leandrof/linux
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

riscv, bpf: Factor common RISC-V JIT code

Browse Source 
This patch factors out code that can be used by both the RV64 and RV32
BPF JITs to a common bpf_jit.h and bpf_jit_core.c.

Move struct definitions and macro-like functions to header. Rename
rv_sb_insn/rv_uj_insn to rv_b_insn/rv_j_insn to match the RISC-V
specification.

Move reusable functions emit_body() and bpf_int_jit_compile() to
bpf_jit_core.c with minor simplifications. Rename emit_insn() and
build_{prologue,epilogue}() to be prefixed with "bpf_jit_" as they are
no longer static.

Rename bpf_jit_comp.c to bpf_jit_comp64.c to be more explicit.

Co-developed-by: Xi Wang <xi.wang@gmail.com>
Signed-off-by: Xi Wang <xi.wang@gmail.com>
Signed-off-by: Luke Nelson <luke.r.nels@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Björn Töpel <bjorn.topel@gmail.com>
Acked-by: Björn Töpel <bjorn.topel@gmail.com>
Link: https://lore.kernel.org/bpf/20200305050207.4159-2-luke.r.nels@gmail.com
This commit is contained in:
Luke Nelson 2020-03-04 21:02:04 -08:00 committed by Daniel Borkmann
parent 9ce6010290
commit ca6cb5447c
4 changed files with 639 additions and 601 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
arch/riscv/net/Makefile
View File

@ -1,2 +1,3 @@
# SPDX-License-Identifier: GPL-2.0-only # SPDX-License-Identifier: GPL-2.0-only
obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o
obj-$(CONFIG_BPF_JIT) += bpf_jit_core.o bpf_jit_comp64.o

466
arch/riscv/net/bpf_jit.h Normal file
View File

@ -0,0 +1,466 @@
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Common functionality for RV32 and RV64 BPF JIT compilers
*
* Copyright (c) 2019 Björn Töpel <bjorn.topel@gmail.com>
*
*/
#ifndef _BPF_JIT_H
#define _BPF_JIT_H
#include <linux/bpf.h>
#include <linux/filter.h>
#include <asm/cacheflush.h>
enum {
RV_REG_ZERO = 0, /* The constant value 0 */
RV_REG_RA = 1, /* Return address */
RV_REG_SP = 2, /* Stack pointer */
RV_REG_GP = 3, /* Global pointer */
RV_REG_TP = 4, /* Thread pointer */
RV_REG_T0 = 5, /* Temporaries */
RV_REG_T1 = 6,
RV_REG_T2 = 7,
RV_REG_FP = 8, /* Saved register/frame pointer */
RV_REG_S1 = 9, /* Saved register */
RV_REG_A0 = 10, /* Function argument/return values */
RV_REG_A1 = 11, /* Function arguments */
RV_REG_A2 = 12,
RV_REG_A3 = 13,
RV_REG_A4 = 14,
RV_REG_A5 = 15,
RV_REG_A6 = 16,
RV_REG_A7 = 17,
RV_REG_S2 = 18, /* Saved registers */
RV_REG_S3 = 19,
RV_REG_S4 = 20,
RV_REG_S5 = 21,
RV_REG_S6 = 22,
RV_REG_S7 = 23,
RV_REG_S8 = 24,
RV_REG_S9 = 25,
RV_REG_S10 = 26,
RV_REG_S11 = 27,
RV_REG_T3 = 28, /* Temporaries */
RV_REG_T4 = 29,
RV_REG_T5 = 30,
RV_REG_T6 = 31,
};
struct rv_jit_context {
struct bpf_prog *prog;
u32 *insns; /* RV insns */
int ninsns;
int epilogue_offset;
int *offset; /* BPF to RV */
unsigned long flags;
int stack_size;
};
struct rv_jit_data {
struct bpf_binary_header *header;
u8 *image;
struct rv_jit_context ctx;
};
static inline void bpf_fill_ill_insns(void *area, unsigned int size)
{
memset(area, 0, size);
}
static inline void bpf_flush_icache(void *start, void *end)
{
flush_icache_range((unsigned long)start, (unsigned long)end);
}
static inline void emit(const u32 insn, struct rv_jit_context *ctx)
{
if (ctx->insns)
ctx->insns[ctx->ninsns] = insn;
ctx->ninsns++;
}
static inline int epilogue_offset(struct rv_jit_context *ctx)
{
int to = ctx->epilogue_offset, from = ctx->ninsns;
return (to - from) << 2;
}
/* Return -1 or inverted cond. */
static inline int invert_bpf_cond(u8 cond)
{
switch (cond) {
case BPF_JEQ:
return BPF_JNE;
case BPF_JGT:
return BPF_JLE;
case BPF_JLT:
return BPF_JGE;
case BPF_JGE:
return BPF_JLT;
