averello/linux-stable-mirror
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git synced 2026-06-21 15:43:21 +02:00
Code Issues Packages Projects Releases Wiki Activity

net: mana: Use per-queue allocation for tx_qp to reduce allocation size

Browse Source 
Convert tx_qp from a single contiguous array allocation to per-queue
individual allocations. Each mana_tx_qp struct is approximately 35KB.
With many queues (e.g., 32/64), the flat array requires a single
contiguous allocation that can fail under memory fragmentation.

Change mana_tx_qp *tx_qp to mana_tx_qp **tx_qp (array of pointers),
allocating each queue's mana_tx_qp individually via kvzalloc. This
reduces each allocation to ~35KB and provides vmalloc fallback,
avoiding allocation failure due to fragmentation.

Signed-off-by: Aditya Garg <gargaditya@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Link: https://patch.msgid.link/20260502074552.23857-2-gargaditya@linux.microsoft.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This commit is contained in:
Aditya Garg
2026-05-02 00:45:33 -07:00
committed by Jakub Kicinski
parent 561e066284
commit d07efe5a6e
4 changed files with 33 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files
drivers/net/ethernet/microsoft/mana/mana_bpf.c
+1 -1
View File
@@ -68,7 +68,7 @@ int mana_xdp_xmit(struct net_device *ndev, int n, struct xdp_frame **frames,
count++;
}
tx_stats = &apc->tx_qp[q_idx].txq.stats;
tx_stats = &apc->tx_qp[q_idx]->txq.stats;
u64_stats_update_begin(&tx_stats->syncp);
tx_stats->xdp_xmit += count;
drivers/net/ethernet/microsoft/mana/mana_en.c
+30 -19
View File
@@ -355,9 +355,9 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev)
if (skb_cow_head(skb, MANA_HEADROOM))
goto tx_drop_count;
txq = &apc->tx_qp[txq_idx].txq;
txq = &apc->tx_qp[txq_idx]->txq;
gdma_sq = txq->gdma_sq;
cq = &apc->tx_qp[txq_idx].tx_cq;
cq = &apc->tx_qp[txq_idx]->tx_cq;
tx_stats = &txq->stats;
BUILD_BUG_ON(MAX_TX_WQE_SGL_ENTRIES != MANA_MAX_TX_WQE_SGL_ENTRIES);
@@ -614,7 +614,7 @@ static void mana_get_stats64(struct net_device *ndev,
}
for (q = 0; q < num_queues; q++) {
tx_stats = &apc->tx_qp[q].txq.stats;
tx_stats = &apc->tx_qp[q]->txq.stats;
do {
start = u64_stats_fetch_begin(&tx_stats->syncp);
@@ -2327,21 +2327,26 @@ static void mana_destroy_txq(struct mana_port_context *apc)
return;
for (i = 0; i < apc->num_queues; i++) {
debugfs_remove_recursive(apc->tx_qp[i].mana_tx_debugfs);
apc->tx_qp[i].mana_tx_debugfs = NULL;
if (!apc->tx_qp[i])
continue;
napi = &apc->tx_qp[i].tx_cq.napi;
if (apc->tx_qp[i].txq.napi_initialized) {
debugfs_remove_recursive(apc->tx_qp[i]->mana_tx_debugfs);
apc->tx_qp[i]->mana_tx_debugfs = NULL;
napi = &apc->tx_qp[i]->tx_cq.napi;
if (apc->tx_qp[i]->txq.napi_initialized) {
napi_synchronize(napi);
napi_disable_locked(napi);
netif_napi_del_locked(napi);
apc->tx_qp[i].txq.napi_initialized = false;
apc->tx_qp[i]->txq.napi_initialized = false;
}
mana_destroy_wq_obj(apc, GDMA_SQ, apc->tx_qp[i].tx_object);
mana_destroy_wq_obj(apc, GDMA_SQ, apc->tx_qp[i]->tx_object);
mana_deinit_cq(apc, &apc->tx_qp[i].tx_cq);
mana_deinit_cq(apc, &apc->tx_qp[i]->tx_cq);
mana_deinit_txq(apc, &apc->tx_qp[i].txq);
mana_deinit_txq(apc, &apc->tx_qp[i]->txq);
kvfree(apc->tx_qp[i]);
}
kfree(apc->tx_qp);
@@ -2350,7 +2355,7 @@ static void mana_destroy_txq(struct mana_port_context *apc)
static void mana_create_txq_debugfs(struct mana_port_context *apc, int idx)
{
struct mana_tx_qp *tx_qp = &apc->tx_qp[idx];
struct mana_tx_qp *tx_qp = apc->tx_qp[idx];
char qnum[32];
sprintf(qnum, "TX-%d", idx);
@@ -2389,7 +2394,7 @@ static int mana_create_txq(struct mana_port_context *apc,
int err;
int i;
apc->tx_qp = kzalloc_objs(struct mana_tx_qp, apc->num_queues);
apc->tx_qp = kzalloc_objs(struct mana_tx_qp *, apc->num_queues);
if (!apc->tx_qp)
return -ENOMEM;
@@ -2409,10 +2414,16 @@ static int mana_create_txq(struct mana_port_context *apc,
gc = gd->gdma_context;
for (i = 0; i < apc->num_queues; i++) {
apc->tx_qp[i].tx_object = INVALID_MANA_HANDLE;
apc->tx_qp[i] = kvzalloc_obj(*apc->tx_qp[i]);
if (!apc->tx_qp[i]) {
err = -ENOMEM;
goto out;
}
apc->tx_qp[i]->tx_object = INVALID_MANA_HANDLE;
/* Create SQ */
txq = &apc->tx_qp[i].txq;
txq = &apc->tx_qp[i]->txq;
u64_stats_init(&txq->stats.syncp);
txq->ndev = net;
@@ -2430,7 +2441,7 @@ static int mana_create_txq(struct mana_port_context *apc,
goto out;
/* Create SQ's CQ */
cq = &apc->tx_qp[i].tx_cq;
cq = &apc->tx_qp[i]->tx_cq;
cq->type = MANA_CQ_TYPE_TX;
cq->txq = txq;
@@ -2459,7 +2470,7 @@ static int mana_create_txq(struct mana_port_context *apc,
err = mana_create_wq_obj(apc, apc->port_handle, GDMA_SQ,
&wq_spec, &cq_spec,
&apc->tx_qp[i].tx_object);
&apc->tx_qp[i]->tx_object);
if (err)
goto out;
@@ -3294,7 +3305,7 @@ static int mana_dealloc_queues(struct net_device *ndev)
*/
for (i = 0; i < apc->num_queues; i++) {
txq = &apc->tx_qp[i].txq;
txq = &apc->tx_qp[i]->txq;
tsleep = 1000;
while (atomic_read(&txq->pending_sends) > 0 &&
time_before(jiffies, timeout)) {
@@ -3313,7 +3324,7 @@ static int mana_dealloc_queues(struct net_device *ndev)
}
for (i = 0; i < apc->num_queues; i++) {
txq = &apc->tx_qp[i].txq;
txq = &apc->tx_qp[i]->txq;
while ((skb = skb_dequeue(&txq->pending_skbs))) {
mana_unmap_skb(skb, apc);
dev_kfree_skb_any(skb);
drivers/net/ethernet/microsoft/mana/mana_ethtool.c
+1 -1
View File
@@ -260,7 +260,7 @@ static void mana_get_ethtool_stats(struct net_device *ndev,
}
for (q = 0; q < num_queues; q++) {
tx_stats = &apc->tx_qp[q].txq.stats;
tx_stats = &apc->tx_qp[q]->txq.stats;
do {
start = u64_stats_fetch_begin(&tx_stats->syncp);
include/net/mana/mana.h
+1 -1
View File
@@ -507,7 +507,7 @@ struct mana_port_context {
bool tx_shortform_allowed;
u16 tx_vp_offset;
struct mana_tx_qp *tx_qp;
struct mana_tx_qp **tx_qp;
/* Indirection Table for RX & TX. The values are queue indexes */
u32 *indir_table;