static void bpf_jit_emit_func_call(u32 *image, struct codegen_context *ctx, u64 func)
{
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();
#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.
*/
PPC_BPF_LL(2, 12, 8);
/* Load actual entry point from function descriptor */
PPC_BPF_LL(12, 12, 0);
#endif
PPC_MTLR(12);
PPC_BLRL();
}
static void bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx,
u64 func)
{
#ifdef PPC64_ELF_ABI_v1
/* func points to the function descriptor */
PPC_LI64(b2p[TMP_REG_2], func);
/* Load actual entry point from function descriptor */
PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_2], 0);
/* ... and move it to LR */
PPC_MTLR(b2p[TMP_REG_1]);
/*
* 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.
*/
PPC_BPF_LL(2, b2p[TMP_REG_2], 8);
#else
/* We can clobber r12 */
PPC_FUNC_ADDR(12, func);
PPC_MTLR(12);
#endif
PPC_BLRL();
}
/* Assemble the body code between the prologue & epilogue. */
static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
struct codegen_context *ctx,
unsigned int *addrs)
{
const struct sock_filter *filter = fp->insns;
int flen = fp->len;
u8 *func;
unsigned int true_cond;
int i;
/* Start of epilogue code */
unsigned int exit_addr = addrs[flen];
for (i = 0; i < flen; i++) {
unsigned int K = filter[i].k;
u16 code = bpf_anc_helper(&filter[i]);
/*
* addrs[] maps a BPF bytecode address into a real offset from
* the start of the body code.
*/
addrs[i] = ctx->idx * 4;
switch (code) {
/*** ALU ops ***/
case BPF_ALU | BPF_ADD | BPF_X: /* A += X; */
ctx->seen |= SEEN_XREG;
PPC_ADD(r_A, r_A, r_X);
break;
case BPF_ALU | BPF_ADD | BPF_K: /* A += K; */
if (!K)
break;
PPC_ADDI(r_A, r_A, IMM_L(K));
if (K >= 32768)
PPC_ADDIS(r_A, r_A, IMM_HA(K));
break;
case BPF_ALU | BPF_SUB | BPF_X: /* A -= X; */
ctx->seen |= SEEN_XREG;
PPC_SUB(r_A, r_A, r_X);
break;
case BPF_ALU | BPF_SUB | BPF_K: /* A -= K */
if (!K)
break;
PPC_ADDI(r_A, r_A, IMM_L(-K));
if (K >= 32768)
PPC_ADDIS(r_A, r_A, IMM_HA(-K));
break;
case BPF_ALU | BPF_MUL | BPF_X: /* A *= X; */
ctx->seen |= SEEN_XREG;
PPC_MUL(r_A, r_A, r_X);
break;
case BPF_ALU | BPF_MUL | BPF_K: /* A *= K */
if (K < 32768)
PPC_MULI(r_A, r_A, K);
else {
PPC_LI32(r_scratch1, K);
PPC_MUL(r_A, r_A, r_scratch1);
}
break;
case BPF_ALU | BPF_MOD | BPF_X: /* A %= X; */
ctx->seen |= SEEN_XREG;
PPC_CMPWI(r_X, 0);
if (ctx->pc_ret0 != -1) {
PPC_BCC(COND_EQ, addrs[ctx->pc_ret0]);
} else {
PPC_BCC_SHORT(COND_NE, (ctx->idx*4)+12);
PPC_LI(r_ret, 0);
PPC_JMP(exit_addr);
}
PPC_DIVWU(r_scratch1, r_A, r_X);
PPC_MUL(r_scratch1, r_X, r_scratch1);
PPC_SUB(r_A, r_A, r_scratch1);
break;
case BPF_ALU | BPF_MOD | BPF_K: /* A %= K; */
PPC_LI32(r_scratch2, K);
PPC_DIVWU(r_scratch1, r_A, r_scratch2);
PPC_MUL(r_scratch1, r_scratch2, r_scratch1);
PPC_SUB(r_A, r_A, r_scratch1);
break;
case BPF_ALU | BPF_DIV | BPF_X: /* A /= X; */
ctx->seen |= SEEN_XREG;
PPC_CMPWI(r_X, 0);
if (ctx->pc_ret0 != -1) {
PPC_BCC(COND_EQ, addrs[ctx->pc_ret0]);
} else {
/*
* Exit, returning 0; first pass hits here
* (longer worst-case code size).
