* [PATCH net-next v3 1/6] net: mana: Create separate EQs for each vPort
2026-03-06 21:32 [PATCH net-next v3 0/6] net: mana: Per-vPort EQ and MSI-X interrupt management Long Li
@ 2026-03-06 21:32 ` Long Li
2026-03-06 21:32 ` [PATCH net-next v3 2/6] net: mana: Query device capabilities and configure MSI-X sharing for EQs Long Li
` (4 subsequent siblings)
5 siblings, 0 replies; 9+ messages in thread
From: Long Li @ 2026-03-06 21:32 UTC (permalink / raw)
To: K . Y . Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui,
David S . Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Shradha Gupta, Simon Horman, Konstantin Taranov,
Souradeep Chakrabarti, Erick Archer, linux-hyperv, netdev,
linux-kernel, linux-rdma
Cc: Long Li
To prepare for assigning vPorts to dedicated MSI-X vectors, remove EQ
sharing among the vPorts and create dedicated EQs for each vPort.
Move the EQ definition from struct mana_context to struct mana_port_context
and update related support functions. Export mana_create_eq() and
mana_destroy_eq() for use by the MANA RDMA driver.
Signed-off-by: Long Li <longli@microsoft.com>
---
Changes in v3:
- Added NULL check for mpc->eqs in mana_ib_create_qp_rss() to prevent
kernel crash when RSS QP is created before EQs are allocated
---
drivers/infiniband/hw/mana/main.c | 14 ++-
drivers/infiniband/hw/mana/qp.c | 12 +-
drivers/net/ethernet/microsoft/mana/mana_en.c | 109 ++++++++++--------
include/net/mana/mana.h | 7 +-
4 files changed, 90 insertions(+), 52 deletions(-)
diff --git a/drivers/infiniband/hw/mana/main.c b/drivers/infiniband/hw/mana/main.c
index 8d99cd00f002..d51dd0ee85f4 100644
--- a/drivers/infiniband/hw/mana/main.c
+++ b/drivers/infiniband/hw/mana/main.c
@@ -20,8 +20,10 @@ void mana_ib_uncfg_vport(struct mana_ib_dev *dev, struct mana_ib_pd *pd,
pd->vport_use_count--;
WARN_ON(pd->vport_use_count < 0);
- if (!pd->vport_use_count)
+ if (!pd->vport_use_count) {
+ mana_destroy_eq(mpc);
mana_uncfg_vport(mpc);
+ }
mutex_unlock(&pd->vport_mutex);
}
@@ -55,15 +57,21 @@ int mana_ib_cfg_vport(struct mana_ib_dev *dev, u32 port, struct mana_ib_pd *pd,
return err;
}
- mutex_unlock(&pd->vport_mutex);
pd->tx_shortform_allowed = mpc->tx_shortform_allowed;
pd->tx_vp_offset = mpc->tx_vp_offset;
+ err = mana_create_eq(mpc);
+ if (err) {
+ mana_uncfg_vport(mpc);
+ pd->vport_use_count--;
+ }
+
+ mutex_unlock(&pd->vport_mutex);
ibdev_dbg(&dev->ib_dev, "vport handle %llx pdid %x doorbell_id %x\n",
mpc->port_handle, pd->pdn, doorbell_id);
- return 0;
+ return err;
}
int mana_ib_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
diff --git a/drivers/infiniband/hw/mana/qp.c b/drivers/infiniband/hw/mana/qp.c
index 82f84f7ad37a..039c86eca0dc 100644
--- a/drivers/infiniband/hw/mana/qp.c
+++ b/drivers/infiniband/hw/mana/qp.c
@@ -188,7 +188,15 @@ static int mana_ib_create_qp_rss(struct ib_qp *ibqp, struct ib_pd *pd,
cq_spec.gdma_region = cq->queue.gdma_region;
cq_spec.queue_size = cq->cqe * COMP_ENTRY_SIZE;
cq_spec.modr_ctx_id = 0;
- eq = &mpc->ac->eqs[cq->comp_vector];
+ /* EQs are created when a raw QP configures the vport.
+ * A raw QP must be created before creating rwq_ind_tbl.
+ */
+ if (!mpc->eqs) {
+ ret = -EINVAL;
+ i--;
+ goto fail;
+ }
+ eq = &mpc->eqs[cq->comp_vector % mpc->num_queues];
cq_spec.attached_eq = eq->eq->id;
ret = mana_create_wq_obj(mpc, mpc->port_handle, GDMA_RQ,
@@ -340,7 +348,7 @@ static int mana_ib_create_qp_raw(struct ib_qp *ibqp, struct ib_pd *ibpd,
cq_spec.queue_size = send_cq->cqe * COMP_ENTRY_SIZE;
cq_spec.modr_ctx_id = 0;
eq_vec = send_cq->comp_vector;
- eq = &mpc->ac->eqs[eq_vec];
+ eq = &mpc->eqs[eq_vec % mpc->num_queues];
cq_spec.attached_eq = eq->eq->id;
err = mana_create_wq_obj(mpc, mpc->port_handle, GDMA_SQ, &wq_spec,
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 56ee993e3a43..428dafaf315b 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -1588,78 +1588,82 @@ void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type,
}
EXPORT_SYMBOL_NS(mana_destroy_wq_obj, "NET_MANA");
-static void mana_destroy_eq(struct mana_context *ac)
+void mana_destroy_eq(struct mana_port_context *apc)
{
+ struct mana_context *ac = apc->ac;
struct gdma_context *gc = ac->gdma_dev->gdma_context;
struct gdma_queue *eq;
int i;
- if (!ac->eqs)
+ if (!apc->eqs)
return;
- debugfs_remove_recursive(ac->mana_eqs_debugfs);
- ac->mana_eqs_debugfs = NULL;
+ debugfs_remove_recursive(apc->mana_eqs_debugfs);
+ apc->mana_eqs_debugfs = NULL;
- for (i = 0; i < gc->max_num_queues; i++) {
- eq = ac->eqs[i].eq;
+ for (i = 0; i < apc->num_queues; i++) {
+ eq = apc->eqs[i].eq;
if (!eq)
continue;
mana_gd_destroy_queue(gc, eq);
}
- kfree(ac->eqs);
- ac->eqs = NULL;
+ kfree(apc->eqs);
+ apc->eqs = NULL;
}
+EXPORT_SYMBOL_NS(mana_destroy_eq, "NET_MANA");
-static void mana_create_eq_debugfs(struct mana_context *ac, int i)
+static void mana_create_eq_debugfs(struct mana_port_context *apc, int i)
{
- struct mana_eq eq = ac->eqs[i];
+ struct mana_eq eq = apc->eqs[i];
char eqnum[32];
sprintf(eqnum, "eq%d", i);
- eq.mana_eq_debugfs = debugfs_create_dir(eqnum, ac->mana_eqs_debugfs);
+ eq.mana_eq_debugfs = debugfs_create_dir(eqnum, apc->mana_eqs_debugfs);
debugfs_create_u32("head", 0400, eq.mana_eq_debugfs, &eq.eq->head);
debugfs_create_u32("tail", 0400, eq.mana_eq_debugfs, &eq.eq->tail);
debugfs_create_file("eq_dump", 0400, eq.mana_eq_debugfs, eq.eq, &mana_dbg_q_fops);
}
-static int mana_create_eq(struct mana_context *ac)
+int mana_create_eq(struct mana_port_context *apc)
{
- struct gdma_dev *gd = ac->gdma_dev;
+ struct gdma_dev *gd = apc->ac->gdma_dev;
struct gdma_context *gc = gd->gdma_context;
struct gdma_queue_spec spec = {};
int err;
int i;
- ac->eqs = kzalloc_objs(struct mana_eq, gc->max_num_queues);
- if (!ac->eqs)
+ WARN_ON(apc->eqs);
+ apc->eqs = kzalloc_objs(struct mana_eq, apc->num_queues);
+ if (!apc->eqs)
return -ENOMEM;
spec.type = GDMA_EQ;
spec.monitor_avl_buf = false;
spec.queue_size = EQ_SIZE;
spec.eq.callback = NULL;
- spec.eq.context = ac->eqs;
+ spec.eq.context = apc->eqs;
spec.eq.log2_throttle_limit = LOG2_EQ_THROTTLE;
- ac->mana_eqs_debugfs = debugfs_create_dir("EQs", gc->mana_pci_debugfs);
+ apc->mana_eqs_debugfs = debugfs_create_dir("EQs", apc->mana_port_debugfs);
- for (i = 0; i < gc->max_num_queues; i++) {
+ for (i = 0; i < apc->num_queues; i++) {
spec.eq.msix_index = (i + 1) % gc->num_msix_usable;
- err = mana_gd_create_mana_eq(gd, &spec, &ac->eqs[i].eq);
+ err = mana_gd_create_mana_eq(gd, &spec, &apc->eqs[i].eq);
if (err) {
dev_err(gc->dev, "Failed to create EQ %d : %d\n", i, err);
goto out;
}
- mana_create_eq_debugfs(ac, i);
+ mana_create_eq_debugfs(apc, i);
}
return 0;
out:
- mana_destroy_eq(ac);
+ mana_destroy_eq(apc);
return err;
}
+EXPORT_SYMBOL_NS(mana_create_eq, "NET_MANA");
static int mana_fence_rq(struct mana_port_context *apc, struct mana_rxq *rxq)
