Skip to content

R
raspberrypi-kernel

openeuler / raspberrypi-kernel

通知 13
Star 1
Fork 0
R
raspberrypi-kernel
切换分支/标签
  1. 16 5月, 2014 2 次提交
    • A
      net: filter: x86: internal BPF JIT · 62258278
      由 Alexei Starovoitov 提交于 
      Maps all internal BPF instructions into x86_64 instructions.
This patch replaces original BPF x64 JIT with internal BPF x64 JIT.
sysctl net.core.bpf_jit_enable is reused as on/off switch.

Performance:

1. old BPF JIT and internal BPF JIT generate equivalent x86_64 code.
  No performance difference is observed for filters that were JIT-able before

Example assembler code for BPF filter "tcpdump port 22"

original BPF -> old JIT:            original BPF -> internal BPF -> new JIT:
   0:   push   %rbp                      0:     push   %rbp
   1:   mov    %rsp,%rbp                 1:     mov    %rsp,%rbp
   4:   sub    $0x60,%rsp                4:     sub    $0x228,%rsp
   8:   mov    %rbx,-0x8(%rbp)           b:     mov    %rbx,-0x228(%rbp) // prologue
                                        12:     mov    %r13,-0x220(%rbp)
                                        19:     mov    %r14,-0x218(%rbp)
                                        20:     mov    %r15,-0x210(%rbp)
                                        27:     xor    %eax,%eax         // clear A
   c:   xor    %ebx,%ebx                29:     xor    %r13,%r13         // clear X
   e:   mov    0x68(%rdi),%r9d          2c:     mov    0x68(%rdi),%r9d
  12:   sub    0x6c(%rdi),%r9d          30:     sub    0x6c(%rdi),%r9d
  16:   mov    0xd8(%rdi),%r8           34:     mov    0xd8(%rdi),%r10
                                        3b:     mov    %rdi,%rbx
  1d:   mov    $0xc,%esi                3e:     mov    $0xc,%esi
  22:   callq  0xffffffffe1021e15       43:     callq  0xffffffffe102bd75
  27:   cmp    $0x86dd,%eax             48:     cmp    $0x86dd,%rax
  2c:   jne    0x0000000000000069       4f:     jne    0x000000000000009a
  2e:   mov    $0x14,%esi               51:     mov    $0x14,%esi
  33:   callq  0xffffffffe1021e31       56:     callq  0xffffffffe102bd91
  38:   cmp    $0x84,%eax               5b:     cmp    $0x84,%rax
  3d:   je     0x0000000000000049       62:     je     0x0000000000000074
  3f:   cmp    $0x6,%eax                64:     cmp    $0x6,%rax
  42:   je     0x0000000000000049       68:     je     0x0000000000000074
  44:   cmp    $0x11,%eax               6a:     cmp    $0x11,%rax
  47:   jne    0x00000000000000c6       6e:     jne    0x0000000000000117
  49:   mov    $0x36,%esi               74:     mov    $0x36,%esi
  4e:   callq  0xffffffffe1021e15       79:     callq  0xffffffffe102bd75
  53:   cmp    $0x16,%eax               7e:     cmp    $0x16,%rax
  56:   je     0x00000000000000bf       82:     je     0x0000000000000110
  58:   mov    $0x38,%esi               88:     mov    $0x38,%esi
  5d:   callq  0xffffffffe1021e15       8d:     callq  0xffffffffe102bd75
  62:   cmp    $0x16,%eax               92:     cmp    $0x16,%rax
  65:   je     0x00000000000000bf       96:     je     0x0000000000000110
  67:   jmp    0x00000000000000c6       98:     jmp    0x0000000000000117
  69:   cmp    $0x800,%eax              9a:     cmp    $0x800,%rax
  6e:   jne    0x00000000000000c6       a1:     jne    0x0000000000000117
  70:   mov    $0x17,%esi               a3:     mov    $0x17,%esi
  75:   callq  0xffffffffe1021e31       a8:     callq  0xffffffffe102bd91
  7a:   cmp    $0x84,%eax               ad:     cmp    $0x84,%rax
  7f:   je     0x000000000000008b       b4:     je     0x00000000000000c2
  81:   cmp    $0x6,%eax                b6:     cmp    $0x6,%rax
  84:   je     0x000000000000008b       ba:     je     0x00000000000000c2
  86:   cmp    $0x11,%eax               bc:     cmp    $0x11,%rax
  89:   jne    0x00000000000000c6       c0:     jne    0x0000000000000117
  8b:   mov    $0x14,%esi               c2:     mov    $0x14,%esi
  90:   callq  0xffffffffe1021e15       c7:     callq  0xffffffffe102bd75
  95:   test   $0x1fff,%ax              cc:     test   $0x1fff,%rax
  99:   jne    0x00000000000000c6       d3:     jne    0x0000000000000117
                                        d5:     mov    %rax,%r14
  9b:   mov    $0xe,%esi                d8:     mov    $0xe,%esi
  a0:   callq  0xffffffffe1021e44       dd:     callq  0xffffffffe102bd91 // MSH
                                        e2:     and    $0xf,%eax
                                        e5:     shl    $0x2,%eax
                                        e8:     mov    %rax,%r13
                                        eb:     mov    %r14,%rax
                                        ee:     mov    %r13,%rsi
  a5:   lea    0xe(%rbx),%esi           f1:     add    $0xe,%esi
  a8:   callq  0xffffffffe1021e0d       f4:     callq  0xffffffffe102bd6d
  ad:   cmp    $0x16,%eax               f9:     cmp    $0x16,%rax
  b0:   je     0x00000000000000bf       fd:     je     0x0000000000000110
                                        ff:     mov    %r13,%rsi
  b2:   lea    0x10(%rbx),%esi         102:     add    $0x10,%esi
  b5:   callq  0xffffffffe1021e0d      105:     callq  0xffffffffe102bd6d
  ba:   cmp    $0x16,%eax              10a:     cmp    $0x16,%rax
  bd:   jne    0x00000000000000c6      10e:     jne    0x0000000000000117
  bf:   mov    $0xffff,%eax            110:     mov    $0xffff,%eax
  c4:   jmp    0x00000000000000c8      115:     jmp    0x000000000000011c
  c6:   xor    %eax,%eax               117:     mov    $0x0,%eax
  c8:   mov    -0x8(%rbp),%rbx         11c:     mov    -0x228(%rbp),%rbx // epilogue
  cc:   leaveq                         123:     mov    -0x220(%rbp),%r13
  cd:   retq                           12a:     mov    -0x218(%rbp),%r14
                                       131:     mov    -0x210(%rbp),%r15
                                       138:     leaveq
                                       139:     retq

