Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To:     linux-kernel@vger.kernel.org
Cc:     Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
        stable@vger.kernel.org, Andrea Arcangeli <aarcange@redhat.com>,
        Mike Rapoport <rppt@linux.ibm.com>,
        Hugh Dickins <hughd@google.com>, Jann Horn <jannh@google.com>,
        "Dr. David Alan Gilbert" <dgilbert@redhat.com>,
        Mike Kravetz <mike.kravetz@oracle.com>,
        Peter Xu <peterx@redhat.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Linus Torvalds <torvalds@linux-foundation.org>
Subject: [PATCH 4.14 24/55] userfaultfd: shmem: add i_size checks
Date:   Thu,  6 Dec 2018 15:38:58 +0100
Message-Id: <20181206143003.056725404@linuxfoundation.org>
In-Reply-To: <20181206143001.749982936@linuxfoundation.org>
References: <20181206143001.749982936@linuxfoundation.org>
User-Agent: quilt/0.65
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

4.14-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Andrea Arcangeli <aarcange@redhat.com>

commit e2a50c1f64145a04959df2442305d57307e5395a upstream.

With MAP_SHARED: recheck the i_size after taking the PT lock, to
serialize against truncate with the PT lock.  Delete the page from the
pagecache if the i_size_read check fails.

With MAP_PRIVATE: check the i_size after the PT lock before mapping
anonymous memory or zeropages into the MAP_PRIVATE shmem mapping.

A mostly irrelevant cleanup: like we do the delete_from_page_cache()
pagecache removal after dropping the PT lock, the PT lock is a spinlock
so drop it before the sleepable page lock.

Link: http://lkml.kernel.org/r/20181126173452.26955-5-aarcange@redhat.com
Fixes: 4c27fe4c4c84 ("userfaultfd: shmem: add shmem_mcopy_atomic_pte for userfaultfd support")
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Reviewed-by: Hugh Dickins <hughd@google.com>
Reported-by: Jann Horn <jannh@google.com>
Cc: <stable@vger.kernel.org>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

---
 mm/shmem.c       |   18 ++++++++++++++++--
 mm/userfaultfd.c |   26 ++++++++++++++++++++++++--
 2 files changed, 40 insertions(+), 4 deletions(-)

--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2244,6 +2244,7 @@ static int shmem_mfill_atomic_pte(struct
 	struct page *page;
 	pte_t _dst_pte, *dst_pte;
 	int ret;
+	pgoff_t offset, max_off;
 
 	ret = -ENOMEM;
 	if (!shmem_inode_acct_block(inode, 1))
@@ -2281,6 +2282,12 @@ static int shmem_mfill_atomic_pte(struct
 	__SetPageSwapBacked(page);
 	__SetPageUptodate(page);
 
+	ret = -EFAULT;
+	offset = linear_page_index(dst_vma, dst_addr);
+	max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
+	if (unlikely(offset >= max_off))
+		goto out_release;
+
 	ret = mem_cgroup_try_charge(page, dst_mm, gfp, &memcg, false);
 	if (ret)
 		goto out_release;
@@ -2299,8 +2306,14 @@ static int shmem_mfill_atomic_pte(struct
 	if (dst_vma->vm_flags & VM_WRITE)
 		_dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte));
 
-	ret = -EEXIST;
 	dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
+
+	ret = -EFAULT;
+	max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
+	if (unlikely(offset >= max_off))
+		goto out_release_uncharge_unlock;
+
+	ret = -EEXIST;
 	if (!pte_none(*dst_pte))
 		goto out_release_uncharge_unlock;
 
@@ -2318,13 +2331,14 @@ static int shmem_mfill_atomic_pte(struct
 
 	/* No need to invalidate - it was non-present before */
 	update_mmu_cache(dst_vma, dst_addr, dst_pte);
-	unlock_page(page);
 	pte_unmap_unlock(dst_pte, ptl);
+	unlock_page(page);
 	ret = 0;
 out:
 	return ret;
 out_release_uncharge_unlock:
 	pte_unmap_unlock(dst_pte, ptl);
+	delete_from_page_cache(page);
 out_release_uncharge:
 	mem_cgroup_cancel_charge(page, memcg, false);
 out_release:
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -34,6 +34,8 @@ static int mcopy_atomic_pte(struct mm_st
 	void *page_kaddr;
 	int ret;
 	struct page *page;
+	pgoff_t offset, max_off;
+	struct inode *inode;
 
 	if (!*pagep) {
 		ret = -ENOMEM;
@@ -74,8 +76,17 @@ static int mcopy_atomic_pte(struct mm_st
 	if (dst_vma->vm_flags & VM_WRITE)
 		_dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte));
 
-	ret = -EEXIST;
 	dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
+	if (dst_vma->vm_file) {
+		/* the shmem MAP_PRIVATE case requires checking the i_size */
+		inode = dst_vma->vm_file->f_inode;
+		offset = linear_page_index(dst_vma, dst_addr);
+		max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
+		ret = -EFAULT;
+		if (unlikely(offset >= max_off))
+			goto out_release_uncharge_unlock;
+	}
+	ret = -EEXIST;
 	if (!pte_none(*dst_pte))
 		goto out_release_uncharge_unlock;
 
@@ -109,11 +120,22 @@ static int mfill_zeropage_pte(struct mm_
 	pte_t _dst_pte, *dst_pte;
 	spinlock_t *ptl;
 	int ret;
+	pgoff_t offset, max_off;
+	struct inode *inode;
 
 	_dst_pte = pte_mkspecial(pfn_pte(my_zero_pfn(dst_addr),
 					 dst_vma->vm_page_prot));
-	ret = -EEXIST;
 	dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
+	if (dst_vma->vm_file) {
+		/* the shmem MAP_PRIVATE case requires checking the i_size */
+		inode = dst_vma->vm_file->f_inode;
+		offset = linear_page_index(dst_vma, dst_addr);
+		max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
+		ret = -EFAULT;
+		if (unlikely(offset >= max_off))
+			goto out_unlock;
+	}
+	ret = -EEXIST;
 	if (!pte_none(*dst_pte))
 		goto out_unlock;
 	set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);