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 07/24] userfaultfd: wp: add the writeprotect API to userfaultfd ioctl
Date: Mon, 21 Jan 2019 15:57:05 +0800 [thread overview]
Message-ID: <20190121075722.7945-8-peterx@redhat.com> (raw)
In-Reply-To: <20190121075722.7945-1-peterx@redhat.com>
From: Andrea Arcangeli <aarcange@redhat.com>
v1: From: Shaohua Li <shli@fb.com>
v2: cleanups, remove a branch.
[peterx writes up the commit message, as below...]
This patch introduces the new uffd-wp APIs for userspace.
Firstly, we'll allow to do UFFDIO_REGISTER with write protection
tracking using the new UFFDIO_REGISTER_MODE_WP flag. Note that this
flag can co-exist with the existing UFFDIO_REGISTER_MODE_MISSING, in
which case the userspace program can not only resolve missing page
faults, and at the same time tracking page data changes along the way.
Secondly, we introduced the new UFFDIO_WRITEPROTECT API to do page
level write protection tracking. Note that we will need to register
the memory region with UFFDIO_REGISTER_MODE_WP before that.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
[peterx: remove useless block, write commit message]
Signed-off-by: Peter Xu <peterx@redhat.com>
---
fs/userfaultfd.c | 78 +++++++++++++++++++++++++-------
include/uapi/linux/userfaultfd.h | 11 +++++
2 files changed, 73 insertions(+), 16 deletions(-)
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index bc9f6230a3f0..6ff8773d6797 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -305,8 +305,11 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
if (!pmd_present(_pmd))
goto out;
- if (pmd_trans_huge(_pmd))
+ if (pmd_trans_huge(_pmd)) {
+ if (!pmd_write(_pmd) && (reason & VM_UFFD_WP))
+ ret = true;
goto out;
+ }
/*
* the pmd is stable (as in !pmd_trans_unstable) so we can re-read it
@@ -319,6 +322,8 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
*/
if (pte_none(*pte))
ret = true;
+ if (!pte_write(*pte) && (reason & VM_UFFD_WP))
+ ret = true;
pte_unmap(pte);
out:
@@ -1252,10 +1257,13 @@ static __always_inline int validate_range(struct mm_struct *mm,
return 0;
}
-static inline bool vma_can_userfault(struct vm_area_struct *vma)
+static inline bool vma_can_userfault(struct vm_area_struct *vma,
+ unsigned long vm_flags)
{
- return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) ||
- vma_is_shmem(vma);
+ /* FIXME: add WP support to hugetlbfs and shmem */
+ return vma_is_anonymous(vma) ||
+ ((is_vm_hugetlb_page(vma) || vma_is_shmem(vma)) &&
+ !(vm_flags & VM_UFFD_WP));
}
static int userfaultfd_register(struct userfaultfd_ctx *ctx,
@@ -1287,15 +1295,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
vm_flags = 0;
if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MISSING)
vm_flags |= VM_UFFD_MISSING;
- if (uffdio_register.mode & UFFDIO_REGISTER_MODE_WP) {
+ if (uffdio_register.mode & UFFDIO_REGISTER_MODE_WP)
vm_flags |= VM_UFFD_WP;
- /*
- * FIXME: remove the below error constraint by
- * implementing the wprotect tracking mode.
- */
- ret = -EINVAL;
- goto out;
- }
ret = validate_range(mm, uffdio_register.range.start,
uffdio_register.range.len);
@@ -1343,7 +1344,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
/* check not compatible vmas */
ret = -EINVAL;
- if (!vma_can_userfault(cur))
+ if (!vma_can_userfault(cur, vm_flags))
goto out_unlock;
/*
@@ -1371,6 +1372,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
if (end & (vma_hpagesize - 1))
goto out_unlock;
}
+ if ((vm_flags & VM_UFFD_WP) && !(cur->vm_flags & VM_WRITE))
+ goto out_unlock;
/*
* Check that this vma isn't already owned by a
@@ -1400,7 +1403,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
do {
cond_resched();
- BUG_ON(!vma_can_userfault(vma));
+ BUG_ON(!vma_can_userfault(vma, vm_flags));
BUG_ON(vma->vm_userfaultfd_ctx.ctx &&
vma->vm_userfaultfd_ctx.ctx != ctx);
WARN_ON(!(vma->vm_flags & VM_MAYWRITE));
@@ -1535,7 +1538,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
* provides for more strict behavior to notice
* unregistration errors.
*/
- if (!vma_can_userfault(cur))
+ if (!vma_can_userfault(cur, cur->vm_flags))
goto out_unlock;
found = true;
@@ -1549,7 +1552,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
do {
cond_resched();
- BUG_ON(!vma_can_userfault(vma));
+ BUG_ON(!vma_can_userfault(vma, vma->vm_flags));
WARN_ON(!(vma->vm_flags & VM_MAYWRITE));
/*
@@ -1760,6 +1763,46 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
return ret;
}
+static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx,
+ unsigned long arg)
+{
+ int ret;
+ struct uffdio_writeprotect uffdio_wp;
+ struct uffdio_writeprotect __user *user_uffdio_wp;
+ struct userfaultfd_wake_range range;
+
+ user_uffdio_wp = (struct uffdio_writeprotect __user *) arg;
+
+ if (copy_from_user(&uffdio_wp, user_uffdio_wp,
+ sizeof(struct uffdio_writeprotect)))
+ return -EFAULT;
+
+ ret = validate_range(ctx->mm, uffdio_wp.range.start,
+ uffdio_wp.range.len);
+ if (ret)
+ return ret;
+
+ if (uffdio_wp.mode & ~(UFFDIO_WRITEPROTECT_MODE_DONTWAKE |
+ UFFDIO_WRITEPROTECT_MODE_WP))
+ return -EINVAL;
+ if ((uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_WP) &&
+ (uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_DONTWAKE))
+ return -EINVAL;
+
+ ret = mwriteprotect_range(ctx->mm, uffdio_wp.range.start,
+ uffdio_wp.range.len, uffdio_wp.mode &
+ UFFDIO_WRITEPROTECT_MODE_WP);
+ if (ret)
+ return ret;
+
+ if (!(uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_DONTWAKE)) {
+ range.start = uffdio_wp.range.start;
+ range.len = uffdio_wp.range.len;
+ wake_userfault(ctx, &range);
+ }
+ return ret;
+}
+
static inline unsigned int uffd_ctx_features(__u64 user_features)
{
/*
@@ -1837,6 +1880,9 @@ static long userfaultfd_ioctl(struct file *file, unsigned cmd,
case UFFDIO_ZEROPAGE:
ret = userfaultfd_zeropage(ctx, arg);
break;
+ case UFFDIO_WRITEPROTECT:
+ ret = userfaultfd_writeprotect(ctx, arg);
+ break;
}
return ret;
}
diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
index 48f1a7c2f1f0..11517f796275 100644
--- a/include/uapi/linux/userfaultfd.h
+++ b/include/uapi/linux/userfaultfd.h
@@ -52,6 +52,7 @@
#define _UFFDIO_WAKE (0x02)
#define _UFFDIO_COPY (0x03)
#define _UFFDIO_ZEROPAGE (0x04)
+#define _UFFDIO_WRITEPROTECT (0x06)
#define _UFFDIO_API (0x3F)
/* userfaultfd ioctl ids */
@@ -68,6 +69,8 @@
struct uffdio_copy)
#define UFFDIO_ZEROPAGE _IOWR(UFFDIO, _UFFDIO_ZEROPAGE, \
struct uffdio_zeropage)
+#define UFFDIO_WRITEPROTECT _IOWR(UFFDIO, _UFFDIO_WRITEPROTECT, \
+ struct uffdio_writeprotect)
/* read() structure */
struct uffd_msg {
@@ -231,4 +234,12 @@ struct uffdio_zeropage {
__s64 zeropage;
};
+struct uffdio_writeprotect {
+ struct uffdio_range range;
+ /* !WP means undo writeprotect. DONTWAKE is valid only with !WP */
+#define UFFDIO_WRITEPROTECT_MODE_WP ((__u64)1<<0)
+#define UFFDIO_WRITEPROTECT_MODE_DONTWAKE ((__u64)1<<1)
+ __u64 mode;
+};
+
#endif /* _LINUX_USERFAULTFD_H */
--
2.17.1
next prev parent reply other threads:[~2019-01-21 7:58 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 ` Peter Xu [this message]
2019-01-21 10:42 ` [PATCH RFC 07/24] userfaultfd: wp: add the writeprotect API to userfaultfd ioctl 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 ` [PATCH RFC 12/24] userfaultfd: wp: add UFFDIO_COPY_MODE_WP Peter Xu
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=20190121075722.7945-8-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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox