* [PATCH net-next 0/4] Support bandwidth clamping in mana using net shapers
From: Erni Sri Satya Vennela @ 2025-06-11 8:46 UTC (permalink / raw)
To: kys, haiyangz, wei.liu, decui, andrew+netdev, davem, edumazet,
kuba, pabeni, kotaranov, longli, horms, shirazsaleem, leon, ernis,
shradhagupta, schakrabarti, rosenp, sdf, linux-hyperv, netdev,
linux-kernel, linux-rdma
This patchset introduces hardware-backed bandwidth rate limiting
for MANA NICs via the net_shaper_ops interface, enabling efficient and
fine-grained traffic shaping directly on the device.
Previously, MANA lacked a mechanism for user-configurable bandwidth
control. With this addition, users can now configure shaping parameters,
allowing better traffic management and performance isolation.
The implementation includes the net_shaper_ops callbacks in the MANA
driver and supports one shaper per vport. Add shaping support via
mana_set_bw_clamp(), allowing the configuration of bandwidth rates
in 100 Mbps increments (minimum 100 Mbps). The driver validates input
and rejects unsupported values. On failure, it restores the previous
configuration which is queried using mana_query_link_cfg() or
retains the current state.
To prevent potential deadlocks introduced by net_shaper_ops, switch to
_locked variants of NAPI APIs when netdevops_lock is held during
VF setup and teardown.
Also, Add support for ethtool get_link_ksettings to report the maximum
link speed supported by the SKU in mbps.
These APIs when invoked on hardware that are older or that do
not support these APIs, the speed would be reported as UNKNOWN and
the net-shaper calls to set speed would fail.
Erni Sri Satya Vennela (4):
net: mana: Fix potential deadlocks in mana napi ops
net: mana: Add support for net_shaper_ops
net: mana: Add speed support in mana_get_link_ksettings
net: mana: Handle unsupported HWC commands
.../net/ethernet/microsoft/mana/hw_channel.c | 4 +
drivers/net/ethernet/microsoft/mana/mana_en.c | 206 +++++++++++++++++-
.../ethernet/microsoft/mana/mana_ethtool.c | 6 +
include/net/mana/mana.h | 42 ++++
4 files changed, 249 insertions(+), 9 deletions(-)
--
2.34.1
^ permalink raw reply
* [PATCH net-next 1/4] net: mana: Fix potential deadlocks in mana napi ops
From: Erni Sri Satya Vennela @ 2025-06-11 8:46 UTC (permalink / raw)
To: kys, haiyangz, wei.liu, decui, andrew+netdev, davem, edumazet,
kuba, pabeni, kotaranov, longli, horms, shirazsaleem, leon, ernis,
shradhagupta, schakrabarti, rosenp, sdf, linux-hyperv, netdev,
linux-kernel, linux-rdma
In-Reply-To: <1749631576-2517-1-git-send-email-ernis@linux.microsoft.com>
When net_shaper_ops are enabled for MANA, netdev_ops_lock
becomes active.
The netvsc sets up MANA VF via following call chain:
netvsc_vf_setup()
dev_change_flags()
...
__dev_open() OR __dev_close()
dev_change_flags() holds the netdev mutex via netdev_lock_ops.
During this process, mana_create_txq() and mana_create_rxq()
invoke netif_napi_add_tx(), netif_napi_add_weight(), and napi_enable(),
all of which attempt to acquire the same lock,
leading to a potential deadlock.
Similarly, mana_destroy_txq() and mana_destroy_rxq() call
netif_napi_disable() and netif_napi_del(), which also contend
for the same lock.
Switch to the _locked variants of these APIs to avoid deadlocks
when the netdev_ops_lock is held.
Fixes: d4c22ec680c8 ("net: hold netdev instance lock during ndo_open/ndo_stop")
Signed-off-by: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
---
drivers/net/ethernet/microsoft/mana/mana_en.c | 39 ++++++++++++++-----
1 file changed, 30 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index ccd2885c939e..3c879d8a39e3 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -1911,8 +1911,13 @@ static void mana_destroy_txq(struct mana_port_context *apc)
napi = &apc->tx_qp[i].tx_cq.napi;
if (apc->tx_qp[i].txq.napi_initialized) {
napi_synchronize(napi);
- napi_disable(napi);
- netif_napi_del(napi);
+ if (netdev_need_ops_lock(napi->dev)) {
+ napi_disable_locked(napi);
+ netif_napi_del_locked(napi);
+ } else {
+ napi_disable(napi);
+ netif_napi_del(napi);
+ }
apc->tx_qp[i].txq.napi_initialized = false;
}
mana_destroy_wq_obj(apc, GDMA_SQ, apc->tx_qp[i].tx_object);
@@ -2064,8 +2069,14 @@ static int mana_create_txq(struct mana_port_context *apc,
mana_create_txq_debugfs(apc, i);
- netif_napi_add_tx(net, &cq->napi, mana_poll);
- napi_enable(&cq->napi);
+ if (netdev_need_ops_lock(net)) {
+ set_bit(NAPI_STATE_NO_BUSY_POLL, &cq->napi.state);
+ netif_napi_add_locked(net, &cq->napi, mana_poll);
+ napi_enable_locked(&cq->napi);
+ } else {
+ netif_napi_add_tx(net, &cq->napi, mana_poll);
+ napi_enable(&cq->napi);
+ }
txq->napi_initialized = true;
mana_gd_ring_cq(cq->gdma_cq, SET_ARM_BIT);
@@ -2101,9 +2112,13 @@ static void mana_destroy_rxq(struct mana_port_context *apc,
if (napi_initialized) {
napi_synchronize(napi);
- napi_disable(napi);
-
- netif_napi_del(napi);
+ if (netdev_need_ops_lock(napi->dev)) {
+ napi_disable_locked(napi);
+ netif_napi_del_locked(napi);
+ } else {
+ napi_disable(napi);
+ netif_napi_del(napi);
+ }
}
xdp_rxq_info_unreg(&rxq->xdp_rxq);
@@ -2354,14 +2369,20 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc,
gc->cq_table[cq->gdma_id] = cq->gdma_cq;
- netif_napi_add_weight(ndev, &cq->napi, mana_poll, 1);
+ if (netdev_need_ops_lock(ndev))
+ netif_napi_add_weight_locked(ndev, &cq->napi, mana_poll, 1);
+ else
+ netif_napi_add_weight(ndev, &cq->napi, mana_poll, 1);
WARN_ON(xdp_rxq_info_reg(&rxq->xdp_rxq, ndev, rxq_idx,
cq->napi.napi_id));
WARN_ON(xdp_rxq_info_reg_mem_model(&rxq->xdp_rxq, MEM_TYPE_PAGE_POOL,
rxq->page_pool));
- napi_enable(&cq->napi);
+ if (netdev_need_ops_lock(ndev))
+ napi_enable_locked(&cq->napi);
+ else
+ napi_enable(&cq->napi);
mana_gd_ring_cq(cq->gdma_cq, SET_ARM_BIT);
out:
--
2.34.1
^ permalink raw reply related
* [PATCH net-next 2/4] net: mana: Add support for net_shaper_ops
From: Erni Sri Satya Vennela @ 2025-06-11 8:46 UTC (permalink / raw)
To: kys, haiyangz, wei.liu, decui, andrew+netdev, davem, edumazet,
kuba, pabeni, kotaranov, longli, horms, shirazsaleem, leon, ernis,
shradhagupta, schakrabarti, rosenp, sdf, linux-hyperv, netdev,
linux-kernel, linux-rdma
In-Reply-To: <1749631576-2517-1-git-send-email-ernis@linux.microsoft.com>
Introduce support for net_shaper_ops in the MANA driver,
enabling configuration of rate limiting on the MANA NIC.
To apply rate limiting, the driver issues a HWC command via
mana_set_bw_clamp() and updates the corresponding shaper object
in the net_shaper cache. If an error occurs during this process,
the driver restores the previous speed by querying the current link
configuration using mana_query_link_cfg().
The minimum supported bandwidth is 100 Mbps, and only values that are
exact multiples of 100 Mbps are allowed. Any other values are rejected.
To remove a shaper, the driver resets the bandwidth to the maximum
supported by the SKU using mana_set_bw_clamp() and clears the
associated cache entry. If an error occurs during this process,
the shaper details are retained.
On the hardware that does not support these APIs, the net-shaper
calls to set speed would fail.
Set the speed:
./tools/net/ynl/pyynl/cli.py \
--spec Documentation/netlink/specs/net_shaper.yaml \
--do set --json '{"ifindex":'$IFINDEX',
"handle":{"scope": "netdev", "id":'$ID' },
"bw-max": 200000000 }'
Get the shaper details:
./tools/net/ynl/pyynl/cli.py \
--spec Documentation/netlink/specs/net_shaper.yaml \
--do get --json '{"ifindex":'$IFINDEX',
"handle":{"scope": "netdev", "id":'$ID' }}'
> {'bw-max': 200000000,
> 'handle': {'scope': 'netdev'},
> 'ifindex': $IFINDEX,
> 'metric': 'bps'}
Delete the shaper object:
./tools/net/ynl/pyynl/cli.py \
--spec Documentation/netlink/specs/net_shaper.yaml \
--do delete --json '{"ifindex":'$IFINDEX',
"handle":{"scope": "netdev","id":'$ID' }}'
Signed-off-by: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
---
drivers/net/ethernet/microsoft/mana/mana_en.c | 155 ++++++++++++++++++
include/net/mana/mana.h | 40 +++++
2 files changed, 195 insertions(+)
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 3c879d8a39e3..b704dbc5e344 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -719,6 +719,78 @@ static int mana_change_mtu(struct net_device *ndev, int new_mtu)
return err;
}
+static int mana_shaper_set(struct net_shaper_binding *binding,
+ const struct net_shaper *shaper,
+ struct netlink_ext_ack *extack)
+{
+ struct mana_port_context *apc = netdev_priv(binding->netdev);
+ u32 old_speed, rate;
+ int err;
+
+ if (shaper->handle.scope != NET_SHAPER_SCOPE_NETDEV) {
+ NL_SET_ERR_MSG_MOD(extack, "net shaper scope should be netdev");
+ return -EINVAL;
+ }
+
+ if (apc->handle.id && shaper->handle.id != apc->handle.id) {
+ NL_SET_ERR_MSG_MOD(extack, "Cannot create multiple shapers");
+ return -EOPNOTSUPP;
+ }
+
+ if (!shaper->bw_max || (shaper->bw_max % 100000000)) {
+ NL_SET_ERR_MSG_MOD(extack, "Please use multiples of 100Mbps for bandwidth");
+ return -EINVAL;
+ }
+
+ rate = div_u64(shaper->bw_max, 1000); /* Convert bps to Kbps */
+ rate = div_u64(rate, 1000); /* Convert Kbps to Mbps */
+
+ /* Get current speed */
+ err = mana_query_link_cfg(apc);
+ old_speed = (err) ? SPEED_UNKNOWN : apc->speed;
+
+ if (!err) {
+ err = mana_set_bw_clamp(apc, rate, TRI_STATE_TRUE);
+ apc->speed = (err) ? old_speed : rate;
+ apc->handle = (err) ? apc->handle : shaper->handle;
+ }
+
+ return err;
+}
+
+static int mana_shaper_del(struct net_shaper_binding *binding,
+ const struct net_shaper_handle *handle,
+ struct netlink_ext_ack *extack)
+{
+ struct mana_port_context *apc = netdev_priv(binding->netdev);
+ int err;
+
+ err = mana_set_bw_clamp(apc, 0, TRI_STATE_FALSE);
+
+ if (!err) {
+ /* Reset mana port context parameters */
+ apc->handle.id = 0;
+ apc->handle.scope = NET_SHAPER_SCOPE_UNSPEC;
+ apc->speed = 0;
+ }
+
+ return err;
+}
+
+static void mana_shaper_cap(struct net_shaper_binding *binding,
+ enum net_shaper_scope scope,
+ unsigned long *flags)
+{
+ *flags = BIT(NET_SHAPER_A_CAPS_SUPPORT_BW_MAX) |
+ BIT(NET_SHAPER_A_CAPS_SUPPORT_METRIC_BPS);
+}
+
+static const struct net_shaper_ops mana_shaper_ops = {
+ .set = mana_shaper_set,
+ .delete = mana_shaper_del,
+ .capabilities = mana_shaper_cap,
+};
+
static const struct net_device_ops mana_devops = {
.ndo_open = mana_open,
.ndo_stop = mana_close,
@@ -729,6 +801,7 @@ static const struct net_device_ops mana_devops = {
.ndo_bpf = mana_bpf,
.ndo_xdp_xmit = mana_xdp_xmit,
.ndo_change_mtu = mana_change_mtu,
+ .net_shaper_ops = &mana_shaper_ops,
};
static void mana_cleanup_port_context(struct mana_port_context *apc)
@@ -1161,6 +1234,86 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc,
return err;
}
+int mana_query_link_cfg(struct mana_port_context *apc)
+{
+ struct net_device *ndev = apc->ndev;
+ struct mana_query_link_config_resp resp = {};
+ struct mana_query_link_config_req req = {};
+ int err;
+
+ mana_gd_init_req_hdr(&req.hdr, MANA_QUERY_LINK_CONFIG,
+ sizeof(req), sizeof(resp));
+
+ req.vport = apc->port_handle;
+ req.hdr.resp.msg_version = GDMA_MESSAGE_V2;
+
+ err = mana_send_request(apc->ac, &req, sizeof(req), &resp,
+ sizeof(resp));
+
+ if (err) {
+ netdev_err(ndev, "Failed to query link config: %d\n", err);
+ return err;
+ }
+
+ err = mana_verify_resp_hdr(&resp.hdr, MANA_QUERY_LINK_CONFIG,
+ sizeof(resp));
+
+ if (err || resp.hdr.status) {
+ netdev_err(ndev, "Failed to query link config: %d, 0x%x\n", err,
+ resp.hdr.status);
+ if (!err)
+ err = -EOPNOTSUPP;
+ return err;
+ }
+
+ if (resp.qos_unconfigured) {
+ err = -EINVAL;
+ return err;
+ }
+ apc->speed = resp.link_speed_mbps;
+ return 0;
+}
+
+int mana_set_bw_clamp(struct mana_port_context *apc, u32 speed,
+ int enable_clamping)
+{
+ struct mana_set_bw_clamp_resp resp = {};
+ struct mana_set_bw_clamp_req req = {};
+ struct net_device *ndev = apc->ndev;
+ int err;
+
+ mana_gd_init_req_hdr(&req.hdr, MANA_SET_BW_CLAMP,
+ sizeof(req), sizeof(resp));
+ req.vport = apc->port_handle;
+ req.link_speed_mbps = speed;
+ req.enable_clamping = enable_clamping;
+
+ err = mana_send_request(apc->ac, &req, sizeof(req), &resp,
+ sizeof(resp));
+
+ if (err) {
+ netdev_err(ndev, "Failed to set bandwidth clamp for speed %u, err = %d",
+ speed, err);
+ return err;
+ }
+
+ err = mana_verify_resp_hdr(&resp.hdr, MANA_SET_BW_CLAMP,
+ sizeof(resp));
+
+ if (err || resp.hdr.status) {
+ netdev_err(ndev, "Failed to set bandwidth clamp: %d, 0x%x\n", err,
+ resp.hdr.status);
+ if (!err)
+ err = -EOPNOTSUPP;
+ return err;
+ }
+
+ if (resp.qos_unconfigured) {
+ netdev_err(ndev, "QoS is unconfigured\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
int mana_create_wq_obj(struct mana_port_context *apc,
mana_handle_t vport,
u32 wq_type, struct mana_obj_spec *wq_spec,
@@ -2939,6 +3092,8 @@ static int mana_probe_port(struct mana_context *ac, int port_idx,
goto free_indir;
}
+ debugfs_create_u32("current_speed", 0400, apc->mana_port_debugfs, &apc->speed);
+
return 0;
free_indir:
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index 9abb66461211..0df84e51d541 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -5,6 +5,7 @@
#define _MANA_H
#include <net/xdp.h>
+#include <net/net_shaper.h>
#include "gdma.h"
#include "hw_channel.h"
@@ -467,7 +468,12 @@ struct mana_port_context {
struct mutex vport_mutex;
int vport_use_count;
+ /* Net shaper handle*/
+ struct net_shaper_handle handle;
+
u16 port_idx;
+ /* Currently configured speed (mbps) */
+ u32 speed;
bool port_is_up;
bool port_st_save; /* Saved port state */
@@ -501,6 +507,9 @@ 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_query_link_cfg(struct mana_port_context *apc);
+int mana_set_bw_clamp(struct mana_port_context *apc, u32 speed,
+ int enable_clamping);
int mana_pre_alloc_rxbufs(struct mana_port_context *apc, int mtu, int num_queues);
void mana_pre_dealloc_rxbufs(struct mana_port_context *apc);
@@ -527,6 +536,8 @@ enum mana_command_code {
MANA_FENCE_RQ = 0x20006,
MANA_CONFIG_VPORT_RX = 0x20007,
MANA_QUERY_VPORT_CONFIG = 0x20008,
+ MANA_QUERY_LINK_CONFIG = 0x2000A,
+ MANA_SET_BW_CLAMP = 0x2000B,
/* Privileged commands for the PF mode */
MANA_REGISTER_FILTER = 0x28000,
@@ -535,6 +546,35 @@ enum mana_command_code {
MANA_DEREGISTER_HW_PORT = 0x28004,
};
+/* Query Link Configuration*/
+struct mana_query_link_config_req {
+ struct gdma_req_hdr hdr;
+ mana_handle_t vport;
+}; /* HW DATA */
+
+struct mana_query_link_config_resp {
+ struct gdma_resp_hdr hdr;
+ u32 qos_speed_mbps;
+ u8 qos_unconfigured;
+ u8 reserved1[3];
+ u32 link_speed_mbps;
+ u8 reserved2[4];
+}; /* HW DATA */
+
+/* Set Bandwidth Clamp*/
+struct mana_set_bw_clamp_req {
+ struct gdma_req_hdr hdr;
+ mana_handle_t vport;
+ enum TRI_STATE enable_clamping;
+ u32 link_speed_mbps;
+}; /* HW DATA */
+
+struct mana_set_bw_clamp_resp {
+ struct gdma_resp_hdr hdr;
+ u8 qos_unconfigured;
+ u8 reserved[7];
+}; /* HW DATA */
+
/* Query Device Configuration */
struct mana_query_device_cfg_req {
struct gdma_req_hdr hdr;
--
2.34.1
^ permalink raw reply related
* [PATCH net-next 3/4] net: mana: Add speed support in mana_get_link_ksettings
From: Erni Sri Satya Vennela @ 2025-06-11 8:46 UTC (permalink / raw)
To: kys, haiyangz, wei.liu, decui, andrew+netdev, davem, edumazet,
kuba, pabeni, kotaranov, longli, horms, shirazsaleem, leon, ernis,
shradhagupta, schakrabarti, rosenp, sdf, linux-hyperv, netdev,
linux-kernel, linux-rdma
In-Reply-To: <1749631576-2517-1-git-send-email-ernis@linux.microsoft.com>
Allow mana ethtool get_link_ksettings operation to report
the maximum speed supported by the SKU in mbps.
The driver retrieves this information by issuing a
HWC command to the hardware via mana_query_link_cfg(),
which retrieves the SKU's maximum supported speed.
These APIs when invoked on hardware that are older ot that do
not support these APIs, the speed would be reported as UNKNOWN.
Before:
$ethtool enP30832s1
> Settings for enP30832s1:
Supported ports: [ ]
Supported link modes: Not reported
Supported pause frame use: No
Supports auto-negotiation: No
Supported FEC modes: Not reported
Advertised link modes: Not reported
Advertised pause frame use: No
Advertised auto-negotiation: No
Advertised FEC modes: Not reported
Speed: Unknown!
Duplex: Full
Auto-negotiation: off
Port: Other
PHYAD: 0
Transceiver: internal
Link detected: yes
After:
$ethtool enP30832s1
> Settings for enP30832s1:
Supported ports: [ ]
Supported link modes: Not reported
Supported pause frame use: No
Supports auto-negotiation: No
Supported FEC modes: Not reported
Advertised link modes: Not reported
Advertised pause frame use: No
Advertised auto-negotiation: No
Advertised FEC modes: Not reported
Speed: 16000Mb/s
Duplex: Full
Auto-negotiation: off
Port: Other
PHYAD: 0
Transceiver: internal
Link detected: yes
Signed-off-by: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
---
drivers/net/ethernet/microsoft/mana/mana_en.c | 1 +
drivers/net/ethernet/microsoft/mana/mana_ethtool.c | 6 ++++++
include/net/mana/mana.h | 2 ++
3 files changed, 9 insertions(+)
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index b704dbc5e344..d5644400e71f 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -1271,6 +1271,7 @@ int mana_query_link_cfg(struct mana_port_context *apc)
return err;
}
apc->speed = resp.link_speed_mbps;
+ apc->max_speed = resp.qos_speed_mbps;
return 0;
}
diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
index c419626073f5..1026b0b2b59f 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
@@ -427,6 +427,12 @@ static int mana_set_ringparam(struct net_device *ndev,
static int mana_get_link_ksettings(struct net_device *ndev,
struct ethtool_link_ksettings *cmd)
{
+ struct mana_port_context *apc = netdev_priv(ndev);
+ int err;
+
+ err = mana_query_link_cfg(apc);
+ cmd->base.speed = (err) ? SPEED_UNKNOWN : apc->max_speed;
+
cmd->base.duplex = DUPLEX_FULL;
cmd->base.port = PORT_OTHER;
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index 0df84e51d541..5f38dec04d31 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -474,6 +474,8 @@ struct mana_port_context {
u16 port_idx;
/* Currently configured speed (mbps) */
u32 speed;
+ /* Maximum speed supported by the SKU (mbps) */
+ u32 max_speed;
bool port_is_up;
bool port_st_save; /* Saved port state */
--
2.34.1
^ permalink raw reply related
* [PATCH net-next 4/4] net: mana: Handle unsupported HWC commands
From: Erni Sri Satya Vennela @ 2025-06-11 8:46 UTC (permalink / raw)
To: kys, haiyangz, wei.liu, decui, andrew+netdev, davem, edumazet,
kuba, pabeni, kotaranov, longli, horms, shirazsaleem, leon, ernis,
shradhagupta, schakrabarti, rosenp, sdf, linux-hyperv, netdev,
linux-kernel, linux-rdma
In-Reply-To: <1749631576-2517-1-git-send-email-ernis@linux.microsoft.com>
If any of the HWC commands are not recognized by the
underlying hardware, the hardware returns the response
header status of -1. Log the information using
netdev_info_once to avoid multiple error logs in dmesg.
Signed-off-by: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
---
drivers/net/ethernet/microsoft/mana/hw_channel.c | 4 ++++
drivers/net/ethernet/microsoft/mana/mana_en.c | 11 +++++++++++
2 files changed, 15 insertions(+)
diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c
index a8c4d8db75a5..70c3b57b1e75 100644
--- a/drivers/net/ethernet/microsoft/mana/hw_channel.c
+++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c
@@ -890,6 +890,10 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len,
}
if (ctx->status_code && ctx->status_code != GDMA_STATUS_MORE_ENTRIES) {
+ if (ctx->status_code == -1) {
+ err = -EOPNOTSUPP;
+ goto out;
+ }
dev_err(hwc->dev, "HWC: Failed hw_channel req: 0x%x\n",
ctx->status_code);
err = -EPROTO;
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index d5644400e71f..10e766c73fca 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -847,6 +847,9 @@ static int mana_send_request(struct mana_context *ac, void *in_buf,
err = mana_gd_send_request(gc, in_len, in_buf, out_len,
out_buf);
if (err || resp->status) {
+ if (err == -EOPNOTSUPP)
+ return err;
+
dev_err(dev, "Failed to send mana message: %d, 0x%x\n",
err, resp->status);
return err ? err : -EPROTO;
@@ -1251,6 +1254,10 @@ int mana_query_link_cfg(struct mana_port_context *apc)
sizeof(resp));
if (err) {
+ if (err == -EOPNOTSUPP) {
+ netdev_info_once(ndev, "MANA_QUERY_LINK_CONFIG not supported\n");
+ return err;
+ }
netdev_err(ndev, "Failed to query link config: %d\n", err);
return err;
}
@@ -1293,6 +1300,10 @@ int mana_set_bw_clamp(struct mana_port_context *apc, u32 speed,
sizeof(resp));
if (err) {
+ if (err == -EOPNOTSUPP) {
+ netdev_info_once(ndev, "MANA_SET_BW_CLAMP not supported\n");
+ return err;
+ }
netdev_err(ndev, "Failed to set bandwidth clamp for speed %u, err = %d",
speed, err);
return err;
--
2.34.1
^ permalink raw reply related
* [PATCH 0/6] Fix warning for missing export.h in Hyper-V drivers
From: Naman Jain @ 2025-06-11 10:04 UTC (permalink / raw)
To: K . Y . Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen, x86,
H . Peter Anvin, Vitaly Kuznetsov, Sean Christopherson,
Paolo Bonzini, Daniel Lezcano, Andrew Lunn, David S . Miller,
Eric Dumazet, Jakub Kicinski, Paolo Abeni, Lorenzo Pieralisi,
Krzysztof Wilczyński, Manivannan Sadhasivam, Rob Herring,
Bjorn Helgaas, Konstantin Taranov, Leon Romanovsky, Long Li,
Shiraz Saleem, Shradha Gupta, Maxim Levitsky, Peter Zijlstra,
Erni Sri Satya Vennela, Souradeep Chakrabarti
Cc: linux-hyperv, linux-kernel, kvm, netdev, linux-pci
When the kernel is compiled with W=1 option, a warning is reported
if a .c file exports a symbol but does not include export.h header
file. This warning was added in below patch, which merged recently:
commit a934a57a42f6 ("scripts/misc-check: check missing #include <linux/export.h> when W=1")
Fix this issue in Hyper-V drivers. This does not bring any
functional changes.
The one in drivers/hv/vmbus_drv.c is going to be fixed with
https://lore.kernel.org/all/20250611072704.83199-2-namjain@linux.microsoft.com/
so it is not included in this series.
Naman Jain (6):
Drivers: hv: Fix warnings for missing export.h header inclusion
x86/hyperv: Fix warnings for missing export.h header inclusion
KVM: x86: hyper-v: Fix warnings for missing export.h header inclusion
clocksource: hyper-v: Fix warnings for missing export.h header
inclusion
PCI: hv: Fix warnings for missing export.h header inclusion
net: mana: Fix warnings for missing export.h header inclusion
arch/x86/hyperv/hv_init.c | 1 +
arch/x86/hyperv/irqdomain.c | 1 +
arch/x86/hyperv/ivm.c | 1 +
arch/x86/hyperv/nested.c | 1 +
arch/x86/kvm/hyperv.c | 1 +
arch/x86/kvm/kvm_onhyperv.c | 1 +
drivers/clocksource/hyperv_timer.c | 1 +
drivers/hv/channel.c | 1 +
drivers/hv/channel_mgmt.c | 1 +
drivers/hv/hv_proc.c | 1 +
drivers/hv/mshv_common.c | 1 +
drivers/hv/mshv_root_hv_call.c | 1 +
drivers/hv/ring_buffer.c | 1 +
drivers/net/ethernet/microsoft/mana/gdma_main.c | 1 +
drivers/net/ethernet/microsoft/mana/mana_en.c | 1 +
drivers/pci/controller/pci-hyperv-intf.c | 1 +
16 files changed, 16 insertions(+)
base-commit: 475c850a7fdd0915b856173186d5922899d65686
--
2.34.1
^ permalink raw reply
* [PATCH 1/6] Drivers: hv: Fix warnings for missing export.h header inclusion
From: Naman Jain @ 2025-06-11 10:04 UTC (permalink / raw)
To: K . Y . Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen, x86,
H . Peter Anvin, Vitaly Kuznetsov, Sean Christopherson,
Paolo Bonzini, Daniel Lezcano, Andrew Lunn, David S . Miller,
Eric Dumazet, Jakub Kicinski, Paolo Abeni, Lorenzo Pieralisi,
Krzysztof Wilczyński, Manivannan Sadhasivam, Rob Herring,
Bjorn Helgaas, Konstantin Taranov, Leon Romanovsky, Long Li,
Shiraz Saleem, Shradha Gupta, Maxim Levitsky, Peter Zijlstra,
Erni Sri Satya Vennela, Souradeep Chakrabarti
Cc: linux-hyperv, linux-kernel, kvm, netdev, linux-pci
In-Reply-To: <20250611100459.92900-1-namjain@linux.microsoft.com>
Fix below warning in Hyper-V drivers that comes when kernel is compiled
with W=1 option. Include export.h in driver files to fix it.
* warning: EXPORT_SYMBOL() is used, but #include <linux/export.h>
is missing
Signed-off-by: Naman Jain <namjain@linux.microsoft.com>
---
drivers/hv/channel.c | 1 +
drivers/hv/channel_mgmt.c | 1 +
drivers/hv/hv_proc.c | 1 +
drivers/hv/mshv_common.c | 1 +
drivers/hv/mshv_root_hv_call.c | 1 +
drivers/hv/ring_buffer.c | 1 +
6 files changed, 6 insertions(+)
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 35f26fa1ffe7..7c7c66e0dc3f 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -18,6 +18,7 @@
#include <linux/uio.h>
#include <linux/interrupt.h>
#include <linux/set_memory.h>
+#include <linux/export.h>
#include <asm/page.h>
#include <asm/mshyperv.h>
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 6e084c207414..65dd299e2944 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -20,6 +20,7 @@
#include <linux/delay.h>
#include <linux/cpu.h>
#include <linux/hyperv.h>
+#include <linux/export.h>
#include <asm/mshyperv.h>
#include <linux/sched/isolation.h>
diff --git a/drivers/hv/hv_proc.c b/drivers/hv/hv_proc.c
index 7d7ecb6f6137..fbb4eb3901bb 100644
--- a/drivers/hv/hv_proc.c
+++ b/drivers/hv/hv_proc.c
@@ -6,6 +6,7 @@
#include <linux/slab.h>
#include <linux/cpuhotplug.h>
#include <linux/minmax.h>
+#include <linux/export.h>
#include <asm/mshyperv.h>
/*
diff --git a/drivers/hv/mshv_common.c b/drivers/hv/mshv_common.c
index 2575e6d7a71f..6f227a8a5af7 100644
--- a/drivers/hv/mshv_common.c
+++ b/drivers/hv/mshv_common.c
@@ -13,6 +13,7 @@
#include <linux/mm.h>
#include <asm/mshyperv.h>
#include <linux/resume_user_mode.h>
+#include <linux/export.h>
#include "mshv.h"
diff --git a/drivers/hv/mshv_root_hv_call.c b/drivers/hv/mshv_root_hv_call.c
index a222a16107f6..c9c274f29c3c 100644
--- a/drivers/hv/mshv_root_hv_call.c
+++ b/drivers/hv/mshv_root_hv_call.c
@@ -9,6 +9,7 @@
#include <linux/kernel.h>
#include <linux/mm.h>
+#include <linux/export.h>
#include <asm/mshyperv.h>
#include "mshv_root.h"
diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c
index 3c9b02471760..23ce1fb70de1 100644
--- a/drivers/hv/ring_buffer.c
+++ b/drivers/hv/ring_buffer.c
@@ -18,6 +18,7 @@
#include <linux/slab.h>
#include <linux/prefetch.h>
#include <linux/io.h>
+#include <linux/export.h>
#include <asm/mshyperv.h>
#include "hyperv_vmbus.h"
--
2.34.1
^ permalink raw reply related
* [PATCH 2/6] x86/hyperv: Fix warnings for missing export.h header inclusion
From: Naman Jain @ 2025-06-11 10:04 UTC (permalink / raw)
To: K . Y . Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen, x86,
H . Peter Anvin, Vitaly Kuznetsov, Sean Christopherson,
Paolo Bonzini, Daniel Lezcano, Andrew Lunn, David S . Miller,
Eric Dumazet, Jakub Kicinski, Paolo Abeni, Lorenzo Pieralisi,
Krzysztof Wilczyński, Manivannan Sadhasivam, Rob Herring,
Bjorn Helgaas, Konstantin Taranov, Leon Romanovsky, Long Li,
Shiraz Saleem, Shradha Gupta, Maxim Levitsky, Peter Zijlstra,
Erni Sri Satya Vennela, Souradeep Chakrabarti
Cc: linux-hyperv, linux-kernel, kvm, netdev, linux-pci
In-Reply-To: <20250611100459.92900-1-namjain@linux.microsoft.com>
Fix below warning in Hyper-V drivers that comes when kernel is compiled
with W=1 option. Include export.h in driver files to fix it.
* warning: EXPORT_SYMBOL() is used, but #include <linux/export.h>
is missing
Signed-off-by: Naman Jain <namjain@linux.microsoft.com>
---
arch/x86/hyperv/hv_init.c | 1 +
arch/x86/hyperv/irqdomain.c | 1 +
arch/x86/hyperv/ivm.c | 1 +
arch/x86/hyperv/nested.c | 1 +
4 files changed, 4 insertions(+)
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 3d1d3547095a..afdbda2dd7b7 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -34,6 +34,7 @@
#include <linux/syscore_ops.h>
#include <clocksource/hyperv_timer.h>
#include <linux/highmem.h>
+#include <linux/export.h>
void *hv_hypercall_pg;
EXPORT_SYMBOL_GPL(hv_hypercall_pg);
diff --git a/arch/x86/hyperv/irqdomain.c b/arch/x86/hyperv/irqdomain.c
index 31f0d29cbc5e..f7627bc8fe49 100644
--- a/arch/x86/hyperv/irqdomain.c
+++ b/arch/x86/hyperv/irqdomain.c
@@ -10,6 +10,7 @@
#include <linux/pci.h>
#include <linux/irq.h>
+#include <linux/export.h>
#include <asm/mshyperv.h>
static int hv_map_interrupt(union hv_device_id device_id, bool level,
diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
index e93a2f488ff7..ade6c665c97e 100644
--- a/arch/x86/hyperv/ivm.c
+++ b/arch/x86/hyperv/ivm.c
@@ -10,6 +10,7 @@
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/cpu.h>
+#include <linux/export.h>
#include <asm/svm.h>
#include <asm/sev.h>
#include <asm/io.h>
diff --git a/arch/x86/hyperv/nested.c b/arch/x86/hyperv/nested.c
index 1083dc8646f9..8ccbb7c4fc27 100644
--- a/arch/x86/hyperv/nested.c
+++ b/arch/x86/hyperv/nested.c
@@ -11,6 +11,7 @@
#include <linux/types.h>
+#include <linux/export.h>
#include <hyperv/hvhdk.h>
#include <asm/mshyperv.h>
#include <asm/tlbflush.h>
--
2.34.1
^ permalink raw reply related
* [PATCH 3/6] KVM: x86: hyper-v: Fix warnings for missing export.h header inclusion
From: Naman Jain @ 2025-06-11 10:04 UTC (permalink / raw)
To: K . Y . Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen, x86,
H . Peter Anvin, Vitaly Kuznetsov, Sean Christopherson,
Paolo Bonzini, Daniel Lezcano, Andrew Lunn, David S . Miller,
Eric Dumazet, Jakub Kicinski, Paolo Abeni, Lorenzo Pieralisi,
Krzysztof Wilczyński, Manivannan Sadhasivam, Rob Herring,
Bjorn Helgaas, Konstantin Taranov, Leon Romanovsky, Long Li,
Shiraz Saleem, Shradha Gupta, Maxim Levitsky, Peter Zijlstra,
Erni Sri Satya Vennela, Souradeep Chakrabarti
Cc: linux-hyperv, linux-kernel, kvm, netdev, linux-pci
In-Reply-To: <20250611100459.92900-1-namjain@linux.microsoft.com>
Fix below warning in Hyper-V drivers that comes when kernel is compiled
with W=1 option. Include export.h in driver files to fix it.
* warning: EXPORT_SYMBOL() is used, but #include <linux/export.h>
is missing
Signed-off-by: Naman Jain <namjain@linux.microsoft.com>
---
arch/x86/kvm/hyperv.c | 1 +
arch/x86/kvm/kvm_onhyperv.c | 1 +
2 files changed, 2 insertions(+)
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 24f0318c50d7..09f9de4555dd 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -33,6 +33,7 @@
#include <linux/sched/cputime.h>
#include <linux/spinlock.h>
#include <linux/eventfd.h>
+#include <linux/export.h>
#include <asm/apicdef.h>
#include <asm/mshyperv.h>
diff --git a/arch/x86/kvm/kvm_onhyperv.c b/arch/x86/kvm/kvm_onhyperv.c
index ded0bd688c65..ba45f8364187 100644
--- a/arch/x86/kvm/kvm_onhyperv.c
+++ b/arch/x86/kvm/kvm_onhyperv.c
@@ -5,6 +5,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kvm_host.h>
+#include <linux/export.h>
#include <asm/mshyperv.h>
#include "hyperv.h"
--
2.34.1
^ permalink raw reply related
* [PATCH 4/6] clocksource: hyper-v: Fix warnings for missing export.h header inclusion
From: Naman Jain @ 2025-06-11 10:04 UTC (permalink / raw)
To: K . Y . Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen, x86,
H . Peter Anvin, Vitaly Kuznetsov, Sean Christopherson,
Paolo Bonzini, Daniel Lezcano, Andrew Lunn, David S . Miller,
Eric Dumazet, Jakub Kicinski, Paolo Abeni, Lorenzo Pieralisi,
Krzysztof Wilczyński, Manivannan Sadhasivam, Rob Herring,
Bjorn Helgaas, Konstantin Taranov, Leon Romanovsky, Long Li,
Shiraz Saleem, Shradha Gupta, Maxim Levitsky, Peter Zijlstra,
Erni Sri Satya Vennela, Souradeep Chakrabarti
Cc: linux-hyperv, linux-kernel, kvm, netdev, linux-pci
In-Reply-To: <20250611100459.92900-1-namjain@linux.microsoft.com>
Fix below warning in Hyper-V clocksource driver that comes when kernel
is compiled with W=1 option. Include export.h in driver files to fix it.
* warning: EXPORT_SYMBOL() is used, but #include <linux/export.h>
is missing
Signed-off-by: Naman Jain <namjain@linux.microsoft.com>
---
drivers/clocksource/hyperv_timer.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c
index 09549451dd51..2edc13ca184e 100644
--- a/drivers/clocksource/hyperv_timer.c
+++ b/drivers/clocksource/hyperv_timer.c
@@ -22,6 +22,7 @@
#include <linux/irq.h>
#include <linux/acpi.h>
#include <linux/hyperv.h>
+#include <linux/export.h>
#include <clocksource/hyperv_timer.h>
#include <hyperv/hvhdk.h>
#include <asm/mshyperv.h>
--
2.34.1
^ permalink raw reply related
* [PATCH 5/6] PCI: hv: Fix warnings for missing export.h header inclusion
From: Naman Jain @ 2025-06-11 10:04 UTC (permalink / raw)
To: K . Y . Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen, x86,
H . Peter Anvin, Vitaly Kuznetsov, Sean Christopherson,
Paolo Bonzini, Daniel Lezcano, Andrew Lunn, David S . Miller,
Eric Dumazet, Jakub Kicinski, Paolo Abeni, Lorenzo Pieralisi,
Krzysztof Wilczyński, Manivannan Sadhasivam, Rob Herring,
Bjorn Helgaas, Konstantin Taranov, Leon Romanovsky, Long Li,
Shiraz Saleem, Shradha Gupta, Maxim Levitsky, Peter Zijlstra,
Erni Sri Satya Vennela, Souradeep Chakrabarti
Cc: linux-hyperv, linux-kernel, kvm, netdev, linux-pci
In-Reply-To: <20250611100459.92900-1-namjain@linux.microsoft.com>
Fix below warning in Hyper-V PCI driver that comes when kernel is
compiled with W=1 option. Include export.h in driver files to fix it.
* warning: EXPORT_SYMBOL() is used, but #include <linux/export.h>
is missing
Signed-off-by: Naman Jain <namjain@linux.microsoft.com>
---
drivers/pci/controller/pci-hyperv-intf.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/pci/controller/pci-hyperv-intf.c b/drivers/pci/controller/pci-hyperv-intf.c
index cc96be450360..28b3e93d31c0 100644
--- a/drivers/pci/controller/pci-hyperv-intf.c
+++ b/drivers/pci/controller/pci-hyperv-intf.c
@@ -14,6 +14,7 @@
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/hyperv.h>
+#include <linux/export.h>
struct hyperv_pci_block_ops hvpci_block_ops;
EXPORT_SYMBOL_GPL(hvpci_block_ops);
--
2.34.1
^ permalink raw reply related
* [PATCH 6/6] net: mana: Fix warnings for missing export.h header inclusion
From: Naman Jain @ 2025-06-11 10:04 UTC (permalink / raw)
To: K . Y . Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen, x86,
H . Peter Anvin, Vitaly Kuznetsov, Sean Christopherson,
Paolo Bonzini, Daniel Lezcano, Andrew Lunn, David S . Miller,
Eric Dumazet, Jakub Kicinski, Paolo Abeni, Lorenzo Pieralisi,
Krzysztof Wilczyński, Manivannan Sadhasivam, Rob Herring,
Bjorn Helgaas, Konstantin Taranov, Leon Romanovsky, Long Li,
Shiraz Saleem, Shradha Gupta, Maxim Levitsky, Peter Zijlstra,
Erni Sri Satya Vennela, Souradeep Chakrabarti
Cc: linux-hyperv, linux-kernel, kvm, netdev, linux-pci
In-Reply-To: <20250611100459.92900-1-namjain@linux.microsoft.com>
Fix below warning in Hyper-V's MANA drivers that comes when kernel is
compiled with W=1 option. Include export.h in driver files to fix it.
* warning: EXPORT_SYMBOL() is used, but #include <linux/export.h>
is missing
Signed-off-by: Naman Jain <namjain@linux.microsoft.com>
---
drivers/net/ethernet/microsoft/mana/gdma_main.c | 1 +
drivers/net/ethernet/microsoft/mana/mana_en.c | 1 +
2 files changed, 2 insertions(+)
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 3504507477c6..019e32b60043 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -6,6 +6,7 @@
#include <linux/pci.h>
#include <linux/utsname.h>
#include <linux/version.h>
+#include <linux/export.h>
#include <net/mana/mana.h>
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index ccd2885c939e..faad1cb880f8 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -10,6 +10,7 @@
#include <linux/filter.h>
#include <linux/mm.h>
#include <linux/pci.h>
+#include <linux/export.h>
#include <net/checksum.h>
#include <net/ip6_checksum.h>
--
2.34.1
^ permalink raw reply related
* Re: [PATCH net-next 1/4] net: mana: Fix potential deadlocks in mana napi ops
From: Saurabh Singh Sengar @ 2025-06-11 11:03 UTC (permalink / raw)
To: Erni Sri Satya Vennela
Cc: kys, haiyangz, wei.liu, decui, andrew+netdev, davem, edumazet,
kuba, pabeni, kotaranov, longli, horms, shirazsaleem, leon,
shradhagupta, schakrabarti, rosenp, sdf, linux-hyperv, netdev,
linux-kernel, linux-rdma
In-Reply-To: <1749631576-2517-2-git-send-email-ernis@linux.microsoft.com>
On Wed, Jun 11, 2025 at 01:46:13AM -0700, Erni Sri Satya Vennela wrote:
> When net_shaper_ops are enabled for MANA, netdev_ops_lock
> becomes active.
>
> The netvsc sets up MANA VF via following call chain:
>
> netvsc_vf_setup()
> dev_change_flags()
> ...
> __dev_open() OR __dev_close()
>
> dev_change_flags() holds the netdev mutex via netdev_lock_ops.
>
> During this process, mana_create_txq() and mana_create_rxq()
> invoke netif_napi_add_tx(), netif_napi_add_weight(), and napi_enable(),
> all of which attempt to acquire the same lock,
> leading to a potential deadlock.
commit message could be better oriented.
>
> Similarly, mana_destroy_txq() and mana_destroy_rxq() call
> netif_napi_disable() and netif_napi_del(), which also contend
> for the same lock.
>
> Switch to the _locked variants of these APIs to avoid deadlocks
> when the netdev_ops_lock is held.
>
> Fixes: d4c22ec680c8 ("net: hold netdev instance lock during ndo_open/ndo_stop")
> Signed-off-by: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
> Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
> Reviewed-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
> ---
> drivers/net/ethernet/microsoft/mana/mana_en.c | 39 ++++++++++++++-----
> 1 file changed, 30 insertions(+), 9 deletions(-)
>
> diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
> index ccd2885c939e..3c879d8a39e3 100644
> --- a/drivers/net/ethernet/microsoft/mana/mana_en.c
> +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
> @@ -1911,8 +1911,13 @@ static void mana_destroy_txq(struct mana_port_context *apc)
> napi = &apc->tx_qp[i].tx_cq.napi;
> if (apc->tx_qp[i].txq.napi_initialized) {
> napi_synchronize(napi);
> - napi_disable(napi);
> - netif_napi_del(napi);
> + if (netdev_need_ops_lock(napi->dev)) {
> + napi_disable_locked(napi);
> + netif_napi_del_locked(napi);
> + } else {
> + napi_disable(napi);
> + netif_napi_del(napi);
> + }
Instead of using if-else, we can used netdev_lock_ops(), followed by *_locked api-s.
Same for rest of the patch.
Reviewed-by: Saurabh Sengar <ssengar@linux.microsoft.com>
- Saurabh
^ permalink raw reply
* Re: [PATCH 0/6] Fix warning for missing export.h in Hyper-V drivers
From: Saurabh Singh Sengar @ 2025-06-11 11:12 UTC (permalink / raw)
To: Naman Jain
Cc: K . Y . Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen, x86,
H . Peter Anvin, Vitaly Kuznetsov, Sean Christopherson,
Paolo Bonzini, Daniel Lezcano, Andrew Lunn, David S . Miller,
Eric Dumazet, Jakub Kicinski, Paolo Abeni, Lorenzo Pieralisi,
Krzysztof Wilczyński, Manivannan Sadhasivam, Rob Herring,
Bjorn Helgaas, Konstantin Taranov, Leon Romanovsky, Long Li,
Shiraz Saleem, Shradha Gupta, Maxim Levitsky, Peter Zijlstra,
Erni Sri Satya Vennela, Souradeep Chakrabarti, linux-hyperv,
linux-kernel, kvm, netdev, linux-pci
In-Reply-To: <20250611100459.92900-1-namjain@linux.microsoft.com>
On Wed, Jun 11, 2025 at 03:34:53PM +0530, Naman Jain wrote:
> When the kernel is compiled with W=1 option, a warning is reported
> if a .c file exports a symbol but does not include export.h header
> file. This warning was added in below patch, which merged recently:
> commit a934a57a42f6 ("scripts/misc-check: check missing #include <linux/export.h> when W=1")
>
> Fix this issue in Hyper-V drivers. This does not bring any
> functional changes.
>
> The one in drivers/hv/vmbus_drv.c is going to be fixed with
> https://lore.kernel.org/all/20250611072704.83199-2-namjain@linux.microsoft.com/
> so it is not included in this series.
>
> Naman Jain (6):
> Drivers: hv: Fix warnings for missing export.h header inclusion
> x86/hyperv: Fix warnings for missing export.h header inclusion
> KVM: x86: hyper-v: Fix warnings for missing export.h header inclusion
> clocksource: hyper-v: Fix warnings for missing export.h header
> inclusion
> PCI: hv: Fix warnings for missing export.h header inclusion
> net: mana: Fix warnings for missing export.h header inclusion
>
> arch/x86/hyperv/hv_init.c | 1 +
> arch/x86/hyperv/irqdomain.c | 1 +
> arch/x86/hyperv/ivm.c | 1 +
> arch/x86/hyperv/nested.c | 1 +
> arch/x86/kvm/hyperv.c | 1 +
> arch/x86/kvm/kvm_onhyperv.c | 1 +
> drivers/clocksource/hyperv_timer.c | 1 +
> drivers/hv/channel.c | 1 +
> drivers/hv/channel_mgmt.c | 1 +
> drivers/hv/hv_proc.c | 1 +
> drivers/hv/mshv_common.c | 1 +
> drivers/hv/mshv_root_hv_call.c | 1 +
> drivers/hv/ring_buffer.c | 1 +
> drivers/net/ethernet/microsoft/mana/gdma_main.c | 1 +
> drivers/net/ethernet/microsoft/mana/mana_en.c | 1 +
> drivers/pci/controller/pci-hyperv-intf.c | 1 +
> 16 files changed, 16 insertions(+)
>
>
> base-commit: 475c850a7fdd0915b856173186d5922899d65686
> --
> 2.34.1
>
For the series,
Reviewed-by: Saurabh Sengar <ssengar@linux.microsoft.com>
^ permalink raw reply
* Re: [PATCH net-next 4/4] net: mana: Handle unsupported HWC commands
From: Dipayaan Roy @ 2025-06-11 11:35 UTC (permalink / raw)
To: Erni Sri Satya Vennela
Cc: kys, haiyangz, wei.liu, decui, andrew+netdev, davem, edumazet,
kuba, pabeni, kotaranov, longli, horms, shirazsaleem, leon,
shradhagupta, schakrabarti, rosenp, sdf, linux-hyperv, netdev,
linux-kernel, linux-rdma
In-Reply-To: <1749631576-2517-5-git-send-email-ernis@linux.microsoft.com>
On Wed, Jun 11, 2025 at 01:46:16AM -0700, Erni Sri Satya Vennela wrote:
> If any of the HWC commands are not recognized by the
> underlying hardware, the hardware returns the response
> header status of -1. Log the information using
> netdev_info_once to avoid multiple error logs in dmesg.
>
> Signed-off-by: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
> Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
> Reviewed-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
> ---
> drivers/net/ethernet/microsoft/mana/hw_channel.c | 4 ++++
> drivers/net/ethernet/microsoft/mana/mana_en.c | 11 +++++++++++
> 2 files changed, 15 insertions(+)
>
> diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c
> index a8c4d8db75a5..70c3b57b1e75 100644
> --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c
> +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c
> @@ -890,6 +890,10 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len,
> }
>
> if (ctx->status_code && ctx->status_code != GDMA_STATUS_MORE_ENTRIES) {
> + if (ctx->status_code == -1) {
Minor comment: instead of == -1 could use some macro like GDMA_STATUS_CMD_UNSUPPORTED, rest LGTM.
> + err = -EOPNOTSUPP;
> + goto out;
> + }
> dev_err(hwc->dev, "HWC: Failed hw_channel req: 0x%x\n",
> ctx->status_code);
> err = -EPROTO;
> diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
> index d5644400e71f..10e766c73fca 100644
> --- a/drivers/net/ethernet/microsoft/mana/mana_en.c
> +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
> @@ -847,6 +847,9 @@ static int mana_send_request(struct mana_context *ac, void *in_buf,
> err = mana_gd_send_request(gc, in_len, in_buf, out_len,
> out_buf);
> if (err || resp->status) {
> + if (err == -EOPNOTSUPP)
> + return err;
> +
> dev_err(dev, "Failed to send mana message: %d, 0x%x\n",
> err, resp->status);
> return err ? err : -EPROTO;
> @@ -1251,6 +1254,10 @@ int mana_query_link_cfg(struct mana_port_context *apc)
> sizeof(resp));
>
> if (err) {
> + if (err == -EOPNOTSUPP) {
> + netdev_info_once(ndev, "MANA_QUERY_LINK_CONFIG not supported\n");
> + return err;
> + }
> netdev_err(ndev, "Failed to query link config: %d\n", err);
> return err;
> }
> @@ -1293,6 +1300,10 @@ int mana_set_bw_clamp(struct mana_port_context *apc, u32 speed,
> sizeof(resp));
>
> if (err) {
> + if (err == -EOPNOTSUPP) {
> + netdev_info_once(ndev, "MANA_SET_BW_CLAMP not supported\n");
> + return err;
> + }
> netdev_err(ndev, "Failed to set bandwidth clamp for speed %u, err = %d",
> speed, err);
> return err;
> --
> 2.34.1
>
Reviewed-by: Dipayaan Roy <dipayanroy@linux.microsoft.com>
^ permalink raw reply
* Re: [PATCH] firmware: smccc: support both conduits for getting hyp UUID
From: Sudeep Holla @ 2025-06-11 12:52 UTC (permalink / raw)
To: Roman Kisel
Cc: anirudh, linux-arm-kernel, Sudeep Holla, linux-hyperv,
linux-kernel, lpieralisi, mark.rutland
In-Reply-To: <20250610160656.11984-1-romank@linux.microsoft.com>
On Tue, Jun 10, 2025 at 09:06:48AM -0700, Roman Kisel wrote:
> > (sorry for the delay, found the patch in the spam 🙁)
>
> "b4" shows the the mail server used for the patch submission
> doesn't pass the DKIM check, so finding the patch in the spam seems
> expected :) Thanks for your help!
>
Thought so looking at the header but I just have very basic knowledge
there, so couldn't comment.
> >
> > On Wed, May 21, 2025 at 09:40:48AM +0000, Anirudh Rayabharam wrote:
> >> From: Anirudh Rayabharam (Microsoft) <anirudh@anirudhrb.com>
> >>
> >> When Linux is running as the root partition under Microsoft Hypervisor
> >> (MSHV) a.k.a Hyper-V, smc is used as the conduit for smc calls.
> >>
> >> Extend arm_smccc_hypervisor_has_uuid() to support this usecase. Use
> >> arm_smccc_1_1_invoke to retrieve and use the appropriate conduit instead
> >> of supporting only hvc.
> >>
> >> Boot tested on MSHV guest, MSHV root & KVM guest.
> >>
> >
> > Reviewed-by: Sudeep Holla <sudeep.holla@arm.com>
> >
> > Are they any dependent patches or series using this ? Do you plan to
> > route it via KVM tree if there are any dependency. Or else I can push
> > it through (arm-)soc tree. Let me know.
>
> Anirudh had been OOF for some time and would be for another
> week iiuc so I thought I'd reply.
>
> The patch this depends on is 13423063c7cb
> ("arm64: kvm, smccc: Introduce and use API for getting hypervisor UUID"),
> and this patch has already been pulled into the Linus'es tree.
>
Had a quick look at the commit to refresh my memory and as you mentioned
it is new feature. I was checking to see if this is a fix.
> As for routing, (arm-)soc should be good it appears as the change
> is contained within the firmware drivers path. Although I'd trust more to your,
> Arnd's or Wei's opinion than mine!
>
I will queue this once I start collecting patches for v6.17 in 1/2 weeks'
time, so expect silence until then 😄.
--
Regards,
Sudeep
^ permalink raw reply
* Re: [PATCH net-next 1/4] net: mana: Fix potential deadlocks in mana napi ops
From: Saurabh Singh Sengar @ 2025-06-11 12:55 UTC (permalink / raw)
To: Erni Sri Satya Vennela
Cc: kys, haiyangz, wei.liu, decui, andrew+netdev, davem, edumazet,
kuba, pabeni, kotaranov, longli, horms, shirazsaleem, leon,
shradhagupta, schakrabarti, rosenp, sdf, linux-hyperv, netdev,
linux-kernel, linux-rdma
In-Reply-To: <20250611110352.GA31913@linuxonhyperv3.guj3yctzbm1etfxqx2vob5hsef.xx.internal.cloudapp.net>
On Wed, Jun 11, 2025 at 04:03:52AM -0700, Saurabh Singh Sengar wrote:
> On Wed, Jun 11, 2025 at 01:46:13AM -0700, Erni Sri Satya Vennela wrote:
> > When net_shaper_ops are enabled for MANA, netdev_ops_lock
> > becomes active.
> >
> > The netvsc sets up MANA VF via following call chain:
> >
> > netvsc_vf_setup()
> > dev_change_flags()
> > ...
> > __dev_open() OR __dev_close()
> >
> > dev_change_flags() holds the netdev mutex via netdev_lock_ops.
> >
> > During this process, mana_create_txq() and mana_create_rxq()
> > invoke netif_napi_add_tx(), netif_napi_add_weight(), and napi_enable(),
> > all of which attempt to acquire the same lock,
> > leading to a potential deadlock.
>
> commit message could be better oriented.
>
> >
> > Similarly, mana_destroy_txq() and mana_destroy_rxq() call
> > netif_napi_disable() and netif_napi_del(), which also contend
> > for the same lock.
> >
> > Switch to the _locked variants of these APIs to avoid deadlocks
> > when the netdev_ops_lock is held.
> >
> > Fixes: d4c22ec680c8 ("net: hold netdev instance lock during ndo_open/ndo_stop")
> > Signed-off-by: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
> > Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
> > Reviewed-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
> > ---
> > drivers/net/ethernet/microsoft/mana/mana_en.c | 39 ++++++++++++++-----
> > 1 file changed, 30 insertions(+), 9 deletions(-)
> >
> > diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
> > index ccd2885c939e..3c879d8a39e3 100644
> > --- a/drivers/net/ethernet/microsoft/mana/mana_en.c
> > +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
> > @@ -1911,8 +1911,13 @@ static void mana_destroy_txq(struct mana_port_context *apc)
> > napi = &apc->tx_qp[i].tx_cq.napi;
> > if (apc->tx_qp[i].txq.napi_initialized) {
> > napi_synchronize(napi);
> > - napi_disable(napi);
> > - netif_napi_del(napi);
> > + if (netdev_need_ops_lock(napi->dev)) {
> > + napi_disable_locked(napi);
> > + netif_napi_del_locked(napi);
> > + } else {
> > + napi_disable(napi);
> > + netif_napi_del(napi);
> > + }
>
> Instead of using if-else, we can used netdev_lock_ops(), followed by *_locked api-s.
> Same for rest of the patch.
>
I later realized that what we actually need is:
if (!netdev_need_ops_lock(napi->dev))
netdev_lock(dev);
not
if (netdev_need_ops_lock(napi->dev))
netdev_lock(dev);
Hence, netdev_lock_ops() is not appropriate. Instead, netdev_lock_ops_to_full()
seems to be a better choice.
> Reviewed-by: Saurabh Sengar <ssengar@linux.microsoft.com>
>
> - Saurabh
>
^ permalink raw reply
* Re: [PATCH 3/6] KVM: x86: hyper-v: Fix warnings for missing export.h header inclusion
From: Sean Christopherson @ 2025-06-11 12:58 UTC (permalink / raw)
To: Naman Jain
Cc: K . Y . Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen, x86,
H . Peter Anvin, Vitaly Kuznetsov, Paolo Bonzini, Daniel Lezcano,
Andrew Lunn, David S . Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Lorenzo Pieralisi, Krzysztof Wilczyński,
Manivannan Sadhasivam, Rob Herring, Bjorn Helgaas,
Konstantin Taranov, Leon Romanovsky, Long Li, Shiraz Saleem,
Shradha Gupta, Maxim Levitsky, Peter Zijlstra,
Erni Sri Satya Vennela, Souradeep Chakrabarti, linux-hyperv,
linux-kernel, kvm, netdev, linux-pci
In-Reply-To: <20250611100459.92900-4-namjain@linux.microsoft.com>
On Wed, Jun 11, 2025, Naman Jain wrote:
> Fix below warning in Hyper-V drivers
KVM is quite obviously not a Hyper-V driver.
> that comes when kernel is compiled with W=1 option. Include export.h in
> driver files to fix it. * warning: EXPORT_SYMBOL() is used, but #include
> <linux/export.h> is missing
NAK. I agree with Heiko[*], this is absurd. And if the W=1 change isn't reverted
for some reason, I'd rather "fix" all of KVM in one shot, not update random files
just because of their name.
Sorry.
[*] https://lore.kernel.org/all/20250611075533.8102A57-hca@linux.ibm.com
> Signed-off-by: Naman Jain <namjain@linux.microsoft.com>
> ---
> arch/x86/kvm/hyperv.c | 1 +
> arch/x86/kvm/kvm_onhyperv.c | 1 +
> 2 files changed, 2 insertions(+)
>
> diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
> index 24f0318c50d7..09f9de4555dd 100644
> --- a/arch/x86/kvm/hyperv.c
> +++ b/arch/x86/kvm/hyperv.c
> @@ -33,6 +33,7 @@
> #include <linux/sched/cputime.h>
> #include <linux/spinlock.h>
> #include <linux/eventfd.h>
> +#include <linux/export.h>
>
> #include <asm/apicdef.h>
> #include <asm/mshyperv.h>
> diff --git a/arch/x86/kvm/kvm_onhyperv.c b/arch/x86/kvm/kvm_onhyperv.c
> index ded0bd688c65..ba45f8364187 100644
> --- a/arch/x86/kvm/kvm_onhyperv.c
> +++ b/arch/x86/kvm/kvm_onhyperv.c
> @@ -5,6 +5,7 @@
> #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
>
> #include <linux/kvm_host.h>
> +#include <linux/export.h>
> #include <asm/mshyperv.h>
>
> #include "hyperv.h"
> --
> 2.34.1
>
^ permalink raw reply
* [PATCH v6 0/5] Allow dyn MSI-X vector allocation of MANA
From: Shradha Gupta @ 2025-06-11 14:09 UTC (permalink / raw)
Cc: Shradha Gupta, linux-hyperv, linux-pci, linux-kernel, Nipun Gupta,
Yury Norov, Jason Gunthorpe, Jonathan Cameron, Anna-Maria Behnsen,
Kevin Tian, Long Li, Thomas Gleixner, Bjorn Helgaas, Rob Herring,
Manivannan Sadhasivam, Krzysztof Wilczy�~Dski,
Lorenzo Pieralisi, Dexuan Cui, Wei Liu, Haiyang Zhang,
K. Y. Srinivasan, Andrew Lunn, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Konstantin Taranov, Simon Horman,
Leon Romanovsky, Maxim Levitsky, Erni Sri Satya Vennela,
Peter Zijlstra, netdev, linux-rdma, Paul Rosswurm, Shradha Gupta
In this patchset we want to enable the MANA driver to be able to
allocate MSI-X vectors in PCI dynamically.
The first patch exports pci_msix_prepare_desc() in PCI to be able to
correctly prepare descriptors for dynamically added MSI-X vectors.
The second patch adds the support of dynamic vector allocation in
pci-hyperv PCI controller by enabling the MSI_FLAG_PCI_MSIX_ALLOC_DYN
flag and using the pci_msix_prepare_desc() exported in first patch.
The third patch adds a detailed description of the irq_setup(), to
help understand the function design better.
The fourth patch is a preparation patch for mana changes to support
dynamic IRQ allocation. It contains changes in irq_setup() to allow
skipping first sibling CPU sets, in case certain IRQs are already
affinitized to them.
The fifth patch has the changes in MANA driver to be able to allocate
MSI-X vectors dynamically. If the support does not exist it defaults to
older behavior.
Since this patchset has patches from PCI and net tree, I am not entirely
sure what should be the target tree. Any suggestions/recommendations on
the same are welcomed.
---
Changes in v6
* rebased to linux-next's v6.16-rc1 as per Jakub's suggestion
---
Changes in v5
* Added Yury as Author of the 3rd patch
* Fixed base commit information in the cover letter
* Correctly initialized start_irqs, so that it is cleaned properly
* rearranged the cpu_lock to minimize the critical section
---
Change in v4
* add a patch describing the functionality of irq_setup() through a
comment
* In irq_setup(), avoid using a label next_cpumask:
* modify the changes in MANA patch about restructuring the error
handling path in mana_gd_setup_dyn_irqs()
* modify the mana_gd_setup_irqs() to simplify handling around
start_irq_index
* add warning if an invalid gic is returned
* place the xa_destroy() cleanup in mana_gd_remove
---
Changes in v3
* split the 3rd patch into preparation patch around irq_setup() and
changes in mana driver to allow dynamic IRQ allocation
* Add arm64 support for dynamic MSI-X allocation in pci_hyperv
controller
---
Changes in v2
* split the first patch into two(exporting the preapre_desc
func and using the function and flag in pci-hyperv)
* replace 'pci vectors' by 'MSI-X vectors'
* Change the cover letter description to align with changes made
---
Shradha Gupta (4):
PCI/MSI: Export pci_msix_prepare_desc() for dynamic MSI-X allocations
PCI: hv: Allow dynamic MSI-X vector allocation
net: mana: Allow irq_setup() to skip cpus for affinity
net: mana: Allocate MSI-X vectors dynamically
Yury Norov (1):
net: mana: explain irq_setup() algorithm
.../net/ethernet/microsoft/mana/gdma_main.c | 366 ++++++++++++++----
drivers/pci/controller/pci-hyperv.c | 3 +-
drivers/pci/msi/irqdomain.c | 5 +-
include/linux/msi.h | 2 +
include/net/mana/gdma.h | 8 +-
5 files changed, 294 insertions(+), 90 deletions(-)
base-commit: 19a60293b9925080d97f22f122aca3fc46dadaf9
--
2.34.1
^ permalink raw reply
* [PATCH v6 1/5] PCI/MSI: Export pci_msix_prepare_desc() for dynamic MSI-X allocations
From: Shradha Gupta @ 2025-06-11 14:10 UTC (permalink / raw)
To: Jason Gunthorpe, Jonathan Cameron, Anna-Maria Behnsen,
Thomas Gleixner, Bjorn Helgaas, Michael Kelley
Cc: Shradha Gupta, linux-hyperv, linux-pci, linux-kernel, Nipun Gupta,
Yury Norov, Kevin Tian, Long Li, Rob Herring,
Manivannan Sadhasivam, Krzysztof Wilczy�~Dski,
Lorenzo Pieralisi, Dexuan Cui, Wei Liu, Haiyang Zhang,
K. Y. Srinivasan, Andrew Lunn, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Konstantin Taranov, Simon Horman,
Leon Romanovsky, Maxim Levitsky, Erni Sri Satya Vennela,
Peter Zijlstra, netdev, linux-rdma, Paul Rosswurm, Shradha Gupta
In-Reply-To: <1749650984-9193-1-git-send-email-shradhagupta@linux.microsoft.com>
For supporting dynamic MSI-X vector allocation by PCI controllers, enabling
the flag MSI_FLAG_PCI_MSIX_ALLOC_DYN is not enough, msix_prepare_msi_desc()
to prepare the MSI descriptor is also needed.
Export pci_msix_prepare_desc() to allow PCI controllers to support dynamic
MSI-X vector allocation.
Signed-off-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Saurabh Sengar <ssengar@linux.microsoft.com>
---
drivers/pci/msi/irqdomain.c | 5 +++--
include/linux/msi.h | 2 ++
2 files changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c
index c05152733993..765312c92d9b 100644
--- a/drivers/pci/msi/irqdomain.c
+++ b/drivers/pci/msi/irqdomain.c
@@ -222,13 +222,14 @@ static void pci_irq_unmask_msix(struct irq_data *data)
pci_msix_unmask(irq_data_get_msi_desc(data));
}
-static void pci_msix_prepare_desc(struct irq_domain *domain, msi_alloc_info_t *arg,
- struct msi_desc *desc)
+void pci_msix_prepare_desc(struct irq_domain *domain, msi_alloc_info_t *arg,
+ struct msi_desc *desc)
{
/* Don't fiddle with preallocated MSI descriptors */
if (!desc->pci.mask_base)
msix_prepare_msi_desc(to_pci_dev(desc->dev), desc);
}
+EXPORT_SYMBOL_GPL(pci_msix_prepare_desc);
static const struct msi_domain_template pci_msix_template = {
.chip = {
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 6863540f4b71..7f254bde5426 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -706,6 +706,8 @@ struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode,
struct irq_domain *parent);
u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev);
struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev);
+void pci_msix_prepare_desc(struct irq_domain *domain, msi_alloc_info_t *arg,
+ struct msi_desc *desc);
#else /* CONFIG_PCI_MSI */
static inline struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev)
{
--
2.34.1
^ permalink raw reply related
* [PATCH v6 2/5] PCI: hv: Allow dynamic MSI-X vector allocation
From: Shradha Gupta @ 2025-06-11 14:10 UTC (permalink / raw)
To: Bjorn Helgaas, Rob Herring, Manivannan Sadhasivam,
Krzysztof Wilczy�~Dski, Lorenzo Pieralisi, Dexuan Cui,
Wei Liu, Haiyang Zhang, K. Y. Srinivasan, Michael Kelley
Cc: Shradha Gupta, linux-hyperv, linux-pci, linux-kernel, Nipun Gupta,
Yury Norov, Jason Gunthorpe, Jonathan Cameron, Anna-Maria Behnsen,
Kevin Tian, Long Li, Thomas Gleixner, Andrew Lunn,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Konstantin Taranov, Simon Horman, Leon Romanovsky, Maxim Levitsky,
Erni Sri Satya Vennela, Peter Zijlstra, netdev, linux-rdma,
Paul Rosswurm, Shradha Gupta
In-Reply-To: <1749650984-9193-1-git-send-email-shradhagupta@linux.microsoft.com>
Allow dynamic MSI-X vector allocation for pci_hyperv PCI controller
by adding support for the flag MSI_FLAG_PCI_MSIX_ALLOC_DYN and using
pci_msix_prepare_desc() to prepare the MSI-X descriptors.
Feature support added for both x86 and ARM64
Signed-off-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Saurabh Sengar <ssengar@linux.microsoft.com>
---
Changes in v4:
* use the same prepare_desc() callback for arm and x86
---
Changes in v3:
* Add arm64 support
---
Changes in v2:
* split the patch to keep changes in PCI and pci_hyperv controller
seperate
* replace strings "pci vectors" by "MSI-X vectors"
---
drivers/pci/controller/pci-hyperv.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index ef5d655a0052..86ca041bf74a 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -2119,6 +2119,7 @@ static struct irq_chip hv_msi_irq_chip = {
static struct msi_domain_ops hv_msi_ops = {
.msi_prepare = hv_msi_prepare,
.msi_free = hv_msi_free,
+ .prepare_desc = pci_msix_prepare_desc,
};
/**
@@ -2140,7 +2141,7 @@ static int hv_pcie_init_irq_domain(struct hv_pcibus_device *hbus)
hbus->msi_info.ops = &hv_msi_ops;
hbus->msi_info.flags = (MSI_FLAG_USE_DEF_DOM_OPS |
MSI_FLAG_USE_DEF_CHIP_OPS | MSI_FLAG_MULTI_PCI_MSI |
- MSI_FLAG_PCI_MSIX);
+ MSI_FLAG_PCI_MSIX | MSI_FLAG_PCI_MSIX_ALLOC_DYN);
hbus->msi_info.handler = FLOW_HANDLER;
hbus->msi_info.handler_name = FLOW_NAME;
hbus->msi_info.data = hbus;
--
2.34.1
^ permalink raw reply related
* [PATCH v6 3/5] net: mana: explain irq_setup() algorithm
From: Shradha Gupta @ 2025-06-11 14:10 UTC (permalink / raw)
To: Dexuan Cui, Wei Liu, Haiyang Zhang, K. Y. Srinivasan, Andrew Lunn,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Konstantin Taranov, Simon Horman, Leon Romanovsky, Maxim Levitsky,
Erni Sri Satya Vennela, Peter Zijlstra, Michael Kelley
Cc: Yury Norov, linux-hyperv, linux-pci, linux-kernel, Nipun Gupta,
Jason Gunthorpe, Jonathan Cameron, Anna-Maria Behnsen,
Shradha Gupta, Kevin Tian, Long Li, Thomas Gleixner,
Bjorn Helgaas, Rob Herring, Manivannan Sadhasivam,
Krzysztof Wilczy�~Dski, Lorenzo Pieralisi, netdev,
linux-rdma, Paul Rosswurm, Shradha Gupta
In-Reply-To: <1749650984-9193-1-git-send-email-shradhagupta@linux.microsoft.com>
From: Yury Norov <yury.norov@gmail.com>
Commit 91bfe210e196 ("net: mana: add a function to spread IRQs per CPUs")
added the irq_setup() function that distributes IRQs on CPUs according
to a tricky heuristic. The corresponding commit message explains the
heuristic.
Duplicate it in the source code to make available for readers without
digging git in history. Also, add more detailed explanation about how
the heuristics is implemented.
Signed-off-by: Yury Norov <yury.norov@gmail.com>
Signed-off-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
---
Changes in v5:
* Corrected the Authur of the patch
---
.../net/ethernet/microsoft/mana/gdma_main.c | 41 +++++++++++++++++++
1 file changed, 41 insertions(+)
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 3504507477c6..6c4e143972a1 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -1288,6 +1288,47 @@ void mana_gd_free_res_map(struct gdma_resource *r)
r->size = 0;
}
+/*
+ * Spread on CPUs with the following heuristics:
+ *
+ * 1. No more than one IRQ per CPU, if possible;
+ * 2. NUMA locality is the second priority;
+ * 3. Sibling dislocality is the last priority.
+ *
+ * Let's consider this topology:
+ *
+ * Node 0 1
+ * Core 0 1 2 3
+ * CPU 0 1 2 3 4 5 6 7
+ *
+ * The most performant IRQ distribution based on the above topology
+ * and heuristics may look like this:
+ *
+ * IRQ Nodes Cores CPUs
+ * 0 1 0 0-1
+ * 1 1 1 2-3
+ * 2 1 0 0-1
+ * 3 1 1 2-3
+ * 4 2 2 4-5
+ * 5 2 3 6-7
+ * 6 2 2 4-5
+ * 7 2 3 6-7
+ *
+ * The heuristics is implemented as follows.
+ *
+ * The outer for_each() loop resets the 'weight' to the actual number
+ * of CPUs in the hop. Then inner for_each() loop decrements it by the
+ * number of sibling groups (cores) while assigning first set of IRQs
+ * to each group. IRQs 0 and 1 above are distributed this way.
+ *
+ * Now, because NUMA locality is more important, we should walk the
+ * same set of siblings and assign 2nd set of IRQs (2 and 3), and it's
+ * implemented by the medium while() loop. We do like this unless the
+ * number of IRQs assigned on this hop will not become equal to number
+ * of CPUs in the hop (weight == 0). Then we switch to the next hop and
+ * do the same thing.
+ */
+
static int irq_setup(unsigned int *irqs, unsigned int len, int node)
{
const struct cpumask *next, *prev = cpu_none_mask;
--
2.34.1
^ permalink raw reply related
* [PATCH v6 4/5] net: mana: Allow irq_setup() to skip cpus for affinity
From: Shradha Gupta @ 2025-06-11 14:10 UTC (permalink / raw)
To: Dexuan Cui, Wei Liu, Haiyang Zhang, K. Y. Srinivasan, Andrew Lunn,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Konstantin Taranov, Simon Horman, Leon Romanovsky, Maxim Levitsky,
Erni Sri Satya Vennela, Peter Zijlstra, Michael Kelley
Cc: Shradha Gupta, linux-hyperv, linux-pci, linux-kernel, Nipun Gupta,
Yury Norov, Jason Gunthorpe, Jonathan Cameron, Anna-Maria Behnsen,
Kevin Tian, Long Li, Thomas Gleixner, Bjorn Helgaas, Rob Herring,
Manivannan Sadhasivam, Krzysztof Wilczy�~Dski,
Lorenzo Pieralisi, netdev, linux-rdma, Paul Rosswurm,
Shradha Gupta
In-Reply-To: <1749650984-9193-1-git-send-email-shradhagupta@linux.microsoft.com>
In order to prepare the MANA driver to allocate the MSI-X IRQs
dynamically, we need to enhance irq_setup() to allow skipping
affinitizing IRQs to the first CPU sibling group.
This would be for cases when the number of IRQs is less than or equal
to the number of online CPUs. In such cases for dynamically added IRQs
the first CPU sibling group would already be affinitized with HWC IRQ.
Signed-off-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Yury Norov [NVIDIA] <yury.norov@gmail.com>
---
Changes in v4
* fix commit description
* avoided using next_cpumask: label in the irq_setup()
---
drivers/net/ethernet/microsoft/mana/gdma_main.c | 16 ++++++++++++----
1 file changed, 12 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 6c4e143972a1..6e468c0f2c40 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -1329,7 +1329,8 @@ void mana_gd_free_res_map(struct gdma_resource *r)
* do the same thing.
*/
-static int irq_setup(unsigned int *irqs, unsigned int len, int node)
+static int irq_setup(unsigned int *irqs, unsigned int len, int node,
+ bool skip_first_cpu)
{
const struct cpumask *next, *prev = cpu_none_mask;
cpumask_var_t cpus __free(free_cpumask_var);
@@ -1344,11 +1345,18 @@ static int irq_setup(unsigned int *irqs, unsigned int len, int node)
while (weight > 0) {
cpumask_andnot(cpus, next, prev);
for_each_cpu(cpu, cpus) {
+ cpumask_andnot(cpus, cpus, topology_sibling_cpumask(cpu));
+ --weight;
+
+ if (unlikely(skip_first_cpu)) {
+ skip_first_cpu = false;
+ continue;
+ }
+
if (len-- == 0)
goto done;
+
irq_set_affinity_and_hint(*irqs++, topology_sibling_cpumask(cpu));
- cpumask_andnot(cpus, cpus, topology_sibling_cpumask(cpu));
- --weight;
}
}
prev = next;
@@ -1444,7 +1452,7 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev)
}
}
- err = irq_setup(irqs, (nvec - start_irq_index), gc->numa_node);
+ err = irq_setup(irqs, nvec - start_irq_index, gc->numa_node, false);
if (err)
goto free_irq;
--
2.34.1
^ permalink raw reply related
* [PATCH v6 5/5] net: mana: Allocate MSI-X vectors dynamically
From: Shradha Gupta @ 2025-06-11 14:11 UTC (permalink / raw)
To: Dexuan Cui, Wei Liu, Haiyang Zhang, K. Y. Srinivasan, Andrew Lunn,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Konstantin Taranov, Simon Horman, Leon Romanovsky, Maxim Levitsky,
Erni Sri Satya Vennela, Peter Zijlstra, Michael Kelley
Cc: Shradha Gupta, linux-hyperv, linux-pci, linux-kernel, Nipun Gupta,
Yury Norov, Jason Gunthorpe, Jonathan Cameron, Anna-Maria Behnsen,
Kevin Tian, Long Li, Thomas Gleixner, Bjorn Helgaas, Rob Herring,
Manivannan Sadhasivam, Krzysztof Wilczy�~Dski,
Lorenzo Pieralisi, netdev, linux-rdma, Paul Rosswurm,
Shradha Gupta
In-Reply-To: <1749650984-9193-1-git-send-email-shradhagupta@linux.microsoft.com>
Currently, the MANA driver allocates MSI-X vectors statically based on
MANA_MAX_NUM_QUEUES and num_online_cpus() values and in some cases ends
up allocating more vectors than it needs. This is because, by this time
we do not have a HW channel and do not know how many IRQs should be
allocated.
To avoid this, we allocate 1 MSI-X vector during the creation of HWC and
after getting the value supported by hardware, dynamically add the
remaining MSI-X vectors.
Signed-off-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
---
Changes in v5:
* Correctly initialized start_irqs, so that it is cleaned properly
* rearranged the cpu_lock to minimize the critical section
---
Changes in v4:
* added BUG_ON at appropriate places
* moved xa_destroy to mana_gd_remove()
* rearragned the cleanup logic in mana_gd_setup_dyn_irqs()
* simplified processing around start_irq_index in mana_gd_setup_irqs()
* return 0 instead of return err as appropriate
---
Changes in v3:
* implemented irq_contexts as xarrays rather than list
* split the patch to create a perparation patch around irq_setup()
* add log when IRQ allocation/setup for remaining IRQs fails
---
Changes in v2:
* Use string 'MSI-X vectors' instead of 'pci vectors'
* make skip-cpu a bool instead of int
* rearrange the comment arout skip_cpu variable appropriately
* update the capability bit for driver indicating dynamic IRQ
* allocation
* enforced max line length to 80
* enforced RCT convention
* initialized gic to NULL, for when there is a possibility of gic
not being populated correctly
---
.../net/ethernet/microsoft/mana/gdma_main.c | 311 +++++++++++++-----
include/net/mana/gdma.h | 8 +-
2 files changed, 235 insertions(+), 84 deletions(-)
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 6e468c0f2c40..d0040c12b8a2 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -6,6 +6,8 @@
#include <linux/pci.h>
#include <linux/utsname.h>
#include <linux/version.h>
+#include <linux/msi.h>
+#include <linux/irqdomain.h>
#include <net/mana/mana.h>
@@ -80,8 +82,15 @@ static int mana_gd_query_max_resources(struct pci_dev *pdev)
return err ? err : -EPROTO;
}
- if (gc->num_msix_usable > resp.max_msix)
- gc->num_msix_usable = resp.max_msix;
+ if (!pci_msix_can_alloc_dyn(pdev)) {
+ if (gc->num_msix_usable > resp.max_msix)
+ gc->num_msix_usable = resp.max_msix;
+ } else {
+ /* If dynamic allocation is enabled we have already allocated
+ * hwc msi
+ */
+ gc->num_msix_usable = min(resp.max_msix, num_online_cpus() + 1);
+ }
if (gc->num_msix_usable <= 1)
return -ENOSPC;
@@ -483,7 +492,9 @@ static int mana_gd_register_irq(struct gdma_queue *queue,
}
queue->eq.msix_index = msi_index;
- gic = &gc->irq_contexts[msi_index];
+ gic = xa_load(&gc->irq_contexts, msi_index);
+ if (WARN_ON(!gic))
+ return -EINVAL;
spin_lock_irqsave(&gic->lock, flags);
list_add_rcu(&queue->entry, &gic->eq_list);
@@ -508,7 +519,10 @@ static void mana_gd_deregiser_irq(struct gdma_queue *queue)
if (WARN_ON(msix_index >= gc->num_msix_usable))
return;
- gic = &gc->irq_contexts[msix_index];
+ gic = xa_load(&gc->irq_contexts, msix_index);
+ if (WARN_ON(!gic))
+ return;
+
spin_lock_irqsave(&gic->lock, flags);
list_for_each_entry_rcu(eq, &gic->eq_list, entry) {
if (queue == eq) {
@@ -1366,47 +1380,108 @@ static int irq_setup(unsigned int *irqs, unsigned int len, int node,
return 0;
}
-static int mana_gd_setup_irqs(struct pci_dev *pdev)
+static int mana_gd_setup_dyn_irqs(struct pci_dev *pdev, int nvec)
{
struct gdma_context *gc = pci_get_drvdata(pdev);
- unsigned int max_queues_per_port;
struct gdma_irq_context *gic;
- unsigned int max_irqs, cpu;
- int start_irq_index = 1;
- int nvec, *irqs, irq;
- int err, i = 0, j;
+ bool skip_first_cpu = false;
+ int *irqs, irq, err, i;
- cpus_read_lock();
- max_queues_per_port = num_online_cpus();
- if (max_queues_per_port > MANA_MAX_NUM_QUEUES)
- max_queues_per_port = MANA_MAX_NUM_QUEUES;
+ irqs = kmalloc_array(nvec, sizeof(int), GFP_KERNEL);
+ if (!irqs)
+ return -ENOMEM;
+
+ /*
+ * While processing the next pci irq vector, we start with index 1,
+ * as IRQ vector at index 0 is already processed for HWC.
+ * However, the population of irqs array starts with index 0, to be
+ * further used in irq_setup()
+ */
+ for (i = 1; i <= nvec; i++) {
+ gic = kzalloc(sizeof(*gic), GFP_KERNEL);
+ 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);
- /* Need 1 interrupt for the Hardware communication Channel (HWC) */
- max_irqs = max_queues_per_port + 1;
+ snprintf(gic->name, MANA_IRQ_NAME_SZ, "mana_q%d@pci:%s",
+ i - 1, pci_name(pdev));
- nvec = pci_alloc_irq_vectors(pdev, 2, max_irqs, PCI_IRQ_MSIX);
- if (nvec < 0) {
- cpus_read_unlock();
- return nvec;
+ /* 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);
}
- if (nvec <= num_online_cpus())
- start_irq_index = 0;
- irqs = kmalloc_array((nvec - start_irq_index), sizeof(int), GFP_KERNEL);
- if (!irqs) {
- err = -ENOMEM;
- goto free_irq_vector;
+ /*
+ * When calling irq_setup() for dynamically added IRQs, if number of
+ * CPUs is more than or equal to allocated MSI-X, we need to skip the
+ * first CPU sibling group since they are already affinitized to HWC IRQ
+ */
+ cpus_read_lock();
+ if (gc->num_msix_usable <= num_online_cpus())
+ skip_first_cpu = true;
+
+ err = irq_setup(irqs, nvec, gc->numa_node, skip_first_cpu);
+ if (err) {
+ cpus_read_unlock();
+ goto free_irq;
}
- gc->irq_contexts = kcalloc(nvec, sizeof(struct gdma_irq_context),
- GFP_KERNEL);
- if (!gc->irq_contexts) {
- err = -ENOMEM;
- goto free_irq_array;
+ cpus_read_unlock();
+ 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);
}
+ kfree(irqs);
+ return err;
+}
+
+static int mana_gd_setup_irqs(struct pci_dev *pdev, int nvec)
+{
+ struct gdma_context *gc = pci_get_drvdata(pdev);
+ struct gdma_irq_context *gic;
+ int *irqs, *start_irqs, irq;
+ unsigned int cpu;
+ int err, i;
+
+ irqs = kmalloc_array(nvec, sizeof(int), GFP_KERNEL);
+ if (!irqs)
+ return -ENOMEM;
+
+ start_irqs = irqs;
for (i = 0; i < nvec; i++) {
- gic = &gc->irq_contexts[i];
+ gic = kzalloc(sizeof(*gic), GFP_KERNEL);
+ 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);
@@ -1418,69 +1493,128 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev)
snprintf(gic->name, MANA_IRQ_NAME_SZ, "mana_q%d@pci:%s",
i - 1, pci_name(pdev));
- irq = pci_irq_vector(pdev, i);
- if (irq < 0) {
- err = irq;
- goto free_irq;
+ irqs[i] = pci_irq_vector(pdev, i);
+ if (irqs[i] < 0) {
+ err = irqs[i];
+ goto free_current_gic;
}
- if (!i) {
- err = request_irq(irq, mana_gd_intr, 0, gic->name, gic);
- if (err)
- goto free_irq;
-
- /* If number of IRQ is one extra than number of online CPUs,
- * then we need to assign IRQ0 (hwc irq) and IRQ1 to
- * same CPU.
- * Else we will use different CPUs for IRQ0 and IRQ1.
- * Also we are using cpumask_local_spread instead of
- * cpumask_first for the node, because the node can be
- * mem only.
- */
- if (start_irq_index) {
- cpu = cpumask_local_spread(i, gc->numa_node);
- irq_set_affinity_and_hint(irq, cpumask_of(cpu));
- } else {
- irqs[start_irq_index] = irq;
- }
- } else {
- irqs[i - start_irq_index] = irq;
- err = request_irq(irqs[i - start_irq_index], mana_gd_intr, 0,
- gic->name, gic);
- if (err)
- goto free_irq;
- }
+ 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);
}
- err = irq_setup(irqs, nvec - start_irq_index, gc->numa_node, false);
- if (err)
+ /* If number of IRQ is one extra than number of online CPUs,
+ * then we need to assign IRQ0 (hwc irq) and IRQ1 to
+ * same CPU.
+ * Else we will use different CPUs for IRQ0 and IRQ1.
+ * Also we are using cpumask_local_spread instead of
+ * cpumask_first for the node, because the node can be
+ * mem only.
+ */
+ cpus_read_lock();
+ if (nvec > num_online_cpus()) {
+ cpu = cpumask_local_spread(0, gc->numa_node);
+ irq_set_affinity_and_hint(irqs[0], cpumask_of(cpu));
+ irqs++;
+ nvec -= 1;
+ }
+
+ err = irq_setup(irqs, nvec, gc->numa_node, false);
+ if (err) {
+ cpus_read_unlock();
goto free_irq;
+ }
- gc->max_num_msix = nvec;
- gc->num_msix_usable = nvec;
cpus_read_unlock();
- kfree(irqs);
+ kfree(start_irqs);
return 0;
+free_current_gic:
+ kfree(gic);
free_irq:
- for (j = i - 1; j >= 0; j--) {
- irq = pci_irq_vector(pdev, j);
- gic = &gc->irq_contexts[j];
+ 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);
}
- kfree(gc->irq_contexts);
- gc->irq_contexts = NULL;
-free_irq_array:
- kfree(irqs);
-free_irq_vector:
- cpus_read_unlock();
- pci_free_irq_vectors(pdev);
+ kfree(start_irqs);
return err;
}
+static int mana_gd_setup_hwc_irqs(struct pci_dev *pdev)
+{
+ struct gdma_context *gc = pci_get_drvdata(pdev);
+ unsigned int max_irqs, min_irqs;
+ int nvec, err;
+
+ if (pci_msix_can_alloc_dyn(pdev)) {
+ max_irqs = 1;
+ min_irqs = 1;
+ } else {
+ /* Need 1 interrupt for HWC */
+ max_irqs = min(num_online_cpus(), MANA_MAX_NUM_QUEUES) + 1;
+ min_irqs = 2;
+ }
+
+ nvec = pci_alloc_irq_vectors(pdev, min_irqs, max_irqs, PCI_IRQ_MSIX);
+ if (nvec < 0)
+ return nvec;
+
+ err = mana_gd_setup_irqs(pdev, nvec);
+ if (err) {
+ pci_free_irq_vectors(pdev);
+ return err;
+ }
+
+ gc->num_msix_usable = nvec;
+ gc->max_num_msix = nvec;
+
+ return 0;
+}
+
+static int mana_gd_setup_remaining_irqs(struct pci_dev *pdev)
+{
+ struct gdma_context *gc = pci_get_drvdata(pdev);
+ struct msi_map irq_map;
+ int max_irqs, i, err;
+
+ if (!pci_msix_can_alloc_dyn(pdev))
+ /* remain irqs are already allocated with HWC IRQ */
+ return 0;
+
+ /* allocate only remaining IRQs*/
+ max_irqs = gc->num_msix_usable - 1;
+
+ for (i = 1; i <= max_irqs; i++) {
+ irq_map = pci_msix_alloc_irq_at(pdev, i, NULL);
+ if (!irq_map.virq) {
+ err = irq_map.index;
+ /* caller will handle cleaning up all allocated
+ * irqs, after HWC is destroyed
+ */
+ return err;
+ }
+ }
+
+ err = mana_gd_setup_dyn_irqs(pdev, max_irqs);
+ if (err)
+ return err;
+
+ gc->max_num_msix = gc->max_num_msix + max_irqs;
+
+ return 0;
+}
+
static void mana_gd_remove_irqs(struct pci_dev *pdev)
{
struct gdma_context *gc = pci_get_drvdata(pdev);
@@ -1495,19 +1629,21 @@ static void mana_gd_remove_irqs(struct pci_dev *pdev)
if (irq < 0)
continue;
- gic = &gc->irq_contexts[i];
+ gic = xa_load(&gc->irq_contexts, i);
+ if (WARN_ON(!gic))
+ continue;
/* Need to clear the hint before free_irq */
irq_update_affinity_hint(irq, NULL);
free_irq(irq, gic);
+ xa_erase(&gc->irq_contexts, i);
+ kfree(gic);
}
pci_free_irq_vectors(pdev);
gc->max_num_msix = 0;
gc->num_msix_usable = 0;
- kfree(gc->irq_contexts);
- gc->irq_contexts = NULL;
}
static int mana_gd_setup(struct pci_dev *pdev)
@@ -1522,9 +1658,10 @@ static int mana_gd_setup(struct pci_dev *pdev)
if (!gc->service_wq)
return -ENOMEM;
- err = mana_gd_setup_irqs(pdev);
+ err = mana_gd_setup_hwc_irqs(pdev);
if (err) {
- dev_err(gc->dev, "Failed to setup IRQs: %d\n", err);
+ dev_err(gc->dev, "Failed to setup IRQs for HWC creation: %d\n",
+ err);
goto free_workqueue;
}
@@ -1540,6 +1677,12 @@ static int mana_gd_setup(struct pci_dev *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);
if (err)
goto destroy_hwc;
@@ -1620,6 +1763,7 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
gc->is_pf = mana_is_pf(pdev->device);
gc->bar0_va = bar0_va;
gc->dev = &pdev->dev;
+ xa_init(&gc->irq_contexts);
if (gc->is_pf)
gc->mana_pci_debugfs = debugfs_create_dir("0", mana_debugfs_root);
@@ -1654,6 +1798,7 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
*/
debugfs_remove_recursive(gc->mana_pci_debugfs);
gc->mana_pci_debugfs = NULL;
+ xa_destroy(&gc->irq_contexts);
pci_iounmap(pdev, bar0_va);
free_gc:
pci_set_drvdata(pdev, NULL);
@@ -1679,6 +1824,8 @@ static void mana_gd_remove(struct pci_dev *pdev)
gc->mana_pci_debugfs = NULL;
+ xa_destroy(&gc->irq_contexts);
+
pci_iounmap(pdev, gc->bar0_va);
vfree(gc);
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index 3ce56a816425..87162ba96d91 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -388,7 +388,7 @@ struct gdma_context {
unsigned int max_num_queues;
unsigned int max_num_msix;
unsigned int num_msix_usable;
- struct gdma_irq_context *irq_contexts;
+ struct xarray irq_contexts;
/* L2 MTU */
u16 adapter_mtu;
@@ -578,12 +578,16 @@ enum {
/* Driver can handle holes (zeros) in the device list */
#define GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP BIT(11)
+/* Driver supports dynamic MSI-X vector allocation */
+#define GDMA_DRV_CAP_FLAG_1_DYNAMIC_IRQ_ALLOC_SUPPORT BIT(13)
+
#define GDMA_DRV_CAP_FLAGS1 \
(GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT | \
GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX | \
GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG | \
GDMA_DRV_CAP_FLAG_1_VARIABLE_INDIRECTION_TABLE_SUPPORT | \
- GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP)
+ GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP | \
+ GDMA_DRV_CAP_FLAG_1_DYNAMIC_IRQ_ALLOC_SUPPORT)
#define GDMA_DRV_CAP_FLAGS2 0
--
2.34.1
^ permalink raw reply related
* [PATCH net-next 9/9] net: drv: hyperv: migrate to new RXFH callbacks
From: Jakub Kicinski @ 2025-06-11 14:59 UTC (permalink / raw)
To: davem
Cc: netdev, edumazet, pabeni, andrew+netdev, horms, ecree.xilinx,
Jakub Kicinski, kys, haiyangz, wei.liu, decui, linux-hyperv
In-Reply-To: <20250611145949.2674086-1-kuba@kernel.org>
Add support for the new rxfh_fields callbacks, instead of de-muxing
the rxnfc calls. This driver does not support flow filtering so
the set_rxnfc callback is completely removed.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
CC: kys@microsoft.com
CC: haiyangz@microsoft.com
CC: wei.liu@kernel.org
CC: decui@microsoft.com
CC: linux-hyperv@vger.kernel.org
---
drivers/net/hyperv/netvsc_drv.c | 30 +++++++++++-------------------
1 file changed, 11 insertions(+), 19 deletions(-)
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index c41a025c66f0..42d98e99566e 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -1580,9 +1580,10 @@ static void netvsc_get_strings(struct net_device *dev, u32 stringset, u8 *data)
}
static int
-netvsc_get_rss_hash_opts(struct net_device_context *ndc,
- struct ethtool_rxnfc *info)
+netvsc_get_rxfh_fields(struct net_device *ndev,
+ struct ethtool_rxfh_fields *info)
{
+ struct net_device_context *ndc = netdev_priv(ndev);
const u32 l4_flag = RXH_L4_B_0_1 | RXH_L4_B_2_3;
info->data = RXH_IP_SRC | RXH_IP_DST;
@@ -1637,16 +1638,17 @@ netvsc_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info,
case ETHTOOL_GRXRINGS:
info->data = nvdev->num_chn;
return 0;
-
- case ETHTOOL_GRXFH:
- return netvsc_get_rss_hash_opts(ndc, info);
}
return -EOPNOTSUPP;
}
-static int netvsc_set_rss_hash_opts(struct net_device_context *ndc,
- struct ethtool_rxnfc *info)
+static int
+netvsc_set_rxfh_fields(struct net_device *dev,
+ const struct ethtool_rxfh_fields *info,
+ struct netlink_ext_ack *extack)
{
+ struct net_device_context *ndc = netdev_priv(dev);
+
if (info->data == (RXH_IP_SRC | RXH_IP_DST |
RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
switch (info->flow_type) {
@@ -1701,17 +1703,6 @@ static int netvsc_set_rss_hash_opts(struct net_device_context *ndc,
return -EOPNOTSUPP;
}
-static int
-netvsc_set_rxnfc(struct net_device *ndev, struct ethtool_rxnfc *info)
-{
- struct net_device_context *ndc = netdev_priv(ndev);
-
- if (info->cmd == ETHTOOL_SRXFH)
- return netvsc_set_rss_hash_opts(ndc, info);
-
- return -EOPNOTSUPP;
-}
-
static u32 netvsc_get_rxfh_key_size(struct net_device *dev)
{
return NETVSC_HASH_KEYLEN;
@@ -1979,11 +1970,12 @@ static const struct ethtool_ops ethtool_ops = {
.set_channels = netvsc_set_channels,
.get_ts_info = ethtool_op_get_ts_info,
.get_rxnfc = netvsc_get_rxnfc,
- .set_rxnfc = netvsc_set_rxnfc,
.get_rxfh_key_size = netvsc_get_rxfh_key_size,
.get_rxfh_indir_size = netvsc_rss_indir_size,
.get_rxfh = netvsc_get_rxfh,
.set_rxfh = netvsc_set_rxfh,
+ .get_rxfh_fields = netvsc_get_rxfh_fields,
+ .set_rxfh_fields = netvsc_set_rxfh_fields,
.get_link_ksettings = netvsc_get_link_ksettings,
.set_link_ksettings = netvsc_set_link_ksettings,
.get_ringparam = netvsc_get_ringparam,
--
2.49.0
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox