aboutsummaryrefslogtreecommitdiffstats
path: root/tools
diff options
context:
space:
mode:
authorJakub Kicinski <jakub.kicinski@netronome.com>2019-12-14 17:16:12 -0800
committerJakub Kicinski <jakub.kicinski@netronome.com>2019-12-14 17:16:12 -0800
commit8ed001c966b0dd812a1cc57ae4b9c7b6d1454a25 (patch)
tree0c3c21f1217705dad14aecd5de3c69715fc70760 /tools
parentbonding: fix active-backup transition after link failure (diff)
parentgtp: avoid zero size hashtable (diff)
downloadlinux-dev-8ed001c966b0dd812a1cc57ae4b9c7b6d1454a25.tar.xz
linux-dev-8ed001c966b0dd812a1cc57ae4b9c7b6d1454a25.zip
Merge branch 'gtp-fix-several-bugs-in-gtp-module'
Taehee Yoo says: ==================== 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. ==================== Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Diffstat (limited to 'tools')
0 files changed, 0 insertions, 0 deletions