linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Xiao Guangrong <guangrong.xiao@linux.intel.com>
To: pbonzini@redhat.com
Cc: gleb@kernel.org, mtosatti@redhat.com, kvm@vger.kernel.org,
	linux-kernel@vger.kernel.org,
	Xiao Guangrong <guangrong.xiao@linux.intel.com>
Subject: [PATCH 15/15] KVM: VMX: fully implement guest MTRR virtualization
Date: Sat, 30 May 2015 18:59:26 +0800	[thread overview]
Message-ID: <1432983566-15773-16-git-send-email-guangrong.xiao@linux.intel.com> (raw)
In-Reply-To: <1432983566-15773-1-git-send-email-guangrong.xiao@linux.intel.com>

Currently guest MTRR is completely prohibited if cache snoop is supported on
IOMMU (!noncoherent_dma) and host does the emulation based on the knowledge
from host side, however, host side is not the good point to know
what the purpose of guest is. A good example is that pass-throughed VGA
frame buffer is not always UC as host expected

This patchset enables full MTRR virtualization and currently only works on
Intel EPT architecture

Signed-off-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
---
 arch/x86/include/asm/kvm_host.h |  2 +-
 arch/x86/kvm/mmu.c              |  3 +--
 arch/x86/kvm/mtrr.c             |  3 +--
 arch/x86/kvm/svm.c              |  2 +-
 arch/x86/kvm/vmx.c              | 28 ++++------------------------
 5 files changed, 8 insertions(+), 30 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 5be8f2e..b34de27 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -806,7 +806,7 @@ struct kvm_x86_ops {
 	void (*sync_pir_to_irr)(struct kvm_vcpu *vcpu);
 	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
 	int (*get_tdp_level)(void);
-	u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
+	u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn);
 	int (*get_lpage_level)(void);
 	bool (*rdtscp_supported)(void);
 	bool (*invpcid_supported)(void);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index c8c2a90..828fcd6 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2496,8 +2496,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	if (level > PT_PAGE_TABLE_LEVEL)
 		spte |= PT_PAGE_SIZE_MASK;
 	if (tdp_enabled)
-		spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn,
-			kvm_is_reserved_pfn(pfn));
+		spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn);
 
 	if (host_writable)
 		spte |= SPTE_HOST_WRITEABLE;
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index 703a66b..bf84218 100644
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -259,8 +259,7 @@ static void update_mtrr(struct kvm_vcpu *vcpu, u32 msr)
 	gfn_t start, end;
 	int index;
 
-	if (msr == MSR_IA32_CR_PAT || !tdp_enabled ||
-	      !kvm_arch_has_noncoherent_dma(vcpu->kvm))
+	if (msr == MSR_IA32_CR_PAT || !tdp_enabled)
 		return;
 
 	if (!mtrr_state->mtrr_enabled && msr != MSR_MTRRdefType)
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index b9f9e10..23dd78a 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -4075,7 +4075,7 @@ static bool svm_cpu_has_accelerated_tpr(void)
 	return false;
 }
 
-static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
+static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn)
 {
 	return 0;
 }
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index fe7a589..78b77be 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -8626,31 +8626,11 @@ static int get_ept_level(void)
 	return VMX_EPT_DEFAULT_GAW + 1;
 }
 
-static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
-{
-	u64 ret;
-
-	/* For VT-d and EPT combination
-	 * 1. MMIO: always map as UC
-	 * 2. EPT with VT-d:
-	 *   a. VT-d without snooping control feature: can't guarantee the
-	 *	result, try to trust guest.
-	 *   b. VT-d with snooping control feature: snooping control feature of
-	 *	VT-d engine can guarantee the cache correctness. Just set it
-	 *	to WB to keep consistent with host. So the same as item 3.
-	 * 3. EPT without VT-d: always map as WB and set IPAT=1 to keep
-	 *    consistent with host MTRR
-	 */
-	if (is_mmio)
-		ret = MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT;
-	else if (kvm_arch_has_noncoherent_dma(vcpu->kvm))
-		ret = kvm_mtrr_get_guest_memory_type(vcpu, gfn) <<
-		      VMX_EPT_MT_EPTE_SHIFT;
-	else
-		ret = (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT)
-			| VMX_EPT_IPAT_BIT;
+static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+	u8 type = kvm_mtrr_get_guest_memory_type(vcpu, gfn);
 