*/
PPC_BCC_SHORT(COND_NE, (ctx->idx*4)+12);
PPC_LI(r_ret, 0);
PPC_JMP(exit_addr);
}
PPC_DIVWU(r_A, r_A, r_X);
break;
case BPF_ALU | BPF_DIV | BPF_K: /* A /= K */
if (K == 1)
break;
PPC_LI32(r_scratch1, K);
PPC_DIVWU(r_A, r_A, r_scratch1);
break;
case BPF_ALU | BPF_AND | BPF_X:
ctx->seen |= SEEN_XREG;
PPC_AND(r_A, r_A, r_X);
break;
case BPF_ALU | BPF_AND | BPF_K:
if (!IMM_H(K))
PPC_ANDI(r_A, r_A, K);
else {
PPC_LI32(r_scratch1, K);
PPC_AND(r_A, r_A, r_scratch1);
}
break;
case BPF_ALU | BPF_OR | BPF_X:
ctx->seen |= SEEN_XREG;
PPC_OR(r_A, r_A, r_X);
break;
case BPF_ALU | BPF_OR | BPF_K:
if (IMM_L(K))
PPC_ORI(r_A, r_A, IMM_L(K));
if (K >= 65536)
PPC_ORIS(r_A, r_A, IMM_H(K));
break;
case BPF_ANC | SKF_AD_ALU_XOR_X:
case BPF_ALU | BPF_XOR | BPF_X: /* A ^= X */
ctx->seen |= SEEN_XREG;
PPC_XOR(r_A, r_A, r_X);
break;
case BPF_ALU | BPF_XOR | BPF_K: /* A ^= K */
if (IMM_L(K))
PPC_XORI(r_A, r_A, IMM_L(K));
if (K >= 65536)
PPC_XORIS(r_A, r_A, IMM_H(K));
break;
case BPF_ALU | BPF_LSH | BPF_X: /* A <<= X; */
ctx->seen |= SEEN_XREG;
PPC_SLW(r_A, r_A, r_X);
break;
case BPF_ALU | BPF_LSH | BPF_K:
if (K == 0)
break;
else
PPC_SLWI(r_A, r_A, K);
break;
case BPF_ALU | BPF_RSH | BPF_X: /* A >>= X; */
ctx->seen |= SEEN_XREG;
PPC_SRW(r_A, r_A, r_X);
break;
case BPF_ALU | BPF_RSH | BPF_K: /* A >>= K; */
if (K == 0)
break;
else
PPC_SRWI(r_A, r_A, K);
break;
case BPF_ALU | BPF_NEG:
PPC_NEG(r_A, r_A);
break;
case BPF_RET | BPF_K:
PPC_LI32(r_ret, K);
if (!K) {
if (ctx->pc_ret0 == -1)
ctx->pc_ret0 = i;
}
/*
* If this isn't the very last instruction, branch to
* the epilogue if we've stuff to clean up. Otherwise,
* if there's nothing to tidy, just return. If we /are/
* the last instruction, we're about to fall through to
* the epilogue to return.
*/
if (i != flen - 1) {
/*
* Note: 'seen' is properly valid only on pass
* #2. Both parts of this conditional are the
* same instruction size though, meaning the
* first pass will still correctly determine the
* code size/addresses.
