Merge branch 'powercap'

[deliverable/linux.git] / include / linux / filter.h

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

#include <stdarg.h>

#include <linux/atomic.h>
#include <linux/compat.h>
#include <linux/skbuff.h>
#include <linux/linkage.h>
#include <linux/printk.h>
#include <linux/workqueue.h>
#include <linux/sched.h>
#include <linux/capability.h>

#include <net/sch_generic.h>

#include <asm/cacheflush.h>

#include <uapi/linux/filter.h>
#include <uapi/linux/bpf.h>

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
 * 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

/* Kernel hidden auxiliary/helper register for hardening step.
 * Only used by eBPF JITs. It's nothing more than a temporary
 * register that JITs use internally, only that here it's part
 * of eBPF instructions that have been rewritten for blinding
 * constants. See JIT pre-step in bpf_jit_blind_constants().
 */
#define BPF_REG_AX		MAX_BPF_REG
#define MAX_BPF_JIT_REG		(MAX_BPF_REG + 1)

/* 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 })

/* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */
#define BPF_LD_IMM64(DST, IMM)					\
	BPF_LD_IMM64_RAW(DST, 0, IMM)

#define BPF_LD_IMM64_RAW(DST, SRC, IMM)				\
	((struct bpf_insn) {					\
		.code  = BPF_LD | BPF_DW | BPF_IMM,		\
		.dst_reg = DST,					\
		.src_reg = SRC,					\
		.off   = 0,					\
		.imm   = (__u32) (IMM) }),			\
	((struct bpf_insn) {					\
		.code  = 0, /* zero is reserved opcode */	\
		.dst_reg = 0,					\
		.src_reg = 0,					\
		.off   = 0,					\
		.imm   = ((__u64) (IMM)) >> 32 })

/* 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)			\
	((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 })

/* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */

#define BPF_STX_XADD(SIZE, DST, SRC, OFF)			\
	((struct bpf_insn) {					\
		.code  = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD,	\
		.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 })

/* Internal classic blocks for direct assignment */

#define __BPF_STMT(CODE, K)					\
	((struct sock_filter) BPF_STMT(CODE, K))

#define __BPF_JUMP(CODE, K, JT, JF)				\
	((struct sock_filter) BPF_JUMP(CODE, K, JT, JF))

#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;						\
})

#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 bpf_binary_header {
	unsigned int pages;
	u8 image[];
};

struct bpf_prog {
	u16			pages;		/* Number of allocated pages */
	kmemcheck_bitfield_begin(meta);
	u16			jited:1,	/* Is our filter JIT'ed? */
				gpl_compatible:1, /* Is filter GPL compatible? */
				cb_access:1,	/* Is control block accessed? */
				dst_needed:1;	/* Do we need dst entry? */
	kmemcheck_bitfield_end(meta);
	u32			len;		/* Number of filter blocks */
	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 */
	union {
		struct sock_filter	insns[0];
		struct bpf_insn		insnsi[0];
	};
};

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)

#define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN

struct bpf_skb_data_end {
	struct qdisc_skb_cb qdisc_cb;
	void *data_end;
};

/* compute the linear packet data range [data, data_end) which
 * will be accessed by cls_bpf and act_bpf programs
 */
static inline void bpf_compute_data_end(struct sk_buff *skb)
{
	struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb;

	BUILD_BUG_ON(sizeof(*cb) > FIELD_SIZEOF(struct sk_buff, cb));
	cb->data_end = skb->data + skb_headlen(skb);
}

static inline u8 *bpf_skb_cb(struct sk_buff *skb)
{
	/* eBPF programs may read/write skb->cb[] area to transfer meta
	 * data between tail calls. Since this also needs to work with
	 * tc, that scratch memory is mapped to qdisc_skb_cb's data area.
	 *
	 * In some socket filter cases, the cb unfortunately needs to be
	 * saved/restored so that protocol specific skb->cb[] data won't
	 * be lost. In any case, due to unpriviledged eBPF programs
	 * attached to sockets, we need to clear the bpf_skb_cb() area
	 * to not leak previous contents to user space.
	 */
	BUILD_BUG_ON(FIELD_SIZEOF(struct __sk_buff, cb) != BPF_SKB_CB_LEN);
	BUILD_BUG_ON(FIELD_SIZEOF(struct __sk_buff, cb) !=
		     FIELD_SIZEOF(struct qdisc_skb_cb, data));

	return qdisc_skb_cb(skb)->data;
}

static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog,
				       struct sk_buff *skb)
{
	u8 *cb_data = bpf_skb_cb(skb);
	u8 cb_saved[BPF_SKB_CB_LEN];
	u32 res;

