linux/include
Jinjiang Tu f1acf5887c mm/huge_memory: fix folio isn't locked in softleaf_to_folio()
[ Upstream commit 4c5e7f0fcd ]

On arm64 server, we found folio that get from migration entry isn't locked
in softleaf_to_folio().  This issue triggers when mTHP splitting and
zap_nonpresent_ptes() races, and the root cause is lack of memory barrier
in softleaf_to_folio().  The race is as follows:

	CPU0                                             CPU1

deferred_split_scan()                              zap_nonpresent_ptes()
  lock folio
  split_folio()
    unmap_folio()
      change ptes to migration entries
    __split_folio_to_order()                         softleaf_to_folio()
      set flags(including PG_locked) for tail pages    folio = pfn_folio(softleaf_to_pfn(entry))
      smp_wmb()                                        VM_WARN_ON_ONCE(!folio_test_locked(folio))
      prep_compound_page() for tail pages

In __split_folio_to_order(), smp_wmb() guarantees page flags of tail pages
are visible before the tail page becomes non-compound.  smp_wmb() should
be paired with smp_rmb() in softleaf_to_folio(), which is missed.  As a
result, if zap_nonpresent_ptes() accesses migration entry that stores tail
pfn, softleaf_to_folio() may see the updated compound_head of tail page
before page->flags.

This issue will trigger VM_WARN_ON_ONCE() in pfn_swap_entry_folio()
because of the race between folio split and zap_nonpresent_ptes()
leading to a folio incorrectly undergoing modification without a folio
lock being held.

This is a BUG_ON() before commit 93976a2034 ("mm: eliminate further
swapops predicates"), which in merged in v6.19-rc1.

To fix it, add missing smp_rmb() if the softleaf entry is migration entry
in softleaf_to_folio() and softleaf_to_page().

[tujinjiang@huawei.com: update function name and comments]
  Link: https://lkml.kernel.org/r/20260321075214.3305564-1-tujinjiang@huawei.com
Link: https://lkml.kernel.org/r/20260319012541.4158561-1-tujinjiang@huawei.com
Fixes: e9b61f1985 ("thp: reintroduce split_huge_page()")
Signed-off-by: Jinjiang Tu <tujinjiang@huawei.com>
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Reviewed-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Cc: Barry Song <baohua@kernel.org>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Nanyong Sun <sunnanyong@huawei.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
[ adapted fix from leafops.h softleaf_to_page()/softleaf_to_folio() ]
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
History 2026-04-18 10:33:38 +02:00
..
acpi ACPICA: Allow address_space_handler Install and _REG execution as 2 separate steps 2026-04-18 10:33:26 +02:00
asm-generic mm/hugetlb: fix excessive IPI broadcasts when unsharing PMD tables using mmu_gather 2026-04-18 10:33:18 +02:00
clocksource x86/hyperv: Fix hv tsc page based sched_clock for hibernation 2025-01-09 13:28:42 +01:00
crypto crypto: af_alg - Fix incorrect boolean values in af_alg_ctx 2025-10-02 13:39:13 +02:00
drm drm: of: drm_of_panel_bridge_remove(): fix device_node leak 2026-03-04 07:20:30 -05:00
dt-bindings clk: ti: am43xx: Add clkctrl data for am43xx ADC1 2025-07-10 15:57:35 +02:00
keys KEYS: trusted: allow use of kernel RNG for key material 2023-10-19 23:05:33 +02:00
kunit kunit: fix kernel-doc warnings due to mismatched arg names 2021-10-06 17:54:07 -06:00
kvm KVM: arm64: vgic-v4: Make the doorbell request robust w.r.t preemption 2024-07-05 09:14:51 +02:00
linux mm/huge_memory: fix folio isn't locked in softleaf_to_folio() 2026-04-18 10:33:38 +02:00
math-emu math-emu: Fix fall-through warning 2021-07-13 13:57:44 -05:00
media media: dvb-core: dmxdevfilter must always flush bufs 2026-03-04 07:20:01 -05:00
memory memory: renesas-rpc-if: Fix HF/OSPI data transfer in Manual Mode 2022-05-09 09:14:34 +02:00
misc ocxl: Update the Process Element Entry 2020-12-04 01:01:30 +11:00
net netfilter: nft_ct: fix use-after-free in timeout object destroy 2026-04-18 10:33:36 +02:00
pcmcia pcmcia: Replace zero-length array with flexible-array 2020-05-18 10:28:31 +02:00
ras Revert "mm/memory-failure.c: fix race with changing page compound again" 2022-07-12 16:35:17 +02:00
rdma RDMA/core: add rdma_rw_max_sge() helper for SQ sizing 2026-03-04 07:19:43 -05:00
scsi scsi: libsas: Add sas_task_find_rq() 2025-10-19 16:21:40 +02:00
soc soc: qcom: rpmh-rsc: Enhance check for VRM in-flight request 2024-06-16 13:39:55 +02:00
sound ASoC: core: Do not call link_exit() on uninitialized rtd objects 2026-04-18 10:33:12 +02:00
target scsi: target: Fix multiple LUN_RESET handling 2023-05-11 23:00:26 +09:00
trace mm/tracing: rss_stat: ensure curr is false from kthread context 2026-04-18 10:33:14 +02:00
uapi netfilter: ctnetlink: use netlink policy range checks 2026-04-18 10:33:25 +02:00
vdso time64.h: Consolidated PSEC_PER_SEC definition 2021-04-06 16:32:17 -07:00
video video: of_display_timing.h: include errno.h 2022-07-12 16:35:10 +02:00
xen xen: replace xen_remap() with memremap() 2025-07-17 18:30:48 +02:00