All of lore.kernel.org
 help / color / mirror / Atom feed
From: Peter Xu <peterx@redhat.com>
To: linux-mm@kvack.org, linux-kernel@vger.kernel.org
Cc: Hugh Dickins <hughd@google.com>, Maya Gokhale <gokhale2@llnl.gov>,
	Jerome Glisse <jglisse@redhat.com>,
	Johannes Weiner <hannes@cmpxchg.org>,
	peterx@redhat.com, Martin Cracauer <cracauer@cons.org>,
	Denis Plotnikov <dplotnikov@virtuozzo.com>,
	Shaohua Li <shli@fb.com>, Andrea Arcangeli <aarcange@redhat.com>,
	Pavel Emelyanov <xemul@parallels.com>,
	Mike Kravetz <mike.kravetz@oracle.com>,
	Marty McFadden <mcfadden8@llnl.gov>,
	Mike Rapoport <rppt@linux.vnet.ibm.com>,
	Mel Gorman <mgorman@suse.de>,
	"Kirill A . Shutemov" <kirill@shutemov.name>,
	"Dr . David Alan Gilbert" <dgilbert@redhat.com>
Subject: [PATCH RFC 12/24] userfaultfd: wp: add UFFDIO_COPY_MODE_WP
Date: Mon, 21 Jan 2019 15:57:10 +0800	[thread overview]
Message-ID: <20190121075722.7945-13-peterx@redhat.com> (raw)
In-Reply-To: <20190121075722.7945-1-peterx@redhat.com>

From: Andrea Arcangeli <aarcange@redhat.com>

This allows UFFDIO_COPY to map pages wrprotected.

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
---
 fs/userfaultfd.c                 |  5 +++--
 include/linux/userfaultfd_k.h    |  2 +-
 include/uapi/linux/userfaultfd.h | 11 +++++-----
 mm/userfaultfd.c                 | 36 ++++++++++++++++++++++----------
 4 files changed, 35 insertions(+), 19 deletions(-)

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 6ff8773d6797..455b87c0596f 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1686,11 +1686,12 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
 	ret = -EINVAL;
 	if (uffdio_copy.src + uffdio_copy.len <= uffdio_copy.src)
 		goto out;
-	if (uffdio_copy.mode & ~UFFDIO_COPY_MODE_DONTWAKE)
+	if (uffdio_copy.mode & ~(UFFDIO_COPY_MODE_DONTWAKE|UFFDIO_COPY_MODE_WP))
 		goto out;
 	if (mmget_not_zero(ctx->mm)) {
 		ret = mcopy_atomic(ctx->mm, uffdio_copy.dst, uffdio_copy.src,
-				   uffdio_copy.len, &ctx->mmap_changing);
+				   uffdio_copy.len, &ctx->mmap_changing,
+				   uffdio_copy.mode);
 		mmput(ctx->mm);
 	} else {
 		return -ESRCH;
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 0d3b32b54e2a..7d870e9a5761 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -34,7 +34,7 @@ extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason);
 
 extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start,
 			    unsigned long src_start, unsigned long len,
-			    bool *mmap_changing);
+			    bool *mmap_changing, __u64 mode);
 extern ssize_t mfill_zeropage(struct mm_struct *dst_mm,
 			      unsigned long dst_start,
 			      unsigned long len,
diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
index 9de61cd8e228..a50f1ed24d23 100644
--- a/include/uapi/linux/userfaultfd.h
+++ b/include/uapi/linux/userfaultfd.h
@@ -208,13 +208,14 @@ struct uffdio_copy {
 	__u64 dst;
 	__u64 src;
 	__u64 len;
+#define UFFDIO_COPY_MODE_DONTWAKE		((__u64)1<<0)
 	/*
-	 * There will be a wrprotection flag later that allows to map
-	 * pages wrprotected on the fly. And such a flag will be
-	 * available if the wrprotection ioctl are implemented for the
-	 * range according to the uffdio_register.ioctls.
+	 * UFFDIO_COPY_MODE_WP will map the page wrprotected on the
+	 * fly. UFFDIO_COPY_MODE_WP is available only if the
+	 * wrprotection ioctl are implemented for the range according
+	 * to the uffdio_register.ioctls.
 	 */
-#define UFFDIO_COPY_MODE_DONTWAKE		((__u64)1<<0)
+#define UFFDIO_COPY_MODE_WP			((__u64)1<<1)
 	__u64 mode;
 
 	/*
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index c38903f501c7..005291b9b62f 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -25,7 +25,8 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm,
 			    struct vm_area_struct *dst_vma,
 			    unsigned long dst_addr,
 			    unsigned long src_addr,
-			    struct page **pagep)
+			    struct page **pagep,
+			    bool wp_copy)
 {
 	struct mem_cgroup *memcg;
 	pte_t _dst_pte, *dst_pte;
@@ -71,9 +72,9 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm,
 	if (mem_cgroup_try_charge(page, dst_mm, GFP_KERNEL, &memcg, false))
 		goto out_release;
 
