All of lore.kernel.org
 help / color / mirror / Atom feed
From: Billy McFall <bmcfall@redhat.com>
To: thomas.monjalon@6wind.com, wenzhuo.lu@intel.com, olivier.matz@6wind.com
Cc: dev@dpdk.org, Billy McFall <bmcfall@redhat.com>
Subject: [PATCH v7 1/3] ethdev: new API to free consumed buffers in Tx ring
Date: Wed, 15 Mar 2017 14:02:24 -0400	[thread overview]
Message-ID: <20170315180226.5999-2-bmcfall@redhat.com> (raw)
In-Reply-To: <20170315180226.5999-1-bmcfall@redhat.com>

Add a new API to force free consumed buffers on Tx ring. API will return
the number of packets freed (0-n) or error code if feature not supported
(-ENOTSUP) or input invalid (-ENODEV).

Signed-off-by: Billy McFall <bmcfall@redhat.com>
---
 doc/guides/conf.py                      |  7 +++++--
 doc/guides/nics/features/default.ini    |  4 +++-
 doc/guides/prog_guide/poll_mode_drv.rst | 28 ++++++++++++++++++++++++++++
 doc/guides/rel_notes/release_17_05.rst  |  7 ++++++-
 lib/librte_ether/rte_ethdev.c           | 14 ++++++++++++++
 lib/librte_ether/rte_ethdev.h           | 31 +++++++++++++++++++++++++++++++
 6 files changed, 87 insertions(+), 4 deletions(-)

diff --git a/doc/guides/conf.py b/doc/guides/conf.py
index 34c62de..4cac26d 100644
--- a/doc/guides/conf.py
+++ b/doc/guides/conf.py
@@ -64,6 +64,9 @@
 
 master_doc = 'index'
 
+# Maximum feature description string length
+feature_str_len = 25
+
 # Figures, tables and code-blocks automatically numbered if they have caption
 numfig = True
 
@@ -300,7 +303,7 @@ def print_table_body(outfile, num_cols, ini_files, ini_data, default_features):
 def print_table_row(outfile, feature, line):
     """ Print a single row of the table with fixed formatting. """
     line = line.rstrip()
-    print('   {:<20}{}'.format(feature, line), file=outfile)
+    print('   {:<{}}{}'.format(feature, feature_str_len, line), file=outfile)
 
 
 def print_table_divider(outfile, num_cols):
@@ -309,7 +312,7 @@ def print_table_divider(outfile, num_cols):
     column_dividers = ['='] * num_cols
     line += ' '.join(column_dividers)
 
-    feature = '=' * 20
+    feature = '=' * feature_str_len
 
     print_table_row(outfile, feature, line)
 
diff --git a/doc/guides/nics/features/default.ini b/doc/guides/nics/features/default.ini
index 299078f..0135c0c 100644
--- a/doc/guides/nics/features/default.ini
+++ b/doc/guides/nics/features/default.ini
@@ -3,7 +3,8 @@
 ;
 ; This file defines the features that are valid for inclusion in
 ; the other driver files and also the order that they appear in
-; the features table in the documentation.
+; the features table in the documentation. The feature description
+; string should not exceed feature_str_len defined in conf.py.
 ;
 [Features]
 Speed capabilities   =
@@ -11,6 +12,7 @@ Link status          =
 Link status event    =
 Queue status event   =
 Rx interrupt         =
+Free Tx mbuf on demand =
 Queue start/stop     =
 MTU update           =
 Jumbo frame          =
diff --git a/doc/guides/prog_guide/poll_mode_drv.rst b/doc/guides/prog_guide/poll_mode_drv.rst
index d4c92ea..21f7a9d 100644
--- a/doc/guides/prog_guide/poll_mode_drv.rst
+++ b/doc/guides/prog_guide/poll_mode_drv.rst
@@ -249,6 +249,34 @@ One descriptor in the TX ring is used as a sentinel to avoid a hardware race con
 
     When configuring for DCB operation, at port initialization, both the number of transmit queues and the number of receive queues must be set to 128.
 
