Merge branch 'akpm' (Andrew's patch-bomb)

Merge misc patches from Andrew Morton:

 - the "misc" tree - stuff from all over the map

 - checkpatch updates

 - fatfs

 - kmod changes

 - procfs

 - cpumask

 - UML

 - kexec

 - mqueue

 - rapidio

 - pidns

 - some checkpoint-restore feature work.  Reluctantly.  Most of it
   delayed a release.  I'm still rather worried that we don't have a
   clear roadmap to completion for this work.

* emailed from Andrew Morton <[email protected]>: (78 patches)
  kconfig: update compression algorithm info
  c/r: prctl: add ability to set new mm_struct::exe_file
  c/r: prctl: extend PR_SET_MM to set up more mm_struct entries
  c/r: procfs: add arg_start/end, env_start/end and exit_code members to /proc/$pid/stat
  syscalls, x86: add __NR_kcmp syscall
  fs, proc: introduce /proc/<pid>/task/<tid>/children entry
  sysctl: make kernel.ns_last_pid control dependent on CHECKPOINT_RESTORE
  aio/vfs: cleanup of rw_copy_check_uvector() and compat_rw_copy_check_uvector()
  eventfd: change int to __u64 in eventfd_signal()
  fs/nls: add Apple NLS
  pidns: make killed children autoreap
  pidns: use task_active_pid_ns in do_notify_parent
  rapidio/tsi721: add DMA engine support
  rapidio: add DMA engine support for RIO data transfers
  ipc/mqueue: add rbtree node caching support
  tools/selftests: add mq_perf_tests
  ipc/mqueue: strengthen checks on mqueue creation
  ipc/mqueue: correct mq_attr_ok test
  ipc/mqueue: improve performance of send/recv
  selftests: add mq_open_tests
  ...

.mailmap

@@ -113,3 +113,5 @@ Uwe Kleine-König <[email protected]>
 Valdis Kletnieks <[email protected]>
 Takashi YOSHII <[email protected]>
 Yusuke Goda <[email protected]>
+Gustavo Padovan <[email protected]>
+Gustavo Padovan <[email protected]>

Documentation/CodingStyle

@@ -671,8 +671,9 @@ ones already enabled by DEBUG.
 		Chapter 14: Allocating memory
 
 The kernel provides the following general purpose memory allocators:
-kmalloc(), kzalloc(), kcalloc(), vmalloc(), and vzalloc().  Please refer to
-the API documentation for further information about them.
+kmalloc(), kzalloc(), kmalloc_array(), kcalloc(), vmalloc(), and
+vzalloc().  Please refer to the API documentation for further information
+about them.
 
 The preferred form for passing a size of a struct is the following:
 
@@ -686,6 +687,17 @@ Casting the return value which is a void pointer is redundant. The conversion
 from void pointer to any other pointer type is guaranteed by the C programming
 language.
 
+The preferred form for allocating an array is the following:
+
+	p = kmalloc_array(n, sizeof(...), ...);
+
+The preferred form for allocating a zeroed array is the following:
+
+	p = kcalloc(n, sizeof(...), ...);
+
+Both forms check for overflow on the allocation size n * sizeof(...),
+and return NULL if that occurred.
+
 
 		Chapter 15: The inline disease
 

Documentation/filesystems/proc.txt

@@ -40,6 +40,7 @@ Table of Contents
   3.4	/proc/<pid>/coredump_filter - Core dump filtering settings
   3.5	/proc/<pid>/mountinfo - Information about mounts
   3.6	/proc/<pid>/comm  & /proc/<pid>/task/<tid>/comm
+  3.7   /proc/<pid>/task/<tid>/children - Information about task children
 
   4	Configuring procfs
   4.1	Mount options
@@ -310,6 +311,11 @@ Table 1-4: Contents of the stat files (as of 2.6.30-rc7)
   start_data    address above which program data+bss is placed
   end_data      address below which program data+bss is placed
   start_brk     address above which program heap can be expanded with brk()
+  arg_start     address above which program command line is placed
+  arg_end       address below which program command line is placed
+  env_start     address above which program environment is placed
+  env_end       address below which program environment is placed
+  exit_code     the thread's exit_code in the form reported by the waitpid system call
 ..............................................................................
 
