From mboxrd@z Thu Jan 1 00:00:00 1970 From: KarimAllah Ahmed Subject: [RFC 08/10] x86/idle: Control Indirect Branch Speculation in idle Date: Sat, 20 Jan 2018 20:22:59 +0100 Message-ID: <1516476182-5153-9-git-send-email-karahmed@amazon.de> References: <1516476182-5153-1-git-send-email-karahmed@amazon.de> Cc: KarimAllah Ahmed , Andi Kleen , Andrea Arcangeli , Andy Lutomirski , Arjan van de Ven , Ashok Raj , Asit Mallick , Borislav Petkov , Dan Williams , Dave Hansen , David Woodhouse , Greg Kroah-Hartman , "H . Peter Anvin" , Ingo Molnar , Janakarajan Natarajan , Joerg Roedel , Jun Nakajima , Laura Abbott , Linus Torvalds , Masami Hiramatsu Received: from smtp-fw-33001.amazon.com ([207.171.190.10]:40622 "EHLO smtp-fw-33001.amazon.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932681AbeATTYB (ORCPT ); Sat, 20 Jan 2018 14:24:01 -0500 In-Reply-To: <1516476182-5153-1-git-send-email-karahmed@amazon.de> Sender: kvm-owner@vger.kernel.org List-ID: From: Thomas Gleixner Indirect Branch Speculation (IBS) is controlled per physical core. If one thread disables it then it's disabled for the core. If a thread enters idle it makes sense to reenable IBS so the sibling thread can run with full speculation enabled in user space. This makes only sense in mwait_idle_with_hints() because mwait_idle() can serve an interrupt immediately before speculation can be stopped again. SKL which requires IBRS should use mwait_idle_with_hints() so this is a non issue and in the worst case a missed optimization. Originally-by: Tim Chen Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/mwait.h | 14 ++++++++++++++ arch/x86/kernel/process.c | 14 ++++++++++++++ 2 files changed, 28 insertions(+) diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index 39a2fb2..f173072 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -6,6 +6,7 @@ #include #include +#include #define MWAIT_SUBSTATE_MASK 0xf #define MWAIT_CSTATE_MASK 0xf @@ -106,7 +107,20 @@ static inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx) mb(); } + /* + * Indirect Branch Speculation (IBS) is controlled per + * physical core. If one thread disables it, then it's + * disabled on all threads of the core. The kernel disables + * it on entry from user space. Reenable it on the thread + * which goes idle so the other thread has a chance to run + * with full speculation enabled in userspace. + */ + unrestrict_branch_speculation(); __monitor((void *)¤t_thread_info()->flags, 0, 0); + /* + * Restrict IBS again to protect kernel execution. + */ + restrict_branch_speculation(); if (!need_resched()) __mwait(eax, ecx); } diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 3cb2486..f941c5d 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -461,6 +461,20 @@ static __cpuidle void mwait_idle(void) mb(); /* quirk */ } + /* + * Indirect Branch Speculation (IBS) is controlled per + * physical core. If one thread disables it, then it's + * disabled on all threads of the core. The kernel disables + * it on entry from user space. For __sti_mwait() it's + * wrong to reenable it because an interrupt can be served + * before speculation can be stopped again. + * + * To plug that hole the interrupt entry code would need to + * save current state and restore. Not worth the trouble as + * SKL should not use mwait_idle(). It should use + * mwait_idle_with_hints() which can do speculation control + * safely. + */ __monitor((void *)¤t_thread_info()->flags, 0, 0); if (!need_resched()) __sti_mwait(0, 0); -- 2.7.4