On Sun, May 01, 2005 at 01:13:28AM +0200, Jesper Juhl wrote:

On Sun, 1 May 2005, Alexey Dobriyan wrote:

quoted

On Sat, Apr 30, 2005 at 10:36:00PM +0200, Jesper Juhl wrote:

quoted

Since Andrew merged the patch that makes calling crypto_free_tfm() with a 
NULL pointer safe into 2.6.12-rc3-mm1, I made a patch to remove checks for 
NULL before calling that function
 drivers/net/wireless/hostap/hostap_crypt_ccmp.c |    5 -
 drivers/net/wireless/hostap/hostap_crypt_tkip.c |   10 +-
 drivers/net/wireless/hostap/hostap_crypt_wep.c  |    5 -
 net/ieee80211/ieee80211_crypt_ccmp.c            |    5 -
 net/ieee80211/ieee80211_crypt_tkip.c            |   10 +-
 net/ieee80211/ieee80211_crypt_wep.c             |    5 -

I think I have a better one for these.

--- linux-2.6.12-rc3-mm1/drivers/net/wireless/hostap/hostap_crypt_ccmp.c	2005-05-01 01:53:50.000000000 +0000
+++ linux-2.6.12-rc3-mm1-hostap/drivers/net/wireless/hostap/hostap_crypt_ccmp.c	2005-05-01 02:21:10.000000000 +0000

quoted

@@ -121,8 +118,7 @@ fail:
 static void hostap_ccmp_deinit(void *priv)
 {
 	struct hostap_ccmp_data *_priv = priv;
-	if (_priv && _priv->tfm)
-		crypto_free_tfm(_priv->tfm);
+	crypto_free_tfm(_priv->tfm);
 	kfree(priv);
 	module_put(THIS_MODULE);
 }

This will Oops if _priv is NULL. That's why my patch did 

if (_priv)
	crypto_free_tfm(_priv->tfm);

After hostap_ccmp_init() returns successfully:
1. priv is valid pointer	line 95
2. priv->tfm is valid pointer	line 102