Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6 into for-linus-1

* 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6: (9356 commits)
  [media] rc: update for bitop name changes
  fs: simplify iget & friends
  fs: pull inode->i_lock up out of writeback_single_inode
  fs: rename inode_lock to inode_hash_lock
  fs: move i_wb_list out from under inode_lock
  fs: move i_sb_list out from under inode_lock
  fs: remove inode_lock from iput_final and prune_icache
  fs: Lock the inode LRU list separately
  fs: factor inode disposal
  fs: protect inode->i_state with inode->i_lock
  lib, arch: add filter argument to show_mem and fix private implementations
  SLUB: Write to per cpu data when allocating it
  slub: Fix debugobjects with lockless fastpath
  autofs4: Do not potentially dereference NULL pointer returned by fget() in autofs_dev_ioctl_setpipefd()
  autofs4 - remove autofs4_lock
  autofs4 - fix d_manage() return on rcu-walk
  autofs4 - fix autofs4_expire_indirect() traversal
  autofs4 - fix dentry leak in autofs4_expire_direct()
  autofs4 - reinstate last used update on access
  vfs - check non-mountpoint dentry might block in __follow_mount_rcu()
  ...

NOTE!

This merge commit was created to fix compilation error. The block
tree was merged upstream and removed the 'elv_queue_empty()'
function which the new 'mtdswap' driver is using. So a simple
merge of the mtd tree with upstream does not compile. And the
mtd tree has already be published, so re-basing it is not an option.

To fix this unfortunate situation, I had to merge upstream into the
mtd-2.6.git tree without committing, put the fixup patch on top of
this, and then commit this. The result is that we do not have commits
which do not compile.

In other words, this merge commit "merges" 3 things: the MTD tree, the
upstream tree, and the fixup patch.

6 files changed, 102 insertions, 148 deletions

diff --git a/init/Kconfig b/init/Kconfig
index be788c0957d4..56240e724d9a 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -69,11 +69,6 @@ config BROKEN_ON_SMP
 	depends on BROKEN || !SMP
 	default y
 
-config LOCK_KERNEL
-	bool
-	depends on (SMP || PREEMPT) && BKL
-	default y
-
 config INIT_ENV_ARG_LIMIT
 	int
 	default 32 if !UML
@@ -287,6 +282,18 @@ config BSD_PROCESS_ACCT_V3
 	  for processing it. A preliminary version of these tools is available
 	  at <http://www.gnu.org/software/acct/>.
 
+config FHANDLE
+	bool "open by fhandle syscalls"
+	select EXPORTFS
+	help
+	  If you say Y here, a user level program will be able to map
+	  file names to handle and then later use the handle for
+	  different file system operations. This is useful in implementing
+	  userspace file servers, which now track files using handles instead
+	  of names. The handle would remain the same even if file names
+	  get renamed. Enables open_by_handle_at(2) and name_to_handle_at(2)
+	  syscalls.
+
 config TASKSTATS
 	bool "Export task/process statistics through netlink (EXPERIMENTAL)"
 	depends on NET
@@ -683,6 +690,16 @@ config CGROUP_MEM_RES_CTLR_SWAP_ENABLED
 	  select this option (if, for some reason, they need to disable it
 	  then noswapaccount does the trick).
 
+config CGROUP_PERF
+	bool "Enable perf_event per-cpu per-container group (cgroup) monitoring"
+	depends on PERF_EVENTS && CGROUPS
+	help
+	  This option extends the per-cpu mode to restrict monitoring to
+	  threads which belong to the cgroup specified and run on the
+	  designated cpu.
+
+	  Say N if unsure.
+
 menuconfig CGROUP_SCHED
 	bool "Group CPU scheduler"
 	depends on EXPERIMENTAL
@@ -728,9 +745,9 @@ config BLK_CGROUP
 
 	This option only enables generic Block IO controller infrastructure.
 	One needs to also enable actual IO controlling logic/policy. For
-	enabling proportional weight division of disk bandwidth in CFQ seti
-	CONFIG_CFQ_GROUP_IOSCHED=y and for enabling throttling policy set
-	CONFIG_BLK_THROTTLE=y.
+	enabling proportional weight division of disk bandwidth in CFQ, set
+	CONFIG_CFQ_GROUP_IOSCHED=y; for enabling throttling policy, set
+	CONFIG_BLK_DEV_THROTTLING=y.
 
