Presently, the 'Buffer Split' feature supports sending multiple
segments of the received packet to PMD, which programs the HW
to receive the packet in segments from different pools.
This patch extends the feature to support the pool sort capability.
Some of the HW has support for choosing memory pools based on the
packet's size. The pool sort capability allows PMD to choose a
memory pool based on the packet's length.
This is often useful for saving the memory where the application
can create a different pool to steer the specific size of the
packet, thus enabling effective use of memory.
For example, let's say HW has a capability of three pools,
- pool-1 size is 2K
- pool-2 size is > 2K and < 4K
- pool-3 size is > 4K
Here,
pool-1 can accommodate packets with sizes < 2K
pool-2 can accommodate packets with sizes > 2K and < 4K
pool-3 can accommodate packets with sizes > 4K
With pool sort capability enabled in SW, an application may create
three pools of different sizes and send them to PMD. Allowing PMD
to program HW based on packet lengths. So that packets with less
than 2K are received on pool-1, packets with lengths between 2K
and 4K are received on pool-2 and finally packets greater than 4K
are received on pool-3.
The following two capabilities are added to the rte_eth_rxseg_capa
structure,
1. pool_sort --> tells pool sort capability is supported by HW.
2. max_npool --> max number of pools supported by HW.
Defined new structure rte_eth_rxseg_sort, to be used only when pool
sort capability is present. If required this may be extended further
to support more configurations.
Signed-off-by: Hanumanth Pothula <hpoth...@marvell.com>
v2:
- Along with spec changes, uploading testpmd and driver changes.
---
lib/ethdev/rte_ethdev.c | 87 +++++++++++++++++++++++++++++++++++------
lib/ethdev/rte_ethdev.h | 45 +++++++++++++++++++--
2 files changed, 118 insertions(+), 14 deletions(-)
diff --git a/lib/ethdev/rte_ethdev.c b/lib/ethdev/rte_ethdev.c
index 1979dc0850..7fd5443eb8 100644
--- a/lib/ethdev/rte_ethdev.c
+++ b/lib/ethdev/rte_ethdev.c
@@ -1635,7 +1635,55 @@ rte_eth_dev_is_removed(uint16_t port_id)
}
static int
-rte_eth_rx_queue_check_split(const struct rte_eth_rxseg_split *rx_seg,
+rte_eth_rx_queue_check_sort(const struct rte_eth_rxseg *rx_seg,
+ uint16_t n_seg, uint32_t *mbp_buf_size,
+ const struct rte_eth_dev_info *dev_info)
+{
+ const struct rte_eth_rxseg_capa *seg_capa = &dev_info->rx_seg_capa;
+ uint16_t seg_idx;
+
+ if (!seg_capa->multi_pools || n_seg > seg_capa->max_npool) {
+ RTE_ETHDEV_LOG(ERR,
+ "Invalid capabilities, multi_pools:%d differnt
length segments %u exceed supported %u\n",
+ seg_capa->multi_pools, n_seg,
seg_capa->max_nseg);
+ return -EINVAL;
+ }
+
+ for (seg_idx = 0; seg_idx < n_seg; seg_idx++) {
+ struct rte_mempool *mpl = rx_seg[seg_idx].sort.mp;
+ uint32_t length = rx_seg[seg_idx].sort.length;
+
+ if (mpl == NULL) {
+ RTE_ETHDEV_LOG(ERR, "null mempool pointer\n");
+ return -EINVAL;
+ }
+
+ if (mpl->private_data_size <
+ sizeof(struct rte_pktmbuf_pool_private)) {
+ RTE_ETHDEV_LOG(ERR,
+ "%s private_data_size %u < %u\n",
+ mpl->name, mpl->private_data_size,
+ (unsigned int)sizeof
+ (struct rte_pktmbuf_pool_private));
+ return -ENOSPC;
+ }
+
+ *mbp_buf_size = rte_pktmbuf_data_room_size(mpl);
+ length = length != 0 ? length : (*mbp_buf_size -
RTE_PKTMBUF_HEADROOM);
+ if (*mbp_buf_size < length + RTE_PKTMBUF_HEADROOM) {
+ RTE_ETHDEV_LOG(ERR,
+ "%s mbuf_data_room_size %u < %u))\n",
+ mpl->name, *mbp_buf_size,
+ length);
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
+static int
+rte_eth_rx_queue_check_split(const struct rte_eth_rxseg *rx_seg,
uint16_t n_seg, uint32_t *mbp_buf_size,
const struct rte_eth_dev_info *dev_info)
{
@@ -1654,12 +1702,12 @@ rte_eth_rx_queue_check_split(const struct
rte_eth_rxseg_split *rx_seg,
* Check the sizes and offsets against buffer sizes
* for each segment specified in extended configuration.
