Merge tag 'v3.8-rc4' into irq/core

Merge Linux 3.8-rc4 before pulling in new commits - we were on an old v3.7 base.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

4 files changed, 138 insertions, 51 deletions

diff --git a/init/Kconfig b/init/Kconfig
index 6fdd6e339326..be8b7f55312d 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -486,35 +486,35 @@ config PREEMPT_RCU
 	  This option enables preemptible-RCU code that is common between
 	  the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations.
 
+config CONTEXT_TRACKING
+       bool
+
 config RCU_USER_QS
 	bool "Consider userspace as in RCU extended quiescent state"
-	depends on HAVE_RCU_USER_QS && SMP
+	depends on HAVE_CONTEXT_TRACKING && SMP
+	select CONTEXT_TRACKING
 	help
 	  This option sets hooks on kernel / userspace boundaries and
 	  puts RCU in extended quiescent state when the CPU runs in
 	  userspace. It means that when a CPU runs in userspace, it is
 	  excluded from the global RCU state machine and thus doesn't
-	  to keep the timer tick on for RCU.
+	  try to keep the timer tick on for RCU.
 
 	  Unless you want to hack and help the development of the full
-	  tickless feature, you shouldn't enable this option. It adds
-	  unnecessary overhead.
+	  dynticks mode, you shouldn't enable this option.  It also
+	  adds unnecessary overhead.
 
 	  If unsure say N
 
-config RCU_USER_QS_FORCE
-	bool "Force userspace extended QS by default"
-	depends on RCU_USER_QS
+config CONTEXT_TRACKING_FORCE
+	bool "Force context tracking"
+	depends on CONTEXT_TRACKING
 	help
-	  Set the hooks in user/kernel boundaries by default in order to
-	  test this feature that treats userspace as an extended quiescent
-	  state until we have a real user like a full adaptive nohz option.
-
-	  Unless you want to hack and help the development of the full
-	  tickless feature, you shouldn't enable this option. It adds
-	  unnecessary overhead.
-
-	  If unsure say N
+	  Probe on user/kernel boundaries by default in order to
+	  test the features that rely on it such as userspace RCU extended
+	  quiescent states.
+	  This test is there for debugging until we have a real user like the
+	  full dynticks mode.
 
 config RCU_FANOUT
 	int "Tree-based hierarchical RCU fanout value"
@@ -582,14 +582,13 @@ config RCU_FAST_NO_HZ
 	depends on NO_HZ && SMP
 	default n
 	help
-	  This option causes RCU to attempt to accelerate grace periods
-	  in order to allow CPUs to enter dynticks-idle state more
-	  quickly.  On the other hand, this option increases the overhead
-	  of the dynticks-idle checking, particularly on systems with
-	  large numbers of CPUs.
+	  This option causes RCU to attempt to accelerate grace periods in
+	  order to allow CPUs to enter dynticks-idle state more quickly.
+	  On the other hand, this option increases the overhead of the
+	  dynticks-idle checking, thus degrading scheduling latency.
 
-	  Say Y if energy efficiency is critically important, particularly
-	  	if you have relatively few CPUs.
+	  Say Y if energy efficiency is critically important, and you don't
+	  	care about real-time response.
 
 	  Say N if you are unsure.
 
@@ -655,6 +654,28 @@ config RCU_BOOST_DELAY
 
 	  Accept the default if unsure.
 
+config RCU_NOCB_CPU
+	bool "Offload RCU callback processing from boot-selected CPUs"
+	depends on TREE_RCU || TREE_PREEMPT_RCU
+	default n
+	help
+	  Use this option to reduce OS jitter for aggressive HPC or
+	  real-time workloads.	It can also be used to offload RCU
+	  callback invocation to energy-efficient CPUs in battery-powered
+	  asymmetric multiprocessors.
+
+	  This option offloads callback invocation from the set of
+	  CPUs specified at boot time by the rcu_nocbs parameter.
+	  For each such CPU, a kthread ("rcuoN") will be created to
+	  invoke callbacks, where the "N" is the CPU being offloaded.
+	  Nothing prevents this kthread from running on the specified
+	  CPUs, but (1) the kthreads may be preempted between each
+	  callback, and (2) affinity or cgroups can be used to force
+	  the kthreads to run on whatever set of CPUs is desired.
+
+	  Say Y here if you want reduced OS jitter on selected CPUs.
+	  Say N here if you are unsure.
+
 endmenu # "RCU Subsystem"
 
 config IKCONFIG
@@ -696,6 +717,50 @@ config LOG_BUF_SHIFT
 config HAVE_UNSTABLE_SCHED_CLOCK
 	bool
 
