Merge tag 'v5.2' into perf/core, to pick up fixes

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

kernel/cpu.c

@@ -1964,6 +1964,9 @@ static ssize_t write_cpuhp_fail(struct device *dev,
 	if (ret)
 		return ret;
 
+	if (fail < CPUHP_OFFLINE || fail > CPUHP_ONLINE)
+		return -EINVAL;
+
 	/*
 	 * Cannot fail STARTING/DYING callbacks.
 	 */
@@ -2339,6 +2342,9 @@ static int __init mitigations_parse_cmdline(char *arg)
 		cpu_mitigations = CPU_MITIGATIONS_AUTO;
 	else if (!strcmp(arg, "auto,nosmt"))
 		cpu_mitigations = CPU_MITIGATIONS_AUTO_NOSMT;
+	else
+		pr_crit("Unsupported mitigations=%s, system may still be vulnerable\n",
+			arg);
 
 	return 0;
 }

kernel/events/core.c

@@ -5007,6 +5007,9 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
 	if (perf_event_check_period(event, value))
 		return -EINVAL;
 
+	if (!event->attr.freq && (value & (1ULL << 63)))
+		return -EINVAL;
+
 	event_function_call(event, __perf_event_period, &value);
 
 	return 0;
@@ -5925,7 +5928,7 @@ static void perf_sample_regs_user(struct perf_regs *regs_user,
 	if (user_mode(regs)) {
 		regs_user->abi = perf_reg_abi(current);
 		regs_user->regs = regs;
-	} else if (current->mm) {
+	} else if (!(current->flags & PF_KTHREAD)) {
 		perf_get_regs_user(regs_user, regs, regs_user_copy);
 	} else {
 		regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
@@ -10041,6 +10044,12 @@ void perf_pmu_unregister(struct pmu *pmu)
 }
 EXPORT_SYMBOL_GPL(perf_pmu_unregister);
 
+static inline bool has_extended_regs(struct perf_event *event)
+{
+	return (event->attr.sample_regs_user & PERF_REG_EXTENDED_MASK) ||
+	       (event->attr.sample_regs_intr & PERF_REG_EXTENDED_MASK);
+}
+
 static int perf_try_init_event(struct pmu *pmu, struct perf_event *event)
 {
 	struct perf_event_context *ctx = NULL;
@@ -10072,12 +10081,16 @@ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event)
 		perf_event_ctx_unlock(event->group_leader, ctx);
 
 	if (!ret) {
+		if (!(pmu->capabilities & PERF_PMU_CAP_EXTENDED_REGS) &&
+		    has_extended_regs(event))
+			ret = -EOPNOTSUPP;
+
 		if (pmu->capabilities & PERF_PMU_CAP_NO_EXCLUDE &&
-				event_has_any_exclude_flag(event)) {
-			if (event->destroy)
-				event->destroy(event);
+		    event_has_any_exclude_flag(event))
 			ret = -EINVAL;
-		}
+
+		if (ret && event->destroy)
+			event->destroy(event);
 	}
 
 	if (ret)

kernel/fork.c

@@ -248,7 +248,11 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
 	struct page *page = alloc_pages_node(node, THREADINFO_GFP,
 					     THREAD_SIZE_ORDER);
 
-	return page ? page_address(page) : NULL;
+	if (likely(page)) {
+		tsk->stack = page_address(page);
+		return tsk->stack;
+	}
+	return NULL;
 #endif
 }
 
@@ -1712,31 +1716,6 @@ const struct file_operations pidfd_fops = {
 #endif
 };
 
-/**
- * pidfd_create() - Create a new pid file descriptor.
- *
- * @pid:  struct pid that the pidfd will reference
- *
- * This creates a new pid file descriptor with the O_CLOEXEC flag set.
- *
- * Note, that this function can only be called after the fd table has
- * been unshared to avoid leaking the pidfd to the new process.
- *
- * Return: On success, a cloexec pidfd is returned.
- *         On error, a negative errno number will be returned.
- */
-static int pidfd_create(struct pid *pid)
-{
-	int fd;
-
-	fd = anon_inode_getfd("[pidfd]", &pidfd_fops, get_pid(pid),
-			      O_RDWR | O_CLOEXEC);
-	if (fd < 0)
-		put_pid(pid);
-
-	return fd;
-}
-
 static void __delayed_free_task(struct rcu_head *rhp)
 {
 	struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
@@ -1774,6 +1753,7 @@ static __latent_entropy struct task_struct *copy_process(
 	int pidfd = -1, retval;
 	struct task_struct *p;
 	struct multiprocess_signals delayed;
+	struct file *pidfile = NULL;
 
 	/*
 	 * Don't allow sharing the root directory with processes in a different
@@ -1822,8 +1802,6 @@ static __latent_entropy struct task_struct *copy_process(
 	}
 
 	if (clone_flags & CLONE_PIDFD) {
-		int reserved;
-
 		/*
 		 * - CLONE_PARENT_SETTID is useless for pidfds and also
 		 *   parent_tidptr is used to return pidfds.
@@ -1834,16 +1812,6 @@ static __latent_entropy struct task_struct *copy_process(
 		if (clone_flags &
 		    (CLONE_DETACHED | CLONE_PARENT_SETTID | CLONE_THREAD))
 			return ERR_PTR(-EINVAL);
-
-		/*
-		 * Verify that parent_tidptr is sane so we can potentially
-		 * reuse it later.
-		 */
-		if (get_user(reserved, parent_tidptr))
-			return ERR_PTR(-EFAULT);
-
-		if (reserved != 0)
-			return ERR_PTR(-EINVAL);
 	}
 
 	/*
@@ -2058,11 +2026,21 @@ static __latent_entropy struct task_struct *copy_process(
 	 * if the fd table isn't shared).
 	 */
 	if (clone_flags & CLONE_PIDFD) {
-		retval = pidfd_create(pid);
+		retval = get_unused_fd_flags(O_RDWR | O_CLOEXEC);
 		if (retval < 0)
 			goto bad_fork_free_pid;
 
 		pidfd = retval;
+
+		pidfile = anon_inode_getfile("[pidfd]", &pidfd_fops, pid,
+					      O_RDWR | O_CLOEXEC);
+		if (IS_ERR(pidfile)) {
+			put_unused_fd(pidfd);
+			retval = PTR_ERR(pidfile);
+			goto bad_fork_free_pid;
+		}
+		get_pid(pid);	/* held by pidfile now */
+
 		retval = put_user(pidfd, parent_tidptr);
 		if (retval)
 			goto bad_fork_put_pidfd;
@@ -2180,6 +2158,9 @@ static __latent_entropy struct task_struct *copy_process(
 		goto bad_fork_cancel_cgroup;
 	}
 
+	/* past the last point of failure */
+	if (pidfile)
+		fd_install(pidfd, pidfile);
 
 	init_task_pid_links(p);
 	if (likely(p->pid)) {
@@ -2246,8 +2227,10 @@ bad_fork_cancel_cgroup:
 bad_fork_cgroup_threadgroup_change_end:
 	cgroup_threadgroup_change_end(current);
 bad_fork_put_pidfd:
-	if (clone_flags & CLONE_PIDFD)
-		ksys_close(pidfd);
+	if (clone_flags & CLONE_PIDFD) {
+		fput(pidfile);
+		put_unused_fd(pidfd);
+	}
 bad_fork_free_pid:
 	if (pid != &init_struct_pid)
 		free_pid(pid);

kernel/power/suspend.c

@@ -493,6 +493,9 @@ int suspend_devices_and_enter(suspend_state_t state)
 
 	pm_suspend_target_state = state;
 
+	if (state == PM_SUSPEND_TO_IDLE)
+		pm_set_suspend_no_platform();
+
 	error = platform_suspend_begin(state);
 	if (error)
 		goto Close;

kernel/ptrace.c

@@ -79,9 +79,7 @@ void __ptrace_link(struct task_struct *child, struct task_struct *new_parent,
  */
 static void ptrace_link(struct task_struct *child, struct task_struct *new_parent)
 {
-	rcu_read_lock();
-	__ptrace_link(child, new_parent, __task_cred(new_parent));
-	rcu_read_unlock();
+	__ptrace_link(child, new_parent, current_cred());
 }
 
 /**

kernel/signal.c

@@ -2912,7 +2912,8 @@ EXPORT_SYMBOL(set_compat_user_sigmask);
  * This is useful for syscalls such as ppoll, pselect, io_pgetevents and
  * epoll_pwait where a new sigmask is passed in from userland for the syscalls.
  */
-void restore_user_sigmask(const void __user *usigmask, sigset_t *sigsaved)
+void restore_user_sigmask(const void __user *usigmask, sigset_t *sigsaved,
+				bool interrupted)
 {
 
 	if (!usigmask)
@@ -2922,7 +2923,7 @@ void restore_user_sigmask(const void __user *usigmask, sigset_t *sigsaved)
 	 * Restoring sigmask here can lead to delivering signals that the above
 	 * syscalls are intended to block because of the sigmask passed in.
 	 */
-	if (signal_pending(current)) {
+	if (interrupted) {
 		current->saved_sigmask = *sigsaved;
 		set_restore_sigmask();
 		return;

kernel/trace/ftrace.c

@@ -34,7 +34,6 @@
 #include <linux/hash.h>
 #include <linux/rcupdate.h>
 #include <linux/kprobes.h>
-#include <linux/memory.h>
 
 #include <trace/events/sched.h>
 
@@ -2611,12 +2610,10 @@ static void ftrace_run_update_code(int command)
 {
 	int ret;
 
-	mutex_lock(&text_mutex);
-
 	ret = ftrace_arch_code_modify_prepare();
 	FTRACE_WARN_ON(ret);
 	if (ret)
-		goto out_unlock;
+		return;
 
 	/*
 	 * By default we use stop_machine() to modify the code.
@@ -2628,9 +2625,6 @@ static void ftrace_run_update_code(int command)
 
 	ret = ftrace_arch_code_modify_post_process();
 	FTRACE_WARN_ON(ret);
-
-out_unlock:
-	mutex_unlock(&text_mutex);
 }
 
 static void ftrace_run_modify_code(struct ftrace_ops *ops, int command,
@@ -5784,7 +5778,6 @@ void ftrace_module_enable(struct module *mod)
 	struct ftrace_page *pg;
 
 	mutex_lock(&ftrace_lock);
-	mutex_lock(&text_mutex);
 
 	if (ftrace_disabled)
 		goto out_unlock;
@@ -5846,7 +5839,6 @@ void ftrace_module_enable(struct module *mod)
 		ftrace_arch_code_modify_post_process();
 
  out_unlock:
-	mutex_unlock(&text_mutex);
 	mutex_unlock(&ftrace_lock);
 
 	process_cached_mods(mod->name);

kernel/trace/trace.c

@@ -6719,11 +6719,13 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt,
 			break;
 		}
 #endif
-		if (!tr->allocated_snapshot) {
+		if (tr->allocated_snapshot)
+			ret = resize_buffer_duplicate_size(&tr->max_buffer,
+					&tr->trace_buffer, iter->cpu_file);
+		else
 			ret = tracing_alloc_snapshot_instance(tr);
-			if (ret < 0)
-				break;
-		}
+		if (ret < 0)
+			break;
 		local_irq_disable();
 		/* Now, we're going to swap */
 		if (iter->cpu_file == RING_BUFFER_ALL_CPUS)
@@ -7126,12 +7128,24 @@ static ssize_t tracing_err_log_write(struct file *file,
 	return count;
 }
 
+static int tracing_err_log_release(struct inode *inode, struct file *file)
+{
+	struct trace_array *tr = inode->i_private;
+
+	trace_array_put(tr);
+
+	if (file->f_mode & FMODE_READ)
+		seq_release(inode, file);
+
+	return 0;
+}
+
 static const struct file_operations tracing_err_log_fops = {
 	.open           = tracing_err_log_open,
 	.write		= tracing_err_log_write,
 	.read           = seq_read,
 	.llseek         = seq_lseek,
-	.release	= tracing_release_generic_tr,
+	.release        = tracing_err_log_release,
 };
 
 static int tracing_buffers_open(struct inode *inode, struct file *filp)