From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andre Przywara Subject: Re: [PATCH 1/2] KVM: arm/arm64: Add save/restore support for firmware workaround state Date: Wed, 30 Jan 2019 11:39:00 +0000 Message-ID: <20190130113900.10089070@donnerap.cambridge.arm.com> References: <20190107120537.184252-1-andre.przywara@arm.com> <20190107120537.184252-2-andre.przywara@arm.com> <20190122151714.GG3578@e103592.cambridge.arm.com> <20190125144657.3db91c91@donnerap.cambridge.arm.com> <20190129213223.GB3567@e103592.cambridge.arm.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Cc: Marc Zyngier , linux-arm-kernel@lists.infradead.org, kvm@vger.kernel.org, kvmarm@lists.cs.columbia.edu To: Dave Martin , Peter Maydell Return-path: In-Reply-To: <20190129213223.GB3567@e103592.cambridge.arm.com> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: kvmarm-bounces@lists.cs.columbia.edu Sender: kvmarm-bounces@lists.cs.columbia.edu List-Id: kvm.vger.kernel.org On Tue, 29 Jan 2019 21:32:23 +0000 Dave Martin wrote: Hi Dave, > On Fri, Jan 25, 2019 at 02:46:57PM +0000, Andre Przywara wrote: > > On Tue, 22 Jan 2019 15:17:14 +0000 > > Dave Martin wrote: > > > > Hi Dave, > > > > thanks for having a look! > > > > > On Mon, Jan 07, 2019 at 12:05:36PM +0000, Andre Przywara wrote: > > > > KVM implements the firmware interface for mitigating cache > > > > speculation vulnerabilities. Guests may use this interface to > > > > ensure mitigation is active. > > > > If we want to migrate such a guest to a host with a different > > > > support level for those workarounds, migration might need to > > > > fail, to ensure that critical guests don't loose their > > > > protection. > > > > > > > > Introduce a way for userland to save and restore the workarounds > > > > state. On restoring we do checks that make sure we don't > > > > downgrade our mitigation level. > > > > > > > > Signed-off-by: Andre Przywara > > > > --- > > > > arch/arm/include/asm/kvm_emulate.h | 10 ++ > > > > arch/arm/include/uapi/asm/kvm.h | 9 ++ > > > > arch/arm64/include/asm/kvm_emulate.h | 14 +++ > > > > arch/arm64/include/uapi/asm/kvm.h | 9 ++ > > > > virt/kvm/arm/psci.c | 138 > > > > ++++++++++++++++++++++++++- 5 files changed, 178 insertions(+), > > > > 2 deletions(-) > > > > > > > > diff --git a/arch/arm/include/asm/kvm_emulate.h > > > > b/arch/arm/include/asm/kvm_emulate.h index > > > > 77121b713bef..2255c50debab 100644 --- > > > > a/arch/arm/include/asm/kvm_emulate.h +++ > > > > b/arch/arm/include/asm/kvm_emulate.h @@ -275,6 +275,16 @@ static > > > > inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu > > > > *vcpu) return vcpu_cp15(vcpu, c0_MPIDR) & MPIDR_HWID_BITMASK; } > > > > > > > > +static inline bool kvm_arm_get_vcpu_workaround_2_flag(struct > > > > kvm_vcpu *vcpu) +{ > > > > + return false; > > > > +} > > > > + > > > > +static inline void kvm_arm_set_vcpu_workaround_2_flag(struct > > > > kvm_vcpu *vcpu, > > > > + bool > > > > flag) +{ > > > > +} > > > > + > > > > static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu) > > > > { > > > > *vcpu_cpsr(vcpu) |= PSR_E_BIT; > > > > diff --git a/arch/arm/include/uapi/asm/kvm.h > > > > b/arch/arm/include/uapi/asm/kvm.h index > > > > 4602464ebdfb..02c93b1d8f6d 100644 --- > > > > a/arch/arm/include/uapi/asm/kvm.h +++ > > > > b/arch/arm/include/uapi/asm/kvm.h @@ -214,6 +214,15 @@ struct > > > > kvm_vcpu_events { #define KVM_REG_ARM_FW_REG(r) > > > > (KVM_REG_ARM | KVM_REG_SIZE_U64 | \ KVM_REG_ARM_FW | ((r) & > > > > 0xffff)) #define KVM_REG_ARM_PSCI_VERSION > > > > KVM_REG_ARM_FW_REG(0) +#define > > > > KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1 KVM_REG_ARM_FW_REG(1) > > > > +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL 0 > > > > +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL 1 > > > > +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 > > > > KVM_REG_ARM_FW_REG(2) +#define > > > > KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_MASK 0x3 +#define > > > > KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL 0 +#define > > > > KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL 1 +#define > > > > KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNAFFECTED 2 > > > > +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED > > > > 4 /* Device Control API: ARM VGIC */ #define > > > > KVM_DEV_ARM_VGIC_GRP_ADDR 0 diff --git > > > > a/arch/arm64/include/asm/kvm_emulate.h > > > > b/arch/arm64/include/asm/kvm_emulate.h index > > > > 506386a3edde..a44f07f68da4 100644 --- > > > > a/arch/arm64/include/asm/kvm_emulate.h +++ > > > > b/arch/arm64/include/asm/kvm_emulate.h @@ -336,6 +336,20 @@ > > > > static inline unsigned long kvm_vcpu_get_mpidr_aff(struct > > > > kvm_vcpu *vcpu) return vcpu_read_sys_reg(vcpu, MPIDR_EL1) & > > > > MPIDR_HWID_BITMASK; } +static inline bool > > > > kvm_arm_get_vcpu_workaround_2_flag(struct kvm_vcpu *vcpu) +{ > > > > + return vcpu->arch.workaround_flags & > > > > VCPU_WORKAROUND_2_FLAG; +} > > > > + > > > > +static inline void kvm_arm_set_vcpu_workaround_2_flag(struct > > > > kvm_vcpu *vcpu, > > > > + bool > > > > flag) +{ > > > > + if (flag) > > > > + vcpu->arch.workaround_flags |= > > > > VCPU_WORKAROUND_2_FLAG; > > > > + else > > > > + vcpu->arch.workaround_flags &= > > > > ~VCPU_WORKAROUND_2_FLAG; +} > > > > + > > > > static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu) > > > > { > > > > if (vcpu_mode_is_32bit(vcpu)) { > > > > diff --git a/arch/arm64/include/uapi/asm/kvm.h > > > > b/arch/arm64/include/uapi/asm/kvm.h index > > > > 97c3478ee6e7..4a19ef199a99 100644 --- > > > > a/arch/arm64/include/uapi/asm/kvm.h +++ > > > > b/arch/arm64/include/uapi/asm/kvm.h @@ -225,6 +225,15 @@ struct > > > > kvm_vcpu_events { #define KVM_REG_ARM_FW_REG(r) > > > > (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \ KVM_REG_ARM_FW | ((r) & > > > > 0xffff)) #define KVM_REG_ARM_PSCI_VERSION > > > > KVM_REG_ARM_FW_REG(0) +#define > > > > KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1 KVM_REG_ARM_FW_REG(1) > > > > +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL 0 > > > > +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL 1 > > > > +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 > > > > KVM_REG_ARM_FW_REG(2) +#define > > > > KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_MASK 0x3 +#define > > > > KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL 0 +#define > > > > KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL 1 +#define > > > > KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNAFFECTED 2 +#define > > > > KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED 4 > > > > > > If this is the first exposure of this information to userspace, I > > > wonder if we can come up with some common semantics that avoid > > > having to add new ad-hoc code (and bugs) every time a new > > > vulnerability/workaround is defined. > > > > > > We seem to have at least the two following independent properties > > > for a vulnerability, with the listed values for each: > > > > > > * vulnerability (Vulnerable, Unknown, Not Vulnerable) > > > > > > * mitigation support (Not Requestable, Requestable) > > > > > > Migrations must not move to the left in _either_ list for any > > > vulnerability. > > > > > > If we want to hedge out bets we could follow the style of the ID > > > registers and allocate to each theoretical vulnerability a pair of > > > signed 2- or (for more expansion room if we think we might need > > > it) 4-bit fields. > > > > > > We could perhaps allocate as follows: > > > > > > * -1=Vulnerable, 0=Unknown, 1=Not Vulnerable > > > * 0=Mitigation not requestable, 1=Mitigation requestable > > > > So as discussed in person, that sounds quite neat. I implemented > > that, but the sign extension and masking to n bits is not very > > pretty and limits readability. > > However the property of having a kind of "vulnerability scale", > > where a simple comparison would determine compatibility, is a good > > thing to have and drastically simplifies the checking code. > > > > > Checking code wouldn't need to know which fields describe > > > mitigation mechanisms and which describe vulnerabilities: we'd > > > just do a strict > > > >= comparison on each. > > > > > > Further, if a register is never written before the vcpu is first > > > run, we should imply a write of 0 to it as part of KVM_RUN (so > > > that if the destination node has a negative value anywhere, > > > KVM_RUN barfs cleanly. > > > > What I like about the signedness is this "0 means unknown", which is > > magically forwards compatible. However I am not sure we can transfer > > this semantic into every upcoming register that pops up in the > > future. > > I appreciate the concern, but can you give an example of how it might > break? The general problem is that we don't know how future firmware registers would need to look like and whether they are actually for workarounds. Take for instance KVM_REG_ARM_FW_REG(0), which holds the PSCI version. So at the very least we would need to reserve a region of the 64K firmware registers to use this scheme, yet don't know how many we would need. > My idea is that you can check for compatibility by comparing fields > without any need to know what they mean, but we wouldn't pre-assign > meanings for the values of unallocated fields, just create a precedent > that future fields can follow (where it works). For clarity, what do you mean with "... you can check ...", exactly? I think this "you" would be the receiving kernel, which is very strict about unknown registers (-EINVAL), because we don't take any chances. >>From what I understand how QEMU works, is that it just takes the list of registers from the originating kernel and asks the receiving kernel about them. It doesn't try to interpret most registers in any way. Now QEMU *could* ignore the -EINVAL return and proceed anyway, if it would be very sure about the implications or the admin told it so. But I believe this should be done on a per register basis, and in QEMU, relying on some forward looking scheme sounds a bit fragile to me. It is my understanding that QEMU does not want to gamble with migration. > This is much like the CPU ID features scheme itself. A "0" might > mean that something is absent, but there's no way (or need) to know > what. So I think we don't disagree about that this is possible or even would be nice, but it's just not how it's used today. I am not sure we want to introduce something like this, given that we don't know if there will be any future workaround registers at all. Sounds a bit over-engineered and fragile to me. Peter, can you give your opinion about whether having some generic class of firmware workaround registers which could be checked in a generic way is something we want? > > Actually we might not need this: > > My understanding of how QEMU handles this in migration is that it > > reads the f/w reg on the originating host A and writes this into > > the target host B, without itself interpreting this in any way. > > It's up to the target kernel (basically this code here) to check > > compatibility. So I am not sure we actually need a stable scheme. > > If host A doesn't know about > > Nothing stops userspace from interpreting the data, so there's a risk > people may grow to rely on it even if we don't want them to. Well, but userland would not interpret unknown registers, under the current scheme, would it? So it can surely tinker with KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1, because it knows about its meaning. But I would be very careful judging about anything else. The moment we introduce some scheme, we would have to stick with it forever. I am just not sure that's worth it. At the end of the day you could always update QEMU to ignore an -EINVAL on a new firmware w/a register. > So we should try to have something that's forward-compatible if at all > possible... > > a certain register, it won't appear in the result of the > > KVM_GET_REG_LIST ioctl, so it won't be transferred to host B at > > all. In the opposite case the receiving host would reject an > > unknown register, which I believe is safer, although I see that it > > leaves the "unknown" case on the table. > > > > It would be good to have some opinion of how forward looking we > > want to (and can) be here. > > > > Meanwhile I am sending a v2 which implements the linear scale idea, > > without using signed values, as this indeed simplifies the code. > > I have the signed version still in a branch here, let me know if you > > want to have a look. > > Happy to take a look at it. See below. > I was hoping that cpufeatures already had a helper for extracting a > signed field, but I didn't go looking for it... > > At the asm level this is just a sbfx, so it's hardly expensive. The length of the code or the "performance" is hardly an issue (we are talking about migration here, which is mostly limited by the speed of the network). And yes, we have sign_extend32() and (i & 0xf) to convert, it just looks a bit odd in the code and in the API documentation. Cheers, Andre diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h index 6c6757c9571b..a7b10d835ce7 100644 --- a/arch/arm/include/uapi/asm/kvm.h +++ b/arch/arm/include/uapi/asm/kvm.h @@ -218,10 +218,10 @@ struct kvm_vcpu_events { #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL 0 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL 1 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 KVM_REG_ARM_FW_REG(2) -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL 0 -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN 1 -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL 2 -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNAFFECTED 3 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL (-1 & 0xf) +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN 0 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL 1 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNAFFECTED 2 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED (1U << 4) /* Device Control API: ARM VGIC */ diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 367e96fe654e..7d03f8339100 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -229,10 +229,10 @@ struct kvm_vcpu_events { #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL 0 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL 1 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 KVM_REG_ARM_FW_REG(2) -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL 0 -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN 1 -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL 2 -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNAFFECTED 3 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL (-1 & 0xf) +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN 0 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL 1 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNAFFECTED 2 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED (1U << 4) /* Device Control API: ARM VGIC */ diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c index fb6af5ca259e..cfb1519b9a11 100644 --- a/virt/kvm/arm/psci.c +++ b/virt/kvm/arm/psci.c @@ -498,7 +498,8 @@ static int get_kernel_wa_level(u64 regid) case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: switch (fake_kvm_arm_have_ssbd()) { case KVM_SSBD_FORCE_DISABLE: - return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL; + return sign_extend32(KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL, + KVM_REG_FEATURE_LEVEL_WIDTH - 1); case KVM_SSBD_KERNEL: return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL; case KVM_SSBD_FORCE_ENABLE: @@ -574,7 +575,7 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) } case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: - wa_level = val & KVM_REG_FEATURE_LEVEL_MASK; + wa_level = sign_extend32(val, KVM_REG_FEATURE_LEVEL_WIDTH - 1); if (get_kernel_wa_level(reg->id) < wa_level) return -EINVAL; @@ -582,7 +583,7 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) return 0; case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: - wa_level = val & KVM_REG_FEATURE_LEVEL_MASK; + wa_level = sign_extend32(val, KVM_REG_FEATURE_LEVEL_WIDTH - 1); if (get_kernel_wa_level(reg->id) < wa_level) return -EINVAL; From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-7.0 required=3.0 tests=DKIMWL_WL_HIGH,DKIM_SIGNED, DKIM_VALID,HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH,MAILING_LIST_MULTI, SIGNED_OFF_BY,SPF_PASS,URIBL_BLOCKED autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 0761FC282D7 for ; Wed, 30 Jan 2019 11:39:13 +0000 (UTC) Received: from bombadil.infradead.org (bombadil.infradead.org [198.137.202.133]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id C958021852 for ; Wed, 30 Jan 2019 11:39:12 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (2048-bit key) header.d=lists.infradead.org header.i=@lists.infradead.org header.b="f6uIFyVF" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org C958021852 Authentication-Results: mail.kernel.org; dmarc=none (p=none dis=none) header.from=arm.com Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=linux-arm-kernel-bounces+infradead-linux-arm-kernel=archiver.kernel.org@lists.infradead.org DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=lists.infradead.org; s=bombadil.20170209; h=Sender: Content-Transfer-Encoding:Content-Type:Cc:List-Subscribe:List-Help:List-Post: List-Archive:List-Unsubscribe:List-Id:MIME-Version:References:In-Reply-To: Message-ID:Subject:To:From:Date:Reply-To:Content-ID:Content-Description: Resent-Date:Resent-From:Resent-Sender:Resent-To:Resent-Cc:Resent-Message-ID: List-Owner; bh=VC0yWz5kIzyQMyPxNovj8Y3ThRFP13j6yNPVZhH3n/0=; b=f6uIFyVFHi6dok