@@ -88,6 +88,7 @@ static void rxe_init_device_param(struct rxe_dev *rxe)
rxe->attr.odp_caps.per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_RECV;
rxe->attr.odp_caps.per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_WRITE;
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;
}
}
@@ -194,5 +194,7 @@ int rxe_create_user_odp_mr(struct ib_pd *pd, 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);
+enum resp_states rxe_odp_atomic_ops(struct rxe_qp *qp, struct rxe_pkt_info *pkt,
+ struct rxe_mr *mr);
#endif /* RXE_LOC_H */
@@ -8,6 +8,7 @@
#include <rdma/ib_umem_odp.h>
#include "rxe.h"
+#include "rxe_resp.h"
bool rxe_ib_invalidate_range(struct mmu_interval_notifier *mni,
const struct mmu_notifier_range *range,
@@ -285,3 +286,44 @@ int rxe_odp_mr_copy(struct rxe_mr *mr, u64 iova, void *addr, int length,
return __rxe_odp_mr_copy(mr, iova, addr, length, dir);
}
+
+static inline void *rxe_odp_get_virt_atomic(struct rxe_qp *qp, struct rxe_mr *mr)
+{
+ struct ib_umem_odp *umem_odp = to_ib_umem_odp(mr->umem);
+ u64 iova = qp->resp.va + qp->resp.offset;
+ int idx;
+ size_t offset;
+
+ if (rxe_odp_map_range(mr, iova, sizeof(char), 0))
+ return NULL;
+
+ idx = (iova - ib_umem_start(umem_odp)) >> umem_odp->page_shift;
+ offset = iova & (BIT(umem_odp->page_shift) - 1);
+
+ return rxe_odp_get_virt(umem_odp, idx, offset);
+}
+
+enum resp_states rxe_odp_atomic_ops(struct rxe_qp *qp, struct rxe_pkt_info *pkt,
+ struct rxe_mr *mr)
+{
+ struct ib_umem_odp *umem_odp = to_ib_umem_odp(mr->umem);
+ u64 *vaddr;
+ int ret;
+
+ if (WARN_ON(!mr->odp_enabled))
+ return RESPST_ERR_RKEY_VIOLATION;
+
+ /* umem mutex is locked here to prevent MR invalidation before memory
+ * access completes.
+ */
+ vaddr = (u64 *)rxe_odp_get_virt_atomic(qp, mr);
+
+ if (pkt->mask & RXE_ATOMIC_MASK)
+ ret = rxe_process_atomic(qp, pkt, vaddr);
+ else
+ /* ATOMIC WRITE operation will come here. */
+ ret = RESPST_ERR_RKEY_VIOLATION;
+
+ mutex_unlock(&umem_odp->umem_mutex);
+ return ret;
+}
@@ -9,41 +9,7 @@
#include "rxe.h"
#include "rxe_loc.h"
#include "rxe_queue.h"
-
-enum resp_states {
- RESPST_NONE,
- RESPST_GET_REQ,
- RESPST_CHK_PSN,
- RESPST_CHK_OP_SEQ,
- RESPST_CHK_OP_VALID,
- RESPST_CHK_RESOURCE,
- RESPST_CHK_LENGTH,
- RESPST_CHK_RKEY,
- RESPST_EXECUTE,
- RESPST_READ_REPLY,
- RESPST_ATOMIC_REPLY,
- RESPST_COMPLETE,
- RESPST_ACKNOWLEDGE,
- RESPST_CLEANUP,
- RESPST_DUPLICATE_REQUEST,
- RESPST_ERR_MALFORMED_WQE,
- RESPST_ERR_UNSUPPORTED_OPCODE,
- RESPST_ERR_MISALIGNED_ATOMIC,
- RESPST_ERR_PSN_OUT_OF_SEQ,
- RESPST_ERR_MISSING_OPCODE_FIRST,
- RESPST_ERR_MISSING_OPCODE_LAST_C,
- RESPST_ERR_MISSING_OPCODE_LAST_D1E,
- RESPST_ERR_TOO_MANY_RDMA_ATM_REQ,
