From: Xueming Li <xuemingl@nvidia.com>
To: Long Li <longli@microsoft.com>
Cc: Xueming Li <xuemingl@nvidia.com>, dpdk stable <stable@dpdk.org>
Subject: patch 'net/mana: fix multi-process tracking' has been queued to stable release 23.11.4
Date: Tue, 8 Apr 2025 15:44:32 +0800 [thread overview]
Message-ID: <20250408074515.361046-8-xuemingl@nvidia.com> (raw)
In-Reply-To: <20250408074515.361046-1-xuemingl@nvidia.com>
Hi,
FYI, your patch has been queued to stable release 23.11.4
Note it hasn't been pushed to http://dpdk.org/browse/dpdk-stable yet.
It will be pushed if I get no objections before 04/10/25. So please
shout if anyone has objections.
Also note that after the patch there's a diff of the upstream commit vs the
patch applied to the branch. This will indicate if there was any rebasing
needed to apply to the stable branch. If there were code changes for rebasing
(ie: not only metadata diffs), please double check that the rebase was
correctly done.
Queued patches are on a temporary branch at:
https://git.dpdk.org/dpdk-stable/log/?h=23.11-staging
This queued commit can be viewed at:
https://git.dpdk.org/dpdk-stable/commit/?h=23.11-staging&id=60357a01f1fd647417e59ed35c16e25023ea620e
Thanks.
Xueming Li <xuemingl@nvidia.com>
---
From 60357a01f1fd647417e59ed35c16e25023ea620e Mon Sep 17 00:00:00 2001
From: Long Li <longli@microsoft.com>
Date: Thu, 20 Feb 2025 15:32:02 -0800
Subject: [PATCH] net/mana: fix multi-process tracking
Cc: Xueming Li <xuemingl@nvidia.com>
[ upstream commit 57aa3ec91ecf13ab2f11e4dc0dc74c50a2afa0cc ]
The driver uses mana_shared_data for tracking usage count for primary
process. This is not correct as the mana_shared_data is allocated
by the primary and is meant to track usage of secondary process by the
primary process. And it creates a race condition when the device is
removed because the counter is no longer available if this shared
memory is freed.
Move the usage count tracking to mana_local_data and fix the race
condition in mana_pci_remove().
Fixes: 517ed6e2d590 ("net/mana: add basic driver with build environment")
Signed-off-by: Long Li <longli@microsoft.com>
---
drivers/net/mana/mana.c | 103 +++++++++++++++++++++++-----------------
drivers/net/mana/mana.h | 6 +--
drivers/net/mana/mp.c | 2 +-
3 files changed, 61 insertions(+), 50 deletions(-)
diff --git a/drivers/net/mana/mana.c b/drivers/net/mana/mana.c
index 65ca139be5..c0ff132fe1 100644
--- a/drivers/net/mana/mana.c
+++ b/drivers/net/mana/mana.c
@@ -23,9 +23,14 @@
#include "mana.h"
/* Shared memory between primary/secondary processes, per driver */
-/* Data to track primary/secondary usage */
struct mana_shared_data *mana_shared_data;
-static struct mana_shared_data mana_local_data;
+
+/* Local data to track device instance usage for primary/secondary processes */
+static struct mana_local_data {
+ int init_done;
+ unsigned int primary_cnt;
+ unsigned int secondary_cnt;
+} mana_local_data;
/* The memory region for the above data */
static const struct rte_memzone *mana_shared_mz;
@@ -1163,8 +1168,12 @@ mana_init_shared_data(void)
rte_spinlock_lock(&mana_shared_data_lock);
/* Skip if shared data is already initialized */
- if (mana_shared_data)
+ if (mana_shared_data) {
+ DRV_LOG(INFO, "shared data is already initialized");
goto exit;
+ }
+
+ memset(&mana_local_data, 0, sizeof(mana_local_data));
if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
mana_shared_mz = rte_memzone_reserve(MZ_MANA_SHARED_DATA,
@@ -1177,8 +1186,8 @@ mana_init_shared_data(void)
}
mana_shared_data = mana_shared_mz->addr;
- memset(mana_shared_data, 0, sizeof(*mana_shared_data));
- rte_spinlock_init(&mana_shared_data->lock);
+ rte_atomic_store_explicit(&mana_shared_data->secondary_cnt, 0,
+ rte_memory_order_relaxed);
} else {
secondary_mz = rte_memzone_lookup(MZ_MANA_SHARED_DATA);
if (!secondary_mz) {
@@ -1188,7 +1197,6 @@ mana_init_shared_data(void)
}
mana_shared_data = secondary_mz->addr;
- memset(&mana_local_data, 0, sizeof(mana_local_data));
}
exit:
@@ -1209,11 +1217,11 @@ mana_init_once(void)
if (ret)
return ret;
- rte_spinlock_lock(&mana_shared_data->lock);
+ rte_spinlock_lock(&mana_shared_data_lock);
switch (rte_eal_process_type()) {
case RTE_PROC_PRIMARY:
- if (mana_shared_data->init_done)
+ if (mana_local_data.init_done)
break;
ret = mana_mp_init_primary();
@@ -1221,7 +1229,7 @@ mana_init_once(void)
break;
DRV_LOG(ERR, "MP INIT PRIMARY");
- mana_shared_data->init_done = 1;
+ mana_local_data.init_done = 1;
break;
case RTE_PROC_SECONDARY:
@@ -1244,7 +1252,7 @@ mana_init_once(void)
break;
}
- rte_spinlock_unlock(&mana_shared_data->lock);
+ rte_spinlock_unlock(&mana_shared_data_lock);
return ret;
}
@@ -1315,11 +1323,6 @@ mana_probe_port(struct ibv_device *ibdev, struct ibv_device_attr_ex *dev_attr,
eth_dev->tx_pkt_burst = mana_tx_burst_removed;
eth_dev->rx_pkt_burst = mana_rx_burst_removed;
- rte_spinlock_lock(&mana_shared_data->lock);
- mana_shared_data->secondary_cnt++;
- mana_local_data.secondary_cnt++;
- rte_spinlock_unlock(&mana_shared_data->lock);
-
rte_eth_copy_pci_info(eth_dev, pci_dev);
rte_eth_dev_probing_finish(eth_dev);
@@ -1402,10 +1405,6 @@ mana_probe_port(struct ibv_device *ibdev, struct ibv_device_attr_ex *dev_attr,
goto failed;
}
- rte_spinlock_lock(&mana_shared_data->lock);
- mana_shared_data->primary_cnt++;
- rte_spinlock_unlock(&mana_shared_data->lock);
-
eth_dev->device = &pci_dev->device;
DRV_LOG(INFO, "device %s at port %u", name, eth_dev->data->port_id);
@@ -1548,13 +1547,38 @@ mana_pci_probe(struct rte_pci_driver *pci_drv __rte_unused,
count = mana_pci_probe_mac(pci_dev, NULL);
}
+ /* If no device is found, clean up resources if this is the last one */
if (!count) {
- rte_memzone_free(mana_shared_mz);
- mana_shared_mz = NULL;
- ret = -ENODEV;
+ rte_spinlock_lock(&mana_shared_data_lock);
+ if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
+ if (!mana_local_data.primary_cnt) {
+ mana_mp_uninit_primary();
+ rte_memzone_free(mana_shared_mz);
+ mana_shared_mz = NULL;
+ mana_shared_data = NULL;
+ }
+ } else {
+ if (!mana_local_data.secondary_cnt) {
+ mana_mp_uninit_secondary();
+ mana_shared_data = NULL;
+ }
+ }
+ rte_spinlock_unlock(&mana_shared_data_lock);
+ return -ENODEV;
}
- return ret;
+ /* At least one eth_dev is probed, increase counter for shared data */
+ rte_spinlock_lock(&mana_shared_data_lock);
+ if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
+ mana_local_data.primary_cnt++;
+ } else {
+ rte_atomic_fetch_add_explicit(&mana_shared_data->secondary_cnt, 1,
+ rte_memory_order_relaxed);
+ mana_local_data.secondary_cnt++;
+ }
+ rte_spinlock_unlock(&mana_shared_data_lock);
+
+ return 0;
}
static int
@@ -1569,45 +1593,36 @@ mana_dev_uninit(struct rte_eth_dev *dev)
static int
mana_pci_remove(struct rte_pci_device *pci_dev)
{
+ rte_spinlock_lock(&mana_shared_data_lock);
if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
- rte_spinlock_lock(&mana_shared_data_lock);
-
- rte_spinlock_lock(&mana_shared_data->lock);
+ RTE_VERIFY(mana_local_data.primary_cnt > 0);
+ mana_local_data.primary_cnt--;
- RTE_VERIFY(mana_shared_data->primary_cnt > 0);
- mana_shared_data->primary_cnt--;
- if (!mana_shared_data->primary_cnt) {
+ if (!mana_local_data.primary_cnt) {
DRV_LOG(DEBUG, "mp uninit primary");
mana_mp_uninit_primary();
- }
-
- rte_spinlock_unlock(&mana_shared_data->lock);
- /* Also free the shared memory if this is the last */
- if (!mana_shared_data->primary_cnt) {
+ /* Also free the shared memory if this is the last */
DRV_LOG(DEBUG, "free shared memezone data");
rte_memzone_free(mana_shared_mz);
mana_shared_mz = NULL;
+ mana_shared_data = NULL;
}
-
- rte_spinlock_unlock(&mana_shared_data_lock);
} else {
- rte_spinlock_lock(&mana_shared_data_lock);
-
- rte_spinlock_lock(&mana_shared_data->lock);
- RTE_VERIFY(mana_shared_data->secondary_cnt > 0);
- mana_shared_data->secondary_cnt--;
- rte_spinlock_unlock(&mana_shared_data->lock);
+ RTE_VERIFY(rte_atomic_load_explicit(&mana_shared_data->secondary_cnt,
+ rte_memory_order_relaxed) > 0);
+ rte_atomic_fetch_sub_explicit(&mana_shared_data->secondary_cnt, 1,
+ rte_memory_order_relaxed);
RTE_VERIFY(mana_local_data.secondary_cnt > 0);
mana_local_data.secondary_cnt--;
if (!mana_local_data.secondary_cnt) {
DRV_LOG(DEBUG, "mp uninit secondary");
mana_mp_uninit_secondary();
+ mana_shared_data = NULL;
}
-
- rte_spinlock_unlock(&mana_shared_data_lock);
}
+ rte_spinlock_unlock(&mana_shared_data_lock);
return rte_eth_dev_pci_generic_remove(pci_dev, mana_dev_uninit);
}
diff --git a/drivers/net/mana/mana.h b/drivers/net/mana/mana.h
index 822b8a1f15..7931a443a4 100644
--- a/drivers/net/mana/mana.h
+++ b/drivers/net/mana/mana.h
@@ -8,12 +8,8 @@
#define PCI_VENDOR_ID_MICROSOFT 0x1414
#define PCI_DEVICE_ID_MICROSOFT_MANA 0x00ba
-/* Shared data between primary/secondary processes */
struct mana_shared_data {
- rte_spinlock_t lock;
- int init_done;
- unsigned int primary_cnt;
- unsigned int secondary_cnt;
+ RTE_ATOMIC(uint32_t) secondary_cnt;
};
#define MANA_MAX_MTU 9000
diff --git a/drivers/net/mana/mp.c b/drivers/net/mana/mp.c
index 738487f65a..3d0aa0d493 100644
--- a/drivers/net/mana/mp.c
+++ b/drivers/net/mana/mp.c
@@ -305,7 +305,7 @@ mana_mp_req_on_rxtx(struct rte_eth_dev *dev, enum mana_mp_req_type type)
return;
}
- if (!mana_shared_data->secondary_cnt)
+ if (rte_atomic_load_explicit(&mana_shared_data->secondary_cnt, rte_memory_order_relaxed) == 0)
return;
mp_init_msg(&mp_req, type, dev->data->port_id);
--
2.34.1
---
Diff of the applied patch vs upstream commit (please double-check if non-empty:
---
--- - 2025-04-08 15:39:06.259162174 +0800
+++ 0007-net-mana-fix-multi-process-tracking.patch 2025-04-08 15:39:05.876436597 +0800
@@ -1 +1 @@
-From 57aa3ec91ecf13ab2f11e4dc0dc74c50a2afa0cc Mon Sep 17 00:00:00 2001
+From 60357a01f1fd647417e59ed35c16e25023ea620e Mon Sep 17 00:00:00 2001
@@ -4,0 +5,3 @@
+Cc: Xueming Li <xuemingl@nvidia.com>
+
+[ upstream commit 57aa3ec91ecf13ab2f11e4dc0dc74c50a2afa0cc ]
@@ -17 +19,0 @@
-Cc: stable@dpdk.org
@@ -27 +29 @@
-index c37c4e3444..2934da29f7 100644
+index 65ca139be5..c0ff132fe1 100644
@@ -47 +49 @@
-@@ -1167,8 +1172,12 @@ mana_init_shared_data(void)
+@@ -1163,8 +1168,12 @@ mana_init_shared_data(void)
@@ -61 +63 @@
-@@ -1181,8 +1190,8 @@ mana_init_shared_data(void)
+@@ -1177,8 +1186,8 @@ mana_init_shared_data(void)
@@ -72 +74 @@
-@@ -1192,7 +1201,6 @@ mana_init_shared_data(void)
+@@ -1188,7 +1197,6 @@ mana_init_shared_data(void)
@@ -80 +82 @@
-@@ -1213,11 +1221,11 @@ mana_init_once(void)
+@@ -1209,11 +1217,11 @@ mana_init_once(void)
@@ -94 +96 @@
-@@ -1225,7 +1233,7 @@ mana_init_once(void)
+@@ -1221,7 +1229,7 @@ mana_init_once(void)
@@ -103 +105 @@
-@@ -1248,7 +1256,7 @@ mana_init_once(void)
+@@ -1244,7 +1252,7 @@ mana_init_once(void)
@@ -112,3 +114,3 @@
-@@ -1319,11 +1327,6 @@ mana_probe_port(struct ibv_device *ibdev, struct ibv_device_attr_ex *dev_attr,
- eth_dev->tx_pkt_burst = mana_tx_burst;
- eth_dev->rx_pkt_burst = mana_rx_burst;
+@@ -1315,11 +1323,6 @@ mana_probe_port(struct ibv_device *ibdev, struct ibv_device_attr_ex *dev_attr,
+ eth_dev->tx_pkt_burst = mana_tx_burst_removed;
+ eth_dev->rx_pkt_burst = mana_rx_burst_removed;
@@ -124 +126 @@
-@@ -1406,10 +1409,6 @@ mana_probe_port(struct ibv_device *ibdev, struct ibv_device_attr_ex *dev_attr,
+@@ -1402,10 +1405,6 @@ mana_probe_port(struct ibv_device *ibdev, struct ibv_device_attr_ex *dev_attr,
@@ -135 +137 @@
-@@ -1552,13 +1551,38 @@ mana_pci_probe(struct rte_pci_driver *pci_drv __rte_unused,
+@@ -1548,13 +1547,38 @@ mana_pci_probe(struct rte_pci_driver *pci_drv __rte_unused,
@@ -178 +180 @@
-@@ -1573,45 +1597,36 @@ mana_dev_uninit(struct rte_eth_dev *dev)
+@@ -1569,45 +1593,36 @@ mana_dev_uninit(struct rte_eth_dev *dev)
@@ -237 +239 @@
-index 41a0ca6dfe..855d98911b 100644
+index 822b8a1f15..7931a443a4 100644
@@ -255 +257 @@
-index 34b45ed832..5467d385ce 100644
+index 738487f65a..3d0aa0d493 100644
@@ -258 +260 @@
-@@ -306,7 +306,7 @@ mana_mp_req_on_rxtx(struct rte_eth_dev *dev, enum mana_mp_req_type type)
+@@ -305,7 +305,7 @@ mana_mp_req_on_rxtx(struct rte_eth_dev *dev, enum mana_mp_req_type type)
next prev parent reply other threads:[~2025-04-08 7:46 UTC|newest]
Thread overview: 138+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-02-18 12:33 patch " Xueming Li
2025-02-18 12:33 ` patch 'test/ring: fix init with custom number of lcores' " Xueming Li
2025-02-18 12:33 ` patch 'vhost: clear ring addresses when getting vring base' " Xueming Li
2025-02-18 12:33 ` patch 'vhost: check GSO size validity' " Xueming Li
2025-02-18 12:33 ` patch 'vhost: fix log when setting max queue num' " Xueming Li
2025-02-18 12:34 ` patch 'vhost: reset packets count when not ready' " Xueming Li
2025-02-18 12:34 ` patch 'crypto/cnxk: fix build with GCC 15' " Xueming Li
2025-02-18 12:34 ` patch 'net/thunderx/base: " Xueming Li
2025-02-18 12:34 ` patch 'eal/x86: fix some intrinsics header include for Windows' " Xueming Li
2025-02-18 12:34 ` patch 'test/bonding: fix active backup receive test' " Xueming Li
2025-02-18 12:34 ` patch 'net/bonding: fix dedicated queue setup' " Xueming Li
2025-02-18 12:34 ` patch 'net/hns3: fix mbuf freeing in simple Tx path' " Xueming Li
2025-02-18 12:34 ` patch 'net/hns3: remove PVID info dump for VF' " Xueming Li
2025-02-18 12:34 ` patch 'net/hns3: rename RAS module' " Xueming Li
2025-02-18 12:34 ` patch 'net/sfc: remove unnecessary assignment' " Xueming Li
2025-02-18 12:34 ` patch 'net/mlx5: fix polling CQEs' " Xueming Li
2025-02-18 12:34 ` patch 'net/iavf: remove reset of Tx prepare function pointer' " Xueming Li
2025-02-18 12:34 ` patch 'net/ice: fix memory leak in scalar Rx' " Xueming Li
2025-02-18 12:34 ` patch 'common/cnxk: fix atomic load in batch ops' " Xueming Li
2025-02-18 12:34 ` patch 'common/cnxk: fix DPI mailbox structure' " Xueming Li
2025-02-18 12:34 ` patch 'eventdev: fix format string data type in log messages' " Xueming Li
2025-02-18 12:34 ` patch 'crypto/virtio: fix redundant queue free' " Xueming Li
2025-02-18 12:34 ` patch 'crypto/openssl: fix CMAC auth context update' " Xueming Li
2025-02-18 12:34 ` patch 'crypto/virtio: fix data queues iteration' " Xueming Li
2025-02-18 12:34 ` patch 'net/octeon_ep: remove useless assignment' " Xueming Li
2025-02-18 12:34 ` patch 'net/enetfec: " Xueming Li
2025-02-18 12:34 ` patch 'net/nfp: fix multiple PFs check from NSP' " Xueming Li
2025-02-18 12:34 ` patch 'net/nfp: fix misuse of function return values' " Xueming Li
2025-02-18 12:34 ` patch 'net/nfp: fix multi-PF control flag' " Xueming Li
2025-02-18 12:34 ` patch 'net/ice: fix flows handling' " Xueming Li