*/
if (ctx->seen)
PPC_JMP(exit_addr);
else
PPC_BLR();
}
break;
case BPF_RET | BPF_A:
PPC_MR(r_ret, r_A);
if (i != flen - 1) {
if (ctx->seen)
PPC_JMP(exit_addr);
else
PPC_BLR();
}
break;
case BPF_MISC | BPF_TAX: /* X = A */
PPC_MR(r_X, r_A);
break;
case BPF_MISC | BPF_TXA: /* A = X */
ctx->seen |= SEEN_XREG;
PPC_MR(r_A, r_X);
break;
/*** Constant loads/M[] access ***/
case BPF_LD | BPF_IMM: /* A = K */
PPC_LI32(r_A, K);
break;
case BPF_LDX | BPF_IMM: /* X = K */
PPC_LI32(r_X, K);
break;
case BPF_LD | BPF_MEM: /* A = mem[K] */
PPC_MR(r_A, r_M + (K & 0xf));
ctx->seen |= SEEN_MEM | (1<<(K & 0xf));
break;
case BPF_LDX | BPF_MEM: /* X = mem[K] */
PPC_MR(r_X, r_M + (K & 0xf));
ctx->seen |= SEEN_MEM | (1<<(K & 0xf));
break;
case BPF_ST: /* mem[K] = A */
PPC_MR(r_M + (K & 0xf), r_A);
ctx->seen |= SEEN_MEM | (1<<(K & 0xf));
break;
case BPF_STX: /* mem[K] = X */
PPC_MR(r_M + (K & 0xf), r_X);
ctx->seen |= SEEN_XREG | SEEN_MEM | (1<<(K & 0xf));
break;
case BPF_LD | BPF_W | BPF_LEN: /* A = skb->len; */
BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4);
PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, len));
break;
case BPF_LDX | BPF_W | BPF_LEN: /* X = skb->len; */
PPC_LWZ_OFFS(r_X, r_skb, offsetof(struct sk_buff, len));
break;
/*** Ancillary info loads ***/
case BPF_ANC | SKF_AD_PROTOCOL: /* A = ntohs(skb->protocol); */
BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
protocol) != 2);
PPC_NTOHS_OFFS(r_A, r_skb, offsetof(struct sk_buff,
protocol));
break;
case BPF_ANC | SKF_AD_IFINDEX:
PPC_LD_OFFS(r_scratch1, r_skb, offsetof(struct sk_buff,
dev));
PPC_CMPDI(r_scratch1, 0);
if (ctx->pc_ret0 != -1) {
PPC_BCC(COND_EQ, addrs[ctx->pc_ret0]);
} else {
/* Exit, returning 0; first pass hits here. */
PPC_BCC_SHORT(COND_NE, (ctx->idx*4)+12);
PPC_LI(r_ret, 0);
PPC_JMP(exit_addr);
}
BUILD_BUG_ON(FIELD_SIZEOF(struct net_device,
ifindex) != 4);
PPC_LWZ_OFFS(r_A, r_scratch1,
offsetof(struct net_device, ifindex));
break;
case BPF_ANC | SKF_AD_MARK:
BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);
PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff,
mark));
break;
case BPF_ANC | SKF_AD_RXHASH:
BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);
PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff,
hash));
break;
case BPF_ANC | SKF_AD_VLAN_TAG:
case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT:
BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000);
PPC_LHZ_OFFS(r_A, r_skb, offsetof(struct sk_buff,
vlan_tci));
if (code == (BPF_ANC | SKF_AD_VLAN_TAG)) {
PPC_ANDI(r_A, r_A, ~VLAN_TAG_PRESENT);
} else {
PPC_ANDI(r_A, r_A, VLAN_TAG_PRESENT);
PPC_SRWI(r_A, r_A, 12);
}
break;
case BPF_ANC | SKF_AD_QUEUE:
BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
queue_mapping) != 2);
PPC_LHZ_OFFS(r_A, r_skb, offsetof(struct sk_buff,
queue_mapping));
break;
case BPF_ANC | SKF_AD_CPU:
#ifdef CONFIG_SMP
/*
* PACA ptr is r13:
* raw_smp_processor_id() = local_paca->paca_index
*/
BUILD_BUG_ON(FIELD_SIZEOF(struct paca_struct,
paca_index) != 2);
PPC_LHZ_OFFS(r_A, 13,
offsetof(struct paca_struct, paca_index));
#else
PPC_LI(r_A, 0);
#endif
break;
/*** Absolute loads from packet header/data ***/
case BPF_LD | BPF_W | BPF_ABS:
func = CHOOSE_LOAD_FUNC(K, sk_load_word);
goto common_load;
case BPF_LD | BPF_H | BPF_ABS:
func = CHOOSE_LOAD_FUNC(K, sk_load_half);
goto common_load;
case BPF_LD | BPF_B | BPF_ABS:
func = CHOOSE_LOAD_FUNC(K, sk_load_byte);
common_load:
/* Load from [K]. */
ctx->seen |= SEEN_DATAREF;
PPC_LI64(r_scratch1, func);
PPC_MTLR(r_scratch1);
PPC_LI32(r_addr, K);
PPC_BLRL();
/*
* Helper returns 'lt' condition on error, and an
* appropriate return value in r3
*/
PPC_BCC(COND_LT, exit_addr);
break;
/*** Indirect loads from packet header/data ***/
case BPF_LD | BPF_W | BPF_IND:
func = sk_load_word;
goto common_load_ind;
case BPF_LD | BPF_H | BPF_IND:
func = sk_load_half;
goto common_load_ind;
case BPF_LD | BPF_B | BPF_IND:
func = sk_load_byte;
common_load_ind:
/*
* Load from [X + K]. Negative offsets are tested for
* in the helper functions.
*/
ctx->seen |= SEEN_DATAREF | SEEN_XREG;
PPC_LI64(r_scratch1, func);
PPC_MTLR(r_scratch1);
PPC_ADDI(r_addr, r_X, IMM_L(K));
if (K >= 32768)
PPC_ADDIS(r_addr, r_addr, IMM_HA(K));
PPC_BLRL();
/* If error, cr0.LT set */
PPC_BCC(COND_LT, exit_addr);
break;
case BPF_LDX | BPF_B | BPF_MSH:
func = CHOOSE_LOAD_FUNC(K, sk_load_byte_msh);
goto common_load;
break;
/*** Jump and branches ***/
case BPF_JMP | BPF_JA:
if (K != 0)
PPC_JMP(addrs[i + 1 + K]);
break;
case BPF_JMP | BPF_JGT | BPF_K:
case BPF_JMP | BPF_JGT | BPF_X:
true_cond = COND_GT;
goto cond_branch;
case BPF_JMP | BPF_JGE | BPF_K:
case BPF_JMP | BPF_JGE | BPF_X:
true_cond = COND_GE;
goto cond_branch;
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_JSET | BPF_K:
case BPF_JMP | BPF_JSET | BPF_X:
true_cond = COND_NE;
/* Fall through */
cond_branch:
/* same targets, can avoid doing the test :) */
if (filter[i].jt == filter[i].jf) {
if (filter[i].jt > 0)
PPC_JMP(addrs[i + 1 + filter[i].jt]);
break;
}
switch (code) {
case BPF_JMP | BPF_JGT | BPF_X:
case BPF_JMP | BPF_JGE | BPF_X:
case BPF_JMP | BPF_JEQ | BPF_X:
ctx->seen |= SEEN_XREG;
PPC_CMPLW(r_A, r_X);
break;
case BPF_JMP | BPF_JSET | BPF_X:
ctx->seen |= SEEN_XREG;
PPC_AND_DOT(r_scratch1, r_A, r_X);
break;
case BPF_JMP | BPF_JEQ | BPF_K:
case BPF_JMP | BPF_JGT | BPF_K:
case BPF_JMP | BPF_JGE | BPF_K:
if (K < 32768)
PPC_CMPLWI(r_A, K);
else {
PPC_LI32(r_scratch1, K);
PPC_CMPLW(r_A, r_scratch1);
}
break;
case BPF_JMP | BPF_JSET | BPF_K:
if (K < 32768)
/* PPC_ANDI is /only/ dot-form */
PPC_ANDI(r_scratch1, r_A, K);
else {
PPC_LI32(r_scratch1, K);
PPC_AND_DOT(r_scratch1, r_A,
r_scratch1);
}
break;
}
/* Sometimes branches are constructed "backward", with
* the false path being the branch and true path being
* a fallthrough to the next instruction.
*/
if (filter[i].jt == 0)
/* Swap the sense of the branch */
PPC_BCC(true_cond ^ COND_CMP_TRUE,
addrs[i + 1 + filter[i].jf]);
else {
PPC_BCC(true_cond, addrs[i + 1 + filter[i].jt]);
if (filter[i].jf != 0)
PPC_JMP(addrs[i + 1 + filter[i].jf]);
}
break;
default:
/* The filter contains something cruel & unusual.
* We don't handle it, but also there shouldn't be
* anything missing from our list.
*/
if (printk_ratelimit())
pr_err("BPF filter opcode %04x (@%d) unsupported\n",
filter[i].code, i);
return -ENOTSUPP;
}
}
/* Set end-of-body-code address for exit. */
addrs[i] = ctx->idx * 4;
return 0;
}
/* Assemble the body code between the prologue & epilogue. */
static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
struct codegen_context *ctx,
unsigned int *addrs)
{
const struct sock_filter *filter = fp->insns;
int flen = fp->len;
u8 *func;
unsigned int true_cond;
int i;
/* Start of epilogue code */
unsigned int exit_addr = addrs[flen];
for (i = 0; i < flen; i++) {
unsigned int K = filter[i].k;
/*
* addrs[] maps a BPF bytecode address into a real offset from
* the start of the body code.
