diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index e279124baf2d..040fa935c4ef 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1305,8 +1305,7 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma, unsigned long vm_flags) { if (vm_flags & VM_UFFD_MINOR) { - /* FIXME: Add minor fault interception for shmem. */ - if (!is_vm_hugetlb_page(vma)) + if (!(is_vm_hugetlb_page(vma) || vma_is_shmem(vma))) return false; } @@ -1940,7 +1939,8 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx, /* report all available features and ioctls to userland */ uffdio_api.features = UFFD_API_FEATURES; #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR - uffdio_api.features &= ~UFFD_FEATURE_MINOR_HUGETLBFS; + uffdio_api.features &= + ~(UFFD_FEATURE_MINOR_HUGETLBFS | UFFD_FEATURE_MINOR_SHMEM); #endif uffdio_api.ioctls = UFFD_API_IOCTLS; ret = -EFAULT; diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index de8e4b71e3ba..bcbfcfdc9fc4 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -8,6 +8,7 @@ #include #include #include +#include /* inode in-kernel data */ @@ -122,21 +123,16 @@ static inline bool shmem_huge_enabled(struct vm_area_struct *vma) } #endif +#ifdef CONFIG_USERFAULTFD #ifdef CONFIG_SHMEM -extern int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, - struct vm_area_struct *dst_vma, - unsigned long dst_addr, - unsigned long src_addr, - struct page **pagep); -extern int shmem_mfill_zeropage_pte(struct mm_struct *dst_mm, - pmd_t *dst_pmd, - struct vm_area_struct *dst_vma, - unsigned long dst_addr); -#else -#define shmem_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, \ - src_addr, pagep) ({ BUG(); 0; }) -#define shmem_mfill_zeropage_pte(dst_mm, dst_pmd, dst_vma, \ - dst_addr) ({ BUG(); 0; }) -#endif +int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, unsigned long src_addr, + enum mcopy_atomic_mode mode, struct page **pagep); +#else /* !CONFIG_SHMEM */ +#define shmem_mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, \ + src_addr, mode, pagep) ({ BUG(); 0; }) +#endif /* CONFIG_SHMEM */ +#endif /* CONFIG_USERFAULTFD */ #endif diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index 3158e52e95ea..979219550184 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -30,7 +30,8 @@ UFFD_FEATURE_MISSING_SHMEM | \ UFFD_FEATURE_SIGBUS | \ UFFD_FEATURE_THREAD_ID | \ - UFFD_FEATURE_MINOR_HUGETLBFS) + UFFD_FEATURE_MINOR_HUGETLBFS | \ + UFFD_FEATURE_MINOR_SHMEM) #define UFFD_API_IOCTLS \ ((__u64)1 << _UFFDIO_REGISTER | \ (__u64)1 << _UFFDIO_UNREGISTER | \ @@ -191,6 +192,7 @@ struct uffdio_api { #define UFFD_FEATURE_SIGBUS (1<<7) #define UFFD_FEATURE_THREAD_ID (1<<8) #define UFFD_FEATURE_MINOR_HUGETLBFS (1<<9) +#define UFFD_FEATURE_MINOR_SHMEM (1<<10) __u64 features; __u64 ioctls; diff --git a/mm/memory.c b/mm/memory.c index 37e14b073b68..2a633f7284bb 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3899,9 +3899,11 @@ static vm_fault_t do_read_fault(struct vm_fault *vmf) * something). */ if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) { - ret = do_fault_around(vmf); - if (ret) - return ret; + if (likely(!userfaultfd_minor(vmf->vma))) { + ret = do_fault_around(vmf); + if (ret) + return ret; + } } ret = __do_fault(vmf); diff --git a/mm/shmem.c b/mm/shmem.c index 28deb63c21a7..2ef9be724928 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -77,7 +77,6 @@ static struct vfsmount *shm_mnt; #include #include #include -#include #include #include @@ -1739,8 +1738,8 @@ unlock: * vm. If we swap it in we mark it dirty since we also free the swap * entry since a page cannot live in both the swap and page cache. * - * vmf and fault_type are only supplied by shmem_fault: - * otherwise they are NULL. + * vma, vmf, and fault_type are only supplied by shmem_fault: otherwise they + * are NULL. */ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, struct page **pagep, enum sgp_type sgp, gfp_t gfp, @@ -1783,6 +1782,12 @@ repeat: return error; } + if (page && vma && userfaultfd_minor(vma)) { + unlock_page(page); + *fault_type = handle_userfault(vmf, VM_UFFD_MINOR); + return 0; + } + if (page && sgp == SGP_WRITE) mark_page_accessed(page); @@ -2296,14 +2301,13 @@ bool shmem_mapping(struct address_space *mapping) return mapping->a_ops == &shmem_aops; } -static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, - pmd_t *dst_pmd, - struct vm_area_struct *dst_vma, - unsigned long dst_addr, - unsigned long src_addr, - bool zeropage, - struct page **pagep) +#ifdef CONFIG_USERFAULTFD +int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, unsigned long src_addr, + enum mcopy_atomic_mode mode, struct page **pagep) { + bool is_continue = (mode == MCOPY_ATOMIC_CONTINUE); struct inode *inode = file_inode(dst_vma->vm_file); struct shmem_inode_info *info = SHMEM_I(inode); struct address_space *mapping = inode->i_mapping; @@ -2331,12 +2335,17 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, goto out; } - if (!*pagep) { + if (is_continue) { + ret = -EFAULT; + page = find_lock_page(mapping, pgoff); + if (!page) + goto out_unacct_blocks; + } else if (!*pagep) { page = shmem_alloc_page(gfp, info, pgoff); if (!page) goto out_unacct_blocks; - if (!zeropage) { /* mcopy_atomic */ + if (mode == MCOPY_ATOMIC_NORMAL) { /* mcopy_atomic */ page_kaddr = kmap_atomic(page); ret = copy_from_user(page_kaddr, (const void __user *)src_addr, @@ -2350,7 +2359,7 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, /* don't free the page */ return -ENOENT; } - } else { /* mfill_zeropage_atomic */ + } else { /* zeropage */ clear_highpage(page); } } else { @@ -2358,10 +2367,13 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, *pagep = NULL; } - VM_BUG_ON(PageLocked(page) || PageSwapBacked(page)); - __SetPageLocked(page); - __SetPageSwapBacked(page); - __SetPageUptodate(page); + if (!is_continue) { + VM_BUG_ON(PageSwapBacked(page)); + VM_BUG_ON(PageLocked(page)); + __SetPageLocked(page); + __SetPageSwapBacked(page); + __SetPageUptodate(page); + } ret = -EFAULT; offset = linear_page_index(dst_vma, dst_addr); @@ -2369,16 +2381,19 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, if (unlikely(offset >= max_off)) goto out_release; - ret = mem_cgroup_try_charge_delay(page, dst_mm, gfp, &memcg, false); - if (ret) - goto out_release; + /* If page wasn't already in the page cache, add it. */ + if (!is_continue) { + ret = mem_cgroup_try_charge_delay(page, dst_mm, gfp, &memcg, false); + if (ret) + goto out_release; - ret = shmem_add_to_page_cache(page, mapping, pgoff, NULL, + ret = shmem_add_to_page_cache(page, mapping, pgoff, NULL, gfp & GFP_RECLAIM_MASK); - if (ret) - goto out_release_uncharge; + if (ret) + goto out_release_uncharge; - mem_cgroup_commit_charge(page, memcg, false, false); + mem_cgroup_commit_charge(page, memcg, false, false); + } _dst_pte = mk_pte(page, dst_vma->vm_page_prot); if (dst_vma->vm_flags & VM_WRITE) @@ -2405,13 +2420,15 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, if (!pte_none(*dst_pte)) goto out_release_uncharge_unlock; - lru_cache_add_anon(page); + if (!is_continue) { + lru_cache_add_anon(page); - spin_lock_irq(&info->lock); - info->alloced++; - inode->i_blocks += BLOCKS_PER_PAGE; - shmem_recalc_inode(inode); - spin_unlock_irq(&info->lock); + spin_lock_irq(&info->lock); + info->alloced++; + inode->i_blocks += BLOCKS_PER_PAGE; + shmem_recalc_inode(inode); + spin_unlock_irq(&info->lock); + } inc_mm_counter(dst_mm, mm_counter_file(page)); page_add_file_rmap(page, false); @@ -2437,28 +2454,7 @@ out_unacct_blocks: shmem_inode_unacct_blocks(inode, 1); goto out; } - -int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, - pmd_t *dst_pmd, - struct vm_area_struct *dst_vma, - unsigned long dst_addr, - unsigned long src_addr, - struct page **pagep) -{ - return shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, - dst_addr, src_addr, false, pagep); -} - -int shmem_mfill_zeropage_pte(struct mm_struct *dst_mm, - pmd_t *dst_pmd, - struct vm_area_struct *dst_vma, - unsigned long dst_addr) -{ - struct page *page = NULL; - - return shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, - dst_addr, 0, true, &page); -} +#endif /* CONFIG_USERFAULTFD */ #ifdef CONFIG_TMPFS static const struct inode_operations shmem_symlink_inode_operations; diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index c9e870dbcfb1..5ba5aecac948 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -407,7 +407,7 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm, unsigned long dst_addr, unsigned long src_addr, struct page **page, - bool zeropage) + enum mcopy_atomic_mode mode) { ssize_t err; @@ -422,20 +422,22 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm, * and not in the radix tree. */ if (!(dst_vma->vm_flags & VM_SHARED)) { - if (!zeropage) + switch (mode) { + case MCOPY_ATOMIC_NORMAL: err = mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, src_addr, page); - else + break; + case MCOPY_ATOMIC_ZEROPAGE: err = mfill_zeropage_pte(dst_mm, dst_pmd, dst_vma, dst_addr); + break; + case MCOPY_ATOMIC_CONTINUE: + err = -EINVAL; + break; + } } else { - if (!zeropage) - err = shmem_mcopy_atomic_pte(dst_mm, dst_pmd, - dst_vma, dst_addr, - src_addr, page); - else - err = shmem_mfill_zeropage_pte(dst_mm, dst_pmd, - dst_vma, dst_addr); + err = shmem_mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, + src_addr, mode, page); } return err; @@ -454,7 +456,6 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm, unsigned long src_addr, dst_addr; long copied; struct page *page; - bool zeropage = (mcopy_mode == MCOPY_ATOMIC_ZEROPAGE); /* * Sanitize the command parameters: @@ -521,7 +522,7 @@ retry: if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma)) goto out_unlock; - if (mcopy_mode == MCOPY_ATOMIC_CONTINUE) + if (!vma_is_shmem(dst_vma) && mcopy_mode == MCOPY_ATOMIC_CONTINUE) goto out_unlock; /* @@ -569,7 +570,7 @@ retry: BUG_ON(pmd_trans_huge(*dst_pmd)); err = mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, - src_addr, &page, zeropage); + src_addr, &page, mcopy_mode); cond_resched(); if (unlikely(err == -ENOENT)) {