Merge branch 'master' into for-next

Fast-forward merge with Linus to be able to merge patches
based on more recent version of the tree.

kernel/Makefile

@@ -10,7 +10,7 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o \
 	    kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
 	    hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
 	    notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \
-	    async.o range.o jump_label.o
+	    async.o range.o
 obj-y += groups.o
 
 ifdef CONFIG_FUNCTION_TRACER
@@ -107,6 +107,7 @@ obj-$(CONFIG_PERF_EVENTS) += events/
 obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o
 obj-$(CONFIG_PADATA) += padata.o
 obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
+obj-$(CONFIG_JUMP_LABEL) += jump_label.o
 
 ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is

kernel/audit.c

@@ -43,7 +43,7 @@
 
 #include <linux/init.h>
 #include <asm/types.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/slab.h>

kernel/auditsc.c

@@ -44,7 +44,7 @@
 
 #include <linux/init.h>
 #include <asm/types.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 #include <linux/fs.h>
 #include <linux/namei.h>
 #include <linux/mm.h>

kernel/cgroup.c

@@ -27,9 +27,11 @@
  */
 
 #include <linux/cgroup.h>
+#include <linux/cred.h>
 #include <linux/ctype.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
+#include <linux/init_task.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/mm.h>
@@ -59,7 +61,7 @@
 #include <linux/poll.h>
 #include <linux/flex_array.h> /* used in cgroup_attach_proc */
 
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 
 static DEFINE_MUTEX(cgroup_mutex);
 
@@ -1514,6 +1516,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 		struct cgroup *root_cgrp = &root->top_cgroup;
 		struct inode *inode;
 		struct cgroupfs_root *existing_root;
+		const struct cred *cred;
 		int i;
 
 		BUG_ON(sb->s_root != NULL);
@@ -1593,7 +1596,9 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 		BUG_ON(!list_empty(&root_cgrp->children));
 		BUG_ON(root->number_of_cgroups != 1);
 
+		cred = override_creds(&init_cred);
 		cgroup_populate_dir(root_cgrp);
+		revert_creds(cred);
 		mutex_unlock(&cgroup_mutex);
 		mutex_unlock(&inode->i_mutex);
 	} else {

kernel/compat.c

@@ -158,6 +158,7 @@ int put_compat_timespec(const struct timespec *ts, struct compat_timespec __user
 			__put_user(ts->tv_sec, &cts->tv_sec) ||
 			__put_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0;
 }
+EXPORT_SYMBOL_GPL(put_compat_timespec);
 
 static long compat_nanosleep_restart(struct restart_block *restart)
 {
@@ -992,11 +993,8 @@ asmlinkage long compat_sys_rt_sigsuspend(compat_sigset_t __user *unewset, compat
 	sigset_from_compat(&newset, &newset32);
 	sigdelsetmask(&newset, sigmask(SIGKILL)|sigmask(SIGSTOP));
 
-	spin_lock_irq(&current->sighand->siglock);
 	current->saved_sigmask = current->blocked;
-	current->blocked = newset;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+	set_current_blocked(&newset);
 
 	current->state = TASK_INTERRUPTIBLE;
 	schedule();

kernel/cpuset.c

@@ -55,7 +55,7 @@
 #include <linux/sort.h>
 
 #include <asm/uaccess.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 #include <linux/mutex.h>
 #include <linux/workqueue.h>
 #include <linux/cgroup.h>
@@ -2460,11 +2460,19 @@ static int cpuset_spread_node(int *rotor)
 
 int cpuset_mem_spread_node(void)
 {
+	if (current->cpuset_mem_spread_rotor == NUMA_NO_NODE)
+		current->cpuset_mem_spread_rotor =
+			node_random(&current->mems_allowed);
+
 	return cpuset_spread_node(&current->cpuset_mem_spread_rotor);
 }
 
 int cpuset_slab_spread_node(void)
 {
+	if (current->cpuset_slab_spread_rotor == NUMA_NO_NODE)
+		current->cpuset_slab_spread_rotor =
+			node_random(&current->mems_allowed);
+
 	return cpuset_spread_node(&current->cpuset_slab_spread_rotor);
 }
 

kernel/cred.c

@@ -508,10 +508,8 @@ int commit_creds(struct cred *new)
 		key_fsgid_changed(task);
 
 	/* do it
-	 * - What if a process setreuid()'s and this brings the
-	 *   new uid over his NPROC rlimit?  We can check this now
-	 *   cheaply with the new uid cache, so if it matters
-	 *   we should be checking for it.  -DaveM
+	 * RLIMIT_NPROC limits on user->processes have already been checked
+	 * in set_user().
 	 */
 	alter_cred_subscribers(new, 2);
 	if (new->user != old->user)

kernel/debug/debug_core.c

@@ -51,7 +51,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/byteorder.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 #include <asm/system.h>
 
 #include "debug_core.h"

kernel/debug/gdbstub.c

@@ -42,6 +42,8 @@
 /* Our I/O buffers. */
 static char			remcom_in_buffer[BUFMAX];
 static char			remcom_out_buffer[BUFMAX];
+static int			gdbstub_use_prev_in_buf;
+static int			gdbstub_prev_in_buf_pos;
 
 /* Storage for the registers, in GDB format. */
 static unsigned long		gdb_regs[(NUMREGBYTES +
@@ -58,6 +60,13 @@ static int gdbstub_read_wait(void)
 	int ret = -1;
 	int i;
 
+	if (unlikely(gdbstub_use_prev_in_buf)) {
+		if (gdbstub_prev_in_buf_pos < gdbstub_use_prev_in_buf)
+			return remcom_in_buffer[gdbstub_prev_in_buf_pos++];
+		else
+			gdbstub_use_prev_in_buf = 0;
+	}
+
 	/* poll any additional I/O interfaces that are defined */
 	while (ret < 0)
 		for (i = 0; kdb_poll_funcs[i] != NULL; i++) {
@@ -109,7 +118,6 @@ static void get_packet(char *buffer)
 			buffer[count] = ch;
 			count = count + 1;
 		}
-		buffer[count] = 0;
 
 		if (ch == '#') {
 			xmitcsum = hex_to_bin(gdbstub_read_wait()) << 4;
@@ -124,6 +132,7 @@ static void get_packet(char *buffer)
 			if (dbg_io_ops->flush)
 				dbg_io_ops->flush();
 		}
+		buffer[count] = 0;
 	} while (checksum != xmitcsum);
 }
 
@@ -1082,12 +1091,11 @@ int gdbstub_state(struct kgdb_state *ks, char *cmd)
 	case 'c':
 		strcpy(remcom_in_buffer, cmd);
 		return 0;
-	case '?':
-		gdb_cmd_status(ks);
-		break;
-	case '\0':
-		strcpy(remcom_out_buffer, "");
-		break;
+	case '$':
+		strcpy(remcom_in_buffer, cmd);
+		gdbstub_use_prev_in_buf = strlen(remcom_in_buffer);
+		gdbstub_prev_in_buf_pos = 0;
+		return 0;
 	}
 	dbg_io_ops->write_char('+');
 	put_packet(remcom_out_buffer);

kernel/debug/kdb/kdb_bt.c

@@ -112,9 +112,8 @@ kdb_bt(int argc, const char **argv)
 	unsigned long addr;
 	long offset;
 
-	kdbgetintenv("BTARGS", &argcount);	/* Arguments to print */
-	kdbgetintenv("BTAPROMPT", &btaprompt);	/* Prompt after each
-						 * proc in bta */
+	/* Prompt after each proc in bta */
+	kdbgetintenv("BTAPROMPT", &btaprompt);
 
 	if (strcmp(argv[0], "bta") == 0) {
 		struct task_struct *g, *p;

kernel/debug/kdb/kdb_cmds

@@ -18,16 +18,12 @@ defcmd dumpcommon "" "Common kdb debugging"
 endefcmd
 
 defcmd dumpall "" "First line debugging"
-  set BTSYMARG 1
-  set BTARGS 9
   pid R
   -dumpcommon
   -bta
 endefcmd
 
 defcmd dumpcpu "" "Same as dumpall but only tasks on cpus"
-  set BTSYMARG 1
-  set BTARGS 9
   pid R
   -dumpcommon
   -btc

kernel/debug/kdb/kdb_debugger.c

@@ -30,6 +30,8 @@ EXPORT_SYMBOL_GPL(kdb_poll_funcs);
 int kdb_poll_idx = 1;
 EXPORT_SYMBOL_GPL(kdb_poll_idx);
 
+static struct kgdb_state *kdb_ks;
+
 int kdb_stub(struct kgdb_state *ks)
 {
 	int error = 0;
@@ -39,6 +41,7 @@ int kdb_stub(struct kgdb_state *ks)
 	kdb_dbtrap_t db_result = KDB_DB_NOBPT;
 	int i;
 
+	kdb_ks = ks;
 	if (KDB_STATE(REENTRY)) {
 		reason = KDB_REASON_SWITCH;
 		KDB_STATE_CLEAR(REENTRY);
@@ -123,20 +126,8 @@ int kdb_stub(struct kgdb_state *ks)
 	KDB_STATE_CLEAR(PAGER);
 	kdbnearsym_cleanup();
 	if (error == KDB_CMD_KGDB) {
-		if (KDB_STATE(DOING_KGDB) || KDB_STATE(DOING_KGDB2)) {
-	/*
-	 * This inteface glue which allows kdb to transition in into
-	 * the gdb stub.  In order to do this the '?' or '' gdb serial
-	 * packet response is processed here.  And then control is
-	 * passed to the gdbstub.
-	 */
-			if (KDB_STATE(DOING_KGDB))
-				gdbstub_state(ks, "?");
-			else
-				gdbstub_state(ks, "");
+		if (KDB_STATE(DOING_KGDB))
 			KDB_STATE_CLEAR(DOING_KGDB);
-			KDB_STATE_CLEAR(DOING_KGDB2);
-		}
 		return DBG_PASS_EVENT;
 	}
 	kdb_bp_install(ks->linux_regs);
@@ -166,3 +157,7 @@ int kdb_stub(struct kgdb_state *ks)
 	return kgdb_info[ks->cpu].ret_state;
 }
 
+void kdb_gdb_state_pass(char *buf)
+{
+	gdbstub_state(kdb_ks, buf);
+}

kernel/debug/kdb/kdb_io.c

@@ -31,15 +31,21 @@ char kdb_prompt_str[CMD_BUFLEN];
 
 int kdb_trap_printk;
 
-static void kgdb_transition_check(char *buffer)
+static int kgdb_transition_check(char *buffer)
 {
-	int slen = strlen(buffer);
-	if (strncmp(buffer, "$?#3f", slen) != 0 &&
-	    strncmp(buffer, "$qSupported#37", slen) != 0 &&
-	    strncmp(buffer, "+$qSupported#37", slen) != 0) {
+	if (buffer[0] != '+' && buffer[0] != '$') {
 		KDB_STATE_SET(KGDB_TRANS);
 		kdb_printf("%s", buffer);
+	} else {
+		int slen = strlen(buffer);
+		if (slen > 3 && buffer[slen - 3] == '#') {
+			kdb_gdb_state_pass(buffer);
+			strcpy(buffer, "kgdb");
+			KDB_STATE_SET(DOING_KGDB);
+			return 1;
+		}
 	}
+	return 0;
 }
 
 static int kdb_read_get_key(char *buffer, size_t bufsize)
@@ -251,6 +257,10 @@ poll_again:
 	case 13: /* enter */
 		*lastchar++ = '\n';
 		*lastchar++ = '\0';
+		if (!KDB_STATE(KGDB_TRANS)) {
+			KDB_STATE_SET(KGDB_TRANS);
+			kdb_printf("%s", buffer);
+		}
 		kdb_printf("\n");
 		return buffer;
 	case 4: /* Del */
@@ -382,22 +392,26 @@ poll_again:
 				 * printed characters if we think that
 				 * kgdb is connecting, until the check
 				 * fails */
-				if (!KDB_STATE(KGDB_TRANS))
-					kgdb_transition_check(buffer);
-				else
+				if (!KDB_STATE(KGDB_TRANS)) {
+					if (kgdb_transition_check(buffer))
+						return buffer;
+				} else {
 					kdb_printf("%c", key);
+				}
 			}
 			/* Special escape to kgdb */
 			if (lastchar - buffer >= 5 &&
 			    strcmp(lastchar - 5, "$?#3f") == 0) {
+				kdb_gdb_state_pass(lastchar - 5);
 				strcpy(buffer, "kgdb");
 				KDB_STATE_SET(DOING_KGDB);
 				return buffer;
 			}
-			if (lastchar - buffer >= 14 &&
-			    strcmp(lastchar - 14, "$qSupported#37") == 0) {
+			if (lastchar - buffer >= 11 &&
+			    strcmp(lastchar - 11, "$qSupported") == 0) {
+				kdb_gdb_state_pass(lastchar - 11);
 				strcpy(buffer, "kgdb");
-				KDB_STATE_SET(DOING_KGDB2);
+				KDB_STATE_SET(DOING_KGDB);
 				return buffer;
 			}
 		}

kernel/debug/kdb/kdb_main.c

@@ -145,7 +145,6 @@ static char *__env[] = {
 #endif
  "RADIX=16",
  "MDCOUNT=8",			/* lines of md output */
- "BTARGS=9",			/* 9 possible args in bt */
  KDB_PLATFORM_ENV,
  "DTABCOUNT=30",
  "NOSECT=1",
@@ -172,6 +171,7 @@ static char *__env[] = {
  (char *)0,
  (char *)0,
  (char *)0,
+ (char *)0,
 };
 
 static const int __nenv = (sizeof(__env) / sizeof(char *));
@@ -1386,7 +1386,7 @@ int kdb_main_loop(kdb_reason_t reason, kdb_reason_t reason2, int error,
 		}
 
 		if (result == KDB_CMD_KGDB) {
-			if (!(KDB_STATE(DOING_KGDB) || KDB_STATE(DOING_KGDB2)))
+			if (!KDB_STATE(DOING_KGDB))
 				kdb_printf("Entering please attach debugger "
 					   "or use $D#44+ or $3#33\n");
 			break;

kernel/debug/kdb/kdb_private.h

@@ -21,7 +21,6 @@
 #define KDB_CMD_SS	(-1003)
 #define KDB_CMD_SSB	(-1004)
 #define KDB_CMD_KGDB (-1005)
-#define KDB_CMD_KGDB2 (-1006)
 
 /* Internal debug flags */
 #define KDB_DEBUG_FLAG_BP	0x0002	/* Breakpoint subsystem debug */
@@ -146,7 +145,6 @@ extern int kdb_state;
 						 * keyboard on this cpu */
 #define KDB_STATE_KEXEC		0x00040000	/* kexec issued */
 #define KDB_STATE_DOING_KGDB	0x00080000	/* kgdb enter now issued */
-#define KDB_STATE_DOING_KGDB2	0x00100000	/* kgdb enter now issued */
 #define KDB_STATE_KGDB_TRANS	0x00200000	/* Transition to kgdb */
 #define KDB_STATE_ARCH		0xff000000	/* Reserved for arch
 						 * specific use */
@@ -218,6 +216,7 @@ extern void kdb_print_nameval(const char *name, unsigned long val);
 extern void kdb_send_sig_info(struct task_struct *p, struct siginfo *info);
 extern void kdb_meminfo_proc_show(void);
 extern char *kdb_getstr(char *, size_t, char *);
+extern void kdb_gdb_state_pass(char *buf);
 
 /* Defines for kdb_symbol_print */
 #define KDB_SP_SPACEB	0x0001		/* Space before string */

kernel/events/core.c

@@ -399,14 +399,54 @@ void perf_cgroup_switch(struct task_struct *task, int mode)
 	local_irq_restore(flags);
 }
 
-static inline void perf_cgroup_sched_out(struct task_struct *task)
+static inline void perf_cgroup_sched_out(struct task_struct *task,
+					 struct task_struct *next)
 {
-	perf_cgroup_switch(task, PERF_CGROUP_SWOUT);
+	struct perf_cgroup *cgrp1;
+	struct perf_cgroup *cgrp2 = NULL;
+
+	/*
+	 * we come here when we know perf_cgroup_events > 0
+	 */
+	cgrp1 = perf_cgroup_from_task(task);
+
+	/*
+	 * next is NULL when called from perf_event_enable_on_exec()
+	 * that will systematically cause a cgroup_switch()
+	 */
+	if (next)
+		cgrp2 = perf_cgroup_from_task(next);
+
+	/*
+	 * only schedule out current cgroup events if we know
+	 * that we are switching to a different cgroup. Otherwise,
+	 * do no touch the cgroup events.
+	 */
+	if (cgrp1 != cgrp2)
+		perf_cgroup_switch(task, PERF_CGROUP_SWOUT);
 }
 
-static inline void perf_cgroup_sched_in(struct task_struct *task)
+static inline void perf_cgroup_sched_in(struct task_struct *prev,
+					struct task_struct *task)
 {
-	perf_cgroup_switch(task, PERF_CGROUP_SWIN);
+	struct perf_cgroup *cgrp1;
+	struct perf_cgroup *cgrp2 = NULL;
+
+	/*
+	 * we come here when we know perf_cgroup_events > 0
+	 */
+	cgrp1 = perf_cgroup_from_task(task);
+
+	/* prev can never be NULL */
+	cgrp2 = perf_cgroup_from_task(prev);
+
+	/*
+	 * only need to schedule in cgroup events if we are changing
+	 * cgroup during ctxsw. Cgroup events were not scheduled
+	 * out of ctxsw out if that was not the case.
+	 */
+	if (cgrp1 != cgrp2)
+		perf_cgroup_switch(task, PERF_CGROUP_SWIN);
 }
 
 static inline int perf_cgroup_connect(int fd, struct perf_event *event,
@@ -518,11 +558,13 @@ static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx)
 {
 }
 
-static inline void perf_cgroup_sched_out(struct task_struct *task)
+static inline void perf_cgroup_sched_out(struct task_struct *task,
+					 struct task_struct *next)
 {
 }
 
-static inline void perf_cgroup_sched_in(struct task_struct *task)
+static inline void perf_cgroup_sched_in(struct task_struct *prev,
+					struct task_struct *task)
 {
 }
 
@@ -1988,7 +2030,7 @@ void __perf_event_task_sched_out(struct task_struct *task,
 	 * cgroup event are system-wide mode only
 	 */
 	if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
-		perf_cgroup_sched_out(task);
+		perf_cgroup_sched_out(task, next);
 }
 
 static void task_ctx_sched_out(struct perf_event_context *ctx)
@@ -2153,7 +2195,8 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
  * accessing the event control register. If a NMI hits, then it will
  * keep the event running.
  */
-void __perf_event_task_sched_in(struct task_struct *task)
+void __perf_event_task_sched_in(struct task_struct *prev,
+				struct task_struct *task)
 {
 	struct perf_event_context *ctx;
 	int ctxn;
@@ -2171,7 +2214,7 @@ void __perf_event_task_sched_in(struct task_struct *task)
 	 * cgroup event are system-wide mode only
 	 */
 	if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
-		perf_cgroup_sched_in(task);
+		perf_cgroup_sched_in(prev, task);
 }
 
 static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
@@ -2427,7 +2470,7 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx)
 	 * ctxswin cgroup events which are already scheduled
 	 * in.
 	 */
-	perf_cgroup_sched_out(current);
+	perf_cgroup_sched_out(current, NULL);
 
 	raw_spin_lock(&ctx->lock);
 	task_ctx_sched_out(ctx);
@@ -3353,8 +3396,8 @@ static int perf_event_index(struct perf_event *event)
 }
 
 static void calc_timer_values(struct perf_event *event,
-				u64 *running,
-				u64 *enabled)
+				u64 *enabled,
+				u64 *running)
 {
 	u64 now, ctx_time;
 

kernel/exit.c

@@ -980,6 +980,7 @@ NORET_TYPE void do_exit(long code)
 	trace_sched_process_exit(tsk);
 
 	exit_sem(tsk);
+	exit_shm(tsk);
 	exit_files(tsk);
 	exit_fs(tsk);
 	check_stack_usage();

kernel/fork.c

@@ -80,7 +80,7 @@
  * Protected counters by write_lock_irq(&tasklist_lock)
  */
 unsigned long total_forks;	/* Handle normal Linux uptimes. */
-int nr_threads; 		/* The idle threads do not count.. */
+int nr_threads;			/* The idle threads do not count.. */
 
 int max_threads;		/* tunable limit on nr_threads */
 
@@ -232,7 +232,7 @@ void __init fork_init(unsigned long mempages)
 	/*
 	 * we need to allow at least 20 threads to boot a system
 	 */
-	if(max_threads < 20)
+	if (max_threads < 20)
 		max_threads = 20;
 
 	init_task.signal->rlim[RLIMIT_NPROC].rlim_cur = max_threads/2;
@@ -268,7 +268,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 		return NULL;
 	}
 
- 	err = arch_dup_task_struct(tsk, orig);
+	err = arch_dup_task_struct(tsk, orig);
 	if (err)
 		goto out;
 
@@ -288,8 +288,11 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 	tsk->stack_canary = get_random_int();
 #endif
 
-	/* One for us, one for whoever does the "release_task()" (usually parent) */
-	atomic_set(&tsk->usage,2);
+	/*
+	 * One for us, one for whoever does the "release_task()" (usually
+	 * parent)
+	 */
+	atomic_set(&tsk->usage, 2);
 #ifdef CONFIG_BLK_DEV_IO_TRACE
 	tsk->btrace_seq = 0;
 #endif
@@ -437,7 +440,7 @@ fail_nomem:
 	goto out;
 }
 
-static inline int mm_alloc_pgd(struct mm_struct * mm)
+static inline int mm_alloc_pgd(struct mm_struct *mm)
 {
 	mm->pgd = pgd_alloc(mm);
 	if (unlikely(!mm->pgd))
@@ -445,7 +448,7 @@ static inline int mm_alloc_pgd(struct mm_struct * mm)
 	return 0;
 }
 
-static inline void mm_free_pgd(struct mm_struct * mm)
+static inline void mm_free_pgd(struct mm_struct *mm)
 {
 	pgd_free(mm, mm->pgd);
 }
@@ -482,7 +485,7 @@ static void mm_init_aio(struct mm_struct *mm)
 #endif
 }
 
-static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
+static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
 {
 	atomic_set(&mm->mm_users, 1);
 	atomic_set(&mm->mm_count, 1);
@@ -513,9 +516,9 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
 /*
  * Allocate and initialize an mm_struct.
  */
-struct mm_struct * mm_alloc(void)
+struct mm_struct *mm_alloc(void)
 {
-	struct mm_struct * mm;
+	struct mm_struct *mm;
 
 	mm = allocate_mm();
 	if (!mm)
@@ -583,7 +586,7 @@ void added_exe_file_vma(struct mm_struct *mm)
 void removed_exe_file_vma(struct mm_struct *mm)
 {
 	mm->num_exe_file_vmas--;
-	if ((mm->num_exe_file_vmas == 0) && mm->exe_file){
+	if ((mm->num_exe_file_vmas == 0) && mm->exe_file) {
 		fput(mm->exe_file);
 		mm->exe_file = NULL;
 	}
@@ -775,9 +778,9 @@ fail_nocontext:
 	return NULL;
 }
 
-static int copy_mm(unsigned long clone_flags, struct task_struct * tsk)
+static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
 {
-	struct mm_struct * mm, *oldmm;
+	struct mm_struct *mm, *oldmm;
 	int retval;
 
 	tsk->min_flt = tsk->maj_flt = 0;
@@ -844,7 +847,7 @@ static int copy_fs(unsigned long clone_flags, struct task_struct *tsk)
 	return 0;
 }
 
-static int copy_files(unsigned long clone_flags, struct task_struct * tsk)
+static int copy_files(unsigned long clone_flags, struct task_struct *tsk)
 {
 	struct files_struct *oldf, *newf;
 	int error = 0;
@@ -1108,6 +1111,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		    p->real_cred->user != INIT_USER)
 			goto bad_fork_free;
 	}
+	current->flags &= ~PF_NPROC_EXCEEDED;
 
 	retval = copy_creds(p, clone_flags);
 	if (retval < 0)
@@ -1166,13 +1170,17 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	cgroup_fork(p);
 #ifdef CONFIG_NUMA
 	p->mempolicy = mpol_dup(p->mempolicy);
- 	if (IS_ERR(p->mempolicy)) {
- 		retval = PTR_ERR(p->mempolicy);
- 		p->mempolicy = NULL;
- 		goto bad_fork_cleanup_cgroup;
- 	}
+	if (IS_ERR(p->mempolicy)) {
+		retval = PTR_ERR(p->mempolicy);
+		p->mempolicy = NULL;
+		goto bad_fork_cleanup_cgroup;
+	}
 	mpol_fix_fork_child_flag(p);
 #endif
+#ifdef CONFIG_CPUSETS
+	p->cpuset_mem_spread_rotor = NUMA_NO_NODE;
+	p->cpuset_slab_spread_rotor = NUMA_NO_NODE;
+#endif
 #ifdef CONFIG_TRACE_IRQFLAGS
 	p->irq_events = 0;
 #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
@@ -1212,25 +1220,33 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	retval = perf_event_init_task(p);
 	if (retval)
 		goto bad_fork_cleanup_policy;
-
-	if ((retval = audit_alloc(p)))
+	retval = audit_alloc(p);
+	if (retval)
 		goto bad_fork_cleanup_policy;
 	/* copy all the process information */
-	if ((retval = copy_semundo(clone_flags, p)))
+	retval = copy_semundo(clone_flags, p);
+	if (retval)
 		goto bad_fork_cleanup_audit;
-	if ((retval = copy_files(clone_flags, p)))
+	retval = copy_files(clone_flags, p);
+	if (retval)
 		goto bad_fork_cleanup_semundo;
-	if ((retval = copy_fs(clone_flags, p)))
+	retval = copy_fs(clone_flags, p);
+	if (retval)
 		goto bad_fork_cleanup_files;
-	if ((retval = copy_sighand(clone_flags, p)))
+	retval = copy_sighand(clone_flags, p);
+	if (retval)
 		goto bad_fork_cleanup_fs;
-	if ((retval = copy_signal(clone_flags, p)))
+	retval = copy_signal(clone_flags, p);
+	if (retval)
 		goto bad_fork_cleanup_sighand;
-	if ((retval = copy_mm(clone_flags, p)))
+	retval = copy_mm(clone_flags, p);
+	if (retval)
 		goto bad_fork_cleanup_signal;
-	if ((retval = copy_namespaces(clone_flags, p)))
+	retval = copy_namespaces(clone_flags, p);
+	if (retval)
 		goto bad_fork_cleanup_mm;
-	if ((retval = copy_io(clone_flags, p)))
+	retval = copy_io(clone_flags, p);
+	if (retval)
 		goto bad_fork_cleanup_namespaces;
 	retval = copy_thread(clone_flags, stack_start, stack_size, p, regs);
 	if (retval)
@@ -1252,7 +1268,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	/*
 	 * Clear TID on mm_release()?
 	 */
-	p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr: NULL;
+	p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr : NULL;
 #ifdef CONFIG_BLOCK
 	p->plug = NULL;
 #endif
@@ -1320,7 +1336,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	 * it's process group.
 	 * A fatal signal pending means that current will exit, so the new
 	 * thread can't slip out of an OOM kill (or normal SIGKILL).
- 	 */
+	*/
 	recalc_sigpending();
 	if (signal_pending(current)) {
 		spin_unlock(&current->sighand->siglock);
@@ -1681,12 +1697,14 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 	 */
 	if (unshare_flags & (CLONE_NEWIPC|CLONE_SYSVSEM))
 		do_sysvsem = 1;
-	if ((err = unshare_fs(unshare_flags, &new_fs)))
+	err = unshare_fs(unshare_flags, &new_fs);
+	if (err)
 		goto bad_unshare_out;
-	if ((err = unshare_fd(unshare_flags, &new_fd)))
+	err = unshare_fd(unshare_flags, &new_fd);
+	if (err)
 		goto bad_unshare_cleanup_fs;
-	if ((err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy,
-			new_fs)))
+	err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy, new_fs);
+	if (err)
 		goto bad_unshare_cleanup_fd;
 
 	if (new_fs || new_fd || do_sysvsem || new_nsproxy) {

kernel/futex.c

@@ -218,6 +218,8 @@ static void drop_futex_key_refs(union futex_key *key)
  * @uaddr:	virtual address of the futex
  * @fshared:	0 for a PROCESS_PRIVATE futex, 1 for PROCESS_SHARED
  * @key:	address where result is stored.
+ * @rw:		mapping needs to be read/write (values: VERIFY_READ,
+ *              VERIFY_WRITE)
  *
  * Returns a negative error code or 0
  * The key words are stored in *key on success.
@@ -229,12 +231,12 @@ static void drop_futex_key_refs(union futex_key *key)
  * lock_page() might sleep, the caller should not hold a spinlock.
  */
 static int
-get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key)
+get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
 {
 	unsigned long address = (unsigned long)uaddr;
 	struct mm_struct *mm = current->mm;
 	struct page *page, *page_head;
-	int err;
+	int err, ro = 0;
 
 	/*
 	 * The futex address must be "naturally" aligned.
@@ -262,8 +264,18 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key)
 
 again:
 	err = get_user_pages_fast(address, 1, 1, &page);
+	/*
+	 * If write access is not required (eg. FUTEX_WAIT), try
+	 * and get read-only access.
+	 */
+	if (err == -EFAULT && rw == VERIFY_READ) {
+		err = get_user_pages_fast(address, 1, 0, &page);
+		ro = 1;
+	}
 	if (err < 0)
 		return err;
+	else
+		err = 0;
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	page_head = page;
@@ -305,6 +317,13 @@ again:
 	if (!page_head->mapping) {
 		unlock_page(page_head);
 		put_page(page_head);
+		/*
+		* ZERO_PAGE pages don't have a mapping. Avoid a busy loop
+		* trying to find one. RW mapping would have COW'd (and thus
+		* have a mapping) so this page is RO and won't ever change.
+		*/
+		if ((page_head == ZERO_PAGE(address)))
+			return -EFAULT;
 		goto again;
 	}
 
@@ -316,6 +335,15 @@ again:
 	 * the object not the particular process.
 	 */
 	if (PageAnon(page_head)) {
+		/*
+		 * A RO anonymous page will never change and thus doesn't make
+		 * sense for futex operations.
+		 */
+		if (ro) {
+			err = -EFAULT;
+			goto out;
+		}
+
 		key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */
 		key->private.mm = mm;
 		key->private.address = address;
@@ -327,9 +355,10 @@ again:
 
 	get_futex_key_refs(key);
 
+out:
 	unlock_page(page_head);
 	put_page(page_head);
-	return 0;
+	return err;
 }
 
 static inline void put_futex_key(union futex_key *key)
@@ -940,7 +969,7 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
 	if (!bitset)
 		return -EINVAL;
 
-	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key);
+	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, VERIFY_READ);
 	if (unlikely(ret != 0))
 		goto out;
 
@@ -986,10 +1015,10 @@ futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2,
 	int ret, op_ret;
 
 retry:
-	ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1);
+	ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, VERIFY_READ);
 	if (unlikely(ret != 0))
 		goto out;
-	ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2);
+	ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE);
 	if (unlikely(ret != 0))
 		goto out_put_key1;
 
@@ -1243,10 +1272,11 @@ retry:
 		pi_state = NULL;
 	}
 
-	ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1);
+	ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, VERIFY_READ);
 	if (unlikely(ret != 0))
 		goto out;
-	ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2);
+	ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2,
+			    requeue_pi ? VERIFY_WRITE : VERIFY_READ);
 	if (unlikely(ret != 0))
 		goto out_put_key1;
 
@@ -1790,7 +1820,7 @@ static int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags,
 	 * while the syscall executes.
 	 */
 retry:
-	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q->key);
+	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q->key, VERIFY_READ);
 	if (unlikely(ret != 0))
 		return ret;
 
@@ -1941,7 +1971,7 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, int detect,
 	}
 
 retry:
-	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q.key);
+	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q.key, VERIFY_WRITE);
 	if (unlikely(ret != 0))
 		goto out;
 
@@ -2060,7 +2090,7 @@ retry:
 	if ((uval & FUTEX_TID_MASK) != vpid)
 		return -EPERM;
 
-	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key);
+	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, VERIFY_WRITE);
 	if (unlikely(ret != 0))
 		goto out;
 
@@ -2249,7 +2279,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 	debug_rt_mutex_init_waiter(&rt_waiter);
 	rt_waiter.task = NULL;
 
-	ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2);
+	ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE);
 	if (unlikely(ret != 0))
 		goto out;
 

kernel/gcov/Kconfig

@@ -3,7 +3,7 @@ menu "GCOV-based kernel profiling"
 config GCOV_KERNEL
 	bool "Enable gcov-based kernel profiling"
 	depends on DEBUG_FS
-	select CONSTRUCTORS
+	select CONSTRUCTORS if !UML
 	default n
 	---help---
 	This option enables gcov-based code profiling (e.g. for code coverage

kernel/irq/Kconfig

@@ -52,6 +52,10 @@ config IRQ_EDGE_EOI_HANDLER
 config GENERIC_IRQ_CHIP
        bool
 
+# Generic irq_domain hw <--> linux irq number translation
+config IRQ_DOMAIN
+	bool
+
 # Support forced irq threading
 config IRQ_FORCED_THREADING
        bool

kernel/irq/Makefile

@@ -2,6 +2,7 @@
 obj-y := irqdesc.o handle.o manage.o spurious.o resend.o chip.o dummychip.o devres.o
 obj-$(CONFIG_GENERIC_IRQ_CHIP) += generic-chip.o
 obj-$(CONFIG_GENERIC_IRQ_PROBE) += autoprobe.o
+obj-$(CONFIG_IRQ_DOMAIN) += irqdomain.o
 obj-$(CONFIG_PROC_FS) += proc.o
 obj-$(CONFIG_GENERIC_PENDING_IRQ) += migration.o
 obj-$(CONFIG_PM_SLEEP) += pm.o

kernel/irq/generic-chip.c

@@ -246,7 +246,7 @@ void irq_setup_generic_chip(struct irq_chip_generic *gc, u32 msk,
 		gc->mask_cache = irq_reg_readl(gc->reg_base + ct->regs.mask);
 
 	for (i = gc->irq_base; msk; msk >>= 1, i++) {
-		if (!msk & 0x01)
+		if (!(msk & 0x01))
 			continue;
 
 		if (flags & IRQ_GC_INIT_NESTED_LOCK)
@@ -301,7 +301,7 @@ void irq_remove_generic_chip(struct irq_chip_generic *gc, u32 msk,
 	raw_spin_unlock(&gc_lock);
 
 	for (; msk; msk >>= 1, i++) {
-		if (!msk & 0x01)
+		if (!(msk & 0x01))
 			continue;
 
 		/* Remove handler first. That will mask the irq line */

kernel/irq/irqdesc.c

@@ -70,7 +70,8 @@ static inline void desc_smp_init(struct irq_desc *desc, int node) { }
 static inline int desc_node(struct irq_desc *desc) { return 0; }
 #endif
 
-static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node)
+static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node,
+		struct module *owner)
 {
 	int cpu;
 
@@ -86,6 +87,7 @@ static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node)
 	desc->irq_count = 0;
 	desc->irqs_unhandled = 0;
 	desc->name = NULL;
+	desc->owner = owner;
 	for_each_possible_cpu(cpu)
 		*per_cpu_ptr(desc->kstat_irqs, cpu) = 0;
 	desc_smp_init(desc, node);
@@ -128,7 +130,7 @@ static void free_masks(struct irq_desc *desc)
 static inline void free_masks(struct irq_desc *desc) { }
 #endif
 
-static struct irq_desc *alloc_desc(int irq, int node)
+static struct irq_desc *alloc_desc(int irq, int node, struct module *owner)
 {
 	struct irq_desc *desc;
 	gfp_t gfp = GFP_KERNEL;
@@ -147,7 +149,7 @@ static struct irq_desc *alloc_desc(int irq, int node)
 	raw_spin_lock_init(&desc->lock);
 	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
 
-	desc_set_defaults(irq, desc, node);
+	desc_set_defaults(irq, desc, node, owner);
 
 	return desc;
 
@@ -173,13 +175,14 @@ static void free_desc(unsigned int irq)
 	kfree(desc);
 }
 
-static int alloc_descs(unsigned int start, unsigned int cnt, int node)
+static int alloc_descs(unsigned int start, unsigned int cnt, int node,
+		       struct module *owner)
 {
 	struct irq_desc *desc;
 	int i;
 
 	for (i = 0; i < cnt; i++) {
-		desc = alloc_desc(start + i, node);
+		desc = alloc_desc(start + i, node, owner);
 		if (!desc)
 			goto err;
 		mutex_lock(&sparse_irq_lock);
@@ -227,7 +230,7 @@ int __init early_irq_init(void)
 		nr_irqs = initcnt;
 
 	for (i = 0; i < initcnt; i++) {
-		desc = alloc_desc(i, node);
+		desc = alloc_desc(i, node, NULL);
 		set_bit(i, allocated_irqs);
 		irq_insert_desc(i, desc);
 	}
@@ -261,7 +264,7 @@ int __init early_irq_init(void)
 		alloc_masks(&desc[i], GFP_KERNEL, node);
 		raw_spin_lock_init(&desc[i].lock);
 		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
-		desc_set_defaults(i, &desc[i], node);
+		desc_set_defaults(i, &desc[i], node, NULL);
 	}
 	return arch_early_irq_init();
 }
@@ -276,8 +279,16 @@ static void free_desc(unsigned int irq)
 	dynamic_irq_cleanup(irq);
 }
 
-static inline int alloc_descs(unsigned int start, unsigned int cnt, int node)
+static inline int alloc_descs(unsigned int start, unsigned int cnt, int node,
+			      struct module *owner)
 {
+	u32 i;
+
+	for (i = 0; i < cnt; i++) {
+		struct irq_desc *desc = irq_to_desc(start + i);
+
+		desc->owner = owner;
+	}
 	return start;
 }
 
@@ -333,11 +344,13 @@ EXPORT_SYMBOL_GPL(irq_free_descs);
  * @from:	Start the search from this irq number
  * @cnt:	Number of consecutive irqs to allocate.
  * @node:	Preferred node on which the irq descriptor should be allocated
+ * @owner:	Owning module (can be NULL)
  *
  * Returns the first irq number or error code
  */
 int __ref
-irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node)
+__irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
+		  struct module *owner)
 {
 	int start, ret;
 
@@ -366,13 +379,13 @@ irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node)
 
 	bitmap_set(allocated_irqs, start, cnt);
 	mutex_unlock(&sparse_irq_lock);
-	return alloc_descs(start, cnt, node);
+	return alloc_descs(start, cnt, node, owner);
 
 err:
 	mutex_unlock(&sparse_irq_lock);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(irq_alloc_descs);
+EXPORT_SYMBOL_GPL(__irq_alloc_descs);
 
 /**
  * irq_reserve_irqs - mark irqs allocated
@@ -440,7 +453,7 @@ void dynamic_irq_cleanup(unsigned int irq)
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
-	desc_set_defaults(irq, desc, desc_node(desc));
+	desc_set_defaults(irq, desc, desc_node(desc), NULL);
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 }
 

kernel/irq/irqdomain.c

@@ -0,0 +1,180 @@
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+
+static LIST_HEAD(irq_domain_list);
+static DEFINE_MUTEX(irq_domain_mutex);
+
+/**
+ * irq_domain_add() - Register an irq_domain
+ * @domain: ptr to initialized irq_domain structure
+ *
+ * Registers an irq_domain structure.  The irq_domain must at a minimum be
+ * initialized with an ops structure pointer, and either a ->to_irq hook or
+ * a valid irq_base value.  Everything else is optional.
+ */
+void irq_domain_add(struct irq_domain *domain)
+{
+	struct irq_data *d;
+	int hwirq;
+
+	/*
+	 * This assumes that the irq_domain owner has already allocated
+	 * the irq_descs.  This block will be removed when support for dynamic
+	 * allocation of irq_descs is added to irq_domain.
+	 */
+	for (hwirq = 0; hwirq < domain->nr_irq; hwirq++) {
+		d = irq_get_irq_data(irq_domain_to_irq(domain, hwirq));
+		if (d || d->domain) {
+			/* things are broken; just report, don't clean up */
+			WARN(1, "error: irq_desc already assigned to a domain");
+			return;
+		}
+		d->domain = domain;
+		d->hwirq = hwirq;
+	}
+
+	mutex_lock(&irq_domain_mutex);
+	list_add(&domain->list, &irq_domain_list);
+	mutex_unlock(&irq_domain_mutex);
+}
+
+/**
+ * irq_domain_del() - Unregister an irq_domain
+ * @domain: ptr to registered irq_domain.
+ */
+void irq_domain_del(struct irq_domain *domain)
+{
+	struct irq_data *d;
+	int hwirq;
+
+	mutex_lock(&irq_domain_mutex);
+	list_del(&domain->list);
+	mutex_unlock(&irq_domain_mutex);
+
+	/* Clear the irq_domain assignments */
+	for (hwirq = 0; hwirq < domain->nr_irq; hwirq++) {
+		d = irq_get_irq_data(irq_domain_to_irq(domain, hwirq));
+		d->domain = NULL;
+	}
+}
+
+#if defined(CONFIG_OF_IRQ)
+/**
+ * irq_create_of_mapping() - Map a linux irq number from a DT interrupt spec
+ *
+ * Used by the device tree interrupt mapping code to translate a device tree
+ * interrupt specifier to a valid linux irq number.  Returns either a valid
+ * linux IRQ number or 0.
+ *
+ * When the caller no longer need the irq number returned by this function it
+ * should arrange to call irq_dispose_mapping().
+ */
+unsigned int irq_create_of_mapping(struct device_node *controller,
+				   const u32 *intspec, unsigned int intsize)
+{
+	struct irq_domain *domain;
+	unsigned long hwirq;
+	unsigned int irq, type;
+	int rc = -EINVAL;
+
+	/* Find a domain which can translate the irq spec */
+	mutex_lock(&irq_domain_mutex);
+	list_for_each_entry(domain, &irq_domain_list, list) {
+		if (!domain->ops->dt_translate)
+			continue;
+		rc = domain->ops->dt_translate(domain, controller,
+					intspec, intsize, &hwirq, &type);
+		if (rc == 0)
+			break;
+	}
+	mutex_unlock(&irq_domain_mutex);
+
+	if (rc != 0)
+		return 0;
+
+	irq = irq_domain_to_irq(domain, hwirq);
+	if (type != IRQ_TYPE_NONE)
+		irq_set_irq_type(irq, type);
+	pr_debug("%s: mapped hwirq=%i to irq=%i, flags=%x\n",
+		 controller->full_name, (int)hwirq, irq, type);
+	return irq;
+}
+EXPORT_SYMBOL_GPL(irq_create_of_mapping);
+
+/**
+ * irq_dispose_mapping() - Discard a mapping created by irq_create_of_mapping()
+ * @irq: linux irq number to be discarded
+ *
+ * Calling this function indicates the caller no longer needs a reference to
+ * the linux irq number returned by a prior call to irq_create_of_mapping().
+ */
+void irq_dispose_mapping(unsigned int irq)
+{
+	/*
+	 * nothing yet; will be filled when support for dynamic allocation of
+	 * irq_descs is added to irq_domain
+	 */
+}
+EXPORT_SYMBOL_GPL(irq_dispose_mapping);
+
+int irq_domain_simple_dt_translate(struct irq_domain *d,
+			    struct device_node *controller,
+			    const u32 *intspec, unsigned int intsize,
+			    unsigned long *out_hwirq, unsigned int *out_type)
+{
+	if (d->of_node != controller)
+		return -EINVAL;
+	if (intsize < 1)
+		return -EINVAL;
+
+	*out_hwirq = intspec[0];
+	*out_type = IRQ_TYPE_NONE;
+	if (intsize > 1)
+		*out_type = intspec[1] & IRQ_TYPE_SENSE_MASK;
+	return 0;
+}
+
+struct irq_domain_ops irq_domain_simple_ops = {
+	.dt_translate = irq_domain_simple_dt_translate,
+};
+EXPORT_SYMBOL_GPL(irq_domain_simple_ops);
+
+/**
+ * irq_domain_create_simple() - Set up a 'simple' translation range
+ */
+void irq_domain_add_simple(struct device_node *controller, int irq_base)
+{
+	struct irq_domain *domain;
+
+	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
+	if (!domain) {
+		WARN_ON(1);
+		return;
+	}
+
+	domain->irq_base = irq_base;
+	domain->of_node = of_node_get(controller);
+	domain->ops = &irq_domain_simple_ops;
+	irq_domain_add(domain);
+}
+EXPORT_SYMBOL_GPL(irq_domain_add_simple);
+
+void irq_domain_generate_simple(const struct of_device_id *match,
+				u64 phys_base, unsigned int irq_start)
+{
+	struct device_node *node;
+	pr_info("looking for phys_base=%llx, irq_start=%i\n",
+		(unsigned long long) phys_base, (int) irq_start);
+	node = of_find_matching_node_by_address(NULL, match, phys_base);
+	if (node)
+		irq_domain_add_simple(node, irq_start);
+	else
+		pr_info("no node found\n");
+}
+EXPORT_SYMBOL_GPL(irq_domain_generate_simple);
+#endif /* CONFIG_OF_IRQ */

kernel/irq/manage.c

@@ -883,6 +883,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 
 	if (desc->irq_data.chip == &no_irq_chip)
 		return -ENOSYS;
+	if (!try_module_get(desc->owner))
+		return -ENODEV;
 	/*
 	 * Some drivers like serial.c use request_irq() heavily,
 	 * so we have to be careful not to interfere with a
@@ -906,8 +908,10 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 	 */
 	nested = irq_settings_is_nested_thread(desc);
 	if (nested) {
-		if (!new->thread_fn)
-			return -EINVAL;
+		if (!new->thread_fn) {
+			ret = -EINVAL;
+			goto out_mput;
+		}
 		/*
 		 * Replace the primary handler which was provided from
 		 * the driver for non nested interrupt handling by the
@@ -929,8 +933,10 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 
 		t = kthread_create(irq_thread, new, "irq/%d-%s", irq,
 				   new->name);
-		if (IS_ERR(t))
-			return PTR_ERR(t);
+		if (IS_ERR(t)) {
+			ret = PTR_ERR(t);
+			goto out_mput;
+		}
 		/*
 		 * We keep the reference to the task struct even if
 		 * the thread dies to avoid that the interrupt code
@@ -1095,6 +1101,8 @@ out_thread:
 			kthread_stop(t);
 		put_task_struct(t);
 	}
+out_mput:
+	module_put(desc->owner);
 	return ret;
 }
 
@@ -1203,6 +1211,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
 		put_task_struct(action->thread);
 	}
 
+	module_put(desc->owner);
 	return action;
 }
 

kernel/kmod.c

@@ -274,7 +274,7 @@ static void __call_usermodehelper(struct work_struct *work)
  * (used for preventing user land processes from being created after the user
  * land has been frozen during a system-wide hibernation or suspend operation).
  */
-static int usermodehelper_disabled;
+static int usermodehelper_disabled = 1;
 
 /* Number of helpers running */
 static atomic_t running_helpers = ATOMIC_INIT(0);

kernel/lockdep.c

@@ -2468,7 +2468,7 @@ mark_held_locks(struct task_struct *curr, enum mark_type mark)
 
 		BUG_ON(usage_bit >= LOCK_USAGE_STATES);
 
-		if (hlock_class(hlock)->key == &__lockdep_no_validate__)
+		if (hlock_class(hlock)->key == __lockdep_no_validate__.subkeys)
 			continue;
 
 		if (!mark_lock(curr, hlock, usage_bit))
@@ -2485,23 +2485,9 @@ static void __trace_hardirqs_on_caller(unsigned long ip)
 {
 	struct task_struct *curr = current;
 
-	if (DEBUG_LOCKS_WARN_ON(unlikely(early_boot_irqs_disabled)))
-		return;
-
-	if (unlikely(curr->hardirqs_enabled)) {
-		/*
-		 * Neither irq nor preemption are disabled here
-		 * so this is racy by nature but losing one hit
-		 * in a stat is not a big deal.
-		 */
-		__debug_atomic_inc(redundant_hardirqs_on);
-		return;
-	}
 	/* we'll do an OFF -> ON transition: */
 	curr->hardirqs_enabled = 1;
 
-	if (DEBUG_LOCKS_WARN_ON(current->hardirq_context))
-		return;
 	/*
 	 * We are going to turn hardirqs on, so set the
 	 * usage bit for all held locks:
@@ -2529,9 +2515,25 @@ void trace_hardirqs_on_caller(unsigned long ip)
 	if (unlikely(!debug_locks || current->lockdep_recursion))
 		return;
 
+	if (unlikely(current->hardirqs_enabled)) {
+		/*
+		 * Neither irq nor preemption are disabled here
+		 * so this is racy by nature but losing one hit
+		 * in a stat is not a big deal.
+		 */
+		__debug_atomic_inc(redundant_hardirqs_on);
+		return;
+	}
+
 	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
 		return;
 
+	if (DEBUG_LOCKS_WARN_ON(unlikely(early_boot_irqs_disabled)))
+		return;
+
+	if (DEBUG_LOCKS_WARN_ON(current->hardirq_context))
+		return;
+
 	current->lockdep_recursion = 1;
 	__trace_hardirqs_on_caller(ip);
 	current->lockdep_recursion = 0;
@@ -2872,10 +2874,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 void lockdep_init_map(struct lockdep_map *lock, const char *name,
 		      struct lock_class_key *key, int subclass)
 {
-	int i;
-
-	for (i = 0; i < NR_LOCKDEP_CACHING_CLASSES; i++)
-		lock->class_cache[i] = NULL;
+	memset(lock, 0, sizeof(*lock));
 
 #ifdef CONFIG_LOCK_STAT
 	lock->cpu = raw_smp_processor_id();
@@ -3112,7 +3111,13 @@ static int match_held_lock(struct held_lock *hlock, struct lockdep_map *lock)
 		if (!class)
 			class = look_up_lock_class(lock, 0);
 
-		if (DEBUG_LOCKS_WARN_ON(!class))
+		/*
+		 * If look_up_lock_class() failed to find a class, we're trying
+		 * to test if we hold a lock that has never yet been acquired.
+		 * Clearly if the lock hasn't been acquired _ever_, we're not
+		 * holding it either, so report failure.
+		 */
+		if (!class)
 			return 0;
 
 		if (DEBUG_LOCKS_WARN_ON(!hlock->nest_lock))

kernel/panic.c

@@ -119,6 +119,8 @@ NORET_TYPE void panic(const char * fmt, ...)
 			}
 			mdelay(PANIC_TIMER_STEP);
 		}
+	}
+	if (panic_timeout != 0) {
 		/*
 		 * This will not be a clean reboot, with everything
 		 * shutting down.  But if there is a chance of

kernel/power/Kconfig

@@ -231,3 +231,7 @@ config PM_CLK
 config PM_GENERIC_DOMAINS
 	bool
 	depends on PM
+
+config PM_GENERIC_DOMAINS_RUNTIME
+	def_bool y
+	depends on PM_RUNTIME && PM_GENERIC_DOMAINS

kernel/printk.c

@@ -318,8 +318,10 @@ static int check_syslog_permissions(int type, bool from_file)
 			return 0;
 		/* For historical reasons, accept CAP_SYS_ADMIN too, with a warning */
 		if (capable(CAP_SYS_ADMIN)) {
-			WARN_ONCE(1, "Attempt to access syslog with CAP_SYS_ADMIN "
-				 "but no CAP_SYSLOG (deprecated).\n");
+			printk_once(KERN_WARNING "%s (%d): "
+				 "Attempt to access syslog with CAP_SYS_ADMIN "
+				 "but no CAP_SYSLOG (deprecated).\n",
+				 current->comm, task_pid_nr(current));
 			return 0;
 		}
 		return -EPERM;
@@ -1602,7 +1604,7 @@ static int __init printk_late_init(void)
 	struct console *con;
 
 	for_each_console(con) {
-		if (con->flags & CON_BOOT) {
+		if (!keep_bootcon && con->flags & CON_BOOT) {
 			printk(KERN_INFO "turn off boot console %s%d\n",
 				con->name, con->index);
 			unregister_console(con);

kernel/rcupdate.c

@@ -37,7 +37,7 @@
 #include <linux/smp.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 #include <linux/bitops.h>
 #include <linux/percpu.h>
 #include <linux/notifier.h>

kernel/rcutorture.c

@@ -33,7 +33,7 @@
 #include <linux/rcupdate.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 #include <linux/bitops.h>
 #include <linux/completion.h>
 #include <linux/moduleparam.h>

kernel/rcutree_trace.c

@@ -31,7 +31,7 @@
 #include <linux/rcupdate.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 #include <linux/bitops.h>
 #include <linux/module.h>
 #include <linux/completion.h>

kernel/resource.c

@@ -553,6 +553,27 @@ int allocate_resource(struct resource *root, struct resource *new,
 
 EXPORT_SYMBOL(allocate_resource);
 
