18 files changed, 938 insertions, 240 deletions

diff --git a/kernel/audit.c b/kernel/audit.c
index 32fa03ad1984..d13ab7d2d899 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -267,7 +267,7 @@ static int audit_set_failure(int state, uid_t loginuid)
         return old;
 }
 
-int kauditd_thread(void *dummy)
+static int kauditd_thread(void *dummy)
 {
         struct sk_buff *skb;
 
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 7430640f9816..eab64e23bcae 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -39,6 +39,7 @@
 #include <linux/namei.h>
 #include <linux/pagemap.h>
 #include <linux/proc_fs.h>
+#include <linux/rcupdate.h>
 #include <linux/sched.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
@@ -54,7 +55,23 @@
 #include <asm/atomic.h>
 #include <asm/semaphore.h>
 
-#define CPUSET_SUPER_MAGIC              0x27e0eb
+#define CPUSET_SUPER_MAGIC              0x27e0eb
+
+/*
+ * Tracks how many cpusets are currently defined in system.
+ * When there is only one cpuset (the root cpuset) we can
+ * short circuit some hooks.
+ */
+int number_of_cpusets __read_mostly;
+
+/* See "Frequency meter" comments, below. */
+
+struct fmeter {
+        int cnt;                /* unprocessed events count */
+        int val;                /* most recent output value */
+        time_t time;            /* clock (secs) when val computed */
+        spinlock_t lock;        /* guards read or write of above */
+};
 
 struct cpuset {
         unsigned long flags;            /* "unsigned long" so bitops work */
@@ -80,13 +97,16 @@ struct cpuset {
          * Copy of global cpuset_mems_generation as of the most
          * recent time this cpuset changed its mems_allowed.
          */
-         int mems_generation;
+        int mems_generation;
+
+        struct fmeter fmeter;           /* memory_pressure filter */
 };
 
 /* bits in struct cpuset flags field */
 typedef enum {
         CS_CPU_EXCLUSIVE,
         CS_MEM_EXCLUSIVE,
+        CS_MEMORY_MIGRATE,
         CS_REMOVED,
         CS_NOTIFY_ON_RELEASE
 } cpuset_flagbits_t;
@@ -112,6 +132,11 @@ static inline int notify_on_release(const struct cpuset *cs)
         return !!test_bit(CS_NOTIFY_ON_RELEASE, &cs->flags);
 }
 
+static inline int is_memory_migrate(const struct cpuset *cs)
+{
+        return !!test_bit(CS_MEMORY_MIGRATE, &cs->flags);
+}
+
 /*
  * Increment this atomic integer everytime any cpuset changes its
  * mems_allowed value.  Users of cpusets can track this generation
@@ -137,13 +162,10 @@ static struct cpuset top_cpuset = {
         .count = ATOMIC_INIT(0),
         .sibling = LIST_HEAD_INIT(top_cpuset.sibling),
         .children = LIST_HEAD_INIT(top_cpuset.children),
-        .parent = NULL,
-        .dentry = NULL,
-        .mems_generation = 0,
 };
 
 static struct vfsmount *cpuset_mount;
-static struct super_block *cpuset_sb = NULL;
+static struct super_block *cpuset_sb;
 
 /*
  * We have two global cpuset semaphores below.  They can nest.
@@ -227,6 +249,11 @@ static struct super_block *cpuset_sb = NULL;
  * a tasks cpuset pointer we use task_lock(), which acts on a spinlock
  * (task->alloc_lock) already in the task_struct routinely used for
  * such matters.
+ *
+ * P.S.  One more locking exception.  RCU is used to guard the
+ * update of a tasks cpuset pointer by attach_task() and the
+ * access of task->cpuset->mems_generation via that pointer in
+ * the routine cpuset_update_task_memory_state().
  */
 
 static DECLARE_MUTEX(manage_sem);
@@ -304,7 +331,7 @@ static void cpuset_d_remove_dir(struct dentry *dentry)
         spin_lock(&dcache_lock);
         node = dentry->d_subdirs.next;
         while (node != &dentry->d_subdirs) {
-                struct dentry *d = list_entry(node, struct dentry, d_child);
+                struct dentry *d = list_entry(node, struct dentry, d_u.d_child);
                 list_del_init(node);
                 if (d->d_inode) {
                         d = dget_locked(d);
@@ -316,7 +343,7 @@ static void cpuset_d_remove_dir(struct dentry *dentry)
                 }
                 node = dentry->d_subdirs.next;
         }
-        list_del_init(&dentry->d_child);
+        list_del_init(&dentry->d_u.d_child);
         spin_unlock(&dcache_lock);
         remove_dir(dentry);
 }
@@ -570,20 +597,43 @@ static void guarantee_online_mems(const struct cpuset *cs, nodemask_t *pmask)
         BUG_ON(!nodes_intersects(*pmask, node_online_map));
 }
 
-/*
- * Refresh current tasks mems_allowed and mems_generation from current
- * tasks cpuset.
+/**
+ * cpuset_update_task_memory_state - update task memory placement
  *
- * Call without callback_sem or task_lock() held.  May be called with
- * or without manage_sem held.  Will acquire task_lock() and might
- * acquire callback_sem during call.
+ * If the current tasks cpusets mems_allowed changed behind our
+ * backs, update current->mems_allowed, mems_generation and task NUMA
+ * mempolicy to the new value.
+ *
+ * Task mempolicy is updated by rebinding it relative to the
+ * current->cpuset if a task has its memory placement changed.
+ * Do not call this routine if in_interrupt().
  *
- * The task_lock() is required to dereference current->cpuset safely.
- * Without it, we could pick up the pointer value of current->cpuset
- * in one instruction, and then attach_task could give us a different
- * cpuset, and then the cpuset we had could be removed and freed,
- * and then on our next instruction, we could dereference a no longer
- * valid cpuset pointer to get its mems_generation field.
+ * Call without callback_sem or task_lock() held.  May be called
+ * with or without manage_sem held.  Doesn't need task_lock to guard
+ * against another task changing a non-NULL cpuset pointer to NULL,
+ * as that is only done by a task on itself, and if the current task
+ * is here, it is not simultaneously in the exit code NULL'ing its
+ * cpuset pointer.  This routine also might acquire callback_sem and
+ * current->mm->mmap_sem during call.
+ *
+ * Reading current->cpuset->mems_generation doesn't need task_lock
+ * to guard the current->cpuset derefence, because it is guarded
+ * from concurrent freeing of current->cpuset by attach_task(),
+ * using RCU.
+ *
+ * The rcu_dereference() is technically probably not needed,
+ * as I don't actually mind if I see a new cpuset pointer but
+ * an old value of mems_generation.  However this really only
+ * matters on alpha systems using cpusets heavily.  If I dropped
+ * that rcu_dereference(), it would save them a memory barrier.
+ * For all other arch's, rcu_dereference is a no-op anyway, and for
+ * alpha systems not using cpusets, another planned optimization,
+ * avoiding the rcu critical section for tasks in the root cpuset
+ * which is statically allocated, so can't vanish, will make this
+ * irrelevant.  Better to use RCU as intended, than to engage in
+ * some cute trick to save a memory barrier that is impossible to
+ * test, for alpha systems using cpusets heavily, which might not
+ * even exist.
  *
  * This routine is needed to update the per-task mems_allowed data,
  * within the tasks context, when it is trying to allocate memory
@@ -591,27 +641,31 @@ static void guarantee_online_mems(const struct cpuset *cs, nodemask_t *pmask)
  * task has been modifying its cpuset.
  */
 
-static void refresh_mems(void)
+void cpuset_update_task_memory_state()
 {
         int my_cpusets_mem_gen;
+        struct task_struct *tsk = current;
+        struct cpuset *cs;
 
-        task_lock(current);
-        my_cpusets_mem_gen = current->cpuset->mems_generation;
-        task_unlock(current);
-
-        if (current->cpuset_mems_generation != my_cpusets_mem_gen) {
-                struct cpuset *cs;
-                nodemask_t oldmem = current->mems_allowed;
+        if (tsk->cpuset == &top_cpuset) {
+                /* Don't need rcu for top_cpuset.  It's never freed. */
+                my_cpusets_mem_gen = top_cpuset.mems_generation;
+        } else {
+                rcu_read_lock();
+                cs = rcu_dereference(tsk->cpuset);
+                my_cpusets_mem_gen = cs->mems_generation;
+                rcu_read_unlock();
+        }
 
+        if (my_cpusets_mem_gen != tsk->cpuset_mems_generation) {
                 down(&callback_sem);
-                task_lock(current);
-                cs = current->cpuset;
-                guarantee_online_mems(cs, &current->mems_allowed);
-                current->cpuset_mems_generation = cs->mems_generation;
-                task_unlock(current);
+                task_lock(tsk);
+                cs = tsk->cpuset;       /* Maybe changed when task not locked */
+                guarantee_online_mems(cs, &tsk->mems_allowed);
+                tsk->cpuset_mems_generation = cs->mems_generation;
+                task_unlock(tsk);
                 up(&callback_sem);
-                if (!nodes_equal(oldmem, current->mems_allowed))
-                        numa_policy_rebind(&oldmem, &current->mems_allowed);
+                mpol_rebind_task(tsk, &tsk->mems_allowed);
         }
 }
 
@@ -766,36 +820,150 @@ static int update_cpumask(struct cpuset *cs, char *buf)
 }
 
 /*
+ * Handle user request to change the 'mems' memory placement
+ * of a cpuset.  Needs to validate the request, update the
+ * cpusets mems_allowed and mems_generation, and for each
+ * task in the cpuset, rebind any vma mempolicies and if
+ * the cpuset is marked 'memory_migrate', migrate the tasks
+ * pages to the new memory.
+ *
  * Call with manage_sem held.  May take callback_sem during call.
+ * Will take tasklist_lock, scan tasklist for tasks in cpuset cs,
+ * lock each such tasks mm->mmap_sem, scan its vma's and rebind
+ * their mempolicies to the cpusets new mems_allowed.
  */
 
 static int update_nodemask(struct cpuset *cs, char *buf)
 {
         struct cpuset trialcs;
+        nodemask_t oldmem;
+        struct task_struct *g, *p;
+        struct mm_struct **mmarray;
+        int i, n, ntasks;
+        int migrate;
+        int fudge;
         int retval;
 
         trialcs = *cs;
         retval = nodelist_parse(buf, trialcs.mems_allowed);
         if (retval < 0)
-                return retval;
+                goto done;
         nodes_and(trialcs.mems_allowed, trialcs.mems_allowed, node_online_map);
-        if (nodes_empty(trialcs.mems_allowed))
-                return -ENOSPC;
+        oldmem = cs->mems_allowed;
+        if (nodes_equal(oldmem, trialcs.mems_allowed)) {
+                retval = 0;             /* Too easy - nothing to do */
+                goto done;
+        }
+        if (nodes_empty(trialcs.mems_allowed)) {
+                retval = -ENOSPC;
+                goto done;
+        }
         retval = validate_change(cs, &trialcs);
-        if (retval == 0) {
-                down(&callback_sem);
-                cs->mems_allowed = trialcs.mems_allowed;
-                atomic_inc(&cpuset_mems_generation);
-                cs->mems_generation = atomic_read(&cpuset_mems_generation);
-                up(&callback_sem);
+        if (retval < 0)
+                goto done;
+
+        down(&callback_sem);
+        cs->mems_allowed = trialcs.mems_allowed;
+        atomic_inc(&cpuset_mems_generation);
+        cs->mems_generation = atomic_read(&cpuset_mems_generation);
+        up(&callback_sem);
+
+        set_cpuset_being_rebound(cs);           /* causes mpol_copy() rebind */
+
+        fudge = 10;                             /* spare mmarray[] slots */
+        fudge += cpus_weight(cs->cpus_allowed); /* imagine one fork-bomb/cpu */
+        retval = -ENOMEM;
+
+        /*
+         * Allocate mmarray[] to hold mm reference for each task
+         * in cpuset cs.  Can't kmalloc GFP_KERNEL while holding
+         * tasklist_lock.  We could use GFP_ATOMIC, but with a
+         * few more lines of code, we can retry until we get a big
+         * enough mmarray[] w/o using GFP_ATOMIC.
+         */
+        while (1) {
+                ntasks = atomic_read(&cs->count);       /* guess */
+                ntasks += fudge;
+                mmarray = kmalloc(ntasks * sizeof(*mmarray), GFP_KERNEL);
+                if (!mmarray)
+                        goto done;
+                write_lock_irq(&tasklist_lock);         /* block fork */
+                if (atomic_read(&cs->count) <= ntasks)
+                        break;                          /* got enough */
+                write_unlock_irq(&tasklist_lock);       /* try again */
+                kfree(mmarray);
         }
+
+        n = 0;
+
+        /* Load up mmarray[] with mm reference for each task in cpuset. */
+        do_each_thread(g, p) {
+                struct mm_struct *mm;
+
+                if (n >= ntasks) {
+                        printk(KERN_WARNING
+                                "Cpuset mempolicy rebind incomplete.\n");
+                        continue;
+                }
+                if (p->cpuset != cs)
+                        continue;
+                mm = get_task_mm(p);
+                if (!mm)
+                        continue;
+                mmarray[n++] = mm;
+        } while_each_thread(g, p);
+        write_unlock_irq(&tasklist_lock);
+
+        /*
+         * Now that we've dropped the tasklist spinlock, we can
+         * rebind the vma mempolicies of each mm in mmarray[] to their
+         * new cpuset, and release that mm.  The mpol_rebind_mm()
+         * call takes mmap_sem, which we couldn't take while holding
+         * tasklist_lock.  Forks can happen again now - the mpol_copy()
+         * cpuset_being_rebound check will catch such forks, and rebind
+         * their vma mempolicies too.  Because we still hold the global
+         * cpuset manage_sem, we know that no other rebind effort will
+         * be contending for the global variable cpuset_being_rebound.
+         * It's ok if we rebind the same mm twice; mpol_rebind_mm()
+         * is idempotent.  Also migrate pages in each mm to new nodes.
+         */
+        migrate = is_memory_migrate(cs);
+        for (i = 0; i < n; i++) {
+                struct mm_struct *mm = mmarray[i];
+
+                mpol_rebind_mm(mm, &cs->mems_allowed);
+                if (migrate) {
+                        do_migrate_pages(mm, &oldmem, &cs->mems_allowed,
+                                                        MPOL_MF_MOVE_ALL);
+                }
+                mmput(mm);
+        }
+
+        /* We're done rebinding vma's to this cpusets new mems_allowed. */
+        kfree(mmarray);
+        set_cpuset_being_rebound(NULL);
+        retval = 0;
+done:
         return retval;
 }
 
 /*
+ * Call with manage_sem held.
+ */
+
+static int update_memory_pressure_enabled(struct cpuset *cs, char *buf)
+{
+        if (simple_strtoul(buf, NULL, 10) != 0)
+                cpuset_memory_pressure_enabled = 1;
+        else
+                cpuset_memory_pressure_enabled = 0;
+        return 0;
+}
+
+/*
  * update_flag - read a 0 or a 1 in a file and update associated flag
  * bit: the bit to update (CS_CPU_EXCLUSIVE, CS_MEM_EXCLUSIVE,
- *                                              CS_NOTIFY_ON_RELEASE)
+ *                              CS_NOTIFY_ON_RELEASE, CS_MEMORY_MIGRATE)
  * cs:  the cpuset to update
  * buf: the buffer where we read the 0 or 1
  *
@@ -834,6 +1002,104 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, char *buf)
 }
 
 /*
+ * Frequency meter - How fast is some event occuring?
+ *
+ * These routines manage a digitally filtered, constant time based,
+ * event frequency meter.  There are four routines:
+ *   fmeter_init() - initialize a frequency meter.
+ *   fmeter_markevent() - called each time the event happens.
+ *   fmeter_getrate() - returns the recent rate of such events.
+ *   fmeter_update() - internal routine used to update fmeter.
+ *
+ * A common data structure is passed to each of these routines,
+ * which is used to keep track of the state required to manage the
+ * frequency meter and its digital filter.
+ *
+ * The filter works on the number of events marked per unit time.
+ * The filter is single-pole low-pass recursive (IIR).  The time unit
+ * is 1 second.  Arithmetic is done using 32-bit integers scaled to
+ * simulate 3 decimal digits of precision (multiplied by 1000).
+ *
+ * With an FM_COEF of 933, and a time base of 1 second, the filter
+ * has a half-life of 10 seconds, meaning that if the events quit
+ * happening, then the rate returned from the fmeter_getrate()
+ * will be cut in half each 10 seconds, until it converges to zero.
+ *
+ * It is not worth doing a real infinitely recursive filter.  If more
+ * than FM_MAXTICKS ticks have elapsed since the last filter event,
+ * just compute FM_MAXTICKS ticks worth, by which point the level
+ * will be stable.
+ *
+ * Limit the count of unprocessed events to FM_MAXCNT, so as to avoid
+ * arithmetic overflow in the fmeter_update() routine.
+ *
+ * Given the simple 32 bit integer arithmetic used, this meter works
+ * best for reporting rates between one per millisecond (msec) and
+ * one per 32 (approx) seconds.  At constant rates faster than one
+ * per msec it maxes out at values just under 1,000,000.  At constant
+ * rates between one per msec, and one per second it will stabilize
+ * to a value N*1000, where N is the rate of events per second.
+ * At constant rates between one per second and one per 32 seconds,
+ * it will be choppy, moving up on the seconds that have an event,
+ * and then decaying until the next event.  At rates slower than
+ * about one in 32 seconds, it decays all the way back to zero between
+ * each event.
+ */
+
+#define FM_COEF 933             /* coefficient for half-life of 10 secs */
+#define FM_MAXTICKS ((time_t)99) /* useless computing more ticks than this */
+#define FM_MAXCNT 1000000       /* limit cnt to avoid overflow */
+#define FM_SCALE 1000           /* faux fixed point scale */
+
+/* Initialize a frequency meter */
+static void fmeter_init(struct fmeter *fmp)
+{
+        fmp->cnt = 0;
+        fmp->val = 0;
+        fmp->time = 0;
+        spin_lock_init(&fmp->lock);
+}
+
+/* Internal meter update - process cnt events and update value */
+static void fmeter_update(struct fmeter *fmp)
+{
+        time_t now = get_seconds();
+        time_t ticks = now - fmp->time;
+
+        if (ticks == 0)
+                return;
+
+        ticks = min(FM_MAXTICKS, ticks);
+        while (ticks-- > 0)
+                fmp->val = (FM_COEF * fmp->val) / FM_SCALE;
+        fmp->time = now;
+
+        fmp->val += ((FM_SCALE - FM_COEF) * fmp->cnt) / FM_SCALE;
+        fmp->cnt = 0;
+}
+
+/* Process any previous ticks, then bump cnt by one (times scale). */
+static void fmeter_markevent(struct fmeter *fmp)
+{
+        spin_lock(&fmp->lock);
+        fmeter_update(fmp);
+        fmp->cnt = min(FM_MAXCNT, fmp->cnt + FM_SCALE);
+        spin_unlock(&fmp->lock);
+}
+
+/* Process any previous ticks, then return current value. */
+static int fmeter_getrate(struct fmeter *fmp)
+{
+        int val;
+
+        spin_lock(&fmp->lock);
+        fmeter_update(fmp);
+        val = fmp->val;
+        spin_unlock(&fmp->lock);
+        return val;
+}
+
+/*
  * Attack task specified by pid in 'pidbuf' to cpuset 'cs', possibly
  * writing the path of the old cpuset in 'ppathbuf' if it needs to be
  * notified on release.
@@ -848,6 +1114,8 @@ static int attach_task(struct cpuset *cs, char *pidbuf, char **ppathbuf)
         struct task_struct *tsk;
         struct cpuset *oldcs;
         cpumask_t cpus;
+        nodemask_t from, to;
+        struct mm_struct *mm;
 
         if (sscanf(pidbuf, "%d", &pid) != 1)
                 return -EIO;
@@ -887,14 +1155,27 @@ static int attach_task(struct cpuset *cs, char *pidbuf, char **ppathbuf)
                 return -ESRCH;
         }
         atomic_inc(&cs->count);
-        tsk->cpuset = cs;
+        rcu_assign_pointer(tsk->cpuset, cs);
         task_unlock(tsk);
 
         guarantee_online_cpus(cs, &cpus);
         set_cpus_allowed(tsk, cpus);
 
+        from = oldcs->mems_allowed;
+        to = cs->mems_allowed;
+
         up(&callback_sem);
+
+        mm = get_task_mm(tsk);
+        if (mm) {
+                mpol_rebind_mm(mm, &to);
+                mmput(mm);
+        }
+
+        if (is_memory_migrate(cs))
+                do_migrate_pages(tsk->mm, &from, &to, MPOL_MF_MOVE_ALL);
         put_task_struct(tsk);
+        synchronize_rcu();
         if (atomic_dec_and_test(&oldcs->count))
                 check_for_release(oldcs, ppathbuf);
         return 0;
@@ -905,11 +1186,14 @@ static int attach_task(struct cpuset *cs, char *pidbuf, char **ppathbuf)
 typedef enum {
         FILE_ROOT,
         FILE_DIR,
+        FILE_MEMORY_MIGRATE,
         FILE_CPULIST,
         FILE_MEMLIST,
         FILE_CPU_EXCLUSIVE,
         FILE_MEM_EXCLUSIVE,
         FILE_NOTIFY_ON_RELEASE,
+        FILE_MEMORY_PRESSURE_ENABLED,
+        FILE_MEMORY_PRESSURE,
         FILE_TASKLIST,
 } cpuset_filetype_t;
 
@@ -960,6 +1244,15 @@ static ssize_t cpuset_common_file_write(struct file *file, const char __user *us
         case FILE_NOTIFY_ON_RELEASE:
                 retval = update_flag(CS_NOTIFY_ON_RELEASE, cs, buffer);
                 break;
+        case FILE_MEMORY_MIGRATE:
+                retval = update_flag(CS_MEMORY_MIGRATE, cs, buffer);
+                break;
+        case FILE_MEMORY_PRESSURE_ENABLED:
+                retval = update_memory_pressure_enabled(cs, buffer);
+                break;
+        case FILE_MEMORY_PRESSURE:
+                retval = -EACCES;
+                break;
         case FILE_TASKLIST:
                 retval = attach_task(cs, buffer, &pathbuf);
                 break;
@@ -1060,6 +1353,15 @@ static ssize_t cpuset_common_file_read(struct file *file, char __user *buf,
         case FILE_NOTIFY_ON_RELEASE:
                 *s++ = notify_on_release(cs) ? '1' : '0';
                 break;
+        case FILE_MEMORY_MIGRATE:
+                *s++ = is_memory_migrate(cs) ? '1' : '0';
+                break;
+        case FILE_MEMORY_PRESSURE_ENABLED:
+                *s++ = cpuset_memory_pressure_enabled ? '1' : '0';
+                break;
+        case FILE_MEMORY_PRESSURE:
+                s += sprintf(s, "%d", fmeter_getrate(&cs->fmeter));
+                break;
         default:
                 retval = -EINVAL;
                 goto out;
@@ -1178,7 +1480,7 @@ static int cpuset_create_file(struct dentry *dentry, int mode)
 
 /*
  *      cpuset_create_dir - create a directory for an object.
- *      cs:     the cpuset we create the directory for.
+ *      cs:     the cpuset we create the directory for.
  *              It must have a valid ->parent field
  *              And we are going to fill its ->dentry field.
  *      name:   The name to give to the cpuset directory. Will be copied.
@@ -1408,6 +1710,21 @@ static struct cftype cft_notify_on_release = {
         .private = FILE_NOTIFY_ON_RELEASE,
 };
 
+static struct cftype cft_memory_migrate = {
+        .name = "memory_migrate",
+        .private = FILE_MEMORY_MIGRATE,
+};
+
+static struct cftype cft_memory_pressure_enabled = {
+        .name = "memory_pressure_enabled",
+        .private = FILE_MEMORY_PRESSURE_ENABLED,
+};
+
+static struct cftype cft_memory_pressure = {
+        .name = "memory_pressure",
+        .private = FILE_MEMORY_PRESSURE,
+};
+
 static int cpuset_populate_dir(struct dentry *cs_dentry)
 {
         int err;
@@ -1422,6 +1739,10 @@ static int cpuset_populate_dir(struct dentry *cs_dentry)
                 return err;
         if ((err = cpuset_add_file(cs_dentry, &cft_notify_on_release)) < 0)
                 return err;
+        if ((err = cpuset_add_file(cs_dentry, &cft_memory_migrate)) < 0)
+                return err;
+        if ((err = cpuset_add_file(cs_dentry, &cft_memory_pressure)) < 0)
+                return err;
         if ((err = cpuset_add_file(cs_dentry, &cft_tasks)) < 0)
                 return err;
         return 0;
@@ -1446,7 +1767,7 @@ static long cpuset_create(struct cpuset *parent, const char *name, int mode)
                 return -ENOMEM;
 
         down(&manage_sem);
-        refresh_mems();
+        cpuset_update_task_memory_state();
         cs->flags = 0;
         if (notify_on_release(parent))
                 set_bit(CS_NOTIFY_ON_RELEASE, &cs->flags);
@@ -1457,11 +1778,13 @@ static long cpuset_create(struct cpuset *parent, const char *name, int mode)
         INIT_LIST_HEAD(&cs->children);
         atomic_inc(&cpuset_mems_generation);
         cs->mems_generation = atomic_read(&cpuset_mems_generation);
+        fmeter_init(&cs->fmeter);
 
         cs->parent = parent;
 
         down(&callback_sem);
         list_add(&cs->sibling, &cs->parent->children);
+        number_of_cpusets++;
         up(&callback_sem);
 
         err = cpuset_create_dir(cs, name, mode);
@@ -1503,7 +1826,7 @@ static int cpuset_rmdir(struct inode *unused_dir, struct dentry *dentry)
         /* the vfs holds both inode->i_sem already */
 
         down(&manage_sem);
-        refresh_mems();
+        cpuset_update_task_memory_state();
         if (atomic_read(&cs->count) > 0) {
                 up(&manage_sem);
                 return -EBUSY;
@@ -1524,6 +1847,7 @@ static int cpuset_rmdir(struct inode *unused_dir, struct dentry *dentry)
         spin_unlock(&d->d_lock);
         cpuset_d_remove_dir(d);
         dput(d);
+        number_of_cpusets--;
         up(&callback_sem);
         if (list_empty(&parent->children))
                 check_for_release(parent, &pathbuf);
@@ -1532,6 +1856,21 @@ static int cpuset_rmdir(struct inode *unused_dir, struct dentry *dentry)
         return 0;
 }
 
+/*
+ * cpuset_init_early - just enough so that the calls to
+ * cpuset_update_task_memory_state() in early init code
+ * are harmless.
+ */
+
+int __init cpuset_init_early(void)
+{
+        struct task_struct *tsk = current;
+
+        tsk->cpuset = &top_cpuset;
+        tsk->cpuset->mems_generation = atomic_read(&cpuset_mems_generation);
+        return 0;
+}
+
 /**
  * cpuset_init - initialize cpusets at system boot
  *
@@ -1546,6 +1885,7 @@ int __init cpuset_init(void)
         top_cpuset.cpus_allowed = CPU_MASK_ALL;
         top_cpuset.mems_allowed = NODE_MASK_ALL;
 
+        fmeter_init(&top_cpuset.fmeter);
         atomic_inc(&cpuset_mems_generation);
         top_cpuset.mems_generation = atomic_read(&cpuset_mems_generation);
 
@@ -1566,7 +1906,11 @@ int __init cpuset_init(void)
         root->d_inode->i_nlink++;
         top_cpuset.dentry = root;
         root->d_inode->i_op = &cpuset_dir_inode_operations;
+        number_of_cpusets = 1;
         err = cpuset_populate_dir(root);
+        /* memory_pressure_enabled is in root cpuset only */
+        if (err == 0)
+                err = cpuset_add_file(root, &cft_memory_pressure_enabled);
 out:
         return err;
 }
@@ -1632,15 +1976,13 @@ void cpuset_fork(struct task_struct *child)
  *
  * We don't need to task_lock() this reference to tsk->cpuset,
  * because tsk is already marked PF_EXITING, so attach_task() won't
- * mess with it.
+ * mess with it, or task is a failed fork, never visible to attach_task.
  **/
 
 void cpuset_exit(struct task_struct *tsk)
 {
         struct cpuset *cs;
 
-        BUG_ON(!(tsk->flags & PF_EXITING));
-
         cs = tsk->cpuset;
         tsk->cpuset = NULL;
 
@@ -1667,14 +2009,14 @@ void cpuset_exit(struct task_struct *tsk)
  * tasks cpuset.
  **/
 
-cpumask_t cpuset_cpus_allowed(const struct task_struct *tsk)
+cpumask_t cpuset_cpus_allowed(struct task_struct *tsk)
 {
         cpumask_t mask;
 
         down(&callback_sem);
-        task_lock((struct task_struct *)tsk);
+        task_lock(tsk);
         guarantee_online_cpus(tsk->cpuset, &mask);
-        task_unlock((struct task_struct *)tsk);
+        task_unlock(tsk);
         up(&callback_sem);
 
         return mask;
@@ -1686,43 +2028,26 @@ void cpuset_init_current_mems_allowed(void)
 }
 
 /**
- * cpuset_update_current_mems_allowed - update mems parameters to new values
- *
- * If the current tasks cpusets mems_allowed changed behind our backs,
- * update current->mems_allowed and mems_generation to the new value.
- * Do not call this routine if in_interrupt().
+ * cpuset_mems_allowed - return mems_allowed mask from a tasks cpuset.
+ * @tsk: pointer to task_struct from which to obtain cpuset->mems_allowed.
  *
- * Call without callback_sem or task_lock() held.  May be called
- * with or without manage_sem held.  Unless exiting, it will acquire
- * task_lock().  Also might acquire callback_sem during call to
- * refresh_mems().
- */
+ * Description: Returns the nodemask_t mems_allowed of the cpuset
+ * attached to the specified @tsk.  Guaranteed to return some non-empty
+ * subset of node_online_map, even if this means going outside the
+ * tasks cpuset.
+ **/
 
-void cpuset_update_current_mems_allowed(void)
+nodemask_t cpuset_mems_allowed(struct task_struct *tsk)
 {
-        struct cpuset *cs;
-        int need_to_refresh = 0;
+        nodemask_t mask;
 
-        task_lock(current);
-        cs = current->cpuset;
-        if (!cs)
-                goto done;
-        if (current->cpuset_mems_generation != cs->mems_generation)
-                need_to_refresh = 1;
-done:
-        task_unlock(current);
-        if (need_to_refresh)
-                refresh_mems();
-}
+        down(&callback_sem);
+        task_lock(tsk);
+        guarantee_online_mems(tsk->cpuset, &mask);
+        task_unlock(tsk);
+        up(&callback_sem);
 
-/**
- * cpuset_restrict_to_mems_allowed - limit nodes to current mems_allowed
- * @nodes: pointer to a node bitmap that is and-ed with mems_allowed
- */
-void cpuset_restrict_to_mems_allowed(unsigned long *nodes)
-{
-        bitmap_and(nodes, nodes, nodes_addr(current->mems_allowed),
-                                                        MAX_NUMNODES);
+        return mask;
 }
 
 /**
@@ -1795,7 +2120,7 @@ static const struct cpuset *nearest_exclusive_ancestor(const struct cpuset *cs)
  *      GFP_USER     - only nodes in current tasks mems allowed ok.
  **/
 