	if (unlikely(prog->cb_access)) {
		memcpy(cb_saved, cb_data, sizeof(cb_saved));
		memset(cb_data, 0, sizeof(cb_saved));
	}

	res = BPF_PROG_RUN(prog, skb);

	if (unlikely(prog->cb_access))
		memcpy(cb_data, cb_saved, sizeof(cb_saved));

	return res;
}

static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog,
					struct sk_buff *skb)
{
	u8 *cb_data = bpf_skb_cb(skb);

	if (unlikely(prog->cb_access))
		memset(cb_data, 0, BPF_SKB_CB_LEN);

	return BPF_PROG_RUN(prog, skb);
}

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

static inline bool bpf_prog_was_classic(const struct bpf_prog *prog)
{
	/* When classic BPF programs have been loaded and the arch
	 * does not have a classic BPF JIT (anymore), they have been
	 * converted via bpf_migrate_filter() to eBPF and thus always
	 * have an unspec program type.
	 */
	return prog->type == BPF_PROG_TYPE_UNSPEC;
}

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

#ifdef CONFIG_DEBUG_SET_MODULE_RONX
static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
{
	set_memory_ro((unsigned long)fp, fp->pages);
}

static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
{
	set_memory_rw((unsigned long)fp, fp->pages);
}
#else
static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
{
}

static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
{
}
#endif /* CONFIG_DEBUG_SET_MODULE_RONX */

int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap);
static inline int sk_filter(struct sock *sk, struct sk_buff *skb)
{
	return sk_filter_trim_cap(sk, skb, 1);
}

struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err);
void bpf_prog_free(struct bpf_prog *fp);

struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags);
struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
				  gfp_t gfp_extra_flags);
void __bpf_prog_free(struct bpf_prog *fp);

static inline void bpf_prog_unlock_free(struct bpf_prog *fp)
{
	bpf_prog_unlock_ro(fp);
	__bpf_prog_free(fp);
}

typedef int (*bpf_aux_classic_check_t)(struct sock_filter *filter,
				       unsigned int flen);

int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog);
int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog,
			      bpf_aux_classic_check_t trans, bool save_orig);
void bpf_prog_destroy(struct bpf_prog *fp);

int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
int sk_attach_bpf(u32 ufd, struct sock *sk);
int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk);
int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk);
int sk_detach_filter(struct sock *sk);
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);

struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog);
bool bpf_helper_changes_skb_data(void *func);

struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
				       const struct bpf_insn *patch, u32 len);

#ifdef CONFIG_BPF_JIT
extern int bpf_jit_enable;
extern int bpf_jit_harden;

typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size);

struct bpf_binary_header *
bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
		     unsigned int alignment,
		     bpf_jit_fill_hole_t bpf_fill_ill_insns);
void bpf_jit_binary_free(struct bpf_binary_header *hdr);

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

struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *fp);
void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other);

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 from=%s pid=%d\n", flen,
	       proglen, pass, image, current->comm, task_pid_nr(current));

	if (image)
		print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_OFFSET,
			       16, 1, image, proglen, false);
}

static inline bool bpf_jit_is_ebpf(void)
{
# ifdef CONFIG_HAVE_EBPF_JIT
	return true;
# else
	return false;
# endif
}

static inline bool bpf_jit_blinding_enabled(void)
{
	/* These are the prerequisites, should someone ever have the
	 * idea to call blinding outside of them, we make sure to
	 * bail out.
	 */
	if (!bpf_jit_is_ebpf())
		return false;
	if (!bpf_jit_enable)
		return false;
	if (!bpf_jit_harden)
		return false;
	if (bpf_jit_harden == 1 && capable(CAP_SYS_ADMIN))
		return false;

	return true;
}
#else
static inline void bpf_jit_compile(struct bpf_prog *fp)
{
}

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

#define BPF_ANC		BIT(15)

static inline bool bpf_needs_clear_a(const struct sock_filter *first)
{
	switch (first->code) {
	case BPF_RET | BPF_K:
	case BPF_LD | BPF_W | BPF_LEN:
		return false;

	case BPF_LD | BPF_W | BPF_ABS:
	case BPF_LD | BPF_H | BPF_ABS:
	case BPF_LD | BPF_B | BPF_ABS:
		if (first->k == SKF_AD_OFF + SKF_AD_ALU_XOR_X)
			return true;
		return false;

	default:
		return true;
	}
}

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);
		BPF_ANCILLARY(VLAN_TPID);
		}
		/* 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);
}

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

#endif /* __LINUX_FILTER_H__ */