18 files changed, 223 insertions, 176 deletions

diff --git a/drivers/infiniband/sw/rxe/Kconfig b/drivers/infiniband/sw/rxe/Kconfig
index c180e7ebcfc5..1ed5b63f8afc 100644
--- a/drivers/infiniband/sw/rxe/Kconfig
+++ b/drivers/infiniband/sw/rxe/Kconfig
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config RDMA_RXE
 	tristate "Software RDMA over Ethernet (RoCE) driver"
-	depends on INET && PCI && INFINIBAND
+	depends on INET && PCI && INFINIBAND && 64BIT
 	depends on INFINIBAND_VIRT_DMA
 	select NET_UDP_TUNNEL
 	select CRC32
diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c
index b248c68bf9b1..3a77d6db1720 100644
--- a/drivers/infiniband/sw/rxe/rxe.c
+++ b/drivers/infiniband/sw/rxe/rxe.c
@@ -101,6 +101,8 @@ 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_READ;
 		rxe->attr.odp_caps.per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_ATOMIC;
 		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;
 	}
 }
 
diff --git a/drivers/infiniband/sw/rxe/rxe_cq.c b/drivers/infiniband/sw/rxe/rxe_cq.c
index fec87c9030ab..fffd144d509e 100644
--- a/drivers/infiniband/sw/rxe/rxe_cq.c
+++ b/drivers/infiniband/sw/rxe/rxe_cq.c
@@ -56,11 +56,8 @@ int rxe_cq_from_init(struct rxe_dev *rxe, struct rxe_cq *cq, int cqe,
 
 	err = do_mmap_info(rxe, uresp ? &uresp->mi : NULL, udata,
 			   cq->queue->buf, cq->queue->buf_size, &cq->queue->ip);
-	if (err) {
-		vfree(cq->queue->buf);
-		kfree(cq->queue);
+	if (err)
 		return err;
-	}
 
 	cq->is_user = uresp;
 
diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h
index feb386d98d1d..876702058c84 100644
--- a/drivers/infiniband/sw/rxe/rxe_loc.h
+++ b/drivers/infiniband/sw/rxe/rxe_loc.h
@@ -70,9 +70,9 @@ int copy_data(struct rxe_pd *pd, int access, struct rxe_dma_info *dma,
 	      void *addr, int length, enum rxe_mr_copy_dir dir);
 int rxe_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg,
 		  int sg_nents, unsigned int *sg_offset);
-int rxe_mr_do_atomic_op(struct rxe_mr *mr, u64 iova, int opcode,
-			u64 compare, u64 swap_add, u64 *orig_val);
-int rxe_mr_do_atomic_write(struct rxe_mr *mr, u64 iova, u64 value);
+enum resp_states rxe_mr_do_atomic_op(struct rxe_mr *mr, u64 iova, int opcode,
+				     u64 compare, u64 swap_add, u64 *orig_val);
+enum resp_states rxe_mr_do_atomic_write(struct rxe_mr *mr, u64 iova, u64 value);
 struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 key,
 			 enum rxe_mr_lookup_type type);
 int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length);
@@ -140,6 +140,12 @@ static inline int qp_mtu(struct rxe_qp *qp)
 		return IB_MTU_4096;
 }
 
+static inline bool is_odp_mr(struct rxe_mr *mr)
+{
+	return IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING) && mr->umem &&
+	       mr->umem->is_odp;
+}
+
 void free_rd_atomic_resource(struct resp_res *res);
 
 static inline void rxe_advance_resp_resource(struct rxe_qp *qp)
@@ -187,13 +193,16 @@ static inline unsigned int wr_opcode_mask(int opcode, struct rxe_qp *qp)
 /* rxe_odp.c */
 extern const struct mmu_interval_notifier_ops rxe_mn_ops;
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+#if defined CONFIG_INFINIBAND_ON_DEMAND_PAGING
 int rxe_odp_mr_init_user(struct rxe_dev *rxe, u64 start, u64 length,
 			 u64 iova, int access_flags, struct rxe_mr *mr);
 int rxe_odp_mr_copy(struct rxe_mr *mr, u64 iova, void *addr, int length,
 		    enum rxe_mr_copy_dir dir);
-int rxe_odp_atomic_op(struct rxe_mr *mr, u64 iova, int opcode,
-			 u64 compare, u64 swap_add, u64 *orig_val);
+enum resp_states rxe_odp_atomic_op(struct rxe_mr *mr, u64 iova, int opcode,
+				   u64 compare, u64 swap_add, u64 *orig_val);
+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);
 #else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 static inline int
 rxe_odp_mr_init_user(struct rxe_dev *rxe, u64 start, u64 length, u64 iova,
@@ -206,9 +215,19 @@ static inline int rxe_odp_mr_copy(struct rxe_mr *mr, u64 iova, void *addr,
 {
 	return -EOPNOTSUPP;
 }
-static inline int
+static inline enum resp_states
 rxe_odp_atomic_op(struct rxe_mr *mr, u64 iova, int opcode,
-		     u64 compare, u64 swap_add, u64 *orig_val)
+		  u64 compare, u64 swap_add, u64 *orig_val)
+{
+	return RESPST_ERR_UNSUPPORTED_OPCODE;
+}
+static inline int rxe_odp_flush_pmem_iova(struct rxe_mr *mr, u64 iova,
+					  unsigned int length)
+{
+	return -EOPNOTSUPP;
+}
+static inline enum resp_states rxe_odp_do_atomic_write(struct rxe_mr *mr,
+						       u64 iova, u64 value)
 {
 	return RESPST_ERR_UNSUPPORTED_OPCODE;
 }
diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c
index 868d2f0b74e9..bcb97b3ea58a 100644
--- a/drivers/infiniband/sw/rxe/rxe_mr.c
+++ b/drivers/infiniband/sw/rxe/rxe_mr.c
@@ -323,7 +323,7 @@ int rxe_mr_copy(struct rxe_mr *mr, u64 iova, void *addr,
 		return err;
 	}
 
