Received-SPF: pass (google.com: best guess record for domain of linux-ext4-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   ira.weiny@intel.com
To:     Andrew Morton <akpm@linux-foundation.org>
Cc:     Jason Gunthorpe <jgg@ziepe.ca>,
        Dan Williams <dan.j.williams@intel.com>,
        Matthew Wilcox <willy@infradead.org>, Jan Kara <jack@suse.cz>,
        "Theodore Ts'o" <tytso@mit.edu>,
        John Hubbard <jhubbard@nvidia.com>,
        Michal Hocko <mhocko@suse.com>,
        Dave Chinner <david@fromorbit.com>, linux-xfs@vger.kernel.org,
        linux-rdma@vger.kernel.org, linux-kernel@vger.kernel.org,
        linux-fsdevel@vger.kernel.org, linux-nvdimm@lists.01.org,
        linux-ext4@vger.kernel.org, linux-mm@kvack.org,
        Ira Weiny <ira.weiny@intel.com>
Subject: [RFC PATCH v2 19/19] mm/gup: Remove FOLL_LONGTERM DAX exclusion
Date:   Fri,  9 Aug 2019 15:58:33 -0700
Message-Id: <20190809225833.6657-20-ira.weiny@intel.com>
In-Reply-To: <20190809225833.6657-1-ira.weiny@intel.com>
References: <20190809225833.6657-1-ira.weiny@intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-ext4-owner@vger.kernel.org
Precedence: bulk

From: Ira Weiny <ira.weiny@intel.com>

Now that there is a mechanism for users to safely take LONGTERM pins on
FS DAX pages, remove the FS DAX exclusion from the GUP implementation.

Special processing remains in effect for CONFIG_CMA

NOTE: Some callers still fail because the vaddr_pin information has not
been passed into the new interface.  As new users appear they can start
to use the new interface to support FS DAX.

Signed-off-by: Ira Weiny <ira.weiny@intel.com>
---
 mm/gup.c | 78 ++++++--------------------------------------------------
 1 file changed, 8 insertions(+), 70 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c
index 6d23f70d7847..58f008a3c153 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1415,26 +1415,6 @@ static long __get_user_pages_locked(struct task_struct *tsk,
 }
 #endif /* !CONFIG_MMU */
 
-#if defined(CONFIG_FS_DAX) || defined (CONFIG_CMA)
-static bool check_dax_vmas(struct vm_area_struct **vmas, long nr_pages)
-{
-	long i;
-	struct vm_area_struct *vma_prev = NULL;
-
-	for (i = 0; i < nr_pages; i++) {
-		struct vm_area_struct *vma = vmas[i];
-
-		if (vma == vma_prev)
-			continue;
-
-		vma_prev = vma;
-
-		if (vma_is_fsdax(vma))
-			return true;
-	}
-	return false;
-}
-
 #ifdef CONFIG_CMA
 static struct page *new_non_cma_page(struct page *page, unsigned long private)
 {
@@ -1568,18 +1548,6 @@ static long check_and_migrate_cma_pages(struct task_struct *tsk,
 
 	return nr_pages;
 }
-#else
-static long check_and_migrate_cma_pages(struct task_struct *tsk,
-					struct mm_struct *mm,
-					unsigned long start,
-					unsigned long nr_pages,
-					struct page **pages,
-					struct vm_area_struct **vmas,
-					unsigned int gup_flags)
-{
-	return nr_pages;
-}
-#endif /* CONFIG_CMA */
 
 /*
  * __gup_longterm_locked() is a wrapper for __get_user_pages_locked which
@@ -1594,49 +1562,28 @@ static long __gup_longterm_locked(struct task_struct *tsk,
 				  unsigned int gup_flags,
 				  struct vaddr_pin *vaddr_pin)
 {
-	struct vm_area_struct **vmas_tmp = vmas;
 	unsigned long flags = 0;
-	long rc, i;
+	long rc;
 
-	if (gup_flags & FOLL_LONGTERM) {
-		if (!pages)
-			return -EINVAL;
-
-		if (!vmas_tmp) {
-			vmas_tmp = kcalloc(nr_pages,
-					   sizeof(struct vm_area_struct *),
-					   GFP_KERNEL);
-			if (!vmas_tmp)
-				return -ENOMEM;
-		}
+	if (flags & FOLL_LONGTERM)
 		flags = memalloc_nocma_save();
-	}
 
 	rc = __get_user_pages_locked(tsk, mm, start, nr_pages, pages,
-				     vmas_tmp, NULL, gup_flags, vaddr_pin);
+				     vmas, NULL, gup_flags, vaddr_pin);
 
 	if (gup_flags & FOLL_LONGTERM) {
 		memalloc_nocma_restore(flags);
 		if (rc < 0)
 			goto out;
 
-		if (check_dax_vmas(vmas_tmp, rc)) {
-			for (i = 0; i < rc; i++)
-				put_page(pages[i]);
-			rc = -EOPNOTSUPP;
-			goto out;
-		}
-
 		rc = check_and_migrate_cma_pages(tsk, mm, start, rc, pages,
-						 vmas_tmp, gup_flags);
+						 vmas, gup_flags);
 	}
 
 out:
-	if (vmas_tmp != vmas)
-		kfree(vmas_tmp);
 	return rc;
 }
-#else /* !CONFIG_FS_DAX && !CONFIG_CMA */
+#else /* !CONFIG_CMA */
 static __always_inline long __gup_longterm_locked(struct task_struct *tsk,
 						  struct mm_struct *mm,
 						  unsigned long start,
@@ -1649,7 +1596,7 @@ static __always_inline long __gup_longterm_locked(struct task_struct *tsk,
 	return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,
 				       NULL, flags, vaddr_pin);
 }
-#endif /* CONFIG_FS_DAX || CONFIG_CMA */
+#endif /* CONFIG_CMA */
 
 /*
  * This is the same as get_user_pages_remote(), just with a
@@ -1887,9 +1834,6 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 			goto pte_unmap;
 
 		if (pte_devmap(pte)) {
-			if (unlikely(flags & FOLL_LONGTERM))
-				goto pte_unmap;
-
 			pgmap = get_dev_pagemap(pte_pfn(pte), pgmap);
 			if (unlikely(!pgmap)) {
 				undo_dev_pagemap(nr, nr_start, pages);
@@ -2139,12 +2083,9 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 	if (!pmd_access_permitted(orig, flags & FOLL_WRITE))
 		return 0;
 
-	if (pmd_devmap(orig)) {
-		if (unlikely(flags & FOLL_LONGTERM))
-			return 0;
+	if (pmd_devmap(orig))
 		return __gup_device_huge_pmd(orig, pmdp, addr, end, pages, nr,
 					     flags, vaddr_pin);
-	}
 
 	refs = 0;
 	page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
@@ -2182,12 +2123,9 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 	if (!pud_access_permitted(orig, flags & FOLL_WRITE))
 		return 0;
 
-	if (pud_devmap(orig)) {
-		if (unlikely(flags & FOLL_LONGTERM))
-			return 0;
+	if (pud_devmap(orig))
 		return __gup_device_huge_pud(orig, pudp, addr, end, pages, nr,
 					     flags, vaddr_pin);
-	}
 
 	refs = 0;
 	page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
-- 
2.20.1