bpf: expand BPF syscall with program load/unload

eBPF programs are similar to kernel modules. They are loaded by the user
process and automatically unloaded when process exits. Each eBPF program is
a safe run-to-completion set of instructions. eBPF verifier statically
determines that the program terminates and is safe to execute.

The following syscall wrapper can be used to load the program:
int bpf_prog_load(enum bpf_prog_type prog_type,
                  const struct bpf_insn *insns, int insn_cnt,
                  const char *license)
{
    union bpf_attr attr = {
        .prog_type = prog_type,
        .insns = ptr_to_u64(insns),
        .insn_cnt = insn_cnt,
        .license = ptr_to_u64(license),
    };

    return bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
}
where 'insns' is an array of eBPF instructions and 'license' is a string
that must be GPL compatible to call helper functions marked gpl_only

Upon succesful load the syscall returns prog_fd.
Use close(prog_fd) to unload the program.

User space tests and examples follow in the later patches

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 66 insertions, 6 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 2887f3f9da59..92979182be81 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -46,4 +46,42 @@ void bpf_register_map_type(struct bpf_map_type_list *tl);
 void bpf_map_put(struct bpf_map *map);
 struct bpf_map *bpf_map_get(struct fd f);
 
+/* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs
+ * to in-kernel helper functions and for adjusting imm32 field in BPF_CALL
+ * instructions after verifying
+ */
+struct bpf_func_proto {
+        u64 (*func)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
+        bool gpl_only;
+};
+
+struct bpf_verifier_ops {
+        /* return eBPF function prototype for verification */
+        const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id);
+};
+
+struct bpf_prog_type_list {
+        struct list_head list_node;
+        struct bpf_verifier_ops *ops;
+        enum bpf_prog_type type;
+};
+
+void bpf_register_prog_type(struct bpf_prog_type_list *tl);
+
+struct bpf_prog;
+
+struct bpf_prog_aux {
+        atomic_t refcnt;
+        bool is_gpl_compatible;
+        enum bpf_prog_type prog_type;
+        struct bpf_verifier_ops *ops;
+        struct bpf_map **used_maps;
+        u32 used_map_cnt;
+        struct bpf_prog *prog;
+        struct work_struct work;
+};
+
+void bpf_prog_put(struct bpf_prog *prog);
+struct bpf_prog *bpf_prog_get(u32 ufd);
+
 #endif /* _LINUX_BPF_H */
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 1a0bc6d134d7..4ffc0958d85e 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -21,6 +21,7 @@
 struct sk_buff;
 struct sock;
 struct seccomp_data;
+struct bpf_prog_aux;
 
 /* ArgX, context and stack frame pointer register positions. Note,
  * Arg1, Arg2, Arg3, etc are used as argument mappings of function
@@ -300,17 +301,12 @@ struct bpf_binary_header {
         u8 image[];
 };
 
-struct bpf_work_struct {
-        struct bpf_prog *prog;
-        struct work_struct work;
-};
-
 struct bpf_prog {
         u16                     pages;          /* Number of allocated pages */
         bool                    jited;          /* Is our filter JIT'ed? */
         u32                     len;            /* Number of filter blocks */
         struct sock_fprog_kern  *orig_prog;     /* Original BPF program */
-        struct bpf_work_struct  *work;          /* Deferred free work struct */
+        struct bpf_prog_aux     *aux;           /* Auxiliary fields */
         unsigned int            (*bpf_func)(const struct sk_buff *skb,
                                             const struct bpf_insn *filter);
         /* Instructions for interpreter */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 395cabd2ca0a..424f442016e7 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -99,12 +99,23 @@ enum bpf_cmd {
          * returns zero and stores next key or negative error
          */
         BPF_MAP_GET_NEXT_KEY,
+
+        /* verify and load eBPF program
+         * prog_fd = bpf(BPF_PROG_LOAD, union bpf_attr *attr, u32 size)
+         * Using attr->prog_type, attr->insns, attr->license
+         * returns fd or negative error
+         */
+        BPF_PROG_LOAD,
 };
 
 enum bpf_map_type {
         BPF_MAP_TYPE_UNSPEC,
 };
 
+enum bpf_prog_type {
+        BPF_PROG_TYPE_UNSPEC,
+};
+
 union bpf_attr {
         struct { /* anonymous struct used by BPF_MAP_CREATE command */
                 __u32   map_type;       /* one of enum bpf_map_type */
@@ -121,6 +132,21 @@ union bpf_attr {
                         __aligned_u64 next_key;
                 };
         };
+
+        struct { /* anonymous struct used by BPF_PROG_LOAD command */
+                __u32           prog_type;      /* one of enum bpf_prog_type */
+                __u32           insn_cnt;
+                __aligned_u64   insns;
+                __aligned_u64   license;
+        };
 } __attribute__((aligned(8)));
 
+/* integer value in 'imm' field of BPF_CALL instruction selects which helper
+ * function eBPF program intends to call
+ */
+enum bpf_func_id {
+        BPF_FUNC_unspec,
+        __BPF_FUNC_MAX_ID,
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */