From f91fe17e243d1f279d425071a35e3d41290758a0 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 1 Mar 2015 12:31:41 +0100 Subject: [PATCH 1/8] ebpf: remove kernel test stubs Now that we have BPF_PROG_TYPE_SOCKET_FILTER up and running, we can remove the test stubs which were added to get the verifier suite up. We can just let the test cases probe under socket filter type instead. In the fill/spill test case, we cannot (yet) access fields from the context (skb), but we may adapt that test case in future. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/bpf/Makefile | 3 -- kernel/bpf/test_stub.c | 78 ------------------------------------- samples/bpf/test_verifier.c | 5 ++- 3 files changed, 3 insertions(+), 83 deletions(-) delete mode 100644 kernel/bpf/test_stub.c diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index a5ae60f0b0a2d..e6983be12bd37 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -1,5 +1,2 @@ obj-y := core.o obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o hashtab.o arraymap.o helpers.o -ifdef CONFIG_TEST_BPF -obj-$(CONFIG_BPF_SYSCALL) += test_stub.o -endif diff --git a/kernel/bpf/test_stub.c b/kernel/bpf/test_stub.c deleted file mode 100644 index 0ceae1e6e8b52..0000000000000 --- a/kernel/bpf/test_stub.c +++ /dev/null @@ -1,78 +0,0 @@ -/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of version 2 of the GNU General Public - * License as published by the Free Software Foundation. - */ -#include -#include -#include -#include -#include - -/* test stubs for BPF_MAP_TYPE_UNSPEC and for BPF_PROG_TYPE_UNSPEC - * to be used by user space verifier testsuite - */ -struct bpf_context { - u64 arg1; - u64 arg2; -}; - -static const struct bpf_func_proto *test_func_proto(enum bpf_func_id func_id) -{ - switch (func_id) { - case BPF_FUNC_map_lookup_elem: - return &bpf_map_lookup_elem_proto; - case BPF_FUNC_map_update_elem: - return &bpf_map_update_elem_proto; - case BPF_FUNC_map_delete_elem: - return &bpf_map_delete_elem_proto; - default: - return NULL; - } -} - -static const struct bpf_context_access { - int size; - enum bpf_access_type type; -} test_ctx_access[] = { - [offsetof(struct bpf_context, arg1)] = { - FIELD_SIZEOF(struct bpf_context, arg1), - BPF_READ - }, - [offsetof(struct bpf_context, arg2)] = { - FIELD_SIZEOF(struct bpf_context, arg2), - BPF_READ - }, -}; - -static bool test_is_valid_access(int off, int size, enum bpf_access_type type) -{ - const struct bpf_context_access *access; - - if (off < 0 || off >= ARRAY_SIZE(test_ctx_access)) - return false; - - access = &test_ctx_access[off]; - if (access->size == size && (access->type & type)) - return true; - - return false; -} - -static struct bpf_verifier_ops test_ops = { - .get_func_proto = test_func_proto, - .is_valid_access = test_is_valid_access, -}; - -static struct bpf_prog_type_list tl_prog = { - .ops = &test_ops, - .type = BPF_PROG_TYPE_UNSPEC, -}; - -static int __init register_test_ops(void) -{ - bpf_register_prog_type(&tl_prog); - return 0; -} -late_initcall(register_test_ops); diff --git a/samples/bpf/test_verifier.c b/samples/bpf/test_verifier.c index b96175e903639..7b56b59fad8eb 100644 --- a/samples/bpf/test_verifier.c +++ b/samples/bpf/test_verifier.c @@ -288,7 +288,8 @@ static struct bpf_test tests[] = { BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -8), /* should be able to access R0 = *(R2 + 8) */ - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 8), + /* BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 8), */ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), BPF_EXIT_INSN(), }, .result = ACCEPT, @@ -687,7 +688,7 @@ static int test(void) } printf("#%d %s ", i, tests[i].descr); - prog_fd = bpf_prog_load(BPF_PROG_TYPE_UNSPEC, prog, + prog_fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, prog, prog_len * sizeof(struct bpf_insn), "GPL"); From a2c83fff582ae133d9f5bb187404ea9ce4da1f96 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 1 Mar 2015 12:31:42 +0100 Subject: [PATCH 2/8] ebpf: constify various function pointer structs We can move bpf_map_ops and bpf_verifier_ops and other structs into ro section, bpf_map_type_list and bpf_prog_type_list into read mostly. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 14 +++++++------- kernel/bpf/arraymap.c | 6 +++--- kernel/bpf/hashtab.c | 6 +++--- kernel/bpf/helpers.c | 6 +++--- net/core/filter.c | 6 +++--- 5 files changed, 19 insertions(+), 19 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index bbfceb7564523..78446860f7963 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -32,13 +32,13 @@ struct bpf_map { u32 key_size; u32 value_size; u32 max_entries; - struct bpf_map_ops *ops; + const struct bpf_map_ops *ops; struct work_struct work; }; struct bpf_map_type_list { struct list_head list_node; - struct bpf_map_ops *ops; + const struct bpf_map_ops *ops; enum bpf_map_type type; }; @@ -109,7 +109,7 @@ struct bpf_verifier_ops { struct bpf_prog_type_list { struct list_head list_node; - struct bpf_verifier_ops *ops; + const struct bpf_verifier_ops *ops; enum bpf_prog_type type; }; @@ -121,7 +121,7 @@ struct bpf_prog_aux { atomic_t refcnt; bool is_gpl_compatible; enum bpf_prog_type prog_type; - struct bpf_verifier_ops *ops; + const struct bpf_verifier_ops *ops; struct bpf_map **used_maps; u32 used_map_cnt; struct bpf_prog *prog; @@ -138,8 +138,8 @@ struct bpf_prog *bpf_prog_get(u32 ufd); int bpf_check(struct bpf_prog *fp, union bpf_attr *attr); /* verifier prototypes for helper functions called from eBPF programs */ -extern struct bpf_func_proto bpf_map_lookup_elem_proto; -extern struct bpf_func_proto bpf_map_update_elem_proto; -extern struct bpf_func_proto bpf_map_delete_elem_proto; +extern const struct bpf_func_proto bpf_map_lookup_elem_proto; +extern const struct bpf_func_proto bpf_map_update_elem_proto; +extern const struct bpf_func_proto bpf_map_delete_elem_proto; #endif /* _LINUX_BPF_H */ diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 9eb4d8a7cd870..8a6616583f38a 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -134,7 +134,7 @@ static void array_map_free(struct bpf_map *map) kvfree(array); } -static struct bpf_map_ops array_ops = { +static const struct bpf_map_ops array_ops = { .map_alloc = array_map_alloc, .map_free = array_map_free, .map_get_next_key = array_map_get_next_key, @@ -143,14 +143,14 @@ static struct bpf_map_ops array_ops = { .map_delete_elem = array_map_delete_elem, }; -static struct bpf_map_type_list tl = { +static struct bpf_map_type_list array_type __read_mostly = { .ops = &array_ops, .type = BPF_MAP_TYPE_ARRAY, }; static int __init register_array_map(void) { - bpf_register_map_type(&tl); + bpf_register_map_type(&array_type); return 0; } late_initcall(register_array_map); diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index b3ba436743101..83c209d9b17ae 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -345,7 +345,7 @@ static void htab_map_free(struct bpf_map *map) kfree(htab); } -static struct bpf_map_ops htab_ops = { +static const struct bpf_map_ops htab_ops = { .map_alloc = htab_map_alloc, .map_free = htab_map_free, .map_get_next_key = htab_map_get_next_key, @@ -354,14 +354,14 @@ static struct bpf_map_ops htab_ops = { .map_delete_elem = htab_map_delete_elem, }; -static struct bpf_map_type_list tl = { +static struct bpf_map_type_list htab_type __read_mostly = { .ops = &htab_ops, .type = BPF_MAP_TYPE_HASH, }; static int __init register_htab_map(void) { - bpf_register_map_type(&tl); + bpf_register_map_type(&htab_type); return 0; } late_initcall(register_htab_map); diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 9e3414d854593..a3c7701a8b5e8 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -41,7 +41,7 @@ static u64 bpf_map_lookup_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) return (unsigned long) value; } -struct bpf_func_proto bpf_map_lookup_elem_proto = { +const struct bpf_func_proto bpf_map_lookup_elem_proto = { .func = bpf_map_lookup_elem, .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, @@ -60,7 +60,7 @@ static u64 bpf_map_update_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) return map->ops->map_update_elem(map, key, value, r4); } -struct bpf_func_proto bpf_map_update_elem_proto = { +const struct bpf_func_proto bpf_map_update_elem_proto = { .func = bpf_map_update_elem, .gpl_only = false, .ret_type = RET_INTEGER, @@ -80,7 +80,7 @@ static u64 bpf_map_delete_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) return map->ops->map_delete_elem(map, key); } -struct bpf_func_proto bpf_map_delete_elem_proto = { +const struct bpf_func_proto bpf_map_delete_elem_proto = { .func = bpf_map_delete_elem, .gpl_only = false, .ret_type = RET_INTEGER, diff --git a/net/core/filter.c b/net/core/filter.c index f6bdc2b1ba012..6fe09e36dad9b 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1159,19 +1159,19 @@ static bool sock_filter_is_valid_access(int off, int size, enum bpf_access_type return false; } -static struct bpf_verifier_ops sock_filter_ops = { +static const struct bpf_verifier_ops sock_filter_ops = { .get_func_proto = sock_filter_func_proto, .is_valid_access = sock_filter_is_valid_access, }; -static struct bpf_prog_type_list tl = { +static struct bpf_prog_type_list sock_filter_type __read_mostly = { .ops = &sock_filter_ops, .type = BPF_PROG_TYPE_SOCKET_FILTER, }; static int __init register_sock_filter_ops(void) { - bpf_register_prog_type(&tl); + bpf_register_prog_type(&sock_filter_type); return 0; } late_initcall(register_sock_filter_ops); From f1a66f85b74c5ef7b503f746ea97742dacd56419 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 1 Mar 2015 12:31:43 +0100 Subject: [PATCH 3/8] ebpf: export BPF_PSEUDO_MAP_FD to uapi We need to export BPF_PSEUDO_MAP_FD to user space, as it's used in the ELF BPF loader where instructions are being loaded that need map fixups. An initial stage loads all maps into the kernel, and later on replaces related instructions in the eBPF blob with BPF_PSEUDO_MAP_FD as source register and the actual fd as immediate value. The kernel verifier recognizes this keyword and replaces the map fd with a real pointer internally. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/filter.h | 2 -- include/uapi/linux/bpf.h | 2 ++ samples/bpf/libbpf.h | 4 +++- 3 files changed, 5 insertions(+), 3 deletions(-) diff --git a/include/linux/filter.h b/include/linux/filter.h index caac2087a4d5e..5e3863d5f666c 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -145,8 +145,6 @@ struct bpf_prog_aux; .off = 0, \ .imm = ((__u64) (IMM)) >> 32 }) -#define BPF_PSEUDO_MAP_FD 1 - /* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */ #define BPF_LD_MAP_FD(DST, MAP_FD) \ BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 45da7ec7d2742..0248180bf2e22 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -120,6 +120,8 @@ enum bpf_prog_type { BPF_PROG_TYPE_SOCKET_FILTER, }; +#define BPF_PSEUDO_MAP_FD 1 + /* flags for BPF_MAP_UPDATE_ELEM command */ #define BPF_ANY 0 /* create new element or update existing */ #define BPF_NOEXIST 1 /* create new element if it didn't exist */ diff --git a/samples/bpf/libbpf.h b/samples/bpf/libbpf.h index 58c5fe1bdba1f..a6bb7e9c22c39 100644 --- a/samples/bpf/libbpf.h +++ b/samples/bpf/libbpf.h @@ -92,7 +92,9 @@ extern char bpf_log_buf[LOG_BUF_SIZE]; .off = 0, \ .imm = ((__u64) (IMM)) >> 32 }) -#define BPF_PSEUDO_MAP_FD 1 +#ifndef BPF_PSEUDO_MAP_FD +# define BPF_PSEUDO_MAP_FD 1 +#endif /* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */ #define BPF_LD_MAP_FD(DST, MAP_FD) \ From 0fc174dea54546e2b1146e1197da1b6d4bc48107 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 1 Mar 2015 12:31:44 +0100 Subject: [PATCH 4/8] ebpf: make internal bpf API independent of CONFIG_BPF_SYSCALL ifdefs Socket filter code and other subsystems with upcoming eBPF support should not need to deal with the fact that we have CONFIG_BPF_SYSCALL defined or not. Having the bpf syscall as a config option is a nice thing and I'd expect it to stay that way for expert users (I presume one day the default setting of it might change, though), but code making use of it should not care if it's actually enabled or not. Instead, hide this via header files and let the rest deal with it. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 78446860f7963..9c458144cdb43 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -113,8 +113,6 @@ struct bpf_prog_type_list { enum bpf_prog_type type; }; -void bpf_register_prog_type(struct bpf_prog_type_list *tl); - struct bpf_prog; struct bpf_prog_aux { @@ -129,11 +127,25 @@ struct bpf_prog_aux { }; #ifdef CONFIG_BPF_SYSCALL +void bpf_register_prog_type(struct bpf_prog_type_list *tl); + void bpf_prog_put(struct bpf_prog *prog); +struct bpf_prog *bpf_prog_get(u32 ufd); #else -static inline void bpf_prog_put(struct bpf_prog *prog) {} +static inline void bpf_register_prog_type(struct bpf_prog_type_list *tl) +{ +} + +static inline struct bpf_prog *bpf_prog_get(u32 ufd) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline void bpf_prog_put(struct bpf_prog *prog) +{ +} #endif -struct bpf_prog *bpf_prog_get(u32 ufd); + /* verify correctness of eBPF program */ int bpf_check(struct bpf_prog *fp, union bpf_attr *attr); From d4052c4aea0cf455110457c0a0c299d45689ba05 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 1 Mar 2015 12:31:45 +0100 Subject: [PATCH 5/8] ebpf: remove CONFIG_BPF_SYSCALL ifdefs in socket filter code This gets rid of CONFIG_BPF_SYSCALL ifdefs in the socket filter code, now that the BPF internal header can deal with it. While going over it, I also changed eBPF related functions to a sk_filter prefix to be more consistent with the rest of the file. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- net/core/filter.c | 36 ++++++++++++++---------------------- 1 file changed, 14 insertions(+), 22 deletions(-) diff --git a/net/core/filter.c b/net/core/filter.c index 6fe09e36dad9b..7417212331665 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1093,7 +1093,6 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) } EXPORT_SYMBOL_GPL(sk_attach_filter); -#ifdef CONFIG_BPF_SYSCALL int sk_attach_bpf(u32 ufd, struct sock *sk) { struct sk_filter *fp, *old_fp; @@ -1107,7 +1106,6 @@ int sk_attach_bpf(u32 ufd, struct sock *sk) return PTR_ERR(prog); if (prog->aux->prog_type != BPF_PROG_TYPE_SOCKET_FILTER) { - /* valid fd, but invalid program type */ bpf_prog_put(prog); return -EINVAL; } @@ -1117,8 +1115,8 @@ int sk_attach_bpf(u32 ufd, struct sock *sk) bpf_prog_put(prog); return -ENOMEM; } - fp->prog = prog; + fp->prog = prog; atomic_set(&fp->refcnt, 0); if (!sk_filter_charge(sk, fp)) { @@ -1136,10 +1134,8 @@ int sk_attach_bpf(u32 ufd, struct sock *sk) return 0; } -/* allow socket filters to call - * bpf_map_lookup_elem(), bpf_map_update_elem(), bpf_map_delete_elem() - */ -static const struct bpf_func_proto *sock_filter_func_proto(enum bpf_func_id func_id) +static const struct bpf_func_proto * +sk_filter_func_proto(enum bpf_func_id func_id) { switch (func_id) { case BPF_FUNC_map_lookup_elem: @@ -1153,34 +1149,30 @@ static const struct bpf_func_proto *sock_filter_func_proto(enum bpf_func_id func } } -static bool sock_filter_is_valid_access(int off, int size, enum bpf_access_type type) +static bool sk_filter_is_valid_access(int off, int size, + enum bpf_access_type type) { /* skb fields cannot be accessed yet */ return false; } -static const struct bpf_verifier_ops sock_filter_ops = { - .get_func_proto = sock_filter_func_proto, - .is_valid_access = sock_filter_is_valid_access, +static const struct bpf_verifier_ops sk_filter_ops = { + .get_func_proto = sk_filter_func_proto, + .is_valid_access = sk_filter_is_valid_access, }; -static struct bpf_prog_type_list sock_filter_type __read_mostly = { - .ops = &sock_filter_ops, +static struct bpf_prog_type_list sk_filter_type __read_mostly = { + .ops = &sk_filter_ops, .type = BPF_PROG_TYPE_SOCKET_FILTER, }; -static int __init register_sock_filter_ops(void) +static int __init register_sk_filter_ops(void) { - bpf_register_prog_type(&sock_filter_type); + bpf_register_prog_type(&sk_filter_type); return 0; } -late_initcall(register_sock_filter_ops); -#else -int sk_attach_bpf(u32 ufd, struct sock *sk) -{ - return -EOPNOTSUPP; -} -#endif +late_initcall(register_sk_filter_ops); + int sk_detach_filter(struct sock *sk) { int ret = -ENOENT; From 96be4325f443dbbfeb37d2a157675ac0736531a1 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 1 Mar 2015 12:31:46 +0100 Subject: [PATCH 6/8] ebpf: add sched_cls_type and map it to sk_filter's verifier ops As discussed recently and at netconf/netdev01, we want to prevent making bpf_verifier_ops registration available for modules, but have them at a controlled place inside the kernel instead. The reason for this is, that out-of-tree modules can go crazy and define and register any verfifier ops they want, doing all sorts of crap, even bypassing available GPLed eBPF helper functions. We don't want to offer such a shiny playground, of course, but keep strict control to ourselves inside the core kernel. This also encourages us to design eBPF user helpers carefully and generically, so they can be shared among various subsystems using eBPF. For the eBPF traffic classifier (cls_bpf), it's a good start to share the same helper facilities as we currently do in eBPF for socket filters. That way, we have BPF_PROG_TYPE_SCHED_CLS look like it's own type, thus one day if there's a good reason to diverge the set of helper functions from the set available to socket filters, we keep ABI compatibility. In future, we could place all bpf_prog_type_list at a central place, perhaps. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 1 + kernel/bpf/verifier.c | 15 +++++++++++++-- net/core/filter.c | 7 +++++++ 3 files changed, 21 insertions(+), 2 deletions(-) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 0248180bf2e22..3fa1af8a58d70 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -118,6 +118,7 @@ enum bpf_map_type { enum bpf_prog_type { BPF_PROG_TYPE_UNSPEC, BPF_PROG_TYPE_SOCKET_FILTER, + BPF_PROG_TYPE_SCHED_CLS, }; #define BPF_PSEUDO_MAP_FD 1 diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a28e09c7825d7..594d341f04dbb 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1172,6 +1172,17 @@ static int check_ld_imm(struct verifier_env *env, struct bpf_insn *insn) return 0; } +static bool may_access_skb(enum bpf_prog_type type) +{ + switch (type) { + case BPF_PROG_TYPE_SOCKET_FILTER: + case BPF_PROG_TYPE_SCHED_CLS: + return true; + default: + return false; + } +} + /* verify safety of LD_ABS|LD_IND instructions: * - they can only appear in the programs where ctx == skb * - since they are wrappers of function calls, they scratch R1-R5 registers, @@ -1194,8 +1205,8 @@ static int check_ld_abs(struct verifier_env *env, struct bpf_insn *insn) struct reg_state *reg; int i, err; - if (env->prog->aux->prog_type != BPF_PROG_TYPE_SOCKET_FILTER) { - verbose("BPF_LD_ABS|IND instructions are only allowed in socket filters\n"); + if (!may_access_skb(env->prog->aux->prog_type)) { + verbose("BPF_LD_ABS|IND instructions not allowed for this program type\n"); return -EINVAL; } diff --git a/net/core/filter.c b/net/core/filter.c index 7417212331665..514d4082f3261 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1166,9 +1166,16 @@ static struct bpf_prog_type_list sk_filter_type __read_mostly = { .type = BPF_PROG_TYPE_SOCKET_FILTER, }; +static struct bpf_prog_type_list sched_cls_type __read_mostly = { + .ops = &sk_filter_ops, + .type = BPF_PROG_TYPE_SCHED_CLS, +}; + static int __init register_sk_filter_ops(void) { bpf_register_prog_type(&sk_filter_type); + bpf_register_prog_type(&sched_cls_type); + return 0; } late_initcall(register_sk_filter_ops); From 24701ecea76b0b93bd9667486934ec310825f558 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 1 Mar 2015 12:31:47 +0100 Subject: [PATCH 7/8] ebpf: move read-only fields to bpf_prog and shrink bpf_prog_aux is_gpl_compatible and prog_type should be moved directly into bpf_prog as they stay immutable during bpf_prog's lifetime, are core attributes and they can be locked as read-only later on via bpf_prog_select_runtime(). With a bit of rearranging, this also allows us to shrink bpf_prog_aux to exactly 1 cacheline. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 4 +--- include/linux/filter.h | 4 +++- kernel/bpf/syscall.c | 7 +++---- kernel/bpf/verifier.c | 4 ++-- net/core/filter.c | 4 ++-- 5 files changed, 11 insertions(+), 12 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9c458144cdb43..a1a7ff2df3282 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -117,11 +117,9 @@ struct bpf_prog; struct bpf_prog_aux { atomic_t refcnt; - bool is_gpl_compatible; - enum bpf_prog_type prog_type; + u32 used_map_cnt; const struct bpf_verifier_ops *ops; struct bpf_map **used_maps; - u32 used_map_cnt; struct bpf_prog *prog; struct work_struct work; }; diff --git a/include/linux/filter.h b/include/linux/filter.h index 5e3863d5f666c..9ee8c67ea249f 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -308,9 +308,11 @@ struct bpf_binary_header { struct bpf_prog { u16 pages; /* Number of allocated pages */ bool jited; /* Is our filter JIT'ed? */ + bool gpl_compatible; /* Is our filter GPL compatible? */ u32 len; /* Number of filter blocks */ - struct sock_fprog_kern *orig_prog; /* Original BPF program */ + enum bpf_prog_type type; /* Type of BPF program */ struct bpf_prog_aux *aux; /* Auxiliary fields */ + struct sock_fprog_kern *orig_prog; /* Original BPF program */ unsigned int (*bpf_func)(const struct sk_buff *skb, const struct bpf_insn *filter); /* Instructions for interpreter */ diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 536edc2be3072..0d69449acbd01 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -354,10 +354,11 @@ static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) list_for_each_entry(tl, &bpf_prog_types, list_node) { if (tl->type == type) { prog->aux->ops = tl->ops; - prog->aux->prog_type = type; + prog->type = type; return 0; } } + return -EINVAL; } @@ -508,7 +509,7 @@ static int bpf_prog_load(union bpf_attr *attr) prog->jited = false; atomic_set(&prog->aux->refcnt, 1); - prog->aux->is_gpl_compatible = is_gpl; + prog->gpl_compatible = is_gpl; /* find program type: socket_filter vs tracing_filter */ err = find_prog_type(type, prog); @@ -517,7 +518,6 @@ static int bpf_prog_load(union bpf_attr *attr) /* run eBPF verifier */ err = bpf_check(prog, attr); - if (err < 0) goto free_used_maps; @@ -528,7 +528,6 @@ static int bpf_prog_load(union bpf_attr *attr) bpf_prog_select_runtime(prog); err = anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog, O_RDWR | O_CLOEXEC); - if (err < 0) /* failed to allocate fd */ goto free_used_maps; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 594d341f04dbb..bdf4192a889b1 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -852,7 +852,7 @@ static int check_call(struct