From patchwork Tue Jul 15 19:32:36 2014 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Andy Lutomirski X-Patchwork-Id: 4558041 Return-Path: X-Original-To: patchwork-linux-arm@patchwork.kernel.org Delivered-To: patchwork-parsemail@patchwork2.web.kernel.org Received: from mail.kernel.org (mail.kernel.org [198.145.19.201]) by patchwork2.web.kernel.org (Postfix) with ESMTP id 18BDBC0514 for ; Tue, 15 Jul 2014 19:35:36 +0000 (UTC) Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id 1C8BE201B4 for ; Tue, 15 Jul 2014 19:35:35 +0000 (UTC) Received: from bombadil.infradead.org (bombadil.infradead.org [198.137.202.9]) (using TLSv1.2 with cipher DHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id 1708C2017E for ; Tue, 15 Jul 2014 19:35:34 +0000 (UTC) Received: from localhost ([127.0.0.1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.80.1 #2 (Red Hat Linux)) id 1X78U7-0006lh-99; Tue, 15 Jul 2014 19:33:55 +0000 Received: from mail-pd0-f175.google.com ([209.85.192.175]) by bombadil.infradead.org with esmtps (Exim 4.80.1 #2 (Red Hat Linux)) id 1X78Tq-0006KU-Sh for linux-arm-kernel@lists.infradead.org; Tue, 15 Jul 2014 19:33:39 +0000 Received: by mail-pd0-f175.google.com with SMTP id v10so7624734pde.34 for ; Tue, 15 Jul 2014 12:33:17 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:in-reply-to:references; bh=/6//1l4qKKGHL90vpxo5yCcz0R6jiTQ+Bj7SYtaLpIk=; b=Q6x/WDfRzlZjgYlUJp3CubcoMKDNyG3QqHwT/SIkuhtCBvSXDgZARK8F4quZScGHPp r0DLUcHs+PGfWjkb2ZNTYzSmuB7rPLaA4DvLElb7t38n1syObn0YoDAznVqzMlYdJQNg 65nATdt5UoolnIwZrCGAgtbpXytN0qwVUnZ9xVWihWDygTWzxWZKdylUNK/ZVmjxmsT8 sPOmHmRCtns58pQGe5+lHjncU5wGIo6m3VqFZP1wWgjsSkS1AvVAS1Hm0RNxek3ki9fl UdX6qabyvj3VDypWQyuXz7JaoWDI4cglHkJQ95h01pj+rbGLLW+lZT0Z7nNMo6Tn9h7V z4zA== X-Gm-Message-State: ALoCoQnakC+tNoNsE2SSpLOvP09bfFZ9+HxW57cPy7DikRodoXQ/OY+e6tIFUEgOG7dqXQVc3zsG X-Received: by 10.66.66.135 with SMTP id f7mr6673098pat.32.1405452797330; Tue, 15 Jul 2014 12:33:17 -0700 (PDT) Received: from localhost ([2001:5a8:4:83c0:b456:e6bb:934a:3ab7]) by mx.google.com with ESMTPSA id ez1sm14740347pbd.91.2014.07.15.12.33.13 for (version=TLSv1.2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Tue, 15 Jul 2014 12:33:15 -0700 (PDT) From: Andy Lutomirski To: linux-kernel@vger.kernel.org, Kees Cook , Will Drewry , James Morris Subject: [PATCH 7/7] x86_64, entry: Use split-phase syscall_trace_enter for 64-bit syscalls Date: Tue, 15 Jul 2014 12:32:36 -0700 Message-Id: <5cb038436f48107f7b855ce2431bb6d63d3e9294.1405452484.git.luto@amacapital.net> X-Mailer: git-send-email 1.9.3 In-Reply-To: References: In-Reply-To: References: X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20140715_123338_972605_CF10CE05 X-CRM114-Status: GOOD ( 11.25 ) X-Spam-Score: -0.0 (/) Cc: linux-arch@vger.kernel.org, linux-mips@linux-mips.org, x86@kernel.org, Oleg Nesterov , Andy Lutomirski , linux-security-module@vger.kernel.org, linux-arm-kernel@lists.infradead.org, Alexei Starovoitov X-BeenThere: linux-arm-kernel@lists.infradead.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , MIME-Version: 1.0 Sender: "linux-arm-kernel" Errors-To: linux-arm-kernel-bounces+patchwork-linux-arm=patchwork.kernel.org@lists.infradead.org X-Spam-Status: No, score=-1.9 required=5.0 tests=BAYES_00,RP_MATCHES_RCVD, UNPARSEABLE_RELAY autolearn=unavailable version=3.3.1 X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on mail.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP On KVM on my box, this reduces the overhead from an always-accept seccomp filter from ~130ns to ~17ns. Most of that comes from avoiding IRET on every syscall when seccomp is enabled. In extremely approximate hacked-up benchmarking, just bypassing IRET saves about 80ns, so there's another 43ns of savings here from simplifying the seccomp path. The diffstat is also rather nice :) Signed-off-by: Andy Lutomirski --- arch/x86/kernel/entry_64.S | 40 ++++++++++++++++------------------------ 1 file changed, 16 insertions(+), 24 deletions(-) diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 432c190..13e0c1d 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -479,22 +479,6 @@ sysret_signal: #ifdef CONFIG_AUDITSYSCALL /* - * Fast path for syscall audit without full syscall trace. - * We just call __audit_syscall_entry() directly, and then - * jump back to the normal fast path. - */ -auditsys: - movq %r10,%r9 /* 6th arg: 4th syscall arg */ - movq %rdx,%r8 /* 5th arg: 3rd syscall arg */ - movq %rsi,%rcx /* 4th arg: 2nd syscall arg */ - movq %rdi,%rdx /* 3rd arg: 1st syscall arg */ - movq %rax,%rsi /* 2nd arg: syscall number */ - movl $AUDIT_ARCH_X86_64,%edi /* 1st arg: audit arch */ - call __audit_syscall_entry - LOAD_ARGS 0 /* reload call-clobbered registers */ - jmp system_call_fastpath - - /* * Return fast path for syscall audit. Call __audit_syscall_exit() * directly and then jump back to the fast path with TIF_SYSCALL_AUDIT * masked off. @@ -511,17 +495,25 @@ sysret_audit: /* Do syscall tracing */ tracesys: -#ifdef CONFIG_AUDITSYSCALL - testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) - jz auditsys -#endif + leaq -REST_SKIP(%rsp), %rdi + movq $AUDIT_ARCH_X86_64, %rsi + call syscall_trace_enter_phase1 + test %rax, %rax + jnz tracesys_phase2 /* if needed, run the slow path */ + LOAD_ARGS 0 /* else restore clobbered regs */ + jmp system_call_fastpath /* and return to the fast path */ + +tracesys_phase2: SAVE_REST FIXUP_TOP_OF_STACK %rdi - movq %rsp,%rdi - call syscall_trace_enter + movq %rsp, %rdi + movq $AUDIT_ARCH_X86_64, %rsi + movq %rax,%rdx + call syscall_trace_enter_phase2 + /* * Reload arg registers from stack in case ptrace changed them. - * We don't reload %rax because syscall_trace_enter() returned + * We don't reload %rax because syscall_trace_entry_phase2() returned * the value it wants us to use in the table lookup. */ LOAD_ARGS ARGOFFSET, 1 @@ -532,7 +524,7 @@ tracesys: andl $__SYSCALL_MASK,%eax cmpl $__NR_syscall_max,%eax #endif - ja int_ret_from_sys_call /* RAX(%rsp) set to -ENOSYS above */ + ja int_ret_from_sys_call /* RAX(%rsp) is already set */ movq %r10,%rcx /* fixup for C */ call *sys_call_table(,%rax,8) movq %rax,RAX-ARGOFFSET(%rsp)