fiHBQL2hivzLsPxNxRxTH8Zga5QWioj70Jvyu7IzVVxFXSCzshXHvE0N54F3ZfNoaiLMbMW2hOgx7 AaxPvqieMetFLCPZxZY8+Be/a9QLEhObO1IcAF+GNHkyJ0pzt2/wbQJMIcgc1AmFqOdZKNAWXSBvz W9H7QHzyluf5I+a357q5YFC3NRXB690dFXiQpXNrmjeOJaNOTrz5naOts/tlMoscCCXraTQxWwKTp xVnZcTZdHEsLevBQxda4lj3zfwOAgq5Q3ztUTynObTUdv7LVE501tFFawggfYEb+dS86+6bTP0Cap lQUp954beZRyFdVPjkkA==; Received: from localhost ([127.0.0.1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.90_1 #2 (Red Hat Linux)) id 1gooD1-0000eL-K1; Wed, 30 Jan 2019 11:39:11 +0000 Received: from usa-sjc-mx-foss1.foss.arm.com ([217.140.101.70] helo=foss.arm.com) by bombadil.infradead.org with esmtp (Exim 4.90_1 #2 (Red Hat Linux)) id 1gooCx-0000df-V7 for linux-arm-kernel@lists.infradead.org; Wed, 30 Jan 2019 11:39:09 +0000 Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.72.51.249]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id 8DA42A78; Wed, 30 Jan 2019 03:39:05 -0800 (PST) Received: from donnerap.cambridge.arm.com (usa-sjc-imap-foss1.foss.arm.com [10.72.51.249]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPSA id 599653F59C; Wed, 30 Jan 2019 03:39:04 -0800 (PST) Date: Wed, 30 Jan 2019 11:39:00 +0000 From: Andre Przywara To: Dave Martin , Peter Maydell Subject: Re: [PATCH 1/2] KVM: arm/arm64: Add save/restore support for firmware workaround state Message-ID: <20190130113900.10089070@donnerap.cambridge.arm.com> In-Reply-To: <20190129213223.GB3567@e103592.cambridge.arm.com> References: <20190107120537.184252-1-andre.przywara@arm.com> <20190107120537.184252-2-andre.przywara@arm.com> <20190122151714.GG3578@e103592.cambridge.arm.com> <20190125144657.3db91c91@donnerap.cambridge.arm.com> <20190129213223.GB3567@e103592.cambridge.arm.com> Organization: ARM X-Mailer: Claws Mail 3.17.3 (GTK+ 2.24.32; aarch64-unknown-linux-gnu) MIME-Version: 1.0 X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20190130_033908_020046_F7E835E5 X-CRM114-Status: GOOD ( 53.38 ) X-BeenThere: linux-arm-kernel@lists.infradead.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: Marc Zyngier , linux-arm-kernel@lists.infradead.org, kvm@vger.kernel.org, kvmarm@lists.cs.columbia.edu Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Sender: "linux-arm-kernel" Errors-To: linux-arm-kernel-bounces+infradead-linux-arm-kernel=archiver.kernel.org@lists.infradead.org On Tue, 29 Jan 2019 21:32:23 +0000 Dave Martin wrote: Hi Dave, > On Fri, Jan 25, 2019 at 02:46:57PM +0000, Andre Przywara wrote: > > On Tue, 22 Jan 2019 15:17:14 +0000 > > Dave Martin wrote: > > > > Hi Dave, > > > > thanks for having a look! > > > > > On Mon, Jan 07, 2019 at 12:05:36PM +0000, Andre Przywara wrote: > > > > KVM implements the firmware interface for mitigating cache > > > > speculation vulnerabilities. Guests may use this interface to > > > > ensure mitigation is active. > > > > If we want to migrate such a guest to a host with a different > > > > support level for those workarounds, migration might need to > > > > fail, to ensure that critical guests don't loose their > > > > protection. > > > > > > > > Introduce a way for userland to save and restore the workarounds > > > > state. On restoring we do checks that make sure we don't > > > > downgrade our mitigation level. > > > > > > > > Signed-off-by: Andre Przywara > > > > --- > > > > arch/arm/include/asm/kvm_emulate.h | 10 ++ > > > > arch/arm/include/uapi/asm/kvm.h | 9 ++ > > > > arch/arm64/include/asm/kvm_emulate.h | 14 +++ > > > > arch/arm64/include/uapi/asm/kvm.h | 9 ++ > > > > virt/kvm/arm/psci.c | 138 > > > > ++++++++++++++++++++++++++- 5 files changed, 178 insertions(+), > > > > 2 deletions(-) > > > > > > > > diff --git a/arch/arm/include/asm/kvm_emulate.h > > > > b/arch/arm/include/asm/kvm_emulate.h index > > > > 77121b713bef..2255c50debab 100644 --- > > > > a/arch/arm/include/asm/kvm_emulate.h +++ > > > > b/arch/arm/include/asm/kvm_emulate.h @@ -275,6 +275,16 @@ static > > > > inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu > > > > *vcpu) return vcpu_cp15(vcpu, c0_MPIDR) & MPIDR_HWID_BITMASK; } > > > > > > > > +static inline bool kvm_arm_get_vcpu_workaround_2_flag(struct > > > > kvm_vcpu *vcpu) +{ > > > > + return false; > > > > +} > > > > + > > > > +static inline void kvm_arm_set_vcpu_workaround_2_flag(struct > > > > kvm_vcpu *vcpu, > > > > + bool > > > > flag) +{ > > > > +} > > > > + > > > > static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu) > > > > { > > > > *vcpu_cpsr(vcpu) |= PSR_E_BIT; > > > > diff --git a/arch/arm/include/uapi/asm/kvm.h > > > > b/arch/arm/include/uapi/asm/kvm.h index > > > > 4602464ebdfb..02c93b1d8f6d 100644 --- > > > > a/arch/arm/include/uapi/asm/kvm.h +++ > > > > b/arch/arm/include/uapi/asm/kvm.h @@ -214,6 +214,15 @@ struct > > > > kvm_vcpu_events { #define KVM_REG_ARM_FW_REG(r) > > > > (KVM_REG_ARM | KVM_REG_SIZE_U64 | \ KVM_REG_ARM_FW | ((r) & > > > > 0xffff)) #define KVM_REG_ARM_PSCI_VERSION > > > > KVM_REG_ARM_FW_REG(0) +#define > > > > KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1 KVM_REG_ARM_FW_REG(1) > > > > +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL 0 > > > > +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL 1 > > > > +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 > > > > KVM_REG_ARM_FW_REG(2) +#define > > > > KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_MASK 0x3 +#define > > > > KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL 0 +#define > > > > KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL 1 +#define > > > > KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNAFFECTED 2 > > > > +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED > > > > 4 /* Device Control API: ARM VGIC */ #define > > > > KVM_DEV_ARM_VGIC_GRP_ADDR 0 diff --git > > > > a/arch/arm64/include/asm/kvm_emulate.h > > > > b/arch/arm64/include/asm/kvm_emulate.h index > > > > 506386a3edde..a44f07f68da4 100644 --- > > > > a/arch/arm64/include/asm/kvm_emulate.h +++ > > > > b/arch/arm64/include/asm/kvm_emulate.h @@ -336,6 +336,20 @@ > > > > static inline unsigned long kvm_vcpu_get_mpidr_aff(struct > > > > kvm_vcpu *vcpu) return vcpu_read_sys_reg(vcpu, MPIDR_EL1) & > > > > MPIDR_HWID_BITMASK; } +static inline bool > > > > kvm_arm_get_vcpu_workaround_2_flag(struct kvm_vcpu *vcpu) +{ > > > > + return vcpu->arch.workaround_flags & > > > > VCPU_WORKAROUND_2_FLAG; +} > > > > + > > > > +static inline void kvm_arm_set_vcpu_workaround_2_flag(struct > > > > kvm_vcpu *vcpu, > > > > + bool > > > > flag) +{ > > > > + if (flag) > > > > + vcpu->arch.workaround_flags |= > > > > VCPU_WORKAROUND_2_FLAG; > > > > + else > > > > + vcpu->arch.workaround_flags &= > > > > ~VCPU_WORKAROUND_2_FLAG; +} > > > > + > > > > static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu) > > > > { > > > > if (vcpu_mode_is_32bit(vcpu)) { > > > > diff --git a/arch/arm64/include/uapi/asm/kvm.h > > > > b/arch/arm64/include/uapi/asm/kvm.h index > > > > 97c3478ee6e7..4a19ef199a99 100644 --- > > > > a/arch/arm64/include/uapi/asm/kvm.h +++ > > > > b/arch/arm64/include/uapi/asm/kvm.h @@ -225,6 +225,15 @@ struct > > > > kvm_vcpu_events { #define KVM_REG_ARM_FW_REG(r) > > > > (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \ KVM_REG_ARM_FW | ((r) & > > > > 0xffff)) #define KVM_REG_ARM_PSCI_VERSION > > > > KVM_REG_ARM_FW_REG(0) +#define > > > > KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1 KVM_REG_ARM_FW_REG(1) > > > > +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL 0 > > > > +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL 1 > > > > +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 > > > > KVM_REG_ARM_FW_REG(2) +#define > > > > KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_MASK 0x3 +#define > > > > KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL 0 +#define > > > > KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL 1 +#define > > > > KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNAFFECTED 2 +#define > > > > KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED 4 > > > > > > If this is the first exposure of this information to userspace, I > > > wonder if we can come up with some common semantics that avoid > > > having to add new ad-hoc code (and bugs) every time a new > > > vulnerability/workaround is defined. > > > > > > We seem to have at least the two following independent properties > > > for a vulnerability, with the listed values for each: > > > > > > * vulnerability (Vulnerable, Unknown, Not Vulnerable) > > > > > > * mitigation support (Not Requestable, Requestable) > > > > > > Migrations must not move to the left in _either_ list for any > > > vulnerability. > > > > > > If we want to hedge out bets we could follow the style of the ID > > > registers and allocate to each theoretical vulnerability a pair of > > > signed 2- or (for more expansion room if we think we might need > > > it) 4-bit fields. > > > > > > We could perhaps allocate as follows: > > > > > > * -1=Vulnerable, 0=Unknown, 1=Not Vulnerable > > > * 0=Mitigation not requestable, 1=Mitigation requestable > > > > So as discussed in person, that sounds quite neat. I implemented > > that, but the sign extension and masking to n bits is not very > > pretty and limits readability. > > However the property of having a kind of "vulnerability scale", > > where a simple comparison would determine compatibility, is a good > > thing to have and drastically simplifies the checking code. > > > > > Checking code wouldn't need to know which fields describe > > > mitigation mechanisms and which describe vulnerabilities: we'd > > > just do a strict > > > >= comparison on each. > > > > > > Further, if a register is never written before the vcpu is first > > > run, we should imply a write of 0 to it as part of KVM_RUN (so > > > that if the destination node has a negative value anywhere, > > > KVM_RUN barfs cleanly. > > > > What I like about the signedness is this "0 means unknown", which is > > magically forwards compatible. However I am not sure we can transfer > > this semantic into every upcoming register that pops up in the > > future. > > I appreciate the concern, but can you give an example of how it might > break? The general problem is that we don't know how future firmware registers would need to look like and whether they are actually for workarounds. Take for instance KVM_REG_ARM_FW_REG(0), which holds the PSCI version. So at the very least we would need to reserve a region of the 64K firmware registers to use this scheme, yet don't know how many we would need. > My idea is that you can check for compatibility by comparing fields > without any need to know what they mean, but we wouldn't pre-assign > meanings for the values of unallocated fields, just create a precedent > that future fields can follow (where it works). For clarity, what do you mean with "... you can check ...", exactly? I think this "you" would be the receiving kernel, which is very strict about unknown registers (-EINVAL), because we don't take any chances. >From what I understand how QEMU works, is that it just takes the list of registers from the originating kernel and asks the receiving kernel about them. It doesn't try to interpret most registers in any way. Now QEMU *could* ignore the -EINVAL return and proceed anyway, if it would be very sure about the implications or the admin told it so. But I believe this should be done on a per register basis, and in QEMU, relying on some forward looking scheme sounds a bit fragile to me. It is my understanding that QEMU does not want to gamble with migration. > This is much like the CPU ID features scheme itself. A "0" might > mean that something is absent, but there's no way (or need) to know > what. So I think we don't disagree about that this is possible or even would be nice, but it's just not how it's used today. I am not sure we want to introduce something like this, given that we don't know if there will be any future workaround registers at all. Sounds a bit over-engineered and fragile to me. Peter, can you give your opinion about whether having some generic class of firmware workaround registers which could be checked in a generic way is something we want? > > Actually we might not need this: > > My understanding of how QEMU handles this in migration is that it > > reads the f/w reg on the originating host A and writes this into > > the target host B, without itself interpreting this in any way. > > It's up to the target kernel (basically this code here) to check > > compatibility. So I am not sure we actually need a stable scheme. > > If host A doesn't know about > > Nothing stops userspace from interpreting the data, so there's a risk > people may grow to rely on it even if we don't want them to. Well, but userland would not interpret unknown registers, under the current scheme, would it? So it can surely tinker with KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1, because it knows about its meaning. But I would be very careful judging about anything else. The moment we introduce some scheme, we would have to stick with it forever. I am just not sure that's worth it. At the end of the day you could always update QEMU to ignore an -EINVAL on a new firmware w/a register. > So we should try to have something that's forward-compatible if at all > possible... > > a certain register, it won't appear in the result of the > > KVM_GET_REG_LIST ioctl, so it won't be