[v13,000/137] Memory folios

Message ID	20210712030701.4000097-1-willy@infradead.org (mailing list archive)
Headers	show Return-Path: <SRS0=Bpcp=ME=kvack.org=owner-linux-mm@kernel.org> DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 7B85F60200 From: "Matthew Wilcox (Oracle)" <willy@infradead.org> To: linux-kernel@vger.kernel.org Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>, linux-mm@kvack.org, linux-fsdevel@vger.kernel.org Subject: [PATCH v13 000/137] Memory folios Date: Mon, 12 Jul 2021 04:04:44 +0100 Message-Id: <20210712030701.4000097-1-willy@infradead.org> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Sender: owner-linux-mm@kvack.org Precedence: bulk
Series	Memory folios \| expand [v13,000/137] Memory folios [v13,001/137] mm: Convert get_page_unless_zero() to return bool [v13,002/137] mm: Introduce struct folio [v13,003/137] mm: Add folio_pgdat(), folio_zone() and folio_zonenum() [v13,004/137] mm/vmstat: Add functions to account folio statistics [v13,005/137] mm/debug: Add VM_BUG_ON_FOLIO() and VM_WARN_ON_ONCE_FOLIO() [v13,006/137] mm: Add folio reference count functions [v13,007/137] mm: Add folio_put() [v13,008/137] mm: Add folio_get() [v13,009/137] mm: Add folio_try_get_rcu() [v13,010/137] mm: Add folio flag manipulation functions [v13,011/137] mm/lru: Add folio LRU functions [v13,012/137] mm: Handle per-folio private data [v13,013/137] mm/filemap: Add folio_index(), folio_file_page() and folio_contains() [v13,014/137] mm/filemap: Add folio_next_index() [v13,015/137] mm/filemap: Add folio_pos() and folio_file_pos() [v13,016/137] mm/util: Add folio_mapping() and folio_file_mapping() [v13,017/137] mm/filemap: Add folio_unlock() [v13,018/137] mm/filemap: Add folio_lock() [v13,019/137] mm/filemap: Add folio_lock_killable() [v13,020/137] mm/filemap: Add __folio_lock_async() [v13,021/137] mm/filemap: Add folio_wait_locked() [v13,022/137] mm/filemap: Add __folio_lock_or_retry() [v13,023/137] mm/swap: Add folio_rotate_reclaimable() [v13,024/137] mm/filemap: Add folio_end_writeback() [v13,025/137] mm/writeback: Add folio_wait_writeback() [v13,026/137] mm/writeback: Add folio_wait_stable() [v13,027/137] mm/filemap: Add folio_wait_bit() [v13,028/137] mm/filemap: Add folio_wake_bit() [v13,029/137] mm/filemap: Convert page wait queues to be folios [v13,030/137] mm/filemap: Add folio private_2 functions [v13,031/137] fs/netfs: Add folio fscache functions [v13,032/137] mm: Add folio_mapped() [v13,033/137] mm: Add folio_nid() [v13,034/137] mm/memcg: Remove 'page' parameter to mem_cgroup_charge_statistics() [v13,035/137] mm/memcg: Use the node id in mem_cgroup_update_tree() [v13,036/137] mm/memcg: Remove soft_limit_tree_node() [v13,037/137] mm/memcg: Convert memcg_check_events to take a node ID [v13,038/137] mm/memcg: Add folio_memcg() and related functions [v13,039/137] mm/memcg: Convert commit_charge() to take a folio [v13,040/137] mm/memcg: Convert mem_cgroup_charge() to take a folio [v13,041/137] mm/memcg: Convert uncharge_page() to uncharge_folio() [v13,042/137] mm/memcg: Convert mem_cgroup_uncharge() to take a folio [v13,043/137] mm/memcg: Convert mem_cgroup_migrate() to take folios [v13,044/137] mm/memcg: Convert mem_cgroup_track_foreign_dirty_slowpath() to folio [v13,045/137] mm/memcg: Add folio_memcg_lock() and folio_memcg_unlock() [v13,046/137] mm/memcg: Convert mem_cgroup_move_account() to use a folio [v13,047/137] mm/memcg: Add folio_lruvec() [v13,048/137] mm/memcg: Add folio_lruvec_lock() and similar functions [v13,049/137] mm/memcg: Add folio_lruvec_relock_irq() and folio_lruvec_relock_irqsave() [v13,050/137] mm/workingset: Convert workingset_activation to take a folio [v13,051/137] mm: Add folio_pfn() [v13,052/137] mm: Add folio_raw_mapping() [v13,053/137] mm: Add flush_dcache_folio() [v13,054/137] mm: Add kmap_local_folio() [v13,055/137] mm: Add arch_make_folio_accessible() [v13,056/137] mm: Add folio_young() and folio_idle() [v13,057/137] mm/swap: Add folio_activate() [v13,058/137] mm/swap: Add folio_mark_accessed() [v13,059/137] mm/rmap: Add folio_mkclean() [v13,060/137] mm/migrate: Add folio_migrate_mapping() [v13,061/137] mm/migrate: Add folio_migrate_flags() [v13,062/137] mm/migrate: Add folio_migrate_copy() [v13,063/137] mm/writeback: Rename __add_wb_stat() to wb_stat_mod() [v13,064/137] flex_proportions: Allow N events instead of 1 [v13,065/137] mm/writeback: Change __wb_writeout_inc() to __wb_writeout_add() [v13,066/137] mm/writeback: Add __folio_end_writeback() [v13,067/137] mm/writeback: Add folio_start_writeback() [v13,068/137] mm/writeback: Add folio_mark_dirty() [v13,069/137] mm/writeback: Add __folio_mark_dirty() [v13,070/137] mm/writeback: Add filemap_dirty_folio() [v13,071/137] mm/writeback: Add folio_account_cleaned() [v13,072/137] mm/writeback: Add folio_cancel_dirty() [v13,073/137] mm/writeback: Add folio_clear_dirty_for_io() [v13,074/137] mm/writeback: Add folio_account_redirty() [v13,075/137] mm/writeback: Add folio_redirty_for_writepage() [v13,076/137] mm/filemap: Add i_blocks_per_folio() [v13,077/137] mm/filemap: Add folio_mkwrite_check_truncate() [v13,078/137] mm/filemap: Add readahead_folio() [v13,079/137] mm/workingset: Convert workingset_refault() to take a folio [v13,080/137] mm: Add folio_evictable() [v13,081/137] mm/lru: Convert __pagevec_lru_add_fn to take a folio [v13,082/137] mm/lru: Add folio_add_lru() [v13,083/137] mm/page_alloc: Add folio allocation functions [v13,084/137] mm/filemap: Add filemap_alloc_folio [v13,085/137] mm/filemap: Add filemap_add_folio() [v13,086/137] mm/filemap: Convert mapping_get_entry to return a folio [v13,087/137] mm/filemap: Add filemap_get_folio [v13,088/137] mm/filemap: Add FGP_STABLE [v13,089/137] block: Add bio_add_folio() [v13,090/137] block: Add bio_for_each_folio_all() [v13,091/137] iomap: Convert to_iomap_page to take a folio [v13,092/137] iomap: Convert iomap_page_create to take a folio [v13,093/137] iomap: Convert iomap_page_release to take a folio [v13,094/137] iomap: Convert iomap_releasepage to use a folio [v13,095/137] iomap: Convert iomap_invalidatepage to use a folio [v13,096/137] iomap: Pass the iomap_page into iomap_set_range_uptodate [v13,097/137] iomap: Use folio offsets instead of page offsets [v13,098/137] iomap: Convert bio completions to use folios [v13,099/137] iomap: Convert readahead and readpage to use a folio [v13,100/137] iomap: Convert iomap_page_mkwrite to use a folio [v13,101/137] iomap: Convert iomap_write_begin and iomap_write_end to folios [v13,102/137] iomap: Convert iomap_read_inline_data to take a folio [v13,103/137] iomap: Convert iomap_write_end_inline to take a folio [v13,104/137] iomap: Convert iomap_add_to_ioend to take a folio [v13,105/137] iomap: Convert iomap_do_writepage to use a folio [v13,106/137] iomap: Convert iomap_migrate_page to use folios [v13,107/137] mm/filemap: Convert page_cache_delete to take a folio [v13,108/137] mm/filemap: Convert unaccount_page_cache_page to filemap_unaccount_folio [v13,109/137] mm/filemap: Add filemap_remove_folio and __filemap_remove_folio [v13,110/137] mm/filemap: Convert find_get_entry to return a folio [v13,111/137] mm/filemap: Convert filemap_get_read_batch to use folios [v13,112/137] mm/filemap: Convert find_get_pages_contig to folios [v13,113/137] mm/filemap: Convert filemap_read_page to take a folio [v13,114/137] mm/filemap: Convert filemap_create_page to folio [v13,115/137] mm/filemap: Convert filemap_range_uptodate to folios [v13,116/137] mm/filemap: Convert filemap_fault to folio [v13,117/137] mm/filemap: Add read_cache_folio and read_mapping_folio [v13,118/137] mm/filemap: Convert filemap_get_pages to use folios [v13,119/137] mm/filemap: Convert page_cache_delete_batch to folios [v13,120/137] mm/filemap: Remove PageHWPoison check from next_uptodate_page() [v13,121/137] mm/filemap: Use folios in next_uptodate_page [v13,122/137] mm/filemap: Use a folio in filemap_map_pages [v13,123/137] fs: Convert vfs_dedupe_file_range_compare to folios [v13,124/137] mm/truncate,shmem: Handle truncates that split THPs [v13,125/137] mm/filemap: Return only head pages from find_get_entries [v13,126/137] mm: Use multi-index entries in the page cache [v13,127/137] iomap: Support multi-page folios in invalidatepage [v13,128/137] xfs: Support THPs [v13,129/137] mm/truncate: Convert invalidate_inode_pages2_range to folios [v13,130/137] mm/truncate: Fix invalidate_complete_page2 for THPs [v13,131/137] mm/vmscan: Free non-shmem THPs without splitting them [v13,132/137] mm: Fix READ_ONLY_THP warning [v13,133/137] mm: Support arbitrary THP sizes [v13,134/137] mm/filemap: Allow multi-page folios to be added to the page cache [v13,135/137] mm/vmscan: Optimise shrink_page_list for smaller THPs [v13,136/137] mm/readahead: Convert page_cache_async_ra() to take a folio [v13,137/137] mm/readahead: Add multi-page folio readahead

