[PATCH v2 12/13] mm/gup: Handle hugepd for follow_page()

peterx at redhat.com peterx at redhat.com
Wed Jan 3 01:14:22 PST 2024


From: Peter Xu <peterx at redhat.com>

Hugepd is only used in PowerPC so far on 4K page size kernels where hash
mmu is used.  follow_page_mask() used to leverage hugetlb APIs to access
hugepd entries.  Teach follow_page_mask() itself on hugepd.

With previous refactors on fast-gup gup_huge_pd(), most of the code can be
easily leveraged.  There's something not needed for follow page, for
example, gup_hugepte() tries to detect pgtable entry change which will
never happen with slow gup (which has the pgtable lock held), but that's
not a problem to check.

Since follow_page() always only fetch one page, set the end to "address +
PAGE_SIZE" should suffice.  We will still do the pgtable walk once for each
hugetlb page by setting ctx->page_mask properly.

One thing worth mentioning is that some level of pgtable's _bad() helper
will report is_hugepd() entries as TRUE on Power8 hash MMUs.  I think it at
least applies to PUD on Power8 with 4K pgsize.  It means feeding a hugepd
entry to pud_bad() will report a false positive. Let's leave that for now
because it can be arch-specific where I am a bit declined to touch.  In
this patch it's not a problem as long as hugepd is detected before any bad
pgtable entries.

Signed-off-by: Peter Xu <peterx at redhat.com>
---
 mm/gup.c | 78 +++++++++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 69 insertions(+), 9 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c
index d96429b6fc55..245214b64108 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -30,6 +30,11 @@ struct follow_page_context {
 	unsigned int page_mask;
 };
 
+static struct page *follow_hugepd(struct vm_area_struct *vma, hugepd_t hugepd,
+				  unsigned long addr, unsigned int pdshift,
+				  unsigned int flags,
+				  struct follow_page_context *ctx);
+
 static inline void sanity_check_pinned_pages(struct page **pages,
 					     unsigned long npages)
 {
@@ -871,6 +876,9 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 		return no_page_table(vma, flags, address);
 	if (!pmd_present(pmdval))
 		return no_page_table(vma, flags, address);
+	if (unlikely(is_hugepd(__hugepd(pmd_val(pmdval)))))
+		return follow_hugepd(vma, __hugepd(pmd_val(pmdval)),
+				     address, PMD_SHIFT, flags, ctx);
 	if (pmd_devmap(pmdval)) {
 		ptl = pmd_lock(mm, pmd);
 		page = follow_devmap_pmd(vma, address, pmd, flags, &ctx->pgmap);
@@ -921,6 +929,9 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma,
 	pud = READ_ONCE(*pudp);
 	if (pud_none(pud) || !pud_present(pud))
 		return no_page_table(vma, flags, address);
+	if (unlikely(is_hugepd(__hugepd(pud_val(pud)))))
+		return follow_hugepd(vma, __hugepd(pud_val(pud)),
+				     address, PUD_SHIFT, flags, ctx);
 	if (pud_huge(pud)) {
 		ptl = pud_lock(mm, pudp);
 		page = follow_huge_pud(vma, address, pudp, flags, ctx);
@@ -940,13 +951,17 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma,
 				    unsigned int flags,
 				    struct follow_page_context *ctx)
 {
-	p4d_t *p4d;
+	p4d_t *p4d, p4dval;
 
 	p4d = p4d_offset(pgdp, address);
-	if (p4d_none(*p4d))
-		return no_page_table(vma, flags, address);
-	BUILD_BUG_ON(p4d_huge(*p4d));
-	if (unlikely(p4d_bad(*p4d)))
+	p4dval = *p4d;
+	BUILD_BUG_ON(p4d_huge(p4dval));
+
+	if (unlikely(is_hugepd(__hugepd(p4d_val(p4dval)))))
+		return follow_hugepd(vma, __hugepd(p4d_val(p4dval)),
+				     address, P4D_SHIFT, flags, ctx);
+
+	if (p4d_none(p4dval) || unlikely(p4d_bad(p4dval)))
 		return no_page_table(vma, flags, address);
 
 	return follow_pud_mask(vma, address, p4d, flags, ctx);
@@ -980,7 +995,7 @@ static struct page *follow_page_mask(struct vm_area_struct *vma,
 			      unsigned long address, unsigned int flags,
 			      struct follow_page_context *ctx)
 {
-	pgd_t *pgd;
+	pgd_t *pgd, pgdval;
 	struct mm_struct *mm = vma->vm_mm;
 
 	ctx->page_mask = 0;
@@ -995,11 +1010,17 @@ static struct page *follow_page_mask(struct vm_area_struct *vma,
 						&ctx->page_mask);
 
 	pgd = pgd_offset(mm, address);
+	pgdval = *pgd;
 
-	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
-		return no_page_table(vma, flags, address);
+	if (unlikely(is_hugepd(__hugepd(pgd_val(pgdval)))))
+		page = follow_hugepd(vma, __hugepd(pgd_val(pgdval)),
+				     address, PGDIR_SHIFT, flags, ctx);
+	else if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
+		page = no_page_table(vma, flags, address);
+	else
+		page = follow_p4d_mask(vma, address, pgd, flags, ctx);
 
-	return follow_p4d_mask(vma, address, pgd, flags, ctx);
+	return page;
 }
 
 struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
@@ -3026,6 +3047,37 @@ static int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
 
 	return 1;
 }
+
+static struct page *follow_hugepd(struct vm_area_struct *vma, hugepd_t hugepd,
+				  unsigned long addr, unsigned int pdshift,
+				  unsigned int flags,
+				  struct follow_page_context *ctx)
+{
+	struct page *page;
+	struct hstate *h;
+	spinlock_t *ptl;
+	int nr = 0, ret;
+	pte_t *ptep;
+
+	/* Only hugetlb supports hugepd */
+	if (WARN_ON_ONCE(!is_vm_hugetlb_page(vma)))
+		return ERR_PTR(-EFAULT);
+
+	h = hstate_vma(vma);
+	ptep = hugepte_offset(hugepd, addr, pdshift);
+	ptl = huge_pte_lock(h, vma->vm_mm, ptep);
+	ret = gup_huge_pd(hugepd, addr, pdshift, addr + PAGE_SIZE,
+			  flags, &page, &nr);
+	spin_unlock(ptl);
+
+	if (ret) {
+		WARN_ON_ONCE(nr != 1);
+		ctx->page_mask = (1U << huge_page_order(h)) - 1;
+		return page;
+	}
+
+	return NULL;
+}
 #else
 static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
 		unsigned int pdshift, unsigned long end, unsigned int flags,
@@ -3033,6 +3085,14 @@ static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
 {
 	return 0;
 }
+
+static struct page *follow_hugepd(struct vm_area_struct *vma, hugepd_t hugepd,
+				  unsigned long addr, unsigned int pdshift,
+				  unsigned int flags,
+				  struct follow_page_context *ctx)
+{
+	return NULL;
+}
 #endif /* CONFIG_ARCH_HAS_HUGEPD */
 
 static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
-- 
2.41.0




More information about the linux-riscv mailing list