case BPF_JLE:
return BPF_JGT;
case BPF_JNE:
return BPF_JEQ;
case BPF_JSGT:
return BPF_JSLE;
case BPF_JSLT:
return BPF_JSGE;
case BPF_JSGE:
return BPF_JSLT;
case BPF_JSLE:
return BPF_JSGT;
}
return -1;
}
static inline bool is_12b_int(long val)
{
return -(1L << 11) <= val && val < (1L << 11);
}
static inline int is_12b_check(int off, int insn)
{
if (!is_12b_int(off)) {
pr_err("bpf-jit: insn=%d 12b < offset=%d not supported yet!\n",
insn, (int)off);
return -1;
}
return 0;
}
static inline bool is_13b_int(long val)
{
return -(1L << 12) <= val && val < (1L << 12);
}
static inline bool is_21b_int(long val)
{
return -(1L << 20) <= val && val < (1L << 20);
}
static inline int rv_offset(int insn, int off, struct rv_jit_context *ctx)
{
int from, to;
off++; /* BPF branch is from PC+1, RV is from PC */
from = (insn > 0) ? ctx->offset[insn - 1] : 0;
to = (insn + off > 0) ? ctx->offset[insn + off - 1] : 0;
return (to - from) << 2;
}
/* Instruction formats. */
static inline u32 rv_r_insn(u8 funct7, u8 rs2, u8 rs1, u8 funct3, u8 rd,
u8 opcode)
{
return (funct7 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) |
(rd << 7) | opcode;
}
static inline u32 rv_i_insn(u16 imm11_0, u8 rs1, u8 funct3, u8 rd, u8 opcode)
{
return (imm11_0 << 20) | (rs1 << 15) | (funct3 << 12) | (rd << 7) |
opcode;
}
static inline u32 rv_s_insn(u16 imm11_0, u8 rs2, u8 rs1, u8 funct3, u8 opcode)
{
u8 imm11_5 = imm11_0 >> 5, imm4_0 = imm11_0 & 0x1f;
return (imm11_5 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) |
(imm4_0 << 7) | opcode;
}
static inline u32 rv_b_insn(u16 imm12_1, u8 rs2, u8 rs1, u8 funct3, u8 opcode)
{
u8 imm12 = ((imm12_1 & 0x800) >> 5) | ((imm12_1 & 0x3f0) >> 4);
u8 imm4_1 = ((imm12_1 & 0xf) << 1) | ((imm12_1 & 0x400) >> 10);
return (imm12 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) |
(imm4_1 << 7) | opcode;
}
static inline u32 rv_u_insn(u32 imm31_12, u8 rd, u8 opcode)
{
return (imm31_12 << 12) | (rd << 7) | opcode;
}
static inline u32 rv_j_insn(u32 imm20_1, u8 rd, u8 opcode)
{
u32 imm;
imm = (imm20_1 & 0x80000) | ((imm20_1 & 0x3ff) << 9) |
((imm20_1 & 0x400) >> 2) | ((imm20_1 & 0x7f800) >> 11);
return (imm << 12) | (rd << 7) | opcode;
}
static inline u32 rv_amo_insn(u8 funct5, u8 aq, u8 rl, u8 rs2, u8 rs1,
u8 funct3, u8 rd, u8 opcode)
{
u8 funct7 = (funct5 << 2) | (aq << 1) | rl;
return rv_r_insn(funct7, rs2, rs1, funct3, rd, opcode);
}
static inline u32 rv_addi(u8 rd, u8 rs1, u16 imm11_0)
{
return rv_i_insn(imm11_0, rs1, 0, rd, 0x13);
}
static inline u32 rv_andi(u8 rd, u8 rs1, u16 imm11_0)
{
return rv_i_insn(imm11_0, rs1, 7, rd, 0x13);
}
static inline u32 rv_ori(u8 rd, u8 rs1, u16 imm11_0)
{
return rv_i_insn(imm11_0, rs1, 6, rd, 0x13);
}
static inline u32 rv_xori(u8 rd, u8 rs1, u16 imm11_0)
{
return rv_i_insn(imm11_0, rs1, 4, rd, 0x13);
}
static inline u32 rv_slli(u8 rd, u8 rs1, u16 imm11_0)
{
return rv_i_insn(imm11_0, rs1, 1, rd, 0x13);
}
static inline u32 rv_srli(u8 rd, u8 rs1, u16 imm11_0)
{
return rv_i_insn(imm11_0, rs1, 5, rd, 0x13);
}
static inline u32 rv_srai(u8 rd, u8 rs1, u16 imm11_0)
{
return rv_i_insn(0x400 | imm11_0, rs1, 5, rd, 0x13);
}
static inline u32 rv_lui(u8 rd, u32 imm31_12)
{
return rv_u_insn(imm31_12, rd, 0x37);
}
static inline u32 rv_auipc(u8 rd, u32 imm31_12)
{
return rv_u_insn(imm31_12, rd, 0x17);
}
static inline u32 rv_add(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(0, rs2, rs1, 0, rd, 0x33);
}
static inline u32 rv_sub(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(0x20, rs2, rs1, 0, rd, 0x33);
}
static inline u32 rv_and(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(0, rs2, rs1, 7, rd, 0x33);
}
