Commit 3410d0e1 authored by Shradha Gupta's avatar Shradha Gupta Committed by Jakub Kicinski

net: mana: Implement get_ringparam/set_ringparam for mana

Currently the values of WQs for RX and TX queues for MANA devices
are hardcoded to default sizes.
Allow configuring these values for MANA devices as ringparam
configuration(get/set) through ethtool_ops.
Pre-allocate buffers at the beginning of this operation, to
prevent complete network loss in low-memory conditions.
Signed-off-by: default avatarShradha Gupta <shradhagupta@linux.microsoft.com>
Reviewed-by: default avatarHaiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: default avatarSaurabh Sengar <ssengar@linux.microsoft.com>
Link: https://patch.msgid.link/1724688461-12203-1-git-send-email-shradhagupta@linux.microsoft.comSigned-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent cf740e3c
......@@ -511,7 +511,7 @@ static u16 mana_select_queue(struct net_device *ndev, struct sk_buff *skb,
}
/* Release pre-allocated RX buffers */
static void mana_pre_dealloc_rxbufs(struct mana_port_context *mpc)
void mana_pre_dealloc_rxbufs(struct mana_port_context *mpc)
{
struct device *dev;
int i;
......@@ -608,7 +608,7 @@ static void mana_get_rxbuf_cfg(int mtu, u32 *datasize, u32 *alloc_size,
*datasize = mtu + ETH_HLEN;
}
static int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu)
int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu)
{
struct device *dev;
struct page *page;
......@@ -622,7 +622,7 @@ static int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu)
dev = mpc->ac->gdma_dev->gdma_context->dev;
num_rxb = mpc->num_queues * RX_BUFFERS_PER_QUEUE;
num_rxb = mpc->num_queues * mpc->rx_queue_size;
WARN(mpc->rxbufs_pre, "mana rxbufs_pre exists\n");
mpc->rxbufs_pre = kmalloc_array(num_rxb, sizeof(void *), GFP_KERNEL);
......@@ -1909,15 +1909,17 @@ static int mana_create_txq(struct mana_port_context *apc,
return -ENOMEM;
/* The minimum size of the WQE is 32 bytes, hence
* MAX_SEND_BUFFERS_PER_QUEUE represents the maximum number of WQEs
* apc->tx_queue_size represents the maximum number of WQEs
* the SQ can store. This value is then used to size other queues
* to prevent overflow.
* Also note that the txq_size is always going to be MANA_PAGE_ALIGNED,
* as min val of apc->tx_queue_size is 128 and that would make
* txq_size 128*32 = 4096 and the other higher values of apc->tx_queue_size
* are always power of two
*/
txq_size = MAX_SEND_BUFFERS_PER_QUEUE * 32;
BUILD_BUG_ON(!MANA_PAGE_ALIGNED(txq_size));
txq_size = apc->tx_queue_size * 32;
cq_size = MAX_SEND_BUFFERS_PER_QUEUE * COMP_ENTRY_SIZE;
cq_size = MANA_PAGE_ALIGN(cq_size);
cq_size = apc->tx_queue_size * COMP_ENTRY_SIZE;
gc = gd->gdma_context;
......@@ -2155,10 +2157,11 @@ static int mana_push_wqe(struct mana_rxq *rxq)
static int mana_create_page_pool(struct mana_rxq *rxq, struct gdma_context *gc)
{
struct mana_port_context *mpc = netdev_priv(rxq->ndev);
struct page_pool_params pprm = {};
int ret;
pprm.pool_size = RX_BUFFERS_PER_QUEUE;
pprm.pool_size = mpc->rx_queue_size;
pprm.nid = gc->numa_node;
pprm.napi = &rxq->rx_cq.napi;
pprm.netdev = rxq->ndev;
......@@ -2190,13 +2193,13 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc,
gc = gd->gdma_context;
rxq = kzalloc(struct_size(rxq, rx_oobs, RX_BUFFERS_PER_QUEUE),
rxq = kzalloc(struct_size(rxq, rx_oobs, apc->rx_queue_size),
GFP_KERNEL);
if (!rxq)
return NULL;
rxq->ndev = ndev;
rxq->num_rx_buf = RX_BUFFERS_PER_QUEUE;
rxq->num_rx_buf = apc->rx_queue_size;
rxq->rxq_idx = rxq_idx;
rxq->rxobj = INVALID_MANA_HANDLE;
......@@ -2744,6 +2747,8 @@ static int mana_probe_port(struct mana_context *ac, int port_idx,
apc->ndev = ndev;
apc->max_queues = gc->max_num_queues;
apc->num_queues = gc->max_num_queues;
apc->tx_queue_size = DEF_TX_BUFFERS_PER_QUEUE;
apc->rx_queue_size = DEF_RX_BUFFERS_PER_QUEUE;
apc->port_handle = INVALID_MANA_HANDLE;
apc->pf_filter_handle = INVALID_MANA_HANDLE;
apc->port_idx = port_idx;
......
