[v8,00/10] iov_iter: Improve page extraction (pin or just list)

  Hi Al, Christoph,

Here are patches to provide support for extracting pages from an iov_iter
and to use this in the extraction functions in the block layer bio code.

The patches make the following changes:

 (1) Add a function, iov_iter_extract_pages() to replace
     iov_iter_get_pages*() that gets refs, pins or just lists the pages as
     appropriate to the iterator type.

     Add a function, iov_iter_extract_mode() that will indicate from the
     iterator type how the cleanup is to be performed, returning FOLL_PIN
     or 0.

 (2) Add a function, folio_put_unpin(), and a wrapper, page_put_unpin(),
     that take a page and the return from iov_iter_extract_mode() and do
     the right thing to clean up the page.

 (3) Make the bio struct carry a pair of flags to indicate the cleanup
     mode.  BIO_NO_PAGE_REF is replaced with BIO_PAGE_REFFED (equivalent to
     FOLL_GET) and BIO_PAGE_PINNED (equivalent to BIO_PAGE_PINNED) is
     added.

 (4) Add a function, bio_release_page(), to release a page appropriately to
     the cleanup mode indicated by the BIO_PAGE_* flags.

 (5) Make the iter-to-bio code use iov_iter_extract_pages() to retain the
     pages appropriately and clean them up later.

 (6) Fix bio_flagged() so that it doesn't prevent a gcc optimisation.

 (7) Renumber FOLL_PIN and FOLL_GET down so that they're at bits 0 and 1
     and coincident with BIO_PAGE_PINNED and BIO_PAGE_REFFED.  The compiler
     can then optimise on that.  Also, it's probably going to be necessary
     to embed these in the page pointer in sk_buff fragments.  This patch
     can go independently through the mm tree.

I've pushed the patches here also:

	https://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs.git/log/?h=iov-extract

David

Changes:
========
ver #8)
 - Import Christoph Hellwig's changes.
   - Split the conversion-to-extraction patch.
   - Drop the extract_flags arg from iov_iter_extract_mode().
   - Don't default bios to BIO_PAGE_REFFED, but set explicitly.
 - Switch FOLL_PIN and FOLL_GET when renumbering so PIN is at bit 0.
 - Switch BIO_PAGE_PINNED and BIO_PAGE_REFFED so PINNED is at bit 0.
 - We should always be using FOLL_PIN (not FOLL_GET) for DIO, so adjust the
   patches for that.

ver #7)
 - For now, drop the parts to pass the I/O direction to iov_iter_*pages*()
   as it turned out to be a lot more complicated, with places not setting
   IOCB_WRITE when they should, for example.
 - Drop all the patches that changed things other then the block layer's
   bio handling.  The netfslib and cifs changes can go into a separate
   patchset.
 - Add support for extracting pages from KVEC-type iterators.
 - When extracting from BVEC/KVEC, skip over empty vecs at the front.

ver #6)
 - Fix write() syscall and co. not setting IOCB_WRITE.
 - Added iocb_is_read() and iocb_is_write() to check IOCB_WRITE.
 - Use op_is_write() in bio_copy_user_iov().
 - Drop the iterator direction checks from smbd_recv().
 - Define FOLL_SOURCE_BUF and FOLL_DEST_BUF and pass them in as part of
   gup_flags to iov_iter_get/extract_pages*().
 - Replace iov_iter_get_pages*2() with iov_iter_get_pages*() and remove.
 - Add back the function to indicate the cleanup mode.
 - Drop the cleanup_mode return arg to iov_iter_extract_pages().
 - Provide a helper to clean up a page.
 - Renumbered FOLL_GET and FOLL_PIN and made BIO_PAGE_REFFED/PINNED have
   the same numerical values, enforced with an assertion.
 - Converted AF_ALG, SCSI vhost, generic DIO, FUSE, splice to pipe, 9P and
   NFS.
 - Added in the patches to make CIFS do top-to-bottom iterators and use
   various of the added extraction functions.
 - Added a pair of work-in-progess patches to make sk_buff fragments store
   FOLL_GET and FOLL_PIN.

ver #5)
 - Replace BIO_NO_PAGE_REF with BIO_PAGE_REFFED and split into own patch.
 - Transcribe FOLL_GET/PIN into BIO_PAGE_REFFED/PINNED flags.
 - Add patch to allow bio_flagged() to be combined by gcc.

ver #4)
 - Drop the patch to move the FOLL_* flags to linux/mm_types.h as they're
   no longer referenced by linux/uio.h.
 - Add ITER_SOURCE/DEST cleanup patches.
 - Make iov_iter/netfslib iter extraction patches use ITER_SOURCE/DEST.
 - Allow additional gup_flags to be passed into iov_iter_extract_pages().
 - Add struct bio patch.

ver #3)
 - Switch to using EXPORT_SYMBOL_GPL to prevent indirect 3rd-party access
   to get/pin_user_pages_fast()[1].

ver #2)
 - Rolled the extraction cleanup mode query function into the extraction
   function, returning the indication through the argument list.
 - Fixed patch 4 (extract to scatterlist) to actually use the new
   extraction API.

Link: https://lore.kernel.org/r/Y3zFzdWnWlEJ8X8/@infradead.org/ [1]
Link: https://lore.kernel.org/r/166697254399.61150.1256557652599252121.stgit@warthog.procyon.org.uk/ # rfc
Link: https://lore.kernel.org/r/166722777223.2555743.162508599131141451.stgit@warthog.procyon.org.uk/ # rfc
Link: https://lore.kernel.org/r/166732024173.3186319.18204305072070871546.stgit@warthog.procyon.org.uk/ # rfc
Link: https://lore.kernel.org/r/166869687556.3723671.10061142538708346995.stgit@warthog.procyon.org.uk/ # rfc
Link: https://lore.kernel.org/r/166920902005.1461876.2786264600108839814.stgit@warthog.procyon.org.uk/ # v2
Link: https://lore.kernel.org/r/166997419665.9475.15014699817597102032.stgit@warthog.procyon.org.uk/ # v3
Link: https://lore.kernel.org/r/167305160937.1521586.133299343565358971.stgit@warthog.procyon.org.uk/ # v4
Link: https://lore.kernel.org/r/167344725490.2425628.13771289553670112965.stgit@warthog.procyon.org.uk/ # v5
Link: https://lore.kernel.org/r/167391047703.2311931.8115712773222260073.stgit@warthog.procyon.org.uk/ # v6
Link: https://lore.kernel.org/r/20230120175556.3556978-1-dhowells@redhat.com/ # v7

Christoph Hellwig (2):
  iomap: don't get an reference on ZERO_PAGE for direct I/O block
    zeroing
  block: Rename BIO_NO_PAGE_REF to BIO_PAGE_REFFED and invert the
    meaning

David Howells (8):
  iov_iter: Define flags to qualify page extraction.
  iov_iter: Add a function to extract a page list from an iterator
  mm: Provide a helper to drop a pin/ref on a page
  block: Fix bio_flagged() so that gcc can better optimise it
  block: Switch to pinning pages.
  block: Convert bio_iov_iter_get_pages to use iov_iter_extract_pages
  block: convert bio_map_user_iov to use iov_iter_extract_pages
  mm: Renumber FOLL_PIN and FOLL_GET down

 block/bio.c               |  33 ++--
 block/blk-map.c           |  25 ++-
 block/blk.h               |  28 ++++
 fs/direct-io.c            |   2 +
 fs/iomap/direct-io.c      |   1 -
 include/linux/bio.h       |   5 +-
 include/linux/blk_types.h |   3 +-
 include/linux/mm.h        |  35 ++--
 include/linux/uio.h       |  29 +++-
 lib/iov_iter.c            | 334 +++++++++++++++++++++++++++++++++++++-
 mm/gup.c                  |  22 +++
 11 files changed, 461 insertions(+), 56 deletions(-)
  

On 1/23/23 09:29, David Howells wrote:
> Hi Al, Christoph,
> 
> Here are patches to provide support for extracting pages from an iov_iter
> and to use this in the extraction functions in the block layer bio code.
> 

Hi David,

It's great to see this series. I attempted this a few times but got
caught in a loop of "don't quite see all the pieces, but it almost makes
sense...Al Viro has spotted major problems (again)...squirrel!"; and
repeat. :)

I saw your earlier versions go by and expected that they would end up
being an iov_iter prerequisite to getting Direct IO converted over to
FOLL_PIN. But now it looks like you are actually doing the conversion as
well! That's really excellent.

I've made a first pass through the series and have some minor notes
that I'll send out shortly, but it looks nice overall.

thanks,
  

On 23.01.23 18:29, David Howells wrote:
> Hi Al, Christoph,
> 
> Here are patches to provide support for extracting pages from an iov_iter
> and to use this in the extraction functions in the block layer bio code.
> 
> The patches make the following changes:
> 
>   (1) Add a function, iov_iter_extract_pages() to replace
>       iov_iter_get_pages*() that gets refs, pins or just lists the pages as
>       appropriate to the iterator type.
> 
>       Add a function, iov_iter_extract_mode() that will indicate from the
>       iterator type how the cleanup is to be performed, returning FOLL_PIN
>       or 0.
> 
>   (2) Add a function, folio_put_unpin(), and a wrapper, page_put_unpin(),
>       that take a page and the return from iov_iter_extract_mode() and do
>       the right thing to clean up the page.
> 
>   (3) Make the bio struct carry a pair of flags to indicate the cleanup
>       mode.  BIO_NO_PAGE_REF is replaced with BIO_PAGE_REFFED (equivalent to
>       FOLL_GET) and BIO_PAGE_PINNED (equivalent to BIO_PAGE_PINNED) is
>       added.
> 
>   (4) Add a function, bio_release_page(), to release a page appropriately to
>       the cleanup mode indicated by the BIO_PAGE_* flags.
> 
>   (5) Make the iter-to-bio code use iov_iter_extract_pages() to retain the
>       pages appropriately and clean them up later.
> 
>   (6) Fix bio_flagged() so that it doesn't prevent a gcc optimisation.
> 
>   (7) Renumber FOLL_PIN and FOLL_GET down so that they're at bits 0 and 1
>       and coincident with BIO_PAGE_PINNED and BIO_PAGE_REFFED.  The compiler
>       can then optimise on that.  Also, it's probably going to be necessary
>       to embed these in the page pointer in sk_buff fragments.  This patch
>       can go independently through the mm tree.

^ I feel like some of that information might be stale now that you're 
only using FOLL_PIN.

> 
> I've pushed the patches here also:
> 
> 	https://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs.git/log/?h=iov-extract

I gave this a quick test and it indeed fixes the last remaining test 
case of my O_DIRECT+fork tests [1] that was still failing on upstream 
(test3).


Once landed upstream, if we feel confident enough (I tend to), we could 
adjust the open() man page to state that O_DIRECT can now be run 
concurrently with fork(). Especially, the following documentation might 
be adjusted:

"O_DIRECT  I/Os  should  never  be run concurrently with the fork(2) 
system call, if the memory buffer is a private mapping (i.e., any 
mapping created with the mmap(2) MAP_PRIVATE flag; this includes  memory 
  allocated  on  the  heap  and statically allocated buffers).  Any such 
I/Os, whether submitted via an asynchronous I/O interface or from 
another thread in the  process, should  be completed before fork(2) is 
called.  Failure to do so can result in data corruption and undefined 
behavior in parent and child processes."


This series does not yet fix vmsplice()+hugetlb ... simply because your 
series does not mess with the vmsplice() implementation I assume ;) Once 
vmsplice() uses FOLL_PIN, all cow tests should be passing as well. Easy 
to test:

$ cd tools/testing/selftests/vm/
$ echo 2 > /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages
$ echo 2 > /sys/kernel/mm/hugepages/hugepages-1048576kB/nr_hugepages
$ ./cow
...
Bail out! 8 out of 190 tests failed
# Totals: pass:181 fail:8 xfail:0 xpass:0 skip:1 error:0


[1] https://gitlab.com/davidhildenbrand/o_direct_fork_tests
  

On Tue, Jan 24, 2023 at 01:44:21PM +0100, David Hildenbrand wrote:
> Once landed upstream, if we feel confident enough (I tend to), we could
> adjust the open() man page to state that O_DIRECT can now be run
> concurrently with fork(). Especially, the following documentation might be
> adjusted:

Note that while these series coverts the two most commonly used
O_DIRECT implementations, there are various others ones that do not
pin the pages yet.
  

On 24.01.23 14:16, Christoph Hellwig wrote:
> On Tue, Jan 24, 2023 at 01:44:21PM +0100, David Hildenbrand wrote:
>> Once landed upstream, if we feel confident enough (I tend to), we could
>> adjust the open() man page to state that O_DIRECT can now be run
>> concurrently with fork(). Especially, the following documentation might be
>> adjusted:
> 
> Note that while these series coverts the two most commonly used
> O_DIRECT implementations, there are various others ones that do not
> pin the pages yet.

Thanks for the info ... I assume these are then for other filesystems, 
right? (such that we could adjust the tests to exercise these as well)

... do we have a list (or is it easy to make one)? :)
  

On Tue, Jan 24, 2023 at 02:22:36PM +0100, David Hildenbrand wrote:
> > Note that while these series coverts the two most commonly used
> > O_DIRECT implementations, there are various others ones that do not
> > pin the pages yet.
> 
> Thanks for the info ... I assume these are then for other filesystems,
> right? (such that we could adjust the tests to exercise these as well)

Yes.  There's the fs/direct-io.c code still used by a few block based
file systems, and then all the not block based file systems as well
(e.g. NFS, cifs).

> ... do we have a list (or is it easy to make one)? :)

fs/direct-io.c is easy, just grep for blockdev_direct_IO.

The others are more complicated to find, but a grep for
iov_iter_get_pages2 and iov_iter_get_pages_alloc2 in fs/ should be a
good approximation.
  

On 24.01.23 14:32, Christoph Hellwig wrote:
> On Tue, Jan 24, 2023 at 02:22:36PM +0100, David Hildenbrand wrote:
>>> Note that while these series coverts the two most commonly used
>>> O_DIRECT implementations, there are various others ones that do not
>>> pin the pages yet.
>>
>> Thanks for the info ... I assume these are then for other filesystems,
>> right? (such that we could adjust the tests to exercise these as well)
> 
> Yes.  There's the fs/direct-io.c code still used by a few block based
> file systems, and then all the not block based file systems as well
> (e.g. NFS, cifs).
> 
>> ... do we have a list (or is it easy to make one)? :)
> 
> fs/direct-io.c is easy, just grep for blockdev_direct_IO.
> 
> The others are more complicated to find, but a grep for
> iov_iter_get_pages2 and iov_iter_get_pages_alloc2 in fs/ should be a
> good approximation.

Right, iov_iter_get_pages2() includes vmsplice() that still needs love. 
Thanks!
  

If you look here:

	https://lore.kernel.org/r/167391047703.2311931.8115712773222260073.stgit@warthog.procyon.org.uk/

you can see additional patches fixing other users.  Christoph asked if I could
pare down the patchset to the minimum to fix the bio case for the moment.

It will be easier to do the others once iov_iter_extract_pages() is upstream
as the individual bits can go via their respective maintainers.

However, I do want to see about adding cifs iteratorisation in this merge
window also, which also depends on the iov_iter_extract_pages() function being
added.

David