projects/linux·commit f1d38e42

Merge git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/sysctl

f1d38e42 · Linus Torvalds <[email protected]> · 2012-03-23 18:08:58 -07:00

Pull sysctl updates from Eric Biederman:

 - Rewrite of sysctl for speed and clarity.

   Insert/remove/Lookup in sysctl are all now O(NlogN) operations, and
   are no longer bottlenecks in the process of adding and removing
   network devices.

   sysctl is now focused on being a filesystem instead of system call
   and the code can all be found in fs/proc/proc_sysctl.c.  Hopefully
   this means the code is now approachable.

   Much thanks is owed to Lucian Grinjincu for keeping at this until
   something was found that was usable.

 - The recent proc_sys_poll oops found by the fuzzer during hibernation
   is fixed.

* git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/sysctl: (36 commits)
  sysctl: protect poll() in entries that may go away
  sysctl: Don't call sysctl_follow_link unless we are a link.
  sysctl: Comments to make the code clearer.
  sysctl: Correct error return from get_subdir
  sysctl: An easier to read version of find_subdir
  sysctl: fix memset parameters in setup_sysctl_set()
  sysctl: remove an unused variable
  sysctl: Add register_sysctl for normal sysctl users
  sysctl: Index sysctl directories with rbtrees.
  sysctl: Make the header lists per directory.
  sysctl: Move sysctl_check_dups into insert_header
  sysctl: Modify __register_sysctl_paths to take a set instead of a root and an nsproxy
  sysctl: Replace root_list with links between sysctl_table_sets.
  sysctl: Add sysctl_print_dir and use it in get_subdir
  sysctl: Stop requiring explicit management of sysctl directories
  sysctl: Add a root pointer to ctl_table_set
  sysctl: Rewrite proc_sys_readdir in terms of first_entry and next_entry
  sysctl: Rewrite proc_sys_lookup introducing find_entry and lookup_entry.
  sysctl: Normalize the root_table data structure.
  sysctl: Factor out insert_header and erase_header
  ...
Commit
f1d38e423a697b7aa06e12d3ca4753bcc1aa3531
Parents
dae430c6 · 4e474a00

Merge commit. Changes below are compared with the first parent: dae430c6.

Changes

8 files changed · +1280 −797

FileStatusAddDelContent
fs/proc/internal.hmodified+3−0View file
fs/proc/proc_sysctl.cmodified+1198−76View file
include/linux/sysctl.hmodified+67−39View file
kernel/Makefilemodified+0−1View file
kernel/sysctl.cmodified+3−498View file
kernel/sysctl_check.cdeleted+0−160View before deletion
lib/Kconfig.debugmodified+0−8View file
net/sysctl_net.cmodified+9−15View file

Only the first 600 diff lines are shown. Download the complete patch.

fs/proc/internal.h

View file
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index c44efe1..5f79bb8 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -10,12 +10,15 @@
*/
#include <linux/proc_fs.h>
+struct ctl_table_header;
extern struct proc_dir_entry proc_root;
#ifdef CONFIG_PROC_SYSCTL
extern int proc_sys_init(void);
+extern void sysctl_head_put(struct ctl_table_header *head);
#else
static inline void proc_sys_init(void) { }
+static inline void sysctl_head_put(struct ctl_table_header *head) { }
#endif
#ifdef CONFIG_NET
extern int proc_net_init(void);

fs/proc/proc_sysctl.c

View file
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 67bbf6e..21d836f 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -9,6 +9,7 @@
#include <linux/sched.h>
#include <linux/namei.h>
#include <linux/mm.h>
+#include <linux/module.h>
#include "internal.h"
static const struct dentry_operations proc_sys_dentry_operations;
@@ -26,6 +27,371 @@ void proc_sys_poll_notify(struct ctl_table_poll *poll)
wake_up_interruptible(&poll->wait);
}
+static struct ctl_table root_table[] = {
+ {
+ .procname = "",
+ .mode = S_IFDIR|S_IRUGO|S_IXUGO,
+ },
+ { }
+};
+static struct ctl_table_root sysctl_table_root = {
+ .default_set.dir.header = {
+ {{.count = 1,
+ .nreg = 1,
+ .ctl_table = root_table }},
+ .ctl_table_arg = root_table,
+ .root = &sysctl_table_root,
+ .set = &sysctl_table_root.default_set,
+ },
+};
+
+static DEFINE_SPINLOCK(sysctl_lock);
+
+static void drop_sysctl_table(struct ctl_table_header *header);
+static int sysctl_follow_link(struct ctl_table_header **phead,
+ struct ctl_table **pentry, struct nsproxy *namespaces);
+static int insert_links(struct ctl_table_header *head);
+static void put_links(struct ctl_table_header *header);
+
+static void sysctl_print_dir(struct ctl_dir *dir)
+{
+ if (dir->header.parent)
+ sysctl_print_dir(dir->header.parent);
+ printk(KERN_CONT "%s/", dir->header.ctl_table[0].procname);
+}
+
+static int namecmp(const char *name1, int len1, const char *name2, int len2)
+{
+ int minlen;
+ int cmp;
+
+ minlen = len1;
+ if (minlen > len2)
+ minlen = len2;
+
+ cmp = memcmp(name1, name2, minlen);
+ if (cmp == 0)
+ cmp = len1 - len2;
+ return cmp;
+}
+
+/* Called under sysctl_lock */
+static struct ctl_table *find_entry(struct ctl_table_header **phead,
+ struct ctl_dir *dir, const char *name, int namelen)
+{
+ struct ctl_table_header *head;
+ struct ctl_table *entry;
+ struct rb_node *node = dir->root.rb_node;
+
+ while (node)
+ {
+ struct ctl_node *ctl_node;
+ const char *procname;
+ int cmp;
+
+ ctl_node = rb_entry(node, struct ctl_node, node);
+ head = ctl_node->header;
+ entry = &head->ctl_table[ctl_node - head->node];
+ procname = entry->procname;
+
+ cmp = namecmp(name, namelen, procname, strlen(procname));
+ if (cmp < 0)
+ node = node->rb_left;
+ else if (cmp > 0)
+ node = node->rb_right;
+ else {
+ *phead = head;
+ return entry;
+ }
+ }
+ return NULL;
+}
+
+static int insert_entry(struct ctl_table_header *head, struct ctl_table *entry)
+{
+ struct rb_node *node = &head->node[entry - head->ctl_table].node;
+ struct rb_node **p = &head->parent->root.rb_node;
+ struct rb_node *parent = NULL;
+ const char *name = entry->procname;
+ int namelen = strlen(name);
+
+ while (*p) {
+ struct ctl_table_header *parent_head;
+ struct ctl_table *parent_entry;
+ struct ctl_node *parent_node;
+ const char *parent_name;
+ int cmp;
+
+ parent = *p;
+ parent_node = rb_entry(parent, struct ctl_node, node);
+ parent_head = parent_node->header;
+ parent_entry = &parent_head->ctl_table[parent_node - parent_head->node];
+ parent_name = parent_entry->procname;
+
+ cmp = namecmp(name, namelen, parent_name, strlen(parent_name));
+ if (cmp < 0)
+ p = &(*p)->rb_left;
+ else if (cmp > 0)
+ p = &(*p)->rb_right;
+ else {
+ printk(KERN_ERR "sysctl duplicate entry: ");
+ sysctl_print_dir(head->parent);
+ printk(KERN_CONT "/%s\n", entry->procname);
+ return -EEXIST;
+ }
+ }
+
+ rb_link_node(node, parent, p);
+ return 0;
+}
+
+static void erase_entry(struct ctl_table_header *head, struct ctl_table *entry)
+{
+ struct rb_node *node = &head->node[entry - head->ctl_table].node;
+
+ rb_erase(node, &head->parent->root);
+}
+
+static void init_header(struct ctl_table_header *head,
+ struct ctl_table_root *root, struct ctl_table_set *set,
+ struct ctl_node *node, struct ctl_table *table)
+{
+ head->ctl_table = table;
+ head->ctl_table_arg = table;
+ head->used = 0;
+ head->count = 1;
+ head->nreg = 1;
+ head->unregistering = NULL;
+ head->root = root;
+ head->set = set;
+ head->parent = NULL;
+ head->node = node;
+ if (node) {
+ struct ctl_table *entry;
+ for (entry = table; entry->procname; entry++, node++) {
+ rb_init_node(&node->node);
+ node->header = head;
+ }
+ }
+}
+
+static void erase_header(struct ctl_table_header *head)
+{
+ struct ctl_table *entry;
+ for (entry = head->ctl_table; entry->procname; entry++)
+ erase_entry(head, entry);
+}
+
+static int insert_header(struct ctl_dir *dir, struct ctl_table_header *header)
+{
+ struct ctl_table *entry;
+ int err;
+
+ dir->header.nreg++;
+ header->parent = dir;
+ err = insert_links(header);
+ if (err)
+ goto fail_links;
+ for (entry = header->ctl_table; entry->procname; entry++) {
+ err = insert_entry(header, entry);
+ if (err)
+ goto fail;
+ }
+ return 0;
+fail:
+ erase_header(header);
+ put_links(header);
+fail_links:
+ header->parent = NULL;
+ drop_sysctl_table(&dir->header);
+ return err;
+}
+
+/* called under sysctl_lock */
+static int use_table(struct ctl_table_header *p)
+{
+ if (unlikely(p->unregistering))
+ return 0;
+ p->used++;
+ return 1;
+}
+
+/* called under sysctl_lock */
+static void unuse_table(struct ctl_table_header *p)
+{
+ if (!--p->used)
+ if (unlikely(p->unregistering))
+ complete(p->unregistering);
+}
+
+/* called under sysctl_lock, will reacquire if has to wait */
+static void start_unregistering(struct ctl_table_header *p)
+{
+ /*
+ * if p->used is 0, nobody will ever touch that entry again;
+ * we'll eliminate all paths to it before dropping sysctl_lock
+ */
+ if (unlikely(p->used)) {
+ struct completion wait;
+ init_completion(&wait);
+ p->unregistering = &wait;
+ spin_unlock(&sysctl_lock);
+ wait_for_completion(&wait);
+ spin_lock(&sysctl_lock);
+ } else {
+ /* anything non-NULL; we'll never dereference it */
+ p->unregistering = ERR_PTR(-EINVAL);
+ }
+ /*
+ * do not remove from the list until nobody holds it; walking the
+ * list in do_sysctl() relies on that.
+ */
+ erase_header(p);
+}
+
+static void sysctl_head_get(struct ctl_table_header *head)
+{
+ spin_lock(&sysctl_lock);
+ head->count++;
+ spin_unlock(&sysctl_lock);
+}
+
+void sysctl_head_put(struct ctl_table_header *head)
+{
+ spin_lock(&sysctl_lock);
+ if (!--head->count)
+ kfree_rcu(head, rcu);
+ spin_unlock(&sysctl_lock);
+}
+
+static struct ctl_table_header *sysctl_head_grab(struct ctl_table_header *head)
+{
+ if (!head)
+ BUG();
+ spin_lock(&sysctl_lock);
+ if (!use_table(head))
+ head = ERR_PTR(-ENOENT);
+ spin_unlock(&sysctl_lock);
+ return head;
+}
+
+static void sysctl_head_finish(struct ctl_table_header *head)
+{
+ if (!head)
+ return;
+ spin_lock(&sysctl_lock);
+ unuse_table(head);
+ spin_unlock(&sysctl_lock);
+}
+
+static struct ctl_table_set *
+lookup_header_set(struct ctl_table_root *root, struct nsproxy *namespaces)
+{
+ struct ctl_table_set *set = &root->default_set;
+ if (root->lookup)
+ set = root->lookup(root, namespaces);
+ return set;
+}
+
+static struct ctl_table *lookup_entry(struct ctl_table_header **phead,
+ struct ctl_dir *dir,
+ const char *name, int namelen)
+{
+ struct ctl_table_header *head;
+ struct ctl_table *entry;
+
+ spin_lock(&sysctl_lock);
+ entry = find_entry(&head, dir, name, namelen);
+ if (entry && use_table(head))
+ *phead = head;
+ else
+ entry = NULL;
+ spin_unlock(&sysctl_lock);
+ return entry;
+}
+
+static struct ctl_node *first_usable_entry(struct rb_node *node)
+{
+ struct ctl_node *ctl_node;
+
+ for (;node; node = rb_next(node)) {
+ ctl_node = rb_entry(node, struct ctl_node, node);
+ if (use_table(ctl_node->header))
+ return ctl_node;
+ }
+ return NULL;
+}
+
+static void first_entry(struct ctl_dir *dir,
+ struct ctl_table_header **phead, struct ctl_table **pentry)
+{
+ struct ctl_table_header *head = NULL;
+ struct ctl_table *entry = NULL;
+ struct ctl_node *ctl_node;
+
+ spin_lock(&sysctl_lock);
+ ctl_node = first_usable_entry(rb_first(&dir->root));
+ spin_unlock(&sysctl_lock);
+ if (ctl_node) {
+ head = ctl_node->header;
+ entry = &head->ctl_table[ctl_node - head->node];
+ }
+ *phead = head;
+ *pentry = entry;
+}
+
+static void next_entry(struct ctl_table_header **phead, struct ctl_table **pentry)
+{
+ struct ctl_table_header *head = *phead;
+ struct ctl_table *entry = *pentry;
+ struct ctl_node *ctl_node = &head->node[entry - head->ctl_table];
+
+ spin_lock(&sysctl_lock);
+ unuse_table(head);
+
+ ctl_node = first_usable_entry(rb_next(&ctl_node->node));
+ spin_unlock(&sysctl_lock);
+ head = NULL;
+ if (ctl_node) {
+ head = ctl_node->header;
+ entry = &head->ctl_table[ctl_node - head->node];
+ }
+ *phead = head;
+ *pentry = entry;
+}
+
+void register_sysctl_root(struct ctl_table_root *root)
+{
+}
+
+/*
+ * sysctl_perm does NOT grant the superuser all rights automatically, because
+ * some sysctl variables are readonly even to root.
+ */
+
+static int test_perm(int mode, int op)
+{
+ if (!current_euid())
+ mode >>= 6;
+ else if (in_egroup_p(0))
+ mode >>= 3;
+ if ((op & ~mode & (MAY_READ|MAY_WRITE|MAY_EXEC)) == 0)
+ return 0;
+ return -EACCES;
+}
+
+static int sysctl_perm(struct ctl_table_root *root, struct ctl_table *table, int op)
+{
+ int mode;
+
+ if (root->permissions)
+ mode = root->permissions(root, current->nsproxy, table);
+ else
+ mode = table->mode;
+
+ return test_perm(mode, op);
+}
+
static struct inode *proc_sys_make_inode(struct super_block *sb,
struct ctl_table_header *head, struct ctl_table *table)
{
@@ -45,13 +411,12 @@ static struct inode *proc_sys_make_inode(struct super_block *sb,
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
inode->i_mode = table->mode;
- if (!table->child) {
+ if (!S_ISDIR(table->mode)) {
inode->i_mode |= S_IFREG;
inode->i_op = &proc_sys_inode_operations;
inode->i_fop = &proc_sys_file_operations;
} else {
inode->i_mode |= S_IFDIR;
- clear_nlink(inode);
inode->i_op = &proc_sys_dir_operations;
inode->i_fop = &proc_sys_dir_file_operations;
}
@@ -59,70 +424,42 @@ out:
return inode;
}
-static struct ctl_table *find_in_table(struct ctl_table *p, struct qstr *name)
-{
- int len;
- for ( ; p->procname; p++) {
-
- if (!p->procname)
- continue;
-
- len = strlen(p->procname);
- if (len != name->len)
- continue;
-
- if (memcmp(p->procname, name->name, len) != 0)
- continue;
-
- /* I have a match */
- return p;
- }
- return NULL;
-}
-
static struct ctl_table_header *grab_header(struct inode *inode)
{
- if (PROC_I(inode)->sysctl)
- return sysctl_head_grab(PROC_I(inode)->sysctl);
- else
- return sysctl_head_next(NULL);
+ struct ctl_table_header *head = PROC_I(inode)->sysctl;
+ if (!head)
+ head = &sysctl_table_root.default_set.dir.header;
+ return sysctl_head_grab(head);
}
static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
struct nameidata *nd)
{
struct ctl_table_header *head = grab_header(dir);
- struct ctl_table *table = PROC_I(dir)->sysctl_entry;
struct ctl_table_header *h = NULL;
struct qstr *name = &dentry->d_name;
struct ctl_table *p;
struct inode *inode;
struct dentry *err = ERR_PTR(-ENOENT);
+ struct ctl_dir *ctl_dir;
+ int ret;
if (IS_ERR(head))
return ERR_CAST(head);
- if (table && !table->child) {
- WARN_ON(1);
- goto out;
- }
-
- table = table ? table->child : head->ctl_table;
-
- p = find_in_table(table, name);
- if (!p) {
- for (h = sysctl_head_next(NULL); h; h = sysctl_head_next(h)) {
- if (h->attached_to != table)
- continue;
- p = find_in_table(h->attached_by, name);
- if (p)
- break;
- }
- }
+ ctl_dir = container_of(head, struct ctl_dir, header);
+ p = lookup_entry(&h, ctl_dir, name->name, name->len);
if (!p)
goto out;
+ if (S_ISLNK(p->mode)) {
+ ret = sysctl_follow_link(&h, &p, current->nsproxy);
+ err = ERR_PTR(ret);
+ if (ret)
+ goto out;
+ }
+
err = ERR_PTR(-ENOMEM);
inode = proc_sys_make_inode(dir->i_sb, h ? h : head, p);
if (h)
@@ -190,20 +527,32 @@ static ssize_t proc_sys_write(struct file *filp, const char __user *buf,
static int proc_sys_open(struct inode *inode, struct file *filp)
{
+ struct ctl_table_header *head = grab_header(inode);
struct ctl_table *table = PROC_I(inode)->sysctl_entry;
+ /* sysctl was unregistered */
+ if (IS_ERR(head))
+ return PTR_ERR(head);
+
if (table->poll)
filp->private_data = proc_sys_poll_event(table->poll);
+ sysctl_head_finish(head);
+
return 0;
}
static unsigned int proc_sys_poll(struct file *filp, poll_table *wait)
{
struct inode *inode = filp->f_path.dentry->d_inode;
+ struct ctl_table_header *head = grab_header(inode);
struct ctl_table *table = PROC_I(inode)->sysctl_entry;
- unsigned long event = (unsigned long)filp->private_data;
unsigned int ret = DEFAULT_POLLMASK;
+ unsigned long event;
+
+ /* sysctl was unregistered */
+ if (IS_ERR(head))
+ return POLLERR | POLLHUP;
if (!table->proc_handler)
goto out;
@@ -211,6 +560,7 @@ static unsigned int proc_sys_poll(struct file *filp, poll_table *wait)
if (!table->poll)
goto out;
+ event = (unsigned long)filp->private_data;
poll_wait(filp, &table->poll->wait, wait);
if (event != atomic_read(&table->poll->event)) {
@@ -219,6 +569,8 @@ static unsigned int proc_sys_poll(struct file *filp, poll_table *wait)
}
out:
+ sysctl_head_finish(head);
+
return ret;
}
@@ -260,28 +612,45 @@ static int proc_sys_fill_cache(struct file *filp, void *dirent,
return !!filldir(dirent, qname.name, qname.len, filp->f_pos, ino, type);
}
+static int proc_sys_link_fill_cache(struct file *filp, void *dirent,
+ filldir_t filldir,
+ struct ctl_table_header *head,
+ struct ctl_table *table)
+{
+ int err, ret = 0;
+ head = sysctl_head_grab(head);
+
+ if (S_ISLNK(table->mode)) {
+ /* It is not an error if we can not follow the link ignore it */
+ err = sysctl_follow_link(&head, &table, current->nsproxy);
+ if (err)
+ goto out;
+ }
+
+ ret = proc_sys_fill_cache(filp, dirent, filldir, head, table);
+out:
+ sysctl_head_finish(head);
+ return ret;
+}
+
static int scan(struct ctl_table_header *head, ctl_table *table,
unsigned long *pos, struct file *file,
void *dirent, filldir_t filldir)
{
+ int res;
- for (; table->procname; table++, (*pos)++) {
- int res;
-
- /* Can't do anything without a proc name */
- if (!table->procname)
- continue;
-
- if (*pos < file->f_pos)
- continue;
+ if ((*pos)++ < file->f_pos)
+ return 0;
+ if (unlikely(S_ISLNK(table->mode)))

This diff is incomplete. Download the complete patch.

include/linux/sysctl.h

View file

This diff is incomplete. Download the complete patch.

kernel/Makefile

View file

This diff is incomplete. Download the complete patch.

kernel/sysctl.c

View file

This diff is incomplete. Download the complete patch.

kernel/sysctl_check.c

View before deletion

This diff is incomplete. Download the complete patch.

lib/Kconfig.debug

View file

This diff is incomplete. Download the complete patch.

net/sysctl_net.c

View file

This diff is incomplete. Download the complete patch.