Merge remote-tracking branch 'remotes/marcel/tags/rdma-pull-request' into staging

RDMA queue

* better memory registration performance

# gpg: Signature made Wed 06 Nov 2019 14:37:47 GMT
# gpg:                using RSA key 36D4C0F0CF2FE46D
# gpg: Good signature from "Marcel Apfelbaum <marcel.apfelbaum@zoho.com>" [marginal]
# gpg:                 aka "Marcel Apfelbaum <marcel@redhat.com>" [marginal]
# gpg:                 aka "Marcel Apfelbaum <marcel.apfelbaum@gmail.com>" [marginal]
# gpg: WARNING: This key is not certified with sufficiently trusted signatures!
# gpg:          It is not certain that the signature belongs to the owner.
# Primary key fingerprint: B1C6 3A57 F92E 08F2 640F  31F5 36D4 C0F0 CF2F E46D

* remotes/marcel/tags/rdma-pull-request:
  hw/rdma: Utilize ibv_reg_mr_iova for memory registration
  configure: Check if we can use ibv_reg_mr_iova

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

5 files changed, 57 insertions, 0 deletions

diff --git a/configure b/configure
index 72553f98eaa..efe165edf9a 100755
--- a/configure
+++ b/configure
@@ -3217,6 +3217,34 @@ else
     pvrdma="no"
 fi
 
+# Let's see if enhanced reg_mr is supported
+if test "$pvrdma" = "yes" ; then
+
+cat > $TMPC <<EOF &&
+#include <infiniband/verbs.h>
+
+int
+main(void)
+{
+    struct ibv_mr *mr;
+    struct ibv_pd *pd = NULL;
+    size_t length = 10;
+    uint64_t iova = 0;
+    int access = 0;
+    void *addr = NULL;
+
+    mr = ibv_reg_mr_iova(pd, addr, length, iova, access);
+
+    ibv_dereg_mr(mr);
+
+    return 0;
+}
+EOF
+    if ! compile_prog "" "-libverbs"; then
+        QEMU_CFLAGS="$QEMU_CFLAGS -DLEGACY_RDMA_REG_MR"
+    fi
+fi
+
 ##########################################
 # VNC SASL detection
 if test "$vnc" = "yes" && test "$vnc_sasl" != "no" ; then
diff --git a/hw/rdma/rdma_backend.c b/hw/rdma/rdma_backend.c
index c39051068d1..c346407cd36 100644
--- a/hw/rdma/rdma_backend.c
+++ b/hw/rdma/rdma_backend.c
@@ -391,7 +391,11 @@ static int build_host_sge_array(RdmaDeviceResources *rdma_dev_res,
             return VENDOR_ERR_INVLKEY | ssge[ssge_idx].lkey;
         }
 
+#ifdef LEGACY_RDMA_REG_MR
         dsge->addr = (uintptr_t)mr->virt + ssge[ssge_idx].addr - mr->start;
+#else
+        dsge->addr = ssge[ssge_idx].addr;
+#endif
         dsge->length = ssge[ssge_idx].length;
         dsge->lkey = rdma_backend_mr_lkey(&mr->backend_mr);
 
@@ -735,10 +739,19 @@ void rdma_backend_destroy_pd(RdmaBackendPD *pd)
     }
 }
 
+#ifdef LEGACY_RDMA_REG_MR
 int rdma_backend_create_mr(RdmaBackendMR *mr, RdmaBackendPD *pd, void *addr,
                            size_t length, int access)
+#else
+int rdma_backend_create_mr(RdmaBackendMR *mr, RdmaBackendPD *pd, void *addr,
+                           size_t length, uint64_t guest_start, int access)
+#endif
 {
+#ifdef LEGACY_RDMA_REG_MR
     mr->ibmr = ibv_reg_mr(pd->ibpd, addr, length, access);
+#else
+    mr->ibmr = ibv_reg_mr_iova(pd->ibpd, addr, length, guest_start, access);
+#endif
     if (!mr->ibmr) {
         rdma_error_report("ibv_reg_mr fail, errno=%d", errno);
         return -EIO;
diff --git a/hw/rdma/rdma_backend.h b/hw/rdma/rdma_backend.h
index 7c1a19a2b5f..127f96e2d53 100644
--- a/hw/rdma/rdma_backend.h
+++ b/hw/rdma/rdma_backend.h
@@ -78,8 +78,13 @@ int rdma_backend_query_port(RdmaBackendDev *backend_dev,
 int rdma_backend_create_pd(RdmaBackendDev *backend_dev, RdmaBackendPD *pd);
 void rdma_backend_destroy_pd(RdmaBackendPD *pd);
 
+#ifdef LEGACY_RDMA_REG_MR
 int rdma_backend_create_mr(RdmaBackendMR *mr, RdmaBackendPD *pd, void *addr,
                            size_t length, int access);
+#else
+int rdma_backend_create_mr(RdmaBackendMR *mr, RdmaBackendPD *pd, void *addr,
+                           size_t length, uint64_t guest_start, int access);
+#endif
 void rdma_backend_destroy_mr(RdmaBackendMR *mr);
 
 int rdma_backend_create_cq(RdmaBackendDev *backend_dev, RdmaBackendCQ *cq,
diff --git a/hw/rdma/rdma_rm.c b/hw/rdma/rdma_rm.c
index 1927f85472a..1524dfaeaa7 100644
--- a/hw/rdma/rdma_rm.c
+++ b/hw/rdma/rdma_rm.c
@@ -227,8 +227,13 @@ int rdma_rm_alloc_mr(RdmaDeviceResources *dev_res, uint32_t pd_handle,
         mr->length = guest_length;
         mr->virt += (mr->start & (TARGET_PAGE_SIZE - 1));
 
+#ifdef LEGACY_RDMA_REG_MR
         ret = rdma_backend_create_mr(&mr->backend_mr, &pd->backend_pd, mr->virt,
                                      mr->length, access_flags);
+#else
+        ret = rdma_backend_create_mr(&mr->backend_mr, &pd->backend_pd, mr->virt,
+                                     mr->length, guest_start, access_flags);
+#endif
         if (ret) {
             ret = -EIO;
             goto out_dealloc_mr;
diff --git a/hw/rdma/vmw/pvrdma_main.c b/hw/rdma/vmw/pvrdma_main.c
index 3722d9e772a..6f0fc405c77 100644
--- a/hw/rdma/vmw/pvrdma_main.c
+++ b/hw/rdma/vmw/pvrdma_main.c
@@ -664,6 +664,12 @@ static void pvrdma_realize(PCIDevice *pdev, Error **errp)
     dev->shutdown_notifier.notify = pvrdma_shutdown_notifier;
     qemu_register_shutdown_notifier(&dev->shutdown_notifier);
 
+#ifdef LEGACY_RDMA_REG_MR
+    rdma_info_report("Using legacy reg_mr");
+#else
+    rdma_info_report("Using iova reg_mr");
+#endif
+
 out:
     if (rc) {
         pvrdma_fini(pdev);