-	if (mr->umem->is_odp)
+	if (is_odp_mr(mr))
 		return rxe_odp_mr_copy(mr, iova, addr, length, dir);
 	else
 		return rxe_mr_copy_xarray(mr, iova, addr, length, dir);
@@ -424,7 +424,7 @@ err1:
 	return err;
 }
 
-int rxe_flush_pmem_iova(struct rxe_mr *mr, u64 iova, unsigned int length)
+static int rxe_mr_flush_pmem_iova(struct rxe_mr *mr, u64 iova, unsigned int length)
 {
 	unsigned int page_offset;
 	unsigned long index;
@@ -433,16 +433,6 @@ int rxe_flush_pmem_iova(struct rxe_mr *mr, u64 iova, unsigned int length)
 	int err;
 	u8 *va;
 
-	/* mr must be valid even if length is zero */
-	if (WARN_ON(!mr))
-		return -EINVAL;
-
-	if (length == 0)
-		return 0;
-
-	if (mr->ibmr.type == IB_MR_TYPE_DMA)
-		return -EFAULT;
-
 	err = mr_check_range(mr, iova, length);
 	if (err)
 		return err;
@@ -454,7 +444,7 @@ int rxe_flush_pmem_iova(struct rxe_mr *mr, u64 iova, unsigned int length)
 		if (!page)
 			return -EFAULT;
 		bytes = min_t(unsigned int, length,
-				mr_page_size(mr) - page_offset);
+			      mr_page_size(mr) - page_offset);
 
 		va = kmap_local_page(page);
 		arch_wb_cache_pmem(va + page_offset, bytes);
@@ -468,11 +458,33 @@ int rxe_flush_pmem_iova(struct rxe_mr *mr, u64 iova, unsigned int length)
 	return 0;
 }
 
+int rxe_flush_pmem_iova(struct rxe_mr *mr, u64 start, unsigned int length)
+{
+	int err;
+
+	/* mr must be valid even if length is zero */
+	if (WARN_ON(!mr))
+		return -EINVAL;
+
+	if (length == 0)
+		return 0;
+
+	if (mr->ibmr.type == IB_MR_TYPE_DMA)
+		return -EFAULT;
+
+	if (is_odp_mr(mr))
+		err = rxe_odp_flush_pmem_iova(mr, start, length);
+	else
+		err = rxe_mr_flush_pmem_iova(mr, start, length);
+
+	return err;
+}
+
 /* Guarantee atomicity of atomic operations at the machine level. */
 DEFINE_SPINLOCK(atomic_ops_lock);
 
-int rxe_mr_do_atomic_op(struct rxe_mr *mr, u64 iova, int opcode,
-			u64 compare, u64 swap_add, u64 *orig_val)
+enum resp_states rxe_mr_do_atomic_op(struct rxe_mr *mr, u64 iova, int opcode,
+				     u64 compare, u64 swap_add, u64 *orig_val)
 {
 	unsigned int page_offset;
 	struct page *page;
@@ -524,27 +536,15 @@ int rxe_mr_do_atomic_op(struct rxe_mr *mr, u64 iova, int opcode,
 
 	kunmap_local(va);
 
-	return 0;
+	return RESPST_NONE;
 }
 
-#if defined CONFIG_64BIT
-/* only implemented or called for 64 bit architectures */
-int rxe_mr_do_atomic_write(struct rxe_mr *mr, u64 iova, u64 value)
+enum resp_states rxe_mr_do_atomic_write(struct rxe_mr *mr, u64 iova, u64 value)
 {
 	unsigned int page_offset;
 	struct page *page;
 	u64 *va;
 
-	/* ODP is not supported right now. WIP. */
-	if (mr->umem->is_odp)
-		return RESPST_ERR_UNSUPPORTED_OPCODE;
-
-	/* See IBA oA19-28 */
-	if (unlikely(mr->state != RXE_MR_STATE_VALID)) {
-		rxe_dbg_mr(mr, "mr not in valid state\n");
-		return RESPST_ERR_RKEY_VIOLATION;
-	}
-
 	if (mr->ibmr.type == IB_MR_TYPE_DMA) {
 		page_offset = iova & (PAGE_SIZE - 1);
 		page = ib_virt_dma_to_page(iova);
@@ -572,20 +572,12 @@ int rxe_mr_do_atomic_write(struct rxe_mr *mr, u64 iova, u64 value)
 	}
 
 	va = kmap_local_page(page);
-
 	/* Do atomic write after all prior operations have completed */
 	smp_store_release(&va[page_offset >> 3], value);
-
 	kunmap_local(va);
 
-	return 0;
-}
-#else
-int rxe_mr_do_atomic_write(struct rxe_mr *mr, u64 iova, u64 value)
-{
-	return RESPST_ERR_UNSUPPORTED_OPCODE;
+	return RESPST_NONE;
 }
-#endif
 
 int advance_dma_data(struct rxe_dma_info *dma, unsigned int length)
 {
diff --git a/drivers/infiniband/sw/rxe/rxe_odp.c b/drivers/infiniband/sw/rxe/rxe_odp.c
index 9f6e2bb2a269..dbc5a5600eb7 100644
--- a/drivers/infiniband/sw/rxe/rxe_odp.c
+++ b/drivers/infiniband/sw/rxe/rxe_odp.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/hmm.h>
+#include <linux/libnvdimm.h>
 
 #include <rdma/ib_umem_odp.h>
 
@@ -26,7 +27,7 @@ static bool rxe_ib_invalidate_range(struct mmu_interval_notifier *mni,
 	start = max_t(u64, ib_umem_start(umem_odp), range->start);
 	end = min_t(u64, ib_umem_end(umem_odp), range->end);
 
-	/* update umem_odp->dma_list */
+	/* update umem_odp->map.pfn_list */
 	ib_umem_odp_unmap_dma_pages(umem_odp, start, end);
 
 	mutex_unlock(&umem_odp->umem_mutex);
@@ -44,12 +45,11 @@ static int rxe_odp_do_pagefault_and_lock(struct rxe_mr *mr, u64 user_va, int bcn
 {
 	struct ib_umem_odp *umem_odp = to_ib_umem_odp(mr->umem);
 	bool fault = !(flags & RXE_PAGEFAULT_SNAPSHOT);
-	u64 access_mask;
+	u64 access_mask = 0;
 	int np;
 
-	access_mask = ODP_READ_ALLOWED_BIT;
 	if (umem_odp->umem.writable && !(flags & RXE_PAGEFAULT_RDONLY))
-		access_mask |= ODP_WRITE_ALLOWED_BIT;
+		access_mask |= HMM_PFN_WRITE;
 
 	/*
 	 * ib_umem_odp_map_dma_and_lock() locks umem_mutex on success.
@@ -124,8 +124,8 @@ int rxe_odp_mr_init_user(struct rxe_dev *rxe, u64 start, u64 length,
 	return err;
 }
 
-static inline bool rxe_check_pagefault(struct ib_umem_odp *umem_odp,
-				       u64 iova, int length, u32 perm)
+static inline bool rxe_check_pagefault(struct ib_umem_odp *umem_odp, u64 iova,
+				       int length)
 {
 	bool need_fault = false;
 	u64 addr;
@@ -137,7 +137,7 @@ static inline bool rxe_check_pagefault(struct ib_umem_odp *umem_odp,
 	while (addr < iova + length) {
 		idx = (addr - ib_umem_start(umem_odp)) >> umem_odp->page_shift;
 
-		if (!(umem_odp->dma_list[idx] & perm)) {
+		if (!(umem_odp->map.pfn_list[idx] & HMM_PFN_VALID)) {
 			need_fault = true;
 			break;
 		}
@@ -147,23 +147,28 @@ static inline bool rxe_check_pagefault(struct ib_umem_odp *umem_odp,
 	return need_fault;
 }
 
+static unsigned long rxe_odp_iova_to_index(struct ib_umem_odp *umem_odp, u64 iova)
+{
+	return (iova - ib_umem_start(umem_odp)) >> umem_odp->page_shift;
+}
+
+static unsigned long rxe_odp_iova_to_page_offset(struct ib_umem_odp *umem_odp, u64 iova)
+{
+	return iova & (BIT(umem_odp->page_shift) - 1);
+}
+
 static int rxe_odp_map_range_and_lock(struct rxe_mr *mr, u64 iova, int length, u32 flags)
 {
 	struct ib_umem_odp *umem_odp = to_ib_umem_odp(mr->umem);
 	bool need_fault;
-	u64 perm;
 	int err;
 
 	if (unlikely(length < 1))
 		return -EINVAL;
 
-	perm = ODP_READ_ALLOWED_BIT;
-	if (!(flags & RXE_PAGEFAULT_RDONLY))
-		perm |= ODP_WRITE_ALLOWED_BIT;
-
 	mutex_lock(&umem_odp->umem_mutex);
 
-	need_fault = rxe_check_pagefault(umem_odp, iova, length, perm);
+	need_fault = rxe_check_pagefault(umem_odp, iova, length);
 	if (need_fault) {
 		mutex_unlock(&umem_odp->umem_mutex);
 
@@ -173,7 +178,7 @@ static int rxe_odp_map_range_and_lock(struct rxe_mr *mr, u64 iova, int length, u
 		if (err < 0)
 			return err;
 
-		need_fault = rxe_check_pagefault(umem_odp, iova, length, perm);
+		need_fault = rxe_check_pagefault(umem_odp, iova, length);
 		if (need_fault)
 			return -EFAULT;
 	}
@@ -190,13 +195,13 @@ static int __rxe_odp_mr_copy(struct rxe_mr *mr, u64 iova, void *addr,
 	size_t offset;
 	u8 *user_va;
 
-	idx = (iova - ib_umem_start(umem_odp)) >> umem_odp->page_shift;
-	offset = iova & (BIT(umem_odp->page_shift) - 1);
+	idx = rxe_odp_iova_to_index(umem_odp, iova);
+	offset = rxe_odp_iova_to_page_offset(umem_odp, iova);
 
 	while (length > 0) {
 		u8 *src, *dest;
 
-		page = hmm_pfn_to_page(umem_odp->pfn_list[idx]);
+		page = hmm_pfn_to_page(umem_odp->map.pfn_list[idx]);
 		user_va = kmap_local_page(page);
 		if (!user_va)
 			return -EFAULT;
@@ -255,8 +260,9 @@ int rxe_odp_mr_copy(struct rxe_mr *mr, u64 iova, void *addr, int length,
 	return err;
 }
 
-static int rxe_odp_do_atomic_op(struct rxe_mr *mr, u64 iova, int opcode,
-				u64 compare, u64 swap_add, u64 *orig_val)
+static enum resp_states rxe_odp_do_atomic_op(struct rxe_mr *mr, u64 iova,
+					     int opcode, u64 compare,
+					     u64 swap_add, u64 *orig_val)
 {
 	struct ib_umem_odp *umem_odp = to_ib_umem_odp(mr->umem);
 	unsigned int page_offset;
@@ -277,9 +283,9 @@ static int rxe_odp_do_atomic_op(struct rxe_mr *mr, u64 iova, int opcode,
 		return RESPST_ERR_RKEY_VIOLATION;
 	}
 
-	idx = (iova - ib_umem_start(umem_odp)) >> umem_odp->page_shift;
-	page_offset = iova & (BIT(umem_odp->page_shift) - 1);
-	page = hmm_pfn_to_page(umem_odp->pfn_list[idx]);
+	idx = rxe_odp_iova_to_index(umem_odp, iova);
+	page_offset = rxe_odp_iova_to_page_offset(umem_odp, iova);
+	page = hmm_pfn_to_page(umem_odp->map.pfn_list[idx]);
 	if (!page)
 		return RESPST_ERR_RKEY_VIOLATION;
 
@@ -304,11 +310,11 @@ static int rxe_odp_do_atomic_op(struct rxe_mr *mr, u64 iova, int opcode,
 
 	kunmap_local(va);
 
-	return 0;
+	return RESPST_NONE;
 }
 
-int rxe_odp_atomic_op(struct rxe_mr *mr, u64 iova, int opcode,
-			 u64 compare, u64 swap_add, u64 *orig_val)
+enum resp_states rxe_odp_atomic_op(struct rxe_mr *mr, u64 iova, int opcode,
+				   u64 compare, u64 swap_add, u64 *orig_val)
 {
 	struct ib_umem_odp *umem_odp = to_ib_umem_odp(mr->umem);
 	int err;
@@ -324,3 +330,91 @@ int rxe_odp_atomic_op(struct rxe_mr *mr, u64 iova, int opcode,
 
 	return err;
 }
+
+int rxe_odp_flush_pmem_iova(struct rxe_mr *mr, u64 iova,
+			    unsigned int length)
+{
+	struct ib_umem_odp *umem_odp = to_ib_umem_odp(mr->umem);
+	unsigned int page_offset;
+	unsigned long index;
+	struct page *page;
+	unsigned int bytes;
+	int err;
+	u8 *va;
+
+	err = rxe_odp_map_range_and_lock(mr, iova, length,
+					 RXE_PAGEFAULT_DEFAULT);
+	if (err)
+		return err;
+
+	while (length > 0) {
+		index = rxe_odp_iova_to_index(umem_odp, iova);
+		page_offset = rxe_odp_iova_to_page_offset(umem_odp, iova);
+
+		page = hmm_pfn_to_page(umem_odp->map.pfn_list[index]);
+		if (!page) {
+			mutex_unlock(&umem_odp->umem_mutex);
+			return -EFAULT;
+		}
+
+		bytes = min_t(unsigned int, length,
+			      mr_page_size(mr) - page_offset);
+
+		va = kmap_local_page(page);
+		arch_wb_cache_pmem(va + page_offset, bytes);
+		kunmap_local(va);
+
+		length -= bytes;
+		iova += bytes;
+		page_offset = 0;
+	}
+
+	mutex_unlock(&umem_odp->umem_mutex);
+
+	return 0;
+}
+
+enum resp_states rxe_odp_do_atomic_write(struct rxe_mr *mr, u64 iova, u64 value)
+{
+	struct ib_umem_odp *umem_odp = to_ib_umem_odp(mr->umem);
+	unsigned int page_offset;
+	unsigned long index;
+	struct page *page;
+	int err;
+	u64 *va;
+
+	/* See IBA oA19-28 */
+	err = mr_check_range(mr, iova, sizeof(value));
+	if (unlikely(err)) {
+		rxe_dbg_mr(mr, "iova out of range\n");
+		return RESPST_ERR_RKEY_VIOLATION;
+	}
+
+	err = rxe_odp_map_range_and_lock(mr, iova, sizeof(value),
+					 RXE_PAGEFAULT_DEFAULT);
+	if (err)
+		return RESPST_ERR_RKEY_VIOLATION;
+
+	page_offset = rxe_odp_iova_to_page_offset(umem_odp, iova);
+	index = rxe_odp_iova_to_index(umem_odp, iova);
+	page = hmm_pfn_to_page(umem_odp->map.pfn_list[index]);
+	if (!page) {
+		mutex_unlock(&umem_odp->umem_mutex);
+		return RESPST_ERR_RKEY_VIOLATION;
+	}
+	/* See IBA A19.4.2 */
+	if (unlikely(page_offset & 0x7)) {
+		mutex_unlock(&umem_odp->umem_mutex);
+		rxe_dbg_mr(mr, "misaligned address\n");
+		return RESPST_ERR_MISALIGNED_ATOMIC;
+	}
+
+	va = kmap_local_page(page);
+	/* Do atomic write after all prior operations have completed */
+	smp_store_release(&va[page_offset >> 3], value);
+	kunmap_local(va);
+
+	mutex_unlock(&umem_odp->umem_mutex);
+
+	return RESPST_NONE;
+}
diff --git a/drivers/infiniband/sw/rxe/rxe_param.h b/drivers/infiniband/sw/rxe/rxe_param.h
index 003f681e5dc0..767870568372 100644
--- a/drivers/infiniband/sw/rxe/rxe_param.h
+++ b/drivers/infiniband/sw/rxe/rxe_param.h
@@ -53,12 +53,9 @@ enum rxe_device_param {
 					| IB_DEVICE_MEM_WINDOW
 					| IB_DEVICE_FLUSH_GLOBAL
 					| IB_DEVICE_FLUSH_PERSISTENT
-#ifdef CONFIG_64BIT
 					| IB_DEVICE_MEM_WINDOW_TYPE_2B
 					| IB_DEVICE_ATOMIC_WRITE,
-#else
-					| IB_DEVICE_MEM_WINDOW_TYPE_2B,
-#endif /* CONFIG_64BIT */
+
 	RXE_MAX_SGE			= 32,
 	RXE_MAX_WQE_SIZE		= sizeof(struct rxe_send_wqe) +
 					  sizeof(struct ib_sge) * RXE_MAX_SGE,
diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c
index 7975fb0e2782..f2af3e0aef35 100644
--- a/drivers/infiniband/sw/rxe/rxe_qp.c
+++ b/drivers/infiniband/sw/rxe/rxe_qp.c
@@ -811,7 +811,12 @@ static void rxe_qp_do_cleanup(struct work_struct *work)
 	spin_unlock_irqrestore(&qp->state_lock, flags);
 	qp->qp_timeout_jiffies = 0;
 
-	if (qp_type(qp) == IB_QPT_RC) {
+	/* In the function timer_setup, .function is initialized. If .function
+	 * is NULL, it indicates the function timer_setup is not called, the
+	 * timer is not initialized. Or else, the timer is initialized.
+	 */
+	if (qp_type(qp) == IB_QPT_RC && qp->retrans_timer.function &&
+		qp->rnr_nak_timer.function) {
 		timer_delete_sync(&qp->retrans_timer);
 		timer_delete_sync(&qp->rnr_nak_timer);
 	}
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index 54ba9ee1acc5..711f73e0bbb1 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -649,10 +649,6 @@ static enum resp_states process_flush(struct rxe_qp *qp,
 	struct rxe_mr *mr = qp->resp.mr;
 	struct resp_res *res = qp->resp.res;
 
-	/* ODP is not supported right now. WIP. */
-	if (mr->umem->is_odp)
-		return RESPST_ERR_UNSUPPORTED_OPCODE;
-
 	/* oA19-14, oA19-15 */
 	if (res && res->replay)
 		return RESPST_ACKNOWLEDGE;
@@ -706,7 +702,7 @@ static enum resp_states atomic_reply(struct rxe_qp *qp,
 	if (!res->replay) {
 		u64 iova = qp->resp.va + qp->resp.offset;
 
-		if (mr->umem->is_odp)
+		if (is_odp_mr(mr))
 			err = rxe_odp_atomic_op(mr, iova, pkt->opcode,
 						atmeth_comp(pkt),
 						atmeth_swap_add(pkt),
@@ -753,7 +749,16 @@ static enum resp_states atomic_write_reply(struct rxe_qp *qp,
 	value = *(u64 *)payload_addr(pkt);
 	iova = qp->resp.va + qp->resp.offset;
 
-	err = rxe_mr_do_atomic_write(mr, iova, value);
+	/* See IBA oA19-28 */
+	if (unlikely(mr->state != RXE_MR_STATE_VALID)) {
+		rxe_dbg_mr(mr, "mr not in valid state\n");
+		return RESPST_ERR_RKEY_VIOLATION;
+	}
+
+	if (is_odp_mr(mr))
+		err = rxe_odp_do_atomic_write(mr, iova, value);
+	else
+		err = rxe_mr_do_atomic_write(mr, iova, value);
 	if (err)
 		return err;
 
diff --git a/drivers/infiniband/sw/rxe/rxe_task.c b/drivers/infiniband/sw/rxe/rxe_task.c
index 80332638d9e3..6f8f353e9583 100644
--- a/drivers/infiniband/sw/rxe/rxe_task.c
+++ b/drivers/infiniband/sw/rxe/rxe_task.c
@@ -85,17 +85,17 @@ static bool is_done(struct rxe_task *task)
 
 /* do_task is a wrapper for the three tasks (requester,
  * completer, responder) and calls them in a loop until
- * they return a non-zero value. It is called either
- * directly by rxe_run_task or indirectly if rxe_sched_task
- * schedules the task. They must call __reserve_if_idle to
- * move the task to busy before calling or scheduling.
- * The task can also be moved to drained or invalid
- * by calls to rxe_cleanup_task or rxe_disable_task.
- * In that case tasks which get here are not executed but
- * just flushed. The tasks are designed to look to see if
- * there is work to do and then do part of it before returning
- * here with a return value of zero until all the work
- * has been consumed then it returns a non-zero value.
+ * they return a non-zero value. It is called indirectly
+ * when rxe_sched_task schedules the task. They must
+ * call __reserve_if_idle to move the task to busy before
+ * calling or scheduling. The task can also be moved to
+ * drained or invalid by calls to rxe_cleanup_task or
+ * rxe_disable_task. In that case tasks which get here
+ * are not executed but just flushed. The tasks are
+ * designed to look to see if there is work to do and
+ * then do part of it before returning here with a return
+ * value of zero until all the work has been consumed then
+ * it returns a non-zero value.
  * The number of times the task can be run is limited by
  * max iterations so one task cannot hold the cpu forever.
  * If the limit is hit and work remains the task is rescheduled.
@@ -234,24 +234,6 @@ void rxe_cleanup_task(struct rxe_task *task)
 	spin_unlock_irqrestore(&task->lock, flags);
 }
 
-/* run the task inline if it is currently idle
- * cannot call do_task holding the lock
- */
-void rxe_run_task(struct rxe_task *task)
-{
-	unsigned long flags;
-	bool run;
-
-	WARN_ON(rxe_read(task->qp) <= 0);
-
-	spin_lock_irqsave(&task->lock, flags);
-	run = __reserve_if_idle(task);
-	spin_unlock_irqrestore(&task->lock, flags);
-
-	if (run)
-		do_task(task);
-}
-
 /* schedule the task to run later as a work queue entry.
  * the queue_work call can be called holding
  * the lock.
diff --git a/drivers/infiniband/sw/rxe/rxe_task.h b/drivers/infiniband/sw/rxe/rxe_task.h
index a63e258b3d66..a8c9a77b6027 100644
--- a/drivers/infiniband/sw/rxe/rxe_task.h
+++ b/drivers/infiniband/sw/rxe/rxe_task.h
@@ -47,8 +47,6 @@ int rxe_init_task(struct rxe_task *task, struct rxe_qp *qp,
 /* cleanup task */
 void rxe_cleanup_task(struct rxe_task *task);
 
-void rxe_run_task(struct rxe_task *task);
-
 void rxe_sched_task(struct rxe_task *task);
 
 /* keep a task from scheduling */
diff --git a/drivers/infiniband/sw/siw/Kconfig b/drivers/infiniband/sw/siw/Kconfig
index ae4a953e2a03..186f182b80e7 100644
--- a/drivers/infiniband/sw/siw/Kconfig
+++ b/drivers/infiniband/sw/siw/Kconfig
@@ -3,6 +3,7 @@ config RDMA_SIW
 	depends on INET && INFINIBAND
 	depends on INFINIBAND_VIRT_DMA
 	select CRC32
+	select NET_CRC32C
 	help
 	This driver implements the iWARP RDMA transport over
 	the Linux TCP/IP network stack. It enables a system with a
diff --git a/drivers/infiniband/sw/siw/siw.h b/drivers/infiniband/sw/siw/siw.h
index 385067e07faf..f5fd71717b80 100644
--- a/drivers/infiniband/sw/siw/siw.h
+++ b/drivers/infiniband/sw/siw/siw.h
@@ -693,29 +693,9 @@ static inline void siw_crc_oneshot(const void *data, size_t len, u8 out[4])
 	return siw_crc_final(&crc, out);
 }
 
-static inline __wsum siw_csum_update(const void *buff, int len, __wsum sum)
-{
-	return (__force __wsum)crc32c((__force __u32)sum, buff, len);
-}
-
-static inline __wsum siw_csum_combine(__wsum csum, __wsum csum2, int offset,
-				      int len)
-{
-	return (__force __wsum)crc32c_combine((__force __u32)csum,
-					      (__force __u32)csum2, len);
-}
-
 static inline void siw_crc_skb(struct siw_rx_stream *srx, unsigned int len)
 {
-	const struct skb_checksum_ops siw_cs_ops = {
-		.update = siw_csum_update,
-		.combine = siw_csum_combine,
-	};
-	__wsum crc = (__force __wsum)srx->mpa_crc;
-
-	crc = __skb_checksum(srx->skb, srx->skb_offset, len, crc,
-			     &siw_cs_ops);
-	srx->mpa_crc = (__force u32)crc;
+	srx->mpa_crc = skb_crc32c(srx->skb, srx->skb_offset, len, srx->mpa_crc);
 }
 
 #define siw_dbg(ibdev, fmt, ...)                                               \
@@ -738,7 +718,7 @@ static inline void siw_crc_skb(struct siw_rx_stream *srx, unsigned int len)
 		  "MEM[0x%08x] %s: " fmt, mem->stag, __func__, ##__VA_ARGS__)
 
 #define siw_dbg_cep(cep, fmt, ...)                                             \
-	ibdev_dbg(&cep->sdev->base_dev, "CEP[0x%pK] %s: " fmt,                 \
+	ibdev_dbg(&cep->sdev->base_dev, "CEP[0x%p] %s: " fmt,                 \
 		  cep, __func__, ##__VA_ARGS__)
 
 void siw_cq_flush(struct siw_cq *cq);
diff --git a/drivers/infiniband/sw/siw/siw_cq.c b/drivers/infiniband/sw/siw/siw_cq.c
index f3c2226aff94..25b3c741b66b 100644
--- a/drivers/infiniband/sw/siw/siw_cq.c
+++ b/drivers/infiniband/sw/siw/siw_cq.c
@@ -72,7 +72,7 @@ int siw_reap_cqe(struct siw_cq *cq, struct ib_wc *wc)
 			wc->opcode = map_wc_opcode[cqe->opcode];
 			wc->status = map_cqe_status[cqe->status].ib;
 			siw_dbg_cq(cq,
-				   "idx %u, type %d, flags %2x, id 0x%pK\n",
+				   "idx %u, type %d, flags %2x, id 0x%p\n",
 				   cq->cq_get % cq->num_cqe, cqe->opcode,
 				   cqe->flags, (void *)(uintptr_t)cqe->id);
 		} else {
diff --git a/drivers/infiniband/sw/siw/siw_mem.c b/drivers/infiniband/sw/siw/siw_mem.c
index dcb963607c8b..d5ddeb17bd22 100644
--- a/drivers/infiniband/sw/siw/siw_mem.c
+++ b/drivers/infiniband/sw/siw/siw_mem.c
@@ -18,30 +18,6 @@
 #define SIW_STAG_MAX_INDEX	0x00ffffff
 
 /*
- * The code avoids special Stag of zero and tries to randomize
- * STag values between 1 and SIW_STAG_MAX_INDEX.
- */
-int siw_mem_add(struct siw_device *sdev, struct siw_mem *m)
-{
-	struct xa_limit limit = XA_LIMIT(1, SIW_STAG_MAX_INDEX);
-	u32 id, next;
-
-	get_random_bytes(&next, 4);
-	next &= SIW_STAG_MAX_INDEX;
-
-	if (xa_alloc_cyclic(&sdev->mem_xa, &id, m, limit, &next,
-	    GFP_KERNEL) < 0)
-		return -ENOMEM;
-
-	/* Set the STag index part */
-	m->stag = id << 8;
-
-	siw_dbg_mem(m, "new MEM object\n");
-
-	return 0;
-}
-
-/*
  * siw_mem_id2obj()
  *
  * resolves memory from stag given by id. might be called from:
@@ -181,10 +157,10 @@ int siw_check_mem(struct ib_pd *pd, struct siw_mem *mem, u64 addr,
 	 */
 	if (addr < mem->va || addr + len > mem->va + mem->len) {
 		siw_dbg_pd(pd, "MEM interval len %d\n", len);
-		siw_dbg_pd(pd, "[0x%pK, 0x%pK] out of bounds\n",
+		siw_dbg_pd(pd, "[0x%p, 0x%p] out of bounds\n",
 			   (void *)(uintptr_t)addr,
 			   (void *)(uintptr_t)(addr + len));
-		siw_dbg_pd(pd, "[0x%pK, 0x%pK] STag=0x%08x\n",
+		siw_dbg_pd(pd, "[0x%p, 0x%p] STag=0x%08x\n",
 			   (void *)(uintptr_t)mem->va,
 			   (void *)(uintptr_t)(mem->va + mem->len),
 			   mem->stag);
diff --git a/drivers/infiniband/sw/siw/siw_mem.h b/drivers/infiniband/sw/siw/siw_mem.h
index e74cfcd6dbc1..8e769d30e2ac 100644
--- a/drivers/infiniband/sw/siw/siw_mem.h
+++ b/drivers/infiniband/sw/siw/siw_mem.h
@@ -12,7 +12,6 @@ void siw_umem_release(struct siw_umem *umem);
 struct siw_pbl *siw_pbl_alloc(u32 num_buf);
 dma_addr_t siw_pbl_get_buffer(struct siw_pbl *pbl, u64 off, int *len, int *idx);
 struct siw_mem *siw_mem_id2obj(struct siw_device *sdev, int stag_index);
-int siw_mem_add(struct siw_device *sdev, struct siw_mem *m);
 int siw_invalidate_stag(struct ib_pd *pd, u32 stag);
 int siw_check_mem(struct ib_pd *pd, struct siw_mem *mem, u64 addr,
 		  enum ib_access_flags perms, int len);
diff --git a/drivers/infiniband/sw/siw/siw_qp_rx.c b/drivers/infiniband/sw/siw/siw_qp_rx.c
index 32554eba1eac..a10820e33887 100644
--- a/drivers/infiniband/sw/siw/siw_qp_rx.c
+++ b/drivers/infiniband/sw/siw/siw_qp_rx.c
@@ -38,7 +38,7 @@ static int siw_rx_umem(struct siw_rx_stream *srx, struct siw_umem *umem,
 
 		p = siw_get_upage(umem, dest_addr);
 		if (unlikely(!p)) {
-			pr_warn("siw: %s: [QP %u]: bogus addr: %pK, %pK\n",
+			pr_warn("siw: %s: [QP %u]: bogus addr: %p, %p\n",
 				__func__, qp_id(rx_qp(srx)),
 				(void *)(uintptr_t)dest_addr,
 				(void *)(uintptr_t)umem->fp_addr);
@@ -51,7 +51,7 @@ static int siw_rx_umem(struct siw_rx_stream *srx, struct siw_umem *umem,
 		pg_off = dest_addr & ~PAGE_MASK;
 		bytes = min(len, (int)PAGE_SIZE - pg_off);
 
-		siw_dbg_qp(rx_qp(srx), "page %pK, bytes=%u\n", p, bytes);
+		siw_dbg_qp(rx_qp(srx), "page %p, bytes=%u\n", p, bytes);
 
 		dest = kmap_atomic(p);
 		rv = skb_copy_bits(srx->skb, srx->skb_offset, dest + pg_off,
@@ -105,11 +105,11 @@ static int siw_rx_kva(struct siw_rx_stream *srx, void *kva, int len)
 {
 	int rv;
 
-	siw_dbg_qp(rx_qp(srx), "kva: 0x%pK, len: %u\n", kva, len);
+	siw_dbg_qp(rx_qp(srx), "kva: 0x%p, len: %u\n", kva, len);
 
 	rv = skb_copy_bits(srx->skb, srx->skb_offset, kva, len);
 	if (unlikely(rv)) {
-		pr_warn("siw: [QP %u]: %s, len %d, kva 0x%pK, rv %d\n",
+		pr_warn("siw: [QP %u]: %s, len %d, kva 0x%p, rv %d\n",
 			qp_id(rx_qp(srx)), __func__, len, kva, rv);
 
 		return rv;
diff --git a/drivers/infiniband/sw/siw/siw_verbs.c b/drivers/infiniband/sw/siw/siw_verbs.c
index fd7b266a221b..2b2a7b8e93b0 100644
--- a/drivers/infiniband/sw/siw/siw_verbs.c
+++ b/drivers/infiniband/sw/siw/siw_verbs.c
@@ -936,7 +936,7 @@ int siw_post_send(struct ib_qp *base_qp, const struct ib_send_wr *wr,
 			rv = -EINVAL;
 			break;
 		}
-		siw_dbg_qp(qp, "opcode %d, flags 0x%x, wr_id 0x%pK\n",
+		siw_dbg_qp(qp, "opcode %d, flags 0x%x, wr_id 0x%p\n",
 			   sqe->opcode, sqe->flags,
 			   (void *)(uintptr_t)sqe->id);
 
@@ -1102,7 +1102,7 @@ int siw_post_receive(struct ib_qp *base_qp, const struct ib_recv_wr *wr,
 		siw_dbg_qp(qp, "error %d\n", rv);
 		*bad_wr = wr;
 	}
-	return rv > 0 ? 0 : rv;
+	return rv;
 }
 
 int siw_destroy_cq(struct ib_cq *base_cq, struct ib_udata *udata)
@@ -1332,7 +1332,7 @@ struct ib_mr *siw_reg_user_mr(struct ib_pd *pd, u64 start, u64 len,
 	struct siw_device *sdev = to_siw_dev(pd->device);
 	int rv;
 
-	siw_dbg_pd(pd, "start: 0x%pK, va: 0x%pK, len: %llu\n",
+	siw_dbg_pd(pd, "start: 0x%p, va: 0x%p, len: %llu\n",
 		   (void *)(uintptr_t)start, (void *)(uintptr_t)rnic_va,
 		   (unsigned long long)len);
 
@@ -1525,7 +1525,7 @@ int siw_map_mr_sg(struct ib_mr *base_mr, struct scatterlist *sl, int num_sle,
 		mem->len = base_mr->length;
 		mem->va = base_mr->iova;
 		siw_dbg_mem(mem,
-			"%llu bytes, start 0x%pK, %u SLE to %u entries\n",
+			"%llu bytes, start 0x%p, %u SLE to %u entries\n",
 			mem->len, (void *)(uintptr_t)mem->va, num_sle,
 			pbl->num_buf);
 	}