seccomp: add generic code for jitted seccomp filters.

This patchset adds support for jitted seccomp BPF filters, with the
required modifications to make it work on the ARM architecture.

- The first patch in the serie adds the required boiler plate in the
  core kernel seccomp code to invoke the JIT compilation/free code.

- The second patch reworks the ARM BPF JIT code to make the generation
  process less dependent on struct sk_filter.

- The last patch actually implements the ARM part in the BPF jit code.

Some benchmarks, on a 1.6Ghz 88f6282 CPU:

Each system call is tested in two way (fast/slow):

 - on the fast version, the tested system call is accepted immediately
   after checking the architecture (5 BPF instructions).

 - on the slow version, the tested system call is accepted after
   previously checking for 85 syscall (90 instructions, including the
   architecture check).

The tested syscall is invoked in a loop 1000000 time, the reported
time is the time spent in the loop in seconds.

Without Seccomp JIT:

Syscall		Time-Fast  Time-Slow
--------------- ---------- ----------
gettimeofday	0.389	   1.633
getpid		0.406	   1.688
getresuid	1.003	   2.266
getcwd		1.342	   2.128

With Seccomp JIT:

Syscall		Time-Fast  Time-Slow
--------------- ----------- ---------
gettimeofday	0.348	    0.428
getpid		0.365	    0.480
getresuid	0.981	    1.060
getcwd		1.237	    1.294

For reference, the same code without any seccomp filter:

Syscall		Time
--------------- -----
gettimeofday	0.119
getpid		0.137
getresuid	0.747
getcwd		1.021

The activation of the BPF JIT for seccomp is still controled with the
/proc/sys/net/core/bpf_jit_enable sysctl knob.

This patch:

Architecture must select HAVE_SECCOMP_FILTER_JIT and implement
seccomp_jit_compile() and seccomp_jit_free() if they intend to support
jitted seccomp filters.

Accessors to struct seccomp_filter fields are provided in
<linux/seccomp.h> to be used by the JIT code.  With this, the 'struct
seccomp_filter' structure can stay opaque when outside kernel/seccomp.c.

In a way similar to the net BPF, the jit compilation code is expected to
updates struct seccomp_filter.bpf_func pointer (using the correct
accessor) to the generated code.

Signed-off-by: Nicolas Schichan <nschichan@freebox.fr>
Cc: Will Drewry <wad@chromium.org>
Cc: Mircea Gherzan <mgherzan@gmail.com>
Cc: Nicolas Schichan <nschichan@freebox.fr>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Daniel Borkmann <daniel.borkmann@tik.ee.ethz.ch>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 14 insertions, 0 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index 8d2ae24b9f4a..651a9e747ceb 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -332,6 +332,10 @@ config HAVE_ARCH_SECCOMP_FILTER
 	  - secure_computing return value is checked and a return value of -1
 	    results in the system call being skipped immediately.
 
+# Used by archs to tell that they support SECCOMP_FILTER_JIT
+config HAVE_SECCOMP_FILTER_JIT
+	bool
+
 config SECCOMP_FILTER
 	def_bool y
 	depends on HAVE_ARCH_SECCOMP_FILTER && SECCOMP && NET
@@ -342,6 +346,16 @@ config SECCOMP_FILTER
 
 	  See Documentation/prctl/seccomp_filter.txt for details.
 
+config SECCOMP_FILTER_JIT
+	bool "enable Seccomp filter Just In Time compiler"
+	depends on HAVE_SECCOMP_FILTER_JIT && BPF_JIT && SECCOMP_FILTER
+	help
+	  Seccomp syscall filtering capabilities are normally handled
+	  by an interpreter. This option allows kernel to generate a native
+	  code when filter is loaded in memory. This should speedup
+	  syscall filtering. Note : Admin should enable this feature
+	  changing /proc/sys/net/core/bpf_jit_enable
+
 config HAVE_CONTEXT_TRACKING
 	bool
 	help