From 7c6a469e3416fa23568c2395a3faa7dd6e376dcb Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 15 Oct 2019 20:24:56 -0700 Subject: bpf: Add typecast to bpf helpers to help BTF generation When pahole converts dwarf to btf it emits only used types. Wrap existing bpf helper functions into typedef and use it in typecast to make gcc emits this type into dwarf. Then pahole will convert it to btf. The "btf_#name_of_helper" types will be used to figure out types of arguments of bpf helpers. The generated code before and after is the same. Only dwarf and btf sections are different. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: John Fastabend Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20191016032505.2089704-3-ast@kernel.org --- include/linux/filter.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 2ce57645f3cd..d3d51d7aff2c 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -464,10 +464,11 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) #define BPF_CALL_x(x, name, ...) \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ + typedef u64 (*btf_##name)(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)); \ u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)) \ { \ - return ____##name(__BPF_MAP(x,__BPF_CAST,__BPF_N,__VA_ARGS__));\ + return ((btf_##name)____##name)(__BPF_MAP(x,__BPF_CAST,__BPF_N,__VA_ARGS__));\ } \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)) -- cgit v1.2.3 From 8580ac9404f6240668a026785d7d8856f0530409 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 15 Oct 2019 20:24:57 -0700 Subject: bpf: Process in-kernel BTF If in-kernel BTF exists parse it and prepare 'struct btf *btf_vmlinux' for further use by the verifier. In-kernel BTF is trusted just like kallsyms and other build artifacts embedded into vmlinux. Yet run this BTF image through BTF verifier to make sure that it is valid and it wasn't mangled during the build. If in-kernel BTF is incorrect it means either gcc or pahole or kernel are buggy. In such case disallow loading BPF programs. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20191016032505.2089704-4-ast@kernel.org --- include/linux/bpf_verifier.h | 4 +++- include/linux/btf.h | 1 + 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 26a6d58ca78c..713efae62e96 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -330,10 +330,12 @@ static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log) #define BPF_LOG_STATS 4 #define BPF_LOG_LEVEL (BPF_LOG_LEVEL1 | BPF_LOG_LEVEL2) #define BPF_LOG_MASK (BPF_LOG_LEVEL | BPF_LOG_STATS) +#define BPF_LOG_KERNEL (BPF_LOG_MASK + 1) /* kernel internal flag */ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) { - return log->level && log->ubuf && !bpf_verifier_log_full(log); + return (log->level && log->ubuf && !bpf_verifier_log_full(log)) || + log->level == BPF_LOG_KERNEL; } #define BPF_MAX_SUBPROGS 256 diff --git a/include/linux/btf.h b/include/linux/btf.h index 64cdf2a23d42..55d43bc856be 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -56,6 +56,7 @@ bool btf_type_is_void(const struct btf_type *t); #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); +struct btf *btf_parse_vmlinux(void); #else static inline const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) -- cgit v1.2.3 From ccfe29eb29c2edcea6552072ef00ff4117f53e83 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 15 Oct 2019 20:24:58 -0700 Subject: bpf: Add attach_btf_id attribute to program load Add attach_btf_id attribute to prog_load command. It's similar to existing expected_attach_type attribute which is used in several cgroup based program types. Unfortunately expected_attach_type is ignored for tracing programs and cannot be reused for new purpose. Hence introduce attach_btf_id to verify bpf programs against given in-kernel BTF type id at load time. It is strictly checked to be valid for raw_tp programs only. In a later patches it will become: btf_id == 0 semantics of existing raw_tp progs. btd_id > 0 raw_tp with BTF and additional type safety. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20191016032505.2089704-5-ast@kernel.org --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 282e28bf41ec..f916380675dd 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -375,6 +375,7 @@ struct bpf_prog_aux { u32 id; u32 func_cnt; /* used by non-func prog as the number of func progs */ u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */ + u32 attach_btf_id; /* in-kernel BTF type id to attach to */ bool verifier_zext; /* Zero extensions has been inserted by verifier. */ bool offload_requested; struct bpf_prog **func; -- cgit v1.2.3 From 9e15db66136a14cde3f35691f1d839d950118826 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 15 Oct 2019 20:25:00 -0700 Subject: bpf: Implement accurate raw_tp context access via BTF libbpf analyzes bpf C program, searches in-kernel BTF for given type name and stores it into expected_attach_type. The kernel verifier expects this btf_id to point to something like: typedef void (*btf_trace_kfree_skb)(void *, struct sk_buff *skb, void *loc); which represents signature of raw_tracepoint "kfree_skb". Then btf_ctx_access() matches ctx+0 access in bpf program with 'skb' and 'ctx+8' access with 'loc' arguments of "kfree_skb" tracepoint. In first case it passes btf_id of 'struct sk_buff *' back to the verifier core and 'void *' in second case. Then the verifier tracks PTR_TO_BTF_ID as any other pointer type. Like PTR_TO_SOCKET points to 'struct bpf_sock', PTR_TO_TCP_SOCK points to 'struct bpf_tcp_sock', and so on. PTR_TO_BTF_ID points to in-kernel structs. If 1234 is btf_id of 'struct sk_buff' in vmlinux's BTF then PTR_TO_BTF_ID#1234 points to one of in kernel skbs. When PTR_TO_BTF_ID#1234 is dereferenced (like r2 = *(u64 *)r1 + 32) the btf_struct_access() checks which field of 'struct sk_buff' is at offset 32. Checks that size of access matches type definition of the field and continues to track the dereferenced type. If that field was a pointer to 'struct net_device' the r2's type will be PTR_TO_BTF_ID#456. Where 456 is btf_id of 'struct net_device' in vmlinux's BTF. Such verifier analysis prevents "cheating" in BPF C program. The program cannot cast arbitrary pointer to 'struct sk_buff *' and access it. C compiler would allow type cast, of course, but the verifier will notice type mismatch based on BPF assembly and in-kernel BTF. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20191016032505.2089704-7-ast@kernel.org --- include/linux/bpf.h | 17 ++++++++++++++++- include/linux/bpf_verifier.h | 4 ++++ 2 files changed, 20 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f916380675dd..028555fcd10d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -16,6 +16,7 @@ #include struct bpf_verifier_env; +struct bpf_verifier_log; struct perf_event; struct bpf_prog; struct bpf_map; @@ -281,6 +282,7 @@ enum bpf_reg_type { PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */ PTR_TO_TP_BUFFER, /* reg points to a writable raw tp's buffer */ PTR_TO_XDP_SOCK, /* reg points to struct xdp_sock */ + PTR_TO_BTF_ID, /* reg points to kernel struct */ }; /* The information passed from prog-specific *_is_valid_access @@ -288,7 +290,11 @@ enum bpf_reg_type { */ struct bpf_insn_access_aux { enum bpf_reg_type reg_type; - int ctx_field_size; + union { + int ctx_field_size; + u32 btf_id; + }; + struct bpf_verifier_log *log; /* for verbose logs */ }; static inline void @@ -483,6 +489,7 @@ struct bpf_event_entry { bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); int bpf_prog_calc_tag(struct bpf_prog *fp); +const char *kernel_type_name(u32 btf_type_id); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); @@ -748,6 +755,14 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); +bool btf_ctx_access(int off, int size, enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info); +int btf_struct_access(struct bpf_verifier_log *log, + const struct btf_type *t, int off, int size, + enum bpf_access_type atype, + u32 *next_btf_id); + #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 713efae62e96..6e7284ea1468 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -52,6 +52,8 @@ struct bpf_reg_state { */ struct bpf_map *map_ptr; + u32 btf_id; /* for PTR_TO_BTF_ID */ + /* Max size from any of the above. */ unsigned long raw; }; @@ -399,6 +401,8 @@ __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt, va_list args); __printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env, const char *fmt, ...); +__printf(2, 3) void bpf_log(struct bpf_verifier_log *log, + const char *fmt, ...); static inline struct bpf_func_state *cur_func(struct bpf_verifier_env *env) { -- cgit v1.2.3 From 2a02759ef5f8a34792df22b41d5e10658fd7bbd3 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 15 Oct 2019 20:25:02 -0700 Subject: bpf: Add support for BTF pointers to interpreter Pointer to BTF object is a pointer to kernel object or NULL. The memory access in the interpreter has to be done via probe_kernel_read to avoid page faults. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20191016032505.2089704-9-ast@kernel.org --- include/linux/filter.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index d3d51d7aff2c..22ebea2e64ea 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -65,6 +65,9 @@ struct ctl_table_header; /* unused opcode to mark special call to bpf_tail_call() helper */ #define BPF_TAIL_CALL 0xf0 +/* unused opcode to mark special load instruction. Same as BPF_ABS */ +#define BPF_PROBE_MEM 0x20 + /* unused opcode to mark call to interpreter with arguments */ #define BPF_CALL_ARGS 0xe0 -- cgit v1.2.3 From 3dec541b2e632d630fe7142ed44f0b3702ef1f8c Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 15 Oct 2019 20:25:03 -0700 Subject: bpf: Add support for BTF pointers to x86 JIT Pointer to BTF object is a pointer to kernel object or NULL. Such pointers can only be used by BPF_LDX instructions. The verifier changed their opcode from LDX|MEM|size to LDX|PROBE_MEM|size to make JITing easier. The number of entries in extable is the number of BPF_LDX insns that access kernel memory via "pointer to BTF type". Only these load instructions can fault. Since x86 extable is relative it has to be allocated in the same memory region as JITed code. Allocate it prior to last pass of JITing and let the last pass populate it. Pointer to extable in bpf_prog_aux is necessary to make page fault handling fast. Page fault handling is done in two steps: 1. bpf_prog_kallsyms_find() finds BPF program that page faulted. It's done by walking rb tree. 2. then extable for given bpf program is binary searched. This process is similar to how page faulting is done for kernel modules. The exception handler skips over faulting x86 instruction and initializes destination register with zero. This mimics exact behavior of bpf_probe_read (when probe_kernel_read faults dest is zeroed). JITs for other architectures can add support in similar way. Until then they will reject unknown opcode and fallback to interpreter. Since extable should be aligned and placed near JITed code make bpf_jit_binary_alloc() return 4 byte aligned image offset, so that extable aligning formula in bpf_int_jit_compile() doesn't need to rely on internal implementation of bpf_jit_binary_alloc(). On x86 gcc defaults to 16-byte alignment for regular kernel functions due to better performance. JITed code may be aligned to 16 in the future, but it will use 4 in the meantime. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20191016032505.2089704-10-ast@kernel.org --- include/linux/bpf.h | 3 +++ include/linux/extable.h | 10 ++++++++++ 2 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 028555fcd10d..a7330d75bb94 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -24,6 +24,7 @@ struct sock; struct seq_file; struct btf; struct btf_type; +struct exception_table_entry; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; @@ -423,6 +424,8 @@ struct bpf_prog_aux { * main prog always has linfo_idx == 0 */ u32 linfo_idx; + u32 num_exentries; + struct exception_table_entry *extable; struct bpf_prog_stats __percpu *stats; union { struct work_struct work; diff --git a/include/linux/extable.h b/include/linux/extable.h index 81ecfaa83ad3..4ab9e78f313b 100644 --- a/include/linux/extable.h +++ b/include/linux/extable.h @@ -33,4 +33,14 @@ search_module_extables(unsigned long addr) } #endif /*CONFIG_MODULES*/ +#ifdef CONFIG_BPF_JIT +const struct exception_table_entry *search_bpf_extables(unsigned long addr); +#else +static inline const struct exception_table_entry * +search_bpf_extables(unsigned long addr) +{ + return NULL; +} +#endif + #endif /* _LINUX_EXTABLE_H */ -- cgit v1.2.3 From a7658e1a4164ce2b9eb4a11aadbba38586e93bd6 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 15 Oct 2019 20:25:04 -0700 Subject: bpf: Check types of arguments passed into helpers Introduce new helper that reuses existing skb perf_event output implementation, but can be called from raw_tracepoint programs that receive 'struct sk_buff *' as tracepoint argument or can walk other kernel data structures to skb pointer. In order to do that teach verifier to resolve true C types of bpf helpers into in-kernel BTF ids. The type of kernel pointer passed by raw tracepoint into bpf program will be tracked by the verifier all the way until it's passed into helper function. For example: kfree_skb() kernel function calls trace_kfree_skb(skb, loc); bpf programs receives that skb pointer and may eventually pass it into bpf_skb_output() bpf helper which in-kernel is implemented via bpf_skb_event_output() kernel function. Its first argument in the kernel is 'struct sk_buff *'. The verifier makes sure that types match all the way. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20191016032505.2089704-11-ast@kernel.org --- include/linux/bpf.h | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a7330d75bb94..2c2c29b49845 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -213,6 +213,7 @@ enum bpf_arg_type { ARG_PTR_TO_INT, /* pointer to int */ ARG_PTR_TO_LONG, /* pointer to long */ ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */ + ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */ }; /* type of values returned from helper functions */ @@ -235,11 +236,17 @@ struct bpf_func_proto { bool gpl_only; bool pkt_access; enum bpf_return_type ret_type; - enum bpf_arg_type arg1_type; - enum bpf_arg_type arg2_type; - enum bpf_arg_type arg3_type; - enum bpf_arg_type arg4_type; - enum bpf_arg_type arg5_type; + union { + struct { + enum bpf_arg_type arg1_type; + enum bpf_arg_type arg2_type; + enum bpf_arg_type arg3_type; + enum bpf_arg_type arg4_type; + enum bpf_arg_type arg5_type; + }; + enum bpf_arg_type arg_type[5]; + }; + u32 *btf_id; /* BTF ids of arguments */ }; /* bpf_context is intentionally undefined structure. Pointer to bpf_context is @@ -765,6 +772,7 @@ int btf_struct_access(struct bpf_verifier_log *log, const struct btf_type *t, int off, int size, enum bpf_access_type atype, u32 *next_btf_id); +u32 btf_resolve_helper_id(struct bpf_verifier_log *log, void *, int); #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) -- cgit v1.2.3 From 3820729160440158a014add69cc0d371061a96b2 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 24 Oct 2019 17:18:11 -0700 Subject: bpf: Prepare btf_ctx_access for non raw_tp use case This patch makes a few changes to btf_ctx_access() to prepare it for non raw_tp use case where the attach_btf_id is not necessary a BTF_KIND_TYPEDEF. It moves the "btf_trace_" prefix check and typedef-follow logic to a new function "check_attach_btf_id()" which is called only once during bpf_check(). btf_ctx_access() only operates on a BTF_KIND_FUNC_PROTO type now. That should also be more efficient since it is done only one instead of every-time check_ctx_access() is called. "check_attach_btf_id()" needs to find the func_proto type from the attach_btf_id. It needs to store the result into the newly added prog->aux->attach_func_proto. func_proto btf type has no name, so a proper name should be stored into "attach_func_name" also. v2: - Move the "btf_trace_" check to an earlier verifier phase (Alexei) Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20191025001811.1718491-1-kafai@fb.com --- include/linux/bpf.h | 5 +++++ include/linux/btf.h | 31 +++++++++++++++++++++++++++++++ 2 files changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 2c2c29b49845..171be30fe0ae 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -392,6 +392,11 @@ struct bpf_prog_aux { u32 attach_btf_id; /* in-kernel BTF type id to attach to */ bool verifier_zext; /* Zero extensions has been inserted by verifier. */ bool offload_requested; + bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */ + /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ + const struct btf_type *attach_func_proto; + /* function name for valid attach_btf_id */ + const char *attach_func_name; struct bpf_prog **func; void *jit_data; /* JIT specific data. arch dependent */ struct latch_tree_node ksym_tnode; diff --git a/include/linux/btf.h b/include/linux/btf.h index 55d43bc856be..9dee00859c5f 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -5,6 +5,7 @@ #define _LINUX_BTF_H 1 #include +#include struct btf; struct btf_member; @@ -53,6 +54,36 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t); bool btf_type_is_void(const struct btf_type *t); +static inline bool btf_type_is_ptr(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_PTR; +} + +static inline bool btf_type_is_int(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_INT; +} + +static inline bool btf_type_is_enum(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM; +} + +static inline bool btf_type_is_typedef(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_TYPEDEF; +} + +static inline bool btf_type_is_func(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC; +} + +static inline bool btf_type_is_func_proto(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC_PROTO; +} + #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); -- cgit v1.2.3