Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:
 "257 patches.

  Subsystems affected by this patch series: scripts, ocfs2, vfs, and
  mm (slab-generic, slab, slub, kconfig, dax, kasan, debug, pagecache,
  gup, swap, memcg, pagemap, mprotect, mremap, iomap, tracing, vmalloc,
  pagealloc, memory-failure, hugetlb, userfaultfd, vmscan, tools,
  memblock, oom-kill, hugetlbfs, migration, thp, readahead, nommu, ksm,
  vmstat, madvise, memory-hotplug, rmap, zsmalloc, highmem, zram,
  cleanups, kfence, and damon)"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (257 commits)
  mm/damon: remove return value from before_terminate callback
  mm/damon: fix a few spelling mistakes in comments and a pr_debug message
  mm/damon: simplify stop mechanism
  Docs/admin-guide/mm/pagemap: wordsmith page flags descriptions
  Docs/admin-guide/mm/damon/start: simplify the content
  Docs/admin-guide/mm/damon/start: fix a wrong link
  Docs/admin-guide/mm/damon/start: fix wrong example commands
  mm/damon/dbgfs: add adaptive_targets list check before enable monitor_on
  mm/damon: remove unnecessary variable initialization
  Documentation/admin-guide/mm/damon: add a document for DAMON_RECLAIM
  mm/damon: introduce DAMON-based Reclamation (DAMON_RECLAIM)
  selftests/damon: support watermarks
  mm/damon/dbgfs: support watermarks
  mm/damon/schemes: activate schemes based on a watermarks mechanism
  tools/selftests/damon: update for regions prioritization of schemes
  mm/damon/dbgfs: support prioritization weights
  mm/damon/vaddr,paddr: support pageout prioritization
  mm/damon/schemes: prioritize regions within the quotas
  mm/damon/selftests: support schemes quotas
  mm/damon/dbgfs: support quotas of schemes
  ...

Documentation/admin-guide/blockdev/zram.rst

@@ -328,6 +328,14 @@ as idle::
 From now on, any pages on zram are idle pages. The idle mark
 will be removed until someone requests access of the block.
 IOW, unless there is access request, those pages are still idle pages.
+Additionally, when CONFIG_ZRAM_MEMORY_TRACKING is enabled pages can be
+marked as idle based on how long (in seconds) it's been since they were
+last accessed::
+
+        echo 86400 > /sys/block/zramX/idle
+
+In this example all pages which haven't been accessed in more than 86400
+seconds (one day) will be marked idle.
 
 Admin can request writeback of those idle pages at right timing via::
 

Documentation/admin-guide/cgroup-v1/memory.rst

@@ -87,10 +87,8 @@ Brief summary of control files.
  memory.oom_control		     set/show oom controls.
  memory.numa_stat		     show the number of memory usage per numa
 				     node
- memory.kmem.limit_in_bytes          set/show hard limit for kernel memory
+ memory.kmem.limit_in_bytes          This knob is deprecated and writing to
-                                     This knob is deprecated and shouldn't be
+                                     it will return -ENOTSUPP.
-                                     used. It is planned that this be removed in
-                                     the foreseeable future.
  memory.kmem.usage_in_bytes          show current kernel memory allocation
  memory.kmem.failcnt                 show the number of kernel memory usage
 				     hits limits
@@ -518,11 +516,6 @@ will be charged as a new owner of it.
   charged file caches. Some out-of-use page caches may keep charged until
   memory pressure happens. If you want to avoid that, force_empty will be useful.
 
-  Also, note that when memory.kmem.limit_in_bytes is set the charges due to
-  kernel pages will still be seen. This is not considered a failure and the
-  write will still return success. In this case, it is expected that
-  memory.kmem.usage_in_bytes == memory.usage_in_bytes.
-
 5.2 stat file
 -------------
 

Documentation/admin-guide/kernel-parameters.txt

@@ -1582,8 +1582,10 @@
 			registers.  Default set by CONFIG_HPET_MMAP_DEFAULT.
 
 	hugetlb_cma=	[HW,CMA] The size of a CMA area used for allocation
-			of gigantic hugepages.
+			of gigantic hugepages. Or using node format, the size
-			Format: nn[KMGTPE]
+			of a CMA area per node can be specified.
+			Format: nn[KMGTPE] or (node format)
+				<node>:nn[KMGTPE][,<node>:nn[KMGTPE]]
 
 			Reserve a CMA area of given size and allocate gigantic
 			hugepages using the CMA allocator. If enabled, the
@@ -1594,9 +1596,11 @@
 			the number of pages of hugepagesz to be allocated.
 			If this is the first HugeTLB parameter on the command
 			line, it specifies the number of pages to allocate for
-			the default huge page size.  See also
+			the default huge page size. If using node format, the
-			Documentation/admin-guide/mm/hugetlbpage.rst.
+			number of pages to allocate per-node can be specified.
-			Format: <integer>
+			See also Documentation/admin-guide/mm/hugetlbpage.rst.
+			Format: <integer> or (node format)
+				<node>:<integer>[,<node>:<integer>]
 
 	hugepagesz=
 			[HW] The size of the HugeTLB pages.  This is used in

Documentation/admin-guide/mm/damon/index.rst

@@ -13,3 +13,4 @@ optimize those.
 
    start
    usage
+   reclaim

Documentation/admin-guide/mm/damon/reclaim.rst

@@ -0,0 +1,235 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=======================
+DAMON-based Reclamation
+=======================
+
+DAMON-based Reclamation (DAMON_RECLAIM) is a static kernel module that aimed to
+be used for proactive and lightweight reclamation under light memory pressure.
+It doesn't aim to replace the LRU-list based page_granularity reclamation, but
+to be selectively used for different level of memory pressure and requirements.
+
+Where Proactive Reclamation is Required?
+========================================
+
+On general memory over-committed systems, proactively reclaiming cold pages
+helps saving memory and reducing latency spikes that incurred by the direct
+reclaim of the process or CPU consumption of kswapd, while incurring only
+minimal performance degradation [1]_ [2]_ .
+
+Free Pages Reporting [3]_ based memory over-commit virtualization systems are
+good example of the cases.  In such systems, the guest VMs reports their free
+memory to host, and the host reallocates the reported memory to other guests.
+As a result, the memory of the systems are fully utilized.  However, the
+guests could be not so memory-frugal, mainly because some kernel subsystems and
+user-space applications are designed to use as much memory as available.  Then,
+guests could report only small amount of memory as free to host, results in
+memory utilization drop of the systems.  Running the proactive reclamation in
+guests could mitigate this problem.
+
+How It Works?
+=============
+
+DAMON_RECLAIM finds memory regions that didn't accessed for specific time
+duration and page out.  To avoid it consuming too much CPU for the paging out
+operation, a speed limit can be configured.  Under the speed limit, it pages
+out memory regions that didn't accessed longer time first.  System
+administrators can also configure under what situation this scheme should
+automatically activated and deactivated with three memory pressure watermarks.
+
+Interface: Module Parameters
+============================
+
+To use this feature, you should first ensure your system is running on a kernel
+that is built with ``CONFIG_DAMON_RECLAIM=y``.
+
+To let sysadmins enable or disable it and tune for the given system,
+DAMON_RECLAIM utilizes module parameters.  That is, you can put
+``damon_reclaim.<parameter>=<value>`` on the kernel boot command line or write
+proper values to ``/sys/modules/damon_reclaim/parameters/<parameter>`` files.
+
+Note that the parameter values except ``enabled`` are applied only when
+DAMON_RECLAIM starts.  Therefore, if you want to apply new parameter values in
+runtime and DAMON_RECLAIM is already enabled, you should disable and re-enable
+it via ``enabled`` parameter file.  Writing of the new values to proper
+parameter values should be done before the re-enablement.
+
+Below are the description of each parameter.
+
+enabled
+-------
+
+Enable or disable DAMON_RECLAIM.
+
+You can enable DAMON_RCLAIM by setting the value of this parameter as ``Y``.
+Setting it as ``N`` disables DAMON_RECLAIM.  Note that DAMON_RECLAIM could do
+no real monitoring and reclamation due to the watermarks-based activation
+condition.  Refer to below descriptions for the watermarks parameter for this.
+
+min_age
+-------
+
+Time threshold for cold memory regions identification in microseconds.
+
+If a memory region is not accessed for this or longer time, DAMON_RECLAIM
+identifies the region as cold, and reclaims it.
+
+120 seconds by default.
+
+quota_ms
+--------
+
+Limit of time for the reclamation in milliseconds.
+
+DAMON_RECLAIM tries to use only up to this time within a time window
+(quota_reset_interval_ms) for trying reclamation of cold pages.  This can be
+used for limiting CPU consumption of DAMON_RECLAIM.  If the value is zero, the
+limit is disabled.
+
+10 ms by default.
+
+quota_sz
+--------
+
+Limit of size of memory for the reclamation in bytes.
+
+DAMON_RECLAIM charges amount of memory which it tried to reclaim within a time
+window (quota_reset_interval_ms) and makes no more than this limit is tried.
+This can be used for limiting consumption of CPU and IO.  If this value is
+zero, the limit is disabled.
+
+128 MiB by default.
+
+quota_reset_interval_ms
+-----------------------
+
+The time/size quota charge reset interval in milliseconds.
+
+The charget reset interval for the quota of time (quota_ms) and size
+(quota_sz).  That is, DAMON_RECLAIM does not try reclamation for more than
+quota_ms milliseconds or quota_sz bytes within quota_reset_interval_ms
+milliseconds.
+
+1 second by default.
+
+wmarks_interval
+---------------
+
+Minimal time to wait before checking the watermarks, when DAMON_RECLAIM is
+enabled but inactive due to its watermarks rule.
+
+wmarks_high
+-----------
+
+Free memory rate (per thousand) for the high watermark.
+
+If free memory of the system in bytes per thousand bytes is higher than this,
+DAMON_RECLAIM becomes inactive, so it does nothing but only periodically checks
+the watermarks.
+
+wmarks_mid
+----------
+
+Free memory rate (per thousand) for the middle watermark.
+
+If free memory of the system in bytes per thousand bytes is between this and
+the low watermark, DAMON_RECLAIM becomes active, so starts the monitoring and
+the reclaiming.
+
+wmarks_low
+----------
+
+Free memory rate (per thousand) for the low watermark.
+
+If free memory of the system in bytes per thousand bytes is lower than this,
+DAMON_RECLAIM becomes inactive, so it does nothing but periodically checks the
+watermarks.  In the case, the system falls back to the LRU-list based page
+granularity reclamation logic.
+
+sample_interval
+---------------
+
+Sampling interval for the monitoring in microseconds.
+
+The sampling interval of DAMON for the cold memory monitoring.  Please refer to
+the DAMON documentation (:doc:`usage`) for more detail.
+
+aggr_interval
+-------------
+
+Aggregation interval for the monitoring in microseconds.
+
+The aggregation interval of DAMON for the cold memory monitoring.  Please
+refer to the DAMON documentation (:doc:`usage`) for more detail.
+
+min_nr_regions
+--------------
+
+Minimum number of monitoring regions.
+
+The minimal number of monitoring regions of DAMON for the cold memory
+monitoring.  This can be used to set lower-bound of the monitoring quality.
+But, setting this too high could result in increased monitoring overhead.
+Please refer to the DAMON documentation (:doc:`usage`) for more detail.
+
+max_nr_regions
+--------------
+
+Maximum number of monitoring regions.
+
+The maximum number of monitoring regions of DAMON for the cold memory
+monitoring.  This can be used to set upper-bound of the monitoring overhead.
+However, setting this too low could result in bad monitoring quality.  Please
+refer to the DAMON documentation (:doc:`usage`) for more detail.
+
+monitor_region_start
+--------------------
+
+Start of target memory region in physical address.
+
+The start physical address of memory region that DAMON_RECLAIM will do work
+against.  That is, DAMON_RECLAIM will find cold memory regions in this region
+and reclaims.  By default, biggest System RAM is used as the region.
+
+monitor_region_end
+------------------
+
+End of target memory region in physical address.
+
+The end physical address of memory region that DAMON_RECLAIM will do work
+against.  That is, DAMON_RECLAIM will find cold memory regions in this region
+and reclaims.  By default, biggest System RAM is used as the region.
+
+kdamond_pid
+-----------
+
+PID of the DAMON thread.
+
+If DAMON_RECLAIM is enabled, this becomes the PID of the worker thread.  Else,
+-1.
+
+Example
+=======
+
+Below runtime example commands make DAMON_RECLAIM to find memory regions that
+not accessed for 30 seconds or more and pages out.  The reclamation is limited
+to be done only up to 1 GiB per second to avoid DAMON_RECLAIM consuming too
+much CPU time for the paging out operation.  It also asks DAMON_RECLAIM to do
+nothing if the system's free memory rate is more than 50%, but start the real
+works if it becomes lower than 40%.  If DAMON_RECLAIM doesn't make progress and
+therefore the free memory rate becomes lower than 20%, it asks DAMON_RECLAIM to
+do nothing again, so that we can fall back to the LRU-list based page
+granularity reclamation. ::
+
+    # cd /sys/modules/damon_reclaim/parameters
+    # echo 30000000 > min_age
+    # echo $((1 * 1024 * 1024 * 1024)) > quota_sz
+    # echo 1000 > quota_reset_interval_ms
+    # echo 500 > wmarks_high
+    # echo 400 > wmarks_mid
+    # echo 200 > wmarks_low
+    # echo Y > enabled
+
+.. [1] https://research.google/pubs/pub48551/
+.. [2] https://lwn.net/Articles/787611/
+.. [3] https://www.kernel.org/doc/html/latest/vm/free_page_reporting.html

Documentation/admin-guide/mm/damon/start.rst

@@ -6,39 +6,9 @@ Getting Started
 
 This document briefly describes how you can use DAMON by demonstrating its
 default user space tool.  Please note that this document describes only a part
-of its features for brevity.  Please refer to :doc:`usage` for more details.
+of its features for brevity.  Please refer to the usage `doc
-
+<https://github.com/awslabs/damo/blob/next/USAGE.md>`_ of the tool for more
-
+details.
-TL; DR
-======
-
-Follow the commands below to monitor and visualize the memory access pattern of
-your workload. ::
-
-    # # build the kernel with CONFIG_DAMON_*=y, install it, and reboot
-    # mount -t debugfs none /sys/kernel/debug/
-    # git clone https://github.com/awslabs/damo
-    # ./damo/damo record $(pidof <your workload>)
-    # ./damo/damo report heat --plot_ascii
-
-The final command draws the access heatmap of ``<your workload>``.  The heatmap
-shows which memory region (x-axis) is accessed when (y-axis) and how frequently
-(number; the higher the more accesses have been observed). ::
-
-    111111111111111111111111111111111111111111111111111111110000
-    111121111111111111111111111111211111111111111111111111110000
-    000000000000000000000000000000000000000000000000001555552000
-    000000000000000000000000000000000000000000000222223555552000
-    000000000000000000000000000000000000000011111677775000000000
-    000000000000000000000000000000000000000488888000000000000000
-    000000000000000000000000000000000177888400000000000000000000
-    000000000000000000000000000046666522222100000000000000000000
-    000000000000000000000014444344444300000000000000000000000000
-    000000000000000002222245555510000000000000000000000000000000
-    # access_frequency:  0  1  2  3  4  5  6  7  8  9
-    # x-axis: space (140286319947776-140286426374096: 101.496 MiB)
-    # y-axis: time (605442256436361-605479951866441: 37.695430s)
-    # resolution: 60x10 (1.692 MiB and 3.770s for each character)
 
 
 Prerequisites
@@ -91,24 +61,74 @@ pattern in the ``damon.data`` file.
 Visualizing Recorded Patterns
 =============================
 
-The following three commands visualize the recorded access patterns and save
+You can visualize the pattern in a heatmap, showing which memory region
-the results as separate image files. ::
+(x-axis) got accessed when (y-axis) and how frequently (number).::
 
-    $ damo report heats --heatmap access_pattern_heatmap.png
+    $ sudo damo report heats --heatmap stdout
-    $ damo report wss --range 0 101 1 --plot wss_dist.png
+    22222222222222222222222222222222222222211111111111111111111111111111111111111100
-    $ damo report wss --range 0 101 1 --sortby time --plot wss_chron_change.png
+    44444444444444444444444444444444444444434444444444444444444444444444444444443200
+    44444444444444444444444444444444444444433444444444444444444444444444444444444200
+    33333333333333333333333333333333333333344555555555555555555555555555555555555200
+    33333333333333333333333333333333333344444444444444444444444444444444444444444200
+    22222222222222222222222222222222222223355555555555555555555555555555555555555200
+    00000000000000000000000000000000000000288888888888888888888888888888888888888400
+    00000000000000000000000000000000000000288888888888888888888888888888888888888400
+    33333333333333333333333333333333333333355555555555555555555555555555555555555200
+    88888888888888888888888888888888888888600000000000000000000000000000000000000000
+    88888888888888888888888888888888888888600000000000000000000000000000000000000000
+    33333333333333333333333333333333333333444444444444444444444444444444444444443200
+    00000000000000000000000000000000000000288888888888888888888888888888888888888400
+    [...]
+    # access_frequency:  0  1  2  3  4  5  6  7  8  9
+    # x-axis: space (139728247021568-139728453431248: 196.848 MiB)
+    # y-axis: time (15256597248362-15326899978162: 1 m 10.303 s)
+    # resolution: 80x40 (2.461 MiB and 1.758 s for each character)
 
-- ``access_pattern_heatmap.png`` will visualize the data access pattern in a
+You can also visualize the distribution of the working set size, sorted by the
-  heatmap, showing which memory region (y-axis) got accessed when (x-axis)
+size.::
-  and how frequently (color).
-- ``wss_dist.png`` will show the distribution of the working set size.
-- ``wss_chron_change.png`` will show how the working set size has
-  chronologically changed.
 
-You can view the visualizations of this example workload at [1]_.
+    $ sudo damo report wss --range 0 101 10
-Visualizations of other realistic workloads are available at [2]_ [3]_ [4]_.
+    # <percentile> <wss>
+    # target_id     18446632103789443072
+    # avr:  107.708 MiB
+      0             0 B |                                                           |
+     10      95.328 MiB |****************************                               |
+     20      95.332 MiB |****************************                               |
+     30      95.340 MiB |****************************                               |
+     40      95.387 MiB |****************************                               |
+     50      95.387 MiB |****************************                               |
+     60      95.398 MiB |****************************                               |
+     70      95.398 MiB |****************************                               |
+     80      95.504 MiB |****************************                               |
+     90     190.703 MiB |*********************************************************  |
+    100     196.875 MiB |***********************************************************|
 
-.. [1] https://damonitor.github.io/doc/html/v17/admin-guide/mm/damon/start.html#visualizing-recorded-patterns
+Using ``--sortby`` option with the above command, you can show how the working
-.. [2] https://damonitor.github.io/test/result/visual/latest/rec.heatmap.1.png.html
+set size has chronologically changed.::
-.. [3] https://damonitor.github.io/test/result/visual/latest/rec.wss_sz.png.html
+
-.. [4] https://damonitor.github.io/test/result/visual/latest/rec.wss_time.png.html
+    $ sudo damo report wss --range 0 101 10 --sortby time
+    # <percentile> <wss>
+    # target_id     18446632103789443072
+    # avr:  107.708 MiB
+      0       3.051 MiB |                                                           |
+     10     190.703 MiB |***********************************************************|
+     20      95.336 MiB |*****************************                              |
+     30      95.328 MiB |*****************************                              |
+     40      95.387 MiB |*****************************                              |
+     50      95.332 MiB |*****************************                              |
+     60      95.320 MiB |*****************************                              |
+     70      95.398 MiB |*****************************                              |
+     80      95.398 MiB |*****************************                              |
+     90      95.340 MiB |*****************************                              |
+    100      95.398 MiB |*****************************                              |
+
+
+Data Access Pattern Aware Memory Management
+===========================================
+
+Below three commands make every memory region of size >=4K that doesn't
+accessed for >=60 seconds in your workload to be swapped out. ::
+
+    $ echo "#min-size max-size min-acc max-acc min-age max-age action" > test_scheme
+    $ echo "4K        max      0       0       60s     max     pageout" >> test_scheme
+    $ damo schemes -c test_scheme <pid of your workload>

Documentation/admin-guide/mm/damon/usage.rst

@@ -10,15 +10,16 @@ DAMON provides below three interfaces for different users.
   This is for privileged people such as system administrators who want a
   just-working human-friendly interface.  Using this, users can use the DAMON’s
   major features in a human-friendly way.  It may not be highly tuned for
-  special cases, though.  It supports only virtual address spaces monitoring.
+  special cases, though.  It supports both virtual and physical address spaces
+  monitoring.
 - *debugfs interface.*
   This is for privileged user space programmers who want more optimized use of
   DAMON.  Using this, users can use DAMON’s major features by reading
   from and writing to special debugfs files.  Therefore, you can write and use
   your personalized DAMON debugfs wrapper programs that reads/writes the
   debugfs files instead of you.  The DAMON user space tool is also a reference
-  implementation of such programs.  It supports only virtual address spaces
+  implementation of such programs.  It supports both virtual and physical
-  monitoring.
+  address spaces monitoring.
 - *Kernel Space Programming Interface.*
   This is for kernel space programmers.  Using this, users can utilize every
   feature of DAMON most flexibly and efficiently by writing kernel space
@@ -34,8 +35,9 @@ the reason, this document describes only the debugfs interface
 debugfs Interface
 =================
 
-DAMON exports three files, ``attrs``, ``target_ids``, and ``monitor_on`` under
+DAMON exports five files, ``attrs``, ``target_ids``, ``init_regions``,
-its debugfs directory, ``<debugfs>/damon/``.
+``schemes`` and ``monitor_on`` under its debugfs directory,
+``<debugfs>/damon/``.
 
 
 Attributes
@@ -71,9 +73,106 @@ check it again::
     # cat target_ids
     42 4242
 
+Users can also monitor the physical memory address space of the system by
+writing a special keyword, "``paddr\n``" to the file.  Because physical address
+space monitoring doesn't support multiple targets, reading the file will show a
+fake value, ``42``, as below::
+
+    # cd <debugfs>/damon
+    # echo paddr > target_ids
+    # cat target_ids
+    42
+
 Note that setting the target ids doesn't start the monitoring.
 
 
+Initial Monitoring Target Regions
+---------------------------------
+
+In case of the virtual address space monitoring, DAMON automatically sets and
+updates the monitoring target regions so that entire memory mappings of target
+processes can be covered.  However, users can want to limit the monitoring
+region to specific address ranges, such as the heap, the stack, or specific
+file-mapped area.  Or, some users can know the initial access pattern of their
+workloads and therefore want to set optimal initial regions for the 'adaptive
+regions adjustment'.
+
+In contrast, DAMON do not automatically sets and updates the monitoring target
+regions in case of physical memory monitoring.  Therefore, users should set the
+monitoring target regions by themselves.
+
+In such cases, users can explicitly set the initial monitoring target regions
+as they want, by writing proper values to the ``init_regions`` file.  Each line
+of the input should represent one region in below form.::
+
+    <target id> <start address> <end address>
+
+The ``target id`` should already in ``target_ids`` file, and the regions should
+be passed in address order.  For example, below commands will set a couple of
+address ranges, ``1-100`` and ``100-200`` as the initial monitoring target
+region of process 42, and another couple of address ranges, ``20-40`` and
+``50-100`` as that of process 4242.::
+
+    # cd <debugfs>/damon
+    # echo "42   1       100
+            42   100     200
+            4242 20      40
+            4242 50      100" > init_regions
+
+Note that this sets the initial monitoring target regions only.  In case of
+virtual memory monitoring, DAMON will automatically updates the boundary of the
+regions after one ``regions update interval``.  Therefore, users should set the
+``regions update interval`` large enough in this case, if they don't want the
+update.
+
+
+Schemes
+-------
+
+For usual DAMON-based data access aware memory management optimizations, users
+would simply want the system to apply a memory management action to a memory
+region of a specific size having a specific access frequency for a specific
+time.  DAMON receives such formalized operation schemes from the user and
+applies those to the target processes.  It also counts the total number and
+size of regions that each scheme is applied.  This statistics can be used for
+online analysis or tuning of the schemes.
+
+Users can get and set the schemes by reading from and writing to ``schemes``
+debugfs file.  Reading the file also shows the statistics of each scheme.  To
+the file, each of the schemes should be represented in each line in below form:
+
+    min-size max-size min-acc max-acc min-age max-age action
+
+Note that the ranges are closed interval.  Bytes for the size of regions
+(``min-size`` and ``max-size``), number of monitored accesses per aggregate
+interval for access frequency (``min-acc`` and ``max-acc``), number of
+aggregate intervals for the age of regions (``min-age`` and ``max-age``), and a
+predefined integer for memory management actions should be used.  The supported
+numbers and their meanings are as below.
+
+ - 0: Call ``madvise()`` for the region with ``MADV_WILLNEED``
+ - 1: Call ``madvise()`` for the region with ``MADV_COLD``
+ - 2: Call ``madvise()`` for the region with ``MADV_PAGEOUT``
+ - 3: Call ``madvise()`` for the region with ``MADV_HUGEPAGE``
+ - 4: Call ``madvise()`` for the region with ``MADV_NOHUGEPAGE``
+ - 5: Do nothing but count the statistics
+
+You can disable schemes by simply writing an empty string to the file.  For
+example, below commands applies a scheme saying "If a memory region of size in
+[4KiB, 8KiB] is showing accesses per aggregate interval in [0, 5] for aggregate
+interval in [10, 20], page out the region", check the entered scheme again, and
+finally remove the scheme. ::
+
+    # cd <debugfs>/damon
+    # echo "4096 8192    0 5    10 20    2" > schemes
+    # cat schemes
+    4096 8192 0 5 10 20 2 0 0
+    # echo > schemes
+
+The last two integers in the 4th line of above example is the total number and
+the total size of the regions that the scheme is applied.
+
+
 Turning On/Off
 --------------
 

Documentation/admin-guide/mm/hugetlbpage.rst

@@ -128,7 +128,9 @@ hugepages
 	implicitly specifies the number of huge pages of default size to
 	allocate.  If the number of huge pages of default size is implicitly
 	specified, it can not be overwritten by a hugepagesz,hugepages
-	parameter pair for the default size.
+	parameter pair for the default size.  This parameter also has a
+	node format.  The node format specifies the number of huge pages
+	to allocate on specific nodes.
 
 	For example, on an architecture with 2M default huge page size::
 
@@ -138,6 +140,14 @@ hugepages
 	indicating that the hugepages=512 parameter is ignored.  If a hugepages
 	parameter is preceded by an invalid hugepagesz parameter, it will
 	be ignored.
+
+	Node format example::
+
+		hugepagesz=2M hugepages=0:1,1:2
+
+	It will allocate 1 2M hugepage on node0 and 2 2M hugepages on node1.
+	If the node number is invalid,  the parameter will be ignored.
+
 default_hugepagesz
 	Specify the default huge page size.  This parameter can
 	only be specified once on the command line.  default_hugepagesz can
@@ -234,8 +244,12 @@ will exist, of the form::
 
 	hugepages-${size}kB
 
-Inside each of these directories, the same set of files will exist::
+Inside each of these directories, the set of files contained in ``/proc``
+will exist.  In addition, two additional interfaces for demoting huge
+pages may exist::
 
+        demote
+        demote_size
 	nr_hugepages
 	nr_hugepages_mempolicy
 	nr_overcommit_hugepages
@@ -243,7 +257,29 @@ Inside each of these directories, the same set of files will exist::
 	resv_hugepages
 	surplus_hugepages
 
-which function as described above for the default huge page-sized case.
+The demote interfaces provide the ability to split a huge page into
+smaller huge pages.  For example, the x86 architecture supports both
+1GB and 2MB huge pages sizes.  A 1GB huge page can be split into 512
+2MB huge pages.  Demote interfaces are not available for the smallest
+huge page size.  The demote interfaces are:
+
+demote_size
+        is the size of demoted pages.  When a page is demoted a corresponding
+        number of huge pages of demote_size will be created.  By default,
+        demote_size is set to the next smaller huge page size.  If there are
+        multiple smaller huge page sizes, demote_size can be set to any of
+        these smaller sizes.  Only huge page sizes less than the current huge
+        pages size are allowed.
+
+demote
+        is used to demote a number of huge pages.  A user with root privileges
+        can write to this file.  It may not be possible to demote the
+        requested number of huge pages.  To determine how many pages were
+        actually demoted, compare the value of nr_hugepages before and after
+        writing to the demote interface.  demote is a write only interface.
+
+The interfaces which are the same as in ``/proc`` (all except demote and
+demote_size) function as described above for the default huge page-sized case.
 
