For each node, memcgs are divided into two generations: the old and
the young. For each generation, memcgs are randomly sharded into
multiple bins to improve scalability. For each bin, an RCU hlist_nulls
is virtually divided into three segments: the head, the tail and the
default.

An onlining memcg is added to the tail of a random bin in the old
generation. The eviction starts at the head of a random bin in the old
generation. The per-node memcg generation counter, whose reminder (mod
2) indexes the old generation, is incremented when all its bins become
empty.

There are four operations:
1. MEMCG_LRU_HEAD, which moves an memcg to the head of a random bin in
   its current generation (old or young) and updates its "seg" to
   "head";
2. MEMCG_LRU_TAIL, which moves an memcg to the tail of a random bin in
   its current generation (old or young) and updates its "seg" to
   "tail";
3. MEMCG_LRU_OLD, which moves an memcg to the head of a random bin in
   the old generation, updates its "gen" to "old" and resets its "seg"
   to "default";
4. MEMCG_LRU_YOUNG, which moves an memcg to the tail of a random bin
   in the young generation, updates its "gen" to "young" and resets
   its "seg" to "default".

The events that trigger the above operations are:
1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD;
2. The first attempt to reclaim an memcg below low, which triggers
   MEMCG_LRU_TAIL;
3. The first attempt to reclaim an memcg below reclaimable size
   threshold, which triggers MEMCG_LRU_TAIL;
4. The second attempt to reclaim an memcg below reclaimable size
   threshold, which triggers MEMCG_LRU_YOUNG;
5. Attempting to reclaim an memcg below min, which triggers
   MEMCG_LRU_YOUNG;
6. Finishing the aging on the eviction path, which triggers
   MEMCG_LRU_YOUNG;
7. Offlining an memcg, which triggers MEMCG_LRU_OLD.

Note that memcg LRU only applies to global reclaim, and the
round-robin incrementing of their max_seq counters ensures the
eventual fairness to all eligible memcgs. For memcg reclaim, it still
relies on mem_cgroup_iter().

Link: https://lkml.kernel.org/r/20221222041905.2431096-7-yuzhao@google.com
Signed-off-by: Yu Zhao <yuzhao@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Michael Larabel <Michael@MichaelLarabel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Move should_run_aging() next to its only caller left.

Link: https://lkml.kernel.org/r/20221222041905.2431096-6-yuzhao@google.com
Signed-off-by: Yu Zhao <yuzhao@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Michael Larabel <Michael@MichaelLarabel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Recall that the aging produces the youngest generation: first it scans
for accessed folios and updates their gen counters; then it increments
lrugen->max_seq.

The current aging fairness safeguard for kswapd uses two passes to
ensure the fairness to multiple eligible memcgs. On the first pass,
which is shared with the eviction, it checks whether all eligible
memcgs are low on cold folios. If so, it requires a second pass, on
which it ages all those memcgs at the same time.

With memcg LRU, the aging, while ensuring eventual fairness, will run
when necessary. Therefore the current aging fairness safeguard for
kswapd will not be needed.

Note that memcg LRU only applies to global reclaim. For memcg reclaim,
the aging can be unfair to different memcgs, i.e., their
lrugen->max_seq can be incremented at different paces.

Link: https://lkml.kernel.org/r/20221222041905.2431096-5-yuzhao@google.com
Signed-off-by: Yu Zhao <yuzhao@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Michael Larabel <Michael@MichaelLarabel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Recall that the eviction consumes the oldest generation: first it
bucket-sorts folios whose gen counters were updated by the aging and
reclaims the rest; then it increments lrugen->min_seq.

The current eviction fairness safeguard for global reclaim has a
dilemma: when there are multiple eligible memcgs, should it continue
or stop upon meeting the reclaim goal? If it continues, it overshoots
and increases direct reclaim latency; if it stops, it loses fairness
between memcgs it has taken memory away from and those it has yet to.

With memcg LRU, the eviction, while ensuring eventual fairness, will
stop upon meeting its goal. Therefore the current eviction fairness
safeguard for global reclaim will not be needed.

Note that memcg LRU only applies to global reclaim. For memcg reclaim,
the eviction will continue, even if it is overshooting. This becomes
unconditional due to code simplification.

