* [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 07/12] net: hns3: ignore new coming low-level reset while doing high-level 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 processing a higher level reset, the pending lower level reset
does not have to be processed anymore, because the higher level
reset is the superset of the lower level reset.
Therefore, when processing an higher level reset, the request of
lower level reset needs to be cleared.
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
---
.../ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 27 +++++++++++++---------
1 file changed, 16 insertions(+), 11 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index b784db0..62022d55 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2414,20 +2414,25 @@ static enum hnae3_reset_type hclge_get_reset_level(struct hclge_dev *hdev,
enum hnae3_reset_type rst_level = HNAE3_NONE_RESET;
/* return the highest priority reset level amongst all */
- if (test_bit(HNAE3_GLOBAL_RESET, addr))
+ if (test_bit(HNAE3_IMP_RESET, addr)) {
+ rst_level = HNAE3_IMP_RESET;
+ clear_bit(HNAE3_IMP_RESET, addr);
+ clear_bit(HNAE3_GLOBAL_RESET, addr);
+ clear_bit(HNAE3_CORE_RESET, addr);
+ clear_bit(HNAE3_FUNC_RESET, addr);
+ } else if (test_bit(HNAE3_GLOBAL_RESET, addr)) {
rst_level = HNAE3_GLOBAL_RESET;
- else if (test_bit(HNAE3_CORE_RESET, addr))
+ clear_bit(HNAE3_GLOBAL_RESET, addr);
+ clear_bit(HNAE3_CORE_RESET, addr);
+ clear_bit(HNAE3_FUNC_RESET, addr);
+ } else if (test_bit(HNAE3_CORE_RESET, addr)) {
rst_level = HNAE3_CORE_RESET;
- else if (test_bit(HNAE3_IMP_RESET, addr))
- rst_level = HNAE3_IMP_RESET;
- else if (test_bit(HNAE3_FUNC_RESET, addr))
+ clear_bit(HNAE3_CORE_RESET, addr);
+ clear_bit(HNAE3_FUNC_RESET, addr);
+ } else if (test_bit(HNAE3_FUNC_RESET, addr)) {
rst_level = HNAE3_FUNC_RESET;
-
- /* now, clear all other resets */
- clear_bit(HNAE3_GLOBAL_RESET, addr);
- clear_bit(HNAE3_CORE_RESET, addr);
- clear_bit(HNAE3_IMP_RESET, addr);
- clear_bit(HNAE3_FUNC_RESET, addr);
+ clear_bit(HNAE3_FUNC_RESET, addr);
+ }
return rst_level;
}
--
2.7.4
^ permalink raw reply related
* [Patch net-next 08/12] net: hns3: move some reset information from hnae3_handle into hclge_dev/hclgevf_dev
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>
Saving reset related information in the hclge_dev/hclgevf_dev
structure is more suitable than the hnae3_handle, since hardware
related information is kept in these two structure.
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
---
drivers/net/ethernet/hisilicon/hns3/hnae3.h | 3 ---
drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 16 +++------------
.../ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 23 +++++++++++-----------
.../ethernet/hisilicon/hns3/hns3pf/hclge_main.h | 2 ++
.../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 10 ++++++----
.../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h | 6 ++++--
.../ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c | 2 +-
7 files changed, 28 insertions(+), 34 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index f57034d..5b3b104 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -534,9 +534,6 @@ struct hnae3_handle {
struct hnae3_ae_algo *ae_algo; /* the class who provides this handle */
u64 flags; /* Indicate the capabilities for this handle*/
- unsigned long last_reset_time;
- enum hnae3_reset_type reset_level;
-
union {
struct net_device *netdev; /* first member */
struct hnae3_knic_private_info kinfo;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index d573f5f..183fd83 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -379,7 +379,6 @@ static int hns3_nic_net_up(struct net_device *netdev)
static int hns3_nic_net_open(struct net_device *netdev)
{
- struct hns3_nic_priv *priv = netdev_priv(netdev);
struct hnae3_handle *h = hns3_get_handle(netdev);
struct hnae3_knic_private_info *kinfo;
int i, ret;
@@ -406,7 +405,6 @@ static int hns3_nic_net_open(struct net_device *netdev)
kinfo->prio_tc[i]);
}
- priv->ae_handle->last_reset_time = jiffies;
return 0;
}
@@ -1648,10 +1646,9 @@ static void hns3_nic_net_timeout(struct net_device *ndev)
priv->tx_timeout_count++;
- if (time_before(jiffies, (h->last_reset_time + ndev->watchdog_timeo)))
- return;
-
- /* request the reset */
+ /* request the reset, and let the hclge to determine
+ * which reset level should be done
+ */
if (h->ae_algo->ops->reset_event)
h->ae_algo->ops->reset_event(h->pdev, h);
}
@@ -3370,7 +3367,6 @@ static int hns3_client_init(struct hnae3_handle *handle)
priv->dev = &pdev->dev;
priv->netdev = netdev;
priv->ae_handle = handle;
- priv->ae_handle->last_reset_time = jiffies;
priv->tx_timeout_count = 0;
handle->kinfo.netdev = netdev;
@@ -3390,11 +3386,6 @@ static int hns3_client_init(struct hnae3_handle *handle)
/* Carrier off reporting is important to ethtool even BEFORE open */
netif_carrier_off(netdev);
- if (handle->flags & HNAE3_SUPPORT_VF)
- handle->reset_level = HNAE3_VF_RESET;
- else
- handle->reset_level = HNAE3_FUNC_RESET;
-
ret = hns3_get_ring_config(priv);
if (ret) {
ret = -ENOMEM;
@@ -3785,7 +3776,6 @@ static int hns3_reset_notify_up_enet(struct hnae3_handle *handle)
"hns net up fail, ret=%d!\n", ret);
return ret;
}
- handle->last_reset_time = jiffies;
}
clear_bit(HNS3_NIC_STATE_RESETTING, &priv->state);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 62022d55..a90c19e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2465,15 +2465,14 @@ static void hclge_clear_reset_cause(struct hclge_dev *hdev)
static void hclge_reset(struct hclge_dev *hdev)
{
struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
- struct hnae3_handle *handle;
/* Initialize ae_dev reset status as well, in case enet layer wants to
* know if device is undergoing reset
*/
ae_dev->reset_type = hdev->reset_type;
hdev->reset_count++;
+ hdev->last_reset_time = jiffies;
/* perform reset of the stack & ae device for a client */
- handle = &hdev->vport[0].nic;
rtnl_lock();
hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
rtnl_unlock();
@@ -2493,7 +2492,6 @@ static void hclge_reset(struct hclge_dev *hdev)
}
hclge_notify_client(hdev, HNAE3_UP_CLIENT);
- handle->last_reset_time = jiffies;
rtnl_unlock();
ae_dev->reset_type = HNAE3_NONE_RESET;
}
@@ -2521,24 +2519,24 @@ static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle)
if (!handle)
handle = &hdev->vport[0].nic;
- if (time_before(jiffies, (handle->last_reset_time + 3 * HZ)))
+ if (time_before(jiffies, (hdev->last_reset_time + 3 * HZ)))
return;
else if (hdev->default_reset_request)
- handle->reset_level =
+ hdev->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;
+ else if (time_after(jiffies, (hdev->last_reset_time + 4 * 5 * HZ)))
+ hdev->reset_level = HNAE3_FUNC_RESET;
dev_info(&hdev->pdev->dev, "received reset event , reset type is %d",
- handle->reset_level);
+ hdev->reset_level);
/* request reset & schedule reset task */
- set_bit(handle->reset_level, &hdev->reset_request);
+ set_bit(hdev->reset_level, &hdev->reset_request);
hclge_reset_task_schedule(hdev);
- if (handle->reset_level < HNAE3_GLOBAL_RESET)
- handle->reset_level++;
+ if (hdev->reset_level < HNAE3_GLOBAL_RESET)
+ hdev->reset_level++;
}
static void hclge_set_def_reset_request(struct hnae3_ae_dev *ae_dev,
@@ -2560,6 +2558,7 @@ static void hclge_reset_subtask(struct hclge_dev *hdev)
* b. else, we can come back later to check this status so re-sched
* now.
*/
+ hdev->last_reset_time = jiffies;
hdev->reset_type = hclge_get_reset_level(hdev, &hdev->reset_pending);
if (hdev->reset_type != HNAE3_NONE_RESET)
hclge_reset(hdev);
@@ -6670,6 +6669,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
hdev->pdev = pdev;
hdev->ae_dev = ae_dev;
hdev->reset_type = HNAE3_NONE_RESET;
+ hdev->reset_level = HNAE3_FUNC_RESET;
ae_dev->priv = hdev;
ret = hclge_pci_init(hdev);
@@ -6814,6 +6814,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
hclge_enable_vector(&hdev->misc_vector, true);
hclge_state_init(hdev);
+ hdev->last_reset_time = jiffies;
pr_info("%s driver initialization finished.\n", HCLGE_DRIVER_NAME);
return 0;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index b6a17f5..69bdb7f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -593,8 +593,10 @@ struct hclge_dev {
struct hclge_misc_vector misc_vector;
struct hclge_hw_stats hw_stats;
unsigned long state;
+ unsigned long last_reset_time;
enum hnae3_reset_type reset_type;
+ enum hnae3_reset_type reset_level;
unsigned long default_reset_request;
unsigned long reset_request; /* reset has been requested */
unsigned long reset_pending; /* client rst is pending to be served */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 7531bdd..4a2148b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1234,17 +1234,17 @@ static void hclgevf_reset_event(struct pci_dev *pdev,
dev_info(&hdev->pdev->dev, "received reset request from VF enet\n");
if (!hdev->default_reset_request)
- handle->reset_level =
+ hdev->reset_level =
hclgevf_get_reset_level(hdev,
&hdev->default_reset_request);
else
- handle->reset_level = HNAE3_VF_RESET;
+ hdev->reset_level = HNAE3_VF_RESET;
/* reset of this VF requested */
set_bit(HCLGEVF_RESET_REQUESTED, &hdev->reset_state);
hclgevf_reset_task_schedule(hdev);
- handle->last_reset_time = jiffies;
+ hdev->last_reset_time = jiffies;
}
static void hclgevf_set_def_reset_request(struct hnae3_ae_dev *ae_dev,
@@ -1372,7 +1372,7 @@ static void hclgevf_reset_service_task(struct work_struct *work)
*/
if (hdev->reset_attempts > 3) {
/* prepare for full reset of stack + pcie interface */
- hdev->nic.reset_level = HNAE3_VF_FULL_RESET;
+ hdev->reset_level = HNAE3_VF_FULL_RESET;
/* "defer" schedule the reset task again */
set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
@@ -1985,6 +1985,7 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
}
hclgevf_state_init(hdev);
+ hdev->reset_level = HNAE3_VF_RESET;
ret = hclgevf_misc_irq_init(hdev);
if (ret) {
@@ -2026,6 +2027,7 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
goto err_config;
}
+ hdev->last_reset_time = jiffies;
pr_info("finished initializing %s driver\n", HCLGEVF_DRIVER_NAME);
return 0;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index ffb8c77..0ea4c9b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -146,6 +146,8 @@ struct hclgevf_dev {
struct hclgevf_rss_cfg rss_cfg;
unsigned long state;
unsigned long default_reset_request;
+ unsigned long last_reset_time;
+ enum hnae3_reset_type reset_level;
#define HCLGEVF_RESET_REQUESTED 0
#define HCLGEVF_RESET_PENDING 1
@@ -198,14 +200,14 @@ static inline bool hclgevf_dev_ongoing_reset(struct hclgevf_dev *hdev)
{
return (hdev &&
(test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state)) &&
- (hdev->nic.reset_level == HNAE3_VF_RESET));
+ (hdev->reset_level == HNAE3_VF_RESET));
}
static inline bool hclgevf_dev_ongoing_full_reset(struct hclgevf_dev *hdev)
{
return (hdev &&
(test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state)) &&
- (hdev->nic.reset_level == HNAE3_VF_FULL_RESET));
+ (hdev->reset_level == HNAE3_VF_FULL_RESET));
}
int hclgevf_send_mbx_msg(struct hclgevf_dev *hdev, u16 code, u16 subcode,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
index e9d5a4f..558e3b8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
@@ -267,7 +267,7 @@ void hclgevf_mbx_async_handler(struct hclgevf_dev *hdev)
* has been completely reset. After this stack should
* eventually be re-initialized.
*/
- hdev->nic.reset_level = HNAE3_VF_RESET;
+ hdev->reset_level = HNAE3_VF_RESET;
set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
hclgevf_reset_task_schedule(hdev);
--
2.7.4
^ permalink raw reply related
* [Patch net-next 09/12] net: hns3: adjust the process of PF 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 PF reset, the driver needs to do some preparatory work
before asserting PF reset. Since when hardware is resetting, it
is necessary to stop tx/rx queue, clear hardware table, etc,
otherwise hardware may run into unrecoverable state if there is
still IO running when the hardware is resetting.
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
---
.../ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 38 ++++++++++++++++++++--
1 file changed, 36 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index a90c19e..3c327f8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2396,7 +2396,6 @@ static void hclge_do_reset(struct hclge_dev *hdev)
break;
case HNAE3_FUNC_RESET:
dev_info(&pdev->dev, "PF Reset requested\n");
- hclge_func_reset_cmd(hdev, 0);
/* schedule again to check later */
set_bit(HNAE3_FUNC_RESET, &hdev->reset_pending);
hclge_reset_task_schedule(hdev);
@@ -2462,6 +2461,35 @@ static void hclge_clear_reset_cause(struct hclge_dev *hdev)
hclge_enable_vector(&hdev->misc_vector, true);
}
+static int hclge_reset_prepare_wait(struct hclge_dev *hdev)
+{
+ int ret = 0;
+
+ switch (hdev->reset_type) {
+ case HNAE3_FUNC_RESET:
+ ret = hclge_func_reset_cmd(hdev, 0);
+ if (ret) {
+ dev_err(&hdev->pdev->dev,
+ "assertting function reset fail %d!\n", ret);
+ return ret;
+ }
+
+ /* After performaning pf reset, it is not necessary to do the
+ * mailbox handling or send any command to firmware, because
+ * any mailbox handling or command to firmware is only valid
+ * after hclge_cmd_init is called.
+ */
+ set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
+ break;
+ default:
+ break;
+ }
+
+ dev_info(&hdev->pdev->dev, "prepare wait ok\n");
+
+ return ret;
+}
+
static void hclge_reset(struct hclge_dev *hdev)
{
struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
@@ -2477,6 +2505,8 @@ static void hclge_reset(struct hclge_dev *hdev)
hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
rtnl_unlock();
+ hclge_reset_prepare_wait(hdev);
+
if (!hclge_reset_wait(hdev)) {
rtnl_lock();
hclge_notify_client(hdev, HNAE3_UNINIT_CLIENT);
@@ -4873,7 +4903,11 @@ static void hclge_ae_stop(struct hnae3_handle *handle)
cancel_work_sync(&hdev->service_task);
clear_bit(HCLGE_STATE_SERVICE_SCHED, &hdev->state);
- if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) {
+ /* If it is not PF reset, the firmware will disable the MAC,
+ * so it only need to stop phy here.
+ */
+ if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) &&
+ hdev->reset_type != HNAE3_FUNC_RESET) {
hclge_mac_stop_phy(hdev);
return;
}
--
2.7.4
^ permalink raw reply related
* [Patch net-next 10/12] net: hns3: call roce's reset notify callback when 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 doing resetting, roce should do its uninitailization part
before nic's, and do its initialization part after nic's.
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
---
.../ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 33 ++++++++++++++++++++++
1 file changed, 33 insertions(+)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 3c327f8..0c0327b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2315,6 +2315,34 @@ static int hclge_notify_client(struct hclge_dev *hdev,
return 0;
}
+static int hclge_notify_roce_client(struct hclge_dev *hdev,
+ enum hnae3_reset_notify_type type)
+{
+ struct hnae3_client *client = hdev->roce_client;
+ int ret = 0;
+ u16 i;
+
+ if (!client)
+ return 0;
+
+ if (!client->ops->reset_notify)
+ return -EOPNOTSUPP;
+
+ for (i = 0; i < hdev->num_vmdq_vport + 1; i++) {
+ struct hnae3_handle *handle = &hdev->vport[i].roce;
+
+ ret = client->ops->reset_notify(handle, type);
+ if (ret) {
+ dev_err(&hdev->pdev->dev,
+ "notify roce client failed %d(%d)",
+ type, ret);
+ return ret;
+ }
+ }
+
+ return ret;
+}
+
static int hclge_reset_wait(struct hclge_dev *hdev)
{
#define HCLGE_RESET_WATI_MS 100
@@ -2501,6 +2529,7 @@ static void hclge_reset(struct hclge_dev *hdev)
hdev->reset_count++;
hdev->last_reset_time = jiffies;
/* perform reset of the stack & ae device for a client */
+ hclge_notify_roce_client(hdev, HNAE3_DOWN_CLIENT);
rtnl_lock();
hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
rtnl_unlock();
@@ -2508,6 +2537,7 @@ static void hclge_reset(struct hclge_dev *hdev)
hclge_reset_prepare_wait(hdev);
if (!hclge_reset_wait(hdev)) {
+ hclge_notify_roce_client(hdev, HNAE3_UNINIT_CLIENT);
rtnl_lock();
hclge_notify_client(hdev, HNAE3_UNINIT_CLIENT);
hclge_reset_ae_dev(hdev->ae_dev);
@@ -2524,6 +2554,9 @@ static void hclge_reset(struct hclge_dev *hdev)
hclge_notify_client(hdev, HNAE3_UP_CLIENT);
rtnl_unlock();
ae_dev->reset_type = HNAE3_NONE_RESET;
+
+ hclge_notify_roce_client(hdev, HNAE3_INIT_CLIENT);
+ hclge_notify_roce_client(hdev, HNAE3_UP_CLIENT);
}
static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle)
--
2.7.4
^ permalink raw reply related
* [Patch net-next 11/12] net: hns3: add error handler for hclge_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 hclge_reset() is called, it may fail for several reasons.
For example, an higher-level reset event occurs, memory allocation
failure, hardware reset timeout, etc. Therefore, it is necessary
to add corresponding error handling for these situations.
1. A high-level reset is required due to a high-level reset failure.
2. For memory allocation failure, a high-level reset is initiated by
the timer to recover. The reason for using the timer is to prevent this
new high-level reset to interrupt the reset process of other pf/vf;
3. For the case of hardware reset timeout, reschedule the reset task
to wait for the hardware to complete the reset.
For memory allocation failure and reset timeouts, in order to prevent
an infinite number of scheduled reset tasks, the number of error
recovery needs to be limited.
This patch also add some reset related debug log printing.
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
---
.../ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 139 +++++++++++++++++----
.../ethernet/hisilicon/hns3/hns3pf/hclge_main.h | 3 +
2 files changed, 120 insertions(+), 22 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 0c0327b..579945b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2145,6 +2145,7 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
/* check for vector0 reset event sources */
if (BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B) & rst_src_reg) {
+ dev_info(&hdev->pdev->dev, "global reset interrupt\n");
set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
set_bit(HNAE3_GLOBAL_RESET, &hdev->reset_pending);
*clearval = BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B);
@@ -2152,6 +2153,7 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
}
if (BIT(HCLGE_VECTOR0_CORERESET_INT_B) & rst_src_reg) {
+ dev_info(&hdev->pdev->dev, "core reset interrupt\n");
set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
set_bit(HNAE3_CORE_RESET, &hdev->reset_pending);
*clearval = BIT(HCLGE_VECTOR0_CORERESET_INT_B);
@@ -2159,6 +2161,7 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
}
if (BIT(HCLGE_VECTOR0_IMPRESET_INT_B) & rst_src_reg) {
+ dev_info(&hdev->pdev->dev, "IMP reset interrupt\n");
set_bit(HNAE3_IMP_RESET, &hdev->reset_pending);
*clearval = BIT(HCLGE_VECTOR0_IMPRESET_INT_B);
return HCLGE_VECTOR0_EVENT_RST;
@@ -2308,8 +2311,11 @@ static int hclge_notify_client(struct hclge_dev *hdev,
int ret;
ret = client->ops->reset_notify(handle, type);
- if (ret)
+ if (ret) {
+ dev_err(&hdev->pdev->dev,
+ "notify nic client failed %d(%d)\n", type, ret);
return ret;
+ }
}
return 0;
@@ -2518,9 +2524,49 @@ static int hclge_reset_prepare_wait(struct hclge_dev *hdev)
return ret;
}
+static bool hclge_reset_err_handle(struct hclge_dev *hdev, bool is_timeout)
+{
+#define MAX_RESET_FAIL_CNT 5
+#define RESET_UPGRADE_DELAY_SEC 10
+
+ if (hdev->reset_pending) {
+ dev_info(&hdev->pdev->dev, "Reset pending %lu\n",
+ hdev->reset_pending);
+ return true;
+ } else if ((hdev->reset_type != HNAE3_IMP_RESET) &&
+ (hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG) &
+ BIT(HCLGE_IMP_RESET_BIT))) {
+ dev_info(&hdev->pdev->dev,
+ "reset failed because IMP Reset is pending\n");
+ hclge_clear_reset_cause(hdev);
+ return false;
+ } else if (hdev->reset_fail_cnt < MAX_RESET_FAIL_CNT) {
+ hdev->reset_fail_cnt++;
+ if (is_timeout) {
+ set_bit(hdev->reset_type, &hdev->reset_pending);
+ dev_info(&hdev->pdev->dev,
+ "re-schedule to wait for hw reset done\n");
+ return true;
+ }
+
+ dev_info(&hdev->pdev->dev, "Upgrade reset level\n");
+ hclge_clear_reset_cause(hdev);
+ mod_timer(&hdev->reset_timer,
+ jiffies + RESET_UPGRADE_DELAY_SEC * HZ);
+
+ return false;
+ }
+
+ hclge_clear_reset_cause(hdev);
+ dev_err(&hdev->pdev->dev, "Reset fail!\n");
+ return false;
+}
+
static void hclge_reset(struct hclge_dev *hdev)
{
struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
+ bool is_timeout = false;
+ int ret;
/* Initialize ae_dev reset status as well, in case enet layer wants to
* know if device is undergoing reset
@@ -2529,34 +2575,66 @@ static void hclge_reset(struct hclge_dev *hdev)
hdev->reset_count++;
hdev->last_reset_time = jiffies;
/* perform reset of the stack & ae device for a client */
- hclge_notify_roce_client(hdev, HNAE3_DOWN_CLIENT);
+ ret = hclge_notify_roce_client(hdev, HNAE3_DOWN_CLIENT);
+ if (ret)
+ goto err_reset;
+
rtnl_lock();
- hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
- rtnl_unlock();
+ ret = hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
+ if (ret)
+ goto err_reset_lock;
- hclge_reset_prepare_wait(hdev);
+ rtnl_unlock();
- if (!hclge_reset_wait(hdev)) {
- hclge_notify_roce_client(hdev, HNAE3_UNINIT_CLIENT);
- rtnl_lock();
- hclge_notify_client(hdev, HNAE3_UNINIT_CLIENT);
- hclge_reset_ae_dev(hdev->ae_dev);
- hclge_notify_client(hdev, HNAE3_INIT_CLIENT);
+ ret = hclge_reset_prepare_wait(hdev);
+ if (ret)
+ goto err_reset;
- hclge_clear_reset_cause(hdev);
- } else {
- rtnl_lock();
- /* schedule again to check pending resets later */
- set_bit(hdev->reset_type, &hdev->reset_pending);
- hclge_reset_task_schedule(hdev);
+ if (hclge_reset_wait(hdev)) {
+ is_timeout = true;
+ goto err_reset;
}
- hclge_notify_client(hdev, HNAE3_UP_CLIENT);
+ ret = hclge_notify_roce_client(hdev, HNAE3_UNINIT_CLIENT);
+ if (ret)
+ goto err_reset;
+
+ rtnl_lock();
+ ret = hclge_notify_client(hdev, HNAE3_UNINIT_CLIENT);
+ if (ret)
+ goto err_reset_lock;
+
+ ret = hclge_reset_ae_dev(hdev->ae_dev);
+ if (ret)
+ goto err_reset_lock;
+
+ ret = hclge_notify_client(hdev, HNAE3_INIT_CLIENT);
+ if (ret)
+ goto err_reset_lock;
+
+ hclge_clear_reset_cause(hdev);
+
+ ret = hclge_notify_client(hdev, HNAE3_UP_CLIENT);
+ if (ret)
+ goto err_reset_lock;
+
rtnl_unlock();
- ae_dev->reset_type = HNAE3_NONE_RESET;
- hclge_notify_roce_client(hdev, HNAE3_INIT_CLIENT);
- hclge_notify_roce_client(hdev, HNAE3_UP_CLIENT);
+ ret = hclge_notify_roce_client(hdev, HNAE3_INIT_CLIENT);
+ if (ret)
+ goto err_reset;
+
+ ret = hclge_notify_roce_client(hdev, HNAE3_UP_CLIENT);
+ if (ret)
+ goto err_reset;
+
+ return;
+
+err_reset_lock:
+ rtnl_unlock();
+err_reset:
+ if (hclge_reset_err_handle(hdev, is_timeout))
+ hclge_reset_task_schedule(hdev);
}
static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle)
@@ -2610,6 +2688,16 @@ static void hclge_set_def_reset_request(struct hnae3_ae_dev *ae_dev,
set_bit(rst_type, &hdev->default_reset_request);
}
+static void hclge_reset_timer(struct timer_list *t)
+{
+ struct hclge_dev *hdev = from_timer(hdev, t, reset_timer);
+
+ dev_info(&hdev->pdev->dev,
+ "triggering global reset in reset timer\n");
+ set_bit(HNAE3_GLOBAL_RESET, &hdev->default_reset_request);
+ hclge_reset_event(hdev->pdev, NULL);
+}
+
static void hclge_reset_subtask(struct hclge_dev *hdev)
{
/* check if there is any ongoing reset in the hardware. This status can
@@ -4416,8 +4504,12 @@ static int hclge_restore_fd_entries(struct hnae3_handle *handle)
struct hlist_node *node;
int ret;
+ /* Return ok here, because reset error handling will check this
+ * return value. If error is returned here, the reset process will
+ * fail.
+ */
if (!hnae3_dev_fd_supported(hdev))
- return -EOPNOTSUPP;
+ return 0;
hlist_for_each_entry_safe(rule, node, &hdev->fd_rule_list, rule_node) {
ret = hclge_config_action(hdev, HCLGE_FD_STAGE_1, rule);
@@ -6713,6 +6805,8 @@ static void hclge_state_uninit(struct hclge_dev *hdev)
if (hdev->service_timer.function)
del_timer_sync(&hdev->service_timer);
+ if (hdev->reset_timer.function)
+ del_timer_sync(&hdev->reset_timer);
if (hdev->service_task.func)
cancel_work_sync(&hdev->service_task);
if (hdev->rst_service_task.func)
@@ -6871,6 +6965,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
hclge_dcb_ops_set(hdev);
timer_setup(&hdev->service_timer, hclge_service_timer, 0);
+ timer_setup(&hdev->reset_timer, hclge_reset_timer, 0);
INIT_WORK(&hdev->service_task, hclge_service_task);
INIT_WORK(&hdev->rst_service_task, hclge_reset_service_task);
INIT_WORK(&hdev->mbx_service_task, hclge_mailbox_service_task);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 69bdb7f..36f3413 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -102,6 +102,7 @@ enum HLCGE_PORT_TYPE {
#define HCLGE_GLOBAL_RESET_REG 0x20A00
#define HCLGE_GLOBAL_RESET_BIT 0
#define HCLGE_CORE_RESET_BIT 1
+#define HCLGE_IMP_RESET_BIT 2
#define HCLGE_FUN_RST_ING 0x20C00
#define HCLGE_FUN_RST_ING_B 0
@@ -601,6 +602,7 @@ struct hclge_dev {
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 reset_fail_cnt;
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 */
@@ -648,6 +650,7 @@ struct hclge_dev {
unsigned long service_timer_period;
unsigned long service_timer_previous;
struct timer_list service_timer;
+ struct timer_list reset_timer;
struct work_struct service_task;
struct work_struct rst_service_task;
struct work_struct mbx_service_task;
--
2.7.4
^ permalink raw reply related
* [Patch net-next 12/12] net: hns3: fix for cmd queue memory not freed problem during 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>
It is not necessary to reallocate the descriptor and remap the
descriptor memory in reset process, otherwise it may cause memory
not freed problem.
Also, this patch initializes the cmd queue's spinlocks in
hclgevf_alloc_cmd_queue, and take the spinlocks when reinitializing
cmd queue' registers.
Fixes: fedd0c15d288 ("net: hns3: Add HNS3 VF IMP(Integrated Management Proc) cmd interface")
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
.../ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c | 141 ++++++++++++---------
.../ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h | 1 +
.../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 14 +-
3 files changed, 91 insertions(+), 65 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
index 0d3b445..b917acf 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
@@ -72,6 +72,45 @@ static bool hclgevf_is_special_opcode(u16 opcode)
return false;
}
+static void hclgevf_cmd_config_regs(struct hclgevf_cmq_ring *ring)
+{
+ struct hclgevf_dev *hdev = ring->dev;
+ struct hclgevf_hw *hw = &hdev->hw;
+ u32 reg_val;
+
+ if (ring->flag == HCLGEVF_TYPE_CSQ) {
+ reg_val = (u32)ring->desc_dma_addr;
+ hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_BASEADDR_L_REG, reg_val);
+ reg_val = (u32)((ring->desc_dma_addr >> 31) >> 1);
+ hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_BASEADDR_H_REG, reg_val);
+
+ reg_val = (ring->desc_num >> HCLGEVF_NIC_CMQ_DESC_NUM_S);
+ reg_val |= HCLGEVF_NIC_CMQ_ENABLE;
+ hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_DEPTH_REG, reg_val);
+
+ hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_HEAD_REG, 0);
+ hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_TAIL_REG, 0);
+ } else {
+ reg_val = (u32)ring->desc_dma_addr;
+ hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_BASEADDR_L_REG, reg_val);
+ reg_val = (u32)((ring->desc_dma_addr >> 31) >> 1);
+ hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_BASEADDR_H_REG, reg_val);
+
+ reg_val = (ring->desc_num >> HCLGEVF_NIC_CMQ_DESC_NUM_S);
+ reg_val |= HCLGEVF_NIC_CMQ_ENABLE;
+ hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_DEPTH_REG, reg_val);
+
+ hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_HEAD_REG, 0);
+ hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_TAIL_REG, 0);
+ }
+}
+
+static void hclgevf_cmd_init_regs(struct hclgevf_hw *hw)
+{
+ hclgevf_cmd_config_regs(&hw->cmq.csq);
+ hclgevf_cmd_config_regs(&hw->cmq.crq);
+}
+
static int hclgevf_alloc_cmd_desc(struct hclgevf_cmq_ring *ring)
{
int size = ring->desc_num * sizeof(struct hclgevf_desc);
@@ -96,61 +135,23 @@ static void hclgevf_free_cmd_desc(struct hclgevf_cmq_ring *ring)
}
}
-static int hclgevf_init_cmd_queue(struct hclgevf_dev *hdev,
- struct hclgevf_cmq_ring *ring)
+static int hclgevf_alloc_cmd_queue(struct hclgevf_dev *hdev, int ring_type)
{
struct hclgevf_hw *hw = &hdev->hw;
- int ring_type = ring->flag;
- u32 reg_val;
+ struct hclgevf_cmq_ring *ring =
+ (ring_type == HCLGEVF_TYPE_CSQ) ? &hw->cmq.csq : &hw->cmq.crq;
int ret;
- ring->desc_num = HCLGEVF_NIC_CMQ_DESC_NUM;
- spin_lock_init(&ring->lock);
- ring->next_to_clean = 0;
- ring->next_to_use = 0;
ring->dev = hdev;
+ ring->flag = ring_type;
/* allocate CSQ/CRQ descriptor */
ret = hclgevf_alloc_cmd_desc(ring);
- if (ret) {
+ if (ret)
dev_err(&hdev->pdev->dev, "failed(%d) to alloc %s desc\n", ret,
(ring_type == HCLGEVF_TYPE_CSQ) ? "CSQ" : "CRQ");
- return ret;
- }
-
- /* initialize the hardware registers with csq/crq dma-address,
- * descriptor number, head & tail pointers
- */
- switch (ring_type) {
- case HCLGEVF_TYPE_CSQ:
- reg_val = (u32)ring->desc_dma_addr;
- hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_BASEADDR_L_REG, reg_val);
- reg_val = (u32)((ring->desc_dma_addr >> 31) >> 1);
- hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_BASEADDR_H_REG, reg_val);
- reg_val = (ring->desc_num >> HCLGEVF_NIC_CMQ_DESC_NUM_S);
- reg_val |= HCLGEVF_NIC_CMQ_ENABLE;
- hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_DEPTH_REG, reg_val);
-
- hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_HEAD_REG, 0);
- hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_TAIL_REG, 0);
- return 0;
- case HCLGEVF_TYPE_CRQ:
- reg_val = (u32)ring->desc_dma_addr;
- hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_BASEADDR_L_REG, reg_val);
- reg_val = (u32)((ring->desc_dma_addr >> 31) >> 1);
- hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_BASEADDR_H_REG, reg_val);
-
- reg_val = (ring->desc_num >> HCLGEVF_NIC_CMQ_DESC_NUM_S);
- reg_val |= HCLGEVF_NIC_CMQ_ENABLE;
- hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_DEPTH_REG, reg_val);
-
- hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_HEAD_REG, 0);
- hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_TAIL_REG, 0);
- return 0;
- default:
- return -EINVAL;
- }
+ return ret;
}
void hclgevf_cmd_setup_basic_desc(struct hclgevf_desc *desc,
@@ -282,55 +283,73 @@ static int hclgevf_cmd_query_firmware_version(struct hclgevf_hw *hw,
return status;
}
-int hclgevf_cmd_init(struct hclgevf_dev *hdev)
+int hclgevf_cmd_queue_init(struct hclgevf_dev *hdev)
{
- u32 version;
int ret;
- /* setup Tx write back timeout */
+ /* Setup the lock for command queue */
+ spin_lock_init(&hdev->hw.cmq.csq.lock);
+ spin_lock_init(&hdev->hw.cmq.crq.lock);
+
hdev->hw.cmq.tx_timeout = HCLGEVF_CMDQ_TX_TIMEOUT;
+ hdev->hw.cmq.csq.desc_num = HCLGEVF_NIC_CMQ_DESC_NUM;
+ hdev->hw.cmq.crq.desc_num = HCLGEVF_NIC_CMQ_DESC_NUM;
- /* setup queue CSQ/CRQ rings */
- hdev->hw.cmq.csq.flag = HCLGEVF_TYPE_CSQ;
- ret = hclgevf_init_cmd_queue(hdev, &hdev->hw.cmq.csq);
+ ret = hclgevf_alloc_cmd_queue(hdev, HCLGEVF_TYPE_CSQ);
if (ret) {
dev_err(&hdev->pdev->dev,
- "failed(%d) to initialize CSQ ring\n", ret);
+ "CSQ ring setup error %d\n", ret);
return ret;
}
- hdev->hw.cmq.crq.flag = HCLGEVF_TYPE_CRQ;
- ret = hclgevf_init_cmd_queue(hdev, &hdev->hw.cmq.crq);
+ ret = hclgevf_alloc_cmd_queue(hdev, HCLGEVF_TYPE_CRQ);
if (ret) {
dev_err(&hdev->pdev->dev,
- "failed(%d) to initialize CRQ ring\n", ret);
+ "CRQ ring setup error %d\n", ret);
goto err_csq;
}
+ return 0;
+err_csq:
+ hclgevf_free_cmd_desc(&hdev->hw.cmq.csq);
+ return ret;
+}
+
+int hclgevf_cmd_init(struct hclgevf_dev *hdev)
+{
+ u32 version;
+ int ret;
+
+ spin_lock_bh(&hdev->hw.cmq.csq.lock);
+ spin_lock_bh(&hdev->hw.cmq.crq.lock);
+
/* initialize the pointers of async rx queue of mailbox */
hdev->arq.hdev = hdev;
hdev->arq.head = 0;
hdev->arq.tail = 0;
hdev->arq.count = 0;
+ hdev->hw.cmq.csq.next_to_clean = 0;
+ hdev->hw.cmq.csq.next_to_use = 0;
+ hdev->hw.cmq.crq.next_to_clean = 0;
+ hdev->hw.cmq.crq.next_to_use = 0;
+
+ hclgevf_cmd_init_regs(&hdev->hw);
+
+ spin_unlock_bh(&hdev->hw.cmq.crq.lock);
+ spin_unlock_bh(&hdev->hw.cmq.csq.lock);
/* get firmware version */
ret = hclgevf_cmd_query_firmware_version(&hdev->hw, &version);
if (ret) {
dev_err(&hdev->pdev->dev,
"failed(%d) to query firmware version\n", ret);
- goto err_crq;
+ return ret;
}
hdev->fw_version = version;
dev_info(&hdev->pdev->dev, "The firmware version is %08x\n", version);
return 0;
-err_crq:
- hclgevf_free_cmd_desc(&hdev->hw.cmq.crq);
-err_csq:
- hclgevf_free_cmd_desc(&hdev->hw.cmq.csq);
-
- return ret;
}
void hclgevf_cmd_uninit(struct hclgevf_dev *hdev)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
index bc294b0..090541d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
@@ -256,6 +256,7 @@ static inline u32 hclgevf_read_reg(u8 __iomem *base, u32 reg)
int hclgevf_cmd_init(struct hclgevf_dev *hdev);
void hclgevf_cmd_uninit(struct hclgevf_dev *hdev);
+int hclgevf_cmd_queue_init(struct hclgevf_dev *hdev);
int hclgevf_cmd_send(struct hclgevf_hw *hw, struct hclgevf_desc *desc, int num);
void hclgevf_cmd_setup_basic_desc(struct hclgevf_desc *desc,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 4a2148b..29da480 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1966,6 +1966,12 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
return ret;
}
+ ret = hclgevf_cmd_queue_init(hdev);
+ if (ret) {
+ dev_err(&pdev->dev, "Cmd queue init failed: %d\n", ret);
+ goto err_cmd_queue_init;
+ }
+
ret = hclgevf_cmd_init(hdev);
if (ret)
goto err_cmd_init;
@@ -1975,13 +1981,13 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
if (ret) {
dev_err(&hdev->pdev->dev,
"Query vf status error, ret = %d.\n", ret);
- goto err_query_vf;
+ goto err_cmd_init;
}
ret = hclgevf_init_msi(hdev);
if (ret) {
dev_err(&pdev->dev, "failed(%d) to init MSI/MSI-X\n", ret);
- goto err_query_vf;
+ goto err_cmd_init;
}
hclgevf_state_init(hdev);
@@ -2037,9 +2043,9 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
err_misc_irq_init:
hclgevf_state_uninit(hdev);
hclgevf_uninit_msi(hdev);
-err_query_vf:
- hclgevf_cmd_uninit(hdev);
err_cmd_init:
+ hclgevf_cmd_uninit(hdev);
+err_cmd_queue_init:
hclgevf_pci_uninit(hdev);
return ret;
}
--
2.7.4
^ permalink raw reply related
* Re: [PATCH v2 net 0/3] net: bql: better deal with GSO
From: David Miller @ 2018-11-06 18:41 UTC (permalink / raw)
To: ecree; +Cc: edumazet, netdev, eric.dumazet
In-Reply-To: <02bf6e76-a987-b3a4-809e-332b72558bb2@solarflare.com>
From: Edward Cree <ecree@solarflare.com>
Date: Tue, 6 Nov 2018 18:23:42 +0000
> 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?
As the driver maintainer I guess I can lead that judgment up to you
at least to a certain extent.
^ permalink raw reply
* Re: [PATCH bpf-next v2 02/13] bpf: btf: Add BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO
From: Edward Cree @ 2018-11-06 18:52 UTC (permalink / raw)
To: Alexei Starovoitov
Cc: Martin Lau, Yonghong Song, Alexei Starovoitov,
daniel@iogearbox.net, netdev@vger.kernel.org, Kernel Team
In-Reply-To: <20181106062913.h7zxoduijayfqvbr@ast-mbp>
On 06/11/18 06:29, Alexei Starovoitov wrote:
> BTF is not pure type information. BTF is everything that verifier needs
> to know to make safety decisions that bpf instruction set doesn't have.
Yes, I'm not disputing that and never have.
I'm just saying that it will be much cleaner and better if it's
internally organised differently.
> Splitting pure types into one section, variables into another,
> functions into yet another is not practical, since the same
> modifiers (like const or volatile) need to be applied to
> variables and functions. At the end all sections will have
> the same style of encoding, hence no need to duplicate
> the encoding three times and instead it's cleaner to encode
> all of them BTF-style via different KINDs.
This shows that you've misunderstood what I'm proposing, probably
I explained it poorly so I'll try again.
I'm not suggesting that the 'functions' and 'variables' sections
would have _type_ records in them, only that they would reference
records in the 'types' section. So if for instance we have
int foo(int x) { int quux; /* ... */ }
int bar(int y) { /* ... */ }
in the source, then in the 'types' section we would have
1 INT 32bits encoding=signed offset=0
2 FUNC args=(name="x" type=1,), ret=1
3 FUNC args=(name="y" type=1,), ret=1
while in the 'functions' section we would have
1 "foo" type=2 start_insn_idx=23 insn_count=19 (... maybe other info too...)
2 "bar" type=3 start_insn_idx=42 insn_count=5
and in the 'variables' section we might have
1 "quux" type=1 where=stack func=1 offset=-8
Thus the graph of types lives entirely in the 'types' section, but
things-that-are-not-types don't. I'm not making a distinction
between "pure types" and (somehow) impure types; I'm making a
distinction between types (with all their impurities) and
*instances* of those types.
Note that these 'sections' may all really be regions of the '.BTF'
ELF section, if that makes the implementation easier. Also, the
'functions' and 'variables' sections _won't_ have the same style
of encoding as the 'types', because they're storing entirely
different data and in fact don't need variable record sizes.
And note that in this case any const or volatile qualifiers happen
_in the 'types' section_, because they're just another way of
deriving a type, and the records in other sections that might want
them will just point at a BTF_KIND_CONST or BTF_KIND_VOLATILE
record in the 'types' section.
-Ed
^ permalink raw reply
* net-next is OPEN...
From: David Miller @ 2018-11-06 19:13 UTC (permalink / raw)
To: netdev
Do it, to it.
^ permalink raw reply
* [PATCH net-next 0/3] mlxsw: Add fw_version_check devlink parameter
From: Ido Schimmel @ 2018-11-06 20:04 UTC (permalink / raw)
To: netdev@vger.kernel.org
Cc: davem@davemloft.net, Jiri Pirko, Shalom Toledo, Moshe Shemesh,
dsahern@gmail.com, jakub.kicinski@netronome.com, andrew@lunn.ch,
f.fainelli@gmail.com, mlxsw, Ido Schimmel
Shalom says:
Currently, drivers do not have the ability to skip the firmware version
check during their initialization flow. Hence, drivers will always flash
a compatible version. This prevents drivers from running the device with
a different firmware version for testing and/or debugging purposes. For
example, testing a firmware bug fix.
For these situations, the new devlink generic parameter,
fw_version_check, gives the ability to skip the version check and allows
drivers to run with a different firmware version than what is required
by the driver.
Patch #1 adds the new parameter to devlink. The other two patches, #2
and #3, add support for this parameter in the mlxsw driver.
Shalom Toledo (3):
devlink: Add fw_version_check generic parameter
mlxsw: core: Reset firmware after flash during driver initialization
mlxsw: spectrum: Skip firmware version check based on devlink
parameter
drivers/net/ethernet/mellanox/mlxsw/core.c | 45 +++++++++++++++++--
drivers/net/ethernet/mellanox/mlxsw/core.h | 2 +
drivers/net/ethernet/mellanox/mlxsw/pci.c | 11 +----
.../net/ethernet/mellanox/mlxsw/spectrum.c | 45 +++++++++++++++++++
include/net/devlink.h | 4 ++
net/core/devlink.c | 5 +++
6 files changed, 98 insertions(+), 14 deletions(-)
--
2.19.1
^ permalink raw reply
* [PATCH net-next 1/3] devlink: Add fw_version_check generic parameter
From: Ido Schimmel @ 2018-11-06 20:05 UTC (permalink / raw)
To: netdev@vger.kernel.org
Cc: davem@davemloft.net, Jiri Pirko, Shalom Toledo, Moshe Shemesh,
dsahern@gmail.com, jakub.kicinski@netronome.com, andrew@lunn.ch,
f.fainelli@gmail.com, mlxsw, Ido Schimmel
In-Reply-To: <20181106200314.29918-1-idosch@mellanox.com>
From: Shalom Toledo <shalomt@mellanox.com>
Many drivers checking the device's firmware version during the
initialization flow and flashing a compatible version if the current
version is not.
fw_version_check gives the ability to skip this check which allows to run
the device with a different firmware version than required by the driver
for testing and/or debugging purposes.
Signed-off-by: Shalom Toledo <shalomt@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
---
include/net/devlink.h | 4 ++++
net/core/devlink.c | 5 +++++
2 files changed, 9 insertions(+)
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 45db0c79462d..d47ea9d38252 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -365,6 +365,7 @@ enum devlink_param_generic_id {
DEVLINK_PARAM_GENERIC_ID_IGNORE_ARI,
DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX,
DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN,
+ DEVLINK_PARAM_GENERIC_ID_FW_VERSION_CHECK,
/* add new param generic ids above here*/
__DEVLINK_PARAM_GENERIC_ID_MAX,
@@ -392,6 +393,9 @@ enum devlink_param_generic_id {
#define DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_NAME "msix_vec_per_pf_min"
#define DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_TYPE DEVLINK_PARAM_TYPE_U32
+#define DEVLINK_PARAM_GENERIC_FW_VERSION_CHECK_NAME "fw_version_check"
+#define DEVLINK_PARAM_GENERIC_FW_VERSION_CHECK_TYPE DEVLINK_PARAM_TYPE_BOOL
+
#define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate) \
{ \
.id = DEVLINK_PARAM_GENERIC_ID_##_id, \
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 3a4b29a13d31..1a09ad057851 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -2692,6 +2692,11 @@ static const struct devlink_param devlink_param_generic[] = {
.name = DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_NAME,
.type = DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_TYPE,
},
+ {
+ .id = DEVLINK_PARAM_GENERIC_ID_FW_VERSION_CHECK,
+ .name = DEVLINK_PARAM_GENERIC_FW_VERSION_CHECK_NAME,
+ .type = DEVLINK_PARAM_GENERIC_FW_VERSION_CHECK_TYPE,
+ },
};
static int devlink_param_generic_verify(const struct devlink_param *param)
--
2.19.1
^ permalink raw reply related
* [PATCH net-next 2/3] mlxsw: core: Reset firmware after flash during driver initialization
From: Ido Schimmel @ 2018-11-06 20:05 UTC (permalink / raw)
To: netdev@vger.kernel.org
Cc: davem@davemloft.net, Jiri Pirko, Shalom Toledo, Moshe Shemesh,
dsahern@gmail.com, jakub.kicinski@netronome.com, andrew@lunn.ch,
f.fainelli@gmail.com, mlxsw, Ido Schimmel
In-Reply-To: <20181106200314.29918-1-idosch@mellanox.com>
From: Shalom Toledo <shalomt@mellanox.com>
After flashing new firmware during the driver initialization flow (reload
or not), the driver should do a firmware reset when it gets -EAGAIN in
order to load the new one.
Signed-off-by: Shalom Toledo <shalomt@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
---
drivers/net/ethernet/mellanox/mlxsw/core.c | 32 +++++++++++++++++++---
drivers/net/ethernet/mellanox/mlxsw/pci.c | 11 +-------
2 files changed, 29 insertions(+), 14 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 30f751e69698..b2e1b83525db 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -965,10 +965,11 @@ static const struct devlink_ops mlxsw_devlink_ops = {
.sb_occ_tc_port_bind_get = mlxsw_devlink_sb_occ_tc_port_bind_get,
};
-int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
- const struct mlxsw_bus *mlxsw_bus,
- void *bus_priv, bool reload,
- struct devlink *devlink)
+static int
+__mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
+ const struct mlxsw_bus *mlxsw_bus,
+ void *bus_priv, bool reload,
+ struct devlink *devlink)
{
const char *device_kind = mlxsw_bus_info->device_kind;
struct mlxsw_core *mlxsw_core;
@@ -1076,6 +1077,29 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
err_devlink_alloc:
return err;
}
+
+int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
+ const struct mlxsw_bus *mlxsw_bus,
+ void *bus_priv, bool reload,
+ struct devlink *devlink)
+{
+ bool called_again = false;
+ int err;
+
+again:
+ err = __mlxsw_core_bus_device_register(mlxsw_bus_info, mlxsw_bus,
+ bus_priv, reload, devlink);
+ /* -EAGAIN is returned in case the FW was updated. FW needs
+ * a reset, so lets try to call __mlxsw_core_bus_device_register()
+ * again.
+ */
+ if (err == -EAGAIN && !called_again) {
+ called_again = true;
+ goto again;
+ }
+
+ return err;
+}
EXPORT_SYMBOL(mlxsw_core_bus_device_register);
void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index 5890fdfd62c3..66b8098c6fd2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -1720,7 +1720,6 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
const char *driver_name = pdev->driver->name;
struct mlxsw_pci *mlxsw_pci;
- bool called_again = false;
int err;
mlxsw_pci = kzalloc(sizeof(*mlxsw_pci), GFP_KERNEL);
@@ -1777,18 +1776,10 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
mlxsw_pci->bus_info.dev = &pdev->dev;
mlxsw_pci->id = id;
-again:
err = mlxsw_core_bus_device_register(&mlxsw_pci->bus_info,
&mlxsw_pci_bus, mlxsw_pci, false,
NULL);
- /* -EAGAIN is returned in case the FW was updated. FW needs
- * a reset, so lets try to call mlxsw_core_bus_device_register()
- * again.
- */
- if (err == -EAGAIN && !called_again) {
- called_again = true;
- goto again;
- } else if (err) {
+ if (err) {
dev_err(&pdev->dev, "cannot register bus device\n");
goto err_bus_device_register;
}
--
2.19.1
^ permalink raw reply related
* [PATCH net-next 3/3] mlxsw: spectrum: Skip firmware version check based on devlink parameter
From: Ido Schimmel @ 2018-11-06 20:05 UTC (permalink / raw)
To: netdev@vger.kernel.org
Cc: davem@davemloft.net, Jiri Pirko, Shalom Toledo, Moshe Shemesh,
dsahern@gmail.com, jakub.kicinski@netronome.com, andrew@lunn.ch,
f.fainelli@gmail.com, mlxsw, Ido Schimmel
In-Reply-To: <20181106200314.29918-1-idosch@mellanox.com>
From: Shalom Toledo <shalomt@mellanox.com>
Based on fw_version_check devlink parameter, skip firmware version check in
order to run the device with different firmware version than required by
the driver for testing and/or debugging purposes.
Signed-off-by: Shalom Toledo <shalomt@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
---
drivers/net/ethernet/mellanox/mlxsw/core.c | 13 ++++++
drivers/net/ethernet/mellanox/mlxsw/core.h | 2 +
.../net/ethernet/mellanox/mlxsw/spectrum.c | 45 +++++++++++++++++++
3 files changed, 60 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index b2e1b83525db..281aeb1c2386 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -1036,6 +1036,12 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
goto err_devlink_register;
}
+ if (mlxsw_driver->params_register && !reload) {
+ err = mlxsw_driver->params_register(mlxsw_core);
+ if (err)
+ goto err_register_params;
+ }
+
err = mlxsw_hwmon_init(mlxsw_core, mlxsw_bus_info, &mlxsw_core->hwmon);
if (err)
goto err_hwmon_init;
@@ -1058,6 +1064,9 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
err_thermal_init:
mlxsw_hwmon_fini(mlxsw_core->hwmon);
err_hwmon_init:
+ if (mlxsw_driver->params_unregister && !reload)
+ mlxsw_driver->params_unregister(mlxsw_core);
+err_register_params:
if (!reload)
devlink_unregister(devlink);
err_devlink_register:
@@ -1121,6 +1130,8 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core,
mlxsw_core->driver->fini(mlxsw_core);
mlxsw_thermal_fini(mlxsw_core->thermal);
mlxsw_hwmon_fini(mlxsw_core->hwmon);
+ if (mlxsw_core->driver->params_unregister && !reload)
+ mlxsw_core->driver->params_unregister(mlxsw_core);
if (!reload)
devlink_unregister(devlink);
mlxsw_emad_fini(mlxsw_core);
@@ -1133,6 +1144,8 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core,
return;
reload_fail_deinit:
+ if (mlxsw_core->driver->params_unregister)
+ mlxsw_core->driver->params_unregister(mlxsw_core);
devlink_unregister(devlink);
devlink_resources_unregister(devlink, NULL);
devlink_free(devlink);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h
index c35be477856f..d811be8989b0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.h
@@ -282,6 +282,8 @@ struct mlxsw_driver {
const struct mlxsw_config_profile *profile,
u64 *p_single_size, u64 *p_double_size,
u64 *p_linear_size);
+ int (*params_register)(struct mlxsw_core *mlxsw_core);
+ void (*params_unregister)(struct mlxsw_core *mlxsw_core);
u8 txhdr_len;
const struct mlxsw_config_profile *profile;
bool res_query_enabled;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 9bec940330a4..ab1ca8c1d6df 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -318,6 +318,7 @@ static int mlxsw_sp_fw_rev_validate(struct mlxsw_sp *mlxsw_sp)
const struct mlxsw_fw_rev *rev = &mlxsw_sp->bus_info->fw_rev;
const struct mlxsw_fw_rev *req_rev = mlxsw_sp->req_rev;
const char *fw_filename = mlxsw_sp->fw_filename;
+ union devlink_param_value value;
const struct firmware *firmware;
int err;
@@ -325,6 +326,15 @@ static int mlxsw_sp_fw_rev_validate(struct mlxsw_sp *mlxsw_sp)
if (!req_rev || !fw_filename)
return 0;
+ /* Don't check if devlink fw_version_check param is false */
+ err = devlink_param_driverinit_value_get(priv_to_devlink(mlxsw_sp->core),
+ DEVLINK_PARAM_GENERIC_ID_FW_VERSION_CHECK,
+ &value);
+ if (err)
+ return err;
+ if (!value.vbool)
+ return 0;
+
/* Validate driver & FW are compatible */
if (rev->major != req_rev->major) {
WARN(1, "Mismatch in major FW version [%d:%d] is never expected; Please contact support\n",
@@ -4171,6 +4181,37 @@ static int mlxsw_sp_kvd_sizes_get(struct mlxsw_core *mlxsw_core,
return 0;
}
+static const struct devlink_param mlxsw_sp_devlink_params[] = {
+ DEVLINK_PARAM_GENERIC(FW_VERSION_CHECK,
+ BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+ NULL, NULL, NULL),
+};
+
+static int mlxsw_sp_params_register(struct mlxsw_core *mlxsw_core)
+{
+ struct devlink *devlink = priv_to_devlink(mlxsw_core);
+ union devlink_param_value value;
+ int err;
+
+ err = devlink_params_register(devlink, mlxsw_sp_devlink_params,
+ ARRAY_SIZE(mlxsw_sp_devlink_params));
+ if (err)
+ return err;
+
+ value.vbool = true;
+ devlink_param_driverinit_value_set(devlink,
+ DEVLINK_PARAM_GENERIC_ID_FW_VERSION_CHECK,
+ value);
+ return 0;
+}
+
+static void mlxsw_sp_params_unregister(struct mlxsw_core *mlxsw_core)
+{
+ devlink_params_unregister(priv_to_devlink(mlxsw_core),
+ mlxsw_sp_devlink_params,
+ ARRAY_SIZE(mlxsw_sp_devlink_params));
+}
+
static struct mlxsw_driver mlxsw_sp1_driver = {
.kind = mlxsw_sp1_driver_name,
.priv_size = sizeof(struct mlxsw_sp),
@@ -4192,6 +4233,8 @@ static struct mlxsw_driver mlxsw_sp1_driver = {
.txhdr_construct = mlxsw_sp_txhdr_construct,
.resources_register = mlxsw_sp1_resources_register,
.kvd_sizes_get = mlxsw_sp_kvd_sizes_get,
+ .params_register = mlxsw_sp_params_register,
+ .params_unregister = mlxsw_sp_params_unregister,
.txhdr_len = MLXSW_TXHDR_LEN,
.profile = &mlxsw_sp1_config_profile,
.res_query_enabled = true,
@@ -4217,6 +4260,8 @@ static struct mlxsw_driver mlxsw_sp2_driver = {
.sb_occ_tc_port_bind_get = mlxsw_sp_sb_occ_tc_port_bind_get,
.txhdr_construct = mlxsw_sp_txhdr_construct,
.resources_register = mlxsw_sp2_resources_register,
+ .params_register = mlxsw_sp_params_register,
+ .params_unregister = mlxsw_sp_params_unregister,
.txhdr_len = MLXSW_TXHDR_LEN,
.profile = &mlxsw_sp2_config_profile,
.res_query_enabled = true,
--
2.19.1
^ permalink raw reply related
* bpf-next is OPEN
From: Daniel Borkmann @ 2018-11-06 19:39 UTC (permalink / raw)
To: netdev; +Cc: ast
Merge window is over so bpf-next is open again!
Thanks,
Daniel
^ permalink raw reply
* Re: [PATCH net-next 1/3] devlink: Add fw_version_check generic parameter
From: Jakub Kicinski @ 2018-11-06 20:19 UTC (permalink / raw)
To: Ido Schimmel
Cc: netdev@vger.kernel.org, davem@davemloft.net, Jiri Pirko,
Shalom Toledo, Moshe Shemesh, dsahern@gmail.com, andrew@lunn.ch,
f.fainelli@gmail.com, mlxsw
In-Reply-To: <20181106200314.29918-2-idosch@mellanox.com>
On Tue, 6 Nov 2018 20:05:00 +0000, Ido Schimmel wrote:
> From: Shalom Toledo <shalomt@mellanox.com>
>
> Many drivers checking the device's firmware version during the
> initialization flow and flashing a compatible version if the current
> version is not.
>
> fw_version_check gives the ability to skip this check which allows to run
> the device with a different firmware version than required by the driver
> for testing and/or debugging purposes.
>
> Signed-off-by: Shalom Toledo <shalomt@mellanox.com>
> Reviewed-by: Jiri Pirko <jiri@mellanox.com>
> Signed-off-by: Ido Schimmel <idosch@mellanox.com>
The documentation is missing, so it's hard to comment on the definition
of the parameter... We have a FW loading policy for NFP, too, so it'd
be good to see if we can find a common ground.
^ permalink raw reply
* [PATCH bpf-next 1/2] bpf: add perf-event notificaton support for sock_ops
From: Sowmini Varadhan @ 2018-11-06 20:28 UTC (permalink / raw)
To: sowmini.varadhan, daniel, netdev, davem
In-Reply-To: <cover.1541535172.git.sowmini.varadhan@oracle.com>
This patch allows eBPF programs that use sock_ops to send
perf-based event notifications using bpf_perf_event_output()
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
---
net/core/filter.c | 19 +++++++++++++++++++
1 files changed, 19 insertions(+), 0 deletions(-)
diff --git a/net/core/filter.c b/net/core/filter.c
index e521c5e..23464a3 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4048,6 +4048,23 @@ static unsigned long bpf_xdp_copy(void *dst_buff, const void *src_buff,
return ret;
}
+BPF_CALL_5(bpf_sock_opts_event_output, struct bpf_sock_ops *, skops,
+ struct bpf_map *, map, u64, flags, void *, data, u64, size)
+{
+ return bpf_event_output(map, flags, data, size, NULL, 0, NULL);
+}
+
+static const struct bpf_func_proto bpf_sock_ops_event_output_proto = {
+ .func = bpf_sock_opts_event_output,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_CONST_MAP_PTR,
+ .arg3_type = ARG_ANYTHING,
+ .arg4_type = ARG_PTR_TO_MEM,
+ .arg5_type = ARG_CONST_SIZE_OR_ZERO,
+};
+
static const struct bpf_func_proto bpf_setsockopt_proto = {
.func = bpf_setsockopt,
.gpl_only = false,
@@ -5226,6 +5243,8 @@ bool bpf_helper_changes_pkt_data(void *func)
sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
switch (func_id) {
+ case BPF_FUNC_perf_event_output:
+ return &bpf_sock_ops_event_output_proto;
case BPF_FUNC_setsockopt:
return &bpf_setsockopt_proto;
case BPF_FUNC_getsockopt:
--
1.7.1
^ permalink raw reply related
* [PATCH bpf-next 0/2] TCP-BPF event notification support
From: Sowmini Varadhan @ 2018-11-06 20:28 UTC (permalink / raw)
To: sowmini.varadhan, daniel, netdev, davem
This patchset uses eBPF perf-event based notification mechanism to solve
the problem described in
https://marc.info/?l=linux-netdev&m=154022219423571&w=2.
Thanks to Daniel Borkmann for feedback/input.
The problem statement is
We would like to monitor some subset of TCP sockets in user-space,
(the monitoring application would define 4-tuples it wants to monitor)
using TCP_INFO stats to analyze reported problems. The idea is to
use those stats to see where the bottlenecks are likely to be ("is it
application-limited?" or "is there evidence of BufferBloat in the
path?" etc)
Today we can do this by periodically polling for tcp_info, but this
could be made more efficient if the kernel would asynchronously
notify the application via tcp_info when some "interesting"
thresholds (e.g., "RTT variance > X", or "total_retrans > Y" etc)
are reached. And to make this effective, it is better if
we could apply the threshold check *before* constructing the
tcp_info netlink notification, so that we don't waste resources
constructing notifications that will be discarded by the filter.
This patchset solves the problem by adding perf-event based notification
support for sock_ops (Patch1). The eBPF kernel module can thus
be designed to apply any desired filters to the bpf_sock_ops and
trigger a perf-event notification based on the verdict from the filter.
The uspace component can use these perf-event notifications to either
read any state managed by the eBPF kernel module, or issue a TCP_INFO
netlink call if desired.
Patch 2 provides a simple example that shows how to use this infra
(and also provides a test case for it)
Sowmini Varadhan (2):
bpf: add perf-event notificaton support for sock_ops
selftests/bpf: add a test case for sock_ops perf-event notification
net/core/filter.c | 19 ++
tools/testing/selftests/bpf/Makefile | 4 +-
tools/testing/selftests/bpf/perf-sys.h | 74 ++++++++
tools/testing/selftests/bpf/test_tcpnotify.h | 19 ++
tools/testing/selftests/bpf/test_tcpnotify_kern.c | 95 +++++++++++
tools/testing/selftests/bpf/test_tcpnotify_user.c | 186 +++++++++++++++++++++
6 files changed, 396 insertions(+), 1 deletions(-)
create mode 100644 tools/testing/selftests/bpf/perf-sys.h
create mode 100644 tools/testing/selftests/bpf/test_tcpnotify.h
create mode 100644 tools/testing/selftests/bpf/test_tcpnotify_kern.c
create mode 100644 tools/testing/selftests/bpf/test_tcpnotify_user.c
^ permalink raw reply
* [PATCH bpf-next 2/2] selftests/bpf: add a test case for sock_ops perf-event notification
From: Sowmini Varadhan @ 2018-11-06 20:28 UTC (permalink / raw)
To: sowmini.varadhan, daniel, netdev, davem
In-Reply-To: <cover.1541535172.git.sowmini.varadhan@oracle.com>
This patch provides a tcp_bpf based eBPF sample. The test
- ncat(1) as the TCP client program to connect() to a port
with the intention of triggerring SYN retransmissions: we
first install an iptables DROP rule to make sure ncat SYNs are
resent (instead of aborting instantly after a TCP RST)
- has a bpf kernel module that sends a perf-event notification for
each TCP retransmit, and also tracks the number of such notifications
sent in the global_map
The test passes when the number of event notifications intercepted
in user-space matches the value in the global_map.
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
---
tools/testing/selftests/bpf/Makefile | 4 +-
tools/testing/selftests/bpf/perf-sys.h | 74 ++++++++
tools/testing/selftests/bpf/test_tcpnotify.h | 19 ++
tools/testing/selftests/bpf/test_tcpnotify_kern.c | 95 +++++++++++
tools/testing/selftests/bpf/test_tcpnotify_user.c | 186 +++++++++++++++++++++
5 files changed, 377 insertions(+), 1 deletions(-)
create mode 100644 tools/testing/selftests/bpf/perf-sys.h
create mode 100644 tools/testing/selftests/bpf/test_tcpnotify.h
create mode 100644 tools/testing/selftests/bpf/test_tcpnotify_kern.c
create mode 100644 tools/testing/selftests/bpf/test_tcpnotify_user.c
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index e39dfb4..6c94048 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -24,12 +24,13 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test
test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
test_sock test_btf test_sockmap test_lirc_mode2_user get_cgroup_id_user \
test_socket_cookie test_cgroup_storage test_select_reuseport test_section_names \
- test_netcnt
+ test_netcnt test_tcpnotify_user
TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \
sockmap_verdict_prog.o dev_cgroup.o sample_ret0.o test_tracepoint.o \
test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o \
+ test_tcpnotify_kern.o \
sample_map_ret0.o test_tcpbpf_kern.o test_stacktrace_build_id.o \
sockmap_tcp_msg_prog.o connect4_prog.o connect6_prog.o test_adjust_tail.o \
test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o test_tunnel_kern.o \
@@ -74,6 +75,7 @@ $(OUTPUT)/test_sock_addr: cgroup_helpers.c
$(OUTPUT)/test_socket_cookie: cgroup_helpers.c
$(OUTPUT)/test_sockmap: cgroup_helpers.c
$(OUTPUT)/test_tcpbpf_user: cgroup_helpers.c
+$(OUTPUT)/test_tcpnotify_user: cgroup_helpers.c trace_helpers.c
$(OUTPUT)/test_progs: trace_helpers.c
$(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c
$(OUTPUT)/test_cgroup_storage: cgroup_helpers.c
diff --git a/tools/testing/selftests/bpf/perf-sys.h b/tools/testing/selftests/bpf/perf-sys.h
new file mode 100644
index 0000000..3eb7a39
--- /dev/null
+++ b/tools/testing/selftests/bpf/perf-sys.h
@@ -0,0 +1,74 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _PERF_SYS_H
+#define _PERF_SYS_H
+
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/syscall.h>
+#include <linux/types.h>
+#include <linux/compiler.h>
+#include <linux/perf_event.h>
+#include <asm/barrier.h>
+
+#ifdef __powerpc__
+#define CPUINFO_PROC {"cpu"}
+#endif
+
+#ifdef __s390__
+#define CPUINFO_PROC {"vendor_id"}
+#endif
+
+#ifdef __sh__
+#define CPUINFO_PROC {"cpu type"}
+#endif
+
+#ifdef __hppa__
+#define CPUINFO_PROC {"cpu"}
+#endif
+
+#ifdef __sparc__
+#define CPUINFO_PROC {"cpu"}
+#endif
+
+#ifdef __alpha__
+#define CPUINFO_PROC {"cpu model"}
+#endif
+
+#ifdef __arm__
+#define CPUINFO_PROC {"model name", "Processor"}
+#endif
+
+#ifdef __mips__
+#define CPUINFO_PROC {"cpu model"}
+#endif
+
+#ifdef __arc__
+#define CPUINFO_PROC {"Processor"}
+#endif
+
+#ifdef __xtensa__
+#define CPUINFO_PROC {"core ID"}
+#endif
+
+#ifndef CPUINFO_PROC
+#define CPUINFO_PROC { "model name", }
+#endif
+
+static inline int
+sys_perf_event_open(struct perf_event_attr *attr,
+ pid_t pid, int cpu, int group_fd,
+ unsigned long flags)
+{
+ int fd;
+
+ fd = syscall(__NR_perf_event_open, attr, pid, cpu,
+ group_fd, flags);
+
+#ifdef HAVE_ATTR_TEST
+ if (unlikely(test_attr__enabled))
+ test_attr__open(attr, pid, cpu, fd, group_fd, flags);
+#endif
+ return fd;
+}
+
+#endif /* _PERF_SYS_H */
diff --git a/tools/testing/selftests/bpf/test_tcpnotify.h b/tools/testing/selftests/bpf/test_tcpnotify.h
new file mode 100644
index 0000000..8b6cea0
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tcpnotify.h
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifndef _TEST_TCPBPF_H
+#define _TEST_TCPBPF_H
+
+struct tcpnotify_globals {
+ __u32 total_retrans;
+ __u32 ncalls;
+};
+
+struct tcp_notifier {
+ __u8 type;
+ __u8 subtype;
+ __u8 source;
+ __u8 hash;
+};
+
+#define TESTPORT 12877
+#endif
diff --git a/tools/testing/selftests/bpf/test_tcpnotify_kern.c b/tools/testing/selftests/bpf/test_tcpnotify_kern.c
new file mode 100644
index 0000000..edbca20
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tcpnotify_kern.c
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stddef.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/tcp.h>
+#include <netinet/in.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+#include "test_tcpnotify.h"
+
+struct bpf_map_def SEC("maps") global_map = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(struct tcpnotify_globals),
+ .max_entries = 4,
+};
+
+struct bpf_map_def SEC("maps") perf_event_map = {
+ .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+ .key_size = sizeof(int),
+ .value_size = sizeof(__u32),
+ .max_entries = 2,
+};
+
+int _version SEC("version") = 1;
+
+SEC("sockops")
+int bpf_testcb(struct bpf_sock_ops *skops)
+{
+ int rv = -1;
+ int op;
+
+ op = (int) skops->op;
+
+ if (bpf_ntohl(skops->remote_port) != TESTPORT) {
+ skops->reply = -1;
+ return 0;
+ }
+
+ switch (op) {
+ case BPF_SOCK_OPS_TIMEOUT_INIT:
+ case BPF_SOCK_OPS_RWND_INIT:
+ case BPF_SOCK_OPS_NEEDS_ECN:
+ case BPF_SOCK_OPS_BASE_RTT:
+ case BPF_SOCK_OPS_RTO_CB:
+ rv = 1;
+ break;
+
+ case BPF_SOCK_OPS_TCP_CONNECT_CB:
+ case BPF_SOCK_OPS_TCP_LISTEN_CB:
+ case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
+ case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+ bpf_sock_ops_cb_flags_set(skops, (BPF_SOCK_OPS_RETRANS_CB_FLAG|
+ BPF_SOCK_OPS_RTO_CB_FLAG));
+ rv = 1;
+ break;
+ case BPF_SOCK_OPS_RETRANS_CB: {
+ __u32 key = 0;
+ struct tcpnotify_globals g, *gp;
+ struct tcp_notifier msg = {
+ .type = 0xde,
+ .subtype = 0xad,
+ .source = 0xbe,
+ .hash = 0xef,
+ };
+
+ rv = 1;
+
+ /* Update results */
+ gp = bpf_map_lookup_elem(&global_map, &key);
+ if (!gp)
+ break;
+ g = *gp;
+ g.total_retrans = skops->total_retrans;
+ g.ncalls++;
+ bpf_map_update_elem(&global_map, &key, &g,
+ BPF_ANY);
+ bpf_perf_event_output(skops, &perf_event_map,
+ BPF_F_CURRENT_CPU,
+ &msg, sizeof(msg));
+ }
+ break;
+ default:
+ rv = -1;
+ }
+ skops->reply = rv;
+ return 1;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_tcpnotify_user.c b/tools/testing/selftests/bpf/test_tcpnotify_user.c
new file mode 100644
index 0000000..8f88cb9
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tcpnotify_user.c
@@ -0,0 +1,186 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <pthread.h>
+#include <inttypes.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <asm/types.h>
+#include <errno.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <sys/socket.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include <sys/ioctl.h>
+#include <linux/rtnetlink.h>
+#include <signal.h>
+#include <linux/perf_event.h>
+#include "perf-sys.h"
+
+#include "bpf_rlimit.h"
+#include "bpf_util.h"
+#include "cgroup_helpers.h"
+
+#include "test_tcpnotify.h"
+#include "trace_helpers.h"
+
+#define SOCKET_BUFFER_SIZE (getpagesize() < 8192L ? getpagesize() : 8192L)
+
+pthread_t tid;
+int rx_callbacks;
+
+static int dummyfn(void *data, int size)
+{
+ struct tcp_notifier *t = data;
+
+ if (t->type != 0xde || t->subtype != 0xad ||
+ t->source != 0xbe || t->hash != 0xef)
+ return 1;
+ rx_callbacks++;
+ return 0;
+}
+
+void tcp_notifier_poller(int fd)
+{
+ while (1)
+ perf_event_poller(fd, dummyfn);
+}
+
+static void *poller_thread(void *arg)
+{
+ int fd = *(int *)arg;
+
+ tcp_notifier_poller(fd);
+ return arg;
+}
+
+int verify_result(const struct tcpnotify_globals *result)
+{
+ return (result->ncalls > 0 && result->ncalls == rx_callbacks ? 0 : 1);
+}
+
+static int bpf_find_map(const char *test, struct bpf_object *obj,
+ const char *name)
+{
+ struct bpf_map *map;
+
+ map = bpf_object__find_map_by_name(obj, name);
+ if (!map) {
+ printf("%s:FAIL:map '%s' not found\n", test, name);
+ return -1;
+ }
+ return bpf_map__fd(map);
+}
+
+static int setup_bpf_perf_event(int mapfd)
+{
+ struct perf_event_attr attr = {
+ .sample_type = PERF_SAMPLE_RAW,
+ .type = PERF_TYPE_SOFTWARE,
+ .config = PERF_COUNT_SW_BPF_OUTPUT,
+ };
+ int key = 0;
+ int pmu_fd;
+
+ pmu_fd = sys_perf_event_open(&attr, -1, 0, -1, 0);
+ if (pmu_fd < 0)
+ return pmu_fd;
+ bpf_map_update_elem(mapfd, &key, &pmu_fd, BPF_ANY);
+
+ ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
+ return pmu_fd;
+}
+
+int main(int argc, char **argv)
+{
+ const char *file = "test_tcpnotify_kern.o";
+ int prog_fd, map_fd, perf_event_fd;
+ struct tcpnotify_globals g = {0};
+ const char *cg_path = "/foo";
+ int error = EXIT_FAILURE;
+ struct bpf_object *obj;
+ int cg_fd = -1;
+ __u32 key = 0;
+ int rv;
+ char test_script[80];
+ int pmu_fd;
+ cpu_set_t cpuset;
+
+ CPU_ZERO(&cpuset);
+ CPU_SET(0, &cpuset);
+ pthread_setaffinity_np(pthread_self(), sizeof(cpu_set_t), &cpuset);
+
+ if (setup_cgroup_environment())
+ goto err;
+
+ cg_fd = create_and_get_cgroup(cg_path);
+ if (!cg_fd)
+ goto err;
+
+ if (join_cgroup(cg_path))
+ goto err;
+
+ if (bpf_prog_load(file, BPF_PROG_TYPE_SOCK_OPS, &obj, &prog_fd)) {
+ printf("FAILED: load_bpf_file failed for: %s\n", file);
+ goto err;
+ }
+
+ rv = bpf_prog_attach(prog_fd, cg_fd, BPF_CGROUP_SOCK_OPS, 0);
+ if (rv) {
+ printf("FAILED: bpf_prog_attach: %d (%s)\n",
+ error, strerror(errno));
+ goto err;
+ }
+
+ perf_event_fd = bpf_find_map(__func__, obj, "perf_event_map");
+ if (perf_event_fd < 0)
+ goto err;
+
+ map_fd = bpf_find_map(__func__, obj, "global_map");
+ if (map_fd < 0)
+ goto err;
+
+ pmu_fd = setup_bpf_perf_event(perf_event_fd);
+ if (pmu_fd < 0 || perf_event_mmap(pmu_fd) < 0)
+ goto err;
+
+ pthread_create(&tid, NULL, poller_thread, (void *)&pmu_fd);
+
+ sprintf(test_script,
+ "/usr/sbin/iptables -A INPUT -p tcp --dport %d -j DROP",
+ TESTPORT);
+ system(test_script);
+
+ sprintf(test_script,
+ "/usr/bin/nc 127.0.0.1 %d < /etc/passwd > /dev/null 2>&1 ",
+ TESTPORT);
+ system(test_script);
+
+ sprintf(test_script,
+ "/usr/sbin/iptables -D INPUT -p tcp --dport %d -j DROP",
+ TESTPORT);
+ system(test_script);
+
+ rv = bpf_map_lookup_elem(map_fd, &key, &g);
+ if (rv != 0) {
+ printf("FAILED: bpf_map_lookup_elem returns %d\n", rv);
+ goto err;
+ }
+
+ sleep(10);
+
+ if (verify_result(&g)) {
+ printf("FAILED: Wrong stats Expected %d calls, got %d\n",
+ g.ncalls, rx_callbacks);
+ goto err;
+ }
+
+ printf("PASSED!\n");
+ error = 0;
+err:
+ bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS);
+ close(cg_fd);
+ cleanup_cgroup_environment();
+ return error;
+}
--
1.7.1
^ permalink raw reply related
* Re: [PATCH net-next 1/3] devlink: Add fw_version_check generic parameter
From: Ido Schimmel @ 2018-11-06 20:37 UTC (permalink / raw)
To: Jakub Kicinski
Cc: Ido Schimmel, netdev@vger.kernel.org, davem@davemloft.net,
Jiri Pirko, Shalom Toledo, Moshe Shemesh, dsahern@gmail.com,
andrew@lunn.ch, f.fainelli@gmail.com, mlxsw
In-Reply-To: <20181106121913.036b8c4d@cakuba.netronome.com>
On Tue, Nov 06, 2018 at 12:19:13PM -0800, Jakub Kicinski wrote:
> On Tue, 6 Nov 2018 20:05:00 +0000, Ido Schimmel wrote:
> > From: Shalom Toledo <shalomt@mellanox.com>
> >
> > Many drivers checking the device's firmware version during the
> > initialization flow and flashing a compatible version if the current
> > version is not.
> >
> > fw_version_check gives the ability to skip this check which allows to run
> > the device with a different firmware version than required by the driver
> > for testing and/or debugging purposes.
> >
> > Signed-off-by: Shalom Toledo <shalomt@mellanox.com>
> > Reviewed-by: Jiri Pirko <jiri@mellanox.com>
> > Signed-off-by: Ido Schimmel <idosch@mellanox.com>
>
> The documentation is missing, so it's hard to comment on the definition
> of the parameter...
I assume you mean Documentation/networking/devlink-params.txt ?
> We have a FW loading policy for NFP, too, so it'd be good to see if we
> can find a common ground.
If the parameter is set, then device runs with whatever firmware version
was last flashed (via ethtool, for example). Otherwise, the driver will
flash a version according to its policy. In mlxsw, it is a specific
version.
Will that work for you?
^ permalink raw reply
* [PATCH net-next 0/3] net: More extack messages
From: David Ahern @ 2018-11-06 20:51 UTC (permalink / raw)
To: netdev; +Cc: David Ahern
From: David Ahern <dsahern@gmail.com>
Add more extack messages for several link create errors (e.g., invalid
number of queues, unknown link kind) and invalid metrics argument.
David Ahern (3):
net: Add extack argument to rtnl_create_link
net: Add extack argument to ip_fib_metrics_init
rtnetlink: Add more extack messages to rtnl_newlink
drivers/net/can/vxcan.c | 2 +-
drivers/net/geneve.c | 2 +-
drivers/net/veth.c | 2 +-
drivers/net/vxlan.c | 2 +-
include/net/ip.h | 3 ++-
include/net/rtnetlink.h | 3 ++-
net/core/rtnetlink.c | 24 ++++++++++++++++--------
net/ipv4/fib_semantics.c | 2 +-
net/ipv4/ip_gre.c | 2 +-
net/ipv4/metrics.c | 26 +++++++++++++++++++-------
net/ipv6/route.c | 5 +++--
11 files changed, 48 insertions(+), 25 deletions(-)
--
2.11.0
^ permalink raw reply
* [PATCH net-next 3/3] rtnetlink: Add more extack messages to rtnl_newlink
From: David Ahern @ 2018-11-06 20:51 UTC (permalink / raw)
To: netdev; +Cc: David Ahern
In-Reply-To: <20181106205116.7718-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Add extack arg to the nla_parse_nested calls in rtnl_newlink, and
add messages for unknown device type and link network namespace id.
In particular, it improves the failure message when the wrong link
type is used. From
$ ip li add bond1 type bonding
RTNETLINK answers: Operation not supported
to
$ ip li add bond1 type bonding
Error: Unknown device type.
(The module name is bonding but the link type is bond.)
Signed-off-by: David Ahern <dsahern@gmail.com>
---
net/core/rtnetlink.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index f787b7640d49..86f2d9cbdae3 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3054,7 +3054,7 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
if (ops->maxtype && linkinfo[IFLA_INFO_DATA]) {
err = nla_parse_nested(attr, ops->maxtype,
linkinfo[IFLA_INFO_DATA],
- ops->policy, NULL);
+ ops->policy, extack);
if (err < 0)
return err;
data = attr;
@@ -3076,7 +3076,7 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
m_ops->slave_maxtype,
linkinfo[IFLA_INFO_SLAVE_DATA],
m_ops->slave_policy,
- NULL);
+ extack);
if (err < 0)
return err;
slave_data = slave_attr;
@@ -3140,6 +3140,7 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
goto replay;
}
#endif
+ NL_SET_ERR_MSG(extack, "Unknown device type");
return -EOPNOTSUPP;
}
@@ -3160,6 +3161,7 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
link_net = get_net_ns_by_id(dest_net, id);
if (!link_net) {
+ NL_SET_ERR_MSG(extack, "Unknown network namespace id");
err = -EINVAL;
goto out;
}
--
2.11.0
^ permalink raw reply related
* [PATCH net-next 1/3] net: Add extack argument to rtnl_create_link
From: David Ahern @ 2018-11-06 20:51 UTC (permalink / raw)
To: netdev; +Cc: David Ahern
In-Reply-To: <20181106205116.7718-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Add extack arg to rtnl_create_link and add messages for invalid
number of Tx or Rx queues.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
drivers/net/can/vxcan.c | 2 +-
drivers/net/geneve.c | 2 +-
drivers/net/veth.c | 2 +-
drivers/net/vxlan.c | 2 +-
include/net/rtnetlink.h | 3 ++-
net/core/rtnetlink.c | 18 ++++++++++++------
net/ipv4/ip_gre.c | 2 +-
7 files changed, 19 insertions(+), 12 deletions(-)
diff --git a/drivers/net/can/vxcan.c b/drivers/net/can/vxcan.c
index ed6828821fbd..80af658e530d 100644
--- a/drivers/net/can/vxcan.c
+++ b/drivers/net/can/vxcan.c
@@ -207,7 +207,7 @@ static int vxcan_newlink(struct net *net, struct net_device *dev,
return PTR_ERR(peer_net);
peer = rtnl_create_link(peer_net, ifname, name_assign_type,
- &vxcan_link_ops, tbp);
+ &vxcan_link_ops, tbp, extack);
if (IS_ERR(peer)) {
put_net(peer_net);
return PTR_ERR(peer);
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index a0cd1c41cf5f..fbfc13d81f66 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1666,7 +1666,7 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
memset(tb, 0, sizeof(tb));
dev = rtnl_create_link(net, name, name_assign_type,
- &geneve_link_ops, tb);
+ &geneve_link_ops, tb, NULL);
if (IS_ERR(dev))
return dev;
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 890fa5b905e2..f412ea1cef18 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -1253,7 +1253,7 @@ static int veth_newlink(struct net *src_net, struct net_device *dev,
return PTR_ERR(net);
peer = rtnl_create_link(net, ifname, name_assign_type,
- &veth_link_ops, tbp);
+ &veth_link_ops, tbp, extack);
if (IS_ERR(peer)) {
put_net(net);
return PTR_ERR(peer);
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 297cdeaef479..ae969f806d56 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -3749,7 +3749,7 @@ struct net_device *vxlan_dev_create(struct net *net, const char *name,
memset(&tb, 0, sizeof(tb));
dev = rtnl_create_link(net, name, name_assign_type,
- &vxlan_link_ops, tb);
+ &vxlan_link_ops, tb, NULL);
if (IS_ERR(dev))
return dev;
diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
index cf26e5aacac4..e2091bb2b3a8 100644
--- a/include/net/rtnetlink.h
+++ b/include/net/rtnetlink.h
@@ -159,7 +159,8 @@ struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]);
struct net_device *rtnl_create_link(struct net *net, const char *ifname,
unsigned char name_assign_type,
const struct rtnl_link_ops *ops,
- struct nlattr *tb[]);
+ struct nlattr *tb[],
+ struct netlink_ext_ack *extack);
int rtnl_delete_link(struct net_device *dev);
int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 33d9227a8b80..f787b7640d49 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2885,9 +2885,11 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm)
}
EXPORT_SYMBOL(rtnl_configure_link);
-struct net_device *rtnl_create_link(struct net *net,
- const char *ifname, unsigned char name_assign_type,
- const struct rtnl_link_ops *ops, struct nlattr *tb[])
+struct net_device *rtnl_create_link(struct net *net, const char *ifname,
+ unsigned char name_assign_type,
+ const struct rtnl_link_ops *ops,
+ struct nlattr *tb[],
+ struct netlink_ext_ack *extack)
{
struct net_device *dev;
unsigned int num_tx_queues = 1;
@@ -2903,11 +2905,15 @@ struct net_device *rtnl_create_link(struct net *net,
else if (ops->get_num_rx_queues)
num_rx_queues = ops->get_num_rx_queues();
- if (num_tx_queues < 1 || num_tx_queues > 4096)
+ if (num_tx_queues < 1 || num_tx_queues > 4096) {
+ NL_SET_ERR_MSG(extack, "Invalid number of transmit queues");
return ERR_PTR(-EINVAL);
+ }
- if (num_rx_queues < 1 || num_rx_queues > 4096)
+ if (num_rx_queues < 1 || num_rx_queues > 4096) {
+ NL_SET_ERR_MSG(extack, "Invalid number of receive queues");
return ERR_PTR(-EINVAL);
+ }
dev = alloc_netdev_mqs(ops->priv_size, ifname, name_assign_type,
ops->setup, num_tx_queues, num_rx_queues);
@@ -3163,7 +3169,7 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
}
dev = rtnl_create_link(link_net ? : dest_net, ifname,
- name_assign_type, ops, tb);
+ name_assign_type, ops, tb, extack);
if (IS_ERR(dev)) {
err = PTR_ERR(dev);
goto out;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 38befe829caf..2c67af644e64 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1601,7 +1601,7 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
memset(&tb, 0, sizeof(tb));
dev = rtnl_create_link(net, name, name_assign_type,
- &ipgre_tap_ops, tb);
+ &ipgre_tap_ops, tb, NULL);
if (IS_ERR(dev))
return dev;
--
2.11.0
^ permalink raw reply related
* [PATCH net-next 2/3] net: Add extack argument to ip_fib_metrics_init
From: David Ahern @ 2018-11-06 20:51 UTC (permalink / raw)
To: netdev; +Cc: David Ahern
In-Reply-To: <20181106205116.7718-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Add extack argument to ip_fib_metrics_init and add messages for invalid
metrics.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/ip.h | 3 ++-
net/ipv4/fib_semantics.c | 2 +-
net/ipv4/metrics.c | 26 +++++++++++++++++++-------
net/ipv6/route.c | 5 +++--
4 files changed, 25 insertions(+), 11 deletions(-)
diff --git a/include/net/ip.h b/include/net/ip.h
index 72593e171d14..462182f78236 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -421,7 +421,8 @@ static inline unsigned int ip_skb_dst_mtu(struct sock *sk,
}
struct dst_metrics *ip_fib_metrics_init(struct net *net, struct nlattr *fc_mx,
- int fc_mx_len);
+ int fc_mx_len,
+ struct netlink_ext_ack *extack);
static inline void ip_fib_metrics_put(struct dst_metrics *fib_metrics)
{
if (fib_metrics != &dst_default_metrics &&
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index b5c3937ca6ec..5022bc63863a 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1076,7 +1076,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
if (!fi)
goto failure;
fi->fib_metrics = ip_fib_metrics_init(fi->fib_net, cfg->fc_mx,
- cfg->fc_mx_len);
+ cfg->fc_mx_len, extack);
if (unlikely(IS_ERR(fi->fib_metrics))) {
err = PTR_ERR(fi->fib_metrics);
kfree(fi);
diff --git a/net/ipv4/metrics.c b/net/ipv4/metrics.c
index 6d218f5a2e71..ca9a5fefdefa 100644
--- a/net/ipv4/metrics.c
+++ b/net/ipv4/metrics.c
@@ -6,7 +6,8 @@
#include <net/tcp.h>
static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx,
- int fc_mx_len, u32 *metrics)
+ int fc_mx_len, u32 *metrics,
+ struct netlink_ext_ack *extack)
{
bool ecn_ca = false;
struct nlattr *nla;
@@ -21,19 +22,26 @@ static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx,
if (!type)
continue;
- if (type > RTAX_MAX)
+ if (type > RTAX_MAX) {
+ NL_SET_ERR_MSG(extack, "Invalid metric type");
return -EINVAL;
+ }
if (type == RTAX_CC_ALGO) {
char tmp[TCP_CA_NAME_MAX];
nla_strlcpy(tmp, nla, sizeof(tmp));
val = tcp_ca_get_key_by_name(net, tmp, &ecn_ca);
- if (val == TCP_CA_UNSPEC)
+ if (val == TCP_CA_UNSPEC) {
+ NL_SET_ERR_MSG(extack, "Unknown tcp congestion algorithm");
return -EINVAL;
+ }
} else {
- if (nla_len(nla) != sizeof(u32))
+ if (nla_len(nla) != sizeof(u32)) {
+ NL_SET_ERR_MSG_ATTR(extack, nla,
+ "Invalid attribute in metrics");
return -EINVAL;
+ }
val = nla_get_u32(nla);
}
if (type == RTAX_ADVMSS && val > 65535 - 40)
@@ -42,8 +50,10 @@ static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx,
val = 65535 - 15;
if (type == RTAX_HOPLIMIT && val > 255)
val = 255;
- if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK))
+ if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK)) {
+ NL_SET_ERR_MSG(extack, "Unknown flag set in feature mask in metrics attribute");
return -EINVAL;
+ }
metrics[type - 1] = val;
}
@@ -54,7 +64,8 @@ static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx,
}
struct dst_metrics *ip_fib_metrics_init(struct net *net, struct nlattr *fc_mx,
- int fc_mx_len)
+ int fc_mx_len,
+ struct netlink_ext_ack *extack)
{
struct dst_metrics *fib_metrics;
int err;
@@ -66,7 +77,8 @@ struct dst_metrics *ip_fib_metrics_init(struct net *net, struct nlattr *fc_mx,
if (unlikely(!fib_metrics))
return ERR_PTR(-ENOMEM);
- err = ip_metrics_convert(net, fc_mx, fc_mx_len, fib_metrics->metrics);
+ err = ip_metrics_convert(net, fc_mx, fc_mx_len, fib_metrics->metrics,
+ extack);
if (!err) {
refcount_set(&fib_metrics->refcnt, 1);
} else {
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 2a7423c39456..b2447b7c7303 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2975,7 +2975,8 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
if (!rt)
goto out;
- rt->fib6_metrics = ip_fib_metrics_init(net, cfg->fc_mx, cfg->fc_mx_len);
+ rt->fib6_metrics = ip_fib_metrics_init(net, cfg->fc_mx, cfg->fc_mx_len,
+ extack);
if (IS_ERR(rt->fib6_metrics)) {
err = PTR_ERR(rt->fib6_metrics);
/* Do not leave garbage there. */
@@ -3708,7 +3709,7 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net,
if (!f6i)
return ERR_PTR(-ENOMEM);
- f6i->fib6_metrics = ip_fib_metrics_init(net, NULL, 0);
+ f6i->fib6_metrics = ip_fib_metrics_init(net, NULL, 0, NULL);
f6i->dst_nocount = true;
f6i->dst_host = true;
f6i->fib6_protocol = RTPROT_KERNEL;
--
2.11.0
^ permalink raw reply related
* [RFC perf,bpf 0/5] reveal invisible bpf programs
From: Song Liu @ 2018-11-06 20:52 UTC (permalink / raw)
To: netdev, linux-kernel; +Cc: kernel-team, Song Liu, ast, daniel, peterz, acme
This is to follow up Alexei's early effort to show bpf programs
https://www.spinics.net/lists/netdev/msg524232.html
In this version, PERF_RECORD_BPF_EVENT is introduced to send real time BPF
load/unload events to user space. In user space, perf-record is modified
to listen to these events (through a dedicated ring buffer) and generate
detailed information about the program (struct bpf_prog_info_event). Then,
perf-report translates these events into proper symbols.
With this set, perf-report will show bpf program as:
18.49% 0.16% test [kernel.vmlinux] [k] ksys_write
18.01% 0.47% test [kernel.vmlinux] [k] vfs_write
17.02% 0.40% test bpf_prog [k] bpf_prog_F
16.97% 0.10% test [kernel.vmlinux] [k] __vfs_write
16.86% 0.12% test [kernel.vmlinux] [k] comm_write
16.67% 0.39% test [kernel.vmlinux] [k] bpf_probe_read
Note that, the program name is still work in progress, it will be cleaner
with function types in BTF.
Please share your comments on this.
Thanks,
Song
Song Liu (5):
perf, bpf: Introduce PERF_RECORD_BPF_EVENT
perf: sync tools/include/uapi/linux/perf_event.h
perf util: basic handling of PERF_RECORD_BPF_EVENT
perf util: introduce bpf_prog_info_event
perf util: generate bpf_prog_info_event for short living bpf programs
include/linux/perf_event.h | 5 +
include/uapi/linux/perf_event.h | 27 ++-
kernel/bpf/syscall.c | 4 +
kernel/events/core.c | 82 +++++++-
tools/include/uapi/linux/perf_event.h | 27 ++-
tools/perf/builtin-record.c | 55 +++++
tools/perf/builtin-report.c | 2 +
tools/perf/util/Build | 2 +
tools/perf/util/bpf-info.c | 287 ++++++++++++++++++++++++++
tools/perf/util/bpf-info.h | 29 +++
tools/perf/util/event.c | 20 ++
tools/perf/util/event.h | 29 +++
tools/perf/util/evlist.c | 42 +++-
tools/perf/util/evlist.h | 4 +
tools/perf/util/evsel.c | 9 +
tools/perf/util/evsel.h | 3 +
tools/perf/util/machine.c | 10 +
tools/perf/util/machine.h | 2 +
tools/perf/util/session.c | 8 +
tools/perf/util/tool.h | 7 +-
20 files changed, 646 insertions(+), 8 deletions(-)
create mode 100644 tools/perf/util/bpf-info.c
create mode 100644 tools/perf/util/bpf-info.h
^ 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