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

…rnel/git/akpm/mm

.mailmap

@@ -78,6 +78,7 @@ Boris Brezillon <bbrezillon@kernel.org> <b.brezillon.dev@gmail.com>
 Boris Brezillon <bbrezillon@kernel.org> <b.brezillon@overkiz.com>
 Boris Brezillon <bbrezillon@kernel.org> <boris.brezillon@bootlin.com>
 Boris Brezillon <bbrezillon@kernel.org> <boris.brezillon@free-electrons.com>
+Brendan Higgins <brendan.higgins@linux.dev> <brendanhiggins@google.com>
 Brian Avery <b.avery@hp.com>
 Brian King <brking@us.ibm.com>
 Brian Silverman <bsilver16384@gmail.com> <brian.silverman@bluerivertech.com>
@@ -230,7 +231,7 @@ Kees Cook <keescook@chromium.org> <kees@ubuntu.com>
 Keith Busch <kbusch@kernel.org> <keith.busch@intel.com>
 Keith Busch <kbusch@kernel.org> <keith.busch@linux.intel.com>
 Kenneth W Chen <kenneth.w.chen@intel.com>
-Kirill Tkhai <kirill.tkhai@openvz.org> <ktkhai@virtuozzo.com>
+Kirill Tkhai <tkhai@ya.ru> <ktkhai@virtuozzo.com>
 Konstantin Khlebnikov <koct9i@gmail.com> <khlebnikov@yandex-team.ru>
 Konstantin Khlebnikov <koct9i@gmail.com> <k.khlebnikov@samsung.com>
 Koushik <raghavendra.koushik@neterion.com>

Documentation/admin-guide/cgroup-v2.rst

@@ -1237,6 +1237,13 @@ PAGE_SIZE multiple when read back.
 	the target cgroup. If less bytes are reclaimed than the
 	specified amount, -EAGAIN is returned.
 
+	Please note that the proactive reclaim (triggered by this
+	interface) is not meant to indicate memory pressure on the
+	memory cgroup. Therefore socket memory balancing triggered by
+	the memory reclaim normally is not exercised in this case.
+	This means that the networking layer will not adapt based on
+	reclaim induced by memory.reclaim.
+
   memory.peak
 	A read-only single value file which exists on non-root
 	cgroups.

Documentation/admin-guide/kernel-parameters.txt

@@ -1735,12 +1735,13 @@
 	hugetlb_free_vmemmap=
 			[KNL] Reguires CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
 			enabled.
+			Control if HugeTLB Vmemmap Optimization (HVO) is enabled.
 			Allows heavy hugetlb users to free up some more
 			memory (7 * PAGE_SIZE for each 2MB hugetlb page).
-			Format: { [oO][Nn]/Y/y/1 | [oO][Ff]/N/n/0 (default) }
+			Format: { on | off (default) }
 
-			[oO][Nn]/Y/y/1: enable the feature
-			[oO][Ff]/N/n/0: disable the feature
+			on: enable HVO
+			off: disable HVO
 
 			Built with CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON=y,
 			the default is on.

Documentation/admin-guide/mm/hugetlbpage.rst

@@ -164,8 +164,8 @@ default_hugepagesz
 	will all result in 256 2M huge pages being allocated.  Valid default
 	huge page size is architecture dependent.
 hugetlb_free_vmemmap
-	When CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP is set, this enables optimizing
-	unused vmemmap pages associated with each HugeTLB page.
+	When CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP is set, this enables HugeTLB
+	Vmemmap Optimization (HVO).
 
 When multiple huge page sizes are supported, ``/proc/sys/vm/nr_hugepages``
 indicates the current number of pre-allocated huge pages of the default size.

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

@@ -653,8 +653,8 @@ block might fail:
 - Concurrent activity that operates on the same physical memory area, such as
   allocating gigantic pages, can result in temporary offlining failures.
 
-- Out of memory when dissolving huge pages, especially when freeing unused
-  vmemmap pages associated with each hugetlb page is enabled.
+- Out of memory when dissolving huge pages, especially when HugeTLB Vmemmap
+  Optimization (HVO) is enabled.
 
   Offlining code may be able to migrate huge page contents, but may not be able
   to dissolve the source huge page because it fails allocating (unmovable) pages

Documentation/admin-guide/sysctl/vm.rst

@@ -569,8 +569,7 @@ This knob is not available when the size of 'struct page' (a structure defined
 in include/linux/mm_types.h) is not power of two (an unusual system config could
 result in this).
 
-Enable (set to 1) or disable (set to 0) the feature of optimizing vmemmap pages
-associated with each HugeTLB page.
+Enable (set to 1) or disable (set to 0) HugeTLB Vmemmap Optimization (HVO).
 