static inline u32 rv_or(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(0, rs2, rs1, 6, rd, 0x33);
}
static inline u32 rv_xor(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(0, rs2, rs1, 4, rd, 0x33);
}
static inline u32 rv_sll(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(0, rs2, rs1, 1, rd, 0x33);
}
static inline u32 rv_srl(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(0, rs2, rs1, 5, rd, 0x33);
}
static inline u32 rv_sra(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(0x20, rs2, rs1, 5, rd, 0x33);
}
static inline u32 rv_mul(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(1, rs2, rs1, 0, rd, 0x33);
}
static inline u32 rv_divu(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(1, rs2, rs1, 5, rd, 0x33);
}
static inline u32 rv_remu(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(1, rs2, rs1, 7, rd, 0x33);
}
static inline u32 rv_jal(u8 rd, u32 imm20_1)
{
return rv_j_insn(imm20_1, rd, 0x6f);
}
static inline u32 rv_jalr(u8 rd, u8 rs1, u16 imm11_0)
{
return rv_i_insn(imm11_0, rs1, 0, rd, 0x67);
}
static inline u32 rv_beq(u8 rs1, u8 rs2, u16 imm12_1)
{
return rv_b_insn(imm12_1, rs2, rs1, 0, 0x63);
}
static inline u32 rv_bne(u8 rs1, u8 rs2, u16 imm12_1)
{
return rv_b_insn(imm12_1, rs2, rs1, 1, 0x63);
}
static inline u32 rv_bltu(u8 rs1, u8 rs2, u16 imm12_1)
{
return rv_b_insn(imm12_1, rs2, rs1, 6, 0x63);
}
static inline u32 rv_bgeu(u8 rs1, u8 rs2, u16 imm12_1)
{
return rv_b_insn(imm12_1, rs2, rs1, 7, 0x63);
}
static inline u32 rv_blt(u8 rs1, u8 rs2, u16 imm12_1)
{
return rv_b_insn(imm12_1, rs2, rs1, 4, 0x63);
}
static inline u32 rv_bge(u8 rs1, u8 rs2, u16 imm12_1)
{
return rv_b_insn(imm12_1, rs2, rs1, 5, 0x63);
}
static inline u32 rv_lbu(u8 rd, u16 imm11_0, u8 rs1)
{
return rv_i_insn(imm11_0, rs1, 4, rd, 0x03);
}
static inline u32 rv_lhu(u8 rd, u16 imm11_0, u8 rs1)
{
return rv_i_insn(imm11_0, rs1, 5, rd, 0x03);
}
static inline u32 rv_sb(u8 rs1, u16 imm11_0, u8 rs2)
{
return rv_s_insn(imm11_0, rs2, rs1, 0, 0x23);
}
static inline u32 rv_sh(u8 rs1, u16 imm11_0, u8 rs2)
{
return rv_s_insn(imm11_0, rs2, rs1, 1, 0x23);
}
static inline u32 rv_sw(u8 rs1, u16 imm11_0, u8 rs2)
{
return rv_s_insn(imm11_0, rs2, rs1, 2, 0x23);
}
static inline u32 rv_amoadd_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
{
return rv_amo_insn(0, aq, rl, rs2, rs1, 2, rd, 0x2f);
}
static inline u32 rv_addiw(u8 rd, u8 rs1, u16 imm11_0)
{
return rv_i_insn(imm11_0, rs1, 0, rd, 0x1b);
}
static inline u32 rv_slliw(u8 rd, u8 rs1, u16 imm11_0)
{
return rv_i_insn(imm11_0, rs1, 1, rd, 0x1b);
}
static inline u32 rv_srliw(u8 rd, u8 rs1, u16 imm11_0)
{
return rv_i_insn(imm11_0, rs1, 5, rd, 0x1b);
}
static inline u32 rv_sraiw(u8 rd, u8 rs1, u16 imm11_0)
{
return rv_i_insn(0x400 | imm11_0, rs1, 5, rd, 0x1b);
}
static inline u32 rv_addw(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(0, rs2, rs1, 0, rd, 0x3b);
}
static inline u32 rv_subw(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(0x20, rs2, rs1, 0, rd, 0x3b);
}
static inline u32 rv_sllw(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(0, rs2, rs1, 1, rd, 0x3b);
}
static inline u32 rv_srlw(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(0, rs2, rs1, 5, rd, 0x3b);
}
static inline u32 rv_sraw(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(0x20, rs2, rs1, 5, rd, 0x3b);
}
static inline u32 rv_mulw(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(1, rs2, rs1, 0, rd, 0x3b);
}
static inline u32 rv_divuw(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(1, rs2, rs1, 5, rd, 0x3b);
}
static inline u32 rv_remuw(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(1, rs2, rs1, 7, rd, 0x3b);
}
static inline u32 rv_ld(u8 rd, u16 imm11_0, u8 rs1)
