linux-kernel - Re: [PATCH v2 3/3] KVM: x86: #GP when attempts to write reserved bits of Variable Range MTRRs

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <5400AEBA.2080405@redhat.com>
Date:	Fri, 29 Aug 2014 18:47:54 +0200
From:	Paolo Bonzini <pbonzini@...hat.com>
To:	Wanpeng Li <wanpeng.li@...ux.intel.com>
CC:	Marcelo Tosatti <mtosatti@...hat.com>,
	Gleb Natapov <gleb@...nel.org>,
	Zhang Yang <yang.z.zhang@...el.com>, kvm@...r.kernel.org,
	linux-kernel@...r.kernel.org, Jan Kiszka <jan.kiszka@...mens.com>
Subject: Re: [PATCH v2 3/3] KVM: x86: #GP when attempts to write reserved
 bits of Variable Range MTRRs

Il 19/08/2014 11:04, Wanpeng Li ha scritto:
> Section 11.11.2.3 of the SDM mentions "All other bits in the IA32_MTRR_PHYSBASEn 
> and IA32_MTRR_PHYSMASKn registers are reserved; the processor generates a 
> general-protection exception(#GP) if software attempts to write to them". This 
> patch do it in kvm.
> 
> Signed-off-by: Wanpeng Li <wanpeng.li@...ux.intel.com>

This breaks if the guest maxphyaddr is higher than the host's (which 
sometimes happens depending on your hardware and how QEMU is 
configured).

You need to use cpuid_maxphyaddr, like this

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a375dfc42f6a..916e89515210 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1726,7 +1726,7 @@ static bool valid_mtrr_type(unsigned t)
 static bool mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 {
 	int i;
-	u64 mask = 0;
+	u64 mask;
 
 	if (!msr_mtrr_valid(msr))
 		return false;
@@ -1750,8 +1750,7 @@ static bool mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 	/* variable MTRRs */
 	WARN_ON(!(msr >= 0x200 && msr < 0x200 + 2 * KVM_NR_VAR_MTRR));
 
-	for (i = 63; i > boot_cpu_data.x86_phys_bits; i--)
-		mask |= (1ULL << i);
+	mask = (~0ULL) << cpuid_maxphyaddr(vcpu);
 	if ((msr & 1) == 0) {
 		/* MTRR base */
 		if (!valid_mtrr_type(data & 0xff))


Jan, can you see if this patch fixes the SeaBIOS triple fault you reported?

Paolo

> ---
>  arch/x86/kvm/x86.c | 18 +++++++++++++++---
>  1 file changed, 15 insertions(+), 3 deletions(-)
> 
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index fb3ea7a..b85da5f 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -1726,6 +1726,7 @@ static bool valid_mtrr_type(unsigned t)
>  static bool mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
>  {
>  	int i;
> +	u64 mask = 0;
>  
>  	if (!msr_mtrr_valid(msr))
>  		return false;
> @@ -1749,10 +1750,21 @@ static bool mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
>  	/* variable MTRRs */
>  	WARN_ON(!(msr >= 0x200 && msr < 0x200 + 2 * KVM_NR_VAR_MTRR));
>  
> -	if ((msr & 1) == 0)
> +	for (i = 63; i > boot_cpu_data.x86_phys_bits; i--)
> +		mask |= (1ULL << i);
> +	if ((msr & 1) == 0) {
>  		/* MTRR base */
> -		return valid_mtrr_type(data & 0xff);
> -	/* MTRR mask */
> +		if (!valid_mtrr_type(data & 0xff))
> +			return false;
> +		 mask |= 0xf00;
> +	} else
> +		/* MTRR mask */
> +		mask |= 0x7ff;
> +	if (data & mask) {
> +		kvm_inject_gp(vcpu, 0);
> +		return false;
> +	}
> +
>  	return true;
>  }
>  
> 

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/