*/
- mp_first = rx_seg[0].mp;
+ mp_first = rx_seg[0].split.mp;
offset_mask = RTE_BIT32(seg_capa->offset_align_log2) - 1;
for (seg_idx = 0; seg_idx < n_seg; seg_idx++) {
- struct rte_mempool *mpl = rx_seg[seg_idx].mp;
- uint32_t length = rx_seg[seg_idx].length;
- uint32_t offset = rx_seg[seg_idx].offset;
+ struct rte_mempool *mpl = rx_seg[seg_idx].split.mp;
+ uint32_t length = rx_seg[seg_idx].split.length;
+ uint32_t offset = rx_seg[seg_idx].split.offset;
if (mpl == NULL) {
RTE_ETHDEV_LOG(ERR, "null mempool pointer\n");
@@ -1693,7 +1741,11 @@ rte_eth_rx_queue_check_split(const struct
rte_eth_rxseg_split *rx_seg,
}
offset += seg_idx != 0 ? 0 : RTE_PKTMBUF_HEADROOM;
*mbp_buf_size = rte_pktmbuf_data_room_size(mpl);
- length = length != 0 ? length : *mbp_buf_size;
+ /* On segment length == 0, update segment's length with
+ * the pool's length - headeroom space, to make sure enough
+ * space is accomidate for header.
+ **/
+ length = length != 0 ? length : (*mbp_buf_size -
RTE_PKTMBUF_HEADROOM);
if (*mbp_buf_size < length + offset) {
RTE_ETHDEV_LOG(ERR,
"%s mbuf_data_room_size %u < %u (segment
length=%u + segment offset=%u)\n",
@@ -1764,7 +1816,6 @@ rte_eth_rx_queue_setup(uint16_t port_id, uint16_t
rx_queue_id,
return -EINVAL;
}
} else {
- const struct rte_eth_rxseg_split *rx_seg;
uint16_t n_seg;
/* Extended multi-segment configuration check. */
@@ -1774,13 +1825,27 @@ rte_eth_rx_queue_setup(uint16_t port_id, uint16_t
rx_queue_id,
return -EINVAL;
}
- rx_seg = (const struct rte_eth_rxseg_split *)rx_conf->rx_seg;
n_seg = rx_conf->rx_nseg;
if (rx_conf->offloads & RTE_ETH_RX_OFFLOAD_BUFFER_SPLIT) {
- ret = rte_eth_rx_queue_check_split(rx_seg, n_seg,
- &mbp_buf_size,
- &dev_info);
+ ret = -1; /* To make sure at least one of below
conditions becomes true */
+
+ /* Check both NIX and application supports buffer-split
capability */
+ if (dev_info.rx_seg_capa.mode_split &&
+ rx_conf->mode_flag == RTE_ETH_RXSEG_MODE_SPLIT) {
+ ret =
rte_eth_rx_queue_check_split(rx_conf->rx_seg, n_seg,
+
&mbp_buf_size,
+ &dev_info);
+ }
+
+ /* Check both NIX and application supports pool-sort
capability */
+ if (dev_info.rx_seg_capa.mode_sort &&
+ rx_conf->mode_flag == RTE_ETH_RXSEG_MODE_SORT) {
+ ret =
rte_eth_rx_queue_check_sort(rx_conf->rx_seg, n_seg,
+ &mbp_buf_size,
+ &dev_info);
+ }
+
if (ret != 0)
return ret;
} else {
diff --git a/lib/ethdev/rte_ethdev.h b/lib/ethdev/rte_ethdev.h
index de9e970d4d..9f6787d7ad 100644
--- a/lib/ethdev/rte_ethdev.h
+++ b/lib/ethdev/rte_ethdev.h
@@ -1204,16 +1204,46 @@ struct rte_eth_rxseg_split {
uint32_t reserved; /**< Reserved field. */
};
+/**
+ * The pool sort capability allows PMD to choose a memory pool based on the
+ * packet's length. So, basically, PMD programs HW for receiving packets from
+ * different pools, based on the packet's length.
