Merge branch 'akpm' (aka "Andrew's patch-bomb, take two")

Andrew explains:

 - various misc stuff

 - Most of the rest of MM: memcg, threaded hugepages, others.

 - cpumask

 - kexec

 - kdump

 - some direct-io performance tweaking

 - radix-tree optimisations

 - new selftests code

   A note on this: often people will develop a new userspace-visible
   feature and will develop userspace code to exercise/test that
   feature.  Then they merge the patch and the selftest code dies.
   Sometimes we paste it into the changelog.  Sometimes the code gets
   thrown into Documentation/(!).

   This saddens me.  So this patch creates a bare-bones framework which
   will henceforth allow me to ask people to include their test apps in
   the kernel tree so we can keep them alive.  Then when people enhance
   or fix the feature, I can ask them to update the test app too.

   The infrastruture is terribly trivial at present - let's see how it
   evolves.

 - checkpoint/restart feature work.

   A note on this: this is a project by various mad Russians to perform
   c/r mainly from userspace, with various oddball helper code added
   into the kernel where the need is demonstrated.

   So rather than some large central lump of code, what we have is
   little bits and pieces popping up in various places which either
   expose something new or which permit something which is normally
   kernel-private to be modified.

   The overall project is an ongoing thing.  I've judged that the size
   and scope of the thing means that we're more likely to be successful
   with it if we integrate the support into mainline piecemeal rather
   than allowing it all to develop out-of-tree.

   However I'm less confident than the developers that it will all
   eventually work! So what I'm asking them to do is to wrap each piece
   of new code inside CONFIG_CHECKPOINT_RESTORE.  So if it all
   eventually comes to tears and the project as a whole fails, it should
   be a simple matter to go through and delete all trace of it.

This lot pretty much wraps up the -rc1 merge for me.

* akpm: (96 commits)
  unlzo: fix input buffer free
  ramoops: update parameters only after successful init
  ramoops: fix use of rounddown_pow_of_two()
  c/r: prctl: add PR_SET_MM codes to set up mm_struct entries
  c/r: procfs: add start_data, end_data, start_brk members to /proc/$pid/stat v4
  c/r: introduce CHECKPOINT_RESTORE symbol
  selftests: new x86 breakpoints selftest
  selftests: new very basic kernel selftests directory
  radix_tree: take radix_tree_path off stack
  radix_tree: remove radix_tree_indirect_to_ptr()
  dio: optimize cache misses in the submission path
  vfs: cache request_queue in struct block_device
  fs/direct-io.c: calculate fs_count correctly in get_more_blocks()
  drivers/parport/parport_pc.c: fix warnings
  panic: don't print redundant backtraces on oops
  sysctl: add the kernel.ns_last_pid control
  kdump: add udev events for memory online/offline
  include/linux/crash_dump.h needs elf.h
  kdump: fix crash_kexec()/smp_send_stop() race in panic()
  kdump: crashk_res init check for /sys/kernel/kexec_crash_size
  ...

7 files changed, 200 insertions, 15 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index 94ed6e20bb53..c44738267be7 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -887,7 +887,7 @@ static void check_stack_usage(void)
 static inline void check_stack_usage(void) {}
 #endif
 
-NORET_TYPE void do_exit(long code)
+void do_exit(long code)
 {
 	struct task_struct *tsk = current;
 	int group_dead;
@@ -1051,7 +1051,7 @@ NORET_TYPE void do_exit(long code)
 
 EXPORT_SYMBOL_GPL(do_exit);
 
-NORET_TYPE void complete_and_exit(struct completion *comp, long code)
+void complete_and_exit(struct completion *comp, long code)
 {
 	if (comp)
 		complete(comp);
@@ -1070,7 +1070,7 @@ SYSCALL_DEFINE1(exit, int, error_code)
  * Take down every thread in the group.  This is called by fatal signals
  * as well as by sys_exit_group (below).
  */
-NORET_TYPE void
+void
 do_group_exit(int exit_code)
 {
 	struct signal_struct *sig = current->signal;
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 090ee10d9604..7b0886786701 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -32,7 +32,6 @@
 #include <linux/console.h>
 #include <linux/vmalloc.h>
 #include <linux/swap.h>
-#include <linux/kmsg_dump.h>
 #include <linux/syscore_ops.h>
 
 #include <asm/page.h>
@@ -1094,8 +1093,6 @@ void crash_kexec(struct pt_regs *regs)
 		if (kexec_crash_image) {
 			struct pt_regs fixed_regs;
 
-			kmsg_dump(KMSG_DUMP_KEXEC);
-
 			crash_setup_regs(&fixed_regs, regs);
 			crash_save_vmcoreinfo();
 			machine_crash_shutdown(&fixed_regs);
@@ -1132,6 +1129,8 @@ int crash_shrink_memory(unsigned long new_size)
 {
 	int ret = 0;
 	unsigned long start, end;
+	unsigned long old_size;
+	struct resource *ram_res;
 
 	mutex_lock(&kexec_mutex);
 
@@ -1141,11 +1140,15 @@ int crash_shrink_memory(unsigned long new_size)
 	}
 	start = crashk_res.start;
 	end = crashk_res.end;
+	old_size = (end == 0) ? 0 : end - start + 1;
+	if (new_size >= old_size) {
+		ret = (new_size == old_size) ? 0 : -EINVAL;
+		goto unlock;
+	}
 
-	if (new_size >= end - start + 1) {
-		ret = -EINVAL;
-		if (new_size == end - start + 1)
-			ret = 0;
+	ram_res = kzalloc(sizeof(*ram_res), GFP_KERNEL);
+	if (!ram_res) {
+		ret = -ENOMEM;
 		goto unlock;
 	}
 
@@ -1157,7 +1160,15 @@ int crash_shrink_memory(unsigned long new_size)
 
 	if ((start == end) && (crashk_res.parent != NULL))
 		release_resource(&crashk_res);
+
+	ram_res->start = end;
+	ram_res->end = crashk_res.end;
+	ram_res->flags = IORESOURCE_BUSY | IORESOURCE_MEM;
+	ram_res->name = "System RAM";
+
 	crashk_res.end = end - 1;
+
+	insert_resource(&iomem_resource, ram_res);
 	crash_unmap_reserved_pages();
 
 unlock:
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index e5d84644823b..95dd7212e610 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2198,7 +2198,7 @@ static ssize_t write_enabled_file_bool(struct file *file,
 	       const char __user *user_buf, size_t count, loff_t *ppos)
 {
 	char buf[32];
-	int buf_size;
+	size_t buf_size;
 
 	buf_size = min(count, (sizeof(buf)-1));
 	if (copy_from_user(buf, user_buf, buf_size))
diff --git a/kernel/panic.c b/kernel/panic.c
index 3458469eb7c3..80aed44e345a 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -49,6 +49,15 @@ static long no_blink(int state)
 long (*panic_blink)(int state);
 EXPORT_SYMBOL(panic_blink);
 
+/*
+ * Stop ourself in panic -- architecture code may override this
+ */
+void __weak panic_smp_self_stop(void)
+{
+	while (1)
+		cpu_relax();
+}
+
 /**
  *	panic - halt the system
  *	@fmt: The text string to print
@@ -57,8 +66,9 @@ EXPORT_SYMBOL(panic_blink);
  *
  *	This function never returns.
  */
-NORET_TYPE void panic(const char * fmt, ...)
+void panic(const char *fmt, ...)
 {
+	static DEFINE_SPINLOCK(panic_lock);
 	static char buf[1024];
 	va_list args;
 	long i, i_next = 0;
@@ -68,8 +78,14 @@ NORET_TYPE void panic(const char * fmt, ...)
 	 * It's possible to come here directly from a panic-assertion and
 	 * not have preempt disabled. Some functions called from here want
 	 * preempt to be disabled. No point enabling it later though...
+	 *
+	 * Only one CPU is allowed to execute the panic code from here. For
+	 * multiple parallel invocations of panic, all other CPUs either
+	 * stop themself or will wait until they are stopped by the 1st CPU
+	 * with smp_send_stop().
 	 */
-	preempt_disable();
+	if (!spin_trylock(&panic_lock))
+		panic_smp_self_stop();
 
 	console_verbose();
 	bust_spinlocks(1);
@@ -78,7 +94,11 @@ NORET_TYPE void panic(const char * fmt, ...)
 	va_end(args);
 	printk(KERN_EMERG "Kernel panic - not syncing: %s\n",buf);
 #ifdef CONFIG_DEBUG_BUGVERBOSE
-	dump_stack();
+	/*
+	 * Avoid nested stack-dumping if a panic occurs during oops processing
+	 */
+	if (!oops_in_progress)
+		dump_stack();
 #endif
 
 	/*
diff --git a/kernel/pid.c b/kernel/pid.c
index fa5f72227e5f..ce8e00deaccb 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -137,7 +137,9 @@ static int pid_before(int base, int a, int b)
 }
 
 /*
- * We might be racing with someone else trying to set pid_ns->last_pid.
+ * We might be racing with someone else trying to set pid_ns->last_pid
+ * at the pid allocation time (there's also a sysctl for this, but racing
+ * with this one is OK, see comment in kernel/pid_namespace.c about it).
  * We want the winner to have the "later" value, because if the
  * "earlier" value prevails, then a pid may get reused immediately.
  *
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index e9c9adc84ca6..a8968396046d 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -191,9 +191,40 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 	return;
 }
 
+static int pid_ns_ctl_handler(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table tmp = *table;
+
+	if (write && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	/*
+	 * Writing directly to ns' last_pid field is OK, since this field
+	 * is volatile in a living namespace anyway and a code writing to
+	 * it should synchronize its usage with external means.
+	 */
+
+	tmp.data = &current->nsproxy->pid_ns->last_pid;
+	return proc_dointvec(&tmp, write, buffer, lenp, ppos);
+}
+
+static struct ctl_table pid_ns_ctl_table[] = {
+	{
+		.procname = "ns_last_pid",
+		.maxlen = sizeof(int),
+		.mode = 0666, /* permissions are checked in the handler */
+		.proc_handler = pid_ns_ctl_handler,
+	},
+	{ }
+};
+
+static struct ctl_path kern_path[] = { { .procname = "kernel", }, { } };
+
 static __init int pid_namespaces_init(void)
 {
 	pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC);
+	register_sysctl_paths(kern_path, pid_ns_ctl_table);
 	return 0;
 }
 
diff --git a/kernel/sys.c b/kernel/sys.c
index ddf8155bf3f8..40701538fbd1 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1692,6 +1692,124 @@ SYSCALL_DEFINE1(umask, int, mask)
 	return mask;
 }
 
+#ifdef CONFIG_CHECKPOINT_RESTORE
+static int prctl_set_mm(int opt, unsigned long addr,
+			unsigned long arg4, unsigned long arg5)
+{
+	unsigned long rlim = rlimit(RLIMIT_DATA);
+	unsigned long vm_req_flags;
+	unsigned long vm_bad_flags;
+	struct vm_area_struct *vma;
+	int error = 0;
+	struct mm_struct *mm = current->mm;
+
+	if (arg4 | arg5)
+		return -EINVAL;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (addr >= TASK_SIZE)
+		return -EINVAL;
+
+	down_read(&mm->mmap_sem);
+	vma = find_vma(mm, addr);
+
+	if (opt != PR_SET_MM_START_BRK && opt != PR_SET_MM_BRK) {
+		/* It must be existing VMA */
+		if (!vma || vma->vm_start > addr)
+			goto out;
+	}
+
+	error = -EINVAL;
+	switch (opt) {
+	case PR_SET_MM_START_CODE:
+	case PR_SET_MM_END_CODE:
+		vm_req_flags = VM_READ | VM_EXEC;
+		vm_bad_flags = VM_WRITE | VM_MAYSHARE;
+
+		if ((vma->vm_flags & vm_req_flags) != vm_req_flags ||
+		    (vma->vm_flags & vm_bad_flags))
+			goto out;
+
+		if (opt == PR_SET_MM_START_CODE)
+			mm->start_code = addr;
+		else
+			mm->end_code = addr;
+		break;
+
+	case PR_SET_MM_START_DATA:
+	case PR_SET_MM_END_DATA:
+		vm_req_flags = VM_READ | VM_WRITE;
+		vm_bad_flags = VM_EXEC | VM_MAYSHARE;
+
+		if ((vma->vm_flags & vm_req_flags) != vm_req_flags ||
+		    (vma->vm_flags & vm_bad_flags))
+			goto out;
+
+		if (opt == PR_SET_MM_START_DATA)
+			mm->start_data = addr;
+		else
+			mm->end_data = addr;
+		break;
+
+	case PR_SET_MM_START_STACK:
+
+#ifdef CONFIG_STACK_GROWSUP
+		vm_req_flags = VM_READ | VM_WRITE | VM_GROWSUP;
+#else
+		vm_req_flags = VM_READ | VM_WRITE | VM_GROWSDOWN;
+#endif
+		if ((vma->vm_flags & vm_req_flags) != vm_req_flags)
+			goto out;
+
+		mm->start_stack = addr;
+		break;
+
+	case PR_SET_MM_START_BRK:
+		if (addr <= mm->end_data)
+			goto out;
+
+		if (rlim < RLIM_INFINITY &&
+		    (mm->brk - addr) +
+		    (mm->end_data - mm->start_data) > rlim)
+			goto out;
+
+		mm->start_brk = addr;
+		break;
+
+	case PR_SET_MM_BRK:
+		if (addr <= mm->end_data)
+			goto out;
+
+		if (rlim < RLIM_INFINITY &&
+		    (addr - mm->start_brk) +
+		    (mm->end_data - mm->start_data) > rlim)
+			goto out;
+
+		mm->brk = addr;
+		break;
+
+	default:
+		error = -EINVAL;
+		goto out;
+	}
+
+	error = 0;
+
+out:
+	up_read(&mm->mmap_sem);
+
+	return error;
+}
+#else /* CONFIG_CHECKPOINT_RESTORE */
+static int prctl_set_mm(int opt, unsigned long addr,
+			unsigned long arg4, unsigned long arg5)
+{
+	return -EINVAL;
+}
+#endif
+
 SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		unsigned long, arg4, unsigned long, arg5)
 {
@@ -1841,6 +1959,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 			else
 				error = PR_MCE_KILL_DEFAULT;
 			break;
+		case PR_SET_MM:
+			error = prctl_set_mm(arg2, arg3, arg4, arg5);
+			break;
 		default:
 			error = -EINVAL;
 			break;