linux-stable.git/include/linux/mm_types.h, branch v6.1.172

mm/hugetlb: fix excessive IPI broadcasts when unsharing PMD tables using mmu_gather

2026-03-25T10:03:14+00:00

commit 8ce720d5bd91e9dc16db3604aa4b1bf76770a9a1 upstream.

As reported, ever since commit 1013af4f585f ("mm/hugetlb: fix
huge_pmd_unshare() vs GUP-fast race") we can end up in some situations
where we perform so many IPI broadcasts when unsharing hugetlb PMD page
tables that it severely regresses some workloads.

In particular, when we fork()+exit(), or when we munmap() a large
area backed by many shared PMD tables, we perform one IPI broadcast per
unshared PMD table.

There are two optimizations to be had:

(1) When we process (unshare) multiple such PMD tables, such as during
    exit(), it is sufficient to send a single IPI broadcast (as long as
    we respect locking rules) instead of one per PMD table.

    Locking prevents that any of these PMD tables could get reused before
    we drop the lock.

(2) When we are not the last sharer (> 2 users including us), there is
    no need to send the IPI broadcast. The shared PMD tables cannot
    become exclusive (fully unshared) before an IPI will be broadcasted
    by the last sharer.

    Concurrent GUP-fast could walk into a PMD table just before we
    unshared it. It could then succeed in grabbing a page from the
    shared page table even after munmap() etc succeeded (and supressed
    an IPI). But there is not difference compared to GUP-fast just
    sleeping for a while after grabbing the page and re-enabling IRQs.

    Most importantly, GUP-fast will never walk into page tables that are
    no-longer shared, because the last sharer will issue an IPI
    broadcast.

    (if ever required, checking whether the PUD changed in GUP-fast
     after grabbing the page like we do in the PTE case could handle
     this)

So let's rework PMD sharing TLB flushing + IPI sync to use the mmu_gather
infrastructure so we can implement these optimizations and demystify the
code at least a bit. Extend the mmu_gather infrastructure to be able to
deal with our special hugetlb PMD table sharing implementation.

To make initialization of the mmu_gather easier when working on a single
VMA (in particular, when dealing with hugetlb), provide
tlb_gather_mmu_vma().

We'll consolidate the handling for (full) unsharing of PMD tables in
tlb_unshare_pmd_ptdesc() and tlb_flush_unshared_tables(), and track
in "struct mmu_gather" whether we had (full) unsharing of PMD tables.

Because locking is very special (concurrent unsharing+reuse must be
prevented), we disallow deferring flushing to tlb_finish_mmu() and instead
require an explicit earlier call to tlb_flush_unshared_tables().

From hugetlb code, we call huge_pmd_unshare_flush() where we make sure
that the expected lock protecting us from concurrent unsharing+reuse is
still held.

Check with a VM_WARN_ON_ONCE() in tlb_finish_mmu() that
tlb_flush_unshared_tables() was properly called earlier.

Document it all properly.

Notes about tlb_remove_table_sync_one() interaction with unsharing:

There are two fairly tricky things:

(1) tlb_remove_table_sync_one() is a NOP on architectures without
    CONFIG_MMU_GATHER_RCU_TABLE_FREE.

    Here, the assumption is that the previous TLB flush would send an
    IPI to all relevant CPUs. Careful: some architectures like x86 only
    send IPIs to all relevant CPUs when tlb->freed_tables is set.

    The relevant architectures should be selecting
    MMU_GATHER_RCU_TABLE_FREE, but x86 might not do that in stable
    kernels and it might have been problematic before this patch.

    Also, the arch flushing behavior (independent of IPIs) is different
    when tlb->freed_tables is set. Do we have to enlighten them to also
    take care of tlb->unshared_tables? So far we didn't care, so
    hopefully we are fine. Of course, we could be setting
    tlb->freed_tables as well, but that might then unnecessarily flush
    too much, because the semantics of tlb->freed_tables are a bit
    fuzzy.

    This patch changes nothing in this regard.

(2) tlb_remove_table_sync_one() is not a NOP on architectures with
    CONFIG_MMU_GATHER_RCU_TABLE_FREE that actually don't need a sync.

    Take x86 as an example: in the common case (!pv, !X86_FEATURE_INVLPGB)
    we still issue IPIs during TLB flushes and don't actually need the
    second tlb_remove_table_sync_one().

    This optimized can be implemented on top of this, by checking e.g., in
    tlb_remove_table_sync_one() whether we really need IPIs. But as
    described in (1), it really must honor tlb->freed_tables then to
    send IPIs to all relevant CPUs.

Notes on TLB flushing changes:

(1) Flushing for non-shared PMD tables

    We're converting from flush_hugetlb_tlb_range() to
    tlb_remove_huge_tlb_entry(). Given that we properly initialize the
    MMU gather in tlb_gather_mmu_vma() to be hugetlb aware, similar to
    __unmap_hugepage_range(), that should be fine.

(2) Flushing for shared PMD tables

    We're converting from various things (flush_hugetlb_tlb_range(),
    tlb_flush_pmd_range(), flush_tlb_range()) to tlb_flush_pmd_range().

    tlb_flush_pmd_range() achieves the same that
    tlb_remove_huge_tlb_entry() would achieve in these scenarios.
    Note that tlb_remove_huge_tlb_entry() also calls
    __tlb_remove_tlb_entry(), however that is only implemented on
    powerpc, which does not support PMD table sharing.

    Similar to (1), tlb_gather_mmu_vma() should make sure that TLB
    flushing keeps on working as expected.

Further, note that the ptdesc_pmd_pts_dec() in huge_pmd_share() is not a
concern, as we are holding the i_mmap_lock the whole time, preventing
concurrent unsharing. That ptdesc_pmd_pts_dec() usage will be removed
separately as a cleanup later.

There are plenty more cleanups to be had, but they have to wait until
this is fixed.

[david@kernel.org: fix kerneldoc]
  Link: https://lkml.kernel.org/r/f223dd74-331c-412d-93fc-69e360a5006c@kernel.org
Link: https://lkml.kernel.org/r/20251223214037.580860-5-david@kernel.org
Fixes: 1013af4f585f ("mm/hugetlb: fix huge_pmd_unshare() vs GUP-fast race")
Signed-off-by: David Hildenbrand (Red Hat) 
Reported-by: "Uschakow, Stanislav" 
Closes: https://lore.kernel.org/all/4d3878531c76479d9f8ca9789dc6485d@amazon.de/
Tested-by: Laurence Oberman 
Acked-by: Harry Yoo 
Reviewed-by: Lorenzo Stoakes 
Cc: Lance Yang 
Cc: Liu Shixin 
Cc: Oscar Salvador 
Cc: Rik van Riel 
Cc: 
Signed-off-by: Andrew Morton 
[ David: We don't have ptdesc and the wrappers, so work directly on
  page->pt_share_count and pass "struct page" instead of "struct ptdesc".
  CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING is still called
  CONFIG_ARCH_WANT_HUGE_PMD_SHARE and is set even without
  CONFIG_HUGETLB_PAGE. move_hugetlb_page_tables() still uses
  flush_tlb_range() instead of flush_hugetlb_tlb_range(). Some smaller
  contextual stuff. ]
Signed-off-by: David Hildenbrand (Arm) 
Signed-off-by: Greg Kroah-Hartman

mm: hugetlb: independent PMD page table shared count

2025-06-27T10:07:38+00:00

commit 59d9094df3d79443937add8700b2ef1a866b1081 upstream.

The folio refcount may be increased unexpectly through try_get_folio() by
caller such as split_huge_pages.  In huge_pmd_unshare(), we use refcount
to check whether a pmd page table is shared.  The check is incorrect if
the refcount is increased by the above caller, and this can cause the page
table leaked:

 BUG: Bad page state in process sh  pfn:109324
 page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x66 pfn:0x109324
 flags: 0x17ffff800000000(node=0|zone=2|lastcpupid=0xfffff)
 page_type: f2(table)
 raw: 017ffff800000000 0000000000000000 0000000000000000 0000000000000000
 raw: 0000000000000066 0000000000000000 00000000f2000000 0000000000000000
 page dumped because: nonzero mapcount
 ...
 CPU: 31 UID: 0 PID: 7515 Comm: sh Kdump: loaded Tainted: G    B              6.13.0-rc2master+ #7
 Tainted: [B]=BAD_PAGE
 Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015
 Call trace:
  show_stack+0x20/0x38 (C)
  dump_stack_lvl+0x80/0xf8
  dump_stack+0x18/0x28
  bad_page+0x8c/0x130
  free_page_is_bad_report+0xa4/0xb0
  free_unref_page+0x3cc/0x620
  __folio_put+0xf4/0x158
  split_huge_pages_all+0x1e0/0x3e8
  split_huge_pages_write+0x25c/0x2d8
  full_proxy_write+0x64/0xd8
  vfs_write+0xcc/0x280
  ksys_write+0x70/0x110
  __arm64_sys_write+0x24/0x38
  invoke_syscall+0x50/0x120
  el0_svc_common.constprop.0+0xc8/0xf0
  do_el0_svc+0x24/0x38
  el0_svc+0x34/0x128
  el0t_64_sync_handler+0xc8/0xd0
  el0t_64_sync+0x190/0x198

The issue may be triggered by damon, offline_page, page_idle, etc, which
will increase the refcount of page table.

1. The page table itself will be discarded after reporting the
   "nonzero mapcount".

2. The HugeTLB page mapped by the page table miss freeing since we
   treat the page table as shared and a shared page table will not be
   unmapped.

Fix it by introducing independent PMD page table shared count.  As
described by comment, pt_index/pt_mm/pt_frag_refcount are used for s390
gmap, x86 pgds and powerpc, pt_share_count is used for x86/arm64/riscv
pmds, so we can reuse the field as pt_share_count.

Link: https://lkml.kernel.org/r/20241216071147.3984217-1-liushixin2@huawei.com
Fixes: 39dde65c9940 ("[PATCH] shared page table for hugetlb page")
Signed-off-by: Liu Shixin 
Cc: Kefeng Wang 
Cc: Ken Chen 
Cc: Muchun Song 
Cc: Nanyong Sun 
Cc: Jane Chu 
Cc: 
Signed-off-by: Andrew Morton 
[backport note: struct ptdesc did not exist yet, stuff it equivalently
into struct page instead]
Signed-off-by: Jann Horn 
Signed-off-by: Greg Kroah-Hartman

mm: add private field of first tail to struct page and struct folio

2024-05-17T09:55:51+00:00

[ Upstream commit d340625f4849ab5dbfebbc7d84709fbfcd39e52f ]

Allow struct folio to store hugetlb metadata that is contained in the
private field of the first tail page.  On 32-bit, _private_1 aligns with
page[1].private.

Link: https://lkml.kernel.org/r/20220922154207.1575343-3-sidhartha.kumar@oracle.com
Signed-off-by: Sidhartha Kumar 
Acked-by: Mike Kravetz 
Cc: Arnd Bergmann 
Cc: Colin Cross 
Cc: David Howells 
Cc: "Eric W . Biederman" 
Cc: Hugh Dickins 
Cc: kernel test robot 
Cc: Matthew Wilcox 
Cc: Muchun Song 
Cc: Peter Xu 
Cc: Vlastimil Babka 
Cc: William Kucharski 
Signed-off-by: Andrew Morton 
Stable-dep-of: b76b46902c2d ("mm/hugetlb: fix missing hugetlb_lock for resv uncharge")
Signed-off-by: Sasha Levin

mm: enable maple tree RCU mode by default.

2023-04-13T14:55:40+00:00

commit 3dd4432549415f3c65dd52d5c687629efbf4ece1 upstream.

Use the maple tree in RCU mode for VMA tracking.

The maple tree tracks the stack and is able to update the pivot
(lower/upper boundary) in-place to allow the page fault handler to write
to the tree while holding just the mmap read lock.  This is safe as the
writes to the stack have a guard VMA which ensures there will always be
a NULL in the direction of the growth and thus will only update a pivot.

It is possible, but not recommended, to have VMAs that grow up/down
without guard VMAs.  syzbot has constructed a testcase which sets up a
VMA to grow and consume the empty space.  Overwriting the entire NULL
entry causes the tree to be altered in a way that is not safe for
concurrent readers; the readers may see a node being rewritten or one
that does not match the maple state they are using.

Enabling RCU mode allows the concurrent readers to see a stable node and
will return the expected result.

Link: https://lkml.kernel.org/r/20230227173632.3292573-9-surenb@google.com
Cc: stable@vger.kernel.org
Fixes: d4af56c5c7c6 ("mm: start tracking VMAs with maple tree")
Signed-off-by: Liam R. Howlett 
Reported-by: syzbot+8d95422d3537159ca390@syzkaller.appspotmail.com
Signed-off-by: Greg Kroah-Hartman

kmsan: add KMSAN runtime core

2022-10-03T21:03:19+00:00

For each memory location KernelMemorySanitizer maintains two types of
metadata:

1. The so-called shadow of that location - а byte:byte mapping describing
   whether or not individual bits of memory are initialized (shadow is 0)
   or not (shadow is 1).
2. The origins of that location - а 4-byte:4-byte mapping containing
   4-byte IDs of the stack traces where uninitialized values were
   created.

Each struct page now contains pointers to two struct pages holding KMSAN
metadata (shadow and origins) for the original struct page.  Utility
routines in mm/kmsan/core.c and mm/kmsan/shadow.c handle the metadata
creation, addressing, copying and checking.  mm/kmsan/report.c performs
error reporting in the cases an uninitialized value is used in a way that
leads to undefined behavior.

KMSAN compiler instrumentation is responsible for tracking the metadata
along with the kernel memory.  mm/kmsan/instrumentation.c provides the
implementation for instrumentation hooks that are called from files
compiled with -fsanitize=kernel-memory.

To aid parameter passing (also done at instrumentation level), each
task_struct now contains a struct kmsan_task_state used to track the
metadata of function parameters and return values for that task.

Finally, this patch provides CONFIG_KMSAN that enables KMSAN, and declares
CFLAGS_KMSAN, which are applied to files compiled with KMSAN.  The
KMSAN_SANITIZE:=n Makefile directive can be used to completely disable
KMSAN instrumentation for certain files.

Similarly, KMSAN_ENABLE_CHECKS:=n disables KMSAN checks and makes newly
created stack memory initialized.

Users can also use functions from include/linux/kmsan-checks.h to mark
certain memory regions as uninitialized or initialized (this is called
"poisoning" and "unpoisoning") or check that a particular region is
initialized.

Link: https://lkml.kernel.org/r/20220915150417.722975-12-glider@google.com
Signed-off-by: Alexander Potapenko 
Acked-by: Marco Elver 
Cc: Alexander Viro 
Cc: Alexei Starovoitov 
Cc: Andrey Konovalov 
Cc: Andrey Konovalov 
Cc: Andy Lutomirski 
Cc: Arnd Bergmann 
Cc: Borislav Petkov 
Cc: Christoph Hellwig 
Cc: Christoph Lameter 
Cc: David Rientjes 
Cc: Dmitry Vyukov 
Cc: Eric Biggers 
Cc: Eric Biggers 
Cc: Eric Dumazet 
Cc: Greg Kroah-Hartman 
Cc: Herbert Xu 
Cc: Ilya Leoshkevich 
Cc: Ingo Molnar 
Cc: Jens Axboe 
Cc: Joonsoo Kim 
Cc: Kees Cook 
Cc: Mark Rutland 
Cc: Matthew Wilcox 
Cc: Michael S. Tsirkin 
Cc: Pekka Enberg 
Cc: Peter Zijlstra 
Cc: Petr Mladek 
Cc: Stephen Rothwell 
Cc: Steven Rostedt 
Cc: Thomas Gleixner 
Cc: Vasily Gorbik 
Cc: Vegard Nossum 
Cc: Vlastimil Babka 
Signed-off-by: Andrew Morton

mm: add the first tail page to struct folio

2022-10-03T21:02:44+00:00

Some of the static checkers get confused by extracting the page from the
folio and referring to fields in the first tail page.  Adding these fields
to struct folio lets us avoid doing that.  It has the risk that people
will refer to those fields without checking that the folio is actually a
large folio, so prefix them with underscores and document the preferred
function to use instead.

Link: https://lkml.kernel.org/r/20220902194653.1739778-3-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) 
Signed-off-by: Andrew Morton

ksm: count allocated ksm rmap_items for each process

2022-09-27T02:46:29+00:00

Patch series "ksm: count allocated rmap_items and update documentation",
v5.

KSM can save memory by merging identical pages, but also can consume
additional memory, because it needs to generate rmap_items to save each
scanned page's brief rmap information.

To determine how beneficial the ksm-policy (like madvise), they are using
brings, so we add a new interface /proc//ksm_stat for each process
The value "ksm_rmap_items" in it indicates the total allocated ksm
rmap_items of this process.

The detailed description can be seen in the following patches' commit
message.


This patch (of 2):

KSM can save memory by merging identical pages, but also can consume
additional memory, because it needs to generate rmap_items to save each
scanned page's brief rmap information.  Some of these pages may be merged,
but some may not be abled to be merged after being checked several times,
which are unprofitable memory consumed.

The information about whether KSM save memory or consume memory in
system-wide range can be determined by the comprehensive calculation of
pages_sharing, pages_shared, pages_unshared and pages_volatile.  A simple
approximate calculation:

	profit =~ pages_sharing * sizeof(page) - (all_rmap_items) *
	         sizeof(rmap_item);

where all_rmap_items equals to the sum of pages_sharing, pages_shared,
pages_unshared and pages_volatile.

But we cannot calculate this kind of ksm profit inner single-process wide
because the information of ksm rmap_item's number of a process is lacked. 
For user applications, if this kind of information could be obtained, it
helps upper users know how beneficial the ksm-policy (like madvise) they
are using brings, and then optimize their app code.  For example, one
application madvise 1000 pages as MERGEABLE, while only a few pages are
really merged, then it's not cost-efficient.

So we add a new interface /proc//ksm_stat for each process in which
the value of ksm_rmap_itmes is only shown now and so more values can be
added in future.

So similarly, we can calculate the ksm profit approximately for a single
process by:

	profit =~ ksm_merging_pages * sizeof(page) - ksm_rmap_items *
		 sizeof(rmap_item);

where ksm_merging_pages is shown at /proc//ksm_merging_pages, and
ksm_rmap_items is shown in /proc//ksm_stat.

Link: https://lkml.kernel.org/r/20220830143731.299702-1-xu.xin16@zte.com.cn
Link: https://lkml.kernel.org/r/20220830143838.299758-1-xu.xin16@zte.com.cn
Signed-off-by: xu xin 
Reviewed-by: Xiaokai Ran 
Reviewed-by: Yang Yang 
Signed-off-by: CGEL ZTE 
Cc: Alexey Dobriyan 
Cc: Bagas Sanjaya 
Cc: Hugh Dickins 
Cc: Izik Eidus 
Cc: Matthew Wilcox 
Signed-off-by: Andrew Morton

mm: fixup documentation regarding pte_numa() and PROT_NUMA

2022-09-27T02:46:28+00:00

pte_numa() no longer exists -- replaced by pte_protnone() -- and PROT_NUMA
probably never existed: MM_CP_PROT_NUMA also ends up using PROT_NONE.

Let's fixup the doc.

Link: https://lkml.kernel.org/r/20220825164659.89824-4-david@redhat.com
Signed-off-by: David Hildenbrand 
Cc: Andrea Arcangeli 
Cc: Hugh Dickins 
Cc: Jason Gunthorpe 
Cc: John Hubbard 
Cc: Matthew Wilcox 
Cc: Mel Gorman 
Cc: Peter Xu 
Signed-off-by: Andrew Morton

mm: remove the vma linked list

2022-09-27T02:46:26+00:00

Replace any vm_next use with vma_find().

Update free_pgtables(), unmap_vmas(), and zap_page_range() to use the
maple tree.

Use the new free_pgtables() and unmap_vmas() in do_mas_align_munmap().  At
the same time, alter the loop to be more compact.

Now that free_pgtables() and unmap_vmas() take a maple tree as an
argument, rearrange do_mas_align_munmap() to use the new tree to hold the
vmas to remove.

Remove __vma_link_list() and __vma_unlink_list() as they are exclusively
used to update the linked list.

Drop linked list update from __insert_vm_struct().

Rework validation of tree as it was depending on the linked list.

[yang.lee@linux.alibaba.com: fix one kernel-doc comment]
  Link: https://bugzilla.openanolis.cn/show_bug.cgi?id=1949
  Link: https://lkml.kernel.org/r/20220824021918.94116-1-yang.lee@linux.alibaba.comLink: https://lkml.kernel.org/r/20220906194824.2110408-69-Liam.Howlett@oracle.com
Signed-off-by: Liam R. Howlett 
Signed-off-by: Yang Li 
Tested-by: Yu Zhao 
Cc: Catalin Marinas 
Cc: David Hildenbrand 
Cc: David Howells 
Cc: Davidlohr Bueso 
Cc: "Matthew Wilcox (Oracle)" 
Cc: SeongJae Park 
Cc: Sven Schnelle 
Cc: Vlastimil Babka 
Cc: Will Deacon 
Signed-off-by: Andrew Morton

mm: remove vmacache

2022-09-27T02:46:18+00:00

By using the maple tree and the maple tree state, the vmacache is no
longer beneficial and is complicating the VMA code.  Remove the vmacache
to reduce the work in keeping it up to date and code complexity.

Link: https://lkml.kernel.org/r/20220906194824.2110408-26-Liam.Howlett@oracle.com
Signed-off-by: Liam R. Howlett 
Acked-by: Vlastimil Babka 
Tested-by: Yu Zhao 
Cc: Catalin Marinas 
Cc: David Hildenbrand 
Cc: David Howells 
Cc: Davidlohr Bueso 
Cc: "Matthew Wilcox (Oracle)" 
Cc: SeongJae Park 
Cc: Sven Schnelle 
Cc: Will Deacon 
Signed-off-by: Andrew Morton