| Message ID | 20230227222957.24501-27-rick.p.edgecombe@intel.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | Shadow stacks for userspace | expand |
On Mon, Feb 27, 2023 at 02:29:42PM -0800, Rick Edgecombe wrote: > The x86 Control-flow Enforcement Technology (CET) feature includes a new > type of memory called shadow stack. This shadow stack memory has some > unusual properties, which requires some core mm changes to function > properly. > > One sharp edge is that PTEs that are both Write=0 and Dirty=1 are > treated as shadow by the CPU, but this combination used to be created by > the kernel on x86. Previous patches have changed the kernel to now avoid > creating these PTEs unless they are for shadow stack memory. In case any > missed corners of the kernel are still creating PTEs like this for > non-shadow stack memory, and to catch any re-introductions of the logic, > warn if any shadow stack PTEs (Write=0, Dirty=1) are found in non-shadow > stack VMAs when they are being zapped. This won't catch transient cases > but should have decent coverage. It will be compiled out when shadow > stack is not configured. > > In order to check if a pte is shadow stack in core mm code, add two arch s/pte/PTE/
On Wed, 2023-03-08 at 09:53 +0100, Borislav Petkov wrote: > On Mon, Feb 27, 2023 at 02:29:42PM -0800, Rick Edgecombe wrote: > > The x86 Control-flow Enforcement Technology (CET) feature includes > > a new > > type of memory called shadow stack. This shadow stack memory has > > some > > unusual properties, which requires some core mm changes to function > > properly. > > > > One sharp edge is that PTEs that are both Write=0 and Dirty=1 are > > treated as shadow by the CPU, but this combination used to be > > created by > > the kernel on x86. Previous patches have changed the kernel to now > > avoid > > creating these PTEs unless they are for shadow stack memory. In > > case any > > missed corners of the kernel are still creating PTEs like this for > > non-shadow stack memory, and to catch any re-introductions of the > > logic, > > warn if any shadow stack PTEs (Write=0, Dirty=1) are found in non- > > shadow > > stack VMAs when they are being zapped. This won't catch transient > > cases > > but should have decent coverage. It will be compiled out when > > shadow > > stack is not configured. > > > > In order to check if a pte is shadow stack in core mm code, add two > > arch > > s/pte/PTE/ Yes, it matches the rest.
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 2e3d8cca1195..e5b3dce0d9fe 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1684,6 +1684,12 @@ static inline bool arch_has_hw_pte_young(void) return true; } +#define arch_check_zapped_pte arch_check_zapped_pte +void arch_check_zapped_pte(struct vm_area_struct *vma, pte_t pte); + +#define arch_check_zapped_pmd arch_check_zapped_pmd +void arch_check_zapped_pmd(struct vm_area_struct *vma, pmd_t pmd); + #ifdef CONFIG_XEN_PV #define arch_has_hw_nonleaf_pmd_young arch_has_hw_nonleaf_pmd_young static inline bool arch_has_hw_nonleaf_pmd_young(void) diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 98856bcc8102..afab0bc7862b 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -906,3 +906,15 @@ pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma) return pmd; } + +void arch_check_zapped_pte(struct vm_area_struct *vma, pte_t pte) +{ + VM_WARN_ON_ONCE(!(vma->vm_flags & VM_SHADOW_STACK) && + pte_shstk(pte)); +} + +void arch_check_zapped_pmd(struct vm_area_struct *vma, pmd_t pmd) +{ + VM_WARN_ON_ONCE(!(vma->vm_flags & VM_SHADOW_STACK) && + pmd_shstk(pmd)); +} diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index c63cd44777ec..4a8970b9fb11 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -291,6 +291,20 @@ static inline bool arch_has_hw_pte_young(void) } #endif +#ifndef arch_check_zapped_pte +static inline void arch_check_zapped_pte(struct vm_area_struct *vma, + pte_t pte) +{ +} +#endif + +#ifndef arch_check_zapped_pmd +static inline void arch_check_zapped_pmd(struct vm_area_struct *vma, + pmd_t pmd) +{ +} +#endif + #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long address, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index aaf815838144..24797be05fcb 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1689,6 +1689,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, */ orig_pmd = pmdp_huge_get_and_clear_full(vma, addr, pmd, tlb->fullmm); + arch_check_zapped_pmd(vma, orig_pmd); tlb_remove_pmd_tlb_entry(tlb, pmd, addr); if (vma_is_special_huge(vma)) { if (arch_needs_pgtable_deposit()) diff --git a/mm/memory.c b/mm/memory.c index d0972d2d6f36..c953c2c4588c 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1389,6 +1389,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, continue; ptent = ptep_get_and_clear_full(mm, addr, pte, tlb->fullmm); + arch_check_zapped_pte(vma, ptent); tlb_remove_tlb_entry(tlb, pte, addr); zap_install_uffd_wp_if_needed(vma, addr, pte, details, ptent);