- RESPST_ERR_RNR,
- RESPST_ERR_RKEY_VIOLATION,
- RESPST_ERR_INVALIDATE_RKEY,
- RESPST_ERR_LENGTH,
- RESPST_ERR_CQ_OVERFLOW,
- RESPST_ERROR,
- RESPST_RESET,
- RESPST_DONE,
- RESPST_EXIT,
-};
+#include "rxe_resp.h"
static char *resp_state_name[] = {
[RESPST_NONE] = "NONE",
@@ -673,7 +639,7 @@ static enum resp_states rxe_atomic_reply(struct rxe_qp *qp,
return RESPST_ERR_RKEY_VIOLATION;
if (mr->odp_enabled)
- ret = RESPST_ERR_UNSUPPORTED_OPCODE;
+ ret = rxe_odp_atomic_ops(qp, pkt, mr);
else
ret = rxe_atomic_ops(qp, pkt, mr);
} else
new file mode 100644
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+
+#ifndef RXE_RESP_H
+#define RXE_RESP_H
+
+enum resp_states {
+ RESPST_NONE,
+ RESPST_GET_REQ,
+ RESPST_CHK_PSN,
+ RESPST_CHK_OP_SEQ,
+ RESPST_CHK_OP_VALID,
+ RESPST_CHK_RESOURCE,
+ RESPST_CHK_LENGTH,
+ RESPST_CHK_RKEY,
+ RESPST_EXECUTE,
+ RESPST_READ_REPLY,
+ RESPST_ATOMIC_REPLY,
+ RESPST_COMPLETE,
+ RESPST_ACKNOWLEDGE,
+ RESPST_CLEANUP,
+ RESPST_DUPLICATE_REQUEST,
+ RESPST_ERR_MALFORMED_WQE,
+ RESPST_ERR_UNSUPPORTED_OPCODE,
+ RESPST_ERR_MISALIGNED_ATOMIC,
+ RESPST_ERR_PSN_OUT_OF_SEQ,
+ RESPST_ERR_MISSING_OPCODE_FIRST,
+ RESPST_ERR_MISSING_OPCODE_LAST_C,
+ RESPST_ERR_MISSING_OPCODE_LAST_D1E,
+ RESPST_ERR_TOO_MANY_RDMA_ATM_REQ,
+ RESPST_ERR_RNR,
+ RESPST_ERR_RKEY_VIOLATION,
+ RESPST_ERR_INVALIDATE_RKEY,
+ RESPST_ERR_LENGTH,
+ RESPST_ERR_CQ_OVERFLOW,
+ RESPST_ERROR,
+ RESPST_RESET,
+ RESPST_DONE,
+ RESPST_EXIT,
+};
+
+enum resp_states rxe_process_atomic(struct rxe_qp *qp,
+ struct rxe_pkt_info *pkt, u64 *vaddr);
+
+#endif /* RXE_RESP_H */
Enable 'fetch and add' and 'compare and swap' operations to manipulate data in an ODP-enabled MR. This is comprised of the following steps: 1. Check the driver page table(umem_odp->dma_list) to see if the target page is both readable and writable. 2. If not, then trigger page fault to map the page. 3. Convert its user space address to a kernel logical address using PFNs in the driver page table(umem_odp->pfn_list). 4. Execute the operation. umem_mutex is used to ensure that dma_list (an array of addresses of an MR) is not changed while it is checked and that the target page is not invalidated before data access completes. Signed-off-by: Daisuke Matsuda <matsuda-daisuke@fujitsu.com> --- drivers/infiniband/sw/rxe/rxe.c | 1 + drivers/infiniband/sw/rxe/rxe_loc.h | 2 ++ drivers/infiniband/sw/rxe/rxe_odp.c | 42 ++++++++++++++++++++++++++ drivers/infiniband/sw/rxe/rxe_resp.c | 38 ++---------------------- drivers/infiniband/sw/rxe/rxe_resp.h | 44 ++++++++++++++++++++++++++++ 5 files changed, 91 insertions(+), 36 deletions(-) create mode 100644 drivers/infiniband/sw/rxe/rxe_resp.h