To avoid the following kernel panic when calling kmem_cache_create()
with a NULL pointer from pool_cache(), move the rxe_cache_init() to the
context of device initialization.
BUG: unable to handle kernel NULL pointer dereference at 000000000000000b
PGD 0 P4D 0
Oops: 0000 [#1] SMP NOPTI
CPU: 4 PID: 8512 Comm: modprobe Kdump: loaded Not tainted 4.18.0-231.el8.x86_64 #1
Hardware name: HPE ProLiant DL385 Gen10/ProLiant DL385 Gen10, BIOS A40 10/02/2018
RIP: 0010:kmem_cache_alloc+0xd1/0x1b0
Code: 8b 57 18 45 8b 77 1c 48 8b 5c 24 30 0f 1f 44 00 00 5b 48 89 e8 5d 41 5c 41 5d 41 5e 41 5f c3 81 e3 00 00 10 00 75 0e 4d 89 fe <41> f6 47 0b 04 0f 84 6c ff ff ff 4c 89 ff e8 cc da 01 00 49 89 c6
RSP: 0018:ffffa2b8c773f9d0 EFLAGS: 00010246
RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000005
RDX: 0000000000000004 RSI: 00000000006080c0 RDI: 0000000000000000
RBP: ffff8ea0a8634fd0 R08: ffffa2b8c773f988 R09: 00000000006000c0
R10: 0000000000000000 R11: 0000000000000230 R12: 00000000006080c0
R13: ffffffffc0a97fc8 R14: 0000000000000000 R15: 0000000000000000
FS: 00007f9138ed9740(0000) GS:ffff8ea4ae800000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000000000000000b CR3: 000000046d59a000 CR4: 00000000003406e0
Call Trace:
rxe_alloc+0xc8/0x160 [rdma_rxe]
rxe_get_dma_mr+0x25/0xb0 [rdma_rxe]
__ib_alloc_pd+0xcb/0x160 [ib_core]
ib_mad_init_device+0x296/0x8b0 [ib_core]
add_client_context+0x11a/0x160 [ib_core]
enable_device_and_get+0xdc/0x1d0 [ib_core]
ib_register_device+0x572/0x6b0 [ib_core]
? crypto_create_tfm+0x32/0xe0
? crypto_create_tfm+0x7a/0xe0
? crypto_alloc_tfm+0x58/0xf0
rxe_register_device+0x19d/0x1c0 [rdma_rxe]
rxe_net_add+0x3d/0x70 [rdma_rxe]
? dev_get_by_name_rcu+0x73/0x90
rxe_param_set_add+0xaf/0xc0 [rdma_rxe]
parse_args+0x179/0x370
? ref_module+0x1b0/0x1b0
load_module+0x135e/0x17e0
? ref_module+0x1b0/0x1b0
? __do_sys_init_module+0x13b/0x180
__do_sys_init_module+0x13b/0x180
do_syscall_64+0x5b/0x1a0
entry_SYSCALL_64_after_hwframe+0x65/0xca
RIP: 0033:0x7f9137ed296e
Fixes: 8700e3e7c485 ("Soft RoCE driver")
Signed-off-by: Kamal Heib <kamalheib1@xxxxxxxxx>
---
v2: Call rxe_cache_init() from rxe_init().
---
drivers/infiniband/sw/rxe/rxe.c | 14 +++++++-------
drivers/infiniband/sw/rxe/rxe_pool.c | 3 +++
2 files changed, 10 insertions(+), 7 deletions(-)
diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c
index 5642eefb4ba1..c80f7c183957 100644
--- a/drivers/infiniband/sw/rxe/rxe.c
+++ b/drivers/infiniband/sw/rxe/rxe.c
@@ -252,6 +252,13 @@ static int rxe_init(struct rxe_dev *rxe)
/* init default device parameters */
rxe_init_device_param(rxe);
+ /* initialize slab caches for managed objects */
+ err = rxe_cache_init();
+ if (err) {
+ pr_err("unable to init object pools\n");
+ return err;
+ }
+
err = rxe_init_ports(rxe);
if (err)
goto err1;
@@ -336,13 +343,6 @@ static int __init rxe_module_init(void)
{
int err;
- /* initialize slab caches for managed objects */
- err = rxe_cache_init();
- if (err) {
- pr_err("unable to init object pools\n");
- return err;
- }
-
err = rxe_net_init();
if (err)
return err;
diff --git a/drivers/infiniband/sw/rxe/rxe_pool.c b/drivers/infiniband/sw/rxe/rxe_pool.c
index fbcbac52290b..06c6d1f835b7 100644
--- a/drivers/infiniband/sw/rxe/rxe_pool.c
+++ b/drivers/infiniband/sw/rxe/rxe_pool.c
@@ -139,6 +139,9 @@ int rxe_cache_init(void)
for (i = 0; i < RXE_NUM_TYPES; i++) {
type = &rxe_type_info[i];
size = ALIGN(type->size, RXE_POOL_ALIGN);
+ if (type->cache)
+ continue;
+
if (!(type->flags & RXE_POOL_NO_ALLOC)) {
type->cache =
kmem_cache_create(type->name, size,
--
2.26.2
