| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Sun, 7 Aug 2022 15:18:34 -0700
From: isaku.yamahata@...el.com
To: kvm@...r.kernel.org, linux-kernel@...r.kernel.org
Cc: isaku.yamahata@...el.com, isaku.yamahata@...il.com,
Paolo Bonzini <pbonzini@...hat.com>, erdemaktas@...gle.com,
Sean Christopherson <seanjc@...gle.com>,
Sagi Shahar <sagis@...gle.com>
Subject: [RFC PATCH 01/13] KVM: Update lpage info when private/shared memory are mixed
From: Chao Peng <chao.p.peng@...ux.intel.com>
Update lpage_info when private/shared memory attribute is changed. If both
private and shared pages are within large page region, it can't be mapped
as large page. Reserve a bit in disallow_lpage to indicate a large page has
private/share pages mixed.
Signed-off-by: Chao Peng <chao.p.peng@...ux.intel.com>
Signed-off-by: Isaku Yamahata <isaku.yamahata@...el.com>
---
arch/x86/include/asm/kvm_host.h | 8 ++
arch/x86/kvm/mmu/mmu.c | 152 +++++++++++++++++++++++++++++++-
arch/x86/kvm/mmu/mmu_internal.h | 2 +
include/linux/kvm_host.h | 10 +++
virt/kvm/kvm_main.c | 9 +-
5 files changed, 178 insertions(+), 3 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index d68130be5bf7..2bdb1de9bce0 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -37,6 +37,7 @@
#include <asm/hyperv-tlfs.h>
#define __KVM_HAVE_ARCH_VCPU_DEBUGFS
+#define __KVM_HAVE_ARCH_UPDATE_MEM_ATTR
#define __KVM_HAVE_ZAP_GFN_RANGE
#define KVM_MAX_VCPUS 1024
@@ -981,6 +982,13 @@ struct kvm_vcpu_arch {
#endif
};
+/*
+ * Use a bit in disallow_lpage to indicate private/shared pages mixed at the
+ * level. The remaining bits will be used as a reference count for other users.
+ */
+#define KVM_LPAGE_PRIVATE_SHARED_MIXED (1U << 31)
+#define KVM_LPAGE_COUNT_MAX ((1U << 31) - 1)
+
struct kvm_lpage_info {
int disallow_lpage;
};
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index c61fb6848d0d..a03aa609a0da 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -818,11 +818,16 @@ static void update_gfn_disallow_lpage_count(const struct kvm_memory_slot *slot,
{
struct kvm_lpage_info *linfo;
int i;
+ int disallow_count;
for (i = PG_LEVEL_2M; i <= KVM_MAX_HUGEPAGE_LEVEL; ++i) {
linfo = lpage_info_slot(gfn, slot, i);
+
+ disallow_count = linfo->disallow_lpage & KVM_LPAGE_COUNT_MAX;
+ WARN_ON(disallow_count + count < 0 ||
+ disallow_count > KVM_LPAGE_COUNT_MAX - count);
+
linfo->disallow_lpage += count;
- WARN_ON(linfo->disallow_lpage < 0);
}
}
@@ -7236,3 +7241,148 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
if (kvm->arch.nx_lpage_recovery_thread)
kthread_stop(kvm->arch.nx_lpage_recovery_thread);
}
+
+bool kvm_mem_attr_is_mixed(struct kvm_memory_slot *slot, gfn_t gfn, int level)
+{
+ gfn_t pages = KVM_PAGES_PER_HPAGE(level);
+ gfn_t mask = ~(pages - 1);
+ struct kvm_lpage_info *linfo = lpage_info_slot(gfn & mask, slot, level);
+
+ WARN_ON(level == PG_LEVEL_4K);
+ return linfo->disallow_lpage & KVM_LPAGE_PRIVATE_SHARED_MIXED;
+}
+
+static void update_mixed(struct kvm_lpage_info *linfo, bool mixed)
+{
+ if (mixed)
+ linfo->disallow_lpage |= KVM_LPAGE_PRIVATE_SHARED_MIXED;
+ else
+ linfo->disallow_lpage &= ~KVM_LPAGE_PRIVATE_SHARED_MIXED;
+}
+
+static bool __mem_attr_is_mixed(struct kvm *kvm, gfn_t start, gfn_t end)
+{
+ XA_STATE(xas, &kvm->mem_attr_array, start);
+ bool mixed = false;
+ gfn_t gfn = start;
+ void *s_entry;
+ void *entry;
+
+ rcu_read_lock();
+ s_entry = xas_load(&xas);
+ while (gfn < end) {
+ if (xas_retry(&xas, entry))
+ continue;
+
+ KVM_BUG_ON(gfn != xas.xa_index, kvm);
+
+ entry = xas_next(&xas);
+ if (entry != s_entry) {
+ mixed = true;
+ break;
+ }
+ gfn++;
+ }
+ rcu_read_unlock();
+ return mixed;
+}
+
+static bool mem_attr_is_mixed(struct kvm *kvm,
+ struct kvm_memory_slot *slot, int level,
+ gfn_t start, gfn_t end)
+{
+ struct kvm_lpage_info *child_linfo;
+ unsigned long child_pages;
+ bool mixed = false;
+ unsigned long gfn;
+ void *entry;
+
+ if (WARN_ON(level == PG_LEVEL_4K))
+ return false;
+
+ if (level == PG_LEVEL_2M)
+ return __mem_attr_is_mixed(kvm, start, end);
+
+ /* This assumes that level - 1 is already updated. */
+ rcu_read_lock();
+ child_pages = KVM_PAGES_PER_HPAGE(level - 1);
+ entry = xa_load(&kvm->mem_attr_array, start);
+ for (gfn = start; gfn < end; gfn += child_pages) {
+ child_linfo = lpage_info_slot(gfn, slot, level - 1);
+ if (child_linfo->disallow_lpage & KVM_LPAGE_PRIVATE_SHARED_MIXED) {
+ mixed = true;
+ break;
+ }
+ if (xa_load(&kvm->mem_attr_array, gfn) != entry) {
+ mixed = true;
+ break;
+ }
+ }
+ rcu_read_unlock();
+ return mixed;
+}
+
+static void update_mem_lpage_info(struct kvm *kvm,
+ struct kvm_memory_slot *slot,
+ unsigned int attr,
+ gfn_t start, gfn_t end)
+{
+ unsigned long lpage_start, lpage_end;
+ unsigned long gfn, pages, mask;
+ int level;
+
+ for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) {
+ pages = KVM_PAGES_PER_HPAGE(level);
+ mask = ~(pages - 1);
+ lpage_start = start & mask;
+ lpage_end = (end - 1) & mask;
+
+ /*
+ * We only need to scan the head and tail page, for middle pages
+ * we know they are not mixed.