-	_dst_pte = mk_pte(page, dst_vma->vm_page_prot);
-	if (dst_vma->vm_flags & VM_WRITE)
-		_dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte));
+	_dst_pte = pte_mkdirty(mk_pte(page, dst_vma->vm_page_prot));
+	if (dst_vma->vm_flags & VM_WRITE && !wp_copy)
+		_dst_pte = pte_mkwrite(_dst_pte);
 
 	dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
 	if (dst_vma->vm_file) {
@@ -399,7 +400,8 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm,
 						unsigned long dst_addr,
 						unsigned long src_addr,
 						struct page **page,
-						bool zeropage)
+						bool zeropage,
+						bool wp_copy)
 {
 	ssize_t err;
 
@@ -416,11 +418,13 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm,
 	if (!(dst_vma->vm_flags & VM_SHARED)) {
 		if (!zeropage)
 			err = mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma,
-					       dst_addr, src_addr, page);
+					       dst_addr, src_addr, page,
+					       wp_copy);
 		else
 			err = mfill_zeropage_pte(dst_mm, dst_pmd,
 						 dst_vma, dst_addr);
 	} else {
+		VM_WARN_ON(wp_copy); /* WP only available for anon */
 		if (!zeropage)
 			err = shmem_mcopy_atomic_pte(dst_mm, dst_pmd,
 						     dst_vma, dst_addr,
@@ -438,7 +442,8 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
 					      unsigned long src_start,
 					      unsigned long len,
 					      bool zeropage,
-					      bool *mmap_changing)
+					      bool *mmap_changing,
+					      __u64 mode)
 {
 	struct vm_area_struct *dst_vma;
 	ssize_t err;
@@ -446,6 +451,7 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
 	unsigned long src_addr, dst_addr;
 	long copied;
 	struct page *page;
+	bool wp_copy;
 
 	/*
 	 * Sanitize the command parameters:
@@ -502,6 +508,14 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
 	    dst_vma->vm_flags & VM_SHARED))
 		goto out_unlock;
 
+	/*
+	 * validate 'mode' now that we know the dst_vma: don't allow
+	 * a wrprotect copy if the userfaultfd didn't register as WP.
+	 */
+	wp_copy = mode & UFFDIO_COPY_MODE_WP;
+	if (wp_copy && !(dst_vma->vm_flags & VM_UFFD_WP))
+		goto out_unlock;
+
 	/*
 	 * If this is a HUGETLB vma, pass off to appropriate routine
 	 */
@@ -557,7 +571,7 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
 		BUG_ON(pmd_trans_huge(*dst_pmd));
 
 		err = mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr,
-				       src_addr, &page, zeropage);
+				       src_addr, &page, zeropage, wp_copy);
 		cond_resched();
 
 		if (unlikely(err == -ENOENT)) {
@@ -604,16 +618,16 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
 
 ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start,
 		     unsigned long src_start, unsigned long len,
-		     bool *mmap_changing)
+		     bool *mmap_changing, __u64 mode)
 {
 	return __mcopy_atomic(dst_mm, dst_start, src_start, len, false,
-			      mmap_changing);
+			      mmap_changing, mode);
 }
 
 ssize_t mfill_zeropage(struct mm_struct *dst_mm, unsigned long start,
 		       unsigned long len, bool *mmap_changing)
 {
-	return __mcopy_atomic(dst_mm, start, 0, len, true, mmap_changing);
+	return __mcopy_atomic(dst_mm, start, 0, len, true, mmap_changing, 0);
 }
 
 int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start,
-- 
2.17.1


  parent reply	other threads:[~2019-01-21  7:59 UTC|newest]

Thread overview: 65+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-01-21  7:56 [PATCH RFC 00/24] userfaultfd: write protection support Peter Xu
2019-01-21  7:56 ` [PATCH RFC 01/24] mm: gup: rename "nonblocking" to "locked" where proper Peter Xu
2019-01-21 10:20   ` Mike Rapoport
2019-01-21  7:57 ` [PATCH RFC 02/24] mm: userfault: return VM_FAULT_RETRY on signals Peter Xu
2019-01-21 15:40   ` Jerome Glisse
2019-01-22  6:10     ` Peter Xu
2019-01-21  7:57 ` [PATCH RFC 03/24] mm: allow VM_FAULT_RETRY for multiple times Peter Xu
2019-01-21 15:55   ` Jerome Glisse
2019-01-22  8:22     ` Peter Xu
2019-01-22 16:53       ` Jerome Glisse
2019-01-23  2:12         ` Peter Xu
2019-01-23  2:39           ` Jerome Glisse
2019-01-24  5:45             ` Peter Xu
2019-01-21  7:57 ` [PATCH RFC 04/24] mm: gup: " Peter Xu
2019-01-21 16:24   ` Jerome Glisse
2019-01-24  7:05     ` Peter Xu
2019-01-24 15:34       ` Jerome Glisse
2019-01-25  2:49         ` Peter Xu
2019-01-21  7:57 ` [PATCH RFC 05/24] userfaultfd: wp: add helper for writeprotect check Peter Xu
2019-01-21 10:23   ` Mike Rapoport
2019-01-22  8:31     ` Peter Xu
2019-01-21  7:57 ` [PATCH RFC 06/24] userfaultfd: wp: support write protection for userfault vma range Peter Xu
2019-01-21 10:20   ` Mike Rapoport
2019-01-22  8:55     ` Peter Xu
2019-01-21 14:05   ` Jerome Glisse
2019-01-22  9:39     ` Peter Xu
2019-01-22 17:02       ` Jerome Glisse
2019-01-23  2:17         ` Peter Xu
2019-01-23  2:43           ` Jerome Glisse
2019-01-24  5:47             ` Peter Xu
2019-01-21  7:57 ` [PATCH RFC 07/24] userfaultfd: wp: add the writeprotect API to userfaultfd ioctl Peter Xu
2019-01-21 10:42   ` Mike Rapoport
2019-01-24  4:56     ` Peter Xu
2019-01-24  7:27       ` Mike Rapoport
2019-01-24  9:28         ` Peter Xu
2019-01-25  7:54           ` Mike Rapoport
2019-01-25 10:12             ` Peter Xu
2019-01-21  7:57 ` [PATCH RFC 08/24] userfaultfd: wp: hook userfault handler to write protection fault Peter Xu
2019-01-21  7:57 ` [PATCH RFC 09/24] userfaultfd: wp: enabled write protection in userfaultfd API Peter Xu
2019-01-21  7:57 ` [PATCH RFC 10/24] userfaultfd: wp: add WP pagetable tracking to x86 Peter Xu
2019-01-21 15:09   ` Jerome Glisse
2019-01-24  5:16     ` Peter Xu
2019-01-24 15:40       ` Jerome Glisse
2019-01-25  3:30         ` Peter Xu
2019-01-21  7:57 ` [PATCH RFC 11/24] userfaultfd: wp: userfaultfd_pte/huge_pmd_wp() helpers Peter Xu
2019-01-21  7:57 ` Peter Xu [this message]
2019-01-21  7:57 ` [PATCH RFC 13/24] mm: merge parameters for change_protection() Peter Xu
2019-01-21 13:54   ` Jerome Glisse
2019-01-24  5:22     ` Peter Xu
2019-01-21  7:57 ` [PATCH RFC 14/24] userfaultfd: wp: apply _PAGE_UFFD_WP bit Peter Xu
2019-01-21  7:57 ` [PATCH RFC 15/24] mm: export wp_page_copy() Peter Xu
2019-01-21  7:57 ` [PATCH RFC 16/24] userfaultfd: wp: handle COW properly for uffd-wp Peter Xu
2019-01-21  7:57 ` [PATCH RFC 17/24] userfaultfd: wp: drop _PAGE_UFFD_WP properly when fork Peter Xu
2019-01-21  7:57 ` [PATCH RFC 18/24] userfaultfd: wp: add pmd_swp_*uffd_wp() helpers Peter Xu
2019-01-21  7:57 ` [PATCH RFC 19/24] userfaultfd: wp: support swap and page migration Peter Xu
2019-01-21  7:57 ` [PATCH RFC 20/24] userfaultfd: wp: don't wake up when doing write protect Peter Xu
2019-01-21 11:10   ` Mike Rapoport
2019-01-24  5:36     ` Peter Xu
2019-01-21  7:57 ` [PATCH RFC 21/24] khugepaged: skip collapse if uffd-wp detected Peter Xu
2019-01-21  7:57 ` [PATCH RFC 22/24] userfaultfd: wp: UFFDIO_REGISTER_MODE_WP documentation update Peter Xu
2019-01-21  7:57 ` [PATCH RFC 23/24] userfaultfd: selftests: refactor statistics Peter Xu
2019-01-21  7:57 ` [PATCH RFC 24/24] userfaultfd: selftests: add write-protect test Peter Xu
2019-01-21 14:33 ` [PATCH RFC 00/24] userfaultfd: write protection support David Hildenbrand
2019-01-22  3:18   ` Peter Xu
2019-01-22  8:59     ` David Hildenbrand

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190121075722.7945-13-peterx@redhat.com \
    --to=peterx@redhat.com \
    --cc=aarcange@redhat.com \
    --cc=cracauer@cons.org \
    --cc=dgilbert@redhat.com \
    --cc=dplotnikov@virtuozzo.com \
    --cc=gokhale2@llnl.gov \
    --cc=hannes@cmpxchg.org \
    --cc=hughd@google.com \
    --cc=jglisse@redhat.com \
    --cc=kirill@shutemov.name \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mcfadden8@llnl.gov \
    --cc=mgorman@suse.de \
    --cc=mike.kravetz@oracle.com \
    --cc=rppt@linux.vnet.ibm.com \
    --cc=shli@fb.com \
    --cc=xemul@parallels.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.