WSL2-Linux-Kernel/include/linux/filter.h

160 строки
3.6 KiB
C
Исходник Обычный вид История

/*
* Linux Socket Filter Data Structures
*/
#ifndef __LINUX_FILTER_H__
#define __LINUX_FILTER_H__
#include <linux/atomic.h>
#include <linux/compat.h>
net: fix unsafe set_memory_rw from softirq on x86 system with net.core.bpf_jit_enable = 1 sudo tcpdump -i eth1 'tcp port 22' causes the warning: [ 56.766097] Possible unsafe locking scenario: [ 56.766097] [ 56.780146] CPU0 [ 56.786807] ---- [ 56.793188] lock(&(&vb->lock)->rlock); [ 56.799593] <Interrupt> [ 56.805889] lock(&(&vb->lock)->rlock); [ 56.812266] [ 56.812266] *** DEADLOCK *** [ 56.812266] [ 56.830670] 1 lock held by ksoftirqd/1/13: [ 56.836838] #0: (rcu_read_lock){.+.+..}, at: [<ffffffff8118f44c>] vm_unmap_aliases+0x8c/0x380 [ 56.849757] [ 56.849757] stack backtrace: [ 56.862194] CPU: 1 PID: 13 Comm: ksoftirqd/1 Not tainted 3.12.0-rc3+ #45 [ 56.868721] Hardware name: System manufacturer System Product Name/P8Z77 WS, BIOS 3007 07/26/2012 [ 56.882004] ffffffff821944c0 ffff88080bbdb8c8 ffffffff8175a145 0000000000000007 [ 56.895630] ffff88080bbd5f40 ffff88080bbdb928 ffffffff81755b14 0000000000000001 [ 56.909313] ffff880800000001 ffff880800000000 ffffffff8101178f 0000000000000001 [ 56.923006] Call Trace: [ 56.929532] [<ffffffff8175a145>] dump_stack+0x55/0x76 [ 56.936067] [<ffffffff81755b14>] print_usage_bug+0x1f7/0x208 [ 56.942445] [<ffffffff8101178f>] ? save_stack_trace+0x2f/0x50 [ 56.948932] [<ffffffff810cc0a0>] ? check_usage_backwards+0x150/0x150 [ 56.955470] [<ffffffff810ccb52>] mark_lock+0x282/0x2c0 [ 56.961945] [<ffffffff810ccfed>] __lock_acquire+0x45d/0x1d50 [ 56.968474] [<ffffffff810cce6e>] ? __lock_acquire+0x2de/0x1d50 [ 56.975140] [<ffffffff81393bf5>] ? cpumask_next_and+0x55/0x90 [ 56.981942] [<ffffffff810cef72>] lock_acquire+0x92/0x1d0 [ 56.988745] [<ffffffff8118f52a>] ? vm_unmap_aliases+0x16a/0x380 [ 56.995619] [<ffffffff817628f1>] _raw_spin_lock+0x41/0x50 [ 57.002493] [<ffffffff8118f52a>] ? vm_unmap_aliases+0x16a/0x380 [ 57.009447] [<ffffffff8118f52a>] vm_unmap_aliases+0x16a/0x380 [ 57.016477] [<ffffffff8118f44c>] ? vm_unmap_aliases+0x8c/0x380 [ 57.023607] [<ffffffff810436b0>] change_page_attr_set_clr+0xc0/0x460 [ 57.030818] [<ffffffff810cfb8d>] ? trace_hardirqs_on+0xd/0x10 [ 57.037896] [<ffffffff811a8330>] ? kmem_cache_free+0xb0/0x2b0 [ 57.044789] [<ffffffff811b59c3>] ? free_object_rcu+0x93/0xa0 [ 57.051720] [<ffffffff81043d9f>] set_memory_rw+0x2f/0x40 [ 57.058727] [<ffffffff8104e17c>] bpf_jit_free+0x2c/0x40 [ 57.065577] [<ffffffff81642cba>] sk_filter_release_rcu+0x1a/0x30 [ 57.072338] [<ffffffff811108e2>] rcu_process_callbacks+0x202/0x7c0 [ 57.078962] [<ffffffff81057f17>] __do_softirq+0xf7/0x3f0 [ 57.085373] [<ffffffff81058245>] run_ksoftirqd+0x35/0x70 cannot reuse jited filter memory, since it's readonly, so use original bpf insns memory to hold work_struct defer kfree of sk_filter until jit completed freeing tested on x86_64 and i386 Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-04 11:14:06 +04:00
#include <linux/workqueue.h>
#include <uapi/linux/filter.h>
#ifdef CONFIG_COMPAT
/*
* A struct sock_filter is architecture independent.
*/
struct compat_sock_fprog {
u16 len;
compat_uptr_t filter; /* struct sock_filter * */
};
#endif
struct sk_buff;
struct sock;
struct sk_filter
{
atomic_t refcnt;
unsigned int len; /* Number of filter blocks */
net: fix unsafe set_memory_rw from softirq on x86 system with net.core.bpf_jit_enable = 1 sudo tcpdump -i eth1 'tcp port 22' causes the warning: [ 56.766097] Possible unsafe locking scenario: [ 56.766097] [ 56.780146] CPU0 [ 56.786807] ---- [ 56.793188] lock(&(&vb->lock)->rlock); [ 56.799593] <Interrupt> [ 56.805889] lock(&(&vb->lock)->rlock); [ 56.812266] [ 56.812266] *** DEADLOCK *** [ 56.812266] [ 56.830670] 1 lock held by ksoftirqd/1/13: [ 56.836838] #0: (rcu_read_lock){.+.+..}, at: [<ffffffff8118f44c>] vm_unmap_aliases+0x8c/0x380 [ 56.849757] [ 56.849757] stack backtrace: [ 56.862194] CPU: 1 PID: 13 Comm: ksoftirqd/1 Not tainted 3.12.0-rc3+ #45 [ 56.868721] Hardware name: System manufacturer System Product Name/P8Z77 WS, BIOS 3007 07/26/2012 [ 56.882004] ffffffff821944c0 ffff88080bbdb8c8 ffffffff8175a145 0000000000000007 [ 56.895630] ffff88080bbd5f40 ffff88080bbdb928 ffffffff81755b14 0000000000000001 [ 56.909313] ffff880800000001 ffff880800000000 ffffffff8101178f 0000000000000001 [ 56.923006] Call Trace: [ 56.929532] [<ffffffff8175a145>] dump_stack+0x55/0x76 [ 56.936067] [<ffffffff81755b14>] print_usage_bug+0x1f7/0x208 [ 56.942445] [<ffffffff8101178f>] ? save_stack_trace+0x2f/0x50 [ 56.948932] [<ffffffff810cc0a0>] ? check_usage_backwards+0x150/0x150 [ 56.955470] [<ffffffff810ccb52>] mark_lock+0x282/0x2c0 [ 56.961945] [<ffffffff810ccfed>] __lock_acquire+0x45d/0x1d50 [ 56.968474] [<ffffffff810cce6e>] ? __lock_acquire+0x2de/0x1d50 [ 56.975140] [<ffffffff81393bf5>] ? cpumask_next_and+0x55/0x90 [ 56.981942] [<ffffffff810cef72>] lock_acquire+0x92/0x1d0 [ 56.988745] [<ffffffff8118f52a>] ? vm_unmap_aliases+0x16a/0x380 [ 56.995619] [<ffffffff817628f1>] _raw_spin_lock+0x41/0x50 [ 57.002493] [<ffffffff8118f52a>] ? vm_unmap_aliases+0x16a/0x380 [ 57.009447] [<ffffffff8118f52a>] vm_unmap_aliases+0x16a/0x380 [ 57.016477] [<ffffffff8118f44c>] ? vm_unmap_aliases+0x8c/0x380 [ 57.023607] [<ffffffff810436b0>] change_page_attr_set_clr+0xc0/0x460 [ 57.030818] [<ffffffff810cfb8d>] ? trace_hardirqs_on+0xd/0x10 [ 57.037896] [<ffffffff811a8330>] ? kmem_cache_free+0xb0/0x2b0 [ 57.044789] [<ffffffff811b59c3>] ? free_object_rcu+0x93/0xa0 [ 57.051720] [<ffffffff81043d9f>] set_memory_rw+0x2f/0x40 [ 57.058727] [<ffffffff8104e17c>] bpf_jit_free+0x2c/0x40 [ 57.065577] [<ffffffff81642cba>] sk_filter_release_rcu+0x1a/0x30 [ 57.072338] [<ffffffff811108e2>] rcu_process_callbacks+0x202/0x7c0 [ 57.078962] [<ffffffff81057f17>] __do_softirq+0xf7/0x3f0 [ 57.085373] [<ffffffff81058245>] run_ksoftirqd+0x35/0x70 cannot reuse jited filter memory, since it's readonly, so use original bpf insns memory to hold work_struct defer kfree of sk_filter until jit completed freeing tested on x86_64 and i386 Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-04 11:14:06 +04:00
struct rcu_head rcu;
net: filter: Just In Time compiler for x86-64 In order to speedup packet filtering, here is an implementation of a JIT compiler for x86_64 It is disabled by default, and must be enabled by the admin. echo 1 >/proc/sys/net/core/bpf_jit_enable It uses module_alloc() and module_free() to get memory in the 2GB text kernel range since we call helpers functions from the generated code. EAX : BPF A accumulator EBX : BPF X accumulator RDI : pointer to skb (first argument given to JIT function) RBP : frame pointer (even if CONFIG_FRAME_POINTER=n) r9d : skb->len - skb->data_len (headlen) r8 : skb->data To get a trace of generated code, use : echo 2 >/proc/sys/net/core/bpf_jit_enable Example of generated code : # tcpdump -p -n -s 0 -i eth1 host 192.168.20.0/24 flen=18 proglen=147 pass=3 image=ffffffffa00b5000 JIT code: ffffffffa00b5000: 55 48 89 e5 48 83 ec 60 48 89 5d f8 44 8b 4f 60 JIT code: ffffffffa00b5010: 44 2b 4f 64 4c 8b 87 b8 00 00 00 be 0c 00 00 00 JIT code: ffffffffa00b5020: e8 24 7b f7 e0 3d 00 08 00 00 75 28 be 1a 00 00 JIT code: ffffffffa00b5030: 00 e8 fe 7a f7 e0 24 00 3d 00 14 a8 c0 74 49 be JIT code: ffffffffa00b5040: 1e 00 00 00 e8 eb 7a f7 e0 24 00 3d 00 14 a8 c0 JIT code: ffffffffa00b5050: 74 36 eb 3b 3d 06 08 00 00 74 07 3d 35 80 00 00 JIT code: ffffffffa00b5060: 75 2d be 1c 00 00 00 e8 c8 7a f7 e0 24 00 3d 00 JIT code: ffffffffa00b5070: 14 a8 c0 74 13 be 26 00 00 00 e8 b5 7a f7 e0 24 JIT code: ffffffffa00b5080: 00 3d 00 14 a8 c0 75 07 b8 ff ff 00 00 eb 02 31 JIT code: ffffffffa00b5090: c0 c9 c3 BPF program is 144 bytes long, so native program is almost same size ;) (000) ldh [12] (001) jeq #0x800 jt 2 jf 8 (002) ld [26] (003) and #0xffffff00 (004) jeq #0xc0a81400 jt 16 jf 5 (005) ld [30] (006) and #0xffffff00 (007) jeq #0xc0a81400 jt 16 jf 17 (008) jeq #0x806 jt 10 jf 9 (009) jeq #0x8035 jt 10 jf 17 (010) ld [28] (011) and #0xffffff00 (012) jeq #0xc0a81400 jt 16 jf 13 (013) ld [38] (014) and #0xffffff00 (015) jeq #0xc0a81400 jt 16 jf 17 (016) ret #65535 (017) ret #0 Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@infradead.org> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Hagen Paul Pfeifer <hagen@jauu.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-04-20 13:27:32 +04:00
unsigned int (*bpf_func)(const struct sk_buff *skb,
const struct sock_filter *filter);
net: fix unsafe set_memory_rw from softirq on x86 system with net.core.bpf_jit_enable = 1 sudo tcpdump -i eth1 'tcp port 22' causes the warning: [ 56.766097] Possible unsafe locking scenario: [ 56.766097] [ 56.780146] CPU0 [ 56.786807] ---- [ 56.793188] lock(&(&vb->lock)->rlock); [ 56.799593] <Interrupt> [ 56.805889] lock(&(&vb->lock)->rlock); [ 56.812266] [ 56.812266] *** DEADLOCK *** [ 56.812266] [ 56.830670] 1 lock held by ksoftirqd/1/13: [ 56.836838] #0: (rcu_read_lock){.+.+..}, at: [<ffffffff8118f44c>] vm_unmap_aliases+0x8c/0x380 [ 56.849757] [ 56.849757] stack backtrace: [ 56.862194] CPU: 1 PID: 13 Comm: ksoftirqd/1 Not tainted 3.12.0-rc3+ #45 [ 56.868721] Hardware name: System manufacturer System Product Name/P8Z77 WS, BIOS 3007 07/26/2012 [ 56.882004] ffffffff821944c0 ffff88080bbdb8c8 ffffffff8175a145 0000000000000007 [ 56.895630] ffff88080bbd5f40 ffff88080bbdb928 ffffffff81755b14 0000000000000001 [ 56.909313] ffff880800000001 ffff880800000000 ffffffff8101178f 0000000000000001 [ 56.923006] Call Trace: [ 56.929532] [<ffffffff8175a145>] dump_stack+0x55/0x76 [ 56.936067] [<ffffffff81755b14>] print_usage_bug+0x1f7/0x208 [ 56.942445] [<ffffffff8101178f>] ? save_stack_trace+0x2f/0x50 [ 56.948932] [<ffffffff810cc0a0>] ? check_usage_backwards+0x150/0x150 [ 56.955470] [<ffffffff810ccb52>] mark_lock+0x282/0x2c0 [ 56.961945] [<ffffffff810ccfed>] __lock_acquire+0x45d/0x1d50 [ 56.968474] [<ffffffff810cce6e>] ? __lock_acquire+0x2de/0x1d50 [ 56.975140] [<ffffffff81393bf5>] ? cpumask_next_and+0x55/0x90 [ 56.981942] [<ffffffff810cef72>] lock_acquire+0x92/0x1d0 [ 56.988745] [<ffffffff8118f52a>] ? vm_unmap_aliases+0x16a/0x380 [ 56.995619] [<ffffffff817628f1>] _raw_spin_lock+0x41/0x50 [ 57.002493] [<ffffffff8118f52a>] ? vm_unmap_aliases+0x16a/0x380 [ 57.009447] [<ffffffff8118f52a>] vm_unmap_aliases+0x16a/0x380 [ 57.016477] [<ffffffff8118f44c>] ? vm_unmap_aliases+0x8c/0x380 [ 57.023607] [<ffffffff810436b0>] change_page_attr_set_clr+0xc0/0x460 [ 57.030818] [<ffffffff810cfb8d>] ? trace_hardirqs_on+0xd/0x10 [ 57.037896] [<ffffffff811a8330>] ? kmem_cache_free+0xb0/0x2b0 [ 57.044789] [<ffffffff811b59c3>] ? free_object_rcu+0x93/0xa0 [ 57.051720] [<ffffffff81043d9f>] set_memory_rw+0x2f/0x40 [ 57.058727] [<ffffffff8104e17c>] bpf_jit_free+0x2c/0x40 [ 57.065577] [<ffffffff81642cba>] sk_filter_release_rcu+0x1a/0x30 [ 57.072338] [<ffffffff811108e2>] rcu_process_callbacks+0x202/0x7c0 [ 57.078962] [<ffffffff81057f17>] __do_softirq+0xf7/0x3f0 [ 57.085373] [<ffffffff81058245>] run_ksoftirqd+0x35/0x70 cannot reuse jited filter memory, since it's readonly, so use original bpf insns memory to hold work_struct defer kfree of sk_filter until jit completed freeing tested on x86_64 and i386 Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-04 11:14:06 +04:00
union {
struct sock_filter insns[0];
struct work_struct work;
};
};
net: fix unsafe set_memory_rw from softirq on x86 system with net.core.bpf_jit_enable = 1 sudo tcpdump -i eth1 'tcp port 22' causes the warning: [ 56.766097] Possible unsafe locking scenario: [ 56.766097] [ 56.780146] CPU0 [ 56.786807] ---- [ 56.793188] lock(&(&vb->lock)->rlock); [ 56.799593] <Interrupt> [ 56.805889] lock(&(&vb->lock)->rlock); [ 56.812266] [ 56.812266] *** DEADLOCK *** [ 56.812266] [ 56.830670] 1 lock held by ksoftirqd/1/13: [ 56.836838] #0: (rcu_read_lock){.+.+..}, at: [<ffffffff8118f44c>] vm_unmap_aliases+0x8c/0x380 [ 56.849757] [ 56.849757] stack backtrace: [ 56.862194] CPU: 1 PID: 13 Comm: ksoftirqd/1 Not tainted 3.12.0-rc3+ #45 [ 56.868721] Hardware name: System manufacturer System Product Name/P8Z77 WS, BIOS 3007 07/26/2012 [ 56.882004] ffffffff821944c0 ffff88080bbdb8c8 ffffffff8175a145 0000000000000007 [ 56.895630] ffff88080bbd5f40 ffff88080bbdb928 ffffffff81755b14 0000000000000001 [ 56.909313] ffff880800000001 ffff880800000000 ffffffff8101178f 0000000000000001 [ 56.923006] Call Trace: [ 56.929532] [<ffffffff8175a145>] dump_stack+0x55/0x76 [ 56.936067] [<ffffffff81755b14>] print_usage_bug+0x1f7/0x208 [ 56.942445] [<ffffffff8101178f>] ? save_stack_trace+0x2f/0x50 [ 56.948932] [<ffffffff810cc0a0>] ? check_usage_backwards+0x150/0x150 [ 56.955470] [<ffffffff810ccb52>] mark_lock+0x282/0x2c0 [ 56.961945] [<ffffffff810ccfed>] __lock_acquire+0x45d/0x1d50 [ 56.968474] [<ffffffff810cce6e>] ? __lock_acquire+0x2de/0x1d50 [ 56.975140] [<ffffffff81393bf5>] ? cpumask_next_and+0x55/0x90 [ 56.981942] [<ffffffff810cef72>] lock_acquire+0x92/0x1d0 [ 56.988745] [<ffffffff8118f52a>] ? vm_unmap_aliases+0x16a/0x380 [ 56.995619] [<ffffffff817628f1>] _raw_spin_lock+0x41/0x50 [ 57.002493] [<ffffffff8118f52a>] ? vm_unmap_aliases+0x16a/0x380 [ 57.009447] [<ffffffff8118f52a>] vm_unmap_aliases+0x16a/0x380 [ 57.016477] [<ffffffff8118f44c>] ? vm_unmap_aliases+0x8c/0x380 [ 57.023607] [<ffffffff810436b0>] change_page_attr_set_clr+0xc0/0x460 [ 57.030818] [<ffffffff810cfb8d>] ? trace_hardirqs_on+0xd/0x10 [ 57.037896] [<ffffffff811a8330>] ? kmem_cache_free+0xb0/0x2b0 [ 57.044789] [<ffffffff811b59c3>] ? free_object_rcu+0x93/0xa0 [ 57.051720] [<ffffffff81043d9f>] set_memory_rw+0x2f/0x40 [ 57.058727] [<ffffffff8104e17c>] bpf_jit_free+0x2c/0x40 [ 57.065577] [<ffffffff81642cba>] sk_filter_release_rcu+0x1a/0x30 [ 57.072338] [<ffffffff811108e2>] rcu_process_callbacks+0x202/0x7c0 [ 57.078962] [<ffffffff81057f17>] __do_softirq+0xf7/0x3f0 [ 57.085373] [<ffffffff81058245>] run_ksoftirqd+0x35/0x70 cannot reuse jited filter memory, since it's readonly, so use original bpf insns memory to hold work_struct defer kfree of sk_filter until jit completed freeing tested on x86_64 and i386 Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-04 11:14:06 +04:00
static inline unsigned int sk_filter_size(unsigned int proglen)
{
net: fix unsafe set_memory_rw from softirq on x86 system with net.core.bpf_jit_enable = 1 sudo tcpdump -i eth1 'tcp port 22' causes the warning: [ 56.766097] Possible unsafe locking scenario: [ 56.766097] [ 56.780146] CPU0 [ 56.786807] ---- [ 56.793188] lock(&(&vb->lock)->rlock); [ 56.799593] <Interrupt> [ 56.805889] lock(&(&vb->lock)->rlock); [ 56.812266] [ 56.812266] *** DEADLOCK *** [ 56.812266] [ 56.830670] 1 lock held by ksoftirqd/1/13: [ 56.836838] #0: (rcu_read_lock){.+.+..}, at: [<ffffffff8118f44c>] vm_unmap_aliases+0x8c/0x380 [ 56.849757] [ 56.849757] stack backtrace: [ 56.862194] CPU: 1 PID: 13 Comm: ksoftirqd/1 Not tainted 3.12.0-rc3+ #45 [ 56.868721] Hardware name: System manufacturer System Product Name/P8Z77 WS, BIOS 3007 07/26/2012 [ 56.882004] ffffffff821944c0 ffff88080bbdb8c8 ffffffff8175a145 0000000000000007 [ 56.895630] ffff88080bbd5f40 ffff88080bbdb928 ffffffff81755b14 0000000000000001 [ 56.909313] ffff880800000001 ffff880800000000 ffffffff8101178f 0000000000000001 [ 56.923006] Call Trace: [ 56.929532] [<ffffffff8175a145>] dump_stack+0x55/0x76 [ 56.936067] [<ffffffff81755b14>] print_usage_bug+0x1f7/0x208 [ 56.942445] [<ffffffff8101178f>] ? save_stack_trace+0x2f/0x50 [ 56.948932] [<ffffffff810cc0a0>] ? check_usage_backwards+0x150/0x150 [ 56.955470] [<ffffffff810ccb52>] mark_lock+0x282/0x2c0 [ 56.961945] [<ffffffff810ccfed>] __lock_acquire+0x45d/0x1d50 [ 56.968474] [<ffffffff810cce6e>] ? __lock_acquire+0x2de/0x1d50 [ 56.975140] [<ffffffff81393bf5>] ? cpumask_next_and+0x55/0x90 [ 56.981942] [<ffffffff810cef72>] lock_acquire+0x92/0x1d0 [ 56.988745] [<ffffffff8118f52a>] ? vm_unmap_aliases+0x16a/0x380 [ 56.995619] [<ffffffff817628f1>] _raw_spin_lock+0x41/0x50 [ 57.002493] [<ffffffff8118f52a>] ? vm_unmap_aliases+0x16a/0x380 [ 57.009447] [<ffffffff8118f52a>] vm_unmap_aliases+0x16a/0x380 [ 57.016477] [<ffffffff8118f44c>] ? vm_unmap_aliases+0x8c/0x380 [ 57.023607] [<ffffffff810436b0>] change_page_attr_set_clr+0xc0/0x460 [ 57.030818] [<ffffffff810cfb8d>] ? trace_hardirqs_on+0xd/0x10 [ 57.037896] [<ffffffff811a8330>] ? kmem_cache_free+0xb0/0x2b0 [ 57.044789] [<ffffffff811b59c3>] ? free_object_rcu+0x93/0xa0 [ 57.051720] [<ffffffff81043d9f>] set_memory_rw+0x2f/0x40 [ 57.058727] [<ffffffff8104e17c>] bpf_jit_free+0x2c/0x40 [ 57.065577] [<ffffffff81642cba>] sk_filter_release_rcu+0x1a/0x30 [ 57.072338] [<ffffffff811108e2>] rcu_process_callbacks+0x202/0x7c0 [ 57.078962] [<ffffffff81057f17>] __do_softirq+0xf7/0x3f0 [ 57.085373] [<ffffffff81058245>] run_ksoftirqd+0x35/0x70 cannot reuse jited filter memory, since it's readonly, so use original bpf insns memory to hold work_struct defer kfree of sk_filter until jit completed freeing tested on x86_64 and i386 Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-04 11:14:06 +04:00
return max(sizeof(struct sk_filter),
offsetof(struct sk_filter, insns[proglen]));
}
extern int sk_filter(struct sock *sk, struct sk_buff *skb);
extern unsigned int sk_run_filter(const struct sk_buff *skb,
const struct sock_filter *filter);
extern int sk_unattached_filter_create(struct sk_filter **pfp,
struct sock_fprog *fprog);
extern void sk_unattached_filter_destroy(struct sk_filter *fp);
extern int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
extern int sk_detach_filter(struct sock *sk);
extern int sk_chk_filter(struct sock_filter *filter, unsigned int flen);
sk-filter: Add ability to get socket filter program (v2) The SO_ATTACH_FILTER option is set only. I propose to add the get ability by using SO_ATTACH_FILTER in getsockopt. To be less irritating to eyes the SO_GET_FILTER alias to it is declared. This ability is required by checkpoint-restore project to be able to save full state of a socket. There are two issues with getting filter back. First, kernel modifies the sock_filter->code on filter load, thus in order to return the filter element back to user we have to decode it into user-visible constants. Fortunately the modification in question is interconvertible. Second, the BPF_S_ALU_DIV_K code modifies the command argument k to speed up the run-time division by doing kernel_k = reciprocal(user_k). Bad news is that different user_k may result in same kernel_k, so we can't get the original user_k back. Good news is that we don't have to do it. What we need to is calculate a user2_k so, that reciprocal(user2_k) == reciprocal(user_k) == kernel_k i.e. if it's re-loaded back the compiled again value will be exactly the same as it was. That said, the user2_k can be calculated like this user2_k = reciprocal(kernel_k) with an exception, that if kernel_k == 0, then user2_k == 1. The optlen argument is treated like this -- when zero, kernel returns the amount of sock_fprog elements in filter, otherwise it should be large enough for the sock_fprog array. changes since v1: * Declared SO_GET_FILTER in all arch headers * Added decode of vlan-tag codes Signed-off-by: Pavel Emelyanov <xemul@parallels.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-01 06:01:48 +04:00
extern int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, unsigned len);
extern void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to);
net: filter: Just In Time compiler for x86-64 In order to speedup packet filtering, here is an implementation of a JIT compiler for x86_64 It is disabled by default, and must be enabled by the admin. echo 1 >/proc/sys/net/core/bpf_jit_enable It uses module_alloc() and module_free() to get memory in the 2GB text kernel range since we call helpers functions from the generated code. EAX : BPF A accumulator EBX : BPF X accumulator RDI : pointer to skb (first argument given to JIT function) RBP : frame pointer (even if CONFIG_FRAME_POINTER=n) r9d : skb->len - skb->data_len (headlen) r8 : skb->data To get a trace of generated code, use : echo 2 >/proc/sys/net/core/bpf_jit_enable Example of generated code : # tcpdump -p -n -s 0 -i eth1 host 192.168.20.0/24 flen=18 proglen=147 pass=3 image=ffffffffa00b5000 JIT code: ffffffffa00b5000: 55 48 89 e5 48 83 ec 60 48 89 5d f8 44 8b 4f 60 JIT code: ffffffffa00b5010: 44 2b 4f 64 4c 8b 87 b8 00 00 00 be 0c 00 00 00 JIT code: ffffffffa00b5020: e8 24 7b f7 e0 3d 00 08 00 00 75 28 be 1a 00 00 JIT code: ffffffffa00b5030: 00 e8 fe 7a f7 e0 24 00 3d 00 14 a8 c0 74 49 be JIT code: ffffffffa00b5040: 1e 00 00 00 e8 eb 7a f7 e0 24 00 3d 00 14 a8 c0 JIT code: ffffffffa00b5050: 74 36 eb 3b 3d 06 08 00 00 74 07 3d 35 80 00 00 JIT code: ffffffffa00b5060: 75 2d be 1c 00 00 00 e8 c8 7a f7 e0 24 00 3d 00 JIT code: ffffffffa00b5070: 14 a8 c0 74 13 be 26 00 00 00 e8 b5 7a f7 e0 24 JIT code: ffffffffa00b5080: 00 3d 00 14 a8 c0 75 07 b8 ff ff 00 00 eb 02 31 JIT code: ffffffffa00b5090: c0 c9 c3 BPF program is 144 bytes long, so native program is almost same size ;) (000) ldh [12] (001) jeq #0x800 jt 2 jf 8 (002) ld [26] (003) and #0xffffff00 (004) jeq #0xc0a81400 jt 16 jf 5 (005) ld [30] (006) and #0xffffff00 (007) jeq #0xc0a81400 jt 16 jf 17 (008) jeq #0x806 jt 10 jf 9 (009) jeq #0x8035 jt 10 jf 17 (010) ld [28] (011) and #0xffffff00 (012) jeq #0xc0a81400 jt 16 jf 13 (013) ld [38] (014) and #0xffffff00 (015) jeq #0xc0a81400 jt 16 jf 17 (016) ret #65535 (017) ret #0 Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@infradead.org> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Hagen Paul Pfeifer <hagen@jauu.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-04-20 13:27:32 +04:00
#ifdef CONFIG_BPF_JIT
#include <stdarg.h>
#include <linux/linkage.h>
#include <linux/printk.h>
net: filter: Just In Time compiler for x86-64 In order to speedup packet filtering, here is an implementation of a JIT compiler for x86_64 It is disabled by default, and must be enabled by the admin. echo 1 >/proc/sys/net/core/bpf_jit_enable It uses module_alloc() and module_free() to get memory in the 2GB text kernel range since we call helpers functions from the generated code. EAX : BPF A accumulator EBX : BPF X accumulator RDI : pointer to skb (first argument given to JIT function) RBP : frame pointer (even if CONFIG_FRAME_POINTER=n) r9d : skb->len - skb->data_len (headlen) r8 : skb->data To get a trace of generated code, use : echo 2 >/proc/sys/net/core/bpf_jit_enable Example of generated code : # tcpdump -p -n -s 0 -i eth1 host 192.168.20.0/24 flen=18 proglen=147 pass=3 image=ffffffffa00b5000 JIT code: ffffffffa00b5000: 55 48 89 e5 48 83 ec 60 48 89 5d f8 44 8b 4f 60 JIT code: ffffffffa00b5010: 44 2b 4f 64 4c 8b 87 b8 00 00 00 be 0c 00 00 00 JIT code: ffffffffa00b5020: e8 24 7b f7 e0 3d 00 08 00 00 75 28 be 1a 00 00 JIT code: ffffffffa00b5030: 00 e8 fe 7a f7 e0 24 00 3d 00 14 a8 c0 74 49 be JIT code: ffffffffa00b5040: 1e 00 00 00 e8 eb 7a f7 e0 24 00 3d 00 14 a8 c0 JIT code: ffffffffa00b5050: 74 36 eb 3b 3d 06 08 00 00 74 07 3d 35 80 00 00 JIT code: ffffffffa00b5060: 75 2d be 1c 00 00 00 e8 c8 7a f7 e0 24 00 3d 00 JIT code: ffffffffa00b5070: 14 a8 c0 74 13 be 26 00 00 00 e8 b5 7a f7 e0 24 JIT code: ffffffffa00b5080: 00 3d 00 14 a8 c0 75 07 b8 ff ff 00 00 eb 02 31 JIT code: ffffffffa00b5090: c0 c9 c3 BPF program is 144 bytes long, so native program is almost same size ;) (000) ldh [12] (001) jeq #0x800 jt 2 jf 8 (002) ld [26] (003) and #0xffffff00 (004) jeq #0xc0a81400 jt 16 jf 5 (005) ld [30] (006) and #0xffffff00 (007) jeq #0xc0a81400 jt 16 jf 17 (008) jeq #0x806 jt 10 jf 9 (009) jeq #0x8035 jt 10 jf 17 (010) ld [28] (011) and #0xffffff00 (012) jeq #0xc0a81400 jt 16 jf 13 (013) ld [38] (014) and #0xffffff00 (015) jeq #0xc0a81400 jt 16 jf 17 (016) ret #65535 (017) ret #0 Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@infradead.org> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Hagen Paul Pfeifer <hagen@jauu.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-04-20 13:27:32 +04:00
extern void bpf_jit_compile(struct sk_filter *fp);
extern void bpf_jit_free(struct sk_filter *fp);
static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen,
u32 pass, void *image)
{
pr_err("flen=%u proglen=%u pass=%u image=%pK\n",
flen, proglen, pass, image);
if (image)
print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_OFFSET,
16, 1, image, proglen, false);
}
net: filter: Just In Time compiler for x86-64 In order to speedup packet filtering, here is an implementation of a JIT compiler for x86_64 It is disabled by default, and must be enabled by the admin. echo 1 >/proc/sys/net/core/bpf_jit_enable It uses module_alloc() and module_free() to get memory in the 2GB text kernel range since we call helpers functions from the generated code. EAX : BPF A accumulator EBX : BPF X accumulator RDI : pointer to skb (first argument given to JIT function) RBP : frame pointer (even if CONFIG_FRAME_POINTER=n) r9d : skb->len - skb->data_len (headlen) r8 : skb->data To get a trace of generated code, use : echo 2 >/proc/sys/net/core/bpf_jit_enable Example of generated code : # tcpdump -p -n -s 0 -i eth1 host 192.168.20.0/24 flen=18 proglen=147 pass=3 image=ffffffffa00b5000 JIT code: ffffffffa00b5000: 55 48 89 e5 48 83 ec 60 48 89 5d f8 44 8b 4f 60 JIT code: ffffffffa00b5010: 44 2b 4f 64 4c 8b 87 b8 00 00 00 be 0c 00 00 00 JIT code: ffffffffa00b5020: e8 24 7b f7 e0 3d 00 08 00 00 75 28 be 1a 00 00 JIT code: ffffffffa00b5030: 00 e8 fe 7a f7 e0 24 00 3d 00 14 a8 c0 74 49 be JIT code: ffffffffa00b5040: 1e 00 00 00 e8 eb 7a f7 e0 24 00 3d 00 14 a8 c0 JIT code: ffffffffa00b5050: 74 36 eb 3b 3d 06 08 00 00 74 07 3d 35 80 00 00 JIT code: ffffffffa00b5060: 75 2d be 1c 00 00 00 e8 c8 7a f7 e0 24 00 3d 00 JIT code: ffffffffa00b5070: 14 a8 c0 74 13 be 26 00 00 00 e8 b5 7a f7 e0 24 JIT code: ffffffffa00b5080: 00 3d 00 14 a8 c0 75 07 b8 ff ff 00 00 eb 02 31 JIT code: ffffffffa00b5090: c0 c9 c3 BPF program is 144 bytes long, so native program is almost same size ;) (000) ldh [12] (001) jeq #0x800 jt 2 jf 8 (002) ld [26] (003) and #0xffffff00 (004) jeq #0xc0a81400 jt 16 jf 5 (005) ld [30] (006) and #0xffffff00 (007) jeq #0xc0a81400 jt 16 jf 17 (008) jeq #0x806 jt 10 jf 9 (009) jeq #0x8035 jt 10 jf 17 (010) ld [28] (011) and #0xffffff00 (012) jeq #0xc0a81400 jt 16 jf 13 (013) ld [38] (014) and #0xffffff00 (015) jeq #0xc0a81400 jt 16 jf 17 (016) ret #65535 (017) ret #0 Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@infradead.org> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Hagen Paul Pfeifer <hagen@jauu.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-04-20 13:27:32 +04:00
#define SK_RUN_FILTER(FILTER, SKB) (*FILTER->bpf_func)(SKB, FILTER->insns)
#else
net: fix unsafe set_memory_rw from softirq on x86 system with net.core.bpf_jit_enable = 1 sudo tcpdump -i eth1 'tcp port 22' causes the warning: [ 56.766097] Possible unsafe locking scenario: [ 56.766097] [ 56.780146] CPU0 [ 56.786807] ---- [ 56.793188] lock(&(&vb->lock)->rlock); [ 56.799593] <Interrupt> [ 56.805889] lock(&(&vb->lock)->rlock); [ 56.812266] [ 56.812266] *** DEADLOCK *** [ 56.812266] [ 56.830670] 1 lock held by ksoftirqd/1/13: [ 56.836838] #0: (rcu_read_lock){.+.+..}, at: [<ffffffff8118f44c>] vm_unmap_aliases+0x8c/0x380 [ 56.849757] [ 56.849757] stack backtrace: [ 56.862194] CPU: 1 PID: 13 Comm: ksoftirqd/1 Not tainted 3.12.0-rc3+ #45 [ 56.868721] Hardware name: System manufacturer System Product Name/P8Z77 WS, BIOS 3007 07/26/2012 [ 56.882004] ffffffff821944c0 ffff88080bbdb8c8 ffffffff8175a145 0000000000000007 [ 56.895630] ffff88080bbd5f40 ffff88080bbdb928 ffffffff81755b14 0000000000000001 [ 56.909313] ffff880800000001 ffff880800000000 ffffffff8101178f 0000000000000001 [ 56.923006] Call Trace: [ 56.929532] [<ffffffff8175a145>] dump_stack+0x55/0x76 [ 56.936067] [<ffffffff81755b14>] print_usage_bug+0x1f7/0x208 [ 56.942445] [<ffffffff8101178f>] ? save_stack_trace+0x2f/0x50 [ 56.948932] [<ffffffff810cc0a0>] ? check_usage_backwards+0x150/0x150 [ 56.955470] [<ffffffff810ccb52>] mark_lock+0x282/0x2c0 [ 56.961945] [<ffffffff810ccfed>] __lock_acquire+0x45d/0x1d50 [ 56.968474] [<ffffffff810cce6e>] ? __lock_acquire+0x2de/0x1d50 [ 56.975140] [<ffffffff81393bf5>] ? cpumask_next_and+0x55/0x90 [ 56.981942] [<ffffffff810cef72>] lock_acquire+0x92/0x1d0 [ 56.988745] [<ffffffff8118f52a>] ? vm_unmap_aliases+0x16a/0x380 [ 56.995619] [<ffffffff817628f1>] _raw_spin_lock+0x41/0x50 [ 57.002493] [<ffffffff8118f52a>] ? vm_unmap_aliases+0x16a/0x380 [ 57.009447] [<ffffffff8118f52a>] vm_unmap_aliases+0x16a/0x380 [ 57.016477] [<ffffffff8118f44c>] ? vm_unmap_aliases+0x8c/0x380 [ 57.023607] [<ffffffff810436b0>] change_page_attr_set_clr+0xc0/0x460 [ 57.030818] [<ffffffff810cfb8d>] ? trace_hardirqs_on+0xd/0x10 [ 57.037896] [<ffffffff811a8330>] ? kmem_cache_free+0xb0/0x2b0 [ 57.044789] [<ffffffff811b59c3>] ? free_object_rcu+0x93/0xa0 [ 57.051720] [<ffffffff81043d9f>] set_memory_rw+0x2f/0x40 [ 57.058727] [<ffffffff8104e17c>] bpf_jit_free+0x2c/0x40 [ 57.065577] [<ffffffff81642cba>] sk_filter_release_rcu+0x1a/0x30 [ 57.072338] [<ffffffff811108e2>] rcu_process_callbacks+0x202/0x7c0 [ 57.078962] [<ffffffff81057f17>] __do_softirq+0xf7/0x3f0 [ 57.085373] [<ffffffff81058245>] run_ksoftirqd+0x35/0x70 cannot reuse jited filter memory, since it's readonly, so use original bpf insns memory to hold work_struct defer kfree of sk_filter until jit completed freeing tested on x86_64 and i386 Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-04 11:14:06 +04:00
#include <linux/slab.h>
net: filter: Just In Time compiler for x86-64 In order to speedup packet filtering, here is an implementation of a JIT compiler for x86_64 It is disabled by default, and must be enabled by the admin. echo 1 >/proc/sys/net/core/bpf_jit_enable It uses module_alloc() and module_free() to get memory in the 2GB text kernel range since we call helpers functions from the generated code. EAX : BPF A accumulator EBX : BPF X accumulator RDI : pointer to skb (first argument given to JIT function) RBP : frame pointer (even if CONFIG_FRAME_POINTER=n) r9d : skb->len - skb->data_len (headlen) r8 : skb->data To get a trace of generated code, use : echo 2 >/proc/sys/net/core/bpf_jit_enable Example of generated code : # tcpdump -p -n -s 0 -i eth1 host 192.168.20.0/24 flen=18 proglen=147 pass=3 image=ffffffffa00b5000 JIT code: ffffffffa00b5000: 55 48 89 e5 48 83 ec 60 48 89 5d f8 44 8b 4f 60 JIT code: ffffffffa00b5010: 44 2b 4f 64 4c 8b 87 b8 00 00 00 be 0c 00 00 00 JIT code: ffffffffa00b5020: e8 24 7b f7 e0 3d 00 08 00 00 75 28 be 1a 00 00 JIT code: ffffffffa00b5030: 00 e8 fe 7a f7 e0 24 00 3d 00 14 a8 c0 74 49 be JIT code: ffffffffa00b5040: 1e 00 00 00 e8 eb 7a f7 e0 24 00 3d 00 14 a8 c0 JIT code: ffffffffa00b5050: 74 36 eb 3b 3d 06 08 00 00 74 07 3d 35 80 00 00 JIT code: ffffffffa00b5060: 75 2d be 1c 00 00 00 e8 c8 7a f7 e0 24 00 3d 00 JIT code: ffffffffa00b5070: 14 a8 c0 74 13 be 26 00 00 00 e8 b5 7a f7 e0 24 JIT code: ffffffffa00b5080: 00 3d 00 14 a8 c0 75 07 b8 ff ff 00 00 eb 02 31 JIT code: ffffffffa00b5090: c0 c9 c3 BPF program is 144 bytes long, so native program is almost same size ;) (000) ldh [12] (001) jeq #0x800 jt 2 jf 8 (002) ld [26] (003) and #0xffffff00 (004) jeq #0xc0a81400 jt 16 jf 5 (005) ld [30] (006) and #0xffffff00 (007) jeq #0xc0a81400 jt 16 jf 17 (008) jeq #0x806 jt 10 jf 9 (009) jeq #0x8035 jt 10 jf 17 (010) ld [28] (011) and #0xffffff00 (012) jeq #0xc0a81400 jt 16 jf 13 (013) ld [38] (014) and #0xffffff00 (015) jeq #0xc0a81400 jt 16 jf 17 (016) ret #65535 (017) ret #0 Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@infradead.org> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Hagen Paul Pfeifer <hagen@jauu.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-04-20 13:27:32 +04:00
static inline void bpf_jit_compile(struct sk_filter *fp)
{
}
static inline void bpf_jit_free(struct sk_filter *fp)
{
net: fix unsafe set_memory_rw from softirq on x86 system with net.core.bpf_jit_enable = 1 sudo tcpdump -i eth1 'tcp port 22' causes the warning: [ 56.766097] Possible unsafe locking scenario: [ 56.766097] [ 56.780146] CPU0 [ 56.786807] ---- [ 56.793188] lock(&(&vb->lock)->rlock); [ 56.799593] <Interrupt> [ 56.805889] lock(&(&vb->lock)->rlock); [ 56.812266] [ 56.812266] *** DEADLOCK *** [ 56.812266] [ 56.830670] 1 lock held by ksoftirqd/1/13: [ 56.836838] #0: (rcu_read_lock){.+.+..}, at: [<ffffffff8118f44c>] vm_unmap_aliases+0x8c/0x380 [ 56.849757] [ 56.849757] stack backtrace: [ 56.862194] CPU: 1 PID: 13 Comm: ksoftirqd/1 Not tainted 3.12.0-rc3+ #45 [ 56.868721] Hardware name: System manufacturer System Product Name/P8Z77 WS, BIOS 3007 07/26/2012 [ 56.882004] ffffffff821944c0 ffff88080bbdb8c8 ffffffff8175a145 0000000000000007 [ 56.895630] ffff88080bbd5f40 ffff88080bbdb928 ffffffff81755b14 0000000000000001 [ 56.909313] ffff880800000001 ffff880800000000 ffffffff8101178f 0000000000000001 [ 56.923006] Call Trace: [ 56.929532] [<ffffffff8175a145>] dump_stack+0x55/0x76 [ 56.936067] [<ffffffff81755b14>] print_usage_bug+0x1f7/0x208 [ 56.942445] [<ffffffff8101178f>] ? save_stack_trace+0x2f/0x50 [ 56.948932] [<ffffffff810cc0a0>] ? check_usage_backwards+0x150/0x150 [ 56.955470] [<ffffffff810ccb52>] mark_lock+0x282/0x2c0 [ 56.961945] [<ffffffff810ccfed>] __lock_acquire+0x45d/0x1d50 [ 56.968474] [<ffffffff810cce6e>] ? __lock_acquire+0x2de/0x1d50 [ 56.975140] [<ffffffff81393bf5>] ? cpumask_next_and+0x55/0x90 [ 56.981942] [<ffffffff810cef72>] lock_acquire+0x92/0x1d0 [ 56.988745] [<ffffffff8118f52a>] ? vm_unmap_aliases+0x16a/0x380 [ 56.995619] [<ffffffff817628f1>] _raw_spin_lock+0x41/0x50 [ 57.002493] [<ffffffff8118f52a>] ? vm_unmap_aliases+0x16a/0x380 [ 57.009447] [<ffffffff8118f52a>] vm_unmap_aliases+0x16a/0x380 [ 57.016477] [<ffffffff8118f44c>] ? vm_unmap_aliases+0x8c/0x380 [ 57.023607] [<ffffffff810436b0>] change_page_attr_set_clr+0xc0/0x460 [ 57.030818] [<ffffffff810cfb8d>] ? trace_hardirqs_on+0xd/0x10 [ 57.037896] [<ffffffff811a8330>] ? kmem_cache_free+0xb0/0x2b0 [ 57.044789] [<ffffffff811b59c3>] ? free_object_rcu+0x93/0xa0 [ 57.051720] [<ffffffff81043d9f>] set_memory_rw+0x2f/0x40 [ 57.058727] [<ffffffff8104e17c>] bpf_jit_free+0x2c/0x40 [ 57.065577] [<ffffffff81642cba>] sk_filter_release_rcu+0x1a/0x30 [ 57.072338] [<ffffffff811108e2>] rcu_process_callbacks+0x202/0x7c0 [ 57.078962] [<ffffffff81057f17>] __do_softirq+0xf7/0x3f0 [ 57.085373] [<ffffffff81058245>] run_ksoftirqd+0x35/0x70 cannot reuse jited filter memory, since it's readonly, so use original bpf insns memory to hold work_struct defer kfree of sk_filter until jit completed freeing tested on x86_64 and i386 Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-04 11:14:06 +04:00
kfree(fp);
net: filter: Just In Time compiler for x86-64 In order to speedup packet filtering, here is an implementation of a JIT compiler for x86_64 It is disabled by default, and must be enabled by the admin. echo 1 >/proc/sys/net/core/bpf_jit_enable It uses module_alloc() and module_free() to get memory in the 2GB text kernel range since we call helpers functions from the generated code. EAX : BPF A accumulator EBX : BPF X accumulator RDI : pointer to skb (first argument given to JIT function) RBP : frame pointer (even if CONFIG_FRAME_POINTER=n) r9d : skb->len - skb->data_len (headlen) r8 : skb->data To get a trace of generated code, use : echo 2 >/proc/sys/net/core/bpf_jit_enable Example of generated code : # tcpdump -p -n -s 0 -i eth1 host 192.168.20.0/24 flen=18 proglen=147 pass=3 image=ffffffffa00b5000 JIT code: ffffffffa00b5000: 55 48 89 e5 48 83 ec 60 48 89 5d f8 44 8b 4f 60 JIT code: ffffffffa00b5010: 44 2b 4f 64 4c 8b 87 b8 00 00 00 be 0c 00 00 00 JIT code: ffffffffa00b5020: e8 24 7b f7 e0 3d 00 08 00 00 75 28 be 1a 00 00 JIT code: ffffffffa00b5030: 00 e8 fe 7a f7 e0 24 00 3d 00 14 a8 c0 74 49 be JIT code: ffffffffa00b5040: 1e 00 00 00 e8 eb 7a f7 e0 24 00 3d 00 14 a8 c0 JIT code: ffffffffa00b5050: 74 36 eb 3b 3d 06 08 00 00 74 07 3d 35 80 00 00 JIT code: ffffffffa00b5060: 75 2d be 1c 00 00 00 e8 c8 7a f7 e0 24 00 3d 00 JIT code: ffffffffa00b5070: 14 a8 c0 74 13 be 26 00 00 00 e8 b5 7a f7 e0 24 JIT code: ffffffffa00b5080: 00 3d 00 14 a8 c0 75 07 b8 ff ff 00 00 eb 02 31 JIT code: ffffffffa00b5090: c0 c9 c3 BPF program is 144 bytes long, so native program is almost same size ;) (000) ldh [12] (001) jeq #0x800 jt 2 jf 8 (002) ld [26] (003) and #0xffffff00 (004) jeq #0xc0a81400 jt 16 jf 5 (005) ld [30] (006) and #0xffffff00 (007) jeq #0xc0a81400 jt 16 jf 17 (008) jeq #0x806 jt 10 jf 9 (009) jeq #0x8035 jt 10 jf 17 (010) ld [28] (011) and #0xffffff00 (012) jeq #0xc0a81400 jt 16 jf 13 (013) ld [38] (014) and #0xffffff00 (015) jeq #0xc0a81400 jt 16 jf 17 (016) ret #65535 (017) ret #0 Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@infradead.org> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Hagen Paul Pfeifer <hagen@jauu.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-04-20 13:27:32 +04:00
}
#define SK_RUN_FILTER(FILTER, SKB) sk_run_filter(SKB, FILTER->insns)
#endif
static inline int bpf_tell_extensions(void)
{
net: filter: let bpf_tell_extensions return SKF_AD_MAX Michal Sekletar added in commit ea02f9411d9f ("net: introduce SO_BPF_EXTENSIONS") a facility where user space can enquire the BPF ancillary instruction set, which is imho a step into the right direction for letting user space high-level to BPF optimizers make an informed decision for possibly using these extensions. The original rationale was to return through a getsockopt(2) a bitfield of which instructions are supported and which are not, as of right now, we just return 0 to indicate a base support for SKF_AD_PROTOCOL up to SKF_AD_PAY_OFFSET. Limitations of this approach are that this API which we need to maintain for a long time can only support a maximum of 32 extensions, and needs to be additionally maintained/updated when each new extension that comes in. I thought about this a bit more and what we can do here to overcome this is to just return SKF_AD_MAX. Since we never remove any extension since we cannot break user space and always linearly increase SKF_AD_MAX on each newly added extension, user space can make a decision on what extensions are supported in the whole set of extensions and which aren't, by just checking which of them from the whole set have an offset < SKF_AD_MAX of the underlying kernel. Since SKF_AD_MAX must be updated each time we add new ones, we don't need to introduce an additional enum and got maintenance for free. At some point in time when SO_BPF_EXTENSIONS becomes ubiquitous for most kernels, then an application can simply make use of this and easily be run on newer or older underlying kernels without needing to be recompiled, of course. Since that is for 3.14, it's not too late to do this change. Cc: Michal Sekletar <msekleta@redhat.com> Cc: Eric Dumazet <edumazet@google.com> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Acked-by: Michal Sekletar <msekleta@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-21 03:19:37 +04:00
return SKF_AD_MAX;
}
net: filter: Just In Time compiler for x86-64 In order to speedup packet filtering, here is an implementation of a JIT compiler for x86_64 It is disabled by default, and must be enabled by the admin. echo 1 >/proc/sys/net/core/bpf_jit_enable It uses module_alloc() and module_free() to get memory in the 2GB text kernel range since we call helpers functions from the generated code. EAX : BPF A accumulator EBX : BPF X accumulator RDI : pointer to skb (first argument given to JIT function) RBP : frame pointer (even if CONFIG_FRAME_POINTER=n) r9d : skb->len - skb->data_len (headlen) r8 : skb->data To get a trace of generated code, use : echo 2 >/proc/sys/net/core/bpf_jit_enable Example of generated code : # tcpdump -p -n -s 0 -i eth1 host 192.168.20.0/24 flen=18 proglen=147 pass=3 image=ffffffffa00b5000 JIT code: ffffffffa00b5000: 55 48 89 e5 48 83 ec 60 48 89 5d f8 44 8b 4f 60 JIT code: ffffffffa00b5010: 44 2b 4f 64 4c 8b 87 b8 00 00 00 be 0c 00 00 00 JIT code: ffffffffa00b5020: e8 24 7b f7 e0 3d 00 08 00 00 75 28 be 1a 00 00 JIT code: ffffffffa00b5030: 00 e8 fe 7a f7 e0 24 00 3d 00 14 a8 c0 74 49 be JIT code: ffffffffa00b5040: 1e 00 00 00 e8 eb 7a f7 e0 24 00 3d 00 14 a8 c0 JIT code: ffffffffa00b5050: 74 36 eb 3b 3d 06 08 00 00 74 07 3d 35 80 00 00 JIT code: ffffffffa00b5060: 75 2d be 1c 00 00 00 e8 c8 7a f7 e0 24 00 3d 00 JIT code: ffffffffa00b5070: 14 a8 c0 74 13 be 26 00 00 00 e8 b5 7a f7 e0 24 JIT code: ffffffffa00b5080: 00 3d 00 14 a8 c0 75 07 b8 ff ff 00 00 eb 02 31 JIT code: ffffffffa00b5090: c0 c9 c3 BPF program is 144 bytes long, so native program is almost same size ;) (000) ldh [12] (001) jeq #0x800 jt 2 jf 8 (002) ld [26] (003) and #0xffffff00 (004) jeq #0xc0a81400 jt 16 jf 5 (005) ld [30] (006) and #0xffffff00 (007) jeq #0xc0a81400 jt 16 jf 17 (008) jeq #0x806 jt 10 jf 9 (009) jeq #0x8035 jt 10 jf 17 (010) ld [28] (011) and #0xffffff00 (012) jeq #0xc0a81400 jt 16 jf 13 (013) ld [38] (014) and #0xffffff00 (015) jeq #0xc0a81400 jt 16 jf 17 (016) ret #65535 (017) ret #0 Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@infradead.org> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Hagen Paul Pfeifer <hagen@jauu.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-04-20 13:27:32 +04:00
enum {
BPF_S_RET_K = 1,
BPF_S_RET_A,
BPF_S_ALU_ADD_K,
BPF_S_ALU_ADD_X,
BPF_S_ALU_SUB_K,
BPF_S_ALU_SUB_X,
BPF_S_ALU_MUL_K,
BPF_S_ALU_MUL_X,
BPF_S_ALU_DIV_X,
BPF_S_ALU_MOD_K,
BPF_S_ALU_MOD_X,
net: filter: Just In Time compiler for x86-64 In order to speedup packet filtering, here is an implementation of a JIT compiler for x86_64 It is disabled by default, and must be enabled by the admin. echo 1 >/proc/sys/net/core/bpf_jit_enable It uses module_alloc() and module_free() to get memory in the 2GB text kernel range since we call helpers functions from the generated code. EAX : BPF A accumulator EBX : BPF X accumulator RDI : pointer to skb (first argument given to JIT function) RBP : frame pointer (even if CONFIG_FRAME_POINTER=n) r9d : skb->len - skb->data_len (headlen) r8 : skb->data To get a trace of generated code, use : echo 2 >/proc/sys/net/core/bpf_jit_enable Example of generated code : # tcpdump -p -n -s 0 -i eth1 host 192.168.20.0/24 flen=18 proglen=147 pass=3 image=ffffffffa00b5000 JIT code: ffffffffa00b5000: 55 48 89 e5 48 83 ec 60 48 89 5d f8 44 8b 4f 60 JIT code: ffffffffa00b5010: 44 2b 4f 64 4c 8b 87 b8 00 00 00 be 0c 00 00 00 JIT code: ffffffffa00b5020: e8 24 7b f7 e0 3d 00 08 00 00 75 28 be 1a 00 00 JIT code: ffffffffa00b5030: 00 e8 fe 7a f7 e0 24 00 3d 00 14 a8 c0 74 49 be JIT code: ffffffffa00b5040: 1e 00 00 00 e8 eb 7a f7 e0 24 00 3d 00 14 a8 c0 JIT code: ffffffffa00b5050: 74 36 eb 3b 3d 06 08 00 00 74 07 3d 35 80 00 00 JIT code: ffffffffa00b5060: 75 2d be 1c 00 00 00 e8 c8 7a f7 e0 24 00 3d 00 JIT code: ffffffffa00b5070: 14 a8 c0 74 13 be 26 00 00 00 e8 b5 7a f7 e0 24 JIT code: ffffffffa00b5080: 00 3d 00 14 a8 c0 75 07 b8 ff ff 00 00 eb 02 31 JIT code: ffffffffa00b5090: c0 c9 c3 BPF program is 144 bytes long, so native program is almost same size ;) (000) ldh [12] (001) jeq #0x800 jt 2 jf 8 (002) ld [26] (003) and #0xffffff00 (004) jeq #0xc0a81400 jt 16 jf 5 (005) ld [30] (006) and #0xffffff00 (007) jeq #0xc0a81400 jt 16 jf 17 (008) jeq #0x806 jt 10 jf 9 (009) jeq #0x8035 jt 10 jf 17 (010) ld [28] (011) and #0xffffff00 (012) jeq #0xc0a81400 jt 16 jf 13 (013) ld [38] (014) and #0xffffff00 (015) jeq #0xc0a81400 jt 16 jf 17 (016) ret #65535 (017) ret #0 Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@infradead.org> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Hagen Paul Pfeifer <hagen@jauu.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-04-20 13:27:32 +04:00
BPF_S_ALU_AND_K,
BPF_S_ALU_AND_X,
BPF_S_ALU_OR_K,
BPF_S_ALU_OR_X,
BPF_S_ALU_XOR_K,
BPF_S_ALU_XOR_X,
net: filter: Just In Time compiler for x86-64 In order to speedup packet filtering, here is an implementation of a JIT compiler for x86_64 It is disabled by default, and must be enabled by the admin. echo 1 >/proc/sys/net/core/bpf_jit_enable It uses module_alloc() and module_free() to get memory in the 2GB text kernel range since we call helpers functions from the generated code. EAX : BPF A accumulator EBX : BPF X accumulator RDI : pointer to skb (first argument given to JIT function) RBP : frame pointer (even if CONFIG_FRAME_POINTER=n) r9d : skb->len - skb->data_len (headlen) r8 : skb->data To get a trace of generated code, use : echo 2 >/proc/sys/net/core/bpf_jit_enable Example of generated code : # tcpdump -p -n -s 0 -i eth1 host 192.168.20.0/24 flen=18 proglen=147 pass=3 image=ffffffffa00b5000 JIT code: ffffffffa00b5000: 55 48 89 e5 48 83 ec 60 48 89 5d f8 44 8b 4f 60 JIT code: ffffffffa00b5010: 44 2b 4f 64 4c 8b 87 b8 00 00 00 be 0c 00 00 00 JIT code: ffffffffa00b5020: e8 24 7b f7 e0 3d 00 08 00 00 75 28 be 1a 00 00 JIT code: ffffffffa00b5030: 00 e8 fe 7a f7 e0 24 00 3d 00 14 a8 c0 74 49 be JIT code: ffffffffa00b5040: 1e 00 00 00 e8 eb 7a f7 e0 24 00 3d 00 14 a8 c0 JIT code: ffffffffa00b5050: 74 36 eb 3b 3d 06 08 00 00 74 07 3d 35 80 00 00 JIT code: ffffffffa00b5060: 75 2d be 1c 00 00 00 e8 c8 7a f7 e0 24 00 3d 00 JIT code: ffffffffa00b5070: 14 a8 c0 74 13 be 26 00 00 00 e8 b5 7a f7 e0 24 JIT code: ffffffffa00b5080: 00 3d 00 14 a8 c0 75 07 b8 ff ff 00 00 eb 02 31 JIT code: ffffffffa00b5090: c0 c9 c3 BPF program is 144 bytes long, so native program is almost same size ;) (000) ldh [12] (001) jeq #0x800 jt 2 jf 8 (002) ld [26] (003) and #0xffffff00 (004) jeq #0xc0a81400 jt 16 jf 5 (005) ld [30] (006) and #0xffffff00 (007) jeq #0xc0a81400 jt 16 jf 17 (008) jeq #0x806 jt 10 jf 9 (009) jeq #0x8035 jt 10 jf 17 (010) ld [28] (011) and #0xffffff00 (012) jeq #0xc0a81400 jt 16 jf 13 (013) ld [38] (014) and #0xffffff00 (015) jeq #0xc0a81400 jt 16 jf 17 (016) ret #65535 (017) ret #0 Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@infradead.org> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Hagen Paul Pfeifer <hagen@jauu.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-04-20 13:27:32 +04:00
BPF_S_ALU_LSH_K,
BPF_S_ALU_LSH_X,
BPF_S_ALU_RSH_K,
BPF_S_ALU_RSH_X,
BPF_S_ALU_NEG,
BPF_S_LD_W_ABS,
BPF_S_LD_H_ABS,
BPF_S_LD_B_ABS,
BPF_S_LD_W_LEN,
BPF_S_LD_W_IND,
BPF_S_LD_H_IND,
BPF_S_LD_B_IND,
BPF_S_LD_IMM,
BPF_S_LDX_W_LEN,
BPF_S_LDX_B_MSH,
BPF_S_LDX_IMM,
BPF_S_MISC_TAX,
BPF_S_MISC_TXA,
BPF_S_ALU_DIV_K,
BPF_S_LD_MEM,
BPF_S_LDX_MEM,
BPF_S_ST,
BPF_S_STX,
BPF_S_JMP_JA,
BPF_S_JMP_JEQ_K,
BPF_S_JMP_JEQ_X,
BPF_S_JMP_JGE_K,
BPF_S_JMP_JGE_X,
BPF_S_JMP_JGT_K,
BPF_S_JMP_JGT_X,
BPF_S_JMP_JSET_K,
BPF_S_JMP_JSET_X,
/* Ancillary data */
BPF_S_ANC_PROTOCOL,
BPF_S_ANC_PKTTYPE,
BPF_S_ANC_IFINDEX,
BPF_S_ANC_NLATTR,
BPF_S_ANC_NLATTR_NEST,
BPF_S_ANC_MARK,
BPF_S_ANC_QUEUE,
BPF_S_ANC_HATYPE,
BPF_S_ANC_RXHASH,
BPF_S_ANC_CPU,
BPF_S_ANC_ALU_XOR_X,
BPF_S_ANC_SECCOMP_LD_W,
BPF_S_ANC_VLAN_TAG,
BPF_S_ANC_VLAN_TAG_PRESENT,
BPF_S_ANC_PAY_OFFSET,
net: filter: Just In Time compiler for x86-64 In order to speedup packet filtering, here is an implementation of a JIT compiler for x86_64 It is disabled by default, and must be enabled by the admin. echo 1 >/proc/sys/net/core/bpf_jit_enable It uses module_alloc() and module_free() to get memory in the 2GB text kernel range since we call helpers functions from the generated code. EAX : BPF A accumulator EBX : BPF X accumulator RDI : pointer to skb (first argument given to JIT function) RBP : frame pointer (even if CONFIG_FRAME_POINTER=n) r9d : skb->len - skb->data_len (headlen) r8 : skb->data To get a trace of generated code, use : echo 2 >/proc/sys/net/core/bpf_jit_enable Example of generated code : # tcpdump -p -n -s 0 -i eth1 host 192.168.20.0/24 flen=18 proglen=147 pass=3 image=ffffffffa00b5000 JIT code: ffffffffa00b5000: 55 48 89 e5 48 83 ec 60 48 89 5d f8 44 8b 4f 60 JIT code: ffffffffa00b5010: 44 2b 4f 64 4c 8b 87 b8 00 00 00 be 0c 00 00 00 JIT code: ffffffffa00b5020: e8 24 7b f7 e0 3d 00 08 00 00 75 28 be 1a 00 00 JIT code: ffffffffa00b5030: 00 e8 fe 7a f7 e0 24 00 3d 00 14 a8 c0 74 49 be JIT code: ffffffffa00b5040: 1e 00 00 00 e8 eb 7a f7 e0 24 00 3d 00 14 a8 c0 JIT code: ffffffffa00b5050: 74 36 eb 3b 3d 06 08 00 00 74 07 3d 35 80 00 00 JIT code: ffffffffa00b5060: 75 2d be 1c 00 00 00 e8 c8 7a f7 e0 24 00 3d 00 JIT code: ffffffffa00b5070: 14 a8 c0 74 13 be 26 00 00 00 e8 b5 7a f7 e0 24 JIT code: ffffffffa00b5080: 00 3d 00 14 a8 c0 75 07 b8 ff ff 00 00 eb 02 31 JIT code: ffffffffa00b5090: c0 c9 c3 BPF program is 144 bytes long, so native program is almost same size ;) (000) ldh [12] (001) jeq #0x800 jt 2 jf 8 (002) ld [26] (003) and #0xffffff00 (004) jeq #0xc0a81400 jt 16 jf 5 (005) ld [30] (006) and #0xffffff00 (007) jeq #0xc0a81400 jt 16 jf 17 (008) jeq #0x806 jt 10 jf 9 (009) jeq #0x8035 jt 10 jf 17 (010) ld [28] (011) and #0xffffff00 (012) jeq #0xc0a81400 jt 16 jf 13 (013) ld [38] (014) and #0xffffff00 (015) jeq #0xc0a81400 jt 16 jf 17 (016) ret #65535 (017) ret #0 Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@infradead.org> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Hagen Paul Pfeifer <hagen@jauu.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-04-20 13:27:32 +04:00
};
#endif /* __LINUX_FILTER_H__ */