@@ -819,7 +819,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
* This is supposed to be the vaddr where the page is being
* faulted in, but we have no vaddr here.
*/
- struct page *page;
+ struct folio *folio;
unsigned long addr;
cond_resched();
@@ -844,48 +844,48 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
mutex_lock(&hugetlb_fault_mutex_table[hash]);
/* See if already present in mapping to avoid alloc/free */
- page = find_get_page(mapping, index);
- if (page) {
- put_page(page);
+ folio = filemap_get_folio(mapping, index);
+ if (folio) {
+ folio_put(folio);
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
hugetlb_drop_vma_policy(&pseudo_vma);
continue;
}
/*
- * Allocate page without setting the avoid_reserve argument.
+ * Allocate folio without setting the avoid_reserve argument.
* There certainly are no reserves associated with the
* pseudo_vma. However, there could be shared mappings with
* reserves for the file at the inode level. If we fallocate
- * pages in these areas, we need to consume the reserves
+ * folios in these areas, we need to consume the reserves
* to keep reservation accounting consistent.
*/
- page = alloc_huge_page(&pseudo_vma, addr, 0);
+ folio = alloc_hugetlb_folio(&pseudo_vma, addr, 0);
hugetlb_drop_vma_policy(&pseudo_vma);
- if (IS_ERR(page)) {
+ if (IS_ERR(folio)) {
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
- error = PTR_ERR(page);
+ error = PTR_ERR(folio);
goto out;
}
- clear_huge_page(page, addr, pages_per_huge_page(h));
- __SetPageUptodate(page);
- error = hugetlb_add_to_page_cache(page, mapping, index);
+ clear_huge_page(&folio->page, addr, pages_per_huge_page(h));
+ __folio_mark_uptodate(folio);
+ error = hugetlb_add_to_page_cache(&folio->page, mapping, index);
if (unlikely(error)) {
- restore_reserve_on_error(h, &pseudo_vma, addr, page);
- put_page(page);
+ restore_reserve_on_error(h, &pseudo_vma, addr, &folio->page);
+ folio_put(folio);
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
goto out;
}
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
- SetHPageMigratable(page);
+ folio_set_hugetlb_migratable(folio);
/*
- * unlock_page because locked by hugetlb_add_to_page_cache()
- * put_page() due to reference from alloc_huge_page()
+ * folio_unlock because locked by hugetlb_add_to_page_cache()
+ * folio_put() due to reference from alloc_hugetlb_folio()
*/
- unlock_page(page);
- put_page(page);
+ folio_unlock(folio);
+ folio_put(folio);
}
if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size)
@@ -716,11 +716,11 @@ struct huge_bootmem_page {
};
int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list);
-struct page *alloc_huge_page(struct vm_area_struct *vma,
+struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
unsigned long addr, int avoid_reserve);
struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid,
nodemask_t *nmask, gfp_t gfp_mask);
-struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
+struct folio *alloc_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma,
unsigned long address);
int hugetlb_add_to_page_cache(struct page *page, struct address_space *mapping,
pgoff_t idx);
@@ -1032,7 +1032,7 @@ static inline int isolate_or_dissolve_huge_page(struct page *page,
return -ENOMEM;
}
-static inline struct page *alloc_huge_page(struct vm_area_struct *vma,
+static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
unsigned long addr,
int avoid_reserve)
{
@@ -1046,7 +1046,7 @@ alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid,
return NULL;
}
-static inline struct page *alloc_huge_page_vma(struct hstate *h,
+static inline struct folio *alloc_hugetlb_folio_vma(struct hstate *h,
struct vm_area_struct *vma,
unsigned long address)
{
@@ -2493,7 +2493,7 @@ struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid,
}
/* mempolicy aware migration callback */
-struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
+struct folio *alloc_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma,
unsigned long address)
{
struct mempolicy *mpol;
@@ -2507,7 +2507,7 @@ struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
folio = alloc_hugetlb_folio_nodemask(h, node, nodemask, gfp_mask);
mpol_cond_put(mpol);
- return &folio->page;
+ return folio;
}
/*
@@ -2798,14 +2798,14 @@ static long vma_del_reservation(struct hstate *h,
/*
* This routine is called to restore reservation information on error paths.
- * It should ONLY be called for pages allocated via alloc_huge_page(), and
- * the hugetlb mutex should remain held when calling this routine.
+ * It should ONLY be called for folios allocated via alloc_hugetlb_folio(),
+ * and the hugetlb mutex should remain held when calling this routine.
*
* It handles two specific cases:
* 1) A reservation was in place and the page consumed the reservation.
* HPageRestoreReserve is set in the page.
* 2) No reservation was in place for the page, so HPageRestoreReserve is
- * not set. However, alloc_huge_page always updates the reserve map.
+ * not set. However, alloc_hugetlb_folio always updates the reserve map.
*
* In case 1, free_huge_page later in the error path will increment the
* global reserve count. But, free_huge_page does not have enough context
@@ -2814,7 +2814,7 @@ static long vma_del_reservation(struct hstate *h,
* reserve count adjustments to be made by free_huge_page. Make sure the
* reserve map indicates there is a reservation present.
*
- * In case 2, simply undo reserve map modifications done by alloc_huge_page.
+ * In case 2, simply undo reserve map modifications done by alloc_hugetlb_folio.
*/
void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma,
unsigned long address, struct page *page)
@@ -2844,8 +2844,8 @@ void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma,
if (!rc) {
/*
* This indicates there is an entry in the reserve map
- * not added by alloc_huge_page. We know it was added
- * before the alloc_huge_page call, otherwise
+ * not added by alloc_hugetlb_folio. We know it was added
+ * before the alloc_hugetlb_folio call, otherwise
* hugetlb_restore_reserve would be set on the folio.
* Remove the entry so that a subsequent allocation
* does not consume a reservation.
@@ -3014,7 +3014,7 @@ int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list)
return ret;
}
-struct page *alloc_huge_page(struct vm_area_struct *vma,
+struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
unsigned long addr, int avoid_reserve)
{
struct hugepage_subpool *spool = subpool_vma(vma);
@@ -3130,7 +3130,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h),
pages_per_huge_page(h), folio);
}
- return &folio->page;
+ return folio;
out_uncharge_cgroup:
hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg);
@@ -5080,34 +5080,34 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
} else if (page_try_dup_anon_rmap(ptepage, true,
src_vma)) {
pte_t src_pte_old = entry;
- struct page *new;
+ struct folio *new_folio;
spin_unlock(src_ptl);
spin_unlock(dst_ptl);
/* Do not use reserve as it's private owned */
- new = alloc_huge_page(dst_vma, addr, 1);
- if (IS_ERR(new)) {
+ new_folio = alloc_hugetlb_folio(dst_vma, addr, 1);
+ if (IS_ERR(new_folio)) {
put_page(ptepage);
- ret = PTR_ERR(new);
+ ret = PTR_ERR(new_folio);
break;
}
- copy_user_huge_page(new, ptepage, addr, dst_vma,
+ copy_user_huge_page(&new_folio->page, ptepage, addr, dst_vma,
npages);
put_page(ptepage);
- /* Install the new huge page if src pte stable */
+ /* Install the new hugetlb folio if src pte stable */
dst_ptl = huge_pte_lock(h, dst, dst_pte);
src_ptl = huge_pte_lockptr(h, src, src_pte);
spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
entry = huge_ptep_get(src_pte);
if (!pte_same(src_pte_old, entry)) {
restore_reserve_on_error(h, dst_vma, addr,
- new);
- put_page(new);
+ &new_folio->page);
+ folio_put(new_folio);
/* huge_ptep of dst_pte won't change as in child */
goto again;
}
- hugetlb_install_folio(dst_vma, dst_pte, addr, page_folio(new));
+ hugetlb_install_folio(dst_vma, dst_pte, addr, new_folio);
spin_unlock(src_ptl);
spin_unlock(dst_ptl);
continue;
@@ -5478,8 +5478,8 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma,
const bool unshare = flags & FAULT_FLAG_UNSHARE;
pte_t pte;
struct hstate *h = hstate_vma(vma);
- struct page *old_page, *new_page;
- struct folio *new_folio = NULL;
+ struct page *old_page;
+ struct folio *new_folio;
int outside_reserve = 0;
vm_fault_t ret = 0;
unsigned long haddr = address & huge_page_mask(h);
@@ -5540,9 +5540,9 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma,
* be acquired again before returning to the caller, as expected.
