linux/include/trace/events
Linus Torvalds 49f8275c7d Memory folios
Add memory folios, a new type to represent either order-0 pages or
 the head page of a compound page.  This should be enough infrastructure
 to support filesystems converting from pages to folios.
 -----BEGIN PGP SIGNATURE-----
 
 iQEzBAABCgAdFiEEejHryeLBw/spnjHrDpNsjXcpgj4FAmF9uI0ACgkQDpNsjXcp
 gj7MUAf/R7LCZ+xFiIedw7SAgb/DGK0C9uVjuBEIZgAw21ZUw/GuPI6cuKBMFGGf
 rRcdtlvMpwi7yZJcoNXxaqU/xPaaJMjf2XxscIvYJP1mjlZVuwmP9dOx0neNvWOc
 T+8lqR6c1TLl82lpqIjGFLwvj2eVowq2d3J5jsaIJFd4odmmYVInrhJXOzC/LQ54
 Niloj5ksehf+KUIRLDz7ycppvIHhlVsoAl0eM2dWBAtL0mvT7Nyn/3y+vnMfV2v3
 Flb4opwJUgTJleYc16oxTn9svT2yS8q2uuUemRDLW8ABghoAtH3fUUk43RN+5Krd
 LYCtbeawtkikPVXZMfWybsx5vn0c3Q==
 =7SBe
 -----END PGP SIGNATURE-----

Merge tag 'folio-5.16' of git://git.infradead.org/users/willy/pagecache

Pull memory folios from Matthew Wilcox:
 "Add memory folios, a new type to represent either order-0 pages or the
  head page of a compound page. This should be enough infrastructure to
  support filesystems converting from pages to folios.

  The point of all this churn is to allow filesystems and the page cache
  to manage memory in larger chunks than PAGE_SIZE. The original plan
  was to use compound pages like THP does, but I ran into problems with
  some functions expecting only a head page while others expect the
  precise page containing a particular byte.

  The folio type allows a function to declare that it's expecting only a
  head page. Almost incidentally, this allows us to remove various calls
  to VM_BUG_ON(PageTail(page)) and compound_head().

  This converts just parts of the core MM and the page cache. For 5.17,
  we intend to convert various filesystems (XFS and AFS are ready; other
  filesystems may make it) and also convert more of the MM and page
  cache to folios. For 5.18, multi-page folios should be ready.

  The multi-page folios offer some improvement to some workloads. The
  80% win is real, but appears to be an artificial benchmark (postgres
  startup, which isn't a serious workload). Real workloads (eg building
  the kernel, running postgres in a steady state, etc) seem to benefit
  between 0-10%. I haven't heard of any performance losses as a result
  of this series. Nobody has done any serious performance tuning; I
  imagine that tweaking the readahead algorithm could provide some more
  interesting wins. There are also other places where we could choose to
  create large folios and currently do not, such as writes that are
  larger than PAGE_SIZE.

  I'd like to thank all my reviewers who've offered review/ack tags:
  Christoph Hellwig, David Howells, Jan Kara, Jeff Layton, Johannes
  Weiner, Kirill A. Shutemov, Michal Hocko, Mike Rapoport, Vlastimil
  Babka, William Kucharski, Yu Zhao and Zi Yan.

  I'd also like to thank those who gave feedback I incorporated but
  haven't offered up review tags for this part of the series: Nick
  Piggin, Mel Gorman, Ming Lei, Darrick Wong, Ted Ts'o, John Hubbard,
  Hugh Dickins, and probably a few others who I forget"

* tag 'folio-5.16' of git://git.infradead.org/users/willy/pagecache: (90 commits)
  mm/writeback: Add folio_write_one
  mm/filemap: Add FGP_STABLE
  mm/filemap: Add filemap_get_folio
  mm/filemap: Convert mapping_get_entry to return a folio
  mm/filemap: Add filemap_add_folio()
  mm/filemap: Add filemap_alloc_folio
  mm/page_alloc: Add folio allocation functions
  mm/lru: Add folio_add_lru()
  mm/lru: Convert __pagevec_lru_add_fn to take a folio
  mm: Add folio_evictable()
  mm/workingset: Convert workingset_refault() to take a folio
  mm/filemap: Add readahead_folio()
  mm/filemap: Add folio_mkwrite_check_truncate()
  mm/filemap: Add i_blocks_per_folio()
  mm/writeback: Add folio_redirty_for_writepage()
  mm/writeback: Add folio_account_redirty()
  mm/writeback: Add folio_clear_dirty_for_io()
  mm/writeback: Add folio_cancel_dirty()
  mm/writeback: Add folio_account_cleaned()
  mm/writeback: Add filemap_dirty_folio()
  ...
2021-11-01 08:47:59 -07:00
..
9p.h
afs.h afs: Try to avoid taking RCU read lock when checking vnode validity 2021-09-13 09:10:39 +01:00
alarmtimer.h
asoc.h ASoC: soc-core: tidyup jack.h 2020-11-30 12:54:01 +00:00
avc.h selinux: add basic filtering for audit trace events 2020-08-21 17:07:29 -04:00
bcache.h block: remove superfluous param in blk_fill_rwbs() 2021-02-22 06:37:41 -07:00
block.h blktrace: fix blk_rq_merge documentation 2021-02-22 06:37:41 -07:00
bpf_test_run.h
bridge.h net: bridge: fdb: br_fdb_update can take flags directly 2019-11-01 10:32:43 -07:00
btrfs.h btrfs: use delalloc_bytes to determine flush amount for shrink_delalloc 2021-08-23 13:19:07 +02:00
cachefiles.h cachefiles: Fix oops with cachefiles_cull() due to NULL object 2021-10-05 11:22:06 +01:00
cgroup.h cgroup: use cgrp->kn->id as the cgroup ID 2019-11-12 08:18:04 -08:00
clk.h clk: Trace clk_set_rate() "range" functions 2020-12-17 01:54:31 -08:00
cma.h mm, tracing: unify PFN format strings 2021-06-29 10:53:52 -07:00
compaction.h mm/page_alloc: integrate classzone_idx and high_zoneidx 2020-06-03 20:09:44 -07:00
context_tracking.h
cpuhp.h
damon.h mm/damon: add a tracepoint 2021-09-08 11:50:24 -07:00
devfreq.h PM / devfreq: Add tracepoint for frequency changes 2020-10-26 10:52:37 +09:00
devlink.h devlink: Add a tracepoint for trap reports 2020-09-30 18:01:26 -07:00
dma_fence.h treewide: Add missing semicolons to __assign_str uses 2021-06-30 09:19:14 -04:00
erofs.h erofs: fix up erofs_lookup tracepoint 2021-09-23 23:21:34 +08:00
error_report.h tracing: add error_report_end trace point 2021-02-26 09:41:02 -08:00
ext4.h ext4: delete some unused tracepoint definitions 2021-04-02 11:38:06 -04:00
f2fs.h f2fs: introduce periodic iostat io latency traces 2021-08-23 10:25:51 -07:00
fib6.h
fib.h
filelock.h locks: Remove extra "0x" in tracepoint format specifier 2020-09-01 18:09:34 -04:00
filemap.h mm, tracing: unify PFN format strings 2021-06-29 10:53:52 -07:00
fs_dax.h
fscache.h fscache: Use refcount_t for the cookie refcount instead of atomic_t 2021-08-27 13:34:03 +01:00
fsi_master_aspeed.h fsi: aspeed: Add trace points 2019-11-08 11:28:20 +01:00
fsi_master_ast_cf.h
fsi_master_gpio.h
fsi.h trace: fsi: Print transfer size unsigned 2019-11-08 11:23:37 +01:00
gpio.h
gpu_mem.h gpu/trace: Minor comment updates for gpu_mem_total tracepoint 2020-05-07 13:32:57 -04:00
host1x.h
huge_memory.h khugepaged: introduce 'max_ptes_shared' tunable 2020-06-03 20:09:46 -07:00
hwmon.h
i2c.h
ib_mad.h
ib_umad.h
initcall.h
intel_iommu.h iommu/vt-d: Add prq_report trace event 2021-06-10 09:06:13 +02:00
intel_ish.h
intel-sst.h
io_uring.h io_uring: io_uring_complete() trace should take an integer 2021-09-03 16:59:06 -06:00
iocost.h blk-iocost: Add iocg idle state tracepoint 2020-12-17 07:55:44 -07:00
iommu.h
ipi.h
irq_matrix.h
irq.h
iscsi.h
jbd2.h jbd2,ext4: add a shrinker to release checkpointed buffers 2021-06-24 10:54:49 -04:00
kmem.h mm, tracing: unify PFN format strings 2021-06-29 10:53:52 -07:00
kvm.h KVM: x86/mmu: Drop trace_kvm_age_page() tracepoint 2021-04-17 08:30:56 -04:00
kyber.h kyber: avoid q->disk dereferences in trace points 2021-10-15 21:02:57 -06:00
libata.h
lock.h
mce.h
mdio.h
migrate.h mm/migrate: demote pages during reclaim 2021-09-03 09:58:16 -07:00
mlxsw.h
mmap_lock.h mm: mmap_lock: add tracepoints around lock acquisition 2020-12-15 12:13:41 -08:00
mmap.h mm: mmap: add trace point of vm_unmapped_area 2020-04-02 09:35:30 -07:00
mmc.h
mmflags.h Merge branch 'akpm' (patches from Andrew) 2021-09-08 12:55:35 -07:00
module.h
mptcp.h mptcp: dump csum fields in mptcp_dump_mpext 2021-06-18 11:40:11 -07:00
napi.h tracing: Fix header include guards in trace event headers 2019-07-30 21:49:06 -04:00
nbd.h
neigh.h
net_probe_common.h
net.h net: use %px to print skb address in trace_netif_receive_skb 2021-07-15 10:28:48 -07:00
netfs.h netfs: Move cookie debug ID to struct netfs_cache_resources 2021-08-25 15:20:25 +01:00
netlink.h netlink: add tracepoint at NL_SET_ERR_MSG 2021-02-04 18:05:59 -08:00
nilfs2.h
nmi.h
objagg.h
oom.h
osnoise.h tracing: Fix spelling in osnoise tracer "interferences" -> "interference" 2021-06-28 14:12:27 -04:00
page_isolation.h
page_pool.h mm, tracing: unify PFN format strings 2021-06-29 10:53:52 -07:00
page_ref.h mm: introduce PAGEFLAGS_MASK to replace ((1UL << NR_PAGEFLAGS) - 1) 2021-09-08 11:50:24 -07:00
pagemap.h mm/lru: Convert __pagevec_lru_add_fn to take a folio 2021-10-18 07:49:40 -04:00
percpu.h
power_cpu_migrate.h
power.h PM: QoS: Simplify definitions of CPU latency QoS trace events 2020-02-13 11:26:39 +01:00
preemptirq.h tracing: Change offset type to s32 in preempt/irq tracepoints 2020-01-03 11:34:37 -05:00
printk.h
pwc.h
pwm.h pwm: Implement tracing for .get_state() and .apply_state() 2020-01-20 12:28:37 +01:00
qdisc.h qdisc: add new field for qdisc_enqueue tracepoint 2021-07-27 14:16:38 +01:00
qla.h scsi: qla2xxx: Suppress two recently introduced compiler warnings 2020-05-19 21:43:01 -04:00
qrtr.h net: qrtr: Add tracepoint support 2020-04-22 12:55:54 -07:00
random.h random: remove dead code left over from blocking pool 2021-04-02 18:28:12 +11:00
rcu.h rcu/nocb: Unify timers 2021-05-12 12:10:23 -07:00
rdma_core.h RDMA/core: Add trace points to follow MR allocation 2020-01-07 16:10:53 -04:00
rdma.h RDMA/core: Move the rdma_show_ib_cm_event() macro 2020-08-24 16:01:47 -03:00
regulator.h regulator: core: Add regulator bypass trace points 2020-05-29 17:17:02 +01:00
rpcgss.h treewide: Add missing semicolons to __assign_str uses 2021-06-30 09:19:14 -04:00
rpcrdma.h xprtrdma: Add an xprtrdma_post_send_err tracepoint 2021-08-09 16:42:18 -04:00
rpm.h PM-runtime: add tracepoints for usage_count changes 2020-01-13 12:28:29 +01:00
rseq.h
rtc.h
rxrpc.h rxrpc: Fix a missing NULL-pointer check in a trace 2020-09-14 16:18:59 +01:00
sched.h sched/tracing: Remove the redundant 'success' in the sched tracepoint 2021-06-10 11:16:20 -04:00
scmi.h firmware: arm_scmi: Use signed integer to report transfer status 2020-06-30 14:07:08 +01:00
scsi.h scsi: core: Kill message byte 2021-05-31 22:48:24 -04:00
sctp.h sctp: move trace_sctp_probe_path into sctp_outq_sack 2019-12-26 13:06:45 -08:00
signal.h
siox.h
skb.h
smbus.h
sock.h net: sock: add trace for socket errors 2021-06-29 11:28:21 -07:00
spi.h spi: Enable tracing of the SPI setup CS selection 2021-05-26 21:22:13 +01:00
spmi.h
sunrpc.h NFS Client Updates for Linux 5.15 2021-09-04 10:25:26 -07:00
sunvnet.h
swiotlb.h
syscalls.h
target.h scsi: target: core: Add CONTROL field for trace events 2020-10-02 18:36:19 -04:00
task.h
tcp.h tcp: add tracepoint for checksum errors 2021-05-14 15:26:03 -07:00
tegra_apb_dma.h tracing: Fix header include guards in trace event headers 2019-07-30 21:49:06 -04:00
thermal_power_allocator.h
thermal.h thermal: devfreq_cooling: change tracing function and arguments 2020-12-11 14:10:44 +01:00
thp.h
timer.h tracing: Fix various typos in comments 2021-03-23 14:08:18 -04:00
tlb.h
udp.h
ufs.h scsi: ufs: core: Enable power management for wlun 2021-05-10 22:28:20 -04:00
v4l2.h media: v4l2: abstract timeval handling in v4l2_buffer 2020-01-03 15:43:35 +01:00
vb2.h
vmscan.h include/trace/events/vmscan.h: remove mm_vmscan_inactive_list_is_low 2021-06-30 20:47:28 -07:00
vsock_virtio_transport_common.h virtio/vsock: update trace event for SEQPACKET 2021-06-11 13:32:47 -07:00
wbt.h bdi: use bdi_dev_name() to get device name 2020-05-09 16:07:39 -06:00
workqueue.h workqueue/tracing: Copy workqueue name to buffer in trace event 2021-03-18 12:57:37 -04:00
writeback.h mm/writeback: Convert tracing writeback_page_template to folios 2021-10-18 07:49:39 -04:00
xdp.h xdp: Extend xdp_redirect_map with broadcast support 2021-05-26 09:46:16 +02:00
xen.h x86/mm/tlb: Flush remote and local TLBs concurrently 2021-03-06 12:59:10 +01:00