From: Peter Xu <peterx@redhat.com>
To: linux-mm@kvack.org, linux-kernel@vger.kernel.org
Cc: David Hildenbrand <david@redhat.com>,
Hugh Dickins <hughd@google.com>, Maya Gokhale <gokhale2@llnl.gov>,
Jerome Glisse <jglisse@redhat.com>,
Pavel Emelyanov <xemul@virtuozzo.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>,
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 v5 10/25] userfaultfd: wp: add UFFDIO_COPY_MODE_WP
Date: Thu, 20 Jun 2019 10:19:53 +0800 [thread overview]
Message-ID: <20190620022008.19172-11-peterx@redhat.com> (raw)
In-Reply-To: <20190620022008.19172-1-peterx@redhat.com>
From: Andrea Arcangeli <aarcange@redhat.com>
This allows UFFDIO_COPY to map pages write-protected.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
[peterx: switch to VM_WARN_ON_ONCE in mfill_atomic_pte; add brackets
around "dst_vma->vm_flags & VM_WRITE"; fix wordings in comments and
commit messages]
Reviewed-by: Jerome Glisse <jglisse@redhat.com>
Reviewed-by: Mike Rapoport <rppt@linux.vnet.ibm.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 5dbef45ecbf5..c594945ad5bf 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1694,11 +1694,12 @@ 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 7b91b76aac58..dcd33172b728 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -36,7 +36,7 @@ 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 48f1a7c2f1f0..340f23bc251d 100644
--- a/include/uapi/linux/userfaultfd.h
+++ b/include/uapi/linux/userfaultfd.h
@@ -203,13 +203,14 @@ 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 write protected on
+ * the fly. UFFDIO_COPY_MODE_WP is available only if the
+ * write protected ioctl is 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 9932d5755e4c..c8e7846e9b7e 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) {
@@ -398,7 +399,8 @@ 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;
@@ -415,11 +417,13 @@ 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_ONCE(wp_copy);
if (!zeropage)
err = shmem_mcopy_atomic_pte(dst_mm, dst_pmd,
dst_vma, dst_addr,
@@ -437,7 +441,8 @@ 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;
@@ -445,6 +450,7 @@ 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:
@@ -501,6 +507,14 @@ 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
*/
@@ -556,7 +570,7 @@ 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)) {
@@ -603,14 +617,14 @@ 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);
}
--
2.21.0
next prev parent reply other threads:[~2019-06-20 2:22 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-06-20 2:19 [PATCH v5 00/25] userfaultfd: write protection support Peter Xu
2019-06-20 2:19 ` [PATCH v5 01/25] mm: gup: rename "nonblocking" to "locked" where proper Peter Xu
2019-06-20 2:19 ` [PATCH v5 02/25] mm: userfault: return VM_FAULT_RETRY on signals Peter Xu
2019-06-22 18:02 ` Linus Torvalds
2019-06-22 18:02 ` Linus Torvalds
2019-06-24 7:42 ` Peter Xu
2019-06-24 13:31 ` Linus Torvalds
2019-06-24 13:31 ` Linus Torvalds
2019-06-25 5:30 ` Peter Xu
2019-06-26 1:59 ` Linus Torvalds
2019-06-26 1:59 ` Linus Torvalds
2019-06-26 7:43 ` Peter Xu
2019-06-20 2:19 ` [PATCH v5 03/25] userfaultfd: don't retake mmap_sem to emulate NOPAGE Peter Xu
2019-06-20 2:19 ` [PATCH v5 04/25] mm: allow VM_FAULT_RETRY for multiple times Peter Xu
2019-06-20 2:19 ` [PATCH v5 05/25] mm: gup: " Peter Xu
2019-06-20 2:19 ` [PATCH v5 06/25] userfaultfd: wp: add helper for writeprotect check Peter Xu
2019-06-20 2:19 ` [PATCH v5 07/25] userfaultfd: wp: hook userfault handler to write protection fault Peter Xu
2019-06-20 2:19 ` [PATCH v5 08/25] userfaultfd: wp: add WP pagetable tracking to x86 Peter Xu
2019-06-20 2:19 ` [PATCH v5 09/25] userfaultfd: wp: userfaultfd_pte/huge_pmd_wp() helpers Peter Xu
2019-06-20 2:19 ` Peter Xu [this message]
2019-06-20 2:19 ` [PATCH v5 11/25] mm: merge parameters for change_protection() Peter Xu
2019-06-20 2:19 ` [PATCH v5 12/25] userfaultfd: wp: apply _PAGE_UFFD_WP bit Peter Xu
2019-06-20 2:19 ` [PATCH v5 13/25] userfaultfd: wp: drop _PAGE_UFFD_WP properly when fork Peter Xu
2019-06-20 2:19 ` [PATCH v5 14/25] userfaultfd: wp: add pmd_swp_*uffd_wp() helpers Peter Xu
2019-06-20 2:19 ` [PATCH v5 15/25] userfaultfd: wp: support swap and page migration Peter Xu
2019-06-20 2:19 ` [PATCH v5 16/25] khugepaged: skip collapse if uffd-wp detected Peter Xu
2019-06-20 2:20 ` [PATCH v5 17/25] userfaultfd: introduce helper vma_find_uffd Peter Xu
2019-06-20 2:20 ` [PATCH v5 18/25] userfaultfd: wp: support write protection for userfault vma range Peter Xu
2019-06-20 2:20 ` [PATCH v5 19/25] userfaultfd: wp: add the writeprotect API to userfaultfd ioctl Peter Xu
2019-06-20 2:20 ` [PATCH v5 20/25] userfaultfd: wp: enabled write protection in userfaultfd API Peter Xu
2019-06-20 2:20 ` [PATCH v5 21/25] userfaultfd: wp: don't wake up when doing write protect Peter Xu
2019-06-20 2:20 ` [PATCH v5 22/25] userfaultfd: wp: UFFDIO_REGISTER_MODE_WP documentation update Peter Xu
2019-06-20 2:20 ` [PATCH v5 23/25] userfaultfd: wp: declare _UFFDIO_WRITEPROTECT conditionally Peter Xu
2019-06-20 2:20 ` [PATCH v5 24/25] userfaultfd: selftests: refactor statistics Peter Xu
2019-06-20 2:20 ` [PATCH v5 25/25] userfaultfd: selftests: add write-protect test Peter Xu
2019-06-23 8:39 ` [PATCH v5 10/25] userfaultfd: wp: add UFFDIO_COPY_MODE_WP Hillf Danton
2020-02-18 3:59 ` [PATCH v5 00/25] userfaultfd: write protection support Bobby Powers
2020-02-18 3:59 ` Bobby Powers
2020-02-18 16:11 ` Peter Xu
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=20190620022008.19172-11-peterx@redhat.com \
--to=peterx@redhat.com \
--cc=aarcange@redhat.com \
--cc=cracauer@cons.org \
--cc=david@redhat.com \
--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@virtuozzo.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.