* [Patch net-next 06/12] net: hns3: use HNS3_NIC_STATE_RESETTING to indicate resetting
From: Huazhong Tan @ 2018-11-07 4:06 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-kernel, salil.mehta, yisen.zhuang, linuxarm
In-Reply-To: <1541563578-28973-1-git-send-email-tanhuazhong@huawei.com>
While hclge is going to reset, it will notify its client with
HNAE3_DOWN_CLIENT, so this client should get into a resetting
status from this moment, other operations from the stack need to
be blocked as well. And when the reset is finished, the client
will be notified with HNAE3_UP_CLIENT, so this is the end of
the resetting status.
This patch uses HNS3_NIC_STATE_RESETTING flag to implement that,
and adds hns3_nic_resetting() to indicate which operation is not
allowed.
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
---
drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c | 12 ++++++++++++
drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 10 ++++++++++
drivers/net/ethernet/hisilicon/hns3/hns3_enet.h | 7 +++++++
drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c | 19 +++++++++++++++++++
4 files changed, 48 insertions(+)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c b/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c
index ea5f8a8..b6fabbb 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c
@@ -9,6 +9,9 @@ int hns3_dcbnl_ieee_getets(struct net_device *ndev, struct ieee_ets *ets)
{
struct hnae3_handle *h = hns3_get_handle(ndev);
+ if (hns3_nic_resetting(ndev))
+ return -EBUSY;
+
if (h->kinfo.dcb_ops->ieee_getets)
return h->kinfo.dcb_ops->ieee_getets(h, ets);
@@ -20,6 +23,9 @@ int hns3_dcbnl_ieee_setets(struct net_device *ndev, struct ieee_ets *ets)
{
struct hnae3_handle *h = hns3_get_handle(ndev);
+ if (hns3_nic_resetting(ndev))
+ return -EBUSY;
+
if (h->kinfo.dcb_ops->ieee_setets)
return h->kinfo.dcb_ops->ieee_setets(h, ets);
@@ -31,6 +37,9 @@ int hns3_dcbnl_ieee_getpfc(struct net_device *ndev, struct ieee_pfc *pfc)
{
struct hnae3_handle *h = hns3_get_handle(ndev);
+ if (hns3_nic_resetting(ndev))
+ return -EBUSY;
+
if (h->kinfo.dcb_ops->ieee_getpfc)
return h->kinfo.dcb_ops->ieee_getpfc(h, pfc);
@@ -42,6 +51,9 @@ int hns3_dcbnl_ieee_setpfc(struct net_device *ndev, struct ieee_pfc *pfc)
{
struct hnae3_handle *h = hns3_get_handle(ndev);
+ if (hns3_nic_resetting(ndev))
+ return -EBUSY;
+
if (h->kinfo.dcb_ops->ieee_setpfc)
return h->kinfo.dcb_ops->ieee_setpfc(h, pfc);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index e4cf3247..d573f5f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -384,6 +384,9 @@ static int hns3_nic_net_open(struct net_device *netdev)
struct hnae3_knic_private_info *kinfo;
int i, ret;
+ if (hns3_nic_resetting(netdev))
+ return -EBUSY;
+
netif_carrier_off(netdev);
ret = hns3_nic_set_real_num_queue(netdev);
@@ -3749,6 +3752,10 @@ static int hns3_reset_notify_down_enet(struct hnae3_handle *handle)
struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
struct hnae3_knic_private_info *kinfo = &handle->kinfo;
struct net_device *ndev = kinfo->netdev;
+ struct hns3_nic_priv *priv = netdev_priv(ndev);
+
+ if (test_and_set_bit(HNS3_NIC_STATE_RESETTING, &priv->state))
+ return 0;
/* it is cumbersome for hardware to pick-and-choose entries for deletion
* from table space. Hence, for function reset software intervention is
@@ -3768,6 +3775,7 @@ static int hns3_reset_notify_down_enet(struct hnae3_handle *handle)
static int hns3_reset_notify_up_enet(struct hnae3_handle *handle)
{
struct hnae3_knic_private_info *kinfo = &handle->kinfo;
+ struct hns3_nic_priv *priv = netdev_priv(kinfo->netdev);
int ret = 0;
if (netif_running(kinfo->netdev)) {
@@ -3780,6 +3788,8 @@ static int hns3_reset_notify_up_enet(struct hnae3_handle *handle)
handle->last_reset_time = jiffies;
}
+ clear_bit(HNS3_NIC_STATE_RESETTING, &priv->state);
+
return ret;
}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 3e9db73..cfd6a71 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -599,6 +599,13 @@ static inline bool hns3_dev_ongoing_func_reset(struct hnae3_ae_dev *ae_dev)
#define hns3_read_dev(a, reg) \
hns3_read_reg((a)->io_base, (reg))
+static inline bool hns3_nic_resetting(struct net_device *netdev)
+{
+ struct hns3_nic_priv *priv = netdev_priv(netdev);
+
+ return test_bit(HNS3_NIC_STATE_RESETTING, &priv->state);
+}
+
#define hns3_write_dev(a, reg, value) \
hns3_write_reg((a)->io_base, (reg), (value))
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index a4762c2..4563638 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -291,6 +291,11 @@ static void hns3_self_test(struct net_device *ndev,
int test_index = 0;
u32 i;
+ if (hns3_nic_resetting(ndev)) {
+ netdev_err(ndev, "dev resetting!");
+ return;
+ }
+
/* Only do offline selftest, or pass by default */
if (eth_test->flags != ETH_TEST_FL_OFFLINE)
return;
@@ -530,6 +535,11 @@ static void hns3_get_ringparam(struct net_device *netdev,
struct hnae3_handle *h = priv->ae_handle;
int queue_num = h->kinfo.num_tqps;
+ if (hns3_nic_resetting(netdev)) {
+ netdev_err(netdev, "dev resetting!");
+ return;
+ }
+
param->tx_max_pending = HNS3_RING_MAX_PENDING;
param->rx_max_pending = HNS3_RING_MAX_PENDING;
@@ -760,6 +770,9 @@ static int hns3_set_ringparam(struct net_device *ndev,
u32 old_desc_num, new_desc_num;
int ret;
+ if (hns3_nic_resetting(ndev))
+ return -EBUSY;
+
if (param->rx_mini_pending || param->rx_jumbo_pending)
return -EINVAL;
@@ -872,6 +885,9 @@ static int hns3_get_coalesce_per_queue(struct net_device *netdev, u32 queue,
struct hnae3_handle *h = priv->ae_handle;
u16 queue_num = h->kinfo.num_tqps;
+ if (hns3_nic_resetting(netdev))
+ return -EBUSY;
+
if (queue >= queue_num) {
netdev_err(netdev,
"Invalid queue value %d! Queue max id=%d\n",
@@ -1033,6 +1049,9 @@ static int hns3_set_coalesce(struct net_device *netdev,
int ret;
int i;
+ if (hns3_nic_resetting(netdev))
+ return -EBUSY;
+
ret = hns3_check_coalesce_para(netdev, cmd);
if (ret)
return ret;
--
2.7.4
^ permalink raw reply related
* [Patch net-next 05/12] net: hns3: enable/disable ring in the enet while doing UP/DOWN
From: Huazhong Tan @ 2018-11-07 4:06 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-kernel, salil.mehta, yisen.zhuang, linuxarm
In-Reply-To: <1541563578-28973-1-git-send-email-tanhuazhong@huawei.com>
While hardware gets into reset status, the firmware will not respond to
driver's command request, which may cause ring not disabled problem
during reset process.
So this patch uses register instead of command to enable/disable the ring
in the enet while doing UP/DOWN operation.
Also, HNS3_RING_RX_VM_REG is previously unused, so change it to the
correct meaning, and add a wrapper function for readl().
Fixes: 46a3df9f9718 ("net: hns3: Add HNS3 Acceleration Engine & Compatibility Layer Support")
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
---
drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 30 +++++++++++++++++++
drivers/net/ethernet/hisilicon/hns3/hns3_enet.h | 12 +++++++-
.../ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 8 -----
.../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 35 ----------------------
4 files changed, 41 insertions(+), 44 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 75e3e79..e4cf3247 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -312,6 +312,24 @@ static u16 hns3_get_max_available_channels(struct hnae3_handle *h)
return min_t(u16, rss_size, max_rss_size);
}
+static void hns3_tqp_enable(struct hnae3_queue *tqp)
+{
+ u32 rcb_reg;
+
+ rcb_reg = hns3_read_dev(tqp, HNS3_RING_EN_REG);
+ rcb_reg |= BIT(HNS3_RING_EN_B);
+ hns3_write_dev(tqp, HNS3_RING_EN_REG, rcb_reg);
+}
+
+static void hns3_tqp_disable(struct hnae3_queue *tqp)
+{
+ u32 rcb_reg;
+
+ rcb_reg = hns3_read_dev(tqp, HNS3_RING_EN_REG);
+ rcb_reg &= ~BIT(HNS3_RING_EN_B);
+ hns3_write_dev(tqp, HNS3_RING_EN_REG, rcb_reg);
+}
+
static int hns3_nic_net_up(struct net_device *netdev)
{
struct hns3_nic_priv *priv = netdev_priv(netdev);
@@ -334,6 +352,10 @@ static int hns3_nic_net_up(struct net_device *netdev)
for (i = 0; i < priv->vector_num; i++)
hns3_vector_enable(&priv->tqp_vector[i]);
+ /* enable rcb */
+ for (j = 0; j < h->kinfo.num_tqps; j++)
+ hns3_tqp_enable(h->kinfo.tqp[j]);
+
/* start the ae_dev */
ret = h->ae_algo->ops->start ? h->ae_algo->ops->start(h) : 0;
if (ret)
@@ -344,6 +366,9 @@ static int hns3_nic_net_up(struct net_device *netdev)
return 0;
out_start_err:
+ while (j--)
+ hns3_tqp_disable(h->kinfo.tqp[j]);
+
for (j = i - 1; j >= 0; j--)
hns3_vector_disable(&priv->tqp_vector[j]);
@@ -385,6 +410,7 @@ static int hns3_nic_net_open(struct net_device *netdev)
static void hns3_nic_net_down(struct net_device *netdev)
{
struct hns3_nic_priv *priv = netdev_priv(netdev);
+ struct hnae3_handle *h = hns3_get_handle(netdev);
const struct hnae3_ae_ops *ops;
int i;
@@ -395,6 +421,10 @@ static void hns3_nic_net_down(struct net_device *netdev)
for (i = 0; i < priv->vector_num; i++)
hns3_vector_disable(&priv->tqp_vector[i]);
+ /* disable rcb */
+ for (i = 0; i < h->kinfo.num_tqps; i++)
+ hns3_tqp_disable(h->kinfo.tqp[i]);
+
/* stop ae_dev */
ops = priv->ae_handle->ae_algo->ops;
if (ops->stop)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 7b759e4..3e9db73 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -47,7 +47,7 @@ enum hns3_nic_state {
#define HNS3_RING_PREFETCH_EN_REG 0x0007C
#define HNS3_RING_CFG_VF_NUM_REG 0x00080
#define HNS3_RING_ASID_REG 0x0008C
-#define HNS3_RING_RX_VM_REG 0x00090
+#define HNS3_RING_EN_REG 0x00090
#define HNS3_RING_T0_BE_RST 0x00094
#define HNS3_RING_COULD_BE_RST 0x00098
#define HNS3_RING_WRR_WEIGHT_REG 0x0009c
@@ -194,6 +194,8 @@ enum hns3_nic_state {
#define HNS3_VECTOR_RL_OFFSET 0x900
#define HNS3_VECTOR_RL_EN_B 6
+#define HNS3_RING_EN_B 0
+
enum hns3_pkt_l3t_type {
HNS3_L3T_NONE,
HNS3_L3T_IPV6,
@@ -577,6 +579,11 @@ static inline int is_ring_empty(struct hns3_enet_ring *ring)
return ring->next_to_use == ring->next_to_clean;
}
+static inline u32 hns3_read_reg(void __iomem *base, u32 reg)
+{
+ return readl(base + reg);
+}
+
static inline void hns3_write_reg(void __iomem *base, u32 reg, u32 value)
{
u8 __iomem *reg_addr = READ_ONCE(base);
@@ -589,6 +596,9 @@ static inline bool hns3_dev_ongoing_func_reset(struct hnae3_ae_dev *ae_dev)
return (ae_dev && (ae_dev->reset_type == HNAE3_FUNC_RESET));
}
+#define hns3_read_dev(a, reg) \
+ hns3_read_reg((a)->io_base, (reg))
+
#define hns3_write_dev(a, reg, value) \
hns3_write_reg((a)->io_base, (reg), (value))
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index b669542..b784db0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -4843,10 +4843,6 @@ static int hclge_ae_start(struct hnae3_handle *handle)
{
struct hclge_vport *vport = hclge_get_vport(handle);
struct hclge_dev *hdev = vport->back;
- int i;
-
- for (i = 0; i < vport->alloc_tqps; i++)
- hclge_tqp_enable(hdev, i, 0, true);
/* mac enable */
hclge_cfg_mac_mode(hdev, true);
@@ -4866,7 +4862,6 @@ static void hclge_ae_stop(struct hnae3_handle *handle)
{
struct hclge_vport *vport = hclge_get_vport(handle);
struct hclge_dev *hdev = vport->back;
- int i;
set_bit(HCLGE_STATE_DOWN, &hdev->state);
@@ -4879,9 +4874,6 @@ static void hclge_ae_stop(struct hnae3_handle *handle)
return;
}
- for (i = 0; i < vport->alloc_tqps; i++)
- hclge_tqp_enable(hdev, i, 0, false);
-
/* Mac disable */
hclge_cfg_mac_mode(hdev, false);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 517204b..7531bdd 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -956,13 +956,6 @@ static int hclgevf_tqp_enable(struct hclgevf_dev *hdev, int tqp_id,
return status;
}
-static int hclgevf_get_queue_id(struct hnae3_queue *queue)
-{
- struct hclgevf_tqp *tqp = container_of(queue, struct hclgevf_tqp, q);
-
- return tqp->index;
-}
-
static void hclgevf_reset_tqp_stats(struct hnae3_handle *handle)
{
struct hnae3_knic_private_info *kinfo = &handle->kinfo;
@@ -1593,21 +1586,7 @@ static int hclgevf_init_vlan_config(struct hclgevf_dev *hdev)
static int hclgevf_ae_start(struct hnae3_handle *handle)
{
- struct hnae3_knic_private_info *kinfo = &handle->kinfo;
struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
- int i, queue_id;
-
- for (i = 0; i < kinfo->num_tqps; i++) {
- /* ring enable */
- queue_id = hclgevf_get_queue_id(kinfo->tqp[i]);
- if (queue_id < 0) {
- dev_warn(&hdev->pdev->dev,
- "Get invalid queue id, ignore it\n");
- continue;
- }
-
- hclgevf_tqp_enable(hdev, queue_id, 0, true);
- }
/* reset tqp stats */
hclgevf_reset_tqp_stats(handle);
@@ -1622,24 +1601,10 @@ static int hclgevf_ae_start(struct hnae3_handle *handle)
static void hclgevf_ae_stop(struct hnae3_handle *handle)
{
- struct hnae3_knic_private_info *kinfo = &handle->kinfo;
struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
- int i, queue_id;
set_bit(HCLGEVF_STATE_DOWN, &hdev->state);
- for (i = 0; i < kinfo->num_tqps; i++) {
- /* Ring disable */
- queue_id = hclgevf_get_queue_id(kinfo->tqp[i]);
- if (queue_id < 0) {
- dev_warn(&hdev->pdev->dev,
- "Get invalid queue id, ignore it\n");
- continue;
- }
-
- hclgevf_tqp_enable(hdev, queue_id, 0, false);
- }
-
/* reset tqp stats */
hclgevf_reset_tqp_stats(handle);
del_timer_sync(&hdev->service_timer);
--
2.7.4
^ permalink raw reply related
* [Patch net-next 04/12] net: hns3: adjust the location of clearing the table when doing reset
From: Huazhong Tan @ 2018-11-07 4:06 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-kernel, salil.mehta, yisen.zhuang, linuxarm
In-Reply-To: <1541563578-28973-1-git-send-email-tanhuazhong@huawei.com>
When doing a function reset, the hardware table should be cleared
before the hardware reset. In current code, this clearing is done
in hns3_reset_notify_uninit_enet, but it is too late, because
the hardware reset is already done, hns3_reset_notify_down_enet
is more suitable to do that.
Fixes: bb6b94a896d4 ("net: hns3: Add reset interface implementation in client")
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
---
drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 20 ++++++++++----------
1 file changed, 10 insertions(+), 10 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index d51469c..75e3e79 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -3716,9 +3716,19 @@ static void hns3_restore_coal(struct hns3_nic_priv *priv)
static int hns3_reset_notify_down_enet(struct hnae3_handle *handle)
{
+ struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
struct hnae3_knic_private_info *kinfo = &handle->kinfo;
struct net_device *ndev = kinfo->netdev;
+ /* it is cumbersome for hardware to pick-and-choose entries for deletion
+ * from table space. Hence, for function reset software intervention is
+ * required to delete the entries
+ */
+ if (hns3_dev_ongoing_func_reset(ae_dev)) {
+ hns3_remove_hw_addr(ndev);
+ hns3_del_all_fd_rules(ndev, false);
+ }
+
if (!netif_running(ndev))
return 0;
@@ -3797,7 +3807,6 @@ static int hns3_reset_notify_init_enet(struct hnae3_handle *handle)
static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle)
{
- struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
struct net_device *netdev = handle->kinfo.netdev;
struct hns3_nic_priv *priv = netdev_priv(netdev);
int ret;
@@ -3821,15 +3830,6 @@ static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle)
if (ret)
netdev_err(netdev, "uninit ring error\n");
- /* it is cumbersome for hardware to pick-and-choose entries for deletion
- * from table space. Hence, for function reset software intervention is
- * required to delete the entries
- */
- if (hns3_dev_ongoing_func_reset(ae_dev)) {
- hns3_remove_hw_addr(netdev);
- hns3_del_all_fd_rules(netdev, false);
- }
-
clear_bit(HNS3_NIC_STATE_INITED, &priv->state);
return ret;
--
2.7.4
^ permalink raw reply related
* [Patch net-next 03/12] net: hns3: provide some interface & information for the client
From: Huazhong Tan @ 2018-11-07 4:06 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-kernel, salil.mehta, yisen.zhuang, linuxarm
In-Reply-To: <1541563578-28973-1-git-send-email-tanhuazhong@huawei.com>
The client needs to know if the hardware is resetting when
loading or unloading itself, because client may abort the loading
process or wait for the reset process to finish when unloading
if hardware is resetting.
So this patch provides these interfaces to do it.
1. get_hw_reset_stat, the reset status of hardware.
2. ae_dev_resetting, whether reset task is scheduling.
3. ae_dev_reset_cnt, how many reset has been done.
Also, the RoCE client needs some field in the hnae3_roce_private_info
to save its state, and process_hw_error interface in the
hnae3_client_ops to process hardware errors.
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
---
drivers/net/ethernet/hisilicon/hns3/hnae3.h | 12 +++++++++
.../ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 29 ++++++++++++++++++++++
.../ethernet/hisilicon/hns3/hns3pf/hclge_main.h | 1 +
.../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 25 +++++++++++++++++++
.../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h | 1 +
5 files changed, 68 insertions(+)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 7deab92..f57034d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -162,6 +162,7 @@ struct hnae3_client_ops {
int (*setup_tc)(struct hnae3_handle *handle, u8 tc);
int (*reset_notify)(struct hnae3_handle *handle,
enum hnae3_reset_notify_type type);
+ enum hnae3_reset_type (*process_hw_error)(struct hnae3_handle *handle);
};
#define HNAE3_CLIENT_NAME_LENGTH 16
@@ -432,6 +433,9 @@ struct hnae3_ae_ops {
int (*restore_fd_rules)(struct hnae3_handle *handle);
void (*enable_fd)(struct hnae3_handle *handle, bool enable);
pci_ers_result_t (*process_hw_error)(struct hnae3_ae_dev *ae_dev);
+ bool (*get_hw_reset_stat)(struct hnae3_handle *handle);
+ bool (*ae_dev_resetting)(struct hnae3_handle *handle);
+ unsigned long (*ae_dev_reset_cnt)(struct hnae3_handle *handle);
};
struct hnae3_dcb_ops {
@@ -490,6 +494,14 @@ struct hnae3_roce_private_info {
void __iomem *roce_io_base;
int base_vector;
int num_vectors;
+
+ /* The below attributes defined for RoCE client, hnae3 gives
+ * initial values to them, and RoCE client can modify and use
+ * them.
+ */
+ unsigned long reset_state;
+ unsigned long instance_state;
+ unsigned long state;
};
struct hnae3_unic_private_info {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 5e6006b..b669542 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2466,6 +2466,7 @@ static void hclge_reset(struct hclge_dev *hdev)
* know if device is undergoing reset
*/
ae_dev->reset_type = hdev->reset_type;
+ hdev->reset_count++;
/* perform reset of the stack & ae device for a client */
handle = &hdev->vport[0].nic;
rtnl_lock();
@@ -4604,6 +4605,31 @@ static int hclge_get_all_rules(struct hnae3_handle *handle,
return 0;
}
+static bool hclge_get_hw_reset_stat(struct hnae3_handle *handle)
+{
+ struct hclge_vport *vport = hclge_get_vport(handle);
+ struct hclge_dev *hdev = vport->back;
+
+ return hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG) ||
+ hclge_read_dev(&hdev->hw, HCLGE_FUN_RST_ING);
+}
+
+static bool hclge_ae_dev_resetting(struct hnae3_handle *handle)
+{
+ struct hclge_vport *vport = hclge_get_vport(handle);
+ struct hclge_dev *hdev = vport->back;
+
+ return test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state);
+}
+
+static unsigned long hclge_ae_dev_reset_cnt(struct hnae3_handle *handle)
+{
+ struct hclge_vport *vport = hclge_get_vport(handle);
+ struct hclge_dev *hdev = vport->back;
+
+ return hdev->reset_count;
+}
+
static void hclge_enable_fd(struct hnae3_handle *handle, bool enable)
{
struct hclge_vport *vport = hclge_get_vport(handle);
@@ -7350,6 +7376,9 @@ static const struct hnae3_ae_ops hclge_ops = {
.restore_fd_rules = hclge_restore_fd_entries,
.enable_fd = hclge_enable_fd,
.process_hw_error = hclge_process_ras_hw_error,
+ .get_hw_reset_stat = hclge_get_hw_reset_stat,
+ .ae_dev_resetting = hclge_ae_dev_resetting,
+ .ae_dev_reset_cnt = hclge_ae_dev_reset_cnt,
};
static struct hnae3_ae_algo ae_algo = {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 7cfb61e..b6a17f5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -598,6 +598,7 @@ struct hclge_dev {
unsigned long default_reset_request;
unsigned long reset_request; /* reset has been requested */
unsigned long reset_pending; /* client rst is pending to be served */
+ unsigned long reset_count; /* the number of reset has been done */
u32 fw_version;
u16 num_vmdq_vport; /* Num vmdq vport this PF has set up */
u16 num_tqps; /* Num task queue pairs of this PF */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 42982fc..517204b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1165,6 +1165,7 @@ static int hclgevf_reset(struct hclgevf_dev *hdev)
{
int ret;
+ hdev->reset_count++;
rtnl_lock();
/* bring down the nic to stop any ongoing TX/RX */
@@ -2185,6 +2186,27 @@ static void hclgevf_get_media_type(struct hnae3_handle *handle,
*media_type = hdev->hw.mac.media_type;
}
+static bool hclgevf_get_hw_reset_stat(struct hnae3_handle *handle)
+{
+ struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+
+ return !!hclgevf_read_dev(&hdev->hw, HCLGEVF_FUN_RST_ING);
+}
+
+static bool hclgevf_ae_dev_resetting(struct hnae3_handle *handle)
+{
+ struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+
+ return test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state);
+}
+
+static unsigned long hclgevf_ae_dev_reset_cnt(struct hnae3_handle *handle)
+{
+ struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+
+ return hdev->reset_count;
+}
+
static const struct hnae3_ae_ops hclgevf_ops = {
.init_ae_dev = hclgevf_init_ae_dev,
.uninit_ae_dev = hclgevf_uninit_ae_dev,
@@ -2225,6 +2247,9 @@ static const struct hnae3_ae_ops hclgevf_ops = {
.get_status = hclgevf_get_status,
.get_ksettings_an_result = hclgevf_get_ksettings_an_result,
.get_media_type = hclgevf_get_media_type,
+ .get_hw_reset_stat = hclgevf_get_hw_reset_stat,
+ .ae_dev_resetting = hclgevf_ae_dev_resetting,
+ .ae_dev_reset_cnt = hclgevf_ae_dev_reset_cnt,
};
static struct hnae3_ae_algo ae_algovf = {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index 6b2fd5a..ffb8c77 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -150,6 +150,7 @@ struct hclgevf_dev {
#define HCLGEVF_RESET_REQUESTED 0
#define HCLGEVF_RESET_PENDING 1
unsigned long reset_state; /* requested, pending */
+ unsigned long reset_count; /* the number of reset has been done */
u32 reset_attempts;
u32 fw_version;
--
2.7.4
^ permalink raw reply related
* [Patch net-next 02/12] net: hns3: add set_default_reset_request in the hnae3_ae_ops
From: Huazhong Tan @ 2018-11-07 4:06 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-kernel, salil.mehta, yisen.zhuang, linuxarm
In-Reply-To: <1541563578-28973-1-git-send-email-tanhuazhong@huawei.com>
Currently, when reset_event is called because of tx timeout, it will
upgrade the reset level (For PF, HNAE3_FUNC_RESET -> HNAE3_CORE_RESET
-> HNAE3_GLOBAL_RESET) if the time between the new reset and last reset
is within 20 secs, or restore the reset level to HNAE3_FUNC_RESET if
the time between the new reset and last reset is over 20 secs.
There is requirement that the caller needs to decide the reset level
when triggering a reset, for example, RAS recovery. So this patch
adds the set_default_reset_request to meet this requirement.
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
---
drivers/net/ethernet/hisilicon/hns3/hnae3.h | 2 ++
.../ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 13 ++++++++++
.../ethernet/hisilicon/hns3/hns3pf/hclge_main.h | 1 +
.../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 29 +++++++++++++++++++++-
.../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h | 1 +
5 files changed, 45 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 055b406..7deab92 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -403,6 +403,8 @@ struct hnae3_ae_ops {
u16 vlan, u8 qos, __be16 proto);
int (*enable_hw_strip_rxvtag)(struct hnae3_handle *handle, bool enable);
void (*reset_event)(struct pci_dev *pdev, struct hnae3_handle *handle);
+ void (*set_default_reset_request)(struct hnae3_ae_dev *ae_dev,
+ enum hnae3_reset_type rst_type);
void (*get_channels)(struct hnae3_handle *handle,
struct ethtool_channels *ch);
void (*get_tqps_and_rss_info)(struct hnae3_handle *h,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index ffdd960..5e6006b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2517,6 +2517,10 @@ static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle)
if (time_before(jiffies, (handle->last_reset_time + 3 * HZ)))
return;
+ else if (hdev->default_reset_request)
+ handle->reset_level =
+ hclge_get_reset_level(hdev,
+ &hdev->default_reset_request);
else if (time_after(jiffies, (handle->last_reset_time + 4 * 5 * HZ)))
handle->reset_level = HNAE3_FUNC_RESET;
@@ -2531,6 +2535,14 @@ static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle)
handle->reset_level++;
}
+static void hclge_set_def_reset_request(struct hnae3_ae_dev *ae_dev,
+ enum hnae3_reset_type rst_type)
+{
+ struct hclge_dev *hdev = ae_dev->priv;
+
+ set_bit(rst_type, &hdev->default_reset_request);
+}
+
static void hclge_reset_subtask(struct hclge_dev *hdev)
{
/* check if there is any ongoing reset in the hardware. This status can
@@ -7321,6 +7333,7 @@ static const struct hnae3_ae_ops hclge_ops = {
.set_vf_vlan_filter = hclge_set_vf_vlan_filter,
.enable_hw_strip_rxvtag = hclge_en_hw_strip_rxvtag,
.reset_event = hclge_reset_event,
+ .set_default_reset_request = hclge_set_def_reset_request,
.get_tqps_and_rss_info = hclge_get_tqps_and_rss_info,
.set_channels = hclge_set_channels,
.get_channels = hclge_get_channels,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 0d92154..7cfb61e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -595,6 +595,7 @@ struct hclge_dev {
unsigned long state;
enum hnae3_reset_type reset_type;
+ unsigned long default_reset_request;
unsigned long reset_request; /* reset has been requested */
unsigned long reset_pending; /* client rst is pending to be served */
u32 fw_version;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 085edb9..42982fc 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1219,6 +1219,19 @@ static int hclgevf_do_reset(struct hclgevf_dev *hdev)
return status;
}
+static enum hnae3_reset_type hclgevf_get_reset_level(struct hclgevf_dev *hdev,
+ unsigned long *addr)
+{
+ enum hnae3_reset_type rst_level = HNAE3_NONE_RESET;
+
+ if (test_bit(HNAE3_VF_RESET, addr)) {
+ rst_level = HNAE3_VF_RESET;
+ clear_bit(HNAE3_VF_RESET, addr);
+ }
+
+ return rst_level;
+}
+
static void hclgevf_reset_event(struct pci_dev *pdev,
struct hnae3_handle *handle)
{
@@ -1226,7 +1239,12 @@ static void hclgevf_reset_event(struct pci_dev *pdev,
dev_info(&hdev->pdev->dev, "received reset request from VF enet\n");
- handle->reset_level = HNAE3_VF_RESET;
+ if (!hdev->default_reset_request)
+ handle->reset_level =
+ hclgevf_get_reset_level(hdev,
+ &hdev->default_reset_request);
+ else
+ handle->reset_level = HNAE3_VF_RESET;
/* reset of this VF requested */
set_bit(HCLGEVF_RESET_REQUESTED, &hdev->reset_state);
@@ -1235,6 +1253,14 @@ static void hclgevf_reset_event(struct pci_dev *pdev,
handle->last_reset_time = jiffies;
}
+static void hclgevf_set_def_reset_request(struct hnae3_ae_dev *ae_dev,
+ enum hnae3_reset_type rst_type)
+{
+ struct hclgevf_dev *hdev = ae_dev->priv;
+
+ set_bit(rst_type, &hdev->default_reset_request);
+}
+
static u32 hclgevf_get_fw_version(struct hnae3_handle *handle)
{
struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
@@ -2193,6 +2219,7 @@ static const struct hnae3_ae_ops hclgevf_ops = {
.set_vlan_filter = hclgevf_set_vlan_filter,
.enable_hw_strip_rxvtag = hclgevf_en_hw_strip_rxvtag,
.reset_event = hclgevf_reset_event,
+ .set_default_reset_request = hclgevf_set_def_reset_request,
.get_channels = hclgevf_get_channels,
.get_tqps_and_rss_info = hclgevf_get_tqps_and_rss_info,
.get_status = hclgevf_get_status,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index aed241e..6b2fd5a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -145,6 +145,7 @@ struct hclgevf_dev {
struct hclgevf_misc_vector misc_vector;
struct hclgevf_rss_cfg rss_cfg;
unsigned long state;
+ unsigned long default_reset_request;
#define HCLGEVF_RESET_REQUESTED 0
#define HCLGEVF_RESET_PENDING 1
--
2.7.4
^ permalink raw reply related
* [Patch net-next 01/12] net: hns3: use HNS3_NIC_STATE_INITED to indicate the initialization state of enet
From: Huazhong Tan @ 2018-11-07 4:06 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-kernel, salil.mehta, yisen.zhuang, linuxarm
In-Reply-To: <1541563578-28973-1-git-send-email-tanhuazhong@huawei.com>
Besides of module_init and module_exit, the process of reset will
also uninitialize and initialize the enet client. When reset process
fails with enet client uninitialized, the module_exit does not need
to uninitialize the enet client, otherwise it may cause double
uninitialization problem.
So we need the HNS3_NIC_STATE_INITED flag to indicate whether
the enet client is initialized.
Also HNS3_NIC_STATE_REINITING is previously unused, so change it to
HNS3_NIC_STATE_INITED.
Fixes: bb6b94a896d4 ("net: hns3: Add reset interface implementation in client")
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
---
drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 17 +++++++++++++++++
drivers/net/ethernet/hisilicon/hns3/hns3_enet.h | 2 +-
2 files changed, 18 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 3f96aa3..d51469c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -3397,6 +3397,8 @@ static int hns3_client_init(struct hnae3_handle *handle)
/* MTU range: (ETH_MIN_MTU(kernel default) - 9706) */
netdev->max_mtu = HNS3_MAX_MTU - (ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN);
+ set_bit(HNS3_NIC_STATE_INITED, &priv->state);
+
return ret;
out_reg_netdev_fail:
@@ -3423,6 +3425,11 @@ static void hns3_client_uninit(struct hnae3_handle *handle, bool reset)
if (netdev->reg_state != NETREG_UNINITIALIZED)
unregister_netdev(netdev);
+ if (!test_and_clear_bit(HNS3_NIC_STATE_INITED, &priv->state)) {
+ netdev_warn(netdev, "already uninitialized\n");
+ goto out_netdev_free;
+ }
+
hns3_del_all_fd_rules(netdev, true);
hns3_force_clear_all_rx_ring(handle);
@@ -3443,6 +3450,7 @@ static void hns3_client_uninit(struct hnae3_handle *handle, bool reset)
priv->ring_data = NULL;
+out_netdev_free:
free_netdev(netdev);
}
@@ -3782,6 +3790,8 @@ static int hns3_reset_notify_init_enet(struct hnae3_handle *handle)
priv->ring_data = NULL;
}
+ set_bit(HNS3_NIC_STATE_INITED, &priv->state);
+
return ret;
}
@@ -3792,6 +3802,11 @@ static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle)
struct hns3_nic_priv *priv = netdev_priv(netdev);
int ret;
+ if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state)) {
+ netdev_warn(netdev, "already uninitialized\n");
+ return 0;
+ }
+
hns3_force_clear_all_rx_ring(handle);
ret = hns3_nic_uninit_vector_data(priv);
@@ -3815,6 +3830,8 @@ static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle)
hns3_del_all_fd_rules(netdev, false);
}
+ clear_bit(HNS3_NIC_STATE_INITED, &priv->state);
+
return ret;
}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index d3636d0..7b759e4 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -15,7 +15,7 @@ extern const char hns3_driver_version[];
enum hns3_nic_state {
HNS3_NIC_STATE_TESTING,
HNS3_NIC_STATE_RESETTING,
- HNS3_NIC_STATE_REINITING,
+ HNS3_NIC_STATE_INITED,
HNS3_NIC_STATE_DOWN,
HNS3_NIC_STATE_DISABLED,
HNS3_NIC_STATE_REMOVING,
--
2.7.4
^ permalink raw reply related
* [Patch net-next 00/12] provide new interfaces & bugfixes & code optimization
From: Huazhong Tan @ 2018-11-07 4:06 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-kernel, salil.mehta, yisen.zhuang, linuxarm
This patchset provides some reset interfaces for RAS & RoCE, also
some bugfixes and optimization related to reset.
Huazhong Tan (12):
net: hns3: use HNS3_NIC_STATE_INITED to indicate the initialization
state of enet
net: hns3: add set_default_reset_request in the hnae3_ae_ops
net: hns3: provide some interface & information for the client
net: hns3: adjust the location of clearing the table when doing reset
net: hns3: enable/disable ring in the enet while doing UP/DOWN
net: hns3: use HNS3_NIC_STATE_RESETTING to indicate resetting
net: hns3: ignore new coming low-level reset while doing high-level
reset
net: hns3: move some reset information from hnae3_handle into
hclge_dev/hclgevf_dev
net: hns3: adjust the process of PF reset
net: hns3: call roce's reset notify callback when resetting
net: hns3: add error handler for hclge_reset()
net: hns3: fix for cmd queue memory not freed problem during reset
drivers/net/ethernet/hisilicon/hns3/hnae3.h | 17 +-
drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c | 12 +
drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 91 +++++--
drivers/net/ethernet/hisilicon/hns3/hns3_enet.h | 21 +-
drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c | 19 ++
.../ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 296 +++++++++++++++++----
.../ethernet/hisilicon/hns3/hns3pf/hclge_main.h | 7 +
.../ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c | 141 +++++-----
.../ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h | 1 +
.../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 109 +++++---
.../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h | 8 +-
.../ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c | 2 +-
12 files changed, 544 insertions(+), 180 deletions(-)
--
2.7.4
^ permalink raw reply
* Re: [PATCH net-next v4 9/9] ipv6: do not drop vrf udp multicast packets
From: David Ahern @ 2018-11-06 18:24 UTC (permalink / raw)
To: Mike Manning, netdev; +Cc: Dewi Morgan
In-Reply-To: <20181102191020.14170-10-mmanning@vyatta.att-mail.com>
On 11/2/18 1:10 PM, Mike Manning wrote:
> From: Dewi Morgan <morgand@vyatta.att-mail.com>
>
> For bound udp sockets in a vrf, also check the sdif to get the index
> for ingress devices enslaved to an l3mdev.
>
> Signed-off-by: Dewi Morgan <morgand@vyatta.att-mail.com>
> Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
> ---
> net/ipv6/udp.c | 8 +++++---
> 1 file changed, 5 insertions(+), 3 deletions(-)
>
Reviewed-by: David Ahern <dsahern@gmail.com>
^ permalink raw reply
* Re: [PATCH net-next v4 8/9] ipv6: handling of multicast packets received in VRF
From: David Ahern @ 2018-11-06 18:24 UTC (permalink / raw)
To: Mike Manning, netdev; +Cc: Dewi Morgan
In-Reply-To: <20181102191020.14170-9-mmanning@vyatta.att-mail.com>
On 11/2/18 1:10 PM, Mike Manning wrote:
> If the skb for multicast packets marked as enslaved to a VRF are
> received, then the secondary device index should be used to obtain
> the real device. And verify the multicast address against the
> enslaved rather than the l3mdev device.
>
> Signed-off-by: Dewi Morgan <morgand@vyatta.att-mail.com>
> Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
> ---
> net/ipv6/ip6_input.c | 35 ++++++++++++++++++++++++++++++++---
> 1 file changed, 32 insertions(+), 3 deletions(-)
>
Reviewed-by: David Ahern <dsahern@gmail.com>
^ permalink raw reply
* Re: [PATCH v2 net 0/3] net: bql: better deal with GSO
From: Edward Cree @ 2018-11-06 18:23 UTC (permalink / raw)
To: David Miller; +Cc: edumazet, netdev, eric.dumazet
In-Reply-To: <20181103.154028.1864906755289829872.davem@davemloft.net>
On 03/11/18 22:40, David Miller wrote:
> Series applied, but I wonder how many other commonly used drivers we
> should update the same way mlx4 is here?
Hi David,
I'm doing a patch to update sfc to use this new helper. Is this 'net'
material, or should I wait for 'net-next' to open back up?
-Ed
^ permalink raw reply
* Re: [PATCH net-next v4 7/9] ipv6: allow ping to link-local address in VRF
From: David Ahern @ 2018-11-06 18:14 UTC (permalink / raw)
To: Mike Manning, netdev
In-Reply-To: <20181102191020.14170-8-mmanning@vyatta.att-mail.com>
On 11/2/18 1:10 PM, Mike Manning wrote:
> If link-local packets are marked as enslaved to a VRF, then to allow
> ping to the link-local from a vrf, the error handling for IPV6_PKTINFO
> needs to be relaxed to also allow the pkt ipi6_ifindex to be that of a
> slave device to the vrf.
>
> Note that the real device also needs to be retrieved in icmp6_iif()
> to set the ipv6 flow oif to this for icmp echo reply handling. The
> recent commit 24b711edfc34 ("net/ipv6: Fix linklocal to global address
> with VRF") takes care of this, so the sdif does not need checking here.
>
> This fix makes ping to link-local consistent with that to global
> addresses, in that this can now be done from within the same VRF that
> the address is in.
>
> Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
> ---
> net/ipv6/ipv6_sockglue.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
Reviewed-by: David Ahern <dsahern@gmail.com>
^ permalink raw reply
* Re: [PATCH net-next v4 6/9] vrf: mark skb for multicast or link-local as enslaved to VRF
From: David Ahern @ 2018-11-06 18:13 UTC (permalink / raw)
To: Mike Manning, netdev
In-Reply-To: <20181102191020.14170-7-mmanning@vyatta.att-mail.com>
On 11/2/18 1:10 PM, Mike Manning wrote:
> The skb for packets that are multicast or to a link-local address are
> not marked as being enslaved to a VRF, if they are received on a socket
> bound to the VRF. This is needed for ND and it is preferable for the
> kernel not to have to deal with the additional use-cases if ll or mcast
> packets are handled as enslaved. However, this does not allow service
> instances listening on unbound and bound to VRF sockets to distinguish
> the VRF used, if packets are sent as multicast or to a link-local
> address. The fix is for the VRF driver to also mark these skb as being
> enslaved to the VRF.
>
> Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
> ---
> drivers/net/vrf.c | 19 +++++++++----------
> 1 file changed, 9 insertions(+), 10 deletions(-)
>
Reviewed-by: David Ahern <dsahern@gmail.com>
^ permalink raw reply
* Re: [PATCH net-next v4 5/9] net: fix raw socket lookup device bind matching with VRFs
From: David Ahern @ 2018-11-06 18:08 UTC (permalink / raw)
To: Mike Manning, netdev; +Cc: Duncan Eastoe
In-Reply-To: <20181102191020.14170-6-mmanning@vyatta.att-mail.com>
since you are re-sending, a couple of nits ...
On 11/2/18 1:10 PM, Mike Manning wrote:
> diff --git a/include/net/raw.h b/include/net/raw.h
> index 20ebf0b3dfa8..6ed2ae5b4a80 100644
> --- a/include/net/raw.h
> +++ b/include/net/raw.h
> @@ -18,6 +18,7 @@
> #define _RAW_H
>
>
> +#include <net/inet_sock.h>
Replace one of the extra newlines after '#define _RAW_H' with this new one.
> #include <net/protocol.h>
> #include <linux/icmp.h>
>
> @@ -75,4 +76,15 @@ static inline struct raw_sock *raw_sk(const struct sock *sk)
> return (struct raw_sock *)sk;
> }
>
> +static inline bool raw_sk_bound_dev_eq(struct net *net, int bound_dev_if,
> + int dif, int sdif)
> +{
> +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
> + return inet_bound_dev_eq(net->ipv4.sysctl_raw_l3mdev_accept,
> + bound_dev_if, dif, sdif);
!!net->ipv4.sysctl_raw_l3mdev_accept
^ permalink raw reply
* [PATCH] staging: rtl8723bs: Fix incorrect sense of ether_addr_equal
From: Larry Finger @ 2018-11-07 3:33 UTC (permalink / raw)
To: gregkh; +Cc: netdev, devel, Larry Finger, Stable, youling257,
u.srikant.patnaik
In commit b37f9e1c3801 ("staging: rtl8723bs: Fix lines too long in
update_recvframe_attrib()."), the refactoring involved replacing
two memcmp() calls with ether_addr_equal() calls. What the author
missed is that memcmp() returns false when the two strings are equal,
whereas ether_addr_equal() returns true when the two addresses are
equal. One side effect of this error is that the strength of an
unassociated AP was much stronger than the same AP after association.
This bug is reported at bko#201611.
Fixes: b37f9e1c3801 ("staging: rtl8723bs: Fix lines too long in update_recvframe_attrib().")
Cc: Stable <stable@vger.kernel.org>
Cc: youling257 <youling257@gmail.com>
Cc: u.srikant.patnaik@gmail.com
Reported-and-tested-by: youling257 <youling257@gmail.com>
Signed-off-by: Larry Finger <Larry.Finger@lwfinger.net>
---
drivers/staging/rtl8723bs/hal/rtl8723bs_recv.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/staging/rtl8723bs/hal/rtl8723bs_recv.c b/drivers/staging/rtl8723bs/hal/rtl8723bs_recv.c
index 85077947b9b8..85aba8a503cd 100644
--- a/drivers/staging/rtl8723bs/hal/rtl8723bs_recv.c
+++ b/drivers/staging/rtl8723bs/hal/rtl8723bs_recv.c
@@ -109,12 +109,12 @@ static void update_recvframe_phyinfo(union recv_frame *precvframe,
rx_bssid = get_hdr_bssid(wlanhdr);
pkt_info.bssid_match = ((!IsFrameTypeCtrl(wlanhdr)) &&
!pattrib->icv_err && !pattrib->crc_err &&
- !ether_addr_equal(rx_bssid, my_bssid));
+ ether_addr_equal(rx_bssid, my_bssid));
rx_ra = get_ra(wlanhdr);
my_hwaddr = myid(&padapter->eeprompriv);
pkt_info.to_self = pkt_info.bssid_match &&
- !ether_addr_equal(rx_ra, my_hwaddr);
+ ether_addr_equal(rx_ra, my_hwaddr);
pkt_info.is_beacon = pkt_info.bssid_match &&
--
2.19.1
^ permalink raw reply related
* Re: [PATCH net-next v4 4/9] net: provide a sysctl raw_l3mdev_accept for raw socket lookup with VRFs
From: David Ahern @ 2018-11-06 18:05 UTC (permalink / raw)
To: Mike Manning, netdev
In-Reply-To: <20181102191020.14170-5-mmanning@vyatta.att-mail.com>
On 11/2/18 1:10 PM, Mike Manning wrote:
> diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
> index 8ca3eb06ba04..da453c7dfb75 100644
> --- a/net/ipv4/raw.c
> +++ b/net/ipv4/raw.c
> @@ -805,7 +805,7 @@ static int raw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
> return copied;
> }
>
> -static int raw_init(struct sock *sk)
> +static int raw_sk_init(struct sock *sk)
> {
> struct raw_sock *rp = raw_sk(sk);
>
> @@ -970,7 +970,7 @@ struct proto raw_prot = {
> .connect = ip4_datagram_connect,
> .disconnect = __udp_disconnect,
> .ioctl = raw_ioctl,
> - .init = raw_init,
> + .init = raw_sk_init,
> .setsockopt = raw_setsockopt,
> .getsockopt = raw_getsockopt,
> .sendmsg = raw_sendmsg,
> @@ -1133,4 +1133,16 @@ void __init raw_proc_exit(void)
> {
> unregister_pernet_subsys(&raw_net_ops);
> }
> +
> +static void raw_sysctl_init(void)
> +{
> +#ifdef CONFIG_NET_L3_MASTER_DEV
> + init_net.ipv4.sysctl_raw_l3mdev_accept = 1;
> +#endif
That is not propagated to new network namespaces:
# ip netns add ns1
# ip netns exec ns1 sysctl -a 2>/dev/null | grep l3mdev
net.ipv4.raw_l3mdev_accept = 0
> +}
> +
> +void __init raw_init(void)
> +{
> + raw_sysctl_init();
> +}
> #endif /* CONFIG_PROC_FS */
^ permalink raw reply
* Re: [PATCH net-next v4 3/9] net: ensure unbound datagram socket to be chosen when not in a VRF
From: David Ahern @ 2018-11-06 17:59 UTC (permalink / raw)
To: Mike Manning, netdev
In-Reply-To: <20181102191020.14170-4-mmanning@vyatta.att-mail.com>
On 11/2/18 1:10 PM, Mike Manning wrote:
> diff --git a/include/net/udp.h b/include/net/udp.h
> index 9e82cb391dea..057972d0eea5 100644
> --- a/include/net/udp.h
> +++ b/include/net/udp.h
> @@ -252,6 +252,17 @@ static inline int udp_rqueue_get(struct sock *sk)
> return sk_rmem_alloc_get(sk) - READ_ONCE(udp_sk(sk)->forward_deficit);
> }
>
> +static inline bool udp_sk_bound_dev_eq(struct net *net, int bound_dev_if,
> + int dif, int sdif)
> +{
> +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
> + return inet_bound_dev_eq(net->ipv4.sysctl_udp_l3mdev_accept,
!!net->ipv4.sysctl_udp_l3mdev_accept since first arg is a bool
> + bound_dev_if, dif, sdif);
> +#else
> + return inet_bound_dev_eq(1, bound_dev_if, dif, sdif);
> +#endif
> +}
> +
> /* net/ipv4/udp.c */
> void udp_destruct_sock(struct sock *sk);
> void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len);
...
> diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
> index 1ede7a16a0be..4813293d4fad 100644
> --- a/net/ipv6/datagram.c
> +++ b/net/ipv6/datagram.c
> @@ -782,7 +782,10 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
>
> if (src_info->ipi6_ifindex) {
> if (fl6->flowi6_oif &&
> - src_info->ipi6_ifindex != fl6->flowi6_oif)
> + src_info->ipi6_ifindex != fl6->flowi6_oif &&
> + (sk->sk_bound_dev_if != fl6->flowi6_oif ||
> + !sk_dev_equal_l3scope(
> + sk, src_info->ipi6_ifindex)))
That's getting ugly to read. A tmp variable
int idx = rc_info->ipi6_ifindex;
should shorten that to fit on one line.
> return -EINVAL;
> fl6->flowi6_oif = src_info->ipi6_ifindex;
> }
^ permalink raw reply
* Re: [PATCH net-next v4 2/9] net: ensure unbound stream socket to be chosen when not in a VRF
From: David Ahern @ 2018-11-06 17:55 UTC (permalink / raw)
To: Mike Manning, netdev
In-Reply-To: <20181102191020.14170-3-mmanning@vyatta.att-mail.com>
Since you need to re-send once net-next opens ...
On 11/2/18 1:10 PM, Mike Manning wrote:
> diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
> index 4ae060b4bac2..5de2d9f24c05 100644
> --- a/include/net/inet_hashtables.h
> +++ b/include/net/inet_hashtables.h
> @@ -189,6 +189,17 @@ static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo)
> hashinfo->ehash_locks = NULL;
> }
>
> +static inline bool inet_sk_bound_dev_eq(struct net *net, int bound_dev_if,
> + int dif, int sdif)
> +{
> +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
> + return inet_bound_dev_eq(net->ipv4.sysctl_tcp_l3mdev_accept,
> + bound_dev_if, dif, sdif);
Column misalignment on the bound_dev_if. Also, since the arg to
inet_bound_dev_eq is a bool, that should be
!!net->ipv4.sysctl_tcp_l3mdev_accept
> +#else
> + return inet_bound_dev_eq(1, bound_dev_if, dif, sdif);
> +#endif
> +}
> +
> struct inet_bind_bucket *
> inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net,
> struct inet_bind_hashbucket *head,
^ permalink raw reply
* Re: [PATCH net-next v4 1/9] net: allow binding socket in a VRF when there's an unbound socket
From: David Ahern @ 2018-11-06 17:52 UTC (permalink / raw)
To: Mike Manning, netdev; +Cc: Robert Shearman
In-Reply-To: <20181102191020.14170-2-mmanning@vyatta.att-mail.com>
On 11/2/18 1:10 PM, Mike Manning wrote:
> From: Robert Shearman <rshearma@vyatta.att-mail.com>
>
> Change the inet socket lookup to avoid packets arriving on a device
> enslaved to an l3mdev from matching unbound sockets by removing the
> wildcard for non sk_bound_dev_if and instead relying on check against
> the secondary device index, which will be 0 when the input device is
> not enslaved to an l3mdev and so match against an unbound socket and
> not match when the input device is enslaved.
>
> Change the socket binding to take the l3mdev into account to allow an
> unbound socket to not conflict sockets bound to an l3mdev given the
> datapath isolation now guaranteed.
>
> Signed-off-by: Robert Shearman <rshearma@vyatta.att-mail.com>
> Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
> ---
> Documentation/networking/vrf.txt | 9 +++++----
> include/net/inet6_hashtables.h | 5 ++---
> include/net/inet_hashtables.h | 13 ++++++-------
> include/net/inet_sock.h | 13 +++++++++++++
> net/ipv4/inet_connection_sock.c | 13 ++++++++++---
> net/ipv4/inet_hashtables.c | 20 +++++++++++++++-----
> 6 files changed, 51 insertions(+), 22 deletions(-)
>
Reviewed-by: David Ahern <dsahern@gmail.com>
^ permalink raw reply
* [PATCH net-next] net: hns3: Remove set but not used variable 'reset_level'
From: YueHaibing @ 2018-11-07 2:33 UTC (permalink / raw)
To: Yisen Zhuang, Salil Mehta, Shiju Jose, davem, Colin Ian King
Cc: YueHaibing, netdev, linux-kernel, kernel-janitors
Fixes gcc '-Wunused-but-set-variable' warning:
drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c: In function 'hclge_log_and_clear_ppp_error':
drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c:821:24: warning:
variable 'reset_level' set but not used [-Wunused-but-set-variable]
enum hnae3_reset_type reset_level = HNAE3_NONE_RESET;
It never used since introduction in commit
01865a50d78f ("net: hns3: Add enable and process hw errors of TM scheduler")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
---
drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c | 13 +++----------
1 file changed, 3 insertions(+), 10 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
index 123c37e..6da9e22 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
@@ -818,7 +818,6 @@ static void hclge_process_igu_egu_error(struct hclge_dev *hdev,
static int hclge_log_and_clear_ppp_error(struct hclge_dev *hdev, u32 cmd,
enum hclge_err_int_type int_type)
{
- enum hnae3_reset_type reset_level = HNAE3_NONE_RESET;
struct device *dev = &hdev->pdev->dev;
const struct hclge_hw_error *hw_err_lst1, *hw_err_lst2, *hw_err_lst3;
struct hclge_desc desc[2];
@@ -848,23 +847,17 @@ static int hclge_log_and_clear_ppp_error(struct hclge_dev *hdev, u32 cmd,
}
err_sts = le32_to_cpu(desc[0].data[2]);
- if (err_sts) {
+ if (err_sts)
hclge_log_error(dev, hw_err_lst1, err_sts);
- reset_level = HNAE3_FUNC_RESET;
- }
err_sts = le32_to_cpu(desc[0].data[3]);
- if (err_sts) {
+ if (err_sts)
hclge_log_error(dev, hw_err_lst2, err_sts);
- reset_level = HNAE3_FUNC_RESET;
- }
if (cmd == HCLGE_PPP_CMD0_INT_CMD) {
err_sts = (le32_to_cpu(desc[0].data[4]) >> 8) & 0x3;
- if (err_sts) {
+ if (err_sts)
hclge_log_error(dev, hw_err_lst3, err_sts);
- reset_level = HNAE3_FUNC_RESET;
- }
}
/* clear PPP INT */
^ permalink raw reply related
* Re: [PATCH] iwlegacy: fix small typo
From: Kalle Valo @ 2018-11-06 17:04 UTC (permalink / raw)
To: Yangtao Li
Cc: sgruszka, davem, linux-wireless, netdev, linux-kernel, Yangtao Li
In-Reply-To: <20181101154023.22990-1-tiny.windzz@gmail.com>
Yangtao Li <tiny.windzz@gmail.com> wrote:
> Signed-off-by: Yangtao Li <tiny.windzz@gmail.com>
Patch applied to wireless-drivers-next.git, thanks.
ac9ccb8b991c iwlegacy: fix small typo
--
https://patchwork.kernel.org/patch/10664187/
https://wireless.wiki.kernel.org/en/developers/documentation/submittingpatches
^ permalink raw reply
* Re: WARNING in kmem_cache_create_usercopy
From: Dmitry Vyukov @ 2018-11-07 2:29 UTC (permalink / raw)
To: Dominique Martinet
Cc: syzbot, David Miller, Eric Van Hensbergen, LKML, Latchesar Ionkov,
netdev, syzkaller-bugs, v9fs-developer
In-Reply-To: <20181102223908.GA9565@nautica>
On Fri, Nov 2, 2018 at 3:39 PM, Dominique Martinet
<asmadeus@codewreck.org> wrote:
> syzbot wrote on Fri, Nov 02, 2018:
>> RIP: 0010:kmem_cache_create_usercopy+0xad/0x240 mm/slab_common.c:473
>> Code: 44 89 f0 25 00 60 de 04 45 85 ed 89 45 cc 75 0b 8b 45 d0 85 c0
>> 0f 85 8e 01 00 00 44 39 eb 72 0a 89 d8 44 29 e8 3b 45 d0 73 7e <0f>
>> 0b c7 45 d0 00 00 00 00 4c 8b 45 10 44 89 fa 89 de 4c 89 e7 8b
>> RSP: 0018:ffff8801bc23f5d0 EFLAGS: 00010213
>> RAX: 0000000000000000 RBX: 0000000000000008 RCX: 0000000000000006
>> RDX: 0000000000000000 RSI: 0000000000000020 RDI: ffffffff88b04b20
>> RBP: ffff8801bc23f608 R08: fffffbfff1283a2d R09: fffffbfff1283a2c
>> R10: ffff8801bc23f5c0 R11: ffffffff8941d167 R12: ffffffff88b04b20
>> R13: 00000000fffffffd R14: 0000000000000000 R15: 0000000000000000
>> p9_client_create+0xa58/0x1769 net/9p/client.c:1054
>
> No lower bound on msize, the reproducer gives a reply from the
> pseudo-server with msize=8 and we happily take it, underflowing the
> msize - 11 (hdr+4) argument to kmem_cache_create_usercopy...
> This probably never worked anyway, but we now get a warning :)
>
>
> We need to add a sane lower bound to msize as well as the current upper
> bound set in the transport.
> We have some header sizes in 9p.h for IO header overhead (P9_IOHDRSZ to
> 24 for example) but I think that's too low in practice; stuff like
> readdir will require more than this to get a single entry... We can
> request the server to ask for at least 4k?
> 9p would probably work with less (e.g. 1k; I'd rather not have to
> figgure the minimum length we need to get each messages to work in its
> minimal form) but honestly even with 4k the perforamnces will be
> terrible, so tempted to go with that...
>
> I'll send a patch imposing 4k next week unless someone else does first,
> or replies indicate different preferences.
>
>
> @Dmitry: semi-related, the C reproducer (
> https://syzkaller.appspot.com/x/repro.c?x=1701f831400000 ) has a lot of
> "readable" letters spelled out as "\x63..." or chars as 0x3d - it's fine
> for generated code and that might be easier for the intermediate
> representation syzkaller works with, but do you know something handy
> that would help convert these to readable strings?
> e.g. "\x63\x61\x63\x68\x65\x3d\xc0\x6d\x61\x70" could be written
> "cache=\xc0map", and 0x3d as '=' (hm I guess the later would not always
> make sense to convert so probably best left as is, but it gets annoying
> pretty fast with longer strings)
Hi Dominique,
I've filed https://github.com/google/syzkaller/issues/792 for this.
Thanks for the feedback.
^ permalink raw reply
* WARNING: ODEBUG bug in tls_sw_free_resources_tx
From: syzbot @ 2018-11-07 1:52 UTC (permalink / raw)
To: aviadye, borisp, daniel, davejwatson, davem, john.fastabend,
linux-kernel, netdev, syzkaller-bugs
Hello,
syzbot found the following crash on:
HEAD commit: 7c6c54b505b8 Merge branch 'i2c/for-next' of git://git.kern..
git tree: net-next
console output: https://syzkaller.appspot.com/x/log.txt?x=1276246d400000
kernel config: https://syzkaller.appspot.com/x/.config?x=136ed5b316dbf1d8
dashboard link: https://syzkaller.appspot.com/bug?extid=70ab6a1f8151888c4ea0
compiler: gcc (GCC) 8.0.1 20180413 (experimental)
Unfortunately, I don't have any reproducer for this crash yet.
IMPORTANT: if you fix the bug, please add the following tag to the commit:
Reported-by: syzbot+70ab6a1f8151888c4ea0@syzkaller.appspotmail.com
------------[ cut here ]------------
ODEBUG: free active (active state 0) object type: timer_list hint:
delayed_work_timer_fn+0x0/0x90 include/linux/compiler.h:179
WARNING: CPU: 1 PID: 17315 at lib/debugobjects.c:329
debug_print_object+0x16a/0x210 lib/debugobjects.c:326
Kernel panic - not syncing: panic_on_warn set ...
CPU: 1 PID: 17315 Comm: syz-executor5 Not tainted 4.19.0+ #281
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
Call Trace:
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0x244/0x39d lib/dump_stack.c:113
panic+0x2ad/0x55c kernel/panic.c:188
__warn.cold.8+0x20/0x45 kernel/panic.c:540
report_bug+0x254/0x2d0 lib/bug.c:186
fixup_bug arch/x86/kernel/traps.c:178 [inline]
do_error_trap+0x11b/0x200 arch/x86/kernel/traps.c:271
do_invalid_op+0x36/0x40 arch/x86/kernel/traps.c:290
invalid_op+0x14/0x20 arch/x86/entry/entry_64.S:966
RIP: 0010:debug_print_object+0x16a/0x210 lib/debugobjects.c:326
Code: 60 88 48 89 fa 48 c1 ea 03 80 3c 02 00 0f 85 92 00 00 00 48 8b 14 dd
c0 c2 60 88 4c 89 fe 48 c7 c7 60 b8 60 88 e8 76 ea b5 fd <0f> 0b 83 05 11
01 82 06 01 48 83 c4 18 5b 41 5c 41 5d 41 5e 41 5f
RSP: 0018:ffff880192ea76e0 EFLAGS: 00010086
RAX: 0000000000000000 RBX: 0000000000000003 RCX: 0000000000000000
RDX: 0000000000000000 RSI: ffffffff8165d6c5 RDI: 0000000000000005
RBP: ffff880192ea7720 R08: ffff880190074640 R09: ffffed003b5e3ef8
R10: ffffed003b5e3ef8 R11: ffff8801daf1f7c7 R12: 0000000000000001
R13: ffffffff895a51c0 R14: ffffffff816c19a0 R15: ffffffff8860bd00
__debug_check_no_obj_freed lib/debugobjects.c:786 [inline]
debug_check_no_obj_freed+0x3ae/0x58d lib/debugobjects.c:818
kfree+0xbd/0x230 mm/slab.c:3816
tls_sw_free_resources_tx+0x826/0xcf0 net/tls/tls_sw.c:1808
tls_sk_proto_close+0x602/0x750 net/tls/tls_main.c:278
inet_release+0x104/0x1f0 net/ipv4/af_inet.c:428
inet6_release+0x50/0x70 net/ipv6/af_inet6.c:458
__sock_release+0xd7/0x250 net/socket.c:579
sock_close+0x19/0x20 net/socket.c:1141
__fput+0x385/0xa30 fs/file_table.c:278
____fput+0x15/0x20 fs/file_table.c:309
task_work_run+0x1e8/0x2a0 kernel/task_work.c:113
tracehook_notify_resume include/linux/tracehook.h:188 [inline]
exit_to_usermode_loop+0x318/0x380 arch/x86/entry/common.c:166
prepare_exit_to_usermode arch/x86/entry/common.c:197 [inline]
syscall_return_slowpath arch/x86/entry/common.c:268 [inline]
do_syscall_64+0x6be/0x820 arch/x86/entry/common.c:293
entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x411021
Code: 75 14 b8 03 00 00 00 0f 05 48 3d 01 f0 ff ff 0f 83 34 19 00 00 c3 48
83 ec 08 e8 0a fc ff ff 48 89 04 24 b8 03 00 00 00 0f 05 <48> 8b 3c 24 48
89 c2 e8 53 fc ff ff 48 89 d0 48 83 c4 08 48 3d 01
RSP: 002b:00007ffeccfec1d0 EFLAGS: 00000293 ORIG_RAX: 0000000000000003
RAX: 0000000000000000 RBX: 0000000000000005 RCX: 0000000000411021
RDX: 0000000000000000 RSI: 0000000000730870 RDI: 0000000000000004
RBP: 0000000000000000 R08: 00000000e2abfaa8 R09: 00000000e2abfaac
R10: 00007ffeccfec100 R11: 0000000000000293 R12: 0000000000000000
R13: 0000000000000001 R14: 0000000000000512 R15: 0000000000000005
======================================================
WARNING: possible circular locking dependency detected
4.19.0+ #281 Not tainted
------------------------------------------------------
syz-executor5/17315 is trying to acquire lock:
00000000b56e5405 ((console_sem).lock){-.-.}, at: down_trylock+0x13/0x70
kernel/locking/semaphore.c:136
but task is already holding lock:
000000008f462fd4 (&obj_hash[i].lock){-.-.}, at: __debug_check_no_obj_freed
lib/debugobjects.c:777 [inline]
000000008f462fd4 (&obj_hash[i].lock){-.-.}, at:
debug_check_no_obj_freed+0x17a/0x58d lib/debugobjects.c:818
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #3 (&obj_hash[i].lock){-.-.}:
__raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline]
_raw_spin_lock_irqsave+0x99/0xd0 kernel/locking/spinlock.c:152
__debug_object_init+0x127/0x1290 lib/debugobjects.c:384
debug_object_init+0x16/0x20 lib/debugobjects.c:432
debug_hrtimer_init kernel/time/hrtimer.c:410 [inline]
debug_init kernel/time/hrtimer.c:458 [inline]
hrtimer_init+0x97/0x490 kernel/time/hrtimer.c:1308
init_dl_task_timer+0x1b/0x50 kernel/sched/deadline.c:1057
__sched_fork+0x2ae/0x590 kernel/sched/core.c:2166
init_idle+0x75/0x740 kernel/sched/core.c:5374
sched_init+0xb33/0xc07 kernel/sched/core.c:6057
start_kernel+0x4be/0xa2b init/main.c:608
x86_64_start_reservations+0x2e/0x30 arch/x86/kernel/head64.c:472
x86_64_start_kernel+0x76/0x79 arch/x86/kernel/head64.c:451
secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:243
-> #2 (&rq->lock){-.-.}:
__raw_spin_lock include/linux/spinlock_api_smp.h:142 [inline]
_raw_spin_lock+0x2d/0x40 kernel/locking/spinlock.c:144
rq_lock kernel/sched/sched.h:1126 [inline]
task_fork_fair+0xb0/0x6d0 kernel/sched/fair.c:9768
sched_fork+0x443/0xba0 kernel/sched/core.c:2359
copy_process+0x25b8/0x87a0 kernel/fork.c:1886
_do_fork+0x1cb/0x11d0 kernel/fork.c:2213
kernel_thread+0x34/0x40 kernel/fork.c:2272
rest_init+0x28/0x372 init/main.c:409
arch_call_rest_init+0xe/0x1b
start_kernel+0x9f0/0xa2b init/main.c:745
x86_64_start_reservations+0x2e/0x30 arch/x86/kernel/head64.c:472
x86_64_start_kernel+0x76/0x79 arch/x86/kernel/head64.c:451
secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:243
-> #1 (&p->pi_lock){-.-.}:
__raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline]
_raw_spin_lock_irqsave+0x99/0xd0 kernel/locking/spinlock.c:152
try_to_wake_up+0xdc/0x1490 kernel/sched/core.c:1965
wake_up_process+0x10/0x20 kernel/sched/core.c:2129
__up.isra.1+0x1c0/0x2a0 kernel/locking/semaphore.c:262
up+0x13c/0x1c0 kernel/locking/semaphore.c:187
__up_console_sem+0xbe/0x1b0 kernel/printk/printk.c:236
console_unlock+0x811/0x1190 kernel/printk/printk.c:2432
vprintk_emit+0x391/0x990 kernel/printk/printk.c:1922
vprintk_default+0x28/0x30 kernel/printk/printk.c:1964
vprintk_func+0x7e/0x181 kernel/printk/printk_safe.c:398
printk+0xa7/0xcf kernel/printk/printk.c:1997
check_stack_usage kernel/exit.c:755 [inline]
do_exit.cold.18+0x57/0x16f kernel/exit.c:916
do_group_exit+0x177/0x440 kernel/exit.c:970
__do_sys_exit_group kernel/exit.c:981 [inline]
__se_sys_exit_group kernel/exit.c:979 [inline]
__x64_sys_exit_group+0x3e/0x50 kernel/exit.c:979
do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290
entry_SYSCALL_64_after_hwframe+0x49/0xbe
-> #0 ((console_sem).lock){-.-.}:
lock_acquire+0x1ed/0x520 kernel/locking/lockdep.c:3844
__raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline]
_raw_spin_lock_irqsave+0x99/0xd0 kernel/locking/spinlock.c:152
down_trylock+0x13/0x70 kernel/locking/semaphore.c:136
__down_trylock_console_sem+0xae/0x1f0 kernel/printk/printk.c:219
console_trylock+0x15/0xa0 kernel/printk/printk.c:2247
console_trylock_spinning kernel/printk/printk.c:1653 [inline]
vprintk_emit+0x372/0x990 kernel/printk/printk.c:1921
vprintk_default+0x28/0x30 kernel/printk/printk.c:1964
vprintk_func+0x7e/0x181 kernel/printk/printk_safe.c:398
printk+0xa7/0xcf kernel/printk/printk.c:1997
__warn_printk+0x8c/0xe0 kernel/panic.c:594
debug_print_object+0x16a/0x210 lib/debugobjects.c:326
__debug_check_no_obj_freed lib/debugobjects.c:786 [inline]
debug_check_no_obj_freed+0x3ae/0x58d lib/debugobjects.c:818
kfree+0xbd/0x230 mm/slab.c:3816
tls_sw_free_resources_tx+0x826/0xcf0 net/tls/tls_sw.c:1808
tls_sk_proto_close+0x602/0x750 net/tls/tls_main.c:278
inet_release+0x104/0x1f0 net/ipv4/af_inet.c:428
inet6_release+0x50/0x70 net/ipv6/af_inet6.c:458
__sock_release+0xd7/0x250 net/socket.c:579
sock_close+0x19/0x20 net/socket.c:1141
__fput+0x385/0xa30 fs/file_table.c:278
____fput+0x15/0x20 fs/file_table.c:309
task_work_run+0x1e8/0x2a0 kernel/task_work.c:113
tracehook_notify_resume include/linux/tracehook.h:188 [inline]
exit_to_usermode_loop+0x318/0x380 arch/x86/entry/common.c:166
prepare_exit_to_usermode arch/x86/entry/common.c:197 [inline]
syscall_return_slowpath arch/x86/entry/common.c:268 [inline]
do_syscall_64+0x6be/0x820 arch/x86/entry/common.c:293
entry_SYSCALL_64_after_hwframe+0x49/0xbe
other info that might help us debug this:
Chain exists of:
(console_sem).lock --> &rq->lock --> &obj_hash[i].lock
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(&obj_hash[i].lock);
lock(&rq->lock);
lock(&obj_hash[i].lock);
lock((console_sem).lock);
*** DEADLOCK ***
3 locks held by syz-executor5/17315:
#0: 0000000097b82416 (&sb->s_type->i_mutex_key#11){+.+.}, at: inode_lock
include/linux/fs.h:757 [inline]
#0: 0000000097b82416 (&sb->s_type->i_mutex_key#11){+.+.}, at:
__sock_release+0x8b/0x250 net/socket.c:578
#1: 00000000ea6832e0 (sk_lock-AF_INET6){+.+.}, at: lock_sock
include/net/sock.h:1492 [inline]
#1: 00000000ea6832e0 (sk_lock-AF_INET6){+.+.}, at:
tls_sk_proto_close+0xf5/0x750 net/tls/tls_main.c:262
#2: 000000008f462fd4 (&obj_hash[i].lock){-.-.}, at:
__debug_check_no_obj_freed lib/debugobjects.c:777 [inline]
#2: 000000008f462fd4 (&obj_hash[i].lock){-.-.}, at:
debug_check_no_obj_freed+0x17a/0x58d lib/debugobjects.c:818
stack backtrace:
CPU: 1 PID: 17315 Comm: syz-executor5 Not tainted 4.19.0+ #281
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
Call Trace:
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0x244/0x39d lib/dump_stack.c:113
print_circular_bug.isra.35.cold.54+0x1bd/0x27d
kernel/locking/lockdep.c:1221
check_prev_add kernel/locking/lockdep.c:1863 [inline]
check_prevs_add kernel/locking/lockdep.c:1976 [inline]
validate_chain kernel/locking/lockdep.c:2347 [inline]
__lock_acquire+0x3399/0x4c20 kernel/locking/lockdep.c:3341
lock_acquire+0x1ed/0x520 kernel/locking/lockdep.c:3844
__raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline]
_raw_spin_lock_irqsave+0x99/0xd0 kernel/locking/spinlock.c:152
down_trylock+0x13/0x70 kernel/locking/semaphore.c:136
__down_trylock_console_sem+0xae/0x1f0 kernel/printk/printk.c:219
console_trylock+0x15/0xa0 kernel/printk/printk.c:2247
console_trylock_spinning kernel/printk/printk.c:1653 [inline]
vprintk_emit+0x372/0x990 kernel/printk/printk.c:1921
vprintk_default+0x28/0x30 kernel/printk/printk.c:1964
vprintk_func+0x7e/0x181 kernel/printk/printk_safe.c:398
printk+0xa7/0xcf kernel/printk/printk.c:1997
__warn_printk+0x8c/0xe0 kernel/panic.c:594
debug_print_object+0x16a/0x210 lib/debugobjects.c:326
__debug_check_no_obj_freed lib/debugobjects.c:786 [inline]
debug_check_no_obj_freed+0x3ae/0x58d lib/debugobjects.c:818
kfree+0xbd/0x230 mm/slab.c:3816
tls_sw_free_resources_tx+0x826/0xcf0 net/tls/tls_sw.c:1808
tls_sk_proto_close+0x602/0x750 net/tls/tls_main.c:278
inet_release+0x104/0x1f0 net/ipv4/af_inet.c:428
inet6_release+0x50/0x70 net/ipv6/af_inet6.c:458
__sock_release+0xd7/0x250 net/socket.c:579
sock_close+0x19/0x20 net/socket.c:1141
__fput+0x385/0xa30 fs/file_table.c:278
____fput+0x15/0x20 fs/file_table.c:309
task_work_run+0x1e8/0x2a0 kernel/task_work.c:113
tracehook_notify_resume include/linux/tracehook.h:188 [inline]
exit_to_usermode_loop+0x318/0x380 arch/x86/entry/common.c:166
prepare_exit_to_usermode arch/x86/entry/common.c:197 [inline]
syscall_return_slowpath arch/x86/entry/common.c:268 [inline]
do_syscall_64+0x6be/0x820 arch/x86/entry/common.c:293
entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x411021
Code: 75 14 b8 03 00 00 00 0f 05 48 3d 01 f0 ff ff 0f 83 34 19 00 00 c3 48
83 ec 08 e8 0a fc ff ff 48 89 04 24 b8 03 00 00 00 0f 05 <48> 8b 3c 24 48
89 c2 e8 53 fc ff ff 48 89 d0 48 83 c4 08 48 3d 01
RSP: 002b:00007ffeccfec1d0 EFLAGS: 00000293 ORIG_RAX: 0000000000000003
RAX: 0000000000000000 RBX: 0000000000000005 RCX: 0000000000411021
RDX: 0000000000000000 RSI: 0000000000730870 RDI: 0000000000000004
RBP: 0000000000000000 R08: 00000000e2abfaa8 R09: 00000000e2abfaac
R10: 00007ffeccfec100 R11: 0000000000000293 R12: 0000000000000000
R13: 0000000000000001 R14: 0000000000000512 R15: 0000000000000005
Shutting down cpus with NMI
Kernel Offset: disabled
Rebooting in 86400 seconds..
---
This bug is generated by a bot. It may contain errors.
See https://goo.gl/tpsmEJ for more information about syzbot.
syzbot engineers can be reached at syzkaller@googlegroups.com.
syzbot will keep track of this bug report. See:
https://goo.gl/tpsmEJ#bug-status-tracking for how to communicate with
syzbot.
^ permalink raw reply
* Re: [RFC perf,bpf 5/5] perf util: generate bpf_prog_info_event for short living bpf programs
From: Alexei Starovoitov @ 2018-11-07 1:09 UTC (permalink / raw)
To: David Ahern, David Miller
Cc: Song Liu, netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
Kernel Team, ast@kernel.org, daniel@iogearbox.net,
peterz@infradead.org, acme@kernel.org
In-Reply-To: <7d0b100b-a64b-0d30-8ec0-2689ef44423d@gmail.com>
On 11/6/18 4:44 PM, David Ahern wrote:
>
> So one use case is profiling bpf programs. I was also considering the
> auditing discussion from some weeks ago which I thought the events are
> also targeting.
yes. there should be separate mode for 're: audit discussion' where
only bpf events are collected. This patch set doesn't add that to
perf user space side.
The kernel side is common though. It can be used for bpf load/unload
only and for different use case in this set. Which is making
bpf program appear in normal 'perf report'.
Please see link in cover letter.
We decided to abandon my old approach in favor of this one,
but the end result is the same.
From 0.81% cpu of some magic 0x00007fffa001a660
into 18.13% of bpf_prog_1accc788e7f04c38_balancer_ingres
> As for the overhead, I did not see a separate thread getting spun off
> for the bpf events, so the events are processed inline for this RFC set.
argh. you're right. we have to fix that.
^ permalink raw reply
* [PATCH] net: dsa: bcm_sf2: fix semicolon.cocci warnings
From: kbuild test robot @ 2018-11-07 0:50 UTC (permalink / raw)
To: Florian Fainelli
Cc: kbuild-all, netdev, Andrew Lunn, Vivien Didelot, linux-kernel
In-Reply-To: <201811070831.tDyF0pxQ%fengguang.wu@intel.com>
From: kbuild test robot <fengguang.wu@intel.com>
drivers/net/dsa/bcm_sf2_cfp.c:1168:2-3: Unneeded semicolon
drivers/net/dsa/bcm_sf2_cfp.c:532:2-3: Unneeded semicolon
Remove unneeded semicolon.
Generated by: scripts/coccinelle/misc/semicolon.cocci
Fixes: ae7a5aff783c ("net: dsa: bcm_sf2: Keep copy of inserted rules")
CC: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: kbuild test robot <fengguang.wu@intel.com>
---
tree: https://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git master
head: 5882d526d887e42ead4014d79620e5a8aa741151
commit: ae7a5aff783c79d5ca87867df84b08c43447159b [8/13] net: dsa: bcm_sf2: Keep copy of inserted rules
bcm_sf2_cfp.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -529,7 +529,7 @@ static struct cfp_rule *bcm_sf2_cfp_rule
list_for_each_entry(rule, &priv->cfp.rules_list, next) {
if (rule->port == port && rule->fs.location == location)
break;
- };
+ }
return rule;
}
@@ -1165,7 +1165,7 @@ int bcm_sf2_cfp_resume(struct dsa_switch
dev_err(ds->dev, "failed to restore rule\n");
return ret;
}
- };
+ }
return ret;
}
^ permalink raw reply
* Re: [RFC perf,bpf 5/5] perf util: generate bpf_prog_info_event for short living bpf programs
From: David Ahern @ 2018-11-07 0:44 UTC (permalink / raw)
To: Alexei Starovoitov, David Miller
Cc: Song Liu, netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
Kernel Team, ast@kernel.org, daniel@iogearbox.net,
peterz@infradead.org, acme@kernel.org
In-Reply-To: <82745121-339e-2751-c9db-d1fca02d0b33@fb.com>
On 11/6/18 5:26 PM, Alexei Starovoitov wrote:
> On 11/6/18 4:23 PM, David Ahern wrote:
>> On 11/6/18 5:13 PM, Alexei Starovoitov wrote:
>>> On 11/6/18 3:36 PM, David Miller wrote:
>>>> From: Alexei Starovoitov <ast@fb.com>
>>>> Date: Tue, 6 Nov 2018 23:29:07 +0000
>>>>
>>>>> I think concerns with perf overhead from collecting bpf events
>>>>> are unfounded.
>>>>> I would prefer for this flag to be on by default.
>>>>
>>>> I will sit in userspace looping over bpf load/unload and see how the
>>>> person trying to monitor something else with perf feels about that.
>>>>
>>>> Really, it is inappropriate to turn this on by default, I completely
>>>> agree with David Ahern.
>>>>
>>>> It's hard enough, _AS IS_, for me to fight back all of the bloat that
>>>> is in perf right now and get it back to being able to handle simple
>>>> full workloads without dropping events..
>>>
>>> It's a separate perf thread and separate event with its own epoll.
>>> I don't see how it can affect main event collection.
>>> Let's put it this way. If it does affect somehow, then yes,
>>> it should not be on. If it is not, there is no downside to keep it on.
>>> Typical user expects to type 'perf record' and see everything that
>>> is happening on the system. Right now short lived bpf programs
>>> will not be seen. How user suppose to even know when to use the flag?
>>
>> The default is profiling where perf record collects task events and
>> periodic samples. So for the default record/report, the bpf load /
>> unload events are not relevant.
>
> Exactly the opposite.
> It's for default 'perf record' collection of periodic samples.
> It can be off for -e collection. That's easy.
>
So one use case is profiling bpf programs. I was also considering the
auditing discussion from some weeks ago which I thought the events are
also targeting.
As for the overhead, I did not see a separate thread getting spun off
for the bpf events, so the events are processed inline for this RFC set.
^ permalink raw reply
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