Looking for sponsors for Outreach Program for Women 2014 December-March
Dear QEMU, libvirt, and KVM communities, Thanks to mentors from our communities, we have assembled project ideas for Outreach Program for Women 2014 December-March (with more on the way!): http://qemu-project.org/Outreach_Program_for_Women_2014_DecemberMarch OPW is a program that allows women to work full-time for 12 weeks on open source projects. QEMU, the Linux kernel, and other organizations have participated successfully in the past. Outreach Program for Women participants are funded by sponsors - usually companies or organizations that wish to see the open source community grow and increase inclusion of women in open source. We are now looking for funding to make OPW December-March possible. Maybe your company is interested in becoming a sponsor? All the details are explained here: https://wiki.gnome.org/OutreachProgramForWomen/Admin/InfoForOrgs Thanks, Stefan -- To unsubscribe from this list: send the line unsubscribe kvm in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: [PATCH RFC 2/2] vhost: support urgent descriptors
Il 19/09/2014 09:10, Jason Wang ha scritto:
- if (!vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX)) {
+ if (vq-urgent || !vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX)) {
So the urgent descriptor only work when event index was not enabled?
This seems suboptimal, we may still want to benefit from event index
even if urgent descriptor is used. Looks like we need return true here
when vq-urgent is true?
Its ||, not .
Without event index, all descriptors are treated as urgent.
Paolo
--
To unsubscribe from this list: send the line unsubscribe kvm in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH v7 2/9] kvm: Remove ept_identity_pagetable from struct kvm_arch.
kvm_arch-ept_identity_pagetable holds the ept identity pagetable page. But
it is never used to refer to the page at all.
In vcpu initialization, it indicates two things:
1. indicates if ept page is allocated
2. indicates if a memory slot for identity page is initialized
Actually, kvm_arch-ept_identity_pagetable_done is enough to tell if the ept
identity pagetable is initialized. So we can remove ept_identity_pagetable.
NOTE: In the original code, ept identity pagetable page is pinned in memroy.
As a result, it cannot be migrated/hot-removed. After this patch, since
kvm_arch-ept_identity_pagetable is removed, ept identity pagetable page
is no longer pinned in memory. And it can be migrated/hot-removed.
Signed-off-by: Tang Chen tangc...@cn.fujitsu.com
Reviewed-by: Gleb Natapov g...@kernel.org
---
arch/x86/include/asm/kvm_host.h | 1 -
arch/x86/kvm/vmx.c | 47 +++--
arch/x86/kvm/x86.c | 2 --
3 files changed, 22 insertions(+), 28 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 7c492ed..35171c7 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -580,7 +580,6 @@ struct kvm_arch {
gpa_t wall_clock;
- struct page *ept_identity_pagetable;
bool ept_identity_pagetable_done;
gpa_t ept_identity_map_addr;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 4b80ead..4fb84ad 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -743,6 +743,7 @@ static u32 vmx_segment_access_rights(struct kvm_segment
*var);
static void vmx_sync_pir_to_irr_dummy(struct kvm_vcpu *vcpu);
static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx);
static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx);
+static int alloc_identity_pagetable(struct kvm *kvm);
static DEFINE_PER_CPU(struct vmcs *, vmxarea);
static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
@@ -3938,21 +3939,27 @@ out:
static int init_rmode_identity_map(struct kvm *kvm)
{
- int i, idx, r, ret;
+ int i, idx, r, ret = 0;
pfn_t identity_map_pfn;
u32 tmp;
if (!enable_ept)
return 1;
- if (unlikely(!kvm-arch.ept_identity_pagetable)) {
- printk(KERN_ERR EPT: identity-mapping pagetable
- haven't been allocated!\n);
- return 0;
+
+ /* Protect kvm-arch.ept_identity_pagetable_done. */
+ mutex_lock(kvm-slots_lock);
+
+ if (likely(kvm-arch.ept_identity_pagetable_done)) {
+ ret = 1;
+ goto out2;
}
- if (likely(kvm-arch.ept_identity_pagetable_done))
- return 1;
- ret = 0;
+
identity_map_pfn = kvm-arch.ept_identity_map_addr PAGE_SHIFT;
+
+ r = alloc_identity_pagetable(kvm);
+ if (r)
+ goto out2;
+
idx = srcu_read_lock(kvm-srcu);
r = kvm_clear_guest_page(kvm, identity_map_pfn, 0, PAGE_SIZE);
if (r 0)
@@ -3970,6 +3977,9 @@ static int init_rmode_identity_map(struct kvm *kvm)
ret = 1;
out:
srcu_read_unlock(kvm-srcu, idx);
+
+out2:
+ mutex_unlock(kvm-slots_lock);
return ret;
}
@@ -4019,31 +4029,20 @@ out:
static int alloc_identity_pagetable(struct kvm *kvm)
{
- struct page *page;
+ /* Called with kvm-slots_lock held. */
+
struct kvm_userspace_memory_region kvm_userspace_mem;
int r = 0;
- mutex_lock(kvm-slots_lock);
- if (kvm-arch.ept_identity_pagetable)
- goto out;
+ BUG_ON(kvm-arch.ept_identity_pagetable_done);
+
kvm_userspace_mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT;
kvm_userspace_mem.flags = 0;
kvm_userspace_mem.guest_phys_addr =
kvm-arch.ept_identity_map_addr;
kvm_userspace_mem.memory_size = PAGE_SIZE;
r = __kvm_set_memory_region(kvm, kvm_userspace_mem);
- if (r)
- goto out;
-
- page = gfn_to_page(kvm, kvm-arch.ept_identity_map_addr PAGE_SHIFT);
- if (is_error_page(page)) {
- r = -EFAULT;
- goto out;
- }
- kvm-arch.ept_identity_pagetable = page;
-out:
- mutex_unlock(kvm-slots_lock);
return r;
}
@@ -7643,8 +7642,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm,
unsigned int id)
kvm-arch.ept_identity_map_addr =
VMX_EPT_IDENTITY_PAGETABLE_ADDR;
err = -ENOMEM;
- if (alloc_identity_pagetable(kvm) != 0)
- goto free_vmcs;
if (!init_rmode_identity_map(kvm))
goto free_vmcs;
}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8f1e22d..e05bd58 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7239,8 +7239,6 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
kvm_free_vcpus(kvm);
if
[PATCH v7 8/9] kvm, mem-hotplug: Add arch specific mmu notifier to handle apic access migration.
We are handling L1 and L2 share one apic access page situation when migrating
apic access page. We should do some handling when migration happens in the
following situations:
1) when L0 is running: Update L1's vmcs in the next L0-L1 entry and L2's
vmcs in the next L1-L2 entry.
2) when L1 is running: Force a L1-L0 exit, update L1's vmcs in the next
L0-L1 entry and L2's vmcs in the next L1-L2 entry.
3) when L2 is running: Force a L2-L0 exit, update L2's vmcs in the next
L0-L2 entry and L1's vmcs in the next L2-L1 exit.
This patch force a L1-L0 exit or L2-L0 exit when shared apic access page is
migrated using mmu notifier. Since apic access page is only used on intel x86,
this is arch specific code.
Signed-off-by: Tang Chen tangc...@cn.fujitsu.com
---
arch/x86/kvm/x86.c | 11 +++
include/linux/kvm_host.h | 14 +-
virt/kvm/kvm_main.c | 3 +++
3 files changed, 27 insertions(+), 1 deletion(-)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2ae2dc7..7dd4179 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6011,6 +6011,17 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu
*vcpu)
}
EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page);
+void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
+ unsigned long address)
+{
+ /*
+* The physical address of apic access page is stored in VMCS.
+* Update it when it becomes invalid.
+*/
+ if (address == gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE PAGE_SHIFT))
+ kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD);
+}
+
/*
* Returns 1 to let __vcpu_run() continue the guest execution loop without
* exiting to the userspace. Otherwise, the value will be returned to the
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 73de13c..b6e4d38 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -917,7 +917,19 @@ static inline int mmu_notifier_retry(struct kvm *kvm,
unsigned long mmu_seq)
return 1;
return 0;
}
-#endif
+
+#ifdef _ASM_X86_KVM_HOST_H
+void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
+ unsigned long address);
+#else /* _ASM_X86_KVM_HOST_H */
+inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
+ unsigned long address)
+{
+ return;
+}
+#endif /* _ASM_X86_KVM_HOST_H */
+
+#endif /* CONFIG_MMU_NOTIFIER KVM_ARCH_WANT_MMU_NOTIFIER */
#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 0f8b6f6..5427973d 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -295,6 +295,9 @@ static void kvm_mmu_notifier_invalidate_page(struct
mmu_notifier *mn,
kvm_flush_remote_tlbs(kvm);
spin_unlock(kvm-mmu_lock);
+
+ kvm_arch_mmu_notifier_invalidate_page(kvm, address);
+
srcu_read_unlock(kvm-srcu, idx);
}
--
1.8.3.1
--
To unsubscribe from this list: send the line unsubscribe kvm in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH v7 7/9] kvm, mem-hotplug: Reload L1's apic access page on migration when L2 is running.
We are handling L1 and L2 share one apic access page situation when migrating
apic access page. We should do some handling when migration happens in the
following situations:
1) when L0 is running: Update L1's vmcs in the next L0-L1 entry and L2's
vmcs in the next L1-L2 entry.
2) when L1 is running: Force a L1-L0 exit, update L1's vmcs in the next
L0-L1 entry and L2's vmcs in the next L1-L2 entry.
3) when L2 is running: Force a L2-L0 exit, update L2's vmcs in the next
L0-L2 entry and L1's vmcs in the next L2-L1 exit.
This patch handles 3).
In L0-L2 entry, L2's vmcs will be updated in prepare_vmcs02() called by
nested_vm_run(). So we need to do nothing.
In L2-L1 exit, this patch requests apic access page reload in L2-L1 vmexit.
Signed-off-by: Tang Chen tangc...@cn.fujitsu.com
---
arch/x86/include/asm/kvm_host.h | 1 +
arch/x86/kvm/vmx.c | 6 ++
arch/x86/kvm/x86.c | 3 ++-
3 files changed, 9 insertions(+), 1 deletion(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 56156eb..1a8317e 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1047,6 +1047,7 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
void kvm_vcpu_reset(struct kvm_vcpu *vcpu);
+void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu);
void kvm_define_shared_msr(unsigned index, u32 msr);
void kvm_set_shared_msr(unsigned index, u64 val, u64 mask);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c8e90ec..baac78a 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -8803,6 +8803,12 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32
exit_reason,
}
/*
+* We are now running in L2, mmu_notifier will force to reload the
+* page's hpa for L2 vmcs. Need to reload it for L1 before entering L1.
+*/
+ kvm_vcpu_reload_apic_access_page(vcpu);
+
+ /*
* Exiting from L2 to L1, we're now back to L1 which thinks it just
* finished a VMLAUNCH or VMRESUME instruction, so we need to set the
* success or failure flag accordingly.
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index fc54fa6..2ae2dc7 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5989,7 +5989,7 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
kvm_apic_update_tmr(vcpu, tmr);
}
-static void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
+void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
{
/*
* Only APIC access page shared by L1 and L2 vm is handled. The APIC
@@ -6009,6 +6009,7 @@ static void kvm_vcpu_reload_apic_access_page(struct
kvm_vcpu *vcpu)
page_to_phys(vcpu-kvm-arch.apic_access_page));
}
}
+EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page);
/*
* Returns 1 to let __vcpu_run() continue the guest execution loop without
--
1.8.3.1
--
To unsubscribe from this list: send the line unsubscribe kvm in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH v7 9/9] kvm, mem-hotplug: Unpin and remove kvm_arch-apic_access_page.
To make apic access page migratable, we do not pin it in memory now.
When it is migrated, we should reload its physical address for all
vmcses. But when we tried to do this, all vcpu will access
kvm_arch-apic_access_page without any locking. This is not safe.
Actually, we do not need kvm_arch-apic_access_page anymore. Since
apic access page is not pinned in memory now, we can remove
kvm_arch-apic_access_page. When we need to write its physical address
into vmcs, use gfn_to_page() to get its page struct, which will also
pin it. And unpin it after then.
Suggested-by: Gleb Natapov g...@kernel.org
Signed-off-by: Tang Chen tangc...@cn.fujitsu.com
---
arch/x86/include/asm/kvm_host.h | 2 +-
arch/x86/kvm/vmx.c | 15 +--
arch/x86/kvm/x86.c | 16 +++-
3 files changed, 21 insertions(+), 12 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 1a8317e..9fb3d4c 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -576,7 +576,7 @@ struct kvm_arch {
struct kvm_apic_map *apic_map;
unsigned int tss_addr;
- struct page *apic_access_page;
+ bool apic_access_page_done;
gpa_t wall_clock;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index baac78a..12f0715 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -4002,7 +4002,7 @@ static int alloc_apic_access_page(struct kvm *kvm)
int r = 0;
mutex_lock(kvm-slots_lock);
- if (kvm-arch.apic_access_page)
+ if (kvm-arch.apic_access_page_done)
goto out;
kvm_userspace_mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT;
kvm_userspace_mem.flags = 0;
@@ -4018,7 +4018,12 @@ static int alloc_apic_access_page(struct kvm *kvm)
goto out;
}
- kvm-arch.apic_access_page = page;
+ /*
+* Do not pin apic access page in memory so that memory hotplug
+* process is able to migrate it.
+*/
+ put_page(page);
+ kvm-arch.apic_access_page_done = true;
out:
mutex_unlock(kvm-slots_lock);
return r;
@@ -4534,8 +4539,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu)
}
if (vm_need_virtualize_apic_accesses(vmx-vcpu.kvm))
- vmcs_write64(APIC_ACCESS_ADDR,
-
page_to_phys(vmx-vcpu.kvm-arch.apic_access_page));
+ kvm_vcpu_reload_apic_access_page(vcpu);
if (vmx_vm_has_apicv(vcpu-kvm))
memset(vmx-pi_desc, 0, sizeof(struct pi_desc));
@@ -8003,8 +8007,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct
vmcs12 *vmcs12)
} else if (vm_need_virtualize_apic_accesses(vmx-vcpu.kvm)) {
exec_control |=
SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
- vmcs_write64(APIC_ACCESS_ADDR,
- page_to_phys(vcpu-kvm-arch.apic_access_page));
+ kvm_vcpu_reload_apic_access_page(vcpu);
}
vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 7dd4179..996af6e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5991,6 +5991,8 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
{
+ struct page *page = NULL;
+
/*
* Only APIC access page shared by L1 and L2 vm is handled. The APIC
* access page prepared by L1 for L2's execution is still pinned in
@@ -6003,10 +6005,16 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu
*vcpu)
* migrated, GUP will wait till the migrate entry is replaced
* with the new pte entry pointing to the new page.
*/
- vcpu-kvm-arch.apic_access_page = gfn_to_page(vcpu-kvm,
- APIC_DEFAULT_PHYS_BASE PAGE_SHIFT);
+ page = gfn_to_page(vcpu-kvm,
+ APIC_DEFAULT_PHYS_BASE PAGE_SHIFT);
kvm_x86_ops-set_apic_access_page_addr(vcpu-kvm,
- page_to_phys(vcpu-kvm-arch.apic_access_page));
+ page_to_phys(page));
+
+ /*
+* Do not pin apic access page in memory so that memory hotplug
+* process is able to migrate it.
+*/
+ put_page(page);
}
}
EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page);
@@ -7272,8 +7280,6 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
kfree(kvm-arch.vpic);
kfree(kvm-arch.vioapic);
kvm_free_vcpus(kvm);
- if (kvm-arch.apic_access_page)
- put_page(kvm-arch.apic_access_page);
kfree(rcu_dereference_check(kvm-arch.apic_map, 1));
}
--
1.8.3.1
--
To unsubscribe from this
[PATCH v7 5/9] kvm, mem-hotplug: Reload L1's apic access page in vcpu_enter_guest().
We are handling L1 and L2 share one apic access page situation when migrating
apic access page. We should do some handling when migration happens in the
following situations:
1) when L0 is running: Update L1's vmcs in the next L0-L1 entry and L2's
vmcs in the next L1-L2 entry.
2) when L1 is running: Force a L1-L0 exit, update L1's vmcs in the next
L0-L1 entry and L2's vmcs in the next L1-L2 entry.
3) when L2 is running: Force a L2-L0 exit, update L2's vmcs in the next
L0-L2 entry and L1's vmcs in the next L2-L1 exit.
This patch handles 1) and 2) by making a new vcpu request named
KVM_REQ_APIC_PAGE_RELOAD
to reload apic access page in L0-L1 entry.
Since we don't handle L1 ans L2 have separate apic access pages situation,
when we update vmcs, we need to check if we are in L2 and if L2's secondary
exec virtualzed apic accesses is enabled.
Signed-off-by: Tang Chen tangc...@cn.fujitsu.com
---
arch/x86/include/asm/kvm_host.h | 1 +
arch/x86/kvm/svm.c | 6 ++
arch/x86/kvm/vmx.c | 6 ++
arch/x86/kvm/x86.c | 23 +++
include/linux/kvm_host.h| 1 +
5 files changed, 37 insertions(+)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 69fe032..56156eb 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -740,6 +740,7 @@ struct kvm_x86_ops {
void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
void (*set_virtual_x2apic_mode)(struct kvm_vcpu *vcpu, bool set);
bool (*has_secondary_apic_access)(struct kvm_vcpu *vcpu);
+ void (*set_apic_access_page_addr)(struct kvm *kvm, hpa_t hpa);
void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
void (*sync_pir_to_irr)(struct kvm_vcpu *vcpu);
int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 9c8ae32..99378d7 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -3624,6 +3624,11 @@ static bool svm_has_secondary_apic_access(struct
kvm_vcpu *vcpu)
return false;
}
+static void svm_set_apic_access_page_addr(struct kvm *kvm, hpa_t hpa)
+{
+ return;
+}
+
static int svm_vm_has_apicv(struct kvm *kvm)
{
return 0;
@@ -4379,6 +4384,7 @@ static struct kvm_x86_ops svm_x86_ops = {
.update_cr8_intercept = update_cr8_intercept,
.set_virtual_x2apic_mode = svm_set_virtual_x2apic_mode,
.has_secondary_apic_access = svm_has_secondary_apic_access,
+ .set_apic_access_page_addr = svm_set_apic_access_page_addr,
.vm_has_apicv = svm_vm_has_apicv,
.load_eoi_exitmap = svm_load_eoi_exitmap,
.hwapic_isr_update = svm_hwapic_isr_update,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 0b541d9..c8e90ec 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -7098,6 +7098,11 @@ static bool vmx_has_secondary_apic_access(struct
kvm_vcpu *vcpu)
SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
}
+static void vmx_set_apic_access_page_addr(struct kvm *kvm, hpa_t hpa)
+{
+ vmcs_write64(APIC_ACCESS_ADDR, hpa);
+}
+
static void vmx_hwapic_isr_update(struct kvm *kvm, int isr)
{
u16 status;
@@ -8918,6 +8923,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
.update_cr8_intercept = update_cr8_intercept,
.set_virtual_x2apic_mode = vmx_set_virtual_x2apic_mode,
.has_secondary_apic_access = vmx_has_secondary_apic_access,
+ .set_apic_access_page_addr = vmx_set_apic_access_page_addr,
.vm_has_apicv = vmx_vm_has_apicv,
.load_eoi_exitmap = vmx_load_eoi_exitmap,
.hwapic_irr_update = vmx_hwapic_irr_update,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e05bd58..fc54fa6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5989,6 +5989,27 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
kvm_apic_update_tmr(vcpu, tmr);
}
+static void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
+{
+ /*
+* Only APIC access page shared by L1 and L2 vm is handled. The APIC
+* access page prepared by L1 for L2's execution is still pinned in
+* memory, and it cannot be migrated.
+*/
+ if (!is_guest_mode(vcpu) ||
+ !kvm_x86_ops-has_secondary_apic_access(vcpu)) {
+ /*
+* APIC access page could be migrated. When the page is being
+* migrated, GUP will wait till the migrate entry is replaced
+* with the new pte entry pointing to the new page.
+*/
+ vcpu-kvm-arch.apic_access_page = gfn_to_page(vcpu-kvm,
+ APIC_DEFAULT_PHYS_BASE PAGE_SHIFT);
+ kvm_x86_ops-set_apic_access_page_addr(vcpu-kvm,
+ page_to_phys(vcpu-kvm-arch.apic_access_page));
+ }
+}
+
/*
* Returns 1 to let __vcpu_run() continue
[PATCH v7 6/9] kvm: Rename make_all_cpus_request() to kvm_make_all_cpus_request() and make it non-static.
Since different architectures need different handling, we will add some arch
specific
code later. The code may need to make cpu requests outside kvm_main.c, so make
it
non-static and rename it to kvm_make_all_cpus_request().
