17 files changed, 131 insertions, 110 deletions

diff --git a/kernel/audit.c b/kernel/audit.c
index 0a36091ed712..963fd15c9621 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1028,6 +1028,9 @@ void audit_log_hex(struct audit_buffer *ab, const unsigned char *buf,
         struct sk_buff *skb;
         static const unsigned char *hex = "0123456789ABCDEF";
 
+        if (!ab)
+                return;
+
         BUG_ON(!ab->skb);
         skb = ab->skb;
         avail = skb_tailroom(skb);
@@ -1060,6 +1063,9 @@ static void audit_log_n_string(struct audit_buffer *ab, size_t slen,
         unsigned char *ptr;
         struct sk_buff *skb;
 
+        if (!ab)
+                return;
+
         BUG_ON(!ab->skb);
         skb = ab->skb;
         avail = skb_tailroom(skb);
diff --git a/kernel/audit.h b/kernel/audit.h
index 6aa33b848cf2..a3370232a390 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -104,6 +104,7 @@ static inline int audit_hash_ino(u32 ino)
         return (ino & (AUDIT_INODE_BUCKETS-1));
 }
 
+extern int audit_match_class(int class, unsigned syscall);
 extern int audit_comparator(const u32 left, const u32 op, const u32 right);
 extern int audit_compare_dname_path(const char *dname, const char *path,
                                     int *dirlen);
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 6a9a5c5a4e7d..a44879b0c72f 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -302,6 +302,15 @@ int __init audit_register_class(int class, unsigned *list)
         return 0;
 }
 
+int audit_match_class(int class, unsigned syscall)
+{
+        if (unlikely(syscall >= AUDIT_BITMASK_SIZE * sizeof(__u32)))
+                return 0;
+        if (unlikely(class >= AUDIT_SYSCALL_CLASSES || !classes[class]))
+                return 0;
+        return classes[class][AUDIT_WORD(syscall)] & AUDIT_BIT(syscall);
+}
+
 /* Common user-space to kernel rule translation. */
 static inline struct audit_entry *audit_to_entry_common(struct audit_rule *rule)
 {
@@ -404,6 +413,7 @@ static struct audit_entry *audit_rule_to_entry(struct audit_rule *rule)
                 case AUDIT_PERS:
                 case AUDIT_ARCH:
                 case AUDIT_MSGTYPE:
+                case AUDIT_PPID:
                 case AUDIT_DEVMAJOR:
                 case AUDIT_DEVMINOR:
                 case AUDIT_EXIT:
@@ -413,6 +423,10 @@ static struct audit_entry *audit_rule_to_entry(struct audit_rule *rule)
                 case AUDIT_ARG2:
                 case AUDIT_ARG3:
                         break;
+                case AUDIT_PERM:
+                        if (f->val & ~15)
+                                goto exit_free;
+                        break;
                 case AUDIT_INODE:
                         err = audit_to_inode(&entry->rule, f);
                         if (err)
@@ -567,6 +581,10 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
                         entry->rule.buflen += f->val;
                         entry->rule.filterkey = str;
                         break;
+                case AUDIT_PERM:
+                        if (f->val & ~15)
+                                goto exit_free;
+                        break;
                 default:
                         goto exit_free;
                 }
@@ -913,7 +931,7 @@ static void audit_update_watch(struct audit_parent *parent,
                 }
 
                 ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE);
-                audit_log_format(ab, "audit updated rules specifying watch=");
+                audit_log_format(ab, "audit updated rules specifying path=");
                 audit_log_untrustedstring(ab, owatch->path);
                 audit_log_format(ab, " with dev=%u ino=%lu\n", dev, ino);
                 audit_log_end(ab);
@@ -936,19 +954,28 @@ static void audit_remove_parent_watches(struct audit_parent *parent)
         struct audit_watch *w, *nextw;
         struct audit_krule *r, *nextr;
         struct audit_entry *e;
+        struct audit_buffer *ab;
 