verifier_env *env, int func_id) } /* eBPF programs must be GPL compatible to use GPL-ed functions */ - if (!env->prog->aux->is_gpl_compatible && fn->gpl_only) { + if (!env->prog->gpl_compatible && fn->gpl_only) { verbose("cannot call GPL only function from proprietary program\n"); return -EINVAL; } @@ -1205,7 +1205,7 @@ static int check_ld_abs(struct verifier_env *env, struct bpf_insn *insn) struct reg_state *reg; int i, err; - if (!may_access_skb(env->prog->aux->prog_type)) { + if (!may_access_skb(env->prog->type)) { verbose("BPF_LD_ABS|IND instructions not allowed for this program type\n"); return -EINVAL; } diff --git a/net/core/filter.c b/net/core/filter.c index 514d4082f3261..ff000cb25e0aa 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -814,7 +814,7 @@ static void bpf_release_orig_filter(struct bpf_prog *fp) static void __bpf_prog_release(struct bpf_prog *prog) { - if (prog->aux->prog_type == BPF_PROG_TYPE_SOCKET_FILTER) { + if (prog->type == BPF_PROG_TYPE_SOCKET_FILTER) { bpf_prog_put(prog); } else { bpf_release_orig_filter(prog); @@ -1105,7 +1105,7 @@ int sk_attach_bpf(u32 ufd, struct sock *sk) if (IS_ERR(prog)) return PTR_ERR(prog); - if (prog->aux->prog_type != BPF_PROG_TYPE_SOCKET_FILTER) { + if (prog->type != BPF_PROG_TYPE_SOCKET_FILTER) { bpf_prog_put(prog); return -EINVAL; } From e2e9b6541dd4b31848079da80fe2253daaafb549 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 1 Mar 2015 12:31:48 +0100 Subject: [PATCH 8/8] cls_bpf: add initial eBPF support for programmable classifiers This work extends the "classic" BPF programmable tc classifier by extending its scope also to native eBPF code! This allows for user space to implement own custom, 'safe' C like classifiers (or whatever other frontend language LLVM et al may provide in future), that can then be compiled with the LLVM eBPF backend to an eBPF elf file. The result of this can be loaded into the kernel via iproute2's tc. In the kernel, they can be JITed on major archs and thus run in native performance. Simple, minimal toy example to demonstrate the workflow: #include #include #include #include "tc_bpf_api.h" __section("classify") int cls_main(struct sk_buff *skb) { return (0x800 << 16) | load_byte(skb, ETH_HLEN + __builtin_offsetof(struct iphdr, tos)); } char __license[] __section("license") = "GPL"; The classifier can then be compiled into eBPF opcodes and loaded via tc, for example: clang -O2 -emit-llvm -c cls.c -o - | llc -march=bpf -filetype=obj -o cls.o tc filter add dev em1 parent 1: bpf cls.o [...] As it has been demonstrated, the scope can even reach up to a fully fledged flow dissector (similarly as in samples/bpf/sockex2_kern.c). For tc, maps are allowed to be used, but from kernel context only, in other words, eBPF code can keep state across filter invocations. In future, we perhaps may reattach from a different application to those maps e.g., to read out collected statistics/state. Similarly as in socket filters, we may extend functionality for eBPF classifiers over time depending on the use cases. For that purpose, cls_bpf programs are using BPF_PROG_TYPE_SCHED_CLS program type, so we can allow additional functions/accessors (e.g. an ABI compatible offset translation to skb fields/metadata). For an initial cls_bpf support, we allow the same set of helper functions as eBPF socket filters, but we could diverge at some point in time w/o problem. I was wondering whether cls_bpf and act_bpf could share C programs, I can imagine that at some point, we introduce i) further common handlers for both (or even beyond their scope), and/or if truly needed ii) some restricted function space for each of them. Both can be abstracted easily through struct bpf_verifier_ops in future. The context of cls_bpf versus act_bpf is slightly different though: a cls_bpf program will return a specific classid whereas act_bpf a drop/non-drop return code, latter may also in future mangle skbs. That said, we can surely have a "classify" and "action" section in a single object file, or considered mentioned constraint add a possibility of a shared section. The workflow for getting native eBPF running from tc [1] is as follows: for f_bpf, I've added a slightly modified ELF parser code from Alexei's kernel sample, which reads out the LLVM compiled object, sets up maps (and dynamically fixes up map fds) if any, and loads the eBPF instructions all centrally through the bpf syscall. The resulting fd from the loaded program itself is being passed down to cls_bpf, which looks up struct bpf_prog from the fd store, and holds reference, so