Received-SPF: pass (google.com: domain of linux-kernel+bounces-110736-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
From: peterx@redhat.com
To: linux-mm@kvack.org,
	linux-kernel@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org,
	Michael Ellerman <mpe@ellerman.id.au>,
	Christophe Leroy <christophe.leroy@csgroup.eu>,
	Matthew Wilcox <willy@infradead.org>,
	Rik van Riel <riel@surriel.com>,
	Lorenzo Stoakes <lstoakes@gmail.com>,
	Axel Rasmussen <axelrasmussen@google.com>,
	peterx@redhat.com,
	Yang Shi <shy828301@gmail.com>,
	John Hubbard <jhubbard@nvidia.com>,
	linux-arm-kernel@lists.infradead.org,
	"Kirill A . Shutemov" <kirill@shutemov.name>,
	Andrew Jones <andrew.jones@linux.dev>,
	Vlastimil Babka <vbabka@suse.cz>,
	Mike Rapoport <rppt@kernel.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Muchun Song <muchun.song@linux.dev>,
	Christoph Hellwig <hch@infradead.org>,
	linux-riscv@lists.infradead.org,
	James Houghton <jthoughton@google.com>,
	David Hildenbrand <david@redhat.com>,
	Jason Gunthorpe <jgg@nvidia.com>,
	Andrea Arcangeli <aarcange@redhat.com>,
	"Aneesh Kumar K . V" <aneesh.kumar@kernel.org>,
	Mike Kravetz <mike.kravetz@oracle.com>
Subject: [PATCH v3 10/12] mm/gup: Handle huge pmd for follow_pmd_mask()
Date: Thu, 21 Mar 2024 18:08:00 -0400
Message-ID: <20240321220802.679544-11-peterx@redhat.com>
In-Reply-To: <20240321220802.679544-1-peterx@redhat.com>
References: <20240321220802.679544-1-peterx@redhat.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

From: Peter Xu <peterx@redhat.com>

Replace pmd_trans_huge() with pmd_leaf() to also cover pmd_huge() as long
as enabled.

FOLL_TOUCH and FOLL_SPLIT_PMD only apply to THP, not yet huge.

Since now follow_trans_huge_pmd() can process hugetlb pages, renaming it
into follow_huge_pmd() to match what it does.  Move it into gup.c so not
depend on CONFIG_THP.

When at it, move the ctx->page_mask setup into follow_huge_pmd(), only set
it when the page is valid.  It was not a bug to set it before even if GUP
failed (page==NULL), because follow_page_mask() callers always ignores
page_mask if so.  But doing so makes the code cleaner.

Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
---
 mm/gup.c         | 107 ++++++++++++++++++++++++++++++++++++++++++++---
 mm/huge_memory.c |  86 +------------------------------------
 mm/internal.h    |   5 +--
 3 files changed, 105 insertions(+), 93 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c
index ae21afb9434e..00cdf4cb0cd4 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -580,6 +580,93 @@ static struct page *follow_huge_pud(struct vm_area_struct *vma,
 
