Merge branch 'akpm' (patches from Andrew)

Merge patch-bomb from Andrew Morton:

 - a few misc things

 - Andy's "ambient capabilities"

 - fs/nofity updates

 - the ocfs2 queue

 - kernel/watchdog.c updates and feature work.

 - some of MM.  Includes Andrea's userfaultfd feature.

[ Hadn't noticed that userfaultfd was 'default y' when applying the
  patches, so that got fixed in this merge instead.  We do _not_ mark
  new features that nobody uses yet 'default y'   - Linus ]

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (118 commits)
  mm/hugetlb.c: make vma_has_reserves() return bool
  mm/madvise.c: make madvise_behaviour_valid() return bool
  mm/memory.c: make tlb_next_batch() return bool
  mm/dmapool.c: change is_page_busy() return from int to bool
  mm: remove struct node_active_region
  mremap: simplify the "overlap" check in mremap_to()
  mremap: don't do uneccesary checks if new_len == old_len
  mremap: don't do mm_populate(new_addr) on failure
  mm: move ->mremap() from file_operations to vm_operations_struct
  mremap: don't leak new_vma if f_op->mremap() fails
  mm/hugetlb.c: make vma_shareable() return bool
  mm: make GUP handle pfn mapping unless FOLL_GET is requested
  mm: fix status code which move_pages() returns for zero page
  mm: memcontrol: bring back the VM_BUG_ON() in mem_cgroup_swapout()
  genalloc: add support of multiple gen_pools per device
  genalloc: add name arg to gen_pool_get() and devm_gen_pool_create()
  mm/memblock: WARN_ON when nid differs from overlap region
  Documentation/features/vm: add feature description and arch support status for batched TLB flush after unmap
  mm: defer flush of writable TLB entries
  mm: send one IPI per CPU to TLB flush all entries after unmapping pages
  ...

4 files changed, 187 insertions, 1 deletions

diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index aafb993..70ff1d9 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -456,3 +456,4 @@ header-y += xfrm.h
 header-y += xilinx-v4l2-controls.h
 header-y += zorro.h
 header-y += zorro_ids.h
+header-y += userfaultfd.h
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 31891d9..a8d0759 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -190,4 +190,11 @@ struct prctl_mm_map {
 # define PR_FP_MODE_FR		(1 << 0)	/* 64b FP registers */
 # define PR_FP_MODE_FRE		(1 << 1)	/* 32b compatibility */
 
+/* Control the ambient capability set */
+#define PR_CAP_AMBIENT			47
+# define PR_CAP_AMBIENT_IS_SET		1
+# define PR_CAP_AMBIENT_RAISE		2
+# define PR_CAP_AMBIENT_LOWER		3
+# define PR_CAP_AMBIENT_CLEAR_ALL	4
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/include/uapi/linux/securebits.h b/include/uapi/linux/securebits.h
index 985aac9..35ac35c 100644
--- a/include/uapi/linux/securebits.h
+++ b/include/uapi/linux/securebits.h
@@ -43,9 +43,18 @@
 #define SECBIT_KEEP_CAPS	(issecure_mask(SECURE_KEEP_CAPS))
 #define SECBIT_KEEP_CAPS_LOCKED (issecure_mask(SECURE_KEEP_CAPS_LOCKED))
 
+/* When set, a process cannot add new capabilities to its ambient set. */
+#define SECURE_NO_CAP_AMBIENT_RAISE		6
+#define SECURE_NO_CAP_AMBIENT_RAISE_LOCKED	7  /* make bit-6 immutable */
+
+#define SECBIT_NO_CAP_AMBIENT_RAISE (issecure_mask(SECURE_NO_CAP_AMBIENT_RAISE))
+#define SECBIT_NO_CAP_AMBIENT_RAISE_LOCKED \
+			(issecure_mask(SECURE_NO_CAP_AMBIENT_RAISE_LOCKED))
+
 #define SECURE_ALL_BITS		(issecure_mask(SECURE_NOROOT) | \
 				 issecure_mask(SECURE_NO_SETUID_FIXUP) | \
-				 issecure_mask(SECURE_KEEP_CAPS))
+				 issecure_mask(SECURE_KEEP_CAPS) | \
+				 issecure_mask(SECURE_NO_CAP_AMBIENT_RAISE))
 #define SECURE_ALL_LOCKS	(SECURE_ALL_BITS << 1)
 
 #endif /* _UAPI_LINUX_SECUREBITS_H */
diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
new file mode 100644
index 0000000..df0e09b
--- /dev/null
+++ b/include/uapi/linux/userfaultfd.h
@@ -0,0 +1,169 @@
+/*
+ *  include/linux/userfaultfd.h
+ *
+ *  Copyright (C) 2007  Davide Libenzi <davidel@xmailserver.org>
+ *  Copyright (C) 2015  Red Hat, Inc.
+ *
+ */
+
+#ifndef _LINUX_USERFAULTFD_H
+#define _LINUX_USERFAULTFD_H
+
+#include <linux/types.h>
+
+#include <linux/compiler.h>
+
+#define UFFD_API ((__u64)0xAA)
+/*
+ * After implementing the respective features it will become:
+ * #define UFFD_API_FEATURES (UFFD_FEATURE_PAGEFAULT_FLAG_WP | \
+ *			      UFFD_FEATURE_EVENT_FORK)
+ */
+#define UFFD_API_FEATURES (0)
+#define UFFD_API_IOCTLS				\
+	((__u64)1 << _UFFDIO_REGISTER |		\
+	 (__u64)1 << _UFFDIO_UNREGISTER |	\
+	 (__u64)1 << _UFFDIO_API)
+#define UFFD_API_RANGE_IOCTLS			\
+	((__u64)1 << _UFFDIO_WAKE |		\
+	 (__u64)1 << _UFFDIO_COPY |		\
+	 (__u64)1 << _UFFDIO_ZEROPAGE)
+
+/*
+ * Valid ioctl command number range with this API is from 0x00 to
+ * 0x3F.  UFFDIO_API is the fixed number, everything else can be
+ * changed by implementing a different UFFD_API. If sticking to the
+ * same UFFD_API more ioctl can be added and userland will be aware of
+ * which ioctl the running kernel implements through the ioctl command
+ * bitmask written by the UFFDIO_API.
+ */
+#define _UFFDIO_REGISTER		(0x00)
+#define _UFFDIO_UNREGISTER		(0x01)
+#define _UFFDIO_WAKE			(0x02)
+#define _UFFDIO_COPY			(0x03)
+#define _UFFDIO_ZEROPAGE		(0x04)
+#define _UFFDIO_API			(0x3F)
+
+/* userfaultfd ioctl ids */
+#define UFFDIO 0xAA
+#define UFFDIO_API		_IOWR(UFFDIO, _UFFDIO_API,	\
+				      struct uffdio_api)
+#define UFFDIO_REGISTER		_IOWR(UFFDIO, _UFFDIO_REGISTER, \
+				      struct uffdio_register)
+#define UFFDIO_UNREGISTER	_IOR(UFFDIO, _UFFDIO_UNREGISTER,	\
+				     struct uffdio_range)
+#define UFFDIO_WAKE		_IOR(UFFDIO, _UFFDIO_WAKE,	\
+				     struct uffdio_range)
+#define UFFDIO_COPY		_IOWR(UFFDIO, _UFFDIO_COPY,	\
+				      struct uffdio_copy)
+#define UFFDIO_ZEROPAGE		_IOWR(UFFDIO, _UFFDIO_ZEROPAGE,	\
+				      struct uffdio_zeropage)
+
+/* read() structure */
+struct uffd_msg {
+	__u8	event;
+
+	__u8	reserved1;
+	__u16	reserved2;
+	__u32	reserved3;
+
+	union {
+		struct {
+			__u64	flags;
+			__u64	address;
+		} pagefault;
+
+		struct {
+			/* unused reserved fields */
+			__u64	reserved1;
+			__u64	reserved2;
+			__u64	reserved3;
+		} reserved;
+	} arg;
+} __packed;
+
+/*
+ * Start at 0x12 and not at 0 to be more strict against bugs.
+ */
+#define UFFD_EVENT_PAGEFAULT	0x12
+#if 0 /* not available yet */
+#define UFFD_EVENT_FORK		0x13
+#endif
+
+/* flags for UFFD_EVENT_PAGEFAULT */
+#define UFFD_PAGEFAULT_FLAG_WRITE	(1<<0)	/* If this was a write fault */
+#define UFFD_PAGEFAULT_FLAG_WP		(1<<1)	/* If reason is VM_UFFD_WP */
+
+struct uffdio_api {
+	/* userland asks for an API number and the features to enable */
+	__u64 api;
+	/*
+	 * Kernel answers below with the all available features for
+	 * the API, this notifies userland of which events and/or
+	 * which flags for each event are enabled in the current
+	 * kernel.
+	 *
+	 * Note: UFFD_EVENT_PAGEFAULT and UFFD_PAGEFAULT_FLAG_WRITE
+	 * are to be considered implicitly always enabled in all kernels as
+	 * long as the uffdio_api.api requested matches UFFD_API.
+	 */
+#if 0 /* not available yet */
+#define UFFD_FEATURE_PAGEFAULT_FLAG_WP		(1<<0)
+#define UFFD_FEATURE_EVENT_FORK			(1<<1)
+#endif
+	__u64 features;
+
+	__u64 ioctls;
+};
+
+struct uffdio_range {
+	__u64 start;
+	__u64 len;
+};
+
+struct uffdio_register {
+	struct uffdio_range range;
+#define UFFDIO_REGISTER_MODE_MISSING	((__u64)1<<0)
+#define UFFDIO_REGISTER_MODE_WP		((__u64)1<<1)
+	__u64 mode;
+
+	/*
+	 * kernel answers which ioctl commands are available for the
+	 * range, keep at the end as the last 8 bytes aren't read.
+	 */
+	__u64 ioctls;
+};
+
+struct uffdio_copy {
+	__u64 dst;
+	__u64 src;
+	__u64 len;
+	/*
+	 * There will be a wrprotection flag later that allows to map
+	 * pages wrprotected on the fly. And such a flag will be
+	 * available if the wrprotection ioctl are implemented for the
+	 * range according to the uffdio_register.ioctls.
+	 */
+#define UFFDIO_COPY_MODE_DONTWAKE		((__u64)1<<0)
+	__u64 mode;
+
+	/*
+	 * "copy" is written by the ioctl and must be at the end: the
+	 * copy_from_user will not read the last 8 bytes.
+	 */
+	__s64 copy;
+};
+
+struct uffdio_zeropage {
+	struct uffdio_range range;
+#define UFFDIO_ZEROPAGE_MODE_DONTWAKE		((__u64)1<<0)
+	__u64 mode;
+
+	/*
+	 * "zeropage" is written by the ioctl and must be at the end:
+	 * the copy_from_user will not read the last 8 bytes.
+	 */
+	__s64 zeropage;
+};
+
+#endif /* _LINUX_USERFAULTFD_H */