On fully cached SKBs both JITed functions take 12 nsec to execute.
BPF interpreter executes the program in 30 nsec.

The difference in generated assembler is due to the following:

Old BPF imlements LDX_MSH instruction via sk_load_byte_msh() helper function
inside bpf_jit.S.
New JIT removes the helper and does it explicitly, so ldx_msh cost
is the same for both JITs, but generated code looks longer.

New JIT has 4 registers to save, so prologue/epilogue are larger,
but the cost is within noise on x64.

Old JIT checks whether first insn clears A and if not emits 'xor %eax,%eax'.
New JIT clears %rax unconditionally.

2. old BPF JIT doesn't support ANC_NLATTR, ANC_PAY_OFFSET, ANC_RANDOM
  extensions. New JIT supports all BPF extensions.
  Performance of such filters improves 2-4 times depending on a filter.
  The longer the filter the higher performance gain.
  Synthetic benchmarks with many ancillary loads see 20x speedup
  which seems to be the maximum gain from JIT

Notes:

. net.core.bpf_jit_enable=2 + tools/net/bpf_jit_disasm is still functional
  and can be used to see generated assembler

. there are two jit_compile() functions and code flow for classic filters is:
  sk_attach_filter() - load classic BPF
  bpf_jit_compile() - try to JIT from classic BPF
  sk_convert_filter() - convert classic to internal
  bpf_int_jit_compile() - JIT from internal BPF

  seccomp and tracing filters will just call bpf_int_jit_compile()
Signed-off-by: NAlexei Starovoitov <ast@plumgrid.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      62258278
    • A
      net: filter: x86: split bpf_jit_compile() · f3c2af7b
      由 Alexei Starovoitov 提交于 
      Split bpf_jit_compile() into two functions to improve readability
of for(pass++) loop. The change follows similar style of JIT compilers
for arm, powerpc, s390

The body of new do_jit() was not reformatted to reduce noise
in this patch, since the following patch replaces most of it.

