Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

10 files changed, 83 insertions, 197 deletions

diff --git a/kernel/audit.c b/kernel/audit.c
index b7d3709cc452..e8692a5748c2 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -572,16 +572,17 @@ void audit_send_reply(int pid, int seq, int type, int done, int multi,
 
         skb = audit_make_reply(pid, seq, type, done, multi, payload, size);
         if (!skb)
-                return;
+                goto out;
 
         reply->pid = pid;
         reply->skb = skb;
 
         tsk = kthread_run(audit_send_reply_thread, reply, "audit_send_reply");
-        if (IS_ERR(tsk)) {
-                kfree(reply);
-                kfree_skb(skb);
-        }
+        if (!IS_ERR(tsk))
+                return;
+        kfree_skb(skb);
+out:
+        kfree(reply);
 }
 
 /*
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 9ef5e0aacc3c..f7921a2ecf16 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -172,10 +172,9 @@ static void insert_hash(struct audit_chunk *chunk)
 struct audit_chunk *audit_tree_lookup(const struct inode *inode)
 {
         struct list_head *list = chunk_hash(inode);
-        struct list_head *pos;
+        struct audit_chunk *p;
 
-        list_for_each_rcu(pos, list) {
-                struct audit_chunk *p = container_of(pos, struct audit_chunk, hash);
+        list_for_each_entry_rcu(p, list, hash) {
                 if (p->watch.inode == inode) {
                         get_inotify_watch(&p->watch);
                         return p;
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 8da627d33804..86ea9e34e326 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1031,11 +1031,9 @@ int current_cpuset_is_being_rebound(void)
         return task_cs(current) == cpuset_being_rebound;
 }
 
-static int update_relax_domain_level(struct cpuset *cs, char *buf)
+static int update_relax_domain_level(struct cpuset *cs, s64 val)
 {
-        int val = simple_strtol(buf, NULL, 10);
-
-        if (val < 0)
+        if ((int)val < 0)
                 val = -1;
 
         if (val != cs->relax_domain_level) {
@@ -1280,9 +1278,6 @@ static ssize_t cpuset_common_file_write(struct cgroup *cont,
         case FILE_MEMLIST:
                 retval = update_nodemask(cs, buffer);
                 break;
-        case FILE_SCHED_RELAX_DOMAIN_LEVEL:
-                retval = update_relax_domain_level(cs, buffer);
-                break;
         default:
                 retval = -EINVAL;
                 goto out2;
@@ -1348,6 +1343,30 @@ static int cpuset_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val)
         return retval;
 }
 
+static int cpuset_write_s64(struct cgroup *cgrp, struct cftype *cft, s64 val)
+{
+        int retval = 0;
+        struct cpuset *cs = cgroup_cs(cgrp);
+        cpuset_filetype_t type = cft->private;
+
+        cgroup_lock();
+
+        if (cgroup_is_removed(cgrp)) {
+                cgroup_unlock();
+                return -ENODEV;
+        }
+        switch (type) {
+        case FILE_SCHED_RELAX_DOMAIN_LEVEL:
+                retval = update_relax_domain_level(cs, val);
+                break;
+        default:
+                retval = -EINVAL;
+                break;
+        }
+        cgroup_unlock();
+        return retval;
+}
+
 /*
  * These ascii lists should be read in a single call, by using a user
  * buffer large enough to hold the entire map.  If read in smaller
@@ -1406,9 +1425,6 @@ static ssize_t cpuset_common_file_read(struct cgroup *cont,
         case FILE_MEMLIST:
                 s += cpuset_sprintf_memlist(s, cs);
                 break;
-        case FILE_SCHED_RELAX_DOMAIN_LEVEL:
-                s += sprintf(s, "%d", cs->relax_domain_level);
-                break;
         default:
                 retval = -EINVAL;
                 goto out;
@@ -1449,6 +1465,18 @@ static u64 cpuset_read_u64(struct cgroup *cont, struct cftype *cft)
         }
 }
 
+static s64 cpuset_read_s64(struct cgroup *cont, struct cftype *cft)
+{
+        struct cpuset *cs = cgroup_cs(cont);
+        cpuset_filetype_t type = cft->private;
+        switch (type) {
+        case FILE_SCHED_RELAX_DOMAIN_LEVEL:
+                return cs->relax_domain_level;
+        default:
+                BUG();
+        }
+}
+
 
 /*
  * for the common functions, 'private' gives the type of file
@@ -1499,8 +1527,8 @@ static struct cftype files[] = {
 
         {
                 .name = "sched_relax_domain_level",
-                .read_u64 = cpuset_read_u64,
-                .write_u64 = cpuset_write_u64,
+                .read_s64 = cpuset_read_s64,
+                .write_s64 = cpuset_write_s64,
                 .private = FILE_SCHED_RELAX_DOMAIN_LEVEL,
         },
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 933e60ebccae..19908b26cf80 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -660,136 +660,6 @@ static int copy_fs(unsigned long clone_flags, struct task_struct *tsk)
         return 0;
 }
 
-static int count_open_files(struct fdtable *fdt)
-{
-        int size = fdt->max_fds;
-        int i;
-
-        /* Find the last open fd */
-        for (i = size/(8*sizeof(long)); i > 0; ) {
-                if (fdt->open_fds->fds_bits[--i])
-                        break;
-        }
-        i = (i+1) * 8 * sizeof(long);
-        return i;
-}
-
-static struct files_struct *alloc_files(void)
-{
-        struct files_struct *newf;
-        struct fdtable *fdt;
-
-        newf = kmem_cache_alloc(files_cachep, GFP_KERNEL);
-        if (!newf)
-                goto out;
-
-        atomic_set(&newf->count, 1);
-
-        spin_lock_init(&newf->file_lock);
-        newf->next_fd = 0;
-        fdt = &newf->fdtab;
-        fdt->max_fds = NR_OPEN_DEFAULT;
-        fdt->close_on_exec = (fd_set *)&newf->close_on_exec_init;
-        fdt->open_fds = (fd_set *)&newf->open_fds_init;
-        fdt->fd = &newf->fd_array[0];
-        INIT_RCU_HEAD(&fdt->rcu);
-        fdt->next = NULL;
-        rcu_assign_pointer(newf->fdt, fdt);
-out:
-        return newf;
-}
-
-/*
- * Allocate a new files structure and copy contents from the
- * passed in files structure.
- * errorp will be valid only when the returned files_struct is NULL.
- */
-static struct files_struct *dup_fd(struct files_struct *oldf, int *errorp)
-{
-        struct files_struct *newf;
-        struct file **old_fds, **new_fds;
-        int open_files, size, i;
-        struct fdtable *old_fdt, *new_fdt;
-
-        *errorp = -ENOMEM;
-        newf = alloc_files();
-        if (!newf)
-                goto out;
-
-        spin_lock(&oldf->file_lock);
-        old_fdt = files_fdtable(oldf);
-        new_fdt = files_fdtable(newf);
-        open_files = count_open_files(old_fdt);
-
-        /*
-         * Check whether we need to allocate a larger fd array and fd set.
-         * Note: we're not a clone task, so the open count won't change.
-         */
-        if (open_files > new_fdt->max_fds) {
-                new_fdt->max_fds = 0;
-                spin_unlock(&oldf->file_lock);
-                spin_lock(&newf->file_lock);
-                *errorp = expand_files(newf, open_files-1);
-                spin_unlock(&newf->file_lock);
-                if (*errorp < 0)
-                        goto out_release;
-                new_fdt = files_fdtable(newf);
-                /*
-                 * Reacquire the oldf lock and a pointer to its fd table
-                 * who knows it may have a new bigger fd table. We need
-                 * the latest pointer.
-                 */
-                spin_lock(&oldf->file_lock);
-                old_fdt = files_fdtable(oldf);
-        }
-
-        old_fds = old_fdt->fd;
-        new_fds = new_fdt->fd;
-
-        memcpy(new_fdt->open_fds->fds_bits,
-                old_fdt->open_fds->fds_bits, open_files/8);
-        memcpy(new_fdt->close_on_exec->fds_bits,
-                old_fdt->close_on_exec->fds_bits, open_files/8);
-
-        for (i = open_files; i != 0; i--) {
-                struct file *f = *old_fds++;
-                if (f) {
-                        get_file(f);
-                } else {
-                        /*
-                         * The fd may be claimed in the fd bitmap but not yet
-                         * instantiated in the files array if a sibling thread
-                         * is partway through open().  So make sure that this
-                         * fd is available to the new process.
-                         */
-                        FD_CLR(open_files - i, new_fdt->open_fds);
-                }
-                rcu_assign_pointer(*new_fds++, f);
-        }
-        spin_unlock(&oldf->file_lock);
-
-        /* compute the remainder to be cleared */
-        size = (new_fdt->max_fds - open_files) * sizeof(struct file *);
-
-        /* This is long word aligned thus could use a optimized version */
-        memset(new_fds, 0, size);
-
-        if (new_fdt->max_fds > open_files) {
-                int left = (new_fdt->max_fds-open_files)/8;
-                int start = open_files / (8 * sizeof(unsigned long));
-
-                memset(&new_fdt->open_fds->fds_bits[start], 0, left);
-                memset(&new_fdt->close_on_exec->fds_bits[start], 0, left);
-        }
-
-        return newf;
-
-out_release:
-        kmem_cache_free(files_cachep, newf);
-out:
-        return NULL;
-}
-
 static int copy_files(unsigned long clone_flags, struct task_struct * tsk)
 {
         struct files_struct *oldf, *newf;
diff --git a/kernel/kgdb.c b/kernel/kgdb.c
index 39e31a036f5b..14787de568b3 100644
--- a/kernel/kgdb.c
+++ b/kernel/kgdb.c
@@ -346,14 +346,6 @@ static void put_packet(char *buffer)
         }
 }
 
-static char *pack_hex_byte(char *pkt, u8 byte)
-{
-        *pkt++ = hexchars[byte >> 4];
-        *pkt++ = hexchars[byte & 0xf];
-
-        return pkt;
-}
-
 /*
  * Convert the memory pointed to by mem into hex, placing result in buf.
  * Return a pointer to the last char put in buf (null). May return an error.
diff --git a/kernel/module.c b/kernel/module.c
index 8e4528c9909f..f5e9491ef7ac 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -917,6 +917,10 @@ static int check_version(Elf_Shdr *sechdrs,
         if (!crc)
                 return 1;
 
+        /* No versions at all?  modprobe --force does this. */
+        if (versindex == 0)
+                return try_to_force_load(mod, symname) == 0;
+
         versions = (void *) sechdrs[versindex].sh_addr;
         num_versions = sechdrs[versindex].sh_size
                 / sizeof(struct modversion_info);
@@ -932,8 +936,9 @@ static int check_version(Elf_Shdr *sechdrs,
                 goto bad_version;
         }
 
-        if (!try_to_force_load(mod, symname))
-                return 1;
+        printk(KERN_WARNING "%s: no symbol version for %s\n",
+               mod->name, symname);
+        return 0;
 
 bad_version:
         printk("%s: disagrees about version of symbol %s\n",
@@ -952,11 +957,14 @@ static inline int check_modstruct_version(Elf_Shdr *sechdrs,
         return check_version(sechdrs, versindex, "struct_module", mod, crc);
 }
 
-/* First part is kernel version, which we ignore. */
-static inline int same_magic(const char *amagic, const char *bmagic)
+/* First part is kernel version, which we ignore if module has crcs. */
+static inline int same_magic(const char *amagic, const char *bmagic,
+                             bool has_crcs)
 {
-        amagic += strcspn(amagic, " ");
-        bmagic += strcspn(bmagic, " ");
+        if (has_crcs) {
+                amagic += strcspn(amagic, " ");
+                bmagic += strcspn(bmagic, " ");
+        }
         return strcmp(amagic, bmagic) == 0;
 }
 #else
@@ -976,7 +984,8 @@ static inline int check_modstruct_version(Elf_Shdr *sechdrs,
         return 1;
 }
 
-static inline int same_magic(const char *amagic, const char *bmagic)
+static inline int same_magic(const char *amagic, const char *bmagic,
+                             bool has_crcs)
 {
         return strcmp(amagic, bmagic) == 0;
 }
@@ -1869,7 +1878,7 @@ static struct module *load_module(void __user *umod,
                 err = try_to_force_load(mod, "magic");
                 if (err)
                         goto free_hdr;
-        } else if (!same_magic(modmagic, vermagic)) {
+        } else if (!same_magic(modmagic, vermagic, versindex)) {
                 printk(KERN_ERR "%s: version magic '%s' should be '%s'\n",
                        mod->name, modmagic, vermagic);
                 err = -ENOEXEC;
diff --git a/kernel/relay.c b/kernel/relay.c
index 7de644cdec43..bc24dcdc570f 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -1191,7 +1191,7 @@ static ssize_t relay_file_splice_read(struct file *in,
         ret = 0;
         spliced = 0;
 
-        while (len && !spliced) {
+        while (len) {
                 ret = subbuf_splice_actor(in, ppos, pipe, len, flags, &nonpad_ret);
                 if (ret < 0)
                         break;
diff --git a/kernel/sched.c b/kernel/sched.c
index 58fb8af15776..cfa222a91539 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4567,8 +4567,6 @@ EXPORT_SYMBOL(schedule);
 asmlinkage void __sched preempt_schedule(void)
 {
         struct thread_info *ti = current_thread_info();
-        struct task_struct *task = current;
-        int saved_lock_depth;
 
         /*
          * If there is a non-zero preempt_count or interrupts are disabled,
@@ -4579,16 +4577,7 @@ asmlinkage void __sched preempt_schedule(void)
 
         do {
                 add_preempt_count(PREEMPT_ACTIVE);
-
-                /*
-                 * We keep the big kernel semaphore locked, but we
-                 * clear ->lock_depth so that schedule() doesnt
-                 * auto-release the semaphore:
-                 */
-                saved_lock_depth = task->lock_depth;
-                task->lock_depth = -1;
                 schedule();
-                task->lock_depth = saved_lock_depth;
                 sub_preempt_count(PREEMPT_ACTIVE);
 
                 /*
@@ -4609,26 +4598,15 @@ EXPORT_SYMBOL(preempt_schedule);
 asmlinkage void __sched preempt_schedule_irq(void)
 {
         struct thread_info *ti = current_thread_info();
-        struct task_struct *task = current;
-        int saved_lock_depth;
 
         /* Catch callers which need to be fixed */
         BUG_ON(ti->preempt_count || !irqs_disabled());
 
         do {
                 add_preempt_count(PREEMPT_ACTIVE);
-
-                /*
-                 * We keep the big kernel semaphore locked, but we
-                 * clear ->lock_depth so that schedule() doesnt
-                 * auto-release the semaphore:
-                 */
-                saved_lock_depth = task->lock_depth;
-                task->lock_depth = -1;
                 local_irq_enable();
                 schedule();
                 local_irq_disable();
-                task->lock_depth = saved_lock_depth;
                 sub_preempt_count(PREEMPT_ACTIVE);
 
                 /*
@@ -5547,7 +5525,6 @@ static void __cond_resched(void)
         } while (need_resched());
 }
 
-#if !defined(CONFIG_PREEMPT) || defined(CONFIG_PREEMPT_VOLUNTARY)
 int __sched _cond_resched(void)
 {
         if (need_resched() && !(preempt_count() & PREEMPT_ACTIVE) &&
@@ -5558,7 +5535,6 @@ int __sched _cond_resched(void)
         return 0;
 }
 EXPORT_SYMBOL(_cond_resched);
-#endif
 
 /*
  * cond_resched_lock() - if a reschedule is pending, drop the given lock,
@@ -5853,8 +5829,11 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
         spin_unlock_irqrestore(&rq->lock, flags);
 
         /* Set the preempt count _outside_ the spinlocks! */
+#if defined(CONFIG_PREEMPT)
+        task_thread_info(idle)->preempt_count = (idle->lock_depth >= 0);
+#else
         task_thread_info(idle)->preempt_count = 0;
-
+#endif
         /*
          * The idle tasks have their own, simple scheduling class:
          */
@@ -9007,7 +8986,7 @@ static u64 cpu_shares_read_u64(struct cgroup *cgrp, struct cftype *cft)
 #endif
 
 #ifdef CONFIG_RT_GROUP_SCHED
-static ssize_t cpu_rt_runtime_write(struct cgroup *cgrp, struct cftype *cft,
+static int cpu_rt_runtime_write(struct cgroup *cgrp, struct cftype *cft,
                                 s64 val)
 {
         return sched_group_set_rt_runtime(cgroup_tg(cgrp), val);
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index c863663d204d..e24ecd39c4b8 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -662,10 +662,15 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
         if (!initial) {
                 /* sleeps upto a single latency don't count. */
                 if (sched_feat(NEW_FAIR_SLEEPERS)) {
+                        unsigned long thresh = sysctl_sched_latency;
+
+                        /*
+                         * convert the sleeper threshold into virtual time
+                         */
                         if (sched_feat(NORMALIZED_SLEEPER))
-                                vruntime -= calc_delta_weight(sysctl_sched_latency, se);
-                        else
-                                vruntime -= sysctl_sched_latency;
+                                thresh = calc_delta_fair(thresh, se);
+
+                        vruntime -= thresh;
                 }
 
                 /* ensure we never gain time by being placed backwards. */
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index d7ffdc59816a..29116652dca8 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -81,6 +81,7 @@ extern int compat_log;
 extern int maps_protect;
 extern int sysctl_stat_interval;
 extern int latencytop_enabled;
+extern int sysctl_nr_open_min, sysctl_nr_open_max;
 
 /* Constants used for minimum and  maximum */
 #if defined(CONFIG_DETECT_SOFTLOCKUP) || defined(CONFIG_HIGHMEM)
@@ -1190,7 +1191,9 @@ static struct ctl_table fs_table[] = {
                 .data           = &sysctl_nr_open,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = &proc_dointvec_minmax,
+                .extra1         = &sysctl_nr_open_min,
+                .extra2         = &sysctl_nr_open_max,
         },
         {
                 .ctl_name       = FS_DENTRY,