All of lore.kernel.org
 help / color / mirror / Atom feed
From: Andrew Morton <akpm@linux-foundation.org>
To: mm-commits@vger.kernel.org, willy@infradead.org,
	rppt@linux.vnet.ibm.com, nadav.amit@gmail.com,
	mike.kravetz@oracle.com, kirill@shutemov.name,
	jglisse@redhat.com, hughd@google.com, david@redhat.com,
	axelrasmussen@google.com, apopple@nvidia.com,
	aarcange@redhat.com, peterx@redhat.com,
	akpm@linux-foundation.org
Subject: + mm-hugetlb-handle-uffd-wp-during-fork.patch added to -mm tree
Date: Tue, 05 Apr 2022 13:17:11 -0700	[thread overview]
Message-ID: <20220405201712.2ECD7C385A1@smtp.kernel.org> (raw)


The patch titled
     Subject: mm/hugetlb: handle uffd-wp during fork()
has been added to the -mm tree.  Its filename is
     mm-hugetlb-handle-uffd-wp-during-fork.patch

This patch should soon appear at
    https://ozlabs.org/~akpm/mmots/broken-out/mm-hugetlb-handle-uffd-wp-during-fork.patch
and later at
    https://ozlabs.org/~akpm/mmotm/broken-out/mm-hugetlb-handle-uffd-wp-during-fork.patch

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next and is updated
there every 3-4 working days

------------------------------------------------------
From: Peter Xu <peterx@redhat.com>
Subject: mm/hugetlb: handle uffd-wp during fork()

Firstly, we'll need to pass in dst_vma into copy_hugetlb_page_range()
because for uffd-wp it's the dst vma that matters on deciding how we
should treat uffd-wp protected ptes.

We should recognize pte markers during fork and do the pte copy if needed.

Link: https://lkml.kernel.org/r/20220405014918.14932-1-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 include/linux/hugetlb.h |    7 ++++--
 mm/hugetlb.c            |   42 +++++++++++++++++++++++++-------------
 mm/memory.c             |    2 -
 3 files changed, 34 insertions(+), 17 deletions(-)

--- a/include/linux/hugetlb.h~mm-hugetlb-handle-uffd-wp-during-fork
+++ a/include/linux/hugetlb.h
@@ -137,7 +137,8 @@ int move_hugetlb_page_tables(struct vm_a
 			     struct vm_area_struct *new_vma,
 			     unsigned long old_addr, unsigned long new_addr,
 			     unsigned long len);
-int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *);
+int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *,
+			    struct vm_area_struct *, struct vm_area_struct *);
 long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *,
 			 struct page **, struct vm_area_struct **,
 			 unsigned long *, unsigned long *, long, unsigned int,
@@ -269,7 +270,9 @@ static inline struct page *follow_huge_a
 }
 
 static inline int copy_hugetlb_page_range(struct mm_struct *dst,
-			struct mm_struct *src, struct vm_area_struct *vma)
+					  struct mm_struct *src,
+					  struct vm_area_struct *dst_vma,
+					  struct vm_area_struct *src_vma)
 {
 	BUG();
 	return 0;
--- a/mm/hugetlb.c~mm-hugetlb-handle-uffd-wp-during-fork
+++ a/mm/hugetlb.c
@@ -4706,23 +4706,24 @@ hugetlb_install_page(struct vm_area_stru
 }
 
 int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
-			    struct vm_area_struct *vma)
+			    struct vm_area_struct *dst_vma,
+			    struct vm_area_struct *src_vma)
 {
 	pte_t *src_pte, *dst_pte, entry, dst_entry;
 	struct page *ptepage;
 	unsigned long addr;
-	bool cow = is_cow_mapping(vma->vm_flags);
-	struct hstate *h = hstate_vma(vma);
+	bool cow = is_cow_mapping(src_vma->vm_flags);
+	struct hstate *h = hstate_vma(src_vma);
 	unsigned long sz = huge_page_size(h);
 	unsigned long npages = pages_per_huge_page(h);
-	struct address_space *mapping = vma->vm_file->f_mapping;
+	struct address_space *mapping = src_vma->vm_file->f_mapping;
 	struct mmu_notifier_range range;
 	int ret = 0;
 
 	if (cow) {
-		mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, src,
-					vma->vm_start,
-					vma->vm_end);
+		mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, src_vma, src,
+					src_vma->vm_start,
+					src_vma->vm_end);
 		mmu_notifier_invalidate_range_start(&range);
 		mmap_assert_write_locked(src);
 		raw_write_seqcount_begin(&src->write_protect_seq);
@@ -4736,12 +4737,12 @@ int copy_hugetlb_page_range(struct mm_st
 		i_mmap_lock_read(mapping);
 	}
 
-	for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) {
+	for (addr = src_vma->vm_start; addr < src_vma->vm_end; addr += sz) {
 		spinlock_t *src_ptl, *dst_ptl;
 		src_pte = huge_pte_offset(src, addr, sz);
 		if (!src_pte)
 			continue;
-		dst_pte = huge_pte_alloc(dst, vma, addr, sz);
+		dst_pte = huge_pte_alloc(dst, dst_vma, addr, sz);
 		if (!dst_pte) {
 			ret = -ENOMEM;
 			break;
@@ -4776,6 +4777,7 @@ again:
 		} else if (unlikely(is_hugetlb_entry_migration(entry) ||
 				    is_hugetlb_entry_hwpoisoned(entry))) {
 			swp_entry_t swp_entry = pte_to_swp_entry(entry);
+			bool uffd_wp = huge_pte_uffd_wp(entry);
 
 			if (!is_readable_migration_entry(swp_entry) && cow) {
 				/*
@@ -4785,10 +4787,21 @@ again:
 				swp_entry = make_readable_migration_entry(
 							swp_offset(swp_entry));
 				entry = swp_entry_to_pte(swp_entry);
+				if (userfaultfd_wp(src_vma) && uffd_wp)
+					entry = huge_pte_mkuffd_wp(entry);
 				set_huge_swap_pte_at(src, addr, src_pte,
 						     entry, sz);
 			}
+			if (!userfaultfd_wp(dst_vma) && uffd_wp)
+				entry = huge_pte_clear_uffd_wp(entry);
 			set_huge_swap_pte_at(dst, addr, dst_pte, entry, sz);
+		} else if (unlikely(is_pte_marker(entry))) {
+			/*
+			 * We copy the pte marker only if the dst vma has
+			 * uffd-wp enabled.
+			 */
+			if (userfaultfd_wp(dst_vma))
+				set_huge_pte_at(dst, addr, dst_pte, entry);
 		} else {
 			entry = huge_ptep_get(src_pte);
 			ptepage = pte_page(entry);
@@ -4806,20 +4819,21 @@ again:
 			 */
 			if (!PageAnon(ptepage)) {
 				page_dup_file_rmap(ptepage, true);
-			} else if (page_try_dup_anon_rmap(ptepage, true, vma)) {
+			} else if (page_try_dup_anon_rmap(ptepage, true,
+							  src_vma)) {
 				pte_t src_pte_old = entry;
 				struct page *new;
 
 				spin_unlock(src_ptl);
 				spin_unlock(dst_ptl);
 				/* Do not use reserve as it's private owned */
-				new = alloc_huge_page(vma, addr, 1);
+				new = alloc_huge_page(dst_vma, addr, 1);
 				if (IS_ERR(new)) {
 					put_page(ptepage);
 					ret = PTR_ERR(new);
 					break;
 				}
-				copy_user_huge_page(new, ptepage, addr, vma,
+				copy_user_huge_page(new, ptepage, addr, dst_vma,
 						    npages);
 				put_page(ptepage);
 
@@ -4829,13 +4843,13 @@ again:
 				spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
 				entry = huge_ptep_get(src_pte);
 				if (!pte_same(src_pte_old, entry)) {
-					restore_reserve_on_error(h, vma, addr,
+					restore_reserve_on_error(h, dst_vma, addr,
 								new);
 					put_page(new);
 					/* dst_entry won't change as in child */
 					goto again;
 				}
-				hugetlb_install_page(vma, dst_pte, addr, new);
+				hugetlb_install_page(dst_vma, dst_pte, addr, new);
 				spin_unlock(src_ptl);
 				spin_unlock(dst_ptl);
 				continue;
--- a/mm/memory.c~mm-hugetlb-handle-uffd-wp-during-fork
+++ a/mm/memory.c
@@ -1278,7 +1278,7 @@ copy_page_range(struct vm_area_struct *d
 		return 0;
 
 	if (is_vm_hugetlb_page(src_vma))
-		return copy_hugetlb_page_range(dst_mm, src_mm, src_vma);
+		return copy_hugetlb_page_range(dst_mm, src_mm, dst_vma, src_vma);
 
 	if (unlikely(src_vma->vm_flags & VM_PFNMAP)) {
 		/*
_

Patches currently in -mm which might be from peterx@redhat.com are

mm-introduce-pte_marker-swap-entry.patch
mm-teach-core-mm-about-pte-markers.patch
mm-check-against-orig_pte-for-finish_fault.patch
mm-uffd-pte_marker_uffd_wp.patch
mm-shmem-take-care-of-uffdio_copy_mode_wp.patch
mm-shmem-handle-uffd-wp-special-pte-in-page-fault-handler.patch
mm-shmem-persist-uffd-wp-bit-across-zapping-for-file-backed.patch
mm-shmem-allow-uffd-wr-protect-none-pte-for-file-backed-mem.patch
mm-shmem-allows-file-back-mem-to-be-uffd-wr-protected-on-thps.patch
mm-shmem-handle-uffd-wp-during-fork.patch
mm-hugetlb-introduce-huge-pte-version-of-uffd-wp-helpers.patch
mm-hugetlb-hook-page-faults-for-uffd-write-protection.patch
mm-hugetlb-take-care-of-uffdio_copy_mode_wp.patch
mm-hugetlb-handle-uffdio_writeprotect.patch
mm-hugetlb-handle-pte-markers-in-page-faults.patch
mm-hugetlb-allow-uffd-wr-protect-none-ptes.patch
mm-hugetlb-only-drop-uffd-wp-special-pte-if-required.patch
mm-hugetlb-handle-uffd-wp-during-fork.patch
mm-khugepaged-dont-recycle-vma-pgtable-if-uffd-wp-registered.patch
mm-pagemap-recognize-uffd-wp-bit-for-shmem-hugetlbfs.patch
mm-uffd-enable-write-protection-for-shmem-hugetlbfs.patch
mm-enable-pte-markers-by-default.patch
selftests-uffd-enable-uffd-wp-for-shmem-hugetlbfs.patch


                 reply	other threads:[~2022-04-06  1:56 UTC|newest]

Thread overview: [no followups] expand[flat|nested]  mbox.gz  Atom feed

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=20220405201712.2ECD7C385A1@smtp.kernel.org \
    --to=akpm@linux-foundation.org \
    --cc=aarcange@redhat.com \
    --cc=apopple@nvidia.com \
    --cc=axelrasmussen@google.com \
    --cc=david@redhat.com \
    --cc=hughd@google.com \
    --cc=jglisse@redhat.com \
    --cc=kirill@shutemov.name \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mike.kravetz@oracle.com \
    --cc=mm-commits@vger.kernel.org \
    --cc=nadav.amit@gmail.com \
    --cc=peterx@redhat.com \
    --cc=rppt@linux.vnet.ibm.com \
    --cc=willy@infradead.org \
    /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.