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 19/24] userfaultfd: wp: support swap and page migration
Date: Mon, 21 Jan 2019 15:57:17 +0800 [thread overview]
Message-ID: <20190121075722.7945-20-peterx@redhat.com> (raw)
In-Reply-To: <20190121075722.7945-1-peterx@redhat.com>
For either swap and page migration, we all use the bit 2 of the entry to
identify whether this entry is uffd write-protected. It plays a similar
role as the existing soft dirty bit in swap entries but only for keeping
the uffd-wp tracking for a specific PTE/PMD.
Something special here is that when we want to recover the uffd-wp bit
from a swap/migration entry to the PTE bit we'll also need to take care
of the _PAGE_RW bit and make sure it's cleared, otherwise even with the
_PAGE_UFFD_WP bit we can't trap it at all.
Note that this patch removed two lines from "userfaultfd: wp: hook
userfault handler to write protection fault" where we try to remove the
VM_FAULT_WRITE from vmf->flags when uffd-wp is set for the VMA. This
patch will still keep the write flag there.
Signed-off-by: Peter Xu <peterx@redhat.com>
---
include/linux/swapops.h | 2 ++
mm/huge_memory.c | 3 +++
mm/memory.c | 8 ++++++--
mm/migrate.c | 7 +++++++
mm/mprotect.c | 2 ++
mm/rmap.c | 6 ++++++
6 files changed, 26 insertions(+), 2 deletions(-)
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index 4d961668e5fc..0c2923b1cdb7 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -68,6 +68,8 @@ static inline swp_entry_t pte_to_swp_entry(pte_t pte)
if (pte_swp_soft_dirty(pte))
pte = pte_swp_clear_soft_dirty(pte);
+ if (pte_swp_uffd_wp(pte))
+ pte = pte_swp_clear_uffd_wp(pte);
arch_entry = __pte_to_swp_entry(pte);
return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry));
}
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 2a3ec62e83b6..682f1427da1a 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2171,6 +2171,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
write = is_write_migration_entry(entry);
young = false;
soft_dirty = pmd_swp_soft_dirty(old_pmd);
+ uffd_wp = pmd_swp_uffd_wp(old_pmd);
} else {
page = pmd_page(old_pmd);
if (pmd_dirty(old_pmd))
@@ -2203,6 +2204,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
entry = swp_entry_to_pte(swp_entry);
if (soft_dirty)
entry = pte_swp_mksoft_dirty(entry);
+ if (uffd_wp)
+ entry = pte_swp_mkuffd_wp(entry);
} else {
entry = mk_pte(page + i, READ_ONCE(vma->vm_page_prot));
entry = maybe_mkwrite(entry, vma);
diff --git a/mm/memory.c b/mm/memory.c
index f5497752d2a3..ac7d659e40fe 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -736,6 +736,8 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pte = swp_entry_to_pte(entry);
if (pte_swp_soft_dirty(*src_pte))
pte = pte_swp_mksoft_dirty(pte);
+ if (pte_swp_uffd_wp(*src_pte))
+ pte = pte_swp_mkuffd_wp(pte);
set_pte_at(src_mm, addr, src_pte, pte);
}
} else if (is_device_private_entry(entry)) {
@@ -2814,8 +2816,6 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
dec_mm_counter_fast(vma->vm_mm, MM_SWAPENTS);
pte = mk_pte(page, vma->vm_page_prot);
- if (userfaultfd_wp(vma))
- vmf->flags &= ~FAULT_FLAG_WRITE;
if ((vmf->flags & FAULT_FLAG_WRITE) && reuse_swap_page(page, NULL)) {
pte = maybe_mkwrite(pte_mkdirty(pte), vma);
vmf->flags &= ~FAULT_FLAG_WRITE;
@@ -2825,6 +2825,10 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
flush_icache_page(vma, page);
if (pte_swp_soft_dirty(vmf->orig_pte))
pte = pte_mksoft_dirty(pte);
+ if (pte_swp_uffd_wp(vmf->orig_pte)) {
+ pte = pte_mkuffd_wp(pte);
+ pte = pte_wrprotect(pte);
+ }
set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte);
arch_do_swap_page(vma->vm_mm, vma, vmf->address, pte, vmf->orig_pte);
vmf->orig_pte = pte;
diff --git a/mm/migrate.c b/mm/migrate.c
index f7e4bfdc13b7..963d3dd65cf0 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -242,6 +242,11 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma,
if (is_write_migration_entry(entry))
pte = maybe_mkwrite(pte, vma);
+ if (pte_swp_uffd_wp(*pvmw.pte)) {
+ pte = pte_mkuffd_wp(pte);
+ pte = pte_wrprotect(pte);
+ }
+
if (unlikely(is_zone_device_page(new))) {
if (is_device_private_page(new)) {
entry = make_device_private_entry(new, pte_write(pte));
@@ -2265,6 +2270,8 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
swp_pte = swp_entry_to_pte(entry);
if (pte_soft_dirty(pte))
swp_pte = pte_swp_mksoft_dirty(swp_pte);
+ if (pte_uffd_wp(pte))
+ swp_pte = pte_swp_mkuffd_wp(swp_pte);
set_pte_at(mm, addr, ptep, swp_pte);
/*
diff --git a/mm/mprotect.c b/mm/mprotect.c
index c37c9aa7a54e..2ce62d806108 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -187,6 +187,8 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
newpte = swp_entry_to_pte(entry);
if (pte_swp_soft_dirty(oldpte))
newpte = pte_swp_mksoft_dirty(newpte);
+ if (pte_swp_uffd_wp(oldpte))
+ newpte = pte_swp_mkuffd_wp(newpte);
set_pte_at(mm, addr, pte, newpte);
pages++;
diff --git a/mm/rmap.c b/mm/rmap.c
index 85b7f9423352..e1cf191db4f3 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1463,6 +1463,8 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
swp_pte = swp_entry_to_pte(entry);
if (pte_soft_dirty(pteval))
swp_pte = pte_swp_mksoft_dirty(swp_pte);
+ if (pte_uffd_wp(pteval))
+ swp_pte = pte_swp_mkuffd_wp(swp_pte);
set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte);
/*
* No need to invalidate here it will synchronize on
@@ -1555,6 +1557,8 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
swp_pte = swp_entry_to_pte(entry);
if (pte_soft_dirty(pteval))
swp_pte = pte_swp_mksoft_dirty(swp_pte);
+ if (pte_uffd_wp(pteval))
+ swp_pte = pte_swp_mkuffd_wp(swp_pte);
set_pte_at(mm, address, pvmw.pte, swp_pte);
/*
* No need to invalidate here it will synchronize on
@@ -1621,6 +1625,8 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
swp_pte = swp_entry_to_pte(entry);
if (pte_soft_dirty(pteval))
swp_pte = pte_swp_mksoft_dirty(swp_pte);
+ if (pte_uffd_wp(pteval))
+ swp_pte = pte_swp_mkuffd_wp(swp_pte);
set_pte_at(mm, address, pvmw.pte, swp_pte);
/* Invalidate as we cleared the pte */
mmu_notifier_invalidate_range(mm, address,
--
2.17.1
next prev parent reply other threads:[~2019-01-21 8:00 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 ` [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 ` Peter Xu [this message]
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=20190121075722.7945-20-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;
as well as URLs for NNTP newsgroup(s).