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: Brian Geffon <bgeffon@google.com>,
	Pavel Emelyanov <xemul@virtuozzo.com>,
	Mike Kravetz <mike.kravetz@oracle.com>,
	David Hildenbrand <david@redhat.com>,
	peterx@redhat.com, Martin Cracauer <cracauer@cons.org>,
	Andrea Arcangeli <aarcange@redhat.com>,
	Mel Gorman <mgorman@suse.de>,
	Bobby Powers <bobbypowers@gmail.com>,
	Mike Rapoport <rppt@linux.vnet.ibm.com>,
	"Kirill A . Shutemov" <kirill@shutemov.name>,
	Maya Gokhale <gokhale2@llnl.gov>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Marty McFadden <mcfadden8@llnl.gov>,
	Denis Plotnikov <dplotnikov@virtuozzo.com>,
	Hugh Dickins <hughd@google.com>,
	"Dr . David Alan Gilbert" <dgilbert@redhat.com>,
	Jerome Glisse <jglisse@redhat.com>
Subject: [PATCH v6 10/19] userfaultfd: wp: support swap and page migration
Date: Thu, 20 Feb 2020 11:31:03 -0500	[thread overview]
Message-ID: <20200220163112.11409-11-peterx@redhat.com> (raw)
In-Reply-To: <20200220163112.11409-1-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.

In change_pte_range() we do nothing for uffd if the PTE is a swap
entry.  That can lead to data mismatch if the page that we are going
to write protect is swapped out when sending the UFFDIO_WRITEPROTECT.
This patch also applies/removes the uffd-wp bit even for the swap
entries.

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            |  6 ++++++
 mm/mprotect.c           | 28 +++++++++++++++++-----------
 mm/rmap.c               |  6 ++++++
 6 files changed, 42 insertions(+), 11 deletions(-)

diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index 877fd239b6ff..9a6f06de183b 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 134bef68a1de..ef18ad16b7ed 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2252,6 +2252,7 @@ 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))
@@ -2284,6 +2285,8 @@ 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 557837ec29c3..103c1cf9b794 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -733,6 +733,8 @@ 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)) {
@@ -762,6 +764,8 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 			    is_cow_mapping(vm_flags)) {
 				make_device_private_entry_read(&entry);
 				pte = swp_entry_to_pte(entry);
+				if (pte_swp_uffd_wp(*src_pte))
+					pte = pte_swp_mkuffd_wp(pte);
 				set_pte_at(src_mm, addr, src_pte, pte);
 			}
 		}
@@ -3079,6 +3083,10 @@ 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 b1092876e537..73cbdbf69fc5 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -243,11 +243,15 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma,
 		entry = pte_to_swp_entry(*pvmw.pte);
 		if (is_write_migration_entry(entry))
 			pte = maybe_mkwrite(pte, vma);
+		else if (pte_swp_uffd_wp(*pvmw.pte))
+			pte = pte_mkuffd_wp(pte);
 
 		if (unlikely(is_zone_device_page(new))) {
 			if (is_device_private_page(new)) {
 				entry = make_device_private_entry(new, pte_write(pte));
 				pte = swp_entry_to_pte(entry);
+				if (pte_swp_uffd_wp(*pvmw.pte))
+					pte = pte_mkuffd_wp(pte);
 			}
 		}
 
@@ -2318,6 +2322,8 @@ 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 22a1c78e3f51..104ac88163d4 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -139,11 +139,11 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 			}
 			ptep_modify_prot_commit(vma, addr, pte, oldpte, ptent);
 			pages++;
-		} else if (IS_ENABLED(CONFIG_MIGRATION)) {
+		} else if (is_swap_pte(oldpte)) {
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
+			pte_t newpte;
 
 			if (is_write_migration_entry(entry)) {
-				pte_t newpte;
 				/*
 				 * A protection check is difficult so
 				 * just be safe and disable write
@@ -152,22 +152,28 @@ 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);
-				set_pte_at(vma->vm_mm, addr, pte, newpte);
-
-				pages++;
-			}
-
-			if (is_write_device_private_entry(entry)) {
-				pte_t newpte;
-
+				if (pte_swp_uffd_wp(oldpte))
+					newpte = pte_swp_mkuffd_wp(newpte);
+			} else if (is_write_device_private_entry(entry)) {
 				/*
 				 * We do not preserve soft-dirtiness. See
 				 * copy_one_pte() for explanation.
 				 */
 				make_device_private_entry_read(&entry);
 				newpte = swp_entry_to_pte(entry);
-				set_pte_at(vma->vm_mm, addr, pte, newpte);
+				if (pte_swp_uffd_wp(oldpte))
+					newpte = pte_swp_mkuffd_wp(newpte);
+			} else {
+				newpte = oldpte;
+			}
 
+			if (uffd_wp)
+				newpte = pte_swp_mkuffd_wp(newpte);
+			else if (uffd_wp_resolve)
+				newpte = pte_swp_clear_uffd_wp(newpte);
+
+			if (!pte_same(oldpte, newpte)) {
+				set_pte_at(vma->vm_mm, addr, pte, newpte);
 				pages++;
 			}
 		}
diff --git a/mm/rmap.c b/mm/rmap.c
index b3e381919835..ce935d0ddf75 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1497,6 +1497,8 @@ 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
@@ -1596,6 +1598,8 @@ 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
@@ -1662,6 +1666,8 @@ 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,
-- 
2.24.1


  parent reply	other threads:[~2020-02-20 16:31 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-02-20 16:30 [PATCH v6 00/19] userfaultfd: write protection support Peter Xu
2020-02-20 16:30 ` [PATCH v6 01/19] userfaultfd: wp: add helper for writeprotect check Peter Xu
2020-02-20 16:30 ` [PATCH v6 02/19] userfaultfd: wp: hook userfault handler to write protection fault Peter Xu
2020-02-20 16:30 ` [PATCH v6 03/19] userfaultfd: wp: add WP pagetable tracking to x86 Peter Xu
2020-02-20 16:30 ` [PATCH v6 04/19] userfaultfd: wp: userfaultfd_pte/huge_pmd_wp() helpers Peter Xu
2020-02-20 16:30 ` [PATCH v6 05/19] userfaultfd: wp: add UFFDIO_COPY_MODE_WP Peter Xu
2020-02-20 16:30 ` [PATCH v6 06/19] mm: merge parameters for change_protection() Peter Xu
2020-02-20 16:31 ` [PATCH v6 07/19] userfaultfd: wp: apply _PAGE_UFFD_WP bit Peter Xu
2020-02-20 16:31 ` [PATCH v6 08/19] userfaultfd: wp: drop _PAGE_UFFD_WP properly when fork Peter Xu
2020-02-20 16:31 ` [PATCH v6 09/19] userfaultfd: wp: add pmd_swp_*uffd_wp() helpers Peter Xu
2020-02-20 16:31 ` Peter Xu [this message]
2020-02-20 16:31 ` [PATCH v6 11/19] khugepaged: skip collapse if uffd-wp detected Peter Xu
2020-02-20 16:31 ` [PATCH v6 12/19] userfaultfd: wp: support write protection for userfault vma range Peter Xu
2020-02-20 16:31 ` [PATCH v6 13/19] userfaultfd: wp: add the writeprotect API to userfaultfd ioctl Peter Xu
2020-02-20 16:31 ` [PATCH v6 14/19] userfaultfd: wp: enabled write protection in userfaultfd API Peter Xu
2020-02-20 16:31 ` [PATCH v6 15/19] userfaultfd: wp: don't wake up when doing write protect Peter Xu
2020-02-20 16:31 ` [PATCH v6 16/19] userfaultfd: wp: UFFDIO_REGISTER_MODE_WP documentation update Peter Xu
2020-02-20 16:31 ` [PATCH v6 17/19] userfaultfd: wp: declare _UFFDIO_WRITEPROTECT conditionally Peter Xu
2020-02-20 16:31 ` [PATCH v6 18/19] userfaultfd: selftests: refactor statistics Peter Xu
2020-02-20 16:31 ` [PATCH v6 19/19] userfaultfd: selftests: add write-protect test 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=20200220163112.11409-11-peterx@redhat.com \
    --to=peterx@redhat.com \
    --cc=aarcange@redhat.com \
    --cc=bgeffon@google.com \
    --cc=bobbypowers@gmail.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=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.