Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:
 "More mm/ work, plenty more to come

  Subsystems affected by this patch series: slub, memcg, gup, kasan,
  pagealloc, hugetlb, vmscan, tools, mempolicy, memblock, hugetlbfs,
  thp, mmap, kconfig"

* akpm: (131 commits)
  arm64: mm: use ARCH_HAS_DEBUG_WX instead of arch defined
  x86: mm: use ARCH_HAS_DEBUG_WX instead of arch defined
  riscv: support DEBUG_WX
  mm: add DEBUG_WX support
  drivers/base/memory.c: cache memory blocks in xarray to accelerate lookup
  mm/thp: rename pmd_mknotpresent() as pmd_mkinvalid()
  powerpc/mm: drop platform defined pmd_mknotpresent()
  mm: thp: don't need to drain lru cache when splitting and mlocking THP
  hugetlbfs: get unmapped area below TASK_UNMAPPED_BASE for hugetlbfs
  sparc32: register memory occupied by kernel as memblock.memory
  include/linux/memblock.h: fix minor typo and unclear comment
  mm, mempolicy: fix up gup usage in lookup_node
  tools/vm/page_owner_sort.c: filter out unneeded line
  mm: swap: memcg: fix memcg stats for huge pages
  mm: swap: fix vmstats for huge pages
  mm: vmscan: limit the range of LRU type balancing
  mm: vmscan: reclaim writepage is IO cost
  mm: vmscan: determine anon/file pressure balance at the reclaim root
  mm: balance LRU lists based on relative thrashing
  mm: only count actual rotations as LRU reclaim cost
  ...

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

@@ -199,11 +199,11 @@ An RSS page is unaccounted when it's fully unmapped. A PageCache page is
 unaccounted when it's removed from radix-tree. Even if RSS pages are fully
 unmapped (by kswapd), they may exist as SwapCache in the system until they
 are really freed. Such SwapCaches are also accounted.
-A swapped-in page is not accounted until it's mapped.
+A swapped-in page is accounted after adding into swapcache.
 
 Note: The kernel does swapin-readahead and reads multiple swaps at once.
-This means swapped-in pages may contain pages for other tasks than a task
-causing page fault. So, we avoid accounting at swap-in I/O.
+Since page's memcg recorded into swap whatever memsw enabled, the page will
+be accounted after swapin.
 
 At page migration, accounting information is kept.
 
@@ -222,18 +222,13 @@ the cgroup that brought it in -- this will happen on memory pressure).
 But see section 8.2: when moving a task to another cgroup, its pages may
 be recharged to the new cgroup, if move_charge_at_immigrate has been chosen.
 
-Exception: If CONFIG_MEMCG_SWAP is not used.
-When you do swapoff and make swapped-out pages of shmem(tmpfs) to
-be backed into memory in force, charges for pages are accounted against the
-caller of swapoff rather than the users of shmem.
-
-2.4 Swap Extension (CONFIG_MEMCG_SWAP)
+2.4 Swap Extension
 --------------------------------------
 
-Swap Extension allows you to record charge for swap. A swapped-in page is
-charged back to original page allocator if possible.
+Swap usage is always recorded for each of cgroup. Swap Extension allows you to
+read and limit it.
 
-When swap is accounted, following files are added.
+When CONFIG_SWAP is enabled, following files are added.
 
  - memory.memsw.usage_in_bytes.
  - memory.memsw.limit_in_bytes.

Documentation/admin-guide/kernel-parameters.txt

@@ -834,12 +834,15 @@
 			See also Documentation/networking/decnet.rst.
 
 	default_hugepagesz=
-			[same as hugepagesz=] The size of the default
-			HugeTLB page size. This is the size represented by
-			the legacy /proc/ hugepages APIs, used for SHM, and
-			default size when mounting hugetlbfs filesystems.
-			Defaults to the default architecture's huge page size
-			if not specified.
+			[HW] The size of the default HugeTLB page. This is
+			the size represented by the legacy /proc/ hugepages
+			APIs.  In addition, this is the default hugetlb size
+			used for shmget(), mmap() and mounting hugetlbfs
+			filesystems.  If not specified, defaults to the
+			architecture's default huge page size.  Huge page
+			sizes are architecture dependent.  See also
+			Documentation/admin-guide/mm/hugetlbpage.rst.
+			Format: size[KMG]
 
 	deferred_probe_timeout=
 			[KNL] Debugging option to set a timeout in seconds for
@@ -1484,13 +1487,24 @@
 			hugepages using the cma allocator. If enabled, the
 			boot-time allocation of gigantic hugepages is skipped.
 
-	hugepages=	[HW,X86-32,IA-64] HugeTLB pages to allocate at boot.
-	hugepagesz=	[HW,IA-64,PPC,X86-64] The size of the HugeTLB pages.
-			On x86-64 and powerpc, this option can be specified
-			multiple times interleaved with hugepages= to reserve
-			huge pages of different sizes. Valid pages sizes on
-			x86-64 are 2M (when the CPU supports "pse") and 1G
-			(when the CPU supports the "pdpe1gb" cpuinfo flag).
+	hugepages=	[HW] Number of HugeTLB pages to allocate at boot.
+			If this follows hugepagesz (below), it specifies
+			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
+			Documentation/admin-guide/mm/hugetlbpage.rst.
+			Format: <integer>
+
+	hugepagesz=
+			[HW] The size of the HugeTLB pages.  This is used in
+			conjunction with hugepages (above) to allocate huge
+			pages of a specific size at boot.  The pair
+			hugepagesz=X hugepages=Y can be specified once for
+			each supported huge page size. Huge page sizes are
+			architecture dependent.  See also
+			Documentation/admin-guide/mm/hugetlbpage.rst.
+			Format: size[KMG]
 
 	hung_task_panic=
 			[KNL] Should the hung task detector generate panics.

Documentation/admin-guide/mm/hugetlbpage.rst

@@ -100,6 +100,41 @@ with a huge page size selection parameter "hugepagesz=<size>".  <size> must
 be specified in bytes with optional scale suffix [kKmMgG].  The default huge
 page size may be selected with the "default_hugepagesz=<size>" boot parameter.
 
+Hugetlb boot command line parameter semantics
+hugepagesz - Specify a huge page size.  Used in conjunction with hugepages
+	parameter to preallocate a number of huge pages of the specified
+	size.  Hence, hugepagesz and hugepages are typically specified in
+	pairs such as:
+		hugepagesz=2M hugepages=512
+	hugepagesz can only be specified once on the command line for a
+	specific huge page size.  Valid huge page sizes are architecture
+	dependent.
+hugepages - Specify the number of huge pages to preallocate.  This typically
+	follows a valid hugepagesz or default_hugepagesz parameter.  However,
+	if hugepages is the first or only hugetlb command line parameter it
+	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.
+	For example, on an architecture with 2M default huge page size:
+		hugepages=256 hugepagesz=2M hugepages=512
+	will result in 256 2M huge pages being allocated and a warning message
+	indicating that the hugepages=512 parameter is ignored.  If a hugepages
+	parameter is preceded by an invalid hugepagesz parameter, it 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
+	optionally be followed by the hugepages parameter to preallocate a
+	specific number of huge pages of default size.  The number of default
+	sized huge pages to preallocate can also be implicitly specified as
+	mentioned in the hugepages section above.  Therefore, on an
+	architecture with 2M default huge page size:
+		hugepages=256
+		default_hugepagesz=2M hugepages=256
+		hugepages=256 default_hugepagesz=2M
+	will all result in 256 2M huge pages being allocated.  Valid default
+	huge page size is architecture dependent.
+
 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.
 Thus, one can use the following command to dynamically allocate/deallocate

Documentation/admin-guide/mm/transhuge.rst

@@ -220,6 +220,13 @@ memory. A lower value can prevent THPs from being
 collapsed, resulting fewer pages being collapsed into
 THPs, and lower memory access performance.
 
+``max_ptes_shared`` specifies how many pages can be shared across multiple
+processes. Exceeding the number would block the collapse::
+
+	/sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_shared
+
+A higher value may increase memory footprint for some workloads.
+
 Boot parameter
 ==============
 

Documentation/admin-guide/sysctl/vm.rst

@@ -831,14 +831,27 @@ tooling to work, you can do::
 swappiness
 ==========
 
-This control is used to define how aggressive the kernel will swap
-memory pages.  Higher values will increase aggressiveness, lower values
-decrease the amount of swap.  A value of 0 instructs the kernel not to
-initiate swap until the amount of free and file-backed pages is less
-than the high water mark in a zone.
+This control is used to define the rough relative IO cost of swapping
+and filesystem paging, as a value between 0 and 200. At 100, the VM
+assumes equal IO cost and will thus apply memory pressure to the page
+cache and swap-backed pages equally; lower values signify more
+expensive swap IO, higher values indicates cheaper.
+
+Keep in mind that filesystem IO patterns under memory pressure tend to
+be more efficient than swap's random IO. An optimal value will require
+experimentation and will also be workload-dependent.
 
