From: Alexei Starovoitov Date: Fri, 28 Mar 2014 17:58:25 +0000 (+0100) Subject: net: filter: rework/optimize internal BPF interpreter's instruction set X-Git-Url: https://git.karo-electronics.de/?a=commitdiff_plain;h=bd4cf0ed3;p=linux-beck.git net: filter: rework/optimize internal BPF interpreter's instruction set This patch replaces/reworks the kernel-internal BPF interpreter with an optimized BPF instruction set format that is modelled closer to mimic native instruction sets and is designed to be JITed with one to one mapping. Thus, the new interpreter is noticeably faster than the current implementation of sk_run_filter(); mainly for two reasons: 1. Fall-through jumps: BPF jump instructions are forced to go either 'true' or 'false' branch which causes branch-miss penalty. The new BPF jump instructions have only one branch and fall-through otherwise, which fits the CPU branch predictor logic better. `perf stat` shows drastic difference for branch-misses between the old and new code. 2. Jump-threaded implementation of interpreter vs switch statement: Instead of single table-jump at the top of 'switch' statement, gcc will now generate multiple table-jump instructions, which helps CPU branch predictor logic. Note that the verification of filters is still being done through sk_chk_filter() in classical BPF format, so filters from user- or kernel space are verified in the same way as we do now, and same restrictions/constraints hold as well. We reuse current BPF JIT compilers in a way that this upgrade would even be fine as is, but nevertheless allows for a successive upgrade of BPF JIT compilers to the new format. The internal instruction set migration is being done after the probing for JIT compilation, so in case JIT compilers are able to create a native opcode image, we're going to use that, and in all other cases we're doing a follow-up migration of the BPF program's instruction set, so that it can be transparently run in the new interpreter. In short, the *internal* format extends BPF in the following way (more details can be taken from the appended documentation): - Number of registers increase from 2 to 10 - Register width increases from 32-bit to 64-bit - Conditional jt/jf targets replaced with jt/fall-through - Adds signed > and >= insns - 16 4-byte stack slots for register spill-fill replaced with up to 512 bytes of multi-use stack space - Introduction of bpf_call insn and register passing convention for zero overhead calls from/to other kernel functions - Adds arithmetic right shift and endianness conversion insns - Adds atomic_add insn - Old tax/txa insns are replaced with 'mov dst,src' insn Performance of two BPF filters generated by libpcap resp. bpf_asm was measured on x86_64, i386 and arm32 (other libpcap programs have similar performance differences): fprog #1 is taken from Documentation/networking/filter.txt: tcpdump -i eth0 port 22 -dd fprog #2 is taken from 'man tcpdump': tcpdump -i eth0 'tcp port 22 and (((ip[2:2] - ((ip[0]&0xf)<<2)) - ((tcp[12]&0xf0)>>2)) != 0)' -dd Raw performance data from BPF micro-benchmark: SK_RUN_FILTER on the same SKB (cache-hit) or 10k SKBs (cache-miss); time in ns per call, smaller is better: --x86_64-- fprog #1 fprog #1 fprog #2 fprog #2 cache-hit cache-miss cache-hit cache-miss old BPF 90 101 192 202 new BPF 31 71 47 97 old BPF jit 12 34 17 44 new BPF jit TBD --i386-- fprog #1 fprog #1 fprog #2 fprog #2 cache-hit cache-miss cache-hit cache-miss old BPF 107 136 227 252 new BPF 40 119 69 172 --arm32-- fprog #1 fprog #1 fprog #2 fprog #2 cache-hit cache-miss cache-hit cache-miss old BPF 202 300 475 540 new BPF 180 270 330 470 old BPF jit 26 182 37 202 new BPF jit TBD Thus, without changing any userland BPF filters, applications on top of AF_PACKET (or other families) such as libpcap/tcpdump, cls_bpf classifier, netfilter's xt_bpf, team driver's load-balancing mode, and many more will have better interpreter filtering performance. While we are replacing the internal BPF interpreter, we also need to convert seccomp BPF in the same step to make use of the new internal structure since it makes use of lower-level API details without being further decoupled through higher-level calls like sk_unattached_filter_{create,destroy}(), for example. Just as for normal socket filtering, also seccomp BPF experiences a time-to-verdict speedup: 05-sim-long_jumps.c of libseccomp was used as micro-benchmark: seccomp_rule_add_exact(ctx,... seccomp_rule_add_exact(ctx,... rc = seccomp_load(ctx); for (i = 0; i < 10000000; i++) syscall(199, 100); 'short filter' has 2 rules 'large filter' has 200 rules 'short filter' performance is slightly better on x86_64/i386/arm32 'large filter' is much faster on x86_64 and i386 and shows no difference on arm32 --x86_64-- short filter old BPF: 2.7 sec 39.12% bench libc-2.15.so [.] syscall 8.10% bench [kernel.kallsyms] [k] sk_run_filter 6.31% bench [kernel.kallsyms] [k] system_call 5.59% bench [kernel.kallsyms] [k] trace_hardirqs_on_caller 4.37% bench [kernel.kallsyms] [k] trace_hardirqs_off_caller 3.70% bench [kernel.kallsyms] [k] __secure_computing 3.67% bench [kernel.kallsyms] [k] lock_is_held 3.03% bench [kernel.kallsyms] [k] seccomp_bpf_load new BPF: 2.58 sec 42.05% bench libc-2.15.so [.] syscall 6.91% bench [kernel.kallsyms] [k] system_call 6.25% bench [kernel.kallsyms] [k] trace_hardirqs_on_caller 6.07% bench [kernel.kallsyms] [k] __secure_computing 5.08% bench [kernel.kallsyms] [k] sk_run_filter_int_seccomp --arm32-- short filter old BPF: 4.0 sec 39.92% bench [kernel.kallsyms] [k] vector_swi 16.60% bench [kernel.kallsyms] [k] sk_run_filter 14.66% bench libc-2.17.so [.] syscall 5.42% bench [kernel.kallsyms] [k] seccomp_bpf_load 5.10% bench [kernel.kallsyms] [k] __secure_computing new BPF: 3.7 sec 35.93% bench [kernel.kallsyms] [k] vector_swi 21.89% bench libc-2.17.so [.] syscall 13.45% bench [kernel.kallsyms] [k] sk_run_filter_int_seccomp 6.25% bench [kernel.kallsyms] [k] __secure_computing 3.96% bench [kernel.kallsyms] [k] syscall_trace_exit --x86_64-- large filter old BPF: 8.6 seconds 73.38% bench [kernel.kallsyms] [k] sk_run_filter 10.70% bench libc-2.15.so [.] syscall 5.09% bench [kernel.kallsyms] [k] seccomp_bpf_load 1.97% bench [kernel.kallsyms] [k] system_call new BPF: 5.7 seconds 66.20% bench [kernel.kallsyms] [k] sk_run_filter_int_seccomp 16.75% bench libc-2.15.so [.] syscall 3.31% bench [kernel.kallsyms] [k] system_call 2.88% bench [kernel.kallsyms] [k] __secure_computing --i386-- large filter old BPF: 5.4 sec new BPF: 3.8 sec --arm32-- large filter old BPF: 13.5 sec 73.88% bench [kernel.kallsyms] [k] sk_run_filter 10.29% bench [kernel.kallsyms] [k] vector_swi 6.46% bench libc-2.17.so [.] syscall 2.94% bench [kernel.kallsyms] [k] seccomp_bpf_load 1.19% bench [kernel.kallsyms] [k] __secure_computing 0.87% bench [kernel.kallsyms] [k] sys_getuid new BPF: 13.5 sec 76.08% bench [kernel.kallsyms] [k] sk_run_filter_int_seccomp 10.98% bench [kernel.kallsyms] [k] vector_swi 5.87% bench libc-2.17.so [.] syscall 1.77% bench [kernel.kallsyms] [k] __secure_computing 0.93% bench [kernel.kallsyms] [k] sys_getuid BPF filters generated by seccomp are very branchy, so the new internal BPF performance is better than the old one. Performance gains will be even higher when BPF JIT is committed for the new structure, which is planned in future work (as successive JIT migrations). BPF has also been stress-tested with trinity's BPF fuzzer. Joint work with Daniel Borkmann. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Cc: Hagen Paul Pfeifer Cc: Kees Cook Cc: Paul Moore Cc: Ingo Molnar Cc: H. Peter Anvin Cc: linux-kernel@vger.kernel.org Acked-by: Kees Cook Signed-off-by: David S. Miller --- diff --git a/include/linux/filter.h b/include/linux/filter.h index 9bde3ed19fe6..262dcbb75ffe 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -9,13 +9,58 @@ #include #include -#ifdef CONFIG_COMPAT -/* - * A struct sock_filter is architecture independent. +/* Internally used and optimized filter representation with extended + * instruction set based on top of classic BPF. */ + +/* instruction classes */ +#define BPF_ALU64 0x07 /* alu mode in double word width */ + +/* ld/ldx fields */ +#define BPF_DW 0x18 /* double word */ +#define BPF_XADD 0xc0 /* exclusive add */ + +/* alu/jmp fields */ +#define BPF_MOV 0xb0 /* mov reg to reg */ +#define BPF_ARSH 0xc0 /* sign extending arithmetic shift right */ + +/* change endianness of a register */ +#define BPF_END 0xd0 /* flags for endianness conversion: */ +#define BPF_TO_LE 0x00 /* convert to little-endian */ +#define BPF_TO_BE 0x08 /* convert to big-endian */ +#define BPF_FROM_LE BPF_TO_LE +#define BPF_FROM_BE BPF_TO_BE + +#define BPF_JNE 0x50 /* jump != */ +#define BPF_JSGT 0x60 /* SGT is signed '>', GT in x86 */ +#define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */ +#define BPF_CALL 0x80 /* function call */ +#define BPF_EXIT 0x90 /* function return */ + +/* BPF has 10 general purpose 64-bit registers and stack frame. */ +#define MAX_BPF_REG 11 + +/* BPF program can access up to 512 bytes of stack space. */ +#define MAX_BPF_STACK 512 + +/* Arg1, context and stack frame pointer register positions. */ +#define ARG1_REG 1 +#define CTX_REG 6 +#define FP_REG 10 + +struct sock_filter_int { + __u8 code; /* opcode */ + __u8 a_reg:4; /* dest register */ + __u8 x_reg:4; /* source register */ + __s16 off; /* signed offset */ + __s32 imm; /* signed immediate constant */ +}; + +#ifdef CONFIG_COMPAT +/* A struct sock_filter is architecture independent. */ struct compat_sock_fprog { u16 len; - compat_uptr_t filter; /* struct sock_filter * */ + compat_uptr_t filter; /* struct sock_filter * */ }; #endif @@ -26,6 +71,7 @@ struct sock_fprog_kern { struct sk_buff; struct sock; +struct seccomp_data; struct sk_filter { atomic_t refcnt; @@ -34,9 +80,10 @@ struct sk_filter { struct sock_fprog_kern *orig_prog; /* Original BPF program */ struct rcu_head rcu; unsigned int (*bpf_func)(const struct sk_buff *skb, - const struct sock_filter *filter); + const struct sock_filter_int *filter); union { - struct sock_filter insns[0]; + struct sock_filter insns[0]; + struct sock_filter_int insnsi[0]; struct work_struct work; }; }; @@ -50,9 +97,18 @@ static inline unsigned int sk_filter_size(unsigned int proglen) #define sk_filter_proglen(fprog) \ (fprog->len * sizeof(fprog->filter[0])) +#define SK_RUN_FILTER(filter, ctx) \ + (*filter->bpf_func)(ctx, filter->insnsi) + int sk_filter(struct sock *sk, struct sk_buff *skb); -unsigned int sk_run_filter(const struct sk_buff *skb, - const struct sock_filter *filter); + +u32 sk_run_filter_int_seccomp(const struct seccomp_data *ctx, + const struct sock_filter_int *insni); +u32 sk_run_filter_int_skb(const struct sk_buff *ctx, + const struct sock_filter_int *insni); + +int sk_convert_filter(struct sock_filter *prog, int len, + struct sock_filter_int *new_prog, int *new_len); int sk_unattached_filter_create(struct sk_filter **pfp, struct sock_fprog *fprog); @@ -86,7 +142,6 @@ static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen, print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_OFFSET, 16, 1, image, proglen, false); } -#define SK_RUN_FILTER(FILTER, SKB) (*FILTER->bpf_func)(SKB, FILTER->insns) #else #include static inline void bpf_jit_compile(struct sk_filter *fp) @@ -96,7 +151,6 @@ static inline void bpf_jit_free(struct sk_filter *fp) { kfree(fp); } -#define SK_RUN_FILTER(FILTER, SKB) sk_run_filter(SKB, FILTER->insns) #endif static inline int bpf_tell_extensions(void) diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index 6f19cfd1840e..4054b0994071 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -76,7 +76,6 @@ static inline int seccomp_mode(struct seccomp *s) #ifdef CONFIG_SECCOMP_FILTER extern void put_seccomp_filter(struct task_struct *tsk); extern void get_seccomp_filter(struct task_struct *tsk); -extern u32 seccomp_bpf_load(int off); #else /* CONFIG_SECCOMP_FILTER */ static inline void put_seccomp_filter(struct task_struct *tsk) { diff --git a/kernel/seccomp.c b/kernel/seccomp.c index b7a10048a32c..4f18e754c23e 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -55,60 +55,33 @@ struct seccomp_filter { atomic_t usage; struct seccomp_filter *prev; unsigned short len; /* Instruction count */ - struct sock_filter insns[]; + struct sock_filter_int insnsi[]; }; /* Limit any path through the tree to 256KB worth of instructions. */ #define MAX_INSNS_PER_PATH ((1 << 18) / sizeof(struct sock_filter)) -/** - * get_u32 - returns a u32 offset into data - * @data: a unsigned 64 bit value - * @index: 0 or 1 to return the first or second 32-bits - * - * This inline exists to hide the length of unsigned long. If a 32-bit - * unsigned long is passed in, it will be extended and the top 32-bits will be - * 0. If it is a 64-bit unsigned long, then whatever data is resident will be - * properly returned. - * +/* * Endianness is explicitly ignored and left for BPF program authors to manage * as per the specific architecture. */ -static inline u32 get_u32(u64 data, int index) +static void populate_seccomp_data(struct seccomp_data *sd) { - return ((u32 *)&data)[index]; -} + struct task_struct *task = current; + struct pt_regs *regs = task_pt_regs(task); -/* Helper for bpf_load below. */ -#define BPF_DATA(_name) offsetof(struct seccomp_data, _name) -/** - * bpf_load: checks and returns a pointer to the requested offset - * @off: offset into struct seccomp_data to load from - * - * Returns the requested 32-bits of data. - * seccomp_check_filter() should assure that @off is 32-bit aligned - * and not out of bounds. Failure to do so is a BUG. - */ -u32 seccomp_bpf_load(int off) -{ - struct pt_regs *regs = task_pt_regs(current); - if (off == BPF_DATA(nr)) - return syscall_get_nr(current, regs); - if (off == BPF_DATA(arch)) - return syscall_get_arch(current, regs); - if (off >= BPF_DATA(args[0]) && off < BPF_DATA(args[6])) { - unsigned long value; - int arg = (off - BPF_DATA(args[0])) / sizeof(u64); - int index = !!