From: "Kirill A. Shutemov" <kirill@shutemov.name>
To: Matthew Wilcox <willy@linux.intel.com>
Cc: Matthew Wilcox <matthew.r.wilcox@intel.com>,
linux-fsdevel@vger.kernel.org, linux-mm@kvack.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH v8 05/22] Add vm_replace_mixed()
Date: Wed, 23 Jul 2014 17:20:48 +0300 [thread overview]
Message-ID: <20140723142048.GA11963@node.dhcp.inet.fi> (raw)
In-Reply-To: <20140723135221.GA6754@linux.intel.com>
On Wed, Jul 23, 2014 at 09:52:22AM -0400, Matthew Wilcox wrote:
> On Wed, Jul 23, 2014 at 02:45:40PM +0300, Kirill A. Shutemov wrote:
> > On Tue, Jul 22, 2014 at 03:47:53PM -0400, Matthew Wilcox wrote:
> > > From: Matthew Wilcox <willy@linux.intel.com>
> > >
> > > vm_insert_mixed() will fail if there is already a valid PTE at that
> > > location. The DAX code would rather replace the previous value with
> > > the new PTE.
>
> > > @@ -1492,8 +1492,12 @@ static int insert_page(struct vm_area_struct *vma, unsigned long addr,
> > > if (!pte)
> > > goto out;
> > > retval = -EBUSY;
> > > - if (!pte_none(*pte))
> > > - goto out_unlock;
> > > + if (!pte_none(*pte)) {
> > > + if (!replace)
> > > + goto out_unlock;
> > > + VM_BUG_ON(!mutex_is_locked(&vma->vm_file->f_mapping->i_mmap_mutex));
> > > + zap_page_range_single(vma, addr, PAGE_SIZE, NULL);
> >
> > zap_page_range_single() takes ptl by itself in zap_pte_range(). It's not
> > going to work.
>
> I have a test program that exercises this path ... it seems to work!
> Following the code, I don't understand why it does. Maybe it's not
> exercising this path after all? I've attached the program (so that I
> have an "oh, duh" moment about 5 seconds after sending the email).
See below.
>
> > And zap_page_range*() is pretty heavy weapon to shoot down one pte, which
> > we already have pointer to. Why?
>
> I'd love to use a lighter-weight weapon! What would you recommend using,
> zap_pte_range()?
The most straight-forward way: extract body of pte cycle from
zap_pte_range() to separate function -- zap_pte() -- and use it.
> #include <stdio.h>
> #include <stdlib.h>
> #include <string.h>
> #include <sys/types.h>
> #include <sys/mman.h>
> #include <fcntl.h>
> #include <unistd.h>
> #include <errno.h>
>
> int
> main(int argc, char *argv[])
> {
> int fd;
> void *addr;
> char buf[4096];
>
> if (argc != 2) {
> fprintf(stderr, "usage: %s filename\n", argv[0]);
> exit(1);
> }
>
> if ((fd = open(argv[1], O_CREAT|O_RDWR, 0666)) < 0) {
> perror(argv[1]);
> exit(1);
> }
>
> if (ftruncate(fd, 4096) < 0) {
Shouldn't this be ftruncate(fd, 0)? Otherwise the memcpy() below will
fault in page from backing storage, not hole and write will not replace
anything.
> perror("ftruncate");
> exit(1);
> }
>
> if ((addr = mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_SHARED,
> fd, 0)) == MAP_FAILED) {
> perror("mmap");
> exit(1);
> }
>
> close(fd);
>
> /* first read */
> memcpy(buf, addr, 4096);
>
> /* now write a bit */
> memcpy(addr, buf, 8);
>
> printf("%s: test passed.\n", argv[0]);
> exit(0);
> }
--
Kirill A. Shutemov
next prev parent reply other threads:[~2014-07-23 14:21 UTC|newest]
Thread overview: 61+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-07-22 19:47 [PATCH v8 00/22] Support ext4 on NV-DIMMs Matthew Wilcox
2014-07-22 19:47 ` [PATCH v8 01/22] Fix XIP fault vs truncate race Matthew Wilcox
2014-07-23 11:21 ` Kirill A. Shutemov
2014-07-22 19:47 ` [PATCH v8 02/22] Allow page fault handlers to perform the COW Matthew Wilcox
2014-07-23 11:23 ` Kirill A. Shutemov
2014-07-22 19:47 ` [PATCH v8 03/22] axonram: Fix bug in direct_access Matthew Wilcox
2014-07-23 11:24 ` Kirill A. Shutemov
2014-07-22 19:47 ` [PATCH v8 04/22] Change direct_access calling convention Matthew Wilcox
2014-07-30 16:03 ` Boaz Harrosh
2014-07-30 16:12 ` Boaz Harrosh
2014-07-30 20:34 ` Matthew Wilcox
2014-07-31 10:16 ` Boaz Harrosh
2014-07-30 19:45 ` Matthew Wilcox
2014-07-31 10:11 ` Boaz Harrosh
2014-07-31 14:13 ` Matthew Wilcox
2014-07-31 15:28 ` Boaz Harrosh
2014-07-31 17:19 ` Matthew Wilcox
2014-07-31 18:04 ` Boaz Harrosh
2014-07-31 20:30 ` Zwisler, Ross
2014-08-01 18:45 ` Zwisler, Ross
2014-07-22 19:47 ` [PATCH v8 05/22] Add vm_replace_mixed() Matthew Wilcox
2014-07-23 9:10 ` Jan Kara
2014-07-23 11:45 ` Kirill A. Shutemov
2014-07-23 13:52 ` Matthew Wilcox
2014-07-23 14:20 ` Kirill A. Shutemov [this message]
2014-07-23 14:27 ` Matthew Wilcox
2014-07-23 15:55 ` Kirill A. Shutemov
2014-07-24 1:36 ` Zhang, Tianfei
2014-07-25 19:44 ` Matthew Wilcox
2014-07-28 13:25 ` Kirill A. Shutemov
2014-07-29 1:55 ` Zhang, Tianfei
2014-07-22 19:47 ` [PATCH v8 06/22] Introduce IS_DAX(inode) Matthew Wilcox
2014-07-22 19:47 ` [PATCH v8 07/22] Add copy_to_iter(), copy_from_iter() and iov_iter_zero() Matthew Wilcox
2014-07-22 19:47 ` [PATCH v8 08/22] Replace XIP read and write with DAX I/O Matthew Wilcox
2014-07-22 19:47 ` [PATCH v8 09/22] Replace ext2_clear_xip_target with dax_clear_blocks Matthew Wilcox
2014-07-22 19:47 ` [PATCH v8 10/22] Replace the XIP page fault handler with the DAX page fault handler Matthew Wilcox
2014-07-23 12:10 ` Kirill A. Shutemov
2014-07-23 13:55 ` Matthew Wilcox
2014-07-23 14:10 ` [PATCH v8 00/22] Support ext4 on NV-DIMMs Howard Chu
2014-07-23 14:34 ` Matthew Wilcox
2014-07-23 15:28 ` Howard Chu
2014-07-23 20:55 ` Theodore Ts'o
2014-07-23 16:57 ` [PATCH v8 10/22] Replace the XIP page fault handler with the DAX page fault handler Boaz Harrosh
2014-07-23 19:57 ` Matthew Wilcox
2014-07-22 19:47 ` [PATCH v8 11/22] Replace xip_truncate_page with dax_truncate_page Matthew Wilcox
2014-07-22 19:48 ` [PATCH v8 12/22] Replace XIP documentation with DAX documentation Matthew Wilcox
2014-07-22 19:48 ` [PATCH v8 13/22] Remove get_xip_mem Matthew Wilcox
2014-07-22 19:48 ` [PATCH v8 14/22] ext2: Remove ext2_xip_verify_sb() Matthew Wilcox
2014-07-22 19:48 ` [PATCH v8 15/22] ext2: Remove ext2_use_xip Matthew Wilcox
2014-07-22 19:48 ` [PATCH v8 16/22] ext2: Remove xip.c and xip.h Matthew Wilcox
2014-07-22 19:48 ` [PATCH v8 17/22] Remove CONFIG_EXT2_FS_XIP and rename CONFIG_FS_XIP to CONFIG_FS_DAX Matthew Wilcox
2014-07-22 19:48 ` [PATCH v8 18/22] ext2: Remove ext2_aops_xip Matthew Wilcox
2014-07-22 19:48 ` [PATCH v8 19/22] Get rid of most mentions of XIP in ext2 Matthew Wilcox
2014-07-22 19:48 ` [PATCH v8 20/22] xip: Add xip_zero_page_range Matthew Wilcox
2014-07-22 19:48 ` [PATCH v8 21/22] ext4: Add DAX functionality Matthew Wilcox
2014-07-22 19:48 ` [PATCH v8 22/22] brd: Rename XIP to DAX Matthew Wilcox
2014-07-23 12:30 ` [PATCH v8 00/22] Support ext4 on NV-DIMMs Kirill A. Shutemov
2014-07-23 13:59 ` Matthew Wilcox
2014-07-23 15:58 ` Boaz Harrosh
2014-07-23 19:50 ` Matthew Wilcox
2014-07-24 18:51 ` Ross Zwisler
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=20140723142048.GA11963@node.dhcp.inet.fi \
--to=kirill@shutemov.name \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=matthew.r.wilcox@intel.com \
--cc=willy@linux.intel.com \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).