[PATCH 5.4 085/165] cxgb4: Fix kernel panic while accessing sge_info

From: Greg Kroah-Hartman
Date: Sat Jan 11 2020 - 05:26:35 EST


From: Vishal Kulkarni <vishal@xxxxxxxxxxx>

[ Upstream commit 479a0d1376f6d97c60871442911f1394d4446a25 ]

The sge_info debugfs collects offload queue info even when offload
capability is disabled and leads to panic.

[ 144.139871] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 144.139874] CR2: 0000000000000000 CR3: 000000082d456005 CR4: 00000000001606e0
[ 144.139876] Call Trace:
[ 144.139887] sge_queue_start+0x12/0x30 [cxgb4]
[ 144.139897] seq_read+0x1d4/0x3d0
[ 144.139906] full_proxy_read+0x50/0x70
[ 144.139913] vfs_read+0x89/0x140
[ 144.139916] ksys_read+0x55/0xd0
[ 144.139924] do_syscall_64+0x5b/0x1d0
[ 144.139933] entry_SYSCALL_64_after_hwframe+0x44/0xa9
[ 144.139936] RIP: 0033:0x7f4b01493990

Fix this crash by skipping the offload queue access in sge_qinfo when
offload capability is disabled

Signed-off-by: Herat Ramani <herat@xxxxxxxxxxx>
Signed-off-by: Vishal Kulkarni <vishal@xxxxxxxxxxx>
Signed-off-by: Jakub Kicinski <jakub.kicinski@xxxxxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c | 4 ++++
1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index ae6a47dd7dc9..fb8ade9a05a9 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -2996,6 +2996,9 @@ static int sge_queue_entries(const struct adapter *adap)
int tot_uld_entries = 0;
int i;

+ if (!is_uld(adap))
+ goto lld_only;
+
mutex_lock(&uld_mutex);
for (i = 0; i < CXGB4_TX_MAX; i++)
tot_uld_entries += sge_qinfo_uld_txq_entries(adap, i);
@@ -3006,6 +3009,7 @@ static int sge_queue_entries(const struct adapter *adap)
}
mutex_unlock(&uld_mutex);

+lld_only:
return DIV_ROUND_UP(adap->sge.ethqsets, 4) +
tot_uld_entries +
DIV_ROUND_UP(MAX_CTRL_QUEUES, 4) + 1;
--
2.20.1