f8f559422b
This patch tries to introduce a very simple and scale way to invalidate all mmio sptes - it need not walk any shadow pages and hold mmu-lock KVM maintains a global mmio valid generation-number which is stored in kvm->memslots.generation and every mmio spte stores the current global generation-number into his available bits when it is created When KVM need zap all mmio sptes, it just simply increase the global generation-number. When guests do mmio access, KVM intercepts a MMIO #PF then it walks the shadow page table and get the mmio spte. If the generation-number on the spte does not equal the global generation-number, it will go to the normal #PF handler to update the mmio spte Since 19 bits are used to store generation-number on mmio spte, we zap all mmio sptes when the number is round Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com> Reviewed-by: Gleb Natapov <gleb@redhat.com> Reviewed-by: Marcelo Tosatti <mtosatti@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
119 lines
3.1 KiB
C
119 lines
3.1 KiB
C
#ifndef __KVM_X86_MMU_H
|
|
#define __KVM_X86_MMU_H
|
|
|
|
#include <linux/kvm_host.h>
|
|
#include "kvm_cache_regs.h"
|
|
|
|
#define PT64_PT_BITS 9
|
|
#define PT64_ENT_PER_PAGE (1 << PT64_PT_BITS)
|
|
#define PT32_PT_BITS 10
|
|
#define PT32_ENT_PER_PAGE (1 << PT32_PT_BITS)
|
|
|
|
#define PT_WRITABLE_SHIFT 1
|
|
|
|
#define PT_PRESENT_MASK (1ULL << 0)
|
|
#define PT_WRITABLE_MASK (1ULL << PT_WRITABLE_SHIFT)
|
|
#define PT_USER_MASK (1ULL << 2)
|
|
#define PT_PWT_MASK (1ULL << 3)
|
|
#define PT_PCD_MASK (1ULL << 4)
|
|
#define PT_ACCESSED_SHIFT 5
|
|
#define PT_ACCESSED_MASK (1ULL << PT_ACCESSED_SHIFT)
|
|
#define PT_DIRTY_SHIFT 6
|
|
#define PT_DIRTY_MASK (1ULL << PT_DIRTY_SHIFT)
|
|
#define PT_PAGE_SIZE_SHIFT 7
|
|
#define PT_PAGE_SIZE_MASK (1ULL << PT_PAGE_SIZE_SHIFT)
|
|
#define PT_PAT_MASK (1ULL << 7)
|
|
#define PT_GLOBAL_MASK (1ULL << 8)
|
|
#define PT64_NX_SHIFT 63
|
|
#define PT64_NX_MASK (1ULL << PT64_NX_SHIFT)
|
|
|
|
#define PT_PAT_SHIFT 7
|
|
#define PT_DIR_PAT_SHIFT 12
|
|
#define PT_DIR_PAT_MASK (1ULL << PT_DIR_PAT_SHIFT)
|
|
|
|
#define PT32_DIR_PSE36_SIZE 4
|
|
#define PT32_DIR_PSE36_SHIFT 13
|
|
#define PT32_DIR_PSE36_MASK \
|
|
(((1ULL << PT32_DIR_PSE36_SIZE) - 1) << PT32_DIR_PSE36_SHIFT)
|
|
|
|
#define PT64_ROOT_LEVEL 4
|
|
#define PT32_ROOT_LEVEL 2
|
|
#define PT32E_ROOT_LEVEL 3
|
|
|
|
#define PT_PDPE_LEVEL 3
|
|
#define PT_DIRECTORY_LEVEL 2
|
|
#define PT_PAGE_TABLE_LEVEL 1
|
|
|
|
#define PFERR_PRESENT_MASK (1U << 0)
|
|
#define PFERR_WRITE_MASK (1U << 1)
|
|
#define PFERR_USER_MASK (1U << 2)
|
|
#define PFERR_RSVD_MASK (1U << 3)
|
|
#define PFERR_FETCH_MASK (1U << 4)
|
|
|
|
int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]);
|
|
void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask);
|
|
|
|
/*
|
|
* Return values of handle_mmio_page_fault_common:
|
|
* RET_MMIO_PF_EMULATE: it is a real mmio page fault, emulate the instruction
|
|
* directly.
|
|
* RET_MMIO_PF_INVALID: invalid spte is detected then let the real page
|
|
* fault path update the mmio spte.
|
|
* RET_MMIO_PF_RETRY: let CPU fault again on the address.
|
|
* RET_MMIO_PF_BUG: bug is detected.
|
|
*/
|
|
enum {
|
|
RET_MMIO_PF_EMULATE = 1,
|
|
RET_MMIO_PF_INVALID = 2,
|
|
RET_MMIO_PF_RETRY = 0,
|
|
RET_MMIO_PF_BUG = -1
|
|
};
|
|
|
|
int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct);
|
|
int kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context);
|
|
|
|
static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
|
|
{
|
|
if (kvm->arch.n_max_mmu_pages > kvm->arch.n_used_mmu_pages)
|
|
return kvm->arch.n_max_mmu_pages -
|
|
kvm->arch.n_used_mmu_pages;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu)
|
|
{
|
|
if (likely(vcpu->arch.mmu.root_hpa != INVALID_PAGE))
|
|
return 0;
|
|
|
|
return kvm_mmu_load(vcpu);
|
|
}
|
|
|
|
static inline int is_present_gpte(unsigned long pte)
|
|
{
|
|
return pte & PT_PRESENT_MASK;
|
|
}
|
|
|
|
static inline int is_writable_pte(unsigned long pte)
|
|
{
|
|
return pte & PT_WRITABLE_MASK;
|
|
}
|
|
|
|
static inline bool is_write_protection(struct kvm_vcpu *vcpu)
|
|
{
|
|
return kvm_read_cr0_bits(vcpu, X86_CR0_WP);
|
|
}
|
|
|
|
/*
|
|
* Will a fault with a given page-fault error code (pfec) cause a permission
|
|
* fault with the given access (in ACC_* format)?
|
|
*/
|
|
static inline bool permission_fault(struct kvm_mmu *mmu, unsigned pte_access,
|
|
unsigned pfec)
|
|
{
|
|
return (mmu->permissions[pfec >> 1] >> pte_access) & 1;
|
|
}
|
|
|
|
void kvm_mmu_invalidate_zap_all_pages(struct kvm *kvm);
|
|
#endif
|