-	return ret;
+	return type << VMX_EPT_MT_EPTE_SHIFT;
 }
 
 static int vmx_get_lpage_level(void)
-- 
2.1.0


      parent reply	other threads:[~2015-05-30 11:01 UTC|newest]

Thread overview: 44+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-05-30 10:59 [PATCH 00/15] KVM: x86: fully implement vMTRR Xiao Guangrong
2015-05-30 10:58 ` Xiao Guangrong
2015-05-30 10:59 ` [PATCH 01/15] KVM: x86: move MTRR related code to a separate file Xiao Guangrong
2015-05-30 10:59 ` [PATCH 02/15] KVM: MTRR: handle MSR_MTRRcap in kvm_mtrr_get_msr Xiao Guangrong
2015-05-30 10:59 ` [PATCH 03/15] KVM: MTRR: remove mtrr_state.have_fixed Xiao Guangrong
2015-05-30 10:59 ` [PATCH 04/15] KVM: MTRR: exactly define the size of variable MTRRs Xiao Guangrong
2015-05-30 10:59 ` [PATCH 05/15] KVM: MTRR: clean up mtrr default type Xiao Guangrong
2015-06-01  9:11   ` Paolo Bonzini
2015-06-03  1:55     ` Xiao Guangrong
2015-06-09  0:35   ` David Matlack
2015-05-30 10:59 ` [PATCH 06/15] KVM: MTRR: do not split 64 bits MSR content Xiao Guangrong
2015-05-30 10:59 ` [PATCH 07/15] KVM: MTRR: improve kvm_mtrr_get_guest_memory_type Xiao Guangrong
2015-06-01  9:16   ` Paolo Bonzini
2015-06-03  2:12     ` Xiao Guangrong
2015-06-03  7:57       ` Paolo Bonzini
2015-05-30 10:59 ` [PATCH 08/15] KVM: MTRR: introduce fixed_mtrr_segment table Xiao Guangrong
2015-06-01  9:25   ` Paolo Bonzini
2015-06-03  2:29     ` Xiao Guangrong
2015-05-30 10:59 ` [PATCH 09/15] KVM: MTRR: introduce var_mtrr_range Xiao Guangrong
2015-06-09  0:36   ` David Matlack
2015-06-09  2:38     ` Xiao Guangrong
2015-05-30 10:59 ` [PATCH 10/15] KVM: MTRR: sort variable MTRRs Xiao Guangrong
2015-06-01  9:27   ` Paolo Bonzini
2015-06-03  2:31     ` Xiao Guangrong
2015-05-30 10:59 ` [PATCH 11/15] KVM: MTRR: introduce fixed_mtrr_addr_* functions Xiao Guangrong
2015-05-30 10:59 ` [PATCH 12/15] KVM: MTRR: introduce mtrr_for_each_mem_type Xiao Guangrong
2015-06-01  9:33   ` Paolo Bonzini
2015-06-01 14:26     ` Paolo Bonzini
2015-06-03  2:57       ` Xiao Guangrong
2015-06-03  2:40     ` Xiao Guangrong
2015-06-09  0:36   ` David Matlack
2015-06-09  2:45     ` Xiao Guangrong
2015-05-30 10:59 ` [PATCH 13/15] KVM: MTRR: simplify kvm_mtrr_get_guest_memory_type Xiao Guangrong
2015-05-30 10:59 ` [PATCH 14/15] KVM: MTRR: do not map huage page for non-consistent range Xiao Guangrong
2015-06-01  9:36   ` Paolo Bonzini
2015-06-01  9:38     ` Paolo Bonzini
2015-06-03  2:56     ` Xiao Guangrong
2015-06-03  7:55       ` Paolo Bonzini
2015-06-04  8:23         ` Xiao Guangrong
2015-06-04  8:26           ` Xiao Guangrong
2015-06-04  8:34             ` Paolo Bonzini
2015-06-04  8:36           ` Paolo Bonzini
2015-06-05  6:33             ` Xiao Guangrong
2015-05-30 10:59 ` Xiao Guangrong [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1432983566-15773-16-git-send-email-guangrong.xiao@linux.intel.com \
    --to=guangrong.xiao@linux.intel.com \
    --cc=gleb@kernel.org \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mtosatti@redhat.com \
    --cc=pbonzini@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).