Linux-Fsdevel Archive on lore.kernel.org
 help / color / Atom feed
* [PATCH v2 00/25] Large pages in the page cache
@ 2020-02-12  4:18 Matthew Wilcox
  2020-02-12  4:18 ` [PATCH v2 01/25] mm: Use vm_fault error code directly Matthew Wilcox
                   ` (24 more replies)
  0 siblings, 25 replies; 68+ messages in thread
From: Matthew Wilcox @ 2020-02-12  4:18 UTC (permalink / raw)
  To: linux-fsdevel, linux-mm; +Cc: Matthew Wilcox (Oracle), linux-kernel

From: "Matthew Wilcox (Oracle)" <willy@infradead.org>

This patch set does not pass xfstests.  Test at your own risk.  It is
based on the readahead patchset which I posted yesterday.

The principal idea here is that a large part of the overhead in dealing
with individual pages is that there's just so darned many of them.  We
would be better off dealing with fewer, larger pages, even if they don't
get to be the size necessary for the CPU to use a larger TLB entry.

The first five patches are more or less random cleanups which I came
across while working on this patchset ... Andrew, if you want to just
take those into your tree, it'd probably be a good thing.

hpage_nr_pages() is adapted to handle arbitrary order pages.  I also
add thp_order() and thp_size() for legibility.  Then the patches tear
through the page cache fixing the places which assume pages are either
PMD_SIZE or PAGE_SIZE.  After that, I tackle the iomap buffered I/O path,
removing the assumptions of PAGE_SIZE there.

Finally, we get to actually allocating large pages in the readahead code.
We gradually grow the page size that is allocated, so we don't just
jump straight from order-0 to order-9 pages, but gradually get there
through order-2, order-4, order-6, order-8 and order-9 (on x86; other
architectures will have a different PMD_ORDER).

In some testing, I've seen the code go as far as order-6.  Right now it
falls over on an earlier xfstest when it discovers a delayed allocation
extent in an inode which is being removed at unmount.

Matthew Wilcox (Oracle) (24):
  mm: Use vm_fault error code directly
  mm: Optimise find_subpage for !THP
  mm: Use VM_BUG_ON_PAGE in clear_page_dirty_for_io
  mm: Unexport find_get_entry
  mm: Fix documentation of FGP flags
  mm: Allow hpages to be arbitrary order
  mm: Introduce thp_size
  mm: Introduce thp_order
  fs: Add a filesystem flag for large pages
  fs: Introduce i_blocks_per_page
  fs: Make page_mkwrite_check_truncate thp-aware
  mm: Add file_offset_of_ helpers
  fs: Add zero_user_large
  iomap: Support arbitrarily many blocks per page
  iomap: Support large pages in iomap_adjust_read_range
  iomap: Support large pages in read paths
  iomap: Support large pages in write paths
  iomap: Inline data shouldn't see large pages
  xfs: Support large pages
  mm: Make prep_transhuge_page return its argument
  mm: Add __page_cache_alloc_order
  mm: Allow large pages to be added to the page cache
  mm: Allow large pages to be removed from the page cache
  mm: Add large page readahead

William Kucharski (1):
  mm: Align THP mappings for non-DAX

 drivers/net/ethernet/ibm/ibmveth.c |   2 -
 drivers/nvdimm/btt.c               |   4 +-
 drivers/nvdimm/pmem.c              |   3 +-
 fs/iomap/buffered-io.c             | 111 ++++++++++++++++-------------
 fs/jfs/jfs_metapage.c              |   2 +-
 fs/xfs/xfs_aops.c                  |   4 +-
 fs/xfs/xfs_super.c                 |   2 +-
 include/linux/fs.h                 |   1 +
 include/linux/highmem.h            |  22 ++++++
 include/linux/huge_mm.h            |  21 +++---
 include/linux/mm.h                 |   2 +
 include/linux/pagemap.h            |  78 ++++++++++++++++----
 mm/filemap.c                       |  67 +++++++++++------
 mm/huge_memory.c                   |  14 ++--
 mm/internal.h                      |   2 +-
 mm/page-writeback.c                |   2 +-
 mm/page_io.c                       |   2 +-
 mm/page_vma_mapped.c               |   4 +-
 mm/readahead.c                     |  98 +++++++++++++++++++++++--
 19 files changed, 322 insertions(+), 119 deletions(-)

-- 
2.25.0


^ permalink raw reply	[flat|nested] 68+ messages in thread

end of thread, back to index

Thread overview: 68+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-02-12  4:18 [PATCH v2 00/25] Large pages in the page cache Matthew Wilcox
2020-02-12  4:18 ` [PATCH v2 01/25] mm: Use vm_fault error code directly Matthew Wilcox
2020-02-12  7:34   ` Christoph Hellwig
2020-02-12  4:18 ` [PATCH v2 02/25] mm: Optimise find_subpage for !THP Matthew Wilcox
2020-02-12  7:41   ` Christoph Hellwig
2020-02-12 13:02     ` Matthew Wilcox
2020-02-12 17:52       ` Christoph Hellwig
2020-02-13 13:50       ` Kirill A. Shutemov
2020-02-12  4:18 ` [PATCH v2 03/25] mm: Use VM_BUG_ON_PAGE in clear_page_dirty_for_io Matthew Wilcox
2020-02-12  7:38   ` Christoph Hellwig
2020-02-13 13:50   ` Kirill A. Shutemov
2020-02-12  4:18 ` [PATCH v2 04/25] mm: Unexport find_get_entry Matthew Wilcox
2020-02-12  7:37   ` Christoph Hellwig
2020-02-13 13:51   ` Kirill A. Shutemov
2020-02-12  4:18 ` [PATCH v2 05/25] mm: Fix documentation of FGP flags Matthew Wilcox
2020-02-12  7:42   ` Christoph Hellwig
2020-02-12 19:11     ` Matthew Wilcox
2020-02-13 14:00       ` Kirill A. Shutemov
2020-02-13 13:59   ` Kirill A. Shutemov
2020-02-13 14:34     ` Matthew Wilcox
2020-02-12  4:18 ` [PATCH v2 06/25] mm: Allow hpages to be arbitrary order Matthew Wilcox
2020-02-13 14:11   ` Kirill A. Shutemov
2020-02-13 14:30     ` Matthew Wilcox
2020-02-12  4:18 ` [PATCH v2 07/25] mm: Introduce thp_size Matthew Wilcox
2020-02-13 14:19   ` Kirill A. Shutemov
2020-02-12  4:18 ` [PATCH v2 08/25] mm: Introduce thp_order Matthew Wilcox
2020-02-13 14:20   ` Kirill A. Shutemov
2020-02-12  4:18 ` [PATCH v2 09/25] fs: Add a filesystem flag for large pages Matthew Wilcox
2020-02-12  7:43   ` Christoph Hellwig
2020-02-12 14:59     ` Matthew Wilcox
2020-02-12  4:18 ` [PATCH v2 10/25] fs: Introduce i_blocks_per_page Matthew Wilcox
2020-02-12  7:44   ` Christoph Hellwig
2020-02-12 15:05     ` Matthew Wilcox
2020-02-12 17:54       ` Christoph Hellwig
2020-02-13 15:40   ` Kirill A. Shutemov
2020-02-13 16:07     ` Matthew Wilcox
2020-02-12  4:18 ` [PATCH v2 11/25] fs: Make page_mkwrite_check_truncate thp-aware Matthew Wilcox
2020-02-13 15:44   ` Kirill A. Shutemov
2020-02-13 16:26     ` Matthew Wilcox
2020-02-12  4:18 ` [PATCH v2 12/25] mm: Add file_offset_of_ helpers Matthew Wilcox
2020-02-12  7:46   ` Christoph Hellwig
2020-02-12  4:18 ` [PATCH v2 13/25] fs: Add zero_user_large Matthew Wilcox
2020-02-14 13:52   ` Kirill A. Shutemov
2020-02-14 16:03     ` Matthew Wilcox
2020-02-18 14:16       ` Kirill A. Shutemov
2020-02-18 16:13         ` Matthew Wilcox
2020-02-18 17:10           ` Kirill A. Shutemov
2020-02-18 18:07             ` Matthew Wilcox
2020-02-21 12:42               ` Kirill A. Shutemov
2020-02-12  4:18 ` [PATCH v2 14/25] iomap: Support arbitrarily many blocks per page Matthew Wilcox
2020-02-12  8:05   ` Christoph Hellwig
2020-02-12  4:18 ` [PATCH v2 15/25] iomap: Support large pages in iomap_adjust_read_range Matthew Wilcox
2020-02-12  8:11   ` Christoph Hellwig
2020-02-12  4:18 ` [PATCH v2 16/25] iomap: Support large pages in read paths Matthew Wilcox
2020-02-12  8:13   ` Christoph Hellwig
2020-02-12 17:45     ` Matthew Wilcox
2020-02-12  4:18 ` [PATCH v2 17/25] iomap: Support large pages in write paths Matthew Wilcox
2020-02-12  8:17   ` Christoph Hellwig
2020-02-12  4:18 ` [PATCH v2 18/25] iomap: Inline data shouldn't see large pages Matthew Wilcox
2020-02-12  8:05   ` Christoph Hellwig
2020-02-12  4:18 ` [PATCH v2 19/25] xfs: Support " Matthew Wilcox
2020-02-12  4:18 ` [PATCH v2 20/25] mm: Make prep_transhuge_page return its argument Matthew Wilcox
2020-02-12  4:18 ` [PATCH v2 21/25] mm: Add __page_cache_alloc_order Matthew Wilcox
2020-02-12  4:18 ` [PATCH v2 22/25] mm: Allow large pages to be added to the page cache Matthew Wilcox
2020-02-12  4:18 ` [PATCH v2 23/25] mm: Allow large pages to be removed from " Matthew Wilcox
2020-02-12  4:18 ` [PATCH v2 24/25] mm: Add large page readahead Matthew Wilcox
2020-02-12  4:18 ` [PATCH v2 25/25] mm: Align THP mappings for non-DAX Matthew Wilcox
2020-02-12  7:50   ` Christoph Hellwig

Linux-Fsdevel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-fsdevel/0 linux-fsdevel/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-fsdevel linux-fsdevel/ https://lore.kernel.org/linux-fsdevel \
		linux-fsdevel@vger.kernel.org
	public-inbox-index linux-fsdevel

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-fsdevel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git