vfs: don't do RCU lookup of empty pathnames

Normal pathname lookup doesn't allow empty pathnames, but using
AT_EMPTY_PATH (with name_to_handle_at() or fstatat(), for example) you
can trigger an empty pathname lookup.

And not only is the RCU lookup in that case entirely unnecessary
(because we'll obviously immediately finalize the end result), it is
actively wrong.

Why? An empth path is a special case that will return the original
'dirfd' dentry - and that dentry may not actually be RCU-free'd,
resulting in a potential use-after-free if we were to initialize the
path lazily under the RCU read lock and depend on complete_walk()
finalizing the dentry.

Found by syzkaller and KASAN.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Reported-by: Vegard Nossum <vegard.nossum@gmail.com>
Acked-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

0 files changed, 0 insertions, 0 deletions

path: root/tools/perf/scripts/python/call-graph-from-postgresql.py

/*
 *	Generic address resolution entity
 *
 *	Authors:
 *	Pedro Roque		<roque@di.fc.ul.pt>
 *	Alexey Kuznetsov	<kuznet@ms2.inr.ac.ru>
 *
 *	This program is free software; you can redistribute it and/or
 *      modify it under the terms of the GNU General Public License
 *      as published by the Free Software Foundation; either version
 *      2 of the License, or (at your option) any later version.
 *
 *	Fixes:
 *	Vitaly E. Lavrov	releasing NULL neighbor in neigh_add.
 *	Harald Welte		Add neighbour cache statistics like rtstat
 */

#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/socket.h>
#include <linux/netdevice.h>
#include <linux/proc_fs.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
#include <linux/times.h>
#include <net/neighbour.h>
#include <net/dst.h>
#include <net/sock.h>
#include <net/netevent.h>
#include <net/netlink.h>
#include <linux/rtnetlink.h>
#include <linux/random.h>
#include <linux/string.h>

#define NEIGH_DEBUG 1

#define NEIGH_PRINTK(x...) printk(x)
#define NEIGH_NOPRINTK(x...) do { ; } while(0)
#define NEIGH_PRINTK0 NEIGH_PRINTK
#define NEIGH_PRINTK1 NEIGH_NOPRINTK
#define NEIGH_PRINTK2 NEIGH_NOPRINTK

#if NEIGH_DEBUG >= 1
#undef NEIGH_PRINTK1
#define NEIGH_PRINTK1 NEIGH_PRINTK
#endif
#if NEIGH_DEBUG >= 2
#undef NEIGH_PRINTK2
#define NEIGH_PRINTK2 NEIGH_PRINTK
#endif

#define PNEIGH_HASHMASK		0xF

static void neigh_timer_handler(unsigned long arg);
#ifdef CONFIG_ARPD
static void neigh_app_notify(struct neighbour *n);
#endif
static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev);
void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev);

static struct neigh_table *neigh_tables;
#ifdef CONFIG_PROC_FS
static const struct file_operations neigh_stat_seq_fops;
#endif

/*
   Neighbour hash table buckets are protected with rwlock tbl->lock.

   - All the scans/updates to hash buckets MUST be made under this lock.
   - NOTHING clever should be made under this lock: no callbacks
     to protocol backends, no attempts to send something to network.
     It will result in deadlocks, if backend/driver wants to use neighbour
     cache.
   - If the entry requires some non-trivial actions, increase
     its reference count and release table lock.

   Neighbour entries are protected:
   - with reference count.
   - with rwlock neigh->lock

   Reference count prevents destruction.

   neigh->lock mainly serializes ll address data and its validity state.
   However, the same lock is used to protect another entry fields:
    - timer
    - resolution queue

   Again, nothing clever shall be made under neigh->lock,
   the most complicated procedure, which we allow is dev->hard_header.
   It is supposed, that dev->hard_header is simplistic and does
   not make callbacks to neighbour tables.

   The last lock is neigh_tbl_lock. It is pure SMP lock, protecting
   list of neighbour tables. This list is used only in process context,
 */

static DEFINE_RWLOCK(neigh_tbl_lock);

static int neigh_blackhole(struct sk_buff *skb)
{
	kfree_skb(skb);
	return -ENETDOWN;
}

/*
 * It is random distribution in the interval (1/2)*base...(3/2)*base.
 * It corresponds to default IPv6 settings and is not overridable,
 * because it is really reasonable choice.
 */

unsigned long neigh_rand_reach_time(unsigned long base)
{
	return (base ? (net_random() % base) + (base >> 1) : 0);
}


static int neigh_forced_gc(struct neigh_table *tbl)
{
	int shrunk = 0;
	int i;

	NEIGH_CACHE_STAT_INC(tbl, forced_gc_runs);

	write_lock_bh(&tbl->lock);
	for (i = 0; i <= tbl->hash_mask; i++) {
		struct neighbour *n, **np;

		np = &tbl->hash_buckets[i];
		while ((n = *np) != NULL) {
			/* Neighbour record may be discarded if:
			 * - nobody refers to it.
			 * - it is not permanent
			 */
			write_lock(&n->lock);
			if (atomic_read(&n->refcnt) == 1 &&
			    !(n->nud_state & NUD_PERMANENT)) {
				*np	= n->next;
				n->dead = 1;
				shrunk	= 1;
				write_unlock(&n->lock);
				if (n->parms->neigh_cleanup)
					n->parms->neigh_cleanup(n);
				neigh_release(n);
				continue;
			}
			write_unlock(&n->lock);
			np = &n->next;
		}
	}

	tbl->last_flush = jiffies;

	write_unlock_bh(&tbl->lock);

	return shrunk;
}

static int neigh_del_timer(struct neighbour *n)
{
	if ((n->nud_state & NUD_IN_TIMER) &&
	    del_timer(&n->timer)) {
		neigh_release(n);
		return 1;
	}
	return 0;
}

static void pneigh_queue_purge(struct sk_buff_head *list)
{
	struct sk_buff *skb;

	while ((skb = skb_dequeue(list)) != NULL) {
		dev_put(skb->dev);
		kfree_skb(skb);
	}
}

static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev)
{
	int i;

	for (i = 0; i <= tbl->hash_mask; i++) {
		struct neighbour *n, **np = &tbl->hash_buckets[i];

		while ((n = *np) != NULL) {
			if (dev && n->dev != dev) {
				np = &n->next;
				continue;
			}
			*np = n->next;
			write_lock(&n->lock);
			neigh_del_timer(n);
			n->dead = 1;

			if (atomic_read(&n->refcnt) != 1) {
				/* The most unpleasant situation.
				   We must destroy neighbour entry,
				   but someone still uses it.

				   The destroy will be delayed until
				   the last user releases us, but
				   we must kill timers etc. and move
				   it to safe state.
				 */
				skb_queue_purge(&n->arp_queue);
				n->output = neigh_blackhole;
				if (n->nud_state & NUD_VALID)
					n->nud_state = NUD_NOARP;
				else
					n->nud_state = NUD_NONE;
				NEIGH_PRINTK2("neigh %p is stray.\n", n);
			}
			write_unlock(&n->lock);
			if (n->parms->neigh_cleanup)
				n->parms->neigh_cleanup(n);
			neigh_release(n);
		}
	}
}

void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev)
{
	write_lock_bh(&tbl->lock);
	neigh_flush_dev(tbl, dev);
	write_unlock_bh(&tbl->lock);
}

int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
{
	write_lock_bh(&tbl->lock);
	neigh_flush_dev(tbl, dev);
	pneigh_ifdown(tbl, dev);
	write_unlock_bh(&tbl->lock);

	del_timer_sync(&tbl->proxy_timer);
	pneigh_queue_purge(&tbl->proxy_queue);
	return 0;
}

static struct neighbour *neigh_alloc(struct neigh_table *tbl)
{
	struct neighbour *n = NULL;
	unsigned long now = jiffies;
	int entries;

	entries = atomic_inc_return(&tbl->entries) - 1;
	if (entries >= tbl->gc_thresh3 ||
	    (entries >= tbl->gc_thresh2 &&
	     time_after(now, tbl->last_flush + 5 * HZ))) {
		if (!neigh_forced_gc(tbl) &&
		    entries >= tbl->gc_thresh3)
			goto out_entries;
	}

	n = kmem_cache_zalloc(tbl->kmem_cachep, GFP_ATOMIC);
	if (!n)
		goto out_entries;

	skb_queue_head_init(&n->arp_queue);
	rwlock_init(&n->lock);
	n->updated	  = n->used = now;
	n->nud_state	  = NUD_NONE;
	n->output	  = neigh_blackhole;
	n->parms	  = neigh_parms_clone(&tbl->parms);
	init_timer(&n->timer);
	n->timer.function = neigh_timer_handler;
	n->timer.data	  = (unsigned long)n;

	NEIGH_CACHE_STAT_INC(tbl, allocs);
	n->tbl		  = tbl;
	atomic_set(&n->refcnt, 1);
	n->dead		  = 1;
out:
	return n;

out_entries:
	atomic_dec(&tbl->entries);
	goto out;
}

static struct neighbour **neigh_hash_alloc(unsigned int entries)
{
	unsigned long size = entries * sizeof(struct neighbour *);
	struct neighbour **ret;

	if (size <= PAGE_SIZE) {
		ret = kzalloc(size, GFP_ATOMIC);
	} else {
		ret = (struct neighbour **)
		      __get_free_pages(GFP_ATOMIC|__GFP_ZERO, get_order(size));
	}
	return ret;
}

static void neigh_hash_free(struct neighbour **hash, unsigned int entries)
{
	unsigned long size = entries * sizeof(struct neighbour *);

	if (size <= PAGE_SIZE)
		kfree(hash);
	else
		free_pages((unsigned long)hash, get_order(size));
}

static void neigh_hash_grow(struct neigh_table *tbl, unsigned long new_entries)
{
	struct neighbour **new_hash, **old_hash;
	unsigned int i, new_hash_mask, old_entries;

	NEIGH_CACHE_STAT_INC(tbl, hash_grows);

	BUG_ON(new_entries & (new_entries - 1));
	new_hash = neigh_hash_alloc(new_entries);
	if (!new_hash)
		return;

	old_entries = tbl->hash_mask + 1;
	new_hash_mask = new_entries - 1;
	old_hash = tbl->hash_buckets;

	get_random_bytes(&tbl->hash_rnd, sizeof(tbl->hash_rnd));
	for (i = 0; i < old_entries; i++) {
		struct neighbour *n, *next;

		for (n = old_hash[i]; n; n = next) {
			unsigned int hash_val = tbl->hash(n->primary_key, n->dev);

			hash_val &= new_hash_mask;
			next = n->next;

			n->next = new_hash[hash_val];
			new_hash[hash_val] = n;
		}
	}
	tbl->hash_buckets = new_hash;
	tbl->hash_mask = new_hash_mask;

	neigh_hash_free(old_hash, old_entries);
}

struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey,
			       struct net_device *dev)
{
	struct neighbour *n;
	int key_len = tbl->key_len;
	u32 hash_val = tbl->hash(pkey, dev);

	NEIGH_CACHE_STAT_INC(tbl, lookups);

	read_lock_bh(&tbl->lock);
	for (n = tbl->hash_buckets[hash_val & tbl->hash_mask]; n; n = n->next) {
		if (dev == n->dev && !memcmp(n->primary_key, pkey, key_len)) {
			neigh_hold(n);
			NEIGH_CACHE_STAT_INC(tbl, hits);
			break;
		}
	}
	read_unlock_bh(&tbl->lock);
	return n;
}

struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, const void *pkey)
{
	struct neighbour *n;
	int key_len = tbl->key_len;
	u32 hash_val = tbl->hash(pkey, NULL);

	NEIGH_CACHE_STAT_INC(tbl, lookups);

	read_lock_bh(&tbl->lock);
	for (n = tbl->hash_buckets[hash_val & tbl->hash_mask]; n; n = n->next) {
		if (!memcmp(n->primary_key, pkey, key_len)) {
			neigh_hold(n);
			NEIGH_CACHE_STAT_INC(tbl, hits);
			break;
		}
	}
	read_unlock_bh(&tbl->lock);
	return n;
}

struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey,
			       struct net_device *dev)
{
	u32 hash_val;
	int key_len = tbl->key_len;
	int error;
	struct neighbour *n1, *rc, *n = neigh_alloc(tbl);

	if (!n) {
		rc = ERR_PTR(-ENOBUFS);
		goto out;
	}

	memcpy(n->primary_key, pkey, key_len);
	n->dev = dev;
	dev_hold(dev);

	/* Protocol specific setup. */
	if (tbl->constructor &&	(error = tbl->constructor(n)) < 0) {
		rc = ERR_PTR(error);
		goto out_neigh_release;
	}

	/* Device specific setup. */
	if (n->parms->neigh_setup &&
	    (error = n->parms->neigh_setup(n)) < 0) {
		rc = ERR_PTR(error);
		goto out_neigh_release;
	}

	n->confirmed = jiffies - (n->parms->base_reachable_time << 1);

	write_lock_bh(&tbl->lock);

	if (atomic_read(&tbl->entries) > (tbl->hash_mask + 1))
		neigh_hash_grow(tbl, (tbl->hash_mask + 1) << 1);

	hash_val = tbl->hash(pkey, dev) & tbl->hash_mask;

	if (n->parms->dead) {
		rc = ERR_PTR(-EINVAL);
		goto out_tbl_unlock;
	}

	for (n1 = tbl->hash_buckets[hash_val]; n1; n1 = n1->next) {
		if (dev == n1->dev && !memcmp(n1->primary_key, pkey, key_len)) {
			neigh_hold(n1);
			rc = n1;
			goto out_tbl_unlock;
		}
	}

	n->next = tbl->hash_buckets[hash_val];
	tbl->hash_buckets[hash_val] = n;
	n->dead = 0;
	neigh_hold(n);
	write_unlock_bh(&tbl->lock);
	NEIGH_PRINTK2("neigh %p is created.\n", n);
	rc = n;
out:
	return rc;
out_tbl_unlock:
	write_unlock_bh(&tbl->lock);
out_neigh_release:
	neigh_release(n);
	goto out;
}

struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl, const void *pkey,
				    struct net_device *dev, int creat)
{
	struct pneigh_entry *n;
	int key_len = tbl->key_len;
	u32 hash_val = *(u32 *)(pkey + key_len - 4);

	hash_val ^= (hash_val >> 16);
	hash_val ^= hash_val >> 8;
	hash_val ^= hash_val >> 4;
	hash_val &= PNEIGH_HASHMASK;

	read_lock_bh(&tbl->lock);

	for (n = tbl->phash_buckets[hash_val]; n; n = n->next) {
		if (!memcmp(n->key, pkey, key_len) &&
		    (n->dev == dev || !n->dev)) {
			read_unlock_bh(&tbl->lock);
			goto out;
		}
	}
	read_unlock_bh(&tbl->lock);
	n = NULL;
	if (!creat)
		goto out;

	n = kmalloc(sizeof(*n) + key_len, GFP_KERNEL);
	if (!n)
		goto out;

	memcpy(n->key, pkey, key_len);
	n->dev = dev;
	if (dev)
		dev_hold(dev);

	if (tbl->pconstructor && tbl->pconstructor(n)) {
		if (dev)
			dev_put(dev);
		kfree(n);
		n = NULL;
		goto out;
	}

	write_lock_bh(&tbl->lock);
	n->next = tbl->phash_buckets[hash_val];
	tbl->phash_buckets[hash_val] = n;
	write_unlock_bh(&tbl->lock);
out:
	return n;
}


int pneigh_delete(struct neigh_table *tbl, const void *pkey,
		  struct net_device *dev)
{
	struct pneigh_entry *n, **np;
	int key_len = tbl->key_len;
	u32 hash_val = *(u32 *)(pkey + key_len - 4);

	hash_val ^= (hash_val >> 16);
	hash_val ^= hash_val >> 8;
	hash_val ^= hash_val >> 4;
	hash_val &= PNEIGH_HASHMASK;

	write_lock_bh(&tbl->lock);
	for (np = &tbl->phash_buckets[hash_val]; (n = *np) != NULL;
	     np = &n->next) {
		if (!memcmp(n->key, pkey, key_len) && n->dev == dev) {
			*np = n->next;
			write_unlock_bh(&tbl->lock);
			if (tbl->pdestructor)
				tbl->pdestructor(n);
			if (n->dev)
				dev_put(n->dev);
			kfree(n);
			return 0;
		}
	}
	write_unlock_bh(&tbl->lock);
	return -ENOENT;
}

static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
{
	struct pneigh_entry *n, **np;
	u32 h;

	for (h = 0; h <= PNEIGH_HASHMASK; h++) {
		np = &tbl->phash_buckets[h];
		while ((n = *np) != NULL) {
			if (!dev || n->dev == dev) {
				*np = n->next;
				if (tbl->pdestructor)
					tbl->pdestructor(n);
				if (n->dev)
					dev_put(n->dev);
				kfree(n);
				continue;
			}
			np = &n->next;
		}
	}
	return -ENOENT;
}


/*
 *	neighbour must already be out of the table;
 *
 */
void neigh_destroy(struct neighbour *neigh)
{
	struct hh_cache *hh;

	NEIGH_CACHE_STAT_INC(neigh->tbl, destroys);

	if (!neigh->dead) {
		printk(KERN_WARNING
		       "Destroying alive neighbour %p\n", neigh);
		dump_stack();
		return;
	}

	if (neigh_del_timer(neigh))
		printk(KERN_WARNING "Impossible event.\n");

	while ((hh = neigh->hh) != NULL) {
		neigh->hh = hh->hh_next;
		hh->hh_next = NULL;

		write_seqlock_bh(&hh->hh_lock);
		hh->hh_output = neigh_blackhole;
		write_sequnlock_bh(&hh->hh_lock);
		if (atomic_dec_and_test(&hh->hh_refcnt))
			kfree(hh);
	}

	skb_queue_purge(&neigh->arp_queue);

	dev_put(neigh->dev);
	neigh_parms_put(neigh->parms);

	NEIGH_PRINTK2("neigh %p is destroyed.\n", neigh);

	atomic_dec(&neigh->tbl->entries);