mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-16 00:34:20 +08:00
cd6362befe
14 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Alexei Starovoitov
|
bd4cf0ed33 |
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 <ast@plumgrid.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Cc: Hagen Paul Pfeifer <hagen@jauu.net>
Cc: Kees Cook <keescook@chromium.org>
Cc: Paul Moore <pmoore@redhat.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: H. Peter Anvin <hpa@linux.intel.com>
Cc: linux-kernel@vger.kernel.org
Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
||
Nicolas Schichan
|
d13274794a |
seccomp: allow BPF_XOR based ALU instructions.
Allow BPF_XOR based ALU instructions. Signed-off-by: Nicolas Schichan <nschichan@freebox.fr> Acked-by: Kees Cook <keescook@chromium.org> Acked-by: Will Drewry <wad@chromium.org> Signed-off-by: James Morris <james.l.morris@oracle.com> |
||
Andy Lutomirski
|
87b526d349 |
seccomp: Make syscall skipping and nr changes more consistent
This fixes two issues that could cause incompatibility between kernel versions: - If a tracer uses SECCOMP_RET_TRACE to select a syscall number higher than the largest known syscall, emulate the unknown vsyscall by returning -ENOSYS. (This is unlikely to make a noticeable difference on x86-64 due to the way the system call entry works.) - On x86-64 with vsyscall=emulate, skipped vsyscalls were buggy. This updates the documentation accordingly. Signed-off-by: Andy Lutomirski <luto@amacapital.net> Acked-by: Will Drewry <wad@chromium.org> Signed-off-by: James Morris <james.l.morris@oracle.com> |
||
Will Drewry
|
8156b451f3 |
seccomp: fix build warnings when there is no CONFIG_SECCOMP_FILTER
If both audit and seccomp filter support are disabled, 'ret' is marked as unused. If just seccomp filter support is disabled, data and skip are considered unused. This change fixes those build warnings. Reported-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Will Drewry <wad@chromium.org> Acked-by: Kees Cook <keescook@chromium.org> Signed-off-by: James Morris <james.l.morris@oracle.com> |
||
|
Will Drewry
|
fb0fadf9b2 |
ptrace,seccomp: Add PTRACE_SECCOMP support
This change adds support for a new ptrace option, PTRACE_O_TRACESECCOMP,
and a new return value for seccomp BPF programs, SECCOMP_RET_TRACE.
When a tracer specifies the PTRACE_O_TRACESECCOMP ptrace option, the
tracer will be notified, via PTRACE_EVENT_SECCOMP, for any syscall that
results in a BPF program returning SECCOMP_RET_TRACE. The 16-bit
SECCOMP_RET_DATA mask of the BPF program return value will be passed as
the ptrace_message and may be retrieved using PTRACE_GETEVENTMSG.
If the subordinate process is not using seccomp filter, then no
system call notifications will occur even if the option is specified.
If there is no tracer with PTRACE_O_TRACESECCOMP when SECCOMP_RET_TRACE
is returned, the system call will not be executed and an -ENOSYS errno
will be returned to userspace.
This change adds a dependency on the system call slow path. Any future
efforts to use the system call fast path for seccomp filter will need to
address this restriction.
Signed-off-by: Will Drewry <wad@chromium.org>
Acked-by: Eric Paris <eparis@redhat.com>
v18: - rebase
- comment fatal_signal check
- acked-by
- drop secure_computing_int comment
v17: - ...
v16: - update PT_TRACE_MASK to 0xbf4 so that STOP isn't clear on SETOPTIONS call (indan@nul.nu)
[note PT_TRACE_MASK disappears in linux-next]
v15: - add audit support for non-zero return codes
- clean up style (indan@nul.nu)
v14: - rebase/nochanges
v13: - rebase on to
|
||
|
Will Drewry
|
bb6ea4301a |
seccomp: Add SECCOMP_RET_TRAP
Adds a new return value to seccomp filters that triggers a SIGSYS to be
delivered with the new SYS_SECCOMP si_code.
This allows in-process system call emulation, including just specifying
an errno or cleanly dumping core, rather than just dying.
Suggested-by: Markus Gutschke <markus@chromium.org>
Suggested-by: Julien Tinnes <jln@chromium.org>
Signed-off-by: Will Drewry <wad@chromium.org>
Acked-by: Eric Paris <eparis@redhat.com>
v18: - acked-by, rebase
- don't mention secure_computing_int() anymore
v15: - use audit_seccomp/skip
- pad out error spacing; clean up switch (indan@nul.nu)
v14: - n/a
v13: - rebase on to
|
||
|
Will Drewry
|
acf3b2c71e |
seccomp: add SECCOMP_RET_ERRNO
This change adds the SECCOMP_RET_ERRNO as a valid return value from a
seccomp filter. Additionally, it makes the first use of the lower
16-bits for storing a filter-supplied errno. 16-bits is more than
enough for the errno-base.h calls.
Returning errors instead of immediately terminating processes that
violate seccomp policy allow for broader use of this functionality
for kernel attack surface reduction. For example, a linux container
could maintain a whitelist of pre-existing system calls but drop
all new ones with errnos. This would keep a logically static attack
surface while providing errnos that may allow for graceful failure
without the downside of do_exit() on a bad call.
This change also changes the signature of __secure_computing. It
appears the only direct caller is the arm entry code and it clobbers
any possible return value (register) immediately.
Signed-off-by: Will Drewry <wad@chromium.org>
Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Eric Paris <eparis@redhat.com>
v18: - fix up comments and rebase
- fix bad var name which was fixed in later revs
- remove _int() and just change the __secure_computing signature
v16-v17: ...
v15: - use audit_seccomp and add a skip label. (eparis@redhat.com)
- clean up and pad out return codes (indan@nul.nu)
v14: - no change/rebase
v13: - rebase on to
|
||
Kees Cook
|
3dc1c1b2d2 |
seccomp: remove duplicated failure logging
This consolidates the seccomp filter error logging path and adds more details to the audit log. Signed-off-by: Will Drewry <wad@chromium.org> Signed-off-by: Kees Cook <keescook@chromium.org> Acked-by: Eric Paris <eparis@redhat.com> v18: make compat= permanent in the record v15: added a return code to the audit_seccomp path by wad@chromium.org (suggested by eparis@redhat.com) v*: original by keescook@chromium.org Signed-off-by: James Morris <james.l.morris@oracle.com> |
||
|
Will Drewry
|
e2cfabdfd0 |
seccomp: add system call filtering using BPF
[This patch depends on luto@mit.edu's no_new_privs patch:
https://lkml.org/lkml/2012/1/30/264
The whole series including Andrew's patches can be found here:
https://github.com/redpig/linux/tree/seccomp
Complete diff here:
https://github.com/redpig/linux/compare/1dc65fed...seccomp
]
This patch adds support for seccomp mode 2. Mode 2 introduces the
ability for unprivileged processes to install system call filtering
policy expressed in terms of a Berkeley Packet Filter (BPF) program.
This program will be evaluated in the kernel for each system call
the task makes and computes a result based on data in the format
of struct seccomp_data.
A filter program may be installed by calling:
struct sock_fprog fprog = { ... };
...
prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &fprog);
The return value of the filter program determines if the system call is
allowed to proceed or denied. If the first filter program installed
allows prctl(2) calls, then the above call may be made repeatedly
by a task to further reduce its access to the kernel. All attached
programs must be evaluated before a system call will be allowed to
proceed.
Filter programs will be inherited across fork/clone and execve.
However, if the task attaching the filter is unprivileged
(!CAP_SYS_ADMIN) the no_new_privs bit will be set on the task. This
ensures that unprivileged tasks cannot attach filters that affect
privileged tasks (e.g., setuid binary).
There are a number of benefits to this approach. A few of which are
as follows:
- BPF has been exposed to userland for a long time
- BPF optimization (and JIT'ing) are well understood
- Userland already knows its ABI: system call numbers and desired
arguments
- No time-of-check-time-of-use vulnerable data accesses are possible.
- system call arguments are loaded on access only to minimize copying
required for system call policy decisions.
Mode 2 support is restricted to architectures that enable
HAVE_ARCH_SECCOMP_FILTER. In this patch, the primary dependency is on
syscall_get_arguments(). The full desired scope of this feature will
add a few minor additional requirements expressed later in this series.
Based on discussion, SECCOMP_RET_ERRNO and SECCOMP_RET_TRACE seem to be
the desired additional functionality.
No architectures are enabled in this patch.
Signed-off-by: Will Drewry <wad@chromium.org>
Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Reviewed-by: Indan Zupancic <indan@nul.nu>
Acked-by: Eric Paris <eparis@redhat.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
v18: - rebase to v3.4-rc2
- s/chk/check/ (akpm@linux-foundation.org,jmorris@namei.org)
- allocate with GFP_KERNEL|__GFP_NOWARN (indan@nul.nu)
- add a comment for get_u32 regarding endianness (akpm@)
- fix other typos, style mistakes (akpm@)
- added acked-by
v17: - properly guard seccomp filter needed headers (leann@ubuntu.com)
- tighten return mask to 0x7fff0000
v16: - no change
v15: - add a 4 instr penalty when counting a path to account for seccomp_filter
size (indan@nul.nu)
- drop the max insns to 256KB (indan@nul.nu)
- return ENOMEM if the max insns limit has been hit (indan@nul.nu)
- move IP checks after args (indan@nul.nu)
- drop !user_filter check (indan@nul.nu)
- only allow explicit bpf codes (indan@nul.nu)
- exit_code -> exit_sig
v14: - put/get_seccomp_filter takes struct task_struct
(indan@nul.nu,keescook@chromium.org)
- adds seccomp_chk_filter and drops general bpf_run/chk_filter user
- add seccomp_bpf_load for use by net/core/filter.c
- lower max per-process/per-hierarchy: 1MB
- moved nnp/capability check prior to allocation
(all of the above: indan@nul.nu)
v13: - rebase on to
|
||
Eric Paris
|
85e7bac33b |
seccomp: audit abnormal end to a process due to seccomp
The audit system likes to collect information about processes that end abnormally (SIGSEGV) as this may me useful intrusion detection information. This patch adds audit support to collect information when seccomp forces a task to exit because of misbehavior in a similar way. Signed-off-by: Eric Paris <eparis@redhat.com> |
||
Roland McGrath
|
5b1017404a |
x86-64: seccomp: fix 32/64 syscall hole
On x86-64, a 32-bit process (TIF_IA32) can switch to 64-bit mode with
ljmp, and then use the "syscall" instruction to make a 64-bit system
call. A 64-bit process make a 32-bit system call with int $0x80.
In both these cases under CONFIG_SECCOMP=y, secure_computing() will use
the wrong system call number table. The fix is simple: test TS_COMPAT
instead of TIF_IA32. Here is an example exploit:
/* test case for seccomp circumvention on x86-64
There are two failure modes: compile with -m64 or compile with -m32.
The -m64 case is the worst one, because it does "chmod 777 ." (could
be any chmod call). The -m32 case demonstrates it was able to do
stat(), which can glean information but not harm anything directly.
A buggy kernel will let the test do something, print, and exit 1; a
fixed kernel will make it exit with SIGKILL before it does anything.
*/
#define _GNU_SOURCE
#include <assert.h>
#include <inttypes.h>
#include <stdio.h>
#include <linux/prctl.h>
#include <sys/stat.h>
#include <unistd.h>
#include <asm/unistd.h>
int
main (int argc, char **argv)
{
char buf[100];
static const char dot[] = ".";
long ret;
unsigned st[24];
if (prctl (PR_SET_SECCOMP, 1, 0, 0, 0) != 0)
perror ("prctl(PR_SET_SECCOMP) -- not compiled into kernel?");
#ifdef __x86_64__
assert ((uintptr_t) dot < (1UL << 32));
asm ("int $0x80 # %0 <- %1(%2 %3)"
: "=a" (ret) : "0" (15), "b" (dot), "c" (0777));
ret = snprintf (buf, sizeof buf,
"result %ld (check mode on .!)\n", ret);
#elif defined __i386__
asm (".code32\n"
"pushl %%cs\n"
"pushl $2f\n"
"ljmpl $0x33, $1f\n"
".code64\n"
"1: syscall # %0 <- %1(%2 %3)\n"
"lretl\n"
".code32\n"
"2:"
: "=a" (ret) : "0" (4), "D" (dot), "S" (&st));
if (ret == 0)
ret = snprintf (buf, sizeof buf,
"stat . -> st_uid=%u\n", st[7]);
else
ret = snprintf (buf, sizeof buf, "result %ld\n", ret);
#else
# error "not this one"
#endif
write (1, buf, ret);
syscall (__NR_exit, 1);
return 2;
}
Signed-off-by: Roland McGrath <roland@redhat.com>
[ I don't know if anybody actually uses seccomp, but it's enabled in
at least both Fedora and SuSE kernels, so maybe somebody is. - Linus ]
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
||
Andrea Arcangeli
|
cf99abace7 |
make seccomp zerocost in schedule
This follows a suggestion from Chuck Ebbert on how to make seccomp absolutely zerocost in schedule too. The only remaining footprint of seccomp is in terms of the bzImage size that becomes a few bytes (perhaps even a few kbytes) larger, measure it if you care in the embedded. Signed-off-by: Andrea Arcangeli <andrea@cpushare.com> Cc: Andi Kleen <ak@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> |
||
|
Andrea Arcangeli
|
1d9d02feee |
move seccomp from /proc to a prctl
This reduces the memory footprint and it enforces that only the current task can enable seccomp on itself (this is a requirement for a strightforward [modulo preempt ;) ] TIF_NOTSC implementation). Signed-off-by: Andrea Arcangeli <andrea@cpushare.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> |
||
Linus Torvalds
|
1da177e4c3 |
Linux-2.6.12-rc2
Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip! |