{
return rv_i_insn(imm11_0, rs1, 3, rd, 0x03);
}
static inline u32 rv_lwu(u8 rd, u16 imm11_0, u8 rs1)
{
return rv_i_insn(imm11_0, rs1, 6, rd, 0x03);
}
static inline u32 rv_sd(u8 rs1, u16 imm11_0, u8 rs2)
{
return rv_s_insn(imm11_0, rs2, rs1, 3, 0x23);
}
static inline u32 rv_amoadd_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
{
return rv_amo_insn(0, aq, rl, rs2, rs1, 3, rd, 0x2f);
}
void bpf_jit_build_prologue(struct rv_jit_context *ctx);
void bpf_jit_build_epilogue(struct rv_jit_context *ctx);
int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
bool extra_pass);
#endif /* _BPF_JIT_H */

605
arch/riscv/net/bpf_jit_comp.c → arch/riscv/net/bpf_jit_comp64.c
View File

@ -7,42 +7,7 @@
#include <linux/bpf.h> #include <linux/bpf.h>
#include <linux/filter.h> #include <linux/filter.h>
#include <asm/cacheflush.h> #include "bpf_jit.h"
enum {
RV_REG_ZERO = 0, /* The constant value 0 */
RV_REG_RA = 1, /* Return address */
RV_REG_SP = 2, /* Stack pointer */
RV_REG_GP = 3, /* Global pointer */
RV_REG_TP = 4, /* Thread pointer */
RV_REG_T0 = 5, /* Temporaries */
RV_REG_T1 = 6,
RV_REG_T2 = 7,
RV_REG_FP = 8,
RV_REG_S1 = 9, /* Saved registers */
RV_REG_A0 = 10, /* Function argument/return values */
RV_REG_A1 = 11, /* Function arguments */
RV_REG_A2 = 12,
RV_REG_A3 = 13,
RV_REG_A4 = 14,
RV_REG_A5 = 15,
RV_REG_A6 = 16,
RV_REG_A7 = 17,
RV_REG_S2 = 18, /* Saved registers */
RV_REG_S3 = 19,
RV_REG_S4 = 20,
RV_REG_S5 = 21,
RV_REG_S6 = 22,
RV_REG_S7 = 23,
RV_REG_S8 = 24,
RV_REG_S9 = 25,
RV_REG_S10 = 26,
RV_REG_S11 = 27,
RV_REG_T3 = 28, /* Temporaries */
RV_REG_T4 = 29,
RV_REG_T5 = 30,
RV_REG_T6 = 31,
};
#define RV_REG_TCC RV_REG_A6 #define RV_REG_TCC RV_REG_A6
#define RV_REG_TCC_SAVED RV_REG_S6 /* Store A6 in S6 if program do calls */ #define RV_REG_TCC_SAVED RV_REG_S6 /* Store A6 in S6 if program do calls */
@ -73,22 +38,6 @@ enum {
RV_CTX_F_SEEN_S6 = RV_REG_S6, RV_CTX_F_SEEN_S6 = RV_REG_S6,
}; };
struct rv_jit_context {
struct bpf_prog *prog;
u32 *insns; /* RV insns */
int ninsns;
int epilogue_offset;
int *offset; /* BPF to RV */
unsigned long flags;
int stack_size;
};
struct rv_jit_data {
struct bpf_binary_header *header;
u8 *image;
struct rv_jit_context ctx;
};
static u8 bpf_to_rv_reg(int bpf_reg, struct rv_jit_context *ctx) static u8 bpf_to_rv_reg(int bpf_reg, struct rv_jit_context *ctx)
{ {
u8 reg = regmap[bpf_reg]; u8 reg = regmap[bpf_reg];
@ -156,346 +105,11 @@ static u8 rv_tail_call_reg(struct rv_jit_context *ctx)
return RV_REG_A6; return RV_REG_A6;
} }
static void emit(const u32 insn, struct rv_jit_context *ctx)
{
if (ctx->insns)
ctx->insns[ctx->ninsns] = insn;
ctx->ninsns++;
}
static u32 rv_r_insn(u8 funct7, u8 rs2, u8 rs1, u8 funct3, u8 rd, u8 opcode)
{
return (funct7 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) |
(rd << 7) | opcode;
}
static u32 rv_i_insn(u16 imm11_0, u8 rs1, u8 funct3, u8 rd, u8 opcode)
{
return (imm11_0 << 20) | (rs1 << 15) | (funct3 << 12) | (rd << 7) |
opcode;
}
static u32 rv_s_insn(u16 imm11_0, u8 rs2, u8 rs1, u8 funct3, u8 opcode)
{
u8 imm11_5 = imm11_0 >> 5, imm4_0 = imm11_0 & 0x1f;
return (imm11_5 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) |
(imm4_0 << 7) | opcode;
}
static u32 rv_sb_insn(u16 imm12_1, u8 rs2, u8 rs1, u8 funct3, u8 opcode)
{
u8 imm12 = ((imm12_1 & 0x800) >> 5) | ((imm12_1 & 0x3f0) >> 4);
u8 imm4_1 = ((imm12_1 & 0xf) << 1) | ((imm12_1 & 0x400) >> 10);
return (imm12 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) |
(imm4_1 << 7) | opcode;
}
static u32 rv_u_insn(u32 imm31_12, u8 rd, u8 opcode)
{
return (imm31_12 << 12) | (rd << 7) | opcode;
}
static u32 rv_uj_insn(u32 imm20_1, u8 rd, u8 opcode)
{
u32 imm;
imm = (imm20_1 & 0x80000) | ((imm20_1 & 0x3ff) << 9) |
((imm20_1 & 0x400) >> 2) | ((imm20_1 & 0x7f800) >> 11);
return (imm << 12) | (rd << 7) | opcode;
}
static u32 rv_amo_insn(u8 funct5, u8 aq, u8 rl, u8 rs2, u8 rs1,
u8 funct3, u8 rd, u8 opcode)
{
u8 funct7 = (funct5 << 2) | (aq << 1) | rl;
return rv_r_insn(funct7, rs2, rs1, funct3, rd, opcode);
}
static u32 rv_addiw(u8 rd, u8 rs1, u16 imm11_0)
{
return rv_i_insn(imm11_0, rs1, 0, rd, 0x1b);
}
static u32 rv_addi(u8 rd, u8 rs1, u16 imm11_0)
{
return rv_i_insn(imm11_0, rs1, 0, rd, 0x13);
}
static u32 rv_addw(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(0, rs2, rs1, 0, rd, 0x3b);
}
static u32 rv_add(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(0, rs2, rs1, 0, rd, 0x33);
}
static u32 rv_subw(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(0x20, rs2, rs1, 0, rd, 0x3b);
}
static u32 rv_sub(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(0x20, rs2, rs1, 0, rd, 0x33);
}
static u32 rv_and(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(0, rs2, rs1, 7, rd, 0x33);
}
static u32 rv_or(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(0, rs2, rs1, 6, rd, 0x33);
}
static u32 rv_xor(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(0, rs2, rs1, 4, rd, 0x33);
}
static u32 rv_mulw(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(1, rs2, rs1, 0, rd, 0x3b);
}
static u32 rv_mul(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(1, rs2, rs1, 0, rd, 0x33);
}
static u32 rv_divuw(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(1, rs2, rs1, 5, rd, 0x3b);
}
static u32 rv_divu(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(1, rs2, rs1, 5, rd, 0x33);
}
static u32 rv_remuw(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(1, rs2, rs1, 7, rd, 0x3b);
}
static u32 rv_remu(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(1, rs2, rs1, 7, rd, 0x33);
}
static u32 rv_sllw(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(0, rs2, rs1, 1, rd, 0x3b);
}
static u32 rv_sll(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(0, rs2, rs1, 1, rd, 0x33);
}
static u32 rv_srlw(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(0, rs2, rs1, 5, rd, 0x3b);
}
static u32 rv_srl(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(0, rs2, rs1, 5, rd, 0x33);
}
static u32 rv_sraw(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(0x20, rs2, rs1, 5, rd, 0x3b);
}
static u32 rv_sra(u8 rd, u8 rs1, u8 rs2)
{
return rv_r_insn(0x20, rs2, rs1, 5, rd, 0x33);
}
static u32 rv_lui(u8 rd, u32 imm31_12)
{
return rv_u_insn(imm31_12, rd, 0x37);
}
static u32 rv_slli(u8 rd, u8 rs1, u16 imm11_0)
{
return rv_i_insn(imm11_0, rs1, 1, rd, 0x13);
}
static u32 rv_andi(u8 rd, u8 rs1, u16 imm11_0)
{
return rv_i_insn(imm11_0, rs1, 7, rd, 0x13);
}
static u32 rv_ori(u8 rd, u8 rs1, u16 imm11_0)
{
return rv_i_insn(imm11_0, rs1, 6, rd, 0x13);
}
static u32 rv_xori(u8 rd, u8 rs1, u16 imm11_0)
{
return rv_i_insn(imm11_0, rs1, 4, rd, 0x13);
}
static u32 rv_slliw(u8 rd, u8 rs1, u16 imm11_0)
{
return rv_i_insn(imm11_0, rs1, 1, rd, 0x1b);
}
static u32 rv_srliw(u8 rd, u8 rs1, u16 imm11_0)
{
return rv_i_insn(imm11_0, rs1, 5, rd, 0x1b);
}
static u32 rv_srli(u8 rd, u8 rs1, u16 imm11_0)
{
return rv_i_insn(imm11_0, rs1, 5, rd, 0x13);
}
static u32 rv_sraiw(u8 rd, u8 rs1, u16 imm11_0)
{
return rv_i_insn(0x400 | imm11_0, rs1, 5, rd, 0x1b);
}
static u32 rv_srai(u8 rd, u8 rs1, u16 imm11_0)
{
return rv_i_insn(0x400 | imm11_0, rs1, 5, rd, 0x13);
}
static u32 rv_jal(u8 rd, u32 imm20_1)
{
return rv_uj_insn(imm20_1, rd, 0x6f);
}
static u32 rv_jalr(u8 rd, u8 rs1, u16 imm11_0)
{
return rv_i_insn(imm11_0, rs1, 0, rd, 0x67);
}
static u32 rv_beq(u8 rs1, u8 rs2, u16 imm12_1)
{
return rv_sb_insn(imm12_1, rs2, rs1, 0, 0x63);
}
static u32 rv_bltu(u8 rs1, u8 rs2, u16 imm12_1)
{
return rv_sb_insn(imm12_1, rs2, rs1, 6, 0x63);
}
static u32 rv_bgeu(u8 rs1, u8 rs2, u16 imm12_1)
{
return rv_sb_insn(imm12_1, rs2, rs1, 7, 0x63);
}
static u32 rv_bne(u8 rs1, u8 rs2, u16 imm12_1)
{
return rv_sb_insn(imm12_1, rs2, rs1, 1, 0x63);
}
static u32 rv_blt(u8 rs1, u8 rs2, u16 imm12_1)
{
return rv_sb_insn(imm12_1, rs2, rs1, 4, 0x63);
}
static u32 rv_bge(u8 rs1, u8 rs2, u16 imm12_1)
{
return rv_sb_insn(imm12_1, rs2, rs1, 5, 0x63);
}
static u32 rv_sb(u8 rs1, u16 imm11_0, u8 rs2)
{
return rv_s_insn(imm11_0, rs2, rs1, 0, 0x23);
}
static u32 rv_sh(u8 rs1, u16 imm11_0, u8 rs2)
{
return rv_s_insn(imm11_0, rs2, rs1, 1, 0x23);
}
static u32 rv_sw(u8 rs1, u16 imm11_0, u8 rs2)
{
return rv_s_insn(imm11_0, rs2, rs1, 2, 0x23);
}
static u32 rv_sd(u8 rs1, u16 imm11_0, u8 rs2)
{
return rv_s_insn(imm11_0, rs2, rs1, 3, 0x23);
}
static u32 rv_lbu(u8 rd, u16 imm11_0, u8 rs1)
{
return rv_i_insn(imm11_0, rs1, 4, rd, 0x03);
}
static u32 rv_lhu(u8 rd, u16 imm11_0, u8 rs1)
{
return rv_i_insn(imm11_0, rs1, 5, rd, 0x03);
}
static u32 rv_lwu(u8 rd, u16 imm11_0, u8 rs1)
{
return rv_i_insn(imm11_0, rs1, 6, rd, 0x03);
}
static u32 rv_ld(u8 rd, u16 imm11_0, u8 rs1)
{
return rv_i_insn(imm11_0, rs1, 3, rd, 0x03);
}
static u32 rv_amoadd_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
{
return rv_amo_insn(0, aq, rl, rs2, rs1, 2, rd, 0x2f);
}
static u32 rv_amoadd_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
{
return rv_amo_insn(0, aq, rl, rs2, rs1, 3, rd, 0x2f);
}
static u32 rv_auipc(u8 rd, u32 imm31_12)
{
return rv_u_insn(imm31_12, rd, 0x17);
}
static bool is_12b_int(s64 val)
{
return -(1 << 11) <= val && val < (1 << 11);
}
static bool is_13b_int(s64 val)
{
return -(1 << 12) <= val && val < (1 << 12);
}
static bool is_21b_int(s64 val)
{
return -(1L << 20) <= val && val < (1L << 20);
}
static bool is_32b_int(s64 val) static bool is_32b_int(s64 val)
{ {
return -(1L << 31) <= val && val < (1L << 31); return -(1L << 31) <= val && val < (1L << 31);
} }
static int is_12b_check(int off, int insn)
{
if (!is_12b_int(off)) {
pr_err("bpf-jit: insn=%d 12b < offset=%d not supported yet!\n",
insn, (int)off);
return -1;
}
return 0;
}
static void emit_imm(u8 rd, s64 val, struct rv_jit_context *ctx) static void emit_imm(u8 rd, s64 val, struct rv_jit_context *ctx)
{ {
/* Note that the immediate from the add is sign-extended, /* Note that the immediate from the add is sign-extended,
@ -535,23 +149,6 @@ static void emit_imm(u8 rd, s64 val, struct rv_jit_context *ctx)
emit(rv_addi(rd, rd, lower), ctx); emit(rv_addi(rd, rd, lower), ctx);
} }
static int rv_offset(int insn, int off, struct rv_jit_context *ctx)
{
int from, to;
off++; /* BPF branch is from PC+1, RV is from PC */
from = (insn > 0) ? ctx->offset[insn - 1] : 0;
to = (insn + off > 0) ? ctx->offset[insn + off - 1] : 0;
return (to - from) << 2;
}
static int epilogue_offset(struct rv_jit_context *ctx)
{
int to = ctx->epilogue_offset, from = ctx->ninsns;
return (to - from) << 2;
}
static void __build_epilogue(bool is_tail_call, struct rv_jit_context *ctx) static void __build_epilogue(bool is_tail_call, struct rv_jit_context *ctx)
{ {
int stack_adjust = ctx->stack_size, store_offset = stack_adjust - 8; int stack_adjust = ctx->stack_size, store_offset = stack_adjust - 8;
@ -596,34 +193,6 @@ static void __build_epilogue(bool is_tail_call, struct rv_jit_context *ctx)
ctx); ctx);
} }
/* return -1 or inverted cond */
static int invert_bpf_cond(u8 cond)
{
switch (cond) {
case BPF_JEQ:
return BPF_JNE;
case BPF_JGT:
return BPF_JLE;
case BPF_JLT:
return BPF_JGE;
case BPF_JGE:
return BPF_JLT;
case BPF_JLE:
return BPF_JGT;
case BPF_JNE:
return BPF_JEQ;
case BPF_JSGT:
return BPF_JSLE;
case BPF_JSLT:
return BPF_JSGE;
case BPF_JSGE:
return BPF_JSLT;
case BPF_JSLE:
return BPF_JSGT;
}
return -1;
}
static void emit_bcc(u8 cond, u8 rd, u8 rs, int rvoff, static void emit_bcc(u8 cond, u8 rd, u8 rs, int rvoff,
struct rv_jit_context *ctx) struct rv_jit_context *ctx)
{ {
@ -855,8 +424,8 @@ static int emit_call(bool fixed, u64 addr, struct rv_jit_context *ctx)
return 0; return 0;
} }
static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
bool extra_pass) bool extra_pass)
{ {
bool is64 = BPF_CLASS(insn->code) == BPF_ALU64 || bool is64 = BPF_CLASS(insn->code) == BPF_ALU64 ||
BPF_CLASS(insn->code) == BPF_JMP; BPF_CLASS(insn->code) == BPF_JMP;
@ -1434,7 +1003,7 @@ out_be:
return 0; return 0;
} }
static void build_prologue(struct rv_jit_context *ctx) void bpf_jit_build_prologue(struct rv_jit_context *ctx)
{ {
int stack_adjust = 0, store_offset, bpf_stack_adjust; int stack_adjust = 0, store_offset, bpf_stack_adjust;
@ -1515,175 +1084,11 @@ static void build_prologue(struct rv_jit_context *ctx)
ctx->stack_size = stack_adjust; ctx->stack_size = stack_adjust;
} }
static void build_epilogue(struct rv_jit_context *ctx) void bpf_jit_build_epilogue(struct rv_jit_context *ctx)
{ {
__build_epilogue(false, ctx); __build_epilogue(false, ctx);
} }
static int build_body(struct rv_jit_context *ctx, bool extra_pass, int *offset)
{
const struct bpf_prog *prog = ctx->prog;
int i;
for (i = 0; i < prog->len; i++) {
const struct bpf_insn *insn = &prog->insnsi[i];
int ret;
ret = emit_insn(insn, ctx, extra_pass);
if (ret > 0) {
i++;
if (offset)
offset[i] = ctx->ninsns;
continue;
}
if (offset)
offset[i] = ctx->ninsns;
if (ret)
return ret;
}
return 0;
}
static void bpf_fill_ill_insns(void *area, unsigned int size)
{
memset(area, 0, size);
}
static void bpf_flush_icache(void *start, void *end)
{
flush_icache_range((unsigned long)start, (unsigned long)end);
}
bool bpf_jit_needs_zext(void)
{
return true;
}
struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
{
bool tmp_blinded = false, extra_pass = false;
struct bpf_prog *tmp, *orig_prog = prog;
int pass = 0, prev_ninsns = 0, i;
struct rv_jit_data *jit_data;
unsigned int image_size = 0;
struct rv_jit_context *ctx;
if (!prog->jit_requested)
return orig_prog;
tmp = bpf_jit_blind_constants(prog);
if (IS_ERR(tmp))
return orig_prog;
if (tmp != prog) {
tmp_blinded = true;
prog = tmp;
}
jit_data = prog->aux->jit_data;
if (!jit_data) {
jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL);
if (!jit_data) {
prog = orig_prog;
goto out;
}
prog->aux->jit_data = jit_data;
}
ctx = &jit_data->ctx;
if (ctx->offset) {
extra_pass = true;
image_size = sizeof(u32) * ctx->ninsns;
goto skip_init_ctx;
}
ctx->prog = prog;
ctx->offset = kcalloc(prog->len, sizeof(int), GFP_KERNEL);
if (!ctx->offset) {
prog = orig_prog;
goto out_offset;
}
for (i = 0; i < prog->len; i++) {
prev_ninsns += 32;
ctx->offset[i] = prev_ninsns;
}
for (i = 0; i < 16; i++) {
pass++;
ctx->ninsns = 0;
if (build_body(ctx, extra_pass, ctx->offset)) {
prog = orig_prog;
goto out_offset;
}
build_prologue(ctx);
ctx->epilogue_offset = ctx->ninsns;
build_epilogue(ctx);
if (ctx->ninsns == prev_ninsns) {
if (jit_data->header)
break;
image_size = sizeof(u32) * ctx->ninsns;
jit_data->header =
bpf_jit_binary_alloc(image_size,
&jit_data->image,
sizeof(u32),
bpf_fill_ill_insns);
if (!jit_data->header) {
prog = orig_prog;
goto out_offset;
}
ctx->insns = (u32 *)jit_data->image;
/* Now, when the image is allocated, the image
* can potentially shrink more (auipc/jalr ->
* jal).