 The /proc/PID/maps file containing the currently mapped memory regions and
@@ -1578,6 +1584,23 @@ then the kernel's TASK_COMM_LEN (currently 16 chars) will result in a truncated
 comm value.
 
 
+3.7	/proc/<pid>/task/<tid>/children - Information about task children
+-------------------------------------------------------------------------
+This file provides a fast way to retrieve first level children pids
+of a task pointed by <pid>/<tid> pair. The format is a space separated
+stream of pids.
+
+Note the "first level" here -- if a child has own children they will
+not be listed here, one needs to read /proc/<children-pid>/task/<tid>/children
+to obtain the descendants.
+
+Since this interface is intended to be fast and cheap it doesn't
+guarantee to provide precise results and some children might be
+skipped, especially if they've exited right after we printed their
+pids, so one need to either stop or freeze processes being inspected
+if precise results are needed.
+
+
 ------------------------------------------------------------------------------
 Configuring procfs
 ------------------------------------------------------------------------------

Documentation/sysctl/fs.txt

@@ -225,6 +225,13 @@ a queue must be less or equal then msg_max.
 maximum  message size value (it is every  message queue's attribute set during
 its creation).
 
+/proc/sys/fs/mqueue/msg_default is  a read/write  file for setting/getting the
+default number of messages in a queue value if attr parameter of mq_open(2) is
+NULL. If it exceed msg_max, the default value is initialized msg_max.
+
+/proc/sys/fs/mqueue/msgsize_default is a read/write file for setting/getting
+the default message size value if attr parameter of mq_open(2) is NULL. If it
+exceed msgsize_max, the default value is initialized msgsize_max.
 
 4. /proc/sys/fs/epoll - Configuration options for the epoll interface
 --------------------------------------------------------

Documentation/vm/pagemap.txt

@@ -16,7 +16,7 @@ There are three components to pagemap:
     * Bits 0-4   swap type if swapped
     * Bits 5-54  swap offset if swapped
     * Bits 55-60 page shift (page size = 1<<page shift)
-    * Bit  61    reserved for future use
+    * Bit  61    page is file-page or shared-anon
     * Bit  62    page swapped
     * Bit  63    page present
 

arch/arm/kernel/smp.c

@@ -109,7 +109,6 @@ static void percpu_timer_stop(void);
 int __cpu_disable(void)
 {
 	unsigned int cpu = smp_processor_id();
-	struct task_struct *p;
 	int ret;
 
 	ret = platform_cpu_disable(cpu);
@@ -139,12 +138,7 @@ int __cpu_disable(void)
 	flush_cache_all();
 	local_flush_tlb_all();
 
-	read_lock(&tasklist_lock);
-	for_each_process(p) {
-		if (p->mm)
-			cpumask_clear_cpu(cpu, mm_cpumask(p->mm));
-	}
-	read_unlock(&tasklist_lock);
+	clear_tasks_mm_cpumask(cpu);
 
 	return 0;
 }

arch/blackfin/kernel/trace.c

@@ -10,6 +10,8 @@
 #include <linux/hardirq.h>
 #include <linux/thread_info.h>
 #include <linux/mm.h>
+#include <linux/oom.h>
+#include <linux/sched.h>
 #include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/kallsyms.h>
@@ -27,8 +29,7 @@ void decode_address(char *buf, unsigned long address)
 {
 	struct task_struct *p;
 	struct mm_struct *mm;
-	unsigned long flags, offset;
-	unsigned char in_atomic = (bfin_read_IPEND() & 0x10) || in_atomic();
+	unsigned long offset;
 	struct rb_node *n;
 
 #ifdef CONFIG_KALLSYMS
@@ -112,17 +113,17 @@ void decode_address(char *buf, unsigned long address)
 	 * mappings of all our processes and see if we can't be a whee
 	 * bit more specific
 	 */
-	write_lock_irqsave(&tasklist_lock, flags);
+	read_lock(&tasklist_lock);
 	for_each_process(p) {
-		mm = (in_atomic ? p->mm : get_task_mm(p));
-		if (!mm)
-			continue;
+		struct task_struct *t;
 
-		if (!down_read_trylock(&mm->mmap_sem)) {
-			if (!in_atomic)
-				mmput(mm);
+		t = find_lock_task_mm(p);
+		if (!t)
 			continue;
-		}
+
+		mm = t->mm;
+		if (!down_read_trylock(&mm->mmap_sem))
+			goto __continue;
 
 		for (n = rb_first(&mm->mm_rb); n; n = rb_next(n)) {
 			struct vm_area_struct *vma;
@@ -131,7 +132,7 @@ void decode_address(char *buf, unsigned long address)
 
 			if (address >= vma->vm_start && address < vma->vm_end) {
 				char _tmpbuf[256];
-				char *name = p->comm;
+				char *name = t->comm;
 				struct file *file = vma->vm_file;
 
 				if (file) {
@@ -164,8 +165,7 @@ void decode_address(char *buf, unsigned long address)
 						name, vma->vm_start, vma->vm_end);
 
 				up_read(&mm->mmap_sem);
-				if (!in_atomic)
-					mmput(mm);
+				task_unlock(t);
 
 				if (buf[0] == '\0')
 					sprintf(buf, "[ %s ] dynamic memory", name);
@@ -175,8 +175,8 @@ void decode_address(char *buf, unsigned long address)
 		}
 
 		up_read(&mm->mmap_sem);
-		if (!in_atomic)
-			mmput(mm);
+__continue:
+		task_unlock(t);
 	}
 
 	/*
@@ -186,7 +186,7 @@ void decode_address(char *buf, unsigned long address)
 	sprintf(buf, "/* kernel dynamic memory */");
 
 done:
-	write_unlock_irqrestore(&tasklist_lock, flags);
+	read_unlock(&tasklist_lock);
 }
 
 #define EXPAND_LEN ((1 << CONFIG_DEBUG_BFIN_HWTRACE_EXPAND_LEN) * 256 - 1)

arch/powerpc/mm/mmu_context_nohash.c

@@ -333,9 +333,7 @@ static int __cpuinit mmu_context_cpu_notify(struct notifier_block *self,
 					    unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (unsigned int)(long)hcpu;
-#ifdef CONFIG_HOTPLUG_CPU
-	struct task_struct *p;
-#endif
+
 	/* We don't touch CPU 0 map, it's allocated at aboot and kept
 	 * around forever
 	 */
@@ -358,12 +356,7 @@ static int __cpuinit mmu_context_cpu_notify(struct notifier_block *self,
 		stale_map[cpu] = NULL;
 
 		/* We also clear the cpu_vm_mask bits of CPUs going away */
-		read_lock(&tasklist_lock);
-		for_each_process(p) {
-			if (p->mm)
-				cpumask_clear_cpu(cpu, mm_cpumask(p->mm));
-		}
-		read_unlock(&tasklist_lock);
+		clear_tasks_mm_cpumask(cpu);
 	break;
 #endif /* CONFIG_HOTPLUG_CPU */
 	}

arch/sh/kernel/smp.c

@@ -123,7 +123,6 @@ void native_play_dead(void)
 int __cpu_disable(void)
 {
 	unsigned int cpu = smp_processor_id();
-	struct task_struct *p;
 	int ret;
 
 	ret = mp_ops->cpu_disable(cpu);
@@ -153,11 +152,7 @@ int __cpu_disable(void)
 	flush_cache_all();
 	local_flush_tlb_all();
 
-	read_lock(&tasklist_lock);
-	for_each_process(p)
-		if (p->mm)
-			cpumask_clear_cpu(cpu, mm_cpumask(p->mm));
-	read_unlock(&tasklist_lock);
+	clear_tasks_mm_cpumask(cpu);
 
 	return 0;
 }

arch/um/kernel/reboot.c

@@ -4,7 +4,9 @@
  */
 
 #include "linux/sched.h"
+#include "linux/spinlock.h"
 #include "linux/slab.h"
+#include "linux/oom.h"
 #include "kern_util.h"
 #include "os.h"
 #include "skas.h"
@@ -22,13 +24,18 @@ static void kill_off_processes(void)
 		struct task_struct *p;
 		int pid;
 
+		read_lock(&tasklist_lock);
 		for_each_process(p) {
-			if (p->mm == NULL)
-				continue;
+			struct task_struct *t;
 
-			pid = p->mm->context.id.u.pid;
+			t = find_lock_task_mm(p);
+			if (!t)
+				continue;
+			pid = t->mm->context.id.u.pid;
+			task_unlock(t);
 			os_kill_ptraced_process(pid, 1);
 		}
+		read_unlock(&tasklist_lock);
 	}
 }
 

arch/um/kernel/trap.c

@@ -30,6 +30,8 @@ int handle_page_fault(unsigned long address, unsigned long ip,
 	pmd_t *pmd;
 	pte_t *pte;
 	int err = -EFAULT;
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
+				 (is_write ? FAULT_FLAG_WRITE : 0);
 
 	*code_out = SEGV_MAPERR;
 
@@ -40,6 +42,7 @@ int handle_page_fault(unsigned long address, unsigned long ip,
 	if (in_atomic())
 		goto out_nosemaphore;
 
+retry:
 	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, address);
 	if (!vma)
@@ -65,7 +68,11 @@ int handle_page_fault(unsigned long address, unsigned long ip,
 	do {
 		int fault;
 
-		fault = handle_mm_fault(mm, vma, address, is_write ? FAULT_FLAG_WRITE : 0);
+		fault = handle_mm_fault(mm, vma, address, flags);
+
+		if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+			goto out_nosemaphore;
+
 		if (unlikely(fault & VM_FAULT_ERROR)) {
 			if (fault & VM_FAULT_OOM) {
 				goto out_of_memory;
@@ -75,10 +82,17 @@ int handle_page_fault(unsigned long address, unsigned long ip,
 			}
 			BUG();
 		}
-		if (fault & VM_FAULT_MAJOR)
-			current->maj_flt++;
-		else
-			current->min_flt++;
+		if (flags & FAULT_FLAG_ALLOW_RETRY) {
+			if (fault & VM_FAULT_MAJOR)
+				current->maj_flt++;
+			else
+				current->min_flt++;
+			if (fault & VM_FAULT_RETRY) {
+				flags &= ~FAULT_FLAG_ALLOW_RETRY;
+
+				goto retry;
+			}
+		}
 
 		pgd = pgd_offset(mm, address);
 		pud = pud_offset(pgd, address);

arch/x86/syscalls/syscall_32.tbl

@@ -355,3 +355,4 @@
 346	i386	setns			sys_setns
 347	i386	process_vm_readv	sys_process_vm_readv		compat_sys_process_vm_readv
 348	i386	process_vm_writev	sys_process_vm_writev		compat_sys_process_vm_writev
+349	i386	kcmp			sys_kcmp

arch/x86/syscalls/syscall_64.tbl

@@ -318,6 +318,8 @@
 309	common	getcpu			sys_getcpu
 310	64	process_vm_readv	sys_process_vm_readv
 311	64	process_vm_writev	sys_process_vm_writev
+312	64	kcmp			sys_kcmp
+
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
 # for native 64-bit operation.