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
  ...

2 files changed, 85 insertions, 41 deletions

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 1f394095eb88..13eda8de2998 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1982,19 +1982,21 @@ static int pid_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	struct inode *inode;
 	struct task_struct *task;
+	int ret = 0;
 
-	if (flags & LOOKUP_RCU)
-		return -ECHILD;
-
-	inode = d_inode(dentry);
-	task = get_proc_task(inode);
+	rcu_read_lock();
+	inode = d_inode_rcu(dentry);
+	if (!inode)
+		goto out;
+	task = pid_task(proc_pid(inode), PIDTYPE_PID);
 
 	if (task) {
 		pid_update_inode(task, inode);
-		put_task_struct(task);
-		return 1;
+		ret = 1;
 	}
-	return 0;
+out:
+	rcu_read_unlock();
+	return ret;
 }
 
 static inline bool proc_inode_is_dead(struct inode *inode)
@@ -3802,7 +3804,10 @@ static int proc_task_readdir(struct file *file, struct dir_context *ctx)
 	     task = next_tid(task), ctx->pos++) {
 		char name[10 + 1];
 		unsigned int len;
+
 		tid = task_pid_nr_ns(task, ns);
+		if (!tid)
+			continue;	/* The task has just exited. */
 		len = snprintf(name, sizeof(name), "%u", tid);
 		if (!proc_fill_cache(file, ctx, name, len,
 				proc_task_instantiate, task, NULL)) {
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index cdbbf819d2d6..30a3b66f475a 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -62,46 +62,75 @@ core_param(novmcoredd, vmcoredd_disabled, bool, 0);
 /* Device Dump Size */
 static size_t vmcoredd_orig_sz;
 
-/*
- * Returns > 0 for RAM pages, 0 for non-RAM pages, < 0 on error
- * The called function has to take care of module refcounting.
- */
-static int (*oldmem_pfn_is_ram)(unsigned long pfn);
-
-int register_oldmem_pfn_is_ram(int (*fn)(unsigned long pfn))
+static DECLARE_RWSEM(vmcore_cb_rwsem);
+/* List of registered vmcore callbacks. */
+static LIST_HEAD(vmcore_cb_list);
+/* Whether we had a surprise unregistration of a callback. */
+static bool vmcore_cb_unstable;
+/* Whether the vmcore has been opened once. */
+static bool vmcore_opened;
+
+void register_vmcore_cb(struct vmcore_cb *cb)
 {
-	if (oldmem_pfn_is_ram)
-		return -EBUSY;
-	oldmem_pfn_is_ram = fn;
-	return 0;
+	down_write(&vmcore_cb_rwsem);
+	INIT_LIST_HEAD(&cb->next);
+	list_add_tail(&cb->next, &vmcore_cb_list);
+	/*
+	 * Registering a vmcore callback after the vmcore was opened is
+	 * very unusual (e.g., manual driver loading).
+	 */
+	if (vmcore_opened)
+		pr_warn_once("Unexpected vmcore callback registration\n");
+	up_write(&vmcore_cb_rwsem);
 }
-EXPORT_SYMBOL_GPL(register_oldmem_pfn_is_ram);
+EXPORT_SYMBOL_GPL(register_vmcore_cb);
 
-void unregister_oldmem_pfn_is_ram(void)
+void unregister_vmcore_cb(struct vmcore_cb *cb)
 {
-	oldmem_pfn_is_ram = NULL;
-	wmb();
+	down_write(&vmcore_cb_rwsem);
+	list_del(&cb->next);
+	/*
+	 * Unregistering a vmcore callback after the vmcore was opened is
+	 * very unusual (e.g., forced driver removal), but we cannot stop
+	 * unregistering.
+	 */
+	if (vmcore_opened) {
+		pr_warn_once("Unexpected vmcore callback unregistration\n");
+		vmcore_cb_unstable = true;
+	}
+	up_write(&vmcore_cb_rwsem);
 }
-EXPORT_SYMBOL_GPL(unregister_oldmem_pfn_is_ram);
+EXPORT_SYMBOL_GPL(unregister_vmcore_cb);
 
-static int pfn_is_ram(unsigned long pfn)
+static bool pfn_is_ram(unsigned long pfn)
 {
-	int (*fn)(unsigned long pfn);
-	/* pfn is ram unless fn() checks pagetype */
-	int ret = 1;
+	struct vmcore_cb *cb;
+	bool ret = true;
 
-	/*
-	 * Ask hypervisor if the pfn is really ram.
-	 * A ballooned page contains no data and reading from such a page
-	 * will cause high load in the hypervisor.
-	 */
-	fn = oldmem_pfn_is_ram;
-	if (fn)
-		ret = fn(pfn);
+	lockdep_assert_held_read(&vmcore_cb_rwsem);
+	if (unlikely(vmcore_cb_unstable))
+		return false;
+
+	list_for_each_entry(cb, &vmcore_cb_list, next) {
+		if (unlikely(!cb->pfn_is_ram))
+			continue;
+		ret = cb->pfn_is_ram(cb, pfn);
+		if (!ret)
+			break;
+	}
 
 	return ret;
 }
 
+static int open_vmcore(struct inode *inode, struct file *file)
+{
+	down_read(&vmcore_cb_rwsem);
+	vmcore_opened = true;
+	up_read(&vmcore_cb_rwsem);
+
+	return 0;
+}
+
 /* Reads a page from the oldmem device from given offset. */
 ssize_t read_from_oldmem(char *buf, size_t count,
 			 u64 *ppos, int userbuf,
@@ -117,6 +146,7 @@ ssize_t read_from_oldmem(char *buf, size_t count,
 	offset = (unsigned long)(*ppos % PAGE_SIZE);
 	pfn = (unsigned long)(*ppos / PAGE_SIZE);
 
+	down_read(&vmcore_cb_rwsem);
 	do {
 		if (count > (PAGE_SIZE - offset))
 			nr_bytes = PAGE_SIZE - offset;
@@ -124,7 +154,7 @@ ssize_t read_from_oldmem(char *buf, size_t count,
 			nr_bytes = count;
 
 		/* If pfn is not ram, return zeros for sparse dump files */
-		if (pfn_is_ram(pfn) == 0)
+		if (!pfn_is_ram(pfn))
 			memset(buf, 0, nr_bytes);
 		else {
 			if (encrypted)
@@ -136,8 +166,10 @@ ssize_t read_from_oldmem(char *buf, size_t count,
 				tmp = copy_oldmem_page(pfn, buf, nr_bytes,
 						       offset, userbuf);
 
-			if (tmp < 0)
+			if (tmp < 0) {
+				up_read(&vmcore_cb_rwsem);
 				return tmp;
+			}
 		}
 		*ppos += nr_bytes;
 		count -= nr_bytes;
@@ -147,6 +179,7 @@ ssize_t read_from_oldmem(char *buf, size_t count,
 		offset = 0;
 	} while (count);
 
+	up_read(&vmcore_cb_rwsem);
 	return read;
 }
 
@@ -537,14 +570,19 @@ static int vmcore_remap_oldmem_pfn(struct vm_area_struct *vma,
 			    unsigned long from, unsigned long pfn,
 			    unsigned long size, pgprot_t prot)
 {
+	int ret;
+
 	/*
 	 * Check if oldmem_pfn_is_ram was registered to avoid
 	 * looping over all pages without a reason.
 	 */
-	if (oldmem_pfn_is_ram)
-		return remap_oldmem_pfn_checked(vma, from, pfn, size, prot);
+	down_read(&vmcore_cb_rwsem);
+	if (!list_empty(&vmcore_cb_list) || vmcore_cb_unstable)
+		ret = remap_oldmem_pfn_checked(vma, from, pfn, size, prot);
 	else
-		return remap_oldmem_pfn_range(vma, from, pfn, size, prot);
+		ret = remap_oldmem_pfn_range(vma, from, pfn, size, prot);
+	up_read(&vmcore_cb_rwsem);
+	return ret;
 }
 
 static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
@@ -668,6 +706,7 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
 #endif
 
 static const struct proc_ops vmcore_proc_ops = {
+	.proc_open	= open_vmcore,
 	.proc_read	= read_vmcore,
 	.proc_lseek	= default_llseek,
 	.proc_mmap	= mmap_vmcore,