Signed-off-by: Tang Chen tangc...@cn.fujitsu.com
---
include/linux/kvm_host.h | 1 +
virt/kvm/kvm_main.c | 10 +-
2 files changed, 6 insertions(+), 5 deletions(-)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index c23236a..73de13c 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -580,6 +580,7 @@ void kvm_flush_remote_tlbs(struct kvm *kvm);
void kvm_reload_remote_mmus(struct kvm *kvm);
void kvm_make_mclock_inprogress_request(struct kvm *kvm);
void kvm_make_scan_ioapic_request(struct kvm *kvm);
+bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req);
long kvm_arch_dev_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 33712fb..0f8b6f6 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -152,7 +152,7 @@ static void ack_flush(void *_completed)
{
}
-static bool make_all_cpus_request(struct kvm *kvm, unsigned int req)
+bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req)
{
int i, cpu, me;
cpumask_var_t cpus;
@@ -189,7 +189,7 @@ void kvm_flush_remote_tlbs(struct kvm *kvm)
long dirty_count = kvm-tlbs_dirty;
smp_mb();
- if (make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH))
+ if (kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH))
++kvm-stat.remote_tlb_flush;
cmpxchg(kvm-tlbs_dirty, dirty_count, 0);
}
@@ -197,17 +197,17 @@ EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs);
void kvm_reload_remote_mmus(struct kvm *kvm)
{
- make_all_cpus_request(kvm, KVM_REQ_MMU_RELOAD);
+ kvm_make_all_cpus_request(kvm, KVM_REQ_MMU_RELOAD);
}
void kvm_make_mclock_inprogress_request(struct kvm *kvm)
{
- make_all_cpus_request(kvm, KVM_REQ_MCLOCK_INPROGRESS);
+ kvm_make_all_cpus_request(kvm, KVM_REQ_MCLOCK_INPROGRESS);
}
void kvm_make_scan_ioapic_request(struct kvm *kvm)
{
- make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC);
+ kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC);
}
int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
--
1.8.3.1
--
To unsubscribe from this list: send the line unsubscribe kvm in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH v7 4/9] kvm: Add interface to check if secondary exec virtualzed apic accesses is enabled.
We wants to migrate apic access page pinned by guest (L1 and L2) to make memory
hotplug available.
There are two situations need to be handled for apic access page used by L2 vm:
1. L1 prepares a separate apic access page for L2.
L2 pins a lot of pages in memory. Even if we can migrate apic access page,
memory hotplug is not available when L2 is running. So do not handle this
now. Migrate apic access page only.
2. L1 and L2 share one apic access page.
Since we will migrate L1's apic access page, we should do some handling when
migration happens in the following situations:
1) when L0 is running: Update L1's vmcs in the next L0-L1 entry and L2's
vmcs in the next L1-L2 entry.
2) when L1 is running: Force a L1-L0 exit, update L1's vmcs in the next
L0-L1 entry and L2's vmcs in the next L1-L2 entry.
3) when L2 is running: Force a L2-L0 exit, update L2's vmcs in the next
L0-L2 entry and L1's vmcs in the next L2-L1 exit.
Since we don't handle L1 ans L2 have separate apic access pages situation,
when we update vmcs, we need to check if we are in L2 and if L2's secondary
exec virtualzed apic accesses is enabled.
This patch adds an interface to check if L2's secondary exec virtualzed apic
accesses is enabled, because vmx cannot be accessed outside vmx.c.
Signed-off-by: Tang Chen tangc...@cn.fujitsu.com
---
arch/x86/include/asm/kvm_host.h | 1 +
arch/x86/kvm/svm.c | 6 ++
arch/x86/kvm/vmx.c | 9 +
3 files changed, 16 insertions(+)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 35171c7..69fe032 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -739,6 +739,7 @@ struct kvm_x86_ops {
void (*hwapic_isr_update)(struct kvm *kvm, int isr);
void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
void (*set_virtual_x2apic_mode)(struct kvm_vcpu *vcpu, bool set);
+ bool (*has_secondary_apic_access)(struct kvm_vcpu *vcpu);
void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
void (*sync_pir_to_irr)(struct kvm_vcpu *vcpu);
int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 1d941ad..9c8ae32 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -3619,6 +3619,11 @@ static void svm_set_virtual_x2apic_mode(struct kvm_vcpu
*vcpu, bool set)
return;
}
+static bool svm_has_secondary_apic_access(struct kvm_vcpu *vcpu)
+{
+ return false;
+}
+
static int svm_vm_has_apicv(struct kvm *kvm)
{
return 0;
@@ -4373,6 +4378,7 @@ static struct kvm_x86_ops svm_x86_ops = {
.enable_irq_window = enable_irq_window,
.update_cr8_intercept = update_cr8_intercept,
.set_virtual_x2apic_mode = svm_set_virtual_x2apic_mode,
+ .has_secondary_apic_access = svm_has_secondary_apic_access,
.vm_has_apicv = svm_vm_has_apicv,
.load_eoi_exitmap = svm_load_eoi_exitmap,
.hwapic_isr_update = svm_hwapic_isr_update,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 72a0470..0b541d9 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -7090,6 +7090,14 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu
*vcpu, bool set)
vmx_set_msr_bitmap(vcpu);
}
+static bool vmx_has_secondary_apic_access(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+ return (vmx-nested.current_vmcs12-secondary_vm_exec_control
+ SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
+}
+
static void vmx_hwapic_isr_update(struct kvm *kvm, int isr)
{
u16 status;
@@ -8909,6 +8917,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
.enable_irq_window = enable_irq_window,
.update_cr8_intercept = update_cr8_intercept,
.set_virtual_x2apic_mode = vmx_set_virtual_x2apic_mode,
+ .has_secondary_apic_access = vmx_has_secondary_apic_access,
.vm_has_apicv = vmx_vm_has_apicv,
.load_eoi_exitmap = vmx_load_eoi_exitmap,
.hwapic_irr_update = vmx_hwapic_irr_update,
--
1.8.3.1
--
To unsubscribe from this list: send the line unsubscribe kvm in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH v7 0/9] kvm, mem-hotplug: Do not pin ept identity pagetable and apic access page.