+Free Tx mbuf on Demand
+~~~~~~~~~~~~~~~~~~~~~~
+
+Many of the drivers don't release the mbuf back to the mempool, or local cache, immediately after the packet has been
+transmitted.
+Instead, they leave the mbuf in their Tx ring and either perform a bulk release when the ``tx_rs_thresh`` has been
+crossed or free the mbuf when a slot in the Tx ring is needed.
+
+An application can request the driver to release used mbufs with the ``rte_eth_tx_done_cleanup()`` API.
+This API requests the driver to release mbufs that are no longer in use, independent of whether or not the
+``tx_rs_thresh`` has been crossed.
+There are two scenarios when an application may want the mbuf released immediately:
+
+* When a given packet needs to be sent to multiple destination interfaces (either for Layer 2 flooding or Layer 3
+  multi-cast).
+  One option is to make a copy of the packet or a copy of the header portion that needs to be manipulated.
+  A second option is to transmit the packet and then poll the ``rte_eth_tx_done_cleanup()`` API until the reference
+  count on the packet is decremented.
+  Then the same packet can be transmitted to the next destination interface.
+
+* If an application is designed to make multiple runs, like a packet generator, and one run has completed.
+  The application may want to reset to a clean state.
+  In this case, it may want to call the ``rte_eth_tx_done_cleanup()`` API to request each destination interface it has
+  been using to release all of its used mbufs.
+
+To determine if a driver supports this API, check for the *Free Tx mbuf on demand* feature in the *Network Interface
+Controller Drivers* document.
+
 Hardware Offload
 ~~~~~~~~~~~~~~~~
 
diff --git a/doc/guides/rel_notes/release_17_05.rst b/doc/guides/rel_notes/release_17_05.rst
index 4b90036..7b9c92c 100644
--- a/doc/guides/rel_notes/release_17_05.rst
+++ b/doc/guides/rel_notes/release_17_05.rst
@@ -41,11 +41,16 @@ New Features
      Also, make sure to start the actual text at the margin.
      =========================================================
 
-
 * **Added powerpc support in pci probing for vfio-pci devices.**
 
   sPAPR IOMMU based pci probing enabled for vfio-pci devices.
 
+* **Added free Tx mbuf on demand API.**
+
+  Added a new function ``rte_eth_tx_done_cleanup()`` which allows an application
+  to request the driver to release mbufs from their Tx ring that are no longer
+  in use, independent of whether or not the ``tx_rs_thresh`` has been crossed.
+
 Resolved Issues
 ---------------
 
diff --git a/lib/librte_ether/rte_ethdev.c b/lib/librte_ether/rte_ethdev.c
index eb0a94a..b796e7d 100644
--- a/lib/librte_ether/rte_ethdev.c
+++ b/lib/librte_ether/rte_ethdev.c
@@ -1275,6 +1275,20 @@ rte_eth_tx_buffer_init(struct rte_eth_dev_tx_buffer *buffer, uint16_t size)
 	return ret;
 }
 
+int
+rte_eth_tx_done_cleanup(uint8_t port_id, uint16_t queue_id, uint32_t free_cnt)
+{
+	struct rte_eth_dev *dev = &rte_eth_devices[port_id];
+
+	/* Validate Input Data. Bail if not valid or not supported. */
+	RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
+	RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->tx_done_cleanup, -ENOTSUP);
