[PATCH v4 6/7] mm/x86: Add missing pud helpers

[Peter Xu]

These new helpers will be needed for pud entry updates soon.  Introduce
these helpers by referencing the pmd ones.  Namely:

- pudp_invalidate()
- pud_modify()

Cc: Thomas Gleixner <tglx at linutronix.de>
Cc: Ingo Molnar <mingo at redhat.com>
Cc: Borislav Petkov <bp at alien8.de>
Cc: Dave Hansen <dave.hansen at linux.intel.com>
Cc: x86 at kernel.org
Signed-off-by: Peter Xu <peterx at redhat.com>
---
 arch/x86/include/asm/pgtable.h | 55 +++++++++++++++++++++++++++++-----
 arch/x86/mm/pgtable.c          | 12 ++++++++
 2 files changed, 59 insertions(+), 8 deletions(-)

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index fdb8ac9e7030..a7c1e9cfea41 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -787,6 +787,12 @@ static inline pmd_t pmd_mkinvalid(pmd_t pmd)
 		      __pgprot(pmd_flags(pmd) & ~(_PAGE_PRESENT|_PAGE_PROTNONE)));
 }
 
+static inline pud_t pud_mkinvalid(pud_t pud)
+{
+	return pfn_pud(pud_pfn(pud),
+		       __pgprot(pud_flags(pud) & ~(_PAGE_PRESENT|_PAGE_PROTNONE)));
+}
+
 static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask);
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
@@ -834,14 +840,8 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 	pmd_result = __pmd(val);
 
 	/*
-	 * To avoid creating Write=0,Dirty=1 PMDs, pte_modify() needs to avoid:
-	 *  1. Marking Write=0 PMDs Dirty=1
-	 *  2. Marking Dirty=1 PMDs Write=0
-	 *
-	 * The first case cannot happen because the _PAGE_CHG_MASK will filter
-	 * out any Dirty bit passed in newprot. Handle the second case by
-	 * going through the mksaveddirty exercise. Only do this if the old
-	 * value was Write=1 to avoid doing this on Shadow Stack PTEs.
+	 * Avoid creating shadow stack PMD by accident.  See comment in
+	 * pte_modify().
 	 */
 	if (oldval & _PAGE_RW)
 		pmd_result = pmd_mksaveddirty(pmd_result);
@@ -851,6 +851,29 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 	return pmd_result;
 }
 
+static inline pud_t pud_modify(pud_t pud, pgprot_t newprot)
+{
+	pudval_t val = pud_val(pud), oldval = val;
+	pud_t pud_result;
+
+	val &= _HPAGE_CHG_MASK;
+	val |= check_pgprot(newprot) & ~_HPAGE_CHG_MASK;
+	val = flip_protnone_guard(oldval, val, PHYSICAL_PUD_PAGE_MASK);
+
+	pud_result = __pud(val);
+
+	/*
+	 * Avoid creating shadow stack PUD by accident.  See comment in
+	 * pte_modify().
+	 */
+	if (oldval & _PAGE_RW)
+		pud_result = pud_mksaveddirty(pud_result);
+	else
+		pud_result = pud_clear_saveddirty(pud_result);
+
+	return pud_result;
+}
+
 /*
  * mprotect needs to preserve PAT and encryption bits when updating
  * vm_page_prot
@@ -1389,10 +1412,26 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
 }
 #endif
 
+static inline pud_t pudp_establish(struct vm_area_struct *vma,
+		unsigned long address, pud_t *pudp, pud_t pud)
+{
+	page_table_check_pud_set(vma->vm_mm, pudp, pud);
+	if (IS_ENABLED(CONFIG_SMP)) {
+		return xchg(pudp, pud);
+	} else {
+		pud_t old = *pudp;
+		WRITE_ONCE(*pudp, pud);
+		return old;
+	}
+}
+
 #define __HAVE_ARCH_PMDP_INVALIDATE_AD
 extern pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma,
 				unsigned long address, pmd_t *pmdp);
 
+pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address,
+		      pud_t *pudp);
+
 /*
  * Page table pages are page-aligned.  The lower half of the top
  * level is used for userspace and the top half for the kernel.
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index d4b3ccf90236..9fc2dabf8427 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -641,6 +641,18 @@ pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address,
 }
 #endif
 
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \
+	defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
+pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address,
+		     pud_t *pudp)
+{
+	VM_WARN_ON_ONCE(!pud_present(*pudp));
+	pud_t old = pudp_establish(vma, address, pudp, pud_mkinvalid(*pudp));
+	flush_pud_tlb_range(vma, address, address + HPAGE_PUD_SIZE);
+	return old;
+}
+#endif
+
 /**
  * reserve_top_address - reserves a hole in the top of kernel address space
  * @reserve - size of hole to reserve
-- 
2.45.0