(off % sizeof(u64)); - syscall_get_arguments(current, regs, arg, 1, &value); - return get_u32(value, index); - } - if (off == BPF_DATA(instruction_pointer)) - return get_u32(KSTK_EIP(current), 0); - if (off == BPF_DATA(instruction_pointer) + sizeof(u32)) - return get_u32(KSTK_EIP(current), 1); - /* seccomp_check_filter should make this impossible. */ - BUG(); + sd->nr = syscall_get_nr(task, regs); + sd->arch = syscall_get_arch(task, regs); + + /* Unroll syscall_get_args to help gcc on arm. */ + syscall_get_arguments(task, regs, 0, 1, (unsigned long *) &sd->args[0]); + syscall_get_arguments(task, regs, 1, 1, (unsigned long *) &sd->args[1]); + syscall_get_arguments(task, regs, 2, 1, (unsigned long *) &sd->args[2]); + syscall_get_arguments(task, regs, 3, 1, (unsigned long *) &sd->args[3]); + syscall_get_arguments(task, regs, 4, 1, (unsigned long *) &sd->args[4]); + syscall_get_arguments(task, regs, 5, 1, (unsigned long *) &sd->args[5]); + + sd->instruction_pointer = KSTK_EIP(task); } /** @@ -133,17 +106,17 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen) switch (code) { case BPF_S_LD_W_ABS: - ftest->code = BPF_S_ANC_SECCOMP_LD_W; + ftest->code = BPF_LDX | BPF_W | BPF_ABS; /* 32-bit aligned and not out of bounds. */ if (k >= sizeof(struct seccomp_data) || k & 3) return -EINVAL; continue; case BPF_S_LD_W_LEN: - ftest->code = BPF_S_LD_IMM; + ftest->code = BPF_LD | BPF_IMM; ftest->k = sizeof(struct seccomp_data); continue; case BPF_S_LDX_W_LEN: - ftest->code = BPF_S_LDX_IMM; + ftest->code = BPF_LDX | BPF_IMM; ftest->k = sizeof(struct seccomp_data); continue; /* Explicitly include allowed calls. */ @@ -185,6 +158,7 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen) case BPF_S_JMP_JGT_X: case BPF_S_JMP_JSET_K: case BPF_S_JMP_JSET_X: + sk_decode_filter(ftest, ftest); continue; default: return -EINVAL; @@ -202,18 +176,21 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen) static u32 seccomp_run_filters(int syscall) { struct seccomp_filter *f; + struct seccomp_data sd; u32 ret = SECCOMP_RET_ALLOW; /* Ensure unexpected behavior doesn't result in failing open. */ if (WARN_ON(current->seccomp.filter == NULL)) return SECCOMP_RET_KILL; + populate_seccomp_data(&sd); + /* * All filters in the list are evaluated and the lowest BPF return * value always takes priority (ignoring the DATA). */ for (f = current->seccomp.filter; f; f = f->prev) { - u32 cur_ret = sk_run_filter(NULL, f->insns); + u32 cur_ret = sk_run_filter_int_seccomp(&sd, f->insnsi); if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION)) ret = cur_ret; } @@ -231,6 +208,8 @@ static long seccomp_attach_filter(struct sock_fprog *fprog) struct seccomp_filter *filter; unsigned long fp_size = fprog->len * sizeof(struct sock_filter); unsigned long total_insns = fprog->len; + struct sock_filter *fp; + int new_len; long ret; if (fprog->len == 0 || fprog->len > BPF_MAXINSNS) @@ -252,28 +231,43 @@ static long seccomp_attach_filter(struct sock_fprog *fprog) CAP_SYS_ADMIN) != 0) return -EACCES; - /* Allocate a new seccomp_filter */ - filter = kzalloc(sizeof(struct seccomp_filter) + fp_size, - GFP_KERNEL|__GFP_NOWARN); - if (!filter) + fp = kzalloc(fp_size, GFP_KERNEL|__GFP_NOWARN); + if (!fp) return -ENOMEM; - atomic_set(&filter->usage, 1); - filter->len = fprog->len; /* Copy the instructions from fprog. */ ret = -EFAULT; - if (copy_from_user(filter->insns, fprog->filter, fp_size)) - goto fail; + if (copy_from_user(fp, fprog->filter, fp_size)) + goto free_prog; /* Check and rewrite the fprog via the skb checker */ - ret = sk_chk_filter(filter->insns, filter->len); + ret = sk_chk_filter(fp, fprog->len); if (ret) - goto fail; + goto free_prog; /* Check and rewrite the fprog for seccomp use */ - ret = seccomp_check_filter(filter->insns, filter->len); + ret = seccomp_check_filter(fp, fprog->len); + if (ret) + goto free_prog; + + /* Convert 'sock_filter' insns to 'sock_filter_int' insns */ + ret = sk_convert_filter(fp, fprog->len, NULL, &new_len); + if (ret) + goto free_prog; + + /* Allocate a new seccomp_filter */ + filter = kzalloc(sizeof(struct seccomp_filter) + + sizeof(struct sock_filter_int) * new_len, + GFP_KERNEL|__GFP_NOWARN); + if (!filter) + goto free_prog; + + ret = sk_convert_filter(fp, fprog->len, filter->insnsi, &new_len); if (ret) - goto fail; + goto free_filter; + + atomic_set(&filter->usage, 1); + filter->len = new_len; /* * If there is an existing filter, make it the prev and don't drop its @@ -282,8 +276,11 @@ static long seccomp_attach_filter(struct sock_fprog *fprog) filter->prev = current->seccomp.filter; current->seccomp.filter = filter; return 0; -fail: + +free_filter: kfree(filter); +free_prog: + kfree(fp); return ret; } diff --git a/net/core/filter.c b/net/core/filter.c index 5b3427aaeca5..3733381190ec 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1,11 +1,16 @@ /* * Linux Socket Filter - Kernel level socket filtering * - * Author: - * Jay Schulist + * Based on the design of the Berkeley Packet Filter. The new + * internal format has been designed by PLUMgrid: * - * Based on the design of: - * - The Berkeley Packet Filter + * Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com + * + * Authors: + * + * Jay Schulist + * Alexei Starovoitov + * Daniel Borkmann * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -108,304 +113,1045 @@ 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 socket - * @skb: buffer to run the filter on + * __sk_run_filter - run a filter on a given context + * @ctx: buffer to run the filter on * @fentry: filter to apply * - * Decode and apply filter instructions to the skb->data. - * Return length to keep, 0 for none. @skb is the data we are - * filtering, @filter is the array of filter instructions. - * Because all jumps are guaranteed to be before last instruction, - * and last instruction guaranteed to be a RET, we dont need to check - * flen. (We used to pass to this function the length of filter) + * Decode and apply filter instructions to the skb->data. Return length to + * keep, 0 for none. @ctx is the data we are operating on, @filter is the + * array of filter instructions. */ -unsigned int sk_run_filter(const struct sk_buff *skb, - const struct sock_filter *fentry) +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; void *ptr; - u32 A = 0; /* Accumulator */ - u32 X = 0; /* Index Register */ - u32 mem[BPF_MEMWORDS]; /* Scratch Memory Store */ - u32 tmp; - int k; + int off; + +#define K insn->imm +#define A regs[insn->a_reg] +#define X regs[insn->x_reg] +#define R0 regs[0] + +#define CONT ({insn++; goto select_insn; }) +#define CONT_JMP ({insn++; goto select_insn; }) + + static const void *jumptable[256] = { + [0 ... 255] = &&default_label, + /* Now overwrite non-defaults ... */ +#define DL(A, B, C) [A|B|C] = &&A##_##B##_##C + DL(BPF_ALU, BPF_ADD, BPF_X), + DL(BPF_ALU, BPF_ADD, BPF_K), + DL(BPF_ALU, BPF_SUB, BPF_X), + DL(BPF_ALU, BPF_SUB, BPF_K), + DL(BPF_ALU, BPF_AND, BPF_X), + DL(BPF_ALU, BPF_AND, BPF_K), + DL(BPF_ALU, BPF_OR, BPF_X), + DL(BPF_ALU, BPF_OR, BPF_K), + DL(BPF_ALU, BPF_LSH, BPF_X), + DL(BPF_ALU, BPF_LSH, BPF_K), + DL(BPF_ALU, BPF_RSH, BPF_X), + DL(BPF_ALU, BPF_RSH, BPF_K), + DL(BPF_ALU, BPF_XOR, BPF_X), + DL(BPF_ALU, BPF_XOR, BPF_K), + DL(BPF_ALU, BPF_MUL, BPF_X), + DL(BPF_ALU, BPF_MUL, BPF_K), + DL(BPF_ALU, BPF_MOV, BPF_X), + DL(BPF_ALU, BPF_MOV, BPF_K), + DL(BPF_ALU, BPF_DIV, BPF_X), + DL(BPF_ALU, BPF_DIV, BPF_K), + DL(BPF_ALU, BPF_MOD, BPF_X), + DL(BPF_ALU, BPF_MOD, BPF_K), + DL(BPF_ALU, BPF_NEG, 0), + DL(BPF_ALU, BPF_END, BPF_TO_BE), + DL(BPF_ALU, BPF_END, BPF_TO_LE), + DL(BPF_ALU64, BPF_ADD, BPF_X), + DL(BPF_ALU64, BPF_ADD, BPF_K), + DL(BPF_ALU64, BPF_SUB, BPF_X), + DL(BPF_ALU64, BPF_SUB, BPF_K), + DL(BPF_ALU64, BPF_AND, BPF_X), + DL(BPF_ALU64, BPF_AND, BPF_K), + DL(BPF_ALU64, BPF_OR, BPF_X), + DL(BPF_ALU64, BPF_OR, BPF_K), + DL(BPF_ALU64, BPF_LSH, BPF_X), + DL(BPF_ALU64, BPF_LSH, BPF_K), + DL(BPF_ALU64, BPF_RSH, BPF_X), + DL(BPF_ALU64, BPF_RSH, BPF_K), + DL(BPF_ALU64, BPF_XOR, BPF_X), + DL(BPF_ALU64, BPF_XOR, BPF_K), + DL(BPF_ALU64, BPF_MUL, BPF_X), + DL(BPF_ALU64, BPF_MUL, BPF_K), + DL(BPF_ALU64, BPF_MOV, BPF_X), + DL(BPF_ALU64, BPF_MOV, BPF_K), + DL(BPF_ALU64, BPF_ARSH, BPF_X), + DL(BPF_ALU64, BPF_ARSH, BPF_K), + DL(BPF_ALU64, BPF_DIV, BPF_X), + DL(BPF_ALU64, BPF_DIV, BPF_K), + DL(BPF_ALU64, BPF_MOD, BPF_X), + DL(BPF_ALU64, BPF_MOD, BPF_K), + DL(BPF_ALU64, BPF_NEG, 0), + DL(BPF_JMP, BPF_CALL, 0), + DL(BPF_JMP, BPF_JA, 0), + DL(BPF_JMP, BPF_JEQ, BPF_X), + DL(BPF_JMP, BPF_JEQ, BPF_K), + DL(BPF_JMP, BPF_JNE, BPF_X), + DL(BPF_JMP, BPF_JNE, BPF_K), + DL(BPF_JMP, BPF_JGT, BPF_X), + DL(BPF_JMP, BPF_JGT, BPF_K), + DL(BPF_JMP, BPF_JGE, BPF_X), + DL(BPF_JMP, BPF_JGE, BPF_K), + DL(BPF_JMP, BPF_JSGT, BPF_X), + DL(BPF_JMP, BPF_JSGT, BPF_K), + DL(BPF_JMP, BPF_JSGE, BPF_X), + DL(BPF_JMP, BPF_JSGE, BPF_K), + DL(BPF_JMP, BPF_JSET, BPF_X), + DL(BPF_JMP, BPF_JSET, BPF_K), + DL(BPF_JMP, BPF_EXIT, 0), + DL(BPF_STX, BPF_MEM, BPF_B), + DL(BPF_STX, BPF_MEM, BPF_H), + DL(BPF_STX, BPF_MEM, BPF_W), + DL(BPF_STX, BPF_MEM, BPF_DW), + DL(BPF_STX, BPF_XADD, BPF_W), + DL(BPF_STX, BPF_XADD, BPF_DW), + DL(BPF_ST, BPF_MEM, BPF_B), + DL(BPF_ST, BPF_MEM, BPF_H), + DL(BPF_ST, BPF_MEM, BPF_W), + DL(BPF_ST, BPF_MEM, BPF_DW), + DL(BPF_LDX, BPF_MEM, BPF_B), + DL(BPF_LDX, BPF_MEM, BPF_H), + DL(BPF_LDX, BPF_MEM, BPF_W), + DL(BPF_LDX, BPF_MEM, BPF_DW), + DL(BPF_LD, BPF_ABS, BPF_W), + DL(BPF_LD, BPF_ABS, BPF_H), + DL(BPF_LD, BPF_ABS, BPF_B), + DL(BPF_LD, BPF_IND, BPF_W), + DL(BPF_LD, BPF_IND, BPF_H), + DL(BPF_LD, BPF_IND, BPF_B), +#undef DL + }; - /* - * Process array of filter instructions. - */ - for (;; fentry++) { -#if defined(CONFIG_X86_32) -#define K (fentry->k) -#else - const u32 K = fentry->k; -#endif - - switch (fentry->code) { - case BPF_S_ALU_ADD_X: - A += X; - continue; - case BPF_S_ALU_ADD_K: - A += K; - continue; - case BPF_S_ALU_SUB_X: - A -= X; - continue; - case BPF_S_ALU_SUB_K: - A -= K; - continue; - case BPF_S_ALU_MUL_X: - A *= X; - continue; - case BPF_S_ALU_MUL_K: - A *= K; - continue; - case BPF_S_ALU_DIV_X: - if (X == 0) - return 0; - A /= X; - continue; - case BPF_S_ALU_DIV_K: - A /= K; - continue; - case BPF_S_ALU_MOD_X: - if (X == 0) - return 0; - A %= X; - continue; - case BPF_S_ALU_MOD_K: - A %= K; - continue; - case BPF_S_ALU_AND_X: - A &= X; - continue; - case BPF_S_ALU_AND_K: - A &= K; - continue; - case BPF_S_ALU_OR_X: - A |= X; - continue; - case BPF_S_ALU_OR_K: - A |= K; - continue; - case BPF_S_ANC_ALU_XOR_X: - case BPF_S_ALU_XOR_X: - A ^= X; - continue; - case BPF_S_ALU_XOR_K: - A ^= K; - continue; - case BPF_S_ALU_LSH_X: - A <<= X; - continue; - case BPF_S_ALU_LSH_K: - A <<= K; - continue; - case BPF_S_ALU_RSH_X: - A >>= X; - continue; - case BPF_S_ALU_RSH_K: - A >>= K; - continue; - case BPF_S_ALU_NEG: - A = -A; - continue; - case BPF_S_JMP_JA: - fentry += K; - continue; - case BPF_S_JMP_JGT_K: - fentry += (A > K) ? fentry->jt : fentry->jf; - continue; - case BPF_S_JMP_JGE_K: - fentry += (A >= K) ? fentry->jt : fentry->jf; - continue; - case BPF_S_JMP_JEQ_K: - fentry += (A == K) ? fentry->jt : fentry->jf; - continue; - case BPF_S_JMP_JSET_K: - fentry += (A & K) ? fentry->jt : fentry->jf; - continue; - case BPF_S_JMP_JGT_X: - fentry += (A > X) ? fentry->jt : fentry->jf; - continue; - case BPF_S_JMP_JGE_X: - fentry += (A >= X) ? fentry->jt : fentry->jf; - continue; - case BPF_S_JMP_JEQ_X: - fentry += (A == X) ? fentry->jt : fentry->jf; - continue; - case BPF_S_JMP_JSET_X: - fentry += (A & X) ? fentry->jt : fentry->jf; - continue; - case BPF_S_LD_W_ABS: - k = K; -load_w: - ptr = load_pointer(skb, k, 4, &tmp); - if (ptr != NULL) { - A = get_unaligned_be32(ptr); - continue; - } - return 0; - case BPF_S_LD_H_ABS: - k = K; -load_h: - ptr = load_pointer(skb, k, 2, &tmp); - if (ptr != NULL) { - A = get_unaligned_be16(ptr); - continue; + regs[FP_REG] = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; + regs[ARG1_REG] = (u64) (unsigned long) ctx; + +select_insn: + goto *jumptable[insn->code]; + + /* ALU */ +#define ALU(OPCODE, OP) \ + BPF_ALU64_##OPCODE##_BPF_X: \ + A = A OP X; \ + CONT; \ + BPF_ALU_##OPCODE##_BPF_X: \ + A = (u32) A OP (u32) X; \ + CONT; \ + BPF_ALU64_##OPCODE##_BPF_K: \ + A = A OP K; \ + CONT; \ + BPF_ALU_##OPCODE##_BPF_K: \ + A = (u32) A OP (u32) K; \ + CONT; + + ALU(BPF_ADD, +) + ALU(BPF_SUB, -) + ALU(BPF_AND, &) + ALU(BPF_OR, |) + ALU(BPF_LSH, <<) + ALU(BPF_RSH, >>) + ALU(BPF_XOR, ^) + ALU(BPF_MUL, *) +#undef ALU + BPF_ALU_BPF_NEG_0: + A = (u32) -A; + CONT; + BPF_ALU64_BPF_NEG_0: + A = -A; + CONT; + BPF_ALU_BPF_MOV_BPF_X: + A = (u32) X; + CONT; + BPF_ALU_BPF_MOV_BPF_K: + A = (u32) K; + CONT; + BPF_ALU64_BPF_MOV_BPF_X: + A = X; + CONT; + BPF_ALU64_BPF_MOV_BPF_K: + A = K; + CONT; + BPF_ALU64_BPF_ARSH_BPF_X: + (*(s64 *) &A) >>= X; + CONT; + BPF_ALU64_BPF_ARSH_BPF_K: + (*(s64 *) &A) >>= K; + CONT; + BPF_ALU64_BPF_MOD_BPF_X: + tmp = A; + if (X) + A = do_div(tmp, X); + CONT; + BPF_ALU_BPF_MOD_BPF_X: + tmp = (u32) A; + if (X) + A = do_div(tmp, (u32) X); + CONT; + BPF_ALU64_BPF_MOD_BPF_K: + tmp = A; + if (K) + A = do_div(tmp, K); + CONT; + BPF_ALU_BPF_MOD_BPF_K: + tmp = (u32) A; + if (K) + A = do_div(tmp, (u32) K); + CONT; + BPF_ALU64_BPF_DIV_BPF_X: + if (X) + do_div(A, X); + CONT; + BPF_ALU_BPF_DIV_BPF_X: + tmp = (u32) A; + if (X) + do_div(tmp, (u32) X); + A = (u32) tmp; + CONT; + BPF_ALU64_BPF_DIV_BPF_K: + if (K) + do_div(A, K); + CONT; + BPF_ALU_BPF_DIV_BPF_K: + tmp = (u32) A; + if (K) + do_div(tmp, (u32) K); + A = (u32) tmp; + CONT; + BPF_ALU_BPF_END_BPF_TO_BE: + switch (K) { + case 16: + A = (__force u16) cpu_to_be16(A); + break; + case 32: + A = (__force u32) cpu_to_be32(A); + break; + case 64: + A = (__force u64) cpu_to_be64(A); + break; + } + CONT; + BPF_ALU_BPF_END_BPF_TO_LE: + switch (K) { + case 16: + A = (__force u16) cpu_to_le16(A); + break; + case 32: + A = (__force u32) cpu_to_le32(A); + break; + case 64: + A = (__force u64) cpu_to_le64(A); + break; + } + CONT; + + /* CALL */ + BPF_JMP_BPF_CALL_0: + /* Function call scratches R1-R5 registers, preserves R6-R9, + * and stores return value into R0. + */ + R0 = (__bpf_call_base + insn->imm)(regs[1], regs[2], regs[3], + regs[4], regs[5]); + CONT; + + /* JMP */ + BPF_JMP_BPF_JA_0: + insn += insn->off; + CONT; + BPF_JMP_BPF_JEQ_BPF_X: + if (A == X) { + insn += insn->off; + CONT_JMP; + } + CONT; + BPF_JMP_BPF_JEQ_BPF_K: + if (A == K) { + insn += insn->off; + CONT_JMP; + } + CONT; + BPF_JMP_BPF_JNE_BPF_X: + if (A != X) { + insn += insn->off; + CONT_JMP; + } + CONT; + BPF_JMP_BPF_JNE_BPF_K: + if (A != K) { + insn += insn->off; + CONT_JMP; + } + CONT; + BPF_JMP_BPF_JGT_BPF_X: + if (A > X) { + insn += insn->off; + CONT_JMP; + } + CONT; + BPF_JMP_BPF_JGT_BPF_K: + if (A > K) { + insn += insn->off; + CONT_JMP; + } + CONT; + BPF_JMP_BPF_JGE_BPF_X: + if (A >= X) { + insn += insn->off; + CONT_JMP; + } + CONT; + BPF_JMP_BPF_JGE_BPF_K: + if (A >= K) { + insn += insn->off; + CONT_JMP; + } + CONT; + BPF_JMP_BPF_JSGT_BPF_X: + if (((s64)A) > ((s64)X)) { + insn += insn->off; + CONT_JMP; + } + CONT; + BPF_JMP_BPF_JSGT_BPF_K: + if (((s64)A) > ((s64)K)) { + insn += insn->off; + CONT_JMP; + } + CONT; + BPF_JMP_BPF_JSGE_BPF_X: + if (((s64)A) >= ((s64)X)) { + insn += insn->off; + CONT_JMP; + } + CONT; + BPF_JMP_BPF_JSGE_BPF_K: + if (((s64)A) >= ((s64)K)) { + insn += insn->off; + CONT_JMP; + } + CONT; + BPF_JMP_BPF_JSET_BPF_X: + if (A & X) { + insn += insn->off; + CONT_JMP; + } + CONT; + BPF_JMP_BPF_JSET_BPF_K: + if (A & K) { + insn += insn->off; + CONT_JMP; + } + CONT; + BPF_JMP_BPF_EXIT_0: + return R0; + + /* STX and ST and LDX*/ +#define LDST(SIZEOP, SIZE) \ + BPF_STX_BPF_MEM_##SIZEOP: \ + *(SIZE *)(unsigned long) (A + insn->off) = X; \ + CONT; \ + BPF_ST_BPF_MEM_##SIZEOP: \ + *(SIZE *)(unsigned long) (A + insn->off) = K; \ + CONT; \ + BPF_LDX_BPF_MEM_##SIZEOP: \ + A = *(SIZE *)(unsigned long) (X + insn->off); \ + CONT; + + LDST(BPF_B, u8) + LDST(BPF_H, u16) + LDST(BPF_W, u32) + LDST(BPF_DW, u64) +#undef LDST + BPF_STX_BPF_XADD_BPF_W: /* lock xadd *(u32 *)(A + insn->off) += X */ + atomic_add((u32) X, (atomic_t *)(unsigned long) + (A + insn->off)); + CONT; + BPF_STX_BPF_XADD_BPF_DW: /* lock xadd *(u64 *)(A + insn->off) += X */ + atomic64_add((u64) X, (atomic64_t *)(unsigned long) + (A + insn->off)); + CONT; + BPF_LD_BPF_ABS_BPF_W: /* R0 = ntohl(*(u32 *) (skb->data + K)) */ + off = K; +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[CTX_REG] == R6, sk_convert_filter() + * saves it in R6, internal BPF verifier will check that + * R6 == ctx. + * + * BPF_ABS and BPF_IND are wrappers of function calls, so + * they scratch R1-R5 registers, preserve R6-R9, and store + * return value into R0. + * + * Implicit input: + * ctx + * + * Explicit input: + * X == any register + * K == 32-bit immediate + * + * Output: + * R0 - 8/16/32-bit skb data converted to cpu endianness + */ + ptr = load_pointer((struct sk_buff *) ctx, off, 4, &tmp); + if (likely(ptr != NULL)) { + R0 = get_unaligned_be32(ptr); + CONT; + } + return 0; + BPF_LD_BPF_ABS_BPF_H: /* R0 = ntohs(*(u16 *) (skb->data + K)) */ + off = K; +load_half: + ptr = load_pointer((struct sk_buff *) ctx, off, 2, &tmp); + if (likely(ptr != NULL)) { + R0 = get_unaligned_be16(ptr); + CONT; + } + return 0; + BPF_LD_BPF_ABS_BPF_B: /* R0 = *(u8 *) (ctx + K) */ + off = K; +load_byte: + ptr = load_pointer((struct sk_buff *) ctx, off, 1, &tmp); + if (likely(ptr != NULL)) { + R0 = *(u8 *)ptr; + CONT; + } + return 0; + BPF_LD_BPF_IND_BPF_W: /* R0 = ntohl(*(u32 *) (skb->data + X + K)) */ + off = K + X; + goto load_word; + BPF_LD_BPF_IND_BPF_H: /* R0 = ntohs(*(u16 *) (skb->data + X + K)) */ + off = K + X; + goto load_half; + BPF_LD_BPF_IND_BPF_B: /* R0 = *(u8 *) (skb->data + X + K) */ + off = K + X; + 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; +#undef CONT_JMP +#undef CONT + +#undef R0 +#undef X +#undef A +#undef K +} + +u32 sk_run_filter_int_seccomp(const struct seccomp_data *ctx, + const struct sock_filter_int *insni) + __attribute__ ((alias ("__sk_run_filter"))); + +u32 sk_run_filter_int_skb(const struct sk_buff *ctx, + const struct sock_filter_int *insni) + __attribute__ ((alias ("__sk_run_filter"))); +EXPORT_SYMBOL_GPL(sk_run_filter_int_skb); + +/* 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. + */ +#define PKT_TYPE_MAX 7 +static unsigned int pkt_type_offset(void) +{ + struct sk_buff skb_probe = { .pkt_type = ~0, }; + u8 *ct = (u8 *) &skb_probe; + unsigned int off; + + for (off = 0; off < sizeof(struct sk_buff); off++) { + if (ct[off] == PKT_TYPE_MAX) + return off; + } + + pr_err_once("Please fix %s, as pkt_type couldn't be found!\n", __func__); + return -1; +} + +static u64 __skb_get_pay_offset(u64 ctx, u64 A, u64 X, u64 r4, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *)(long) ctx; + + return __skb_get_poff(skb); +} + +static u64 __skb_get_nlattr(u64 ctx, u64 A, u64 X, u64 r4, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *)(long) ctx; + struct nlattr *nla; + + if (skb_is_nonlinear(skb)) + return 0; + + if (A > skb->len - sizeof(struct nlattr)) + return 0; + + nla = nla_find((struct nlattr *) &skb->data[A], skb->len - A, X); + if (nla) + return (void *) nla - (void *) skb->data; + + return 0; +} + +static u64 __skb_get_nlattr_nest(u64 ctx, u64 A, u64 X, u64 r4, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *)(long) ctx; + struct nlattr *nla; + + if (skb_is_nonlinear(skb)) + return 0; + + if (A > skb->len - sizeof(struct nlattr)) + return 0; + + nla = (struct nlattr *) &skb->data[A]; + if (nla->nla_len > A - skb->len) + return 0; + + nla = nla_find_nested(nla, X); + if (nla) + return (void *) nla - (void *) skb->data; + + return 0; +} + +static u64 __get_raw_cpu_id(u64 ctx, u64 A, u64 X, u64 r4, u64 r5) +{ + return raw_smp_processor_id(); +} + +/* Register mappings for user programs. */ +#define A_REG 0 +#define X_REG 7 +#define TMP_REG 8 +#define ARG2_REG 2 +#define ARG3_REG 3 + +static bool convert_bpf_extensions(struct sock_filter *fp, + struct sock_filter_int **insnp) +{ + struct sock_filter_int *insn = *insnp; + + switch (fp->k) { + case SKF_AD_OFF + SKF_AD_PROTOCOL: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2); + + insn->code = BPF_LDX | BPF_MEM | BPF_H; + insn->a_reg = A_REG; + insn->x_reg = CTX_REG; + insn->off = offsetof(struct sk_buff, protocol); + insn++; + + /* A = ntohs(A) [emitting a nop or swap16] */ + insn->code = BPF_ALU | BPF_END | BPF_FROM_BE; + insn->a_reg = A_REG; + insn->imm = 16; + break; + + case SKF_AD_OFF + SKF_AD_PKTTYPE: + insn->code = BPF_LDX | BPF_MEM | BPF_B; + insn->a_reg = A_REG; + insn->x_reg = CTX_REG; + insn->off = pkt_type_offset(); + if (insn->off < 0) + return false; + insn++; + + insn->code = BPF_ALU | BPF_AND | BPF_K; + insn->a_reg = A_REG; + insn->imm = PKT_TYPE_MAX; + break; + + case SKF_AD_OFF + SKF_AD_IFINDEX: + case SKF_AD_OFF + SKF_AD_HATYPE: + if (FIELD_SIZEOF(struct sk_buff, dev) == 8) + insn->code = BPF_LDX | BPF_MEM | BPF_DW; + else + insn->code = BPF_LDX | BPF_MEM | BPF_W; + insn->a_reg = TMP_REG; + insn->x_reg = CTX_REG; + insn->off = offsetof(struct sk_buff, dev); + insn++; + + insn->code = BPF_JMP | BPF_JNE | BPF_K; + insn->a_reg = TMP_REG; + insn->imm = 0; + insn->off = 1; + insn++; + + insn->code = BPF_JMP | BPF_EXIT; + insn++; + + BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); + BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, type) != 2); + + insn->a_reg = A_REG; + insn->x_reg = TMP_REG; + + if (fp->k == SKF_AD_OFF + SKF_AD_IFINDEX) { + insn->code = BPF_LDX | BPF_MEM | BPF_W; + insn->off = offsetof(struct net_device, ifindex); + } else { + insn->code = BPF_LDX | BPF_MEM | BPF_H; + insn->off = offsetof(struct net_device, type); + } + break; + + case SKF_AD_OFF + SKF_AD_MARK: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); + + insn->code = BPF_LDX | BPF_MEM | BPF_W; + insn->a_reg = A_REG; + insn->x_reg = CTX_REG; + insn->off = offsetof(struct sk_buff, mark); + break; + + case SKF_AD_OFF + SKF_AD_RXHASH: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4); + + insn->code = BPF_LDX | BPF_MEM | BPF_W; + insn->a_reg = A_REG; + insn->x_reg = CTX_REG; + insn->off = offsetof(struct sk_buff, hash); + break; + + case SKF_AD_OFF + SKF_AD_QUEUE: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2); + + insn->code = BPF_LDX | BPF_MEM | BPF_H; + insn->a_reg = A_REG; + insn->x_reg = CTX_REG; + insn->off = offsetof(struct sk_buff, queue_mapping); + break; + + case SKF_AD_OFF + SKF_AD_VLAN_TAG: + case SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2); + + insn->code = BPF_LDX | BPF_MEM | BPF_H; + insn->a_reg = A_REG; + insn->x_reg = CTX_REG; + insn->off = offsetof(struct sk_buff, vlan_tci); + insn++; + + BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000); + + if (fp->k == SKF_AD_OFF + SKF_AD_VLAN_TAG) { + insn->code = BPF_ALU | BPF_AND | BPF_K; + insn->a_reg = A_REG; + insn->imm = ~VLAN_TAG_PRESENT; + } else { + insn->code = BPF_ALU | BPF_RSH | BPF_K; + insn->a_reg = A_REG; + insn->imm = 12; + insn++; + + insn->code = BPF_ALU | BPF_AND | BPF_K; + insn->a_reg = A_REG; + insn->imm = 1; + } + break; + + case SKF_AD_OFF + SKF_AD_PAY_OFFSET: + case SKF_AD_OFF + SKF_AD_NLATTR: + case SKF_AD_OFF + SKF_AD_NLATTR_NEST: + case SKF_AD_OFF + SKF_AD_CPU: + /* arg1 = ctx */ + insn->code = BPF_ALU64 | BPF_MOV | BPF_X; + insn->a_reg = ARG1_REG; + insn->x_reg = CTX_REG; + insn++; + + /* arg2 = A */ + insn->code = BPF_ALU64 | BPF_MOV | BPF_X; + insn->a_reg = ARG2_REG; + insn->x_reg = A_REG; + insn++; + + /* arg3 = X */ + insn->code = BPF_ALU64 | BPF_MOV | BPF_X; + insn->a_reg = ARG3_REG; + insn->x_reg = X_REG; + insn++; + + /* Emit call(ctx, arg2=A, arg3=X) */ + insn->code = BPF_JMP | BPF_CALL; + switch (fp->k) { + case SKF_AD_OFF + SKF_AD_PAY_OFFSET: + insn->imm = __skb_get_pay_offset - __bpf_call_base; + break; + case SKF_AD_OFF + SKF_AD_NLATTR: + insn->imm = __skb_get_nlattr - __bpf_call_base; + break; + case SKF_AD_OFF + SKF_AD_NLATTR_NEST: + insn->imm = __skb_get_nlattr_nest - __bpf_call_base; + break; + case SKF_AD_OFF + SKF_AD_CPU: + insn->imm = __get_raw_cpu_id - __bpf_call_base; + break; + } + break; + + case SKF_AD_OFF + SKF_AD_ALU_XOR_X: + insn->code = BPF_ALU | BPF_XOR | BPF_X; + insn->a_reg = A_REG; + insn->x_reg = X_REG; + break; + + default: + /* This is just a dummy call to avoid letting the compiler + * evict __bpf_call_base() as an optimization. Placed here + * where no-one bothers. + */ + BUG_ON(__bpf_call_base(0, 0, 0, 0, 0) != 0); + return false; + } + + *insnp = insn; + return true; +} + +/** + * sk_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 + * @new_len: pointer to store length of converted program + * + * Remap 'sock_filter' style BPF instruction set to 'sock_filter_ext' style. + * Conversion workflow: + * + * 1) First pass for calculating the new program length: + * sk_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); + * + * 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 + * register 10; Context 'void *ctx' is stored in register 1, that is, + * 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 new_flen = 0, pass = 0, target, i; + struct sock_filter_int *new_insn; + struct sock_filter *fp; + int *addrs = NULL; + u8 bpf_src; + + BUILD_BUG_ON(BPF_MEMWORDS * sizeof(u32) > MAX_BPF_STACK); + BUILD_BUG_ON(FP_REG + 1 != MAX_BPF_REG); + + if (len <= 0 || len >= BPF_MAXINSNS) + return -EINVAL; + + if (new_prog) { + addrs = kzalloc(len * sizeof(*addrs), GFP_KERNEL); + if (!addrs) + return -ENOMEM; + } + +do_pass: + new_insn = new_prog; + fp = prog; + + if (new_insn) { + new_insn->code = BPF_ALU64 | BPF_MOV | BPF_X; + new_insn->a_reg = CTX_REG; + new_insn->x_reg = ARG1_REG; + } + new_insn++; + + for (i = 0; i < len; fp++, i++) { + struct sock_filter_int tmp_insns[6] = { }; + struct sock_filter_int *insn = tmp_insns; + + if (addrs) + addrs[i] = new_insn - new_prog; + + switch (fp->code) { + /* All arithmetic insns and skb loads map as-is. */ + case BPF_ALU | BPF_ADD | BPF_X: + case BPF_ALU | BPF_ADD | BPF_K: + case BPF_ALU | BPF_SUB | BPF_X: + case BPF_ALU | BPF_SUB | BPF_K: + case BPF_ALU | BPF_AND | BPF_X: + case BPF_ALU | BPF_AND | BPF_K: + case BPF_ALU | BPF_OR | BPF_X: + case BPF_ALU | BPF_OR | BPF_K: + case BPF_ALU | BPF_LSH | BPF_X: + case BPF_ALU | BPF_LSH | BPF_K: + case BPF_ALU | BPF_RSH | BPF_X: + case BPF_ALU | BPF_RSH | BPF_K: + case BPF_ALU | BPF_XOR | BPF_X: + case BPF_ALU | BPF_XOR | BPF_K: + case BPF_ALU | BPF_MUL | BPF_X: + case BPF_ALU | BPF_MUL | BPF_K: + case BPF_ALU | BPF_DIV | BPF_X: + case BPF_ALU | BPF_DIV | BPF_K: + case BPF_ALU | BPF_MOD | BPF_X: + case BPF_ALU | BPF_MOD | BPF_K: + case BPF_ALU | BPF_NEG: + case BPF_LD | BPF_ABS | BPF_W: + case BPF_LD | BPF_ABS | BPF_H: + case BPF_LD | BPF_ABS | BPF_B: + case BPF_LD | BPF_IND | BPF_W: + case BPF_LD | BPF_IND | BPF_H: + case BPF_LD | BPF_IND | BPF_B: + /* Check for overloaded BPF extension and + * directly convert it if found, otherwise + * just move on with mapping. + */ + if (BPF_CLASS(fp->code) == BPF_LD && + BPF_MODE(fp->code) == BPF_ABS && + convert_bpf_extensions(fp, &insn)) + break; + + insn->code = fp->code; + insn->a_reg = A_REG; + insn->x_reg = X_REG; + insn->imm = fp->k; + break; + + /* Jump opcodes map as-is, but offsets need adjustment. */ + case BPF_JMP | BPF_JA: + target = i + fp->k + 1; + insn->code = fp->code; +#define EMIT_JMP \ + do { \ + if (target >= len || target < 0) \ + goto err; \ + insn->off = addrs ? addrs[target] - addrs[i] - 1 : 0; \ + /* Adjust pc relative offset for 2nd or 3rd insn. */ \ + insn->off -= insn - tmp_insns; \ + } while (0) + + EMIT_JMP; + break; + + case BPF_JMP | BPF_JEQ | BPF_K: + case BPF_JMP | BPF_JEQ | BPF_X: + case BPF_JMP | BPF_JSET | BPF_K: + case BPF_JMP | BPF_JSET | BPF_X: + case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP | BPF_JGE | BPF_X: + if (BPF_SRC(fp->code) == BPF_K && (int) fp->k < 0) { + /* BPF immediates are signed, zero extend + * immediate into tmp register and use it + * in compare insn. + */ + insn->code = BPF_ALU | BPF_MOV | BPF_K; + insn->a_reg = TMP_REG; + insn->imm = fp->k; + insn++; + + insn->a_reg = A_REG; + insn->x_reg = TMP_REG; + bpf_src = BPF_X; + } else { + insn->a_reg = A_REG; + insn->x_reg = X_REG; + insn->imm = fp->k; + bpf_src = BPF_SRC(fp->code); } - return 0; - case BPF_S_LD_B_ABS: - k = K; -load_b: - ptr = load_pointer(skb, k, 1, &tmp); - if (ptr != NULL) { - A = *(u8 *)ptr; - continue; + + /* Common case where 'jump_false' is next insn. */ + if (fp->jf == 0) { + insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src; + target = i + fp->jt + 1; + EMIT_JMP; + break; } - return 0; - case BPF_S_LD_W_LEN: - A = skb->len; - continue; - case BPF_S_LDX_W_LEN: - X = skb->len; - continue; - case BPF_S_LD_W_IND: - k = X + K; - goto load_w; - case BPF_S_LD_H_IND: - k = X + K; - goto load_h; - case BPF_S_LD_B_IND: - k = X + K; - goto load_b; - case BPF_S_LDX_B_MSH: - ptr = load_pointer(skb, K, 1, &tmp); - if (ptr != NULL) { - X = (*(u8 *)ptr & 0xf) << 2; - continue; + + /* Convert JEQ into JNE when 'jump_true' is next insn. */ + if (fp->jt == 0 && BPF_OP(fp->code) == BPF_JEQ) { + insn->code = BPF_JMP | BPF_JNE | bpf_src; + target = i + fp->jf + 1; + EMIT_JMP; + break; } - return 0; - case BPF_S_LD_IMM: - A = K; - continue; - case BPF_S_LDX_IMM: - X = K; - continue; - case BPF_S_LD_MEM: - A = mem[K]; - continue; - case BPF_S_LDX_MEM: - X = mem[K]; - continue; - case BPF_S_MISC_TAX: - X = A; - continue; - case BPF_S_MISC_TXA: - A = X; - continue; - case BPF_S_RET_K: - return K; - case BPF_S_RET_A: - return A; - case BPF_S_ST: - mem[K] = A; - continue; - case BPF_S_STX: - mem[K] = X; - continue; - case BPF_S_ANC_PROTOCOL: - A = ntohs(skb->protocol); - continue; - case BPF_S_ANC_PKTTYPE: - A = skb->pkt_type; - continue; - case BPF_S_ANC_IFINDEX: - if (!skb->dev) - return 0; - A = skb->dev->ifindex; - continue; - case BPF_S_ANC_MARK: - A = skb->mark; - continue; - case BPF_S_ANC_QUEUE: - A = skb->queue_mapping; - continue; - case BPF_S_ANC_HATYPE: - if (!skb->dev) - return 0; - A = skb->dev->type; - continue; - case BPF_S_ANC_RXHASH: - A = skb->hash; - continue; - case BPF_S_ANC_CPU: - A = raw_smp_processor_id(); - continue; - case BPF_S_ANC_VLAN_TAG: - A = vlan_tx_tag_get(skb); - continue; - case BPF_S_ANC_VLAN_TAG_PRESENT: - A = !!vlan_tx_tag_present(skb); - continue; - case BPF_S_ANC_PAY_OFFSET: - A = __skb_get_poff(skb); - continue; - case BPF_S_ANC_NLATTR: { - struct nlattr *nla; - - if (skb_is_nonlinear(skb)) - return 0; - if (A > skb->len - sizeof(struct nlattr)) - return 0; - - nla = nla_find((struct nlattr *)&skb->data[A], - skb->len - A, X); - if (nla) - A = (void *)nla - (void *)skb->data; - else - A = 0; - continue; - } - case BPF_S_ANC_NLATTR_NEST: { - struct nlattr *nla; - - if (skb_is_nonlinear(skb)) - return 0; - if (A > skb->len - sizeof(struct nlattr)) - return 0; - - nla = (struct nlattr *)&skb->data[A]; - if (nla->nla_len > A - skb->len) - return 0; - - nla = nla_find_nested(nla, X); - if (nla) - A = (void *)nla - (void *)skb->data; - else - A = 0; - continue; - } -#ifdef CONFIG_SECCOMP_FILTER - case BPF_S_ANC_SECCOMP_LD_W: - A = seccomp_bpf_load(fentry->k); - continue; -#endif + + /* Other jumps are mapped into two insns: Jxx and JA. */ + target = i + fp->jt + 1; + insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src; + EMIT_JMP; + insn++; + + insn->code = BPF_JMP | BPF_JA; + target = i + fp->jf + 1; + EMIT_JMP; + break; + + /* ldxb 4 * ([14] & 0xf) is remaped into 6 insns. */ + case BPF_LDX | BPF_MSH | BPF_B: + insn->code = BPF_ALU64 | BPF_MOV | BPF_X; + insn->a_reg = TMP_REG; + insn->x_reg = A_REG; + insn++; + + insn->code = BPF_LD | BPF_ABS | BPF_B; + insn->a_reg = A_REG; + insn->imm = fp->k; + insn++; + + insn->code = BPF_ALU | BPF_AND | BPF_K; + insn->a_reg = A_REG; + insn->imm = 0xf; + insn++; + + insn->code = BPF_ALU | BPF_LSH | BPF_K; + insn->a_reg = A_REG; + insn->imm = 2; + insn++; + + insn->code = BPF_ALU64 | BPF_MOV | BPF_X; + insn->a_reg = X_REG; + insn->x_reg = A_REG; + insn++; + + insn->code = BPF_ALU64 | BPF_MOV | BPF_X; + insn->a_reg = A_REG; + insn->x_reg = TMP_REG; + break; + + /* RET_K, RET_A are remaped into 2 insns. */ + case BPF_RET | BPF_A: + case BPF_RET | BPF_K: + insn->code = BPF_ALU | BPF_MOV | + (BPF_RVAL(fp->code) == BPF_K ? + BPF_K : BPF_X); + insn->a_reg = 0; + insn->x_reg = A_REG; + insn->imm = fp->k; + insn++; + + insn->code = BPF_JMP | BPF_EXIT; + break; + + /* Store to stack. */ + case BPF_ST: + case BPF_STX: + insn->code = BPF_STX | BPF_MEM | BPF_W; + insn->a_reg = FP_REG; + insn->x_reg = fp->code == BPF_ST ? A_REG : X_REG; + insn->off = -(BPF_MEMWORDS - fp->k) * 4; + break; + + /* Load from stack. */ + case BPF_LD | BPF_MEM: + case BPF_LDX | BPF_MEM: + insn->code = BPF_LDX | BPF_MEM | BPF_W; + insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ? + A_REG : X_REG; + insn->x_reg = FP_REG; + insn->off = -(BPF_MEMWORDS - fp->k) * 4; + break; + + /* A = K or X = K */ + case BPF_LD | BPF_IMM: + case BPF_LDX | BPF_IMM: + insn->code = BPF_ALU | BPF_MOV | BPF_K; + insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ? + A_REG : X_REG; + insn->imm = fp->k; + break; + + /* X = A */ + case BPF_MISC | BPF_TAX: + insn->code = BPF_ALU64 | BPF_MOV | BPF_X; + insn->a_reg = X_REG; + insn->x_reg = A_REG; + break; + + /* A = X */ + case BPF_MISC | BPF_TXA: + insn->code = BPF_ALU64 | BPF_MOV | BPF_X; + insn->a_reg = A_REG; + insn->x_reg = X_REG; + break; + + /* A = skb->len or X = skb->len */ + case BPF_LD | BPF_W | BPF_LEN: + case BPF_LDX | BPF_W | BPF_LEN: + insn->code = BPF_LDX | BPF_MEM | BPF_W; + insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ? + A_REG : X_REG; + insn->x_reg = CTX_REG; + insn->off = offsetof(struct sk_buff, len); + break; + + /* access seccomp_data fields */ + case BPF_LDX | BPF_ABS | BPF_W: + insn->code = BPF_LDX | BPF_MEM | BPF_W; + insn->a_reg = A_REG; + insn->x_reg = CTX_REG; + insn->off = fp->k; + break; + default: - WARN_RATELIMIT(1, "Unknown code:%u jt:%u tf:%u k:%u\n", - fentry->code, fentry->jt, - fentry->jf, fentry->k); - return 0; + goto err; } + + insn++; + if (new_prog) + memcpy(new_insn, tmp_insns, + sizeof(*insn) * (insn - tmp_insns)); + + new_insn += insn - tmp_insns; } + if (!new_prog) { + /* Only calculating new length. */ + *new_len = new_insn - new_prog; + return 0; + } + + pass++; + if (new_flen != new_insn - new_prog) { + new_flen = new_insn - new_prog; + if (pass > 2) + goto err; + + goto do_pass; + } + + kfree(addrs); + BUG_ON(*new_len != new_flen); return 0; +err: + kfree(addrs); + return -EINVAL; } -EXPORT_SYMBOL(sk_run_filter); -/* - * Security : +/* Security: + * * A BPF program is able to use 16 cells of memory to store intermediate - * values (check u32 mem[BPF_MEMWORDS] in sk_run_filter()) + * values (check u32 mem[BPF_MEMWORDS] in sk_run_filter()). + * * As we dont want to clear mem[] array for each packet going through * sk_run_filter(), we check that filter loaded by user never try to read * a cell if not previously written, and we check all branches to be sure @@ -696,19 +1442,130 @@ void sk_filter_charge(struct sock *sk, struct sk_filter *fp) atomic_add(sk_filter_size(fp->len), &sk->sk_omem_alloc); } -static int __sk_prepare_filter(struct sk_filter *fp) +static struct sk_filter *__sk_migrate_realloc(struct sk_filter *fp, + struct sock *sk, + unsigned int len) +{ + 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) { + memcpy(fp_new, fp, sizeof(struct sk_filter)); + /* As we're kepping 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); + } + + return fp_new; +} + +static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp, + struct sock *sk) +{ + struct sock_filter *old_prog; + struct sk_filter *old_fp; + int i, err, new_len, old_len = fp->len; + + /* We are free to overwrite insns et al right here as it + * won't be used at this point in time anymore internally + * after the migration to the internal BPF instruction + * representation. + */ + BUILD_BUG_ON(sizeof(struct sock_filter) != + sizeof(struct sock_filter_int)); + + /* For now, we need to unfiddle BPF_S_* identifiers in place. + * This can sooner or later on be subject to removal, e.g. when + * JITs have been converted. + */ + for (i = 0; i < fp->len; i++) + sk_decode_filter(&fp->insns[i], &fp->insns[i]); + + /* Conversion cannot happen on overlapping memory areas, + * so we need to keep the user BPF around until the 2nd + * pass. At this time, the user BPF is stored in fp->insns. + */ + old_prog = kmemdup(fp->insns, old_len * sizeof(struct sock_filter), + GFP_KERNEL); + if (!old_prog) { + err = -ENOMEM; + goto out_err; + } + + /* 1st pass: calculate the new program length. */ + err = sk_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)); + if (!fp) { + /* The old_fp is still around in case we couldn't + * allocate new memory, so uncharge on that one. + */ + fp = old_fp; + err = -ENOMEM; + goto out_err_free; + } + + fp->bpf_func = sk_run_filter_int_skb; + 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); + if (err) + /* 2nd sk_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(). + */ + goto out_err_free; + + kfree(old_prog); + return fp; + +out_err_free: + kfree(old_prog); +out_err: + /* Rollback filter setup. */ + if (sk != NULL) + sk_filter_uncharge(sk, fp); + else + kfree(fp); + return ERR_PTR(err); +} + +static struct sk_filter *__sk_prepare_filter(struct sk_filter *fp, + struct sock *sk) { int err; - fp->bpf_func = sk_run_filter; + fp->bpf_func = NULL; fp->jited = 0; err = sk_chk_filter(fp->insns, fp->len); if (err) - return err; + return ERR_PTR(err); + /* Probe if we can JIT compile the filter and if so, do + * the compilation of the filter. + */ bpf_jit_compile(fp); - return 0; + + /* JIT compiler couldn't process this filter, so do the + * internal BPF translation for the optimized interpreter. + */ + if (!fp->jited) + fp = __sk_migrate_filter(fp, sk); + + return fp; } /** @@ -726,7 +1583,6 @@ int sk_unattached_filter_create(struct sk_filter **pfp, { unsigned int fsize = sk_filter_proglen(fprog); struct sk_filter *fp; - int err; /* Make sure new filter is there and in the right amounts. */ if (fprog->filter == NULL) @@ -746,15 +1602,15 @@ int sk_unattached_filter_create(struct sk_filter **pfp, */ fp->orig_prog = NULL; - err = __sk_prepare_filter(fp); - if (err) - goto free_mem; + /* __sk_prepare_filter() already takes care of uncharging + * memory in case something goes wrong. + */ + fp = __sk_prepare_filter(fp, NULL); + if (IS_ERR(fp)) + return PTR_ERR(fp); *pfp = fp; return 0; -free_mem: - kfree(fp); - return err; } EXPORT_SYMBOL_GPL(sk_unattached_filter_create); @@ -806,11 +1662,12 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) return -ENOMEM; } - err = __sk_prepare_filter(fp); - if (err) { - sk_filter_uncharge(sk, fp); - return err; - } + /* __sk_prepare_filter() already takes care of uncharging + * memory in case something goes wrong. + */ + fp = __sk_prepare_filter(fp, sk); + if (IS_ERR(fp)) + return PTR_ERR(fp); old_fp = rcu_dereference_protected(sk->sk_filter, sock_owned_by_user(sk));