*/
addrs[i] = ctx->idx * 4;
switch (filter[i].code) {
/*** ALU ops ***/
case BPF_S_ALU_ADD_X: /* A += X; */
ctx->seen |= SEEN_XREG;
PPC_ADD(r_A, r_A, r_X);
break;
case BPF_S_ALU_ADD_K: /* A += K; */
if (!K)
break;
PPC_ADDI(r_A, r_A, IMM_L(K));
if (K >= 32768)
PPC_ADDIS(r_A, r_A, IMM_HA(K));
break;
case BPF_S_ALU_SUB_X: /* A -= X; */
ctx->seen |= SEEN_XREG;
PPC_SUB(r_A, r_A, r_X);
break;
case BPF_S_ALU_SUB_K: /* A -= K */
if (!K)
break;
PPC_ADDI(r_A, r_A, IMM_L(-K));
if (K >= 32768)
PPC_ADDIS(r_A, r_A, IMM_HA(-K));
break;
case BPF_S_ALU_MUL_X: /* A *= X; */
ctx->seen |= SEEN_XREG;
PPC_MUL(r_A, r_A, r_X);
break;
case BPF_S_ALU_MUL_K: /* A *= K */
if (K < 32768)
PPC_MULI(r_A, r_A, K);
else {
PPC_LI32(r_scratch1, K);
PPC_MUL(r_A, r_A, r_scratch1);
}
break;
case BPF_S_ALU_DIV_X: /* A /= X; */
ctx->seen |= SEEN_XREG;
PPC_CMPWI(r_X, 0);
if (ctx->pc_ret0 != -1) {
PPC_BCC(COND_EQ, addrs[ctx->pc_ret0]);
} else {
/*
* Exit, returning 0; first pass hits here
* (longer worst-case code size).
*/
PPC_BCC_SHORT(COND_NE, (ctx->idx*4)+12);
PPC_LI(r_ret, 0);
PPC_JMP(exit_addr);
}
PPC_DIVWU(r_A, r_A, r_X);
break;
case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K); */
PPC_LI32(r_scratch1, K);
/* Top 32 bits of 64bit result -> A */
PPC_MULHWU(r_A, r_A, r_scratch1);
break;
case BPF_S_ALU_AND_X:
ctx->seen |= SEEN_XREG;
PPC_AND(r_A, r_A, r_X);
break;
case BPF_S_ALU_AND_K:
if (!IMM_H(K))
PPC_ANDI(r_A, r_A, K);
else {
PPC_LI32(r_scratch1, K);
PPC_AND(r_A, r_A, r_scratch1);
}
break;
case BPF_S_ALU_OR_X:
ctx->seen |= SEEN_XREG;
PPC_OR(r_A, r_A, r_X);
break;
case BPF_S_ALU_OR_K:
if (IMM_L(K))
PPC_ORI(r_A, r_A, IMM_L(K));
if (K >= 65536)
PPC_ORIS(r_A, r_A, IMM_H(K));
break;
case BPF_S_ALU_LSH_X: /* A <<= X; */
ctx->seen |= SEEN_XREG;
PPC_SLW(r_A, r_A, r_X);
break;
case BPF_S_ALU_LSH_K:
if (K == 0)
break;
else
PPC_SLWI(r_A, r_A, K);
break;
case BPF_S_ALU_RSH_X: /* A >>= X; */
ctx->seen |= SEEN_XREG;
PPC_SRW(r_A, r_A, r_X);
break;
case BPF_S_ALU_RSH_K: /* A >>= K; */
if (K == 0)
break;
else
PPC_SRWI(r_A, r_A, K);
break;
case BPF_S_ALU_NEG:
PPC_NEG(r_A, r_A);
break;
case BPF_S_RET_K:
PPC_LI32(r_ret, K);
if (!K) {
if (ctx->pc_ret0 == -1)
ctx->pc_ret0 = i;
}
/*
* If this isn't the very last instruction, branch to
* the epilogue if we've stuff to clean up. Otherwise,
* if there's nothing to tidy, just return. If we /are/
* the last instruction, we're about to fall through to
* the epilogue to return.
*/
if (i != flen - 1) {
/*
* Note: 'seen' is properly valid only on pass
* #2. Both parts of this conditional are the
* same instruction size though, meaning the
* first pass will still correctly determine the
* code size/addresses.
*/
if (ctx->seen)
PPC_JMP(exit_addr);
else
PPC_BLR();
}
break;
case BPF_S_RET_A:
PPC_MR(r_ret, r_A);
if (i != flen - 1) {
if (ctx->seen)
PPC_JMP(exit_addr);
else
PPC_BLR();
}
break;
case BPF_S_MISC_TAX: /* X = A */
PPC_MR(r_X, r_A);
break;
case BPF_S_MISC_TXA: /* A = X */
ctx->seen |= SEEN_XREG;
PPC_MR(r_A, r_X);
break;
/*** Constant loads/M[] access ***/
case BPF_S_LD_IMM: /* A = K */
PPC_LI32(r_A, K);
break;
case BPF_S_LDX_IMM: /* X = K */
PPC_LI32(r_X, K);
break;
case BPF_S_LD_MEM: /* A = mem[K] */
PPC_MR(r_A, r_M + (K & 0xf));
ctx->seen |= SEEN_MEM | (1<<(K & 0xf));
break;
case BPF_S_LDX_MEM: /* X = mem[K] */
PPC_MR(r_X, r_M + (K & 0xf));
ctx->seen |= SEEN_MEM | (1<<(K & 0xf));
break;
case BPF_S_ST: /* mem[K] = A */
PPC_MR(r_M + (K & 0xf), r_A);
ctx->seen |= SEEN_MEM | (1<<(K & 0xf));
break;
case BPF_S_STX: /* mem[K] = X */
PPC_MR(r_M + (K & 0xf), r_X);
ctx->seen |= SEEN_XREG | SEEN_MEM | (1<<(K & 0xf));
break;
case BPF_S_LD_W_LEN: /* A = skb->len; */
BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4);
PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, len));
break;
case BPF_S_LDX_W_LEN: /* X = skb->len; */
PPC_LWZ_OFFS(r_X, r_skb, offsetof(struct sk_buff, len));
break;
/*** Ancillary info loads ***/
/* None of the BPF_S_ANC* codes appear to be passed by
* sk_chk_filter(). The interpreter and the x86 BPF
* compiler implement them so we do too -- they may be
* planted in future.
*/
case BPF_S_ANC_PROTOCOL: /* A = ntohs(skb->protocol); */
BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
protocol) != 2);
PPC_LHZ_OFFS(r_A, r_skb, offsetof(struct sk_buff,
protocol));
/* ntohs is a NOP with BE loads. */
break;
case BPF_S_ANC_IFINDEX:
PPC_LD_OFFS(r_scratch1, r_skb, offsetof(struct sk_buff,
dev));
PPC_CMPDI(r_scratch1, 0);
if (ctx->pc_ret0 != -1) {
PPC_BCC(COND_EQ, addrs[ctx->pc_ret0]);
} else {
/* Exit, returning 0; first pass hits here. */
PPC_BCC_SHORT(COND_NE, (ctx->idx*4)+12);
PPC_LI(r_ret, 0);
PPC_JMP(exit_addr);
}
BUILD_BUG_ON(FIELD_SIZEOF(struct net_device,
ifindex) != 4);
PPC_LWZ_OFFS(r_A, r_scratch1,
offsetof(struct net_device, ifindex));
break;
case BPF_S_ANC_MARK:
BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);
PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff,
mark));
break;
case BPF_S_ANC_RXHASH:
BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, rxhash) != 4);
PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff,
rxhash));
break;
case BPF_S_ANC_QUEUE:
BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
queue_mapping) != 2);
PPC_LHZ_OFFS(r_A, r_skb, offsetof(struct sk_buff,
queue_mapping));
break;
case BPF_S_ANC_CPU:
#ifdef CONFIG_SMP
/*
* PACA ptr is r13:
* raw_smp_processor_id() = local_paca->paca_index
*/
BUILD_BUG_ON(FIELD_SIZEOF(struct paca_struct,
paca_index) != 2);
PPC_LHZ_OFFS(r_A, 13,
offsetof(struct paca_struct, paca_index));
#else
PPC_LI(r_A, 0);
#endif
break;
/*** Absolute loads from packet header/data ***/
case BPF_S_LD_W_ABS:
func = sk_load_word;
goto common_load;
case BPF_S_LD_H_ABS:
func = sk_load_half;
goto common_load;
case BPF_S_LD_B_ABS:
func = sk_load_byte;
common_load:
/*
* Load from [K]. Reference with the (negative)
* SKF_NET_OFF/SKF_LL_OFF offsets is unsupported.
*/
ctx->seen |= SEEN_DATAREF;
if ((int)K < 0)
return -ENOTSUPP;
PPC_LI64(r_scratch1, func);
PPC_MTLR(r_scratch1);
PPC_LI32(r_addr, K);
PPC_BLRL();
/*
* Helper returns 'lt' condition on error, and an
* appropriate return value in r3
*/
PPC_BCC(COND_LT, exit_addr);
break;
/*** Indirect loads from packet header/data ***/
case BPF_S_LD_W_IND:
func = sk_load_word;
goto common_load_ind;
case BPF_S_LD_H_IND:
func = sk_load_half;
goto common_load_ind;
case BPF_S_LD_B_IND:
func = sk_load_byte;
common_load_ind:
/*
* Load from [X + K]. Negative offsets are tested for
* in the helper functions, and result in a 'ret 0'.
*/
ctx->seen |= SEEN_DATAREF | SEEN_XREG;
PPC_LI64(r_scratch1, func);
PPC_MTLR(r_scratch1);
PPC_ADDI(r_addr, r_X, IMM_L(K));
if (K >= 32768)
PPC_ADDIS(r_addr, r_addr, IMM_HA(K));
PPC_BLRL();
/* If error, cr0.LT set */
PPC_BCC(COND_LT, exit_addr);
break;
case BPF_S_LDX_B_MSH:
/*
* x86 version drops packet (RET 0) when K<0, whereas
* interpreter does allow K<0 (__load_pointer, special
* ancillary data). common_load returns ENOTSUPP if K<0,
* so we fall back to interpreter & filter works.
*/
func = sk_load_byte_msh;
goto common_load;
break;
/*** Jump and branches ***/
case BPF_S_JMP_JA:
if (K != 0)
PPC_JMP(addrs[i + 1 + K]);
break;
case BPF_S_JMP_JGT_K:
case BPF_S_JMP_JGT_X:
true_cond = COND_GT;
goto cond_branch;
case BPF_S_JMP_JGE_K:
case BPF_S_JMP_JGE_X:
true_cond = COND_GE;
goto cond_branch;
case BPF_S_JMP_JEQ_K:
case BPF_S_JMP_JEQ_X:
true_cond = COND_EQ;
goto cond_branch;
case BPF_S_JMP_JSET_K:
case BPF_S_JMP_JSET_X:
true_cond = COND_NE;
/* Fall through */
cond_branch:
/* same targets, can avoid doing the test :) */
if (filter[i].jt == filter[i].jf) {
if (filter[i].jt > 0)
PPC_JMP(addrs[i + 1 + filter[i].jt]);
break;
}
switch (filter[i].code) {
case BPF_S_JMP_JGT_X:
case BPF_S_JMP_JGE_X:
case BPF_S_JMP_JEQ_X:
ctx->seen |= SEEN_XREG;
PPC_CMPLW(r_A, r_X);
break;
case BPF_S_JMP_JSET_X:
ctx->seen |= SEEN_XREG;
PPC_AND_DOT(r_scratch1, r_A, r_X);
break;
case BPF_S_JMP_JEQ_K:
case BPF_S_JMP_JGT_K:
case BPF_S_JMP_JGE_K:
if (K < 32768)
PPC_CMPLWI(r_A, K);
else {
PPC_LI32(r_scratch1, K);
PPC_CMPLW(r_A, r_scratch1);
}
break;
case BPF_S_JMP_JSET_K:
if (K < 32768)
/* PPC_ANDI is /only/ dot-form */
PPC_ANDI(r_scratch1, r_A, K);
else {
PPC_LI32(r_scratch1, K);
PPC_AND_DOT(r_scratch1, r_A,
r_scratch1);
}
break;
}
/* Sometimes branches are constructed "backward", with
* the false path being the branch and true path being
* a fallthrough to the next instruction.