         mutex_lock(&audit_filter_mutex);
         parent->flags |= AUDIT_PARENT_INVALID;
         list_for_each_entry_safe(w, nextw, &parent->watches, wlist) {
                 list_for_each_entry_safe(r, nextr, &w->rules, rlist) {
                         e = container_of(r, struct audit_entry, rule);
+
+                        ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE);
+                        audit_log_format(ab, "audit implicitly removed rule path=");
+                        audit_log_untrustedstring(ab, w->path);
+                        if (r->filterkey) {
+                                audit_log_format(ab, " key=");
+                                audit_log_untrustedstring(ab, r->filterkey);
+                        } else
+                                audit_log_format(ab, " key=(null)");
+                        audit_log_format(ab, " list=%d", r->listnr);
+                        audit_log_end(ab);
+
                         list_del(&r->rlist);
                         list_del_rcu(&e->list);
                         call_rcu(&e->rcu, audit_free_rule_rcu);
-
-                        audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE,
-                                 "audit implicitly removed rule from list=%d\n",
-                                  AUDIT_FILTER_EXIT);
                 }
                 audit_remove_watch(w);
         }
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index efc1b74bebf3..1bd8827a0102 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -209,6 +209,54 @@ struct audit_context {
 #endif
 };
 
+#define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE])
+static inline int open_arg(int flags, int mask)
+{
+        int n = ACC_MODE(flags);
+        if (flags & (O_TRUNC | O_CREAT))
+                n |= AUDIT_PERM_WRITE;
+        return n & mask;
+}
+
+static int audit_match_perm(struct audit_context *ctx, int mask)
+{
+        unsigned n = ctx->major;
+        switch (audit_classify_syscall(ctx->arch, n)) {
+        case 0: /* native */
+                if ((mask & AUDIT_PERM_WRITE) &&
+                     audit_match_class(AUDIT_CLASS_WRITE, n))
+                        return 1;
+                if ((mask & AUDIT_PERM_READ) &&
+                     audit_match_class(AUDIT_CLASS_READ, n))
+                        return 1;
+                if ((mask & AUDIT_PERM_ATTR) &&
+                     audit_match_class(AUDIT_CLASS_CHATTR, n))
+                        return 1;
+                return 0;
+        case 1: /* 32bit on biarch */
+                if ((mask & AUDIT_PERM_WRITE) &&
+                     audit_match_class(AUDIT_CLASS_WRITE_32, n))
+                        return 1;
+                if ((mask & AUDIT_PERM_READ) &&
+                     audit_match_class(AUDIT_CLASS_READ_32, n))
+                        return 1;
+                if ((mask & AUDIT_PERM_ATTR) &&
+                     audit_match_class(AUDIT_CLASS_CHATTR_32, n))
+                        return 1;
+                return 0;
+        case 2: /* open */
+                return mask & ACC_MODE(ctx->argv[1]);
+        case 3: /* openat */
+                return mask & ACC_MODE(ctx->argv[2]);
+        case 4: /* socketcall */
+                return ((mask & AUDIT_PERM_WRITE) && ctx->argv[0] == SYS_BIND);
+        case 5: /* execve */
+                return mask & AUDIT_PERM_EXEC;
+        default:
+                return 0;
+        }
+}
+
 /* Determine if any context name data matches a rule's watch data */
 /* Compare a task_struct with an audit_rule.  Return 1 on match, 0
  * otherwise. */
@@ -397,6 +445,9 @@ static int audit_filter_rules(struct task_struct *tsk,
                         /* ignore this field for filtering */
                         result = 1;
                         break;
+                case AUDIT_PERM:
+                        result = audit_match_perm(ctx, f->val);
+                        break;
                 }
 
                 if (!result)
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index 57ca3730205d..36752f124c6a 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -41,24 +41,11 @@ void delayacct_init(void)
 
 void __delayacct_tsk_init(struct task_struct *tsk)
 {
-        spin_lock_init(&tsk->delays_lock);
-        /* No need to acquire tsk->delays_lock for allocation here unless
-           __delayacct_tsk_init called after tsk is attached to tasklist
-        */
         tsk->delays = kmem_cache_zalloc(delayacct_cache, SLAB_KERNEL);
         if (tsk->delays)
                 spin_lock_init(&tsk->delays->lock);
 }
 
-void __delayacct_tsk_exit(struct task_struct *tsk)
-{
-        struct task_delay_info *delays = tsk->delays;
-        spin_lock(&tsk->delays_lock);
-        tsk->delays = NULL;
-        spin_unlock(&tsk->delays_lock);
-        kmem_cache_free(delayacct_cache, delays);
-}
-
 /*
  * Start accounting for a delay statistic using
  * its starting timestamp (@start)
@@ -118,8 +105,6 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
         struct timespec ts;
         unsigned long t1,t2,t3;
 
-        spin_lock(&tsk->delays_lock);
-
         /* Though tsk->delays accessed later, early exit avoids
          * unnecessary returning of other data
          */
@@ -161,7 +146,6 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
         spin_unlock(&tsk->delays->lock);
 
 done:
-        spin_unlock(&tsk->delays_lock);
         return 0;
 }
 
diff --git a/kernel/exit.c b/kernel/exit.c
index dba194a8d416..d891883420f7 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -908,7 +908,6 @@ fastcall NORET_TYPE void do_exit(long code)
                 audit_free(tsk);
         taskstats_exit_send(tsk, tidstats, group_dead, mycpu);
         taskstats_exit_free(tidstats);
-        delayacct_tsk_exit(tsk);
 
         exit_mm(tsk);
 
@@ -1054,7 +1053,7 @@ static int eligible_child(pid_t pid, int options, struct task_struct *p)
          * Do not consider thread group leaders that are
          * in a non-empty thread group:
          */
-        if (current->tgid != p->tgid && delay_group_leader(p))
+        if (delay_group_leader(p))
                 return 2;
 
         if (security_task_wait(p))
diff --git a/kernel/fork.c b/kernel/fork.c
index aa36c43783cc..f9b014e3e700 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -117,6 +117,7 @@ void __put_task_struct(struct task_struct *tsk)
         security_task_free(tsk);
         free_uid(tsk->user);
         put_group_info(tsk->group_info);
+        delayacct_tsk_free(tsk);
 
         if (!profile_handoff_task(tsk))
                 free_task(tsk);
@@ -1011,7 +1012,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
         retval = -EFAULT;
         if (clone_flags & CLONE_PARENT_SETTID)
                 if (put_user(p->pid, parent_tidptr))
-                        goto bad_fork_cleanup;
+                        goto bad_fork_cleanup_delays_binfmt;
 
         INIT_LIST_HEAD(&p->children);
         INIT_LIST_HEAD(&p->sibling);
@@ -1277,7 +1278,8 @@ bad_fork_cleanup_policy:
 bad_fork_cleanup_cpuset:
 #endif
         cpuset_exit(p);
-bad_fork_cleanup:
+bad_fork_cleanup_delays_binfmt:
+        delayacct_tsk_free(p);
         if (p->binfmt)
                 module_put(p->binfmt->module);
 bad_fork_cleanup_put_domain:
diff --git a/kernel/futex.c b/kernel/futex.c
index b9b8aea5389e..9d260e838cff 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1120,9 +1120,10 @@ static int futex_wait(u32 __user *uaddr, u32 val, unsigned long time)
  * if there are waiters then it will block, it does PI, etc. (Due to
  * races the kernel might see a 0 value of the futex too.)
  */
-static int do_futex_lock_pi(u32 __user *uaddr, int detect, int trylock,
-                            struct hrtimer_sleeper *to)
+static int futex_lock_pi(u32 __user *uaddr, int detect, unsigned long sec,
+                         long nsec, int trylock)
 {
+        struct hrtimer_sleeper timeout, *to = NULL;
         struct task_struct *curr = current;
         struct futex_hash_bucket *hb;
         u32 uval, newval, curval;
@@ -1132,6 +1133,13 @@ static int do_futex_lock_pi(u32 __user *uaddr, int detect, int trylock,
         if (refill_pi_state_cache())
                 return -ENOMEM;
 
+        if (sec != MAX_SCHEDULE_TIMEOUT) {
+                to = &timeout;
+                hrtimer_init(&to->timer, CLOCK_REALTIME, HRTIMER_ABS);
+                hrtimer_init_sleeper(to, current);
+                to->timer.expires = ktime_set(sec, nsec);
+        }
+
         q.pi_state = NULL;
  retry:
         down_read(&curr->mm->mmap_sem);
@@ -1307,7 +1315,7 @@ static int do_futex_lock_pi(u32 __user *uaddr, int detect, int trylock,
         if (!detect && ret == -EDEADLK && 0)
                 force_sig(SIGKILL, current);
 
-        return ret;
+        return ret != -EINTR ? ret : -ERESTARTNOINTR;
 
  out_unlock_release_sem:
         queue_unlock(&q, hb);
@@ -1342,76 +1350,6 @@ static int do_futex_lock_pi(u32 __user *uaddr, int detect, int trylock,
 }
 
 /*
- * Restart handler
- */
-static long futex_lock_pi_restart(struct restart_block *restart)
-{
-        struct hrtimer_sleeper timeout, *to = NULL;
-        int ret;
-
-        restart->fn = do_no_restart_syscall;
-
-        if (restart->arg2 || restart->arg3) {
-                to = &timeout;
-                hrtimer_init(&to->timer, CLOCK_REALTIME, HRTIMER_ABS);
-                hrtimer_init_sleeper(to, current);
-                to->timer.expires.tv64 = ((u64)restart->arg1 << 32) |
-                        (u64) restart->arg0;
-        }
-
-        pr_debug("lock_pi restart: %p, %d (%d)\n",
-                 (u32 __user *)restart->arg0, current->pid);
-
-        ret = do_futex_lock_pi((u32 __user *)restart->arg0, restart->arg1,
-                               0, to);
-
-        if (ret != -EINTR)
-                return ret;
-
-        restart->fn = futex_lock_pi_restart;
-
-        /* The other values are filled in */
-        return -ERESTART_RESTARTBLOCK;
-}
-
-/*
- * Called from the syscall entry below.
- */
-static int futex_lock_pi(u32 __user *uaddr, int detect, unsigned long sec,
-                         long nsec, int trylock)
-{
-        struct hrtimer_sleeper timeout, *to = NULL;
-        struct restart_block *restart;
-        int ret;
-
-        if (sec != MAX_SCHEDULE_TIMEOUT) {
-                to = &timeout;
-                hrtimer_init(&to->timer, CLOCK_REALTIME, HRTIMER_ABS);
-                hrtimer_init_sleeper(to, current);
-                to->timer.expires = ktime_set(sec, nsec);
-        }
-
-        ret = do_futex_lock_pi(uaddr, detect, trylock, to);
-
-        if (ret != -EINTR)
-                return ret;
-
-        pr_debug("lock_pi interrupted: %p, %d (%d)\n", uaddr, current->pid);
-
-        restart = &current_thread_info()->restart_block;
-        restart->fn = futex_lock_pi_restart;
-        restart->arg0 = (unsigned long) uaddr;
-        restart->arg1 = detect;
-        if (to) {
-                restart->arg2 = to->timer.expires.tv64 & 0xFFFFFFFF;
-                restart->arg3 = to->timer.expires.tv64 >> 32;
-        } else
-                restart->arg2 = restart->arg3 = 0;
-
-        return -ERESTART_RESTARTBLOCK;
-}
-
-/*
  * Userspace attempted a TID -> 0 atomic transition, and failed.
  * This is the in-kernel slowpath: we look up the PI state (if any),
  * and do the rt-mutex unlock.
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 9336f2e89e40..ac1f850d4937 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -252,7 +252,7 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc, struct pt_regs *regs)
         mask_ack_irq(desc, irq);
 
         if (unlikely(desc->status & IRQ_INPROGRESS))
-                goto out;
+                goto out_unlock;
         desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
         kstat_cpu(cpu).irqs[irq]++;
 
@@ -263,7 +263,7 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc, struct pt_regs *regs)
         action = desc->action;
         if (unlikely(!action || (desc->status & IRQ_DISABLED))) {
                 desc->status |= IRQ_PENDING;
-                goto out;
+                goto out_unlock;
         }
 
         desc->status |= IRQ_INPROGRESS;
@@ -276,9 +276,9 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc, struct pt_regs *regs)
 
         spin_lock(&desc->lock);
         desc->status &= ~IRQ_INPROGRESS;
-out:
         if (!(desc->status & IRQ_DISABLED) && desc->chip->unmask)
                 desc->chip->unmask(irq);
+out_unlock:
         spin_unlock(&desc->lock);
 }
 
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index fc4e906aedbd..48a53f68af96 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -20,6 +20,11 @@
 
 /**
  * handle_bad_irq - handle spurious and unhandled irqs
+ * @irq:       the interrupt number
+ * @desc:      description of the interrupt
+ * @regs:      pointer to a register structure
+ *
+ * Handles spurious and unhandled IRQ's. It also prints a debugmessage.
  */
 void fastcall
 handle_bad_irq(unsigned int irq, struct irq_desc *desc, struct pt_regs *regs)
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index 872f91ba2ce8..35f10f7ff94a 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -63,8 +63,7 @@ void check_irq_resend(struct irq_desc *desc, unsigned int irq)
         desc->chip->enable(irq);
 
         if ((status & (IRQ_PENDING | IRQ_REPLAY)) == IRQ_PENDING) {
-                desc->status &= ~IRQ_PENDING;
-                desc->status = status | IRQ_REPLAY;
+                desc->status = (status & ~IRQ_PENDING) | IRQ_REPLAY;
 
                 if (!desc->chip || !desc->chip->retrigger ||
                                         !desc->chip->retrigger(irq)) {
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 1d32defa38ab..5c470c57fb57 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -197,11 +197,12 @@ static void __call_usermodehelper(void *data)
 {
         struct subprocess_info *sub_info = data;
         pid_t pid;
+        int wait = sub_info->wait;
 
