2016-06-23 00:25:07 +08:00
|
|
|
/*
|
|
|
|
|
* bpf_jit_comp64.c: eBPF JIT compiler
|
|
|
|
|
*
|
|
|
|
|
* Copyright 2016 Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
|
|
|
|
|
* IBM Corporation
|
|
|
|
|
*
|
|
|
|
|
* Based on the powerpc classic BPF JIT compiler by Matt Evans
|
|
|
|
|
*
|
|
|
|
|
* 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/moduleloader.h>
|
|
|
|
|
#include <asm/cacheflush.h>
|
2018-07-06 00:24:57 +08:00
|
|
|
#include <asm/asm-compat.h>
|
2016-06-23 00:25:07 +08:00
|
|
|
#include <linux/netdevice.h>
|
|
|
|
|
#include <linux/filter.h>
|
|
|
|
|
#include <linux/if_vlan.h>
|
|
|
|
|
#include <asm/kprobes.h>
|
2016-09-24 04:35:01 +08:00
|
|
|
#include <linux/bpf.h>
|
2016-06-23 00:25:07 +08:00
|
|
|
|
|
|
|
|
#include "bpf_jit64.h"
|
|
|
|
|
|
|
|
|
|
static void bpf_jit_fill_ill_insns(void *area, unsigned int size)
|
|
|
|
|
{
|
2017-03-28 03:37:41 +08:00
|
|
|
memset32(area, BREAKPOINT_INSTRUCTION, size/4);
|
2016-06-23 00:25:07 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void bpf_flush_icache(void *start, void *end)
|
|
|
|
|
{
|
|
|
|
|
smp_wmb();
|
|
|
|
|
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 - b2p[i])));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void bpf_set_seen_register(struct codegen_context *ctx, int i)
|
|
|
|
|
{
|
|
|
|
|
ctx->seen |= (1 << (31 - b2p[i]));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline bool bpf_has_stack_frame(struct codegen_context *ctx)
|
|
|
|
|
{
|
|
|
|
|
/*
|
|
|
|
|
* We only need a stack frame if:
|
|
|
|
|
* - we call other functions (kernel helpers), or
|
|
|
|
|
* - the bpf program uses its stack area
|
|
|
|
|
* The latter condition is deduced from the usage of BPF_REG_FP
|
|
|
|
|
*/
|
|
|
|
|
return ctx->seen & SEEN_FUNC || bpf_is_seen_register(ctx, BPF_REG_FP);
|
|
|
|
|
}
|
|
|
|
|
|
2016-09-24 04:35:00 +08:00
|
|
|
/*
|
|
|
|
|
* When not setting up our own stackframe, the redzone usage is:
|
|
|
|
|
*
|
|
|
|
|
* [ prev sp ] <-------------
|
|
|
|
|
* [ ... ] |
|
|
|
|
|
* sp (r1) ---> [ stack pointer ] --------------
|
2018-05-04 07:08:21 +08:00
|
|
|
* [ nv gpr save area ] 6*8
|
2016-09-24 04:35:00 +08:00
|
|
|
* [ tail_call_cnt ] 8
|
|
|
|
|
* [ local_tmp_var ] 8
|
|
|
|
|
* [ unused red zone ] 208 bytes protected
|
|
|
|
|
*/
|
|
|
|
|
static int bpf_jit_stack_local(struct codegen_context *ctx)
|
|
|
|
|
{
|
|
|
|
|
if (bpf_has_stack_frame(ctx))
|
2017-09-02 02:53:01 +08:00
|
|
|
return STACK_FRAME_MIN_SIZE + ctx->stack_size;
|
2016-09-24 04:35:00 +08:00
|
|
|
else
|
|
|
|
|
return -(BPF_PPC_STACK_SAVE + 16);
|
|
|
|
|
}
|
|
|
|
|
|
2016-09-24 04:35:01 +08:00
|
|
|
static int bpf_jit_stack_tailcallcnt(struct codegen_context *ctx)
|
|
|
|
|
{
|
|
|
|
|
return bpf_jit_stack_local(ctx) + 8;
|
|
|
|
|
}
|
|
|
|
|
|
2016-09-24 04:35:00 +08:00
|
|
|
static int bpf_jit_stack_offsetof(struct codegen_context *ctx, int reg)
|
|
|
|
|
{
|
|
|
|
|
if (reg >= BPF_PPC_NVR_MIN && reg < 32)
|
2017-09-02 02:53:01 +08:00
|
|
|
return (bpf_has_stack_frame(ctx) ?
|
|
|
|
|
(BPF_PPC_STACKFRAME + ctx->stack_size) : 0)
|
|
|
|
|
- (8 * (32 - reg));
|
2016-09-24 04:35:00 +08:00
|
|
|
|
|
|
|
|
pr_err("BPF JIT is asking about unknown registers");
|
|
|
|
|
BUG();
|
|
|
|
|
}
|
|
|
|
|
|
2016-09-24 04:35:01 +08:00
|
|
|
static void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
|
2016-06-23 00:25:07 +08:00
|
|
|
{
|
2016-09-24 04:35:01 +08:00
|
|
|
int i;
|
|
|
|
|
|
2016-06-23 00:25:07 +08:00
|
|
|
/*
|
2016-09-24 04:35:01 +08:00
|
|
|
* Initialize tail_call_cnt if we do tail calls.
|
|
|
|
|
* Otherwise, put in NOPs so that it can be skipped when we are
|
|
|
|
|
* invoked through a tail call.
|
2016-06-23 00:25:07 +08:00
|
|
|
*/
|
2016-09-24 04:35:01 +08:00
|
|
|
if (ctx->seen & SEEN_TAILCALL) {
|
|
|
|
|
PPC_LI(b2p[TMP_REG_1], 0);
|
|
|
|
|
/* this goes in the redzone */
|
|
|
|
|
PPC_BPF_STL(b2p[TMP_REG_1], 1, -(BPF_PPC_STACK_SAVE + 8));
|
|
|
|
|
} else {
|
|
|
|
|
PPC_NOP();
|
|
|
|
|
PPC_NOP();
|
|
|
|
|
}
|
2016-06-23 00:25:07 +08:00
|
|
|
|
2016-09-24 04:35:01 +08:00
|
|
|
#define BPF_TAILCALL_PROLOGUE_SIZE 8
|
2016-06-23 00:25:07 +08:00
|
|
|
|
2016-09-24 04:35:00 +08:00
|
|
|
if (bpf_has_stack_frame(ctx)) {
|
2016-06-23 00:25:07 +08:00
|
|
|
/*
|
|
|
|
|
* We need a stack frame, but we don't necessarily need to
|
|
|
|
|
* save/restore LR unless we call other functions
|
|
|
|
|
*/
|
|
|
|
|
if (ctx->seen & SEEN_FUNC) {
|
|
|
|
|
EMIT(PPC_INST_MFLR | __PPC_RT(R0));
|
|
|
|
|
PPC_BPF_STL(0, 1, PPC_LR_STKOFF);
|
|
|
|
|
}
|
|
|
|
|
|
2017-09-02 02:53:01 +08:00
|
|
|
PPC_BPF_STLU(1, 1, -(BPF_PPC_STACKFRAME + ctx->stack_size));
|
2016-06-23 00:25:07 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Back up non-volatile regs -- BPF registers 6-10
|
|
|
|
|
* If we haven't created our own stack frame, we save these
|
|
|
|
|
* in the protected zone below the previous stack frame
|
|
|
|
|
*/
|
|
|
|
|
for (i = BPF_REG_6; i <= BPF_REG_10; i++)
|
|
|
|
|
if (bpf_is_seen_register(ctx, i))
|
2016-09-24 04:35:00 +08:00
|
|
|
PPC_BPF_STL(b2p[i], 1, bpf_jit_stack_offsetof(ctx, b2p[i]));
|
2016-06-23 00:25:07 +08:00
|
|
|
|
|
|
|
|
/* Setup frame pointer to point to the bpf stack area */
|
|
|
|
|
if (bpf_is_seen_register(ctx, BPF_REG_FP))
|
|
|
|
|
PPC_ADDI(b2p[BPF_REG_FP], 1,
|
2017-09-02 02:53:01 +08:00
|
|
|
STACK_FRAME_MIN_SIZE + ctx->stack_size);
|
2016-06-23 00:25:07 +08:00
|
|
|
}
|
|
|
|
|
|
2016-09-24 04:35:01 +08:00
|
|
|
static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx)
|
2016-06-23 00:25:07 +08:00
|
|
|
{
|
|
|
|
|
int i;
|
|
|
|
|
|
|
|
|
|
/* Restore NVRs */
|
|
|
|
|
for (i = BPF_REG_6; i <= BPF_REG_10; i++)
|
|
|
|
|
if (bpf_is_seen_register(ctx, i))
|
2016-09-24 04:35:00 +08:00
|
|
|
PPC_BPF_LL(b2p[i], 1, bpf_jit_stack_offsetof(ctx, b2p[i]));
|
2016-06-23 00:25:07 +08:00
|
|
|
|
|
|
|
|
/* Tear down our stack frame */
|
2016-09-24 04:35:00 +08:00
|
|
|
if (bpf_has_stack_frame(ctx)) {
|
2017-09-02 02:53:01 +08:00
|
|
|
PPC_ADDI(1, 1, BPF_PPC_STACKFRAME + ctx->stack_size);
|
2016-06-23 00:25:07 +08:00
|
|
|
if (ctx->seen & SEEN_FUNC) {
|
|
|
|
|
PPC_BPF_LL(0, 1, PPC_LR_STKOFF);
|
|
|
|
|
PPC_MTLR(0);
|
|
|
|
|
}
|
|
|
|
|
}
|
2016-09-24 04:35:01 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
|
|
|
|
|
{
|
|
|
|
|
bpf_jit_emit_common_epilogue(image, ctx);
|
|
|
|
|
|
|
|
|
|
/* Move result to r3 */
|
|
|
|
|
PPC_MR(3, b2p[BPF_REG_0]);
|
2016-06-23 00:25:07 +08:00
|
|
|
|
|
|
|
|
PPC_BLR();
|
|
|
|
|
}
|
|
|
|
|
|
2016-09-24 04:35:01 +08:00
|
|
|
static void bpf_jit_emit_func_call(u32 *image, struct codegen_context *ctx, u64 func)
|
|
|
|
|
{
|
2018-05-24 14:56:46 +08:00
|
|
|
unsigned int i, ctx_idx = ctx->idx;
|
|
|
|
|
|
|
|
|
|
/* Load function address into r12 */
|
|
|
|
|
PPC_LI64(12, func);
|
|
|
|
|
|
|
|
|
|
/* For bpf-to-bpf function calls, the callee's address is unknown
|
|
|
|
|
* until the last extra pass. As seen above, we use PPC_LI64() to
|
|
|
|
|
* load the callee's address, but this may optimize the number of
|
|
|
|
|
* instructions required based on the nature of the address.
|
|
|
|
|
*
|
|
|
|
|
* Since we don't want the number of instructions emitted to change,
|
|
|
|
|
* we pad the optimized PPC_LI64() call with NOPs to guarantee that
|
|
|
|
|
* we always have a five-instruction sequence, which is the maximum
|
|
|
|
|
* that PPC_LI64() can emit.
|
|
|
|
|
*/
|
|
|
|
|
for (i = ctx->idx - ctx_idx; i < 5; i++)
|
|
|
|
|
PPC_NOP();
|
|
|
|
|
|
2016-09-24 04:35:01 +08:00
|
|
|
#ifdef PPC64_ELF_ABI_v1
|
|
|
|
|
/*
|
|
|
|
|
* Load TOC from function descriptor at offset 8.
|
|
|
|
|
* We can clobber r2 since we get called through a
|
|
|
|
|
* function pointer (so caller will save/restore r2)
|
|
|
|
|
* and since we don't use a TOC ourself.
