Minimal implementation of ibv_advise_mr(3) requires synchronous calls being
successful with the IBV_ADVISE_MR_FLAG_FLUSH flag. Asynchronous requests,
which are best-effort, will be added subsequently.

Signed-off-by: Daisuke Matsuda <dskmtsd@gmail.com>
---
 drivers/infiniband/sw/rxe/rxe.c     |  7 +++
 drivers/infiniband/sw/rxe/rxe_loc.h | 10 ++++
 drivers/infiniband/sw/rxe/rxe_odp.c | 86 +++++++++++++++++++++++++++++
 3 files changed, 103 insertions(+)

diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c
index 3a77d6db1720..e891199cbdef 100644
--- a/drivers/infiniband/sw/rxe/rxe.c
+++ b/drivers/infiniband/sw/rxe/rxe.c
@@ -34,6 +34,10 @@ void rxe_dealloc(struct ib_device *ib_dev)
 	mutex_destroy(&rxe->usdev_lock);
 }
 
+static const struct ib_device_ops rxe_ib_dev_odp_ops = {
+	.advise_mr = rxe_ib_advise_mr,
+};
+
 /* initialize rxe device parameters */
 static void rxe_init_device_param(struct rxe_dev *rxe, struct net_device *ndev)
 {
@@ -103,6 +107,9 @@ static void rxe_init_device_param(struct rxe_dev *rxe, struct net_device *ndev)
 		rxe->attr.odp_caps.per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_SRQ_RECV;
 		rxe->attr.odp_caps.per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_FLUSH;
 		rxe->attr.odp_caps.per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_ATOMIC_WRITE;
+
+		/* set handler for ODP prefetching API - ibv_advise_mr(3) */
+		ib_set_device_ops(&rxe->ib_dev, &rxe_ib_dev_odp_ops);
 	}
 }
 
diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h
index f7dbb9cddd12..ca302ced0922 100644
--- a/drivers/infiniband/sw/rxe/rxe_loc.h
+++ b/drivers/infiniband/sw/rxe/rxe_loc.h
@@ -197,6 +197,9 @@ enum resp_states rxe_odp_atomic_op(struct rxe_mr *mr, u64 iova, int opcode,
 int rxe_odp_flush_pmem_iova(struct rxe_mr *mr, u64 iova,
 			    unsigned int length);
 enum resp_states rxe_odp_do_atomic_write(struct rxe_mr *mr, u64 iova, u64 value);
+int rxe_ib_advise_mr(struct ib_pd *pd, enum ib_uverbs_advise_mr_advice advice,
+		     u32 flags, struct ib_sge *sg_list, u32 num_sge,
+		     struct uverbs_attr_bundle *attrs);
 #else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 static inline int
 rxe_odp_mr_init_user(struct rxe_dev *rxe, u64 start, u64 length, u64 iova,
@@ -225,6 +228,13 @@ static inline enum resp_states rxe_odp_do_atomic_write(struct rxe_mr *mr,
 {
 	return RESPST_ERR_UNSUPPORTED_OPCODE;
 }
+int rxe_ib_advise_mr(struct ib_pd *pd, enum ib_uverbs_advise_mr_advice advice,
+		     u32 flags, struct ib_sge *sg_list, u32 num_sge,
+		     struct uverbs_attr_bundle *attrs)
+{
+	return -EOPNOTSUPP;
+}
+
 #endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 
 #endif /* RXE_LOC_H */
diff --git a/drivers/infiniband/sw/rxe/rxe_odp.c b/drivers/infiniband/sw/rxe/rxe_odp.c
index 6149d9ffe7f7..e5c60b061d7e 100644
--- a/drivers/infiniband/sw/rxe/rxe_odp.c
+++ b/drivers/infiniband/sw/rxe/rxe_odp.c
@@ -424,3 +424,89 @@ enum resp_states rxe_odp_do_atomic_write(struct rxe_mr *mr, u64 iova, u64 value)
 
 	return RESPST_NONE;
 }
+
+static int rxe_ib_prefetch_sg_list(struct ib_pd *ibpd,
+				   enum ib_uverbs_advise_mr_advice advice,
+				   u32 pf_flags, struct ib_sge *sg_list,
+				   u32 num_sge)
+{
+	struct rxe_pd *pd = container_of(ibpd, struct rxe_pd, ibpd);
+	unsigned int i;
+	int ret = 0;
+
+	for (i = 0; i < num_sge; ++i) {
+		struct rxe_mr *mr;
+		struct ib_umem_odp *umem_odp;
+
+		mr = lookup_mr(pd, IB_ACCESS_LOCAL_WRITE,
+			       sg_list[i].lkey, RXE_LOOKUP_LOCAL);
+
+		if (IS_ERR(mr)) {
+			rxe_dbg_pd(pd, "mr with lkey %x not found\n", sg_list[i].lkey);
+			return PTR_ERR(mr);
+		}
+
+		if (advice == IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH_WRITE &&
+		    !mr->umem->writable) {
+			rxe_dbg_mr(mr, "missing write permission\n");
+			rxe_put(mr);
+			return -EPERM;
+		}
+
+		ret = rxe_odp_do_pagefault_and_lock(mr, sg_list[i].addr,
+						    sg_list[i].length, pf_flags);
+		if (ret < 0) {
+			if (sg_list[i].length == 0)
+				continue;
+
+			rxe_dbg_mr(mr, "failed to prefetch the mr\n");
+			rxe_put(mr);
+			return ret;
+		}
+
+		umem_odp = to_ib_umem_odp(mr->umem);
+		mutex_unlock(&umem_odp->umem_mutex);
+
+		rxe_put(mr);
+	}
+
+	return 0;
+}
+
+static int rxe_ib_advise_mr_prefetch(struct ib_pd *ibpd,
+				     enum ib_uverbs_advise_mr_advice advice,
+				     u32 flags, struct ib_sge *sg_list, u32 num_sge)
+{
+	u32 pf_flags = RXE_PAGEFAULT_DEFAULT;
+
+	if (advice == IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH)
+		pf_flags |= RXE_PAGEFAULT_RDONLY;
+
+	if (advice == IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH_NO_FAULT)
+		pf_flags |= RXE_PAGEFAULT_SNAPSHOT;
+
+	/* Synchronous call */
+	if (flags & IB_UVERBS_ADVISE_MR_FLAG_FLUSH)
+		return rxe_ib_prefetch_sg_list(ibpd, advice, pf_flags, sg_list,
+					       num_sge);
+
+	/* Asynchronous call is "best-effort" */
+
+	return 0;
+}
+
+int rxe_ib_advise_mr(struct ib_pd *ibpd,
+		     enum ib_uverbs_advise_mr_advice advice,
+		     u32 flags,
+		     struct ib_sge *sg_list,
+		     u32 num_sge,
+		     struct uverbs_attr_bundle *attrs)
+{
+	if (advice != IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH &&
+	    advice != IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH_WRITE &&
+	    advice != IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH_NO_FAULT)
+		return -EOPNOTSUPP;
+
+	return rxe_ib_advise_mr_prefetch(ibpd, advice, flags,
+					 sg_list, num_sge);
+}
-- 
2.43.0

Hi Daisuke,

kernel test robot noticed the following build errors:

[auto build test ERROR on rdma/for-next]
[also build test ERROR on next-20250502]
[cannot apply to linus/master v6.15-rc4]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Daisuke-Matsuda/RDMA-rxe-Implement-synchronous-prefetch-for-ODP-MRs/20250502-112436
base:   https://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma.git for-next
patch link:    https://lore.kernel.org/r/20250502032216.2312-2-dskmtsd%40gmail.com
patch subject: [PATCH for-next v1 1/2] RDMA/rxe: Implement synchronous prefetch for ODP MRs
config: x86_64-buildonly-randconfig-005-20250503 (https://download.01.org/0day-ci/archive/20250503/202505030925.esKbABQW-lkp@intel.com/config)
compiler: clang version 20.1.2 (https://github.com/llvm/llvm-project 58df0ef89dd64126512e4ee27b4ac3fd8ddf6247)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250503/202505030925.esKbABQW-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202505030925.esKbABQW-lkp@intel.com/

All error/warnings (new ones prefixed by >>):

   In file included from drivers/infiniband/sw/rxe/rxe_srq.c:8:
   In file included from drivers/infiniband/sw/rxe/rxe.h:30:
>> drivers/infiniband/sw/rxe/rxe_loc.h:231:5: warning: no previous prototype for function 'rxe_ib_advise_mr' [-Wmissing-prototypes]
     231 | int rxe_ib_advise_mr(struct ib_pd *pd, enum ib_uverbs_advise_mr_advice advice,
         |     ^
   drivers/infiniband/sw/rxe/rxe_loc.h:231:1: note: declare 'static' if the function is not intended to be used outside of this translation unit
     231 | int rxe_ib_advise_mr(struct ib_pd *pd, enum ib_uverbs_advise_mr_advice advice,
         | ^
         | static 
   1 warning generated.
--
>> ld.lld: error: duplicate symbol: rxe_ib_advise_mr
   >>> defined in drivers/infiniband/sw/rxe/rxe.o
   >>> defined in drivers/infiniband/sw/rxe/rxe_hw_counters.o
--
>> ld.lld: error: duplicate symbol: rxe_ib_advise_mr
   >>> defined in drivers/infiniband/sw/rxe/rxe.o
   >>> defined in drivers/infiniband/sw/rxe/rxe_net.o
--
>> ld.lld: error: duplicate symbol: rxe_ib_advise_mr
   >>> defined in drivers/infiniband/sw/rxe/rxe.o
   >>> defined in drivers/infiniband/sw/rxe/rxe_verbs.o
--
>> ld.lld: error: duplicate symbol: rxe_ib_advise_mr
   >>> defined in drivers/infiniband/sw/rxe/rxe.o
   >>> defined in drivers/infiniband/sw/rxe/rxe_queue.o
--
>> ld.lld: error: duplicate symbol: rxe_ib_advise_mr
   >>> defined in drivers/infiniband/sw/rxe/rxe.o
   >>> defined in drivers/infiniband/sw/rxe/rxe_srq.o
--
>> ld.lld: error: duplicate symbol: rxe_ib_advise_mr
   >>> defined in drivers/infiniband/sw/rxe/rxe.o
   >>> defined in drivers/infiniband/sw/rxe/rxe_pool.o
--
>> ld.lld: error: duplicate symbol: rxe_ib_advise_mr
   >>> defined in drivers/infiniband/sw/rxe/rxe.o
   >>> defined in drivers/infiniband/sw/rxe/rxe_resp.o
--
>> ld.lld: error: duplicate symbol: rxe_ib_advise_mr
   >>> defined in drivers/infiniband/sw/rxe/rxe.o
   >>> defined in drivers/infiniband/sw/rxe/rxe_qp.o
--
>> ld.lld: error: duplicate symbol: rxe_ib_advise_mr
   >>> defined in drivers/infiniband/sw/rxe/rxe.o
   >>> defined in drivers/infiniband/sw/rxe/rxe_recv.o
--
>> ld.lld: error: duplicate symbol: rxe_ib_advise_mr
   >>> defined in drivers/infiniband/sw/rxe/rxe.o
   >>> defined in drivers/infiniband/sw/rxe/rxe_req.o
..

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki