diff options
Diffstat (limited to 'net/core/filter.c')
-rw-r--r-- | net/core/filter.c | 728 |
1 files changed, 106 insertions, 622 deletions
diff --git a/net/core/filter.c b/net/core/filter.c index 1dbf6462f766..d814b8a89d0f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -18,7 +18,7 @@ * 2 of the License, or (at your option) any later version. * * Andi Kleen - Fix a few bad bugs and races. - * Kris Katterjohn - Added many additional checks in sk_chk_filter() + * Kris Katterjohn - Added many additional checks in bpf_check_classic() */ #include <linux/module.h> @@ -45,54 +45,6 @@ #include <linux/seccomp.h> #include <linux/if_vlan.h> -/* Registers */ -#define BPF_R0 regs[BPF_REG_0] -#define BPF_R1 regs[BPF_REG_1] -#define BPF_R2 regs[BPF_REG_2] -#define BPF_R3 regs[BPF_REG_3] -#define BPF_R4 regs[BPF_REG_4] -#define BPF_R5 regs[BPF_REG_5] -#define BPF_R6 regs[BPF_REG_6] -#define BPF_R7 regs[BPF_REG_7] -#define BPF_R8 regs[BPF_REG_8] -#define BPF_R9 regs[BPF_REG_9] -#define BPF_R10 regs[BPF_REG_10] - -/* Named registers */ -#define DST regs[insn->dst_reg] -#define SRC regs[insn->src_reg] -#define FP regs[BPF_REG_FP] -#define ARG1 regs[BPF_REG_ARG1] -#define CTX regs[BPF_REG_CTX] -#define IMM insn->imm - -/* No hurry in this branch - * - * Exported for the bpf jit load helper. - */ -void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size) -{ - u8 *ptr = NULL; - - if (k >= SKF_NET_OFF) - ptr = skb_network_header(skb) + k - SKF_NET_OFF; - else if (k >= SKF_LL_OFF) - ptr = skb_mac_header(skb) + k - SKF_LL_OFF; - if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb)) - return ptr; - - return NULL; -} - -static inline void *load_pointer(const struct sk_buff *skb, int k, - unsigned int size, void *buffer) -{ - if (k >= 0) - return skb_header_pointer(skb, k, size, buffer); - - return bpf_internal_load_pointer_neg_helper(skb, k, size); -} - /** * sk_filter - run a packet through a socket filter * @sk: sock associated with &sk_buff @@ -135,451 +87,6 @@ int sk_filter(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(sk_filter); -/* Base function for offset calculation. Needs to go into .text section, - * therefore keeping it non-static as well; will also be used by JITs - * anyway later on, so do not let the compiler omit it. - */ -noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) -{ - return 0; -} - -/** - * __sk_run_filter - run a filter on a given context - * @ctx: buffer to run the filter on - * @insn: filter to apply - * - * Decode and apply filter instructions to the skb->data. Return length to - * keep, 0 for none. @ctx is the data we are operating on, @insn is the - * array of filter instructions. - */ -static unsigned int __sk_run_filter(void *ctx, const struct sock_filter_int *insn) -{ - u64 stack[MAX_BPF_STACK / sizeof(u64)]; - u64 regs[MAX_BPF_REG], tmp; - static const void *jumptable[256] = { - [0 ... 255] = &&default_label, - /* Now overwrite non-defaults ... */ - /* 32 bit ALU operations */ - [BPF_ALU | BPF_ADD | BPF_X] = &&ALU_ADD_X, - [BPF_ALU | BPF_ADD | BPF_K] = &&ALU_ADD_K, - [BPF_ALU | BPF_SUB | BPF_X] = &&ALU_SUB_X, - [BPF_ALU | BPF_SUB | BPF_K] = &&ALU_SUB_K, - [BPF_ALU | BPF_AND | BPF_X] = &&ALU_AND_X, - [BPF_ALU | BPF_AND | BPF_K] = &&ALU_AND_K, - [BPF_ALU | BPF_OR | BPF_X] = &&ALU_OR_X, - [BPF_ALU | BPF_OR | BPF_K] = &&ALU_OR_K, - [BPF_ALU | BPF_LSH | BPF_X] = &&ALU_LSH_X, - [BPF_ALU | BPF_LSH | BPF_K] = &&ALU_LSH_K, - [BPF_ALU | BPF_RSH | BPF_X] = &&ALU_RSH_X, - [BPF_ALU | BPF_RSH | BPF_K] = &&ALU_RSH_K, - [BPF_ALU | BPF_XOR | BPF_X] = &&ALU_XOR_X, - [BPF_ALU | BPF_XOR | BPF_K] = &&ALU_XOR_K, - [BPF_ALU | BPF_MUL | BPF_X] = &&ALU_MUL_X, - [BPF_ALU | BPF_MUL | BPF_K] = &&ALU_MUL_K, - [BPF_ALU | BPF_MOV | BPF_X] = &&ALU_MOV_X, - [BPF_ALU | BPF_MOV | BPF_K] = &&ALU_MOV_K, - [BPF_ALU | BPF_DIV | BPF_X] = &&ALU_DIV_X, - [BPF_ALU | BPF_DIV | BPF_K] = &&ALU_DIV_K, - [BPF_ALU | BPF_MOD | BPF_X] = &&ALU_MOD_X, - [BPF_ALU | BPF_MOD | BPF_K] = &&ALU_MOD_K, - [BPF_ALU | BPF_NEG] = &&ALU_NEG, - [BPF_ALU | BPF_END | BPF_TO_BE] = &&ALU_END_TO_BE, - [BPF_ALU | BPF_END | BPF_TO_LE] = &&ALU_END_TO_LE, - /* 64 bit ALU operations */ - [BPF_ALU64 | BPF_ADD | BPF_X] = &&ALU64_ADD_X, - [BPF_ALU64 | BPF_ADD | BPF_K] = &&ALU64_ADD_K, - [BPF_ALU64 | BPF_SUB | BPF_X] = &&ALU64_SUB_X, - [BPF_ALU64 | BPF_SUB | BPF_K] = &&ALU64_SUB_K, - [BPF_ALU64 | BPF_AND | BPF_X] = &&ALU64_AND_X, - [BPF_ALU64 | BPF_AND | BPF_K] = &&ALU64_AND_K, - [BPF_ALU64 | BPF_OR | BPF_X] = &&ALU64_OR_X, - [BPF_ALU64 | BPF_OR | BPF_K] = &&ALU64_OR_K, - [BPF_ALU64 | BPF_LSH | BPF_X] = &&ALU64_LSH_X, - [BPF_ALU64 | BPF_LSH | BPF_K] = &&ALU64_LSH_K, - [BPF_ALU64 | BPF_RSH | BPF_X] = &&ALU64_RSH_X, - [BPF_ALU64 | BPF_RSH | BPF_K] = &&ALU64_RSH_K, - [BPF_ALU64 | BPF_XOR | BPF_X] = &&ALU64_XOR_X, - [BPF_ALU64 | BPF_XOR | BPF_K] = &&ALU64_XOR_K, - [BPF_ALU64 | BPF_MUL | BPF_X] = &&ALU64_MUL_X, - [BPF_ALU64 | BPF_MUL | BPF_K] = &&ALU64_MUL_K, - [BPF_ALU64 | BPF_MOV | BPF_X] = &&ALU64_MOV_X, - [BPF_ALU64 | BPF_MOV | BPF_K] = &&ALU64_MOV_K, - [BPF_ALU64 | BPF_ARSH | BPF_X] = &&ALU64_ARSH_X, - [BPF_ALU64 | BPF_ARSH | BPF_K] = &&ALU64_ARSH_K, - [BPF_ALU64 | BPF_DIV | BPF_X] = &&ALU64_DIV_X, - [BPF_ALU64 | BPF_DIV | BPF_K] = &&ALU64_DIV_K, - [BPF_ALU64 | BPF_MOD | BPF_X] = &&ALU64_MOD_X, - [BPF_ALU64 | BPF_MOD | BPF_K] = &&ALU64_MOD_K, - [BPF_ALU64 | BPF_NEG] = &&ALU64_NEG, - /* Call instruction */ - [BPF_JMP | BPF_CALL] = &&JMP_CALL, - /* Jumps */ - [BPF_JMP | BPF_JA] = &&JMP_JA, - [BPF_JMP | BPF_JEQ | BPF_X] = &&JMP_JEQ_X, - [BPF_JMP | BPF_JEQ | BPF_K] = &&JMP_JEQ_K, - [BPF_JMP | BPF_JNE | BPF_X] = &&JMP_JNE_X, - [BPF_JMP | BPF_JNE | BPF_K] = &&JMP_JNE_K, - [BPF_JMP | BPF_JGT | BPF_X] = &&JMP_JGT_X, - [BPF_JMP | BPF_JGT | BPF_K] = &&JMP_JGT_K, - [BPF_JMP | BPF_JGE | BPF_X] = &&JMP_JGE_X, - [BPF_JMP | BPF_JGE | BPF_K] = &&JMP_JGE_K, - [BPF_JMP | BPF_JSGT | BPF_X] = &&JMP_JSGT_X, - [BPF_JMP | BPF_JSGT | BPF_K] = &&JMP_JSGT_K, - [BPF_JMP | BPF_JSGE | BPF_X] = &&JMP_JSGE_X, - [BPF_JMP | BPF_JSGE | BPF_K] = &&JMP_JSGE_K, - [BPF_JMP | BPF_JSET | BPF_X] = &&JMP_JSET_X, - [BPF_JMP | BPF_JSET | BPF_K] = &&JMP_JSET_K, - /* Program return */ - [BPF_JMP | BPF_EXIT] = &&JMP_EXIT, - /* Store instructions */ - [BPF_STX | BPF_MEM | BPF_B] = &&STX_MEM_B, - [BPF_STX | BPF_MEM | BPF_H] = &&STX_MEM_H, - [BPF_STX | BPF_MEM | BPF_W] = &&STX_MEM_W, - [BPF_STX | BPF_MEM | BPF_DW] = &&STX_MEM_DW, - [BPF_STX | BPF_XADD | BPF_W] = &&STX_XADD_W, - [BPF_STX | BPF_XADD | BPF_DW] = &&STX_XADD_DW, - [BPF_ST | BPF_MEM | BPF_B] = &&ST_MEM_B, - [BPF_ST | BPF_MEM | BPF_H] = &&ST_MEM_H, - [BPF_ST | BPF_MEM | BPF_W] = &&ST_MEM_W, - [BPF_ST | BPF_MEM | BPF_DW] = &&ST_MEM_DW, - /* Load instructions */ - [BPF_LDX | BPF_MEM | BPF_B] = &&LDX_MEM_B, - [BPF_LDX | BPF_MEM | BPF_H] = &&LDX_MEM_H, - [BPF_LDX | BPF_MEM | BPF_W] = &&LDX_MEM_W, - [BPF_LDX | BPF_MEM | BPF_DW] = &&LDX_MEM_DW, - [BPF_LD | BPF_ABS | BPF_W] = &&LD_ABS_W, - [BPF_LD | BPF_ABS | BPF_H] = &&LD_ABS_H, - [BPF_LD | BPF_ABS | BPF_B] = &&LD_ABS_B, - [BPF_LD | BPF_IND | BPF_W] = &&LD_IND_W, - [BPF_LD | BPF_IND | BPF_H] = &&LD_IND_H, - [BPF_LD | BPF_IND | BPF_B] = &&LD_IND_B, - }; - void *ptr; - int off; - -#define CONT ({ insn++; goto select_insn; }) -#define CONT_JMP ({ insn++; goto select_insn; }) - - FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; - ARG1 = (u64) (unsigned long) ctx; - - /* Registers used in classic BPF programs need to be reset first. */ - regs[BPF_REG_A] = 0; - regs[BPF_REG_X] = 0; - -select_insn: - goto *jumptable[insn->code]; - - /* ALU */ -#define ALU(OPCODE, OP) \ - ALU64_##OPCODE##_X: \ - DST = DST OP SRC; \ - CONT; \ - ALU_##OPCODE##_X: \ - DST = (u32) DST OP (u32) SRC; \ - CONT; \ - ALU64_##OPCODE##_K: \ - DST = DST OP IMM; \ - CONT; \ - ALU_##OPCODE##_K: \ - DST = (u32) DST OP (u32) IMM; \ - CONT; - - ALU(ADD, +) - ALU(SUB, -) - ALU(AND, &) - ALU(OR, |) - ALU(LSH, <<) - ALU(RSH, >>) - ALU(XOR, ^) - ALU(MUL, *) -#undef ALU - ALU_NEG: - DST = (u32) -DST; - CONT; - ALU64_NEG: - DST = -DST; - CONT; - ALU_MOV_X: - DST = (u32) SRC; - CONT; - ALU_MOV_K: - DST = (u32) IMM; - CONT; - ALU64_MOV_X: - DST = SRC; - CONT; - ALU64_MOV_K: - DST = IMM; - CONT; - ALU64_ARSH_X: - (*(s64 *) &DST) >>= SRC; - CONT; - ALU64_ARSH_K: - (*(s64 *) &DST) >>= IMM; - CONT; - ALU64_MOD_X: - if (unlikely(SRC == 0)) - return 0; - tmp = DST; - DST = do_div(tmp, SRC); - CONT; - ALU_MOD_X: - if (unlikely(SRC == 0)) - return 0; - tmp = (u32) DST; - DST = do_div(tmp, (u32) SRC); - CONT; - ALU64_MOD_K: - tmp = DST; - DST = do_div(tmp, IMM); - CONT; - ALU_MOD_K: - tmp = (u32) DST; - DST = do_div(tmp, (u32) IMM); - CONT; - ALU64_DIV_X: - if (unlikely(SRC == 0)) - return 0; - do_div(DST, SRC); - CONT; - ALU_DIV_X: - if (unlikely(SRC == 0)) - return 0; - tmp = (u32) DST; - do_div(tmp, (u32) SRC); - DST = (u32) tmp; - CONT; - ALU64_DIV_K: - do_div(DST, IMM); - CONT; - ALU_DIV_K: - tmp = (u32) DST; - do_div(tmp, (u32) IMM); - DST = (u32) tmp; - CONT; - ALU_END_TO_BE: - switch (IMM) { - case 16: - DST = (__force u16) cpu_to_be16(DST); - break; - case 32: - DST = (__force u32) cpu_to_be32(DST); - break; - case 64: - DST = (__force u64) cpu_to_be64(DST); - break; - } - CONT; - ALU_END_TO_LE: - switch (IMM) { - case 16: - DST = (__force u16) cpu_to_le16(DST); - break; - case 32: - DST = (__force u32) cpu_to_le32(DST); - break; - case 64: - DST = (__force u64) cpu_to_le64(DST); - break; - } - CONT; - - /* CALL */ - JMP_CALL: - /* Function call scratches BPF_R1-BPF_R5 registers, - * preserves BPF_R6-BPF_R9, and stores return value - * into BPF_R0. - */ - BPF_R0 = (__bpf_call_base + insn->imm)(BPF_R1, BPF_R2, BPF_R3, - BPF_R4, BPF_R5); - CONT; - - /* JMP */ - JMP_JA: - insn += insn->off; - CONT; - JMP_JEQ_X: - if (DST == SRC) { - insn += insn->off; - CONT_JMP; - } - CONT; - JMP_JEQ_K: - if (DST == IMM) { - insn += insn->off; - CONT_JMP; - } - CONT; - JMP_JNE_X: - if (DST != SRC) { - insn += insn->off; - CONT_JMP; - } - CONT; - JMP_JNE_K: - if (DST != IMM) { - insn += insn->off; - CONT_JMP; - } - CONT; - JMP_JGT_X: - if (DST > SRC) { - insn += insn->off; - CONT_JMP; - } - CONT; - JMP_JGT_K: - if (DST > IMM) { - insn += insn->off; - CONT_JMP; - } - CONT; - JMP_JGE_X: - if (DST >= SRC) { - insn += insn->off; - CONT_JMP; - } - CONT; - JMP_JGE_K: - if (DST >= IMM) { - insn += insn->off; - CONT_JMP; - } - CONT; - JMP_JSGT_X: - if (((s64) DST) > ((s64) SRC)) { - insn += insn->off; - CONT_JMP; - } - CONT; - JMP_JSGT_K: - if (((s64) DST) > ((s64) IMM)) { - insn += insn->off; - CONT_JMP; - } - CONT; - JMP_JSGE_X: - if (((s64) DST) >= ((s64) SRC)) { - insn += insn->off; - CONT_JMP; - } - CONT; - JMP_JSGE_K: - if (((s64) DST) >= ((s64) IMM)) { - insn += insn->off; - CONT_JMP; - } - CONT; - JMP_JSET_X: - if (DST & SRC) { - insn += insn->off; - CONT_JMP; - } - CONT; - JMP_JSET_K: - if (DST & IMM) { - insn += insn->off; - CONT_JMP; - } - CONT; - JMP_EXIT: - return BPF_R0; - - /* STX and ST and LDX*/ -#define LDST(SIZEOP, SIZE) \ - STX_MEM_##SIZEOP: \ - *(SIZE *)(unsigned long) (DST + insn->off) = SRC; \ - CONT; \ - ST_MEM_##SIZEOP: \ - *(SIZE *)(unsigned long) (DST + insn->off) = IMM; \ - CONT; \ - LDX_MEM_##SIZEOP: \ - DST = *(SIZE *)(unsigned long) (SRC + insn->off); \ - CONT; - - LDST(B, u8) - LDST(H, u16) - LDST(W, u32) - LDST(DW, u64) -#undef LDST - STX_XADD_W: /* lock xadd *(u32 *)(dst_reg + off16) += src_reg */ - atomic_add((u32) SRC, (atomic_t *)(unsigned long) - (DST + insn->off)); - CONT; - STX_XADD_DW: /* lock xadd *(u64 *)(dst_reg + off16) += src_reg */ - atomic64_add((u64) SRC, (atomic64_t *)(unsigned long) - (DST + insn->off)); - CONT; - LD_ABS_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + imm32)) */ - off = IMM; -load_word: - /* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are - * only appearing in the programs where ctx == - * skb. All programs keep 'ctx' in regs[BPF_REG_CTX] - * == BPF_R6, sk_convert_filter() saves it in BPF_R6, - * internal BPF verifier will check that BPF_R6 == - * ctx. - * - * BPF_ABS and BPF_IND are wrappers of function calls, - * so they scratch BPF_R1-BPF_R5 registers, preserve - * BPF_R6-BPF_R9, and store return value into BPF_R0. - * - * Implicit input: - * ctx == skb == BPF_R6 == CTX - * - * Explicit input: - * SRC == any register - * IMM == 32-bit immediate - * - * Output: - * BPF_R0 - 8/16/32-bit skb data converted to cpu endianness - */ - - ptr = load_pointer((struct sk_buff *) (unsigned long) CTX, off, 4, &tmp); - if (likely(ptr != NULL)) { - BPF_R0 = get_unaligned_be32(ptr); - CONT; - } - - return 0; - LD_ABS_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + imm32)) */ - off = IMM; -load_half: - ptr = load_pointer((struct sk_buff *) (unsigned long) CTX, off, 2, &tmp); - if (likely(ptr != NULL)) { - BPF_R0 = get_unaligned_be16(ptr); - CONT; - } - - return 0; - LD_ABS_B: /* BPF_R0 = *(u8 *) (skb->data + imm32) */ - off = IMM; -load_byte: - ptr = load_pointer((struct sk_buff *) (unsigned long) CTX, off, 1, &tmp); - if (likely(ptr != NULL)) { - BPF_R0 = *(u8 *)ptr; - CONT; - } - - return 0; - LD_IND_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + src_reg + imm32)) */ - off = IMM + SRC; - goto load_word; - LD_IND_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + src_reg + imm32)) */ - off = IMM + SRC; - goto load_half; - LD_IND_B: /* BPF_R0 = *(u8 *) (skb->data + src_reg + imm32) */ - off = IMM + SRC; - goto load_byte; - - default_label: - /* If we ever reach this, we have a bug somewhere. */ - WARN_RATELIMIT(1, "unknown opcode %02x\n", insn->code); - return 0; -} - /* Helper to find the offset of pkt_type in sk_buff structure. We want * to make sure its still a 3bit field starting at a byte boundary; * taken from arch/x86/net/bpf_jit_comp.c. @@ -667,9 +174,9 @@ static u64 __get_random_u32(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) } static bool convert_bpf_extensions(struct sock_filter *fp, - struct sock_filter_int **insnp) + struct bpf_insn **insnp) { - struct sock_filter_int *insn = *insnp; + struct bpf_insn *insn = *insnp; switch (fp->k) { case SKF_AD_OFF + SKF_AD_PROTOCOL: @@ -805,7 +312,7 @@ static bool convert_bpf_extensions(struct sock_filter *fp, } /** - * sk_convert_filter - convert filter program + * bpf_convert_filter - convert filter program * @prog: the user passed filter program * @len: the length of the user passed filter program * @new_prog: buffer where converted program will be stored @@ -815,12 +322,12 @@ static bool convert_bpf_extensions(struct sock_filter *fp, * Conversion workflow: * * 1) First pass for calculating the new program length: - * sk_convert_filter(old_prog, old_len, NULL, &new_len) + * bpf_convert_filter(old_prog, old_len, NULL, &new_len) * * 2) 2nd pass to remap in two passes: 1st pass finds new * jump offsets, 2nd pass remapping: - * new_prog = kmalloc(sizeof(struct sock_filter_int) * new_len); - * sk_convert_filter(old_prog, old_len, new_prog, &new_len); + * new_prog = kmalloc(sizeof(struct bpf_insn) * new_len); + * bpf_convert_filter(old_prog, old_len, new_prog, &new_len); * * User BPF's register A is mapped to our BPF register 6, user BPF * register X is mapped to BPF register 7; frame pointer is always @@ -828,11 +335,11 @@ static bool convert_bpf_extensions(struct sock_filter *fp, * for socket filters: ctx == 'struct sk_buff *', for seccomp: * ctx == 'struct seccomp_data *'. */ -int sk_convert_filter(struct sock_filter *prog, int len, - struct sock_filter_int *new_prog, int *new_len) +int bpf_convert_filter(struct sock_filter *prog, int len, + struct bpf_insn *new_prog, int *new_len) { int new_flen = 0, pass = 0, target, i; - struct sock_filter_int *new_insn; + struct bpf_insn *new_insn; struct sock_filter *fp; int *addrs = NULL; u8 bpf_src; @@ -858,8 +365,8 @@ do_pass: new_insn++; for (i = 0; i < len; fp++, i++) { - struct sock_filter_int tmp_insns[6] = { }; - struct sock_filter_int *insn = tmp_insns; + struct bpf_insn tmp_insns[6] = { }; + struct bpf_insn *insn = tmp_insns; if (addrs) addrs[i] = new_insn - new_prog; @@ -1094,7 +601,7 @@ err: * a cell if not previously written, and we check all branches to be sure * a malicious user doesn't try to abuse us. */ -static int check_load_and_stores(struct sock_filter *filter, int flen) +static int check_load_and_stores(const struct sock_filter *filter, int flen) { u16 *masks, memvalid = 0; /* One bit per cell, 16 cells */ int pc, ret = 0; @@ -1214,7 +721,7 @@ static bool chk_code_allowed(u16 code_to_probe) } /** - * sk_chk_filter - verify socket filter code + * bpf_check_classic - verify socket filter code * @filter: filter to verify * @flen: length of filter * @@ -1227,7 +734,7 @@ static bool chk_code_allowed(u16 code_to_probe) * * Returns 0 if the rule set is legal or -EINVAL if not. */ -int sk_chk_filter(struct sock_filter *filter, unsigned int flen) +int bpf_check_classic(const struct sock_filter *filter, unsigned int flen) { bool anc_found; int pc; @@ -1237,7 +744,7 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen) /* Check the filter code now */ for (pc = 0; pc < flen; pc++) { - struct sock_filter *ftest = &filter[pc]; + const struct sock_filter *ftest = &filter[pc]; /* May we actually operate on this code? */ if (!chk_code_allowed(ftest->code)) @@ -1301,12 +808,12 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen) return -EINVAL; } -EXPORT_SYMBOL(sk_chk_filter); +EXPORT_SYMBOL(bpf_check_classic); -static int sk_store_orig_filter(struct sk_filter *fp, - const struct sock_fprog *fprog) +static int bpf_prog_store_orig_filter(struct bpf_prog *fp, + const struct sock_fprog *fprog) { - unsigned int fsize = sk_filter_proglen(fprog); + unsigned int fsize = bpf_classic_proglen(fprog); struct sock_fprog_kern *fkprog; fp->orig_prog = kmalloc(sizeof(*fkprog), GFP_KERNEL); @@ -1324,7 +831,7 @@ static int sk_store_orig_filter(struct sk_filter *fp, return 0; } -static void sk_release_orig_filter(struct sk_filter *fp) +static void bpf_release_orig_filter(struct bpf_prog *fp) { struct sock_fprog_kern *fprog = fp->orig_prog; @@ -1334,6 +841,18 @@ static void sk_release_orig_filter(struct sk_filter *fp) } } +static void __bpf_prog_release(struct bpf_prog *prog) +{ + bpf_release_orig_filter(prog); + bpf_prog_free(prog); +} + +static void __sk_filter_release(struct sk_filter *fp) +{ + __bpf_prog_release(fp->prog); + kfree(fp); +} + /** * sk_filter_release_rcu - Release a socket filter by rcu_head * @rcu: rcu_head that contains the sk_filter to free @@ -1342,8 +861,7 @@ static void sk_filter_release_rcu(struct rcu_head *rcu) { struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu); - sk_release_orig_filter(fp); - sk_filter_free(fp); + __sk_filter_release(fp); } /** @@ -1360,44 +878,33 @@ static void sk_filter_release(struct sk_filter *fp) void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp) { - atomic_sub(sk_filter_size(fp->len), &sk->sk_omem_alloc); - sk_filter_release(fp); -} + u32 filter_size = bpf_prog_size(fp->prog->len); -void sk_filter_charge(struct sock *sk, struct sk_filter *fp) -{ - atomic_inc(&fp->refcnt); - atomic_add(sk_filter_size(fp->len), &sk->sk_omem_alloc); + atomic_sub(filter_size, &sk->sk_omem_alloc); + sk_filter_release(fp); } -static struct sk_filter *__sk_migrate_realloc(struct sk_filter *fp, - struct sock *sk, - unsigned int len) +/* try to charge the socket memory if there is space available + * return true on success + */ +bool sk_filter_charge(struct sock *sk, struct sk_filter *fp) { - struct sk_filter *fp_new; - - if (sk == NULL) - return krealloc(fp, len, GFP_KERNEL); - - fp_new = sock_kmalloc(sk, len, GFP_KERNEL); - if (fp_new) { - *fp_new = *fp; - /* As we're keeping orig_prog in fp_new along, - * we need to make sure we're not evicting it - * from the old fp. - */ - fp->orig_prog = NULL; - sk_filter_uncharge(sk, fp); + u32 filter_size = bpf_prog_size(fp->prog->len); + + /* same check as in sock_kmalloc() */ + if (filter_size <= sysctl_optmem_max && + atomic_read(&sk->sk_omem_alloc) + filter_size < sysctl_optmem_max) { + atomic_inc(&fp->refcnt); + atomic_add(filter_size, &sk->sk_omem_alloc); + return true; } - - return fp_new; + return false; } -static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp, - struct sock *sk) +static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp) { struct sock_filter *old_prog; - struct sk_filter *old_fp; + struct bpf_prog *old_fp; int err, new_len, old_len = fp->len; /* We are free to overwrite insns et al right here as it @@ -1406,7 +913,7 @@ static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp, * representation. */ BUILD_BUG_ON(sizeof(struct sock_filter) != - sizeof(struct sock_filter_int)); + sizeof(struct bpf_insn)); /* Conversion cannot happen on overlapping memory areas, * so we need to keep the user BPF around until the 2nd @@ -1420,13 +927,13 @@ static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp, } /* 1st pass: calculate the new program length. */ - err = sk_convert_filter(old_prog, old_len, NULL, &new_len); + err = bpf_convert_filter(old_prog, old_len, NULL, &new_len); if (err) goto out_err_free; /* Expand