The patch titled
Subject: mm: merge folio_is_secretmem() into folio_fast_pin_allowed()
has been added to the -mm mm-unstable branch. Its filename is
mm-merge-folio_is_secretmem-into-folio_fast_pin_allowed.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-merge-folio_is_secretmem-into-folio_fast_pin_allowed.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
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 via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: David Hildenbrand <david@xxxxxxxxxx>
Subject: mm: merge folio_is_secretmem() into folio_fast_pin_allowed()
Date: Mon, 25 Mar 2024 14:41:14 +0100
folio_is_secretmem() is currently only used during GUP-fast, and using it
in wrong context where concurrent truncation might happen, could be
problematic.
Nowadays, folio_fast_pin_allowed() performs similar checks during GUP-fast
and contains a lot of careful handling -- READ_ONCE( -- ), sanity checks
-- lockdep_assert_irqs_disabled() -- and helpful comments on how this
handling is safe and correct.
So let's merge folio_is_secretmem() into folio_fast_pin_allowed(), still
avoiding checking the actual mapping only if really required.
Link: https://lkml.kernel.org/r/20240325134114.257544-4-david@xxxxxxxxxx
Signed-off-by: David Hildenbrand <david@xxxxxxxxxx>
Cc: Lorenzo Stoakes <lstoakes@xxxxxxxxx>
Cc: "Mike Rapoport (IBM)" <rppt@xxxxxxxxxx>
Cc: Miklos Szeredi <mszeredi@xxxxxxxxxx>
Cc: xingwei lee <xrivendell7@xxxxxxxxx>
Cc: yue sun <samsun1006219@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/secretmem.h | 21 ++-------------------
mm/gup.c | 33 +++++++++++++++++++++------------
2 files changed, 23 insertions(+), 31 deletions(-)
--- a/include/linux/secretmem.h~mm-merge-folio_is_secretmem-into-folio_fast_pin_allowed
+++ a/include/linux/secretmem.h
@@ -6,25 +6,8 @@
extern const struct address_space_operations secretmem_aops;
-static inline bool folio_is_secretmem(struct folio *folio)
+static inline bool secretmem_mapping(struct address_space *mapping)
{
- struct address_space *mapping;
-
- /*
- * Using folio_mapping() is quite slow because of the actual call
- * instruction.
- * We know that secretmem pages are not compound and LRU so we can
- * save a couple of cycles here.
- */
- if (folio_test_large(folio) || folio_test_lru(folio))
- return false;
-
- mapping = (struct address_space *)
- ((unsigned long)folio->mapping & ~PAGE_MAPPING_FLAGS);
-
- if (!mapping || mapping != folio->mapping)
- return false;
-
return mapping->a_ops == &secretmem_aops;
}
@@ -38,7 +21,7 @@ static inline bool vma_is_secretmem(stru
return false;
}
-static inline bool folio_is_secretmem(struct folio *folio)
+static inline bool secretmem_mapping(struct address_space *mapping)
{
return false;
}
--- a/mm/gup.c~mm-merge-folio_is_secretmem-into-folio_fast_pin_allowed
+++ a/mm/gup.c
@@ -2472,6 +2472,8 @@ EXPORT_SYMBOL(get_user_pages_unlocked);
* This call assumes the caller has pinned the folio, that the lowest page table
* level still points to this folio, and that interrupts have been disabled.
*
+ * GUP-fast must reject all secretmem folios.
+ *
* Writing to pinned file-backed dirty tracked folios is inherently problematic
* (see comment describing the writable_file_mapping_allowed() function). We
* therefore try to avoid the most egregious case of a long-term mapping doing
@@ -2484,22 +2486,32 @@ EXPORT_SYMBOL(get_user_pages_unlocked);
static bool folio_fast_pin_allowed(struct folio *folio, unsigned int flags)
{
struct address_space *mapping;
+ bool check_secretmem = false;
+ bool reject_file_backed = false;
unsigned long mapping_flags;
/*
* If we aren't pinning then no problematic write can occur. A long term
* pin is the most egregious case so this is the one we disallow.
*/
- if ((flags & (FOLL_PIN | FOLL_LONGTERM | FOLL_WRITE)) !=
+ if ((flags & (FOLL_PIN | FOLL_LONGTERM | FOLL_WRITE)) ==
(FOLL_PIN | FOLL_LONGTERM | FOLL_WRITE))
- return true;
+ reject_file_backed = true;
+
+ /* We hold a folio reference, so we can safely access folio fields. */
+
+ /* secretmem folios are only order-0 folios and never LRU folios. */
+ if (IS_ENABLED(CONFIG_SECRETMEM) && !folio_test_large(folio) &&
+ !folio_test_lru(folio))
+ check_secretmem = true;
- /* The folio is pinned, so we can safely access folio fields. */
+ if (!reject_file_backed && !check_secretmem)
+ return true;
if (WARN_ON_ONCE(folio_test_slab(folio)))
return false;
- /* hugetlb mappings do not require dirty-tracking. */
+ /* hugetlb neither requires dirty-tracking nor can be secretmem. */
if (folio_test_hugetlb(folio))
return true;
@@ -2535,10 +2547,12 @@ static bool folio_fast_pin_allowed(struc
/*
* At this point, we know the mapping is non-null and points to an
- * address_space object. The only remaining whitelisted file system is
- * shmem.
+ * address_space object.
*/
- return shmem_mapping(mapping);
+ if (check_secretmem && secretmem_mapping(mapping))
+ return false;
+ /* The only remaining allowed file system is shmem. */
+ return !reject_file_backed || shmem_mapping(mapping);
}
static void __maybe_unused undo_dev_pagemap(int *nr, int nr_start,
@@ -2624,11 +2638,6 @@ static int gup_pte_range(pmd_t pmd, pmd_
if (!folio)
goto pte_unmap;
- if (unlikely(folio_is_secretmem(folio))) {
- gup_put_folio(folio, 1, flags);
- goto pte_unmap;
- }
-
if (unlikely(pmd_val(pmd) != pmd_val(*pmdp)) ||
unlikely(pte_val(pte) != pte_val(ptep_get(ptep)))) {
gup_put_folio(folio, 1, flags);
_
Patches currently in -mm which might be from david@xxxxxxxxxx are
mm-secretmem-fix-gup-fast-succeeding-on-secretmem-folios.patch
mm-madvise-make-madv_populate_readwrite-handle-vm_fault_retry-properly.patch
mm-madvise-dont-perform-madvise-vma-walk-for-madv_populate_readwrite.patch
mm-userfaultfd-dont-place-zeropages-when-zeropages-are-disallowed.patch
s390-mm-re-enable-the-shared-zeropage-for-pv-and-skeys-kvm-guests.patch
mm-convert-folio_estimated_sharers-to-folio_likely_mapped_shared.patch
selftests-memfd_secret-add-vmsplice-test.patch
mm-merge-folio_is_secretmem-into-folio_fast_pin_allowed.patch
