On Tue, Aug 17, 2021 at 1:19 AM Hugh Dickins <hughd@xxxxxxxxxx> wrote:
>
> Extend shmem_huge_enabled(vma) to shmem_is_huge(vma, inode, index), so
> that a consistent set of checks can be applied, even when the inode is
> accessed through read/write syscalls (with NULL vma) instead of mmaps
> (the index argument is seldom of interest, but required by mount option
> "huge=within_size"). Clean up and rearrange the checks a little.
>
> This then replaces the checks which shmem_fault() and shmem_getpage_gfp()
> were making, and eliminates the SGP_HUGE and SGP_NOHUGE modes.
>
> Replace a couple of 0s by explicit SHMEM_HUGE_NEVERs; and replace the
> obscure !shmem_mapping() symlink check by explicit S_ISLNK() - nothing
> else needs that symlink check, so leave it there in shmem_getpage_gfp().
>
> Signed-off-by: Hugh Dickins <hughd@xxxxxxxxxx>
Reviewed-by: Yang Shi <shy828301@xxxxxxxxx>
> ---
> include/linux/shmem_fs.h | 9 +++--
> mm/shmem.c | 84 ++++++++++++----------------------------
> 2 files changed, 31 insertions(+), 62 deletions(-)
>
> diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
> index 7d97b15a2f7a..60c6e4eac275 100644
> --- a/include/linux/shmem_fs.h
> +++ b/include/linux/shmem_fs.h
> @@ -86,7 +86,12 @@ extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end);
> extern int shmem_unuse(unsigned int type, bool frontswap,
> unsigned long *fs_pages_to_unuse);
>
> -extern bool shmem_huge_enabled(struct vm_area_struct *vma);
> +extern bool shmem_is_huge(struct vm_area_struct *vma,
> + struct inode *inode, pgoff_t index);
> +static inline bool shmem_huge_enabled(struct vm_area_struct *vma)
> +{
> + return shmem_is_huge(vma, file_inode(vma->vm_file), vma->vm_pgoff);
> +}
> extern unsigned long shmem_swap_usage(struct vm_area_struct *vma);
> extern unsigned long shmem_partial_swap_usage(struct address_space *mapping,
> pgoff_t start, pgoff_t end);
> @@ -96,8 +101,6 @@ enum sgp_type {
> SGP_READ, /* don't exceed i_size, don't allocate page */
> SGP_NOALLOC, /* similar, but fail on hole or use fallocated page */
> SGP_CACHE, /* don't exceed i_size, may allocate page */
> - SGP_NOHUGE, /* like SGP_CACHE, but no huge pages */
> - SGP_HUGE, /* like SGP_CACHE, huge pages preferred */
> SGP_WRITE, /* may exceed i_size, may allocate !Uptodate page */
> SGP_FALLOC, /* like SGP_WRITE, but make existing page Uptodate */
> };
> diff --git a/mm/shmem.c b/mm/shmem.c
> index 226ac3a911e9..56ee56b1cab6 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -474,39 +474,35 @@ static bool shmem_confirm_swap(struct address_space *mapping,
> #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_huge_enabled(struct vm_area_struct *vma)
> +bool shmem_is_huge(struct vm_area_struct *vma,
> + struct inode *inode, pgoff_t index)
> {
> - 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 ((vma->vm_flags & VM_NOHUGEPAGE) ||
> - test_bit(MMF_DISABLE_THP, &vma->vm_mm->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:
> + 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:
> - off = round_up(vma->vm_pgoff, HPAGE_PMD_NR);
> + 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 >= off)
> + if (i_size >= HPAGE_PMD_SIZE && (i_size >> PAGE_SHIFT) >= index)
> return true;
> fallthrough;
> case SHMEM_HUGE_ADVISE:
> - /* TODO: implement fadvise() hints */
> - return (vma->vm_flags & VM_HUGEPAGE);
> + if (vma && (vma->vm_flags & VM_HUGEPAGE))
> + return true;
> + fallthrough;
> default:
> - VM_BUG_ON(1);
> return false;
> }
> }
> @@ -680,6 +676,12 @@ static long shmem_unused_huge_count(struct super_block *sb,
>
> #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)
> {
> @@ -1829,7 +1831,6 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t 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;
> @@ -1838,8 +1839,6 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
>
> 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)) {
> @@ -1903,36 +1902,12 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
> 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);
> @@ -2088,7 +2063,6 @@ static vm_fault_t shmem_fault(struct vm_fault *vmf)
> 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;
>
> @@ -2151,15 +2125,7 @@ static vm_fault_t shmem_fault(struct vm_fault *vmf)
> 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);
> @@ -3966,7 +3932,7 @@ int __init shmem_init(void)
> 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;
>
> --
> 2.26.2
>