*/
}
prev_ninsns = ctx->ninsns;
}
if (i == 16) {
pr_err("bpf-jit: image did not converge in <%d passes!\n", i);
bpf_jit_binary_free(jit_data->header);
prog = orig_prog;
goto out_offset;
}
skip_init_ctx:
pass++;
ctx->ninsns = 0;
build_prologue(ctx);
if (build_body(ctx, extra_pass, NULL)) {
bpf_jit_binary_free(jit_data->header);
prog = orig_prog;
goto out_offset;
}
build_epilogue(ctx);
if (bpf_jit_enable > 1)
bpf_jit_dump(prog->len, image_size, pass, ctx->insns);
prog->bpf_func = (void *)ctx->insns;
prog->jited = 1;
prog->jited_len = image_size;
bpf_flush_icache(jit_data->header, ctx->insns + ctx->ninsns);
if (!prog->is_func || extra_pass) {
out_offset:
kfree(ctx->offset);
kfree(jit_data);
prog->aux->jit_data = NULL;
}
out:
if (tmp_blinded)
bpf_jit_prog_release_other(prog, prog == orig_prog ?
tmp : orig_prog);
return prog;
}
void *bpf_jit_alloc_exec(unsigned long size) void *bpf_jit_alloc_exec(unsigned long size)
{ {
return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START, return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START,

166
arch/riscv/net/bpf_jit_core.c Normal file
View File

@ -0,0 +1,166 @@
// SPDX-License-Identifier: GPL-2.0
/*
* Common functionality for RV32 and RV64 BPF JIT compilers
*
* Copyright (c) 2019 Björn Töpel <bjorn.topel@gmail.com>
*
*/
#include <linux/bpf.h>
#include <linux/filter.h>
#include "bpf_jit.h"
/* Number of iterations to try until offsets converge. */
#define NR_JIT_ITERATIONS 16
static int build_body(struct rv_jit_context *ctx, bool extra_pass, int *offset)
{
const struct bpf_prog *prog = ctx->prog;
int i;
for (i = 0; i < prog->len; i++) {
const struct bpf_insn *insn = &prog->insnsi[i];
int ret;
ret = bpf_jit_emit_insn(insn, ctx, extra_pass);
/* BPF_LD | BPF_IMM | BPF_DW: skip the next instruction. */
if (ret > 0)
i++;
if (offset)
offset[i] = ctx->ninsns;
if (ret < 0)
return ret;
}
return 0;
}
bool bpf_jit_needs_zext(void)
{
return true;
}
struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
{
bool tmp_blinded = false, extra_pass = false;
struct bpf_prog *tmp, *orig_prog = prog;
int pass = 0, prev_ninsns = 0, i;
struct rv_jit_data *jit_data;
struct rv_jit_context *ctx;
unsigned int image_size = 0;
if (!prog->jit_requested)
return orig_prog;
tmp = bpf_jit_blind_constants(prog);
if (IS_ERR(tmp))
return orig_prog;
if (tmp != prog) {
tmp_blinded = true;
prog = tmp;
}
jit_data = prog->aux->jit_data;
if (!jit_data) {
jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL);
if (!jit_data) {
prog = orig_prog;
goto out;
}
prog->aux->jit_data = jit_data;
}
ctx = &jit_data->ctx;
if (ctx->offset) {
extra_pass = true;
image_size = sizeof(u32) * ctx->ninsns;
goto skip_init_ctx;
}
ctx->prog = prog;
ctx->offset = kcalloc(prog->len, sizeof(int), GFP_KERNEL);
if (!ctx->offset) {
prog = orig_prog;
goto out_offset;
}
for (i = 0; i < prog->len; i++) {
prev_ninsns += 32;
ctx->offset[i] = prev_ninsns;
}
for (i = 0; i < NR_JIT_ITERATIONS; i++) {
pass++;
ctx->ninsns = 0;
if (build_body(ctx, extra_pass, ctx->offset)) {
prog = orig_prog;
goto out_offset;
}
bpf_jit_build_prologue(ctx);
ctx->epilogue_offset = ctx->ninsns;
bpf_jit_build_epilogue(ctx);
if (ctx->ninsns == prev_ninsns) {
if (jit_data->header)
break;
image_size = sizeof(u32) * ctx->ninsns;
jit_data->header =
bpf_jit_binary_alloc(image_size,
&jit_data->image,
sizeof(u32),
bpf_fill_ill_insns);
if (!jit_data->header) {
prog = orig_prog;
goto out_offset;
}
ctx->insns = (u32 *)jit_data->image;
/*
* Now, when the image is allocated, the image can
* potentially shrink more (auipc/jalr -> jal).
*/
}
prev_ninsns = ctx->ninsns;
}
if (i == NR_JIT_ITERATIONS) {
pr_err("bpf-jit: image did not converge in <%d passes!\n", i);
bpf_jit_binary_free(jit_data->header);
prog = orig_prog;
goto out_offset;
}
skip_init_ctx:
pass++;
ctx->ninsns = 0;
bpf_jit_build_prologue(ctx);
if (build_body(ctx, extra_pass, NULL)) {
bpf_jit_binary_free(jit_data->header);
prog = orig_prog;
goto out_offset;
}
bpf_jit_build_epilogue(ctx);
if (bpf_jit_enable > 1)
bpf_jit_dump(prog->len, image_size, pass, ctx->insns);
prog->bpf_func = (void *)ctx->insns;
prog->jited = 1;
prog->jited_len = image_size;
bpf_flush_icache(jit_data->header, ctx->insns + ctx->ninsns);
if (!prog->is_func || extra_pass) {
out_offset:
kfree(ctx->offset);
kfree(jit_data);
prog->aux->jit_data = NULL;
}
out:
if (tmp_blinded)
bpf_jit_prog_release_other(prog, prog == orig_prog ?
tmp : orig_prog);
return prog;
}