ept identity pagetable and apic access page in kvm are pinned in memory. As a result, they cannot be migrated/hot-removed. But actually they don't need to be pinned in memory. [For ept identity page] Just do not pin it. When it is migrated, guest will be able to find the new page in the next ept violation. [For apic access page] The hpa of apic access page is stored in VMCS APIC_ACCESS_ADDR pointer. When apic access page is migrated, we update VMCS APIC_ACCESS_ADDR pointer for each vcpu in addition. This patch-set is based on Linux 3.17.0-rc5. NOTE: Tested with -cpu xxx,-x2apic option. But since nested vm pins some other pages in memory, if user uses nested vm, memory hot-remove will not work. Change log v6 - v7: 1. Patch 1/9~3/9 are applied to kvm/queue by Paolo Bonzini pbonz...@redhat.com. Just resend them, no changes. 2. In the new patch 4/9, add a new interface to check if secondary exec virtualized apic access is enabled. 3. In new patch 6/9, rename make_all_cpus_request() to kvm_make_all_cpus_request() and make it non-static so that we can use it in other patches. 4. In new patch 8/9, add arch specific function to make apic access page reload request in mmu notifier. Tang Chen (9): kvm: Use APIC_DEFAULT_PHYS_BASE macro as the apic access page address. kvm: Remove ept_identity_pagetable from struct kvm_arch. kvm: Make init_rmode_identity_map() return 0 on success. kvm: Add interface to check if secondary exec virtualzed apic accesses is enabled. kvm, mem-hotplug: Reload L1's apic access page in vcpu_enter_guest(). kvm: Rename make_all_cpus_request() to kvm_make_all_cpus_request() and make it non-static. kvm, mem-hotplug: Reload L1's apic access page on migration when L2 is running. kvm, mem-hotplug: Add arch specific mmu notifier to handle apic access migration. kvm, mem-hotplug: Unpin and remove kvm_arch-apic_access_page. arch/x86/include/asm/kvm_host.h | 6 ++- arch/x86/kvm/svm.c | 15 +- arch/x86/kvm/vmx.c | 104 arch/x86/kvm/x86.c | 47 -- include/linux/kvm_host.h| 16 ++- virt/kvm/kvm_main.c | 13 +++-- 6 files changed, 146 insertions(+), 55 deletions(-) -- 1.8.3.1 -- To unsubscribe from this list: send the line unsubscribe kvm in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH v7 3/9] kvm: Make init_rmode_identity_map() return 0 on success.
In init_rmode_identity_map(), there two variables indicating the return
value, r and ret, and it return 0 on error, 1 on success. The function
is only called by vmx_create_vcpu(), and r is redundant.
This patch removes the redundant variable r, and make init_rmode_identity_map()
return 0 on success, -errno on failure.
Signed-off-by: Tang Chen tangc...@cn.fujitsu.com
---
arch/x86/kvm/vmx.c | 31 +++
1 file changed, 15 insertions(+), 16 deletions(-)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 4fb84ad..72a0470 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3939,45 +3939,42 @@ out:
static int init_rmode_identity_map(struct kvm *kvm)
{
- int i, idx, r, ret = 0;
+ int i, idx, ret = 0;
pfn_t identity_map_pfn;
u32 tmp;
if (!enable_ept)
- return 1;
+ return 0;
/* Protect kvm-arch.ept_identity_pagetable_done. */
mutex_lock(kvm-slots_lock);
- if (likely(kvm-arch.ept_identity_pagetable_done)) {
- ret = 1;
+ if (likely(kvm-arch.ept_identity_pagetable_done))
goto out2;
- }
identity_map_pfn = kvm-arch.ept_identity_map_addr PAGE_SHIFT;
- r = alloc_identity_pagetable(kvm);
- if (r)
+ ret = alloc_identity_pagetable(kvm);
+ if (ret)
goto out2;
idx = srcu_read_lock(kvm-srcu);
- r = kvm_clear_guest_page(kvm, identity_map_pfn, 0, PAGE_SIZE);
- if (r 0)
+ ret = kvm_clear_guest_page(kvm, identity_map_pfn, 0, PAGE_SIZE);
+ if (ret)
goto out;
/* Set up identity-mapping pagetable for EPT in real mode */
for (i = 0; i PT32_ENT_PER_PAGE; i++) {
tmp = (i 22) + (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |
_PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_PSE);
- r = kvm_write_guest_page(kvm, identity_map_pfn,
+ ret = kvm_write_guest_page(kvm, identity_map_pfn,
tmp, i * sizeof(tmp), sizeof(tmp));
- if (r 0)
+ if (ret)
goto out;
}
kvm-arch.ept_identity_pagetable_done = true;
- ret = 1;
+
out:
srcu_read_unlock(kvm-srcu, idx);
-
out2:
mutex_unlock(kvm-slots_lock);
return ret;
@@ -7604,11 +7601,13 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm
*kvm, unsigned int id)
if (err)
goto free_vcpu;
+ /* Set err to -ENOMEM to handle memory allocation error. */
+ err = -ENOMEM;
+
vmx-guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL);
BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) * sizeof(vmx-guest_msrs[0])
PAGE_SIZE);
- err = -ENOMEM;
if (!vmx-guest_msrs) {
goto uninit_vcpu;
}
@@ -7641,8 +7640,8 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm,
unsigned int id)
if (!kvm-arch.ept_identity_map_addr)
kvm-arch.ept_identity_map_addr =
VMX_EPT_IDENTITY_PAGETABLE_ADDR;
- err = -ENOMEM;
- if (!init_rmode_identity_map(kvm))
+ err = init_rmode_identity_map(kvm);
+ if (err 0)
goto free_vmcs;
}
--
1.8.3.1
--
To unsubscribe from this list: send the line unsubscribe kvm in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH v7 1/9] kvm: Use APIC_DEFAULT_PHYS_BASE macro as the apic access page address.
We have APIC_DEFAULT_PHYS_BASE defined as 0xfee0, which is also the address
of
apic access page. So use this macro.
Signed-off-by: Tang Chen tangc...@cn.fujitsu.com
Reviewed-by: Gleb Natapov g...@kernel.org
---
arch/x86/kvm/svm.c | 3 ++-
arch/x86/kvm/vmx.c | 6 +++---
2 files changed, 5 insertions(+), 4 deletions(-)
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index ddf7427..1d941ad 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1257,7 +1257,8 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm,
unsigned int id)
svm-asid_generation = 0;
init_vmcb(svm);
- svm-vcpu.arch.apic_base = 0xfee0 | MSR_IA32_APICBASE_ENABLE;
+ svm-vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE |
+ MSR_IA32_APICBASE_ENABLE;
if (kvm_vcpu_is_bsp(svm-vcpu))
svm-vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index bfe11cf..4b80ead 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3999,13 +3999,13 @@ static int alloc_apic_access_page(struct kvm *kvm)
goto out;
kvm_userspace_mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT;
kvm_userspace_mem.flags = 0;
- kvm_userspace_mem.guest_phys_addr = 0xfee0ULL;
+ kvm_userspace_mem.guest_phys_addr = APIC_DEFAULT_PHYS_BASE;
kvm_userspace_mem.memory_size = PAGE_SIZE;
r = __kvm_set_memory_region(kvm, kvm_userspace_mem);
if (r)
goto out;
- page = gfn_to_page(kvm, 0xfee00);
+ page = gfn_to_page(kvm, APIC_DEFAULT_PHYS_BASE PAGE_SHIFT);
if (is_error_page(page)) {
r = -EFAULT;
goto out;
@@ -4477,7 +4477,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu)
vmx-vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
kvm_set_cr8(vmx-vcpu, 0);
- apic_base_msr.data = 0xfee0 | MSR_IA32_APICBASE_ENABLE;
+ apic_base_msr.data = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE;
if (kvm_vcpu_is_bsp(vmx-vcpu))
apic_base_msr.data |= MSR_IA32_APICBASE_BSP;
apic_base_msr.host_initiated = true;
--
1.8.3.1
--
To unsubscribe from this list: send the line unsubscribe kvm in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