......@@ -369,6 +369,78 @@ static int mana_set_channels(struct net_device *ndev,
return err;
}
static void mana_get_ringparam(struct net_device *ndev,
struct ethtool_ringparam *ring,
struct kernel_ethtool_ringparam *kernel_ring,
struct netlink_ext_ack *extack)
{
struct mana_port_context *apc = netdev_priv(ndev);
ring->rx_pending = apc->rx_queue_size;
ring->tx_pending = apc->tx_queue_size;
ring->rx_max_pending = MAX_RX_BUFFERS_PER_QUEUE;
ring->tx_max_pending = MAX_TX_BUFFERS_PER_QUEUE;
}
static int mana_set_ringparam(struct net_device *ndev,
struct ethtool_ringparam *ring,
struct kernel_ethtool_ringparam *kernel_ring,
struct netlink_ext_ack *extack)
{
struct mana_port_context *apc = netdev_priv(ndev);
u32 new_tx, new_rx;
u32 old_tx, old_rx;
int err;
old_tx = apc->tx_queue_size;
old_rx = apc->rx_queue_size;
if (ring->tx_pending < MIN_TX_BUFFERS_PER_QUEUE) {
NL_SET_ERR_MSG_FMT(extack, "tx:%d less than the min:%d", ring->tx_pending,
MIN_TX_BUFFERS_PER_QUEUE);
return -EINVAL;
}
if (ring->rx_pending < MIN_RX_BUFFERS_PER_QUEUE) {
NL_SET_ERR_MSG_FMT(extack, "rx:%d less than the min:%d", ring->rx_pending,
MIN_RX_BUFFERS_PER_QUEUE);
return -EINVAL;
}
new_rx = roundup_pow_of_two(ring->rx_pending);
new_tx = roundup_pow_of_two(ring->tx_pending);
netdev_info(ndev, "Using nearest power of 2 values for Txq:%d Rxq:%d\n",
new_tx, new_rx);
/* pre-allocating new buffers to prevent failures in mana_attach() later */
apc->rx_queue_size = new_rx;
err = mana_pre_alloc_rxbufs(apc, ndev->mtu);
apc->rx_queue_size = old_rx;
if (err) {
netdev_err(ndev, "Insufficient memory for new allocations\n");
return err;
}
err = mana_detach(ndev, false);
if (err) {
netdev_err(ndev, "mana_detach failed: %d\n", err);
goto out;
}
apc->tx_queue_size = new_tx;
apc->rx_queue_size = new_rx;
err = mana_attach(ndev);
if (err) {
netdev_err(ndev, "mana_attach failed: %d\n", err);
apc->tx_queue_size = old_tx;
apc->rx_queue_size = old_rx;
}
out:
mana_pre_dealloc_rxbufs(apc);
return err;
}
const struct ethtool_ops mana_ethtool_ops = {
.get_ethtool_stats = mana_get_ethtool_stats,
.get_sset_count = mana_get_sset_count,
......@@ -380,4 +452,6 @@ const struct ethtool_ops mana_ethtool_ops = {
.set_rxfh = mana_set_rxfh,
.get_channels = mana_get_channels,
.set_channels = mana_set_channels,
.get_ringparam = mana_get_ringparam,
.set_ringparam = mana_set_ringparam,
};
......@@ -38,9 +38,21 @@ enum TRI_STATE {
#define COMP_ENTRY_SIZE 64
#define RX_BUFFERS_PER_QUEUE 512
/* This Max value for RX buffers is derived from __alloc_page()'s max page
* allocation calculation. It allows maximum 2^(MAX_ORDER -1) pages. RX buffer
* size beyond this value gets rejected by __alloc_page() call.
*/
#define MAX_RX_BUFFERS_PER_QUEUE 8192
#define DEF_RX_BUFFERS_PER_QUEUE 512
#define MIN_RX_BUFFERS_PER_QUEUE 128
#define MAX_SEND_BUFFERS_PER_QUEUE 256
/* This max value for TX buffers is derived as the maximum allocatable
* pages supported on host per guest through testing. TX buffer size beyond
* this value is rejected by the hardware.
*/
#define MAX_TX_BUFFERS_PER_QUEUE 16384
#define DEF_TX_BUFFERS_PER_QUEUE 256
#define MIN_TX_BUFFERS_PER_QUEUE 128
#define EQ_SIZE (8 * MANA_PAGE_SIZE)
......@@ -286,7 +298,7 @@ struct mana_recv_buf_oob {
void *buf_va;
bool from_pool; /* allocated from a page pool */
/* SGL of the buffer going to be sent has part of the work request. */
/* SGL of the buffer going to be sent as part of the work request. */
u32 num_sge;
struct gdma_sge sgl[MAX_RX_WQE_SGL_ENTRIES];
......@@ -438,6 +450,9 @@ struct mana_port_context {
unsigned int max_queues;
unsigned int num_queues;
unsigned int rx_queue_size;
unsigned int tx_queue_size;
mana_handle_t port_handle;
mana_handle_t pf_filter_handle;
......@@ -473,6 +488,8 @@ struct bpf_prog *mana_xdp_get(struct mana_port_context *apc);
void mana_chn_setxdp(struct mana_port_context *apc, struct bpf_prog *prog);
int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf);
void mana_query_gf_stats(struct mana_port_context *apc);
int mana_pre_alloc_rxbufs(struct mana_port_context *apc, int mtu);
void mana_pre_dealloc_rxbufs(struct mana_port_context *apc);
extern const struct ethtool_ops mana_ethtool_ops;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment