Merge branch 'mm-everything' of git://git.kernel.org/pub/scm/linux/ke…

…rnel/git/akpm/mm

# Conflicts:
#	mm/damon/sysfs.c
#	mm/gup.c
#	mm/huge_memory.c

.clang-format

@@ -136,6 +136,7 @@ ForEachMacros:
   - 'data__for_each_file'
   - 'data__for_each_file_new'
   - 'data__for_each_file_start'
+  - 'dax_for_each_folio'
   - 'device_for_each_child_node'
   - 'displayid_iter_for_each'
   - 'dma_fence_array_for_each'

.mailmap

@@ -228,6 +228,7 @@ Juha Yrjola <at solidboot.com>
 Juha Yrjola <juha.yrjola@nokia.com>
 Juha Yrjola <juha.yrjola@solidboot.com>
 Julien Thierry <julien.thierry.kdev@gmail.com> <julien.thierry@arm.com>
+Iskren Chernev <me@iskren.info> <iskren.chernev@gmail.com>
 Kalle Valo <kvalo@kernel.org> <kvalo@codeaurora.org>
 Kalyan Thota <quic_kalyant@quicinc.com> <kalyan_t@codeaurora.org>
 Kay Sievers <kay.sievers@vrfy.org>

Documentation/ABI/testing/sysfs-block-zram

@@ -137,3 +137,17 @@ Description:
 		The writeback_limit file is read-write and specifies the maximum
 		amount of writeback ZRAM can do. The limit could be changed
 		in run time.
+
+What:		/sys/block/zram<id>/recomp_algorithm
+Date:		November 2022
+Contact:	Sergey Senozhatsky <senozhatsky@chromium.org>
+Description:
+		The recomp_algorithm file is read-write and allows to set
+		or show secondary compression algorithms.
+
+What:		/sys/block/zram<id>/recompress
+Date:		November 2022
+Contact:	Sergey Senozhatsky <senozhatsky@chromium.org>
+Description:
+		The recompress file is write-only and triggers re-compression
+		with secondary compression algorithms.

Documentation/ABI/testing/sysfs-class-bdi

@@ -44,6 +44,21 @@ Description:
 
 	(read-write)
 
+What:		/sys/class/bdi/<bdi>/min_ratio_fine
+Date:		November 2022
+Contact:	Stefan Roesch <shr@devkernel.io>
+Description:
+	Under normal circumstances each device is given a part of the
+	total write-back cache that relates to its current average
+	writeout speed in relation to the other devices.
+
+	The 'min_ratio_fine' parameter allows assigning a minimum reserve
+	of the write-back cache to a particular device. The value is
+	expressed as part of 1 million. For example, this is useful for
+	providing a minimum QoS.
+
+	(read-write)
+
 What:		/sys/class/bdi/<bdi>/max_ratio
 Date:		January 2008
 Contact:	Peter Zijlstra <a.p.zijlstra@chello.nl>
@@ -55,6 +70,59 @@ Description:
 	mount that is prone to get stuck, or a FUSE mount which cannot
 	be trusted to play fair.
 
+	(read-write)
+
+What:		/sys/class/bdi/<bdi>/max_ratio_fine
+Date:		November 2022
+Contact:	Stefan Roesch <shr@devkernel.io>
+Description:
+	Allows limiting a particular device to use not more than the
+	given value of the write-back cache.  The value is given as part
+	of 1 million. This is useful in situations where we want to avoid
+	one device taking all or most of the write-back cache.  For example
+	in case of an NFS mount that is prone to get stuck, or a FUSE mount
+	which cannot be trusted to play fair.
+
+	(read-write)
+
+What:		/sys/class/bdi/<bdi>/min_bytes
+Date:		October 2022
+Contact:	Stefan Roesch <shr@devkernel.io>
+Description:
+	Under normal circumstances each device is given a part of the
+	total write-back cache that relates to its current average
+	writeout speed in relation to the other devices.
+
+	The 'min_bytes' parameter allows assigning a minimum
+	percentage of the write-back cache to a particular device
+	expressed in bytes.
+	For example, this is useful for providing a minimum QoS.
+
+	(read-write)
+
+What:		/sys/class/bdi/<bdi>/max_bytes
+Date:		October 2022
+Contact:	Stefan Roesch <shr@devkernel.io>
+Description:
+	Allows limiting a particular device to use not more than the
+	given 'max_bytes' of the write-back cache.  This is useful in
+	situations where we want to avoid one device taking all or
+	most of the write-back cache.  For example in case of an NFS
+	mount that is prone to get stuck, a FUSE mount which cannot be
+	trusted to play fair, or a nbd device.
+
+	(read-write)
+
+What:		/sys/class/bdi/<bdi>/strict_limit
+Date:		October 2022
+Contact:	Stefan Roesch <shr@devkernel.io>
+Description:
+	Forces per-BDI checks for the share of given device in the write-back
+	cache even before the global background dirty limit is reached. This
+	is useful in situations where the global limit is much higher than
+	affordable for given relatively slow (or untrusted) device. Turning
+	strictlimit on has no visible effect if max_ratio is equal to 100%.
+
 	(read-write)
 What:		/sys/class/bdi/<bdi>/stable_pages_required
 Date:		January 2008

Documentation/ABI/testing/sysfs-kernel-mm-damon

@@ -27,6 +27,10 @@ Description:	Writing 'on' or 'off' to this file makes the kdamond starts or
 		makes the kdamond reads the user inputs in the sysfs files
 		except 'state' again.  Writing 'update_schemes_stats' to the
 		file updates contents of schemes stats files of the kdamond.
+		Writing 'update_schemes_tried_regions' to the file updates
+		contents of 'tried_regions' directory of every scheme directory
+		of this kdamond.  Writing 'clear_schemes_tried_regions' to the
+		file removes contents of the 'tried_regions' directory.
 
 What:		/sys/kernel/mm/damon/admin/kdamonds/<K>/pid
 Date:		Mar 2022
@@ -283,3 +287,31 @@ Date:		Mar 2022
 Contact:	SeongJae Park <sj@kernel.org>
 Description:	Reading this file returns the number of the exceed events of
 		the scheme's quotas.
+
+What:		/sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/tried_regions/<R>/start
+Date:		Oct 2022
+Contact:	SeongJae Park <sj@kernel.org>
+Description:	Reading this file returns the start address of a memory region
+		that corresponding DAMON-based Operation Scheme's action has
+		tried to be applied.
+
+What:		/sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/tried_regions/<R>/end
+Date:		Oct 2022
+Contact:	SeongJae Park <sj@kernel.org>
+Description:	Reading this file returns the end address of a memory region
+		that corresponding DAMON-based Operation Scheme's action has
+		tried to be applied.
+
+What:		/sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/tried_regions/<R>/nr_accesses
+Date:		Oct 2022
+Contact:	SeongJae Park <sj@kernel.org>
+Description:	Reading this file returns the 'nr_accesses' of a memory region
+		that corresponding DAMON-based Operation Scheme's action has
+		tried to be applied.
+
+What:		/sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/tried_regions/<R>/age
+Date:		Oct 2022
+Contact:	SeongJae Park <sj@kernel.org>
+Description:	Reading this file returns the 'age' of a memory region that
+		corresponding DAMON-based Operation Scheme's action has tried
+		to be applied.

Documentation/admin-guide/blockdev/zram.rst

@@ -348,8 +348,13 @@ this can be accomplished with::
 
         echo huge_idle > /sys/block/zramX/writeback
 
+If a user chooses to writeback only incompressible pages (pages that none of
+algorithms can compress) this can be accomplished with::
+
+	echo incompressible > /sys/block/zramX/writeback
+
 If an admin wants to write a specific page in zram device to the backing device,
-they could write a page index into the interface.
+they could write a page index into the interface::
 
 	echo "page_index=1251" > /sys/block/zramX/writeback
 
@@ -401,6 +406,87 @@ budget in next setting is user's job.
 If admin wants to measure writeback count in a certain period, they could
 know it via /sys/block/zram0/bd_stat's 3rd column.
 