+
+	/* Call driver to free pending mbufs. */
+	return (*dev->dev_ops->tx_done_cleanup)(dev->data->tx_queues[queue_id],
+			free_cnt);
+}
+
 void
 rte_eth_promiscuous_enable(uint8_t port_id)
 {
diff --git a/lib/librte_ether/rte_ethdev.h b/lib/librte_ether/rte_ethdev.h
index 4be217c..b3ee872 100644
--- a/lib/librte_ether/rte_ethdev.h
+++ b/lib/librte_ether/rte_ethdev.h
@@ -1183,6 +1183,9 @@ typedef int (*eth_fw_version_get_t)(struct rte_eth_dev *dev,
 				     char *fw_version, size_t fw_size);
 /**< @internal Get firmware information of an Ethernet device. */
 
+typedef int (*eth_tx_done_cleanup_t)(void *txq, uint32_t free_cnt);
+/**< @internal Force mbufs to be from TX ring. */
+
 typedef void (*eth_rxq_info_get_t)(struct rte_eth_dev *dev,
 	uint16_t rx_queue_id, struct rte_eth_rxq_info *qinfo);
 
@@ -1488,6 +1491,7 @@ struct eth_dev_ops {
 	eth_rx_disable_intr_t      rx_queue_intr_disable; /**< Disable Rx queue interrupt. */
 	eth_tx_queue_setup_t       tx_queue_setup;/**< Set up device TX queue. */
 	eth_queue_release_t        tx_queue_release; /**< Release TX queue. */
+	eth_tx_done_cleanup_t      tx_done_cleanup;/**< Free tx ring mbufs */
 
 	eth_dev_led_on_t           dev_led_on;    /**< Turn on LED. */
 	eth_dev_led_off_t          dev_led_off;   /**< Turn off LED. */
@@ -3178,6 +3182,33 @@ rte_eth_tx_buffer_count_callback(struct rte_mbuf **pkts, uint16_t unsent,
 		void *userdata);
 
 /**
+ * Request the driver to free mbufs currently cached by the driver. The
+ * driver will only free the mbuf if it is no longer in use. It is the
+ * application's responsibity to ensure rte_eth_tx_buffer_flush(..) is
+ * called if needed.
+ *
+ * @param port_id
+ *   The port identifier of the Ethernet device.
+ * @param queue_id
+ *   The index of the transmit queue through which output packets must be
+ *   sent.
+ *   The value must be in the range [0, nb_tx_queue - 1] previously supplied
+ *   to rte_eth_dev_configure().
+ * @param free_cnt
+ *   Maximum number of packets to free. Use 0 to indicate all possible packets
+ *   should be freed. Note that a packet may be using multiple mbufs.
+ * @return
+ *   Failure: < 0
+ *     -ENODEV: Invalid interface
+ *     -ENOTSUP: Driver does not support function
+ *   Success: >= 0
+ *     0-n: Number of packets freed. More packets may still remain in ring that
+ *     are in use.
+ */
+int
+rte_eth_tx_done_cleanup(uint8_t port_id, uint16_t queue_id, uint32_t free_cnt);
+
+/**
  * The eth device event type for interrupt, and maybe others in the future.
  */
 enum rte_eth_event_type {
-- 
2.9.3

  reply	other threads:[~2017-03-15 18:02 UTC|newest]

Thread overview: 54+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-01-20 16:01 [PATCH v3 0/3] new API to free consumed buffers in Tx ring Billy McFall
2017-01-20 16:01 ` [PATCH v3 1/3] ethdev: " Billy McFall
2017-01-20 16:01 ` [PATCH v3 2/3] net/e1000: e1000 igb support to free consumed buffers Billy McFall
2017-01-22  3:47   ` Lu, Wenzhuo
2017-01-23 13:49     ` Billy McFall
2017-01-24  0:42       ` Lu, Wenzhuo
2017-01-20 16:01 ` [PATCH v3 3/3] net/vhost: vHost " Billy McFall
2017-01-23 15:25 ` [PATCH v3 0/3] new API to free consumed buffers in Tx ring Thomas Monjalon