that it stays available also after tc program lifetime. On tc filter destruction, it will then drop its reference. Moreover, I've also added the optional possibility to annotate an eBPF filter with a name (e.g. path to object file, or something else if preferred) so that when tc dumps currently installed filters, some more context can be given to an admin for a given instance (as opposed to just the file descriptor number). Last but not least, bpf_prog_get() and bpf_prog_put() needed to be exported, so that eBPF can be used from cls_bpf built as a module. Thanks to 60a3b2253c41 ("net: bpf: make eBPF interpreter images read-only") I think this is of no concern since anything wanting to alter eBPF opcode after verification stage would crash the kernel. [1] http://git.breakpoint.cc/cgit/dborkman/iproute2.git/log/?h=ebpf Signed-off-by: Daniel Borkmann Cc: Jamal Hadi Salim Cc: Jiri Pirko Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 2 + kernel/bpf/syscall.c | 2 + net/sched/cls_bpf.c | 206 ++++++++++++++++++++++++++--------- 3 files changed, 158 insertions(+), 52 deletions(-) diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 25731dfb3fcc2..bf08e76bf5052 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -397,6 +397,8 @@ enum { TCA_BPF_CLASSID, TCA_BPF_OPS_LEN, TCA_BPF_OPS, + TCA_BPF_FD, + TCA_BPF_NAME, __TCA_BPF_MAX, }; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 0d69449acbd01..669719ccc9ee3 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -419,6 +419,7 @@ void bpf_prog_put(struct bpf_prog *prog) bpf_prog_free(prog); } } +EXPORT_SYMBOL_GPL(bpf_prog_put); static int bpf_prog_release(struct inode *inode, struct file *filp) { @@ -466,6 +467,7 @@ struct bpf_prog *bpf_prog_get(u32 ufd) fdput(f); return prog; } +EXPORT_SYMBOL_GPL(bpf_prog_get); /* last field in 'union bpf_attr' used by this command */ #define BPF_PROG_LOAD_LAST_FIELD log_buf diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 5f3ee9e4b5bf5..6f7ed8f8e6ee7 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -16,6 +16,8 @@ #include #include #include +#include + #include #include #include @@ -24,6 +26,8 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Daniel Borkmann "); MODULE_DESCRIPTION("TC BPF based classifier"); +#define CLS_BPF_NAME_LEN 256 + struct cls_bpf_head { struct list_head plist; u32 hgen; @@ -32,18 +36,24 @@ struct cls_bpf_head { struct cls_bpf_prog { struct bpf_prog *filter; - struct sock_filter *bpf_ops; - struct tcf_exts exts; - struct tcf_result res; struct list_head link; + struct tcf_result res; + struct tcf_exts exts; u32 handle; - u16 bpf_num_ops; + union { + u32 bpf_fd; + u16 bpf_num_ops; + }; + struct sock_filter *bpf_ops; + const char *bpf_name; struct tcf_proto *tp; struct rcu_head rcu; }; static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = { [TCA_BPF_CLASSID] = { .type = NLA_U32 }, + [TCA_BPF_FD] = { .type = NLA_U32 }, + [TCA_BPF_NAME] = { .type = NLA_NUL_STRING, .len = CLS_BPF_NAME_LEN }, [TCA_BPF_OPS_LEN] = { .type = NLA_U16 }, [TCA_BPF_OPS] = { .type = NLA_BINARY, .len = sizeof(struct sock_filter) * BPF_MAXINSNS }, @@ -76,6 +86,11 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, return -1; } +static bool cls_bpf_is_ebpf(const struct cls_bpf_prog *prog) +{ + return !prog->bpf_ops; +} + static int cls_bpf_init(struct tcf_proto *tp) { struct cls_bpf_head *head; @@ -94,8 +109,12 @@ static void cls_bpf_delete_prog(struct tcf_proto *tp, struct cls_bpf_prog *prog) { tcf_exts_destroy(&prog->exts); - bpf_prog_destroy(prog->filter); + if (cls_bpf_is_ebpf(prog)) + bpf_prog_put(prog->filter); + else + bpf_prog_destroy(prog->filter); + kfree(prog->bpf_name); kfree(prog->bpf_ops); kfree(prog); } @@ -114,6 +133,7 @@ static int cls_bpf_delete(struct tcf_proto *tp, unsigned long arg) list_del_rcu(&prog->link); tcf_unbind_filter(tp, &prog->res); call_rcu(&prog->rcu, __cls_bpf_delete_prog); + return 0; } @@ -151,69 +171,121 @@ static unsigned long cls_bpf_get(struct tcf_proto *tp, u32 handle) return ret; } -static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, - struct cls_bpf_prog *prog, - unsigned long base, struct nlattr **tb, - struct nlattr *est, bool ovr) +static int cls_bpf_prog_from_ops(struct nlattr **tb, + struct cls_bpf_prog *prog, u32 classid) { struct sock_filter *bpf_ops; - struct tcf_exts exts; - struct sock_fprog_kern tmp; + struct sock_fprog_kern fprog_tmp; struct bpf_prog *fp; u16 bpf_size, bpf_num_ops; - u32 classid; int ret; - if (!tb[TCA_BPF_OPS_LEN] || !tb[TCA_BPF_OPS] || !tb[TCA_BPF_CLASSID]) - return -EINVAL; - - tcf_exts_init(&exts, TCA_BPF_ACT, TCA_BPF_POLICE); - ret = tcf_exts_validate(net, tp, tb, est, &exts, ovr); - if (ret < 0) - return ret; - - classid = nla_get_u32(tb[TCA_BPF_CLASSID]); bpf_num_ops = nla_get_u16(tb[TCA_BPF_OPS_LEN]); - if (bpf_num_ops > BPF_MAXINSNS || bpf_num_ops == 0) { - ret = -EINVAL; - goto errout; - } + if (bpf_num_ops > BPF_MAXINSNS || bpf_num_ops == 0) + return -EINVAL; bpf_size = bpf_num_ops * sizeof(*bpf_ops); - if (bpf_size != nla_len(tb[TCA_BPF_OPS])) { - ret = -EINVAL; - goto errout; - } + if (bpf_size != nla_len(tb[TCA_BPF_OPS])) + return -EINVAL; bpf_ops = kzalloc(bpf_size, GFP_KERNEL); - if (bpf_ops == NULL) { - ret = -ENOMEM; - goto errout; - } + if (bpf_ops == NULL) + return -ENOMEM; memcpy(bpf_ops, nla_data(tb[TCA_BPF_OPS]), bpf_size); - tmp.len = bpf_num_ops; - tmp.filter = bpf_ops; + fprog_tmp.len = bpf_num_ops; + fprog_tmp.filter = bpf_ops; - ret = bpf_prog_create(&fp, &tmp); - if (ret) - goto errout_free; + ret = bpf_prog_create(&fp, &fprog_tmp); + if (ret < 0) { + kfree(bpf_ops); + return ret; + } - prog->bpf_num_ops = bpf_num_ops; prog->bpf_ops = bpf_ops; + prog->bpf_num_ops = bpf_num_ops; + prog->bpf_name = NULL; + prog->filter = fp; prog->res.classid = classid; + return 0; +} + +static int cls_bpf_prog_from_efd(struct nlattr **tb, + struct cls_bpf_prog *prog, u32 classid) +{ + struct bpf_prog *fp; + char *name = NULL; + u32 bpf_fd; + + bpf_fd = nla_get_u32(tb[TCA_BPF_FD]); + + fp = bpf_prog_get(bpf_fd); + if (IS_ERR(fp)) + return PTR_ERR(fp); + + if (fp->type != BPF_PROG_TYPE_SCHED_CLS) { + bpf_prog_put(fp); + return -EINVAL; + } + + if (tb[TCA_BPF_NAME]) { + name = kmemdup(nla_data(tb[TCA_BPF_NAME]), + nla_len(tb[TCA_BPF_NAME]), + GFP_KERNEL); + if (!name) { + bpf_prog_put(fp); + return -ENOMEM; + } + } + + prog->bpf_ops = NULL; + prog->bpf_fd = bpf_fd; + prog->bpf_name = name; + + prog->filter = fp; + prog->res.classid = classid; + + return 0; +} + +static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, + struct cls_bpf_prog *prog, + unsigned long base, struct nlattr **tb, + struct nlattr *est, bool ovr) +{ + struct tcf_exts exts; + bool is_bpf, is_ebpf; + u32 classid; + int ret; + + is_bpf = tb[TCA_BPF_OPS_LEN] && tb[TCA_BPF_OPS]; + is_ebpf = tb[TCA_BPF_FD]; + + if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf) || + !tb[TCA_BPF_CLASSID]) + return -EINVAL; + + tcf_exts_init(&exts, TCA_BPF_ACT, TCA_BPF_POLICE); + ret = tcf_exts_validate(net, tp, tb, est, &exts, ovr); + if (ret < 0) + return ret; + + classid = nla_get_u32(tb[TCA_BPF_CLASSID]); + + ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog, classid) : + cls_bpf_prog_from_efd(tb, prog, classid); + if (ret < 0) { + tcf_exts_destroy(&exts); + return ret; + } + tcf_bind_filter(tp, &prog->res, base); tcf_exts_change(tp, &prog->exts, &exts); return 0; -errout_free: - kfree(bpf_ops); -errout: - tcf_exts_destroy(&exts); - return ret; } static u32 cls_bpf_grab_new_handle(struct tcf_proto *tp, @@ -297,11 +369,43 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, return ret; } +static int cls_bpf_dump_bpf_info(const struct cls_bpf_prog *prog, + struct sk_buff *skb) +{ + struct nlattr *nla; + + if (nla_put_u16(skb, TCA_BPF_OPS_LEN, prog->bpf_num_ops)) + return -EMSGSIZE; + + nla = nla_reserve(skb, TCA_BPF_OPS, prog->bpf_num_ops * + sizeof(struct sock_filter)); + if (nla == NULL) + return -EMSGSIZE; + + memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla)); + + return 0; +} + +static int cls_bpf_dump_ebpf_info(const struct cls_bpf_prog *prog, + struct sk_buff *skb) +{ + if (nla_put_u32(skb, TCA_BPF_FD, prog->bpf_fd)) + return -EMSGSIZE; + + if (prog->bpf_name && + nla_put_string(skb, TCA_BPF_NAME, prog->bpf_name)) + return -EMSGSIZE; + + return 0; +} + static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *tm) { struct cls_bpf_prog *prog = (struct cls_bpf_prog *) fh; - struct nlattr *nest, *nla; + struct nlattr *nest; + int ret; if (prog == NULL) return skb->len; @@ -314,16 +418,14 @@ static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, if (nla_put_u32(skb, TCA_BPF_CLASSID, prog->res.classid)) goto nla_put_failure; - if (nla_put_u16(skb, TCA_BPF_OPS_LEN, prog->bpf_num_ops)) - goto nla_put_failure; - nla = nla_reserve(skb, TCA_BPF_OPS, prog->bpf_num_ops * - sizeof(struct sock_filter)); - if (nla == NULL) + if (cls_bpf_is_ebpf(prog)) + ret = cls_bpf_dump_ebpf_info(prog, skb); + else + ret = cls_bpf_dump_bpf_info(prog, skb); + if (ret) goto nla_put_failure; - memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla)); - if (tcf_exts_dump(skb, &prog->exts) < 0) goto nla_put_failure;