New adapters expose additional ordering capabilities.
Query the new caps and apply them when creating DevX mkeys via
mlx5_devx_mkey_attr_set_ordering(), which sets PCI relaxed ordering
and RAW=RO when relaxed order is supported.
Use this helper on Windows (still gated by Haswell/Broadwell) and for
Linux wrapped mkeys and crypto/regex/vdpa indirect mkeys when
relaxed order only flag is set.
Linux wrapped mkeys continue to use the legacy Haswell/Broadwell rule for
IBV_ACCESS_RELAXED_ORDERING on the verbs MR.
Upcoming FW will requires setting the correct ordering attributes,
otherwise it fails to create the memory key.

Signed-off-by: Maayan Kashani <[email protected]>
Acked-by: Viacheslav Ovsiienko <[email protected]>
---
 drivers/common/mlx5/linux/mlx5_common_os.c   |  8 +++++
 drivers/common/mlx5/mlx5_devx_cmds.c         | 31 ++++++++++++++++++++
 drivers/common/mlx5/mlx5_devx_cmds.h         |  9 ++++++
 drivers/common/mlx5/mlx5_prm.h               | 18 ++++++++++--
 drivers/common/mlx5/windows/mlx5_common_os.c |  8 ++---
 drivers/crypto/mlx5/mlx5_crypto.c            |  4 +++
 drivers/regex/mlx5/mlx5_regex_fastpath.c     |  5 ++++
 drivers/regex/mlx5/mlx5_rxp.c                |  4 +++
 drivers/vdpa/mlx5/mlx5_vdpa_mem.c            |  4 +++
 9 files changed, 83 insertions(+), 8 deletions(-)

diff --git a/drivers/common/mlx5/linux/mlx5_common_os.c 
b/drivers/common/mlx5/linux/mlx5_common_os.c
index e3db6c41245..36b7874ce77 100644
--- a/drivers/common/mlx5/linux/mlx5_common_os.c
+++ b/drivers/common/mlx5/linux/mlx5_common_os.c
@@ -997,6 +997,7 @@ int
 mlx5_os_wrapped_mkey_create(void *ctx, void *pd, uint32_t pdn, void *addr,
                            size_t length, struct mlx5_pmd_wrapped_mr *pmd_mr)
 {
+       struct mlx5_hca_attr hca_attr = { 0 };
        struct mlx5_klm klm = {
                .byte_count = length,
                .address = (uintptr_t)addr,
@@ -1019,6 +1020,13 @@ mlx5_os_wrapped_mkey_create(void *ctx, void *pd, 
uint32_t pdn, void *addr,
        klm.mkey = ibv_mr->lkey;
        mkey_attr.addr = (uintptr_t)addr;
        mkey_attr.size = length;
+       if (mlx5_devx_cmd_query_hca_attr(ctx, &hca_attr)) {
+               claim_zero(mlx5_glue->dereg_mr(ibv_mr));
+               return -1;
+       }
+       /* If only relaxed order is allowed. */
+       if (hca_attr.mkc_order_write_after_write_ro_only)
+               mlx5_devx_mkey_attr_set_ordering(&mkey_attr, &hca_attr);
        mkey = mlx5_devx_cmd_mkey_create(ctx, &mkey_attr);
        if (!mkey) {
                claim_zero(mlx5_glue->dereg_mr(ibv_mr));
diff --git a/drivers/common/mlx5/mlx5_devx_cmds.c 
b/drivers/common/mlx5/mlx5_devx_cmds.c
index c4ac2aaceed..140b057ab47 100644
--- a/drivers/common/mlx5/mlx5_devx_cmds.c
+++ b/drivers/common/mlx5/mlx5_devx_cmds.c
@@ -331,6 +331,29 @@ mlx5_devx_cmd_flow_counter_query(struct mlx5_devx_obj *dcs,
        return 0;
 }
 
+/**
+ * Apply PCI relaxed-ordering and read-after-write ordering to mkey attributes.
+ *
+ * @param[in, out] mkey_attr
+ *   Mkey attributes to update.
+ * @param[in] hca_attr
+ *   HCA capabilities from mlx5_devx_cmd_query_hca_attr().
+ */
+RTE_EXPORT_INTERNAL_SYMBOL(mlx5_devx_mkey_attr_set_ordering)
+void
+mlx5_devx_mkey_attr_set_ordering(struct mlx5_devx_mkey_attr *mkey_attr,
+                                const struct mlx5_hca_attr *hca_attr)
+{
+       if (!mkey_attr || !hca_attr)
+               return;
+
+       mkey_attr->relaxed_ordering_write = hca_attr->relaxed_ordering_write;
+       mkey_attr->relaxed_ordering_read =
+               hca_attr->relaxed_ordering_read || 
hca_attr->pci_relaxed_ordered_read;
+       if (hca_attr->mkc_order_read_after_write)
+               mkey_attr->read_after_write_ordering = MLX5_MKC_RAW_ORDERING_RO;
+}
+
 /**
  * Create a new mkey.
  *
@@ -417,6 +440,8 @@ mlx5_devx_cmd_mkey_create(void *ctx,
        MLX5_SET(mkc, mkc, relaxed_ordering_write,
                 attr->relaxed_ordering_write);
        MLX5_SET(mkc, mkc, relaxed_ordering_read, attr->relaxed_ordering_read);
+       MLX5_SET(mkc, mkc, order_read_after_write,
+                attr->read_after_write_ordering);
        MLX5_SET64(mkc, mkc, start_addr, attr->addr);
        MLX5_SET64(mkc, mkc, len, attr->size);
        MLX5_SET(mkc, mkc, crypto_en, attr->crypto_en);
@@ -1003,6 +1028,12 @@ mlx5_devx_cmd_query_hca_attr(void *ctx,
                                                relaxed_ordering_write);
        attr->relaxed_ordering_read = MLX5_GET(cmd_hca_cap, hcattr,
                                               relaxed_ordering_read);
+       attr->pci_relaxed_ordered_read = MLX5_GET(cmd_hca_cap, hcattr,
+                                                 pci_relaxed_ordered_read);
+       attr->mkc_order_read_after_write = MLX5_GET(cmd_hca_cap, hcattr,
+                                                   mkc_order_read_after_write);
+       attr->mkc_order_write_after_write_ro_only = MLX5_GET(cmd_hca_cap, 
hcattr,
+                                                            
mkc_order_write_after_write_ro_only);
        attr->access_register_user = MLX5_GET(cmd_hca_cap, hcattr,
                                              access_register_user);
        attr->eth_net_offloads = MLX5_GET(cmd_hca_cap, hcattr,
diff --git a/drivers/common/mlx5/mlx5_devx_cmds.h 
b/drivers/common/mlx5/mlx5_devx_cmds.h
index 82d949972bb..90beb2e9e6c 100644
--- a/drivers/common/mlx5/mlx5_devx_cmds.h
+++ b/drivers/common/mlx5/mlx5_devx_cmds.h
@@ -34,6 +34,7 @@ struct mlx5_devx_mkey_attr {
        uint32_t pg_access:1;
        uint32_t relaxed_ordering_write:1;
        uint32_t relaxed_ordering_read:1;
+       uint32_t read_after_write_ordering:2;
        uint32_t umr_en:1;
        uint32_t crypto_en:2;
        uint32_t set_remote_rw:1;
@@ -237,6 +238,9 @@ struct mlx5_hca_attr {
        uint32_t vhca_id:16;
        uint32_t relaxed_ordering_write:1;
        uint32_t relaxed_ordering_read:1;
+       uint32_t pci_relaxed_ordered_read:1;
+       uint32_t mkc_order_read_after_write:1;
+       uint32_t mkc_order_write_after_write_ro_only:1;
        uint32_t access_register_user:1;
        uint32_t wqe_index_ignore:1;
        uint32_t cross_channel:1;
@@ -748,6 +752,11 @@ int mlx5_devx_cmd_query_hca_attr(void *ctx,
 __rte_internal
 struct mlx5_devx_obj *mlx5_devx_cmd_mkey_create(void *ctx,
                                              struct mlx5_devx_mkey_attr *attr);
+
+__rte_internal
+void
+mlx5_devx_mkey_attr_set_ordering(struct mlx5_devx_mkey_attr *mkey_attr,
+                                const struct mlx5_hca_attr *hca_attr);
 __rte_internal
 int mlx5_devx_get_out_command_status(void *out);
 __rte_internal
diff --git a/drivers/common/mlx5/mlx5_prm.h b/drivers/common/mlx5/mlx5_prm.h
index 3bb072a7fec..c2810194f8e 100644
--- a/drivers/common/mlx5/mlx5_prm.h
+++ b/drivers/common/mlx5/mlx5_prm.h
@@ -1463,7 +1463,9 @@ struct mlx5_ifc_mkc_bits {
        u8 bsf_octword_size[0x20];
        u8 reserved_at_120[0x80];
        u8 translations_octword_size[0x20];
-       u8 reserved_at_1c0[0x19];
+       u8 reserved_at_1c0[0x16];
+       u8 order_read_after_write[0x2];
+       u8 reserved_at_1d8[0x1];
        u8 relaxed_ordering_read[0x1];
        u8 reserved_at_1da[0x1];
        u8 log_page_size[0x5];
@@ -1478,6 +1480,13 @@ enum {
        MLX5_MKEY_CRYPTO_ENABLED = 0x1,
 };
 
+/* MKC read_after_write_ordering field (2-bit, dword 0x38 bits 9:8). */
+enum mlx5_mkc_raw_ordering {
+       MLX5_MKC_RAW_ORDERING_SO = 0x0,
+       MLX5_MKC_RAW_ORDERING_SAO = 0x1,
+       MLX5_MKC_RAW_ORDERING_RO = 0x2,
+};
+
 struct mlx5_ifc_create_mkey_out_bits {
        u8 status[0x8];
        u8 reserved_at_8[0x18];
@@ -1827,7 +1836,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
        u8 log_max_mcg[0x8];
        u8 reserved_at_320[0x3];
        u8 log_max_transport_domain[0x5];
-       u8 reserved_at_328[0x3];
+       u8 reserved_at_328[0x2];
+       u8 pci_relaxed_ordered_read[0x1];
        u8 log_max_pd[0x5];
        u8 reserved_at_330[0xb];
        u8 log_max_xrcd[0x5];
@@ -1860,7 +1870,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
        u8 ext_stride_num_range[0x1];
        u8 reserved_at_3a1[0x2];
        u8 log_max_stride_sz_rq[0x5];
-       u8 reserved_at_3a8[0x3];
+       u8 mkc_order_read_after_write[0x1];
+       u8 mkc_order_write_after_write_ro_only[0x1];
+       u8 reserved_at_3aa[0x1];
        u8 log_min_stride_sz_rq[0x5];
        u8 reserved_at_3b0[0x3];
        u8 log_max_stride_sz_sq[0x5];
diff --git a/drivers/common/mlx5/windows/mlx5_common_os.c 
b/drivers/common/mlx5/windows/mlx5_common_os.c
index c790c9a4aeb..bdafb95df98 100644
--- a/drivers/common/mlx5/windows/mlx5_common_os.c
+++ b/drivers/common/mlx5/windows/mlx5_common_os.c
@@ -384,7 +384,7 @@ mlx5_os_reg_mr(void *pd,
 {
        struct mlx5_devx_mkey_attr mkey_attr;
        struct mlx5_pd *mlx5_pd = (struct mlx5_pd *)pd;
-       struct mlx5_hca_attr attr;
+       struct mlx5_hca_attr attr = { 0 };
        struct mlx5_devx_obj *mkey;
        void *obj;
 
@@ -403,10 +403,8 @@ mlx5_os_reg_mr(void *pd,
        mkey_attr.size = length;
        mkey_attr.umem_id = ((struct mlx5_devx_umem *)(obj))->umem_id;
        mkey_attr.pd = mlx5_pd->pdn;
-       if (!mlx5_haswell_broadwell_cpu) {
-               mkey_attr.relaxed_ordering_write = attr.relaxed_ordering_write;
-               mkey_attr.relaxed_ordering_read = attr.relaxed_ordering_read;
-       }
+       if (!mlx5_haswell_broadwell_cpu)
+               mlx5_devx_mkey_attr_set_ordering(&mkey_attr, &attr);
        mkey = mlx5_devx_cmd_mkey_create(mlx5_pd->devx_ctx, &mkey_attr);
        if (!mkey) {
                claim_zero(mlx5_os_umem_dereg(obj));
diff --git a/drivers/crypto/mlx5/mlx5_crypto.c 
b/drivers/crypto/mlx5/mlx5_crypto.c
index dd0aabb6d75..448dd0c5a4e 100644
--- a/drivers/crypto/mlx5/mlx5_crypto.c
+++ b/drivers/crypto/mlx5/mlx5_crypto.c
@@ -97,7 +97,11 @@ mlx5_crypto_indirect_mkeys_prepare(struct mlx5_crypto_priv 
*priv,
                                   mlx5_crypto_mkey_update_t update_cb)
 {
        uint32_t i;
+       struct mlx5_hca_attr *hca_attr = &priv->cdev->config.hca_attr;
 