+ *
+ * This is often useful for saving the memory where the application can create
+ * a different pool to steer the specific size of the packet, thus enabling
+ * effective use of memory.
+ */
+struct rte_eth_rxseg_sort {
+ struct rte_mempool *mp; /**< Memory pool to allocate packets from. */
+ uint16_t length; /**< Packet data length. */
+ uint32_t reserved; /**< Reserved field. */
+};
+
+enum rte_eth_rxseg_mode {
+ /**
+ * Buffer split mode: PMD split the received packets into multiple
segments.
+ * @see struct rte_eth_rxseg_split
+ */
+ RTE_ETH_RXSEG_MODE_SPLIT = RTE_BIT64(0),
+ /**
+ * Pool sort mode: PMD to chooses a memory pool based on the packet's
length.
+ * @see struct rte_eth_rxseg_sort
+ */
+ RTE_ETH_RXSEG_MODE_SORT = RTE_BIT64(1),
+};
+
/**
* @warning
* @b EXPERIMENTAL: this structure may change without prior notice.
*
* A common structure used to describe Rx packet segment properties.
*/
-union rte_eth_rxseg {
+struct rte_eth_rxseg {
/* The settings for buffer split offload. */
struct rte_eth_rxseg_split split;
- /* The other features settings should be added here. */
+
+ /*The settings for packet sort offload. */
+ struct rte_eth_rxseg_sort sort;
};
/**
@@ -1239,6 +1269,11 @@ struct rte_eth_rxconf {
* fields on rte_eth_dev_info structure are allowed to be set.
*/
uint64_t offloads;
+ /**
+ * PMD may support more than one rxseg mode. This allows application
+ * to chose which mode to enable.
+ */
+ enum rte_eth_rxseg_mode mode_flag;
/**
* Points to the array of segment descriptions for an entire packet.
* Array elements are properties for consecutive Rx segments.
@@ -1246,7 +1281,7 @@ struct rte_eth_rxconf {
* The supported capabilities of receiving segmentation is reported
* in rte_eth_dev_info.rx_seg_capa field.
*/
- union rte_eth_rxseg *rx_seg;
+ struct rte_eth_rxseg *rx_seg;
uint64_t reserved_64s[2]; /**< Reserved for future fields */
void *reserved_ptrs[2]; /**< Reserved for future fields */
@@ -1827,10 +1862,14 @@ struct rte_eth_switch_info {
*/
struct rte_eth_rxseg_capa {
__extension__
+ uint32_t mode_split : 1; /**< Supports buffer split capability @see
struct rte_eth_rxseg_split */
+ uint32_t mode_sort : 1; /**< Supports pool sort capability @see struct
rte_eth_rxseg_sort */
uint32_t multi_pools:1; /**< Supports receiving to multiple pools.*/
uint32_t offset_allowed:1; /**< Supports buffer offsets. */
uint32_t offset_align_log2:4; /**< Required offset alignment. */
uint16_t max_nseg; /**< Maximum amount of segments to split. */
+ /* < Maximum amount of pools that PMD can sort based on packet/segment
lengths */
+ uint16_t max_npool;
uint16_t reserved; /**< Reserved field. */
};
--
2.25.1
