From bd4cf0ed331a275e9bf5a49e6d0fd55dffc551b8 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Fri, 28 Mar 2014 18:58:25 +0100 Subject: 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 --- kernel/seccomp.c | 119 +++++++++++++++++++++++++++---------------------------- 1 file changed, 58 insertions(+), 61 deletions(-) (limited to 'kernel') 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; } -- cgit v1.2.3-70-g09d2