Merge branch 'vfs-scale-working' of git://git.kernel.org/pub/scm/linux/kernel/git/npiggin/linux-npiggin

* 'vfs-scale-working' of git://git.kernel.org/pub/scm/linux/kernel/git/npiggin/linux-npiggin: (57 commits)
  fs: scale mntget/mntput
  fs: rename vfsmount counter helpers
  fs: implement faster dentry memcmp
  fs: prefetch inode data in dcache lookup
  fs: improve scalability of pseudo filesystems
  fs: dcache per-inode inode alias locking
  fs: dcache per-bucket dcache hash locking
  bit_spinlock: add required includes
  kernel: add bl_list
  xfs: provide simple rcu-walk ACL implementation
  btrfs: provide simple rcu-walk ACL implementation
  ext2,3,4: provide simple rcu-walk ACL implementation
  fs: provide simple rcu-walk generic_check_acl implementation
  fs: provide rcu-walk aware permission i_ops
  fs: rcu-walk aware d_revalidate method
  fs: cache optimise dentry and inode for rcu-walk
  fs: dcache reduce branches in lookup path
  fs: dcache remove d_mounted
  fs: fs_struct use seqlock
  fs: rcu-walk for path lookup
  ...

4 files changed, 68 insertions, 29 deletions

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 08cba2c3b612..b20962c71a52 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1795,10 +1795,16 @@ static int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat
  */
 static int pid_revalidate(struct dentry *dentry, struct nameidata *nd)
 {
-        struct inode *inode = dentry->d_inode;
-        struct task_struct *task = get_proc_task(inode);
+        struct inode *inode;
+        struct task_struct *task;
         const struct cred *cred;
 
+        if (nd && nd->flags & LOOKUP_RCU)
+                return -ECHILD;
+
+        inode = dentry->d_inode;
+        task = get_proc_task(inode);
+
         if (task) {
                 if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) ||
                     task_dumpable(task)) {
@@ -1820,7 +1826,7 @@ static int pid_revalidate(struct dentry *dentry, struct nameidata *nd)
         return 0;
 }
 
-static int pid_delete_dentry(struct dentry * dentry)
+static int pid_delete_dentry(const struct dentry * dentry)
 {
         /* Is the task we represent dead?
          * If so, then don't put the dentry on the lru list,
@@ -1964,12 +1970,19 @@ static int proc_fd_link(struct inode *inode, struct path *path)
 
 static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd)
 {
-        struct inode *inode = dentry->d_inode;
-        struct task_struct *task = get_proc_task(inode);
-        int fd = proc_fd(inode);
+        struct inode *inode;
+        struct task_struct *task;
+        int fd;
         struct files_struct *files;
         const struct cred *cred;
 
+        if (nd && nd->flags & LOOKUP_RCU)
+                return -ECHILD;
+
+        inode = dentry->d_inode;
+        task = get_proc_task(inode);
+        fd = proc_fd(inode);
+
         if (task) {
                 files = get_files_struct(task);
                 if (files) {
@@ -2045,7 +2058,7 @@ static struct dentry *proc_fd_instantiate(struct inode *dir,
         inode->i_op = &proc_pid_link_inode_operations;
         inode->i_size = 64;
         ei->op.proc_get_link = proc_fd_link;
-        dentry->d_op = &tid_fd_dentry_operations;
+        d_set_d_op(dentry, &tid_fd_dentry_operations);
         d_add(dentry, inode);
         /* Close the race of the process dying before we return the dentry */
         if (tid_fd_revalidate(dentry, NULL))
@@ -2177,11 +2190,13 @@ static const struct file_operations proc_fd_operations = {
  * /proc/pid/fd needs a special permission handler so that a process can still
  * access /proc/self/fd after it has executed a setuid().
  */
-static int proc_fd_permission(struct inode *inode, int mask)
+static int proc_fd_permission(struct inode *inode, int mask, unsigned int flags)
 {
         int rv;
 
-        rv = generic_permission(inode, mask, NULL);
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
+        rv = generic_permission(inode, mask, flags, NULL);
         if (rv == 0)
                 return 0;
         if (task_pid(current) == proc_pid(inode))
@@ -2213,7 +2228,7 @@ static struct dentry *proc_fdinfo_instantiate(struct inode *dir,
         ei->fd = fd;
         inode->i_mode = S_IFREG | S_IRUSR;
         inode->i_fop = &proc_fdinfo_file_operations;
-        dentry->d_op = &tid_fd_dentry_operations;
+        d_set_d_op(dentry, &tid_fd_dentry_operations);
         d_add(dentry, inode);
         /* Close the race of the process dying before we return the dentry */
         if (tid_fd_revalidate(dentry, NULL))
@@ -2272,7 +2287,7 @@ static struct dentry *proc_pident_instantiate(struct inode *dir,
         if (p->fop)
                 inode->i_fop = p->fop;
         ei->op = p->op;
-        dentry->d_op = &pid_dentry_operations;
+        d_set_d_op(dentry, &pid_dentry_operations);
         d_add(dentry, inode);
         /* Close the race of the process dying before we return the dentry */
         if (pid_revalidate(dentry, NULL))
@@ -2639,8 +2654,14 @@ static const struct pid_entry proc_base_stuff[] = {
  */
 static int proc_base_revalidate(struct dentry *dentry, struct nameidata *nd)
 {
-        struct inode *inode = dentry->d_inode;
-        struct task_struct *task = get_proc_task(inode);
+        struct inode *inode;
+        struct task_struct *task;
+
+        if (nd->flags & LOOKUP_RCU)
+                return -ECHILD;
+
+        inode = dentry->d_inode;
+        task = get_proc_task(inode);
         if (task) {
                 put_task_struct(task);
                 return 1;
@@ -2691,7 +2712,7 @@ static struct dentry *proc_base_instantiate(struct inode *dir,
         if (p->fop)
                 inode->i_fop = p->fop;
         ei->op = p->op;
-        dentry->d_op = &proc_base_dentry_operations;
+        d_set_d_op(dentry, &proc_base_dentry_operations);
         d_add(dentry, inode);
         error = NULL;
 out:
@@ -3005,7 +3026,7 @@ static struct dentry *proc_pid_instantiate(struct inode *dir,
         inode->i_nlink = 2 + pid_entry_count_dirs(tgid_base_stuff,
                 ARRAY_SIZE(tgid_base_stuff));
 
-        dentry->d_op = &pid_dentry_operations;
+        d_set_d_op(dentry, &pid_dentry_operations);
 
         d_add(dentry, inode);
         /* Close the race of the process dying before we return the dentry */
@@ -3248,7 +3269,7 @@ static struct dentry *proc_task_instantiate(struct inode *dir,
         inode->i_nlink = 2 + pid_entry_count_dirs(tid_base_stuff,
                 ARRAY_SIZE(tid_base_stuff));
 
-        dentry->d_op = &pid_dentry_operations;
+        d_set_d_op(dentry, &pid_dentry_operations);
 
         d_add(dentry, inode);
         /* Close the race of the process dying before we return the dentry */
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index dd29f0337661..f766be29d2c7 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -400,7 +400,7 @@ static const struct inode_operations proc_link_inode_operations = {
  * smarter: we could keep a "volatile" flag in the 
  * inode to indicate which ones to keep.
  */
-static int proc_delete_dentry(struct dentry * dentry)
+static int proc_delete_dentry(const struct dentry * dentry)
 {
         return 1;
 }
@@ -439,7 +439,7 @@ struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir,
 out_unlock:
 
         if (inode) {
-                dentry->d_op = &proc_dentry_operations;
+                d_set_d_op(dentry, &proc_dentry_operations);
                 d_add(dentry, inode);
                 return NULL;
         }
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 3ddb6068177c..6bcb926b101b 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -65,11 +65,18 @@ static struct inode *proc_alloc_inode(struct super_block *sb)
         return inode;
 }
 
-static void proc_destroy_inode(struct inode *inode)
+static void proc_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(proc_inode_cachep, PROC_I(inode));
 }
 
+static void proc_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, proc_i_callback);
+}
+
 static void init_once(void *foo)
 {
         struct proc_inode *ei = (struct proc_inode *) foo;
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index b652cb00906b..09a1f92a34ef 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -5,6 +5,7 @@
 #include <linux/sysctl.h>
 #include <linux/proc_fs.h>
 #include <linux/security.h>
+#include <linux/namei.h>
 #include "internal.h"
 
 static const struct dentry_operations proc_sys_dentry_operations;
@@ -120,7 +121,7 @@ static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
                 goto out;
 
         err = NULL;
-        dentry->d_op = &proc_sys_dentry_operations;
+        d_set_d_op(dentry, &proc_sys_dentry_operations);
         d_add(dentry, inode);
 
 out:
@@ -201,7 +202,7 @@ static int proc_sys_fill_cache(struct file *filp, void *dirent,
                                 dput(child);
                                 return -ENOMEM;
                         } else {
-                                child->d_op = &proc_sys_dentry_operations;
+                                d_set_d_op(child, &proc_sys_dentry_operations);
                                 d_add(child, inode);
                         }
                 } else {
@@ -294,7 +295,7 @@ out:
         return ret;
 }
 
-static int proc_sys_permission(struct inode *inode, int mask)
+static int proc_sys_permission(struct inode *inode, int mask,unsigned int flags)
 {
         /*
          * sysctl entries that are not writeable,
@@ -304,6 +305,9 @@ static int proc_sys_permission(struct inode *inode, int mask)
         struct ctl_table *table;
         int error;
 
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
+
         /* Executable files are not allowed under /proc/sys/ */
         if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))
                 return -EACCES;
@@ -389,23 +393,30 @@ static const struct inode_operations proc_sys_dir_operations = {
 
 static int proc_sys_revalidate(struct dentry *dentry, struct nameidata *nd)
 {
+        if (nd->flags & LOOKUP_RCU)
+                return -ECHILD;
         return !PROC_I(dentry->d_inode)->sysctl->unregistering;
 }
 
-static int proc_sys_delete(struct dentry *dentry)
+static int proc_sys_delete(const struct dentry *dentry)
 {
         return !!PROC_I(dentry->d_inode)->sysctl->unregistering;
 }
 
-static int proc_sys_compare(struct dentry *dir, struct qstr *qstr,
-                            struct qstr *name)
+static int proc_sys_compare(const struct dentry *parent,
+                const struct inode *pinode,
+                const struct dentry *dentry, const struct inode *inode,
+                unsigned int len, const char *str, const struct qstr *name)
 {
-        struct dentry *dentry = container_of(qstr, struct dentry, d_name);
-        if (qstr->len != name->len)
+        /* Although proc doesn't have negative dentries, rcu-walk means
+         * that inode here can be NULL */
+        if (!inode)
+                return 0;
+        if (name->len != len)
                 return 1;
-        if (memcmp(qstr->name, name->name, name->len))
+        if (memcmp(name->name, str, len))
                 return 1;
-        return !sysctl_is_seen(PROC_I(dentry->d_inode)->sysctl);
+        return !sysctl_is_seen(PROC_I(inode)->sysctl);
 }
 
 static const struct dentry_operations proc_sys_dentry_operations = {