Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/mm/shmem.c b/mm/shmem.c
index b119c44..d3d8c5e 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -82,7 +82,6 @@
#include <linux/uuid.h>
#include <linux/uaccess.h>
-#include <asm/pgtable.h>
#include "internal.h"
@@ -115,11 +114,13 @@
kuid_t uid;
kgid_t gid;
umode_t mode;
+ bool full_inums;
int huge;
int seen;
#define SHMEM_SEEN_BLOCKS 1
#define SHMEM_SEEN_INODES 2
#define SHMEM_SEEN_HUGE 4
+#define SHMEM_SEEN_INUMS 8
};
#ifdef CONFIG_TMPFS
@@ -261,18 +262,78 @@
static LIST_HEAD(shmem_swaplist);
static DEFINE_MUTEX(shmem_swaplist_mutex);
-static int shmem_reserve_inode(struct super_block *sb)
+/*
+ * shmem_reserve_inode() performs bookkeeping to reserve a shmem inode, and
+ * produces a novel ino for the newly allocated inode.
+ *
+ * It may also be called when making a hard link to permit the space needed by
+ * each dentry. However, in that case, no new inode number is needed since that
+ * internally draws from another pool of inode numbers (currently global
+ * get_next_ino()). This case is indicated by passing NULL as inop.
+ */
+#define SHMEM_INO_BATCH 1024
+static int shmem_reserve_inode(struct super_block *sb, ino_t *inop)
{
struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
- if (sbinfo->max_inodes) {
+ ino_t ino;
+
+ if (!(sb->s_flags & SB_KERNMOUNT)) {
spin_lock(&sbinfo->stat_lock);
- if (!sbinfo->free_inodes) {
- spin_unlock(&sbinfo->stat_lock);
- return -ENOSPC;
+ if (sbinfo->max_inodes) {
+ if (!sbinfo->free_inodes) {
+ spin_unlock(&sbinfo->stat_lock);
+ return -ENOSPC;
+ }
+ sbinfo->free_inodes--;
}
- sbinfo->free_inodes--;
+ if (inop) {
+ ino = sbinfo->next_ino++;
+ if (unlikely(is_zero_ino(ino)))
+ ino = sbinfo->next_ino++;
+ if (unlikely(!sbinfo->full_inums &&
+ ino > UINT_MAX)) {
+ /*
+ * Emulate get_next_ino uint wraparound for
+ * compatibility
+ */
+ if (IS_ENABLED(CONFIG_64BIT))
+ pr_warn("%s: inode number overflow on device %d, consider using inode64 mount option\n",
+ __func__, MINOR(sb->s_dev));
+ sbinfo->next_ino = 1;
+ ino = sbinfo->next_ino++;
+ }
+ *inop = ino;
+ }
spin_unlock(&sbinfo->stat_lock);
+ } else if (inop) {
+ /*
+ * __shmem_file_setup, one of our callers, is lock-free: it
+ * doesn't hold stat_lock in shmem_reserve_inode since
+ * max_inodes is always 0, and is called from potentially
+ * unknown contexts. As such, use a per-cpu batched allocator
+ * which doesn't require the per-sb stat_lock unless we are at
+ * the batch boundary.
+ *
+ * We don't need to worry about inode{32,64} since SB_KERNMOUNT
+ * shmem mounts are not exposed to userspace, so we don't need
+ * to worry about things like glibc compatibility.
+ */
+ ino_t *next_ino;
+ next_ino = per_cpu_ptr(sbinfo->ino_batch, get_cpu());
+ ino = *next_ino;
+ if (unlikely(ino % SHMEM_INO_BATCH == 0)) {
+ spin_lock(&sbinfo->stat_lock);
+ ino = sbinfo->next_ino;
+ sbinfo->next_ino += SHMEM_INO_BATCH;
+ spin_unlock(&sbinfo->stat_lock);
+ if (unlikely(is_zero_ino(ino)))
+ ino++;
+ }
+ *inop = ino;
+ *next_ino = ++ino;
+ put_cpu();
}
+
return 0;
}
@@ -410,7 +471,7 @@
#define SHMEM_HUGE_DENY (-1)
#define SHMEM_HUGE_FORCE (-2)
-#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/* ifdef here to avoid bloating shmem.o when not necessary */
static int shmem_huge __read_mostly;
@@ -466,7 +527,7 @@
struct shmem_inode_info *info;
struct page *page;
unsigned long batch = sc ? sc->nr_to_scan : 128;
- int removed = 0, split = 0;
+ int split = 0;
if (list_empty(&sbinfo->shrinklist))
return SHRINK_STOP;
@@ -481,7 +542,6 @@
/* inode is about to be evicted */
if (!inode) {
list_del_init(&info->shrinklist);
- removed++;
goto next;
}
@@ -489,12 +549,12 @@
if (round_up(inode->i_size, PAGE_SIZE) ==
round_up(inode->i_size, HPAGE_PMD_SIZE)) {
list_move(&info->shrinklist, &to_remove);
- removed++;
goto next;
}
list_move(&info->shrinklist, &list);
next:
+ sbinfo->shrinklist_len--;
if (!--batch)
break;
}
@@ -514,7 +574,7 @@
inode = &info->vfs_inode;
if (nr_to_split && split >= nr_to_split)
- goto leave;
+ goto move_back;
page = find_get_page(inode->i_mapping,
(inode->i_size & HPAGE_PMD_MASK) >> PAGE_SHIFT);
@@ -528,38 +588,44 @@
}
/*
- * Leave the inode on the list if we failed to lock
- * the page at this time.
+ * Move the inode on the list back to shrinklist if we failed
+ * to lock the page at this time.
*
* Waiting for the lock may lead to deadlock in the
* reclaim path.
*/
if (!trylock_page(page)) {
put_page(page);
- goto leave;
+ goto move_back;
}
ret = split_huge_page(page);
unlock_page(page);
put_page(page);
- /* If split failed leave the inode on the list */
+ /* If split failed move the inode on the list back to shrinklist */
if (ret)
- goto leave;
+ goto move_back;
split++;
drop:
list_del_init(&info->shrinklist);
- removed++;
-leave:
+ goto put;
+move_back:
+ /*
+ * Make sure the inode is either on the global list or deleted
+ * from any local list before iput() since it could be deleted
+ * in another thread once we put the inode (then the local list
+ * is corrupted).
+ */
+ spin_lock(&sbinfo->shrinklist_lock);
+ list_move(&info->shrinklist, &sbinfo->shrinklist);
+ sbinfo->shrinklist_len++;
+ spin_unlock(&sbinfo->shrinklist_lock);
+put:
iput(inode);
}
- spin_lock(&sbinfo->shrinklist_lock);
- list_splice_tail(&list, &sbinfo->shrinklist);
- sbinfo->shrinklist_len -= removed;
- spin_unlock(&sbinfo->shrinklist_lock);
-
return split;
}
@@ -580,7 +646,7 @@
struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
return READ_ONCE(sbinfo->shrinklist_len);
}
-#else /* !CONFIG_TRANSPARENT_HUGE_PAGECACHE */
+#else /* !CONFIG_TRANSPARENT_HUGEPAGE */
#define shmem_huge SHMEM_HUGE_DENY
@@ -589,11 +655,11 @@
{
return 0;
}
-#endif /* CONFIG_TRANSPARENT_HUGE_PAGECACHE */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
static inline bool is_huge_enabled(struct shmem_sb_info *sbinfo)
{
- if (IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE) &&
+ if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
(shmem_huge == SHMEM_HUGE_FORCE || sbinfo->huge) &&
shmem_huge != SHMEM_HUGE_DENY)
return true;
@@ -605,11 +671,13 @@
*/
static int shmem_add_to_page_cache(struct page *page,
struct address_space *mapping,
- pgoff_t index, void *expected, gfp_t gfp)
+ 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 i = 0;
unsigned long nr = compound_nr(page);
+ int error;
VM_BUG_ON_PAGE(PageTail(page), page);
VM_BUG_ON_PAGE(index != round_down(index, nr), page);
@@ -621,6 +689,18 @@
page->mapping = mapping;
page->index = index;
+ if (!PageSwapCache(page)) {
+ error = mem_cgroup_charge(page, charge_mm, gfp);
+ if (error) {
+ if (PageTransHuge(page)) {
+ count_vm_event(THP_FILE_FALLBACK);
+ count_vm_event(THP_FILE_FALLBACK_CHARGE);
+ }
+ goto error;
+ }
+ }
+ cgroup_throttle_swaprate(page, gfp);
+
do {
void *entry;
xas_lock_irq(&xas);
@@ -641,19 +721,22 @@
__inc_node_page_state(page, NR_SHMEM_THPS);
}
mapping->nrpages += nr;
- __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr);
- __mod_node_page_state(page_pgdat(page), NR_SHMEM, nr);
+ __mod_lruvec_page_state(page, NR_FILE_PAGES, nr);
+ __mod_lruvec_page_state(page, NR_SHMEM, nr);
unlock:
xas_unlock_irq(&xas);
} while (xas_nomem(&xas, gfp));
if (xas_error(&xas)) {
- page->mapping = NULL;
- page_ref_sub(page, nr);
- return xas_error(&xas);
+ error = xas_error(&xas);
+ goto error;
}
return 0;
+error:
+ page->mapping = NULL;
+ page_ref_sub(page, nr);
+ return error;
}
/*
@@ -670,8 +753,8 @@
error = shmem_replace_entry(mapping, page->index, page, radswap);
page->mapping = NULL;
mapping->nrpages--;
- __dec_node_page_state(page, NR_FILE_PAGES);
- __dec_node_page_state(page, NR_SHMEM);
+ __dec_lruvec_page_state(page, NR_FILE_PAGES);
+ __dec_lruvec_page_state(page, NR_SHMEM);
xa_unlock_irq(&mapping->i_pages);
put_page(page);
BUG_ON(error);
@@ -789,6 +872,32 @@
}
/*
+ * Check whether a hole-punch or truncation needs to split a huge page,
+ * returning true if no split was required, or the split has been successful.
+ *
+ * Eviction (or truncation to 0 size) should never need to split a huge page;
+ * but in rare cases might do so, if shmem_undo_range() failed to trylock on
+ * head, and then succeeded to trylock on tail.
+ *
+ * A split can only succeed when there are no additional references on the
+ * huge page: so the split below relies upon find_get_entries() having stopped
+ * when it found a subpage of the huge page, without getting further references.
+ */
+static bool shmem_punch_compound(struct page *page, pgoff_t start, pgoff_t end)
+{
+ if (!PageTransCompound(page))
+ return true;
+
+ /* Just proceed to delete a huge page wholly within the range punched */
+ if (PageHead(page) &&
+ page->index >= start && page->index + HPAGE_PMD_NR <= end)
+ return true;
+
+ /* Try to split huge page, so we can truly punch the hole or truncate */
+ return split_huge_page(page) >= 0;
+}
+
+/*
* Remove range of pages and swap entries from page cache, and free them.
* If !unfalloc, truncate or punch hole; if unfalloc, undo failed fallocate.
*/
@@ -838,31 +947,11 @@
if (!trylock_page(page))
continue;
- if (PageTransTail(page)) {
- /* Middle of THP: zero out the page */
- clear_highpage(page);
- unlock_page(page);
- continue;
- } else if (PageTransHuge(page)) {
- if (index == round_down(end, HPAGE_PMD_NR)) {
- /*
- * Range ends in the middle of THP:
- * zero out the page
- */
- clear_highpage(page);
- unlock_page(page);
- continue;
- }
- index += HPAGE_PMD_NR - 1;
- i += HPAGE_PMD_NR - 1;
- }
-
- if (!unfalloc || !PageUptodate(page)) {
- VM_BUG_ON_PAGE(PageTail(page), page);
- if (page_mapping(page) == mapping) {
- VM_BUG_ON_PAGE(PageWriteback(page), page);
+ if ((!unfalloc || !PageUptodate(page)) &&
+ page_mapping(page) == mapping) {
+ VM_BUG_ON_PAGE(PageWriteback(page), page);
+ if (shmem_punch_compound(page, start, end))
truncate_inode_page(mapping, page);
- }
}
unlock_page(page);
}
@@ -936,43 +1025,25 @@
lock_page(page);
- if (PageTransTail(page)) {
- /* Middle of THP: zero out the page */
- clear_highpage(page);
- unlock_page(page);
- /*
- * Partial thp truncate due 'start' in middle
- * of THP: don't need to look on these pages
- * again on !pvec.nr restart.
- */
- if (index != round_down(end, HPAGE_PMD_NR))
- start++;
- continue;
- } else if (PageTransHuge(page)) {
- if (index == round_down(end, HPAGE_PMD_NR)) {
- /*
- * Range ends in the middle of THP:
- * zero out the page
- */
- clear_highpage(page);
- unlock_page(page);
- continue;
- }
- index += HPAGE_PMD_NR - 1;
- i += HPAGE_PMD_NR - 1;
- }
-
if (!unfalloc || !PageUptodate(page)) {
- VM_BUG_ON_PAGE(PageTail(page), page);
- if (page_mapping(page) == mapping) {
- VM_BUG_ON_PAGE(PageWriteback(page), page);
- truncate_inode_page(mapping, page);
- } else {
+ if (page_mapping(page) != mapping) {
/* Page was replaced by swap: retry */
unlock_page(page);
index--;
break;
}
+ VM_BUG_ON_PAGE(PageWriteback(page), page);
+ if (shmem_punch_compound(page, start, end))
+ truncate_inode_page(mapping, page);
+ else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
+ /* Wipe the page and don't get stuck */
+ clear_highpage(page);
+ flush_dcache_page(page);
+ set_page_dirty(page);
+ if (index <
+ round_up(start, HPAGE_PMD_NR))
+ start = index + 1;
+ }
}
unlock_page(page);
}
@@ -1059,7 +1130,7 @@
* Part of the huge page can be beyond i_size: subject
* to shrink under memory pressure.
*/
- if (IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE)) {
+ if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
spin_lock(&sbinfo->shrinklist_lock);
/*
* _careful to defend against unlocked access to
@@ -1369,7 +1440,9 @@
if (list_empty(&info->swaplist))
list_add(&info->swaplist, &shmem_swaplist);
- if (add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) {
+ if (add_to_swap_cache(page, swap,
+ __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN,
+ NULL) == 0) {
spin_lock_irq(&info->lock);
shmem_recalc_inode(inode);
info->swapped++;
@@ -1471,9 +1544,6 @@
pgoff_t hindex;
struct page *page;
- if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE))
- return NULL;
-
hindex = round_down(index, HPAGE_PMD_NR);
if (xa_find(&mapping->i_pages, &hindex, hindex + HPAGE_PMD_NR - 1,
XA_PRESENT))
@@ -1485,6 +1555,8 @@
shmem_pseudo_vma_destroy(&pvma);
if (page)
prep_transhuge_page(page);
+ else
+ count_vm_event(THP_FILE_FALLBACK);
return page;
}
@@ -1510,7 +1582,7 @@
int nr;
int err = -ENOSPC;
- if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE))
+ if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
huge = false;
nr = huge ? HPAGE_PMD_NR : 1;
@@ -1590,8 +1662,9 @@
xa_lock_irq(&swap_mapping->i_pages);
error = shmem_replace_entry(swap_mapping, swap_index, oldpage, newpage);
if (!error) {
- __inc_node_page_state(newpage, NR_FILE_PAGES);
- __dec_node_page_state(oldpage, NR_FILE_PAGES);
+ mem_cgroup_migrate(oldpage, newpage);
+ __inc_lruvec_page_state(newpage, NR_FILE_PAGES);
+ __dec_lruvec_page_state(oldpage, NR_FILE_PAGES);
}
xa_unlock_irq(&swap_mapping->i_pages);
@@ -1603,8 +1676,7 @@
*/
oldpage = newpage;
} else {
- mem_cgroup_migrate(oldpage, newpage);
- lru_cache_add_anon(newpage);
+ lru_cache_add(newpage);
*pagep = newpage;
}
@@ -1621,7 +1693,7 @@
* Swap in the page pointed to by *pagep.
* Caller has to make sure that *pagep contains a valid swapped page.
* Returns 0 and the page in pagep if success. On failure, returns the
- * the error code and NULL in *pagep.
+ * error code and NULL in *pagep.
*/
static int shmem_swapin_page(struct inode *inode, pgoff_t index,
struct page **pagep, enum sgp_type sgp,
@@ -1631,7 +1703,6 @@
struct address_space *mapping = inode->i_mapping;
struct shmem_inode_info *info = SHMEM_I(inode);
struct mm_struct *charge_mm = vma ? vma->vm_mm : current->mm;
- struct mem_cgroup *memcg;
struct page *page;
swp_entry_t swap;
int error;
@@ -1670,37 +1741,24 @@
}
wait_on_page_writeback(page);
+ /*
+ * Some architectures may have to restore extra metadata to the
+ * physical page after reading from swap.
+ */
+ arch_swap_restore(swap, page);
+
if (shmem_should_replace_page(page, gfp)) {
error = shmem_replace_page(&page, gfp, info, index);
if (error)
goto failed;
}
- error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg,
- false);
- if (!error) {
- error = shmem_add_to_page_cache(page, mapping, index,
- swp_to_radix_entry(swap), gfp);
- /*
- * We already confirmed swap under page lock, and make
- * no memory allocation here, so usually no possibility
- * of error; but free_swap_and_cache() only trylocks a
- * page, so it is just possible that the entry has been
- * truncated or holepunched since swap was confirmed.
- * shmem_undo_range() will have done some of the
- * unaccounting, now delete_from_swap_cache() will do
- * the rest.
- */
- if (error) {
- mem_cgroup_cancel_charge(page, memcg, false);
- delete_from_swap_cache(page);
- }
- }
+ error = shmem_add_to_page_cache(page, mapping, index,
+ swp_to_radix_entry(swap), gfp,
+ charge_mm);
if (error)
goto failed;
- mem_cgroup_commit_charge(page, memcg, true, false);
-
spin_lock_irq(&info->lock);
info->swapped--;
shmem_recalc_inode(inode);
@@ -1746,7 +1804,6 @@
struct shmem_inode_info *info = SHMEM_I(inode);
struct shmem_sb_info *sbinfo;
struct mm_struct *charge_mm;
- struct mem_cgroup *memcg;
struct page *page;
enum sgp_type sgp_huge = sgp;
pgoff_t hindex = index;
@@ -1778,6 +1835,8 @@
return error;
}
+ if (page)
+ hindex = page->index;
if (page && sgp == SGP_WRITE)
mark_page_accessed(page);
@@ -1788,11 +1847,10 @@
unlock_page(page);
put_page(page);
page = NULL;
+ hindex = index;
}
- if (page || sgp == SGP_READ) {
- *pagep = page;
- return 0;
- }
+ if (page || sgp == SGP_READ)
+ goto out;
/*
* Fast cache lookup did not find it:
@@ -1812,17 +1870,20 @@
if (shmem_huge == SHMEM_HUGE_FORCE)
goto alloc_huge;
switch (sbinfo->huge) {
- loff_t i_size;
- pgoff_t off;
case SHMEM_HUGE_NEVER:
goto alloc_nohuge;
- case SHMEM_HUGE_WITHIN_SIZE:
+ case SHMEM_HUGE_WITHIN_SIZE: {
+ loff_t i_size;
+ pgoff_t off;
+
off = round_up(index, HPAGE_PMD_NR);
i_size = round_up(i_size_read(inode), PAGE_SIZE);
if (i_size >= HPAGE_PMD_SIZE &&
i_size >> PAGE_SHIFT >= off)
goto alloc_huge;
- /* fallthrough */
+
+ fallthrough;
+ }
case SHMEM_HUGE_ADVISE:
if (sgp_huge == SGP_HUGE)
goto alloc_huge;
@@ -1868,20 +1929,12 @@
if (sgp == SGP_WRITE)
__SetPageReferenced(page);
- error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg,
- PageTransHuge(page));
+ error = shmem_add_to_page_cache(page, mapping, hindex,
+ NULL, gfp & GFP_RECLAIM_MASK,
+ charge_mm);
if (error)
goto unacct;
- error = shmem_add_to_page_cache(page, mapping, hindex,
- NULL, gfp & GFP_RECLAIM_MASK);
- if (error) {
- mem_cgroup_cancel_charge(page, memcg,
- PageTransHuge(page));
- goto unacct;
- }
- mem_cgroup_commit_charge(page, memcg, false,
- PageTransHuge(page));
- lru_cache_add_anon(page);
+ lru_cache_add(page);
spin_lock_irq(&info->lock);
info->alloced += compound_nr(page);
@@ -1922,14 +1975,13 @@
* it now, lest undo on failure cancel our earlier guarantee.
*/
if (sgp != SGP_WRITE && !PageUptodate(page)) {
- struct page *head = compound_head(page);
int i;
- for (i = 0; i < compound_nr(head); i++) {
- clear_highpage(head + i);
- flush_dcache_page(head + i);
+ for (i = 0; i < compound_nr(page); i++) {
+ clear_highpage(page + i);
+ flush_dcache_page(page + i);
}
- SetPageUptodate(head);
+ SetPageUptodate(page);
}
/* Perhaps the file has been truncated since we checked */
@@ -1945,6 +1997,7 @@
error = -EINVAL;
goto unlock;
}
+out:
*pagep = page + index - hindex;
return 0;
@@ -2088,7 +2141,7 @@
get_area = current->mm->get_unmapped_area;
addr = get_area(file, uaddr, len, pgoff, flags);
- if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE))
+ if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
return addr;
if (IS_ERR_VALUE(addr))
return addr;
@@ -2214,9 +2267,12 @@
if (ret)
return ret;
+ /* arm64 - allow memory tagging on RAM-based files */
+ vma->vm_flags |= VM_MTE_ALLOWED;
+
file_accessed(file);
vma->vm_ops = &shmem_vm_ops;
- if (IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE) &&
+ 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);
@@ -2230,13 +2286,14 @@
struct inode *inode;
struct shmem_inode_info *info;
struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
+ ino_t ino;
- if (shmem_reserve_inode(sb))
+ if (shmem_reserve_inode(sb, &ino))
return NULL;
inode = new_inode(sb);
if (inode) {
- inode->i_ino = get_next_ino();
+ inode->i_ino = ino;
inode_init_owner(inode, dir, mode);
inode->i_blocks = 0;
inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
@@ -2304,7 +2361,6 @@
struct address_space *mapping = inode->i_mapping;
gfp_t gfp = mapping_gfp_mask(mapping);
pgoff_t pgoff = linear_page_index(dst_vma, dst_addr);
- struct mem_cgroup *memcg;
spinlock_t *ptl;
void *page_kaddr;
struct page *page;
@@ -2338,7 +2394,7 @@
PAGE_SIZE);
kunmap_atomic(page_kaddr);
- /* fallback to copy_from_user outside mmap_sem */
+ /* fallback to copy_from_user outside mmap_lock */
if (unlikely(ret)) {
*pagep = page;
shmem_inode_unacct_blocks(inode, 1);
@@ -2364,17 +2420,11 @@
if (unlikely(offset >= max_off))
goto out_release;
- ret = mem_cgroup_try_charge_delay(page, dst_mm, gfp, &memcg, false);
+ ret = shmem_add_to_page_cache(page, mapping, pgoff, NULL,
+ gfp & GFP_RECLAIM_MASK, dst_mm);
if (ret)
goto out_release;
- ret = shmem_add_to_page_cache(page, mapping, pgoff, NULL,
- gfp & GFP_RECLAIM_MASK);
- if (ret)
- goto out_release_uncharge;
-
- 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)
_dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte));
@@ -2394,13 +2444,13 @@
ret = -EFAULT;
max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
if (unlikely(offset >= max_off))
- goto out_release_uncharge_unlock;
+ goto out_release_unlock;
ret = -EEXIST;
if (!pte_none(*dst_pte))
- goto out_release_uncharge_unlock;
+ goto out_release_unlock;
- lru_cache_add_anon(page);
+ lru_cache_add(page);
spin_lock_irq(&info->lock);
info->alloced++;
@@ -2419,12 +2469,10 @@
ret = 0;
out:
return ret;
-out_release_uncharge_unlock:
+out_release_unlock:
pte_unmap_unlock(dst_pte, ptl);
ClearPageDirty(page);
delete_from_page_cache(page);
-out_release_uncharge:
- mem_cgroup_cancel_charge(page, memcg, false);
out_release:
unlock_page(page);
put_page(page);
@@ -2959,7 +3007,7 @@
* first link must skip that, to get the accounting right.
*/
if (inode->i_nlink) {
- ret = shmem_reserve_inode(inode->i_sb);
+ ret = shmem_reserve_inode(inode->i_sb, NULL);
if (ret)
goto out;
}
@@ -3111,12 +3159,9 @@
error = security_inode_init_security(inode, dir, &dentry->d_name,
shmem_initxattrs, NULL);
- if (error) {
- if (error != -EOPNOTSUPP) {
- iput(inode);
- return error;
- }
- error = 0;
+ if (error && error != -EOPNOTSUPP) {
+ iput(inode);
+ return error;
}
inode->i_size = len-1;
@@ -3208,7 +3253,7 @@
new_xattr->name = kmalloc(XATTR_SECURITY_PREFIX_LEN + len,
GFP_KERNEL);
if (!new_xattr->name) {
- kfree(new_xattr);
+ kvfree(new_xattr);
return -ENOMEM;
}
@@ -3241,7 +3286,7 @@
struct shmem_inode_info *info = SHMEM_I(inode);
name = xattr_full_name(handler, name);
- return simple_xattr_set(&info->xattrs, name, value, size, flags);
+ return simple_xattr_set(&info->xattrs, name, value, size, flags, NULL);
}
static const struct xattr_handler shmem_security_xattr_handler = {
@@ -3377,34 +3422,32 @@
Opt_nr_inodes,
Opt_size,
Opt_uid,
+ Opt_inode32,
+ Opt_inode64,
};
-static const struct fs_parameter_spec shmem_param_specs[] = {
+static const struct constant_table shmem_param_enums_huge[] = {
+ {"never", SHMEM_HUGE_NEVER },
+ {"always", SHMEM_HUGE_ALWAYS },
+ {"within_size", SHMEM_HUGE_WITHIN_SIZE },
+ {"advise", SHMEM_HUGE_ADVISE },
+ {}
+};
+
+const struct fs_parameter_spec shmem_fs_parameters[] = {
fsparam_u32 ("gid", Opt_gid),
- fsparam_enum ("huge", Opt_huge),
+ fsparam_enum ("huge", Opt_huge, shmem_param_enums_huge),
fsparam_u32oct("mode", Opt_mode),
fsparam_string("mpol", Opt_mpol),
fsparam_string("nr_blocks", Opt_nr_blocks),
fsparam_string("nr_inodes", Opt_nr_inodes),
fsparam_string("size", Opt_size),
fsparam_u32 ("uid", Opt_uid),
+ fsparam_flag ("inode32", Opt_inode32),
+ fsparam_flag ("inode64", Opt_inode64),
{}
};
-static const struct fs_parameter_enum shmem_param_enums[] = {
- { Opt_huge, "never", SHMEM_HUGE_NEVER },
- { Opt_huge, "always", SHMEM_HUGE_ALWAYS },
- { Opt_huge, "within_size", SHMEM_HUGE_WITHIN_SIZE },
- { Opt_huge, "advise", SHMEM_HUGE_ADVISE },
- {}
-};
-
-const struct fs_parameter_description shmem_fs_parameters = {
- .name = "tmpfs",
- .specs = shmem_param_specs,
- .enums = shmem_param_enums,
-};
-
static int shmem_parse_one(struct fs_context *fc, struct fs_parameter *param)
{
struct shmem_options *ctx = fc->fs_private;
@@ -3413,7 +3456,7 @@
char *rest;
int opt;
- opt = fs_parse(fc, &shmem_fs_parameters, param, &result);
+ opt = fs_parse(fc, shmem_fs_parameters, param, &result);
if (opt < 0)
return opt;
@@ -3459,7 +3502,7 @@
case Opt_huge:
ctx->huge = result.uint_32;
if (ctx->huge != SHMEM_HUGE_NEVER &&
- !(IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE) &&
+ !(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
has_transparent_hugepage()))
goto unsupported_parameter;
ctx->seen |= SHMEM_SEEN_HUGE;
@@ -3473,13 +3516,25 @@
break;
}
goto unsupported_parameter;
+ case Opt_inode32:
+ ctx->full_inums = false;
+ ctx->seen |= SHMEM_SEEN_INUMS;
+ break;
+ case Opt_inode64:
+ if (sizeof(ino_t) < 8) {
+ return invalfc(fc,
+ "Cannot use inode64 with <64bit inums in kernel\n");
+ }
+ ctx->full_inums = true;
+ ctx->seen |= SHMEM_SEEN_INUMS;
+ break;
}
return 0;
unsupported_parameter:
- return invalf(fc, "tmpfs: Unsupported parameter '%s'", param->key);
+ return invalfc(fc, "Unsupported parameter '%s'", param->key);
bad_value:
- return invalf(fc, "tmpfs: Bad value for '%s'", param->key);
+ return invalfc(fc, "Bad value for '%s'", param->key);
}
static int shmem_parse_options(struct fs_context *fc, void *data)
@@ -3564,8 +3619,16 @@
}
}
+ if ((ctx->seen & SHMEM_SEEN_INUMS) && !ctx->full_inums &&
+ sbinfo->next_ino > UINT_MAX) {
+ err = "Current inum too high to switch to 32-bit inums";
+ goto out;
+ }
+
if (ctx->seen & SHMEM_SEEN_HUGE)
sbinfo->huge = ctx->huge;
+ if (ctx->seen & SHMEM_SEEN_INUMS)
+ sbinfo->full_inums = ctx->full_inums;
if (ctx->seen & SHMEM_SEEN_BLOCKS)
sbinfo->max_blocks = ctx->blocks;
if (ctx->seen & SHMEM_SEEN_INODES) {
@@ -3585,7 +3648,7 @@
return 0;
out:
spin_unlock(&sbinfo->stat_lock);
- return invalf(fc, "tmpfs: %s", err);
+ return invalfc(fc, "%s", err);
}
static int shmem_show_options(struct seq_file *seq, struct dentry *root)
@@ -3605,7 +3668,30 @@
if (!gid_eq(sbinfo->gid, GLOBAL_ROOT_GID))
seq_printf(seq, ",gid=%u",
from_kgid_munged(&init_user_ns, sbinfo->gid));
-#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE
+
+ /*
+ * Showing inode{64,32} might be useful even if it's the system default,
+ * since then people don't have to resort to checking both here and
+ * /proc/config.gz to confirm 64-bit inums were successfully applied
+ * (which may not even exist if IKCONFIG_PROC isn't enabled).
+ *
+ * We hide it when inode64 isn't the default and we are using 32-bit
+ * inodes, since that probably just means the feature isn't even under
+ * consideration.
+ *
+ * As such:
+ *
+ * +-----------------+-----------------+
+ * | TMPFS_INODE64=y | TMPFS_INODE64=n |
+ * +------------------+-----------------+-----------------+
+ * | full_inums=true | show | show |
+ * | full_inums=false | show | hide |
+ * +------------------+-----------------+-----------------+
+ *
+ */
+ if (IS_ENABLED(CONFIG_TMPFS_INODE64) || sbinfo->full_inums)
+ seq_printf(seq, ",inode%d", (sbinfo->full_inums ? 64 : 32));
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/* Rightly or wrongly, show huge mount option unmasked by shmem_huge */
if (sbinfo->huge)
seq_printf(seq, ",huge=%s", shmem_format_huge(sbinfo->huge));
@@ -3620,6 +3706,7 @@
{
struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
+ free_percpu(sbinfo->ino_batch);
percpu_counter_destroy(&sbinfo->used_blocks);
mpol_put(sbinfo->mpol);
kfree(sbinfo);
@@ -3652,6 +3739,8 @@
ctx->blocks = shmem_default_max_blocks();
if (!(ctx->seen & SHMEM_SEEN_INODES))
ctx->inodes = shmem_default_max_inodes();
+ if (!(ctx->seen & SHMEM_SEEN_INUMS))
+ ctx->full_inums = IS_ENABLED(CONFIG_TMPFS_INODE64);
} else {
sb->s_flags |= SB_NOUSER;
}
@@ -3662,8 +3751,14 @@
#endif
sbinfo->max_blocks = ctx->blocks;
sbinfo->free_inodes = sbinfo->max_inodes = ctx->inodes;
+ if (sb->s_flags & SB_KERNMOUNT) {
+ sbinfo->ino_batch = alloc_percpu(ino_t);
+ if (!sbinfo->ino_batch)
+ goto failed;
+ }
sbinfo->uid = ctx->uid;
sbinfo->gid = ctx->gid;
+ sbinfo->full_inums = ctx->full_inums;
sbinfo->mode = ctx->mode;
sbinfo->huge = ctx->huge;
sbinfo->mpol = ctx->mpol;
@@ -3850,7 +3945,7 @@
.evict_inode = shmem_evict_inode,
.drop_inode = generic_delete_inode,
.put_super = shmem_put_super,
-#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
.nr_cached_objects = shmem_unused_huge_count,
.free_cached_objects = shmem_unused_huge_scan,
#endif
@@ -3887,10 +3982,10 @@
.name = "tmpfs",
.init_fs_context = shmem_init_fs_context,
#ifdef CONFIG_TMPFS
- .parameters = &shmem_fs_parameters,
+ .parameters = shmem_fs_parameters,
#endif
.kill_sb = kill_litter_super,
- .fs_flags = FS_USERNS_MOUNT,
+ .fs_flags = FS_USERNS_MOUNT | FS_THP_SUPPORT,
};
int __init shmem_init(void)
@@ -3912,7 +4007,7 @@
goto out1;
}
-#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
if (has_transparent_hugepage() && shmem_huge > SHMEM_HUGE_DENY)
SHMEM_SB(shm_mnt->mnt_sb)->huge = shmem_huge;
else
@@ -3928,11 +4023,11 @@
return error;
}
-#if defined(CONFIG_TRANSPARENT_HUGE_PAGECACHE) && defined(CONFIG_SYSFS)
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && defined(CONFIG_SYSFS)
static ssize_t shmem_enabled_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
- int values[] = {
+ static const int values[] = {
SHMEM_HUGE_ALWAYS,
SHMEM_HUGE_WITHIN_SIZE,
SHMEM_HUGE_ADVISE,
@@ -3980,9 +4075,9 @@
struct kobj_attribute shmem_enabled_attr =
__ATTR(shmem_enabled, 0644, shmem_enabled_show, shmem_enabled_store);
-#endif /* CONFIG_TRANSPARENT_HUGE_PAGECACHE && CONFIG_SYSFS */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE && CONFIG_SYSFS */
-#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
bool shmem_huge_enabled(struct vm_area_struct *vma)
{
struct inode *inode = file_inode(vma->vm_file);
@@ -3990,8 +4085,7 @@
loff_t i_size;
pgoff_t off;
- if ((vma->vm_flags & VM_NOHUGEPAGE) ||
- test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))
+ if (!transhuge_vma_enabled(vma, vma->vm_flags))
return false;
if (shmem_huge == SHMEM_HUGE_FORCE)
return true;
@@ -4008,7 +4102,7 @@
if (i_size >= HPAGE_PMD_SIZE &&
i_size >> PAGE_SHIFT >= off)
return true;
- /* fall through */
+ fallthrough;
case SHMEM_HUGE_ADVISE:
/* TODO: implement fadvise() hints */
return (vma->vm_flags & VM_HUGEPAGE);
@@ -4017,7 +4111,7 @@
return false;
}
}
-#endif /* CONFIG_TRANSPARENT_HUGE_PAGECACHE */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#else /* !CONFIG_SHMEM */
@@ -4033,7 +4127,7 @@
static struct file_system_type shmem_fs_type = {
.name = "tmpfs",
.init_fs_context = ramfs_init_fs_context,
- .parameters = &ramfs_fs_parameters,
+ .parameters = ramfs_fs_parameters,
.kill_sb = kill_litter_super,
.fs_flags = FS_USERNS_MOUNT,
};
@@ -4164,7 +4258,7 @@
/**
* shmem_zero_setup - setup a shared anonymous mapping
- * @vma: the vma to be mmapped is prepared by do_mmap_pgoff
+ * @vma: the vma to be mmapped is prepared by do_mmap
*/
int shmem_zero_setup(struct vm_area_struct *vma)
{
@@ -4172,7 +4266,7 @@
loff_t size = vma->vm_end - vma->vm_start;
/*
- * Cloning a new file under mmap_sem leads to a lock ordering conflict
+ * Cloning a new file under mmap_lock leads to a lock ordering conflict
* between XFS directory reading and selinux: since this file is only
* accessible to the user through its mapping, use S_PRIVATE flag to
* bypass file security, in the same way as shmem_kernel_file_setup().
@@ -4186,7 +4280,7 @@
vma->vm_file = file;
vma->vm_ops = &shmem_vm_ops;
- if (IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE) &&
+ 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);