summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-10-16 21:31:55 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2020-10-16 21:31:55 +0300
commitc4cf498dc0241fa2d758dba177634268446afb06 (patch)
tree77e86dd4f211c6681ff9fbab481295732dc23422 /include
parent9ff9b0d392ea08090cd1780fb196f36dbb586529 (diff)
parent4d0e9df5e43dba52d38b251e3b909df8fa1110be (diff)
downloadlinux-c4cf498dc0241fa2d758dba177634268446afb06.tar.xz
Merge branch 'akpm' (patches from Andrew)
Merge more updates from Andrew Morton: "155 patches. Subsystems affected by this patch series: mm (dax, debug, thp, readahead, page-poison, util, memory-hotplug, zram, cleanups), misc, core-kernel, get_maintainer, MAINTAINERS, lib, bitops, checkpatch, binfmt, ramfs, autofs, nilfs, rapidio, panic, relay, kgdb, ubsan, romfs, and fault-injection" * emailed patches from Andrew Morton <akpm@linux-foundation.org>: (155 commits) lib, uaccess: add failure injection to usercopy functions lib, include/linux: add usercopy failure capability ROMFS: support inode blocks calculation ubsan: introduce CONFIG_UBSAN_LOCAL_BOUNDS for Clang sched.h: drop in_ubsan field when UBSAN is in trap mode scripts/gdb/tasks: add headers and improve spacing format scripts/gdb/proc: add struct mount & struct super_block addr in lx-mounts command kernel/relay.c: drop unneeded initialization panic: dump registers on panic_on_warn rapidio: fix the missed put_device() for rio_mport_add_riodev rapidio: fix error handling path nilfs2: fix some kernel-doc warnings for nilfs2 autofs: harden ioctl table ramfs: fix nommu mmap with gaps in the page cache mm: remove the now-unnecessary mmget_still_valid() hack mm/gup: take mmap_lock in get_dump_page() binfmt_elf, binfmt_elf_fdpic: use a VMA list snapshot coredump: rework elf/elf_fdpic vma_dump_size() into common helper coredump: refactor page range dumping into common helper coredump: let dump_emit() bail out on short writes ...
Diffstat (limited to 'include')
-rw-r--r--include/linux/bitops.h13
-rw-r--r--include/linux/blkdev.h1
-rw-r--r--include/linux/bvec.h6
-rw-r--r--include/linux/coredump.h11
-rw-r--r--include/linux/fault-inject-usercopy.h22
-rw-r--r--include/linux/fs.h28
-rw-r--r--include/linux/idr.h13
-rw-r--r--include/linux/ioport.h11
-rw-r--r--include/linux/jiffies.h3
-rw-r--r--include/linux/kernel.h150
-rw-r--r--include/linux/list.h29
-rw-r--r--include/linux/memory_hotplug.h42
-rw-r--r--include/linux/minmax.h153
-rw-r--r--include/linux/mm.h5
-rw-r--r--include/linux/mmzone.h17
-rw-r--r--include/linux/node.h16
-rw-r--r--include/linux/nodemask.h2
-rw-r--r--include/linux/page-flags.h6
-rw-r--r--include/linux/page_owner.h6
-rw-r--r--include/linux/pagemap.h107
-rw-r--r--include/linux/sched.h2
-rw-r--r--include/linux/sched/mm.h25
-rw-r--r--include/linux/uaccess.h12
-rw-r--r--include/linux/vmstat.h2
-rw-r--r--include/linux/xarray.h22
-rw-r--r--include/ras/ras_event.h3
26 files changed, 419 insertions, 288 deletions
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 99f2ac30b1d9..5b74bdf159d6 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -188,12 +188,10 @@ static inline unsigned fls_long(unsigned long l)
static inline int get_count_order(unsigned int count)
{
- int order;
+ if (count == 0)
+ return -1;
- order = fls(count) - 1;
- if (count & (count - 1))
- order++;
- return order;
+ return fls(--count);
}
/**
@@ -206,10 +204,7 @@ static inline int get_count_order_long(unsigned long l)
{
if (l == 0UL)
return -1;
- else if (l & (l - 1UL))
- return (int)fls_long(l);
- else
- return (int)fls_long(l) - 1;
+ return (int)fls_long(--l);
}
/**
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c09375e0a0eb..639cae2c158b 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -8,6 +8,7 @@
#include <linux/genhd.h>
#include <linux/list.h>
#include <linux/llist.h>
+#include <linux/minmax.h>
#include <linux/timer.h>
#include <linux/workqueue.h>
#include <linux/pagemap.h>
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index dd74503f7e5e..2efec10bf792 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -7,10 +7,14 @@
#ifndef __LINUX_BVEC_ITER_H
#define __LINUX_BVEC_ITER_H
-#include <linux/kernel.h>
#include <linux/bug.h>
#include <linux/errno.h>
+#include <linux/limits.h>
+#include <linux/minmax.h>
#include <linux/mm.h>
+#include <linux/types.h>
+
+struct page;
/**
* struct bio_vec - a contiguous range of physical memory addresses
diff --git a/include/linux/coredump.h b/include/linux/coredump.h
index 7a899e83835d..e58e8c207782 100644
--- a/include/linux/coredump.h
+++ b/include/linux/coredump.h
@@ -7,6 +7,12 @@
#include <linux/fs.h>
#include <asm/siginfo.h>
+struct core_vma_metadata {
+ unsigned long start, end;
+ unsigned long flags;
+ unsigned long dump_size;
+};
+
/*
* These are the only things you should do on a core-file: use only these
* functions to write out all the necessary info.
@@ -16,6 +22,11 @@ extern int dump_skip(struct coredump_params *cprm, size_t nr);
extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr);
extern int dump_align(struct coredump_params *cprm, int align);
extern void dump_truncate(struct coredump_params *cprm);
+int dump_user_range(struct coredump_params *cprm, unsigned long start,
+ unsigned long len);
+int dump_vma_snapshot(struct coredump_params *cprm, int *vma_count,
+ struct core_vma_metadata **vma_meta,
+ size_t *vma_data_size_ptr);
#ifdef CONFIG_COREDUMP
extern void do_coredump(const kernel_siginfo_t *siginfo);
#else
diff --git a/include/linux/fault-inject-usercopy.h b/include/linux/fault-inject-usercopy.h
new file mode 100644
index 000000000000..56c3a693fdd9
--- /dev/null
+++ b/include/linux/fault-inject-usercopy.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_FAULT_INJECT_USERCOPY_H__
+#define __LINUX_FAULT_INJECT_USERCOPY_H__
+
+/*
+ * This header provides a wrapper for injecting failures to user space memory
+ * access functions.