+ */
+ update_mixed(lpage_info_slot(lpage_start, slot, level),
+ mem_attr_is_mixed(kvm, slot, level,
+ lpage_start, lpage_start + pages));
+
+ if (lpage_start == lpage_end)
+ return;
+
+ for (gfn = lpage_start + pages; gfn < lpage_end; gfn += pages) {
+ update_mixed(lpage_info_slot(gfn, slot, level), false);
+ }
+
+ update_mixed(lpage_info_slot(lpage_end, slot, level),
+ mem_attr_is_mixed(kvm, slot, level,
+ lpage_end, lpage_end + pages));
+ }
+}
+
+void kvm_arch_update_mem_attr(struct kvm *kvm, unsigned int attr,
+ gfn_t start, gfn_t end)
+{
+ struct kvm_memory_slot *slot;
+ struct kvm_memslots *slots;
+ struct kvm_memslot_iter iter;
+ int idx;
+ int i;
+
+ WARN_ONCE(!(attr & (KVM_MEM_ATTR_PRIVATE | KVM_MEM_ATTR_SHARED)),
+ "Unsupported mem attribute.\n");
+
+ idx = srcu_read_lock(&kvm->srcu);
+ for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+ slots = __kvm_memslots(kvm, i);
+
+ kvm_for_each_memslot_in_gfn_range(&iter, slots, start, end) {
+ slot = iter.slot;
+ start = max(start, slot->base_gfn);
+ end = min(end, slot->base_gfn + slot->npages);
+ if (WARN_ON_ONCE(start >= end))
+ continue;
+
+ update_mem_lpage_info(kvm, slot, attr, start, end);
+ }
+ }
+ srcu_read_unlock(&kvm->srcu, idx);
+}
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 4b581209b3b9..e5d5fea29bfa 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -259,6 +259,8 @@ static inline gfn_t kvm_gfn_for_root(struct kvm *kvm, struct kvm_mmu_page *root,
}
#endif
+bool kvm_mem_attr_is_mixed(struct kvm_memory_slot *slot, gfn_t gfn, int level);
+
static inline bool kvm_mmu_page_ad_need_write_protect(struct kvm_mmu_page *sp)
{
/*
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 3c29e0eb754c..7e3d582cc1ba 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2295,6 +2295,16 @@ static inline void kvm_handle_signal_exit(struct kvm_vcpu *vcpu)
/* Max number of entries allowed for each kvm dirty ring */
#define KVM_DIRTY_RING_MAX_ENTRIES 65536
+#ifdef __KVM_HAVE_ARCH_UPDATE_MEM_ATTR
+void kvm_arch_update_mem_attr(struct kvm *kvm, unsigned int attr,
+ gfn_t start, gfn_t end);
+#else
+static inline void kvm_arch_update_mem_attr(struct kvm *kvm, unsigned int attr,
+ gfn_t start, gfn_t end)
+{
+}
+#endif /* __KVM_HAVE_ARCH_UPDATE_MEM_ATTR */
+
#ifdef CONFIG_HAVE_KVM_PRIVATE_MEM
static inline int kvm_private_mem_get_pfn(struct kvm_memory_slot *slot,
gfn_t gfn, kvm_pfn_t *pfn, int *order)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 2ec940354749..9f9b2c0e7afc 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -943,6 +943,7 @@ EXPORT_SYMBOL_GPL(kvm_vm_reserve_mem_attr);
int kvm_vm_set_mem_attr(struct kvm *kvm, int attr, gfn_t start, gfn_t end)
{
void *entry;
+ int r;
/* By default, the entry is private. */
switch (attr) {
@@ -958,8 +959,12 @@ int kvm_vm_set_mem_attr(struct kvm *kvm, int attr, gfn_t start, gfn_t end)
}
WARN_ON(start >= end);
- return xa_err(xa_store_range(&kvm->mem_attr_array, start, end - 1,
- entry, GFP_KERNEL_ACCOUNT));
+ r = xa_err(xa_store_range(&kvm->mem_attr_array, start, end - 1,
+ entry, GFP_KERNEL_ACCOUNT));
+ if (r)
+ return r;
+ kvm_arch_update_mem_attr(kvm, attr, start, end);
+ return 0;
}
EXPORT_SYMBOL_GPL(kvm_vm_set_mem_attr);
#endif /* CONFIG_HAVE_KVM_PRIVATE_MEM_ATTR */
--
2.25.1
Powered by blists - more mailing lists