Merge branch 'sched/urgent' into sched/core

Pick up fixes before queueing up new changes.

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

18 files changed, 83 insertions, 78 deletions

diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 18ba8a627f46..2ff2e8d982be 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -121,8 +121,7 @@ void blk_mq_init_commands(struct request_queue *, void (*init)(void *data, struc
 
 void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
 
-void blk_mq_insert_request(struct request_queue *, struct request *,
-                bool, bool);
+void blk_mq_insert_request(struct request *, bool, bool, bool);
 void blk_mq_run_queues(struct request_queue *q, bool async);
 void blk_mq_free_request(struct request *rq);
 bool blk_mq_can_queue(struct blk_mq_hw_ctx *);
@@ -134,7 +133,13 @@ struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *, const int ctx_ind
 struct blk_mq_hw_ctx *blk_mq_alloc_single_hw_queue(struct blk_mq_reg *, unsigned int);
 void blk_mq_free_single_hw_queue(struct blk_mq_hw_ctx *, unsigned int);
 
-void blk_mq_end_io(struct request *rq, int error);
+bool blk_mq_end_io_partial(struct request *rq, int error,
+                unsigned int nr_bytes);
+static inline void blk_mq_end_io(struct request *rq, int error)
+{
+        bool done = !blk_mq_end_io_partial(rq, error, blk_rq_bytes(rq));
+        BUG_ON(!done);
+}
 
 void blk_mq_complete_request(struct request *rq);
 
diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h
index 092b64168d7f..4a21a872dbbd 100644
--- a/include/linux/clk/ti.h
+++ b/include/linux/clk/ti.h
@@ -245,6 +245,10 @@ long omap2_dpll_round_rate(struct clk_hw *hw, unsigned long target_rate,
 void omap2_init_clk_clkdm(struct clk_hw *clk);
 unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw,
                                     unsigned long parent_rate);
+int omap3_clkoutx2_set_rate(struct clk_hw *hw, unsigned long rate,
+                                        unsigned long parent_rate);
+long omap3_clkoutx2_round_rate(struct clk_hw *hw, unsigned long rate,
+                unsigned long *prate);
 int omap2_clkops_enable_clkdm(struct clk_hw *hw);
 void omap2_clkops_disable_clkdm(struct clk_hw *hw);
 int omap2_clk_disable_autoidle_all(void);
diff --git a/include/linux/file.h b/include/linux/file.h
index cbacf4faf447..4d69123377a2 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -28,33 +28,36 @@ static inline void fput_light(struct file *file, int fput_needed)
 
 struct fd {
         struct file *file;
-        int need_put;
+        unsigned int flags;
 };
+#define FDPUT_FPUT       1
+#define FDPUT_POS_UNLOCK 2
 
 static inline void fdput(struct fd fd)
 {
-        if (fd.need_put)
+        if (fd.flags & FDPUT_FPUT)
                 fput(fd.file);
 }
 
 extern struct file *fget(unsigned int fd);
-extern struct file *fget_light(unsigned int fd, int *fput_needed);
+extern struct file *fget_raw(unsigned int fd);
+extern unsigned long __fdget(unsigned int fd);
+extern unsigned long __fdget_raw(unsigned int fd);
+extern unsigned long __fdget_pos(unsigned int fd);
 
-static inline struct fd fdget(unsigned int fd)
+static inline struct fd __to_fd(unsigned long v)
 {
-        int b;
-        struct file *f = fget_light(fd, &b);
-        return (struct fd){f,b};
+        return (struct fd){(struct file *)(v & ~3),v & 3};
 }
 
-extern struct file *fget_raw(unsigned int fd);
-extern struct file *fget_raw_light(unsigned int fd, int *fput_needed);
+static inline struct fd fdget(unsigned int fd)
+{
+        return __to_fd(__fdget(fd));
+}
 
 static inline struct fd fdget_raw(unsigned int fd)
 {
-        int b;
-        struct file *f = fget_raw_light(fd, &b);
-        return (struct fd){f,b};
+        return __to_fd(__fdget_raw(fd));
 }
 
 extern int f_dupfd(unsigned int from, struct file *file, unsigned flags);
diff --git a/include/linux/firewire.h b/include/linux/firewire.h
index 5d7782e42b8f..c3683bdf28fe 100644
--- a/include/linux/firewire.h
+++ b/include/linux/firewire.h
@@ -200,6 +200,7 @@ struct fw_device {
         unsigned irmc:1;
         unsigned bc_implemented:2;
 
+        work_func_t workfn;
         struct delayed_work work;
         struct fw_attribute_group attribute_group;
 };
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 60829565e552..23b2a35d712e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -123,6 +123,9 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 /* File is opened with O_PATH; almost nothing can be done with it */
 #define FMODE_PATH              ((__force fmode_t)0x4000)
 
+/* File needs atomic accesses to f_pos */
+#define FMODE_ATOMIC_POS        ((__force fmode_t)0x8000)
+
 /* File was opened by fanotify and shouldn't generate fanotify events */
 #define FMODE_NONOTIFY          ((__force fmode_t)0x1000000)
 
@@ -780,13 +783,14 @@ struct file {
         const struct file_operations    *f_op;
 
         /*
-         * Protects f_ep_links, f_flags, f_pos vs i_size in lseek SEEK_CUR.
+         * Protects f_ep_links, f_flags.
          * Must not be taken from IRQ context.
          */
         spinlock_t              f_lock;
         atomic_long_t           f_count;
         unsigned int            f_flags;
         fmode_t                 f_mode;
+        struct mutex            f_pos_lock;
         loff_t                  f_pos;
         struct fown_struct      f_owner;
         const struct cred       *f_cred;
@@ -808,7 +812,7 @@ struct file {
 #ifdef CONFIG_DEBUG_WRITECOUNT
         unsigned long f_mnt_write_state;
 #endif
-};
+} __attribute__((aligned(4)));  /* lest something weird decides that 2 is OK */
 
 struct file_handle {
         __u32 handle_bytes;
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 3d286ff49ab0..64cf3ef50696 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -99,7 +99,7 @@ struct fsnotify_ops {
                             struct fsnotify_mark *inode_mark,
                             struct fsnotify_mark *vfsmount_mark,
                             u32 mask, void *data, int data_type,
-                            const unsigned char *file_name);
+                            const unsigned char *file_name, u32 cookie);
         void (*free_group_priv)(struct fsnotify_group *group);
         void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group);
         void (*free_event)(struct fsnotify_event *event);
@@ -160,7 +160,7 @@ struct fsnotify_group {
 
         struct fasync_struct *fsn_fa;    /* async notification */
 
-        struct fsnotify_event overflow_event;   /* Event we queue when the
+        struct fsnotify_event *overflow_event;  /* Event we queue when the
                                                  * notification list is too
                                                  * full */
 
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 0437439bc047..39b81dc7d01a 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -123,6 +123,10 @@ struct vm_area_struct;
                          __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN | \
                          __GFP_NO_KSWAPD)
 
+/*
+ * GFP_THISNODE does not perform any reclaim, you most likely want to
+ * use __GFP_THISNODE to allocate from a given node without fallback!
+ */
 #ifdef CONFIG_NUMA
 #define GFP_THISNODE    (__GFP_THISNODE | __GFP_NOWARN | __GFP_NORETRY)
 #else
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index db512014e061..b826239bdce0 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -157,46 +157,6 @@ static inline int hpage_nr_pages(struct page *page)
                 return HPAGE_PMD_NR;
         return 1;
 }
-/*
- * compound_trans_head() should be used instead of compound_head(),
- * whenever the "page" passed as parameter could be the tail of a
- * transparent hugepage that could be undergoing a
- * __split_huge_page_refcount(). The page structure layout often
- * changes across releases and it makes extensive use of unions. So if
- * the page structure layout will change in a way that
- * page->first_page gets clobbered by __split_huge_page_refcount, the
- * implementation making use of smp_rmb() will be required.
- *
- * Currently we define compound_trans_head as compound_head, because
- * page->private is in the same union with page->first_page, and
- * page->private isn't clobbered. However this also means we're
- * currently leaving dirt into the page->private field of anonymous
- * pages resulting from a THP split, instead of setting page->private
- * to zero like for every other page that has PG_private not set. But
- * anonymous pages don't use page->private so this is not a problem.
- */
-#if 0
-/* This will be needed if page->private will be clobbered in split_huge_page */
-static inline struct page *compound_trans_head(struct page *page)
-{
-        if (PageTail(page)) {
-                struct page *head;
-                head = page->first_page;
-                smp_rmb();
-                /*
-                 * head may be a dangling pointer.
-                 * __split_huge_page_refcount clears PageTail before
-                 * overwriting first_page, so if PageTail is still
-                 * there it means the head pointer isn't dangling.
-                 */
-                if (PageTail(page))
-                        return head;
-        }
-        return page;
-}
-#else
-#define compound_trans_head(page) compound_head(page)
-#endif
 
 extern int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
                                 unsigned long addr, pmd_t pmd, pmd_t *pmdp);
@@ -226,7 +186,6 @@ static inline int split_huge_page(struct page *page)
         do { } while (0)
 #define split_huge_page_pmd_mm(__mm, __address, __pmd)  \
         do { } while (0)
-#define compound_trans_head(page) compound_head(page)
 static inline int hugepage_madvise(struct vm_area_struct *vma,
                                    unsigned long *vm_flags, int advice)
 {
diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index e7831d203737..35e7eca4e33b 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -118,9 +118,7 @@ extern int mq_init_ns(struct ipc_namespace *ns);
  *     the new maximum will handle anyone else.  I may have to revisit this
  *     in the future.
  */
-#define MIN_QUEUESMAX                   1
 #define DFLT_QUEUESMAX                256
-#define HARD_QUEUESMAX               1024
 #define MIN_MSGMAX                      1
 #define DFLT_MSG                       10U
 #define DFLT_MSGMAX                    10
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 5be9f0228a3b..d267623c28cf 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -249,7 +249,8 @@ void kernfs_notify(struct kernfs_node *kn);
 
 const void *kernfs_super_ns(struct super_block *sb);
 struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
-                               struct kernfs_root *root, const void *ns);
+                               struct kernfs_root *root, bool *new_sb_created,
+                               const void *ns);
 void kernfs_kill_sb(struct super_block *sb);
 
 void kernfs_init(void);
@@ -317,7 +318,7 @@ static inline const void *kernfs_super_ns(struct super_block *sb)
 
 static inline struct dentry *
 kernfs_mount_ns(struct file_system_type *fs_type, int flags,
-                struct kernfs_root *root, const void *ns)
+                struct kernfs_root *root, bool *new_sb_created, const void *ns)
 { return ERR_PTR(-ENOSYS); }
 
 static inline void kernfs_kill_sb(struct super_block *sb) { }
@@ -368,9 +369,9 @@ static inline int kernfs_remove_by_name(struct kernfs_node *parent,
 
 static inline struct dentry *
 kernfs_mount(struct file_system_type *fs_type, int flags,
-             struct kernfs_root *root)
+             struct kernfs_root *root, bool *new_sb_created)
 {
-        return kernfs_mount_ns(fs_type, flags, root, NULL);
+        return kernfs_mount_ns(fs_type, flags, root, new_sb_created, NULL);
 }
 
 #endif  /* __LINUX_KERNFS_H */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index f28f46eade6a..c1b7414c7bef 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -175,7 +175,7 @@ extern unsigned int kobjsize(const void *objp);
  * Special vmas that are non-mergable, non-mlock()able.
  * Note: mm/huge_memory.c VM_NO_THP depends on this definition.
  */
-#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP)
+#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP)
 
 /*
  * mapping from the currently active vm_flags protection bits (the
@@ -399,8 +399,18 @@ static inline void compound_unlock_irqrestore(struct page *page,
 
 static inline struct page *compound_head(struct page *page)
 {
-        if (unlikely(PageTail(page)))
-                return page->first_page;
+        if (unlikely(PageTail(page))) {
+                struct page *head = page->first_page;
+
+                /*
+                 * page->first_page may be a dangling pointer to an old
+                 * compound page, so recheck that it is still a tail
+                 * page before returning.
+                 */
+                smp_rmb();
+                if (likely(PageTail(page)))
+                        return head;
+        }
         return page;
 }
 
@@ -757,7 +767,7 @@ static inline bool __cpupid_match_pid(pid_t task_pid, int cpupid)
 #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
 static inline int page_cpupid_xchg_last(struct page *page, int cpupid)
 {
-        return xchg(&page->_last_cpupid, cpupid);
+        return xchg(&page->_last_cpupid, cpupid & LAST_CPUPID_MASK);
 }
 
 static inline int page_cpupid_last(struct page *page)
@@ -766,7 +776,7 @@ static inline int page_cpupid_last(struct page *page)
 }
 static inline void page_cpupid_reset_last(struct page *page)
 {
-        page->_last_cpupid = -1;
+        page->_last_cpupid = -1 & LAST_CPUPID_MASK;
 }
 #else
 static inline int page_cpupid_last(struct page *page)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 5f2052c83154..9b61b9bf81ac 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -590,10 +590,10 @@ static inline bool zone_is_empty(struct zone *zone)
 
 /*
  * The NUMA zonelists are doubled because we need zonelists that restrict the
- * allocations to a single node for GFP_THISNODE.
+ * allocations to a single node for __GFP_THISNODE.
  *
  * [0]  : Zonelist with fallback
- * [1]  : No fallback (GFP_THISNODE)
+ * [1]  : No fallback (__GFP_THISNODE)
  */
 #define MAX_ZONELISTS 2
 
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index b2fb167b2e6d..5624e4e2763c 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -467,9 +467,14 @@ struct nfs_lockt_res {
 };
 
 struct nfs_release_lockowner_args {
+        struct nfs4_sequence_args       seq_args;
         struct nfs_lowner       lock_owner;
 };
 
+struct nfs_release_lockowner_res {
+        struct nfs4_sequence_res        seq_res;
+};
+
 struct nfs4_delegreturnargs {
         struct nfs4_sequence_args       seq_args;
         const struct nfs_fh *fhandle;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 3ebbbe7b6d05..5e1e6f2d98c2 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2725,7 +2725,7 @@ static inline void nf_reset(struct sk_buff *skb)
 
 static inline void nf_reset_trace(struct sk_buff *skb)
 {
-#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
+#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES)
         skb->nf_trace = 0;
 #endif
 }
@@ -2742,6 +2742,9 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src)
         dst->nf_bridge  = src->nf_bridge;
         nf_bridge_get(src->nf_bridge);
 #endif
+#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES)
+        dst->nf_trace = src->nf_trace;
+#endif
 }
 
 static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src)
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 9260abdd67df..b5b2df60299e 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -410,7 +410,7 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags)
  *
  * %GFP_NOWAIT - Allocation will not sleep.
  *
- * %GFP_THISNODE - Allocate node-local memory only.
+ * %__GFP_THISNODE - Allocate node-local memory only.
  *
  * %GFP_DMA - Allocation suitable for DMA.
  *   Should only be used for kmalloc() caches. Otherwise, use a
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 40ed9e9a77e5..a747a77ea584 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -281,13 +281,15 @@ asmlinkage long sys_sched_setscheduler(pid_t pid, int policy,
 asmlinkage long sys_sched_setparam(pid_t pid,
                                         struct sched_param __user *param);
 asmlinkage long sys_sched_setattr(pid_t pid,
-                                        struct sched_attr __user *attr);
+                                        struct sched_attr __user *attr,
+                                        unsigned int flags);
 asmlinkage long sys_sched_getscheduler(pid_t pid);
 asmlinkage long sys_sched_getparam(pid_t pid,
                                         struct sched_param __user *param);
 asmlinkage long sys_sched_getattr(pid_t pid,
                                         struct sched_attr __user *attr,
-                                        unsigned int size);
+                                        unsigned int size,
+                                        unsigned int flags);
 asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len,
                                         unsigned long __user *user_mask_ptr);
 asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len,
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index accc497f8d72..7159a0a933df 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -60,6 +60,12 @@ struct tp_module {
         unsigned int num_tracepoints;
         struct tracepoint * const *tracepoints_ptrs;
 };
+bool trace_module_has_bad_taint(struct module *mod);
+#else
+static inline bool trace_module_has_bad_taint(struct module *mod)
+{
+        return false;
+}
 #endif /* CONFIG_MODULES */
 
 struct tracepoint_iter {
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index fc0e4320aa6d..021b8a319b9e 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -97,7 +97,7 @@ void writeback_inodes_sb_nr(struct super_block *, unsigned long nr,
 int try_to_writeback_inodes_sb(struct super_block *, enum wb_reason reason);
 int try_to_writeback_inodes_sb_nr(struct super_block *, unsigned long nr,
                                   enum wb_reason reason);
-void sync_inodes_sb(struct super_block *sb, unsigned long older_than_this);
+void sync_inodes_sb(struct super_block *);
 void wakeup_flusher_threads(long nr_pages, enum wb_reason reason);
 void inode_wait_for_writeback(struct inode *inode);