mm/gup: handle hugepd for follow_page()

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
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.

To allow slow gup like follow_*_page() to access hugepd helpers, hugepd
codes are moved to the top.  Besides that, the helper record_subpages()
will be used by either hugepd or fast-gup now.  To avoid "unused function"
warnings we must provide a "#ifdef" for it, unfortunately.

Link: https://lkml.kernel.org/r/20240327152332.950956-13-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Tested-by: Ryan Roberts <ryan.roberts@arm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andrew Jones <andrew.jones@linux.dev>
Cc: Aneesh Kumar K.V (IBM) <aneesh.kumar@kernel.org>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: James Houghton <jthoughton@google.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Lorenzo Stoakes <lstoakes@gmail.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Mike Rapoport (IBM)" <rppt@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Rik van Riel <riel@surriel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 163 insertions, 106 deletions

diff --git a/mm/gup.c b/mm/gup.c
index f7028c698c26..a572a1169aa7 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -500,6 +500,149 @@ static inline void mm_set_has_pinned_flag(unsigned long *mm_flags)
 }
 
 #ifdef CONFIG_MMU
+
+#if defined(CONFIG_ARCH_HAS_HUGEPD) || defined(CONFIG_HAVE_FAST_GUP)
+static int record_subpages(struct page *page, unsigned long sz,
+			   unsigned long addr, unsigned long end,
+			   struct page **pages)
+{
+	struct page *start_page;
+	int nr;
+
+	start_page = nth_page(page, (addr & (sz - 1)) >> PAGE_SHIFT);
+	for (nr = 0; addr != end; nr++, addr += PAGE_SIZE)
+		pages[nr] = nth_page(start_page, nr);
+
+	return nr;
+}
+#endif	/* CONFIG_ARCH_HAS_HUGEPD || CONFIG_HAVE_FAST_GUP */
+
+#ifdef CONFIG_ARCH_HAS_HUGEPD
+static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
+				      unsigned long sz)
+{
+	unsigned long __boundary = (addr + sz) & ~(sz-1);
+	return (__boundary - 1 < end - 1) ? __boundary : end;
+}
+
+static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
+		       unsigned long end, unsigned int flags,
+		       struct page **pages, int *nr)
+{
+	unsigned long pte_end;
+	struct page *page;
+	struct folio *folio;
+	pte_t pte;
+	int refs;
+
+	pte_end = (addr + sz) & ~(sz-1);
+	if (pte_end < end)
+		end = pte_end;
+
+	pte = huge_ptep_get(ptep);
+
+	if (!pte_access_permitted(pte, flags & FOLL_WRITE))
+		return 0;
+
+	/* hugepages are never "special" */
+	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+
+	page = pte_page(pte);
+	refs = record_subpages(page, sz, addr, end, pages + *nr);
+
+	folio = try_grab_folio(page, refs, flags);
+	if (!folio)
+		return 0;
+
+	if (unlikely(pte_val(pte) != pte_val(ptep_get(ptep)))) {
+		gup_put_folio(folio, refs, flags);
+		return 0;
+	}
+
+	if (!pte_write(pte) && gup_must_unshare(NULL, flags, &folio->page)) {
+		gup_put_folio(folio, refs, flags);
+		return 0;
+	}
+
+	*nr += refs;
+	folio_set_referenced(folio);
+	return 1;
+}
+
+/*
+ * NOTE: currently GUP for a hugepd is only possible on hugetlbfs file
+ * systems on Power, which does not have issue with folio writeback against
+ * GUP updates.  When hugepd will be extended to support non-hugetlbfs or
+ * even anonymous memory, we need to do extra check as what we do with most
+ * of the other folios. See writable_file_mapping_allowed() and
+ * gup_fast_folio_allowed() for more information.
+ */
+static int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
+		unsigned int pdshift, unsigned long end, unsigned int flags,
+		struct page **pages, int *nr)
+{
+	pte_t *ptep;
+	unsigned long sz = 1UL << hugepd_shift(hugepd);
+	unsigned long next;
+
+	ptep = hugepte_offset(hugepd, addr, pdshift);
+	do {
+		next = hugepte_addr_end(addr, end, sz);
+		if (!gup_hugepte(ptep, sz, addr, end, flags, pages, nr))
+			return 0;
+	} while (ptep++, addr = next, addr != end);
+
+	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 /* CONFIG_ARCH_HAS_HUGEPD */
+static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
+		unsigned int pdshift, unsigned long end, unsigned int flags,
+		struct page **pages, int *nr)
+{
+	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 struct page *no_page_table(struct vm_area_struct *vma,
 				  unsigned int flags, unsigned long address)
 {
@@ -868,6 +1011,9 @@ 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);
@@ -918,6 +1064,9 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma,
 	pud = READ_ONCE(*pudp);
 	if (!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_leaf(pud)) {
 		ptl = pud_lock(mm, pudp);
 		page = follow_huge_pud(vma, address, pudp, flags, ctx);
@@ -941,10 +1090,13 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma,
 
 	p4dp = p4d_offset(pgdp, address);
 	p4d = READ_ONCE(*p4dp);
-	if (!p4d_present(p4d))
-		return no_page_table(vma, flags, address);
 	BUILD_BUG_ON(p4d_leaf(p4d));
-	if (unlikely(p4d_bad(p4d)))
+
+	if (unlikely(is_hugepd(__hugepd(p4d_val(p4d)))))
+		return follow_hugepd(vma, __hugepd(p4d_val(p4d)),
+				     address, P4D_SHIFT, flags, ctx);
+
+	if (!p4d_present(p4d) || p4d_bad(p4d))
 		return no_page_table(vma, flags, address);
 
 	return follow_pud_mask(vma, address, p4dp, flags, ctx);
@@ -994,10 +1146,15 @@ static struct page *follow_page_mask(struct vm_area_struct *vma,
 
 	pgd = pgd_offset(mm, address);
 
-	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
-		return no_page_table(vma, flags, address);
+	if (unlikely(is_hugepd(__hugepd(pgd_val(*pgd)))))
+		page = follow_hugepd(vma, __hugepd(pgd_val(*pgd)),
+				     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,
@@ -2954,106 +3111,6 @@ static int __gup_device_huge_pud(pud_t pud, pud_t *pudp, unsigned long addr,
 }
 #endif
 
-static int record_subpages(struct page *page, unsigned long sz,
-			   unsigned long addr, unsigned long end,
-			   struct page **pages)
-{
-	struct page *start_page;
-	int nr;
-
-	start_page = nth_page(page, (addr & (sz - 1)) >> PAGE_SHIFT);
-	for (nr = 0; addr != end; nr++, addr += PAGE_SIZE)
-		pages[nr] = nth_page(start_page, nr);
-
-	return nr;
-}
-
-#ifdef CONFIG_ARCH_HAS_HUGEPD
-static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
-				      unsigned long sz)
-{
-	unsigned long __boundary = (addr + sz) & ~(sz-1);
-	return (__boundary - 1 < end - 1) ? __boundary : end;
-}
-
-static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
-		       unsigned long end, unsigned int flags,
-		       struct page **pages, int *nr)
-{
-	unsigned long pte_end;
-	struct page *page;
-	struct folio *folio;
-	pte_t pte;
-	int refs;
-
-	pte_end = (addr + sz) & ~(sz-1);
-	if (pte_end < end)
-		end = pte_end;
-
-	pte = huge_ptep_get(ptep);
-
-	if (!pte_access_permitted(pte, flags & FOLL_WRITE))
-		return 0;
-
-	/* hugepages are never "special" */
-	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
-
-	page = pte_page(pte);
-	refs = record_subpages(page, sz, addr, end, pages + *nr);
-
-	folio = try_grab_folio(page, refs, flags);
-	if (!folio)
-		return 0;
-
-	if (unlikely(pte_val(pte) != pte_val(ptep_get(ptep)))) {
-		gup_put_folio(folio, refs, flags);
-		return 0;
-	}
-
-	if (!pte_write(pte) && gup_must_unshare(NULL, flags, &folio->page)) {
-		gup_put_folio(folio, refs, flags);
-		return 0;
-	}
-
-	*nr += refs;
-	folio_set_referenced(folio);
-	return 1;
-}
-
-/*
- * NOTE: currently GUP for a hugepd is only possible on hugetlbfs file
- * systems on Power, which does not have issue with folio writeback against
- * GUP updates.  When hugepd will be extended to support non-hugetlbfs or
- * even anonymous memory, we need to do extra check as what we do with most
- * of the other folios. See writable_file_mapping_allowed() and
- * gup_fast_folio_allowed() for more information.
- */
-static int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
-		unsigned int pdshift, unsigned long end, unsigned int flags,
-		struct page **pages, int *nr)
-{
-	pte_t *ptep;
-	unsigned long sz = 1UL << hugepd_shift(hugepd);
-	unsigned long next;
-
-	ptep = hugepte_offset(hugepd, addr, pdshift);
-	do {
-		next = hugepte_addr_end(addr, end, sz);
-		if (!gup_hugepte(ptep, sz, addr, end, flags, pages, nr))
-			return 0;
-	} while (ptep++, addr = next, addr != end);
-
-	return 1;
-}
-#else
-static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
-		unsigned int pdshift, unsigned long end, unsigned int flags,
-		struct page **pages, int *nr)
-{
-	return 0;
-}
-#endif /* CONFIG_ARCH_HAS_HUGEPD */
-
 static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 			unsigned long end, unsigned int flags,
 			struct page **pages, int *nr)