Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:
 "87 patches.

  Subsystems affected by this patch series: mm (pagecache and hugetlb),
  procfs, misc, MAINTAINERS, lib, checkpatch, binfmt, kallsyms, ramfs,
  init, codafs, nilfs2, hfs, crash_dump, signals, seq_file, fork,
  sysvfs, kcov, gdb, resource, selftests, and ipc"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (87 commits)
  ipc/ipc_sysctl.c: remove fallback for !CONFIG_PROC_SYSCTL
  ipc: check checkpoint_restore_ns_capable() to modify C/R proc files
  selftests/kselftest/runner/run_one(): allow running non-executable files
  virtio-mem: disallow mapping virtio-mem memory via /dev/mem
  kernel/resource: disallow access to exclusive system RAM regions
  kernel/resource: clean up and optimize iomem_is_exclusive()
  scripts/gdb: handle split debug for vmlinux
  kcov: replace local_irq_save() with a local_lock_t
  kcov: avoid enable+disable interrupts if !in_task()
  kcov: allocate per-CPU memory on the relevant node
  Documentation/kcov: define `ip' in the example
  Documentation/kcov: include types.h in the example
  sysv: use BUILD_BUG_ON instead of runtime check
  kernel/fork.c: unshare(): use swap() to make code cleaner
  seq_file: fix passing wrong private data
  seq_file: move seq_escape() to a header
  signal: remove duplicate include in signal.h
  crash_dump: remove duplicate include in crash_dump.h
  crash_dump: fix boolreturn.cocci warning
  hfs/hfsplus: use WARN_ON for sanity check
  ...

6 files changed, 66 insertions, 71 deletions

diff --git a/kernel/extable.c b/kernel/extable.c
index 290661f68e6b..b6f330f0fe74 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -62,40 +62,13 @@ const struct exception_table_entry *search_exception_tables(unsigned long addr)
 	return e;
 }
 
-int init_kernel_text(unsigned long addr)
-{
-	if (addr >= (unsigned long)_sinittext &&
-	    addr < (unsigned long)_einittext)
-		return 1;
-	return 0;
-}
-
 int notrace core_kernel_text(unsigned long addr)
 {
-	if (addr >= (unsigned long)_stext &&
-	    addr < (unsigned long)_etext)
+	if (is_kernel_text(addr))
 		return 1;
 
 	if (system_state < SYSTEM_FREEING_INITMEM &&
-	    init_kernel_text(addr))
-		return 1;
-	return 0;
-}
-
-/**
- * core_kernel_data - tell if addr points to kernel data
- * @addr: address to test
- *
- * Returns true if @addr passed in is from the core kernel data
- * section.
- *
- * Note: On some archs it may return true for core RODATA, and false
- *  for others. But will always be true for core RW data.
- */
-int core_kernel_data(unsigned long addr)
-{
-	if (addr >= (unsigned long)_sdata &&
-	    addr < (unsigned long)_edata)
+	    is_kernel_inittext(addr))
 		return 1;
 	return 0;
 }
@@ -112,7 +85,7 @@ int __kernel_text_address(unsigned long addr)
 	 * Since we are after the module-symbols check, there's
 	 * no danger of address overlap:
 	 */
-	if (init_kernel_text(addr))
+	if (is_kernel_inittext(addr))
 		return 1;
 	return 0;
 }
diff --git a/kernel/fork.c b/kernel/fork.c
index 3f112b11a9ad..5de23f3e08bf 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -3024,7 +3024,7 @@ int unshare_fd(unsigned long unshare_flags, unsigned int max_fds,
 int ksys_unshare(unsigned long unshare_flags)
 {
 	struct fs_struct *fs, *new_fs = NULL;
-	struct files_struct *fd, *new_fd = NULL;
+	struct files_struct *new_fd = NULL;
 	struct cred *new_cred = NULL;
 	struct nsproxy *new_nsproxy = NULL;
 	int do_sysvsem = 0;
@@ -3111,11 +3111,8 @@ int ksys_unshare(unsigned long unshare_flags)
 			spin_unlock(&fs->lock);
 		}
 
-		if (new_fd) {
-			fd = current->files;
-			current->files = new_fd;
-			new_fd = fd;
-		}
+		if (new_fd)
+			swap(current->files, new_fd);
 
 		task_unlock(current);
 
diff --git a/kernel/kcov.c b/kernel/kcov.c
index 80bfe71bbe13..36ca640c4f8e 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -88,6 +88,7 @@ static struct list_head kcov_remote_areas = LIST_HEAD_INIT(kcov_remote_areas);
 
 struct kcov_percpu_data {
 	void			*irq_area;
+	local_lock_t		lock;
 
 	unsigned int		saved_mode;
 	unsigned int		saved_size;
@@ -96,7 +97,9 @@ struct kcov_percpu_data {
 	int			saved_sequence;
 };
 
-static DEFINE_PER_CPU(struct kcov_percpu_data, kcov_percpu_data);
+static DEFINE_PER_CPU(struct kcov_percpu_data, kcov_percpu_data) = {
+	.lock = INIT_LOCAL_LOCK(lock),
+};
 
 /* Must be called with kcov_remote_lock locked. */
 static struct kcov_remote *kcov_remote_find(u64 handle)
@@ -824,7 +827,7 @@ void kcov_remote_start(u64 handle)
 	if (!in_task() && !in_serving_softirq())
 		return;
 
-	local_irq_save(flags);
+	local_lock_irqsave(&kcov_percpu_data.lock, flags);
 
 	/*
 	 * Check that kcov_remote_start() is not called twice in background
@@ -832,7 +835,7 @@ void kcov_remote_start(u64 handle)
 	 */
 	mode = READ_ONCE(t->kcov_mode);
 	if (WARN_ON(in_task() && kcov_mode_enabled(mode))) {
-		local_irq_restore(flags);
+		local_unlock_irqrestore(&kcov_percpu_data.lock, flags);
 		return;
 	}
 	/*
@@ -841,14 +844,15 @@ void kcov_remote_start(u64 handle)
 	 * happened while collecting coverage from a background thread.
 	 */
 	if (WARN_ON(in_serving_softirq() && t->kcov_softirq)) {
-		local_irq_restore(flags);
+		local_unlock_irqrestore(&kcov_percpu_data.lock, flags);
 		return;
 	}
 
 	spin_lock(&kcov_remote_lock);
 	remote = kcov_remote_find(handle);
 	if (!remote) {
-		spin_unlock_irqrestore(&kcov_remote_lock, flags);
+		spin_unlock(&kcov_remote_lock);
+		local_unlock_irqrestore(&kcov_percpu_data.lock, flags);
 		return;
 	}
 	kcov_debug("handle = %llx, context: %s\n", handle,
@@ -869,19 +873,19 @@ void kcov_remote_start(u64 handle)
 		size = CONFIG_KCOV_IRQ_AREA_SIZE;
 		area = this_cpu_ptr(&kcov_percpu_data)->irq_area;
 	}
-	spin_unlock_irqrestore(&kcov_remote_lock, flags);
+	spin_unlock(&kcov_remote_lock);
 
 	/* Can only happen when in_task(). */
 	if (!area) {
+		local_unlock_irqrestore(&kcov_percpu_data.lock, flags);
 		area = vmalloc(size * sizeof(unsigned long));
 		if (!area) {
 			kcov_put(kcov);
 			return;
 		}
+		local_lock_irqsave(&kcov_percpu_data.lock, flags);
 	}
 
-	local_irq_save(flags);
-
 	/* Reset coverage size. */
 	*(u64 *)area = 0;
 
@@ -891,7 +895,7 @@ void kcov_remote_start(u64 handle)
 	}
 	kcov_start(t, kcov, size, area, mode, sequence);
 
-	local_irq_restore(flags);
+	local_unlock_irqrestore(&kcov_percpu_data.lock, flags);
 
 }
 EXPORT_SYMBOL(kcov_remote_start);
@@ -965,12 +969,12 @@ void kcov_remote_stop(void)
 	if (!in_task() && !in_serving_softirq())
 		return;
 
-	local_irq_save(flags);
+	local_lock_irqsave(&kcov_percpu_data.lock, flags);
 
 	mode = READ_ONCE(t->kcov_mode);
 	barrier();
 	if (!kcov_mode_enabled(mode)) {
-		local_irq_restore(flags);
+		local_unlock_irqrestore(&kcov_percpu_data.lock, flags);
 		return;
 	}
 	/*
@@ -978,12 +982,12 @@ void kcov_remote_stop(void)
 	 * actually found the remote handle and started collecting coverage.
 	 */
 	if (in_serving_softirq() && !t->kcov_softirq) {
-		local_irq_restore(flags);
+		local_unlock_irqrestore(&kcov_percpu_data.lock, flags);
 		return;
 	}
 	/* Make sure that kcov_softirq is only set when in softirq. */
 	if (WARN_ON(!in_serving_softirq() && t->kcov_softirq)) {
-		local_irq_restore(flags);
+		local_unlock_irqrestore(&kcov_percpu_data.lock, flags);
 		return;
 	}
 
@@ -1013,7 +1017,7 @@ void kcov_remote_stop(void)
 		spin_unlock(&kcov_remote_lock);
 	}
 
-	local_irq_restore(flags);
+	local_unlock_irqrestore(&kcov_percpu_data.lock, flags);
 
 	/* Get in kcov_remote_start(). */
 	kcov_put(kcov);
@@ -1034,8 +1038,8 @@ static int __init kcov_init(void)
 	int cpu;
 
 	for_each_possible_cpu(cpu) {
-		void *area = vmalloc(CONFIG_KCOV_IRQ_AREA_SIZE *
-				sizeof(unsigned long));
+		void *area = vmalloc_node(CONFIG_KCOV_IRQ_AREA_SIZE *
+				sizeof(unsigned long), cpu_to_node(cpu));
 		if (!area)
 			return -ENOMEM;
 		per_cpu_ptr(&kcov_percpu_data, cpu)->irq_area = area;
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 74d371665747..2270ec68f10a 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -818,9 +818,6 @@ static int static_obj(const void *obj)
 	if ((addr >= start) && (addr < end))
 		return 1;
 
-	if (arch_is_kernel_data(addr))
-		return 1;
-
 	/*
 	 * in-kernel percpu var?
 	 */
diff --git a/kernel/resource.c b/kernel/resource.c
index ca9f5198a01f..5ad3eba619ba 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -73,6 +73,18 @@ static struct resource *next_resource(struct resource *p)
 	return p->sibling;
 }
 
+static struct resource *next_resource_skip_children(struct resource *p)
+{
+	while (!p->sibling && p->parent)
+		p = p->parent;
+	return p->sibling;
+}
+
+#define for_each_resource(_root, _p, _skip_children) \
+	for ((_p) = (_root)->child; (_p); \
+	     (_p) = (_skip_children) ? next_resource_skip_children(_p) : \
+				       next_resource(_p))
+
 static void *r_next(struct seq_file *m, void *v, loff_t *pos)
 {
 	struct resource *p = v;
@@ -1707,37 +1719,49 @@ static int strict_iomem_checks;
 #endif
 
 /*
- * check if an address is reserved in the iomem resource tree
- * returns true if reserved, false if not reserved.
+ * Check if an address is exclusive to the kernel and must not be mapped to
+ * user space, for example, via /dev/mem.
+ *
+ * Returns true if exclusive to the kernel, otherwise returns false.
  */
 bool iomem_is_exclusive(u64 addr)
 {
-	struct resource *p = &iomem_resource;
-	bool err = false;
-	loff_t l;
+	const unsigned int exclusive_system_ram = IORESOURCE_SYSTEM_RAM |
+						  IORESOURCE_EXCLUSIVE;
+	bool skip_children = false, err = false;
 	int size = PAGE_SIZE;
-
-	if (!strict_iomem_checks)
-		return false;
+	struct resource *p;
 
 	addr = addr & PAGE_MASK;
 
 	read_lock(&resource_lock);
-	for (p = p->child; p ; p = r_next(NULL, p, &l)) {
-		/*
-		 * We can probably skip the resources without
-		 * IORESOURCE_IO attribute?
-		 */
+	for_each_resource(&iomem_resource, p, skip_children) {
 		if (p->start >= addr + size)
 			break;
-		if (p->end < addr)
+		if (p->end < addr) {
+			skip_children = true;
 			continue;
+		}
+		skip_children = false;
+
+		/*
+		 * IORESOURCE_SYSTEM_RAM resources are exclusive if
+		 * IORESOURCE_EXCLUSIVE is set, even if they
+		 * are not busy and even if "iomem=relaxed" is set. The
+		 * responsible driver dynamically adds/removes system RAM within
+		 * such an area and uncontrolled access is dangerous.
+		 */
+		if ((p->flags & exclusive_system_ram) == exclusive_system_ram) {
+			err = true;
+			break;
+		}
+
 		/*
 		 * A resource is exclusive if IORESOURCE_EXCLUSIVE is set
 		 * or CONFIG_IO_STRICT_DEVMEM is enabled and the
 		 * resource is busy.
 		 */
-		if ((p->flags & IORESOURCE_BUSY) == 0)
+		if (!strict_iomem_checks || !(p->flags & IORESOURCE_BUSY))
 			continue;
 		if (IS_ENABLED(CONFIG_IO_STRICT_DEVMEM)
 				|| p->flags & IORESOURCE_EXCLUSIVE) {
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f3ea4e20072f..007a3ded0358 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -318,7 +318,7 @@ int __register_ftrace_function(struct ftrace_ops *ops)
 	if (!ftrace_enabled && (ops->flags & FTRACE_OPS_FL_PERMANENT))
 		return -EBUSY;
 
-	if (!core_kernel_data((unsigned long)ops))
+	if (!is_kernel_core_data((unsigned long)ops))
 		ops->flags |= FTRACE_OPS_FL_DYNAMIC;
 
 	add_ftrace_ops(&ftrace_ops_list, ops);