Merge commit 'v2.6.37-rc2' into sched/core

Merge reason: Move to a .37-rc base.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 106 insertions, 39 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 291ba3d04bea..66a416b42c18 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -52,7 +52,6 @@
 #include <linux/cgroupstats.h>
 #include <linux/hash.h>
 #include <linux/namei.h>
-#include <linux/smp_lock.h>
 #include <linux/pid_namespace.h>
 #include <linux/idr.h>
 #include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
@@ -244,6 +243,11 @@ static int notify_on_release(const struct cgroup *cgrp)
         return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
 }
 
+static int clone_children(const struct cgroup *cgrp)
+{
+        return test_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+}
+
 /*
  * for_each_subsys() allows you to iterate on each subsystem attached to
  * an active hierarchy
@@ -778,6 +782,7 @@ static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb)
         struct inode *inode = new_inode(sb);
 
         if (inode) {
+                inode->i_ino = get_next_ino();
                 inode->i_mode = mode;
                 inode->i_uid = current_fsuid();
                 inode->i_gid = current_fsgid();
@@ -1040,6 +1045,8 @@ static int cgroup_show_options(struct seq_file *seq, struct vfsmount *vfs)
                 seq_puts(seq, ",noprefix");
         if (strlen(root->release_agent_path))
                 seq_printf(seq, ",release_agent=%s", root->release_agent_path);
+        if (clone_children(&root->top_cgroup))
+                seq_puts(seq, ",clone_children");
         if (strlen(root->name))
                 seq_printf(seq, ",name=%s", root->name);
         mutex_unlock(&cgroup_mutex);
@@ -1050,6 +1057,7 @@ struct cgroup_sb_opts {
         unsigned long subsys_bits;
         unsigned long flags;
         char *release_agent;
+        bool clone_children;
         char *name;
         /* User explicitly requested empty subsystem */
         bool none;
@@ -1066,7 +1074,8 @@ struct cgroup_sb_opts {
  */
 static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 {
-        char *token, *o = data ?: "all";
+        char *token, *o = data;
+        bool all_ss = false, one_ss = false;
         unsigned long mask = (unsigned long)-1;
         int i;
         bool module_pin_failed = false;
@@ -1082,22 +1091,27 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
         while ((token = strsep(&o, ",")) != NULL) {
                 if (!*token)
                         return -EINVAL;
-                if (!strcmp(token, "all")) {
-                        /* Add all non-disabled subsystems */
-                        opts->subsys_bits = 0;
-                        for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
-                                struct cgroup_subsys *ss = subsys[i];
-                                if (ss == NULL)
-                                        continue;
-                                if (!ss->disabled)
-                                        opts->subsys_bits |= 1ul << i;
-                        }
-                } else if (!strcmp(token, "none")) {
+                if (!strcmp(token, "none")) {
                         /* Explicitly have no subsystems */
                         opts->none = true;
-                } else if (!strcmp(token, "noprefix")) {
+                        continue;
+                }
+                if (!strcmp(token, "all")) {
+                        /* Mutually exclusive option 'all' + subsystem name */
+                        if (one_ss)
+                                return -EINVAL;
+                        all_ss = true;
+                        continue;
+                }
+                if (!strcmp(token, "noprefix")) {
                         set_bit(ROOT_NOPREFIX, &opts->flags);
-                } else if (!strncmp(token, "release_agent=", 14)) {
+                        continue;
+                }
+                if (!strcmp(token, "clone_children")) {
+                        opts->clone_children = true;
+                        continue;
+                }
+                if (!strncmp(token, "release_agent=", 14)) {
                         /* Specifying two release agents is forbidden */
                         if (opts->release_agent)
                                 return -EINVAL;
@@ -1105,7 +1119,9 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
                                 kstrndup(token + 14, PATH_MAX - 1, GFP_KERNEL);
                         if (!opts->release_agent)
                                 return -ENOMEM;
-                } else if (!strncmp(token, "name=", 5)) {
+                        continue;
+                }
+                if (!strncmp(token, "name=", 5)) {
                         const char *name = token + 5;
                         /* Can't specify an empty name */
                         if (!strlen(name))
@@ -1127,20 +1143,44 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
                                               GFP_KERNEL);
                         if (!opts->name)
                                 return -ENOMEM;
-                } else {
-                        struct cgroup_subsys *ss;
-                        for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
-                                ss = subsys[i];
-                                if (ss == NULL)
-                                        continue;
-                                if (!strcmp(token, ss->name)) {
-                                        if (!ss->disabled)
-                                                set_bit(i, &opts->subsys_bits);
-                                        break;
-                                }
-                        }
-                        if (i == CGROUP_SUBSYS_COUNT)
-                                return -ENOENT;
+
+                        continue;
+                }
+
+                for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+                        struct cgroup_subsys *ss = subsys[i];
+                        if (ss == NULL)
+                                continue;
+                        if (strcmp(token, ss->name))
+                                continue;
+                        if (ss->disabled)
+                                continue;
+
+                        /* Mutually exclusive option 'all' + subsystem name */
+                        if (all_ss)
+                                return -EINVAL;
+                        set_bit(i, &opts->subsys_bits);
+                        one_ss = true;
+
+                        break;
+                }
+                if (i == CGROUP_SUBSYS_COUNT)
+                        return -ENOENT;
+        }
+
+        /*
+         * If the 'all' option was specified select all the subsystems,
+         * otherwise 'all, 'none' and a subsystem name options were not
+         * specified, let's default to 'all'
+         */
+        if (all_ss || (!all_ss && !one_ss && !opts->none)) {
+                for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+                        struct cgroup_subsys *ss = subsys[i];
+                        if (ss == NULL)
+                                continue;
+                        if (ss->disabled)
+                                continue;
+                        set_bit(i, &opts->subsys_bits);
                 }
         }
 
