[PATCH v3 6/8] mm/x86: arch_check_zapped_pud()

[Peter Xu]

Introduce arch_check_zapped_pud() to sanity check shadow stack on PUD zaps.
It has the same logic of the PMD helper.

One thing to mention is, it might be a good idea to use page_table_check in
the future for trapping wrong setups of shadow stack pgtable entries [1].
That is left for the future as a separate effort.

[1] https://lore.kernel.org/all/59d518698f664e07c036a5098833d7b56b953305.camel@xxxxxxxxx

Cc: "Edgecombe, Rick P" <rick.p.edgecombe@xxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: x86@xxxxxxxxxx
Signed-off-by: Peter Xu <peterx@xxxxxxxxxx>
---
 arch/x86/include/asm/pgtable.h | 10 ++++++++++
 arch/x86/mm/pgtable.c          |  7 +++++++
 include/linux/pgtable.h        |  7 +++++++
 mm/huge_memory.c               |  4 +++-
 4 files changed, 27 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 25fc6d809572..cdf044c2ad6e 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -169,6 +169,13 @@ static inline int pud_young(pud_t pud)
 	return pud_flags(pud) & _PAGE_ACCESSED;
 }
 
+static inline bool pud_shstk(pud_t pud)
+{
+	return cpu_feature_enabled(X86_FEATURE_SHSTK) &&
+	       (pud_flags(pud) & (_PAGE_RW | _PAGE_DIRTY | _PAGE_PSE)) ==
+	       (_PAGE_DIRTY | _PAGE_PSE);
+}
+
 static inline int pte_write(pte_t pte)
 {
 	/*
@@ -1662,6 +1669,9 @@ 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);
 
+#define arch_check_zapped_pud arch_check_zapped_pud
+void arch_check_zapped_pud(struct vm_area_struct *vma, pud_t pud);
+
 #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 93e54ba91fbf..564b8945951e 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -926,3 +926,10 @@ 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));
 }
+
+void arch_check_zapped_pud(struct vm_area_struct *vma, pud_t pud)
+{
+	/* See note in arch_check_zapped_pte() */
+	VM_WARN_ON_ONCE(!(vma->vm_flags & VM_SHADOW_STACK) &&
+			pud_shstk(pud));
+}
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 2a6a3cccfc36..2289e9f7aa1b 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -447,6 +447,13 @@ static inline void arch_check_zapped_pmd(struct vm_area_struct *vma,
 }
 #endif
 
+#ifndef arch_check_zapped_pud
+static inline void arch_check_zapped_pud(struct vm_area_struct *vma,
+					 pud_t pud)
+{
+}
+#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 9fec5bd1c8b0..c10247bef08a 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2291,12 +2291,14 @@ int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		 pud_t *pud, unsigned long addr)
 {
 	spinlock_t *ptl;
+	pud_t orig_pud;
 
 	ptl = __pud_trans_huge_lock(pud, vma);
 	if (!ptl)
 		return 0;
 
-	pudp_huge_get_and_clear_full(vma, addr, pud, tlb->fullmm);
+	orig_pud = pudp_huge_get_and_clear_full(vma, addr, pud, tlb->fullmm);
+	arch_check_zapped_pud(vma, orig_pud);
 	tlb_remove_pud_tlb_entry(tlb, pud, addr);
 	if (vma_is_special_huge(vma)) {
 		spin_unlock(ptl);
-- 
2.45.0