*/
spin_unlock(ptl);
- new_page = alloc_huge_page(vma, haddr, outside_reserve);
+ new_folio = alloc_hugetlb_folio(vma, haddr, outside_reserve);
- if (IS_ERR(new_page)) {
+ if (IS_ERR(new_folio)) {
/*
* If a process owning a MAP_PRIVATE mapping fails to COW,
* it is due to references held by a child and an insufficient
@@ -5587,13 +5587,9 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma,
return 0;
}
- ret = vmf_error(PTR_ERR(new_page));
+ ret = vmf_error(PTR_ERR(new_folio));
goto out_release_old;
}
-
- if (new_page)
- new_folio = page_folio(new_page);
-
/*
* When the original hugepage is shared one, it does not have
* anon_vma prepared.
@@ -5627,7 +5623,7 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma,
make_huge_pte(vma, &new_folio->page, !unshare));
folio_set_hugetlb_migratable(new_folio);
/* Make the old page be freed below */
- new_page = old_page;
+ new_folio = page_folio(old_page);
}
spin_unlock(ptl);
mmu_notifier_invalidate_range_end(&range);
@@ -5636,7 +5632,7 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma,
* No restore in case of successful pagetable update (Break COW or
* unshare)
*/
- if (new_page != old_page)
+ if (new_folio != page_folio(old_page))
restore_reserve_on_error(h, vma, haddr, &new_folio->page);
folio_put(new_folio);
out_release_old:
@@ -5759,8 +5755,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
vm_fault_t ret = VM_FAULT_SIGBUS;
int anon_rmap = 0;
unsigned long size;
- struct page *page;
- struct folio *folio = NULL;
+ struct folio *folio;
pte_t new_pte;
spinlock_t *ptl;
unsigned long haddr = address & huge_page_mask(h);
@@ -5784,8 +5779,8 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
* before we get page_table_lock.
*/
new_page = false;
- page = find_lock_page(mapping, idx);
- if (!page) {
+ folio = filemap_lock_folio(mapping, idx);
+ if (!folio) {
size = i_size_read(mapping->host) >> huge_page_shift(h);
if (idx >= size)
goto out;
@@ -5818,8 +5813,8 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
VM_UFFD_MISSING);
}
- page = alloc_huge_page(vma, haddr, 0);
- if (IS_ERR(page)) {
+ folio = alloc_hugetlb_folio(vma, haddr, 0);
+ if (IS_ERR(folio)) {
/*
* Returning error will result in faulting task being
* sent SIGBUS. The hugetlb fault mutex prevents two
@@ -5833,15 +5828,11 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
* sure there really is no pte entry.
*/
if (hugetlb_pte_stable(h, mm, ptep, old_pte))
- ret = vmf_error(PTR_ERR(page));
+ ret = vmf_error(PTR_ERR(folio));
else
ret = 0;
goto out;
}
-
- if (page)
- folio = page_folio(page);
-
clear_huge_page(&folio->page, address, pages_per_huge_page(h));
__folio_mark_uptodate(folio);
new_page = true;
@@ -5870,7 +5861,6 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
anon_rmap = 1;
}
} else {
- folio = page_folio(page);
/*
* If memory error occurs between mmap() and fault, some process
* don't have hwpoisoned swap entry for errored virtual address.
