KVM: Add coalesced MMIO support (common part)
This patch adds all needed structures to coalesce MMIOs.
Until an architecture uses it, it is not compiled.
Coalesced MMIO introduces two ioctl() to define where are the MMIO zones that
can be coalesced:
- KVM_REGISTER_COALESCED_MMIO registers a coalesced MMIO zone.
It requests one parameter (struct kvm_coalesced_mmio_zone) which defines
a memory area where MMIOs can be coalesced until the next switch to
user space. The maximum number of MMIO zones is KVM_COALESCED_MMIO_ZONE_MAX.
- KVM_UNREGISTER_COALESCED_MMIO cancels all registered zones inside
the given bounds (bounds are also given by struct kvm_coalesced_mmio_zone).
The userspace client can check kernel coalesced MMIO availability by asking
ioctl(KVM_CHECK_EXTENSION) for the KVM_CAP_COALESCED_MMIO capability.
The ioctl() call to KVM_CAP_COALESCED_MMIO will return 0 if not supported,
or the page offset where will be stored the ring buffer.
The page offset depends on the architecture.
After an ioctl(KVM_RUN), the first page of the KVM memory mapped points to
a kvm_run structure. The offset given by KVM_CAP_COALESCED_MMIO is
an offset to the coalesced MMIO ring expressed in PAGE_SIZE relatively
to the address of the start of th kvm_run structure. The MMIO ring buffer
is defined by the structure kvm_coalesced_mmio_ring.
[akio: fix oops during guest shutdown]
Signed-off-by: Laurent Vivier <Laurent.Vivier@bull.net>
Signed-off-by: Akio Takebe <takebe_akio@jp.fujitsu.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 9330fad..7d10dfa 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -47,6 +47,10 @@
#include <asm/uaccess.h>
#include <asm/pgtable.h>
+#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+#include "coalesced_mmio.h"
+#endif
+
MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");
@@ -185,10 +189,23 @@
static struct kvm *kvm_create_vm(void)
{
struct kvm *kvm = kvm_arch_create_vm();
+#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+ struct page *page;
+#endif
if (IS_ERR(kvm))
goto out;
+#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+ page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+ if (!page) {
+ kfree(kvm);
+ return ERR_PTR(-ENOMEM);
+ }
+ kvm->coalesced_mmio_ring =
+ (struct kvm_coalesced_mmio_ring *)page_address(page);
+#endif
+
kvm->mm = current->mm;
atomic_inc(&kvm->mm->mm_count);
spin_lock_init(&kvm->mmu_lock);
@@ -200,6 +217,9 @@
spin_lock(&kvm_lock);
list_add(&kvm->vm_list, &vm_list);
spin_unlock(&kvm_lock);
+#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+ kvm_coalesced_mmio_init(kvm);
+#endif
out:
return kvm;
}
@@ -242,6 +262,10 @@
spin_unlock(&kvm_lock);
kvm_io_bus_destroy(&kvm->pio_bus);
kvm_io_bus_destroy(&kvm->mmio_bus);
+#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+ if (kvm->coalesced_mmio_ring != NULL)
+ free_page((unsigned long)kvm->coalesced_mmio_ring);
+#endif
kvm_arch_destroy_vm(kvm);
mmdrop(mm);
}
@@ -826,6 +850,10 @@
else if (vmf->pgoff == KVM_PIO_PAGE_OFFSET)
page = virt_to_page(vcpu->arch.pio_data);
#endif
+#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+ else if (vmf->pgoff == KVM_COALESCED_MMIO_PAGE_OFFSET)
+ page = virt_to_page(vcpu->kvm->coalesced_mmio_ring);
+#endif
else
return VM_FAULT_SIGBUS;
get_page(page);
@@ -1148,6 +1176,32 @@
goto out;
break;
}
+#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+ case KVM_REGISTER_COALESCED_MMIO: {
+ struct kvm_coalesced_mmio_zone zone;
+ r = -EFAULT;
+ if (copy_from_user(&zone, argp, sizeof zone))
+ goto out;
+ r = -ENXIO;
+ r = kvm_vm_ioctl_register_coalesced_mmio(kvm, &zone);
+ if (r)
+ goto out;
+ r = 0;
+ break;
+ }
+ case KVM_UNREGISTER_COALESCED_MMIO: {
+ struct kvm_coalesced_mmio_zone zone;
+ r = -EFAULT;
+ if (copy_from_user(&zone, argp, sizeof zone))
+ goto out;
+ r = -ENXIO;
+ r = kvm_vm_ioctl_unregister_coalesced_mmio(kvm, &zone);
+ if (r)
+ goto out;
+ r = 0;
+ break;
+ }
+#endif
default:
r = kvm_arch_vm_ioctl(filp, ioctl, arg);
}
@@ -1232,6 +1286,9 @@
#ifdef CONFIG_X86
r += PAGE_SIZE; /* pio data page */
#endif
+#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+ r += PAGE_SIZE; /* coalesced mmio ring page */
+#endif
break;
case KVM_TRACE_ENABLE:
case KVM_TRACE_PAUSE: