Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:

 - almost all of the rest of MM

 - misc bits

 - KASAN updates

 - procfs

 - lib/ updates

 - checkpatch updates

* emailed patches from Andrew Morton <[email protected]>: (124 commits)
  checkpatch: remove false unbalanced braces warning
  checkpatch: notice unbalanced else braces in a patch
  checkpatch: add another old address for the FSF
  checkpatch: update $logFunctions
  checkpatch: warn on logging continuations
  checkpatch: warn on embedded function names
  lib/lz4: remove back-compat wrappers
  fs/pstore: fs/squashfs: change usage of LZ4 to work with new LZ4 version
  crypto: change LZ4 modules to work with new LZ4 module version
  lib/decompress_unlz4: change module to work with new LZ4 module version
  lib: update LZ4 compressor module
  lib/test_sort.c: make it explicitly non-modular
  lib: add CONFIG_TEST_SORT to enable self-test of sort()
  rbtree: use designated initializers
  linux/kernel.h: fix DIV_ROUND_CLOSEST to support negative divisors
  lib/find_bit.c: micro-optimise find_next_*_bit
  lib: add module support to atomic64 tests
  lib: add module support to glob tests
  lib: add module support to crc32 tests
  kernel/ksysfs.c: add __ro_after_init to bin_attribute structure
  ...

Documentation/blockdev/zram.txt

@@ -201,8 +201,8 @@ File /sys/block/zram<id>/mm_stat
 The stat file represents device's mm statistics. It consists of a single
 line of text and contains the following stats separated by whitespace:
  orig_data_size   uncompressed size of data stored in this disk.
-                  This excludes zero-filled pages (zero_pages) since no
-                  memory is allocated for them.
+		  This excludes same-element-filled pages (same_pages) since
+		  no memory is allocated for them.
                   Unit: bytes
  compr_data_size  compressed size of data stored in this disk
  mem_used_total   the amount of memory allocated for this disk. This
@@ -214,7 +214,7 @@ line of text and contains the following stats separated by whitespace:
                   the compressed data
  mem_used_max     the maximum amount of memory zram have consumed to
                   store the data
- zero_pages       the number of zero filled pages written to this disk.
+ 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
 

Documentation/sysctl/vm.txt

@@ -376,8 +376,8 @@ max_map_count:
 
 This file contains the maximum number of memory map areas a process
 may have. Memory map areas are used as a side-effect of calling
-malloc, directly by mmap and mprotect, and also when loading shared
-libraries.
+malloc, directly by mmap, mprotect, and madvise, and also when loading
+shared libraries.
 
 While most applications need less than a thousand maps, certain
 programs, particularly malloc debuggers, may consume lots of them,

Documentation/vm/ksm.txt

@@ -38,6 +38,10 @@ the range for whenever the KSM daemon is started; even if the range
 cannot contain any pages which KSM could actually merge; even if
 MADV_UNMERGEABLE is applied to a range which was never MADV_MERGEABLE.
 
+If a region of memory must be split into at least one new MADV_MERGEABLE
+or MADV_UNMERGEABLE region, the madvise may return ENOMEM if the process
+will exceed vm.max_map_count (see Documentation/sysctl/vm.txt).
+
 Like other madvise calls, they are intended for use on mapped areas of
 the user address space: they will report ENOMEM if the specified range
 includes unmapped gaps (though working on the intervening mapped areas),
@@ -80,6 +84,20 @@ run              - set 0 to stop ksmd from running but keep merged pages,
                    Default: 0 (must be changed to 1 to activate KSM,
                                except if CONFIG_SYSFS is disabled)
 
+use_zero_pages   - specifies whether empty pages (i.e. allocated pages
+                   that only contain zeroes) should be treated specially.
+                   When set to 1, empty pages are merged with the kernel
+                   zero page(s) instead of with each other as it would
+                   happen normally. This can improve the performance on
+                   architectures with coloured zero pages, depending on
+                   the workload. Care should be taken when enabling this
+                   setting, as it can potentially degrade the performance
+                   of KSM for some workloads, for example if the checksums
+                   of pages candidate for merging match the checksum of
+                   an empty page. This setting can be changed at any time,
+                   it is only effective for pages merged after the change.
+                   Default: 0 (normal KSM behaviour as in earlier releases)
+
 The effectiveness of KSM and MADV_MERGEABLE is shown in /sys/kernel/mm/ksm/:
 
 pages_shared     - how many shared pages are being used

Documentation/vm/userfaultfd.txt

@@ -54,6 +54,26 @@ uffdio_api.features and uffdio_api.ioctls two 64bit bitmasks of
 respectively all the available features of the read(2) protocol and
 the generic ioctl available.
 
+The uffdio_api.features bitmask returned by the UFFDIO_API ioctl
+defines what memory types are supported by the userfaultfd and what
+events, except page fault notifications, may be generated.
+
+If the kernel supports registering userfaultfd ranges on hugetlbfs
+virtual memory areas, UFFD_FEATURE_MISSING_HUGETLBFS will be set in
+uffdio_api.features. Similarly, UFFD_FEATURE_MISSING_SHMEM will be
+set if the kernel supports registering userfaultfd ranges on shared
+memory (covering all shmem APIs, i.e. tmpfs, IPCSHM, /dev/zero
+MAP_SHARED, memfd_create, etc).
+
+The userland application that wants to use userfaultfd with hugetlbfs
+or shared memory need to set the corresponding flag in
+uffdio_api.features to enable those features.
+
+If the userland desires to receive notifications for events other than
+page faults, it has to verify that uffdio_api.features has appropriate
+UFFD_FEATURE_EVENT_* bits set. These events are described in more
+detail below in "Non-cooperative userfaultfd" section.
+
 Once the userfaultfd has been enabled the UFFDIO_REGISTER ioctl should
 be invoked (if present in the returned uffdio_api.ioctls bitmask) to
 register a memory range in the userfaultfd by setting the
@@ -142,3 +162,72 @@ course the bitmap is updated accordingly. It's also useful to avoid
 sending the same page twice (in case the userfault is read by the
 postcopy thread just before UFFDIO_COPY|ZEROPAGE runs in the migration
 thread).
+
+== Non-cooperative userfaultfd ==
+
+When the userfaultfd is monitored by an external manager, the manager
+must be able to track changes in the process virtual memory
+layout. Userfaultfd can notify the manager about such changes using
+the same read(2) protocol as for the page fault notifications. The
+manager has to explicitly enable these events by setting appropriate
+bits in uffdio_api.features passed to UFFDIO_API ioctl:
+
+UFFD_FEATURE_EVENT_EXIT - enable notification about exit() of the
+non-cooperative process. When the monitored process exits, the uffd
+manager will get UFFD_EVENT_EXIT.
+
+UFFD_FEATURE_EVENT_FORK - enable userfaultfd hooks for fork(). When
+this feature is enabled, the userfaultfd context of the parent process
+is duplicated into the newly created process. The manager receives
+UFFD_EVENT_FORK with file descriptor of the new userfaultfd context in
+the uffd_msg.fork.
+
+UFFD_FEATURE_EVENT_REMAP - enable notifications about mremap()
+calls. When the non-cooperative process moves a virtual memory area to
+a different location, the manager will receive UFFD_EVENT_REMAP. The
+uffd_msg.remap will contain the old and new addresses of the area and
+its original length.
+
+UFFD_FEATURE_EVENT_REMOVE - enable notifications about
+madvise(MADV_REMOVE) and madvise(MADV_DONTNEED) calls. The event
+UFFD_EVENT_REMOVE will be generated upon these calls to madvise. The
+uffd_msg.remove will contain start and end addresses of the removed
+area.
+
+UFFD_FEATURE_EVENT_UNMAP - enable notifications about memory
+unmapping. The manager will get UFFD_EVENT_UNMAP with uffd_msg.remove
+containing start and end addresses of the unmapped area.
+
+Although the UFFD_FEATURE_EVENT_REMOVE and UFFD_FEATURE_EVENT_UNMAP
+are pretty similar, they quite differ in the action expected from the
+userfaultfd manager. In the former case, the virtual memory is
+removed, but the area is not, the area remains monitored by the
+userfaultfd, and if a page fault occurs in that area it will be
+delivered to the manager. The proper resolution for such page fault is
+to zeromap the faulting address. However, in the latter case, when an
+area is unmapped, either explicitly (with munmap() system call), or
+implicitly (e.g. during mremap()), the area is removed and in turn the
+userfaultfd context for such area disappears too and the manager will
+not get further userland page faults from the removed area. Still, the
+notification is required in order to prevent manager from using
+UFFDIO_COPY on the unmapped area.
+
+Unlike userland page faults which have to be synchronous and require
+explicit or implicit wakeup, all the events are delivered
+asynchronously and the non-cooperative process resumes execution as
+soon as manager executes read(). The userfaultfd manager should
+carefully synchronize calls to UFFDIO_COPY with the events
+processing. To aid the synchronization, the UFFDIO_COPY ioctl will
+return -ENOSPC when the monitored process exits at the time of
+UFFDIO_COPY, and -ENOENT, when the non-cooperative process has changed
+its virtual memory layout simultaneously with outstanding UFFDIO_COPY
+operation.
+
+The current asynchronous model of the event delivery is optimal for
+single threaded non-cooperative userfaultfd manager implementations. A
+synchronous event delivery model can be added later as a new
+userfaultfd feature to facilitate multithreading enhancements of the
+non cooperative manager, for example to allow UFFDIO_COPY ioctls to
+run in parallel to the event reception. Single threaded
+implementations should continue to use the current async event
+delivery model instead.

arch/Kconfig

@@ -571,6 +571,9 @@ config HAVE_IRQ_TIME_ACCOUNTING
 config HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	bool
 
+config HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+	bool
+
 config HAVE_ARCH_HUGE_VMAP
 	bool
 

arch/alpha/include/asm/Kbuild

@@ -9,3 +9,4 @@ generic-y += mm-arch-hooks.h
 generic-y += preempt.h
 generic-y += sections.h
 generic-y += trace_clock.h
+generic-y += current.h

arch/arm/mm/dma-mapping.c

@@ -349,7 +349,7 @@ static void __dma_free_buffer(struct page *page, size_t size)
 static void *__alloc_from_contiguous(struct device *dev, size_t size,
 				     pgprot_t prot, struct page **ret_page,
 				     const void *caller, bool want_vaddr,
-				     int coherent_flag);
+				     int coherent_flag, gfp_t gfp);
 
 static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
 				 pgprot_t prot, struct page **ret_page,
@@ -420,7 +420,8 @@ static int __init atomic_pool_init(void)
 	 */
 	if (dev_get_cma_area(NULL))
 		ptr = __alloc_from_contiguous(NULL, atomic_pool_size, prot,
-				      &page, atomic_pool_init, true, NORMAL);
+				      &page, atomic_pool_init, true, NORMAL,
+				      GFP_KERNEL);
 	else
 		ptr = __alloc_remap_buffer(NULL, atomic_pool_size, gfp, prot,
 					   &page, atomic_pool_init, true);
@@ -594,14 +595,14 @@ static int __free_from_pool(void *start, size_t size)
 static void *__alloc_from_contiguous(struct device *dev, size_t size,
 				     pgprot_t prot, struct page **ret_page,
 				     const void *caller, bool want_vaddr,
-				     int coherent_flag)
+				     int coherent_flag, gfp_t gfp)
 {
 	unsigned long order = get_order(size);
 	size_t count = size >> PAGE_SHIFT;
 	struct page *page;
 	void *ptr = NULL;
 
-	page = dma_alloc_from_contiguous(dev, count, order);
+	page = dma_alloc_from_contiguous(dev, count, order, gfp);
 	if (!page)
 		return NULL;
 
@@ -655,7 +656,7 @@ static inline pgprot_t __get_dma_pgprot(unsigned long attrs, pgprot_t prot)
 #define __get_dma_pgprot(attrs, prot)				__pgprot(0)
 #define __alloc_remap_buffer(dev, size, gfp, prot, ret, c, wv)	NULL
 #define __alloc_from_pool(size, ret_page)			NULL
-#define __alloc_from_contiguous(dev, size, prot, ret, c, wv, coherent_flag)	NULL
+#define __alloc_from_contiguous(dev, size, prot, ret, c, wv, coherent_flag, gfp)	NULL
 #define __free_from_pool(cpu_addr, size)			do { } while (0)
 #define __free_from_contiguous(dev, page, cpu_addr, size, wv)	do { } while (0)
 #define __dma_free_remap(cpu_addr, size)			do { } while (0)
@@ -697,7 +698,8 @@ static void *cma_allocator_alloc(struct arm_dma_alloc_args *args,
 {
 	return __alloc_from_contiguous(args->dev, args->size, args->prot,
 				       ret_page, args->caller,
-				       args->want_vaddr, args->coherent_flag);
+				       args->want_vaddr, args->coherent_flag,
+				       args->gfp);
 }
 
 static void cma_allocator_free(struct arm_dma_free_args *args)
@@ -1312,7 +1314,7 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
 		unsigned long order = get_order(size);
 		struct page *page;
 
-		page = dma_alloc_from_contiguous(dev, count, order);
+		page = dma_alloc_from_contiguous(dev, count, order, gfp);
 		if (!page)
 			goto error;
 

arch/arm64/mm/dma-mapping.c

@@ -107,7 +107,7 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size,
 		void *addr;
 
 		page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT,
-							get_order(size));
+						 get_order(size), flags);
 		if (!page)
 			return NULL;
 
@@ -390,7 +390,7 @@ static int __init atomic_pool_init(void)
 
 	if (dev_get_cma_area(NULL))
 		page = dma_alloc_from_contiguous(NULL, nr_pages,
-							pool_size_order);
+						 pool_size_order, GFP_KERNEL);
 	else
 		page = alloc_pages(GFP_DMA, pool_size_order);
 

arch/cris/include/asm/Kbuild

@@ -4,6 +4,7 @@ generic-y += barrier.h
 generic-y += bitsperlong.h
 generic-y += clkdev.h
 generic-y += cmpxchg.h
+generic-y += current.h
 generic-y += device.h
 generic-y += div64.h
 generic-y += errno.h

arch/frv/mb93090-mb00/pci-frv.c

@@ -147,7 +147,7 @@ static void __init pcibios_allocate_resources(int pass)
 static void __init pcibios_assign_resources(void)
 {
 	struct pci_dev *dev = NULL;
-	int idx;
+	int idx, err;
 	struct resource *r;
 
 	for_each_pci_dev(dev) {
@@ -172,8 +172,13 @@ static void __init pcibios_assign_resources(void)
 			 *  the BIOS forgot to do so or because we have decided the old
 			 *  address was unusable for some reason.
 			 */
-			if (!r->start && r->end)
-				pci_assign_resource(dev, idx);
+			if (!r->start && r->end) {
+				err = pci_assign_resource(dev, idx);
+				if (err)
+					dev_err(&dev->dev,
+						"Failed to assign new address to %d\n",
+						idx);
+			}
 		}
 	}
 }

arch/m68k/68000/bootlogo-vz.h

@@ -1,6 +1,8 @@
+#include <linux/compiler.h>
+
 #define splash_width 640
 #define splash_height 480
-unsigned char __attribute__ ((aligned(16))) bootlogo_bits[] = {
+unsigned char __aligned(16) bootlogo_bits[] = {
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,

arch/m68k/68000/bootlogo.h

@@ -1,6 +1,8 @@
+#include <linux/compiler.h>
+
 #define bootlogo_width 160
 #define bootlogo_height 160
-unsigned char __attribute__ ((aligned(16))) bootlogo_bits[] = {
+unsigned char __aligned(16) bootlogo_bits[] = {
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x55, 0x01, 0x00, 0x00, 0x00,
   0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
   0x00, 0x00, 0x40, 0x55, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,

arch/m68k/include/asm/MC68328.h

@@ -8,6 +8,7 @@
  * Copyright (C) 1998  Kenneth Albanowski <[email protected]>,
  *
  */
+#include <linux/compiler.h>
 
 #ifndef _MC68328_H_
 #define _MC68328_H_
@@ -993,7 +994,7 @@ typedef volatile struct {
   volatile unsigned short int pad1;
   volatile unsigned short int pad2;
   volatile unsigned short int pad3;
-} __attribute__((packed)) m68328_uart;
+} __packed m68328_uart;
 
 
 /**********

arch/m68k/include/asm/MC68EZ328.h

@@ -9,6 +9,7 @@
  *                     The Silver Hammer Group, Ltd.
  *
  */
+#include <linux/compiler.h>
 
 #ifndef _MC68EZ328_H_
 #define _MC68EZ328_H_
@@ -815,7 +816,7 @@ typedef volatile struct {
   volatile unsigned short int nipr;
   volatile unsigned short int pad1;
   volatile unsigned short int pad2;
-} __attribute__((packed)) m68328_uart;
+} __packed m68328_uart;
 
 
 /**********

arch/m68k/include/asm/MC68VZ328.h

@@ -909,7 +909,7 @@ typedef struct {
   volatile unsigned short int nipr;
   volatile unsigned short int hmark;
   volatile unsigned short int unused;
-} __attribute__((packed)) m68328_uart;
+} __packed m68328_uart;
 
 
 

arch/m68k/include/asm/natfeat.h

@@ -6,6 +6,7 @@
  * This software may be used and distributed according to the terms of
  * the GNU General Public License (GPL), incorporated herein by reference.
  */
+#include <linux/compiler.h>
 
 #ifndef _NATFEAT_H
 #define _NATFEAT_H
@@ -17,6 +18,6 @@ void nf_init(void);
 void nf_shutdown(void);
 
 void nfprint(const char *fmt, ...)
-	__attribute__ ((format (printf, 1, 2)));
+	__printf(1, 2);
 
 # endif /* _NATFEAT_H */