2025-02-18 12:34 ` patch 'net/cnxk: fix NIX send header L3 type' " Xueming Li
2025-02-18 12:34 ` patch 'gro: fix unprocessed IPv4 packets' " Xueming Li
2025-02-18 12:34 ` patch 'eal/linux: fix memseg length in legacy mem init' " Xueming Li
2025-02-18 12:34 ` patch 'buildtools: fix some Python regex syntax warnings' " Xueming Li
2025-02-18 12:34 ` patch 'use Python raw string notation' " Xueming Li
2025-02-18 12:34 ` patch 'net/af_packet: fix socket close on device stop' " Xueming Li
2025-02-18 12:34 ` patch 'ethdev: fix functions available in new device event' " Xueming Li
2025-02-18 12:34 ` patch 'vhost: add null callback checks' " Xueming Li
2025-02-18 12:34 ` patch 'build: force GCC 15 to initialize padding bits' " Xueming Li
2025-02-18 12:34 ` patch 'net/bnxt: fix indication of allocation' " Xueming Li
2025-02-18 12:34 ` patch 'net/bnxt: fix crash when representor is re-attached' " Xueming Li
2025-02-18 12:34 ` patch 'net/mlx5: fix Netlink socket leak' " Xueming Li
2025-02-18 12:34 ` patch 'net/mlx5: adjust actions per rule limitation' " Xueming Li
2025-02-18 12:34 ` patch 'net/mlx5: fix flush of non-template flow rules' " Xueming Li
2025-02-18 12:34 ` patch 'net/mlx5: fix GRE flow match with SWS' " Xueming Li
2025-02-18 12:34 ` patch 'net/igc/base: fix deadlock when writing i225 register' " Xueming Li
2025-02-18 12:34 ` patch 'net/igc/base: fix infinite loop' " Xueming Li
2025-02-18 12:34 ` patch 'net/igc/base: fix bitwise operation type' " Xueming Li
2025-02-18 12:34 ` patch 'net/igc/base: increase PHY power up delay' " Xueming Li
2025-02-18 12:34 ` patch 'net/igc/base: reset loop variable' " Xueming Li
2025-02-18 12:34 ` patch 'net/igc/base: fix LTR for i225' " Xueming Li
2025-02-18 12:34 ` patch 'net/igc/base: fix typo in LTR calculation' " Xueming Li
2025-02-18 12:34 ` patch 'net/igc/base: fix unused value' " Xueming Li
2025-02-18 12:34 ` patch 'net/igc/base: fix semaphore timeout " Xueming Li
2025-02-18 12:34 ` patch 'net/igc/base: fix iterator type' " Xueming Li
2025-02-18 12:34 ` patch 'net/igc/base: fix MAC address hash bit shift' " Xueming Li
2025-02-18 12:34 ` patch 'net/igc/base: fix data type in MAC hash' " Xueming Li
2025-02-18 12:34 ` patch 'net/igc/base: fix NVM data type in bit shift' " Xueming Li
2025-02-18 12:34 ` patch 'net/e1000/base: fix semaphore timeout value' " Xueming Li
2025-02-18 12:34 ` patch 'net/e1000/base: correct mPHY access logic' " Xueming Li
2025-02-18 12:34 ` patch 'net/e1000/base: fix iterator type' " Xueming Li
2025-02-18 12:34 ` patch 'net/e1000/base: fix MAC address hash bit shift' " Xueming Li
2025-02-18 12:34 ` patch 'net/e1000/base: fix data type in MAC hash' " Xueming Li
2025-02-18 12:34 ` patch 'net/e1000/base: fix uninitialized variable' " Xueming Li
2025-02-18 12:34 ` patch 'net/e1000/base: fix bitwise operation type' " Xueming Li
2025-02-18 12:35 ` patch 'net/e1000/base: fix NVM data type in bit shift' " Xueming Li
2025-02-18 12:35 ` patch 'net/e1000/base: fix reset for 82580' " Xueming Li
2025-02-18 12:35 ` patch 'net/e1000/base: fix unchecked return' " Xueming Li
2025-02-18 12:35 ` patch 'net/e1000/base: skip management check for 82575' " Xueming Li
2025-02-18 12:35 ` patch 'common/idpf: fix void function returning a value' " Xueming Li
2025-02-18 12:35 ` patch 'net/intel: fix void functions " Xueming Li
2025-02-18 12:35 ` patch 'net/intel: fix build with icx' " Xueming Li
2025-02-18 12:35 ` patch 'net/hns3: fix copper port initialization' " Xueming Li
2025-02-18 12:35 ` patch 'net/hns3: fix reset timeout' " Xueming Li
2025-02-18 12:35 ` patch 'net/cpfl: fix representor parsing log' " Xueming Li
2025-02-18 12:35 ` patch 'raw/cnxk_gpio: fix file descriptor leak' " Xueming Li
2025-02-18 12:35 ` patch 'eal: fix devargs layers parsing out of bounds' " Xueming Li
2025-02-18 12:35 ` patch 'net/qede: fix debug messages array' " Xueming Li
2025-02-18 12:35 ` patch 'net/hinic: fix flow type bitmask overflow' " Xueming Li
2025-02-18 12:35 ` patch 'crypto/dpaa2_sec: fix bitmask truncation' " Xueming Li
2025-02-18 12:35 ` patch 'crypto/dpaa_sec: " Xueming Li
2025-02-18 12:35 ` patch 'event/dpaa: " Xueming Li
2025-02-18 12:35 ` patch 'net/dpaa: " Xueming Li
2025-02-18 12:35 ` patch 'net/dpaa2: " Xueming Li
2025-02-18 12:35 ` patch 'net/qede: fix nested loops' " Xueming Li
2025-02-18 12:35 ` patch 'examples/l3fwd: fix socket ID check' " Xueming Li
2025-02-18 12:35 ` patch 'common/cnxk: fix null " Xueming Li
2025-02-18 12:35 ` patch 'eal/linux: remove useless assignments' " Xueming Li
2025-02-18 12:35 ` patch 'mempool: fix errno in empty create' " Xueming Li
2025-04-08 7:44 ` patch " Xueming Li
2025-04-08 7:44 ` patch 'ci: build with MSVC in GHA' " Xueming Li
2025-04-08 7:44 ` patch 'net/netvsc: scan all net devices under the PCI device' " Xueming Li
2025-04-08 7:44 ` patch 'net/netvsc: remove device if its net devices removed' " Xueming Li
2025-04-08 7:44 ` patch 'doc: fix feature flags for queue start/stop' " Xueming Li
2025-04-08 7:44 ` patch 'app/testpmd: show all DCB priority TC map' " Xueming Li
2025-04-08 7:44 ` patch 'app/testpmd: avoid crash in DCB config' " Xueming Li
2025-04-08 7:44 ` Xueming Li [this message]
2025-04-08 7:44 ` patch 'app/testpmd: fix out-of-bound reference in offload " Xueming Li
2025-04-08 7:44 ` patch 'net/txgbe: remove useless condition for SW-FW sync' " Xueming Li
2025-04-08 7:44 ` patch 'bus/pci: fix registered device name' " Xueming Li
2025-04-08 7:44 ` patch 'vhost/crypto: skip fetch before vring init' " Xueming Li
2025-04-08 7:44 ` patch 'examples/vhost_crypto: fix user callbacks' " Xueming Li
2025-04-08 7:44 ` patch 'vhost: check descriptor chains length' " Xueming Li
2025-04-08 7:44 ` patch 'test/bbdev: update FFT test vectors' " Xueming Li
2025-04-08 8:01 ` patch 'test/event: fix number of queues in eventdev conf' " Xueming Li
2025-04-08 8:01 ` patch 'net/e1000: fix crashes in secondary processes' " Xueming Li
2025-04-08 8:01 ` patch 'net/ixgbe: " Xueming Li
2025-04-08 8:01 ` patch 'net/ixgbe: fix minimum Rx/Tx descriptors' " Xueming Li
2025-04-08 8:01 ` patch 'net/mlx5/hws: fix fragmented packet type matching' " Xueming Li
2025-04-08 8:01 ` patch 'net/mlx5: fix leak in HWS flow counter action' " Xueming Li
2025-04-08 8:01 ` patch 'net/mlx5: fix hardware packet type translation' " Xueming Li
2025-04-08 8:01 ` patch 'common/cnxk: fix inbound IPsec SA setup' " Xueming Li
2025-04-08 8:01 ` patch 'stack: fix pop in C11 implementation' " Xueming Li
2025-04-08 8:01 ` patch 'test/crypto: fix AES-ECB test lengths' " Xueming Li
2025-04-08 8:01 ` patch 'examples/ipsec-secgw: fix IV length in CTR 192/256' " Xueming Li
2025-04-08 8:01 ` patch 'crypto/cnxk: fix asymmetric operation status code' " Xueming Li
2025-04-08 8:01 ` patch 'test/crypto: remove unused variable' " Xueming Li
2025-04-08 8:01 ` patch 'crypto/openssl: validate incorrect RSA signature' " Xueming Li
2025-04-08 8:01 ` patch 'test/crypto: fix check for OOP header data' " Xueming Li
2025-04-08 8:01 ` patch 'crypto/qat: fix SM3 state size' " Xueming Li
2025-04-08 8:01 ` patch 'test/dma: fix pointers in IOVA as PA mode' " Xueming Li
2025-04-08 8:01 ` patch 'net/iavf: fix mbuf release in Arm multi-process' " Xueming Li
2025-04-08 8:01 ` patch 'net/ice: fix flow engines order' " Xueming Li
2025-04-08 8:01 ` patch 'net/ice: fix dropped packets when using VRRP' " Xueming Li
2025-04-08 8:10 ` patch 'net/iavf: check interrupt registration failure' " Xueming Li
2025-04-08 8:10 ` patch 'net/iavf: fix crash on app exit on FreeBSD' " Xueming Li
2025-04-08 8:10 ` patch 'net/mlx5: fix hairpin queue release' " Xueming Li
2025-04-08 8:10 ` patch 'net/mlx5: fix LACP packet handling in isolated mode' " Xueming Li
2025-04-08 8:10 ` patch 'net/mlx5/hws: fix crash using represented port without ID' " Xueming Li
2025-04-08 8:10 ` patch 'net/mlx5/hws: fix GTP flags matching' " Xueming Li
2025-04-08 8:10 ` patch 'net/mlx5: fix IPIP tunnel verification' " Xueming Li
2025-04-08 8:10 ` patch 'net/mlx5: fix GRE matching on root table' " Xueming Li
2025-04-08 8:10 ` patch 'pdump: clear statistics when enabled' " Xueming Li
2025-04-08 8:10 ` patch 'examples/ipsec-secgw: fix cryptodev and eventdev IDs' " Xueming Li
2025-04-08 8:16 ` patch 'eal: fix undetected NUMA nodes' " Xueming Li
2025-04-08 8:16 ` patch 'examples/ptpclient: fix message parsing' " Xueming Li
2025-04-08 8:16 ` patch 'net/nfp: fix VF link speed problem' " Xueming Li
2025-04-08 8:16 ` patch 'net/gve: allocate Rx QPL pages using malloc' " Xueming Li
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20250408074515.361046-8-xuemingl@nvidia.com \
--to=xuemingl@nvidia.com \
--cc=longli@microsoft.com \
--cc=stable@dpdk.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).