>From 9ad1e65a31f51a0dc687cd9d6083b9e920d2da61 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Tue, 6 Dec 2022 11:38:47 -0500 Subject: [PATCH] fixup! mm/hugetlb: Make walk_hugetlb_range() safe to pmd unshare Content-type: text/plain Signed-off-by: Peter Xu --- arch/s390/mm/gmap.c | 2 ++ fs/proc/task_mmu.c | 2 ++ include/linux/pagewalk.h | 8 +++++++- mm/hmm.c | 8 +++++++- 4 files changed, 18 insertions(+), 2 deletions(-) diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 8947451ae021..292a54c490d4 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -2643,7 +2643,9 @@ static int __s390_enable_skey_hugetlb(pte_t *pte, unsigned long addr, end = start + HPAGE_SIZE - 1; __storage_key_init_range(start, end); set_bit(PG_arch_1, &page->flags); + hugetlb_vma_unlock_read(walk->vma); cond_resched(); + hugetlb_vma_lock_read(walk->vma); return 0; } diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 89338950afd3..d7155f3bb678 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1612,7 +1612,9 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask, frame++; } + hugetlb_vma_unlock_read(walk->vma); cond_resched(); + hugetlb_vma_lock_read(walk->vma); return err; } diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h index 959f52e5867d..1f7c2011f6cb 100644 --- a/include/linux/pagewalk.h +++ b/include/linux/pagewalk.h @@ -21,7 +21,13 @@ struct mm_walk; * depth is -1 if not known, 0:PGD, 1:P4D, 2:PUD, 3:PMD. * Any folded depths (where PTRS_PER_P?D is equal to 1) * are skipped. - * @hugetlb_entry: if set, called for each hugetlb entry + * @hugetlb_entry: if set, called for each hugetlb entry. Note that + * currently the hook function is protected by hugetlb + * vma lock to make sure pte_t* and the spinlock is valid + * to access. If the hook function needs to yield the + * thread or retake the vma lock for some reason, it + * needs to properly release the vma lock manually, + * and retake it before the function returns. * @test_walk: caller specific callback function to determine whether * we walk over the current vma or not. Returning 0 means * "do page table walk over the current vma", returning diff --git a/mm/hmm.c b/mm/hmm.c index 3850fb625dda..dcd624f28bcf 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -493,8 +493,14 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask, required_fault = hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, cpu_flags); if (required_fault) { + int ret; + spin_unlock(ptl); - return hmm_vma_fault(addr, end, required_fault, walk); + hugetlb_vma_unlock_read(vma); + /* hmm_vma_fault() can retake the vma lock */ + ret = hmm_vma_fault(addr, end, required_fault, walk); + hugetlb_vma_lock_read(vma); + return ret; } pfn = pte_pfn(entry) + ((start & ~hmask) >> PAGE_SHIFT); -- 2.37.3