Regards,
Anthony Liguori
Subject: [PATCH] KVM: Add paravirt MMU write support
Author: Anthony Liguori <[EMAIL PROTECTED]>
On at least AMD hardware, hypercall based manipulation of page table memory
is significantly faster than taking a page fault. Additionally, using
hypercalls to manipulation page table memory provides the infrastructure needed
to do lazy MMU updates.
Signed-off-by: Anthony Liguori <[EMAIL PROTECTED]>
diff --git a/arch/i386/kernel/kvm.c b/arch/i386/kernel/kvm.c
index bf77159..21133e4 100644
--- a/arch/i386/kernel/kvm.c
+++ b/arch/i386/kernel/kvm.c
@@ -25,6 +25,7 @@
#include <linux/kvm_para.h>
#include <linux/cpu.h>
#include <linux/mm.h>
+#include <asm/tlbflush.h>
#include <linux/clocksource.h>
#include <linux/workqueue.h>
@@ -54,6 +55,7 @@ struct kvm_paravirt_state
static DEFINE_PER_CPU(struct kvm_paravirt_state *, paravirt_state);
+static int do_mmu_write;
static int do_cr_read_caching;
static int do_nop_io_delay;
static int do_paravirt_clock;
@@ -197,6 +199,84 @@ static void kvm_write_cr4(unsigned long value)
kvm_write_cr(4, value);
}
+static void kvm_mmu_write(void *dest, const void *src, size_t size)
+{
+ const uint8_t *p = src;
+ u32 a1 = 0;
+
+ size >>= 2;
+ if (size == 2)
+ a1 = *(u32 *)&p[4];
+
+ kvm_hypercall(KVM_HYPERCALL_MMU_WRITE, (u32)dest, size, *(u32 *)p, a1);
+}
+
+/*
+ * We only need to hook operations that are MMU writes. We hook these so that
+ * we can use lazy MMU mode to batch these operations. We could probably
+ * improve the performance of the host code if we used some of the information
+ * here to simplify processing of batched writes.
+ */
+static void kvm_set_pte(pte_t *ptep, pte_t pte)
+{
+ kvm_mmu_write(ptep, &pte, sizeof(pte));
+}
+
+static void kvm_set_pte_at(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pte)
+{
+ kvm_mmu_write(ptep, &pte, sizeof(pte));
+}
+
+static void kvm_set_pte_atomic(pte_t *ptep, pte_t pte)
+{
+ kvm_mmu_write(ptep, &pte, sizeof(pte));
+}
+
+static void kvm_set_pte_present(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pte)
+{
+ kvm_mmu_write(ptep, &pte, sizeof(pte));
+}
+
+static void kvm_pte_clear(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep)
+{
+ pte_t pte = __pte(0);
+ kvm_mmu_write(ptep, &pte, sizeof(pte));
+}
+
+static void kvm_set_pmd(pmd_t *pmdp, pmd_t pmd)
+{
+ kvm_mmu_write(pmdp, &pmd, sizeof(pmd));
+}
+
+static void kvm_set_pud(pud_t *pudp, pud_t pud)
+{
+ kvm_mmu_write(pudp, &pud, sizeof(pud));
+}
+
+static void kvm_pmd_clear(pmd_t *pmdp)
+{
+ pmd_t pmd = __pmd(0);
+ kvm_mmu_write(pmdp, &pmd, sizeof(pmd));
+}
+
+static void kvm_flush_tlb(void)
+{
+ kvm_hypercall(KVM_HYPERCALL_FLUSH_TLB, 0, 0, 0, 0);
+}
+
+static void kvm_flush_tlb_single(unsigned long addr)
+{
+ kvm_hypercall(KVM_HYPERCALL_FLUSH_TLB_SINGLE, addr, 0, 0, 0);
+}
+
+static void kvm_release_pt(u32 pfn)
+{
+ kvm_hypercall(KVM_HYPERCALL_RELEASE_PT, pfn << PAGE_SHIFT, 0, 0, 0);
+}
+
static void paravirt_ops_setup(void)
{
paravirt_ops.name = "KVM";
@@ -225,6 +305,21 @@ static void paravirt_ops_setup(void)
paravirt_ops.read_cr4_safe = kvm_read_cr4;
}
+ if (do_mmu_write) {
+ paravirt_ops.set_pte = kvm_set_pte;
+ paravirt_ops.set_pte_at = kvm_set_pte_at;
+ paravirt_ops.set_pte_atomic = kvm_set_pte_atomic;
+ paravirt_ops.set_pte_present = kvm_set_pte_present;
+ paravirt_ops.pte_clear = kvm_pte_clear;
+ paravirt_ops.set_pmd = kvm_set_pmd;
+ paravirt_ops.pmd_clear = kvm_pmd_clear;
+ paravirt_ops.set_pud = kvm_set_pud;
+ paravirt_ops.flush_tlb_user = kvm_flush_tlb;
+ paravirt_ops.flush_tlb_single = kvm_flush_tlb_single;
+ paravirt_ops.release_pt = kvm_release_pt;
+ paravirt_ops.release_pd = kvm_release_pt;
+ }
+
paravirt_ops.paravirt_enabled = 1;
}
@@ -267,6 +362,9 @@ static int paravirt_initialize(void)
if ((edx & KVM_FEATURE_CR_READ_CACHE))
do_cr_read_caching = 1;
+ if ((edx & KVM_FEATURE_MMU_WRITE))
+ do_mmu_write = 1;
+
on_each_cpu(paravirt_activate, NULL, 0, 1);
return 0;
diff --git a/drivers/kvm/kvm.h b/drivers/kvm/kvm.h
index b08272b..9a7462a 100644
--- a/drivers/kvm/kvm.h
+++ b/drivers/kvm/kvm.h
@@ -538,6 +538,7 @@ void kvm_resched(struct kvm_vcpu *vcpu);
void kvm_load_guest_fpu(struct kvm_vcpu *vcpu);
void kvm_put_guest_fpu(struct kvm_vcpu *vcpu);
void kvm_flush_remote_tlbs(struct kvm *kvm);
+void mmu_unshadow(struct kvm_vcpu *vcpu, gfn_t gfn);
int kvm_read_guest(struct kvm_vcpu *vcpu,
gva_t addr,
diff --git a/drivers/kvm/kvm_main.c b/drivers/kvm/kvm_main.c
index 35d73b8..91aec56 100644
--- a/drivers/kvm/kvm_main.c
+++ b/drivers/kvm/kvm_main.c
@@ -95,7 +95,8 @@ struct vfsmount *kvmfs_mnt;
#define KVM_PARAVIRT_FEATURES \
(KVM_FEATURE_VMCA | KVM_FEATURE_NOP_IO_DELAY | \
- KVM_FEATURE_PARAVIRT_CLOCK | KVM_FEATURE_CR_READ_CACHE)
+ KVM_FEATURE_PARAVIRT_CLOCK | KVM_FEATURE_CR_READ_CACHE | \
+ KVM_FEATURE_MMU_WRITE)
#define KVM_MSR_SET_VMCA 0x87655678
@@ -1348,6 +1349,28 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu)
}
EXPORT_SYMBOL_GPL(kvm_emulate_halt);
+static int kvm_hypercall_mmu_write(struct kvm_vcpu *vcpu, gva_t addr,
+ unsigned long size, unsigned long a0,
+ unsigned long a1)
+{
+ gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, addr);
+ u64 value;
+
+ if (gpa == UNMAPPED_GVA)
+ return -KVM_EFAULT;
+ if (size == 1) {
+ if (!emulator_write_phys(vcpu, gpa, &a0, sizeof(a0)))
+ return -KVM_EFAULT;
+ } else if (size == 2) {
+ value = (u64)a1 << 32 | a0;
+ if (!emulator_write_phys(vcpu, gpa, &value, sizeof(value)))
+ return -KVM_EFAULT;
+ } else
+ return -KVM_E2BIG;
+
+ return 0;
+}
+
static int kvm_hypercall_update_time(struct kvm_vcpu *vcpu)
{
struct kvm_vmca *vmca;
@@ -1368,13 +1391,40 @@ static int kvm_hypercall_update_time(struct kvm_vcpu *vcpu)
return 0;
}
+static int kvm_hypercall_flush_tlb(struct kvm_vcpu *vcpu)
+{
+ kvm_arch_ops->tlb_flush(vcpu);
+ return 0;
+}
+
+static int kvm_hypercall_flush_tlb_single(struct kvm_vcpu *vcpu, gva_t addr)
+{
+ if (kvm_arch_ops->invlpg)
+ kvm_arch_ops->invlpg(vcpu, addr);
+ return 0;
+}
+
+static int kvm_hypercall_release_pt(struct kvm_vcpu *vcpu, gpa_t addr)
+{
+ mmu_unshadow(vcpu, addr >> PAGE_SHIFT);
+ return 0;
+}
+
static int dispatch_hypercall(struct kvm_vcpu *vcpu, unsigned long nr,
unsigned long p1, unsigned long p2,
unsigned long p3, unsigned long p4)
{
switch (nr) {
+ case KVM_HYPERCALL_MMU_WRITE:
+ return kvm_hypercall_mmu_write(vcpu, p1, p2, p3, p4);
case KVM_HYPERCALL_UPDATE_TIME:
return kvm_hypercall_update_time(vcpu);
+ case KVM_HYPERCALL_FLUSH_TLB:
+ return kvm_hypercall_flush_tlb(vcpu);
+ case KVM_HYPERCALL_FLUSH_TLB_SINGLE:
+ return kvm_hypercall_flush_tlb_single(vcpu, p1);
+ case KVM_HYPERCALL_RELEASE_PT:
+ return kvm_hypercall_release_pt(vcpu, p1);
}
return -KVM_ENOSYS;
}
diff --git a/drivers/kvm/mmu.c b/drivers/kvm/mmu.c
index ad50cfd..1581286 100644
--- a/drivers/kvm/mmu.c
+++ b/drivers/kvm/mmu.c
@@ -728,7 +728,7 @@ static int kvm_mmu_unprotect_page(struct kvm_vcpu *vcpu, gfn_t gfn)
return r;
}
-static void mmu_unshadow(struct kvm_vcpu *vcpu, gfn_t gfn)
+void mmu_unshadow(struct kvm_vcpu *vcpu, gfn_t gfn)
{
struct kvm_mmu_page *page;
diff --git a/include/linux/kvm_para.h b/include/linux/kvm_para.h
index d4aa7e8..560de6a 100644
--- a/include/linux/kvm_para.h
+++ b/include/linux/kvm_para.h
@@ -26,6 +26,7 @@ static int __init kvm_guest_init(void)
#define KVM_FEATURE_NOP_IO_DELAY (1UL << 1)
#define KVM_FEATURE_PARAVIRT_CLOCK (1UL << 2)
#define KVM_FEATURE_CR_READ_CACHE (1UL << 3)
+#define KVM_FEATURE_MMU_WRITE (1UL << 4)
struct kvm_vmca
{
@@ -46,7 +47,13 @@ struct kvm_vmca
#define KVM_ENOSYS ENOSYS
#define KVM_EINVAL EINVAL
+#define KVM_EFAULT EFAULT
+#define KVM_E2BIG E2BIG
#define KVM_HYPERCALL_UPDATE_TIME 0
+#define KVM_HYPERCALL_MMU_WRITE 1
+#define KVM_HYPERCALL_FLUSH_TLB 2
+#define KVM_HYPERCALL_FLUSH_TLB_SINGLE 3
+#define KVM_HYPERCALL_RELEASE_PT 4
#endif
-------------------------------------------------------------------------
This SF.net email is sponsored by DB2 Express
Download DB2 Express C - the FREE version of DB2 express and take
control of your XML. No limits. Just data. Click to get it now.
http://sourceforge.net/powerbar/db2/
_______________________________________________
kvm-devel mailing list
kvm-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/kvm-devel