 .. _mem_policy_and_hp_alloc:
 

Documentation/admin-guide/mm/index.rst

@@ -37,5 +37,7 @@ the Linux memory management.
    numaperf
    pagemap
    soft-dirty
+   swap_numa
    transhuge
    userfaultfd
+   zswap

Documentation/admin-guide/mm/memory-hotplug.rst

@@ -165,9 +165,8 @@ Or alternatively::
 
 	% echo 1 > /sys/devices/system/memory/memoryXXX/online
 
-The kernel will select the target zone automatically, usually defaulting to
+The kernel will select the target zone automatically, depending on the
-``ZONE_NORMAL`` unless ``movablecore=1`` has been specified on the kernel
+configured ``online_policy``.
-command line or if the memory block would intersect the ZONE_MOVABLE already.
 
 One can explicitly request to associate an offline memory block with
 ZONE_MOVABLE by::
@@ -198,6 +197,9 @@ Auto-onlining can be enabled by writing ``online``, ``online_kernel`` or
 
 	% echo online > /sys/devices/system/memory/auto_online_blocks
 
+Similarly to manual onlining, with ``online`` the kernel will select the
+target zone automatically, depending on the configured ``online_policy``.
+
 Modifying the auto-online behavior will only affect all subsequently added
 memory blocks only.
 
@@ -393,11 +395,16 @@ command line parameters are relevant:
 ======================== =======================================================
 ``memhp_default_state``	 configure auto-onlining by essentially setting
                          ``/sys/devices/system/memory/auto_online_blocks``.
-``movablecore``		 configure automatic zone selection of the kernel. When
+``movable_node``	 configure automatic zone selection in the kernel when
-			 set, the kernel will default to ZONE_MOVABLE, unless
+			 using the ``contig-zones`` online policy. When
-			 other zones can be kept contiguous.
+			 set, the kernel will default to ZONE_MOVABLE when
+			 onlining a memory block, unless other zones can be kept
+			 contiguous.
 ======================== =======================================================
 
+See Documentation/admin-guide/kernel-parameters.txt for a more generic
+description of these command line parameters.
+
 Module Parameters
 ------------------
 
@@ -410,24 +417,118 @@ them with ``memory_hotplug.`` such as::
 
 and they can be observed (and some even modified at runtime) via::
 
-	/sys/modules/memory_hotplug/parameters/
+	/sys/module/memory_hotplug/parameters/
 
 The following module parameters are currently defined:
 
-======================== =======================================================
+================================ ===============================================
-``memmap_on_memory``	 read-write: Allocate memory for the memmap from the
+``memmap_on_memory``		 read-write: Allocate memory for the memmap from
-			 added memory block itself. Even if enabled, actual
+				 the added memory block itself. Even if enabled,
-			 support depends on various other system properties and
+				 actual support depends on various other system
-			 should only be regarded as a hint whether the behavior
+				 properties and should only be regarded as a
-			 would be desired.
+				 hint whether the behavior would be desired.
 
-			 While allocating the memmap from the memory block
+				 While allocating the memmap from the memory
-			 itself makes memory hotplug less likely to fail and
+				 block itself makes memory hotplug less likely
-			 keeps the memmap on the same NUMA node in any case, it
+				 to fail and keeps the memmap on the same NUMA
-			 can fragment physical memory in a way that huge pages
+				 node in any case, it can fragment physical
-			 in bigger granularity cannot be formed on hotplugged
+				 memory in a way that huge pages in bigger
-			 memory.
+				 granularity cannot be formed on hotplugged
-======================== =======================================================
+				 memory.
+``online_policy``		 read-write: Set the basic policy used for
+				 automatic zone selection when onlining memory
+				 blocks without specifying a target zone.
+				 ``contig-zones`` has been the kernel default
+				 before this parameter was added. After an
+				 online policy was configured and memory was
+				 online, the policy should not be changed
+				 anymore.
+
+				 When set to ``contig-zones``, the kernel will
+				 try keeping zones contiguous. If a memory block
+				 intersects multiple zones or no zone, the
+				 behavior depends on the ``movable_node`` kernel
+				 command line parameter: default to ZONE_MOVABLE
+				 if set, default to the applicable kernel zone
+				 (usually ZONE_NORMAL) if not set.
+
+				 When set to ``auto-movable``, the kernel will
+				 try onlining memory blocks to ZONE_MOVABLE if
+				 possible according to the configuration and
+				 memory device details. With this policy, one
+				 can avoid zone imbalances when eventually
+				 hotplugging a lot of memory later and still
+				 wanting to be able to hotunplug as much as
+				 possible reliably, very desirable in
+				 virtualized environments. This policy ignores
+				 the ``movable_node`` kernel command line
+				 parameter and isn't really applicable in
+				 environments that require it (e.g., bare metal
+				 with hotunpluggable nodes) where hotplugged
+				 memory might be exposed via the
+				 firmware-provided memory map early during boot
+				 to the system instead of getting detected,
+				 added and onlined  later during boot (such as
+				 done by virtio-mem or by some hypervisors
+				 implementing emulated DIMMs). As one example, a
+				 hotplugged DIMM will be onlined either
+				 completely to ZONE_MOVABLE or completely to
+				 ZONE_NORMAL, not a mixture.
+				 As another example, as many memory blocks
+				 belonging to a virtio-mem device will be
+				 onlined to ZONE_MOVABLE as possible,
+				 special-casing units of memory blocks that can
+				 only get hotunplugged together. *This policy
+				 does not protect from setups that are
+				 problematic with ZONE_MOVABLE and does not
+				 change the zone of memory blocks dynamically
+				 after they were onlined.*
+``auto_movable_ratio``		 read-write: Set the maximum MOVABLE:KERNEL
+				 memory ratio in % for the ``auto-movable``
+				 online policy. Whether the ratio applies only
+				 for the system across all NUMA nodes or also
+				 per NUMA nodes depends on the
+				 ``auto_movable_numa_aware`` configuration.
+
+				 All accounting is based on present memory pages
+				 in the zones combined with accounting per
+				 memory device. Memory dedicated to the CMA
+				 allocator is accounted as MOVABLE, although
+				 residing on one of the kernel zones. The
+				 possible ratio depends on the actual workload.
+				 The kernel default is "301" %, for example,
+				 allowing for hotplugging 24 GiB to a 8 GiB VM
+				 and automatically onlining all hotplugged
+				 memory to ZONE_MOVABLE in many setups. The
+				 additional 1% deals with some pages being not
+				 present, for example, because of some firmware
+				 allocations.
+
+				 Note that ZONE_NORMAL memory provided by one
+				 memory device does not allow for more
+				 ZONE_MOVABLE memory for a different memory
+				 device. As one example, onlining memory of a
+				 hotplugged DIMM to ZONE_NORMAL will not allow
+				 for another hotplugged DIMM to get onlined to
+				 ZONE_MOVABLE automatically. In contrast, memory
+				 hotplugged by a virtio-mem device that got
+				 onlined to ZONE_NORMAL will allow for more
+				 ZONE_MOVABLE memory within *the same*
+				 virtio-mem device.
+``auto_movable_numa_aware``	 read-write: Configure whether the
+				 ``auto_movable_ratio`` in the ``auto-movable``
+				 online policy also applies per NUMA
+				 node in addition to the whole system across all
+				 NUMA nodes. The kernel default is "Y".
+
+				 Disabling NUMA awareness can be helpful when
+				 dealing with NUMA nodes that should be
+				 completely hotunpluggable, onlining the memory
+				 completely to ZONE_MOVABLE automatically if
+				 possible.
+
+				 Parameter availability depends on CONFIG_NUMA.
+================================ ===============================================
 
 ZONE_MOVABLE
 ============

Documentation/admin-guide/mm/pagemap.rst

@@ -90,13 +90,14 @@ Short descriptions to the page flags
 ====================================
 
 0 - LOCKED
-   page is being locked for exclusive access, e.g. by undergoing read/write IO
+   The page is being locked for exclusive access, e.g. by undergoing read/write
+   IO.
 7 - SLAB
-   page is managed by the SLAB/SLOB/SLUB/SLQB kernel memory allocator
+   The page is managed by the SLAB/SLOB/SLUB/SLQB kernel memory allocator.
    When compound page is used, SLUB/SLQB will only set this flag on the head
    page; SLOB will not flag it at all.
 10 - BUDDY
-    a free memory block managed by the buddy system allocator
+    A free memory block managed by the buddy system allocator.
     The buddy system organizes free memory in blocks of various orders.
     An order N block has 2^N physically contiguous pages, with the BUDDY flag
     set for and _only_ for the first page.
@@ -112,65 +113,65 @@ Short descriptions to the page flags
 16 - COMPOUND_TAIL
     A compound page tail (see description above).
 17 - HUGE
-    this is an integral part of a HugeTLB page
+    This is an integral part of a HugeTLB page.
 19 - HWPOISON
-    hardware detected memory corruption on this page: don't touch the data!
+    Hardware detected memory corruption on this page: don't touch the data!
 20 - NOPAGE
-    no page frame exists at the requested address
+    No page frame exists at the requested address.
 21 - KSM
-    identical memory pages dynamically shared between one or more processes
+    Identical memory pages dynamically shared between one or more processes.
 22 - THP
-    contiguous pages which construct transparent hugepages
+    Contiguous pages which construct transparent hugepages.
 23 - OFFLINE
-    page is logically offline
+    The page is logically offline.
 24 - ZERO_PAGE
-    zero page for pfn_zero or huge_zero page
+    Zero page for pfn_zero or huge_zero page.
 25 - IDLE
-    page has not been accessed since it was marked idle (see
+    The page has not been accessed since it was marked idle (see
     :ref:`Documentation/admin-guide/mm/idle_page_tracking.rst <idle_page_tracking>`).
     Note that this flag may be stale in case the page was accessed via
     a PTE. To make sure the flag is up-to-date one has to read
     ``/sys/kernel/mm/page_idle/bitmap`` first.
 26 - PGTABLE
-    page is in use as a page table
+    The page is in use as a page table.
 
 IO related page flags
 ---------------------
 
 1 - ERROR
-   IO error occurred
+   IO error occurred.
 3 - UPTODATE
-   page has up-to-date data
+   The page has up-to-date data.
    ie. for file backed page: (in-memory data revision >= on-disk one)
 4 - DIRTY
-   page has been written to, hence contains new data
+   The page has been written to, hence contains new data.
    i.e. for file backed page: (in-memory data revision >  on-disk one)
 8 - WRITEBACK
-   page is being synced to disk
+   The page is being synced to disk.
 
 LRU related page flags
 ----------------------
 
 5 - LRU
-   page is in one of the LRU lists
+   The page is in one of the LRU lists.
 6 - ACTIVE
-   page is in the active LRU list
+   The page is in the active LRU list.
 18 - UNEVICTABLE
-   page is in the unevictable (non-)LRU list It is somehow pinned and
+   The page is in the unevictable (non-)LRU list It is somehow pinned and
    not a candidate for LRU page reclaims, e.g. ramfs pages,
-   shmctl(SHM_LOCK) and mlock() memory segments
+   shmctl(SHM_LOCK) and mlock() memory segments.
 2 - REFERENCED
-   page has been referenced since last LRU list enqueue/requeue
+   The page has been referenced since last LRU list enqueue/requeue.
 9 - RECLAIM
-   page will be reclaimed soon after its pageout IO completed
+   The page will be reclaimed soon after its pageout IO completed.
 11 - MMAP
-   a memory mapped page
+   A memory mapped page.
 12 - ANON
-   a memory mapped page that is not part of a file
+   A memory mapped page that is not part of a file.
 13 - SWAPCACHE
-   page is mapped to swap space, i.e. has an associated swap entry
+   The page is mapped to swap space, i.e. has an associated swap entry.
 14 - SWAPBACKED
-   page is backed by swap/RAM
+   The page is backed by swap/RAM.
 
 The page-types tool in the tools/vm directory can be used to query the
 above flags.

Documentation/core-api/memory-hotplug.rst

@@ -57,7 +57,6 @@ The third argument (arg) passes a pointer of struct memory_notify::
 		unsigned long start_pfn;
 		unsigned long nr_pages;
 		int status_change_nid_normal;
-		int status_change_nid_high;
 		int status_change_nid;
 	}
 
@@ -65,8 +64,6 @@ The third argument (arg) passes a pointer of struct memory_notify::
 - nr_pages is # of pages of online/offline memory.
 - status_change_nid_normal is set node id when N_NORMAL_MEMORY of nodemask
   is (will be) set/clear, if this is -1, then nodemask status is not changed.
-- status_change_nid_high is set node id when N_HIGH_MEMORY of nodemask
-  is (will be) set/clear, if this is -1, then nodemask status is not changed.
 - status_change_nid is set node id when N_MEMORY of nodemask is (will be)
   set/clear. It means a new(memoryless) node gets new memory by online and a
   node loses all memory. If this is -1, then nodemask status is not changed.

Documentation/dev-tools/kfence.rst

@@ -231,10 +231,14 @@ Guarded allocations are set up based on the sample interval. After expiration
 of the sample interval, the next allocation through the main allocator (SLAB or
 SLUB) returns a guarded allocation from the KFENCE object pool (allocation
 sizes up to PAGE_SIZE are supported). At this point, the timer is reset, and
-the next allocation is set up after the expiration of the interval. To "gate" a
+the next allocation is set up after the expiration of the interval.
-KFENCE allocation through the main allocator's fast-path without overhead,
+
-KFENCE relies on static branches via the static keys infrastructure. The static
+When using ``CONFIG_KFENCE_STATIC_KEYS=y``, KFENCE allocations are "gated"
-branch is toggled to redirect the allocation to KFENCE.
+through the main allocator's fast-path by relying on static branches via the
+static keys infrastructure. The static branch is toggled to redirect the
+allocation to KFENCE. Depending on sample interval, target workloads, and
+system architecture, this may perform better than the simple dynamic branch.
+Careful benchmarking is recommended.
 
 KFENCE objects each reside on a dedicated page, at either the left or right
 page boundaries selected at random. The pages to the left and right of the
@@ -269,6 +273,17 @@ tail of KFENCE's freelist, so that the least recently freed objects are reused
 first, and the chances of detecting use-after-frees of recently freed objects
 is increased.
 
+If pool utilization reaches 75% (default) or above, to reduce the risk of the
+pool eventually being fully occupied by allocated objects yet ensure diverse
+coverage of allocations, KFENCE limits currently covered allocations of the
+same source from further filling up the pool. The "source" of an allocation is
+based on its partial allocation stack trace. A side-effect is that this also
+limits frequent long-lived allocations (e.g. pagecache) of the same source
+filling up the pool permanently, which is the most common risk for the pool
+becoming full and the sampled allocation rate dropping to zero. The threshold
+at which to start limiting currently covered allocations can be configured via
+the boot parameter ``kfence.skip_covered_thresh`` (pool usage%).
+
 Interface
 ---------
 

Documentation/translations/zh_CN/core-api/memory-hotplug.rst

@@ -63,7 +63,6 @@ memory_notify结构体的指针::
 		unsigned long start_pfn;
 		unsigned long nr_pages;
 		int status_change_nid_normal;
-		int status_change_nid_high;
 		int status_change_nid;
 	}
 
@@ -74,9 +73,6 @@ memory_notify结构体的指针::
 - status_change_nid_normal是当nodemask的N_NORMAL_MEMORY被设置/清除时设置节
   点id，如果是-1，则nodemask状态不改变。
 
-- status_change_nid_high是当nodemask的N_HIGH_MEMORY被设置/清除时设置的节点
-  id，如果这个值为-1，那么nodemask状态不会改变。
-
 - status_change_nid是当nodemask的N_MEMORY被（将）设置/清除时设置的节点id。这
   意味着一个新的（没上线的）节点通过联机获得新的内存，而一个节点失去了所有的内
   存。如果这个值为-1，那么nodemask的状态就不会改变。

Documentation/vm/damon/design.rst

@@ -35,13 +35,17 @@ two parts:
 1. Identification of the monitoring target address range for the address space.
 2. Access check of specific address range in the target space.
 
-DAMON currently provides the implementation of the primitives for only the
+DAMON currently provides the implementations of the primitives for the physical
-virtual address spaces. Below two subsections describe how it works.
+and virtual address spaces. Below two subsections describe how those work.
 
 
 VMA-based Target Address Range Construction
 -------------------------------------------
 
+This is only for the virtual address space primitives implementation.  That for
+the physical address space simply asks users to manually set the monitoring
+target address ranges.
+
 Only small parts in the super-huge virtual address space of the processes are
 mapped to the physical memory and accessed.  Thus, tracking the unmapped
 address regions is just wasteful.  However, because DAMON can deal with some
@@ -71,15 +75,18 @@ to make a reasonable trade-off.  Below shows this in detail::
 PTE Accessed-bit Based Access Check
 -----------------------------------
 
-The implementation for the virtual address space uses PTE Accessed-bit for
+Both of the implementations for physical and virtual address spaces use PTE
-basic access checks.  It finds the relevant PTE Accessed bit from the address
+Accessed-bit for basic access checks.  Only one difference is the way of
-by walking the page table for the target task of the address.  In this way, the
+finding the relevant PTE Accessed bit(s) from the address.  While the
-implementation finds and clears the bit for next sampling target address and
+implementation for the virtual address walks the page table for the target task
-checks whether the bit set again after one sampling period.  This could disturb
+of the address, the implementation for the physical address walks every page
-other kernel subsystems using the Accessed bits, namely Idle page tracking and
+table having a mapping to the address.  In this way, the implementations find
-the reclaim logic.  To avoid such disturbances, DAMON makes it mutually
+and clear the bit(s) for next sampling target address and checks whether the
-exclusive with Idle page tracking and uses ``PG_idle`` and ``PG_young`` page
+bit(s) set again after one sampling period.  This could disturb other kernel
-flags to solve the conflict with the reclaim logic, as Idle page tracking does.
+subsystems using the Accessed bits, namely Idle page tracking and the reclaim
+logic.  To avoid such disturbances, DAMON makes it mutually exclusive with Idle
+page tracking and uses ``PG_idle`` and ``PG_young`` page flags to solve the
+conflict with the reclaim logic, as Idle page tracking does.
 
 
 Address Space Independent Core Mechanisms

Documentation/vm/damon/faq.rst

@@ -36,10 +36,9 @@ constructions and actual access checks can be implemented and configured on the
 DAMON core by the users.  In this way, DAMON users can monitor any address
 space with any access check technique.
 
-Nonetheless, DAMON provides vma tracking and PTE Accessed bit check based
+Nonetheless, DAMON provides vma/rmap tracking and PTE Accessed bit check based
 implementations of the address space dependent functions for the virtual memory
-by default, for a reference and convenient use.  In near future, we will
+and the physical memory by default, for a reference and convenient use.
-provide those for physical memory address space.
 
 
 Can I simply monitor page granularity?

Documentation/vm/damon/index.rst

@@ -27,4 +27,3 @@ workloads and systems.
    faq
    design
    api
-   plans

Documentation/vm/index.rst

@@ -3,27 +3,11 @@ Linux Memory Management Documentation
 =====================================
 
 This is a collection of documents about the Linux memory management (mm)
-subsystem.  If you are looking for advice on simply allocating memory,
+subsystem internals with different level of details ranging from notes and
-see the :ref:`memory_allocation`.
+mailing list responses for elaborating descriptions of data structures and
-
+algorithms.  If you are looking for advice on simply allocating memory, see the
-User guides for MM features
+:ref:`memory_allocation`.  For controlling and tuning guides, see the
-===========================
+:doc:`admin guide <../admin-guide/mm/index>`.
-
-The following documents provide guides for controlling and tuning
-various features of the Linux memory management
-
-.. toctree::
-   :maxdepth: 1
-
-   swap_numa
-   zswap
-
-Kernel developers MM documentation
-==================================
-
-The below documents describe MM internals with different level of
-details ranging from notes and mailing list responses to elaborate
-descriptions of data structures and algorithms.
 
 .. toctree::
    :maxdepth: 1

Documentation/vm/page_owner.rst

@@ -85,5 +85,26 @@ Usage
 	cat /sys/kernel/debug/page_owner > page_owner_full.txt
 	./page_owner_sort page_owner_full.txt sorted_page_owner.txt
 
+   The general output of ``page_owner_full.txt`` is as follows:
+
+	Page allocated via order XXX, ...
+	PFN XXX ...
+	 // Detailed stack
+
+	Page allocated via order XXX, ...
+	PFN XXX ...
+	 // Detailed stack
+
+   The ``page_owner_sort`` tool ignores ``PFN`` rows, puts the remaining rows
+   in buf, uses regexp to extract the page order value, counts the times
+   and pages of buf, and finally sorts them according to the times.
+
    See the result about who allocated each page
-   in the ``sorted_page_owner.txt``.
+   in the ``sorted_page_owner.txt``. General output:
+
+	XXX times, XXX pages:
+	Page allocated via order XXX, ...
+	 // Detailed stack
+
+   By default, ``page_owner_sort`` is sorted according to the times of buf.
+   If you want to sort by the pages nums of buf, use the ``-m`` parameter.

MAINTAINERS

@@ -5220,7 +5220,7 @@ F:	net/ax25/ax25_timer.c
 F:	net/ax25/sysctl_net_ax25.c
 
 DATA ACCESS MONITOR
-M:	SeongJae Park <sjpark@amazon.de>
+M:	SeongJae Park <sj@kernel.org>
 L:	linux-mm@kvack.org
 S:	Maintained
 F:	Documentation/admin-guide/mm/damon/

Makefile

@@ -1011,6 +1011,21 @@ ifdef CONFIG_CC_IS_GCC
 KBUILD_CFLAGS += -Wno-maybe-uninitialized
 endif
 
+ifdef CONFIG_CC_IS_GCC
+# The allocators already balk at large sizes, so silence the compiler
+# warnings for bounds checks involving those possible values. While
+# -Wno-alloc-size-larger-than would normally be used here, earlier versions
+# of gcc (<9.1) weirdly don't handle the option correctly when _other_
+# warnings are produced (?!). Using -Walloc-size-larger-than=SIZE_MAX
+# doesn't work (as it is documented to), silently resolving to "0" prior to
+# version 9.1 (and producing an error more recently). Numeric values larger
+# than PTRDIFF_MAX also don't work prior to version 9.1, which are silently
+# ignored, continuing to default to PTRDIFF_MAX. So, left with no other
+# choice, we must perform a versioned check to disable this warning.
+# https://lore.kernel.org/lkml/20210824115859.187f272f@canb.auug.org.au
+KBUILD_CFLAGS += $(call cc-ifversion, -ge, 0901, -Wno-alloc-size-larger-than)
+endif
+
 # disable invalid "can't wrap" optimizations for signed / pointers
 KBUILD_CFLAGS	+= -fno-strict-overflow
 

arch/alpha/kernel/core_irongate.c

@@ -233,7 +233,7 @@ albacore_init_arch(void)
 			unsigned long size;
 
 			size = initrd_end - initrd_start;
-			memblock_free(__pa(initrd_start), PAGE_ALIGN(size));
+			memblock_free((void *)initrd_start, PAGE_ALIGN(size));
 			if (!move_initrd(pci_mem))
 				printk("irongate_init_arch: initrd too big "
 				       "(%ldK)\ndisabling initrd\n",

arch/arc/mm/init.c

@@ -59,13 +59,13 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 
 		low_mem_sz = size;
 		in_use = 1;
-		memblock_add_node(base, size, 0);
+		memblock_add_node(base, size, 0, MEMBLOCK_NONE);
 	} else {
 #ifdef CONFIG_HIGHMEM
 		high_mem_start = base;
 		high_mem_sz = size;
 		in_use = 1;
-		memblock_add_node(base, size, 1);
+		memblock_add_node(base, size, 1, MEMBLOCK_NONE);
 		memblock_reserve(base, size);
 #endif
 	}
@@ -173,7 +173,7 @@ static void __init highmem_init(void)
 #ifdef CONFIG_HIGHMEM
 	unsigned long tmp;
 
-	memblock_free(high_mem_start, high_mem_sz);
+	memblock_phys_free(high_mem_start, high_mem_sz);
 	for (tmp = min_high_pfn; tmp < max_high_pfn; tmp++)
 		free_highmem_page(pfn_to_page(tmp));
 #endif

arch/arm/mach-hisi/platmcpm.c

@@ -339,7 +339,7 @@ err_fabric:
 err_sysctrl:
 	iounmap(relocation);
 err_reloc:
-	memblock_free(hip04_boot_method[0], hip04_boot_method[1]);
+	memblock_phys_free(hip04_boot_method[0], hip04_boot_method[1]);
 err:
 	return ret;
 }

arch/arm/mm/init.c

@@ -158,7 +158,7 @@ phys_addr_t __init arm_memblock_steal(phys_addr_t size, phys_addr_t align)
 		panic("Failed to steal %pa bytes at %pS\n",
 		      &size, (void *)_RET_IP_);
 
-	memblock_free(phys, size);
+	memblock_phys_free(phys, size);
 	memblock_remove(phys, size);
 
 	return phys;

arch/arm64/Kconfig

@@ -1163,6 +1163,10 @@ config NEED_PER_CPU_EMBED_FIRST_CHUNK
 	def_bool y
 	depends on NUMA
 
+config NEED_PER_CPU_PAGE_FIRST_CHUNK
+	def_bool y
+	depends on NUMA
+
 source "kernel/Kconfig.hz"
 
 config ARCH_SPARSEMEM_ENABLE

arch/arm64/mm/kasan_init.c

@@ -287,6 +287,22 @@ static void __init kasan_init_depth(void)
 	init_task.kasan_depth = 0;
 }
 
+#ifdef CONFIG_KASAN_VMALLOC
+void __init kasan_populate_early_vm_area_shadow(void *start, unsigned long size)
+{
+	unsigned long shadow_start, shadow_end;
+
+	if (!is_vmalloc_or_module_addr(start))
+		return;
+
+	shadow_start = (unsigned long)kasan_mem_to_shadow(start);
+	shadow_start = ALIGN_DOWN(shadow_start, PAGE_SIZE);
+	shadow_end = (unsigned long)kasan_mem_to_shadow(start + size);
+	shadow_end = ALIGN(shadow_end, PAGE_SIZE);
+	kasan_map_populate(shadow_start, shadow_end, NUMA_NO_NODE);
+}
+#endif
+
 void __init kasan_init(void)
 {
 	kasan_init_shadow();

arch/arm64/mm/mmu.c

@@ -738,8 +738,8 @@ void __init paging_init(void)
 	cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
 	init_mm.pgd = swapper_pg_dir;
 
-	memblock_free(__pa_symbol(init_pg_dir),
+	memblock_phys_free(__pa_symbol(init_pg_dir),
-		      __pa_symbol(init_pg_end) - __pa_symbol(init_pg_dir));
+			   __pa_symbol(init_pg_end) - __pa_symbol(init_pg_dir));
 
 	memblock_allow_resize();
 }

arch/ia64/mm/contig.c

@@ -153,7 +153,7 @@ find_memory (void)
 	efi_memmap_walk(find_max_min_low_pfn, NULL);
 	max_pfn = max_low_pfn;
 
-	memblock_add_node(0, PFN_PHYS(max_low_pfn), 0);
+	memblock_add_node(0, PFN_PHYS(max_low_pfn), 0, MEMBLOCK_NONE);
 
 	find_initrd();
 

arch/ia64/mm/init.c

@@ -378,7 +378,7 @@ int __init register_active_ranges(u64 start, u64 len, int nid)
 #endif
 
 	if (start < end)
-		memblock_add_node(__pa(start), end - start, nid);
+		memblock_add_node(__pa(start), end - start, nid, MEMBLOCK_NONE);
 	return 0;
 }
 

arch/m68k/mm/mcfmmu.c

@@ -174,7 +174,8 @@ void __init cf_bootmem_alloc(void)
 	m68k_memory[0].addr = _rambase;
 	m68k_memory[0].size = _ramend - _rambase;
 
-	memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0);
+	memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0,
+			  MEMBLOCK_NONE);
 
 	/* compute total pages in system */
 	num_pages = PFN_DOWN(_ramend - _rambase);

arch/m68k/mm/motorola.c

@@ -410,7 +410,8 @@ void __init paging_init(void)
 
 	min_addr = m68k_memory[0].addr;
 	max_addr = min_addr + m68k_memory[0].size;
-	memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0);
+	memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0,
+			  MEMBLOCK_NONE);
 	for (i = 1; i < m68k_num_memory;) {
 		if (m68k_memory[i].addr < min_addr) {
 			printk("Ignoring memory chunk at 0x%lx:0x%lx before the first chunk\n",
@@ -421,7 +422,8 @@ void __init paging_init(void)
 				(m68k_num_memory - i) * sizeof(struct m68k_mem_info));
 			continue;
 		}
-		memblock_add_node(m68k_memory[i].addr, m68k_memory[i].size, i);
+		memblock_add_node(m68k_memory[i].addr, m68k_memory[i].size, i,
+				  MEMBLOCK_NONE);
 		addr = m68k_memory[i].addr + m68k_memory[i].size;
 		if (addr > max_addr)
 			max_addr = addr;

arch/mips/loongson64/init.c

@@ -77,7 +77,9 @@ void __init szmem(unsigned int node)
 				(u32)node_id, mem_type, mem_start, mem_size);
 			pr_info("       start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n",
 				start_pfn, end_pfn, num_physpages);
-			memblock_add_node(PFN_PHYS(start_pfn), PFN_PHYS(node_psize), node);
+			memblock_add_node(PFN_PHYS(start_pfn),
+					  PFN_PHYS(node_psize), node,
+					  MEMBLOCK_NONE);
 			break;
 		case SYSTEM_RAM_RESERVED:
 			pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx MB\n",

arch/mips/mm/init.c

@@ -529,7 +529,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size,
 
 static void __init pcpu_fc_free(void *ptr, size_t size)
 {
-	memblock_free_early(__pa(ptr), size);
+	memblock_free(ptr, size);
 }
 
 void __init setup_per_cpu_areas(void)

arch/mips/sgi-ip27/ip27-memory.c

@@ -341,7 +341,8 @@ static void __init szmem(void)
 				continue;
 			}
 			memblock_add_node(PFN_PHYS(slot_getbasepfn(node, slot)),
-					  PFN_PHYS(slot_psize), node);
+					  PFN_PHYS(slot_psize), node,
+					  MEMBLOCK_NONE);
 		}
 	}
 }

arch/mips/sgi-ip30/ip30-setup.c

@@ -69,10 +69,10 @@ static void __init ip30_mem_init(void)
 		total_mem += size;
 
 		if (addr >= IP30_REAL_MEMORY_START)
-			memblock_free(addr, size);
+			memblock_phys_free(addr, size);
 		else if ((addr + size) > IP30_REAL_MEMORY_START)
-			memblock_free(IP30_REAL_MEMORY_START,
+			memblock_phys_free(IP30_REAL_MEMORY_START,
-				     size - IP30_MAX_PROM_MEMORY);
+					   size - IP30_MAX_PROM_MEMORY);
 	}
 	pr_info("Detected %luMB of physical memory.\n", MEM_SHIFT(total_mem));
 }

arch/powerpc/configs/skiroot_defconfig

@@ -274,7 +274,6 @@ CONFIG_NLS_UTF8=y
 CONFIG_ENCRYPTED_KEYS=y
 CONFIG_SECURITY=y
 CONFIG_HARDENED_USERCOPY=y
-# CONFIG_HARDENED_USERCOPY_FALLBACK is not set
 CONFIG_HARDENED_USERCOPY_PAGESPAN=y
 CONFIG_FORTIFY_SOURCE=y
 CONFIG_SECURITY_LOCKDOWN_LSM=y

arch/powerpc/include/asm/machdep.h

@@ -31,7 +31,7 @@ struct machdep_calls {
 #ifdef CONFIG_PM
 	void		(*iommu_restore)(void);
 #endif
-#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
+#ifdef CONFIG_MEMORY_HOTPLUG
 	unsigned long	(*memory_block_size)(void);
 #endif
 #endif /* CONFIG_PPC64 */

arch/powerpc/include/asm/sections.h

@@ -6,21 +6,8 @@
 #include <linux/elf.h>
 #include <linux/uaccess.h>
 
-#define arch_is_kernel_initmem_freed arch_is_kernel_initmem_freed
-
 #include <asm-generic/sections.h>
 
-extern bool init_mem_is_free;
-
-static inline int arch_is_kernel_initmem_freed(unsigned long addr)
-{
-	if (!init_mem_is_free)
-		return 0;
-
-	return addr >= (unsigned long)__init_begin &&
-		addr < (unsigned long)__init_end;
-}
-
 extern char __head_end[];
 
 #ifdef __powerpc64__

arch/powerpc/kernel/dt_cpu_ftrs.c

@@ -1095,8 +1095,8 @@ static int __init dt_cpu_ftrs_scan_callback(unsigned long node, const char
 
 	cpufeatures_setup_finished();
 
-	memblock_free(__pa(dt_cpu_features),
+	memblock_free(dt_cpu_features,
-			sizeof(struct dt_cpu_feature)*nr_dt_cpu_features);
+		      sizeof(struct dt_cpu_feature) * nr_dt_cpu_features);
 
 	return 0;
 }

arch/powerpc/kernel/paca.c

@@ -322,8 +322,8 @@ void __init free_unused_pacas(void)
 
 	new_ptrs_size = sizeof(struct paca_struct *) * nr_cpu_ids;
 	if (new_ptrs_size < paca_ptrs_size)
-		memblock_free(__pa(paca_ptrs) + new_ptrs_size,
+		memblock_phys_free(__pa(paca_ptrs) + new_ptrs_size,
-					paca_ptrs_size - new_ptrs_size);
+				   paca_ptrs_size - new_ptrs_size);
 
 	paca_nr_cpu_ids = nr_cpu_ids;
 	paca_ptrs_size = new_ptrs_size;
@@ -331,8 +331,8 @@ void __init free_unused_pacas(void)
 #ifdef CONFIG_PPC_BOOK3S_64
 	if (early_radix_enabled()) {
 		/* Ugly fixup, see new_slb_shadow() */
-		memblock_free(__pa(paca_ptrs[boot_cpuid]->slb_shadow_ptr),
+		memblock_phys_free(__pa(paca_ptrs[boot_cpuid]->slb_shadow_ptr),
-				sizeof(struct slb_shadow));
+				   sizeof(struct slb_shadow));
 		paca_ptrs[boot_cpuid]->slb_shadow_ptr = NULL;
 	}
 #endif

arch/powerpc/kernel/setup-common.c

@@ -822,7 +822,7 @@ static void __init smp_setup_pacas(void)
 		set_hard_smp_processor_id(cpu, cpu_to_phys_id[cpu]);
 	}
 
-	memblock_free(__pa(cpu_to_phys_id), nr_cpu_ids * sizeof(u32));
+	memblock_free(cpu_to_phys_id, nr_cpu_ids * sizeof(u32));
 	cpu_to_phys_id = NULL;
 }
 #endif

arch/powerpc/kernel/setup_64.c

@@ -812,7 +812,7 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size,
 
 static void __init pcpu_free_bootmem(void *ptr, size_t size)
 {
-	memblock_free(__pa(ptr), size);
+	memblock_free(ptr, size);
 }
 
 static int pcpu_cpu_distance(unsigned int from, unsigned int to)
@@ -912,7 +912,7 @@ void __init setup_per_cpu_areas(void)
 }
 #endif
 
-#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
+#ifdef CONFIG_MEMORY_HOTPLUG
 unsigned long memory_block_size_bytes(void)
 {
 	if (ppc_md.memory_block_size)

arch/powerpc/mm/hugetlbpage.c

@@ -229,17 +229,22 @@ static int __init pseries_alloc_bootmem_huge_page(struct hstate *hstate)
 	m->hstate = hstate;
 	return 1;
 }
+
+bool __init hugetlb_node_alloc_supported(void)
+{
+	return false;
+}
 #endif
 
 
-int __init alloc_bootmem_huge_page(struct hstate *h)
+int __init alloc_bootmem_huge_page(struct hstate *h, int nid)
 {
 
 #ifdef CONFIG_PPC_BOOK3S_64
 	if (firmware_has_feature(FW_FEATURE_LPAR) && !radix_enabled())
 		return pseries_alloc_bootmem_huge_page(h);
 #endif
-	return __alloc_bootmem_huge_page(h);
+	return __alloc_bootmem_huge_page(h, nid);
 }
 
 #ifndef CONFIG_PPC_BOOK3S_64

arch/powerpc/platforms/powernv/pci-ioda.c

@@ -2981,7 +2981,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	if (!phb->hose) {
 		pr_err("  Can't allocate PCI controller for %pOF\n",
 		       np);
-		memblock_free(__pa(phb), sizeof(struct pnv_phb));
+		memblock_free(phb, sizeof(struct pnv_phb));
 		return;
 	}
 

arch/powerpc/platforms/powernv/setup.c

@@ -440,7 +440,7 @@ static void pnv_kexec_cpu_down(int crash_shutdown, int secondary)
 }
 #endif /* CONFIG_KEXEC_CORE */
 
-#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
+#ifdef CONFIG_MEMORY_HOTPLUG
 static unsigned long pnv_memory_block_size(void)
 {
 	/*
@@ -553,7 +553,7 @@ define_machine(powernv) {
 #ifdef CONFIG_KEXEC_CORE
 	.kexec_cpu_down		= pnv_kexec_cpu_down,
 #endif
-#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
+#ifdef CONFIG_MEMORY_HOTPLUG
 	.memory_block_size	= pnv_memory_block_size,
 #endif
 };

arch/powerpc/platforms/pseries/setup.c

@@ -1088,7 +1088,7 @@ define_machine(pseries) {
 	.machine_kexec          = pSeries_machine_kexec,
 	.kexec_cpu_down         = pseries_kexec_cpu_down,
 #endif
-#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
+#ifdef CONFIG_MEMORY_HOTPLUG
 	.memory_block_size	= pseries_memory_block_size,
 #endif
 };

arch/powerpc/platforms/pseries/svm.c

@@ -57,8 +57,7 @@ void __init svm_swiotlb_init(void)
 		return;
 
 
-	memblock_free_early(__pa(vstart),
+	memblock_free(vstart, PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
-			    PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
 	panic("SVM: Cannot allocate SWIOTLB buffer");
 }
 

arch/riscv/kernel/setup.c

@@ -230,13 +230,13 @@ static void __init init_resources(void)
 
 	/* Clean-up any unused pre-allocated resources */
 	if (res_idx >= 0)
-		memblock_free(__pa(mem_res), (res_idx + 1) * sizeof(*mem_res));
+		memblock_free(mem_res, (res_idx + 1) * sizeof(*mem_res));
 	return;
 
  error:
 	/* Better an empty resource tree than an inconsistent one */
 	release_child_resources(&iomem_resource);
-	memblock_free(__pa(mem_res), mem_res_sz);
+	memblock_free(mem_res, mem_res_sz);
 }
 
 

arch/s390/include/asm/sections.h

@@ -2,20 +2,8 @@
 #ifndef _S390_SECTIONS_H
 #define _S390_SECTIONS_H
 
-#define arch_is_kernel_initmem_freed arch_is_kernel_initmem_freed
-
 #include <asm-generic/sections.h>
 
-extern bool initmem_freed;
-
-static inline int arch_is_kernel_initmem_freed(unsigned long addr)
-{
-	if (!initmem_freed)
-		return 0;
-	return addr >= (unsigned long)__init_begin &&
-	       addr < (unsigned long)__init_end;
-}
-
 /*
  * .boot.data section contains variables "shared" between the decompressor and
  * the decompressed kernel. The decompressor will store values in them, and

arch/s390/kernel/setup.c

@@ -593,7 +593,8 @@ static void __init setup_resources(void)
 	 * part of the System RAM resource.
 	 */
 	if (crashk_res.end) {
-		memblock_add_node(crashk_res.start, resource_size(&crashk_res), 0);
+		memblock_add_node(crashk_res.start, resource_size(&crashk_res),
+				  0, MEMBLOCK_NONE);
 		memblock_reserve(crashk_res.start, resource_size(&crashk_res));
 		insert_resource(&iomem_resource, &crashk_res);
 	}
@@ -693,7 +694,7 @@ static void __init reserve_crashkernel(void)
 	}
 
 	if (register_memory_notifier(&kdump_mem_nb)) {
-		memblock_free(crash_base, crash_size);
+		memblock_phys_free(crash_base, crash_size);
 		return;
 	}
 
@@ -748,7 +749,7 @@ static void __init free_mem_detect_info(void)
 
 	get_mem_detect_reserved(&start, &size);
 	if (size)
-		memblock_free(start, size);
+		memblock_phys_free(start, size);
 }
 
 static const char * __init get_mem_info_source(void)
@@ -793,7 +794,7 @@ static void __init check_initrd(void)
 	if (initrd_data.start && initrd_data.size &&
 	    !memblock_is_region_memory(initrd_data.start, initrd_data.size)) {
 		pr_err("The initial RAM disk does not fit into the memory\n");
-		memblock_free(initrd_data.start, initrd_data.size);
+		memblock_phys_free(initrd_data.start, initrd_data.size);
 		initrd_start = initrd_end = 0;
 	}
 #endif
@@ -890,7 +891,7 @@ static void __init setup_randomness(void)
 
 	if (stsi(vmms, 3, 2, 2) == 0 && vmms->count)
 		add_device_randomness(&vmms->vm, sizeof(vmms->vm[0]) * vmms->count);
-	memblock_free((unsigned long) vmms, PAGE_SIZE);
+	memblock_phys_free((unsigned long)vmms, PAGE_SIZE);
 }
 
 /*

arch/s390/kernel/smp.c

@@ -723,7 +723,7 @@ void __init smp_save_dump_cpus(void)
 			/* Get the CPU registers */
 			smp_save_cpu_regs(sa, addr, is_boot_cpu, page);
 	}
-	memblock_free(page, PAGE_SIZE);
+	memblock_phys_free(page, PAGE_SIZE);
 	diag_amode31_ops.diag308_reset();
 	pcpu_set_smt(0);
 }
@@ -880,7 +880,7 @@ void __init smp_detect_cpus(void)
 
 	/* Add CPUs present at boot */
 	__smp_rescan_cpus(info, true);
-	memblock_free_early((unsigned long)info, sizeof(*info));
+	memblock_phys_free((unsigned long)info, sizeof(*info));
 }
 
 /*

arch/s390/kernel/uv.c

@@ -64,7 +64,7 @@ void __init setup_uv(void)
 	}
 
 	if (uv_init(uv_stor_base, uv_info.uv_base_stor_len)) {
-		memblock_free(uv_stor_base, uv_info.uv_base_stor_len);
+		memblock_phys_free(uv_stor_base, uv_info.uv_base_stor_len);
 		goto fail;
 	}
 

arch/s390/mm/init.c

@@ -58,8 +58,6 @@ unsigned long empty_zero_page, zero_page_mask;
 EXPORT_SYMBOL(empty_zero_page);
 EXPORT_SYMBOL(zero_page_mask);
 
