Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Three sets of overlapping changes, two in the packet scheduler
and one in the meson-gxl PHY driver.

Signed-off-by: David S. Miller <davem@davemloft.net>

18 files changed, 49 insertions, 232 deletions

diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 188ed9f65517..52e611ab9a6c 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -220,21 +220,21 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 /*
  * Prevent the compiler from merging or refetching reads or writes. The
  * compiler is also forbidden from reordering successive instances of
- * READ_ONCE, WRITE_ONCE and ACCESS_ONCE (see below), but only when the
- * compiler is aware of some particular ordering.  One way to make the
- * compiler aware of ordering is to put the two invocations of READ_ONCE,
- * WRITE_ONCE or ACCESS_ONCE() in different C statements.
+ * READ_ONCE and WRITE_ONCE, but only when the compiler is aware of some
+ * particular ordering. One way to make the compiler aware of ordering is to
+ * put the two invocations of READ_ONCE or WRITE_ONCE in different C
+ * statements.
  *
- * In contrast to ACCESS_ONCE these two macros will also work on aggregate
- * data types like structs or unions. If the size of the accessed data
- * type exceeds the word size of the machine (e.g., 32 bits or 64 bits)
- * READ_ONCE() and WRITE_ONCE() will fall back to memcpy(). There's at
- * least two memcpy()s: one for the __builtin_memcpy() and then one for
- * the macro doing the copy of variable - '__u' allocated on the stack.
+ * These two macros will also work on aggregate data types like structs or
+ * unions. If the size of the accessed data type exceeds the word size of
+ * the machine (e.g., 32 bits or 64 bits) READ_ONCE() and WRITE_ONCE() will
+ * fall back to memcpy(). There's at least two memcpy()s: one for the
+ * __builtin_memcpy() and then one for the macro doing the copy of variable
+ * - '__u' allocated on the stack.
  *
  * Their two major use cases are: (1) Mediating communication between
  * process-level code and irq/NMI handlers, all running on the same CPU,
- * and (2) Ensuring that the compiler does not  fold, spindle, or otherwise
+ * and (2) Ensuring that the compiler does not fold, spindle, or otherwise
  * mutilate accesses that either do not require ordering or that interact
  * with an explicit memory barrier or atomic instruction that provides the
  * required ordering.
@@ -327,29 +327,4 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 	compiletime_assert(__native_word(t),				\
 		"Need native word sized stores/loads for atomicity.")
 
-/*
- * Prevent the compiler from merging or refetching accesses.  The compiler
- * is also forbidden from reordering successive instances of ACCESS_ONCE(),
- * but only when the compiler is aware of some particular ordering.  One way
- * to make the compiler aware of ordering is to put the two invocations of
- * ACCESS_ONCE() in different C statements.
- *
- * ACCESS_ONCE will only work on scalar types. For union types, ACCESS_ONCE
- * on a union member will work as long as the size of the member matches the
- * size of the union and the size is smaller than word size.
- *
- * The major use cases of ACCESS_ONCE used to be (1) Mediating communication
- * between process-level code and irq/NMI handlers, all running on the same CPU,
- * and (2) Ensuring that the compiler does not  fold, spindle, or otherwise
- * mutilate accesses that either do not require ordering or that interact
- * with an explicit memory barrier or atomic instruction that provides the
- * required ordering.
- *
- * If possible use READ_ONCE()/WRITE_ONCE() instead.
- */
-#define __ACCESS_ONCE(x) ({ \
-	 __maybe_unused typeof(x) __var = (__force typeof(x)) 0; \
-	(volatile typeof(x) *)&(x); })
-#define ACCESS_ONCE(x) (*__ACCESS_ONCE(x))
-
 #endif /* __LINUX_COMPILER_H */
diff --git a/include/linux/completion.h b/include/linux/completion.h
index 0662a417febe..94a59ba7d422 100644
--- a/include/linux/completion.h
+++ b/include/linux/completion.h
@@ -10,9 +10,6 @@
  */
 
 #include <linux/wait.h>
-#ifdef CONFIG_LOCKDEP_COMPLETIONS
-#include <linux/lockdep.h>
-#endif
 
 /*
  * struct completion - structure used to maintain state for a "completion"
@@ -29,58 +26,16 @@
 struct completion {
 	unsigned int done;
 	wait_queue_head_t wait;
-#ifdef CONFIG_LOCKDEP_COMPLETIONS
-	struct lockdep_map_cross map;
-#endif
 };
 
-#ifdef CONFIG_LOCKDEP_COMPLETIONS
-static inline void complete_acquire(struct completion *x)
-{
-	lock_acquire_exclusive((struct lockdep_map *)&x->map, 0, 0, NULL, _RET_IP_);
-}
-
-static inline void complete_release(struct completion *x)
-{
-	lock_release((struct lockdep_map *)&x->map, 0, _RET_IP_);
-}
-
-static inline void complete_release_commit(struct completion *x)
-{
-	lock_commit_crosslock((struct lockdep_map *)&x->map);
-}
-
-#define init_completion_map(x, m)					\
-do {									\
-	lockdep_init_map_crosslock((struct lockdep_map *)&(x)->map,	\
-			(m)->name, (m)->key, 0);				\
-	__init_completion(x);						\
-} while (0)
-
-#define init_completion(x)						\
-do {									\
-	static struct lock_class_key __key;				\
-	lockdep_init_map_crosslock((struct lockdep_map *)&(x)->map,	\
-			"(completion)" #x,				\
-			&__key, 0);					\
-	__init_completion(x);						\
-} while (0)
-#else
 #define init_completion_map(x, m) __init_completion(x)
 #define init_completion(x) __init_completion(x)
 static inline void complete_acquire(struct completion *x) {}
 static inline void complete_release(struct completion *x) {}
 static inline void complete_release_commit(struct completion *x) {}
-#endif
 
-#ifdef CONFIG_LOCKDEP_COMPLETIONS
-#define COMPLETION_INITIALIZER(work) \
-	{ 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait), \
-	STATIC_CROSS_LOCKDEP_MAP_INIT("(completion)" #work, &(work)) }
-#else
 #define COMPLETION_INITIALIZER(work) \
 	{ 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) }
-#endif
 
 #define COMPLETION_INITIALIZER_ONSTACK_MAP(work, map) \
 	(*({ init_completion_map(&(work), &(map)); &(work); }))
diff --git a/include/linux/cred.h b/include/linux/cred.h
index 099058e1178b..631286535d0f 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -83,6 +83,7 @@ extern int set_current_groups(struct group_info *);
 extern void set_groups(struct cred *, struct group_info *);
 extern int groups_search(const struct group_info *, kgid_t);
 extern bool may_setgroups(void);
+extern void groups_sort(struct group_info *);
 
 /*
  * The security context of a task
diff --git a/include/linux/idr.h b/include/linux/idr.h
index 7c3a365f7e12..fa14f834e4ed 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -15,6 +15,7 @@
 #include <linux/radix-tree.h>
 #include <linux/gfp.h>
 #include <linux/percpu.h>
+#include <linux/bug.h>
 
 struct idr {
 	struct radix_tree_root	idr_rt;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 893d6d606cd0..6bdd4b9f6611 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -232,7 +232,7 @@ struct kvm_vcpu {
 	struct mutex mutex;
 	struct kvm_run *run;
 
-	int guest_fpu_loaded, guest_xcr0_loaded;
+	int guest_xcr0_loaded;
 	struct swait_queue_head wq;
 	struct pid __rcu *pid;
 	int sigset_active;
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index a842551fe044..2e75dc34bff5 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -158,12 +158,6 @@ struct lockdep_map {
 	int				cpu;
 	unsigned long			ip;
 #endif
-#ifdef CONFIG_LOCKDEP_CROSSRELEASE
-	/*
-	 * Whether it's a crosslock.
-	 */
-	int				cross;
-#endif
 };
 
 static inline void lockdep_copy_map(struct lockdep_map *to,
@@ -267,96 +261,9 @@ struct held_lock {
 	unsigned int hardirqs_off:1;
 	unsigned int references:12;					/* 32 bits */
 	unsigned int pin_count;
-#ifdef CONFIG_LOCKDEP_CROSSRELEASE
-	/*
-	 * Generation id.
-	 *
-	 * A value of cross_gen_id will be stored when holding this,
-	 * which is globally increased whenever each crosslock is held.
-	 */
-	unsigned int gen_id;
-#endif
-};
-
-#ifdef CONFIG_LOCKDEP_CROSSRELEASE
-#define MAX_XHLOCK_TRACE_ENTRIES 5
-
-/*
- * This is for keeping locks waiting for commit so that true dependencies
- * can be added at commit step.
- */
-struct hist_lock {
-	/*
-	 * Id for each entry in the ring buffer. This is used to
-	 * decide whether the ring buffer was overwritten or not.
-	 *
-	 * For example,
-	 *
-	 *           |<----------- hist_lock ring buffer size ------->|
-	 *           pppppppppppppppppppppiiiiiiiiiiiiiiiiiiiiiiiiiiiii
-	 * wrapped > iiiiiiiiiiiiiiiiiiiiiiiiiii.......................
-	 *
-	 *           where 'p' represents an acquisition in process
-	 *           context, 'i' represents an acquisition in irq
-	 *           context.
-	 *
-	 * In this example, the ring buffer was overwritten by
-	 * acquisitions in irq context, that should be detected on
-	 * rollback or commit.
-	 */
-	unsigned int hist_id;
-
-	/*
-	 * Seperate stack_trace data. This will be used at commit step.
-	 */
-	struct stack_trace	trace;
-	unsigned long		trace_entries[MAX_XHLOCK_TRACE_ENTRIES];
-
-	/*
-	 * Seperate hlock instance. This will be used at commit step.
-	 *
-	 * TODO: Use a smaller data structure containing only necessary
-	 * data. However, we should make lockdep code able to handle the
-	 * smaller one first.
-	 */
-	struct held_lock	hlock;
 };
 
 /*
- * To initialize a lock as crosslock, lockdep_init_map_crosslock() should
- * be called instead of lockdep_init_map().
- */
-struct cross_lock {
-	/*
-	 * When more than one acquisition of crosslocks are overlapped,
-	 * we have to perform commit for them based on cross_gen_id of
-	 * the first acquisition, which allows us to add more true
-	 * dependencies.
-	 *
-	 * Moreover, when no acquisition of a crosslock is in progress,
-	 * we should not perform commit because the lock might not exist
-	 * any more, which might cause incorrect memory access. So we
-	 * have to track the number of acquisitions of a crosslock.
-	 */
-	int nr_acquire;
-
-	/*
-	 * Seperate hlock instance. This will be used at commit step.
-	 *
-	 * TODO: Use a smaller data structure containing only necessary
-	 * data. However, we should make lockdep code able to handle the
-	 * smaller one first.
-	 */
-	struct held_lock	hlock;
-};
-
-struct lockdep_map_cross {
-	struct lockdep_map map;
-	struct cross_lock xlock;
-};
-#endif
-
-/*
  * Initialization, self-test and debugging-output methods:
  */
 extern void lockdep_info(void);
@@ -560,37 +467,6 @@ enum xhlock_context_t {
 	XHLOCK_CTX_NR,
 };
 
-#ifdef CONFIG_LOCKDEP_CROSSRELEASE
-extern void lockdep_init_map_crosslock(struct lockdep_map *lock,
-				       const char *name,
-				       struct lock_class_key *key,
-				       int subclass);
-extern void lock_commit_crosslock(struct lockdep_map *lock);
-
-/*
- * What we essencially have to initialize is 'nr_acquire'. Other members
- * will be initialized in add_xlock().
- */
-#define STATIC_CROSS_LOCK_INIT() \
-	{ .nr_acquire = 0,}
-
-#define STATIC_CROSS_LOCKDEP_MAP_INIT(_name, _key) \
-	{ .map.name = (_name), .map.key = (void *)(_key), \
-	  .map.cross = 1, .xlock = STATIC_CROSS_LOCK_INIT(), }
-
-/*
- * To initialize a lockdep_map statically use this macro.
- * Note that _name must not be NULL.
- */
-#define STATIC_LOCKDEP_MAP_INIT(_name, _key) \
-	{ .name = (_name), .key = (void *)(_key), .cross = 0, }
-
-extern void crossrelease_hist_start(enum xhlock_context_t c);
-extern void crossrelease_hist_end(enum xhlock_context_t c);
-extern void lockdep_invariant_state(bool force);
-extern void lockdep_init_task(struct task_struct *task);
-extern void lockdep_free_task(struct task_struct *task);
-#else /* !CROSSRELEASE */
 #define lockdep_init_map_crosslock(m, n, k, s) do {} while (0)
 /*
  * To initialize a lockdep_map statically use this macro.
@@ -604,7 +480,6 @@ static inline void crossrelease_hist_end(enum xhlock_context_t c) {}
 static inline void lockdep_invariant_state(bool force) {}
 static inline void lockdep_init_task(struct task_struct *task) {}
 static inline void lockdep_free_task(struct task_struct *task) {}
-#endif /* CROSSRELEASE */
 
 #ifdef CONFIG_LOCK_STAT
 
diff --git a/include/linux/oom.h b/include/linux/oom.h
index 01c91d874a57..5bad038ac012 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -67,6 +67,15 @@ static inline bool tsk_is_oom_victim(struct task_struct * tsk)
 }
 
 /*
+ * Use this helper if tsk->mm != mm and the victim mm needs a special
+ * handling. This is guaranteed to stay true after once set.
+ */
+static inline bool mm_is_oom_victim(struct mm_struct *mm)
+{
+	return test_bit(MMF_OOM_VICTIM, &mm->flags);
+}
+
+/*
  * Checks whether a page fault on the given mm is still reliable.
  * This is no longer true if the oom reaper started to reap the
  * address space which is reflected by MMF_UNSTABLE flag set in
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 483b780655bb..0314e0716c30 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1675,6 +1675,9 @@ static inline struct pci_dev *pci_get_slot(struct pci_bus *bus,
 static inline struct pci_dev *pci_get_bus_and_slot(unsigned int bus,
 						unsigned int devfn)
 { return NULL; }
+static inline struct pci_dev *pci_get_domain_bus_and_slot(int domain,
+					unsigned int bus, unsigned int devfn)
+{ return NULL; }
 
 static inline int pci_domain_nr(struct pci_bus *bus) { return 0; }
 static inline struct pci_dev *pci_dev_get(struct pci_dev *dev) { return NULL; }
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 65d39115f06d..492ed473ba7e 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -765,6 +765,7 @@ extern int pm_generic_poweroff_late(struct device *dev);
 extern int pm_generic_poweroff(struct device *dev);
 extern void pm_generic_complete(struct device *dev);
 
+extern void dev_pm_skip_next_resume_phases(struct device *dev);
 extern bool dev_pm_smart_suspend_and_suspended(struct device *dev);
 
 #else /* !CONFIG_PM_SLEEP */
diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h
index 37b4bb2545b3..6866df4f31b5 100644
--- a/include/linux/ptr_ring.h
+++ b/include/linux/ptr_ring.h
@@ -101,12 +101,18 @@ static inline bool ptr_ring_full_bh(struct ptr_ring *r)
 
 /* Note: callers invoking this in a loop must use a compiler barrier,
  * for example cpu_relax(). Callers must hold producer_lock.
+ * Callers are responsible for making sure pointer that is being queued
+ * points to a valid data.
  */
 static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr)
 {
 	if (unlikely(!r->size) || r->queue[r->producer])
 		return -ENOSPC;
 
+	/* Make sure the pointer we are storing points to a valid data. */
+	/* Pairs with smp_read_barrier_depends in __ptr_ring_consume. */
+	smp_wmb();
+
 	r->queue[r->producer++] = ptr;
 	if (unlikely(r->producer >= r->size))
 		r->producer = 0;
@@ -275,6 +281,9 @@ static inline void *__ptr_ring_consume(struct ptr_ring *r)
 	if (ptr)
 		__ptr_ring_discard_one(r);
 
+	/* Make sure anyone accessing data through the pointer is up to date. */
+	/* Pairs with smp_wmb in __ptr_ring_produce. */
+	smp_read_barrier_depends();
 	return ptr;
 }
 
diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h
index d574361943ea..fcbeed4053ef 100644
--- a/include/linux/rbtree.h
+++ b/include/linux/rbtree.h
@@ -99,6 +99,8 @@ extern void rb_replace_node(struct rb_node *victim, struct rb_node *new,
 			    struct rb_root *root);
 extern void rb_replace_node_rcu(struct rb_node *victim, struct rb_node *new,
 				struct rb_root *root);
+extern void rb_replace_node_cached(struct rb_node *victim, struct rb_node *new,
+				   struct rb_root_cached *root);
 
 static inline void rb_link_node(struct rb_node *node, struct rb_node *parent,
 				struct rb_node **rb_link)
diff --git a/include/linux/rwlock_types.h b/include/linux/rwlock_types.h
index cc0072e93e36..857a72ceb794 100644
--- a/include/linux/rwlock_types.h
+++ b/include/linux/rwlock_types.h
@@ -10,9 +10,6 @@
  */
 typedef struct {
 	arch_rwlock_t raw_lock;
-#ifdef CONFIG_GENERIC_LOCKBREAK
-	unsigned int break_lock;
-#endif
 #ifdef CONFIG_DEBUG_SPINLOCK
 	unsigned int magic, owner_cpu;
 	void *owner;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 21991d668d35..d2588263a989 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -849,17 +849,6 @@ struct task_struct {
 	struct held_lock		held_locks[MAX_LOCK_DEPTH];
 #endif
 
-#ifdef CONFIG_LOCKDEP_CROSSRELEASE
-#define MAX_XHLOCKS_NR 64UL
-	struct hist_lock *xhlocks; /* Crossrelease history locks */
-	unsigned int xhlock_idx;
-	/* For restoring at history boundaries */
-	unsigned int xhlock_idx_hist[XHLOCK_CTX_NR];
-	unsigned int hist_id;
-	/* For overwrite check at each context exit */
-	unsigned int hist_id_save[XHLOCK_CTX_NR];
-#endif
-
 #ifdef CONFIG_UBSAN
 	unsigned int			in_ubsan;
 #endif
@@ -1503,7 +1492,11 @@ static inline void set_task_comm(struct task_struct *tsk, const char *from)
 	__set_task_comm(tsk, from, false);
 }
 
-extern char *get_task_comm(char *to, struct task_struct *tsk);
+extern char *__get_task_comm(char *to, size_t len, struct task_struct *tsk);
+#define get_task_comm(buf, tsk) ({			\
+	BUILD_BUG_ON(sizeof(buf) != TASK_COMM_LEN);	\
+	__get_task_comm(buf, sizeof(buf), tsk);		\
+})
 
 #ifdef CONFIG_SMP
 void scheduler_ipi(void);
diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h
index 9c8847395b5e..ec912d01126f 100644
--- a/include/linux/sched/coredump.h
+++ b/include/linux/sched/coredump.h
@@ -70,6 +70,7 @@ static inline int get_dumpable(struct mm_struct *mm)
 #define MMF_UNSTABLE		22	/* mm is unstable for copy_from_user */
 #define MMF_HUGE_ZERO_PAGE	23      /* mm has ever used the global huge zero page */
 #define MMF_DISABLE_THP		24	/* disable THP for all VMAs */
+#define MMF_OOM_VICTIM		25	/* mm is the oom victim */
 #define MMF_DISABLE_THP_MASK	(1 << MMF_DISABLE_THP)
 
 #define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 10fd28b118ee..4894d322d258 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -107,16 +107,11 @@ do {								\
 
 #define raw_spin_is_locked(lock)	arch_spin_is_locked(&(lock)->raw_lock)
 
-#ifdef CONFIG_GENERIC_LOCKBREAK
-#define raw_spin_is_contended(lock) ((lock)->break_lock)
-#else
-
 #ifdef arch_spin_is_contended
 #define raw_spin_is_contended(lock)	arch_spin_is_contended(&(lock)->raw_lock)
 #else
 #define raw_spin_is_contended(lock)	(((void)(lock), 0))
 #endif /*arch_spin_is_contended*/
-#endif
 
 /*
  * This barrier must provide two things:
diff --git a/include/linux/spinlock_types.h b/include/linux/spinlock_types.h
index 73548eb13a5d..24b4e6f2c1a2 100644
--- a/include/linux/spinlock_types.h
+++ b/include/linux/spinlock_types.h
@@ -19,9 +19,6 @@
 
 typedef struct raw_spinlock {
 	arch_spinlock_t raw_lock;
-#ifdef CONFIG_GENERIC_LOCKBREAK
-	unsigned int break_lock;
-#endif
 #ifdef CONFIG_DEBUG_SPINLOCK
 	unsigned int magic, owner_cpu;
 	void *owner;
diff --git a/include/linux/string.h b/include/linux/string.h
index 410ecf17de3c..cfd83eb2f926 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -259,7 +259,10 @@ __FORTIFY_INLINE __kernel_size_t strlen(const char *p)
 {
 	__kernel_size_t ret;
 	size_t p_size = __builtin_object_size(p, 0);
-	if (p_size == (size_t)-1)
+
+	/* Work around gcc excess stack consumption issue */
+	if (p_size == (size_t)-1 ||
+	    (__builtin_constant_p(p[p_size - 1]) && p[p_size - 1] == '\0'))
 		return __builtin_strlen(p);
 	ret = strnlen(p, p_size);
 	if (p_size <= ret)
diff --git a/include/linux/trace.h b/include/linux/trace.h
index d24991c1fef3..b95ffb2188ab 100644
--- a/include/linux/trace.h
+++ b/include/linux/trace.h
@@ -18,7 +18,7 @@
  */
 struct trace_export {
 	struct trace_export __rcu	*next;
-	void (*write)(const void *, unsigned int);
+	void (*write)(struct trace_export *, const void *, unsigned int);
 };
 
 int register_ftrace_export(struct trace_export *export);