@@ -1222,7 +1262,6 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
         struct cgroup *cgrp = &root->top_cgroup;
         struct cgroup_sb_opts opts;
 
-        lock_kernel();
         mutex_lock(&cgrp->dentry->d_inode->i_mutex);
         mutex_lock(&cgroup_mutex);
 
@@ -1255,7 +1294,6 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
         kfree(opts.name);
         mutex_unlock(&cgroup_mutex);
         mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
-        unlock_kernel();
         return ret;
 }
 
@@ -1357,6 +1395,8 @@ static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts)
                 strcpy(root->release_agent_path, opts->release_agent);
         if (opts->name)
                 strcpy(root->name, opts->name);
+        if (opts->clone_children)
+                set_bit(CGRP_CLONE_CHILDREN, &root->top_cgroup.flags);
         return root;
 }
 
@@ -1420,9 +1460,9 @@ static int cgroup_get_rootdir(struct super_block *sb)
         return 0;
 }
 
-static int cgroup_get_sb(struct file_system_type *fs_type,
+static struct dentry *cgroup_mount(struct file_system_type *fs_type,
                          int flags, const char *unused_dev_name,
-                         void *data, struct vfsmount *mnt)
+                         void *data)
 {
         struct cgroup_sb_opts opts;
         struct cgroupfs_root *root;
@@ -1556,10 +1596,9 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
                 drop_parsed_module_refcounts(opts.subsys_bits);
         }
 
-        simple_set_mnt(mnt, sb);
         kfree(opts.release_agent);
         kfree(opts.name);
-        return 0;
+        return dget(sb->s_root);
 
  drop_new_super:
         deactivate_locked_super(sb);
@@ -1568,8 +1607,7 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
  out_err:
         kfree(opts.release_agent);
         kfree(opts.name);
-
-        return ret;
+        return ERR_PTR(ret);
 }
 
 static void cgroup_kill_sb(struct super_block *sb) {
@@ -1619,7 +1657,7 @@ static void cgroup_kill_sb(struct super_block *sb) {
 
 static struct file_system_type cgroup_fs_type = {
         .name = "cgroup",
-        .get_sb = cgroup_get_sb,
+        .mount = cgroup_mount,
         .kill_sb = cgroup_kill_sb,
 };
 
@@ -1883,6 +1921,8 @@ static int cgroup_release_agent_write(struct cgroup *cgrp, struct cftype *cft,
                                       const char *buffer)
 {
         BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX);
+        if (strlen(buffer) >= PATH_MAX)
+                return -EINVAL;
         if (!cgroup_lock_live_group(cgrp))
                 return -ENODEV;
         strcpy(cgrp->root->release_agent_path, buffer);
@@ -3176,6 +3216,23 @@ fail:
         return ret;
 }
 
+static u64 cgroup_clone_children_read(struct cgroup *cgrp,
+                                    struct cftype *cft)
+{
+        return clone_children(cgrp);
+}
+
+static int cgroup_clone_children_write(struct cgroup *cgrp,
+                                     struct cftype *cft,
+                                     u64 val)
+{
+        if (val)
+                set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+        else
+                clear_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+        return 0;
+}
+
 /*
  * for the common functions, 'private' gives the type of file
  */
@@ -3206,6 +3263,11 @@ static struct cftype files[] = {
                 .write_string = cgroup_write_event_control,
                 .mode = S_IWUGO,
         },
+        {
+                .name = "cgroup.clone_children",
+                .read_u64 = cgroup_clone_children_read,
+                .write_u64 = cgroup_clone_children_write,
+        },
 };
 
 static struct cftype cft_release_agent = {
@@ -3335,6 +3397,9 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
         if (notify_on_release(parent))
                 set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
 
+        if (clone_children(parent))
+                set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+
         for_each_subsys(root, ss) {
                 struct cgroup_subsys_state *css = ss->create(ss, cgrp);
 
@@ -3349,6 +3414,8 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
                                 goto err_destroy;
                 }
                 /* At error, ->destroy() callback has to free assigned ID. */
+                if (clone_children(parent) && ss->post_clone)
+                        ss->post_clone(ss, cgrp);
         }
 
         cgroup_lock_hierarchy(root);