Merge branch 'locking/urgent' into locking/core, before applying larger changes and to refresh the branch with fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

21 files changed, 126 insertions, 42 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index 5a645769f020..d2633ee099d9 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -186,6 +186,15 @@ static inline void *bio_data(struct bio *bio)
 #define BIOVEC_SEG_BOUNDARY(q, b1, b2) \
         __BIO_SEG_BOUNDARY(bvec_to_phys((b1)), bvec_to_phys((b2)) + (b2)->bv_len, queue_segment_boundary((q)))
 
+/*
+ * Check if adding a bio_vec after bprv with offset would create a gap in
+ * the SG list. Most drivers don't care about this, but some do.
+ */
+static inline bool bvec_gap_to_prev(struct bio_vec *bprv, unsigned int offset)
+{
+        return offset || ((bprv->bv_offset + bprv->bv_len) & (PAGE_SIZE - 1));
+}
+
 #define bio_io_error(bio) bio_endio((bio), -EIO)
 
 /*
@@ -644,10 +653,6 @@ struct biovec_slab {
 
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 
-
-
-#define bip_vec_idx(bip, idx)   (&(bip->bip_vec[(idx)]))
-
 #define bip_for_each_vec(bvl, bip, iter)                                \
         for_each_bvec(bvl, (bip)->bip_vec, iter, (bip)->bip_iter)
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index a002cf191427..eb726b9c5762 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -42,7 +42,7 @@ struct blk_mq_hw_ctx {
         unsigned int            nr_ctx;
         struct blk_mq_ctx       **ctxs;
 
-        unsigned int            wait_index;
+        atomic_t                wait_index;
 
         struct blk_mq_tags      *tags;
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 31e11051f1ba..8699bcf5f099 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -512,6 +512,7 @@ struct request_queue {
 #define QUEUE_FLAG_DEAD        19       /* queue tear-down finished */
 #define QUEUE_FLAG_INIT_DONE   20       /* queue is initialized */
 #define QUEUE_FLAG_NO_SG_MERGE 21       /* don't attempt to merge SG segments*/
+#define QUEUE_FLAG_SG_GAPS     22       /* queue doesn't support SG gaps */
 
 #define QUEUE_FLAG_DEFAULT      ((1 << QUEUE_FLAG_IO_STAT) |            \
                                  (1 << QUEUE_FLAG_STACKABLE)    |       \
@@ -920,7 +921,7 @@ static inline unsigned int blk_max_size_offset(struct request_queue *q,
                                                sector_t offset)
 {
         if (!q->limits.chunk_sectors)
-                return q->limits.max_hw_sectors;
+                return q->limits.max_sectors;
 
         return q->limits.chunk_sectors -
                         (offset & (q->limits.chunk_sectors - 1));
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 4ff262e2bf37..45a91474487d 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -133,7 +133,6 @@ extern struct request *elv_latter_request(struct request_queue *, struct request
 extern int elv_register_queue(struct request_queue *q);
 extern void elv_unregister_queue(struct request_queue *q);
 extern int elv_may_queue(struct request_queue *, int);
-extern void elv_abort_queue(struct request_queue *);
 extern void elv_completed_request(struct request_queue *, struct request *);
 extern int elv_set_request(struct request_queue *q, struct request *rq,
                            struct bio *bio, gfp_t gfp_mask);
@@ -144,7 +143,7 @@ extern void elv_drain_elevator(struct request_queue *);
  * io scheduler registration
  */
 extern void __init load_default_elevator_module(void);
-extern int __init elv_register(struct elevator_type *);
+extern int elv_register(struct elevator_type *);
 extern void elv_unregister(struct elevator_type *);
 
 /*
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 338e6f758c6d..e11d60cc867b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1921,6 +1921,12 @@ static inline int break_lease(struct inode *inode, unsigned int mode)
 
 static inline int break_deleg(struct inode *inode, unsigned int mode)
 {
+        /*
+         * Since this check is lockless, we must ensure that any refcounts
+         * taken are done before checking inode->i_flock. Otherwise, we could
+         * end up racing with tasks trying to set a new lease on this file.
+         */
+        smp_mb();
         if (inode->i_flock)
                 return __break_lease(inode, mode, FL_DELEG);
         return 0;
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 17aa1cce6f8e..30faf797c2c3 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -91,6 +91,7 @@ struct kernfs_elem_attr {
         const struct kernfs_ops *ops;
         struct kernfs_open_node *open;
         loff_t                  size;
+        struct kernfs_node      *notify_next;   /* for kernfs_notify() */
 };
 
 /*
@@ -304,6 +305,7 @@ struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
                                struct kernfs_root *root, unsigned long magic,
                                bool *new_sb_created, const void *ns);
 void kernfs_kill_sb(struct super_block *sb);
+struct super_block *kernfs_pin_sb(struct kernfs_root *root, const void *ns);
 
 void kernfs_init(void);
 
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index 11692dea18aa..42aa9b9ecd5f 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -17,6 +17,7 @@
 #include <linux/lockdep.h>
 #include <linux/atomic.h>
 #include <asm/processor.h>
+#include <linux/osq_lock.h>
 
 /*
  * Simple, straightforward mutexes with strict semantics:
@@ -46,7 +47,6 @@
  * - detects multi-task circular deadlocks and prints out all affected
  *   locks and tasks (and only those tasks)
  */
-struct optimistic_spin_queue;
 struct mutex {
         /* 1: unlocked, 0: locked, negative: locked, possible waiters */
         atomic_t                count;
@@ -56,7 +56,7 @@ struct mutex {
         struct task_struct      *owner;
 #endif
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
-        struct optimistic_spin_queue    *osq;   /* Spinner MCS lock */
+        struct optimistic_spin_queue osq; /* Spinner MCS lock */
 #endif
 #ifdef CONFIG_DEBUG_MUTEXES
         const char              *name;
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 6a45fb583ff1..447775ee2c4b 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -32,15 +32,24 @@ static inline void touch_nmi_watchdog(void)
 #ifdef arch_trigger_all_cpu_backtrace
 static inline bool trigger_all_cpu_backtrace(void)
 {
-        arch_trigger_all_cpu_backtrace();
+        arch_trigger_all_cpu_backtrace(true);
 
         return true;
 }
+static inline bool trigger_allbutself_cpu_backtrace(void)
+{
+        arch_trigger_all_cpu_backtrace(false);
+        return true;
+}
 #else
 static inline bool trigger_all_cpu_backtrace(void)
 {
         return false;
 }
+static inline bool trigger_allbutself_cpu_backtrace(void)
+{
+        return false;
+}
 #endif
 
 #ifdef CONFIG_LOCKUP_DETECTOR
@@ -48,6 +57,7 @@ int hw_nmi_is_cpu_stuck(struct pt_regs *);
 u64 hw_nmi_get_sample_period(int watchdog_thresh);
 extern int watchdog_user_enabled;
 extern int watchdog_thresh;
+extern int sysctl_softlockup_all_cpu_backtrace;
 struct ctl_table;
 extern int proc_dowatchdog(struct ctl_table *, int ,
                            void __user *, size_t *, loff_t *);
diff --git a/include/linux/osq_lock.h b/include/linux/osq_lock.h
new file mode 100644
index 000000000000..90230d5811c5
--- /dev/null
+++ b/include/linux/osq_lock.h
@@ -0,0 +1,27 @@
+#ifndef __LINUX_OSQ_LOCK_H
+#define __LINUX_OSQ_LOCK_H
+
+/*
+ * An MCS like lock especially tailored for optimistic spinning for sleeping
+ * lock implementations (mutex, rwsem, etc).
+ */
+
+#define OSQ_UNLOCKED_VAL (0)
+
+struct optimistic_spin_queue {
+        /*
+         * Stores an encoded value of the CPU # of the tail node in the queue.
+         * If the queue is empty, then it's set to OSQ_UNLOCKED_VAL.
+         */
+        atomic_t tail;
+};
+
+/* Init macro and function. */
+#define OSQ_LOCK_UNLOCKED { ATOMIC_INIT(OSQ_UNLOCKED_VAL) }
+
+static inline void osq_lock_init(struct optimistic_spin_queue *lock)
+{
+        atomic_set(&lock->tail, OSQ_UNLOCKED_VAL);
+}
+
+#endif
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 3c545b48aeab..8304959ad336 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -360,6 +360,9 @@ static inline void ClearPageCompound(struct page *page)
         ClearPageHead(page);
 }
 #endif
+
+#define PG_head_mask ((1L << PG_head))
+
 #else
 /*
  * Reduce page flag use as much as possible by overlapping
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index a5fc7d01aad6..dec01d6c3f80 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -146,10 +146,10 @@
  * Declaration/definition used for per-CPU variables that must be read mostly.
  */
 #define DECLARE_PER_CPU_READ_MOSTLY(type, name)                 \
-        DECLARE_PER_CPU_SECTION(type, name, "..readmostly")
+        DECLARE_PER_CPU_SECTION(type, name, "..read_mostly")
 
 #define DEFINE_PER_CPU_READ_MOSTLY(type, name)                          \
-        DEFINE_PER_CPU_SECTION(type, name, "..readmostly")
+        DEFINE_PER_CPU_SECTION(type, name, "..read_mostly")
 
 /*
  * Intermodule exports for per-CPU variables.  sparse forgets about
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 864ddafad8cc..68041446c450 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -536,6 +536,15 @@ struct phy_driver {
         /* See set_wol, but for checking whether Wake on LAN is enabled. */
         void (*get_wol)(struct phy_device *dev, struct ethtool_wolinfo *wol);
 
+        /*
+         * Called to inform a PHY device driver when the core is about to
+         * change the link state. This callback is supposed to be used as
+         * fixup hook for drivers that need to take action when the link
+         * state changes. Drivers are by no means allowed to mess with the
+         * PHY device structure in their implementations.
+         */
+        void (*link_change_notify)(struct phy_device *dev);
+
         struct device_driver driver;
 };
 #define to_phy_driver(d) container_of(d, struct phy_driver, driver)
diff --git a/include/linux/profile.h b/include/linux/profile.h
index aaad3861beb8..b537a25ffa17 100644
--- a/include/linux/profile.h
+++ b/include/linux/profile.h
@@ -44,6 +44,7 @@ extern int prof_on __read_mostly;
 int profile_init(void);
 int profile_setup(char *str);
 void profile_tick(int type);
+int setup_profiling_timer(unsigned int multiplier);
 
 /*
  * Add multiple profiler hits to a given address:
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 077904c8b70d..cc79eff4a1ad 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -334,6 +334,9 @@ static inline void user_single_step_siginfo(struct task_struct *tsk,
  * calling arch_ptrace_stop() when it would be superfluous.  For example,
  * if the thread has not been back to user mode since the last stop, the
  * thread state might indicate that nothing needs to be done.
+ *
+ * This is guaranteed to be invoked once before a task stops for ptrace and
+ * may include arch-specific operations necessary prior to a ptrace stop.
  */
 #define arch_ptrace_stop_needed(code, info)     (0)
 #endif
diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h
index a2d9d81038d1..14ec18d5e18b 100644
--- a/include/linux/regulator/consumer.h
+++ b/include/linux/regulator/consumer.h
@@ -395,6 +395,11 @@ static inline void regulator_bulk_free(int num_consumers,
 {
 }
 
+static inline int regulator_can_change_voltage(struct regulator *regulator)
+{
+        return 0;
+}
+
 static inline int regulator_set_voltage(struct regulator *regulator,
                                         int min_uV, int max_uV)
 {
diff --git a/include/linux/rwsem-spinlock.h b/include/linux/rwsem-spinlock.h
index d5b13bc07a0b..561e8615528d 100644
--- a/include/linux/rwsem-spinlock.h
+++ b/include/linux/rwsem-spinlock.h
@@ -15,13 +15,13 @@
 #ifdef __KERNEL__
 /*
  * the rw-semaphore definition
- * - if activity is 0 then there are no active readers or writers
- * - if activity is +ve then that is the number of active readers
- * - if activity is -1 then there is one active writer
+ * - if count is 0 then there are no active readers or writers
+ * - if count is +ve then that is the number of active readers
+ * - if count is -1 then there is one active writer
  * - if wait_list is not empty, then there are processes waiting for the semaphore
  */
 struct rw_semaphore {
-        __s32                   activity;
+        __s32                   count;
         raw_spinlock_t          wait_lock;
         struct list_head        wait_list;
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 8d79708146aa..035d3c57fc8a 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -13,10 +13,11 @@
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/spinlock.h>
-
 #include <linux/atomic.h>
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
+#include <linux/osq_lock.h>
+#endif
 
-struct optimistic_spin_queue;
 struct rw_semaphore;
 
 #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK
@@ -25,15 +26,15 @@ struct rw_semaphore;
 /* All arch specific implementations share the same struct */
 struct rw_semaphore {
         long count;
-        raw_spinlock_t wait_lock;
         struct list_head wait_list;
-#ifdef CONFIG_SMP
+        raw_spinlock_t wait_lock;
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
+        struct optimistic_spin_queue osq; /* spinner MCS lock */
         /*
          * Write owner. Used as a speculative check to see
          * if the owner is running on the cpu.
          */
         struct task_struct *owner;
-        struct optimistic_spin_queue *osq; /* spinner MCS lock */
 #endif
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
         struct lockdep_map      dep_map;
@@ -64,22 +65,19 @@ static inline int rwsem_is_locked(struct rw_semaphore *sem)
 # define __RWSEM_DEP_MAP_INIT(lockname)
 #endif
 
-#if defined(CONFIG_SMP) && !defined(CONFIG_RWSEM_GENERIC_SPINLOCK)
-#define __RWSEM_INITIALIZER(name)                       \
-        { RWSEM_UNLOCKED_VALUE,                         \
-          __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock),     \
-          LIST_HEAD_INIT((name).wait_list),             \
-          NULL, /* owner */                             \
-          NULL /* mcs lock */                           \
-          __RWSEM_DEP_MAP_INIT(name) }
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
+#define __RWSEM_OPT_INIT(lockname) , .osq = OSQ_LOCK_UNLOCKED, .owner = NULL
 #else
-#define __RWSEM_INITIALIZER(name)                       \
-        { RWSEM_UNLOCKED_VALUE,                         \
-          __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock),     \
-          LIST_HEAD_INIT((name).wait_list)              \
-          __RWSEM_DEP_MAP_INIT(name) }
+#define __RWSEM_OPT_INIT(lockname)
 #endif
 
+#define __RWSEM_INITIALIZER(name)                               \
+        { .count = RWSEM_UNLOCKED_VALUE,                        \
+          .wait_list = LIST_HEAD_INIT((name).wait_list),        \
+          .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock) \
+          __RWSEM_OPT_INIT(name)                                \
+          __RWSEM_DEP_MAP_INIT(name) }
+
 #define DECLARE_RWSEM(name) \
         struct rw_semaphore name = __RWSEM_INITIALIZER(name)
 
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 8e98297f1388..ec538fc287a6 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -305,8 +305,6 @@ struct ucred {
 /* IPX options */
 #define IPX_TYPE        1
 
-extern int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov,
-                               int offset, int len);
 extern int csum_partial_copy_fromiovecend(unsigned char *kdata, 
                                           struct iovec *iov, 
                                           int offset, 
@@ -315,8 +313,6 @@ extern unsigned long iov_pages(const struct iovec *iov, int offset,
                                unsigned long nr_segs);
 
 extern int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *address, int mode);
-extern int memcpy_toiovecend(const struct iovec *v, unsigned char *kdata,
-                             int offset, int len);
 extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr);
 extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data);
 
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index f76994b9396c..519064e0c943 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -327,6 +327,7 @@ extern unsigned long get_safe_page(gfp_t gfp_mask);
 extern void hibernation_set_ops(const struct platform_hibernation_ops *ops);
 extern int hibernate(void);
 extern bool system_entering_hibernation(void);
+extern bool hibernation_available(void);
 asmlinkage int swsusp_save(void);
 extern struct pbe *restore_pblist;
 #else /* CONFIG_HIBERNATION */
@@ -339,6 +340,7 @@ static inline void swsusp_unset_page_free(struct page *p) {}
 static inline void hibernation_set_ops(const struct platform_hibernation_ops *ops) {}
 static inline int hibernate(void) { return -ENOSYS; }
 static inline bool system_entering_hibernation(void) { return false; }
+static inline bool hibernation_available(void) { return false; }
 #endif /* CONFIG_HIBERNATION */
 
 /* Hibernation and suspend events */
diff --git a/include/linux/uio.h b/include/linux/uio.h
index e2231e47cec1..09a7cffc224e 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -94,8 +94,20 @@ static inline size_t iov_iter_count(struct iov_iter *i)
         return i->count;
 }
 
-static inline void iov_iter_truncate(struct iov_iter *i, size_t count)
+/*
+ * Cap the iov_iter by given limit; note that the second argument is
+ * *not* the new size - it's upper limit for such.  Passing it a value
+ * greater than the amount of data in iov_iter is fine - it'll just do
+ * nothing in that case.
+ */
+static inline void iov_iter_truncate(struct iov_iter *i, u64 count)
 {
+        /*
+         * count doesn't have to fit in size_t - comparison extends both
+         * operands to u64 here and any value that would be truncated by
+         * conversion in assignement is by definition greater than all
+         * values of size_t, including old i->count.
+         */
         if (i->count > count)
                 i->count = count;
 }
@@ -111,6 +123,9 @@ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count)
 
 int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len);
 int memcpy_toiovec(struct iovec *iov, unsigned char *kdata, int len);
-
+int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov,
+                        int offset, int len);
+int memcpy_toiovecend(const struct iovec *v, unsigned char *kdata,
+                      int offset, int len);
 
 #endif
diff --git a/include/linux/usb_usual.h b/include/linux/usb_usual.h
index 1a64b26046ed..9b7de1b46437 100644
--- a/include/linux/usb_usual.h
+++ b/include/linux/usb_usual.h
@@ -70,7 +70,9 @@
         US_FLAG(NEEDS_CAP16,    0x00400000)                     \
                 /* cannot handle READ_CAPACITY_10 */            \
         US_FLAG(IGNORE_UAS,     0x00800000)                     \
-                /* Device advertises UAS but it is broken */
+                /* Device advertises UAS but it is broken */    \
+        US_FLAG(BROKEN_FUA,     0x01000000)                     \
+                /* Cannot handle FUA in WRITE or READ CDBs */   \
 
 #define US_FLAG(name, value)    US_FL_##name = value ,
 enum { US_DO_ALL_FLAGS };