|
|
|
|
|
*/
|
2018-05-24 14:56:46 +08:00
|
|
|
PPC_BPF_LL(2, 12, 8);
|
|
|
|
|
/* Load actual entry point from function descriptor */
|
|
|
|
|
PPC_BPF_LL(12, 12, 0);
|
2016-09-24 04:35:01 +08:00
|
|
|
#endif
|
2018-05-24 14:56:46 +08:00
|
|
|
|
|
|
|
|
PPC_MTLR(12);
|
2016-09-24 04:35:01 +08:00
|
|
|
PPC_BLRL();
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out)
|
|
|
|
|
{
|
|
|
|
|
/*
|
|
|
|
|
* By now, the eBPF program has already setup parameters in r3, r4 and r5
|
|
|
|
|
* r3/BPF_REG_1 - pointer to ctx -- passed as is to the next bpf program
|
|
|
|
|
* r4/BPF_REG_2 - pointer to bpf_array
|
|
|
|
|
* r5/BPF_REG_3 - index in bpf_array
|
|
|
|
|
*/
|
|
|
|
|
int b2p_bpf_array = b2p[BPF_REG_2];
|
|
|
|
|
int b2p_index = b2p[BPF_REG_3];
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* if (index >= array->map.max_entries)
|
|
|
|
|
* goto out;
|
|
|
|
|
*/
|
|
|
|
|
PPC_LWZ(b2p[TMP_REG_1], b2p_bpf_array, offsetof(struct bpf_array, map.max_entries));
|
2018-02-27 05:00:47 +08:00
|
|
|
PPC_RLWINM(b2p_index, b2p_index, 0, 0, 31);
|
2016-09-24 04:35:01 +08:00
|
|
|
PPC_CMPLW(b2p_index, b2p[TMP_REG_1]);
|
|
|
|
|
PPC_BCC(COND_GE, out);
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* if (tail_call_cnt > MAX_TAIL_CALL_CNT)
|
|
|
|
|
* goto out;
|
|
|
|
|
*/
|
|
|
|
|
PPC_LD(b2p[TMP_REG_1], 1, bpf_jit_stack_tailcallcnt(ctx));
|
|
|
|
|
PPC_CMPLWI(b2p[TMP_REG_1], MAX_TAIL_CALL_CNT);
|
|
|
|
|
PPC_BCC(COND_GT, out);
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* tail_call_cnt++;
|
|
|
|
|
*/
|
|
|
|
|
PPC_ADDI(b2p[TMP_REG_1], b2p[TMP_REG_1], 1);
|
|
|
|
|
PPC_BPF_STL(b2p[TMP_REG_1], 1, bpf_jit_stack_tailcallcnt(ctx));
|
|
|
|
|
|
|
|
|
|
/* prog = array->ptrs[index]; */
|
|
|
|
|
PPC_MULI(b2p[TMP_REG_1], b2p_index, 8);
|
|
|
|
|
PPC_ADD(b2p[TMP_REG_1], b2p[TMP_REG_1], b2p_bpf_array);
|
|
|
|
|
PPC_LD(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_array, ptrs));
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* if (prog == NULL)
|
|
|
|
|
* goto out;
|
|
|
|
|
*/
|
|
|
|
|
PPC_CMPLDI(b2p[TMP_REG_1], 0);
|
|
|
|
|
PPC_BCC(COND_EQ, out);
|
|
|
|
|
|
|
|
|
|
/* goto *(prog->bpf_func + prologue_size); */
|
|
|
|
|
PPC_LD(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_prog, bpf_func));
|
|
|
|
|
#ifdef PPC64_ELF_ABI_v1
|
|
|
|
|
/* skip past the function descriptor */
|
|
|
|
|
PPC_ADDI(b2p[TMP_REG_1], b2p[TMP_REG_1],
|
|
|
|
|
FUNCTION_DESCR_SIZE + BPF_TAILCALL_PROLOGUE_SIZE);
|
|
|
|
|
#else
|
|
|
|
|
PPC_ADDI(b2p[TMP_REG_1], b2p[TMP_REG_1], BPF_TAILCALL_PROLOGUE_SIZE);
|
|
|
|
|
#endif
|
|
|
|
|
PPC_MTCTR(b2p[TMP_REG_1]);
|
|
|
|
|
|
|
|
|
|
/* tear down stack, restore NVRs, ... */
|
|
|
|
|
bpf_jit_emit_common_epilogue(image, ctx);
|
|
|
|
|
|
|
|
|
|
PPC_BCTR();
|
|
|
|
|
/* out: */
|
|
|
|
|
}
|
|
|
|
|
|
2016-06-23 00:25:07 +08:00
|
|
|
/* Assemble the body code between the prologue & epilogue */
|
|
|
|
|
static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
|
|
|
|
|
struct codegen_context *ctx,
|
2018-05-24 14:56:47 +08:00
|
|
|
u32 *addrs, bool extra_pass)
|
2016-06-23 00:25:07 +08:00
|
|
|
{
|
|
|
|
|
const struct bpf_insn *insn = fp->insnsi;
|
|
|
|
|
int flen = fp->len;
|
|
|
|
|
int i;
|
|
|
|
|
|
|
|
|
|
/* Start of epilogue code - will only be valid 2nd pass onwards */
|
|
|
|
|
u32 exit_addr = addrs[flen];
|
|
|
|
|
|
|
|
|
|
for (i = 0; i < flen; i++) {
|
|
|
|
|
u32 code = insn[i].code;
|
|
|
|
|
u32 dst_reg = b2p[insn[i].dst_reg];
|
|
|
|
|
u32 src_reg = b2p[insn[i].src_reg];
|
|
|
|
|
s16 off = insn[i].off;
|
|
|
|
|
s32 imm = insn[i].imm;
|
|
|
|
|
u64 imm64;
|
|
|
|
|
u8 *func;
|
|
|
|
|
u32 true_cond;
|
2018-07-20 00:18:35 +08:00
|
|
|
u32 tmp_idx;
|
2016-06-23 00:25:07 +08:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* addrs[] maps a BPF bytecode address into a real offset from
|
|
|
|
|
* the start of the body code.
|
|
|
|
|
*/
|
|
|
|
|
addrs[i] = ctx->idx * 4;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* As an optimization, we note down which non-volatile registers
|
|
|
|
|
* are used so that we can only save/restore those in our
|
|
|
|
|
* prologue and epilogue. We do this here regardless of whether
|
|
|
|
|
* the actual BPF instruction uses src/dst registers or not
|
|
|
|
|
* (for instance, BPF_CALL does not use them). The expectation
|
|
|
|
|
* is that those instructions will have src_reg/dst_reg set to
|
|
|
|
|
* 0. Even otherwise, we just lose some prologue/epilogue
|
|
|
|
|
* optimization but everything else should work without
|
|
|
|
|
* any issues.
|
|
|
|
|
*/
|
2016-09-24 04:35:00 +08:00
|
|
|
if (dst_reg >= BPF_PPC_NVR_MIN && dst_reg < 32)
|
2016-06-23 00:25:07 +08:00
|
|
|
bpf_set_seen_register(ctx, insn[i].dst_reg);
|
2016-09-24 04:35:00 +08:00
|
|
|
if (src_reg >= BPF_PPC_NVR_MIN && src_reg < 32)
|
2016-06-23 00:25:07 +08:00
|
|
|
bpf_set_seen_register(ctx, insn[i].src_reg);
|
|
|
|
|
|
|
|
|
|
switch (code) {
|
|
|
|
|
/*
|
|
|
|
|
* Arithmetic operations: ADD/SUB/MUL/DIV/MOD/NEG
|
|
|
|
|
*/
|
|
|
|
|
case BPF_ALU | BPF_ADD | BPF_X: /* (u32) dst += (u32) src */
|
|
|
|
|
case BPF_ALU64 | BPF_ADD | BPF_X: /* dst += src */
|
|
|
|
|
PPC_ADD(dst_reg, dst_reg, src_reg);
|
|
|
|
|
goto bpf_alu32_trunc;
|
|
|
|
|
case BPF_ALU | BPF_SUB | BPF_X: /* (u32) dst -= (u32) src */
|
|
|
|
|
case BPF_ALU64 | BPF_SUB | BPF_X: /* dst -= src */
|
|
|
|
|
PPC_SUB(dst_reg, dst_reg, src_reg);
|
|
|
|
|
goto bpf_alu32_trunc;
|
|
|
|
|
case BPF_ALU | BPF_ADD | BPF_K: /* (u32) dst += (u32) imm */
|
|
|
|
|
case BPF_ALU | BPF_SUB | BPF_K: /* (u32) dst -= (u32) imm */
|
|
|
|
|
case BPF_ALU64 | BPF_ADD | BPF_K: /* dst += imm */
|
|
|
|
|
case BPF_ALU64 | BPF_SUB | BPF_K: /* dst -= imm */
|
|
|
|
|
if (BPF_OP(code) == BPF_SUB)
|
|
|
|
|
imm = -imm;
|
|
|
|
|
if (imm) {
|
|
|
|
|
if (imm >= -32768 && imm < 32768)
|
|
|
|
|
PPC_ADDI(dst_reg, dst_reg, IMM_L(imm));
|
|
|
|
|
else {
|
|
|
|
|
PPC_LI32(b2p[TMP_REG_1], imm);
|
|
|
|
|
PPC_ADD(dst_reg, dst_reg, b2p[TMP_REG_1]);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
goto bpf_alu32_trunc;
|
|
|
|
|
case BPF_ALU | BPF_MUL | BPF_X: /* (u32) dst *= (u32) src */
|
|
|
|
|
case BPF_ALU64 | BPF_MUL | BPF_X: /* dst *= src */
|
|
|
|
|
if (BPF_CLASS(code) == BPF_ALU)
|
|
|
|
|
PPC_MULW(dst_reg, dst_reg, src_reg);
|
|
|
|
|
else
|
|
|
|
|
PPC_MULD(dst_reg, dst_reg, src_reg);
|
|
|
|
|
goto bpf_alu32_trunc;
|
|
|
|
|
case BPF_ALU | BPF_MUL | BPF_K: /* (u32) dst *= (u32) imm */
|
|
|
|
|
case BPF_ALU64 | BPF_MUL | BPF_K: /* dst *= imm */
|
|
|
|
|
if (imm >= -32768 && imm < 32768)
|
|
|
|
|
PPC_MULI(dst_reg, dst_reg, IMM_L(imm));
|
|
|
|
|
else {
|
|
|
|
|
PPC_LI32(b2p[TMP_REG_1], imm);
|
|
|
|
|
if (BPF_CLASS(code) == BPF_ALU)
|
|
|
|
|
PPC_MULW(dst_reg, dst_reg,
|
|
|
|
|
b2p[TMP_REG_1]);
|
|
|
|
|
else
|
|
|
|
|
PPC_MULD(dst_reg, dst_reg,
|
|
|
|
|
b2p[TMP_REG_1]);
|
|
|
|
|
}
|
|
|
|
|
goto bpf_alu32_trunc;
|
|
|
|
|
case BPF_ALU | BPF_DIV | BPF_X: /* (u32) dst /= (u32) src */
|
|
|
|
|
case BPF_ALU | BPF_MOD | BPF_X: /* (u32) dst %= (u32) src */
|
|
|
|
|
if (BPF_OP(code) == BPF_MOD) {
|
|
|
|
|
PPC_DIVWU(b2p[TMP_REG_1], dst_reg, src_reg);
|
|
|
|
|
PPC_MULW(b2p[TMP_REG_1], src_reg,
|
|
|
|
|
b2p[TMP_REG_1]);
|
|
|
|
|
PPC_SUB(dst_reg, dst_reg, b2p[TMP_REG_1]);
|
|
|
|
|
} else
|
|
|
|
|
PPC_DIVWU(dst_reg, dst_reg, src_reg);
|
|
|
|
|
goto bpf_alu32_trunc;
|
|
|
|
|
case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */
|
|
|
|
|
case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */
|
|
|
|
|
if (BPF_OP(code) == BPF_MOD) {
|
|
|
|
|
PPC_DIVD(b2p[TMP_REG_1], dst_reg, src_reg);
|
|
|
|
|
PPC_MULD(b2p[TMP_REG_1], src_reg,
|
|
|
|
|
b2p[TMP_REG_1]);
|
|
|
|
|
PPC_SUB(dst_reg, dst_reg, b2p[TMP_REG_1]);
|
|
|
|
|
} else
|
|
|
|
|
PPC_DIVD(dst_reg, dst_reg, src_reg);
|
|
|
|
|
break;
|
|
|
|
|
case BPF_ALU | BPF_MOD | BPF_K: /* (u32) dst %= (u32) imm */
|
|
|
|
|
case BPF_ALU | BPF_DIV | BPF_K: /* (u32) dst /= (u32) imm */
|
|
|
|
|
case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */
|
|
|
|
|
case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */
|
|
|
|
|
if (imm == 0)
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
else if (imm == 1)
|
|
|
|
|
goto bpf_alu32_trunc;
|
|
|
|
|
|
|
|
|
|
PPC_LI32(b2p[TMP_REG_1], imm);
|
|
|
|
|
switch (BPF_CLASS(code)) {
|
|
|
|
|
case BPF_ALU:
|
|
|
|
|
if (BPF_OP(code) == BPF_MOD) {
|
|
|
|
|
PPC_DIVWU(b2p[TMP_REG_2], dst_reg,
|
|
|
|
|
b2p[TMP_REG_1]);
|
|
|
|
|
PPC_MULW(b2p[TMP_REG_1],
|
|
|
|
|
b2p[TMP_REG_1],
|
|
|
|
|
b2p[TMP_REG_2]);
|
|
|
|
|
PPC_SUB(dst_reg, dst_reg,
|
|
|
|
|
b2p[TMP_REG_1]);
|
|
|
|
|
} else
|
|
|
|
|
PPC_DIVWU(dst_reg, dst_reg,
|
|
|
|
|
b2p[TMP_REG_1]);
|
|
|
|
|
break;
|
|
|
|
|
case BPF_ALU64:
|
|
|
|
|
if (BPF_OP(code) == BPF_MOD) {
|
|
|
|
|
PPC_DIVD(b2p[TMP_REG_2], dst_reg,
|
|
|
|
|
b2p[TMP_REG_1]);
|
|
|
|
|
PPC_MULD(b2p[TMP_REG_1],
|
|
|
|
|
b2p[TMP_REG_1],
|
|
|
|
|
b2p[TMP_REG_2]);
|
|
|
|
|
PPC_SUB(dst_reg, dst_reg,
|
|
|
|
|
b2p[TMP_REG_1]);
|
|
|
|
|
} else
|
|
|
|
|
PPC_DIVD(dst_reg, dst_reg,
|
|
|
|
|
b2p[TMP_REG_1]);
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
goto bpf_alu32_trunc;
|
|
|
|
|
case BPF_ALU | BPF_NEG: /* (u32) dst = -dst */
|
|
|
|
|
case BPF_ALU64 | BPF_NEG: /* dst = -dst */
|
|
|
|
|
PPC_NEG(dst_reg, dst_reg);
|
|
|
|
|
goto bpf_alu32_trunc;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Logical operations: AND/OR/XOR/[A]LSH/[A]RSH
|
|
|
|
|
*/
|
|
|
|
|
case BPF_ALU | BPF_AND | BPF_X: /* (u32) dst = dst & src */
|
|
|
|
|
case BPF_ALU64 | BPF_AND | BPF_X: /* dst = dst & src */
|
|
|
|
|
PPC_AND(dst_reg, dst_reg, src_reg);
|
|
|
|
|
goto bpf_alu32_trunc;
|
|
|
|
|
case BPF_ALU | BPF_AND | BPF_K: /* (u32) dst = dst & imm */
|
|
|
|
|
case BPF_ALU64 | BPF_AND | BPF_K: /* dst = dst & imm */
|
|
|
|
|
if (!IMM_H(imm))
|
|
|
|
|
PPC_ANDI(dst_reg, dst_reg, IMM_L(imm));
|
|
|
|
|
else {
|
|
|
|
|
/* Sign-extended */
|
|
|
|
|
PPC_LI32(b2p[TMP_REG_1], imm);
|
|
|
|
|
PPC_AND(dst_reg, dst_reg, b2p[TMP_REG_1]);
|
|
|
|
|
}
|
|
|
|
|
goto bpf_alu32_trunc;
|
|
|
|
|
case BPF_ALU | BPF_OR | BPF_X: /* dst = (u32) dst | (u32) src */
|
|
|
|
|
case BPF_ALU64 | BPF_OR | BPF_X: /* dst = dst | src */
|
|
|
|
|
PPC_OR(dst_reg, dst_reg, src_reg);
|
|
|
|
|
goto bpf_alu32_trunc;
|
|
|
|
|
case BPF_ALU | BPF_OR | BPF_K:/* dst = (u32) dst | (u32) imm */
|
|
|
|
|
case BPF_ALU64 | BPF_OR | BPF_K:/* dst = dst | imm */
|
|
|
|
|
if (imm < 0 && BPF_CLASS(code) == BPF_ALU64) {
|
|
|
|
|
/* Sign-extended */
|
|
|
|
|
PPC_LI32(b2p[TMP_REG_1], imm);
|
|
|
|
|
PPC_OR(dst_reg, dst_reg, b2p[TMP_REG_1]);
|
|
|
|
|
} else {
|
|
|
|
|
if (IMM_L(imm))
|
|
|
|
|
PPC_ORI(dst_reg, dst_reg, IMM_L(imm));
|
|
|
|
|
if (IMM_H(imm))
|
|
|
|
|
PPC_ORIS(dst_reg, dst_reg, IMM_H(imm));
|
|
|
|
|
}
|
|
|
|
|
goto bpf_alu32_trunc;
|
|
|
|
|
case BPF_ALU | BPF_XOR | BPF_X: /* (u32) dst ^= src */
|
|
|
|
|
case BPF_ALU64 | BPF_XOR | BPF_X: /* dst ^= src */
|
|
|
|
|
PPC_XOR(dst_reg, dst_reg, src_reg);
|
|
|
|
|
goto bpf_alu32_trunc;
|
|
|
|
|
case BPF_ALU | BPF_XOR | BPF_K: /* (u32) dst ^= (u32) imm */
|
|
|
|
|
case BPF_ALU64 | BPF_XOR | BPF_K: /* dst ^= imm */
|
|
|
|
|
if (imm < 0 && BPF_CLASS(code) == BPF_ALU64) {
|
|
|
|
|
/* Sign-extended */
|
|
|
|
|
PPC_LI32(b2p[TMP_REG_1], imm);
|
|
|
|
|
PPC_XOR(dst_reg, dst_reg, b2p[TMP_REG_1]);
|
|
|
|
|
} else {
|
|
|
|
|
if (IMM_L(imm))
|
|
|
|
|
PPC_XORI(dst_reg, dst_reg, IMM_L(imm));
|
|
|
|
|
if (IMM_H(imm))
|
|
|
|
|
PPC_XORIS(dst_reg, dst_reg, IMM_H(imm));
|
|
|
|
|
}
|
|
|
|
|
goto bpf_alu32_trunc;
|
|
|
|
|
case BPF_ALU | BPF_LSH | BPF_X: /* (u32) dst <<= (u32) src */
|
|
|
|
|
/* slw clears top 32 bits */
|
|
|
|
|
PPC_SLW(dst_reg, dst_reg, src_reg);
|
|
|
|
|
break;
|
|
|
|
|
case BPF_ALU64 | BPF_LSH | BPF_X: /* dst <<= src; */
|
|
|
|
|
PPC_SLD(dst_reg, dst_reg, src_reg);
|
|
|
|
|
break;
|
|
|
|
|
case BPF_ALU | BPF_LSH | BPF_K: /* (u32) dst <<== (u32) imm */
|
|
|
|
|
/* with imm 0, we still need to clear top 32 bits */
|
|
|
|
|
PPC_SLWI(dst_reg, dst_reg, imm);
|
|
|
|
|
break;
|
|
|
|
|
case BPF_ALU64 | BPF_LSH | BPF_K: /* dst <<== imm */
|
|
|
|
|
if (imm != 0)
|
|
|
|
|
PPC_SLDI(dst_reg, dst_reg, imm);
|
|
|
|
|
break;
|
|
|
|
|
case BPF_ALU | BPF_RSH | BPF_X: /* (u32) dst >>= (u32) src */
|
|
|
|
|
PPC_SRW(dst_reg, dst_reg, src_reg);
|
|
|
|
|
break;
|
|
|
|
|
case BPF_ALU64 | BPF_RSH | BPF_X: /* dst >>= src */
|
|
|
|
|
PPC_SRD(dst_reg, dst_reg, src_reg);
|
|
|
|
|
break;
|
|
|
|
|
case BPF_ALU | BPF_RSH | BPF_K: /* (u32) dst >>= (u32) imm */
|
|
|
|
|
PPC_SRWI(dst_reg, dst_reg, imm);
|
|
|
|
|
break;
|
|
|
|
|
case BPF_ALU64 | BPF_RSH | BPF_K: /* dst >>= imm */
|
|
|
|
|
if (imm != 0)
|
|
|
|
|
PPC_SRDI(dst_reg, dst_reg, imm);
|
|
|
|
|
break;
|
|
|
|
|
case BPF_ALU64 | BPF_ARSH | BPF_X: /* (s64) dst >>= src */
|
|
|
|
|
PPC_SRAD(dst_reg, dst_reg, src_reg);
|
|
|
|
|
break;
|
|
|
|
|
case BPF_ALU64 | BPF_ARSH | BPF_K: /* (s64) dst >>= imm */
|
|
|
|
|
if (imm != 0)
|
|
|
|
|
PPC_SRADI(dst_reg, dst_reg, imm);
|
|
|
|
|
break;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* MOV
|
|
|
|
|
*/
|
|
|
|
|
case BPF_ALU | BPF_MOV | BPF_X: /* (u32) dst = src */
|
|
|
|
|
case BPF_ALU64 | BPF_MOV | BPF_X: /* dst = src */
|
|
|
|
|
PPC_MR(dst_reg, src_reg);
|
|
|
|
|
goto bpf_alu32_trunc;
|
|
|
|
|
case BPF_ALU | BPF_MOV | BPF_K: /* (u32) dst = imm */
|
|
|
|
|
case BPF_ALU64 | BPF_MOV | BPF_K: /* dst = (s64) imm */
|
|
|
|
|
PPC_LI32(dst_reg, imm);
|
|
|
|
|
if (imm < 0)
|
|
|
|
|
goto bpf_alu32_trunc;
|
|
|
|
|
break;
|
|
|
|
|
|
|
|
|
|
bpf_alu32_trunc:
|
|
|
|
|
/* Truncate to 32-bits */
|
|
|
|
|
if (BPF_CLASS(code) == BPF_ALU)
|
|
|
|
|
PPC_RLWINM(dst_reg, dst_reg, 0, 0, 31);
|
|
|
|
|
break;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* BPF_FROM_BE/LE
|
|
|
|
|
*/
|
|
|
|
|
case BPF_ALU | BPF_END | BPF_FROM_LE:
|
|
|
|
|
case BPF_ALU | BPF_END | BPF_FROM_BE:
|
|
|
|
|
#ifdef __BIG_ENDIAN__
|
|
|
|
|
if (BPF_SRC(code) == BPF_FROM_BE)
|
|
|
|
|
goto emit_clear;
|
|
|
|
|
#else /* !__BIG_ENDIAN__ */
|
|
|
|
|
if (BPF_SRC(code) == BPF_FROM_LE)
|
|
|
|
|
goto emit_clear;
|
|
|
|
|
#endif
|
|
|
|
|
switch (imm) {
|
|
|
|
|
case 16:
|
|
|
|
|
/* Rotate 8 bits left & mask with 0x0000ff00 */
|
|
|
|
|
PPC_RLWINM(b2p[TMP_REG_1], dst_reg, 8, 16, 23);
|
|
|
|
|
/* Rotate 8 bits right & insert LSB to reg */
|
|
|
|
|
PPC_RLWIMI(b2p[TMP_REG_1], dst_reg, 24, 24, 31);
|
|
|
|
|
/* Move result back to dst_reg */
|
|
|
|
|
PPC_MR(dst_reg, b2p[TMP_REG_1]);
|
|
|
|
|
break;
|
|
|
|
|
case 32:
|
|
|
|
|
/*
|
|
|
|
|
* Rotate word left by 8 bits:
|
|
|
|
|
* 2 bytes are already in their final position
|
|
|
|
|
* -- byte 2 and 4 (of bytes 1, 2, 3 and 4)
|
|
|
|
|
*/
|
|
|
|
|
PPC_RLWINM(b2p[TMP_REG_1], dst_reg, 8, 0, 31);
|
|
|
|
|
/* Rotate 24 bits and insert byte 1 */
|
|
|
|
|
PPC_RLWIMI(b2p[TMP_REG_1], dst_reg, 24, 0, 7);
|
|
|
|
|
/* Rotate 24 bits and insert byte 3 */
|
|
|
|
|
PPC_RLWIMI(b2p[TMP_REG_1], dst_reg, 24, 16, 23);
|
|
|
|
|
PPC_MR(dst_reg, b2p[TMP_REG_1]);
|
|
|
|
|
break;
|
|
|
|
|
case 64:
|
|
|
|
|
/*
|
|
|
|
|
* Way easier and faster(?) to store the value
|
|
|
|
|
* into stack and then use ldbrx
|
|
|
|
|
*
|
|
|
|
|
* ctx->seen will be reliable in pass2, but
|
|
|
|
|
* the instructions generated will remain the
|
|
|
|
|
* same across all passes
|
|
|
|
|
*/
|
2016-09-24 04:35:00 +08:00
|
|
|
PPC_STD(dst_reg, 1, bpf_jit_stack_local(ctx));
|
|
|
|
|
PPC_ADDI(b2p[TMP_REG_1], 1, bpf_jit_stack_local(ctx));
|
2016-06-23 00:25:07 +08:00
|
|
|
PPC_LDBRX(dst_reg, 0, b2p[TMP_REG_1]);
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
break;
|
|
|
|
|
|
|
|
|
|
emit_clear:
|
|
|
|
|
switch (imm) {
|
|
|
|
|
case 16:
|
|
|
|
|
/* zero-extend 16 bits into 64 bits */
|
|
|
|
|
PPC_RLDICL(dst_reg, dst_reg, 0, 48);
|
|
|
|
|
break;
|
|
|
|
|
case 32:
|
|
|
|
|
/* zero-extend 32 bits into 64 bits */
|
|
|
|
|
PPC_RLDICL(dst_reg, dst_reg, 0, 32);
|
|
|
|
|
break;
|
|
|
|
|
case 64:
|
|
|
|
|
/* nop */
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
break;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* BPF_ST(X)
|
|
|
|
|
*/
|
|
|
|
|
case BPF_STX | BPF_MEM | BPF_B: /* *(u8 *)(dst + off) = src */
|
|
|
|
|
case BPF_ST | BPF_MEM | BPF_B: /* *(u8 *)(dst + off) = imm */
|
|
|
|
|
if (BPF_CLASS(code) == BPF_ST) {
|
|
|
|
|
PPC_LI(b2p[TMP_REG_1], imm);
|
|
|
|
|
src_reg = b2p[TMP_REG_1];
|
|
|
|
|
}
|
|
|
|
|
PPC_STB(src_reg, dst_reg, off);
|
|
|
|
|
break;
|
|
|
|
|
case BPF_STX | BPF_MEM | BPF_H: /* (u16 *)(dst + off) = src */
|
|
|
|
|
case BPF_ST | BPF_MEM | BPF_H: /* (u16 *)(dst + off) = imm */
|
|
|
|
|
if (BPF_CLASS(code) == BPF_ST) {
|
|
|
|
|
PPC_LI(b2p[TMP_REG_1], imm);
|
|
|
|
|
src_reg = b2p[TMP_REG_1];
|
|
|
|
|
}
|
|
|
|
|
PPC_STH(src_reg, dst_reg, off);
|
|
|
|
|
break;
|
|
|
|
|
case BPF_STX | BPF_MEM | BPF_W: /* *(u32 *)(dst + off) = src */
|
|
|
|
|
case BPF_ST | BPF_MEM | BPF_W: /* *(u32 *)(dst + off) = imm */
|
|
|
|
|
if (BPF_CLASS(code) == BPF_ST) {
|
|
|
|
|
PPC_LI32(b2p[TMP_REG_1], imm);
|
|
|
|
|
src_reg = b2p[TMP_REG_1];
|
|
|
|
|
}
|
|
|
|
|
PPC_STW(src_reg, dst_reg, off);
|
|
|
|
|
break;
|
|
|
|
|
case BPF_STX | BPF_MEM | BPF_DW: /* (u64 *)(dst + off) = src */
|
|
|
|
|
case BPF_ST | BPF_MEM | BPF_DW: /* *(u64 *)(dst + off) = imm */
|
|
|
|
|
if (BPF_CLASS(code) == BPF_ST) {
|
|
|
|
|
PPC_LI32(b2p[TMP_REG_1], imm);
|
|
|
|
|
src_reg = b2p[TMP_REG_1];
|
|
|
|
|
}
|
|
|
|
|
PPC_STD(src_reg, dst_reg, off);
|
|
|
|
|
break;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* BPF_STX XADD (atomic_add)
|
|
|
|
|
*/
|
|
|
|
|
/* *(u32 *)(dst + off) += src */
|
|
|
|
|
case BPF_STX | BPF_XADD | BPF_W:
|
|
|
|
|
/* Get EA into TMP_REG_1 */
|
|
|
|
|
PPC_ADDI(b2p[TMP_REG_1], dst_reg, off);
|
2018-07-20 00:18:35 +08:00
|
|
|
tmp_idx = ctx->idx * 4;
|
2016-06-23 00:25:07 +08:00
|
|
|
/* load value from memory into TMP_REG_2 */
|
|
|
|
|
PPC_BPF_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
|
|
|
|
|
/* add value from src_reg into this */
|
|
|
|
|
PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg);
|
|
|
|
|
/* store result back */
|
|
|
|
|
PPC_BPF_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
|
|
|
|
|
/* we're done if this succeeded */
|
2018-07-20 00:18:35 +08:00
|
|
|
PPC_BCC_SHORT(COND_NE, tmp_idx);
|
2016-06-23 00:25:07 +08:00
|
|
|
break;
|
|
|
|
|
/* *(u64 *)(dst + off) += src */
|
|
|
|
|
case BPF_STX | BPF_XADD | BPF_DW:
|
|
|
|
|
PPC_ADDI(b2p[TMP_REG_1], dst_reg, off);
|
2018-07-20 00:18:35 +08:00
|
|
|
tmp_idx = ctx->idx * 4;
|
2016-06-23 00:25:07 +08:00
|
|
|
PPC_BPF_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
|
|
|
|
|
PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg);
|
|
|
|
|
PPC_BPF_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
|
2018-07-20 00:18:35 +08:00
|
|
|
PPC_BCC_SHORT(COND_NE, tmp_idx);
|
2016-06-23 00:25:07 +08:00
|
|
|
break;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* BPF_LDX
|
|
|
|
|
*/
|
|
|
|
|
/* dst = *(u8 *)(ul) (src + off) */
|
|
|
|
|
case BPF_LDX | BPF_MEM | BPF_B:
|
|
|
|
|
PPC_LBZ(dst_reg, src_reg, off);
|
|
|
|
|
break;
|
|
|
|
|
/* dst = *(u16 *)(ul) (src + off) */
|
|
|
|
|
case BPF_LDX | BPF_MEM | BPF_H:
|
|
|
|
|
PPC_LHZ(dst_reg, src_reg, off);
|
|
|
|
|
break;
|
|
|
|
|
/* dst = *(u32 *)(ul) (src + off) */
|
|
|
|
|
case BPF_LDX | BPF_MEM | BPF_W:
|
|
|
|
|
PPC_LWZ(dst_reg, src_reg, off);
|
|
|
|
|
break;
|
|
|
|
|
/* dst = *(u64 *)(ul) (src + off) */
|
|
|
|
|
case BPF_LDX | BPF_MEM | BPF_DW:
|
|
|
|
|
PPC_LD(dst_reg, src_reg, off);
|
|
|
|
|
break;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Doubleword load
|
|
|
|
|
* 16 byte instruction that uses two 'struct bpf_insn'
|
|
|
|
|
*/
|
|
|
|
|
case BPF_LD | BPF_IMM | BPF_DW: /* dst = (u64) imm */
|
|
|
|
|
imm64 = ((u64)(u32) insn[i].imm) |
|
|
|
|
|
(((u64)(u32) insn[i+1].imm) << 32);
|
|
|
|
|
/* Adjust for two bpf instructions */
|
|
|
|
|
addrs[++i] = ctx->idx * 4;
|
|
|
|
|
PPC_LI64(dst_reg, imm64);
|
|
|
|
|
break;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Return/Exit
|
|
|
|
|
*/
|
|
|
|
|
case BPF_JMP | BPF_EXIT:
|
|
|
|
|
/*
|
|
|
|
|
* If this isn't the very last instruction, branch to
|
|
|
|
|
* the epilogue. If we _are_ the last instruction,
|
|
|
|
|
* we'll just fall through to the epilogue.
|
|
|
|
|
*/
|
|
|
|
|
if (i != flen - 1)
|
|
|
|
|
PPC_JMP(exit_addr);
|
|
|
|
|
/* else fall through to the epilogue */
|
|
|
|
|
break;
|
|
|
|
|
|
|
|
|
|
/*
|
2018-05-24 14:56:47 +08:00
|
|
|
* Call kernel helper or bpf function
|
2016-06-23 00:25:07 +08:00
|
|
|
*/
|
|
|
|
|
case BPF_JMP | BPF_CALL:
|
|
|
|
|
ctx->seen |= SEEN_FUNC;
|
2018-05-24 14:56:47 +08:00
|
|
|
|
|
|
|
|
/* bpf function call */
|
|
|
|
|
if (insn[i].src_reg == BPF_PSEUDO_CALL)
|
|
|
|
|
if (!extra_pass)
|
|
|
|
|
func = NULL;
|
|
|
|
|
else if (fp->aux->func && off < fp->aux->func_cnt)
|
|
|
|
|
/* use the subprog id from the off
|
|
|
|
|
* field to lookup the callee address
|
|
|
|
|
*/
|
|
|
|
|
func = (u8 *) fp->aux->func[off]->bpf_func;
|
|
|
|
|
else
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
/* kernel helper call */
|
|
|
|
|
else
|
|
|
|
|
func = (u8 *) __bpf_call_base + imm;
|
2016-06-23 00:25:07 +08:00
|
|
|
|
|
|
|
|
bpf_jit_emit_func_call(image, ctx, (u64)func);
|
|
|
|
|
|
|
|
|
|
/* move return value from r3 to BPF_REG_0 */
|
|
|
|
|
PPC_MR(b2p[BPF_REG_0], 3);
|
|
|
|
|
break;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Jumps and branches
|
|
|
|
|
*/
|
|
|
|
|
case BPF_JMP | BPF_JA:
|
|
|
|
|
PPC_JMP(addrs[i + 1 + off]);
|
|
|
|
|
break;
|
|
|
|
|
|
|
|
|
|
case BPF_JMP | BPF_JGT | BPF_K:
|
|
|
|
|
case BPF_JMP | BPF_JGT | BPF_X:
|
|
|
|
|
case BPF_JMP | BPF_JSGT | BPF_K:
|
|
|
|
|
case BPF_JMP | BPF_JSGT | BPF_X:
|
|
|
|
|
true_cond = COND_GT;
|
|
|
|
|
goto cond_branch;
|
2017-08-10 07:40:00 +08:00
|
|
|
case BPF_JMP | BPF_JLT | BPF_K:
|
|
|
|
|
case BPF_JMP | BPF_JLT | BPF_X:
|
|
|
|
|
case BPF_JMP | BPF_JSLT | BPF_K:
|
|
|
|
|
case BPF_JMP | BPF_JSLT | BPF_X:
|
|
|
|
|
true_cond = COND_LT;
|
|
|
|
|
goto cond_branch;
|
2016-06-23 00:25:07 +08:00
|
|
|
case BPF_JMP | BPF_JGE | BPF_K:
|
|
|
|
|
case BPF_JMP | BPF_JGE | BPF_X:
|
|
|
|
|
case BPF_JMP | BPF_JSGE | BPF_K:
|
|
|
|
|
case BPF_JMP | BPF_JSGE | BPF_X:
|
|
|
|
|
true_cond = COND_GE;
|
|
|
|
|
goto cond_branch;
|
2017-08-10 07:40:00 +08:00
|
|
|
case BPF_JMP | BPF_JLE | BPF_K:
|
|
|
|
|
case BPF_JMP | BPF_JLE | BPF_X:
|
|
|
|
|
case BPF_JMP | BPF_JSLE | BPF_K:
|
|
|
|
|
case BPF_JMP | BPF_JSLE | BPF_X:
|
|
|
|
|
true_cond = COND_LE;
|
|
|
|
|
goto cond_branch;
|
2016-06-23 00:25:07 +08:00
|
|
|
case BPF_JMP | BPF_JEQ | BPF_K:
|
|
|
|
|
case BPF_JMP | BPF_JEQ | BPF_X:
|
|
|
|
|
true_cond = COND_EQ;
|
|
|
|
|
goto cond_branch;
|
|
|
|
|
case BPF_JMP | BPF_JNE | BPF_K:
|
|
|
|
|
case BPF_JMP | BPF_JNE | BPF_X:
|
|
|
|
|
true_cond = COND_NE;
|
|
|
|
|
goto cond_branch;
|
|
|
|
|
case BPF_JMP | BPF_JSET | BPF_K:
|
|
|
|
|
case BPF_JMP | BPF_JSET | BPF_X:
|
|
|
|
|
true_cond = COND_NE;
|
|
|
|
|
/* Fall through */
|
|
|
|
|
|
|
|
|
|
cond_branch:
|
|
|
|
|
switch (code) {
|
|
|
|
|
case BPF_JMP | BPF_JGT | BPF_X:
|
2017-08-10 07:40:00 +08:00
|
|
|
case BPF_JMP | BPF_JLT | BPF_X:
|
2016-06-23 00:25:07 +08:00
|
|
|
case BPF_JMP | BPF_JGE | BPF_X:
|
2017-08-10 07:40:00 +08:00
|
|
|
case BPF_JMP | BPF_JLE | BPF_X:
|
2016-06-23 00:25:07 +08:00
|
|
|
case BPF_JMP | BPF_JEQ | BPF_X:
|
|
|
|
|
case BPF_JMP | BPF_JNE | BPF_X:
|
|
|
|
|
/* unsigned comparison */
|
|
|
|
|
PPC_CMPLD(dst_reg, src_reg);
|
|
|
|
|
break;
|
|
|
|
|
case BPF_JMP | BPF_JSGT | BPF_X:
|
2017-08-10 07:40:00 +08:00
|
|
|
case BPF_JMP | BPF_JSLT | BPF_X:
|
2016-06-23 00:25:07 +08:00
|
|
|
case BPF_JMP | BPF_JSGE | BPF_X:
|
2017-08-10 07:40:00 +08:00
|
|
|
case BPF_JMP | BPF_JSLE | BPF_X:
|
2016-06-23 00:25:07 +08:00
|
|
|
/* signed comparison */
|
|
|
|
|
PPC_CMPD(dst_reg, src_reg);
|
|
|
|
|
break;
|
|
|
|
|
case BPF_JMP | BPF_JSET | BPF_X:
|
|
|
|
|
PPC_AND_DOT(b2p[TMP_REG_1], dst_reg, src_reg);
|
|
|
|
|
break;
|
|
|
|
|
case BPF_JMP | BPF_JNE | BPF_K:
|
|
|
|
|
case BPF_JMP | BPF_JEQ | BPF_K:
|
|
|
|
|
case BPF_JMP | BPF_JGT | BPF_K:
|
2017-08-10 07:40:00 +08:00
|
|
|
case BPF_JMP | BPF_JLT | BPF_K:
|
2016-06-23 00:25:07 +08:00
|
|
|
case BPF_JMP | BPF_JGE | BPF_K:
|
2017-08-10 07:40:00 +08:00
|
|
|
case BPF_JMP | BPF_JLE | BPF_K:
|
2016-06-23 00:25:07 +08:00
|
|
|
/*
|
|
|
|
|
* Need sign-extended load, so only positive
|
|
|
|
|
* values can be used as imm in cmpldi
|
|
|
|
|
*/
|
|
|
|
|
if (imm >= 0 && imm < 32768)
|
|
|
|
|
PPC_CMPLDI(dst_reg, imm);
|
|
|
|
|
else {
|
|
|
|
|
/* sign-extending load */
|
|
|
|
|
PPC_LI32(b2p[TMP_REG_1], imm);
|
|
|
|
|
/* ... but unsigned comparison */
|
|
|
|
|
PPC_CMPLD(dst_reg, b2p[TMP_REG_1]);
|
|
|
|
|
}
|
|
|
|
|
break;
|
|
|
|
|
case BPF_JMP | BPF_JSGT | BPF_K:
|
2017-08-10 07:40:00 +08:00
|
|
|
case BPF_JMP | BPF_JSLT | BPF_K:
|
2016-06-23 00:25:07 +08:00
|
|
|
case BPF_JMP | BPF_JSGE | BPF_K:
|
2017-08-10 07:40:00 +08:00
|
|
|
case BPF_JMP | BPF_JSLE | BPF_K:
|
2016-06-23 00:25:07 +08:00
|
|
|
/*
|
|
|
|
|
* signed comparison, so any 16-bit value
|
|
|
|
|
* can be used in cmpdi
|
|
|
|
|
*/
|
|
|
|
|
if (imm >= -32768 && imm < 32768)
|
|
|
|
|
PPC_CMPDI(dst_reg, imm);
|
|
|
|
|
else {
|
|
|
|
|
PPC_LI32(b2p[TMP_REG_1], imm);
|
|
|
|
|
PPC_CMPD(dst_reg, b2p[TMP_REG_1]);
|
|
|
|
|
}
|
|
|
|
|
break;
|
|
|
|
|
case BPF_JMP | BPF_JSET | BPF_K:
|
|
|
|
|
/* andi does not sign-extend the immediate */
|
|
|
|
|
if (imm >= 0 && imm < 32768)
|
|
|
|
|
/* PPC_ANDI is _only/always_ dot-form */
|
|
|
|
|
PPC_ANDI(b2p[TMP_REG_1], dst_reg, imm);
|
|
|
|
|
else {
|
|
|
|
|
PPC_LI32(b2p[TMP_REG_1], imm);
|
|
|
|
|
PPC_AND_DOT(b2p[TMP_REG_1], dst_reg,
|
|
|
|
|
b2p[TMP_REG_1]);
|
|
|
|
|
}
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
PPC_BCC(true_cond, addrs[i + 1 + off]);
|
|
|
|
|
break;
|
|
|
|
|
|
|
|
|
|
/*
|
2016-09-24 04:35:01 +08:00
|
|
|
* Tail call
|
2016-06-23 00:25:07 +08:00
|
|
|
*/
|
2017-05-31 04:31:27 +08:00
|
|
|
case BPF_JMP | BPF_TAIL_CALL:
|
2016-09-24 04:35:01 +08:00
|
|
|
ctx->seen |= SEEN_TAILCALL;
|
|
|
|
|
bpf_jit_emit_tail_call(image, ctx, addrs[i + 1]);
|
|
|
|
|
break;
|
2016-06-23 00:25:07 +08:00
|
|
|
|
|
|
|
|
default:
|
|
|
|
|
/*
|
|
|
|
|
* The filter contains something cruel & unusual.
|
|
|
|
|
* We don't handle it, but also there shouldn't be
|
|
|
|
|
* anything missing from our list.
|
|
|
|
|
*/
|
|
|
|
|
pr_err_ratelimited("eBPF filter opcode %04x (@%d) unsupported\n",
|
|
|
|
|
code, i);
|
|
|
|
|
return -ENOTSUPP;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Set end-of-body-code address for exit. */
|
|
|
|
|
addrs[i] = ctx->idx * 4;
|
|
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
2018-05-24 14:56:47 +08:00
|
|
|
struct powerpc64_jit_data {
|
|
|
|
|
struct bpf_binary_header *header;
|
|
|
|
|
u32 *addrs;
|
|
|
|
|
u8 *image;
|
|
|
|
|
u32 proglen;
|
|
|
|
|
struct codegen_context ctx;
|
|
|
|
|
};
|
|
|
|
|
|
2016-06-23 00:25:07 +08:00
|
|
|
struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
|
|
|
|
|
{
|
|
|
|
|
u32 proglen;
|
|
|
|
|
u32 alloclen;
|
|
|
|
|
u8 *image = NULL;
|
|
|
|
|
u32 *code_base;
|
|
|
|
|
u32 *addrs;
|
2018-05-24 14:56:47 +08:00
|
|
|
struct powerpc64_jit_data *jit_data;
|
2016-06-23 00:25:07 +08:00
|
|
|
struct codegen_context cgctx;
|
|
|
|
|
int pass;
|
|
|
|
|
int flen;
|
|
|
|
|
struct bpf_binary_header *bpf_hdr;
|
powerpc/bpf: Add support for bpf constant blinding
In line with similar support for other architectures by Daniel Borkmann.
'MOD Default X' from test_bpf without constant blinding:
84 bytes emitted from JIT compiler (pass:3, flen:7)
d0000000058a4688 + <x>:
0: nop
4: nop
8: std r27,-40(r1)
c: std r28,-32(r1)
10: xor r8,r8,r8
14: xor r28,r28,r28
18: mr r27,r3
1c: li r8,66
20: cmpwi r28,0
24: bne 0x0000000000000030
28: li r8,0
2c: b 0x0000000000000044
30: divwu r9,r8,r28
34: mullw r9,r28,r9
38: subf r8,r9,r8
3c: rotlwi r8,r8,0
40: li r8,66
44: ld r27,-40(r1)
48: ld r28,-32(r1)
4c: mr r3,r8
50: blr
... and with constant blinding:
140 bytes emitted from JIT compiler (pass:3, flen:11)
d00000000bd6ab24 + <x>:
0: nop
4: nop
8: std r27,-40(r1)
c: std r28,-32(r1)
10: xor r8,r8,r8
14: xor r28,r28,r28
18: mr r27,r3
1c: lis r2,-22834
20: ori r2,r2,36083
24: rotlwi r2,r2,0
28: xori r2,r2,36017
2c: xoris r2,r2,42702
30: rotlwi r2,r2,0
34: mr r8,r2
38: rotlwi r8,r8,0
3c: cmpwi r28,0
40: bne 0x000000000000004c
44: li r8,0
48: b 0x000000000000007c
4c: divwu r9,r8,r28
50: mullw r9,r28,r9
54: subf r8,r9,r8
58: rotlwi r8,r8,0
5c: lis r2,-17137
60: ori r2,r2,39065
64: rotlwi r2,r2,0
68: xori r2,r2,39131
6c: xoris r2,r2,48399
70: rotlwi r2,r2,0
74: mr r8,r2
78: rotlwi r8,r8,0
7c: ld r27,-40(r1)
80: ld r28,-32(r1)
84: mr r3,r8
88: blr
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-09-24 04:35:02 +08:00
|
|
|
struct bpf_prog *org_fp = fp;
|
|
|
|
|
struct bpf_prog *tmp_fp;
|
|
|
|
|
bool bpf_blinded = false;
|
2018-05-24 14:56:47 +08:00
|
|
|
bool extra_pass = false;
|
2016-06-23 00:25:07 +08:00
|
|
|
|
2017-12-15 09:55:14 +08:00
|
|
|
if (!fp->jit_requested)
|
powerpc/bpf: Add support for bpf constant blinding
In line with similar support for other architectures by Daniel Borkmann.
'MOD Default X' from test_bpf without constant blinding:
84 bytes emitted from JIT compiler (pass:3, flen:7)
d0000000058a4688 + <x>:
0: nop
4: nop
8: std r27,-40(r1)
c: std r28,-32(r1)
10: xor r8,r8,r8
14: xor r28,r28,r28
18: mr r27,r3
1c: li r8,66
20: cmpwi r28,0
24: bne 0x0000000000000030
28: li r8,0
2c: b 0x0000000000000044
30: divwu r9,r8,r28
34: mullw r9,r28,r9
38: subf r8,r9,r8
3c: rotlwi r8,r8,0
40: li r8,66
44: ld r27,-40(r1)
48: ld r28,-32(r1)
4c: mr r3,r8
50: blr
... and with constant blinding:
140 bytes emitted from JIT compiler (pass:3, flen:11)
d00000000bd6ab24 + <x>:
0: nop
4: nop
8: std r27,-40(r1)
c: std r28,-32(r1)
10: xor r8,r8,r8
14: xor r28,r28,r28
18: mr r27,r3
1c: lis r2,-22834
20: ori r2,r2,36083
24: rotlwi r2,r2,0
28: xori r2,r2,36017
2c: xoris r2,r2,42702
30: rotlwi r2,r2,0
34: mr r8,r2
38: rotlwi r8,r8,0
3c: cmpwi r28,0
40: bne 0x000000000000004c
44: li r8,0
48: b 0x000000000000007c
4c: divwu r9,r8,r28
50: mullw r9,r28,r9
54: subf r8,r9,r8
58: rotlwi r8,r8,0
5c: lis r2,-17137
60: ori r2,r2,39065
64: rotlwi r2,r2,0
68: xori r2,r2,39131
6c: xoris r2,r2,48399
70: rotlwi r2,r2,0
74: mr r8,r2
78: rotlwi r8,r8,0
7c: ld r27,-40(r1)
80: ld r28,-32(r1)
84: mr r3,r8
88: blr
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-09-24 04:35:02 +08:00
|
|
|
return org_fp;
|
|
|
|
|
|
|
|
|
|
tmp_fp = bpf_jit_blind_constants(org_fp);
|
|
|
|
|
if (IS_ERR(tmp_fp))
|
|
|
|
|
return org_fp;
|
|
|
|
|
|
|
|
|
|
if (tmp_fp != org_fp) {
|
|
|
|
|
bpf_blinded = true;
|
|
|
|
|
fp = tmp_fp;
|
|
|
|
|
}
|
2016-06-23 00:25:07 +08:00
|
|
|
|
2018-05-24 14:56:47 +08:00
|
|
|
jit_data = fp->aux->jit_data;
|
|
|
|
|
if (!jit_data) {
|
|
|
|
|
jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL);
|
|
|
|
|
if (!jit_data) {
|
|
|
|
|
fp = org_fp;
|
|
|
|
|
goto out;
|
|
|
|
|
}
|
|
|
|
|
fp->aux->jit_data = jit_data;
|
|
|
|
|
}
|
|
|
|
|
|
2016-06-23 00:25:07 +08:00
|
|
|
flen = fp->len;
|
2018-05-24 14:56:47 +08:00
|
|
|
addrs = jit_data->addrs;
|
|
|
|
|
if (addrs) {
|
|
|
|
|
cgctx = jit_data->ctx;
|
|
|
|
|
image = jit_data->image;
|
|
|
|
|
bpf_hdr = jit_data->header;
|
|
|
|
|
proglen = jit_data->proglen;
|
|
|
|
|
alloclen = proglen + FUNCTION_DESCR_SIZE;
|
|
|
|
|
extra_pass = true;
|
|
|
|
|
goto skip_init_ctx;
|
|
|
|
|
}
|
|
|
|
|
|
treewide: kzalloc() -> kcalloc()
The kzalloc() function has a 2-factor argument form, kcalloc(). This
patch replaces cases of:
kzalloc(a * b, gfp)
with:
kcalloc(a * b, gfp)
as well as handling cases of:
kzalloc(a * b * c, gfp)
with:
kzalloc(array3_size(a, b, c), gfp)
as it's slightly less ugly than:
kzalloc_array(array_size(a, b), c, gfp)
This does, however, attempt to ignore constant size factors like:
kzalloc(4 * 1024, gfp)
though any constants defined via macros get caught up in the conversion.
Any factors with a sizeof() of "unsigned char", "char", and "u8" were
dropped, since they're redundant.
The Coccinelle script used for this was:
// Fix redundant parens around sizeof().
@@
type TYPE;
expression THING, E;
@@
(
kzalloc(
- (sizeof(TYPE)) * E
+ sizeof(TYPE) * E
, ...)
|
kzalloc(
- (sizeof(THING)) * E
+ sizeof(THING) * E
, ...)
)
// Drop single-byte sizes and redundant parens.
@@
expression COUNT;
typedef u8;
typedef __u8;
@@
(
kzalloc(
- sizeof(u8) * (COUNT)
+ COUNT
, ...)
|
kzalloc(
- sizeof(__u8) * (COUNT)
+ COUNT
, ...)
|
kzalloc(
- sizeof(char) * (COUNT)
+ COUNT
, ...)
|
kzalloc(
- sizeof(unsigned char) * (COUNT)
+ COUNT
, ...)
|
kzalloc(
- sizeof(u8) * COUNT
+ COUNT
, ...)
|
kzalloc(
- sizeof(__u8) * COUNT
+ COUNT
, ...)
|
kzalloc(
- sizeof(char) * COUNT
+ COUNT
, ...)
|
kzalloc(
- sizeof(unsigned char) * COUNT
+ COUNT
, ...)
)
// 2-factor product with sizeof(type/expression) and identifier or constant.
@@
type TYPE;
expression THING;
identifier COUNT_ID;
constant COUNT_CONST;
@@
(
- kzalloc
+ kcalloc
(
- sizeof(TYPE) * (COUNT_ID)
+ COUNT_ID, sizeof(TYPE)
, ...)
|
- kzalloc
+ kcalloc
(
- sizeof(TYPE) * COUNT_ID
+ COUNT_ID, sizeof(TYPE)
, ...)
|
- kzalloc
+ kcalloc
(
- sizeof(TYPE) * (COUNT_CONST)
+ COUNT_CONST, sizeof(TYPE)
, ...)
|
- kzalloc
+ kcalloc
(
- sizeof(TYPE) * COUNT_CONST
+ COUNT_CONST, sizeof(TYPE)
, ...)
|
- kzalloc
+ kcalloc
(
- sizeof(THING) * (COUNT_ID)
+ COUNT_ID, sizeof(THING)
, ...)
|
- kzalloc
+ kcalloc
(
- sizeof(THING) * COUNT_ID
+ COUNT_ID, sizeof(THING)
, ...)
|
- kzalloc
+ kcalloc
(
- sizeof(THING) * (COUNT_CONST)
+ COUNT_CONST, sizeof(THING)
, ...)
|
- kzalloc
+ kcalloc
(
- sizeof(THING) * COUNT_CONST
+ COUNT_CONST, sizeof(THING)
, ...)
)
// 2-factor product, only identifiers.
@@
identifier SIZE, COUNT;
@@
- kzalloc
+ kcalloc
(
- SIZE * COUNT
+ COUNT, SIZE
, ...)
// 3-factor product with 1 sizeof(type) or sizeof(expression), with
// redundant parens removed.
@@
expression THING;
identifier STRIDE, COUNT;
type TYPE;
@@
(
kzalloc(
- sizeof(TYPE) * (COUNT) * (STRIDE)
+ array3_size(COUNT, STRIDE, sizeof(TYPE))
, ...)
|
kzalloc(
- sizeof(TYPE) * (COUNT) * STRIDE
+ array3_size(COUNT, STRIDE, sizeof(TYPE))
, ...)
|
kzalloc(
- sizeof(TYPE) * COUNT * (STRIDE)
+ array3_size(COUNT, STRIDE, sizeof(TYPE))
, ...)
|
kzalloc(
- sizeof(TYPE) * COUNT * STRIDE
+ array3_size(COUNT, STRIDE, sizeof(TYPE))
, ...)
|
kzalloc(
- sizeof(THING) * (COUNT) * (STRIDE)
+ array3_size(COUNT, STRIDE, sizeof(THING))
, ...)
|
kzalloc(
- sizeof(THING) * (COUNT) * STRIDE
+ array3_size(COUNT, STRIDE, sizeof(THING))
, ...)
|
kzalloc(
- sizeof(THING) * COUNT * (STRIDE)
+ array3_size(COUNT, STRIDE, sizeof(THING))
, ...)
|
kzalloc(
- sizeof(THING) * COUNT * STRIDE
+ array3_size(COUNT, STRIDE, sizeof(THING))
, ...)
)
// 3-factor product with 2 sizeof(variable), with redundant parens removed.
@@
expression THING1, THING2;
identifier COUNT;
type TYPE1, TYPE2;
@@
(
kzalloc(
- sizeof(TYPE1) * sizeof(TYPE2) * COUNT
+ array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
, ...)
|
kzalloc(
- sizeof(TYPE1) * sizeof(THING2) * (COUNT)
+ array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
, ...)
|
kzalloc(
- sizeof(THING1) * sizeof(THING2) * COUNT
+ array3_size(COUNT, sizeof(THING1), sizeof(THING2))
, ...)
|
kzalloc(
- sizeof(THING1) * sizeof(THING2) * (COUNT)
+ array3_size(COUNT, sizeof(THING1), sizeof(THING2))
, ...)
|
kzalloc(
- sizeof(TYPE1) * sizeof(THING2) * COUNT
+ array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
, ...)
|
kzalloc(
- sizeof(TYPE1) * sizeof(THING2) * (COUNT)
+ array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
, ...)
)
// 3-factor product, only identifiers, with redundant parens removed.
@@
identifier STRIDE, SIZE, COUNT;
@@
(
kzalloc(
- (COUNT) * STRIDE * SIZE
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
|
kzalloc(
- COUNT * (STRIDE) * SIZE
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
|
kzalloc(
- COUNT * STRIDE * (SIZE)
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
|
kzalloc(
- (COUNT) * (STRIDE) * SIZE
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
|
kzalloc(
- COUNT * (STRIDE) * (SIZE)
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
|
kzalloc(
- (COUNT) * STRIDE * (SIZE)
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
|
kzalloc(
- (COUNT) * (STRIDE) * (SIZE)
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
|
kzalloc(
- COUNT * STRIDE * SIZE
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
)
// Any remaining multi-factor products, first at least 3-factor products,
// when they're not all constants...
@@
expression E1, E2, E3;
constant C1, C2, C3;
@@
(
kzalloc(C1 * C2 * C3, ...)
|
kzalloc(
- (E1) * E2 * E3
+ array3_size(E1, E2, E3)
, ...)
|
kzalloc(
- (E1) * (E2) * E3
+ array3_size(E1, E2, E3)
, ...)
|
kzalloc(
- (E1) * (E2) * (E3)
+ array3_size(E1, E2, E3)
, ...)
|
kzalloc(
- E1 * E2 * E3
+ array3_size(E1, E2, E3)
, ...)
)
// And then all remaining 2 factors products when they're not all constants,
// keeping sizeof() as the second factor argument.
@@
expression THING, E1, E2;
type TYPE;
constant C1, C2, C3;
@@
(
kzalloc(sizeof(THING) * C2, ...)
|
kzalloc(sizeof(TYPE) * C2, ...)
|
kzalloc(C1 * C2 * C3, ...)
|
kzalloc(C1 * C2, ...)
|
- kzalloc
+ kcalloc
(
- sizeof(TYPE) * (E2)
+ E2, sizeof(TYPE)
, ...)
|
- kzalloc
+ kcalloc
(
- sizeof(TYPE) * E2
+ E2, sizeof(TYPE)
, ...)
|
- kzalloc
+ kcalloc
(
- sizeof(THING) * (E2)
+ E2, sizeof(THING)
, ...)
|
- kzalloc
+ kcalloc
(
- sizeof(THING) * E2
+ E2, sizeof(THING)
, ...)
|
- kzalloc
+ kcalloc
(
- (E1) * E2
+ E1, E2
, ...)
|
- kzalloc
+ kcalloc
(
- (E1) * (E2)
+ E1, E2
, ...)
|
- kzalloc
+ kcalloc
(
- E1 * E2
+ E1, E2
, ...)
)
Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-13 05:03:40 +08:00
|
|
|
addrs = kcalloc(flen + 1, sizeof(*addrs), GFP_KERNEL);
|
powerpc/bpf: Add support for bpf constant blinding
In line with similar support for other architectures by Daniel Borkmann.
'MOD Default X' from test_bpf without constant blinding:
84 bytes emitted from JIT compiler (pass:3, flen:7)
d0000000058a4688 + <x>:
0: nop
4: nop
8: std r27,-40(r1)
c: std r28,-32(r1)
10: xor r8,r8,r8
14: xor r28,r28,r28
18: mr r27,r3
1c: li r8,66
20: cmpwi r28,0
24: bne 0x0000000000000030
28: li r8,0
2c: b 0x0000000000000044
30: divwu r9,r8,r28
34: mullw r9,r28,r9
38: subf r8,r9,r8
3c: rotlwi r8,r8,0
40: li r8,66
44: ld r27,-40(r1)
48: ld r28,-32(r1)
4c: mr r3,r8
50: blr
... and with constant blinding:
140 bytes emitted from JIT compiler (pass:3, flen:11)
d00000000bd6ab24 + <x>:
0: nop
4: nop
8: std r27,-40(r1)
c: std r28,-32(r1)
10: xor r8,r8,r8
14: xor r28,r28,r28
18: mr r27,r3
1c: lis r2,-22834
20: ori r2,r2,36083
24: rotlwi r2,r2,0
28: xori r2,r2,36017
2c: xoris r2,r2,42702
30: rotlwi r2,r2,0
34: mr r8,r2
38: rotlwi r8,r8,0
3c: cmpwi r28,0
40: bne 0x000000000000004c
44: li r8,0
48: b 0x000000000000007c
4c: divwu r9,r8,r28
50: mullw r9,r28,r9
54: subf r8,r9,r8
58: rotlwi r8,r8,0
5c: lis r2,-17137
60: ori r2,r2,39065
64: rotlwi r2,r2,0
68: xori r2,r2,39131
6c: xoris r2,r2,48399
70: rotlwi r2,r2,0
74: mr r8,r2
78: rotlwi r8,r8,0
7c: ld r27,-40(r1)
80: ld r28,-32(r1)
84: mr r3,r8
88: blr
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-09-24 04:35:02 +08:00
|
|
|
if (addrs == NULL) {
|
|
|
|
|
fp = org_fp;
|
2018-05-24 14:56:47 +08:00
|
|
|
goto out_addrs;
|
powerpc/bpf: Add support for bpf constant blinding
In line with similar support for other architectures by Daniel Borkmann.
'MOD Default X' from test_bpf without constant blinding:
84 bytes emitted from JIT compiler (pass:3, flen:7)
d0000000058a4688 + <x>:
0: nop
4: nop
8: std r27,-40(r1)
c: std r28,-32(r1)
10: xor r8,r8,r8
14: xor r28,r28,r28
18: mr r27,r3
1c: li r8,66
20: cmpwi r28,0
24: bne 0x0000000000000030
28: li r8,0
2c: b 0x0000000000000044
30: divwu r9,r8,r28
34: mullw r9,r28,r9
38: subf r8,r9,r8
3c: rotlwi r8,r8,0
40: li r8,66
44: ld r27,-40(r1)
48: ld r28,-32(r1)
4c: mr r3,r8
50: blr
... and with constant blinding:
140 bytes emitted from JIT compiler (pass:3, flen:11)
d00000000bd6ab24 + <x>:
0: nop
4: nop
8: std r27,-40(r1)
c: std r28,-32(r1)
10: xor r8,r8,r8
14: xor r28,r28,r28
18: mr r27,r3
1c: lis r2,-22834
20: ori r2,r2,36083
24: rotlwi r2,r2,0
28: xori r2,r2,36017
2c: xoris r2,r2,42702
30: rotlwi r2,r2,0
34: mr r8,r2
38: rotlwi r8,r8,0
3c: cmpwi r28,0
40: bne 0x000000000000004c
44: li r8,0
48: b 0x000000000000007c
4c: divwu r9,r8,r28
50: mullw r9,r28,r9
54: subf r8,r9,r8
58: rotlwi r8,r8,0
5c: lis r2,-17137
60: ori r2,r2,39065
64: rotlwi r2,r2,0
68: xori r2,r2,39131
6c: xoris r2,r2,48399
70: rotlwi r2,r2,0
74: mr r8,r2
78: rotlwi r8,r8,0
7c: ld r27,-40(r1)
80: ld r28,-32(r1)
84: mr r3,r8
88: blr
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-09-24 04:35:02 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
memset(&cgctx, 0, sizeof(struct codegen_context));
|
2016-06-23 00:25:07 +08:00
|
|
|
|
2017-09-02 02:53:01 +08:00
|
|
|
/* Make sure that the stack is quadword aligned. */
|
|
|
|
|
cgctx.stack_size = round_up(fp->aux->stack_depth, 16);
|
|
|
|
|
|
2016-06-23 00:25:07 +08:00
|
|
|
/* Scouting faux-generate pass 0 */
|
2018-05-24 14:56:47 +08:00
|
|
|
if (bpf_jit_build_body(fp, 0, &cgctx, addrs, false)) {
|
2016-06-23 00:25:07 +08:00
|
|
|
/* We hit something illegal or unsupported. */
|
powerpc/bpf: Add support for bpf constant blinding
In line with similar support for other architectures by Daniel Borkmann.
'MOD Default X' from test_bpf without constant blinding:
84 bytes emitted from JIT compiler (pass:3, flen:7)
d0000000058a4688 + <x>:
0: nop
4: nop
8: std r27,-40(r1)
c: std r28,-32(r1)
10: xor r8,r8,r8
14: xor r28,r28,r28
18: mr r27,r3
1c: li r8,66
20: cmpwi r28,0
24: bne 0x0000000000000030
28: li r8,0
2c: b 0x0000000000000044
30: divwu r9,r8,r28
34: mullw r9,r28,r9
38: subf r8,r9,r8
3c: rotlwi r8,r8,0
40: li r8,66
44: ld r27,-40(r1)
48: ld r28,-32(r1)
4c: mr r3,r8
50: blr
... and with constant blinding:
140 bytes emitted from JIT compiler (pass:3, flen:11)
d00000000bd6ab24 + <x>:
0: nop
4: nop
8: std r27,-40(r1)
c: std r28,-32(r1)
10: xor r8,r8,r8
14: xor r28,r28,r28
18: mr r27,r3
1c: lis r2,-22834
20: ori r2,r2,36083
24: rotlwi r2,r2,0
28: xori r2,r2,36017
2c: xoris r2,r2,42702
30: rotlwi r2,r2,0
34: mr r8,r2
38: rotlwi r8,r8,0
3c: cmpwi r28,0
40: bne 0x000000000000004c
44: li r8,0
48: b 0x000000000000007c
4c: divwu r9,r8,r28
50: mullw r9,r28,r9
54: subf r8,r9,r8
58: rotlwi r8,r8,0
5c: lis r2,-17137
60: ori r2,r2,39065
64: rotlwi r2,r2,0
68: xori r2,r2,39131
6c: xoris r2,r2,48399
70: rotlwi r2,r2,0
74: mr r8,r2
78: rotlwi r8,r8,0
7c: ld r27,-40(r1)
80: ld r28,-32(r1)
84: mr r3,r8
88: blr
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-09-24 04:35:02 +08:00
|
|
|
fp = org_fp;
|
2018-05-24 14:56:47 +08:00
|
|
|
goto out_addrs;
|
powerpc/bpf: Add support for bpf constant blinding
In line with similar support for other architectures by Daniel Borkmann.
'MOD Default X' from test_bpf without constant blinding:
84 bytes emitted from JIT compiler (pass:3, flen:7)
d0000000058a4688 + <x>:
0: nop
4: nop
8: std r27,-40(r1)
c: std r28,-32(r1)
10: xor r8,r8,r8
14: xor r28,r28,r28
18: mr r27,r3
1c: li r8,66
20: cmpwi r28,0
24: bne 0x0000000000000030
28: li r8,0
2c: b 0x0000000000000044
30: divwu r9,r8,r28
34: mullw r9,r28,r9
38: subf r8,r9,r8
3c: rotlwi r8,r8,0
40: li r8,66
44: ld r27,-40(r1)
48: ld r28,-32(r1)
4c: mr r3,r8
50: blr
... and with constant blinding:
140 bytes emitted from JIT compiler (pass:3, flen:11)
d00000000bd6ab24 + <x>:
0: nop
4: nop
8: std r27,-40(r1)
c: std r28,-32(r1)
10: xor r8,r8,r8
14: xor r28,r28,r28
18: mr r27,r3
1c: lis r2,-22834
20: ori r2,r2,36083
24: rotlwi r2,r2,0
28: xori r2,r2,36017
2c: xoris r2,r2,42702
30: rotlwi r2,r2,0
34: mr r8,r2
38: rotlwi r8,r8,0
3c: cmpwi r28,0
40: bne 0x000000000000004c
44: li r8,0
48: b 0x000000000000007c
4c: divwu r9,r8,r28
50: mullw r9,r28,r9
54: subf r8,r9,r8
58: rotlwi r8,r8,0
5c: lis r2,-17137
60: ori r2,r2,39065
64: rotlwi r2,r2,0
68: xori r2,r2,39131
6c: xoris r2,r2,48399
70: rotlwi r2,r2,0
74: mr r8,r2
78: rotlwi r8,r8,0
7c: ld r27,-40(r1)
80: ld r28,-32(r1)
84: mr r3,r8
88: blr
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-09-24 04:35:02 +08:00
|
|
|
}
|
2016-06-23 00:25:07 +08:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Pretend to build prologue, given the features we've seen. This will
|
|
|
|
|
* update ctgtx.idx as it pretends to output instructions, then we can
|
|
|
|
|
* calculate total size from idx.
|
|
|
|
|
*/
|
|
|
|
|
bpf_jit_build_prologue(0, &cgctx);
|
|
|
|
|
bpf_jit_build_epilogue(0, &cgctx);
|
|
|
|
|
|
|
|
|
|
proglen = cgctx.idx * 4;
|
|
|
|
|
alloclen = proglen + FUNCTION_DESCR_SIZE;
|
|
|
|
|
|
|
|
|
|
bpf_hdr = bpf_jit_binary_alloc(alloclen, &image, 4,
|
|
|
|
|
bpf_jit_fill_ill_insns);
|
powerpc/bpf: Add support for bpf constant blinding
In line with similar support for other architectures by Daniel Borkmann.
'MOD Default X' from test_bpf without constant blinding:
84 bytes emitted from JIT compiler (pass:3, flen:7)
d0000000058a4688 + <x>:
0: nop
4: nop
8: std r27,-40(r1)
c: std r28,-32(r1)
10: xor r8,r8,r8
14: xor r28,r28,r28
18: mr r27,r3
1c: li r8,66
20: cmpwi r28,0
24: bne 0x0000000000000030
28: li r8,0
2c: b 0x0000000000000044
30: divwu r9,r8,r28
34: mullw r9,r28,r9
38: subf r8,r9,r8
3c: rotlwi r8,r8,0
40: li r8,66
44: ld r27,-40(r1)
48: ld r28,-32(r1)
4c: mr r3,r8
50: blr
... and with constant blinding:
140 bytes emitted from JIT compiler (pass:3, flen:11)
d00000000bd6ab24 + <x>:
0: nop
4: nop
8: std r27,-40(r1)
c: std r28,-32(r1)
10: xor r8,r8,r8
14: xor r28,r28,r28
18: mr r27,r3
1c: lis r2,-22834
20: ori r2,r2,36083
24: rotlwi r2,r2,0
28: xori r2,r2,36017
2c: xoris r2,r2,42702
30: rotlwi r2,r2,0
34: mr r8,r2
38: rotlwi r8,r8,0
3c: cmpwi r28,0
40: bne 0x000000000000004c
44: li r8,0
48: b 0x000000000000007c
4c: divwu r9,r8,r28
50: mullw r9,r28,r9
54: subf r8,r9,r8
58: rotlwi r8,r8,0
5c: lis r2,-17137
60: ori r2,r2,39065
64: rotlwi r2,r2,0
68: xori r2,r2,39131
6c: xoris r2,r2,48399
70: rotlwi r2,r2,0
74: mr r8,r2
78: rotlwi r8,r8,0
7c: ld r27,-40(r1)
80: ld r28,-32(r1)
84: mr r3,r8
88: blr
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-09-24 04:35:02 +08:00
|
|
|
if (!bpf_hdr) {
|
|
|
|
|
fp = org_fp;
|
2018-05-24 14:56:47 +08:00
|
|
|
goto out_addrs;
|
powerpc/bpf: Add support for bpf constant blinding
In line with similar support for other architectures by Daniel Borkmann.
'MOD Default X' from test_bpf without constant blinding:
84 bytes emitted from JIT compiler (pass:3, flen:7)
d0000000058a4688 + <x>:
0: nop
4: nop
8: std r27,-40(r1)
c: std r28,-32(r1)
10: xor r8,r8,r8
14: xor r28,r28,r28
18: mr r27,r3
1c: li r8,66
20: cmpwi r28,0
24: bne 0x0000000000000030
28: li r8,0
2c: b 0x0000000000000044
30: divwu r9,r8,r28
34: mullw r9,r28,r9
38: subf r8,r9,r8
3c: rotlwi r8,r8,0
40: li r8,66
44: ld r27,-40(r1)
48: ld r28,-32(r1)
4c: mr r3,r8
50: blr
... and with constant blinding:
140 bytes emitted from JIT compiler (pass:3, flen:11)
d00000000bd6ab24 + <x>:
0: nop
4: nop
8: std r27,-40(r1)
c: std r28,-32(r1)
10: xor r8,r8,r8
14: xor r28,r28,r28
18: mr r27,r3
1c: lis r2,-22834
20: ori r2,r2,36083
24: rotlwi r2,r2,0
28: xori r2,r2,36017
2c: xoris r2,r2,42702
30: rotlwi r2,r2,0
34: mr r8,r2
38: rotlwi r8,r8,0
3c: cmpwi r28,0
40: bne 0x000000000000004c
44: li r8,0
48: b 0x000000000000007c
4c: divwu r9,r8,r28
50: mullw r9,r28,r9
54: subf r8,r9,r8
58: rotlwi r8,r8,0
5c: lis r2,-17137
60: ori r2,r2,39065
64: rotlwi r2,r2,0
68: xori r2,r2,39131
6c: xoris r2,r2,48399
70: rotlwi r2,r2,0
74: mr r8,r2
78: rotlwi r8,r8,0
7c: ld r27,-40(r1)
80: ld r28,-32(r1)
84: mr r3,r8
88: blr
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-09-24 04:35:02 +08:00
|
|
|
}
|
2016-06-23 00:25:07 +08:00
|
|
|
|
2018-05-24 14:56:47 +08:00
|
|
|
skip_init_ctx:
|
2016-06-23 00:25:07 +08:00
|
|
|
code_base = (u32 *)(image + FUNCTION_DESCR_SIZE);
|
|
|
|
|
|
|
|
|
|
/* Code generation passes 1-2 */
|
|
|
|
|
for (pass = 1; pass < 3; pass++) {
|
|
|
|
|
/* Now build the prologue, body code & epilogue for real. */
|
|
|
|
|
cgctx.idx = 0;
|
|
|
|
|
bpf_jit_build_prologue(code_base, &cgctx);
|
2018-05-24 14:56:47 +08:00
|
|
|
bpf_jit_build_body(fp, code_base, &cgctx, addrs, extra_pass);
|
2016-06-23 00:25:07 +08:00
|
|
|
bpf_jit_build_epilogue(code_base, &cgctx);
|
|
|
|
|
|
|
|
|
|
if (bpf_jit_enable > 1)
|
|
|
|
|
pr_info("Pass %d: shrink = %d, seen = 0x%x\n", pass,
|
|
|
|
|
proglen - (cgctx.idx * 4), cgctx.seen);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if (bpf_jit_enable > 1)
|
|
|
|
|
/*
|
|
|
|
|
* Note that we output the base address of the code_base
|
|
|
|
|
* rather than image, since opcodes are in code_base.
|
|
|
|
|
*/
|
|
|
|
|
bpf_jit_dump(flen, proglen, pass, code_base);
|
|
|
|
|
|
|
|
|
|
#ifdef PPC64_ELF_ABI_v1
|
2017-01-14 01:10:00 +08:00
|
|
|
/* Function descriptor nastiness: Address + TOC */
|
|
|
|
|
((u64 *)image)[0] = (u64)code_base;
|
|
|
|
|
((u64 *)image)[1] = local_paca->kernel_toc;
|
2016-06-23 00:25:07 +08:00
|
|
|
#endif
|
2017-01-14 01:10:00 +08:00
|
|
|
|
|
|
|
|
fp->bpf_func = (void *)image;
|
|
|
|
|
fp->jited = 1;
|
2017-06-06 03:15:51 +08:00
|
|
|
fp->jited_len = alloclen;
|
2016-06-23 00:25:07 +08:00
|
|
|
|
2017-01-14 01:10:01 +08:00
|
|
|
bpf_flush_icache(bpf_hdr, (u8 *)bpf_hdr + (bpf_hdr->pages * PAGE_SIZE));
|
2018-05-24 14:56:47 +08:00
|
|
|
if (!fp->is_func || extra_pass) {
|
|
|
|
|
out_addrs:
|
|
|
|
|
kfree(addrs);
|
|
|
|
|
kfree(jit_data);
|
|
|
|
|
fp->aux->jit_data = NULL;
|
|
|
|
|
} else {
|
|
|
|
|
jit_data->addrs = addrs;
|
|
|
|
|
jit_data->ctx = cgctx;
|
|
|
|
|
jit_data->proglen = proglen;
|
|
|
|
|
jit_data->image = image;
|
|
|
|
|
jit_data->header = bpf_hdr;
|
|
|
|
|
}
|
2016-06-23 00:25:07 +08:00
|
|
|
|
|
|
|
|
out:
|
powerpc/bpf: Add support for bpf constant blinding
In line with similar support for other architectures by Daniel Borkmann.
'MOD Default X' from test_bpf without constant blinding:
84 bytes emitted from JIT compiler (pass:3, flen:7)
d0000000058a4688 + <x>:
0: nop
4: nop
8: std r27,-40(r1)
c: std r28,-32(r1)
10: xor r8,r8,r8
14: xor r28,r28,r28
18: mr r27,r3
1c: li r8,66
20: cmpwi r28,0
24: bne 0x0000000000000030
28: li r8,0
2c: b 0x0000000000000044
30: divwu r9,r8,r28
34: mullw r9,r28,r9
38: subf r8,r9,r8
3c: rotlwi r8,r8,0
40: li r8,66
44: ld r27,-40(r1)
48: ld r28,-32(r1)
4c: mr r3,r8
50: blr
... and with constant blinding:
140 bytes emitted from JIT compiler (pass:3, flen:11)
d00000000bd6ab24 + <x>:
0: nop
4: nop
8: std r27,-40(r1)
c: std r28,-32(r1)
10: xor r8,r8,r8
14: xor r28,r28,r28
18: mr r27,r3
1c: lis r2,-22834
20: ori r2,r2,36083
24: rotlwi r2,r2,0
28: xori r2,r2,36017
2c: xoris r2,r2,42702
30: rotlwi r2,r2,0
34: mr r8,r2
38: rotlwi r8,r8,0
3c: cmpwi r28,0
40: bne 0x000000000000004c
44: li r8,0
48: b 0x000000000000007c
4c: divwu r9,r8,r28
50: mullw r9,r28,r9
54: subf r8,r9,r8
58: rotlwi r8,r8,0
5c: lis r2,-17137
60: ori r2,r2,39065
64: rotlwi r2,r2,0
68: xori r2,r2,39131
6c: xoris r2,r2,48399
70: rotlwi r2,r2,0
74: mr r8,r2
78: rotlwi r8,r8,0
7c: ld r27,-40(r1)
80: ld r28,-32(r1)
84: mr r3,r8
88: blr
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-09-24 04:35:02 +08:00
|
|
|
if (bpf_blinded)
|
|
|
|
|
bpf_jit_prog_release_other(fp, fp == org_fp ? tmp_fp : org_fp);
|
|
|
|
|
|
2016-06-23 00:25:07 +08:00
|
|
|
return fp;
|
|
|
|
|
}
|
|
|
|
|
|
bpf: make jited programs visible in traces
Long standing issue with JITed programs is that stack traces from
function tracing check whether a given address is kernel code
through {__,}kernel_text_address(), which checks for code in core
kernel, modules and dynamically allocated ftrace trampolines. But
what is still missing is BPF JITed programs (interpreted programs
are not an issue as __bpf_prog_run() will be attributed to them),
thus when a stack trace is triggered, the code walking the stack
won't see any of the JITed ones. The same for address correlation
done from user space via reading /proc/kallsyms. This is read by
tools like perf, but the latter is also useful for permanent live
tracing with eBPF itself in combination with stack maps when other
eBPF types are part of the callchain. See offwaketime example on
dumping stack from a map.
This work tries to tackle that issue by making the addresses and
symbols known to the kernel. The lookup from *kernel_text_address()
is implemented through a latched RB tree that can be read under
RCU in fast-path that is also shared for symbol/size/offset lookup
for a specific given address in kallsyms. The slow-path iteration
through all symbols in the seq file done via RCU list, which holds
a tiny fraction of all exported ksyms, usually below 0.1 percent.
Function symbols are exported as bpf_prog_<tag>, in order to aide
debugging and attribution. This facility is currently enabled for
root-only when bpf_jit_kallsyms is set to 1, and disabled if hardening
is active in any mode. The rationale behind this is that still a lot
of systems ship with world read permissions on kallsyms thus addresses
should not get suddenly exposed for them. If that situation gets
much better in future, we always have the option to change the
default on this. Likewise, unprivileged programs are not allowed
to add entries there either, but that is less of a concern as most
such programs types relevant in this context are for root-only anyway.
If enabled, call graphs and stack traces will then show a correct
attribution; one example is illustrated below, where the trace is
now visible in tooling such as perf script --kallsyms=/proc/kallsyms
and friends.
Before:
7fff8166889d bpf_clone_redirect+0x80007f0020ed (/lib/modules/4.9.0-rc8+/build/vmlinux)
f5d80 __sendmsg_nocancel+0xffff006451f1a007 (/usr/lib64/libc-2.18.so)
After:
7fff816688b7 bpf_clone_redirect+0x80007f002107 (/lib/modules/4.9.0-rc8+/build/vmlinux)
7fffa0575728 bpf_prog_33c45a467c9e061a+0x8000600020fb (/lib/modules/4.9.0-rc8+/build/vmlinux)
7fffa07ef1fc cls_bpf_classify+0x8000600020dc (/lib/modules/4.9.0-rc8+/build/vmlinux)
7fff81678b68 tc_classify+0x80007f002078 (/lib/modules/4.9.0-rc8+/build/vmlinux)
7fff8164d40b __netif_receive_skb_core+0x80007f0025fb (/lib/modules/4.9.0-rc8+/build/vmlinux)
7fff8164d718 __netif_receive_skb+0x80007f002018 (/lib/modules/4.9.0-rc8+/build/vmlinux)
7fff8164e565 process_backlog+0x80007f002095 (/lib/modules/4.9.0-rc8+/build/vmlinux)
7fff8164dc71 net_rx_action+0x80007f002231 (/lib/modules/4.9.0-rc8+/build/vmlinux)
7fff81767461 __softirqentry_text_start+0x80007f0020d1 (/lib/modules/4.9.0-rc8+/build/vmlinux)
7fff817658ac do_softirq_own_stack+0x80007f00201c (/lib/modules/4.9.0-rc8+/build/vmlinux)
7fff810a2c20 do_softirq+0x80007f002050 (/lib/modules/4.9.0-rc8+/build/vmlinux)
7fff810a2cb5 __local_bh_enable_ip+0x80007f002085 (/lib/modules/4.9.0-rc8+/build/vmlinux)
7fff8168d452 ip_finish_output2+0x80007f002152 (/lib/modules/4.9.0-rc8+/build/vmlinux)
7fff8168ea3d ip_finish_output+0x80007f00217d (/lib/modules/4.9.0-rc8+/build/vmlinux)
7fff8168f2af ip_output+0x80007f00203f (/lib/modules/4.9.0-rc8+/build/vmlinux)
[...]
7fff81005854 do_syscall_64+0x80007f002054 (/lib/modules/4.9.0-rc8+/build/vmlinux)
7fff817649eb return_from_SYSCALL_64+0x80007f002000 (/lib/modules/4.9.0-rc8+/build/vmlinux)
f5d80 __sendmsg_nocancel+0xffff01c484812007 (/usr/lib64/libc-2.18.so)
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-17 05:24:50 +08:00
|
|
|
/* Overriding bpf_jit_free() as we don't set images read-only. */
|
2016-06-23 00:25:07 +08:00
|
|
|
void bpf_jit_free(struct bpf_prog *fp)
|
|
|
|
|
{
|
|
|
|
|
unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK;
|
|
|
|
|
struct bpf_binary_header *bpf_hdr = (void *)addr;
|
|
|
|
|
|
|
|
|
|
if (fp->jited)
|
|
|
|
|
bpf_jit_binary_free(bpf_hdr);
|
|
|
|
|
|
|
|
|
|
bpf_prog_unlock_free(fp);
|
|
|
|
|
}
|