 The default value is 60.
 
+For in-memory swap, like zram or zswap, as well as hybrid setups that
+have swap on faster devices than the filesystem, values beyond 100 can
+be considered. For example, if the random IO against the swap device
+is on average 2x faster than IO from the filesystem, swappiness should
+be 133 (x + 2x = 200, 2x = 133.33).
+
+At 0, the kernel will not initiate swap until the amount of free and
+file-backed pages is less than the high watermark in a zone.
+
 
 unprivileged_userfaultfd
 ========================

Documentation/core-api/padata.rst

@@ -4,23 +4,26 @@
 The padata parallel execution mechanism
 =======================================
 
-:Date: December 2019
+:Date: May 2020
 
 Padata is a mechanism by which the kernel can farm jobs out to be done in
-parallel on multiple CPUs while retaining their ordering.  It was developed for
-use with the IPsec code, which needs to be able to perform encryption and
-decryption on large numbers of packets without reordering those packets.  The
-crypto developers made a point of writing padata in a sufficiently general
-fashion that it could be put to other uses as well.
+parallel on multiple CPUs while optionally retaining their ordering.
 
-Usage
-=====
+It was originally developed for IPsec, which needs to perform encryption and
+decryption on large numbers of packets without reordering those packets.  This
+is currently the sole consumer of padata's serialized job support.
+
+Padata also supports multithreaded jobs, splitting up the job evenly while load
+balancing and coordinating between threads.
+
+Running Serialized Jobs
+=======================
 
 Initializing
 ------------
 
-The first step in using padata is to set up a padata_instance structure for
-overall control of how jobs are to be run::
+The first step in using padata to run serialized jobs is to set up a
+padata_instance structure for overall control of how jobs are to be run::
 
     #include <linux/padata.h>
 
@@ -162,6 +165,24 @@ functions that correspond to the allocation in reverse::
 It is the user's responsibility to ensure all outstanding jobs are complete
 before any of the above are called.
 
+Running Multithreaded Jobs
+==========================
+
+A multithreaded job has a main thread and zero or more helper threads, with the
+main thread participating in the job and then waiting until all helpers have
+finished.  padata splits the job into units called chunks, where a chunk is a
+piece of the job that one thread completes in one call to the thread function.
+
+A user has to do three things to run a multithreaded job.  First, describe the
+job by defining a padata_mt_job structure, which is explained in the Interface
+section.  This includes a pointer to the thread function, which padata will
+call each time it assigns a job chunk to a thread.  Then, define the thread
+function, which accepts three arguments, ``start``, ``end``, and ``arg``, where
+the first two delimit the range that the thread operates on and the last is a
+pointer to the job's shared state, if any.  Prepare the shared state, which is
+typically allocated on the main thread's stack.  Last, call
+padata_do_multithreaded(), which will return once the job is finished.
+
 Interface
 =========
 

Documentation/vm/memory-model.rst

@@ -46,11 +46,10 @@ maps the entire physical memory. For most architectures, the holes
 have entries in the `mem_map` array. The `struct page` objects
 corresponding to the holes are never fully initialized.
 
-To allocate the `mem_map` array, architecture specific setup code
-should call :c:func:`free_area_init_node` function or its convenience
-wrapper :c:func:`free_area_init`. Yet, the mappings array is not
-usable until the call to :c:func:`memblock_free_all` that hands all
-the memory to the page allocator.
+To allocate the `mem_map` array, architecture specific setup code should
+call :c:func:`free_area_init` function. Yet, the mappings array is not
+usable until the call to :c:func:`memblock_free_all` that hands all the
+memory to the page allocator.
 
 If an architecture enables `CONFIG_ARCH_HAS_HOLES_MEMORYMODEL` option,
 it may free parts of the `mem_map` array that do not cover the

Documentation/vm/page_owner.rst

@@ -83,8 +83,7 @@ Usage
 4) Analyze information from page owner::
 
 	cat /sys/kernel/debug/page_owner > page_owner_full.txt
-	grep -v ^PFN page_owner_full.txt > page_owner.txt
-	./page_owner_sort page_owner.txt sorted_page_owner.txt
+	./page_owner_sort page_owner_full.txt sorted_page_owner.txt
 
    See the result about who allocated each page
    in the ``sorted_page_owner.txt``.

arch/alpha/mm/init.c

@@ -243,21 +243,17 @@ callback_init(void * kernel_end)
  */
 void __init paging_init(void)
 {
-	unsigned long zones_size[MAX_NR_ZONES] = {0, };
-	unsigned long dma_pfn, high_pfn;
+	unsigned long max_zone_pfn[MAX_NR_ZONES] = {0, };
+	unsigned long dma_pfn;
 
 	dma_pfn = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
-	high_pfn = max_pfn = max_low_pfn;
+	max_pfn = max_low_pfn;
 
-	if (dma_pfn >= high_pfn)
-		zones_size[ZONE_DMA] = high_pfn;
-	else {
-		zones_size[ZONE_DMA] = dma_pfn;
-		zones_size[ZONE_NORMAL] = high_pfn - dma_pfn;
-	}
+	max_zone_pfn[ZONE_DMA] = dma_pfn;
+	max_zone_pfn[ZONE_NORMAL] = max_pfn;
 
 	/* Initialize mem_map[].  */
-	free_area_init(zones_size);
+	free_area_init(max_zone_pfn);
 
 	/* Initialize the kernel's ZERO_PGE. */
 	memset((void *)ZERO_PGE, 0, PAGE_SIZE);

arch/alpha/mm/numa.c

@@ -144,8 +144,8 @@ setup_memory_node(int nid, void *kernel_end)
 	if (!nid && (node_max_pfn < end_kernel_pfn || node_min_pfn > start_kernel_pfn))
 		panic("kernel loaded out of ram");
 
-	memblock_add(PFN_PHYS(node_min_pfn),
-		     (node_max_pfn - node_min_pfn) << PAGE_SHIFT);
+	memblock_add_node(PFN_PHYS(node_min_pfn),
+			  (node_max_pfn - node_min_pfn) << PAGE_SHIFT, nid);
 
 	/* Zone start phys-addr must be 2^(MAX_ORDER-1) aligned.
 	   Note that we round this down, not up - node memory
@@ -202,8 +202,7 @@ setup_memory(void *kernel_end)
 
 void __init paging_init(void)
 {
-	unsigned int    nid;
-	unsigned long   zones_size[MAX_NR_ZONES] = {0, };
+	unsigned long   max_zone_pfn[MAX_NR_ZONES] = {0, };
 	unsigned long	dma_local_pfn;
 
 	/*
@@ -215,19 +214,10 @@ void __init paging_init(void)
 	 */
 	dma_local_pfn = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
 
-	for_each_online_node(nid) {
-		unsigned long start_pfn = NODE_DATA(nid)->node_start_pfn;
-		unsigned long end_pfn = start_pfn + NODE_DATA(nid)->node_present_pages;
+	max_zone_pfn[ZONE_DMA] = dma_local_pfn;
+	max_zone_pfn[ZONE_NORMAL] = max_pfn;
 
-		if (dma_local_pfn >= end_pfn - start_pfn)
-			zones_size[ZONE_DMA] = end_pfn - start_pfn;
-		else {
-			zones_size[ZONE_DMA] = dma_local_pfn;
-			zones_size[ZONE_NORMAL] = (end_pfn - start_pfn) - dma_local_pfn;
-		}
-		node_set_state(nid, N_NORMAL_MEMORY);
-		free_area_init_node(nid, zones_size, start_pfn, NULL);
-	}
+	free_area_init(max_zone_pfn);
 
 	/* Initialize the kernel's ZERO_PGE. */
 	memset((void *)ZERO_PGE, 0, PAGE_SIZE);

arch/arc/include/asm/hugepage.h

@@ -26,7 +26,7 @@ static inline pmd_t pte_pmd(pte_t pte)
 #define pmd_mkold(pmd)		pte_pmd(pte_mkold(pmd_pte(pmd)))
 #define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
 #define pmd_mkhuge(pmd)		pte_pmd(pte_mkhuge(pmd_pte(pmd)))
-#define pmd_mknotpresent(pmd)	pte_pmd(pte_mknotpresent(pmd_pte(pmd)))
+#define pmd_mkinvalid(pmd)	pte_pmd(pte_mknotpresent(pmd_pte(pmd)))
 #define pmd_mkclean(pmd)	pte_pmd(pte_mkclean(pmd_pte(pmd)))
 
 #define pmd_write(pmd)		pte_write(pmd_pte(pmd))