3 files changed, 143 insertions, 43 deletions

diff --git a/init/Kconfig b/init/Kconfig
index 2de5b1cbadd9..3ae8ffe738eb 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -21,6 +21,13 @@ config CONSTRUCTORS
         depends on !UML
         default y
 
+config HAVE_IRQ_WORK
+        bool
+
+config IRQ_WORK
+        bool
+        depends on HAVE_IRQ_WORK
+
 menu "General setup"
 
 config EXPERIMENTAL
@@ -64,7 +71,7 @@ config BROKEN_ON_SMP
 
 config LOCK_KERNEL
         bool
-        depends on SMP || PREEMPT
+        depends on (SMP || PREEMPT) && BKL
         default y
 
 config INIT_ENV_ARG_LIMIT
@@ -179,7 +186,7 @@ config KERNEL_LZO
         depends on HAVE_KERNEL_LZO
         help
           Its compression ratio is the poorest among the 4. The kernel
-          size is about about 10% bigger than gzip; however its speed
+          size is about 10% bigger than gzip; however its speed
           (both compression and decompression) is the fastest.
 
 endchoice
@@ -332,6 +339,8 @@ config AUDIT_TREE
         depends on AUDITSYSCALL
         select FSNOTIFY
 
+source "kernel/irq/Kconfig"
+
 menu "RCU Subsystem"
 
 choice
@@ -340,6 +349,7 @@ choice
 
 config TREE_RCU
         bool "Tree-based hierarchical RCU"
+        depends on !PREEMPT && SMP
         help
           This option selects the RCU implementation that is
           designed for very large SMP system with hundreds or
@@ -347,7 +357,7 @@ config TREE_RCU
           smaller systems.
 
 config TREE_PREEMPT_RCU
-        bool "Preemptable tree-based hierarchical RCU"
+        bool "Preemptible tree-based hierarchical RCU"
         depends on PREEMPT
         help
           This option selects the RCU implementation that is
@@ -365,8 +375,22 @@ config TINY_RCU
           is not required.  This option greatly reduces the
           memory footprint of RCU.
 
+config TINY_PREEMPT_RCU
+        bool "Preemptible UP-only small-memory-footprint RCU"
+        depends on !SMP && PREEMPT
+        help
+          This option selects the RCU implementation that is designed
+          for real-time UP systems.  This option greatly reduces the
+          memory footprint of RCU.
+
 endchoice
 
+config PREEMPT_RCU
+        def_bool ( TREE_PREEMPT_RCU || TINY_PREEMPT_RCU )
+        help
+          This option enables preemptible-RCU code that is common between
+          the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations.
+
 config RCU_TRACE
         bool "Enable tracing for RCU"
         depends on TREE_RCU || TREE_PREEMPT_RCU
@@ -387,9 +411,12 @@ config RCU_FANOUT
         help
           This option controls the fanout of hierarchical implementations
           of RCU, allowing RCU to work efficiently on machines with
-          large numbers of CPUs.  This value must be at least the cube
-          root of NR_CPUS, which allows NR_CPUS up to 32,768 for 32-bit
-          systems and up to 262,144 for 64-bit systems.
+          large numbers of CPUs.  This value must be at least the fourth
+          root of NR_CPUS, which allows NR_CPUS to be insanely large.
+          The default value of RCU_FANOUT should be used for production
+          systems, but if you are stress-testing the RCU implementation
+          itself, small RCU_FANOUT values allow you to test large-system
+          code paths on small(er) systems.
 
           Select a specific number if testing RCU itself.
           Take the default if unsure.
@@ -634,11 +661,14 @@ config BLK_CGROUP
 
         Currently, CFQ IO scheduler uses it to recognize task groups and
         control disk bandwidth allocation (proportional time slice allocation)
-        to such task groups.
+        to such task groups. It is also used by bio throttling logic in
+        block layer to implement upper limit in IO rates on a device.
 
         This option only enables generic Block IO controller infrastructure.
-        One needs to also enable actual IO controlling logic in CFQ for it
-        to take effect. (CONFIG_CFQ_GROUP_IOSCHED=y).
+        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.
 
         See Documentation/cgroups/blkio-controller.txt for more information.
 
@@ -656,40 +686,42 @@ config MM_OWNER
         bool
 
 config SYSFS_DEPRECATED
-        bool
-
-config SYSFS_DEPRECATED_V2
         bool "enable deprecated sysfs features to support old userspace tools"
         depends on SYSFS
         default n
-        select SYSFS_DEPRECATED
-        help
-          This option switches the layout of sysfs to the deprecated
-          version. Do not use it on recent distributions.
-
-          The current sysfs layout features a unified device tree at
-          /sys/devices/, which is able to express a hierarchy between
-          class devices. If the deprecated option is set to Y, the
-          unified device tree is split into a bus device tree at
-          /sys/devices/ and several individual class device trees at
-          /sys/class/. The class and bus devices will be connected by
-          "<subsystem>:<name>" and the "device" links. The "block"
-          class devices, will not show up in /sys/class/block/. Some
-          subsystems will suppress the creation of some devices which
-          depend on the unified device tree.
-
-          This option is not a pure compatibility option that can
-          be safely enabled on newer distributions. It will change the
-          layout of sysfs to the non-extensible deprecated version,
-          and disable some features, which can not be exported without
-          confusing older userspace tools. Since 2007/2008 all major
-          distributions do not enable this option, and ship no tools which
-          depend on the deprecated layout or this option.
-
-          If you are using a new kernel on an older distribution, or use
-          older userspace tools, you might need to say Y here. Do not say Y,
-          if the original kernel, that came with your distribution, has
-          this option set to N.
+        help
+          This option adds code that switches the layout of the "block" class
+          devices, to not show up in /sys/class/block/, but only in
+          /sys/block/.
+
+          This switch is only active when the sysfs.deprecated=1 boot option is
+          passed or the SYSFS_DEPRECATED_V2 option is set.
+
+          This option allows new kernels to run on old distributions and tools,
+          which might get confused by /sys/class/block/. Since 2007/2008 all
+          major distributions and tools handle this just fine.
+
+          Recent distributions and userspace tools after 2009/2010 depend on
+          the existence of /sys/class/block/, and will not work with this
+          option enabled.
+
+          Only if you are using a new kernel on an old distribution, you might
+          need to say Y here.
+
+config SYSFS_DEPRECATED_V2
+        bool "enabled deprecated sysfs features by default"
+        default n
+        depends on SYSFS
+        depends on SYSFS_DEPRECATED
+        help
+          Enable deprecated sysfs by default.
+
+          See the CONFIG_SYSFS_DEPRECATED option for more details about this
+          option.
+
+          Only if you are using a new kernel on an old distribution, you might
+          need to say Y here. Even then, odds are you would not need it
+          enabled, you can always pass the boot option if absolutely necessary.
 
 config RELAY
         bool "Kernel->user space relay support (formerly relayfs)"
@@ -987,6 +1019,7 @@ config PERF_EVENTS
         default y if (PROFILING || PERF_COUNTERS)
         depends on HAVE_PERF_EVENTS
         select ANON_INODES
+        select IRQ_WORK
         help
           Enable kernel support for various performance events provided
           by software and hardware.
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 52387f14f9b4..62a47eafa8e9 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -58,6 +58,62 @@ static int __init readwrite(char *str)
 __setup("ro", readonly);
 __setup("rw", readwrite);
 
+#ifdef CONFIG_BLOCK
+/**
+ * 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
+ *
+ * Returns 1 if the device matches, and 0 otherwise.
+ */
+static int match_dev_by_uuid(struct device *dev, void *data)
+{
+        u8 *uuid = 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;
+
+        return 1;
+no_match:
+        return 0;
+}
+
+
+/**
+ * devt_from_partuuid - looks up the dev_t of a partition by its UUID
+ * @uuid:       36 byte char array containing a hex 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
+ * by filesystem UUIDs.
+ *
+ * Returns the matching dev_t on success or 0 on failure.
+ */
+static dev_t __init devt_from_partuuid(char *uuid_str)
+{
+        dev_t res = 0;
+        struct device *dev = NULL;
+        u8 uuid[16];
+
+        /* Pack the requested UUID in the expected format. */
+        part_pack_uuid(uuid_str, uuid);
+
+        dev = class_find_device(&block_class, NULL, uuid, &match_dev_by_uuid);
+        if (!dev)
+                goto done;
+
+        res = dev->devt;
+        put_device(dev);
+
+done:
+        return res;
+}
+#endif
+
 /*
  *      Convert a name into device number.  We accept the following variants:
  *
@@ -68,6 +124,8 @@ __setup("rw", readwrite);
  *         of partition - device number of disk plus the partition number
  *      5) /dev/<disk_name>p<decimal> - same as the above, that form is
  *         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.
  *
  *      If name doesn't have fall into the categories above, we return (0,0).
  *      block_class is used to check if something is a disk name. If the disk
@@ -82,6 +140,18 @@ dev_t name_to_dev_t(char *name)
         dev_t res = 0;
         int part;
 
+#ifdef CONFIG_BLOCK
+        if (strncmp(name, "PARTUUID=", 9) == 0) {
+                name += 9;
+                if (strlen(name) != 36)
+                        goto fail;
+                res = devt_from_partuuid(name);
+                if (!res)
+                        goto fail;
+                goto done;
+        }
+#endif
+
         if (strncmp(name, "/dev/", 5) != 0) {
                 unsigned maj, min;
 
diff --git a/init/main.c b/init/main.c
index 94ab488039aa..e59af24a0b7c 100644
--- a/init/main.c
+++ b/init/main.c
@@ -424,7 +424,6 @@ static void __init setup_command_line(char *command_line)
 static __initdata DECLARE_COMPLETION(kthreadd_done);
 
 static noinline void __init_refok rest_init(void)
-        __releases(kernel_lock)
 {
         int pid;
 
@@ -556,7 +555,6 @@ asmlinkage void __init start_kernel(void)
 
         local_irq_disable();
         early_boot_irqs_off();
-        early_init_irq_lock_class();
 
 /*
  * Interrupts are still disabled. Do necessary setups, then
@@ -819,7 +817,6 @@ static void run_init_process(const char *init_filename)
  * makes it inline to init() and it becomes part of init.text section
  */
 static noinline int init_post(void)
-        __releases(kernel_lock)
 {
         /* need to finish all async __init code before freeing the memory */
         async_synchronize_full();