[PATCH v4 6/7] net/mlx5: add private API to config host port shaper

[Spike Du <spiked@nvidia.com>]

Host port shaper can be configured with QSHR(QoS Shaper Host Register).
Add check in build files to enable this function or not.

The host shaper configuration affects all the ethdev ports belonging to the
same host port.

Host shaper can configure shaper rate and lwm-triggered for a host port.
The shaper limits the rate of traffic from host port to wire port.
If lwm-triggered is enabled, a 100Mbps shaper is enabled automatically
when one of the host port's Rx queues receives fill threshold event.

Signed-off-by: Spike Du <spiked@nvidia.com>
---
 doc/guides/nics/mlx5.rst               |  35 +++++++++++
 doc/guides/rel_notes/release_22_07.rst |   1 +
 drivers/common/mlx5/linux/meson.build  |  13 +++++
 drivers/common/mlx5/mlx5_prm.h         |  25 ++++++++
 drivers/net/mlx5/mlx5.h                |   2 +
 drivers/net/mlx5/mlx5_rx.c             | 103 +++++++++++++++++++++++++++++++++
 drivers/net/mlx5/rte_pmd_mlx5.h        |  30 ++++++++++
 drivers/net/mlx5/version.map           |   2 +
 8 files changed, 211 insertions(+)

diff --git a/doc/guides/nics/mlx5.rst b/doc/guides/nics/mlx5.rst
index ea393fb..39bfebb 100644
--- a/doc/guides/nics/mlx5.rst
+++ b/doc/guides/nics/mlx5.rst
@@ -94,6 +94,7 @@ Features
 - Sub-Function representors.
 - Sub-Function.
 - Rx queue fill threshold configuration.
+- Host shaper support.
 
 
 Limitations
@@ -525,6 +526,12 @@ Limitations
 
   - Doesn't support shared Rx queue and Hairpin Rx queue.
 
+- Host shaper:
+
+  - Support BlueField series NIC from BlueField 2.
+  - When configure host shaper with MLX5_HOST_SHAPER_FLAG_FILL_THRESH_TRIGGERED flag set,
+    only rate 0 and 100Mbps are supported.
+
 Statistics
 ----------
 
@@ -1692,3 +1699,31 @@ Fill threshold is a per Rx queue attribute, it should be configured as
 a percentage of the Rx queue size.
 When Rx queue fullness is above the threshold, an event is sent to PMD.
 
+Host shaper introduction
+------------------------
+
+Host shaper register is per host port register which sets a shaper
+on the host port.
+All VF/hostPF representors belonging to one host port share one host shaper.
+For example, if representor 0 and representor 1 belong to same host port,
+and a host shaper rate of 1Gbps is configured, the shaper throttles both
+representors' traffic from host.
+Host shaper has two modes for setting the shaper, immediate and deferred to
+fill threshold event trigger. In immediate mode, the rate limit is configured
+immediately to host shaper. When deferring to fill threshold trigger, the shaper
+is not set until an fill threshold event is received by any Rx queue in a VF
+representor belonging to the host port. The only rate supported for deferred
+mode is 100Mbps (there is no limit on the supported rates for immediate mode).
+In deferred mode, the shaper is set on the host port by the firmware upon
+receiving the fill threshold event, which allows throttling host traffic on
+fill threshold events at minimum latency, preventing excess drops in the
+Rx queue.
+
+Host shaper dependency for mstflint package
+-------------------------------------------
+
+In order to configure host shaper register, ``librte_net_mlx5`` depends on ``libmtcr_ul``
+which can be installed from OFED mstflint package.
+Meson detects ``libmtcr_ul`` existence at configure stage.
+If the library is detected, the application must link with ``-lmtcr_ul``,
+as done by the pkg-config file libdpdk.pc.
diff --git a/doc/guides/rel_notes/release_22_07.rst b/doc/guides/rel_notes/release_22_07.rst
index 62a8874..eaf074c 100644
--- a/doc/guides/rel_notes/release_22_07.rst
+++ b/doc/guides/rel_notes/release_22_07.rst
@@ -90,6 +90,7 @@ New Features
   * Added support for MTU on Windows.
   * Added matching and RSS on IPsec ESP.
   * Added Rx queue fill threshold support.
+  * Added host shaper support.
 
 * **Updated Marvell cnxk crypto driver.**
 
diff --git a/drivers/common/mlx5/linux/meson.build b/drivers/common/mlx5/linux/meson.build
index 5335f5b..51c6e5d 100644
--- a/drivers/common/mlx5/linux/meson.build
+++ b/drivers/common/mlx5/linux/meson.build
@@ -45,6 +45,13 @@ if static_ibverbs
     ext_deps += declare_dependency(link_args:ibv_ldflags.split())
 endif
 
+libmtcr_ul_found = false
+lib = cc.find_library('mtcr_ul', required:false)
+if lib.found() and run_command('meson', '--version').stdout().version_compare('>= 0.49.2')
+    libmtcr_ul_found = true
+    ext_deps += lib
+endif
+
 sources += files('mlx5_nl.c')
 sources += files('mlx5_common_auxiliary.c')
 sources += files('mlx5_common_os.c')
@@ -207,6 +214,12 @@ has_sym_args = [
         [ 'HAVE_MLX5_IBV_IMPORT_CTX_PD_AND_MR', 'infiniband/verbs.h',
             'ibv_import_device' ],
 ]
+if  libmtcr_ul_found
+    has_sym_args += [
+        [  'HAVE_MLX5_MSTFLINT', 'mstflint/mtcr.h',
+            'mopen'],
+    ]
+endif
 config = configuration_data()
 foreach arg:has_sym_args
     config.set(arg[0], cc.has_header_symbol(arg[1], arg[2], dependencies: libs))
diff --git a/drivers/common/mlx5/mlx5_prm.h b/drivers/common/mlx5/mlx5_prm.h
index 3b5e605..92d05a7 100644
--- a/drivers/common/mlx5/mlx5_prm.h
+++ b/drivers/common/mlx5/mlx5_prm.h
@@ -3771,6 +3771,7 @@ enum {
 	MLX5_CRYPTO_COMMISSIONING_REGISTER_ID = 0xC003,
 	MLX5_IMPORT_KEK_HANDLE_REGISTER_ID = 0xC004,
 	MLX5_CREDENTIAL_HANDLE_REGISTER_ID = 0xC005,
+	MLX5_QSHR_REGISTER_ID = 0x4030,
 };
 
 struct mlx5_ifc_register_mtutc_bits {
@@ -3785,6 +3786,30 @@ struct mlx5_ifc_register_mtutc_bits {
 	u8 time_adjustment[0x20];
 };
 
+struct mlx5_ifc_ets_global_config_register_bits {
+	u8 reserved_at_0[0x2];
+	u8 rate_limit_update[0x1];
+	u8 reserved_at_3[0x29];
+	u8 max_bw_units[0x4];
+	u8 reserved_at_48[0x8];
+	u8 max_bw_value[0x8];
+};
+
+#define ETS_GLOBAL_CONFIG_BW_UNIT_DISABLED      0x0
+#define ETS_GLOBAL_CONFIG_BW_UNIT_HUNDREDS_MBPS 0x3
+#define ETS_GLOBAL_CONFIG_BW_UNIT_GBPS          0x4
+
+struct mlx5_ifc_register_qshr_bits {
+	u8 reserved_at_0[0x4];
+	u8 connected_host[0x1];
+	u8 vqos[0x1];
+	u8 fast_response[0x1];
+	u8 reserved_at_7[0x1];
+	u8 local_port[0x8];
+	u8 reserved_at_16[0x230];
+	struct mlx5_ifc_ets_global_config_register_bits global_config;
+};
+
 #define MLX5_MTUTC_TIMESTAMP_MODE_INTERNAL_TIMER 0
 #define MLX5_MTUTC_TIMESTAMP_MODE_REAL_TIME 1
 
diff --git a/drivers/net/mlx5/mlx5.h b/drivers/net/mlx5/mlx5.h
index a76f2fe..8af84ae 100644
--- a/drivers/net/mlx5/mlx5.h
+++ b/drivers/net/mlx5/mlx5.h
@@ -1271,6 +1271,8 @@ struct mlx5_dev_ctx_shared {
 	void *devx_channel_lwm;
 	struct rte_intr_handle *intr_handle_lwm;
 	pthread_mutex_t lwm_config_lock;
+	uint32_t host_shaper_rate:8;
+	uint32_t lwm_triggered:1;
 	/* Availability of mreg_c's. */
 	struct mlx5_dev_shared_port port[]; /* per device port data array. */
 };
diff --git a/drivers/net/mlx5/mlx5_rx.c b/drivers/net/mlx5/mlx5_rx.c
index 4099496..b908bf7 100644
--- a/drivers/net/mlx5/mlx5_rx.c
+++ b/drivers/net/mlx5/mlx5_rx.c
@@ -28,6 +28,9 @@
 #include "mlx5_rxtx.h"
 #include "mlx5_devx.h"
 #include "mlx5_rx.h"
+#ifdef HAVE_MLX5_MSTFLINT
+#include <mstflint/mtcr.h>
+#endif
 
 
 static __rte_always_inline uint32_t
@@ -1376,3 +1379,103 @@ int mlx5_get_monitor_addr(void *rx_queue, struct rte_power_monitor_cond *pmc)
 	return ret;
 }
 
+/**
+ * Mlx5 access register function to configure host shaper.
+ * It calls API in libmtcr_ul to access QSHR(Qos Shaper Host Register)
+ * in firmware.
+ *
+ * @param dev
+ *   Pointer to rte_eth_dev.
+ * @param lwm_triggered
+ *   Flag to enable/disable lwm_triggered bit in QSHR.
+ * @param rate
+ *   Host shaper rate, unit is 100Mbps, set to 0 means disable the shaper.
+ * @return
+ *   0 : operation success.
+ *   Otherwise:
+ *   - ENOENT - no ibdev interface.
+ *   - EBUSY  - the register access unit is busy.
+ *   - EIO    - the register access command meets IO error.
+ */
+static int
+mlxreg_host_shaper_config(struct rte_eth_dev *dev,
+			  bool lwm_triggered, uint8_t rate)
+{
+#ifdef HAVE_MLX5_MSTFLINT
+	struct mlx5_priv *priv = dev->data->dev_private;
+	uint32_t data[MLX5_ST_SZ_DW(register_qshr)] = {0};
+	int rc, retry_count = 3;
+	mfile *mf = NULL;
+	int status;
+	void *ptr;
+
+	mf = mopen(priv->sh->ibdev_name);
+	if (!mf) {
+		DRV_LOG(WARNING, "mopen failed\n");
+		rte_errno = ENOENT;
+		return -rte_errno;
+	}
+	MLX5_SET(register_qshr, data, connected_host, 1);
+	MLX5_SET(register_qshr, data, fast_response, lwm_triggered ? 1 : 0);
+	MLX5_SET(register_qshr, data, local_port, 1);
+	ptr = MLX5_ADDR_OF(register_qshr, data, global_config);
+	MLX5_SET(ets_global_config_register, ptr, rate_limit_update, 1);
+	MLX5_SET(ets_global_config_register, ptr, max_bw_units,
+		 rate ? ETS_GLOBAL_CONFIG_BW_UNIT_HUNDREDS_MBPS :
+		 ETS_GLOBAL_CONFIG_BW_UNIT_DISABLED);
+	MLX5_SET(ets_global_config_register, ptr, max_bw_value, rate);
+	do {
+		rc = maccess_reg(mf,
+				 MLX5_QSHR_REGISTER_ID,
+				 MACCESS_REG_METHOD_SET,
+				 (u_int32_t *)&data[0],
+				 sizeof(data),
+				 sizeof(data),
+				 sizeof(data),
+				 &status);
+		if ((rc != ME_ICMD_STATUS_IFC_BUSY &&
+		     status != ME_REG_ACCESS_BAD_PARAM) ||
+		    !(mf->flags & MDEVS_REM)) {
+			break;
+		}
+		DRV_LOG(WARNING, "%s retry.", __func__);
+		usleep(10000);
+	} while (retry_count-- > 0);
+	mclose(mf);
+	rte_errno = (rc == ME_REG_ACCESS_DEV_BUSY) ? EBUSY : EIO;
+	return rc ? -rte_errno : 0;
+#else
+	(void)dev;
+	(void)lwm_triggered;
+	(void)rate;
+	return -1;
+#endif
+}
+
+int rte_pmd_mlx5_host_shaper_config(int port_id, uint8_t rate,
+				    uint32_t flags)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+	struct mlx5_priv *priv = dev->data->dev_private;
+	bool lwm_triggered =
+	     !!(flags & RTE_BIT32(MLX5_HOST_SHAPER_FLAG_FILL_THRESH_TRIGGERED));
+
+	if (!lwm_triggered) {
+		priv->sh->host_shaper_rate = rate;
+	} else {
+		switch (rate) {
+		case 0:
+		/* Rate 0 means disable lwm_triggered. */
+			priv->sh->lwm_triggered = 0;
+			break;
+		case 1:
+		/* Rate 1 means enable lwm_triggered. */
+			priv->sh->lwm_triggered = 1;
+			break;
+		default:
+			return -ENOTSUP;
+		}
+	}
+	return mlxreg_host_shaper_config(dev, priv->sh->lwm_triggered,
+					 priv->sh->host_shaper_rate);
+}
diff --git a/drivers/net/mlx5/rte_pmd_mlx5.h b/drivers/net/mlx5/rte_pmd_mlx5.h
index 6e7907e..d7cd149 100644
--- a/drivers/net/mlx5/rte_pmd_mlx5.h
+++ b/drivers/net/mlx5/rte_pmd_mlx5.h
@@ -109,6 +109,36 @@ int rte_pmd_mlx5_external_rx_queue_id_map(uint16_t port_id, uint16_t dpdk_idx,
 int rte_pmd_mlx5_external_rx_queue_id_unmap(uint16_t port_id,
 					    uint16_t dpdk_idx);
 
+/**
+ * The rate of the host port shaper will be updated directly at the next
+ * fill threshold event to the rate that comes with this flag set; set rate 0
+ * to disable this rate update.
+ * Unset this flag to update the rate of the host port shaper directly in
+ * the API call; use rate 0 to disable the current shaper.
+ */
+#define MLX5_HOST_SHAPER_FLAG_FILL_THRESH_TRIGGERED 0
+
+/**
+ * Configure a HW shaper to limit Tx rate for a host port.
+ * The configuration will affect all the ethdev ports belonging to
+ * the same rte_device.
+ *
+ * @param[in] port_id
+ *   The port identifier of the Ethernet device.
+ * @param[in] rate
+ *   Unit is 100Mbps, setting the rate to 0 disables the shaper.
+ * @param[in] flags
+ *   Host shaper flags.
+ * @return
+ *   0 : operation success.
+ *   Otherwise:
+ *   - ENOENT - no ibdev interface.
+ *   - EBUSY  - the register access unit is busy.
+ *   - EIO    - the register access command meets IO error.
+ */
+__rte_experimental
+int rte_pmd_mlx5_host_shaper_config(int port_id, uint8_t rate, uint32_t flags);
+
 #ifdef __cplusplus
 }
 #endif
diff --git a/drivers/net/mlx5/version.map b/drivers/net/mlx5/version.map
index 79cb79a..c97dfe4 100644
--- a/drivers/net/mlx5/version.map
+++ b/drivers/net/mlx5/version.map
@@ -12,4 +12,6 @@ EXPERIMENTAL {
 	# added in 22.03
 	rte_pmd_mlx5_external_rx_queue_id_map;
 	rte_pmd_mlx5_external_rx_queue_id_unmap;
+	# added in 22.07
+	rte_pmd_mlx5_host_shaper_config;
 };
-- 
1.8.3.1