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 19/25] userfaultfd: wp: add the writeprotect API to userfaultfd ioctl
Date: Thu, 20 Jun 2019 10:20:02 +0800 [thread overview]
Message-ID: <20190620022008.19172-20-peterx@redhat.com> (raw)
In-Reply-To: <20190620022008.19172-1-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, check against
VM_MAYWRITE rather than VM_WRITE when register]
Reviewed-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
---
fs/userfaultfd.c | 82 +++++++++++++++++++++++++-------
include/uapi/linux/userfaultfd.h | 23 +++++++++
2 files changed, 89 insertions(+), 16 deletions(-)
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index c594945ad5bf..3cf19aeaa0e0 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -306,8 +306,11 @@ 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
@@ -320,6 +323,8 @@ 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:
@@ -1258,10 +1263,13 @@ 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,
@@ -1293,15 +1301,8 @@ 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);
@@ -1351,7 +1352,7 @@ 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;
/*
@@ -1379,6 +1380,8 @@ 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_MAYWRITE))
+ goto out_unlock;
/*
* Check that this vma isn't already owned by a
@@ -1408,7 +1411,7 @@ 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));
@@ -1545,7 +1548,7 @@ 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;
@@ -1559,7 +1562,7 @@ 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));
/*
* Nothing to do: this vma is already registered into this
@@ -1772,6 +1775,50 @@ 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;
+
+ if (READ_ONCE(ctx->mmap_changing))
+ return -EAGAIN;
+
+ 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,
+ &ctx->mmap_changing);
+ 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)
{
/*
@@ -1849,6 +1896,9 @@ 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 340f23bc251d..95c4a160e5f8 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 {
@@ -232,4 +235,24 @@ struct uffdio_zeropage {
__s64 zeropage;
};
+struct uffdio_writeprotect {
+ struct uffdio_range range;
+/*
+ * UFFDIO_WRITEPROTECT_MODE_WP: set the flag to write protect a range,
+ * unset the flag to undo protection of a range which was previously
+ * write protected.
+ *
+ * UFFDIO_WRITEPROTECT_MODE_DONTWAKE: set the flag to avoid waking up
+ * any wait thread after the operation succeeds.
+ *
+ * NOTE: Write protecting a region (WP=1) is unrelated to page faults,
+ * therefore DONTWAKE flag is meaningless with WP=1. Removing write
+ * protection (WP=0) in response to a page fault wakes the faulting
+ * task unless DONTWAKE is set.
+ */
+#define UFFDIO_WRITEPROTECT_MODE_WP ((__u64)1<<0)
+#define UFFDIO_WRITEPROTECT_MODE_DONTWAKE ((__u64)1<<1)
+ __u64 mode;
+};
+
#endif /* _LINUX_USERFAULTFD_H */
--
2.21.0
next prev parent reply other threads:[~2019-06-20 2:24 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 ` [PATCH v5 10/25] userfaultfd: wp: add UFFDIO_COPY_MODE_WP Peter Xu
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 ` Peter Xu [this message]
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=20190620022008.19172-20-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.