 	return page;
 }
+
+/* FOLL_FORCE can write to even unwritable PMDs in COW mappings. */
+static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page,
+					struct vm_area_struct *vma,
+					unsigned int flags)
+{
+	/* If the pmd is writable, we can write to the page. */
+	if (pmd_write(pmd))
+		return true;
+
+	/* Maybe FOLL_FORCE is set to override it? */
+	if (!(flags & FOLL_FORCE))
+		return false;
+
+	/* But FOLL_FORCE has no effect on shared mappings */
+	if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED))
+		return false;
+
+	/* ... or read-only private ones */
+	if (!(vma->vm_flags & VM_MAYWRITE))
+		return false;
+
+	/* ... or already writable ones that just need to take a write fault */
+	if (vma->vm_flags & VM_WRITE)
+		return false;
+
+	/*
+	 * See can_change_pte_writable(): we broke COW and could map the page
+	 * writable if we have an exclusive anonymous page ...
+	 */
+	if (!page || !PageAnon(page) || !PageAnonExclusive(page))
+		return false;
+
+	/* ... and a write-fault isn't required for other reasons. */
+	if (vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd))
+		return false;
+	return !userfaultfd_huge_pmd_wp(vma, pmd);
+}
+
+static struct page *follow_huge_pmd(struct vm_area_struct *vma,
+				    unsigned long addr, pmd_t *pmd,
+				    unsigned int flags,
+				    struct follow_page_context *ctx)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	pmd_t pmdval = *pmd;
+	struct page *page;
+	int ret;
+
+	assert_spin_locked(pmd_lockptr(mm, pmd));
+
+	page = pmd_page(pmdval);
+	VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page);
+
+	if ((flags & FOLL_WRITE) &&
+	    !can_follow_write_pmd(pmdval, page, vma, flags))
+		return NULL;
+
+	/* Avoid dumping huge zero page */
+	if ((flags & FOLL_DUMP) && is_huge_zero_pmd(pmdval))
+		return ERR_PTR(-EFAULT);
+
+	if (pmd_protnone(*pmd) && !gup_can_follow_protnone(vma, flags))
+		return NULL;
+
+	if (!pmd_write(pmdval) && gup_must_unshare(vma, flags, page))
+		return ERR_PTR(-EMLINK);
+
+	VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) &&
+			!PageAnonExclusive(page), page);
+
+	ret = try_grab_page(page, flags);
+	if (ret)
+		return ERR_PTR(ret);
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	if (pmd_trans_huge(pmdval) && (flags & FOLL_TOUCH))
+		touch_pmd(vma, addr, pmd, flags & FOLL_WRITE);
+#endif	/* CONFIG_TRANSPARENT_HUGEPAGE */
+
+	page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT;
+	ctx->page_mask = HPAGE_PMD_NR - 1;
+	VM_BUG_ON_PAGE(!PageCompound(page) && !is_zone_device_page(page), page);
+
+	return page;
+}
+
 #else  /* CONFIG_PGTABLE_HAS_HUGE_LEAVES */
 static struct page *follow_huge_pud(struct vm_area_struct *vma,
 				    unsigned long addr, pud_t *pudp,
@@ -587,6 +674,14 @@ static struct page *follow_huge_pud(struct vm_area_struct *vma,
 {
 	return NULL;
 }
+
+static struct page *follow_huge_pmd(struct vm_area_struct *vma,
+				    unsigned long addr, pmd_t *pmd,
+				    unsigned int flags,
+				    struct follow_page_context *ctx)
+{
+	return NULL;
+}
 #endif	/* CONFIG_PGTABLE_HAS_HUGE_LEAVES */
 
 static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address,
@@ -784,31 +879,31 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 			return page;
 		return no_page_table(vma, flags, address);
 	}
-	if (likely(!pmd_trans_huge(pmdval)))
+	if (likely(!pmd_leaf(pmdval)))
 		return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
 
 	if (pmd_protnone(pmdval) && !gup_can_follow_protnone(vma, flags))
 		return no_page_table(vma, flags, address);
 
 	ptl = pmd_lock(mm, pmd);
-	if (unlikely(!pmd_present(*pmd))) {
+	pmdval = *pmd;
+	if (unlikely(!pmd_present(pmdval))) {
 		spin_unlock(ptl);
 		return no_page_table(vma, flags, address);
 	}
-	if (unlikely(!pmd_trans_huge(*pmd))) {
+	if (unlikely(!pmd_leaf(pmdval))) {
 		spin_unlock(ptl);
 		return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
 	}
-	if (flags & FOLL_SPLIT_PMD) {
+	if (pmd_trans_huge(pmdval) && (flags & FOLL_SPLIT_PMD)) {
 		spin_unlock(ptl);
 		split_huge_pmd(vma, pmd, address);
 		/* If pmd was left empty, stuff a page table in there quickly */
 		return pte_alloc(mm, pmd) ? ERR_PTR(-ENOMEM) :
 			follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
 	}
-	page = follow_trans_huge_pmd(vma, address, pmd, flags);
+	page = follow_huge_pmd(vma, address, pmd, flags, ctx);
 	spin_unlock(ptl);
-	ctx->page_mask = HPAGE_PMD_NR - 1;
 	return page;
 }
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index f8bd2012bc27..e747dacb5051 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1206,8 +1206,8 @@ vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write)
 EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud);
 #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
 
