Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - a few misc things

 - ocfs2 updates

 - v9fs updates

 - MM

 - procfs updates

 - lib/ updates

 - autofs updates

* emailed patches from Andrew Morton <[email protected]>: (118 commits)
  autofs: small cleanup in autofs_getpath()
  autofs: clean up includes
  autofs: comment on selinux changes needed for module autoload
  autofs: update MAINTAINERS entry for autofs
  autofs: use autofs instead of autofs4 in documentation
  autofs: rename autofs documentation files
  autofs: create autofs Kconfig and Makefile
  autofs: delete fs/autofs4 source files
  autofs: update fs/autofs4/Makefile
  autofs: update fs/autofs4/Kconfig
  autofs: copy autofs4 to autofs
  autofs4: use autofs instead of autofs4 everywhere
  autofs4: merge auto_fs.h and auto_fs4.h
  fs/binfmt_misc.c: do not allow offset overflow
  checkpatch: improve patch recognition
  lib/ucs2_string.c: add MODULE_LICENSE()
  lib/mpi: headers cleanup
  lib/percpu_ida.c: use _irqsave() instead of local_irq_save() + spin_lock
  lib/idr.c: remove simple_ida_lock
  lib/bitmap.c: micro-optimization for __bitmap_complement()
  ...

Author: torvalds

Documentation/admin-guide/cgroup-v2.rst

@@ -1001,14 +1001,44 @@ PAGE_SIZE multiple when read back.
 	The total amount of memory currently being used by the cgroup
 	and its descendants.
 
+  memory.min
+	A read-write single value file which exists on non-root
+	cgroups.  The default is "0".
+
+	Hard memory protection.  If the memory usage of a cgroup
+	is within its effective min boundary, the cgroup's memory
+	won't be reclaimed under any conditions. If there is no
+	unprotected reclaimable memory available, OOM killer
+	is invoked.
+
+       Effective min boundary is limited by memory.min values of
+	all ancestor cgroups. If there is memory.min overcommitment
+	(child cgroup or cgroups are requiring more protected memory
+	than parent will allow), then each child cgroup will get
+	the part of parent's protection proportional to its
+	actual memory usage below memory.min.
+
+	Putting more memory than generally available under this
+	protection is discouraged and may lead to constant OOMs.
+
+	If a memory cgroup is not populated with processes,
+	its memory.min is ignored.
+
   memory.low
 	A read-write single value file which exists on non-root
 	cgroups.  The default is "0".
 
-	Best-effort memory protection.  If the memory usages of a
-	cgroup and all its ancestors are below their low boundaries,
-	the cgroup's memory won't be reclaimed unless memory can be
-	reclaimed from unprotected cgroups.
+	Best-effort memory protection.  If the memory usage of a
+	cgroup is within its effective low boundary, the cgroup's
+	memory won't be reclaimed unless memory can be reclaimed
+	from unprotected cgroups.
+
+	Effective low boundary is limited by memory.low values of
+	all ancestor cgroups. If there is memory.low overcommitment
+	(child cgroup or cgroups are requiring more protected memory
+	than parent will allow), then each child cgroup will get
+	the part of parent's protection proportional to its
+	actual memory usage below memory.low.
 
 	Putting more memory than generally available under this
 	protection is discouraged.
@@ -1199,6 +1229,27 @@ PAGE_SIZE multiple when read back.
 	Swap usage hard limit.  If a cgroup's swap usage reaches this
 	limit, anonymous memory of the cgroup will not be swapped out.
 
+  memory.swap.events
+	A read-only flat-keyed file which exists on non-root cgroups.
+	The following entries are defined.  Unless specified
+	otherwise, a value change in this file generates a file
+	modified event.
+
+	  max
+		The number of times the cgroup's swap usage was about
+		to go over the max boundary and swap allocation
+		failed.
+
+	  fail
+		The number of times swap allocation failed either
+		because of running out of swap system-wide or max
+		limit.
+
+	When reduced under the current usage, the existing swap
+	entries are reclaimed gradually and the swap usage may stay
+	higher than the limit for an extended period of time.  This
+	reduces the impact on the workload and memory management.
+
 
 Usage Guidelines
 ~~~~~~~~~~~~~~~~
@@ -1934,17 +1985,8 @@ system performance due to overreclaim, to the point where the feature
 becomes self-defeating.
 
 The memory.low boundary on the other hand is a top-down allocated
-reserve.  A cgroup enjoys reclaim protection when it and all its
-ancestors are below their low boundaries, which makes delegation of
-subtrees possible.  Secondly, new cgroups have no reserve per default
-and in the common case most cgroups are eligible for the preferred
-reclaim pass.  This allows the new low boundary to be efficiently
-implemented with just a minor addition to the generic reclaim code,
-without the need for out-of-band data structures and reclaim passes.
-Because the generic reclaim code considers all cgroups except for the
-ones running low in the preferred first reclaim pass, overreclaim of
-individual groups is eliminated as well, resulting in much better
-overall workload performance.
+reserve.  A cgroup enjoys reclaim protection when it's within its low,
+which makes delegation of subtrees possible.
 
 The original high boundary, the hard limit, is defined as a strict
 limit that can not budge, even if the OOM killer has to be called.

Documentation/blockdev/zram.txt

@@ -218,6 +218,7 @@ line of text and contains the following stats separated by whitespace:
  same_pages       the number of same element filled pages written to this disk.
                   No memory is allocated for such pages.
  pages_compacted  the number of pages freed during compaction
+ huge_pages	  the number of incompressible pages
 
 9) Deactivate:
 	swapoff /dev/zram0
@@ -242,5 +243,29 @@ to backing storage rather than keeping it in memory.
 User should set up backing device via /sys/block/zramX/backing_dev
 before disksize setting.
 
+= memory tracking
+
+With CONFIG_ZRAM_MEMORY_TRACKING, user can know information of the
+zram block. It could be useful to catch cold or incompressible
+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 ..h
+
+First column is zram's block index.
+Second column is access time since the system was booted
+Third column is state of the block.
+(s: same page
+w: written page to backing store
+h: huge page)
+
+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
+storage. It's a debugging feature so anyone shouldn't rely on it to work
+properly.
+
 Nitin Gupta
 [email protected]

Documentation/features/vm/pte_special/arch-support.txt

@@ -1,6 +1,6 @@
 #
 # Feature name:          pte_special
-#         Kconfig:       __HAVE_ARCH_PTE_SPECIAL
+#         Kconfig:       ARCH_HAS_PTE_SPECIAL
 #         description:   arch supports the pte_special()/pte_mkspecial() VM APIs
 #
     -----------------------

Documentation/filesystems/00-INDEX

@@ -10,8 +10,8 @@ afs.txt
 	- info and examples for the distributed AFS (Andrew File System) fs.
 affs.txt
 	- info and mount options for the Amiga Fast File System.
-autofs4-mount-control.txt
-	- info on device control operations for autofs4 module.
+autofs-mount-control.txt
+	- info on device control operations for autofs module.
 automount-support.txt
 	- information about filesystem automount support.
 befs.txt

Documentation/filesystems/autofs4-mount-control.txt renamed to Documentation/filesystems/autofs-mount-control.txt

@@ -1,5 +1,5 @@
 
-Miscellaneous Device control operations for the autofs4 kernel module
+Miscellaneous Device control operations for the autofs kernel module
 ====================================================================
 
 The problem
@@ -164,7 +164,7 @@ possibility for future development due to the requirements of the
 message bus architecture.
 
 
-autofs4 Miscellaneous Device mount control interface
+autofs Miscellaneous Device mount control interface
 ====================================================
 
 The control interface is opening a device node, typically /dev/autofs.
@@ -244,7 +244,7 @@ The device node ioctl operations implemented by this interface are:
 AUTOFS_DEV_IOCTL_VERSION
 ------------------------
 
-Get the major and minor version of the autofs4 device ioctl kernel module
+Get the major and minor version of the autofs device ioctl kernel module
 implementation. It requires an initialized struct autofs_dev_ioctl as an
 input parameter and sets the version information in the passed in structure.
 It returns 0 on success or the error -EINVAL if a version mismatch is
@@ -254,7 +254,7 @@ detected.
 AUTOFS_DEV_IOCTL_PROTOVER_CMD and AUTOFS_DEV_IOCTL_PROTOSUBVER_CMD
 ------------------------------------------------------------------
 
-Get the major and minor version of the autofs4 protocol version understood
+Get the major and minor version of the autofs protocol version understood
 by loaded module. This call requires an initialized struct autofs_dev_ioctl
 with the ioctlfd field set to a valid autofs mount point descriptor
 and sets the requested version number in version field of struct args_protover
@@ -404,4 +404,3 @@ type is also given we are looking for a particular autofs mount and if
 a match isn't found a fail is returned. If the the located path is the
 root of a mount 1 is returned along with the super magic of the mount
 or 0 otherwise.
-

Documentation/filesystems/autofs4.txt renamed to Documentation/filesystems/autofs.txt

@@ -30,15 +30,15 @@ key advantages:
 Context
 -------
 
-The "autofs4" filesystem module is only one part of an autofs system.
+The "autofs" filesystem module is only one part of an autofs system.
 There also needs to be a user-space program which looks up names
 and mounts filesystems.  This will often be the "automount" program,
-though other tools including "systemd" can make use of "autofs4".
+though other tools including "systemd" can make use of "autofs".
 This document describes only the kernel module and the interactions
 required with any user-space program.  Subsequent text refers to this
 as the "automount daemon" or simply "the daemon".
 
-"autofs4" is a Linux kernel module with provides the "autofs"
+"autofs" is a Linux kernel module with provides the "autofs"
 filesystem type.  Several "autofs" filesystems can be mounted and they
 can each be managed separately, or all managed by the same daemon.
 
@@ -215,7 +215,7 @@ of expiry.
 The VFS also supports "expiry" of mounts using the MNT_EXPIRE flag to
 the `umount` system call.  Unmounting with MNT_EXPIRE will fail unless
 a previous attempt had been made, and the filesystem has been inactive
-and untouched since that previous attempt.  autofs4 does not depend on
+and untouched since that previous attempt.  autofs does not depend on
 this but has its own internal tracking of whether filesystems were
 recently used.  This allows individual names in the autofs directory
 to expire separately.
@@ -415,7 +415,7 @@ which can be used to communicate directly with the autofs filesystem.
 It requires CAP_SYS_ADMIN for access.
 
 The `ioctl`s that can be used on this device are described in a separate
-document `autofs4-mount-control.txt`, and are summarized briefly here.
+document `autofs-mount-control.txt`, and are summarized briefly here.
 Each ioctl is passed a pointer to an `autofs_dev_ioctl` structure:
 
         struct autofs_dev_ioctl {

Documentation/filesystems/automount-support.txt

@@ -9,7 +9,7 @@ also be requested by userspace.
 IN-KERNEL AUTOMOUNTING
 ======================
 
-See section "Mount Traps" of  Documentation/filesystems/autofs4.txt
+See section "Mount Traps" of  Documentation/filesystems/autofs.txt
 
 Then from userspace, you can just do something like:
 

Documentation/filesystems/path-lookup.md

@@ -460,7 +460,7 @@ this retry process in the next article.
 Automount points are locations in the filesystem where an attempt to
 lookup a name can trigger changes to how that lookup should be
 handled, in particular by mounting a filesystem there.  These are
-covered in greater detail in autofs4.txt in the Linux documentation
+covered in greater detail in autofs.txt in the Linux documentation
 tree, but a few notes specifically related to path lookup are in order
 here.
 

MAINTAINERS

@@ -7723,11 +7723,11 @@ W:	https://linuxtv.org
 S:	Maintained
 F:	drivers/media/radio/radio-keene*
 
-KERNEL AUTOMOUNTER v4 (AUTOFS4)
+KERNEL AUTOMOUNTER
 M:	Ian Kent <[email protected]>
 L:	[email protected]
 S:	Maintained
-F:	fs/autofs4/
+F:	fs/autofs/
 
 KERNEL BUILD + files below scripts/ (unless maintained elsewhere)
 M:	Masahiro Yamada <[email protected]>

arch/arc/Kconfig

@@ -48,6 +48,7 @@ config ARC
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZMA
+	select ARCH_HAS_PTE_SPECIAL
 
 config MIGHT_HAVE_PCI
 	bool

arch/arc/include/asm/pgtable.h

@@ -320,8 +320,6 @@ PTE_BIT_FUNC(mkexec,	|= (_PAGE_EXECUTE));
 PTE_BIT_FUNC(mkspecial,	|= (_PAGE_SPECIAL));
 PTE_BIT_FUNC(mkhuge,	|= (_PAGE_HW_SZ));
 
-#define __HAVE_ARCH_PTE_SPECIAL
-
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot));

arch/arm/Kconfig

@@ -8,6 +8,7 @@ config ARM
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FORTIFY_SOURCE
+	select ARCH_HAS_PTE_SPECIAL if ARM_LPAE
 	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_PHYS_TO_DMA
 	select ARCH_HAS_STRICT_KERNEL_RWX if MMU && !XIP_KERNEL

arch/arm/include/asm/pgtable-3level.h

@@ -219,7 +219,6 @@ static inline pte_t pte_mkspecial(pte_t pte)
 	pte_val(pte) |= L_PTE_SPECIAL;
 	return pte;
 }
-#define	__HAVE_ARCH_PTE_SPECIAL
 
 #define pmd_write(pmd)		(pmd_isclear((pmd), L_PMD_SECT_RDONLY))
 #define pmd_dirty(pmd)		(pmd_isset((pmd), L_PMD_SECT_DIRTY))

arch/arm64/Kconfig

@@ -17,6 +17,7 @@ config ARM64
 	select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
 	select ARCH_HAS_KCOV
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
+	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAS_STRICT_KERNEL_RWX

arch/arm64/include/asm/pgtable.h

@@ -306,8 +306,6 @@ static inline int pte_same(pte_t pte_a, pte_t pte_b)
 #define HPAGE_MASK		(~(HPAGE_SIZE - 1))
 #define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
 
-#define __HAVE_ARCH_PTE_SPECIAL
-
 static inline pte_t pgd_pte(pgd_t pgd)
 {
 	return __pte(pgd_val(pgd));

arch/powerpc/Kconfig

@@ -135,6 +135,7 @@ config PPC
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_PHYS_TO_DMA
 	select ARCH_HAS_PMEM_API                if PPC64
+	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_MEMBARRIER_CALLBACKS
 	select ARCH_HAS_SCALED_CPUTIME		if VIRT_CPU_ACCOUNTING_NATIVE
 	select ARCH_HAS_SG_CHAIN

arch/powerpc/include/asm/book3s/64/pgtable.h

@@ -335,9 +335,6 @@ extern unsigned long pci_io_base;
 /* Advertise special mapping type for AGP */
 #define HAVE_PAGE_AGP
 
-/* Advertise support for _PAGE_SPECIAL */
-#define __HAVE_ARCH_PTE_SPECIAL
-
 #ifndef __ASSEMBLY__
 
 /*

arch/powerpc/include/asm/pte-common.h

@@ -208,9 +208,6 @@ static inline bool pte_user(pte_t pte)
 #define PAGE_AGP		(PAGE_KERNEL_NC)
 #define HAVE_PAGE_AGP
 
-/* Advertise support for _PAGE_SPECIAL */
-#define __HAVE_ARCH_PTE_SPECIAL
-
 #ifndef _PAGE_READ
 /* if not defined, we should not find _PAGE_WRITE too */
 #define _PAGE_READ 0

arch/riscv/Kconfig

@@ -42,6 +42,7 @@ config RISCV
 	select THREAD_INFO_IN_TASK
 	select RISCV_TIMER
 	select GENERIC_IRQ_MULTI_HANDLER
+	select ARCH_HAS_PTE_SPECIAL
 
 config MMU
 	def_bool y

arch/riscv/include/asm/pgtable-bits.h

@@ -42,7 +42,4 @@
 					  _PAGE_WRITE | _PAGE_EXEC |	\
 					  _PAGE_USER | _PAGE_GLOBAL))
 
-/* Advertise support for _PAGE_SPECIAL */
-#define __HAVE_ARCH_PTE_SPECIAL
-
 #endif /* _ASM_RISCV_PGTABLE_BITS_H */

arch/s390/Kconfig

@@ -65,6 +65,7 @@ config S390
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
 	select ARCH_HAS_KCOV
+	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAS_STRICT_KERNEL_RWX

arch/s390/include/asm/pgtable.h

@@ -171,7 +171,6 @@ static inline int is_module_addr(void *addr)
 #define _PAGE_WRITE	0x020		/* SW pte write bit */
 #define _PAGE_SPECIAL	0x040		/* SW associated with special page */
 #define _PAGE_UNUSED	0x080		/* SW bit for pgste usage state */
-#define __HAVE_ARCH_PTE_SPECIAL
 
 #ifdef CONFIG_MEM_SOFT_DIRTY
 #define _PAGE_SOFT_DIRTY 0x002		/* SW pte soft dirty bit */