KVM: Push rmap into kvm_arch_memory_slot
Two reasons:
- x86 can integrate rmap and rmap_pde and remove heuristics in
__gfn_to_rmap().
- Some architectures do not need rmap.
Since rmap is one of the most memory consuming stuff in KVM, ppc'd
better restrict the allocation to Book3S HV.
Signed-off-by: Takuya Yoshikawa <yoshikawa.takuya@oss.ntt.co.jp>
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Avi Kivity <avi@redhat.com>
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 48e7131..1309e69 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -504,7 +504,7 @@
};
struct kvm_arch_memory_slot {
- unsigned long *rmap_pde[KVM_NR_PAGE_SIZES - 1];
+ unsigned long *rmap[KVM_NR_PAGE_SIZES];
struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1];
};
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index ee768bb..aa9a987 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -970,11 +970,8 @@
{
unsigned long idx;
- if (likely(level == PT_PAGE_TABLE_LEVEL))
- return &slot->rmap[gfn - slot->base_gfn];
-
idx = gfn_to_index(gfn, slot->base_gfn, level);
- return &slot->arch.rmap_pde[level - PT_DIRECTORY_LEVEL][idx];
+ return &slot->arch.rmap[level - PT_PAGE_TABLE_LEVEL][idx];
}
/*
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index abc039d..ebf2109 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6303,14 +6303,18 @@
{
int i;
- for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
- if (!dont || free->arch.rmap_pde[i] != dont->arch.rmap_pde[i]) {
- kvm_kvfree(free->arch.rmap_pde[i]);
- free->arch.rmap_pde[i] = NULL;
+ for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) {
+ if (!dont || free->arch.rmap[i] != dont->arch.rmap[i]) {
+ kvm_kvfree(free->arch.rmap[i]);
+ free->arch.rmap[i] = NULL;
}
- if (!dont || free->arch.lpage_info[i] != dont->arch.lpage_info[i]) {
- kvm_kvfree(free->arch.lpage_info[i]);
- free->arch.lpage_info[i] = NULL;
+ if (i == 0)
+ continue;
+
+ if (!dont || free->arch.lpage_info[i - 1] !=
+ dont->arch.lpage_info[i - 1]) {
+ kvm_kvfree(free->arch.lpage_info[i - 1]);
+ free->arch.lpage_info[i - 1] = NULL;
}
}
}
@@ -6319,28 +6323,30 @@
{
int i;
- for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
+ for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) {
unsigned long ugfn;
int lpages;
- int level = i + 2;
+ int level = i + 1;
lpages = gfn_to_index(slot->base_gfn + npages - 1,
slot->base_gfn, level) + 1;
- slot->arch.rmap_pde[i] =
- kvm_kvzalloc(lpages * sizeof(*slot->arch.rmap_pde[i]));
- if (!slot->arch.rmap_pde[i])
+ slot->arch.rmap[i] =
+ kvm_kvzalloc(lpages * sizeof(*slot->arch.rmap[i]));
+ if (!slot->arch.rmap[i])
goto out_free;
+ if (i == 0)
+ continue;
- slot->arch.lpage_info[i] =
- kvm_kvzalloc(lpages * sizeof(*slot->arch.lpage_info[i]));
- if (!slot->arch.lpage_info[i])
+ slot->arch.lpage_info[i - 1] = kvm_kvzalloc(lpages *
+ sizeof(*slot->arch.lpage_info[i - 1]));
+ if (!slot->arch.lpage_info[i - 1])
goto out_free;
if (slot->base_gfn & (KVM_PAGES_PER_HPAGE(level) - 1))
- slot->arch.lpage_info[i][0].write_count = 1;
+ slot->arch.lpage_info[i - 1][0].write_count = 1;
if ((slot->base_gfn + npages) & (KVM_PAGES_PER_HPAGE(level) - 1))
- slot->arch.lpage_info[i][lpages - 1].write_count = 1;
+ slot->arch.lpage_info[i - 1][lpages - 1].write_count = 1;
ugfn = slot->userspace_addr >> PAGE_SHIFT;
/*
* If the gfn and userspace address are not aligned wrt each
@@ -6352,18 +6358,21 @@
unsigned long j;
for (j = 0; j < lpages; ++j)
- slot->arch.lpage_info[i][j].write_count = 1;
+ slot->arch.lpage_info[i - 1][j].write_count = 1;
}
}
return 0;
out_free:
- for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
- kvm_kvfree(slot->arch.rmap_pde[i]);
- kvm_kvfree(slot->arch.lpage_info[i]);
- slot->arch.rmap_pde[i] = NULL;
- slot->arch.lpage_info[i] = NULL;
+ for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) {
+ kvm_kvfree(slot->arch.rmap[i]);
+ slot->arch.rmap[i] = NULL;
+ if (i == 0)
+ continue;
+
+ kvm_kvfree(slot->arch.lpage_info[i - 1]);
+ slot->arch.lpage_info[i - 1] = NULL;
}
return -ENOMEM;
}