void bpf_jit_compile(struct bpf_prog *fp)
{
unsigned int cleanup_addr, proglen, oldproglen = 0;
u32 temp[8], *prog, *func, seen = 0, pass;
const struct sock_filter *filter = fp->insns;
int i, flen = fp->len, pc_ret0 = -1;
unsigned int *addrs;
void *image;
if (!bpf_jit_enable)
return;
addrs = kmalloc_array(flen, sizeof(*addrs), GFP_KERNEL);
if (addrs == NULL)
return;
/* Before first pass, make a rough estimation of addrs[]
* each bpf instruction is translated to less than 64 bytes
*/
for (proglen = 0, i = 0; i < flen; i++) {
proglen += 64;
addrs[i] = proglen;
}
cleanup_addr = proglen; /* epilogue address */
image = NULL;
for (pass = 0; pass < 10; pass++) {
u8 seen_or_pass0 = (pass == 0) ? (SEEN_XREG | SEEN_DATAREF | SEEN_MEM) : seen;
/* no prologue/epilogue for trivial filters (RET something) */
proglen = 0;
prog = temp;
/* Prologue */
if (seen_or_pass0) {
if (seen_or_pass0 & SEEN_MEM) {
unsigned int sz = BASE_STACKFRAME;
sz += BPF_MEMWORDS * sizeof(u32);
emit_alloc_stack(sz);
}
/* Make sure we dont leek kernel memory. */
if (seen_or_pass0 & SEEN_XREG)
emit_clear(r_X);
/* If this filter needs to access skb data,
* load %o4 and %o5 with:
* %o4 = skb->len - skb->data_len
* %o5 = skb->data
* And also back up %o7 into r_saved_O7 so we can
* invoke the stubs using 'call'.
*/
if (seen_or_pass0 & SEEN_DATAREF) {
emit_load32(r_SKB, struct sk_buff, len, r_HEADLEN);
emit_load32(r_SKB, struct sk_buff, data_len, r_TMP);
emit_sub(r_HEADLEN, r_TMP, r_HEADLEN);
emit_loadptr(r_SKB, struct sk_buff, data, r_SKB_DATA);
}
}
emit_reg_move(O7, r_saved_O7);
/* Make sure we dont leak kernel information to the user. */
if (bpf_needs_clear_a(&filter[0]))
emit_clear(r_A); /* A = 0 */
for (i = 0; i < flen; i++) {
unsigned int K = filter[i].k;
unsigned int t_offset;
unsigned int f_offset;
u32 t_op, f_op;
u16 code = bpf_anc_helper(&filter[i]);
int ilen;
switch (code) {
case BPF_ALU | BPF_ADD | BPF_X: /* A += X; */
emit_alu_X(ADD);
break;
case BPF_ALU | BPF_ADD | BPF_K: /* A += K; */
emit_alu_K(ADD, K);
break;
case BPF_ALU | BPF_SUB | BPF_X: /* A -= X; */
emit_alu_X(SUB);
break;
case BPF_ALU | BPF_SUB | BPF_K: /* A -= K */
emit_alu_K(SUB, K);
break;
case BPF_ALU | BPF_AND | BPF_X: /* A &= X */
emit_alu_X(AND);
break;
case BPF_ALU | BPF_AND | BPF_K: /* A &= K */
emit_alu_K(AND, K);
break;
case BPF_ALU | BPF_OR | BPF_X: /* A |= X */
emit_alu_X(OR);
break;
case BPF_ALU | BPF_OR | BPF_K: /* A |= K */
emit_alu_K(OR, K);
break;
case BPF_ANC | SKF_AD_ALU_XOR_X: /* A ^= X; */
case BPF_ALU | BPF_XOR | BPF_X:
emit_alu_X(XOR);
break;
case BPF_ALU | BPF_XOR | BPF_K: /* A ^= K */
emit_alu_K(XOR, K);
break;
case BPF_ALU | BPF_LSH | BPF_X: /* A <<= X */
emit_alu_X(SLL);
break;
case BPF_ALU | BPF_LSH | BPF_K: /* A <<= K */
emit_alu_K(SLL, K);
break;
case BPF_ALU | BPF_RSH | BPF_X: /* A >>= X */
emit_alu_X(SRL);
break;
case BPF_ALU | BPF_RSH | BPF_K: /* A >>= K */
emit_alu_K(SRL, K);
break;
case BPF_ALU | BPF_MUL | BPF_X: /* A *= X; */
emit_alu_X(MUL);
break;
case BPF_ALU | BPF_MUL | BPF_K: /* A *= K */
emit_alu_K(MUL, K);
break;
case BPF_ALU | BPF_DIV | BPF_K: /* A /= K with K != 0*/
if (K == 1)
break;
emit_write_y(G0);
/* The Sparc v8 architecture requires
* three instructions between a %y
* register write and the first use.
*/
emit_nop();
emit_nop();
emit_nop();
emit_alu_K(DIV, K);
break;
case BPF_ALU | BPF_DIV | BPF_X: /* A /= X; */
emit_cmpi(r_X, 0);
if (pc_ret0 > 0) {
t_offset = addrs[pc_ret0 - 1];
emit_branch(BE, t_offset + 20);
emit_nop(); /* delay slot */
} else {
emit_branch_off(BNE, 16);
emit_nop();
emit_jump(cleanup_addr + 20);
emit_clear(r_A);
}
emit_write_y(G0);
/* The Sparc v8 architecture requires
* three instructions between a %y
* register write and the first use.
*/
emit_nop();
emit_nop();
emit_nop();
emit_alu_X(DIV);
break;
case BPF_ALU | BPF_NEG:
emit_neg();
break;
case BPF_RET | BPF_K:
if (!K) {
if (pc_ret0 == -1)
pc_ret0 = i;
emit_clear(r_A);
} else {
emit_loadimm(K, r_A);
}
/* Fallthrough */
case BPF_RET | BPF_A:
if (seen_or_pass0) {
if (i != flen - 1) {
emit_jump(cleanup_addr);
emit_nop();
break;
}
if (seen_or_pass0 & SEEN_MEM) {
unsigned int sz = BASE_STACKFRAME;
sz += BPF_MEMWORDS * sizeof(u32);
emit_release_stack(sz);
}
}
/* jmpl %r_saved_O7 + 8, %g0 */
emit_jmpl(r_saved_O7, 8, G0);
emit_reg_move(r_A, O0); /* delay slot */
break;
case BPF_MISC | BPF_TAX:
seen |= SEEN_XREG;
emit_reg_move(r_A, r_X);
break;
case BPF_MISC | BPF_TXA:
seen |= SEEN_XREG;
emit_reg_move(r_X, r_A);
break;
case BPF_ANC | SKF_AD_CPU:
emit_load_cpu(r_A);
break;
case BPF_ANC | SKF_AD_PROTOCOL:
emit_skb_load16(protocol, r_A);
break;
case BPF_ANC | SKF_AD_PKTTYPE:
__emit_skb_load8(__pkt_type_offset, r_A);
emit_andi(r_A, PKT_TYPE_MAX, r_A);
emit_alu_K(SRL, 5);
break;
case BPF_ANC | SKF_AD_IFINDEX:
emit_skb_loadptr(dev, r_A);
emit_cmpi(r_A, 0);
emit_branch(BE_PTR, cleanup_addr + 4);
emit_nop();
emit_load32(r_A, struct net_device, ifindex, r_A);
break;
case BPF_ANC | SKF_AD_MARK:
emit_skb_load32(mark, r_A);
break;
case BPF_ANC | SKF_AD_QUEUE:
emit_skb_load16(queue_mapping, r_A);
break;
case BPF_ANC | SKF_AD_HATYPE:
emit_skb_loadptr(dev, r_A);
emit_cmpi(r_A, 0);
emit_branch(BE_PTR, cleanup_addr + 4);
emit_nop();
emit_load16(r_A, struct net_device, type, r_A);
break;
case BPF_ANC | SKF_AD_RXHASH:
emit_skb_load32(hash, r_A);
break;
case BPF_ANC | SKF_AD_VLAN_TAG:
emit_skb_load16(vlan_tci, r_A);
break;
case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT:
__emit_skb_load8(__pkt_vlan_present_offset, r_A);
if (PKT_VLAN_PRESENT_BIT)
emit_alu_K(SRL, PKT_VLAN_PRESENT_BIT);
if (PKT_VLAN_PRESENT_BIT < 7)
emit_andi(r_A, 1, r_A);
break;
case BPF_LD | BPF_W | BPF_LEN:
emit_skb_load32(len, r_A);
break;
case BPF_LDX | BPF_W | BPF_LEN:
emit_skb_load32(len, r_X);
break;
case BPF_LD | BPF_IMM:
emit_loadimm(K, r_A);
break;
case BPF_LDX | BPF_IMM:
emit_loadimm(K, r_X);
break;
case BPF_LD | BPF_MEM:
seen |= SEEN_MEM;
emit_ldmem(K * 4, r_A);
break;
case BPF_LDX | BPF_MEM:
seen |= SEEN_MEM | SEEN_XREG;
emit_ldmem(K * 4, r_X);
break;
case BPF_ST:
seen |= SEEN_MEM;
emit_stmem(K * 4, r_A);
break;
case BPF_STX:
seen |= SEEN_MEM | SEEN_XREG;
emit_stmem(K * 4, r_X);
break;
#define CHOOSE_LOAD_FUNC(K, func) \
((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
case BPF_LD | BPF_W | BPF_ABS:
func = CHOOSE_LOAD_FUNC(K, bpf_jit_load_word);
common_load: seen |= SEEN_DATAREF;
emit_loadimm(K, r_OFF);
emit_call(func);
break;
case BPF_LD | BPF_H | BPF_ABS:
func = CHOOSE_LOAD_FUNC(K, bpf_jit_load_half);
