Merge commit 'v2.6.28-rc2' into x86/pci-ioapic-boot-irq-quirks

1 files changed, 129 insertions, 106 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index adefc1131f27..f6083561dfe0 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -27,15 +27,18 @@
 #include <linux/key.h>
 #include <linux/binfmts.h>
 #include <linux/mman.h>
+#include <linux/mmu_notifier.h>
 #include <linux/fs.h>
 #include <linux/nsproxy.h>
 #include <linux/capability.h>
 #include <linux/cpu.h>
 #include <linux/cgroup.h>
 #include <linux/security.h>
+#include <linux/hugetlb.h>
 #include <linux/swap.h>
 #include <linux/syscalls.h>
 #include <linux/jiffies.h>
+#include <linux/tracehook.h>
 #include <linux/futex.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/rcupdate.h>
@@ -55,6 +58,7 @@
 #include <linux/tty.h>
 #include <linux/proc_fs.h>
 #include <linux/blkdev.h>
+#include <trace/sched.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -92,6 +96,23 @@ int nr_processes(void)
 static struct kmem_cache *task_struct_cachep;
 #endif
 
+#ifndef __HAVE_ARCH_THREAD_INFO_ALLOCATOR
+static inline struct thread_info *alloc_thread_info(struct task_struct *tsk)
+{
+#ifdef CONFIG_DEBUG_STACK_USAGE
+        gfp_t mask = GFP_KERNEL | __GFP_ZERO;
+#else
+        gfp_t mask = GFP_KERNEL;
+#endif
+        return (struct thread_info *)__get_free_pages(mask, THREAD_SIZE_ORDER);
+}
+
+static inline void free_thread_info(struct thread_info *ti)
+{
+        free_pages((unsigned long)ti, THREAD_SIZE_ORDER);
+}
+#endif
+
 /* SLAB cache for signal_struct structures (tsk->signal) */
 static struct kmem_cache *signal_cachep;
 
@@ -307,6 +328,14 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
                 }
 
                 /*
+                 * Clear hugetlb-related page reserves for children. This only
+                 * affects MAP_PRIVATE mappings. Faults generated by the child
+                 * are not guaranteed to succeed, even if read-only
+                 */
+                if (is_vm_hugetlb_page(tmp))
+                        reset_vma_resv_huge_pages(tmp);
+
+                /*
                  * Link in the new vma and copy the page table entries.
                  */
                 *pprev = tmp;
@@ -374,7 +403,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
         INIT_LIST_HEAD(&mm->mmlist);
         mm->flags = (current->mm) ? current->mm->flags
                                   : MMF_DUMP_FILTER_DEFAULT;
-        mm->core_waiters = 0;
+        mm->core_state = NULL;
         mm->nr_ptes = 0;
         set_mm_counter(mm, file_rss, 0);
         set_mm_counter(mm, anon_rss, 0);
@@ -387,6 +416,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
 
         if (likely(!mm_alloc_pgd(mm))) {
                 mm->def_flags = 0;
+                mmu_notifier_mm_init(mm);
                 return mm;
         }
 
@@ -419,6 +449,7 @@ void __mmdrop(struct mm_struct *mm)
         BUG_ON(mm == &init_mm);
         mm_free_pgd(mm);
         destroy_context(mm);
+        mmu_notifier_mm_destroy(mm);
         free_mm(mm);
 }
 EXPORT_SYMBOL_GPL(__mmdrop);
@@ -448,7 +479,7 @@ EXPORT_SYMBOL_GPL(mmput);
 /**
  * get_task_mm - acquire a reference to the task's mm
  *
- * Returns %NULL if the task has no mm.  Checks PF_BORROWED_MM (meaning
+ * Returns %NULL if the task has no mm.  Checks PF_KTHREAD (meaning
  * this kernel workthread has transiently adopted a user mm with use_mm,
  * to do its AIO) is not set and if so returns a reference to it, after
  * bumping up the use count.  User must release the mm via mmput()
@@ -461,7 +492,7 @@ struct mm_struct *get_task_mm(struct task_struct *task)
         task_lock(task);
         mm = task->mm;
         if (mm) {
-                if (task->flags & PF_BORROWED_MM)
+                if (task->flags & PF_KTHREAD)
                         mm = NULL;
                 else
                         atomic_inc(&mm->mm_users);
@@ -630,13 +661,6 @@ static struct fs_struct *__copy_fs_struct(struct fs_struct *old)
                 path_get(&old->root);
                 fs->pwd = old->pwd;
                 path_get(&old->pwd);
-                if (old->altroot.dentry) {
-                        fs->altroot = old->altroot;
-                        path_get(&old->altroot);
-                } else {
-                        fs->altroot.mnt = NULL;
-                        fs->altroot.dentry = NULL;
-                }
                 read_unlock(&old->lock);
         }
         return fs;
@@ -736,15 +760,44 @@ void __cleanup_sighand(struct sighand_struct *sighand)
                 kmem_cache_free(sighand_cachep, sighand);
 }
 
+
+/*
+ * Initialize POSIX timer handling for a thread group.
+ */
+static void posix_cpu_timers_init_group(struct signal_struct *sig)
+{
+        /* Thread group counters. */
+        thread_group_cputime_init(sig);
+
+        /* Expiration times and increments. */
+        sig->it_virt_expires = cputime_zero;
+        sig->it_virt_incr = cputime_zero;
+        sig->it_prof_expires = cputime_zero;
+        sig->it_prof_incr = cputime_zero;
+
+        /* Cached expiration times. */
+        sig->cputime_expires.prof_exp = cputime_zero;
+        sig->cputime_expires.virt_exp = cputime_zero;
+        sig->cputime_expires.sched_exp = 0;
+
+        /* The timer lists. */
+        INIT_LIST_HEAD(&sig->cpu_timers[0]);
+        INIT_LIST_HEAD(&sig->cpu_timers[1]);
+        INIT_LIST_HEAD(&sig->cpu_timers[2]);
+}
+
 static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 {
         struct signal_struct *sig;
         int ret;
 
         if (clone_flags & CLONE_THREAD) {
-                atomic_inc(&current->signal->count);
-                atomic_inc(&current->signal->live);
-                return 0;
+                ret = thread_group_cputime_clone_thread(current);
+                if (likely(!ret)) {
+                        atomic_inc(&current->signal->count);
+                        atomic_inc(&current->signal->live);
+                }
+                return ret;
         }
         sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL);
         tsk->signal = sig;
@@ -772,38 +825,25 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
         sig->it_real_incr.tv64 = 0;
         sig->real_timer.function = it_real_fn;
 
-        sig->it_virt_expires = cputime_zero;
-        sig->it_virt_incr = cputime_zero;
-        sig->it_prof_expires = cputime_zero;
-        sig->it_prof_incr = cputime_zero;
-
         sig->leader = 0;        /* session leadership doesn't inherit */
         sig->tty_old_pgrp = NULL;
+        sig->tty = NULL;
 
-        sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero;
+        sig->cutime = sig->cstime = cputime_zero;
         sig->gtime = cputime_zero;
         sig->cgtime = cputime_zero;
         sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0;
         sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0;
         sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0;
-        sig->sum_sched_runtime = 0;
-        INIT_LIST_HEAD(&sig->cpu_timers[0]);
-        INIT_LIST_HEAD(&sig->cpu_timers[1]);
-        INIT_LIST_HEAD(&sig->cpu_timers[2]);
+        task_io_accounting_init(&sig->ioac);
         taskstats_tgid_init(sig);
 
         task_lock(current->group_leader);
         memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim);
         task_unlock(current->group_leader);
 
-        if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) {
-                /*
-                 * New sole thread in the process gets an expiry time
-                 * of the whole CPU time limit.
-                 */
-                tsk->it_prof_expires =
-                        secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur);
-        }
+        posix_cpu_timers_init_group(sig);
+
         acct_init_pacct(&sig->pacct);
 
         tty_audit_fork(sig);
@@ -813,7 +853,9 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 
 void __cleanup_signal(struct signal_struct *sig)
 {
+        thread_group_cputime_free(sig);
         exit_thread_group_keys(sig);
+        tty_kref_put(sig->tty);
         kmem_cache_free(signal_cachep, sig);
 }
 
@@ -833,8 +875,7 @@ static void copy_flags(unsigned long clone_flags, struct task_struct *p)
 
         new_flags &= ~PF_SUPERPRIV;
         new_flags |= PF_FORKNOEXEC;
-        if (!(clone_flags & CLONE_PTRACE))
-                p->ptrace = 0;
+        new_flags |= PF_STARTING;
         p->flags = new_flags;
         clear_freeze_flag(p);
 }
@@ -863,6 +904,19 @@ void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
 #endif /* CONFIG_MM_OWNER */
 
 /*
+ * Initialize POSIX timer handling for a single task.
+ */
+static void posix_cpu_timers_init(struct task_struct *tsk)
+{
+        tsk->cputime_expires.prof_exp = cputime_zero;
+        tsk->cputime_expires.virt_exp = cputime_zero;
+        tsk->cputime_expires.sched_exp = 0;
+        INIT_LIST_HEAD(&tsk->cpu_timers[0]);
+        INIT_LIST_HEAD(&tsk->cpu_timers[1]);
+        INIT_LIST_HEAD(&tsk->cpu_timers[2]);
+}
+
+/*
  * This creates a new process as a copy of the old one,
  * but does not actually start it yet.
  *
@@ -875,7 +929,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
                                         struct pt_regs *regs,
                                         unsigned long stack_size,
                                         int __user *child_tidptr,
-                                        struct pid *pid)
+                                        struct pid *pid,
+                                        int trace)
 {
         int retval;
         struct task_struct *p;
@@ -963,26 +1018,17 @@ static struct task_struct *copy_process(unsigned long clone_flags,
         p->prev_utime = cputime_zero;
         p->prev_stime = cputime_zero;
 
+        p->default_timer_slack_ns = current->timer_slack_ns;
+
 #ifdef CONFIG_DETECT_SOFTLOCKUP
         p->last_switch_count = 0;
         p->last_switch_timestamp = 0;
 #endif
 
-#ifdef CONFIG_TASK_XACCT
-        p->rchar = 0;           /* I/O counter: bytes read */
-        p->wchar = 0;           /* I/O counter: bytes written */
-        p->syscr = 0;           /* I/O counter: read syscalls */
-        p->syscw = 0;           /* I/O counter: write syscalls */
-#endif
-        task_io_accounting_init(p);
+        task_io_accounting_init(&p->ioac);
         acct_clear_integrals(p);
 
-        p->it_virt_expires = cputime_zero;
-        p->it_prof_expires = cputime_zero;
-        p->it_sched_expires = 0;
-        INIT_LIST_HEAD(&p->cpu_timers[0]);
-        INIT_LIST_HEAD(&p->cpu_timers[1]);
-        INIT_LIST_HEAD(&p->cpu_timers[2]);
+        posix_cpu_timers_init(p);
 
         p->lock_depth = -1;             /* -1 = no lock */
         do_posix_clock_monotonic_gettime(&p->start_time);
@@ -1081,6 +1127,12 @@ static struct task_struct *copy_process(unsigned long clone_flags,
         if (clone_flags & CLONE_THREAD)
                 p->tgid = current->tgid;
 
+        if (current->nsproxy != p->nsproxy) {
+                retval = ns_cgroup_clone(p, pid);
+                if (retval)
+                        goto bad_fork_free_pid;
+        }
+
         p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
         /*
          * Clear TID on mm_release()?
@@ -1125,8 +1177,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
          */
         p->group_leader = p;
         INIT_LIST_HEAD(&p->thread_group);
-        INIT_LIST_HEAD(&p->ptrace_entry);
-        INIT_LIST_HEAD(&p->ptraced);
 
         /* Now that the task is set up, run cgroup callbacks if
          * necessary. We need to run them before the task is visible
@@ -1157,7 +1207,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
                 p->real_parent = current->real_parent;
         else
                 p->real_parent = current;
-        p->parent = p->real_parent;
 
         spin_lock(&current->sighand->siglock);
 
@@ -1180,34 +1229,19 @@ static struct task_struct *copy_process(unsigned long clone_flags,
         if (clone_flags & CLONE_THREAD) {
                 p->group_leader = current->group_leader;
                 list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group);
-
-                if (!cputime_eq(current->signal->it_virt_expires,
-                                cputime_zero) ||
-                    !cputime_eq(current->signal->it_prof_expires,
-                                cputime_zero) ||
-                    current->signal->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY ||
-                    !list_empty(&current->signal->cpu_timers[0]) ||
-                    !list_empty(&current->signal->cpu_timers[1]) ||
-                    !list_empty(&current->signal->cpu_timers[2])) {
-                        /*
-                         * Have child wake up on its first tick to check
-                         * for process CPU timers.
-                         */
-                        p->it_prof_expires = jiffies_to_cputime(1);
-                }
         }
 
         if (likely(p->pid)) {
                 list_add_tail(&p->sibling, &p->real_parent->children);
-                if (unlikely(p->ptrace & PT_PTRACED))
-                        __ptrace_link(p, current->parent);
+                tracehook_finish_clone(p, clone_flags, trace);
 
                 if (thread_group_leader(p)) {
                         if (clone_flags & CLONE_NEWPID)
                                 p->nsproxy->pid_ns->child_reaper = p;
 
