aboutsummaryrefslogtreecommitdiffstats
path: root/mm/shmem.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-05-26 12:32:41 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2022-05-26 12:32:41 -0700
commit98931dd95fd489fcbfa97da563505a6f071d7c77 (patch)
tree44683fc4a92efa614acdca2742a7ff19d26da1e3 /mm/shmem.c
parentMerge tag 'kbuild-v5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/masahiroy/linux-kbuild (diff)
parentmm: kfence: use PAGE_ALIGNED helper (diff)
downloadlinux-dev-98931dd95fd489fcbfa97da563505a6f071d7c77.tar.xz
linux-dev-98931dd95fd489fcbfa97da563505a6f071d7c77.zip
Merge tag 'mm-stable-2022-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull MM updates from Andrew Morton: "Almost all of MM here. A few things are still getting finished off, reviewed, etc. - Yang Shi has improved the behaviour of khugepaged collapsing of readonly file-backed transparent hugepages. - Johannes Weiner has arranged for zswap memory use to be tracked and managed on a per-cgroup basis. - Munchun Song adds a /proc knob ("hugetlb_optimize_vmemmap") for runtime enablement of the recent huge page vmemmap optimization feature. - Baolin Wang contributes a series to fix some issues around hugetlb pagetable invalidation. - Zhenwei Pi has fixed some interactions between hwpoisoned pages and virtualization. - Tong Tiangen has enabled the use of the presently x86-only page_table_check debugging feature on arm64 and riscv. - David Vernet has done some fixup work on the memcg selftests. - Peter Xu has taught userfaultfd to handle write protection faults against shmem- and hugetlbfs-backed files. - More DAMON development from SeongJae Park - adding online tuning of the feature and support for monitoring of fixed virtual address ranges. Also easier discovery of which monitoring operations are available. - Nadav Amit has done some optimization of TLB flushing during mprotect(). - Neil Brown continues to labor away at improving our swap-over-NFS support. - David Hildenbrand has some fixes to anon page COWing versus get_user_pages(). - Peng Liu fixed some errors in the core hugetlb code. - Joao Martins has reduced the amount of memory consumed by device-dax's compound devmaps. - Some cleanups of the arch-specific pagemap code from Anshuman Khandual. - Muchun Song has found and fixed some errors in the TLB flushing of transparent hugepages. - Roman Gushchin has done more work on the memcg selftests. ... and, of course, many smaller fixes and cleanups. Notably, the customary million cleanup serieses from Miaohe Lin" * tag 'mm-stable-2022-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (381 commits) mm: kfence: use PAGE_ALIGNED helper selftests: vm: add the "settings" file with timeout variable selftests: vm: add "test_hmm.sh" to TEST_FILES selftests: vm: check numa_available() before operating "merge_across_nodes" in ksm_tests selftests: vm: add migration to the .gitignore selftests/vm/pkeys: fix typo in comment ksm: fix typo in comment selftests: vm: add process_mrelease tests Revert "mm/vmscan: never demote for memcg reclaim" mm/kfence: print disabling or re-enabling message include/trace/events/percpu.h: cleanup for "percpu: improve percpu_alloc_percpu event trace" include/trace/events/mmflags.h: cleanup for "tracing: incorrect gfp_t conversion" mm: fix a potential infinite loop in start_isolate_page_range() MAINTAINERS: add Muchun as co-maintainer for HugeTLB zram: fix Kconfig dependency warning mm/shmem: fix shmem folio swapoff hang cgroup: fix an error handling path in alloc_pagecache_max_30M() mm: damon: use HPAGE_PMD_SIZE tracing: incorrect isolate_mote_t cast in mm_vmscan_lru_isolate nodemask.h: fix compilation error with GCC12 ...
Diffstat (limited to 'mm/shmem.c')
-rw-r--r--mm/shmem.c353
1 files changed, 168 insertions, 185 deletions
diff --git a/mm/shmem.c b/mm/shmem.c
index f3e8de8ff75c..da30c769b376 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -34,10 +34,10 @@
#include <linux/export.h>
#include <linux/swap.h>
#include <linux/uio.h>
-#include <linux/khugepaged.h>
#include <linux/hugetlb.h>
#include <linux/fs_parser.h>
#include <linux/swapfile.h>
+#include "swap.h"
static struct vfsmount *shm_mnt;
@@ -134,8 +134,8 @@ static unsigned long shmem_default_max_inodes(void)
}
#endif
-static int shmem_swapin_page(struct inode *inode, pgoff_t index,
- struct page **pagep, enum sgp_type sgp,
+static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
+ struct folio **foliop, enum sgp_type sgp,
gfp_t gfp, struct vm_area_struct *vma,
vm_fault_t *fault_type);
static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
@@ -553,7 +553,7 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
LIST_HEAD(to_remove);
struct inode *inode;
struct shmem_inode_info *info;
- struct page *page;
+ struct folio *folio;
unsigned long batch = sc ? sc->nr_to_scan : 128;
int split = 0;
@@ -597,6 +597,7 @@ next:
list_for_each_safe(pos, next, &list) {
int ret;
+ pgoff_t index;
info = list_entry(pos, struct shmem_inode_info, shrinklist);
inode = &info->vfs_inode;
@@ -604,14 +605,14 @@ next:
if (nr_to_split && split >= nr_to_split)
goto move_back;
- page = find_get_page(inode->i_mapping,
- (inode->i_size & HPAGE_PMD_MASK) >> PAGE_SHIFT);
- if (!page)
+ index = (inode->i_size & HPAGE_PMD_MASK) >> PAGE_SHIFT;
+ folio = filemap_get_folio(inode->i_mapping, index);
+ if (!folio)
goto drop;
/* No huge page at the end of the file: nothing to split */
- if (!PageTransHuge(page)) {
- put_page(page);
+ if (!folio_test_large(folio)) {
+ folio_put(folio);
goto drop;
}
@@ -622,14 +623,14 @@ next:
* Waiting for the lock may lead to deadlock in the
* reclaim path.
*/
- if (!trylock_page(page)) {
- put_page(page);
+ if (!folio_trylock(folio)) {
+ folio_put(folio);
goto move_back;
}
- ret = split_huge_page(page);
- unlock_page(page);
- put_page(page);
+ ret = split_huge_page(&folio->page);
+ folio_unlock(folio);
+ folio_put(folio);
/* If split failed move the inode on the list back to shrinklist */
if (ret)
@@ -694,36 +695,35 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
/*
* Like add_to_page_cache_locked, but error if expected item has gone.
*/
-static int shmem_add_to_page_cache(struct page *page,
+static int shmem_add_to_page_cache(struct folio *folio,
struct address_space *mapping,
pgoff_t index, void *expected, gfp_t gfp,
struct mm_struct *charge_mm)
{
- XA_STATE_ORDER(xas, &mapping->i_pages, index, compound_order(page));
- unsigned long nr = compound_nr(page);
+ XA_STATE_ORDER(xas, &mapping->i_pages, index, folio_order(folio));
+ long nr = folio_nr_pages(folio);
int error;
- VM_BUG_ON_PAGE(PageTail(page), page);
- VM_BUG_ON_PAGE(index != round_down(index, nr), page);
- VM_BUG_ON_PAGE(!PageLocked(page), page);
- VM_BUG_ON_PAGE(!PageSwapBacked(page), page);
- VM_BUG_ON(expected && PageTransHuge(page));
+ VM_BUG_ON_FOLIO(index != round_down(index, nr), folio);
+ VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
+ VM_BUG_ON_FOLIO(!folio_test_swapbacked(folio), folio);
+ VM_BUG_ON(expected && folio_test_large(folio));
- page_ref_add(page, nr);
- page->mapping = mapping;
- page->index = index;
+ folio_ref_add(folio, nr);
+ folio->mapping = mapping;
+ folio->index = index;
- if (!PageSwapCache(page)) {
- error = mem_cgroup_charge(page_folio(page), charge_mm, gfp);
+ if (!folio_test_swapcache(folio)) {
+ error = mem_cgroup_charge(folio, charge_mm, gfp);
if (error) {
- if (PageTransHuge(page)) {
+ if (folio_test_pmd_mappable(folio)) {
count_vm_event(THP_FILE_FALLBACK);
count_vm_event(THP_FILE_FALLBACK_CHARGE);
}
goto error;
}
}
- cgroup_throttle_swaprate(page, gfp);
+ folio_throttle_swaprate(folio, gfp);
do {
xas_lock_irq(&xas);
@@ -735,16 +735,16 @@ static int shmem_add_to_page_cache(struct page *page,
xas_set_err(&xas, -EEXIST);
goto unlock;
}
- xas_store(&xas, page);
+ xas_store(&xas, folio);
if (xas_error(&xas))
goto unlock;
- if (PageTransHuge(page)) {
+ if (folio_test_pmd_mappable(folio)) {
count_vm_event(THP_FILE_ALLOC);
- __mod_lruvec_page_state(page, NR_SHMEM_THPS, nr);
+ __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, nr);
}
mapping->nrpages += nr;
- __mod_lruvec_page_state(page, NR_FILE_PAGES, nr);
- __mod_lruvec_page_state(page, NR_SHMEM, nr);
+ __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr);
+ __lruvec_stat_mod_folio(folio, NR_SHMEM, nr);
unlock:
xas_unlock_irq(&xas);
} while (xas_nomem(&xas, gfp));
@@ -756,8 +756,8 @@ unlock:
return 0;
error:
- page->mapping = NULL;
- page_ref_sub(page, nr);
+ folio->mapping = NULL;
+ folio_ref_sub(folio, nr);
return error;
}
@@ -1158,69 +1158,63 @@ static void shmem_evict_inode(struct inode *inode)
}
static int shmem_find_swap_entries(struct address_space *mapping,
- pgoff_t start, unsigned int nr_entries,
- struct page **entries, pgoff_t *indices,
- unsigned int type)
+ pgoff_t start, struct folio_batch *fbatch,
+ pgoff_t *indices, unsigned int type)
{
XA_STATE(xas, &mapping->i_pages, start);
- struct page *page;
+ struct folio *folio;
swp_entry_t entry;
- unsigned int ret = 0;
-
- if (!nr_entries)
- return 0;
rcu_read_lock();
- xas_for_each(&xas, page, ULONG_MAX) {
- if (xas_retry(&xas, page))
+ xas_for_each(&xas, folio, ULONG_MAX) {
+ if (xas_retry(&xas, folio))
continue;
- if (!xa_is_value(page))
+ if (!xa_is_value(folio))
continue;
- entry = radix_to_swp_entry(page);
+ entry = radix_to_swp_entry(folio);
if (swp_type(entry) != type)
continue;
- indices[ret] = xas.xa_index;
- entries[ret] = page;
+ indices[folio_batch_count(fbatch)] = xas.xa_index;
+ if (!folio_batch_add(fbatch, folio))
+ break;
if (need_resched()) {
xas_pause(&xas);
cond_resched_rcu();
}
- if (++ret == nr_entries)
- break;
}
rcu_read_unlock();
- return ret;
+ return xas.xa_index;
}
/*
* Move the swapped pages for an inode to page cache. Returns the count
* of pages swapped in, or the error in case of failure.
*/
-static int shmem_unuse_swap_entries(struct inode *inode, struct pagevec pvec,
- pgoff_t *indices)
+static int shmem_unuse_swap_entries(struct inode *inode,
+ struct folio_batch *fbatch, pgoff_t *indices)
{
int i = 0;
int ret = 0;
int error = 0;
struct address_space *mapping = inode->i_mapping;
- for (i = 0; i < pvec.nr; i++) {
- struct page *page = pvec.pages[i];
+ for (i = 0; i < folio_batch_count(fbatch); i++) {
+ struct folio *folio = fbatch->folios[i];
- if (!xa_is_value(page))
+ if (!xa_is_value(folio))
continue;
- error = shmem_swapin_page(inode, indices[i],
- &page, SGP_CACHE,
+ error = shmem_swapin_folio(inode, indices[i],
+ &folio, SGP_CACHE,
mapping_gfp_mask(mapping),
NULL, NULL);
if (error == 0) {
- unlock_page(page);
- put_page(page);
+ folio_unlock(folio);
+ folio_put(folio);
ret++;
}
if (error == -ENOMEM)
@@ -1237,26 +1231,23 @@ static int shmem_unuse_inode(struct inode *inode, unsigned int type)
{
struct address_space *mapping = inode->i_mapping;
pgoff_t start = 0;
- struct pagevec pvec;
+ struct folio_batch fbatch;
pgoff_t indices[PAGEVEC_SIZE];
int ret = 0;
- pagevec_init(&pvec);
do {
- unsigned int nr_entries = PAGEVEC_SIZE;
-
- pvec.nr = shmem_find_swap_entries(mapping, start, nr_entries,
- pvec.pages, indices, type);
- if (pvec.nr == 0) {
+ folio_batch_init(&fbatch);
+ shmem_find_swap_entries(mapping, start, &fbatch, indices, type);
+ if (folio_batch_count(&fbatch) == 0) {
ret = 0;
break;
}
- ret = shmem_unuse_swap_entries(inode, pvec, indices);
+ ret = shmem_unuse_swap_entries(inode, &fbatch, indices);
if (ret < 0)
break;
- start = indices[pvec.nr - 1];
+ start = indices[folio_batch_count(&fbatch) - 1];
} while (true);
return ret;
@@ -1312,6 +1303,7 @@ int shmem_unuse(unsigned int type)
*/
static int shmem_writepage(struct page *page, struct writeback_control *wbc)
{
+ struct folio *folio = page_folio(page);
struct shmem_inode_info *info;
struct address_space *mapping;
struct inode *inode;
@@ -1385,7 +1377,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
SetPageUptodate(page);
}
- swap = get_swap_page(page);
+ swap = folio_alloc_swap(folio);
if (!swap.val)
goto redirty;
@@ -1521,13 +1513,13 @@ static gfp_t limit_gfp_mask(gfp_t huge_gfp, gfp_t limit_gfp)
return result;
}
-static struct page *shmem_alloc_hugepage(gfp_t gfp,
+static struct folio *shmem_alloc_hugefolio(gfp_t gfp,
struct shmem_inode_info *info, pgoff_t index)
{
struct vm_area_struct pvma;
struct address_space *mapping = info->vfs_inode.i_mapping;
pgoff_t hindex;
- struct page *page;
+ struct folio *folio;
hindex = round_down(index, HPAGE_PMD_NR);
if (xa_find(&mapping->i_pages, &hindex, hindex + HPAGE_PMD_NR - 1,
@@ -1535,34 +1527,37 @@ static struct page *shmem_alloc_hugepage(gfp_t gfp,
return NULL;
shmem_pseudo_vma_init(&pvma, info, hindex);
- page = alloc_pages_vma(gfp, HPAGE_PMD_ORDER, &pvma, 0, true);
+ folio = vma_alloc_folio(gfp, HPAGE_PMD_ORDER, &pvma, 0, true);
shmem_pseudo_vma_destroy(&pvma);
- if (page)
- prep_transhuge_page(page);
- else
+ if (!folio)
count_vm_event(THP_FILE_FALLBACK);
- return page;
+ return folio;
}
-static struct page *shmem_alloc_page(gfp_t gfp,
+static struct folio *shmem_alloc_folio(gfp_t gfp,
struct shmem_inode_info *info, pgoff_t index)
{
struct vm_area_struct pvma;
- struct page *page;
+ struct folio *folio;
shmem_pseudo_vma_init(&pvma, info, index);
- page = alloc_page_vma(gfp, &pvma, 0);
+ folio = vma_alloc_folio(gfp, 0, &pvma, 0, false);
shmem_pseudo_vma_destroy(&pvma);
- return page;
+ return folio;
+}
+
+static struct page *shmem_alloc_page(gfp_t gfp,
+ struct shmem_inode_info *info, pgoff_t index)
+{
+ return &shmem_alloc_folio(gfp, info, index)->page;
}
-static struct page *shmem_alloc_and_acct_page(gfp_t gfp,
- struct inode *inode,
+static struct folio *shmem_alloc_and_acct_folio(gfp_t gfp, struct inode *inode,
pgoff_t index, bool huge)
{
struct shmem_inode_info *info = SHMEM_I(inode);
- struct page *page;
+ struct folio *folio;
int nr;
int err = -ENOSPC;
@@ -1574,13 +1569,13 @@ static struct page *shmem_alloc_and_acct_page(gfp_t gfp,
goto failed;
if (huge)
- page = shmem_alloc_hugepage(gfp, info, index);
+ folio = shmem_alloc_hugefolio(gfp, info, index);
else
- page = shmem_alloc_page(gfp, info, index);
- if (page) {
- __SetPageLocked(page);
- __SetPageSwapBacked(page);
- return page;
+ folio = shmem_alloc_folio(gfp, info, index);
+ if (folio) {
+ __folio_set_locked(folio);
+ __folio_set_swapbacked(folio);
+ return folio;
}
err = -ENOMEM;
@@ -1601,9 +1596,9 @@ failed:
* NUMA mempolicy, and applied also to anonymous pages in do_swap_page();
* but for now it is a simple matter of zone.
*/
-static bool shmem_should_replace_page(struct page *page, gfp_t gfp)
+static bool shmem_should_replace_folio(struct folio *folio, gfp_t gfp)
{
- return page_zonenum(page) > gfp_zone(gfp);
+ return folio_zonenum(folio) > gfp_zone(gfp);
}
static int shmem_replace_page(struct page **pagep, gfp_t gfp,
@@ -1682,8 +1677,8 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
* Returns 0 and the page in pagep if success. On failure, returns the
* error code and NULL in *pagep.
*/
-static int shmem_swapin_page(struct inode *inode, pgoff_t index,
- struct page **pagep, enum sgp_type sgp,
+static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
+ struct folio **foliop, enum sgp_type sgp,
gfp_t gfp, struct vm_area_struct *vma,
vm_fault_t *fault_type)
{
@@ -1691,12 +1686,13 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index,
struct shmem_inode_info *info = SHMEM_I(inode);
struct mm_struct *charge_mm = vma ? vma->vm_mm : NULL;
struct page *page;
+ struct folio *folio = NULL;
swp_entry_t swap;
int error;
- VM_BUG_ON(!*pagep || !xa_is_value(*pagep));
- swap = radix_to_swp_entry(*pagep);
- *pagep = NULL;
+ VM_BUG_ON(!*foliop || !xa_is_value(*foliop));
+ swap = radix_to_swp_entry(*foliop);
+ *foliop = NULL;
/* Look it up and read it in.. */
page = lookup_swap_cache(swap, NULL, 0);
@@ -1714,33 +1710,35 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index,
goto failed;
}
}
+ folio = page_folio(page);
/* We have to do this with page locked to prevent races */
- lock_page(page);
- if (!PageSwapCache(page) || page_private(page) != swap.val ||
+ folio_lock(folio);
+ if (!folio_test_swapcache(folio) ||
+ folio_swap_entry(folio).val != swap.val ||
!shmem_confirm_swap(mapping, index, swap)) {
error = -EEXIST;
goto unlock;
}
- if (!PageUptodate(page)) {
+ if (!folio_test_uptodate(folio)) {
error = -EIO;
goto failed;
}
- wait_on_page_writeback(page);
+ folio_wait_writeback(folio);
/*
* Some architectures may have to restore extra metadata to the
- * physical page after reading from swap.
+ * folio after reading from swap.
*/
- arch_swap_restore(swap, page);
+ arch_swap_restore(swap, folio);
- if (shmem_should_replace_page(page, gfp)) {
+ if (shmem_should_replace_folio(folio, gfp)) {
error = shmem_replace_page(&page, gfp, info, index);
if (error)
goto failed;
}
- error = shmem_add_to_page_cache(page, mapping, index,
+ error = shmem_add_to_page_cache(folio, mapping, index,
swp_to_radix_entry(swap), gfp,
charge_mm);
if (error)
@@ -1752,21 +1750,21 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index,
spin_unlock_irq(&info->lock);
if (sgp == SGP_WRITE)
- mark_page_accessed(page);
+ folio_mark_accessed(folio);
- delete_from_swap_cache(page);
- set_page_dirty(page);
+ delete_from_swap_cache(&folio->page);
+ folio_mark_dirty(folio);
swap_free(swap);
- *pagep = page;
+ *foliop = folio;
return 0;
failed:
if (!shmem_confirm_swap(mapping, index, swap))
error = -EEXIST;
unlock:
- if (page) {
- unlock_page(page);
- put_page(page);
+ if (folio) {
+ folio_unlock(folio);
+ folio_put(folio);
}
return error;
@@ -1791,7 +1789,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
struct shmem_inode_info *info = SHMEM_I(inode);
struct shmem_sb_info *sbinfo;
struct mm_struct *charge_mm;
- struct page *page;
+ struct folio *folio;
pgoff_t hindex = index;
gfp_t huge_gfp;
int error;
@@ -1809,39 +1807,37 @@ repeat:
sbinfo = SHMEM_SB(inode->i_sb);
charge_mm = vma ? vma->vm_mm : NULL;
- page = pagecache_get_page(mapping, index,
- FGP_ENTRY | FGP_HEAD | FGP_LOCK, 0);
-
- if (page && vma && userfaultfd_minor(vma)) {
- if (!xa_is_value(page)) {
- unlock_page(page);
- put_page(page);
+ folio = __filemap_get_folio(mapping, index, FGP_ENTRY | FGP_LOCK, 0);
+ if (folio && vma && userfaultfd_minor(vma)) {
+ if (!xa_is_value(folio)) {
+ folio_unlock(folio);
+ folio_put(folio);
}
*fault_type = handle_userfault(vmf, VM_UFFD_MINOR);
return 0;
}
- if (xa_is_value(page)) {
- error = shmem_swapin_page(inode, index, &page,
+ if (xa_is_value(folio)) {
+ error = shmem_swapin_folio(inode, index, &folio,
sgp, gfp, vma, fault_type);
if (error == -EEXIST)
goto repeat;
- *pagep = page;
+ *pagep = &folio->page;
return error;
}
- if (page) {
- hindex = page->index;
+ if (folio) {
+ hindex = folio->index;
if (sgp == SGP_WRITE)
- mark_page_accessed(page);
- if (PageUptodate(page))
+ folio_mark_accessed(folio);
+ if (folio_test_uptodate(folio))
goto out;
/* fallocated page */
if (sgp != SGP_READ)
goto clear;
- unlock_page(page);
- put_page(page);
+ folio_unlock(folio);
+ folio_put(folio);
}
/*
@@ -1868,17 +1864,16 @@ repeat:
huge_gfp = vma_thp_gfp_mask(vma);
huge_gfp = limit_gfp_mask(huge_gfp, gfp);
- page = shmem_alloc_and_acct_page(huge_gfp, inode, index, true);
- if (IS_ERR(page)) {
+ folio = shmem_alloc_and_acct_folio(huge_gfp, inode, index, true);
+ if (IS_ERR(folio)) {
alloc_nohuge:
- page = shmem_alloc_and_acct_page(gfp, inode,
- index, false);
+ folio = shmem_alloc_and_acct_folio(gfp, inode, index, false);
}
- if (IS_ERR(page)) {
+ if (IS_ERR(folio)) {
int retry = 5;
- error = PTR_ERR(page);
- page = NULL;
+ error = PTR_ERR(folio);
+ folio = NULL;
if (error != -ENOSPC)
goto unlock;
/*
@@ -1897,29 +1892,26 @@ alloc_nohuge:
goto unlock;
}
- if (PageTransHuge(page))
- hindex = round_down(index, HPAGE_PMD_NR);
- else
- hindex = index;
+ hindex = round_down(index, folio_nr_pages(folio));
if (sgp == SGP_WRITE)
- __SetPageReferenced(page);
+ __folio_set_referenced(folio);
- error = shmem_add_to_page_cache(page, mapping, hindex,
+ error = shmem_add_to_page_cache(folio, mapping, hindex,
NULL, gfp & GFP_RECLAIM_MASK,
charge_mm);
if (error)
goto unacct;
- lru_cache_add(page);
+ folio_add_lru(folio);
spin_lock_irq(&info->lock);
- info->alloced += compound_nr(page);
- inode->i_blocks += BLOCKS_PER_PAGE << compound_order(page);
+ info->alloced += folio_nr_pages(folio);
+ inode->i_blocks += BLOCKS_PER_PAGE << folio_order(folio);
shmem_recalc_inode(inode);
spin_unlock_irq(&info->lock);
alloced = true;
- if (PageTransHuge(page) &&
+ if (folio_test_pmd_mappable(folio) &&
DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE) <
hindex + HPAGE_PMD_NR - 1) {
/*
@@ -1950,22 +1942,21 @@ clear:
* but SGP_FALLOC on a page fallocated earlier must initialize
* it now, lest undo on failure cancel our earlier guarantee.
*/
- if (sgp != SGP_WRITE && !PageUptodate(page)) {
- int i;
+ if (sgp != SGP_WRITE && !folio_test_uptodate(folio)) {
+ long i, n = folio_nr_pages(folio);
- for (i = 0; i < compound_nr(page); i++) {
- clear_highpage(page + i);
- flush_dcache_page(page + i);
- }
- SetPageUptodate(page);
+ for (i = 0; i < n; i++)
+ clear_highpage(folio_page(folio, i));
+ flush_dcache_folio(folio);
+ folio_mark_uptodate(folio);
}
/* Perhaps the file has been truncated since we checked */
if (sgp <= SGP_CACHE &&
((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) {
if (alloced) {
- ClearPageDirty(page);
- delete_from_page_cache(page);
+ folio_clear_dirty(folio);
+ filemap_remove_folio(folio);
spin_lock_irq(&info->lock);
shmem_recalc_inode(inode);
spin_unlock_irq(&info->lock);
@@ -1974,24 +1965,24 @@ clear:
goto unlock;
}
out:
- *pagep = page + index - hindex;
+ *pagep = folio_page(folio, index - hindex);
return 0;
/*
* Error recovery.
*/
unacct:
- shmem_inode_unacct_blocks(inode, compound_nr(page));
+ shmem_inode_unacct_blocks(inode, folio_nr_pages(folio));
- if (PageTransHuge(page)) {
- unlock_page(page);
- put_page(page);
+ if (folio_test_large(folio)) {
+ folio_unlock(folio);
+ folio_put(folio);
goto alloc_nohuge;
}
unlock:
- if (page) {
- unlock_page(page);
- put_page(page);
+ if (folio) {
+ folio_unlock(folio);
+ folio_put(folio);
}
if (error == -ENOSPC && !once++) {
spin_lock_irq(&info->lock);
@@ -2239,11 +2230,6 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma)
file_accessed(file);
vma->vm_ops = &shmem_vm_ops;
- if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
- ((vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK) <
- (vma->vm_end & HPAGE_PMD_MASK)) {
- khugepaged_enter(vma, vma->vm_flags);
- }
return 0;
}
@@ -2318,7 +2304,7 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
struct vm_area_struct *dst_vma,
unsigned long dst_addr,
unsigned long src_addr,
- bool zeropage,
+ bool zeropage, bool wp_copy,
struct page **pagep)
{
struct inode *inode = file_inode(dst_vma->vm_file);
@@ -2327,6 +2313,7 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
gfp_t gfp = mapping_gfp_mask(mapping);
pgoff_t pgoff = linear_page_index(dst_vma, dst_addr);
void *page_kaddr;
+ struct folio *folio;
struct page *page;
int ret;
pgoff_t max_off;
@@ -2385,13 +2372,14 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
if (unlikely(pgoff >= max_off))
goto out_release;
- ret = shmem_add_to_page_cache(page, mapping, pgoff, NULL,
+ folio = page_folio(page);
+ ret = shmem_add_to_page_cache(folio, mapping, pgoff, NULL,
gfp & GFP_RECLAIM_MASK, dst_mm);
if (ret)
goto out_release;
ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr,
- page, true, false);
+ page, true, wp_copy);
if (ret)
goto out_delete_from_cache;
@@ -3487,6 +3475,10 @@ static int shmem_reconfigure(struct fs_context *fc)
raw_spin_lock(&sbinfo->stat_lock);
inodes = sbinfo->max_inodes - sbinfo->free_inodes;
+ if (ctx->blocks > S64_MAX) {
+ err = "Number of blocks too large";
+ goto out;
+ }
if ((ctx->seen & SHMEM_SEEN_BLOCKS) && ctx->blocks) {
if (!sbinfo->max_blocks) {
err = "Cannot retroactively limit size";
@@ -3888,7 +3880,7 @@ static struct file_system_type shmem_fs_type = {
.fs_flags = FS_USERNS_MOUNT,
};
-int __init shmem_init(void)
+void __init shmem_init(void)
{
int error;
@@ -3913,14 +3905,13 @@ int __init shmem_init(void)
else
shmem_huge = SHMEM_HUGE_NEVER; /* just in case it was patched */
#endif
- return 0;
+ return;
out1:
unregister_filesystem(&shmem_fs_type);
out2:
shmem_destroy_inodecache();
shm_mnt = ERR_PTR(error);
- return error;
}
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && defined(CONFIG_SYSFS)
@@ -3998,14 +3989,12 @@ static struct file_system_type shmem_fs_type = {
.fs_flags = FS_USERNS_MOUNT,
};
-int __init shmem_init(void)
+void __init shmem_init(void)
{
BUG_ON(register_filesystem(&shmem_fs_type) != 0);
shm_mnt = kern_mount(&shmem_fs_type);
BUG_ON(IS_ERR(shm_mnt));
-
- return 0;
}
int shmem_unuse(unsigned int type)
@@ -4145,12 +4134,6 @@ int shmem_zero_setup(struct vm_area_struct *vma)
vma->vm_file = file;
vma->vm_ops = &shmem_vm_ops;
- if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
- ((vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK) <
- (vma->vm_end & HPAGE_PMD_MASK)) {
- khugepaged_enter(vma, vma->vm_flags);
- }
-
return 0;
}