*/
if (filter[i].jt == 0)
/* Swap the sense of the branch */
PPC_BCC(true_cond ^ COND_CMP_TRUE,
addrs[i + 1 + filter[i].jf]);
else {
PPC_BCC(true_cond, addrs[i + 1 + filter[i].jt]);
if (filter[i].jf != 0)
PPC_JMP(addrs[i + 1 + filter[i].jf]);
}
break;
default:
/* The filter contains something cruel & unusual.
* We don't handle it, but also there shouldn't be
* anything missing from our list.
*/
if (printk_ratelimit())
pr_err("BPF filter opcode %04x (@%d) unsupported\n",
filter[i].code, i);
return -ENOTSUPP;
}
}
/* Set end-of-body-code address for exit. */
addrs[i] = ctx->idx * 4;
return 0;
}
/* Assemble the body code between the prologue & epilogue */
static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
struct codegen_context *ctx,
u32 *addrs, bool extra_pass)
{
const struct bpf_insn *insn = fp->insnsi;
int flen = fp->len;
int i, ret;
/* 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;
bool func_addr_fixed;
u64 func_addr;
u64 imm64;
u32 true_cond;
u32 tmp_idx;
/*
* 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.
*/
if (dst_reg >= BPF_PPC_NVR_MIN && dst_reg < 32)
bpf_set_seen_register(ctx, insn[i].dst_reg);
if (src_reg >= BPF_PPC_NVR_MIN && src_reg < 32)
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_ALU | BPF_ARSH | BPF_X: /* (s32) dst >>= src */
PPC_SRAW(dst_reg, dst_reg, src_reg);
goto bpf_alu32_trunc;
case BPF_ALU64 | BPF_ARSH | BPF_X: /* (s64) dst >>= src */
PPC_SRAD(dst_reg, dst_reg, src_reg);
break;
case BPF_ALU | BPF_ARSH | BPF_K: /* (s32) dst >>= imm */
PPC_SRAWI(dst_reg, dst_reg, imm);
goto bpf_alu32_trunc;
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
*/
PPC_STD(dst_reg, 1, bpf_jit_stack_local(ctx));
PPC_ADDI(b2p[TMP_REG_1], 1, bpf_jit_stack_local(ctx));
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);
tmp_idx = ctx->idx * 4;
/* 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 */
PPC_BCC_SHORT(COND_NE, tmp_idx);
break;
/* *(u64 *)(dst + off) += src */
case BPF_STX | BPF_XADD | BPF_DW:
PPC_ADDI(b2p[TMP_REG_1], dst_reg, off);
tmp_idx = ctx->idx * 4;
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]);
PPC_BCC_SHORT(COND_NE, tmp_idx);
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;
/*
* Call kernel helper or bpf function
*/
case BPF_JMP | BPF_CALL:
ctx->seen |= SEEN_FUNC;
ret = bpf_jit_get_func_addr(fp, &insn[i], extra_pass,
&func_addr, &func_addr_fixed);
if (ret < 0)
return ret;
if (func_addr_fixed)
bpf_jit_emit_func_call_hlp(image, ctx, func_addr);
else
bpf_jit_emit_func_call_rel(image, ctx, func_addr);
/* 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;
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;
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;
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;
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:
case BPF_JMP | BPF_JLT | BPF_X:
case BPF_JMP | BPF_JGE | BPF_X:
case BPF_JMP | BPF_JLE | BPF_X:
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:
case BPF_JMP | BPF_JSLT | BPF_X:
case BPF_JMP | BPF_JSGE | BPF_X:
case BPF_JMP | BPF_JSLE | BPF_X:
/* 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:
case BPF_JMP | BPF_JLT | BPF_K:
case BPF_JMP | BPF_JGE | BPF_K:
case BPF_JMP | BPF_JLE | BPF_K:
/*
* 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:
case BPF_JMP | BPF_JSLT | BPF_K:
case BPF_JMP | BPF_JSGE | BPF_K:
case BPF_JMP | BPF_JSLE | BPF_K:
/*
* 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;
/*
* Tail call
*/
case BPF_JMP | BPF_TAIL_CALL:
ctx->seen |= SEEN_TAILCALL;
bpf_jit_emit_tail_call(image, ctx, addrs[i + 1]);
break;
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;
}