2017-01-23 21:13 ` [PATCH v4 " Billy McFall
2017-01-23 21:13   ` [PATCH v4 1/3] ethdev: " Billy McFall
2017-01-23 21:13   ` [PATCH v4 2/3] net/e1000: e1000 igb support to free consumed buffers Billy McFall
2017-01-23 21:13   ` [PATCH v4 3/3] net/vhost: vHost " Billy McFall
2017-01-27 18:37   ` [PATCH v5 0/3] new API to free consumed buffers in Tx ring Billy McFall
2017-01-27 18:37     ` [PATCH v5 1/3] ethdev: " Billy McFall
2017-02-27 13:48       ` Thomas Monjalon
2017-03-07 14:29         ` Billy McFall
2017-03-07 16:03           ` Thomas Monjalon
2017-03-09 15:49             ` Billy McFall
2017-03-09 17:11               ` Thomas Monjalon
2017-03-07 16:35           ` Mcnamara, John
2017-03-07 16:42       ` Mcnamara, John
2017-01-27 18:37     ` [PATCH v5 2/3] net/e1000: e1000 igb support to free consumed buffers Billy McFall
2017-02-27 13:49       ` Thomas Monjalon
2017-02-28  1:07       ` Lu, Wenzhuo
2017-01-27 18:38     ` [PATCH v5 3/3] net/vhost: vHost " Billy McFall
2017-02-27 13:50       ` Thomas Monjalon
2017-02-28  6:41         ` Yuanhan Liu
2017-03-01 10:15           ` Maxime Coquelin
2017-03-07 21:59     ` [PATCH v5 0/3] new API to free consumed buffers in Tx ring Thomas Monjalon
2017-03-09 20:51     ` [PATCH v6 " Billy McFall
2017-03-09 20:51       ` [PATCH v6 1/3] ethdev: " Billy McFall
2017-03-15 10:29         ` Olivier Matz
2017-03-15 15:01           ` Billy McFall
2017-03-15 10:30         ` Thomas Monjalon
2017-03-09 20:51       ` [PATCH v6 2/3] net/e1000: e1000 igb support to free consumed buffers Billy McFall
2017-03-13  3:17         ` Lu, Wenzhuo
2017-03-09 20:51       ` [PATCH v6 3/3] net/vhost: vHost " Billy McFall
2017-03-15 10:27         ` Thomas Monjalon
2017-03-15 18:02       ` [PATCH v7 0/3] new API to free consumed buffers in Tx ring Billy McFall
2017-03-15 18:02         ` Billy McFall [this message]
2017-03-23 10:37           ` [PATCH v7 1/3] ethdev: " Olivier MATZ
2017-03-23 13:32             ` Billy McFall
2017-03-24 12:46               ` Olivier Matz
2017-03-24 13:18                 ` Billy McFall
2017-03-24 13:30                   ` Olivier Matz
2017-03-15 18:02         ` [PATCH v7 2/3] net/e1000: e1000 igb support to free consumed buffers Billy McFall
2017-03-15 18:02         ` [PATCH v7 3/3] net/vhost: vHost " Billy McFall
2017-03-15 20:25         ` [PATCH v7 0/3] new API to free consumed buffers in Tx ring Wiles, Keith
2017-03-24 18:55         ` [PATCH v8 " Billy McFall
2017-03-24 18:55           ` [PATCH v8 1/3] ethdev: " Billy McFall
2017-03-24 18:55           ` [PATCH v8 2/3] net/e1000: e1000 igb support to free consumed buffers Billy McFall
2017-03-24 18:55           ` [PATCH v8 3/3] net/vhost: vHost " Billy McFall
2017-03-27 15:20           ` [PATCH v8 0/3] new API to free consumed buffers in Tx ring Thomas Monjalon
2017-04-19 16:25           ` Ferruh Yigit

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20170315180226.5999-2-bmcfall@redhat.com \
    --to=bmcfall@redhat.com \
    --cc=dev@dpdk.org \
    --cc=olivier.matz@6wind.com \
    --cc=thomas.monjalon@6wind.com \
    --cc=wenzhuo.lu@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.