-int cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
+int __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
 {
         int node;                       /* node that zone z is on */
         const struct cpuset *cs;        /* current cpuset ancestors */
@@ -1867,6 +2192,42 @@ done:
 }
 
 /*
+ * Collection of memory_pressure is suppressed unless
+ * this flag is enabled by writing "1" to the special
+ * cpuset file 'memory_pressure_enabled' in the root cpuset.
+ */
+
+int cpuset_memory_pressure_enabled __read_mostly;
+
+/**
+ * cpuset_memory_pressure_bump - keep stats of per-cpuset reclaims.
+ *
+ * Keep a running average of the rate of synchronous (direct)
+ * page reclaim efforts initiated by tasks in each cpuset.
+ *
+ * This represents the rate at which some task in the cpuset
+ * ran low on memory on all nodes it was allowed to use, and
+ * had to enter the kernels page reclaim code in an effort to
+ * create more free memory by tossing clean pages or swapping
+ * or writing dirty pages.
+ *
+ * Display to user space in the per-cpuset read-only file
+ * "memory_pressure".  Value displayed is an integer
+ * representing the recent rate of entry into the synchronous
+ * (direct) page reclaim by any task attached to the cpuset.
+ **/
+
+void __cpuset_memory_pressure_bump(void)
+{
+        struct cpuset *cs;
+
+        task_lock(current);
+        cs = current->cpuset;
+        fmeter_markevent(&cs->fmeter);
+        task_unlock(current);
+}
+
+/*
  * proc_cpuset_show()
  *  - Print tasks cpuset path into seq_file.
  *  - Used for /proc/<pid>/cpuset.
diff --git a/kernel/exit.c b/kernel/exit.c
index ee515683b92d..caceabf3f230 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -72,7 +72,6 @@ repeat:
                 __ptrace_unlink(p);
         BUG_ON(!list_empty(&p->ptrace_list) || !list_empty(&p->ptrace_children));
         __exit_signal(p);
-        __exit_sighand(p);
         /*
          * Note that the fastpath in sys_times depends on __exit_signal having
          * updated the counters before a task is removed from the tasklist of
@@ -258,7 +257,7 @@ static inline void reparent_to_init(void)
 
 void __set_special_pids(pid_t session, pid_t pgrp)
 {
-        struct task_struct *curr = current;
+        struct task_struct *curr = current->group_leader;
 
         if (curr->signal->session != session) {
                 detach_pid(curr, PIDTYPE_SID);
@@ -926,7 +925,6 @@ do_group_exit(int exit_code)
                         /* Another thread got here before we took the lock.  */
                         exit_code = sig->group_exit_code;
                 else {
-                        sig->flags = SIGNAL_GROUP_EXIT;
                         sig->group_exit_code = exit_code;
                         zap_other_threads(current);
                 }
diff --git a/kernel/fork.c b/kernel/fork.c
index fb8572a42297..72e3252c6763 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -743,6 +743,14 @@ int unshare_files(void)
 
 EXPORT_SYMBOL(unshare_files);
 
+void sighand_free_cb(struct rcu_head *rhp)
+{
+        struct sighand_struct *sp;
+
+        sp = container_of(rhp, struct sighand_struct, rcu);
+        kmem_cache_free(sighand_cachep, sp);
+}
+
 static inline int copy_sighand(unsigned long clone_flags, struct task_struct * tsk)
 {
         struct sighand_struct *sig;
@@ -752,7 +760,7 @@ static inline int copy_sighand(unsigned long clone_flags, struct task_struct * t
                 return 0;
         }
         sig = kmem_cache_alloc(sighand_cachep, GFP_KERNEL);
-        tsk->sighand = sig;
+        rcu_assign_pointer(tsk->sighand, sig);
         if (!sig)
                 return -ENOMEM;
         spin_lock_init(&sig->siglock);
@@ -803,9 +811,6 @@ static inline int copy_signal(unsigned long clone_flags, struct task_struct * ts
         sig->it_prof_expires = cputime_zero;
         sig->it_prof_incr = cputime_zero;
 
-        sig->tty = current->signal->tty;
-        sig->pgrp = process_group(current);
-        sig->session = current->signal->session;
         sig->leader = 0;        /* session leadership doesn't inherit */
         sig->tty_old_pgrp = 0;
 
@@ -964,12 +969,13 @@ static task_t *copy_process(unsigned long clone_flags,
         p->io_context = NULL;
         p->io_wait = NULL;
         p->audit_context = NULL;
+        cpuset_fork(p);
 #ifdef CONFIG_NUMA
         p->mempolicy = mpol_copy(p->mempolicy);
         if (IS_ERR(p->mempolicy)) {
                 retval = PTR_ERR(p->mempolicy);
                 p->mempolicy = NULL;
-                goto bad_fork_cleanup;
+                goto bad_fork_cleanup_cpuset;
         }
 #endif
 
@@ -1127,25 +1133,19 @@ static task_t *copy_process(unsigned long clone_flags,
         attach_pid(p, PIDTYPE_PID, p->pid);
         attach_pid(p, PIDTYPE_TGID, p->tgid);
         if (thread_group_leader(p)) {
+                p->signal->tty = current->signal->tty;
+                p->signal->pgrp = process_group(current);
+                p->signal->session = current->signal->session;
                 attach_pid(p, PIDTYPE_PGID, process_group(p));
                 attach_pid(p, PIDTYPE_SID, p->signal->session);
                 if (p->pid)
                         __get_cpu_var(process_counts)++;
         }
 
-        if (!current->signal->tty && p->signal->tty)
-                p->signal->tty = NULL;
-
         nr_threads++;
         total_forks++;
         write_unlock_irq(&tasklist_lock);
         proc_fork_connector(p);
-        cpuset_fork(p);
-        retval = 0;
-
-fork_out:
-        if (retval)
-                return ERR_PTR(retval);
         return p;
 
 bad_fork_cleanup_namespace:
@@ -1172,7 +1172,9 @@ bad_fork_cleanup_security:
 bad_fork_cleanup_policy:
 #ifdef CONFIG_NUMA
         mpol_free(p->mempolicy);
+bad_fork_cleanup_cpuset:
 #endif
+        cpuset_exit(p);
 bad_fork_cleanup:
         if (p->binfmt)
                 module_put(p->binfmt->module);
@@ -1184,7 +1186,8 @@ bad_fork_cleanup_count:
         free_uid(p->user);
 bad_fork_free:
         free_task(p);
-        goto fork_out;
+fork_out:
+        return ERR_PTR(retval);
 }
 
 struct pt_regs * __devinit __attribute__((weak)) idle_regs(struct pt_regs *regs)
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 8a64a4844cde..d03b5eef8ce0 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -10,6 +10,8 @@
 #include <linux/proc_fs.h>
 #include <linux/interrupt.h>
 
+#include "internals.h"
+
 static struct proc_dir_entry *root_irq_dir, *irq_dir[NR_IRQS];
 
 #ifdef CONFIG_SMP
diff --git a/kernel/module.c b/kernel/module.c
index 4b06bbad49c2..e4276046a1b6 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -496,15 +496,15 @@ static void module_unload_free(struct module *mod)
 }
 
 #ifdef CONFIG_MODULE_FORCE_UNLOAD
-static inline int try_force(unsigned int flags)
+static inline int try_force_unload(unsigned int flags)
 {
         int ret = (flags & O_TRUNC);
         if (ret)
-                add_taint(TAINT_FORCED_MODULE);
+                add_taint(TAINT_FORCED_RMMOD);
         return ret;
 }
 #else
-static inline int try_force(unsigned int flags)
+static inline int try_force_unload(unsigned int flags)
 {
         return 0;
 }
@@ -524,7 +524,7 @@ static int __try_stop_module(void *_sref)
 
         /* If it's not unused, quit unless we are told to block. */
         if ((sref->flags & O_NONBLOCK) && module_refcount(sref->mod) != 0) {
-                if (!(*sref->forced = try_force(sref->flags)))
+                if (!(*sref->forced = try_force_unload(sref->flags)))
                         return -EWOULDBLOCK;
         }
 
@@ -609,7 +609,7 @@ sys_delete_module(const char __user *name_user, unsigned int flags)
         /* If it has an init func, it must have an exit func to unload */
         if ((mod->init != NULL && mod->exit == NULL)
             || mod->unsafe) {
-                forced = try_force(flags);
+                forced = try_force_unload(flags);
                 if (!forced) {
                         /* This module can't be removed */
                         ret = -EBUSY;
@@ -958,7 +958,6 @@ static unsigned long resolve_symbol(Elf_Shdr *sechdrs,
         unsigned long ret;
         const unsigned long *crc;
 
-        spin_lock_irq(&modlist_lock);
         ret = __find_symbol(name, &owner, &crc, mod->license_gplok);
         if (ret) {
                 /* use_module can fail due to OOM, or module unloading */
@@ -966,7 +965,6 @@ static unsigned long resolve_symbol(Elf_Shdr *sechdrs,
                     !use_module(mod, owner))
                         ret = 0;
         }
-        spin_unlock_irq(&modlist_lock);
         return ret;
 }
 
@@ -1204,6 +1202,39 @@ void *__symbol_get(const char *symbol)
 }
 EXPORT_SYMBOL_GPL(__symbol_get);
 
+/*
+ * Ensure that an exported symbol [global namespace] does not already exist
+ * in the Kernel or in some other modules exported symbol table.
+ */
+static int verify_export_symbols(struct module *mod)
+{
+        const char *name = NULL;
+        unsigned long i, ret = 0;
+        struct module *owner;
+        const unsigned long *crc;
+
+        for (i = 0; i < mod->num_syms; i++)
+                if (__find_symbol(mod->syms[i].name, &owner, &crc, 1)) {
+                        name = mod->syms[i].name;
+                        ret = -ENOEXEC;
+                        goto dup;
+                }
+
+        for (i = 0; i < mod->num_gpl_syms; i++)
+                if (__find_symbol(mod->gpl_syms[i].name, &owner, &crc, 1)) {
+                        name = mod->gpl_syms[i].name;
+                        ret = -ENOEXEC;
+                        goto dup;
+                }
+
+dup:
+        if (ret)
+                printk(KERN_ERR "%s: exports duplicate symbol %s (owned by %s)\n",
+                        mod->name, name, module_name(owner));
+
+        return ret;
+}
+
 /* Change all symbols so that sh_value encodes the pointer directly. */
 static int simplify_symbols(Elf_Shdr *sechdrs,
                             unsigned int symindex,
@@ -1715,6 +1746,11 @@ static struct module *load_module(void __user *umod,
         /* Set up license info based on the info section */
         set_license(mod, get_modinfo(sechdrs, infoindex, "license"));
 
