github-mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-07-27 17:47:41 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity Graph

KVM: x86/mmu: add support for MBEC to EPT page table walks

Browse Source 
Extend the page walker to support moving bit 10 of the PTEs
into ACC_USER_EXEC_MASK and bit 6 of the exit qualification of
EPT violation VM exits.

Note that while mmu_has_mbec()/cr4_smep affect the interpretation of
ACC_USER_EXEC_MASK and add bit 10 as a "present bit" in guest EPT page
table entries, they do not affect how KVM operates on SPTEs.  That's
because the MMU uses explicit ACC_USER_EXEC_MASK/shadow_xu_mask even for
the non-nested EPT; the only difference is that ACC_USER_EXEC_MASK and
ACC_EXEC_MASK will always be set in tandem outside the nested scenario.

Tested-by: David Riley <d.riley@proxmox.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This commit is contained in:
Paolo Bonzini 2026-04-08 11:42:08 -04:00
parent 9c167cb3c1
commit d220bcf026
4 changed files with 43 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
arch/x86/kvm/mmu/mmu.c
View File

@ -5570,7 +5570,6 @@ static void update_permission_bitmask(struct kvm_mmu *mmu, bool ept)
{
unsigned index;
const u16 x = ACC_BITS_MASK(ACC_EXEC_MASK);
const u16 w = ACC_BITS_MASK(ACC_WRITE_MASK);
const u16 r = ACC_BITS_MASK(ACC_READ_MASK);
@ -5611,8 +5610,18 @@ static void update_permission_bitmask(struct kvm_mmu *mmu, bool ept)
u16 smapf = 0;
if (ept) {
ff = (pfec & PFERR_FETCH_MASK) ? (u16)~x : 0;
const u16 xs = ACC_BITS_MASK(ACC_EXEC_MASK);
const u16 xu = ACC_BITS_MASK(ACC_USER_EXEC_MASK);
if (pfec & PFERR_FETCH_MASK) {
/* Ignore XU unless MBEC is enabled. */
if (cr4_smep)
ff = pfec & PFERR_USER_MASK ? (u16)~xu : (u16)~xs;
else
ff = (u16)~xs;
}
} else {
const u16 x = ACC_BITS_MASK(ACC_EXEC_MASK);
const u16 u = ACC_BITS_MASK(ACC_USER_MASK);
/* Faults from kernel mode accesses to user pages */

27
arch/x86/kvm/mmu/paging_tmpl.h
View File

@ -124,12 +124,17 @@ static inline void FNAME(protect_clean_gpte)(struct kvm_mmu *mmu, unsigned *acce
*access &= mask;
}
static inline int FNAME(is_present_gpte)(unsigned long pte)
static inline int FNAME(is_present_gpte)(struct kvm_mmu *mmu,
unsigned long pte)
{
#if PTTYPE != PTTYPE_EPT
return pte & PT_PRESENT_MASK;
#else
return pte & 7;
/*
* For EPT, an entry is present if any of bits 2:0 are set.
* With mode-based execute control, bit 10 also indicates presence.
*/
return pte & (7 | (mmu_has_mbec(mmu) ? VMX_EPT_USER_EXECUTABLE_MASK : 0));
#endif
}
@ -152,7 +157,7 @@ static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu,
struct kvm_mmu_page *sp, u64 *spte,
u64 gpte)
{
if (!FNAME(is_present_gpte)(gpte))
if (!FNAME(is_present_gpte)(vcpu->arch.mmu, gpte))
goto no_present;
/* Prefetch only accessed entries (unless A/D bits are disabled). */
@ -173,10 +178,17 @@ static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu,
static inline unsigned FNAME(gpte_access)(u64 gpte)
{
unsigned access;
/*
* Set bits in ACC_*_MASK even if they might not be used in the
* actual checks. For example, if EFER.NX is clear permission_fault()
* will ignore ACC_EXEC_MASK, and if MBEC is disabled it will
* ignore ACC_USER_EXEC_MASK.
*/
#if PTTYPE == PTTYPE_EPT
access = ((gpte & VMX_EPT_WRITABLE_MASK) ? ACC_WRITE_MASK : 0) |
((gpte & VMX_EPT_EXECUTABLE_MASK) ? ACC_EXEC_MASK : 0) |
((gpte & VMX_EPT_READABLE_MASK) ? ACC_READ_MASK : 0);
((gpte & VMX_EPT_READABLE_MASK) ? ACC_READ_MASK : 0) |
((gpte & VMX_EPT_USER_EXECUTABLE_MASK) ? ACC_USER_EXEC_MASK : 0);
#else
/*
* P is set here, so the page is always readable and W/U/!NX represent
@ -331,7 +343,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
if (walker->level == PT32E_ROOT_LEVEL) {
pte = mmu->get_pdptr(vcpu, (addr >> 30) & 3);
trace_kvm_mmu_paging_element(pte, walker->level);
if (!FNAME(is_present_gpte)(pte))
if (!FNAME(is_present_gpte)(mmu, pte))
goto error;
--walker->level;
}
@ -414,7 +426,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
*/
pte_access = pt_access & (pte ^ walk_nx_mask);
if (unlikely(!FNAME(is_present_gpte)(pte)))
if (unlikely(!FNAME(is_present_gpte)(mmu, pte)))
goto error;
if (unlikely(FNAME(is_rsvd_bits_set)(mmu, pte, walker->level))) {
@ -521,6 +533,9 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
* ACC_*_MASK flags!
*/
walker->fault.exit_qualification |= EPT_VIOLATION_RWX_TO_PROT(pte_access);
if (mmu_has_mbec(mmu))
walker->fault.exit_qualification |=
EPT_VIOLATION_USER_EXEC_TO_PROT(pte_access);
}
#endif
walker->fault.address = addr;

2
arch/x86/kvm/mmu/spte.h
View File

@ -395,6 +395,8 @@ static inline bool __is_rsvd_bits_set(struct rsvd_bits_validate *rsvd_check,
static inline bool __is_bad_mt_xwr(struct rsvd_bits_validate *rsvd_check,
u64 pte)
{
if (pte & VMX_EPT_USER_EXECUTABLE_MASK)
pte |= VMX_EPT_EXECUTABLE_MASK;
return rsvd_check->bad_mt_xwr & BIT_ULL(pte & 0x3f);
}

9
arch/x86/kvm/vmx/nested.c
View File

@ -7452,6 +7452,15 @@ static gpa_t vmx_translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa,
struct kvm_mmu *mmu = vcpu->arch.mmu;
BUG_ON(!mmu_is_nested(vcpu));
/*
* MBEC differentiates based on the effective U/S bit of
* the guest page tables; not the processor CPL.
*/
access &= ~PFERR_USER_MASK;
if ((pte_access & ACC_USER_MASK) && (access & PFERR_GUEST_FINAL_MASK))
access |= PFERR_USER_MASK;
return mmu->gva_to_gpa(vcpu, mmu, gpa, access, exception);
}