+/**
+ * lookup_resource - find an existing resource by a resource start address
+ * @root: root resource descriptor
+ * @start: resource start address
+ *
+ * Returns a pointer to the resource if found, NULL otherwise
+ */
+struct resource *lookup_resource(struct resource *root, resource_size_t start)
+{
+	struct resource *res;
+
+	read_lock(&resource_lock);
+	for (res = root->child; res; res = res->sibling) {
+		if (res->start == start)
+			break;
+	}
+	read_unlock(&resource_lock);
+
+	return res;
+}
+
 /*
  * Insert a resource into the resource tree. If successful, return NULL,
  * otherwise return the conflicting resource (compare to __request_resource())

kernel/rwsem.c

@@ -11,7 +11,7 @@
 #include <linux/rwsem.h>
 
 #include <asm/system.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 
 /*
  * lock for reading

kernel/sched.c

@@ -3065,7 +3065,7 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
 	local_irq_disable();
 #endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
-	perf_event_task_sched_in(current);
+	perf_event_task_sched_in(prev, current);
 #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
 	local_irq_enable();
 #endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
@@ -4279,9 +4279,9 @@ pick_next_task(struct rq *rq)
 }
 
 /*
- * schedule() is the main scheduler function.
+ * __schedule() is the main scheduler function.
  */
-asmlinkage void __sched schedule(void)
+static void __sched __schedule(void)
 {
 	struct task_struct *prev, *next;
 	unsigned long *switch_count;
@@ -4322,16 +4322,6 @@ need_resched:
 				if (to_wakeup)
 					try_to_wake_up_local(to_wakeup);
 			}
-
-			/*
-			 * If we are going to sleep and we have plugged IO
-			 * queued, make sure to submit it to avoid deadlocks.
-			 */
-			if (blk_needs_flush_plug(prev)) {
-				raw_spin_unlock(&rq->lock);
-				blk_schedule_flush_plug(prev);
-				raw_spin_lock(&rq->lock);
-			}
 		}
 		switch_count = &prev->nvcsw;
 	}
@@ -4369,6 +4359,26 @@ need_resched:
 	if (need_resched())
 		goto need_resched;
 }
+
+static inline void sched_submit_work(struct task_struct *tsk)
+{
+	if (!tsk->state)
+		return;
+	/*
+	 * If we are going to sleep and we have plugged IO queued,
+	 * make sure to submit it to avoid deadlocks.
+	 */
+	if (blk_needs_flush_plug(tsk))
+		blk_schedule_flush_plug(tsk);
+}
+
+asmlinkage void schedule(void)
+{
+	struct task_struct *tsk = current;
+
+	sched_submit_work(tsk);
+	__schedule();
+}
 EXPORT_SYMBOL(schedule);
 
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
@@ -4435,7 +4445,7 @@ asmlinkage void __sched notrace preempt_schedule(void)
 
 	do {
 		add_preempt_count_notrace(PREEMPT_ACTIVE);
-		schedule();
+		__schedule();
 		sub_preempt_count_notrace(PREEMPT_ACTIVE);
 
 		/*
@@ -4463,7 +4473,7 @@ asmlinkage void __sched preempt_schedule_irq(void)
 	do {
 		add_preempt_count(PREEMPT_ACTIVE);
 		local_irq_enable();
-		schedule();
+		__schedule();
 		local_irq_disable();
 		sub_preempt_count(PREEMPT_ACTIVE);
 
@@ -5588,7 +5598,7 @@ static inline int should_resched(void)
 static void __cond_resched(void)
 {
 	add_preempt_count(PREEMPT_ACTIVE);
-	schedule();
+	__schedule();
 	sub_preempt_count(PREEMPT_ACTIVE);
 }
 
@@ -7443,6 +7453,7 @@ static void __sdt_free(const struct cpumask *cpu_map)
 			struct sched_domain *sd = *per_cpu_ptr(sdd->sd, j);
 			if (sd && (sd->flags & SD_OVERLAP))
 				free_sched_groups(sd->groups, 0);
+			kfree(*per_cpu_ptr(sdd->sd, j));
 			kfree(*per_cpu_ptr(sdd->sg, j));
 			kfree(*per_cpu_ptr(sdd->sgp, j));
 		}

kernel/signal.c

@@ -3102,15 +3102,11 @@ SYSCALL_DEFINE0(sgetmask)
 
 SYSCALL_DEFINE1(ssetmask, int, newmask)
 {
-	int old;
+	int old = current->blocked.sig[0];
+	sigset_t newset;
 
-	spin_lock_irq(&current->sighand->siglock);
-	old = current->blocked.sig[0];
-
-	siginitset(&current->blocked, newmask & ~(sigmask(SIGKILL)|
-						  sigmask(SIGSTOP)));
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+	siginitset(&newset, newmask & ~(sigmask(SIGKILL) | sigmask(SIGSTOP)));
+	set_current_blocked(&newset);
 
 	return old;
 }
@@ -3167,11 +3163,8 @@ SYSCALL_DEFINE2(rt_sigsuspend, sigset_t __user *, unewset, size_t, sigsetsize)
 		return -EFAULT;
 	sigdelsetmask(&newset, sigmask(SIGKILL)|sigmask(SIGSTOP));
 
-	spin_lock_irq(&current->sighand->siglock);
 	current->saved_sigmask = current->blocked;
-	current->blocked = newset;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+	set_current_blocked(&newset);
 
 	current->state = TASK_INTERRUPTIBLE;
 	schedule();

kernel/stop_machine.c

@@ -19,7 +19,7 @@
 #include <linux/interrupt.h>
 #include <linux/kallsyms.h>
 
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 
 /*
  * Structure to determine completion condition and record errors.  May

kernel/sys.c

@@ -37,6 +37,8 @@
 #include <linux/fs_struct.h>
 #include <linux/gfp.h>
 #include <linux/syscore_ops.h>
+#include <linux/version.h>
+#include <linux/ctype.h>
 
 #include <linux/compat.h>
 #include <linux/syscalls.h>
@@ -44,6 +46,8 @@
 #include <linux/user_namespace.h>
 
 #include <linux/kmsg_dump.h>
+/* Move somewhere else to avoid recompiling? */
+#include <generated/utsrelease.h>
 
 #include <asm/uaccess.h>
 #include <asm/io.h>
@@ -621,11 +625,18 @@ static int set_user(struct cred *new)
 	if (!new_user)
 		return -EAGAIN;
 
+	/*
+	 * We don't fail in case of NPROC limit excess here because too many
+	 * poorly written programs don't check set*uid() return code, assuming
+	 * it never fails if called by root.  We may still enforce NPROC limit
+	 * for programs doing set*uid()+execve() by harmlessly deferring the
+	 * failure to the execve() stage.
+	 */
 	if (atomic_read(&new_user->processes) >= rlimit(RLIMIT_NPROC) &&
-			new_user != INIT_USER) {
-		free_uid(new_user);
-		return -EAGAIN;
-	}
+			new_user != INIT_USER)
+		current->flags |= PF_NPROC_EXCEEDED;
+	else
+		current->flags &= ~PF_NPROC_EXCEEDED;
 
 	free_uid(new->user);
 	new->user = new_user;
@@ -1154,6 +1165,34 @@ DECLARE_RWSEM(uts_sem);
 #define override_architecture(name)	0
 #endif
 
+/*
+ * Work around broken programs that cannot handle "Linux 3.0".
+ * Instead we map 3.x to 2.6.40+x, so e.g. 3.0 would be 2.6.40
+ */
+static int override_release(char __user *release, int len)
+{
+	int ret = 0;
+	char buf[len];
+
+	if (current->personality & UNAME26) {
+		char *rest = UTS_RELEASE;
+		int ndots = 0;
+		unsigned v;
+
+		while (*rest) {
+			if (*rest == '.' && ++ndots >= 3)
+				break;
+			if (!isdigit(*rest) && *rest != '.')
+				break;
+			rest++;
+		}
+		v = ((LINUX_VERSION_CODE >> 8) & 0xff) + 40;
+		snprintf(buf, len, "2.6.%u%s", v, rest);
+		ret = copy_to_user(release, buf, len);
+	}
+	return ret;
+}
+
 SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name)
 {
 	int errno = 0;
@@ -1163,6 +1202,8 @@ SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name)
 		errno = -EFAULT;
 	up_read(&uts_sem);
 
+	if (!errno && override_release(name->release, sizeof(name->release)))
+		errno = -EFAULT;
 	if (!errno && override_architecture(name))
 		errno = -EFAULT;
 	return errno;
@@ -1184,6 +1225,8 @@ SYSCALL_DEFINE1(uname, struct old_utsname __user *, name)
 		error = -EFAULT;
 	up_read(&uts_sem);
 
+	if (!error && override_release(name->release, sizeof(name->release)))
+		error = -EFAULT;
 	if (!error && override_architecture(name))
 		error = -EFAULT;
 	return error;
@@ -1218,6 +1261,8 @@ SYSCALL_DEFINE1(olduname, struct oldold_utsname __user *, name)
 
 	if (!error && override_architecture(name))
 		error = -EFAULT;
+	if (!error && override_release(name->release, sizeof(name->release)))
+		error = -EFAULT;
 	return error ? -EFAULT : 0;
 }
 #endif

kernel/sys_ni.c

@@ -16,7 +16,6 @@ asmlinkage long sys_ni_syscall(void)
 	return -ENOSYS;
 }
 
-cond_syscall(sys_nfsservctl);
 cond_syscall(sys_quotactl);
 cond_syscall(sys32_quotactl);
 cond_syscall(sys_acct);

kernel/sysctl_binary.c

@@ -1,6 +1,6 @@
 #include <linux/stat.h>
 #include <linux/sysctl.h>
-#include "../fs/xfs/linux-2.6/xfs_sysctl.h"
+#include "../fs/xfs/xfs_sysctl.h"
 #include <linux/sunrpc/debug.h>
 #include <linux/string.h>
 #include <net/ip_vs.h>

kernel/sysctl_check.c

@@ -1,6 +1,6 @@
 #include <linux/stat.h>
 #include <linux/sysctl.h>
-#include "../fs/xfs/linux-2.6/xfs_sysctl.h"
+#include "../fs/xfs/xfs_sysctl.h"
 #include <linux/sunrpc/debug.h>
 #include <linux/string.h>
 #include <net/ip_vs.h>

kernel/taskstats.c

@@ -28,7 +28,7 @@
 #include <linux/fs.h>
 #include <linux/file.h>
 #include <net/genetlink.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 
 /*
  * Maximum length of a cpumask that can be specified in
@@ -291,30 +291,28 @@ static int add_del_listener(pid_t pid, const struct cpumask *mask, int isadd)
 	if (!cpumask_subset(mask, cpu_possible_mask))
 		return -EINVAL;
 
-	s = NULL;
 	if (isadd == REGISTER) {
 		for_each_cpu(cpu, mask) {
-			if (!s)
-				s = kmalloc_node(sizeof(struct listener),
-						 GFP_KERNEL, cpu_to_node(cpu));
+			s = kmalloc_node(sizeof(struct listener),
+					GFP_KERNEL, cpu_to_node(cpu));
 			if (!s)
 				goto cleanup;
+
 			s->pid = pid;
-			INIT_LIST_HEAD(&s->list);
 			s->valid = 1;
 
 			listeners = &per_cpu(listener_array, cpu);
 			down_write(&listeners->sem);
-			list_for_each_entry_safe(s2, tmp, &listeners->list, list) {
-				if (s2->pid == pid)
-					goto next_cpu;
+			list_for_each_entry(s2, &listeners->list, list) {
+				if (s2->pid == pid && s2->valid)
+					goto exists;
 			}
 			list_add(&s->list, &listeners->list);
 			s = NULL;
-next_cpu:
+exists:
 			up_write(&listeners->sem);
+			kfree(s); /* nop if NULL */
 		}
-		kfree(s);
 		return 0;
 	}
 

kernel/time/alarmtimer.c

@@ -441,6 +441,8 @@ static int alarm_timer_create(struct k_itimer *new_timer)
 static void alarm_timer_get(struct k_itimer *timr,
 				struct itimerspec *cur_setting)
 {
+	memset(cur_setting, 0, sizeof(struct itimerspec));
+
 	cur_setting->it_interval =
 			ktime_to_timespec(timr->it.alarmtimer.period);
 	cur_setting->it_value =
@@ -479,11 +481,17 @@ static int alarm_timer_set(struct k_itimer *timr, int flags,
 	if (!rtcdev)
 		return -ENOTSUPP;
 
-	/* Save old values */
-	old_setting->it_interval =
-			ktime_to_timespec(timr->it.alarmtimer.period);
-	old_setting->it_value =
-			ktime_to_timespec(timr->it.alarmtimer.node.expires);
+	/*
+	 * XXX HACK! Currently we can DOS a system if the interval
+	 * period on alarmtimers is too small. Cap the interval here
+	 * to 100us and solve this properly in a future patch! -jstultz
+	 */
+	if ((new_setting->it_interval.tv_sec == 0) &&
+			(new_setting->it_interval.tv_nsec < 100000))
+		new_setting->it_interval.tv_nsec = 100000;
+
+	if (old_setting)
+		alarm_timer_get(timr, old_setting);
 
 	/* If the timer was already set, cancel it */
 	alarm_cancel(&timr->it.alarmtimer);

kernel/trace/Kconfig

@@ -82,7 +82,7 @@ config EVENT_POWER_TRACING_DEPRECATED
 	  power:power_frequency
 	  This is for userspace compatibility
 	  and will vanish after 5 kernel iterations,
-	  namely 2.6.41.
+	  namely 3.1.
 
 config CONTEXT_SWITCH_TRACER
 	bool

kernel/trace/blktrace.c

@@ -206,6 +206,8 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	what |= MASK_TC_BIT(rw, RAHEAD);
 	what |= MASK_TC_BIT(rw, META);
 	what |= MASK_TC_BIT(rw, DISCARD);
+	what |= MASK_TC_BIT(rw, FLUSH);
+	what |= MASK_TC_BIT(rw, FUA);
 
 	pid = tsk->pid;
 	if (act_log_check(bt, what, sector, pid))
@@ -1054,6 +1056,9 @@ static void fill_rwbs(char *rwbs, const struct blk_io_trace *t)
 		goto out;
 	}
 
+	if (tc & BLK_TC_FLUSH)
+		rwbs[i++] = 'F';
+
 	if (tc & BLK_TC_DISCARD)
 		rwbs[i++] = 'D';
 	else if (tc & BLK_TC_WRITE)
@@ -1063,10 +1068,10 @@ static void fill_rwbs(char *rwbs, const struct blk_io_trace *t)
 	else
 		rwbs[i++] = 'N';
 
+	if (tc & BLK_TC_FUA)
+		rwbs[i++] = 'F';
 	if (tc & BLK_TC_AHEAD)
 		rwbs[i++] = 'A';
-	if (tc & BLK_TC_BARRIER)
-		rwbs[i++] = 'B';
 	if (tc & BLK_TC_SYNC)
 		rwbs[i++] = 'S';
 	if (tc & BLK_TC_META)
@@ -1132,7 +1137,7 @@ typedef int (blk_log_action_t) (struct trace_iterator *iter, const char *act);
 
 static int blk_log_action_classic(struct trace_iterator *iter, const char *act)
 {
-	char rwbs[6];
+	char rwbs[RWBS_LEN];
 	unsigned long long ts  = iter->ts;
 	unsigned long nsec_rem = do_div(ts, NSEC_PER_SEC);
 	unsigned secs	       = (unsigned long)ts;
@@ -1148,7 +1153,7 @@ static int blk_log_action_classic(struct trace_iterator *iter, const char *act)
 
 static int blk_log_action(struct trace_iterator *iter, const char *act)
 {
-	char rwbs[6];
+	char rwbs[RWBS_LEN];
 	const struct blk_io_trace *t = te_blk_io_trace(iter->ent);
 
 	fill_rwbs(rwbs, t);
@@ -1561,7 +1566,7 @@ static const struct {
 } mask_maps[] = {
 	{ BLK_TC_READ,		"read"		},
 	{ BLK_TC_WRITE,		"write"		},
-	{ BLK_TC_BARRIER,	"barrier"	},
+	{ BLK_TC_FLUSH,		"flush"		},
 	{ BLK_TC_SYNC,		"sync"		},
 	{ BLK_TC_QUEUE,		"queue"		},
 	{ BLK_TC_REQUEUE,	"requeue"	},
@@ -1573,6 +1578,7 @@ static const struct {
 	{ BLK_TC_META,		"meta"		},
 	{ BLK_TC_DISCARD,	"discard"	},
 	{ BLK_TC_DRV_DATA,	"drv_data"	},
+	{ BLK_TC_FUA,		"fua"		},
 };
 
 static int blk_trace_str2mask(const char *str)
@@ -1788,6 +1794,9 @@ void blk_fill_rwbs(char *rwbs, u32 rw, int bytes)
 {
 	int i = 0;
 
+	if (rw & REQ_FLUSH)
+		rwbs[i++] = 'F';
+
 	if (rw & WRITE)
 		rwbs[i++] = 'W';
 	else if (rw & REQ_DISCARD)
@@ -1797,6 +1806,8 @@ void blk_fill_rwbs(char *rwbs, u32 rw, int bytes)
 	else
 		rwbs[i++] = 'N';
 
+	if (rw & REQ_FUA)
+		rwbs[i++] = 'F';
 	if (rw & REQ_RAHEAD)
 		rwbs[i++] = 'A';
 	if (rw & REQ_SYNC)

kernel/trace/trace.h

@@ -2,7 +2,7 @@
 #define _LINUX_KERNEL_TRACE_H
 
 #include <linux/fs.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 #include <linux/sched.h>
 #include <linux/clocksource.h>
 #include <linux/ring_buffer.h>

kernel/trace/trace_mmiotrace.c

@@ -12,7 +12,7 @@
 #include <linux/slab.h>
 #include <linux/time.h>
 
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 
 #include "trace.h"
 #include "trace_output.h"

kernel/workqueue.c

@@ -2412,8 +2412,13 @@ reflush:
 
 	for_each_cwq_cpu(cpu, wq) {
 		struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
+		bool drained;
 
-		if (!cwq->nr_active && list_empty(&cwq->delayed_works))
+		spin_lock_irq(&cwq->gcwq->lock);
+		drained = !cwq->nr_active && list_empty(&cwq->delayed_works);
+		spin_unlock_irq(&cwq->gcwq->lock);
+
+		if (drained)
 			continue;
 
 		if (++flush_cnt == 10 ||