[PATCH 11/46] hugetlb: add hugetlb_pte to track HugeTLB page table entries

[James Houghton <jthoughton@google.com>]

After high-granularity mapping, page table entries for HugeTLB pages can
be of any size/type. (For example, we can have a 1G page mapped with a
mix of PMDs and PTEs.) This struct is to help keep track of a HugeTLB
PTE after we have done a page table walk.

Without this, we'd have to pass around the "size" of the PTE everywhere.
We effectively did this before; it could be fetched from the hstate,
which we pass around pretty much everywhere.

hugetlb_pte_present_leaf is included here as a helper function that will
be used frequently later on.

Signed-off-by: James Houghton <jthoughton@google.com>
---
 include/linux/hugetlb.h | 72 +++++++++++++++++++++++++++++++++++++++++
 mm/hugetlb.c            | 29 +++++++++++++++++
 2 files changed, 101 insertions(+)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 3f098363cd6e..bf441d8a1b52 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -38,6 +38,54 @@ typedef struct { unsigned long pd; } hugepd_t;
  */
 #define __NR_USED_SUBPAGE 3
 
+enum hugetlb_level {
+	HUGETLB_LEVEL_PTE = 1,
+	/*
+	 * We always include PMD, PUD, and P4D in this enum definition so that,
+	 * when logged as an integer, we can easily tell which level it is.
+	 */
+	HUGETLB_LEVEL_PMD,
+	HUGETLB_LEVEL_PUD,
+	HUGETLB_LEVEL_P4D,
+	HUGETLB_LEVEL_PGD,
+};
+
+struct hugetlb_pte {
+	pte_t *ptep;
+	unsigned int shift;
+	enum hugetlb_level level;
+	spinlock_t *ptl;
+};
+
+static inline
+void __hugetlb_pte_populate(struct hugetlb_pte *hpte, pte_t *ptep,
+			    unsigned int shift, enum hugetlb_level level,
+			    spinlock_t *ptl)
+{
+	/*
+	 * If 'shift' indicates that this PTE is contiguous, then @ptep must
+	 * be the first pte of the contiguous bunch.
+	 */
+	hpte->ptl = ptl;
+	hpte->ptep = ptep;
+	hpte->shift = shift;
+	hpte->level = level;
+}
+
+static inline
+unsigned long hugetlb_pte_size(const struct hugetlb_pte *hpte)
+{
+	return 1UL << hpte->shift;
+}
+
+static inline
+unsigned long hugetlb_pte_mask(const struct hugetlb_pte *hpte)
+{
+	return ~(hugetlb_pte_size(hpte) - 1);
+}
+
+bool hugetlb_pte_present_leaf(const struct hugetlb_pte *hpte, pte_t pte);
+
 struct hugepage_subpool {
 	spinlock_t lock;
 	long count;
@@ -1232,6 +1280,30 @@ static inline spinlock_t *huge_pte_lock(struct hstate *h,
 	return ptl;
 }
 
+static inline
+spinlock_t *hugetlb_pte_lockptr(struct hugetlb_pte *hpte)
+{
+	return hpte->ptl;
+}
+
+static inline
+spinlock_t *hugetlb_pte_lock(struct hugetlb_pte *hpte)
+{
+	spinlock_t *ptl = hugetlb_pte_lockptr(hpte);
+
+	spin_lock(ptl);
+	return ptl;
+}
+
+static inline
+void hugetlb_pte_populate(struct mm_struct *mm, struct hugetlb_pte *hpte,
+			  pte_t *ptep, unsigned int shift,
+			  enum hugetlb_level level)
+{
+	__hugetlb_pte_populate(hpte, ptep, shift, level,
+			huge_pte_lockptr(shift, mm, ptep));
+}
+
 #if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_CMA)
 extern void __init hugetlb_cma_reserve(int order);
 #else
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 4db38dc79d0e..2d83a2c359a2 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1266,6 +1266,35 @@ static bool vma_has_reserves(struct vm_area_struct *vma, long chg)
 	return false;
 }
 
+bool hugetlb_pte_present_leaf(const struct hugetlb_pte *hpte, pte_t pte)
+{
+	pgd_t pgd;
+	p4d_t p4d;
+	pud_t pud;
+	pmd_t pmd;
+
+	switch (hpte->level) {
+	case HUGETLB_LEVEL_PGD:
+		pgd = __pgd(pte_val(pte));
+		return pgd_present(pgd) && pgd_leaf(pgd);
+	case HUGETLB_LEVEL_P4D:
+		p4d = __p4d(pte_val(pte));
+		return p4d_present(p4d) && p4d_leaf(p4d);
+	case HUGETLB_LEVEL_PUD:
+		pud = __pud(pte_val(pte));
+		return pud_present(pud) && pud_leaf(pud);
+	case HUGETLB_LEVEL_PMD:
+		pmd = __pmd(pte_val(pte));
+		return pmd_present(pmd) && pmd_leaf(pmd);
+	case HUGETLB_LEVEL_PTE:
+		return pte_present(pte);
+	default:
+		WARN_ON_ONCE(1);
+		return false;
+	}
+}
+
+
 static void enqueue_hugetlb_folio(struct hstate *h, struct folio *folio)
 {
 	int nid = folio_nid(folio);
-- 
2.39.0.314.g84b9a713c41-goog