* [PATCH v3 7/7] net/netvsc: handle VF recovery events for service reset
From: Long Li @ 2026-05-15 19:28 UTC (permalink / raw)
To: dev, Wei Hu, Stephen Hemminger; +Cc: Long Li
In-Reply-To: <20260515192843.552762-1-longli@microsoft.com>
Register callbacks for RTE_ETH_EVENT_ERR_RECOVERING,
RTE_ETH_EVENT_RECOVERY_SUCCESS, and RTE_ETH_EVENT_RECOVERY_FAILED
events on the VF port to handle MANA service resets.
- On ERR_RECOVERING: defer data path switch to synthetic via
rte_eal_alarm_set, keeping VF attached in DPDK
- On RECOVERY_SUCCESS: defer data path switch back to VF
- On RECOVERY_FAILED: do full VF removal (same as INTR_RMV)
- Unregister all recovery callbacks and cancel pending alarms
during detach, removal, and close
All recovery callbacks defer work via rte_eal_alarm_set, consistent
with the existing INTR_RMV pattern, to avoid cross-driver lock-order
assumptions in event-callback context.
This ensures that during a service reset (kernel suspend/resume
without PCI remove), netvsc keeps the VF attached and seamlessly
switches back to it after recovery, without requiring a PCI
hot-add event.
This change is compatible with the current behavior when no
service reset messages are received.
Signed-off-by: Long Li <longli@microsoft.com>
---
v3:
- Deferred recovering and recovery_success callbacks via
rte_eal_alarm_set, consistent with INTR_RMV pattern
- Dropped unlocked vf_attached guard in recovery_failed
- Cancel new deferred alarms in hn_vf_close
v2:
- Added dev_started check in recovery_success
- Added vf_attached guard in recovery_failed
- Added comment explaining direct lock acquisition
drivers/net/netvsc/hn_vf.c | 165 +++++++++++++++++++++++++++++++++++++
1 file changed, 165 insertions(+)
diff --git a/drivers/net/netvsc/hn_vf.c b/drivers/net/netvsc/hn_vf.c
index c83cc973fd..27c46ce404 100644
--- a/drivers/net/netvsc/hn_vf.c
+++ b/drivers/net/netvsc/hn_vf.c
@@ -50,6 +50,13 @@ static int hn_vf_match(const struct rte_eth_dev *dev)
}
+static int hn_eth_recovering_callback(uint16_t port_id,
+ enum rte_eth_event_type event, void *cb_arg, void *out);
+static int hn_eth_recovery_success_callback(uint16_t port_id,
+ enum rte_eth_event_type event, void *cb_arg, void *out);
+static int hn_eth_recovery_failed_callback(uint16_t port_id,
+ enum rte_eth_event_type event, void *cb_arg, void *out);
+
/*
* Attach new PCI VF device and return the port_id
*/
@@ -111,7 +118,56 @@ static int hn_vf_attach(struct rte_eth_dev *dev, struct hn_data *hv)
return ret;
}
+ /* Register recovery event callbacks for service reset handling */
+ ret = rte_eth_dev_callback_register(hv->vf_ctx.vf_port,
+ RTE_ETH_EVENT_ERR_RECOVERING,
+ hn_eth_recovering_callback, hv);
+ if (ret) {
+ PMD_DRV_LOG(ERR,
+ "Registering recovering callback failed for vf port %d ret %d",
+ port, ret);
+ goto err_recovering;
+ }
+
+ ret = rte_eth_dev_callback_register(hv->vf_ctx.vf_port,
+ RTE_ETH_EVENT_RECOVERY_SUCCESS,
+ hn_eth_recovery_success_callback, hv);
+ if (ret) {
+ PMD_DRV_LOG(ERR,
+ "Registering recovery success callback failed for vf port %d ret %d",
+ port, ret);
+ goto err_recovery_success;
+ }
+
+ ret = rte_eth_dev_callback_register(hv->vf_ctx.vf_port,
+ RTE_ETH_EVENT_RECOVERY_FAILED,
+ hn_eth_recovery_failed_callback, hv);
+ if (ret) {
+ PMD_DRV_LOG(ERR,
+ "Registering recovery failed callback failed for vf port %d ret %d",
+ port, ret);
+ goto err_recovery_failed;
+ }
+
return 0;
+
+err_recovery_failed:
+ rte_eth_dev_callback_unregister(hv->vf_ctx.vf_port,
+ RTE_ETH_EVENT_RECOVERY_SUCCESS,
+ hn_eth_recovery_success_callback, hv);
+err_recovery_success:
+ rte_eth_dev_callback_unregister(hv->vf_ctx.vf_port,
+ RTE_ETH_EVENT_ERR_RECOVERING,
+ hn_eth_recovering_callback, hv);
+err_recovering:
+ rte_eth_dev_callback_unregister(hv->vf_ctx.vf_port,
+ RTE_ETH_EVENT_INTR_RMV,
+ hn_eth_rmv_event_callback, hv);
+ hv->vf_ctx.vf_attached = false;
+ hv->vf_ctx.vf_port = 0;
+ if (rte_eth_dev_owner_unset(port, hv->owner.id) < 0)
+ PMD_DRV_LOG(ERR, "Failed to unset owner for port %d", port);
+ return ret;
}
static void hn_vf_remove_unlocked(struct hn_data *hv);
@@ -143,6 +199,12 @@ static void hn_remove_delayed(void *args)
PMD_DRV_LOG(ERR,
"rte_eth_dev_callback_unregister failed ret=%d",
ret);
+ rte_eth_dev_callback_unregister(port_id, RTE_ETH_EVENT_ERR_RECOVERING,
+ hn_eth_recovering_callback, hv);
+ rte_eth_dev_callback_unregister(port_id, RTE_ETH_EVENT_RECOVERY_SUCCESS,
+ hn_eth_recovery_success_callback, hv);
+ rte_eth_dev_callback_unregister(port_id, RTE_ETH_EVENT_RECOVERY_FAILED,
+ hn_eth_recovery_failed_callback, hv);
/* Detach and release port_id from system */
ret = rte_eth_dev_stop(port_id);
@@ -187,6 +249,89 @@ int hn_eth_rmv_event_callback(uint16_t port_id,
return 0;
}
+/*
+ * Deferred handler for VF error recovery event.
+ * Switch data path to synthetic but keep the VF attached.
+ */
+static void hn_recovering_delayed(void *args)
+{
+ struct hn_data *hv = args;
+
+ rte_rwlock_write_lock(&hv->vf_lock);
+ hn_vf_remove_unlocked(hv);
+ rte_rwlock_write_unlock(&hv->vf_lock);
+}
+
+static int
+hn_eth_recovering_callback(uint16_t port_id,
+ enum rte_eth_event_type event __rte_unused,
+ void *cb_arg, void *out __rte_unused)
+{
+ struct hn_data *hv = cb_arg;
+
+ PMD_DRV_LOG(NOTICE, "VF port %u recovering from error", port_id);
+ rte_eal_alarm_set(1, hn_recovering_delayed, hv);
+
+ return 0;
+}
+
+/*
+ * Deferred handler for VF recovery success event.
+ * Switch data path back to VF.
+ */
+static void hn_recovery_success_delayed(void *args)
+{
+ struct hn_data *hv = args;
+ struct rte_eth_dev *dev = &rte_eth_devices[hv->port_id];
+ int ret;
+
+ rte_rwlock_write_lock(&hv->vf_lock);
+ /* Only switch data path to VF if the netvsc device is started,
+ * mirroring the check in hn_vf_add_unlocked. If the device was
+ * stopped during recovery, defer to hn_vf_start().
+ */
+ if (dev->data->dev_started &&
+ hv->vf_ctx.vf_attached && !hv->vf_ctx.vf_vsc_switched) {
+ ret = hn_nvs_set_datapath(hv, NVS_DATAPATH_VF);
+ if (ret)
+ PMD_DRV_LOG(ERR,
+ "Failed to switch to VF after recovery");
+ else
+ hv->vf_ctx.vf_vsc_switched = true;
+ }
+ rte_rwlock_write_unlock(&hv->vf_lock);
+}
+
+static int
+hn_eth_recovery_success_callback(uint16_t port_id,
+ enum rte_eth_event_type event __rte_unused,
+ void *cb_arg, void *out __rte_unused)
+{
+ struct hn_data *hv = cb_arg;
+
+ PMD_DRV_LOG(NOTICE, "VF port %u recovery succeeded", port_id);
+ rte_eal_alarm_set(1, hn_recovery_success_delayed, hv);
+
+ return 0;
+}
+
+/*
+ * Handle VF recovery failure event from MANA PMD.
+ * VF is unusable, do full removal.
+ */
+static int
+hn_eth_recovery_failed_callback(uint16_t port_id,
+ enum rte_eth_event_type event __rte_unused,
+ void *cb_arg, void *out __rte_unused)
+{
+ struct hn_data *hv = cb_arg;
+
+ PMD_DRV_LOG(NOTICE, "VF port %u recovery failed, removing", port_id);
+ rte_eal_alarm_set(1, hn_remove_delayed, hv);
+
+ return 0;
+}
+
static int hn_setup_vf_queues(int port, struct rte_eth_dev *dev)
{
struct hn_rx_queue *rx_queue;
@@ -247,6 +392,12 @@ static void hn_vf_detach(struct hn_data *hv)
rte_eth_dev_callback_unregister(port, RTE_ETH_EVENT_INTR_RMV,
hn_eth_rmv_event_callback, hv);
+ rte_eth_dev_callback_unregister(port, RTE_ETH_EVENT_ERR_RECOVERING,
+ hn_eth_recovering_callback, hv);
+ rte_eth_dev_callback_unregister(port, RTE_ETH_EVENT_RECOVERY_SUCCESS,
+ hn_eth_recovery_success_callback, hv);
+ rte_eth_dev_callback_unregister(port, RTE_ETH_EVENT_RECOVERY_FAILED,
+ hn_eth_recovery_failed_callback, hv);
if (rte_eth_dev_owner_unset(port, hv->owner.id) < 0)
PMD_DRV_LOG(ERR, "Failed to unset owner for port %d", port);
@@ -630,7 +781,21 @@ int hn_vf_close(struct rte_eth_dev *dev)
RTE_ETH_EVENT_INTR_RMV,
hn_eth_rmv_event_callback,
hv);
+ rte_eth_dev_callback_unregister(hv->vf_ctx.vf_port,
+ RTE_ETH_EVENT_ERR_RECOVERING,
+ hn_eth_recovering_callback,
+ hv);
+ rte_eth_dev_callback_unregister(hv->vf_ctx.vf_port,
+ RTE_ETH_EVENT_RECOVERY_SUCCESS,
+ hn_eth_recovery_success_callback,
+ hv);
+ rte_eth_dev_callback_unregister(hv->vf_ctx.vf_port,
+ RTE_ETH_EVENT_RECOVERY_FAILED,
+ hn_eth_recovery_failed_callback,
+ hv);
rte_eal_alarm_cancel(hn_remove_delayed, hv);
+ rte_eal_alarm_cancel(hn_recovering_delayed, hv);
+ rte_eal_alarm_cancel(hn_recovery_success_delayed, hv);
ret = rte_eth_dev_close(hv->vf_ctx.vf_port);
hv->vf_ctx.vf_attached = false;
}
--
2.43.0
^ permalink raw reply related
* [PATCH v3 6/7] net/netvsc: forward per-queue stats from VF device
From: Long Li @ 2026-05-15 19:28 UTC (permalink / raw)
To: dev, Wei Hu, Stephen Hemminger; +Cc: Long Li, stable
In-Reply-To: <20260515192843.552762-1-longli@microsoft.com>
hn_vf_stats_get was ignoring the qstats parameter (__rte_unused),
calling rte_eth_stats_get which only collects aggregate stats. This
meant per-queue stats (rx_q0_good_packets, tx_q0_good_packets, etc.)
were always zero when VF datapath was active, even though the
underlying MANA driver populates them in its stats_get callback.
Call the VF device's stats_get op directly with the qstats pointer
so per-queue counters are forwarded through netvsc to the xstats
telemetry output.
Fixes: dc7680e8597c ("net/netvsc: support integrated VF")
Cc: stable@dpdk.org
Signed-off-by: Long Li <longli@microsoft.com>
---
v3:
- Removed dead -ENOTSUP fallback to rte_eth_stats_get,
replaced with direct -ENOTSUP return
- Documented caller contract for zeroed buffers
v2:
- Added comment for direct dev_ops call
- Added -ENOTSUP fallback
drivers/net/netvsc/hn_vf.c | 17 ++++++++++++++---
1 file changed, 14 insertions(+), 3 deletions(-)
diff --git a/drivers/net/netvsc/hn_vf.c b/drivers/net/netvsc/hn_vf.c
index 1fcc65a712..c83cc973fd 100644
--- a/drivers/net/netvsc/hn_vf.c
+++ b/drivers/net/netvsc/hn_vf.c
@@ -749,7 +749,7 @@ void hn_vf_rx_queue_release(struct hn_data *hv, uint16_t queue_id)
int hn_vf_stats_get(struct rte_eth_dev *dev,
struct rte_eth_stats *stats,
- struct eth_queue_stats *qstats __rte_unused)
+ struct eth_queue_stats *qstats)
{
struct hn_data *hv = dev->data->dev_private;
struct rte_eth_dev *vf_dev;
@@ -757,8 +757,19 @@ int hn_vf_stats_get(struct rte_eth_dev *dev,
rte_rwlock_read_lock(&hv->vf_lock);
vf_dev = hn_get_vf_dev(hv);
- if (vf_dev)
- ret = rte_eth_stats_get(vf_dev->data->port_id, stats);
+ if (vf_dev) {
+ /* Call dev_ops->stats_get directly instead of the public
+ * rte_eth_stats_get API because we need to forward the
+ * per-queue stats (qstats) which the public API does not
+ * support. The caller (eth_stats_qstats_get) has already
+ * zeroed stats and qstats before invoking this callback.
+ */
+ if (vf_dev->dev_ops->stats_get != NULL)
+ ret = vf_dev->dev_ops->stats_get(vf_dev, stats,
+ qstats);
+ else
+ ret = -ENOTSUP;
+ }
rte_rwlock_read_unlock(&hv->vf_lock);
return ret;
}
--
2.43.0
^ permalink raw reply related
* [PATCH v3 5/7] net/netvsc: retry when no matching MAC found in net directory
From: Long Li @ 2026-05-15 19:28 UTC (permalink / raw)
To: dev, Wei Hu, Stephen Hemminger; +Cc: Long Li, stable
In-Reply-To: <20260515192843.552762-1-longli@microsoft.com>
On multi-NIC Azure VMs, a single MANA PCI device (7870:00:00.0) hosts
multiple VF interfaces. After PCI rescan, these interfaces register
at different times — the management NIC's VF appears first, followed
by the test NIC's VF.
Previously, when netvsc_hotplug_retry scanned the net/ directory and
found interfaces with non-matching MACs, it would exit the readdir
loop and free the hotadd context, permanently giving up. The matching
VF interface had not appeared yet.
Now, when the readdir loop ends without finding a matching MAC (dir
is NULL after loop), schedule another retry instead of giving up.
This uses a separate mac_retry counter (limit 120, ~2 minutes) so
the main retry loop remains unlimited.
Fixes: a2a23a794b3a ("net/netvsc: support VF device hot add/remove")
Cc: stable@dpdk.org
Signed-off-by: Long Li <longli@microsoft.com>
---
v3: no change
v2:
- Fixed commit message (limit 120 not 30)
- Changed mac_retry log to DEBUG
- Explicit NULL comparisons
drivers/net/netvsc/hn_ethdev.c | 36 +++++++++++++++++++++++++++++++++-
drivers/net/netvsc/hn_var.h | 1 +
2 files changed, 36 insertions(+), 1 deletion(-)
diff --git a/drivers/net/netvsc/hn_ethdev.c b/drivers/net/netvsc/hn_ethdev.c
index 16fb2b344d..72743872bb 100644
--- a/drivers/net/netvsc/hn_ethdev.c
+++ b/drivers/net/netvsc/hn_ethdev.c
@@ -92,6 +92,12 @@ struct netvsc_mp_param {
/* Retry interval for hot-add VF device (microseconds) */
#define NETVSC_HOTADD_RETRY_INTERVAL 1000000
+/* Max retries when net/ directory exists but no matching MAC found.
+ * On multi-NIC PCI devices, a second VF may register later.
+ * 120 retries = ~2 minutes.
+ */
+#define NETVSC_MAX_MAC_RETRY 120
+
struct hn_xstats_name_off {
char name[RTE_ETH_XSTATS_NAME_SIZE];
unsigned int offset;
@@ -768,8 +774,36 @@ static void netvsc_hotplug_retry(void *args)
RTE_ETHER_ADDR_BYTES(dev->data->mac_addrs));
}
+ /* If we opened the net directory but didn't find a matching MAC,
+ * the VF interface may not have appeared yet (e.g. on a multi-NIC
+ * PCI device, the second VF registers later). Retry.
+ */
+ if (di != NULL) {
+ closedir(di);
+ di = NULL;
+ if (dir == NULL) {
+ /* readdir returned NULL — loop ended without match */
+ hot_ctx->mac_retry++;
+ if (hot_ctx->mac_retry < NETVSC_MAX_MAC_RETRY) {
+ PMD_DRV_LOG(DEBUG,
+ "%s: no matching MAC found in %s, "
+ "retrying in 1 second (mac_retry %d/%d)",
+ __func__, buf,
+ hot_ctx->mac_retry,
+ NETVSC_MAX_MAC_RETRY);
+ rte_eal_alarm_set(NETVSC_HOTADD_RETRY_INTERVAL,
+ netvsc_hotplug_retry,
+ hot_ctx);
+ return;
+ }
+ PMD_DRV_LOG(NOTICE,
+ "%s: no matching MAC found after %d retries, giving up",
+ __func__, hot_ctx->mac_retry);
+ }
+ }
+
free_hotadd_ctx:
- if (di)
+ if (di != NULL)
closedir(di);
PMD_DRV_LOG(DEBUG, "%s: retry loop exiting for device %s (retry %d)",
diff --git a/drivers/net/netvsc/hn_var.h b/drivers/net/netvsc/hn_var.h
index ef55dee28e..574b909c82 100644
--- a/drivers/net/netvsc/hn_var.h
+++ b/drivers/net/netvsc/hn_var.h
@@ -127,6 +127,7 @@ struct hv_hotadd_context {
struct hn_data *hv;
struct rte_devargs da;
int eal_hot_plug_retry;
+ int mac_retry;
};
struct hn_data {
--
2.43.0
^ permalink raw reply related
* [PATCH v3 4/7] net/netvsc: add debug logging for VF hotplug retry
From: Long Li @ 2026-05-15 19:28 UTC (permalink / raw)
To: dev, Wei Hu, Stephen Hemminger; +Cc: Long Li
In-Reply-To: <20260515192843.552762-1-longli@microsoft.com>
Add detailed DEBUG-level logging at every decision point in the
netvsc_hotplug_retry function to diagnose VF re-attach failures:
- Log each interface found in the net/ directory
- Log when sa_family is not ARPHRD_ETHER
- Log MAC address comparison details on mismatch using
RTE_ETHER_ADDR_PRT_FMT for consistency with the rest of DPDK
- Log when the retry loop exits (with retry count)
Per-iteration trace uses DEBUG level to avoid flooding the log on
multi-NIC VMs with indefinite retries; NOTICE is reserved for
one-shot state transitions.
These logs help correlate DPDK hotplug retry behavior with kernel
dmesg timestamps to identify timing issues during VF re-attach
after PCI rescan on Azure.
Signed-off-by: Long Li <longli@microsoft.com>
---
v3:
- Changed "retry loop exiting" log from NOTICE to DEBUG to
avoid noise on every successful VF re-attach
v2:
- Changed per-iteration logs from NOTICE to DEBUG
- Used RTE_ETHER_ADDR_PRT_FMT macros
drivers/net/netvsc/hn_ethdev.c | 22 +++++++++++++++++++++-
1 file changed, 21 insertions(+), 1 deletion(-)
diff --git a/drivers/net/netvsc/hn_ethdev.c b/drivers/net/netvsc/hn_ethdev.c
index 9e4fc33949..16fb2b344d 100644
--- a/drivers/net/netvsc/hn_ethdev.c
+++ b/drivers/net/netvsc/hn_ethdev.c
@@ -663,6 +663,11 @@ static void netvsc_hotplug_retry(void *args)
if (!strcmp(dir->d_name, ".") || !strcmp(dir->d_name, ".."))
continue;
+ PMD_DRV_LOG(DEBUG,
+ "%s: checking interface %s in %s (retry %d)",
+ __func__, dir->d_name, buf,
+ hot_ctx->eal_hot_plug_retry);
+
/* trying to get mac address if this is a network device*/
s = socket(PF_INET, SOCK_DGRAM, IPPROTO_IP);
if (s == -1) {
@@ -687,8 +692,12 @@ static void netvsc_hotplug_retry(void *args)
netvsc_hotplug_retry, hot_ctx);
return;
}
- if (req.ifr_hwaddr.sa_family != ARPHRD_ETHER)
+ if (req.ifr_hwaddr.sa_family != ARPHRD_ETHER) {
+ PMD_DRV_LOG(DEBUG,
+ "%s: device %s sa_family=%d not ARPHRD_ETHER, skipping",
+ __func__, dir->d_name, req.ifr_hwaddr.sa_family);
continue;
+ }
memcpy(eth_addr.addr_bytes, req.ifr_hwaddr.sa_data,
RTE_DIM(eth_addr.addr_bytes));
@@ -749,12 +758,23 @@ static void netvsc_hotplug_retry(void *args)
PMD_DRV_LOG(ERR, "Failed to add VF: %d", ret);
break;
}
+
+ PMD_DRV_LOG(DEBUG,
+ "%s: MAC mismatch for %s: got "
+ RTE_ETHER_ADDR_PRT_FMT
+ " expected " RTE_ETHER_ADDR_PRT_FMT,
+ __func__, dir->d_name,
+ RTE_ETHER_ADDR_BYTES(ð_addr),
+ RTE_ETHER_ADDR_BYTES(dev->data->mac_addrs));
}
free_hotadd_ctx:
if (di)
closedir(di);
+ PMD_DRV_LOG(DEBUG, "%s: retry loop exiting for device %s (retry %d)",
+ __func__, d->name, hot_ctx->eal_hot_plug_retry);
+
rte_spinlock_lock(&hv->hotadd_lock);
LIST_REMOVE(hot_ctx, list);
rte_spinlock_unlock(&hv->hotadd_lock);
--
2.43.0
^ permalink raw reply related
* [PATCH v3 3/7] net/netvsc: retry full probe when IB device not ready during hotplug
From: Long Li @ 2026-05-15 19:28 UTC (permalink / raw)
To: dev, Wei Hu, Stephen Hemminger; +Cc: Long Li, stable
In-Reply-To: <20260515192843.552762-1-longli@microsoft.com>
When rte_eal_hotplug_add returns -ENODEV during VF hot-add, it means the
MANA IB/verbs device is not yet registered by the mana_ib kernel module.
This happens because the mana_ib auxiliary driver probes asynchronously
after the MANA net driver creates the network interface.
On Azure VMs, the gap between netdev registration and IB device
registration can be several seconds. Previously, netvsc would log the
error and give up after finding the matching MAC address.
Now, on -ENODEV, restart the full retry loop from the PCI device
existence check. This re-scans the net directory to pick up any
interface renames (e.g. eth1 -> ens1) and retries until the IB device
is ready.
The -EEXIST return (device already probed by another netvsc port on the
same PCI device) is handled silently, as hn_vf_add will find the
already-probed VF port.
Fixes: a2a23a794b3a ("net/netvsc: support VF device hot add/remove")
Cc: stable@dpdk.org
Signed-off-by: Long Li <longli@microsoft.com>
---
v3: no change
v2:
- Restored ERR log level for non-ENODEV/non-EEXIST failures
from rte_eal_hotplug_add
- Added comment explaining why ENODEV retry is safe
drivers/net/netvsc/hn_ethdev.c | 29 ++++++++++++++++++++++++-----
1 file changed, 24 insertions(+), 5 deletions(-)
diff --git a/drivers/net/netvsc/hn_ethdev.c b/drivers/net/netvsc/hn_ethdev.c
index 096489d66d..9e4fc33949 100644
--- a/drivers/net/netvsc/hn_ethdev.c
+++ b/drivers/net/netvsc/hn_ethdev.c
@@ -717,17 +717,36 @@ static void netvsc_hotplug_retry(void *args)
* parent device, restore its args.
*/
ret = rte_eal_hotplug_add(d->bus->name, d->name, drv_str ? drv_str : "");
- if (ret) {
- PMD_DRV_LOG(ERR,
- "Failed to add PCI device %s",
+ free(drv_str);
+
+ if (ret == -ENODEV) {
+ /* IB device not ready yet (mana_ib not probed).
+ * Restart the full retry from the PCI device
+ * check so we re-verify the device exists and
+ * get fresh interface names after any renames.
+ * This retries indefinitely — the PCI sysfs
+ * check at the top of this function ensures
+ * we stop if the device disappears.
+ */
+ PMD_DRV_LOG(NOTICE,
+ "IB device not ready for %s, "
+ "restarting probe in 1 second",
d->name);
+ closedir(di);
+ rte_eal_alarm_set(NETVSC_HOTADD_RETRY_INTERVAL,
+ netvsc_hotplug_retry,
+ hot_ctx);
+ return;
}
- free(drv_str);
+ if (ret && ret != -EEXIST)
+ PMD_DRV_LOG(ERR,
+ "Failed to add PCI device %s (ret=%d)",
+ d->name, ret);
ret = hn_vf_add(dev, hv);
if (ret)
- PMD_DRV_LOG(ERR, "Failed to add VF in hotplug retry: %d", ret);
+ PMD_DRV_LOG(ERR, "Failed to add VF: %d", ret);
break;
}
}
--
2.43.0
^ permalink raw reply related
* [PATCH v3 2/7] net/netvsc: retry on SIOCGIFHWADDR failure during VF hotplug
From: Long Li @ 2026-05-15 19:28 UTC (permalink / raw)
To: dev, Wei Hu, Stephen Hemminger; +Cc: Long Li, stable
In-Reply-To: <20260515192843.552762-1-longli@microsoft.com>
When the MANA VF net directory appears after PCI rescan, udev may rename
the interface (e.g. eth1 → ens1) before DPDK can query its MAC address
via SIOCGIFHWADDR. The ioctl fails because the interface name is stale
during the rename window.
Instead of giving up when SIOCGIFHWADDR fails, close the directory and
schedule another retry. The next attempt will re-read the directory with
the updated interface name (e.g. ens1 instead of eth1) and succeed.
This was observed on Azure VMs where the MANA kernel driver takes >30
seconds to probe after PCI rescan, and udev renames the interface
immediately after registration.
Fixes: a2a23a794b3a ("net/netvsc: support VF device hot add/remove")
Cc: stable@dpdk.org
Signed-off-by: Long Li <longli@microsoft.com>
---
v3: no change
v2:
- Changed SIOCGIFHWADDR retry log level from NOTICE to DEBUG
- Updated comment to reference PCI device check as safety bound
drivers/net/netvsc/hn_ethdev.c | 14 +++++++++++---
1 file changed, 11 insertions(+), 3 deletions(-)
diff --git a/drivers/net/netvsc/hn_ethdev.c b/drivers/net/netvsc/hn_ethdev.c
index 85e500c178..096489d66d 100644
--- a/drivers/net/netvsc/hn_ethdev.c
+++ b/drivers/net/netvsc/hn_ethdev.c
@@ -674,10 +674,18 @@ static void netvsc_hotplug_retry(void *args)
ret = ioctl(s, SIOCGIFHWADDR, &req);
close(s);
if (ret == -1) {
- PMD_DRV_LOG(ERR,
- "Failed to send SIOCGIFHWADDR for device %s",
+ /* Interface may be renamed by udev (e.g. eth1 → ens1).
+ * Retry from the top — the PCI device check above
+ * ensures we stop if the device disappears.
+ */
+ PMD_DRV_LOG(DEBUG,
+ "Failed to send SIOCGIFHWADDR for device %s, "
+ "interface may be renaming, retrying",
dir->d_name);
- break;
+ closedir(di);
+ rte_eal_alarm_set(NETVSC_HOTADD_RETRY_INTERVAL,
+ netvsc_hotplug_retry, hot_ctx);
+ return;
}
if (req.ifr_hwaddr.sa_family != ARPHRD_ETHER)
continue;
--
2.43.0
^ permalink raw reply related
* [PATCH v3 1/7] net/netvsc: retry VF hotplug indefinitely until PCI device disappears
From: Long Li @ 2026-05-15 19:28 UTC (permalink / raw)
To: dev, Wei Hu, Stephen Hemminger; +Cc: Long Li, stable
In-Reply-To: <20260515192843.552762-1-longli@microsoft.com>
After PCI rescan on Azure, the MANA kernel driver can take over 100
seconds to probe and create the /sys/bus/pci/devices/<dev>/net directory.
The previous fixed retry limit (NETVSC_MAX_HOTADD_RETRY=10, ~12 seconds)
was insufficient, causing VF re-attach to fail with 'Failed to parse PCI
device' on systems with slow MANA driver initialization.
Replace the fixed retry limit with an indefinite retry that only gives up
when the PCI device itself disappears from sysfs. This is safe because:
- The retry uses rte_eal_alarm callbacks which are serialized on the EAL
interrupt thread, preventing races with VF remove or device close paths.
- Device close (eth_hn_dev_uninit) explicitly cancels all pending hotplug
alarms via rte_eal_alarm_cancel and frees the context.
- If the PCI device is removed while retrying, access() detects the
missing sysfs path and stops immediately.
A periodic NOTICE log every 30 retries (~30s) provides visibility into
long waits without flooding the log at DEBUG level.
Fixes: a2a23a794b3a ("net/netvsc: support VF device hot add/remove")
Cc: stable@dpdk.org
Signed-off-by: Long Li <longli@microsoft.com>
---
v3:
- Wrapped rte_eal_alarm_set lines to stay within 100 columns
(checkpatch line-length warning)
v2:
- Added detailed comment explaining why indefinite retry is
safe (PCI sysfs disappearance is the termination condition)
drivers/net/netvsc/hn_ethdev.c | 41 +++++++++++++++++++++++++---------
1 file changed, 31 insertions(+), 10 deletions(-)
diff --git a/drivers/net/netvsc/hn_ethdev.c b/drivers/net/netvsc/hn_ethdev.c
index b8880edb4c..85e500c178 100644
--- a/drivers/net/netvsc/hn_ethdev.c
+++ b/drivers/net/netvsc/hn_ethdev.c
@@ -89,8 +89,8 @@ struct netvsc_mp_param {
#define NETVSC_ARG_TXBREAK "tx_copybreak"
#define NETVSC_ARG_RX_EXTMBUF_ENABLE "rx_extmbuf_enable"
-/* The max number of retry when hot adding a VF device */
-#define NETVSC_MAX_HOTADD_RETRY 10
+/* Retry interval for hot-add VF device (microseconds) */
+#define NETVSC_HOTADD_RETRY_INTERVAL 1000000
struct hn_xstats_name_off {
char name[RTE_ETH_XSTATS_NAME_SIZE];
@@ -622,19 +622,39 @@ static void netvsc_hotplug_retry(void *args)
PMD_DRV_LOG(DEBUG, "%s: retry count %d",
__func__, hot_ctx->eal_hot_plug_retry);
- if (hot_ctx->eal_hot_plug_retry++ > NETVSC_MAX_HOTADD_RETRY) {
- PMD_DRV_LOG(NOTICE, "Failed to parse PCI device retry=%d",
- hot_ctx->eal_hot_plug_retry);
+ hot_ctx->eal_hot_plug_retry++;
+
+ /* Check if PCI device still exists — if it disappeared, give up.
+ * Otherwise keep retrying indefinitely until the net directory
+ * appears. This is safe because:
+ * - MANA driver probe can take >100s after PCI rescan
+ * - The retry uses rte_eal_alarm callbacks serialized on the
+ * EAL interrupt thread, preventing races with device close
+ * - Device close cancels pending alarms and frees the context
+ * - If the PCI device is removed, the access() check below
+ * detects the missing sysfs path and stops immediately
+ */
+ snprintf(buf, sizeof(buf), "/sys/bus/pci/devices/%s", d->name);
+ if (access(buf, F_OK) != 0) {
+ PMD_DRV_LOG(NOTICE,
+ "PCI device %s no longer exists, giving up after %d retries",
+ d->name, hot_ctx->eal_hot_plug_retry);
goto free_hotadd_ctx;
}
snprintf(buf, sizeof(buf), "/sys/bus/pci/devices/%s/net", d->name);
di = opendir(buf);
if (!di) {
- PMD_DRV_LOG(DEBUG, "%s: can't open directory %s, "
- "retrying in 1 second", __func__, buf);
- /* The device is still being initialized, retry after 1 second */
- rte_eal_alarm_set(1000000, netvsc_hotplug_retry, hot_ctx);
+ if (hot_ctx->eal_hot_plug_retry % 30 == 0)
+ PMD_DRV_LOG(NOTICE,
+ "%s: waiting for %s (retry %d, %ds elapsed)",
+ __func__, buf, hot_ctx->eal_hot_plug_retry,
+ hot_ctx->eal_hot_plug_retry);
+ else
+ PMD_DRV_LOG(DEBUG, "%s: can't open directory %s, "
+ "retrying in 1 second", __func__, buf);
+ rte_eal_alarm_set(NETVSC_HOTADD_RETRY_INTERVAL,
+ netvsc_hotplug_retry, hot_ctx);
return;
}
@@ -758,7 +778,8 @@ netvsc_hotadd_callback(const char *device_name, enum rte_dev_event_type type,
rte_spinlock_lock(&hv->hotadd_lock);
LIST_INSERT_HEAD(&hv->hotadd_list, hot_ctx, list);
rte_spinlock_unlock(&hv->hotadd_lock);
- rte_eal_alarm_set(1000000, netvsc_hotplug_retry, hot_ctx);
+ rte_eal_alarm_set(NETVSC_HOTADD_RETRY_INTERVAL,
+ netvsc_hotplug_retry, hot_ctx);
return;
}
--
2.43.0
^ permalink raw reply related
* [PATCH v3 0/7] net/netvsc: fix VF hotplug and service reset handling
From: Long Li @ 2026-05-15 19:28 UTC (permalink / raw)
To: dev, Wei Hu, Stephen Hemminger; +Cc: Long Li
In-Reply-To: <20260506020529.281654-1-longli@microsoft.com>
This series fixes several issues in the netvsc PMD's VF hot-plug retry
logic and adds support for MANA service reset (suspend/resume) recovery.
Patches 1-5 fix the VF hot-add retry path to handle Azure-specific
timing issues: slow MANA driver probe (>100s), udev interface renames,
asynchronous mana_ib registration, and multi-NIC staggered VF
appearance.
Patch 6 fixes per-queue stats forwarding from VF to netvsc.
Patch 7 adds recovery event handling for MANA service resets, where
the kernel suspends/resumes the VF without PCI remove.
v3:
- Patch 1: wrapped rte_eal_alarm_set lines to fix checkpatch
line-length warning
- Patch 4: changed "retry loop exiting" log from NOTICE to DEBUG
to avoid noise on every successful VF re-attach
- Patch 6: removed dead -ENOTSUP fallback to rte_eth_stats_get,
replaced with direct -ENOTSUP return; documented caller contract
for zeroed buffers
- Patch 7: deferred all recovery callbacks via rte_eal_alarm_set
consistent with INTR_RMV pattern; dropped unlocked vf_attached
guard in recovery_failed; cancel new alarms in hn_vf_close
v2:
- Patch 1: added comment explaining why indefinite retry is safe
- Patch 2: changed SIOCGIFHWADDR retry log to DEBUG
- Patch 3: restored ERR log for non-ENODEV/EEXIST failures
- Patch 4: changed per-iteration logs from NOTICE to DEBUG;
used RTE_ETHER_ADDR_PRT_FMT macros
- Patch 5: fixed commit message (limit 120 not 30); changed
mac_retry log to DEBUG; explicit NULL comparisons
- Patch 6: added comment for direct dev_ops call; added -ENOTSUP
fallback
- Patch 7: added dev_started check in recovery_success; added
vf_attached guard in recovery_failed
Long Li (7):
net/netvsc: retry VF hotplug indefinitely until PCI device disappears
net/netvsc: retry on SIOCGIFHWADDR failure during VF hotplug
net/netvsc: retry full probe when IB device not ready during hotplug
net/netvsc: add debug logging for VF hotplug retry
net/netvsc: retry when no matching MAC found in net directory
net/netvsc: forward per-queue stats from VF device
net/netvsc: handle VF recovery events for service reset
drivers/net/netvsc/hn_ethdev.c | 142 +++++++++++++++++++++----
drivers/net/netvsc/hn_var.h | 1 +
drivers/net/netvsc/hn_vf.c | 182 ++++++++++++++++++++++++++++++++-
3 files changed, 302 insertions(+), 23 deletions(-)
--
2.43.0
^ permalink raw reply
* [PATCH v1] dts: add sleep to trex setup
From: Andrew Bailey @ 2026-05-15 17:47 UTC (permalink / raw)
To: dev, luca.vizzarro, patrickrobb1997
Cc: lylavoie, ahassick, knimoji, Andrew Bailey
Previously, there were some cases where the single core performance test
suite would report zero Mpps. Adding a sleep in between setting up the
TREX generator and sending the packets resolves this issue.
Bugzilla ID: 1946
Fixes: d77d7f04f24c ("dts: add single-core performance test suite")
Signed-off-by: Andrew Bailey <abailey@iol.unh.edu>
---
dts/framework/testbed_model/traffic_generator/trex.py | 1 +
1 file changed, 1 insertion(+)
diff --git a/dts/framework/testbed_model/traffic_generator/trex.py b/dts/framework/testbed_model/traffic_generator/trex.py
index 22cd20dea9..19a71a7dd5 100644
--- a/dts/framework/testbed_model/traffic_generator/trex.py
+++ b/dts/framework/testbed_model/traffic_generator/trex.py
@@ -184,6 +184,7 @@ def _generate_traffic(
"""
self._create_packet_stream(packet)
self._setup_trex_client()
+ time.sleep(1)
stats = self._send_traffic_and_get_stats(duration, send_mpps)
--
2.50.1
^ permalink raw reply related
* Re: 23.11.7 patches review and test
From: Kevin Traynor @ 2026-05-15 16:03 UTC (permalink / raw)
To: Luca Boccassi
Cc: Shani Peretz, stable, dev, Robin Jarry, David Marchand,
Thomas Monjalon
In-Reply-To: <CAMw=ZnSLnz8uxwPJgZThKUm4fpsge_dvb8+o4grBeNYYsmuBMw@mail.gmail.com>
On 5/15/26 1:36 PM, Luca Boccassi wrote:
> On Fri, 15 May 2026 at 11:32, Kevin Traynor <ktraynor@redhat.com> wrote:
>>
>> On 4/30/26 12:02 PM, Kevin Traynor wrote:
>>> On 4/30/26 10:58 AM, Thomas Monjalon wrote:
>>>> 30/04/2026 11:32, Kevin Traynor:
>>>>> On 4/21/26 7:46 AM, Shani Peretz wrote:
>>>>>> The planned date for the final release is 30 April 2026.
>>>>>
>>>>> As discussed on thread [0] there was a quite serious regression caused
>>>>> by "net: fix packet type for stacked VLAN"
>>>>>
>>>>> As discussion on the fix is ongoing, I would suggest to just revert this
>>>>> patch for your release.
>>>>
>>>> I agree the revert is the best option here.
>>>>
>>>>> It doesn't require a new RC and re-validation as it's an isolated issue
>>>>> (and there wasn't test cases to catch before Robin's new patch anyway)
>>>>
>>>> I suppose 24.11.5 and 25.11.1 are also impacted?
>>>>
>>>>
>>>
>>> Yes, I was hoping we would have a fix in a few days and we could add and
>>> re-release. Given that there's now discussion on the patch and what
>>> functionality is needed, it's probably best to just revert and release a
>>> new 24.11/25.11.
>>
>> Hi Luca. Are you planning to do a 24.11 release with revert for above
>> issue ? If you have a time issue, let me know and I can help out.
>
> Hi, is it strictly necessary? Could it wait for the next one?
>
It's a user visible regression from the previous release that impacts
tap device with VLAN, causing good packets to be discarded. It's also
visible to any application using the net API in a similar way. Given the
effort is low as it's just a revert and we don't need validation teams
involved, then I think it's worthwhile.
^ permalink raw reply
* Re: [PATCH] maintainers: update for compress/uadk and crypto/uadk driver
From: Thomas Monjalon @ 2026-05-15 14:04 UTC (permalink / raw)
To: ZongYu Wu, fengchengwen; +Cc: dev, fanghao11, liulongfang
In-Reply-To: <3c80e9fb-c285-4928-ade2-15a2bc1da914@huawei.com>
15/05/2026 02:06, fengchengwen:
> Acked-by: Chengwen Feng <fengchengwen@huawei.com>
>
> Please
> 1\ For commitlog, each line contain a maximum of 72 characters.
> 2\ Add you name in .mailmap
>
> On 5/14/2026 8:40 PM, ZongYu Wu wrote:
> > From: Zongyu Wu <wuzongyu1@huawei.com>
> >
> > Zongyu Wu replaces Zhangfei Gao as the maintainer of compress/uadk and crypto/uadk.
> >
> > Signed-off-by: Zongyu Wu <wuzongyu1@huawei.com>
Applied with mailmap addition, thanks.
^ permalink raw reply
* [PATCH] net/mlx5: redirect LACP traffic for legacy E-Switch
From: Dariusz Sosnowski @ 2026-05-15 12:37 UTC (permalink / raw)
To: Viacheslav Ovsiienko, Bing Zhao, Ori Kam, Suanming Mou,
Matan Azrad
Cc: dev, stable
Offending patch fixed the LACP miss rule logic for NICs where
switchdev is enabled. In this case, LACP miss rules should be inserted
if and only if started port is a main port on the embedded switch.
Side effect of that change was that LACP miss rules are not inserted
when switchdev is disabled and legacy SR-IOV switch mode is used.
This patch addresses that:
- Fix the LACP rule insertion condition.
- Move HWS table for LACP rule creation out of FDB rules,
so they can be created separately.
Fixes: 87e4384d2662 ("net/mlx5: fix condition of LACP miss flow")
Cc: stable@dpdk.org
Signed-off-by: Dariusz Sosnowski <dsosnowski@nvidia.com>
---
drivers/net/mlx5/mlx5.h | 1 +
drivers/net/mlx5/mlx5_flow.h | 40 ++++++++-
drivers/net/mlx5/mlx5_flow_hw.c | 140 ++++++++++++++++++++++++--------
drivers/net/mlx5/mlx5_trigger.c | 7 +-
4 files changed, 145 insertions(+), 43 deletions(-)
diff --git a/drivers/net/mlx5/mlx5.h b/drivers/net/mlx5/mlx5.h
index 49a0c03544..ab5c76bfc4 100644
--- a/drivers/net/mlx5/mlx5.h
+++ b/drivers/net/mlx5/mlx5.h
@@ -2040,6 +2040,7 @@ struct mlx5_priv {
rte_spinlock_t hw_ctrl_lock;
LIST_HEAD(hw_ctrl_flow, mlx5_ctrl_flow_entry) hw_ctrl_flows;
LIST_HEAD(hw_ext_ctrl_flow, mlx5_ctrl_flow_entry) hw_ext_ctrl_flows;
+ struct mlx5_flow_hw_lacp_miss *hw_lacp_miss; /* HWS LACP miss flow tables */
struct mlx5_flow_hw_ctrl_fdb *hw_ctrl_fdb; /* FDB control flow context */
struct mlx5_flow_hw_ctrl_nic *hw_ctrl_nic; /* NIC control flow context */
struct rte_flow_pattern_template *hw_tx_repr_tagging_pt;
diff --git a/drivers/net/mlx5/mlx5_flow.h b/drivers/net/mlx5/mlx5_flow.h
index c9e72a33d6..3f5ba55bf9 100644
--- a/drivers/net/mlx5/mlx5_flow.h
+++ b/drivers/net/mlx5/mlx5_flow.h
@@ -3031,6 +3031,13 @@ struct mlx5_flow_hw_ctrl_rx {
[MLX5_FLOW_HW_CTRL_RX_EXPANDED_RSS_MAX];
};
+/* Contains all templates and table required for redirecting LACP traffic with HWS. */
+struct mlx5_flow_hw_lacp_miss {
+ struct rte_flow_pattern_template *lacp_rx_items_tmpl;
+ struct rte_flow_actions_template *lacp_rx_actions_tmpl;
+ struct rte_flow_template_table *hw_lacp_rx_tbl;
+};
+
/* Contains all templates required for control flow rules in FDB with HWS. */
struct mlx5_flow_hw_ctrl_fdb {
struct rte_flow_pattern_template *esw_mgr_items_tmpl;
@@ -3042,9 +3049,6 @@ struct mlx5_flow_hw_ctrl_fdb {
struct rte_flow_pattern_template *port_items_tmpl;
struct rte_flow_actions_template *jump_one_actions_tmpl;
struct rte_flow_template_table *hw_esw_zero_tbl;
- struct rte_flow_pattern_template *lacp_rx_items_tmpl;
- struct rte_flow_actions_template *lacp_rx_actions_tmpl;
- struct rte_flow_template_table *hw_lacp_rx_tbl;
};
struct mlx5_flow_hw_ctrl_nic {
@@ -3735,6 +3739,36 @@ mlx5_indirect_list_handles_release(struct rte_eth_dev *dev);
bool mlx5_flow_is_steering_disabled(void);
+/**
+ * Returns true if Rx control rule for LACP traffic is needed.
+ *
+ * mlx5 PMD needs to create a rule matching LACP traffic and forwarding it back to kernel if:
+ *
+ * - Underlying device is a bond interface.
+ * - User did not request to handle LACP traffic in user space.
+ *
+ * Creation of this rule is also controlled by the E-Switch mode:
+ *
+ * - It must be created in legacy mode.
+ * - It must be created only on proxy port in switchdev mode.
+ *
+ * @param[in] priv
+ * Pointer to Ethernet device structure.
+ *
+ * @return
+ * True if LACP rules must be created.
+ * False otherwise.
+ */
+static inline bool
+mlx5_flow_lacp_miss_needed(struct rte_eth_dev *dev)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+
+ return !priv->sh->config.lacp_by_user &&
+ priv->pf_bond >= 0 &&
+ (!priv->sh->esw_mode || (priv->sh->esw_mode && priv->master));
+}
+
#ifdef HAVE_MLX5_HWS_SUPPORT
#define MLX5_REPR_STC_MEMORY_LOG 11
diff --git a/drivers/net/mlx5/mlx5_flow_hw.c b/drivers/net/mlx5/mlx5_flow_hw.c
index b6bb9f12a6..c133230cb7 100644
--- a/drivers/net/mlx5/mlx5_flow_hw.c
+++ b/drivers/net/mlx5/mlx5_flow_hw.c
@@ -10820,15 +10820,6 @@ flow_hw_cleanup_ctrl_fdb_tables(struct rte_eth_dev *dev)
if (!priv->hw_ctrl_fdb)
return;
hw_ctrl_fdb = priv->hw_ctrl_fdb;
- /* Clean up templates used for LACP default miss table. */
- if (hw_ctrl_fdb->hw_lacp_rx_tbl)
- claim_zero(flow_hw_table_destroy(dev, hw_ctrl_fdb->hw_lacp_rx_tbl, NULL));
- if (hw_ctrl_fdb->lacp_rx_actions_tmpl)
- claim_zero(flow_hw_actions_template_destroy(dev, hw_ctrl_fdb->lacp_rx_actions_tmpl,
- NULL));
- if (hw_ctrl_fdb->lacp_rx_items_tmpl)
- claim_zero(flow_hw_pattern_template_destroy(dev, hw_ctrl_fdb->lacp_rx_items_tmpl,
- NULL));
/* Clean up templates used for default FDB jump rule. */
if (hw_ctrl_fdb->hw_esw_zero_tbl)
claim_zero(flow_hw_table_destroy(dev, hw_ctrl_fdb->hw_esw_zero_tbl, NULL));
@@ -10898,6 +10889,99 @@ flow_hw_create_lacp_rx_table(struct rte_eth_dev *dev,
return flow_hw_table_create(dev, &cfg, &it, 1, &at, 1, error);
}
+/*
+ * Clean up templates and table used for redirecting LACP traffic to kernel.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ */
+static void
+flow_hw_cleanup_lacp_miss_tables(struct rte_eth_dev *dev)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_flow_hw_lacp_miss *hw_lacp_miss;
+
+ if (priv->hw_lacp_miss == NULL)
+ return;
+
+ hw_lacp_miss = priv->hw_lacp_miss;
+
+ if (hw_lacp_miss->hw_lacp_rx_tbl)
+ claim_zero(flow_hw_table_destroy(dev, hw_lacp_miss->hw_lacp_rx_tbl, NULL));
+ if (hw_lacp_miss->lacp_rx_actions_tmpl)
+ claim_zero(flow_hw_actions_template_destroy(dev,
+ hw_lacp_miss->lacp_rx_actions_tmpl,
+ NULL));
+ if (hw_lacp_miss->lacp_rx_items_tmpl)
+ claim_zero(flow_hw_pattern_template_destroy(dev,
+ hw_lacp_miss->lacp_rx_items_tmpl,
+ NULL));
+
+ mlx5_free(hw_lacp_miss);
+ priv->hw_lacp_miss = NULL;
+}
+
+/*
+ * Create templates and table for redirecting LACP traffic to kernel.
+ *
+ * LACP traffic redirection is needed whenever LACP bond is managed by the kernel.
+ * Required rule has a following structure:
+ *
+ * - ingress rule on root table
+ * - match EtherType 0x8809
+ * - action DEFAULT_MISS
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ *
+ * @return
+ * 0 on success. Negative errno otherwise.
+ */
+static int
+flow_hw_create_lacp_miss_tables(struct rte_eth_dev *dev)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_flow_hw_lacp_miss *hw_lacp_miss;
+
+ if (mlx5_flow_is_steering_disabled())
+ return 0;
+
+ hw_lacp_miss = mlx5_malloc(MLX5_MEM_ZERO, sizeof(*hw_lacp_miss), 0, SOCKET_ID_ANY);
+ if (!hw_lacp_miss) {
+ DRV_LOG(ERR, "port %u Failed to allocate memory for LACP miss tables",
+ dev->data->port_id);
+ return -ENOMEM;
+ }
+ priv->hw_lacp_miss = hw_lacp_miss;
+
+ hw_lacp_miss->lacp_rx_items_tmpl = flow_hw_create_lacp_rx_pattern_template(dev, NULL);
+ if (!hw_lacp_miss->lacp_rx_items_tmpl) {
+ DRV_LOG(ERR, "port %u Failed to create pattern template for LACP Rx traffic",
+ dev->data->port_id);
+ goto error;
+ }
+ hw_lacp_miss->lacp_rx_actions_tmpl = flow_hw_create_lacp_rx_actions_template(dev, NULL);
+ if (!hw_lacp_miss->lacp_rx_actions_tmpl) {
+ DRV_LOG(ERR, "port %u Failed to create actions template for LACP Rx traffic",
+ dev->data->port_id);
+ goto error;
+ }
+ hw_lacp_miss->hw_lacp_rx_tbl =
+ flow_hw_create_lacp_rx_table(dev, hw_lacp_miss->lacp_rx_items_tmpl,
+ hw_lacp_miss->lacp_rx_actions_tmpl, NULL);
+ if (!hw_lacp_miss->hw_lacp_rx_tbl) {
+ DRV_LOG(ERR, "port %u Failed to create template table for LACP Rx traffic",
+ dev->data->port_id);
+ goto error;
+ }
+
+ return 0;
+
+error:
+ flow_hw_cleanup_lacp_miss_tables(dev);
+ return -EINVAL;
+}
+
/**
* Creates a set of flow tables used to create control flows used
* when E-Switch is engaged.
@@ -11000,31 +11084,6 @@ flow_hw_create_fdb_ctrl_tables(struct rte_eth_dev *dev, struct rte_flow_error *e
goto err;
}
}
- /* Create LACP default miss table. */
- if (!priv->sh->config.lacp_by_user && priv->pf_bond >= 0 && priv->master) {
- hw_ctrl_fdb->lacp_rx_items_tmpl =
- flow_hw_create_lacp_rx_pattern_template(dev, error);
- if (!hw_ctrl_fdb->lacp_rx_items_tmpl) {
- DRV_LOG(ERR, "port %u failed to create pattern template"
- " for LACP Rx traffic", dev->data->port_id);
- goto err;
- }
- hw_ctrl_fdb->lacp_rx_actions_tmpl =
- flow_hw_create_lacp_rx_actions_template(dev, error);
- if (!hw_ctrl_fdb->lacp_rx_actions_tmpl) {
- DRV_LOG(ERR, "port %u failed to create actions template"
- " for LACP Rx traffic", dev->data->port_id);
- goto err;
- }
- hw_ctrl_fdb->hw_lacp_rx_tbl = flow_hw_create_lacp_rx_table
- (dev, hw_ctrl_fdb->lacp_rx_items_tmpl,
- hw_ctrl_fdb->lacp_rx_actions_tmpl, error);
- if (!hw_ctrl_fdb->hw_lacp_rx_tbl) {
- DRV_LOG(ERR, "port %u failed to create template table for"
- " for LACP Rx traffic", dev->data->port_id);
- goto err;
- }
- }
return 0;
err:
@@ -11754,6 +11813,7 @@ __mlx5_flow_hw_resource_release(struct rte_eth_dev *dev, bool ctx_close)
mlx5_flow_hw_rxq_flag_set(dev, false);
flow_hw_flush_all_ctrl_flows(dev);
+ flow_hw_cleanup_lacp_miss_tables(dev);
flow_hw_cleanup_ctrl_fdb_tables(dev);
flow_hw_cleanup_ctrl_nic_tables(dev);
flow_hw_cleanup_tx_repr_tagging(dev);
@@ -12160,6 +12220,14 @@ __flow_hw_configure(struct rte_eth_dev *dev,
if (ret)
goto err;
}
+ if (mlx5_flow_lacp_miss_needed(dev)) {
+ ret = flow_hw_create_lacp_miss_tables(dev);
+ if (ret) {
+ rte_flow_error_set(error, -ret, RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL,
+ "Unable to create LACP miss flow tables");
+ goto err;
+ }
+ }
if (is_proxy) {
ret = flow_hw_create_vport_actions(priv);
if (ret) {
@@ -16234,10 +16302,10 @@ mlx5_flow_hw_lacp_rx_flow(struct rte_eth_dev *dev)
.type = MLX5_CTRL_FLOW_TYPE_LACP_RX,
};
- if (!priv->dr_ctx || !priv->hw_ctrl_fdb || !priv->hw_ctrl_fdb->hw_lacp_rx_tbl)
+ if (!priv->dr_ctx || !priv->hw_lacp_miss || !priv->hw_lacp_miss->hw_lacp_rx_tbl)
return 0;
return flow_hw_create_ctrl_flow(dev, dev,
- priv->hw_ctrl_fdb->hw_lacp_rx_tbl,
+ priv->hw_lacp_miss->hw_lacp_rx_tbl,
eth_lacp, 0, miss_action, 0, &flow_info, false);
}
diff --git a/drivers/net/mlx5/mlx5_trigger.c b/drivers/net/mlx5/mlx5_trigger.c
index a070aaecfd..32cd18717d 100644
--- a/drivers/net/mlx5/mlx5_trigger.c
+++ b/drivers/net/mlx5/mlx5_trigger.c
@@ -1672,9 +1672,8 @@ mlx5_traffic_enable_hws(struct rte_eth_dev *dev)
} else {
DRV_LOG(INFO, "port %u FDB default rule is disabled", dev->data->port_id);
}
- if (!priv->sh->config.lacp_by_user && priv->pf_bond >= 0 && priv->master)
- if (mlx5_flow_hw_lacp_rx_flow(dev))
- goto error;
+ if (mlx5_flow_lacp_miss_needed(dev) && mlx5_flow_hw_lacp_rx_flow(dev) != 0)
+ goto error;
if (priv->isolated)
return 0;
ret = mlx5_flow_hw_create_ctrl_rx_tables(dev);
@@ -1796,7 +1795,7 @@ mlx5_traffic_enable(struct rte_eth_dev *dev)
DRV_LOG(INFO, "port %u FDB default rule is disabled",
dev->data->port_id);
}
- if (!priv->sh->config.lacp_by_user && priv->pf_bond >= 0 && priv->master) {
+ if (mlx5_flow_lacp_miss_needed(dev)) {
ret = mlx5_flow_lacp_miss(dev);
if (ret)
DRV_LOG(INFO, "port %u LACP rule cannot be created - "
--
2.47.3
^ permalink raw reply related
* Re: 23.11.7 patches review and test
From: Luca Boccassi @ 2026-05-15 12:36 UTC (permalink / raw)
To: Kevin Traynor
Cc: Shani Peretz, stable, dev, Robin Jarry, David Marchand,
Thomas Monjalon
In-Reply-To: <91a6d5df-57c8-4045-9cc4-4ea0f5170f52@redhat.com>
On Fri, 15 May 2026 at 11:32, Kevin Traynor <ktraynor@redhat.com> wrote:
>
> On 4/30/26 12:02 PM, Kevin Traynor wrote:
> > On 4/30/26 10:58 AM, Thomas Monjalon wrote:
> >> 30/04/2026 11:32, Kevin Traynor:
> >>> On 4/21/26 7:46 AM, Shani Peretz wrote:
> >>>> The planned date for the final release is 30 April 2026.
> >>>
> >>> As discussed on thread [0] there was a quite serious regression caused
> >>> by "net: fix packet type for stacked VLAN"
> >>>
> >>> As discussion on the fix is ongoing, I would suggest to just revert this
> >>> patch for your release.
> >>
> >> I agree the revert is the best option here.
> >>
> >>> It doesn't require a new RC and re-validation as it's an isolated issue
> >>> (and there wasn't test cases to catch before Robin's new patch anyway)
> >>
> >> I suppose 24.11.5 and 25.11.1 are also impacted?
> >>
> >>
> >
> > Yes, I was hoping we would have a fix in a few days and we could add and
> > re-release. Given that there's now discussion on the patch and what
> > functionality is needed, it's probably best to just revert and release a
> > new 24.11/25.11.
>
> Hi Luca. Are you planning to do a 24.11 release with revert for above
> issue ? If you have a time issue, let me know and I can help out.
Hi, is it strictly necessary? Could it wait for the next one?
^ permalink raw reply
* [PATCH] net/mlx5: fix uninitialized skip count
From: Dariusz Sosnowski @ 2026-05-15 12:33 UTC (permalink / raw)
To: Viacheslav Ovsiienko, Bing Zhao, Ori Kam, Suanming Mou,
Matan Azrad, Alexander Kozyrev
Cc: dev, Kiran Vedere, stable
From: Kiran Vedere <kiranv@nvidia.com>
mlx5_rx_poll_len() may return MLX5_ERROR_CQE_MASK when
mlx5_rx_err_handle() reports MLX5_CQE_STATUS_HW_OWN while the Rx queue
is in IGNORE error state. In this HW_OWN case mlx5_rx_err_handle()
does not necessarily write to *skip_cnt, yet the caller (mlx5_rx_burst)
unconditionally uses skip_cnt to advance rq_ci.
This can cause rq_ci to jump by an undefined value, desynchronizing the
RQ and CQ rings and leading to persistent bad packet delivery until the
queue is reset.
Fixes: aa67ed308458 ("net/mlx5: ignore non-critical syndromes for Rx queue")
Cc: akozyrev@nvidia.com
Cc: stable@dpdk.org
Signed-off-by: Kiran Vedere <kiranv@nvidia.com>
Acked-by: Dariusz Sosnowski <dsosnowski@nvidia.com>
---
drivers/net/mlx5/mlx5_rx.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/mlx5/mlx5_rx.c b/drivers/net/mlx5/mlx5_rx.c
index 185bfd4fff..09cd3f1ffb 100644
--- a/drivers/net/mlx5/mlx5_rx.c
+++ b/drivers/net/mlx5/mlx5_rx.c
@@ -1051,7 +1051,7 @@ mlx5_rx_burst(void *dpdk_rxq, struct rte_mbuf **pkts, uint16_t pkts_n)
int len = 0; /* keep its value across iterations. */
while (pkts_n) {
- uint16_t skip_cnt;
+ uint16_t skip_cnt = 0;
unsigned int idx = rq_ci & wqe_mask;
volatile struct mlx5_wqe_data_seg *wqe =
&((volatile struct mlx5_wqe_data_seg *)rxq->wqes)[idx];
@@ -1497,7 +1497,7 @@ mlx5_rx_burst_mprq(void *dpdk_rxq, struct rte_mbuf **pkts, uint16_t pkts_n)
uint16_t strd_cnt;
uint16_t strd_idx;
uint32_t byte_cnt;
- uint16_t skip_cnt;
+ uint16_t skip_cnt = 0;
volatile struct mlx5_mini_cqe8 *mcqe = NULL;
enum mlx5_rqx_code rxq_code;
--
2.47.3
^ permalink raw reply related
* Re: [PATCH dpdk v4] net: fix VLAN packet type
From: Kevin Traynor @ 2026-05-15 11:17 UTC (permalink / raw)
To: David Marchand, Robin Jarry
Cc: dev, Gregory Etelson, stable, Thomas Monjalon, Luca Boccassi
In-Reply-To: <CAJFAV8yAhr-iXkn6JvderT_Yy4rB91LVWqYvwRqJH0DdmNkJ1g@mail.gmail.com>
On 4/25/26 10:40 AM, David Marchand wrote:
> On Thu, 23 Apr 2026 at 13:25, Robin Jarry <rjarry@redhat.com> wrote:
>> diff --git a/lib/net/rte_net.c b/lib/net/rte_net.c
>> index 458b4814a9c9..a871318b21c2 100644
>> --- a/lib/net/rte_net.c
>> +++ b/lib/net/rte_net.c
>> @@ -357,12 +357,14 @@ uint32_t rte_net_get_ptype(const struct rte_mbuf *m,
>> const struct rte_vlan_hdr *vh;
>> struct rte_vlan_hdr vh_copy;
>>
>> + if (vlan_depth == 0) {
>> + pkt_type =
>> + proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_VLAN) ?
>> + RTE_PTYPE_L2_ETHER_VLAN :
>> + RTE_PTYPE_L2_ETHER_QINQ;
>> + }
>
> This code is becoming too complex.
> The original usecase with more than 2 stacked vlan is a bit strange,
> but the max depth limit seems just arbitrary (why 8?).
> We have clear boundaries, with the size of the packet (see below,
> check on vh == NULL).
>
> The offending commit also allows stacking mpls on top of vlan, without
> mentioning it.
> I think we want this behavior, but still was it intended?
>
> In the end, reverting the previous fix then just advancing off and
> breaking once proto is not a vlan/qinq type gives a much simpler fix
> when compared to v25.11.
>
> (ignoring indent changes with -w)
>
> $ git diff -w v25.11 lib/net/rte_net.c
> diff --git a/lib/net/rte_net.c b/lib/net/rte_net.c
> index c70b57fdc0..f58d699c83 100644
> --- a/lib/net/rte_net.c
> +++ b/lib/net/rte_net.c
> @@ -349,30 +349,28 @@ uint32_t rte_net_get_ptype(const struct rte_mbuf *m,
> if (proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4))
> goto l3; /* fast path if packet is IPv4 */
>
> - if (proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_VLAN)) {
> + if (proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_VLAN) ||
> + proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_QINQ)) {
> const struct rte_vlan_hdr *vh;
> struct rte_vlan_hdr vh_copy;
>
> + if (proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_VLAN))
> pkt_type = RTE_PTYPE_L2_ETHER_VLAN;
> + else
> + pkt_type = RTE_PTYPE_L2_ETHER_QINQ;
> +
> + do {
> vh = rte_pktmbuf_read(m, off, sizeof(*vh), &vh_copy);
> if (unlikely(vh == NULL))
> return pkt_type;
> off += sizeof(*vh);
> hdr_lens->l2_len += sizeof(*vh);
> proto = vh->eth_proto;
> - } else if (proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_QINQ)) {
> - const struct rte_vlan_hdr *vh;
> - struct rte_vlan_hdr vh_copy;
> + } while (proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_VLAN) ||
> + proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_QINQ));
> + }
>
> - pkt_type = RTE_PTYPE_L2_ETHER_QINQ;
> - vh = rte_pktmbuf_read(m, off + sizeof(*vh), sizeof(*vh),
> - &vh_copy);
> - if (unlikely(vh == NULL))
> - return pkt_type;
> - off += 2 * sizeof(*vh);
> - hdr_lens->l2_len += 2 * sizeof(*vh);
> - proto = vh->eth_proto;
> - } else if ((proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_MPLS)) ||
> + if ((proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_MPLS)) ||
> (proto == rte_cpu_to_be_16(RTE_ETHER_TYPE_MPLSM))) {
> unsigned int i;
> const struct rte_mpls_hdr *mh;
>
>
> This is untested, but what do you think?
>
>
This version LGTM. Maybe we should consider returning NULL on invalid
packets
^ permalink raw reply
* Re: 23.11.7 patches review and test
From: Kevin Traynor @ 2026-05-15 10:31 UTC (permalink / raw)
To: Luca Boccassi, Shani Peretz
Cc: stable, dev, Robin Jarry, David Marchand, Thomas Monjalon
In-Reply-To: <f27bd211-66c0-4a87-9d11-de6d83cae4c9@redhat.com>
On 4/30/26 12:02 PM, Kevin Traynor wrote:
> On 4/30/26 10:58 AM, Thomas Monjalon wrote:
>> 30/04/2026 11:32, Kevin Traynor:
>>> On 4/21/26 7:46 AM, Shani Peretz wrote:
>>>> The planned date for the final release is 30 April 2026.
>>>
>>> As discussed on thread [0] there was a quite serious regression caused
>>> by "net: fix packet type for stacked VLAN"
>>>
>>> As discussion on the fix is ongoing, I would suggest to just revert this
>>> patch for your release.
>>
>> I agree the revert is the best option here.
>>
>>> It doesn't require a new RC and re-validation as it's an isolated issue
>>> (and there wasn't test cases to catch before Robin's new patch anyway)
>>
>> I suppose 24.11.5 and 25.11.1 are also impacted?
>>
>>
>
> Yes, I was hoping we would have a fix in a few days and we could add and
> re-release. Given that there's now discussion on the patch and what
> functionality is needed, it's probably best to just revert and release a
> new 24.11/25.11.
Hi Luca. Are you planning to do a 24.11 release with revert for above
issue ? If you have a time issue, let me know and I can help out.
^ permalink raw reply
* [PATCH 0/1] crypto/zsda: update product name and maintainer
From: Chengfei Han @ 2026-05-15 8:12 UTC (permalink / raw)
To: dev; +Cc: ran.ming, Chengfei Han
[-- Attachment #1.1.1: Type: text/plain, Size: 463 bytes --]
*** BLURB HERE ***
This patch updates the ZSDA PMD driver:
- Correct product name from '1cf2' to 'Neo X510/X512' in documentation
- Update maintainer for ZTE Storage Data Accelerator (ZSDA)
Chengfei Han (1):
crypto/zsda: Update product name and maintainer
MAINTAINERS | 3 ++-
doc/guides/compressdevs/zsda.rst | 3 +--
doc/guides/cryptodevs/zsda.rst | 3 +--
3 files changed, 4 insertions(+), 5 deletions(-)
--
2.27.0
[-- Attachment #1.1.2: Type: text/html , Size: 949 bytes --]
^ permalink raw reply
* [PATCH 1/1] crypto/zsda: Update product name and maintainer
From: Chengfei Han @ 2026-05-15 8:12 UTC (permalink / raw)
To: dev; +Cc: ran.ming, Chengfei Han
In-Reply-To: <20260515081212.3565572-1-han.chengfei@zte.com.cn>
[-- Attachment #1.1.1: Type: text/plain, Size: 1826 bytes --]
Correct product name from '1cf2' to 'Neo X510/X512' in PMD documentation.
Update maintainer for ZTE Storage Data Accelerator (ZSDA)
Signed-off-by: Chengfei Han <han.chengfei@zte.com.cn>
---
MAINTAINERS | 3 ++-
doc/guides/compressdevs/zsda.rst | 3 +--
doc/guides/cryptodevs/zsda.rst | 3 +--
3 files changed, 4 insertions(+), 5 deletions(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index 0f5539f851..7f30205b24 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1352,7 +1352,8 @@ F: doc/guides/compressdevs/zlib.rst
F: doc/guides/compressdevs/features/zlib.ini
ZTE Storage Data Accelerator (ZSDA)
-M: Hanxiao Li <li.hanxiao@zte.com.cn>
+M: Chengfei Han <han.chengfei@zte.com.cn>
+M: Ming Ran <ran.ming@zte.com.cn>
F: drivers/common/zsda/
F: drivers/compress/zsda/
F: doc/guides/compressdevs/zsda.rst
diff --git a/doc/guides/compressdevs/zsda.rst b/doc/guides/compressdevs/zsda.rst
index 25b7884535..5b8d4846a0 100644
--- a/doc/guides/compressdevs/zsda.rst
+++ b/doc/guides/compressdevs/zsda.rst
@@ -7,8 +7,7 @@ ZTE Storage Data Accelerator (ZSDA) Poll Mode Driver
The ZSDA compression PMD provides poll mode compression & decompression driver
support for the following hardware accelerator devices:
-* ZTE Processing accelerators 1cf2
-
+- Neo X510/X512
Features
--------
diff --git a/doc/guides/cryptodevs/zsda.rst b/doc/guides/cryptodevs/zsda.rst
index b024f537c1..8885663e9e 100644
--- a/doc/guides/cryptodevs/zsda.rst
+++ b/doc/guides/cryptodevs/zsda.rst
@@ -7,8 +7,7 @@ ZTE Storage Data Accelerator (ZSDA) Poll Mode Driver
The ZSDA crypto PMD provides poll mode Cipher and Hash driver
support for the following hardware accelerator devices:
-* ZTE Processing accelerators 1cf2
-
+- Neo X510/X512
Features
--------
--
2.27.0
[-- Attachment #1.1.2: Type: text/html , Size: 3054 bytes --]
^ permalink raw reply related
* Re: [PATCH v13 4/5] vhost_user: Function defs for add/rem mem regions
From: fengchengwen @ 2026-05-15 1:04 UTC (permalink / raw)
To: pravin.bathija, dev, stephen, maxime.coquelin; +Cc: thomas
In-Reply-To: <20260514224627.2014566-5-pravin.bathija@dell.com>
On 5/15/2026 6:46 AM, pravin.bathija@dell.com wrote:
> From: Pravin M Bathija <pravin.bathija@dell.com>
>
> These changes cover the function definition for add/remove memory
> region calls which are invoked on receiving vhost user message from
> vhost user front-end (e.g. Qemu). In our case, in addition to testing
> with qemu front-end, the testing has also been performed with libblkio
> front-end and spdk/dpdk back-end. We did I/O using libblkio based device
> driver, to spdk based drives.
> There are also changes for set_mem_table and new definition for get memory
> slots. Our changes optimize the set memory table call to use common support
> functions. A new vhost_user_initialize_memory() function is introduced to
> factor out the common memory initialization logic from the function
> vhost_user_set_mem_table(), which is now called from both the SET_MEM_TABLE
> message handler and the ADD_MEM_REG handler (for the first region).
> Message get memory slots is how the vhost-user front-end queries the
> vhost-user back-end about the number of memory slots available to be
> registered by the back-end. In addition support function to invalidate
> vring is also defined which is used in add/remove memory region functions.
> The helper function remove_guest_pages is also defined here which is called
> from vhost_user_add_mem_reg.
Two much detail which provide noisy infomation I think, how about:
vhost: add mem region add/remove handlers
Add support for VHOST_USER_ADD_MEM_REG, VHOST_USER_REM_MEM_REG and
VHOST_USER_GET_MAX_MEM_SLOTS. Refactor memory initialization into
common helper and add supporting functions for dynamic memory management.
Signed-off-by: Pravin M Bathija <pravin.bathija@dell.com>
>
> Signed-off-by: Pravin M Bathija <pravin.bathija@dell.com>
> ---
> lib/vhost/vhost_user.c | 329 ++++++++++++++++++++++++++++++++++++-----
> 1 file changed, 296 insertions(+), 33 deletions(-)
>
> diff --git a/lib/vhost/vhost_user.c b/lib/vhost/vhost_user.c
> index 0ee3fe7a5e..fdcb7e0158 100644
> --- a/lib/vhost/vhost_user.c
> +++ b/lib/vhost/vhost_user.c
> @@ -71,6 +71,9 @@ VHOST_MESSAGE_HANDLER(VHOST_USER_SET_FEATURES, vhost_user_set_features, false, t
> VHOST_MESSAGE_HANDLER(VHOST_USER_SET_OWNER, vhost_user_set_owner, false, true) \
> VHOST_MESSAGE_HANDLER(VHOST_USER_RESET_OWNER, vhost_user_reset_owner, false, false) \
> VHOST_MESSAGE_HANDLER(VHOST_USER_SET_MEM_TABLE, vhost_user_set_mem_table, true, true) \
> +VHOST_MESSAGE_HANDLER(VHOST_USER_GET_MAX_MEM_SLOTS, vhost_user_get_max_mem_slots, false, false) \
> +VHOST_MESSAGE_HANDLER(VHOST_USER_ADD_MEM_REG, vhost_user_add_mem_reg, true, true) \
> +VHOST_MESSAGE_HANDLER(VHOST_USER_REM_MEM_REG, vhost_user_rem_mem_reg, true, true) \
> VHOST_MESSAGE_HANDLER(VHOST_USER_SET_LOG_BASE, vhost_user_set_log_base, true, true) \
> VHOST_MESSAGE_HANDLER(VHOST_USER_SET_LOG_FD, vhost_user_set_log_fd, true, true) \
> VHOST_MESSAGE_HANDLER(VHOST_USER_SET_VRING_NUM, vhost_user_set_vring_num, false, true) \
> @@ -1167,6 +1170,24 @@ add_guest_pages(struct virtio_net *dev, struct rte_vhost_mem_region *reg,
> return 0;
> }
>
> +static void
> +remove_guest_pages(struct virtio_net *dev, struct rte_vhost_mem_region *reg)
> +{
> + uint64_t reg_start = reg->host_user_addr;
> + uint64_t reg_end = reg_start + reg->size;
> + uint32_t i, j = 0;
> +
> + for (i = 0; i < dev->nr_guest_pages; i++) {
> + if (dev->guest_pages[i].host_user_addr >= reg_start &&
> + dev->guest_pages[i].host_user_addr < reg_end)
> + continue;
> + if (j != i)
> + dev->guest_pages[j] = dev->guest_pages[i];
> + j++;
> + }
> + dev->nr_guest_pages = j;
> +}
> +
> #ifdef RTE_LIBRTE_VHOST_DEBUG
> /* TODO: enable it only in debug mode? */
> static void
> @@ -1413,6 +1434,52 @@ vhost_user_mmap_region(struct virtio_net *dev,
> return 0;
> }
>
> +static int
> +vhost_user_initialize_memory(struct virtio_net **pdev)
> +{
> + struct virtio_net *dev = *pdev;
> + int numa_node = SOCKET_ID_ANY;
> +
> + if (dev->mem != NULL) {
> + VHOST_CONFIG_LOG(dev->ifname, ERR,
> + "memory already initialized, free it first");
> + return -1;
> + }
> +
> + /*
> + * If VQ 0 has already been allocated, try to allocate on the same
> + * NUMA node. It can be reallocated later in numa_realloc().
> + */
> + if (dev->nr_vring > 0)
> + numa_node = dev->virtqueue[0]->numa_node;
> +
> + dev->nr_guest_pages = 0;
> + if (dev->guest_pages == NULL) {
> + dev->max_guest_pages = 8;
> + dev->guest_pages = rte_zmalloc_socket(NULL,
> + dev->max_guest_pages *
> + sizeof(struct guest_page),
> + RTE_CACHE_LINE_SIZE,
> + numa_node);
> + if (dev->guest_pages == NULL) {
> + VHOST_CONFIG_LOG(dev->ifname, ERR,
> + "failed to allocate memory for dev->guest_pages");
> + return -1;
> + }
> + }
> +
> + dev->mem = rte_zmalloc_socket("vhost-mem-table", sizeof(struct rte_vhost_memory) +
> + sizeof(struct rte_vhost_mem_region) * VHOST_MEMORY_MAX_NREGIONS, 0, numa_node);
> + if (dev->mem == NULL) {
> + VHOST_CONFIG_LOG(dev->ifname, ERR, "failed to allocate memory for dev->mem");
> + rte_free(dev->guest_pages);
> + dev->guest_pages = NULL;
> + return -1;
> + }
> +
> + return 0;
> +}
> +
> static int
> vhost_user_set_mem_table(struct virtio_net **pdev,
> struct vhu_msg_context *ctx,
> @@ -1421,7 +1488,6 @@ vhost_user_set_mem_table(struct virtio_net **pdev,
> struct virtio_net *dev = *pdev;
> struct VhostUserMemory *memory = &ctx->msg.payload.memory;
> struct rte_vhost_mem_region *reg;
> - int numa_node = SOCKET_ID_ANY;
> uint64_t mmap_offset;
> uint32_t i;
> bool async_notify = false;
> @@ -1466,39 +1532,13 @@ vhost_user_set_mem_table(struct virtio_net **pdev,
> if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
> vhost_user_iotlb_flush_all(dev);
>
> - free_mem_region(dev);
> + free_all_mem_regions(dev);
This should be done in commit 3/5, I suspect that 3/5 of the code may fail to be compiled.
Please make sure each commit should compile OK, so that git commit binary search and
troubleshooting could work.
> rte_free(dev->mem);
> dev->mem = NULL;
> }
>
> - /*
> - * If VQ 0 has already been allocated, try to allocate on the same
> - * NUMA node. It can be reallocated later in numa_realloc().
> - */
> - if (dev->nr_vring > 0)
> - numa_node = dev->virtqueue[0]->numa_node;
> -
> - dev->nr_guest_pages = 0;
> - if (dev->guest_pages == NULL) {
> - dev->max_guest_pages = 8;
> - dev->guest_pages = rte_zmalloc_socket(NULL,
> - dev->max_guest_pages *
> - sizeof(struct guest_page),
> - RTE_CACHE_LINE_SIZE,
> - numa_node);
> - if (dev->guest_pages == NULL) {
> - VHOST_CONFIG_LOG(dev->ifname, ERR,
> - "failed to allocate memory for dev->guest_pages");
> - goto close_msg_fds;
> - }
> - }
> -
> - dev->mem = rte_zmalloc_socket("vhost-mem-table", sizeof(struct rte_vhost_memory) +
> - sizeof(struct rte_vhost_mem_region) * memory->nregions, 0, numa_node);
> - if (dev->mem == NULL) {
> - VHOST_CONFIG_LOG(dev->ifname, ERR, "failed to allocate memory for dev->mem");
> - goto free_guest_pages;
> - }
> + if (vhost_user_initialize_memory(pdev) < 0)
> + goto close_msg_fds;
>
> for (i = 0; i < memory->nregions; i++) {
> reg = &dev->mem->regions[i];
> @@ -1562,11 +1602,9 @@ vhost_user_set_mem_table(struct virtio_net **pdev,
> return RTE_VHOST_MSG_RESULT_OK;
>
> free_mem_table:
> - free_mem_region(dev);
> + free_all_mem_regions(dev);
Same, it should be done in commit 3/5
> rte_free(dev->mem);
> dev->mem = NULL;
> -
> -free_guest_pages:
> rte_free(dev->guest_pages);
> dev->guest_pages = NULL;
> close_msg_fds:
> @@ -1574,6 +1612,231 @@ vhost_user_set_mem_table(struct virtio_net **pdev,
> return RTE_VHOST_MSG_RESULT_ERR;
> }
>
> +
> +static int
> +vhost_user_get_max_mem_slots(struct virtio_net **pdev __rte_unused,
> + struct vhu_msg_context *ctx,
> + int main_fd __rte_unused)
> +{
> + uint32_t max_mem_slots = VHOST_MEMORY_MAX_NREGIONS;
> +
> + ctx->msg.payload.u64 = (uint64_t)max_mem_slots;
> + ctx->msg.size = sizeof(ctx->msg.payload.u64);
> + ctx->fd_num = 0;
> +
> + return RTE_VHOST_MSG_RESULT_REPLY;
> +}
> +
> +static void
> +_dev_invalidate_vrings(struct virtio_net **pdev)
It seems that there is no such naming convention in vhost.
> +{
> + struct virtio_net *dev = *pdev;
> + uint32_t i;
> +
> + for (i = 0; i < dev->nr_vring; i++) {
> + struct vhost_virtqueue *vq = dev->virtqueue[i];
> +
> + if (!vq)
> + continue;
> +
> + if (vq->desc || vq->avail || vq->used) {
> + vq_assert_lock(dev, vq);
> +
> + /*
> + * If the memory table got updated, the ring addresses
> + * need to be translated again as virtual addresses have
> + * changed.
> + */
> + vring_invalidate(dev, vq);
> +
> + translate_ring_addresses(&dev, &vq);
> + }
> + }
> +
> + *pdev = dev;
why do this?
> +}
> +
> +/*
> + * Macro wrapper that performs the compile-time lock assertion with the
> + * correct message ID at the call site, then calls the implementation.
> + */
> +#define dev_invalidate_vrings(pdev, id) do { \
> + static_assert(id ## _LOCK_ALL_QPS, \
> + #id " handler is not declared as locking all queue pairs"); \
> + _dev_invalidate_vrings(pdev); \
> +} while (0)
> +
> +static int
> +vhost_user_add_mem_reg(struct virtio_net **pdev,
> + struct vhu_msg_context *ctx,
> + int main_fd __rte_unused)
> +{
> + uint32_t i;
> + struct virtio_net *dev = *pdev;
> + struct VhostUserMemoryRegion *region = &ctx->msg.payload.memreg.region;
Local variables should be arranged in descending order of length.
struct VhostUserMemoryRegion *region = &ctx->msg.payload.memreg.region;
struct virtio_net *dev = *pdev;
uint32_t i;
> +
> + /* convert first region add to normal memory table set */
> + if (dev->mem == NULL) {
> + if (vhost_user_initialize_memory(pdev) < 0)
> + goto close_msg_fds;
> + }
> +
> + /* make sure new region will fit */
> + if (dev->mem->nregions >= VHOST_MEMORY_MAX_NREGIONS) {
> + VHOST_CONFIG_LOG(dev->ifname, ERR, "too many memory regions already (%u)",
> + dev->mem->nregions);
> + goto close_msg_fds;
> + }
> +
> + /* make sure supplied memory fd present */
> + if (ctx->fd_num != 1) {
> + VHOST_CONFIG_LOG(dev->ifname, ERR, "fd count makes no sense (%u)", ctx->fd_num);
> + goto close_msg_fds;
> + }
> +
> + /* Make sure no overlap in guest virtual address space */
> + for (i = 0; i < dev->mem->nregions; i++) {
> + struct rte_vhost_mem_region *current_region = &dev->mem->regions[i];
> + uint64_t current_region_guest_start = current_region->guest_user_addr;
> + uint64_t current_region_guest_end = current_region_guest_start
> + + current_region->size - 1;
> + uint64_t proposed_region_guest_start = region->userspace_addr;
> + uint64_t proposed_region_guest_end = proposed_region_guest_start
> + + region->memory_size - 1;
why not use short name?
> +
> + if (!((proposed_region_guest_end < current_region_guest_start) ||
> + (proposed_region_guest_start > current_region_guest_end))) {
> + VHOST_CONFIG_LOG(dev->ifname, ERR,
> + "requested memory region overlaps with another region");
> + VHOST_CONFIG_LOG(dev->ifname, ERR,
> + "\tRequested region address:0x%" PRIx64,
> + region->userspace_addr);
> + VHOST_CONFIG_LOG(dev->ifname, ERR,
> + "\tRequested region size:0x%" PRIx64,
> + region->memory_size);
> + VHOST_CONFIG_LOG(dev->ifname, ERR,
> + "\tOverlapping region address:0x%" PRIx64,
> + current_region->guest_user_addr);
> + VHOST_CONFIG_LOG(dev->ifname, ERR,
> + "\tOverlapping region size:0x%" PRIx64,
> + current_region->size);
> + goto close_msg_fds;
> + }
> + }
> +
> + /* New region goes at the end of the contiguous array */
> + struct rte_vhost_mem_region *reg = &dev->mem->regions[dev->mem->nregions];
> +
> + reg->guest_phys_addr = region->guest_phys_addr;
> + reg->guest_user_addr = region->userspace_addr;
> + reg->size = region->memory_size;
> + reg->fd = ctx->fds[0];
> + ctx->fds[0] = -1;
> +
> + if (vhost_user_mmap_region(dev, reg, region->mmap_offset) < 0) {
> + VHOST_CONFIG_LOG(dev->ifname, ERR, "failed to mmap region");
> + if (reg->mmap_addr) {
> + /* mmap succeeded but a later step (e.g. add_guest_pages)
> + * failed; undo the mapping and any guest-page entries.
> + */
> + remove_guest_pages(dev, reg);
> + free_mem_region(reg);
> + } else {
> + close(reg->fd);
> + reg->fd = -1;
> + }
> + goto close_msg_fds;
> + }
> +
> + dev->mem->nregions++;
> +
> + if (dev->async_copy && rte_vfio_is_enabled("vfio")) {
> + if (async_dma_map_region(dev, reg, true) < 0)
> + goto free_new_region;
I point it out in v12, maybe not so clear, so again:
the goto will invoke async_dma_map_region(dev, reg, false), it should not invoke in
this branch.
> + }
> +
> + if (dev->postcopy_listening) {
> + /*
> + * Cannot use vhost_user_postcopy_register() here because it
> + * reads ctx->msg.payload.memory (SET_MEM_TABLE layout), but
> + * ADD_MEM_REG uses the memreg payload. Register the
> + * single new region directly instead.
> + */
> + if (vhost_user_postcopy_region_register(dev, reg) < 0)
> + goto free_new_region;
> + }
> +
> + dev_invalidate_vrings(pdev, VHOST_USER_ADD_MEM_REG);
> + dev = *pdev;
What the meaning? the dev already set *pdev in the beginning.
I also point it out in v12, I don't know what happening.
> + dump_guest_pages(dev);
> +
> + return RTE_VHOST_MSG_RESULT_OK;
> +
> +free_new_region:
> + if (dev->async_copy && rte_vfio_is_enabled("vfio"))
> + async_dma_map_region(dev, reg, false);
> + remove_guest_pages(dev, reg);
> + free_mem_region(reg);
> + dev->mem->nregions--;
> +close_msg_fds:
> + close_msg_fds(ctx);
> + return RTE_VHOST_MSG_RESULT_ERR;
> +}
> +
> +static int
> +vhost_user_rem_mem_reg(struct virtio_net **pdev,
> + struct vhu_msg_context *ctx,
> + int main_fd __rte_unused)
> +{
> + uint32_t i;
> + struct virtio_net *dev = *pdev;
> + struct VhostUserMemoryRegion *region = &ctx->msg.payload.memreg.region;
> +
> + if (dev->mem == NULL || dev->mem->nregions == 0) {
> + VHOST_CONFIG_LOG(dev->ifname, ERR, "no memory regions to remove");
> + close_msg_fds(ctx);
> + return RTE_VHOST_MSG_RESULT_ERR;
> + }
> +
> + for (i = 0; i < dev->mem->nregions; i++) {
> + struct rte_vhost_mem_region *current_region = &dev->mem->regions[i];
> +
> + /*
> + * According to the vhost-user specification:
> + * The memory region to be removed is identified by its GPA,
> + * user address and size. The mmap offset is ignored.
> + */
> + if (region->userspace_addr == current_region->guest_user_addr
> + && region->guest_phys_addr == current_region->guest_phys_addr
> + && region->memory_size == current_region->size) {
> + if (dev->async_copy && rte_vfio_is_enabled("vfio"))
> + async_dma_map_region(dev, current_region, false);
> + remove_guest_pages(dev, current_region);
> + free_mem_region(current_region);
> +
> + /* Compact the regions array to keep it contiguous */
> + if (i < dev->mem->nregions - 1) {
> + memmove(&dev->mem->regions[i],
> + &dev->mem->regions[i + 1],
> + (dev->mem->nregions - 1 - i) *
> + sizeof(struct rte_vhost_mem_region));
> + memset(&dev->mem->regions[dev->mem->nregions - 1],
> + 0, sizeof(struct rte_vhost_mem_region));
> + }
> +
> + dev->mem->nregions--;
> + dev_invalidate_vrings(pdev, VHOST_USER_REM_MEM_REG);
> + dev = *pdev;
I still don't know what the assignment meaning/function?
> + close_msg_fds(ctx);
> + return RTE_VHOST_MSG_RESULT_OK;
> + }
> + }
> +
> + VHOST_CONFIG_LOG(dev->ifname, ERR, "failed to find region");
> + close_msg_fds(ctx);
> + return RTE_VHOST_MSG_RESULT_ERR;
> +}
> +
> static bool
> vq_is_ready(struct virtio_net *dev, struct vhost_virtqueue *vq)
> {
^ permalink raw reply
* Re: [PATCH v13 3/5] vhost_user: support function defines for back-end
From: fengchengwen @ 2026-05-15 0:33 UTC (permalink / raw)
To: pravin.bathija, dev, stephen, maxime.coquelin; +Cc: thomas
In-Reply-To: <20260514224627.2014566-4-pravin.bathija@dell.com>
please use vhost as the commit title prefix (please use git blame to refer),
the same as other commit in this patchset.
How about: vhost: refactor memory helper functions
On 5/15/2026 6:46 AM, pravin.bathija@dell.com wrote:
> From: Pravin M Bathija <pravin.bathija@dell.com>
>
> Here we define support functions which are called from the various
> vhost-user back-end message functions like set memory table, get
> memory slots, add memory region, remove memory region. These are
> essentially common functions to unmap a set of memory regions,
> perform register copy, align memory addresses and dma map/unmap a
> single memory region.
Two much detail, how about:
Extract reusable helper routines for vhost-user backend memory operations:
split DMA map/unmap into per-region logic, decouple and rework memory
region free routines, and iterate over VHOST_MEMORY_MAX_NREGIONS
uniformly across related functions to simplify code reuse.
As above fixed:
Acked-by: Chengwen Feng <fengchengwen@huawei.com>
>
> Signed-off-by: Pravin M Bathija <pravin.bathija@dell.com>
> ---
> lib/vhost/vhost_user.c | 89 ++++++++++++++++++++++++++++--------------
> 1 file changed, 60 insertions(+), 29 deletions(-)
>
> diff --git a/lib/vhost/vhost_user.c b/lib/vhost/vhost_user.c
> index 4bfb13fb98..0ee3fe7a5e 100644
> --- a/lib/vhost/vhost_user.c
> +++ b/lib/vhost/vhost_user.c
> @@ -171,20 +171,27 @@ get_blk_size(int fd)
> return ret == -1 ? (uint64_t)-1 : (uint64_t)stat.st_blksize;
> }
>
> -static void
> -async_dma_map(struct virtio_net *dev, bool do_map)
> +static int
> +async_dma_map_region(struct virtio_net *dev, struct rte_vhost_mem_region *reg, bool do_map)
> {
> - int ret = 0;
> uint32_t i;
> - struct guest_page *page;
> + int ret;
> + uint64_t reg_start = reg->host_user_addr;
> + uint64_t reg_end = reg_start + reg->size;
> +
> + for (i = 0; i < dev->nr_guest_pages; i++) {
> + struct guest_page *page = &dev->guest_pages[i];
> +
> + /* Only process pages belonging to this region */
> + if (page->host_user_addr < reg_start ||
> + page->host_user_addr >= reg_end)
> + continue;
>
> - if (do_map) {
> - for (i = 0; i < dev->nr_guest_pages; i++) {
> - page = &dev->guest_pages[i];
> + if (do_map) {
> ret = rte_vfio_container_dma_map(RTE_VFIO_DEFAULT_CONTAINER_FD,
> - page->host_user_addr,
> - page->host_iova,
> - page->size);
> + page->host_user_addr,
> + page->host_iova,
> + page->size);
> if (ret) {
> /*
> * DMA device may bind with kernel driver, in this case,
> @@ -199,33 +206,57 @@ async_dma_map(struct virtio_net *dev, bool do_map)
> * normal case in async path. This is a workaround.
> */
> if (rte_errno == ENODEV)
> - return;
> + return 0;
>
> /* DMA mapping errors won't stop VHOST_USER_SET_MEM_TABLE. */
> VHOST_CONFIG_LOG(dev->ifname, ERR, "DMA engine map failed");
> + return -1;
> }
> - }
> -
> - } else {
> - for (i = 0; i < dev->nr_guest_pages; i++) {
> - page = &dev->guest_pages[i];
> + } else {
> ret = rte_vfio_container_dma_unmap(RTE_VFIO_DEFAULT_CONTAINER_FD,
> - page->host_user_addr,
> - page->host_iova,
> - page->size);
> + page->host_user_addr,
> + page->host_iova,
> + page->size);
> if (ret) {
> /* like DMA map, ignore the kernel driver case when unmap. */
> if (rte_errno == EINVAL)
> - return;
> + return 0;
>
> VHOST_CONFIG_LOG(dev->ifname, ERR, "DMA engine unmap failed");
> + return -1;
> }
> }
> }
> +
> + return 0;
> +}
> +
> +static void
> +async_dma_map(struct virtio_net *dev, bool do_map)
> +{
> + uint32_t i;
> + struct rte_vhost_mem_region *reg;
> +
> + for (i = 0; i < VHOST_MEMORY_MAX_NREGIONS; i++) {
> + reg = &dev->mem->regions[i];
> + if (reg->host_user_addr == 0)
> + continue;
> + async_dma_map_region(dev, reg, do_map);
> + }
> }
>
> static void
> -free_mem_region(struct virtio_net *dev)
> +free_mem_region(struct rte_vhost_mem_region *reg)
> +{
> + if (reg != NULL && reg->mmap_addr) {
> + munmap(reg->mmap_addr, reg->mmap_size);
> + close(reg->fd);
> + memset(reg, 0, sizeof(struct rte_vhost_mem_region));
> + }
> +}
> +
> +static void
> +free_all_mem_regions(struct virtio_net *dev)
> {
> uint32_t i;
> struct rte_vhost_mem_region *reg;
> @@ -236,12 +267,10 @@ free_mem_region(struct virtio_net *dev)
> if (dev->async_copy && rte_vfio_is_enabled("vfio"))
> async_dma_map(dev, false);
>
> - for (i = 0; i < dev->mem->nregions; i++) {
> + for (i = 0; i < VHOST_MEMORY_MAX_NREGIONS; i++) {
> reg = &dev->mem->regions[i];
> - if (reg->host_user_addr) {
> - munmap(reg->mmap_addr, reg->mmap_size);
> - close(reg->fd);
> - }
> + if (reg->mmap_addr)
> + free_mem_region(reg);
> }
> }
>
> @@ -255,7 +284,7 @@ vhost_backend_cleanup(struct virtio_net *dev)
> vdpa_dev->ops->dev_cleanup(dev->vid);
>
> if (dev->mem) {
> - free_mem_region(dev);
> + free_all_mem_regions(dev);
> rte_free(dev->mem);
> dev->mem = NULL;
> }
> @@ -704,7 +733,7 @@ numa_realloc(struct virtio_net **pdev, struct vhost_virtqueue **pvq)
> vhost_devices[dev->vid] = dev;
>
> mem_size = sizeof(struct rte_vhost_memory) +
> - sizeof(struct rte_vhost_mem_region) * dev->mem->nregions;
> + sizeof(struct rte_vhost_mem_region) * VHOST_MEMORY_MAX_NREGIONS;
> mem = rte_realloc_socket(dev->mem, mem_size, 0, node);
> if (!mem) {
> VHOST_CONFIG_LOG(dev->ifname, ERR,
> @@ -808,8 +837,10 @@ hua_to_alignment(struct rte_vhost_memory *mem, void *ptr)
> uint32_t i;
> uintptr_t hua = (uintptr_t)ptr;
>
> - for (i = 0; i < mem->nregions; i++) {
> + for (i = 0; i < VHOST_MEMORY_MAX_NREGIONS; i++) {
> r = &mem->regions[i];
> + if (r->host_user_addr == 0)
> + continue;
> if (hua >= r->host_user_addr &&
> hua < r->host_user_addr + r->size) {
> return get_blk_size(r->fd);
^ permalink raw reply
* Re: [PATCH v13 1/5] vhost: add user to mailmap and define to vhost hdr
From: fengchengwen @ 2026-05-15 0:20 UTC (permalink / raw)
To: pravin.bathija, dev, stephen, maxime.coquelin; +Cc: thomas
In-Reply-To: <20260514224627.2014566-2-pravin.bathija@dell.com>
On 5/15/2026 6:46 AM, pravin.bathija@dell.com wrote:
> From: Pravin M Bathija <pravin.bathija@dell.com>
>
> - add user to mailmap file.
> - define a bit-field called VHOST_USER_PROTOCOL_F_CONFIGURE_MEM_SLOTS
> that depicts if the feature/capability to add/remove memory regions
> is supported. This is a part of the overall support for add/remove
> memory region feature in this patchset.
>
> Signed-off-by: Pravin M Bathija <pravin.bathija@dell.com>
Please attach reviewed/acked-by of this commit in new version
^ permalink raw reply
* Re: [PATCH] maintainers: update for compress/uadk and crypto/uadk driver
From: fengchengwen @ 2026-05-15 0:06 UTC (permalink / raw)
To: ZongYu Wu, dev; +Cc: fanghao11, liulongfang, thomas
In-Reply-To: <20260514124049.3133884-1-wuzongyu1@huawei.com>
Acked-by: Chengwen Feng <fengchengwen@huawei.com>
Please
1\ For commitlog, each line contain a maximum of 72 characters.
2\ Add you name in .mailmap
On 5/14/2026 8:40 PM, ZongYu Wu wrote:
> From: Zongyu Wu <wuzongyu1@huawei.com>
>
> Zongyu Wu replaces Zhangfei Gao as the maintainer of compress/uadk and crypto/uadk.
>
> Signed-off-by: Zongyu Wu <wuzongyu1@huawei.com>
> ---
> MAINTAINERS | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/MAINTAINERS b/MAINTAINERS
> index 0f5539f851..84133b00ea 100644
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -1201,7 +1201,7 @@ F: drivers/crypto/scheduler/
> F: doc/guides/cryptodevs/scheduler.rst
>
> HiSilicon UADK crypto
> -M: Zhangfei Gao <zhangfei.gao@linaro.org>
> +M: Zongyu Wu <wuzongyu1@huawei.com>
> F: drivers/crypto/uadk/
> F: doc/guides/cryptodevs/uadk.rst
> F: doc/guides/cryptodevs/features/uadk.ini
> @@ -1318,7 +1318,7 @@ F: doc/guides/compressdevs/octeontx.rst
> F: doc/guides/compressdevs/features/octeontx.ini
>
> HiSilicon UADK compress
> -M: Zhangfei Gao <zhangfei.gao@linaro.org>
> +M: Zongyu Wu <wuzongyu1@huawei.com>
> F: drivers/compress/uadk/
> F: doc/guides/compressdevs/uadk.rst
> F: doc/guides/compressdevs/features/uadk.ini
^ permalink raw reply
* [PATCH v13 5/5] vhost_user: enable configure memory slots
From: pravin.bathija @ 2026-05-14 22:46 UTC (permalink / raw)
To: dev, fengchengwen, stephen, maxime.coquelin; +Cc: pravin.bathija, thomas
In-Reply-To: <20260514224627.2014566-1-pravin.bathija@dell.com>
From: Pravin M Bathija <pravin.bathija@dell.com>
This patch enables configure memory slots in the header define
VHOST_USER_PROTOCOL_FEATURES.
Signed-off-by: Pravin M Bathija <pravin.bathija@dell.com>
---
lib/vhost/vhost_user.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/lib/vhost/vhost_user.h b/lib/vhost/vhost_user.h
index 6435816534..732aa4dc02 100644
--- a/lib/vhost/vhost_user.h
+++ b/lib/vhost/vhost_user.h
@@ -32,6 +32,7 @@
(1ULL << VHOST_USER_PROTOCOL_F_BACKEND_SEND_FD) | \
(1ULL << VHOST_USER_PROTOCOL_F_HOST_NOTIFIER) | \
(1ULL << VHOST_USER_PROTOCOL_F_PAGEFAULT) | \
+ (1ULL << VHOST_USER_PROTOCOL_F_CONFIGURE_MEM_SLOTS) | \
(1ULL << VHOST_USER_PROTOCOL_F_STATUS))
typedef enum VhostUserRequest {
--
2.43.0
^ permalink raw reply related
* [PATCH v13 4/5] vhost_user: Function defs for add/rem mem regions
From: pravin.bathija @ 2026-05-14 22:46 UTC (permalink / raw)
To: dev, fengchengwen, stephen, maxime.coquelin; +Cc: pravin.bathija, thomas
In-Reply-To: <20260514224627.2014566-1-pravin.bathija@dell.com>
From: Pravin M Bathija <pravin.bathija@dell.com>
These changes cover the function definition for add/remove memory
region calls which are invoked on receiving vhost user message from
vhost user front-end (e.g. Qemu). In our case, in addition to testing
with qemu front-end, the testing has also been performed with libblkio
front-end and spdk/dpdk back-end. We did I/O using libblkio based device
driver, to spdk based drives.
There are also changes for set_mem_table and new definition for get memory
slots. Our changes optimize the set memory table call to use common support
functions. A new vhost_user_initialize_memory() function is introduced to
factor out the common memory initialization logic from the function
vhost_user_set_mem_table(), which is now called from both the SET_MEM_TABLE
message handler and the ADD_MEM_REG handler (for the first region).
Message get memory slots is how the vhost-user front-end queries the
vhost-user back-end about the number of memory slots available to be
registered by the back-end. In addition support function to invalidate
vring is also defined which is used in add/remove memory region functions.
The helper function remove_guest_pages is also defined here which is called
from vhost_user_add_mem_reg.
Signed-off-by: Pravin M Bathija <pravin.bathija@dell.com>
---
lib/vhost/vhost_user.c | 329 ++++++++++++++++++++++++++++++++++++-----
1 file changed, 296 insertions(+), 33 deletions(-)
diff --git a/lib/vhost/vhost_user.c b/lib/vhost/vhost_user.c
index 0ee3fe7a5e..fdcb7e0158 100644
--- a/lib/vhost/vhost_user.c
+++ b/lib/vhost/vhost_user.c
@@ -71,6 +71,9 @@ VHOST_MESSAGE_HANDLER(VHOST_USER_SET_FEATURES, vhost_user_set_features, false, t
VHOST_MESSAGE_HANDLER(VHOST_USER_SET_OWNER, vhost_user_set_owner, false, true) \
VHOST_MESSAGE_HANDLER(VHOST_USER_RESET_OWNER, vhost_user_reset_owner, false, false) \
VHOST_MESSAGE_HANDLER(VHOST_USER_SET_MEM_TABLE, vhost_user_set_mem_table, true, true) \
+VHOST_MESSAGE_HANDLER(VHOST_USER_GET_MAX_MEM_SLOTS, vhost_user_get_max_mem_slots, false, false) \
+VHOST_MESSAGE_HANDLER(VHOST_USER_ADD_MEM_REG, vhost_user_add_mem_reg, true, true) \
+VHOST_MESSAGE_HANDLER(VHOST_USER_REM_MEM_REG, vhost_user_rem_mem_reg, true, true) \
VHOST_MESSAGE_HANDLER(VHOST_USER_SET_LOG_BASE, vhost_user_set_log_base, true, true) \
VHOST_MESSAGE_HANDLER(VHOST_USER_SET_LOG_FD, vhost_user_set_log_fd, true, true) \
VHOST_MESSAGE_HANDLER(VHOST_USER_SET_VRING_NUM, vhost_user_set_vring_num, false, true) \
@@ -1167,6 +1170,24 @@ add_guest_pages(struct virtio_net *dev, struct rte_vhost_mem_region *reg,
return 0;
}
+static void
+remove_guest_pages(struct virtio_net *dev, struct rte_vhost_mem_region *reg)
+{
+ uint64_t reg_start = reg->host_user_addr;
+ uint64_t reg_end = reg_start + reg->size;
+ uint32_t i, j = 0;
+
+ for (i = 0; i < dev->nr_guest_pages; i++) {
+ if (dev->guest_pages[i].host_user_addr >= reg_start &&
+ dev->guest_pages[i].host_user_addr < reg_end)
+ continue;
+ if (j != i)
+ dev->guest_pages[j] = dev->guest_pages[i];
+ j++;
+ }
+ dev->nr_guest_pages = j;
+}
+
#ifdef RTE_LIBRTE_VHOST_DEBUG
/* TODO: enable it only in debug mode? */
static void
@@ -1413,6 +1434,52 @@ vhost_user_mmap_region(struct virtio_net *dev,
return 0;
}
+static int
+vhost_user_initialize_memory(struct virtio_net **pdev)
+{
+ struct virtio_net *dev = *pdev;
+ int numa_node = SOCKET_ID_ANY;
+
+ if (dev->mem != NULL) {
+ VHOST_CONFIG_LOG(dev->ifname, ERR,
+ "memory already initialized, free it first");
+ return -1;
+ }
+
+ /*
+ * If VQ 0 has already been allocated, try to allocate on the same
+ * NUMA node. It can be reallocated later in numa_realloc().
+ */
+ if (dev->nr_vring > 0)
+ numa_node = dev->virtqueue[0]->numa_node;
+
+ dev->nr_guest_pages = 0;
+ if (dev->guest_pages == NULL) {
+ dev->max_guest_pages = 8;
+ dev->guest_pages = rte_zmalloc_socket(NULL,
+ dev->max_guest_pages *
+ sizeof(struct guest_page),
+ RTE_CACHE_LINE_SIZE,
+ numa_node);
+ if (dev->guest_pages == NULL) {
+ VHOST_CONFIG_LOG(dev->ifname, ERR,
+ "failed to allocate memory for dev->guest_pages");
+ return -1;
+ }
+ }
+
+ dev->mem = rte_zmalloc_socket("vhost-mem-table", sizeof(struct rte_vhost_memory) +
+ sizeof(struct rte_vhost_mem_region) * VHOST_MEMORY_MAX_NREGIONS, 0, numa_node);
+ if (dev->mem == NULL) {
+ VHOST_CONFIG_LOG(dev->ifname, ERR, "failed to allocate memory for dev->mem");
+ rte_free(dev->guest_pages);
+ dev->guest_pages = NULL;
+ return -1;
+ }
+
+ return 0;
+}
+
static int
vhost_user_set_mem_table(struct virtio_net **pdev,
struct vhu_msg_context *ctx,
@@ -1421,7 +1488,6 @@ vhost_user_set_mem_table(struct virtio_net **pdev,
struct virtio_net *dev = *pdev;
struct VhostUserMemory *memory = &ctx->msg.payload.memory;
struct rte_vhost_mem_region *reg;
- int numa_node = SOCKET_ID_ANY;
uint64_t mmap_offset;
uint32_t i;
bool async_notify = false;
@@ -1466,39 +1532,13 @@ vhost_user_set_mem_table(struct virtio_net **pdev,
if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
vhost_user_iotlb_flush_all(dev);
- free_mem_region(dev);
+ free_all_mem_regions(dev);
rte_free(dev->mem);
dev->mem = NULL;
}
- /*
- * If VQ 0 has already been allocated, try to allocate on the same
- * NUMA node. It can be reallocated later in numa_realloc().
- */
- if (dev->nr_vring > 0)
- numa_node = dev->virtqueue[0]->numa_node;
-
- dev->nr_guest_pages = 0;
- if (dev->guest_pages == NULL) {
- dev->max_guest_pages = 8;
- dev->guest_pages = rte_zmalloc_socket(NULL,
- dev->max_guest_pages *
- sizeof(struct guest_page),
- RTE_CACHE_LINE_SIZE,
- numa_node);
- if (dev->guest_pages == NULL) {
- VHOST_CONFIG_LOG(dev->ifname, ERR,
- "failed to allocate memory for dev->guest_pages");
- goto close_msg_fds;
- }
- }
-
- dev->mem = rte_zmalloc_socket("vhost-mem-table", sizeof(struct rte_vhost_memory) +
- sizeof(struct rte_vhost_mem_region) * memory->nregions, 0, numa_node);
- if (dev->mem == NULL) {
- VHOST_CONFIG_LOG(dev->ifname, ERR, "failed to allocate memory for dev->mem");
- goto free_guest_pages;
- }
+ if (vhost_user_initialize_memory(pdev) < 0)
+ goto close_msg_fds;
for (i = 0; i < memory->nregions; i++) {
reg = &dev->mem->regions[i];
@@ -1562,11 +1602,9 @@ vhost_user_set_mem_table(struct virtio_net **pdev,
return RTE_VHOST_MSG_RESULT_OK;
free_mem_table:
- free_mem_region(dev);
+ free_all_mem_regions(dev);
rte_free(dev->mem);
dev->mem = NULL;
-
-free_guest_pages:
rte_free(dev->guest_pages);
dev->guest_pages = NULL;
close_msg_fds:
@@ -1574,6 +1612,231 @@ vhost_user_set_mem_table(struct virtio_net **pdev,
return RTE_VHOST_MSG_RESULT_ERR;
}
+
+static int
+vhost_user_get_max_mem_slots(struct virtio_net **pdev __rte_unused,
+ struct vhu_msg_context *ctx,
+ int main_fd __rte_unused)
+{
+ uint32_t max_mem_slots = VHOST_MEMORY_MAX_NREGIONS;
+
+ ctx->msg.payload.u64 = (uint64_t)max_mem_slots;
+ ctx->msg.size = sizeof(ctx->msg.payload.u64);
+ ctx->fd_num = 0;
+
+ return RTE_VHOST_MSG_RESULT_REPLY;
+}
+
+static void
+_dev_invalidate_vrings(struct virtio_net **pdev)
+{
+ struct virtio_net *dev = *pdev;
+ uint32_t i;
+
+ for (i = 0; i < dev->nr_vring; i++) {
+ struct vhost_virtqueue *vq = dev->virtqueue[i];
+
+ if (!vq)
+ continue;
+
+ if (vq->desc || vq->avail || vq->used) {
+ vq_assert_lock(dev, vq);
+
+ /*
+ * If the memory table got updated, the ring addresses
+ * need to be translated again as virtual addresses have
+ * changed.
+ */
+ vring_invalidate(dev, vq);
+
+ translate_ring_addresses(&dev, &vq);
+ }
+ }
+
+ *pdev = dev;
+}
+
+/*
+ * Macro wrapper that performs the compile-time lock assertion with the
+ * correct message ID at the call site, then calls the implementation.
+ */
+#define dev_invalidate_vrings(pdev, id) do { \
+ static_assert(id ## _LOCK_ALL_QPS, \
+ #id " handler is not declared as locking all queue pairs"); \
+ _dev_invalidate_vrings(pdev); \
+} while (0)
+
+static int
+vhost_user_add_mem_reg(struct virtio_net **pdev,
+ struct vhu_msg_context *ctx,
+ int main_fd __rte_unused)
+{
+ uint32_t i;
+ struct virtio_net *dev = *pdev;
+ struct VhostUserMemoryRegion *region = &ctx->msg.payload.memreg.region;
+
+ /* convert first region add to normal memory table set */
+ if (dev->mem == NULL) {
+ if (vhost_user_initialize_memory(pdev) < 0)
+ goto close_msg_fds;
+ }
+
+ /* make sure new region will fit */
+ if (dev->mem->nregions >= VHOST_MEMORY_MAX_NREGIONS) {
+ VHOST_CONFIG_LOG(dev->ifname, ERR, "too many memory regions already (%u)",
+ dev->mem->nregions);
+ goto close_msg_fds;
+ }
+
+ /* make sure supplied memory fd present */
+ if (ctx->fd_num != 1) {
+ VHOST_CONFIG_LOG(dev->ifname, ERR, "fd count makes no sense (%u)", ctx->fd_num);
+ goto close_msg_fds;
+ }
+
+ /* Make sure no overlap in guest virtual address space */
+ for (i = 0; i < dev->mem->nregions; i++) {
+ struct rte_vhost_mem_region *current_region = &dev->mem->regions[i];
+ uint64_t current_region_guest_start = current_region->guest_user_addr;
+ uint64_t current_region_guest_end = current_region_guest_start
+ + current_region->size - 1;
+ uint64_t proposed_region_guest_start = region->userspace_addr;
+ uint64_t proposed_region_guest_end = proposed_region_guest_start
+ + region->memory_size - 1;
+
+ if (!((proposed_region_guest_end < current_region_guest_start) ||
+ (proposed_region_guest_start > current_region_guest_end))) {
+ VHOST_CONFIG_LOG(dev->ifname, ERR,
+ "requested memory region overlaps with another region");
+ VHOST_CONFIG_LOG(dev->ifname, ERR,
+ "\tRequested region address:0x%" PRIx64,
+ region->userspace_addr);
+ VHOST_CONFIG_LOG(dev->ifname, ERR,
+ "\tRequested region size:0x%" PRIx64,
+ region->memory_size);
+ VHOST_CONFIG_LOG(dev->ifname, ERR,
+ "\tOverlapping region address:0x%" PRIx64,
+ current_region->guest_user_addr);
+ VHOST_CONFIG_LOG(dev->ifname, ERR,
+ "\tOverlapping region size:0x%" PRIx64,
+ current_region->size);
+ goto close_msg_fds;
+ }
+ }
+
+ /* New region goes at the end of the contiguous array */
+ struct rte_vhost_mem_region *reg = &dev->mem->regions[dev->mem->nregions];
+
+ reg->guest_phys_addr = region->guest_phys_addr;
+ reg->guest_user_addr = region->userspace_addr;
+ reg->size = region->memory_size;
+ reg->fd = ctx->fds[0];
+ ctx->fds[0] = -1;
+
+ if (vhost_user_mmap_region(dev, reg, region->mmap_offset) < 0) {
+ VHOST_CONFIG_LOG(dev->ifname, ERR, "failed to mmap region");
+ if (reg->mmap_addr) {
+ /* mmap succeeded but a later step (e.g. add_guest_pages)
+ * failed; undo the mapping and any guest-page entries.
+ */
+ remove_guest_pages(dev, reg);
+ free_mem_region(reg);
+ } else {
+ close(reg->fd);
+ reg->fd = -1;
+ }
+ goto close_msg_fds;
+ }
+
+ dev->mem->nregions++;
+
+ if (dev->async_copy && rte_vfio_is_enabled("vfio")) {
+ if (async_dma_map_region(dev, reg, true) < 0)
+ goto free_new_region;
+ }
+
+ if (dev->postcopy_listening) {
+ /*
+ * Cannot use vhost_user_postcopy_register() here because it
+ * reads ctx->msg.payload.memory (SET_MEM_TABLE layout), but
+ * ADD_MEM_REG uses the memreg payload. Register the
+ * single new region directly instead.
+ */
+ if (vhost_user_postcopy_region_register(dev, reg) < 0)
+ goto free_new_region;
+ }
+
+ dev_invalidate_vrings(pdev, VHOST_USER_ADD_MEM_REG);
+ dev = *pdev;
+ dump_guest_pages(dev);
+
+ return RTE_VHOST_MSG_RESULT_OK;
+
+free_new_region:
+ if (dev->async_copy && rte_vfio_is_enabled("vfio"))
+ async_dma_map_region(dev, reg, false);
+ remove_guest_pages(dev, reg);
+ free_mem_region(reg);
+ dev->mem->nregions--;
+close_msg_fds:
+ close_msg_fds(ctx);
+ return RTE_VHOST_MSG_RESULT_ERR;
+}
+
+static int
+vhost_user_rem_mem_reg(struct virtio_net **pdev,
+ struct vhu_msg_context *ctx,
+ int main_fd __rte_unused)
+{
+ uint32_t i;
+ struct virtio_net *dev = *pdev;
+ struct VhostUserMemoryRegion *region = &ctx->msg.payload.memreg.region;
+
+ if (dev->mem == NULL || dev->mem->nregions == 0) {
+ VHOST_CONFIG_LOG(dev->ifname, ERR, "no memory regions to remove");
+ close_msg_fds(ctx);
+ return RTE_VHOST_MSG_RESULT_ERR;
+ }
+
+ for (i = 0; i < dev->mem->nregions; i++) {
+ struct rte_vhost_mem_region *current_region = &dev->mem->regions[i];
+
+ /*
+ * According to the vhost-user specification:
+ * The memory region to be removed is identified by its GPA,
+ * user address and size. The mmap offset is ignored.
+ */
+ if (region->userspace_addr == current_region->guest_user_addr
+ && region->guest_phys_addr == current_region->guest_phys_addr
+ && region->memory_size == current_region->size) {
+ if (dev->async_copy && rte_vfio_is_enabled("vfio"))
+ async_dma_map_region(dev, current_region, false);
+ remove_guest_pages(dev, current_region);
+ free_mem_region(current_region);
+
+ /* Compact the regions array to keep it contiguous */
+ if (i < dev->mem->nregions - 1) {
+ memmove(&dev->mem->regions[i],
+ &dev->mem->regions[i + 1],
+ (dev->mem->nregions - 1 - i) *
+ sizeof(struct rte_vhost_mem_region));
+ memset(&dev->mem->regions[dev->mem->nregions - 1],
+ 0, sizeof(struct rte_vhost_mem_region));
+ }
+
+ dev->mem->nregions--;
+ dev_invalidate_vrings(pdev, VHOST_USER_REM_MEM_REG);
+ dev = *pdev;
+ close_msg_fds(ctx);
+ return RTE_VHOST_MSG_RESULT_OK;
+ }
+ }
+
+ VHOST_CONFIG_LOG(dev->ifname, ERR, "failed to find region");
+ close_msg_fds(ctx);
+ return RTE_VHOST_MSG_RESULT_ERR;
+}
+
static bool
vq_is_ready(struct virtio_net *dev, struct vhost_virtqueue *vq)
{
--
2.43.0
^ permalink raw reply related
* [PATCH v13 3/5] vhost_user: support function defines for back-end
From: pravin.bathija @ 2026-05-14 22:46 UTC (permalink / raw)
To: dev, fengchengwen, stephen, maxime.coquelin; +Cc: pravin.bathija, thomas
In-Reply-To: <20260514224627.2014566-1-pravin.bathija@dell.com>
From: Pravin M Bathija <pravin.bathija@dell.com>
Here we define support functions which are called from the various
vhost-user back-end message functions like set memory table, get
memory slots, add memory region, remove memory region. These are
essentially common functions to unmap a set of memory regions,
perform register copy, align memory addresses and dma map/unmap a
single memory region.
Signed-off-by: Pravin M Bathija <pravin.bathija@dell.com>
---
lib/vhost/vhost_user.c | 89 ++++++++++++++++++++++++++++--------------
1 file changed, 60 insertions(+), 29 deletions(-)
diff --git a/lib/vhost/vhost_user.c b/lib/vhost/vhost_user.c
index 4bfb13fb98..0ee3fe7a5e 100644
--- a/lib/vhost/vhost_user.c
+++ b/lib/vhost/vhost_user.c
@@ -171,20 +171,27 @@ get_blk_size(int fd)
return ret == -1 ? (uint64_t)-1 : (uint64_t)stat.st_blksize;
}
-static void
-async_dma_map(struct virtio_net *dev, bool do_map)
+static int
+async_dma_map_region(struct virtio_net *dev, struct rte_vhost_mem_region *reg, bool do_map)
{
- int ret = 0;
uint32_t i;
- struct guest_page *page;
+ int ret;
+ uint64_t reg_start = reg->host_user_addr;
+ uint64_t reg_end = reg_start + reg->size;
+
+ for (i = 0; i < dev->nr_guest_pages; i++) {
+ struct guest_page *page = &dev->guest_pages[i];
+
+ /* Only process pages belonging to this region */
+ if (page->host_user_addr < reg_start ||
+ page->host_user_addr >= reg_end)
+ continue;
- if (do_map) {
- for (i = 0; i < dev->nr_guest_pages; i++) {
- page = &dev->guest_pages[i];
+ if (do_map) {
ret = rte_vfio_container_dma_map(RTE_VFIO_DEFAULT_CONTAINER_FD,
- page->host_user_addr,
- page->host_iova,
- page->size);
+ page->host_user_addr,
+ page->host_iova,
+ page->size);
if (ret) {
/*
* DMA device may bind with kernel driver, in this case,
@@ -199,33 +206,57 @@ async_dma_map(struct virtio_net *dev, bool do_map)
* normal case in async path. This is a workaround.
*/
if (rte_errno == ENODEV)
- return;
+ return 0;
/* DMA mapping errors won't stop VHOST_USER_SET_MEM_TABLE. */
VHOST_CONFIG_LOG(dev->ifname, ERR, "DMA engine map failed");
+ return -1;
}
- }
-
- } else {
- for (i = 0; i < dev->nr_guest_pages; i++) {
- page = &dev->guest_pages[i];
+ } else {
ret = rte_vfio_container_dma_unmap(RTE_VFIO_DEFAULT_CONTAINER_FD,
- page->host_user_addr,
- page->host_iova,
- page->size);
+ page->host_user_addr,
+ page->host_iova,
+ page->size);
if (ret) {
/* like DMA map, ignore the kernel driver case when unmap. */
if (rte_errno == EINVAL)
- return;
+ return 0;
VHOST_CONFIG_LOG(dev->ifname, ERR, "DMA engine unmap failed");
+ return -1;
}
}
}
+
+ return 0;
+}
+
+static void
+async_dma_map(struct virtio_net *dev, bool do_map)
+{
+ uint32_t i;
+ struct rte_vhost_mem_region *reg;
+
+ for (i = 0; i < VHOST_MEMORY_MAX_NREGIONS; i++) {
+ reg = &dev->mem->regions[i];
+ if (reg->host_user_addr == 0)
+ continue;
+ async_dma_map_region(dev, reg, do_map);
+ }
}
static void
-free_mem_region(struct virtio_net *dev)
+free_mem_region(struct rte_vhost_mem_region *reg)
+{
+ if (reg != NULL && reg->mmap_addr) {
+ munmap(reg->mmap_addr, reg->mmap_size);
+ close(reg->fd);
+ memset(reg, 0, sizeof(struct rte_vhost_mem_region));
+ }
+}
+
+static void
+free_all_mem_regions(struct virtio_net *dev)
{
uint32_t i;
struct rte_vhost_mem_region *reg;
@@ -236,12 +267,10 @@ free_mem_region(struct virtio_net *dev)
if (dev->async_copy && rte_vfio_is_enabled("vfio"))
async_dma_map(dev, false);
- for (i = 0; i < dev->mem->nregions; i++) {
+ for (i = 0; i < VHOST_MEMORY_MAX_NREGIONS; i++) {
reg = &dev->mem->regions[i];
- if (reg->host_user_addr) {
- munmap(reg->mmap_addr, reg->mmap_size);
- close(reg->fd);
- }
+ if (reg->mmap_addr)
+ free_mem_region(reg);
}
}
@@ -255,7 +284,7 @@ vhost_backend_cleanup(struct virtio_net *dev)
vdpa_dev->ops->dev_cleanup(dev->vid);
if (dev->mem) {
- free_mem_region(dev);
+ free_all_mem_regions(dev);
rte_free(dev->mem);
dev->mem = NULL;
}
@@ -704,7 +733,7 @@ numa_realloc(struct virtio_net **pdev, struct vhost_virtqueue **pvq)
vhost_devices[dev->vid] = dev;
mem_size = sizeof(struct rte_vhost_memory) +
- sizeof(struct rte_vhost_mem_region) * dev->mem->nregions;
+ sizeof(struct rte_vhost_mem_region) * VHOST_MEMORY_MAX_NREGIONS;
mem = rte_realloc_socket(dev->mem, mem_size, 0, node);
if (!mem) {
VHOST_CONFIG_LOG(dev->ifname, ERR,
@@ -808,8 +837,10 @@ hua_to_alignment(struct rte_vhost_memory *mem, void *ptr)
uint32_t i;
uintptr_t hua = (uintptr_t)ptr;
- for (i = 0; i < mem->nregions; i++) {
+ for (i = 0; i < VHOST_MEMORY_MAX_NREGIONS; i++) {
r = &mem->regions[i];
+ if (r->host_user_addr == 0)
+ continue;
if (hua >= r->host_user_addr &&
hua < r->host_user_addr + r->size) {
return get_blk_size(r->fd);
--
2.43.0
^ 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