+ */
+
+#include <linux/types.h>
+
+#ifdef CONFIG_FAULT_INJECTION_USERCOPY
+
+bool should_fail_usercopy(void);
+
+#else
+
+static inline bool should_fail_usercopy(void) { return false; }
+
+#endif /* CONFIG_FAULT_INJECTION_USERCOPY */
+
+#endif /* __LINUX_FAULT_INJECT_USERCOPY_H__ */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ae97d87a00d2..d1d166b46131 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2209,6 +2209,7 @@ struct file_system_type {
#define FS_HAS_SUBTYPE 4
#define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */
#define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */
+#define FS_THP_SUPPORT 8192 /* Remove once all fs converted */
#define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */
int (*init_fs_context)(struct fs_context *);
const struct fs_parameter_spec *parameters;
@@ -2696,33 +2697,6 @@ static inline errseq_t file_sample_sb_err(struct file *file)
return errseq_sample(&file->f_path.dentry->d_sb->s_wb_err);
}
-static inline int filemap_nr_thps(struct address_space *mapping)
-{
-#ifdef CONFIG_READ_ONLY_THP_FOR_FS
- return atomic_read(&mapping->nr_thps);
-#else
- return 0;
-#endif
-}
-
-static inline void filemap_nr_thps_inc(struct address_space *mapping)
-{
-#ifdef CONFIG_READ_ONLY_THP_FOR_FS
- atomic_inc(&mapping->nr_thps);
-#else
- WARN_ON_ONCE(1);
-#endif
-}
-
-static inline void filemap_nr_thps_dec(struct address_space *mapping)
-{
-#ifdef CONFIG_READ_ONLY_THP_FOR_FS
- atomic_dec(&mapping->nr_thps);
-#else
- WARN_ON_ONCE(1);
-#endif
-}
-
extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end,
int datasync);
extern int vfs_fsync(struct file *file, int datasync);
diff --git a/include/linux/idr.h b/include/linux/idr.h
index 3ade03e5c7af..a0dce14090a9 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -263,7 +263,8 @@ void ida_destroy(struct ida *ida);
*
* Allocate an ID between 0 and %INT_MAX, inclusive.
*
- * Context: Any context.
+ * Context: Any context. It is safe to call this function without
+ * locking in your code.
* Return: The allocated ID, or %-ENOMEM if memory could not be allocated,
* or %-ENOSPC if there are no free IDs.
*/
@@ -280,7 +281,8 @@ static inline int ida_alloc(struct ida *ida, gfp_t gfp)
*
* Allocate an ID between @min and %INT_MAX, inclusive.
*
- * Context: Any context.
+ * Context: Any context. It is safe to call this function without
+ * locking in your code.
* Return: The allocated ID, or %-ENOMEM if memory could not be allocated,
* or %-ENOSPC if there are no free IDs.
*/
@@ -297,7 +299,8 @@ static inline int ida_alloc_min(struct ida *ida, unsigned int min, gfp_t gfp)
*
* Allocate an ID between 0 and @max, inclusive.
*
- * Context: Any context.
+ * Context: Any context. It is safe to call this function without
+ * locking in your code.
* Return: The allocated ID, or %-ENOMEM if memory could not be allocated,
* or %-ENOSPC if there are no free IDs.
*/
@@ -311,6 +314,10 @@ static inline void ida_init(struct ida *ida)
xa_init_flags(&ida->xa, IDA_INIT_FLAGS);
}
+/*
+ * ida_simple_get() and ida_simple_remove() are deprecated. Use
+ * ida_alloc() and ida_free() instead respectively.
+ */
#define ida_simple_get(ida, start, end, gfp) \
ida_alloc_range(ida, start, (end) - 1, gfp)
#define ida_simple_remove(ida, id) ida_free(ida, id)
diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index 6c2b06fe8beb..5135d4b86cd6 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -58,6 +58,10 @@ struct resource {
#define IORESOURCE_EXT_TYPE_BITS 0x01000000 /* Resource extended types */
#define IORESOURCE_SYSRAM 0x01000000 /* System RAM (modifier) */
+/* IORESOURCE_SYSRAM specific bits. */
+#define IORESOURCE_SYSRAM_DRIVER_MANAGED 0x02000000 /* Always detected via a driver. */
+#define IORESOURCE_SYSRAM_MERGEABLE 0x04000000 /* Resource can be merged. */
+
#define IORESOURCE_EXCLUSIVE 0x08000000 /* Userland may not map this resource */
#define IORESOURCE_DISABLED 0x10000000
@@ -103,7 +107,6 @@ struct resource {
#define IORESOURCE_MEM_32BIT (3<<3)
#define IORESOURCE_MEM_SHADOWABLE (1<<5) /* dup: IORESOURCE_SHADOWABLE */
#define IORESOURCE_MEM_EXPANSIONROM (1<<6)
-#define IORESOURCE_MEM_DRIVER_MANAGED (1<<7)
/* PnP I/O specific bits (IORESOURCE_BITS) */
#define IORESOURCE_IO_16BIT_ADDR (1<<0)
@@ -248,8 +251,10 @@ extern struct resource * __request_region(struct resource *,
extern void __release_region(struct resource *, resource_size_t,
resource_size_t);
#ifdef CONFIG_MEMORY_HOTREMOVE
-extern int release_mem_region_adjustable(struct resource *, resource_size_t,
- resource_size_t);
+extern void release_mem_region_adjustable(resource_size_t, resource_size_t);
+#endif
+#ifdef CONFIG_MEMORY_HOTPLUG
+extern void merge_system_ram_resource(struct resource *res);
#endif
/* Wrappers for managed devices */
diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h
index fed6ba96c527..5e13f801c902 100644
--- a/include/linux/jiffies.h
+++ b/include/linux/jiffies.h
@@ -3,8 +3,9 @@
#define _LINUX_JIFFIES_H
#include <linux/cache.h>
+#include <linux/limits.h>
#include <linux/math64.h>
-#include <linux/kernel.h>
+#include <linux/minmax.h>
#include <linux/types.h>
#include <linux/time.h>
#include <linux/timex.h>
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index e4aa29b1ad62..c629215fdad9 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -11,6 +11,7 @@
#include <linux/compiler.h>
#include <linux/bitops.h>
#include <linux/log2.h>
+#include <linux/minmax.h>
#include <linux/typecheck.h>
#include <linux/printk.h>
#include <linux/build_bug.h>
@@ -833,155 +834,6 @@ ftrace_vprintk(const char *fmt, va_list ap)
static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
#endif /* CONFIG_TRACING */
-/*
- * min()/max()/clamp() macros must accomplish three things:
- *
- * - avoid multiple evaluations of the arguments (so side-effects like
- * "x++" happen only once) when non-constant.
- * - perform strict type-checking (to generate warnings instead of
- * nasty runtime surprises). See the "unnecessary" pointer comparison
- * in __typecheck().
- * - retain result as a constant expressions when called with only
- * constant expressions (to avoid tripping VLA warnings in stack
- * allocation usage).
- */
-#define __typecheck(x, y) \
- (!!(sizeof((typeof(x) *)1 == (typeof(y) *)1)))
-
-/*
- * This returns a constant expression while determining if an argument is
- * a constant expression, most importantly without evaluating the argument.
- * Glory to Martin Uecker <Martin.Uecker@med.uni-goettingen.de>
- */
-#define __is_constexpr(x) \
- (sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8)))
-
-#define __no_side_effects(x, y) \
- (__is_constexpr(x) && __is_constexpr(y))
-
-#define __safe_cmp(x, y) \
- (__typecheck(x, y) && __no_side_effects(x, y))
-
-#define __cmp(x, y, op) ((x) op (y) ? (x) : (y))
-
-#define __cmp_once(x, y, unique_x, unique_y, op) ({ \
- typeof(x) unique_x = (x); \
- typeof(y) unique_y = (y); \
- __cmp(unique_x, unique_y, op); })
-
-#define __careful_cmp(x, y, op) \
- __builtin_choose_expr(__safe_cmp(x, y), \
- __cmp(x, y, op), \
- __cmp_once(x, y, __UNIQUE_ID(__x), __UNIQUE_ID(__y), op))
-
-/**
- * min - return minimum of two values of the same or compatible types
- * @x: first value
- * @y: second value
- */
-#define min(x, y) __careful_cmp(x, y, <)
-
-/**
- * max - return maximum of two values of the same or compatible types
- * @x: first value
- * @y: second value
- */
-#define max(x, y) __careful_cmp(x, y, >)
-
-/**
- * min3 - return minimum of three values
- * @x: first value
- * @y: second value
- * @z: third value
- */
-#define min3(x, y, z) min((typeof(x))min(x, y), z)
-
-/**
- * max3 - return maximum of three values
- * @x: first value
- * @y: second value
- * @z: third value
- */
-#define max3(x, y, z) max((typeof(x))max(x, y), z)
-
-/**
- * min_not_zero - return the minimum that is _not_ zero, unless both are zero
- * @x: value1
- * @y: value2
- */
-#define min_not_zero(x, y) ({ \
- typeof(x) __x = (x); \
- typeof(y) __y = (y); \
- __x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); })
-
-/**
- * clamp - return a value clamped to a given range with strict typechecking
- * @val: current value
- * @lo: lowest allowable value
- * @hi: highest allowable value
- *
- * This macro does strict typechecking of @lo/@hi to make sure they are of the
- * same type as @val. See the unnecessary pointer comparisons.
- */
-#define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi)
-
-/*
- * ..and if you can't take the strict
- * types, you can specify one yourself.
- *
- * Or not use min/max/clamp at all, of course.
- */
-
-/**
- * min_t - return minimum of two values, using the specified type
- * @type: data type to use
- * @x: first value
- * @y: second value
- */
-#define min_t(type, x, y) __careful_cmp((type)(x), (type)(y), <)
-
-/**
- * max_t - return maximum of two values, using the specified type
- * @type: data type to use
- * @x: first value
- * @y: second value
- */
-#define max_t(type, x, y) __careful_cmp((type)(x), (type)(y), >)
-
-/**
- * clamp_t - return a value clamped to a given range using a given type
- * @type: the type of variable to use
- * @val: current value
- * @lo: minimum allowable value
- * @hi: maximum allowable value
- *
- * This macro does no typechecking and uses temporary variables of type
- * @type to make all the comparisons.
- */
-#define clamp_t(type, val, lo, hi) min_t(type, max_t(type, val, lo), hi)
-
-/**
- * clamp_val - return a value clamped to a given range using val's type
- * @val: current value
- * @lo: minimum allowable value
- * @hi: maximum allowable value
- *
- * This macro does no typechecking and uses temporary variables of whatever
- * type the input argument @val is. This is useful when @val is an unsigned
- * type and @lo and @hi are literals that will otherwise be assigned a signed
- * integer type.
- */
-#define clamp_val(val, lo, hi) clamp_t(typeof(val), val, lo, hi)
-
-
-/**
- * swap - swap values of @a and @b
- * @a: first value
- * @b: second value
- */
-#define swap(a, b) \
- do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
-
/* This counts to 12. Any more, it will return 13th argument. */
#define __COUNT_ARGS(_0, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _n, X...) _n
#define COUNT_ARGS(X...) __COUNT_ARGS(, ##X, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
diff --git a/include/linux/list.h b/include/linux/list.h
index 0d0d17a10d25..a18c87b63376 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -610,6 +610,15 @@ static inline void list_splice_tail_init(struct list_head *list,
pos = n, n = pos->prev)
/**
+ * list_entry_is_head - test if the entry points to the head of the list
+ * @pos: the type * to cursor
+ * @head: the head for your list.
+ * @member: the name of the list_head within the struct.
+ */
+#define list_entry_is_head(pos, head, member) \
+ (&pos->member == (head))
+
+/**
* list_for_each_entry - iterate over list of given type
* @pos: the type * to use as a loop cursor.
* @head: the head for your list.
@@ -617,7 +626,7 @@ static inline void list_splice_tail_init(struct list_head *list,
*/
#define list_for_each_entry(pos, head, member) \
for (pos = list_first_entry(head, typeof(*pos), member); \
- &pos->member != (head); \
+ !list_entry_is_head(pos, head, member); \
pos = list_next_entry(pos, member))
/**
@@ -628,7 +637,7 @@ static inline void list_splice_tail_init(struct list_head *list,
*/
#define list_for_each_entry_reverse(pos, head, member) \
for (pos = list_last_entry(head, typeof(*pos), member); \
- &pos->member != (head); \
+ !list_entry_is_head(pos, head, member); \
pos = list_prev_entry(pos, member))
/**
@@ -653,7 +662,7 @@ static inline void list_splice_tail_init(struct list_head *list,
*/
#define list_for_each_entry_continue(pos, head, member) \
for (pos = list_next_entry(pos, member); \
- &pos->member != (head); \
+ !list_entry_is_head(pos, head, member); \
pos = list_next_entry(pos, member))
/**
@@ -667,7 +676,7 @@ static inline void list_splice_tail_init(struct list_head *list,
*/
#define list_for_each_entry_continue_reverse(pos, head, member) \
for (pos = list_prev_entry(pos, member); \
- &pos->member != (head); \
+ !list_entry_is_head(pos, head, member); \
pos = list_prev_entry(pos, member))
/**
@@ -679,7 +688,7 @@ static inline void list_splice_tail_init(struct list_head *list,
* Iterate over list of given type, continuing from current position.
*/
#define list_for_each_entry_from(pos, head, member) \
- for (; &pos->member != (head); \
+ for (; !list_entry_is_head(pos, head, member); \
pos = list_next_entry(pos, member))
/**
@@ -692,7 +701,7 @@ static inline void list_splice_tail_init(struct list_head *list,
* Iterate backwards over list of given type, continuing from current position.
*/
#define list_for_each_entry_from_reverse(pos, head, member) \
- for (; &pos->member != (head); \
+ for (; !list_entry_is_head(pos, head, member); \
pos = list_prev_entry(pos, member))
/**
@@ -705,7 +714,7 @@ static inline void list_splice_tail_init(struct list_head *list,
#define list_for_each_entry_safe(pos, n, head, member) \
for (pos = list_first_entry(head, typeof(*pos), member), \
n = list_next_entry(pos, member); \
- &pos->member != (head); \
+ !list_entry_is_head(pos, head, member); \
pos = n, n = list_next_entry(n, member))
/**
@@ -721,7 +730,7 @@ static inline void list_splice_tail_init(struct list_head *list,
#define list_for_each_entry_safe_continue(pos, n, head, member) \
for (pos = list_next_entry(pos, member), \
n = list_next_entry(pos, member); \
- &pos->member != (head); \
+ !list_entry_is_head(pos, head, member); \
pos = n, n = list_next_entry(n, member))
/**
@@ -736,7 +745,7 @@ static inline void list_splice_tail_init(struct list_head *list,
*/
#define list_for_each_entry_safe_from(pos, n, head, member) \
for (n = list_next_entry(pos, member); \
- &pos->member != (head); \
+ !list_entry_is_head(pos, head, member); \
pos = n, n = list_next_entry(n, member))
/**
@@ -752,7 +761,7 @@ static inline void list_splice_tail_init(struct list_head *list,
#define list_for_each_entry_safe_reverse(pos, n, head, member) \
for (pos = list_last_entry(head, typeof(*pos), member), \
n = list_prev_entry(pos, member); \
- &pos->member != (head); \
+ !list_entry_is_head(pos, head, member); \
pos = n, n = list_prev_entry(n, member))
/**
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index c0faa7a30c46..d65c6fdc5cfc 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -57,6 +57,19 @@ enum {
MMOP_ONLINE_MOVABLE,
};
+/* Flags for add_memory() and friends to specify memory hotplug details. */
+typedef int __bitwise mhp_t;
+
+/* No special request */
+#define MHP_NONE ((__force mhp_t)0)
+/*
+ * Allow merging of the added System RAM resource with adjacent,
+ * mergeable resources. After a successful call to add_memory_resource()
+ * with this flag set, the resource pointer must no longer be used as it
+ * might be stale, or the resource might have changed.
+ */
+#define MEMHP_MERGE_RESOURCE ((__force mhp_t)BIT(0))
+
/*
* Extended parameters for memory hotplug:
* altmap: alternative allocator for memmap array (optional)
@@ -103,8 +116,8 @@ extern int online_pages(unsigned long pfn, unsigned long nr_pages,
int online_type, int nid);
extern struct zone *test_pages_in_a_zone(unsigned long start_pfn,
unsigned long end_pfn);
-extern unsigned long __offline_isolated_pages(unsigned long start_pfn,
- unsigned long end_pfn);
+extern void __offline_isolated_pages(unsigned long start_pfn,
+ unsigned long end_pfn);
typedef void (*online_page_callback_t)(struct page *page, unsigned int order);
@@ -247,13 +260,6 @@ static inline void zone_span_writelock(struct zone *zone) {}
static inline void zone_span_writeunlock(struct zone *zone) {}
static inline void zone_seqlock_init(struct zone *zone) {}
-static inline int mhp_notimplemented(const char *func)
-{
- printk(KERN_WARNING "%s() called, with CONFIG_MEMORY_HOTPLUG disabled\n", func);
- dump_stack();
- return -ENOSYS;
-}
-
static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
{
}
@@ -344,14 +350,18 @@ static inline void __remove_memory(int nid, u64 start, u64 size) {}
extern void set_zone_contiguous(struct zone *zone);
extern void clear_zone_contiguous(struct zone *zone);
+#ifdef CONFIG_MEMORY_HOTPLUG
extern void __ref free_area_init_core_hotplug(int nid);
-extern int __add_memory(int nid, u64 start, u64 size);
-extern int add_memory(int nid, u64 start, u64 size);
-extern int add_memory_resource(int nid, struct resource *resource);
+extern int __add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags);
+extern int add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags);
+extern int add_memory_resource(int nid, struct resource *resource,
+ mhp_t mhp_flags);
extern int add_memory_driver_managed(int nid, u64 start, u64 size,
- const char *resource_name);
+ const char *resource_name,
+ mhp_t mhp_flags);
extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
- unsigned long nr_pages, struct vmem_altmap *altmap);
+ unsigned long nr_pages,
+ struct vmem_altmap *altmap, int migratetype);
extern void remove_pfn_range_from_zone(struct zone *zone,
unsigned long start_pfn,
unsigned long nr_pages);
@@ -363,8 +373,8 @@ extern void sparse_remove_section(struct mem_section *ms,
unsigned long map_offset, struct vmem_altmap *altmap);
extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
unsigned long pnum);
-extern bool allow_online_pfn_range(int nid, unsigned long pfn, unsigned long nr_pages,
- int online_type);
extern struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn,
unsigned long nr_pages);
+#endif /* CONFIG_MEMORY_HOTPLUG */
+
#endif /* __LINUX_MEMORY_HOTPLUG_H */
diff --git a/include/linux/minmax.h b/include/linux/minmax.h
new file mode 100644
index 000000000000..c0f57b0c64d9
--- /dev/null
+++ b/include/linux/minmax.h
@@ -0,0 +1,153 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_MINMAX_H
+#define _LINUX_MINMAX_H
+
+/*
+ * min()/max()/clamp() macros must accomplish three things:
+ *
+ * - avoid multiple evaluations of the arguments (so side-effects like
+ * "x++" happen only once) when non-constant.
+ * - perform strict type-checking (to generate warnings instead of
+ * nasty runtime surprises). See the "unnecessary" pointer comparison
+ * in __typecheck().
+ * - retain result as a constant expressions when called with only
+ * constant expressions (to avoid tripping VLA warnings in stack
+ * allocation usage).
+ */
+#define __typecheck(x, y) \
+ (!!(sizeof((typeof(x) *)1 == (typeof(y) *)1)))
+
+/*
+ * This returns a constant expression while determining if an argument is
+ * a constant expression, most importantly without evaluating the argument.
+ * Glory to Martin Uecker <Martin.Uecker@med.uni-goettingen.de>
+ */
+#define __is_constexpr(x) \
+ (sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8)))
+
+#define __no_side_effects(x, y) \
+ (__is_constexpr(x) && __is_constexpr(y))
+
+#define __safe_cmp(x, y) \
+ (__typecheck(x, y) && __no_side_effects(x, y))
+
+#define __cmp(x, y, op) ((x) op (y) ? (x) : (y))
+
+#define __cmp_once(x, y, unique_x, unique_y, op) ({ \
+ typeof(x) unique_x = (x); \
+ typeof(y) unique_y = (y); \
+ __cmp(unique_x, unique_y, op); })
+
+#define __careful_cmp(x, y, op) \
+ __builtin_choose_expr(__safe_cmp(x, y), \
+ __cmp(x, y, op), \
+ __cmp_once(x, y, __UNIQUE_ID(__x), __UNIQUE_ID(__y), op))
+
+/**
+ * min - return minimum of two values of the same or compatible types
+ * @x: first value
+ * @y: second value
+ */
+#define min(x, y) __careful_cmp(x, y, <)
+
+/**
+ * max - return maximum of two values of the same or compatible types
+ * @x: first value
+ * @y: second value
+ */
+#define max(x, y) __careful_cmp(x, y, >)
+
+/**
+ * min3 - return minimum of three values
+ * @x: first value
+ * @y: second value
+ * @z: third value
+ */
+#define min3(x, y, z) min((typeof(x))min(x, y), z)
+
+/**
+ * max3 - return maximum of three values
+ * @x: first value
+ * @y: second value
+ * @z: third value
+ */
+#define max3(x, y, z) max((typeof(x))max(x, y), z)
+
+/**
+ * min_not_zero - return the minimum that is _not_ zero, unless both are zero
+ * @x: value1
+ * @y: value2
+ */
+#define min_not_zero(x, y) ({ \
+ typeof(x) __x = (x); \
+ typeof(y) __y = (y); \
+ __x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); })
+
+/**
+ * clamp - return a value clamped to a given range with strict typechecking
+ * @val: current value
+ * @lo: lowest allowable value
+ * @hi: highest allowable value
+ *
+ * This macro does strict typechecking of @lo/@hi to make sure they are of the
+ * same type as @val. See the unnecessary pointer comparisons.
+ */
+#define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi)
+
+/*
+ * ..and if you can't take the strict
+ * types, you can specify one yourself.
+ *
+ * Or not use min/max/clamp at all, of course.
+ */
+
+/**
+ * min_t - return minimum of two values, using the specified type
+ * @type: data type to use
+ * @x: first value
+ * @y: second value
+ */
+#define min_t(type, x, y) __careful_cmp((type)(x), (type)(y), <)
+
+/**
+ * max_t - return maximum of two values, using the specified type
+ * @type: data type to use
+ * @x: first value
+ * @y: second value
+ */
+#define max_t(type, x, y) __careful_cmp((type)(x), (type)(y), >)
+
+/**
+ * clamp_t - return a value clamped to a given range using a given type
+ * @type: the type of variable to use
+ * @val: current value
+ * @lo: minimum allowable value
+ * @hi: maximum allowable value
+ *
+ * This macro does no typechecking and uses temporary variables of type
+ * @type to make all the comparisons.
+ */
+#define clamp_t(type, val, lo, hi) min_t(type, max_t(type, val, lo), hi)
+
+/**
+ * clamp_val - return a value clamped to a given range using val's type
+ * @val: current value
+ * @lo: minimum allowable value
+ * @hi: maximum allowable value
+ *
+ * This macro does no typechecking and uses temporary variables of whatever
+ * type the input argument @val is. This is useful when @val is an unsigned
+ * type and @lo and @hi are literals that will otherwise be assigned a signed
+ * integer type.
+ */
+#define clamp_val(val, lo, hi) clamp_t(typeof(val), val, lo, hi)
+
+/**
+ * swap - swap values of @a and @b
+ * @a: first value
+ * @b: second value
+ */
+#define swap(a, b) \
+ do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
+
+#endif /* _LINUX_MINMAX_H */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 620961e4f32b..61a2633fcc7f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2440,7 +2440,7 @@ extern int __meminit __early_pfn_to_nid(unsigned long pfn,
extern void set_dma_reserve(unsigned long new_dma_reserve);
extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long,
- enum meminit_context, struct vmem_altmap *);
+ enum meminit_context, struct vmem_altmap *, int migratetype);
extern void setup_per_zone_wmarks(void);
extern int __meminit init_per_zone_wmark_min(void);
extern void mem_init(void);
@@ -3025,8 +3025,6 @@ extern int memory_failure(unsigned long pfn, int flags);
extern void memory_failure_queue(unsigned long pfn, int flags);
extern void memory_failure_queue_kick(int cpu);
extern int unpoison_memory(unsigned long pfn);
-extern int get_hwpoison_page(struct page *page);
-#define put_hwpoison_page(page) put_page(page)
extern int sysctl_memory_failure_early_kill;
extern int sysctl_memory_failure_recovery;
extern void shake_page(struct page *p, int access);
@@ -3066,6 +3064,7 @@ enum mf_action_page_type {
MF_MSG_BUDDY,
MF_MSG_BUDDY_2ND,
MF_MSG_DAX,
+ MF_MSG_UNSPLIT_THP,
MF_MSG_UNKNOWN,
};
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index c27fb1faffe5..fb3bf696c05e 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -266,6 +266,8 @@ static inline bool is_active_lru(enum lru_list lru)
return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE);
}
+#define ANON_AND_FILE 2
+
enum lruvec_flags {
LRUVEC_CONGESTED, /* lruvec has many dirty pages
* backed by a congested BDI
@@ -283,8 +285,8 @@ struct lruvec {
unsigned long file_cost;
/* Non-resident age, driven by LRU movement */
atomic_long_t nonresident_age;
- /* Refaults at the time of last reclaim cycle, anon=0, file=1 */
- unsigned long refaults[2];
+ /* Refaults at the time of last reclaim cycle */
+ unsigned long refaults[ANON_AND_FILE];
/* Various lruvec state flags (enum lruvec_flags) */
unsigned long flags;
#ifdef CONFIG_MEMCG
@@ -441,6 +443,8 @@ enum zone_type {
#ifndef __GENERATING_BOUNDS_H
+#define ASYNC_AND_SYNC 2
+
struct zone {
/* Read-mostly fields */
@@ -560,8 +564,8 @@ struct zone {
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
/* pfn where compaction free scanner should start */
unsigned long compact_cached_free_pfn;
- /* pfn where async and sync compaction migration scanner should start */
- unsigned long compact_cached_migrate_pfn[2];
+ /* pfn where compaction migration scanner should start */
+ unsigned long compact_cached_migrate_pfn[ASYNC_AND_SYNC];
unsigned long compact_init_migrate_pfn;
unsigned long compact_init_free_pfn;
#endif
@@ -1416,7 +1420,6 @@ static inline unsigned long next_present_section_nr(unsigned long section_nr)
#define pfn_to_nid(pfn) (0)
#endif
-#define early_pfn_valid(pfn) pfn_valid(pfn)
void sparse_init(void);
#else
#define sparse_init() do {} while (0)
@@ -1436,10 +1439,6 @@ struct mminit_pfnnid_cache {
int last_nid;
};
-#ifndef early_pfn_valid
-#define early_pfn_valid(pfn) (1)
-#endif
-
/*
* If it is possible to have holes within a MAX_ORDER_NR_PAGES, then we
* need to check pfn validity within that MAX_ORDER_NR_PAGES block.
diff --git a/include/linux/node.h b/include/linux/node.h
index 014ba3ab2efd..8e5a29897936 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -99,15 +99,14 @@ extern struct node *node_devices[];
typedef void (*node_registration_func_t)(struct node *);
#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA)
-int link_mem_sections(int nid, unsigned long start_pfn,
- unsigned long end_pfn,
- enum meminit_context context);
+void link_mem_sections(int nid, unsigned long start_pfn,
+ unsigned long end_pfn,
+ enum meminit_context context);
#else
-static inline int link_mem_sections(int nid, unsigned long start_pfn,
- unsigned long end_pfn,
- enum meminit_context context)
+static inline void link_mem_sections(int nid, unsigned long start_pfn,
+ unsigned long end_pfn,
+ enum meminit_context context)
{
- return 0;
}
#endif
@@ -130,8 +129,7 @@ static inline int register_one_node(int nid)
if (error)
return error;
/* link memory sections under this node */
- error = link_mem_sections(nid, start_pfn, end_pfn,
- MEMINIT_EARLY);
+ link_mem_sections(nid, start_pfn, end_pfn, MEMINIT_EARLY);
}
return error;
diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index 3334ce056335..ac398e143c9a 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -90,9 +90,9 @@
* for such situations. See below and CPUMASK_ALLOC also.
*/
-#include <linux/kernel.h>
#include <linux/threads.h>
#include <linux/bitmap.h>
+#include <linux/minmax.h>
#include <linux/numa.h>
typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t;
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 38ded408bd4c..4f6ba9379112 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -431,13 +431,9 @@ PAGEFLAG_FALSE(Uncached)
PAGEFLAG(HWPoison, hwpoison, PF_ANY)
TESTSCFLAG(HWPoison, hwpoison, PF_ANY)
#define __PG_HWPOISON (1UL << PG_hwpoison)
-extern bool set_hwpoison_free_buddy_page(struct page *page);
+extern bool take_page_off_buddy(struct page *page);
#else
PAGEFLAG_FALSE(HWPoison)
-static inline bool set_hwpoison_free_buddy_page(struct page *page)
-{
- return 0;
-}
#define __PG_HWPOISON 0
#endif
diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h
index 8679ccd722e8..3468794f83d2 100644
--- a/include/linux/page_owner.h
+++ b/include/linux/page_owner.h
@@ -11,7 +11,7 @@ extern struct page_ext_operations page_owner_ops;
extern void __reset_page_owner(struct page *page, unsigned int order);
extern void __set_page_owner(struct page *page,
unsigned int order, gfp_t gfp_mask);
-extern void __split_page_owner(struct page *page, unsigned int order);
+extern void __split_page_owner(struct page *page, unsigned int nr);
extern void __copy_page_owner(struct page *oldpage, struct page *newpage);
extern void __set_page_owner_migrate_reason(struct page *page, int reason);
extern void __dump_page_owner(struct page *page);
@@ -31,10 +31,10 @@ static inline void set_page_owner(struct page *page,
__set_page_owner(page, order, gfp_mask);
}
-static inline void split_page_owner(struct page *page, unsigned int order)
+static inline void split_page_owner(struct page *page, unsigned int nr)
{
if (static_branch_unlikely(&page_owner_inited))
- __split_page_owner(page, order);
+ __split_page_owner(page, nr);
}
static inline void copy_page_owner(struct page *oldpage, struct page *newpage)
{
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index c3afd3242b54..c77b7c31b2e4 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -29,6 +29,7 @@ enum mapping_flags {
AS_EXITING = 4, /* final truncate in progress */
/* writeback related tags are not used */
AS_NO_WRITEBACK_TAGS = 5,
+ AS_THP_SUPPORT = 6, /* THPs supported */
};
/**
@@ -120,6 +121,40 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask)
m->gfp_mask = mask;
}
+static inline bool mapping_thp_support(struct address_space *mapping)
+{
+ return test_bit(AS_THP_SUPPORT, &mapping->flags);
+}
+
+static inline int filemap_nr_thps(struct address_space *mapping)
+{
+#ifdef CONFIG_READ_ONLY_THP_FOR_FS
+ return atomic_read(&mapping->nr_thps);
+#else
+ return 0;
+#endif
+}
+
+static inline void filemap_nr_thps_inc(struct address_space *mapping)
+{
+#ifdef CONFIG_READ_ONLY_THP_FOR_FS
+ if (!mapping_thp_support(mapping))
+ atomic_inc(&mapping->nr_thps);
+#else
+ WARN_ON_ONCE(1);
+#endif
+}
+
+static inline void filemap_nr_thps_dec(struct address_space *mapping)
+{
+#ifdef CONFIG_READ_ONLY_THP_FOR_FS
+ if (!mapping_thp_support(mapping))
+ atomic_dec(&mapping->nr_thps);
+#else
+ WARN_ON_ONCE(1);
+#endif
+}
+
void release_pages(struct page **pages, int nr);
/*
@@ -726,17 +761,6 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask);
void delete_from_page_cache_batch(struct address_space *mapping,
struct pagevec *pvec);
-#define VM_READAHEAD_PAGES (SZ_128K / PAGE_SIZE)
-
-void page_cache_sync_readahead(struct address_space *, struct file_ra_state *,
- struct file *, pgoff_t index, unsigned long req_count);
-void page_cache_async_readahead(struct address_space *, struct file_ra_state *,
- struct file *, struct page *, pgoff_t index,
- unsigned long req_count);
-void page_cache_readahead_unbounded(struct address_space *, struct file *,
- pgoff_t index, unsigned long nr_to_read,
- unsigned long lookahead_count);
-
/*
* Like add_to_page_cache_locked, but used to add newly allocated pages:
* the page is new, so we can just run __SetPageLocked() against it.
@@ -777,6 +801,67 @@ struct readahead_control {
unsigned int _batch_count;
};
+#define DEFINE_READAHEAD(rac, f, m, i) \
+ struct readahead_control rac = { \
+ .file = f, \
+ .mapping = m, \
+ ._index = i, \
+ }
+
+#define VM_READAHEAD_PAGES (SZ_128K / PAGE_SIZE)
+
+void page_cache_ra_unbounded(struct readahead_control *,
+ unsigned long nr_to_read, unsigned long lookahead_count);
+void page_cache_sync_ra(struct readahead_control *, struct file_ra_state *,
+ unsigned long req_count);
+void page_cache_async_ra(struct readahead_control *, struct file_ra_state *,
+ struct page *, unsigned long req_count);
+
+/**
+ * page_cache_sync_readahead - generic file readahead
+ * @mapping: address_space which holds the pagecache and I/O vectors
+ * @ra: file_ra_state which holds the readahead state
+ * @file: Used by the filesystem for authentication.
+ * @index: Index of first page to be read.
+ * @req_count: Total number of pages being read by the caller.
+ *
+ * page_cache_sync_readahead() should be called when a cache miss happened:
+ * it will submit the read. The readahead logic may decide to piggyback more
+ * pages onto the read request if access patterns suggest it will improve
+ * performance.
+ */
+static inline
+void page_cache_sync_readahead(struct address_space *mapping,
+ struct file_ra_state *ra, struct file *file, pgoff_t index,
+ unsigned long req_count)
+{
+ DEFINE_READAHEAD(ractl, file, mapping, index);
+ page_cache_sync_ra(&ractl, ra, req_count);
+}
+
+/**
+ * page_cache_async_readahead - file readahead for marked pages
+ * @mapping: address_space which holds the pagecache and I/O vectors
+ * @ra: file_ra_state which holds the readahead state
+ * @file: Used by the filesystem for authentication.
+ * @page: The page at @index which triggered the readahead call.
+ * @index: Index of first page to be read.
+ * @req_count: Total number of pages being read by the caller.
+ *
+ * page_cache_async_readahead() should be called when a page is used which
+ * is marked as PageReadahead; this is a marker to suggest that the application
+ * has used up enough of the readahead window that we should start pulling in
+ * more pages.
+ */
+static inline
+void page_cache_async_readahead(struct address_space *mapping,
+ struct file_ra_state *ra, struct file *file,
+ struct page *page, pgoff_t index, unsigned long req_count)
+{
+ DEFINE_READAHEAD(ractl, file, mapping, index);
+ page_cache_async_ra(&ractl, ra, page, req_count);
+}
+
/**
* readahead_page - Get the next page to read.
* @rac: The current readahead request.
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9030f3abd969..063cd120b459 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1013,7 +1013,7 @@ struct task_struct {
struct held_lock held_locks[MAX_LOCK_DEPTH];
#endif
-#ifdef CONFIG_UBSAN
+#if defined(CONFIG_UBSAN) && !defined(CONFIG_UBSAN_TRAP)
unsigned int in_ubsan;
#endif
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 15bfb06f2884..981e34cb1409 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -49,31 +49,6 @@ static inline void mmdrop(struct mm_struct *mm)
__mmdrop(mm);
}
-/*
- * This has to be called after a get_task_mm()/mmget_not_zero()
- * followed by taking the mmap_lock for writing before modifying the
- * vmas or anything the coredump pretends not to change from under it.
- *
- * It also has to be called when mmgrab() is used in the context of
- * the process, but then the mm_count refcount is transferred outside
- * the context of the process to run down_write() on that pinned mm.
- *
- * NOTE: find_extend_vma() called from GUP context is the only place
- * that can modify the "mm" (notably the vm_start/end) under mmap_lock
- * for reading and outside the context of the process, so it is also
- * the only case that holds the mmap_lock for reading that must call
- * this function. Generally if the mmap_lock is hold for reading
- * there's no need of this check after get_task_mm()/mmget_not_zero().
- *
- * This function can be obsoleted and the check can be removed, after
- * the coredump code will hold the mmap_lock for writing before
- * invoking the ->core_dump methods.
- */
-static inline bool mmget_still_valid(struct mm_struct *mm)
-{
- return likely(!mm->core_state);
-}
-
/**
* mmget() - Pin the address space associated with a &struct mm_struct.
* @mm: The address space to pin.
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 1ae36bc8db35..1b8c9d6162bc 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -2,7 +2,9 @@
#ifndef __LINUX_UACCESS_H__
#define __LINUX_UACCESS_H__
+#include <linux/fault-inject-usercopy.h>
#include <linux/instrumented.h>
+#include <linux/minmax.h>
#include <linux/sched.h>
#include <linux/thread_info.h>
@@ -83,6 +85,8 @@ static __always_inline __must_check unsigned long
__copy_from_user(void *to, const void __user *from, unsigned long n)
{
might_fault();
+ if (should_fail_usercopy())
+ return n;
instrument_copy_from_user(to, from, n);
check_object_size(to, n, false);
return raw_copy_from_user(to, from, n);
@@ -104,6 +108,8 @@ __copy_from_user(void *to, const void __user *from, unsigned long n)
static __always_inline __must_check unsigned long
__copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
{
+ if (should_fail_usercopy())
+ return n;
instrument_copy_to_user(to, from, n);
check_object_size(from, n, true);
return raw_copy_to_user(to, from, n);
@@ -113,6 +119,8 @@ static __always_inline __must_check unsigned long
__copy_to_user(void __user *to, const void *from, unsigned long n)
{
might_fault();
+ if (should_fail_usercopy())
+ return n;
instrument_copy_to_user(to, from, n);
check_object_size(from, n, true);
return raw_copy_to_user(to, from, n);
@@ -124,7 +132,7 @@ _copy_from_user(void *to, const void __user *from, unsigned long n)
{
unsigned long res = n;
might_fault();
- if (likely(access_ok(from, n))) {
+ if (!should_fail_usercopy() && likely(access_ok(from, n))) {
instrument_copy_from_user(to, from, n);
res = raw_copy_from_user(to, from, n);
}
@@ -142,6 +150,8 @@ static inline __must_check unsigned long
_copy_to_user(void __user *to, const void *from, unsigned long n)
{
might_fault();
+ if (should_fail_usercopy())
+ return n;
if (access_ok(to, n)) {
instrument_copy_to_user(to, from, n);
n = raw_copy_to_user(to, from, n);
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 7557c1070fd7..322dcbfcc933 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -28,7 +28,7 @@ struct reclaim_stat {
unsigned nr_writeback;
unsigned nr_immediate;
unsigned nr_pageout;
- unsigned nr_activate[2];
+ unsigned nr_activate[ANON_AND_FILE];
unsigned nr_ref_keep;
unsigned nr_unmap_fail;
unsigned nr_lazyfree_fail;
diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index b4d70e7568b2..5cdf441f6377 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -1505,6 +1505,28 @@ void xas_pause(struct xa_state *);
void xas_create_range(struct xa_state *);
+#ifdef CONFIG_XARRAY_MULTI
+int xa_get_order(struct xarray *, unsigned long index);
+void xas_split(struct xa_state *, void *entry, unsigned int order);
+void xas_split_alloc(struct xa_state *, void *entry, unsigned int order, gfp_t);
+#else
+static inline int xa_get_order(struct xarray *xa, unsigned long index)
+{
+ return 0;
+}
+
+static inline void xas_split(struct xa_state *xas, void *entry,
+ unsigned int order)
+{
+ xas_store(xas, entry);
+}
+
+static inline void xas_split_alloc(struct xa_state *xas, void *entry,
+ unsigned int order, gfp_t gfp)
+{
+}
+#endif
+
/**
* xas_reload() - Refetch an entry from the xarray.
* @xas: XArray operation state.
diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
index 36c5c5e38c1d..0bdbc0d17d2f 100644
--- a/include/ras/ras_event.h
+++ b/include/ras/ras_event.h
@@ -361,6 +361,7 @@ TRACE_EVENT(aer_event,
EM ( MF_MSG_POISONED_HUGE, "huge page already hardware poisoned" ) \
EM ( MF_MSG_HUGE, "huge page" ) \
EM ( MF_MSG_FREE_HUGE, "free huge page" ) \
+ EM ( MF_MSG_NON_PMD_HUGE, "non-pmd-sized huge page" ) \
EM ( MF_MSG_UNMAP_FAILED, "unmapping failed page" ) \
EM ( MF_MSG_DIRTY_SWAPCACHE, "dirty swapcache page" ) \
EM ( MF_MSG_CLEAN_SWAPCACHE, "clean swapcache page" ) \
@@ -373,6 +374,8 @@ TRACE_EVENT(aer_event,
EM ( MF_MSG_TRUNCATED_LRU, "already truncated LRU page" ) \
EM ( MF_MSG_BUDDY, "free buddy page" ) \
EM ( MF_MSG_BUDDY_2ND, "free buddy page (2nd try)" ) \
+ EM ( MF_MSG_DAX, "dax page" ) \
+ EM ( MF_MSG_UNSPLIT_THP, "unsplit thp" ) \
EMe ( MF_MSG_UNKNOWN, "unknown page" )
/*