LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Yang Shi <shy828301@gmail.com>
To: Hugh Dickins <hughd@google.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	Shakeel Butt <shakeelb@google.com>,
	"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
	Miaohe Lin <linmiaohe@huawei.com>,
	Mike Kravetz <mike.kravetz@oracle.com>,
	Michal Hocko <mhocko@suse.com>, Rik van Riel <riel@surriel.com>,
	Matthew Wilcox <willy@infradead.org>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	Linux MM <linux-mm@kvack.org>
Subject: Re: [PATCH 7/9] huge tmpfs: shmem_is_huge(vma, inode, index)
Date: Tue, 17 Aug 2021 13:16:12 -0700	[thread overview]
Message-ID: <CAHbLzkrFTxLb6jmfQBvGdnOHCAc8d8Y21c0TniHGGkVZOLPpdw@mail.gmail.com> (raw)
In-Reply-To: <23a77889-2ddc-b030-75cd-44ca27fd4d1@google.com>

On Tue, Aug 17, 2021 at 1:19 AM Hugh Dickins <hughd@google.com> 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@google.com>

Reviewed-by: Yang Shi <shy828301@gmail.com>

> ---
>  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
>

  reply	other threads:[~2021-08-17 20:21 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-17  8:03 [PATCH 0/9] huge tmpfs: shmem_is_huge() fixes and cleanups Hugh Dickins
2021-08-17  8:06 ` [PATCH 1/9] huge tmpfs: fix fallocate(vanilla) advance over huge pages Hugh Dickins
2021-08-17  8:08 ` [PATCH 2/9] huge tmpfs: fix split_huge_page() after FALLOC_FL_KEEP_SIZE Hugh Dickins
2021-08-17  8:10 ` [PATCH 3/9] huge tmpfs: remove shrinklist addition from shmem_setattr() Hugh Dickins
2021-08-17  8:12 ` [PATCH 4/9] huge tmpfs: revert shmem's use of transhuge_vma_enabled() Hugh Dickins
2021-08-17  8:14 ` [PATCH 5/9] huge tmpfs: move shmem_huge_enabled() upwards Hugh Dickins
2021-08-17  8:17 ` [PATCH 6/9] huge tmpfs: SGP_NOALLOC to stop collapse_file() on race Hugh Dickins
2021-08-17 20:14   ` Yang Shi
2021-08-17  8:19 ` [PATCH 7/9] huge tmpfs: shmem_is_huge(vma, inode, index) Hugh Dickins
2021-08-17 20:16   ` Yang Shi [this message]
2021-08-17  8:22 ` [PATCH 8/9] huge tmpfs: decide stat.st_blksize by shmem_is_huge() Hugh Dickins
2021-08-17  8:28 ` [PATCH 9/9] shmem: shmem_writepage() split unlikely i915 THP Hugh Dickins

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=CAHbLzkrFTxLb6jmfQBvGdnOHCAc8d8Y21c0TniHGGkVZOLPpdw@mail.gmail.com \
    --to=shy828301@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=hughd@google.com \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=linmiaohe@huawei.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@suse.com \
    --cc=mike.kravetz@oracle.com \
    --cc=riel@surriel.com \
    --cc=shakeelb@google.com \
    --cc=willy@infradead.org \
    --subject='Re: [PATCH 7/9] huge tmpfs: shmem_is_huge(vma, inode, index)' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).