#include <linux/hugetlb.h>
#include <linux/frontswap.h>
#include <linux/fs_parser.h>
-
-#include <asm/tlbflush.h> /* for arch/microblaze update_mmu_cache() */
+#include <linux/swapfile.h>
static struct vfsmount *shm_mnt;
/*
* shmem_fallocate communicates with shmem_fault or shmem_writepage via
- * inode->i_private (with i_mutex making sure that it has only one user at
+ * inode->i_private (with i_rwsem making sure that it has only one user at
* a time): we would prefer not to enlarge the shmem inode just for that.
*/
struct shmem_falloc {
}
#endif
-static bool shmem_should_replace_page(struct page *page, gfp_t gfp);
-static int shmem_replace_page(struct page **pagep, gfp_t gfp,
- struct shmem_inode_info *info, pgoff_t index);
static int shmem_swapin_page(struct inode *inode, pgoff_t index,
struct page **pagep, enum sgp_type sgp,
gfp_t gfp, struct vm_area_struct *vma,
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/* ifdef here to avoid bloating shmem.o when not necessary */
-static int shmem_huge __read_mostly;
+static int shmem_huge __read_mostly = SHMEM_HUGE_NEVER;
+
+bool shmem_is_huge(struct vm_area_struct *vma,
+ struct inode *inode, pgoff_t index)
+{
+ loff_t i_size;
+
+ if (shmem_huge == SHMEM_HUGE_DENY)
+ return false;
+ if (vma && ((vma->vm_flags & VM_NOHUGEPAGE) ||
+ test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)))
+ return false;
+ if (shmem_huge == SHMEM_HUGE_FORCE)
+ return true;
+
+ switch (SHMEM_SB(inode->i_sb)->huge) {
+ case SHMEM_HUGE_ALWAYS:
+ return true;
+ case SHMEM_HUGE_WITHIN_SIZE:
+ index = 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) >= index)
+ return true;
+ fallthrough;
+ case SHMEM_HUGE_ADVISE:
+ if (vma && (vma->vm_flags & VM_HUGEPAGE))
+ return true;
+ fallthrough;
+ default:
+ return false;
+ }
+}
#if defined(CONFIG_SYSFS)
static int shmem_parse_huge(const char *str)
#define shmem_huge SHMEM_HUGE_DENY
+bool shmem_is_huge(struct vm_area_struct *vma,
+ struct inode *inode, pgoff_t index)
+{
+ return false;
+}
+
static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
struct shrink_control *sc, unsigned long nr_to_split)
{
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-static inline bool is_huge_enabled(struct shmem_sb_info *sbinfo)
-{
- if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
- (shmem_huge == SHMEM_HUGE_FORCE || sbinfo->huge) &&
- shmem_huge != SHMEM_HUGE_DENY)
- return true;
- return false;
-}
-
/*
* Like add_to_page_cache_locked, but error if expected item has gone.
*/
* Determine (in bytes) how many of the shmem object's pages mapped by the
* given offsets are swapped out.
*
- * This is safe to call without i_mutex or the i_pages lock thanks to RCU,
+ * This is safe to call without i_rwsem or the i_pages lock thanks to RCU,
* as long as the inode doesn't go away and racy results are not a problem.
*/
unsigned long shmem_partial_swap_usage(struct address_space *mapping,
* Determine (in bytes) how many of the shmem object's pages mapped by the
* given vma is swapped out.
*
- * This is safe to call without i_mutex or the i_pages lock thanks to RCU,
+ * This is safe to call without i_rwsem or the i_pages lock thanks to RCU,
* as long as the inode doesn't go away and racy results are not a problem.
*/
unsigned long shmem_swap_usage(struct vm_area_struct *vma)
if (lend == -1)
end = -1; /* unsigned, so actually very big */
+ if (info->fallocend > start && info->fallocend <= end && !unfalloc)
+ info->fallocend = start;
+
pagevec_init(&pvec);
index = start;
while (index < end && find_lock_entries(mapping, index, end - 1,
{
struct inode *inode = path->dentry->d_inode;
struct shmem_inode_info *info = SHMEM_I(inode);
- struct shmem_sb_info *sb_info = SHMEM_SB(inode->i_sb);
if (info->alloced - info->swapped != inode->i_mapping->nrpages) {
spin_lock_irq(&info->lock);
}
generic_fillattr(&init_user_ns, inode, stat);
- if (is_huge_enabled(sb_info))
+ if (shmem_is_huge(NULL, inode, 0))
stat->blksize = HPAGE_PMD_SIZE;
return 0;
{
struct inode *inode = d_inode(dentry);
struct shmem_inode_info *info = SHMEM_I(inode);
- struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
int error;
error = setattr_prepare(&init_user_ns, dentry, attr);
loff_t oldsize = inode->i_size;
loff_t newsize = attr->ia_size;
- /* protected by i_mutex */
+ /* protected by i_rwsem */
if ((newsize < oldsize && (info->seals & F_SEAL_SHRINK)) ||
(newsize > oldsize && (info->seals & F_SEAL_GROW)))
return -EPERM;
if (oldsize > holebegin)
unmap_mapping_range(inode->i_mapping,
holebegin, 0, 1);
-
- /*
- * Part of the huge page can be beyond i_size: subject
- * to shrink under memory pressure.
- */
- if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
- spin_lock(&sbinfo->shrinklist_lock);
- /*
- * _careful to defend against unlocked access to
- * ->shrink_list in shmem_unused_huge_shrink()
- */
- if (list_empty_careful(&info->shrinklist)) {
- list_add_tail(&info->shrinklist,
- &sbinfo->shrinklist);
- sbinfo->shrinklist_len++;
- }
- spin_unlock(&sbinfo->shrinklist_lock);
- }
}
}
clear_inode(inode);
}
-extern struct swap_info_struct *swap_info[];
-
static int shmem_find_swap_entries(struct address_space *mapping,
pgoff_t start, unsigned int nr_entries,
struct page **entries, pgoff_t *indices,
swp_entry_t swap;
pgoff_t index;
- VM_BUG_ON_PAGE(PageCompound(page), page);
+ /*
+ * If /sys/kernel/mm/transparent_hugepage/shmem_enabled is "always" or
+ * "force", drivers/gpu/drm/i915/gem/i915_gem_shmem.c gets huge pages,
+ * and its shmem_writeback() needs them to be split when swapping.
+ */
+ if (PageTransCompound(page)) {
+ /* Ensure the subpages are still dirty */
+ SetPageDirty(page);
+ if (split_huge_page(page) < 0)
+ goto redirty;
+ ClearPageDirty(page);
+ }
+
BUG_ON(!PageLocked(page));
mapping = page->mapping;
index = page->index;
struct shmem_sb_info *sbinfo;
struct mm_struct *charge_mm;
struct page *page;
- enum sgp_type sgp_huge = sgp;
pgoff_t hindex = index;
gfp_t huge_gfp;
int error;
if (index > (MAX_LFS_FILESIZE >> PAGE_SHIFT))
return -EFBIG;
- if (sgp == SGP_NOHUGE || sgp == SGP_HUGE)
- sgp = SGP_CACHE;
repeat:
if (sgp <= SGP_CACHE &&
((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) {
return error;
}
- if (page)
+ if (page) {
hindex = page->index;
- if (page && sgp == SGP_WRITE)
- mark_page_accessed(page);
-
- /* fallocated page? */
- if (page && !PageUptodate(page)) {
+ if (sgp == SGP_WRITE)
+ mark_page_accessed(page);
+ if (PageUptodate(page))
+ goto out;
+ /* fallocated page */
if (sgp != SGP_READ)
goto clear;
unlock_page(page);
put_page(page);
- page = NULL;
- hindex = index;
}
- if (page || sgp == SGP_READ)
- goto out;
/*
- * Fast cache lookup did not find it:
- * bring it back from swap or allocate.
+ * SGP_READ: succeed on hole, with NULL page, letting caller zero.
+ * SGP_NOALLOC: fail on hole, with NULL page, letting caller fail.
+ */
+ *pagep = NULL;
+ if (sgp == SGP_READ)
+ return 0;
+ if (sgp == SGP_NOALLOC)
+ return -ENOENT;
+
+ /*
+ * Fast cache lookup and swap lookup did not find it: allocate.
*/
if (vma && userfaultfd_missing(vma)) {
return 0;
}
- /* shmem_symlink() */
- if (!shmem_mapping(mapping))
- goto alloc_nohuge;
- if (shmem_huge == SHMEM_HUGE_DENY || sgp_huge == SGP_NOHUGE)
+ /* Never use a huge page for shmem_symlink() */
+ if (S_ISLNK(inode->i_mode))
goto alloc_nohuge;
- if (shmem_huge == SHMEM_HUGE_FORCE)
- goto alloc_huge;
- switch (sbinfo->huge) {
- case SHMEM_HUGE_NEVER:
+ if (!shmem_is_huge(vma, inode, index))
goto alloc_nohuge;
- 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;
- }
- case SHMEM_HUGE_ADVISE:
- if (sgp_huge == SGP_HUGE)
- goto alloc_huge;
- /* TODO: implement fadvise() hints */
- goto alloc_nohuge;
- }
-
-alloc_huge:
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);
struct vm_area_struct *vma = vmf->vma;
struct inode *inode = file_inode(vma->vm_file);
gfp_t gfp = mapping_gfp_mask(inode->i_mapping);
- enum sgp_type sgp;
int err;
vm_fault_t ret = VM_FAULT_LOCKED;
/*
* Trinity finds that probing a hole which tmpfs is punching can
* prevent the hole-punch from ever completing: which in turn
- * locks writers out with its hold on i_mutex. So refrain from
+ * locks writers out with its hold on i_rwsem. So refrain from
* faulting pages into the hole while it's being punched. Although
* shmem_undo_range() does remove the additions, it may be unable to
* keep up, as each new page needs its own unmap_mapping_range() call,
* we just need to make racing faults a rare case.
*
* The implementation below would be much simpler if we just used a
- * standard mutex or completion: but we cannot take i_mutex in fault,
+ * standard mutex or completion: but we cannot take i_rwsem in fault,
* and bloating every shmem inode for this unlikely case would be sad.
*/
if (unlikely(inode->i_private)) {
spin_unlock(&inode->i_lock);
}
- sgp = SGP_CACHE;
-
- if ((vma->vm_flags & VM_NOHUGEPAGE) ||
- test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))
- sgp = SGP_NOHUGE;
- else if (vma->vm_flags & VM_HUGEPAGE)
- sgp = SGP_HUGE;
-
- err = shmem_getpage_gfp(inode, vmf->pgoff, &vmf->page, sgp,
+ err = shmem_getpage_gfp(inode, vmf->pgoff, &vmf->page, SGP_CACHE,
gfp, vma, vmf, &ret);
if (err)
return vmf_error(err);
struct shmem_inode_info *info = SHMEM_I(inode);
pgoff_t index = pos >> PAGE_SHIFT;
- /* i_mutex is held by caller */
+ /* i_rwsem is held by caller */
if (unlikely(info->seals & (F_SEAL_GROW |
F_SEAL_WRITE | F_SEAL_FUTURE_WRITE))) {
if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE))
/*
* We must evaluate after, since reads (unlike writes)
- * are called without i_mutex protection against truncate
+ * are called without i_rwsem protection against truncate
*/
nr = PAGE_SIZE;
i_size = i_size_read(inode);
return -ENXIO;
inode_lock(inode);
- /* We're holding i_mutex so we can access i_size directly */
+ /* We're holding i_rwsem so we can access i_size directly */
offset = mapping_seek_hole_data(mapping, offset, inode->i_size, whence);
if (offset >= 0)
offset = vfs_setpos(file, offset, MAX_LFS_FILESIZE);
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
struct shmem_inode_info *info = SHMEM_I(inode);
struct shmem_falloc shmem_falloc;
- pgoff_t start, index, end;
+ pgoff_t start, index, end, undo_fallocend;
int error;
if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
loff_t unmap_end = round_down(offset + len, PAGE_SIZE) - 1;
DECLARE_WAIT_QUEUE_HEAD_ONSTACK(shmem_falloc_waitq);
- /* protected by i_mutex */
+ /* protected by i_rwsem */
if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) {
error = -EPERM;
goto out;
inode->i_private = &shmem_falloc;
spin_unlock(&inode->i_lock);
- for (index = start; index < end; index++) {
+ /*
+ * info->fallocend is only relevant when huge pages might be
+ * involved: to prevent split_huge_page() freeing fallocated
+ * pages when FALLOC_FL_KEEP_SIZE committed beyond i_size.
+ */
+ undo_fallocend = info->fallocend;
+ if (info->fallocend < end)
+ info->fallocend = end;
+
+ for (index = start; index < end; ) {
struct page *page;
/*
else
error = shmem_getpage(inode, index, &page, SGP_FALLOC);
if (error) {
+ info->fallocend = undo_fallocend;
/* Remove the !PageUptodate pages we added */
if (index > start) {
shmem_undo_range(inode,
goto undone;
}
+ index++;
+ /*
+ * Here is a more important optimization than it appears:
+ * a second SGP_FALLOC on the same huge page will clear it,
+ * making it PageUptodate and un-undoable if we fail later.
+ */
+ if (PageTransCompound(page)) {
+ index = round_up(index, HPAGE_PMD_NR);
+ /* Beware 32-bit wraparound */
+ if (!index)
+ index--;
+ }
+
/*
* Inform shmem_writepage() how far we have reached.
* No need for lock or barrier: we have the page lock.
*/
- shmem_falloc.next++;
if (!PageUptodate(page))
- shmem_falloc.nr_falloced++;
+ shmem_falloc.nr_falloced += index - shmem_falloc.next;
+ shmem_falloc.next = index;
/*
* If !PageUptodate, leave it that way so that freeable pages
if (has_transparent_hugepage() && shmem_huge > SHMEM_HUGE_DENY)
SHMEM_SB(shm_mnt->mnt_sb)->huge = shmem_huge;
else
- shmem_huge = 0; /* just in case it was patched */
+ shmem_huge = SHMEM_HUGE_NEVER; /* just in case it was patched */
#endif
return 0;
__ATTR(shmem_enabled, 0644, shmem_enabled_show, shmem_enabled_store);
#endif /* CONFIG_TRANSPARENT_HUGEPAGE && CONFIG_SYSFS */
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-bool shmem_huge_enabled(struct vm_area_struct *vma)
-{
- struct inode *inode = file_inode(vma->vm_file);
- struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
- loff_t i_size;
- pgoff_t off;
-
- if (!transhuge_vma_enabled(vma, vma->vm_flags))
- return false;
- if (shmem_huge == SHMEM_HUGE_FORCE)
- return true;
- if (shmem_huge == SHMEM_HUGE_DENY)
- return false;
- switch (sbinfo->huge) {
- case SHMEM_HUGE_NEVER:
- return false;
- case SHMEM_HUGE_ALWAYS:
- return true;
- case SHMEM_HUGE_WITHIN_SIZE:
- off = round_up(vma->vm_pgoff, HPAGE_PMD_NR);
- i_size = round_up(i_size_read(inode), PAGE_SIZE);
- if (i_size >= HPAGE_PMD_SIZE &&
- i_size >> PAGE_SHIFT >= off)
- return true;
- fallthrough;
- case SHMEM_HUGE_ADVISE:
- /* TODO: implement fadvise() hints */
- return (vma->vm_flags & VM_HUGEPAGE);
- default:
- VM_BUG_ON(1);
- return false;
- }
-}
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-
#else /* !CONFIG_SHMEM */
/*
projects / linux-2.6-microblaze.git / blobdiff