Link: https://lkml.kernel.org/r/20221222041905.2431096-4-yuzhao@google.com
Signed-off-by: Yu Zhao <yuzhao@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Michael Larabel <Michael@MichaelLarabel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

lru_gen_folio will be chained into per-node lists by the coming
lrugen->list.

Link: https://lkml.kernel.org/r/20221222041905.2431096-3-yuzhao@google.com
Signed-off-by: Yu Zhao <yuzhao@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Michael Larabel <Michael@MichaelLarabel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Patch series "mm: multi-gen LRU: memcg LRU", v3.

Overview
========

An memcg LRU is a per-node LRU of memcgs.  It is also an LRU of LRUs,
since each node and memcg combination has an LRU of folios (see
mem_cgroup_lruvec()).

Its goal is to improve the scalability of global reclaim, which is
critical to system-wide memory overcommit in data centers.  Note that
memcg reclaim is currently out of scope.

Its memory bloat is a pointer to each lruvec and negligible to each
pglist_data.  In terms of traversing memcgs during global reclaim, it
improves the best-case complexity from O(n) to O(1) and does not affect
the worst-case complexity O(n).  Therefore, on average, it has a sublinear
complexity in contrast to the current linear complexity.

The basic structure of an memcg LRU can be understood by an analogy to
the active/inactive LRU (of folios):
1. It has the young and the old (generations), i.e., the counterparts
   to the active and the inactive;
2. The increment of max_seq triggers promotion, i.e., the counterpart
   to activation;
3. Other events trigger similar operations, e.g., offlining an memcg
   triggers demotion, i.e., the counterpart to deactivation.

In terms of global reclaim, it has two distinct features:
1. Sharding, which allows each thread to start at a random memcg (in
   the old generation) and improves parallelism;
2. Eventual fairness, which allows direct reclaim to bail out at will
   and reduces latency without affecting fairness over some time.

The commit message in patch 6 details the workflow:
https://lore.kernel.org/r/20221222041905.2431096-7-yuzhao@google.com/

The following is a simple test to quickly verify its effectiveness.

  Test design:
  1. Create multiple memcgs.
  2. Each memcg contains a job (fio).
  3. All jobs access the same amount of memory randomly.
  4. The system does not experience global memory pressure.
  5. Periodically write to the root memory.reclaim.

  Desired outcome:
  1. All memcgs have similar pgsteal counts, i.e., stddev(pgsteal)
     over mean(pgsteal) is close to 0%.
  2. The total pgsteal is close to the total requested through
     memory.reclaim, i.e., sum(pgsteal) over sum(requested) is close
     to 100%.

  Actual outcome [1]:
                                     MGLRU off    MGLRU on
  stddev(pgsteal) / mean(pgsteal)    75%          20%
  sum(pgsteal) / sum(requested)      425%         95%

  ####################################################################
  MEMCGS=128

  for ((memcg = 0; memcg < $MEMCGS; memcg++)); do
      mkdir /sys/fs/cgroup/memcg$memcg
  done

  start() {
      echo $BASHPID > /sys/fs/cgroup/memcg$memcg/cgroup.procs

      fio -name=memcg$memcg --numjobs=1 --ioengine=mmap \
          --filename=/dev/zero --size=1920M --rw=randrw \
          --rate=64m,64m --random_distribution=random \
          --fadvise_hint=0 --time_based --runtime=10h \
          --group_reporting --minimal
  }

  for ((memcg = 0; memcg < $MEMCGS; memcg++)); do
      start &
  done

  sleep 600

  for ((i = 0; i < 600; i++)); do
      echo 256m >/sys/fs/cgroup/memory.reclaim
      sleep 6
  done

  for ((memcg = 0; memcg < $MEMCGS; memcg++)); do
      grep "pgsteal " /sys/fs/cgroup/memcg$memcg/memory.stat
  done
  ####################################################################

[1]: This was obtained from running the above script (touches less
     than 256GB memory) on an EPYC 7B13 with 512GB DRAM for over an
     hour.


This patch (of 8):

The new name lru_gen_folio will be more distinct from the coming
lru_gen_memcg.

Link: https://lkml.kernel.org/r/20221222041905.2431096-1-yuzhao@google.com
Link: https://lkml.kernel.org/r/20221222041905.2431096-2-yuzhao@google.com
Signed-off-by: Yu Zhao <yuzhao@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Michael Larabel <Michael@MichaelLarabel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Currently a vm_unmap_ram() functions triggers a BUG() if an area is not
found.  Replace it by the WARN_ON_ONCE() error message and keep machine
alive instead of stopping it.

The worst case is a memory leaking.

Link: https://lkml.kernel.org/r/20221222190022.134380-3-urezki@gmail.com
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Reviewed-by: Lorenzo Stoakes <lstoakes@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Baoquan He <bhe@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sony.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Currently the __vunmap() path calls __find_vmap_area() twice.  Once on
entry to check that the area exists, then inside the remove_vm_area()
function which also performs a new search for the VA.

In order to improvie it from a performance point of view we split
remove_vm_area() into two new parts:
  - find_unlink_vmap_area() that does a search and unlink from tree;
  - __remove_vm_area() that removes without searching.

In this case there is no any functional change for remove_vm_area()
whereas vm_remove_mappings(), where a second search happens, switches to
the __remove_vm_area() variant where the already detached VA is passed as
a parameter, so there is no need to find it again.

Performance wise, i use test_vmalloc.sh with 32 threads doing alloc
free on a 64-CPUs-x86_64-box:

perf without this patch:
-   31.41%     0.50%  vmalloc_test/10  [kernel.vmlinux]    [k] __vunmap
   - 30.92% __vunmap
      - 17.67% _raw_spin_lock
           native_queued_spin_lock_slowpath
      - 12.33% remove_vm_area
         - 11.79% free_vmap_area_noflush
            - 11.18% _raw_spin_lock
                 native_queued_spin_lock_slowpath
        0.76% free_unref_page

perf with this patch:
-   11.35%     0.13%  vmalloc_test/14  [kernel.vmlinux]    [k] __vunmap
   - 11.23% __vunmap
      - 8.28% find_unlink_vmap_area
         - 7.95% _raw_spin_lock
              7.44% native_queued_spin_lock_slowpath
      - 1.93% free_vmap_area_noflush
         - 0.56% _raw_spin_lock
              0.53% native_queued_spin_lock_slowpath
        0.60% __vunmap_range_noflush

__vunmap() consumes around ~20% less CPU cycles on this test.

Also, switch from find_vmap_area() to find_unlink_vmap_area() to prevent a
double access to the vmap_area_lock: one for finding area, second time is
for unlinking from a tree.

[urezki@gmail.com: switch to find_unlink_vmap_area() in vm_unmap_ram()]
  Link: https://lkml.kernel.org/r/20221222190022.134380-2-urezki@gmail.com
Link: https://lkml.kernel.org/r/20221222190022.134380-1-urezki@gmail.com
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Reported-by: Roman Gushchin <roman.gushchin@linux.dev>
Reviewed-by: Lorenzo Stoakes <lstoakes@gmail.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sony.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Move FOLL_* definitions to linux/mm_types.h to make them more accessible
without having to drag in all of linux/mm.h and everything that drags in
too[1].

Link: https://lkml.kernel.org/r/2161258.1671657894@warthog.procyon.org.uk
Signed-off-by: David Howells <dhowells@redhat.com>
Suggested-by: Matthew Wilcox <willy@infradead.org>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Similar to kmemdup(), but support large amount of bytes with kvmalloc()
and does *not* guarantee that the result will be physically contiguous. 
Use only in cases where kvmalloc() is needed and free it with kvfree(). 
Also adapt policy_unpack.c in case someone bisect into this.

Link: https://lkml.kernel.org/r/20221221144245.27164-1-sunhao.th@gmail.com
Signed-off-by: Hao Sun <sunhao.th@gmail.com>
Suggested-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Nick Terrell <terrelln@fb.com>
Cc: John Johansen <john.johansen@canonical.com>
Cc: Paul Moore <paul@paul-moore.com>
Cc: James Morris <jmorris@namei.org>
Cc: "Serge E. Hallyn" <serge@hallyn.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Deactivate_page() has already been converted to use folios, this change
converts it to take in a folio argument instead of calling page_folio(). 
It also renames the function folio_deactivate() to be more consistent with
other folio functions.

[akpm@linux-foundation.org: fix left-over comments, per Yu Zhao]
Link: https://lkml.kernel.org/r/20221221180848.20774-5-vishal.moola@gmail.com
Signed-off-by: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

This change replaces 2 calls to compound_head() from put_page() and 1 call
from mark_page_accessed() with one from page_folio().  This is in
preparation for the conversion of deactivate_page() to folio_deactivate().

Link: https://lkml.kernel.org/r/20221221180848.20774-4-vishal.moola@gmail.com
Signed-off-by: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Reviewed-by: SeongJae Park <sj@kernel.org>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

This change removes a number of calls to compound_head(), and saves
1729 bytes of kernel text.

Link: https://lkml.kernel.org/r/20221221180848.20774-3-vishal.moola@gmail.com
Signed-off-by: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Patch series "Convert deactivate_page() to folio_deactivate()", v4.

Deactivate_page() has already been converted to use folios.  This patch
series modifies the callers of deactivate_page() to use folios.  It also
introduces vm_normal_folio() to assist with folio conversions, and
converts deactivate_page() to folio_deactivate() which takes in a folio.


This patch (of 4):

Introduce a wrapper function called vm_normal_folio().  This function
calls vm_normal_page() and returns the folio of the page found, or null if
no page is found.

This function allows callers to get a folio from a pte, which will
eventually allow them to completely replace their struct page variables
with struct folio instead.

Link: https://lkml.kernel.org/r/20221221180848.20774-1-vishal.moola@gmail.com
Link: https://lkml.kernel.org/r/20221221180848.20774-2-vishal.moola@gmail.com
Signed-off-by: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Invert the conditional judgment of the mid_split, to focus the return
statement in the last statement, which is easier to understand and for
better readability.

Link: https://lkml.kernel.org/r/20221221060058.609003-8-vernon2gm@gmail.com
Signed-off-by: Vernon Yang <vernon2gm@gmail.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

If mas->node is an MAS_START, there are three cases, and they all assign
different values to mas->node and mas->offset.  So there is no need to set
them to a default value before updating.

Update them directly to make them easier to understand and for better
readability.

Link: https://lkml.kernel.org/r/20221221060058.609003-7-vernon2gm@gmail.com
Signed-off-by: Vernon Yang <vernon2gm@gmail.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

The macros CONFIG_DEBUG_MAPLE_TREE_VERBOSE no one uses, functions
mas_dup_tree() and mas_dup_store() are not implemented, just function
declaration, so drop it.

Link: https://lkml.kernel.org/r/20221221060058.609003-6-vernon2gm@gmail.com
Signed-off-by: Vernon Yang <vernon2gm@gmail.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

When you need to compare whether node->parent is parent of the
root node, using macro MA_ROOT_PARENT is easier to understand
and for better readability.

Link: https://lkml.kernel.org/r/20221221060058.609003-5-vernon2gm@gmail.com
Signed-off-by: Vernon Yang <vernon2gm@gmail.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Use mt_node_max() to get the maximum number of slots for a node,
rather than direct operations mt_max[], makes it better portability.

Link: https://lkml.kernel.org/r/20221221060058.609003-4-vernon2gm@gmail.com
Signed-off-by: Vernon Yang <vernon2gm@gmail.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

For functions with a return type of void, it is unnecessary to
add a reurn statement at the end of the function, so drop it.

Link: https://lkml.kernel.org/r/20221221060058.609003-3-vernon2gm@gmail.com
Signed-off-by: Vernon Yang <vernon2gm@gmail.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Patch series "Clean up and refinement for maple tree", v2.

This patchset cleans up and refines some maple tree code.  A few small
changes make the code easier to understand and for better readability.


This patch (of 7):

These extra space and blank lines are unnecessary, so drop them.

Link: https://lkml.kernel.org/r/20221221060058.609003-1-vernon2gm@gmail.com
Link: https://lkml.kernel.org/r/20221221060058.609003-2-vernon2gm@gmail.com
Signed-off-by: Vernon Yang <vernon2gm@gmail.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

This function sets __GFP_NOWARN in the gfp_mask rendering the warn_alloc()
invocations no-ops.  Remove this and instead rely on this flag being set
only for the vm_area_alloc_pages() function, ensuring it is cleared for
each of the warn_alloc() calls.

Link: https://lkml.kernel.org/r/20221219123659.90614-1-lstoakes@gmail.com
Signed-off-by: Lorenzo Stoakes <lstoakes@gmail.com>
Reviewed-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Although when a process terminates, the kernel will removes memory
associated with that process, It's neither good style nor proper design to
leave it to kernel.  This patch free allocated memory before process exit.

Link: https://lkml.kernel.org/r/20221219164917.14132-1-iecedge@gmail.com
Signed-off-by: Jianlin Lv <iecedge@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

As Hardware Tag-Based KASAN is intended to be used in production, its
performance impact is crucial.  As page_alloc allocations tend to be big,
tagging and checking all such allocations can introduce a significant
slowdown.

Add two new boot parameters that allow to alleviate that slowdown:

- kasan.page_alloc.sample, which makes Hardware Tag-Based KASAN tag only
  every Nth page_alloc allocation with the order configured by the second
  added parameter (default: tag every such allocation).

- kasan.page_alloc.sample.order, which makes sampling enabled by the first
  parameter only affect page_alloc allocations with the order equal or
  greater than the specified value (default: 3, see below).

The exact performance improvement caused by using the new parameters
depends on their values and the applied workload.

The chosen default value for kasan.page_alloc.sample.order is 3, which
matches both PAGE_ALLOC_COSTLY_ORDER and SKB_FRAG_PAGE_ORDER.  This is
done for two reasons:

1. PAGE_ALLOC_COSTLY_ORDER is "the order at which allocations are deemed
   costly to service", which corresponds to the idea that only large and
   thus costly allocations are supposed to sampled.

2. One of the workloads targeted by this patch is a benchmark that sends
   a large amount of data over a local loopback connection. Most multi-page
   data allocations in the networking subsystem have the order of
   SKB_FRAG_PAGE_ORDER (or PAGE_ALLOC_COSTLY_ORDER).

When running a local loopback test on a testing MTE-enabled device in sync
mode, enabling Hardware Tag-Based KASAN introduces a ~50% slowdown. 
Applying this patch and setting kasan.page_alloc.sampling to a value
higher than 1 allows to lower the slowdown.  The performance improvement
saturates around the sampling interval value of 10 with the default
sampling page order of 3.  This lowers the slowdown to ~20%.  The slowdown
in real scenarios involving the network will likely be better.

Enabling page_alloc sampling has a downside: KASAN misses bad accesses to
a page_alloc allocation that has not been tagged.  This lowers the value
of KASAN as a security mitigation.

However, based on measuring the number of page_alloc allocations of
different orders during boot in a test build, sampling with the default
kasan.page_alloc.sample.order value affects only ~7% of allocations.  The
rest ~93% of allocations are still checked deterministically.

Link: https://lkml.kernel.org/r/129da0614123bb85ed4dd61ae30842b2dd7c903f.1671471846.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Reviewed-by: Marco Elver <elver@google.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Mark Brand <markbrand@google.com>
Cc: Peter Collingbourne <pcc@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

All its callers either already hold a reference to, or lock the swap
device while calling this function.  There is only one exception in
shmem_swapin_folio, just make this caller also hold a reference of the
swap device, so this helper can be simplified and saves a few cycles.

This also provides finer control of error handling in shmem_swapin_folio,
on race (with swap off), it can just try again.  For invalid swap entry,
it can fail with a proper error code.

Link: https://lkml.kernel.org/r/20221219185840.25441-5-ryncsn@gmail.com
Signed-off-by: Kairui Song <kasong@tencent.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

This makes the code cleaner.  This helper is made of only two line of self
explanational code and not reused anywhere else.

And this actually make the compiled object smaller by a bit.

bloat-o-meter results on x86_64 of mm/swap_state.o:

add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-35 (-35)
Function                                     old     new   delta
swap_ra_info.constprop                       512     477     -35
Total: Before=8388, After=8353, chg -0.42%

Link: https://lkml.kernel.org/r/20221219185840.25441-4-ryncsn@gmail.com
Signed-off-by: Kairui Song <kasong@tencent.com>
Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Avoid a redundant pte map/unmap when swap readahead window is 1.

Link: https://lkml.kernel.org/r/20221219185840.25441-3-ryncsn@gmail.com
Signed-off-by: Kairui Song <kasong@tencent.com>
Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Patch series "Clean up and fixes for swap", v2.

This series cleans up some code paths, saves a few cycles and reduces the
object size by a bit.  It also fixes some rare race issue with statistics.


This patch (of 4):

Convert a volatile variable to more readable READ_ONCE.  And this actually
avoids the code from reading the variable twice redundantly when it races.

Link: https://lkml.kernel.org/r/20221219185840.25441-1-ryncsn@gmail.com
Link: https://lkml.kernel.org/r/20221219185840.25441-2-ryncsn@gmail.com
Signed-off-by: Kairui Song <kasong@tencent.com>
Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Document newly added DAMON sysfs interface files for DAMOS filtering on
the DAMON ABI document.

Link: https://lkml.kernel.org/r/20221205230830.144349-12-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Document about the newly added files for DAMOS filters on the DAMON usage
document.

Link: https://lkml.kernel.org/r/20221205230830.144349-11-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Add simple test cases for scheme filters of DAMON sysfs interface.  The
test cases check if the files are populated as expected, receives some
valid inputs, and refuses some invalid inputs.

Link: https://lkml.kernel.org/r/20221205230830.144349-10-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Implement scheme filters functionality of DAMON sysfs interface by making
the code reads the values of files under the filter directories and pass
that to DAMON using DAMON kernel API.

[sj@kernel.org: fix leaking a filter for wrong cgroup path]
  Link: https://lkml.kernel.org/r/20221219171807.55708-2-sj@kernel.org
[sj@kernel.org: return an error for filter memcg path id lookup failure]
  Link: https://lkml.kernel.org/r/20221219171807.55708-3-sj@kernel.org
Link: https://lkml.kernel.org/r/20221205230830.144349-9-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Implement 'nr_filters' file under 'filters' directory, which will be used
to populate specific number of 'filter' directory under the directory,
similar to other 'nr_*' files in DAMON sysfs interface.

Link: https://lkml.kernel.org/r/20221205230830.144349-8-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Implement DAMOS filter directory which will be located under the filters
directory.  The directory provides three files, namely type, matching, and
memcg_path.  'type' and 'matching' will be directly connected to the
fields of 'struct damos_filter' having same name.  'memcg_path' will
receive the path of the memory cgroup of the interest and later converted
to memcg id when it's committed.

Link: https://lkml.kernel.org/r/20221205230830.144349-7-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

DAMOS filters are currently supported by only DAMON kernel API.  To expose
the feature to user space, implement a DAMON sysfs directory named
'filters' under each scheme directory.  Please note that this is
implementing only the directory.  Following commits will implement more
files and directories, and finally connect the DAMOS filters feature.

Link: https://lkml.kernel.org/r/20221205230830.144349-6-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Document the newly added 'skip_anon' parameter of DAMON_RECLAIM, which can
be used to avoid anonymous pages reclamation.

Link: https://lkml.kernel.org/r/20221205230830.144349-5-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

In some cases, for example if users have confidence at anonymous pages
management or the swap device is too slow, users would want to avoid
DAMON_RECLAIM swapping the anonymous pages out.  For such case, add yet
another DAMON_RECLAIM parameter, namely 'skip_anon'.  When it is set as
'Y', DAMON_RECLAIM will avoid reclaiming anonymous pages using a DAMOS
filter.

Link: https://lkml.kernel.org/r/20221205230830.144349-4-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Implement support of the DAMOS filters in the physical address space
monitoring operations set, for all DAMOS actions that it supports
including 'pageout', 'lru_prio', and 'lru_deprio'.

Link: https://lkml.kernel.org/r/20221205230830.144349-3-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Patch series "implement DAMOS filtering for anon pages and/or specific
memory cgroups"

DAMOS let users do system operations in a data access pattern oriented
way.  The data access pattern, which is extracted by DAMON, is somewhat
accurate more than what user space could know in many cases.  However, in
some situation, users could know something more than the kernel about the
pattern or some special requirements for some types of memory or
processes.  For example, some users would have slow swap devices and knows
latency-ciritical processes and therefore want to use DAMON-based
proactive reclamation (DAMON_RECLAIM) for only non-anonymous pages of
non-latency-critical processes.

For such restriction, users could exclude the memory regions from the
initial monitoring regions and use non-dynamic monitoring regions update
monitoring operations set including fvaddr and paddr.  They could also
adjust the DAMOS target access pattern.  For dynamically changing memory
layout and access pattern, those would be not enough.

To help the case, add an interface, namely DAMOS filters, which can be
used to avoid the DAMOS actions be applied to specific types of memory, to
DAMON kernel API (damon.h).  At the moment, it supports filtering
anonymous pages and/or specific memory cgroups in or out for each DAMOS
scheme.

This patchset adds the support for all DAMOS actions that 'paddr'
monitoring operations set supports ('pageout', 'lru_prio', and
'lru_deprio'), and the functionality is exposed via DAMON kernel API
(damon.h) the DAMON sysfs interface (/sys/kernel/mm/damon/admins/), and
DAMON_RECLAIM module parameters.

Patches Sequence
----------------

First patch implements DAMOS filter interface to DAMON kernel API.  Second
patch makes the physical address space monitoring operations set to
support the filters from all supporting DAMOS actions.  Third patch adds
anonymous pages filter support to DAMON_RECLAIM, and the fourth patch
documents the DAMON_RECLAIM's new feature.  Fifth to seventh patches
implement DAMON sysfs files for support of the filters, and eighth patch
connects the file to use DAMOS filters feature.  Ninth patch adds simple
self test cases for DAMOS filters of the sysfs interface.  Finally,
following two patches (tenth and eleventh) document the new features and
interfaces.


This patch (of 11):

DAMOS lets users do system operation in a data access pattern oriented
way.  The data access pattern, which is extracted by DAMON, is somewhat
accurate more than what user space could know in many cases.  However, in
some situation, users could know something more than the kernel about the
pattern or some special requirements for some types of memory or
processes.  For example, some users would have slow swap devices and knows
latency-ciritical processes and therefore want to use DAMON-based
proactive reclamation (DAMON_RECLAIM) for only non-anonymous pages of
non-latency-critical processes.

For such restriction, users could exclude the memory regions from the
initial monitoring regions and use non-dynamic monitoring regions update
monitoring operations set including fvaddr and paddr.  They could also
adjust the DAMOS target access pattern.  For dynamically changing memory
layout and access pattern, those would be not enough.

To help the case, add an interface, namely DAMOS filters, which can be
used to avoid the DAMOS actions be applied to specific types of memory, to
DAMON kernel API (damon.h).  At the moment, it supports filtering
anonymous pages and/or specific memory cgroups in or out for each DAMOS
scheme.

Note that this commit adds only the interface to the DAMON kernel API. 
The impelmentation should be made in the monitoring operations sets, and
following commits will add that.

Link: https://lkml.kernel.org/r/20221205230830.144349-1-sj@kernel.org
Link: https://lkml.kernel.org/r/20221205230830.144349-2-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Charge moving mode in cgroup1 allows memory to follow tasks as they
migrate between cgroups.  This is, and always has been, a questionable
thing to do - for several reasons.

First, it's expensive.  Pages need to be identified, locked and isolated
from various MM operations, and reassigned, one by one.

Second, it's unreliable.  Once pages are charged to a cgroup, there isn't
always a clear owner task anymore.  Cache isn't moved at all, for example.
Mapped memory is moved - but if trylocking or isolating a page fails,
it's arbitrarily left behind.  Frequent moving between domains may leave a
task's memory scattered all over the place.

Third, it isn't really needed.  Launcher tasks can kick off workload tasks
directly in their target cgroup.  Using dedicated per-workload groups
allows fine-grained policy adjustments - no need to move tasks and their
physical pages between control domains.  The feature was never
forward-ported to cgroup2, and it hasn't been missed.

Despite it being a niche usecase, the maintenance overhead of supporting
it is enormous.  Because pages are moved while they are live and subject
to various MM operations, the synchronization rules are complicated. 
There are lock_page_memcg() in MM and FS code, which non-cgroup people
don't understand.  In some cases we've been able to shift code and cgroup
API calls around such that we can rely on native locking as much as
possible.  But that's fragile, and sometimes we need to hold MM locks for
longer than we otherwise would (pte lock e.g.).

Mark the feature deprecated. Hopefully we can remove it soon.

And backport into -stable kernels so that people who develop against
earlier kernels are warned about this deprecation as early as possible.

[akpm@linux-foundation.org: fix memory.rst underlining]
Link: https://lkml.kernel.org/r/Y5COd+qXwk/S+n8N@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Hugh Dickins <hughd@google.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>