         /* CLONE_VFORK: wait until the usermode helper has execve'd
          * successfully We need the data structures to stay around
          * until that is done.  */
-        if (sub_info->wait)
+        if (wait)
                 pid = kernel_thread(wait_for_helper, sub_info,
                                     CLONE_FS | CLONE_FILES | SIGCHLD);
         else
@@ -211,7 +212,7 @@ static void __call_usermodehelper(void *data)
         if (pid < 0) {
                 sub_info->retval = pid;
                 complete(sub_info->complete);
-        } else if (!sub_info->wait)
+        } else if (!wait)
                 complete(sub_info->complete);
 }
 
diff --git a/kernel/lockdep_internals.h b/kernel/lockdep_internals.h
index 0d355f24fe04..eab043c83bb2 100644
--- a/kernel/lockdep_internals.h
+++ b/kernel/lockdep_internals.h
@@ -27,7 +27,7 @@
  * Stack-trace: tightly packed array of stack backtrace
  * addresses. Protected by the hash_lock.
  */
-#define MAX_STACK_TRACE_ENTRIES 131072UL
+#define MAX_STACK_TRACE_ENTRIES 262144UL
 
 extern struct list_head all_lock_classes;
 
diff --git a/kernel/panic.c b/kernel/panic.c
index 9b8dcfd1ca93..8010b9b17aca 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -173,7 +173,7 @@ const char *print_tainted(void)
 
 void add_taint(unsigned flag)
 {
-        debug_locks_off(); /* can't trust the integrity of the kernel anymore */
+        debug_locks = 0; /* can't trust the integrity of the kernel anymore */
         tainted |= flag;
 }
 EXPORT_SYMBOL(add_taint);
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index ae44a70aae8a..619ecabf7c58 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -56,7 +56,7 @@ config PM_TRACE
 
 config SOFTWARE_SUSPEND
         bool "Software Suspend"
-        depends on PM && SWAP && (X86 && (!SMP || SUSPEND_SMP)) || ((FRV || PPC32) && !SMP)
+        depends on PM && SWAP && ((X86 && (!SMP || SUSPEND_SMP) && !X86_PAE) || ((FRV || PPC32) && !SMP))
         ---help---
           Enable the possibility of suspending the machine.
           It doesn't need ACPI or APM.
@@ -78,6 +78,10 @@ config SOFTWARE_SUSPEND
 
           For more information take a look at <file:Documentation/power/swsusp.txt>.
 
+          (For now, swsusp is incompatible with PAE aka HIGHMEM_64G on i386.
+          we need identity mapping for resume to work, and that is trivial
+          to get with 4MB pages, but less than trivial on PAE).
+
 config PM_STD_PARTITION
         string "Default resume partition"
         depends on SOFTWARE_SUSPEND
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index 436ab35f6fa7..523e46483b99 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -241,12 +241,16 @@ static void rcu_do_batch(struct rcu_data *rdp)
                 next = rdp->donelist = list->next;
                 list->func(list);
                 list = next;
-                rdp->qlen--;
                 if (++count >= rdp->blimit)
                         break;
         }
+
+        local_irq_disable();
+        rdp->qlen -= count;
+        local_irq_enable();
         if (rdp->blimit == INT_MAX && rdp->qlen <= qlowmark)
                 rdp->blimit = blimit;
+
         if (!rdp->donelist)
                 rdp->donetail = &rdp->donelist;
         else
diff --git a/kernel/spinlock.c b/kernel/spinlock.c
index bfd6ad9c0330..fb524b009eef 100644
--- a/kernel/spinlock.c
+++ b/kernel/spinlock.c
@@ -72,7 +72,7 @@ EXPORT_SYMBOL(_write_trylock);
  * not re-enabled during lock-acquire (which the preempt-spin-ops do):
  */
 #if !defined(CONFIG_PREEMPT) || !defined(CONFIG_SMP) || \
-        defined(CONFIG_PROVE_LOCKING)
+        defined(CONFIG_DEBUG_LOCK_ALLOC)
 
 void __lockfunc _read_lock(rwlock_t *lock)
 {