[for-next,v4,2/8] RDMA/rxe: Always schedule works before accessing user MRs
Commit Message
Both responder and completer can sleep to execute page-fault when used
with ODP. It happens when they are going to access user MRs, so works must
be scheduled in such cases.
Signed-off-by: Daisuke Matsuda <matsuda-daisuke@fujitsu.com>
---
drivers/infiniband/sw/rxe/rxe_comp.c | 12 ++++++++++--
drivers/infiniband/sw/rxe/rxe_loc.h | 4 ++--
drivers/infiniband/sw/rxe/rxe_recv.c | 4 ++--
drivers/infiniband/sw/rxe/rxe_resp.c | 14 +++++++++-----
4 files changed, 23 insertions(+), 11 deletions(-)
Comments
Hi Daisuke,
kernel test robot noticed the following build warnings:
[auto build test WARNING on f605f26ea196a3b49bea249330cbd18dba61a33e]
url: https://github.com/intel-lab-lkp/linux/commits/Daisuke-Matsuda/RDMA-rxe-Tentative-workqueue-implementation/20230419-135731
base: f605f26ea196a3b49bea249330cbd18dba61a33e
patch link: https://lore.kernel.org/r/7441c59fcea601c03c70ec03b5d17a69032e51f8.1681882651.git.matsuda-daisuke%40fujitsu.com
patch subject: [PATCH for-next v4 2/8] RDMA/rxe: Always schedule works before accessing user MRs
config: x86_64-randconfig-a011-20230417 (https://download.01.org/0day-ci/archive/20230420/202304200354.oGlN33Lg-lkp@intel.com/config)
compiler: clang version 14.0.6 (https://github.com/llvm/llvm-project f28c006a5895fc0e329fe15fead81e37457cb1d1)
reproduce (this is a W=1 build):
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# https://github.com/intel-lab-lkp/linux/commit/493fb0777100e2e1b6358176e84b4b29372105ae
git remote add linux-review https://github.com/intel-lab-lkp/linux
git fetch --no-tags linux-review Daisuke-Matsuda/RDMA-rxe-Tentative-workqueue-implementation/20230419-135731
git checkout 493fb0777100e2e1b6358176e84b4b29372105ae
# save the config file
mkdir build_dir && cp config build_dir/.config
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross W=1 O=build_dir ARCH=x86_64 olddefconfig
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross W=1 O=build_dir ARCH=x86_64 SHELL=/bin/bash drivers/infiniband/sw/rxe/
If you fix the issue, kindly add following tag where applicable
| Reported-by: kernel test robot <lkp@intel.com>
| Link: https://lore.kernel.org/oe-kbuild-all/202304200354.oGlN33Lg-lkp@intel.com/
All warnings (new ones prefixed by >>):
>> drivers/infiniband/sw/rxe/rxe_comp.c:139:36: warning: converting the enum constant to a boolean [-Wint-in-bool-context]
if (pkt->mask | (RXE_PAYLOAD_MASK || RXE_ATMACK_MASK))
^
1 warning generated.
vim +139 drivers/infiniband/sw/rxe/rxe_comp.c
128
129 void rxe_comp_queue_pkt(struct rxe_pkt_info *pkt, struct sk_buff *skb)
130 {
131 struct rxe_qp *qp = pkt->qp;
132 int must_sched;
133
134 skb_queue_tail(&qp->resp_pkts, skb);
135
136 /* Schedule the task if processing Read responses or Atomic acks.
137 * In these cases, completer may sleep to access ODP-enabled MRs.
138 */
> 139 if (pkt->mask | (RXE_PAYLOAD_MASK || RXE_ATMACK_MASK))
140 must_sched = 1;
141 else
142 must_sched = skb_queue_len(&qp->resp_pkts) > 1;
143
144 if (must_sched != 0)
145 rxe_counter_inc(SKB_TO_PKT(skb)->rxe, RXE_CNT_COMPLETER_SCHED);
146
147 if (must_sched)
148 rxe_sched_task(&qp->comp.task);
149 else
150 rxe_run_task(&qp->comp.task);
151 }
152
@@ -126,13 +126,21 @@ void retransmit_timer(struct timer_list *t)
spin_unlock_bh(&qp->state_lock);
}
-void rxe_comp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb)
+void rxe_comp_queue_pkt(struct rxe_pkt_info *pkt, struct sk_buff *skb)
{
+ struct rxe_qp *qp = pkt->qp;
int must_sched;
skb_queue_tail(&qp->resp_pkts, skb);
- must_sched = skb_queue_len(&qp->resp_pkts) > 1;
+ /* Schedule the task if processing Read responses or Atomic acks.
+ * In these cases, completer may sleep to access ODP-enabled MRs.
+ */
+ if (pkt->mask | (RXE_PAYLOAD_MASK || RXE_ATMACK_MASK))
+ must_sched = 1;
+ else
+ must_sched = skb_queue_len(&qp->resp_pkts) > 1;
+
if (must_sched != 0)
rxe_counter_inc(SKB_TO_PKT(skb)->rxe, RXE_CNT_COMPLETER_SCHED);
@@ -179,9 +179,9 @@ int rxe_icrc_init(struct rxe_dev *rxe);
int rxe_icrc_check(struct sk_buff *skb, struct rxe_pkt_info *pkt);
void rxe_icrc_generate(struct sk_buff *skb, struct rxe_pkt_info *pkt);
-void rxe_resp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb);
+void rxe_resp_queue_pkt(struct rxe_pkt_info *pkt, struct sk_buff *skb);
-void rxe_comp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb);
+void rxe_comp_queue_pkt(struct rxe_pkt_info *pkt, struct sk_buff *skb);
static inline unsigned int wr_opcode_mask(int opcode, struct rxe_qp *qp)
{
@@ -181,9 +181,9 @@ static int hdr_check(struct rxe_pkt_info *pkt)
static inline void rxe_rcv_pkt(struct rxe_pkt_info *pkt, struct sk_buff *skb)
{
if (pkt->mask & RXE_REQ_MASK)
- rxe_resp_queue_pkt(pkt->qp, skb);
+ rxe_resp_queue_pkt(pkt, skb);
else
- rxe_comp_queue_pkt(pkt->qp, skb);
+ rxe_comp_queue_pkt(pkt, skb);
}
static void rxe_rcv_mcast_pkt(struct rxe_dev *rxe, struct sk_buff *skb)
@@ -47,15 +47,19 @@ static char *resp_state_name[] = {
};
/* rxe_recv calls here to add a request packet to the input queue */
-void rxe_resp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb)
+void rxe_resp_queue_pkt(struct rxe_pkt_info *pkt, struct sk_buff *skb)
{
- int must_sched;
- struct rxe_pkt_info *pkt = SKB_TO_PKT(skb);
+ int must_sched = 1;
+ struct rxe_qp *qp = pkt->qp;
skb_queue_tail(&qp->req_pkts, skb);
- must_sched = (pkt->opcode == IB_OPCODE_RC_RDMA_READ_REQUEST) ||
- (skb_queue_len(&qp->req_pkts) > 1);
+ /* responder can sleep to access an ODP-enabled MR. Always schedule
+ * tasks for non-zero-byte operations, RDMA Read, and Atomic.
+ */
+ if ((skb_queue_len(&qp->req_pkts) == 1) && (payload_size(pkt) == 0)
+ && !(pkt->mask & RXE_READ_OR_ATOMIC_MASK))
+ must_sched = 0;
if (must_sched)
rxe_sched_task(&qp->resp.task);