Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.37 as permitted sender) client-ip=23.128.96.37;
From:   Peter Xu <peterx@redhat.com>
To:     linux-kernel@vger.kernel.org, linux-mm@kvack.org
Cc:     Mike Kravetz <mike.kravetz@oracle.com>,
        "Kirill A . Shutemov" <kirill@shutemov.name>,
        Lorenzo Stoakes <lstoakes@gmail.com>,
        Axel Rasmussen <axelrasmussen@google.com>,
        Matthew Wilcox <willy@infradead.org>,
        John Hubbard <jhubbard@nvidia.com>,
        Mike Rapoport <rppt@kernel.org>, peterx@redhat.com,
        Hugh Dickins <hughd@google.com>,
        David Hildenbrand <david@redhat.com>,
        Andrea Arcangeli <aarcange@redhat.com>,
        Rik van Riel <riel@surriel.com>,
        James Houghton <jthoughton@google.com>,
        Yang Shi <shy828301@gmail.com>,
        Jason Gunthorpe <jgg@nvidia.com>,
        Vlastimil Babka <vbabka@suse.cz>,
        Andrew Morton <akpm@linux-foundation.org>
Subject: [PATCH RFC 11/12] mm/gup: Handle hugepd for follow_page()
Date:   Wed, 15 Nov 2023 20:29:07 -0500
Message-ID: <20231116012908.392077-12-peterx@redhat.com>
In-Reply-To: <20231116012908.392077-1-peterx@redhat.com>
References: <20231116012908.392077-1-peterx@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Hugepd is only used in PowerPC's hugetlbfs.  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.  Since follow_page() always only fetch one page, set the
end to "address + PAGE_SIZE" should suffice.

Signed-off-by: Peter Xu <peterx@redhat.com>
---
 mm/gup.c | 77 ++++++++++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 69 insertions(+), 8 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c
index 7c210206470f..e635278f65f9 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -25,6 +25,11 @@
 
 #include "internal.h"
 
+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)
 {
@@ -713,6 +718,9 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 		spin_unlock(ptl);
 		return page;
 	}
+	if (unlikely(is_hugepd(__hugepd(pmd_val(pmdval)))))
+		return follow_hugepd(vma, __hugepd(pmd_val(pmdval)),
+				     address, PMD_SHIFT, flags, ctx);
 	if (likely(!pmd_thp_or_huge(pmdval)))
 		return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
 
@@ -764,6 +772,10 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma,
 	if (unlikely(pud_bad(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);
+
 	return follow_pmd_mask(vma, address, pudp, flags, ctx);
 }
 
@@ -772,15 +784,19 @@ 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 (p4d_none(p4dval) || unlikely(p4d_bad(p4dval)))
 		return no_page_table(vma, flags, address);
 
+	if (unlikely(is_hugepd(__hugepd(p4d_val(p4dval)))))
+		return follow_hugepd(vma, __hugepd(p4d_val(p4dval)),
+				     address, P4D_SHIFT, flags, ctx);
+
 	return follow_pud_mask(vma, address, p4d, flags, ctx);
 }
 
@@ -812,7 +828,7 @@ 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;
@@ -827,11 +843,17 @@ 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);
+		page = no_page_table(vma, flags, address);
+	else if (unlikely(is_hugepd(__hugepd(pgd_val(pgdval)))))
+		page = follow_hugepd(vma, __hugepd(pgd_val(pgdval)),
+				     address, PGDIR_SHIFT, flags, ctx);
+	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,
@@ -2850,6 +2872,37 @@ 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, 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,
@@ -2857,6 +2910,14 @@ 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