Received: by 10.213.65.68 with SMTP id h4csp429640imn; Tue, 13 Mar 2018 08:48:07 -0700 (PDT) X-Google-Smtp-Source: AG47ELsxYiI2aZyLUr79Aic3tm9aR8orlnxZw1uXuyDR1Ji2gYj2p/aIm8kijArGSWq435aqMZbY X-Received: by 2002:a17:902:8c83:: with SMTP id t3-v6mr993945plo.310.1520956087419; Tue, 13 Mar 2018 08:48:07 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1520956087; cv=none; d=google.com; s=arc-20160816; b=cv+zHnhYX+6ShK+Ks+EeegVk5Qxoo5iUGjj9g40Q3xS7gCxbT/gyzRfV8RS7923eND DKKICCQeSMounJ4W2Jhi0bYCCt2F5TlN0aArsrVstfckBRYQ11ciF32AG3GoKMAYsiM7 fUrnsg4xQDQqzIpXxv8ZA6bBgLHpYGCoOrHBZHXTd4xHIf4ezLuTvSLB2Kdb51nda2WB yQ5/zQTEjOIarBpQFKihNq2gK900ai9p8rQaNahC0zKgoQunXljOrpjNoapAvpVnso7U hiIwDTgLYQwwDl9in6LRbuo6pF839xQm06KRl90+1b9+Pzo4YIthHhKXwV+sLbVqYgQC uDLw== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-id:precedence:sender:mime-version:user-agent:references :in-reply-to:message-id:date:subject:cc:to:from :arc-authentication-results; bh=uLw1pysXvRcN6iYdyztWciYJxhMYr7zC0la4eV6Hmpo=; b=biKamvfWSM8z7C7FOBl/g/gJoPH3VYVWa8Y9OGPyU4IcE50ow+Rs9KO07YHWCsdCAj m3T6l/p0s8mTbS2Nxw2ikMygwkNxSMrw3hI3bNTVA+bnAiNSZjCkI7kN6EH9NdpODHzd STx3edHyvZI03K7anSjHLR9drFM5Rd1CEuCfdzKDX2usVjRvUXhXFPPxL+085++jB9f5 0iBuRgx80JnxbzKk8lVwvAHjfLCwgaEp0sgdx/K0+v46NrFdMxchcSW79vc3xLb+IGM+ bax3wVNt61wTnIEAebRa+rffNQu80oZY4nkQEXyWXtdcCWbAW0NWFbeOqqC/KfqBrduU MzGw== ARC-Authentication-Results: i=1; mx.google.com; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org Return-Path: Received: from vger.kernel.org (vger.kernel.org. [209.132.180.67]) by mx.google.com with ESMTP id e12-v6si306175plj.126.2018.03.13.08.47.52; Tue, 13 Mar 2018 08:48:07 -0700 (PDT) Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67; Authentication-Results: mx.google.com; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S934979AbeCMPl1 (ORCPT + 99 others); Tue, 13 Mar 2018 11:41:27 -0400 Received: from mail.linuxfoundation.org ([140.211.169.12]:36808 "EHLO mail.linuxfoundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932400AbeCMPlV (ORCPT ); Tue, 13 Mar 2018 11:41:21 -0400 Received: from localhost (LFbn-1-12258-90.w90-92.abo.wanadoo.fr [90.92.71.90]) by mail.linuxfoundation.org (Postfix) with ESMTPSA id 772CD10F4; Tue, 13 Mar 2018 15:40:50 +0000 (UTC) From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, David Woodhouse , Thomas Gleixner , Linus Torvalds , Peter Zijlstra , arjan.van.de.ven@intel.com, bp@alien8.de, dave.hansen@intel.com, jmattson@google.com, karahmed@amazon.de, kvm@vger.kernel.org, pbonzini@redhat.com, rkrcmar@redhat.com, Ingo Molnar Subject: [PATCH 4.14 123/140] Revert "x86/retpoline: Simplify vmexit_fill_RSB()" Date: Tue, 13 Mar 2018 16:25:26 +0100 Message-Id: <20180313152506.439985421@linuxfoundation.org> X-Mailer: git-send-email 2.16.2 In-Reply-To: <20180313152458.201155692@linuxfoundation.org> References: <20180313152458.201155692@linuxfoundation.org> User-Agent: quilt/0.65 X-stable: review MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 4.14-stable review patch. If anyone has any objections, please let me know. ------------------ From: David Woodhouse commit d1c99108af3c5992640aa2afa7d2e88c3775c06e upstream. This reverts commit 1dde7415e99933bb7293d6b2843752cbdb43ec11. By putting the RSB filling out of line and calling it, we waste one RSB slot for returning from the function itself, which means one fewer actual function call we can make if we're doing the Skylake abomination of call-depth counting. It also changed the number of RSB stuffings we do on vmexit from 32, which was correct, to 16. Let's just stop with the bikeshedding; it didn't actually *fix* anything anyway. Signed-off-by: David Woodhouse Acked-by: Thomas Gleixner Cc: Linus Torvalds Cc: Peter Zijlstra Cc: arjan.van.de.ven@intel.com Cc: bp@alien8.de Cc: dave.hansen@intel.com Cc: jmattson@google.com Cc: karahmed@amazon.de Cc: kvm@vger.kernel.org Cc: pbonzini@redhat.com Cc: rkrcmar@redhat.com Link: http://lkml.kernel.org/r/1519037457-7643-4-git-send-email-dwmw@amazon.co.uk Signed-off-by: Ingo Molnar Signed-off-by: Greg Kroah-Hartman --- arch/x86/entry/entry_32.S | 3 - arch/x86/entry/entry_64.S | 3 - arch/x86/include/asm/asm-prototypes.h | 3 - arch/x86/include/asm/nospec-branch.h | 70 ++++++++++++++++++++++++++++++---- arch/x86/lib/Makefile | 1 arch/x86/lib/retpoline.S | 56 --------------------------- 6 files changed, 65 insertions(+), 71 deletions(-) --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -252,8 +252,7 @@ ENTRY(__switch_to_asm) * exist, overwrite the RSB with entries which capture * speculative execution to prevent attack. */ - /* Clobbers %ebx */ - FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW + FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW #endif /* restore callee-saved registers */ --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -360,8 +360,7 @@ ENTRY(__switch_to_asm) * exist, overwrite the RSB with entries which capture * speculative execution to prevent attack. */ - /* Clobbers %rbx */ - FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW + FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW #endif /* restore callee-saved registers */ --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -38,7 +38,4 @@ INDIRECT_THUNK(dx) INDIRECT_THUNK(si) INDIRECT_THUNK(di) INDIRECT_THUNK(bp) -asmlinkage void __fill_rsb(void); -asmlinkage void __clear_rsb(void); - #endif /* CONFIG_RETPOLINE */ --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -8,6 +8,50 @@ #include #include +/* + * Fill the CPU return stack buffer. + * + * Each entry in the RSB, if used for a speculative 'ret', contains an + * infinite 'pause; lfence; jmp' loop to capture speculative execution. + * + * This is required in various cases for retpoline and IBRS-based + * mitigations for the Spectre variant 2 vulnerability. Sometimes to + * eliminate potentially bogus entries from the RSB, and sometimes + * purely to ensure that it doesn't get empty, which on some CPUs would + * allow predictions from other (unwanted!) sources to be used. + * + * We define a CPP macro such that it can be used from both .S files and + * inline assembly. It's possible to do a .macro and then include that + * from C via asm(".include ") but let's not go there. + */ + +#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ +#define RSB_FILL_LOOPS 16 /* To avoid underflow */ + +/* + * Google experimented with loop-unrolling and this turned out to be + * the optimal version — two calls, each with their own speculation + * trap should their return address end up getting used, in a loop. + */ +#define __FILL_RETURN_BUFFER(reg, nr, sp) \ + mov $(nr/2), reg; \ +771: \ + call 772f; \ +773: /* speculation trap */ \ + pause; \ + lfence; \ + jmp 773b; \ +772: \ + call 774f; \ +775: /* speculation trap */ \ + pause; \ + lfence; \ + jmp 775b; \ +774: \ + dec reg; \ + jnz 771b; \ + add $(BITS_PER_LONG/8) * nr, sp; + #ifdef __ASSEMBLY__ /* @@ -78,10 +122,17 @@ #endif .endm -/* This clobbers the BX register */ -.macro FILL_RETURN_BUFFER nr:req ftr:req + /* + * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP + * monstrosity above, manually. + */ +.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req #ifdef CONFIG_RETPOLINE - ALTERNATIVE "", "call __clear_rsb", \ftr + ANNOTATE_NOSPEC_ALTERNATIVE + ALTERNATIVE "jmp .Lskip_rsb_\@", \ + __stringify(__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP)) \ + \ftr +.Lskip_rsb_\@: #endif .endm @@ -156,10 +207,15 @@ extern char __indirect_thunk_end[]; static inline void vmexit_fill_RSB(void) { #ifdef CONFIG_RETPOLINE - alternative_input("", - "call __fill_rsb", - X86_FEATURE_RETPOLINE, - ASM_NO_INPUT_CLOBBER(_ASM_BX, "memory")); + unsigned long loops; + + asm volatile (ANNOTATE_NOSPEC_ALTERNATIVE + ALTERNATIVE("jmp 910f", + __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)), + X86_FEATURE_RETPOLINE) + "910:" + : "=r" (loops), ASM_CALL_CONSTRAINT + : : "memory" ); #endif } --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -27,7 +27,6 @@ lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o lib-$(CONFIG_RETPOLINE) += retpoline.o -OBJECT_FILES_NON_STANDARD_retpoline.o :=y obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -7,7 +7,6 @@ #include #include #include -#include .macro THUNK reg .section .text.__x86.indirect_thunk @@ -47,58 +46,3 @@ GENERATE_THUNK(r13) GENERATE_THUNK(r14) GENERATE_THUNK(r15) #endif - -/* - * Fill the CPU return stack buffer. - * - * Each entry in the RSB, if used for a speculative 'ret', contains an - * infinite 'pause; lfence; jmp' loop to capture speculative execution. - * - * This is required in various cases for retpoline and IBRS-based - * mitigations for the Spectre variant 2 vulnerability. Sometimes to - * eliminate potentially bogus entries from the RSB, and sometimes - * purely to ensure that it doesn't get empty, which on some CPUs would - * allow predictions from other (unwanted!) sources to be used. - * - * Google experimented with loop-unrolling and this turned out to be - * the optimal version - two calls, each with their own speculation - * trap should their return address end up getting used, in a loop. - */ -.macro STUFF_RSB nr:req sp:req - mov $(\nr / 2), %_ASM_BX - .align 16 -771: - call 772f -773: /* speculation trap */ - pause - lfence - jmp 773b - .align 16 -772: - call 774f -775: /* speculation trap */ - pause - lfence - jmp 775b - .align 16 -774: - dec %_ASM_BX - jnz 771b - add $((BITS_PER_LONG/8) * \nr), \sp -.endm - -#define RSB_FILL_LOOPS 16 /* To avoid underflow */ - -ENTRY(__fill_rsb) - STUFF_RSB RSB_FILL_LOOPS, %_ASM_SP - ret -END(__fill_rsb) -EXPORT_SYMBOL_GPL(__fill_rsb) - -#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ - -ENTRY(__clear_rsb) - STUFF_RSB RSB_CLEAR_LOOPS, %_ASM_SP - ret -END(__clear_rsb) -EXPORT_SYMBOL_GPL(__clear_rsb)