-static void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
-		      pmd_t *pmd, bool write)
+void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
+	       pmd_t *pmd, bool write)
 {
 	pmd_t _pmd;
 
@@ -1562,88 +1562,6 @@ static inline bool can_change_pmd_writable(struct vm_area_struct *vma,
 	return pmd_dirty(pmd);
 }
 
-/* FOLL_FORCE can write to even unwritable PMDs in COW mappings. */
-static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page,
-					struct vm_area_struct *vma,
-					unsigned int flags)
-{
-	/* If the pmd is writable, we can write to the page. */
-	if (pmd_write(pmd))
-		return true;
-
-	/* Maybe FOLL_FORCE is set to override it? */
-	if (!(flags & FOLL_FORCE))
-		return false;
-
-	/* But FOLL_FORCE has no effect on shared mappings */
-	if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED))
-		return false;
-
-	/* ... or read-only private ones */
-	if (!(vma->vm_flags & VM_MAYWRITE))
-		return false;
-
-	/* ... or already writable ones that just need to take a write fault */
-	if (vma->vm_flags & VM_WRITE)
-		return false;
-
-	/*
-	 * See can_change_pte_writable(): we broke COW and could map the page
-	 * writable if we have an exclusive anonymous page ...
-	 */
-	if (!page || !PageAnon(page) || !PageAnonExclusive(page))
-		return false;
-
-	/* ... and a write-fault isn't required for other reasons. */
-	if (vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd))
-		return false;
-	return !userfaultfd_huge_pmd_wp(vma, pmd);
-}
-
-struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
-				   unsigned long addr,
-				   pmd_t *pmd,
-				   unsigned int flags)
-{
-	struct mm_struct *mm = vma->vm_mm;
-	struct page *page;
-	int ret;
-
-	assert_spin_locked(pmd_lockptr(mm, pmd));
-
-	page = pmd_page(*pmd);
-	VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page);
-
-	if ((flags & FOLL_WRITE) &&
-	    !can_follow_write_pmd(*pmd, page, vma, flags))
-		return NULL;
-
-	/* Avoid dumping huge zero page */
-	if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd))
-		return ERR_PTR(-EFAULT);
-
-	if (pmd_protnone(*pmd) && !gup_can_follow_protnone(vma, flags))
-		return NULL;
-
-	if (!pmd_write(*pmd) && gup_must_unshare(vma, flags, page))
-		return ERR_PTR(-EMLINK);
-
-	VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) &&
-			!PageAnonExclusive(page), page);
-
-	ret = try_grab_page(page, flags);
-	if (ret)
-		return ERR_PTR(ret);
-
-	if (flags & FOLL_TOUCH)
-		touch_pmd(vma, addr, pmd, flags & FOLL_WRITE);
-
-	page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT;
-	VM_BUG_ON_PAGE(!PageCompound(page) && !is_zone_device_page(page), page);
-
-	return page;
-}
-
 /* NUMA hinting page fault entry point for trans huge pmds */
 vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
 {
diff --git a/mm/internal.h b/mm/internal.h
index 63e4f6e001be..d47862e6d968 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1104,9 +1104,8 @@ int __must_check try_grab_page(struct page *page, unsigned int flags);
  */
 void touch_pud(struct vm_area_struct *vma, unsigned long addr,
 	       pud_t *pud, bool write);
-struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
-				   unsigned long addr, pmd_t *pmd,
-				   unsigned int flags);
+void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
+	       pmd_t *pmd, bool write);
 
 #ifdef CONFIG_MEMCG
 static inline
-- 
2.44.0