@@ -6185,15 +6175,14 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
pte_t _dst_pte;
spinlock_t *ptl;
int ret = -ENOMEM;
- struct page *page;
- struct folio *folio = NULL;
+ struct folio *folio;
int writable;
bool page_in_pagecache = false;
if (is_continue) {
ret = -EFAULT;
- page = find_lock_page(mapping, idx);
- if (!page)
+ folio = filemap_lock_folio(mapping, idx);
+ if (!folio)
goto out;
page_in_pagecache = true;
} else if (!*pagep) {
@@ -6206,34 +6195,34 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
goto out;
}
- page = alloc_huge_page(dst_vma, dst_addr, 0);
- if (IS_ERR(page)) {
+ folio = alloc_hugetlb_folio(dst_vma, dst_addr, 0);
+ if (IS_ERR(folio)) {
ret = -ENOMEM;
goto out;
}
- ret = copy_huge_page_from_user(page,
+ ret = copy_huge_page_from_user(&folio->page,
(const void __user *) src_addr,
pages_per_huge_page(h), false);
/* fallback to copy_from_user outside mmap_lock */
if (unlikely(ret)) {
ret = -ENOENT;
- /* Free the allocated page which may have
+ /* Free the allocated folio which may have
* consumed a reservation.
*/
- restore_reserve_on_error(h, dst_vma, dst_addr, page);
- put_page(page);
+ restore_reserve_on_error(h, dst_vma, dst_addr, &folio->page);
+ folio_put(folio);
- /* Allocate a temporary page to hold the copied
+ /* Allocate a temporary folio to hold the copied
* contents.
*/
- page = alloc_huge_page_vma(h, dst_vma, dst_addr);
- if (!page) {
+ folio = alloc_hugetlb_folio_vma(h, dst_vma, dst_addr);
+ if (!folio) {
ret = -ENOMEM;
goto out;
}
- *pagep = page;
+ *pagep = &folio->page;
/* Set the outparam pagep and return to the caller to
* copy the contents outside the lock. Don't free the
* page.
@@ -6249,22 +6238,18 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
goto out;
}
- page = alloc_huge_page(dst_vma, dst_addr, 0);
- if (IS_ERR(page)) {
+ folio = alloc_hugetlb_folio(dst_vma, dst_addr, 0);
+ if (IS_ERR(folio)) {
put_page(*pagep);
ret = -ENOMEM;
*pagep = NULL;
goto out;
}
- copy_user_huge_page(page, *pagep, dst_addr, dst_vma,
+ copy_user_huge_page(&folio->page, *pagep, dst_addr, dst_vma,
pages_per_huge_page(h));
put_page(*pagep);
*pagep = NULL;
}
-
- if (page)
- folio = page_folio(page);
-
/*
* The memory barrier inside __folio_mark_uptodate makes sure that
* preceding stores to the page contents become visible before
@@ -6887,7 +6872,7 @@ bool hugetlb_reserve_pages(struct inode *inode,
/*
* pages in this range were added to the reserve
* map between region_chg and region_add. This
- * indicates a race with alloc_huge_page. Adjust
+ * indicates a race with alloc_hugetlb_folio. Adjust
* the subpool and reserve counts modified above
* based on the difference.
*/
@@ -1218,9 +1218,11 @@ static struct page *new_page(struct page *page, unsigned long start)
break;
}
- if (folio_test_hugetlb(src))
- return alloc_huge_page_vma(page_hstate(&src->page),
+ if (folio_test_hugetlb(src)) {
+ dst = alloc_hugetlb_folio_vma(folio_hstate(src),
vma, address);
+ return &dst->page;
+ }
if (folio_test_large(src))
gfp = GFP_TRANSHUGE;
Change alloc_huge_page() to alloc_hugetlb_folio() by changing all callers to handle the now folio return type of the function. In this conversion, alloc_huge_page_vma() is also changed to alloc_hugetlb_folio_vma(). Many additions of the use of &folio->page are cleaned up in subsequent patches. Signed-off-by: Sidhartha Kumar <sidhartha.kumar@oracle.com> --- fs/hugetlbfs/inode.c | 38 +++++++------- include/linux/hugetlb.h | 8 +-- mm/hugetlb.c | 113 +++++++++++++++++----------------------- mm/mempolicy.c | 6 ++- 4 files changed, 76 insertions(+), 89 deletions(-)