3 files changed, 146 insertions, 7 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
new file mode 100644
index 000000000000..3cf91754a957
--- /dev/null
+++ b/include/linux/bpf.h
@@ -0,0 +1,136 @@
+/* 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.
+ */
+#ifndef _LINUX_BPF_H
+#define _LINUX_BPF_H 1
+
+#include <uapi/linux/bpf.h>
+#include <linux/workqueue.h>
+#include <linux/file.h>
+
+struct bpf_map;
+
+/* map is generic key/value storage optionally accesible by eBPF programs */
+struct bpf_map_ops {
+        /* funcs callable from userspace (via syscall) */
+        struct bpf_map *(*map_alloc)(union bpf_attr *attr);
+        void (*map_free)(struct bpf_map *);
+        int (*map_get_next_key)(struct bpf_map *map, void *key, void *next_key);
+
+        /* funcs callable from userspace and from eBPF programs */
+        void *(*map_lookup_elem)(struct bpf_map *map, void *key);
+        int (*map_update_elem)(struct bpf_map *map, void *key, void *value);
+        int (*map_delete_elem)(struct bpf_map *map, void *key);
+};
+
+struct bpf_map {
+        atomic_t refcnt;
+        enum bpf_map_type map_type;
+        u32 key_size;
+        u32 value_size;
+        u32 max_entries;
+        struct bpf_map_ops *ops;
+        struct work_struct work;
+};
+
+struct bpf_map_type_list {
+        struct list_head list_node;
+        struct bpf_map_ops *ops;
+        enum bpf_map_type type;
+};
+
+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);
+
+/* function argument constraints */
+enum bpf_arg_type {
+        ARG_ANYTHING = 0,       /* any argument is ok */
+
+        /* the following constraints used to prototype
+         * bpf_map_lookup/update/delete_elem() functions
+         */
+        ARG_CONST_MAP_PTR,      /* const argument used as pointer to bpf_map */
+        ARG_PTR_TO_MAP_KEY,     /* pointer to stack used as map key */
+        ARG_PTR_TO_MAP_VALUE,   /* pointer to stack used as map value */
+
+        /* the following constraints used to prototype bpf_memcmp() and other
+         * functions that access data on eBPF program stack
+         */
+        ARG_PTR_TO_STACK,       /* any pointer to eBPF program stack */
+        ARG_CONST_STACK_SIZE,   /* number of bytes accessed from stack */
+};
+
+/* type of values returned from helper functions */
+enum bpf_return_type {
+        RET_INTEGER,                    /* function returns integer */
+        RET_VOID,                       /* function doesn't return anything */
+        RET_PTR_TO_MAP_VALUE_OR_NULL,   /* returns a pointer to map elem value or NULL */
+};
+
+/* 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;
+        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;
+};
+
+/* bpf_context is intentionally undefined structure. Pointer to bpf_context is
+ * the first argument to eBPF programs.
+ * For socket filters: 'struct bpf_context *' == 'struct sk_buff *'
+ */
+struct bpf_context;
+
+enum bpf_access_type {
+        BPF_READ = 1,
+        BPF_WRITE = 2
+};
+
+struct bpf_verifier_ops {
+        /* return eBPF function prototype for verification */
+        const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id);
+
+        /* return true if 'size' wide access at offset 'off' within bpf_context
+         * with 'type' (read or write) is allowed
+         */
+        bool (*is_valid_access)(int off, int size, enum bpf_access_type type);
+};
+
+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);
+/* verify correctness of eBPF program */
+int bpf_check(struct bpf_prog *fp, union bpf_attr *attr);
+
+#endif /* _LINUX_BPF_H */
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 1a0bc6d134d7..ca95abd2bed1 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
@@ -144,6 +145,12 @@ struct seccomp_data;
                 .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)
+
 /* Short form of mov based on type, BPF_X: dst_reg = src_reg, BPF_K: dst_reg = imm32 */
 
 #define BPF_MOV64_RAW(TYPE, DST, SRC, IMM)                      \
@@ -300,17 +307,12 @@ 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/linux/syscalls.h b/include/linux/syscalls.h
index 0f86d85a9ce4..bda9b81357cc 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -65,6 +65,7 @@ struct old_linux_dirent;
 struct perf_event_attr;
 struct file_handle;
 struct sigaltstack;
+union bpf_attr;
 
 #include <linux/types.h>
 #include <linux/aio_abi.h>
@@ -875,5 +876,5 @@ asmlinkage long sys_seccomp(unsigned int op, unsigned int flags,
                             const char __user *uargs);
 asmlinkage long sys_getrandom(char __user *buf, size_t count,
                               unsigned int flags);
-
+asmlinkage long sys_bpf(int cmd, union bpf_attr *attr, unsigned int size);
 #endif