+        if (strcmp(mod->name, "ndiswrapper") == 0)
+                add_taint(TAINT_PROPRIETARY_MODULE);
+        if (strcmp(mod->name, "driverloader") == 0)
+                add_taint(TAINT_PROPRIETARY_MODULE);
+
 #ifdef CONFIG_MODULE_UNLOAD
         /* Set up MODINFO_ATTR fields */
         setup_modinfo(mod, sechdrs, infoindex);
@@ -1767,6 +1803,12 @@ static struct module *load_module(void __user *umod,
                         goto cleanup;
         }
 
+        /* Find duplicate symbols */
+        err = verify_export_symbols(mod);
+
+        if (err < 0)
+                goto cleanup;
+
         /* Set up and sort exception table */
         mod->num_exentries = sechdrs[exindex].sh_size / sizeof(*mod->extable);
         mod->extable = extable = (void *)sechdrs[exindex].sh_addr;
diff --git a/kernel/pid.c b/kernel/pid.c
index edba31c681ac..1acc07246991 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -136,7 +136,7 @@ struct pid * fastcall find_pid(enum pid_type type, int nr)
         struct hlist_node *elem;
         struct pid *pid;
 
-        hlist_for_each_entry(pid, elem,
+        hlist_for_each_entry_rcu(pid, elem,
                         &pid_hash[type][pid_hashfn(nr)], pid_chain) {
                 if (pid->nr == nr)
                         return pid;
@@ -150,15 +150,15 @@ int fastcall attach_pid(task_t *task, enum pid_type type, int nr)
 
         task_pid = &task->pids[type];
         pid = find_pid(type, nr);
+        task_pid->nr = nr;
         if (pid == NULL) {
-                hlist_add_head(&task_pid->pid_chain,
-                                &pid_hash[type][pid_hashfn(nr)]);
                 INIT_LIST_HEAD(&task_pid->pid_list);
+                hlist_add_head_rcu(&task_pid->pid_chain,
+                                   &pid_hash[type][pid_hashfn(nr)]);
         } else {
                 INIT_HLIST_NODE(&task_pid->pid_chain);
-                list_add_tail(&task_pid->pid_list, &pid->pid_list);
+                list_add_tail_rcu(&task_pid->pid_list, &pid->pid_list);
         }
-        task_pid->nr = nr;
 
         return 0;
 }
@@ -170,20 +170,20 @@ static fastcall int __detach_pid(task_t *task, enum pid_type type)
 
         pid = &task->pids[type];
         if (!hlist_unhashed(&pid->pid_chain)) {
-                hlist_del(&pid->pid_chain);
 
-                if (list_empty(&pid->pid_list))
+                if (list_empty(&pid->pid_list)) {
                         nr = pid->nr;
-                else {
+                        hlist_del_rcu(&pid->pid_chain);
+                } else {
                         pid_next = list_entry(pid->pid_list.next,
                                                 struct pid, pid_list);
                         /* insert next pid from pid_list to hash */
-                        hlist_add_head(&pid_next->pid_chain,
-                                &pid_hash[type][pid_hashfn(pid_next->nr)]);
+                        hlist_replace_rcu(&pid->pid_chain,
+                                          &pid_next->pid_chain);
                 }
         }
 
-        list_del(&pid->pid_list);
+        list_del_rcu(&pid->pid_list);
         pid->nr = 0;
 
         return nr;
diff --git a/kernel/printk.c b/kernel/printk.c
index 5287be83e3e7..2251be80cd22 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -569,7 +569,7 @@ asmlinkage int vprintk(const char *fmt, va_list args)
                                    p[1] <= '7' && p[2] == '>') {
                                         loglev_char = p[1];
                                         p += 3;
-                                        printed_len += 3;
+                                        printed_len -= 3;
                                 } else {
                                         loglev_char = default_message_loglevel
                                                 + '0';
@@ -584,7 +584,7 @@ asmlinkage int vprintk(const char *fmt, va_list args)
 
                                 for (tp = tbuf; tp < tbuf + tlen; tp++)
                                         emit_log_char(*tp);
-                                printed_len += tlen - 3;
+                                printed_len += tlen;
                         } else {
                                 if (p[0] != '<' || p[1] < '0' ||
                                    p[1] > '7' || p[2] != '>') {
@@ -592,8 +592,8 @@ asmlinkage int vprintk(const char *fmt, va_list args)
                                         emit_log_char(default_message_loglevel
                                                 + '0');
                                         emit_log_char('>');
+                                        printed_len += 3;
                                 }
-                                printed_len += 3;
                         }
                         log_level_unknown = 0;
                         if (!*p)
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 656476eedb1b..cceaf09ac413 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -408,54 +408,62 @@ int ptrace_request(struct task_struct *child, long request,
         return ret;
 }
 
-#ifndef __ARCH_SYS_PTRACE
-static int ptrace_get_task_struct(long request, long pid,
-                struct task_struct **childp)
+/**
+ * ptrace_traceme  --  helper for PTRACE_TRACEME
+ *
+ * Performs checks and sets PT_PTRACED.
+ * Should be used by all ptrace implementations for PTRACE_TRACEME.
+ */
+int ptrace_traceme(void)
 {
-        struct task_struct *child;
         int ret;
 
         /*
-         * Callers use child == NULL as an indication to exit early even
-         * when the return value is 0, so make sure it is non-NULL here.
+         * Are we already being traced?
+         */
+        if (current->ptrace & PT_PTRACED)
+                return -EPERM;
+        ret = security_ptrace(current->parent, current);
+        if (ret)
+                return -EPERM;
+        /*
+         * Set the ptrace bit in the process ptrace flags.
          */
-        *childp = NULL;
+        current->ptrace |= PT_PTRACED;
+        return 0;
+}
 
-        if (request == PTRACE_TRACEME) {
-                /*
-                 * Are we already being traced?
-                 */
-                if (current->ptrace & PT_PTRACED)
-                        return -EPERM;
-                ret = security_ptrace(current->parent, current);
-                if (ret)
-                        return -EPERM;
-                /*
-                 * Set the ptrace bit in the process ptrace flags.
-                 */
-                current->ptrace |= PT_PTRACED;
-                return 0;
-        }
+/**
+ * ptrace_get_task_struct  --  grab a task struct reference for ptrace
+ * @pid:       process id to grab a task_struct reference of
+ *
+ * This function is a helper for ptrace implementations.  It checks
+ * permissions and then grabs a task struct for use of the actual
+ * ptrace implementation.
+ *
+ * Returns the task_struct for @pid or an ERR_PTR() on failure.
+ */
+struct task_struct *ptrace_get_task_struct(pid_t pid)
+{
+        struct task_struct *child;
 
         /*
-         * You may not mess with init
+         * Tracing init is not allowed.
          */
         if (pid == 1)
-                return -EPERM;
+                return ERR_PTR(-EPERM);
 
-        ret = -ESRCH;
         read_lock(&tasklist_lock);
         child = find_task_by_pid(pid);
         if (child)
                 get_task_struct(child);
         read_unlock(&tasklist_lock);
         if (!child)
-                return -ESRCH;
-
-        *childp = child;
-        return 0;
+                return ERR_PTR(-ESRCH);
+        return child;
 }
 
+#ifndef __ARCH_SYS_PTRACE
 asmlinkage long sys_ptrace(long request, long pid, long addr, long data)
 {
         struct task_struct *child;
@@ -465,9 +473,16 @@ asmlinkage long sys_ptrace(long request, long pid, long addr, long data)
          * This lock_kernel fixes a subtle race with suid exec
          */
         lock_kernel();
-        ret = ptrace_get_task_struct(request, pid, &child);
-        if (!child)
+        if (request == PTRACE_TRACEME) {
+                ret = ptrace_traceme();
                 goto out;
+        }
+
+        child = ptrace_get_task_struct(pid);
+        if (IS_ERR(child)) {
+                ret = PTR_ERR(child);
+                goto out;
+        }
 
         if (request == PTRACE_ATTACH) {
                 ret = ptrace_attach(child);
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index 48d3bce465b8..ccc45d49ce71 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -35,6 +35,7 @@
 #include <linux/init.h>
 #include <linux/spinlock.h>
 #include <linux/smp.h>
+#include <linux/rcupdate.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
 #include <asm/atomic.h>
@@ -45,7 +46,6 @@
 #include <linux/percpu.h>
 #include <linux/notifier.h>
 #include <linux/rcupdate.h>
-#include <linux/rcuref.h>
 #include <linux/cpu.h>
 
 /* Definition for rcupdate control block. */
@@ -61,9 +61,9 @@ struct rcu_state {
                                       /* for current batch to proceed.        */
 };
 
-static struct rcu_state rcu_state ____cacheline_maxaligned_in_smp =
+static struct rcu_state rcu_state ____cacheline_internodealigned_in_smp =
           {.lock = SPIN_LOCK_UNLOCKED, .cpumask = CPU_MASK_NONE };
-static struct rcu_state rcu_bh_state ____cacheline_maxaligned_in_smp =
+static struct rcu_state rcu_bh_state ____cacheline_internodealigned_in_smp =
           {.lock = SPIN_LOCK_UNLOCKED, .cpumask = CPU_MASK_NONE };
 
 DEFINE_PER_CPU(struct rcu_data, rcu_data) = { 0L };
@@ -73,19 +73,6 @@ DEFINE_PER_CPU(struct rcu_data, rcu_bh_data) = { 0L };
 static DEFINE_PER_CPU(struct tasklet_struct, rcu_tasklet) = {NULL};
 static int maxbatch = 10000;
 
-#ifndef __HAVE_ARCH_CMPXCHG
-/*
- * We use an array of spinlocks for the rcurefs -- similar to ones in sparc
- * 32 bit atomic_t implementations, and a hash function similar to that
- * for our refcounting needs.
- * Can't help multiprocessors which donot have cmpxchg :(
- */
-
-spinlock_t __rcuref_hash[RCUREF_HASH_SIZE] = {
-        [0 ... (RCUREF_HASH_SIZE-1)] = SPIN_LOCK_UNLOCKED
-};
-#endif
-
 /**
  * call_rcu - Queue an RCU callback for invocation after a grace period.
  * @head: structure to be used for queueing the RCU updates.
@@ -442,6 +429,36 @@ static void rcu_process_callbacks(unsigned long unused)
                                 &__get_cpu_var(rcu_bh_data));
 }
 
+static int __rcu_pending(struct rcu_ctrlblk *rcp, struct rcu_data *rdp)
+{
+        /* This cpu has pending rcu entries and the grace period
+         * for them has completed.
+         */
+        if (rdp->curlist && !rcu_batch_before(rcp->completed, rdp->batch))
+                return 1;
+
+        /* This cpu has no pending entries, but there are new entries */
+        if (!rdp->curlist && rdp->nxtlist)
+                return 1;
+
+        /* This cpu has finished callbacks to invoke */
+        if (rdp->donelist)
+                return 1;
+
+        /* The rcu core waits for a quiescent state from the cpu */
+        if (rdp->quiescbatch != rcp->cur || rdp->qs_pending)
+                return 1;
+
+        /* nothing to do */
+        return 0;
+}
+
+int rcu_pending(int cpu)
+{
+        return __rcu_pending(&rcu_ctrlblk, &per_cpu(rcu_data, cpu)) ||
+                __rcu_pending(&rcu_bh_ctrlblk, &per_cpu(rcu_bh_data, cpu));
+}
+
 void rcu_check_callbacks(int cpu, int user)
 {
         if (user || 
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 49fbbeff201c..773219907dd8 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -39,7 +39,6 @@
 #include <linux/moduleparam.h>
 #include <linux/percpu.h>
 #include <linux/notifier.h>
-#include <linux/rcuref.h>
 #include <linux/cpu.h>
 #include <linux/random.h>
 #include <linux/delay.h>
@@ -49,9 +48,11 @@
 MODULE_LICENSE("GPL");
 
 static int nreaders = -1;       /* # reader threads, defaults to 4*ncpus */
-static int stat_interval = 0;   /* Interval between stats, in seconds. */
+static int stat_interval;       /* Interval between stats, in seconds. */
                                 /*  Defaults to "only at end of test". */
-static int verbose = 0;         /* Print more debug info. */
+static int verbose;             /* Print more debug info. */
+static int test_no_idle_hz;     /* Test RCU's support for tickless idle CPUs. */
+static int shuffle_interval = 5; /* Interval between shuffles (in sec)*/
 
 MODULE_PARM(nreaders, "i");
 MODULE_PARM_DESC(nreaders, "Number of RCU reader threads");
@@ -59,6 +60,10 @@ MODULE_PARM(stat_interval, "i");
 MODULE_PARM_DESC(stat_interval, "Number of seconds between stats printk()s");
 MODULE_PARM(verbose, "i");
 MODULE_PARM_DESC(verbose, "Enable verbose debugging printk()s");
+MODULE_PARM(test_no_idle_hz, "i");
+MODULE_PARM_DESC(test_no_idle_hz, "Test support for tickless idle CPUs");
+MODULE_PARM(shuffle_interval, "i");
+MODULE_PARM_DESC(shuffle_interval, "Number of seconds between shuffles");
 #define TORTURE_FLAG "rcutorture: "
 #define PRINTK_STRING(s) \
         do { printk(KERN_ALERT TORTURE_FLAG s "\n"); } while (0)
@@ -73,6 +78,7 @@ static int nrealreaders;
 static struct task_struct *writer_task;
 static struct task_struct **reader_tasks;
 static struct task_struct *stats_task;
+static struct task_struct *shuffler_task;
 
 #define RCU_TORTURE_PIPE_LEN 10
 
@@ -103,7 +109,7 @@ atomic_t n_rcu_torture_error;
 /*
  * Allocate an element from the rcu_tortures pool.
  */
-struct rcu_torture *
+static struct rcu_torture *
 rcu_torture_alloc(void)
 {
         struct list_head *p;
@@ -376,12 +382,77 @@ rcu_torture_stats(void *arg)
         return 0;
 }
 
+static int rcu_idle_cpu;        /* Force all torture tasks off this CPU */
+
+/* Shuffle tasks such that we allow @rcu_idle_cpu to become idle. A special case
+ * is when @rcu_idle_cpu = -1, when we allow the tasks to run on all CPUs.
+ */
+void rcu_torture_shuffle_tasks(void)
+{
+        cpumask_t tmp_mask = CPU_MASK_ALL;
+        int i;
+
+        lock_cpu_hotplug();
+
+        /* No point in shuffling if there is only one online CPU (ex: UP) */
+        if (num_online_cpus() == 1) {
+                unlock_cpu_hotplug();
+                return;
+        }
+
+        if (rcu_idle_cpu != -1)
+                cpu_clear(rcu_idle_cpu, tmp_mask);
+
+        set_cpus_allowed(current, tmp_mask);
+
+        if (reader_tasks != NULL) {
+                for (i = 0; i < nrealreaders; i++)
+                        if (reader_tasks[i])
+                                set_cpus_allowed(reader_tasks[i], tmp_mask);
+        }
+
+        if (writer_task)
+                set_cpus_allowed(writer_task, tmp_mask);
+
+        if (stats_task)
+                set_cpus_allowed(stats_task, tmp_mask);
+
+        if (rcu_idle_cpu == -1)
+                rcu_idle_cpu = num_online_cpus() - 1;
+        else
+                rcu_idle_cpu--;
+
+        unlock_cpu_hotplug();
+}
+
+/* Shuffle tasks across CPUs, with the intent of allowing each CPU in the
+ * system to become idle at a time and cut off its timer ticks. This is meant
+ * to test the support for such tickless idle CPU in RCU.
+ */
+static int
+rcu_torture_shuffle(void *arg)
+{
+        VERBOSE_PRINTK_STRING("rcu_torture_shuffle task started");
+        do {
+                schedule_timeout_interruptible(shuffle_interval * HZ);
+                rcu_torture_shuffle_tasks();
+        } while (!kthread_should_stop());
+        VERBOSE_PRINTK_STRING("rcu_torture_shuffle task stopping");
+        return 0;
+}
+
 static void
 rcu_torture_cleanup(void)
 {
         int i;
 
         fullstop = 1;
+        if (shuffler_task != NULL) {
+                VERBOSE_PRINTK_STRING("Stopping rcu_torture_shuffle task");
+                kthread_stop(shuffler_task);
+        }
+        shuffler_task = NULL;
+
         if (writer_task != NULL) {
                 VERBOSE_PRINTK_STRING("Stopping rcu_torture_writer task");
                 kthread_stop(writer_task);
@@ -430,9 +501,11 @@ rcu_torture_init(void)
                 nrealreaders = nreaders;
         else
                 nrealreaders = 2 * num_online_cpus();
-        printk(KERN_ALERT TORTURE_FLAG
-               "--- Start of test: nreaders=%d stat_interval=%d verbose=%d\n",
-               nrealreaders, stat_interval, verbose);
+        printk(KERN_ALERT TORTURE_FLAG "--- Start of test: nreaders=%d "
+                "stat_interval=%d verbose=%d test_no_idle_hz=%d "
+                "shuffle_interval = %d\n",
+                nrealreaders, stat_interval, verbose, test_no_idle_hz,
+                shuffle_interval);
         fullstop = 0;
 
         /* Set up the freelist. */
@@ -502,6 +575,18 @@ rcu_torture_init(void)
                         goto unwind;
                 }
         }
+        if (test_no_idle_hz) {
+                rcu_idle_cpu = num_online_cpus() - 1;
+                /* Create the shuffler thread */
+                shuffler_task = kthread_run(rcu_torture_shuffle, NULL,
+                                          "rcu_torture_shuffle");
+                if (IS_ERR(shuffler_task)) {
+                        firsterr = PTR_ERR(shuffler_task);
+                        VERBOSE_PRINTK_ERRSTRING("Failed to create shuffler");
+                        shuffler_task = NULL;
+                        goto unwind;
+                }
+        }
         return 0;
 
 unwind:
diff --git a/kernel/sched.c b/kernel/sched.c
index 6f46c94cc29e..92733091154c 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -176,6 +176,13 @@ static unsigned int task_timeslice(task_t *p)
 #define task_hot(p, now, sd) ((long long) ((now) - (p)->last_ran)       \
                                 < (long long) (sd)->cache_hot_time)
 
+void __put_task_struct_cb(struct rcu_head *rhp)
+{
+        __put_task_struct(container_of(rhp, struct task_struct, rcu));
+}
+
+EXPORT_SYMBOL_GPL(__put_task_struct_cb);
+
 /*
  * These are the runqueue data structures:
  */
diff --git a/kernel/signal.c b/kernel/signal.c
index d7611f189ef7..08aa5b263f36 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -329,13 +329,20 @@ void __exit_sighand(struct task_struct *tsk)
         /* Ok, we're done with the signal handlers */
         tsk->sighand = NULL;
         if (atomic_dec_and_test(&sighand->count))
-                kmem_cache_free(sighand_cachep, sighand);
+                sighand_free(sighand);
 }
 
 void exit_sighand(struct task_struct *tsk)
 {
         write_lock_irq(&tasklist_lock);
-        __exit_sighand(tsk);
+        rcu_read_lock();
+        if (tsk->sighand != NULL) {
+                struct sighand_struct *sighand = rcu_dereference(tsk->sighand);
+                spin_lock(&sighand->siglock);
+                __exit_sighand(tsk);
+                spin_unlock(&sighand->siglock);
+        }
+        rcu_read_unlock();
         write_unlock_irq(&tasklist_lock);
 }
 
@@ -345,19 +352,20 @@ void exit_sighand(struct task_struct *tsk)
 void __exit_signal(struct task_struct *tsk)
 {
         struct signal_struct * sig = tsk->signal;
-        struct sighand_struct * sighand = tsk->sighand;
+        struct sighand_struct * sighand;
 
         if (!sig)
                 BUG();
         if (!atomic_read(&sig->count))
                 BUG();
+        rcu_read_lock();
+        sighand = rcu_dereference(tsk->sighand);
         spin_lock(&sighand->siglock);
         posix_cpu_timers_exit(tsk);
         if (atomic_dec_and_test(&sig->count)) {
                 posix_cpu_timers_exit_group(tsk);
-                if (tsk == sig->curr_target)
-                        sig->curr_target = next_thread(tsk);
                 tsk->signal = NULL;
+                __exit_sighand(tsk);
                 spin_unlock(&sighand->siglock);
                 flush_sigqueue(&sig->shared_pending);
         } else {
@@ -389,9 +397,11 @@ void __exit_signal(struct task_struct *tsk)
                 sig->nvcsw += tsk->nvcsw;
                 sig->nivcsw += tsk->nivcsw;
                 sig->sched_time += tsk->sched_time;
+                __exit_sighand(tsk);
                 spin_unlock(&sighand->siglock);
                 sig = NULL;     /* Marker for below.  */
         }
+        rcu_read_unlock();
         clear_tsk_thread_flag(tsk,TIF_SIGPENDING);
         flush_sigqueue(&tsk->pending);
         if (sig) {
@@ -613,6 +623,33 @@ void signal_wake_up(struct task_struct *t, int resume)
  * Returns 1 if any signals were found.
  *
  * All callers must be holding the siglock.
+ *
+ * This version takes a sigset mask and looks at all signals,
+ * not just those in the first mask word.
+ */
+static int rm_from_queue_full(sigset_t *mask, struct sigpending *s)
+{
+        struct sigqueue *q, *n;
+        sigset_t m;
+
+        sigandsets(&m, mask, &s->signal);
+        if (sigisemptyset(&m))
+                return 0;
+
+        signandsets(&s->signal, &s->signal, mask);
+        list_for_each_entry_safe(q, n, &s->list, list) {
+                if (sigismember(mask, q->info.si_signo)) {
+                        list_del_init(&q->list);
+                        __sigqueue_free(q);
+                }
+        }
+        return 1;
+}
+/*
+ * Remove signals in mask from the pending set and queue.
+ * Returns 1 if any signals were found.
+ *
+ * All callers must be holding the siglock.
  */
 static int rm_from_queue(unsigned long mask, struct sigpending *s)
 {
@@ -1080,18 +1117,29 @@ void zap_other_threads(struct task_struct *p)
 }
 
 /*
- * Must be called with the tasklist_lock held for reading!
+ * Must be called under rcu_read_lock() or with tasklist_lock read-held.
  */
 int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
 {
         unsigned long flags;
+        struct sighand_struct *sp;
         int ret;
 
+retry:
         ret = check_kill_permission(sig, info, p);
-        if (!ret && sig && p->sighand) {
-                spin_lock_irqsave(&p->sighand->siglock, flags);
+        if (!ret && sig && (sp = rcu_dereference(p->sighand))) {
+                spin_lock_irqsave(&sp->siglock, flags);
+                if (p->sighand != sp) {
+                        spin_unlock_irqrestore(&sp->siglock, flags);
+                        goto retry;
+                }
+                if ((atomic_read(&sp->count) == 0) ||
+                                (atomic_read(&p->usage) == 0)) {
+                        spin_unlock_irqrestore(&sp->siglock, flags);
+                        return -ESRCH;
+                }
                 ret = __group_send_sig_info(sig, info, p);
-                spin_unlock_irqrestore(&p->sighand->siglock, flags);
+                spin_unlock_irqrestore(&sp->siglock, flags);
         }
 
         return ret;
@@ -1136,14 +1184,21 @@ int
 kill_proc_info(int sig, struct siginfo *info, pid_t pid)
 {
         int error;
+        int acquired_tasklist_lock = 0;
         struct task_struct *p;
 
-        read_lock(&tasklist_lock);
+        rcu_read_lock();
+        if (unlikely(sig_kernel_stop(sig) || sig == SIGCONT)) {
+                read_lock(&tasklist_lock);
+                acquired_tasklist_lock = 1;
+        }
         p = find_task_by_pid(pid);
         error = -ESRCH;
         if (p)
                 error = group_send_sig_info(sig, info, p);
-        read_unlock(&tasklist_lock);
+        if (unlikely(acquired_tasklist_lock))
+                read_unlock(&tasklist_lock);
+        rcu_read_unlock();
         return error;
 }
 
@@ -1163,8 +1218,7 @@ int kill_proc_info_as_uid(int sig, struct siginfo *info, pid_t pid,
                 ret = -ESRCH;
                 goto out_unlock;
         }
-        if ((!info || ((unsigned long)info != 1 &&
-                        (unsigned long)info != 2 && SI_FROMUSER(info)))
+        if ((info == SEND_SIG_NOINFO || (!is_si_special(info) && SI_FROMUSER(info)))
             && (euid != p->suid) && (euid != p->uid)
             && (uid != p->suid) && (uid != p->uid)) {
                 ret = -EPERM;
@@ -1355,16 +1409,54 @@ send_sigqueue(int sig, struct sigqueue *q, struct task_struct *p)
 {
         unsigned long flags;
         int ret = 0;
+        struct sighand_struct *sh;
 
         BUG_ON(!(q->flags & SIGQUEUE_PREALLOC));
-        read_lock(&tasklist_lock);
+
+        /*
+         * The rcu based delayed sighand destroy makes it possible to
+         * run this without tasklist lock held. The task struct itself
+         * cannot go away as create_timer did get_task_struct().
+         *
+         * We return -1, when the task is marked exiting, so
+         * posix_timer_event can redirect it to the group leader
+         */
+        rcu_read_lock();
 
         if (unlikely(p->flags & PF_EXITING)) {
                 ret = -1;
                 goto out_err;
         }
 
-        spin_lock_irqsave(&p->sighand->siglock, flags);
+retry:
+        sh = rcu_dereference(p->sighand);
+
+        spin_lock_irqsave(&sh->siglock, flags);
+        if (p->sighand != sh) {
+                /* We raced with exec() in a multithreaded process... */
+                spin_unlock_irqrestore(&sh->siglock, flags);
+                goto retry;
+        }
+
+        /*
+         * We do the check here again to handle the following scenario:
+         *
+         * CPU 0                CPU 1
+         * send_sigqueue
+         * check PF_EXITING
+         * interrupt            exit code running
+         *                      __exit_signal
+         *                      lock sighand->siglock
+         *                      unlock sighand->siglock
+         * lock sh->siglock
+         * add(tsk->pending)    flush_sigqueue(tsk->pending)
+         *
+         */
+
+        if (unlikely(p->flags & PF_EXITING)) {
+                ret = -1;
+                goto out;
+        }
 
         if (unlikely(!list_empty(&q->list))) {
                 /*
@@ -1388,9 +1480,9 @@ send_sigqueue(int sig, struct sigqueue *q, struct task_struct *p)
                 signal_wake_up(p, sig == SIGKILL);
 
 out:
-        spin_unlock_irqrestore(&p->sighand->siglock, flags);
+        spin_unlock_irqrestore(&sh->siglock, flags);
 out_err:
-        read_unlock(&tasklist_lock);
+        rcu_read_unlock();
 
         return ret;
 }
@@ -1402,7 +1494,9 @@ send_group_sigqueue(int sig, struct sigqueue *q, struct task_struct *p)
         int ret = 0;
 
         BUG_ON(!(q->flags & SIGQUEUE_PREALLOC));
+
         read_lock(&tasklist_lock);
+        /* Since it_lock is held, p->sighand cannot be NULL. */
         spin_lock_irqsave(&p->sighand->siglock, flags);
         handle_stop_signal(sig, p);
 
@@ -1436,7 +1530,7 @@ send_group_sigqueue(int sig, struct sigqueue *q, struct task_struct *p)
 out:
         spin_unlock_irqrestore(&p->sighand->siglock, flags);
         read_unlock(&tasklist_lock);
-        return(ret);
+        return ret;
 }
 
 /*
@@ -2338,6 +2432,7 @@ int
 do_sigaction(int sig, const struct k_sigaction *act, struct k_sigaction *oact)
 {
         struct k_sigaction *k;
+        sigset_t mask;
 
         if (!valid_signal(sig) || sig < 1 || (act && sig_kernel_only(sig)))
                 return -EINVAL;
@@ -2385,9 +2480,11 @@ do_sigaction(int sig, const struct k_sigaction *act, struct k_sigaction *oact)
                         *k = *act;
                         sigdelsetmask(&k->sa.sa_mask,
                                       sigmask(SIGKILL) | sigmask(SIGSTOP));
-                        rm_from_queue(sigmask(sig), &t->signal->shared_pending);
+                        sigemptyset(&mask);
+                        sigaddset(&mask, sig);
+                        rm_from_queue_full(&mask, &t->signal->shared_pending);
                         do {
-                                rm_from_queue(sigmask(sig), &t->pending);
+                                rm_from_queue_full(&mask, &t->pending);
                                 recalc_sigpending_tsk(t);
                                 t = next_thread(t);
                         } while (t != current);
diff --git a/kernel/sys.c b/kernel/sys.c
index eecf84526afe..b6941e06d5d5 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -489,6 +489,12 @@ asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user
                         magic2 != LINUX_REBOOT_MAGIC2C))
                 return -EINVAL;
 
+        /* Instead of trying to make the power_off code look like
+         * halt when pm_power_off is not set do it the easy way.
+         */
+        if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off)
+                cmd = LINUX_REBOOT_CMD_HALT;
+
         lock_kernel();
         switch (cmd) {
         case LINUX_REBOOT_CMD_RESTART:
@@ -1084,10 +1090,11 @@ asmlinkage long sys_times(struct tms __user * tbuf)
 asmlinkage long sys_setpgid(pid_t pid, pid_t pgid)
 {
         struct task_struct *p;
+        struct task_struct *group_leader = current->group_leader;
         int err = -EINVAL;
 
         if (!pid)
-                pid = current->pid;
+                pid = group_leader->pid;
         if (!pgid)
                 pgid = pid;
         if (pgid < 0)
@@ -1107,16 +1114,16 @@ asmlinkage long sys_setpgid(pid_t pid, pid_t pgid)
         if (!thread_group_leader(p))
                 goto out;
 
-        if (p->parent == current || p->real_parent == current) {
+        if (p->real_parent == group_leader) {
                 err = -EPERM;
-                if (p->signal->session != current->signal->session)
+                if (p->signal->session != group_leader->signal->session)
                         goto out;
                 err = -EACCES;
                 if (p->did_exec)
                         goto out;
         } else {
                 err = -ESRCH;
-                if (p != current)
+                if (p != group_leader)
                         goto out;
         }
 
@@ -1128,7 +1135,7 @@ asmlinkage long sys_setpgid(pid_t pid, pid_t pgid)
                 struct task_struct *p;
 
                 do_each_task_pid(pgid, PIDTYPE_PGID, p) {
-                        if (p->signal->session == current->signal->session)
+                        if (p->signal->session == group_leader->signal->session)
                                 goto ok_pgid;
                 } while_each_task_pid(pgid, PIDTYPE_PGID, p);
                 goto out;
@@ -1208,24 +1215,22 @@ asmlinkage long sys_getsid(pid_t pid)
 
 asmlinkage long sys_setsid(void)
 {
+        struct task_struct *group_leader = current->group_leader;
         struct pid *pid;
         int err = -EPERM;
 
-        if (!thread_group_leader(current))
-                return -EINVAL;
-
         down(&tty_sem);
         write_lock_irq(&tasklist_lock);
 
-        pid = find_pid(PIDTYPE_PGID, current->pid);
+        pid = find_pid(PIDTYPE_PGID, group_leader->pid);
         if (pid)
                 goto out;
 
-        current->signal->leader = 1;
-        __set_special_pids(current->pid, current->pid);
-        current->signal->tty = NULL;
-        current->signal->tty_old_pgrp = 0;
-        err = process_group(current);
+        group_leader->signal->leader = 1;
+        __set_special_pids(group_leader->pid, group_leader->pid);
+        group_leader->signal->tty = NULL;
+        group_leader->signal->tty_old_pgrp = 0;
+        err = process_group(group_leader);
 out:
         write_unlock_irq(&tasklist_lock);
         up(&tty_sem);
@@ -1687,7 +1692,10 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
         if (unlikely(!p->signal))
                 return;
 
+        utime = stime = cputime_zero;
+
         switch (who) {
+                case RUSAGE_BOTH:
                 case RUSAGE_CHILDREN:
                         spin_lock_irqsave(&p->sighand->siglock, flags);
                         utime = p->signal->cutime;
@@ -1697,22 +1705,11 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
                         r->ru_minflt = p->signal->cmin_flt;
                         r->ru_majflt = p->signal->cmaj_flt;
                         spin_unlock_irqrestore(&p->sighand->siglock, flags);
-                        cputime_to_timeval(utime, &r->ru_utime);
-                        cputime_to_timeval(stime, &r->ru_stime);
-                        break;
+
+                        if (who == RUSAGE_CHILDREN)
+                                break;
+
                 case RUSAGE_SELF:
-                        spin_lock_irqsave(&p->sighand->siglock, flags);
-                        utime = stime = cputime_zero;
-                        goto sum_group;
-                case RUSAGE_BOTH:
-                        spin_lock_irqsave(&p->sighand->siglock, flags);
-                        utime = p->signal->cutime;
-                        stime = p->signal->cstime;
-                        r->ru_nvcsw = p->signal->cnvcsw;
-                        r->ru_nivcsw = p->signal->cnivcsw;
-                        r->ru_minflt = p->signal->cmin_flt;
-                        r->ru_majflt = p->signal->cmaj_flt;
-                sum_group:
                         utime = cputime_add(utime, p->signal->utime);
                         stime = cputime_add(stime, p->signal->stime);
                         r->ru_nvcsw += p->signal->nvcsw;
@@ -1729,13 +1726,14 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
                                 r->ru_majflt += t->maj_flt;
                                 t = next_thread(t);
                         } while (t != p);
-                        spin_unlock_irqrestore(&p->sighand->siglock, flags);
-                        cputime_to_timeval(utime, &r->ru_utime);
-                        cputime_to_timeval(stime, &r->ru_stime);
                         break;
+
                 default:
                         BUG();
         }
+
+        cputime_to_timeval(utime, &r->ru_utime);
+        cputime_to_timeval(stime, &r->ru_stime);
 }
 
 int getrusage(struct task_struct *p, int who, struct rusage __user *ru)
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index d4739a475d23..17313b99e53d 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -82,6 +82,28 @@ cond_syscall(compat_sys_socketcall);
 cond_syscall(sys_inotify_init);
 cond_syscall(sys_inotify_add_watch);
 cond_syscall(sys_inotify_rm_watch);
+cond_syscall(sys_migrate_pages);
+cond_syscall(sys_chown16);
+cond_syscall(sys_fchown16);
+cond_syscall(sys_getegid16);
+cond_syscall(sys_geteuid16);
+cond_syscall(sys_getgid16);
+cond_syscall(sys_getgroups16);
+cond_syscall(sys_getresgid16);
+cond_syscall(sys_getresuid16);
+cond_syscall(sys_getuid16);
+cond_syscall(sys_lchown16);
+cond_syscall(sys_setfsgid16);
+cond_syscall(sys_setfsuid16);
+cond_syscall(sys_setgid16);
+cond_syscall(sys_setgroups16);
+cond_syscall(sys_setregid16);
+cond_syscall(sys_setresgid16);
+cond_syscall(sys_setresuid16);
+cond_syscall(sys_setreuid16);
+cond_syscall(sys_setuid16);
+cond_syscall(sys_vm86old);
+cond_syscall(sys_vm86);
 
 /* arch-specific weak syscall entries */
 cond_syscall(sys_pciconfig_read);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index a85047bb5739..03b0598f2369 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -68,6 +68,8 @@ extern int min_free_kbytes;
 extern int printk_ratelimit_jiffies;
 extern int printk_ratelimit_burst;
 extern int pid_max_min, pid_max_max;
+extern int sysctl_drop_caches;
+extern int percpu_pagelist_fraction;
 
 #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
 int unknown_nmi_panic;
@@ -78,6 +80,7 @@ extern int proc_unknown_nmi_panic(ctl_table *, int, struct file *,
 /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
 static int maxolduid = 65535;
 static int minolduid;
+static int min_percpu_pagelist_fract = 8;
 
 static int ngroups_max = NGROUPS_MAX;
 
@@ -775,6 +778,15 @@ static ctl_table vm_table[] = {
                 .strategy       = &sysctl_intvec,
         },
         {
+                .ctl_name       = VM_DROP_PAGECACHE,
+                .procname       = "drop_caches",
+                .data           = &sysctl_drop_caches,
+                .maxlen         = sizeof(int),
+                .mode           = 0644,
+                .proc_handler   = drop_caches_sysctl_handler,
+                .strategy       = &sysctl_intvec,
+        },
+        {
                 .ctl_name       = VM_MIN_FREE_KBYTES,
                 .procname       = "min_free_kbytes",
                 .data           = &min_free_kbytes,
@@ -784,6 +796,16 @@ static ctl_table vm_table[] = {
                 .strategy       = &sysctl_intvec,
                 .extra1         = &zero,
         },
+        {
+                .ctl_name       = VM_PERCPU_PAGELIST_FRACTION,
+                .procname       = "percpu_pagelist_fraction",
+                .data           = &percpu_pagelist_fraction,
+                .maxlen         = sizeof(percpu_pagelist_fraction),
+                .mode           = 0644,
+                .proc_handler   = &percpu_pagelist_fraction_sysctl_handler,
+                .strategy       = &sysctl_intvec,
+                .extra1         = &min_percpu_pagelist_fract,
+        },
 #ifdef CONFIG_MMU
         {
                 .ctl_name       = VM_MAX_MAP_COUNT,
diff --git a/kernel/timer.c b/kernel/timer.c
index fd74268d8663..074b4bd5cfd8 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -33,6 +33,7 @@
 #include <linux/posix-timers.h>
 #include <linux/cpu.h>
 #include <linux/syscalls.h>
+#include <linux/delay.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 2bd5aee1c736..82c4fa70595c 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -29,7 +29,8 @@
 #include <linux/kthread.h>
 
 /*
- * The per-CPU workqueue (if single thread, we always use cpu 0's).
+ * The per-CPU workqueue (if single thread, we always use the first
+ * possible cpu).
  *
  * The sequence counters are for flush_scheduled_work().  It wants to wait
  * until until all currently-scheduled works are completed, but it doesn't
@@ -69,6 +70,8 @@ struct workqueue_struct {
 static DEFINE_SPINLOCK(workqueue_lock);
 static LIST_HEAD(workqueues);
 
+static int singlethread_cpu;
+
 /* If it's single threaded, it isn't in the list of workqueues. */
 static inline int is_single_threaded(struct workqueue_struct *wq)
 {
@@ -102,7 +105,7 @@ int fastcall queue_work(struct workqueue_struct *wq, struct work_struct *work)
 
         if (!test_and_set_bit(0, &work->pending)) {
                 if (unlikely(is_single_threaded(wq)))
-                        cpu = any_online_cpu(cpu_online_map);
+                        cpu = singlethread_cpu;
                 BUG_ON(!list_empty(&work->entry));
                 __queue_work(per_cpu_ptr(wq->cpu_wq, cpu), work);
                 ret = 1;
@@ -118,7 +121,7 @@ static void delayed_work_timer_fn(unsigned long __data)
         int cpu = smp_processor_id();
 
         if (unlikely(is_single_threaded(wq)))
-                cpu = any_online_cpu(cpu_online_map);
+                cpu = singlethread_cpu;
 
         __queue_work(per_cpu_ptr(wq->cpu_wq, cpu), work);
 }
@@ -267,7 +270,7 @@ void fastcall flush_workqueue(struct workqueue_struct *wq)
 
         if (is_single_threaded(wq)) {
                 /* Always use first cpu's area. */
-                flush_cpu_workqueue(per_cpu_ptr(wq->cpu_wq, any_online_cpu(cpu_online_map)));
+                flush_cpu_workqueue(per_cpu_ptr(wq->cpu_wq, singlethread_cpu));
         } else {
                 int cpu;
 
@@ -315,12 +318,17 @@ struct workqueue_struct *__create_workqueue(const char *name,
                 return NULL;
 
         wq->cpu_wq = alloc_percpu(struct cpu_workqueue_struct);
+        if (!wq->cpu_wq) {
+                kfree(wq);
+                return NULL;
+        }
+
         wq->name = name;
         /* We don't need the distraction of CPUs appearing and vanishing. */
         lock_cpu_hotplug();
         if (singlethread) {
                 INIT_LIST_HEAD(&wq->list);
-                p = create_workqueue_thread(wq, any_online_cpu(cpu_online_map));
+                p = create_workqueue_thread(wq, singlethread_cpu);
                 if (!p)
                         destroy = 1;
                 else
@@ -374,7 +382,7 @@ void destroy_workqueue(struct workqueue_struct *wq)
         /* We don't need the distraction of CPUs appearing and vanishing. */
         lock_cpu_hotplug();
         if (is_single_threaded(wq))
-                cleanup_workqueue_thread(wq, any_online_cpu(cpu_online_map));
+                cleanup_workqueue_thread(wq, singlethread_cpu);
         else {
                 for_each_online_cpu(cpu)
                         cleanup_workqueue_thread(wq, cpu);
@@ -419,6 +427,25 @@ int schedule_delayed_work_on(int cpu,
         return ret;
 }
 
+int schedule_on_each_cpu(void (*func) (void *info), void *info)
+{
+        int cpu;
+        struct work_struct *work;
+
+        work = kmalloc(NR_CPUS * sizeof(struct work_struct), GFP_KERNEL);
+
+        if (!work)
+                return -ENOMEM;
+        for_each_online_cpu(cpu) {
+                INIT_WORK(work + cpu, func, info);
+                __queue_work(per_cpu_ptr(keventd_wq->cpu_wq, cpu),
+                                work + cpu);
+        }
+        flush_workqueue(keventd_wq);
+        kfree(work);
+        return 0;
+}
+
 void flush_scheduled_work(void)
 {
         flush_workqueue(keventd_wq);
@@ -543,6 +570,7 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
 
 void init_workqueues(void)
 {
+        singlethread_cpu = first_cpu(cpu_possible_map);
         hotcpu_notifier(workqueue_cpu_callback, 0);
         keventd_wq = create_workqueue("events");
         BUG_ON(!keventd_wq);