Skip to contentSkip to conversation

gtp: fix several bugs in gtp module

PATCH In review Taehee Yoo 2 participants 2 messages Dec 11, 2019 – Dec 15, 2019

Subsystems (2)
lore
Share & tools
lore

Taehee Yoo

author
#0 lore raw

cover gtp: fix several bugs in gtp module

This patchset fixes several bugs in the GTP module.

1. Do not allow adding duplicate TID and ms_addr pdp context. In the current code, duplicate TID and ms_addr pdp context could be added. So, RX and TX path could find correct pdp context.

2. Fix wrong condition in ->dumpit() callback.
->dumpit() callback is re-called if dump packet size is too big. So, before return, it saves last position and then restart from last dump position.
TID value is used to find last dump position.
GTP module allows adding zero TID value. But ->dumpit() callback ignores zero TID value.
So, dump would not work correctly if dump packet size too big.

3. Fix use-after-free in ipv4_pdp_find().
RX and TX patch always uses gtp->tid_hash and gtp->addr_hash. but while packet processing, these hash pointer would be freed. So, use-after-free would occur.

4. Fix panic because of zero size hashtable
GTP hashtable size could be set by user-space.
If hashsize is set to 0, hashtable will not work and panic will occur.

Taehee Yoo (4):
gtp: do not allow adding duplicate tid and ms_addr pdp context
gtp: fix wrong condition in gtp_genl_dump_pdp()
gtp: fix an use-after-free in ipv4_pdp_find()
gtp: avoid zero size hashtable

 drivers/net/gtp.c | 109 +++++++++++++++++++++++++++-------------------
 1 file changed, 63 insertions(+), 46 deletions(-)
Signature · 1 line
2.17.1
#1 lore raw
Quoted 15 lines · Taehee Yoo

This patchset fixes several bugs in the GTP module.

1. Do not allow adding duplicate TID and ms_addr pdp context. In the current code, duplicate TID and ms_addr pdp context could be added. So, RX and TX path could find correct pdp context.

2. Fix wrong condition in ->dumpit() callback.
->dumpit() callback is re-called if dump packet size is too big. So, before return, it saves last position and then restart from last dump position.
TID value is used to find last dump position.
GTP module allows adding zero TID value. But ->dumpit() callback ignores zero TID value.
So, dump would not work correctly if dump packet size too big.

Quoted 8 lines

3. Fix use-after-free in ipv4_pdp_find().
RX and TX patch always uses gtp->tid_hash and gtp->addr_hash. but while packet processing, these hash pointer would be freed. So, use-after-free would occur.

4. Fix panic because of zero size hashtable
GTP hashtable size could be set by user-space.
If hashsize is set to 0, hashtable will not work and panic will occur.

Looks good to me, thank you, applied and queued for stable.