Merge branch 'for-2.6.32' into for-2.6.33

3 files changed, 68 insertions, 97 deletions

diff --git a/init/Kconfig b/init/Kconfig
index 1ce05a4cb5f..c7bac39d6c6 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -316,38 +316,29 @@ choice
         prompt "RCU Implementation"
         default TREE_RCU
 
-config CLASSIC_RCU
-        bool "Classic RCU"
-        help
-          This option selects the classic RCU implementation that is
-          designed for best read-side performance on non-realtime
-          systems.
-
-          Select this option if you are unsure.
-
 config TREE_RCU
         bool "Tree-based hierarchical RCU"
         help
           This option selects the RCU implementation that is
           designed for very large SMP system with hundreds or
-          thousands of CPUs.
+          thousands of CPUs.  It also scales down nicely to
+          smaller systems.
 
-config PREEMPT_RCU
-        bool "Preemptible RCU"
+config TREE_PREEMPT_RCU
+        bool "Preemptable tree-based hierarchical RCU"
         depends on PREEMPT
         help
-          This option reduces the latency of the kernel by making certain
-          RCU sections preemptible. Normally RCU code is non-preemptible, if
-          this option is selected then read-only RCU sections become
-          preemptible. This helps latency, but may expose bugs due to
-          now-naive assumptions about each RCU read-side critical section
-          remaining on a given CPU through its execution.
+          This option selects the RCU implementation that is
+          designed for very large SMP systems with hundreds or
+          thousands of CPUs, but for which real-time response
+          is also required.  It also scales down nicely to
+          smaller systems.
 
 endchoice
 
 config RCU_TRACE
         bool "Enable tracing for RCU"
-        depends on TREE_RCU || PREEMPT_RCU
+        depends on TREE_RCU || TREE_PREEMPT_RCU
         help
           This option provides tracing in RCU which presents stats
           in debugfs for debugging RCU implementation.
@@ -359,7 +350,7 @@ config RCU_FANOUT
         int "Tree-based hierarchical RCU fanout value"
         range 2 64 if 64BIT
         range 2 32 if !64BIT
-        depends on TREE_RCU
+        depends on TREE_RCU || TREE_PREEMPT_RCU
         default 64 if 64BIT
         default 32 if !64BIT
         help
@@ -374,7 +365,7 @@ config RCU_FANOUT
 
 config RCU_FANOUT_EXACT
         bool "Disable tree-based hierarchical RCU auto-balancing"
-        depends on TREE_RCU
+        depends on TREE_RCU || TREE_PREEMPT_RCU
         default n
         help
           This option forces use of the exact RCU_FANOUT value specified,
@@ -387,18 +378,12 @@ config RCU_FANOUT_EXACT
           Say N if unsure.
 
 config TREE_RCU_TRACE
-        def_bool RCU_TRACE && TREE_RCU
+        def_bool RCU_TRACE && ( TREE_RCU || TREE_PREEMPT_RCU )
         select DEBUG_FS
         help
-          This option provides tracing for the TREE_RCU implementation,
-          permitting Makefile to trivially select kernel/rcutree_trace.c.
-
-config PREEMPT_RCU_TRACE
-        def_bool RCU_TRACE && PREEMPT_RCU
-        select DEBUG_FS
-        help
-          This option provides tracing for the PREEMPT_RCU implementation,
-          permitting Makefile to trivially select kernel/rcupreempt_trace.c.
+          This option provides tracing for the TREE_RCU and
+          TREE_PREEMPT_RCU implementations, permitting Makefile to
+          trivially select kernel/rcutree_trace.c.
 
 endmenu # "RCU Subsystem"
 
@@ -931,39 +916,65 @@ config AIO
           by some high performance threaded applications. Disabling
           this option saves about 7k.
 
-config HAVE_PERF_COUNTERS
+config HAVE_PERF_EVENTS
         bool
         help
           See tools/perf/design.txt for details.
 
-menu "Performance Counters"
+menu "Kernel Performance Events And Counters"
 
-config PERF_COUNTERS
-        bool "Kernel Performance Counters"
-        depends on HAVE_PERF_COUNTERS
+config PERF_EVENTS
+        bool "Kernel performance events and counters"
+        default y if (PROFILING || PERF_COUNTERS)
+        depends on HAVE_PERF_EVENTS
         select ANON_INODES
         help
-          Enable kernel support for performance counter hardware.
+          Enable kernel support for various performance events provided
+          by software and hardware.
+
+          Software events are supported either build-in or via the
+          use of generic tracepoints.
 
-          Performance counters are special hardware registers available
-          on most modern CPUs. These registers count the number of certain
+          Most modern CPUs support performance events via performance
+          counter registers. These registers count the number of certain
           types of hw events: such as instructions executed, cachemisses
           suffered, or branches mis-predicted - without slowing down the
           kernel or applications. These registers can also trigger interrupts
           when a threshold number of events have passed - and can thus be
           used to profile the code that runs on that CPU.
 
-          The Linux Performance Counter subsystem provides an abstraction of
-          these hardware capabilities, available via a system call. It
+          The Linux Performance Event subsystem provides an abstraction of
+          these software and hardware cevent apabilities, available via a
+          system call and used by the "perf" utility in tools/perf/. It
           provides per task and per CPU counters, and it provides event
           capabilities on top of those.
 
           Say Y if unsure.
 
 config EVENT_PROFILE
-        bool "Tracepoint profile sources"
-        depends on PERF_COUNTERS && EVENT_TRACER
+        bool "Tracepoint profiling sources"
+        depends on PERF_EVENTS && EVENT_TRACING
         default y
+        help
+         Allow the use of tracepoints as software performance events.
+
+         When this is enabled, you can create perf events based on
+         tracepoints using PERF_TYPE_TRACEPOINT and the tracepoint ID
+         found in debugfs://tracing/events/*/*/id. (The -e/--events
+         option to the perf tool can parse and interpret symbolic
+         tracepoints, in the subsystem:tracepoint_name format.)
+
+config PERF_COUNTERS
+        bool "Kernel performance counters (old config option)"
+        depends on HAVE_PERF_EVENTS
+        help
+          This config has been obsoleted by the PERF_EVENTS
+          config option - please see that one for details.
+
+          It has no effect on the kernel whether you enable
+          it or not, it is a compatibility placeholder.
+
+          Say N if unsure.
 
 endmenu
 
@@ -995,14 +1006,6 @@ config SLUB_DEBUG
           SLUB sysfs support. /sys/slab will not exist and there will be
           no support for cache validation etc.
 
-config STRIP_ASM_SYMS
-        bool "Strip assembler-generated symbols during link"
-        default n
-        help
-          Strip internal assembler-generated symbols during a link (symbols
-          that look like '.Lxxx') so they don't pollute the output of
-          get_wchan() and suchlike.
-
 config COMPAT_BRK
         bool "Disable heap randomization"
         default y
@@ -1061,13 +1064,6 @@ config PROFILING
 config TRACEPOINTS
         bool
 
-config MARKERS
-        bool "Activate markers"
-        select TRACEPOINTS
-        help
-          Place an empty function call at each marker site. Can be
-          dynamically changed for a probe function.
-
 source "arch/Kconfig"
 
 config SLOW_WORK
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 093f6591550..bb008d064c1 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -415,7 +415,7 @@ void __init prepare_namespace(void)
 
         mount_root();
 out:
+        devtmpfs_mount("dev");
         sys_mount(".", "/", NULL, MS_MOVE, NULL);
         sys_chroot(".");
 }
-
diff --git a/init/main.c b/init/main.c
index 2c5ade79eb8..7449819a480 100644
--- a/init/main.c
+++ b/init/main.c
@@ -18,7 +18,6 @@
 #include <linux/string.h>
 #include <linux/ctype.h>
 #include <linux/delay.h>
-#include <linux/utsname.h>
 #include <linux/ioport.h>
 #include <linux/init.h>
 #include <linux/smp_lock.h>
@@ -68,6 +67,8 @@
 #include <linux/async.h>
 #include <linux/kmemcheck.h>
 #include <linux/kmemtrace.h>
+#include <linux/sfi.h>
+#include <linux/shmem_fs.h>
 #include <trace/boot.h>
 
 #include <asm/io.h>
@@ -353,17 +354,11 @@ static void __init smp_init(void)
 #define smp_init()      do { } while (0)
 #endif
 
-static inline void setup_per_cpu_areas(void) { }
 static inline void setup_nr_cpu_ids(void) { }
 static inline void smp_prepare_cpus(unsigned int maxcpus) { }
 
 #else
 
-#if NR_CPUS > BITS_PER_LONG
-cpumask_t cpu_mask_all __read_mostly = CPU_MASK_ALL;
-EXPORT_SYMBOL(cpu_mask_all);
-#endif
-
 /* Setup number of possible processor ids */
 int nr_cpu_ids __read_mostly = NR_CPUS;
 EXPORT_SYMBOL(nr_cpu_ids);
@@ -374,29 +369,6 @@ static void __init setup_nr_cpu_ids(void)
         nr_cpu_ids = find_last_bit(cpumask_bits(cpu_possible_mask),NR_CPUS) + 1;
 }
 
-#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
-unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
-
-EXPORT_SYMBOL(__per_cpu_offset);
-
-static void __init setup_per_cpu_areas(void)
-{
-        unsigned long size, i;
-        char *ptr;
-        unsigned long nr_possible_cpus = num_possible_cpus();
-
-        /* Copy section for each CPU (we discard the original) */
-        size = ALIGN(PERCPU_ENOUGH_ROOM, PAGE_SIZE);
-        ptr = alloc_bootmem_pages(size * nr_possible_cpus);
-
-        for_each_possible_cpu(i) {
-                __per_cpu_offset[i] = ptr - __per_cpu_start;
-                memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
-                ptr += size;
-        }
-}
-#endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */
-
 /* Called by boot processor to activate the rest. */
 static void __init smp_init(void)
 {
@@ -451,6 +423,7 @@ static noinline void __init_refok rest_init(void)
 {
         int pid;
 
+        rcu_scheduler_starting();
         kernel_thread(kernel_init, NULL, CLONE_FS | CLONE_SIGHAND);
         numa_default_policy();
         pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES);
@@ -462,7 +435,6 @@ static noinline void __init_refok rest_init(void)
          * at least once to get things moving:
          */
         init_idle_bootup_task(current);
-        rcu_scheduler_starting();
         preempt_enable_no_resched();
         schedule();
         preempt_disable();
@@ -584,8 +556,8 @@ asmlinkage void __init start_kernel(void)
         setup_arch(&command_line);
         mm_init_owner(&init_mm, &init_task);
         setup_command_line(command_line);
-        setup_per_cpu_areas();
         setup_nr_cpu_ids();
+        setup_per_cpu_areas();
         smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */
 
         build_all_zonelists();
@@ -631,7 +603,6 @@ asmlinkage void __init start_kernel(void)
         softirq_init();
         timekeeping_init();
         time_init();
-        sched_clock_init();
         profile_init();
         if (!irqs_disabled())
                 printk(KERN_CRIT "start_kernel(): bug: interrupts were "
@@ -682,6 +653,7 @@ asmlinkage void __init start_kernel(void)
         numa_policy_init();
         if (late_time_init)
                 late_time_init();
+        sched_clock_init();
         calibrate_delay();
         pidmap_init();
         anon_vma_init();
@@ -691,12 +663,12 @@ asmlinkage void __init start_kernel(void)
 #endif
         thread_info_cache_init();
         cred_init();
-        fork_init(num_physpages);
+        fork_init(totalram_pages);
         proc_caches_init();
         buffer_init();
         key_init();
         security_init();
-        vfs_caches_init(num_physpages);
+        vfs_caches_init(totalram_pages);
         radix_tree_init();
         signals_init();
         /* rootfs populating might need page-writeback */
@@ -712,6 +684,7 @@ asmlinkage void __init start_kernel(void)
         check_bugs();
 
         acpi_early_init(); /* before LAPIC and SMP init */
+        sfi_init_late();
 
         ftrace_init();
 
@@ -733,13 +706,14 @@ static void __init do_ctors(void)
 int initcall_debug;
 core_param(initcall_debug, initcall_debug, bool, 0644);
 
+static char msgbuf[64];
+static struct boot_trace_call call;
+static struct boot_trace_ret ret;
+
 int do_one_initcall(initcall_t fn)
 {
         int count = preempt_count();
         ktime_t calltime, delta, rettime;
-        char msgbuf[64];
-        struct boot_trace_call call;
-        struct boot_trace_ret ret;
 
         if (initcall_debug) {
                 call.caller = task_pid_nr(current);
@@ -808,6 +782,7 @@ static void __init do_basic_setup(void)
         init_workqueues();
         cpuset_init_smp();
         usermodehelper_init();
+        init_tmpfs();
         driver_init();
         init_irq_proc();
         do_ctors();