 	See Documentation/cgroups/blkio-controller.txt for more information.
 
@@ -814,7 +831,7 @@ config MM_OWNER
 	bool
 
 config SYSFS_DEPRECATED
-	bool "enable deprecated sysfs features to support old userspace tools"
+	bool "Enable deprecated sysfs features to support old userspace tools"
 	depends on SYSFS
 	default n
 	help
@@ -837,7 +854,7 @@ config SYSFS_DEPRECATED
 	  need to say Y here.
 
 config SYSFS_DEPRECATED_V2
-	bool "enabled deprecated sysfs features by default"
+	bool "Enable deprecated sysfs features by default"
 	default n
 	depends on SYSFS
 	depends on SYSFS_DEPRECATED
diff --git a/init/calibrate.c b/init/calibrate.c
index 6eb48e53d61c..76ac9194cbc4 100644
--- a/init/calibrate.c
+++ b/init/calibrate.c
@@ -66,7 +66,7 @@ static unsigned long __cpuinit calibrate_delay_direct(void)
 		pre_start = 0;
 		read_current_timer(&start);
 		start_jiffies = jiffies;
-		while (jiffies <= (start_jiffies + 1)) {
+		while (time_before_eq(jiffies, start_jiffies + 1)) {
 			pre_start = start;
 			read_current_timer(&start);
 		}
@@ -74,8 +74,8 @@ static unsigned long __cpuinit calibrate_delay_direct(void)
 
 		pre_end = 0;
 		end = post_start;
-		while (jiffies <=
-		       (start_jiffies + 1 + DELAY_CALIBRATION_TICKS)) {
+		while (time_before_eq(jiffies, start_jiffies + 1 +
+					       DELAY_CALIBRATION_TICKS)) {
 			pre_end = end;
 			read_current_timer(&end);
 		}
@@ -110,8 +110,8 @@ static unsigned long __cpuinit calibrate_delay_direct(void) {return 0;}
 
 /*
  * This is the number of bits of precision for the loops_per_jiffy.  Each
- * bit takes on average 1.5/HZ seconds.  This (like the original) is a little
- * better than 1%
+ * time we refine our estimate after the first takes 1.5/HZ seconds, so try
+ * to start with a good estimate.
  * For the boot cpu we can skip the delay calibration and assign it a value
  * calculated based on the timer frequency.
  * For the rest of the CPUs we cannot assume that the timer frequency is same as
@@ -119,10 +119,72 @@ static unsigned long __cpuinit calibrate_delay_direct(void) {return 0;}
  */
 #define LPS_PREC 8
 
+static unsigned long __cpuinit calibrate_delay_converge(void)
+{
+	/* First stage - slowly accelerate to find initial bounds */
+	unsigned long lpj, lpj_base, ticks, loopadd, loopadd_base, chop_limit;
+	int trials = 0, band = 0, trial_in_band = 0;
+
+	lpj = (1<<12);
+
+	/* wait for "start of" clock tick */
+	ticks = jiffies;
+	while (ticks == jiffies)
+		; /* nothing */
+	/* Go .. */
+	ticks = jiffies;
+	do {
+		if (++trial_in_band == (1<<band)) {
+			++band;
+			trial_in_band = 0;
+		}
+		__delay(lpj * band);
+		trials += band;
+	} while (ticks == jiffies);
+	/*
+	 * We overshot, so retreat to a clear underestimate. Then estimate
+	 * the largest likely undershoot. This defines our chop bounds.
+	 */
+	trials -= band;
+	loopadd_base = lpj * band;
+	lpj_base = lpj * trials;
+
+recalibrate:
+	lpj = lpj_base;
+	loopadd = loopadd_base;
+
+	/*
+	 * Do a binary approximation to get lpj set to
+	 * equal one clock (up to LPS_PREC bits)
+	 */
+	chop_limit = lpj >> LPS_PREC;
+	while (loopadd > chop_limit) {
+		lpj += loopadd;
+		ticks = jiffies;
+		while (ticks == jiffies)
+			; /* nothing */
+		ticks = jiffies;
+		__delay(lpj);
+		if (jiffies != ticks)	/* longer than 1 tick */
+			lpj -= loopadd;
+		loopadd >>= 1;
+	}
+	/*
+	 * If we incremented every single time possible, presume we've
+	 * massively underestimated initially, and retry with a higher
+	 * start, and larger range. (Only seen on x86_64, due to SMIs)
+	 */
+	if (lpj + loopadd * 2 == lpj_base + loopadd_base * 2) {
+		lpj_base = lpj;
+		loopadd_base <<= 2;
+		goto recalibrate;
+	}
+
+	return lpj;
+}
+
 void __cpuinit calibrate_delay(void)
 {
-	unsigned long ticks, loopbit;
-	int lps_precision = LPS_PREC;
 	static bool printed;
 
 	if (preset_lpj) {
@@ -139,39 +201,9 @@ void __cpuinit calibrate_delay(void)
 			pr_info("Calibrating delay using timer "
 				"specific routine.. ");
 	} else {
-		loops_per_jiffy = (1<<12);
-
 		if (!printed)
 			pr_info("Calibrating delay loop... ");
-		while ((loops_per_jiffy <<= 1) != 0) {
-			/* wait for "start of" clock tick */
-			ticks = jiffies;
-			while (ticks == jiffies)
-				/* nothing */;
-			/* Go .. */
-			ticks = jiffies;
-			__delay(loops_per_jiffy);
-			ticks = jiffies - ticks;
-			if (ticks)
-				break;
-		}
-
-		/*
-		 * Do a binary approximation to get loops_per_jiffy set to
-		 * equal one clock (up to lps_precision bits)
-		 */
-		loops_per_jiffy >>= 1;
-		loopbit = loops_per_jiffy;
-		while (lps_precision-- && (loopbit >>= 1)) {
-			loops_per_jiffy |= loopbit;
-			ticks = jiffies;
-			while (ticks == jiffies)
-				/* nothing */;
-			ticks = jiffies;
-			__delay(loops_per_jiffy);
-			if (jiffies != ticks)	/* longer than 1 tick */
-				loops_per_jiffy &= ~loopbit;
-		}
+		loops_per_jiffy = calibrate_delay_converge();
 	}
 	if (!printed)
 		pr_cont("%lu.%02lu BogoMIPS (lpj=%lu)\n",
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 2b54bef33b55..3e0112157795 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -293,7 +293,8 @@ static int __init do_mount_root(char *name, char *fs, int flags, void *data)
 
 	sys_chdir((const char __user __force *)"/root");
 	ROOT_DEV = current->fs->pwd.mnt->mnt_sb->s_dev;
-	printk("VFS: Mounted root (%s filesystem)%s on device %u:%u.\n",
+	printk(KERN_INFO
+	       "VFS: Mounted root (%s filesystem)%s on device %u:%u.\n",
 	       current->fs->pwd.mnt->mnt_sb->s_type->name,
 	       current->fs->pwd.mnt->mnt_sb->s_flags & MS_RDONLY ?
 	       " readonly" : "", MAJOR(ROOT_DEV), MINOR(ROOT_DEV));
diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c
index 6e1ee6987c78..fe9acb0ae480 100644
--- a/init/do_mounts_rd.c
+++ b/init/do_mounts_rd.c
@@ -64,7 +64,7 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor)
 
 	buf = kmalloc(size, GFP_KERNEL);
 	if (!buf)
-		return -1;
+		return -ENOMEM;
 
 	minixsb = (struct minix_super_block *) buf;
 	ext2sb = (struct ext2_super_block *) buf;
diff --git a/init/main.c b/init/main.c
index 33c37c379e96..4a9479ef4540 100644
--- a/init/main.c
+++ b/init/main.c
@@ -129,63 +129,6 @@ static char *static_command_line;
 static char *execute_command;
 static char *ramdisk_execute_command;
 
-#ifdef CONFIG_SMP
-/* Setup configured maximum number of CPUs to activate */
-unsigned int setup_max_cpus = NR_CPUS;
-EXPORT_SYMBOL(setup_max_cpus);
-
-
-/*
- * Setup routine for controlling SMP activation
- *
- * Command-line option of "nosmp" or "maxcpus=0" will disable SMP
- * activation entirely (the MPS table probe still happens, though).
- *
- * Command-line option of "maxcpus=<NUM>", where <NUM> is an integer
- * greater than 0, limits the maximum number of CPUs activated in
- * SMP mode to <NUM>.
- */
-
-void __weak arch_disable_smp_support(void) { }
-
-static int __init nosmp(char *str)
-{
-	setup_max_cpus = 0;
-	arch_disable_smp_support();
-
-	return 0;
-}
-
-early_param("nosmp", nosmp);
-
-/* this is hard limit */
-static int __init nrcpus(char *str)
-{
-	int nr_cpus;
-
-	get_option(&str, &nr_cpus);
-	if (nr_cpus > 0 && nr_cpus < nr_cpu_ids)
-		nr_cpu_ids = nr_cpus;
-
-	return 0;
-}
-
-early_param("nr_cpus", nrcpus);
-
-static int __init maxcpus(char *str)
-{
-	get_option(&str, &setup_max_cpus);
-	if (setup_max_cpus == 0)
-		arch_disable_smp_support();
-
-	return 0;
-}
-
-early_param("maxcpus", maxcpus);
-#else
-static const unsigned int setup_max_cpus = NR_CPUS;
-#endif
-
 /*
  * If set, this is an indication to the drivers that reset the underlying
  * device before going ahead with the initialization otherwise driver might
@@ -362,7 +305,7 @@ static int __init rdinit_setup(char *str)
 __setup("rdinit=", rdinit_setup);
 
 #ifndef CONFIG_SMP
-
+static const unsigned int setup_max_cpus = NR_CPUS;
 #ifdef CONFIG_X86_LOCAL_APIC
 static void __init smp_init(void)
 {
@@ -374,37 +317,6 @@ static void __init smp_init(void)
 
 static inline void setup_nr_cpu_ids(void) { }
 static inline void smp_prepare_cpus(unsigned int maxcpus) { }
-
-#else
-
-/* Setup number of possible processor ids */
-int nr_cpu_ids __read_mostly = NR_CPUS;
-EXPORT_SYMBOL(nr_cpu_ids);
-
-/* An arch may set nr_cpu_ids earlier if needed, so this would be redundant */
-static void __init setup_nr_cpu_ids(void)
-{
-	nr_cpu_ids = find_last_bit(cpumask_bits(cpu_possible_mask),NR_CPUS) + 1;
-}
-
-/* Called by boot processor to activate the rest. */
-static void __init smp_init(void)
-{
-	unsigned int cpu;
-
-	/* FIXME: This should be done in userspace --RR */
-	for_each_present_cpu(cpu) {
-		if (num_online_cpus() >= setup_max_cpus)
-			break;
-		if (!cpu_online(cpu))
-			cpu_up(cpu);
-	}
-
-	/* Any cleanup work */
-	printk(KERN_INFO "Brought up %ld CPUs\n", (long)num_online_cpus());
-	smp_cpus_done(setup_max_cpus);
-}
-
 #endif
 
 /*
@@ -875,15 +787,6 @@ static int __init kernel_init(void * unused)
 	 * init can run on any cpu.
 	 */
 	set_cpus_allowed_ptr(current, cpu_all_mask);
-	/*
-	 * Tell the world that we're going to be the grim
-	 * reaper of innocent orphaned children.
-	 *
-	 * We don't want people to have to make incorrect
-	 * assumptions about where in the task array this
-	 * can be found.
-	 */
-	init_pid_ns.child_reaper = current;
 
 	cad_pid = task_pid(current);
 
diff --git a/init/version.c b/init/version.c
index adff586401a5..86fe0ccb997a 100644
--- a/init/version.c
+++ b/init/version.c
@@ -33,6 +33,7 @@ struct uts_namespace init_uts_ns = {
 		.machine	= UTS_MACHINE,
 		.domainname	= UTS_DOMAINNAME,
 	},
+	.user_ns = &init_user_ns,
 };
 EXPORT_SYMBOL_GPL(init_uts_ns);