| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <8EF5F030-FA56-4124-B3D1-D4B1A536DD7F@oracle.com>
Date: Tue, 7 Jun 2022 12:01:32 +0000
From: William Kucharski <william.kucharski@...cle.com>
To: Alistair Popple <apopple@...dia.com>
CC: "akpm@...ux-foundation.org" <akpm@...ux-foundation.org>,
"linux-mm@...ck.org" <linux-mm@...ck.org>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
"willy@...radead.org" <willy@...radead.org>
Subject: Re: [PATCH] mm/filemap.c: Always read one page in
do_sync_mmap_readahead()
Looks good, a nice cleanup.
Reviewed-by: William Kucharski <william.kucharski@...cle.com>
> On Jun 7, 2022, at 2:37 AM, Alistair Popple <apopple@...dia.com> wrote:
>
> filemap_fault() calls do_sync_mmap_readahead() to read pages when no
> page is found in the page cache. However do_sync_mmap_readahead() will
> not actually read any pages if VM_RAND_READ is specified or if there
> have been a lot of page cache misses.
>
> This means filemap_fault() will see a folio that is not up-to-date which
> is treated as an IO error. The IO error handling path happens to make
> VM_RAND_READ work as expected though because it retries reading the
> page.
>
> However it would be cleaner if this was handled in
> do_sync_mmap_readahead() to match what is done for VM_HUGEPAGE. Also as
> do_sync_mmap_readahead() adds the newly allocated folio to the pagecache
> and unlocks it this clean-up also allows the FGP_FOR_MMAP flag to be
> removed.
>
> Signed-off-by: Alistair Popple <apopple@...dia.com>
> Suggested-by: Matthew Wilcox <willy@...radead.org>
> ---
> include/linux/pagemap.h | 7 +++---
> mm/filemap.c | 47 +++++++++++++----------------------------
> 2 files changed, 18 insertions(+), 36 deletions(-)
>
> diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
> index 993994cd943a..e0e0f5e7d4a0 100644
> --- a/include/linux/pagemap.h
> +++ b/include/linux/pagemap.h
> @@ -505,10 +505,9 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping,
> #define FGP_WRITE 0x00000008
> #define FGP_NOFS 0x00000010
> #define FGP_NOWAIT 0x00000020
> -#define FGP_FOR_MMAP 0x00000040
> -#define FGP_HEAD 0x00000080
> -#define FGP_ENTRY 0x00000100
> -#define FGP_STABLE 0x00000200
> +#define FGP_HEAD 0x00000040
> +#define FGP_ENTRY 0x00000080
> +#define FGP_STABLE 0x00000100
>
> struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
> int fgp_flags, gfp_t gfp);
> diff --git a/mm/filemap.c b/mm/filemap.c
> index 9a1eef6c5d35..15d7e0a0ad4b 100644
> --- a/mm/filemap.c
> +++ b/mm/filemap.c
> @@ -1922,9 +1922,6 @@ static void *mapping_get_entry(struct address_space *mapping, pgoff_t index)
> * * %FGP_CREAT - If no page is present then a new page is allocated using
> * @gfp and added to the page cache and the VM's LRU list.
> * The page is returned locked and with an increased refcount.
> - * * %FGP_FOR_MMAP - The caller wants to do its own locking dance if the
> - * page is already in cache. If the page was allocated, unlock it before
> - * returning so the caller can do the same dance.
> * * %FGP_WRITE - The page will be written to by the caller.
> * * %FGP_NOFS - __GFP_FS will get cleared in gfp.
> * * %FGP_NOWAIT - Don't get blocked by page lock.
> @@ -1993,7 +1990,7 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
> if (!folio)
> return NULL;
>
> - if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP))))
> + if (WARN_ON_ONCE(!(fgp_flags & FGP_LOCK)))
> fgp_flags |= FGP_LOCK;
>
> /* Init accessed so avoid atomic mark_page_accessed later */
> @@ -2007,13 +2004,6 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
> if (err == -EEXIST)
> goto repeat;
> }
> -
> - /*
> - * filemap_add_folio locks the page, and for mmap
> - * we expect an unlocked page.
> - */
> - if (folio && (fgp_flags & FGP_FOR_MMAP))
> - folio_unlock(folio);
> }
>
> return folio;
> @@ -3011,14 +3001,8 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
> }
> #endif
>
> - /* If we don't want any read-ahead, don't bother */
> - if (vmf->vma->vm_flags & VM_RAND_READ)
> - return fpin;
> - if (!ra->ra_pages)
> - return fpin;
> -
> + fpin = maybe_unlock_mmap_for_io(vmf, fpin);
> if (vmf->vma->vm_flags & VM_SEQ_READ) {
> - fpin = maybe_unlock_mmap_for_io(vmf, fpin);
> page_cache_sync_ra(&ractl, ra->ra_pages);
> return fpin;
> }
> @@ -3029,19 +3013,20 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
> WRITE_ONCE(ra->mmap_miss, ++mmap_miss);
>
> /*
> - * Do we miss much more than hit in this file? If so,
> - * stop bothering with read-ahead. It will only hurt.
> + * mmap read-around. If we don't want any read-ahead or if we miss more
> + * than we hit don't bother with read-ahead and just read a single page.
> */
> - if (mmap_miss > MMAP_LOTSAMISS)
> - return fpin;
> + if ((vmf->vma->vm_flags & VM_RAND_READ) ||
> + !ra->ra_pages || mmap_miss > MMAP_LOTSAMISS) {
> + ra->start = vmf->pgoff;
> + ra->size = 1;
> + ra->async_size = 0;
> + } else {
> + ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2);
> + ra->size = ra->ra_pages;
> + ra->async_size = ra->ra_pages / 4;
> + }
>
> - /*
> - * mmap read-around
> - */
> - fpin = maybe_unlock_mmap_for_io(vmf, fpin);
> - ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2);
> - ra->size = ra->ra_pages;
> - ra->async_size = ra->ra_pages / 4;
> ractl._index = ra->start;
> page_cache_ra_order(&ractl, ra, 0);
> return fpin;
> @@ -3145,9 +3130,7 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
> filemap_invalidate_lock_shared(mapping);
> mapping_locked = true;
> }
> - folio = __filemap_get_folio(mapping, index,
> - FGP_CREAT|FGP_FOR_MMAP,
> - vmf->gfp_mask);
> + folio = filemap_get_folio(mapping, index);
> if (!folio) {
> if (fpin)
> goto out_retry;
> --
> 2.35.1
>
>
Powered by blists - more mailing lists