From 4849807114b83e1897381ed3f851632f376a0b7e Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 28 Jun 2023 17:53:08 -0400 Subject: [PATCH] mm/gup: retire follow_hugetlb_page() Now __get_user_pages() should be well prepared to handle thp completely, as long as hugetlb gup requests even without the hugetlb's special path. Time to retire follow_hugetlb_page(). Tweak misc comments to reflect reality of follow_hugetlb_page()'s removal. Link: https://lkml.kernel.org/r/20230628215310.73782-7-peterx@redhat.com Signed-off-by: Peter Xu Acked-by: David Hildenbrand Cc: Andrea Arcangeli Cc: Hugh Dickins Cc: James Houghton Cc: Jason Gunthorpe Cc: John Hubbard Cc: Kirill A . Shutemov Cc: Lorenzo Stoakes Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Mike Rapoport (IBM) Cc: Vlastimil Babka Cc: Yang Shi Signed-off-by: Andrew Morton --- fs/userfaultfd.c | 2 +- include/linux/hugetlb.h | 12 --- mm/gup.c | 19 ---- mm/hugetlb.c | 224 ---------------------------------------- 4 files changed, 1 insertion(+), 256 deletions(-) diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 7cecd49e078b..ae711f1d7a83 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -427,7 +427,7 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) * * We also don't do userfault handling during * coredumping. hugetlbfs has the special - * follow_hugetlb_page() to skip missing pages in the + * hugetlb_follow_page_mask() to skip missing pages in the * FOLL_DUMP case, anon memory also checks for FOLL_DUMP with * the no_page_table() helper in follow_page_mask(), but the * shmem_vm_ops->fault method is invoked even during diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 9f282f370d96..9bc3c2d71b71 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -133,9 +133,6 @@ int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma, unsigned long address, unsigned int flags, unsigned int *page_mask); -long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, - struct page **, unsigned long *, unsigned long *, - long, unsigned int, int *); void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long, struct page *, zap_flags_t); @@ -305,15 +302,6 @@ static inline struct page *hugetlb_follow_page_mask( BUILD_BUG(); /* should never be compiled in if !CONFIG_HUGETLB_PAGE*/ } -static inline long follow_hugetlb_page(struct mm_struct *mm, - struct vm_area_struct *vma, struct page **pages, - unsigned long *position, unsigned long *nr_pages, - long i, unsigned int flags, int *nonblocking) -{ - BUG(); - return 0; -} - static inline int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *dst_vma, diff --git a/mm/gup.c b/mm/gup.c index 59e182634ba8..2493ffa10f4b 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -819,9 +819,6 @@ static struct page *follow_page_mask(struct vm_area_struct *vma, * Call hugetlb_follow_page_mask for hugetlb vmas as it will use * special hugetlb page table walking code. This eliminates the * need to check for hugetlb entries in the general walking code. - * - * hugetlb_follow_page_mask is only for follow_page() handling here. - * Ordinary GUP uses follow_hugetlb_page for hugetlb processing. */ if (is_vm_hugetlb_page(vma)) return hugetlb_follow_page_mask(vma, address, flags, @@ -1221,22 +1218,6 @@ static long __get_user_pages(struct mm_struct *mm, ret = check_vma_flags(vma, gup_flags); if (ret) goto out; - - if (is_vm_hugetlb_page(vma)) { - i = follow_hugetlb_page(mm, vma, pages, - &start, &nr_pages, i, - gup_flags, locked); - if (!*locked) { - /* - * We've got a VM_FAULT_RETRY - * and we've lost mmap_lock. - * We must stop here. - */ - BUG_ON(gup_flags & FOLL_NOWAIT); - goto out; - } - continue; - } } retry: /* diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ab52214b5a75..e3839eee4657 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5721,7 +5721,6 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma, /* * Return whether there is a pagecache page to back given address within VMA. - * Caller follow_hugetlb_page() holds page_table_lock so we cannot lock_page. */ static bool hugetlbfs_pagecache_present(struct hstate *h, struct vm_area_struct *vma, unsigned long address) @@ -6422,37 +6421,6 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, } #endif /* CONFIG_USERFAULTFD */ -static void record_subpages(struct page *page, struct vm_area_struct *vma, - int refs, struct page **pages) -{ - int nr; - - for (nr = 0; nr < refs; nr++) { - if (likely(pages)) - pages[nr] = nth_page(page, nr); - } -} - -static inline bool __follow_hugetlb_must_fault(struct vm_area_struct *vma, - unsigned int flags, pte_t *pte, - bool *unshare) -{ - pte_t pteval = huge_ptep_get(pte); - - *unshare = false; - if (is_swap_pte(pteval)) - return true; - if (huge_pte_write(pteval)) - return false; - if (flags & FOLL_WRITE) - return true; - if (gup_must_unshare(vma, flags, pte_page(pteval))) { - *unshare = true; - return true; - } - return false; -} - struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma, unsigned long address, unsigned int flags, unsigned int *page_mask) @@ -6524,198 +6492,6 @@ struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma, return page; } -long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, - struct page **pages, unsigned long *position, - unsigned long *nr_pages, long i, unsigned int flags, - int *locked) -{ - unsigned long pfn_offset; - unsigned long vaddr = *position; - unsigned long remainder = *nr_pages; - struct hstate *h = hstate_vma(vma); - int err = -EFAULT, refs; - - while (vaddr < vma->vm_end && remainder) { - pte_t *pte; - spinlock_t *ptl = NULL; - bool unshare = false; - int absent; - struct page *page; - - /* - * If we have a pending SIGKILL, don't keep faulting pages and - * potentially allocating memory. - */ - if (fatal_signal_pending(current)) { - remainder = 0; - break; - } - - hugetlb_vma_lock_read(vma); - /* - * Some archs (sparc64, sh*) have multiple pte_ts to - * each hugepage. We have to make sure we get the - * first, for the page indexing below to work. - * - * Note that page table lock is not held when pte is null. - */ - pte = hugetlb_walk(vma, vaddr & huge_page_mask(h), - huge_page_size(h)); - if (pte) - ptl = huge_pte_lock(h, mm, pte); - absent = !pte || huge_pte_none(huge_ptep_get(pte)); - - /* - * When coredumping, it suits get_dump_page if we just return - * an error where there's an empty slot with no huge pagecache - * to back it. This way, we avoid allocating a hugepage, and - * the sparse dumpfile avoids allocating disk blocks, but its - * huge holes still show up with zeroes where they need to be. - */ - if (absent && (flags & FOLL_DUMP) && - !hugetlbfs_pagecache_present(h, vma, vaddr)) { - if (pte) - spin_unlock(ptl); - hugetlb_vma_unlock_read(vma); - remainder = 0; - break; - } - - /* - * We need call hugetlb_fault for both hugepages under migration - * (in which case hugetlb_fault waits for the migration,) and - * hwpoisoned hugepages (in which case we need to prevent the - * caller from accessing to them.) In order to do this, we use - * here is_swap_pte instead of is_hugetlb_entry_migration and - * is_hugetlb_entry_hwpoisoned. This is because it simply covers - * both cases, and because we can't follow correct pages - * directly from any kind of swap entries. - */ - if (absent || - __follow_hugetlb_must_fault(vma, flags, pte, &unshare)) { - vm_fault_t ret; - unsigned int fault_flags = 0; - - if (pte) - spin_unlock(ptl); - hugetlb_vma_unlock_read(vma); - - if (flags & FOLL_WRITE) - fault_flags |= FAULT_FLAG_WRITE; - else if (unshare) - fault_flags |= FAULT_FLAG_UNSHARE; - if (locked) { - fault_flags |= FAULT_FLAG_ALLOW_RETRY | - FAULT_FLAG_KILLABLE; - if (flags & FOLL_INTERRUPTIBLE) - fault_flags |= FAULT_FLAG_INTERRUPTIBLE; - } - if (flags & FOLL_NOWAIT) - fault_flags |= FAULT_FLAG_ALLOW_RETRY | - FAULT_FLAG_RETRY_NOWAIT; - if (flags & FOLL_TRIED) { - /* - * Note: FAULT_FLAG_ALLOW_RETRY and - * FAULT_FLAG_TRIED can co-exist - */ - fault_flags |= FAULT_FLAG_TRIED; - } - ret = hugetlb_fault(mm, vma, vaddr, fault_flags); - if (ret & VM_FAULT_ERROR) { - err = vm_fault_to_errno(ret, flags); - remainder = 0; - break; - } - if (ret & VM_FAULT_RETRY) { - if (locked && - !(fault_flags & FAULT_FLAG_RETRY_NOWAIT)) - *locked = 0; - *nr_pages = 0; - /* - * VM_FAULT_RETRY must not return an - * error, it will return zero - * instead. - * - * No need to update "position" as the - * caller will not check it after - * *nr_pages is set to 0. - */ - return i; - } - continue; - } - - pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT; - page = pte_page(huge_ptep_get(pte)); - - VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && - !PageAnonExclusive(page), page); - - /* - * If subpage information not requested, update counters - * and skip the same_page loop below. - */ - if (!pages && !pfn_offset && - (vaddr + huge_page_size(h) < vma->vm_end) && - (remainder >= pages_per_huge_page(h))) { - vaddr += huge_page_size(h); - remainder -= pages_per_huge_page(h); - i += pages_per_huge_page(h); - spin_unlock(ptl); - hugetlb_vma_unlock_read(vma); - continue; - } - - /* vaddr may not be aligned to PAGE_SIZE */ - refs = min3(pages_per_huge_page(h) - pfn_offset, remainder, - (vma->vm_end - ALIGN_DOWN(vaddr, PAGE_SIZE)) >> PAGE_SHIFT); - - if (pages) - record_subpages(nth_page(page, pfn_offset), - vma, refs, - likely(pages) ? pages + i : NULL); - - if (pages) { - /* - * try_grab_folio() should always succeed here, - * because: a) we hold the ptl lock, and b) we've just - * checked that the huge page is present in the page - * tables. If the huge page is present, then the tail - * pages must also be present. The ptl prevents the - * head page and tail pages from being rearranged in - * any way. As this is hugetlb, the pages will never - * be p2pdma or not longterm pinable. So this page - * must be available at this point, unless the page - * refcount overflowed: - */ - if (WARN_ON_ONCE(!try_grab_folio(pages[i], refs, - flags))) { - spin_unlock(ptl); - hugetlb_vma_unlock_read(vma); - remainder = 0; - err = -ENOMEM; - break; - } - } - - vaddr += (refs << PAGE_SHIFT); - remainder -= refs; - i += refs; - - spin_unlock(ptl); - hugetlb_vma_unlock_read(vma); - } - *nr_pages = remainder; - /* - * setting position is actually required only if remainder is - * not zero but it's faster not to add a "if (remainder)" - * branch. - */ - *position = vaddr; - - return i ? i : err; -} - long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags)