From: Alexei Starovoitov <ast@plumgrid.com>
To: "David S. Miller" <davem@davemloft.net>
Cc: Ingo Molnar <mingo@kernel.org>,
Linus Torvalds <torvalds@linux-foundation.org>,
Andy Lutomirski <luto@amacapital.net>,
Steven Rostedt <rostedt@goodmis.org>,
Daniel Borkmann <dborkman@redhat.com>,
Chema Gonzalez <chema@google.com>,
Eric Dumazet <edumazet@google.com>,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
Brendan Gregg <brendan.d.gregg@gmail.com>,
Namhyung Kim <namhyung@kernel.org>,
"H. Peter Anvin" <hpa@zytor.com>,
Andrew Morton <akpm@linux-foundation.org>,
Kees Cook <keescook@chromium.org>,
linux-api@vger.kernel.org, netdev@vger.kernel.org,
linux-kernel@vger.kernel.org
Subject: [PATCH v5 net-next 01/29] bpf: x86: add missing 'shift by register' instructions to x64 eBPF JIT
Date: Sun, 24 Aug 2014 13:21:02 -0700 [thread overview]
Message-ID: <1408911690-7598-2-git-send-email-ast@plumgrid.com> (raw)
In-Reply-To: <1408911690-7598-1-git-send-email-ast@plumgrid.com>
'shift by register' operations are supported by eBPF interpreter, but were
accidently left out of x64 JIT compiler. Fix it and add a testcase.
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
---
arch/x86/net/bpf_jit_comp.c | 42 ++++++++++++++++++++++++++++++++++++++++++
lib/test_bpf.c | 38 ++++++++++++++++++++++++++++++++++++++
2 files changed, 80 insertions(+)
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 5c8cb8043c5a..b08a98c59530 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -515,6 +515,48 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
EMIT3(0xC1, add_1reg(b3, dst_reg), imm32);
break;
+ case BPF_ALU | BPF_LSH | BPF_X:
+ case BPF_ALU | BPF_RSH | BPF_X:
+ case BPF_ALU | BPF_ARSH | BPF_X:
+ case BPF_ALU64 | BPF_LSH | BPF_X:
+ case BPF_ALU64 | BPF_RSH | BPF_X:
+ case BPF_ALU64 | BPF_ARSH | BPF_X:
+
+ /* check for bad case when dst_reg == rcx */
+ if (dst_reg == BPF_REG_4) {
+ /* mov r11, dst_reg */
+ EMIT_mov(AUX_REG, dst_reg);
+ dst_reg = AUX_REG;
+ }
+
+ if (src_reg != BPF_REG_4) { /* common case */
+ EMIT1(0x51); /* push rcx */
+
+ /* mov rcx, src_reg */
+ EMIT_mov(BPF_REG_4, src_reg);
+ }
+
+ /* shl %rax, %cl | shr %rax, %cl | sar %rax, %cl */
+ if (BPF_CLASS(insn->code) == BPF_ALU64)
+ EMIT1(add_1mod(0x48, dst_reg));
+ else if (is_ereg(dst_reg))
+ EMIT1(add_1mod(0x40, dst_reg));
+
+ switch (BPF_OP(insn->code)) {
+ case BPF_LSH: b3 = 0xE0; break;
+ case BPF_RSH: b3 = 0xE8; break;
+ case BPF_ARSH: b3 = 0xF8; break;
+ }
+ EMIT2(0xD3, add_1reg(b3, dst_reg));
+
+ if (src_reg != BPF_REG_4)
+ EMIT1(0x59); /* pop rcx */
+
+ if (insn->dst_reg == BPF_REG_4)
+ /* mov dst_reg, r11 */
+ EMIT_mov(insn->dst_reg, AUX_REG);
+ break;
+
case BPF_ALU | BPF_END | BPF_FROM_BE:
switch (imm32) {
case 16:
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 89e0345733bd..8c66c6aace04 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -1342,6 +1342,44 @@ static struct bpf_test tests[] = {