Tested with BPF testsuite.
Signed-off-by: NAlexei Starovoitov <ast@plumgrid.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      f3c2af7b
  3. 14 5月, 2014 1 次提交
    • A
      net: filter: x86: fix JIT address randomization · 773cd38f
      由 Alexei Starovoitov 提交于 
      bpf_alloc_binary() adds 128 bytes of room to JITed program image
and rounds it up to the nearest page size. If image size is close
to page size (like 4000), it is rounded to two pages:
round_up(4000 + 4 + 128) == 8192
then 'hole' is computed as 8192 - (4000 + 4) = 4188
If prandom_u32() % hole selects a number >= PAGE_SIZE - sizeof(*header)
then kernel will crash during bpf_jit_free():

kernel BUG at arch/x86/mm/pageattr.c:887!
Call Trace:
 [<ffffffff81037285>] change_page_attr_set_clr+0x135/0x460
 [<ffffffff81694cc0>] ? _raw_spin_unlock_irq+0x30/0x50
 [<ffffffff810378ff>] set_memory_rw+0x2f/0x40
 [<ffffffffa01a0d8d>] bpf_jit_free_deferred+0x2d/0x60
 [<ffffffff8106bf98>] process_one_work+0x1d8/0x6a0
 [<ffffffff8106bf38>] ? process_one_work+0x178/0x6a0
 [<ffffffff8106c90c>] worker_thread+0x11c/0x370

since bpf_jit_free() does:
  unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK;
  struct bpf_binary_header *header = (void *)addr;
to compute start address of 'bpf_binary_header'
and header->pages will pass junk to:
  set_memory_rw(addr, header->pages);

Fix it by making sure that &header->image[prandom_u32() % hole] and &header
are in the same page

Fixes: 314beb9b ("x86: bpf_jit_comp: secure bpf jit against spraying attacks")
Signed-off-by: NAlexei Starovoitov <ast@plumgrid.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      773cd38f
  5. 31 3月, 2014 1 次提交
    • D
      net: filter: add jited flag to indicate jit compiled filters · f8bbbfc3
      由 Daniel Borkmann 提交于 
      This patch adds a jited flag into sk_filter struct in order to indicate
whether a filter is currently jited or not. The size of sk_filter is
not being expanded as the 32 bit 'len' member allows upper bits to be
reused since a filter can currently only grow as large as BPF_MAXINSNS.

Therefore, there's enough room also for other in future needed flags to
reuse 'len' field if necessary. The jited flag also allows for having
alternative interpreter functions running as currently, we can only
detect jit compiled filters by testing fp->bpf_func to not equal the
address of sk_run_filter().

Joint work with Alexei Starovoitov.
Signed-off-by: NAlexei Starovoitov <ast@plumgrid.com>
Signed-off-by: NDaniel Borkmann <dborkman@redhat.com>
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      f8bbbfc3
  7. 27 3月, 2014 1 次提交
  9. 16 1月, 2014 1 次提交
  11. 08 11月, 2013 1 次提交
    • A
      net: x86: bpf: don't forget to free sk_filter (v2) · 98bbc06a
      由 Andrey Vagin 提交于 
      sk_filter isn't freed if bpf_func is equal to sk_run_filter.

This memory leak was introduced by v3.12-rc3-224-gd45ed4a4
"net: fix unsafe set_memory_rw from softirq".

Before this patch sk_filter was freed in sk_filter_release_rcu,
now it should be freed in bpf_jit_free.

Here is output of kmemleak:
unreferenced object 0xffff8800b774eab0 (size 128):
  comm "systemd", pid 1, jiffies 4294669014 (age 124.062s)
  hex dump (first 32 bytes):
    00 00 00 00 0b 00 00 00 20 63 7f b7 00 88 ff ff  ........ c......
    60 d4 55 81 ff ff ff ff 30 d9 55 81 ff ff ff ff  `.U.....0.U.....
  backtrace:
    [<ffffffff816444be>] kmemleak_alloc+0x4e/0xb0
    [<ffffffff811845af>] __kmalloc+0xef/0x260
    [<ffffffff81534028>] sock_kmalloc+0x38/0x60
    [<ffffffff8155d4dd>] sk_attach_filter+0x5d/0x190
    [<ffffffff815378a1>] sock_setsockopt+0x991/0x9e0
    [<ffffffff81531bd6>] SyS_setsockopt+0xb6/0xd0
    [<ffffffff8165f3e9>] system_call_fastpath+0x16/0x1b
    [<ffffffffffffffff>] 0xffffffffffffffff

v2: add extra { } after else

Fixes: d45ed4a4 ("net: fix unsafe set_memory_rw from softirq")
Acked-by: NDaniel Borkmann <dborkman@redhat.com>
Cc: Alexei Starovoitov <ast@plumgrid.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: NAndrey Vagin <avagin@openvz.org>
Acked-by: NAlexei Starovoitov <ast@plumgrid.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      98bbc06a
  13. 08 10月, 2013 1 次提交
    • A
      net: fix unsafe set_memory_rw from softirq · d45ed4a4
      由 Alexei Starovoitov 提交于 
      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: NAlexei Starovoitov <ast@plumgrid.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      d45ed4a4
  15. 20 5月, 2013 1 次提交
  17. 18 5月, 2013 1 次提交
  19. 22 3月, 2013 1 次提交
    • D
      filter: bpf_jit_comp: refactor and unify BPF JIT image dump output · 79617801
      由 Daniel Borkmann 提交于 
      If bpf_jit_enable > 1, then we dump the emitted JIT compiled image
after creation. Currently, only SPARC and PowerPC has similar output
as in the reference implementation on x86_64. Make a small helper
function in order to reduce duplicated code and make the dump output
uniform across architectures x86_64, SPARC, PPC, ARM (e.g. on ARM
flen, pass and proglen are currently not shown, but would be
interesting to know as well), also for future BPF JIT implementations
on other archs.

Cc: Mircea Gherzan <mgherzan@gmail.com>
Cc: Matt Evans <matt@ozlabs.org>
Cc: Eric Dumazet <eric.dumazet@google.com>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: NDaniel Borkmann <dborkman@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      79617801
  21. 31 1月, 2013 1 次提交
  23. 01 11月, 2012 1 次提交
  25. 25 9月, 2012 1 次提交
  27. 11 9月, 2012 1 次提交
  29. 07 6月, 2012 1 次提交
  31. 04 4月, 2012 1 次提交
  33. 30 3月, 2012 1 次提交
  35. 20 3月, 2012 1 次提交
  37. 19 1月, 2012 1 次提交
    • E
      net: bpf_jit: fix divide by 0 generation · d00a9dd2
      由 Eric Dumazet 提交于 
      Several problems fixed in this patch :

1) Target of the conditional jump in case a divide by 0 is performed
   by a bpf is wrong.

2) Must 'generate' the full function prologue/epilogue at pass=0,
   or else we can stop too early in pass=1 if the proglen doesnt change.
   (if the increase of prologue/epilogue equals decrease of all
    instructions length because some jumps are converted to near jumps)

3) Change the wrong length detection at the end of code generation to
   issue a more explicit message, no need for a full stack trace.
Reported-by: NPhil Oester <kernel@linuxace.com>
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      d00a9dd2
  39. 20 12月, 2011 1 次提交
  41. 28 4月, 2011 1 次提交
    • E
      net: filter: Just In Time compiler for x86-64 · 0a14842f
      由 Eric Dumazet 提交于 
      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: NEric 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: NDavid S. Miller <davem@davemloft.net>
      0a14842f