+       /* If only relaxed order is allowed. */
+       if (hca_attr->mkc_order_write_after_write_ro_only)
+               mlx5_devx_mkey_attr_set_ordering(attr, hca_attr);
        for (i = 0; i < qp->entries_n; i++) {
                attr->klm_array = update_cb(priv, qp, i);
                qp->mkey[i] = mlx5_devx_cmd_mkey_create(priv->cdev->ctx, attr);
diff --git a/drivers/regex/mlx5/mlx5_regex_fastpath.c 
b/drivers/regex/mlx5/mlx5_regex_fastpath.c
index 3207bcbc603..55f7411593a 100644
--- a/drivers/regex/mlx5/mlx5_regex_fastpath.c
+++ b/drivers/regex/mlx5/mlx5_regex_fastpath.c
@@ -755,9 +755,14 @@ mlx5_regexdev_setup_fastpath(struct mlx5_regex_priv *priv, 
uint32_t qp_id)
        setup_qps(priv, qp);
 
        if (priv->has_umr) {
+               struct mlx5_hca_attr *hca_attr = &priv->cdev->config.hca_attr;
+
 #ifdef HAVE_IBV_FLOW_DV_SUPPORT
                attr.pd = priv->cdev->pdn;
 #endif
+               /* If only relaxed order is allowed. */
+               if (hca_attr->mkc_order_write_after_write_ro_only)
+                       mlx5_devx_mkey_attr_set_ordering(&attr, hca_attr);
                for (i = 0; i < qp->nb_desc; i++) {
                        attr.klm_num = MLX5_REGEX_MAX_KLM_NUM;
                        attr.klm_array = qp->jobs[i].imkey_array;
diff --git a/drivers/regex/mlx5/mlx5_rxp.c b/drivers/regex/mlx5/mlx5_rxp.c
index dda4a7fdb0b..b865c08b53c 100644
--- a/drivers/regex/mlx5/mlx5_rxp.c
+++ b/drivers/regex/mlx5/mlx5_rxp.c
@@ -54,6 +54,7 @@ rxp_create_mkey(struct mlx5_regex_priv *priv, void *ptr, 
size_t size,
        uint32_t access, struct mlx5_regex_mkey *mkey)
 {
        struct mlx5_devx_mkey_attr mkey_attr;
+       struct mlx5_hca_attr *hca_attr = &priv->cdev->config.hca_attr;
 
        /* Register the memory. */
        mkey->umem = mlx5_glue->devx_umem_reg(priv->cdev->ctx, ptr, size, 
access);
@@ -72,6 +73,9 @@ rxp_create_mkey(struct mlx5_regex_priv *priv, void *ptr, 
size_t size,
 #ifdef HAVE_IBV_FLOW_DV_SUPPORT
        mkey_attr.pd = priv->cdev->pdn;
 #endif
+       /* If only relaxed order is allowed. */
+       if (hca_attr->mkc_order_write_after_write_ro_only)
+               mlx5_devx_mkey_attr_set_ordering(&mkey_attr, hca_attr);
        mkey->mkey = mlx5_devx_cmd_mkey_create(priv->cdev->ctx, &mkey_attr);
        if (!mkey->mkey) {
                DRV_LOG(ERR, "Failed to create direct mkey!");
diff --git a/drivers/vdpa/mlx5/mlx5_vdpa_mem.c 
b/drivers/vdpa/mlx5/mlx5_vdpa_mem.c
index 4dfe800b8fc..8c9d169d2a8 100644
--- a/drivers/vdpa/mlx5/mlx5_vdpa_mem.c
+++ b/drivers/vdpa/mlx5/mlx5_vdpa_mem.c
@@ -179,6 +179,7 @@ static int
 mlx5_vdpa_create_indirect_mkey(struct mlx5_vdpa_priv *priv)
 {
        struct mlx5_devx_mkey_attr mkey_attr;
+       struct mlx5_hca_attr *hca_attr = &priv->cdev->config.hca_attr;
        struct mlx5_vdpa_query_mr *mrs =
                (struct mlx5_vdpa_query_mr *)priv->mrs;
        struct mlx5_vdpa_query_mr *entry;
@@ -242,6 +243,9 @@ mlx5_vdpa_create_indirect_mkey(struct mlx5_vdpa_priv *priv)
        mkey_attr.pg_access = 0;
        mkey_attr.klm_array = klm_array;
        mkey_attr.klm_num = klm_index;
+       /* If only relaxed order is allowed. */
+       if (hca_attr->mkc_order_write_after_write_ro_only)
+               mlx5_devx_mkey_attr_set_ordering(&mkey_attr, hca_attr);
        entry = &mrs[mem->nregions];
        entry->mkey = mlx5_devx_cmd_mkey_create(priv->cdev->ctx, &mkey_attr);
        if (!entry->mkey) {
-- 
2.21.0

Reply via email to