{ { 0, -1 } }
},
{
+ "INT: shifts by register",
+ .u.insns_int = {
+ BPF_MOV64_IMM(R0, -1234),
+ BPF_MOV64_IMM(R1, 1),
+ BPF_ALU32_REG(BPF_RSH, R0, R1),
+ BPF_JMP_IMM(BPF_JEQ, R0, 0x7ffffd97, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_IMM(R2, 1),
+ BPF_ALU64_REG(BPF_LSH, R0, R2),
+ BPF_MOV32_IMM(R4, -1234),
+ BPF_JMP_REG(BPF_JEQ, R0, R4, 1),
+ BPF_EXIT_INSN(),
+ BPF_ALU64_IMM(BPF_AND, R4, 63),
+ BPF_ALU64_REG(BPF_LSH, R0, R4), /* R0 <= 46 */
+ BPF_MOV64_IMM(R3, 47),
+ BPF_ALU64_REG(BPF_ARSH, R0, R3),
+ BPF_JMP_IMM(BPF_JEQ, R0, -617, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_IMM(R2, 1),
+ BPF_ALU64_REG(BPF_LSH, R4, R2), /* R4 = 46 << 1 */
+ BPF_JMP_IMM(BPF_JEQ, R4, 92, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_IMM(R4, 4),
+ BPF_ALU64_REG(BPF_LSH, R4, R4), /* R4 = 4 << 4 */
+ BPF_JMP_IMM(BPF_JEQ, R4, 64, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_IMM(R4, 5),
+ BPF_ALU32_REG(BPF_LSH, R4, R4), /* R4 = 5 << 5 */
+ BPF_JMP_IMM(BPF_JEQ, R4, 160, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_IMM(R0, -1),
+ BPF_EXIT_INSN(),
+ },
+ INTERNAL,
+ { },
+ { { 0, -1 } }
+ },
+ {
"INT: DIV + ABS",
.u.insns_int = {
BPF_ALU64_REG(BPF_MOV, R6, R1),
--
1.7.9.5
next prev parent reply other threads:[~2014-08-24 20:21 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-08-24 20:21 [PATCH v5 net-next 00/29] BPF syscall, maps, verifier, samples, llvm Alexei Starovoitov
2014-08-24 20:21 ` Alexei Starovoitov [this message]
2014-08-24 20:21 ` [PATCH v5 net-next 02/29] net: filter: add "load 64-bit immediate" eBPF instruction Alexei Starovoitov
2014-08-24 20:21 ` [PATCH v5 net-next 03/29] net: filter: split filter.h and expose eBPF to user space Alexei Starovoitov
2014-08-24 20:21 ` [PATCH v5 net-next 04/29] bpf: introduce syscall(BPF, ...) and BPF maps Alexei Starovoitov
[not found] ` <1408911690-7598-1-git-send-email-ast-uqk4Ao+rVK5Wk0Htik3J/w@public.gmane.org>
2014-08-24 20:21 ` [PATCH v5 net-next 05/29] bpf: enable bpf syscall on x64 and i386 Alexei Starovoitov
2014-08-24 20:21 ` [PATCH v5 net-next 06/29] bpf: add lookup/update/delete/iterate methods to BPF maps Alexei Starovoitov
[not found] ` <1408911690-7598-7-git-send-email-ast-uqk4Ao+rVK5Wk0Htik3J/w@public.gmane.org>
2014-08-25 21:33 ` Cong Wang
[not found] ` <CAHA+R7MTJcsDpw=5P7hOsVf_pEOEZX_=cLrcw4ep4xntUxk=3Q-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2014-08-25 22:07 ` Alexei Starovoitov
2014-08-24 20:21 ` [PATCH v5 net-next 07/29] bpf: add hashtable type of " Alexei Starovoitov
2014-08-24 20:21 ` [PATCH v5 net-next 08/29] bpf: expand BPF syscall with program load/unload Alexei Starovoitov
2014-08-24 20:21 ` [PATCH v5 net-next 09/29] bpf: handle pseudo BPF_CALL insn Alexei Starovoitov
2014-08-24 20:21 ` [PATCH v5 net-next 12/29] bpf: handle pseudo BPF_LD_IMM64 insn Alexei Starovoitov
2014-08-24 20:21 ` [PATCH v5 net-next 21/29] tracing: allow eBPF programs to call ktime_get_ns() and get_current() Alexei Starovoitov
2014-08-24 20:21 ` [PATCH v5 net-next 27/29] samples: bpf: eBPF example in C Alexei Starovoitov
2014-08-25 0:39 ` [PATCH v5 net-next 00/29] BPF syscall, maps, verifier, samples, llvm David Miller
2014-08-24 20:21 ` [PATCH v5 net-next 10/29] bpf: verifier (add docs) Alexei Starovoitov
2014-08-24 20:21 ` [PATCH v5 net-next 11/29] bpf: verifier (add ability to receive verification log) Alexei Starovoitov
2014-08-24 20:21 ` [PATCH v5 net-next 13/29] bpf: verifier (add branch/goto checks) Alexei Starovoitov
2014-08-24 20:21 ` [PATCH v5 net-next 14/29] bpf: verifier (add verifier core) Alexei Starovoitov
2014-08-24 20:21 ` [PATCH v5 net-next 15/29] bpf: verifier (add state prunning optimization) Alexei Starovoitov
2014-08-24 20:21 ` [PATCH v5 net-next 16/29] bpf: allow eBPF programs to use maps Alexei Starovoitov
2014-08-24 20:21 ` [PATCH v5 net-next 17/29] bpf: split eBPF out of NET Alexei Starovoitov
2014-08-24 20:21 ` [PATCH v5 net-next 18/29] tracing: allow eBPF programs to be attached to events Alexei Starovoitov
2014-08-24 20:21 ` [PATCH v5 net-next 19/29] tracing: allow eBPF programs call printk() Alexei Starovoitov
2014-08-24 20:21 ` [PATCH v5 net-next 20/29] tracing: allow eBPF programs to be attached to kprobe/kretprobe Alexei Starovoitov
2014-08-24 20:21 ` [PATCH v5 net-next 22/29] samples: bpf: add mini eBPF library to manipulate maps and programs Alexei Starovoitov
2014-08-24 20:21 ` [PATCH v5 net-next 23/29] samples: bpf: example of tracing filters with eBPF Alexei Starovoitov
2014-08-24 20:21 ` [PATCH v5 net-next 24/29] bpf: verifier test Alexei Starovoitov
2014-08-24 20:21 ` [PATCH v5 net-next 25/29] bpf: llvm backend Alexei Starovoitov
2014-08-24 20:21 ` [PATCH v5 net-next 26/29] samples: bpf: elf file loader Alexei Starovoitov
2014-08-24 20:21 ` [PATCH v5 net-next 28/29] samples: bpf: counting eBPF example in C Alexei Starovoitov
2014-08-24 20:21 ` [PATCH v5 net-next 29/29] samples: bpf: IO latency analysis (iosnoop/heatmap) Alexei Starovoitov
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1408911690-7598-2-git-send-email-ast@plumgrid.com \
--to=ast@plumgrid.com \
--cc=a.p.zijlstra@chello.nl \
--cc=akpm@linux-foundation.org \
--cc=brendan.d.gregg@gmail.com \
--cc=chema@google.com \
--cc=davem@davemloft.net \
--cc=dborkman@redhat.com \
--cc=edumazet@google.com \
--cc=hpa@zytor.com \
--cc=keescook@chromium.org \
--cc=linux-api@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@amacapital.net \
--cc=mingo@kernel.org \
--cc=namhyung@kernel.org \
--cc=netdev@vger.kernel.org \
--cc=rostedt@goodmis.org \
--cc=torvalds@linux-foundation.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).