{
@@ -2377,7 +2381,7 @@ static int mana_create_txq(struct mana_port_context *apc,
spec.monitor_avl_buf = false;
spec.queue_size = cq_size;
spec.cq.callback = mana_schedule_napi;
- spec.cq.parent_eq = ac->eqs[i].eq;
+ spec.cq.parent_eq = apc->eqs[i].eq;
spec.cq.context = cq;
err = mana_gd_create_mana_wq_cq(gd, &spec, &cq->gdma_cq);
if (err)
@@ -2770,13 +2774,12 @@ static void mana_create_rxq_debugfs(struct mana_port_context *apc, int idx)
static int mana_add_rx_queues(struct mana_port_context *apc,
struct net_device *ndev)
{
- struct mana_context *ac = apc->ac;
struct mana_rxq *rxq;
int err = 0;
int i;
for (i = 0; i < apc->num_queues; i++) {
- rxq = mana_create_rxq(apc, i, &ac->eqs[i], ndev);
+ rxq = mana_create_rxq(apc, i, &apc->eqs[i], ndev);
if (!rxq) {
err = -ENOMEM;
netdev_err(ndev, "Failed to create rxq %d : %d\n", i, err);
@@ -2795,9 +2798,8 @@ static int mana_add_rx_queues(struct mana_port_context *apc,
return err;
}
-static void mana_destroy_vport(struct mana_port_context *apc)
+static void mana_destroy_rxqs(struct mana_port_context *apc)
{
- struct gdma_dev *gd = apc->ac->gdma_dev;
struct mana_rxq *rxq;
u32 rxq_idx;
@@ -2809,8 +2811,12 @@ static void mana_destroy_vport(struct mana_port_context *apc)
mana_destroy_rxq(apc, rxq, true);
apc->rxqs[rxq_idx] = NULL;
}
+}
+
+static void mana_destroy_vport(struct mana_port_context *apc)
+{
+ struct gdma_dev *gd = apc->ac->gdma_dev;
- mana_destroy_txq(apc);
mana_uncfg_vport(apc);
if (gd->gdma_context->is_pf && !apc->ac->bm_hostmode)
@@ -2831,11 +2837,7 @@ static int mana_create_vport(struct mana_port_context *apc,
return err;
}
- err = mana_cfg_vport(apc, gd->pdid, gd->doorbell);
- if (err)
- return err;
-
- return mana_create_txq(apc, net);
+ return mana_cfg_vport(apc, gd->pdid, gd->doorbell);
}
static int mana_rss_table_alloc(struct mana_port_context *apc)
@@ -3112,21 +3114,36 @@ int mana_alloc_queues(struct net_device *ndev)
err = mana_create_vport(apc, ndev);
if (err) {
- netdev_err(ndev, "Failed to create vPort %u : %d\n", apc->port_idx, err);
+ netdev_err(ndev, "Failed to create vPort %u : %d\n",
+ apc->port_idx, err);
return err;
}
+ err = mana_create_eq(apc);
+ if (err) {
+ netdev_err(ndev, "Failed to create EQ on vPort %u: %d\n",
+ apc->port_idx, err);
+ goto destroy_vport;
+ }
+
+ err = mana_create_txq(apc, ndev);
+ if (err) {
+ netdev_err(ndev, "Failed to create TXQ on vPort %u: %d\n",
+ apc->port_idx, err);
+ goto destroy_eq;
+ }
+
err = netif_set_real_num_tx_queues(ndev, apc->num_queues);
if (err) {
netdev_err(ndev,
"netif_set_real_num_tx_queues () failed for ndev with num_queues %u : %d\n",
apc->num_queues, err);
- goto destroy_vport;
+ goto destroy_txq;
}
err = mana_add_rx_queues(apc, ndev);
if (err)
- goto destroy_vport;
+ goto destroy_rxq;
apc->rss_state = apc->num_queues > 1 ? TRI_STATE_TRUE : TRI_STATE_FALSE;
@@ -3135,7 +3152,7 @@ int mana_alloc_queues(struct net_device *ndev)
netdev_err(ndev,
"netif_set_real_num_rx_queues () failed for ndev with num_queues %u : %d\n",
apc->num_queues, err);
- goto destroy_vport;
+ goto destroy_rxq;
}
mana_rss_table_init(apc);
@@ -3143,19 +3160,25 @@ int mana_alloc_queues(struct net_device *ndev)
err = mana_config_rss(apc, TRI_STATE_TRUE, true, true);
if (err) {
netdev_err(ndev, "Failed to configure RSS table: %d\n", err);
- goto destroy_vport;
+ goto destroy_rxq;
}
if (gd->gdma_context->is_pf && !apc->ac->bm_hostmode) {
err = mana_pf_register_filter(apc);
if (err)
- goto destroy_vport;
+ goto destroy_rxq;
}
mana_chn_setxdp(apc, mana_xdp_get(apc));
return 0;
+destroy_rxq:
+ mana_destroy_rxqs(apc);
+destroy_txq:
+ mana_destroy_txq(apc);
+destroy_eq:
+ mana_destroy_eq(apc);
destroy_vport:
mana_destroy_vport(apc);
return err;
@@ -3258,6 +3281,9 @@ static int mana_dealloc_queues(struct net_device *ndev)
netdev_err(ndev, "Failed to disable vPort: %d\n", err);
/* Even in err case, still need to cleanup the vPort */
+ mana_destroy_rxqs(apc);
+ mana_destroy_txq(apc);
+ mana_destroy_eq(apc);
mana_destroy_vport(apc);
return 0;
@@ -3572,12 +3598,6 @@ int mana_probe(struct gdma_dev *gd, bool resuming)
gd->driver_data = ac;
}
- err = mana_create_eq(ac);
- if (err) {
- dev_err(dev, "Failed to create EQs: %d\n", err);
- goto out;
- }
-
err = mana_query_device_cfg(ac, MANA_MAJOR_VERSION, MANA_MINOR_VERSION,
MANA_MICRO_VERSION, &num_ports, &bm_hostmode);
if (err)
@@ -3716,7 +3736,6 @@ void mana_remove(struct gdma_dev *gd, bool suspending)
free_netdev(ndev);
}
- mana_destroy_eq(ac);
out:
if (ac->per_port_queue_reset_wq) {
destroy_workqueue(ac->per_port_queue_reset_wq);
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index a078af283bdd..787e637059df 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -478,8 +478,6 @@ struct mana_context {
u8 bm_hostmode;
struct mana_ethtool_hc_stats hc_stats;
- struct mana_eq *eqs;
- struct dentry *mana_eqs_debugfs;
struct workqueue_struct *per_port_queue_reset_wq;
/* Workqueue for querying hardware stats */
struct delayed_work gf_stats_work;
@@ -499,6 +497,9 @@ struct mana_port_context {
u8 mac_addr[ETH_ALEN];
+ struct mana_eq *eqs;
+ struct dentry *mana_eqs_debugfs;
+
enum TRI_STATE rss_state;
mana_handle_t default_rxobj;
@@ -1023,6 +1024,8 @@ void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type,
int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id,
u32 doorbell_pg_id);
void mana_uncfg_vport(struct mana_port_context *apc);
+int mana_create_eq(struct mana_port_context *apc);
+void mana_destroy_eq(struct mana_port_context *apc);
struct net_device *mana_get_primary_netdev(struct mana_context *ac,
u32 port_index,
--
2.43.0
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH net-next v3 2/6] net: mana: Query device capabilities and configure MSI-X sharing for EQs
2026-03-06 21:32 [PATCH net-next v3 0/6] net: mana: Per-vPort EQ and MSI-X interrupt management Long Li
2026-03-06 21:32 ` [PATCH net-next v3 1/6] net: mana: Create separate EQs for each vPort Long Li
@ 2026-03-06 21:32 ` Long Li
2026-03-06 21:32 ` [PATCH net-next v3 3/6] net: mana: Introduce GIC context with refcounting for interrupt management Long Li
` (3 subsequent siblings)
5 siblings, 0 replies; 9+ messages in thread
From: Long Li @ 2026-03-06 21:32 UTC (permalink / raw)
To: K . Y . Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui,
David S . Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Shradha Gupta, Simon Horman, Konstantin Taranov,
Souradeep Chakrabarti, Erick Archer, linux-hyperv, netdev,
linux-kernel, linux-rdma
Cc: Long Li
When querying the device, adjust the max number of queues to allow
dedicated MSI-X vectors for each vPort. The number of queues per vPort
is clamped to no less than 16. MSI-X sharing among vPorts is disabled
by default and is only enabled when there are not enough MSI-X vectors
for dedicated allocation.
