aiot/efHeterogeneousSynchronization/main.c

/*
 * Just-In-Time compiler for BPF filters on 32bit ARM
 *
 * Copyright (c) 2011 Mircea Gherzan <mgherzan@gmail.com>
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License as published by the
 * Free Software Foundation; version 2 of the License.
 */

#include <linux/bitops.h>
#include <linux/compiler.h>
#include <linux/errno.h>
#include <linux/filter.h>
#include <linux/moduleloader.h>
#include <linux/netdevice.h>
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/if_vlan.h>
#include <asm/cacheflush.h>
#include <asm/hwcap.h>

#include "bpf_jit_32.h"

/*
 * ABI:
 *
 * r0	scratch register
 * r4	BPF register A
 * r5	BPF register X
 * r6	pointer to the skb
 * r7	skb->data
 * r8	skb_headlen(skb)
 */

#define r_scratch	ARM_R0
/* r1-r3 are (also) used for the unaligned loads on the non-ARMv7 slowpath */
#define r_off		ARM_R1
#define r_A		ARM_R4
#define r_X		ARM_R5
#define r_skb		ARM_R6
#define r_skb_data	ARM_R7
#define r_skb_hl	ARM_R8

#define SCRATCH_SP_OFFSET	0
#define SCRATCH_OFF(k)		(SCRATCH_SP_OFFSET + 4 * (k))

#define SEEN_MEM		((1 << BPF_MEMWORDS) - 1)
#define SEEN_MEM_WORD(k)	(1 << (k))
#define SEEN_X			(1 << BPF_MEMWORDS)
#define SEEN_CALL		(1 << (BPF_MEMWORDS + 1))
#define SEEN_SKB		(1 << (BPF_MEMWORDS + 2))
#define SEEN_DATA		(1 << (BPF_MEMWORDS + 3))

#define FLAG_NEED_X_RESET	(1 << 0)

struct jit_ctx {
	const struct sk_filter *skf;
	unsigned idx;
	unsigned prologue_bytes;
	int ret0_fp_idx;
	u32 seen;
	u32 flags;
	u32 *offsets;
	u32 *target;
#if __LINUX_ARM_ARCH__ < 7
	u16 epilogue_bytes;
	u16 imm_count;
	u32 *imms;
#endif
};

int bpf_jit_enable __read_mostly;

static u64 jit_get_skb_b(struct sk_buff *skb, unsigned offset)
{
	u8 ret;
	int err;

	err = skb_copy_bits(skb, offset, &ret, 1);

	return (u64)err << 32 | ret;
}

static u64 jit_get_skb_h(struct sk_buff *skb, unsigned offset)
{
	u16 ret;
	int err;

	err = skb_copy_bits(skb, offset, &ret, 2);

	return (u64)err << 32 | ntohs(ret);
}

static u64 jit_get_skb_w(struct sk_buff *skb, unsigned offset)
{
	u32 ret;
	int err;

	err = skb_copy_bits(skb, offset, &ret, 4);

	return (u64)err << 32 | ntohl(ret);
}

/*
 * Wrapper that handles both OABI and EABI and assures Thumb2 interworking
 * (where the assembly routines like __aeabi_uidiv could cause problems).
 */
static u32 jit_udiv(u32 dividend, u32 divisor)
{
	return dividend / divisor;
}

static inline void _emit(int cond, u32 inst, struct jit_ctx *ctx)
{
	if (ctx->target != NULL)
		ctx->target[ctx->idx] = inst | (cond << 28);

	ctx->idx++;
}

/*
 * Emit an instruction that will be executed unconditionally.
 */
static inline void emit(u32 inst, struct jit_ctx *ctx)
{
	_emit(ARM_COND_AL, inst, ctx);
}

static u16 saved_regs(struct jit_ctx *ctx)
{
	u16 ret = 0;

	if ((ctx->skf->len > 1) ||
	    (ctx->skf->insns[0].code == BPF_S_RET_A))
		ret |= 1 << r_A;

#ifdef CONFIG_FRAME_POINTER
	ret |= (1 << ARM_FP) | (1 << ARM_IP) | (1 << ARM_LR) | (1 << ARM_PC);
#else
	if (ctx->seen & SEEN_CALL)
		ret |= 1 << ARM_LR;
#endif
	if (ctx->seen & (SEEN_DATA | SEEN_SKB))
		ret |= 1 << r_skb;
	if (ctx->seen & SEEN_DATA)
		ret |= (1 << r_skb_data) | (1 << r_skb_hl);
	if (ctx->seen & SEEN_X)
		ret |= 1 << r_X;

	return ret;
}

static inline int mem_words_used(struct jit_ctx *ctx)
{
	/* yes, we do waste some stack space IF there are "holes" in the set" */
	return fls(ctx->seen & SEEN_MEM);
}

static inline bool is_load_to_a(u16 inst)
{
	switch (inst) {
	case BPF_S_LD_W_LEN:
	case BPF_S_LD_W_ABS:
	case BPF_S_LD_H_ABS:
	case BPF_S_LD_B_ABS:
	case BPF_S_ANC_CPU:
	case BPF_S_ANC_IFINDEX:
	case BPF_S_ANC_MARK:
	case BPF_S_ANC_PROTOCOL:
	case BPF_S_ANC_RXHASH:
	case BPF_S_ANC_VLAN_TAG:
	case BPF_S_ANC_VLAN_TAG_PRESENT:
	case BPF_S_ANC_QUEUE:
		return true;
	default:
		return false;
	}
}

static void build_prologue(struct jit_ctx *ctx)
{
	u16 reg_set = saved_regs(ctx);
	u16 first_inst = ctx->skf->insns[0].code;
	u16 off;

#ifdef CONFIG_FRAME_POINTER
	emit(ARM_MOV_R(ARM_IP, ARM_SP), ctx);
	emit(ARM_PUSH(reg_set), ctx);
	emit(ARM_SUB_I(ARM_FP, ARM_IP, 4), ctx);
#else
	if (reg_set)
		emit(ARM_PUSH(reg_set), ctx);
#endif

	if (ctx->seen & (SEEN_DATA | SEEN_SKB))
		emit(ARM_MOV_R(r_skb, ARM_R0), ctx);

	if (ctx->seen & SEEN_DATA) {
		off = offsetof(struct sk_buff, data);
		emit(ARM_LDR_I(r_skb_data, r_skb, off), ctx);
		/* headlen = len - data_len */
		off = offsetof(struct sk_buff, len);
		emit(ARM_LDR_I(r_skb_hl, r_skb, off), ctx);
		off = offsetof(struct sk_buff, data_len);
		emit(ARM_LDR_I(r_scratch, r_skb, off), ctx);
		emit(ARM_SUB_R(r_skb_hl, r_skb_hl, r_scratch), ctx);
	}

	if (ctx->flags & FLAG_NEED_X_RESET)
		emit(ARM_MOV_I(r_X, 0), ctx);

	/* do not leak kernel data to userspace */
	if ((first_inst != BPF_S_RET_K) && !(is_load_to_a(first_inst)))
		emit(ARM_MOV_I(r_A, 0), ctx);

	/* stack space for the BPF_MEM words */
	if (ctx->seen & SEEN_MEM)
		emit(ARM_SUB_I(ARM_SP, ARM_SP, mem_words_used(ctx) * 4), ctx);
}

static void build_epilogue(struct jit_ctx *ctx)
{
	u16 reg_set = saved_regs(ctx);

	if (ctx->seen & SEEN_MEM)
		emit(ARM_ADD_I(ARM_SP, ARM_SP, mem_words_used(ctx) * 4), ctx);

	reg_set &= ~(1 << ARM_LR);

#ifdef CONFIG_FRAME_POINTER
	/* the first instruction of the prologue was: mov ip, sp */
	reg_set &= ~(1 << ARM_IP);
	reg_set |= (1 << ARM_SP);
	emit(ARM_LDM(ARM_SP, reg_set), ctx);
#else
	if (reg_set) {
		if (ctx->seen & SEEN_CALL)
			reg_set |= 1 << ARM_PC;
		emit(ARM_POP(reg_set), ctx);
	}

	if (!(ctx->seen & SEEN_CALL))
		emit(ARM_BX(ARM_LR), ctx);
#endif
}

static int16_t imm8m(u32 x)
{
	u32 rot;

	for (rot = 0; rot < 16; rot++)
		if ((x & ~ror32(0xff, 2 * rot)) == 0)
			return rol32(x, 2 * rot) | (rot << 8);

	return -1;
}

#if __LINUX_ARM_ARCH__ < 7

static u16 imm_offset(u32 k, struct jit_ctx *ctx)
{
	unsigned i = 0, offset;
	u16 imm;

	/* on the "fake" run we just count them (duplicates included) */
	if (ctx->target == NULL) {
		ctx->imm_count++;
		return 0;
	}

	while ((i < ctx->imm_count) && ctx->imms[i]) {
		if (ctx->imms[i] == k)
			break;
		i++;
	}

	if (ctx->imms[i] == 0)
		ctx->imms[i] = k;

	/* constants go just after the epilogue */
	offset =  ctx->offsets[ctx->skf->len];
	offset += ctx->prologue_bytes;
	offset += ctx->epilogue_bytes;
	offset += i * 4;

	ctx->target[offset / 4] = k;

	/* PC in ARM mode == address of the instruction + 8 */
	imm = offset - (8 + ctx->idx * 4);

	return imm;
}

#endif /* __LINUX_ARM_ARCH__ */

/*
 * Move an immediate that's not an imm8m to a core register.
 */
static inline void emit_mov_i_no8m(int rd, u32 val, struct jit_ctx *ctx)
{
#if __LINUX_ARM_ARCH__ < 7
	emit(ARM_LDR_I(rd, ARM_PC, imm_offset(val, ctx)), ctx);
#else
	emit(ARM_MOVW(rd, val & 0xffff), ctx);
	if (val > 0xffff)
		emit(ARM_MOVT(rd, val >> 16), ctx);
#endif
}

static inline void emit_mov_i(int rd, u32 val, struct jit_ctx *ctx)
{
	int imm12 = imm8m(val);

	if (imm12 >= 0)
		emit(ARM_MOV_I(rd, imm12), ctx);
	else
		emit_mov_i_no8m(rd, val, ctx);
}

#if __LINUX_ARM_ARCH__ < 6

static void emit_load_be32(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx)
{
	_emit(cond, ARM_LDRB_I(ARM_R3, r_addr, 1), ctx);
	_emit(cond, ARM_LDRB_I(ARM_R1, r_addr, 0), ctx);
	_emit(cond, ARM_LDRB_I(ARM_R2, r_addr, 3), ctx);
	_emit(cond, ARM_LSL_I(ARM_R3, ARM_R3, 16), ctx);
	_emit(cond, ARM_LDRB_I(ARM_R0, r_addr, 2), ctx);
	_emit(cond, ARM_ORR_S(ARM_R3, ARM_R3, ARM_R1, SRTYPE_LSL, 24), ctx);
	_emit(cond, ARM_ORR_R(ARM_R3, ARM_R3, ARM_R2), ctx);
	_emit(cond, ARM_ORR_S(r_res, ARM_R3, ARM_R0, SRTYPE_LSL, 8), ctx);
}

static void emit_load_be16(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx)
{
	_emit(cond, ARM_LDRB_I(ARM_R1, r_addr, 0), ctx);
	_emit(cond, ARM_LDRB_I(ARM_R2, r_addr, 1), ctx);
	_emit(cond, ARM_ORR_S(r_res, ARM_R2, ARM_R1, SRTYPE_LSL, 8), ctx);
}

static inline void emit_swap16(u8 r_dst, u8 r_src, struct jit_ctx *ctx)
{
	emit(ARM_LSL_R(ARM_R1, r_src, 8), ctx);
	emit(ARM_ORR_S(r_dst, ARM_R1, r_src, SRTYPE_LSL, 8), ctx);
	emit(ARM_LSL_I(r_dst, r_dst, 8), ctx);
	emit(ARM_LSL_R(r_dst, r_dst, 8), ctx);
}

#else  /* ARMv6+ */

static void emit_load_be32(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx)
{
	_emit(cond, ARM_LDR_I(r_res, r_addr, 0), ctx);
#ifdef __LITTLE_ENDIAN
	_emit(cond, ARM_REV(r_res, r_res), ctx);
#endif
}

static void emit_load_be16(u8 cond, u8 r_res, u8 r_addr, struct jit_ctx *ctx)
{
	_emit(cond, ARM_LDRH_I(r_res, r_addr, 0), ctx);
#ifdef __LITTLE_ENDIAN
	_emit(cond, ARM_REV16(r_res, r_res), ctx);
#endif
}

static inline void emit_swap16(u8 r_dst __maybe_unused,
			       u8 r_src __maybe_unused,