include/linux/filter.h

/*
 * Linux Socket Filter Data Structures
 */
#ifndef __LINUX_FILTER_H__
#define __LINUX_FILTER_H__

#include <linux/atomic.h>
#include <linux/compat.h>
#include <linux/skbuff.h>
#include <linux/workqueue.h>
#include <uapi/linux/filter.h>

/* Internally used and optimized filter representation with extended
 * instruction set based on top of classic BPF.
 */

/* instruction classes */
#define BPF_ALU64	0x07	/* alu mode in double word width */

/* ld/ldx fields */
#define BPF_DW		0x18	/* double word */
#define BPF_XADD	0xc0	/* exclusive add */

/* alu/jmp fields */
#define BPF_MOV		0xb0	/* mov reg to reg */
#define BPF_ARSH	0xc0	/* sign extending arithmetic shift right */

/* change endianness of a register */
#define BPF_END		0xd0	/* flags for endianness conversion: */
#define BPF_TO_LE	0x00	/* convert to little-endian */
#define BPF_TO_BE	0x08	/* convert to big-endian */
#define BPF_FROM_LE	BPF_TO_LE
#define BPF_FROM_BE	BPF_TO_BE

#define BPF_JNE		0x50	/* jump != */
#define BPF_JSGT	0x60	/* SGT is signed '>', GT in x86 */
#define BPF_JSGE	0x70	/* SGE is signed '>=', GE in x86 */
#define BPF_CALL	0x80	/* function call */
#define BPF_EXIT	0x90	/* function return */

/* Register numbers */
enum {
	BPF_REG_0 = 0,
	BPF_REG_1,
	BPF_REG_2,
	BPF_REG_3,
	BPF_REG_4,
	BPF_REG_5,
	BPF_REG_6,
	BPF_REG_7,
	BPF_REG_8,
	BPF_REG_9,
	BPF_REG_10,
	__MAX_BPF_REG,
};

/* BPF has 10 general purpose 64-bit registers and stack frame. */
#define MAX_BPF_REG	__MAX_BPF_REG

/* ArgX, context and stack frame pointer register positions. Note,
 * Arg1, Arg2, Arg3, etc are used as argument mappings of function
 * calls in BPF_CALL instruction.
 */
#define BPF_REG_ARG1	BPF_REG_1
#define BPF_REG_ARG2	BPF_REG_2
#define BPF_REG_ARG3	BPF_REG_3
#define BPF_REG_ARG4	BPF_REG_4
#define BPF_REG_ARG5	BPF_REG_5
#define BPF_REG_CTX	BPF_REG_6
#define BPF_REG_FP	BPF_REG_10

/* Additional register mappings for converted user programs. */
#define BPF_REG_A	BPF_REG_0
#define BPF_REG_X	BPF_REG_7
#define BPF_REG_TMP	BPF_REG_8

/* BPF program can access up to 512 bytes of stack space. */
#define MAX_BPF_STACK	512

/* Helper macros for filter block array initializers. */

/* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */

#define BPF_ALU64_REG(OP, DST, SRC)				\
	((struct bpf_insn) {					\
		.code  = BPF_ALU64 | BPF_OP(OP) | BPF_X,	\
		.dst_reg = DST,					\
		.src_reg = SRC,					\
		.off   = 0,					\
		.imm   = 0 })

#define BPF_ALU32_REG(OP, DST, SRC)				\
	((struct bpf_insn) {					\
		.code  = BPF_ALU | BPF_OP(OP) | BPF_X,		\
		.dst_reg = DST,					\
		.src_reg = SRC,					\
		.off   = 0,					\
		.imm   = 0 })

/* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */

#define BPF_ALU64_IMM(OP, DST, IMM)				\
	((struct bpf_insn) {					\
		.code  = BPF_ALU64 | BPF_OP(OP) | BPF_K,	\
		.dst_reg = DST,					\
		.src_reg = 0,					\
		.off   = 0,					\
		.imm   = IMM })

#define BPF_ALU32_IMM(OP, DST, IMM)				\
	((struct bpf_insn) {					\
		.code  = BPF_ALU | BPF_OP(OP) | BPF_K,		\
		.dst_reg = DST,					\
		.src_reg = 0,					\
		.off   = 0,					\
		.imm   = IMM })

/* Endianess conversion, cpu_to_{l,b}e(), {l,b}e_to_cpu() */

#define BPF_ENDIAN(TYPE, DST, LEN)				\
	((struct bpf_insn) {					\
		.code  = BPF_ALU | BPF_END | BPF_SRC(TYPE),	\
		.dst_reg = DST,					\
		.src_reg = 0,					\
		.off   = 0,					\
		.imm   = LEN })

/* Short form of mov, dst_reg = src_reg */

#define BPF_MOV64_REG(DST, SRC)					\
	((struct bpf_insn) {					\
		.code  = BPF_ALU64 | BPF_MOV | BPF_X,		\
		.dst_reg = DST,					\
		.src_reg = SRC,					\
		.off   = 0,					\
		.imm   = 0 })

#define BPF_MOV32_REG(DST, SRC)					\
	((struct bpf_insn) {					\
		.code  = BPF_ALU | BPF_MOV | BPF_X,		\
		.dst_reg = DST,					\
		.src_reg = SRC,					\
		.off   = 0,					\
		.imm   = 0 })

/* Short form of mov, dst_reg = imm32 */

#define BPF_MOV64_IMM(DST, IMM)					\
	((struct bpf_insn) {					\
		.code  = BPF_ALU64 | BPF_MOV | BPF_K,		\
		.dst_reg = DST,					\
		.src_reg = 0,					\
		.off   = 0,					\
		.imm   = IMM })

#define BPF_MOV32_IMM(DST, IMM)					\
	((struct bpf_insn) {					\
		.code  = BPF_ALU | BPF_MOV | BPF_K,		\
		.dst_reg = DST,					\
		.src_reg = 0,					\
		.off   = 0,					\
		.imm   = IMM })

/* 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)			\
	((struct bpf_insn) {					\
		.code  = BPF_ALU64 | BPF_MOV | BPF_SRC(TYPE),	\
		.dst_reg = DST,					\
		.src_reg = SRC,					\
		.off   = 0,					\
		.imm   = IMM })

#define BPF_MOV32_RAW(TYPE, DST, SRC, IMM)			\
	((struct bpf_insn) {					\
		.code  = BPF_ALU | BPF_MOV | BPF_SRC(TYPE),	\
		.dst_reg = DST,					\
		.src_reg = SRC,					\
		.off   = 0,					\
		.imm   = IMM })

/* Direct packet access, R0 = *(uint *) (skb->data + imm32) */

#define BPF_LD_ABS(SIZE, IMM)					\
	((struct bpf_insn) {					\
		.code  = BPF_LD | BPF_SIZE(SIZE) | BPF_ABS,	\
		.dst_reg = 0,					\
		.src_reg = 0,					\
		.off   = 0,					\
		.imm   = IMM })

/* Indirect packet access, R0 = *(uint *) (skb->data + src_reg + imm32) */

#define BPF_LD_IND(SIZE, SRC, IMM)				\
	((struct bpf_insn) {					\
		.code  = BPF_LD | BPF_SIZE(SIZE) | BPF_IND,	\
		.dst_reg = 0,					\
		.src_reg = SRC,					\
		.off   = 0,					\
		.imm   = IMM })

/* Memory load, dst_reg = *(uint *) (src_reg + off16) */

#define BPF_LDX_MEM(SIZE, DST, SRC, OFF)			\
	((struct bpf_insn) {					\
		.code  = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEM,	\
		.dst_reg = DST,					\
		.src_reg = SRC,					\
		.off   = OFF,					\
		.imm   = 0 })

/* Memory store, *(uint *) (dst_reg + off16) = src_reg */

#define BPF_STX_MEM(SIZE, DST, SRC, OFF)			\
	((struct bpf_insn) {					\
		.code  = BPF_STX | BPF_SIZE(SIZE) | BPF_MEM,	\
		.dst_reg = DST,					\
		.src_reg = SRC,					\
		.off   = OFF,					\
		.imm   = 0 })

