17 files changed, 169 insertions, 85 deletions

diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 2043af2141c1..01448e01b40d 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -616,5 +616,11 @@ static inline struct inode *d_real_inode(struct dentry *dentry)
 	return d_backing_inode(d_real(dentry));
 }
 
+struct name_snapshot {
+	const char *name;
+	char inline_name[DNAME_INLINE_LEN];
+};
+void take_dentry_name_snapshot(struct name_snapshot *, struct dentry *);
+void release_dentry_name_snapshot(struct name_snapshot *);
 
 #endif	/* __LINUX_DCACHE_H */
diff --git a/include/linux/device.h b/include/linux/device.h
index b8f411b57dcb..7075a2485ed3 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -368,6 +368,7 @@ int subsys_virtual_register(struct bus_type *subsys,
  * @suspend:	Used to put the device to sleep mode, usually to a low power
  *		state.
  * @resume:	Used to bring the device from the sleep mode.
+ * @shutdown:	Called at shut-down time to quiesce the device.
  * @ns_type:	Callbacks so sysfs can detemine namespaces.
  * @namespace:	Namespace of the device belongs to this class.
  * @pm:		The default device power management operations of this class.
@@ -396,6 +397,7 @@ struct class {
 
 	int (*suspend)(struct device *dev, pm_message_t state);
 	int (*resume)(struct device *dev);
+	int (*shutdown)(struct device *dev);
 
 	const struct kobj_ns_type_operations *ns_type;
 	const void *(*namespace)(struct device *dev);
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 7ee1774edee5..a7789559078b 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -310,35 +310,4 @@ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid)
 	}
 }
 
-#if defined(CONFIG_FSNOTIFY)	/* notify helpers */
-
-/*
- * fsnotify_oldname_init - save off the old filename before we change it
- */
-static inline const unsigned char *fsnotify_oldname_init(const unsigned char *name)
-{
-	return kstrdup(name, GFP_KERNEL);
-}
-
-/*
- * fsnotify_oldname_free - free the name we got from fsnotify_oldname_init
- */
-static inline void fsnotify_oldname_free(const unsigned char *old_name)
-{
-	kfree(old_name);
-}
-
-#else	/* CONFIG_FSNOTIFY */
-
-static inline const char *fsnotify_oldname_init(const unsigned char *name)
-{
-	return NULL;
-}
-
-static inline void fsnotify_oldname_free(const unsigned char *old_name)
-{
-}
-
-#endif	/*  CONFIG_FSNOTIFY */
-
 #endif	/* _LINUX_FS_NOTIFY_H */
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 1c1ff7e4faa4..021b1e9ff6cd 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -15,6 +15,8 @@
 #include <net/net_namespace.h>
 #include <linux/sched/rt.h>
 
+#include <asm/thread_info.h>
+
 #ifdef CONFIG_SMP
 # define INIT_PUSHABLE_TASKS(tsk)					\
 	.pushable_tasks = PLIST_NODE_INIT(tsk.pushable_tasks, MAX_PRIO),
@@ -183,14 +185,21 @@ extern struct task_group root_task_group;
 # define INIT_KASAN(tsk)
 #endif
 
+#ifdef CONFIG_THREAD_INFO_IN_TASK
+# define INIT_TASK_TI(tsk) .thread_info = INIT_THREAD_INFO(tsk),
+#else
+# define INIT_TASK_TI(tsk)
+#endif
+
 /*
  *  INIT_TASK is used to set up the first task table, touch at
  * your own risk!. Base=0, limit=0x1fffff (=2MB)
  */
 #define INIT_TASK(tsk)	\
 {									\
+	INIT_TASK_TI(tsk)						\
 	.state		= 0,						\
-	.stack		= &init_thread_info,				\
+	.stack		= init_stack,					\
 	.usage		= ATOMIC_INIT(2),				\
 	.flags		= PF_KTHREAD,					\
 	.prio		= MAX_PRIO-20,					\
diff --git a/include/linux/kdb.h b/include/linux/kdb.h
index a19bcf9e762e..410decacff8f 100644
--- a/include/linux/kdb.h
+++ b/include/linux/kdb.h
@@ -177,7 +177,7 @@ extern int kdb_get_kbd_char(void);
 static inline
 int kdb_process_cpu(const struct task_struct *p)
 {
-	unsigned int cpu = task_thread_info(p)->cpu;
+	unsigned int cpu = task_cpu(p);
 	if (cpu > num_possible_cpus())
 		cpu = 0;
 	return cpu;
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index 2a6b9947aaa3..743b34f56f2b 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -44,6 +44,7 @@ struct list_lru_node {
 	/* for cgroup aware lrus points to per cgroup lists, otherwise NULL */
 	struct list_lru_memcg	*memcg_lrus;
 #endif
+	long nr_items;
 } ____cacheline_aligned_in_smp;
 
 struct list_lru {
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index af25bc12472b..b32cb7add09c 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -511,6 +511,10 @@ struct mm_struct {
 	 */
 	bool tlb_flush_pending;
 #endif
+#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
+	/* See flush_tlb_batched_pending() */
+	bool tlb_flush_batched;
+#endif
 	struct uprobes_state uprobes_state;
 #ifdef CONFIG_X86_INTEL_MPX
 	/* address of the bounds directory */
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 05fde31b6dc6..b64825d6ad26 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -785,6 +785,10 @@ int genphy_read_status(struct phy_device *phydev);
 int genphy_suspend(struct phy_device *phydev);
 int genphy_resume(struct phy_device *phydev);
 int genphy_soft_reset(struct phy_device *phydev);
+static inline int genphy_no_soft_reset(struct phy_device *phydev)
+{
+	return 0;
+}
 void phy_driver_unregister(struct phy_driver *drv);
 void phy_drivers_unregister(struct phy_driver *drv, int n);
 int phy_driver_register(struct phy_driver *new_driver);
diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h
index 45ac5a0d29ee..7097a45dbc25 100644
--- a/include/linux/pstore_ram.h
+++ b/include/linux/pstore_ram.h
@@ -24,6 +24,13 @@
 #include <linux/list.h>
 #include <linux/types.h>
 
+/*
+ * Choose whether access to the RAM zone requires locking or not.  If a zone
+ * can be written to from different CPUs like with ftrace for example, then
+ * PRZ_FLAG_NO_LOCK is used. For all other cases, locking is required.
+ */
+#define PRZ_FLAG_NO_LOCK	BIT(0)
+
 struct persistent_ram_buffer;
 struct rs_control;
 
@@ -40,6 +47,8 @@ struct persistent_ram_zone {
 	void *vaddr;
 	struct persistent_ram_buffer *buffer;
 	size_t buffer_size;
+	u32 flags;
+	raw_spinlock_t buffer_lock;
 
 	/* ECC correction */
 	char *par_buffer;
@@ -55,7 +64,7 @@ struct persistent_ram_zone {
 
 struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size,
 			u32 sig, struct persistent_ram_ecc_info *ecc_info,
-			unsigned int memtype);
+			unsigned int memtype, u32 flags);
 void persistent_ram_free(struct persistent_ram_zone *prz);
 void persistent_ram_zap(struct persistent_ram_zone *prz);
 
diff --git a/include/linux/restart_block.h b/include/linux/restart_block.h
new file mode 100644
index 000000000000..0d905d8ec553
--- /dev/null
+++ b/include/linux/restart_block.h
@@ -0,0 +1,51 @@
+/*
+ * Common syscall restarting data
+ */
+#ifndef __LINUX_RESTART_BLOCK_H
+#define __LINUX_RESTART_BLOCK_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+struct timespec;
+struct compat_timespec;
+struct pollfd;
+
+/*
+ * System call restart block.
+ */
+struct restart_block {
+	long (*fn)(struct restart_block *);
+	union {
+		/* For futex_wait and futex_wait_requeue_pi */
+		struct {
+			u32 __user *uaddr;
+			u32 val;
+			u32 flags;
+			u32 bitset;
+			u64 time;
+			u32 __user *uaddr2;
+		} futex;
+		/* For nanosleep */
+		struct {
+			clockid_t clockid;
+			struct timespec __user *rmtp;
+#ifdef CONFIG_COMPAT
+			struct compat_timespec __user *compat_rmtp;
+#endif
+			u64 expires;
+		} nanosleep;
+		/* For poll */
+		struct {
+			struct pollfd __user *ufds;
+			int nfds;
+			int has_timeout;
+			unsigned long tv_sec;
+			unsigned long tv_nsec;
+		} poll;
+	};
+};
+
+extern long do_no_restart_syscall(struct restart_block *parm);
+
+#endif /* __LINUX_RESTART_BLOCK_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ad2c304b29b8..436c308bb1d5 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -813,6 +813,16 @@ struct signal_struct {
 
 #define SIGNAL_UNKILLABLE	0x00000040 /* for init: ignore fatal signals */
 
+#define SIGNAL_STOP_MASK (SIGNAL_CLD_MASK | SIGNAL_STOP_STOPPED | \
+			  SIGNAL_STOP_CONTINUED)
+
+static inline void signal_set_stop_flags(struct signal_struct *sig,
+					 unsigned int flags)
+{
+	WARN_ON(sig->flags & (SIGNAL_GROUP_EXIT|SIGNAL_GROUP_COREDUMP));
+	sig->flags = (sig->flags & ~SIGNAL_STOP_MASK) | flags;
+}
+
 /* If true, all threads except ->group_exit_task have pending SIGKILL */
 static inline int signal_group_exit(const struct signal_struct *sig)
 {
@@ -1518,6 +1528,13 @@ struct tlbflush_unmap_batch {
 };
 
 struct task_struct {
+#ifdef CONFIG_THREAD_INFO_IN_TASK
+	/*
+	 * For reasons of header soup (see current_thread_info()), this
+	 * must be the first element of task_struct.
+	 */
+	struct thread_info thread_info;
+#endif
 	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
 	void *stack;
 	atomic_t usage;
@@ -1527,6 +1544,9 @@ struct task_struct {
 #ifdef CONFIG_SMP
 	struct llist_node wake_entry;
 	int on_cpu;
+#ifdef CONFIG_THREAD_INFO_IN_TASK
+	unsigned int cpu;	/* current CPU */
+#endif
 	unsigned int wakee_flips;
 	unsigned long wakee_flip_decay_ts;
 	struct task_struct *last_wakee;
@@ -2556,7 +2576,9 @@ extern void set_curr_task(int cpu, struct task_struct *p);
 void yield(void);
 
 union thread_union {
+#ifndef CONFIG_THREAD_INFO_IN_TASK
 	struct thread_info thread_info;
+#endif
 	unsigned long stack[THREAD_SIZE/sizeof(long)];
 };
 
@@ -2946,10 +2968,34 @@ static inline void threadgroup_change_end(struct task_struct *tsk)
 	cgroup_threadgroup_change_end(tsk);
 }
 
-#ifndef __HAVE_THREAD_FUNCTIONS
+#ifdef CONFIG_THREAD_INFO_IN_TASK
+
+static inline struct thread_info *task_thread_info(struct task_struct *task)
+{
+	return &task->thread_info;
+}
+
+/*
+ * When accessing the stack of a non-current task that might exit, use
+ * try_get_task_stack() instead.  task_stack_page will return a pointer
+ * that could get freed out from under you.
+ */
+static inline void *task_stack_page(const struct task_struct *task)
+{
+	return task->stack;
+}
+
+#define setup_thread_stack(new,old)	do { } while(0)
+
+static inline unsigned long *end_of_stack(const struct task_struct *task)
+{
+	return task->stack;
+}
+
+#elif !defined(__HAVE_THREAD_FUNCTIONS)
 
 #define task_thread_info(task)	((struct thread_info *)(task)->stack)
-#define task_stack_page(task)	((task)->stack)
+#define task_stack_page(task)	((void *)(task)->stack)
 
 static inline void setup_thread_stack(struct task_struct *p, struct task_struct *org)
 {
@@ -2976,6 +3022,14 @@ static inline unsigned long *end_of_stack(struct task_struct *p)
 }
 
 #endif
+
+static inline void *try_get_task_stack(struct task_struct *tsk)
+{
+	return task_stack_page(tsk);
+}
+
+static inline void put_task_stack(struct task_struct *tsk) {}
+
 #define task_stack_end_corrupted(task) \
 		(*(end_of_stack(task)) != STACK_END_MAGIC)
 
@@ -2986,7 +3040,7 @@ static inline int object_is_on_stack(void *obj)
 	return (obj >= stack) && (obj < (stack + THREAD_SIZE));
 }
 
-extern void thread_info_cache_init(void);
+extern void thread_stack_cache_init(void);
 
 #ifdef CONFIG_DEBUG_STACK_USAGE
 static inline unsigned long stack_not_used(struct task_struct *p)
@@ -3241,7 +3295,11 @@ static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume)
 
 static inline unsigned int task_cpu(const struct task_struct *p)
 {
+#ifdef CONFIG_THREAD_INFO_IN_TASK
+	return p->cpu;
+#else
 	return task_thread_info(p)->cpu;
+#endif
 }
 
 static inline int task_node(const struct task_struct *p)
diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h
index dde00defbaa5..f3d45dd42695 100644
--- a/include/linux/seq_file.h
+++ b/include/linux/seq_file.h
@@ -7,13 +7,10 @@
 #include <linux/mutex.h>
 #include <linux/cpumask.h>
 #include <linux/nodemask.h>
+#include <linux/fs.h>
+#include <linux/cred.h>
 
 struct seq_operations;
-struct file;
-struct path;
-struct inode;
-struct dentry;
-struct user_namespace;
 
 struct seq_file {
 	char *buf;
@@ -27,9 +24,7 @@ struct seq_file {
 	struct mutex lock;
 	const struct seq_operations *op;
 	int poll_event;
-#ifdef CONFIG_USER_NS
-	struct user_namespace *user_ns;
-#endif
+	const struct file *file;
 	void *private;
 };
 
@@ -147,7 +142,7 @@ int seq_release_private(struct inode *, struct file *);
 static inline struct user_namespace *seq_user_ns(struct seq_file *seq)
 {
 #ifdef CONFIG_USER_NS
-	return seq->user_ns;
+	return seq->file->f_cred->user_ns;
 #else
 	extern struct user_namespace init_user_ns;
 	return &init_user_ns;
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 4ef384b172e0..b4e739f04ee6 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -215,7 +215,7 @@ static inline const char *__check_heap_object(const void *ptr,
  * (PAGE_SIZE*2).  Larger requests are passed to the page allocator.
  */
 #define KMALLOC_SHIFT_HIGH	(PAGE_SHIFT + 1)
-#define KMALLOC_SHIFT_MAX	(MAX_ORDER + PAGE_SHIFT)
+#define KMALLOC_SHIFT_MAX	(MAX_ORDER + PAGE_SHIFT - 1)
 #ifndef KMALLOC_SHIFT_LOW
 #define KMALLOC_SHIFT_LOW	3
 #endif
@@ -228,7 +228,7 @@ static inline const char *__check_heap_object(const void *ptr,
  * be allocated from the same page.
  */
 #define KMALLOC_SHIFT_HIGH	PAGE_SHIFT
-#define KMALLOC_SHIFT_MAX	30
+#define KMALLOC_SHIFT_MAX	(MAX_ORDER + PAGE_SHIFT - 1)
 #ifndef KMALLOC_SHIFT_LOW
 #define KMALLOC_SHIFT_LOW	3
 #endif
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index 4cf89517783a..8933ecc2bc9f 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -9,46 +9,17 @@
 
 #include <linux/types.h>
 #include <linux/bug.h>
+#include <linux/restart_block.h>
 
-struct timespec;
-struct compat_timespec;
-
+#ifdef CONFIG_THREAD_INFO_IN_TASK
 /*
- * System call restart block.
+ * For CONFIG_THREAD_INFO_IN_TASK kernels we need <asm/current.h> for the
+ * definition of current, but for !CONFIG_THREAD_INFO_IN_TASK kernels,
+ * including <asm/current.h> can cause a circular dependency on some platforms.
  */
-struct restart_block {
-	long (*fn)(struct restart_block *);
-	union {
-		/* For futex_wait and futex_wait_requeue_pi */
-		struct {
-			u32 __user *uaddr;
-			u32 val;
-			u32 flags;
-			u32 bitset;
-			u64 time;
-			u32 __user *uaddr2;
-		} futex;
-		/* For nanosleep */
-		struct {
-			clockid_t clockid;
-			struct timespec __user *rmtp;
-#ifdef CONFIG_COMPAT
-			struct compat_timespec __user *compat_rmtp;
+#include <asm/current.h>
+#define current_thread_info() ((struct thread_info *)current)
 #endif
-			u64 expires;
-		} nanosleep;
-		/* For poll */
-		struct {
-			struct pollfd __user *ufds;
-			int nfds;
-			int has_timeout;
-			unsigned long tv_sec;
-			unsigned long tv_nsec;
-		} poll;
-	};
-};
-
-extern long do_no_restart_syscall(struct restart_block *parm);
 
 #include <linux/bitops.h>
 #include <asm/thread_info.h>
diff --git a/include/linux/tick.h b/include/linux/tick.h
index e312219ff823..af5ac7f91a3b 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -103,6 +103,7 @@ extern void tick_nohz_idle_enter(void);
 extern void tick_nohz_idle_exit(void);
 extern void tick_nohz_irq_exit(void);
 extern ktime_t tick_nohz_get_sleep_length(void);
+extern unsigned long tick_nohz_get_idle_calls(void);
 extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
 extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time);
 #else /* !CONFIG_NO_HZ_COMMON */
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index ddb440975382..34851bf2e2c8 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -85,6 +85,8 @@ extern void vfio_unregister_iommu_driver(
  */
 extern struct vfio_group *vfio_group_get_external_user(struct file *filep);
 extern void vfio_group_put_external_user(struct vfio_group *group);
+extern bool vfio_external_group_match_file(struct vfio_group *group,
+					   struct file *filep);
 extern int vfio_external_user_iommu_id(struct vfio_group *group);
 extern long vfio_external_check_extension(struct vfio_group *group,
 					  unsigned long arg);
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 0197358f1e81..262d5c95dfc8 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -311,6 +311,7 @@ enum {
 
 	__WQ_DRAINING		= 1 << 16, /* internal: workqueue is draining */
 	__WQ_ORDERED		= 1 << 17, /* internal: workqueue is ordered */
+	__WQ_ORDERED_EXPLICIT	= 1 << 18, /* internal: alloc_ordered_workqueue() */
 
 	WQ_MAX_ACTIVE		= 512,	  /* I like 512, better ideas? */
 	WQ_MAX_UNBOUND_PER_CPU	= 4,	  /* 4 * #cpus for unbound wq */
@@ -408,7 +409,8 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active,
  * Pointer to the allocated workqueue on success, %NULL on failure.
  */
 #define alloc_ordered_workqueue(fmt, flags, args...)			\
-	alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args)
+	alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED |		\
+			__WQ_ORDERED_EXPLICIT | (flags), 1, ##args)
 
 #define create_workqueue(name)						\
 	alloc_workqueue("%s", WQ_MEM_RECLAIM, 1, (name))