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

Conflicts:
	drivers/net/ethernet/mediatek/mtk_eth_soc.c
	drivers/net/ethernet/qlogic/qed/qed_dcbx.c
	drivers/net/phy/Kconfig

All conflicts were cases of overlapping commits.

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

kernel/audit_watch.c

@@ -19,6 +19,7 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
+#include <linux/file.h>
 #include <linux/kernel.h>
 #include <linux/audit.h>
 #include <linux/kthread.h>
@@ -544,10 +545,11 @@ int audit_exe_compare(struct task_struct *tsk, struct audit_fsnotify_mark *mark)
 	unsigned long ino;
 	dev_t dev;
 
-	rcu_read_lock();
-	exe_file = rcu_dereference(tsk->mm->exe_file);
+	exe_file = get_task_exe_file(tsk);
+	if (!exe_file)
+		return 0;
 	ino = exe_file->f_inode->i_ino;
 	dev = exe_file->f_inode->i_sb->s_dev;
-	rcu_read_unlock();
+	fput(exe_file);
 	return audit_mark_compare(mark, ino, dev);
 }

kernel/configs/tiny.config

@@ -1,4 +1,12 @@
+# CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE is not set
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+# CONFIG_KERNEL_GZIP is not set
+# CONFIG_KERNEL_BZIP2 is not set
+# CONFIG_KERNEL_LZMA is not set
 CONFIG_KERNEL_XZ=y
+# CONFIG_KERNEL_LZO is not set
+# CONFIG_KERNEL_LZ4 is not set
 CONFIG_OPTIMIZE_INLINING=y
+# CONFIG_SLAB is not set
+# CONFIG_SLUB is not set
 CONFIG_SLOB=y

kernel/cpuset.c

@@ -2069,6 +2069,20 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css)
 	mutex_unlock(&cpuset_mutex);
 }
 
+/*
+ * Make sure the new task conform to the current state of its parent,
+ * which could have been changed by cpuset just after it inherits the
+ * state from the parent and before it sits on the cgroup's task list.
+ */
+void cpuset_fork(struct task_struct *task)
+{
+	if (task_css_is_root(task, cpuset_cgrp_id))
+		return;
+
+	set_cpus_allowed_ptr(task, &current->cpus_allowed);
+	task->mems_allowed = current->mems_allowed;
+}
+
 struct cgroup_subsys cpuset_cgrp_subsys = {
 	.css_alloc	= cpuset_css_alloc,
 	.css_online	= cpuset_css_online,
@@ -2079,6 +2093,7 @@ struct cgroup_subsys cpuset_cgrp_subsys = {
 	.attach		= cpuset_attach,
 	.post_attach	= cpuset_post_attach,
 	.bind		= cpuset_bind,
+	.fork		= cpuset_fork,
 	.legacy_cftypes	= files,
 	.early_init	= true,
 };

kernel/exit.c

@@ -848,12 +848,7 @@ void do_exit(long code)
 	TASKS_RCU(preempt_enable());
 	exit_notify(tsk, group_dead);
 	proc_exit_connector(tsk);
-#ifdef CONFIG_NUMA
-	task_lock(tsk);
-	mpol_put(tsk->mempolicy);
-	tsk->mempolicy = NULL;
-	task_unlock(tsk);
-#endif
+	mpol_put_task_policy(tsk);
 #ifdef CONFIG_FUTEX
 	if (unlikely(current->pi_state_cache))
 		kfree(current->pi_state_cache);

kernel/fork.c

@@ -798,6 +798,29 @@ struct file *get_mm_exe_file(struct mm_struct *mm)
 }
 EXPORT_SYMBOL(get_mm_exe_file);
 
+/**
+ * get_task_exe_file - acquire a reference to the task's executable file
+ *
+ * Returns %NULL if task's mm (if any) has no associated executable file or
+ * this is a kernel thread with borrowed mm (see the comment above get_task_mm).
+ * User must release file via fput().
+ */
+struct file *get_task_exe_file(struct task_struct *task)
+{
+	struct file *exe_file = NULL;
+	struct mm_struct *mm;
+
+	task_lock(task);
+	mm = task->mm;
+	if (mm) {
+		if (!(task->flags & PF_KTHREAD))
+			exe_file = get_mm_exe_file(mm);
+	}
+	task_unlock(task);
+	return exe_file;
+}
+EXPORT_SYMBOL(get_task_exe_file);
+
 /**
  * get_task_mm - acquire a reference to the task's mm
  *
@@ -913,14 +936,12 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
 	deactivate_mm(tsk, mm);
 
 	/*
-	 * If we're exiting normally, clear a user-space tid field if
-	 * requested.  We leave this alone when dying by signal, to leave
-	 * the value intact in a core dump, and to save the unnecessary
-	 * trouble, say, a killed vfork parent shouldn't touch this mm.
-	 * Userland only wants this done for a sys_exit.
+	 * Signal userspace if we're not exiting with a core dump
+	 * because we want to leave the value intact for debugging
+	 * purposes.
 	 */
 	if (tsk->clear_child_tid) {
-		if (!(tsk->flags & PF_SIGNALED) &&
+		if (!(tsk->signal->flags & SIGNAL_GROUP_COREDUMP) &&
 		    atomic_read(&mm->mm_users) > 1) {
 			/*
 			 * We don't check the error code - if userspace has
@@ -1404,7 +1425,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->real_start_time = ktime_get_boot_ns();
 	p->io_context = NULL;
 	p->audit_context = NULL;
-	threadgroup_change_begin(current);
 	cgroup_fork(p);
 #ifdef CONFIG_NUMA
 	p->mempolicy = mpol_dup(p->mempolicy);
@@ -1556,6 +1576,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	INIT_LIST_HEAD(&p->thread_group);
 	p->task_works = NULL;
 
+	threadgroup_change_begin(current);
 	/*
 	 * Ensure that the cgroup subsystem policies allow the new process to be
 	 * forked. It should be noted the the new process's css_set can be changed
@@ -1656,6 +1677,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 bad_fork_cancel_cgroup:
 	cgroup_cancel_fork(p);
 bad_fork_free_pid:
+	threadgroup_change_end(current);
 	if (pid != &init_struct_pid)
 		free_pid(pid);
 bad_fork_cleanup_thread:
@@ -1688,7 +1710,6 @@ bad_fork_cleanup_policy:
 	mpol_put(p->mempolicy);
 bad_fork_cleanup_threadgroup_lock:
 #endif
-	threadgroup_change_end(current);
 	delayacct_tsk_free(p);
 bad_fork_cleanup_count:
 	atomic_dec(&p->cred->user->processes);

kernel/kexec_file.c

@@ -887,7 +887,10 @@ int kexec_load_purgatory(struct kimage *image, unsigned long min,
 	return 0;
 out:
 	vfree(pi->sechdrs);
+	pi->sechdrs = NULL;
+
 	vfree(pi->purgatory_buf);
+	pi->purgatory_buf = NULL;
 	return ret;
 }
 

kernel/memremap.c

@@ -247,6 +247,7 @@ static void devm_memremap_pages_release(struct device *dev, void *data)
 	align_start = res->start & ~(SECTION_SIZE - 1);
 	align_size = ALIGN(resource_size(res), SECTION_SIZE);
 	arch_remove_memory(align_start, align_size);
+	untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
 	pgmap_radix_release(res);
 	dev_WARN_ONCE(dev, pgmap->altmap && pgmap->altmap->alloc,
 			"%s: failed to free all reserved pages\n", __func__);
@@ -282,6 +283,7 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 		struct percpu_ref *ref, struct vmem_altmap *altmap)
 {
 	resource_size_t key, align_start, align_size, align_end;
+	pgprot_t pgprot = PAGE_KERNEL;
 	struct dev_pagemap *pgmap;
 	struct page_map *page_map;
 	int error, nid, is_ram;
@@ -351,6 +353,11 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 	if (nid < 0)
 		nid = numa_mem_id();
 
+	error = track_pfn_remap(NULL, &pgprot, PHYS_PFN(align_start), 0,
+			align_size);
+	if (error)
+		goto err_pfn_remap;
+
 	error = arch_add_memory(nid, align_start, align_size, true);
 	if (error)
 		goto err_add_memory;
@@ -371,6 +378,8 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 	return __va(res->start);
 
  err_add_memory:
+	untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
+ err_pfn_remap:
  err_radix:
 	pgmap_radix_release(res);
 	devres_free(page_map);

kernel/power/qos.c

@@ -482,7 +482,16 @@ void pm_qos_update_request(struct pm_qos_request *req,
 		return;
 	}
 
-	cancel_delayed_work_sync(&req->work);
+	/*
+	 * This function may be called very early during boot, for example,
+	 * from of_clk_init(), where irq needs to stay disabled.
+	 * cancel_delayed_work_sync() assumes that irq is enabled on
+	 * invocation and re-enables it on return.  Avoid calling it until
+	 * workqueue is initialized.
+	 */
+	if (keventd_up())
+		cancel_delayed_work_sync(&req->work);
+
 	__pm_qos_update_request(req, new_value);
 }
 EXPORT_SYMBOL_GPL(pm_qos_update_request);

kernel/printk/nmi.c

@@ -99,26 +99,32 @@ again:
 	return add;
 }
 
-/*
- * printk one line from the temporary buffer from @start index until
- * and including the @end index.
- */
-static void print_nmi_seq_line(struct nmi_seq_buf *s, int start, int end)
+static void printk_nmi_flush_line(const char *text, int len)
 {
-	const char *buf = s->buffer + start;
-
 	/*
 	 * The buffers are flushed in NMI only on panic.  The messages must
 	 * go only into the ring buffer at this stage.  Consoles will get
 	 * explicitly called later when a crashdump is not generated.
 	 */
 	if (in_nmi())
-		printk_deferred("%.*s", (end - start) + 1, buf);
+		printk_deferred("%.*s", len, text);
 	else
-		printk("%.*s", (end - start) + 1, buf);
+		printk("%.*s", len, text);
 
 }
 
+/*
+ * printk one line from the temporary buffer from @start index until
+ * and including the @end index.
+ */
+static void printk_nmi_flush_seq_line(struct nmi_seq_buf *s,
+					int start, int end)
+{
+	const char *buf = s->buffer + start;
+
+	printk_nmi_flush_line(buf, (end - start) + 1);
+}
+
 /*
  * Flush data from the associated per_CPU buffer. The function
  * can be called either via IRQ work or independently.
@@ -150,9 +156,11 @@ more:
 	 * the buffer an unexpected way. If we printed something then
 	 * @len must only increase.
 	 */
-	if (i && i >= len)
-		pr_err("printk_nmi_flush: internal error: i=%d >= len=%zu\n",
-		       i, len);
+	if (i && i >= len) {
+		const char *msg = "printk_nmi_flush: internal error\n";
+
+		printk_nmi_flush_line(msg, strlen(msg));
+	}
 
 	if (!len)
 		goto out; /* Someone else has already flushed the buffer. */
@@ -166,14 +174,14 @@ more:
 	/* Print line by line. */
 	for (; i < size; i++) {
 		if (s->buffer[i] == '\n') {
-			print_nmi_seq_line(s, last_i, i);
+			printk_nmi_flush_seq_line(s, last_i, i);
 			last_i = i + 1;
 		}
 	}
 	/* Check if there was a partial line. */
 	if (last_i < size) {
-		print_nmi_seq_line(s, last_i, size - 1);
-		pr_cont("\n");
+		printk_nmi_flush_seq_line(s, last_i, size - 1);
+		printk_nmi_flush_line("\n", strlen("\n"));
 	}
 
 	/*

kernel/seccomp.c

@@ -605,12 +605,16 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
 		ptrace_event(PTRACE_EVENT_SECCOMP, data);
 		/*
 		 * The delivery of a fatal signal during event
-		 * notification may silently skip tracer notification.
-		 * Terminating the task now avoids executing a system
-		 * call that may not be intended.
+		 * notification may silently skip tracer notification,
+		 * which could leave us with a potentially unmodified
+		 * syscall that the tracer would have liked to have
+		 * changed. Since the process is about to die, we just
+		 * force the syscall to be skipped and let the signal
+		 * kill the process and correctly handle any tracer exit
+		 * notifications.
 		 */
 		if (fatal_signal_pending(current))
-			do_exit(SIGSYS);
+			goto skip;
 		/* Check if the tracer forced the syscall to be skipped. */
 		this_syscall = syscall_get_nr(current, task_pt_regs(current));
 		if (this_syscall < 0)

kernel/time/tick-sched.c

@@ -908,10 +908,11 @@ static void __tick_nohz_idle_enter(struct tick_sched *ts)
 	ktime_t now, expires;
 	int cpu = smp_processor_id();
 
+	now = tick_nohz_start_idle(ts);
+
 	if (can_stop_idle_tick(cpu, ts)) {
 		int was_stopped = ts->tick_stopped;
 
-		now = tick_nohz_start_idle(ts);
 		ts->idle_calls++;
 
 		expires = tick_nohz_stop_sched_tick(ts, now, cpu);