                         p->signal->leader_pid = pid;
-                        p->signal->tty = current->signal->tty;
+                        tty_kref_put(p->signal->tty);
+                        p->signal->tty = tty_kref_get(current->signal->tty);
                         set_task_pgrp(p, task_pgrp_nr(current));
                         set_task_session(p, task_session_nr(current));
                         attach_pid(p, PIDTYPE_PGID, task_pgrp(current));
@@ -1285,29 +1319,13 @@ struct task_struct * __cpuinit fork_idle(int cpu)
         struct pt_regs regs;
 
         task = copy_process(CLONE_VM, 0, idle_regs(&regs), 0, NULL,
-                                &init_struct_pid);
+                            &init_struct_pid, 0);
         if (!IS_ERR(task))
                 init_idle(task, cpu);
 
         return task;
 }
 
-static int fork_traceflag(unsigned clone_flags)
-{
-        if (clone_flags & CLONE_UNTRACED)
-                return 0;
-        else if (clone_flags & CLONE_VFORK) {
-                if (current->ptrace & PT_TRACE_VFORK)
-                        return PTRACE_EVENT_VFORK;
-        } else if ((clone_flags & CSIGNAL) != SIGCHLD) {
-                if (current->ptrace & PT_TRACE_CLONE)
-                        return PTRACE_EVENT_CLONE;
-        } else if (current->ptrace & PT_TRACE_FORK)
-                return PTRACE_EVENT_FORK;
-
-        return 0;
-}
-
 /*
  *  Ok, this is the main fork-routine.
  *
@@ -1342,14 +1360,14 @@ long do_fork(unsigned long clone_flags,
                 }
         }
 
-        if (unlikely(current->ptrace)) {
-                trace = fork_traceflag (clone_flags);
-                if (trace)
-                        clone_flags |= CLONE_PTRACE;
-        }
+        /*
+         * When called from kernel_thread, don't do user tracing stuff.
+         */
+        if (likely(user_mode(regs)))
+                trace = tracehook_prepare_clone(clone_flags);
 
         p = copy_process(clone_flags, stack_start, regs, stack_size,
-                        child_tidptr, NULL);
+                         child_tidptr, NULL, trace);
         /*
          * Do this prior waking up the new thread - the thread pointer
          * might get invalid after that point, if the thread exits quickly.
@@ -1357,6 +1375,8 @@ long do_fork(unsigned long clone_flags,
         if (!IS_ERR(p)) {
                 struct completion vfork;
 
+                trace_sched_process_fork(current, p);
+
                 nr = task_pid_vnr(p);
 
                 if (clone_flags & CLONE_PARENT_SETTID)
@@ -1367,32 +1387,35 @@ long do_fork(unsigned long clone_flags,
                         init_completion(&vfork);
                 }
 
-                if ((p->ptrace & PT_PTRACED) || (clone_flags & CLONE_STOPPED)) {
+                tracehook_report_clone(trace, regs, clone_flags, nr, p);
+
+                /*
+                 * We set PF_STARTING at creation in case tracing wants to
+                 * use this to distinguish a fully live task from one that
+                 * hasn't gotten to tracehook_report_clone() yet.  Now we
+                 * clear it and set the child going.
+                 */
+                p->flags &= ~PF_STARTING;
+
+                if (unlikely(clone_flags & CLONE_STOPPED)) {
                         /*
                          * We'll start up with an immediate SIGSTOP.
                          */
                         sigaddset(&p->pending.signal, SIGSTOP);
                         set_tsk_thread_flag(p, TIF_SIGPENDING);
-                }
-
-                if (!(clone_flags & CLONE_STOPPED))
-                        wake_up_new_task(p, clone_flags);
-                else
                         __set_task_state(p, TASK_STOPPED);
-
-                if (unlikely (trace)) {
-                        current->ptrace_message = nr;
-                        ptrace_notify ((trace << 8) | SIGTRAP);
+                } else {
+                        wake_up_new_task(p, clone_flags);
                 }
 
+                tracehook_report_clone_complete(trace, regs,
+                                                clone_flags, nr, p);
+
                 if (clone_flags & CLONE_VFORK) {
                         freezer_do_not_count();
                         wait_for_completion(&vfork);
                         freezer_count();
-                        if (unlikely (current->ptrace & PT_TRACE_VFORK_DONE)) {
-                                current->ptrace_message = nr;
-                                ptrace_notify ((PTRACE_EVENT_VFORK_DONE << 8) | SIGTRAP);
-                        }
+                        tracehook_report_vfork_done(p, nr);
                 }
         } else {
                 nr = PTR_ERR(p);
@@ -1404,7 +1427,7 @@ long do_fork(unsigned long clone_flags,
 #define ARCH_MIN_MMSTRUCT_ALIGN 0
 #endif
 
-static void sighand_ctor(struct kmem_cache *cachep, void *data)
+static void sighand_ctor(void *data)
 {
         struct sighand_struct *sighand = data;