/* Memory store, *(uint *) (dst_reg + off16) = imm32 */

#define BPF_ST_MEM(SIZE, DST, OFF, IMM)				\
	((struct bpf_insn) {					\
		.code  = BPF_ST | BPF_SIZE(SIZE) | BPF_MEM,	\
		.dst_reg = DST,					\
		.src_reg = 0,					\
		.off   = OFF,					\
		.imm   = IMM })

/* Conditional jumps against registers, if (dst_reg 'op' src_reg) goto pc + off16 */

#define BPF_JMP_REG(OP, DST, SRC, OFF)				\
	((struct bpf_insn) {					\
		.code  = BPF_JMP | BPF_OP(OP) | BPF_X,		\
		.dst_reg = DST,					\
		.src_reg = SRC,					\
		.off   = OFF,					\
		.imm   = 0 })

/* Conditional jumps against immediates, if (dst_reg 'op' imm32) goto pc + off16 */

#define BPF_JMP_IMM(OP, DST, IMM, OFF)				\
	((struct bpf_insn) {					\
		.code  = BPF_JMP | BPF_OP(OP) | BPF_K,		\
		.dst_reg = DST,					\
		.src_reg = 0,					\
		.off   = OFF,					\
		.imm   = IMM })

/* Function call */

#define BPF_EMIT_CALL(FUNC)					\
	((struct bpf_insn) {					\
		.code  = BPF_JMP | BPF_CALL,			\
		.dst_reg = 0,					\
		.src_reg = 0,					\
		.off   = 0,					\
		.imm   = ((FUNC) - __bpf_call_base) })

/* Raw code statement block */

#define BPF_RAW_INSN(CODE, DST, SRC, OFF, IMM)			\
	((struct bpf_insn) {					\
		.code  = CODE,					\
		.dst_reg = DST,					\
		.src_reg = SRC,					\
		.off   = OFF,					\
		.imm   = IMM })

/* Program exit */

#define BPF_EXIT_INSN()						\
	((struct bpf_insn) {					\
		.code  = BPF_JMP | BPF_EXIT,			\
		.dst_reg = 0,					\
		.src_reg = 0,					\
		.off   = 0,					\
		.imm   = 0 })

#define bytes_to_bpf_size(bytes)				\
({								\
	int bpf_size = -EINVAL;					\
								\
	if (bytes == sizeof(u8))				\
		bpf_size = BPF_B;				\
	else if (bytes == sizeof(u16))				\
		bpf_size = BPF_H;				\
	else if (bytes == sizeof(u32))				\
		bpf_size = BPF_W;				\
	else if (bytes == sizeof(u64))				\
		bpf_size = BPF_DW;				\
								\
	bpf_size;						\
})

/* Macro to invoke filter function. */
#define SK_RUN_FILTER(filter, ctx) \
	(*filter->prog->bpf_func)(ctx, filter->prog->insnsi)

struct bpf_insn {
	__u8	code;		/* opcode */
	__u8	dst_reg:4;	/* dest register */
	__u8	src_reg:4;	/* source register */
	__s16	off;		/* signed offset */
	__s32	imm;		/* signed immediate constant */
};

#ifdef CONFIG_COMPAT
/* A struct sock_filter is architecture independent. */
struct compat_sock_fprog {
	u16		len;
	compat_uptr_t	filter;	/* struct sock_filter * */
};
#endif

struct sock_fprog_kern {
	u16			len;
	struct sock_filter	*filter;
};

struct sk_buff;
struct sock;
struct seccomp_data;

struct bpf_prog {
	u32			jited:1,	/* Is our filter JIT'ed? */
				len:31;		/* Number of filter blocks */
	struct sock_fprog_kern	*orig_prog;	/* Original BPF program */
	unsigned int		(*bpf_func)(const struct sk_buff *skb,
					    const struct bpf_insn *filter);
	union {
		struct sock_filter	insns[0];
		struct bpf_insn		insnsi[0];
		struct work_struct	work;
	};
};

struct sk_filter {
	atomic_t	refcnt;
	struct rcu_head	rcu;
	struct bpf_prog	*prog;
};

