summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorJesper Juhl <jj@chaosbits.net>2011-02-17 21:33:56 +0100
committerMauro Carvalho Chehab <mchehab@redhat.com>2011-03-22 10:51:55 +0100
commit7e270941c8f0a11224e383d3d38946451f66fbbf (patch)
tree8cd6d401c30d854c355c13bbd992a712a30e34d0
parent[media] V4L: videobuf, don't use dma addr as physical (diff)
downloadlinux-7e270941c8f0a11224e383d3d38946451f66fbbf.tar.xz
linux-7e270941c8f0a11224e383d3d38946451f66fbbf.zip
[media] Zarlink zl10036 DVB-S: Fix mem leak in zl10036_attach
On Thu, 17 Feb 2011, Matthias Schwarzott wrote: > On Sunday 06 February 2011, Jesper Juhl wrote: > > If the memory allocation to 'state' succeeds but we jump to the 'error' > > label before 'state' is assigned to fe->tuner_priv, then the call to > > 'zl10036_release(fe)' at the 'error:' label will not free 'state', but > > only what was previously assigned to 'tuner_priv', thus leaking the memory > > allocated to 'state'. > > There are may ways to fix this, including assigning the allocated memory > > directly to 'fe->tuner_priv', but I did not go for that since the > > additional pointer derefs are more expensive than the local variable, so I > > just added a 'kfree(state)' call. I guess the call to 'zl10036_release' > > might not even be needed in this case, but I wasn't sure, so I left it in. > > > Yeah, that call to zl10036_release can be completely eleminated. > Another thing is: jumping to the error label only makes sense when memory was > already allocated. So the jump in line 471 can be replaced by "return NULL", > as the other error handling before allocation: > if (NULL == config) { > printk(KERN_ERR "%s: no config specified", __func__); > goto error; > } > > I suggest to improve the patch to clean the code up when changing that. > > But I am fine with commiting this patch also if you do not want to change it. > Thank you for your feedback. It makes a lot of sense. Changing it is not a problem :) How about the updated patch below? If the memory allocation to 'state' succeeds but we jump to the 'error' label before 'state' is assigned to fe->tuner_priv, then the call to 'zl10036_release(fe)' at the 'error:' label will not free 'state', but only what was previously assigned to 'tuner_priv', thus leaking the memory allocated to 'state'. This patch fixes the leak and also does not jump to 'error:' before mem has been allocated but instead just returns. Also some small style cleanups. Signed-off-by: Jesper Juhl <jj@chaosbits.net> Signed-off-by: Matthias Schwarzott <zzam@gentoo.org> Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
-rw-r--r--drivers/media/dvb/frontends/zl10036.c10
1 files changed, 5 insertions, 5 deletions
diff --git a/drivers/media/dvb/frontends/zl10036.c b/drivers/media/dvb/frontends/zl10036.c
index 4627f491656b..81aa984c551f 100644
--- a/drivers/media/dvb/frontends/zl10036.c
+++ b/drivers/media/dvb/frontends/zl10036.c
@@ -463,16 +463,16 @@ struct dvb_frontend *zl10036_attach(struct dvb_frontend *fe,
const struct zl10036_config *config,
struct i2c_adapter *i2c)
{
- struct zl10036_state *state = NULL;
+ struct zl10036_state *state;
int ret;
- if (NULL == config) {
+ if (!config) {
printk(KERN_ERR "%s: no config specified", __func__);
- goto error;
+ return NULL;
}
state = kzalloc(sizeof(struct zl10036_state), GFP_KERNEL);
- if (NULL == state)
+ if (!state)
return NULL;
state->config = config;
@@ -507,7 +507,7 @@ struct dvb_frontend *zl10036_attach(struct dvb_frontend *fe,
return fe;
error:
- zl10036_release(fe);
+ kfree(state);
return NULL;
}
EXPORT_SYMBOL(zl10036_attach);