 Once enabled, the vmemmap pages of subsequent allocation of HugeTLB pages from
 buddy allocator will be optimized (7 pages per 2MB HugeTLB page and 4095 pages

Documentation/filesystems/proc.rst

@@ -1891,25 +1891,30 @@ if precise results are needed.
 3.8	/proc/<pid>/fdinfo/<fd> - Information about opened file
 ---------------------------------------------------------------
 This file provides information associated with an opened file. The regular
-files have at least four fields -- 'pos', 'flags', 'mnt_id' and 'ino'.
+files have at least five fields -- 'pos', 'flags', 'mnt_id', 'ino', and 'size'.
+
 The 'pos' represents the current offset of the opened file in decimal
 form [see lseek(2) for details], 'flags' denotes the octal O_xxx mask the
 file has been created with [see open(2) for details] and 'mnt_id' represents
 mount ID of the file system containing the opened file [see 3.5
 /proc/<pid>/mountinfo for details]. 'ino' represents the inode number of
-the file.
+the file, and 'size' represents the size of the file in bytes.
 
 A typical output is::
 
 	pos:	0
 	flags:	0100002
 	mnt_id:	19
 	ino:	63107
+	size:	0
 
 All locks associated with a file descriptor are shown in its fdinfo too::
 
     lock:       1: FLOCK  ADVISORY  WRITE 359 00:13:11691 0 EOF
 
+Files with anonymous inodes have an additional 'path' field which represents
+the anonymous file path.
+
 The files such as eventfd, fsnotify, signalfd, epoll among the regular pos/flags
 pair provide additional information particular to the objects they represent.
 
@@ -1922,6 +1927,8 @@ Eventfd files
 	flags:	04002
 	mnt_id:	9
 	ino:	63107
+	size:   0
+	path:	anon_inode:[eventfd]
 	eventfd-count:	5a
 
 where 'eventfd-count' is hex value of a counter.
@@ -1935,6 +1942,8 @@ Signalfd files
 	flags:	04002
 	mnt_id:	9
 	ino:	63107
+	size:   0
+	path:	anon_inode:[signalfd]
 	sigmask:	0000000000000200
 
 where 'sigmask' is hex value of the signal mask associated
@@ -1949,6 +1958,8 @@ Epoll files
 	flags:	02
 	mnt_id:	9
 	ino:	63107
+	size:   0
+	path:	anon_inode:[eventpoll]
 	tfd:        5 events:       1d data: ffffffffffffffff pos:0 ino:61af sdev:7
 
 where 'tfd' is a target file descriptor number in decimal form,
@@ -1967,6 +1978,8 @@ For inotify files the format is the following::
 	flags:	02000000
 	mnt_id:	9
 	ino:	63107
+	size:   0
+	path:	anon_inode:inotify
 	inotify wd:3 ino:9e7e sdev:800013 mask:800afce ignored_mask:0 fhandle-bytes:8 fhandle-type:1 f_handle:7e9e0000640d1b6d
 
 where 'wd' is a watch descriptor in decimal form, i.e. a target file
@@ -1990,6 +2003,8 @@ For fanotify files the format is::
 	flags:	02
 	mnt_id:	9
 	ino:	63107
+	size:   0
+	path:	anon_inode:[fanotify]
 	fanotify flags:10 event-flags:0
 	fanotify mnt_id:12 mflags:40 mask:38 ignored_mask:40000003
 	fanotify ino:4f969 sdev:800013 mflags:0 mask:3b ignored_mask:40000000 fhandle-bytes:8 fhandle-type:1 f_handle:69f90400c275b5b4
@@ -2015,6 +2030,8 @@ Timerfd files
 	flags:	02
 	mnt_id:	9
 	ino:	63107
+	size:   0
+	path:	anon_inode:[timerfd]
 	clockid: 0
 	ticks: 0
 	settime flags: 01
@@ -2039,6 +2056,7 @@ DMA Buffer files
 	mnt_id:	9
 	ino:	63107
 	size:   32768
+	path:	/dmabuf:
 	count:  2
 	exp_name:  system-heap
 

Documentation/mm/balance.rst

@@ -6,7 +6,7 @@ Memory Balancing
 
 Started Jan 2000 by Kanoj Sarcar <kanoj@sgi.com>
 
-Memory balancing is needed for !__GFP_ATOMIC and !__GFP_KSWAPD_RECLAIM as
+Memory balancing is needed for !__GFP_HIGH and !__GFP_KSWAPD_RECLAIM as
 well as for non __GFP_IO allocations.
 
 The first reason why a caller may avoid reclaim is that the caller can not

Documentation/mm/vmemmap_dedup.rst

@@ -7,23 +7,25 @@ A vmemmap diet for HugeTLB and Device DAX
 HugeTLB
 =======
 
-The struct page structures (page structs) are used to describe a physical
-page frame. By default, there is a one-to-one mapping from a page frame to
-it's corresponding page struct.
+This section is to explain how HugeTLB Vmemmap Optimization (HVO) works.
+
+The ``struct page`` structures are used to describe a physical page frame. By
+default, there is a one-to-one mapping from a page frame to it's corresponding
+``struct page``.
 
 HugeTLB pages consist of multiple base page size pages and is supported by many
 architectures. See Documentation/admin-guide/mm/hugetlbpage.rst for more
 details. On the x86-64 architecture, HugeTLB pages of size 2MB and 1GB are
 currently supported. Since the base page size on x86 is 4KB, a 2MB HugeTLB page
 consists of 512 base pages and a 1GB HugeTLB page consists of 4096 base pages.
-For each base page, there is a corresponding page struct.
+For each base page, there is a corresponding ``struct page``.
 
-Within the HugeTLB subsystem, only the first 4 page structs are used to
-contain unique information about a HugeTLB page. __NR_USED_SUBPAGE provides
-this upper limit. The only 'useful' information in the remaining page structs
+Within the HugeTLB subsystem, only the first 4 ``struct page`` are used to
+contain unique information about a HugeTLB page. ``__NR_USED_SUBPAGE`` provides
+this upper limit. The only 'useful' information in the remaining ``struct page``
 is the compound_head field, and this field is the same for all tail pages.
 
-By removing redundant page structs for HugeTLB pages, memory can be returned
+By removing redundant ``struct page`` for HugeTLB pages, memory can be returned
 to the buddy allocator for other uses.
 
 Different architectures support different HugeTLB pages. For example, the
@@ -44,7 +46,7 @@ page.
 |              |   64KB    |    2MB    |  512MB    |    16GB   |           |
 +--------------+-----------+-----------+-----------+-----------+-----------+
 
-When the system boot up, every HugeTLB page has more than one struct page
+When the system boot up, every HugeTLB page has more than one ``struct page``
 structs which size is (unit: pages)::
 
    struct_size = HugeTLB_Size / PAGE_SIZE * sizeof(struct page) / PAGE_SIZE
@@ -74,10 +76,10 @@ Where n is how many pte entries which one page can contains. So the value of
 n is (PAGE_SIZE / sizeof(pte_t)).
 
 This optimization only supports 64-bit system, so the value of sizeof(pte_t)
-is 8. And this optimization also applicable only when the size of struct page
-is a power of two. In most cases, the size of struct page is 64 bytes (e.g.
+is 8. And this optimization also applicable only when the size of ``struct page``
+is a power of two. In most cases, the size of ``struct page`` is 64 bytes (e.g.
 x86-64 and arm64). So if we use pmd level mapping for a HugeTLB page, the
-size of struct page structs of it is 8 page frames which size depends on the
+size of ``struct page`` structs of it is 8 page frames which size depends on the
 size of the base page.
 
 For the HugeTLB page of the pud level mapping, then::
@@ -86,15 +88,15 @@ For the HugeTLB page of the pud level mapping, then::
                = PAGE_SIZE / 8 * 8 (pages)
                = PAGE_SIZE (pages)
 
-Where the struct_size(pmd) is the size of the struct page structs of a
+Where the struct_size(pmd) is the size of the ``struct page`` structs of a
 HugeTLB page of the pmd level mapping.
 
 E.g.: A 2MB HugeTLB page on x86_64 consists in 8 page frames while 1GB
 HugeTLB page consists in 4096.
 
 Next, we take the pmd level mapping of the HugeTLB page as an example to
 show the internal implementation of this optimization. There are 8 pages
-struct page structs associated with a HugeTLB page which is pmd mapped.
+``struct page`` structs associated with a HugeTLB page which is pmd mapped.
 
 Here is how things look before optimization::
 
@@ -122,10 +124,10 @@ Here is how things look before optimization::
  +-----------+
 
 The value of page->compound_head is the same for all tail pages. The first
-page of page structs (page 0) associated with the HugeTLB page contains the 4
-page structs necessary to describe the HugeTLB. The only use of the remaining
-pages of page structs (page 1 to page 7) is to point to page->compound_head.
-Therefore, we can remap pages 1 to 7 to page 0. Only 1 page of page structs
+page of ``struct page`` (page 0) associated with the HugeTLB page contains the 4
+``struct page`` necessary to describe the HugeTLB. The only use of the remaining
+pages of ``struct page`` (page 1 to page 7) is to point to page->compound_head.
+Therefore, we can remap pages 1 to 7 to page 0. Only 1 page of ``struct page``
 will be used for each HugeTLB page. This will allow us to free the remaining
 7 pages to the buddy allocator.
 
@@ -167,13 +169,37 @@ entries that can be cached in a single TLB entry.
 
 The contiguous bit is used to increase the mapping size at the pmd and pte
 (last) level. So this type of HugeTLB page can be optimized only when its
-size of the struct page structs is greater than 1 page.
+size of the ``struct page`` structs is greater than **1** page.
 
 Notice: The head vmemmap page is not freed to the buddy allocator and all
 tail vmemmap pages are mapped to the head vmemmap page frame. So we can see
-more than one struct page struct with PG_head (e.g. 8 per 2 MB HugeTLB page)
-associated with each HugeTLB page. The compound_head() can handle this
-correctly (more details refer to the comment above compound_head()).
+more than one ``struct page`` struct with ``PG_head`` (e.g. 8 per 2 MB HugeTLB
+page) associated with each HugeTLB page. The ``compound_head()`` can handle
+this correctly. There is only **one** head ``struct page``, the tail
+``struct page`` with ``PG_head`` are fake head ``struct page``.  We need an
+approach to distinguish between those two different types of ``struct page`` so
+that ``compound_head()`` can return the real head ``struct page`` when the
+parameter is the tail ``struct page`` but with ``PG_head``. The following code
+snippet describes how to distinguish between real and fake head ``struct page``.
+
+.. code-block:: c
+
+	if (test_bit(PG_head, &page->flags)) {
+		unsigned long head = READ_ONCE(page[1].compound_head);
+
+		if (head & 1) {
+			if (head == (unsigned long)page + 1)
+				/* head struct page */
+			else
+				/* tail struct page */
+		} else {
+			/* head struct page */
+		}
+	}
+
+We can safely access the field of the **page[1]** with ``PG_head`` because the
+page is a compound page composed with at least two contiguous pages.
+The implementation refers to ``page_fixed_fake_head()``.
 
 Device DAX
 ==========
@@ -187,7 +213,7 @@ PMD_SIZE (2M on x86_64) and PUD_SIZE (1G on x86_64).
 
 The differences with HugeTLB are relatively minor.
 
-It only use 3 page structs for storing all information as opposed
+It only use 3 ``struct page`` for storing all information as opposed
 to 4 on HugeTLB pages.
 
 There's no remapping of vmemmap given that device-dax memory is not part of

MAINTAINERS

@@ -11074,6 +11074,7 @@ F:	fs/smbfs_common/
 
 KERNEL UNIT TESTING FRAMEWORK (KUnit)
 M:	Brendan Higgins <brendanhiggins@google.com>
+M:	David Gow <davidgow@google.com>
 L:	linux-kselftest@vger.kernel.org
 L:	kunit-dev@googlegroups.com
 S:	Maintained

arch/alpha/include/uapi/asm/mman.h

@@ -76,6 +76,8 @@
 
 #define MADV_DONTNEED_LOCKED	24	/* like DONTNEED, but drop locked pages too */
 
+#define MADV_COLLAPSE	25		/* Synchronous hugepage collapse */
+
 /* compatibility flags */
 #define MAP_FILE	0
 

arch/alpha/kernel/smp.c

@@ -497,12 +497,6 @@ smp_cpus_done(unsigned int max_cpus)
 	       ((bogosum + 2500) / (5000/HZ)) % 100);
 }
 
-int
-setup_profiling_timer(unsigned int multiplier)
-{
-	return -EINVAL;
-}
-
 static void
 send_ipi_message(const struct cpumask *to_whom, enum ipi_message_type operation)
 {

arch/arc/kernel/smp.c

@@ -232,14 +232,6 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 	return 0;
 }
 
-/*
- * not supported here
- */
-int setup_profiling_timer(unsigned int multiplier)
-{
-	return -EINVAL;
-}
-
 /*****************************************************************************/
 /*              Inter Processor Interrupt Handling                           */
 /*****************************************************************************/

arch/arm/kernel/smp.c

@@ -787,14 +787,6 @@ void panic_smp_self_stop(void)
 		cpu_relax();
 }
 
-/*
- * not supported here
- */
-int setup_profiling_timer(unsigned int multiplier)
-{
-	return -EINVAL;
-}
-
 #ifdef CONFIG_CPU_FREQ
 
 static DEFINE_PER_CPU(unsigned long, l_p_j_ref);