+#
+# For architectures that want to enable the support for NUMA-affine scheduler
+# balancing logic:
+#
+config ARCH_SUPPORTS_NUMA_BALANCING
+	bool
+
+# For architectures that (ab)use NUMA to represent different memory regions
+# all cpu-local but of different latencies, such as SuperH.
+#
+config ARCH_WANT_NUMA_VARIABLE_LOCALITY
+	bool
+
+#
+# For architectures that are willing to define _PAGE_NUMA as _PAGE_PROTNONE
+config ARCH_WANTS_PROT_NUMA_PROT_NONE
+	bool
+
+config ARCH_USES_NUMA_PROT_NONE
+	bool
+	default y
+	depends on ARCH_WANTS_PROT_NUMA_PROT_NONE
+	depends on NUMA_BALANCING
+
+config NUMA_BALANCING_DEFAULT_ENABLED
+	bool "Automatically enable NUMA aware memory/task placement"
+	default y
+	depends on NUMA_BALANCING
+	help
+	  If set, autonumic NUMA balancing will be enabled if running on a NUMA
+	  machine.
+
+config NUMA_BALANCING
+	bool "Memory placement aware NUMA scheduler"
+	depends on ARCH_SUPPORTS_NUMA_BALANCING
+	depends on !ARCH_WANT_NUMA_VARIABLE_LOCALITY
+	depends on SMP && NUMA && MIGRATION
+	help
+	  This option adds support for automatic NUMA aware memory/task placement.
+	  The mechanism is quite primitive and is based on migrating memory when
+	  it is references to the node the task is running on.
+
+	  This system will be inactive on UMA systems.
+
 menuconfig CGROUPS
 	boolean "Control Group support"
 	depends on EVENTFD
@@ -817,7 +882,7 @@ config MEMCG_SWAP_ENABLED
 config MEMCG_KMEM
 	bool "Memory Resource Controller Kernel Memory accounting (EXPERIMENTAL)"
 	depends on MEMCG && EXPERIMENTAL
-	default n
+	depends on SLUB || SLAB
 	help
 	  The Kernel Memory extension for Memory Resource Controller can limit
 	  the amount of memory used by kernel objects in the system. Those are
@@ -1004,11 +1069,9 @@ config UIDGID_CONVERTED
 	# Filesystems
 	depends on 9P_FS = n
 	depends on AFS_FS = n
-	depends on AUTOFS4_FS = n
 	depends on CEPH_FS = n
 	depends on CIFS = n
 	depends on CODA_FS = n
-	depends on FUSE_FS = n
 	depends on GFS2_FS = n
 	depends on NCP_FS = n
 	depends on NFSD = n
@@ -1119,7 +1182,7 @@ config CC_OPTIMIZE_FOR_SIZE
 	  Enabling this option will pass "-Os" instead of "-O2" to gcc
 	  resulting in a smaller kernel.
 
-	  If unsure, say Y.
+	  If unsure, say N.
 
 config SYSCTL
 	bool
diff --git a/init/do_mounts.c b/init/do_mounts.c
index f8a66424360d..1d1b6348f903 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -69,23 +69,28 @@ __setup("ro", readonly);
 __setup("rw", readwrite);
 
 #ifdef CONFIG_BLOCK
+struct uuidcmp {
+	const char *uuid;
+	int len;
+};
+
 /**
  * match_dev_by_uuid - callback for finding a partition using its uuid
  * @dev:	device passed in by the caller
- * @data:	opaque pointer to a 36 byte char array with a UUID
+ * @data:	opaque pointer to the desired struct uuidcmp to match
  *
  * Returns 1 if the device matches, and 0 otherwise.
  */
 static int match_dev_by_uuid(struct device *dev, void *data)
 {
-	u8 *uuid = data;
+	struct uuidcmp *cmp = data;
 	struct hd_struct *part = dev_to_part(dev);
 
 	if (!part->info)
 		goto no_match;
 
-	if (memcmp(uuid, part->info->uuid, sizeof(part->info->uuid)))
-			goto no_match;
+	if (strncasecmp(cmp->uuid, part->info->uuid, cmp->len))
+		goto no_match;
 
 	return 1;
 no_match:
@@ -95,7 +100,7 @@ no_match:
 
 /**
  * devt_from_partuuid - looks up the dev_t of a partition by its UUID
- * @uuid:	min 36 byte char array containing a hex ascii UUID
+ * @uuid:	char array containing ascii UUID
  *
  * The function will return the first partition which contains a matching
  * UUID value in its partition_meta_info struct.  This does not search
@@ -106,38 +111,41 @@ no_match:
  *
  * Returns the matching dev_t on success or 0 on failure.
  */
-static dev_t devt_from_partuuid(char *uuid_str)
+static dev_t devt_from_partuuid(const char *uuid_str)
 {
 	dev_t res = 0;
+	struct uuidcmp cmp;
 	struct device *dev = NULL;
-	u8 uuid[16];
 	struct gendisk *disk;
 	struct hd_struct *part;
 	int offset = 0;
+	bool clear_root_wait = false;
+	char *slash;
 
-	if (strlen(uuid_str) < 36)
-		goto done;
+	cmp.uuid = uuid_str;
 
