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

14 files changed, 126 insertions, 43 deletions

diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h
index 277ab9af9ac2..7883e901f65c 100644
--- a/include/linux/devpts_fs.h
+++ b/include/linux/devpts_fs.h
@@ -19,7 +19,7 @@
 
 struct pts_fs_info;
 
-struct pts_fs_info *devpts_acquire(struct file *);
+struct pts_fs_info *devpts_acquire(struct file *, struct vfsmount **ptsmnt);
 void devpts_release(struct pts_fs_info *);
 
 int devpts_new_index(struct pts_fs_info *);
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 77d427974f57..bae11c7e7bf3 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -61,6 +61,7 @@ extern int memblock_debug;
 #ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
 #define __init_memblock __meminit
 #define __initdata_memblock __meminitdata
+void memblock_discard(void);
 #else
 #define __init_memblock
 #define __initdata_memblock
@@ -74,8 +75,6 @@ phys_addr_t memblock_find_in_range_node(phys_addr_t size, phys_addr_t align,
 					int nid, ulong flags);
 phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end,
 				   phys_addr_t size, phys_addr_t align);
-phys_addr_t get_allocated_memblock_reserved_regions_info(phys_addr_t *addr);
-phys_addr_t get_allocated_memblock_memory_regions_info(phys_addr_t *addr);
 void memblock_allow_resize(void);
 int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid);
 int memblock_add(phys_addr_t base, phys_addr_t size);
@@ -110,6 +109,9 @@ void __next_mem_range_rev(u64 *idx, int nid, ulong flags,
 void __next_reserved_mem_region(u64 *idx, phys_addr_t *out_start,
 				phys_addr_t *out_end);
 
+void __memblock_free_early(phys_addr_t base, phys_addr_t size);
+void __memblock_free_late(phys_addr_t base, phys_addr_t size);
+
 /**
  * for_each_mem_range - iterate through memblock areas from type_a and not
  * included in type_b. Or just type_a if type_b is NULL.
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 3914e3dd6168..9b15a4bcfa77 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -484,7 +484,8 @@ bool mem_cgroup_oom_synchronize(bool wait);
 extern int do_swap_account;
 #endif
 
-void lock_page_memcg(struct page *page);
+struct mem_cgroup *lock_page_memcg(struct page *page);
+void __unlock_page_memcg(struct mem_cgroup *memcg);
 void unlock_page_memcg(struct page *page);
 
 static inline unsigned long memcg_page_state(struct mem_cgroup *memcg,
@@ -809,7 +810,12 @@ mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 {
 }
 
-static inline void lock_page_memcg(struct page *page)
+static inline struct mem_cgroup *lock_page_memcg(struct page *page)
+{
+	return NULL;
+}
+
+static inline void __unlock_page_memcg(struct mem_cgroup *memcg)
 {
 }
 
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 8aa01fd859fb..a36abe2da13e 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -168,6 +168,14 @@ extern int sysctl_hardlockup_all_cpu_backtrace;
 #define sysctl_softlockup_all_cpu_backtrace 0
 #define sysctl_hardlockup_all_cpu_backtrace 0
 #endif
+
+#if defined(CONFIG_HARDLOCKUP_CHECK_TIMESTAMP) && \
+    defined(CONFIG_HARDLOCKUP_DETECTOR)
+void watchdog_update_hrtimer_threshold(u64 period);
+#else
+static inline void watchdog_update_hrtimer_threshold(u64 period) { }
+#endif
+
 extern bool is_hardlockup(void);
 struct ctl_table;
 extern int proc_watchdog(struct ctl_table *, int ,
diff --git a/include/linux/oom.h b/include/linux/oom.h
index 8a266e2be5a6..76aac4ce39bc 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -6,6 +6,8 @@
 #include <linux/types.h>
 #include <linux/nodemask.h>
 #include <uapi/linux/oom.h>
+#include <linux/sched/coredump.h> /* MMF_* */
+#include <linux/mm.h> /* VM_FAULT* */
 
 struct zonelist;
 struct notifier_block;
@@ -63,6 +65,26 @@ static inline bool tsk_is_oom_victim(struct task_struct * tsk)
 	return tsk->signal->oom_mm;
 }
 
+/*
+ * 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
+ * the mm. At that moment any !shared mapping would lose the content
+ * and could cause a memory corruption (zero pages instead of the
+ * original content).
+ *
+ * User should call this before establishing a page table entry for
+ * a !shared mapping and under the proper page table lock.
+ *
+ * Return 0 when the PF is safe VM_FAULT_SIGBUS otherwise.
+ */
+static inline int check_stable_address_space(struct mm_struct *mm)
+{
+	if (unlikely(test_bit(MMF_UNSTABLE, &mm->flags)))
+		return VM_FAULT_SIGBUS;
+	return 0;
+}
+
 extern unsigned long oom_badness(struct task_struct *p,
 		struct mem_cgroup *memcg, const nodemask_t *nodemask,
 		unsigned long totalpages);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index a3b873fc59e4..b14095bcf4bb 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -310,8 +310,8 @@ struct pmu {
 	 * Notification that the event was mapped or unmapped.  Called
 	 * in the context of the mapping task.
 	 */
-	void (*event_mapped)		(struct perf_event *event); /*optional*/
-	void (*event_unmapped)		(struct perf_event *event); /*optional*/
+	void (*event_mapped)		(struct perf_event *event, struct mm_struct *mm); /* optional */
+	void (*event_unmapped)		(struct perf_event *event, struct mm_struct *mm); /* optional */
 
 	/*
 	 * Flags for ->add()/->del()/ ->start()/->stop(). There are
diff --git a/include/linux/pid.h b/include/linux/pid.h
index 4d179316e431..719582744a2e 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -8,7 +8,9 @@ enum pid_type
 	PIDTYPE_PID,
 	PIDTYPE_PGID,
 	PIDTYPE_SID,
-	PIDTYPE_MAX
+	PIDTYPE_MAX,
+	/* only valid to __task_pid_nr_ns() */
+	__PIDTYPE_TGID
 };
 
 /*
diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h
index d8c97ec8a8e6..37b4bb2545b3 100644
--- a/include/linux/ptr_ring.h
+++ b/include/linux/ptr_ring.h
@@ -436,9 +436,9 @@ static inline int ptr_ring_consume_batched_bh(struct ptr_ring *r,
 	__PTR_RING_PEEK_CALL_v; \
 })
 
-static inline void **__ptr_ring_init_queue_alloc(int size, gfp_t gfp)
+static inline void **__ptr_ring_init_queue_alloc(unsigned int size, gfp_t gfp)
 {
-	return kzalloc(ALIGN(size * sizeof(void *), SMP_CACHE_BYTES), gfp);
+	return kcalloc(size, sizeof(void *), gfp);
 }
 
 static inline void __ptr_ring_set_size(struct ptr_ring *r, int size)
@@ -582,7 +582,8 @@ static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp,
  * In particular if you consume ring in interrupt or BH context, you must
  * disable interrupts/BH when doing so.
  */
-static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, int nrings,
+static inline int ptr_ring_resize_multiple(struct ptr_ring **rings,
+					   unsigned int nrings,
 					   int size,
 					   gfp_t gfp, void (*destroy)(void *))
 {
@@ -590,7 +591,7 @@ static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, int nrings,
 	void ***queues;
 	int i;
 
-	queues = kmalloc(nrings * sizeof *queues, gfp);
+	queues = kmalloc_array(nrings, sizeof(*queues), gfp);
 	if (!queues)
 		goto noqueues;
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8337e2db0bb2..c05ac5f5aa03 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1163,13 +1163,6 @@ static inline pid_t task_tgid_nr(struct task_struct *tsk)
 	return tsk->tgid;
 }
 
-extern pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);
-
-static inline pid_t task_tgid_vnr(struct task_struct *tsk)
-{
-	return pid_vnr(task_tgid(tsk));
-}
-
 /**
  * pid_alive - check that a task structure is not stale
  * @p: Task structure to be checked.
@@ -1185,23 +1178,6 @@ static inline int pid_alive(const struct task_struct *p)
 	return p->pids[PIDTYPE_PID].pid != NULL;
 }
 
-static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns)
-{
-	pid_t pid = 0;
-
-	rcu_read_lock();
-	if (pid_alive(tsk))
-		pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns);
-	rcu_read_unlock();
-
-	return pid;
-}
-
-static inline pid_t task_ppid_nr(const struct task_struct *tsk)
-{
-	return task_ppid_nr_ns(tsk, &init_pid_ns);
-}
-
 static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
 {
 	return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns);
@@ -1223,6 +1199,33 @@ static inline pid_t task_session_vnr(struct task_struct *tsk)
 	return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL);
 }
 
+static inline pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
+{
+	return __task_pid_nr_ns(tsk, __PIDTYPE_TGID, ns);
+}
+
+static inline pid_t task_tgid_vnr(struct task_struct *tsk)
+{
+	return __task_pid_nr_ns(tsk, __PIDTYPE_TGID, NULL);
+}
+
+static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns)
+{
+	pid_t pid = 0;
+
+	rcu_read_lock();
+	if (pid_alive(tsk))
+		pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns);
+	rcu_read_unlock();
+
+	return pid;
+}
+
+static inline pid_t task_ppid_nr(const struct task_struct *tsk)
+{
+	return task_ppid_nr_ns(tsk, &init_pid_ns);
+}
+
 /* Obsolete, do not use: */
 static inline pid_t task_pgrp_nr(struct task_struct *tsk)
 {
diff --git a/include/linux/skb_array.h b/include/linux/skb_array.h
index 35226cd4efb0..8621ffdeecbf 100644
--- a/include/linux/skb_array.h
+++ b/include/linux/skb_array.h
@@ -193,7 +193,8 @@ static inline int skb_array_resize(struct skb_array *a, int size, gfp_t gfp)
 }
 
 static inline int skb_array_resize_multiple(struct skb_array **rings,
-					    int nrings, int size, gfp_t gfp)
+					    int nrings, unsigned int size,
+					    gfp_t gfp)
 {
 	BUILD_BUG_ON(offsetof(struct skb_array, ring));
 	return ptr_ring_resize_multiple((struct ptr_ring **)rings,
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 5b74e36c0ca8..dc19880c02f5 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -757,6 +757,43 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_entry_t *);
 	__ret;									\
 })
 
+#define __wait_event_killable_timeout(wq_head, condition, timeout)		\
+	___wait_event(wq_head, ___wait_cond_timeout(condition),			\
+		      TASK_KILLABLE, 0, timeout,				\
+		      __ret = schedule_timeout(__ret))
+
+/**
+ * wait_event_killable_timeout - sleep until a condition gets true or a timeout elapses
+ * @wq_head: the waitqueue to wait on
+ * @condition: a C expression for the event to wait for
+ * @timeout: timeout, in jiffies
+ *
+ * The process is put to sleep (TASK_KILLABLE) until the
+ * @condition evaluates to true or a kill signal is received.
+ * The @condition is checked each time the waitqueue @wq_head is woken up.
+ *
+ * wake_up() has to be called after changing any variable that could
+ * change the result of the wait condition.
+ *
+ * Returns:
+ * 0 if the @condition evaluated to %false after the @timeout elapsed,
+ * 1 if the @condition evaluated to %true after the @timeout elapsed,
+ * the remaining jiffies (at least 1) if the @condition evaluated
+ * to %true before the @timeout elapsed, or -%ERESTARTSYS if it was
+ * interrupted by a kill signal.
+ *
+ * Only kill signals interrupt this process.
+ */
+#define wait_event_killable_timeout(wq_head, condition, timeout)		\
+({										\
+	long __ret = timeout;							\
+	might_sleep();								\
+	if (!___wait_cond_timeout(condition))					\
+		__ret = __wait_event_killable_timeout(wq_head,			\
+						condition, timeout);		\
+	__ret;									\
+})
+
 
 #define __wait_event_lock_irq(wq_head, condition, lock, cmd)			\
 	(void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
diff --git a/include/net/ip.h b/include/net/ip.h
index 39db596eb89f..9896f46cbbf1 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -362,7 +362,7 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,
 	    !forwarding)
 		return dst_mtu(dst);
 
-	return min(dst->dev->mtu, IP_MAX_MTU);
+	return min(READ_ONCE(dst->dev->mtu), IP_MAX_MTU);
 }
 
 static inline unsigned int ip_skb_dst_mtu(struct sock *sk,
@@ -374,7 +374,7 @@ static inline unsigned int ip_skb_dst_mtu(struct sock *sk,
 		return ip_dst_mtu_maybe_forward(skb_dst(skb), forwarding);
 	}
 
-	return min(skb_dst(skb)->dev->mtu, IP_MAX_MTU);
+	return min(READ_ONCE(skb_dst(skb)->dev->mtu), IP_MAX_MTU);
 }
 
 u32 ip_idents_reserve(u32 hash, int segs);
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 107c52432245..1688f0f6c7ba 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -808,8 +808,11 @@ static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new,
 	old = *pold;
 	*pold = new;
 	if (old != NULL) {
-		qdisc_tree_reduce_backlog(old, old->q.qlen, old->qstats.backlog);
+		unsigned int qlen = old->q.qlen;
+		unsigned int backlog = old->qstats.backlog;
+
 		qdisc_reset(old);
+		qdisc_tree_reduce_backlog(old, qlen, backlog);
 	}
 	sch_tree_unlock(sch);
 
diff --git a/include/net/sock.h b/include/net/sock.h
index fe1a0bc25cd3..1c2912d433e8 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -509,9 +509,7 @@ int sk_set_peek_off(struct sock *sk, int val);
 static inline int sk_peek_offset(struct sock *sk, int flags)
 {
 	if (unlikely(flags & MSG_PEEK)) {
-		s32 off = READ_ONCE(sk->sk_peek_off);
-		if (off >= 0)
-			return off;
+		return READ_ONCE(sk->sk_peek_off);
 	}
 
 	return 0;