Merge branch 'linus' into x86/asm, to pick up recent fixes

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

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/events/core.c

@@ -2496,11 +2496,11 @@ static int __perf_event_stop(void *info)
 	return 0;
 }
 
-static int perf_event_restart(struct perf_event *event)
+static int perf_event_stop(struct perf_event *event, int restart)
 {
 	struct stop_event_data sd = {
 		.event		= event,
-		.restart	= 1,
+		.restart	= restart,
 	};
 	int ret = 0;
 
@@ -3549,10 +3549,18 @@ static int perf_event_read(struct perf_event *event, bool group)
 			.group = group,
 			.ret = 0,
 		};
-		ret = smp_call_function_single(event->oncpu, __perf_event_read, &data, 1);
-		/* The event must have been read from an online CPU: */
-		WARN_ON_ONCE(ret);
-		ret = ret ? : data.ret;
+		/*
+		 * Purposely ignore the smp_call_function_single() return
+		 * value.
+		 *
+		 * If event->oncpu isn't a valid CPU it means the event got
+		 * scheduled out and that will have updated the event count.
+		 *
+		 * Therefore, either way, we'll have an up-to-date event count
+		 * after this.
+		 */
+		(void)smp_call_function_single(event->oncpu, __perf_event_read, &data, 1);
+		ret = data.ret;
 	} else if (event->state == PERF_EVENT_STATE_INACTIVE) {
 		struct perf_event_context *ctx = event->ctx;
 		unsigned long flags;
@@ -4837,6 +4845,19 @@ static void ring_buffer_attach(struct perf_event *event,
 		spin_unlock_irqrestore(&rb->event_lock, flags);
 	}
 
+	/*
+	 * Avoid racing with perf_mmap_close(AUX): stop the event
+	 * before swizzling the event::rb pointer; if it's getting
+	 * unmapped, its aux_mmap_count will be 0 and it won't
+	 * restart. See the comment in __perf_pmu_output_stop().
+	 *
+	 * Data will inevitably be lost when set_output is done in
+	 * mid-air, but then again, whoever does it like this is
+	 * not in for the data anyway.
+	 */
+	if (has_aux(event))
+		perf_event_stop(event, 0);
+
 	rcu_assign_pointer(event->rb, rb);
 
 	if (old_rb) {
@@ -6112,7 +6133,7 @@ static void perf_event_addr_filters_exec(struct perf_event *event, void *data)
 	raw_spin_unlock_irqrestore(&ifh->lock, flags);
 
 	if (restart)
-		perf_event_restart(event);
+		perf_event_stop(event, 1);
 }
 
 void perf_event_exec(void)
@@ -6156,7 +6177,13 @@ static void __perf_event_output_stop(struct perf_event *event, void *data)
 
 	/*
 	 * In case of inheritance, it will be the parent that links to the
-	 * ring-buffer, but it will be the child that's actually using it:
+	 * ring-buffer, but it will be the child that's actually using it.
+	 *
+	 * We are using event::rb to determine if the event should be stopped,
+	 * however this may race with ring_buffer_attach() (through set_output),
+	 * which will make us skip the event that actually needs to be stopped.
+	 * So ring_buffer_attach() has to stop an aux event before re-assigning
+	 * its rb pointer.
 	 */
 	if (rcu_dereference(parent->rb) == rb)
 		ro->err = __perf_event_stop(&sd);
@@ -6166,7 +6193,7 @@ static int __perf_pmu_output_stop(void *info)
 {
 	struct perf_event *event = info;
 	struct pmu *pmu = event->pmu;
-	struct perf_cpu_context *cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
 	struct remote_output ro = {
 		.rb	= event->rb,
 	};
@@ -6670,7 +6697,7 @@ static void __perf_addr_filters_adjust(struct perf_event *event, void *data)
 	raw_spin_unlock_irqrestore(&ifh->lock, flags);
 
 	if (restart)
-		perf_event_restart(event);
+		perf_event_stop(event, 1);
 }
 
 /*
@@ -7859,7 +7886,7 @@ static void perf_event_addr_filters_apply(struct perf_event *event)
 	mmput(mm);
 
 restart:
-	perf_event_restart(event);
+	perf_event_stop(event, 1);
 }
 
 /*

kernel/events/ring_buffer.c

@@ -330,15 +330,22 @@ void *perf_aux_output_begin(struct perf_output_handle *handle,
 	if (!rb)
 		return NULL;
 
-	if (!rb_has_aux(rb) || !atomic_inc_not_zero(&rb->aux_refcount))
+	if (!rb_has_aux(rb))
 		goto err;
 
 	/*
-	 * If rb::aux_mmap_count is zero (and rb_has_aux() above went through),
-	 * the aux buffer is in perf_mmap_close(), about to get freed.
+	 * If aux_mmap_count is zero, the aux buffer is in perf_mmap_close(),
+	 * about to get freed, so we leave immediately.
+	 *
+	 * Checking rb::aux_mmap_count and rb::refcount has to be done in
+	 * the same order, see perf_mmap_close. Otherwise we end up freeing
+	 * aux pages in this path, which is a bug, because in_atomic().
 	 */
 	if (!atomic_read(&rb->aux_mmap_count))
-		goto err_put;
+		goto err;
+
+	if (!atomic_inc_not_zero(&rb->aux_refcount))
+		goto err;
 
 	/*
 	 * Nesting is not supported for AUX area, make sure nested

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

@@ -854,6 +854,29 @@ 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
  *
@@ -969,14 +992,12 @@ 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
@@ -1460,7 +1481,6 @@ 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);
@@ -1612,6 +1632,7 @@ 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
@@ -1712,6 +1733,7 @@ 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:
@@ -1744,7 +1766,6 @@ 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/irq/affinity.c

@@ -39,6 +39,7 @@ struct cpumask *irq_create_affinity_mask(unsigned int *nr_vecs)
 		return NULL;
 	}
 
+	get_online_cpus();
 	if (max_vecs >= num_online_cpus()) {
 		cpumask_copy(affinity_mask, cpu_online_mask);
 		*nr_vecs = num_online_cpus();
@@ -56,6 +57,7 @@ struct cpumask *irq_create_affinity_mask(unsigned int *nr_vecs)
 		}
 		*nr_vecs = vecs;
 	}
+	put_online_cpus();
 
 	return affinity_mask;
 }

kernel/irq/chip.c

@@ -820,6 +820,17 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle,
 	desc->name = name;
 
 	if (handle != handle_bad_irq && is_chained) {
+		/*
+		 * We're about to start this interrupt immediately,
+		 * hence the need to set the trigger configuration.
+		 * But the .set_type callback may have overridden the
+		 * flow handler, ignoring that we're dealing with a
+		 * chained interrupt. Reset it immediately because we
+		 * do know better.
+		 */
+		__irq_set_trigger(desc, irqd_get_trigger_type(&desc->irq_data));
+		desc->handle_irq = handle;
+
 		irq_settings_set_noprobe(desc);
 		irq_settings_set_norequest(desc);
 		irq_settings_set_nothread(desc);

kernel/irq/manage.c

@@ -1681,8 +1681,10 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
 	action->dev_id = dev_id;
 
 	retval = irq_chip_pm_get(&desc->irq_data);
-	if (retval < 0)
+	if (retval < 0) {
+		kfree(action);
 		return retval;
+	}
 
 	chip_bus_lock(desc);
 	retval = __setup_irq(irq, desc, action);
@@ -1985,8 +1987,10 @@ int request_percpu_irq(unsigned int irq, irq_handler_t handler,
 	action->percpu_dev_id = dev_id;
 
 	retval = irq_chip_pm_get(&desc->irq_data);
-	if (retval < 0)
+	if (retval < 0) {
+		kfree(action);
 		return retval;
+	}
 
 	chip_bus_lock(desc);
 	retval = __setup_irq(irq, desc, action);

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/braille.c

@@ -9,10 +9,10 @@
 
 char *_braille_console_setup(char **str, char **brl_options)
 {
-	if (!memcmp(*str, "brl,", 4)) {
+	if (!strncmp(*str, "brl,", 4)) {
 		*brl_options = "";
 		*str += 4;
-	} else if (!memcmp(str, "brl=", 4)) {
+	} else if (!strncmp(*str, "brl=", 4)) {
 		*brl_options = *str + 4;
 		*str = strchr(*brl_options, ',');
 		if (!*str)

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/sched/core.c

@@ -2016,6 +2016,28 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	success = 1; /* we're going to change ->state */
 	cpu = task_cpu(p);
 
+	/*
+	 * Ensure we load p->on_rq _after_ p->state, otherwise it would
+	 * be possible to, falsely, observe p->on_rq == 0 and get stuck
+	 * in smp_cond_load_acquire() below.
+	 *
+	 * sched_ttwu_pending()                 try_to_wake_up()
+	 *   [S] p->on_rq = 1;                  [L] P->state
+	 *       UNLOCK rq->lock  -----.
+	 *                              \
+	 *				 +---   RMB
+	 * schedule()                   /
+	 *       LOCK rq->lock    -----'
+	 *       UNLOCK rq->lock
+	 *
+	 * [task p]
+	 *   [S] p->state = UNINTERRUPTIBLE     [L] p->on_rq
+	 *
+	 * Pairs with the UNLOCK+LOCK on rq->lock from the
+	 * last wakeup of our task and the schedule that got our task
+	 * current.
+	 */
+	smp_rmb();
 	if (p->on_rq && ttwu_remote(p, wake_flags))
 		goto stat;
 

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/sysctl.c

@@ -2140,6 +2140,21 @@ static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp,
 	return 0;
 }
 
+static int do_proc_douintvec_conv(bool *negp, unsigned long *lvalp,
+				 int *valp,
+				 int write, void *data)
+{
+	if (write) {
+		if (*negp)
+			return -EINVAL;
+		*valp = *lvalp;
+	} else {
+		unsigned int val = *valp;
+		*lvalp = (unsigned long)val;
+	}
+	return 0;
+}
+
 static const char proc_wspace_sep[] = { ' ', '\t', '\n' };
 
 static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
@@ -2259,8 +2274,27 @@ static int do_proc_dointvec(struct ctl_table *table, int write,
 int proc_dointvec(struct ctl_table *table, int write,
 		     void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-    return do_proc_dointvec(table,write,buffer,lenp,ppos,
-		    	    NULL,NULL);
+	return do_proc_dointvec(table, write, buffer, lenp, ppos, NULL, NULL);
+}
+
+/**
+ * proc_douintvec - read a vector of unsigned integers
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned int) unsigned integer
+ * values from/to the user buffer, treated as an ASCII string.
+ *
+ * Returns 0 on success.
+ */
+int proc_douintvec(struct ctl_table *table, int write,
+		     void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	return do_proc_dointvec(table, write, buffer, lenp, ppos,
+				do_proc_douintvec_conv, NULL);
 }
 
 /*
@@ -2858,6 +2892,12 @@ int proc_dointvec(struct ctl_table *table, int write,
 	return -ENOSYS;
 }
 
+int proc_douintvec(struct ctl_table *table, int write,
+		  void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	return -ENOSYS;
+}
+
 int proc_dointvec_minmax(struct ctl_table *table, int write,
 		    void __user *buffer, size_t *lenp, loff_t *ppos)
 {
@@ -2903,6 +2943,7 @@ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
  * exception granted :-)
  */
 EXPORT_SYMBOL(proc_dointvec);
+EXPORT_SYMBOL(proc_douintvec);
 EXPORT_SYMBOL(proc_dointvec_jiffies);
 EXPORT_SYMBOL(proc_dointvec_minmax);
 EXPORT_SYMBOL(proc_dointvec_userhz_jiffies);

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);

kernel/time/timekeeping.c

@@ -401,7 +401,10 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf)
 	do {
 		seq = raw_read_seqcount_latch(&tkf->seq);
 		tkr = tkf->base + (seq & 0x01);
-		now = ktime_to_ns(tkr->base) + timekeeping_get_ns(tkr);
+		now = ktime_to_ns(tkr->base);
+
+		now += clocksource_delta(tkr->read(tkr->clock),
+					 tkr->cycle_last, tkr->mask);
 	} while (read_seqcount_retry(&tkf->seq, seq));
 
 	return now;

kernel/time/timekeeping_debug.c

@@ -23,7 +23,9 @@
 
 #include "timekeeping_internal.h"
 
-static unsigned int sleep_time_bin[32] = {0};
+#define NUM_BINS 32
+
+static unsigned int sleep_time_bin[NUM_BINS] = {0};
 
 static int tk_debug_show_sleep_time(struct seq_file *s, void *data)
 {
@@ -69,6 +71,9 @@ late_initcall(tk_debug_sleep_time_init);
 
 void tk_debug_account_sleep_time(struct timespec64 *t)
 {
-	sleep_time_bin[fls(t->tv_sec)]++;
+	/* Cap bin index so we don't overflow the array */
+	int bin = min(fls(t->tv_sec), NUM_BINS-1);
+
+	sleep_time_bin[bin]++;
 }
 

kernel/trace/blktrace.c

@@ -223,7 +223,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	what |= MASK_TC_BIT(op_flags, META);
 	what |= MASK_TC_BIT(op_flags, PREFLUSH);
 	what |= MASK_TC_BIT(op_flags, FUA);
-	if (op == REQ_OP_DISCARD)
+	if (op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE)
 		what |= BLK_TC_ACT(BLK_TC_DISCARD);
 	if (op == REQ_OP_FLUSH)
 		what |= BLK_TC_ACT(BLK_TC_FLUSH);