#define BPF_PROG_RUN(filter, ctx)  (*filter->bpf_func)(ctx, filter->insnsi)

static inline unsigned int bpf_prog_size(unsigned int proglen)
{
	return max(sizeof(struct bpf_prog),
		   offsetof(struct bpf_prog, insns[proglen]));
}

#define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0]))

int sk_filter(struct sock *sk, struct sk_buff *skb);

void bpf_prog_select_runtime(struct bpf_prog *fp);
void bpf_prog_free(struct bpf_prog *fp);

int bpf_convert_filter(struct sock_filter *prog, int len,
		       struct bpf_insn *new_prog, int *new_len);

int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog);
void bpf_prog_destroy(struct bpf_prog *fp);

int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
int sk_detach_filter(struct sock *sk);

int bpf_check_classic(const struct sock_filter *filter, unsigned int flen);
int sk_get_filter(struct sock *sk, struct sock_filter __user *filter,
		  unsigned int len);

bool sk_filter_charge(struct sock *sk, struct sk_filter *fp);
void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp);

u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
void bpf_int_jit_compile(struct bpf_prog *fp);

#define BPF_ANC		BIT(15)

static inline u16 bpf_anc_helper(const struct sock_filter *ftest)
{
	BUG_ON(ftest->code & BPF_ANC);

	switch (ftest->code) {
	case BPF_LD | BPF_W | BPF_ABS:
	case BPF_LD | BPF_H | BPF_ABS:
	case BPF_LD | BPF_B | BPF_ABS:
#define BPF_ANCILLARY(CODE)	case SKF_AD_OFF + SKF_AD_##CODE:	\
				return BPF_ANC | SKF_AD_##CODE
		switch (ftest->k) {
		BPF_ANCILLARY(PROTOCOL);
		BPF_ANCILLARY(PKTTYPE);
		BPF_ANCILLARY(IFINDEX);
		BPF_ANCILLARY(NLATTR);
		BPF_ANCILLARY(NLATTR_NEST);
		BPF_ANCILLARY(MARK);
		BPF_ANCILLARY(QUEUE);
		BPF_ANCILLARY(HATYPE);
		BPF_ANCILLARY(RXHASH);
		BPF_ANCILLARY(CPU);
		BPF_ANCILLARY(ALU_XOR_X);
		BPF_ANCILLARY(VLAN_TAG);
		BPF_ANCILLARY(VLAN_TAG_PRESENT);
		BPF_ANCILLARY(PAY_OFFSET);
		BPF_ANCILLARY(RANDOM);
		}
		/* Fallthrough. */
	default:
		return ftest->code;
	}
}

void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb,
					   int k, unsigned int size);

static inline void *bpf_load_pointer(const struct sk_buff *skb, int k,
				     unsigned int size, void *buffer)
{
	if (k >= 0)
		return skb_header_pointer(skb, k, size, buffer);

	return bpf_internal_load_pointer_neg_helper(skb, k, size);
}

#ifdef CONFIG_BPF_JIT
#include <stdarg.h>
#include <linux/linkage.h>
#include <linux/printk.h>

void bpf_jit_compile(struct bpf_prog *fp);
void bpf_jit_free(struct bpf_prog *fp);

static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen,
				u32 pass, void *image)
{
	pr_err("flen=%u proglen=%u pass=%u image=%pK\n",
	       flen, proglen, pass, image);
	if (image)
		print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_OFFSET,
			       16, 1, image, proglen, false);
}
#else
#include <linux/slab.h>

static inline void bpf_jit_compile(struct bpf_prog *fp)
{
}

static inline void bpf_jit_free(struct bpf_prog *fp)
{
	kfree(fp);
}
#endif /* CONFIG_BPF_JIT */

static inline int bpf_tell_extensions(void)
{
	return SKF_AD_MAX;
}

#endif /* __LINUX_FILTER_H__ */