+	slash = strchr(uuid_str, '/');
 	/* Check for optional partition number offset attributes. */
-	if (uuid_str[36]) {
+	if (slash) {
 		char c = 0;
 		/* Explicitly fail on poor PARTUUID syntax. */
-		if (sscanf(&uuid_str[36],
-			   "/PARTNROFF=%d%c", &offset, &c) != 1) {
-			printk(KERN_ERR "VFS: PARTUUID= is invalid.\n"
-			 "Expected PARTUUID=<valid-uuid-id>[/PARTNROFF=%%d]\n");
-			if (root_wait)
-				printk(KERN_ERR
-				     "Disabling rootwait; root= is invalid.\n");
-			root_wait = 0;
+		if (sscanf(slash + 1,
+			   "PARTNROFF=%d%c", &offset, &c) != 1) {
+			clear_root_wait = true;
 			goto done;
 		}
+		cmp.len = slash - uuid_str;
+	} else {
+		cmp.len = strlen(uuid_str);
 	}
 
-	/* Pack the requested UUID in the expected format. */
-	part_pack_uuid(uuid_str, uuid);
+	if (!cmp.len) {
+		clear_root_wait = true;
+		goto done;
+	}
 
-	dev = class_find_device(&block_class, NULL, uuid, &match_dev_by_uuid);
+	dev = class_find_device(&block_class, NULL, &cmp,
+				&match_dev_by_uuid);
 	if (!dev)
 		goto done;
 
@@ -158,6 +166,13 @@ static dev_t devt_from_partuuid(char *uuid_str)
 no_offset:
 	put_device(dev);
 done:
+	if (clear_root_wait) {
+		pr_err("VFS: PARTUUID= is invalid.\n"
+		       "Expected PARTUUID=<valid-uuid-id>[/PARTNROFF=%%d]\n");
+		if (root_wait)
+			pr_err("Disabling rootwait; root= is invalid.\n");
+		root_wait = 0;
+	}
 	return res;
 }
 #endif
@@ -174,6 +189,10 @@ done:
  *	   used when disk name of partitioned disk ends on a digit.
  *	6) PARTUUID=00112233-4455-6677-8899-AABBCCDDEEFF representing the
  *	   unique id of a partition if the partition table provides it.
+ *	   The UUID may be either an EFI/GPT UUID, or refer to an MSDOS
+ *	   partition using the format SSSSSSSS-PP, where SSSSSSSS is a zero-
+ *	   filled hex representation of the 32-bit "NT disk signature", and PP
+ *	   is a zero-filled hex representation of the 1-based partition number.
  *	7) PARTUUID=<UUID>/PARTNROFF=<int> to select a partition in relation to
  *	   a partition with a known unique id.
  *
diff --git a/init/main.c b/init/main.c
index 9cf77ab138a6..85d69dffe864 100644
--- a/init/main.c
+++ b/init/main.c
@@ -442,9 +442,11 @@ void __init __weak smp_setup_processor_id(void)
 {
 }
 
+# if THREAD_SIZE >= PAGE_SIZE
 void __init __weak thread_info_cache_init(void)
 {
 }
+#endif
 
 /*
  * Set up kernel memory allocators
@@ -795,7 +797,9 @@ static void __init do_pre_smp_initcalls(void)
 static int run_init_process(const char *init_filename)
 {
 	argv_init[0] = init_filename;
-	return kernel_execve(init_filename, argv_init, envp_init);
+	return do_execve(init_filename,
+		(const char __user *const __user *)argv_init,
+		(const char __user *const __user *)envp_init);
 }
 
 static void __init kernel_init_freeable(void);
@@ -810,7 +814,6 @@ static int __ref kernel_init(void *unused)
 	system_state = SYSTEM_RUNNING;
 	numa_default_policy();
 
-	current->signal->flags |= SIGNAL_UNKILLABLE;
 	flush_delayed_fput();
 
 	if (ramdisk_execute_command) {
@@ -855,7 +858,7 @@ static void __init kernel_init_freeable(void)
 	/*
 	 * init can allocate pages on any node
 	 */
-	set_mems_allowed(node_states[N_HIGH_MEMORY]);
+	set_mems_allowed(node_states[N_MEMORY]);
 	/*
 	 * init can run on any cpu.
 	 */
diff --git a/init/version.c b/init/version.c
index 86fe0ccb997a..58170f18912d 100644
--- a/init/version.c
+++ b/init/version.c
@@ -12,6 +12,7 @@
 #include <linux/utsname.h>
 #include <generated/utsrelease.h>
 #include <linux/version.h>
+#include <linux/proc_fs.h>
 
 #ifndef CONFIG_KALLSYMS
 #define version(a) Version_ ## a
@@ -34,6 +35,7 @@ struct uts_namespace init_uts_ns = {
 		.domainname	= UTS_DOMAINNAME,
 	},
 	.user_ns = &init_user_ns,
+	.proc_inum = PROC_UTS_INIT_INO,
 };
 EXPORT_SYMBOL_GPL(init_uts_ns);