fp for appending the new filter representation. */ old_fp = fp; - fp = __sk_migrate_realloc(old_fp, sk, sk_filter_size(new_len)); + fp = krealloc(old_fp, bpf_prog_size(new_len), GFP_KERNEL); if (!fp) { /* The old_fp is still around in case we couldn't * allocate new memory, so uncharge on that one. @@ -1438,17 +945,17 @@ static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp, fp->len = new_len; - /* 2nd pass: remap sock_filter insns into sock_filter_int insns. */ - err = sk_convert_filter(old_prog, old_len, fp->insnsi, &new_len); + /* 2nd pass: remap sock_filter insns into bpf_insn insns. */ + err = bpf_convert_filter(old_prog, old_len, fp->insnsi, &new_len); if (err) - /* 2nd sk_convert_filter() can fail only if it fails + /* 2nd bpf_convert_filter() can fail only if it fails * to allocate memory, remapping must succeed. Note, * that at this time old_fp has already been released - * by __sk_migrate_realloc(). + * by krealloc(). */ goto out_err_free; - sk_filter_select_runtime(fp); + bpf_prog_select_runtime(fp); kfree(old_prog); return fp; @@ -1456,55 +963,20 @@ static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp, out_err_free: kfree(old_prog); out_err: - /* Rollback filter setup. */ - if (sk != NULL) - sk_filter_uncharge(sk, fp); - else - kfree(fp); + __bpf_prog_release(fp); return ERR_PTR(err); } -void __weak bpf_int_jit_compile(struct sk_filter *prog) -{ -} - -/** - * sk_filter_select_runtime - select execution runtime for BPF program - * @fp: sk_filter populated with internal BPF program - * - * try to JIT internal BPF program, if JIT is not available select interpreter - * BPF program will be executed via SK_RUN_FILTER() macro - */ -void sk_filter_select_runtime(struct sk_filter *fp) -{ - fp->bpf_func = (void *) __sk_run_filter; - - /* Probe if internal BPF can be JITed */ - bpf_int_jit_compile(fp); -} -EXPORT_SYMBOL_GPL(sk_filter_select_runtime); - -/* free internal BPF program */ -void sk_filter_free(struct sk_filter *fp) -{ - bpf_jit_free(fp); -} -EXPORT_SYMBOL_GPL(sk_filter_free); - -static struct sk_filter *__sk_prepare_filter(struct sk_filter *fp, - struct sock *sk) +static struct bpf_prog *bpf_prepare_filter(struct bpf_prog *fp) { int err; fp->bpf_func = NULL; fp->jited = 0; - err = sk_chk_filter(fp->insns, fp->len); + err = bpf_check_classic(fp->insns, fp->len); if (err) { - if (sk != NULL) - sk_filter_uncharge(sk, fp); - else - kfree(fp); + __bpf_prog_release(fp); return ERR_PTR(err); } @@ -1517,13 +989,13 @@ static struct sk_filter *__sk_prepare_filter(struct sk_filter *fp, * internal BPF translation for the optimized interpreter. */ if (!fp->jited) - fp = __sk_migrate_filter(fp, sk); + fp = bpf_migrate_filter(fp); return fp; } /** - * sk_unattached_filter_create - create an unattached filter + * bpf_prog_create - create an unattached filter * @pfp: the unattached filter that is created * @fprog: the filter program * @@ -1532,23 +1004,21 @@ static struct sk_filter *__sk_prepare_filter(struct sk_filter *fp, * If an error occurs or there is insufficient memory for the filter * a negative errno code is returned. On success the return is zero. */ -int sk_unattached_filter_create(struct sk_filter **pfp, - struct sock_fprog_kern *fprog) +int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog) { - unsigned int fsize = sk_filter_proglen(fprog); - struct sk_filter *fp; + unsigned int fsize = bpf_classic_proglen(fprog); + struct bpf_prog *fp; /* Make sure new filter is there and in the right amounts. */ if (fprog->filter == NULL) return -EINVAL; - fp = kmalloc(sk_filter_size(fprog->len), GFP_KERNEL); + fp = kmalloc(bpf_prog_size(fprog->len), GFP_KERNEL); if (!fp) return -ENOMEM; memcpy(fp->insns, fprog->filter, fsize); - atomic_set(&fp->refcnt, 1); fp->len = fprog->len; /* Since unattached filters are not copied back to user * space through sk_get_filter(), we do not need to hold @@ -1556,23 +1026,23 @@ int sk_unattached_filter_create(struct sk_filter **pfp, */ fp->orig_prog = NULL; - /* __sk_prepare_filter() already takes care of uncharging + /* bpf_prepare_filter() already takes care of freeing * memory in case something goes wrong. */ - fp = __sk_prepare_filter(fp, NULL); + fp = bpf_prepare_filter(fp); if (IS_ERR(fp)) return PTR_ERR(fp); *pfp = fp; return 0; } -EXPORT_SYMBOL_GPL(sk_unattached_filter_create); +EXPORT_SYMBOL_GPL(bpf_prog_create); -void sk_unattached_filter_destroy(struct sk_filter *fp) +void bpf_prog_destroy(struct bpf_prog *fp) { - sk_filter_release(fp); + __bpf_prog_release(fp); } -EXPORT_SYMBOL_GPL(sk_unattached_filter_destroy); +EXPORT_SYMBOL_GPL(bpf_prog_destroy); /** * sk_attach_filter - attach a socket filter @@ -1587,8 +1057,9 @@ EXPORT_SYMBOL_GPL(sk_unattached_filter_destroy); int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) { struct sk_filter *fp, *old_fp; - unsigned int fsize = sk_filter_proglen(fprog); - unsigned int sk_fsize = sk_filter_size(fprog->len); + unsigned int fsize = bpf_classic_proglen(fprog); + unsigned int bpf_fsize = bpf_prog_size(fprog->len); + struct bpf_prog *prog; int err; if (sock_flag(sk, SOCK_FILTER_LOCKED)) @@ -1598,30 +1069,43 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) if (fprog->filter == NULL) return -EINVAL; - fp = sock_kmalloc(sk, sk_fsize, GFP_KERNEL); - if (!fp) + prog = kmalloc(bpf_fsize, GFP_KERNEL); + if (!prog) return -ENOMEM; - if (copy_from_user(fp->insns, fprog->filter, fsize)) { - sock_kfree_s(sk, fp, sk_fsize); + if (copy_from_user(prog->insns, fprog->filter, fsize)) { + kfree(prog); return -EFAULT; } - atomic_set(&fp->refcnt, 1); - fp->len = fprog->len; + prog->len = fprog->len; - err = sk_store_orig_filter(fp, fprog); + err = bpf_prog_store_orig_filter(prog, fprog); if (err) { - sk_filter_uncharge(sk, fp); + kfree(prog); return -ENOMEM; } - /* __sk_prepare_filter() already takes care of uncharging + /* bpf_prepare_filter() already takes care of freeing * memory in case something goes wrong. */ - fp = __sk_prepare_filter(fp, sk); - if (IS_ERR(fp)) - return PTR_ERR(fp); + prog = bpf_prepare_filter(prog); + if (IS_ERR(prog)) + return PTR_ERR(prog); + + fp = kmalloc(sizeof(*fp), GFP_KERNEL); + if (!fp) { + __bpf_prog_release(prog); + return -ENOMEM; + } + fp->prog = prog; + + atomic_set(&fp->refcnt, 0); + + if (!sk_filter_charge(sk, fp)) { + __sk_filter_release(fp); + return -ENOMEM; + } old_fp = rcu_dereference_protected(sk->sk_filter, sock_owned_by_user(sk)); @@ -1670,7 +1154,7 @@ int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, /* We're copying the filter that has been originally attached, * so no conversion/decode needed anymore. */ - fprog = filter->orig_prog; + fprog = filter->prog->orig_prog; ret = fprog->len; if (!len) @@ -1682,7 +1166,7 @@ int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, goto out; ret = -EFAULT; - if (copy_to_user(ubuf, fprog->filter, sk_filter_proglen(fprog))) + if (copy_to_user(ubuf, fprog->filter, bpf_classic_proglen(fprog))) goto out; /* Instead of bytes, the API requests to return the number |