diff options
| -rw-r--r-- | include/linux/migrate.h | 4 | ||||
| -rw-r--r-- | mm/hugetlb.c | 48 | ||||
| -rw-r--r-- | mm/migrate.c | 2 | ||||
| -rw-r--r-- | mm/userfaultfd.c | 50 |
4 files changed, 45 insertions, 59 deletions
diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 4bb4e519e3f5..7b7b73977278 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -51,6 +51,7 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page); extern int migrate_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page, int extra_count); +extern void copy_huge_page(struct page *dst, struct page *src); #else static inline void putback_movable_pages(struct list_head *l) {} @@ -77,6 +78,9 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping, return -ENOSYS; } +static inline void copy_huge_page(struct page *dst, struct page *src) +{ +} #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_COMPACTION diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 88f2178ad7c9..b14f4d1749b2 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -30,6 +30,7 @@ #include <linux/numa.h> #include <linux/llist.h> #include <linux/cma.h> +#include <linux/migrate.h> #include <asm/page.h> #include <asm/pgalloc.h> @@ -5076,20 +5077,17 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, struct page **pagep) { bool is_continue = (mode == MCOPY_ATOMIC_CONTINUE); - struct address_space *mapping; - pgoff_t idx; + struct hstate *h = hstate_vma(dst_vma); + struct address_space *mapping = dst_vma->vm_file->f_mapping; + pgoff_t idx = vma_hugecache_offset(h, dst_vma, dst_addr); unsigned long size; int vm_shared = dst_vma->vm_flags & VM_SHARED; - struct hstate *h = hstate_vma(dst_vma); pte_t _dst_pte; spinlock_t *ptl; - int ret; + int ret = -ENOMEM; struct page *page; int writable; - mapping = dst_vma->vm_file->f_mapping; - idx = vma_hugecache_offset(h, dst_vma, dst_addr); - if (is_continue) { ret = -EFAULT; page = find_lock_page(mapping, idx); @@ -5118,12 +5116,44 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, /* fallback to copy_from_user outside mmap_lock */ if (unlikely(ret)) { ret = -ENOENT; + /* Free the allocated page which may have + * consumed a reservation. + */ + restore_reserve_on_error(h, dst_vma, dst_addr, page); + put_page(page); + + /* Allocate a temporary page to hold the copied + * contents. + */ + page = alloc_huge_page_vma(h, dst_vma, dst_addr); + if (!page) { + ret = -ENOMEM; + goto out; + } *pagep = page; - /* don't free the page */ + /* Set the outparam pagep and return to the caller to + * copy the contents outside the lock. Don't free the + * page. + */ goto out; } } else { - page = *pagep; + if (vm_shared && + hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) { + put_page(*pagep); + ret = -EEXIST; + *pagep = NULL; + goto out; + } + + page = alloc_huge_page(dst_vma, dst_addr, 0); + if (IS_ERR(page)) { + ret = -ENOMEM; + *pagep = NULL; + goto out; + } + copy_huge_page(page, *pagep); + put_page(*pagep); *pagep = NULL; } diff --git a/mm/migrate.c b/mm/migrate.c index 75a15f0a2698..8fc766e52e52 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -553,7 +553,7 @@ static void __copy_gigantic_page(struct page *dst, struct page *src, } } -static void copy_huge_page(struct page *dst, struct page *src) +void copy_huge_page(struct page *dst, struct page *src) { int i; int nr_pages; diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 63a73e164d55..da5535d2d990 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -209,7 +209,6 @@ static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, unsigned long len, enum mcopy_atomic_mode mode) { - int vm_alloc_shared = dst_vma->vm_flags & VM_SHARED; int vm_shared = dst_vma->vm_flags & VM_SHARED; ssize_t err; pte_t *dst_pte; @@ -308,7 +307,6 @@ retry: mutex_unlock(&hugetlb_fault_mutex_table[hash]); i_mmap_unlock_read(mapping); - vm_alloc_shared = vm_shared; cond_resched(); @@ -346,54 +344,8 @@ retry: out_unlock: mmap_read_unlock(dst_mm); out: - if (page) { - /* - * We encountered an error and are about to free a newly - * allocated huge page. - * - * Reservation handling is very subtle, and is different for - * private and shared mappings. See the routine - * restore_reserve_on_error for details. Unfortunately, we - * can not call restore_reserve_on_error now as it would - * require holding mmap_lock. - * - * If a reservation for the page existed in the reservation - * map of a private mapping, the map was modified to indicate - * the reservation was consumed when the page was allocated. - * We clear the HPageRestoreReserve flag now so that the global - * reserve count will not be incremented in free_huge_page. - * The reservation map will still indicate the reservation - * was consumed and possibly prevent later page allocation. - * This is better than leaking a global reservation. If no - * reservation existed, it is still safe to clear - * HPageRestoreReserve as no adjustments to reservation counts - * were made during allocation. - * - * The reservation map for shared mappings indicates which - * pages have reservations. When a huge page is allocated - * for an address with a reservation, no change is made to - * the reserve map. In this case HPageRestoreReserve will be - * set to indicate that the global reservation count should be - * incremented when the page is freed. This is the desired - * behavior. However, when a huge page is allocated for an - * address without a reservation a reservation entry is added - * to the reservation map, and HPageRestoreReserve will not be - * set. When the page is freed, the global reserve count will - * NOT be incremented and it will appear as though we have - * leaked reserved page. In this case, set HPageRestoreReserve - * so that the global reserve count will be incremented to - * match the reservation map entry which was created. - * - * Note that vm_alloc_shared is based on the flags of the vma - * for which the page was originally allocated. dst_vma could - * be different or NULL on error. - */ - if (vm_alloc_shared) - SetHPageRestoreReserve(page); - else - ClearHPageRestoreReserve(page); + if (page) put_page(page); - } BUG_ON(copied < 0); BUG_ON(err > 0); BUG_ON(!copied && !err); |