+recompression
+-------------
+
+With CONFIG_ZRAM_MULTI_COMP, zram can recompress pages using alternative
+(secondary) compression algorithms. The basic idea is that alternative
+compression algorithm can provide better compression ratio at a price of
+(potentially) slower compression/decompression speeds. Alternative compression
+algorithm can, for example, be more successful compressing huge pages (those
+that default algorithm failed to compress). Another application is idle pages
+recompression - pages that are cold and sit in the memory can be recompressed
+using more effective algorithm and, hence, reduce zsmalloc memory usage.
+
+With CONFIG_ZRAM_MULTI_COMP, zram supports up to 4 compression algorithms:
+one primary and up to 3 secondary ones. Primary zram compressor is explained
+in "3) Select compression algorithm", secondary algorithms are configured
+using recomp_algorithm device attribute.
+
+Example:::
+
+	#show supported recompression algorithms
+	cat /sys/block/zramX/recomp_algorithm
+	#1: lzo lzo-rle lz4 lz4hc [zstd]
+	#2: lzo lzo-rle lz4 [lz4hc] zstd
+
+Alternative compression algorithms are sorted by priority. In the example
+above, zstd is used as the first alternative algorithm, which has priority
+of 1, while lz4hc is configured as a compression algorithm with priority 2.
+Alternative compression algorithm's priority is provided during algorithms
+configuration:::
+
+	#select zstd recompression algorithm, priority 1
+	echo "algo=zstd priority=1" > /sys/block/zramX/recomp_algorithm
+
+	#select deflate recompression algorithm, priority 2
+	echo "algo=deflate priority=2" > /sys/block/zramX/recomp_algorithm
+
+Another device attribute that CONFIG_ZRAM_MULTI_COMP enables is recompress,
+which controls recompression.
+
+Examples:::
+
+	#IDLE pages recompression is activated by `idle` mode
+	echo "type=idle" > /sys/block/zramX/recompress
+
+	#HUGE pages recompression is activated by `huge` mode
+	echo "type=huge" > /sys/block/zram0/recompress
+
+	#HUGE_IDLE pages recompression is activated by `huge_idle` mode
+	echo "type=huge_idle" > /sys/block/zramX/recompress
+
+The number of idle pages can be significant, so user-space can pass a size
+threshold (in bytes) to the recompress knob: zram will recompress only pages
+of equal or greater size:::
+
+	#recompress all pages larger than 3000 bytes
+	echo "threshold=3000" > /sys/block/zramX/recompress
+
+	#recompress idle pages larger than 2000 bytes
+	echo "type=idle threshold=2000" > /sys/block/zramX/recompress
+
+Recompression of idle pages requires memory tracking.
+
+During re-compression for every page, that matches re-compression criteria,
+ZRAM iterates the list of registered alternative compression algorithms in
+order of their priorities. ZRAM stops either when re-compression was
+successful (re-compressed object is smaller in size than the original one)
+and matches re-compression criteria (e.g. size threshold) or when there are
+no secondary algorithms left to try. If none of the secondary algorithms can
+successfully re-compressed the page such a page is marked as incompressible,
+so ZRAM will not attempt to re-compress it in the future.
+
+This re-compression behaviour, when it iterates through the list of
+registered compression algorithms, increases our chances of finding the
+algorithm that successfully compresses a particular page. Sometimes, however,
+it is convenient (and sometimes even necessary) to limit recompression to
+only one particular algorithm so that it will not try any other algorithms.
+This can be achieved by providing a algo=NAME parameter:::
+
+	#use zstd algorithm only (if registered)
+	echo "type=huge algo=zstd" > /sys/block/zramX/recompress
+
 memory tracking
 ===============
 
@@ -411,9 +497,11 @@ pages of the process with*pagemap.
 If you enable the feature, you could see block state via
 /sys/kernel/debug/zram/zram0/block_state". The output is as follows::
 
-	  300    75.033841 .wh.
-	  301    63.806904 s...
-	  302    63.806919 ..hi
+	  300    75.033841 .wh...
+	  301    63.806904 s.....
+	  302    63.806919 ..hi..
+	  303    62.801919 ....r.
+	  304   146.781902 ..hi.n
 
 First column
 	zram's block index.
@@ -430,6 +518,10 @@ Third column
 		huge page
 	i:
 		idle page
+	r:
+		recompressed page (secondary compression algorithm)
+	n:
+		none (including secondary) of algorithms could compress it
 
 First line of above example says 300th block is accessed at 75.033841sec
 and the block's state is huge so it is written back to the backing

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

@@ -543,7 +543,8 @@ inactive_anon	# of bytes of anonymous and swap cache memory on inactive
 		LRU list.
 active_anon	# of bytes of anonymous and swap cache memory on active
 		LRU list.
-inactive_file	# of bytes of file-backed memory on inactive LRU list.
+inactive_file	# of bytes of file-backed memory and MADV_FREE anonymous memory(
+                LazyFree pages) on inactive LRU list.
 active_file	# of bytes of file-backed memory on active LRU list.
 unevictable	# of bytes of memory that cannot be reclaimed (mlocked etc).
 =============== ===============================================================

Documentation/admin-guide/cgroup-v2.rst

@@ -1488,12 +1488,18 @@ PAGE_SIZE multiple when read back.
 	  pgscan_direct (npn)
 		Amount of scanned pages directly  (in an inactive LRU list)
 
+	  pgscan_khugepaged (npn)
+		Amount of scanned pages by khugepaged  (in an inactive LRU list)
+
 	  pgsteal_kswapd (npn)
 		Amount of reclaimed pages by kswapd
 
 	  pgsteal_direct (npn)
 		Amount of reclaimed pages directly
 
+	  pgsteal_khugepaged (npn)
+		Amount of reclaimed pages by khugepaged
+
 	  pgfault (npn)
 		Total number of page faults incurred