-bool initmem_freed;
-
 static void __init setup_zero_pages(void)
 {
 	unsigned int order;
@@ -214,7 +212,6 @@ void __init mem_init(void)
 
 void free_initmem(void)
 {
-	initmem_freed = true;
 	__set_memory((unsigned long)_sinittext,
 		     (unsigned long)(_einittext - _sinittext) >> PAGE_SHIFT,
 		     SET_MEMORY_RW | SET_MEMORY_NX);

arch/s390/mm/kasan_init.c

@@ -399,5 +399,5 @@ void __init kasan_copy_shadow_mapping(void)
 
 void __init kasan_free_early_identity(void)
 {
-	memblock_free(pgalloc_pos, pgalloc_freeable - pgalloc_pos);
+	memblock_phys_free(pgalloc_pos, pgalloc_freeable - pgalloc_pos);
 }

arch/sh/boards/mach-ap325rxa/setup.c

@@ -560,7 +560,7 @@ static void __init ap325rxa_mv_mem_reserve(void)
 	if (!phys)
 		panic("Failed to allocate CEU memory\n");
 
-	memblock_free(phys, size);
+	memblock_phys_free(phys, size);
 	memblock_remove(phys, size);
 
 	ceu_dma_membase = phys;

arch/sh/boards/mach-ecovec24/setup.c

@@ -1502,7 +1502,7 @@ static void __init ecovec_mv_mem_reserve(void)
 	if (!phys)
 		panic("Failed to allocate CEU0 memory\n");
 
-	memblock_free(phys, size);
+	memblock_phys_free(phys, size);
 	memblock_remove(phys, size);
 	ceu0_dma_membase = phys;
 
@@ -1510,7 +1510,7 @@ static void __init ecovec_mv_mem_reserve(void)
 	if (!phys)
 		panic("Failed to allocate CEU1 memory\n");
 
-	memblock_free(phys, size);
+	memblock_phys_free(phys, size);
 	memblock_remove(phys, size);
 	ceu1_dma_membase = phys;
 }

arch/sh/boards/mach-kfr2r09/setup.c

@@ -633,7 +633,7 @@ static void __init kfr2r09_mv_mem_reserve(void)
 	if (!phys)
 		panic("Failed to allocate CEU memory\n");
 
-	memblock_free(phys, size);
+	memblock_phys_free(phys, size);
 	memblock_remove(phys, size);
 
 	ceu_dma_membase = phys;

arch/sh/boards/mach-migor/setup.c

@@ -633,7 +633,7 @@ static void __init migor_mv_mem_reserve(void)
 	if (!phys)
 		panic("Failed to allocate CEU memory\n");
 
-	memblock_free(phys, size);
+	memblock_phys_free(phys, size);
 	memblock_remove(phys, size);
 
 	ceu_dma_membase = phys;

arch/sh/boards/mach-se/7724/setup.c

@@ -966,7 +966,7 @@ static void __init ms7724se_mv_mem_reserve(void)
 	if (!phys)
 		panic("Failed to allocate CEU0 memory\n");
 
-	memblock_free(phys, size);
+	memblock_phys_free(phys, size);
 	memblock_remove(phys, size);
 	ceu0_dma_membase = phys;
 
@@ -974,7 +974,7 @@ static void __init ms7724se_mv_mem_reserve(void)
 	if (!phys)
 		panic("Failed to allocate CEU1 memory\n");
 
-	memblock_free(phys, size);
+	memblock_phys_free(phys, size);
 	memblock_remove(phys, size);
 	ceu1_dma_membase = phys;
 }

arch/sparc/kernel/smp_64.c

@@ -1567,7 +1567,7 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size,
 
 static void __init pcpu_free_bootmem(void *ptr, size_t size)
 {
-	memblock_free(__pa(ptr), size);
+	memblock_free(ptr, size);
 }
 
 static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)

arch/um/kernel/mem.c

@@ -47,7 +47,7 @@ void __init mem_init(void)
 	 */
 	brk_end = (unsigned long) UML_ROUND_UP(sbrk(0));
 	map_memory(brk_end, __pa(brk_end), uml_reserved - brk_end, 1, 1, 0);
-	memblock_free(__pa(brk_end), uml_reserved - brk_end);
+	memblock_free((void *)brk_end, uml_reserved - brk_end);
 	uml_reserved = brk_end;
 
 	/* this will put all low memory onto the freelists */

arch/x86/Kconfig

@@ -63,7 +63,7 @@ config X86
 	select ARCH_CLOCKSOURCE_INIT
 	select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE
 	select ARCH_ENABLE_HUGEPAGE_MIGRATION if X86_64 && HUGETLB_PAGE && MIGRATION
-	select ARCH_ENABLE_MEMORY_HOTPLUG if X86_64 || (X86_32 && HIGHMEM)
+	select ARCH_ENABLE_MEMORY_HOTPLUG if X86_64
 	select ARCH_ENABLE_MEMORY_HOTREMOVE if MEMORY_HOTPLUG
 	select ARCH_ENABLE_SPLIT_PMD_PTLOCK if (PGTABLE_LEVELS > 2) && (X86_64 || X86_PAE)
 	select ARCH_ENABLE_THP_MIGRATION if X86_64 && TRANSPARENT_HUGEPAGE
@@ -1627,7 +1627,7 @@ config ARCH_SELECT_MEMORY_MODEL
 
 config ARCH_MEMORY_PROBE
 	bool "Enable sysfs memory/probe interface"
-	depends on X86_64 && MEMORY_HOTPLUG
+	depends on MEMORY_HOTPLUG
 	help
 	  This option enables a sysfs memory/probe interface for testing.
 	  See Documentation/admin-guide/mm/memory-hotplug.rst for more information.
@@ -2423,7 +2423,7 @@ endmenu
 
 config ARCH_HAS_ADD_PAGES
 	def_bool y
-	depends on X86_64 && ARCH_ENABLE_MEMORY_HOTPLUG
+	depends on ARCH_ENABLE_MEMORY_HOTPLUG
 
 config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
 	def_bool y

arch/x86/kernel/setup.c

@@ -322,7 +322,7 @@ static void __init reserve_initrd(void)
 
 	relocate_initrd();
 
-	memblock_free(ramdisk_image, ramdisk_end - ramdisk_image);
+	memblock_phys_free(ramdisk_image, ramdisk_end - ramdisk_image);
 }
 
 #else
@@ -521,7 +521,7 @@ static void __init reserve_crashkernel(void)
 	}
 
 	if (crash_base >= (1ULL << 32) && reserve_crashkernel_low()) {
-		memblock_free(crash_base, crash_size);
+		memblock_phys_free(crash_base, crash_size);
 		return;
 	}
 

arch/x86/kernel/setup_percpu.c

@@ -135,7 +135,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
 
 static void __init pcpu_fc_free(void *ptr, size_t size)
 {
-	memblock_free_ptr(ptr, size);
+	memblock_free(ptr, size);
 }
 
 static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)

arch/x86/mm/init.c

@@ -618,7 +618,7 @@ static void __init memory_map_top_down(unsigned long map_start,
 	 */
 	addr = memblock_phys_alloc_range(PMD_SIZE, PMD_SIZE, map_start,
 					 map_end);
-	memblock_free(addr, PMD_SIZE);
+	memblock_phys_free(addr, PMD_SIZE);
 	real_end = addr + PMD_SIZE;
 
 	/* step_size need to be small so pgt_buf from BRK could cover it */

arch/x86/mm/init_32.c

@@ -779,37 +779,6 @@ void __init mem_init(void)
 	test_wp_bit();
 }
 
-#ifdef CONFIG_MEMORY_HOTPLUG
-int arch_add_memory(int nid, u64 start, u64 size,
-		    struct mhp_params *params)
-{
-	unsigned long start_pfn = start >> PAGE_SHIFT;
-	unsigned long nr_pages = size >> PAGE_SHIFT;
-	int ret;
-
-	/*
-	 * The page tables were already mapped at boot so if the caller
-	 * requests a different mapping type then we must change all the
-	 * pages with __set_memory_prot().
-	 */
-	if (params->pgprot.pgprot != PAGE_KERNEL.pgprot) {
-		ret = __set_memory_prot(start, nr_pages, params->pgprot);
-		if (ret)
-			return ret;
-	}
-
-	return __add_pages(nid, start_pfn, nr_pages, params);
-}
-
-void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
-{
-	unsigned long start_pfn = start >> PAGE_SHIFT;
-	unsigned long nr_pages = size >> PAGE_SHIFT;
-
-	__remove_pages(start_pfn, nr_pages, altmap);
-}
-#endif
-
 int kernel_set_to_readonly __read_mostly;
 
 static void mark_nxdata_nx(void)

arch/x86/mm/kasan_init_64.c

@@ -49,7 +49,7 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr,
 			p = early_alloc(PMD_SIZE, nid, false);
 			if (p && pmd_set_huge(pmd, __pa(p), PAGE_KERNEL))
 				return;
-			memblock_free_ptr(p, PMD_SIZE);
+			memblock_free(p, PMD_SIZE);
 		}
 
 		p = early_alloc(PAGE_SIZE, nid, true);
@@ -85,7 +85,7 @@ static void __init kasan_populate_pud(pud_t *pud, unsigned long addr,
 			p = early_alloc(PUD_SIZE, nid, false);
 			if (p && pud_set_huge(pud, __pa(p), PAGE_KERNEL))
 				return;
-			memblock_free_ptr(p, PUD_SIZE);
+			memblock_free(p, PUD_SIZE);
 		}
 
 		p = early_alloc(PAGE_SIZE, nid, true);

arch/x86/mm/numa.c

@@ -355,7 +355,7 @@ void __init numa_reset_distance(void)
 
 	/* numa_distance could be 1LU marking allocation failure, test cnt */
 	if (numa_distance_cnt)
-		memblock_free_ptr(numa_distance, size);
+		memblock_free(numa_distance, size);
 	numa_distance_cnt = 0;
 	numa_distance = NULL;	/* enable table creation */
 }

arch/x86/mm/numa_emulation.c

@@ -517,7 +517,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 	}
 
 	/* free the copied physical distance table */
-	memblock_free_ptr(phys_dist, phys_size);
+	memblock_free(phys_dist, phys_size);
 	return;
 
 no_emu:

arch/x86/xen/mmu_pv.c

@@ -1025,7 +1025,7 @@ static void __init xen_free_ro_pages(unsigned long paddr, unsigned long size)
 	for (; vaddr < vaddr_end; vaddr += PAGE_SIZE)
 		make_lowmem_page_readwrite(vaddr);
 
-	memblock_free(paddr, size);
+	memblock_phys_free(paddr, size);
 }
 
 static void __init xen_cleanmfnmap_free_pgtbl(void *pgtbl, bool unpin)
@@ -1151,7 +1151,7 @@ static void __init xen_pagetable_p2m_free(void)
 		xen_cleanhighmap(addr, addr + size);
 		size = PAGE_ALIGN(xen_start_info->nr_pages *
 				  sizeof(unsigned long));
-		memblock_free(__pa(addr), size);
+		memblock_free((void *)addr, size);
 	} else {
 		xen_cleanmfnmap(addr);
 	}
@@ -1956,7 +1956,7 @@ void __init xen_relocate_p2m(void)
 		pfn_end = p2m_pfn_end;
 	}
 
-	memblock_free(PFN_PHYS(pfn), PAGE_SIZE * (pfn_end - pfn));
+	memblock_phys_free(PFN_PHYS(pfn), PAGE_SIZE * (pfn_end - pfn));
 	while (pfn < pfn_end) {
 		if (pfn == p2m_pfn) {
 			pfn = p2m_pfn_end;

arch/x86/xen/p2m.c

@@ -197,7 +197,7 @@ static void * __ref alloc_p2m_page(void)
 static void __ref free_p2m_page(void *p)
 {
 	if (unlikely(!slab_is_available())) {
-		memblock_free((unsigned long)p, PAGE_SIZE);
+		memblock_free(p, PAGE_SIZE);
 		return;
 	}
 

arch/x86/xen/setup.c

@@ -153,7 +153,7 @@ static void __init xen_del_extra_mem(unsigned long start_pfn,
 			break;
 		}
 	}
-	memblock_free(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns));
+	memblock_phys_free(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns));
 }
 
 /*
@@ -719,7 +719,7 @@ static void __init xen_reserve_xen_mfnlist(void)
 		return;
 
 	xen_relocate_p2m();
-	memblock_free(start, size);
+	memblock_phys_free(start, size);
 }
 
 /**
@@ -885,7 +885,7 @@ char * __init xen_memory_setup(void)
 		xen_phys_memcpy(new_area, start, size);
 		pr_info("initrd moved from [mem %#010llx-%#010llx] to [mem %#010llx-%#010llx]\n",
 			start, start + size, new_area, new_area + size);
-		memblock_free(start, size);
+		memblock_phys_free(start, size);
 		boot_params.hdr.ramdisk_image = new_area;
 		boot_params.ext_ramdisk_image = new_area >> 32;
 	}

drivers/base/Makefile

@@ -13,7 +13,7 @@ obj-y			+= power/
 obj-$(CONFIG_ISA_BUS_API)	+= isa.o
 obj-y				+= firmware_loader/
 obj-$(CONFIG_NUMA)	+= node.o
-obj-$(CONFIG_MEMORY_HOTPLUG_SPARSE) += memory.o
+obj-$(CONFIG_MEMORY_HOTPLUG) += memory.o
 ifeq ($(CONFIG_SYSFS),y)
 obj-$(CONFIG_MODULES)	+= module.o
 endif

drivers/base/arch_numa.c

@@ -14,6 +14,7 @@
 #include <linux/of.h>
 
 #include <asm/sections.h>
+#include <asm/pgalloc.h>
 
 struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
 EXPORT_SYMBOL(node_data);
@@ -165,25 +166,86 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size,
 
 static void __init pcpu_fc_free(void *ptr, size_t size)
 {
-	memblock_free_early(__pa(ptr), size);
+	memblock_free(ptr, size);
 }
 
+#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
+static void __init pcpu_populate_pte(unsigned long addr)
+{
+	pgd_t *pgd = pgd_offset_k(addr);
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	p4d = p4d_offset(pgd, addr);
+	if (p4d_none(*p4d)) {
+		pud_t *new;
+
+		new = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+		if (!new)
+			goto err_alloc;
+		p4d_populate(&init_mm, p4d, new);
+	}
+
+	pud = pud_offset(p4d, addr);
+	if (pud_none(*pud)) {
+		pmd_t *new;
+
+		new = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+		if (!new)
+			goto err_alloc;
+		pud_populate(&init_mm, pud, new);
+	}
+
+	pmd = pmd_offset(pud, addr);
+	if (!pmd_present(*pmd)) {
+		pte_t *new;
+
+		new = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+		if (!new)
+			goto err_alloc;
+		pmd_populate_kernel(&init_mm, pmd, new);
+	}
+
+	return;
+
+err_alloc:
+	panic("%s: Failed to allocate %lu bytes align=%lx from=%lx\n",
+	      __func__, PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
+}
+#endif
+
 void __init setup_per_cpu_areas(void)
 {
 	unsigned long delta;
 	unsigned int cpu;
-	int rc;
+	int rc = -EINVAL;
 
-	/*
+	if (pcpu_chosen_fc != PCPU_FC_PAGE) {
-	 * Always reserve area for module percpu variables.  That's
+		/*
-	 * what the legacy allocator did.
+		 * Always reserve area for module percpu variables.  That's
-	 */
+		 * what the legacy allocator did.
-	rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE,
+		 */
-				    PERCPU_DYNAMIC_RESERVE, PAGE_SIZE,
+		rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE,
-				    pcpu_cpu_distance,
+					    PERCPU_DYNAMIC_RESERVE, PAGE_SIZE,
-				    pcpu_fc_alloc, pcpu_fc_free);
+					    pcpu_cpu_distance,
+					    pcpu_fc_alloc, pcpu_fc_free);
+#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
+		if (rc < 0)
+			pr_warn("PERCPU: %s allocator failed (%d), falling back to page size\n",
+				   pcpu_fc_names[pcpu_chosen_fc], rc);
+#endif
+	}
+
+#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
 	if (rc < 0)
-		panic("Failed to initialize percpu areas.");
+		rc = pcpu_page_first_chunk(PERCPU_MODULE_RESERVE,
+					   pcpu_fc_alloc,
+					   pcpu_fc_free,
+					   pcpu_populate_pte);
+#endif
+	if (rc < 0)
+		panic("Failed to initialize percpu areas (err=%d).", rc);
 
 	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
 	for_each_possible_cpu(cpu)
@@ -264,7 +326,7 @@ void __init numa_free_distance(void)
 	size = numa_distance_cnt * numa_distance_cnt *
 		sizeof(numa_distance[0]);
 
-	memblock_free_ptr(numa_distance, size);
+	memblock_free(numa_distance, size);
 	numa_distance_cnt = 0;
 	numa_distance = NULL;
 }
@@ -275,15 +337,13 @@ void __init numa_free_distance(void)
 static int __init numa_alloc_distance(void)
 {
 	size_t size;
-	u64 phys;
 	int i, j;
 
 	size = nr_node_ids * nr_node_ids * sizeof(numa_distance[0]);
-	phys = memblock_phys_alloc_range(size, PAGE_SIZE, 0, PFN_PHYS(max_pfn));
+	numa_distance = memblock_alloc(size, PAGE_SIZE);
-	if (WARN_ON(!phys))
+	if (WARN_ON(!numa_distance))
 		return -ENOMEM;
 
-	numa_distance = __va(phys);
 	numa_distance_cnt = nr_node_ids;
 
 	/* fill with the default distances */

drivers/base/node.c

@@ -629,7 +629,7 @@ static void node_device_release(struct device *dev)
 {
 	struct node *node = to_node(dev);
 
-#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HUGETLBFS)
+#if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_HUGETLBFS)
 	/*
 	 * We schedule the work only when a memory section is
 	 * onlined/offlined on this node. When we come here,
@@ -782,7 +782,7 @@ int unregister_cpu_under_node(unsigned int cpu, unsigned int nid)
 	return 0;
 }
 
-#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
+#ifdef CONFIG_MEMORY_HOTPLUG
 static int __ref get_nid_for_pfn(unsigned long pfn)
 {
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
@@ -958,10 +958,9 @@ static int node_memory_callback(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 #endif	/* CONFIG_HUGETLBFS */
-#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */
+#endif /* CONFIG_MEMORY_HOTPLUG */
 
-#if !defined(CONFIG_MEMORY_HOTPLUG_SPARSE) || \
+#if !defined(CONFIG_MEMORY_HOTPLUG) || !defined(CONFIG_HUGETLBFS)
-    !defined(CONFIG_HUGETLBFS)
 static inline int node_memory_callback(struct notifier_block *self,
 				unsigned long action, void *arg)
 {

drivers/block/zram/zram_drv.c

@@ -291,22 +291,16 @@ static ssize_t mem_used_max_store(struct device *dev,
 	return len;
 }
 
-static ssize_t idle_store(struct device *dev,
+/*
-		struct device_attribute *attr, const char *buf, size_t len)
+ * Mark all pages which are older than or equal to cutoff as IDLE.
+ * Callers should hold the zram init lock in read mode
+ */
+static void mark_idle(struct zram *zram, ktime_t cutoff)
 {
-	struct zram *zram = dev_to_zram(dev);
+	int is_idle = 1;
 	unsigned long nr_pages = zram->disksize >> PAGE_SHIFT;
 	int index;
 
-	if (!sysfs_streq(buf, "all"))
-		return -EINVAL;
-
-	down_read(&zram->init_lock);
-	if (!init_done(zram)) {
-		up_read(&zram->init_lock);
-		return -EINVAL;
-	}
-
 	for (index = 0; index < nr_pages; index++) {
 		/*
 		 * Do not mark ZRAM_UNDER_WB slot as ZRAM_IDLE to close race.
@@ -314,14 +308,50 @@ static ssize_t idle_store(struct device *dev,
 		 */
 		zram_slot_lock(zram, index);
 		if (zram_allocated(zram, index) &&
-				!zram_test_flag(zram, index, ZRAM_UNDER_WB))
+				!zram_test_flag(zram, index, ZRAM_UNDER_WB)) {
-			zram_set_flag(zram, index, ZRAM_IDLE);
+#ifdef CONFIG_ZRAM_MEMORY_TRACKING
+			is_idle = !cutoff || ktime_after(cutoff, zram->table[index].ac_time);
+#endif
+			if (is_idle)
+				zram_set_flag(zram, index, ZRAM_IDLE);
+		}
 		zram_slot_unlock(zram, index);
 	}
+}
 
+static ssize_t idle_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
+{
+	struct zram *zram = dev_to_zram(dev);
+	ktime_t cutoff_time = 0;
+	ssize_t rv = -EINVAL;
+
+	if (!sysfs_streq(buf, "all")) {
+		/*
+		 * If it did not parse as 'all' try to treat it as an integer when
+		 * we have memory tracking enabled.
+		 */
+		u64 age_sec;
+
+		if (IS_ENABLED(CONFIG_ZRAM_MEMORY_TRACKING) && !kstrtoull(buf, 0, &age_sec))
+			cutoff_time = ktime_sub(ktime_get_boottime(),
+					ns_to_ktime(age_sec * NSEC_PER_SEC));
+		else
+			goto out;
+	}
+
+	down_read(&zram->init_lock);
+	if (!init_done(zram))
+		goto out_unlock;
+
+	/* A cutoff_time of 0 marks everything as idle, this is the "all" behavior */
+	mark_idle(zram, cutoff_time);
+	rv = len;
+
+out_unlock:
 	up_read(&zram->init_lock);
-
+out:
-	return len;
+	return rv;
 }
 
 #ifdef CONFIG_ZRAM_WRITEBACK
@@ -587,7 +617,7 @@ static int read_from_bdev_async(struct zram *zram, struct bio_vec *bvec,
 {
 	struct bio *bio;
 
-	bio = bio_alloc(GFP_ATOMIC, 1);
+	bio = bio_alloc(GFP_NOIO, 1);
 	if (!bio)
 		return -ENOMEM;
 
@@ -910,7 +940,7 @@ static ssize_t read_block_state(struct file *file, char __user *buf,
 			zram_test_flag(zram, index, ZRAM_HUGE) ? 'h' : '.',
 			zram_test_flag(zram, index, ZRAM_IDLE) ? 'i' : '.');
 
-		if (count < copied) {
+		if (count <= copied) {
 			zram_slot_unlock(zram, index);
 			break;
 		}

drivers/firmware/efi/memmap.c

@@ -35,7 +35,7 @@ void __init __efi_memmap_free(u64 phys, unsigned long size, unsigned long flags)
 		if (slab_is_available())
 			memblock_free_late(phys, size);
 		else
-			memblock_free(phys, size);
+			memblock_phys_free(phys, size);
 	} else if (flags & EFI_MEMMAP_SLAB) {
 		struct page *p = pfn_to_page(PHYS_PFN(phys));
 		unsigned int order = get_order(size);

drivers/hwmon/occ/p9_sbe.c

@@ -3,6 +3,7 @@
 
 #include <linux/device.h>
 #include <linux/errno.h>
+#include <linux/slab.h>
 #include <linux/fsi-occ.h>
 #include <linux/mm.h>
 #include <linux/module.h>

drivers/macintosh/smu.c

@@ -570,7 +570,7 @@ fail_msg_node:
 fail_db_node:
 	of_node_put(smu->db_node);
 fail_bootmem:
-	memblock_free_ptr(smu, sizeof(struct smu_device));
+	memblock_free(smu, sizeof(struct smu_device));
 	smu = NULL;
 fail_np:
 	of_node_put(np);

drivers/mmc/core/mmc_test.c

@@ -10,7 +10,6 @@
 #include <linux/slab.h>
 
 #include <linux/scatterlist.h>
-#include <linux/swap.h>		/* For nr_free_buffer_pages() */
 #include <linux/list.h>
 
 #include <linux/debugfs.h>

drivers/mtd/mtdcore.c

@@ -2409,6 +2409,7 @@ static void __exit cleanup_mtd(void)
 	if (proc_mtd)
 		remove_proc_entry("mtd", NULL);
 	class_unregister(&mtd_class);
+	bdi_unregister(mtd_bdi);
 	bdi_put(mtd_bdi);
 	idr_destroy(&mtd_idr);
 }

drivers/of/kexec.c

@@ -16,6 +16,7 @@
 #include <linux/of.h>
 #include <linux/of_fdt.h>
 #include <linux/random.h>
+#include <linux/slab.h>
 #include <linux/types.h>
 
 #define RNG_SEED_SIZE		128
@@ -170,8 +171,7 @@ int ima_free_kexec_buffer(void)
 	if (ret)
 		return ret;
 
-	return memblock_free(addr, size);
+	return memblock_phys_free(addr, size);
-
 }
 
 /**

drivers/of/of_reserved_mem.c

@@ -46,7 +46,7 @@ static int __init early_init_dt_alloc_reserved_memory_arch(phys_addr_t size,
 	if (nomap) {
 		err = memblock_mark_nomap(base, size);
 		if (err)
-			memblock_free(base, size);
+			memblock_phys_free(base, size);
 		kmemleak_ignore_phys(base);
 	}
 
@@ -284,7 +284,8 @@ void __init fdt_init_reserved_mem(void)
 				if (nomap)
 					memblock_clear_nomap(rmem->base, rmem->size);
 				else
-					memblock_free(rmem->base, rmem->size);
+					memblock_phys_free(rmem->base,
+							   rmem->size);
 			}
 		}
 	}

drivers/rapidio/devices/rio_mport_cdev.c

@@ -965,6 +965,7 @@ static int rio_mport_transfer_ioctl(struct file *filp, void __user *arg)
 	struct rio_transfer_io *transfer;
 	enum dma_data_direction dir;
 	int i, ret = 0;
+	size_t size;
 
 	if (unlikely(copy_from_user(&transaction, arg, sizeof(transaction))))
 		return -EFAULT;
@@ -976,13 +977,14 @@ static int rio_mport_transfer_ioctl(struct file *filp, void __user *arg)
 	     priv->md->properties.transfer_mode) == 0)
 		return -ENODEV;
 
-	transfer = vmalloc(array_size(sizeof(*transfer), transaction.count));
+	size = array_size(sizeof(*transfer), transaction.count);
+	transfer = vmalloc(size);
 	if (!transfer)
 		return -ENOMEM;
 
 	if (unlikely(copy_from_user(transfer,
 				    (void __user *)(uintptr_t)transaction.block,
-				    array_size(sizeof(*transfer), transaction.count)))) {
+				    size))) {
 		ret = -EFAULT;
 		goto out_free;
 	}
@@ -994,8 +996,7 @@ static int rio_mport_transfer_ioctl(struct file *filp, void __user *arg)
 			transaction.sync, dir, &transfer[i]);
 
 	if (unlikely(copy_to_user((void __user *)(uintptr_t)transaction.block,
-				  transfer,
+				  transfer, size)))
-				  array_size(sizeof(*transfer), transaction.count))))
 		ret = -EFAULT;
 
 out_free:

drivers/s390/char/sclp_early.c

@@ -139,7 +139,7 @@ int __init sclp_early_get_core_info(struct sclp_core_info *info)
 	}
 	sclp_fill_core_info(info, sccb);
 out:
-	memblock_free_early((unsigned long)sccb, length);
+	memblock_phys_free((unsigned long)sccb, length);
 	return rc;
 }
 

drivers/usb/early/xhci-dbc.c

@@ -185,7 +185,7 @@ static void __init xdbc_free_ring(struct xdbc_ring *ring)
 	if (!seg)
 		return;
 
-	memblock_free(seg->dma, PAGE_SIZE);
+	memblock_phys_free(seg->dma, PAGE_SIZE);
 	ring->segment = NULL;
 }
 
@@ -665,10 +665,10 @@ int __init early_xdbc_setup_hardware(void)
 		xdbc_free_ring(&xdbc.in_ring);
 
 		if (xdbc.table_dma)
-			memblock_free(xdbc.table_dma, PAGE_SIZE);
+			memblock_phys_free(xdbc.table_dma, PAGE_SIZE);
 
 		if (xdbc.out_dma)
-			memblock_free(xdbc.out_dma, PAGE_SIZE);
+			memblock_phys_free(xdbc.out_dma, PAGE_SIZE);
 
 		xdbc.table_base = NULL;
 		xdbc.out_buf = NULL;
@@ -987,8 +987,8 @@ free_and_quit:
 	xdbc_free_ring(&xdbc.evt_ring);
 	xdbc_free_ring(&xdbc.out_ring);
 	xdbc_free_ring(&xdbc.in_ring);
-	memblock_free(xdbc.table_dma, PAGE_SIZE);
+	memblock_phys_free(xdbc.table_dma, PAGE_SIZE);
-	memblock_free(xdbc.out_dma, PAGE_SIZE);
+	memblock_phys_free(xdbc.out_dma, PAGE_SIZE);
 	writel(0, &xdbc.xdbc_reg->control);
 	early_iounmap(xdbc.xhci_base, xdbc.xhci_length);
 

drivers/virtio/Kconfig

@@ -108,7 +108,7 @@ config VIRTIO_MEM
 	default m
 	depends on X86_64
 	depends on VIRTIO
-	depends on MEMORY_HOTPLUG_SPARSE
+	depends on MEMORY_HOTPLUG
 	depends on MEMORY_HOTREMOVE
 	depends on CONTIG_ALLOC
 	help

drivers/xen/swiotlb-xen.c

@@ -241,7 +241,7 @@ retry:
 	 */
 	rc = xen_swiotlb_fixup(start, nslabs);
 	if (rc) {
-		memblock_free(__pa(start), PAGE_ALIGN(bytes));
+		memblock_free(start, PAGE_ALIGN(bytes));
 		if (nslabs > 1024 && repeat--) {
 			/* Min is 2MB */
 			nslabs = max(1024UL, ALIGN(nslabs >> 1, IO_TLB_SEGSIZE));

fs/d_path.c

@@ -77,9 +77,8 @@ static bool prepend(struct prepend_buffer *p, const char *str, int namelen)
 
 /**
  * prepend_name - prepend a pathname in front of current buffer pointer
- * @buffer: buffer pointer
+ * @p: prepend buffer which contains buffer pointer and allocated length
- * @buflen: allocated length of the buffer
+ * @name: name string and length qstr structure
- * @name:   name string and length qstr structure
  *
  * With RCU path tracing, it may race with d_move(). Use READ_ONCE() to
  * make sure that either the old or the new name pointer and length are
@@ -141,8 +140,7 @@ static int __prepend_path(const struct dentry *dentry, const struct mount *mnt,
  * prepend_path - Prepend path string to a buffer
  * @path: the dentry/vfsmount to report
  * @root: root vfsmnt/dentry
- * @buffer: pointer to the end of the buffer
+ * @p: prepend buffer which contains buffer pointer and allocated length
- * @buflen: pointer to buffer length
  *
  * The function will first try to write out the pathname without taking any
  * lock other than the RCU read lock to make sure that dentries won't go away.

fs/ocfs2/alloc.c

@@ -5940,6 +5940,7 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb,
 		status = ocfs2_journal_access_di(handle, INODE_CACHE(tl_inode), tl_bh,
 						 OCFS2_JOURNAL_ACCESS_WRITE);
 		if (status < 0) {
+			ocfs2_commit_trans(osb, handle);
 			mlog_errno(status);
 			goto bail;
 		}
@@ -5964,6 +5965,7 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb,
 						     data_alloc_bh, start_blk,
 						     num_clusters);
 			if (status < 0) {
+				ocfs2_commit_trans(osb, handle);
 				mlog_errno(status);
 				goto bail;
 			}
@@ -6921,13 +6923,12 @@ static int ocfs2_grab_eof_pages(struct inode *inode, loff_t start, loff_t end,
 }
 
 /*
- * Zero the area past i_size but still within an allocated
+ * Zero partial cluster for a hole punch or truncate. This avoids exposing
- * cluster. This avoids exposing nonzero data on subsequent file
+ * nonzero data on subsequent file extends.
- * extends.
  *
  * We need to call this before i_size is updated on the inode because
  * otherwise block_write_full_page() will skip writeout of pages past
- * i_size. The new_i_size parameter is passed for this reason.
+ * i_size.
  */
 int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle,
 				  u64 range_start, u64 range_end)
@@ -6945,6 +6946,15 @@ int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle,
 	if (!ocfs2_sparse_alloc(OCFS2_SB(sb)))
 		return 0;
 
+	/*
+	 * Avoid zeroing pages fully beyond current i_size. It is pointless as
+	 * underlying blocks of those pages should be already zeroed out and
+	 * page writeback will skip them anyway.
+	 */
+	range_end = min_t(u64, range_end, i_size_read(inode));
+	if (range_start >= range_end)
+		return 0;
+
 	pages = kcalloc(ocfs2_pages_per_cluster(sb),
 			sizeof(struct page *), GFP_NOFS);
 	if (pages == NULL) {
@@ -6953,9 +6963,6 @@ int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle,
 		goto out;
 	}
 
-	if (range_start == range_end)
-		goto out;
-
 	ret = ocfs2_extent_map_get_blocks(inode,
 					  range_start >> sb->s_blocksize_bits,
 					  &phys, NULL, &ext_flags);

fs/ocfs2/dlm/dlmrecovery.c

@@ -2698,7 +2698,6 @@ static int dlm_send_begin_reco_message(struct dlm_ctxt *dlm, u8 dead_node)
 			continue;
 		}
 retry:
-		ret = -EINVAL;
 		mlog(0, "attempting to send begin reco msg to %d\n",
 			  nodenum);
 		ret = o2net_send_message(DLM_BEGIN_RECO_MSG, dlm->key,

fs/ocfs2/file.c

@@ -476,10 +476,11 @@ int ocfs2_truncate_file(struct inode *inode,
 	 * greater than page size, so we have to truncate them
 	 * anyway.
 	 */
-	unmap_mapping_range(inode->i_mapping, new_i_size + PAGE_SIZE - 1, 0, 1);
-	truncate_inode_pages(inode->i_mapping, new_i_size);
 
 	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+		unmap_mapping_range(inode->i_mapping,
+				    new_i_size + PAGE_SIZE - 1, 0, 1);
+		truncate_inode_pages(inode->i_mapping, new_i_size);
 		status = ocfs2_truncate_inline(inode, di_bh, new_i_size,
 					       i_size_read(inode), 1);
 		if (status)
@@ -498,6 +499,9 @@ int ocfs2_truncate_file(struct inode *inode,
 		goto bail_unlock_sem;
 	}
 
+	unmap_mapping_range(inode->i_mapping, new_i_size + PAGE_SIZE - 1, 0, 1);
+	truncate_inode_pages(inode->i_mapping, new_i_size);
+
 	status = ocfs2_commit_truncate(osb, inode, di_bh);
 	if (status < 0) {
 		mlog_errno(status);

fs/ocfs2/inode.c

@@ -125,7 +125,6 @@ struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 blkno, unsigned flags,
 	struct inode *inode = NULL;
 	struct super_block *sb = osb->sb;
 	struct ocfs2_find_inode_args args;
-	journal_t *journal = OCFS2_SB(sb)->journal->j_journal;
 
 	trace_ocfs2_iget_begin((unsigned long long)blkno, flags,
 			       sysfile_type);
@@ -172,10 +171,11 @@ struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 blkno, unsigned flags,
 	 * part of the transaction - the inode could have been reclaimed and
 	 * now it is reread from disk.
 	 */
-	if (journal) {
+	if (osb->journal) {
 		transaction_t *transaction;
 		tid_t tid;
 		struct ocfs2_inode_info *oi = OCFS2_I(inode);
+		journal_t *journal = osb->journal->j_journal;
 
 		read_lock(&journal->j_state_lock);
 		if (journal->j_running_transaction)

fs/ocfs2/journal.c

@@ -810,19 +810,34 @@ void ocfs2_set_journal_params(struct ocfs2_super *osb)
 	write_unlock(&journal->j_state_lock);
 }
 
-int ocfs2_journal_init(struct ocfs2_journal *journal, int *dirty)
+int ocfs2_journal_init(struct ocfs2_super *osb, int *dirty)
 {
 	int status = -1;
 	struct inode *inode = NULL; /* the journal inode */
 	journal_t *j_journal = NULL;
+	struct ocfs2_journal *journal = NULL;
 	struct ocfs2_dinode *di = NULL;
 	struct buffer_head *bh = NULL;
-	struct ocfs2_super *osb;
 	int inode_lock = 0;
 
-	BUG_ON(!journal);
+	/* initialize our journal structure */
+	journal = kzalloc(sizeof(struct ocfs2_journal), GFP_KERNEL);
+	if (!journal) {
+		mlog(ML_ERROR, "unable to alloc journal\n");
+		status = -ENOMEM;
+		goto done;
+	}
+	osb->journal = journal;
+	journal->j_osb = osb;
 
-	osb = journal->j_osb;
+	atomic_set(&journal->j_num_trans, 0);
+	init_rwsem(&journal->j_trans_barrier);
+	init_waitqueue_head(&journal->j_checkpointed);
+	spin_lock_init(&journal->j_lock);
+	journal->j_trans_id = 1UL;
+	INIT_LIST_HEAD(&journal->j_la_cleanups);
+	INIT_WORK(&journal->j_recovery_work, ocfs2_complete_recovery);
+	journal->j_state = OCFS2_JOURNAL_FREE;
 
 	/* already have the inode for our journal */
 	inode = ocfs2_get_system_file_inode(osb, JOURNAL_SYSTEM_INODE,
@@ -1028,9 +1043,10 @@ void ocfs2_journal_shutdown(struct ocfs2_super *osb)
 
 	journal->j_state = OCFS2_JOURNAL_FREE;
 
-//	up_write(&journal->j_trans_barrier);
 done:
 	iput(inode);
+	kfree(journal);
+	osb->journal = NULL;
 }
 
 static void ocfs2_clear_journal_error(struct super_block *sb,

fs/ocfs2/journal.h

@@ -167,8 +167,7 @@ int ocfs2_compute_replay_slots(struct ocfs2_super *osb);
  *  ocfs2_start_checkpoint - Kick the commit thread to do a checkpoint.
  */
 void   ocfs2_set_journal_params(struct ocfs2_super *osb);
-int    ocfs2_journal_init(struct ocfs2_journal *journal,
+int    ocfs2_journal_init(struct ocfs2_super *osb, int *dirty);
-			  int *dirty);
 void   ocfs2_journal_shutdown(struct ocfs2_super *osb);
 int    ocfs2_journal_wipe(struct ocfs2_journal *journal,
 			  int full);

fs/ocfs2/super.c

@@ -1894,8 +1894,6 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 	/* This will disable recovery and flush any recovery work. */
 	ocfs2_recovery_exit(osb);
 
-	ocfs2_journal_shutdown(osb);
-
 	ocfs2_sync_blockdev(sb);
 
 	ocfs2_purge_refcount_trees(osb);
@@ -1918,6 +1916,8 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 
 	ocfs2_release_system_inodes(osb);
 
+	ocfs2_journal_shutdown(osb);
+
 	/*
 	 * If we're dismounting due to mount error, mount.ocfs2 will clean
 	 * up heartbeat.  If we're a local mount, there is no heartbeat.
@@ -2016,7 +2016,6 @@ static int ocfs2_initialize_super(struct super_block *sb,
 	int i, cbits, bbits;
 	struct ocfs2_dinode *di = (struct ocfs2_dinode *)bh->b_data;
 	struct inode *inode = NULL;
-	struct ocfs2_journal *journal;
 	struct ocfs2_super *osb;
 	u64 total_blocks;
 
@@ -2197,33 +2196,6 @@ static int ocfs2_initialize_super(struct super_block *sb,
 
 	get_random_bytes(&osb->s_next_generation, sizeof(u32));
 
-	/* FIXME
-	 * This should be done in ocfs2_journal_init(), but unknown
-	 * ordering issues will cause the filesystem to crash.
-	 * If anyone wants to figure out what part of the code
-	 * refers to osb->journal before ocfs2_journal_init() is run,
-	 * be my guest.
-	 */
-	/* initialize our journal structure */
-
-	journal = kzalloc(sizeof(struct ocfs2_journal), GFP_KERNEL);
-	if (!journal) {
-		mlog(ML_ERROR, "unable to alloc journal\n");
-		status = -ENOMEM;
-		goto bail;
-	}
-	osb->journal = journal;
-	journal->j_osb = osb;
-
-	atomic_set(&journal->j_num_trans, 0);
-	init_rwsem(&journal->j_trans_barrier);
-	init_waitqueue_head(&journal->j_checkpointed);
-	spin_lock_init(&journal->j_lock);
-	journal->j_trans_id = (unsigned long) 1;
-	INIT_LIST_HEAD(&journal->j_la_cleanups);
-	INIT_WORK(&journal->j_recovery_work, ocfs2_complete_recovery);
-	journal->j_state = OCFS2_JOURNAL_FREE;
-
 	INIT_WORK(&osb->dquot_drop_work, ocfs2_drop_dquot_refs);
 	init_llist_head(&osb->dquot_drop_list);
 
@@ -2404,7 +2376,7 @@ static int ocfs2_check_volume(struct ocfs2_super *osb)
 						  * ourselves. */
 
 	/* Init our journal object. */
-	status = ocfs2_journal_init(osb->journal, &dirty);
+	status = ocfs2_journal_init(osb, &dirty);
 	if (status < 0) {
 		mlog(ML_ERROR, "Could not initialize journal!\n");
 		goto finally;
@@ -2513,12 +2485,6 @@ static void ocfs2_delete_osb(struct ocfs2_super *osb)
 
 	kfree(osb->osb_orphan_wipes);
 	kfree(osb->slot_recovery_generations);
-	/* FIXME
-	 * This belongs in journal shutdown, but because we have to
-	 * allocate osb->journal at the start of ocfs2_initialize_osb(),
-	 * we free it here.
-	 */
-	kfree(osb->journal);
 	kfree(osb->local_alloc_copy);
 	kfree(osb->uuid_str);
 	kfree(osb->vol_label);

fs/open.c

@@ -856,8 +856,20 @@ static int do_dentry_open(struct file *f,
 		 * of THPs into the page cache will fail.
 		 */
 		smp_mb();
-		if (filemap_nr_thps(inode->i_mapping))
+		if (filemap_nr_thps(inode->i_mapping)) {
-			truncate_pagecache(inode, 0);
+			struct address_space *mapping = inode->i_mapping;
+
+			filemap_invalidate_lock(inode->i_mapping);
+			/*
+			 * unmap_mapping_range just need to be called once
+			 * here, because the private pages is not need to be
+			 * unmapped mapping (e.g. data segment of dynamic
+			 * shared libraries here).
+			 */
+			unmap_mapping_range(mapping, 0, 0, 0);
+			truncate_inode_pages(mapping, 0);
+			filemap_invalidate_unlock(inode->i_mapping);
+		}
 	}
 
 	return 0;