Rename mana_query_device_cfg() to mana_gd_query_device_cfg() as it is
used at GDMA device probe time for querying device capabilities.
Signed-off-by: Long Li <longli@microsoft.com>
---
.../net/ethernet/microsoft/mana/gdma_main.c | 66 ++++++++++++++++---
drivers/net/ethernet/microsoft/mana/mana_en.c | 36 +++++-----
include/net/mana/gdma.h | 13 +++-
3 files changed, 91 insertions(+), 24 deletions(-)
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index aef8612b73cb..a6ab2f053fe9 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -107,6 +107,9 @@ static int mana_gd_query_max_resources(struct pci_dev *pdev)
struct gdma_context *gc = pci_get_drvdata(pdev);
struct gdma_query_max_resources_resp resp = {};
struct gdma_general_req req = {};
+ unsigned int max_num_queues;
+ u8 bm_hostmode;
+ u16 num_ports;
int err;
mana_gd_init_req_hdr(&req.hdr, GDMA_QUERY_MAX_RESOURCES,
@@ -152,6 +155,40 @@ static int mana_gd_query_max_resources(struct pci_dev *pdev)
if (gc->max_num_queues > gc->num_msix_usable - 1)
gc->max_num_queues = gc->num_msix_usable - 1;
+ err = mana_gd_query_device_cfg(gc, MANA_MAJOR_VERSION, MANA_MINOR_VERSION,
+ MANA_MICRO_VERSION, &num_ports, &bm_hostmode);
+ if (err)
+ return err;
+
+ if (!num_ports)
+ return -EINVAL;
+
+ /*
+ * Adjust gc->max_num_queues returned from the SOC to allow dedicated MSIx
+ * for each vPort. Reduce max_num_queues to no less than 16 if necessary
+ */
+ max_num_queues = (gc->num_msix_usable - 1) / num_ports;
+ max_num_queues = roundup_pow_of_two(max(max_num_queues, 1U));
+ if (max_num_queues < 16)
+ max_num_queues = 16;
+
+ /*
+ * Use dedicated MSIx for EQs whenever possible, use MSIx sharing for
+ * Ethernet EQs when (max_num_queues * num_ports > num_msix_usable - 1)
+ */
+ max_num_queues = min(gc->max_num_queues, max_num_queues);
+ if (max_num_queues * num_ports > gc->num_msix_usable - 1)
+ gc->msi_sharing = true;
+
+ /* If MSI is shared, use max allowed value */
+ if (gc->msi_sharing)
+ gc->max_num_queues_vport = min(gc->num_msix_usable - 1, gc->max_num_queues);
+ else
+ gc->max_num_queues_vport = max_num_queues;
+
+ dev_info(gc->dev, "MSI sharing mode %d max queues %d\n",
+ gc->msi_sharing, gc->max_num_queues);
+
return 0;
}
@@ -1803,6 +1840,7 @@ static int mana_gd_setup_hwc_irqs(struct pci_dev *pdev)
/* Need 1 interrupt for HWC */
max_irqs = min(num_online_cpus(), MANA_MAX_NUM_QUEUES) + 1;
min_irqs = 2;
+ gc->msi_sharing = true;
}
nvec = pci_alloc_irq_vectors(pdev, min_irqs, max_irqs, PCI_IRQ_MSIX);
@@ -1881,6 +1919,8 @@ static void mana_gd_remove_irqs(struct pci_dev *pdev)
pci_free_irq_vectors(pdev);
+ bitmap_free(gc->msi_bitmap);
+ gc->msi_bitmap = NULL;
gc->max_num_msix = 0;
gc->num_msix_usable = 0;
}
@@ -1912,20 +1952,30 @@ static int mana_gd_setup(struct pci_dev *pdev)
if (err)
goto destroy_hwc;
- err = mana_gd_query_max_resources(pdev);
+ err = mana_gd_detect_devices(pdev);
if (err)
goto destroy_hwc;
- err = mana_gd_setup_remaining_irqs(pdev);
- if (err) {
- dev_err(gc->dev, "Failed to setup remaining IRQs: %d", err);
- goto destroy_hwc;
- }
-
- err = mana_gd_detect_devices(pdev);
+ err = mana_gd_query_max_resources(pdev);
if (err)
goto destroy_hwc;
+ if (!gc->msi_sharing) {
+ gc->msi_bitmap = bitmap_zalloc(gc->num_msix_usable, GFP_KERNEL);
+ if (!gc->msi_bitmap) {
+ err = -ENOMEM;
+ goto destroy_hwc;
+ }
+ /* Set bit for HWC */
+ set_bit(0, gc->msi_bitmap);
+ } else {
+ err = mana_gd_setup_remaining_irqs(pdev);
+ if (err) {
+ dev_err(gc->dev, "Failed to setup remaining IRQs: %d", err);
+ goto destroy_hwc;
+ }
+ }
+
dev_dbg(&pdev->dev, "mana gdma setup successful\n");
return 0;
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 428dafaf315b..bfa0f354355d 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -1000,10 +1000,9 @@ static int mana_init_port_context(struct mana_port_context *apc)
return !apc->rxqs ? -ENOMEM : 0;
}
-static int mana_send_request(struct mana_context *ac, void *in_buf,
- u32 in_len, void *out_buf, u32 out_len)
+static int gdma_mana_send_request(struct gdma_context *gc, void *in_buf,
+ u32 in_len, void *out_buf, u32 out_len)
{
- struct gdma_context *gc = ac->gdma_dev->gdma_context;
struct gdma_resp_hdr *resp = out_buf;
struct gdma_req_hdr *req = in_buf;
struct device *dev = gc->dev;
@@ -1037,6 +1036,14 @@ static int mana_send_request(struct mana_context *ac, void *in_buf,
return 0;
}
+static int mana_send_request(struct mana_context *ac, void *in_buf,
+ u32 in_len, void *out_buf, u32 out_len)
+{
+ struct gdma_context *gc = ac->gdma_dev->gdma_context;
+
+ return gdma_mana_send_request(gc, in_buf, in_len, out_buf, out_len);
+}
+
static int mana_verify_resp_hdr(const struct gdma_resp_hdr *resp_hdr,
const enum mana_command_code expected_code,
const u32 min_size)
@@ -1170,11 +1177,10 @@ static void mana_pf_deregister_filter(struct mana_port_context *apc)
err, resp.hdr.status);
}
-static int mana_query_device_cfg(struct mana_context *ac, u32 proto_major_ver,
- u32 proto_minor_ver, u32 proto_micro_ver,
- u16 *max_num_vports, u8 *bm_hostmode)
+int mana_gd_query_device_cfg(struct gdma_context *gc, u32 proto_major_ver,
+ u32 proto_minor_ver, u32 proto_micro_ver,
+ u16 *max_num_vports, u8 *bm_hostmode)
{
- struct gdma_context *gc = ac->gdma_dev->gdma_context;
struct mana_query_device_cfg_resp resp = {};
struct mana_query_device_cfg_req req = {};
struct device *dev = gc->dev;
@@ -1189,7 +1195,7 @@ static int mana_query_device_cfg(struct mana_context *ac, u32 proto_major_ver,
req.proto_minor_ver = proto_minor_ver;
req.proto_micro_ver = proto_micro_ver;
- err = mana_send_request(ac, &req, sizeof(req), &resp, sizeof(resp));
+ err = gdma_mana_send_request(gc, &req, sizeof(req), &resp, sizeof(resp));
if (err) {
dev_err(dev, "Failed to query config: %d", err);
return err;
@@ -1217,8 +1223,6 @@ static int mana_query_device_cfg(struct mana_context *ac, u32 proto_major_ver,
else
*bm_hostmode = 0;
- debugfs_create_u16("adapter-MTU", 0400, gc->mana_pci_debugfs, &gc->adapter_mtu);
-
return 0;
}
@@ -3329,7 +3333,7 @@ static int mana_probe_port(struct mana_context *ac, int port_idx,
int err;
ndev = alloc_etherdev_mq(sizeof(struct mana_port_context),
- gc->max_num_queues);
+ gc->max_num_queues_vport);
if (!ndev)
return -ENOMEM;
@@ -3338,8 +3342,8 @@ static int mana_probe_port(struct mana_context *ac, int port_idx,
apc = netdev_priv(ndev);
apc->ac = ac;
apc->ndev = ndev;
- apc->max_queues = gc->max_num_queues;
- apc->num_queues = gc->max_num_queues;
+ apc->max_queues = gc->max_num_queues_vport;
+ apc->num_queues = gc->max_num_queues_vport;
apc->tx_queue_size = DEF_TX_BUFFERS_PER_QUEUE;
apc->rx_queue_size = DEF_RX_BUFFERS_PER_QUEUE;
apc->port_handle = INVALID_MANA_HANDLE;
@@ -3598,13 +3602,15 @@ int mana_probe(struct gdma_dev *gd, bool resuming)
gd->driver_data = ac;
}
- err = mana_query_device_cfg(ac, MANA_MAJOR_VERSION, MANA_MINOR_VERSION,
- MANA_MICRO_VERSION, &num_ports, &bm_hostmode);
+ err = mana_gd_query_device_cfg(gc, MANA_MAJOR_VERSION, MANA_MINOR_VERSION,
+ MANA_MICRO_VERSION, &num_ports, &bm_hostmode);
if (err)
goto out;
ac->bm_hostmode = bm_hostmode;
+ debugfs_create_u16("adapter-MTU", 0400, gc->mana_pci_debugfs, &gc->adapter_mtu);
+
if (!resuming) {
ac->num_ports = num_ports;
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index ec17004b10c0..b744253b44e8 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -399,8 +399,10 @@ struct gdma_context {
struct device *dev;
struct dentry *mana_pci_debugfs;
- /* Per-vPort max number of queues */
+ /* Hardware max number of queues */
unsigned int max_num_queues;
+ /* Per-vPort max number of queues */
+ unsigned int max_num_queues_vport;
unsigned int max_num_msix;
unsigned int num_msix_usable;
struct xarray irq_contexts;
@@ -444,6 +446,12 @@ struct gdma_context {
struct workqueue_struct *service_wq;
unsigned long flags;
+
+ /* Indicate if this device is sharing MSI for EQs on MANA */
+ bool msi_sharing;
+
+ /* Bitmap tracks where MSI is allocated when it is not shared for EQs */
+ unsigned long *msi_bitmap;
};
static inline bool mana_gd_is_mana(struct gdma_dev *gd)
@@ -1011,4 +1019,7 @@ int mana_gd_resume(struct pci_dev *pdev);
bool mana_need_log(struct gdma_context *gc, int err);
+int mana_gd_query_device_cfg(struct gdma_context *gc, u32 proto_major_ver,
+ u32 proto_minor_ver, u32 proto_micro_ver,
+ u16 *max_num_vports, u8 *bm_hostmode);
#endif /* _GDMA_H */
--
2.43.0
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH net-next v3 3/6] net: mana: Introduce GIC context with refcounting for interrupt management
2026-03-06 21:32 [PATCH net-next v3 0/6] net: mana: Per-vPort EQ and MSI-X interrupt management Long Li
2026-03-06 21:32 ` [PATCH net-next v3 1/6] net: mana: Create separate EQs for each vPort Long Li
2026-03-06 21:32 ` [PATCH net-next v3 2/6] net: mana: Query device capabilities and configure MSI-X sharing for EQs Long Li
@ 2026-03-06 21:32 ` Long Li
2026-03-06 21:33 ` [PATCH net-next v3 4/6] net: mana: Use GIC functions to allocate global EQs Long Li
` (2 subsequent siblings)
5 siblings, 0 replies; 9+ messages in thread
From: Long Li @ 2026-03-06 21:32 UTC (permalink / raw)
To: K . Y . Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui,
David S . Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Shradha Gupta, Simon Horman, Konstantin Taranov,
Souradeep Chakrabarti, Erick Archer, linux-hyperv, netdev,
linux-kernel, linux-rdma
Cc: Long Li
To allow Ethernet EQs to use dedicated or shared MSI-X vectors and RDMA
EQs to share the same MSI-X, introduce a GIC (GDMA IRQ Context) with
reference counting. This allows the driver to create an interrupt context
on an assigned or unassigned MSI-X vector and share it across multiple
EQ consumers.
Signed-off-by: Long Li <longli@microsoft.com>
---
.../net/ethernet/microsoft/mana/gdma_main.c | 158 ++++++++++++++++++
include/net/mana/gdma.h | 10 ++
2 files changed, 168 insertions(+)
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index a6ab2f053fe9..c43fd8089e77 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -1559,6 +1559,163 @@ static irqreturn_t mana_gd_intr(int irq, void *arg)
return IRQ_HANDLED;
}
+void mana_gd_put_gic(struct gdma_context *gc, bool use_msi_bitmap, int msi)
+{
+ struct pci_dev *dev = to_pci_dev(gc->dev);
+ struct msi_map irq_map;
+ struct gdma_irq_context *gic;
+ int irq;
+
+ mutex_lock(&gc->gic_mutex);
+
+ gic = xa_load(&gc->irq_contexts, msi);
+ if (WARN_ON(!gic)) {
+ mutex_unlock(&gc->gic_mutex);
+ return;
+ }
+
+ if (use_msi_bitmap)
+ gic->bitmap_refs--;
+
+ if (use_msi_bitmap && gic->bitmap_refs == 0)
+ clear_bit(msi, gc->msi_bitmap);
+
+ if (!refcount_dec_and_test(&gic->refcount))
+ goto out;
+
+ irq = pci_irq_vector(dev, msi);
+
+ irq_update_affinity_hint(irq, NULL);
+ free_irq(irq, gic);
+
+ if (pci_msix_can_alloc_dyn(dev)) {
+ irq_map.virq = irq;
+ irq_map.index = msi;
+ pci_msix_free_irq(dev, irq_map);
+ }
+
+ xa_erase(&gc->irq_contexts, msi);
+ kfree(gic);
+
+out:
+ mutex_unlock(&gc->gic_mutex);
+}
+EXPORT_SYMBOL_NS(mana_gd_put_gic, "NET_MANA");
+
+/*
+ * Get a GIC (GDMA IRQ Context) on a MSI vector
+ * a MSI can be shared between different EQs, this function supports setting
+ * up separate MSIs using a bitmap, or directly using the MSI index
+ *
+ * @use_msi_bitmap:
+ * True if MSI is assigned by this function on available slots from bitmap.
+ * False if MSI is passed from *msi_requested
+ */
+struct gdma_irq_context *mana_gd_get_gic(struct gdma_context *gc,
+ bool use_msi_bitmap,
+ int *msi_requested)
+{
+ struct gdma_irq_context *gic;
+ struct pci_dev *dev = to_pci_dev(gc->dev);
+ struct msi_map irq_map = { };
+ int irq;
+ int msi;
+ int err;
+
+ mutex_lock(&gc->gic_mutex);
+
+ if (use_msi_bitmap) {
+ msi = find_first_zero_bit(gc->msi_bitmap, gc->num_msix_usable);
+ if (msi >= gc->num_msix_usable) {
+ dev_err(gc->dev, "No free MSI vectors available\n");
+ gic = NULL;
+ goto out;
+ }
+ *msi_requested = msi;
+ } else {
+ msi = *msi_requested;
+ }
+
+ gic = xa_load(&gc->irq_contexts, msi);
+ if (gic) {
+ refcount_inc(&gic->refcount);
+ if (use_msi_bitmap) {
+ gic->bitmap_refs++;
+ set_bit(msi, gc->msi_bitmap);
+ }
+ goto out;
+ }
+
+ irq = pci_irq_vector(dev, msi);
+ if (irq == -EINVAL) {
+ irq_map = pci_msix_alloc_irq_at(dev, msi, NULL);
+ if (!irq_map.virq) {
+ err = irq_map.index;
+ dev_err(gc->dev,
+ "Failed to alloc irq_map msi %d err %d\n",
+ msi, err);
+ gic = NULL;
+ goto out;
+ }
+ irq = irq_map.virq;
+ msi = irq_map.index;
+ }
+
+ gic = kzalloc(sizeof(*gic), GFP_KERNEL);
+ if (!gic) {
+ if (irq_map.virq)
+ pci_msix_free_irq(dev, irq_map);
+ goto out;
+ }
+
+ gic->handler = mana_gd_process_eq_events;
+ gic->msi = msi;
+ gic->irq = irq;
+ INIT_LIST_HEAD(&gic->eq_list);
+ spin_lock_init(&gic->lock);
+
+ if (!gic->msi)
+ snprintf(gic->name, MANA_IRQ_NAME_SZ, "mana_hwc@pci:%s",
+ pci_name(dev));
+ else
+ snprintf(gic->name, MANA_IRQ_NAME_SZ, "mana_msi%d@pci:%s",
+ gic->msi, pci_name(dev));
+
+ err = request_irq(irq, mana_gd_intr, 0, gic->name, gic);
+ if (err) {
+ dev_err(gc->dev, "Failed to request irq %d %s\n",
+ irq, gic->name);
+ kfree(gic);
+ gic = NULL;
+ if (irq_map.virq)
+ pci_msix_free_irq(dev, irq_map);
+ goto out;
+ }
+
+ refcount_set(&gic->refcount, 1);
+ gic->bitmap_refs = use_msi_bitmap ? 1 : 0;
+
+ err = xa_err(xa_store(&gc->irq_contexts, msi, gic, GFP_KERNEL));
+ if (err) {
+ dev_err(gc->dev, "Failed to store irq context for msi %d: %d\n",
+ msi, err);
+ free_irq(irq, gic);
+ kfree(gic);
+ gic = NULL;
+ if (irq_map.virq)
+ pci_msix_free_irq(dev, irq_map);
+ goto out;
+ }
+
+ if (use_msi_bitmap)
+ set_bit(msi, gc->msi_bitmap);
+
+out:
+ mutex_unlock(&gc->gic_mutex);
+ return gic;
+}
+EXPORT_SYMBOL_NS(mana_gd_get_gic, "NET_MANA");
+
int mana_gd_alloc_res_map(u32 res_avail, struct gdma_resource *r)
{
r->map = bitmap_zalloc(res_avail, GFP_KERNEL);
@@ -2044,6 +2201,7 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
goto release_region;
mutex_init(&gc->eq_test_event_mutex);
+ mutex_init(&gc->gic_mutex);
pci_set_drvdata(pdev, gc);
gc->bar0_pa = pci_resource_start(pdev, 0);
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index b744253b44e8..1a7f4abe7a8b 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -388,6 +388,10 @@ struct gdma_irq_context {
spinlock_t lock;
struct list_head eq_list;
char name[MANA_IRQ_NAME_SZ];
+ unsigned int msi;
+ unsigned int irq;
+ refcount_t refcount;
+ unsigned int bitmap_refs;
};
enum gdma_context_flags {
@@ -447,6 +451,9 @@ struct gdma_context {
unsigned long flags;
+ /* Protect access to GIC context */
+ struct mutex gic_mutex;
+
/* Indicate if this device is sharing MSI for EQs on MANA */
bool msi_sharing;
@@ -1019,6 +1026,9 @@ int mana_gd_resume(struct pci_dev *pdev);
bool mana_need_log(struct gdma_context *gc, int err);
+struct gdma_irq_context *mana_gd_get_gic(struct gdma_context *gc, bool use_msi_bitmap,
+ int *msi_requested);
+void mana_gd_put_gic(struct gdma_context *gc, bool use_msi_bitmap, int msi);
int mana_gd_query_device_cfg(struct gdma_context *gc, u32 proto_major_ver,
u32 proto_minor_ver, u32 proto_micro_ver,
u16 *max_num_vports, u8 *bm_hostmode);
--
2.43.0
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH net-next v3 4/6] net: mana: Use GIC functions to allocate global EQs
2026-03-06 21:32 [PATCH net-next v3 0/6] net: mana: Per-vPort EQ and MSI-X interrupt management Long Li
` (2 preceding siblings ...)
2026-03-06 21:32 ` [PATCH net-next v3 3/6] net: mana: Introduce GIC context with refcounting for interrupt management Long Li
@ 2026-03-06 21:33 ` Long Li
2026-03-10 14:29 ` [net-next,v3,4/6] " Paolo Abeni
2026-03-06 21:33 ` [PATCH net-next v3 5/6] net: mana: Allocate interrupt context for each EQ when creating vPort Long Li
2026-03-06 21:33 ` [PATCH net-next v3 6/6] RDMA/mana_ib: Allocate interrupt contexts on EQs Long Li
5 siblings, 1 reply; 9+ messages in thread
From: Long Li @ 2026-03-06 21:33 UTC (permalink / raw)
To: K . Y . Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui,
David S . Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Shradha Gupta, Simon Horman, Konstantin Taranov,
Souradeep Chakrabarti, Erick Archer, linux-hyperv, netdev,
linux-kernel, linux-rdma
Cc: Long Li
Replace the GDMA global interrupt setup code with the new GIC allocation
and release functions for managing interrupt contexts.
Signed-off-by: Long Li <longli@microsoft.com>
---
.../net/ethernet/microsoft/mana/gdma_main.c | 83 +++----------------
1 file changed, 10 insertions(+), 73 deletions(-)
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index c43fd8089e77..bdc9dc437fb7 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -1831,30 +1831,13 @@ static int mana_gd_setup_dyn_irqs(struct pci_dev *pdev, int nvec)
* further used in irq_setup()
*/
for (i = 1; i <= nvec; i++) {
- gic = kzalloc_obj(*gic);
+ gic = mana_gd_get_gic(gc, false, &i);
if (!gic) {
err = -ENOMEM;
goto free_irq;
}
- gic->handler = mana_gd_process_eq_events;
- INIT_LIST_HEAD(&gic->eq_list);
- spin_lock_init(&gic->lock);
-
- snprintf(gic->name, MANA_IRQ_NAME_SZ, "mana_q%d@pci:%s",
- i - 1, pci_name(pdev));
-
- /* one pci vector is already allocated for HWC */
- irqs[i - 1] = pci_irq_vector(pdev, i);
- if (irqs[i - 1] < 0) {
- err = irqs[i - 1];
- goto free_current_gic;
- }
-
- err = request_irq(irqs[i - 1], mana_gd_intr, 0, gic->name, gic);
- if (err)
- goto free_current_gic;
- xa_store(&gc->irq_contexts, i, gic, GFP_KERNEL);
+ irqs[i - 1] = gic->irq;
}
/*
@@ -1876,19 +1859,11 @@ static int mana_gd_setup_dyn_irqs(struct pci_dev *pdev, int nvec)
kfree(irqs);
return 0;
-free_current_gic:
- kfree(gic);
free_irq:
for (i -= 1; i > 0; i--) {
irq = pci_irq_vector(pdev, i);
- gic = xa_load(&gc->irq_contexts, i);
- if (WARN_ON(!gic))
- continue;
-
irq_update_affinity_hint(irq, NULL);
- free_irq(irq, gic);
- xa_erase(&gc->irq_contexts, i);
- kfree(gic);
+ mana_gd_put_gic(gc, false, i);
}
kfree(irqs);
return err;
@@ -1909,34 +1884,13 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev, int nvec)
start_irqs = irqs;
for (i = 0; i < nvec; i++) {
- gic = kzalloc_obj(*gic);
+ gic = mana_gd_get_gic(gc, false, &i);
if (!gic) {
err = -ENOMEM;
goto free_irq;
}
- gic->handler = mana_gd_process_eq_events;
- INIT_LIST_HEAD(&gic->eq_list);
- spin_lock_init(&gic->lock);
-
- if (!i)
- snprintf(gic->name, MANA_IRQ_NAME_SZ, "mana_hwc@pci:%s",
- pci_name(pdev));
- else
- snprintf(gic->name, MANA_IRQ_NAME_SZ, "mana_q%d@pci:%s",
- i - 1, pci_name(pdev));
-
- irqs[i] = pci_irq_vector(pdev, i);
- if (irqs[i] < 0) {
- err = irqs[i];
- goto free_current_gic;
- }
-
- err = request_irq(irqs[i], mana_gd_intr, 0, gic->name, gic);
- if (err)
- goto free_current_gic;
-
- xa_store(&gc->irq_contexts, i, gic, GFP_KERNEL);
+ irqs[i] = gic->irq;
}
/* If number of IRQ is one extra than number of online CPUs,
@@ -1965,19 +1919,11 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev, int nvec)
kfree(start_irqs);
return 0;
-free_current_gic:
- kfree(gic);
free_irq:
for (i -= 1; i >= 0; i--) {
irq = pci_irq_vector(pdev, i);
- gic = xa_load(&gc->irq_contexts, i);
- if (WARN_ON(!gic))
- continue;
-
irq_update_affinity_hint(irq, NULL);
- free_irq(irq, gic);
- xa_erase(&gc->irq_contexts, i);
- kfree(gic);
+ mana_gd_put_gic(gc, false, i);
}
kfree(start_irqs);
@@ -2052,26 +1998,17 @@ static int mana_gd_setup_remaining_irqs(struct pci_dev *pdev)
static void mana_gd_remove_irqs(struct pci_dev *pdev)
{
struct gdma_context *gc = pci_get_drvdata(pdev);
- struct gdma_irq_context *gic;
int irq, i;
if (gc->max_num_msix < 1)
return;
- for (i = 0; i < gc->max_num_msix; i++) {
- irq = pci_irq_vector(pdev, i);
- if (irq < 0)
- continue;
-
- gic = xa_load(&gc->irq_contexts, i);
- if (WARN_ON(!gic))
- continue;
-
+ for (i = 0; i < (gc->msi_sharing ? gc->max_num_msix : 1); i++) {
/* Need to clear the hint before free_irq */
+ irq = pci_irq_vector(pdev, i);
irq_update_affinity_hint(irq, NULL);
- free_irq(irq, gic);
- xa_erase(&gc->irq_contexts, i);
- kfree(gic);
+
+ mana_gd_put_gic(gc, false, i);
}
pci_free_irq_vectors(pdev);
--
2.43.0
^ permalink raw reply related [flat|nested] 9+ messages in thread* Re: [net-next,v3,4/6] net: mana: Use GIC functions to allocate global EQs
2026-03-06 21:33 ` [PATCH net-next v3 4/6] net: mana: Use GIC functions to allocate global EQs Long Li
@ 2026-03-10 14:29 ` Paolo Abeni
2026-03-10 19:03 ` [EXTERNAL] " Long Li
0 siblings, 1 reply; 9+ messages in thread
From: Paolo Abeni @ 2026-03-10 14:29 UTC (permalink / raw)
To: longli
Cc: kotaranov, erick.archer, wei.liu, linux-hyperv, pabeni,
shradhagupta, haiyangz, kys, horms, linux-kernel, decui,
schakrabarti, kuba, davem, edumazet, netdev, linux-rdma
This is an AI-generated review of your patch. The human sending this
email has considered the AI review valid, or at least plausible.
For local reproduction steps see https://netdev-ai.bots.linux.dev/ai-local.html
---
net: mana: Use GIC functions to allocate global EQs
Replace the GDMA global interrupt setup code with the new GIC allocation
and release functions for managing interrupt contexts.
> diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
> index c43fd8089e77..bdc9dc437fb7 100644
> --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
> +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
[ ... ]
> @@ -2052,26 +1998,17 @@ static int mana_gd_setup_remaining_irqs(struct pci_dev *pdev)
> static void mana_gd_remove_irqs(struct pci_dev *pdev)
> {
> struct gdma_context *gc = pci_get_drvdata(pdev);
> - struct gdma_irq_context *gic;
> int irq, i;
>
> if (gc->max_num_msix < 1)
> return;
>
> - for (i = 0; i < gc->max_num_msix; i++) {
> - irq = pci_irq_vector(pdev, i);
> - if (irq < 0)
> - continue;
> -
> - gic = xa_load(&gc->irq_contexts, i);
> - if (WARN_ON(!gic))
> - continue;
> -
> + for (i = 0; i < (gc->msi_sharing ? gc->max_num_msix : 1); i++) {
^^^
Does this loop condition leak GIC references when msi_sharing is false?
When msi_sharing is false, the loop only releases the GIC at index 0.
However, mana_gd_setup_dyn_irqs allocates GICs at indices 1 through nvec:
drivers/net/ethernet/microsoft/mana/gdma_main.c:mana_gd_setup_dyn_irqs() {
for (i = 1; i <= nvec; i++) {
gic = mana_gd_get_gic(gc, false, &i);
...
}
}
Each mana_gd_get_gic call initializes the GIC with refcount=1. These GICs
at indices 1..nvec are never released because mana_gd_remove_irqs only
processes index 0 when msi_sharing is false.
The old code iterated over all gc->max_num_msix entries unconditionally:
for (i = 0; i < gc->max_num_msix; i++) {
...
gic = xa_load(&gc->irq_contexts, i);
...
free_irq(irq, gic);
xa_erase(&gc->irq_contexts, i);
kfree(gic);
}
This ensured every allocated GIC was freed. The new code with the
conditional loop breaks this, resulting in:
1. Leaked IRQ handlers - request_irq without matching free_irq for indices
1..nvec
2. Leaked gdma_irq_context memory - the GIC structures are never freed
3. Leaked xarray entries - the entries remain in gc->irq_contexts
Additionally, pci_free_irq_vectors is called immediately after the loop,
which attempts to tear down MSI-X vectors while IRQ handlers at indices
1..nvec are still registered. Can this trigger warnings or use-after-free
if an interrupt fires during teardown?
The next commit in the series (4475f13983ab "net: mana: Allocate interrupt
context for each EQ when creating vPort") adds per-EQ get/put of GICs,
but the EQ teardown only drops the EQ's reference (refcount goes from 2 to
1). The base reference from mana_gd_setup_dyn_irqs remains unreleased.
> /* Need to clear the hint before free_irq */
> + irq = pci_irq_vector(pdev, i);
> irq_update_affinity_hint(irq, NULL);
> - free_irq(irq, gic);
> - xa_erase(&gc->irq_contexts, i);
> - kfree(gic);
> +
> + mana_gd_put_gic(gc, false, i);
> }
>
> pci_free_irq_vectors(pdev);
^ permalink raw reply [flat|nested] 9+ messages in thread* RE: [EXTERNAL] Re: [net-next,v3,4/6] net: mana: Use GIC functions to allocate global EQs
2026-03-10 14:29 ` [net-next,v3,4/6] " Paolo Abeni
@ 2026-03-10 19:03 ` Long Li
0 siblings, 0 replies; 9+ messages in thread
From: Long Li @ 2026-03-10 19:03 UTC (permalink / raw)
To: Paolo Abeni
Cc: Konstantin Taranov, erick.archer@outlook.com, wei.liu@kernel.org,
linux-hyperv@vger.kernel.org, shradhagupta@linux.microsoft.com,
Haiyang Zhang, KY Srinivasan, horms@kernel.org,
linux-kernel@vger.kernel.org, Dexuan Cui,
schakrabarti@linux.microsoft.com, kuba@kernel.org,
davem@davemloft.net, edumazet@google.com, netdev@vger.kernel.org,
linux-rdma@vger.kernel.org
> Subject: [EXTERNAL] Re: [net-next,v3,4/6] net: mana: Use GIC functions to
> allocate global EQs
>
> This is an AI-generated review of your patch. The human sending this email has
> considered the AI review valid, or at least plausible.
>
> For local reproduction steps see
> https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fnetdev-
> ai.bots.linux.dev%2Fai-
> local.html&data=05%7C02%7Clongli%40microsoft.com%7Cb43e1b10bd564c760
> a4d08de7eb17c82%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C6390
> 87497958656662%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWU
> sIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%
> 7C0%7C%7C%7C&sdata=r63AcJ7Cd3APZSSpl4SPBcGxSdosinxkIurfTp9yZmc%3D&
> reserved=0
> ---
> net: mana: Use GIC functions to allocate global EQs
>
> Replace the GDMA global interrupt setup code with the new GIC allocation and
> release functions for managing interrupt contexts.
>
> > diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c
> > b/drivers/net/ethernet/microsoft/mana/gdma_main.c
> > index c43fd8089e77..bdc9dc437fb7 100644
> > --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
> > +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
>
> [ ... ]
>
> > @@ -2052,26 +1998,17 @@ static int mana_gd_setup_remaining_irqs(struct
> > pci_dev *pdev) static void mana_gd_remove_irqs(struct pci_dev *pdev)
> > {
> > struct gdma_context *gc = pci_get_drvdata(pdev);
> > - struct gdma_irq_context *gic;
> > int irq, i;
> >
> > if (gc->max_num_msix < 1)
> > return;
> >
> > - for (i = 0; i < gc->max_num_msix; i++) {
> > - irq = pci_irq_vector(pdev, i);
> > - if (irq < 0)
> > - continue;
> > -
> > - gic = xa_load(&gc->irq_contexts, i);
> > - if (WARN_ON(!gic))
> > - continue;
> > -
> > + for (i = 0; i < (gc->msi_sharing ? gc->max_num_msix : 1); i++) {
> ^^^ Does this loop condition leak GIC
> references when msi_sharing is false?
>
> When msi_sharing is false, the loop only releases the GIC at index 0.
> However, mana_gd_setup_dyn_irqs allocates GICs at indices 1 through nvec:
>
> drivers/net/ethernet/microsoft/mana/gdma_main.c:mana_gd_setup_dyn_irqs()
> {
> for (i = 1; i <= nvec; i++) {
> gic = mana_gd_get_gic(gc, false, &i);
> ...
> }
> }
>
> Each mana_gd_get_gic call initializes the GIC with refcount=1. These GICs at
> indices 1..nvec are never released because mana_gd_remove_irqs only processes
> index 0 when msi_sharing is false.
>
> The old code iterated over all gc->max_num_msix entries unconditionally:
>
> for (i = 0; i < gc->max_num_msix; i++) {
> ...
> gic = xa_load(&gc->irq_contexts, i);
> ...
> free_irq(irq, gic);
> xa_erase(&gc->irq_contexts, i);
> kfree(gic);
> }
>
> This ensured every allocated GIC was freed. The new code with the conditional
> loop breaks this, resulting in:
>
> 1. Leaked IRQ handlers - request_irq without matching free_irq for indices
> 1..nvec
> 2. Leaked gdma_irq_context memory - the GIC structures are never freed 3.
> Leaked xarray entries - the entries remain in gc->irq_contexts
>
> Additionally, pci_free_irq_vectors is called immediately after the loop, which
> attempts to tear down MSI-X vectors while IRQ handlers at indices 1..nvec are
> still registered. Can this trigger warnings or use-after-free if an interrupt fires
> during teardown?
>
> The next commit in the series (4475f13983ab "net: mana: Allocate interrupt
> context for each EQ when creating vPort") adds per-EQ get/put of GICs, but the
> EQ teardown only drops the EQ's reference (refcount goes from 2 to 1). The base
> reference from mana_gd_setup_dyn_irqs remains unreleased.
Thank you, I'm sending v4 to fix this.
Long
^ permalink raw reply [flat|nested] 9+ messages in thread
* [PATCH net-next v3 5/6] net: mana: Allocate interrupt context for each EQ when creating vPort
2026-03-06 21:32 [PATCH net-next v3 0/6] net: mana: Per-vPort EQ and MSI-X interrupt management Long Li
` (3 preceding siblings ...)
2026-03-06 21:33 ` [PATCH net-next v3 4/6] net: mana: Use GIC functions to allocate global EQs Long Li
@ 2026-03-06 21:33 ` Long Li
2026-03-06 21:33 ` [PATCH net-next v3 6/6] RDMA/mana_ib: Allocate interrupt contexts on EQs Long Li
5 siblings, 0 replies; 9+ messages in thread
From: Long Li @ 2026-03-06 21:33 UTC (permalink / raw)
To: K . Y . Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui,
David S . Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Shradha Gupta, Simon Horman, Konstantin Taranov,
Souradeep Chakrabarti, Erick Archer, linux-hyperv, netdev,
linux-kernel, linux-rdma
Cc: Long Li
Use GIC functions to create a dedicated interrupt context or acquire a
shared interrupt context for each EQ when setting up a vPort.
Signed-off-by: Long Li <longli@microsoft.com>
---
drivers/net/ethernet/microsoft/mana/gdma_main.c | 2 +-
drivers/net/ethernet/microsoft/mana/mana_en.c | 17 ++++++++++++++++-
include/net/mana/gdma.h | 1 +
3 files changed, 18 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index bdc9dc437fb7..81c0be96c94b 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -809,7 +809,6 @@ static void mana_gd_deregister_irq(struct gdma_queue *queue)
}
spin_unlock_irqrestore(&gic->lock, flags);
- queue->eq.msix_index = INVALID_PCI_MSIX_INDEX;
synchronize_rcu();
}
@@ -924,6 +923,7 @@ static int mana_gd_create_eq(struct gdma_dev *gd,
out:
dev_err(dev, "Failed to create EQ: %d\n", err);
mana_gd_destroy_eq(gc, false, queue);
+ queue->eq.msix_index = INVALID_PCI_MSIX_INDEX;
return err;
}
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index bfa0f354355d..8a60e7567951 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -1598,6 +1598,7 @@ void mana_destroy_eq(struct mana_port_context *apc)
struct gdma_context *gc = ac->gdma_dev->gdma_context;
struct gdma_queue *eq;
int i;
+ unsigned int msi;
if (!apc->eqs)
return;
@@ -1610,7 +1611,9 @@ void mana_destroy_eq(struct mana_port_context *apc)
if (!eq)
continue;
+ msi = eq->eq.msix_index;
mana_gd_destroy_queue(gc, eq);
+ mana_gd_put_gic(gc, !gc->msi_sharing, msi);
}
kfree(apc->eqs);
@@ -1627,6 +1630,7 @@ static void mana_create_eq_debugfs(struct mana_port_context *apc, int i)
eq.mana_eq_debugfs = debugfs_create_dir(eqnum, apc->mana_eqs_debugfs);
debugfs_create_u32("head", 0400, eq.mana_eq_debugfs, &eq.eq->head);
debugfs_create_u32("tail", 0400, eq.mana_eq_debugfs, &eq.eq->tail);
+ debugfs_create_u32("irq", 0400, eq.mana_eq_debugfs, &eq.eq->eq.irq);
debugfs_create_file("eq_dump", 0400, eq.mana_eq_debugfs, eq.eq, &mana_dbg_q_fops);
}
@@ -1637,6 +1641,7 @@ int mana_create_eq(struct mana_port_context *apc)
struct gdma_queue_spec spec = {};
int err;
int i;
+ struct gdma_irq_context *gic;
WARN_ON(apc->eqs);
apc->eqs = kzalloc_objs(struct mana_eq, apc->num_queues);
@@ -1653,12 +1658,22 @@ int mana_create_eq(struct mana_port_context *apc)
apc->mana_eqs_debugfs = debugfs_create_dir("EQs", apc->mana_port_debugfs);
for (i = 0; i < apc->num_queues; i++) {
- spec.eq.msix_index = (i + 1) % gc->num_msix_usable;
+ if (gc->msi_sharing)
+ spec.eq.msix_index = (i + 1) % gc->num_msix_usable;
+
+ gic = mana_gd_get_gic(gc, !gc->msi_sharing, &spec.eq.msix_index);
+ if (!gic) {
+ err = -ENOMEM;
+ goto out;
+ }
+
err = mana_gd_create_mana_eq(gd, &spec, &apc->eqs[i].eq);
if (err) {
dev_err(gc->dev, "Failed to create EQ %d : %d\n", i, err);
+ mana_gd_put_gic(gc, !gc->msi_sharing, spec.eq.msix_index);
goto out;
}
+ apc->eqs[i].eq->eq.irq = gic->irq;
mana_create_eq_debugfs(apc, i);
}
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index 1a7f4abe7a8b..4e0278b00bbb 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -342,6 +342,7 @@ struct gdma_queue {
void *context;
unsigned int msix_index;
+ unsigned int irq;
u32 log2_throttle_limit;
} eq;
--
2.43.0
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH net-next v3 6/6] RDMA/mana_ib: Allocate interrupt contexts on EQs
2026-03-06 21:32 [PATCH net-next v3 0/6] net: mana: Per-vPort EQ and MSI-X interrupt management Long Li
` (4 preceding siblings ...)
2026-03-06 21:33 ` [PATCH net-next v3 5/6] net: mana: Allocate interrupt context for each EQ when creating vPort Long Li
@ 2026-03-06 21:33 ` Long Li
5 siblings, 0 replies; 9+ messages in thread
From: Long Li @ 2026-03-06 21:33 UTC (permalink / raw)
To: K . Y . Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui,
David S . Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Shradha Gupta, Simon Horman, Konstantin Taranov,
Souradeep Chakrabarti, Erick Archer, linux-hyperv, netdev,
linux-kernel, linux-rdma
Cc: Long Li
Use the GIC functions to allocate interrupt contexts for RDMA EQs. These
interrupt contexts may be shared with Ethernet EQs when MSI-X vectors
are limited.
The driver now supports allocating dedicated MSI-X for each EQ. Indicate
this capability through driver capability bits.
Signed-off-by: Long Li <longli@microsoft.com>
---
drivers/infiniband/hw/mana/main.c | 33 ++++++++++++++++++++++++++-----
include/net/mana/gdma.h | 7 +++++--
2 files changed, 33 insertions(+), 7 deletions(-)
diff --git a/drivers/infiniband/hw/mana/main.c b/drivers/infiniband/hw/mana/main.c
index d51dd0ee85f4..0b74dd093b41 100644
--- a/drivers/infiniband/hw/mana/main.c
+++ b/drivers/infiniband/hw/mana/main.c
@@ -787,6 +787,7 @@ int mana_ib_create_eqs(struct mana_ib_dev *mdev)
{
struct gdma_context *gc = mdev_to_gc(mdev);
struct gdma_queue_spec spec = {};
+ struct gdma_irq_context *gic;
int err, i;
spec.type = GDMA_EQ;
@@ -797,9 +798,15 @@ int mana_ib_create_eqs(struct mana_ib_dev *mdev)
spec.eq.log2_throttle_limit = LOG2_EQ_THROTTLE;
spec.eq.msix_index = 0;
+ gic = mana_gd_get_gic(gc, false, &spec.eq.msix_index);
+ if (!gic)
+ return -ENOMEM;
+
err = mana_gd_create_mana_eq(mdev->gdma_dev, &spec, &mdev->fatal_err_eq);
- if (err)
+ if (err) {
+ mana_gd_put_gic(gc, false, 0);
return err;
+ }
mdev->eqs = kzalloc_objs(struct gdma_queue *,
mdev->ib_dev.num_comp_vectors);
@@ -810,31 +817,47 @@ int mana_ib_create_eqs(struct mana_ib_dev *mdev)
spec.eq.callback = NULL;
for (i = 0; i < mdev->ib_dev.num_comp_vectors; i++) {
spec.eq.msix_index = (i + 1) % gc->num_msix_usable;
+
+ gic = mana_gd_get_gic(gc, false, &spec.eq.msix_index);
+ if (!gic) {
+ err = -ENOMEM;
+ goto destroy_eqs;
+ }
+
err = mana_gd_create_mana_eq(mdev->gdma_dev, &spec, &mdev->eqs[i]);
- if (err)
+ if (err) {
+ mana_gd_put_gic(gc, false, spec.eq.msix_index);
goto destroy_eqs;
+ }
}
return 0;
destroy_eqs:
- while (i-- > 0)
+ while (i-- > 0) {
mana_gd_destroy_queue(gc, mdev->eqs[i]);
+ mana_gd_put_gic(gc, false, (i + 1) % gc->num_msix_usable);
+ }
kfree(mdev->eqs);
destroy_fatal_eq:
mana_gd_destroy_queue(gc, mdev->fatal_err_eq);
+ mana_gd_put_gic(gc, false, 0);
return err;
}
void mana_ib_destroy_eqs(struct mana_ib_dev *mdev)
{
struct gdma_context *gc = mdev_to_gc(mdev);
- int i;
+ int i, msi;
mana_gd_destroy_queue(gc, mdev->fatal_err_eq);
+ mana_gd_put_gic(gc, false, 0);
- for (i = 0; i < mdev->ib_dev.num_comp_vectors; i++)
+ for (i = 0; i < mdev->ib_dev.num_comp_vectors; i++) {
mana_gd_destroy_queue(gc, mdev->eqs[i]);
+ msi = (i + 1) % gc->num_msix_usable;
+ mana_gd_put_gic(gc, false, msi);
+ }
kfree(mdev->eqs);
}
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index 4e0278b00bbb..662e58f51e87 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -612,6 +612,7 @@ enum {
#define GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG BIT(3)
#define GDMA_DRV_CAP_FLAG_1_GDMA_PAGES_4MB_1GB_2GB BIT(4)
#define GDMA_DRV_CAP_FLAG_1_VARIABLE_INDIRECTION_TABLE_SUPPORT BIT(5)
+#define GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE BIT(6)
/* Driver can handle holes (zeros) in the device list */
#define GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP BIT(11)
@@ -628,7 +629,8 @@ enum {
/* Driver detects stalled send queues and recovers them */
#define GDMA_DRV_CAP_FLAG_1_HANDLE_STALL_SQ_RECOVERY BIT(18)
-#define GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE BIT(6)
+/* Driver supports separate EQ/MSIs for each vPort */
+#define GDMA_DRV_CAP_FLAG_1_EQ_MSI_UNSHARE_MULTI_VPORT BIT(19)
/* Driver supports linearizing the skb when num_sge exceeds hardware limit */
#define GDMA_DRV_CAP_FLAG_1_SKB_LINEARIZE BIT(20)
@@ -656,7 +658,8 @@ enum {
GDMA_DRV_CAP_FLAG_1_SKB_LINEARIZE | \
GDMA_DRV_CAP_FLAG_1_PROBE_RECOVERY | \
GDMA_DRV_CAP_FLAG_1_HANDLE_STALL_SQ_RECOVERY | \
- GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECOVERY)
+ GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECOVERY | \
+ GDMA_DRV_CAP_FLAG_1_EQ_MSI_UNSHARE_MULTI_VPORT)
#define GDMA_DRV_CAP_FLAGS2 0
--
2.43.0
^ permalink raw reply related [flat|nested] 9+ messages in thread