linux.git/include/linux/hugetlb.h, branch v6.7-rc2

mempolicy: mmap_lock is not needed while migrating folios

2023-10-25T23:47:16+00:00

mbind(2) holds down_write of current task's mmap_lock throughout
(exclusive because it needs to set the new mempolicy on the vmas);
migrate_pages(2) holds down_read of pid's mmap_lock throughout.

They both hold mmap_lock across the internal migrate_pages(), under which
all new page allocations (huge or small) are made.  I'm nervous about it;
and migrate_pages() certainly does not need mmap_lock itself.  It's done
this way for mbind(2), because its page allocator is vma_alloc_folio() or
alloc_hugetlb_folio_vma(), both of which depend on vma and address.

Now that we have alloc_pages_mpol(), depending on (refcounted) memory
policy and interleave index, mbind(2) can be modified to use that or
alloc_hugetlb_folio_nodemask(), and then not need mmap_lock across the
internal migrate_pages() at all: add alloc_migration_target_by_mpol() to
replace mbind's new_page().

(After that change, alloc_hugetlb_folio_vma() is used by nothing but a
userfaultfd function: move it out of hugetlb.h and into the #ifdef.)

migrate_pages(2) has chosen its target node before migrating, so can
continue to use the standard alloc_migration_target(); but let it take and
drop mmap_lock just around migrate_to_node()'s queue_pages_range():
neither the node-to-node calculations nor the page migrations need it.

It seems unlikely, but it is conceivable that some userspace depends on
the kernel's mmap_lock exclusion here, instead of doing its own locking:
more likely in a testsuite than in real life.  It is also possible, of
course, that some pages on the list will be munmapped by another thread
before they are migrated, or a newer memory policy applied to the range by
that time: but such races could happen before, as soon as mmap_lock was
dropped, so it does not appear to be a concern.

Link: https://lkml.kernel.org/r/21e564e8-269f-6a89-7ee2-fd612831c289@google.com
Signed-off-by: Hugh Dickins 
Cc: Andi Kleen 
Cc: Christoph Lameter 
Cc: David Hildenbrand 
Cc: Greg Kroah-Hartman 
Cc: "Huang, Ying" 
Cc: Kefeng Wang 
Cc: Matthew Wilcox (Oracle) 
Cc: Mel Gorman 
Cc: Michal Hocko 
Cc: Mike Kravetz 
Cc: Nhat Pham 
Cc: Sidhartha Kumar 
Cc: Suren Baghdasaryan 
Cc: Tejun heo 
Cc: Vishal Moola (Oracle) 
Cc: Yang Shi 
Cc: Yosry Ahmed 
Signed-off-by: Andrew Morton

hugetlbfs: drop shared NUMA mempolicy pretence

2023-10-25T23:47:15+00:00

Patch series "mempolicy: cleanups leading to NUMA mpol without vma", v2.

Mostly cleanups in mm/mempolicy.c, but finally removing the pseudo-vma
from shmem folio allocation, and removing the mmap_lock around folio
migration for mbind and migrate_pages syscalls.


This patch (of 12):

hugetlbfs_fallocate() goes through the motions of pasting a shared NUMA
mempolicy onto its pseudo-vma, but how could there ever be a shared NUMA
mempolicy for this file?  hugetlb_vm_ops has never offered a set_policy
method, and hugetlbfs_parse_param() has never supported any mpol options
for a mount-wide default policy.

It's just an illusion: clean it away so as not to confuse others, giving
us more freedom to adjust shmem's set_policy/get_policy implementation. 
But hugetlbfs_inode_info is still required, just to accommodate seals.

Yes, shared NUMA mempolicy support could be added to hugetlbfs, with a
set_policy method and/or mpol mount option (Andi's first posting did
include an admitted-unsatisfactory hugetlb_set_policy()); but it seems
that nobody has bothered to add that in the nineteen years since v2.6.7
made it possible, and there is at least one company that has invested
enough into hugetlbfs, that I guess they have learnt well enough how to
manage its NUMA, without needing shared mempolicy.

Remove linux/mempolicy.h from linux/hugetlb.h: include linux/pagemap.h in
its place, because hugetlb.h's recently added use of filemap_lock_folio()
requires that (although most .configs and .c's get it in some other way).

Link: https://lkml.kernel.org/r/ebc0987e-beff-8bfb-9283-234c2cbd17c5@google.com
Link: https://lkml.kernel.org/r/cae82d4b-904a-faaf-282a-34fcc188c81f@google.com
Signed-off-by: Hugh Dickins 
Reviewed-by: Matthew Wilcox (Oracle) 
Cc: Andi Kleen 
Cc: Christoph Lameter 
Cc: David Hildenbrand 
Cc: Greg Kroah-Hartman 
Cc: "Huang, Ying" 
Cc: Kefeng Wang 
Cc: Mel Gorman 
Cc: Michal Hocko 
Cc: Mike Kravetz 
Cc: Sidhartha Kumar 
Cc: Suren Baghdasaryan 
Cc: Tejun heo 
Cc: Vishal Moola (Oracle) 
Cc: Yang Shi 
Cc: Nhat Pham 
Cc: Yosry Ahmed 
Signed-off-by: Andrew Morton

fs/proc/task_mmu: implement IOCTL to get and optionally clear info about PTEs

2023-10-18T21:34:12+00:00

The PAGEMAP_SCAN IOCTL on the pagemap file can be used to get or optionally
clear the info about page table entries. The following operations are
supported in this IOCTL:
- Scan the address range and get the memory ranges matching the provided
  criteria. This is performed when the output buffer is specified.
- Write-protect the pages. The PM_SCAN_WP_MATCHING is used to write-protect
  the pages of interest. The PM_SCAN_CHECK_WPASYNC aborts the operation if
  non-Async Write Protected pages are found. The ``PM_SCAN_WP_MATCHING``
  can be used with or without PM_SCAN_CHECK_WPASYNC.
- Both of those operations can be combined into one atomic operation where
  we can get and write protect the pages as well.

Following flags about pages are currently supported:
- PAGE_IS_WPALLOWED - Page has async-write-protection enabled
- PAGE_IS_WRITTEN - Page has been written to from the time it was write protected
- PAGE_IS_FILE - Page is file backed
- PAGE_IS_PRESENT - Page is present in the memory
- PAGE_IS_SWAPPED - Page is in swapped
- PAGE_IS_PFNZERO - Page has zero PFN
- PAGE_IS_HUGE - Page is THP or Hugetlb backed

This IOCTL can be extended to get information about more PTE bits. The
entire address range passed by user [start, end) is scanned until either
the user provided buffer is full or max_pages have been found.

[akpm@linux-foundation.org: update it for "mm: hugetlb: add huge page size param to set_huge_pte_at()"]
[akpm@linux-foundation.org: fix CONFIG_HUGETLB_PAGE=n warning]
[arnd@arndb.de: hide unused pagemap_scan_backout_range() function]
  Link: https://lkml.kernel.org/r/20230927060257.2975412-1-arnd@kernel.org
[sfr@canb.auug.org.au: fix "fs/proc/task_mmu: hide unused pagemap_scan_backout_range() function"]
  Link: https://lkml.kernel.org/r/20230928092223.0625c6bf@canb.auug.org.au
Link: https://lkml.kernel.org/r/20230821141518.870589-3-usama.anjum@collabora.com
Signed-off-by: Muhammad Usama Anjum 
Signed-off-by: Michał Mirosław 
Signed-off-by: Arnd Bergmann 
Signed-off-by: Stephen Rothwell 
Reviewed-by: Andrei Vagin 
Reviewed-by: Michał Mirosław 
Cc: Alex Sierra 
Cc: Al Viro 
Cc: Axel Rasmussen 
Cc: Christian Brauner 
Cc: Cyrill Gorcunov 
Cc: Dan Williams 
Cc: David Hildenbrand 
Cc: Greg Kroah-Hartman 
Cc: Gustavo A. R. Silva 
Cc: "Liam R. Howlett" 
Cc: Matthew Wilcox 
Cc: Michal Miroslaw 
Cc: Mike Rapoport (IBM) 
Cc: Nadav Amit 
Cc: Pasha Tatashin 
Cc: Paul Gofman 
Cc: Peter Xu 
Cc: Shuah Khan 
Cc: Suren Baghdasaryan 
Cc: Vlastimil Babka 
Cc: Yang Shi 
Cc: Yun Zhou 
Signed-off-by: Andrew Morton

Merge mm-hotfixes-stable into mm-stable to pick up depended-upon changes.

2023-10-18T21:32:58+00:00

hugetlbfs: close race between MADV_DONTNEED and page fault

2023-10-18T19:12:41+00:00

Malloc libraries, like jemalloc and tcalloc, take decisions on when to
call madvise independently from the code in the main application.

This sometimes results in the application page faulting on an address,
right after the malloc library has shot down the backing memory with
MADV_DONTNEED.

Usually this is harmless, because we always have some 4kB pages sitting
around to satisfy a page fault.  However, with hugetlbfs systems often
allocate only the exact number of huge pages that the application wants.

Due to TLB batching, hugetlbfs MADV_DONTNEED will free pages outside of
any lock taken on the page fault path, which can open up the following
race condition:

       CPU 1                            CPU 2

       MADV_DONTNEED
       unmap page
       shoot down TLB entry
                                       page fault
                                       fail to allocate a huge page
                                       killed with SIGBUS
       free page

Fix that race by pulling the locking from __unmap_hugepage_final_range
into helper functions called from zap_page_range_single.  This ensures
page faults stay locked out of the MADV_DONTNEED VMA until the huge pages
have actually been freed.

Link: https://lkml.kernel.org/r/20231006040020.3677377-4-riel@surriel.com
Fixes: 04ada095dcfc ("hugetlb: don't delete vma_lock in hugetlb MADV_DONTNEED processing")
Signed-off-by: Rik van Riel 
Reviewed-by: Mike Kravetz 
Cc: Matthew Wilcox (Oracle) 
Cc: Muchun Song 
Cc: 
Signed-off-by: Andrew Morton

hugetlbfs: extend hugetlb_vma_lock to private VMAs

2023-10-18T19:12:41+00:00

Extend the locking scheme used to protect shared hugetlb mappings from
truncate vs page fault races, in order to protect private hugetlb mappings
(with resv_map) against MADV_DONTNEED.

Add a read-write semaphore to the resv_map data structure, and use that
from the hugetlb_vma_(un)lock_* functions, in preparation for closing the
race between MADV_DONTNEED and page faults.

Link: https://lkml.kernel.org/r/20231006040020.3677377-3-riel@surriel.com
Fixes: 04ada095dcfc ("hugetlb: don't delete vma_lock in hugetlb MADV_DONTNEED processing")
Signed-off-by: Rik van Riel 
Reviewed-by: Mike Kravetz 
Cc: Matthew Wilcox (Oracle) 
Cc: Muchun Song 
Cc: 
Signed-off-by: Andrew Morton

mm/filemap: remove hugetlb special casing in filemap.c

2023-10-16T22:44:38+00:00

Remove special cased hugetlb handling code within the page cache by
changing the granularity of ->index to the base page size rather than the
huge page size.  The motivation of this patch is to reduce complexity
within the filemap code while also increasing performance by removing
branches that are evaluated on every page cache lookup.

To support the change in index, new wrappers for hugetlb page cache
interactions are added.  These wrappers perform the conversion to a linear
index which is now expected by the page cache for huge pages.

========================= PERFORMANCE ======================================

Perf was used to check the performance differences after the patch. 
Overall the performance is similar to mainline with a very small larger
overhead that occurs in __filemap_add_folio() and
hugetlb_add_to_page_cache().  This is because of the larger overhead that
occurs in xa_load() and xa_store() as the xarray is now using more entries
to store hugetlb folios in the page cache.

Timing

aarch64
    2MB Page Size
        6.5-rc3 + this patch:
            [root@sidhakum-ol9-1 hugepages]# time fallocate -l 700GB test.txt
            real    1m49.568s
            user    0m0.000s
            sys     1m49.461s

        6.5-rc3:
            [root]# time fallocate -l 700GB test.txt
            real    1m47.495s
            user    0m0.000s
            sys     1m47.370s
    1GB Page Size
        6.5-rc3 + this patch:
            [root@sidhakum-ol9-1 hugepages1G]# time fallocate -l 700GB test.txt
            real    1m47.024s
            user    0m0.000s
            sys     1m46.921s

        6.5-rc3:
            [root@sidhakum-ol9-1 hugepages1G]# time fallocate -l 700GB test.txt
            real    1m44.551s
            user    0m0.000s
            sys     1m44.438s

x86
    2MB Page Size
        6.5-rc3 + this patch:
            [root@sidhakum-ol9-2 hugepages]# time fallocate -l 100GB test.txt
            real    0m22.383s
            user    0m0.000s
            sys     0m22.255s

        6.5-rc3:
            [opc@sidhakum-ol9-2 hugepages]$ time sudo fallocate -l 100GB /dev/hugepages/test.txt
            real    0m22.735s
            user    0m0.038s
            sys     0m22.567s

    1GB Page Size
        6.5-rc3 + this patch:
            [root@sidhakum-ol9-2 hugepages1GB]# time fallocate -l 100GB test.txt
            real    0m25.786s
            user    0m0.001s
            sys     0m25.589s

        6.5-rc3:
            [root@sidhakum-ol9-2 hugepages1G]# time fallocate -l 100GB test.txt
            real    0m33.454s
            user    0m0.001s
            sys     0m33.193s

aarch64:
    workload - fallocate a 700GB file backed by huge pages

    6.5-rc3 + this patch:
        2MB Page Size:
            --100.00%--__arm64_sys_fallocate
                          ksys_fallocate
                          vfs_fallocate
                          hugetlbfs_fallocate
                          |
                          |--95.04%--__pi_clear_page
                          |
                          |--3.57%--clear_huge_page
                          |          |
                          |          |--2.63%--rcu_all_qs
                          |          |
                          |           --0.91%--__cond_resched
                          |
                           --0.67%--__cond_resched
            0.17%     0.00%             0  fallocate  [kernel.vmlinux]       [k] hugetlb_add_to_page_cache
            0.14%     0.10%            11  fallocate  [kernel.vmlinux]       [k] __filemap_add_folio

    6.5-rc3
        2MB Page Size:
                --100.00%--__arm64_sys_fallocate
                          ksys_fallocate
                          vfs_fallocate
                          hugetlbfs_fallocate
                          |
                          |--94.91%--__pi_clear_page
                          |
                          |--4.11%--clear_huge_page
                          |          |
                          |          |--3.00%--rcu_all_qs
                          |          |
                          |           --1.10%--__cond_resched
                          |
                           --0.59%--__cond_resched
            0.08%     0.01%             1  fallocate  [kernel.kallsyms]  [k] hugetlb_add_to_page_cache
            0.05%     0.03%             3  fallocate  [kernel.kallsyms]  [k] __filemap_add_folio

x86
    workload - fallocate a 100GB file backed by huge pages

    6.5-rc3 + this patch:
        2MB Page Size:
            hugetlbfs_fallocate
            |
            --99.57%--clear_huge_page
                |
                --98.47%--clear_page_erms
                    |
                    --0.53%--asm_sysvec_apic_timer_interrupt

            0.04%     0.04%             1  fallocate  [kernel.kallsyms]     [k] xa_load
            0.04%     0.00%             0  fallocate  [kernel.kallsyms]     [k] hugetlb_add_to_page_cache
            0.04%     0.00%             0  fallocate  [kernel.kallsyms]     [k] __filemap_add_folio
            0.04%     0.00%             0  fallocate  [kernel.kallsyms]     [k] xas_store

    6.5-rc3
        2MB Page Size:
                --99.93%--__x64_sys_fallocate
                          vfs_fallocate
                          hugetlbfs_fallocate
                          |
                           --99.38%--clear_huge_page
                                     |
                                     |--98.40%--clear_page_erms
                                     |
                                      --0.59%--__cond_resched
            0.03%     0.03%             1  fallocate  [kernel.kallsyms]  [k] __filemap_add_folio

========================= TESTING ======================================

This patch passes libhugetlbfs tests and LTP hugetlb tests

********** TEST SUMMARY
*                      2M
*                      32-bit 64-bit
*     Total testcases:   110    113
*             Skipped:     0      0
*                PASS:   107    113
*                FAIL:     0      0
*    Killed by signal:     3      0
*   Bad configuration:     0      0
*       Expected FAIL:     0      0
*     Unexpected PASS:     0      0
*    Test not present:     0      0
* Strange test result:     0      0
**********

    Done executing testcases.
    LTP Version:  20220527-178-g2761a81c4

page migration was also tested using Mike Kravetz's test program.[8]

[dan.carpenter@linaro.org: fix an NULL vs IS_ERR() bug]
  Link: https://lkml.kernel.org/r/1772c296-1417-486f-8eef-171af2192681@moroto.mountain
Link: https://lkml.kernel.org/r/20230926192017.98183-1-sidhartha.kumar@oracle.com
Signed-off-by: Sidhartha Kumar 
Signed-off-by: Dan Carpenter 
Reported-and-tested-by: syzbot+c225dea486da4d5592bd@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=c225dea486da4d5592bd
Cc: Matthew Wilcox (Oracle) 
Cc: Mike Kravetz 
Cc: Muchun Song 
Signed-off-by: Andrew Morton

mm: hugetlb: add huge page size param to set_huge_pte_at()

2023-09-30T00:20:47+00:00

Patch series "Fix set_huge_pte_at() panic on arm64", v2.

This series fixes a bug in arm64's implementation of set_huge_pte_at(),
which can result in an unprivileged user causing a kernel panic.  The
problem was triggered when running the new uffd poison mm selftest for
HUGETLB memory.  This test (and the uffd poison feature) was merged for
v6.5-rc7.

Ideally, I'd like to get this fix in for v6.6 and I've cc'ed stable
(correctly this time) to get it backported to v6.5, where the issue first
showed up.


Description of Bug
==================

arm64's huge pte implementation supports multiple huge page sizes, some of
which are implemented in the page table with multiple contiguous entries. 
So set_huge_pte_at() needs to work out how big the logical pte is, so that
it can also work out how many physical ptes (or pmds) need to be written. 
It previously did this by grabbing the folio out of the pte and querying
its size.

However, there are cases when the pte being set is actually a swap entry. 
But this also used to work fine, because for huge ptes, we only ever saw
migration entries and hwpoison entries.  And both of these types of swap
entries have a PFN embedded, so the code would grab that and everything
still worked out.

But over time, more calls to set_huge_pte_at() have been added that set
swap entry types that do not embed a PFN.  And this causes the code to go
bang.  The triggering case is for the uffd poison test, commit
99aa77215ad0 ("selftests/mm: add uffd unit test for UFFDIO_POISON"), which
causes a PTE_MARKER_POISONED swap entry to be set, coutesey of commit
8a13897fb0da ("mm: userfaultfd: support UFFDIO_POISON for hugetlbfs") -
added in v6.5-rc7.  Although review shows that there are other call sites
that set PTE_MARKER_UFFD_WP (which also has no PFN), these don't trigger
on arm64 because arm64 doesn't support UFFD WP.

If CONFIG_DEBUG_VM is enabled, we do at least get a BUG(), but otherwise,
it will dereference a bad pointer in page_folio():

    static inline struct folio *hugetlb_swap_entry_to_folio(swp_entry_t entry)
    {
        VM_BUG_ON(!is_migration_entry(entry) && !is_hwpoison_entry(entry));

        return page_folio(pfn_to_page(swp_offset_pfn(entry)));
    }


Fix
===

The simplest fix would have been to revert the dodgy cleanup commit
18f3962953e4 ("mm: hugetlb: kill set_huge_swap_pte_at()"), but since
things have moved on, this would have required an audit of all the new
set_huge_pte_at() call sites to see if they should be converted to
set_huge_swap_pte_at().  As per the original intent of the change, it
would also leave us open to future bugs when people invariably get it
wrong and call the wrong helper.

So instead, I've added a huge page size parameter to set_huge_pte_at(). 
This means that the arm64 code has the size in all cases.  It's a bigger
change, due to needing to touch the arches that implement the function,
but it is entirely mechanical, so in my view, low risk.

I've compile-tested all touched arches; arm64, parisc, powerpc, riscv,
s390, sparc (and additionally x86_64).  I've additionally booted and run
mm selftests against arm64, where I observe the uffd poison test is fixed,
and there are no other regressions.


This patch (of 2):

In order to fix a bug, arm64 needs to be told the size of the huge page
for which the pte is being set in set_huge_pte_at().  Provide for this by
adding an `unsigned long sz` parameter to the function.  This follows the
same pattern as huge_pte_clear().

This commit makes the required interface modifications to the core mm as
well as all arches that implement this function (arm64, parisc, powerpc,
riscv, s390, sparc).  The actual arm64 bug will be fixed in a separate
commit.

No behavioral changes intended.

Link: https://lkml.kernel.org/r/20230922115804.2043771-1-ryan.roberts@arm.com
Link: https://lkml.kernel.org/r/20230922115804.2043771-2-ryan.roberts@arm.com
Fixes: 8a13897fb0da ("mm: userfaultfd: support UFFDIO_POISON for hugetlbfs")
Signed-off-by: Ryan Roberts 
Reviewed-by: Christophe Leroy 	[powerpc 8xx]
Reviewed-by: Lorenzo Stoakes 	[vmalloc change]
Cc: Alexandre Ghiti 
Cc: Albert Ou 
Cc: Alexander Gordeev 
Cc: Anshuman Khandual 
Cc: Arnd Bergmann 
Cc: Axel Rasmussen 
Cc: Catalin Marinas 
Cc: Christian Borntraeger 
Cc: Christoph Hellwig 
Cc: David S. Miller 
Cc: Gerald Schaefer 
Cc: Heiko Carstens 
Cc: Helge Deller 
Cc: "James E.J. Bottomley" 
Cc: Mike Kravetz 
Cc: Muchun Song 
Cc: Nicholas Piggin 
Cc: Palmer Dabbelt 
Cc: Paul Walmsley 
Cc: Peter Xu 
Cc: Qi Zheng 
Cc: Ryan Roberts 
Cc: SeongJae Park 
Cc: Sven Schnelle 
Cc: Uladzislau Rezki (Sony) 
Cc: Vasily Gorbik 
Cc: Will Deacon 
Cc: 	[6.5+]
Signed-off-by: Andrew Morton

mm: convert free_huge_page() to free_huge_folio()

2023-08-21T21:28:43+00:00

Pass a folio instead of the head page to save a few instructions.  Update
the documentation, at least in English.

Link: https://lkml.kernel.org/r/20230816151201.3655946-4-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) 
Reviewed-by: Sidhartha Kumar 
Cc: Yanteng Si 
Cc: David Hildenbrand 
Cc: Jens Axboe 
Signed-off-by: Andrew Morton

mm: call free_huge_page() directly

2023-08-21T21:28:43+00:00

Indirect calls are expensive, thanks to Spectre.  Call free_huge_page()
directly if the folio belongs to hugetlb.

Link: https://lkml.kernel.org/r/20230816151201.3655946-3-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) 
Cc: David Hildenbrand 
Cc: Jens Axboe 
Cc: Sidhartha Kumar 
Cc: Yanteng Si 
Signed-off-by: Andrew Morton