Message ID

20210712030701.4000097-1-willy@infradead.org (mailing list archive)

Headers

DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 7B85F60200
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
To: linux-kernel@vger.kernel.org
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>,
	linux-mm@kvack.org,
	linux-fsdevel@vger.kernel.org
Subject: [PATCH v13 000/137] Memory folios
Date: Mon, 12 Jul 2021 04:04:44 +0100
Message-Id: <20210712030701.4000097-1-willy@infradead.org>
MIME-Version: 1.0
Content-Transfer-Encoding: quoted-printable
Sender: owner-linux-mm@kvack.org
Precedence: bulk

Series

Memory folios | expand

Message

Matthew Wilcox July 12, 2021, 3:04 a.m. UTC

Managing memory in 4KiB pages is a serious overhead.  Many benchmarks
benefit from a larger "page size".  As an example, an earlier iteration
of this idea which used compound pages (and wasn't particularly tuned)
got a 7% performance boost when compiling the kernel.

Using compound pages or THPs exposes a weakness of our type system.
Functions are often unprepared for compound pages to be passed to them,
and may only act on PAGE_SIZE chunks.  Even functions which are aware of
compound pages may expect a head page, and do the wrong thing if passed
a tail page.

We also waste a lot of instructions ensuring that we're not looking at
a tail page.  Almost every call to PageFoo() contains one or more hidden
calls to compound_head().  This also happens for get_page(), put_page()
and many more functions.

This patch series uses a new type, the struct folio, to manage memory.
It converts enough of the page cache, iomap and XFS to use folios instead
of pages, and then adds support for multi-page folios.  It passes xfstests
(running on XFS) with no regressions compared to v5.14-rc1.

Git: https://git.infradead.org/users/willy/pagecache.git/shortlog/refs/tags/folio_13

Matthew Wilcox (Oracle) (137):
  mm: Convert get_page_unless_zero() to return bool
  mm: Introduce struct folio
  mm: Add folio_pgdat(), folio_zone() and folio_zonenum()
  mm/vmstat: Add functions to account folio statistics
  mm/debug: Add VM_BUG_ON_FOLIO() and VM_WARN_ON_ONCE_FOLIO()
  mm: Add folio reference count functions
  mm: Add folio_put()
  mm: Add folio_get()
  mm: Add folio_try_get_rcu()
  mm: Add folio flag manipulation functions
  mm/lru: Add folio LRU functions
  mm: Handle per-folio private data
  mm/filemap: Add folio_index(), folio_file_page() and folio_contains()
  mm/filemap: Add folio_next_index()
  mm/filemap: Add folio_pos() and folio_file_pos()
  mm/util: Add folio_mapping() and folio_file_mapping()
  mm/filemap: Add folio_unlock()
  mm/filemap: Add folio_lock()
  mm/filemap: Add folio_lock_killable()
  mm/filemap: Add __folio_lock_async()
  mm/filemap: Add folio_wait_locked()
  mm/filemap: Add __folio_lock_or_retry()
  mm/swap: Add folio_rotate_reclaimable()
  mm/filemap: Add folio_end_writeback()
  mm/writeback: Add folio_wait_writeback()
  mm/writeback: Add folio_wait_stable()
  mm/filemap: Add folio_wait_bit()
  mm/filemap: Add folio_wake_bit()
  mm/filemap: Convert page wait queues to be folios
  mm/filemap: Add folio private_2 functions
  fs/netfs: Add folio fscache functions
  mm: Add folio_mapped()
  mm: Add folio_nid()
  mm/memcg: Remove 'page' parameter to mem_cgroup_charge_statistics()
  mm/memcg: Use the node id in mem_cgroup_update_tree()
  mm/memcg: Remove soft_limit_tree_node()
  mm/memcg: Convert memcg_check_events to take a node ID
  mm/memcg: Add folio_memcg() and related functions
  mm/memcg: Convert commit_charge() to take a folio
  mm/memcg: Convert mem_cgroup_charge() to take a folio
  mm/memcg: Convert uncharge_page() to uncharge_folio()
  mm/memcg: Convert mem_cgroup_uncharge() to take a folio
  mm/memcg: Convert mem_cgroup_migrate() to take folios
  mm/memcg: Convert mem_cgroup_track_foreign_dirty_slowpath() to folio
  mm/memcg: Add folio_memcg_lock() and folio_memcg_unlock()
  mm/memcg: Convert mem_cgroup_move_account() to use a folio
  mm/memcg: Add folio_lruvec()
  mm/memcg: Add folio_lruvec_lock() and similar functions
  mm/memcg: Add folio_lruvec_relock_irq() and
    folio_lruvec_relock_irqsave()
  mm/workingset: Convert workingset_activation to take a folio
  mm: Add folio_pfn()
  mm: Add folio_raw_mapping()
  mm: Add flush_dcache_folio()
  mm: Add kmap_local_folio()
  mm: Add arch_make_folio_accessible()
  mm: Add folio_young() and folio_idle()
  mm/swap: Add folio_activate()
  mm/swap: Add folio_mark_accessed()
  mm/rmap: Add folio_mkclean()
  mm/migrate: Add folio_migrate_mapping()
  mm/migrate: Add folio_migrate_flags()
  mm/migrate: Add folio_migrate_copy()
  mm/writeback: Rename __add_wb_stat() to wb_stat_mod()
  flex_proportions: Allow N events instead of 1
  mm/writeback: Change __wb_writeout_inc() to __wb_writeout_add()
  mm/writeback: Add __folio_end_writeback()
  mm/writeback: Add folio_start_writeback()
  mm/writeback: Add folio_mark_dirty()
  mm/writeback: Add __folio_mark_dirty()
  mm/writeback: Add filemap_dirty_folio()
  mm/writeback: Add folio_account_cleaned()
  mm/writeback: Add folio_cancel_dirty()
  mm/writeback: Add folio_clear_dirty_for_io()
  mm/writeback: Add folio_account_redirty()
  mm/writeback: Add folio_redirty_for_writepage()
  mm/filemap: Add i_blocks_per_folio()
  mm/filemap: Add folio_mkwrite_check_truncate()
  mm/filemap: Add readahead_folio()
  mm/workingset: Convert workingset_refault() to take a folio
  mm: Add folio_evictable()
  mm/lru: Convert __pagevec_lru_add_fn to take a folio
  mm/lru: Add folio_add_lru()
  mm/page_alloc: Add folio allocation functions
  mm/filemap: Add filemap_alloc_folio
  mm/filemap: Add filemap_add_folio()
  mm/filemap: Convert mapping_get_entry to return a folio
  mm/filemap: Add filemap_get_folio
  mm/filemap: Add FGP_STABLE
  block: Add bio_add_folio()
  block: Add bio_for_each_folio_all()
  iomap: Convert to_iomap_page to take a folio
  iomap: Convert iomap_page_create to take a folio
  iomap: Convert iomap_page_release to take a folio
  iomap: Convert iomap_releasepage to use a folio
  iomap: Convert iomap_invalidatepage to use a folio
  iomap: Pass the iomap_page into iomap_set_range_uptodate
  iomap: Use folio offsets instead of page offsets
  iomap: Convert bio completions to use folios
  iomap: Convert readahead and readpage to use a folio
  iomap: Convert iomap_page_mkwrite to use a folio
  iomap: Convert iomap_write_begin and iomap_write_end to folios
  iomap: Convert iomap_read_inline_data to take a folio
  iomap: Convert iomap_write_end_inline to take a folio
  iomap: Convert iomap_add_to_ioend to take a folio
  iomap: Convert iomap_do_writepage to use a folio
  iomap: Convert iomap_migrate_page to use folios
  mm/filemap: Convert page_cache_delete to take a folio
  mm/filemap: Convert unaccount_page_cache_page to
    filemap_unaccount_folio
  mm/filemap: Add filemap_remove_folio and __filemap_remove_folio
  mm/filemap: Convert find_get_entry to return a folio
  mm/filemap: Convert filemap_get_read_batch to use folios
  mm/filemap: Convert find_get_pages_contig to folios
  mm/filemap: Convert filemap_read_page to take a folio
  mm/filemap: Convert filemap_create_page to folio
  mm/filemap: Convert filemap_range_uptodate to folios
  mm/filemap: Convert filemap_fault to folio
  mm/filemap: Add read_cache_folio and read_mapping_folio
  mm/filemap: Convert filemap_get_pages to use folios
  mm/filemap: Convert page_cache_delete_batch to folios
  mm/filemap: Remove PageHWPoison check from next_uptodate_page()
  mm/filemap: Use folios in next_uptodate_page
  mm/filemap: Use a folio in filemap_map_pages
  fs: Convert vfs_dedupe_file_range_compare to folios
  mm/truncate,shmem: Handle truncates that split THPs
  mm/filemap: Return only head pages from find_get_entries
  mm: Use multi-index entries in the page cache
  iomap: Support multi-page folios in invalidatepage
  xfs: Support THPs
  mm/truncate: Convert invalidate_inode_pages2_range to folios
  mm/truncate: Fix invalidate_complete_page2 for THPs
  mm/vmscan: Free non-shmem THPs without splitting them
  mm: Fix READ_ONLY_THP warning
  mm: Support arbitrary THP sizes
  mm/filemap: Allow multi-page folios to be added to the page cache
  mm/vmscan: Optimise shrink_page_list for smaller THPs
  mm/readahead: Convert page_cache_async_ra() to take a folio
  mm/readahead: Add multi-page folio readahead

 Documentation/core-api/cachetlb.rst         |    6 +
 Documentation/core-api/mm-api.rst           |    4 +
 Documentation/filesystems/netfs_library.rst |    2 +
 arch/nds32/include/asm/cacheflush.h         |    1 +
 block/bio.c                                 |   21 +
 fs/afs/write.c                              |    9 +-
 fs/cachefiles/rdwr.c                        |   16 +-
 fs/io_uring.c                               |    2 +-
 fs/iomap/buffered-io.c                      |  524 ++++----
 fs/jfs/jfs_metapage.c                       |    1 +
 fs/remap_range.c                            |  116 +-
 fs/xfs/xfs_aops.c                           |   11 +-
 fs/xfs/xfs_super.c                          |    3 +-
 include/asm-generic/cacheflush.h            |    6 +
 include/linux/backing-dev.h                 |    6 +-
 include/linux/bio.h                         |   46 +-
 include/linux/flex_proportions.h            |    9 +-
 include/linux/gfp.h                         |   22 +-
 include/linux/highmem-internal.h            |   11 +
 include/linux/highmem.h                     |   38 +
 include/linux/huge_mm.h                     |   23 +-
 include/linux/ksm.h                         |    4 +-
 include/linux/memcontrol.h                  |  218 ++--
 include/linux/migrate.h                     |    4 +
 include/linux/mm.h                          |  266 +++-
 include/linux/mm_inline.h                   |   85 +-
 include/linux/mm_types.h                    |   77 ++
 include/linux/mmdebug.h                     |   20 +
 include/linux/netfs.h                       |   77 +-
 include/linux/page-flags.h                  |  267 ++--
 include/linux/page_idle.h                   |   99 +-
 include/linux/page_owner.h                  |    8 +-
 include/linux/page_ref.h                    |  158 ++-
 include/linux/pagemap.h                     |  615 +++++----
 include/linux/rmap.h                        |   10 +-
 include/linux/swap.h                        |   17 +-
 include/linux/vmstat.h                      |  107 ++
 include/linux/writeback.h                   |    9 +-
 include/trace/events/writeback.h            |    8 +-
 kernel/bpf/verifier.c                       |    2 +-
 kernel/events/uprobes.c                     |    3 +-
 lib/flex_proportions.c                      |   28 +-
 mm/Makefile                                 |    2 +-
 mm/compaction.c                             |    4 +-
 mm/filemap.c                                | 1285 +++++++++----------
 mm/folio-compat.c                           |  147 +++
 mm/huge_memory.c                            |   27 +-
 mm/internal.h                               |   40 +-
 mm/khugepaged.c                             |   20 +-
 mm/ksm.c                                    |   34 +-
 mm/memcontrol.c                             |  323 +++--
 mm/memory-failure.c                         |    2 +-
 mm/memory.c                                 |   20 +-
 mm/mempolicy.c                              |   10 +
 mm/memremap.c                               |    2 +-
 mm/migrate.c                                |  246 ++--
 mm/mlock.c                                  |    3 +-
 mm/page-writeback.c                         |  447 ++++---
 mm/page_alloc.c                             |   14 +-
 mm/page_io.c                                |    4 +-
 mm/page_owner.c                             |   10 +-
 mm/readahead.c                              |  108 +-
 mm/rmap.c                                   |   14 +-
 mm/shmem.c                                  |  115 +-
 mm/swap.c                                   |  180 +--
 mm/swap_state.c                             |    2 +-
 mm/swapfile.c                               |    8 +-
 mm/truncate.c                               |  193 +--
 mm/userfaultfd.c                            |    2 +-
 mm/util.c                                   |   92 +-
 mm/vmscan.c                                 |   15 +-
 mm/workingset.c                             |   44 +-
 72 files changed, 3822 insertions(+), 2550 deletions(-)
 create mode 100644 mm/folio-compat.c

Comments

Christoph Hellwig July 12, 2021, 5:46 a.m. UTC | #1

On Mon, Jul 12, 2021 at 04:04:44AM +0100, Matthew Wilcox (Oracle) wrote:
> Managing memory in 4KiB pages is a serious overhead.  Many benchmarks
> benefit from a larger "page size".  As an example, an earlier iteration
> of this idea which used compound pages (and wasn't particularly tuned)
> got a 7% performance boost when compiling the kernel.
> 
> Using compound pages or THPs exposes a weakness of our type system.
> Functions are often unprepared for compound pages to be passed to them,
> and may only act on PAGE_SIZE chunks.  Even functions which are aware of
> compound pages may expect a head page, and do the wrong thing if passed
> a tail page.
> 
> We also waste a lot of instructions ensuring that we're not looking at
> a tail page.  Almost every call to PageFoo() contains one or more hidden
> calls to compound_head().  This also happens for get_page(), put_page()
> and many more functions.
> 
> This patch series uses a new type, the struct folio, to manage memory.
> It converts enough of the page cache, iomap and XFS to use folios instead
> of pages, and then adds support for multi-page folios.  It passes xfstests
> (running on XFS) with no regressions compared to v5.14-rc1.

This seems to miss a changelog vs the previous version.  It also
includes a lot of the follow ups.  I think reviewing a series gets
rather hard at more than 30-ish patches, so chunking it up a little
more would be useful.

Matthew Wilcox July 12, 2021, 11:35 a.m. UTC | #2

On Mon, Jul 12, 2021 at 06:46:05AM +0100, Christoph Hellwig wrote:
> On Mon, Jul 12, 2021 at 04:04:44AM +0100, Matthew Wilcox (Oracle) wrote:
> > Managing memory in 4KiB pages is a serious overhead.  Many benchmarks
> > benefit from a larger "page size".  As an example, an earlier iteration
> > of this idea which used compound pages (and wasn't particularly tuned)
> > got a 7% performance boost when compiling the kernel.
> > 
> > Using compound pages or THPs exposes a weakness of our type system.
> > Functions are often unprepared for compound pages to be passed to them,
> > and may only act on PAGE_SIZE chunks.  Even functions which are aware of
> > compound pages may expect a head page, and do the wrong thing if passed
> > a tail page.
> > 
> > We also waste a lot of instructions ensuring that we're not looking at
> > a tail page.  Almost every call to PageFoo() contains one or more hidden
> > calls to compound_head().  This also happens for get_page(), put_page()
> > and many more functions.
> > 
> > This patch series uses a new type, the struct folio, to manage memory.
> > It converts enough of the page cache, iomap and XFS to use folios instead
> > of pages, and then adds support for multi-page folios.  It passes xfstests
> > (running on XFS) with no regressions compared to v5.14-rc1.
> 
> This seems to miss a changelog vs the previous version.  It also
> includes a lot of the follow ups.  I think reviewing a series gets
> rather hard at more than 30-ish patches, so chunking it up a little
> more would be useful.

I'm not seriously expecting anybody to review 137 patches.  It's more
for the bots to chew on (which they have done and I'm about to look
at their output).  I'll be sending mergable subsets (three rounds; the
base code, the memcg series and the pagecache series) later this week,
once I've addressed the build bot complaints.  You've seen all those
patches individually by now.

My plan is that once those are merged, the rest can proceed in parallel.
The block + iomap series is independent, then there's the second pagecache
series.  The last dozen or so patches still need a bit of work as they
were pulled across from the THP tree and at least need better changelogs.

Since this works for me, I'm hoping some people will also test and
confirm it works for them, and maybe post their own performance numbers
to justify all this.