result of previous discussions ([0]) about various user namespace implications and interactions with BPF token functionality and is necessary to contain BPF token inside intended user namespace. [0] https://lore.kernel.org/bpf/20230704-hochverdient-lehne-eeb9eeef785e@brauner/ Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Christian Brauner Link: https://lore.kernel.org/bpf/20240124022127.2379740-3-andrii@kernel.org --- include/linux/bpf.h | 12 +++++++ kernel/bpf/inode.c | 90 ++++++++++++++++++++++++++++++++++++++++++++++------- 2 files changed, 90 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 75b7f9b19c6a..28374cec49df 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1609,6 +1609,18 @@ struct bpf_link_primer { u32 id; }; +struct bpf_mount_opts { + kuid_t uid; + kgid_t gid; + umode_t mode; + + /* BPF token-related delegation options */ + u64 delegate_cmds; + u64 delegate_maps; + u64 delegate_progs; + u64 delegate_attachs; +}; + struct bpf_struct_ops_value; struct btf_member; diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 41e0a55c35f5..70b748f6228c 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -20,6 +20,7 @@ #include #include #include +#include #include "preload/bpf_preload.h" enum bpf_type { @@ -601,6 +602,7 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) { struct inode *inode = d_inode(root); umode_t mode = inode->i_mode & S_IALLUGO & ~S_ISVTX; + struct bpf_mount_opts *opts = root->d_sb->s_fs_info; if (!uid_eq(inode->i_uid, GLOBAL_ROOT_UID)) seq_printf(m, ",uid=%u", @@ -610,6 +612,26 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) from_kgid_munged(&init_user_ns, inode->i_gid)); if (mode != S_IRWXUGO) seq_printf(m, ",mode=%o", mode); + + if (opts->delegate_cmds == ~0ULL) + seq_printf(m, ",delegate_cmds=any"); + else if (opts->delegate_cmds) + seq_printf(m, ",delegate_cmds=0x%llx", opts->delegate_cmds); + + if (opts->delegate_maps == ~0ULL) + seq_printf(m, ",delegate_maps=any"); + else if (opts->delegate_maps) + seq_printf(m, ",delegate_maps=0x%llx", opts->delegate_maps); + + if (opts->delegate_progs == ~0ULL) + seq_printf(m, ",delegate_progs=any"); + else if (opts->delegate_progs) + seq_printf(m, ",delegate_progs=0x%llx", opts->delegate_progs); + + if (opts->delegate_attachs == ~0ULL) + seq_printf(m, ",delegate_attachs=any"); + else if (opts->delegate_attachs) + seq_printf(m, ",delegate_attachs=0x%llx", opts->delegate_attachs); return 0; } @@ -635,28 +657,31 @@ enum { OPT_UID, OPT_GID, OPT_MODE, + OPT_DELEGATE_CMDS, + OPT_DELEGATE_MAPS, + OPT_DELEGATE_PROGS, + OPT_DELEGATE_ATTACHS, }; static const struct fs_parameter_spec bpf_fs_parameters[] = { fsparam_u32 ("uid", OPT_UID), fsparam_u32 ("gid", OPT_GID), fsparam_u32oct ("mode", OPT_MODE), + fsparam_string ("delegate_cmds", OPT_DELEGATE_CMDS), + fsparam_string ("delegate_maps", OPT_DELEGATE_MAPS), + fsparam_string ("delegate_progs", OPT_DELEGATE_PROGS), + fsparam_string ("delegate_attachs", OPT_DELEGATE_ATTACHS), {} }; -struct bpf_mount_opts { - kuid_t uid; - kgid_t gid; - umode_t mode; -}; - static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) { - struct bpf_mount_opts *opts = fc->fs_private; + struct bpf_mount_opts *opts = fc->s_fs_info; struct fs_parse_result result; kuid_t uid; kgid_t gid; - int opt; + int opt, err; + u64 msk; opt = fs_parse(fc, bpf_fs_parameters, param, &result); if (opt < 0) { @@ -708,6 +733,28 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) case OPT_MODE: opts->mode = result.uint_32 & S_IALLUGO; break; + case OPT_DELEGATE_CMDS: + case OPT_DELEGATE_MAPS: + case OPT_DELEGATE_PROGS: + case OPT_DELEGATE_ATTACHS: + if (strcmp(param->string, "any") == 0) { + msk = ~0ULL; + } else { + err = kstrtou64(param->string, 0, &msk); + if (err) + return err; + } + /* Setting delegation mount options requires privileges */ + if (msk && !capable(CAP_SYS_ADMIN)) + return -EPERM; + switch (opt) { + case OPT_DELEGATE_CMDS: opts->delegate_cmds |= msk; break; + case OPT_DELEGATE_MAPS: opts->delegate_maps |= msk; break; + case OPT_DELEGATE_PROGS: opts->delegate_progs |= msk; break; + case OPT_DELEGATE_ATTACHS: opts->delegate_attachs |= msk; break; + default: return -EINVAL; + } + break; } return 0; @@ -784,10 +831,14 @@ out: static int bpf_fill_super(struct super_block *sb, struct fs_context *fc) { static const struct tree_descr bpf_rfiles[] = { { "" } }; - struct bpf_mount_opts *opts = fc->fs_private; + struct bpf_mount_opts *opts = sb->s_fs_info; struct inode *inode; int ret; + /* Mounting an instance of BPF FS requires privileges */ + if (fc->user_ns != &init_user_ns && !capable(CAP_SYS_ADMIN)) + return -EPERM; + ret = simple_fill_super(sb, BPF_FS_MAGIC, bpf_rfiles); if (ret) return ret; @@ -811,7 +862,7 @@ static int bpf_get_tree(struct fs_context *fc) static void bpf_free_fc(struct fs_context *fc) { - kfree(fc->fs_private); + kfree(fc->s_fs_info); } static const struct fs_context_operations bpf_context_ops = { @@ -835,17 +886,32 @@ static int bpf_init_fs_context(struct fs_context *fc) opts->uid = current_fsuid(); opts->gid = current_fsgid(); - fc->fs_private = opts; + /* start out with no BPF token delegation enabled */ + opts->delegate_cmds = 0; + opts->delegate_maps = 0; + opts->delegate_progs = 0; + opts->delegate_attachs = 0; + + fc->s_fs_info = opts; fc->ops = &bpf_context_ops; return 0; } +static void bpf_kill_super(struct super_block *sb) +{ + struct bpf_mount_opts *opts = sb->s_fs_info; + + kill_litter_super(sb); + kfree(opts); +} + static struct file_system_type bpf_fs_type = { .owner = THIS_MODULE, .name = "bpf", .init_fs_context = bpf_init_fs_context, .parameters = bpf_fs_parameters, - .kill_sb = kill_litter_super, + .kill_sb = bpf_kill_super, + .fs_flags = FS_USERNS_MOUNT, }; static int __init bpf_init(void) -- cgit v1.2.3 From 35f96de04127d332a5c5e8a155d31f452f88c76d Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 23 Jan 2024 18:21:00 -0800 Subject: bpf: Introduce BPF token object Add new kind of BPF kernel object, BPF token. BPF token is meant to allow delegating privileged BPF functionality, like loading a BPF program or creating a BPF map, from privileged process to a *trusted* unprivileged process, all while having a good amount of control over which privileged operations could be performed using provided BPF token. This is achieved through mounting BPF FS instance with extra delegation mount options, which determine what operations are delegatable, and also constraining it to the owning user namespace (as mentioned in the previous patch). BPF token itself is just a derivative from BPF FS and can be created through a new bpf() syscall command, BPF_TOKEN_CREATE, which accepts BPF FS FD, which can be attained through open() API by opening BPF FS mount point. Currently, BPF token "inherits" delegated command, map types, prog type, and attach type bit sets from BPF FS as is. In the future, having an BPF token as a separate object with its own FD, we can allow to further restrict BPF token's allowable set of things either at the creation time or after the fact, allowing the process to guard itself further from unintentionally trying to load undesired kind of BPF programs. But for now we keep things simple and just copy bit sets as is. When BPF token is created from BPF FS mount, we take reference to the BPF super block's owning user namespace, and then use that namespace for checking all the {CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN} capabilities that are normally only checked against init userns (using capable()), but now we check them using ns_capable() instead (if BPF token is provided). See bpf_token_capable() for details. Such setup means that BPF token in itself is not sufficient to grant BPF functionality. User namespaced process has to *also* have necessary combination of capabilities inside that user namespace. So while previously CAP_BPF was useless when granted within user namespace, now it gains a meaning and allows container managers and sys admins to have a flexible control over which processes can and need to use BPF functionality within the user namespace (i.e., container in practice). And BPF FS delegation mount options and derived BPF tokens serve as a per-container "flag" to grant overall ability to use bpf() (plus further restrict on which parts of bpf() syscalls are treated as namespaced). Note also, BPF_TOKEN_CREATE command itself requires ns_capable(CAP_BPF) within the BPF FS owning user namespace, rounding up the ns_capable() story of BPF token. Also creating BPF token in init user namespace is currently not supported, given BPF token doesn't have any effect in init user namespace anyways. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Christian Brauner Link: https://lore.kernel.org/bpf/20240124022127.2379740-4-andrii@kernel.org --- include/linux/bpf.h | 41 ++++++++ include/uapi/linux/bpf.h | 37 +++++++ kernel/bpf/Makefile | 2 +- kernel/bpf/inode.c | 12 ++- kernel/bpf/syscall.c | 17 ++++ kernel/bpf/token.c | 217 +++++++++++++++++++++++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 37 +++++++ 7 files changed, 357 insertions(+), 6 deletions(-) create mode 100644 kernel/bpf/token.c (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 28374cec49df..d9ff7ce547b4 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -52,6 +52,10 @@ struct module; struct bpf_func_state; struct ftrace_ops; struct cgroup; +struct bpf_token; +struct user_namespace; +struct super_block; +struct inode; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; @@ -1621,6 +1625,13 @@ struct bpf_mount_opts { u64 delegate_attachs; }; +struct bpf_token { + struct work_struct work; + atomic64_t refcnt; + struct user_namespace *userns; + u64 allowed_cmds; +}; + struct bpf_struct_ops_value; struct btf_member; @@ -2109,6 +2120,7 @@ static inline void bpf_enable_instrumentation(void) migrate_enable(); } +extern const struct super_operations bpf_super_ops; extern const struct file_operations bpf_map_fops; extern const struct file_operations bpf_prog_fops; extern const struct file_operations bpf_iter_fops; @@ -2243,6 +2255,8 @@ static inline void bpf_map_dec_elem_count(struct bpf_map *map) extern int sysctl_unprivileged_bpf_disabled; +bool bpf_token_capable(const struct bpf_token *token, int cap); + static inline bool bpf_allow_ptr_leaks(void) { return perfmon_capable(); @@ -2277,8 +2291,17 @@ int bpf_link_new_fd(struct bpf_link *link); struct bpf_link *bpf_link_get_from_fd(u32 ufd); struct bpf_link *bpf_link_get_curr_or_next(u32 *id); +void bpf_token_inc(struct bpf_token *token); +void bpf_token_put(struct bpf_token *token); +int bpf_token_create(union bpf_attr *attr); +struct bpf_token *bpf_token_get_from_fd(u32 ufd); + +bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd); + int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname); int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags); +struct inode *bpf_get_inode(struct super_block *sb, const struct inode *dir, + umode_t mode); #define BPF_ITER_FUNC_PREFIX "bpf_iter_" #define DEFINE_BPF_ITER_FUNC(target, args...) \ @@ -2638,6 +2661,24 @@ static inline int bpf_obj_get_user(const char __user *pathname, int flags) return -EOPNOTSUPP; } +static inline bool bpf_token_capable(const struct bpf_token *token, int cap) +{ + return capable(cap) || (cap != CAP_SYS_ADMIN && capable(CAP_SYS_ADMIN)); +} + +static inline void bpf_token_inc(struct bpf_token *token) +{ +} + +static inline void bpf_token_put(struct bpf_token *token) +{ +} + +static inline struct bpf_token *bpf_token_get_from_fd(u32 ufd) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static inline void __dev_flush(void) { } diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 1fef6d5a1330..b9dc0cca172c 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -847,6 +847,36 @@ union bpf_iter_link_info { * Returns zero on success. On error, -1 is returned and *errno* * is set appropriately. * + * BPF_TOKEN_CREATE + * Description + * Create BPF token with embedded information about what + * BPF-related functionality it allows: + * - a set of allowed bpf() syscall commands; + * - a set of allowed BPF map types to be created with + * BPF_MAP_CREATE command, if BPF_MAP_CREATE itself is allowed; + * - a set of allowed BPF program types and BPF program attach + * types to be loaded with BPF_PROG_LOAD command, if + * BPF_PROG_LOAD itself is allowed. + * + * BPF token is created (derived) from an instance of BPF FS, + * assuming it has necessary delegation mount options specified. + * This BPF token can be passed as an extra parameter to various + * bpf() syscall commands to grant BPF subsystem functionality to + * unprivileged processes. + * + * When created, BPF token is "associated" with the owning + * user namespace of BPF FS instance (super block) that it was + * derived from, and subsequent BPF operations performed with + * BPF token would be performing capabilities checks (i.e., + * CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN) within + * that user namespace. Without BPF token, such capabilities + * have to be granted in init user namespace, making bpf() + * syscall incompatible with user namespace, for the most part. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * * NOTES * eBPF objects (maps and programs) can be shared between processes. * @@ -901,6 +931,8 @@ enum bpf_cmd { BPF_ITER_CREATE, BPF_LINK_DETACH, BPF_PROG_BIND_MAP, + BPF_TOKEN_CREATE, + __MAX_BPF_CMD, }; enum bpf_map_type { @@ -1722,6 +1754,11 @@ union bpf_attr { __u32 flags; /* extra flags */ } prog_bind_map; + struct { /* struct used by BPF_TOKEN_CREATE command */ + __u32 flags; + __u32 bpffs_fd; + } token_create; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index f526b7573e97..4ce95acfcaa7 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -6,7 +6,7 @@ cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse endif CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy) -obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o +obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o token.o obj-$(CONFIG_BPF_SYSCALL) += bpf_iter.o map_iter.o task_iter.o prog_iter.o link_iter.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o bloom_filter.o obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 70b748f6228c..565be1f3f1ea 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -99,9 +99,9 @@ static const struct inode_operations bpf_prog_iops = { }; static const struct inode_operations bpf_map_iops = { }; static const struct inode_operations bpf_link_iops = { }; -static struct inode *bpf_get_inode(struct super_block *sb, - const struct inode *dir, - umode_t mode) +struct inode *bpf_get_inode(struct super_block *sb, + const struct inode *dir, + umode_t mode) { struct inode *inode; @@ -603,6 +603,7 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) struct inode *inode = d_inode(root); umode_t mode = inode->i_mode & S_IALLUGO & ~S_ISVTX; struct bpf_mount_opts *opts = root->d_sb->s_fs_info; + u64 mask; if (!uid_eq(inode->i_uid, GLOBAL_ROOT_UID)) seq_printf(m, ",uid=%u", @@ -613,7 +614,8 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) if (mode != S_IRWXUGO) seq_printf(m, ",mode=%o", mode); - if (opts->delegate_cmds == ~0ULL) + mask = (1ULL << __MAX_BPF_CMD) - 1; + if ((opts->delegate_cmds & mask) == mask) seq_printf(m, ",delegate_cmds=any"); else if (opts->delegate_cmds) seq_printf(m, ",delegate_cmds=0x%llx", opts->delegate_cmds); @@ -646,7 +648,7 @@ static void bpf_free_inode(struct inode *inode) free_inode_nonrcu(inode); } -static const struct super_operations bpf_super_ops = { +const struct super_operations bpf_super_ops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, .show_options = bpf_show_options, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index d5f1edee2d50..3ecba592b8ed 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -5426,6 +5426,20 @@ out_prog_put: return ret; } +#define BPF_TOKEN_CREATE_LAST_FIELD token_create.bpffs_fd + +static int token_create(union bpf_attr *attr) +{ + if (CHECK_ATTR(BPF_TOKEN_CREATE)) + return -EINVAL; + + /* no flags are supported yet */ + if (attr->token_create.flags) + return -EINVAL; + + return bpf_token_create(attr); +} + static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) { union bpf_attr attr; @@ -5559,6 +5573,9 @@ static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) case BPF_PROG_BIND_MAP: err = bpf_prog_bind_map(&attr); break; + case BPF_TOKEN_CREATE: + err = token_create(&attr); + break; default: err = -EINVAL; break; diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c new file mode 100644 index 000000000000..bdb6fe697568 --- /dev/null +++ b/kernel/bpf/token.c @@ -0,0 +1,217 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static bool bpf_ns_capable(struct user_namespace *ns, int cap) +{ + return ns_capable(ns, cap) || (cap != CAP_SYS_ADMIN && ns_capable(ns, CAP_SYS_ADMIN)); +} + +bool bpf_token_capable(const struct bpf_token *token, int cap) +{ + struct user_namespace *userns; + + /* BPF token allows ns_capable() level of capabilities */ + userns = token ? token->userns : &init_user_ns; + if (!bpf_ns_capable(userns, cap)) + return false; + return true; +} + +void bpf_token_inc(struct bpf_token *token) +{ + atomic64_inc(&token->refcnt); +} + +static void bpf_token_free(struct bpf_token *token) +{ + put_user_ns(token->userns); + kfree(token); +} + +static void bpf_token_put_deferred(struct work_struct *work) +{ + struct bpf_token *token = container_of(work, struct bpf_token, work); + + bpf_token_free(token); +} + +void bpf_token_put(struct bpf_token *token) +{ + if (!token) + return; + + if (!atomic64_dec_and_test(&token->refcnt)) + return; + + INIT_WORK(&token->work, bpf_token_put_deferred); + schedule_work(&token->work); +} + +static int bpf_token_release(struct inode *inode, struct file *filp) +{ + struct bpf_token *token = filp->private_data; + + bpf_token_put(token); + return 0; +} + +static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp) +{ + struct bpf_token *token = filp->private_data; + u64 mask; + + BUILD_BUG_ON(__MAX_BPF_CMD >= 64); + mask = (1ULL << __MAX_BPF_CMD) - 1; + if ((token->allowed_cmds & mask) == mask) + seq_printf(m, "allowed_cmds:\tany\n"); + else + seq_printf(m, "allowed_cmds:\t0x%llx\n", token->allowed_cmds); +} + +#define BPF_TOKEN_INODE_NAME "bpf-token" + +static const struct inode_operations bpf_token_iops = { }; + +static const struct file_operations bpf_token_fops = { + .release = bpf_token_release, + .show_fdinfo = bpf_token_show_fdinfo, +}; + +int bpf_token_create(union bpf_attr *attr) +{ + struct bpf_mount_opts *mnt_opts; + struct bpf_token *token = NULL; + struct user_namespace *userns; + struct inode *inode; + struct file *file; + struct path path; + struct fd f; + umode_t mode; + int err, fd; + + f = fdget(attr->token_create.bpffs_fd); + if (!f.file) + return -EBADF; + + path = f.file->f_path; + path_get(&path); + fdput(f); + + if (path.dentry != path.mnt->mnt_sb->s_root) { + err = -EINVAL; + goto out_path; + } + if (path.mnt->mnt_sb->s_op != &bpf_super_ops) { + err = -EINVAL; + goto out_path; + } + err = path_permission(&path, MAY_ACCESS); + if (err) + goto out_path; + + userns = path.dentry->d_sb->s_user_ns; + /* + * Enforce that creators of BPF tokens are in the same user + * namespace as the BPF FS instance. This makes reasoning about + * permissions a lot easier and we can always relax this later. + */ + if (current_user_ns() != userns) { + err = -EPERM; + goto out_path; + } + if (!ns_capable(userns, CAP_BPF)) { + err = -EPERM; + goto out_path; + } + + /* Creating BPF token in init_user_ns doesn't make much sense. */ + if (current_user_ns() == &init_user_ns) { + err = -EOPNOTSUPP; + goto out_path; + } + + mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask()); + inode = bpf_get_inode(path.mnt->mnt_sb, NULL, mode); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + goto out_path; + } + + inode->i_op = &bpf_token_iops; + inode->i_fop = &bpf_token_fops; + clear_nlink(inode); /* make sure it is unlinked */ + + file = alloc_file_pseudo(inode, path.mnt, BPF_TOKEN_INODE_NAME, O_RDWR, &bpf_token_fops); + if (IS_ERR(file)) { + iput(inode); + err = PTR_ERR(file); + goto out_path; + } + + token = kzalloc(sizeof(*token), GFP_USER); + if (!token) { + err = -ENOMEM; + goto out_file; + } + + atomic64_set(&token->refcnt, 1); + + /* remember bpffs owning userns for future ns_capable() checks */ + token->userns = get_user_ns(userns); + + mnt_opts = path.dentry->d_sb->s_fs_info; + token->allowed_cmds = mnt_opts->delegate_cmds; + + fd = get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) { + err = fd; + goto out_token; + } + + file->private_data = token; + fd_install(fd, file); + + path_put(&path); + return fd; + +out_token: + bpf_token_free(token); +out_file: + fput(file); +out_path: + path_put(&path); + return err; +} + +struct bpf_token *bpf_token_get_from_fd(u32 ufd) +{ + struct fd f = fdget(ufd); + struct bpf_token *token; + + if (!f.file) + return ERR_PTR(-EBADF); + if (f.file->f_op != &bpf_token_fops) { + fdput(f); + return ERR_PTR(-EINVAL); + } + + token = f.file->private_data; + bpf_token_inc(token); + fdput(f); + + return token; +} + +bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd) +{ + if (!token) + return false; + return token->allowed_cmds & (1ULL << cmd); +} diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 1fef6d5a1330..b9dc0cca172c 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -847,6 +847,36 @@ union bpf_iter_link_info { * Returns zero on success. On error, -1 is returned and *errno* * is set appropriately. * + * BPF_TOKEN_CREATE + * Description + * Create BPF token with embedded information about what + * BPF-related functionality it allows: + * - a set of allowed bpf() syscall commands; + * - a set of allowed BPF map types to be created with + * BPF_MAP_CREATE command, if BPF_MAP_CREATE itself is allowed; + * - a set of allowed BPF program types and BPF program attach + * types to be loaded with BPF_PROG_LOAD command, if + * BPF_PROG_LOAD itself is allowed. + * + * BPF token is created (derived) from an instance of BPF FS, + * assuming it has necessary delegation mount options specified. + * This BPF token can be passed as an extra parameter to various + * bpf() syscall commands to grant BPF subsystem functionality to + * unprivileged processes. + * + * When created, BPF token is "associated" with the owning + * user namespace of BPF FS instance (super block) that it was + * derived from, and subsequent BPF operations performed with + * BPF token would be performing capabilities checks (i.e., + * CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN) within + * that user namespace. Without BPF token, such capabilities + * have to be granted in init user namespace, making bpf() + * syscall incompatible with user namespace, for the most part. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * * NOTES * eBPF objects (maps and programs) can be shared between processes. * @@ -901,6 +931,8 @@ enum bpf_cmd { BPF_ITER_CREATE, BPF_LINK_DETACH, BPF_PROG_BIND_MAP, + BPF_TOKEN_CREATE, + __MAX_BPF_CMD, }; enum bpf_map_type { @@ -1722,6 +1754,11 @@ union bpf_attr { __u32 flags; /* extra flags */ } prog_bind_map; + struct { /* struct used by BPF_TOKEN_CREATE command */ + __u32 flags; + __u32 bpffs_fd; + } token_create; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF -- cgit v1.2.3 From a177fc2bf6fd83704854feaf7aae926b1df4f0b9 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 23 Jan 2024 18:21:01 -0800 Subject: bpf: Add BPF token support to BPF_MAP_CREATE command Allow providing token_fd for BPF_MAP_CREATE command to allow controlled BPF map creation from unprivileged process through delegated BPF token. New BPF_F_TOKEN_FD flag is added to specify together with BPF token FD for BPF_MAP_CREATE command. Wire through a set of allowed BPF map types to BPF token, derived from BPF FS at BPF token creation time. This, in combination with allowed_cmds allows to create a narrowly-focused BPF token (controlled by privileged agent) with a restrictive set of BPF maps that application can attempt to create. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20240124022127.2379740-5-andrii@kernel.org --- include/linux/bpf.h | 2 + include/uapi/linux/bpf.h | 8 +++ kernel/bpf/inode.c | 3 +- kernel/bpf/syscall.c | 59 +++++++++++++++++----- kernel/bpf/token.c | 16 ++++++ tools/include/uapi/linux/bpf.h | 8 +++ .../selftests/bpf/prog_tests/libbpf_probes.c | 2 + .../testing/selftests/bpf/prog_tests/libbpf_str.c | 3 ++ 8 files changed, 86 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d9ff7ce547b4..8252452d0c4d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1630,6 +1630,7 @@ struct bpf_token { atomic64_t refcnt; struct user_namespace *userns; u64 allowed_cmds; + u64 allowed_maps; }; struct bpf_struct_ops_value; @@ -2297,6 +2298,7 @@ int bpf_token_create(union bpf_attr *attr); struct bpf_token *bpf_token_get_from_fd(u32 ufd); bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd); +bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type); int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname); int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index b9dc0cca172c..c78cab8b462d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -983,6 +983,7 @@ enum bpf_map_type { BPF_MAP_TYPE_BLOOM_FILTER, BPF_MAP_TYPE_USER_RINGBUF, BPF_MAP_TYPE_CGRP_STORAGE, + __MAX_BPF_MAP_TYPE }; /* Note that tracing related programs such as @@ -1365,6 +1366,9 @@ enum { /* Flag for value_type_btf_obj_fd, the fd is available */ BPF_F_VTYPE_BTF_OBJ_FD = (1U << 15), + +/* BPF token FD is passed in a corresponding command's token_fd field */ + BPF_F_TOKEN_FD = (1U << 16), }; /* Flags for BPF_PROG_QUERY. */ @@ -1443,6 +1447,10 @@ union bpf_attr { * type data for * btf_vmlinux_value_type_id. */ + /* BPF token FD to use with BPF_MAP_CREATE operation. + * If provided, map_flags should have BPF_F_TOKEN_FD flag set. + */ + __s32 map_token_fd; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 565be1f3f1ea..034b7e4d8f19 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -620,7 +620,8 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) else if (opts->delegate_cmds) seq_printf(m, ",delegate_cmds=0x%llx", opts->delegate_cmds); - if (opts->delegate_maps == ~0ULL) + mask = (1ULL << __MAX_BPF_MAP_TYPE) - 1; + if ((opts->delegate_maps & mask) == mask) seq_printf(m, ",delegate_maps=any"); else if (opts->delegate_maps) seq_printf(m, ",delegate_maps=0x%llx", opts->delegate_maps); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 3ecba592b8ed..b13a4bdcd3a0 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1011,8 +1011,8 @@ int map_check_no_btf(const struct bpf_map *map, return -ENOTSUPP; } -static int map_check_btf(struct bpf_map *map, const struct btf *btf, - u32 btf_key_id, u32 btf_value_id) +static int map_check_btf(struct bpf_map *map, struct bpf_token *token, + const struct btf *btf, u32 btf_key_id, u32 btf_value_id) { const struct btf_type *key_type, *value_type; u32 key_size, value_size; @@ -1040,7 +1040,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, if (!IS_ERR_OR_NULL(map->record)) { int i; - if (!bpf_capable()) { + if (!bpf_token_capable(token, CAP_BPF)) { ret = -EPERM; goto free_map_tab; } @@ -1128,14 +1128,16 @@ static bool bpf_net_capable(void) return capable(CAP_NET_ADMIN) || capable(CAP_SYS_ADMIN); } -#define BPF_MAP_CREATE_LAST_FIELD value_type_btf_obj_fd +#define BPF_MAP_CREATE_LAST_FIELD map_token_fd /* called via syscall */ static int map_create(union bpf_attr *attr) { const struct bpf_map_ops *ops; + struct bpf_token *token = NULL; int numa_node = bpf_map_attr_numa_node(attr); u32 map_type = attr->map_type; struct bpf_map *map; + bool token_flag; int f_flags; int err; @@ -1143,6 +1145,12 @@ static int map_create(union bpf_attr *attr) if (err) return -EINVAL; + /* check BPF_F_TOKEN_FD flag, remember if it's set, and then clear it + * to avoid per-map type checks tripping on unknown flag + */ + token_flag = attr->map_flags & BPF_F_TOKEN_FD; + attr->map_flags &= ~BPF_F_TOKEN_FD; + if (attr->btf_vmlinux_value_type_id) { if (attr->map_type != BPF_MAP_TYPE_STRUCT_OPS || attr->btf_key_type_id || attr->btf_value_type_id) @@ -1183,14 +1191,32 @@ static int map_create(union bpf_attr *attr) if (!ops->map_mem_usage) return -EINVAL; + if (token_flag) { + token = bpf_token_get_from_fd(attr->map_token_fd); + if (IS_ERR(token)) + return PTR_ERR(token); + + /* if current token doesn't grant map creation permissions, + * then we can't use this token, so ignore it and rely on + * system-wide capabilities checks + */ + if (!bpf_token_allow_cmd(token, BPF_MAP_CREATE) || + !bpf_token_allow_map_type(token, attr->map_type)) { + bpf_token_put(token); + token = NULL; + } + } + + err = -EPERM; + /* Intent here is for unprivileged_bpf_disabled to block BPF map * creation for unprivileged users; other actions depend * on fd availability and access to bpffs, so are dependent on * object creation success. Even with unprivileged BPF disabled, * capability checks are still carried out. */ - if (sysctl_unprivileged_bpf_disabled && !bpf_capable()) - return -EPERM; + if (sysctl_unprivileged_bpf_disabled && !bpf_token_capable(token, CAP_BPF)) + goto put_token; /* check privileged map type permissions */ switch (map_type) { @@ -1223,25 +1249,27 @@ static int map_create(union bpf_attr *attr) case BPF_MAP_TYPE_LRU_PERCPU_HASH: case BPF_MAP_TYPE_STRUCT_OPS: case BPF_MAP_TYPE_CPUMAP: - if (!bpf_capable()) - return -EPERM; + if (!bpf_token_capable(token, CAP_BPF)) + goto put_token; break; case BPF_MAP_TYPE_SOCKMAP: case BPF_MAP_TYPE_SOCKHASH: case BPF_MAP_TYPE_DEVMAP: case BPF_MAP_TYPE_DEVMAP_HASH: case BPF_MAP_TYPE_XSKMAP: - if (!bpf_net_capable()) - return -EPERM; + if (!bpf_token_capable(token, CAP_NET_ADMIN)) + goto put_token; break; default: WARN(1, "unsupported map type %d", map_type); - return -EPERM; + goto put_token; } map = ops->map_alloc(attr); - if (IS_ERR(map)) - return PTR_ERR(map); + if (IS_ERR(map)) { + err = PTR_ERR(map); + goto put_token; + } map->ops = ops; map->map_type = map_type; @@ -1278,7 +1306,7 @@ static int map_create(union bpf_attr *attr) map->btf = btf; if (attr->btf_value_type_id) { - err = map_check_btf(map, btf, attr->btf_key_type_id, + err = map_check_btf(map, token, btf, attr->btf_key_type_id, attr->btf_value_type_id); if (err) goto free_map; @@ -1299,6 +1327,7 @@ static int map_create(union bpf_attr *attr) goto free_map_sec; bpf_map_save_memcg(map); + bpf_token_put(token); err = bpf_map_new_fd(map, f_flags); if (err < 0) { @@ -1319,6 +1348,8 @@ free_map_sec: free_map: btf_put(map->btf); map->ops->map_free(map); +put_token: + bpf_token_put(token); return err; } diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c index bdb6fe697568..bc86be4ca567 100644 --- a/kernel/bpf/token.c +++ b/kernel/bpf/token.c @@ -73,6 +73,13 @@ static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp) seq_printf(m, "allowed_cmds:\tany\n"); else seq_printf(m, "allowed_cmds:\t0x%llx\n", token->allowed_cmds); + + BUILD_BUG_ON(__MAX_BPF_MAP_TYPE >= 64); + mask = (1ULL << __MAX_BPF_MAP_TYPE) - 1; + if ((token->allowed_maps & mask) == mask) + seq_printf(m, "allowed_maps:\tany\n"); + else + seq_printf(m, "allowed_maps:\t0x%llx\n", token->allowed_maps); } #define BPF_TOKEN_INODE_NAME "bpf-token" @@ -168,6 +175,7 @@ int bpf_token_create(union bpf_attr *attr) mnt_opts = path.dentry->d_sb->s_fs_info; token->allowed_cmds = mnt_opts->delegate_cmds; + token->allowed_maps = mnt_opts->delegate_maps; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) { @@ -215,3 +223,11 @@ bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd) return false; return token->allowed_cmds & (1ULL << cmd); } + +bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type) +{ + if (!token || type >= __MAX_BPF_MAP_TYPE) + return false; + + return token->allowed_maps & (1ULL << type); +} diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index b9dc0cca172c..c78cab8b462d 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -983,6 +983,7 @@ enum bpf_map_type { BPF_MAP_TYPE_BLOOM_FILTER, BPF_MAP_TYPE_USER_RINGBUF, BPF_MAP_TYPE_CGRP_STORAGE, + __MAX_BPF_MAP_TYPE }; /* Note that tracing related programs such as @@ -1365,6 +1366,9 @@ enum { /* Flag for value_type_btf_obj_fd, the fd is available */ BPF_F_VTYPE_BTF_OBJ_FD = (1U << 15), + +/* BPF token FD is passed in a corresponding command's token_fd field */ + BPF_F_TOKEN_FD = (1U << 16), }; /* Flags for BPF_PROG_QUERY. */ @@ -1443,6 +1447,10 @@ union bpf_attr { * type data for * btf_vmlinux_value_type_id. */ + /* BPF token FD to use with BPF_MAP_CREATE operation. + * If provided, map_flags should have BPF_F_TOKEN_FD flag set. + */ + __s32 map_token_fd; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c index 9f766ddd946a..573249a2814d 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c @@ -68,6 +68,8 @@ void test_libbpf_probe_map_types(void) if (map_type == BPF_MAP_TYPE_UNSPEC) continue; + if (strcmp(map_type_name, "__MAX_BPF_MAP_TYPE") == 0) + continue; if (!test__start_subtest(map_type_name)) continue; diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c index eb34d612d6f8..1f328c0d8aff 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c @@ -132,6 +132,9 @@ static void test_libbpf_bpf_map_type_str(void) const char *map_type_str; char buf[256]; + if (map_type == __MAX_BPF_MAP_TYPE) + continue; + map_type_name = btf__str_by_offset(btf, e->name_off); map_type_str = libbpf_bpf_map_type_str(map_type); ASSERT_OK_PTR(map_type_str, map_type_name); -- cgit v1.2.3 From caf8f28e036c4ba1e823355da6c0c01c39e70ab9 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 23 Jan 2024 18:21:03 -0800 Subject: bpf: Add BPF token support to BPF_PROG_LOAD command Add basic support of BPF token to BPF_PROG_LOAD. BPF_F_TOKEN_FD flag should be set in prog_flags field when providing prog_token_fd. Wire through a set of allowed BPF program types and attach types, derived from BPF FS at BPF token creation time. Then make sure we perform bpf_token_capable() checks everywhere where it's relevant. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20240124022127.2379740-7-andrii@kernel.org --- include/linux/bpf.h | 6 ++ include/uapi/linux/bpf.h | 5 ++ kernel/bpf/core.c | 1 + kernel/bpf/inode.c | 6 +- kernel/bpf/syscall.c | 90 ++++++++++++++++------ kernel/bpf/token.c | 27 +++++++ tools/include/uapi/linux/bpf.h | 5 ++ .../selftests/bpf/prog_tests/libbpf_probes.c | 2 + .../testing/selftests/bpf/prog_tests/libbpf_str.c | 3 + 9 files changed, 118 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8252452d0c4d..d0bf37e3f166 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1489,6 +1489,7 @@ struct bpf_prog_aux { #ifdef CONFIG_SECURITY void *security; #endif + struct bpf_token *token; struct bpf_prog_offload *offload; struct btf *btf; struct bpf_func_info *func_info; @@ -1631,6 +1632,8 @@ struct bpf_token { struct user_namespace *userns; u64 allowed_cmds; u64 allowed_maps; + u64 allowed_progs; + u64 allowed_attachs; }; struct bpf_struct_ops_value; @@ -2299,6 +2302,9 @@ struct bpf_token *bpf_token_get_from_fd(u32 ufd); bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd); bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type); +bool bpf_token_allow_prog_type(const struct bpf_token *token, + enum bpf_prog_type prog_type, + enum bpf_attach_type attach_type); int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname); int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index cb2c888e3bb4..d96708380e52 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1028,6 +1028,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SK_LOOKUP, BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */ BPF_PROG_TYPE_NETFILTER, + __MAX_BPF_PROG_TYPE }; enum bpf_attach_type { @@ -1520,6 +1521,10 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 log_true_size; + /* BPF token FD to use with BPF_PROG_LOAD operation. + * If provided, prog_flags should have BPF_F_TOKEN_FD flag set. + */ + __s32 prog_token_fd; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index fbb1d95a9b44..00dccba29769 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2779,6 +2779,7 @@ void bpf_prog_free(struct bpf_prog *fp) if (aux->dst_prog) bpf_prog_put(aux->dst_prog); + bpf_token_put(aux->token); INIT_WORK(&aux->work, bpf_prog_free_deferred); schedule_work(&aux->work); } diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 034b7e4d8f19..5fb10da5717f 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -626,12 +626,14 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) else if (opts->delegate_maps) seq_printf(m, ",delegate_maps=0x%llx", opts->delegate_maps); - if (opts->delegate_progs == ~0ULL) + mask = (1ULL << __MAX_BPF_PROG_TYPE) - 1; + if ((opts->delegate_progs & mask) == mask) seq_printf(m, ",delegate_progs=any"); else if (opts->delegate_progs) seq_printf(m, ",delegate_progs=0x%llx", opts->delegate_progs); - if (opts->delegate_attachs == ~0ULL) + mask = (1ULL << __MAX_BPF_ATTACH_TYPE) - 1; + if ((opts->delegate_attachs & mask) == mask) seq_printf(m, ",delegate_attachs=any"); else if (opts->delegate_attachs) seq_printf(m, ",delegate_attachs=0x%llx", opts->delegate_attachs); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 45b3a55896eb..61b4bf4cc287 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2626,13 +2626,15 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) } /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD log_true_size +#define BPF_PROG_LOAD_LAST_FIELD prog_token_fd static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) { enum bpf_prog_type type = attr->prog_type; struct bpf_prog *prog, *dst_prog = NULL; struct btf *attach_btf = NULL; + struct bpf_token *token = NULL; + bool bpf_cap; int err; char license[128]; @@ -2646,13 +2648,35 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) BPF_F_TEST_RND_HI32 | BPF_F_XDP_HAS_FRAGS | BPF_F_XDP_DEV_BOUND_ONLY | - BPF_F_TEST_REG_INVARIANTS)) + BPF_F_TEST_REG_INVARIANTS | + BPF_F_TOKEN_FD)) return -EINVAL; + bpf_prog_load_fixup_attach_type(attr); + + if (attr->prog_flags & BPF_F_TOKEN_FD) { + token = bpf_token_get_from_fd(attr->prog_token_fd); + if (IS_ERR(token)) + return PTR_ERR(token); + /* if current token doesn't grant prog loading permissions, + * then we can't use this token, so ignore it and rely on + * system-wide capabilities checks + */ + if (!bpf_token_allow_cmd(token, BPF_PROG_LOAD) || + !bpf_token_allow_prog_type(token, attr->prog_type, + attr->expected_attach_type)) { + bpf_token_put(token); + token = NULL; + } + } + + bpf_cap = bpf_token_capable(token, CAP_BPF); + err = -EPERM; + if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && (attr->prog_flags & BPF_F_ANY_ALIGNMENT) && - !bpf_capable()) - return -EPERM; + !bpf_cap) + goto put_token; /* Intent here is for unprivileged_bpf_disabled to block BPF program * creation for unprivileged users; other actions depend @@ -2661,21 +2685,23 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) * capability checks are still carried out for these * and other operations. */ - if (sysctl_unprivileged_bpf_disabled && !bpf_capable()) - return -EPERM; + if (sysctl_unprivileged_bpf_disabled && !bpf_cap) + goto put_token; if (attr->insn_cnt == 0 || - attr->insn_cnt > (bpf_capable() ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) - return -E2BIG; + attr->insn_cnt > (bpf_cap ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) { + err = -E2BIG; + goto put_token; + } if (type != BPF_PROG_TYPE_SOCKET_FILTER && type != BPF_PROG_TYPE_CGROUP_SKB && - !bpf_capable()) - return -EPERM; + !bpf_cap) + goto put_token; - if (is_net_admin_prog_type(type) && !bpf_net_capable()) - return -EPERM; - if (is_perfmon_prog_type(type) && !perfmon_capable()) - return -EPERM; + if (is_net_admin_prog_type(type) && !bpf_token_capable(token, CAP_NET_ADMIN)) + goto put_token; + if (is_perfmon_prog_type(type) && !bpf_token_capable(token, CAP_PERFMON)) + goto put_token; /* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog * or btf, we need to check which one it is @@ -2685,27 +2711,33 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) if (IS_ERR(dst_prog)) { dst_prog = NULL; attach_btf = btf_get_by_fd(attr->attach_btf_obj_fd); - if (IS_ERR(attach_btf)) - return -EINVAL; + if (IS_ERR(attach_btf)) { + err = -EINVAL; + goto put_token; + } if (!btf_is_kernel(attach_btf)) { /* attaching through specifying bpf_prog's BTF * objects directly might be supported eventually */ btf_put(attach_btf); - return -ENOTSUPP; + err = -ENOTSUPP; + goto put_token; } } } else if (attr->attach_btf_id) { /* fall back to vmlinux BTF, if BTF type ID is specified */ attach_btf = bpf_get_btf_vmlinux(); - if (IS_ERR(attach_btf)) - return PTR_ERR(attach_btf); - if (!attach_btf) - return -EINVAL; + if (IS_ERR(attach_btf)) { + err = PTR_ERR(attach_btf); + goto put_token; + } + if (!attach_btf) { + err = -EINVAL; + goto put_token; + } btf_get(attach_btf); } - bpf_prog_load_fixup_attach_type(attr); if (bpf_prog_load_check_attach(type, attr->expected_attach_type, attach_btf, attr->attach_btf_id, dst_prog)) { @@ -2713,7 +2745,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); - return -EINVAL; + err = -EINVAL; + goto put_token; } /* plain bpf_prog allocation */ @@ -2723,7 +2756,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); - return -ENOMEM; + err = -EINVAL; + goto put_token; } prog->expected_attach_type = attr->expected_attach_type; @@ -2734,6 +2768,10 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE; prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS; + /* move token into prog->aux, reuse taken refcnt */ + prog->aux->token = token; + token = NULL; + err = security_bpf_prog_alloc(prog->aux); if (err) goto free_prog; @@ -2851,6 +2889,8 @@ free_prog: if (prog->aux->attach_btf) btf_put(prog->aux->attach_btf); bpf_prog_free(prog); +put_token: + bpf_token_put(token); return err; } @@ -3858,7 +3898,7 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, case BPF_PROG_TYPE_SK_LOOKUP: return attach_type == prog->expected_attach_type ? 0 : -EINVAL; case BPF_PROG_TYPE_CGROUP_SKB: - if (!bpf_net_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_NET_ADMIN)) /* cg-skb progs can be loaded by unpriv user. * check permissions at attach time. */ diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c index bc86be4ca567..c13c73788d8c 100644 --- a/kernel/bpf/token.c +++ b/kernel/bpf/token.c @@ -80,6 +80,20 @@ static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp) seq_printf(m, "allowed_maps:\tany\n"); else seq_printf(m, "allowed_maps:\t0x%llx\n", token->allowed_maps); + + BUILD_BUG_ON(__MAX_BPF_PROG_TYPE >= 64); + mask = (1ULL << __MAX_BPF_PROG_TYPE) - 1; + if ((token->allowed_progs & mask) == mask) + seq_printf(m, "allowed_progs:\tany\n"); + else + seq_printf(m, "allowed_progs:\t0x%llx\n", token->allowed_progs); + + BUILD_BUG_ON(__MAX_BPF_ATTACH_TYPE >= 64); + mask = (1ULL << __MAX_BPF_ATTACH_TYPE) - 1; + if ((token->allowed_attachs & mask) == mask) + seq_printf(m, "allowed_attachs:\tany\n"); + else + seq_printf(m, "allowed_attachs:\t0x%llx\n", token->allowed_attachs); } #define BPF_TOKEN_INODE_NAME "bpf-token" @@ -176,6 +190,8 @@ int bpf_token_create(union bpf_attr *attr) mnt_opts = path.dentry->d_sb->s_fs_info; token->allowed_cmds = mnt_opts->delegate_cmds; token->allowed_maps = mnt_opts->delegate_maps; + token->allowed_progs = mnt_opts->delegate_progs; + token->allowed_attachs = mnt_opts->delegate_attachs; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) { @@ -231,3 +247,14 @@ bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type t return token->allowed_maps & (1ULL << type); } + +bool bpf_token_allow_prog_type(const struct bpf_token *token, + enum bpf_prog_type prog_type, + enum bpf_attach_type attach_type) +{ + if (!token || prog_type >= __MAX_BPF_PROG_TYPE || attach_type >= __MAX_BPF_ATTACH_TYPE) + return false; + + return (token->allowed_progs & (1ULL << prog_type)) && + (token->allowed_attachs & (1ULL << attach_type)); +} diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index cb2c888e3bb4..d96708380e52 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1028,6 +1028,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SK_LOOKUP, BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */ BPF_PROG_TYPE_NETFILTER, + __MAX_BPF_PROG_TYPE }; enum bpf_attach_type { @@ -1520,6 +1521,10 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 log_true_size; + /* BPF token FD to use with BPF_PROG_LOAD operation. + * If provided, prog_flags should have BPF_F_TOKEN_FD flag set. + */ + __s32 prog_token_fd; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c index 573249a2814d..4ed46ed58a7b 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c @@ -30,6 +30,8 @@ void test_libbpf_probe_prog_types(void) if (prog_type == BPF_PROG_TYPE_UNSPEC) continue; + if (strcmp(prog_type_name, "__MAX_BPF_PROG_TYPE") == 0) + continue; if (!test__start_subtest(prog_type_name)) continue; diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c index 1f328c0d8aff..62ea855ec4d0 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c @@ -189,6 +189,9 @@ static void test_libbpf_bpf_prog_type_str(void) const char *prog_type_str; char buf[256]; + if (prog_type == __MAX_BPF_PROG_TYPE) + continue; + prog_type_name = btf__str_by_offset(btf, e->name_off); prog_type_str = libbpf_bpf_prog_type_str(prog_type); ASSERT_OK_PTR(prog_type_str, prog_type_name); -- cgit v1.2.3 From bbc1d24724e110b86a1a7c3c1724ce0d62cc1e2e Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 23 Jan 2024 18:21:04 -0800 Subject: bpf: Take into account BPF token when fetching helper protos Instead of performing unconditional system-wide bpf_capable() and perfmon_capable() calls inside bpf_base_func_proto() function (and other similar ones) to determine eligibility of a given BPF helper for a given program, use previously recorded BPF token during BPF_PROG_LOAD command handling to inform the decision. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20240124022127.2379740-8-andrii@kernel.org --- drivers/media/rc/bpf-lirc.c | 2 +- include/linux/bpf.h | 5 +++-- kernel/bpf/cgroup.c | 6 +++--- kernel/bpf/helpers.c | 6 +++--- kernel/bpf/syscall.c | 5 +++-- kernel/trace/bpf_trace.c | 2 +- net/core/filter.c | 32 ++++++++++++++++---------------- net/ipv4/bpf_tcp_ca.c | 2 +- net/netfilter/nf_bpf_link.c | 2 +- 9 files changed, 32 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c index fe17c7f98e81..6d07693c6b9f 100644 --- a/drivers/media/rc/bpf-lirc.c +++ b/drivers/media/rc/bpf-lirc.c @@ -110,7 +110,7 @@ lirc_mode2_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_get_prandom_u32: return &bpf_get_prandom_u32_proto; case BPF_FUNC_trace_printk: - if (perfmon_capable()) + if (bpf_token_capable(prog->aux->token, CAP_PERFMON)) return bpf_get_trace_printk_proto(); fallthrough; default: diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d0bf37e3f166..1325225bf602 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2550,7 +2550,8 @@ int btf_find_next_decl_tag(const struct btf *btf, const struct btf_type *pt, struct bpf_prog *bpf_prog_by_id(u32 id); struct bpf_link *bpf_link_by_id(u32 id); -const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id); +const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id, + const struct bpf_prog *prog); void bpf_task_storage_free(struct task_struct *task); void bpf_cgrp_storage_free(struct cgroup *cgroup); bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog); @@ -2810,7 +2811,7 @@ static inline int btf_struct_access(struct bpf_verifier_log *log, } static inline const struct bpf_func_proto * -bpf_base_func_proto(enum bpf_func_id func_id) +bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { return NULL; } diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 491d20038cbe..98e0e3835b28 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1630,7 +1630,7 @@ cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } @@ -2191,7 +2191,7 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } @@ -2348,7 +2348,7 @@ cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index e04ca1af8927..bcb951a2ecf4 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1680,7 +1680,7 @@ const struct bpf_func_proto bpf_probe_read_kernel_str_proto __weak; const struct bpf_func_proto bpf_task_pt_regs_proto __weak; const struct bpf_func_proto * -bpf_base_func_proto(enum bpf_func_id func_id) +bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_map_lookup_elem: @@ -1731,7 +1731,7 @@ bpf_base_func_proto(enum bpf_func_id func_id) break; } - if (!bpf_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_BPF)) return NULL; switch (func_id) { @@ -1789,7 +1789,7 @@ bpf_base_func_proto(enum bpf_func_id func_id) break; } - if (!perfmon_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_PERFMON)) return NULL; switch (func_id) { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 61b4bf4cc287..f76408c957ce 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -5772,7 +5772,7 @@ static const struct bpf_func_proto bpf_sys_bpf_proto = { const struct bpf_func_proto * __weak tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } BPF_CALL_1(bpf_sys_close, u32, fd) @@ -5822,7 +5822,8 @@ syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_sys_bpf: - return !perfmon_capable() ? NULL : &bpf_sys_bpf_proto; + return !bpf_token_capable(prog->aux->token, CAP_PERFMON) + ? NULL : &bpf_sys_bpf_proto; case BPF_FUNC_btf_find_by_name_kind: return &bpf_btf_find_by_name_kind_proto; case BPF_FUNC_sys_close: diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index c98c20abaf99..64fdaf79d113 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1629,7 +1629,7 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_trace_vprintk: return bpf_get_trace_vprintk_proto(); default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } diff --git a/net/core/filter.c b/net/core/filter.c index 6a7abbaa50b8..521bcd0f5e4d 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -87,7 +87,7 @@ #include "dev.h" static const struct bpf_func_proto * -bpf_sk_base_func_proto(enum bpf_func_id func_id); +bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len) { @@ -7862,7 +7862,7 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } @@ -7955,7 +7955,7 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return NULL; } default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -7974,7 +7974,7 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8161,7 +8161,7 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) #endif #endif default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8220,7 +8220,7 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) #endif #endif default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } #if IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES) @@ -8281,7 +8281,7 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_tcp_sock_proto; #endif /* CONFIG_INET */ default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8323,7 +8323,7 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_cgroup_classid_curr_proto; #endif default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8367,7 +8367,7 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_skc_lookup_tcp_proto; #endif default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8378,7 +8378,7 @@ flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skb_load_bytes: return &bpf_flow_dissector_load_bytes_proto; default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8405,7 +8405,7 @@ lwt_out_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skb_under_cgroup: return &bpf_skb_under_cgroup_proto; default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -11236,7 +11236,7 @@ sk_reuseport_func_proto(enum bpf_func_id func_id, case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } @@ -11418,7 +11418,7 @@ sk_lookup_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_sk_release: return &bpf_sk_release_proto; default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -11752,7 +11752,7 @@ const struct bpf_func_proto bpf_sock_from_file_proto = { }; static const struct bpf_func_proto * -bpf_sk_base_func_proto(enum bpf_func_id func_id) +bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func; @@ -11781,10 +11781,10 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id) case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } - if (!perfmon_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_PERFMON)) return NULL; return func; diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 8e7716256d3c..834edc18463a 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -197,7 +197,7 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id, case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } diff --git a/net/netfilter/nf_bpf_link.c b/net/netfilter/nf_bpf_link.c index 0e4beae421f8..5257d5e7eb09 100644 --- a/net/netfilter/nf_bpf_link.c +++ b/net/netfilter/nf_bpf_link.c @@ -314,7 +314,7 @@ static bool nf_is_valid_access(int off, int size, enum bpf_access_type type, static const struct bpf_func_proto * bpf_nf_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } const struct bpf_verifier_ops netfilter_verifier_ops = { -- cgit v1.2.3 From d79a3549754725bb90e58104417449edddf3da3d Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 23 Jan 2024 18:21:05 -0800 Subject: bpf: Consistently use BPF token throughout BPF verifier logic Remove remaining direct queries to perfmon_capable() and bpf_capable() in BPF verifier logic and instead use BPF token (if available) to make decisions about privileges. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20240124022127.2379740-9-andrii@kernel.org --- include/linux/bpf.h | 16 ++++++++-------- include/linux/filter.h | 2 +- kernel/bpf/arraymap.c | 2 +- kernel/bpf/core.c | 2 +- kernel/bpf/verifier.c | 13 ++++++------- net/core/filter.c | 4 ++-- 6 files changed, 19 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1325225bf602..4e146e9708be 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2261,24 +2261,24 @@ extern int sysctl_unprivileged_bpf_disabled; bool bpf_token_capable(const struct bpf_token *token, int cap); -static inline bool bpf_allow_ptr_leaks(void) +static inline bool bpf_allow_ptr_leaks(const struct bpf_token *token) { - return perfmon_capable(); + return bpf_token_capable(token, CAP_PERFMON); } -static inline bool bpf_allow_uninit_stack(void) +static inline bool bpf_allow_uninit_stack(const struct bpf_token *token) { - return perfmon_capable(); + return bpf_token_capable(token, CAP_PERFMON); } -static inline bool bpf_bypass_spec_v1(void) +static inline bool bpf_bypass_spec_v1(const struct bpf_token *token) { - return cpu_mitigations_off() || perfmon_capable(); + return cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON); } -static inline bool bpf_bypass_spec_v4(void) +static inline bool bpf_bypass_spec_v4(const struct bpf_token *token) { - return cpu_mitigations_off() || perfmon_capable(); + return cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON); } int bpf_map_new_fd(struct bpf_map *map, int flags); diff --git a/include/linux/filter.h b/include/linux/filter.h index 35f067fd3840..fee070b9826e 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1140,7 +1140,7 @@ static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog) return false; if (!bpf_jit_harden) return false; - if (bpf_jit_harden == 1 && bpf_capable()) + if (bpf_jit_harden == 1 && bpf_token_capable(prog->aux->token, CAP_BPF)) return false; return true; diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 0bdbbbeab155..13358675ff2e 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -82,7 +82,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; int numa_node = bpf_map_attr_numa_node(attr); u32 elem_size, index_mask, max_entries; - bool bypass_spec_v1 = bpf_bypass_spec_v1(); + bool bypass_spec_v1 = bpf_bypass_spec_v1(NULL); u64 array_size, mask64; struct bpf_array *array; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 00dccba29769..71c459a51d9e 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -682,7 +682,7 @@ static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp) void bpf_prog_kallsyms_add(struct bpf_prog *fp) { if (!bpf_prog_kallsyms_candidate(fp) || - !bpf_capable()) + !bpf_token_capable(fp->aux->token, CAP_BPF)) return; bpf_prog_ksym_set_addr(fp); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f31868ba0c2d..fe833e831cb6 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -20830,7 +20830,12 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 env->prog = *prog; env->ops = bpf_verifier_ops[env->prog->type]; env->fd_array = make_bpfptr(attr->fd_array, uattr.is_kernel); - is_priv = bpf_capable(); + + env->allow_ptr_leaks = bpf_allow_ptr_leaks(env->prog->aux->token); + env->allow_uninit_stack = bpf_allow_uninit_stack(env->prog->aux->token); + env->bypass_spec_v1 = bpf_bypass_spec_v1(env->prog->aux->token); + env->bypass_spec_v4 = bpf_bypass_spec_v4(env->prog->aux->token); + env->bpf_capable = is_priv = bpf_token_capable(env->prog->aux->token, CAP_BPF); bpf_get_btf_vmlinux(); @@ -20862,12 +20867,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 if (attr->prog_flags & BPF_F_ANY_ALIGNMENT) env->strict_alignment = false; - env->allow_ptr_leaks = bpf_allow_ptr_leaks(); - env->allow_uninit_stack = bpf_allow_uninit_stack(); - env->bypass_spec_v1 = bpf_bypass_spec_v1(); - env->bypass_spec_v4 = bpf_bypass_spec_v4(); - env->bpf_capable = bpf_capable(); - if (is_priv) env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ; env->test_reg_invariants = attr->prog_flags & BPF_F_TEST_REG_INVARIANTS; diff --git a/net/core/filter.c b/net/core/filter.c index 521bcd0f5e4d..40121475e8d1 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -8580,7 +8580,7 @@ static bool cg_skb_is_valid_access(int off, int size, return false; case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_end): - if (!bpf_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_BPF)) return false; break; } @@ -8592,7 +8592,7 @@ static bool cg_skb_is_valid_access(int off, int size, case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): break; case bpf_ctx_range(struct __sk_buff, tstamp): - if (!bpf_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_BPF)) return false; break; default: -- cgit v1.2.3 From 1b67772e4e3f16cd647b229cae95fc06d120be08 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 23 Jan 2024 18:21:06 -0800 Subject: bpf,lsm: Refactor bpf_prog_alloc/bpf_prog_free LSM hooks Based on upstream discussion ([0]), rework existing bpf_prog_alloc_security LSM hook. Rename it to bpf_prog_load and instead of passing bpf_prog_aux, pass proper bpf_prog pointer for a full BPF program struct. Also, we pass bpf_attr union with all the user-provided arguments for BPF_PROG_LOAD command. This will give LSMs as much information as we can basically provide. The hook is also BPF token-aware now, and optional bpf_token struct is passed as a third argument. bpf_prog_load LSM hook is called after a bunch of sanity checks were performed, bpf_prog and bpf_prog_aux were allocated and filled out, but right before performing full-fledged BPF verification step. bpf_prog_free LSM hook is now accepting struct bpf_prog argument, for consistency. SELinux code is adjusted to all new names, types, and signatures. Note, given that bpf_prog_load (previously bpf_prog_alloc) hook can be used by some LSMs to allocate extra security blob, but also by other LSMs to reject BPF program loading, we need to make sure that bpf_prog_free LSM hook is called after bpf_prog_load/bpf_prog_alloc one *even* if the hook itself returned error. If we don't do that, we run the risk of leaking memory. This seems to be possible today when combining SELinux and BPF LSM, as one example, depending on their relative ordering. Also, for BPF LSM setup, add bpf_prog_load and bpf_prog_free to sleepable LSM hooks list, as they are both executed in sleepable context. Also drop bpf_prog_load hook from untrusted, as there is no issue with refcount or anything else anymore, that originally forced us to add it to untrusted list in c0c852dd1876 ("bpf: Do not mark certain LSM hook arguments as trusted"). We now trigger this hook much later and it should not be an issue anymore. [0] https://lore.kernel.org/bpf/9fe88aef7deabbe87d3fc38c4aea3c69.paul@paul-moore.com/ Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Paul Moore Link: https://lore.kernel.org/bpf/20240124022127.2379740-10-andrii@kernel.org --- include/linux/lsm_hook_defs.h | 5 +++-- include/linux/security.h | 12 +++++++----- kernel/bpf/bpf_lsm.c | 5 +++-- kernel/bpf/syscall.c | 25 +++++++++++++------------ security/security.c | 25 +++++++++++++++---------- security/selinux/hooks.c | 15 ++++++++------- 6 files changed, 49 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 185924c56378..370181aa685b 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -406,8 +406,9 @@ LSM_HOOK(int, 0, bpf_map, struct bpf_map *map, fmode_t fmode) LSM_HOOK(int, 0, bpf_prog, struct bpf_prog *prog) LSM_HOOK(int, 0, bpf_map_alloc_security, struct bpf_map *map) LSM_HOOK(void, LSM_RET_VOID, bpf_map_free_security, struct bpf_map *map) -LSM_HOOK(int, 0, bpf_prog_alloc_security, struct bpf_prog_aux *aux) -LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free_security, struct bpf_prog_aux *aux) +LSM_HOOK(int, 0, bpf_prog_load, struct bpf_prog *prog, union bpf_attr *attr, + struct bpf_token *token) +LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free, struct bpf_prog *prog) #endif /* CONFIG_BPF_SYSCALL */ LSM_HOOK(int, 0, locked_down, enum lockdown_reason what) diff --git a/include/linux/security.h b/include/linux/security.h index d0eb20f90b26..cb2932fce448 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -2064,15 +2064,16 @@ static inline void securityfs_remove(struct dentry *dentry) union bpf_attr; struct bpf_map; struct bpf_prog; -struct bpf_prog_aux; +struct bpf_token; #ifdef CONFIG_SECURITY extern int security_bpf(int cmd, union bpf_attr *attr, unsigned int size); extern int security_bpf_map(struct bpf_map *map, fmode_t fmode); extern int security_bpf_prog(struct bpf_prog *prog); extern int security_bpf_map_alloc(struct bpf_map *map); extern void security_bpf_map_free(struct bpf_map *map); -extern int security_bpf_prog_alloc(struct bpf_prog_aux *aux); -extern void security_bpf_prog_free(struct bpf_prog_aux *aux); +extern int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, + struct bpf_token *token); +extern void security_bpf_prog_free(struct bpf_prog *prog); #else static inline int security_bpf(int cmd, union bpf_attr *attr, unsigned int size) @@ -2098,12 +2099,13 @@ static inline int security_bpf_map_alloc(struct bpf_map *map) static inline void security_bpf_map_free(struct bpf_map *map) { } -static inline int security_bpf_prog_alloc(struct bpf_prog_aux *aux) +static inline int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, + struct bpf_token *token) { return 0; } -static inline void security_bpf_prog_free(struct bpf_prog_aux *aux) +static inline void security_bpf_prog_free(struct bpf_prog *prog) { } #endif /* CONFIG_SECURITY */ #endif /* CONFIG_BPF_SYSCALL */ diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index e8e910395bf6..7ee0dd011de4 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -263,6 +263,8 @@ BTF_ID(func, bpf_lsm_bpf_map) BTF_ID(func, bpf_lsm_bpf_map_alloc_security) BTF_ID(func, bpf_lsm_bpf_map_free_security) BTF_ID(func, bpf_lsm_bpf_prog) +BTF_ID(func, bpf_lsm_bpf_prog_load) +BTF_ID(func, bpf_lsm_bpf_prog_free) BTF_ID(func, bpf_lsm_bprm_check_security) BTF_ID(func, bpf_lsm_bprm_committed_creds) BTF_ID(func, bpf_lsm_bprm_committing_creds) @@ -358,8 +360,7 @@ BTF_SET_END(sleepable_lsm_hooks) BTF_SET_START(untrusted_lsm_hooks) BTF_ID(func, bpf_lsm_bpf_map_free_security) -BTF_ID(func, bpf_lsm_bpf_prog_alloc_security) -BTF_ID(func, bpf_lsm_bpf_prog_free_security) +BTF_ID(func, bpf_lsm_bpf_prog_free) BTF_ID(func, bpf_lsm_file_alloc_security) BTF_ID(func, bpf_lsm_file_free_security) #ifdef CONFIG_SECURITY_NETWORK diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index f76408c957ce..3857a2a9ae7f 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2180,7 +2180,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu) kvfree(aux->func_info); kfree(aux->func_info_aux); free_uid(aux->user); - security_bpf_prog_free(aux); + security_bpf_prog_free(aux->prog); bpf_prog_free(aux->prog); } @@ -2772,10 +2772,6 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) prog->aux->token = token; token = NULL; - err = security_bpf_prog_alloc(prog->aux); - if (err) - goto free_prog; - prog->aux->user = get_current_user(); prog->len = attr->insn_cnt; @@ -2783,12 +2779,12 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) if (copy_from_bpfptr(prog->insns, make_bpfptr(attr->insns, uattr.is_kernel), bpf_prog_insn_size(prog)) != 0) - goto free_prog_sec; + goto free_prog; /* copy eBPF program license from user space */ if (strncpy_from_bpfptr(license, make_bpfptr(attr->license, uattr.is_kernel), sizeof(license) - 1) < 0) - goto free_prog_sec; + goto free_prog; license[sizeof(license) - 1] = 0; /* eBPF programs must be GPL compatible to use GPL-ed functions */ @@ -2802,14 +2798,14 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) if (bpf_prog_is_dev_bound(prog->aux)) { err = bpf_prog_dev_bound_init(prog, attr); if (err) - goto free_prog_sec; + goto free_prog; } if (type == BPF_PROG_TYPE_EXT && dst_prog && bpf_prog_is_dev_bound(dst_prog->aux)) { err = bpf_prog_dev_bound_inherit(prog, dst_prog); if (err) - goto free_prog_sec; + goto free_prog; } /* @@ -2831,12 +2827,16 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) /* find program type: socket_filter vs tracing_filter */ err = find_prog_type(type, prog); if (err < 0) - goto free_prog_sec; + goto free_prog; prog->aux->load_time = ktime_get_boottime_ns(); err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name, sizeof(attr->prog_name)); if (err < 0) + goto free_prog; + + err = security_bpf_prog_load(prog, attr, token); + if (err) goto free_prog_sec; /* run eBPF verifier */ @@ -2882,10 +2882,11 @@ free_used_maps: */ __bpf_prog_put_noref(prog, prog->aux->real_func_cnt); return err; + free_prog_sec: - free_uid(prog->aux->user); - security_bpf_prog_free(prog->aux); + security_bpf_prog_free(prog); free_prog: + free_uid(prog->aux->user); if (prog->aux->attach_btf) btf_put(prog->aux->attach_btf); bpf_prog_free(prog); diff --git a/security/security.c b/security/security.c index 0144a98d3712..eb159da4b146 100644 --- a/security/security.c +++ b/security/security.c @@ -5423,16 +5423,21 @@ int security_bpf_map_alloc(struct bpf_map *map) } /** - * security_bpf_prog_alloc() - Allocate a bpf program LSM blob - * @aux: bpf program aux info struct + * security_bpf_prog_load() - Check if loading of BPF program is allowed + * @prog: BPF program object + * @attr: BPF syscall attributes used to create BPF program + * @token: BPF token used to grant user access to BPF subsystem * - * Initialize the security field inside bpf program. + * Perform an access control check when the kernel loads a BPF program and + * allocates associated BPF program object. This hook is also responsible for + * allocating any required LSM state for the BPF program. * * Return: Returns 0 on success, error on failure. */ -int security_bpf_prog_alloc(struct bpf_prog_aux *aux) +int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, + struct bpf_token *token) { - return call_int_hook(bpf_prog_alloc_security, 0, aux); + return call_int_hook(bpf_prog_load, 0, prog, attr, token); } /** @@ -5447,14 +5452,14 @@ void security_bpf_map_free(struct bpf_map *map) } /** - * security_bpf_prog_free() - Free a bpf program's LSM blob - * @aux: bpf program aux info struct + * security_bpf_prog_free() - Free a BPF program's LSM blob + * @prog: BPF program struct * - * Clean up the security information stored inside bpf prog. + * Clean up the security information stored inside BPF program. */ -void security_bpf_prog_free(struct bpf_prog_aux *aux) +void security_bpf_prog_free(struct bpf_prog *prog) { - call_void_hook(bpf_prog_free_security, aux); + call_void_hook(bpf_prog_free, prog); } #endif /* CONFIG_BPF_SYSCALL */ diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index a6bf90ace84c..6d64fb189b1b 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -6942,7 +6942,8 @@ static void selinux_bpf_map_free(struct bpf_map *map) kfree(bpfsec); } -static int selinux_bpf_prog_alloc(struct bpf_prog_aux *aux) +static int selinux_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, + struct bpf_token *token) { struct bpf_security_struct *bpfsec; @@ -6951,16 +6952,16 @@ static int selinux_bpf_prog_alloc(struct bpf_prog_aux *aux) return -ENOMEM; bpfsec->sid = current_sid(); - aux->security = bpfsec; + prog->aux->security = bpfsec; return 0; } -static void selinux_bpf_prog_free(struct bpf_prog_aux *aux) +static void selinux_bpf_prog_free(struct bpf_prog *prog) { - struct bpf_security_struct *bpfsec = aux->security; + struct bpf_security_struct *bpfsec = prog->aux->security; - aux->security = NULL; + prog->aux->security = NULL; kfree(bpfsec); } #endif @@ -7325,7 +7326,7 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = { LSM_HOOK_INIT(bpf_map, selinux_bpf_map), LSM_HOOK_INIT(bpf_prog, selinux_bpf_prog), LSM_HOOK_INIT(bpf_map_free_security, selinux_bpf_map_free), - LSM_HOOK_INIT(bpf_prog_free_security, selinux_bpf_prog_free), + LSM_HOOK_INIT(bpf_prog_free, selinux_bpf_prog_free), #endif #ifdef CONFIG_PERF_EVENTS @@ -7383,7 +7384,7 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = { #endif #ifdef CONFIG_BPF_SYSCALL LSM_HOOK_INIT(bpf_map_alloc_security, selinux_bpf_map_alloc), - LSM_HOOK_INIT(bpf_prog_alloc_security, selinux_bpf_prog_alloc), + LSM_HOOK_INIT(bpf_prog_load, selinux_bpf_prog_load), #endif #ifdef CONFIG_PERF_EVENTS LSM_HOOK_INIT(perf_event_alloc, selinux_perf_event_alloc), -- cgit v1.2.3 From a2431c7eabcf9bd5a1e7a1f7ecded40fdda4a8c5 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 23 Jan 2024 18:21:07 -0800 Subject: bpf,lsm: Refactor bpf_map_alloc/bpf_map_free LSM hooks Similarly to bpf_prog_alloc LSM hook, rename and extend bpf_map_alloc hook into bpf_map_create, taking not just struct bpf_map, but also bpf_attr and bpf_token, to give a fuller context to LSMs. Unlike bpf_prog_alloc, there is no need to move the hook around, as it currently is firing right before allocating BPF map ID and FD, which seems to be a sweet spot. But like bpf_prog_alloc/bpf_prog_free combo, make sure that bpf_map_free LSM hook is called even if bpf_map_create hook returned error, as if few LSMs are combined together it could be that one LSM successfully allocated security blob for its needs, while subsequent LSM rejected BPF map creation. The former LSM would still need to free up LSM blob, so we need to ensure security_bpf_map_free() is called regardless of the outcome. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Paul Moore Link: https://lore.kernel.org/bpf/20240124022127.2379740-11-andrii@kernel.org --- include/linux/lsm_hook_defs.h | 5 +++-- include/linux/security.h | 6 ++++-- kernel/bpf/bpf_lsm.c | 6 +++--- kernel/bpf/syscall.c | 4 ++-- security/security.c | 16 ++++++++++------ security/selinux/hooks.c | 7 ++++--- 6 files changed, 26 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 370181aa685b..1be4d3ca6efb 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -404,8 +404,9 @@ LSM_HOOK(void, LSM_RET_VOID, audit_rule_free, void *lsmrule) LSM_HOOK(int, 0, bpf, int cmd, union bpf_attr *attr, unsigned int size) LSM_HOOK(int, 0, bpf_map, struct bpf_map *map, fmode_t fmode) LSM_HOOK(int, 0, bpf_prog, struct bpf_prog *prog) -LSM_HOOK(int, 0, bpf_map_alloc_security, struct bpf_map *map) -LSM_HOOK(void, LSM_RET_VOID, bpf_map_free_security, struct bpf_map *map) +LSM_HOOK(int, 0, bpf_map_create, struct bpf_map *map, union bpf_attr *attr, + struct bpf_token *token) +LSM_HOOK(void, LSM_RET_VOID, bpf_map_free, struct bpf_map *map) LSM_HOOK(int, 0, bpf_prog_load, struct bpf_prog *prog, union bpf_attr *attr, struct bpf_token *token) LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free, struct bpf_prog *prog) diff --git a/include/linux/security.h b/include/linux/security.h index cb2932fce448..83fcdc974116 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -2069,7 +2069,8 @@ struct bpf_token; extern int security_bpf(int cmd, union bpf_attr *attr, unsigned int size); extern int security_bpf_map(struct bpf_map *map, fmode_t fmode); extern int security_bpf_prog(struct bpf_prog *prog); -extern int security_bpf_map_alloc(struct bpf_map *map); +extern int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, + struct bpf_token *token); extern void security_bpf_map_free(struct bpf_map *map); extern int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, struct bpf_token *token); @@ -2091,7 +2092,8 @@ static inline int security_bpf_prog(struct bpf_prog *prog) return 0; } -static inline int security_bpf_map_alloc(struct bpf_map *map) +static inline int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, + struct bpf_token *token) { return 0; } diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 7ee0dd011de4..76976908b302 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -260,8 +260,8 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) BTF_SET_START(sleepable_lsm_hooks) BTF_ID(func, bpf_lsm_bpf) BTF_ID(func, bpf_lsm_bpf_map) -BTF_ID(func, bpf_lsm_bpf_map_alloc_security) -BTF_ID(func, bpf_lsm_bpf_map_free_security) +BTF_ID(func, bpf_lsm_bpf_map_create) +BTF_ID(func, bpf_lsm_bpf_map_free) BTF_ID(func, bpf_lsm_bpf_prog) BTF_ID(func, bpf_lsm_bpf_prog_load) BTF_ID(func, bpf_lsm_bpf_prog_free) @@ -359,7 +359,7 @@ BTF_ID(func, bpf_lsm_userns_create) BTF_SET_END(sleepable_lsm_hooks) BTF_SET_START(untrusted_lsm_hooks) -BTF_ID(func, bpf_lsm_bpf_map_free_security) +BTF_ID(func, bpf_lsm_bpf_map_free) BTF_ID(func, bpf_lsm_bpf_prog_free) BTF_ID(func, bpf_lsm_file_alloc_security) BTF_ID(func, bpf_lsm_file_free_security) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 3857a2a9ae7f..b2750b79ac80 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1318,9 +1318,9 @@ static int map_create(union bpf_attr *attr) attr->btf_vmlinux_value_type_id; } - err = security_bpf_map_alloc(map); + err = security_bpf_map_create(map, attr, token); if (err) - goto free_map; + goto free_map_sec; err = bpf_map_alloc_id(map); if (err) diff --git a/security/security.c b/security/security.c index eb159da4b146..26fcab35b6cd 100644 --- a/security/security.c +++ b/security/security.c @@ -5410,16 +5410,20 @@ int security_bpf_prog(struct bpf_prog *prog) } /** - * security_bpf_map_alloc() - Allocate a bpf map LSM blob - * @map: bpf map + * security_bpf_map_create() - Check if BPF map creation is allowed + * @map: BPF map object + * @attr: BPF syscall attributes used to create BPF map + * @token: BPF token used to grant user access * - * Initialize the security field inside bpf map. + * Do a check when the kernel creates a new BPF map. This is also the + * point where LSM blob is allocated for LSMs that need them. * * Return: Returns 0 on success, error on failure. */ -int security_bpf_map_alloc(struct bpf_map *map) +int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, + struct bpf_token *token) { - return call_int_hook(bpf_map_alloc_security, 0, map); + return call_int_hook(bpf_map_create, 0, map, attr, token); } /** @@ -5448,7 +5452,7 @@ int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, */ void security_bpf_map_free(struct bpf_map *map) { - call_void_hook(bpf_map_free_security, map); + call_void_hook(bpf_map_free, map); } /** diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 6d64fb189b1b..3d336a7952f7 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -6920,7 +6920,8 @@ static int selinux_bpf_prog(struct bpf_prog *prog) BPF__PROG_RUN, NULL); } -static int selinux_bpf_map_alloc(struct bpf_map *map) +static int selinux_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, + struct bpf_token *token) { struct bpf_security_struct *bpfsec; @@ -7325,7 +7326,7 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = { LSM_HOOK_INIT(bpf, selinux_bpf), LSM_HOOK_INIT(bpf_map, selinux_bpf_map), LSM_HOOK_INIT(bpf_prog, selinux_bpf_prog), - LSM_HOOK_INIT(bpf_map_free_security, selinux_bpf_map_free), + LSM_HOOK_INIT(bpf_map_free, selinux_bpf_map_free), LSM_HOOK_INIT(bpf_prog_free, selinux_bpf_prog_free), #endif @@ -7383,7 +7384,7 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = { LSM_HOOK_INIT(audit_rule_init, selinux_audit_rule_init), #endif #ifdef CONFIG_BPF_SYSCALL - LSM_HOOK_INIT(bpf_map_alloc_security, selinux_bpf_map_alloc), + LSM_HOOK_INIT(bpf_map_create, selinux_bpf_map_create), LSM_HOOK_INIT(bpf_prog_load, selinux_bpf_prog_load), #endif #ifdef CONFIG_PERF_EVENTS -- cgit v1.2.3 From f568a3d49af9aed813a184353592efe29b0e3d16 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 23 Jan 2024 18:21:08 -0800 Subject: bpf,lsm: Add BPF token LSM hooks Wire up bpf_token_create and bpf_token_free LSM hooks, which allow to allocate LSM security blob (we add `void *security` field to struct bpf_token for that), but also control who can instantiate BPF token. This follows existing pattern for BPF map and BPF prog. Also add security_bpf_token_allow_cmd() and security_bpf_token_capable() LSM hooks that allow LSM implementation to control and negate (if necessary) BPF token's delegation of a specific bpf_cmd and capability, respectively. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Paul Moore Link: https://lore.kernel.org/bpf/20240124022127.2379740-12-andrii@kernel.org --- include/linux/bpf.h | 3 +++ include/linux/lsm_hook_defs.h | 5 ++++ include/linux/security.h | 25 ++++++++++++++++++ kernel/bpf/bpf_lsm.c | 4 +++ kernel/bpf/token.c | 12 ++++++++- security/security.c | 60 +++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 108 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4e146e9708be..b86bd15a051d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1634,6 +1634,9 @@ struct bpf_token { u64 allowed_maps; u64 allowed_progs; u64 allowed_attachs; +#ifdef CONFIG_SECURITY + void *security; +#endif }; struct bpf_struct_ops_value; diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 1be4d3ca6efb..cd6fbc7af3f8 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -410,6 +410,11 @@ LSM_HOOK(void, LSM_RET_VOID, bpf_map_free, struct bpf_map *map) LSM_HOOK(int, 0, bpf_prog_load, struct bpf_prog *prog, union bpf_attr *attr, struct bpf_token *token) LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free, struct bpf_prog *prog) +LSM_HOOK(int, 0, bpf_token_create, struct bpf_token *token, union bpf_attr *attr, + struct path *path) +LSM_HOOK(void, LSM_RET_VOID, bpf_token_free, struct bpf_token *token) +LSM_HOOK(int, 0, bpf_token_cmd, const struct bpf_token *token, enum bpf_cmd cmd) +LSM_HOOK(int, 0, bpf_token_capable, const struct bpf_token *token, int cap) #endif /* CONFIG_BPF_SYSCALL */ LSM_HOOK(int, 0, locked_down, enum lockdown_reason what) diff --git a/include/linux/security.h b/include/linux/security.h index 83fcdc974116..15804af54f37 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -32,6 +32,7 @@ #include #include #include +#include #include struct linux_binprm; @@ -2075,6 +2076,11 @@ extern void security_bpf_map_free(struct bpf_map *map); extern int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, struct bpf_token *token); extern void security_bpf_prog_free(struct bpf_prog *prog); +extern int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, + struct path *path); +extern void security_bpf_token_free(struct bpf_token *token); +extern int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd); +extern int security_bpf_token_capable(const struct bpf_token *token, int cap); #else static inline int security_bpf(int cmd, union bpf_attr *attr, unsigned int size) @@ -2109,6 +2115,25 @@ static inline int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr * static inline void security_bpf_prog_free(struct bpf_prog *prog) { } + +static inline int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, + struct path *path) +{ + return 0; +} + +static inline void security_bpf_token_free(struct bpf_token *token) +{ } + +static inline int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd) +{ + return 0; +} + +static inline int security_bpf_token_capable(const struct bpf_token *token, int cap) +{ + return 0; +} #endif /* CONFIG_SECURITY */ #endif /* CONFIG_BPF_SYSCALL */ diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 76976908b302..63b4dc495125 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -265,6 +265,10 @@ BTF_ID(func, bpf_lsm_bpf_map_free) BTF_ID(func, bpf_lsm_bpf_prog) BTF_ID(func, bpf_lsm_bpf_prog_load) BTF_ID(func, bpf_lsm_bpf_prog_free) +BTF_ID(func, bpf_lsm_bpf_token_create) +BTF_ID(func, bpf_lsm_bpf_token_free) +BTF_ID(func, bpf_lsm_bpf_token_cmd) +BTF_ID(func, bpf_lsm_bpf_token_capable) BTF_ID(func, bpf_lsm_bprm_check_security) BTF_ID(func, bpf_lsm_bprm_committed_creds) BTF_ID(func, bpf_lsm_bprm_committing_creds) diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c index c13c73788d8c..64c568f47f69 100644 --- a/kernel/bpf/token.c +++ b/kernel/bpf/token.c @@ -7,6 +7,7 @@ #include #include #include +#include static bool bpf_ns_capable(struct user_namespace *ns, int cap) { @@ -21,6 +22,8 @@ bool bpf_token_capable(const struct bpf_token *token, int cap) userns = token ? token->userns : &init_user_ns; if (!bpf_ns_capable(userns, cap)) return false; + if (token && security_bpf_token_capable(token, cap) < 0) + return false; return true; } @@ -31,6 +34,7 @@ void bpf_token_inc(struct bpf_token *token) static void bpf_token_free(struct bpf_token *token) { + security_bpf_token_free(token); put_user_ns(token->userns); kfree(token); } @@ -193,6 +197,10 @@ int bpf_token_create(union bpf_attr *attr) token->allowed_progs = mnt_opts->delegate_progs; token->allowed_attachs = mnt_opts->delegate_attachs; + err = security_bpf_token_create(token, attr, &path); + if (err) + goto out_token; + fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) { err = fd; @@ -237,7 +245,9 @@ bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd) { if (!token) return false; - return token->allowed_cmds & (1ULL << cmd); + if (!(token->allowed_cmds & (1ULL << cmd))) + return false; + return security_bpf_token_cmd(token, cmd) == 0; } bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type) diff --git a/security/security.c b/security/security.c index 26fcab35b6cd..73e009e3d937 100644 --- a/security/security.c +++ b/security/security.c @@ -5444,6 +5444,55 @@ int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, return call_int_hook(bpf_prog_load, 0, prog, attr, token); } +/** + * security_bpf_token_create() - Check if creating of BPF token is allowed + * @token: BPF token object + * @attr: BPF syscall attributes used to create BPF token + * @path: path pointing to BPF FS mount point from which BPF token is created + * + * Do a check when the kernel instantiates a new BPF token object from BPF FS + * instance. This is also the point where LSM blob can be allocated for LSMs. + * + * Return: Returns 0 on success, error on failure. + */ +int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, + struct path *path) +{ + return call_int_hook(bpf_token_create, 0, token, attr, path); +} + +/** + * security_bpf_token_cmd() - Check if BPF token is allowed to delegate + * requested BPF syscall command + * @token: BPF token object + * @cmd: BPF syscall command requested to be delegated by BPF token + * + * Do a check when the kernel decides whether provided BPF token should allow + * delegation of requested BPF syscall command. + * + * Return: Returns 0 on success, error on failure. + */ +int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd) +{ + return call_int_hook(bpf_token_cmd, 0, token, cmd); +} + +/** + * security_bpf_token_capable() - Check if BPF token is allowed to delegate + * requested BPF-related capability + * @token: BPF token object + * @cap: capabilities requested to be delegated by BPF token + * + * Do a check when the kernel decides whether provided BPF token should allow + * delegation of requested BPF-related capabilities. + * + * Return: Returns 0 on success, error on failure. + */ +int security_bpf_token_capable(const struct bpf_token *token, int cap) +{ + return call_int_hook(bpf_token_capable, 0, token, cap); +} + /** * security_bpf_map_free() - Free a bpf map's LSM blob * @map: bpf map @@ -5465,6 +5514,17 @@ void security_bpf_prog_free(struct bpf_prog *prog) { call_void_hook(bpf_prog_free, prog); } + +/** + * security_bpf_token_free() - Free a BPF token's LSM blob + * @token: BPF token struct + * + * Clean up the security information stored inside BPF token. + */ +void security_bpf_token_free(struct bpf_token *token) +{ + call_void_hook(bpf_token_free, token); +} #endif /* CONFIG_BPF_SYSCALL */ /** -- cgit v1.2.3