transferred to host B at > > all. In the opposite case the receiving host would reject an > > unknown register, which I believe is safer, although I see that it > > leaves the "unknown" case on the table. > > > > It would be good to have some opinion of how forward looking we > > want to (and can) be here. > > > > Meanwhile I am sending a v2 which implements the linear scale idea, > > without using signed values, as this indeed simplifies the code. > > I have the signed version still in a branch here, let me know if you > > want to have a look. > > Happy to take a look at it. See below. > I was hoping that cpufeatures already had a helper for extracting a > signed field, but I didn't go looking for it... > > At the asm level this is just a sbfx, so it's hardly expensive. The length of the code or the "performance" is hardly an issue (we are talking about migration here, which is mostly limited by the speed of the network). And yes, we have sign_extend32() and (i & 0xf) to convert, it just looks a bit odd in the code and in the API documentation. Cheers, Andre diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h index 6c6757c9571b..a7b10d835ce7 100644 --- a/arch/arm/include/uapi/asm/kvm.h +++ b/arch/arm/include/uapi/asm/kvm.h @@ -218,10 +218,10 @@ struct kvm_vcpu_events { #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL 0 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL 1 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 KVM_REG_ARM_FW_REG(2) -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL 0 -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN 1 -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL 2 -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNAFFECTED 3 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL (-1 & 0xf) +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN 0 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL 1 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNAFFECTED 2 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED (1U << 4) /* Device Control API: ARM VGIC */ diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 367e96fe654e..7d03f8339100 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -229,10 +229,10 @@ struct kvm_vcpu_events { #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL 0 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL 1 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 KVM_REG_ARM_FW_REG(2) -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL 0 -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN 1 -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL 2 -#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNAFFECTED 3 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL (-1 & 0xf) +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN 0 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL 1 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNAFFECTED 2 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED (1U << 4) /* Device Control API: ARM VGIC */ diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c index fb6af5ca259e..cfb1519b9a11 100644 --- a/virt/kvm/arm/psci.c +++ b/virt/kvm/arm/psci.c @@ -498,7 +498,8 @@ static int get_kernel_wa_level(u64 regid) case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: switch (fake_kvm_arm_have_ssbd()) { case KVM_SSBD_FORCE_DISABLE: - return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL; + return sign_extend32(KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL, + KVM_REG_FEATURE_LEVEL_WIDTH - 1); case KVM_SSBD_KERNEL: return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL; case KVM_SSBD_FORCE_ENABLE: @@ -574,7 +575,7 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) } case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: - wa_level = val & KVM_REG_FEATURE_LEVEL_MASK; + wa_level = sign_extend32(val, KVM_REG_FEATURE_LEVEL_WIDTH - 1); if (get_kernel_wa_level(reg->id) < wa_level) return -EINVAL; @@ -582,7 +583,7 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) return 0; case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: - wa_level = val & KVM_REG_FEATURE_LEVEL_MASK; + wa_level = sign_extend32(val, KVM_REG_FEATURE_LEVEL_WIDTH - 1); if (get_kernel_wa_level(reg->id) < wa_level) return -EINVAL; _______________________________________________ linux-arm-kernel mailing list linux-arm-kernel@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-arm-kernel