goto common_load;
case BPF_LD | BPF_B | BPF_ABS:
func = CHOOSE_LOAD_FUNC(K, bpf_jit_load_byte);
goto common_load;
case BPF_LDX | BPF_B | BPF_MSH:
func = CHOOSE_LOAD_FUNC(K, bpf_jit_load_byte_msh);
goto common_load;
case BPF_LD | BPF_W | BPF_IND:
func = bpf_jit_load_word;
common_load_ind: seen |= SEEN_DATAREF | SEEN_XREG;
if (K) {
if (is_simm13(K)) {
emit_addi(r_X, K, r_OFF);
} else {
emit_loadimm(K, r_TMP);
emit_add(r_X, r_TMP, r_OFF);
}
} else {
emit_reg_move(r_X, r_OFF);
}
emit_call(func);
break;
case BPF_LD | BPF_H | BPF_IND:
func = bpf_jit_load_half;
goto common_load_ind;
case BPF_LD | BPF_B | BPF_IND:
func = bpf_jit_load_byte;
goto common_load_ind;
case BPF_JMP | BPF_JA:
emit_jump(addrs[i + K]);
emit_nop();
break;
#define COND_SEL(CODE, TOP, FOP) \
case CODE: \
t_op = TOP; \
f_op = FOP; \
goto cond_branch
COND_SEL(BPF_JMP | BPF_JGT | BPF_K, BGU, BLEU);
COND_SEL(BPF_JMP | BPF_JGE | BPF_K, BGEU, BLU);
COND_SEL(BPF_JMP | BPF_JEQ | BPF_K, BE, BNE);
COND_SEL(BPF_JMP | BPF_JSET | BPF_K, BNE, BE);
COND_SEL(BPF_JMP | BPF_JGT | BPF_X, BGU, BLEU);
COND_SEL(BPF_JMP | BPF_JGE | BPF_X, BGEU, BLU);
COND_SEL(BPF_JMP | BPF_JEQ | BPF_X, BE, BNE);
COND_SEL(BPF_JMP | BPF_JSET | BPF_X, BNE, BE);
cond_branch: f_offset = addrs[i + filter[i].jf];
t_offset = addrs[i + filter[i].jt];
/* same targets, can avoid doing the test :) */
if (filter[i].jt == filter[i].jf) {
emit_jump(t_offset);
emit_nop();
break;
}
switch (code) {
case BPF_JMP | BPF_JGT | BPF_X:
case BPF_JMP | BPF_JGE | BPF_X:
case BPF_JMP | BPF_JEQ | BPF_X:
seen |= SEEN_XREG;
emit_cmp(r_A, r_X);
break;
case BPF_JMP | BPF_JSET | BPF_X:
seen |= SEEN_XREG;
emit_btst(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 (is_simm13(K)) {
emit_cmpi(r_A, K);
} else {
emit_loadimm(K, r_TMP);
emit_cmp(r_A, r_TMP);
}
break;
case BPF_JMP | BPF_JSET | BPF_K:
if (is_simm13(K)) {
emit_btsti(r_A, K);
} else {
emit_loadimm(K, r_TMP);
emit_btst(r_A, r_TMP);
}
break;
}
if (filter[i].jt != 0) {
if (filter[i].jf)
t_offset += 8;
emit_branch(t_op, t_offset);
emit_nop(); /* delay slot */
if (filter[i].jf) {
emit_jump(f_offset);
emit_nop();
}
break;
}
emit_branch(f_op, f_offset);
emit_nop(); /* delay slot */
break;
default:
/* hmm, too complex filter, give up with jit compiler */
goto out;
}
ilen = (void *) prog - (void *) temp;
if (image) {
if (unlikely(proglen + ilen > oldproglen)) {
pr_err("bpb_jit_compile fatal error\n");
kfree(addrs);
module_memfree(image);
return;
}
memcpy(image + proglen, temp, ilen);
}
proglen += ilen;
addrs[i] = proglen;
prog = temp;
}
/* last bpf instruction is always a RET :
* use it to give the cleanup instruction(s) addr
*/
cleanup_addr = proglen - 8; /* jmpl; mov r_A,%o0; */
if (seen_or_pass0 & SEEN_MEM)
cleanup_addr -= 4; /* add %sp, X, %sp; */
if (image) {
if (proglen != oldproglen)
pr_err("bpb_jit_compile proglen=%u != oldproglen=%u\n",
proglen, oldproglen);
break;
}
if (proglen == oldproglen) {
image = module_alloc(proglen);
if (!image)
goto out;
}
oldproglen = proglen;
}
if (bpf_jit_enable > 1)
bpf_jit_dump(flen, proglen, pass + 1, image);
if (image) {
fp->bpf_func = (void *)image;
fp->jited = 1;
}
out:
kfree(addrs);
return;
}
/* 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;
}
