linux-stable/arch/powerpc/net/bpf_jit.h
Christophe Leroy ee7c3ec3b4 powerpc/ebpf32: Use standard function call for functions within 32M distance
If the target of a function call is within 32 Mbytes distance, use a
standard function call with 'bl' instead of the 'lis/ori/mtlr/blrl'
sequence.

In the first pass, no memory has been allocated yet and the code
position is not known yet (image pointer is NULL). This pass is there
to calculate the amount of memory to allocate for the EBPF code, so
assume the 4 instructions sequence is required, so that enough memory
is allocated.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/74944a1e3e5cfecc141e440a6ccd37920e186b70.1618227846.git.christophe.leroy@csgroup.eu
2021-04-21 22:52:33 +10:00

177 lines
5.6 KiB
C

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* bpf_jit.h: BPF JIT compiler for PPC
*
* Copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation
* 2016 Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
*/
#ifndef _BPF_JIT_H
#define _BPF_JIT_H
#ifndef __ASSEMBLY__
#include <asm/types.h>
#include <asm/ppc-opcode.h>
#ifdef PPC64_ELF_ABI_v1
#define FUNCTION_DESCR_SIZE 24
#else
#define FUNCTION_DESCR_SIZE 0
#endif
#define PLANT_INSTR(d, idx, instr) \
do { if (d) { (d)[idx] = instr; } idx++; } while (0)
#define EMIT(instr) PLANT_INSTR(image, ctx->idx, instr)
/* Long jump; (unconditional 'branch') */
#define PPC_JMP(dest) EMIT(PPC_INST_BRANCH | \
(((dest) - (ctx->idx * 4)) & 0x03fffffc))
/* blr; (unconditional 'branch' with link) to absolute address */
#define PPC_BL_ABS(dest) EMIT(PPC_INST_BL | \
(((dest) - (unsigned long)(image + ctx->idx)) & 0x03fffffc))
/* "cond" here covers BO:BI fields. */
#define PPC_BCC_SHORT(cond, dest) EMIT(PPC_INST_BRANCH_COND | \
(((cond) & 0x3ff) << 16) | \
(((dest) - (ctx->idx * 4)) & \
0xfffc))
/* Sign-extended 32-bit immediate load */
#define PPC_LI32(d, i) do { \
if ((int)(uintptr_t)(i) >= -32768 && \
(int)(uintptr_t)(i) < 32768) \
EMIT(PPC_RAW_LI(d, i)); \
else { \
EMIT(PPC_RAW_LIS(d, IMM_H(i))); \
if (IMM_L(i)) \
EMIT(PPC_RAW_ORI(d, d, IMM_L(i))); \
} } while(0)
#ifdef CONFIG_PPC32
#define PPC_EX32(r, i) EMIT(PPC_RAW_LI((r), (i) < 0 ? -1 : 0))
#endif
#define PPC_LI64(d, i) do { \
if ((long)(i) >= -2147483648 && \
(long)(i) < 2147483648) \
PPC_LI32(d, i); \
else { \
if (!((uintptr_t)(i) & 0xffff800000000000ULL)) \
EMIT(PPC_RAW_LI(d, ((uintptr_t)(i) >> 32) & \
0xffff)); \
else { \
EMIT(PPC_RAW_LIS(d, ((uintptr_t)(i) >> 48))); \
if ((uintptr_t)(i) & 0x0000ffff00000000ULL) \
EMIT(PPC_RAW_ORI(d, d, \
((uintptr_t)(i) >> 32) & 0xffff)); \
} \
EMIT(PPC_RAW_SLDI(d, d, 32)); \
if ((uintptr_t)(i) & 0x00000000ffff0000ULL) \
EMIT(PPC_RAW_ORIS(d, d, \
((uintptr_t)(i) >> 16) & 0xffff)); \
if ((uintptr_t)(i) & 0x000000000000ffffULL) \
EMIT(PPC_RAW_ORI(d, d, (uintptr_t)(i) & \
0xffff)); \
} } while (0)
#ifdef CONFIG_PPC64
#define PPC_FUNC_ADDR(d,i) do { PPC_LI64(d, i); } while(0)
#else
#define PPC_FUNC_ADDR(d,i) do { PPC_LI32(d, i); } while(0)
#endif
static inline bool is_nearbranch(int offset)
{
return (offset < 32768) && (offset >= -32768);
}
/*
* The fly in the ointment of code size changing from pass to pass is
* avoided by padding the short branch case with a NOP. If code size differs
* with different branch reaches we will have the issue of code moving from
* one pass to the next and will need a few passes to converge on a stable
* state.
*/
#define PPC_BCC(cond, dest) do { \
if (is_nearbranch((dest) - (ctx->idx * 4))) { \
PPC_BCC_SHORT(cond, dest); \
EMIT(PPC_RAW_NOP()); \
} else { \
/* Flip the 'T or F' bit to invert comparison */ \
PPC_BCC_SHORT(cond ^ COND_CMP_TRUE, (ctx->idx+2)*4); \
PPC_JMP(dest); \
} } while(0)
/* To create a branch condition, select a bit of cr0... */
#define CR0_LT 0
#define CR0_GT 1
#define CR0_EQ 2
/* ...and modify BO[3] */
#define COND_CMP_TRUE 0x100
#define COND_CMP_FALSE 0x000
/* Together, they make all required comparisons: */
#define COND_GT (CR0_GT | COND_CMP_TRUE)
#define COND_GE (CR0_LT | COND_CMP_FALSE)
#define COND_EQ (CR0_EQ | COND_CMP_TRUE)
#define COND_NE (CR0_EQ | COND_CMP_FALSE)
#define COND_LT (CR0_LT | COND_CMP_TRUE)
#define COND_LE (CR0_GT | COND_CMP_FALSE)
#define SEEN_FUNC 0x20000000 /* might call external helpers */
#define SEEN_STACK 0x40000000 /* uses BPF stack */
#define SEEN_TAILCALL 0x80000000 /* uses tail calls */
#define SEEN_VREG_MASK 0x1ff80000 /* Volatile registers r3-r12 */
#define SEEN_NVREG_MASK 0x0003ffff /* Non volatile registers r14-r31 */
#ifdef CONFIG_PPC64
extern const int b2p[MAX_BPF_JIT_REG + 2];
#else
extern const int b2p[MAX_BPF_JIT_REG + 1];
#endif
struct codegen_context {
/*
* This is used to track register usage as well
* as calls to external helpers.
* - register usage is tracked with corresponding
* bits (r3-r31)
* - rest of the bits can be used to track other
* things -- for now, we use bits 0 to 2
* encoded in SEEN_* macros above
*/
unsigned int seen;
unsigned int idx;
unsigned int stack_size;
int b2p[ARRAY_SIZE(b2p)];
};
static inline void bpf_flush_icache(void *start, void *end)
{
smp_wmb(); /* smp write barrier */
flush_icache_range((unsigned long)start, (unsigned long)end);
}
static inline bool bpf_is_seen_register(struct codegen_context *ctx, int i)
{
return ctx->seen & (1 << (31 - i));
}
static inline void bpf_set_seen_register(struct codegen_context *ctx, int i)
{
ctx->seen |= 1 << (31 - i);
}
static inline void bpf_clear_seen_register(struct codegen_context *ctx, int i)
{
ctx->seen &= ~(1 << (31 - i));
}
void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 func);
int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *ctx,
u32 *addrs, bool extra_pass);
void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx);
void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx);
void bpf_jit_realloc_regs(struct codegen_context *ctx);
#endif
#endif