Marcelo Tosatti wrote:
Hypercall based pte updates are faster than faults, and also allow use
of the lazy MMU mode to batch operations.
Don't report the feature if two dimensional paging is enabled.
+static int kvm_hypercall_mmu_write(struct kvm_vcpu *vcpu, gpa_t addr,
+
Hypercall based pte updates are faster than faults, and also allow use
of the lazy MMU mode to batch operations.
Don't report the feature if two dimensional paging is enabled.
v1-v2:
- guest passes physical destination addr, which is cheaper than doing v-p
translation in the host.
- infer size
Marcelo Tosatti wrote:
Hypercall based pte updates are faster than faults, and also allow use
of the lazy MMU mode to batch operations.
Don't report the feature if two dimensional paging is enabled.
Signed-off-by: Marcelo Tosatti [EMAIL PROTECTED]
+/*
+ * We only need to hook operations
Marcelo Tosatti wrote:
Hypercall based pte updates are faster than faults, and also allow use
of the lazy MMU mode to batch operations.
Don't report the feature if two dimensional paging is enabled.
Signed-off-by: Marcelo Tosatti [EMAIL PROTECTED]
Cc: Anthony Liguori [EMAIL PROTECTED]
Avi Kivity wrote:
Marcelo Tosatti wrote:
Hypercall based pte updates are faster than faults, and also allow use
of the lazy MMU mode to batch operations.
Don't report the feature if two dimensional paging is enabled.
Signed-off-by: Marcelo Tosatti [EMAIL PROTECTED]
+/*
+ * We only need to
On Sun, Feb 17, 2008 at 03:13:47PM +0200, Avi Kivity wrote:
Avi Kivity wrote:
Marcelo Tosatti wrote:
Hypercall based pte updates are faster than faults, and also allow use
of the lazy MMU mode to batch operations.
Don't report the feature if two dimensional paging is enabled.
Marcelo Tosatti wrote:
Issue is the paravirt_ops code in Linux does not cover all pte updates
(bit updates, ptep_get_and_clear, etc).
The plan is to get the basic infrastructure merged into KVM first (which
is a significant improvement already) and then later have paravirt_ops
cover all
On Sun, Feb 17, 2008 at 04:57:36PM +0200, Avi Kivity wrote:
Marcelo Tosatti wrote:
Issue is the paravirt_ops code in Linux does not cover all pte updates
(bit updates, ptep_get_and_clear, etc).
The plan is to get the basic infrastructure merged into KVM first (which
is a significant
Hypercall based pte updates are faster than faults, and also allow use
of the lazy MMU mode to batch operations.
Don't report the feature if two dimensional paging is enabled.
Signed-off-by: Marcelo Tosatti [EMAIL PROTECTED]
Cc: Anthony Liguori [EMAIL PROTECTED]
Index: