diff options
author | Peter Zijlstra <peterz@infradead.org> | 2020-11-26 17:21:30 +0100 |
---|---|---|
committer | Dave Hansen <dave.hansen@linux.intel.com> | 2022-12-15 19:37:27 +0100 |
commit | 1180e732c985ed3c8866d2fd9e02b619848404a0 (patch) | |
tree | d7ce6ce20c24e7c941683d8e5816337d9deb6515 | |
parent | mm: Rename pmd_read_atomic() (diff) | |
download | linux-1180e732c985ed3c8866d2fd9e02b619848404a0.tar.xz linux-1180e732c985ed3c8866d2fd9e02b619848404a0.zip |
mm/gup: Fix the lockless PMD access
On architectures where the PTE/PMD is larger than the native word size
(i386-PAE for example), READ_ONCE() can do the wrong thing. Use
pmdp_get_lockless() just like we use ptep_get_lockless().
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20221022114424.906110403%40infradead.org
-rw-r--r-- | kernel/events/core.c | 2 | ||||
-rw-r--r-- | mm/gup.c | 2 |
2 files changed, 2 insertions, 2 deletions
diff --git a/kernel/events/core.c b/kernel/events/core.c index 4ec3717003d5..b0d38424f3f7 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7306,7 +7306,7 @@ static u64 perf_get_pgtable_size(struct mm_struct *mm, unsigned long addr) return pud_leaf_size(pud); pmdp = pmd_offset_lockless(pudp, pud, addr); - pmd = READ_ONCE(*pmdp); + pmd = pmdp_get_lockless(pmdp); if (!pmd_present(pmd)) return 0; @@ -2808,7 +2808,7 @@ static int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned lo pmdp = pmd_offset_lockless(pudp, pud, addr); do { - pmd_t pmd = READ_ONCE(*pmdp); + pmd_t pmd = pmdp_get_lockless(pmdp); next = pmd_addr_end(addr, end); if (!pmd_present(pmd)) |